3356 files changed, 69162 insertions, 47027 deletions

diff --git a/.clang-format b/.clang-format
index f49620f506f1..f3923a1f9858 100644
--- a/.clang-format
+++ b/.clang-format
@@ -78,6 +78,8 @@ ForEachMacros:
   - 'ata_qc_for_each_with_internal'
   - 'ax25_for_each'
   - 'ax25_uid_for_each'
+  - '__bio_for_each_bvec'
+  - 'bio_for_each_bvec'
   - 'bio_for_each_integrity_vec'
   - '__bio_for_each_segment'
   - 'bio_for_each_segment'
@@ -118,10 +120,12 @@ ForEachMacros:
   - 'drm_for_each_legacy_plane'
   - 'drm_for_each_plane'
   - 'drm_for_each_plane_mask'
+  - 'drm_for_each_privobj'
   - 'drm_mm_for_each_hole'
   - 'drm_mm_for_each_node'
   - 'drm_mm_for_each_node_in_range'
   - 'drm_mm_for_each_node_safe'
+  - 'flow_action_for_each'
   - 'for_each_active_drhd_unit'
   - 'for_each_active_iommu'
   - 'for_each_available_child_of_node'
@@ -158,6 +162,9 @@ ForEachMacros:
   - 'for_each_dss_dev'
   - 'for_each_efi_memory_desc'
   - 'for_each_efi_memory_desc_in_map'
+  - 'for_each_element'
+  - 'for_each_element_extid'
+  - 'for_each_element_id'
   - 'for_each_endpoint_of_node'
   - 'for_each_evictable_lru'
   - 'for_each_fib6_node_rt_rcu'
@@ -195,6 +202,7 @@ ForEachMacros:
   - 'for_each_net_rcu'
   - 'for_each_new_connector_in_state'
   - 'for_each_new_crtc_in_state'
+  - 'for_each_new_mst_mgr_in_state'
   - 'for_each_new_plane_in_state'
   - 'for_each_new_private_obj_in_state'
   - 'for_each_node'
@@ -210,8 +218,10 @@ ForEachMacros:
   - 'for_each_of_pci_range'
   - 'for_each_old_connector_in_state'
   - 'for_each_old_crtc_in_state'
+  - 'for_each_old_mst_mgr_in_state'
   - 'for_each_oldnew_connector_in_state'
   - 'for_each_oldnew_crtc_in_state'
+  - 'for_each_oldnew_mst_mgr_in_state'
   - 'for_each_oldnew_plane_in_state'
   - 'for_each_oldnew_plane_in_state_reverse'
   - 'for_each_oldnew_private_obj_in_state'
@@ -243,6 +253,9 @@ ForEachMacros:
   - 'for_each_sg_dma_page'
   - 'for_each_sg_page'
   - 'for_each_sibling_event'
+  - 'for_each_subelement'
+  - 'for_each_subelement_extid'
+  - 'for_each_subelement_id'
   - '__for_each_thread'
   - 'for_each_thread'
   - 'for_each_zone'
@@ -252,6 +265,8 @@ ForEachMacros:
   - 'fwnode_for_each_child_node'
   - 'fwnode_graph_for_each_endpoint'
   - 'gadget_for_each_ep'
+  - 'genradix_for_each'
+  - 'genradix_for_each_from'
   - 'hash_for_each'
   - 'hash_for_each_possible'
   - 'hash_for_each_possible_rcu'
@@ -293,7 +308,11 @@ ForEachMacros:
   - 'key_for_each'
   - 'key_for_each_safe'
   - 'klp_for_each_func'
+  - 'klp_for_each_func_safe'
+  - 'klp_for_each_func_static'
   - 'klp_for_each_object'
+  - 'klp_for_each_object_safe'
+  - 'klp_for_each_object_static'
   - 'kvm_for_each_memslot'
   - 'kvm_for_each_vcpu'
   - 'list_for_each'
@@ -324,6 +343,8 @@ ForEachMacros:
   - 'media_device_for_each_intf'
   - 'media_device_for_each_link'
   - 'media_device_for_each_pad'
+  - 'mp_bvec_for_each_page'
+  - 'mp_bvec_for_each_segment'
   - 'nanddev_io_for_each_page'
   - 'netdev_for_each_lower_dev'
   - 'netdev_for_each_lower_private'
@@ -375,6 +396,7 @@ ForEachMacros:
   - 'rht_for_each_rcu'
   - 'rht_for_each_rcu_continue'
   - '__rq_for_each_bio'
+  - 'rq_for_each_bvec'
   - 'rq_for_each_segment'
   - 'scsi_for_each_prot_sg'
   - 'scsi_for_each_sg'
@@ -410,6 +432,8 @@ ForEachMacros:
   - 'v4l2_m2m_for_each_src_buf_safe'
   - 'virtio_device_for_each_vq'
   - 'xa_for_each'
+  - 'xa_for_each_marked'
+  - 'xa_for_each_start'
   - 'xas_for_each'
   - 'xas_for_each_conflict'
   - 'xas_for_each_marked'
diff --git a/.mailmap b/.mailmap
index 37e1847c7988..ae2bcad06f4b 100644
--- a/.mailmap
+++ b/.mailmap
@@ -156,6 +156,8 @@ Morten Welinder <welinder@darter.rentec.com>
 Morten Welinder <welinder@troll.com>
 Mythri P K <mythripk@ti.com>
 Nguyen Anh Quynh <aquynh@gmail.com>
+Nicolas Pitre <nico@fluxnic.net> <nicolas.pitre@linaro.org>
+Nicolas Pitre <nico@fluxnic.net> <nico@linaro.org>
 Paolo 'Blaisorblade' Giarrusso <blaisorblade@yahoo.it>
 Patrick Mochel <mochel@digitalimplant.org>
 Paul Burton <paul.burton@mips.com> <paul.burton@imgtec.com>
@@ -224,3 +226,5 @@ Yakir Yang <kuankuan.y@gmail.com> <ykk@rock-chips.com>
 Yusuke Goda <goda.yusuke@renesas.com>
 Gustavo Padovan <gustavo@las.ic.unicamp.br>
 Gustavo Padovan <padovan@profusion.mobi>
+Changbin Du <changbin.du@intel.com> <changbin.du@intel.com>
+Changbin Du <changbin.du@intel.com> <changbin.du@gmail.com>
diff --git a/Documentation/ABI/testing/sysfs-devices-system-cpu b/Documentation/ABI/testing/sysfs-devices-system-cpu
index 9605dbd4b5b5..4fb76c0e8d30 100644
--- a/Documentation/ABI/testing/sysfs-devices-system-cpu
+++ b/Documentation/ABI/testing/sysfs-devices-system-cpu
@@ -511,10 +511,30 @@ Description:	Control Symetric Multi Threading (SMT)
 		control: Read/write interface to control SMT. Possible
 			 values:
 
-			 "on"		SMT is enabled
-			 "off"		SMT is disabled
-			 "forceoff"	SMT is force disabled. Cannot be changed.
-			 "notsupported" SMT is not supported by the CPU
+			 "on"		  SMT is enabled
+			 "off"		  SMT is disabled
+			 "forceoff"	  SMT is force disabled. Cannot be changed.
+			 "notsupported"   SMT is not supported by the CPU
+			 "notimplemented" SMT runtime toggling is not
+					  implemented for the architecture
 
 			 If control status is "forceoff" or "notsupported" writes
 			 are rejected.
+
+What:		/sys/devices/system/cpu/cpu#/power/energy_perf_bias
+Date:		March 2019
+Contact:	linux-pm@vger.kernel.org
+Description:	Intel Energy and Performance Bias Hint (EPB)
+
+		EPB for the given CPU in a sliding scale 0 - 15, where a value
+		of 0 corresponds to a hint preference for highest performance
+		and a value of 15 corresponds to the maximum energy savings.
+
+		In order to change the EPB value for the CPU, write either
+		a number in the 0 - 15 sliding scale above, or one of the
+		strings: "performance", "balance-performance", "normal",
+		"balance-power", "power" (that represent values reflected by
+		their meaning), to this attribute.
+
+		This attribute is present for all online CPUs supporting the
+		Intel EPB feature.
diff --git a/Documentation/RCU/Design/Data-Structures/Data-Structures.html b/Documentation/RCU/Design/Data-Structures/Data-Structures.html
index 18f179807563..c30c1957c7e6 100644
--- a/Documentation/RCU/Design/Data-Structures/Data-Structures.html
+++ b/Documentation/RCU/Design/Data-Structures/Data-Structures.html
@@ -155,8 +155,7 @@ keeping lock contention under control at all tree levels regardless
 of the level of loading on the system.
 
 </p><p>RCU updaters wait for normal grace periods by registering
-RCU callbacks, either directly via <tt>call_rcu()</tt> and
-friends (namely <tt>call_rcu_bh()</tt> and <tt>call_rcu_sched()</tt>),
+RCU callbacks, either directly via <tt>call_rcu()</tt>
 or indirectly via <tt>synchronize_rcu()</tt> and friends.
 RCU callbacks are represented by <tt>rcu_head</tt> structures,
 which are queued on <tt>rcu_data</tt> structures while they are
diff --git a/Documentation/RCU/Design/Expedited-Grace-Periods/Expedited-Grace-Periods.html b/Documentation/RCU/Design/Expedited-Grace-Periods/Expedited-Grace-Periods.html
index 19e7a5fb6b73..57300db4b5ff 100644
--- a/Documentation/RCU/Design/Expedited-Grace-Periods/Expedited-Grace-Periods.html
+++ b/Documentation/RCU/Design/Expedited-Grace-Periods/Expedited-Grace-Periods.html
@@ -56,6 +56,7 @@ sections.
 RCU-preempt Expedited Grace Periods</a></h2>
 
 <p>
+<tt>CONFIG_PREEMPT=y</tt> kernels implement RCU-preempt.
 The overall flow of the handling of a given CPU by an RCU-preempt
 expedited grace period is shown in the following diagram:
 
@@ -139,6 +140,7 @@ or offline, among other things.
 RCU-sched Expedited Grace Periods</a></h2>
 
 <p>
+<tt>CONFIG_PREEMPT=n</tt> kernels implement RCU-sched.
 The overall flow of the handling of a given CPU by an RCU-sched
 expedited grace period is shown in the following diagram:
 
@@ -146,7 +148,7 @@ expedited grace period is shown in the following diagram:
 
 <p>
 As with RCU-preempt, RCU-sched's
-<tt>synchronize_sched_expedited()</tt> ignores offline and
+<tt>synchronize_rcu_expedited()</tt> ignores offline and
 idle CPUs, again because they are in remotely detectable
 quiescent states.
 However, because the
diff --git a/Documentation/RCU/Design/Memory-Ordering/Tree-RCU-Memory-Ordering.html b/Documentation/RCU/Design/Memory-Ordering/Tree-RCU-Memory-Ordering.html
index 8d21af02b1f0..c64f8d26609f 100644
--- a/Documentation/RCU/Design/Memory-Ordering/Tree-RCU-Memory-Ordering.html
+++ b/Documentation/RCU/Design/Memory-Ordering/Tree-RCU-Memory-Ordering.html
@@ -34,12 +34,11 @@ Similarly, any code that happens before the beginning of a given RCU grace
 period is guaranteed to see the effects of all accesses following the end
 of that grace period that are within RCU read-side critical sections.
 
-<p>This guarantee is particularly pervasive for <tt>synchronize_sched()</tt>,
-for which RCU-sched read-side critical sections include any region
+<p>Note well that RCU-sched read-side critical sections include any region
 of code for which preemption is disabled.
 Given that each individual machine instruction can be thought of as
 an extremely small region of preemption-disabled code, one can think of
-<tt>synchronize_sched()</tt> as <tt>smp_mb()</tt> on steroids.
+<tt>synchronize_rcu()</tt> as <tt>smp_mb()</tt> on steroids.
 
 <p>RCU updaters use this guarantee by splitting their updates into
 two phases, one of which is executed before the grace period and
diff --git a/Documentation/RCU/NMI-RCU.txt b/Documentation/RCU/NMI-RCU.txt
index 687777f83b23..881353fd5bff 100644
--- a/Documentation/RCU/NMI-RCU.txt
+++ b/Documentation/RCU/NMI-RCU.txt
@@ -81,18 +81,19 @@ currently executing on some other CPU.  We therefore cannot free
 up any data structures used by the old NMI handler until execution
 of it completes on all other CPUs.
 
-One way to accomplish this is via synchronize_sched(), perhaps as
+One way to accomplish this is via synchronize_rcu(), perhaps as
 follows:
 
 	unset_nmi_callback();
-	synchronize_sched();
+	synchronize_rcu();
 	kfree(my_nmi_data);
 
-This works because synchronize_sched() blocks until all CPUs complete
-any preemption-disabled segments of code that they were executing.
-Since NMI handlers disable preemption, synchronize_sched() is guaranteed
+This works because (as of v4.20) synchronize_rcu() blocks until all
+CPUs complete any preemption-disabled segments of code that they were
+executing.
+Since NMI handlers disable preemption, synchronize_rcu() is guaranteed
 not to return until all ongoing NMI handlers exit.  It is therefore safe
-to free up the handler's data as soon as synchronize_sched() returns.
+to free up the handler's data as soon as synchronize_rcu() returns.
 
 Important note: for this to work, the architecture in question must
 invoke nmi_enter() and nmi_exit() on NMI entry and exit, respectively.
diff --git a/Documentation/RCU/UP.txt b/Documentation/RCU/UP.txt
index 90ec5341ee98..53bde717017b 100644
--- a/Documentation/RCU/UP.txt
+++ b/Documentation/RCU/UP.txt
@@ -86,10 +86,8 @@ even on a UP system.  So do not do it!  Even on a UP system, the RCU
 infrastructure -must- respect grace periods, and -must- invoke callbacks
 from a known environment in which no locks are held.
 
-It -is- safe for synchronize_sched() and synchronize_rcu_bh() to return
-immediately on an UP system.  It is also safe for synchronize_rcu()
-to return immediately on UP systems, except when running preemptable
-RCU.
+Note that it -is- safe for synchronize_rcu() to return immediately on
+UP systems, including !PREEMPT SMP builds running on UP systems.
 
 Quick Quiz #3: Why can't synchronize_rcu() return immediately on
 	UP systems running preemptable RCU?
diff --git a/Documentation/RCU/checklist.txt b/Documentation/RCU/checklist.txt
index 6f469864d9f5..e98ff261a438 100644
--- a/Documentation/RCU/checklist.txt
+++ b/Documentation/RCU/checklist.txt
@@ -182,16 +182,13 @@ over a rather long period of time, but improvements are always welcome!
 		when publicizing a pointer to a structure that can
 		be traversed by an RCU read-side critical section.
 
-5.	If call_rcu(), or a related primitive such as call_rcu_bh(),
-	call_rcu_sched(), or call_srcu() is used, the callback function
-	will be called from softirq context.  In particular, it cannot
-	block.
+5.	If call_rcu() or call_srcu() is used, the callback function will
+	be called from softirq context.  In particular, it cannot block.
 
-6.	Since synchronize_rcu() can block, it cannot be called from
-	any sort of irq context.  The same rule applies for
-	synchronize_rcu_bh(), synchronize_sched(), synchronize_srcu(),
-	synchronize_rcu_expedited(), synchronize_rcu_bh_expedited(),
-	synchronize_sched_expedite(), and synchronize_srcu_expedited().
+6.	Since synchronize_rcu() can block, it cannot be called
+	from any sort of irq context.  The same rule applies
+	for synchronize_srcu(), synchronize_rcu_expedited(), and
+	synchronize_srcu_expedited().
 
 	The expedited forms of these primitives have the same semantics
 	as the non-expedited forms, but expediting is both expensive and
@@ -212,20 +209,20 @@ over a rather long period of time, but improvements are always welcome!
 	of the system, especially to real-time workloads running on
 	the rest of the system.
 
-7.	If the updater uses call_rcu() or synchronize_rcu(), then the
-	corresponding readers must use rcu_read_lock() and
-	rcu_read_unlock().  If the updater uses call_rcu_bh() or
-	synchronize_rcu_bh(), then the corresponding readers must
-	use rcu_read_lock_bh() and rcu_read_unlock_bh().  If the
-	updater uses call_rcu_sched() or synchronize_sched(), then
-	the corresponding readers must disable preemption, possibly
-	by calling rcu_read_lock_sched() and rcu_read_unlock_sched().
-	If the updater uses synchronize_srcu() or call_srcu(), then
-	the corresponding readers must use srcu_read_lock() and
+7.	As of v4.20, a given kernel implements only one RCU flavor,
+	which is RCU-sched for PREEMPT=n and RCU-preempt for PREEMPT=y.
+	If the updater uses call_rcu() or synchronize_rcu(),
+	then the corresponding readers my use rcu_read_lock() and
+	rcu_read_unlock(), rcu_read_lock_bh() and rcu_read_unlock_bh(),
+	or any pair of primitives that disables and re-enables preemption,
+	for example, rcu_read_lock_sched() and rcu_read_unlock_sched().
+	If the updater uses synchronize_srcu() or call_srcu(),
+	then the corresponding readers must use srcu_read_lock() and
 	srcu_read_unlock(), and with the same srcu_struct.  The rules for
 	the expedited primitives are the same as for their non-expedited
 	counterparts.  Mixing things up will result in confusion and
-	broken kernels.
+	broken kernels, and has even resulted in an exploitable security
+	issue.
 
 	One exception to this rule: rcu_read_lock() and rcu_read_unlock()
 	may be substituted for rcu_read_lock_bh() and rcu_read_unlock_bh()
@@ -288,8 +285,7 @@ over a rather long period of time, but improvements are always welcome!
 	d.	Periodically invoke synchronize_rcu(), permitting a limited
 		number of updates per grace period.
 
-	The same cautions apply to call_rcu_bh(), call_rcu_sched(),
-	call_srcu(), and kfree_rcu().
+	The same cautions apply to call_srcu() and kfree_rcu().
 
 	Note that although these primitives do take action to avoid memory
 	exhaustion when any given CPU has too many callbacks, a determined
@@ -322,7 +318,7 @@ over a rather long period of time, but improvements are always welcome!
 
 11.	Any lock acquired by an RCU callback must be acquired elsewhere
 	with softirq disabled, e.g., via spin_lock_irqsave(),
-	spin_lock_bh(), etc.  Failing to disable irq on a given
+	spin_lock_bh(), etc.  Failing to disable softirq on a given
 	acquisition of that lock will result in deadlock as soon as
 	the RCU softirq handler happens to run your RCU callback while
 	interrupting that acquisition's critical section.
@@ -335,13 +331,16 @@ over a rather long period of time, but improvements are always welcome!
 	must use whatever locking or other synchronization is required
 	to safely access and/or modify that data structure.
 
-	RCU callbacks are -usually- executed on the same CPU that executed
-	the corresponding call_rcu(), call_rcu_bh(), or call_rcu_sched(),
-	but are by -no- means guaranteed to be.  For example, if a given
-	CPU goes offline while having an RCU callback pending, then that
-	RCU callback will execute on some surviving CPU.  (If this was
-	not the case, a self-spawning RCU callback would prevent the
-	victim CPU from ever going offline.)
+	Do not assume that RCU callbacks will be executed on the same
+	CPU that executed the corresponding call_rcu() or call_srcu().
+	For example, if a given CPU goes offline while having an RCU
+	callback pending, then that RCU callback will execute on some
+	surviving CPU.	(If this was not the case, a self-spawning RCU
+	callback would prevent the victim CPU from ever going offline.)
+	Furthermore, CPUs designated by rcu_nocbs= might well -always-
+	have their RCU callbacks executed on some other CPUs, in fact,
+	for some  real-time workloads, this is the whole point of using
+	the rcu_nocbs= kernel boot parameter.
 
 13.	Unlike other forms of RCU, it -is- permissible to block in an
 	SRCU read-side critical section (demarked by srcu_read_lock()
@@ -381,11 +380,11 @@ over a rather long period of time, but improvements are always welcome!
 
 	SRCU's expedited primitive (synchronize_srcu_expedited())
 	never sends IPIs to other CPUs, so it is easier on
-	real-time workloads than is synchronize_rcu_expedited(),
-	synchronize_rcu_bh_expedited() or synchronize_sched_expedited().
+	real-time workloads than is synchronize_rcu_expedited().
 
-	Note that rcu_dereference() and rcu_assign_pointer() relate to
-	SRCU just as they do to other forms of RCU.
+	Note that rcu_assign_pointer() relates to SRCU just as it does to
+	other forms of RCU, but instead of rcu_dereference() you should
+	use srcu_dereference() in order to avoid lockdep splats.
 
 14.	The whole point of call_rcu(), synchronize_rcu(), and friends
 	is to wait until all pre-existing readers have finished before
@@ -405,6 +404,9 @@ over a rather long period of time, but improvements are always welcome!
 	read-side critical sections.  It is the responsibility of the
 	RCU update-side primitives to deal with this.
 
+	For SRCU readers, you can use smp_mb__after_srcu_read_unlock()
+	immediately after an srcu_read_unlock() to get a full barrier.
+
 16.	Use CONFIG_PROVE_LOCKING, CONFIG_DEBUG_OBJECTS_RCU_HEAD, and the
 	__rcu sparse checks to validate your RCU code.	These can help
 	find problems as follows:
@@ -428,22 +430,19 @@ over a rather long period of time, but improvements are always welcome!
 	These debugging aids can help you find problems that are
 	otherwise extremely difficult to spot.
 
-17.	If you register a callback using call_rcu(), call_rcu_bh(),
-	call_rcu_sched(), or call_srcu(), and pass in a function defined
-	within a loadable module, then it in necessary to wait for
-	all pending callbacks to be invoked after the last invocation
-	and before unloading that module.  Note that it is absolutely
-	-not- sufficient to wait for a grace period!  The current (say)
-	synchronize_rcu() implementation waits only for all previous
-	callbacks registered on the CPU that synchronize_rcu() is running
-	on, but it is -not- guaranteed to wait for callbacks registered
-	on other CPUs.
+17.	If you register a callback using call_rcu() or call_srcu(), and
+	pass in a function defined within a loadable module, then it in
+	necessary to wait for all pending callbacks to be invoked after
+	the last invocation and before unloading that module.  Note that
+	it is absolutely -not- sufficient to wait for a grace period!
+	The current (say) synchronize_rcu() implementation is -not-
+	guaranteed to wait for callbacks registered on other CPUs.
+	Or even on the current CPU if that CPU recently went offline
+	and came back online.
 
 	You instead need to use one of the barrier functions:
 
 	o	call_rcu() -> rcu_barrier()
-	o	call_rcu_bh() -> rcu_barrier()
-	o	call_rcu_sched() -> rcu_barrier()
 	o	call_srcu() -> srcu_barrier()
 
 	However, these barrier functions are absolutely -not- guaranteed
diff --git a/Documentation/RCU/rcu.txt b/Documentation/RCU/rcu.txt
index 721b3e426515..c818cf65c5a9 100644
--- a/Documentation/RCU/rcu.txt
+++ b/Documentation/RCU/rcu.txt
@@ -52,10 +52,10 @@ o	If I am running on a uniprocessor kernel, which can only do one
 o	How can I see where RCU is currently used in the Linux kernel?
 
 	Search for "rcu_read_lock", "rcu_read_unlock", "call_rcu",
-	"rcu_read_lock_bh", "rcu_read_unlock_bh", "call_rcu_bh",
-	"srcu_read_lock", "srcu_read_unlock", "synchronize_rcu",
-	"synchronize_net", "synchronize_srcu", and the other RCU
-	primitives.  Or grab one of the cscope databases from:
+	"rcu_read_lock_bh", "rcu_read_unlock_bh", "srcu_read_lock",
+	"srcu_read_unlock", "synchronize_rcu", "synchronize_net",
+	"synchronize_srcu", and the other RCU primitives.  Or grab one
+	of the cscope databases from:
 
 	http://www.rdrop.com/users/paulmck/RCU/linuxusage/rculocktab.html
 
diff --git a/Documentation/RCU/rcu_dereference.txt b/Documentation/RCU/rcu_dereference.txt
index ab96227bad42..bf699e8cfc75 100644
--- a/Documentation/RCU/rcu_dereference.txt
+++ b/Documentation/RCU/rcu_dereference.txt
@@ -351,3 +351,106 @@ garbage values.
 
 In short, rcu_dereference() is -not- optional when you are going to
 dereference the resulting pointer.
+
+
+WHICH MEMBER OF THE rcu_dereference() FAMILY SHOULD YOU USE?
+
+First, please avoid using rcu_dereference_raw() and also please avoid
+using rcu_dereference_check() and rcu_dereference_protected() with a
+second argument with a constant value of 1 (or true, for that matter).
+With that caution out of the way, here is some guidance for which
+member of the rcu_dereference() to use in various situations:
+
+1.	If the access needs to be within an RCU read-side critical
+	section, use rcu_dereference().  With the new consolidated
+	RCU flavors, an RCU read-side critical section is entered
+	using rcu_read_lock(), anything that disables bottom halves,
+	anything that disables interrupts, or anything that disables
+	preemption.
+
+2.	If the access might be within an RCU read-side critical section
+	on the one hand, or protected by (say) my_lock on the other,
+	use rcu_dereference_check(), for example:
+
+		p1 = rcu_dereference_check(p->rcu_protected_pointer,
+					   lockdep_is_held(&my_lock));
+
+
+3.	If the access might be within an RCU read-side critical section
+	on the one hand, or protected by either my_lock or your_lock on
+	the other, again use rcu_dereference_check(), for example:
+
+		p1 = rcu_dereference_check(p->rcu_protected_pointer,
+					   lockdep_is_held(&my_lock) ||
+					   lockdep_is_held(&your_lock));
+
+4.	If the access is on the update side, so that it is always protected
+	by my_lock, use rcu_dereference_protected():
+
+		p1 = rcu_dereference_protected(p->rcu_protected_pointer,
+					       lockdep_is_held(&my_lock));
+
+	This can be extended to handle multiple locks as in #3 above,
+	and both can be extended to check other conditions as well.
+
+5.	If the protection is supplied by the caller, and is thus unknown
+	to this code, that is the rare case when rcu_dereference_raw()
+	is appropriate.  In addition, rcu_dereference_raw() might be
+	appropriate when the lockdep expression would be excessively
+	complex, except that a better approach in that case might be to
+	take a long hard look at your synchronization design.  Still,
+	there are data-locking cases where any one of a very large number
+	of locks or reference counters suffices to protect the pointer,
+	so rcu_dereference_raw() does have its place.
+
+	However, its place is probably quite a bit smaller than one
+	might expect given the number of uses in the current kernel.
+	Ditto for its synonym, rcu_dereference_check( ... , 1), and
+	its close relative, rcu_dereference_protected(... , 1).
+
+
+SPARSE CHECKING OF RCU-PROTECTED POINTERS
+
+The sparse static-analysis tool checks for direct access to RCU-protected
+pointers, which can result in "interesting" bugs due to compiler
+optimizations involving invented loads and perhaps also load tearing.
+For example, suppose someone mistakenly does something like this:
+
+	p = q->rcu_protected_pointer;
+	do_something_with(p->a);
+	do_something_else_with(p->b);
+
+If register pressure is high, the compiler might optimize "p" out
+of existence, transforming the code to something like this:
+
+	do_something_with(q->rcu_protected_pointer->a);
+	do_something_else_with(q->rcu_protected_pointer->b);
+
+This could fatally disappoint your code if q->rcu_protected_pointer
+changed in the meantime.  Nor is this a theoretical problem:  Exactly
+this sort of bug cost Paul E. McKenney (and several of his innocent
+colleagues) a three-day weekend back in the early 1990s.
+
+Load tearing could of course result in dereferencing a mashup of a pair
+of pointers, which also might fatally disappoint your code.
+
+These problems could have been avoided simply by making the code instead
+read as follows:
+
+	p = rcu_dereference(q->rcu_protected_pointer);
+	do_something_with(p->a);
+	do_something_else_with(p->b);
+
+Unfortunately, these sorts of bugs can be extremely hard to spot during
+review.  This is where the sparse tool comes into play, along with the
+"__rcu" marker.  If you mark a pointer declaration, whether in a structure
+or as a formal parameter, with "__rcu", which tells sparse to complain if
+this pointer is accessed directly.  It will also cause sparse to complain
+if a pointer not marked with "__rcu" is accessed using rcu_dereference()
+and friends.  For example, ->rcu_protected_pointer might be declared as
+follows:
+
+	struct foo __rcu *rcu_protected_pointer;
+
+Use of "__rcu" is opt-in.  If you choose not to use it, then you should
+ignore the sparse warnings.
diff --git a/Documentation/RCU/rcubarrier.txt b/Documentation/RCU/rcubarrier.txt
index 5d7759071a3e..a2782df69732 100644
--- a/Documentation/RCU/rcubarrier.txt
+++ b/Documentation/RCU/rcubarrier.txt
@@ -83,16 +83,15 @@ Pseudo-code using rcu_barrier() is as follows:
    2. Execute rcu_barrier().
    3. Allow the module to be unloaded.
 
-There are also rcu_barrier_bh(), rcu_barrier_sched(), and srcu_barrier()
-functions for the other flavors of RCU, and you of course must match
-the flavor of rcu_barrier() with that of call_rcu().  If your module
-uses multiple flavors of call_rcu(), then it must also use multiple
+There is also an srcu_barrier() function for SRCU, and you of course
+must match the flavor of rcu_barrier() with that of call_rcu().  If your
+module uses multiple flavors of call_rcu(), then it must also use multiple
 flavors of rcu_barrier() when unloading that module.  For example, if
-it uses call_rcu_bh(), call_srcu() on srcu_struct_1, and call_srcu() on
+it uses call_rcu(), call_srcu() on srcu_struct_1, and call_srcu() on
 srcu_struct_2(), then the following three lines of code will be required
 when unloading:
 
- 1 rcu_barrier_bh();
+ 1 rcu_barrier();
  2 srcu_barrier(&srcu_struct_1);
  3 srcu_barrier(&srcu_struct_2);
 
@@ -185,12 +184,12 @@ module invokes call_rcu() from timers, you will need to first cancel all
 the timers, and only then invoke rcu_barrier() to wait for any remaining
 RCU callbacks to complete.
 
-Of course, if you module uses call_rcu_bh(), you will need to invoke
-rcu_barrier_bh() before unloading.  Similarly, if your module uses
-call_rcu_sched(), you will need to invoke rcu_barrier_sched() before
-unloading.  If your module uses call_rcu(), call_rcu_bh(), -and-
-call_rcu_sched(), then you will need to invoke each of rcu_barrier(),
-rcu_barrier_bh(), and rcu_barrier_sched().
+Of course, if you module uses call_rcu(), you will need to invoke
+rcu_barrier() before unloading.  Similarly, if your module uses
+call_srcu(), you will need to invoke srcu_barrier() before unloading,
+and on the same srcu_struct structure.  If your module uses call_rcu()
+-and- call_srcu(), then you will need to invoke rcu_barrier() -and-
+srcu_barrier().
 
 
 Implementing rcu_barrier()
@@ -223,8 +222,8 @@ shown below. Note that the final "1" in on_each_cpu()'s argument list
 ensures that all the calls to rcu_barrier_func() will have completed
 before on_each_cpu() returns. Line 9 then waits for the completion.
 
-This code was rewritten in 2008 to support rcu_barrier_bh() and
-rcu_barrier_sched() in addition to the original rcu_barrier().
+This code was rewritten in 2008 and several times thereafter, but this
+still gives the general idea.
 
 The rcu_barrier_func() runs on each CPU, where it invokes call_rcu()
 to post an RCU callback, as follows:
diff --git a/Documentation/RCU/whatisRCU.txt b/Documentation/RCU/whatisRCU.txt
index 1ace20815bb1..981651a8b65d 100644
--- a/Documentation/RCU/whatisRCU.txt
+++ b/Documentation/RCU/whatisRCU.txt
@@ -310,7 +310,7 @@ reader, updater, and reclaimer.
 
 
 	    rcu_assign_pointer()
-	    			    +--------+
+	                            +--------+
 	    +---------------------->| reader |---------+
 	    |                       +--------+         |
 	    |                           |              |
@@ -318,12 +318,12 @@ reader, updater, and reclaimer.
 	    |                           |              | rcu_read_lock()
 	    |                           |              | rcu_read_unlock()
 	    |        rcu_dereference()  |              |
-       +---------+                      |              |
-       | updater |<---------------------+              |
-       +---------+                                     V
+	    +---------+                 |              |
+	    | updater |<----------------+              |
+	    +---------+                                V
 	    |                                    +-----------+
 	    +----------------------------------->| reclaimer |
-	    				         +-----------+
+	                                         +-----------+
 	      Defer:
 	      synchronize_rcu() & call_rcu()
 
diff --git a/Documentation/accounting/psi.txt b/Documentation/accounting/psi.txt
index b8ca28b60215..7e71c9c1d8e9 100644
--- a/Documentation/accounting/psi.txt
+++ b/Documentation/accounting/psi.txt
@@ -56,12 +56,12 @@ situation from a state where some tasks are stalled but the CPU is
 still doing productive work. As such, time spent in this subset of the
 stall state is tracked separately and exported in the "full" averages.
 
-The ratios are tracked as recent trends over ten, sixty, and three
-hundred second windows, which gives insight into short term events as
-well as medium and long term trends. The total absolute stall time is
-tracked and exported as well, to allow detection of latency spikes
-which wouldn't necessarily make a dent in the time averages, or to
-average trends over custom time frames.
+The ratios (in %) are tracked as recent trends over ten, sixty, and
+three hundred second windows, which gives insight into short term events
+as well as medium and long term trends. The total absolute stall time
+(in us) is tracked and exported as well, to allow detection of latency
+spikes which wouldn't necessarily make a dent in the time averages,
+or to average trends over custom time frames.
 
 Cgroup2 interface
 =================
diff --git a/Documentation/acpi/aml-debugger.txt b/Documentation/acpi/aml-debugger.txt
deleted file mode 100644
index 75ebeb64ab29..000000000000
--- a/Documentation/acpi/aml-debugger.txt
+++ /dev/null
@@ -1,66 +0,0 @@
-The AML Debugger
-
-Copyright (C) 2016, Intel Corporation
-Author: Lv Zheng <lv.zheng@intel.com>
-
-
-This document describes the usage of the AML debugger embedded in the Linux
-kernel.
-
-1. Build the debugger
-
-   The following kernel configuration items are required to enable the AML
-   debugger interface from the Linux kernel:
-
-   CONFIG_ACPI_DEBUGGER=y
-   CONFIG_ACPI_DEBUGGER_USER=m
-
-   The userspace utilities can be built from the kernel source tree using
-   the following commands:
-
-   $ cd tools
-   $ make acpi
-
-   The resultant userspace tool binary is then located at:
-
-     tools/power/acpi/acpidbg
-
-   It can be installed to system directories by running "make install" (as a
-   sufficiently privileged user).
-
-2. Start the userspace debugger interface
-
-   After booting the kernel with the debugger built-in, the debugger can be
-   started by using the following commands:
-
-   # mount -t debugfs none /sys/kernel/debug
-   # modprobe acpi_dbg
-   # tools/power/acpi/acpidbg
-
-   That spawns the interactive AML debugger environment where you can execute
-   debugger commands.
-
-   The commands are documented in the "ACPICA Overview and Programmer Reference"
-   that can be downloaded from
-
-   https://acpica.org/documentation
-
-   The detailed debugger commands reference is located in Chapter 12 "ACPICA
-   Debugger Reference".  The "help" command can be used for a quick reference.
-
-3. Stop the userspace debugger interface
-
-   The interactive debugger interface can be closed by pressing Ctrl+C or using
-   the "quit" or "exit" commands.  When finished, unload the module with:
-
-   # rmmod acpi_dbg
-
-   The module unloading may fail if there is an acpidbg instance running.
-
-4. Run the debugger in a script
-
-   It may be useful to run the AML debugger in a test script. "acpidbg" supports
-   this in a special "batch" mode.  For example, the following command outputs
-   the entire ACPI namespace:
-
-   # acpidbg -b "namespace"
diff --git a/Documentation/acpi/apei/output_format.txt b/Documentation/acpi/apei/output_format.txt
deleted file mode 100644
index 0c49c197c47a..000000000000
--- a/Documentation/acpi/apei/output_format.txt
+++ /dev/null
@@ -1,147 +0,0 @@
-                     APEI output format
-                     ~~~~~~~~~~~~~~~~~~
-
-APEI uses printk as hardware error reporting interface, the output
-format is as follow.
-
-<error record> :=
-APEI generic hardware error status
-severity: <integer>, <severity string>
-section: <integer>, severity: <integer>, <severity string>
-flags: <integer>
-<section flags strings>
-fru_id: <uuid string>
-fru_text: <string>
-section_type: <section type string>
-<section data>
-
-<severity string>* := recoverable | fatal | corrected | info
-
-<section flags strings># :=
-[primary][, containment warning][, reset][, threshold exceeded]\
-[, resource not accessible][, latent error]
-
-<section type string> := generic processor error | memory error | \
-PCIe error | unknown, <uuid string>
-
-<section data> :=
-<generic processor section data> | <memory section data> | \
-<pcie section data> | <null>
-
-<generic processor section data> :=
-[processor_type: <integer>, <proc type string>]
-[processor_isa: <integer>, <proc isa string>]
-[error_type: <integer>
-<proc error type strings>]
-[operation: <integer>, <proc operation string>]
-[flags: <integer>
-<proc flags strings>]
-[level: <integer>]
-[version_info: <integer>]
-[processor_id: <integer>]
-[target_address: <integer>]
-[requestor_id: <integer>]
-[responder_id: <integer>]
-[IP: <integer>]
-
-<proc type string>* := IA32/X64 | IA64
-
-<proc isa string>* := IA32 | IA64 | X64
-
-<processor error type strings># :=
-[cache error][, TLB error][, bus error][, micro-architectural error]
-
-<proc operation string>* := unknown or generic | data read | data write | \
-instruction execution
-
-<proc flags strings># :=
-[restartable][, precise IP][, overflow][, corrected]
-
-<memory section data> :=
-[error_status: <integer>]
-[physical_address: <integer>]
-[physical_address_mask: <integer>]
-[node: <integer>]
-[card: <integer>]
-[module: <integer>]
-[bank: <integer>]
-[device: <integer>]
-[row: <integer>]
-[column: <integer>]
-[bit_position: <integer>]
-[requestor_id: <integer>]
-[responder_id: <integer>]
-[target_id: <integer>]
-[error_type: <integer>, <mem error type string>]
-
-<mem error type string>* :=
-unknown | no error | single-bit ECC | multi-bit ECC | \
-single-symbol chipkill ECC | multi-symbol chipkill ECC | master abort | \
-target abort | parity error | watchdog timeout | invalid address | \
-mirror Broken | memory sparing | scrub corrected error | \
-scrub uncorrected error
-
-<pcie section data> :=
-[port_type: <integer>, <pcie port type string>]
-[version: <integer>.<integer>]
-[command: <integer>, status: <integer>]
-[device_id: <integer>:<integer>:<integer>.<integer>
-slot: <integer>
-secondary_bus: <integer>
-vendor_id: <integer>, device_id: <integer>
-class_code: <integer>]
-[serial number: <integer>, <integer>]
-[bridge: secondary_status: <integer>, control: <integer>]
-[aer_status: <integer>, aer_mask: <integer>
-<aer status string>
-[aer_uncor_severity: <integer>]
-aer_layer=<aer layer string>, aer_agent=<aer agent string>
-aer_tlp_header: <integer> <integer> <integer> <integer>]
-
-<pcie port type string>* := PCIe end point | legacy PCI end point | \
-unknown | unknown | root port | upstream switch port | \
-downstream switch port | PCIe to PCI/PCI-X bridge | \
-PCI/PCI-X to PCIe bridge | root complex integrated endpoint device | \
-root complex event collector
-
-if section severity is fatal or recoverable
-<aer status string># :=
-unknown | unknown | unknown | unknown | Data Link Protocol | \
-unknown | unknown | unknown | unknown | unknown | unknown | unknown | \
-Poisoned TLP | Flow Control Protocol | Completion Timeout | \
-Completer Abort | Unexpected Completion | Receiver Overflow | \
-Malformed TLP | ECRC | Unsupported Request
-else
-<aer status string># :=
-Receiver Error | unknown | unknown | unknown | unknown | unknown | \
-Bad TLP | Bad DLLP | RELAY_NUM Rollover | unknown | unknown | unknown | \
-Replay Timer Timeout | Advisory Non-Fatal
-fi
-
-<aer layer string> :=
-Physical Layer | Data Link Layer | Transaction Layer
-
-<aer agent string> :=
-Receiver ID | Requester ID | Completer ID | Transmitter ID
-
-Where, [] designate corresponding content is optional
-
-All <field string> description with * has the following format:
-
-field: <integer>, <field string>
-
-Where value of <integer> should be the position of "string" in <field
-string> description. Otherwise, <field string> will be "unknown".
-
-All <field strings> description with # has the following format:
-
-field: <integer>
-<field strings>
-
-Where each string in <fields strings> corresponding to one set bit of
-<integer>. The bit position is the position of "string" in <field
-strings> description.
-
-For more detailed explanation of every field, please refer to UEFI
-specification version 2.3 or later, section Appendix N: Common
-Platform Error Record.
diff --git a/Documentation/acpi/i2c-muxes.txt b/Documentation/acpi/i2c-muxes.txt
deleted file mode 100644
index 9fcc4f0b885e..000000000000
--- a/Documentation/acpi/i2c-muxes.txt
+++ /dev/null
@@ -1,58 +0,0 @@
-ACPI I2C Muxes
---------------
-
-Describing an I2C device hierarchy that includes I2C muxes requires an ACPI
-Device () scope per mux channel.
-
-Consider this topology:
-
-+------+   +------+
-| SMB1 |-->| MUX0 |--CH00--> i2c client A (0x50)
-|      |   | 0x70 |--CH01--> i2c client B (0x50)
-+------+   +------+
-
-which corresponds to the following ASL:
-
-Device (SMB1)
-{
-    Name (_HID, ...)
-    Device (MUX0)
-    {
-        Name (_HID, ...)
-        Name (_CRS, ResourceTemplate () {
-            I2cSerialBus (0x70, ControllerInitiated, I2C_SPEED,
-                          AddressingMode7Bit, "^SMB1", 0x00,
-                          ResourceConsumer,,)
-        }
-
-        Device (CH00)
-        {
-            Name (_ADR, 0)
-
-            Device (CLIA)
-            {
-                Name (_HID, ...)
-                Name (_CRS, ResourceTemplate () {
-                    I2cSerialBus (0x50, ControllerInitiated, I2C_SPEED,
-                                  AddressingMode7Bit, "^CH00", 0x00,
-                                  ResourceConsumer,,)
-                }
-            }
-        }
-
-        Device (CH01)
-        {
-            Name (_ADR, 1)
-
-            Device (CLIB)
-            {
-                Name (_HID, ...)
-                Name (_CRS, ResourceTemplate () {
-                    I2cSerialBus (0x50, ControllerInitiated, I2C_SPEED,
-                                  AddressingMode7Bit, "^CH01", 0x00,
-                                  ResourceConsumer,,)
-                }
-            }
-        }
-    }
-}
diff --git a/Documentation/acpi/initrd_table_override.txt b/Documentation/acpi/initrd_table_override.txt
deleted file mode 100644
index 30437a6db373..000000000000
--- a/Documentation/acpi/initrd_table_override.txt
+++ /dev/null
@@ -1,111 +0,0 @@
-Upgrading ACPI tables via initrd
-================================
-
-1) Introduction (What is this about)
-2) What is this for
-3) How does it work
-4) References (Where to retrieve userspace tools)
-
-1) What is this about
----------------------
-
-If the ACPI_TABLE_UPGRADE compile option is true, it is possible to
-upgrade the ACPI execution environment that is defined by the ACPI tables
-via upgrading the ACPI tables provided by the BIOS with an instrumented,
-modified, more recent version one, or installing brand new ACPI tables.
-
-When building initrd with kernel in a single image, option
-ACPI_TABLE_OVERRIDE_VIA_BUILTIN_INITRD should also be true for this
-feature to work.
-
-For a full list of ACPI tables that can be upgraded/installed, take a look
-at the char *table_sigs[MAX_ACPI_SIGNATURE]; definition in
-drivers/acpi/tables.c.
-All ACPI tables iasl (Intel's ACPI compiler and disassembler) knows should
-be overridable, except:
-   - ACPI_SIG_RSDP (has a signature of 6 bytes)
-   - ACPI_SIG_FACS (does not have an ordinary ACPI table header)
-Both could get implemented as well.
-
-
-2) What is this for
--------------------
-
-Complain to your platform/BIOS vendor if you find a bug which is so severe
-that a workaround is not accepted in the Linux kernel. And this facility
-allows you to upgrade the buggy tables before your platform/BIOS vendor
-releases an upgraded BIOS binary.
-
-This facility can be used by platform/BIOS vendors to provide a Linux
-compatible environment without modifying the underlying platform firmware.
-
-This facility also provides a powerful feature to easily debug and test
-ACPI BIOS table compatibility with the Linux kernel by modifying old
-platform provided ACPI tables or inserting new ACPI tables.
-
-It can and should be enabled in any kernel because there is no functional
-change with not instrumented initrds.
-
-
-3) How does it work
--------------------
-
-# Extract the machine's ACPI tables:
-cd /tmp
-acpidump >acpidump
-acpixtract -a acpidump
-# Disassemble, modify and recompile them:
-iasl -d *.dat
-# For example add this statement into a _PRT (PCI Routing Table) function
-# of the DSDT:
-Store("HELLO WORLD", debug)
-# And increase the OEM Revision. For example, before modification:
-DefinitionBlock ("DSDT.aml", "DSDT", 2, "INTEL ", "TEMPLATE", 0x00000000)
-# After modification:
-DefinitionBlock ("DSDT.aml", "DSDT", 2, "INTEL ", "TEMPLATE", 0x00000001)
-iasl -sa dsdt.dsl
-# Add the raw ACPI tables to an uncompressed cpio archive.
-# They must be put into a /kernel/firmware/acpi directory inside the cpio
-# archive. Note that if the table put here matches a platform table
-# (similar Table Signature, and similar OEMID, and similar OEM Table ID)
-# with a more recent OEM Revision, the platform table will be upgraded by
-# this table. If the table put here doesn't match a platform table
-# (dissimilar Table Signature, or dissimilar OEMID, or dissimilar OEM Table
-# ID), this table will be appended.
-mkdir -p kernel/firmware/acpi
-cp dsdt.aml kernel/firmware/acpi
-# A maximum of "NR_ACPI_INITRD_TABLES (64)" tables are currently allowed
-# (see osl.c):
-iasl -sa facp.dsl
-iasl -sa ssdt1.dsl
-cp facp.aml kernel/firmware/acpi
-cp ssdt1.aml kernel/firmware/acpi
-# The uncompressed cpio archive must be the first. Other, typically
-# compressed cpio archives, must be concatenated on top of the uncompressed
-# one. Following command creates the uncompressed cpio archive and
-# concatenates the original initrd on top:
-find kernel | cpio -H newc --create > /boot/instrumented_initrd
-cat /boot/initrd >>/boot/instrumented_initrd
-# reboot with increased acpi debug level, e.g. boot params:
-acpi.debug_level=0x2 acpi.debug_layer=0xFFFFFFFF
-# and check your syslog:
-[    1.268089] ACPI: PCI Interrupt Routing Table [\_SB_.PCI0._PRT]
-[    1.272091] [ACPI Debug]  String [0x0B] "HELLO WORLD"
-
-iasl is able to disassemble and recompile quite a lot different,
-also static ACPI tables.
-
-
-4) Where to retrieve userspace tools
-------------------------------------
-
-iasl and acpixtract are part of Intel's ACPICA project:
-http://acpica.org/
-and should be packaged by distributions (for example in the acpica package
-on SUSE).
-
-acpidump can be found in Len Browns pmtools:
-ftp://kernel.org/pub/linux/kernel/people/lenb/acpi/utils/pmtools/acpidump
-This tool is also part of the acpica package on SUSE.
-Alternatively, used ACPI tables can be retrieved via sysfs in latest kernels:
-/sys/firmware/acpi/tables
diff --git a/Documentation/acpi/method-customizing.txt b/Documentation/acpi/method-customizing.txt
deleted file mode 100644
index 7235da975f23..000000000000
--- a/Documentation/acpi/method-customizing.txt
+++ /dev/null
@@ -1,73 +0,0 @@
-Linux ACPI Custom Control Method How To
-=======================================
-
-Written by Zhang Rui <rui.zhang@intel.com>
-
-
-Linux supports customizing ACPI control methods at runtime.
-
-Users can use this to
-1. override an existing method which may not work correctly,
-   or just for debugging purposes.
-2. insert a completely new method in order to create a missing
-   method such as _OFF, _ON, _STA, _INI, etc.
-For these cases, it is far simpler to dynamically install a single
-control method rather than override the entire DSDT, because kernel
-rebuild/reboot is not needed and test result can be got in minutes.
-
-Note: Only ACPI METHOD can be overridden, any other object types like
-      "Device", "OperationRegion", are not recognized. Methods
-      declared inside scope operators are also not supported.
-Note: The same ACPI control method can be overridden for many times,
-      and it's always the latest one that used by Linux/kernel.
-Note: To get the ACPI debug object output (Store (AAAA, Debug)),
-      please run "echo 1 > /sys/module/acpi/parameters/aml_debug_output".
-
-1. override an existing method
-   a) get the ACPI table via ACPI sysfs I/F. e.g. to get the DSDT,
-      just run "cat /sys/firmware/acpi/tables/DSDT > /tmp/dsdt.dat"
-   b) disassemble the table by running "iasl -d dsdt.dat".
-   c) rewrite the ASL code of the method and save it in a new file,
-   d) package the new file (psr.asl) to an ACPI table format.
-      Here is an example of a customized \_SB._AC._PSR method,
-
-      DefinitionBlock ("", "SSDT", 1, "", "", 0x20080715)
-      {
-	Method (\_SB_.AC._PSR, 0, NotSerialized)
-	{
-		Store ("In AC _PSR", Debug)
-		Return (ACON)
-	}
-      }
-      Note that the full pathname of the method in ACPI namespace
-      should be used.
-   e) assemble the file to generate the AML code of the method.
-      e.g. "iasl -vw 6084 psr.asl" (psr.aml is generated as a result)
-      If parameter "-vw 6084" is not supported by your iASL compiler,
-      please try a newer version.
-   f) mount debugfs by "mount -t debugfs none /sys/kernel/debug"
-   g) override the old method via the debugfs by running
-      "cat /tmp/psr.aml > /sys/kernel/debug/acpi/custom_method"
-
-2. insert a new method
-   This is easier than overriding an existing method.
-   We just need to create the ASL code of the method we want to
-   insert and then follow the step c) ~ g) in section 1.
-
-3. undo your changes
-   The "undo" operation is not supported for a new inserted method
-   right now, i.e. we can not remove a method currently.
-   For an overridden method, in order to undo your changes, please
-   save a copy of the method original ASL code in step c) section 1,
-   and redo step c) ~ g) to override the method with the original one.
-
-
-Note: We can use a kernel with multiple custom ACPI method running,
-      But each individual write to debugfs can implement a SINGLE
-      method override. i.e. if we want to insert/override multiple
-      ACPI methods, we need to redo step c) ~ g) for multiple times.
-
-Note: Be aware that root can mis-use this driver to modify arbitrary
-      memory and gain additional rights, if root's privileges got
-      restricted (for example if root is not allowed to load additional
-      modules after boot).
diff --git a/Documentation/acpi/method-tracing.txt b/Documentation/acpi/method-tracing.txt
deleted file mode 100644
index 0aba14c8f459..000000000000
--- a/Documentation/acpi/method-tracing.txt
+++ /dev/null
@@ -1,192 +0,0 @@
-ACPICA Trace Facility
-
-Copyright (C) 2015, Intel Corporation
-Author: Lv Zheng <lv.zheng@intel.com>
-
-
-Abstract:
-
-This document describes the functions and the interfaces of the method
-tracing facility.
-
-1. Functionalities and usage examples:
-
-   ACPICA provides method tracing capability. And two functions are
-   currently implemented using this capability.
-
-   A. Log reducer
-   ACPICA subsystem provides debugging outputs when CONFIG_ACPI_DEBUG is
-   enabled. The debugging messages which are deployed via
-   ACPI_DEBUG_PRINT() macro can be reduced at 2 levels - per-component
-   level (known as debug layer, configured via
-   /sys/module/acpi/parameters/debug_layer) and per-type level (known as
-   debug level, configured via /sys/module/acpi/parameters/debug_level).
-
-   But when the particular layer/level is applied to the control method
-   evaluations, the quantity of the debugging outputs may still be too
-   large to be put into the kernel log buffer. The idea thus is worked out
-   to only enable the particular debug layer/level (normally more detailed)
-   logs when the control method evaluation is started, and disable the
-   detailed logging when the control method evaluation is stopped.
-
-   The following command examples illustrate the usage of the "log reducer"
-   functionality:
-   a. Filter out the debug layer/level matched logs when control methods
-      are being evaluated:
-      # cd /sys/module/acpi/parameters
-      # echo "0xXXXXXXXX" > trace_debug_layer
-      # echo "0xYYYYYYYY" > trace_debug_level
-      # echo "enable" > trace_state
-   b. Filter out the debug layer/level matched logs when the specified
-      control method is being evaluated:
-      # cd /sys/module/acpi/parameters
-      # echo "0xXXXXXXXX" > trace_debug_layer
-      # echo "0xYYYYYYYY" > trace_debug_level
-      # echo "\PPPP.AAAA.TTTT.HHHH" > trace_method_name
-      # echo "method" > /sys/module/acpi/parameters/trace_state
-   c. Filter out the debug layer/level matched logs when the specified
-      control method is being evaluated for the first time:
-      # cd /sys/module/acpi/parameters
-      # echo "0xXXXXXXXX" > trace_debug_layer
-      # echo "0xYYYYYYYY" > trace_debug_level
-      # echo "\PPPP.AAAA.TTTT.HHHH" > trace_method_name
-      # echo "method-once" > /sys/module/acpi/parameters/trace_state
-   Where:
-      0xXXXXXXXX/0xYYYYYYYY: Refer to Documentation/acpi/debug.txt for
-			     possible debug layer/level masking values.
-      \PPPP.AAAA.TTTT.HHHH: Full path of a control method that can be found
-			    in the ACPI namespace. It needn't be an entry
-			    of a control method evaluation.
-
-   B. AML tracer
-
-   There are special log entries added by the method tracing facility at
-   the "trace points" the AML interpreter starts/stops to execute a control
-   method, or an AML opcode. Note that the format of the log entries are
-   subject to change:
-     [    0.186427]   exdebug-0398 ex_trace_point        : Method Begin [0xf58394d8:\_SB.PCI0.LPCB.ECOK] execution.
-     [    0.186630]   exdebug-0398 ex_trace_point        : Opcode Begin [0xf5905c88:If] execution.
-     [    0.186820]   exdebug-0398 ex_trace_point        : Opcode Begin [0xf5905cc0:LEqual] execution.
-     [    0.187010]   exdebug-0398 ex_trace_point        : Opcode Begin [0xf5905a20:-NamePath-] execution.
-     [    0.187214]   exdebug-0398 ex_trace_point        : Opcode End [0xf5905a20:-NamePath-] execution.
-     [    0.187407]   exdebug-0398 ex_trace_point        : Opcode Begin [0xf5905f60:One] execution.
-     [    0.187594]   exdebug-0398 ex_trace_point        : Opcode End [0xf5905f60:One] execution.
-     [    0.187789]   exdebug-0398 ex_trace_point        : Opcode End [0xf5905cc0:LEqual] execution.
-     [    0.187980]   exdebug-0398 ex_trace_point        : Opcode Begin [0xf5905cc0:Return] execution.
-     [    0.188146]   exdebug-0398 ex_trace_point        : Opcode Begin [0xf5905f60:One] execution.
-     [    0.188334]   exdebug-0398 ex_trace_point        : Opcode End [0xf5905f60:One] execution.
-     [    0.188524]   exdebug-0398 ex_trace_point        : Opcode End [0xf5905cc0:Return] execution.
-     [    0.188712]   exdebug-0398 ex_trace_point        : Opcode End [0xf5905c88:If] execution.
-     [    0.188903]   exdebug-0398 ex_trace_point        : Method End [0xf58394d8:\_SB.PCI0.LPCB.ECOK] execution.
-
-   Developers can utilize these special log entries to track the AML
-   interpretion, thus can aid issue debugging and performance tuning. Note
-   that, as the "AML tracer" logs are implemented via ACPI_DEBUG_PRINT()
-   macro, CONFIG_ACPI_DEBUG is also required to be enabled for enabling
-   "AML tracer" logs.
-
-   The following command examples illustrate the usage of the "AML tracer"
-   functionality:
-   a. Filter out the method start/stop "AML tracer" logs when control
-      methods are being evaluated:
-      # cd /sys/module/acpi/parameters
-      # echo "0x80" > trace_debug_layer
-      # echo "0x10" > trace_debug_level
-      # echo "enable" > trace_state
-   b. Filter out the method start/stop "AML tracer" when the specified
-      control method is being evaluated:
-      # cd /sys/module/acpi/parameters
-      # echo "0x80" > trace_debug_layer
-      # echo "0x10" > trace_debug_level
-      # echo "\PPPP.AAAA.TTTT.HHHH" > trace_method_name
-      # echo "method" > trace_state
-   c. Filter out the method start/stop "AML tracer" logs when the specified
-      control method is being evaluated for the first time:
-      # cd /sys/module/acpi/parameters
-      # echo "0x80" > trace_debug_layer
-      # echo "0x10" > trace_debug_level
-      # echo "\PPPP.AAAA.TTTT.HHHH" > trace_method_name
-      # echo "method-once" > trace_state
-   d. Filter out the method/opcode start/stop "AML tracer" when the
-      specified control method is being evaluated:
-      # cd /sys/module/acpi/parameters
-      # echo "0x80" > trace_debug_layer
-      # echo "0x10" > trace_debug_level
-      # echo "\PPPP.AAAA.TTTT.HHHH" > trace_method_name
-      # echo "opcode" > trace_state
-   e. Filter out the method/opcode start/stop "AML tracer" when the
-      specified control method is being evaluated for the first time:
-      # cd /sys/module/acpi/parameters
-      # echo "0x80" > trace_debug_layer
-      # echo "0x10" > trace_debug_level
-      # echo "\PPPP.AAAA.TTTT.HHHH" > trace_method_name
-      # echo "opcode-opcode" > trace_state
-
-  Note that all above method tracing facility related module parameters can
-  be used as the boot parameters, for example:
-      acpi.trace_debug_layer=0x80 acpi.trace_debug_level=0x10 \
-      acpi.trace_method_name=\_SB.LID0._LID acpi.trace_state=opcode-once
-
-2. Interface descriptions:
-
-   All method tracing functions can be configured via ACPI module
-   parameters that are accessible at /sys/module/acpi/parameters/:
-
-   trace_method_name
-	The full path of the AML method that the user wants to trace.
-	Note that the full path shouldn't contain the trailing "_"s in its
-	name segments but may contain "\" to form an absolute path.
-
-   trace_debug_layer
-	The temporary debug_layer used when the tracing feature is enabled.
-	Using ACPI_EXECUTER (0x80) by default, which is the debug_layer
-	used to match all "AML tracer" logs.
-
-   trace_debug_level
-	The temporary debug_level used when the tracing feature is enabled.
-	Using ACPI_LV_TRACE_POINT (0x10) by default, which is the
-	debug_level used to match all "AML tracer" logs.
-
-   trace_state
-	The status of the tracing feature.
-	Users can enable/disable this debug tracing feature by executing
-	the following command:
-	    # echo string > /sys/module/acpi/parameters/trace_state
-	Where "string" should be one of the following:
-	"disable"
-	    Disable the method tracing feature.
-	"enable"
-	    Enable the method tracing feature.
-	    ACPICA debugging messages matching
-	    "trace_debug_layer/trace_debug_level" during any method
-	    execution will be logged.
-	"method"
-	    Enable the method tracing feature.
-	    ACPICA debugging messages matching
-	    "trace_debug_layer/trace_debug_level" during method execution
-	    of "trace_method_name" will be logged.
-	"method-once"
-	    Enable the method tracing feature.
-	    ACPICA debugging messages matching
-	    "trace_debug_layer/trace_debug_level" during method execution
-	    of "trace_method_name" will be logged only once.
-	"opcode"
-	    Enable the method tracing feature.
-	    ACPICA debugging messages matching
-	    "trace_debug_layer/trace_debug_level" during method/opcode
-	    execution of "trace_method_name" will be logged.
-	"opcode-once"
-	    Enable the method tracing feature.
-	    ACPICA debugging messages matching
-	    "trace_debug_layer/trace_debug_level" during method/opcode
-	    execution of "trace_method_name" will be logged only once.
-	Note that, the difference between the "enable" and other feature
-        enabling options are:
-	1. When "enable" is specified, since
-	   "trace_debug_layer/trace_debug_level" shall apply to all control
-	   method evaluations, after configuring "trace_state" to "enable",
-	   "trace_method_name" will be reset to NULL.
-	2. When "method/opcode" is specified, if
-	   "trace_method_name" is NULL when "trace_state" is configured to
-	   these options, the "trace_debug_layer/trace_debug_level" will
-	   apply to all control method evaluations.
diff --git a/Documentation/acpi/ssdt-overlays.txt b/Documentation/acpi/ssdt-overlays.txt
deleted file mode 100644
index 5ae13f161ea2..000000000000
--- a/Documentation/acpi/ssdt-overlays.txt
+++ /dev/null
@@ -1,172 +0,0 @@
-
-In order to support ACPI open-ended hardware configurations (e.g. development
-boards) we need a way to augment the ACPI configuration provided by the firmware
-image. A common example is connecting sensors on I2C / SPI buses on development
-boards.
-
-Although this can be accomplished by creating a kernel platform driver or
-recompiling the firmware image with updated ACPI tables, neither is practical:
-the former proliferates board specific kernel code while the latter requires
-access to firmware tools which are often not publicly available.
-
-Because ACPI supports external references in AML code a more practical
-way to augment firmware ACPI configuration is by dynamically loading
-user defined SSDT tables that contain the board specific information.
-
-For example, to enumerate a Bosch BMA222E accelerometer on the I2C bus of the
-Minnowboard MAX development board exposed via the LSE connector [1], the
-following ASL code can be used:
-
-DefinitionBlock ("minnowmax.aml", "SSDT", 1, "Vendor", "Accel", 0x00000003)
-{
-    External (\_SB.I2C6, DeviceObj)
-
-    Scope (\_SB.I2C6)
-    {
-        Device (STAC)
-        {
-            Name (_ADR, Zero)
-            Name (_HID, "BMA222E")
-
-            Method (_CRS, 0, Serialized)
-            {
-                Name (RBUF, ResourceTemplate ()
-                {
-                    I2cSerialBus (0x0018, ControllerInitiated, 0x00061A80,
-                                  AddressingMode7Bit, "\\_SB.I2C6", 0x00,
-                                  ResourceConsumer, ,)
-                    GpioInt (Edge, ActiveHigh, Exclusive, PullDown, 0x0000,
-                             "\\_SB.GPO2", 0x00, ResourceConsumer, , )
-                    { // Pin list
-                        0
-                    }
-                })
-                Return (RBUF)
-            }
-        }
-    }
-}
-
-which can then be compiled to AML binary format:
-
-$ iasl minnowmax.asl
-
-Intel ACPI Component Architecture
-ASL Optimizing Compiler version 20140214-64 [Mar 29 2014]
-Copyright (c) 2000 - 2014 Intel Corporation
-
-ASL Input:     minnomax.asl - 30 lines, 614 bytes, 7 keywords
-AML Output:    minnowmax.aml - 165 bytes, 6 named objects, 1 executable opcodes
-
-[1] http://wiki.minnowboard.org/MinnowBoard_MAX#Low_Speed_Expansion_Connector_.28Top.29
-
-The resulting AML code can then be loaded by the kernel using one of the methods
-below.
-
-== Loading ACPI SSDTs from initrd ==
-
-This option allows loading of user defined SSDTs from initrd and it is useful
-when the system does not support EFI or when there is not enough EFI storage.
-
-It works in a similar way with initrd based ACPI tables override/upgrade: SSDT
-aml code must be placed in the first, uncompressed, initrd under the
-"kernel/firmware/acpi" path. Multiple files can be used and this will translate
-in loading multiple tables. Only SSDT and OEM tables are allowed. See
-initrd_table_override.txt for more details.
-
-Here is an example:
-
-# Add the raw ACPI tables to an uncompressed cpio archive.
-# They must be put into a /kernel/firmware/acpi directory inside the
-# cpio archive.
-# The uncompressed cpio archive must be the first.
-# Other, typically compressed cpio archives, must be
-# concatenated on top of the uncompressed one.
-mkdir -p kernel/firmware/acpi
-cp ssdt.aml kernel/firmware/acpi
-
-# Create the uncompressed cpio archive and concatenate the original initrd
-# on top:
-find kernel | cpio -H newc --create > /boot/instrumented_initrd
-cat /boot/initrd >>/boot/instrumented_initrd
-
-== Loading ACPI SSDTs from EFI variables ==
-
-This is the preferred method, when EFI is supported on the platform, because it
-allows a persistent, OS independent way of storing the user defined SSDTs. There
-is also work underway to implement EFI support for loading user defined SSDTs
-and using this method will make it easier to convert to the EFI loading
-mechanism when that will arrive.
-
-In order to load SSDTs from an EFI variable the efivar_ssdt kernel command line
-parameter can be used. The argument for the option is the variable name to
-use. If there are multiple variables with the same name but with different
-vendor GUIDs, all of them will be loaded.
-
-In order to store the AML code in an EFI variable the efivarfs filesystem can be
-used. It is enabled and mounted by default in /sys/firmware/efi/efivars in all
-recent distribution.
-
-Creating a new file in /sys/firmware/efi/efivars will automatically create a new
-EFI variable. Updating a file in /sys/firmware/efi/efivars will update the EFI
-variable. Please note that the file name needs to be specially formatted as
-"Name-GUID" and that the first 4 bytes in the file (little-endian format)
-represent the attributes of the EFI variable (see EFI_VARIABLE_MASK in
-include/linux/efi.h). Writing to the file must also be done with one write
-operation.
-
-For example, you can use the following bash script to create/update an EFI
-variable with the content from a given file:
-
-#!/bin/sh -e
-
-while ! [ -z "$1" ]; do
-        case "$1" in
-        "-f") filename="$2"; shift;;
-        "-g") guid="$2"; shift;;
-        *) name="$1";;
-        esac
-        shift
-done
-
-usage()
-{
-        echo "Syntax: ${0##*/} -f filename [ -g guid ] name"
-        exit 1
-}
-
-[ -n "$name" -a -f "$filename" ] || usage
-
-EFIVARFS="/sys/firmware/efi/efivars"
-
-[ -d "$EFIVARFS" ] || exit 2
-
-if stat -tf $EFIVARFS | grep -q -v de5e81e4; then
-        mount -t efivarfs none $EFIVARFS
-fi
-
-# try to pick up an existing GUID
-[ -n "$guid" ] || guid=$(find "$EFIVARFS" -name "$name-*" | head -n1 | cut -f2- -d-)
-
-# use a randomly generated GUID
-[ -n "$guid" ] || guid="$(cat /proc/sys/kernel/random/uuid)"
-
-# efivarfs expects all of the data in one write
-tmp=$(mktemp)
-/bin/echo -ne "\007\000\000\000" | cat - $filename > $tmp
-dd if=$tmp of="$EFIVARFS/$name-$guid" bs=$(stat -c %s $tmp)
-rm $tmp
-
-== Loading ACPI SSDTs from configfs ==
-
-This option allows loading of user defined SSDTs from userspace via the configfs
-interface. The CONFIG_ACPI_CONFIGFS option must be select and configfs must be
-mounted. In the following examples, we assume that configfs has been mounted in
-/config.
-
-New tables can be loading by creating new directories in /config/acpi/table/ and
-writing the SSDT aml code in the aml attribute:
-
-cd /config/acpi/table
-mkdir my_ssdt
-cat ~/ssdt.aml > my_ssdt/aml
diff --git a/Documentation/acpi/cppc_sysfs.txt b/Documentation/admin-guide/acpi/cppc_sysfs.rst
index f20fb445135d..a4b99afbe331 100644
--- a/Documentation/acpi/cppc_sysfs.txt
+++ b/Documentation/admin-guide/acpi/cppc_sysfs.rst
@@ -1,5 +1,11 @@
+.. SPDX-License-Identifier: GPL-2.0
 
-	Collaborative Processor Performance Control (CPPC)
+==================================================
+Collaborative Processor Performance Control (CPPC)
+==================================================
+
+CPPC
+====
 
 CPPC defined in the ACPI spec describes a mechanism for the OS to manage the
 performance of a logical processor on a contigious and abstract performance
@@ -10,31 +16,28 @@ For more details on CPPC please refer to the ACPI specification at:
 
 http://uefi.org/specifications
 
-Some of the CPPC registers are exposed via sysfs under:
-
-/sys/devices/system/cpu/cpuX/acpi_cppc/
-
-for each cpu X
+Some of the CPPC registers are exposed via sysfs under::
 
---------------------------------------------------------------------------------
+  /sys/devices/system/cpu/cpuX/acpi_cppc/
 
-$ ls -lR  /sys/devices/system/cpu/cpu0/acpi_cppc/
-/sys/devices/system/cpu/cpu0/acpi_cppc/:
-total 0
--r--r--r-- 1 root root 65536 Mar  5 19:38 feedback_ctrs
--r--r--r-- 1 root root 65536 Mar  5 19:38 highest_perf
--r--r--r-- 1 root root 65536 Mar  5 19:38 lowest_freq
--r--r--r-- 1 root root 65536 Mar  5 19:38 lowest_nonlinear_perf
--r--r--r-- 1 root root 65536 Mar  5 19:38 lowest_perf
--r--r--r-- 1 root root 65536 Mar  5 19:38 nominal_freq
--r--r--r-- 1 root root 65536 Mar  5 19:38 nominal_perf
--r--r--r-- 1 root root 65536 Mar  5 19:38 reference_perf
--r--r--r-- 1 root root 65536 Mar  5 19:38 wraparound_time
+for each cpu X::
 
---------------------------------------------------------------------------------
+  $ ls -lR  /sys/devices/system/cpu/cpu0/acpi_cppc/
+  /sys/devices/system/cpu/cpu0/acpi_cppc/:
+  total 0
+  -r--r--r-- 1 root root 65536 Mar  5 19:38 feedback_ctrs
+  -r--r--r-- 1 root root 65536 Mar  5 19:38 highest_perf
+  -r--r--r-- 1 root root 65536 Mar  5 19:38 lowest_freq
+  -r--r--r-- 1 root root 65536 Mar  5 19:38 lowest_nonlinear_perf
+  -r--r--r-- 1 root root 65536 Mar  5 19:38 lowest_perf
+  -r--r--r-- 1 root root 65536 Mar  5 19:38 nominal_freq
+  -r--r--r-- 1 root root 65536 Mar  5 19:38 nominal_perf
+  -r--r--r-- 1 root root 65536 Mar  5 19:38 reference_perf
+  -r--r--r-- 1 root root 65536 Mar  5 19:38 wraparound_time
 
 * highest_perf : Highest performance of this processor (abstract scale).
-* nominal_perf : Highest sustained performance of this processor (abstract scale).
+* nominal_perf : Highest sustained performance of this processor
+  (abstract scale).
 * lowest_nonlinear_perf : Lowest performance of this processor with nonlinear
   power savings (abstract scale).
 * lowest_perf : Lowest performance of this processor (abstract scale).
@@ -48,22 +51,26 @@ total 0
 * feedback_ctrs : Includes both Reference and delivered performance counter.
   Reference counter ticks up proportional to processor's reference performance.
   Delivered counter ticks up proportional to processor's delivered performance.
-* wraparound_time: Minimum time for the feedback counters to wraparound (seconds).
+* wraparound_time: Minimum time for the feedback counters to wraparound
+  (seconds).
 * reference_perf : Performance level at which reference performance counter
   accumulates (abstract scale).
 
---------------------------------------------------------------------------------
 
-		Computing Average Delivered Performance
+Computing Average Delivered Performance
+=======================================
+
+Below describes the steps to compute the average performance delivered by
+taking two different snapshots of feedback counters at time T1 and T2.
+
+  T1: Read feedback_ctrs as fbc_t1
+      Wait or run some workload
 
-Below describes the steps to compute the average performance delivered by taking
-two different snapshots of feedback counters at time T1 and T2.
+  T2: Read feedback_ctrs as fbc_t2
 
-T1: Read feedback_ctrs as fbc_t1
-    Wait or run some workload
-T2: Read feedback_ctrs as fbc_t2
+::
 
-delivered_counter_delta = fbc_t2[del] - fbc_t1[del]
-reference_counter_delta = fbc_t2[ref] - fbc_t1[ref]
+  delivered_counter_delta = fbc_t2[del] - fbc_t1[del]
+  reference_counter_delta = fbc_t2[ref] - fbc_t1[ref]
 
-delivered_perf = (refernce_perf x delivered_counter_delta) / reference_counter_delta
+  delivered_perf = (refernce_perf x delivered_counter_delta) / reference_counter_delta
diff --git a/Documentation/acpi/dsdt-override.txt b/Documentation/admin-guide/acpi/dsdt-override.rst
index 784841caa6e6..50bd7f194bf4 100644
--- a/Documentation/acpi/dsdt-override.txt
+++ b/Documentation/admin-guide/acpi/dsdt-override.rst
@@ -1,6 +1,12 @@
+.. SPDX-License-Identifier: GPL-2.0
+
+===============
+Overriding DSDT
+===============
+
 Linux supports a method of overriding the BIOS DSDT:
 
-CONFIG_ACPI_CUSTOM_DSDT builds the image into the kernel.
+CONFIG_ACPI_CUSTOM_DSDT - builds the image into the kernel.
 
 When to use this method is described in detail on the
 Linux/ACPI home page:
diff --git a/Documentation/admin-guide/acpi/index.rst b/Documentation/admin-guide/acpi/index.rst
new file mode 100644
index 000000000000..4d13eeea1eca
--- /dev/null
+++ b/Documentation/admin-guide/acpi/index.rst
@@ -0,0 +1,14 @@
+============
+ACPI Support
+============
+
+Here we document in detail how to interact with various mechanisms in
+the Linux ACPI support.
+
+.. toctree::
+   :maxdepth: 1
+
+   initrd_table_override
+   dsdt-override
+   ssdt-overlays
+   cppc_sysfs
diff --git a/Documentation/admin-guide/acpi/initrd_table_override.rst b/Documentation/admin-guide/acpi/initrd_table_override.rst
new file mode 100644
index 000000000000..cbd768207631
--- /dev/null
+++ b/Documentation/admin-guide/acpi/initrd_table_override.rst
@@ -0,0 +1,115 @@
+.. SPDX-License-Identifier: GPL-2.0
+
+================================
+Upgrading ACPI tables via initrd
+================================
+
+What is this about
+==================
+
+If the ACPI_TABLE_UPGRADE compile option is true, it is possible to
+upgrade the ACPI execution environment that is defined by the ACPI tables
+via upgrading the ACPI tables provided by the BIOS with an instrumented,
+modified, more recent version one, or installing brand new ACPI tables.
+
+When building initrd with kernel in a single image, option
+ACPI_TABLE_OVERRIDE_VIA_BUILTIN_INITRD should also be true for this
+feature to work.
+
+For a full list of ACPI tables that can be upgraded/installed, take a look
+at the char `*table_sigs[MAX_ACPI_SIGNATURE];` definition in
+drivers/acpi/tables.c.
+
+All ACPI tables iasl (Intel's ACPI compiler and disassembler) knows should
+be overridable, except:
+
+  - ACPI_SIG_RSDP (has a signature of 6 bytes)
+  - ACPI_SIG_FACS (does not have an ordinary ACPI table header)
+
+Both could get implemented as well.
+
+
+What is this for
+================
+
+Complain to your platform/BIOS vendor if you find a bug which is so severe
+that a workaround is not accepted in the Linux kernel. And this facility
+allows you to upgrade the buggy tables before your platform/BIOS vendor
+releases an upgraded BIOS binary.
+
+This facility can be used by platform/BIOS vendors to provide a Linux
+compatible environment without modifying the underlying platform firmware.
+
+This facility also provides a powerful feature to easily debug and test
+ACPI BIOS table compatibility with the Linux kernel by modifying old
+platform provided ACPI tables or inserting new ACPI tables.
+
+It can and should be enabled in any kernel because there is no functional
+change with not instrumented initrds.
+
+
+How does it work
+================
+::
+
+  # Extract the machine's ACPI tables:
+  cd /tmp
+  acpidump >acpidump
+  acpixtract -a acpidump
+  # Disassemble, modify and recompile them:
+  iasl -d *.dat
+  # For example add this statement into a _PRT (PCI Routing Table) function
+  # of the DSDT:
+  Store("HELLO WORLD", debug)
+  # And increase the OEM Revision. For example, before modification:
+  DefinitionBlock ("DSDT.aml", "DSDT", 2, "INTEL ", "TEMPLATE", 0x00000000)
+  # After modification:
+  DefinitionBlock ("DSDT.aml", "DSDT", 2, "INTEL ", "TEMPLATE", 0x00000001)
+  iasl -sa dsdt.dsl
+  # Add the raw ACPI tables to an uncompressed cpio archive.
+  # They must be put into a /kernel/firmware/acpi directory inside the cpio
+  # archive. Note that if the table put here matches a platform table
+  # (similar Table Signature, and similar OEMID, and similar OEM Table ID)
+  # with a more recent OEM Revision, the platform table will be upgraded by
+  # this table. If the table put here doesn't match a platform table
+  # (dissimilar Table Signature, or dissimilar OEMID, or dissimilar OEM Table
+  # ID), this table will be appended.
+  mkdir -p kernel/firmware/acpi
+  cp dsdt.aml kernel/firmware/acpi
+  # A maximum of "NR_ACPI_INITRD_TABLES (64)" tables are currently allowed
+  # (see osl.c):
+  iasl -sa facp.dsl
+  iasl -sa ssdt1.dsl
+  cp facp.aml kernel/firmware/acpi
+  cp ssdt1.aml kernel/firmware/acpi
+  # The uncompressed cpio archive must be the first. Other, typically
+  # compressed cpio archives, must be concatenated on top of the uncompressed
+  # one. Following command creates the uncompressed cpio archive and
+  # concatenates the original initrd on top:
+  find kernel | cpio -H newc --create > /boot/instrumented_initrd
+  cat /boot/initrd >>/boot/instrumented_initrd
+  # reboot with increased acpi debug level, e.g. boot params:
+  acpi.debug_level=0x2 acpi.debug_layer=0xFFFFFFFF
+  # and check your syslog:
+  [    1.268089] ACPI: PCI Interrupt Routing Table [\_SB_.PCI0._PRT]
+  [    1.272091] [ACPI Debug]  String [0x0B] "HELLO WORLD"
+
+iasl is able to disassemble and recompile quite a lot different,
+also static ACPI tables.
+
+
+Where to retrieve userspace tools
+=================================
+
+iasl and acpixtract are part of Intel's ACPICA project:
+http://acpica.org/
+
+and should be packaged by distributions (for example in the acpica package
+on SUSE).
+
+acpidump can be found in Len Browns pmtools:
+ftp://kernel.org/pub/linux/kernel/people/lenb/acpi/utils/pmtools/acpidump
+
+This tool is also part of the acpica package on SUSE.
+Alternatively, used ACPI tables can be retrieved via sysfs in latest kernels:
+/sys/firmware/acpi/tables
diff --git a/Documentation/admin-guide/acpi/ssdt-overlays.rst b/Documentation/admin-guide/acpi/ssdt-overlays.rst
new file mode 100644
index 000000000000..da37455f96c9
--- /dev/null
+++ b/Documentation/admin-guide/acpi/ssdt-overlays.rst
@@ -0,0 +1,180 @@
+.. SPDX-License-Identifier: GPL-2.0
+
+=============
+SSDT Overlays
+=============
+
+In order to support ACPI open-ended hardware configurations (e.g. development
+boards) we need a way to augment the ACPI configuration provided by the firmware
+image. A common example is connecting sensors on I2C / SPI buses on development
+boards.
+
+Although this can be accomplished by creating a kernel platform driver or
+recompiling the firmware image with updated ACPI tables, neither is practical:
+the former proliferates board specific kernel code while the latter requires
+access to firmware tools which are often not publicly available.
+
+Because ACPI supports external references in AML code a more practical
+way to augment firmware ACPI configuration is by dynamically loading
+user defined SSDT tables that contain the board specific information.
+
+For example, to enumerate a Bosch BMA222E accelerometer on the I2C bus of the
+Minnowboard MAX development board exposed via the LSE connector [1], the
+following ASL code can be used::
+
+    DefinitionBlock ("minnowmax.aml", "SSDT", 1, "Vendor", "Accel", 0x00000003)
+    {
+        External (\_SB.I2C6, DeviceObj)
+
+        Scope (\_SB.I2C6)
+        {
+            Device (STAC)
+            {
+                Name (_ADR, Zero)
+                Name (_HID, "BMA222E")
+
+                Method (_CRS, 0, Serialized)
+                {
+                    Name (RBUF, ResourceTemplate ()
+                    {
+                        I2cSerialBus (0x0018, ControllerInitiated, 0x00061A80,
+                                    AddressingMode7Bit, "\\_SB.I2C6", 0x00,
+                                    ResourceConsumer, ,)
+                        GpioInt (Edge, ActiveHigh, Exclusive, PullDown, 0x0000,
+                                "\\_SB.GPO2", 0x00, ResourceConsumer, , )
+                        { // Pin list
+                            0
+                        }
+                    })
+                    Return (RBUF)
+                }
+            }
+        }
+    }
+
+which can then be compiled to AML binary format::
+
+    $ iasl minnowmax.asl
+
+    Intel ACPI Component Architecture
+    ASL Optimizing Compiler version 20140214-64 [Mar 29 2014]
+    Copyright (c) 2000 - 2014 Intel Corporation
+
+    ASL Input:     minnomax.asl - 30 lines, 614 bytes, 7 keywords
+    AML Output:    minnowmax.aml - 165 bytes, 6 named objects, 1 executable opcodes
+
+[1] http://wiki.minnowboard.org/MinnowBoard_MAX#Low_Speed_Expansion_Connector_.28Top.29
+
+The resulting AML code can then be loaded by the kernel using one of the methods
+below.
+
+Loading ACPI SSDTs from initrd
+==============================
+
+This option allows loading of user defined SSDTs from initrd and it is useful
+when the system does not support EFI or when there is not enough EFI storage.
+
+It works in a similar way with initrd based ACPI tables override/upgrade: SSDT
+aml code must be placed in the first, uncompressed, initrd under the
+"kernel/firmware/acpi" path. Multiple files can be used and this will translate
+in loading multiple tables. Only SSDT and OEM tables are allowed. See
+initrd_table_override.txt for more details.
+
+Here is an example::
+
+    # Add the raw ACPI tables to an uncompressed cpio archive.
+    # They must be put into a /kernel/firmware/acpi directory inside the
+    # cpio archive.
+    # The uncompressed cpio archive must be the first.
+    # Other, typically compressed cpio archives, must be
+    # concatenated on top of the uncompressed one.
+    mkdir -p kernel/firmware/acpi
+    cp ssdt.aml kernel/firmware/acpi
+
+    # Create the uncompressed cpio archive and concatenate the original initrd
+    # on top:
+    find kernel | cpio -H newc --create > /boot/instrumented_initrd
+    cat /boot/initrd >>/boot/instrumented_initrd
+
+Loading ACPI SSDTs from EFI variables
+=====================================
+
+This is the preferred method, when EFI is supported on the platform, because it
+allows a persistent, OS independent way of storing the user defined SSDTs. There
+is also work underway to implement EFI support for loading user defined SSDTs
+and using this method will make it easier to convert to the EFI loading
+mechanism when that will arrive.
+
+In order to load SSDTs from an EFI variable the efivar_ssdt kernel command line
+parameter can be used. The argument for the option is the variable name to
+use. If there are multiple variables with the same name but with different
+vendor GUIDs, all of them will be loaded.
+
+In order to store the AML code in an EFI variable the efivarfs filesystem can be
+used. It is enabled and mounted by default in /sys/firmware/efi/efivars in all
+recent distribution.
+
+Creating a new file in /sys/firmware/efi/efivars will automatically create a new
+EFI variable. Updating a file in /sys/firmware/efi/efivars will update the EFI
+variable. Please note that the file name needs to be specially formatted as
+"Name-GUID" and that the first 4 bytes in the file (little-endian format)
+represent the attributes of the EFI variable (see EFI_VARIABLE_MASK in
+include/linux/efi.h). Writing to the file must also be done with one write
+operation.
+
+For example, you can use the following bash script to create/update an EFI
+variable with the content from a given file::
+
+    #!/bin/sh -e
+
+    while ! [ -z "$1" ]; do
+            case "$1" in
+            "-f") filename="$2"; shift;;
+            "-g") guid="$2"; shift;;
+            *) name="$1";;
+            esac
+            shift
+    done
+
+    usage()
+    {
+            echo "Syntax: ${0##*/} -f filename [ -g guid ] name"
+            exit 1
+    }
+
+    [ -n "$name" -a -f "$filename" ] || usage
+
+    EFIVARFS="/sys/firmware/efi/efivars"
+
+    [ -d "$EFIVARFS" ] || exit 2
+
+    if stat -tf $EFIVARFS | grep -q -v de5e81e4; then
+            mount -t efivarfs none $EFIVARFS
+    fi
+
+    # try to pick up an existing GUID
+    [ -n "$guid" ] || guid=$(find "$EFIVARFS" -name "$name-*" | head -n1 | cut -f2- -d-)
+
+    # use a randomly generated GUID
+    [ -n "$guid" ] || guid="$(cat /proc/sys/kernel/random/uuid)"
+
+    # efivarfs expects all of the data in one write
+    tmp=$(mktemp)
+    /bin/echo -ne "\007\000\000\000" | cat - $filename > $tmp
+    dd if=$tmp of="$EFIVARFS/$name-$guid" bs=$(stat -c %s $tmp)
+    rm $tmp
+
+Loading ACPI SSDTs from configfs
+================================
+
+This option allows loading of user defined SSDTs from userspace via the configfs
+interface. The CONFIG_ACPI_CONFIGFS option must be select and configfs must be
+mounted. In the following examples, we assume that configfs has been mounted in
+/config.
+
+New tables can be loading by creating new directories in /config/acpi/table/ and
+writing the SSDT aml code in the aml attribute::
+
+    cd /config/acpi/table
+    mkdir my_ssdt
+    cat ~/ssdt.aml > my_ssdt/aml
diff --git a/Documentation/admin-guide/index.rst b/Documentation/admin-guide/index.rst
index 0a491676685e..5b8286fdd91b 100644
--- a/Documentation/admin-guide/index.rst
+++ b/Documentation/admin-guide/index.rst
@@ -77,6 +77,7 @@ configure specific aspects of kernel behavior to your liking.
    LSM/index
    mm/index
    perf-security
+   acpi/index
 
 .. only::  subproject and html
 
diff --git a/Documentation/admin-guide/kernel-parameters.rst b/Documentation/admin-guide/kernel-parameters.rst
index b8d0bc07ed0a..0124980dca2d 100644
--- a/Documentation/admin-guide/kernel-parameters.rst
+++ b/Documentation/admin-guide/kernel-parameters.rst
@@ -88,6 +88,7 @@ parameter is applicable::
 	APIC	APIC support is enabled.
 	APM	Advanced Power Management support is enabled.
 	ARM	ARM architecture is enabled.
+	ARM64	ARM64 architecture is enabled.
 	AX25	Appropriate AX.25 support is enabled.
 	CLK	Common clock infrastructure is enabled.
 	CMA	Contiguous Memory Area support is enabled.
diff --git a/Documentation/admin-guide/kernel-parameters.txt b/Documentation/admin-guide/kernel-parameters.txt
index 2b8ee90bb644..fd03e2b629bb 100644
--- a/Documentation/admin-guide/kernel-parameters.txt
+++ b/Documentation/admin-guide/kernel-parameters.txt
@@ -704,8 +704,11 @@
 			upon panic. This parameter reserves the physical
 			memory region [offset, offset + size] for that kernel
 			image. If '@offset' is omitted, then a suitable offset
-			is selected automatically. Check
-			Documentation/kdump/kdump.txt for further details.
+			is selected automatically.
+			[KNL, x86_64] select a region under 4G first, and
+			fall back to reserve region above 4G when '@offset'
+			hasn't been specified.
+			See Documentation/kdump/kdump.txt for further details.
 
 	crashkernel=range1:size1[,range2:size2,...][@offset]
 			[KNL] Same as above, but depends on the memory
@@ -2544,6 +2547,40 @@
 			in the "bleeding edge" mini2440 support kernel at
 			http://repo.or.cz/w/linux-2.6/mini2440.git
 
+	mitigations=
+			[X86,PPC,S390,ARM64] Control optional mitigations for
+			CPU vulnerabilities.  This is a set of curated,
+			arch-independent options, each of which is an
+			aggregation of existing arch-specific options.
+
+			off
+				Disable all optional CPU mitigations.  This
+				improves system performance, but it may also
+				expose users to several CPU vulnerabilities.
+				Equivalent to: nopti [X86,PPC]
+					       kpti=0 [ARM64]
+					       nospectre_v1 [PPC]
+					       nobp=0 [S390]
+					       nospectre_v2 [X86,PPC,S390,ARM64]
+					       spectre_v2_user=off [X86]
+					       spec_store_bypass_disable=off [X86,PPC]
+					       ssbd=force-off [ARM64]
+					       l1tf=off [X86]
+
+			auto (default)
+				Mitigate all CPU vulnerabilities, but leave SMT
+				enabled, even if it's vulnerable.  This is for
+				users who don't want to be surprised by SMT
+				getting disabled across kernel upgrades, or who
+				have other ways of avoiding SMT-based attacks.
+				Equivalent to: (default behavior)
+
+			auto,nosmt
+				Mitigate all CPU vulnerabilities, disabling SMT
+				if needed.  This is for users who always want to
+				be fully mitigated, even if it means losing SMT.
+				Equivalent to: l1tf=flush,nosmt [X86]
+
 	mminit_loglevel=
 			[KNL] When CONFIG_DEBUG_MEMORY_INIT is set, this
 			parameter allows control of the logging verbosity for
@@ -2873,10 +2910,10 @@
 			check bypass). With this option data leaks are possible
 			in the system.
 
-	nospectre_v2	[X86,PPC_FSL_BOOK3E] Disable all mitigations for the Spectre variant 2
-			(indirect branch prediction) vulnerability. System may
-			allow data leaks with this option, which is equivalent
-			to spectre_v2=off.
+	nospectre_v2	[X86,PPC_FSL_BOOK3E,ARM64] Disable all mitigations for
+			the Spectre variant 2 (indirect branch prediction)
+			vulnerability. System may allow data leaks with this
+			option.
 
 	nospec_store_bypass_disable
 			[HW] Disable all mitigations for the Speculative Store Bypass vulnerability
@@ -3394,6 +3431,8 @@
 				bridges without forcing it upstream. Note:
 				this removes isolation between devices and
 				may put more devices in an IOMMU group.
+		force_floating	[S390] Force usage of floating interrupts.
+		nomio		[S390] Do not use MIO instructions.
 
 	pcie_aspm=	[PCIE] Forcibly enable or disable PCIe Active State Power
 			Management.
@@ -3623,7 +3662,9 @@
 				see CONFIG_RAS_CEC help text.
 
 	rcu_nocbs=	[KNL]
-			The argument is a cpu list, as described above.
+			The argument is a cpu list, as described above,
+			except that the string "all" can be used to
+			specify every CPU on the system.
 
 			In kernels built with CONFIG_RCU_NOCB_CPU=y, set
 			the specified list of CPUs to be no-callback CPUs.
@@ -4703,6 +4744,10 @@
 			[x86] unstable: mark the TSC clocksource as unstable, this
 			marks the TSC unconditionally unstable at bootup and
 			avoids any further wobbles once the TSC watchdog notices.
+			[x86] nowatchdog: disable clocksource watchdog. Used
+			in situations with strict latency requirements (where
+			interruptions from clocksource watchdog are not
+			acceptable).
 
 	turbografx.map[2|3]=	[HW,JOY]
 			TurboGraFX parallel port interface
diff --git a/Documentation/admin-guide/pm/cpufreq.rst b/Documentation/admin-guide/pm/cpufreq.rst
index 7eca9026a9ed..0c74a7784964 100644
--- a/Documentation/admin-guide/pm/cpufreq.rst
+++ b/Documentation/admin-guide/pm/cpufreq.rst
@@ -1,3 +1,6 @@
+.. SPDX-License-Identifier: GPL-2.0
+.. include:: <isonum.txt>
+
 .. |struct cpufreq_policy| replace:: :c:type:`struct cpufreq_policy <cpufreq_policy>`
 .. |intel_pstate| replace:: :doc:`intel_pstate <intel_pstate>`
 
@@ -5,9 +8,10 @@
 CPU Performance Scaling
 =======================
 
-::
+:Copyright: |copy| 2017 Intel Corporation
+
+:Author: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
 
- Copyright (c) 2017 Intel Corp., Rafael J. Wysocki <rafael.j.wysocki@intel.com>
 
 The Concept of CPU Performance Scaling
 ======================================
@@ -396,8 +400,8 @@ RT or deadline scheduling classes, the governor will increase the frequency to
 the allowed maximum (that is, the ``scaling_max_freq`` policy limit).  In turn,
 if it is invoked by the CFS scheduling class, the governor will use the
 Per-Entity Load Tracking (PELT) metric for the root control group of the
-given CPU as the CPU utilization estimate (see the `Per-entity load tracking`_
-LWN.net article for a description of the PELT mechanism).  Then, the new
+given CPU as the CPU utilization estimate (see the *Per-entity load tracking*
+LWN.net article [1]_ for a description of the PELT mechanism).  Then, the new
 CPU frequency to apply is computed in accordance with the formula
 
 	f = 1.25 * ``f_0`` * ``util`` / ``max``
@@ -698,4 +702,8 @@ hardware feature (e.g. all Intel ones), even if the
 :c:macro:`CONFIG_X86_ACPI_CPUFREQ_CPB` configuration option is set.
 
 
-.. _Per-entity load tracking: https://lwn.net/Articles/531853/
+References
+==========
+
+.. [1] Jonathan Corbet, *Per-entity load tracking*,
+       https://lwn.net/Articles/531853/
diff --git a/Documentation/admin-guide/pm/cpuidle.rst b/Documentation/admin-guide/pm/cpuidle.rst
index 9c58b35a81cb..e70b365dbc60 100644
--- a/Documentation/admin-guide/pm/cpuidle.rst
+++ b/Documentation/admin-guide/pm/cpuidle.rst
@@ -1,3 +1,6 @@
+.. SPDX-License-Identifier: GPL-2.0
+.. include:: <isonum.txt>
+
 .. |struct cpuidle_state| replace:: :c:type:`struct cpuidle_state <cpuidle_state>`
 .. |cpufreq| replace:: :doc:`CPU Performance Scaling <cpufreq>`
 
@@ -5,9 +8,10 @@
 CPU Idle Time Management
 ========================
 
-::
+:Copyright: |copy| 2018 Intel Corporation
+
+:Author: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
 
- Copyright (c) 2018 Intel Corp., Rafael J. Wysocki <rafael.j.wysocki@intel.com>
 
 Concepts
 ========
diff --git a/Documentation/admin-guide/pm/index.rst b/Documentation/admin-guide/pm/index.rst
index 49237ac73442..39f8f9f81e7a 100644
--- a/Documentation/admin-guide/pm/index.rst
+++ b/Documentation/admin-guide/pm/index.rst
@@ -1,3 +1,5 @@
+.. SPDX-License-Identifier: GPL-2.0
+
 ================
 Power Management
 ================
diff --git a/Documentation/admin-guide/pm/intel_epb.rst b/Documentation/admin-guide/pm/intel_epb.rst
new file mode 100644
index 000000000000..005121167af7
--- /dev/null
+++ b/Documentation/admin-guide/pm/intel_epb.rst
@@ -0,0 +1,41 @@
+.. SPDX-License-Identifier: GPL-2.0
+.. include:: <isonum.txt>
+
+======================================
+Intel Performance and Energy Bias Hint
+======================================
+
+:Copyright: |copy| 2019 Intel Corporation
+
+:Author: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
+
+
+.. kernel-doc:: arch/x86/kernel/cpu/intel_epb.c
+   :doc: overview
+
+Intel Performance and Energy Bias Attribute in ``sysfs``
+========================================================
+
+The Intel Performance and Energy Bias Hint (EPB) value for a given (logical) CPU
+can be checked or updated through a ``sysfs`` attribute (file) under
+:file:`/sys/devices/system/cpu/cpu<N>/power/`, where the CPU number ``<N>``
+is allocated at the system initialization time:
+
+``energy_perf_bias``
+	Shows the current EPB value for the CPU in a sliding scale 0 - 15, where
+	a value of 0 corresponds to a hint preference for highest performance
+	and a value of 15 corresponds to the maximum energy savings.
+
+	In order to update the EPB value for the CPU, this attribute can be
+	written to, either with a number in the 0 - 15 sliding scale above, or
+	with one of the strings: "performance", "balance-performance", "normal",
+	"balance-power", "power" that represent values reflected by their
+	meaning.
+
+	This attribute is present for all online CPUs supporting the EPB
+	feature.
+
+Note that while the EPB interface to the processor is defined at the logical CPU
+level, the physical register backing it may be shared by multiple CPUs (for
+example, SMT siblings or cores in one package).  For this reason, updating the
+EPB value for one CPU may cause the EPB values for other CPUs to change.
diff --git a/Documentation/admin-guide/pm/intel_pstate.rst b/Documentation/admin-guide/pm/intel_pstate.rst
index ec0f7c111f65..67e414e34f37 100644
--- a/Documentation/admin-guide/pm/intel_pstate.rst
+++ b/Documentation/admin-guide/pm/intel_pstate.rst
@@ -1,10 +1,13 @@
+.. SPDX-License-Identifier: GPL-2.0
+.. include:: <isonum.txt>
+
 ===============================================
 ``intel_pstate`` CPU Performance Scaling Driver
 ===============================================
 
-::
+:Copyright: |copy| 2017 Intel Corporation
 
- Copyright (c) 2017 Intel Corp., Rafael J. Wysocki <rafael.j.wysocki@intel.com>
+:Author: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
 
 
 General Information
@@ -20,11 +23,10 @@ you have not done that yet.]
 
 For the processors supported by ``intel_pstate``, the P-state concept is broader
 than just an operating frequency or an operating performance point (see the
-`LinuxCon Europe 2015 presentation by Kristen Accardi <LCEU2015_>`_ for more
+LinuxCon Europe 2015 presentation by Kristen Accardi [1]_ for more
 information about that).  For this reason, the representation of P-states used
 by ``intel_pstate`` internally follows the hardware specification (for details
-refer to `Intel® 64 and IA-32 Architectures Software Developer’s Manual
-Volume 3: System Programming Guide <SDM_>`_).  However, the ``CPUFreq`` core
+refer to Intel Software Developer’s Manual [2]_).  However, the ``CPUFreq`` core
 uses frequencies for identifying operating performance points of CPUs and
 frequencies are involved in the user space interface exposed by it, so
 ``intel_pstate`` maps its internal representation of P-states to frequencies too
@@ -561,9 +563,9 @@ or to pin every task potentially sensitive to them to a specific CPU.]
 
 On the majority of systems supported by ``intel_pstate``, the ACPI tables
 provided by the platform firmware contain ``_PSS`` objects returning information
-that can be used for CPU performance scaling (refer to the `ACPI specification`_
-for details on the ``_PSS`` objects and the format of the information returned
-by them).
+that can be used for CPU performance scaling (refer to the ACPI specification
+[3]_ for details on the ``_PSS`` objects and the format of the information
+returned by them).
 
 The information returned by the ACPI ``_PSS`` objects is used by the
 ``acpi-cpufreq`` scaling driver.  On systems supported by ``intel_pstate``
@@ -728,6 +730,14 @@ P-state is called, the ``ftrace`` filter can be set to to
            <idle>-0     [000] ..s.  2537.654843: intel_pstate_set_pstate <-intel_pstate_timer_func
 
 
-.. _LCEU2015: http://events.linuxfoundation.org/sites/events/files/slides/LinuxConEurope_2015.pdf
-.. _SDM: http://www.intel.com/content/www/us/en/architecture-and-technology/64-ia-32-architectures-software-developer-system-programming-manual-325384.html
-.. _ACPI specification: http://www.uefi.org/sites/default/files/resources/ACPI_6_1.pdf
+References
+==========
+
+.. [1] Kristen Accardi, *Balancing Power and Performance in the Linux Kernel*,
+       http://events.linuxfoundation.org/sites/events/files/slides/LinuxConEurope_2015.pdf
+
+.. [2] *Intel® 64 and IA-32 Architectures Software Developer’s Manual Volume 3: System Programming Guide*,
+       http://www.intel.com/content/www/us/en/architecture-and-technology/64-ia-32-architectures-software-developer-system-programming-manual-325384.html
+
+.. [3] *Advanced Configuration and Power Interface Specification*,
+       https://uefi.org/sites/default/files/resources/ACPI_6_3_final_Jan30.pdf
diff --git a/Documentation/admin-guide/pm/sleep-states.rst b/Documentation/admin-guide/pm/sleep-states.rst
index dbf5acd49f35..cd3a28cb81f4 100644
--- a/Documentation/admin-guide/pm/sleep-states.rst
+++ b/Documentation/admin-guide/pm/sleep-states.rst
@@ -1,10 +1,14 @@
+.. SPDX-License-Identifier: GPL-2.0
+.. include:: <isonum.txt>
+
 ===================
 System Sleep States
 ===================
 
-::
+:Copyright: |copy| 2017 Intel Corporation
+
+:Author: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
 
- Copyright (c) 2017 Intel Corp., Rafael J. Wysocki <rafael.j.wysocki@intel.com>
 
 Sleep states are global low-power states of the entire system in which user
 space code cannot be executed and the overall system activity is significantly
diff --git a/Documentation/admin-guide/pm/strategies.rst b/Documentation/admin-guide/pm/strategies.rst
index afe4d3f831fe..dd0362e32fa5 100644
--- a/Documentation/admin-guide/pm/strategies.rst
+++ b/Documentation/admin-guide/pm/strategies.rst
@@ -1,10 +1,14 @@
+.. SPDX-License-Identifier: GPL-2.0
+.. include:: <isonum.txt>
+
 ===========================
 Power Management Strategies
 ===========================
 
-::
+:Copyright: |copy| 2017 Intel Corporation
+
+:Author: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
 
- Copyright (c) 2017 Intel Corp., Rafael J. Wysocki <rafael.j.wysocki@intel.com>
 
 The Linux kernel supports two major high-level power management strategies.
 
diff --git a/Documentation/admin-guide/pm/system-wide.rst b/Documentation/admin-guide/pm/system-wide.rst
index 0c81e4c5de39..2b1f987b34f0 100644
--- a/Documentation/admin-guide/pm/system-wide.rst
+++ b/Documentation/admin-guide/pm/system-wide.rst
@@ -1,3 +1,5 @@
+.. SPDX-License-Identifier: GPL-2.0
+
 ============================
 System-Wide Power Management
 ============================
diff --git a/Documentation/admin-guide/pm/working-state.rst b/Documentation/admin-guide/pm/working-state.rst
index b6cef9b5e961..fc298eb1234b 100644
--- a/Documentation/admin-guide/pm/working-state.rst
+++ b/Documentation/admin-guide/pm/working-state.rst
@@ -1,3 +1,5 @@
+.. SPDX-License-Identifier: GPL-2.0
+
 ==============================
 Working-State Power Management
 ==============================
@@ -8,3 +10,4 @@ Working-State Power Management
    cpuidle
    cpufreq
    intel_pstate
+   intel_epb
diff --git a/Documentation/arm64/cpu-feature-registers.txt b/Documentation/arm64/cpu-feature-registers.txt
index d4b4dd1fe786..684a0da39378 100644
--- a/Documentation/arm64/cpu-feature-registers.txt
+++ b/Documentation/arm64/cpu-feature-registers.txt
@@ -209,6 +209,22 @@ infrastructure:
      | AT                           | [35-32] |    y    |
      x--------------------------------------------------x
 
+  6) ID_AA64ZFR0_EL1 - SVE feature ID register 0
+
+     x--------------------------------------------------x
+     | Name                         |  bits   | visible |
+     |--------------------------------------------------|
+     | SM4                          | [43-40] |    y    |
+     |--------------------------------------------------|
+     | SHA3                         | [35-32] |    y    |
+     |--------------------------------------------------|
+     | BitPerm                      | [19-16] |    y    |
+     |--------------------------------------------------|
+     | AES                          | [7-4]   |    y    |
+     |--------------------------------------------------|
+     | SVEVer                       | [3-0]   |    y    |
+     x--------------------------------------------------x
+
 Appendix I: Example
 ---------------------------
 
diff --git a/Documentation/arm64/elf_hwcaps.txt b/Documentation/arm64/elf_hwcaps.txt
index 13d6691b37be..b73a2519ecf2 100644
--- a/Documentation/arm64/elf_hwcaps.txt
+++ b/Documentation/arm64/elf_hwcaps.txt
@@ -13,9 +13,9 @@ architected discovery mechanism available to userspace code at EL0. The
 kernel exposes the presence of these features to userspace through a set
 of flags called hwcaps, exposed in the auxilliary vector.
 
-Userspace software can test for features by acquiring the AT_HWCAP entry
-of the auxilliary vector, and testing whether the relevant flags are
-set, e.g.
+Userspace software can test for features by acquiring the AT_HWCAP or
+AT_HWCAP2 entry of the auxiliary vector, and testing whether the relevant
+flags are set, e.g.
 
 bool floating_point_is_present(void)
 {
@@ -135,6 +135,10 @@ HWCAP_DCPOP
 
     Functionality implied by ID_AA64ISAR1_EL1.DPB == 0b0001.
 
+HWCAP2_DCPODP
+
+    Functionality implied by ID_AA64ISAR1_EL1.DPB == 0b0010.
+
 HWCAP_SHA3
 
     Functionality implied by ID_AA64ISAR0_EL1.SHA3 == 0b0001.
@@ -159,6 +163,30 @@ HWCAP_SVE
 
     Functionality implied by ID_AA64PFR0_EL1.SVE == 0b0001.
 
+HWCAP2_SVE2
+
+    Functionality implied by ID_AA64ZFR0_EL1.SVEVer == 0b0001.
+
+HWCAP2_SVEAES
+
+    Functionality implied by ID_AA64ZFR0_EL1.AES == 0b0001.
+
+HWCAP2_SVEPMULL
+
+    Functionality implied by ID_AA64ZFR0_EL1.AES == 0b0010.
+
+HWCAP2_SVEBITPERM
+
+    Functionality implied by ID_AA64ZFR0_EL1.BitPerm == 0b0001.
+
+HWCAP2_SVESHA3
+
+    Functionality implied by ID_AA64ZFR0_EL1.SHA3 == 0b0001.
+
+HWCAP2_SVESM4
+
+    Functionality implied by ID_AA64ZFR0_EL1.SM4 == 0b0001.
+
 HWCAP_ASIMDFHM
 
    Functionality implied by ID_AA64ISAR0_EL1.FHM == 0b0001.
@@ -194,3 +222,10 @@ HWCAP_PACG
     Functionality implied by ID_AA64ISAR1_EL1.GPA == 0b0001 or
     ID_AA64ISAR1_EL1.GPI == 0b0001, as described by
     Documentation/arm64/pointer-authentication.txt.
+
+
+4. Unused AT_HWCAP bits
+-----------------------
+
+For interoperation with userspace, the kernel guarantees that bits 62
+and 63 of AT_HWCAP will always be returned as 0.
diff --git a/Documentation/arm64/silicon-errata.txt b/Documentation/arm64/silicon-errata.txt
index d1e2bb801e1b..68d9b74fd751 100644
--- a/Documentation/arm64/silicon-errata.txt
+++ b/Documentation/arm64/silicon-errata.txt
@@ -61,6 +61,7 @@ stable kernels.
 | ARM            | Cortex-A76      | #1188873        | ARM64_ERRATUM_1188873       |
 | ARM            | Cortex-A76      | #1165522        | ARM64_ERRATUM_1165522       |
 | ARM            | Cortex-A76      | #1286807        | ARM64_ERRATUM_1286807       |
+| ARM            | Neoverse-N1     | #1188873        | ARM64_ERRATUM_1188873       |
 | ARM            | MMU-500         | #841119,#826419 | N/A                         |
 |                |                 |                 |                             |
 | Cavium         | ThunderX ITS    | #22375, #24313  | CAVIUM_ERRATUM_22375        |
@@ -77,6 +78,7 @@ stable kernels.
 | Hisilicon      | Hip0{5,6,7}     | #161010101      | HISILICON_ERRATUM_161010101 |
 | Hisilicon      | Hip0{6,7}       | #161010701      | N/A                         |
 | Hisilicon      | Hip07           | #161600802      | HISILICON_ERRATUM_161600802 |
+| Hisilicon      | Hip08 SMMU PMCG | #162001800      | N/A                         |
 |                |                 |                 |                             |
 | Qualcomm Tech. | Kryo/Falkor v1  | E1003           | QCOM_FALKOR_ERRATUM_1003    |
 | Qualcomm Tech. | Falkor v1       | E1009           | QCOM_FALKOR_ERRATUM_1009    |
diff --git a/Documentation/arm64/sve.txt b/Documentation/arm64/sve.txt
index 7169a0ec41d8..9940e924a47e 100644
--- a/Documentation/arm64/sve.txt
+++ b/Documentation/arm64/sve.txt
@@ -34,6 +34,23 @@ model features for SVE is included in Appendix A.
   following sections: software that needs to verify that those interfaces are
   present must check for HWCAP_SVE instead.
 
+* On hardware that supports the SVE2 extensions, HWCAP2_SVE2 will also
+  be reported in the AT_HWCAP2 aux vector entry.  In addition to this,
+  optional extensions to SVE2 may be reported by the presence of:
+
+	HWCAP2_SVE2
+	HWCAP2_SVEAES
+	HWCAP2_SVEPMULL
+	HWCAP2_SVEBITPERM
+	HWCAP2_SVESHA3
+	HWCAP2_SVESM4
+
+  This list may be extended over time as the SVE architecture evolves.
+
+  These extensions are also reported via the CPU ID register ID_AA64ZFR0_EL1,
+  which userspace can read using an MRS instruction.  See elf_hwcaps.txt and
+  cpu-feature-registers.txt for details.
+
 * Debuggers should restrict themselves to interacting with the target via the
   NT_ARM_SVE regset.  The recommended way of detecting support for this regset
   is to connect to a target process first and then attempt a
diff --git a/Documentation/atomic_t.txt b/Documentation/atomic_t.txt
index 913396ac5824..dca3fb0554db 100644
--- a/Documentation/atomic_t.txt
+++ b/Documentation/atomic_t.txt
@@ -56,6 +56,23 @@ Barriers:
   smp_mb__{before,after}_atomic()
 
 
+TYPES (signed vs unsigned)
+-----
+
+While atomic_t, atomic_long_t and atomic64_t use int, long and s64
+respectively (for hysterical raisins), the kernel uses -fno-strict-overflow
+(which implies -fwrapv) and defines signed overflow to behave like
+2s-complement.
+
+Therefore, an explicitly unsigned variant of the atomic ops is strictly
+unnecessary and we can simply cast, there is no UB.
+
+There was a bug in UBSAN prior to GCC-8 that would generate UB warnings for
+signed types.
+
+With this we also conform to the C/C++ _Atomic behaviour and things like
+P1236R1.
+
 
 SEMANTICS
 ---------
diff --git a/Documentation/bpf/btf.rst b/Documentation/bpf/btf.rst
index 9a60a5d60e38..7313d354f20e 100644
--- a/Documentation/bpf/btf.rst
+++ b/Documentation/bpf/btf.rst
@@ -148,16 +148,16 @@ The ``btf_type.size * 8`` must be equal to or greater than ``BTF_INT_BITS()``
 for the type. The maximum value of ``BTF_INT_BITS()`` is 128.
 
 The ``BTF_INT_OFFSET()`` specifies the starting bit offset to calculate values
-for this int. For example, a bitfield struct member has: * btf member bit
-offset 100 from the start of the structure, * btf member pointing to an int
-type, * the int type has ``BTF_INT_OFFSET() = 2`` and ``BTF_INT_BITS() = 4``
+for this int. For example, a bitfield struct member has:
+ * btf member bit offset 100 from the start of the structure,
+ * btf member pointing to an int type,
+ * the int type has ``BTF_INT_OFFSET() = 2`` and ``BTF_INT_BITS() = 4``
 
 Then in the struct memory layout, this member will occupy ``4`` bits starting
 from bits ``100 + 2 = 102``.
 
 Alternatively, the bitfield struct member can be the following to access the
 same bits as the above:
-
  * btf member bit offset 102,
  * btf member pointing to an int type,
  * the int type has ``BTF_INT_OFFSET() = 0`` and ``BTF_INT_BITS() = 4``
diff --git a/Documentation/core-api/cachetlb.rst b/Documentation/core-api/cachetlb.rst
index 6eb9d3f090cd..93cb65d52720 100644
--- a/Documentation/core-api/cachetlb.rst
+++ b/Documentation/core-api/cachetlb.rst
@@ -101,16 +101,6 @@ changes occur:
 	translations for software managed TLB configurations.
 	The sparc64 port currently does this.
 
-6) ``void tlb_migrate_finish(struct mm_struct *mm)``
-
-	This interface is called at the end of an explicit
-	process migration. This interface provides a hook
-	to allow a platform to update TLB or context-specific
-	information for the address space.
-
-	The ia64 sn2 platform is one example of a platform
-	that uses this interface.
-
 Next, we have the cache flushing interfaces.  In general, when Linux
 is changing an existing virtual-->physical mapping to a new value,
 the sequence will be in one of the following forms::
diff --git a/Documentation/cputopology.txt b/Documentation/cputopology.txt
index c6e7e9196a8b..cb61277e2308 100644
--- a/Documentation/cputopology.txt
+++ b/Documentation/cputopology.txt
@@ -3,79 +3,79 @@ How CPU topology info is exported via sysfs
 ===========================================
 
 Export CPU topology info via sysfs. Items (attributes) are similar
-to /proc/cpuinfo output of some architectures:
+to /proc/cpuinfo output of some architectures.  They reside in
+/sys/devices/system/cpu/cpuX/topology/:
 
-1) /sys/devices/system/cpu/cpuX/topology/physical_package_id:
+physical_package_id:
 
 	physical package id of cpuX. Typically corresponds to a physical
 	socket number, but the actual value is architecture and platform
 	dependent.
 
-2) /sys/devices/system/cpu/cpuX/topology/core_id:
+core_id:
 
 	the CPU core ID of cpuX. Typically it is the hardware platform's
 	identifier (rather than the kernel's).  The actual value is
 	architecture and platform dependent.
 
-3) /sys/devices/system/cpu/cpuX/topology/book_id:
+book_id:
 
 	the book ID of cpuX. Typically it is the hardware platform's
 	identifier (rather than the kernel's).	The actual value is
 	architecture and platform dependent.
 
-4) /sys/devices/system/cpu/cpuX/topology/drawer_id:
+drawer_id:
 
 	the drawer ID of cpuX. Typically it is the hardware platform's
 	identifier (rather than the kernel's).	The actual value is
 	architecture and platform dependent.
 
-5) /sys/devices/system/cpu/cpuX/topology/thread_siblings:
+thread_siblings:
 
 	internal kernel map of cpuX's hardware threads within the same
 	core as cpuX.
 
-6) /sys/devices/system/cpu/cpuX/topology/thread_siblings_list:
+thread_siblings_list:
 
 	human-readable list of cpuX's hardware threads within the same
 	core as cpuX.
 
-7) /sys/devices/system/cpu/cpuX/topology/core_siblings:
+core_siblings:
 
 	internal kernel map of cpuX's hardware threads within the same
 	physical_package_id.
 
-8) /sys/devices/system/cpu/cpuX/topology/core_siblings_list:
+core_siblings_list:
 
 	human-readable list of cpuX's hardware threads within the same
 	physical_package_id.
 
-9) /sys/devices/system/cpu/cpuX/topology/book_siblings:
+book_siblings:
 
 	internal kernel map of cpuX's hardware threads within the same
 	book_id.
 
-10) /sys/devices/system/cpu/cpuX/topology/book_siblings_list:
+book_siblings_list:
 
 	human-readable list of cpuX's hardware threads within the same
 	book_id.
 
-11) /sys/devices/system/cpu/cpuX/topology/drawer_siblings:
+drawer_siblings:
 
 	internal kernel map of cpuX's hardware threads within the same
 	drawer_id.
 
-12) /sys/devices/system/cpu/cpuX/topology/drawer_siblings_list:
+drawer_siblings_list:
 
 	human-readable list of cpuX's hardware threads within the same
 	drawer_id.
 
-To implement it in an architecture-neutral way, a new source file,
-drivers/base/topology.c, is to export the 6 to 12 attributes. The book
-and drawer related sysfs files will only be created if CONFIG_SCHED_BOOK
-and CONFIG_SCHED_DRAWER are selected.
+Architecture-neutral, drivers/base/topology.c, exports these attributes.
+However, the book and drawer related sysfs files will only be created if
+CONFIG_SCHED_BOOK and CONFIG_SCHED_DRAWER are selected, respectively.
 
-CONFIG_SCHED_BOOK and CONFIG_DRAWER are currently only used on s390, where
-they reflect the cpu and cache hierarchy.
+CONFIG_SCHED_BOOK and CONFIG_SCHED_DRAWER are currently only used on s390,
+where they reflect the cpu and cache hierarchy.
 
 For an architecture to support this feature, it must define some of
 these macros in include/asm-XXX/topology.h::
@@ -98,10 +98,10 @@ To be consistent on all architectures, include/linux/topology.h
 provides default definitions for any of the above macros that are
 not defined by include/asm-XXX/topology.h:
 
-1) physical_package_id: -1
-2) core_id: 0
-3) sibling_cpumask: just the given CPU
-4) core_cpumask: just the given CPU
+1) topology_physical_package_id: -1
+2) topology_core_id: 0
+3) topology_sibling_cpumask: just the given CPU
+4) topology_core_cpumask: just the given CPU
 
 For architectures that don't support books (CONFIG_SCHED_BOOK) there are no
 default definitions for topology_book_id() and topology_book_cpumask().
diff --git a/Documentation/crypto/api-samples.rst b/Documentation/crypto/api-samples.rst
index 0f6ca8b7261e..f14afaaf2f32 100644
--- a/Documentation/crypto/api-samples.rst
+++ b/Documentation/crypto/api-samples.rst
@@ -133,7 +133,6 @@ Code Example For Use of Operational State Memory With SHASH
         if (!sdesc)
             return ERR_PTR(-ENOMEM);
         sdesc->shash.tfm = alg;
-        sdesc->shash.flags = 0x0;
         return sdesc;
     }
 
diff --git a/Documentation/dev-tools/kselftest.rst b/Documentation/dev-tools/kselftest.rst
index 7756f7a7c23b..c8c03388b9de 100644
--- a/Documentation/dev-tools/kselftest.rst
+++ b/Documentation/dev-tools/kselftest.rst
@@ -14,6 +14,10 @@ in safe mode with a limited scope. In limited mode, cpu-hotplug test is
 run on a single cpu as opposed to all hotplug capable cpus, and memory
 hotplug test is run on 2% of hotplug capable memory instead of 10%.
 
+kselftest runs as a userspace process.  Tests that can be written/run in
+userspace may wish to use the `Test Harness`_.  Tests that need to be
+run in kernel space may wish to use a `Test Module`_.
+
 Running the selftests (hotplug tests are run in limited mode)
 =============================================================
 
@@ -161,11 +165,97 @@ Contributing new tests (details)
 
    e.g: tools/testing/selftests/android/config
 
+Test Module
+===========
+
+Kselftest tests the kernel from userspace.  Sometimes things need
+testing from within the kernel, one method of doing this is to create a
+test module.  We can tie the module into the kselftest framework by
+using a shell script test runner.  ``kselftest_module.sh`` is designed
+to facilitate this process.  There is also a header file provided to
+assist writing kernel modules that are for use with kselftest:
+
+- ``tools/testing/kselftest/kselftest_module.h``
+- ``tools/testing/kselftest/kselftest_module.sh``
+
+How to use
+----------
+
+Here we show the typical steps to create a test module and tie it into
+kselftest.  We use kselftests for lib/ as an example.
+
+1. Create the test module
+
+2. Create the test script that will run (load/unload) the module
+   e.g. ``tools/testing/selftests/lib/printf.sh``
+
+3. Add line to config file e.g. ``tools/testing/selftests/lib/config``
+
+4. Add test script to makefile  e.g. ``tools/testing/selftests/lib/Makefile``
+
+5. Verify it works:
+
+.. code-block:: sh
+
+   # Assumes you have booted a fresh build of this kernel tree
+   cd /path/to/linux/tree
+   make kselftest-merge
+   make modules
+   sudo make modules_install
+   make TARGETS=lib kselftest
+
+Example Module
+--------------
+
+A bare bones test module might look like this:
+
+.. code-block:: c
+
+   // SPDX-License-Identifier: GPL-2.0+
+
+   #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
+   #include "../tools/testing/selftests/kselftest_module.h"
+
+   KSTM_MODULE_GLOBALS();
+
+   /*
+    * Kernel module for testing the foobinator
+    */
+
+   static int __init test_function()
+   {
+           ...
+   }
+
+   static void __init selftest(void)
+   {
+           KSTM_CHECK_ZERO(do_test_case("", 0));
+   }
+
+   KSTM_MODULE_LOADERS(test_foo);
+   MODULE_AUTHOR("John Developer <jd@fooman.org>");
+   MODULE_LICENSE("GPL");
+
+Example test script
+-------------------
+
+.. code-block:: sh
+
+    #!/bin/bash
+    # SPDX-License-Identifier: GPL-2.0+
+    $(dirname $0)/../kselftest_module.sh "foo" test_foo
+
+
 Test Harness
 ============
 
-The kselftest_harness.h file contains useful helpers to build tests.  The tests
-from tools/testing/selftests/seccomp/seccomp_bpf.c can be used as example.
+The kselftest_harness.h file contains useful helpers to build tests.  The
+test harness is for userspace testing, for kernel space testing see `Test
+Module`_ above.
+
+The tests from tools/testing/selftests/seccomp/seccomp_bpf.c can be used as
+example.
 
 Example
 -------
diff --git a/Documentation/devicetree/bindings/arm/cpus.yaml b/Documentation/devicetree/bindings/arm/cpus.yaml
index 365dcf384d73..82dd7582e945 100644
--- a/Documentation/devicetree/bindings/arm/cpus.yaml
+++ b/Documentation/devicetree/bindings/arm/cpus.yaml
@@ -228,7 +228,7 @@ patternProperties:
                 - renesas,r9a06g032-smp
                 - rockchip,rk3036-smp
                 - rockchip,rk3066-smp
-		- socionext,milbeaut-m10v-smp
+                - socionext,milbeaut-m10v-smp
                 - ste,dbx500-smp
 
       cpu-release-addr:
diff --git a/Documentation/devicetree/bindings/edac/socfpga-eccmgr.txt b/Documentation/devicetree/bindings/edac/socfpga-eccmgr.txt
index 5626560a6cfd..8f52206cfd2a 100644
--- a/Documentation/devicetree/bindings/edac/socfpga-eccmgr.txt
+++ b/Documentation/devicetree/bindings/edac/socfpga-eccmgr.txt
@@ -232,37 +232,152 @@ Example:
 		};
 	};
 
-Stratix10 SoCFPGA ECC Manager
+Stratix10 SoCFPGA ECC Manager (ARM64)
 The Stratix10 SoC ECC Manager handles the IRQs for each peripheral
-in a shared register similar to the Arria10. However, ECC requires
-access to registers that can only be read from Secure Monitor with
-SMC calls. Therefore the device tree is slightly different.
+in a shared register similar to the Arria10. However, Stratix10 ECC
+requires access to registers that can only be read from Secure Monitor
+with SMC calls. Therefore the device tree is slightly different. Note
+that only 1 interrupt is sent in Stratix10 because the double bit errors
+are treated as SErrors in ARM64 instead of IRQs in ARM32.
 
 Required Properties:
 - compatible : Should be "altr,socfpga-s10-ecc-manager"
-- interrupts : Should be single bit error interrupt, then double bit error
-	interrupt.
+- altr,sysgr-syscon : phandle to Stratix10 System Manager Block
+	              containing the ECC manager registers.
+- interrupts : Should be single bit error interrupt.
 - interrupt-controller : boolean indicator that ECC Manager is an interrupt controller
 - #interrupt-cells : must be set to 2.
+- #address-cells: must be 1
+- #size-cells: must be 1
+- ranges : standard definition, should translate from local addresses
 
 Subcomponents:
 
 SDRAM ECC
 Required Properties:
 - compatible : Should be "altr,sdram-edac-s10"
-- interrupts : Should be single bit error interrupt, then double bit error
-	interrupt, in this order.
+- interrupts : Should be single bit error interrupt.
+
+On-Chip RAM ECC
+Required Properties:
+- compatible      : Should be "altr,socfpga-s10-ocram-ecc"
+- reg             : Address and size for ECC block registers.
+- altr,ecc-parent : phandle to parent OCRAM node.
+- interrupts      : Should be single bit error interrupt.
+
+Ethernet FIFO ECC
+Required Properties:
+- compatible      : Should be "altr,socfpga-s10-eth-mac-ecc"
+- reg             : Address and size for ECC block registers.
+- altr,ecc-parent : phandle to parent Ethernet node.
+- interrupts      : Should be single bit error interrupt.
+
+NAND FIFO ECC
+Required Properties:
+- compatible      : Should be "altr,socfpga-s10-nand-ecc"
+- reg             : Address and size for ECC block registers.
+- altr,ecc-parent : phandle to parent NAND node.
+- interrupts      : Should be single bit error interrupt.
+
+DMA FIFO ECC
+Required Properties:
+- compatible      : Should be "altr,socfpga-s10-dma-ecc"
+- reg             : Address and size for ECC block registers.
+- altr,ecc-parent : phandle to parent DMA node.
+- interrupts      : Should be single bit error interrupt.
+
+USB FIFO ECC
+Required Properties:
+- compatible      : Should be "altr,socfpga-s10-usb-ecc"
+- reg             : Address and size for ECC block registers.
+- altr,ecc-parent : phandle to parent USB node.
+- interrupts      : Should be single bit error interrupt.
+
+SDMMC FIFO ECC
+Required Properties:
+- compatible      : Should be "altr,socfpga-s10-sdmmc-ecc"
+- reg             : Address and size for ECC block registers.
+- altr,ecc-parent : phandle to parent SD/MMC node.
+- interrupts      : Should be single bit error interrupt for port A
+		    and then single bit error interrupt for port B.
 
 Example:
 
 	eccmgr {
 		compatible = "altr,socfpga-s10-ecc-manager";
-		interrupts = <0 15 4>, <0 95 4>;
+		altr,sysmgr-syscon = <&sysmgr>;
+		#address-cells = <1>;
+		#size-cells = <1>;
+		interrupts = <0 15 4>;
 		interrupt-controller;
 		#interrupt-cells = <2>;
+		ranges;
 
 		sdramedac {
 			compatible = "altr,sdram-edac-s10";
-			interrupts = <16 4>, <48 4>;
+			interrupts = <16 IRQ_TYPE_LEVEL_HIGH>;
+		};
+
+		ocram-ecc@ff8cc000 {
+			compatible = "altr,socfpga-s10-ocram-ecc";
+			reg = <ff8cc000 0x100>;
+			altr,ecc-parent = <&ocram>;
+			interrupts = <1 IRQ_TYPE_LEVEL_HIGH>;
+		};
+
+		emac0-rx-ecc@ff8c0000 {
+			compatible = "altr,socfpga-s10-eth-mac-ecc";
+			reg = <0xff8c0000 0x100>;
+			altr,ecc-parent = <&gmac0>;
+			interrupts = <4 IRQ_TYPE_LEVEL_HIGH>;
+		};
+
+		emac0-tx-ecc@ff8c0400 {
+			compatible = "altr,socfpga-s10-eth-mac-ecc";
+			reg = <0xff8c0400 0x100>;
+			altr,ecc-parent = <&gmac0>;
+			interrupts = <5 IRQ_TYPE_LEVEL_HIGH>'
+		};
+
+		nand-buf-ecc@ff8c8000 {
+			compatible = "altr,socfpga-s10-nand-ecc";
+			reg = <0xff8c8000 0x100>;
+			altr,ecc-parent = <&nand>;
+			interrupts = <11 IRQ_TYPE_LEVEL_HIGH>;
+		};
+
+		nand-rd-ecc@ff8c8400 {
+			compatible = "altr,socfpga-s10-nand-ecc";
+			reg = <0xff8c8400 0x100>;
+			altr,ecc-parent = <&nand>;
+			interrupts = <13 IRQ_TYPE_LEVEL_HIGH>;
+		};
+
+		nand-wr-ecc@ff8c8800 {
+			compatible = "altr,socfpga-s10-nand-ecc";
+			reg = <0xff8c8800 0x100>;
+			altr,ecc-parent = <&nand>;
+			interrupts = <12 IRQ_TYPE_LEVEL_HIGH>;
+		};
+
+		dma-ecc@ff8c9000 {
+			compatible = "altr,socfpga-s10-dma-ecc";
+			reg = <0xff8c9000 0x100>;
+			altr,ecc-parent = <&pdma>;
+			interrupts = <10 IRQ_TYPE_LEVEL_HIGH>;
+
+		usb0-ecc@ff8c4000 {
+			compatible = "altr,socfpga-s10-usb-ecc";
+			reg = <0xff8c4000 0x100>;
+			altr,ecc-parent = <&usb0>;
+			interrupts = <2 IRQ_TYPE_LEVEL_HIGH>;
+		};
+
+		sdmmc-ecc@ff8c8c00 {
+			compatible = "altr,socfpga-s10-sdmmc-ecc";
+			reg = <0xff8c8c00 0x100>;
+			altr,ecc-parent = <&mmc>;
+			interrupts = <14 IRQ_TYPE_LEVEL_HIGH>,
+				     <15 IRQ_TYPE_LEVEL_HIGH>;
 		};
 	};
diff --git a/Documentation/devicetree/bindings/hwmon/adc128d818.txt b/Documentation/devicetree/bindings/hwmon/adc128d818.txt
index 08bab0e94d25..d0ae46d7bac3 100644
--- a/Documentation/devicetree/bindings/hwmon/adc128d818.txt
+++ b/Documentation/devicetree/bindings/hwmon/adc128d818.txt
@@ -26,7 +26,7 @@ Required node properties:
 
 Optional node properties:
 
- - ti,mode:     Operation mode (see above).
+ - ti,mode:     Operation mode (u8) (see above).
 
 
 Example (operation mode 2):
@@ -34,5 +34,5 @@ Example (operation mode 2):
 	adc128d818@1d {
 		compatible = "ti,adc128d818";
 		reg = <0x1d>;
-		ti,mode = <2>;
+		ti,mode = /bits/ 8 <2>;
 	};
diff --git a/Documentation/devicetree/bindings/hwmon/cirrus,lochnagar.txt b/Documentation/devicetree/bindings/hwmon/cirrus,lochnagar.txt
new file mode 100644
index 000000000000..ffb79ccf51ee
--- /dev/null
+++ b/Documentation/devicetree/bindings/hwmon/cirrus,lochnagar.txt
@@ -0,0 +1,26 @@
+Cirrus Logic Lochnagar Audio Development Board
+
+Lochnagar is an evaluation and development board for Cirrus Logic
+Smart CODEC and Amp devices. It allows the connection of most Cirrus
+Logic devices on mini-cards, as well as allowing connection of
+various application processor systems to provide a full evaluation
+platform.  Audio system topology, clocking and power can all be
+controlled through the Lochnagar, allowing the device under test
+to be used in a variety of possible use cases.
+
+This binding document describes the binding for the hardware monitor
+portion of the driver.
+
+This binding must be part of the Lochnagar MFD binding:
+  [4] ../mfd/cirrus,lochnagar.txt
+
+Required properties:
+
+  - compatible : One of the following strings:
+                 "cirrus,lochnagar2-hwmon"
+
+Example:
+
+lochnagar-hwmon {
+	compatible = "cirrus,lochnagar2-hwmon";
+};
diff --git a/Documentation/devicetree/bindings/hwmon/g762.txt b/Documentation/devicetree/bindings/hwmon/g762.txt
index 25cc6d8ee575..6d154c4923de 100644
--- a/Documentation/devicetree/bindings/hwmon/g762.txt
+++ b/Documentation/devicetree/bindings/hwmon/g762.txt
@@ -21,7 +21,7 @@ If an optional property is not set in .dts file, then current value is kept
 unmodified (e.g. u-boot installed value).
 
 Additional information on operational parameters for the device is available
-in Documentation/hwmon/g762. A detailed datasheet for the device is available
+in Documentation/hwmon/g762.rst. A detailed datasheet for the device is available
 at http://natisbad.org/NAS/refs/GMT_EDS-762_763-080710-0.2.pdf.
 
 Example g762 node:
diff --git a/Documentation/devicetree/bindings/hwmon/lm75.txt b/Documentation/devicetree/bindings/hwmon/lm75.txt
index 12d8cf7cf592..586b5ed70be7 100644
--- a/Documentation/devicetree/bindings/hwmon/lm75.txt
+++ b/Documentation/devicetree/bindings/hwmon/lm75.txt
@@ -25,6 +25,7 @@ Required properties:
 		"ti,tmp175",
 		"ti,tmp275",
 		"ti,tmp75",
+		"ti,tmp75b",
 		"ti,tmp75c",
 
 - reg: I2C bus address of the device
diff --git a/Documentation/devicetree/bindings/hwmon/pwm-fan.txt b/Documentation/devicetree/bindings/hwmon/pwm-fan.txt
index 49ca5d83ed13..6ced829b0e58 100644
--- a/Documentation/devicetree/bindings/hwmon/pwm-fan.txt
+++ b/Documentation/devicetree/bindings/hwmon/pwm-fan.txt
@@ -7,7 +7,16 @@ Required properties:
 			which correspond to thermal cooling states
 
 Optional properties:
-- fan-supply    : phandle to the regulator that provides power to the fan
+- fan-supply		: phandle to the regulator that provides power to the fan
+- interrupts		: This contains a single interrupt specifier which
+			  describes the tachometer output of the fan as an
+			  interrupt source. The output signal must generate a
+			  defined number of interrupts per fan revolution, which
+			  require that it must be self resetting edge interrupts.
+			  See interrupt-controller/interrupts.txt for the format.
+- pulses-per-revolution : define the tachometer pulses per fan revolution as
+			  an integer (default is 2 interrupts per revolution).
+			  The value must be greater than zero.
 
 Example:
 	fan0: pwm-fan {
@@ -38,3 +47,13 @@ Example:
 					};
 			     };
 		};
+
+Example 2:
+	fan0: pwm-fan {
+		compatible = "pwm-fan";
+		pwms = <&pwm 0 40000 0>;
+		fan-supply = <&reg_fan>;
+		interrupt-parent = <&gpio5>;
+		interrupts = <1 IRQ_TYPE_EDGE_FALLING>;
+		pulses-per-revolution = <2>;
+	};
diff --git a/Documentation/devicetree/bindings/i2c/i2c-xscale.txt b/Documentation/devicetree/bindings/i2c/i2c-iop3xx.txt
index dcc8390e0d24..dcc8390e0d24 100644
--- a/Documentation/devicetree/bindings/i2c/i2c-xscale.txt
+++ b/Documentation/devicetree/bindings/i2c/i2c-iop3xx.txt
diff --git a/Documentation/devicetree/bindings/i2c/i2c-mtk.txt b/Documentation/devicetree/bindings/i2c/i2c-mt65xx.txt
index ee4c32454198..ee4c32454198 100644
--- a/Documentation/devicetree/bindings/i2c/i2c-mtk.txt
+++ b/Documentation/devicetree/bindings/i2c/i2c-mt65xx.txt
diff --git a/Documentation/devicetree/bindings/i2c/i2c-st-ddci2c.txt b/Documentation/devicetree/bindings/i2c/i2c-stu300.txt
index bd81a482634f..bd81a482634f 100644
--- a/Documentation/devicetree/bindings/i2c/i2c-st-ddci2c.txt
+++ b/Documentation/devicetree/bindings/i2c/i2c-stu300.txt
diff --git a/Documentation/devicetree/bindings/i2c/i2c-sunxi-p2wi.txt b/Documentation/devicetree/bindings/i2c/i2c-sun6i-p2wi.txt
index 49df0053347a..49df0053347a 100644
--- a/Documentation/devicetree/bindings/i2c/i2c-sunxi-p2wi.txt
+++ b/Documentation/devicetree/bindings/i2c/i2c-sun6i-p2wi.txt
diff --git a/Documentation/devicetree/bindings/i2c/i2c-vt8500.txt b/Documentation/devicetree/bindings/i2c/i2c-wmt.txt
index 94a425eaa6c7..94a425eaa6c7 100644
--- a/Documentation/devicetree/bindings/i2c/i2c-vt8500.txt
+++ b/Documentation/devicetree/bindings/i2c/i2c-wmt.txt
diff --git a/Documentation/devicetree/bindings/net/davinci_emac.txt b/Documentation/devicetree/bindings/net/davinci_emac.txt
index 24c5cdaba8d2..ca83dcc84fb8 100644
--- a/Documentation/devicetree/bindings/net/davinci_emac.txt
+++ b/Documentation/devicetree/bindings/net/davinci_emac.txt
@@ -20,6 +20,8 @@ Required properties:
 Optional properties:
 - phy-handle: See ethernet.txt file in the same directory.
               If absent, davinci_emac driver defaults to 100/FULL.
+- nvmem-cells: phandle, reference to an nvmem node for the MAC address
+- nvmem-cell-names: string, should be "mac-address" if nvmem is to be used
 - ti,davinci-rmii-en: 1 byte, 1 means use RMII
 - ti,davinci-no-bd-ram: boolean, does EMAC have BD RAM?
 
diff --git a/Documentation/devicetree/bindings/net/dsa/qca8k.txt b/Documentation/devicetree/bindings/net/dsa/qca8k.txt
index bbcb255c3150..93a7469e70d4 100644
--- a/Documentation/devicetree/bindings/net/dsa/qca8k.txt
+++ b/Documentation/devicetree/bindings/net/dsa/qca8k.txt
@@ -12,10 +12,15 @@ Required properties:
 Subnodes:
 
 The integrated switch subnode should be specified according to the binding
-described in dsa/dsa.txt. As the QCA8K switches do not have a N:N mapping of
-port and PHY id, each subnode describing a port needs to have a valid phandle
-referencing the internal PHY connected to it. The CPU port of this switch is
-always port 0.
+described in dsa/dsa.txt. If the QCA8K switch is connect to a SoC's external
+mdio-bus each subnode describing a port needs to have a valid phandle
+referencing the internal PHY it is connected to. This is because there's no
+N:N mapping of port and PHY id.
+
+Don't use mixed external and internal mdio-bus configurations, as this is
+not supported by the hardware.
+
+The CPU port of this switch is always port 0.
 
 A CPU port node has the following optional node:
 
@@ -31,8 +36,9 @@ For QCA8K the 'fixed-link' sub-node supports only the following properties:
 - 'full-duplex' (boolean, optional), to indicate that full duplex is
   used. When absent, half duplex is assumed.
 
-Example:
+Examples:
 
+for the external mdio-bus configuration:
 
 	&mdio0 {
 		phy_port1: phy@0 {
@@ -55,12 +61,12 @@ Example:
 			reg = <4>;
 		};
 
-		switch0@0 {
+		switch@10 {
 			compatible = "qca,qca8337";
 			#address-cells = <1>;
 			#size-cells = <0>;
 
-			reg = <0>;
+			reg = <0x10>;
 
 			ports {
 				#address-cells = <1>;
@@ -108,3 +114,56 @@ Example:
 			};
 		};
 	};
+
+for the internal master mdio-bus configuration:
+
+	&mdio0 {
+		switch@10 {
+			compatible = "qca,qca8337";
+			#address-cells = <1>;
+			#size-cells = <0>;
+
+			reg = <0x10>;
+
+			ports {
+				#address-cells = <1>;
+				#size-cells = <0>;
+
+				port@0 {
+					reg = <0>;
+					label = "cpu";
+					ethernet = <&gmac1>;
+					phy-mode = "rgmii";
+					fixed-link {
+						speed = 1000;
+						full-duplex;
+					};
+				};
+
+				port@1 {
+					reg = <1>;
+					label = "lan1";
+				};
+
+				port@2 {
+					reg = <2>;
+					label = "lan2";
+				};
+
+				port@3 {
+					reg = <3>;
+					label = "lan3";
+				};
+
+				port@4 {
+					reg = <4>;
+					label = "lan4";
+				};
+
+				port@5 {
+					reg = <5>;
+					label = "wan";
+				};
+			};
+		};
+	};
diff --git a/Documentation/devicetree/bindings/net/ethernet.txt b/Documentation/devicetree/bindings/net/ethernet.txt
index cfc376bc977a..a68621580584 100644
--- a/Documentation/devicetree/bindings/net/ethernet.txt
+++ b/Documentation/devicetree/bindings/net/ethernet.txt
@@ -10,15 +10,14 @@ Documentation/devicetree/bindings/phy/phy-bindings.txt.
   the boot program; should be used in cases where the MAC address assigned to
   the device by the boot program is different from the "local-mac-address"
   property;
-- nvmem-cells: phandle, reference to an nvmem node for the MAC address;
-- nvmem-cell-names: string, should be "mac-address" if nvmem is to be used;
 - max-speed: number, specifies maximum speed in Mbit/s supported by the device;
 - max-frame-size: number, maximum transfer unit (IEEE defined MTU), rather than
   the maximum frame size (there's contradiction in the Devicetree
   Specification).
 - phy-mode: string, operation mode of the PHY interface. This is now a de-facto
   standard property; supported values are:
-  * "internal"
+  * "internal" (Internal means there is not a standard bus between the MAC and
+     the PHY, something proprietary is being used to embed the PHY in the MAC.)
   * "mii"
   * "gmii"
   * "sgmii"
diff --git a/Documentation/devicetree/bindings/net/macb.txt b/Documentation/devicetree/bindings/net/macb.txt
index 174f292d8a3e..8b80515729d7 100644
--- a/Documentation/devicetree/bindings/net/macb.txt
+++ b/Documentation/devicetree/bindings/net/macb.txt
@@ -26,6 +26,10 @@ Required properties:
 	Optional elements: 'tsu_clk'
 - clocks: Phandles to input clocks.
 
+Optional properties:
+- nvmem-cells: phandle, reference to an nvmem node for the MAC address
+- nvmem-cell-names: string, should be "mac-address" if nvmem is to be used
+
 Optional properties for PHY child node:
 - reset-gpios : Should specify the gpio for phy reset
 - magic-packet : If present, indicates that the hardware supports waking
diff --git a/Documentation/devicetree/bindings/regulator/gpio-regulator.txt b/Documentation/devicetree/bindings/regulator/gpio-regulator.txt
index 1f496159e2bb..dd25e73b5d79 100644
--- a/Documentation/devicetree/bindings/regulator/gpio-regulator.txt
+++ b/Documentation/devicetree/bindings/regulator/gpio-regulator.txt
@@ -4,16 +4,30 @@ Required properties:
 - compatible		: Must be "regulator-gpio".
 - regulator-name	: Defined in regulator.txt as optional, but required
 			  here.
-- states		: Selection of available voltages and GPIO configs.
-                          if there are no states, then use a fixed regulator
+- gpios			: Array of one or more GPIO pins used to select the
+			  regulator voltage/current listed in "states".
+- states		: Selection of available voltages/currents provided by
+			  this regulator and matching GPIO configurations to
+			  achieve them. If there are no states in the "states"
+			  array, use a fixed regulator instead.
 
 Optional properties:
-- enable-gpio		: GPIO to use to enable/disable the regulator.
-- gpios			: GPIO group used to control voltage.
-- gpios-states		: gpios pin's initial states array. 0: LOW, 1: HIGH.
-			  defualt is LOW if nothing is specified.
+- enable-gpios		: GPIO used to enable/disable the regulator.
+			  Warning, the GPIO phandle flags are ignored and the
+			  GPIO polarity is controlled solely by the presence
+			  of "enable-active-high" DT property. This is due to
+			  compatibility with old DTs.
+- enable-active-high	: Polarity of "enable-gpio" GPIO is active HIGH.
+			  Default is active LOW.
+- gpios-states		: On operating systems, that don't support reading back
+			  gpio values in output mode (most notably linux), this
+			  array provides the state of GPIO pins set when
+			  requesting them from the gpio controller. Systems,
+			  that are capable of preserving state when requesting
+			  the lines, are free to ignore this property.
+			  0: LOW, 1: HIGH. Default is LOW if nothing else
+			  is specified.
 - startup-delay-us	: Startup time in microseconds.
-- enable-active-high	: Polarity of GPIO is active high (default is low).
 - regulator-type	: Specifies what is being regulated, must be either
 			  "voltage" or "current", defaults to voltage.
 
@@ -30,7 +44,7 @@ Example:
 		regulator-max-microvolt = <2600000>;
 		regulator-boot-on;
 
-		enable-gpio = <&gpio0 23 0x4>;
+		enable-gpios = <&gpio0 23 0x4>;
 		gpios = <&gpio0 24 0x4
 			 &gpio0 25 0x4>;
 		states = <1800000 0x3
diff --git a/Documentation/devicetree/bindings/regulator/st,stm32mp1-pwr-reg.txt b/Documentation/devicetree/bindings/regulator/st,stm32mp1-pwr-reg.txt
new file mode 100644
index 000000000000..e372dd3f0c8a
--- /dev/null
+++ b/Documentation/devicetree/bindings/regulator/st,stm32mp1-pwr-reg.txt
@@ -0,0 +1,43 @@
+STM32MP1 PWR Regulators
+-----------------------
+
+Available Regulators in STM32MP1 PWR block are:
+  - reg11 for regulator 1V1
+  - reg18 for regulator 1V8
+  - usb33 for the swtich USB3V3
+
+Required properties:
+- compatible: Must be "st,stm32mp1,pwr-reg"
+- list of child nodes that specify the regulator reg11, reg18 or usb33
+  initialization data for defined regulators. The definition for each of
+  these nodes is defined using the standard binding for regulators found at
+  Documentation/devicetree/bindings/regulator/regulator.txt.
+- vdd-supply: phandle to the parent supply/regulator node for vdd input
+- vdd_3v3_usbfs-supply: phandle to the parent supply/regulator node for usb33
+
+Example:
+
+pwr_regulators: pwr@50001000 {
+	compatible = "st,stm32mp1,pwr-reg";
+	reg = <0x50001000 0x10>;
+	vdd-supply = <&vdd>;
+	vdd_3v3_usbfs-supply = <&vdd_usb>;
+
+	reg11: reg11 {
+		regulator-name = "reg11";
+		regulator-min-microvolt = <1100000>;
+		regulator-max-microvolt = <1100000>;
+	};
+
+	reg18: reg18 {
+		regulator-name = "reg18";
+		regulator-min-microvolt = <1800000>;
+		regulator-max-microvolt = <1800000>;
+	};
+
+	usb33: usb33 {
+		regulator-name = "usb33";
+		regulator-min-microvolt = <3300000>;
+		regulator-max-microvolt = <3300000>;
+	};
+};
diff --git a/Documentation/devicetree/bindings/serial/mtk-uart.txt b/Documentation/devicetree/bindings/serial/mtk-uart.txt
index 742cb470595b..bcfb13194f16 100644
--- a/Documentation/devicetree/bindings/serial/mtk-uart.txt
+++ b/Documentation/devicetree/bindings/serial/mtk-uart.txt
@@ -16,6 +16,7 @@ Required properties:
   * "mediatek,mt8127-uart" for MT8127 compatible UARTS
   * "mediatek,mt8135-uart" for MT8135 compatible UARTS
   * "mediatek,mt8173-uart" for MT8173 compatible UARTS
+  * "mediatek,mt8183-uart", "mediatek,mt6577-uart" for MT8183 compatible UARTS
   * "mediatek,mt6577-uart" for MT6577 and all of the above
 
 - reg: The base address of the UART register bank.
diff --git a/Documentation/devicetree/bindings/spi/fsl-spi.txt b/Documentation/devicetree/bindings/spi/fsl-spi.txt
index 8854004a1d3a..411375eac54d 100644
--- a/Documentation/devicetree/bindings/spi/fsl-spi.txt
+++ b/Documentation/devicetree/bindings/spi/fsl-spi.txt
@@ -18,6 +18,10 @@ Optional properties:
 - gpios : specifies the gpio pins to be used for chipselects.
   The gpios will be referred to as reg = <index> in the SPI child nodes.
   If unspecified, a single SPI device without a chip select can be used.
+- fsl,spisel_boot : for the MPC8306 and MPC8309, specifies that the
+  SPISEL_BOOT signal is used as chip select for a slave device. Use
+  reg = <number of gpios> in the corresponding child node, i.e. 0 if
+  the gpios property is not present.
 
 Example:
 	spi@4c0 {
diff --git a/Documentation/devicetree/bindings/spi/nvidia,tegra114-spi.txt b/Documentation/devicetree/bindings/spi/nvidia,tegra114-spi.txt
index 9ba7c5a273b4..db8e0d71c5bc 100644
--- a/Documentation/devicetree/bindings/spi/nvidia,tegra114-spi.txt
+++ b/Documentation/devicetree/bindings/spi/nvidia,tegra114-spi.txt
@@ -23,6 +23,18 @@ Required properties:
 Recommended properties:
 - spi-max-frequency: Definition as per
                      Documentation/devicetree/bindings/spi/spi-bus.txt
+Optional properties:
+- nvidia,tx-clk-tap-delay: Delays the clock going out to the external device
+  with this tap value. This property is used to tune the outgoing data from
+  Tegra SPI master with respect to outgoing Tegra SPI master clock.
+  Tap values vary based on the platform design trace lengths from Tegra SPI
+  to corresponding slave devices. Valid tap values are from 0 thru 63.
+- nvidia,rx-clk-tap-delay: Delays the clock coming in from the external device
+  with this tap value. This property is used to adjust the Tegra SPI master
+  clock with respect to the data from the SPI slave device.
+  Tap values vary based on the platform design trace lengths from Tegra SPI
+  to corresponding slave devices. Valid tap values are from 0 thru 63.
+
 Example:
 
 spi@7000d600 {
@@ -38,4 +50,12 @@ spi@7000d600 {
 	reset-names = "spi";
 	dmas = <&apbdma 16>, <&apbdma 16>;
 	dma-names = "rx", "tx";
+	<spi-client>@<bus_num> {
+		...
+		...
+		nvidia,rx-clk-tap-delay = <0>;
+		nvidia,tx-clk-tap-delay = <16>;
+		...
+	};
+
 };
diff --git a/Documentation/devicetree/bindings/spi/sh-msiof.txt b/Documentation/devicetree/bindings/spi/sh-msiof.txt
index 37cf69586d10..18e14ee257b2 100644
--- a/Documentation/devicetree/bindings/spi/sh-msiof.txt
+++ b/Documentation/devicetree/bindings/spi/sh-msiof.txt
@@ -4,6 +4,7 @@ Required properties:
 - compatible           : "renesas,msiof-r8a7743" (RZ/G1M)
 			 "renesas,msiof-r8a7744" (RZ/G1N)
 			 "renesas,msiof-r8a7745" (RZ/G1E)
+			 "renesas,msiof-r8a77470" (RZ/G1C)
 			 "renesas,msiof-r8a774a1" (RZ/G2M)
 			 "renesas,msiof-r8a774c0" (RZ/G2E)
 			 "renesas,msiof-r8a7790" (R-Car H2)
diff --git a/Documentation/devicetree/bindings/spi/snps,dw-apb-ssi.txt b/Documentation/devicetree/bindings/spi/snps,dw-apb-ssi.txt
index 2864bc6b659c..f54c8c36395e 100644
--- a/Documentation/devicetree/bindings/spi/snps,dw-apb-ssi.txt
+++ b/Documentation/devicetree/bindings/spi/snps,dw-apb-ssi.txt
@@ -8,9 +8,16 @@ Required properties:
 - interrupts : One interrupt, used by the controller.
 - #address-cells : <1>, as required by generic SPI binding.
 - #size-cells : <0>, also as required by generic SPI binding.
+- clocks : phandles for the clocks, see the description of clock-names below.
+   The phandle for the "ssi_clk" is required. The phandle for the "pclk" clock
+   is optional. If a single clock is specified but no clock-name, it is the
+   "ssi_clk" clock. If both clocks are listed, the "ssi_clk" must be first.
 
 Optional properties:
-- cs-gpios : Specifies the gpio pis to be used for chipselects.
+- clock-names : Contains the names of the clocks:
+    "ssi_clk", for the core clock used to generate the external SPI clock.
+    "pclk", the interface clock, required for register access.
+- cs-gpios : Specifies the gpio pins to be used for chipselects.
 - num-cs : The number of chipselects. If omitted, this will default to 4.
 - reg-io-width : The I/O register width (in bytes) implemented by this
   device.  Supported values are 2 or 4 (the default).
@@ -25,6 +32,7 @@ Example:
 		interrupts = <0 154 4>;
 		#address-cells = <1>;
 		#size-cells = <0>;
+		clocks = <&spi_m_clk>;
 		num-cs = <2>;
 		cs-gpios = <&gpio0 13 0>,
 			   <&gpio0 14 0>;
diff --git a/Documentation/devicetree/bindings/spi/spi-fsl-lpspi.txt b/Documentation/devicetree/bindings/spi/spi-fsl-lpspi.txt
index 6cc3c6fe25a3..e71b81a41ac0 100644
--- a/Documentation/devicetree/bindings/spi/spi-fsl-lpspi.txt
+++ b/Documentation/devicetree/bindings/spi/spi-fsl-lpspi.txt
@@ -7,7 +7,11 @@ Required properties:
 - reg : address and length of the lpspi master registers
 - interrupt-parent : core interrupt controller
 - interrupts : lpspi interrupt
-- clocks : lpspi clock specifier
+- clocks : lpspi clock specifier. Its number and order need to correspond to the
+	   value in clock-names.
+- clock-names : Corresponding to per clock and ipg clock in "clocks"
+		respectively. In i.MX7ULP, it only has per clk, so use CLK_DUMMY
+		to fill the "ipg" blank.
 - spi-slave : spi slave mode support. In slave mode, add this attribute without
 	      value. In master mode, remove it.
 
@@ -18,6 +22,8 @@ lpspi2: lpspi@40290000 {
 	reg = <0x40290000 0x10000>;
 	interrupt-parent = <&intc>;
 	interrupts = <GIC_SPI 28 IRQ_TYPE_LEVEL_HIGH>;
-	clocks = <&clks IMX7ULP_CLK_LPSPI2>;
+	clocks = <&clks IMX7ULP_CLK_LPSPI2>,
+		 <&clks IMX7ULP_CLK_DUMMY>;
+	clock-names = "per", "ipg";
 	spi-slave;
 };
diff --git a/Documentation/devicetree/bindings/spi/spi-mt65xx.txt b/Documentation/devicetree/bindings/spi/spi-mt65xx.txt
index 69c356767cf8..c0f6c8ecfa2e 100644
--- a/Documentation/devicetree/bindings/spi/spi-mt65xx.txt
+++ b/Documentation/devicetree/bindings/spi/spi-mt65xx.txt
@@ -10,6 +10,7 @@ Required properties:
     - mediatek,mt8135-spi: for mt8135 platforms
     - mediatek,mt8173-spi: for mt8173 platforms
     - mediatek,mt8183-spi: for mt8183 platforms
+    - "mediatek,mt8516-spi", "mediatek,mt2712-spi": for mt8516 platforms
 
 - #address-cells: should be 1.
 
diff --git a/Documentation/devicetree/bindings/spi/spi-mt7621.txt b/Documentation/devicetree/bindings/spi/spi-mt7621.txt
new file mode 100644
index 000000000000..d5baec0fa56e
--- /dev/null
+++ b/Documentation/devicetree/bindings/spi/spi-mt7621.txt
@@ -0,0 +1,26 @@
+Binding for MTK SPI controller (MT7621 MIPS)
+
+Required properties:
+- compatible: Should be one of the following:
+  - "ralink,mt7621-spi": for mt7621/mt7628/mt7688 platforms
+- #address-cells: should be 1.
+- #size-cells: should be 0.
+- reg: Address and length of the register set for the device
+- resets: phandle to the reset controller asserting this device in
+          reset
+  See ../reset/reset.txt for details.
+
+Optional properties:
+- cs-gpios: see spi-bus.txt.
+
+Example:
+
+- SoC Specific Portion:
+spi0: spi@b00 {
+	compatible = "ralink,mt7621-spi";
+	reg = <0xb00 0x100>;
+	#address-cells = <1>;
+	#size-cells = <0>;
+	resets = <&rstctrl 18>;
+	reset-names = "spi";
+};
diff --git a/Documentation/devicetree/bindings/spi/spi-zynq-qspi.txt b/Documentation/devicetree/bindings/spi/spi-zynq-qspi.txt
new file mode 100644
index 000000000000..16b734ad3102
--- /dev/null
+++ b/Documentation/devicetree/bindings/spi/spi-zynq-qspi.txt
@@ -0,0 +1,25 @@
+Xilinx Zynq QSPI controller Device Tree Bindings
+-------------------------------------------------------------------
+
+Required properties:
+- compatible		: Should be "xlnx,zynq-qspi-1.0".
+- reg			: Physical base address and size of QSPI registers map.
+- interrupts		: Property with a value describing the interrupt
+			  number.
+- clock-names		: List of input clock names - "ref_clk", "pclk"
+			  (See clock bindings for details).
+- clocks		: Clock phandles (see clock bindings for details).
+
+Optional properties:
+- num-cs		: Number of chip selects used.
+
+Example:
+	qspi: spi@e000d000 {
+		compatible = "xlnx,zynq-qspi-1.0";
+		reg = <0xe000d000 0x1000>;
+		interrupt-parent = <&intc>;
+		interrupts = <0 19 4>;
+		clock-names = "ref_clk", "pclk";
+		clocks = <&clkc 10>, <&clkc 43>;
+		num-cs = <1>;
+	};
diff --git a/Documentation/driver-api/acpi/index.rst b/Documentation/driver-api/acpi/index.rst
new file mode 100644
index 000000000000..ace0008e54c2
--- /dev/null
+++ b/Documentation/driver-api/acpi/index.rst
@@ -0,0 +1,9 @@
+============
+ACPI Support
+============
+
+.. toctree::
+   :maxdepth: 2
+
+   linuxized-acpica
+   scan_handlers
diff --git a/Documentation/acpi/linuxized-acpica.txt b/Documentation/driver-api/acpi/linuxized-acpica.rst
index 3ad7b0dfb083..0ca8f1538519 100644
--- a/Documentation/acpi/linuxized-acpica.txt
+++ b/Documentation/driver-api/acpi/linuxized-acpica.rst
@@ -1,31 +1,37 @@
+.. SPDX-License-Identifier: GPL-2.0
+.. include:: <isonum.txt>
+
+============================================================
 Linuxized ACPICA - Introduction to ACPICA Release Automation
+============================================================
 
-Copyright (C) 2013-2016, Intel Corporation
-Author: Lv Zheng <lv.zheng@intel.com>
+:Copyright: |copy| 2013-2016, Intel Corporation
 
+:Author: Lv Zheng <lv.zheng@intel.com>
 
-Abstract:
 
+Abstract
+========
 This document describes the ACPICA project and the relationship between
 ACPICA and Linux.  It also describes how ACPICA code in drivers/acpi/acpica,
 include/acpi and tools/power/acpi is automatically updated to follow the
 upstream.
 
+ACPICA Project
+==============
 
-1. ACPICA Project
-
-   The ACPI Component Architecture (ACPICA) project provides an operating
-   system (OS)-independent reference implementation of the Advanced
-   Configuration and Power Interface Specification (ACPI).  It has been
-   adapted by various host OSes.  By directly integrating ACPICA, Linux can
-   also benefit from the application experiences of ACPICA from other host
-   OSes.
+The ACPI Component Architecture (ACPICA) project provides an operating
+system (OS)-independent reference implementation of the Advanced
+Configuration and Power Interface Specification (ACPI).  It has been
+adapted by various host OSes.  By directly integrating ACPICA, Linux can
+also benefit from the application experiences of ACPICA from other host
+OSes.
 
-   The homepage of ACPICA project is: www.acpica.org, it is maintained and
-   supported by Intel Corporation.
+The homepage of ACPICA project is: www.acpica.org, it is maintained and
+supported by Intel Corporation.
 
-   The following figure depicts the Linux ACPI subsystem where the ACPICA
-   adaptation is included:
+The following figure depicts the Linux ACPI subsystem where the ACPICA
+adaptation is included::
 
       +---------------------------------------------------------+
       |                                                         |
@@ -71,21 +77,27 @@ upstream.
 
                  Figure 1. Linux ACPI Software Components
 
-   NOTE:
+.. note::
     A. OS Service Layer - Provided by Linux to offer OS dependent
        implementation of the predefined ACPICA interfaces (acpi_os_*).
+       ::
+
          include/acpi/acpiosxf.h
          drivers/acpi/osl.c
          include/acpi/platform
          include/asm/acenv.h
     B. ACPICA Functionality - Released from ACPICA code base to offer
        OS independent implementation of the ACPICA interfaces (acpi_*).
+       ::
+
          drivers/acpi/acpica
          include/acpi/ac*.h
          tools/power/acpi
     C. Linux/ACPI Functionality - Providing Linux specific ACPI
        functionality to the other Linux kernel subsystems and user space
        programs.
+       ::
+
          drivers/acpi
          include/linux/acpi.h
          include/linux/acpi*.h
@@ -95,24 +107,27 @@ upstream.
        ACPI subsystem to offer architecture specific implementation of the
        ACPI interfaces.  They are Linux specific components and are out of
        the scope of this document.
+       ::
+
          include/asm/acpi.h
          include/asm/acpi*.h
          arch/*/acpi
 
-2. ACPICA Release
+ACPICA Release
+==============
 
-   The ACPICA project maintains its code base at the following repository URL:
-   https://github.com/acpica/acpica.git. As a rule, a release is made every
-   month.
+The ACPICA project maintains its code base at the following repository URL:
+https://github.com/acpica/acpica.git. As a rule, a release is made every
+month.
 
-   As the coding style adopted by the ACPICA project is not acceptable by
-   Linux, there is a release process to convert the ACPICA git commits into
-   Linux patches.  The patches generated by this process are referred to as
-   "linuxized ACPICA patches".  The release process is carried out on a local
-   copy the ACPICA git repository.  Each commit in the monthly release is
-   converted into a linuxized ACPICA patch.  Together, they form the monthly
-   ACPICA release patchset for the Linux ACPI community.  This process is
-   illustrated in the following figure:
+As the coding style adopted by the ACPICA project is not acceptable by
+Linux, there is a release process to convert the ACPICA git commits into
+Linux patches.  The patches generated by this process are referred to as
+"linuxized ACPICA patches".  The release process is carried out on a local
+copy the ACPICA git repository.  Each commit in the monthly release is
+converted into a linuxized ACPICA patch.  Together, they form the monthly
+ACPICA release patchset for the Linux ACPI community.  This process is
+illustrated in the following figure::
 
     +-----------------------------+
     | acpica / master (-) commits |
@@ -153,7 +168,7 @@ upstream.
 
                 Figure 2. ACPICA -> Linux Upstream Process
 
-   NOTE:
+.. note::
     A. Linuxize Utilities - Provided by the ACPICA repository, including a
        utility located in source/tools/acpisrc folder and a number of
        scripts located in generate/linux folder.
@@ -170,19 +185,20 @@ upstream.
    following kernel configuration options:
    CONFIG_ACPI/CONFIG_ACPI_DEBUG/CONFIG_ACPI_DEBUGGER
 
-3. ACPICA Divergences
+ACPICA Divergences
+==================
 
-   Ideally, all of the ACPICA commits should be converted into Linux patches
-   automatically without manual modifications, the "linux / master" tree should
-   contain the ACPICA code that exactly corresponds to the ACPICA code
-   contained in "new linuxized acpica" tree and it should be possible to run
-   the release process fully automatically.
+Ideally, all of the ACPICA commits should be converted into Linux patches
+automatically without manual modifications, the "linux / master" tree should
+contain the ACPICA code that exactly corresponds to the ACPICA code
+contained in "new linuxized acpica" tree and it should be possible to run
+the release process fully automatically.
 
-   As a matter of fact, however, there are source code differences between
-   the ACPICA code in Linux and the upstream ACPICA code, referred to as
-   "ACPICA Divergences".
+As a matter of fact, however, there are source code differences between
+the ACPICA code in Linux and the upstream ACPICA code, referred to as
+"ACPICA Divergences".
 
-   The various sources of ACPICA divergences include:
+The various sources of ACPICA divergences include:
    1. Legacy divergences - Before the current ACPICA release process was
       established, there already had been divergences between Linux and
       ACPICA. Over the past several years those divergences have been greatly
@@ -213,11 +229,12 @@ upstream.
       rebased on the ACPICA side in order to offer better solutions, new ACPICA
       divergences are generated.
 
-4. ACPICA Development
+ACPICA Development
+==================
 
-   This paragraph guides Linux developers to use the ACPICA upstream release
-   utilities to obtain Linux patches corresponding to upstream ACPICA commits
-   before they become available from the ACPICA release process.
+This paragraph guides Linux developers to use the ACPICA upstream release
+utilities to obtain Linux patches corresponding to upstream ACPICA commits
+before they become available from the ACPICA release process.
 
    1. Cherry-pick an ACPICA commit
 
@@ -225,7 +242,7 @@ upstream.
    you want to cherry pick must be committed into the local repository.
 
    Then the gen-patch.sh command can help to cherry-pick an ACPICA commit
-   from the ACPICA local repository:
+   from the ACPICA local repository::
 
    $ git clone https://github.com/acpica/acpica
    $ cd acpica
@@ -240,7 +257,7 @@ upstream.
    changes that haven't been applied to Linux yet.
 
    You can generate the ACPICA release series yourself and rebase your code on
-   top of the generated ACPICA release patches:
+   top of the generated ACPICA release patches::
 
    $ git clone https://github.com/acpica/acpica
    $ cd acpica
@@ -254,7 +271,7 @@ upstream.
    3. Inspect the current divergences
 
    If you have local copies of both Linux and upstream ACPICA, you can generate
-   a diff file indicating the state of the current divergences:
+   a diff file indicating the state of the current divergences::
 
    # git clone https://github.com/acpica/acpica
    # git clone http://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git
diff --git a/Documentation/acpi/scan_handlers.txt b/Documentation/driver-api/acpi/scan_handlers.rst
index 3246ccf15992..7a197b3a33fc 100644
--- a/Documentation/acpi/scan_handlers.txt
+++ b/Documentation/driver-api/acpi/scan_handlers.rst
@@ -1,7 +1,13 @@
+.. SPDX-License-Identifier: GPL-2.0
+.. include:: <isonum.txt>
+
+==================
 ACPI Scan Handlers
+==================
+
+:Copyright: |copy| 2012, Intel Corporation
 
-Copyright (C) 2012, Intel Corporation
-Author: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
+:Author: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
 
 During system initialization and ACPI-based device hot-add, the ACPI namespace
 is scanned in search of device objects that generally represent various pieces
@@ -30,14 +36,14 @@ to configure that link so that the kernel can use it.
 Those additional configuration tasks usually depend on the type of the hardware
 component represented by the given device node which can be determined on the
 basis of the device node's hardware ID (HID).  They are performed by objects
-called ACPI scan handlers represented by the following structure:
+called ACPI scan handlers represented by the following structure::
 
-struct acpi_scan_handler {
-	const struct acpi_device_id *ids;
-	struct list_head list_node;
-	int (*attach)(struct acpi_device *dev, const struct acpi_device_id *id);
-	void (*detach)(struct acpi_device *dev);
-};
+	struct acpi_scan_handler {
+		const struct acpi_device_id *ids;
+		struct list_head list_node;
+		int (*attach)(struct acpi_device *dev, const struct acpi_device_id *id);
+		void (*detach)(struct acpi_device *dev);
+	};
 
 where ids is the list of IDs of device nodes the given handler is supposed to
 take care of, list_node is the hook to the global list of ACPI scan handlers
diff --git a/Documentation/driver-api/device-io.rst b/Documentation/driver-api/device-io.rst
index b00b23903078..0e389378f71d 100644
--- a/Documentation/driver-api/device-io.rst
+++ b/Documentation/driver-api/device-io.rst
@@ -103,51 +103,6 @@ continuing execution::
         ha->flags.ints_enabled = 0;
     }
 
-In addition to write posting, on some large multiprocessing systems
-(e.g. SGI Challenge, Origin and Altix machines) posted writes won't be
-strongly ordered coming from different CPUs. Thus it's important to
-properly protect parts of your driver that do memory-mapped writes with
-locks and use the :c:func:`mmiowb()` to make sure they arrive in the
-order intended. Issuing a regular readX() will also ensure write ordering,
-but should only be used when the 
-driver has to be sure that the write has actually arrived at the device
-(not that it's simply ordered with respect to other writes), since a
-full readX() is a relatively expensive operation.
-
-Generally, one should use :c:func:`mmiowb()` prior to releasing a spinlock
-that protects regions using :c:func:`writeb()` or similar functions that
-aren't surrounded by readb() calls, which will ensure ordering
-and flushing. The following pseudocode illustrates what might occur if
-write ordering isn't guaranteed via :c:func:`mmiowb()` or one of the
-readX() functions::
-
-    CPU A:  spin_lock_irqsave(&dev_lock, flags)
-    CPU A:  ...
-    CPU A:  writel(newval, ring_ptr);
-    CPU A:  spin_unlock_irqrestore(&dev_lock, flags)
-            ...
-    CPU B:  spin_lock_irqsave(&dev_lock, flags)
-    CPU B:  writel(newval2, ring_ptr);
-    CPU B:  ...
-    CPU B:  spin_unlock_irqrestore(&dev_lock, flags)
-
-In the case above, newval2 could be written to ring_ptr before newval.
-Fixing it is easy though::
-
-    CPU A:  spin_lock_irqsave(&dev_lock, flags)
-    CPU A:  ...
-    CPU A:  writel(newval, ring_ptr);
-    CPU A:  mmiowb(); /* ensure no other writes beat us to the device */
-    CPU A:  spin_unlock_irqrestore(&dev_lock, flags)
-            ...
-    CPU B:  spin_lock_irqsave(&dev_lock, flags)
-    CPU B:  writel(newval2, ring_ptr);
-    CPU B:  ...
-    CPU B:  mmiowb();
-    CPU B:  spin_unlock_irqrestore(&dev_lock, flags)
-
-See tg3.c for a real world example of how to use :c:func:`mmiowb()`
-
 PCI ordering rules also guarantee that PIO read responses arrive after any
 outstanding DMA writes from that bus, since for some devices the result of
 a readb() call may signal to the driver that a DMA transaction is
diff --git a/Documentation/driver-api/index.rst b/Documentation/driver-api/index.rst
index c0b600ed9961..aa87075c7846 100644
--- a/Documentation/driver-api/index.rst
+++ b/Documentation/driver-api/index.rst
@@ -56,6 +56,7 @@ available subsections can be seen below.
    slimbus
    soundwire/index
    fpga/index
+   acpi/index
 
 .. only::  subproject and html
 
diff --git a/Documentation/driver-api/pci/p2pdma.rst b/Documentation/driver-api/pci/p2pdma.rst
index 6d85b5a2598d..44deb52beeb4 100644
--- a/Documentation/driver-api/pci/p2pdma.rst
+++ b/Documentation/driver-api/pci/p2pdma.rst
@@ -132,10 +132,6 @@ precludes passing these pages to userspace.
 P2P memory is also technically IO memory but should never have any side
 effects behind it. Thus, the order of loads and stores should not be important
 and ioreadX(), iowriteX() and friends should not be necessary.
-However, as the memory is not cache coherent, if access ever needs to
-be protected by a spinlock then :c:func:`mmiowb()` must be used before
-unlocking the lock. (See ACQUIRES VS I/O ACCESSES in
-Documentation/memory-barriers.txt)
 
 
 P2P DMA Support Library
diff --git a/Documentation/driver-api/pm/cpuidle.rst b/Documentation/driver-api/pm/cpuidle.rst
index 5842ab621a58..006cf6db40c6 100644
--- a/Documentation/driver-api/pm/cpuidle.rst
+++ b/Documentation/driver-api/pm/cpuidle.rst
@@ -1,3 +1,6 @@
+.. SPDX-License-Identifier: GPL-2.0
+.. include:: <isonum.txt>
+
 .. |struct cpuidle_governor| replace:: :c:type:`struct cpuidle_governor <cpuidle_governor>`
 .. |struct cpuidle_device| replace:: :c:type:`struct cpuidle_device <cpuidle_device>`
 .. |struct cpuidle_driver| replace:: :c:type:`struct cpuidle_driver <cpuidle_driver>`
@@ -7,9 +10,9 @@
 CPU Idle Time Management
 ========================
 
-::
+:Copyright: |copy| 2019 Intel Corporation
 
- Copyright (c) 2019 Intel Corp., Rafael J. Wysocki <rafael.j.wysocki@intel.com>
+:Author: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
 
 
 CPU Idle Time Management Subsystem
diff --git a/Documentation/driver-api/pm/devices.rst b/Documentation/driver-api/pm/devices.rst
index 090c151aa86b..30835683616a 100644
--- a/Documentation/driver-api/pm/devices.rst
+++ b/Documentation/driver-api/pm/devices.rst
@@ -1,3 +1,6 @@
+.. SPDX-License-Identifier: GPL-2.0
+.. include:: <isonum.txt>
+
 .. |struct dev_pm_ops| replace:: :c:type:`struct dev_pm_ops <dev_pm_ops>`
 .. |struct dev_pm_domain| replace:: :c:type:`struct dev_pm_domain <dev_pm_domain>`
 .. |struct bus_type| replace:: :c:type:`struct bus_type <bus_type>`
@@ -12,11 +15,12 @@
 Device Power Management Basics
 ==============================
 
-::
+:Copyright: |copy| 2010-2011 Rafael J. Wysocki <rjw@sisk.pl>, Novell Inc.
+:Copyright: |copy| 2010 Alan Stern <stern@rowland.harvard.edu>
+:Copyright: |copy| 2016 Intel Corporation
+
+:Author: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
 
- Copyright (c) 2010-2011 Rafael J. Wysocki <rjw@sisk.pl>, Novell Inc.
- Copyright (c) 2010 Alan Stern <stern@rowland.harvard.edu>
- Copyright (c) 2016 Intel Corp., Rafael J. Wysocki <rafael.j.wysocki@intel.com>
 
 Most of the code in Linux is device drivers, so most of the Linux power
 management (PM) code is also driver-specific.  Most drivers will do very
diff --git a/Documentation/driver-api/pm/index.rst b/Documentation/driver-api/pm/index.rst
index 56975c6bc789..c2a9ef8d115c 100644
--- a/Documentation/driver-api/pm/index.rst
+++ b/Documentation/driver-api/pm/index.rst
@@ -1,3 +1,5 @@
+.. SPDX-License-Identifier: GPL-2.0
+
 ===============================
 CPU and Device Power Management
 ===============================
diff --git a/Documentation/driver-api/pm/notifiers.rst b/Documentation/driver-api/pm/notifiers.rst
index 62f860026992..186435c43b77 100644
--- a/Documentation/driver-api/pm/notifiers.rst
+++ b/Documentation/driver-api/pm/notifiers.rst
@@ -1,10 +1,14 @@
+.. SPDX-License-Identifier: GPL-2.0
+.. include:: <isonum.txt>
+
 =============================
 Suspend/Hibernation Notifiers
 =============================
 
-::
+:Copyright: |copy| 2016 Intel Corporation
+
+:Author: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
 
- Copyright (c) 2016 Intel Corp., Rafael J. Wysocki <rafael.j.wysocki@intel.com>
 
 There are some operations that subsystems or drivers may want to carry out
 before hibernation/suspend or after restore/resume, but they require the system
diff --git a/Documentation/driver-api/pm/types.rst b/Documentation/driver-api/pm/types.rst
index 3ebdecc54104..73a231caf764 100644
--- a/Documentation/driver-api/pm/types.rst
+++ b/Documentation/driver-api/pm/types.rst
@@ -1,3 +1,5 @@
+.. SPDX-License-Identifier: GPL-2.0
+
 ==================================
 Device Power Management Data Types
 ==================================
diff --git a/Documentation/driver-api/usb/power-management.rst b/Documentation/driver-api/usb/power-management.rst
index 79beb807996b..4a74cf6f2797 100644
--- a/Documentation/driver-api/usb/power-management.rst
+++ b/Documentation/driver-api/usb/power-management.rst
@@ -370,11 +370,15 @@ autosuspend the interface's device.  When the usage counter is = 0
 then the interface is considered to be idle, and the kernel may
 autosuspend the device.
 
-Drivers need not be concerned about balancing changes to the usage
-counter; the USB core will undo any remaining "get"s when a driver
-is unbound from its interface.  As a corollary, drivers must not call
-any of the ``usb_autopm_*`` functions after their ``disconnect``
-routine has returned.
+Drivers must be careful to balance their overall changes to the usage
+counter.  Unbalanced "get"s will remain in effect when a driver is
+unbound from its interface, preventing the device from going into
+runtime suspend should the interface be bound to a driver again.  On
+the other hand, drivers are allowed to achieve this balance by calling
+the ``usb_autopm_*`` functions even after their ``disconnect`` routine
+has returned -- say from within a work-queue routine -- provided they
+retain an active reference to the interface (via ``usb_get_intf`` and
+``usb_put_intf``).
 
 Drivers using the async routines are responsible for their own
 synchronization and mutual exclusion.
diff --git a/Documentation/features/time/modern-timekeeping/arch-support.txt b/Documentation/features/time/modern-timekeeping/arch-support.txt
index 2855dfe2464d..1d46da165b75 100644
--- a/Documentation/features/time/modern-timekeeping/arch-support.txt
+++ b/Documentation/features/time/modern-timekeeping/arch-support.txt
@@ -15,7 +15,7 @@
     |       h8300: |  ok  |
     |     hexagon: |  ok  |
     |        ia64: |  ok  |
-    |        m68k: | TODO |
+    |        m68k: |  ok  |
     |  microblaze: |  ok  |
     |        mips: |  ok  |
     |       nds32: |  ok  |
diff --git a/Documentation/filesystems/mount_api.txt b/Documentation/filesystems/mount_api.txt
index 944d1965e917..00ff0cfccfa7 100644
--- a/Documentation/filesystems/mount_api.txt
+++ b/Documentation/filesystems/mount_api.txt
@@ -12,11 +12,13 @@ CONTENTS
 
  (4) Filesystem context security.
 
- (5) VFS filesystem context operations.
+ (5) VFS filesystem context API.
 
- (6) Parameter description.
+ (6) Superblock creation helpers.
 
- (7) Parameter helper functions.
+ (7) Parameter description.
+
+ (8) Parameter helper functions.
 
 
 ========
@@ -41,12 +43,15 @@ The creation of new mounts is now to be done in a multistep process:
 
  (7) Destroy the context.
 
-To support this, the file_system_type struct gains a new field:
+To support this, the file_system_type struct gains two new fields:
 
 	int (*init_fs_context)(struct fs_context *fc);
+	const struct fs_parameter_description *parameters;
 
-which is invoked to set up the filesystem-specific parts of a filesystem
-context, including the additional space.
+The first is invoked to set up the filesystem-specific parts of a filesystem
+context, including the additional space, and the second points to the
+parameter description for validation at registration time and querying by a
+future system call.
 
 Note that security initialisation is done *after* the filesystem is called so
 that the namespaces may be adjusted first.
@@ -73,9 +78,9 @@ context.  This is represented by the fs_context structure:
 		void			*s_fs_info;
 		unsigned int		sb_flags;
 		unsigned int		sb_flags_mask;
+		unsigned int		s_iflags;
+		unsigned int		lsm_flags;
 		enum fs_context_purpose	purpose:8;
-		bool			sloppy:1;
-		bool			silent:1;
 		...
 	};
 
@@ -141,6 +146,10 @@ The fs_context fields are as follows:
 
      Which bits SB_* flags are to be set/cleared in super_block::s_flags.
 
+ (*) unsigned int s_iflags
+
+     These will be bitwise-OR'd with s->s_iflags when a superblock is created.
+
  (*) enum fs_context_purpose
 
      This indicates the purpose for which the context is intended.  The
@@ -150,17 +159,6 @@ The fs_context fields are as follows:
 	FS_CONTEXT_FOR_SUBMOUNT		-- New automatic submount of extant mount
 	FS_CONTEXT_FOR_RECONFIGURE	-- Change an existing mount
 
- (*) bool sloppy
- (*) bool silent
-
-     These are set if the sloppy or silent mount options are given.
-
-     [NOTE] sloppy is probably unnecessary when userspace passes over one
-     option at a time since the error can just be ignored if userspace deems it
-     to be unimportant.
-
-     [NOTE] silent is probably redundant with sb_flags & SB_SILENT.
-
 The mount context is created by calling vfs_new_fs_context() or
 vfs_dup_fs_context() and is destroyed with put_fs_context().  Note that the
 structure is not refcounted.
@@ -342,28 +340,47 @@ number of operations used by the new mount code for this purpose:
      It should return 0 on success or a negative error code on failure.
 
 
-=================================
-VFS FILESYSTEM CONTEXT OPERATIONS
-=================================
+==========================
+VFS FILESYSTEM CONTEXT API
+==========================
 
-There are four operations for creating a filesystem context and
-one for destroying a context:
+There are four operations for creating a filesystem context and one for
+destroying a context:
 
- (*) struct fs_context *vfs_new_fs_context(struct file_system_type *fs_type,
-					   struct dentry *reference,
-					   unsigned int sb_flags,
-					   unsigned int sb_flags_mask,
-					   enum fs_context_purpose purpose);
+ (*) struct fs_context *fs_context_for_mount(
+		struct file_system_type *fs_type,
+		unsigned int sb_flags);
 
-     Create a filesystem context for a given filesystem type and purpose.  This
-     allocates the filesystem context, sets the superblock flags, initialises
-     the security and calls fs_type->init_fs_context() to initialise the
-     filesystem private data.
+     Allocate a filesystem context for the purpose of setting up a new mount,
+     whether that be with a new superblock or sharing an existing one.  This
+     sets the superblock flags, initialises the security and calls
+     fs_type->init_fs_context() to initialise the filesystem private data.
 
-     reference can be NULL or it may indicate the root dentry of a superblock
-     that is going to be reconfigured (FS_CONTEXT_FOR_RECONFIGURE) or
-     the automount point that triggered a submount (FS_CONTEXT_FOR_SUBMOUNT).
-     This is provided as a source of namespace information.
+     fs_type specifies the filesystem type that will manage the context and
+     sb_flags presets the superblock flags stored therein.
+
+ (*) struct fs_context *fs_context_for_reconfigure(
+		struct dentry *dentry,
+		unsigned int sb_flags,
+		unsigned int sb_flags_mask);
+
+     Allocate a filesystem context for the purpose of reconfiguring an
+     existing superblock.  dentry provides a reference to the superblock to be
+     configured.  sb_flags and sb_flags_mask indicate which superblock flags
+     need changing and to what.
+
+ (*) struct fs_context *fs_context_for_submount(
+		struct file_system_type *fs_type,
+		struct dentry *reference);
+
+     Allocate a filesystem context for the purpose of creating a new mount for
+     an automount point or other derived superblock.  fs_type specifies the
+     filesystem type that will manage the context and the reference dentry
+     supplies the parameters.  Namespaces are propagated from the reference
+     dentry's superblock also.
+
+     Note that it's not a requirement that the reference dentry be of the same
+     filesystem type as fs_type.
 
  (*) struct fs_context *vfs_dup_fs_context(struct fs_context *src_fc);
 
@@ -390,20 +407,6 @@ context pointer or a negative error code.
 For the remaining operations, if an error occurs, a negative error code will be
 returned.
 
- (*) int vfs_get_tree(struct fs_context *fc);
-
-     Get or create the mountable root and superblock, using the parameters in
-     the filesystem context to select/configure the superblock.  This invokes
-     the ->validate() op and then the ->get_tree() op.
-
-     [NOTE] ->validate() could perhaps be rolled into ->get_tree() and
-     ->reconfigure().
-
- (*) struct vfsmount *vfs_create_mount(struct fs_context *fc);
-
-     Create a mount given the parameters in the specified filesystem context.
-     Note that this does not attach the mount to anything.
-
  (*) int vfs_parse_fs_param(struct fs_context *fc,
 			    struct fs_parameter *param);
 
@@ -432,17 +435,80 @@ returned.
      clear the pointer, but then becomes responsible for disposing of the
      object.
 
- (*) int vfs_parse_fs_string(struct fs_context *fc, char *key,
+ (*) int vfs_parse_fs_string(struct fs_context *fc, const char *key,
 			     const char *value, size_t v_size);
 
-     A wrapper around vfs_parse_fs_param() that just passes a constant string.
+     A wrapper around vfs_parse_fs_param() that copies the value string it is
+     passed.
 
  (*) int generic_parse_monolithic(struct fs_context *fc, void *data);
 
      Parse a sys_mount() data page, assuming the form to be a text list
      consisting of key[=val] options separated by commas.  Each item in the
      list is passed to vfs_mount_option().  This is the default when the
-     ->parse_monolithic() operation is NULL.
+     ->parse_monolithic() method is NULL.
+
+ (*) int vfs_get_tree(struct fs_context *fc);
+
+     Get or create the mountable root and superblock, using the parameters in
+     the filesystem context to select/configure the superblock.  This invokes
+     the ->get_tree() method.
+
+ (*) struct vfsmount *vfs_create_mount(struct fs_context *fc);
+
+     Create a mount given the parameters in the specified filesystem context.
+     Note that this does not attach the mount to anything.
+
+
+===========================
+SUPERBLOCK CREATION HELPERS
+===========================
+
+A number of VFS helpers are available for use by filesystems for the creation
+or looking up of superblocks.
+
+ (*) struct super_block *
+     sget_fc(struct fs_context *fc,
+	     int (*test)(struct super_block *sb, struct fs_context *fc),
+	     int (*set)(struct super_block *sb, struct fs_context *fc));
+
+     This is the core routine.  If test is non-NULL, it searches for an
+     existing superblock matching the criteria held in the fs_context, using
+     the test function to match them.  If no match is found, a new superblock
+     is created and the set function is called to set it up.
+
+     Prior to the set function being called, fc->s_fs_info will be transferred
+     to sb->s_fs_info - and fc->s_fs_info will be cleared if set returns
+     success (ie. 0).
+
+The following helpers all wrap sget_fc():
+
+ (*) int vfs_get_super(struct fs_context *fc,
+		       enum vfs_get_super_keying keying,
+		       int (*fill_super)(struct super_block *sb,
+					 struct fs_context *fc))
+
+     This creates/looks up a deviceless superblock.  The keying indicates how
+     many superblocks of this type may exist and in what manner they may be
+     shared:
+
+	(1) vfs_get_single_super
+
+	    Only one such superblock may exist in the system.  Any further
+	    attempt to get a new superblock gets this one (and any parameter
+	    differences are ignored).
+
+	(2) vfs_get_keyed_super
+
+	    Multiple superblocks of this type may exist and they're keyed on
+	    their s_fs_info pointer (for example this may refer to a
+	    namespace).
+
+	(3) vfs_get_independent_super
+
+	    Multiple independent superblocks of this type may exist.  This
+	    function never matches an existing one and always creates a new
+	    one.
 
 
 =====================
@@ -454,35 +520,22 @@ There's a core description struct that links everything together:
 
 	struct fs_parameter_description {
 		const char	name[16];
-		u8		nr_params;
-		u8		nr_alt_keys;
-		u8		nr_enums;
-		bool		ignore_unknown;
-		bool		no_source;
-		const char *const *keys;
-		const struct constant_table *alt_keys;
 		const struct fs_parameter_spec *specs;
 		const struct fs_parameter_enum *enums;
 	};
 
 For example:
 
-	enum afs_param {
+	enum {
 		Opt_autocell,
 		Opt_bar,
 		Opt_dyn,
 		Opt_foo,
 		Opt_source,
-		nr__afs_params
 	};
 
 	static const struct fs_parameter_description afs_fs_parameters = {
 		.name		= "kAFS",
-		.nr_params	= nr__afs_params,
-		.nr_alt_keys	= ARRAY_SIZE(afs_param_alt_keys),
-		.nr_enums	= ARRAY_SIZE(afs_param_enums),
-		.keys		= afs_param_keys,
-		.alt_keys	= afs_param_alt_keys,
 		.specs		= afs_param_specs,
 		.enums		= afs_param_enums,
 	};
@@ -494,28 +547,24 @@ The members are as follows:
      The name to be used in error messages generated by the parse helper
      functions.
 
- (2) u8 nr_params;
-
-     The number of discrete parameter identifiers.  This indicates the number
-     of elements in the ->types[] array and also limits the values that may be
-     used in the values that the ->keys[] array maps to.
-
-     It is expected that, for example, two parameters that are related, say
-     "acl" and "noacl" with have the same ID, but will be flagged to indicate
-     that one is the inverse of the other.  The value can then be picked out
-     from the parse result.
+ (2) const struct fs_parameter_specification *specs;
 
- (3) const struct fs_parameter_specification *specs;
+     Table of parameter specifications, terminated with a null entry, where the
+     entries are of type:
 
-     Table of parameter specifications, where the entries are of type:
-
-	struct fs_parameter_type {
-		enum fs_parameter_spec	type:8;
-		u8			flags;
+	struct fs_parameter_spec {
+		const char		*name;
+		u8			opt;
+		enum fs_parameter_type	type:8;
+		unsigned short		flags;
 	};
 
-     and the parameter identifier is the index to the array.  'type' indicates
-     the desired value type and must be one of:
+     The 'name' field is a string to match exactly to the parameter key (no
+     wildcards, patterns and no case-independence) and 'opt' is the value that
+     will be returned by the fs_parser() function in the case of a successful
+     match.
+
+     The 'type' field indicates the desired value type and must be one of:
 
 	TYPE NAME		EXPECTED VALUE		RESULT IN
 	=======================	=======================	=====================
@@ -525,85 +574,65 @@ The members are as follows:
 	fs_param_is_u32_octal	32-bit octal int	result->uint_32
 	fs_param_is_u32_hex	32-bit hex int		result->uint_32
 	fs_param_is_s32		32-bit signed int	result->int_32
+	fs_param_is_u64		64-bit unsigned int	result->uint_64
 	fs_param_is_enum	Enum value name 	result->uint_32
 	fs_param_is_string	Arbitrary string	param->string
 	fs_param_is_blob	Binary blob		param->blob
 	fs_param_is_blockdev	Blockdev path		* Needs lookup
 	fs_param_is_path	Path			* Needs lookup
-	fs_param_is_fd		File descriptor		param->file
-
-     And each parameter can be qualified with 'flags':
-
-     	fs_param_v_optional	The value is optional
-	fs_param_neg_with_no	If key name is prefixed with "no", it is false
-	fs_param_neg_with_empty	If value is "", it is false
-	fs_param_deprecated	The parameter is deprecated.
-
-     For example:
-
-	static const struct fs_parameter_spec afs_param_specs[nr__afs_params] = {
-		[Opt_autocell]	= { fs_param_is flag },
-		[Opt_bar]	= { fs_param_is_enum },
-		[Opt_dyn]	= { fs_param_is flag },
-		[Opt_foo]	= { fs_param_is_bool, fs_param_neg_with_no },
-		[Opt_source]	= { fs_param_is_string },
-	};
+	fs_param_is_fd		File descriptor		result->int_32
 
      Note that if the value is of fs_param_is_bool type, fs_parse() will try
      to match any string value against "0", "1", "no", "yes", "false", "true".
 
-     [!] NOTE that the table must be sorted according to primary key name so
-     	 that ->keys[] is also sorted.
-
- (4) const char *const *keys;
-
-     Table of primary key names for the parameters.  There must be one entry
-     per defined parameter.  The table is optional if ->nr_params is 0.  The
-     table is just an array of names e.g.:
+     Each parameter can also be qualified with 'flags':
 
-	static const char *const afs_param_keys[nr__afs_params] = {
-		[Opt_autocell]	= "autocell",
-		[Opt_bar]	= "bar",
-		[Opt_dyn]	= "dyn",
-		[Opt_foo]	= "foo",
-		[Opt_source]	= "source",
-	};
-
-     [!] NOTE that the table must be sorted such that the table can be searched
-     	 with bsearch() using strcmp().  This means that the Opt_* values must
-     	 correspond to the entries in this table.
-
- (5) const struct constant_table *alt_keys;
-     u8 nr_alt_keys;
-
-     Table of additional key names and their mappings to parameter ID plus the
-     number of elements in the table.  This is optional.  The table is just an
-     array of { name, integer } pairs, e.g.:
+	fs_param_v_optional	The value is optional
+	fs_param_neg_with_no	result->negated set if key is prefixed with "no"
+	fs_param_neg_with_empty	result->negated set if value is ""
+	fs_param_deprecated	The parameter is deprecated.
 
-	static const struct constant_table afs_param_keys[] = {
-		{ "baz",	Opt_bar },
-		{ "dynamic",	Opt_dyn },
+     These are wrapped with a number of convenience wrappers:
+
+	MACRO			SPECIFIES
+	=======================	===============================================
+	fsparam_flag()		fs_param_is_flag
+	fsparam_flag_no()	fs_param_is_flag, fs_param_neg_with_no
+	fsparam_bool()		fs_param_is_bool
+	fsparam_u32()		fs_param_is_u32
+	fsparam_u32oct()	fs_param_is_u32_octal
+	fsparam_u32hex()	fs_param_is_u32_hex
+	fsparam_s32()		fs_param_is_s32
+	fsparam_u64()		fs_param_is_u64
+	fsparam_enum()		fs_param_is_enum
+	fsparam_string()	fs_param_is_string
+	fsparam_blob()		fs_param_is_blob
+	fsparam_bdev()		fs_param_is_blockdev
+	fsparam_path()		fs_param_is_path
+	fsparam_fd()		fs_param_is_fd
+
+     all of which take two arguments, name string and option number - for
+     example:
+
+	static const struct fs_parameter_spec afs_param_specs[] = {
+		fsparam_flag	("autocell",	Opt_autocell),
+		fsparam_flag	("dyn",		Opt_dyn),
+		fsparam_string	("source",	Opt_source),
+		fsparam_flag_no	("foo",		Opt_foo),
+		{}
 	};
 
-     [!] NOTE that the table must be sorted such that strcmp() can be used with
-     	 bsearch() to search the entries.
-
-     The parameter ID can also be fs_param_key_removed to indicate that a
-     deprecated parameter has been removed and that an error will be given.
-     This differs from fs_param_deprecated where the parameter may still have
-     an effect.
-
-     Further, the behaviour of the parameter may differ when an alternate name
-     is used (for instance with NFS, "v3", "v4.2", etc. are alternate names).
+     An addition macro, __fsparam() is provided that takes an additional pair
+     of arguments to specify the type and the flags for anything that doesn't
+     match one of the above macros.
 
  (6) const struct fs_parameter_enum *enums;
-     u8 nr_enums;
 
-     Table of enum value names to integer mappings and the number of elements
-     stored therein.  This is of type:
+     Table of enum value names to integer mappings, terminated with a null
+     entry.  This is of type:
 
 	struct fs_parameter_enum {
-		u8		param_id;
+		u8		opt;
 		char		name[14];
 		u8		value;
 	};
@@ -621,11 +650,6 @@ The members are as follows:
      try to look the value up in the enum table and the result will be stored
      in the parse result.
 
- (7) bool no_source;
-
-     If this is set, fs_parse() will ignore any "source" parameter and not
-     pass it to the filesystem.
-
 The parser should be pointed to by the parser pointer in the file_system_type
 struct as this will provide validation on registration (if
 CONFIG_VALIDATE_FS_PARSER=y) and will allow the description to be queried from
@@ -650,9 +674,8 @@ process the parameters it is given.
 		int		value;
 	};
 
-     and it must be sorted such that it can be searched using bsearch() using
-     strcmp().  If a match is found, the corresponding value is returned.  If a
-     match isn't found, the not_found value is returned instead.
+     If a match is found, the corresponding value is returned.  If a match
+     isn't found, the not_found value is returned instead.
 
  (*) bool validate_constant_table(const struct constant_table *tbl,
 				  size_t tbl_size,
@@ -665,36 +688,36 @@ process the parameters it is given.
      should just be set to lie inside the low-to-high range.
 
      If all is good, true is returned.  If the table is invalid, errors are
-     logged to dmesg, the stack is dumped and false is returned.
+     logged to dmesg and false is returned.
+
+ (*) bool fs_validate_description(const struct fs_parameter_description *desc);
+
+     This performs some validation checks on a parameter description.  It
+     returns true if the description is good and false if it is not.  It will
+     log errors to dmesg if validation fails.
 
  (*) int fs_parse(struct fs_context *fc,
-		  const struct fs_param_parser *parser,
+		  const struct fs_parameter_description *desc,
 		  struct fs_parameter *param,
-		  struct fs_param_parse_result *result);
+		  struct fs_parse_result *result);
 
      This is the main interpreter of parameters.  It uses the parameter
-     description (parser) to look up the name of the parameter to use and to
-     convert that to a parameter ID (stored in result->key).
+     description to look up a parameter by key name and to convert that to an
+     option number (which it returns).
 
      If successful, and if the parameter type indicates the result is a
      boolean, integer or enum type, the value is converted by this function and
-     the result stored in result->{boolean,int_32,uint_32}.
+     the result stored in result->{boolean,int_32,uint_32,uint_64}.
 
      If a match isn't initially made, the key is prefixed with "no" and no
      value is present then an attempt will be made to look up the key with the
      prefix removed.  If this matches a parameter for which the type has flag
-     fs_param_neg_with_no set, then a match will be made and the value will be
-     set to false/0/NULL.
-
-     If the parameter is successfully matched and, optionally, parsed
-     correctly, 1 is returned.  If the parameter isn't matched and
-     parser->ignore_unknown is set, then 0 is returned.  Otherwise -EINVAL is
-     returned.
-
- (*) bool fs_validate_description(const struct fs_parameter_description *desc);
+     fs_param_neg_with_no set, then a match will be made and result->negated
+     will be set to true.
 
-     This is validates the parameter description.  It returns true if the
-     description is good and false if it is not.
+     If the parameter isn't matched, -ENOPARAM will be returned; if the
+     parameter is matched, but the value is erroneous, -EINVAL will be
+     returned; otherwise the parameter's option number will be returned.
 
  (*) int fs_lookup_param(struct fs_context *fc,
 			 struct fs_parameter *value,
diff --git a/Documentation/acpi/DSD-properties-rules.txt b/Documentation/firmware-guide/acpi/DSD-properties-rules.rst
index 3e4862bdad98..4306f29b6103 100644
--- a/Documentation/acpi/DSD-properties-rules.txt
+++ b/Documentation/firmware-guide/acpi/DSD-properties-rules.rst
@@ -1,8 +1,11 @@
+.. SPDX-License-Identifier: GPL-2.0
+
+==================================
 _DSD Device Properties Usage Rules
-----------------------------------
+==================================
 
 Properties, Property Sets and Property Subsets
-----------------------------------------------
+==============================================
 
 The _DSD (Device Specific Data) configuration object, introduced in ACPI 5.1,
 allows any type of device configuration data to be provided via the ACPI
@@ -18,7 +21,7 @@ specific type) associated with it.
 
 In the ACPI _DSD context it is an element of the sub-package following the
 generic Device Properties UUID in the _DSD return package as specified in the
-Device Properties UUID definition document [1].
+Device Properties UUID definition document [1]_.
 
 It also may be regarded as the definition of a key and the associated data type
 that can be returned by _DSD in the Device Properties UUID sub-package for a
@@ -33,14 +36,14 @@ Property subsets are nested collections of properties.  Each of them is
 associated with an additional key (name) allowing the subset to be referred
 to as a whole (and to be treated as a separate entity).  The canonical
 representation of property subsets is via the mechanism specified in the
-Hierarchical Properties Extension UUID definition document [2].
+Hierarchical Properties Extension UUID definition document [2]_.
 
 Property sets may be hierarchical.  That is, a property set may contain
 multiple property subsets that each may contain property subsets of its
 own and so on.
 
 General Validity Rule for Property Sets
----------------------------------------
+=======================================
 
 Valid property sets must follow the guidance given by the Device Properties UUID
 definition document [1].
@@ -73,7 +76,7 @@ suitable for the ACPI environment and consequently they cannot belong to a valid
 property set.
 
 Property Sets and Device Tree Bindings
---------------------------------------
+======================================
 
 It often is useful to make _DSD return property sets that follow Device Tree
 bindings.
@@ -91,7 +94,7 @@ expected to automatically work in the ACPI environment regardless of their
 contents.
 
 References
-----------
+==========
 
-[1] http://www.uefi.org/sites/default/files/resources/_DSD-device-properties-UUID.pdf
-[2] http://www.uefi.org/sites/default/files/resources/_DSD-hierarchical-data-extension-UUID-v1.1.pdf
+.. [1] http://www.uefi.org/sites/default/files/resources/_DSD-device-properties-UUID.pdf
+.. [2] http://www.uefi.org/sites/default/files/resources/_DSD-hierarchical-data-extension-UUID-v1.1.pdf
diff --git a/Documentation/acpi/acpi-lid.txt b/Documentation/firmware-guide/acpi/acpi-lid.rst
index effe7af3a5af..874ce0ed340d 100644
--- a/Documentation/acpi/acpi-lid.txt
+++ b/Documentation/firmware-guide/acpi/acpi-lid.rst
@@ -1,13 +1,18 @@
-Special Usage Model of the ACPI Control Method Lid Device
+.. SPDX-License-Identifier: GPL-2.0
+.. include:: <isonum.txt>
 
-Copyright (C) 2016, Intel Corporation
-Author: Lv Zheng <lv.zheng@intel.com>
+=========================================================
+Special Usage Model of the ACPI Control Method Lid Device
+=========================================================
 
+:Copyright: |copy| 2016, Intel Corporation
 
-Abstract:
+:Author: Lv Zheng <lv.zheng@intel.com>
 
-Platforms containing lids convey lid state (open/close) to OSPMs using a
-control method lid device. To implement this, the AML tables issue
+Abstract
+========
+Platforms containing lids convey lid state (open/close) to OSPMs
+using a control method lid device. To implement this, the AML tables issue
 Notify(lid_device, 0x80) to notify the OSPMs whenever the lid state has
 changed. The _LID control method for the lid device must be implemented to
 report the "current" state of the lid as either "opened" or "closed".
@@ -19,7 +24,8 @@ taken into account. This document describes the restrictions and the
 expections of the Linux ACPI lid device driver.
 
 
-1. Restrictions of the returning value of the _LID control method
+Restrictions of the returning value of the _LID control method
+==============================================================
 
 The _LID control method is described to return the "current" lid state.
 However the word of "current" has ambiguity, some buggy AML tables return
@@ -30,7 +36,8 @@ initial returning value. When the AML tables implement this control method
 with cached value, the initial returning value is likely not reliable.
 There are platforms always retun "closed" as initial lid state.
 
-2. Restrictions of the lid state change notifications
+Restrictions of the lid state change notifications
+==================================================
 
 There are buggy AML tables never notifying when the lid device state is
 changed to "opened". Thus the "opened" notification is not guaranteed. But
@@ -39,18 +46,22 @@ state is changed to "closed". The "closed" notification is normally used to
 trigger some system power saving operations on Windows. Since it is fully
 tested, it is reliable from all AML tables.
 
-3. Expections for the userspace users of the ACPI lid device driver
+Expections for the userspace users of the ACPI lid device driver
+================================================================
 
 The ACPI button driver exports the lid state to the userspace via the
-following file:
+following file::
+
   /proc/acpi/button/lid/LID0/state
+
 This file actually calls the _LID control method described above. And given
 the previous explanation, it is not reliable enough on some platforms. So
 it is advised for the userspace program to not to solely rely on this file
 to determine the actual lid state.
 
 The ACPI button driver emits the following input event to the userspace:
-  SW_LID
+  * SW_LID
+
 The ACPI lid device driver is implemented to try to deliver the platform
 triggered events to the userspace. However, given the fact that the buggy
 firmware cannot make sure "opened"/"closed" events are paired, the ACPI
@@ -59,20 +70,25 @@ button driver uses the following 3 modes in order not to trigger issues.
 If the userspace hasn't been prepared to ignore the unreliable "opened"
 events and the unreliable initial state notification, Linux users can use
 the following kernel parameters to handle the possible issues:
+
 A. button.lid_init_state=method:
    When this option is specified, the ACPI button driver reports the
    initial lid state using the returning value of the _LID control method
    and whether the "opened"/"closed" events are paired fully relies on the
    firmware implementation.
+
    This option can be used to fix some platforms where the returning value
    of the _LID control method is reliable but the initial lid state
    notification is missing.
+
    This option is the default behavior during the period the userspace
    isn't ready to handle the buggy AML tables.
+
 B. button.lid_init_state=open:
    When this option is specified, the ACPI button driver always reports the
    initial lid state as "opened" and whether the "opened"/"closed" events
    are paired fully relies on the firmware implementation.
+
    This may fix some platforms where the returning value of the _LID
    control method is not reliable and the initial lid state notification is
    missing.
@@ -80,6 +96,7 @@ B. button.lid_init_state=open:
 If the userspace has been prepared to ignore the unreliable "opened" events
 and the unreliable initial state notification, Linux users should always
 use the following kernel parameter:
+
 C. button.lid_init_state=ignore:
    When this option is specified, the ACPI button driver never reports the
    initial lid state and there is a compensation mechanism implemented to
@@ -89,6 +106,7 @@ C. button.lid_init_state=ignore:
    notifications can be delivered to the userspace when the lid is actually
    opens given that some AML tables do not send "opened" notifications
    reliably.
+
    In this mode, if everything is correctly implemented by the platform
    firmware, the old userspace programs should still work. Otherwise, the
    new userspace programs are required to work with the ACPI button driver.
diff --git a/Documentation/firmware-guide/acpi/aml-debugger.rst b/Documentation/firmware-guide/acpi/aml-debugger.rst
new file mode 100644
index 000000000000..a889d43bc6c5
--- /dev/null
+++ b/Documentation/firmware-guide/acpi/aml-debugger.rst
@@ -0,0 +1,75 @@
+.. SPDX-License-Identifier: GPL-2.0
+.. include:: <isonum.txt>
+
+================
+The AML Debugger
+================
+
+:Copyright: |copy| 2016, Intel Corporation
+:Author: Lv Zheng <lv.zheng@intel.com>
+
+
+This document describes the usage of the AML debugger embedded in the Linux
+kernel.
+
+1. Build the debugger
+=====================
+
+The following kernel configuration items are required to enable the AML
+debugger interface from the Linux kernel::
+
+   CONFIG_ACPI_DEBUGGER=y
+   CONFIG_ACPI_DEBUGGER_USER=m
+
+The userspace utilities can be built from the kernel source tree using
+the following commands::
+
+   $ cd tools
+   $ make acpi
+
+The resultant userspace tool binary is then located at::
+
+   tools/power/acpi/acpidbg
+
+It can be installed to system directories by running "make install" (as a
+sufficiently privileged user).
+
+2. Start the userspace debugger interface
+=========================================
+
+After booting the kernel with the debugger built-in, the debugger can be
+started by using the following commands::
+
+   # mount -t debugfs none /sys/kernel/debug
+   # modprobe acpi_dbg
+   # tools/power/acpi/acpidbg
+
+That spawns the interactive AML debugger environment where you can execute
+debugger commands.
+
+The commands are documented in the "ACPICA Overview and Programmer Reference"
+that can be downloaded from
+
+https://acpica.org/documentation
+
+The detailed debugger commands reference is located in Chapter 12 "ACPICA
+Debugger Reference".  The "help" command can be used for a quick reference.
+
+3. Stop the userspace debugger interface
+========================================
+
+The interactive debugger interface can be closed by pressing Ctrl+C or using
+the "quit" or "exit" commands.  When finished, unload the module with::
+
+   # rmmod acpi_dbg
+
+The module unloading may fail if there is an acpidbg instance running.
+
+4. Run the debugger in a script
+===============================
+
+It may be useful to run the AML debugger in a test script. "acpidbg" supports
+this in a special "batch" mode.  For example, the following command outputs
+the entire ACPI namespace::
+
+   # acpidbg -b "namespace"
diff --git a/Documentation/acpi/apei/einj.txt b/Documentation/firmware-guide/acpi/apei/einj.rst
index e550c8b98139..e588bccf5158 100644
--- a/Documentation/acpi/apei/einj.txt
+++ b/Documentation/firmware-guide/acpi/apei/einj.rst
@@ -1,13 +1,16 @@
-			APEI Error INJection
-			~~~~~~~~~~~~~~~~~~~~
+.. SPDX-License-Identifier: GPL-2.0
+
+====================
+APEI Error INJection
+====================
 
 EINJ provides a hardware error injection mechanism. It is very useful
 for debugging and testing APEI and RAS features in general.
 
 You need to check whether your BIOS supports EINJ first. For that, look
-for early boot messages similar to this one:
+for early boot messages similar to this one::
 
-ACPI: EINJ 0x000000007370A000 000150 (v01 INTEL           00000001 INTL 00000001)
+  ACPI: EINJ 0x000000007370A000 000150 (v01 INTEL           00000001 INTL 00000001)
 
 which shows that the BIOS is exposing an EINJ table - it is the
 mechanism through which the injection is done.
@@ -23,11 +26,11 @@ order to see the APEI,EINJ,... functionality supported and exposed by
 the BIOS menu.
 
 To use EINJ, make sure the following are options enabled in your kernel
-configuration:
+configuration::
 
-CONFIG_DEBUG_FS
-CONFIG_ACPI_APEI
-CONFIG_ACPI_APEI_EINJ
+  CONFIG_DEBUG_FS
+  CONFIG_ACPI_APEI
+  CONFIG_ACPI_APEI_EINJ
 
 The EINJ user interface is in <debugfs mount point>/apei/einj.
 
@@ -37,20 +40,22 @@ The following files belong to it:
 
   This file shows which error types are supported:
 
+  ================  ===================================
   Error Type Value	Error Description
-  ================	=================
-  0x00000001		Processor Correctable
-  0x00000002		Processor Uncorrectable non-fatal
-  0x00000004		Processor Uncorrectable fatal
-  0x00000008		Memory Correctable
-  0x00000010		Memory Uncorrectable non-fatal
-  0x00000020		Memory Uncorrectable fatal
-  0x00000040		PCI Express Correctable
-  0x00000080		PCI Express Uncorrectable fatal
-  0x00000100		PCI Express Uncorrectable non-fatal
-  0x00000200		Platform Correctable
-  0x00000400		Platform Uncorrectable non-fatal
-  0x00000800		Platform Uncorrectable fatal
+  ================  ===================================
+  0x00000001        Processor Correctable
+  0x00000002        Processor Uncorrectable non-fatal
+  0x00000004        Processor Uncorrectable fatal
+  0x00000008        Memory Correctable
+  0x00000010        Memory Uncorrectable non-fatal
+  0x00000020        Memory Uncorrectable fatal
+  0x00000040        PCI Express Correctable
+  0x00000080        PCI Express Uncorrectable fatal
+  0x00000100        PCI Express Uncorrectable non-fatal
+  0x00000200        Platform Correctable
+  0x00000400        Platform Uncorrectable non-fatal
+  0x00000800        Platform Uncorrectable fatal
+  ================  ===================================
 
   The format of the file contents are as above, except present are only
   the available error types.
@@ -73,9 +78,12 @@ The following files belong to it:
   injection. Value is a bitmask as specified in ACPI5.0 spec for the
   SET_ERROR_TYPE_WITH_ADDRESS data structure:
 
-	Bit 0 - Processor APIC field valid (see param3 below).
-	Bit 1 - Memory address and mask valid (param1 and param2).
-	Bit 2 - PCIe (seg,bus,dev,fn) valid (see param4 below).
+    Bit 0
+      Processor APIC field valid (see param3 below).
+    Bit 1
+      Memory address and mask valid (param1 and param2).
+    Bit 2
+      PCIe (seg,bus,dev,fn) valid (see param4 below).
 
   If set to zero, legacy behavior is mimicked where the type of
   injection specifies just one bit set, and param1 is multiplexed.
@@ -121,7 +129,7 @@ BIOS versions based on the ACPI 5.0 specification have more control over
 the target of the injection. For processor-related errors (type 0x1, 0x2
 and 0x4), you can set flags to 0x3 (param3 for bit 0, and param1 and
 param2 for bit 1) so that you have more information added to the error
-signature being injected. The actual data passed is this:
+signature being injected. The actual data passed is this::
 
 	memory_address = param1;
 	memory_address_range = param2;
@@ -131,7 +139,7 @@ signature being injected. The actual data passed is this:
 For memory errors (type 0x8, 0x10 and 0x20) the address is set using
 param1 with a mask in param2 (0x0 is equivalent to all ones). For PCI
 express errors (type 0x40, 0x80 and 0x100) the segment, bus, device and
-function are specified using param1:
+function are specified using param1::
 
          31     24 23    16 15    11 10      8  7        0
 	+-------------------------------------------------+
@@ -152,26 +160,26 @@ documentation for details (and expect changes to this API if vendors
 creativity in using this feature expands beyond our expectations).
 
 
-An error injection example:
+An error injection example::
 
-# cd /sys/kernel/debug/apei/einj
-# cat available_error_type		# See which errors can be injected
-0x00000002	Processor Uncorrectable non-fatal
-0x00000008	Memory Correctable
-0x00000010	Memory Uncorrectable non-fatal
-# echo 0x12345000 > param1		# Set memory address for injection
-# echo $((-1 << 12)) > param2		# Mask 0xfffffffffffff000 - anywhere in this page
-# echo 0x8 > error_type			# Choose correctable memory error
-# echo 1 > error_inject			# Inject now
+  # cd /sys/kernel/debug/apei/einj
+  # cat available_error_type		# See which errors can be injected
+  0x00000002	Processor Uncorrectable non-fatal
+  0x00000008	Memory Correctable
+  0x00000010	Memory Uncorrectable non-fatal
+  # echo 0x12345000 > param1		# Set memory address for injection
+  # echo $((-1 << 12)) > param2		# Mask 0xfffffffffffff000 - anywhere in this page
+  # echo 0x8 > error_type			# Choose correctable memory error
+  # echo 1 > error_inject			# Inject now
 
-You should see something like this in dmesg:
+You should see something like this in dmesg::
 
-[22715.830801] EDAC sbridge MC3: HANDLING MCE MEMORY ERROR
-[22715.834759] EDAC sbridge MC3: CPU 0: Machine Check Event: 0 Bank 7: 8c00004000010090
-[22715.834759] EDAC sbridge MC3: TSC 0
-[22715.834759] EDAC sbridge MC3: ADDR 12345000 EDAC sbridge MC3: MISC 144780c86
-[22715.834759] EDAC sbridge MC3: PROCESSOR 0:306e7 TIME 1422553404 SOCKET 0 APIC 0
-[22716.616173] EDAC MC3: 1 CE memory read error on CPU_SrcID#0_Channel#0_DIMM#0 (channel:0 slot:0 page:0x12345 offset:0x0 grain:32 syndrome:0x0 -  area:DRAM err_code:0001:0090 socket:0 channel_mask:1 rank:0)
+  [22715.830801] EDAC sbridge MC3: HANDLING MCE MEMORY ERROR
+  [22715.834759] EDAC sbridge MC3: CPU 0: Machine Check Event: 0 Bank 7: 8c00004000010090
+  [22715.834759] EDAC sbridge MC3: TSC 0
+  [22715.834759] EDAC sbridge MC3: ADDR 12345000 EDAC sbridge MC3: MISC 144780c86
+  [22715.834759] EDAC sbridge MC3: PROCESSOR 0:306e7 TIME 1422553404 SOCKET 0 APIC 0
+  [22716.616173] EDAC MC3: 1 CE memory read error on CPU_SrcID#0_Channel#0_DIMM#0 (channel:0 slot:0 page:0x12345 offset:0x0 grain:32 syndrome:0x0 -  area:DRAM err_code:0001:0090 socket:0 channel_mask:1 rank:0)
 
 For more information about EINJ, please refer to ACPI specification
 version 4.0, section 17.5 and ACPI 5.0, section 18.6.
diff --git a/Documentation/firmware-guide/acpi/apei/output_format.rst b/Documentation/firmware-guide/acpi/apei/output_format.rst
new file mode 100644
index 000000000000..c2e7ebddb529
--- /dev/null
+++ b/Documentation/firmware-guide/acpi/apei/output_format.rst
@@ -0,0 +1,150 @@
+.. SPDX-License-Identifier: GPL-2.0
+
+==================
+APEI output format
+==================
+
+APEI uses printk as hardware error reporting interface, the output
+format is as follow::
+
+        <error record> :=
+        APEI generic hardware error status
+        severity: <integer>, <severity string>
+        section: <integer>, severity: <integer>, <severity string>
+        flags: <integer>
+        <section flags strings>
+        fru_id: <uuid string>
+        fru_text: <string>
+        section_type: <section type string>
+        <section data>
+
+        <severity string>* := recoverable | fatal | corrected | info
+
+        <section flags strings># :=
+        [primary][, containment warning][, reset][, threshold exceeded]\
+        [, resource not accessible][, latent error]
+
+        <section type string> := generic processor error | memory error | \
+        PCIe error | unknown, <uuid string>
+
+        <section data> :=
+        <generic processor section data> | <memory section data> | \
+        <pcie section data> | <null>
+
+        <generic processor section data> :=
+        [processor_type: <integer>, <proc type string>]
+        [processor_isa: <integer>, <proc isa string>]
+        [error_type: <integer>
+        <proc error type strings>]
+        [operation: <integer>, <proc operation string>]
+        [flags: <integer>
+        <proc flags strings>]
+        [level: <integer>]
+        [version_info: <integer>]
+        [processor_id: <integer>]
+        [target_address: <integer>]
+        [requestor_id: <integer>]
+        [responder_id: <integer>]
+        [IP: <integer>]
+
+        <proc type string>* := IA32/X64 | IA64
+
+        <proc isa string>* := IA32 | IA64 | X64
+
+        <processor error type strings># :=
+        [cache error][, TLB error][, bus error][, micro-architectural error]
+
+        <proc operation string>* := unknown or generic | data read | data write | \
+        instruction execution
+
+        <proc flags strings># :=
+        [restartable][, precise IP][, overflow][, corrected]
+
+        <memory section data> :=
+        [error_status: <integer>]
+        [physical_address: <integer>]
+        [physical_address_mask: <integer>]
+        [node: <integer>]
+        [card: <integer>]
+        [module: <integer>]
+        [bank: <integer>]
+        [device: <integer>]
+        [row: <integer>]
+        [column: <integer>]
+        [bit_position: <integer>]
+        [requestor_id: <integer>]
+        [responder_id: <integer>]
+        [target_id: <integer>]
+        [error_type: <integer>, <mem error type string>]
+
+        <mem error type string>* :=
+        unknown | no error | single-bit ECC | multi-bit ECC | \
+        single-symbol chipkill ECC | multi-symbol chipkill ECC | master abort | \
+        target abort | parity error | watchdog timeout | invalid address | \
+        mirror Broken | memory sparing | scrub corrected error | \
+        scrub uncorrected error
+
+        <pcie section data> :=
+        [port_type: <integer>, <pcie port type string>]
+        [version: <integer>.<integer>]
+        [command: <integer>, status: <integer>]
+        [device_id: <integer>:<integer>:<integer>.<integer>
+        slot: <integer>
+        secondary_bus: <integer>
+        vendor_id: <integer>, device_id: <integer>
+        class_code: <integer>]
+        [serial number: <integer>, <integer>]
+        [bridge: secondary_status: <integer>, control: <integer>]
+        [aer_status: <integer>, aer_mask: <integer>
+        <aer status string>
+        [aer_uncor_severity: <integer>]
+        aer_layer=<aer layer string>, aer_agent=<aer agent string>
+        aer_tlp_header: <integer> <integer> <integer> <integer>]
+
+        <pcie port type string>* := PCIe end point | legacy PCI end point | \
+        unknown | unknown | root port | upstream switch port | \
+        downstream switch port | PCIe to PCI/PCI-X bridge | \
+        PCI/PCI-X to PCIe bridge | root complex integrated endpoint device | \
+        root complex event collector
+
+        if section severity is fatal or recoverable
+        <aer status string># :=
+        unknown | unknown | unknown | unknown | Data Link Protocol | \
+        unknown | unknown | unknown | unknown | unknown | unknown | unknown | \
+        Poisoned TLP | Flow Control Protocol | Completion Timeout | \
+        Completer Abort | Unexpected Completion | Receiver Overflow | \
+        Malformed TLP | ECRC | Unsupported Request
+        else
+        <aer status string># :=
+        Receiver Error | unknown | unknown | unknown | unknown | unknown | \
+        Bad TLP | Bad DLLP | RELAY_NUM Rollover | unknown | unknown | unknown | \
+        Replay Timer Timeout | Advisory Non-Fatal
+        fi
+
+        <aer layer string> :=
+        Physical Layer | Data Link Layer | Transaction Layer
+
+        <aer agent string> :=
+        Receiver ID | Requester ID | Completer ID | Transmitter ID
+
+Where, [] designate corresponding content is optional
+
+All <field string> description with * has the following format::
+
+        field: <integer>, <field string>
+
+Where value of <integer> should be the position of "string" in <field
+string> description. Otherwise, <field string> will be "unknown".
+
+All <field strings> description with # has the following format::
+
+        field: <integer>
+        <field strings>
+
+Where each string in <fields strings> corresponding to one set bit of
+<integer>. The bit position is the position of "string" in <field
+strings> description.
+
+For more detailed explanation of every field, please refer to UEFI
+specification version 2.3 or later, section Appendix N: Common
+Platform Error Record.
diff --git a/Documentation/acpi/debug.txt b/Documentation/firmware-guide/acpi/debug.rst
index 65bf47c46b6d..1a152dd1d765 100644
--- a/Documentation/acpi/debug.txt
+++ b/Documentation/firmware-guide/acpi/debug.rst
@@ -1,18 +1,21 @@
-			ACPI Debug Output
+.. SPDX-License-Identifier: GPL-2.0
 
+=================
+ACPI Debug Output
+=================
 
 The ACPI CA, the Linux ACPI core, and some ACPI drivers can generate debug
 output.  This document describes how to use this facility.
 
 Compile-time configuration
---------------------------
+==========================
 
 ACPI debug output is globally enabled by CONFIG_ACPI_DEBUG.  If this config
 option is turned off, the debug messages are not even built into the
 kernel.
 
 Boot- and run-time configuration
---------------------------------
+================================
 
 When CONFIG_ACPI_DEBUG=y, you can select the component and level of messages
 you're interested in.  At boot-time, use the acpi.debug_layer and
@@ -21,7 +24,7 @@ debug_layer and debug_level files in /sys/module/acpi/parameters/ to control
 the debug messages.
 
 debug_layer (component)
------------------------
+=======================
 
 The "debug_layer" is a mask that selects components of interest, e.g., a
 specific driver or part of the ACPI interpreter.  To build the debug_layer
@@ -33,7 +36,7 @@ to /sys/module/acpi/parameters/debug_layer.
 
 The possible components are defined in include/acpi/acoutput.h and
 include/acpi/acpi_drivers.h.  Reading /sys/module/acpi/parameters/debug_layer
-shows the supported mask values, currently these:
+shows the supported mask values, currently these::
 
     ACPI_UTILITIES                  0x00000001
     ACPI_HARDWARE                   0x00000002
@@ -65,7 +68,7 @@ shows the supported mask values, currently these:
     ACPI_PROCESSOR_COMPONENT        0x20000000
 
 debug_level
------------
+===========
 
 The "debug_level" is a mask that selects different types of messages, e.g.,
 those related to initialization, method execution, informational messages, etc.
@@ -81,7 +84,7 @@ to /sys/module/acpi/parameters/debug_level.
 
 The possible levels are defined in include/acpi/acoutput.h.  Reading
 /sys/module/acpi/parameters/debug_level shows the supported mask values,
-currently these:
+currently these::
 
     ACPI_LV_INIT                    0x00000001
     ACPI_LV_DEBUG_OBJECT            0x00000002
@@ -113,9 +116,9 @@ currently these:
     ACPI_LV_EVENTS                  0x80000000
 
 Examples
---------
+========
 
-For example, drivers/acpi/bus.c contains this:
+For example, drivers/acpi/bus.c contains this::
 
     #define _COMPONENT              ACPI_BUS_COMPONENT
     ...
@@ -127,22 +130,22 @@ statement uses ACPI_DB_INFO, which is macro based on the ACPI_LV_INFO
 definition.)
 
 Enable all AML "Debug" output (stores to the Debug object while interpreting
-AML) during boot:
+AML) during boot::
 
     acpi.debug_layer=0xffffffff acpi.debug_level=0x2
 
-Enable PCI and PCI interrupt routing debug messages:
+Enable PCI and PCI interrupt routing debug messages::
 
     acpi.debug_layer=0x400000 acpi.debug_level=0x4
 
-Enable all ACPI hardware-related messages:
+Enable all ACPI hardware-related messages::
 
     acpi.debug_layer=0x2 acpi.debug_level=0xffffffff
 
-Enable all ACPI_DB_INFO messages after boot:
+Enable all ACPI_DB_INFO messages after boot::
 
     # echo 0x4 > /sys/module/acpi/parameters/debug_level
 
-Show all valid component values:
+Show all valid component values::
 
     # cat /sys/module/acpi/parameters/debug_layer
diff --git a/Documentation/acpi/dsd/data-node-references.txt b/Documentation/firmware-guide/acpi/dsd/data-node-references.rst
index c3871565c8cf..1351984e767c 100644
--- a/Documentation/acpi/dsd/data-node-references.txt
+++ b/Documentation/firmware-guide/acpi/dsd/data-node-references.rst
@@ -1,9 +1,12 @@
-Copyright (C) 2018 Intel Corporation
-Author: Sakari Ailus <sakari.ailus@linux.intel.com>
-
+.. SPDX-License-Identifier: GPL-2.0
+.. include:: <isonum.txt>
 
+===================================
 Referencing hierarchical data nodes
------------------------------------
+===================================
+
+:Copyright: |copy| 2018 Intel Corporation
+:Author: Sakari Ailus <sakari.ailus@linux.intel.com>
 
 ACPI in general allows referring to device objects in the tree only.
 Hierarchical data extension nodes may not be referred to directly, hence this
@@ -28,13 +31,14 @@ extension key.
 
 
 Example
--------
+=======
 
-	In the ASL snippet below, the "reference" _DSD property [2] contains a
-	device object reference to DEV0 and under that device object, a
-	hierarchical data extension key "node@1" referring to the NOD1 object
-	and lastly, a hierarchical data extension key "anothernode" referring to
-	the ANOD object which is also the final target node of the reference.
+In the ASL snippet below, the "reference" _DSD property [2] contains a
+device object reference to DEV0 and under that device object, a
+hierarchical data extension key "node@1" referring to the NOD1 object
+and lastly, a hierarchical data extension key "anothernode" referring to
+the ANOD object which is also the final target node of the reference.
+::
 
 	Device (DEV0)
 	{
@@ -75,15 +79,15 @@ Example
 	    })
 	}
 
-Please also see a graph example in graph.txt .
+Please also see a graph example in :doc:`graph`.
 
 References
-----------
+==========
 
 [1] Hierarchical Data Extension UUID For _DSD.
-    <URL:http://www.uefi.org/sites/default/files/resources/_DSD-hierarchical-data-extension-UUID-v1.1.pdf>,
-    referenced 2018-07-17.
+<http://www.uefi.org/sites/default/files/resources/_DSD-hierarchical-data-extension-UUID-v1.1.pdf>,
+referenced 2018-07-17.
 
 [2] Device Properties UUID For _DSD.
-    <URL:http://www.uefi.org/sites/default/files/resources/_DSD-device-properties-UUID.pdf>,
-    referenced 2016-10-04.
+<http://www.uefi.org/sites/default/files/resources/_DSD-device-properties-UUID.pdf>,
+referenced 2016-10-04.
diff --git a/Documentation/acpi/dsd/graph.txt b/Documentation/firmware-guide/acpi/dsd/graph.rst
index b9ce910781dc..e0baed35b037 100644
--- a/Documentation/acpi/dsd/graph.txt
+++ b/Documentation/firmware-guide/acpi/dsd/graph.rst
@@ -1,8 +1,11 @@
-Graphs
+.. SPDX-License-Identifier: GPL-2.0
 
+======
+Graphs
+======
 
 _DSD
-----
+====
 
 _DSD (Device Specific Data) [7] is a predefined ACPI device
 configuration object that can be used to convey information on
@@ -30,7 +33,7 @@ hierarchical data extension array on each depth.
 
 
 Ports and endpoints
--------------------
+===================
 
 The port and endpoint concepts are very similar to those in Devicetree
 [3]. A port represents an interface in a device, and an endpoint
@@ -38,9 +41,9 @@ represents a connection to that interface.
 
 All port nodes are located under the device's "_DSD" node in the hierarchical
 data extension tree. The data extension related to each port node must begin
-with "port" and must be followed by the "@" character and the number of the port
-as its key. The target object it refers to should be called "PRTX", where "X" is
-the number of the port. An example of such a package would be:
+with "port" and must be followed by the "@" character and the number of the
+port as its key. The target object it refers to should be called "PRTX", where
+"X" is the number of the port. An example of such a package would be::
 
     Package() { "port@4", PRT4 }
 
@@ -49,7 +52,7 @@ data extension key of the endpoint nodes must begin with
 "endpoint" and must be followed by the "@" character and the number of the
 endpoint. The object it refers to should be called "EPXY", where "X" is the
 number of the port and "Y" is the number of the endpoint. An example of such a
-package would be:
+package would be::
 
     Package() { "endpoint@0", EP40 }
 
@@ -62,85 +65,85 @@ of that port shall be zero. Similarly, if a port may only have a single
 endpoint, the number of that endpoint shall be zero.
 
 The endpoint reference uses property extension with "remote-endpoint" property
-name followed by a reference in the same package. Such references consist of the
+name followed by a reference in the same package. Such references consist of
 the remote device reference, the first package entry of the port data extension
 reference under the device and finally the first package entry of the endpoint
-data extension reference under the port. Individual references thus appear as:
+data extension reference under the port. Individual references thus appear as::
 
     Package() { device, "port@X", "endpoint@Y" }
 
-In the above example, "X" is the number of the port and "Y" is the number of the
-endpoint.
+In the above example, "X" is the number of the port and "Y" is the number of
+the endpoint.
 
 The references to endpoints must be always done both ways, to the
 remote endpoint and back from the referred remote endpoint node.
 
-A simple example of this is show below:
+A simple example of this is show below::
 
     Scope (\_SB.PCI0.I2C2)
     {
-	Device (CAM0)
-	{
-	    Name (_DSD, Package () {
-		ToUUID("daffd814-6eba-4d8c-8a91-bc9bbf4aa301"),
-		Package () {
-		    Package () { "compatible", Package () { "nokia,smia" } },
-		},
-		ToUUID("dbb8e3e6-5886-4ba6-8795-1319f52a966b"),
-		Package () {
-		    Package () { "port@0", PRT0 },
-		}
-	    })
-	    Name (PRT0, Package() {
-		ToUUID("daffd814-6eba-4d8c-8a91-bc9bbf4aa301"),
-		Package () {
-		    Package () { "reg", 0 },
-		},
-		ToUUID("dbb8e3e6-5886-4ba6-8795-1319f52a966b"),
-		Package () {
-		    Package () { "endpoint@0", EP00 },
-		}
-	    })
-	    Name (EP00, Package() {
-		ToUUID("daffd814-6eba-4d8c-8a91-bc9bbf4aa301"),
-		Package () {
-		    Package () { "reg", 0 },
-		    Package () { "remote-endpoint", Package() { \_SB.PCI0.ISP, "port@4", "endpoint@0" } },
-		}
-	    })
-	}
+        Device (CAM0)
+        {
+            Name (_DSD, Package () {
+                ToUUID("daffd814-6eba-4d8c-8a91-bc9bbf4aa301"),
+                Package () {
+                    Package () { "compatible", Package () { "nokia,smia" } },
+                },
+                ToUUID("dbb8e3e6-5886-4ba6-8795-1319f52a966b"),
+                Package () {
+                    Package () { "port@0", PRT0 },
+                }
+            })
+            Name (PRT0, Package() {
+                ToUUID("daffd814-6eba-4d8c-8a91-bc9bbf4aa301"),
+                Package () {
+                    Package () { "reg", 0 },
+                },
+                ToUUID("dbb8e3e6-5886-4ba6-8795-1319f52a966b"),
+                Package () {
+                    Package () { "endpoint@0", EP00 },
+                }
+            })
+            Name (EP00, Package() {
+                ToUUID("daffd814-6eba-4d8c-8a91-bc9bbf4aa301"),
+                Package () {
+                    Package () { "reg", 0 },
+                    Package () { "remote-endpoint", Package() { \_SB.PCI0.ISP, "port@4", "endpoint@0" } },
+                }
+            })
+        }
     }
 
     Scope (\_SB.PCI0)
     {
-	Device (ISP)
-	{
-	    Name (_DSD, Package () {
-		ToUUID("dbb8e3e6-5886-4ba6-8795-1319f52a966b"),
-		Package () {
-		    Package () { "port@4", PRT4 },
-		}
-	    })
-
-	    Name (PRT4, Package() {
-		ToUUID("daffd814-6eba-4d8c-8a91-bc9bbf4aa301"),
-		Package () {
-		    Package () { "reg", 4 }, /* CSI-2 port number */
-		},
-		ToUUID("dbb8e3e6-5886-4ba6-8795-1319f52a966b"),
-		Package () {
-		    Package () { "endpoint@0", EP40 },
-		}
-	    })
-
-	    Name (EP40, Package() {
-		ToUUID("daffd814-6eba-4d8c-8a91-bc9bbf4aa301"),
-		Package () {
-		    Package () { "reg", 0 },
-		    Package () { "remote-endpoint", Package () { \_SB.PCI0.I2C2.CAM0, "port@0", "endpoint@0" } },
-		}
-	    })
-	}
+        Device (ISP)
+        {
+            Name (_DSD, Package () {
+                ToUUID("dbb8e3e6-5886-4ba6-8795-1319f52a966b"),
+                Package () {
+                    Package () { "port@4", PRT4 },
+                }
+            })
+
+            Name (PRT4, Package() {
+                ToUUID("daffd814-6eba-4d8c-8a91-bc9bbf4aa301"),
+                Package () {
+                    Package () { "reg", 4 }, /* CSI-2 port number */
+                },
+                ToUUID("dbb8e3e6-5886-4ba6-8795-1319f52a966b"),
+                Package () {
+                    Package () { "endpoint@0", EP40 },
+                }
+            })
+
+            Name (EP40, Package() {
+                ToUUID("daffd814-6eba-4d8c-8a91-bc9bbf4aa301"),
+                Package () {
+                    Package () { "reg", 0 },
+                    Package () { "remote-endpoint", Package () { \_SB.PCI0.I2C2.CAM0, "port@0", "endpoint@0" } },
+                }
+            })
+        }
     }
 
 Here, the port 0 of the "CAM0" device is connected to the port 4 of
@@ -148,27 +151,27 @@ the "ISP" device and vice versa.
 
 
 References
-----------
+==========
 
 [1] _DSD (Device Specific Data) Implementation Guide.
-    <URL:http://www.uefi.org/sites/default/files/resources/_DSD-implementation-guide-toplevel-1_1.htm>,
+    http://www.uefi.org/sites/default/files/resources/_DSD-implementation-guide-toplevel-1_1.htm,
     referenced 2016-10-03.
 
-[2] Devicetree. <URL:http://www.devicetree.org>, referenced 2016-10-03.
+[2] Devicetree. http://www.devicetree.org, referenced 2016-10-03.
 
 [3] Documentation/devicetree/bindings/graph.txt
 
 [4] Device Properties UUID For _DSD.
-    <URL:http://www.uefi.org/sites/default/files/resources/_DSD-device-properties-UUID.pdf>,
+    http://www.uefi.org/sites/default/files/resources/_DSD-device-properties-UUID.pdf,
     referenced 2016-10-04.
 
 [5] Hierarchical Data Extension UUID For _DSD.
-    <URL:http://www.uefi.org/sites/default/files/resources/_DSD-hierarchical-data-extension-UUID-v1.1.pdf>,
+    http://www.uefi.org/sites/default/files/resources/_DSD-hierarchical-data-extension-UUID-v1.1.pdf,
     referenced 2016-10-04.
 
 [6] Advanced Configuration and Power Interface Specification.
-    <URL:http://www.uefi.org/sites/default/files/resources/ACPI_6_1.pdf>,
+    http://www.uefi.org/sites/default/files/resources/ACPI_6_1.pdf,
     referenced 2016-10-04.
 
 [7] _DSD Device Properties Usage Rules.
-    Documentation/acpi/DSD-properties-rules.txt
+    :doc:`../DSD-properties-rules`
diff --git a/Documentation/acpi/enumeration.txt b/Documentation/firmware-guide/acpi/enumeration.rst
index 7bcf9c3d9fbe..6b32b7be8c85 100644
--- a/Documentation/acpi/enumeration.txt
+++ b/Documentation/firmware-guide/acpi/enumeration.rst
@@ -1,5 +1,9 @@
-ACPI based device enumeration
-~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+.. SPDX-License-Identifier: GPL-2.0
+
+=============================
+ACPI Based Device Enumeration
+=============================
+
 ACPI 5 introduced a set of new resources (UartTSerialBus, I2cSerialBus,
 SpiSerialBus, GpioIo and GpioInt) which can be used in enumerating slave
 devices behind serial bus controllers.
@@ -11,12 +15,12 @@ that are accessed through memory-mapped registers.
 In order to support this and re-use the existing drivers as much as
 possible we decided to do following:
 
-	o Devices that have no bus connector resource are represented as
-	  platform devices.
+  - Devices that have no bus connector resource are represented as
+    platform devices.
 
-	o Devices behind real busses where there is a connector resource
-	  are represented as struct spi_device or struct i2c_device
-	  (standard UARTs are not busses so there is no struct uart_device).
+  - Devices behind real busses where there is a connector resource
+    are represented as struct spi_device or struct i2c_device
+    (standard UARTs are not busses so there is no struct uart_device).
 
 As both ACPI and Device Tree represent a tree of devices (and their
 resources) this implementation follows the Device Tree way as much as
@@ -31,7 +35,8 @@ enumerated from ACPI namespace. This handle can be used to extract other
 device-specific configuration. There is an example of this below.
 
 Platform bus support
-~~~~~~~~~~~~~~~~~~~~
+====================
+
 Since we are using platform devices to represent devices that are not
 connected to any physical bus we only need to implement a platform driver
 for the device and add supported ACPI IDs. If this same IP-block is used on
@@ -39,7 +44,7 @@ some other non-ACPI platform, the driver might work out of the box or needs
 some minor changes.
 
 Adding ACPI support for an existing driver should be pretty
-straightforward. Here is the simplest example:
+straightforward. Here is the simplest example::
 
 	#ifdef CONFIG_ACPI
 	static const struct acpi_device_id mydrv_acpi_match[] = {
@@ -61,12 +66,13 @@ configuring GPIOs it can get its ACPI handle and extract this information
 from ACPI tables.
 
 DMA support
-~~~~~~~~~~~
+===========
+
 DMA controllers enumerated via ACPI should be registered in the system to
 provide generic access to their resources. For example, a driver that would
 like to be accessible to slave devices via generic API call
 dma_request_slave_channel() must register itself at the end of the probe
-function like this:
+function like this::
 
 	err = devm_acpi_dma_controller_register(dev, xlate_func, dw);
 	/* Handle the error if it's not a case of !CONFIG_ACPI */
@@ -74,7 +80,7 @@ function like this:
 and implement custom xlate function if needed (usually acpi_dma_simple_xlate()
 is enough) which converts the FixedDMA resource provided by struct
 acpi_dma_spec into the corresponding DMA channel. A piece of code for that case
-could look like:
+could look like::
 
 	#ifdef CONFIG_ACPI
 	struct filter_args {
@@ -114,7 +120,7 @@ provided by struct acpi_dma.
 Clients must call dma_request_slave_channel() with the string parameter that
 corresponds to a specific FixedDMA resource. By default "tx" means the first
 entry of the FixedDMA resource array, "rx" means the second entry. The table
-below shows a layout:
+below shows a layout::
 
 	Device (I2C0)
 	{
@@ -138,12 +144,13 @@ acpi_dma_request_slave_chan_by_index() directly and therefore choose the
 specific FixedDMA resource by its index.
 
 SPI serial bus support
-~~~~~~~~~~~~~~~~~~~~~~
+======================
+
 Slave devices behind SPI bus have SpiSerialBus resource attached to them.
 This is extracted automatically by the SPI core and the slave devices are
 enumerated once spi_register_master() is called by the bus driver.
 
-Here is what the ACPI namespace for a SPI slave might look like:
+Here is what the ACPI namespace for a SPI slave might look like::
 
 	Device (EEP0)
 	{
@@ -163,7 +170,7 @@ Here is what the ACPI namespace for a SPI slave might look like:
 
 The SPI device drivers only need to add ACPI IDs in a similar way than with
 the platform device drivers. Below is an example where we add ACPI support
-to at25 SPI eeprom driver (this is meant for the above ACPI snippet):
+to at25 SPI eeprom driver (this is meant for the above ACPI snippet)::
 
 	#ifdef CONFIG_ACPI
 	static const struct acpi_device_id at25_acpi_match[] = {
@@ -182,7 +189,7 @@ to at25 SPI eeprom driver (this is meant for the above ACPI snippet):
 
 Note that this driver actually needs more information like page size of the
 eeprom etc. but at the time writing this there is no standard way of
-passing those. One idea is to return this in _DSM method like:
+passing those. One idea is to return this in _DSM method like::
 
 	Device (EEP0)
 	{
@@ -202,7 +209,7 @@ passing those. One idea is to return this in _DSM method like:
 		}
 
 Then the at25 SPI driver can get this configuration by calling _DSM on its
-ACPI handle like:
+ACPI handle like::
 
 	struct acpi_buffer output = { ACPI_ALLOCATE_BUFFER, NULL };
 	struct acpi_object_list input;
@@ -220,14 +227,15 @@ ACPI handle like:
 	kfree(output.pointer);
 
 I2C serial bus support
-~~~~~~~~~~~~~~~~~~~~~~
+======================
+
 The slaves behind I2C bus controller only need to add the ACPI IDs like
 with the platform and SPI drivers. The I2C core automatically enumerates
 any slave devices behind the controller device once the adapter is
 registered.
 
 Below is an example of how to add ACPI support to the existing mpu3050
-input driver:
+input driver::
 
 	#ifdef CONFIG_ACPI
 	static const struct acpi_device_id mpu3050_acpi_match[] = {
@@ -251,56 +259,57 @@ input driver:
 	};
 
 GPIO support
-~~~~~~~~~~~~
+============
+
 ACPI 5 introduced two new resources to describe GPIO connections: GpioIo
 and GpioInt. These resources can be used to pass GPIO numbers used by
 the device to the driver. ACPI 5.1 extended this with _DSD (Device
 Specific Data) which made it possible to name the GPIOs among other things.
 
-For example:
+For example::
 
-Device (DEV)
-{
-	Method (_CRS, 0, NotSerialized)
+	Device (DEV)
 	{
-		Name (SBUF, ResourceTemplate()
+		Method (_CRS, 0, NotSerialized)
 		{
-			...
-			// Used to power on/off the device
-			GpioIo (Exclusive, PullDefault, 0x0000, 0x0000,
-				IoRestrictionOutputOnly, "\\_SB.PCI0.GPI0",
-				0x00, ResourceConsumer,,)
+			Name (SBUF, ResourceTemplate()
 			{
-				// Pin List
-				0x0055
-			}
+				...
+				// Used to power on/off the device
+				GpioIo (Exclusive, PullDefault, 0x0000, 0x0000,
+					IoRestrictionOutputOnly, "\\_SB.PCI0.GPI0",
+					0x00, ResourceConsumer,,)
+				{
+					// Pin List
+					0x0055
+				}
+
+				// Interrupt for the device
+				GpioInt (Edge, ActiveHigh, ExclusiveAndWake, PullNone,
+					0x0000, "\\_SB.PCI0.GPI0", 0x00, ResourceConsumer,,)
+				{
+					// Pin list
+					0x0058
+				}
+
+				...
 
-			// Interrupt for the device
-			GpioInt (Edge, ActiveHigh, ExclusiveAndWake, PullNone,
-				 0x0000, "\\_SB.PCI0.GPI0", 0x00, ResourceConsumer,,)
-			{
-				// Pin list
-				0x0058
 			}
 
-			...
-
+			Return (SBUF)
 		}
 
-		Return (SBUF)
-	}
-
-	// ACPI 5.1 _DSD used for naming the GPIOs
-	Name (_DSD, Package ()
-	{
-		ToUUID("daffd814-6eba-4d8c-8a91-bc9bbf4aa301"),
-		Package ()
+		// ACPI 5.1 _DSD used for naming the GPIOs
+		Name (_DSD, Package ()
 		{
-			Package () {"power-gpios", Package() {^DEV, 0, 0, 0 }},
-			Package () {"irq-gpios", Package() {^DEV, 1, 0, 0 }},
-		}
-	})
-	...
+			ToUUID("daffd814-6eba-4d8c-8a91-bc9bbf4aa301"),
+			Package ()
+			{
+				Package () {"power-gpios", Package() {^DEV, 0, 0, 0 }},
+				Package () {"irq-gpios", Package() {^DEV, 1, 0, 0 }},
+			}
+		})
+		...
 
 These GPIO numbers are controller relative and path "\\_SB.PCI0.GPI0"
 specifies the path to the controller. In order to use these GPIOs in Linux
@@ -310,7 +319,7 @@ There is a standard GPIO API for that and is documented in
 Documentation/gpio/.
 
 In the above example we can get the corresponding two GPIO descriptors with
-a code like this:
+a code like this::
 
 	#include <linux/gpio/consumer.h>
 	...
@@ -334,21 +343,22 @@ See Documentation/acpi/gpio-properties.txt for more information about the
 _DSD binding related to GPIOs.
 
 MFD devices
-~~~~~~~~~~~
+===========
+
 The MFD devices register their children as platform devices. For the child
 devices there needs to be an ACPI handle that they can use to reference
 parts of the ACPI namespace that relate to them. In the Linux MFD subsystem
 we provide two ways:
 
-	o The children share the parent ACPI handle.
-	o The MFD cell can specify the ACPI id of the device.
+  - The children share the parent ACPI handle.
+  - The MFD cell can specify the ACPI id of the device.
 
 For the first case, the MFD drivers do not need to do anything. The
 resulting child platform device will have its ACPI_COMPANION() set to point
 to the parent device.
 
 If the ACPI namespace has a device that we can match using an ACPI id or ACPI
-adr, the cell should be set like:
+adr, the cell should be set like::
 
 	static struct mfd_cell_acpi_match my_subdevice_cell_acpi_match = {
 		.pnpid = "XYZ0001",
@@ -366,7 +376,8 @@ the MFD device and if found, that ACPI companion device is bound to the
 resulting child platform device.
 
 Device Tree namespace link device ID
-~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+====================================
+
 The Device Tree protocol uses device identification based on the "compatible"
 property whose value is a string or an array of strings recognized as device
 identifiers by drivers and the driver core.  The set of all those strings may be
@@ -410,6 +421,32 @@ Specifically, the device IDs returned by _HID and preceding PRP0001 in the _CID
 return package will be checked first.  Also in that case the bus type the device
 will be enumerated to depends on the device ID returned by _HID.
 
+For example, the following ACPI sample might be used to enumerate an lm75-type
+I2C temperature sensor and match it to the driver using the Device Tree
+namespace link:
+
+	Device (TMP0)
+	{
+		Name (_HID, "PRP0001")
+		Name (_DSD, Package() {
+			ToUUID("daffd814-6eba-4d8c-8a91-bc9bbf4aa301"),
+			Package () {
+				Package (2) { "compatible", "ti,tmp75" },
+			}
+		})
+		Method (_CRS, 0, Serialized)
+		{
+			Name (SBUF, ResourceTemplate ()
+			{
+				I2cSerialBusV2 (0x48, ControllerInitiated,
+					400000, AddressingMode7Bit,
+					"\\_SB.PCI0.I2C1", 0x00,
+					ResourceConsumer, , Exclusive,)
+			})
+			Return (SBUF)
+		}
+	}
+
 It is valid to define device objects with a _HID returning PRP0001 and without
 the "compatible" property in the _DSD or a _CID as long as one of their
 ancestors provides a _DSD with a valid "compatible" property.  Such device
@@ -423,4 +460,4 @@ the _DSD of the device object itself or the _DSD of its ancestor in the
 Otherwise, the _DSD itself is regarded as invalid and therefore the "compatible"
 property returned by it is meaningless.
 
-Refer to DSD-properties-rules.txt for more information.
+Refer to :doc:`DSD-properties-rules` for more information.
diff --git a/Documentation/acpi/gpio-properties.txt b/Documentation/firmware-guide/acpi/gpio-properties.rst
index 88c65cb5bf0a..bb6d74f23ee0 100644
--- a/Documentation/acpi/gpio-properties.txt
+++ b/Documentation/firmware-guide/acpi/gpio-properties.rst
@@ -1,5 +1,8 @@
+.. SPDX-License-Identifier: GPL-2.0
+
+======================================
 _DSD Device Properties Related to GPIO
---------------------------------------
+======================================
 
 With the release of ACPI 5.1, the _DSD configuration object finally
 allows names to be given to GPIOs (and other things as well) returned
@@ -8,7 +11,7 @@ the corresponding GPIO, which is pretty error prone (it depends on
 the _CRS output ordering, for example).
 
 With _DSD we can now query GPIOs using a name instead of an integer
-index, like the ASL example below shows:
+index, like the ASL example below shows::
 
   // Bluetooth device with reset and shutdown GPIOs
   Device (BTH)
@@ -34,15 +37,19 @@ index, like the ASL example below shows:
       })
   }
 
-The format of the supported GPIO property is:
+The format of the supported GPIO property is::
 
   Package () { "name", Package () { ref, index, pin, active_low }}
 
-  ref - The device that has _CRS containing GpioIo()/GpioInt() resources,
-        typically this is the device itself (BTH in our case).
-  index - Index of the GpioIo()/GpioInt() resource in _CRS starting from zero.
-  pin - Pin in the GpioIo()/GpioInt() resource. Typically this is zero.
-  active_low - If 1 the GPIO is marked as active_low.
+ref
+  The device that has _CRS containing GpioIo()/GpioInt() resources,
+  typically this is the device itself (BTH in our case).
+index
+  Index of the GpioIo()/GpioInt() resource in _CRS starting from zero.
+pin
+  Pin in the GpioIo()/GpioInt() resource. Typically this is zero.
+active_low
+  If 1 the GPIO is marked as active_low.
 
 Since ACPI GpioIo() resource does not have a field saying whether it is
 active low or high, the "active_low" argument can be used here.  Setting
@@ -55,7 +62,7 @@ It is possible to leave holes in the array of GPIOs. This is useful in
 cases like with SPI host controllers where some chip selects may be
 implemented as GPIOs and some as native signals. For example a SPI host
 controller can have chip selects 0 and 2 implemented as GPIOs and 1 as
-native:
+native::
 
   Package () {
       "cs-gpios",
@@ -67,7 +74,7 @@ native:
   }
 
 Other supported properties
---------------------------
+==========================
 
 Following Device Tree compatible device properties are also supported by
 _DSD device properties for GPIO controllers:
@@ -78,7 +85,7 @@ _DSD device properties for GPIO controllers:
 - input
 - line-name
 
-Example:
+Example::
 
   Name (_DSD, Package () {
       // _DSD Hierarchical Properties Extension UUID
@@ -100,7 +107,7 @@ Example:
 
 - gpio-line-names
 
-Example:
+Example::
 
   Package () {
       "gpio-line-names",
@@ -114,7 +121,7 @@ See Documentation/devicetree/bindings/gpio/gpio.txt for more information
 about these properties.
 
 ACPI GPIO Mappings Provided by Drivers
---------------------------------------
+======================================
 
 There are systems in which the ACPI tables do not contain _DSD but provide _CRS
 with GpioIo()/GpioInt() resources and device drivers still need to work with
@@ -139,16 +146,16 @@ line in that resource starting from zero, and the active-low flag for that line,
 respectively, in analogy with the _DSD GPIO property format specified above.
 
 For the example Bluetooth device discussed previously the data structures in
-question would look like this:
+question would look like this::
 
-static const struct acpi_gpio_params reset_gpio = { 1, 1, false };
-static const struct acpi_gpio_params shutdown_gpio = { 0, 0, false };
+  static const struct acpi_gpio_params reset_gpio = { 1, 1, false };
+  static const struct acpi_gpio_params shutdown_gpio = { 0, 0, false };
 
-static const struct acpi_gpio_mapping bluetooth_acpi_gpios[] = {
-  { "reset-gpios", &reset_gpio, 1 },
-  { "shutdown-gpios", &shutdown_gpio, 1 },
-  { },
-};
+  static const struct acpi_gpio_mapping bluetooth_acpi_gpios[] = {
+    { "reset-gpios", &reset_gpio, 1 },
+    { "shutdown-gpios", &shutdown_gpio, 1 },
+    { },
+  };
 
 Next, the mapping table needs to be passed as the second argument to
 acpi_dev_add_driver_gpios() that will register it with the ACPI device object
@@ -158,12 +165,12 @@ calling acpi_dev_remove_driver_gpios() on the ACPI device object where that
 table was previously registered.
 
 Using the _CRS fallback
------------------------
+=======================
 
 If a device does not have _DSD or the driver does not create ACPI GPIO
 mapping, the Linux GPIO framework refuses to return any GPIOs. This is
 because the driver does not know what it actually gets. For example if we
-have a device like below:
+have a device like below::
 
   Device (BTH)
   {
@@ -177,7 +184,7 @@ have a device like below:
       })
   }
 
-The driver might expect to get the right GPIO when it does:
+The driver might expect to get the right GPIO when it does::
 
   desc = gpiod_get(dev, "reset", GPIOD_OUT_LOW);
 
@@ -193,22 +200,25 @@ the ACPI GPIO mapping tables are hardly linked to ACPI ID and certain
 objects, as listed in the above chapter, of the device in question.
 
 Getting GPIO descriptor
------------------------
+=======================
+
+There are two main approaches to get GPIO resource from ACPI::
 
-There are two main approaches to get GPIO resource from ACPI:
-	desc = gpiod_get(dev, connection_id, flags);
-	desc = gpiod_get_index(dev, connection_id, index, flags);
+  desc = gpiod_get(dev, connection_id, flags);
+  desc = gpiod_get_index(dev, connection_id, index, flags);
 
 We may consider two different cases here, i.e. when connection ID is
 provided and otherwise.
 
-Case 1:
-	desc = gpiod_get(dev, "non-null-connection-id", flags);
-	desc = gpiod_get_index(dev, "non-null-connection-id", index, flags);
+Case 1::
+
+  desc = gpiod_get(dev, "non-null-connection-id", flags);
+  desc = gpiod_get_index(dev, "non-null-connection-id", index, flags);
+
+Case 2::
 
-Case 2:
-	desc = gpiod_get(dev, NULL, flags);
-	desc = gpiod_get_index(dev, NULL, index, flags);
+  desc = gpiod_get(dev, NULL, flags);
+  desc = gpiod_get_index(dev, NULL, index, flags);
 
 Case 1 assumes that corresponding ACPI device description must have
 defined device properties and will prevent to getting any GPIO resources
diff --git a/Documentation/firmware-guide/acpi/i2c-muxes.rst b/Documentation/firmware-guide/acpi/i2c-muxes.rst
new file mode 100644
index 000000000000..3a8997ccd7c4
--- /dev/null
+++ b/Documentation/firmware-guide/acpi/i2c-muxes.rst
@@ -0,0 +1,61 @@
+.. SPDX-License-Identifier: GPL-2.0
+
+==============
+ACPI I2C Muxes
+==============
+
+Describing an I2C device hierarchy that includes I2C muxes requires an ACPI
+Device () scope per mux channel.
+
+Consider this topology::
+
+    +------+   +------+
+    | SMB1 |-->| MUX0 |--CH00--> i2c client A (0x50)
+    |      |   | 0x70 |--CH01--> i2c client B (0x50)
+    +------+   +------+
+
+which corresponds to the following ASL::
+
+    Device (SMB1)
+    {
+        Name (_HID, ...)
+        Device (MUX0)
+        {
+            Name (_HID, ...)
+            Name (_CRS, ResourceTemplate () {
+                I2cSerialBus (0x70, ControllerInitiated, I2C_SPEED,
+                            AddressingMode7Bit, "^SMB1", 0x00,
+                            ResourceConsumer,,)
+            }
+
+            Device (CH00)
+            {
+                Name (_ADR, 0)
+
+                Device (CLIA)
+                {
+                    Name (_HID, ...)
+                    Name (_CRS, ResourceTemplate () {
+                        I2cSerialBus (0x50, ControllerInitiated, I2C_SPEED,
+                                    AddressingMode7Bit, "^CH00", 0x00,
+                                    ResourceConsumer,,)
+                    }
+                }
+            }
+
+            Device (CH01)
+            {
+                Name (_ADR, 1)
+
+                Device (CLIB)
+                {
+                    Name (_HID, ...)
+                    Name (_CRS, ResourceTemplate () {
+                        I2cSerialBus (0x50, ControllerInitiated, I2C_SPEED,
+                                    AddressingMode7Bit, "^CH01", 0x00,
+                                    ResourceConsumer,,)
+                    }
+                }
+            }
+        }
+    }
diff --git a/Documentation/firmware-guide/acpi/index.rst b/Documentation/firmware-guide/acpi/index.rst
new file mode 100644
index 000000000000..ae609eec4679
--- /dev/null
+++ b/Documentation/firmware-guide/acpi/index.rst
@@ -0,0 +1,26 @@
+.. SPDX-License-Identifier: GPL-2.0
+
+============
+ACPI Support
+============
+
+.. toctree::
+   :maxdepth: 1
+
+   namespace
+   dsd/graph
+   dsd/data-node-references
+   enumeration
+   osi
+   method-customizing
+   method-tracing
+   DSD-properties-rules
+   debug
+   aml-debugger
+   apei/output_format
+   apei/einj
+   gpio-properties
+   i2c-muxes
+   acpi-lid
+   lpit
+   video_extension
diff --git a/Documentation/acpi/lpit.txt b/Documentation/firmware-guide/acpi/lpit.rst
index b426398d2e97..aca928fab027 100644
--- a/Documentation/acpi/lpit.txt
+++ b/Documentation/firmware-guide/acpi/lpit.rst
@@ -1,3 +1,9 @@
+.. SPDX-License-Identifier: GPL-2.0
+
+===========================
+Low Power Idle Table (LPIT)
+===========================
+
 To enumerate platform Low Power Idle states, Intel platforms are using
 “Low Power Idle Table� (LPIT). More details about this table can be
 downloaded from:
@@ -8,13 +14,15 @@ Residencies for each low power state can be read via FFH
 
 On platforms supporting S0ix sleep states, there can be two types of
 residencies:
-- CPU PKG C10 (Read via FFH interface)
-- Platform Controller Hub (PCH) SLP_S0 (Read via memory mapped interface)
+
+  - CPU PKG C10 (Read via FFH interface)
+  - Platform Controller Hub (PCH) SLP_S0 (Read via memory mapped interface)
 
 The following attributes are added dynamically to the cpuidle
-sysfs attribute group:
-	/sys/devices/system/cpu/cpuidle/low_power_idle_cpu_residency_us
-	/sys/devices/system/cpu/cpuidle/low_power_idle_system_residency_us
+sysfs attribute group::
+
+  /sys/devices/system/cpu/cpuidle/low_power_idle_cpu_residency_us
+  /sys/devices/system/cpu/cpuidle/low_power_idle_system_residency_us
 
 The "low_power_idle_cpu_residency_us" attribute shows time spent
 by the CPU package in PKG C10
diff --git a/Documentation/firmware-guide/acpi/method-customizing.rst b/Documentation/firmware-guide/acpi/method-customizing.rst
new file mode 100644
index 000000000000..de3ebcaed4cf
--- /dev/null
+++ b/Documentation/firmware-guide/acpi/method-customizing.rst
@@ -0,0 +1,89 @@
+.. SPDX-License-Identifier: GPL-2.0
+
+=======================================
+Linux ACPI Custom Control Method How To
+=======================================
+
+:Author: Zhang Rui <rui.zhang@intel.com>
+
+
+Linux supports customizing ACPI control methods at runtime.
+
+Users can use this to:
+
+1. override an existing method which may not work correctly,
+   or just for debugging purposes.
+2. insert a completely new method in order to create a missing
+   method such as _OFF, _ON, _STA, _INI, etc.
+
+For these cases, it is far simpler to dynamically install a single
+control method rather than override the entire DSDT, because kernel
+rebuild/reboot is not needed and test result can be got in minutes.
+
+.. note::
+
+  - Only ACPI METHOD can be overridden, any other object types like
+    "Device", "OperationRegion", are not recognized. Methods
+    declared inside scope operators are also not supported.
+
+  - The same ACPI control method can be overridden for many times,
+    and it's always the latest one that used by Linux/kernel.
+
+  - To get the ACPI debug object output (Store (AAAA, Debug)),
+    please run::
+
+      echo 1 > /sys/module/acpi/parameters/aml_debug_output
+
+
+1. override an existing method
+==============================
+a) get the ACPI table via ACPI sysfs I/F. e.g. to get the DSDT,
+   just run "cat /sys/firmware/acpi/tables/DSDT > /tmp/dsdt.dat"
+b) disassemble the table by running "iasl -d dsdt.dat".
+c) rewrite the ASL code of the method and save it in a new file,
+d) package the new file (psr.asl) to an ACPI table format.
+   Here is an example of a customized \_SB._AC._PSR method::
+
+      DefinitionBlock ("", "SSDT", 1, "", "", 0x20080715)
+      {
+         Method (\_SB_.AC._PSR, 0, NotSerialized)
+         {
+            Store ("In AC _PSR", Debug)
+            Return (ACON)
+         }
+      }
+
+   Note that the full pathname of the method in ACPI namespace
+   should be used.
+e) assemble the file to generate the AML code of the method.
+   e.g. "iasl -vw 6084 psr.asl" (psr.aml is generated as a result)
+   If parameter "-vw 6084" is not supported by your iASL compiler,
+   please try a newer version.
+f) mount debugfs by "mount -t debugfs none /sys/kernel/debug"
+g) override the old method via the debugfs by running
+   "cat /tmp/psr.aml > /sys/kernel/debug/acpi/custom_method"
+
+2. insert a new method
+======================
+This is easier than overriding an existing method.
+We just need to create the ASL code of the method we want to
+insert and then follow the step c) ~ g) in section 1.
+
+3. undo your changes
+====================
+The "undo" operation is not supported for a new inserted method
+right now, i.e. we can not remove a method currently.
+For an overridden method, in order to undo your changes, please
+save a copy of the method original ASL code in step c) section 1,
+and redo step c) ~ g) to override the method with the original one.
+
+
+.. note:: We can use a kernel with multiple custom ACPI method running,
+   But each individual write to debugfs can implement a SINGLE
+   method override. i.e. if we want to insert/override multiple
+   ACPI methods, we need to redo step c) ~ g) for multiple times.
+
+.. note:: Be aware that root can mis-use this driver to modify arbitrary
+   memory and gain additional rights, if root's privileges got
+   restricted (for example if root is not allowed to load additional
+   modules after boot).
diff --git a/Documentation/firmware-guide/acpi/method-tracing.rst b/Documentation/firmware-guide/acpi/method-tracing.rst
new file mode 100644
index 000000000000..d0b077b73f5f
--- /dev/null
+++ b/Documentation/firmware-guide/acpi/method-tracing.rst
@@ -0,0 +1,238 @@
+.. SPDX-License-Identifier: GPL-2.0
+.. include:: <isonum.txt>
+
+=====================
+ACPICA Trace Facility
+=====================
+
+:Copyright: |copy| 2015, Intel Corporation
+:Author: Lv Zheng <lv.zheng@intel.com>
+
+
+Abstract
+========
+This document describes the functions and the interfaces of the
+method tracing facility.
+
+Functionalities and usage examples
+==================================
+
+ACPICA provides method tracing capability. And two functions are
+currently implemented using this capability.
+
+Log reducer
+-----------
+
+ACPICA subsystem provides debugging outputs when CONFIG_ACPI_DEBUG is
+enabled. The debugging messages which are deployed via
+ACPI_DEBUG_PRINT() macro can be reduced at 2 levels - per-component
+level (known as debug layer, configured via
+/sys/module/acpi/parameters/debug_layer) and per-type level (known as
+debug level, configured via /sys/module/acpi/parameters/debug_level).
+
+But when the particular layer/level is applied to the control method
+evaluations, the quantity of the debugging outputs may still be too
+large to be put into the kernel log buffer. The idea thus is worked out
+to only enable the particular debug layer/level (normally more detailed)
+logs when the control method evaluation is started, and disable the
+detailed logging when the control method evaluation is stopped.
+
+The following command examples illustrate the usage of the "log reducer"
+functionality:
+
+a. Filter out the debug layer/level matched logs when control methods
+   are being evaluated::
+
+      # cd /sys/module/acpi/parameters
+      # echo "0xXXXXXXXX" > trace_debug_layer
+      # echo "0xYYYYYYYY" > trace_debug_level
+      # echo "enable" > trace_state
+
+b. Filter out the debug layer/level matched logs when the specified
+   control method is being evaluated::
+
+      # cd /sys/module/acpi/parameters
+      # echo "0xXXXXXXXX" > trace_debug_layer
+      # echo "0xYYYYYYYY" > trace_debug_level
+      # echo "\PPPP.AAAA.TTTT.HHHH" > trace_method_name
+      # echo "method" > /sys/module/acpi/parameters/trace_state
+
+c. Filter out the debug layer/level matched logs when the specified
+   control method is being evaluated for the first time::
+
+      # cd /sys/module/acpi/parameters
+      # echo "0xXXXXXXXX" > trace_debug_layer
+      # echo "0xYYYYYYYY" > trace_debug_level
+      # echo "\PPPP.AAAA.TTTT.HHHH" > trace_method_name
+      # echo "method-once" > /sys/module/acpi/parameters/trace_state
+
+Where:
+   0xXXXXXXXX/0xYYYYYYYY
+     Refer to Documentation/acpi/debug.txt for possible debug layer/level
+     masking values.
+   \PPPP.AAAA.TTTT.HHHH
+     Full path of a control method that can be found in the ACPI namespace.
+     It needn't be an entry of a control method evaluation.
+
+AML tracer
+----------
+
+There are special log entries added by the method tracing facility at
+the "trace points" the AML interpreter starts/stops to execute a control
+method, or an AML opcode. Note that the format of the log entries are
+subject to change::
+
+   [    0.186427]   exdebug-0398 ex_trace_point        : Method Begin [0xf58394d8:\_SB.PCI0.LPCB.ECOK] execution.
+   [    0.186630]   exdebug-0398 ex_trace_point        : Opcode Begin [0xf5905c88:If] execution.
+   [    0.186820]   exdebug-0398 ex_trace_point        : Opcode Begin [0xf5905cc0:LEqual] execution.
+   [    0.187010]   exdebug-0398 ex_trace_point        : Opcode Begin [0xf5905a20:-NamePath-] execution.
+   [    0.187214]   exdebug-0398 ex_trace_point        : Opcode End [0xf5905a20:-NamePath-] execution.
+   [    0.187407]   exdebug-0398 ex_trace_point        : Opcode Begin [0xf5905f60:One] execution.
+   [    0.187594]   exdebug-0398 ex_trace_point        : Opcode End [0xf5905f60:One] execution.
+   [    0.187789]   exdebug-0398 ex_trace_point        : Opcode End [0xf5905cc0:LEqual] execution.
+   [    0.187980]   exdebug-0398 ex_trace_point        : Opcode Begin [0xf5905cc0:Return] execution.
+   [    0.188146]   exdebug-0398 ex_trace_point        : Opcode Begin [0xf5905f60:One] execution.
+   [    0.188334]   exdebug-0398 ex_trace_point        : Opcode End [0xf5905f60:One] execution.
+   [    0.188524]   exdebug-0398 ex_trace_point        : Opcode End [0xf5905cc0:Return] execution.
+   [    0.188712]   exdebug-0398 ex_trace_point        : Opcode End [0xf5905c88:If] execution.
+   [    0.188903]   exdebug-0398 ex_trace_point        : Method End [0xf58394d8:\_SB.PCI0.LPCB.ECOK] execution.
+
+Developers can utilize these special log entries to track the AML
+interpretion, thus can aid issue debugging and performance tuning. Note
+that, as the "AML tracer" logs are implemented via ACPI_DEBUG_PRINT()
+macro, CONFIG_ACPI_DEBUG is also required to be enabled for enabling
+"AML tracer" logs.
+
+The following command examples illustrate the usage of the "AML tracer"
+functionality:
+
+a. Filter out the method start/stop "AML tracer" logs when control
+   methods are being evaluated::
+
+      # cd /sys/module/acpi/parameters
+      # echo "0x80" > trace_debug_layer
+      # echo "0x10" > trace_debug_level
+      # echo "enable" > trace_state
+
+b. Filter out the method start/stop "AML tracer" when the specified
+   control method is being evaluated::
+
+      # cd /sys/module/acpi/parameters
+      # echo "0x80" > trace_debug_layer
+      # echo "0x10" > trace_debug_level
+      # echo "\PPPP.AAAA.TTTT.HHHH" > trace_method_name
+      # echo "method" > trace_state
+
+c. Filter out the method start/stop "AML tracer" logs when the specified
+   control method is being evaluated for the first time::
+
+      # cd /sys/module/acpi/parameters
+      # echo "0x80" > trace_debug_layer
+      # echo "0x10" > trace_debug_level
+      # echo "\PPPP.AAAA.TTTT.HHHH" > trace_method_name
+      # echo "method-once" > trace_state
+
+d. Filter out the method/opcode start/stop "AML tracer" when the
+   specified control method is being evaluated::
+
+      # cd /sys/module/acpi/parameters
+      # echo "0x80" > trace_debug_layer
+      # echo "0x10" > trace_debug_level
+      # echo "\PPPP.AAAA.TTTT.HHHH" > trace_method_name
+      # echo "opcode" > trace_state
+
+e. Filter out the method/opcode start/stop "AML tracer" when the
+   specified control method is being evaluated for the first time::
+
+      # cd /sys/module/acpi/parameters
+      # echo "0x80" > trace_debug_layer
+      # echo "0x10" > trace_debug_level
+      # echo "\PPPP.AAAA.TTTT.HHHH" > trace_method_name
+      # echo "opcode-opcode" > trace_state
+
+Note that all above method tracing facility related module parameters can
+be used as the boot parameters, for example::
+
+   acpi.trace_debug_layer=0x80 acpi.trace_debug_level=0x10 \
+   acpi.trace_method_name=\_SB.LID0._LID acpi.trace_state=opcode-once
+
+
+Interface descriptions
+======================
+
+All method tracing functions can be configured via ACPI module
+parameters that are accessible at /sys/module/acpi/parameters/:
+
+trace_method_name
+  The full path of the AML method that the user wants to trace.
+
+  Note that the full path shouldn't contain the trailing "_"s in its
+  name segments but may contain "\" to form an absolute path.
+
+trace_debug_layer
+  The temporary debug_layer used when the tracing feature is enabled.
+
+  Using ACPI_EXECUTER (0x80) by default, which is the debug_layer
+  used to match all "AML tracer" logs.
+
+trace_debug_level
+  The temporary debug_level used when the tracing feature is enabled.
+
+  Using ACPI_LV_TRACE_POINT (0x10) by default, which is the
+  debug_level used to match all "AML tracer" logs.
+
+trace_state
+  The status of the tracing feature.
+
+  Users can enable/disable this debug tracing feature by executing
+  the following command::
+
+   # echo string > /sys/module/acpi/parameters/trace_state
+
+Where "string" should be one of the following:
+
+"disable"
+  Disable the method tracing feature.
+
+"enable"
+  Enable the method tracing feature.
+  
+  ACPICA debugging messages matching "trace_debug_layer/trace_debug_level"
+  during any method execution will be logged.
+
+"method"
+  Enable the method tracing feature.
+
+  ACPICA debugging messages matching "trace_debug_layer/trace_debug_level"
+  during method execution of "trace_method_name" will be logged.
+
+"method-once"
+  Enable the method tracing feature.
+
+  ACPICA debugging messages matching "trace_debug_layer/trace_debug_level"
+  during method execution of "trace_method_name" will be logged only once.
+
+"opcode"
+  Enable the method tracing feature.
+
+  ACPICA debugging messages matching "trace_debug_layer/trace_debug_level"
+  during method/opcode execution of "trace_method_name" will be logged.
+
+"opcode-once"
+  Enable the method tracing feature.
+
+  ACPICA debugging messages matching "trace_debug_layer/trace_debug_level"
+  during method/opcode execution of "trace_method_name" will be logged only
+  once.
+
+Note that, the difference between the "enable" and other feature
+enabling options are:
+
+1. When "enable" is specified, since
+   "trace_debug_layer/trace_debug_level" shall apply to all control
+   method evaluations, after configuring "trace_state" to "enable",
+   "trace_method_name" will be reset to NULL.
+2. When "method/opcode" is specified, if
+   "trace_method_name" is NULL when "trace_state" is configured to
+   these options, the "trace_debug_layer/trace_debug_level" will
+   apply to all control method evaluations.
diff --git a/Documentation/acpi/namespace.txt b/Documentation/firmware-guide/acpi/namespace.rst
index 1860cb3865c6..835521baeb89 100644
--- a/Documentation/acpi/namespace.txt
+++ b/Documentation/firmware-guide/acpi/namespace.rst
@@ -1,85 +1,90 @@
+.. SPDX-License-Identifier: GPL-2.0
+.. include:: <isonum.txt>
+
+===================================================
 ACPI Device Tree - Representation of ACPI Namespace
+===================================================
 
-Copyright (C) 2013, Intel Corporation
-Author: Lv Zheng <lv.zheng@intel.com>
+:Copyright: |copy| 2013, Intel Corporation
 
+:Author: Lv Zheng <lv.zheng@intel.com>
 
-Abstract:
+:Credit:   Thanks for the help from Zhang Rui <rui.zhang@intel.com> and
+           Rafael J.Wysocki <rafael.j.wysocki@intel.com>.
 
+Abstract
+========
 The Linux ACPI subsystem converts ACPI namespace objects into a Linux
 device tree under the /sys/devices/LNXSYSTEM:00 and updates it upon
-receiving ACPI hotplug notification events.  For each device object in this
-hierarchy there is a corresponding symbolic link in the
+receiving ACPI hotplug notification events.  For each device object
+in this hierarchy there is a corresponding symbolic link in the
 /sys/bus/acpi/devices.
+
 This document illustrates the structure of the ACPI device tree.
 
+ACPI Definition Blocks
+======================
+
+The ACPI firmware sets up RSDP (Root System Description Pointer) in the
+system memory address space pointing to the XSDT (Extended System
+Description Table).  The XSDT always points to the FADT (Fixed ACPI
+Description Table) using its first entry, the data within the FADT
+includes various fixed-length entries that describe fixed ACPI features
+of the hardware.  The FADT contains a pointer to the DSDT
+(Differentiated System Descripition Table).  The XSDT also contains
+entries pointing to possibly multiple SSDTs (Secondary System
+Description Table).
+
+The DSDT and SSDT data is organized in data structures called definition
+blocks that contain definitions of various objects, including ACPI
+control methods, encoded in AML (ACPI Machine Language).  The data block
+of the DSDT along with the contents of SSDTs represents a hierarchical
+data structure called the ACPI namespace whose topology reflects the
+structure of the underlying hardware platform.
+
+The relationships between ACPI System Definition Tables described above
+are illustrated in the following diagram::
+
+   +---------+    +-------+    +--------+    +------------------------+
+   |  RSDP   | +->| XSDT  | +->|  FADT  |    |  +-------------------+ |
+   +---------+ |  +-------+ |  +--------+  +-|->|       DSDT        | |
+   | Pointer | |  | Entry |-+  | ...... |  | |  +-------------------+ |
+   +---------+ |  +-------+    | X_DSDT |--+ |  | Definition Blocks | |
+   | Pointer |-+  | ..... |    | ...... |    |  +-------------------+ |
+   +---------+    +-------+    +--------+    |  +-------------------+ |
+                  | Entry |------------------|->|       SSDT        | |
+                  +- - - -+                  |  +-------------------| |
+                  | Entry | - - - - - - - -+ |  | Definition Blocks | |
+                  +- - - -+                | |  +-------------------+ |
+                                          | |  +- - - - - - - - - -+ |
+                                          +-|->|       SSDT        | |
+                                             |  +-------------------+ |
+                                             |  | Definition Blocks | |
+                                             |  +- - - - - - - - - -+ |
+                                             +------------------------+
+                                                         |
+                                             OSPM Loading |
+                                                         \|/
+                                                   +----------------+
+                                                   | ACPI Namespace |
+                                                   +----------------+
+
+                  Figure 1. ACPI Definition Blocks
+
+.. note:: RSDP can also contain a pointer to the RSDT (Root System
+   Description Table).  Platforms provide RSDT to enable
+   compatibility with ACPI 1.0 operating systems.  The OS is expected
+   to use XSDT, if present.
+
+
+Example ACPI Namespace
+======================
+
+All definition blocks are loaded into a single namespace.  The namespace
+is a hierarchy of objects identified by names and paths.
+The following naming conventions apply to object names in the ACPI
+namespace:
 
-Credit:
-
-Thanks for the help from Zhang Rui <rui.zhang@intel.com> and Rafael J.
-Wysocki <rafael.j.wysocki@intel.com>.
-
-
-1. ACPI Definition Blocks
-
-   The ACPI firmware sets up RSDP (Root System Description Pointer) in the
-   system memory address space pointing to the XSDT (Extended System
-   Description Table).  The XSDT always points to the FADT (Fixed ACPI
-   Description Table) using its first entry, the data within the FADT
-   includes various fixed-length entries that describe fixed ACPI features
-   of the hardware.  The FADT contains a pointer to the DSDT
-   (Differentiated System Descripition Table).  The XSDT also contains
-   entries pointing to possibly multiple SSDTs (Secondary System
-   Description Table).
-
-   The DSDT and SSDT data is organized in data structures called definition
-   blocks that contain definitions of various objects, including ACPI
-   control methods, encoded in AML (ACPI Machine Language).  The data block
-   of the DSDT along with the contents of SSDTs represents a hierarchical
-   data structure called the ACPI namespace whose topology reflects the
-   structure of the underlying hardware platform.
-
-   The relationships between ACPI System Definition Tables described above
-   are illustrated in the following diagram.
-
-     +---------+    +-------+    +--------+    +------------------------+
-     |  RSDP   | +->| XSDT  | +->|  FADT  |    |  +-------------------+ |
-     +---------+ |  +-------+ |  +--------+  +-|->|       DSDT        | |
-     | Pointer | |  | Entry |-+  | ...... |  | |  +-------------------+ |
-     +---------+ |  +-------+    | X_DSDT |--+ |  | Definition Blocks | |
-     | Pointer |-+  | ..... |    | ...... |    |  +-------------------+ |
-     +---------+    +-------+    +--------+    |  +-------------------+ |
-                    | Entry |------------------|->|       SSDT        | |
-                    +- - - -+                  |  +-------------------| |
-                    | Entry | - - - - - - - -+ |  | Definition Blocks | |
-                    +- - - -+                | |  +-------------------+ |
-                                             | |  +- - - - - - - - - -+ |
-                                             +-|->|       SSDT        | |
-                                               |  +-------------------+ |
-                                               |  | Definition Blocks | |
-                                               |  +- - - - - - - - - -+ |
-                                               +------------------------+
-                                                           |
-                                              OSPM Loading |
-                                                          \|/
-                                                    +----------------+
-                                                    | ACPI Namespace |
-                                                    +----------------+
-
-                     Figure 1. ACPI Definition Blocks
-
-   NOTE: RSDP can also contain a pointer to the RSDT (Root System
-         Description Table).  Platforms provide RSDT to enable
-         compatibility with ACPI 1.0 operating systems.  The OS is expected
-         to use XSDT, if present.
-
-
-2. Example ACPI Namespace
-
-   All definition blocks are loaded into a single namespace.  The namespace
-   is a hierarchy of objects identified by names and paths.
-   The following naming conventions apply to object names in the ACPI
-   namespace:
    1. All names are 32 bits long.
    2. The first byte of a name must be one of 'A' - 'Z', '_'.
    3. Each of the remaining bytes of a name must be one of 'A' - 'Z', '0'
@@ -91,7 +96,7 @@ Wysocki <rafael.j.wysocki@intel.com>.
       (i.e. names prepended with '^' are relative to the parent of the
       current namespace node).
 
-   The figure below shows an example ACPI namespace.
+The figure below shows an example ACPI namespace::
 
    +------+
    | \    |                     Root
@@ -184,19 +189,20 @@ Wysocki <rafael.j.wysocki@intel.com>.
                      Figure 2. Example ACPI Namespace
 
 
-3. Linux ACPI Device Objects
+Linux ACPI Device Objects
+=========================
 
-   The Linux kernel's core ACPI subsystem creates struct acpi_device
-   objects for ACPI namespace objects representing devices, power resources
-   processors, thermal zones.  Those objects are exported to user space via
-   sysfs as directories in the subtree under /sys/devices/LNXSYSTM:00.  The
-   format of their names is <bus_id:instance>, where 'bus_id' refers to the
-   ACPI namespace representation of the given object and 'instance' is used
-   for distinguishing different object of the same 'bus_id' (it is
-   two-digit decimal representation of an unsigned integer).
+The Linux kernel's core ACPI subsystem creates struct acpi_device
+objects for ACPI namespace objects representing devices, power resources
+processors, thermal zones.  Those objects are exported to user space via
+sysfs as directories in the subtree under /sys/devices/LNXSYSTM:00.  The
+format of their names is <bus_id:instance>, where 'bus_id' refers to the
+ACPI namespace representation of the given object and 'instance' is used
+for distinguishing different object of the same 'bus_id' (it is
+two-digit decimal representation of an unsigned integer).
 
-   The value of 'bus_id' depends on the type of the object whose name it is
-   part of as listed in the table below.
+The value of 'bus_id' depends on the type of the object whose name it is
+part of as listed in the table below::
 
                 +---+-----------------+-------+----------+
                 |   | Object/Feature  | Table | bus_id   |
@@ -226,10 +232,11 @@ Wysocki <rafael.j.wysocki@intel.com>.
 
                  Table 1. ACPI Namespace Objects Mapping
 
-   The following rules apply when creating struct acpi_device objects on
-   the basis of the contents of ACPI System Description Tables (as
-   indicated by the letter in the first column and the notation in the
-   second column of the table above):
+The following rules apply when creating struct acpi_device objects on
+the basis of the contents of ACPI System Description Tables (as
+indicated by the letter in the first column and the notation in the
+second column of the table above):
+
    N:
       The object's source is an ACPI namespace node (as indicated by the
       named object's type in the second column).  In that case the object's
@@ -249,13 +256,14 @@ Wysocki <rafael.j.wysocki@intel.com>.
       struct acpi_device object with LNXVIDEO 'bus_id' will be created for
       it.
 
-   The third column of the above table indicates which ACPI System
-   Description Tables contain information used for the creation of the
-   struct acpi_device objects represented by the given row (xSDT means DSDT
-   or SSDT).
+The third column of the above table indicates which ACPI System
+Description Tables contain information used for the creation of the
+struct acpi_device objects represented by the given row (xSDT means DSDT
+or SSDT).
+
+The forth column of the above table indicates the 'bus_id' generation
+rule of the struct acpi_device object:
 
-   The forth column of the above table indicates the 'bus_id' generation
-   rule of the struct acpi_device object:
    _HID:
       _HID in the last column of the table means that the object's bus_id
       is derived from the _HID/_CID identification objects present under
@@ -275,45 +283,47 @@ Wysocki <rafael.j.wysocki@intel.com>.
       object's bus_id.
 
 
-4. Linux ACPI Physical Device Glue
-
-   ACPI device (i.e. struct acpi_device) objects may be linked to other
-   objects in the Linux' device hierarchy that represent "physical" devices
-   (for example, devices on the PCI bus).  If that happens, it means that
-   the ACPI device object is a "companion" of a device otherwise
-   represented in a different way and is used (1) to provide configuration
-   information on that device which cannot be obtained by other means and
-   (2) to do specific things to the device with the help of its ACPI
-   control methods.  One ACPI device object may be linked this way to
-   multiple "physical" devices.
-
-   If an ACPI device object is linked to a "physical" device, its sysfs
-   directory contains the "physical_node" symbolic link to the sysfs
-   directory of the target device object.  In turn, the target device's
-   sysfs directory will then contain the "firmware_node" symbolic link to
-   the sysfs directory of the companion ACPI device object.
-   The linking mechanism relies on device identification provided by the
-   ACPI namespace.  For example, if there's an ACPI namespace object
-   representing a PCI device (i.e. a device object under an ACPI namespace
-   object representing a PCI bridge) whose _ADR returns 0x00020000 and the
-   bus number of the parent PCI bridge is 0, the sysfs directory
-   representing the struct acpi_device object created for that ACPI
-   namespace object will contain the 'physical_node' symbolic link to the
-   /sys/devices/pci0000:00/0000:00:02:0/ sysfs directory of the
-   corresponding PCI device.
-
-   The linking mechanism is generally bus-specific.  The core of its
-   implementation is located in the drivers/acpi/glue.c file, but there are
-   complementary parts depending on the bus types in question located
-   elsewhere.  For example, the PCI-specific part of it is located in
-   drivers/pci/pci-acpi.c.
-
-
-5. Example Linux ACPI Device Tree
-
-   The sysfs hierarchy of struct acpi_device objects corresponding to the
-   example ACPI namespace illustrated in Figure 2 with the addition of
-   fixed PWR_BUTTON/SLP_BUTTON devices is shown below.
+Linux ACPI Physical Device Glue
+===============================
+
+ACPI device (i.e. struct acpi_device) objects may be linked to other
+objects in the Linux' device hierarchy that represent "physical" devices
+(for example, devices on the PCI bus).  If that happens, it means that
+the ACPI device object is a "companion" of a device otherwise
+represented in a different way and is used (1) to provide configuration
+information on that device which cannot be obtained by other means and
+(2) to do specific things to the device with the help of its ACPI
+control methods.  One ACPI device object may be linked this way to
+multiple "physical" devices.
+
+If an ACPI device object is linked to a "physical" device, its sysfs
+directory contains the "physical_node" symbolic link to the sysfs
+directory of the target device object.  In turn, the target device's
+sysfs directory will then contain the "firmware_node" symbolic link to
+the sysfs directory of the companion ACPI device object.
+The linking mechanism relies on device identification provided by the
+ACPI namespace.  For example, if there's an ACPI namespace object
+representing a PCI device (i.e. a device object under an ACPI namespace
+object representing a PCI bridge) whose _ADR returns 0x00020000 and the
+bus number of the parent PCI bridge is 0, the sysfs directory
+representing the struct acpi_device object created for that ACPI
+namespace object will contain the 'physical_node' symbolic link to the
+/sys/devices/pci0000:00/0000:00:02:0/ sysfs directory of the
+corresponding PCI device.
+
+The linking mechanism is generally bus-specific.  The core of its
+implementation is located in the drivers/acpi/glue.c file, but there are
+complementary parts depending on the bus types in question located
+elsewhere.  For example, the PCI-specific part of it is located in
+drivers/pci/pci-acpi.c.
+
+
+Example Linux ACPI Device Tree
+=================================
+
+The sysfs hierarchy of struct acpi_device objects corresponding to the
+example ACPI namespace illustrated in Figure 2 with the addition of
+fixed PWR_BUTTON/SLP_BUTTON devices is shown below::
 
    +--------------+---+-----------------+
    | LNXSYSTEM:00 | \ | acpi:LNXSYSTEM: |
@@ -377,12 +387,14 @@ Wysocki <rafael.j.wysocki@intel.com>.
 
                   Figure 3. Example Linux ACPI Device Tree
 
-   NOTE: Each node is represented as "object/path/modalias", where:
-         1. 'object' is the name of the object's directory in sysfs.
-         2. 'path' is the ACPI namespace path of the corresponding
-            ACPI namespace object, as returned by the object's 'path'
-            sysfs attribute.
-         3. 'modalias' is the value of the object's 'modalias' sysfs
-            attribute (as described earlier in this document).
-   NOTE: N/A indicates the device object does not have the 'path' or the
-         'modalias' attribute.
+.. note:: Each node is represented as "object/path/modalias", where:
+
+   1. 'object' is the name of the object's directory in sysfs.
+   2. 'path' is the ACPI namespace path of the corresponding
+      ACPI namespace object, as returned by the object's 'path'
+      sysfs attribute.
+   3. 'modalias' is the value of the object's 'modalias' sysfs
+      attribute (as described earlier in this document).
+
+.. note:: N/A indicates the device object does not have the 'path' or the
+   'modalias' attribute.
diff --git a/Documentation/acpi/osi.txt b/Documentation/firmware-guide/acpi/osi.rst
index 50cde0ceb9b0..29e9ef79ebc0 100644
--- a/Documentation/acpi/osi.txt
+++ b/Documentation/firmware-guide/acpi/osi.rst
@@ -1,5 +1,8 @@
+.. SPDX-License-Identifier: GPL-2.0
+
+==========================
 ACPI _OSI and _REV methods
---------------------------
+==========================
 
 An ACPI BIOS can use the "Operating System Interfaces" method (_OSI)
 to find out what the operating system supports. Eg. If BIOS
@@ -14,7 +17,7 @@ This document explains how and why the BIOS and Linux should use these methods.
 It also explains how and why they are widely misused.
 
 How to use _OSI
----------------
+===============
 
 Linux runs on two groups of machines -- those that are tested by the OEM
 to be compatible with Linux, and those that were never tested with Linux,
@@ -62,7 +65,7 @@ the string when that support is added to the kernel.
 That was easy.  Read on, to find out how to do it wrong.
 
 Before _OSI, there was _OS
---------------------------
+==========================
 
 ACPI 1.0 specified "_OS" as an
 "object that evaluates to a string that identifies the operating system."
@@ -96,7 +99,7 @@ That is the *only* viable strategy, as that is what modern Windows does,
 and so doing otherwise could steer the BIOS down an untested path.
 
 _OSI is born, and immediately misused
---------------------------------------
+=====================================
 
 With _OSI, the *BIOS* provides the string describing an interface,
 and asks the OS: "YES/NO, are you compatible with this interface?"
@@ -144,7 +147,7 @@ catastrophic failure resulting from the BIOS taking paths that
 were never validated under *any* OS.
 
 Do not use _REV
----------------
+===============
 
 Since _OSI("Linux") went away, some BIOS writers used _REV
 to support Linux and Windows differences in the same BIOS.
@@ -164,7 +167,7 @@ from mid-2015 onward.  The ACPI specification will also be updated
 to reflect that _REV is deprecated, and always returns 2.
 
 Apple Mac and _OSI("Darwin")
-----------------------------
+============================
 
 On Apple's Mac platforms, the ACPI BIOS invokes _OSI("Darwin")
 to determine if the machine is running Apple OSX.
diff --git a/Documentation/acpi/video_extension.txt b/Documentation/firmware-guide/acpi/video_extension.rst
index 79bf6a4921be..099b8607e07b 100644
--- a/Documentation/acpi/video_extension.txt
+++ b/Documentation/firmware-guide/acpi/video_extension.rst
@@ -1,5 +1,8 @@
+.. SPDX-License-Identifier: GPL-2.0
+
+=====================
 ACPI video extensions
-~~~~~~~~~~~~~~~~~~~~~
+=====================
 
 This driver implement the ACPI Extensions For Display Adapters for
 integrated graphics devices on motherboard, as specified in ACPI 2.0
@@ -8,9 +11,10 @@ defining the video POST device, retrieving EDID information or to
 setup a video output, etc.  Note that this is an ref. implementation
 only.  It may or may not work for your integrated video device.
 
-The ACPI video driver does 3 things regarding backlight control:
+The ACPI video driver does 3 things regarding backlight control.
 
-1 Export a sysfs interface for user space to control backlight level
+Export a sysfs interface for user space to control backlight level
+==================================================================
 
 If the ACPI table has a video device, and acpi_backlight=vendor kernel
 command line is not present, the driver will register a backlight device
@@ -22,36 +26,41 @@ The backlight sysfs interface has a standard definition here:
 Documentation/ABI/stable/sysfs-class-backlight.
 
 And what ACPI video driver does is:
-actual_brightness: on read, control method _BQC will be evaluated to
-get the brightness level the firmware thinks it is at;
-bl_power: not implemented, will set the current brightness instead;
-brightness: on write, control method _BCM will run to set the requested
-brightness level;
-max_brightness: Derived from the _BCL package(see below);
-type: firmware
+
+actual_brightness:
+  on read, control method _BQC will be evaluated to
+  get the brightness level the firmware thinks it is at;
+bl_power:
+  not implemented, will set the current brightness instead;
+brightness:
+  on write, control method _BCM will run to set the requested brightness level;
+max_brightness:
+  Derived from the _BCL package(see below);
+type:
+  firmware
 
 Note that ACPI video backlight driver will always use index for
 brightness, actual_brightness and max_brightness. So if we have
-the following _BCL package:
+the following _BCL package::
 
-Method (_BCL, 0, NotSerialized)
-{
-	Return (Package (0x0C)
+	Method (_BCL, 0, NotSerialized)
 	{
-		0x64,
-		0x32,
-		0x0A,
-		0x14,
-		0x1E,
-		0x28,
-		0x32,
-		0x3C,
-		0x46,
-		0x50,
-		0x5A,
-		0x64
-	})
-}
+		Return (Package (0x0C)
+		{
+			0x64,
+			0x32,
+			0x0A,
+			0x14,
+			0x1E,
+			0x28,
+			0x32,
+			0x3C,
+			0x46,
+			0x50,
+			0x5A,
+			0x64
+		})
+	}
 
 The first two levels are for when laptop are on AC or on battery and are
 not used by Linux currently. The remaining 10 levels are supported levels
@@ -62,13 +71,15 @@ as a "brightness level" indicator. Thus from the user space perspective
 the range of available brightness levels is from 0 to 9 (max_brightness)
 inclusive.
 
-2 Notify user space about hotkey event
+Notify user space about hotkey event
+====================================
 
 There are generally two cases for hotkey event reporting:
+
 i) For some laptops, when user presses the hotkey, a scancode will be
    generated and sent to user space through the input device created by
    the keyboard driver as a key type input event, with proper remap, the
-   following key code will appear to user space:
+   following key code will appear to user space::
 
 	EV_KEY, KEY_BRIGHTNESSUP
 	EV_KEY, KEY_BRIGHTNESSDOWN
@@ -84,23 +95,27 @@ ii) For some laptops, the press of the hotkey will not generate the
     notify value it received and send the event to user space through the
     input device it created:
 
+	=====		==================
 	event		keycode
+	=====		==================
 	0x86		KEY_BRIGHTNESSUP
 	0x87		KEY_BRIGHTNESSDOWN
 	etc.
+	=====		==================
 
 so this would lead to the same effect as case i) now.
 
 Once user space tool receives this event, it can modify the backlight
 level through the sysfs interface.
 
-3 Change backlight level in the kernel
+Change backlight level in the kernel
+====================================
 
 This works for machines covered by case ii) in Section 2. Once the driver
 received a notification, it will set the backlight level accordingly. This does
 not affect the sending of event to user space, they are always sent to user
 space regardless of whether or not the video module controls the backlight level
 directly. This behaviour can be controlled through the brightness_switch_enabled
-module parameter as documented in admin-guide/kernel-parameters.rst. It is recommended to
-disable this behaviour once a GUI environment starts up and wants to have full
-control of the backlight level.
+module parameter as documented in admin-guide/kernel-parameters.rst. It is
+recommended to disable this behaviour once a GUI environment starts up and
+wants to have full control of the backlight level.
diff --git a/Documentation/firmware-guide/index.rst b/Documentation/firmware-guide/index.rst
new file mode 100644
index 000000000000..5355784ca0a2
--- /dev/null
+++ b/Documentation/firmware-guide/index.rst
@@ -0,0 +1,13 @@
+.. SPDX-License-Identifier: GPL-2.0
+
+===============================
+The Linux kernel firmware guide
+===============================
+
+This section describes the ACPI subsystem in Linux from firmware perspective.
+
+.. toctree::
+   :maxdepth: 1
+
+   acpi/index
+
diff --git a/Documentation/hwmon/ab8500 b/Documentation/hwmon/ab8500.rst
index cf169c8ef4e3..33f93a9cec04 100644
--- a/Documentation/hwmon/ab8500
+++ b/Documentation/hwmon/ab8500.rst
@@ -2,19 +2,23 @@ Kernel driver ab8500
 ====================
 
 Supported chips:
+
   * ST-Ericsson AB8500
+
     Prefix: 'ab8500'
+
     Addresses scanned: -
+
     Datasheet: http://www.stericsson.com/developers/documentation.jsp
 
 Authors:
-        Martin Persson <martin.persson@stericsson.com>
-        Hongbo Zhang <hongbo.zhang@linaro.org>
+	- Martin Persson <martin.persson@stericsson.com>
+	- Hongbo Zhang <hongbo.zhang@linaro.org>
 
 Description
 -----------
 
-See also Documentation/hwmon/abx500. This is the ST-Ericsson AB8500 specific
+See also Documentation/hwmon/abx500.rst. This is the ST-Ericsson AB8500 specific
 driver.
 
 Currently only the AB8500 internal sensor and one external sensor for battery
diff --git a/Documentation/hwmon/abituguru b/Documentation/hwmon/abituguru
deleted file mode 100644
index 44013d23b3f0..000000000000
--- a/Documentation/hwmon/abituguru
+++ /dev/null
@@ -1,92 +0,0 @@
-Kernel driver abituguru
-=======================
-
-Supported chips:
-  * Abit uGuru revision 1 & 2 (Hardware Monitor part only)
-    Prefix: 'abituguru'
-    Addresses scanned: ISA 0x0E0
-    Datasheet: Not available, this driver is based on reverse engineering.
-	A "Datasheet" has been written based on the reverse engineering it
-	should be available in the same dir as this file under the name
-	abituguru-datasheet.
-    Note:
-	The uGuru is a microcontroller with onboard firmware which programs
-	it to behave as a hwmon IC. There are many different revisions of the
-	firmware and thus effectivly many different revisions of the uGuru.
-	Below is an incomplete list with which revisions are used for which
-	Motherboards:
-	uGuru 1.00    ~ 1.24    (AI7, KV8-MAX3, AN7) (1)
-	uGuru 2.0.0.0 ~ 2.0.4.2 (KV8-PRO)
-	uGuru 2.1.0.0 ~ 2.1.2.8 (AS8, AV8, AA8, AG8, AA8XE, AX8)
-	uGuru 2.2.0.0 ~ 2.2.0.6 (AA8 Fatal1ty)
-	uGuru 2.3.0.0 ~ 2.3.0.9 (AN8)
-	uGuru 3.0.0.0 ~ 3.0.x.x (AW8, AL8, AT8, NI8 SLI, AT8 32X, AN8 32X,
-				 AW9D-MAX) (2)
-	1) For revisions 2 and 3 uGuru's the driver can autodetect the
-	   sensortype (Volt or Temp) for bank1 sensors, for revision 1 uGuru's
-	   this does not always work. For these uGuru's the autodetection can
-	   be overridden with the bank1_types module param. For all 3 known
-	   revison 1 motherboards the correct use of this param is:
-	   bank1_types=1,1,0,0,0,0,0,2,0,0,0,0,2,0,0,1
-	   You may also need to specify the fan_sensors option for these boards
-	   fan_sensors=5
-	2) There is a separate abituguru3 driver for these motherboards,
-	   the abituguru (without the 3 !) driver will not work on these
-	   motherboards (and visa versa)!
-
-Authors:
-	Hans de Goede <j.w.r.degoede@hhs.nl>,
-	(Initial reverse engineering done by Olle Sandberg
-	 <ollebull@gmail.com>)
-
-
-Module Parameters
------------------
-
-* force: bool		Force detection. Note this parameter only causes the
-			detection to be skipped, and thus the insmod to
-			succeed. If the uGuru can't be read the actual hwmon
-			driver will not load and thus no hwmon device will get
-			registered.
-* bank1_types: int[]	Bank1 sensortype autodetection override:
-			  -1 autodetect (default)
-			   0 volt sensor
-			   1 temp sensor
-			   2 not connected
-* fan_sensors: int	Tell the driver how many fan speed sensors there are
-			on your motherboard. Default: 0 (autodetect).
-* pwms: int		Tell the driver how many fan speed controls (fan
-			pwms) your motherboard has. Default: 0 (autodetect).
-* verbose: int		How verbose should the driver be? (0-3):
-			   0 normal output
-			   1 + verbose error reporting
-			   2 + sensors type probing info (default)
-			   3 + retryable error reporting
-			Default: 2 (the driver is still in the testing phase)
-
-Notice if you need any of the first three options above please insmod the
-driver with verbose set to 3 and mail me <j.w.r.degoede@hhs.nl> the output of:
-dmesg | grep abituguru
-
-
-Description
------------
-
-This driver supports the hardware monitoring features of the first and
-second revision of the Abit uGuru chip found on Abit uGuru featuring
-motherboards (most modern Abit motherboards).
-
-The first and second revision of the uGuru chip in reality is a Winbond
-W83L950D in disguise (despite Abit claiming it is "a new microprocessor
-designed by the ABIT Engineers"). Unfortunately this doesn't help since the
-W83L950D is a generic microcontroller with a custom Abit application running
-on it.
-
-Despite Abit not releasing any information regarding the uGuru, Olle
-Sandberg <ollebull@gmail.com> has managed to reverse engineer the sensor part
-of the uGuru. Without his work this driver would not have been possible.
-
-Known Issues
-------------
-
-The voltage and frequency control parts of the Abit uGuru are not supported.
diff --git a/Documentation/hwmon/abituguru-datasheet b/Documentation/hwmon/abituguru-datasheet.rst
index 86c0b1251c81..6d5253e2223b 100644
--- a/Documentation/hwmon/abituguru-datasheet
+++ b/Documentation/hwmon/abituguru-datasheet.rst
@@ -1,3 +1,4 @@
+===============
 uGuru datasheet
 ===============
 
@@ -168,34 +169,35 @@ This bank contains 0 sensors, iow the sensor address is ignored (but must be
 written) just use 0. Bank 0x20 contains 3 bytes:
 
 Byte 0:
-This byte holds the alarm flags for sensor 0-7 of Sensor Bank1, with bit 0
-corresponding to sensor 0, 1 to 1, etc.
+  This byte holds the alarm flags for sensor 0-7 of Sensor Bank1, with bit 0
+  corresponding to sensor 0, 1 to 1, etc.
 
 Byte 1:
-This byte holds the alarm flags for sensor 8-15 of Sensor Bank1, with bit 0
-corresponding to sensor 8, 1 to 9, etc.
+  This byte holds the alarm flags for sensor 8-15 of Sensor Bank1, with bit 0
+  corresponding to sensor 8, 1 to 9, etc.
 
 Byte 2:
-This byte holds the alarm flags for sensor 0-5 of Sensor Bank2, with bit 0
-corresponding to sensor 0, 1 to 1, etc.
+  This byte holds the alarm flags for sensor 0-5 of Sensor Bank2, with bit 0
+  corresponding to sensor 0, 1 to 1, etc.
 
 
 Bank 0x21 Sensor Bank1 Values / Readings (R)
 --------------------------------------------
 This bank contains 16 sensors, for each sensor it contains 1 byte.
 So far the following sensors are known to be available on all motherboards:
-Sensor  0 CPU temp
-Sensor  1 SYS temp
-Sensor  3 CPU core volt
-Sensor  4 DDR volt
-Sensor 10 DDR Vtt volt
-Sensor 15 PWM temp
+
+- Sensor  0 CPU temp
+- Sensor  1 SYS temp
+- Sensor  3 CPU core volt
+- Sensor  4 DDR volt
+- Sensor 10 DDR Vtt volt
+- Sensor 15 PWM temp
 
 Byte 0:
-This byte holds the reading from the sensor. Sensors in Bank1 can be both
-volt and temp sensors, this is motherboard specific. The uGuru however does
-seem to know (be programmed with) what kindoff sensor is attached see Sensor
-Bank1 Settings description.
+  This byte holds the reading from the sensor. Sensors in Bank1 can be both
+  volt and temp sensors, this is motherboard specific. The uGuru however does
+  seem to know (be programmed with) what kindoff sensor is attached see Sensor
+  Bank1 Settings description.
 
 Volt sensors use a linear scale, a reading 0 corresponds with 0 volt and a
 reading of 255 with 3494 mV. The sensors for higher voltages however are
@@ -207,96 +209,118 @@ Temp sensors also use a linear scale, a reading of 0 corresponds with 0 degree
 Celsius and a reading of 255 with a reading of 255 degrees Celsius.
 
 
-Bank 0x22 Sensor Bank1 Settings (R)
-Bank 0x23 Sensor Bank1 Settings (W)
------------------------------------
+Bank 0x22 Sensor Bank1 Settings (R) and Bank 0x23 Sensor Bank1 Settings (W)
+---------------------------------------------------------------------------
 
-This bank contains 16 sensors, for each sensor it contains 3 bytes. Each
+Those banks contain 16 sensors, for each sensor it contains 3 bytes. Each
 set of 3 bytes contains the settings for the sensor with the same sensor
 address in Bank 0x21 .
 
 Byte 0:
-Alarm behaviour for the selected sensor. A 1 enables the described behaviour.
-Bit 0: Give an alarm if measured temp is over the warning threshold	(RW) *
-Bit 1: Give an alarm if measured volt is over the max threshold		(RW) **
-Bit 2: Give an alarm if measured volt is under the min threshold	(RW) **
-Bit 3: Beep if alarm							(RW)
-Bit 4: 1 if alarm cause measured temp is over the warning threshold	(R)
-Bit 5: 1 if alarm cause measured volt is over the max threshold		(R)
-Bit 6: 1 if alarm cause measured volt is under the min threshold	(R)
-Bit 7: Volt sensor: Shutdown if alarm persist for more than 4 seconds	(RW)
-       Temp sensor: Shutdown if temp is over the shutdown threshold	(RW)
-
-*  This bit is only honored/used by the uGuru if a temp sensor is connected
-** This bit is only honored/used by the uGuru if a volt sensor is connected
-Note with some trickery this can be used to find out what kinda sensor is
-detected see the Linux kernel driver for an example with many comments on
-how todo this.
+  Alarm behaviour for the selected sensor. A 1 enables the described
+  behaviour.
+
+Bit 0:
+  Give an alarm if measured temp is over the warning threshold		(RW) [1]_
+
+Bit 1:
+  Give an alarm if measured volt is over the max threshold		(RW) [2]_
+
+Bit 2:
+  Give an alarm if measured volt is under the min threshold		(RW) [2]_
+
+Bit 3:
+  Beep if alarm								(RW)
+
+Bit 4:
+  1 if alarm cause measured temp is over the warning threshold		(R)
+
+Bit 5:
+  1 if alarm cause measured volt is over the max threshold		(R)
+
+Bit 6:
+  1 if alarm cause measured volt is under the min threshold		(R)
+
+Bit 7:
+  - Volt sensor: Shutdown if alarm persist for more than 4 seconds	(RW)
+  - Temp sensor: Shutdown if temp is over the shutdown threshold	(RW)
+
+.. [1] This bit is only honored/used by the uGuru if a temp sensor is connected
+
+.. [2] This bit is only honored/used by the uGuru if a volt sensor is connected
+       Note with some trickery this can be used to find out what kinda sensor
+       is detected see the Linux kernel driver for an example with many
+       comments on how todo this.
 
 Byte 1:
-Temp sensor: warning threshold  (scale as bank 0x21)
-Volt sensor: min threshold      (scale as bank 0x21)
+  - Temp sensor: warning threshold  (scale as bank 0x21)
+  - Volt sensor: min threshold      (scale as bank 0x21)
 
 Byte 2:
-Temp sensor: shutdown threshold (scale as bank 0x21)
-Volt sensor: max threshold      (scale as bank 0x21)
+  - Temp sensor: shutdown threshold (scale as bank 0x21)
+  - Volt sensor: max threshold      (scale as bank 0x21)
 
 
-Bank 0x24 PWM outputs for FAN's (R)
-Bank 0x25 PWM outputs for FAN's (W)
------------------------------------
+Bank 0x24 PWM outputs for FAN's (R) and Bank 0x25 PWM outputs for FAN's (W)
+---------------------------------------------------------------------------
 
-This bank contains 3 "sensors", for each sensor it contains 5 bytes.
-Sensor 0 usually controls the CPU fan
-Sensor 1 usually controls the NB (or chipset for single chip) fan
-Sensor 2 usually controls the System fan
+Those banks contain 3 "sensors", for each sensor it contains 5 bytes.
+  - Sensor 0 usually controls the CPU fan
+  - Sensor 1 usually controls the NB (or chipset for single chip) fan
+  - Sensor 2 usually controls the System fan
 
 Byte 0:
-Flag 0x80 to enable control, Fan runs at 100% when disabled.
-low nibble (temp)sensor address at bank 0x21 used for control.
+  Flag 0x80 to enable control, Fan runs at 100% when disabled.
+  low nibble (temp)sensor address at bank 0x21 used for control.
 
 Byte 1:
-0-255 = 0-12v (linear), specify voltage at which fan will rotate when under
-low threshold temp (specified in byte 3)
+  0-255 = 0-12v (linear), specify voltage at which fan will rotate when under
+  low threshold temp (specified in byte 3)
 
 Byte 2:
-0-255 = 0-12v (linear), specify voltage at which fan will rotate when above
-high threshold temp (specified in byte 4)
+  0-255 = 0-12v (linear), specify voltage at which fan will rotate when above
+  high threshold temp (specified in byte 4)
 
 Byte 3:
-Low threshold temp  (scale as bank 0x21)
+  Low threshold temp  (scale as bank 0x21)
 
 byte 4:
-High threshold temp (scale as bank 0x21)
+  High threshold temp (scale as bank 0x21)
 
 
 Bank 0x26 Sensors Bank2 Values / Readings (R)
 ---------------------------------------------
 
 This bank contains 6 sensors (AFAIK), for each sensor it contains 1 byte.
+
 So far the following sensors are known to be available on all motherboards:
-Sensor 0: CPU fan speed
-Sensor 1: NB (or chipset for single chip) fan speed
-Sensor 2: SYS fan speed
+  - Sensor 0: CPU fan speed
+  - Sensor 1: NB (or chipset for single chip) fan speed
+  - Sensor 2: SYS fan speed
 
 Byte 0:
-This byte holds the reading from the sensor. 0-255 = 0-15300 (linear)
+  This byte holds the reading from the sensor. 0-255 = 0-15300 (linear)
 
 
-Bank 0x27 Sensors Bank2 Settings (R)
-Bank 0x28 Sensors Bank2 Settings (W)
-------------------------------------
+Bank 0x27 Sensors Bank2 Settings (R) and Bank 0x28 Sensors Bank2 Settings (W)
+-----------------------------------------------------------------------------
 
-This bank contains 6 sensors (AFAIK), for each sensor it contains 2 bytes.
+Those banks contain 6 sensors (AFAIK), for each sensor it contains 2 bytes.
 
 Byte 0:
-Alarm behaviour for the selected sensor. A 1 enables the described behaviour.
-Bit 0: Give an alarm if measured rpm is under the min threshold	(RW)
-Bit 3: Beep if alarm						(RW)
-Bit 7: Shutdown if alarm persist for more than 4 seconds	(RW)
+  Alarm behaviour for the selected sensor. A 1 enables the described behaviour.
+
+Bit 0:
+  Give an alarm if measured rpm is under the min threshold	(RW)
+
+Bit 3:
+  Beep if alarm							(RW)
+
+Bit 7:
+  Shutdown if alarm persist for more than 4 seconds		(RW)
 
 Byte 1:
-min threshold (scale as bank 0x26)
+  min threshold (scale as bank 0x26)
 
 
 Warning for the adventurous
diff --git a/Documentation/hwmon/abituguru.rst b/Documentation/hwmon/abituguru.rst
new file mode 100644
index 000000000000..d8243c827de9
--- /dev/null
+++ b/Documentation/hwmon/abituguru.rst
@@ -0,0 +1,113 @@
+Kernel driver abituguru
+=======================
+
+Supported chips:
+
+  * Abit uGuru revision 1 & 2 (Hardware Monitor part only)
+
+    Prefix: 'abituguru'
+
+    Addresses scanned: ISA 0x0E0
+
+    Datasheet: Not available, this driver is based on reverse engineering.
+    A "Datasheet" has been written based on the reverse engineering it
+    should be available in the same dir as this file under the name
+    abituguru-datasheet.
+
+    Note:
+	The uGuru is a microcontroller with onboard firmware which programs
+	it to behave as a hwmon IC. There are many different revisions of the
+	firmware and thus effectivly many different revisions of the uGuru.
+	Below is an incomplete list with which revisions are used for which
+	Motherboards:
+
+	- uGuru 1.00    ~ 1.24    (AI7, KV8-MAX3, AN7) [1]_
+	- uGuru 2.0.0.0 ~ 2.0.4.2 (KV8-PRO)
+	- uGuru 2.1.0.0 ~ 2.1.2.8 (AS8, AV8, AA8, AG8, AA8XE, AX8)
+	- uGuru 2.2.0.0 ~ 2.2.0.6 (AA8 Fatal1ty)
+	- uGuru 2.3.0.0 ~ 2.3.0.9 (AN8)
+	- uGuru 3.0.0.0 ~ 3.0.x.x (AW8, AL8, AT8, NI8 SLI, AT8 32X, AN8 32X,
+	  AW9D-MAX) [2]_
+
+.. [1]  For revisions 2 and 3 uGuru's the driver can autodetect the
+	sensortype (Volt or Temp) for bank1 sensors, for revision 1 uGuru's
+	this does not always work. For these uGuru's the autodetection can
+	be overridden with the bank1_types module param. For all 3 known
+	revison 1 motherboards the correct use of this param is:
+	bank1_types=1,1,0,0,0,0,0,2,0,0,0,0,2,0,0,1
+	You may also need to specify the fan_sensors option for these boards
+	fan_sensors=5
+
+.. [2]  There is a separate abituguru3 driver for these motherboards,
+	the abituguru (without the 3 !) driver will not work on these
+	motherboards (and visa versa)!
+
+Authors:
+	- Hans de Goede <j.w.r.degoede@hhs.nl>,
+	- (Initial reverse engineering done by Olle Sandberg
+	  <ollebull@gmail.com>)
+
+
+Module Parameters
+-----------------
+
+* force: bool
+			Force detection. Note this parameter only causes the
+			detection to be skipped, and thus the insmod to
+			succeed. If the uGuru can't be read the actual hwmon
+			driver will not load and thus no hwmon device will get
+			registered.
+* bank1_types: int[]
+			Bank1 sensortype autodetection override:
+
+			  * -1 autodetect (default)
+			  *  0 volt sensor
+			  *  1 temp sensor
+			  *  2 not connected
+* fan_sensors: int
+			Tell the driver how many fan speed sensors there are
+			on your motherboard. Default: 0 (autodetect).
+* pwms: int
+			Tell the driver how many fan speed controls (fan
+			pwms) your motherboard has. Default: 0 (autodetect).
+* verbose: int
+			How verbose should the driver be? (0-3):
+
+			   * 0 normal output
+			   * 1 + verbose error reporting
+			   * 2 + sensors type probing info (default)
+			   * 3 + retryable error reporting
+
+			Default: 2 (the driver is still in the testing phase)
+
+Notice: if you need any of the first three options above please insmod the
+driver with verbose set to 3 and mail me <j.w.r.degoede@hhs.nl> the output of:
+dmesg | grep abituguru
+
+
+Description
+-----------
+
+This driver supports the hardware monitoring features of the first and
+second revision of the Abit uGuru chip found on Abit uGuru featuring
+motherboards (most modern Abit motherboards).
+
+The first and second revision of the uGuru chip in reality is a Winbond
+W83L950D in disguise (despite Abit claiming it is "a new microprocessor
+designed by the ABIT Engineers"). Unfortunately this doesn't help since the
+W83L950D is a generic microcontroller with a custom Abit application running
+on it.
+
+Despite Abit not releasing any information regarding the uGuru, Olle
+Sandberg <ollebull@gmail.com> has managed to reverse engineer the sensor part
+of the uGuru. Without his work this driver would not have been possible.
+
+Known Issues
+------------
+
+The voltage and frequency control parts of the Abit uGuru are not supported.
+
+.. toctree::
+   :maxdepth: 1
+
+   abituguru-datasheet.rst
diff --git a/Documentation/hwmon/abituguru3 b/Documentation/hwmon/abituguru3.rst
index a6ccfe4bb6aa..514f11f41e8b 100644
--- a/Documentation/hwmon/abituguru3
+++ b/Documentation/hwmon/abituguru3.rst
@@ -3,41 +3,51 @@ Kernel driver abituguru3
 
 Supported chips:
   * Abit uGuru revision 3 (Hardware Monitor part, reading only)
+
     Prefix: 'abituguru3'
+
     Addresses scanned: ISA 0x0E0
+
     Datasheet: Not available, this driver is based on reverse engineering.
+
     Note:
 	The uGuru is a microcontroller with onboard firmware which programs
 	it to behave as a hwmon IC. There are many different revisions of the
 	firmware and thus effectivly many different revisions of the uGuru.
 	Below is an incomplete list with which revisions are used for which
 	Motherboards:
-	uGuru 1.00    ~ 1.24    (AI7, KV8-MAX3, AN7)
-	uGuru 2.0.0.0 ~ 2.0.4.2 (KV8-PRO)
-	uGuru 2.1.0.0 ~ 2.1.2.8 (AS8, AV8, AA8, AG8, AA8XE, AX8)
-	uGuru 2.3.0.0 ~ 2.3.0.9 (AN8)
-	uGuru 3.0.0.0 ~ 3.0.x.x (AW8, AL8, AT8, NI8 SLI, AT8 32X, AN8 32X,
-				 AW9D-MAX)
+
+	- uGuru 1.00    ~ 1.24    (AI7, KV8-MAX3, AN7)
+	- uGuru 2.0.0.0 ~ 2.0.4.2 (KV8-PRO)
+	- uGuru 2.1.0.0 ~ 2.1.2.8 (AS8, AV8, AA8, AG8, AA8XE, AX8)
+	- uGuru 2.3.0.0 ~ 2.3.0.9 (AN8)
+	- uGuru 3.0.0.0 ~ 3.0.x.x (AW8, AL8, AT8, NI8 SLI, AT8 32X, AN8 32X,
+	  AW9D-MAX)
+
 	The abituguru3 driver is only for revison 3.0.x.x motherboards,
 	this driver will not work on older motherboards. For older
 	motherboards use the abituguru (without the 3 !) driver.
 
 Authors:
-	Hans de Goede <j.w.r.degoede@hhs.nl>,
-	(Initial reverse engineering done by Louis Kruger)
+	- Hans de Goede <j.w.r.degoede@hhs.nl>,
+	- (Initial reverse engineering done by Louis Kruger)
 
 
 Module Parameters
 -----------------
 
-* force: bool		Force detection. Note this parameter only causes the
+* force: bool
+			Force detection. Note this parameter only causes the
 			detection to be skipped, and thus the insmod to
 			succeed. If the uGuru can't be read the actual hwmon
 			driver will not load and thus no hwmon device will get
 			registered.
-* verbose: bool		Should the driver be verbose?
-			0/off/false  normal output
-			1/on/true    + verbose error reporting (default)
+* verbose: bool
+			Should the driver be verbose?
+
+			* 0/off/false  normal output
+			* 1/on/true    + verbose error reporting (default)
+
 			Default: 1 (the driver is still in the testing phase)
 
 Description
@@ -62,4 +72,4 @@ neither is writing any of the sensor settings and writing / reading the
 fanspeed control registers (FanEQ)
 
 If you encounter any problems please mail me <j.w.r.degoede@hhs.nl> and
-include the output of: "dmesg | grep abituguru"
+include the output of: `dmesg | grep abituguru`
diff --git a/Documentation/hwmon/abx500 b/Documentation/hwmon/abx500.rst
index 319a058cec7c..3d88b2ce0f00 100644
--- a/Documentation/hwmon/abx500
+++ b/Documentation/hwmon/abx500.rst
@@ -2,14 +2,18 @@ Kernel driver abx500
 ====================
 
 Supported chips:
+
   * ST-Ericsson ABx500 series
+
     Prefix: 'abx500'
+
     Addresses scanned: -
+
     Datasheet: http://www.stericsson.com/developers/documentation.jsp
 
 Authors:
-        Martin Persson <martin.persson@stericsson.com>
-        Hongbo Zhang <hongbo.zhang@linaro.org>
+	Martin Persson <martin.persson@stericsson.com>
+	Hongbo Zhang <hongbo.zhang@linaro.org>
 
 Description
 -----------
diff --git a/Documentation/hwmon/acpi_power_meter b/Documentation/hwmon/acpi_power_meter.rst
index c80399a00c50..4a0941ade0ca 100644
--- a/Documentation/hwmon/acpi_power_meter
+++ b/Documentation/hwmon/acpi_power_meter.rst
@@ -4,8 +4,11 @@ Kernel driver power_meter
 This driver talks to ACPI 4.0 power meters.
 
 Supported systems:
+
   * Any recent system with ACPI 4.0.
+
     Prefix: 'power_meter'
+
     Datasheet: http://acpi.info/, section 10.4.
 
 Author: Darrick J. Wong
@@ -18,26 +21,26 @@ the ACPI 4.0 spec (Chapter 10.4).  These devices have a simple set of
 features--a power meter that returns average power use over a configurable
 interval, an optional capping mechanism, and a couple of trip points.  The
 sysfs interface conforms with the specification outlined in the "Power" section
-of Documentation/hwmon/sysfs-interface.
+of Documentation/hwmon/sysfs-interface.rst.
 
 Special Features
 ----------------
 
-The power[1-*]_is_battery knob indicates if the power supply is a battery.
-Both power[1-*]_average_{min,max} must be set before the trip points will work.
+The `power[1-*]_is_battery` knob indicates if the power supply is a battery.
+Both `power[1-*]_average_{min,max}` must be set before the trip points will work.
 When both of them are set, an ACPI event will be broadcast on the ACPI netlink
 socket and a poll notification will be sent to the appropriate
-power[1-*]_average sysfs file.
+`power[1-*]_average` sysfs file.
 
-The power[1-*]_{model_number, serial_number, oem_info} fields display arbitrary
-strings that ACPI provides with the meter.  The measures/ directory contains
-symlinks to the devices that this meter measures.
+The `power[1-*]_{model_number, serial_number, oem_info}` fields display
+arbitrary strings that ACPI provides with the meter.  The measures/ directory
+contains symlinks to the devices that this meter measures.
 
 Some computers have the ability to enforce a power cap in hardware.  If this is
-the case, the power[1-*]_cap and related sysfs files will appear.  When the
+the case, the `power[1-*]_cap` and related sysfs files will appear.  When the
 average power consumption exceeds the cap, an ACPI event will be broadcast on
 the netlink event socket and a poll notification will be sent to the
-appropriate power[1-*]_alarm file to indicate that capping has begun, and the
+appropriate `power[1-*]_alarm` file to indicate that capping has begun, and the
 hardware has taken action to reduce power consumption.  Most likely this will
 result in reduced performance.
 
@@ -46,6 +49,6 @@ all cases the ACPI event will be broadcast on the ACPI netlink event socket as
 well as sent as a poll notification to a sysfs file.  The events are as
 follows:
 
-power[1-*]_cap will be notified if the firmware changes the power cap.
-power[1-*]_interval will be notified if the firmware changes the averaging
+`power[1-*]_cap` will be notified if the firmware changes the power cap.
+`power[1-*]_interval` will be notified if the firmware changes the averaging
 interval.
diff --git a/Documentation/hwmon/ad7314 b/Documentation/hwmon/ad7314.rst
index 1912549c7467..bf389736bcd1 100644
--- a/Documentation/hwmon/ad7314
+++ b/Documentation/hwmon/ad7314.rst
@@ -2,14 +2,23 @@ Kernel driver ad7314
 ====================
 
 Supported chips:
+
    * Analog Devices AD7314
+
      Prefix: 'ad7314'
+
      Datasheet: Publicly available at Analog Devices website.
+
    * Analog Devices ADT7301
+
      Prefix: 'adt7301'
+
      Datasheet: Publicly available at Analog Devices website.
+
    * Analog Devices ADT7302
+
      Prefix: 'adt7302'
+
      Datasheet: Publicly available at Analog Devices website.
 
 Description
diff --git a/Documentation/hwmon/adc128d818 b/Documentation/hwmon/adc128d818.rst
index 39c95004dabc..6753468932ab 100644
--- a/Documentation/hwmon/adc128d818
+++ b/Documentation/hwmon/adc128d818.rst
@@ -2,11 +2,14 @@ Kernel driver adc128d818
 ========================
 
 Supported chips:
+
   * Texas Instruments ADC818D818
+
     Prefix: 'adc818d818'
+
     Addresses scanned: I2C 0x1d, 0x1e, 0x1f, 0x2d, 0x2e, 0x2f
-    Datasheet: Publicly available at the TI website
-               http://www.ti.com/
+
+    Datasheet: Publicly available at the TI website http://www.ti.com/
 
 Author: Guenter Roeck
 
diff --git a/Documentation/hwmon/adm1021 b/Documentation/hwmon/adm1021.rst
index 02ad96cf9b2b..6cbb0f75fe00 100644
--- a/Documentation/hwmon/adm1021
+++ b/Documentation/hwmon/adm1021.rst
@@ -2,51 +2,91 @@ Kernel driver adm1021
 =====================
 
 Supported chips:
+
   * Analog Devices ADM1021
+
     Prefix: 'adm1021'
+
     Addresses scanned: I2C 0x18 - 0x1a, 0x29 - 0x2b, 0x4c - 0x4e
+
     Datasheet: Publicly available at the Analog Devices website
+
   * Analog Devices ADM1021A/ADM1023
+
     Prefix: 'adm1023'
+
     Addresses scanned: I2C 0x18 - 0x1a, 0x29 - 0x2b, 0x4c - 0x4e
+
     Datasheet: Publicly available at the Analog Devices website
+
   * Genesys Logic GL523SM
+
     Prefix: 'gl523sm'
+
     Addresses scanned: I2C 0x18 - 0x1a, 0x29 - 0x2b, 0x4c - 0x4e
+
     Datasheet:
+
   * Maxim MAX1617
+
     Prefix: 'max1617'
+
     Addresses scanned: I2C 0x18 - 0x1a, 0x29 - 0x2b, 0x4c - 0x4e
+
     Datasheet: Publicly available at the Maxim website
+
   * Maxim MAX1617A
+
     Prefix: 'max1617a'
+
     Addresses scanned: I2C 0x18 - 0x1a, 0x29 - 0x2b, 0x4c - 0x4e
+
     Datasheet: Publicly available at the Maxim website
+
   * National Semiconductor LM84
+
     Prefix: 'lm84'
+
     Addresses scanned: I2C 0x18 - 0x1a, 0x29 - 0x2b, 0x4c - 0x4e
+
     Datasheet: Publicly available at the National Semiconductor website
+
   * Philips NE1617
+
     Prefix: 'max1617' (probably detected as a max1617)
+
     Addresses scanned: I2C 0x18 - 0x1a, 0x29 - 0x2b, 0x4c - 0x4e
+
     Datasheet: Publicly available at the Philips website
+
   * Philips NE1617A
+
     Prefix: 'max1617' (probably detected as a max1617)
+
     Addresses scanned: I2C 0x18 - 0x1a, 0x29 - 0x2b, 0x4c - 0x4e
+
     Datasheet: Publicly available at the Philips website
+
   * TI THMC10
+
     Prefix: 'thmc10'
+
     Addresses scanned: I2C 0x18 - 0x1a, 0x29 - 0x2b, 0x4c - 0x4e
+
     Datasheet: Publicly available at the TI website
+
   * Onsemi MC1066
+
     Prefix: 'mc1066'
+
     Addresses scanned: I2C 0x18 - 0x1a, 0x29 - 0x2b, 0x4c - 0x4e
+
     Datasheet: Publicly available at the Onsemi website
 
 
 Authors:
-        Frodo Looijaard <frodol@dds.nl>,
-        Philip Edelbrock <phil@netroedge.com>
+	- Frodo Looijaard <frodol@dds.nl>,
+	- Philip Edelbrock <phil@netroedge.com>
 
 Module Parameters
 -----------------
diff --git a/Documentation/hwmon/adm1025 b/Documentation/hwmon/adm1025.rst
index 99f05049c68a..283e65e348a5 100644
--- a/Documentation/hwmon/adm1025
+++ b/Documentation/hwmon/adm1025.rst
@@ -2,23 +2,32 @@ Kernel driver adm1025
 =====================
 
 Supported chips:
+
   * Analog Devices ADM1025, ADM1025A
+
     Prefix: 'adm1025'
+
     Addresses scanned: I2C 0x2c - 0x2e
+
     Datasheet: Publicly available at the Analog Devices website
+
   * Philips NE1619
+
     Prefix: 'ne1619'
+
     Addresses scanned: I2C 0x2c - 0x2d
+
     Datasheet: Publicly available at the Philips website
 
 The NE1619 presents some differences with the original ADM1025:
+
   * Only two possible addresses (0x2c - 0x2d).
   * No temperature offset register, but we don't use it anyway.
   * No INT mode for pin 16. We don't play with it anyway.
 
 Authors:
-        Chen-Yuan Wu <gwu@esoft.com>,
-        Jean Delvare <jdelvare@suse.de>
+	- Chen-Yuan Wu <gwu@esoft.com>,
+	- Jean Delvare <jdelvare@suse.de>
 
 Description
 -----------
diff --git a/Documentation/hwmon/adm1026 b/Documentation/hwmon/adm1026.rst
index d8fabe0c23ac..35d63e6498a3 100644
--- a/Documentation/hwmon/adm1026
+++ b/Documentation/hwmon/adm1026.rst
@@ -3,28 +3,36 @@ Kernel driver adm1026
 
 Supported chips:
   * Analog Devices ADM1026
+
     Prefix: 'adm1026'
+
     Addresses scanned: I2C 0x2c, 0x2d, 0x2e
+
     Datasheet: Publicly available at the Analog Devices website
-               http://www.onsemi.com/PowerSolutions/product.do?id=ADM1026
+
+	       http://www.onsemi.com/PowerSolutions/product.do?id=ADM1026
 
 Authors:
-        Philip Pokorny <ppokorny@penguincomputing.com> for Penguin Computing
-        Justin Thiessen <jthiessen@penguincomputing.com>
+	- Philip Pokorny <ppokorny@penguincomputing.com> for Penguin Computing
+	- Justin Thiessen <jthiessen@penguincomputing.com>
 
 Module Parameters
 -----------------
 
 * gpio_input: int array (min = 1, max = 17)
-  List of GPIO pins (0-16) to program as inputs
+    List of GPIO pins (0-16) to program as inputs
+
 * gpio_output: int array (min = 1, max = 17)
-  List of GPIO pins (0-16) to program as outputs
+    List of GPIO pins (0-16) to program as outputs
+
 * gpio_inverted: int array (min = 1, max = 17)
-  List of GPIO pins (0-16) to program as inverted
+    List of GPIO pins (0-16) to program as inverted
+
 * gpio_normal: int array (min = 1, max = 17)
-  List of GPIO pins (0-16) to program as normal/non-inverted
+    List of GPIO pins (0-16) to program as normal/non-inverted
+
 * gpio_fan: int array (min = 1, max = 8)
-  List of GPIO pins (0-7) to program as fan tachs
+    List of GPIO pins (0-7) to program as fan tachs
 
 
 Description
diff --git a/Documentation/hwmon/adm1031 b/Documentation/hwmon/adm1031.rst
index a143117c99cb..a677c3ab5574 100644
--- a/Documentation/hwmon/adm1031
+++ b/Documentation/hwmon/adm1031.rst
@@ -3,20 +3,28 @@ Kernel driver adm1031
 
 Supported chips:
   * Analog Devices ADM1030
+
     Prefix: 'adm1030'
+
     Addresses scanned: I2C 0x2c to 0x2e
+
     Datasheet: Publicly available at the Analog Devices website
-               http://www.analog.com/en/prod/0%2C2877%2CADM1030%2C00.html
+
+	       http://www.analog.com/en/prod/0%2C2877%2CADM1030%2C00.html
 
   * Analog Devices ADM1031
+
     Prefix: 'adm1031'
+
     Addresses scanned: I2C 0x2c to 0x2e
+
     Datasheet: Publicly available at the Analog Devices website
-               http://www.analog.com/en/prod/0%2C2877%2CADM1031%2C00.html
+
+	       http://www.analog.com/en/prod/0%2C2877%2CADM1031%2C00.html
 
 Authors:
-        Alexandre d'Alton <alex@alexdalton.org>
-        Jean Delvare <jdelvare@suse.de>
+	- Alexandre d'Alton <alex@alexdalton.org>
+	- Jean Delvare <jdelvare@suse.de>
 
 Description
 -----------
diff --git a/Documentation/hwmon/adm1275 b/Documentation/hwmon/adm1275.rst
index 5e277b0d91ce..9a1913e5b4d9 100644
--- a/Documentation/hwmon/adm1275
+++ b/Documentation/hwmon/adm1275.rst
@@ -2,29 +2,53 @@ Kernel driver adm1275
 =====================
 
 Supported chips:
+
   * Analog Devices ADM1075
+
     Prefix: 'adm1075'
+
     Addresses scanned: -
+
     Datasheet: www.analog.com/static/imported-files/data_sheets/ADM1075.pdf
+
   * Analog Devices ADM1272
+
     Prefix: 'adm1272'
+
     Addresses scanned: -
+
     Datasheet: www.analog.com/static/imported-files/data_sheets/ADM1272.pdf
+
   * Analog Devices ADM1275
+
     Prefix: 'adm1275'
+
     Addresses scanned: -
+
     Datasheet: www.analog.com/static/imported-files/data_sheets/ADM1275.pdf
+
   * Analog Devices ADM1276
+
     Prefix: 'adm1276'
+
     Addresses scanned: -
+
     Datasheet: www.analog.com/static/imported-files/data_sheets/ADM1276.pdf
+
   * Analog Devices ADM1278
+
     Prefix: 'adm1278'
+
     Addresses scanned: -
+
     Datasheet: www.analog.com/static/imported-files/data_sheets/ADM1278.pdf
+
   * Analog Devices ADM1293/ADM1294
+
     Prefix: 'adm1293', 'adm1294'
+
     Addresses scanned: -
+
     Datasheet: http://www.analog.com/media/en/technical-documentation/data-sheets/ADM1293_1294.pdf
 
 Author: Guenter Roeck <linux@roeck-us.net>
@@ -44,7 +68,7 @@ integrated 12 bit analog-to-digital converter (ADC), accessed using a
 PMBus interface.
 
 The driver is a client driver to the core PMBus driver. Please see
-Documentation/hwmon/pmbus for details on PMBus client drivers.
+Documentation/hwmon/pmbus.rst for details on PMBus client drivers.
 
 
 Usage Notes
@@ -66,7 +90,7 @@ Platform data support
 ---------------------
 
 The driver supports standard PMBus driver platform data. Please see
-Documentation/hwmon/pmbus for details.
+Documentation/hwmon/pmbus.rst for details.
 
 
 Sysfs entries
@@ -75,6 +99,7 @@ Sysfs entries
 The following attributes are supported. Limits are read-write, history reset
 attributes are write-only, all other attributes are read-only.
 
+======================= =======================================================
 inX_label		"vin1" or "vout1" depending on chip variant and
 			configuration. On ADM1075, ADM1293, and ADM1294,
 			vout1 reports the voltage on the VAUX pin.
@@ -120,3 +145,4 @@ temp1_reset_history	Write any value to reset history.
 
 			Temperature attributes are supported on ADM1272 and
 			ADM1278.
+======================= =======================================================
diff --git a/Documentation/hwmon/adm9240 b/Documentation/hwmon/adm9240.rst
index 9b174fc700cc..91063b0f4c6f 100644
--- a/Documentation/hwmon/adm9240
+++ b/Documentation/hwmon/adm9240.rst
@@ -2,30 +2,43 @@ Kernel driver adm9240
 =====================
 
 Supported chips:
+
   * Analog Devices ADM9240
+
     Prefix: 'adm9240'
+
     Addresses scanned: I2C 0x2c - 0x2f
+
     Datasheet: Publicly available at the Analog Devices website
-    http://www.analog.com/UploadedFiles/Data_Sheets/79857778ADM9240_0.pdf
+
+	http://www.analog.com/UploadedFiles/Data_Sheets/79857778ADM9240_0.pdf
 
   * Dallas Semiconductor DS1780
+
     Prefix: 'ds1780'
+
     Addresses scanned: I2C 0x2c - 0x2f
+
     Datasheet: Publicly available at the Dallas Semiconductor (Maxim) website
-    http://pdfserv.maxim-ic.com/en/ds/DS1780.pdf
+
+	http://pdfserv.maxim-ic.com/en/ds/DS1780.pdf
 
   * National Semiconductor LM81
+
     Prefix: 'lm81'
+
     Addresses scanned: I2C 0x2c - 0x2f
+
     Datasheet: Publicly available at the National Semiconductor website
-    http://www.national.com/ds.cgi/LM/LM81.pdf
+
+	http://www.national.com/ds.cgi/LM/LM81.pdf
 
 Authors:
-    Frodo Looijaard <frodol@dds.nl>,
-    Philip Edelbrock <phil@netroedge.com>,
-    Michiel Rook <michiel@grendelproject.nl>,
-    Grant Coady <gcoady.lk@gmail.com> with guidance
-        from Jean Delvare <jdelvare@suse.de>
+    - Frodo Looijaard <frodol@dds.nl>,
+    - Philip Edelbrock <phil@netroedge.com>,
+    - Michiel Rook <michiel@grendelproject.nl>,
+    - Grant Coady <gcoady.lk@gmail.com> with guidance
+      from Jean Delvare <jdelvare@suse.de>
 
 Interface
 ---------
@@ -87,11 +100,13 @@ rpm = (22500 * 60) / (count * divider)
 Automatic fan clock divider
 
   * User sets 0 to fan_min limit
+
     - low speed alarm is disabled
     - fan clock divider not changed
     - auto fan clock adjuster enabled for valid fan speed reading
 
   * User sets fan_min limit too low
+
     - low speed alarm is enabled
     - fan clock divider set to max
     - fan_min set to register value 254 which corresponds
@@ -101,18 +116,20 @@ Automatic fan clock divider
     - auto fan clock adjuster disabled
 
   * User sets reasonable fan speed
+
     - low speed alarm is enabled
     - fan clock divider set to suit fan_min
     - auto fan clock adjuster enabled: adjusts fan_min
 
   * User sets unreasonably high low fan speed limit
+
     - resolution of the low speed limit may be reduced
     - alarm will be asserted
     - auto fan clock adjuster enabled: adjusts fan_min
 
-    * fan speed may be displayed as zero until the auto fan clock divider
-      adjuster brings fan speed clock divider back into chip measurement
-      range, this will occur within a few measurement cycles.
+  * fan speed may be displayed as zero until the auto fan clock divider
+    adjuster brings fan speed clock divider back into chip measurement
+    range, this will occur within a few measurement cycles.
 
 Analog Output
 -------------
@@ -122,16 +139,21 @@ power up or reset. This doesn't do much on the test Intel SE440BX-2.
 
 Voltage Monitor
 
+^^^^^^^^^^^^^^^
+
 Voltage (IN) measurement is internally scaled:
 
+    === =========== =========== ========= ==========
     nr  label       nominal     maximum   resolution
-                      mV          mV         mV
+		      mV          mV         mV
+    === =========== =========== ========= ==========
     0   +2.5V        2500        3320       13.0
     1   Vccp1        2700        3600       14.1
     2   +3.3V        3300        4380       17.2
     3     +5V        5000        6640       26.0
     4    +12V       12000       15940       62.5
     5   Vccp2        2700        3600       14.1
+    === =========== =========== ========= ==========
 
 The reading is an unsigned 8-bit value, nominal voltage measurement is
 represented by a reading of 192, being 3/4 of the measurement range.
@@ -159,8 +181,9 @@ Clear the CI latch by writing value 0 to the sysfs intrusion0_alarm file.
 
 Alarm flags reported as 16-bit word
 
+    ===     =============       ==========================
     bit     label               comment
-    ---     -------------       --------------------------
+    ===     =============       ==========================
      0      +2.5 V_Error        high or low limit exceeded
      1      VCCP_Error          high or low limit exceeded
      2      +3.3 V_Error        high or low limit exceeded
@@ -171,6 +194,7 @@ Alarm flags reported as 16-bit word
      8      +12 V_Error         high or low limit exceeded
      9      VCCP2_Error         high or low limit exceeded
     12      Chassis_Error       CI pin went high
+    ===     =============       ==========================
 
 Remaining bits are reserved and thus undefined. It is important to note
 that alarm bits may be cleared on read, user-space may latch alarms and
diff --git a/Documentation/hwmon/ads1015 b/Documentation/hwmon/ads1015.rst
index 02d2a459385f..e0951c4e57bb 100644
--- a/Documentation/hwmon/ads1015
+++ b/Documentation/hwmon/ads1015.rst
@@ -2,17 +2,25 @@ Kernel driver ads1015
 =====================
 
 Supported chips:
+
   * Texas Instruments ADS1015
+
     Prefix: 'ads1015'
-    Datasheet: Publicly available at the Texas Instruments website :
-               http://focus.ti.com/lit/ds/symlink/ads1015.pdf
+
+    Datasheet: Publicly available at the Texas Instruments website:
+
+	       http://focus.ti.com/lit/ds/symlink/ads1015.pdf
+
   * Texas Instruments ADS1115
+
     Prefix: 'ads1115'
-    Datasheet: Publicly available at the Texas Instruments website :
-               http://focus.ti.com/lit/ds/symlink/ads1115.pdf
+
+    Datasheet: Publicly available at the Texas Instruments website:
+
+	       http://focus.ti.com/lit/ds/symlink/ads1115.pdf
 
 Authors:
-        Dirk Eibach, Guntermann & Drunck GmbH <eibach@gdsys.de>
+	Dirk Eibach, Guntermann & Drunck GmbH <eibach@gdsys.de>
 
 Description
 -----------
@@ -24,14 +32,15 @@ This device is a 12/16-bit A-D converter with 4 inputs.
 The inputs can be used single ended or in certain differential combinations.
 
 The inputs can be made available by 8 sysfs input files in0_input - in7_input:
-in0: Voltage over AIN0 and AIN1.
-in1: Voltage over AIN0 and AIN3.
-in2: Voltage over AIN1 and AIN3.
-in3: Voltage over AIN2 and AIN3.
-in4: Voltage over AIN0 and GND.
-in5: Voltage over AIN1 and GND.
-in6: Voltage over AIN2 and GND.
-in7: Voltage over AIN3 and GND.
+
+  - in0: Voltage over AIN0 and AIN1.
+  - in1: Voltage over AIN0 and AIN3.
+  - in2: Voltage over AIN1 and AIN3.
+  - in3: Voltage over AIN2 and AIN3.
+  - in4: Voltage over AIN0 and GND.
+  - in5: Voltage over AIN1 and GND.
+  - in6: Voltage over AIN2 and GND.
+  - in7: Voltage over AIN3 and GND.
 
 Which inputs are available can be configured using platform data or devicetree.
 
@@ -42,29 +51,34 @@ Platform Data
 
 In linux/platform_data/ads1015.h platform data is defined, channel_data contains
 configuration data for the used input combinations:
+
 - pga is the programmable gain amplifier (values are full scale)
-  0: +/- 6.144 V
-  1: +/- 4.096 V
-  2: +/- 2.048 V
-  3: +/- 1.024 V
-  4: +/- 0.512 V
-  5: +/- 0.256 V
+
+    - 0: +/- 6.144 V
+    - 1: +/- 4.096 V
+    - 2: +/- 2.048 V
+    - 3: +/- 1.024 V
+    - 4: +/- 0.512 V
+    - 5: +/- 0.256 V
+
 - data_rate in samples per second
-  0: 128
-  1: 250
-  2: 490
-  3: 920
-  4: 1600
-  5: 2400
-  6: 3300
-
-Example:
-struct ads1015_platform_data data = {
+
+    - 0: 128
+    - 1: 250
+    - 2: 490
+    - 3: 920
+    - 4: 1600
+    - 5: 2400
+    - 6: 3300
+
+Example::
+
+  struct ads1015_platform_data data = {
 	.channel_data = {
 		[2] = { .enabled = true, .pga = 1, .data_rate = 0 },
 		[4] = { .enabled = true, .pga = 4, .data_rate = 5 },
 	}
-};
+  };
 
 In this case only in2_input (FS +/- 4.096 V, 128 SPS) and in4_input
 (FS +/- 0.512 V, 2400 SPS) would be created.
diff --git a/Documentation/hwmon/ads7828 b/Documentation/hwmon/ads7828.rst
index f6e263e0f607..b830b490cfe4 100644
--- a/Documentation/hwmon/ads7828
+++ b/Documentation/hwmon/ads7828.rst
@@ -2,20 +2,27 @@ Kernel driver ads7828
 =====================
 
 Supported chips:
+
   * Texas Instruments/Burr-Brown ADS7828
+
     Prefix: 'ads7828'
+
     Datasheet: Publicly available at the Texas Instruments website:
-               http://focus.ti.com/lit/ds/symlink/ads7828.pdf
+
+	       http://focus.ti.com/lit/ds/symlink/ads7828.pdf
 
   * Texas Instruments ADS7830
+
     Prefix: 'ads7830'
+
     Datasheet: Publicly available at the Texas Instruments website:
-               http://focus.ti.com/lit/ds/symlink/ads7830.pdf
+
+	       http://focus.ti.com/lit/ds/symlink/ads7830.pdf
 
 Authors:
-        Steve Hardy <shardy@redhat.com>
-        Vivien Didelot <vivien.didelot@savoirfairelinux.com>
-        Guillaume Roguez <guillaume.roguez@savoirfairelinux.com>
+	- Steve Hardy <shardy@redhat.com>
+	- Vivien Didelot <vivien.didelot@savoirfairelinux.com>
+	- Guillaume Roguez <guillaume.roguez@savoirfairelinux.com>
 
 Platform data
 -------------
@@ -24,16 +31,16 @@ The ads7828 driver accepts an optional ads7828_platform_data structure (defined
 in include/linux/platform_data/ads7828.h). The structure fields are:
 
 * diff_input: (bool) Differential operation
-  set to true for differential mode, false for default single ended mode.
+    set to true for differential mode, false for default single ended mode.
 
 * ext_vref: (bool) External reference
-  set to true if it operates with an external reference, false for default
-  internal reference.
+    set to true if it operates with an external reference, false for default
+    internal reference.
 
 * vref_mv: (unsigned int) Voltage reference
-  if using an external reference, set this to the reference voltage in mV,
-  otherwise it will default to the internal value (2500mV). This value will be
-  bounded with limits accepted by the chip, described in the datasheet.
+    if using an external reference, set this to the reference voltage in mV,
+    otherwise it will default to the internal value (2500mV). This value will be
+    bounded with limits accepted by the chip, described in the datasheet.
 
  If no structure is provided, the configuration defaults to single ended
  operation and internal voltage reference (2.5V).
diff --git a/Documentation/hwmon/adt7410 b/Documentation/hwmon/adt7410.rst
index 9817941e5f19..24caaa83c8ec 100644
--- a/Documentation/hwmon/adt7410
+++ b/Documentation/hwmon/adt7410.rst
@@ -2,26 +2,45 @@ Kernel driver adt7410
 =====================
 
 Supported chips:
+
   * Analog Devices ADT7410
+
     Prefix: 'adt7410'
+
     Addresses scanned: None
+
     Datasheet: Publicly available at the Analog Devices website
-               http://www.analog.com/static/imported-files/data_sheets/ADT7410.pdf
+
+	       http://www.analog.com/static/imported-files/data_sheets/ADT7410.pdf
   * Analog Devices ADT7420
+
     Prefix: 'adt7420'
+
     Addresses scanned: None
+
     Datasheet: Publicly available at the Analog Devices website
-               http://www.analog.com/static/imported-files/data_sheets/ADT7420.pdf
+
+	       http://www.analog.com/static/imported-files/data_sheets/ADT7420.pdf
+
   * Analog Devices ADT7310
+
     Prefix: 'adt7310'
+
     Addresses scanned: None
+
     Datasheet: Publicly available at the Analog Devices website
-               http://www.analog.com/static/imported-files/data_sheets/ADT7310.pdf
+
+	       http://www.analog.com/static/imported-files/data_sheets/ADT7310.pdf
+
   * Analog Devices ADT7320
+
     Prefix: 'adt7320'
+
     Addresses scanned: None
+
     Datasheet: Publicly available at the Analog Devices website
-               http://www.analog.com/static/imported-files/data_sheets/ADT7320.pdf
+
+	       http://www.analog.com/static/imported-files/data_sheets/ADT7320.pdf
 
 Author: Hartmut Knaack <knaack.h@gmx.de>
 
@@ -61,13 +80,15 @@ The device is set to 16 bit resolution and comparator mode.
 sysfs-Interface
 ---------------
 
-temp#_input		- temperature input
-temp#_min		- temperature minimum setpoint
-temp#_max		- temperature maximum setpoint
-temp#_crit		- critical temperature setpoint
-temp#_min_hyst		- hysteresis for temperature minimum (read-only)
-temp#_max_hyst		- hysteresis for temperature maximum (read/write)
-temp#_crit_hyst		- hysteresis for critical temperature (read-only)
-temp#_min_alarm		- temperature minimum alarm flag
-temp#_max_alarm		- temperature maximum alarm flag
-temp#_crit_alarm	- critical temperature alarm flag
+======================== ====================================================
+temp#_input		 temperature input
+temp#_min		 temperature minimum setpoint
+temp#_max		 temperature maximum setpoint
+temp#_crit		 critical temperature setpoint
+temp#_min_hyst		 hysteresis for temperature minimum (read-only)
+temp#_max_hyst		 hysteresis for temperature maximum (read/write)
+temp#_crit_hyst		 hysteresis for critical temperature (read-only)
+temp#_min_alarm		 temperature minimum alarm flag
+temp#_max_alarm		 temperature maximum alarm flag
+temp#_crit_alarm	 critical temperature alarm flag
+======================== ====================================================
diff --git a/Documentation/hwmon/adt7411 b/Documentation/hwmon/adt7411.rst
index 1632960f9745..57ad16fb216a 100644
--- a/Documentation/hwmon/adt7411
+++ b/Documentation/hwmon/adt7411.rst
@@ -2,9 +2,13 @@ Kernel driver adt7411
 =====================
 
 Supported chips:
+
   * Analog Devices ADT7411
+
     Prefix: 'adt7411'
+
     Addresses scanned: 0x48, 0x4a, 0x4b
+
     Datasheet: Publicly available at the Analog Devices website
 
 Author: Wolfram Sang (based on adt7470 by Darrick J. Wong)
@@ -26,15 +30,19 @@ Check the datasheet for details.
 sysfs-Interface
 ---------------
 
-in0_input	- vdd voltage input
-in[1-8]_input	- analog 1-8 input
-temp1_input	- temperature input
+================ =================
+in0_input	 vdd voltage input
+in[1-8]_input	 analog 1-8 input
+temp1_input	 temperature input
+================ =================
 
 Besides standard interfaces, this driver adds (0 = off, 1 = on):
 
-  adc_ref_vdd	- Use vdd as reference instead of 2.25 V
-  fast_sampling	- Sample at 22.5 kHz instead of 1.4 kHz, but drop filters
-  no_average	- Turn off averaging over 16 samples
+  ============== =======================================================
+  adc_ref_vdd	 Use vdd as reference instead of 2.25 V
+  fast_sampling	 Sample at 22.5 kHz instead of 1.4 kHz, but drop filters
+  no_average	 Turn off averaging over 16 samples
+  ============== =======================================================
 
 Notes
 -----
diff --git a/Documentation/hwmon/adt7462 b/Documentation/hwmon/adt7462.rst
index ec660b328275..139e19696188 100644
--- a/Documentation/hwmon/adt7462
+++ b/Documentation/hwmon/adt7462.rst
@@ -1,10 +1,14 @@
 Kernel driver adt7462
-======================
+=====================
 
 Supported chips:
+
   * Analog Devices ADT7462
+
     Prefix: 'adt7462'
+
     Addresses scanned: I2C 0x58, 0x5C
+
     Datasheet: Publicly available at the Analog Devices website
 
 Author: Darrick J. Wong
@@ -57,11 +61,10 @@ Besides standard interfaces driver adds the following:
 * pwm#_auto_point1_pwm and temp#_auto_point1_temp and
 * pwm#_auto_point2_pwm and temp#_auto_point2_temp -
 
-point1: Set the pwm speed at a lower temperature bound.
-point2: Set the pwm speed at a higher temperature bound.
+  - point1: Set the pwm speed at a lower temperature bound.
+  - point2: Set the pwm speed at a higher temperature bound.
 
 The ADT7462 will scale the pwm between the lower and higher pwm speed when
 the temperature is between the two temperature boundaries.  PWM values range
 from 0 (off) to 255 (full speed).  Fan speed will be set to maximum when the
 temperature sensor associated with the PWM control exceeds temp#_max.
-
diff --git a/Documentation/hwmon/adt7470 b/Documentation/hwmon/adt7470.rst
index fe68e18a0c8d..d225f816e992 100644
--- a/Documentation/hwmon/adt7470
+++ b/Documentation/hwmon/adt7470.rst
@@ -2,9 +2,13 @@ Kernel driver adt7470
 =====================
 
 Supported chips:
+
   * Analog Devices ADT7470
+
     Prefix: 'adt7470'
+
     Addresses scanned: I2C 0x2C, 0x2E, 0x2F
+
     Datasheet: Publicly available at the Analog Devices website
 
 Author: Darrick J. Wong
@@ -56,8 +60,8 @@ Besides standard interfaces driver adds the following:
 * pwm#_auto_point1_pwm and pwm#_auto_point1_temp and
 * pwm#_auto_point2_pwm and pwm#_auto_point2_temp -
 
-point1: Set the pwm speed at a lower temperature bound.
-point2: Set the pwm speed at a higher temperature bound.
+  - point1: Set the pwm speed at a lower temperature bound.
+  - point2: Set the pwm speed at a higher temperature bound.
 
 The ADT7470 will scale the pwm between the lower and higher pwm speed when
 the temperature is between the two temperature boundaries.  PWM values range
diff --git a/Documentation/hwmon/adt7475 b/Documentation/hwmon/adt7475.rst
index 01b46b290532..ef3ea1ea9bc1 100644
--- a/Documentation/hwmon/adt7475
+++ b/Documentation/hwmon/adt7475.rst
@@ -2,28 +2,44 @@ Kernel driver adt7475
 =====================
 
 Supported chips:
+
   * Analog Devices ADT7473
+
     Prefix: 'adt7473'
+
     Addresses scanned: I2C 0x2C, 0x2D, 0x2E
+
     Datasheet: Publicly available at the On Semiconductors website
+
   * Analog Devices ADT7475
+
     Prefix: 'adt7475'
+
     Addresses scanned: I2C 0x2E
+
     Datasheet: Publicly available at the On Semiconductors website
+
   * Analog Devices ADT7476
+
     Prefix: 'adt7476'
+
     Addresses scanned: I2C 0x2C, 0x2D, 0x2E
+
     Datasheet: Publicly available at the On Semiconductors website
+
   * Analog Devices ADT7490
+
     Prefix: 'adt7490'
+
     Addresses scanned: I2C 0x2C, 0x2D, 0x2E
+
     Datasheet: Publicly available at the On Semiconductors website
 
 Authors:
-	Jordan Crouse
-	Hans de Goede
-	Darrick J. Wong (documentation)
-	Jean Delvare
+	- Jordan Crouse
+	- Hans de Goede
+	- Darrick J. Wong (documentation)
+	- Jean Delvare
 
 
 Description
@@ -82,14 +98,16 @@ ADT7490:
 Sysfs Mapping
 -------------
 
-     ADT7490     ADT7476     ADT7475   ADT7473
-     -------     -------     -------   -------
+==== =========== =========== ========= ==========
+in   ADT7490     ADT7476     ADT7475   ADT7473
+==== =========== =========== ========= ==========
 in0  2.5VIN (22) 2.5VIN (22) -         -
 in1  VCCP   (23) VCCP   (23) VCCP (14) VCCP (14)
 in2  VCC    (4)  VCC    (4)  VCC  (4)  VCC  (3)
 in3  5VIN   (20) 5VIN   (20)
 in4  12VIN  (21) 12VIN  (21)
 in5  VTT    (8)
+==== =========== =========== ========= ==========
 
 Special Features
 ----------------
@@ -107,8 +125,8 @@ Fan Speed Control
 
 The driver exposes two trip points per PWM channel.
 
-point1: Set the PWM speed at the lower temperature bound
-point2: Set the PWM speed at the higher temperature bound
+- point1: Set the PWM speed at the lower temperature bound
+- point2: Set the PWM speed at the higher temperature bound
 
 The ADT747x will scale the PWM linearly between the lower and higher PWM
 speed when the temperature is between the two temperature boundaries.
@@ -123,12 +141,12 @@ the PWM control exceeds temp#_max.
 
 At Tmin - hysteresis the PWM output can either be off (0% duty cycle) or at the
 minimum (i.e. auto_point1_pwm). This behaviour can be configured using the
-pwm[1-*]_stall_disable sysfs attribute. A value of 0 means the fans will shut
+`pwm[1-*]_stall_disable sysfs attribute`. A value of 0 means the fans will shut
 off. A value of 1 means the fans will run at auto_point1_pwm.
 
 The responsiveness of the ADT747x to temperature changes can be configured.
 This allows smoothing of the fan speed transition. To set the transition time
-set the value in ms in the temp[1-*]_smoothing sysfs attribute.
+set the value in ms in the `temp[1-*]_smoothing` sysfs attribute.
 
 Notes
 -----
diff --git a/Documentation/hwmon/amc6821 b/Documentation/hwmon/amc6821.rst
index ced8359c50f8..5ddb2849da90 100644
--- a/Documentation/hwmon/amc6821
+++ b/Documentation/hwmon/amc6821.rst
@@ -2,9 +2,13 @@ Kernel driver amc6821
 =====================
 
 Supported chips:
+
 	Texas Instruments AMC6821
+
 	Prefix: 'amc6821'
+
 	Addresses scanned: 0x18, 0x19, 0x1a, 0x2c, 0x2d, 0x2e, 0x4c, 0x4d, 0x4e
+
 	Datasheet: http://focus.ti.com/docs/prod/folders/print/amc6821.html
 
 Authors:
@@ -21,10 +25,11 @@ The pwm can be controlled either from software or automatically.
 
 The driver provides the following sensor accesses in sysfs:
 
+======================= ==      ===============================================
 temp1_input		ro	on-chip temperature
 temp1_min		rw	"
 temp1_max		rw	"
-temp1_crit	 	rw	"
+temp1_crit		rw	"
 temp1_min_alarm		ro	"
 temp1_max_alarm		ro	"
 temp1_crit_alarm	ro	"
@@ -32,16 +37,16 @@ temp1_crit_alarm	ro	"
 temp2_input		ro	remote temperature
 temp2_min		rw	"
 temp2_max		rw	"
-temp2_crit	 	rw	"
+temp2_crit		rw	"
 temp2_min_alarm		ro	"
 temp2_max_alarm		ro	"
 temp2_crit_alarm	ro	"
 temp2_fault		ro	"
 
-fan1_input	 	ro	tachometer speed
+fan1_input		ro	tachometer speed
 fan1_min		rw	"
 fan1_max		rw	"
-fan1_fault	 	ro	"
+fan1_fault		ro	"
 fan1_div		rw	Fan divisor can be either 2 or 4.
 
 pwm1			rw	pwm1
@@ -87,6 +92,7 @@ temp2_auto_point3_temp	rw	Above this temperature fan runs at maximum
 				values which depend on temp2_auto_point2_temp
 				and pwm1_auto_point2_pwm. Read it out after
 				writing to get actual value.
+======================= ==      ===============================================
 
 
 Module parameters
@@ -97,6 +103,6 @@ load the module with: init=0.
 
 If your board BIOS doesn't initialize the chip, or you want
 different settings, you can set the following parameters:
-init=1,
-pwminv: 0 default pwm output, 1 inverts pwm output.
 
+- init=1,
+- pwminv: 0 default pwm output, 1 inverts pwm output.
diff --git a/Documentation/hwmon/asb100 b/Documentation/hwmon/asb100.rst
index ab7365e139be..c2d5f97085fe 100644
--- a/Documentation/hwmon/asb100
+++ b/Documentation/hwmon/asb100.rst
@@ -2,9 +2,13 @@ Kernel driver asb100
 ====================
 
 Supported Chips:
+
   * Asus ASB100 and ASB100-A "Bach"
+
     Prefix: 'asb100'
+
     Addresses scanned: I2C 0x2d
+
     Datasheet: none released
 
 Author: Mark M. Hoffman <mhoffman@lightlink.com>
@@ -41,32 +45,29 @@ processor itself. It is a value in volts.
 
 Alarms: (TODO question marks indicate may or may not work)
 
-0x0001 => in0 (?)
-0x0002 => in1 (?)
-0x0004 => in2
-0x0008 => in3
-0x0010 => temp1 (1)
-0x0020 => temp2
-0x0040 => fan1
-0x0080 => fan2
-0x0100 => in4
-0x0200 => in5 (?) (2)
-0x0400 => in6 (?) (2)
-0x0800 => fan3
-0x1000 => chassis switch
-0x2000 => temp3
-
-Alarm Notes:
-
-(1) This alarm will only trigger if the hysteresis value is 127C.
-I.e. it behaves the same as w83781d.
-
-(2) The min and max registers for these values appear to
-be read-only or otherwise stuck at 0x00.
+- 0x0001 => in0 (?)
+- 0x0002 => in1 (?)
+- 0x0004 => in2
+- 0x0008 => in3
+- 0x0010 => temp1 [1]_
+- 0x0020 => temp2
+- 0x0040 => fan1
+- 0x0080 => fan2
+- 0x0100 => in4
+- 0x0200 => in5 (?) [2]_
+- 0x0400 => in6 (?) [2]_
+- 0x0800 => fan3
+- 0x1000 => chassis switch
+- 0x2000 => temp3
+
+.. [1]	This alarm will only trigger if the hysteresis value is 127C.
+	I.e. it behaves the same as w83781d.
+
+.. [2]	The min and max registers for these values appear to
+	be read-only or otherwise stuck at 0x00.
 
 TODO:
-* Experiment with fan divisors > 8.
-* Experiment with temp. sensor types.
-* Are there really 13 voltage inputs? Probably not...
-* Cleanups, no doubt...
-
+  * Experiment with fan divisors > 8.
+  * Experiment with temp. sensor types.
+  * Are there really 13 voltage inputs? Probably not...
+  * Cleanups, no doubt...
diff --git a/Documentation/hwmon/asc7621 b/Documentation/hwmon/asc7621.rst
index 7287be7e1f21..b5a9fad0f172 100644
--- a/Documentation/hwmon/asc7621
+++ b/Documentation/hwmon/asc7621.rst
@@ -1,10 +1,15 @@
+=====================
 Kernel driver asc7621
-==================
+=====================
 
 Supported chips:
+
     Andigilog aSC7621 and aSC7621a
+
     Prefix: 'asc7621'
+
     Addresses scanned: I2C 0x2c, 0x2d, 0x2e
+
     Datasheet: http://www.fairview5.com/linux/asc7621/asc7621.pdf
 
 Author:
@@ -73,8 +78,10 @@ Finally, we have added a tach disable function that turns off the tach
 measurement system for individual tachs in order to save power. That is
 in register 75h.
 
---
+--------------------------------------------------------------------------
+
 aSC7621 Product Description
+===========================
 
 The aSC7621 has a two wire digital interface compatible with SMBus 2.0.
 Using a 10-bit ADC, the aSC7621 measures the temperature of two remote diode
@@ -102,6 +109,8 @@ System voltages of VCCP, 2.5V, 3.3V, 5.0V, and 12V motherboard power are
 monitored efficiently with internal scaling resistors.
 
 Features
+--------
+
 - Supports PECI interface and monitors internal and remote thermal diodes
 - 2-wire, SMBus 2.0 compliant, serial interface
 - 10-bit ADC
@@ -110,7 +119,7 @@ Features
 - Noise filtering of temperature reading for fan speed control
 - 0.25C digital temperature sensor resolution
 - 3 PWM fan speed control outputs for 2-, 3- or 4-wire fans and up to 4 fan
-	tachometer inputs
+  tachometer inputs
 - Enhanced measured temperature to Temperature Zone assignment.
 - Provides high and low PWM frequency ranges
 - 3 GPIO pins for custom use
@@ -123,17 +132,20 @@ Except where noted below, the sysfs entries created by this driver follow
 the standards defined in "sysfs-interface".
 
 temp1_source
+	=	===============================================
 	0 	(default) peci_legacy = 0, Remote 1 Temperature
-			peci_legacy = 1, PECI Processor Temperature 0
+		peci_legacy = 1, PECI Processor Temperature 0
 	1 	Remote 1 Temperature
 	2 	Remote 2 Temperature
 	3 	Internal Temperature
 	4 	PECI Processor Temperature 0
 	5 	PECI Processor Temperature 1
 	6 	PECI Processor Temperature 2
-	7  PECI Processor Temperature 3
+	7	PECI Processor Temperature 3
+	=	===============================================
 
 temp2_source
+	=	===============================================
 	0 	(default) Internal Temperature
 	1 	Remote 1 Temperature
 	2 	Remote 2 Temperature
@@ -142,8 +154,10 @@ temp2_source
 	5 	PECI Processor Temperature 1
 	6 	PECI Processor Temperature 2
 	7 	PECI Processor Temperature 3
+	=	===============================================
 
 temp3_source
+	=	===============================================
 	0 	(default) Remote 2 Temperature
 	1 	Remote 1 Temperature
 	2 	Remote 2 Temperature
@@ -152,10 +166,12 @@ temp3_source
 	5 	PECI Processor Temperature 1
 	6 	PECI Processor Temperature 2
 	7 	PECI Processor Temperature 3
+	=	===============================================
 
 temp4_source
+	=	===============================================
 	0 	(default) peci_legacy = 0, PECI Processor Temperature 0
-			peci_legacy = 1, Remote 1 Temperature
+		peci_legacy = 1, Remote 1 Temperature
 	1 	Remote 1 Temperature
 	2 	Remote 2 Temperature
 	3 	Internal Temperature
@@ -163,58 +179,65 @@ temp4_source
 	5 	PECI Processor Temperature 1
 	6 	PECI Processor Temperature 2
 	7 	PECI Processor Temperature 3
+	=	===============================================
 
-temp[1-4]_smoothing_enable
-temp[1-4]_smoothing_time
+temp[1-4]_smoothing_enable / temp[1-4]_smoothing_time
 	Smooths spikes in temp readings caused by noise.
 	Valid values in milliseconds are:
-	35000
-	17600
-	11800
-	 7000
-	 4400
-	 3000
-	 1600
-	  800
+
+	* 35000
+	* 17600
+	* 11800
+	*  7000
+	*  4400
+	*  3000
+	*  1600
+	*   800
 
 temp[1-4]_crit
 	When the corresponding zone temperature reaches this value,
 	ALL pwm outputs will got to 100%.
 
-temp[5-8]_input
-temp[5-8]_enable
+temp[5-8]_input / temp[5-8]_enable
 	The aSC7621 can also read temperatures provided by the processor
 	via the PECI bus.  Usually these are "core" temps and are relative
 	to the point where the automatic thermal control circuit starts
 	throttling.  This means that these are usually negative numbers.
 
 pwm[1-3]_enable
+	=============== ========================================================
 	0		Fan off.
 	1		Fan on manual control.
 	2		Fan on automatic control and will run at the minimum pwm
-				if the temperature for the zone is below the minimum.
-	3		Fan on automatic control but will be off if the temperature
-				for the zone is below the minimum.
-	4-254	Ignored.
+			if the temperature for the zone is below the minimum.
+	3		Fan on automatic control but will be off if the
+			temperature for the zone is below the minimum.
+	4-254		Ignored.
 	255		Fan on full.
+	=============== ========================================================
 
 pwm[1-3]_auto_channels
 	Bitmap as described in sysctl-interface with the following
 	exceptions...
+
 	Only the following combination of zones (and their corresponding masks)
 	are valid:
-	1
-	2
-	3
-	2,3
-	1,2,3
-	4
-	1,2,3,4
 
-	Special values:
-	0			Disabled.
-	16		Fan on manual control.
-	31		Fan on full.
+	* 1
+	* 2
+	* 3
+	* 2,3
+	* 1,2,3
+	* 4
+	* 1,2,3,4
+
+	* Special values:
+
+	  ==		======================
+	  0		Disabled.
+	  16		Fan on manual control.
+	  31		Fan on full.
+	  ==		======================
 
 
 pwm[1-3]_invert
@@ -226,22 +249,22 @@ pwm[1-3]_freq
 	PWM frequency in Hz
 	Valid values in Hz are:
 
-	10
-	15
-	23
-	30  (default)
-	38
-	47
-	62
-	94
-	23000
-	24000
-	25000
-	26000
-	27000
-	28000
-	29000
-	30000
+	* 10
+	* 15
+	* 23
+	* 30  (default)
+	* 38
+	* 47
+	* 62
+	* 94
+	* 23000
+	* 24000
+	* 25000
+	* 26000
+	* 27000
+	* 28000
+	* 29000
+	* 30000
 
 	Setting any other value will be ignored.
 
@@ -251,17 +274,17 @@ peci_enable
 peci_avg
 	Input filter average time.
 
-	0 	0 Sec. (no Smoothing) (default)
-	1 	0.25 Sec.
-	2 	0.5 Sec.
-	3 	1.0 Sec.
-	4 	2.0 Sec.
-	5 	4.0 Sec.
-	6 	8.0 Sec.
-	7 	0.0 Sec.
+	* 0 	0 Sec. (no Smoothing) (default)
+	* 1 	0.25 Sec.
+	* 2 	0.5 Sec.
+	* 3 	1.0 Sec.
+	* 4 	2.0 Sec.
+	* 5 	4.0 Sec.
+	* 6 	8.0 Sec.
+	* 7 	0.0 Sec.
 
 peci_legacy
-
+	=	============================================
 	0	Standard Mode (default)
 		Remote Diode 1 reading is associated with
 		Temperature Zone 1, PECI is associated with
@@ -270,10 +293,12 @@ peci_legacy
 	1	Legacy Mode
 		PECI is associated with Temperature Zone 1,
 		Remote Diode 1 is associated with Zone 4
+	=	============================================
 
 peci_diode
 	Diode filter
 
+	=	====================
 	0	0.25 Sec.
 	1 	1.1 Sec.
 	2 	2.4 Sec.  (default)
@@ -282,15 +307,20 @@ peci_diode
 	5 	6.8 Sec.
 	6 	10.2 Sec.
 	7 	16.4 Sec.
+	=	====================
 
 peci_4domain
 	Four domain enable
 
+	=	===============================================
 	0 	1 or 2 Domains for enabled processors (default)
 	1 	3 or 4 Domains for enabled processors
+	=	===============================================
 
 peci_domain
 	Domain
 
+	=	==================================================
 	0 	Processor contains a single domain (0) 	 (default)
 	1 	Processor contains two domains (0,1)
+	=	==================================================
diff --git a/Documentation/hwmon/aspeed-pwm-tacho b/Documentation/hwmon/aspeed-pwm-tacho.rst
index 7cfb34977460..6dcec845fbc7 100644
--- a/Documentation/hwmon/aspeed-pwm-tacho
+++ b/Documentation/hwmon/aspeed-pwm-tacho.rst
@@ -15,8 +15,10 @@ controller supports up to 16 tachometer inputs.
 
 The driver provides the following sensor accesses in sysfs:
 
+=============== ======= =====================================================
 fanX_input	ro	provide current fan rotation value in RPM as reported
 			by the fan to the device.
 
 pwmX		rw	get or set PWM fan control value. This is an integer
 			value between 0(off) and 255(full speed).
+=============== ======= =====================================================
diff --git a/Documentation/hwmon/coretemp b/Documentation/hwmon/coretemp.rst
index fec5a9bf755f..c609329e3bc4 100644
--- a/Documentation/hwmon/coretemp
+++ b/Documentation/hwmon/coretemp.rst
@@ -3,20 +3,29 @@ Kernel driver coretemp
 
 Supported chips:
   * All Intel Core family
+
     Prefix: 'coretemp'
-    CPUID: family 0x6, models 0xe (Pentium M DC), 0xf (Core 2 DC 65nm),
-                              0x16 (Core 2 SC 65nm), 0x17 (Penryn 45nm),
-                              0x1a (Nehalem), 0x1c (Atom), 0x1e (Lynnfield),
-                              0x26 (Tunnel Creek Atom), 0x27 (Medfield Atom),
-                              0x36 (Cedar Trail Atom)
-    Datasheet: Intel 64 and IA-32 Architectures Software Developer's Manual
-               Volume 3A: System Programming Guide
-               http://softwarecommunity.intel.com/Wiki/Mobility/720.htm
+
+    CPUID: family 0x6, models
+
+			    - 0xe (Pentium M DC), 0xf (Core 2 DC 65nm),
+			    - 0x16 (Core 2 SC 65nm), 0x17 (Penryn 45nm),
+			    - 0x1a (Nehalem), 0x1c (Atom), 0x1e (Lynnfield),
+			    - 0x26 (Tunnel Creek Atom), 0x27 (Medfield Atom),
+			    - 0x36 (Cedar Trail Atom)
+
+    Datasheet:
+
+	       Intel 64 and IA-32 Architectures Software Developer's Manual
+	       Volume 3A: System Programming Guide
+
+	       http://softwarecommunity.intel.com/Wiki/Mobility/720.htm
 
 Author: Rudolf Marek
 
 Description
 -----------
+
 This driver permits reading the DTS (Digital Temperature Sensor) embedded
 inside Intel CPUs. This driver can read both the per-core and per-package
 temperature using the appropriate sensors. The per-package sensor is new;
@@ -35,14 +44,17 @@ may be raised, if the temperature grows enough (more than TjMax) to trigger
 the Out-Of-Spec bit. Following table summarizes the exported sysfs files:
 
 All Sysfs entries are named with their core_id (represented here by 'X').
-tempX_input	 - Core temperature (in millidegrees Celsius).
-tempX_max	 - All cooling devices should be turned on (on Core2).
-tempX_crit	 - Maximum junction temperature (in millidegrees Celsius).
-tempX_crit_alarm - Set when Out-of-spec bit is set, never clears.
-		   Correct CPU operation is no longer guaranteed.
-tempX_label	 - Contains string "Core X", where X is processor
-		   number. For Package temp, this will be "Physical id Y",
-		   where Y is the package number.
+
+================= ========================================================
+tempX_input	  Core temperature (in millidegrees Celsius).
+tempX_max	  All cooling devices should be turned on (on Core2).
+tempX_crit	  Maximum junction temperature (in millidegrees Celsius).
+tempX_crit_alarm  Set when Out-of-spec bit is set, never clears.
+		  Correct CPU operation is no longer guaranteed.
+tempX_label	  Contains string "Core X", where X is processor
+		  number. For Package temp, this will be "Physical id Y",
+		  where Y is the package number.
+================= ========================================================
 
 On CPU models which support it, TjMax is read from a model-specific register.
 On other models, it is set to an arbitrary value based on weak heuristics.
@@ -52,6 +64,7 @@ as a module parameter (tjmax).
 Appendix A. Known TjMax lists (TBD):
 Some information comes from ark.intel.com
 
+=============== =============================================== ================
 Process		Processor					TjMax(C)
 
 22nm		Core i5/i7 Processors
@@ -179,3 +192,4 @@ Process		Processor					TjMax(C)
 65nm		Celeron Processors
 		T1700/1600					100
 		560/550/540/530					100
+=============== =============================================== ================
diff --git a/Documentation/hwmon/da9052 b/Documentation/hwmon/da9052.rst
index 5bc51346b689..c1c0f1f08904 100644
--- a/Documentation/hwmon/da9052
+++ b/Documentation/hwmon/da9052.rst
@@ -1,6 +1,12 @@
+Kernel driver da9052
+====================
+
 Supported chips:
+
   * Dialog Semiconductors DA9052-BC and DA9053-AA/Bx PMICs
+
     Prefix: 'da9052'
+
     Datasheet: Datasheet is not publicly available.
 
 Authors: David Dajun Chen <dchen@diasemi.com>
@@ -15,17 +21,20 @@ different inputs. The track and hold circuit ensures stable input voltages at
 the input of the ADC during the conversion.
 
 The ADC is used to measure the following inputs:
-Channel 0: VDDOUT - measurement of the system voltage
-Channel 1: ICH - internal battery charger current measurement
-Channel 2: TBAT - output from the battery NTC
-Channel 3: VBAT - measurement of the battery voltage
-Channel 4: ADC_IN4 - high impedance input (0 - 2.5V)
-Channel 5: ADC_IN5 - high impedance input (0 - 2.5V)
-Channel 6: ADC_IN6 - high impedance input (0 - 2.5V)
-Channel 7: XY - TSI interface to measure the X and Y voltage of the touch
-	   screen resistive potentiometers
-Channel 8: Internal Tjunc. - sense (internal temp. sensor)
-Channel 9: VBBAT - measurement of the backup battery voltage
+
+========= ===================================================================
+Channel 0 VDDOUT - measurement of the system voltage
+Channel 1 ICH - internal battery charger current measurement
+Channel 2 TBAT - output from the battery NTC
+Channel 3 VBAT - measurement of the battery voltage
+Channel 4 ADC_IN4 - high impedance input (0 - 2.5V)
+Channel 5 ADC_IN5 - high impedance input (0 - 2.5V)
+Channel 6 ADC_IN6 - high impedance input (0 - 2.5V)
+Channel 7 XY - TSI interface to measure the X and Y voltage of the touch
+	  screen resistive potentiometers
+Channel 8 Internal Tjunc. - sense (internal temp. sensor)
+Channel 9 VBBAT - measurement of the backup battery voltage
+========= ===================================================================
 
 By using sysfs attributes we can measure the system voltage VDDOUT, the battery
 charging current ICH, battery temperature TBAT, battery junction temperature
@@ -37,12 +46,15 @@ Voltage Monitoring
 Voltages are sampled by a 10 bit ADC.
 
 The battery voltage is calculated as:
+
 	Milli volt = ((ADC value * 1000) / 512) + 2500
 
 The backup battery voltage is calculated as:
+
 	Milli volt = (ADC value * 2500) / 512;
 
 The voltages on ADC channels 4, 5 and 6 are calculated as:
+
 	Milli volt = (ADC value * 2500) / 1023
 
 Temperature Monitoring
@@ -52,10 +64,15 @@ Temperatures are sampled by a 10 bit ADC.  Junction and battery temperatures
 are monitored by the ADC channels.
 
 The junction temperature is calculated:
+
 	Degrees celsius = 1.708 * (TJUNC_RES - T_OFFSET) - 108.8
+
 The junction temperature attribute is supported by the driver.
 
 The battery temperature is calculated:
-	Degree Celsius = 1 / (t1 + 1/298)- 273
+
+	Degree Celsius = 1 / (t1 + 1/298) - 273
+
 where t1 = (1/B)* ln(( ADCval * 2.5)/(R25*ITBAT*255))
+
 Default values of R25, B, ITBAT are 10e3, 3380 and 50e-6 respectively.
diff --git a/Documentation/hwmon/da9055 b/Documentation/hwmon/da9055.rst
index 855c3f536e00..beae271a3312 100644
--- a/Documentation/hwmon/da9055
+++ b/Documentation/hwmon/da9055.rst
@@ -1,6 +1,11 @@
+Kernel driver da9055
+====================
+
 Supported chips:
   * Dialog Semiconductors DA9055 PMIC
+
     Prefix: 'da9055'
+
     Datasheet: Datasheet is not publicly available.
 
 Authors: David Dajun Chen <dchen@diasemi.com>
@@ -15,11 +20,12 @@ different inputs. The track and hold circuit ensures stable input voltages at
 the input of the ADC during the conversion.
 
 The ADC is used to measure the following inputs:
-Channel 0: VDDOUT - measurement of the system voltage
-Channel 1: ADC_IN1 - high impedance input (0 - 2.5V)
-Channel 2: ADC_IN2 - high impedance input (0 - 2.5V)
-Channel 3: ADC_IN3 - high impedance input (0 - 2.5V)
-Channel 4: Internal Tjunc. - sense (internal temp. sensor)
+
+- Channel 0: VDDOUT - measurement of the system voltage
+- Channel 1: ADC_IN1 - high impedance input (0 - 2.5V)
+- Channel 2: ADC_IN2 - high impedance input (0 - 2.5V)
+- Channel 3: ADC_IN3 - high impedance input (0 - 2.5V)
+- Channel 4: Internal Tjunc. - sense (internal temp. sensor)
 
 By using sysfs attributes we can measure the system voltage VDDOUT,
 chip junction temperature and auxiliary channels voltages.
@@ -31,9 +37,11 @@ Voltages are sampled in a AUTO mode it can be manually sampled too and results
 are stored in a 10 bit ADC.
 
 The system voltage is calculated as:
+
 	Milli volt = ((ADC value * 1000) / 85) + 2500
 
 The voltages on ADC channels 1, 2 and 3 are calculated as:
+
 	Milli volt = (ADC value * 1000) / 102
 
 Temperature Monitoring
@@ -43,5 +51,7 @@ Temperatures are sampled by a 10 bit ADC.  Junction temperatures
 are monitored by the ADC channels.
 
 The junction temperature is calculated:
+
 	Degrees celsius = -0.4084 * (ADC_RES - T_OFFSET) + 307.6332
+
 The junction temperature attribute is supported by the driver.
diff --git a/Documentation/hwmon/dme1737 b/Documentation/hwmon/dme1737.rst
index 4d2935145a1c..82fcbc6b2b43 100644
--- a/Documentation/hwmon/dme1737
+++ b/Documentation/hwmon/dme1737.rst
@@ -2,21 +2,37 @@ Kernel driver dme1737
 =====================
 
 Supported chips:
+
   * SMSC DME1737 and compatibles (like Asus A8000)
+
     Prefix: 'dme1737'
+
     Addresses scanned: I2C 0x2c, 0x2d, 0x2e
+
     Datasheet: Provided by SMSC upon request and under NDA
+
   * SMSC SCH3112, SCH3114, SCH3116
+
     Prefix: 'sch311x'
+
     Addresses scanned: none, address read from Super-I/O config space
+
     Datasheet: Available on the Internet
+
   * SMSC SCH5027
+
     Prefix: 'sch5027'
+
     Addresses scanned: I2C 0x2c, 0x2d, 0x2e
+
     Datasheet: Provided by SMSC upon request and under NDA
+
   * SMSC SCH5127
+
     Prefix: 'sch5127'
+
     Addresses scanned: none, address read from Super-I/O config space
+
     Datasheet: Provided by SMSC upon request and under NDA
 
 Authors:
@@ -26,11 +42,14 @@ Authors:
 Module Parameters
 -----------------
 
-* force_start: bool	Enables the monitoring of voltage, fan and temp inputs
+* force_start: bool
+			Enables the monitoring of voltage, fan and temp inputs
 			and PWM output control functions. Using this parameter
 			shouldn't be required since the BIOS usually takes care
 			of this.
-* probe_all_addr: bool	Include non-standard LPC addresses 0x162e and 0x164e
+
+* probe_all_addr: bool
+			Include non-standard LPC addresses 0x162e and 0x164e
 			when probing for ISA devices. This is required for the
 			following boards:
 			- VIA EPIA SN18000
@@ -70,7 +89,8 @@ scaling resistors. The values returned by the driver therefore reflect true
 millivolts and don't need scaling. The voltage inputs are mapped as follows
 (the last column indicates the input ranges):
 
-DME1737, A8000:
+DME1737, A8000::
+
 	in0: +5VTR	(+5V standby)		0V - 6.64V
 	in1: Vccp	(processor core)	0V - 3V
 	in2: VCC	(internal +3.3V)	0V - 4.38V
@@ -79,7 +99,8 @@ DME1737, A8000:
 	in5: VTR	(+3.3V standby)		0V - 4.38V
 	in6: Vbat	(+3.0V)			0V - 4.38V
 
-SCH311x:
+SCH311x::
+
 	in0: +2.5V				0V - 3.32V
 	in1: Vccp	(processor core)	0V - 2V
 	in2: VCC	(internal +3.3V)	0V - 4.38V
@@ -88,7 +109,8 @@ SCH311x:
 	in5: VTR	(+3.3V standby)		0V - 4.38V
 	in6: Vbat	(+3.0V)			0V - 4.38V
 
-SCH5027:
+SCH5027::
+
 	in0: +5VTR	(+5V standby)		0V - 6.64V
 	in1: Vccp	(processor core)	0V - 3V
 	in2: VCC	(internal +3.3V)	0V - 4.38V
@@ -97,7 +119,8 @@ SCH5027:
 	in5: VTR	(+3.3V standby)		0V - 4.38V
 	in6: Vbat	(+3.0V)			0V - 4.38V
 
-SCH5127:
+SCH5127::
+
 	in0: +2.5				0V - 3.32V
 	in1: Vccp	(processor core)	0V - 3V
 	in2: VCC	(internal +3.3V)	0V - 4.38V
@@ -119,7 +142,7 @@ Celsius. The chip also features offsets for all 3 temperature inputs which -
 when programmed - get added to the input readings. The chip does all the
 scaling by itself and the driver therefore reports true temperatures that don't
 need any user-space adjustments. The temperature inputs are mapped as follows
-(the last column indicates the input ranges):
+(the last column indicates the input ranges)::
 
 	temp1: Remote diode 1 (3904 type) temperature	-127C - +127C
 	temp2: DME1737 internal temperature		-127C - +127C
@@ -171,6 +194,7 @@ pwm[1-3]_auto_pwm_min, respectively. The thermal thresholds of the zones are
 programmed via zone[1-3]_auto_point[1-3]_temp and
 zone[1-3]_auto_point1_temp_hyst:
 
+	=============================== =======================================
 	pwm[1-3]_auto_point2_pwm	full-speed duty-cycle (255, i.e., 100%)
 	pwm[1-3]_auto_point1_pwm	low-speed duty-cycle
 	pwm[1-3]_auto_pwm_min		min-speed duty-cycle
@@ -179,6 +203,7 @@ zone[1-3]_auto_point1_temp_hyst:
 	zone[1-3]_auto_point2_temp	full-speed temp
 	zone[1-3]_auto_point1_temp	low-speed temp
 	zone[1-3]_auto_point1_temp_hyst	min-speed temp
+	=============================== =======================================
 
 The chip adjusts the output duty-cycle linearly in the range of auto_point1_pwm
 to auto_point2_pwm if the temperature of the associated zone is between
@@ -192,17 +217,21 @@ all PWM outputs are set to 100% duty-cycle.
 Following is another representation of how the chip sets the output duty-cycle
 based on the temperature of the associated thermal zone:
 
-			Duty-Cycle	Duty-Cycle
-	Temperature	Rising Temp	Falling Temp
-	-----------	-----------	------------
+	=============== =============== =================
+	Temperature	Duty-Cycle	Duty-Cycle
+			Rising Temp	Falling Temp
+	=============== =============== =================
 	full-speed	full-speed	full-speed
 
-			< linearly adjusted duty-cycle >
+	-		< linearly	-
+			adjusted
+			duty-cycle >
 
 	low-speed	low-speed	low-speed
-			min-speed	low-speed
+	-		min-speed	low-speed
 	min-speed	min-speed	min-speed
-			min-speed	min-speed
+	-		min-speed	min-speed
+	=============== =============== =================
 
 
 Sysfs Attributes
@@ -211,8 +240,9 @@ Sysfs Attributes
 Following is a list of all sysfs attributes that the driver provides, their
 permissions and a short description:
 
+=============================== ======= =======================================
 Name				Perm	Description
-----				----	-----------
+=============================== ======= =======================================
 cpu0_vid			RO	CPU core reference voltage in
 					millivolts.
 vrm				RW	Voltage regulator module version
@@ -242,9 +272,10 @@ temp[1-3]_fault			RO	Temp input fault. Returns 1 if the chip
 zone[1-3]_auto_channels_temp	RO	Temperature zone to temperature input
 					mapping. This attribute is a bitfield
 					and supports the following values:
-						1: temp1
-						2: temp2
-						4: temp3
+
+						- 1: temp1
+						- 2: temp2
+						- 4: temp3
 zone[1-3]_auto_point1_temp_hyst	RW	Auto PWM temp point1 hysteresis. The
 					output of the corresponding PWM is set
 					to the pwm_auto_min value if the temp
@@ -275,9 +306,10 @@ pmw[1-3,5-6]			RO/RW	Duty-cycle of PWM output. Supported
 					manual mode.
 pwm[1-3]_enable			RW	Enable of PWM outputs 1-3. Supported
 					values are:
-						 0: turned off (output @ 100%)
-						 1: manual mode
-						 2: automatic mode
+
+						- 0: turned off (output @ 100%)
+						- 1: manual mode
+						- 2: automatic mode
 pwm[5-6]_enable			RO	Enable of PWM outputs 5-6. Always
 					returns 1 since these 2 outputs are
 					hard-wired to manual mode.
@@ -294,11 +326,12 @@ pmw[1-3]_ramp_rate		RW	Ramp rate of PWM output. Determines how
 pwm[1-3]_auto_channels_zone	RW	PWM output to temperature zone mapping.
 					This attribute is a bitfield and
 					supports the following values:
-						1: zone1
-						2: zone2
-						4: zone3
-						6: highest of zone[2-3]
-						7: highest of zone[1-3]
+
+						- 1: zone1
+						- 2: zone2
+						- 4: zone3
+						- 6: highest of zone[2-3]
+						- 7: highest of zone[1-3]
 pwm[1-3]_auto_pwm_min		RW	Auto PWM min pwm. Minimum PWM duty-
 					cycle. Supported values are 0 or
 					auto_point1_pwm.
@@ -307,12 +340,14 @@ pwm[1-3]_auto_point1_pwm	RW	Auto PWM pwm point. Auto_point1 is the
 pwm[1-3]_auto_point2_pwm	RO	Auto PWM pwm point. Auto_point2 is the
 					full-speed duty-cycle which is hard-
 					wired to 255 (100% duty-cycle).
+=============================== ======= =======================================
 
 Chip Differences
 ----------------
 
+======================= ======= ======= ======= =======
 Feature			dme1737	sch311x	sch5027	sch5127
--------------------------------------------------------
+======================= ======= ======= ======= =======
 temp[1-3]_offset	yes	yes
 vid			yes
 zone3			yes	yes	yes
@@ -326,3 +361,4 @@ pwm5			opt		opt
 fan6			opt		opt
 pwm6			opt		opt
 in7						yes
+======================= ======= ======= ======= =======
diff --git a/Documentation/hwmon/ds1621 b/Documentation/hwmon/ds1621.rst
index fa3407997795..552b37e9dd34 100644
--- a/Documentation/hwmon/ds1621
+++ b/Documentation/hwmon/ds1621.rst
@@ -2,42 +2,61 @@ Kernel driver ds1621
 ====================
 
 Supported chips:
+
   * Dallas Semiconductor / Maxim Integrated DS1621
+
     Prefix: 'ds1621'
+
     Addresses scanned: none
+
     Datasheet: Publicly available from www.maximintegrated.com
 
   * Dallas Semiconductor DS1625
+
     Prefix: 'ds1625'
+
     Addresses scanned: none
+
     Datasheet: Publicly available from www.datasheetarchive.com
 
   * Maxim Integrated DS1631
+
     Prefix: 'ds1631'
+
     Addresses scanned: none
+
     Datasheet: Publicly available from www.maximintegrated.com
 
   * Maxim Integrated DS1721
+
     Prefix: 'ds1721'
+
     Addresses scanned: none
+
     Datasheet: Publicly available from www.maximintegrated.com
 
   * Maxim Integrated DS1731
+
     Prefix: 'ds1731'
+
     Addresses scanned: none
+
     Datasheet: Publicly available from www.maximintegrated.com
 
 Authors:
-        Christian W. Zuckschwerdt <zany@triq.net>
-        valuable contributions by Jan M. Sendler <sendler@sendler.de>
-        ported to 2.6 by Aurelien Jarno <aurelien@aurel32.net>
-        with the help of Jean Delvare <jdelvare@suse.de>
+      - Christian W. Zuckschwerdt <zany@triq.net>
+      - valuable contributions by Jan M. Sendler <sendler@sendler.de>
+      - ported to 2.6 by Aurelien Jarno <aurelien@aurel32.net>
+	with the help of Jean Delvare <jdelvare@suse.de>
 
 Module Parameters
 ------------------
 
 * polarity int
-  Output's polarity: 0 = active high, 1 = active low
+  Output's polarity:
+
+  * 0 = active high,
+  * 1 = active low
 
 Description
 -----------
@@ -87,28 +106,31 @@ are used internally, however, these flags do get set and cleared as the actual
 temperature crosses the min or max settings (which by default are set to 75
 and 80 degrees respectively).
 
-Temperature Conversion:
------------------------
-DS1621 - 750ms (older devices may take up to 1000ms)
-DS1625 - 500ms
-DS1631 - 93ms..750ms for 9..12 bits resolution, respectively.
-DS1721 - 93ms..750ms for 9..12 bits resolution, respectively.
-DS1731 - 93ms..750ms for 9..12 bits resolution, respectively.
+Temperature Conversion
+----------------------
+
+- DS1621 - 750ms (older devices may take up to 1000ms)
+- DS1625 - 500ms
+- DS1631 - 93ms..750ms for 9..12 bits resolution, respectively.
+- DS1721 - 93ms..750ms for 9..12 bits resolution, respectively.
+- DS1731 - 93ms..750ms for 9..12 bits resolution, respectively.
 
 Note:
 On the DS1621, internal access to non-volatile registers may last for 10ms
 or less (unverified on the other devices).
 
-Temperature Accuracy:
----------------------
-DS1621: +/- 0.5 degree Celsius (from 0 to +70 degrees)
-DS1625: +/- 0.5 degree Celsius (from 0 to +70 degrees)
-DS1631: +/- 0.5 degree Celsius (from 0 to +70 degrees)
-DS1721: +/- 1.0 degree Celsius (from -10 to +85 degrees)
-DS1731: +/- 1.0 degree Celsius (from -10 to +85 degrees)
+Temperature Accuracy
+--------------------
 
-Note:
-Please refer to the device datasheets for accuracy at other temperatures.
+- DS1621: +/- 0.5 degree Celsius (from 0 to +70 degrees)
+- DS1625: +/- 0.5 degree Celsius (from 0 to +70 degrees)
+- DS1631: +/- 0.5 degree Celsius (from 0 to +70 degrees)
+- DS1721: +/- 1.0 degree Celsius (from -10 to +85 degrees)
+- DS1731: +/- 1.0 degree Celsius (from -10 to +85 degrees)
+
+.. Note::
+
+   Please refer to the device datasheets for accuracy at other temperatures.
 
 Temperature Resolution:
 -----------------------
@@ -117,60 +139,67 @@ support, which is achieved via the R0 and R1 config register bits, where:
 
 R0..R1
 ------
- 0  0 => 9 bits, 0.5 degrees Celsius
- 1  0 => 10 bits, 0.25 degrees Celsius
- 0  1 => 11 bits, 0.125 degrees Celsius
- 1  1 => 12 bits, 0.0625 degrees Celsius
 
-Note:
-At initial device power-on, the default resolution is set to 12-bits.
+== ==  ===============================
+R0 R1
+== ==  ===============================
+ 0  0  9 bits, 0.5 degrees Celsius
+ 1  0  10 bits, 0.25 degrees Celsius
+ 0  1  11 bits, 0.125 degrees Celsius
+ 1  1  12 bits, 0.0625 degrees Celsius
+== ==  ===============================
+
+.. Note::
+
+   At initial device power-on, the default resolution is set to 12-bits.
 
 The resolution mode for the DS1631, DS1721, or DS1731 can be changed from
 userspace, via the device 'update_interval' sysfs attribute. This attribute
 will normalize the range of input values to the device maximum resolution
 values defined in the datasheet as follows:
 
+============= ================== ===============
 Resolution    Conversion Time    Input Range
  (C/LSB)       (msec)             (msec)
-------------------------------------------------
+============= ================== ===============
 0.5             93.75              0....94
 0.25            187.5              95...187
 0.125           375                188..375
 0.0625          750                376..infinity
-------------------------------------------------
+============= ================== ===============
 
 The following examples show how the 'update_interval' attribute can be
-used to change the conversion time:
-
-$ cat update_interval
-750
-$ cat temp1_input
-22062
-$
-$ echo 300 > update_interval
-$ cat update_interval
-375
-$ cat temp1_input
-22125
-$
-$ echo 150 > update_interval
-$ cat update_interval
-188
-$ cat temp1_input
-22250
-$
-$ echo 1 > update_interval
-$ cat update_interval
-94
-$ cat temp1_input
-22000
-$
-$ echo 1000 > update_interval
-$ cat update_interval
-750
-$ cat temp1_input
-22062
-$
+used to change the conversion time::
+
+  $ cat update_interval
+  750
+  $ cat temp1_input
+  22062
+  $
+  $ echo 300 > update_interval
+  $ cat update_interval
+  375
+  $ cat temp1_input
+  22125
+  $
+  $ echo 150 > update_interval
+  $ cat update_interval
+  188
+  $ cat temp1_input
+  22250
+  $
+  $ echo 1 > update_interval
+  $ cat update_interval
+  94
+  $ cat temp1_input
+  22000
+  $
+  $ echo 1000 > update_interval
+  $ cat update_interval
+  750
+  $ cat temp1_input
+  22062
+  $
 
 As shown, the ds1621 driver automatically adjusts the 'update_interval'
 user input, via a step function. Reading back the 'update_interval' value
@@ -182,6 +211,7 @@ via the following function:
    g(x) = 0.5 * [minimum_conversion_time/x]
 
 where:
- -> 'x' = the output from 'update_interval'
- -> 'g(x)' = the resolution in degrees C per LSB.
- -> 93.75ms = minimum conversion time
+
+ - 'x' = the output from 'update_interval'
+ - 'g(x)' = the resolution in degrees C per LSB.
+ - 93.75ms = minimum conversion time
diff --git a/Documentation/hwmon/ds620 b/Documentation/hwmon/ds620.rst
index 1fbe3cd916cc..2d686b17b547 100644
--- a/Documentation/hwmon/ds620
+++ b/Documentation/hwmon/ds620.rst
@@ -2,15 +2,19 @@ Kernel driver ds620
 ===================
 
 Supported chips:
+
   * Dallas Semiconductor DS620
+
     Prefix: 'ds620'
+
     Datasheet: Publicly available at the Dallas Semiconductor website
-               http://www.dalsemi.com/
+
+	       http://www.dalsemi.com/
 
 Authors:
-        Roland Stigge <stigge@antcom.de>
-        based on ds1621.c by
-        Christian W. Zuckschwerdt <zany@triq.net>
+	Roland Stigge <stigge@antcom.de>
+	based on ds1621.c by
+	Christian W. Zuckschwerdt <zany@triq.net>
 
 Description
 -----------
diff --git a/Documentation/hwmon/emc1403 b/Documentation/hwmon/emc1403.rst
index a869b0ef6a9d..3a4913b63ef3 100644
--- a/Documentation/hwmon/emc1403
+++ b/Documentation/hwmon/emc1403.rst
@@ -2,28 +2,48 @@ Kernel driver emc1403
 =====================
 
 Supported chips:
+
   * SMSC / Microchip EMC1402, EMC1412
+
     Addresses scanned: I2C 0x18, 0x1c, 0x29, 0x4c, 0x4d, 0x5c
+
     Prefix: 'emc1402'
+
     Datasheets:
-	http://ww1.microchip.com/downloads/en/DeviceDoc/1412.pdf
-	http://ww1.microchip.com/downloads/en/DeviceDoc/1402.pdf
+
+	- http://ww1.microchip.com/downloads/en/DeviceDoc/1412.pdf
+	- http://ww1.microchip.com/downloads/en/DeviceDoc/1402.pdf
+
   * SMSC / Microchip EMC1403, EMC1404, EMC1413, EMC1414
+
     Addresses scanned: I2C 0x18, 0x29, 0x4c, 0x4d
+
     Prefix: 'emc1403', 'emc1404'
+
     Datasheets:
-	http://ww1.microchip.com/downloads/en/DeviceDoc/1403_1404.pdf
-	http://ww1.microchip.com/downloads/en/DeviceDoc/1413_1414.pdf
+
+	- http://ww1.microchip.com/downloads/en/DeviceDoc/1403_1404.pdf
+	- http://ww1.microchip.com/downloads/en/DeviceDoc/1413_1414.pdf
+
   * SMSC / Microchip EMC1422
+
     Addresses scanned: I2C 0x4c
+
     Prefix: 'emc1422'
+
     Datasheet:
-	http://ww1.microchip.com/downloads/en/DeviceDoc/1422.pdf
+
+	- http://ww1.microchip.com/downloads/en/DeviceDoc/1422.pdf
+
   * SMSC / Microchip EMC1423, EMC1424
+
     Addresses scanned: I2C 0x4c
+
     Prefix: 'emc1423', 'emc1424'
+
     Datasheet:
-	http://ww1.microchip.com/downloads/en/DeviceDoc/1423_1424.pdf
+
+	- http://ww1.microchip.com/downloads/en/DeviceDoc/1423_1424.pdf
 
 Author:
     Kalhan Trisal <kalhan.trisal@intel.com
@@ -46,6 +66,7 @@ difference between the limit and its hysteresis is always the same for
 all three limits.
 
 This implementation detail implies the following:
+
 * When setting a limit, its hysteresis will automatically follow, the
   difference staying unchanged. For example, if the old critical limit
   was 80 degrees C, and the hysteresis was 75 degrees C, and you change
diff --git a/Documentation/hwmon/emc2103 b/Documentation/hwmon/emc2103.rst
index a12b2c127140..6a6ca6d1b34e 100644
--- a/Documentation/hwmon/emc2103
+++ b/Documentation/hwmon/emc2103.rst
@@ -2,13 +2,17 @@ Kernel driver emc2103
 ======================
 
 Supported chips:
+
   * SMSC EMC2103
+
     Addresses scanned: I2C 0x2e
+
     Prefix: 'emc2103'
+
     Datasheet: Not public
 
 Authors:
-        Steve Glendinning <steve.glendinning@smsc.com>
+	Steve Glendinning <steve.glendinning@smsc.com>
 
 Description
 -----------
diff --git a/Documentation/hwmon/emc6w201 b/Documentation/hwmon/emc6w201.rst
index 757629b12897..a8e1185b9bb6 100644
--- a/Documentation/hwmon/emc6w201
+++ b/Documentation/hwmon/emc6w201.rst
@@ -2,9 +2,13 @@ Kernel driver emc6w201
 ======================
 
 Supported chips:
+
   * SMSC EMC6W201
+
     Prefix: 'emc6w201'
+
     Addresses scanned: I2C 0x2c, 0x2d, 0x2e
+
     Datasheet: Not public
 
 Author: Jean Delvare <jdelvare@suse.de>
@@ -38,5 +42,6 @@ Known Systems With EMC6W201
 
 The EMC6W201 is a rare device, only found on a few systems, made in
 2005 and 2006. Known systems with this device:
+
 * Dell Precision 670 workstation
 * Gigabyte 2CEWH mainboard
diff --git a/Documentation/hwmon/f71805f b/Documentation/hwmon/f71805f.rst
index 48a356084bc6..1efe5e5d337c 100644
--- a/Documentation/hwmon/f71805f
+++ b/Documentation/hwmon/f71805f.rst
@@ -2,17 +2,29 @@ Kernel driver f71805f
 =====================
 
 Supported chips:
+
   * Fintek F71805F/FG
+
     Prefix: 'f71805f'
+
     Addresses scanned: none, address read from Super I/O config space
+
     Datasheet: Available from the Fintek website
+
   * Fintek F71806F/FG
+
     Prefix: 'f71872f'
+
     Addresses scanned: none, address read from Super I/O config space
+
     Datasheet: Available from the Fintek website
+
   * Fintek F71872F/FG
+
     Prefix: 'f71872f'
+
     Addresses scanned: none, address read from Super I/O config space
+
     Datasheet: Available from the Fintek website
 
 Author: Jean Delvare <jdelvare@suse.de>
@@ -64,24 +76,26 @@ you can only set the limits in steps of 32 mV (before scaling).
 
 The wirings and resistor values suggested by Fintek are as follow:
 
-        pin                                           expected
-        name    use           R1      R2     divider  raw val.
-
+======= ======= =========== ==== ======= ============ ==============
+in      pin                                           expected
+	name    use           R1      R2     divider  raw val.
+======= ======= =========== ==== ======= ============ ==============
 in0     VCC     VCC3.3V     int.    int.        2.00    1.65 V
 in1     VIN1    VTT1.2V      10K       -        1.00    1.20 V
-in2     VIN2    VRAM        100K    100K        2.00   ~1.25 V (1)
-in3     VIN3    VCHIPSET     47K    100K        1.47    2.24 V (2)
+in2     VIN2    VRAM        100K    100K        2.00   ~1.25 V [1]_
+in3     VIN3    VCHIPSET     47K    100K        1.47    2.24 V [2]_
 in4     VIN4    VCC5V       200K     47K        5.25    0.95 V
 in5     VIN5    +12V        200K     20K       11.00    1.05 V
 in6     VIN6    VCC1.5V      10K       -        1.00    1.50 V
-in7     VIN7    VCORE        10K       -        1.00   ~1.40 V (1)
+in7     VIN7    VCORE        10K       -        1.00   ~1.40 V [1]_
 in8     VIN8    VSB5V       200K     47K        1.00    0.95 V
-in10    VSB     VSB3.3V     int.    int.        2.00    1.65 V (3)
-in9     VBAT    VBATTERY    int.    int.        2.00    1.50 V (3)
+in10    VSB     VSB3.3V     int.    int.        2.00    1.65 V [3]_
+in9     VBAT    VBATTERY    int.    int.        2.00    1.50 V [3]_
+======= ======= =========== ==== ======= ============ ==============
 
-(1) Depends on your hardware setup.
-(2) Obviously not correct, swapping R1 and R2 would make more sense.
-(3) F71872F/FG only.
+.. [1] Depends on your hardware setup.
+.. [2] Obviously not correct, swapping R1 and R2 would make more sense.
+.. [3] F71872F/FG only.
 
 These values can be used as hints at best, as motherboard manufacturers
 are free to use a completely different setup. As a matter of fact, the
diff --git a/Documentation/hwmon/f71882fg b/Documentation/hwmon/f71882fg.rst
index 4c3cb8377d74..5c0b7b0db150 100644
--- a/Documentation/hwmon/f71882fg
+++ b/Documentation/hwmon/f71882fg.rst
@@ -2,60 +2,114 @@ Kernel driver f71882fg
 ======================
 
 Supported chips:
+
   * Fintek F71808E
+
     Prefix: 'f71808e'
+
     Addresses scanned: none, address read from Super I/O config space
+
     Datasheet: Not public
+
   * Fintek F71808A
+
     Prefix: 'f71808a'
+
     Addresses scanned: none, address read from Super I/O config space
+
     Datasheet: Not public
+
   * Fintek F71858FG
+
     Prefix: 'f71858fg'
+
     Addresses scanned: none, address read from Super I/O config space
+
     Datasheet: Available from the Fintek website
+
   * Fintek F71862FG and F71863FG
+
     Prefix: 'f71862fg'
+
     Addresses scanned: none, address read from Super I/O config space
+
     Datasheet: Available from the Fintek website
+
   * Fintek F71869F and F71869E
+
     Prefix: 'f71869'
+
     Addresses scanned: none, address read from Super I/O config space
+
     Datasheet: Available from the Fintek website
+
   * Fintek F71869A
+
     Prefix: 'f71869a'
+
     Addresses scanned: none, address read from Super I/O config space
+
     Datasheet: Not public
+
   * Fintek F71882FG and F71883FG
+
     Prefix: 'f71882fg'
+
     Addresses scanned: none, address read from Super I/O config space
+
     Datasheet: Available from the Fintek website
+
   * Fintek F71889FG
+
     Prefix: 'f71889fg'
+
     Addresses scanned: none, address read from Super I/O config space
+
     Datasheet: Available from the Fintek website
+
   * Fintek F71889ED
+
     Prefix: 'f71889ed'
+
     Addresses scanned: none, address read from Super I/O config space
+
     Datasheet: Should become available on the Fintek website soon
+
   * Fintek F71889A
+
     Prefix: 'f71889a'
+
     Addresses scanned: none, address read from Super I/O config space
+
     Datasheet: Should become available on the Fintek website soon
+
   * Fintek F8000
+
     Prefix: 'f8000'
+
     Addresses scanned: none, address read from Super I/O config space
+
     Datasheet: Not public
+
   * Fintek F81801U
+
     Prefix: 'f71889fg'
+
     Addresses scanned: none, address read from Super I/O config space
+
     Datasheet: Not public
-    Note: This is the 64-pin variant of the F71889FG, they have the
+
+    Note:
+	  This is the 64-pin variant of the F71889FG, they have the
 	  same device ID and are fully compatible as far as hardware
 	  monitoring is concerned.
+
   * Fintek F81865F
+
     Prefix: 'f81865f'
+
     Addresses scanned: none, address read from Super I/O config space
+
     Datasheet: Available from the Fintek website
 
 Author: Hans de Goede <hdegoede@redhat.com>
diff --git a/Documentation/hwmon/fam15h_power b/Documentation/hwmon/fam15h_power.rst
index fb594c281c46..fdde632c93a3 100644
--- a/Documentation/hwmon/fam15h_power
+++ b/Documentation/hwmon/fam15h_power.rst
@@ -2,15 +2,20 @@ Kernel driver fam15h_power
 ==========================
 
 Supported chips:
+
 * AMD Family 15h Processors
+
 * AMD Family 16h Processors
 
   Prefix: 'fam15h_power'
+
   Addresses scanned: PCI space
+
   Datasheets:
-  BIOS and Kernel Developer's Guide (BKDG) For AMD Family 15h Processors
-  BIOS and Kernel Developer's Guide (BKDG) For AMD Family 16h Processors
-  AMD64 Architecture Programmer's Manual Volume 2: System Programming
+
+  - BIOS and Kernel Developer's Guide (BKDG) For AMD Family 15h Processors
+  - BIOS and Kernel Developer's Guide (BKDG) For AMD Family 16h Processors
+  - AMD64 Architecture Programmer's Manual Volume 2: System Programming
 
 Author: Andreas Herrmann <herrmann.der.user@googlemail.com>
 
@@ -31,14 +36,19 @@ For AMD Family 15h and 16h processors the following power values can
 be calculated using different processor northbridge function
 registers:
 
-* BasePwrWatts: Specifies in watts the maximum amount of power
-  consumed by the processor for NB and logic external to the core.
-* ProcessorPwrWatts: Specifies in watts the maximum amount of power
-  the processor can support.
-* CurrPwrWatts: Specifies in watts the current amount of power being
-  consumed by the processor.
+* BasePwrWatts:
+    Specifies in watts the maximum amount of power
+    consumed by the processor for NB and logic external to the core.
+
+* ProcessorPwrWatts:
+    Specifies in watts the maximum amount of power
+    the processor can support.
+* CurrPwrWatts:
+    Specifies in watts the current amount of power being
+    consumed by the processor.
 
 This driver provides ProcessorPwrWatts and CurrPwrWatts:
+
 * power1_crit (ProcessorPwrWatts)
 * power1_input (CurrPwrWatts)
 
@@ -53,35 +63,53 @@ calculate the average power consumed by a processor during a
 measurement interval Tm. The feature of accumulated power mechanism is
 indicated by CPUID Fn8000_0007_EDX[12].
 
-* Tsample: compute unit power accumulator sample period
-* Tref: the PTSC counter period
-* PTSC: performance timestamp counter
-* N: the ratio of compute unit power accumulator sample period to the
-  PTSC period
-* Jmax: max compute unit accumulated power which is indicated by
-  MaxCpuSwPwrAcc MSR C001007b
-* Jx/Jy: compute unit accumulated power which is indicated by
-  CpuSwPwrAcc MSR C001007a
-* Tx/Ty: the value of performance timestamp counter which is indicated
-  by CU_PTSC MSR C0010280
-* PwrCPUave: CPU average power
+* Tsample:
+	compute unit power accumulator sample period
+
+* Tref:
+	the PTSC counter period
+
+* PTSC:
+	performance timestamp counter
+
+* N:
+	the ratio of compute unit power accumulator sample period to the
+	PTSC period
+
+* Jmax:
+	max compute unit accumulated power which is indicated by
+	MaxCpuSwPwrAcc MSR C001007b
+
+* Jx/Jy:
+	compute unit accumulated power which is indicated by
+	CpuSwPwrAcc MSR C001007a
+* Tx/Ty:
+	the value of performance timestamp counter which is indicated
+	by CU_PTSC MSR C0010280
+
+* PwrCPUave:
+	CPU average power
 
 i. Determine the ratio of Tsample to Tref by executing CPUID Fn8000_0007.
+
 	N = value of CPUID Fn8000_0007_ECX[CpuPwrSampleTimeRatio[15:0]].
 
 ii. Read the full range of the cumulative energy value from the new
-MSR MaxCpuSwPwrAcc.
+    MSR MaxCpuSwPwrAcc.
+
 	Jmax = value returned.
+
 iii. At time x, SW reads CpuSwPwrAcc MSR and samples the PTSC.
-	Jx = value read from CpuSwPwrAcc and Tx = value read from
-PTSC.
+
+	Jx = value read from CpuSwPwrAcc and Tx = value read from PTSC.
 
 iv. At time y, SW reads CpuSwPwrAcc MSR and samples the PTSC.
-	Jy = value read from CpuSwPwrAcc and Ty = value read from
-PTSC.
+
+	Jy = value read from CpuSwPwrAcc and Ty = value read from PTSC.
 
 v. Calculate the average power consumption for a compute unit over
-time period (y-x). Unit of result is uWatt.
+   time period (y-x). Unit of result is uWatt::
+
 	if (Jy < Jx) // Rollover has occurred
 		Jdelta = (Jy + Jmax) - Jx
 	else
@@ -90,13 +118,14 @@ time period (y-x). Unit of result is uWatt.
 
 This driver provides PwrCPUave and interval(default is 10 millisecond
 and maximum is 1 second):
+
 * power1_average (PwrCPUave)
 * power1_average_interval (Interval)
 
 The power1_average_interval can be updated at /etc/sensors3.conf file
 as below:
 
-chip "fam15h_power-*"
+chip `fam15h_power-*`
 	set power1_average_interval 0.01
 
 Then save it with "sensors -s".
diff --git a/Documentation/hwmon/ftsteutates b/Documentation/hwmon/ftsteutates.rst
index af54db92391b..58a2483d8d0d 100644
--- a/Documentation/hwmon/ftsteutates
+++ b/Documentation/hwmon/ftsteutates.rst
@@ -1,9 +1,12 @@
 Kernel driver ftsteutates
-=====================
+=========================
 
 Supported chips:
+
   * FTS Teutates
+
     Prefix: 'ftsteutates'
+
     Addresses scanned: I2C 0x73 (7-Bit)
 
 Author: Thilo Cestonaro <thilo.cestonaro@ts.fujitsu.com>
@@ -11,6 +14,7 @@ Author: Thilo Cestonaro <thilo.cestonaro@ts.fujitsu.com>
 
 Description
 -----------
+
 The BMC Teutates is the Eleventh generation of Superior System
 monitoring and thermal management solution. It is builds on the basic
 functionality of the BMC Theseus and contains several new features and
@@ -19,9 +23,11 @@ enhancements. It can monitor up to 4 voltages, 16 temperatures and
 implemented in this driver.
 
 To clear a temperature or fan alarm, execute the following command with the
-correct path to the alarm file:
+correct path to the alarm file::
+
 	echo 0 >XXXX_alarm
 
 Specification of the chip can be found here:
-ftp://ftp.ts.fujitsu.com/pub/Mainboard-OEM-Sales/Services/Software&Tools/Linux_SystemMonitoring&Watchdog&GPIO/BMC-Teutates_Specification_V1.21.pdf
-ftp://ftp.ts.fujitsu.com/pub/Mainboard-OEM-Sales/Services/Software&Tools/Linux_SystemMonitoring&Watchdog&GPIO/Fujitsu_mainboards-1-Sensors_HowTo-en-US.pdf
+
+- ftp://ftp.ts.fujitsu.com/pub/Mainboard-OEM-Sales/Services/Software&Tools/Linux_SystemMonitoring&Watchdog&GPIO/BMC-Teutates_Specification_V1.21.pdf
+- ftp://ftp.ts.fujitsu.com/pub/Mainboard-OEM-Sales/Services/Software&Tools/Linux_SystemMonitoring&Watchdog&GPIO/Fujitsu_mainboards-1-Sensors_HowTo-en-US.pdf
diff --git a/Documentation/hwmon/g760a b/Documentation/hwmon/g760a.rst
index cfc894537061..d82952cc8319 100644
--- a/Documentation/hwmon/g760a
+++ b/Documentation/hwmon/g760a.rst
@@ -2,9 +2,13 @@ Kernel driver g760a
 ===================
 
 Supported chips:
+
   * Global Mixed-mode Technology Inc. G760A
+
     Prefix: 'g760a'
+
     Datasheet: Publicly available at the GMT website
+
       http://www.gmt.com.tw/product/datasheet/EDS-760A.pdf
 
 Author: Herbert Valerio Riedel <hvr@gnu.org>
diff --git a/Documentation/hwmon/g762 b/Documentation/hwmon/g762.rst
index 923db9c5b5bc..0371b3365c48 100644
--- a/Documentation/hwmon/g762
+++ b/Documentation/hwmon/g762.rst
@@ -7,7 +7,7 @@ modes - PWM or DC - are supported by the device.
 
 For additional information, a detailed datasheet is available at
 http://natisbad.org/NAS/ref/GMT_EDS-762_763-080710-0.2.pdf. sysfs
-bindings are described in Documentation/hwmon/sysfs-interface.
+bindings are described in Documentation/hwmon/sysfs-interface.rst.
 
 The following entries are available to the user in a subdirectory of
 /sys/bus/i2c/drivers/g762/ to control the operation of the device.
@@ -21,34 +21,43 @@ documented in Documentation/devicetree/bindings/hwmon/g762.txt or
 using a specific platform_data structure in board initialization
 file (see include/linux/platform_data/g762.h).
 
-  fan1_target: set desired fan speed. This only makes sense in closed-loop
-            fan speed control (i.e. when pwm1_enable is set to 2).
+  fan1_target:
+	    set desired fan speed. This only makes sense in closed-loop
+	    fan speed control (i.e. when pwm1_enable is set to 2).
 
-  fan1_input: provide current fan rotation value in RPM as reported by
-            the fan to the device.
+  fan1_input:
+	    provide current fan rotation value in RPM as reported by
+	    the fan to the device.
 
-  fan1_div: fan clock divisor. Supported value are 1, 2, 4 and 8.
+  fan1_div:
+	    fan clock divisor. Supported value are 1, 2, 4 and 8.
 
-  fan1_pulses: number of pulses per fan revolution. Supported values
-            are 2 and 4.
+  fan1_pulses:
+	    number of pulses per fan revolution. Supported values
+	    are 2 and 4.
 
-  fan1_fault: reports fan failure, i.e. no transition on fan gear pin for
-            about 0.7s (if the fan is not voluntarily set off).
+  fan1_fault:
+	    reports fan failure, i.e. no transition on fan gear pin for
+	    about 0.7s (if the fan is not voluntarily set off).
 
-  fan1_alarm: in closed-loop control mode, if fan RPM value is 25% out
-            of the programmed value for over 6 seconds 'fan1_alarm' is
-            set to 1.
+  fan1_alarm:
+	    in closed-loop control mode, if fan RPM value is 25% out
+	    of the programmed value for over 6 seconds 'fan1_alarm' is
+	    set to 1.
 
-  pwm1_enable: set current fan speed control mode i.e. 1 for manual fan
-            speed control (open-loop) via pwm1 described below, 2 for
-            automatic fan speed control (closed-loop) via fan1_target
-            above.
+  pwm1_enable:
+	    set current fan speed control mode i.e. 1 for manual fan
+	    speed control (open-loop) via pwm1 described below, 2 for
+	    automatic fan speed control (closed-loop) via fan1_target
+	    above.
 
-  pwm1_mode: set or get fan driving mode: 1 for PWM mode, 0 for DC mode.
+  pwm1_mode:
+	    set or get fan driving mode: 1 for PWM mode, 0 for DC mode.
 
-  pwm1: get or set PWM fan control value in open-loop mode. This is an
-            integer value between 0 and 255. 0 stops the fan, 255 makes
-            it run at full speed.
+  pwm1:
+	    get or set PWM fan control value in open-loop mode. This is an
+	    integer value between 0 and 255. 0 stops the fan, 255 makes
+	    it run at full speed.
 
 Both in PWM mode ('pwm1_mode' set to 1) and DC mode ('pwm1_mode' set to 0),
 when current fan speed control mode is open-loop ('pwm1_enable' set to 1),
diff --git a/Documentation/hwmon/gl518sm b/Documentation/hwmon/gl518sm.rst
index 494bb55b6e72..bf1e0b5e824b 100644
--- a/Documentation/hwmon/gl518sm
+++ b/Documentation/hwmon/gl518sm.rst
@@ -2,27 +2,34 @@ Kernel driver gl518sm
 =====================
 
 Supported chips:
+
   * Genesys Logic GL518SM release 0x00
+
     Prefix: 'gl518sm'
+
     Addresses scanned: I2C 0x2c and 0x2d
+
   * Genesys Logic GL518SM release 0x80
+
     Prefix: 'gl518sm'
+
     Addresses scanned: I2C 0x2c and 0x2d
+
     Datasheet: http://www.genesyslogic.com/
 
 Authors:
-        Frodo Looijaard <frodol@dds.nl>,
-        Kyösti Mälkki <kmalkki@cc.hut.fi>
-        Hong-Gunn Chew <hglinux@gunnet.org>
-        Jean Delvare <jdelvare@suse.de>
+       - Frodo Looijaard <frodol@dds.nl>,
+       - Kyösti Mälkki <kmalkki@cc.hut.fi>
+       - Hong-Gunn Chew <hglinux@gunnet.org>
+       - Jean Delvare <jdelvare@suse.de>
 
 Description
 -----------
 
-IMPORTANT:
+.. important::
 
-For the revision 0x00 chip, the in0, in1, and in2  values (+5V, +3V,
-and +12V) CANNOT be read. This is a limitation of the chip, not the driver.
+   For the revision 0x00 chip, the in0, in1, and in2  values (+5V, +3V,
+   and +12V) CANNOT be read. This is a limitation of the chip, not the driver.
 
 This driver supports the Genesys Logic GL518SM chip. There are at least
 two revision of this chip, which we call revision 0x00 and 0x80. Revision
diff --git a/Documentation/hwmon/hih6130 b/Documentation/hwmon/hih6130.rst
index 73dae918ea7b..649bd4be4fc2 100644
--- a/Documentation/hwmon/hih6130
+++ b/Documentation/hwmon/hih6130.rst
@@ -2,11 +2,16 @@ Kernel driver hih6130
 =====================
 
 Supported chips:
+
   * Honeywell HIH-6130 / HIH-6131
+
     Prefix: 'hih6130'
+
     Addresses scanned: none
+
     Datasheet: Publicly available at the Honeywell website
-    http://sensing.honeywell.com/index.php?ci_id=3106&la_id=1&defId=44872
+
+	http://sensing.honeywell.com/index.php?ci_id=3106&la_id=1&defId=44872
 
 Author:
   Iain Paton <ipaton0@gmail.com>
@@ -28,8 +33,11 @@ instantiate I2C devices.
 sysfs-Interface
 ---------------
 
-temp1_input - temperature input
-humidity1_input - humidity input
+temp1_input
+	temperature input
+
+humidity1_input
+	humidity input
 
 Notes
 -----
diff --git a/Documentation/hwmon/hwmon-kernel-api.txt b/Documentation/hwmon/hwmon-kernel-api.rst
index 8bdefb41be30..c41eb6108103 100644
--- a/Documentation/hwmon/hwmon-kernel-api.txt
+++ b/Documentation/hwmon/hwmon-kernel-api.rst
@@ -1,5 +1,5 @@
-The Linux Hardware Monitoring kernel API.
-=========================================
+The Linux Hardware Monitoring kernel API
+========================================
 
 Guenter Roeck
 
@@ -12,42 +12,43 @@ drivers that want to use the hardware monitoring framework.
 This document does not describe what a hardware monitoring (hwmon) Driver or
 Device is. It also does not describe the API which can be used by user space
 to communicate with a hardware monitoring device. If you want to know this
-then please read the following file: Documentation/hwmon/sysfs-interface.
+then please read the following file: Documentation/hwmon/sysfs-interface.rst.
 
 For additional guidelines on how to write and improve hwmon drivers, please
-also read Documentation/hwmon/submitting-patches.
+also read Documentation/hwmon/submitting-patches.rst.
 
 The API
 -------
 Each hardware monitoring driver must #include <linux/hwmon.h> and, in most
 cases, <linux/hwmon-sysfs.h>. linux/hwmon.h declares the following
-register/unregister functions:
-
-struct device *
-hwmon_device_register_with_groups(struct device *dev, const char *name,
-				  void *drvdata,
-				  const struct attribute_group **groups);
-
-struct device *
-devm_hwmon_device_register_with_groups(struct device *dev,
-				       const char *name, void *drvdata,
-				       const struct attribute_group **groups);
-
-struct device *
-hwmon_device_register_with_info(struct device *dev,
-				const char *name, void *drvdata,
-				const struct hwmon_chip_info *info,
-				const struct attribute_group **extra_groups);
-
-struct device *
-devm_hwmon_device_register_with_info(struct device *dev,
-				const char *name,
-				void *drvdata,
-				const struct hwmon_chip_info *info,
-				const struct attribute_group **extra_groups);
-
-void hwmon_device_unregister(struct device *dev);
-void devm_hwmon_device_unregister(struct device *dev);
+register/unregister functions::
+
+  struct device *
+  hwmon_device_register_with_groups(struct device *dev, const char *name,
+				    void *drvdata,
+				    const struct attribute_group **groups);
+
+  struct device *
+  devm_hwmon_device_register_with_groups(struct device *dev,
+					 const char *name, void *drvdata,
+					 const struct attribute_group **groups);
+
+  struct device *
+  hwmon_device_register_with_info(struct device *dev,
+				  const char *name, void *drvdata,
+				  const struct hwmon_chip_info *info,
+				  const struct attribute_group **extra_groups);
+
+  struct device *
+  devm_hwmon_device_register_with_info(struct device *dev,
+				       const char *name,
+				       void *drvdata,
+				       const struct hwmon_chip_info *info,
+				       const struct attribute_group **extra_groups);
+
+  void hwmon_device_unregister(struct device *dev);
+
+  void devm_hwmon_device_unregister(struct device *dev);
 
 hwmon_device_register_with_groups registers a hardware monitoring device.
 The first parameter of this function is a pointer to the parent device.
@@ -100,78 +101,89 @@ Using devm_hwmon_device_register_with_info()
 hwmon_device_register_with_info() registers a hardware monitoring device.
 The parameters to this function are
 
-struct device *dev	Pointer to parent device
-const char *name	Device name
-void *drvdata		Driver private data
-const struct hwmon_chip_info *info
-			Pointer to chip description.
-const struct attribute_group **extra_groups
-			Null-terminated list of additional non-standard
-			sysfs attribute groups.
+=============================================== ===============================================
+`struct device *dev`				Pointer to parent device
+`const char *name`				Device name
+`void *drvdata`					Driver private data
+`const struct hwmon_chip_info *info`		Pointer to chip description.
+`const struct attribute_group **extra_groups` 	Null-terminated list of additional non-standard
+						sysfs attribute groups.
+=============================================== ===============================================
 
 This function returns a pointer to the created hardware monitoring device
 on success and a negative error code for failure.
 
-The hwmon_chip_info structure looks as follows.
+The hwmon_chip_info structure looks as follows::
 
-struct hwmon_chip_info {
-	const struct hwmon_ops *ops;
-	const struct hwmon_channel_info **info;
-};
+	struct hwmon_chip_info {
+		const struct hwmon_ops *ops;
+		const struct hwmon_channel_info **info;
+	};
 
 It contains the following fields:
 
-* ops:	Pointer to device operations.
-* info: NULL-terminated list of device channel descriptors.
+* ops:
+	Pointer to device operations.
+* info:
+	NULL-terminated list of device channel descriptors.
 
-The list of hwmon operations is defined as:
+The list of hwmon operations is defined as::
 
-struct hwmon_ops {
+  struct hwmon_ops {
 	umode_t (*is_visible)(const void *, enum hwmon_sensor_types type,
 			      u32 attr, int);
 	int (*read)(struct device *, enum hwmon_sensor_types type,
 		    u32 attr, int, long *);
 	int (*write)(struct device *, enum hwmon_sensor_types type,
 		     u32 attr, int, long);
-};
+  };
 
 It defines the following operations.
 
-* is_visible: Pointer to a function to return the file mode for each supported
-  attribute. This function is mandatory.
+* is_visible:
+    Pointer to a function to return the file mode for each supported
+    attribute. This function is mandatory.
 
-* read: Pointer to a function for reading a value from the chip. This function
-  is optional, but must be provided if any readable attributes exist.
+* read:
+    Pointer to a function for reading a value from the chip. This function
+    is optional, but must be provided if any readable attributes exist.
 
-* write: Pointer to a function for writing a value to the chip. This function is
-  optional, but must be provided if any writeable attributes exist.
+* write:
+    Pointer to a function for writing a value to the chip. This function is
+    optional, but must be provided if any writeable attributes exist.
 
 Each sensor channel is described with struct hwmon_channel_info, which is
-defined as follows.
+defined as follows::
 
-struct hwmon_channel_info {
-	enum hwmon_sensor_types type;
-	u32 *config;
-};
+	struct hwmon_channel_info {
+		enum hwmon_sensor_types type;
+		u32 *config;
+	};
 
 It contains following fields:
 
-* type: The hardware monitoring sensor type.
-  Supported sensor types are
-  * hwmon_chip		A virtual sensor type, used to describe attributes
-  *			which are not bound to a specific input or output
-  * hwmon_temp		Temperature sensor
-  * hwmon_in		Voltage sensor
-  * hwmon_curr		Current sensor
-  * hwmon_power		Power sensor
-  * hwmon_energy	Energy sensor
-  * hwmon_humidity	Humidity sensor
-  * hwmon_fan		Fan speed sensor
-  * hwmon_pwm		PWM control
-
-* config: Pointer to a 0-terminated list of configuration values for each
-  sensor of the given type. Each value is a combination of bit values
-  describing the attributes supposed by a single sensor.
+* type:
+    The hardware monitoring sensor type.
+
+    Supported sensor types are
+
+     ================== ==================================================
+     hwmon_chip		A virtual sensor type, used to describe attributes
+			which are not bound to a specific input or output
+     hwmon_temp		Temperature sensor
+     hwmon_in		Voltage sensor
+     hwmon_curr		Current sensor
+     hwmon_power		Power sensor
+     hwmon_energy	Energy sensor
+     hwmon_humidity	Humidity sensor
+     hwmon_fan		Fan speed sensor
+     hwmon_pwm		PWM control
+     ================== ==================================================
+
+* config:
+    Pointer to a 0-terminated list of configuration values for each
+    sensor of the given type. Each value is a combination of bit values
+    describing the attributes supposed by a single sensor.
 
 As an example, here is the complete description file for a LM75 compatible
 sensor chip. The chip has a single temperature sensor. The driver wants to
@@ -179,48 +191,62 @@ register with the thermal subsystem (HWMON_C_REGISTER_TZ), and it supports
 the update_interval attribute (HWMON_C_UPDATE_INTERVAL). The chip supports
 reading the temperature (HWMON_T_INPUT), it has a maximum temperature
 register (HWMON_T_MAX) as well as a maximum temperature hysteresis register
-(HWMON_T_MAX_HYST).
-
-static const u32 lm75_chip_config[] = {
-	HWMON_C_REGISTER_TZ | HWMON_C_UPDATE_INTERVAL,
-	0
-};
-
-static const struct hwmon_channel_info lm75_chip = {
-	.type = hwmon_chip,
-	.config = lm75_chip_config,
-};
-
-static const u32 lm75_temp_config[] = {
-	HWMON_T_INPUT | HWMON_T_MAX | HWMON_T_MAX_HYST,
-	0
-};
-
-static const struct hwmon_channel_info lm75_temp = {
-	.type = hwmon_temp,
-	.config = lm75_temp_config,
-};
-
-static const struct hwmon_channel_info *lm75_info[] = {
-	&lm75_chip,
-	&lm75_temp,
-	NULL
-};
-
-static const struct hwmon_ops lm75_hwmon_ops = {
-	.is_visible = lm75_is_visible,
-	.read = lm75_read,
-	.write = lm75_write,
-};
-
-static const struct hwmon_chip_info lm75_chip_info = {
-	.ops = &lm75_hwmon_ops,
-	.info = lm75_info,
-};
+(HWMON_T_MAX_HYST)::
+
+	static const u32 lm75_chip_config[] = {
+		HWMON_C_REGISTER_TZ | HWMON_C_UPDATE_INTERVAL,
+		0
+	};
+
+	static const struct hwmon_channel_info lm75_chip = {
+		.type = hwmon_chip,
+		.config = lm75_chip_config,
+	};
+
+	static const u32 lm75_temp_config[] = {
+		HWMON_T_INPUT | HWMON_T_MAX | HWMON_T_MAX_HYST,
+		0
+	};
+
+	static const struct hwmon_channel_info lm75_temp = {
+		.type = hwmon_temp,
+		.config = lm75_temp_config,
+	};
+
+	static const struct hwmon_channel_info *lm75_info[] = {
+		&lm75_chip,
+		&lm75_temp,
+		NULL
+	};
+
+	The HWMON_CHANNEL_INFO() macro can and should be used when possible.
+	With this macro, the above example can be simplified to
+
+	static const struct hwmon_channel_info *lm75_info[] = {
+		HWMON_CHANNEL_INFO(chip,
+				HWMON_C_REGISTER_TZ | HWMON_C_UPDATE_INTERVAL),
+		HWMON_CHANNEL_INFO(temp,
+				HWMON_T_INPUT | HWMON_T_MAX | HWMON_T_MAX_HYST),
+		NULL
+	};
+
+	The remaining declarations are as follows.
+
+	static const struct hwmon_ops lm75_hwmon_ops = {
+		.is_visible = lm75_is_visible,
+		.read = lm75_read,
+		.write = lm75_write,
+	};
+
+	static const struct hwmon_chip_info lm75_chip_info = {
+		.ops = &lm75_hwmon_ops,
+		.info = lm75_info,
+	};
 
 A complete list of bit values indicating individual attribute support
 is defined in include/linux/hwmon.h. Definition prefixes are as follows.
 
+=============== =================================================
 HWMON_C_xxxx	Chip attributes, for use with hwmon_chip.
 HWMON_T_xxxx	Temperature attributes, for use with hwmon_temp.
 HWMON_I_xxxx	Voltage attributes, for use with hwmon_in.
@@ -231,57 +257,76 @@ HWMON_E_xxxx	Energy attributes, for use with hwmon_energy.
 HWMON_H_xxxx	Humidity attributes, for use with hwmon_humidity.
 HWMON_F_xxxx	Fan speed attributes, for use with hwmon_fan.
 HWMON_PWM_xxxx	PWM control attributes, for use with hwmon_pwm.
+=============== =================================================
 
 Driver callback functions
 -------------------------
 
 Each driver provides is_visible, read, and write functions. Parameters
-and return values for those functions are as follows.
+and return values for those functions are as follows::
 
-umode_t is_visible_func(const void *data, enum hwmon_sensor_types type,
-			u32 attr, int channel)
+  umode_t is_visible_func(const void *data, enum hwmon_sensor_types type,
+			  u32 attr, int channel)
 
 Parameters:
-	data:	Pointer to device private data structure.
-	type:	The sensor type.
-	attr:	Attribute identifier associated with a specific attribute.
+	data:
+		Pointer to device private data structure.
+	type:
+		The sensor type.
+	attr:
+		Attribute identifier associated with a specific attribute.
 		For example, the attribute value for HWMON_T_INPUT would be
 		hwmon_temp_input. For complete mappings of bit fields to
 		attribute values please see include/linux/hwmon.h.
-	channel:The sensor channel number.
+	channel:
+		The sensor channel number.
 
 Return value:
 	The file mode for this attribute. Typically, this will be 0 (the
 	attribute will not be created), S_IRUGO, or 'S_IRUGO | S_IWUSR'.
 
-int read_func(struct device *dev, enum hwmon_sensor_types type,
-	      u32 attr, int channel, long *val)
+::
+
+	int read_func(struct device *dev, enum hwmon_sensor_types type,
+		      u32 attr, int channel, long *val)
 
 Parameters:
-	dev:	Pointer to the hardware monitoring device.
-	type:	The sensor type.
-	attr:	Attribute identifier associated with a specific attribute.
+	dev:
+		Pointer to the hardware monitoring device.
+	type:
+		The sensor type.
+	attr:
+		Attribute identifier associated with a specific attribute.
 		For example, the attribute value for HWMON_T_INPUT would be
 		hwmon_temp_input. For complete mappings please see
 		include/linux/hwmon.h.
-	channel:The sensor channel number.
-	val:	Pointer to attribute value.
+	channel:
+		The sensor channel number.
+	val:
+		Pointer to attribute value.
 
 Return value:
 	0 on success, a negative error number otherwise.
 
-int write_func(struct device *dev, enum hwmon_sensor_types type,
-	       u32 attr, int channel, long val)
+::
+
+	int write_func(struct device *dev, enum hwmon_sensor_types type,
+		       u32 attr, int channel, long val)
 
 Parameters:
-	dev:	Pointer to the hardware monitoring device.
-	type:	The sensor type.
-	attr:	Attribute identifier associated with a specific attribute.
+	dev:
+		Pointer to the hardware monitoring device.
+	type:
+		The sensor type.
+	attr:
+		Attribute identifier associated with a specific attribute.
 		For example, the attribute value for HWMON_T_INPUT would be
 		hwmon_temp_input. For complete mappings please see
 		include/linux/hwmon.h.
-	channel:The sensor channel number.
-	val:	The value to write to the chip.
+	channel:
+		The sensor channel number.
+	val:
+		The value to write to the chip.
 
 Return value:
 	0 on success, a negative error number otherwise.
@@ -317,25 +362,25 @@ Standard functions, similar to DEVICE_ATTR_{RW,RO,WO}, have _show and _store
 appended to the provided function name.
 
 SENSOR_DEVICE_ATTR and its variants define a struct sensor_device_attribute
-variable. This structure has the following fields.
+variable. This structure has the following fields::
 
-struct sensor_device_attribute {
-	struct device_attribute dev_attr;
-	int index;
-};
+	struct sensor_device_attribute {
+		struct device_attribute dev_attr;
+		int index;
+	};
 
 You can use to_sensor_dev_attr to get the pointer to this structure from the
 attribute read or write function. Its parameter is the device to which the
 attribute is attached.
 
 SENSOR_DEVICE_ATTR_2 and its variants define a struct sensor_device_attribute_2
-variable, which is defined as follows.
+variable, which is defined as follows::
 
-struct sensor_device_attribute_2 {
-	struct device_attribute dev_attr;
-	u8 index;
-	u8 nr;
-};
+	struct sensor_device_attribute_2 {
+		struct device_attribute dev_attr;
+		u8 index;
+		u8 nr;
+	};
 
 Use to_sensor_dev_attr_2 to get the pointer to this structure. Its parameter
 is the device to which the attribute is attached.
diff --git a/Documentation/hwmon/ibm-cffps b/Documentation/hwmon/ibm-cffps.rst
index e05ecd8ecfcf..52e74e39463a 100644
--- a/Documentation/hwmon/ibm-cffps
+++ b/Documentation/hwmon/ibm-cffps.rst
@@ -2,6 +2,7 @@ Kernel driver ibm-cffps
 =======================
 
 Supported chips:
+
   * IBM Common Form Factor power supply
 
 Author: Eddie James <eajames@us.ibm.com>
@@ -24,6 +25,7 @@ Sysfs entries
 
 The following attributes are supported:
 
+======================= ======================================================
 curr1_alarm		Output current over-current alarm.
 curr1_input		Measured output current in mA.
 curr1_label		"iout1"
@@ -52,3 +54,4 @@ temp2_alarm		Secondary rectifier temp over-temperature alarm.
 temp2_input		Measured secondary rectifier temp in millidegrees C.
 temp3_alarm		ORing FET temperature over-temperature alarm.
 temp3_input		Measured ORing FET temperature in millidegrees C.
+======================= ======================================================
diff --git a/Documentation/hwmon/ibmaem b/Documentation/hwmon/ibmaem.rst
index 1e0d59e000b4..f07a14a1c2f5 100644
--- a/Documentation/hwmon/ibmaem
+++ b/Documentation/hwmon/ibmaem.rst
@@ -1,15 +1,21 @@
 Kernel driver ibmaem
-======================
+====================
 
 This driver talks to the IBM Systems Director Active Energy Manager, known
 henceforth as AEM.
 
 Supported systems:
+
   * Any recent IBM System X server with AEM support.
+
     This includes the x3350, x3550, x3650, x3655, x3755, x3850 M2,
-    x3950 M2, and certain HC10/HS2x/LS2x/QS2x blades.  The IPMI host interface
+    x3950 M2, and certain HC10/HS2x/LS2x/QS2x blades.
+
+    The IPMI host interface
     driver ("ipmi-si") needs to be loaded for this driver to do anything.
+
     Prefix: 'ibmaem'
+
     Datasheet: Not available
 
 Author: Darrick J. Wong
diff --git a/Documentation/hwmon/ibmpowernv b/Documentation/hwmon/ibmpowernv.rst
index 56468258711f..5d642bc3dec0 100644
--- a/Documentation/hwmon/ibmpowernv
+++ b/Documentation/hwmon/ibmpowernv.rst
@@ -2,6 +2,7 @@ Kernel Driver IBMPOWERNV
 ========================
 
 Supported systems:
+
   * Any recent IBM P servers based on POWERNV platform
 
 Author: Neelesh Gupta
@@ -29,10 +30,11 @@ CONFIG_SENSORS_IBMPOWERNV. It can also be built as module 'ibmpowernv'.
 Sysfs attributes
 ----------------
 
+======================= =======================================================
 fanX_input		Measured RPM value.
 fanX_min		Threshold RPM for alert generation.
-fanX_fault		0: No fail condition
-			1: Failing fan
+fanX_fault		- 0: No fail condition
+			- 1: Failing fan
 
 tempX_input		Measured ambient temperature.
 tempX_max		Threshold ambient temperature for alert generation.
@@ -42,20 +44,22 @@ tempX_enable		Enable/disable all temperature sensors belonging to the
 			sub-group. In POWER9, this attribute corresponds to
 			each OCC. Using this attribute each OCC can be asked to
 			disable/enable all of its temperature sensors.
-			1: Enable
-			0: Disable
+
+			- 1: Enable
+			- 0: Disable
 
 inX_input		Measured power supply voltage (millivolt)
-inX_fault		0: No fail condition.
-			1: Failing power supply.
+inX_fault		- 0: No fail condition.
+			- 1: Failing power supply.
 inX_highest		Historical maximum voltage
 inX_lowest		Historical minimum voltage
 inX_enable		Enable/disable all voltage sensors belonging to the
 			sub-group. In POWER9, this attribute corresponds to
 			each OCC. Using this attribute each OCC can be asked to
 			disable/enable all of its voltage sensors.
-			1: Enable
-			0: Disable
+
+			- 1: Enable
+			- 0: Disable
 
 powerX_input		Power consumption (microWatt)
 powerX_input_highest	Historical maximum power
@@ -64,8 +68,9 @@ powerX_enable		Enable/disable all power sensors belonging to the
 			sub-group. In POWER9, this attribute corresponds to
 			each OCC. Using this attribute each OCC can be asked to
 			disable/enable all of its power sensors.
-			1: Enable
-			0: Disable
+
+			- 1: Enable
+			- 0: Disable
 
 currX_input		Measured current (milliampere)
 currX_highest		Historical maximum current
@@ -74,7 +79,9 @@ currX_enable		Enable/disable all current sensors belonging to the
 			sub-group. In POWER9, this attribute corresponds to
 			each OCC. Using this attribute each OCC can be asked to
 			disable/enable all of its current sensors.
-			1: Enable
-			0: Disable
+
+			- 1: Enable
+			- 0: Disable
 
 energyX_input		Cumulative energy (microJoule)
+======================= =======================================================
diff --git a/Documentation/hwmon/ina209 b/Documentation/hwmon/ina209.rst
index 672501de4509..64322075a145 100644
--- a/Documentation/hwmon/ina209
+++ b/Documentation/hwmon/ina209.rst
@@ -1,16 +1,21 @@
 Kernel driver ina209
-=====================
+====================
 
 Supported chips:
+
   * Burr-Brown / Texas Instruments INA209
+
     Prefix: 'ina209'
+
     Addresses scanned: -
+
     Datasheet:
-        http://www.ti.com/lit/gpn/ina209
+	http://www.ti.com/lit/gpn/ina209
 
-Author: Paul Hays <Paul.Hays@cattail.ca>
-Author: Ira W. Snyder <iws@ovro.caltech.edu>
-Author: Guenter Roeck <linux@roeck-us.net>
+Author:
+	- Paul Hays <Paul.Hays@cattail.ca>
+	- Ira W. Snyder <iws@ovro.caltech.edu>
+	- Guenter Roeck <linux@roeck-us.net>
 
 
 Description
@@ -31,7 +36,7 @@ the I2C bus. See the datasheet for details.
 This tries to expose most monitoring features of the hardware via
 sysfs. It does not support every feature of this chip.
 
-
+======================= =======================================================
 in0_input		shunt voltage (mV)
 in0_input_highest	shunt voltage historical maximum reading (mV)
 in0_input_lowest	shunt voltage historical minimum reading (mV)
@@ -70,6 +75,7 @@ curr1_input		current measurement (mA)
 
 update_interval		data conversion time; affects number of samples used
 			to average results for shunt and bus voltages.
+======================= =======================================================
 
 General Remarks
 ---------------
diff --git a/Documentation/hwmon/ina2xx b/Documentation/hwmon/ina2xx.rst
index 0f36c021192d..94b9a260c518 100644
--- a/Documentation/hwmon/ina2xx
+++ b/Documentation/hwmon/ina2xx.rst
@@ -2,35 +2,56 @@ Kernel driver ina2xx
 ====================
 
 Supported chips:
+
   * Texas Instruments INA219
+
+
     Prefix: 'ina219'
     Addresses: I2C 0x40 - 0x4f
+
     Datasheet: Publicly available at the Texas Instruments website
-               http://www.ti.com/
+
+	       http://www.ti.com/
 
   * Texas Instruments INA220
+
     Prefix: 'ina220'
+
     Addresses: I2C 0x40 - 0x4f
+
     Datasheet: Publicly available at the Texas Instruments website
-               http://www.ti.com/
+
+	       http://www.ti.com/
 
   * Texas Instruments INA226
+
     Prefix: 'ina226'
+
     Addresses: I2C 0x40 - 0x4f
+
     Datasheet: Publicly available at the Texas Instruments website
-               http://www.ti.com/
+
+	       http://www.ti.com/
 
   * Texas Instruments INA230
+
     Prefix: 'ina230'
+
     Addresses: I2C 0x40 - 0x4f
+
     Datasheet: Publicly available at the Texas Instruments website
-               http://www.ti.com/
+
+	       http://www.ti.com/
 
   * Texas Instruments INA231
+
     Prefix: 'ina231'
+
     Addresses: I2C 0x40 - 0x4f
+
     Datasheet: Publicly available at the Texas Instruments website
-               http://www.ti.com/
+
+	       http://www.ti.com/
 
 Author: Lothar Felten <lothar.felten@gmail.com>
 
@@ -57,23 +78,27 @@ refer to the Documentation/devicetree/bindings/hwmon/ina2xx.txt for bindings
 if the device tree is used.
 
 Additionally ina226 supports update_interval attribute as described in
-Documentation/hwmon/sysfs-interface. Internally the interval is the sum of
+Documentation/hwmon/sysfs-interface.rst. Internally the interval is the sum of
 bus and shunt voltage conversion times multiplied by the averaging rate. We
 don't touch the conversion times and only modify the number of averages. The
 lower limit of the update_interval is 2 ms, the upper limit is 2253 ms.
 The actual programmed interval may vary from the desired value.
 
 General sysfs entries
--------------
+---------------------
 
+======================= ===============================
 in0_input		Shunt voltage(mV) channel
 in1_input		Bus voltage(mV) channel
 curr1_input		Current(mA) measurement channel
 power1_input		Power(uW) measurement channel
 shunt_resistor		Shunt resistance(uOhm) channel
+======================= ===============================
 
 Sysfs entries for ina226, ina230 and ina231 only
--------------
+------------------------------------------------
 
+======================= ====================================================
 update_interval		data conversion time; affects number of samples used
 			to average results for shunt and bus voltages.
+======================= ====================================================
diff --git a/Documentation/hwmon/ina3221 b/Documentation/hwmon/ina3221.rst
index 4b82cbfb551c..f6007ae8f4e2 100644
--- a/Documentation/hwmon/ina3221
+++ b/Documentation/hwmon/ina3221.rst
@@ -2,11 +2,16 @@ Kernel driver ina3221
 =====================
 
 Supported chips:
+
   * Texas Instruments INA3221
+
     Prefix: 'ina3221'
+
     Addresses: I2C 0x40 - 0x43
+
     Datasheet: Publicly available at the Texas Instruments website
-               http://www.ti.com/
+
+	       http://www.ti.com/
 
 Author: Andrew F. Davis <afd@ti.com>
 
@@ -21,17 +26,37 @@ and power are calculated host-side from these.
 Sysfs entries
 -------------
 
+======================= =======================================================
 in[123]_label           Voltage channel labels
 in[123]_enable          Voltage channel enable controls
 in[123]_input           Bus voltage(mV) channels
 curr[123]_input         Current(mA) measurement channels
 shunt[123]_resistor     Shunt resistance(uOhm) channels
 curr[123]_crit          Critical alert current(mA) setting, activates the
-                          corresponding alarm when the respective current
-                          is above this value
+			corresponding alarm when the respective current
+			is above this value
 curr[123]_crit_alarm    Critical alert current limit exceeded
 curr[123]_max           Warning alert current(mA) setting, activates the
-                          corresponding alarm when the respective current
-                          average is above this value.
+			corresponding alarm when the respective current
+			average is above this value.
 curr[123]_max_alarm     Warning alert current limit exceeded
 in[456]_input           Shunt voltage(uV) for channels 1, 2, and 3 respectively
+samples                 Number of samples using in the averaging mode.
+
+                        Supports the list of number of samples:
+
+                          1, 4, 16, 64, 128, 256, 512, 1024
+
+update_interval         Data conversion time in millisecond, following:
+
+                          update_interval = C x S x (BC + SC)
+
+                          * C:	number of enabled channels
+                          * S:	number of samples
+                          * BC:	bus-voltage conversion time in millisecond
+                          * SC:	shunt-voltage conversion time in millisecond
+
+                        Affects both Bus- and Shunt-voltage conversion time.
+                        Note that setting update_interval to 0ms sets both BC
+                        and SC to 140 us (minimum conversion time).
+======================= =======================================================
diff --git a/Documentation/hwmon/index.rst b/Documentation/hwmon/index.rst
new file mode 100644
index 000000000000..ee090e51653a
--- /dev/null
+++ b/Documentation/hwmon/index.rst
@@ -0,0 +1,182 @@
+=========================
+Linux Hardware Monitoring
+=========================
+
+.. toctree::
+   :maxdepth: 1
+
+   hwmon-kernel-api
+   pmbus-core
+   submitting-patches
+   sysfs-interface
+   userspace-tools
+
+Hardware Monitoring Kernel Drivers
+==================================
+
+.. toctree::
+   :maxdepth: 1
+
+   ab8500
+   abituguru
+   abituguru3
+   abx500
+   acpi_power_meter
+   ad7314
+   adc128d818
+   adm1021
+   adm1025
+   adm1026
+   adm1031
+   adm1275
+   adm9240
+   ads1015
+   ads7828
+   adt7410
+   adt7411
+   adt7462
+   adt7470
+   adt7475
+   amc6821
+   asb100
+   asc7621
+   aspeed-pwm-tacho
+   coretemp
+   da9052
+   da9055
+   dme1737
+   ds1621
+   ds620
+   emc1403
+   emc2103
+   emc6w201
+   f71805f
+   f71882fg
+   fam15h_power
+   ftsteutates
+   g760a
+   g762
+   gl518sm
+   hih6130
+   ibmaem
+   ibm-cffps
+   ibmpowernv
+   ina209
+   ina2xx
+   ina3221
+   ir35221
+   ir38064
+   isl68137
+   it87
+   jc42
+   k10temp
+   k8temp
+   lineage-pem
+   lm25066
+   lm63
+   lm70
+   lm73
+   lm75
+   lm77
+   lm78
+   lm80
+   lm83
+   lm85
+   lm87
+   lm90
+   lm92
+   lm93
+   lm95234
+   lm95245
+   lochnagar
+   ltc2945
+   ltc2978
+   ltc2990
+   ltc3815
+   ltc4151
+   ltc4215
+   ltc4245
+   ltc4260
+   ltc4261
+   max16064
+   max16065
+   max1619
+   max1668
+   max197
+   max20751
+   max31722
+   max31785
+   max31790
+   max34440
+   max6639
+   max6642
+   max6650
+   max6697
+   max8688
+   mc13783-adc
+   mcp3021
+   menf21bmc
+   mlxreg-fan
+   nct6683
+   nct6775
+   nct7802
+   nct7904
+   npcm750-pwm-fan
+   nsa320
+   ntc_thermistor
+   occ
+   pc87360
+   pc87427
+   pcf8591
+   pmbus
+   powr1220
+   pwm-fan
+   raspberrypi-hwmon
+   sch5627
+   sch5636
+   scpi-hwmon
+   sht15
+   sht21
+   sht3x
+   shtc1
+   sis5595
+   smm665
+   smsc47b397
+   smsc47m192
+   smsc47m1
+   tc654
+   tc74
+   thmc50
+   tmp102
+   tmp103
+   tmp108
+   tmp401
+   tmp421
+   tps40422
+   twl4030-madc-hwmon
+   ucd9000
+   ucd9200
+   vexpress
+   via686a
+   vt1211
+   w83627ehf
+   w83627hf
+   w83773g
+   w83781d
+   w83791d
+   w83792d
+   w83793
+   w83795
+   w83l785ts
+   w83l786ng
+   wm831x
+   wm8350
+   xgene-hwmon
+   zl6100
+
+.. only::  subproject and html
+
+   Indices
+   =======
+
+   * :ref:`genindex`
diff --git a/Documentation/hwmon/ir35221 b/Documentation/hwmon/ir35221.rst
index f7e112752c04..a83922e5ccb5 100644
--- a/Documentation/hwmon/ir35221
+++ b/Documentation/hwmon/ir35221.rst
@@ -2,9 +2,12 @@ Kernel driver ir35221
 =====================
 
 Supported chips:
-  * Infinion IR35221
+  * Infineon IR35221
+
     Prefix: 'ir35221'
+
     Addresses scanned: -
+
     Datasheet: Datasheet is not publicly available.
 
 Author: Samuel Mendoza-Jonas <sam@mendozajonas.com>
@@ -23,15 +26,16 @@ This driver does not probe for PMBus devices. You will have to instantiate
 devices explicitly.
 
 Example: the following commands will load the driver for an IR35221
-at address 0x70 on I2C bus #4:
+at address 0x70 on I2C bus #4::
 
-# modprobe ir35221
-# echo ir35221 0x70 > /sys/bus/i2c/devices/i2c-4/new_device
+	# modprobe ir35221
+	# echo ir35221 0x70 > /sys/bus/i2c/devices/i2c-4/new_device
 
 
 Sysfs attributes
 ----------------
 
+======================= =======================================================
 curr1_label		"iin"
 curr1_input		Measured input current
 curr1_max		Maximum current
@@ -85,3 +89,4 @@ temp[1-2]_highest	Highest temperature
 temp[1-2]_lowest	Lowest temperature
 temp[1-2]_max		Maximum temperature
 temp[1-2]_max_alarm	Chip temperature high alarm
+======================= =======================================================
diff --git a/Documentation/hwmon/ir38064.rst b/Documentation/hwmon/ir38064.rst
new file mode 100644
index 000000000000..c455d755a267
--- /dev/null
+++ b/Documentation/hwmon/ir38064.rst
@@ -0,0 +1,66 @@
+Kernel driver ir38064
+=====================
+
+Supported chips:
+
+  * Infineon IR38064
+
+    Prefix: 'ir38064'
+    Addresses scanned: -
+
+    Datasheet: Publicly available at the Infineon webiste
+      https://www.infineon.com/dgdl/Infineon-IR38064MTRPBF-DS-v03_07-EN.pdf?fileId=5546d462584d1d4a0158db0d9efb67ca
+
+Authors:
+      - Maxim Sloyko <maxims@google.com>
+      - Patrick Venture <venture@google.com>
+
+Description
+-----------
+
+IR38064 is a Single-input Voltage, Synchronous Buck Regulator, DC-DC Converter.
+
+Usage Notes
+-----------
+
+This driver does not probe for PMBus devices. You will have to instantiate
+devices explicitly.
+
+Sysfs attributes
+----------------
+
+======================= ===========================
+curr1_label		"iout1"
+curr1_input		Measured output current
+curr1_crit		Critical maximum current
+curr1_crit_alarm	Current critical high alarm
+curr1_max		Maximum current
+curr1_max_alarm		Current high alarm
+
+in1_label		"vin"
+in1_input		Measured input voltage
+in1_crit		Critical maximum input voltage
+in1_crit_alarm		Input voltage critical high alarm
+in1_min			Minimum input voltage
+in1_min_alarm		Input voltage low alarm
+
+in2_label		"vout1"
+in2_input		Measured output voltage
+in2_lcrit		Critical minimum output voltage
+in2_lcrit_alarm		Output voltage critical low alarm
+in2_crit		Critical maximum output voltage
+in2_crit_alarm		Output voltage critical high alarm
+in2_max			Maximum output voltage
+in2_max_alarm		Output voltage high alarm
+in2_min			Minimum output voltage
+in2_min_alarm		Output voltage low alarm
+
+power1_label		"pout1"
+power1_input		Measured output power
+
+temp1_input		Measured temperature
+temp1_crit		Critical high temperature
+temp1_crit_alarm	Chip temperature critical high alarm
+temp1_max		Maximum temperature
+temp1_max_alarm		Chip temperature high alarm
+======================= ===========================
diff --git a/Documentation/hwmon/isl68137.rst b/Documentation/hwmon/isl68137.rst
new file mode 100644
index 000000000000..a5a7c8545c9e
--- /dev/null
+++ b/Documentation/hwmon/isl68137.rst
@@ -0,0 +1,80 @@
+Kernel driver isl68137
+======================
+
+Supported chips:
+
+  * Intersil ISL68137
+
+    Prefix: 'isl68137'
+
+    Addresses scanned: -
+
+    Datasheet:
+
+      Publicly available at the Intersil website
+      https://www.intersil.com/content/dam/Intersil/documents/isl6/isl68137.pdf
+
+Authors:
+      - Maxim Sloyko <maxims@google.com>
+      - Robert Lippert <rlippert@google.com>
+      - Patrick Venture <venture@google.com>
+
+Description
+-----------
+
+Intersil ISL68137 is a digital output 7-phase configurable PWM
+controller with an AVSBus interface.
+
+Usage Notes
+-----------
+
+This driver does not probe for PMBus devices. You will have to instantiate
+devices explicitly.
+
+The ISL68137 AVS operation mode must be enabled/disabled at runtime.
+
+Beyond the normal sysfs pmbus attributes, the driver exposes a control attribute.
+
+Additional Sysfs attributes
+---------------------------
+
+======================= ====================================
+avs(0|1)_enable		Controls the AVS state of each rail.
+
+curr1_label		"iin"
+curr1_input		Measured input current
+curr1_crit		Critical maximum current
+curr1_crit_alarm	Current critical high alarm
+
+curr[2-3]_label		"iout[1-2]"
+curr[2-3]_input		Measured output current
+curr[2-3]_crit		Critical maximum current
+curr[2-3]_crit_alarm	Current critical high alarm
+
+in1_label		"vin"
+in1_input		Measured input voltage
+in1_lcrit		Critical minimum input voltage
+in1_lcrit_alarm		Input voltage critical low alarm
+in1_crit		Critical maximum input voltage
+in1_crit_alarm		Input voltage critical high alarm
+
+in[2-3]_label		"vout[1-2]"
+in[2-3]_input		Measured output voltage
+in[2-3]_lcrit		Critical minimum output voltage
+in[2-3]_lcrit_alarm	Output voltage critical low alarm
+in[2-3]_crit		Critical maximum output voltage
+in[2-3]_crit_alarm	Output voltage critical high alarm
+
+power1_label		"pin"
+power1_input		Measured input power
+power1_alarm		Input power high alarm
+
+power[2-3]_label	"pout[1-2]"
+power[2-3]_input	Measured output power
+
+temp[1-3]_input		Measured temperature
+temp[1-3]_crit		Critical high temperature
+temp[1-3]_crit_alarm	Chip temperature critical high alarm
+temp[1-3]_max		Maximum temperature
+temp[1-3]_max_alarm	Chip temperature high alarm
+======================= ====================================
diff --git a/Documentation/hwmon/it87 b/Documentation/hwmon/it87.rst
index fff6f6bf55bc..2d83f23bee93 100644
--- a/Documentation/hwmon/it87
+++ b/Documentation/hwmon/it87.rst
@@ -2,105 +2,179 @@ Kernel driver it87
 ==================
 
 Supported chips:
+
   * IT8603E/IT8623E
+
     Prefix: 'it8603'
+
     Addresses scanned: from Super I/O config space (8 I/O ports)
+
     Datasheet: Not publicly available
+
   * IT8620E
+
     Prefix: 'it8620'
+
     Addresses scanned: from Super I/O config space (8 I/O ports)
+
   * IT8628E
+
     Prefix: 'it8628'
+
     Addresses scanned: from Super I/O config space (8 I/O ports)
+
     Datasheet: Not publicly available
+
   * IT8705F
+
     Prefix: 'it87'
+
     Addresses scanned: from Super I/O config space (8 I/O ports)
+
     Datasheet: Once publicly available at the ITE website, but no longer
+
   * IT8712F
+
     Prefix: 'it8712'
+
     Addresses scanned: from Super I/O config space (8 I/O ports)
+
     Datasheet: Once publicly available at the ITE website, but no longer
+
   * IT8716F/IT8726F
+
     Prefix: 'it8716'
+
     Addresses scanned: from Super I/O config space (8 I/O ports)
+
     Datasheet: Once publicly available at the ITE website, but no longer
+
   * IT8718F
+
     Prefix: 'it8718'
+
     Addresses scanned: from Super I/O config space (8 I/O ports)
+
     Datasheet: Once publicly available at the ITE website, but no longer
+
   * IT8720F
+
     Prefix: 'it8720'
+
     Addresses scanned: from Super I/O config space (8 I/O ports)
+
     Datasheet: Not publicly available
+
   * IT8721F/IT8758E
+
     Prefix: 'it8721'
+
     Addresses scanned: from Super I/O config space (8 I/O ports)
+
     Datasheet: Not publicly available
+
   * IT8728F
+
     Prefix: 'it8728'
+
     Addresses scanned: from Super I/O config space (8 I/O ports)
+
     Datasheet: Not publicly available
+
   * IT8732F
+
     Prefix: 'it8732'
+
     Addresses scanned: from Super I/O config space (8 I/O ports)
+
     Datasheet: Not publicly available
+
   * IT8771E
+
     Prefix: 'it8771'
+
     Addresses scanned: from Super I/O config space (8 I/O ports)
+
     Datasheet: Not publicly available
+
   * IT8772E
+
     Prefix: 'it8772'
+
     Addresses scanned: from Super I/O config space (8 I/O ports)
+
     Datasheet: Not publicly available
+
   * IT8781F
+
     Prefix: 'it8781'
+
     Addresses scanned: from Super I/O config space (8 I/O ports)
+
     Datasheet: Not publicly available
+
   * IT8782F
+
     Prefix: 'it8782'
+
     Addresses scanned: from Super I/O config space (8 I/O ports)
+
     Datasheet: Not publicly available
+
   * IT8783E/F
+
     Prefix: 'it8783'
+
     Addresses scanned: from Super I/O config space (8 I/O ports)
+
     Datasheet: Not publicly available
+
   * IT8786E
+
     Prefix: 'it8786'
+
     Addresses scanned: from Super I/O config space (8 I/O ports)
+
     Datasheet: Not publicly available
+
   * IT8790E
+
     Prefix: 'it8790'
+
     Addresses scanned: from Super I/O config space (8 I/O ports)
+
     Datasheet: Not publicly available
+
   * SiS950   [clone of IT8705F]
+
     Prefix: 'it87'
+
     Addresses scanned: from Super I/O config space (8 I/O ports)
+
     Datasheet: No longer be available
 
+
 Authors:
-    Christophe Gauthron
-    Jean Delvare <jdelvare@suse.de>
+    - Christophe Gauthron
+    - Jean Delvare <jdelvare@suse.de>
 
 
 Module Parameters
 -----------------
 
 * update_vbat: int
-
-  0 if vbat should report power on value, 1 if vbat should be updated after
-  each read. Default is 0. On some boards the battery voltage is provided
-  by either the battery or the onboard power supply. Only the first reading
-  at power on will be the actual battery voltage (which the chip does
-  automatically). On other boards the battery voltage is always fed to
-  the chip so can be read at any time. Excessive reading may decrease
-  battery life but no information is given in the datasheet.
+    0 if vbat should report power on value, 1 if vbat should be updated after
+    each read. Default is 0. On some boards the battery voltage is provided
+    by either the battery or the onboard power supply. Only the first reading
+    at power on will be the actual battery voltage (which the chip does
+    automatically). On other boards the battery voltage is always fed to
+    the chip so can be read at any time. Excessive reading may decrease
+    battery life but no information is given in the datasheet.
 
 * fix_pwm_polarity int
-
-  Force PWM polarity to active high (DANGEROUS). Some chips are
-  misconfigured by BIOS - PWM values would be inverted. This option tries
-  to fix this. Please contact your BIOS manufacturer and ask him for fix.
+    Force PWM polarity to active high (DANGEROUS). Some chips are
+    misconfigured by BIOS - PWM values would be inverted. This option tries
+    to fix this. Please contact your BIOS manufacturer and ask him for fix.
 
 
 Hardware Interfaces
diff --git a/Documentation/hwmon/jc42 b/Documentation/hwmon/jc42.rst
index b4b671f22453..5b14b49bb6f7 100644
--- a/Documentation/hwmon/jc42
+++ b/Documentation/hwmon/jc42.rst
@@ -2,53 +2,100 @@ Kernel driver jc42
 ==================
 
 Supported chips:
+
   * Analog Devices ADT7408
+
     Datasheets:
+
 	http://www.analog.com/static/imported-files/data_sheets/ADT7408.pdf
+
   * Atmel AT30TS00, AT30TS002A/B, AT30TSE004A
+
     Datasheets:
+
 	http://www.atmel.com/Images/doc8585.pdf
+
 	http://www.atmel.com/Images/doc8711.pdf
+
 	http://www.atmel.com/Images/Atmel-8852-SEEPROM-AT30TSE002A-Datasheet.pdf
+
 	http://www.atmel.com/Images/Atmel-8868-DTS-AT30TSE004A-Datasheet.pdf
+
   * IDT TSE2002B3, TSE2002GB2, TSE2004GB2, TS3000B3, TS3000GB0, TS3000GB2,
+
 	TS3001GB2
+
     Datasheets:
+
 	Available from IDT web site
+
   * Maxim MAX6604
+
     Datasheets:
+
 	http://datasheets.maxim-ic.com/en/ds/MAX6604.pdf
+
   * Microchip MCP9804, MCP9805, MCP9808, MCP98242, MCP98243, MCP98244, MCP9843
+
     Datasheets:
+
 	http://ww1.microchip.com/downloads/en/DeviceDoc/22203C.pdf
+
 	http://ww1.microchip.com/downloads/en/DeviceDoc/21977b.pdf
+
 	http://ww1.microchip.com/downloads/en/DeviceDoc/25095A.pdf
+
 	http://ww1.microchip.com/downloads/en/DeviceDoc/21996a.pdf
+
 	http://ww1.microchip.com/downloads/en/DeviceDoc/22153c.pdf
+
 	http://ww1.microchip.com/downloads/en/DeviceDoc/22327A.pdf
+
   * NXP Semiconductors SE97, SE97B, SE98, SE98A
+
     Datasheets:
+
 	http://www.nxp.com/documents/data_sheet/SE97.pdf
+
 	http://www.nxp.com/documents/data_sheet/SE97B.pdf
+
 	http://www.nxp.com/documents/data_sheet/SE98.pdf
+
 	http://www.nxp.com/documents/data_sheet/SE98A.pdf
+
   * ON Semiconductor CAT34TS02, CAT6095
+
     Datasheet:
+
 	http://www.onsemi.com/pub_link/Collateral/CAT34TS02-D.PDF
+
 	http://www.onsemi.com/pub/Collateral/CAT6095-D.PDF
+
   * ST Microelectronics STTS424, STTS424E02, STTS2002, STTS2004, STTS3000
+
     Datasheets:
+
 	http://www.st.com/web/en/resource/technical/document/datasheet/CD00157556.pdf
+
 	http://www.st.com/web/en/resource/technical/document/datasheet/CD00157558.pdf
+
 	http://www.st.com/web/en/resource/technical/document/datasheet/CD00266638.pdf
+
 	http://www.st.com/web/en/resource/technical/document/datasheet/CD00225278.pdf
+
 	http://www.st.com/web/en/resource/technical/document/datasheet/DM00076709.pdf
+
   * JEDEC JC 42.4 compliant temperature sensor chips
+
     Datasheet:
+
 	http://www.jedec.org/sites/default/files/docs/4_01_04R19.pdf
 
+
   Common for all chips:
+
     Prefix: 'jc42'
+
     Addresses scanned: I2C 0x18 - 0x1f
 
 Author:
@@ -67,10 +114,10 @@ The driver auto-detects the chips listed above, but can be manually instantiated
 to support other JC 42.4 compliant chips.
 
 Example: the following will load the driver for a generic JC 42.4 compliant
-temperature sensor at address 0x18 on I2C bus #1:
+temperature sensor at address 0x18 on I2C bus #1::
 
-# modprobe jc42
-# echo jc42 0x18 > /sys/bus/i2c/devices/i2c-1/new_device
+	# modprobe jc42
+	# echo jc42 0x18 > /sys/bus/i2c/devices/i2c-1/new_device
 
 A JC 42.4 compliant chip supports a single temperature sensor. Minimum, maximum,
 and critical temperature can be configured. There are alarms for high, low,
@@ -90,6 +137,7 @@ cannot be changed.
 Sysfs entries
 -------------
 
+======================= ===========================================
 temp1_input		Temperature (RO)
 temp1_min		Minimum temperature (RO or RW)
 temp1_max		Maximum temperature (RO or RW)
@@ -101,3 +149,4 @@ temp1_max_hyst		Maximum hysteresis temperature (RO)
 temp1_min_alarm		Temperature low alarm
 temp1_max_alarm		Temperature high alarm
 temp1_crit_alarm	Temperature critical alarm
+======================= ===========================================
diff --git a/Documentation/hwmon/k10temp b/Documentation/hwmon/k10temp.rst
index 254d2f55345a..12a86ba17de9 100644
--- a/Documentation/hwmon/k10temp
+++ b/Documentation/hwmon/k10temp.rst
@@ -2,42 +2,77 @@ Kernel driver k10temp
 =====================
 
 Supported chips:
+
 * AMD Family 10h processors:
+
   Socket F: Quad-Core/Six-Core/Embedded Opteron (but see below)
+
   Socket AM2+: Quad-Core Opteron, Phenom (II) X3/X4, Athlon X2 (but see below)
+
   Socket AM3: Quad-Core Opteron, Athlon/Phenom II X2/X3/X4, Sempron II
+
   Socket S1G3: Athlon II, Sempron, Turion II
+
 * AMD Family 11h processors:
+
   Socket S1G2: Athlon (X2), Sempron (X2), Turion X2 (Ultra)
+
 * AMD Family 12h processors: "Llano" (E2/A4/A6/A8-Series)
+
 * AMD Family 14h processors: "Brazos" (C/E/G/Z-Series)
+
 * AMD Family 15h processors: "Bulldozer" (FX-Series), "Trinity", "Kaveri", "Carrizo"
+
 * AMD Family 16h processors: "Kabini", "Mullins"
 
   Prefix: 'k10temp'
+
   Addresses scanned: PCI space
+
   Datasheets:
+
   BIOS and Kernel Developer's Guide (BKDG) For AMD Family 10h Processors:
+
     http://support.amd.com/us/Processor_TechDocs/31116.pdf
+
   BIOS and Kernel Developer's Guide (BKDG) for AMD Family 11h Processors:
+
     http://support.amd.com/us/Processor_TechDocs/41256.pdf
+
   BIOS and Kernel Developer's Guide (BKDG) for AMD Family 12h Processors:
+
     http://support.amd.com/us/Processor_TechDocs/41131.pdf
+
   BIOS and Kernel Developer's Guide (BKDG) for AMD Family 14h Models 00h-0Fh Processors:
+
     http://support.amd.com/us/Processor_TechDocs/43170.pdf
+
   Revision Guide for AMD Family 10h Processors:
+
     http://support.amd.com/us/Processor_TechDocs/41322.pdf
+
   Revision Guide for AMD Family 11h Processors:
+
     http://support.amd.com/us/Processor_TechDocs/41788.pdf
+
   Revision Guide for AMD Family 12h Processors:
+
     http://support.amd.com/us/Processor_TechDocs/44739.pdf
+
   Revision Guide for AMD Family 14h Models 00h-0Fh Processors:
+
     http://support.amd.com/us/Processor_TechDocs/47534.pdf
+
   AMD Family 11h Processor Power and Thermal Data Sheet for Notebooks:
+
     http://support.amd.com/us/Processor_TechDocs/43373.pdf
+
   AMD Family 10h Server and Workstation Processor Power and Thermal Data Sheet:
+
     http://support.amd.com/us/Processor_TechDocs/43374.pdf
+
   AMD Family 10h Desktop Processor Power and Thermal Data Sheet:
+
     http://support.amd.com/us/Processor_TechDocs/43375.pdf
 
 Author: Clemens Ladisch <clemens@ladisch.de>
@@ -60,7 +95,7 @@ are using an AM3 processor on an AM2+ mainboard, you can safely use the
 
 There is one temperature measurement value, available as temp1_input in
 sysfs. It is measured in degrees Celsius with a resolution of 1/8th degree.
-Please note that it is defined as a relative value; to quote the AMD manual:
+Please note that it is defined as a relative value; to quote the AMD manual::
 
   Tctl is the processor temperature control value, used by the platform to
   control cooling systems. Tctl is a non-physical temperature on an
diff --git a/Documentation/hwmon/k8temp b/Documentation/hwmon/k8temp.rst
index 716dc24c7237..72da12aa17e5 100644
--- a/Documentation/hwmon/k8temp
+++ b/Documentation/hwmon/k8temp.rst
@@ -2,12 +2,17 @@ Kernel driver k8temp
 ====================
 
 Supported chips:
+
   * AMD Athlon64/FX or Opteron CPUs
+
     Prefix: 'k8temp'
+
     Addresses scanned: PCI space
+
     Datasheet: http://support.amd.com/us/Processor_TechDocs/32559.pdf
 
 Author: Rudolf Marek
+
 Contact: Rudolf Marek <r.marek@assembler.cz>
 
 Description
@@ -27,10 +32,12 @@ implemented sensors.
 
 Mapping of /sys files is as follows:
 
-temp1_input - temperature of Core 0 and "place" 0
-temp2_input - temperature of Core 0 and "place" 1
-temp3_input - temperature of Core 1 and "place" 0
-temp4_input - temperature of Core 1 and "place" 1
+============= ===================================
+temp1_input   temperature of Core 0 and "place" 0
+temp2_input   temperature of Core 0 and "place" 1
+temp3_input   temperature of Core 1 and "place" 0
+temp4_input   temperature of Core 1 and "place" 1
+============= ===================================
 
 Temperatures are measured in degrees Celsius and measurement resolution is
 1 degree C. It is expected that future CPU will have better resolution. The
@@ -48,7 +55,7 @@ computed temperature called TControl, which must be lower than TControlMax.
 
 The relationship is following:
 
-temp1_input - TjOffset*2 < TControlMax,
+	temp1_input - TjOffset*2 < TControlMax,
 
 TjOffset is not yet exported by the driver, TControlMax is usually
 70 degrees C. The rule of the thumb -> CPU temperature should not cross
diff --git a/Documentation/hwmon/lineage-pem b/Documentation/hwmon/lineage-pem.rst
index 83b2ddc160c8..10c271dc20e8 100644
--- a/Documentation/hwmon/lineage-pem
+++ b/Documentation/hwmon/lineage-pem.rst
@@ -2,11 +2,16 @@ Kernel driver lineage-pem
 =========================
 
 Supported devices:
+
   * Lineage Compact Power Line Power Entry Modules
+
     Prefix: 'lineage-pem'
+
     Addresses scanned: -
+
     Documentation:
-        http://www.lineagepower.com/oem/pdf/CPLI2C.pdf
+
+	http://www.lineagepower.com/oem/pdf/CPLI2C.pdf
 
 Author: Guenter Roeck <linux@roeck-us.net>
 
@@ -31,9 +36,10 @@ which can be safely used to identify the chip. You will have to instantiate
 the devices explicitly.
 
 Example: the following will load the driver for a Lineage PEM at address 0x40
-on I2C bus #1:
-$ modprobe lineage-pem
-$ echo lineage-pem 0x40 > /sys/bus/i2c/devices/i2c-1/new_device
+on I2C bus #1::
+
+	$ modprobe lineage-pem
+	$ echo lineage-pem 0x40 > /sys/bus/i2c/devices/i2c-1/new_device
 
 All Lineage CPL power entry modules have a built-in I2C bus master selector
 (PCA9541). To ensure device access, this driver should only be used as client
@@ -51,6 +57,7 @@ Input voltage, input current, input power, and fan speed measurement is only
 supported on newer devices. The driver detects if those attributes are supported,
 and only creates respective sysfs entries if they are.
 
+======================= ===============================
 in1_input		Output voltage (mV)
 in1_min_alarm		Output undervoltage alarm
 in1_max_alarm		Output overvoltage alarm
@@ -75,3 +82,4 @@ temp1_crit
 temp1_alarm
 temp1_crit_alarm
 temp1_fault
+======================= ===============================
diff --git a/Documentation/hwmon/lm25066 b/Documentation/hwmon/lm25066.rst
index 51b32aa203a8..da15e3094c8c 100644
--- a/Documentation/hwmon/lm25066
+++ b/Documentation/hwmon/lm25066.rst
@@ -2,34 +2,62 @@ Kernel driver lm25066
 =====================
 
 Supported chips:
+
   * TI LM25056
+
     Prefix: 'lm25056'
+
     Addresses scanned: -
+
     Datasheets:
+
 	http://www.ti.com/lit/gpn/lm25056
+
 	http://www.ti.com/lit/gpn/lm25056a
+
   * National Semiconductor LM25066
+
     Prefix: 'lm25066'
+
     Addresses scanned: -
+
     Datasheets:
+
 	http://www.national.com/pf/LM/LM25066.html
+
 	http://www.national.com/pf/LM/LM25066A.html
+
   * National Semiconductor LM5064
+
     Prefix: 'lm5064'
+
     Addresses scanned: -
+
     Datasheet:
+
 	http://www.national.com/pf/LM/LM5064.html
+
   * National Semiconductor LM5066
+
     Prefix: 'lm5066'
+
     Addresses scanned: -
+
     Datasheet:
+
 	http://www.national.com/pf/LM/LM5066.html
+
   * Texas Instruments LM5066I
+
     Prefix: 'lm5066i'
+
     Addresses scanned: -
+
 	Datasheet:
+
     http://www.ti.com/product/LM5066I
 
+
 Author: Guenter Roeck <linux@roeck-us.net>
 
 
@@ -41,7 +69,7 @@ LM25066, LM5064, and LM5066/LM5066I Power Management, Monitoring,
 Control, and Protection ICs.
 
 The driver is a client driver to the core PMBus driver. Please see
-Documentation/hwmon/pmbus for details on PMBus client drivers.
+Documentation/hwmon/pmbus.rst for details on PMBus client drivers.
 
 
 Usage Notes
@@ -64,6 +92,7 @@ Sysfs entries
 The following attributes are supported. Limits are read-write; all other
 attributes are read-only.
 
+======================= =======================================================
 in1_label		"vin"
 in1_input		Measured input voltage.
 in1_average		Average measured input voltage.
@@ -105,3 +134,4 @@ temp1_max		Maximum temperature.
 temp1_crit		Critical high temperature.
 temp1_max_alarm		Chip temperature high alarm.
 temp1_crit_alarm	Chip temperature critical high alarm.
+======================= =======================================================
diff --git a/Documentation/hwmon/lm63 b/Documentation/hwmon/lm63.rst
index 4a00461512a6..f478132b0408 100644
--- a/Documentation/hwmon/lm63
+++ b/Documentation/hwmon/lm63.rst
@@ -2,26 +2,43 @@ Kernel driver lm63
 ==================
 
 Supported chips:
+
   * National Semiconductor LM63
+
     Prefix: 'lm63'
+
     Addresses scanned: I2C 0x4c
+
     Datasheet: Publicly available at the National Semiconductor website
-               http://www.national.com/pf/LM/LM63.html
+
+	       http://www.national.com/pf/LM/LM63.html
+
   * National Semiconductor LM64
+
     Prefix: 'lm64'
+
     Addresses scanned: I2C 0x18 and 0x4e
+
     Datasheet: Publicly available at the National Semiconductor website
-               http://www.national.com/pf/LM/LM64.html
+
+	       http://www.national.com/pf/LM/LM64.html
+
   * National Semiconductor LM96163
+
     Prefix: 'lm96163'
+
     Addresses scanned: I2C 0x4c
+
     Datasheet: Publicly available at the National Semiconductor website
-               http://www.national.com/pf/LM/LM96163.html
+
+	       http://www.national.com/pf/LM/LM96163.html
+
 
 Author: Jean Delvare <jdelvare@suse.de>
 
 Thanks go to Tyan and especially Alex Buckingham for setting up a remote
 access to their S4882 test platform for this driver.
+
   http://www.tyan.com/
 
 Description
@@ -32,6 +49,7 @@ and control.
 
 The LM63 is basically an LM86 with fan speed monitoring and control
 capabilities added. It misses some of the LM86 features though:
+
  - No low limit for local temperature.
  - No critical limit for local temperature.
  - Critical limit for remote temperature can be changed only once. We
diff --git a/Documentation/hwmon/lm70 b/Documentation/hwmon/lm70.rst
index c3a1f2ea017d..f259bc1fcd91 100644
--- a/Documentation/hwmon/lm70
+++ b/Documentation/hwmon/lm70.rst
@@ -2,19 +2,30 @@ Kernel driver lm70
 ==================
 
 Supported chips:
+
   * National Semiconductor LM70
+
     Datasheet: http://www.national.com/pf/LM/LM70.html
+
   * Texas Instruments TMP121/TMP123
+
     Information: http://focus.ti.com/docs/prod/folders/print/tmp121.html
+
   * Texas Instruments TMP122/TMP124
+
     Information: http://www.ti.com/product/tmp122
+
   * National Semiconductor LM71
+
     Datasheet: http://www.ti.com/product/LM71
+
   * National Semiconductor LM74
+
     Datasheet: http://www.ti.com/product/LM74
 
+
 Author:
-        Kaiwan N Billimoria <kaiwan@designergraphix.com>
+	Kaiwan N Billimoria <kaiwan@designergraphix.com>
 
 Description
 -----------
diff --git a/Documentation/hwmon/lm73 b/Documentation/hwmon/lm73.rst
index 8af059dcb642..1d6a46844e85 100644
--- a/Documentation/hwmon/lm73
+++ b/Documentation/hwmon/lm73.rst
@@ -2,13 +2,20 @@ Kernel driver lm73
 ==================
 
 Supported chips:
+
   * Texas Instruments LM73
+
     Prefix: 'lm73'
+
     Addresses scanned: I2C 0x48, 0x49, 0x4a, 0x4c, 0x4d, and 0x4e
+
     Datasheet: Publicly available at the Texas Instruments website
-               http://www.ti.com/product/lm73
+
+	       http://www.ti.com/product/lm73
+
 
 Author: Guillaume Ligneul <guillaume.ligneul@gmail.com>
+
 Documentation: Chris Verges <kg4ysn@gmail.com>
 
 
@@ -29,17 +36,18 @@ conversion time via the 'update_interval' sysfs attribute for the
 device.  This attribute will normalize ranges of input values to the
 maximum times defined for the resolution in the datasheet.
 
+    ============= ============= ============
     Resolution    Conv. Time    Input Range
     (C/LSB)       (msec)        (msec)
-    --------------------------------------
+    ============= ============= ============
     0.25          14             0..14
     0.125         28            15..28
     0.0625        56            29..56
     0.03125       112           57..infinity
-    --------------------------------------
+    ============= ============= ============
 
 The following examples show how the 'update_interval' attribute can be
-used to change the conversion time:
+used to change the conversion time::
 
     $ echo 0 > update_interval
     $ cat update_interval
diff --git a/Documentation/hwmon/lm75 b/Documentation/hwmon/lm75.rst
index 010583608f12..ba8acbd2a6cb 100644
--- a/Documentation/hwmon/lm75
+++ b/Documentation/hwmon/lm75.rst
@@ -2,68 +2,132 @@ Kernel driver lm75
 ==================
 
 Supported chips:
+
   * National Semiconductor LM75
+
     Prefix: 'lm75'
+
     Addresses scanned: I2C 0x48 - 0x4f
+
     Datasheet: Publicly available at the National Semiconductor website
-               http://www.national.com/
+
+	       http://www.national.com/
+
   * National Semiconductor LM75A
+
     Prefix: 'lm75a'
+
     Addresses scanned: I2C 0x48 - 0x4f
+
     Datasheet: Publicly available at the National Semiconductor website
-               http://www.national.com/
+
+	       http://www.national.com/
+
   * Dallas Semiconductor (now Maxim) DS75, DS1775, DS7505
+
     Prefixes: 'ds75', 'ds1775', 'ds7505'
+
     Addresses scanned: none
+
     Datasheet: Publicly available at the Maxim website
-               http://www.maximintegrated.com/
+
+	       http://www.maximintegrated.com/
+
   * Maxim MAX6625, MAX6626, MAX31725, MAX31726
+
     Prefixes: 'max6625', 'max6626', 'max31725', 'max31726'
+
     Addresses scanned: none
+
     Datasheet: Publicly available at the Maxim website
-               http://www.maxim-ic.com/
+
+	       http://www.maxim-ic.com/
+
   * Microchip (TelCom) TCN75
+
     Prefix: 'tcn75'
+
     Addresses scanned: none
+
     Datasheet: Publicly available at the Microchip website
-               http://www.microchip.com/
+
+	       http://www.microchip.com/
+
   * Microchip MCP9800, MCP9801, MCP9802, MCP9803
+
     Prefix: 'mcp980x'
+
     Addresses scanned: none
+
     Datasheet: Publicly available at the Microchip website
-               http://www.microchip.com/
+
+	       http://www.microchip.com/
+
   * Analog Devices ADT75
+
     Prefix: 'adt75'
+
     Addresses scanned: none
+
     Datasheet: Publicly available at the Analog Devices website
-               http://www.analog.com/adt75
+
+	       http://www.analog.com/adt75
+
   * ST Microelectronics STDS75
+
     Prefix: 'stds75'
+
     Addresses scanned: none
+
     Datasheet: Publicly available at the ST website
-               http://www.st.com/internet/analog/product/121769.jsp
+
+	       http://www.st.com/internet/analog/product/121769.jsp
+
   * ST Microelectronics STLM75
+
     Prefix: 'stlm75'
+
     Addresses scanned: none
+
     Datasheet: Publicly available at the ST website
+
 	       https://www.st.com/resource/en/datasheet/stlm75.pdf
-  * Texas Instruments TMP100, TMP101, TMP105, TMP112, TMP75, TMP75C, TMP175, TMP275
-    Prefixes: 'tmp100', 'tmp101', 'tmp105', 'tmp112', 'tmp175', 'tmp75', 'tmp75c', 'tmp275'
+
+  * Texas Instruments TMP100, TMP101, TMP105, TMP112, TMP75, TMP75B, TMP75C, TMP175, TMP275
+
+    Prefixes: 'tmp100', 'tmp101', 'tmp105', 'tmp112', 'tmp175', 'tmp75', 'tmp75b', 'tmp75c', 'tmp275'
+
     Addresses scanned: none
+
     Datasheet: Publicly available at the Texas Instruments website
-               http://www.ti.com/product/tmp100
-               http://www.ti.com/product/tmp101
-               http://www.ti.com/product/tmp105
-               http://www.ti.com/product/tmp112
-               http://www.ti.com/product/tmp75
-               http://www.ti.com/product/tmp75c
-               http://www.ti.com/product/tmp175
-               http://www.ti.com/product/tmp275
+
+	       http://www.ti.com/product/tmp100
+
+	       http://www.ti.com/product/tmp101
+
+	       http://www.ti.com/product/tmp105
+
+	       http://www.ti.com/product/tmp112
+
+	       http://www.ti.com/product/tmp75
+
+	       http://www.ti.com/product/tmp75b
+
+	       http://www.ti.com/product/tmp75c
+
+	       http://www.ti.com/product/tmp175
+
+	       http://www.ti.com/product/tmp275
+
   * NXP LM75B
+
     Prefix: 'lm75b'
+
     Addresses scanned: none
+
     Datasheet: Publicly available at the NXP website
-               http://www.nxp.com/documents/data_sheet/LM75B.pdf
+
+	       http://www.nxp.com/documents/data_sheet/LM75B.pdf
 
 Author: Frodo Looijaard <frodol@dds.nl>
 
diff --git a/Documentation/hwmon/lm77 b/Documentation/hwmon/lm77.rst
index bfc915fe3639..4ed3fe6b999a 100644
--- a/Documentation/hwmon/lm77
+++ b/Documentation/hwmon/lm77.rst
@@ -2,11 +2,17 @@ Kernel driver lm77
 ==================
 
 Supported chips:
+
   * National Semiconductor LM77
+
     Prefix: 'lm77'
+
     Addresses scanned: I2C 0x48 - 0x4b
+
     Datasheet: Publicly available at the National Semiconductor website
-               http://www.national.com/
+
+	       http://www.national.com/
+
 
 Author: Andras BALI <drewie@freemail.hu>
 
@@ -25,6 +31,7 @@ register on the chip, which means that the relative difference between
 the limit and its hysteresis is always the same for all 3 limits.
 
 This implementation detail implies the following:
+
 * When setting a limit, its hysteresis will automatically follow, the
   difference staying unchanged. For example, if the old critical limit
   was 80 degrees C, and the hysteresis was 75 degrees C, and you change
diff --git a/Documentation/hwmon/lm78 b/Documentation/hwmon/lm78.rst
index 4dd47731789f..cb7a4832f35e 100644
--- a/Documentation/hwmon/lm78
+++ b/Documentation/hwmon/lm78.rst
@@ -2,19 +2,31 @@ Kernel driver lm78
 ==================
 
 Supported chips:
+
   * National Semiconductor LM78 / LM78-J
+
     Prefix: 'lm78'
+
     Addresses scanned: I2C 0x28 - 0x2f, ISA 0x290 (8 I/O ports)
+
     Datasheet: Publicly available at the National Semiconductor website
-               http://www.national.com/
+
+	       http://www.national.com/
+
   * National Semiconductor LM79
+
     Prefix: 'lm79'
+
     Addresses scanned: I2C 0x28 - 0x2f, ISA 0x290 (8 I/O ports)
+
     Datasheet: Publicly available at the National Semiconductor website
-               http://www.national.com/
 
-Authors: Frodo Looijaard <frodol@dds.nl>
-         Jean Delvare <jdelvare@suse.de>
+	       http://www.national.com/
+
+
+Authors:
+	- Frodo Looijaard <frodol@dds.nl>
+	- Jean Delvare <jdelvare@suse.de>
 
 Description
 -----------
diff --git a/Documentation/hwmon/lm80 b/Documentation/hwmon/lm80.rst
index a60b43efc32b..c53186abd82e 100644
--- a/Documentation/hwmon/lm80
+++ b/Documentation/hwmon/lm80.rst
@@ -2,20 +2,31 @@ Kernel driver lm80
 ==================
 
 Supported chips:
+
   * National Semiconductor LM80
+
     Prefix: 'lm80'
+
     Addresses scanned: I2C 0x28 - 0x2f
+
     Datasheet: Publicly available at the National Semiconductor website
-               http://www.national.com/
+
+	       http://www.national.com/
+
   * National Semiconductor LM96080
+
     Prefix: 'lm96080'
+
     Addresses scanned: I2C 0x28 - 0x2f
+
     Datasheet: Publicly available at the National Semiconductor website
-               http://www.national.com/
+
+	       http://www.national.com/
+
 
 Authors:
-        Frodo Looijaard <frodol@dds.nl>,
-        Philip Edelbrock <phil@netroedge.com>
+       - Frodo Looijaard <frodol@dds.nl>,
+       - Philip Edelbrock <phil@netroedge.com>
 
 Description
 -----------
diff --git a/Documentation/hwmon/lm83 b/Documentation/hwmon/lm83.rst
index 50be5cb26de9..ecf83819960e 100644
--- a/Documentation/hwmon/lm83
+++ b/Documentation/hwmon/lm83.rst
@@ -2,16 +2,24 @@ Kernel driver lm83
 ==================
 
 Supported chips:
+
   * National Semiconductor LM83
+
     Prefix: 'lm83'
+
     Addresses scanned: I2C 0x18 - 0x1a, 0x29 - 0x2b, 0x4c - 0x4e
+
     Datasheet: Publicly available at the National Semiconductor website
-               http://www.national.com/pf/LM/LM83.html
+
+	       http://www.national.com/pf/LM/LM83.html
+
   * National Semiconductor LM82
+
     Addresses scanned: I2C 0x18 - 0x1a, 0x29 - 0x2b, 0x4c - 0x4e
+
     Datasheet: Publicly available at the National Semiconductor website
-               http://www.national.com/pf/LM/LM82.html
 
+	       http://www.national.com/pf/LM/LM82.html
 
 Author: Jean Delvare <jdelvare@suse.de>
 
@@ -34,13 +42,17 @@ fact that any of these motherboards do actually have an LM83, please
 contact us. Note that the LM90 can easily be misdetected as a LM83.
 
 Confirmed motherboards:
+    ===		=====
     SBS         P014
     SBS         PSL09
+    ===		=====
 
 Unconfirmed motherboards:
+    =========== ==========
     Gigabyte    GA-8IK1100
     Iwill       MPX2
     Soltek      SL-75DRV5
+    =========== ==========
 
 The LM82 is confirmed to have been found on most AMD Geode reference
 designs and test platforms.
diff --git a/Documentation/hwmon/lm85 b/Documentation/hwmon/lm85.rst
index 2329c383efe4..faa92f54431c 100644
--- a/Documentation/hwmon/lm85
+++ b/Documentation/hwmon/lm85.rst
@@ -2,49 +2,85 @@ Kernel driver lm85
 ==================
 
 Supported chips:
+
   * National Semiconductor LM85 (B and C versions)
+
     Prefix: 'lm85b' or 'lm85c'
+
     Addresses scanned: I2C 0x2c, 0x2d, 0x2e
+
     Datasheet: http://www.national.com/pf/LM/LM85.html
+
   * Texas Instruments LM96000
+
     Prefix: 'lm9600'
+
     Addresses scanned: I2C 0x2c, 0x2d, 0x2e
+
     Datasheet: http://www.ti.com/lit/ds/symlink/lm96000.pdf
+
   * Analog Devices ADM1027
+
     Prefix: 'adm1027'
+
     Addresses scanned: I2C 0x2c, 0x2d, 0x2e
+
     Datasheet: http://www.onsemi.com/PowerSolutions/product.do?id=ADM1027
+
   * Analog Devices ADT7463
+
     Prefix: 'adt7463'
+
     Addresses scanned: I2C 0x2c, 0x2d, 0x2e
+
     Datasheet: http://www.onsemi.com/PowerSolutions/product.do?id=ADT7463
+
   * Analog Devices ADT7468
+
     Prefix: 'adt7468'
+
     Addresses scanned: I2C 0x2c, 0x2d, 0x2e
+
     Datasheet: http://www.onsemi.com/PowerSolutions/product.do?id=ADT7468
+
   * SMSC EMC6D100, SMSC EMC6D101
+
     Prefix: 'emc6d100'
+
     Addresses scanned: I2C 0x2c, 0x2d, 0x2e
-    Datasheet: http://www.smsc.com/media/Downloads_Public/discontinued/6d100.pdf 
+
+    Datasheet: http://www.smsc.com/media/Downloads_Public/discontinued/6d100.pdf
+
   * SMSC EMC6D102
+
     Prefix: 'emc6d102'
+
     Addresses scanned: I2C 0x2c, 0x2d, 0x2e
+
     Datasheet: http://www.smsc.com/main/catalog/emc6d102.html
+
   * SMSC EMC6D103
+
     Prefix: 'emc6d103'
+
     Addresses scanned: I2C 0x2c, 0x2d, 0x2e
+
     Datasheet: http://www.smsc.com/main/catalog/emc6d103.html
+
   * SMSC EMC6D103S
+
     Prefix: 'emc6d103s'
+
     Addresses scanned: I2C 0x2c, 0x2d, 0x2e
+
     Datasheet: http://www.smsc.com/main/catalog/emc6d103s.html
 
 Authors:
-        Philip Pokorny <ppokorny@penguincomputing.com>,
-        Frodo Looijaard <frodol@dds.nl>,
-        Richard Barrington <rich_b_nz@clear.net.nz>,
-        Margit Schubert-While <margitsw@t-online.de>,
-        Justin Thiessen <jthiessen@penguincomputing.com>
+       - Philip Pokorny <ppokorny@penguincomputing.com>,
+       - Frodo Looijaard <frodol@dds.nl>,
+       - Richard Barrington <rich_b_nz@clear.net.nz>,
+       - Margit Schubert-While <margitsw@t-online.de>,
+       - Justin Thiessen <jthiessen@penguincomputing.com>
 
 Description
 -----------
@@ -177,38 +213,50 @@ Each temperature sensor is associated with a Zone. There are three
 sensors and therefore three zones (# 1, 2 and 3). Each zone has the following
 temperature configuration points:
 
-* temp#_auto_temp_off - temperature below which fans should be off or spinning very low.
-* temp#_auto_temp_min - temperature over which fans start to spin.
-* temp#_auto_temp_max - temperature when fans spin at full speed.
-* temp#_auto_temp_crit - temperature when all fans will run full speed.
+* temp#_auto_temp_off
+	- temperature below which fans should be off or spinning very low.
+* temp#_auto_temp_min
+	- temperature over which fans start to spin.
+* temp#_auto_temp_max
+	- temperature when fans spin at full speed.
+* temp#_auto_temp_crit
+	- temperature when all fans will run full speed.
 
-* PWM Control
+PWM Control
+^^^^^^^^^^^
 
 There are three PWM outputs. The LM85 datasheet suggests that the
 pwm3 output control both fan3 and fan4. Each PWM can be individually
 configured and assigned to a zone for its control value. Each PWM can be
 configured individually according to the following options.
 
-* pwm#_auto_pwm_min - this specifies the PWM value for temp#_auto_temp_off
-                      temperature. (PWM value from 0 to 255)
+* pwm#_auto_pwm_min
+	- this specifies the PWM value for temp#_auto_temp_off
+	  temperature. (PWM value from 0 to 255)
+
+* pwm#_auto_pwm_minctl
+	- this flags selects for temp#_auto_temp_off temperature
+	  the behaviour of fans. Write 1 to let fans spinning at
+	  pwm#_auto_pwm_min or write 0 to let them off.
 
-* pwm#_auto_pwm_minctl - this flags selects for temp#_auto_temp_off temperature
-                         the behaviour of fans. Write 1 to let fans spinning at
-			 pwm#_auto_pwm_min or write 0 to let them off.
+.. note::
 
-NOTE: It has been reported that there is a bug in the LM85 that causes the flag
-to be associated with the zones not the PWMs. This contradicts all the
-published documentation. Setting pwm#_min_ctl in this case actually affects all
-PWMs controlled by zone '#'.
+	It has been reported that there is a bug in the LM85 that causes
+	the flag to be associated with the zones not the PWMs. This
+	contradicts all the published documentation. Setting pwm#_min_ctl
+	in this case actually affects all PWMs controlled by zone '#'.
 
-* PWM Controlling Zone selection
+PWM Controlling Zone selection
+^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
 
-* pwm#_auto_channels - controls zone that is associated with PWM
+* pwm#_auto_channels
+	- controls zone that is associated with PWM
 
 Configuration choices:
 
-   Value     Meaning
-  ------  ------------------------------------------------
+========== =============================================
+Value      Meaning
+========== =============================================
       1    Controlled by Zone 1
       2    Controlled by Zone 2
       3    Controlled by Zone 3
@@ -217,6 +265,7 @@ Configuration choices:
       0    PWM always 0%  (off)
      -1    PWM always 100%  (full on)
      -2    Manual control (write to 'pwm#' to set)
+========== =============================================
 
 The National LM85's have two vendor specific configuration
 features. Tach. mode and Spinup Control. For more details on these,
diff --git a/Documentation/hwmon/lm87 b/Documentation/hwmon/lm87.rst
index a2339fd9acb9..72fcb577ef2a 100644
--- a/Documentation/hwmon/lm87
+++ b/Documentation/hwmon/lm87.rst
@@ -2,23 +2,32 @@ Kernel driver lm87
 ==================
 
 Supported chips:
+
   * National Semiconductor LM87
+
     Prefix: 'lm87'
+
     Addresses scanned: I2C 0x2c - 0x2e
+
     Datasheet: http://www.national.com/pf/LM/LM87.html
+
   * Analog Devices ADM1024
+
     Prefix: 'adm1024'
+
     Addresses scanned: I2C 0x2c - 0x2e
+
     Datasheet: http://www.analog.com/en/prod/0,2877,ADM1024,00.html
 
+
 Authors:
-        Frodo Looijaard <frodol@dds.nl>,
-        Philip Edelbrock <phil@netroedge.com>,
-        Mark Studebaker <mdsxyz123@yahoo.com>,
-        Stephen Rousset <stephen.rousset@rocketlogix.com>,
-        Dan Eaton <dan.eaton@rocketlogix.com>,
-        Jean Delvare <jdelvare@suse.de>,
-        Original 2.6 port Jeff Oliver
+	- Frodo Looijaard <frodol@dds.nl>,
+	- Philip Edelbrock <phil@netroedge.com>,
+	- Mark Studebaker <mdsxyz123@yahoo.com>,
+	- Stephen Rousset <stephen.rousset@rocketlogix.com>,
+	- Dan Eaton <dan.eaton@rocketlogix.com>,
+	- Jean Delvare <jdelvare@suse.de>,
+	- Original 2.6 port Jeff Oliver
 
 Description
 -----------
diff --git a/Documentation/hwmon/lm90 b/Documentation/hwmon/lm90.rst
index 8122675d30f6..953315987c06 100644
--- a/Documentation/hwmon/lm90
+++ b/Documentation/hwmon/lm90.rst
@@ -2,132 +2,256 @@ Kernel driver lm90
 ==================
 
 Supported chips:
+
   * National Semiconductor LM90
+
     Prefix: 'lm90'
+
     Addresses scanned: I2C 0x4c
+
     Datasheet: Publicly available at the National Semiconductor website
-               http://www.national.com/pf/LM/LM90.html
+
+	       http://www.national.com/pf/LM/LM90.html
+
   * National Semiconductor LM89
+
     Prefix: 'lm89' (no auto-detection)
+
     Addresses scanned: I2C 0x4c and 0x4d
+
     Datasheet: Publicly available at the National Semiconductor website
-               http://www.national.com/mpf/LM/LM89.html
+
+	       http://www.national.com/mpf/LM/LM89.html
+
   * National Semiconductor LM99
+
     Prefix: 'lm99'
+
     Addresses scanned: I2C 0x4c and 0x4d
+
     Datasheet: Publicly available at the National Semiconductor website
-               http://www.national.com/pf/LM/LM99.html
+
+	       http://www.national.com/pf/LM/LM99.html
+
   * National Semiconductor LM86
+
     Prefix: 'lm86'
+
     Addresses scanned: I2C 0x4c
+
     Datasheet: Publicly available at the National Semiconductor website
-               http://www.national.com/mpf/LM/LM86.html
+
+	       http://www.national.com/mpf/LM/LM86.html
+
   * Analog Devices ADM1032
+
     Prefix: 'adm1032'
+
     Addresses scanned: I2C 0x4c and 0x4d
+
     Datasheet: Publicly available at the ON Semiconductor website
-               http://www.onsemi.com/PowerSolutions/product.do?id=ADM1032
+
+	       http://www.onsemi.com/PowerSolutions/product.do?id=ADM1032
+
   * Analog Devices ADT7461
+
     Prefix: 'adt7461'
+
     Addresses scanned: I2C 0x4c and 0x4d
+
     Datasheet: Publicly available at the ON Semiconductor website
-               http://www.onsemi.com/PowerSolutions/product.do?id=ADT7461
+
+	       http://www.onsemi.com/PowerSolutions/product.do?id=ADT7461
+
   * Analog Devices ADT7461A
+
     Prefix: 'adt7461a'
+
     Addresses scanned: I2C 0x4c and 0x4d
+
     Datasheet: Publicly available at the ON Semiconductor website
-               http://www.onsemi.com/PowerSolutions/product.do?id=ADT7461A
+
+	       http://www.onsemi.com/PowerSolutions/product.do?id=ADT7461A
+
   * ON Semiconductor NCT1008
+
     Prefix: 'nct1008'
+
     Addresses scanned: I2C 0x4c and 0x4d
+
     Datasheet: Publicly available at the ON Semiconductor website
-               http://www.onsemi.com/PowerSolutions/product.do?id=NCT1008
+
+	       http://www.onsemi.com/PowerSolutions/product.do?id=NCT1008
+
   * Maxim MAX6646
+
     Prefix: 'max6646'
+
     Addresses scanned: I2C 0x4d
+
     Datasheet: Publicly available at the Maxim website
-               http://www.maxim-ic.com/quick_view2.cfm/qv_pk/3497
+
+	       http://www.maxim-ic.com/quick_view2.cfm/qv_pk/3497
+
   * Maxim MAX6647
+
     Prefix: 'max6646'
+
     Addresses scanned: I2C 0x4e
+
     Datasheet: Publicly available at the Maxim website
-               http://www.maxim-ic.com/quick_view2.cfm/qv_pk/3497
+
+	       http://www.maxim-ic.com/quick_view2.cfm/qv_pk/3497
+
   * Maxim MAX6648
+
     Prefix: 'max6646'
+
     Addresses scanned: I2C 0x4c
+
     Datasheet: Publicly available at the Maxim website
-               http://www.maxim-ic.com/quick_view2.cfm/qv_pk/3500
+
+	       http://www.maxim-ic.com/quick_view2.cfm/qv_pk/3500
+
   * Maxim MAX6649
+
     Prefix: 'max6646'
+
     Addresses scanned: I2C 0x4c
+
     Datasheet: Publicly available at the Maxim website
-               http://www.maxim-ic.com/quick_view2.cfm/qv_pk/3497
+
+	       http://www.maxim-ic.com/quick_view2.cfm/qv_pk/3497
+
   * Maxim MAX6657
+
     Prefix: 'max6657'
+
     Addresses scanned: I2C 0x4c
+
     Datasheet: Publicly available at the Maxim website
-               http://www.maxim-ic.com/quick_view2.cfm/qv_pk/2578
+
+	       http://www.maxim-ic.com/quick_view2.cfm/qv_pk/2578
+
   * Maxim MAX6658
+
     Prefix: 'max6657'
+
     Addresses scanned: I2C 0x4c
+
     Datasheet: Publicly available at the Maxim website
-               http://www.maxim-ic.com/quick_view2.cfm/qv_pk/2578
+
+	       http://www.maxim-ic.com/quick_view2.cfm/qv_pk/2578
+
   * Maxim MAX6659
+
     Prefix: 'max6659'
+
     Addresses scanned: I2C 0x4c, 0x4d, 0x4e
+
     Datasheet: Publicly available at the Maxim website
-               http://www.maxim-ic.com/quick_view2.cfm/qv_pk/2578
+
+	       http://www.maxim-ic.com/quick_view2.cfm/qv_pk/2578
+
   * Maxim MAX6680
+
     Prefix: 'max6680'
+
     Addresses scanned: I2C 0x18, 0x19, 0x1a, 0x29, 0x2a, 0x2b,
-                           0x4c, 0x4d and 0x4e
+
+			   0x4c, 0x4d and 0x4e
+
     Datasheet: Publicly available at the Maxim website
-               http://www.maxim-ic.com/quick_view2.cfm/qv_pk/3370
+
+	       http://www.maxim-ic.com/quick_view2.cfm/qv_pk/3370
+
   * Maxim MAX6681
+
     Prefix: 'max6680'
+
     Addresses scanned: I2C 0x18, 0x19, 0x1a, 0x29, 0x2a, 0x2b,
-                           0x4c, 0x4d and 0x4e
+
+			   0x4c, 0x4d and 0x4e
+
     Datasheet: Publicly available at the Maxim website
-               http://www.maxim-ic.com/quick_view2.cfm/qv_pk/3370
+
+	       http://www.maxim-ic.com/quick_view2.cfm/qv_pk/3370
+
   * Maxim MAX6692
+
     Prefix: 'max6646'
+
     Addresses scanned: I2C 0x4c
+
     Datasheet: Publicly available at the Maxim website
-               http://www.maxim-ic.com/quick_view2.cfm/qv_pk/3500
+
+	       http://www.maxim-ic.com/quick_view2.cfm/qv_pk/3500
+
   * Maxim MAX6695
+
     Prefix: 'max6695'
+
     Addresses scanned: I2C 0x18
+
     Datasheet: Publicly available at the Maxim website
-               http://www.maxim-ic.com/datasheet/index.mvp/id/4199
+
+	       http://www.maxim-ic.com/datasheet/index.mvp/id/4199
+
   * Maxim MAX6696
+
     Prefix: 'max6695'
+
     Addresses scanned: I2C 0x18, 0x19, 0x1a, 0x29, 0x2a, 0x2b,
-                           0x4c, 0x4d and 0x4e
+
+			   0x4c, 0x4d and 0x4e
+
     Datasheet: Publicly available at the Maxim website
-               http://www.maxim-ic.com/datasheet/index.mvp/id/4199
+
+	       http://www.maxim-ic.com/datasheet/index.mvp/id/4199
+
   * Winbond/Nuvoton W83L771W/G
+
     Prefix: 'w83l771'
+
     Addresses scanned: I2C 0x4c
+
     Datasheet: No longer available
+
   * Winbond/Nuvoton W83L771AWG/ASG
+
     Prefix: 'w83l771'
+
     Addresses scanned: I2C 0x4c
+
     Datasheet: Not publicly available, can be requested from Nuvoton
+
   * Philips/NXP SA56004X
+
     Prefix: 'sa56004'
+
     Addresses scanned: I2C 0x48 through 0x4F
+
     Datasheet: Publicly available at NXP website
-               http://ics.nxp.com/products/interface/datasheet/sa56004x.pdf
+
+	       http://ics.nxp.com/products/interface/datasheet/sa56004x.pdf
+
   * GMT G781
+
     Prefix: 'g781'
+
     Addresses scanned: I2C 0x4c, 0x4d
+
     Datasheet: Not publicly available from GMT
+
   * Texas Instruments TMP451
+
     Prefix: 'tmp451'
+
     Addresses scanned: I2C 0x4c
+
     Datasheet: Publicly available at TI website
-               http://www.ti.com/litv/pdf/sbos686
 
+	       http://www.ti.com/litv/pdf/sbos686
 
 Author: Jean Delvare <jdelvare@suse.de>
 
diff --git a/Documentation/hwmon/lm92 b/Documentation/hwmon/lm92.rst
index cfa99a353b8c..c131b923ed36 100644
--- a/Documentation/hwmon/lm92
+++ b/Documentation/hwmon/lm92.rst
@@ -2,22 +2,35 @@ Kernel driver lm92
 ==================
 
 Supported chips:
+
   * National Semiconductor LM92
+
     Prefix: 'lm92'
+
     Addresses scanned: I2C 0x48 - 0x4b
+
     Datasheet: http://www.national.com/pf/LM/LM92.html
+
   * National Semiconductor LM76
+
     Prefix: 'lm92'
+
     Addresses scanned: none, force parameter needed
+
     Datasheet: http://www.national.com/pf/LM/LM76.html
+
   * Maxim MAX6633/MAX6634/MAX6635
+
     Prefix: 'max6635'
+
     Addresses scanned: none, force parameter needed
+
     Datasheet: http://www.maxim-ic.com/quick_view2.cfm/qv_pk/3074
 
+
 Authors:
-        Abraham van der Merwe <abraham@2d3d.co.za>
-        Jean Delvare <jdelvare@suse.de>
+       - Abraham van der Merwe <abraham@2d3d.co.za>
+       - Jean Delvare <jdelvare@suse.de>
 
 
 Description
diff --git a/Documentation/hwmon/lm93 b/Documentation/hwmon/lm93.rst
index f3b2ad2ceb01..49d199b45b67 100644
--- a/Documentation/hwmon/lm93
+++ b/Documentation/hwmon/lm93.rst
@@ -2,20 +2,29 @@ Kernel driver lm93
 ==================
 
 Supported chips:
+
   * National Semiconductor LM93
+
     Prefix 'lm93'
+
     Addresses scanned: I2C 0x2c-0x2e
+
     Datasheet: http://www.national.com/ds.cgi/LM/LM93.pdf
+
   * National Semiconductor LM94
+
     Prefix 'lm94'
+
     Addresses scanned: I2C 0x2c-0x2e
+
     Datasheet: http://www.national.com/ds.cgi/LM/LM94.pdf
 
+
 Authors:
-	Mark M. Hoffman <mhoffman@lightlink.com>
-	Ported to 2.6 by Eric J. Bowersox <ericb@aspsys.com>
-	Adapted to 2.6.20 by Carsten Emde <ce@osadl.org>
-	Modified for mainline integration by Hans J. Koch <hjk@hansjkoch.de>
+	- Mark M. Hoffman <mhoffman@lightlink.com>
+	- Ported to 2.6 by Eric J. Bowersox <ericb@aspsys.com>
+	- Adapted to 2.6.20 by Carsten Emde <ce@osadl.org>
+	- Modified for mainline integration by Hans J. Koch <hjk@hansjkoch.de>
 
 Module Parameters
 -----------------
@@ -67,7 +76,8 @@ LM94 are not supported.
 User Interface
 --------------
 
-#PROCHOT:
+#PROCHOT
+^^^^^^^^
 
 The LM93 can monitor two #PROCHOT signals.  The results are found in the
 sysfs files prochot1, prochot2, prochot1_avg, prochot2_avg, prochot1_max,
@@ -86,7 +96,8 @@ prochot2_interval.  The values in these files specify the intervals for
 list will cause the driver to use the next largest interval.  The available
 intervals are (in seconds):
 
-#PROCHOT intervals: 0.73, 1.46, 2.9, 5.8, 11.7, 23.3, 46.6, 93.2, 186, 372
+#PROCHOT intervals:
+	0.73, 1.46, 2.9, 5.8, 11.7, 23.3, 46.6, 93.2, 186, 372
 
 It is possible to configure the LM93 to logically short the two #PROCHOT
 signals.  I.e. when #P1_PROCHOT is asserted, the LM93 will automatically
@@ -105,16 +116,15 @@ contains a value controlling the duty cycle for the PWM signal used when
 the override function is enabled.  This value ranges from 0 to 15, with 0
 indicating minimum duty cycle and 15 indicating maximum.
 
-#VRD_HOT:
+#VRD_HOT
+^^^^^^^^
 
 The LM93 can monitor two #VRD_HOT signals. The results are found in the
 sysfs files vrdhot1 and vrdhot2. There is one value per file: a boolean for
 which 1 indicates #VRD_HOT is asserted and 0 indicates it is negated. These
 files are read-only.
 
-Smart Tach Mode:
-
-(from the datasheet)
+Smart Tach Mode (from the datasheet)::
 
 	If a fan is driven using a low-side drive PWM, the tachometer
 	output of the fan is corrupted. The LM93 includes smart tachometer
@@ -127,7 +137,8 @@ the fan tachometer with a pwm) to the sysfs file fan<n>_smart_tach.  A zero
 will disable the function for that fan.  Note that Smart tach mode cannot be
 enabled if the PWM output frequency is 22500 Hz (see below).
 
-Manual PWM:
+Manual PWM
+^^^^^^^^^^
 
 The LM93 has a fixed or override mode for the two PWM outputs (although, there
 are still some conditions that will override even this mode - see section
@@ -141,7 +152,8 @@ will cause the driver to use the next largest value.  Also note: when manual
 PWM mode is disabled, the value of pwm1 and pwm2 indicates the current duty
 cycle chosen by the h/w.
 
-PWM Output Frequency:
+PWM Output Frequency
+^^^^^^^^^^^^^^^^^^^^
 
 The LM93 supports several different frequencies for the PWM output channels.
 The sysfs files pwm1_freq and pwm2_freq are used to select the frequency. The
@@ -149,9 +161,11 @@ frequency values are constrained by the hardware.  Selecting a value which is
 not available will cause the driver to use the next largest value.  Also note
 that this parameter has implications for the Smart Tach Mode (see above).
 
-PWM Output Frequencies (in Hz): 12, 36, 48, 60, 72, 84, 96, 22500 (default)
+PWM Output Frequencies (in Hz):
+	12, 36, 48, 60, 72, 84, 96, 22500 (default)
 
-Automatic PWM:
+Automatic PWM
+^^^^^^^^^^^^^
 
 The LM93 is capable of complex automatic fan control, with many different
 points of configuration.  To start, each PWM output can be bound to any
@@ -163,14 +177,16 @@ The eight control sources are: temp1-temp4 (aka "zones" in the datasheet),
 in the sysfs files pwm<n>_auto_channels, where a "1" enables the binding, and
 a "0" disables it. The h/w default is 0x0f (all temperatures bound).
 
-	0x01 - Temp 1
-	0x02 - Temp 2
-	0x04 - Temp 3
-	0x08 - Temp 4
-	0x10 - #PROCHOT 1
-	0x20 - #PROCHOT 2
-	0x40 - #VRDHOT 1
-	0x80 - #VRDHOT 2
+	====== ===========
+	0x01   Temp 1
+	0x02   Temp 2
+	0x04   Temp 3
+	0x08   Temp 4
+	0x10   #PROCHOT 1
+	0x20   #PROCHOT 2
+	0x40   #VRDHOT 1
+	0x80   #VRDHOT 2
+	====== ===========
 
 The function y = f(x) takes a source temperature x to a PWM output y.  This
 function of the LM93 is derived from a base temperature and a table of 12
@@ -180,7 +196,9 @@ degrees C, with the value of offset <i> for temperature value <n> being
 contained in the file temp<n>_auto_offset<i>.  E.g. if the base temperature
 is 40C:
 
+     ========== ======================= =============== =======
      offset #	temp<n>_auto_offset<i>	range		pwm
+     ========== ======================= =============== =======
 	 1		0		-		 25.00%
 	 2		0		-		 28.57%
 	 3		1		40C - 41C	 32.14%
@@ -193,7 +211,8 @@ is 40C:
 	10		2		54C - 56C	 57.14%
 	11		2		56C - 58C	 71.43%
 	12		2		58C - 60C	 85.71%
-					> 60C		100.00%
+	-		-		> 60C		100.00%
+     ========== ======================= =============== =======
 
 Valid offsets are in the range 0C <= x <= 7.5C in 0.5C increments.
 
@@ -213,7 +232,8 @@ temp<n>_auto_pwm_min.  Note, there are only two minimums: one each for temp[12]
 and temp[34].  Therefore, any change to e.g. temp1_auto_pwm_min will also
 affect temp2_auto_pwm_min.
 
-PWM Spin-Up Cycle:
+PWM Spin-Up Cycle
+^^^^^^^^^^^^^^^^^
 
 A spin-up cycle occurs when a PWM output is commanded from 0% duty cycle to
 some value > 0%.  The LM93 supports a minimum duty cycle during spin-up.  These
@@ -225,10 +245,11 @@ the spin-up time in seconds.  The available spin-up times are constrained by
 the hardware.  Selecting a value which is not available will cause the driver
 to use the next largest value.
 
-Spin-up Durations: 0 (disabled, h/w default), 0.1, 0.25, 0.4, 0.7, 1.0,
-		   2.0, 4.0
+Spin-up Durations:
+	0 (disabled, h/w default), 0.1, 0.25, 0.4, 0.7, 1.0, 2.0, 4.0
 
-#PROCHOT and #VRDHOT PWM Ramping:
+#PROCHOT and #VRDHOT PWM Ramping
+^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
 
 If the #PROCHOT or #VRDHOT signals are asserted while bound to a PWM output
 channel, the LM93 will ramp the PWM output up to 100% duty cycle in discrete
@@ -237,9 +258,11 @@ one value each in seconds: pwm_auto_prochot_ramp and pwm_auto_vrdhot_ramp.
 The available ramp times are constrained by the hardware.  Selecting a value
 which is not available will cause the driver to use the next largest value.
 
-Ramp Times: 0 (disabled, h/w default) to 0.75 in 0.05 second intervals
+Ramp Times:
+	0 (disabled, h/w default) to 0.75 in 0.05 second intervals
 
-Fan Boost:
+Fan Boost
+^^^^^^^^^
 
 For each temperature channel, there is a boost temperature: if the channel
 exceeds this limit, the LM93 will immediately drive both PWM outputs to 100%.
@@ -249,7 +272,8 @@ limit is reached, the temperature channel must drop below this value before
 the boost function is disabled.  This temperature is also expressed in degrees
 C in the sysfs files temp<n>_auto_boost_hyst.
 
-GPIO Pins:
+GPIO Pins
+^^^^^^^^^
 
 The LM93 can monitor the logic level of four dedicated GPIO pins as well as the
 four tach input pins.  GPIO0-GPIO3 correspond to (fan) tach 1-4, respectively.
@@ -260,50 +284,29 @@ LSB is GPIO0, and the MSB is GPIO7.
 LM93 Unique sysfs Files
 -----------------------
 
-	file			description
-	-------------------------------------------------------------
-
-	prochot<n>		current #PROCHOT %
-
-	prochot<n>_avg		moving average #PROCHOT %
-
-	prochot<n>_max		limit #PROCHOT %
-
-	prochot_short		enable or disable logical #PROCHOT pin short
-
-	prochot<n>_override	force #PROCHOT assertion as PWM
-
-	prochot_override_duty_cycle
-				duty cycle for the PWM signal used when
-				#PROCHOT is overridden
-
-	prochot<n>_interval	#PROCHOT PWM sampling interval
-
-	vrdhot<n>		0 means negated, 1 means asserted
-
-	fan<n>_smart_tach	enable or disable smart tach mode
-
-	pwm<n>_auto_channels	select control sources for PWM outputs
-
-	pwm<n>_auto_spinup_min	minimum duty cycle during spin-up
-
-	pwm<n>_auto_spinup_time	duration of spin-up
-
-	pwm_auto_prochot_ramp	ramp time per step when #PROCHOT asserted
-
-	pwm_auto_vrdhot_ramp	ramp time per step when #VRDHOT asserted
-
-	temp<n>_auto_base	temperature channel base
-
-	temp<n>_auto_offset[1-12]
-				temperature channel offsets
-
-	temp<n>_auto_offset_hyst
-				temperature channel offset hysteresis
-
-	temp<n>_auto_boost	temperature channel boost (PWMs to 100%) limit
-
-	temp<n>_auto_boost_hyst	temperature channel boost hysteresis
-
-	gpio			input state of 8 GPIO pins; read-only
-
+=========================== ===============================================
+file			    description
+=========================== ===============================================
+prochot<n>		    current #PROCHOT %
+prochot<n>_avg		    moving average #PROCHOT %
+prochot<n>_max		    limit #PROCHOT %
+prochot_short		    enable or disable logical #PROCHOT pin short
+prochot<n>_override	    force #PROCHOT assertion as PWM
+prochot_override_duty_cycle duty cycle for the PWM signal used when
+			    #PROCHOT is overridden
+prochot<n>_interval	    #PROCHOT PWM sampling interval
+vrdhot<n>		    0 means negated, 1 means asserted
+fan<n>_smart_tach	    enable or disable smart tach mode
+pwm<n>_auto_channels	    select control sources for PWM outputs
+pwm<n>_auto_spinup_min	    minimum duty cycle during spin-up
+pwm<n>_auto_spinup_time	    duration of spin-up
+pwm_auto_prochot_ramp	    ramp time per step when #PROCHOT asserted
+pwm_auto_vrdhot_ramp	    ramp time per step when #VRDHOT asserted
+temp<n>_auto_base	    temperature channel base
+temp<n>_auto_offset[1-12]   temperature channel offsets
+temp<n>_auto_offset_hyst    temperature channel offset hysteresis
+temp<n>_auto_boost	    temperature channel boost (PWMs to 100%)
+			    limit
+temp<n>_auto_boost_hyst     temperature channel boost hysteresis
+gpio			    input state of 8 GPIO pins; read-only
+=========================== ===============================================
diff --git a/Documentation/hwmon/lm95234 b/Documentation/hwmon/lm95234.rst
index 32b777ef224c..e4c14bea5efd 100644
--- a/Documentation/hwmon/lm95234
+++ b/Documentation/hwmon/lm95234.rst
@@ -2,15 +2,22 @@ Kernel driver lm95234
 =====================
 
 Supported chips:
+
   * National Semiconductor / Texas Instruments LM95233
+
     Addresses scanned: I2C 0x18, 0x2a, 0x2b
+
     Datasheet: Publicly available at the Texas Instruments website
-               http://www.ti.com/product/lm95233
+
+	       http://www.ti.com/product/lm95233
+
   * National Semiconductor / Texas Instruments LM95234
+
     Addresses scanned: I2C 0x18, 0x4d, 0x4e
+
     Datasheet: Publicly available at the Texas Instruments website
-               http://www.ti.com/product/lm95234
 
+	       http://www.ti.com/product/lm95234
 
 Author: Guenter Roeck <linux@roeck-us.net>
 
diff --git a/Documentation/hwmon/lm95245 b/Documentation/hwmon/lm95245.rst
index d755901f58c4..566d1dc8c5a6 100644
--- a/Documentation/hwmon/lm95245
+++ b/Documentation/hwmon/lm95245.rst
@@ -1,16 +1,23 @@
 Kernel driver lm95245
-==================
+=====================
 
 Supported chips:
+
   * TI LM95235
+
     Addresses scanned: I2C 0x18, 0x29, 0x4c
+
     Datasheet: Publicly available at the TI website
-               http://www.ti.com/lit/ds/symlink/lm95235.pdf
+
+	       http://www.ti.com/lit/ds/symlink/lm95235.pdf
+
   * TI / National Semiconductor LM95245
+
     Addresses scanned: I2C 0x18, 0x19, 0x29, 0x4c, 0x4d
+
     Datasheet: Publicly available at the TI website
-               http://www.ti.com/lit/ds/symlink/lm95245.pdf
 
+	       http://www.ti.com/lit/ds/symlink/lm95245.pdf
 
 Author: Alexander Stein <alexander.stein@systec-electronic.com>
 
diff --git a/Documentation/hwmon/lochnagar.rst b/Documentation/hwmon/lochnagar.rst
new file mode 100644
index 000000000000..1d609c4d18c3
--- /dev/null
+++ b/Documentation/hwmon/lochnagar.rst
@@ -0,0 +1,83 @@
+Kernel Driver Lochnagar
+=======================
+
+Supported systems:
+  * Cirrus Logic : Lochnagar 2
+
+Author: Lucas A. Tanure Alves
+
+Description
+-----------
+
+Lochnagar 2 features built-in Current Monitor circuitry that allows for the
+measurement of both voltage and current on up to eight of the supply voltage
+rails provided to the minicards. The Current Monitor does not require any
+hardware modifications or external circuitry to operate.
+
+The current and voltage measurements are obtained through the standard register
+map interface to the Lochnagar board controller, and can therefore be monitored
+by software.
+
+Sysfs attributes
+----------------
+
+======================= =======================================================
+temp1_input             The Lochnagar board temperature (milliCelsius)
+in0_input               Measured voltage for DBVDD1 (milliVolts)
+in0_label               "DBVDD1"
+curr1_input             Measured current for DBVDD1 (milliAmps)
+curr1_label             "DBVDD1"
+power1_average          Measured average power for DBVDD1 (microWatts)
+power1_average_interval Power averaging time input valid from 1 to 1708mS
+power1_label            "DBVDD1"
+in1_input               Measured voltage for 1V8 DSP (milliVolts)
+in1_label               "1V8 DSP"
+curr2_input             Measured current for 1V8 DSP (milliAmps)
+curr2_label             "1V8 DSP"
+power2_average          Measured average power for 1V8 DSP (microWatts)
+power2_average_interval Power averaging time input valid from 1 to 1708mS
+power2_label            "1V8 DSP"
+in2_input               Measured voltage for 1V8 CDC (milliVolts)
+in2_label               "1V8 CDC"
+curr3_input             Measured current for 1V8 CDC (milliAmps)
+curr3_label             "1V8 CDC"
+power3_average          Measured average power for 1V8 CDC (microWatts)
+power3_average_interval Power averaging time input valid from 1 to 1708mS
+power3_label            "1V8 CDC"
+in3_input               Measured voltage for VDDCORE DSP (milliVolts)
+in3_label               "VDDCORE DSP"
+curr4_input             Measured current for VDDCORE DSP (milliAmps)
+curr4_label             "VDDCORE DSP"
+power4_average          Measured average power for VDDCORE DSP (microWatts)
+power4_average_interval Power averaging time input valid from 1 to 1708mS
+power4_label            "VDDCORE DSP"
+in4_input               Measured voltage for AVDD 1V8 (milliVolts)
+in4_label               "AVDD 1V8"
+curr5_input             Measured current for AVDD 1V8 (milliAmps)
+curr5_label             "AVDD 1V8"
+power5_average          Measured average power for AVDD 1V8 (microWatts)
+power5_average_interval Power averaging time input valid from 1 to 1708mS
+power5_label            "AVDD 1V8"
+curr6_input             Measured current for SYSVDD (milliAmps)
+curr6_label             "SYSVDD"
+power6_average          Measured average power for SYSVDD (microWatts)
+power6_average_interval Power averaging time input valid from 1 to 1708mS
+power6_label            "SYSVDD"
+in6_input               Measured voltage for VDDCORE CDC (milliVolts)
+in6_label               "VDDCORE CDC"
+curr7_input             Measured current for VDDCORE CDC (milliAmps)
+curr7_label             "VDDCORE CDC"
+power7_average          Measured average power for VDDCORE CDC (microWatts)
+power7_average_interval Power averaging time input valid from 1 to 1708mS
+power7_label            "VDDCORE CDC"
+in7_input               Measured voltage for MICVDD (milliVolts)
+in7_label               "MICVDD"
+curr8_input             Measured current for MICVDD (milliAmps)
+curr8_label             "MICVDD"
+power8_average          Measured average power for MICVDD (microWatts)
+power8_average_interval Power averaging time input valid from 1 to 1708mS
+power8_label            "MICVDD"
+======================= =======================================================
+
+Note:
+    It is not possible to measure voltage on the SYSVDD rail.
diff --git a/Documentation/hwmon/ltc2945 b/Documentation/hwmon/ltc2945.rst
index f8d0f7f19adb..20c884985367 100644
--- a/Documentation/hwmon/ltc2945
+++ b/Documentation/hwmon/ltc2945.rst
@@ -2,11 +2,16 @@ Kernel driver ltc2945
 =====================
 
 Supported chips:
+
   * Linear Technology LTC2945
+
     Prefix: 'ltc2945'
+
     Addresses scanned: -
+
     Datasheet:
-        http://cds.linear.com/docs/en/datasheet/2945fa.pdf
+
+	http://cds.linear.com/docs/en/datasheet/2945fa.pdf
 
 Author: Guenter Roeck <linux@roeck-us.net>
 
@@ -26,9 +31,10 @@ which can be safely used to identify the chip. You will have to instantiate
 the devices explicitly.
 
 Example: the following will load the driver for an LTC2945 at address 0x10
-on I2C bus #1:
-$ modprobe ltc2945
-$ echo ltc2945 0x10 > /sys/bus/i2c/devices/i2c-1/new_device
+on I2C bus #1::
+
+	$ modprobe ltc2945
+	$ echo ltc2945 0x10 > /sys/bus/i2c/devices/i2c-1/new_device
 
 
 Sysfs entries
@@ -45,6 +51,7 @@ Current Sense register. The reported value assumes that a 1 mOhm sense resistor
 is installed. If a different sense resistor is installed, calculate the real
 current by dividing the reported value by the sense resistor value in mOhm.
 
+======================= ========================================================
 in1_input		VIN voltage (mV). Voltage is measured either at
 			SENSE+ or VDD pin depending on chip configuration.
 in1_min			Undervoltage threshold
@@ -82,3 +89,4 @@ power1_input_highest	Historical maximum power use
 power1_reset_history	Write 1 to reset power1 history
 power1_min_alarm	Low power alarm
 power1_max_alarm	High power alarm
+======================= ========================================================
diff --git a/Documentation/hwmon/ltc2978 b/Documentation/hwmon/ltc2978.rst
index dfb2caa401d9..01a24fd6d5fe 100644
--- a/Documentation/hwmon/ltc2978
+++ b/Documentation/hwmon/ltc2978.rst
@@ -2,85 +2,143 @@ Kernel driver ltc2978
 =====================
 
 Supported chips:
+
   * Linear Technology LTC2974
+
     Prefix: 'ltc2974'
+
     Addresses scanned: -
+
     Datasheet: http://www.linear.com/product/ltc2974
+
   * Linear Technology LTC2975
+
     Prefix: 'ltc2975'
+
     Addresses scanned: -
+
     Datasheet: http://www.linear.com/product/ltc2975
+
   * Linear Technology LTC2977
+
     Prefix: 'ltc2977'
+
     Addresses scanned: -
+
     Datasheet: http://www.linear.com/product/ltc2977
+
   * Linear Technology LTC2978, LTC2978A
+
     Prefix: 'ltc2978'
+
     Addresses scanned: -
+
     Datasheet: http://www.linear.com/product/ltc2978
-    	       http://www.linear.com/product/ltc2978a
+
+	       http://www.linear.com/product/ltc2978a
+
   * Linear Technology LTC2980
+
     Prefix: 'ltc2980'
+
     Addresses scanned: -
+
     Datasheet: http://www.linear.com/product/ltc2980
+
   * Linear Technology LTC3880
+
     Prefix: 'ltc3880'
+
     Addresses scanned: -
+
     Datasheet: http://www.linear.com/product/ltc3880
+
   * Linear Technology LTC3882
+
     Prefix: 'ltc3882'
+
     Addresses scanned: -
+
     Datasheet: http://www.linear.com/product/ltc3882
+
   * Linear Technology LTC3883
+
     Prefix: 'ltc3883'
+
     Addresses scanned: -
+
     Datasheet: http://www.linear.com/product/ltc3883
+
   * Linear Technology LTC3886
+
     Prefix: 'ltc3886'
+
     Addresses scanned: -
+
     Datasheet: http://www.linear.com/product/ltc3886
+
   * Linear Technology LTC3887
+
     Prefix: 'ltc3887'
+
     Addresses scanned: -
+
     Datasheet: http://www.linear.com/product/ltc3887
+
   * Linear Technology LTM2987
+
     Prefix: 'ltm2987'
+
     Addresses scanned: -
+
     Datasheet: http://www.linear.com/product/ltm2987
+
   * Linear Technology LTM4675
+
     Prefix: 'ltm4675'
+
     Addresses scanned: -
+
     Datasheet: http://www.linear.com/product/ltm4675
+
   * Linear Technology LTM4676
+
     Prefix: 'ltm4676'
+
     Addresses scanned: -
+
     Datasheet: http://www.linear.com/product/ltm4676
+
   * Analog Devices LTM4686
+
     Prefix: 'ltm4686'
+
     Addresses scanned: -
+
     Datasheet: http://www.analog.com/ltm4686
 
+
 Author: Guenter Roeck <linux@roeck-us.net>
 
 
 Description
 -----------
 
-LTC2974 and LTC2975 are quad digital power supply managers.
-LTC2978 is an octal power supply monitor.
-LTC2977 is a pin compatible replacement for LTC2978.
-LTC2980 is a 16-channel Power System Manager, consisting of two LTC2977
-in a single die. The chip is instantiated and reported as two separate chips
-on two different I2C bus addresses.
-LTC3880, LTC3882, LTC3886, and LTC3887 are dual output poly-phase step-down
-DC/DC controllers.
-LTC3883 is a single phase step-down DC/DC controller.
-LTM2987 is a 16-channel Power System Manager with two LTC2977 plus
-additional components on a single die. The chip is instantiated and reported
-as two separate chips on two different I2C bus addresses.
-LTM4675 is a dual 9A or single 18A μModule regulator
-LTM4676 is a dual 13A or single 26A uModule regulator.
-LTM4686 is a dual 10A or single 20A uModule regulator.
+- LTC2974 and LTC2975 are quad digital power supply managers.
+- LTC2978 is an octal power supply monitor.
+- LTC2977 is a pin compatible replacement for LTC2978.
+- LTC2980 is a 16-channel Power System Manager, consisting of two LTC2977
+- in a single die. The chip is instantiated and reported as two separate chips
+- on two different I2C bus addresses.
+- LTC3880, LTC3882, LTC3886, and LTC3887 are dual output poly-phase step-down
+- DC/DC controllers.
+- LTC3883 is a single phase step-down DC/DC controller.
+- LTM2987 is a 16-channel Power System Manager with two LTC2977 plus
+- additional components on a single die. The chip is instantiated and reported
+- as two separate chips on two different I2C bus addresses.
+- LTM4675 is a dual 9A or single 18A μModule regulator
+- LTM4676 is a dual 13A or single 26A uModule regulator.
+- LTM4686 is a dual 10A or single 20A uModule regulator.
 
 
 Usage Notes
@@ -90,127 +148,208 @@ This driver does not probe for PMBus devices. You will have to instantiate
 devices explicitly.
 
 Example: the following commands will load the driver for an LTC2978 at address
-0x60 on I2C bus #1:
+0x60 on I2C bus #1::
 
-# modprobe ltc2978
-# echo ltc2978 0x60 > /sys/bus/i2c/devices/i2c-1/new_device
+	# modprobe ltc2978
+	# echo ltc2978 0x60 > /sys/bus/i2c/devices/i2c-1/new_device
 
 
 Sysfs attributes
 ----------------
 
+======================= ========================================================
 in1_label		"vin"
+
 in1_input		Measured input voltage.
+
 in1_min			Minimum input voltage.
+
 in1_max			Maximum input voltage.
+
 			LTC2974, LTC2975, LTC2977, LTC2980, LTC2978, and
 			LTM2987 only.
+
 in1_lcrit		Critical minimum input voltage.
+
 			LTC2974, LTC2975, LTC2977, LTC2980, LTC2978, and
 			LTM2987 only.
+
 in1_crit		Critical maximum input voltage.
+
 in1_min_alarm		Input voltage low alarm.
+
 in1_max_alarm		Input voltage high alarm.
+
 			LTC2974, LTC2975, LTC2977, LTC2980, LTC2978, and
 			LTM2987 only.
 in1_lcrit_alarm		Input voltage critical low alarm.
+
 			LTC2974, LTC2975, LTC2977, LTC2980, LTC2978, and
 			LTM2987 only.
 in1_crit_alarm		Input voltage critical high alarm.
+
 in1_lowest		Lowest input voltage.
+
 			LTC2974, LTC2975, LTC2977, LTC2980, LTC2978, and
 			LTM2987 only.
 in1_highest		Highest input voltage.
+
 in1_reset_history	Reset input voltage history.
 
 in[N]_label		"vout[1-8]".
-			LTC2974, LTC2975: N=2-5
-			LTC2977, LTC2980, LTM2987: N=2-9
-			LTC2978: N=2-9
-			LTC3880, LTC3882, LTC23886 LTC3887, LTM4675, LTM4676:
-				N=2-3
-			LTC3883: N=2
+
+			- LTC2974, LTC2975: N=2-5
+			- LTC2977, LTC2980, LTM2987: N=2-9
+			- LTC2978: N=2-9
+			- LTC3880, LTC3882, LTC23886 LTC3887, LTM4675, LTM4676:
+			  N=2-3
+			- LTC3883: N=2
+
 in[N]_input		Measured output voltage.
+
 in[N]_min		Minimum output voltage.
+
 in[N]_max		Maximum output voltage.
+
 in[N]_lcrit		Critical minimum output voltage.
+
 in[N]_crit		Critical maximum output voltage.
+
 in[N]_min_alarm		Output voltage low alarm.
+
 in[N]_max_alarm		Output voltage high alarm.
+
 in[N]_lcrit_alarm	Output voltage critical low alarm.
+
 in[N]_crit_alarm	Output voltage critical high alarm.
-in[N]_lowest		Lowest output voltage. LTC2974, LTC2975,
-			and LTC2978 only.
+
+in[N]_lowest		Lowest output voltage.
+
+
+			LTC2974, LTC2975,and LTC2978 only.
+
 in[N]_highest		Highest output voltage.
+
 in[N]_reset_history	Reset output voltage history.
 
 temp[N]_input		Measured temperature.
-			On LTC2974 and LTC2975, temp[1-4] report external
-			temperatures, and temp5 reports the chip temperature.
-			On LTC2977, LTC2980, LTC2978, and LTM2987, only one
-			temperature measurement is supported and reports
-			the chip temperature.
-			On LTC3880, LTC3882, LTC3887, LTM4675, and LTM4676,
-			temp1 and temp2 report external temperatures, and temp3
-			reports the chip temperature.
-			On LTC3883, temp1 reports an external temperature,
-			and temp2 reports the chip temperature.
-temp[N]_min		Mimimum temperature. LTC2974, LCT2977, LTM2980, LTC2978,
-			and LTM2987 only.
+
+			- On LTC2974 and LTC2975, temp[1-4] report external
+			  temperatures, and temp5 reports the chip temperature.
+			- On LTC2977, LTC2980, LTC2978, and LTM2987, only one
+			  temperature measurement is supported and reports
+			  the chip temperature.
+			- On LTC3880, LTC3882, LTC3887, LTM4675, and LTM4676,
+			  temp1 and temp2 report external temperatures, and
+			  temp3 reports the chip temperature.
+			- On LTC3883, temp1 reports an external temperature,
+			  and temp2 reports the chip temperature.
+
+temp[N]_min		Mimimum temperature.
+
+			LTC2974, LCT2977, LTM2980, LTC2978, and LTM2987 only.
+
 temp[N]_max		Maximum temperature.
+
 temp[N]_lcrit		Critical low temperature.
+
 temp[N]_crit		Critical high temperature.
+
 temp[N]_min_alarm	Temperature low alarm.
+
 			LTC2974, LTC2975, LTC2977, LTM2980, LTC2978, and
 			LTM2987 only.
+
 temp[N]_max_alarm	Temperature high alarm.
+
+
 temp[N]_lcrit_alarm	Temperature critical low alarm.
+
 temp[N]_crit_alarm	Temperature critical high alarm.
+
 temp[N]_lowest		Lowest measured temperature.
-			LTC2974, LTC2975, LTC2977, LTM2980, LTC2978, and
-			LTM2987 only.
-			Not supported for chip temperature sensor on LTC2974 and
-			LTC2975.
-temp[N]_highest		Highest measured temperature. Not supported for chip
-			temperature sensor on LTC2974 and LTC2975.
-temp[N]_reset_history	Reset temperature history. Not supported for chip
-			temperature sensor on LTC2974 and LTC2975.
+
+			- LTC2974, LTC2975, LTC2977, LTM2980, LTC2978, and
+			  LTM2987 only.
+			- Not supported for chip temperature sensor on LTC2974
+			  and LTC2975.
+
+temp[N]_highest		Highest measured temperature.
+
+			Not supported for chip temperature sensor on
+			LTC2974 and LTC2975.
+
+temp[N]_reset_history	Reset temperature history.
+
+			Not supported for chip temperature sensor on
+			LTC2974 and LTC2975.
 
 power1_label		"pin". LTC3883 and LTC3886 only.
+
 power1_input		Measured input power.
 
 power[N]_label		"pout[1-4]".
-			LTC2974, LTC2975: N=1-4
-			LTC2977, LTC2980, LTM2987: Not supported
-			LTC2978: Not supported
-			LTC3880, LTC3882, LTC3886, LTC3887, LTM4675, LTM4676:
-				N=1-2
-			LTC3883: N=2
+
+			- LTC2974, LTC2975: N=1-4
+			- LTC2977, LTC2980, LTM2987: Not supported
+			- LTC2978: Not supported
+			- LTC3880, LTC3882, LTC3886, LTC3887, LTM4675, LTM4676:
+			  N=1-2
+			- LTC3883: N=2
+
 power[N]_input		Measured output power.
 
-curr1_label		"iin". LTC3880, LTC3883, LTC3886, LTC3887, LTM4675,
+curr1_label		"iin".
+
+			LTC3880, LTC3883, LTC3886, LTC3887, LTM4675,
 			and LTM4676 only.
+
 curr1_input		Measured input current.
+
 curr1_max		Maximum input current.
+
 curr1_max_alarm		Input current high alarm.
-curr1_highest		Highest input current. LTC3883 and LTC3886 only.
-curr1_reset_history	Reset input current history. LTC3883 and LTC3886 only.
+
+curr1_highest		Highest input current.
+
+			LTC3883 and LTC3886 only.
+
+curr1_reset_history	Reset input current history.
+
+			LTC3883 and LTC3886 only.
 
 curr[N]_label		"iout[1-4]".
-			LTC2974, LTC2975: N=1-4
-			LTC2977, LTC2980, LTM2987: not supported
-			LTC2978: not supported
-			LTC3880, LTC3882, LTC3886, LTC3887, LTM4675, LTM4676:
-				N=2-3
-			LTC3883: N=2
+
+			- LTC2974, LTC2975: N=1-4
+			- LTC2977, LTC2980, LTM2987: not supported
+			- LTC2978: not supported
+			- LTC3880, LTC3882, LTC3886, LTC3887, LTM4675, LTM4676:
+			  N=2-3
+			- LTC3883: N=2
+
 curr[N]_input		Measured output current.
+
 curr[N]_max		Maximum output current.
+
 curr[N]_crit		Critical high output current.
-curr[N]_lcrit		Critical low output current. LTC2974 and LTC2975 only.
+
+curr[N]_lcrit		Critical low output current.
+
+			LTC2974 and LTC2975 only.
+
 curr[N]_max_alarm	Output current high alarm.
+
 curr[N]_crit_alarm	Output current critical high alarm.
+
 curr[N]_lcrit_alarm	Output current critical low alarm.
+
+			LTC2974 and LTC2975 only.
+
+curr[N]_lowest		Lowest output current.
+
 			LTC2974 and LTC2975 only.
-curr[N]_lowest		Lowest output current. LTC2974 and LTC2975 only.
+
 curr[N]_highest		Highest output current.
+
 curr[N]_reset_history	Reset output current history.
+======================= ========================================================
diff --git a/Documentation/hwmon/ltc2990 b/Documentation/hwmon/ltc2990.rst
index 3ed68f676c0f..e0a369e679d3 100644
--- a/Documentation/hwmon/ltc2990
+++ b/Documentation/hwmon/ltc2990.rst
@@ -1,14 +1,23 @@
 Kernel driver ltc2990
 =====================
 
+
 Supported chips:
+
   * Linear Technology LTC2990
+
     Prefix: 'ltc2990'
+
     Addresses scanned: -
+
     Datasheet: http://www.linear.com/product/ltc2990
 
-Author: Mike Looijmans <mike.looijmans@topic.nl>
-        Tom Levens <tom.levens@cern.ch>
+
+
+Author:
+
+	- Mike Looijmans <mike.looijmans@topic.nl>
+	- Tom Levens <tom.levens@cern.ch>
 
 
 Description
@@ -31,17 +40,21 @@ devices explicitly.
 Sysfs attributes
 ----------------
 
+============= ==================================================
 in0_input     Voltage at Vcc pin in millivolt (range 2.5V to 5V)
-temp1_input   Internal chip temperature in millidegrees Celcius
+temp1_input   Internal chip temperature in millidegrees Celsius
+============= ==================================================
 
 A subset of the following attributes are visible, depending on the measurement
 mode of the chip.
 
+============= ==========================================================
 in[1-4]_input Voltage at V[1-4] pin in millivolt
-temp2_input   External temperature sensor TR1 in millidegrees Celcius
-temp3_input   External temperature sensor TR2 in millidegrees Celcius
+temp2_input   External temperature sensor TR1 in millidegrees Celsius
+temp3_input   External temperature sensor TR2 in millidegrees Celsius
 curr1_input   Current in mA across V1-V2 assuming a 1mOhm sense resistor
 curr2_input   Current in mA across V3-V4 assuming a 1mOhm sense resistor
+============= ==========================================================
 
 The "curr*_input" measurements actually report the voltage drop across the
 input pins in microvolts. This is equivalent to the current through a 1mOhm
diff --git a/Documentation/hwmon/ltc3815 b/Documentation/hwmon/ltc3815.rst
index eb7db2d13587..fb0135fc1925 100644
--- a/Documentation/hwmon/ltc3815
+++ b/Documentation/hwmon/ltc3815.rst
@@ -2,9 +2,13 @@ Kernel driver ltc3815
 =====================
 
 Supported chips:
+
   * Linear Technology LTC3815
+
     Prefix: 'ltc3815'
+
     Addresses scanned: -
+
     Datasheet: http://www.linear.com/product/ltc3815
 
 Author: Guenter Roeck <linux@roeck-us.net>
@@ -23,15 +27,16 @@ This driver does not probe for PMBus devices. You will have to instantiate
 devices explicitly.
 
 Example: the following commands will load the driver for an LTC3815
-at address 0x20 on I2C bus #1:
+at address 0x20 on I2C bus #1::
 
-# modprobe ltc3815
-# echo ltc3815 0x20 > /sys/bus/i2c/devices/i2c-1/new_device
+	# modprobe ltc3815
+	# echo ltc3815 0x20 > /sys/bus/i2c/devices/i2c-1/new_device
 
 
 Sysfs attributes
 ----------------
 
+======================= =======================================================
 in1_label		"vin"
 in1_input		Measured input voltage.
 in1_alarm		Input voltage alarm.
@@ -59,3 +64,4 @@ curr2_input		Measured output current.
 curr2_alarm		Output current alarm.
 curr2_highest		Highest output current.
 curr2_reset_history	Reset output current history.
+======================= =======================================================
diff --git a/Documentation/hwmon/ltc4151 b/Documentation/hwmon/ltc4151.rst
index 43c667e6677a..c39229b19624 100644
--- a/Documentation/hwmon/ltc4151
+++ b/Documentation/hwmon/ltc4151.rst
@@ -2,11 +2,16 @@ Kernel driver ltc4151
 =====================
 
 Supported chips:
+
   * Linear Technology LTC4151
+
     Prefix: 'ltc4151'
+
     Addresses scanned: -
+
     Datasheet:
-        http://www.linear.com/docs/Datasheet/4151fc.pdf
+
+	http://www.linear.com/docs/Datasheet/4151fc.pdf
 
 Author: Per Dalen <per.dalen@appeartv.com>
 
@@ -25,9 +30,10 @@ which can be safely used to identify the chip. You will have to instantiate
 the devices explicitly.
 
 Example: the following will load the driver for an LTC4151 at address 0x6f
-on I2C bus #0:
-# modprobe ltc4151
-# echo ltc4151 0x6f > /sys/bus/i2c/devices/i2c-0/new_device
+on I2C bus #0::
+
+	# modprobe ltc4151
+	# echo ltc4151 0x6f > /sys/bus/i2c/devices/i2c-0/new_device
 
 
 Sysfs entries
@@ -40,8 +46,10 @@ Current reading provided by this driver is reported as obtained from the Current
 Sense register. The reported value assumes that a 1 mOhm sense resistor is
 installed.
 
+======================= ==================
 in1_input		VDIN voltage (mV)
 
 in2_input		ADIN voltage (mV)
 
 curr1_input		SENSE current (mA)
+======================= ==================
diff --git a/Documentation/hwmon/ltc4215 b/Documentation/hwmon/ltc4215.rst
index c196a1846259..8d5044d99bab 100644
--- a/Documentation/hwmon/ltc4215
+++ b/Documentation/hwmon/ltc4215.rst
@@ -2,11 +2,16 @@ Kernel driver ltc4215
 =====================
 
 Supported chips:
+
   * Linear Technology LTC4215
+
     Prefix: 'ltc4215'
+
     Addresses scanned: 0x44
+
     Datasheet:
-        http://www.linear.com/pc/downloadDocument.do?navId=H0,C1,C1003,C1006,C1163,P17572,D12697
+
+	http://www.linear.com/pc/downloadDocument.do?navId=H0,C1,C1003,C1006,C1163,P17572,D12697
 
 Author: Ira W. Snyder <iws@ovro.caltech.edu>
 
@@ -26,9 +31,10 @@ of the possible addresses are unfriendly to probing. You will have to
 instantiate the devices explicitly.
 
 Example: the following will load the driver for an LTC4215 at address 0x44
-on I2C bus #0:
-$ modprobe ltc4215
-$ echo ltc4215 0x44 > /sys/bus/i2c/devices/i2c-0/new_device
+on I2C bus #0::
+
+	$ modprobe ltc4215
+	$ echo ltc4215 0x44 > /sys/bus/i2c/devices/i2c-0/new_device
 
 
 Sysfs entries
@@ -38,6 +44,7 @@ The LTC4215 has built-in limits for overvoltage, undervoltage, and
 undercurrent warnings. This makes it very likely that the reference
 circuit will be used.
 
+======================= =========================
 in1_input		input voltage
 in2_input		output voltage
 
@@ -49,3 +56,4 @@ curr1_max_alarm		overcurrent alarm
 
 power1_input		power usage
 power1_alarm		power bad alarm
+======================= =========================
diff --git a/Documentation/hwmon/ltc4245 b/Documentation/hwmon/ltc4245.rst
index 4ca7a9da09f9..3dafd08a4e87 100644
--- a/Documentation/hwmon/ltc4245
+++ b/Documentation/hwmon/ltc4245.rst
@@ -2,11 +2,16 @@ Kernel driver ltc4245
 =====================
 
 Supported chips:
+
   * Linear Technology LTC4245
+
     Prefix: 'ltc4245'
+
     Addresses scanned: 0x20-0x3f
+
     Datasheet:
-        http://www.linear.com/pc/downloadDocument.do?navId=H0,C1,C1003,C1006,C1140,P19392,D13517
+
+	http://www.linear.com/pc/downloadDocument.do?navId=H0,C1,C1003,C1006,C1140,P19392,D13517
 
 Author: Ira W. Snyder <iws@ovro.caltech.edu>
 
@@ -27,9 +32,10 @@ of the possible addresses are unfriendly to probing. You will have to
 instantiate the devices explicitly.
 
 Example: the following will load the driver for an LTC4245 at address 0x23
-on I2C bus #1:
-$ modprobe ltc4245
-$ echo ltc4245 0x23 > /sys/bus/i2c/devices/i2c-1/new_device
+on I2C bus #1::
+
+	$ modprobe ltc4245
+	$ echo ltc4245 0x23 > /sys/bus/i2c/devices/i2c-1/new_device
 
 
 Sysfs entries
@@ -42,6 +48,7 @@ This driver uses the values in the datasheet to change the register values
 into the values specified in the sysfs-interface document. The current readings
 rely on the sense resistors listed in Table 2: "Sense Resistor Values".
 
+======================= =======================================================
 in1_input		12v input voltage (mV)
 in2_input		5v  input voltage (mV)
 in3_input		3v  input voltage (mV)
@@ -80,6 +87,7 @@ power1_input		12v power usage (mW)
 power2_input		5v  power usage (mW)
 power3_input		3v  power usage (mW)
 power4_input		Vee (-12v) power usage (mW)
+======================= =======================================================
 
 
 Note 1
@@ -96,6 +104,7 @@ slowly, -EAGAIN will be returned when you read the sysfs attribute containing
 the sensor reading.
 
 The LTC4245 chip can be configured to sample all GPIO pins with two methods:
+
 1) platform data -- see include/linux/platform_data/ltc4245.h
 2) OF device tree -- add the "ltc4245,use-extra-gpios" property to each chip
 
diff --git a/Documentation/hwmon/ltc4260 b/Documentation/hwmon/ltc4260.rst
index c4ff4ad998b2..4c335b6a51d1 100644
--- a/Documentation/hwmon/ltc4260
+++ b/Documentation/hwmon/ltc4260.rst
@@ -2,11 +2,16 @@ Kernel driver ltc4260
 =====================
 
 Supported chips:
+
   * Linear Technology LTC4260
+
     Prefix: 'ltc4260'
+
     Addresses scanned: -
+
     Datasheet:
-        http://cds.linear.com/docs/en/datasheet/4260fc.pdf
+
+	http://cds.linear.com/docs/en/datasheet/4260fc.pdf
 
 Author: Guenter Roeck <linux@roeck-us.net>
 
@@ -26,9 +31,10 @@ which can be safely used to identify the chip. You will have to instantiate
 the devices explicitly.
 
 Example: the following will load the driver for an LTC4260 at address 0x10
-on I2C bus #1:
-$ modprobe ltc4260
-$ echo ltc4260 0x10 > /sys/bus/i2c/devices/i2c-1/new_device
+on I2C bus #1::
+
+	$ modprobe ltc4260
+	$ echo ltc4260 0x10 > /sys/bus/i2c/devices/i2c-1/new_device
 
 
 Sysfs entries
@@ -45,6 +51,7 @@ Current Sense register. The reported value assumes that a 1 mOhm sense resistor
 is installed. If a different sense resistor is installed, calculate the real
 current by dividing the reported value by the sense resistor value in mOhm.
 
+======================= =======================
 in1_input		SOURCE voltage (mV)
 in1_min_alarm		Undervoltage alarm
 in1_max_alarm		Overvoltage alarm
@@ -54,3 +61,4 @@ in2_alarm		Power bad alarm
 
 curr1_input		SENSE current (mA)
 curr1_alarm		SENSE overcurrent alarm
+======================= =======================
diff --git a/Documentation/hwmon/ltc4261 b/Documentation/hwmon/ltc4261.rst
index 9378a75c6134..c80233f8082e 100644
--- a/Documentation/hwmon/ltc4261
+++ b/Documentation/hwmon/ltc4261.rst
@@ -2,11 +2,16 @@ Kernel driver ltc4261
 =====================
 
 Supported chips:
+
   * Linear Technology LTC4261
+
     Prefix: 'ltc4261'
+
     Addresses scanned: -
+
     Datasheet:
-        http://cds.linear.com/docs/Datasheet/42612fb.pdf
+
+	http://cds.linear.com/docs/Datasheet/42612fb.pdf
 
 Author: Guenter Roeck <linux@roeck-us.net>
 
@@ -26,9 +31,10 @@ which can be safely used to identify the chip. You will have to instantiate
 the devices explicitly.
 
 Example: the following will load the driver for an LTC4261 at address 0x10
-on I2C bus #1:
-$ modprobe ltc4261
-$ echo ltc4261 0x10 > /sys/bus/i2c/devices/i2c-1/new_device
+on I2C bus #1::
+
+	$ modprobe ltc4261
+	$ echo ltc4261 0x10 > /sys/bus/i2c/devices/i2c-1/new_device
 
 
 Sysfs entries
@@ -51,6 +57,7 @@ the proximity of the ADIN2 pin to the OV pin. ADIN2 is, however, not available
 on all chip variants. To ensure that the alarm condition is reported to the user,
 report it with both voltage sensors.
 
+======================= =============================
 in1_input		ADIN2 voltage (mV)
 in1_min_alarm		ADIN/ADIN2 Undervoltage alarm
 in1_max_alarm		ADIN/ADIN2 Overvoltage alarm
@@ -61,3 +68,4 @@ in2_max_alarm		ADIN/ADIN2 Overvoltage alarm
 
 curr1_input		SENSE current (mA)
 curr1_alarm		SENSE overcurrent alarm
+======================= =============================
diff --git a/Documentation/hwmon/max16064 b/Documentation/hwmon/max16064.rst
index 265370f5cb82..6d5e9538991f 100644
--- a/Documentation/hwmon/max16064
+++ b/Documentation/hwmon/max16064.rst
@@ -2,9 +2,13 @@ Kernel driver max16064
 ======================
 
 Supported chips:
+
   * Maxim MAX16064
+
     Prefix: 'max16064'
+
     Addresses scanned: -
+
     Datasheet: http://datasheets.maxim-ic.com/en/ds/MAX16064.pdf
 
 Author: Guenter Roeck <linux@roeck-us.net>
@@ -17,7 +21,7 @@ This driver supports hardware monitoring for Maxim MAX16064 Quad Power-Supply
 Controller with Active-Voltage Output Control and PMBus Interface.
 
 The driver is a client driver to the core PMBus driver.
-Please see Documentation/hwmon/pmbus for details on PMBus client drivers.
+Please see Documentation/hwmon/pmbus.rst for details on PMBus client drivers.
 
 
 Usage Notes
@@ -40,16 +44,20 @@ Sysfs entries
 The following attributes are supported. Limits are read-write; all other
 attributes are read-only.
 
+======================= ========================================================
 in[1-4]_label		"vout[1-4]"
 in[1-4]_input		Measured voltage. From READ_VOUT register.
 in[1-4]_min		Minimum Voltage. From VOUT_UV_WARN_LIMIT register.
 in[1-4]_max		Maximum voltage. From VOUT_OV_WARN_LIMIT register.
 in[1-4]_lcrit		Critical minimum Voltage. VOUT_UV_FAULT_LIMIT register.
-in[1-4]_crit		Critical maximum voltage. From VOUT_OV_FAULT_LIMIT register.
+in[1-4]_crit		Critical maximum voltage. From VOUT_OV_FAULT_LIMIT
+			register.
 in[1-4]_min_alarm	Voltage low alarm. From VOLTAGE_UV_WARNING status.
 in[1-4]_max_alarm	Voltage high alarm. From VOLTAGE_OV_WARNING status.
-in[1-4]_lcrit_alarm	Voltage critical low alarm. From VOLTAGE_UV_FAULT status.
-in[1-4]_crit_alarm	Voltage critical high alarm. From VOLTAGE_OV_FAULT status.
+in[1-4]_lcrit_alarm	Voltage critical low alarm. From VOLTAGE_UV_FAULT
+			status.
+in[1-4]_crit_alarm	Voltage critical high alarm. From VOLTAGE_OV_FAULT
+			status.
 in[1-4]_highest		Historical maximum voltage.
 in[1-4]_reset_history	Write any value to reset history.
 
@@ -64,3 +72,4 @@ temp1_crit_alarm	Chip temperature critical high alarm. Set by comparing
 			status is set.
 temp1_highest		Historical maximum temperature.
 temp1_reset_history	Write any value to reset history.
+======================= ========================================================
diff --git a/Documentation/hwmon/max16065 b/Documentation/hwmon/max16065.rst
index 208a29e43010..fa5c852a178c 100644
--- a/Documentation/hwmon/max16065
+++ b/Documentation/hwmon/max16065.rst
@@ -1,28 +1,48 @@
 Kernel driver max16065
 ======================
 
+
 Supported chips:
+
   * Maxim MAX16065, MAX16066
+
     Prefixes: 'max16065', 'max16066'
+
     Addresses scanned: -
+
     Datasheet:
+
 	http://datasheets.maxim-ic.com/en/ds/MAX16065-MAX16066.pdf
+
  *  Maxim MAX16067
+
     Prefix: 'max16067'
+
     Addresses scanned: -
+
     Datasheet:
+
 	http://datasheets.maxim-ic.com/en/ds/MAX16067.pdf
+
  *  Maxim MAX16068
+
     Prefix: 'max16068'
+
     Addresses scanned: -
+
     Datasheet:
+
 	http://datasheets.maxim-ic.com/en/ds/MAX16068.pdf
+
  *  Maxim MAX16070/MAX16071
+
     Prefixes: 'max16070', 'max16071'
+
     Addresses scanned: -
+
     Datasheet:
-	http://datasheets.maxim-ic.com/en/ds/MAX16070-MAX16071.pdf
 
+	http://datasheets.maxim-ic.com/en/ds/MAX16070-MAX16071.pdf
 
 Author: Guenter Roeck <linux@roeck-us.net>
 
@@ -73,6 +93,7 @@ turn into a brick.
 Sysfs entries
 -------------
 
+======================= ========================================================
 in[0-11]_input		Input voltage measurements.
 
 in12_input		Voltage on CSP (Current Sense Positive) pin.
@@ -103,3 +124,4 @@ curr1_input		Current sense input; only if the chip supports current
 
 curr1_alarm		Overcurrent alarm; only if the chip supports current
 			sensing and if current sensing is enabled.
+======================= ========================================================
diff --git a/Documentation/hwmon/max1619 b/Documentation/hwmon/max1619.rst
index 518bae3a80c4..e25956e70f73 100644
--- a/Documentation/hwmon/max1619
+++ b/Documentation/hwmon/max1619.rst
@@ -2,15 +2,20 @@ Kernel driver max1619
 =====================
 
 Supported chips:
+
   * Maxim MAX1619
+
     Prefix: 'max1619'
+
     Addresses scanned: I2C 0x18-0x1a, 0x29-0x2b, 0x4c-0x4e
+
     Datasheet: Publicly available at the Maxim website
-               http://pdfserv.maxim-ic.com/en/ds/MAX1619.pdf
+
+	       http://pdfserv.maxim-ic.com/en/ds/MAX1619.pdf
 
 Authors:
-        Oleksij Rempel <bug-track@fisher-privat.net>,
-        Jean Delvare <jdelvare@suse.de>
+       - Oleksij Rempel <bug-track@fisher-privat.net>,
+       - Jean Delvare <jdelvare@suse.de>
 
 Description
 -----------
@@ -26,4 +31,3 @@ Only the external sensor has high and low limits.
 The max1619 driver will not update its values more frequently than every
 other second; reading them more often will do no harm, but will return
 'old' values.
-
diff --git a/Documentation/hwmon/max1668 b/Documentation/hwmon/max1668.rst
index 8f9d570dbfec..417f17d750e6 100644
--- a/Documentation/hwmon/max1668
+++ b/Documentation/hwmon/max1668.rst
@@ -2,12 +2,17 @@ Kernel driver max1668
 =====================
 
 Supported chips:
+
   * Maxim MAX1668, MAX1805 and MAX1989
+
     Prefix: 'max1668'
+
     Addresses scanned: I2C 0x18, 0x19, 0x1a, 0x29, 0x2a, 0x2b, 0x4c, 0x4d, 0x4e
+
     Datasheet: http://datasheets.maxim-ic.com/en/ds/MAX1668-MAX1989.pdf
 
 Author:
+
     David George <david.george@ska.ac.za>
 
 Description
@@ -23,8 +28,9 @@ two ICs.
 The driver is able to distinguish between the devices and creates sysfs
 entries as follows:
 
-MAX1805, MAX1668 and MAX1989:
+- MAX1805, MAX1668 and MAX1989:
 
+=============== == ============================================================
 temp1_input     ro local (ambient) temperature
 temp1_max       rw local temperature maximum threshold for alarm
 temp1_max_alarm ro local temperature maximum threshold alarm
@@ -40,8 +46,11 @@ temp3_max       rw remote temperature 2 maximum threshold for alarm
 temp3_max_alarm ro remote temperature 2 maximum threshold alarm
 temp3_min       rw remote temperature 2 minimum threshold for alarm
 temp3_min_alarm ro remote temperature 2 minimum threshold alarm
+=============== == ============================================================
+
+- MAX1668 and MAX1989 only:
 
-MAX1668 and MAX1989 only:
+=============== == ============================================================
 temp4_input     ro remote temperature 3
 temp4_max       rw remote temperature 3 maximum threshold for alarm
 temp4_max_alarm ro remote temperature 3 maximum threshold alarm
@@ -52,6 +61,7 @@ temp5_max       rw remote temperature 4 maximum threshold for alarm
 temp5_max_alarm ro remote temperature 4 maximum threshold alarm
 temp5_min       rw remote temperature 4 minimum threshold for alarm
 temp5_min_alarm ro remote temperature 4 minimum threshold alarm
+=============== == ============================================================
 
 Module Parameters
 -----------------
diff --git a/Documentation/hwmon/max197 b/Documentation/hwmon/max197.rst
index 8d89b9009df8..02fe19bc3428 100644
--- a/Documentation/hwmon/max197
+++ b/Documentation/hwmon/max197.rst
@@ -1,16 +1,22 @@
-Maxim MAX197 driver
-===================
+Kernel driver max197
+====================
 
 Author:
+
   * Vivien Didelot <vivien.didelot@savoirfairelinux.com>
 
 Supported chips:
+
   * Maxim MAX197
+
     Prefix: 'max197'
+
     Datasheet: http://datasheets.maxim-ic.com/en/ds/MAX197.pdf
 
   * Maxim MAX199
+
     Prefix: 'max199'
+
     Datasheet: http://datasheets.maxim-ic.com/en/ds/MAX199.pdf
 
 Description
@@ -26,7 +32,7 @@ Platform data
 -------------
 
 The MAX197 platform data (defined in linux/platform_data/max197.h) should be
-filled with a pointer to a conversion function, defined like:
+filled with a pointer to a conversion function, defined like::
 
     int convert(u8 ctrl);
 
@@ -36,25 +42,29 @@ or a negative error code otherwise.
 
 Control byte format:
 
+======= ========== ============================================
 Bit     Name       Description
 7,6     PD1,PD0    Clock and Power-Down modes
 5       ACQMOD     Internal or External Controlled Acquisition
 4       RNG        Full-scale voltage magnitude at the input
 3       BIP        Unipolar or Bipolar conversion mode
 2,1,0   A2,A1,A0   Channel
+======= ========== ============================================
 
 Sysfs interface
 ---------------
 
-* in[0-7]_input: The conversion value for the corresponding channel.
-                 RO
+  ============== ==============================================================
+  in[0-7]_input  The conversion value for the corresponding channel.
+		 RO
 
-* in[0-7]_min:   The lower limit (in mV) for the corresponding channel.
-                 For the MAX197, it will be adjusted to -10000, -5000, or 0.
-                 For the MAX199, it will be adjusted to -4000, -2000, or 0.
-                 RW
+  in[0-7]_min    The lower limit (in mV) for the corresponding channel.
+		 For the MAX197, it will be adjusted to -10000, -5000, or 0.
+		 For the MAX199, it will be adjusted to -4000, -2000, or 0.
+		 RW
 
-* in[0-7]_max:   The higher limit (in mV) for the corresponding channel.
-                 For the MAX197, it will be adjusted to 0, 5000, or 10000.
-                 For the MAX199, it will be adjusted to 0, 2000, or 4000.
-                 RW
+  in[0-7]_max    The higher limit (in mV) for the corresponding channel.
+		 For the MAX197, it will be adjusted to 0, 5000, or 10000.
+		 For the MAX199, it will be adjusted to 0, 2000, or 4000.
+		 RW
+  ============== ==============================================================
diff --git a/Documentation/hwmon/max20751 b/Documentation/hwmon/max20751.rst
index f9fa25ebb521..aa4469be6674 100644
--- a/Documentation/hwmon/max20751
+++ b/Documentation/hwmon/max20751.rst
@@ -2,10 +2,15 @@ Kernel driver max20751
 ======================
 
 Supported chips:
+
   * maxim MAX20751
+
     Prefix: 'max20751'
+
     Addresses scanned: -
+
     Datasheet: http://datasheets.maximintegrated.com/en/ds/MAX20751.pdf
+
     Application note: http://pdfserv.maximintegrated.com/en/an/AN5941.pdf
 
 Author: Guenter Roeck <linux@roeck-us.net>
@@ -18,7 +23,7 @@ This driver supports MAX20751 Multiphase Master with PMBus Interface
 and Internal Buck Converter.
 
 The driver is a client driver to the core PMBus driver.
-Please see Documentation/hwmon/pmbus for details on PMBus client drivers.
+Please see Documentation/hwmon/pmbus.rst for details on PMBus client drivers.
 
 
 Usage Notes
@@ -40,6 +45,7 @@ Sysfs entries
 
 The following attributes are supported.
 
+======================= =======================================================
 in1_label		"vin1"
 in1_input		Measured voltage.
 in1_min			Minimum input voltage.
@@ -75,3 +81,4 @@ temp1_crit_alarm	Chip temperature critical high alarm.
 
 power1_input		Output power.
 power1_label		"pout1"
+======================= =======================================================
diff --git a/Documentation/hwmon/max31722 b/Documentation/hwmon/max31722.rst
index 090da84538c8..0ab15c00b226 100644
--- a/Documentation/hwmon/max31722
+++ b/Documentation/hwmon/max31722.rst
@@ -2,15 +2,25 @@ Kernel driver max31722
 ======================
 
 Supported chips:
+
   * Maxim Integrated MAX31722
+
     Prefix: 'max31722'
+
     ACPI ID: MAX31722
+
     Addresses scanned: -
+
     Datasheet: https://datasheets.maximintegrated.com/en/ds/MAX31722-MAX31723.pdf
+
   * Maxim Integrated MAX31723
+
     Prefix: 'max31723'
+
     ACPI ID: MAX31723
+
     Addresses scanned: -
+
     Datasheet: https://datasheets.maximintegrated.com/en/ds/MAX31722-MAX31723.pdf
 
 Author: Tiberiu Breana <tiberiu.a.breana@intel.com>
@@ -31,4 +41,6 @@ Sysfs entries
 
 The following attribute is supported:
 
+======================= =======================================================
 temp1_input		Measured temperature. Read-only.
+======================= =======================================================
diff --git a/Documentation/hwmon/max31785 b/Documentation/hwmon/max31785.rst
index 270c5f865261..c8c6756d0ee1 100644
--- a/Documentation/hwmon/max31785
+++ b/Documentation/hwmon/max31785.rst
@@ -2,9 +2,13 @@ Kernel driver max31785
 ======================
 
 Supported chips:
+
   * Maxim MAX31785, MAX31785A
+
     Prefix: 'max31785' or 'max31785a'
+
     Addresses scanned: -
+
     Datasheet: https://datasheets.maximintegrated.com/en/ds/MAX31785.pdf
 
 Author: Andrew Jeffery <andrew@aj.id.au>
@@ -30,6 +34,7 @@ devices explicitly.
 Sysfs attributes
 ----------------
 
+======================= =======================================================
 fan[1-4]_alarm		Fan alarm.
 fan[1-4]_fault		Fan fault.
 fan[1-8]_input		Fan RPM. On the MAX31785A, inputs 5-8 correspond to the
@@ -58,3 +63,4 @@ temp[1-11]_crit_alarm	Chip temperature critical high alarm
 temp[1-11]_input	Measured temperature
 temp[1-11]_max		Maximum temperature
 temp[1-11]_max_alarm	Chip temperature high alarm
+======================= =======================================================
diff --git a/Documentation/hwmon/max31790 b/Documentation/hwmon/max31790.rst
index 855e62430da9..84c62a12ef3a 100644
--- a/Documentation/hwmon/max31790
+++ b/Documentation/hwmon/max31790.rst
@@ -2,9 +2,13 @@ Kernel driver max31790
 ======================
 
 Supported chips:
+
   * Maxim MAX31790
+
     Prefix: 'max31790'
+
     Addresses scanned: -
+
     Datasheet: http://pdfserv.maximintegrated.com/en/ds/MAX31790.pdf
 
 Author: Il Han <corone.il.han@gmail.com>
@@ -30,8 +34,10 @@ also be configured to serve as tachometer inputs.
 Sysfs entries
 -------------
 
+================== === =======================================================
 fan[1-12]_input    RO  fan tachometer speed in RPM
 fan[1-12]_fault    RO  fan experienced fault
 fan[1-6]_target    RW  desired fan speed in RPM
 pwm[1-6]_enable    RW  regulator mode, 0=disabled, 1=manual mode, 2=rpm mode
 pwm[1-6]           RW  fan target duty cycle (0-255)
+================== === =======================================================
diff --git a/Documentation/hwmon/max34440 b/Documentation/hwmon/max34440.rst
index b2de8fa49273..939138e12b02 100644
--- a/Documentation/hwmon/max34440
+++ b/Documentation/hwmon/max34440.rst
@@ -2,34 +2,63 @@ Kernel driver max34440
 ======================
 
 Supported chips:
+
   * Maxim MAX34440
+
     Prefixes: 'max34440'
+
     Addresses scanned: -
+
     Datasheet: http://datasheets.maximintegrated.com/en/ds/MAX34440.pdf
+
   * Maxim MAX34441
+
     PMBus 5-Channel Power-Supply Manager and Intelligent Fan Controller
+
     Prefixes: 'max34441'
+
     Addresses scanned: -
+
     Datasheet: http://datasheets.maximintegrated.com/en/ds/MAX34441.pdf
+
   * Maxim MAX34446
+
     PMBus Power-Supply Data Logger
+
     Prefixes: 'max34446'
+
     Addresses scanned: -
+
     Datasheet: http://datasheets.maximintegrated.com/en/ds/MAX34446.pdf
+
   * Maxim MAX34451
+
     PMBus 16-Channel V/I Monitor and 12-Channel Sequencer/Marginer
+
     Prefixes: 'max34451'
+
     Addresses scanned: -
+
     Datasheet: http://datasheets.maximintegrated.com/en/ds/MAX34451.pdf
+
   * Maxim MAX34460
+
     PMBus 12-Channel Voltage Monitor & Sequencer
+
     Prefix: 'max34460'
+
     Addresses scanned: -
+
     Datasheet: http://datasheets.maximintegrated.com/en/ds/MAX34460.pdf
+
   * Maxim MAX34461
+
     PMBus 16-Channel Voltage Monitor & Sequencer
+
     Prefix: 'max34461'
+
     Addresses scanned: -
+
     Datasheet: http://datasheets.maximintegrated.com/en/ds/MAX34461.pdf
 
 Author: Guenter Roeck <linux@roeck-us.net>
@@ -47,7 +76,7 @@ based on GIN pins. The MAX34460 supports 12 voltage channels, and the MAX34461
 supports 16 voltage channels.
 
 The driver is a client driver to the core PMBus driver. Please see
-Documentation/hwmon/pmbus for details on PMBus client drivers.
+Documentation/hwmon/pmbus.rst for details on PMBus client drivers.
 
 
 Usage Notes
@@ -77,42 +106,67 @@ Sysfs entries
 The following attributes are supported. Limits are read-write; all other
 attributes are read-only.
 
+In
+~~
+
+======================= =======================================================
 in[1-6]_label		"vout[1-6]".
 in[1-6]_input		Measured voltage. From READ_VOUT register.
 in[1-6]_min		Minimum Voltage. From VOUT_UV_WARN_LIMIT register.
 in[1-6]_max		Maximum voltage. From VOUT_OV_WARN_LIMIT register.
 in[1-6]_lcrit		Critical minimum Voltage. VOUT_UV_FAULT_LIMIT register.
-in[1-6]_crit		Critical maximum voltage. From VOUT_OV_FAULT_LIMIT register.
+in[1-6]_crit		Critical maximum voltage. From VOUT_OV_FAULT_LIMIT
+			register.
 in[1-6]_min_alarm	Voltage low alarm. From VOLTAGE_UV_WARNING status.
 in[1-6]_max_alarm	Voltage high alarm. From VOLTAGE_OV_WARNING status.
-in[1-6]_lcrit_alarm	Voltage critical low alarm. From VOLTAGE_UV_FAULT status.
-in[1-6]_crit_alarm	Voltage critical high alarm. From VOLTAGE_OV_FAULT status.
+in[1-6]_lcrit_alarm	Voltage critical low alarm. From VOLTAGE_UV_FAULT
+			status.
+in[1-6]_crit_alarm	Voltage critical high alarm. From VOLTAGE_OV_FAULT
+			status.
 in[1-6]_lowest		Historical minimum voltage.
 in[1-6]_highest		Historical maximum voltage.
 in[1-6]_reset_history	Write any value to reset history.
+======================= =======================================================
+
+.. note:: MAX34446 only supports in[1-4].
 
-			MAX34446 only supports in[1-4].
+Curr
+~~~~
 
+======================= ========================================================
 curr[1-6]_label		"iout[1-6]".
 curr[1-6]_input		Measured current. From READ_IOUT register.
 curr[1-6]_max		Maximum current. From IOUT_OC_WARN_LIMIT register.
-curr[1-6]_crit		Critical maximum current. From IOUT_OC_FAULT_LIMIT register.
+curr[1-6]_crit		Critical maximum current. From IOUT_OC_FAULT_LIMIT
+			register.
 curr[1-6]_max_alarm	Current high alarm. From IOUT_OC_WARNING status.
 curr[1-6]_crit_alarm	Current critical high alarm. From IOUT_OC_FAULT status.
 curr[1-4]_average	Historical average current (MAX34446/34451 only).
 curr[1-6]_highest	Historical maximum current.
 curr[1-6]_reset_history	Write any value to reset history.
+======================= ========================================================
+
+.. note::
+
+    - in6 and curr6 attributes only exist for MAX34440.
+    - MAX34446 only supports curr[1-4].
 
-			in6 and curr6 attributes only exist for MAX34440.
-			MAX34446 only supports curr[1-4].
+Power
+~~~~~
 
+======================= ========================================================
 power[1,3]_label	"pout[1,3]"
 power[1,3]_input	Measured power.
 power[1,3]_average	Historical average power.
 power[1,3]_highest	Historical maximum power.
+======================= ========================================================
 
-			Power attributes only exist for MAX34446.
+.. note:: Power attributes only exist for MAX34446.
 
+Temp
+~~~~
+
+======================= ========================================================
 temp[1-8]_input		Measured temperatures. From READ_TEMPERATURE_1 register.
 			temp1 is the chip's internal temperature. temp2..temp5
 			are remote I2C temperature sensors. For MAX34441, temp6
@@ -125,11 +179,17 @@ temp[1-8]_crit_alarm	Temperature critical high alarm.
 temp[1-8]_average	Historical average temperature (MAX34446 only).
 temp[1-8]_highest	Historical maximum temperature.
 temp[1-8]_reset_history	Write any value to reset history.
+======================= ========================================================
+
+
+.. note::
+   - temp7 and temp8 attributes only exist for MAX34440.
+   - MAX34446 only supports temp[1-3].
+
 
-			temp7 and temp8 attributes only exist for MAX34440.
-			MAX34446 only supports temp[1-3].
+.. note::
 
-MAX34451 supports attribute groups in[1-16] (or curr[1-16] based on input pins)
-and temp[1-5].
-MAX34460 supports attribute groups in[1-12] and temp[1-5].
-MAX34461 supports attribute groups in[1-16] and temp[1-5].
+   - MAX34451 supports attribute groups in[1-16] (or curr[1-16] based on
+     input pins) and temp[1-5].
+   - MAX34460 supports attribute groups in[1-12] and temp[1-5].
+   - MAX34461 supports attribute groups in[1-16] and temp[1-5].
diff --git a/Documentation/hwmon/max6639 b/Documentation/hwmon/max6639.rst
index dc49f8be7167..3da54225f83c 100644
--- a/Documentation/hwmon/max6639
+++ b/Documentation/hwmon/max6639.rst
@@ -2,14 +2,18 @@ Kernel driver max6639
 =====================
 
 Supported chips:
+
   * Maxim MAX6639
+
     Prefix: 'max6639'
+
     Addresses scanned: I2C 0x2c, 0x2e, 0x2f
+
     Datasheet: http://pdfserv.maxim-ic.com/en/ds/MAX6639.pdf
 
 Authors:
-    He Changqing <hechangqing@semptian.com>
-    Roland Stigge <stigge@antcom.de>
+    - He Changqing <hechangqing@semptian.com>
+    - Roland Stigge <stigge@antcom.de>
 
 Description
 -----------
@@ -21,19 +25,20 @@ diode-connected transistors.
 
 The following device attributes are implemented via sysfs:
 
+====================== ==== ===================================================
 Attribute              R/W  Contents
-----------------------------------------------------------------------------
+====================== ==== ===================================================
 temp1_input            R    Temperature channel 1 input (0..150 C)
 temp2_input            R    Temperature channel 2 input (0..150 C)
 temp1_fault            R    Temperature channel 1 diode fault
 temp2_fault            R    Temperature channel 2 diode fault
 temp1_max              RW   Set THERM temperature for input 1
-                            (in C, see datasheet)
+			    (in C, see datasheet)
 temp2_max              RW   Set THERM temperature for input 2
 temp1_crit             RW   Set ALERT temperature for input 1
 temp2_crit             RW   Set ALERT temperature for input 2
 temp1_emergency        RW   Set OT temperature for input 1
-                            (in C, see datasheet)
+			    (in C, see datasheet)
 temp2_emergency        RW   Set OT temperature for input 2
 pwm1                   RW   Fan 1 target duty cycle (0..255)
 pwm2                   RW   Fan 2 target duty cycle (0..255)
@@ -47,3 +52,4 @@ temp1_crit_alarm       R    Alarm on ALERT temperature on channel 1
 temp2_crit_alarm       R    Alarm on ALERT temperature on channel 2
 temp1_emergency_alarm  R    Alarm on OT temperature on channel 1
 temp2_emergency_alarm  R    Alarm on OT temperature on channel 2
+====================== ==== ===================================================
diff --git a/Documentation/hwmon/max6642 b/Documentation/hwmon/max6642.rst
index afbd3e4942e2..7e5b7d4f9492 100644
--- a/Documentation/hwmon/max6642
+++ b/Documentation/hwmon/max6642.rst
@@ -2,14 +2,20 @@ Kernel driver max6642
 =====================
 
 Supported chips:
+
   * Maxim MAX6642
+
     Prefix: 'max6642'
+
     Addresses scanned: I2C 0x48-0x4f
+
     Datasheet: Publicly available at the Maxim website
-               http://datasheets.maxim-ic.com/en/ds/MAX6642.pdf
+
+	       http://datasheets.maxim-ic.com/en/ds/MAX6642.pdf
 
 Authors:
-        Per Dalen <per.dalen@appeartv.com>
+
+	Per Dalen <per.dalen@appeartv.com>
 
 Description
 -----------
diff --git a/Documentation/hwmon/max6650 b/Documentation/hwmon/max6650.rst
index dff1d296a48b..253482add082 100644
--- a/Documentation/hwmon/max6650
+++ b/Documentation/hwmon/max6650.rst
@@ -2,19 +2,27 @@ Kernel driver max6650
 =====================
 
 Supported chips:
+
   * Maxim MAX6650
+
     Prefix: 'max6650'
+
     Addresses scanned: none
+
     Datasheet: http://pdfserv.maxim-ic.com/en/ds/MAX6650-MAX6651.pdf
+
   * Maxim MAX6651
+
     Prefix: 'max6651'
+
     Addresses scanned: none
+
     Datasheet: http://pdfserv.maxim-ic.com/en/ds/MAX6650-MAX6651.pdf
 
 Authors:
-    Hans J. Koch <hjk@hansjkoch.de>
-    John Morris <john.morris@spirentcom.com>
-    Claus Gindhart <claus.gindhart@kontron.com>
+    - Hans J. Koch <hjk@hansjkoch.de>
+    - John Morris <john.morris@spirentcom.com>
+    - Claus Gindhart <claus.gindhart@kontron.com>
 
 Description
 -----------
@@ -28,6 +36,7 @@ The driver is not able to distinguish between the 2 devices.
 
 The driver provides the following sensor accesses in sysfs:
 
+=============== ======= =======================================================
 fan1_input	ro	fan tachometer speed in RPM
 fan2_input	ro	"
 fan3_input	ro	"
@@ -40,6 +49,7 @@ pwm1		rw	relative speed (0-255), 255=max. speed.
 fan1_div	rw	sets the speed range the inputs can handle. Legal
 			values are 1, 2, 4, and 8. Use lower values for
 			faster fans.
+=============== ======= =======================================================
 
 Usage notes
 -----------
@@ -62,4 +72,3 @@ clock: The clock frequency in Hz of the chip the driver should assume [254000]
 
 Please have a look at the MAX6650/6651 data sheet and make sure that you fully
 understand the meaning of these parameters before you attempt to change them.
-
diff --git a/Documentation/hwmon/max6697 b/Documentation/hwmon/max6697.rst
index 6594177ededa..ffc5a7d8d33b 100644
--- a/Documentation/hwmon/max6697
+++ b/Documentation/hwmon/max6697.rst
@@ -2,38 +2,69 @@ Kernel driver max6697
 =====================
 
 Supported chips:
+
   * Maxim MAX6581
+
     Prefix: 'max6581'
+
     Datasheet: http://datasheets.maximintegrated.com/en/ds/MAX6581.pdf
+
   * Maxim MAX6602
+
     Prefix: 'max6602'
+
     Datasheet: http://datasheets.maximintegrated.com/en/ds/MAX6602.pdf
+
   * Maxim MAX6622
+
     Prefix: 'max6622'
+
     Datasheet: http://datasheets.maximintegrated.com/en/ds/MAX6622.pdf
+
   * Maxim MAX6636
+
     Prefix: 'max6636'
+
     Datasheet: http://datasheets.maximintegrated.com/en/ds/MAX6636.pdf
+
   * Maxim MAX6689
+
     Prefix: 'max6689'
+
     Datasheet: http://datasheets.maximintegrated.com/en/ds/MAX6689.pdf
+
   * Maxim MAX6693
+
     Prefix: 'max6693'
+
     Datasheet: http://datasheets.maximintegrated.com/en/ds/MAX6693.pdf
+
   * Maxim MAX6694
+
     Prefix: 'max6694'
+
     Datasheet: http://datasheets.maximintegrated.com/en/ds/MAX6694.pdf
+
   * Maxim MAX6697
+
     Prefix: 'max6697'
+
     Datasheet: http://datasheets.maximintegrated.com/en/ds/MAX6697.pdf
+
   * Maxim MAX6698
+
     Prefix: 'max6698'
+
     Datasheet: http://datasheets.maximintegrated.com/en/ds/MAX6698.pdf
+
   * Maxim MAX6699
+
     Prefix: 'max6699'
+
     Datasheet: http://datasheets.maximintegrated.com/en/ds/MAX6699.pdf
 
 Author:
+
     Guenter Roeck <linux@roeck-us.net>
 
 Description
@@ -50,9 +81,11 @@ The driver provides the following sysfs attributes. temp1 is the local (chip)
 temperature, temp[2..n] are remote temperatures. The actually supported
 per-channel attributes are chip type and channel dependent.
 
+================ == ==========================================================
 tempX_input      RO temperature
 tempX_max        RW temperature maximum threshold
 tempX_max_alarm  RO temperature maximum threshold alarm
 tempX_crit       RW temperature critical threshold
 tempX_crit_alarm RO temperature critical threshold alarm
 tempX_fault      RO temperature diode fault (remote sensors only)
+================ == ==========================================================
diff --git a/Documentation/hwmon/max8688 b/Documentation/hwmon/max8688.rst
index ca233bec7a8a..009487759c61 100644
--- a/Documentation/hwmon/max8688
+++ b/Documentation/hwmon/max8688.rst
@@ -2,9 +2,13 @@ Kernel driver max8688
 =====================
 
 Supported chips:
+
   * Maxim MAX8688
+
     Prefix: 'max8688'
+
     Addresses scanned: -
+
     Datasheet: http://datasheets.maxim-ic.com/en/ds/MAX8688.pdf
 
 Author: Guenter Roeck <linux@roeck-us.net>
@@ -17,7 +21,7 @@ This driver supports hardware monitoring for Maxim MAX8688 Digital Power-Supply
 Controller/Monitor with PMBus Interface.
 
 The driver is a client driver to the core PMBus driver. Please see
-Documentation/hwmon/pmbus for details on PMBus client drivers.
+Documentation/hwmon/pmbus.rst for details on PMBus client drivers.
 
 
 Usage Notes
@@ -40,23 +44,28 @@ Sysfs entries
 The following attributes are supported. Limits are read-write; all other
 attributes are read-only.
 
+======================= ========================================================
 in1_label		"vout1"
 in1_input		Measured voltage. From READ_VOUT register.
 in1_min			Minimum Voltage. From VOUT_UV_WARN_LIMIT register.
 in1_max			Maximum voltage. From VOUT_OV_WARN_LIMIT register.
 in1_lcrit		Critical minimum Voltage. VOUT_UV_FAULT_LIMIT register.
-in1_crit		Critical maximum voltage. From VOUT_OV_FAULT_LIMIT register.
+in1_crit		Critical maximum voltage. From VOUT_OV_FAULT_LIMIT
+			register.
 in1_min_alarm		Voltage low alarm. From VOLTAGE_UV_WARNING status.
 in1_max_alarm		Voltage high alarm. From VOLTAGE_OV_WARNING status.
-in1_lcrit_alarm		Voltage critical low alarm. From VOLTAGE_UV_FAULT status.
-in1_crit_alarm		Voltage critical high alarm. From VOLTAGE_OV_FAULT status.
+in1_lcrit_alarm		Voltage critical low alarm. From VOLTAGE_UV_FAULT
+			status.
+in1_crit_alarm		Voltage critical high alarm. From VOLTAGE_OV_FAULT
+			status.
 in1_highest		Historical maximum voltage.
 in1_reset_history	Write any value to reset history.
 
 curr1_label		"iout1"
 curr1_input		Measured current. From READ_IOUT register.
 curr1_max		Maximum current. From IOUT_OC_WARN_LIMIT register.
-curr1_crit		Critical maximum current. From IOUT_OC_FAULT_LIMIT register.
+curr1_crit		Critical maximum current. From IOUT_OC_FAULT_LIMIT
+			register.
 curr1_max_alarm		Current high alarm. From IOUT_OC_WARN_LIMIT register.
 curr1_crit_alarm	Current critical high alarm. From IOUT_OC_FAULT status.
 curr1_highest		Historical maximum current.
@@ -73,3 +82,4 @@ temp1_crit_alarm	Chip temperature critical high alarm. Set by comparing
 			status is set.
 temp1_highest		Historical maximum temperature.
 temp1_reset_history	Write any value to reset history.
+======================= ========================================================
diff --git a/Documentation/hwmon/mc13783-adc b/Documentation/hwmon/mc13783-adc.rst
index 05ccc9f159f1..cae70350ba2f 100644
--- a/Documentation/hwmon/mc13783-adc
+++ b/Documentation/hwmon/mc13783-adc.rst
@@ -2,16 +2,25 @@ Kernel driver mc13783-adc
 =========================
 
 Supported chips:
+
   * Freescale MC13783
+
     Prefix: 'mc13783'
+
     Datasheet: https://www.nxp.com/docs/en/data-sheet/MC13783.pdf
+
   * Freescale MC13892
+
     Prefix: 'mc13892'
+
     Datasheet: https://www.nxp.com/docs/en/data-sheet/MC13892.pdf
 
+
+
 Authors:
-    Sascha Hauer <s.hauer@pengutronix.de>
-    Luotao Fu <l.fu@pengutronix.de>
+
+   - Sascha Hauer <s.hauer@pengutronix.de>
+   - Luotao Fu <l.fu@pengutronix.de>
 
 Description
 -----------
@@ -30,9 +39,11 @@ the General Purpose inputs and touchscreen.
 See the following tables for the meaning of the different channels and their
 chip internal scaling:
 
-MC13783:
+- MC13783:
+
+======= =============================================== =============== =======
 Channel	Signal						Input Range	Scaling
--------------------------------------------------------------------------------
+======= =============================================== =============== =======
 0	Battery Voltage (BATT)				2.50 - 4.65V	-2.40V
 1	Battery Current (BATT - BATTISNS)		-50 - 50 mV	x20
 2	Application Supply (BP)				2.50 - 4.65V	-2.40V
@@ -52,10 +63,13 @@ Channel	Signal						Input Range	Scaling
 13	General Purpose TSX2 / Touchscreen X-plate 2	0 - 2.30V	No
 14	General Purpose TSY1 / Touchscreen Y-plate 1	0 - 2.30V	No
 15	General Purpose TSY2 / Touchscreen Y-plate 2	0 - 2.30V	No
+======= =============================================== =============== =======
+
+- MC13892:
 
-MC13892:
+======= =============================================== =============== =======
 Channel	Signal						Input Range	Scaling
--------------------------------------------------------------------------------
+======= =============================================== =============== =======
 0	Battery Voltage (BATT)				0 - 4.8V	/2
 1	Battery Current (BATT - BATTISNSCC)		-60 - 60 mV	x20
 2	Application Supply (BPSNS)			0 - 4.8V	/2
@@ -72,3 +86,4 @@ Channel	Signal						Input Range	Scaling
 13	General Purpose TSX2 / Touchscreen X-plate 2	0 - 2.4V	No
 14	General Purpose TSY1 / Touchscreen Y-plate 1	0 - 2.4V	No
 15	General Purpose TSY2 / Touchscreen Y-plate 2	0 - 2.4V	No
+======= =============================================== =============== =======
diff --git a/Documentation/hwmon/mcp3021 b/Documentation/hwmon/mcp3021.rst
index 74a6b72adf5f..83f4bda2f269 100644
--- a/Documentation/hwmon/mcp3021
+++ b/Documentation/hwmon/mcp3021.rst
@@ -1,17 +1,26 @@
 Kernel driver MCP3021
-======================
+=====================
 
 Supported chips:
+
   * Microchip Technology MCP3021
+
     Prefix: 'mcp3021'
+
     Datasheet: http://ww1.microchip.com/downloads/en/DeviceDoc/21805a.pdf
+
   * Microchip Technology MCP3221
+
     Prefix: 'mcp3221'
+
     Datasheet: http://ww1.microchip.com/downloads/en/DeviceDoc/21732c.pdf
 
+
+
 Authors:
-   Mingkai Hu
-   Sven Schuchmann <schuchmann@schleissheimer.de>
+
+   - Mingkai Hu
+   - Sven Schuchmann <schuchmann@schleissheimer.de>
 
 Description
 -----------
diff --git a/Documentation/hwmon/menf21bmc b/Documentation/hwmon/menf21bmc.rst
index 2a273a065c5e..1f0c6b2235ab 100644
--- a/Documentation/hwmon/menf21bmc
+++ b/Documentation/hwmon/menf21bmc.rst
@@ -2,8 +2,11 @@ Kernel driver menf21bmc_hwmon
 =============================
 
 Supported chips:
+
 	* MEN 14F021P00
+
 	  Prefix: 'menf21bmc_hwmon'
+
 	  Adresses scanned: -
 
 Author: Andreas Werner <andreas.werner@men.de>
@@ -34,6 +37,7 @@ Sysfs entries
 The following attributes are supported. All attributes are read only
 The Limits are read once by the driver.
 
+=============== ==========================
 in0_input	+3.3V input voltage
 in1_input	+5.0V input voltage
 in2_input	+12.0V input voltage
@@ -48,3 +52,4 @@ in1_label	"MON_5V"
 in2_label	"MON_12V"
 in3_label	"5V_STANDBY"
 in4_label	"VBAT"
+=============== ==========================
diff --git a/Documentation/hwmon/mlxreg-fan b/Documentation/hwmon/mlxreg-fan.rst
index fc531c6978d4..c92b8e885f7e 100644
--- a/Documentation/hwmon/mlxreg-fan
+++ b/Documentation/hwmon/mlxreg-fan.rst
@@ -2,32 +2,38 @@ Kernel driver mlxreg-fan
 ========================
 
 Provides FAN control for the next Mellanox systems:
-QMB700, equipped with 40x200GbE InfiniBand ports;
-MSN3700, equipped with 32x200GbE or 16x400GbE Ethernet ports;
-MSN3410, equipped with 6x400GbE plus 48x50GbE Ethernet ports;
-MSN3800, equipped with 64x1000GbE Ethernet ports;
+
+- QMB700, equipped with 40x200GbE InfiniBand ports;
+- MSN3700, equipped with 32x200GbE or 16x400GbE Ethernet ports;
+- MSN3410, equipped with 6x400GbE plus 48x50GbE Ethernet ports;
+- MSN3800, equipped with 64x1000GbE Ethernet ports;
+
+Author: Vadim Pasternak <vadimp@mellanox.com>
+
 These are the Top of the Rack systems, equipped with Mellanox switch
 board with Mellanox Quantum or Spectrume-2 devices.
 FAN controller is implemented by the programmable device logic.
 
 The default registers offsets set within the programmable device is as
 following:
-- pwm1			0xe3
-- fan1 (tacho1)		0xe4
-- fan2 (tacho2)		0xe5
-- fan3 (tacho3)		0xe6
-- fan4 (tacho4)		0xe7
-- fan5 (tacho5)		0xe8
-- fan6 (tacho6)		0xe9
-- fan7 (tacho7)		0xea
-- fan8 (tacho8)		0xeb
-- fan9 (tacho9)		0xec
-- fan10 (tacho10)	0xed
-- fan11 (tacho11)	0xee
-- fan12 (tacho12)	0xef
-This setup can be re-programmed with other registers.
 
-Author: Vadim Pasternak <vadimp@mellanox.com>
+======================= ====
+pwm1			0xe3
+fan1 (tacho1)		0xe4
+fan2 (tacho2)		0xe5
+fan3 (tacho3)		0xe6
+fan4 (tacho4)		0xe7
+fan5 (tacho5)		0xe8
+fan6 (tacho6)		0xe9
+fan7 (tacho7)		0xea
+fan8 (tacho8)		0xeb
+fan9 (tacho9)		0xec
+fan10 (tacho10)		0xed
+fan11 (tacho11)		0xee
+fan12 (tacho12)		0xef
+======================= ====
+
+This setup can be re-programmed with other registers.
 
 Description
 -----------
@@ -48,13 +54,17 @@ thermal's sysfs interfaces.
 /sys files in hwmon subsystem
 -----------------------------
 
-fan[1-12]_fault - RO files for tachometers TACH1-TACH12 fault indication
-fan[1-12]_input - RO files for tachometers TACH1-TACH12 input (in RPM)
-pwm1		- RW file for fan[1-12] target duty cycle (0..255)
+================= == ===================================================
+fan[1-12]_fault   RO files for tachometers TACH1-TACH12 fault indication
+fan[1-12]_input   RO files for tachometers TACH1-TACH12 input (in RPM)
+pwm1		  RW file for fan[1-12] target duty cycle (0..255)
+================= == ===================================================
 
 /sys files in thermal subsystem
 -------------------------------
 
-cur_state	- RW file for current cooling state of the cooling device
-		  (0..max_state)
-max_state	- RO file for maximum cooling state of the cooling device
+================= == ====================================================
+cur_state	  RW file for current cooling state of the cooling device
+		     (0..max_state)
+max_state	  RO file for maximum cooling state of the cooling device
+================= == ====================================================
diff --git a/Documentation/hwmon/nct6683 b/Documentation/hwmon/nct6683.rst
index c1301d4300cd..efbf7e9703ec 100644
--- a/Documentation/hwmon/nct6683
+++ b/Documentation/hwmon/nct6683.rst
@@ -2,13 +2,18 @@ Kernel driver nct6683
 =====================
 
 Supported chips:
+
   * Nuvoton NCT6683D
+
     Prefix: 'nct6683'
+
     Addresses scanned: ISA address retrieved from Super I/O registers
+
     Datasheet: Available from Nuvoton upon request
 
 Authors:
-        Guenter Roeck <linux@roeck-us.net>
+
+	Guenter Roeck <linux@roeck-us.net>
 
 Description
 -----------
@@ -50,8 +55,10 @@ Tested Boards and Firmware Versions
 The driver has been reported to work with the following boards and
 firmware versions.
 
+=============== ===============================================
 Board		Firmware version
----------------------------------------------------------------
+=============== ===============================================
 Intel DH87RL	NCT6683D EC firmware version 1.0 build 04/03/13
 Intel DH87MC	NCT6683D EC firmware version 1.0 build 04/03/13
 Intel DB85FL	NCT6683D EC firmware version 1.0 build 04/03/13
+=============== ===============================================
diff --git a/Documentation/hwmon/nct6775 b/Documentation/hwmon/nct6775.rst
index bd59834d310f..1d0315c40952 100644
--- a/Documentation/hwmon/nct6775
+++ b/Documentation/hwmon/nct6775.rst
@@ -1,52 +1,90 @@
-Note
-====
-
-This driver supersedes the NCT6775F and NCT6776F support in the W83627EHF
-driver.
-
 Kernel driver NCT6775
 =====================
 
+.. note::
+
+    This driver supersedes the NCT6775F and NCT6776F support in the W83627EHF
+    driver.
+
 Supported chips:
+
   * Nuvoton NCT6102D/NCT6104D/NCT6106D
+
     Prefix: 'nct6106'
+
     Addresses scanned: ISA address retrieved from Super I/O registers
+
     Datasheet: Available from the Nuvoton web site
+
   * Nuvoton NCT5572D/NCT6771F/NCT6772F/NCT6775F/W83677HG-I
+
     Prefix: 'nct6775'
+
     Addresses scanned: ISA address retrieved from Super I/O registers
+
     Datasheet: Available from Nuvoton upon request
+
   * Nuvoton NCT5573D/NCT5577D/NCT6776D/NCT6776F
+
     Prefix: 'nct6776'
+
     Addresses scanned: ISA address retrieved from Super I/O registers
+
     Datasheet: Available from Nuvoton upon request
+
   * Nuvoton NCT5532D/NCT6779D
+
     Prefix: 'nct6779'
+
     Addresses scanned: ISA address retrieved from Super I/O registers
+
     Datasheet: Available from Nuvoton upon request
+
   * Nuvoton NCT6791D
+
     Prefix: 'nct6791'
+
     Addresses scanned: ISA address retrieved from Super I/O registers
+
     Datasheet: Available from Nuvoton upon request
+
   * Nuvoton NCT6792D
+
     Prefix: 'nct6792'
+
     Addresses scanned: ISA address retrieved from Super I/O registers
+
     Datasheet: Available from Nuvoton upon request
+
   * Nuvoton NCT6793D
+
     Prefix: 'nct6793'
+
     Addresses scanned: ISA address retrieved from Super I/O registers
+
     Datasheet: Available from Nuvoton upon request
+
   * Nuvoton NCT6795D
+
     Prefix: 'nct6795'
+
     Addresses scanned: ISA address retrieved from Super I/O registers
+
     Datasheet: Available from Nuvoton upon request
+
   * Nuvoton NCT6796D
+
     Prefix: 'nct6796'
+
     Addresses scanned: ISA address retrieved from Super I/O registers
+
     Datasheet: Available from Nuvoton upon request
 
+
+
 Authors:
-        Guenter Roeck <linux@roeck-us.net>
+
+	Guenter Roeck <linux@roeck-us.net>
 
 Description
 -----------
@@ -96,10 +134,14 @@ The mode works for fan1-fan5.
 sysfs attributes
 ----------------
 
-pwm[1-7] - this file stores PWM duty cycle or DC value (fan speed) in range:
+pwm[1-7]
+    - this file stores PWM duty cycle or DC value (fan speed) in range:
+
 	   0 (lowest speed) to 255 (full)
 
-pwm[1-7]_enable - this file controls mode of fan/temperature control:
+pwm[1-7]_enable
+    - this file controls mode of fan/temperature control:
+
 	* 0 Fan control disabled (fans set to maximum speed)
 	* 1 Manual mode, write to pwm[0-5] any value 0-255
 	* 2 "Thermal Cruise" mode
@@ -107,15 +149,19 @@ pwm[1-7]_enable - this file controls mode of fan/temperature control:
 	* 4 "Smart Fan III" mode (NCT6775F only)
 	* 5 "Smart Fan IV" mode
 
-pwm[1-7]_mode - controls if output is PWM or DC level
-        * 0 DC output
-        * 1 PWM output
+pwm[1-7]_mode
+    - controls if output is PWM or DC level
+
+	* 0 DC output
+	* 1 PWM output
 
 Common fan control attributes
 -----------------------------
 
-pwm[1-7]_temp_sel	Temperature source. Value is temperature sensor index.
+pwm[1-7]_temp_sel
+			Temperature source. Value is temperature sensor index.
 			For example, select '1' for temp1_input.
+
 pwm[1-7]_weight_temp_sel
 			Secondary temperature source. Value is temperature
 			sensor index. For example, select '1' for temp1_input.
@@ -126,13 +172,16 @@ following attributes.
 
 pwm[1-7]_weight_duty_step
 			Duty step size.
+
 pwm[1-7]_weight_temp_step
 			Temperature step size. With each step over
 			temp_step_base, the value of weight_duty_step is added
 			to the current pwm value.
+
 pwm[1-7]_weight_temp_step_base
 			Temperature at which secondary temperature control kicks
 			in.
+
 pwm[1-7]_weight_temp_step_tol
 			Temperature step tolerance.
 
@@ -141,24 +190,35 @@ Thermal Cruise mode (2)
 
 If the temperature is in the range defined by:
 
-pwm[1-7]_target_temp	Target temperature, unit millidegree Celsius
+pwm[1-7]_target_temp
+			Target temperature, unit millidegree Celsius
 			(range 0 - 127000)
+
 pwm[1-7]_temp_tolerance
 			Target temperature tolerance, unit millidegree Celsius
 
-there are no changes to fan speed. Once the temperature leaves the interval, fan
+There are no changes to fan speed. Once the temperature leaves the interval, fan
 speed increases (if temperature is higher that desired) or decreases (if
 temperature is lower than desired), using the following limits and time
 intervals.
 
-pwm[1-7]_start		fan pwm start value (range 1 - 255), to start fan
+pwm[1-7]_start
+			fan pwm start value (range 1 - 255), to start fan
 			when the temperature is above defined range.
-pwm[1-7]_floor		lowest fan pwm (range 0 - 255) if temperature is below
+
+pwm[1-7]_floor
+			lowest fan pwm (range 0 - 255) if temperature is below
 			the defined range. If set to 0, the fan is expected to
 			stop if the temperature is below the defined range.
-pwm[1-7]_step_up_time	milliseconds before fan speed is increased
-pwm[1-7]_step_down_time	milliseconds before fan speed is decreased
-pwm[1-7]_stop_time	how many milliseconds must elapse to switch
+
+pwm[1-7]_step_up_time
+			milliseconds before fan speed is increased
+
+pwm[1-7]_step_down_time
+			milliseconds before fan speed is decreased
+
+pwm[1-7]_stop_time
+			how many milliseconds must elapse to switch
 			corresponding fan off (when the temperature was below
 			defined range).
 
@@ -167,7 +227,9 @@ Speed Cruise mode (3)
 
 This modes tries to keep the fan speed constant.
 
-fan[1-7]_target		Target fan speed
+fan[1-7]_target
+			Target fan speed
+
 fan[1-7]_tolerance
 			Target speed tolerance
 
@@ -188,16 +250,22 @@ critical temperature mode, in which the fans should run at full speed.
 pwm[1-7]_auto_point[1-7]_pwm
 			pwm value to be set if temperature reaches matching
 			temperature range.
+
 pwm[1-7]_auto_point[1-7]_temp
 			Temperature over which the matching pwm is enabled.
+
 pwm[1-7]_temp_tolerance
 			Temperature tolerance, unit millidegree Celsius
+
 pwm[1-7]_crit_temp_tolerance
 			Temperature tolerance for critical temperature,
 			unit millidegree Celsius
 
-pwm[1-7]_step_up_time	milliseconds before fan speed is increased
-pwm[1-7]_step_down_time	milliseconds before fan speed is decreased
+pwm[1-7]_step_up_time
+			milliseconds before fan speed is increased
+
+pwm[1-7]_step_down_time
+			milliseconds before fan speed is decreased
 
 Usage Notes
 -----------
diff --git a/Documentation/hwmon/nct7802 b/Documentation/hwmon/nct7802.rst
index 5438deb6be02..8b7365a7cb32 100644
--- a/Documentation/hwmon/nct7802
+++ b/Documentation/hwmon/nct7802.rst
@@ -2,13 +2,18 @@ Kernel driver nct7802
 =====================
 
 Supported chips:
+
   * Nuvoton NCT7802Y
+
     Prefix: 'nct7802'
+
     Addresses scanned: I2C 0x28..0x2f
+
     Datasheet: Available from Nuvoton web site
 
 Authors:
-        Guenter Roeck <linux@roeck-us.net>
+
+	Guenter Roeck <linux@roeck-us.net>
 
 Description
 -----------
@@ -25,7 +30,9 @@ Tested Boards and BIOS Versions
 The driver has been reported to work with the following boards and
 BIOS versions.
 
+======================= ===============================================
 Board			BIOS version
----------------------------------------------------------------
+======================= ===============================================
 Kontron COMe-bSC2	CHR2E934.001.GGO
 Kontron COMe-bIP2	CCR2E212
+======================= ===============================================
diff --git a/Documentation/hwmon/nct7904 b/Documentation/hwmon/nct7904.rst
index 57fffe33ebfc..5b2f111582ff 100644
--- a/Documentation/hwmon/nct7904
+++ b/Documentation/hwmon/nct7904.rst
@@ -1,11 +1,16 @@
 Kernel driver nct7904
-====================
+=====================
 
 Supported chip:
+
   * Nuvoton NCT7904D
+
     Prefix: nct7904
+
     Addresses: I2C 0x2d, 0x2e
+
     Datasheet: Publicly available at Nuvoton website
+
 	http://www.nuvoton.com/
 
 Author: Vadim V. Vlasov <vvlasov@dev.rtsoft.ru>
@@ -25,6 +30,7 @@ Sysfs entries
 
 Currently, the driver supports only the following features:
 
+======================= =======================================================
 in[1-20]_input		Input voltage measurements (mV)
 
 fan[1-12]_input		Fan tachometer measurements (rpm)
@@ -40,6 +46,7 @@ pwm[1-4]_enable		R/W, 1/2 for manual or SmartFan mode
 			previously configured by BIOS (or configuration EEPROM)
 
 pwm[1-4]		R/O in SmartFan mode, R/W in manual control mode
+======================= =======================================================
 
 The driver checks sensor control registers and does not export the sensors
 that are not enabled. Anyway, a sensor that is enabled may actually be not
diff --git a/Documentation/hwmon/npcm750-pwm-fan b/Documentation/hwmon/npcm750-pwm-fan.rst
index 6156ef7398e6..c67af08b6773 100644
--- a/Documentation/hwmon/npcm750-pwm-fan
+++ b/Documentation/hwmon/npcm750-pwm-fan.rst
@@ -2,9 +2,11 @@ Kernel driver npcm750-pwm-fan
 =============================
 
 Supported chips:
+
 	NUVOTON NPCM750/730/715/705
 
 Authors:
+
 	<tomer.maimon@nuvoton.com>
 
 Description:
@@ -15,8 +17,10 @@ controller supports up to 16 tachometer inputs.
 
 The driver provides the following sensor accesses in sysfs:
 
+=============== ======= =====================================================
 fanX_input	ro	provide current fan rotation value in RPM as reported
 			by the fan to the device.
 
 pwmX		rw	get or set PWM fan control value. This is an integer
 			value between 0(off) and 255(full speed).
+=============== ======= =====================================================
diff --git a/Documentation/hwmon/nsa320 b/Documentation/hwmon/nsa320.rst
index fdbd6947799b..4fe75fd2f937 100644
--- a/Documentation/hwmon/nsa320
+++ b/Documentation/hwmon/nsa320.rst
@@ -2,14 +2,23 @@ Kernel driver nsa320_hwmon
 ==========================
 
 Supported chips:
+
   * Holtek HT46R065 microcontroller with onboard firmware that configures
+
 	it to act as a hardware monitor.
+
     Prefix: 'nsa320'
+
     Addresses scanned: none
+
     Datasheet: Not available, driver was reverse engineered based upon the
+
 	Zyxel kernel source
 
+
+
 Author:
+
   Adam Baker <linux@baker-net.org.uk>
 
 Description
@@ -31,8 +40,10 @@ tenths of a degree.
 sysfs-Interface
 ---------------
 
-temp1_input - temperature input
-fan1_input - fan speed
+============= =================
+temp1_input   temperature input
+fan1_input    fan speed
+============= =================
 
 Notes
 -----
diff --git a/Documentation/hwmon/ntc_thermistor b/Documentation/hwmon/ntc_thermistor.rst
index 8b9ff23edc32..d0e7f91726b9 100644
--- a/Documentation/hwmon/ntc_thermistor
+++ b/Documentation/hwmon/ntc_thermistor.rst
@@ -1,22 +1,29 @@
 Kernel driver ntc_thermistor
-=================
+============================
 
 Supported thermistors from Murata:
+
 * Murata NTC Thermistors NCP15WB473, NCP18WB473, NCP21WB473, NCP03WB473,
   NCP15WL333, NCP03WF104, NCP15XH103
+
   Prefixes: 'ncp15wb473', 'ncp18wb473', 'ncp21wb473', 'ncp03wb473',
   'ncp15wl333', 'ncp03wf104', 'ncp15xh103'
+
   Datasheet: Publicly available at Murata
 
 Supported thermistors from EPCOS:
+
 * EPCOS NTC Thermistors B57330V2103
+
   Prefixes: b57330v2103
+
   Datasheet: Publicly available at EPCOS
 
 Other NTC thermistors can be supported simply by adding compensation
 tables; e.g., NCP15WL333 support is added by the table ncpXXwl333.
 
 Authors:
+
 	MyungJoo Ham <myungjoo.ham@samsung.com>
 
 Description
@@ -29,57 +36,60 @@ compensation table to get the temperature input.
 The NTC driver provides lookup tables with a linear approximation function
 and four circuit models with an option not to use any of the four models.
 
+Using the following convention::
+
+   $	resistor
+   [TH]	the thermistor
+
 The four circuit models provided are:
 
-	$: resister, [TH]: the thermistor
-
- 1. connect = NTC_CONNECTED_POSITIVE, pullup_ohm > 0
-
-   [pullup_uV]
-       |    |
-      [TH]  $ (pullup_ohm)
-       |    |
-       +----+-----------------------[read_uV]
-       |
-       $ (pulldown_ohm)
-       |
-      --- (ground)
-
- 2. connect = NTC_CONNECTED_POSITIVE, pullup_ohm = 0 (not-connected)
-
-   [pullup_uV]
-       |
-      [TH]
-       |
-       +----------------------------[read_uV]
-       |
-       $ (pulldown_ohm)
-       |
-      --- (ground)
-
- 3. connect = NTC_CONNECTED_GROUND, pulldown_ohm > 0
-
-   [pullup_uV]
-       |
-       $ (pullup_ohm)
-       |
-       +----+-----------------------[read_uV]
-       |    |
-      [TH]  $ (pulldown_ohm)
-       |    |
-      -------- (ground)
-
- 4. connect = NTC_CONNECTED_GROUND, pulldown_ohm = 0 (not-connected)
-
-   [pullup_uV]
-       |
-       $ (pullup_ohm)
-       |
-       +----------------------------[read_uV]
-       |
-      [TH]
-       |
-      --- (ground)
+1. connect = NTC_CONNECTED_POSITIVE, pullup_ohm > 0::
+
+     [pullup_uV]
+	 |    |
+	[TH]  $ (pullup_ohm)
+	 |    |
+	 +----+-----------------------[read_uV]
+	 |
+	 $ (pulldown_ohm)
+	 |
+	-+- (ground)
+
+2. connect = NTC_CONNECTED_POSITIVE, pullup_ohm = 0 (not-connected)::
+
+     [pullup_uV]
+	 |
+	[TH]
+	 |
+	 +----------------------------[read_uV]
+	 |
+	 $ (pulldown_ohm)
+	 |
+	-+- (ground)
+
+3. connect = NTC_CONNECTED_GROUND, pulldown_ohm > 0::
+
+     [pullup_uV]
+	 |
+	 $ (pullup_ohm)
+	 |
+	 +----+-----------------------[read_uV]
+	 |    |
+	[TH]  $ (pulldown_ohm)
+	 |    |
+	-+----+- (ground)
+
+4. connect = NTC_CONNECTED_GROUND, pulldown_ohm = 0 (not-connected)::
+
+     [pullup_uV]
+	 |
+	 $ (pullup_ohm)
+	 |
+	 +----------------------------[read_uV]
+	 |
+	[TH]
+	 |
+	-+- (ground)
 
 When one of the four circuit models is used, read_uV, pullup_uV, pullup_ohm,
 pulldown_ohm, and connect should be provided. When none of the four models
@@ -88,13 +98,14 @@ provide read_ohm and _not_ provide the others.
 
 Sysfs Interface
 ---------------
-name		the mandatory global attribute, the thermistor name.
 
-temp1_type	always 4 (thermistor)
-		RO
+=============== == =============================================================
+name		   the mandatory global attribute, the thermistor name.
+=============== == =============================================================
+temp1_type	RO always 4 (thermistor)
 
-temp1_input	measure the temperature and provide the measured value.
-		(reading this file initiates the reading procedure.)
-		RO
+temp1_input	RO measure the temperature and provide the measured value.
+		   (reading this file initiates the reading procedure.)
+=============== == =============================================================
 
 Note that each NTC thermistor has only _one_ thermistor; thus, only temp1 exists.
diff --git a/Documentation/hwmon/occ b/Documentation/hwmon/occ.rst
index e787596e03fe..bf41c162d70e 100644
--- a/Documentation/hwmon/occ
+++ b/Documentation/hwmon/occ.rst
@@ -2,6 +2,7 @@ Kernel driver occ-hwmon
 =======================
 
 Supported chips:
+
   * POWER8
   * POWER9
 
@@ -37,53 +38,87 @@ Some entries are only present with certain OCC sensor versions or only on
 certain OCCs in the system. The version number is not exported to the user
 but can be inferred.
 
-temp[1-n]_label		OCC sensor ID.
+temp[1-n]_label
+	OCC sensor ID.
+
 [with temperature sensor version 1]
-    temp[1-n]_input	Measured temperature of the component in millidegrees
+
+    temp[1-n]_input
+			Measured temperature of the component in millidegrees
 			Celsius.
+
 [with temperature sensor version >= 2]
-    temp[1-n]_type		The FRU (Field Replaceable Unit) type
+
+    temp[1-n]_type
+				The FRU (Field Replaceable Unit) type
 				(represented by an integer) for the component
 				that this sensor measures.
-    temp[1-n]_fault		Temperature sensor fault boolean; 1 to indicate
+    temp[1-n]_fault
+				Temperature sensor fault boolean; 1 to indicate
 				that a fault is present or 0 to indicate that
 				no fault is present.
+
     [with type == 3 (FRU type is VRM)]
-        temp[1-n]_alarm		VRM temperature alarm boolean; 1 to indicate
+
+	temp[1-n]_alarm
+				VRM temperature alarm boolean; 1 to indicate
 				alarm, 0 to indicate no alarm
+
     [else]
-        temp[1-n]_input		Measured temperature of the component in
-				millidegrees Celsius.
 
-freq[1-n]_label		OCC sensor ID.
-freq[1-n]_input		Measured frequency of the component in MHz.
+	temp[1-n]_input
+				Measured temperature of the component in
+				millidegrees Celsius.
 
-power[1-n]_input	Latest measured power reading of the component in
+freq[1-n]_label
+			OCC sensor ID.
+freq[1-n]_input
+			Measured frequency of the component in MHz.
+power[1-n]_input
+			Latest measured power reading of the component in
 			microwatts.
-power[1-n]_average	Average power of the component in microwatts.
-power[1-n]_average_interval	The amount of time over which the power average
+power[1-n]_average
+			Average power of the component in microwatts.
+power[1-n]_average_interval
+				The amount of time over which the power average
 				was taken in microseconds.
+
 [with power sensor version < 2]
-    power[1-n]_label	OCC sensor ID.
+
+    power[1-n]_label
+			OCC sensor ID.
+
 [with power sensor version >= 2]
-    power[1-n]_label	OCC sensor ID + function ID + channel in the form
+
+    power[1-n]_label
+			OCC sensor ID + function ID + channel in the form
 			of a string, delimited by underscores, i.e. "0_15_1".
 			Both the function ID and channel are integers that
 			further identify the power sensor.
+
 [with power sensor version 0xa0]
-    power[1-n]_label	OCC sensor ID + sensor type in the form of a string,
+
+    power[1-n]_label
+			OCC sensor ID + sensor type in the form of a string,
 			delimited by an underscore, i.e. "0_system". Sensor
 			type will be one of "system", "proc", "vdd" or "vdn".
 			For this sensor version, OCC sensor ID will be the same
 			for all power sensors.
+
 [present only on "master" OCC; represents the whole system power; only one of
- this type of power sensor will be present]
-    power[1-n]_label		"system"
-    power[1-n]_input		Latest system output power in microwatts.
-    power[1-n]_cap		Current system power cap in microwatts.
-    power[1-n]_cap_not_redundant	System power cap in microwatts when
-					there is not redundant power.
-    power[1-n]_cap_max		Maximum power cap that the OCC can enforce in
+this type of power sensor will be present]
+
+    power[1-n]_label
+				"system"
+    power[1-n]_input
+				Latest system output power in microwatts.
+    power[1-n]_cap
+				Current system power cap in microwatts.
+    power[1-n]_cap_not_redundant
+				System power cap in microwatts when
+				there is not redundant power.
+    power[1-n]_cap_max
+				Maximum power cap that the OCC can enforce in
 				microwatts.
     power[1-n]_cap_min		Minimum power cap that the OCC can enforce in
 				microwatts.
@@ -94,8 +129,11 @@ power[1-n]_average_interval	The amount of time over which the power average
 				ignored, i.e. requesting a power cap of
 				500900000 microwatts will result in a power cap
 				request of 500 watts.
+
     [with caps sensor version > 1]
-        power[1-n]_cap_user_source	Indicates how the user power cap was
+
+	power[1-n]_cap_user_source
+					Indicates how the user power cap was
 					set. This is an integer that maps to
 					system or firmware components that can
 					set the user power cap.
@@ -104,9 +142,12 @@ The following "extn" sensors are exported as a way for the OCC to provide data
 that doesn't fit anywhere else. The meaning of these sensors is entirely
 dependent on their data, and cannot be statically defined.
 
-extn[1-n]_label		ASCII ID or OCC sensor ID.
-extn[1-n]_flags		This is one byte hexadecimal value. Bit 7 indicates the
+extn[1-n]_label
+			ASCII ID or OCC sensor ID.
+extn[1-n]_flags
+			This is one byte hexadecimal value. Bit 7 indicates the
 			type of the label attribute; 1 for sensor ID, 0 for
 			ASCII ID. Other bits are reserved.
-extn[1-n]_input		6 bytes of hexadecimal data, with a meaning defined by
+extn[1-n]_input
+			6 bytes of hexadecimal data, with a meaning defined by
 			the sensor ID.
diff --git a/Documentation/hwmon/pc87360 b/Documentation/hwmon/pc87360.rst
index d5f5cf16ce59..4bad07bce54b 100644
--- a/Documentation/hwmon/pc87360
+++ b/Documentation/hwmon/pc87360.rst
@@ -2,14 +2,19 @@ Kernel driver pc87360
 =====================
 
 Supported chips:
+
   * National Semiconductor PC87360, PC87363, PC87364, PC87365 and PC87366
+
     Prefixes: 'pc87360', 'pc87363', 'pc87364', 'pc87365', 'pc87366'
+
     Addresses scanned: none, address read from Super I/O config space
+
     Datasheets: No longer available
 
 Authors: Jean Delvare <jdelvare@suse.de>
 
 Thanks to Sandeep Mehta, Tonko de Rooy and Daniel Ceregatti for testing.
+
 Thanks to Rudolf Marek for helping me investigate conversion issues.
 
 
@@ -17,11 +22,13 @@ Module Parameters
 -----------------
 
 * init int
-  Chip initialization level:
-   0: None
-  *1: Forcibly enable internal voltage and temperature channels, except in9
-   2: Forcibly enable all voltage and temperature channels, except in9
-   3: Forcibly enable all voltage and temperature channels, including in9
+    Chip initialization level:
+
+    - 0: None
+    - **1**: Forcibly enable internal voltage and temperature channels,
+      except in9
+    - 2: Forcibly enable all voltage and temperature channels, except in9
+    - 3: Forcibly enable all voltage and temperature channels, including in9
 
 Note that this parameter has no effect for the PC87360, PC87363 and PC87364
 chips.
@@ -43,13 +50,15 @@ hardware monitoring chipsets, not only controlling and monitoring three fans,
 but also monitoring eleven voltage inputs and two (PC87365) or up to four
 (PC87366) temperatures.
 
+  =========== ======= ======= ======= ======= =====
   Chip        #vin    #fan    #pwm    #temp   devid
-
+  =========== ======= ======= ======= ======= =====
   PC87360     -       2       2       -       0xE1
   PC87363     -       2       2       -       0xE8
   PC87364     -       3       3       -       0xE4
   PC87365     11      3       3       2       0xE5
   PC87366     11      3       3       3-4     0xE9
+  =========== ======= ======= ======= ======= =====
 
 The driver assumes that no more than one chip is present, and one of the
 standard Super I/O addresses is used (0x2E/0x2F or 0x4E/0x4F)
@@ -68,18 +77,23 @@ have to care no more.
 
 For reference, here are a few values about clock dividers:
 
-                slowest         accuracy        highest
-                measurable      around 3000     accurate
+    =========== =============== =============== ===========
+		slowest         accuracy        highest
+		measurable      around 3000     accurate
     divider     speed (RPM)     RPM (RPM)       speed (RPM)
-         1        1882              18           6928
-         2         941              37           4898
-         4         470              74           3464
-         8         235             150           2449
+    =========== =============== =============== ===========
+	 1        1882              18           6928
+	 2         941              37           4898
+	 4         470              74           3464
+	 8         235             150           2449
+    =========== =============== =============== ===========
 
 For the curious, here is how the values above were computed:
+
  * slowest measurable speed: clock/(255*divider)
  * accuracy around 3000 RPM: 3000^2/clock
  * highest accurate speed: sqrt(clock*100)
+
 The clock speed for the PC87360 family is 480 kHz. I arbitrarily chose 100
 RPM as the lowest acceptable accuracy.
 
diff --git a/Documentation/hwmon/pc87427 b/Documentation/hwmon/pc87427.rst
index c313eb66e08a..22d8f62d851f 100644
--- a/Documentation/hwmon/pc87427
+++ b/Documentation/hwmon/pc87427.rst
@@ -2,9 +2,13 @@ Kernel driver pc87427
 =====================
 
 Supported chips:
+
   * National Semiconductor PC87427
+
     Prefix: 'pc87427'
+
     Addresses scanned: none, address read from Super I/O config space
+
     Datasheet: No longer available
 
 Author: Jean Delvare <jdelvare@suse.de>
diff --git a/Documentation/hwmon/pcf8591 b/Documentation/hwmon/pcf8591.rst
index 447c0702c0ec..e98bd542a441 100644
--- a/Documentation/hwmon/pcf8591
+++ b/Documentation/hwmon/pcf8591.rst
@@ -2,16 +2,21 @@ Kernel driver pcf8591
 =====================
 
 Supported chips:
+
   * Philips/NXP PCF8591
+
     Prefix: 'pcf8591'
+
     Addresses scanned: none
+
     Datasheet: Publicly available at the NXP website
-               http://www.nxp.com/pip/PCF8591_6.html
+
+	       http://www.nxp.com/pip/PCF8591_6.html
 
 Authors:
-        Aurelien Jarno <aurelien@aurel32.net>
-        valuable contributions by Jan M. Sendler <sendler@sendler.de>,
-        Jean Delvare <jdelvare@suse.de>
+      - Aurelien Jarno <aurelien@aurel32.net>
+      - valuable contributions by Jan M. Sendler <sendler@sendler.de>,
+      - Jean Delvare <jdelvare@suse.de>
 
 
 Description
@@ -22,24 +27,25 @@ analog output) for the I2C bus produced by Philips Semiconductors (now NXP).
 It is designed to provide a byte I2C interface to up to 4 separate devices.
 
 The PCF8591 has 4 analog inputs programmable as single-ended or
-differential inputs :
+differential inputs:
+
 - mode 0 : four single ended inputs
-        Pins AIN0 to AIN3 are single ended inputs for channels 0 to 3
+	Pins AIN0 to AIN3 are single ended inputs for channels 0 to 3
 
 - mode 1 : three differential inputs
-        Pins AIN3 is the common negative differential input
-        Pins AIN0 to AIN2 are positive differential inputs for channels 0 to 2
+	Pins AIN3 is the common negative differential input
+	Pins AIN0 to AIN2 are positive differential inputs for channels 0 to 2
 
 - mode 2 : single ended and differential mixed
-        Pins AIN0 and AIN1 are single ended inputs for channels 0 and 1
-        Pins AIN2 is the positive differential input for channel 3
-        Pins AIN3 is the negative differential input for channel 3
+	Pins AIN0 and AIN1 are single ended inputs for channels 0 and 1
+	Pins AIN2 is the positive differential input for channel 3
+	Pins AIN3 is the negative differential input for channel 3
 
 - mode 3 : two differential inputs
-        Pins AIN0 is the positive differential input for channel 0
-        Pins AIN1 is the negative differential input for channel 0
-        Pins AIN2 is the positive differential input for channel 1
-        Pins AIN3 is the negative differential input for channel 1
+	Pins AIN0 is the positive differential input for channel 0
+	Pins AIN1 is the negative differential input for channel 0
+	Pins AIN2 is the positive differential input for channel 1
+	Pins AIN3 is the negative differential input for channel 1
 
 See the datasheet for details.
 
@@ -49,10 +55,11 @@ Module parameters
 * input_mode int
 
     Analog input mode:
-         0 = four single ended inputs
-         1 = three differential inputs
-         2 = single ended and differential mixed
-         3 = two differential inputs
+
+	 - 0 = four single ended inputs
+	 - 1 = three differential inputs
+	 - 2 = single ended and differential mixed
+	 - 3 = two differential inputs
 
 
 Accessing PCF8591 via /sys interface
@@ -67,11 +74,12 @@ for details.
 Directories are being created for each instantiated PCF8591:
 
 /sys/bus/i2c/devices/<0>-<1>/
-where <0> is the bus the chip is connected to (e. g. i2c-0)
-and <1> the chip address ([48..4f])
+   where <0> is the bus the chip is connected to (e. g. i2c-0)
+   and <1> the chip address ([48..4f])
 
 Inside these directories, there are such files:
-in0_input, in1_input, in2_input, in3_input, out0_enable, out0_output, name
+
+   in0_input, in1_input, in2_input, in3_input, out0_enable, out0_output, name
 
 Name contains chip name.
 
diff --git a/Documentation/hwmon/pmbus-core b/Documentation/hwmon/pmbus-core.rst
index 8ed10e9ddfb5..92515c446fe3 100644
--- a/Documentation/hwmon/pmbus-core
+++ b/Documentation/hwmon/pmbus-core.rst
@@ -1,3 +1,4 @@
+==================================
 PMBus core driver and internal API
 ==================================
 
@@ -120,24 +121,24 @@ Specifically, it provides the following information.
   non-standard PMBus commands to standard commands, or to augment standard
   command return values with device specific information.
 
-  API functions
-  -------------
+API functions
+=============
 
-  Functions provided by chip driver
-  ---------------------------------
+Functions provided by chip driver
+---------------------------------
 
-  All functions return the command return value (read) or zero (write) if
-  successful. A return value of -ENODATA indicates that there is no manufacturer
-  specific command, but that a standard PMBus command may exist. Any other
-  negative return value indicates that the commands does not exist for this
-  chip, and that no attempt should be made to read or write the standard
-  command.
+All functions return the command return value (read) or zero (write) if
+successful. A return value of -ENODATA indicates that there is no manufacturer
+specific command, but that a standard PMBus command may exist. Any other
+negative return value indicates that the commands does not exist for this
+chip, and that no attempt should be made to read or write the standard
+command.
 
-  As mentioned above, an exception to this rule applies to virtual commands,
-  which  _must_ be handled in driver specific code. See "Virtual PMBus Commands"
-  above for more details.
+As mentioned above, an exception to this rule applies to virtual commands,
+which *must* be handled in driver specific code. See "Virtual PMBus Commands"
+above for more details.
 
-  Command execution in the core PMBus driver code is as follows.
+Command execution in the core PMBus driver code is as follows::
 
 	if (chip_access_function) {
 		status = chip_access_function();
@@ -148,128 +149,160 @@ Specifically, it provides the following information.
 		return -EINVAL;
 	return generic_access();
 
-  Chip drivers may provide pointers to the following functions in struct
-  pmbus_driver_info. All functions are optional.
+Chip drivers may provide pointers to the following functions in struct
+pmbus_driver_info. All functions are optional.
+
+::
 
   int (*read_byte_data)(struct i2c_client *client, int page, int reg);
 
-  Read byte from page <page>, register <reg>.
-  <page> may be -1, which means "current page".
+Read byte from page <page>, register <reg>.
+<page> may be -1, which means "current page".
+
+
+::
 
   int (*read_word_data)(struct i2c_client *client, int page, int reg);
 
-  Read word from page <page>, register <reg>.
+Read word from page <page>, register <reg>.
+
+::
 
   int (*write_word_data)(struct i2c_client *client, int page, int reg,
-		         u16 word);
+			 u16 word);
 
-  Write word to page <page>, register <reg>.
+Write word to page <page>, register <reg>.
+
+::
 
   int (*write_byte)(struct i2c_client *client, int page, u8 value);
 
-  Write byte to page <page>, register <reg>.
-  <page> may be -1, which means "current page".
+Write byte to page <page>, register <reg>.
+<page> may be -1, which means "current page".
+
+::
 
   int (*identify)(struct i2c_client *client, struct pmbus_driver_info *info);
 
-  Determine supported PMBus functionality. This function is only necessary
-  if a chip driver supports multiple chips, and the chip functionality is not
-  pre-determined. It is currently only used by the generic pmbus driver
-  (pmbus.c).
+Determine supported PMBus functionality. This function is only necessary
+if a chip driver supports multiple chips, and the chip functionality is not
+pre-determined. It is currently only used by the generic pmbus driver
+(pmbus.c).
+
+Functions exported by core driver
+---------------------------------
 
-  Functions exported by core driver
-  ---------------------------------
+Chip drivers are expected to use the following functions to read or write
+PMBus registers. Chip drivers may also use direct I2C commands. If direct I2C
+commands are used, the chip driver code must not directly modify the current
+page, since the selected page is cached in the core driver and the core driver
+will assume that it is selected. Using pmbus_set_page() to select a new page
+is mandatory.
 
-  Chip drivers are expected to use the following functions to read or write
-  PMBus registers. Chip drivers may also use direct I2C commands. If direct I2C
-  commands are used, the chip driver code must not directly modify the current
-  page, since the selected page is cached in the core driver and the core driver
-  will assume that it is selected. Using pmbus_set_page() to select a new page
-  is mandatory.
+::
 
   int pmbus_set_page(struct i2c_client *client, u8 page);
 
-  Set PMBus page register to <page> for subsequent commands.
+Set PMBus page register to <page> for subsequent commands.
+
+::
 
   int pmbus_read_word_data(struct i2c_client *client, u8 page, u8 reg);
 
-  Read word data from <page>, <reg>. Similar to i2c_smbus_read_word_data(), but
-  selects page first.
+Read word data from <page>, <reg>. Similar to i2c_smbus_read_word_data(), but
+selects page first.
+
+::
 
   int pmbus_write_word_data(struct i2c_client *client, u8 page, u8 reg,
 			    u16 word);
 
-  Write word data to <page>, <reg>. Similar to i2c_smbus_write_word_data(), but
-  selects page first.
+Write word data to <page>, <reg>. Similar to i2c_smbus_write_word_data(), but
+selects page first.
+
+::
 
   int pmbus_read_byte_data(struct i2c_client *client, int page, u8 reg);
 
-  Read byte data from <page>, <reg>. Similar to i2c_smbus_read_byte_data(), but
-  selects page first. <page> may be -1, which means "current page".
+Read byte data from <page>, <reg>. Similar to i2c_smbus_read_byte_data(), but
+selects page first. <page> may be -1, which means "current page".
+
+::
 
   int pmbus_write_byte(struct i2c_client *client, int page, u8 value);
 
-  Write byte data to <page>, <reg>. Similar to i2c_smbus_write_byte(), but
-  selects page first. <page> may be -1, which means "current page".
+Write byte data to <page>, <reg>. Similar to i2c_smbus_write_byte(), but
+selects page first. <page> may be -1, which means "current page".
+
+::
 
   void pmbus_clear_faults(struct i2c_client *client);
 
-  Execute PMBus "Clear Fault" command on all chip pages.
-  This function calls the device specific write_byte function if defined.
-  Therefore, it must _not_ be called from that function.
+Execute PMBus "Clear Fault" command on all chip pages.
+This function calls the device specific write_byte function if defined.
+Therefore, it must _not_ be called from that function.
+
+::
 
   bool pmbus_check_byte_register(struct i2c_client *client, int page, int reg);
 
-  Check if byte register exists. Return true if the register exists, false
-  otherwise.
-  This function calls the device specific write_byte function if defined to
-  obtain the chip status. Therefore, it must _not_ be called from that function.
+Check if byte register exists. Return true if the register exists, false
+otherwise.
+This function calls the device specific write_byte function if defined to
+obtain the chip status. Therefore, it must _not_ be called from that function.
+
+::
 
   bool pmbus_check_word_register(struct i2c_client *client, int page, int reg);
 
-  Check if word register exists. Return true if the register exists, false
-  otherwise.
-  This function calls the device specific write_byte function if defined to
-  obtain the chip status. Therefore, it must _not_ be called from that function.
+Check if word register exists. Return true if the register exists, false
+otherwise.
+This function calls the device specific write_byte function if defined to
+obtain the chip status. Therefore, it must _not_ be called from that function.
+
+::
 
   int pmbus_do_probe(struct i2c_client *client, const struct i2c_device_id *id,
-                     struct pmbus_driver_info *info);
+		     struct pmbus_driver_info *info);
+
+Execute probe function. Similar to standard probe function for other drivers,
+with the pointer to struct pmbus_driver_info as additional argument. Calls
+identify function if supported. Must only be called from device probe
+function.
 
-  Execute probe function. Similar to standard probe function for other drivers,
-  with the pointer to struct pmbus_driver_info as additional argument. Calls
-  identify function if supported. Must only be called from device probe
-  function.
+::
 
   void pmbus_do_remove(struct i2c_client *client);
 
-  Execute driver remove function. Similar to standard driver remove function.
+Execute driver remove function. Similar to standard driver remove function.
+
+::
 
   const struct pmbus_driver_info
 	*pmbus_get_driver_info(struct i2c_client *client);
 
-  Return pointer to struct pmbus_driver_info as passed to pmbus_do_probe().
+Return pointer to struct pmbus_driver_info as passed to pmbus_do_probe().
 
 
 PMBus driver platform data
 ==========================
 
 PMBus platform data is defined in include/linux/pmbus.h. Platform data
-currently only provides a flag field with a single bit used.
+currently only provides a flag field with a single bit used::
 
-#define PMBUS_SKIP_STATUS_CHECK (1 << 0)
+	#define PMBUS_SKIP_STATUS_CHECK (1 << 0)
 
-struct pmbus_platform_data {
-        u32 flags;              /* Device specific flags */
-};
+	struct pmbus_platform_data {
+		u32 flags;              /* Device specific flags */
+	};
 
 
 Flags
 -----
 
 PMBUS_SKIP_STATUS_CHECK
-
-During register detection, skip checking the status register for
-communication or command errors.
+	During register detection, skip checking the status register for
+	communication or command errors.
 
 Some PMBus chips respond with valid data when trying to read an unsupported
 register. For such chips, checking the status register is mandatory when
diff --git a/Documentation/hwmon/pmbus b/Documentation/hwmon/pmbus.rst
index dfd9c65996c0..abfb9dd4857d 100644
--- a/Documentation/hwmon/pmbus
+++ b/Documentation/hwmon/pmbus.rst
@@ -1,42 +1,77 @@
 Kernel driver pmbus
-====================
+===================
 
 Supported chips:
+
   * Ericsson BMR453, BMR454
+
     Prefixes: 'bmr453', 'bmr454'
+
     Addresses scanned: -
+
     Datasheet:
+
  http://archive.ericsson.net/service/internet/picov/get?DocNo=28701-EN/LZT146395
+
   * ON Semiconductor ADP4000, NCP4200, NCP4208
+
     Prefixes: 'adp4000', 'ncp4200', 'ncp4208'
+
     Addresses scanned: -
+
     Datasheets:
+
 	http://www.onsemi.com/pub_link/Collateral/ADP4000-D.PDF
+
 	http://www.onsemi.com/pub_link/Collateral/NCP4200-D.PDF
+
 	http://www.onsemi.com/pub_link/Collateral/JUNE%202009-%20REV.%200.PDF
+
   * Lineage Power
+
     Prefixes: 'mdt040', 'pdt003', 'pdt006', 'pdt012', 'udt020'
+
     Addresses scanned: -
+
     Datasheets:
+
 	http://www.lineagepower.com/oem/pdf/PDT003A0X.pdf
+
 	http://www.lineagepower.com/oem/pdf/PDT006A0X.pdf
+
 	http://www.lineagepower.com/oem/pdf/PDT012A0X.pdf
+
 	http://www.lineagepower.com/oem/pdf/UDT020A0X.pdf
+
 	http://www.lineagepower.com/oem/pdf/MDT040A0X.pdf
+
   * Texas Instruments TPS40400, TPS544B20, TPS544B25, TPS544C20, TPS544C25
+
     Prefixes: 'tps40400', 'tps544b20', 'tps544b25', 'tps544c20', 'tps544c25'
+
     Addresses scanned: -
+
     Datasheets:
+
 	http://www.ti.com/lit/gpn/tps40400
+
 	http://www.ti.com/lit/gpn/tps544b20
+
 	http://www.ti.com/lit/gpn/tps544b25
+
 	http://www.ti.com/lit/gpn/tps544c20
+
 	http://www.ti.com/lit/gpn/tps544c25
+
   * Generic PMBus devices
+
     Prefix: 'pmbus'
+
     Addresses scanned: -
+
     Datasheet: n.a.
 
+
 Author: Guenter Roeck <linux@roeck-us.net>
 
 
@@ -62,9 +97,10 @@ supported by all chips), and since there is no well defined address range for
 PMBus devices. You will have to instantiate the devices explicitly.
 
 Example: the following will load the driver for an LTC2978 at address 0x60
-on I2C bus #1:
-$ modprobe pmbus
-$ echo ltc2978 0x60 > /sys/bus/i2c/devices/i2c-1/new_device
+on I2C bus #1::
+
+	$ modprobe pmbus
+	$ echo ltc2978 0x60 > /sys/bus/i2c/devices/i2c-1/new_device
 
 
 Platform data support
@@ -72,9 +108,9 @@ Platform data support
 
 Support for additional PMBus chips can be added by defining chip parameters in
 a new chip specific driver file. For example, (untested) code to add support for
-Emerson DS1200 power modules might look as follows.
+Emerson DS1200 power modules might look as follows::
 
-static struct pmbus_driver_info ds1200_info = {
+  static struct pmbus_driver_info ds1200_info = {
 	.pages = 1,
 	/* Note: All other sensors are in linear mode */
 	.direct[PSC_VOLTAGE_OUT] = true,
@@ -95,45 +131,45 @@ static struct pmbus_driver_info ds1200_info = {
 		   | PMBUS_HAVE_PIN | PMBUS_HAVE_POUT
 		   | PMBUS_HAVE_TEMP | PMBUS_HAVE_STATUS_TEMP
 		   | PMBUS_HAVE_FAN12 | PMBUS_HAVE_STATUS_FAN12,
-};
+  };
 
-static int ds1200_probe(struct i2c_client *client,
-			const struct i2c_device_id *id)
-{
+  static int ds1200_probe(struct i2c_client *client,
+			  const struct i2c_device_id *id)
+  {
 	return pmbus_do_probe(client, id, &ds1200_info);
-}
+  }
 
-static int ds1200_remove(struct i2c_client *client)
-{
+  static int ds1200_remove(struct i2c_client *client)
+  {
 	return pmbus_do_remove(client);
-}
+  }
 
-static const struct i2c_device_id ds1200_id[] = {
+  static const struct i2c_device_id ds1200_id[] = {
 	{"ds1200", 0},
 	{}
-};
+  };
 
-MODULE_DEVICE_TABLE(i2c, ds1200_id);
+  MODULE_DEVICE_TABLE(i2c, ds1200_id);
 
-/* This is the driver that will be inserted */
-static struct i2c_driver ds1200_driver = {
+  /* This is the driver that will be inserted */
+  static struct i2c_driver ds1200_driver = {
 	.driver = {
 		   .name = "ds1200",
 		   },
 	.probe = ds1200_probe,
 	.remove = ds1200_remove,
 	.id_table = ds1200_id,
-};
+  };
 
-static int __init ds1200_init(void)
-{
+  static int __init ds1200_init(void)
+  {
 	return i2c_add_driver(&ds1200_driver);
-}
+  }
 
-static void __exit ds1200_exit(void)
-{
+  static void __exit ds1200_exit(void)
+  {
 	i2c_del_driver(&ds1200_driver);
-}
+  }
 
 
 Sysfs entries
@@ -148,6 +184,7 @@ a given sysfs entry.
 The following attributes are supported. Limits are read-write; all other
 attributes are read-only.
 
+======================= ========================================================
 inX_input		Measured voltage. From READ_VIN or READ_VOUT register.
 inX_min			Minimum Voltage.
 			From VIN_UV_WARN_LIMIT or VOUT_UV_WARN_LIMIT register.
@@ -214,3 +251,4 @@ tempX_lcrit_alarm	Chip temperature critical low alarm. Set by comparing
 tempX_crit_alarm	Chip temperature critical high alarm. Set by comparing
 			READ_TEMPERATURE_X with OT_FAULT_LIMIT if
 			TEMP_OT_FAULT status is set.
+======================= ========================================================
diff --git a/Documentation/hwmon/powr1220 b/Documentation/hwmon/powr1220.rst
index 21e44f71ae6e..a7fc258da0a8 100644
--- a/Documentation/hwmon/powr1220
+++ b/Documentation/hwmon/powr1220.rst
@@ -1,12 +1,17 @@
 Kernel driver powr1220
-==================
+======================
 
 Supported chips:
+
   * Lattice POWR1220AT8
+
     Prefix: 'powr1220'
+
     Addresses scanned: none
+
     Datasheet: Publicly available at the Lattice website
-               http://www.latticesemi.com/
+
+	       http://www.latticesemi.com/
 
 Author: Scott Kanowitz <scott.kanowitz@gmail.com>
 
@@ -26,7 +31,9 @@ value over the low measurement range maximum of 2 V.
 
 The input naming convention is as follows:
 
+============== ========
 driver name    pin name
+============== ========
 in0            VMON1
 in1            VMON2
 in2            VMON3
@@ -41,5 +48,6 @@ in10           VMON11
 in11           VMON12
 in12           VCCA
 in13           VCCINP
+============== ========
 
 The ADC readings are updated on request with a minimum period of 1s.
diff --git a/Documentation/hwmon/pwm-fan b/Documentation/hwmon/pwm-fan.rst
index 18529d2e3bcf..82fe96742fee 100644
--- a/Documentation/hwmon/pwm-fan
+++ b/Documentation/hwmon/pwm-fan.rst
@@ -15,3 +15,6 @@ The driver implements a simple interface for driving a fan connected to
 a PWM output. It uses the generic PWM interface, thus it can be used with
 a range of SoCs. The driver exposes the fan to the user space through
 the hwmon's sysfs interface.
+
+The fan rotation speed returned via the optional 'fan1_input' is extrapolated
+from the sampled interrupts from the tachometer signal within 1 second.
diff --git a/Documentation/hwmon/raspberrypi-hwmon b/Documentation/hwmon/raspberrypi-hwmon.rst
index 3c92e2cb52d6..8038ade36490 100644
--- a/Documentation/hwmon/raspberrypi-hwmon
+++ b/Documentation/hwmon/raspberrypi-hwmon.rst
@@ -2,6 +2,7 @@ Kernel driver raspberrypi-hwmon
 ===============================
 
 Supported boards:
+
   * Raspberry Pi A+ (via GPIO on SoC)
   * Raspberry Pi B+ (via GPIO on SoC)
   * Raspberry Pi 2 B (via GPIO on SoC)
@@ -19,4 +20,6 @@ undervoltage conditions.
 Sysfs entries
 -------------
 
+======================= ==================
 in0_lcrit_alarm		Undervoltage alarm
+======================= ==================
diff --git a/Documentation/hwmon/sch5627 b/Documentation/hwmon/sch5627.rst
index 0551d266c51c..187682e99114 100644
--- a/Documentation/hwmon/sch5627
+++ b/Documentation/hwmon/sch5627.rst
@@ -2,9 +2,13 @@ Kernel driver sch5627
 =====================
 
 Supported chips:
+
   * SMSC SCH5627
+
     Prefix: 'sch5627'
+
     Addresses scanned: none, address read from Super I/O config space
+
     Datasheet: Application Note available upon request
 
 Author: Hans de Goede <hdegoede@redhat.com>
diff --git a/Documentation/hwmon/sch5636 b/Documentation/hwmon/sch5636.rst
index 7b0a01da0717..4aaee3672f13 100644
--- a/Documentation/hwmon/sch5636
+++ b/Documentation/hwmon/sch5636.rst
@@ -2,8 +2,11 @@ Kernel driver sch5636
 =====================
 
 Supported chips:
+
   * SMSC SCH5636
+
     Prefix: 'sch5636'
+
     Addresses scanned: none, address read from Super I/O config space
 
 Author: Hans de Goede <hdegoede@redhat.com>
diff --git a/Documentation/hwmon/scpi-hwmon b/Documentation/hwmon/scpi-hwmon.rst
index 4cfcdf2d5eab..eee7022b44db 100644
--- a/Documentation/hwmon/scpi-hwmon
+++ b/Documentation/hwmon/scpi-hwmon.rst
@@ -2,8 +2,11 @@ Kernel driver scpi-hwmon
 ========================
 
 Supported chips:
+
  * Chips based on ARM System Control Processor Interface
+
    Addresses scanned: -
+
    Datasheet: http://infocenter.arm.com/help/index.jsp?topic=/com.arm.doc.dui0922b/index.html
 
 Author: Punit Agrawal <punit.agrawal@arm.com>
@@ -14,7 +17,7 @@ Description
 This driver supports hardware monitoring for SoC's based on the ARM
 System Control Processor (SCP) implementing the System Control
 Processor Interface (SCPI). The following sensor types are supported
-by the SCP -
+by the SCP:
 
   * temperature
   * voltage
@@ -30,4 +33,4 @@ Usage Notes
 The driver relies on device tree node to indicate the presence of SCPI
 support in the kernel. See
 Documentation/devicetree/bindings/arm/arm,scpi.txt for details of the
-devicetree node.
\ No newline at end of file
+devicetree node.
diff --git a/Documentation/hwmon/sht15 b/Documentation/hwmon/sht15.rst
index 5e3207c3b177..485abe037f6c 100644
--- a/Documentation/hwmon/sht15
+++ b/Documentation/hwmon/sht15.rst
@@ -2,29 +2,37 @@ Kernel driver sht15
 ===================
 
 Authors:
+
   * Wouter Horre
   * Jonathan Cameron
   * Vivien Didelot <vivien.didelot@savoirfairelinux.com>
   * Jerome Oufella <jerome.oufella@savoirfairelinux.com>
 
 Supported chips:
+
   * Sensirion SHT10
+
     Prefix: 'sht10'
 
   * Sensirion SHT11
+
     Prefix: 'sht11'
 
   * Sensirion SHT15
+
     Prefix: 'sht15'
 
   * Sensirion SHT71
+
     Prefix: 'sht71'
 
   * Sensirion SHT75
+
     Prefix: 'sht75'
 
 Datasheet: Publicly available at the Sensirion website
-http://www.sensirion.ch/en/pdf/product_information/Datasheet-humidity-sensor-SHT1x.pdf
+
+	http://www.sensirion.ch/en/pdf/product_information/Datasheet-humidity-sensor-SHT1x.pdf
 
 Description
 -----------
@@ -63,11 +71,13 @@ Platform data
 Sysfs interface
 ---------------
 
-* temp1_input:     temperature input
-* humidity1_input: humidity input
-* heater_enable:   write 1 in this attribute to enable the on-chip heater,
-                   0 to disable it. Be careful not to enable the heater
-                   for too long.
-* temp1_fault:     if 1, this means that the voltage is low (below 2.47V) and
-                   measurement may be invalid.
-* humidity1_fault: same as temp1_fault.
+================== ==========================================================
+temp1_input        temperature input
+humidity1_input    humidity input
+heater_enable      write 1 in this attribute to enable the on-chip heater,
+		   0 to disable it. Be careful not to enable the heater
+		   for too long.
+temp1_fault        if 1, this means that the voltage is low (below 2.47V) and
+		   measurement may be invalid.
+humidity1_fault    same as temp1_fault.
+================== ==========================================================
diff --git a/Documentation/hwmon/sht21 b/Documentation/hwmon/sht21.rst
index 8b3cdda541c1..f1f5da030108 100644
--- a/Documentation/hwmon/sht21
+++ b/Documentation/hwmon/sht21.rst
@@ -2,19 +2,33 @@ Kernel driver sht21
 ===================
 
 Supported chips:
+
   * Sensirion SHT21
+
     Prefix: 'sht21'
+
     Addresses scanned: none
+
     Datasheet: Publicly available at the Sensirion website
+
     http://www.sensirion.com/file/datasheet_sht21
 
+
+
   * Sensirion SHT25
+
     Prefix: 'sht25'
+
     Addresses scanned: none
+
     Datasheet: Publicly available at the Sensirion website
+
     http://www.sensirion.com/file/datasheet_sht25
 
+
+
 Author:
+
   Urs Fleisch <urs.fleisch@sensirion.com>
 
 Description
@@ -33,9 +47,13 @@ in the board setup code.
 sysfs-Interface
 ---------------
 
-temp1_input - temperature input
-humidity1_input - humidity input
-eic - Electronic Identification Code
+temp1_input
+	- temperature input
+
+humidity1_input
+	- humidity input
+eic
+	- Electronic Identification Code
 
 Notes
 -----
diff --git a/Documentation/hwmon/sht3x b/Documentation/hwmon/sht3x.rst
index d9daa6ab1e8e..978a7117e4b2 100644
--- a/Documentation/hwmon/sht3x
+++ b/Documentation/hwmon/sht3x.rst
@@ -2,14 +2,19 @@ Kernel driver sht3x
 ===================
 
 Supported chips:
+
   * Sensirion SHT3x-DIS
+
     Prefix: 'sht3x'
+
     Addresses scanned: none
+
     Datasheet: https://www.sensirion.com/file/datasheet_sht3x_digital
 
 Author:
-  David Frey <david.frey@sensirion.com>
-  Pascal Sachs <pascal.sachs@sensirion.com>
+
+  - David Frey <david.frey@sensirion.com>
+  - Pascal Sachs <pascal.sachs@sensirion.com>
 
 Description
 -----------
@@ -24,6 +29,7 @@ addresses 0x44 or 0x45, depending on the wiring. See
 Documentation/i2c/instantiating-devices for methods to instantiate the device.
 
 There are two options configurable by means of sht3x_platform_data:
+
 1. blocking (pull the I2C clock line down while performing the measurement) or
    non-blocking mode. Blocking mode will guarantee the fastest result but
    the I2C bus will be busy during that time. By default, non-blocking mode
@@ -35,12 +41,15 @@ There are two options configurable by means of sht3x_platform_data:
 The sht3x sensor supports a single shot mode as well as 5 periodic measure
 modes, which can be controlled with the update_interval sysfs interface.
 The allowed update_interval in milliseconds are as follows:
-  *     0   single shot mode
-  *  2000   0.5 Hz periodic measurement
-  *  1000   1   Hz periodic measurement
-  *   500   2   Hz periodic measurement
-  *   250   4   Hz periodic measurement
-  *   100  10   Hz periodic measurement
+
+    ===== ======= ====================
+       0          single shot mode
+    2000   0.5 Hz periodic measurement
+    1000   1   Hz periodic measurement
+     500   2   Hz periodic measurement
+     250   4   Hz periodic measurement
+     100  10   Hz periodic measurement
+    ===== ======= ====================
 
 In the periodic measure mode, the sensor automatically triggers a measurement
 with the configured update interval on the chip. When a temperature or humidity
@@ -53,6 +62,7 @@ low.
 sysfs-Interface
 ---------------
 
+=================== ============================================================
 temp1_input:        temperature input
 humidity1_input:    humidity input
 temp1_max:          temperature max value
@@ -64,13 +74,15 @@ temp1_min_hyst:     temperature hysteresis value for min limit
 humidity1_min:      humidity min value
 humidity1_min_hyst: humidity hysteresis value for min limit
 temp1_alarm:        alarm flag is set to 1 if the temperature is outside the
-                    configured limits. Alarm only works in periodic measure mode
+		    configured limits. Alarm only works in periodic measure mode
 humidity1_alarm:    alarm flag is set to 1 if the humidity is outside the
-                    configured limits. Alarm only works in periodic measure mode
+		    configured limits. Alarm only works in periodic measure mode
 heater_enable:      heater enable, heating element removes excess humidity from
-                    sensor
-                        0: turned off
-                        1: turned on
+		    sensor:
+
+			- 0: turned off
+			- 1: turned on
 update_interval:    update interval, 0 for single shot, interval in msec
-                    for periodic measurement. If the interval is not supported
-                    by the sensor, the next faster interval is chosen
+		    for periodic measurement. If the interval is not supported
+		    by the sensor, the next faster interval is chosen
+=================== ============================================================
diff --git a/Documentation/hwmon/shtc1 b/Documentation/hwmon/shtc1.rst
index 6b1e05458f0f..aa116332ba26 100644
--- a/Documentation/hwmon/shtc1
+++ b/Documentation/hwmon/shtc1.rst
@@ -2,17 +2,29 @@ Kernel driver shtc1
 ===================
 
 Supported chips:
+
   * Sensirion SHTC1
+
     Prefix: 'shtc1'
+
     Addresses scanned: none
+
     Datasheet: http://www.sensirion.com/file/datasheet_shtc1
 
+
+
   * Sensirion SHTW1
+
     Prefix: 'shtw1'
+
     Addresses scanned: none
+
     Datasheet: Not publicly available
 
+
+
 Author:
+
   Johannes Winkelmann <johannes.winkelmann@sensirion.com>
 
 Description
@@ -28,6 +40,7 @@ address 0x70. See Documentation/i2c/instantiating-devices for methods to
 instantiate the device.
 
 There are two options configurable by means of shtc1_platform_data:
+
 1. blocking (pull the I2C clock line down while performing the measurement) or
    non-blocking mode. Blocking mode will guarantee the fastest result but
    the I2C bus will be busy during that time. By default, non-blocking mode
@@ -39,5 +52,7 @@ There are two options configurable by means of shtc1_platform_data:
 sysfs-Interface
 ---------------
 
-temp1_input - temperature input
-humidity1_input - humidity input
+temp1_input
+	- temperature input
+humidity1_input
+	- humidity input
diff --git a/Documentation/hwmon/sis5595 b/Documentation/hwmon/sis5595.rst
index 4f8877a34f37..16123b3bfff9 100644
--- a/Documentation/hwmon/sis5595
+++ b/Documentation/hwmon/sis5595.rst
@@ -2,49 +2,67 @@ Kernel driver sis5595
 =====================
 
 Supported chips:
+
   * Silicon Integrated Systems Corp. SiS5595 Southbridge Hardware Monitor
+
     Prefix: 'sis5595'
+
     Addresses scanned: ISA in PCI-space encoded address
+
     Datasheet: Publicly available at the Silicon Integrated Systems Corp. site.
 
+
+
 Authors:
-        Kyösti Mälkki <kmalkki@cc.hut.fi>,
-        Mark D. Studebaker <mdsxyz123@yahoo.com>,
-        Aurelien Jarno <aurelien@aurel32.net> 2.6 port
+
+      - Kyösti Mälkki <kmalkki@cc.hut.fi>,
+      - Mark D. Studebaker <mdsxyz123@yahoo.com>,
+      - Aurelien Jarno <aurelien@aurel32.net> 2.6 port
 
    SiS southbridge has a LM78-like chip integrated on the same IC.
    This driver is a customized copy of lm78.c
 
    Supports following revisions:
+
+       =============== =============== ==============
        Version         PCI ID          PCI Revision
+       =============== =============== ==============
        1               1039/0008       AF or less
        2               1039/0008       B0 or greater
+       =============== =============== ==============
 
    Note: these chips contain a 0008 device which is incompatible with the
-        5595. We recognize these by the presence of the listed
-        "blacklist" PCI ID and refuse to load.
+	5595. We recognize these by the presence of the listed
+	"blacklist" PCI ID and refuse to load.
 
+   =================== =============== ================
    NOT SUPPORTED       PCI ID          BLACKLIST PCI ID
-        540            0008            0540
-        550            0008            0550
+   =================== =============== ================
+	540            0008            0540
+	550            0008            0550
        5513            0008            5511
        5581            0008            5597
        5582            0008            5597
        5597            0008            5597
-        630            0008            0630
-        645            0008            0645
-        730            0008            0730
-        735            0008            0735
+	630            0008            0630
+	645            0008            0645
+	730            0008            0730
+	735            0008            0735
+   =================== =============== ================
 
 
 Module Parameters
 -----------------
+
+======================= =====================================================
 force_addr=0xaddr	Set the I/O base address. Useful for boards
 			that don't set the address in the BIOS. Does not do a
 			PCI force; the device must still be present in lspci.
 			Don't use this unless the driver complains that the
 			base address is not set.
+
 			Example: 'modprobe sis5595 force_addr=0x290'
+======================= =====================================================
 
 
 Description
@@ -103,4 +121,3 @@ Problems
 --------
 Some chips refuse to be enabled. We don't know why.
 The driver will recognize this and print a message in dmesg.
-
diff --git a/Documentation/hwmon/smm665 b/Documentation/hwmon/smm665.rst
index a341eeedab75..a0e27f62b57b 100644
--- a/Documentation/hwmon/smm665
+++ b/Documentation/hwmon/smm665.rst
@@ -2,31 +2,57 @@ Kernel driver smm665
 ====================
 
 Supported chips:
+
   * Summit Microelectronics SMM465
+
     Prefix: 'smm465'
+
     Addresses scanned: -
+
     Datasheet:
+
       http://www.summitmicro.com/prod_select/summary/SMM465/SMM465DS.pdf
+
   * Summit Microelectronics SMM665, SMM665B
+
     Prefix: 'smm665'
+
     Addresses scanned: -
+
     Datasheet:
+
       http://www.summitmicro.com/prod_select/summary/SMM665/SMM665B_2089_20.pdf
+
   * Summit Microelectronics SMM665C
+
     Prefix: 'smm665c'
+
     Addresses scanned: -
+
     Datasheet:
+
       http://www.summitmicro.com/prod_select/summary/SMM665C/SMM665C_2125.pdf
+
   * Summit Microelectronics SMM764
+
     Prefix: 'smm764'
+
     Addresses scanned: -
+
     Datasheet:
+
       http://www.summitmicro.com/prod_select/summary/SMM764/SMM764_2098.pdf
+
   * Summit Microelectronics SMM766, SMM766B
+
     Prefix: 'smm766'
+
     Addresses scanned: -
+
     Datasheets:
+
       http://www.summitmicro.com/prod_select/summary/SMM766/SMM766_2086.pdf
+
       http://www.summitmicro.com/prod_select/summary/SMM766B/SMM766B_2122.pdf
 
 Author: Guenter Roeck <linux@roeck-us.net>
@@ -36,9 +62,10 @@ Module Parameters
 -----------------
 
 * vref: int
-  Default: 1250 (mV)
-  Reference voltage on VREF_ADC pin in mV. It should not be necessary to set
-  this parameter unless a non-default reference voltage is used.
+    Default: 1250 (mV)
+
+    Reference voltage on VREF_ADC pin in mV. It should not be necessary to set
+    this parameter unless a non-default reference voltage is used.
 
 
 Description
@@ -64,9 +91,10 @@ the devices explicitly. When instantiating the device, you have to specify
 its configuration register address.
 
 Example: the following will load the driver for an SMM665 at address 0x57
-on I2C bus #1:
-$ modprobe smm665
-$ echo smm665 0x57 > /sys/bus/i2c/devices/i2c-1/new_device
+on I2C bus #1::
+
+	$ modprobe smm665
+	$ echo smm665 0x57 > /sys/bus/i2c/devices/i2c-1/new_device
 
 
 Sysfs entries
@@ -84,6 +112,7 @@ max otherwise. For details please see the SMM665 datasheet.
 
 For SMM465 and SMM764, values for Channel E and F are reported but undefined.
 
+======================= =======================================================
 in1_input		12V input voltage (mV)
 in2_input		3.3V (VDD) input voltage (mV)
 in3_input		Channel A voltage (mV)
@@ -155,3 +184,4 @@ temp1_min		Mimimum chip temperature
 temp1_max		Maximum chip temperature
 temp1_crit		Critical chip temperature
 temp1_crit_alarm	Temperature critical alarm
+======================= =======================================================
diff --git a/Documentation/hwmon/smsc47b397 b/Documentation/hwmon/smsc47b397.rst
index 3a43b6948924..600194cf1804 100644
--- a/Documentation/hwmon/smsc47b397
+++ b/Documentation/hwmon/smsc47b397.rst
@@ -2,29 +2,38 @@ Kernel driver smsc47b397
 ========================
 
 Supported chips:
+
   * SMSC LPC47B397-NC
+
   * SMSC SCH5307-NS
+
   * SMSC SCH5317
+
     Prefix: 'smsc47b397'
+
     Addresses scanned: none, address read from Super I/O config space
+
     Datasheet: In this file
 
-Authors: Mark M. Hoffman <mhoffman@lightlink.com>
-         Utilitek Systems, Inc.
+Authors:
+
+       - Mark M. Hoffman <mhoffman@lightlink.com>
+       - Utilitek Systems, Inc.
 
 November 23, 2004
 
-The following specification describes the SMSC LPC47B397-NC[1] sensor chip
+The following specification describes the SMSC LPC47B397-NC [1]_ sensor chip
 (for which there is no public datasheet available). This document was
 provided by Craig Kelly (In-Store Broadcast Network) and edited/corrected
 by Mark M. Hoffman <mhoffman@lightlink.com>.
 
-[1] And SMSC SCH5307-NS and SCH5317, which have different device IDs but are
-otherwise compatible.
+.. [1] And SMSC SCH5307-NS and SCH5317, which have different device IDs but are
+       otherwise compatible.
 
-* * * * *
+-------------------------------------------------------------------------
 
-Methods for detecting the HP SIO and reading the thermal data on a dc7100.
+Methods for detecting the HP SIO and reading the thermal data on a dc7100
+-------------------------------------------------------------------------
 
 The thermal information on the dc7100 is contained in the SIO Hardware Monitor
 (HWM). The information is accessed through an index/data pair. The index/data
@@ -35,18 +44,22 @@ and 0x61 (LSB). Currently we are using 0x480 for the HWM Base Address and
 
 Reading temperature information.
 The temperature information is located in the following registers:
+
+=============== ======= =======================================================
 Temp1		0x25	(Currently, this reflects the CPU temp on all systems).
 Temp2		0x26
 Temp3		0x27
 Temp4		0x80
+=============== ======= =======================================================
 
 Programming Example
-The following is an example of how to read the HWM temperature registers:
-MOV	DX,480H
-MOV	AX,25H
-OUT	DX,AL
-MOV	DX,481H
-IN	AL,DX
+The following is an example of how to read the HWM temperature registers::
+
+	MOV	DX,480H
+	MOV	AX,25H
+	OUT	DX,AL
+	MOV	DX,481H
+	IN	AL,DX
 
 AL contains the data in hex, the temperature in Celsius is the decimal
 equivalent.
@@ -55,25 +68,32 @@ Ex: If AL contains 0x2A, the temperature is 42 degrees C.
 
 Reading tach information.
 The fan speed information is located in the following registers:
+
+=============== ======= ======= =================================
 		LSB	MSB
 Tach1		0x28	0x29	(Currently, this reflects the CPU
 				fan speed on all systems).
 Tach2		0x2A	0x2B
 Tach3		0x2C	0x2D
 Tach4		0x2E	0x2F
+=============== ======= ======= =================================
 
-Important!!!
-Reading the tach LSB locks the tach MSB.
-The LSB Must be read first.
+.. Important::
+
+	Reading the tach LSB locks the tach MSB.
+	The LSB Must be read first.
+
+How to convert the tach reading to RPM
+--------------------------------------
 
-How to convert the tach reading to RPM.
 The tach reading (TCount) is given by: (Tach MSB * 256) + (Tach LSB)
 The SIO counts the number of 90kHz (11.111us) pulses per revolution.
 RPM = 60/(TCount * 11.111us)
 
-Example:
-Reg 0x28 = 0x9B
-Reg 0x29 = 0x08
+Example::
+
+	Reg 0x28 = 0x9B
+	Reg 0x29 = 0x08
 
 TCount = 0x89B = 2203
 
@@ -81,21 +101,28 @@ RPM = 60 / (2203 * 11.11111 E-6) = 2451 RPM
 
 Obtaining the SIO version.
 
-CONFIGURATION SEQUENCE
+Configuration Sequence
+----------------------
+
 To program the configuration registers, the following sequence must be followed:
 1. Enter Configuration Mode
 2. Configure the Configuration Registers
 3. Exit Configuration Mode.
 
 Enter Configuration Mode
+^^^^^^^^^^^^^^^^^^^^^^^^
+
 To place the chip into the Configuration State The config key (0x55) is written
 to the CONFIG PORT (0x2E).
 
 Configuration Mode
+^^^^^^^^^^^^^^^^^^
+
 In configuration mode, the INDEX PORT is located at the CONFIG PORT address and
 the DATA PORT is at INDEX PORT address + 1.
 
 The desired configuration registers are accessed in two steps:
+
 a.	Write the index of the Logical Device Number Configuration Register
 	(i.e., 0x07) to the INDEX PORT and then write the number of the
 	desired logical device to the DATA PORT.
@@ -104,30 +131,35 @@ b.	Write the address of the desired configuration register within the
 	logical device to the INDEX PORT and then write or read the config-
 	uration register through the DATA PORT.
 
-Note: If accessing the Global Configuration Registers, step (a) is not required.
+Note:
+	If accessing the Global Configuration Registers, step (a) is not required.
 
 Exit Configuration Mode
+^^^^^^^^^^^^^^^^^^^^^^^
+
 To exit the Configuration State the write 0xAA to the CONFIG PORT (0x2E).
 The chip returns to the RUN State.  (This is important).
 
 Programming Example
-The following is an example of how to read the SIO Device ID located at 0x20
-
-; ENTER CONFIGURATION MODE
-MOV	DX,02EH
-MOV	AX,055H
-OUT	DX,AL
-; GLOBAL CONFIGURATION  REGISTER
-MOV	DX,02EH
-MOV	AL,20H
-OUT	DX,AL
-; READ THE DATA
-MOV	DX,02FH
-IN	AL,DX
-; EXIT CONFIGURATION MODE
-MOV	DX,02EH
-MOV	AX,0AAH
-OUT	DX,AL
+^^^^^^^^^^^^^^^^^^^
+
+The following is an example of how to read the SIO Device ID located at 0x20:
+
+	; ENTER CONFIGURATION MODE
+	MOV	DX,02EH
+	MOV	AX,055H
+	OUT	DX,AL
+	; GLOBAL CONFIGURATION  REGISTER
+	MOV	DX,02EH
+	MOV	AL,20H
+	OUT	DX,AL
+	; READ THE DATA
+	MOV	DX,02FH
+	IN	AL,DX
+	; EXIT CONFIGURATION MODE
+	MOV	DX,02EH
+	MOV	AX,0AAH
+	OUT	DX,AL
 
 The registers of interest for identifying the SIO on the dc7100 are Device ID
 (0x20) and Device Rev  (0x21).
@@ -135,29 +167,31 @@ The registers of interest for identifying the SIO on the dc7100 are Device ID
 The Device ID will read 0x6F (0x81 for SCH5307-NS, and 0x85 for SCH5317)
 The Device Rev currently reads 0x01
 
-Obtaining the HWM Base Address.
+Obtaining the HWM Base Address
+------------------------------
+
 The following is an example of how to read the HWM Base Address located in
-Logical Device 8.
-
-; ENTER CONFIGURATION MODE
-MOV	DX,02EH
-MOV	AX,055H
-OUT	DX,AL
-; CONFIGURE REGISTER CRE0,
-; LOGICAL DEVICE 8
-MOV	DX,02EH
-MOV	AL,07H
-OUT	DX,AL ;Point to LD# Config Reg
-MOV	DX,02FH
-MOV	AL, 08H
-OUT	DX,AL;Point to Logical Device 8
-;
-MOV	DX,02EH
-MOV	AL,60H
-OUT	DX,AL	; Point to HWM Base Addr MSB
-MOV	DX,02FH
-IN	AL,DX	; Get MSB of HWM Base Addr
-; EXIT CONFIGURATION MODE
-MOV	DX,02EH
-MOV	AX,0AAH
-OUT	DX,AL
+Logical Device 8::
+
+	; ENTER CONFIGURATION MODE
+	MOV	DX,02EH
+	MOV	AX,055H
+	OUT	DX,AL
+	; CONFIGURE REGISTER CRE0,
+	; LOGICAL DEVICE 8
+	MOV	DX,02EH
+	MOV	AL,07H
+	OUT	DX,AL ;Point to LD# Config Reg
+	MOV	DX,02FH
+	MOV	AL, 08H
+	OUT	DX,AL;Point to Logical Device 8
+	;
+	MOV	DX,02EH
+	MOV	AL,60H
+	OUT	DX,AL	; Point to HWM Base Addr MSB
+	MOV	DX,02FH
+	IN	AL,DX	; Get MSB of HWM Base Addr
+	; EXIT CONFIGURATION MODE
+	MOV	DX,02EH
+	MOV	AX,0AAH
+	OUT	DX,AL
diff --git a/Documentation/hwmon/smsc47m1 b/Documentation/hwmon/smsc47m1.rst
index 10a24b420686..c54eabd5eb57 100644
--- a/Documentation/hwmon/smsc47m1
+++ b/Documentation/hwmon/smsc47m1.rst
@@ -2,30 +2,53 @@ Kernel driver smsc47m1
 ======================
 
 Supported chips:
+
   * SMSC LPC47B27x, LPC47M112, LPC47M10x, LPC47M13x, LPC47M14x,
+
     LPC47M15x and LPC47M192
+
     Addresses scanned: none, address read from Super I/O config space
+
     Prefix: 'smsc47m1'
+
     Datasheets:
-        http://www.smsc.com/media/Downloads_Public/Data_Sheets/47b272.pdf
-        http://www.smsc.com/media/Downloads_Public/Data_Sheets/47m10x.pdf
-        http://www.smsc.com/media/Downloads_Public/Data_Sheets/47m112.pdf
-        http://www.smsc.com/
+
+	http://www.smsc.com/media/Downloads_Public/Data_Sheets/47b272.pdf
+
+	http://www.smsc.com/media/Downloads_Public/Data_Sheets/47m10x.pdf
+
+	http://www.smsc.com/media/Downloads_Public/Data_Sheets/47m112.pdf
+
+	http://www.smsc.com/
+
   * SMSC LPC47M292
+
     Addresses scanned: none, address read from Super I/O config space
+
     Prefix: 'smsc47m2'
+
     Datasheet: Not public
+
   * SMSC LPC47M997
+
     Addresses scanned: none, address read from Super I/O config space
+
     Prefix: 'smsc47m1'
+
     Datasheet: none
 
+
+
 Authors:
-        Mark D. Studebaker <mdsxyz123@yahoo.com>,
-        With assistance from Bruce Allen <ballen@uwm.edu>, and his
-        fan.c program: http://www.lsc-group.phys.uwm.edu/%7Eballen/driver/
-        Gabriele Gorla <gorlik@yahoo.com>,
-        Jean Delvare <jdelvare@suse.de>
+
+     - Mark D. Studebaker <mdsxyz123@yahoo.com>,
+     - With assistance from Bruce Allen <ballen@uwm.edu>, and his
+       fan.c program:
+
+       - http://www.lsc-group.phys.uwm.edu/%7Eballen/driver/
+
+     - Gabriele Gorla <gorlik@yahoo.com>,
+     - Jean Delvare <jdelvare@suse.de>
 
 Description
 -----------
@@ -57,7 +80,7 @@ hardware registers are read whenever any data is read (unless it is less
 than 1.5 seconds since the last update). This means that you can easily
 miss once-only alarms.
 
+------------------------------------------------------------------
 
-**********************
 The lm_sensors project gratefully acknowledges the support of
 Intel in the development of this driver.
diff --git a/Documentation/hwmon/smsc47m192 b/Documentation/hwmon/smsc47m192
deleted file mode 100644
index 6d54ecb7b3f8..000000000000
--- a/Documentation/hwmon/smsc47m192
+++ /dev/null
@@ -1,103 +0,0 @@
-Kernel driver smsc47m192
-========================
-
-Supported chips:
-  * SMSC LPC47M192, LPC47M15x, LPC47M292 and LPC47M997
-    Prefix: 'smsc47m192'
-    Addresses scanned: I2C 0x2c - 0x2d
-    Datasheet: The datasheet for LPC47M192 is publicly available from
-               http://www.smsc.com/
-               The LPC47M15x, LPC47M292 and LPC47M997 are compatible for
-               hardware monitoring.
-
-Author: Hartmut Rick <linux@rick.claranet.de>
-        Special thanks to Jean Delvare for careful checking
-        of the code and many helpful comments and suggestions.
-
-
-Description
------------
-
-This driver implements support for the hardware sensor capabilities
-of the SMSC LPC47M192 and compatible Super-I/O chips.
-
-These chips support 3 temperature channels and 8 voltage inputs
-as well as CPU voltage VID input.
-
-They do also have fan monitoring and control capabilities, but the
-these features are accessed via ISA bus and are not supported by this
-driver. Use the 'smsc47m1' driver for fan monitoring and control.
-
-Voltages and temperatures are measured by an 8-bit ADC, the resolution
-of the temperatures is 1 bit per degree C.
-Voltages are scaled such that the nominal voltage corresponds to
-192 counts, i.e. 3/4 of the full range. Thus the available range for
-each voltage channel is 0V ... 255/192*(nominal voltage), the resolution
-is 1 bit per (nominal voltage)/192.
-Both voltage and temperature values are scaled by 1000, the sys files
-show voltages in mV and temperatures in units of 0.001 degC.
-
-The +12V analog voltage input channel (in4_input) is multiplexed with
-bit 4 of the encoded CPU voltage. This means that you either get
-a +12V voltage measurement or a 5 bit CPU VID, but not both.
-The default setting is to use the pin as 12V input, and use only 4 bit VID.
-This driver assumes that the information in the configuration register
-is correct, i.e. that the BIOS has updated the configuration if
-the motherboard has this input wired to VID4.
-
-The temperature and voltage readings are updated once every 1.5 seconds.
-Reading them more often repeats the same values.
-
-
-sysfs interface
----------------
-
-in0_input	- +2.5V voltage input
-in1_input	- CPU voltage input (nominal 2.25V)
-in2_input	- +3.3V voltage input
-in3_input	- +5V voltage input
-in4_input	- +12V voltage input (may be missing if used as VID4)
-in5_input	- Vcc voltage input (nominal 3.3V)
-		  This is the supply voltage of the sensor chip itself.
-in6_input	- +1.5V voltage input
-in7_input	- +1.8V voltage input
-
-in[0-7]_min,
-in[0-7]_max	- lower and upper alarm thresholds for in[0-7]_input reading
-
-		  All voltages are read and written in mV.
-
-in[0-7]_alarm	- alarm flags for voltage inputs
-		  These files read '1' in case of alarm, '0' otherwise.
-
-temp1_input	- chip temperature measured by on-chip diode
-temp[2-3]_input	- temperature measured by external diodes (one of these would
-		  typically be wired to the diode inside the CPU)
-
-temp[1-3]_min,
-temp[1-3]_max	- lower and upper alarm thresholds for temperatures
-
-temp[1-3]_offset - temperature offset registers
-		  The chip adds the offsets stored in these registers to
-		  the corresponding temperature readings.
-		  Note that temp1 and temp2 offsets share the same register,
-		  they cannot both be different from zero at the same time.
-		  Writing a non-zero number to one of them will reset the other
-		  offset to zero.
-
-		  All temperatures and offsets are read and written in
-		  units of 0.001 degC.
-
-temp[1-3]_alarm - alarm flags for temperature inputs, '1' in case of alarm,
-		  '0' otherwise.
-temp[2-3]_input_fault - diode fault flags for temperature inputs 2 and 3.
-		  A fault is detected if the two pins for the corresponding
-		  sensor are open or shorted, or any of the two is shorted
-		  to ground or Vcc. '1' indicates a diode fault.
-
-cpu0_vid	- CPU voltage as received from the CPU
-
-vrm		- CPU VID standard used for decoding CPU voltage
-
-		  The *_min, *_max, *_offset and vrm files can be read and
-		  written, all others are read-only.
diff --git a/Documentation/hwmon/smsc47m192.rst b/Documentation/hwmon/smsc47m192.rst
new file mode 100644
index 000000000000..a2e86ab67918
--- /dev/null
+++ b/Documentation/hwmon/smsc47m192.rst
@@ -0,0 +1,116 @@
+Kernel driver smsc47m192
+========================
+
+Supported chips:
+
+  * SMSC LPC47M192, LPC47M15x, LPC47M292 and LPC47M997
+
+    Prefix: 'smsc47m192'
+
+    Addresses scanned: I2C 0x2c - 0x2d
+
+    Datasheet: The datasheet for LPC47M192 is publicly available from
+
+	       http://www.smsc.com/
+
+	       The LPC47M15x, LPC47M292 and LPC47M997 are compatible for
+
+	       hardware monitoring.
+
+
+
+Author:
+      - Hartmut Rick <linux@rick.claranet.de>
+
+      - Special thanks to Jean Delvare for careful checking
+	of the code and many helpful comments and suggestions.
+
+
+Description
+-----------
+
+This driver implements support for the hardware sensor capabilities
+of the SMSC LPC47M192 and compatible Super-I/O chips.
+
+These chips support 3 temperature channels and 8 voltage inputs
+as well as CPU voltage VID input.
+
+They do also have fan monitoring and control capabilities, but the
+these features are accessed via ISA bus and are not supported by this
+driver. Use the 'smsc47m1' driver for fan monitoring and control.
+
+Voltages and temperatures are measured by an 8-bit ADC, the resolution
+of the temperatures is 1 bit per degree C.
+Voltages are scaled such that the nominal voltage corresponds to
+192 counts, i.e. 3/4 of the full range. Thus the available range for
+each voltage channel is 0V ... 255/192*(nominal voltage), the resolution
+is 1 bit per (nominal voltage)/192.
+Both voltage and temperature values are scaled by 1000, the sys files
+show voltages in mV and temperatures in units of 0.001 degC.
+
+The +12V analog voltage input channel (in4_input) is multiplexed with
+bit 4 of the encoded CPU voltage. This means that you either get
+a +12V voltage measurement or a 5 bit CPU VID, but not both.
+The default setting is to use the pin as 12V input, and use only 4 bit VID.
+This driver assumes that the information in the configuration register
+is correct, i.e. that the BIOS has updated the configuration if
+the motherboard has this input wired to VID4.
+
+The temperature and voltage readings are updated once every 1.5 seconds.
+Reading them more often repeats the same values.
+
+
+sysfs interface
+---------------
+
+===================== ==========================================================
+in0_input	      +2.5V voltage input
+in1_input	      CPU voltage input (nominal 2.25V)
+in2_input	      +3.3V voltage input
+in3_input	      +5V voltage input
+in4_input	      +12V voltage input (may be missing if used as VID4)
+in5_input	      Vcc voltage input (nominal 3.3V)
+		      This is the supply voltage of the sensor chip itself.
+in6_input	      +1.5V voltage input
+in7_input	      +1.8V voltage input
+
+in[0-7]_min,
+in[0-7]_max	      lower and upper alarm thresholds for in[0-7]_input reading
+
+		      All voltages are read and written in mV.
+
+in[0-7]_alarm	      alarm flags for voltage inputs
+		      These files read '1' in case of alarm, '0' otherwise.
+
+temp1_input	      chip temperature measured by on-chip diode
+temp[2-3]_input	      temperature measured by external diodes (one of these
+		      would typically be wired to the diode inside the CPU)
+
+temp[1-3]_min,
+temp[1-3]_max	      lower and upper alarm thresholds for temperatures
+
+temp[1-3]_offset      temperature offset registers
+		      The chip adds the offsets stored in these registers to
+		      the corresponding temperature readings.
+		      Note that temp1 and temp2 offsets share the same register,
+		      they cannot both be different from zero at the same time.
+		      Writing a non-zero number to one of them will reset the other
+		      offset to zero.
+
+		      All temperatures and offsets are read and written in
+		      units of 0.001 degC.
+
+temp[1-3]_alarm       alarm flags for temperature inputs, '1' in case of alarm,
+		      '0' otherwise.
+temp[2-3]_input_fault diode fault flags for temperature inputs 2 and 3.
+		      A fault is detected if the two pins for the corresponding
+		      sensor are open or shorted, or any of the two is shorted
+		      to ground or Vcc. '1' indicates a diode fault.
+
+cpu0_vid	      CPU voltage as received from the CPU
+
+vrm		      CPU VID standard used for decoding CPU voltage
+===================== ==========================================================
+
+The `*_min`, `*_max`, `*_offset` and `vrm` files can be read and written,
+all others are read-only.
diff --git a/Documentation/hwmon/submitting-patches b/Documentation/hwmon/submitting-patches.rst
index f88221b46153..f9796b9d9db6 100644
--- a/Documentation/hwmon/submitting-patches
+++ b/Documentation/hwmon/submitting-patches.rst
@@ -1,5 +1,5 @@
-	How to Get Your Patch Accepted Into the Hwmon Subsystem
-	-------------------------------------------------------
+How to Get Your Patch Accepted Into the Hwmon Subsystem
+=======================================================
 
 This text is a collection of suggestions for people writing patches or
 drivers for the hwmon subsystem. Following these suggestions will greatly
@@ -9,11 +9,12 @@ increase the chances of your change being accepted.
 1. General
 ----------
 
-* It should be unnecessary to mention, but please read and follow
-    Documentation/process/submit-checklist.rst
-    Documentation/process/submitting-drivers.rst
-    Documentation/process/submitting-patches.rst
-    Documentation/process/coding-style.rst
+* It should be unnecessary to mention, but please read and follow:
+
+    - Documentation/process/submit-checklist.rst
+    - Documentation/process/submitting-drivers.rst
+    - Documentation/process/submitting-patches.rst
+    - Documentation/process/coding-style.rst
 
 * Please run your patch through 'checkpatch --strict'. There should be no
   errors, no warnings, and few if any check messages. If there are any
@@ -38,7 +39,7 @@ increase the chances of your change being accepted.
 2. Adding functionality to existing drivers
 -------------------------------------------
 
-* Make sure the documentation in Documentation/hwmon/<driver_name> is up to
+* Make sure the documentation in Documentation/hwmon/<driver_name>.rst is up to
   date.
 
 * Make sure the information in Kconfig is up to date.
@@ -60,7 +61,7 @@ increase the chances of your change being accepted.
 
 * Consider adding yourself to MAINTAINERS.
 
-* Document the driver in Documentation/hwmon/<driver_name>.
+* Document the driver in Documentation/hwmon/<driver_name>.rst.
 
 * Add the driver to Kconfig and Makefile in alphabetical order.
 
@@ -133,7 +134,7 @@ increase the chances of your change being accepted.
   non-standard attributes, or you believe you do, discuss it on the mailing list
   first. Either case, provide a detailed explanation why you need the
   non-standard attribute(s).
-  Standard attributes are specified in Documentation/hwmon/sysfs-interface.
+  Standard attributes are specified in Documentation/hwmon/sysfs-interface.rst.
 
 * When deciding which sysfs attributes to support, look at the chip's
   capabilities. While we do not expect your driver to support everything the
diff --git a/Documentation/hwmon/sysfs-interface b/Documentation/hwmon/sysfs-interface.rst
index 2b9e1005d88b..fd590633bb14 100644
--- a/Documentation/hwmon/sysfs-interface
+++ b/Documentation/hwmon/sysfs-interface.rst
@@ -1,5 +1,5 @@
 Naming and data format standards for sysfs files
-------------------------------------------------
+================================================
 
 The libsensors library offers an interface to the raw sensors data
 through the sysfs interface. Since lm-sensors 3.0.0, libsensors is
@@ -32,7 +32,7 @@ this reason, it is still not recommended to bypass the library.
 
 Each chip gets its own directory in the sysfs /sys/devices tree.  To
 find all sensor chips, it is easier to follow the device symlinks from
-/sys/class/hwmon/hwmon*.
+`/sys/class/hwmon/hwmon*`.
 
 Up to lm-sensors 3.0.0, libsensors looks for hardware monitoring attributes
 in the "physical" device directory. Since lm-sensors 3.0.1, attributes found
@@ -67,11 +67,13 @@ are interpreted as 0! For more on how written strings are interpreted see the
 
 -------------------------------------------------------------------------
 
-[0-*]	denotes any positive number starting from 0
-[1-*]	denotes any positive number starting from 1
+======= ===========================================
+`[0-*]`	denotes any positive number starting from 0
+`[1-*]`	denotes any positive number starting from 1
 RO	read only value
 WO	write only value
 RW	read/write value
+======= ===========================================
 
 Read/write values may be read-only for some chips, depending on the
 hardware implementation.
@@ -80,57 +82,82 @@ All entries (except name) are optional, and should only be created in a
 given driver if the chip has the feature.
 
 
-*********************
-* Global attributes *
-*********************
+*****************
+Global attributes
+*****************
 
-name		The chip name.
+`name`
+		The chip name.
 		This should be a short, lowercase string, not containing
 		whitespace, dashes, or the wildcard character '*'.
 		This attribute represents the chip name. It is the only
 		mandatory attribute.
 		I2C devices get this attribute created automatically.
+
 		RO
 
-update_interval	The interval at which the chip will update readings.
+`update_interval`
+		The interval at which the chip will update readings.
 		Unit: millisecond
+
 		RW
+
 		Some devices have a variable update rate or interval.
 		This attribute can be used to change it to the desired value.
 
 
-************
-* Voltages *
-************
+********
+Voltages
+********
+
+`in[0-*]_min`
+		Voltage min value.
 
-in[0-*]_min	Voltage min value.
 		Unit: millivolt
+
 		RW
-		
-in[0-*]_lcrit	Voltage critical min value.
+
+`in[0-*]_lcrit`
+		Voltage critical min value.
+
 		Unit: millivolt
+
 		RW
+
 		If voltage drops to or below this limit, the system may
 		take drastic action such as power down or reset. At the very
 		least, it should report a fault.
 
-in[0-*]_max	Voltage max value.
+`in[0-*]_max`
+		Voltage max value.
+
 		Unit: millivolt
+
 		RW
-		
-in[0-*]_crit	Voltage critical max value.
+
+`in[0-*]_crit`
+		Voltage critical max value.
+
 		Unit: millivolt
+
 		RW
+
 		If voltage reaches or exceeds this limit, the system may
 		take drastic action such as power down or reset. At the very
 		least, it should report a fault.
 
-in[0-*]_input	Voltage input value.
+`in[0-*]_input`
+		Voltage input value.
+
 		Unit: millivolt
+
 		RO
+
 		Voltage measured on the chip pin.
+
 		Actual voltage depends on the scaling resistors on the
 		motherboard, as recommended in the chip datasheet.
+
 		This varies by chip and by motherboard.
 		Because of this variation, values are generally NOT scaled
 		by the chip driver, and must be done by the application.
@@ -140,166 +167,232 @@ in[0-*]_input	Voltage input value.
 		thumb: drivers should report the voltage values at the
 		"pins" of the chip.
 
-in[0-*]_average
+`in[0-*]_average`
 		Average voltage
+
 		Unit: millivolt
+
 		RO
 
-in[0-*]_lowest
+`in[0-*]_lowest`
 		Historical minimum voltage
+
 		Unit: millivolt
+
 		RO
 
-in[0-*]_highest
+`in[0-*]_highest`
 		Historical maximum voltage
+
 		Unit: millivolt
+
 		RO
 
-in[0-*]_reset_history
+`in[0-*]_reset_history`
 		Reset inX_lowest and inX_highest
+
 		WO
 
-in_reset_history
+`in_reset_history`
 		Reset inX_lowest and inX_highest for all sensors
+
 		WO
 
-in[0-*]_label	Suggested voltage channel label.
+`in[0-*]_label`
+		Suggested voltage channel label.
+
 		Text string
+
 		Should only be created if the driver has hints about what
 		this voltage channel is being used for, and user-space
 		doesn't. In all other cases, the label is provided by
 		user-space.
+
 		RO
 
-in[0-*]_enable
+`in[0-*]_enable`
 		Enable or disable the sensors.
+
 		When disabled the sensor read will return -ENODATA.
-		1: Enable
-		0: Disable
+
+		- 1: Enable
+		- 0: Disable
+
 		RW
 
-cpu[0-*]_vid	CPU core reference voltage.
+`cpu[0-*]_vid`
+		CPU core reference voltage.
+
 		Unit: millivolt
+
 		RO
+
 		Not always correct.
 
-vrm		Voltage Regulator Module version number. 
+`vrm`
+		Voltage Regulator Module version number.
+
 		RW (but changing it should no more be necessary)
+
 		Originally the VRM standard version multiplied by 10, but now
 		an arbitrary number, as not all standards have a version
 		number.
+
 		Affects the way the driver calculates the CPU core reference
 		voltage from the vid pins.
 
 Also see the Alarms section for status flags associated with voltages.
 
 
-********
-* Fans *
-********
+****
+Fans
+****
+
+`fan[1-*]_min`
+		Fan minimum value
 
-fan[1-*]_min	Fan minimum value
 		Unit: revolution/min (RPM)
+
 		RW
 
-fan[1-*]_max	Fan maximum value
+`fan[1-*]_max`
+		Fan maximum value
+
 		Unit: revolution/min (RPM)
+
 		Only rarely supported by the hardware.
 		RW
 
-fan[1-*]_input	Fan input value.
+`fan[1-*]_input`
+		Fan input value.
+
 		Unit: revolution/min (RPM)
+
 		RO
 
-fan[1-*]_div	Fan divisor.
+`fan[1-*]_div`
+		Fan divisor.
+
 		Integer value in powers of two (1, 2, 4, 8, 16, 32, 64, 128).
+
 		RW
+
 		Some chips only support values 1, 2, 4 and 8.
 		Note that this is actually an internal clock divisor, which
 		affects the measurable speed range, not the read value.
 
-fan[1-*]_pulses	Number of tachometer pulses per fan revolution.
+`fan[1-*]_pulses`
+		Number of tachometer pulses per fan revolution.
+
 		Integer value, typically between 1 and 4.
+
 		RW
+
 		This value is a characteristic of the fan connected to the
 		device's input, so it has to be set in accordance with the fan
 		model.
+
 		Should only be created if the chip has a register to configure
 		the number of pulses. In the absence of such a register (and
 		thus attribute) the value assumed by all devices is 2 pulses
 		per fan revolution.
 
-fan[1-*]_target
+`fan[1-*]_target`
 		Desired fan speed
+
 		Unit: revolution/min (RPM)
+
 		RW
+
 		Only makes sense if the chip supports closed-loop fan speed
 		control based on the measured fan speed.
 
-fan[1-*]_label	Suggested fan channel label.
+`fan[1-*]_label`
+		Suggested fan channel label.
+
 		Text string
+
 		Should only be created if the driver has hints about what
 		this fan channel is being used for, and user-space doesn't.
 		In all other cases, the label is provided by user-space.
+
 		RO
 
-fan[1-*]_enable
+`fan[1-*]_enable`
 		Enable or disable the sensors.
+
 		When disabled the sensor read will return -ENODATA.
-		1: Enable
-		0: Disable
+
+		- 1: Enable
+		- 0: Disable
+
 		RW
 
 Also see the Alarms section for status flags associated with fans.
 
 
-*******
-* PWM *
-*******
+***
+PWM
+***
+
+`pwm[1-*]`
+		Pulse width modulation fan control.
 
-pwm[1-*]	Pulse width modulation fan control.
 		Integer value in the range 0 to 255
+
 		RW
+
 		255 is max or 100%.
 
-pwm[1-*]_enable
+`pwm[1-*]_enable`
 		Fan speed control method:
-		0: no fan speed control (i.e. fan at full speed)
-		1: manual fan speed control enabled (using pwm[1-*])
-		2+: automatic fan speed control enabled
+
+		- 0: no fan speed control (i.e. fan at full speed)
+		- 1: manual fan speed control enabled (using `pwm[1-*]`)
+		- 2+: automatic fan speed control enabled
+
 		Check individual chip documentation files for automatic mode
 		details.
+
 		RW
 
-pwm[1-*]_mode	0: DC mode (direct current)
-		1: PWM mode (pulse-width modulation)
+`pwm[1-*]_mode`
+		- 0: DC mode (direct current)
+		- 1: PWM mode (pulse-width modulation)
+
 		RW
 
-pwm[1-*]_freq	Base PWM frequency in Hz.
+`pwm[1-*]_freq`
+		Base PWM frequency in Hz.
+
 		Only possibly available when pwmN_mode is PWM, but not always
 		present even then.
+
 		RW
 
-pwm[1-*]_auto_channels_temp
+`pwm[1-*]_auto_channels_temp`
 		Select which temperature channels affect this PWM output in
-		auto mode. Bitfield, 1 is temp1, 2 is temp2, 4 is temp3 etc...
+		auto mode.
+
+		Bitfield, 1 is temp1, 2 is temp2, 4 is temp3 etc...
 		Which values are possible depend on the chip used.
+
 		RW
 
-pwm[1-*]_auto_point[1-*]_pwm
-pwm[1-*]_auto_point[1-*]_temp
-pwm[1-*]_auto_point[1-*]_temp_hyst
-		Define the PWM vs temperature curve. Number of trip points is
-		chip-dependent. Use this for chips which associate trip points
-		to PWM output channels.
+`pwm[1-*]_auto_point[1-*]_pwm` / `pwm[1-*]_auto_point[1-*]_temp` / `pwm[1-*]_auto_point[1-*]_temp_hyst`
+		Define the PWM vs temperature curve.
+
+		Number of trip points is chip-dependent. Use this for chips
+		which associate trip points to PWM output channels.
+
 		RW
 
-temp[1-*]_auto_point[1-*]_pwm
-temp[1-*]_auto_point[1-*]_temp
-temp[1-*]_auto_point[1-*]_temp_hyst
-		Define the PWM vs temperature curve. Number of trip points is
-		chip-dependent. Use this for chips which associate trip points
-		to temperature channels.
+`temp[1-*]_auto_point[1-*]_pwm` / `temp[1-*]_auto_point[1-*]_temp` / `temp[1-*]_auto_point[1-*]_temp_hyst`
+		Define the PWM vs temperature curve.
+
+		Number of trip points is chip-dependent. Use this for chips
+		which associate trip points to temperature channels.
+
 		RW
 
 There is a third case where trip points are associated to both PWM output
@@ -312,122 +405,173 @@ The actual result is up to the chip, but in general the highest candidate
 value (fastest fan speed) wins.
 
 
-****************
-* Temperatures *
-****************
+************
+Temperatures
+************
+
+`temp[1-*]_type`
+		Sensor type selection.
 
-temp[1-*]_type	Sensor type selection.
 		Integers 1 to 6
+
 		RW
-		1: CPU embedded diode
-		2: 3904 transistor
-		3: thermal diode
-		4: thermistor
-		5: AMD AMDSI
-		6: Intel PECI
+
+		- 1: CPU embedded diode
+		- 2: 3904 transistor
+		- 3: thermal diode
+		- 4: thermistor
+		- 5: AMD AMDSI
+		- 6: Intel PECI
+
 		Not all types are supported by all chips
 
-temp[1-*]_max	Temperature max value.
+`temp[1-*]_max`
+		Temperature max value.
+
 		Unit: millidegree Celsius (or millivolt, see below)
+
 		RW
 
-temp[1-*]_min	Temperature min value.
+`temp[1-*]_min`
+		Temperature min value.
+
 		Unit: millidegree Celsius
+
 		RW
 
-temp[1-*]_max_hyst
+`temp[1-*]_max_hyst`
 		Temperature hysteresis value for max limit.
+
 		Unit: millidegree Celsius
+
 		Must be reported as an absolute temperature, NOT a delta
 		from the max value.
+
 		RW
 
-temp[1-*]_min_hyst
+`temp[1-*]_min_hyst`
 		Temperature hysteresis value for min limit.
 		Unit: millidegree Celsius
+
 		Must be reported as an absolute temperature, NOT a delta
 		from the min value.
+
 		RW
 
-temp[1-*]_input Temperature input value.
+`temp[1-*]_input`
+	 Temperature input value.
+
 		Unit: millidegree Celsius
+
 		RO
 
-temp[1-*]_crit	Temperature critical max value, typically greater than
+`temp[1-*]_crit`
+		Temperature critical max value, typically greater than
 		corresponding temp_max values.
+
 		Unit: millidegree Celsius
+
 		RW
 
-temp[1-*]_crit_hyst
+`temp[1-*]_crit_hyst`
 		Temperature hysteresis value for critical limit.
+
 		Unit: millidegree Celsius
+
 		Must be reported as an absolute temperature, NOT a delta
 		from the critical value.
+
 		RW
 
-temp[1-*]_emergency
+`temp[1-*]_emergency`
 		Temperature emergency max value, for chips supporting more than
 		two upper temperature limits. Must be equal or greater than
 		corresponding temp_crit values.
+
 		Unit: millidegree Celsius
+
 		RW
 
-temp[1-*]_emergency_hyst
+`temp[1-*]_emergency_hyst`
 		Temperature hysteresis value for emergency limit.
+
 		Unit: millidegree Celsius
+
 		Must be reported as an absolute temperature, NOT a delta
 		from the emergency value.
+
 		RW
 
-temp[1-*]_lcrit	Temperature critical min value, typically lower than
+`temp[1-*]_lcrit`
+		Temperature critical min value, typically lower than
 		corresponding temp_min values.
+
 		Unit: millidegree Celsius
+
 		RW
 
-temp[1-*]_lcrit_hyst
+`temp[1-*]_lcrit_hyst`
 		Temperature hysteresis value for critical min limit.
+
 		Unit: millidegree Celsius
+
 		Must be reported as an absolute temperature, NOT a delta
 		from the critical min value.
+
 		RW
 
-temp[1-*]_offset
+`temp[1-*]_offset`
 		Temperature offset which is added to the temperature reading
 		by the chip.
+
 		Unit: millidegree Celsius
+
 		Read/Write value.
 
-temp[1-*]_label	Suggested temperature channel label.
+`temp[1-*]_label`
+		Suggested temperature channel label.
+
 		Text string
+
 		Should only be created if the driver has hints about what
 		this temperature channel is being used for, and user-space
 		doesn't. In all other cases, the label is provided by
 		user-space.
+
 		RO
 
-temp[1-*]_lowest
+`temp[1-*]_lowest`
 		Historical minimum temperature
+
 		Unit: millidegree Celsius
+
 		RO
 
-temp[1-*]_highest
+`temp[1-*]_highest`
 		Historical maximum temperature
+
 		Unit: millidegree Celsius
+
 		RO
 
-temp[1-*]_reset_history
+`temp[1-*]_reset_history`
 		Reset temp_lowest and temp_highest
+
 		WO
 
-temp_reset_history
+`temp_reset_history`
 		Reset temp_lowest and temp_highest for all sensors
+
 		WO
 
-temp[1-*]_enable
+`temp[1-*]_enable`
 		Enable or disable the sensors.
+
 		When disabled the sensor read will return -ENODATA.
-		1: Enable
-		0: Disable
+
+		- 1: Enable
+		- 0: Disable
+
 		RW
 
 Some chips measure temperature using external thermistors and an ADC, and
@@ -442,201 +586,300 @@ channels by the driver.
 Also see the Alarms section for status flags associated with temperatures.
 
 
-************
-* Currents *
-************
+********
+Currents
+********
+
+`curr[1-*]_max`
+		Current max value
 
-curr[1-*]_max	Current max value
 		Unit: milliampere
+
 		RW
 
-curr[1-*]_min	Current min value.
+`curr[1-*]_min`
+		Current min value.
+
 		Unit: milliampere
+
 		RW
 
-curr[1-*]_lcrit	Current critical low value
+`curr[1-*]_lcrit`
+		Current critical low value
+
 		Unit: milliampere
+
 		RW
 
-curr[1-*]_crit	Current critical high value.
+`curr[1-*]_crit`
+		Current critical high value.
+
 		Unit: milliampere
+
 		RW
 
-curr[1-*]_input	Current input value
+`curr[1-*]_input`
+		Current input value
+
 		Unit: milliampere
+
 		RO
 
-curr[1-*]_average
+`curr[1-*]_average`
 		Average current use
+
 		Unit: milliampere
+
 		RO
 
-curr[1-*]_lowest
+`curr[1-*]_lowest`
 		Historical minimum current
+
 		Unit: milliampere
+
 		RO
 
-curr[1-*]_highest
+`curr[1-*]_highest`
 		Historical maximum current
 		Unit: milliampere
 		RO
 
-curr[1-*]_reset_history
+`curr[1-*]_reset_history`
 		Reset currX_lowest and currX_highest
+
 		WO
 
-curr_reset_history
+`curr_reset_history`
 		Reset currX_lowest and currX_highest for all sensors
+
 		WO
 
-curr[1-*]_enable
+`curr[1-*]_enable`
 		Enable or disable the sensors.
+
 		When disabled the sensor read will return -ENODATA.
-		1: Enable
-		0: Disable
+
+		- 1: Enable
+		- 0: Disable
+
 		RW
 
 Also see the Alarms section for status flags associated with currents.
 
-*********
-* Power *
-*********
+*****
+Power
+*****
+
+`power[1-*]_average`
+				Average power use
 
-power[1-*]_average		Average power use
 				Unit: microWatt
+
 				RO
 
-power[1-*]_average_interval	Power use averaging interval.  A poll
+`power[1-*]_average_interval`
+				Power use averaging interval.  A poll
 				notification is sent to this file if the
 				hardware changes the averaging interval.
+
 				Unit: milliseconds
+
 				RW
 
-power[1-*]_average_interval_max	Maximum power use averaging interval
+`power[1-*]_average_interval_max`
+				Maximum power use averaging interval
+
 				Unit: milliseconds
+
 				RO
 
-power[1-*]_average_interval_min	Minimum power use averaging interval
+`power[1-*]_average_interval_min`
+				Minimum power use averaging interval
+
 				Unit: milliseconds
+
 				RO
 
-power[1-*]_average_highest	Historical average maximum power use
+`power[1-*]_average_highest`
+				Historical average maximum power use
+
 				Unit: microWatt
+
 				RO
 
-power[1-*]_average_lowest	Historical average minimum power use
+`power[1-*]_average_lowest`
+				Historical average minimum power use
+
 				Unit: microWatt
+
 				RO
 
-power[1-*]_average_max		A poll notification is sent to
-				power[1-*]_average when power use
+`power[1-*]_average_max`
+				A poll notification is sent to
+				`power[1-*]_average` when power use
 				rises above this value.
+
 				Unit: microWatt
+
 				RW
 
-power[1-*]_average_min		A poll notification is sent to
-				power[1-*]_average when power use
+`power[1-*]_average_min`
+				A poll notification is sent to
+				`power[1-*]_average` when power use
 				sinks below this value.
+
 				Unit: microWatt
+
 				RW
 
-power[1-*]_input		Instantaneous power use
+`power[1-*]_input`
+				Instantaneous power use
+
 				Unit: microWatt
+
 				RO
 
-power[1-*]_input_highest	Historical maximum power use
+`power[1-*]_input_highest`
+				Historical maximum power use
+
 				Unit: microWatt
+
 				RO
 
-power[1-*]_input_lowest		Historical minimum power use
+`power[1-*]_input_lowest`
+				Historical minimum power use
+
 				Unit: microWatt
+
 				RO
 
-power[1-*]_reset_history	Reset input_highest, input_lowest,
+`power[1-*]_reset_history`
+				Reset input_highest, input_lowest,
 				average_highest and average_lowest.
+
 				WO
 
-power[1-*]_accuracy		Accuracy of the power meter.
+`power[1-*]_accuracy`
+				Accuracy of the power meter.
+
 				Unit: Percent
+
 				RO
 
-power[1-*]_cap			If power use rises above this limit, the
+`power[1-*]_cap`
+				If power use rises above this limit, the
 				system should take action to reduce power use.
 				A poll notification is sent to this file if the
-				cap is changed by the hardware.  The *_cap
+				cap is changed by the hardware.  The `*_cap`
 				files only appear if the cap is known to be
 				enforced by hardware.
+
 				Unit: microWatt
+
 				RW
 
-power[1-*]_cap_hyst		Margin of hysteresis built around capping and
+`power[1-*]_cap_hyst`
+				Margin of hysteresis built around capping and
 				notification.
+
 				Unit: microWatt
+
 				RW
 
-power[1-*]_cap_max		Maximum cap that can be set.
+`power[1-*]_cap_max`
+				Maximum cap that can be set.
+
 				Unit: microWatt
+
 				RO
 
-power[1-*]_cap_min		Minimum cap that can be set.
+`power[1-*]_cap_min`
+				Minimum cap that can be set.
+
 				Unit: microWatt
+
 				RO
 
-power[1-*]_max			Maximum power.
+`power[1-*]_max`
+				Maximum power.
+
 				Unit: microWatt
+
 				RW
 
-power[1-*]_crit			Critical maximum power.
+`power[1-*]_crit`
+				Critical maximum power.
+
 				If power rises to or above this limit, the
 				system is expected take drastic action to reduce
 				power consumption, such as a system shutdown or
 				a forced powerdown of some devices.
+
 				Unit: microWatt
+
 				RW
 
-power[1-*]_enable		Enable or disable the sensors.
+`power[1-*]_enable`
+				Enable or disable the sensors.
+
 				When disabled the sensor read will return
 				-ENODATA.
-				1: Enable
-				0: Disable
+
+				- 1: Enable
+				- 0: Disable
+
 				RW
 
 Also see the Alarms section for status flags associated with power readings.
 
-**********
-* Energy *
-**********
+******
+Energy
+******
+
+`energy[1-*]_input`
+				Cumulative energy use
 
-energy[1-*]_input		Cumulative energy use
 				Unit: microJoule
+
 				RO
 
-energy[1-*]_enable		Enable or disable the sensors.
+`energy[1-*]_enable`
+				Enable or disable the sensors.
+
 				When disabled the sensor read will return
 				-ENODATA.
-				1: Enable
-				0: Disable
+
+				- 1: Enable
+				- 0: Disable
+
 				RW
 
-************
-* Humidity *
-************
+********
+Humidity
+********
+
+`humidity[1-*]_input`
+				Humidity
 
-humidity[1-*]_input		Humidity
 				Unit: milli-percent (per cent mille, pcm)
+
 				RO
 
 
-humidity[1-*]_enable		Enable or disable the sensors
+`humidity[1-*]_enable`
+				Enable or disable the sensors
+
 				When disabled the sensor read will return
 				-ENODATA.
-				1: Enable
-				0: Disable
+
+				- 1: Enable
+				- 0: Disable
+
 				RW
 
-**********
-* Alarms *
-**********
+******
+Alarms
+******
 
 Each channel or limit may have an associated alarm file, containing a
 boolean value. 1 means than an alarm condition exists, 0 means no alarm.
@@ -645,67 +888,67 @@ Usually a given chip will either use channel-related alarms, or
 limit-related alarms, not both. The driver should just reflect the hardware
 implementation.
 
-in[0-*]_alarm
-curr[1-*]_alarm
-power[1-*]_alarm
-fan[1-*]_alarm
-temp[1-*]_alarm
-		Channel alarm
-		0: no alarm
-		1: alarm
-		RO
-
-OR
-
-in[0-*]_min_alarm
-in[0-*]_max_alarm
-in[0-*]_lcrit_alarm
-in[0-*]_crit_alarm
-curr[1-*]_min_alarm
-curr[1-*]_max_alarm
-curr[1-*]_lcrit_alarm
-curr[1-*]_crit_alarm
-power[1-*]_cap_alarm
-power[1-*]_max_alarm
-power[1-*]_crit_alarm
-fan[1-*]_min_alarm
-fan[1-*]_max_alarm
-temp[1-*]_min_alarm
-temp[1-*]_max_alarm
-temp[1-*]_lcrit_alarm
-temp[1-*]_crit_alarm
-temp[1-*]_emergency_alarm
-		Limit alarm
-		0: no alarm
-		1: alarm
-		RO
++-------------------------------+-----------------------+
+| **`in[0-*]_alarm`,		| Channel alarm		|
+| `curr[1-*]_alarm`,		|			|
+| `power[1-*]_alarm`,		|   - 0: no alarm	|
+| `fan[1-*]_alarm`,		|   - 1: alarm		|
+| `temp[1-*]_alarm`**		|			|
+|				|   RO			|
++-------------------------------+-----------------------+
+
+**OR**
+
++-------------------------------+-----------------------+
+| **`in[0-*]_min_alarm`,	| Limit alarm		|
+| `in[0-*]_max_alarm`,		|			|
+| `in[0-*]_lcrit_alarm`,	|   - 0: no alarm	|
+| `in[0-*]_crit_alarm`,		|   - 1: alarm		|
+| `curr[1-*]_min_alarm`,	|			|
+| `curr[1-*]_max_alarm`,	| RO			|
+| `curr[1-*]_lcrit_alarm`,	|			|
+| `curr[1-*]_crit_alarm`,	|			|
+| `power[1-*]_cap_alarm`,	|			|
+| `power[1-*]_max_alarm`,	|			|
+| `power[1-*]_crit_alarm`,	|			|
+| `fan[1-*]_min_alarm`,		|			|
+| `fan[1-*]_max_alarm`,		|			|
+| `temp[1-*]_min_alarm`,	|			|
+| `temp[1-*]_max_alarm`,	|			|
+| `temp[1-*]_lcrit_alarm`,	|			|
+| `temp[1-*]_crit_alarm`,	|			|
+| `temp[1-*]_emergency_alarm`**	|			|
++-------------------------------+-----------------------+
 
 Each input channel may have an associated fault file. This can be used
 to notify open diodes, unconnected fans etc. where the hardware
 supports it. When this boolean has value 1, the measurement for that
 channel should not be trusted.
 
-fan[1-*]_fault
-temp[1-*]_fault
+`fan[1-*]_fault` / `temp[1-*]_fault`
 		Input fault condition
-		0: no fault occurred
-		1: fault condition
+
+		- 0: no fault occurred
+		- 1: fault condition
+
 		RO
 
 Some chips also offer the possibility to get beeped when an alarm occurs:
 
-beep_enable	Master beep enable
-		0: no beeps
-		1: beeps
+`beep_enable`
+		Master beep enable
+
+		- 0: no beeps
+		- 1: beeps
+
 		RW
 
-in[0-*]_beep
-curr[1-*]_beep
-fan[1-*]_beep
-temp[1-*]_beep
+`in[0-*]_beep`, `curr[1-*]_beep`, `fan[1-*]_beep`, `temp[1-*]_beep`,
 		Channel beep
-		0: disable
-		1: enable
+
+		- 0: disable
+		- 1: enable
+
 		RW
 
 In theory, a chip could provide per-limit beep masking, but no such chip
@@ -715,56 +958,90 @@ Old drivers provided a different, non-standard interface to alarms and
 beeps. These interface files are deprecated, but will be kept around
 for compatibility reasons:
 
-alarms		Alarm bitmask.
+`alarms`
+		Alarm bitmask.
+
 		RO
+
 		Integer representation of one to four bytes.
+
 		A '1' bit means an alarm.
+
 		Chips should be programmed for 'comparator' mode so that
 		the alarm will 'come back' after you read the register
 		if it is still valid.
+
 		Generally a direct representation of a chip's internal
 		alarm registers; there is no standard for the position
 		of individual bits. For this reason, the use of this
 		interface file for new drivers is discouraged. Use
-		individual *_alarm and *_fault files instead.
+		`individual *_alarm` and `*_fault` files instead.
 		Bits are defined in kernel/include/sensors.h.
 
-beep_mask	Bitmask for beep.
+`beep_mask`
+		Bitmask for beep.
 		Same format as 'alarms' with the same bit locations,
 		use discouraged for the same reason. Use individual
-		*_beep files instead.
+		`*_beep` files instead.
 		RW
 
 
-***********************
-* Intrusion detection *
-***********************
+*******************
+Intrusion detection
+*******************
 
-intrusion[0-*]_alarm
+`intrusion[0-*]_alarm`
 		Chassis intrusion detection
-		0: OK
-		1: intrusion detected
+
+		- 0: OK
+		- 1: intrusion detected
+
 		RW
+
 		Contrary to regular alarm flags which clear themselves
 		automatically when read, this one sticks until cleared by
 		the user. This is done by writing 0 to the file. Writing
 		other values is unsupported.
 
-intrusion[0-*]_beep
+`intrusion[0-*]_beep`
 		Chassis intrusion beep
+
 		0: disable
 		1: enable
+
 		RW
 
+****************************
+Average sample configuration
+****************************
+
+Devices allowing for reading {in,power,curr,temp}_average values may export
+attributes for controlling number of samples used to compute average.
+
++--------------+---------------------------------------------------------------+
+| samples      | Sets number of average samples for all types of measurements. |
+|	       |							       |
+|	       | RW							       |
++--------------+---------------------------------------------------------------+
+| in_samples   | Sets number of average samples for specific type of	       |
+| power_samples| measurements.						       |
+| curr_samples |							       |
+| temp_samples | Note that on some devices it won't be possible to set all of  |
+|	       | them to different values so changing one might also change    |
+|	       | some others.						       |
+|	       |							       |
+|	       | RW							       |
++--------------+---------------------------------------------------------------+
 
 sysfs attribute writes interpretation
 -------------------------------------
 
 hwmon sysfs attributes always contain numbers, so the first thing to do is to
 convert the input to a number, there are 2 ways todo this depending whether
-the number can be negative or not:
-unsigned long u = simple_strtoul(buf, NULL, 10);
-long s = simple_strtol(buf, NULL, 10);
+the number can be negative or not::
+
+	unsigned long u = simple_strtoul(buf, NULL, 10);
+	long s = simple_strtol(buf, NULL, 10);
 
 With buf being the buffer with the user input being passed by the kernel.
 Notice that we do not use the second argument of strto[u]l, and thus cannot
@@ -789,13 +1066,13 @@ limits using clamp_val(value, min_limit, max_limit). If it is not continuous
 like for example a tempX_type, then when an invalid value is written,
 -EINVAL should be returned.
 
-Example1, temp1_max, register is a signed 8 bit value (-128 - 127 degrees):
+Example1, temp1_max, register is a signed 8 bit value (-128 - 127 degrees)::
 
 	long v = simple_strtol(buf, NULL, 10) / 1000;
 	v = clamp_val(v, -128, 127);
 	/* write v to register */
 
-Example2, fan divider setting, valid values 2, 4 and 8:
+Example2, fan divider setting, valid values 2, 4 and 8::
 
 	unsigned long v = simple_strtoul(buf, NULL, 10);
 
diff --git a/Documentation/hwmon/tc654 b/Documentation/hwmon/tc654.rst
index 47636a8077b4..ce546ee6dfed 100644
--- a/Documentation/hwmon/tc654
+++ b/Documentation/hwmon/tc654.rst
@@ -2,13 +2,16 @@ Kernel driver tc654
 ===================
 
 Supported chips:
+
   * Microchip TC654 and TC655
+
     Prefix: 'tc654'
-    Datasheet: http://ww1.microchip.com/downloads/en/DeviceDoc/20001734C.pdf
+    Datasheet: http://ww1.m
+    icrochip.com/downloads/en/DeviceDoc/20001734C.pdf
 
 Authors:
-        Chris Packham <chris.packham@alliedtelesis.co.nz>
-        Masahiko Iwamoto <iwamoto@allied-telesis.co.jp>
+      - Chris Packham <chris.packham@alliedtelesis.co.nz>
+      - Masahiko Iwamoto <iwamoto@allied-telesis.co.jp>
 
 Description
 -----------
diff --git a/Documentation/hwmon/tc74 b/Documentation/hwmon/tc74.rst
index 43027aad5f8e..f1764211c129 100644
--- a/Documentation/hwmon/tc74
+++ b/Documentation/hwmon/tc74.rst
@@ -2,8 +2,11 @@ Kernel driver tc74
 ====================
 
 Supported chips:
+
    * Microchip TC74
+
      Prefix: 'tc74'
+
      Datasheet: Publicly available at Microchip website.
 
 Description
diff --git a/Documentation/hwmon/thmc50 b/Documentation/hwmon/thmc50.rst
index 8a7772ade8d0..cfff3885287d 100644
--- a/Documentation/hwmon/thmc50
+++ b/Documentation/hwmon/thmc50.rst
@@ -2,30 +2,41 @@ Kernel driver thmc50
 =====================
 
 Supported chips:
+
   * Analog Devices ADM1022
+
     Prefix: 'adm1022'
+
     Addresses scanned: I2C 0x2c - 0x2e
+
     Datasheet: http://www.analog.com/en/prod/0,2877,ADM1022,00.html
+
   * Texas Instruments THMC50
+
     Prefix: 'thmc50'
+
     Addresses scanned: I2C 0x2c - 0x2e
-    Datasheet: http://www.ti.com/ 
+
+    Datasheet: http://www.ti.com/
+
 
 Author: Krzysztof Helt <krzysztof.h1@wp.pl>
 
 This driver was derived from the 2.4 kernel thmc50.c source file.
 
 Credits:
+
   thmc50.c (2.4 kernel):
-	Frodo Looijaard <frodol@dds.nl>
-	Philip Edelbrock <phil@netroedge.com>
+
+	- Frodo Looijaard <frodol@dds.nl>
+	- Philip Edelbrock <phil@netroedge.com>
 
 Module Parameters
 -----------------
 
 * adm1022_temp3: short array
-  List of adapter,address pairs to force chips into ADM1022 mode with
-  second remote temperature. This does not work for original THMC50 chips.
+    List of adapter,address pairs to force chips into ADM1022 mode with
+    second remote temperature. This does not work for original THMC50 chips.
 
 Description
 -----------
@@ -59,16 +70,20 @@ Driver Features
 
 The driver provides up to three temperatures:
 
-temp1		-- internal
-temp2		-- remote
-temp3		-- 2nd remote only for ADM1022
+temp1
+	- internal
+temp2
+	- remote
+temp3
+	- 2nd remote only for ADM1022
 
-pwm1		-- fan speed (0 = stop, 255 = full)
-pwm1_mode	-- always 0 (DC mode)
+pwm1
+	- fan speed (0 = stop, 255 = full)
+pwm1_mode
+	- always 0 (DC mode)
 
 The value of 0 for pwm1 also forces FAN_OFF signal from the chip,
 so it stops fans even if the value 0 into the ANALOG_OUT register does not.
 
 The driver was tested on Compaq AP550 with two ADM1022 chips (one works
 in the temp3 mode), five temperature readings and two fans.
-
diff --git a/Documentation/hwmon/tmp102 b/Documentation/hwmon/tmp102.rst
index 8454a7763122..b1f585531a88 100644
--- a/Documentation/hwmon/tmp102
+++ b/Documentation/hwmon/tmp102.rst
@@ -2,12 +2,17 @@ Kernel driver tmp102
 ====================
 
 Supported chips:
+
   * Texas Instruments TMP102
+
     Prefix: 'tmp102'
+
     Addresses scanned: none
+
     Datasheet: http://focus.ti.com/docs/prod/folders/print/tmp102.html
 
 Author:
+
 	Steven King <sfking@fdwdc.com>
 
 Description
@@ -23,4 +28,4 @@ The TMP102 has a programmable update rate that can select between 8, 4, 1, and
 0.5 Hz. (Currently the driver only supports the default of 4 Hz).
 
 The driver provides the common sysfs-interface for temperatures (see
-Documentation/hwmon/sysfs-interface under Temperatures).
+Documentation/hwmon/sysfs-interface.rst under Temperatures).
diff --git a/Documentation/hwmon/tmp103 b/Documentation/hwmon/tmp103.rst
index ec00a15645ba..15d25806d585 100644
--- a/Documentation/hwmon/tmp103
+++ b/Documentation/hwmon/tmp103.rst
@@ -2,12 +2,17 @@ Kernel driver tmp103
 ====================
 
 Supported chips:
+
   * Texas Instruments TMP103
+
     Prefix: 'tmp103'
+
     Addresses scanned: none
+
     Product info and datasheet: http://www.ti.com/product/tmp103
 
 Author:
+
 	Heiko Schocher <hs@denx.de>
 
 Description
@@ -22,7 +27,7 @@ Resolution: 8 Bits
 Accuracy: ±1°C Typ (–10°C to +100°C)
 
 The driver provides the common sysfs-interface for temperatures (see
-Documentation/hwmon/sysfs-interface under Temperatures).
+Documentation/hwmon/sysfs-interface.rst under Temperatures).
 
 Please refer how to instantiate this driver:
 Documentation/i2c/instantiating-devices
diff --git a/Documentation/hwmon/tmp108 b/Documentation/hwmon/tmp108.rst
index 25802df23010..5f4266a16cb2 100644
--- a/Documentation/hwmon/tmp108
+++ b/Documentation/hwmon/tmp108.rst
@@ -2,12 +2,17 @@ Kernel driver tmp108
 ====================
 
 Supported chips:
+
   * Texas Instruments TMP108
+
     Prefix: 'tmp108'
+
     Addresses scanned: none
+
     Datasheet: http://www.ti.com/product/tmp108
 
 Author:
+
 	John Muir <john@jmuir.com>
 
 Description
@@ -33,4 +38,4 @@ and then the device is shut down automatically. (This driver only supports
 continuous mode.)
 
 The driver provides the common sysfs-interface for temperatures (see
-Documentation/hwmon/sysfs-interface under Temperatures).
+Documentation/hwmon/sysfs-interface.rst under Temperatures).
diff --git a/Documentation/hwmon/tmp401 b/Documentation/hwmon/tmp401.rst
index 2d9ca42213cf..6a05a0719bc7 100644
--- a/Documentation/hwmon/tmp401
+++ b/Documentation/hwmon/tmp401.rst
@@ -2,33 +2,59 @@ Kernel driver tmp401
 ====================
 
 Supported chips:
+
   * Texas Instruments TMP401
+
     Prefix: 'tmp401'
+
     Addresses scanned: I2C 0x4c
+
     Datasheet: http://focus.ti.com/docs/prod/folders/print/tmp401.html
+
   * Texas Instruments TMP411
+
     Prefix: 'tmp411'
+
     Addresses scanned: I2C 0x4c, 0x4d, 0x4e
+
     Datasheet: http://focus.ti.com/docs/prod/folders/print/tmp411.html
+
   * Texas Instruments TMP431
+
     Prefix: 'tmp431'
+
     Addresses scanned: I2C 0x4c, 0x4d
+
     Datasheet: http://focus.ti.com/docs/prod/folders/print/tmp431.html
+
   * Texas Instruments TMP432
+
     Prefix: 'tmp432'
+
     Addresses scanned: I2C 0x4c, 0x4d
+
     Datasheet: http://focus.ti.com/docs/prod/folders/print/tmp432.html
+
   * Texas Instruments TMP435
+
     Prefix: 'tmp435'
+
     Addresses scanned: I2C 0x48 - 0x4f
+
     Datasheet: http://focus.ti.com/docs/prod/folders/print/tmp435.html
+
   * Texas Instruments TMP461
+
     Prefix: 'tmp461'
+
     Datasheet: http://www.ti.com/product/tmp461
 
+
+
 Authors:
-         Hans de Goede <hdegoede@redhat.com>
-	 Andre Prendel <andre.prendel@gmx.de>
+
+	- Hans de Goede <hdegoede@redhat.com>
+	- Andre Prendel <andre.prendel@gmx.de>
 
 Description
 -----------
@@ -42,7 +68,7 @@ supported by the driver so far, so using the default resolution of 0.5
 degree).
 
 The driver provides the common sysfs-interface for temperatures (see
-Documentation/hwmon/sysfs-interface under Temperatures).
+Documentation/hwmon/sysfs-interface.rst under Temperatures).
 
 The TMP411 and TMP431 chips are compatible with TMP401. TMP411 provides
 some additional features.
diff --git a/Documentation/hwmon/tmp421 b/Documentation/hwmon/tmp421.rst
index 9e6fe5549ca1..1ba926a3605c 100644
--- a/Documentation/hwmon/tmp421
+++ b/Documentation/hwmon/tmp421.rst
@@ -2,28 +2,49 @@ Kernel driver tmp421
 ====================
 
 Supported chips:
+
   * Texas Instruments TMP421
+
     Prefix: 'tmp421'
+
     Addresses scanned: I2C 0x2a, 0x4c, 0x4d, 0x4e and 0x4f
+
     Datasheet: http://focus.ti.com/docs/prod/folders/print/tmp421.html
+
   * Texas Instruments TMP422
+
     Prefix: 'tmp422'
+
     Addresses scanned: I2C 0x4c, 0x4d, 0x4e and 0x4f
+
     Datasheet: http://focus.ti.com/docs/prod/folders/print/tmp421.html
+
   * Texas Instruments TMP423
+
     Prefix: 'tmp423'
+
     Addresses scanned: I2C 0x4c and 0x4d
+
     Datasheet: http://focus.ti.com/docs/prod/folders/print/tmp421.html
+
   * Texas Instruments TMP441
+
     Prefix: 'tmp441'
+
     Addresses scanned: I2C 0x2a, 0x4c, 0x4d, 0x4e and 0x4f
+
     Datasheet: http://www.ti.com/product/tmp441
+
   * Texas Instruments TMP442
+
     Prefix: 'tmp442'
+
     Addresses scanned: I2C 0x4c and 0x4d
+
     Datasheet: http://www.ti.com/product/tmp442
 
 Authors:
+
 	Andre Prendel <andre.prendel@gmx.de>
 
 Description
@@ -40,5 +61,6 @@ for both the local and remote channels is 0.0625 degree C.
 The chips support only temperature measurement. The driver exports
 the temperature values via the following sysfs files:
 
-temp[1-4]_input
-temp[2-4]_fault
+**temp[1-4]_input**
+
+**temp[2-4]_fault**
diff --git a/Documentation/hwmon/tps40422 b/Documentation/hwmon/tps40422.rst
index 24bb0688d515..b691e30479dd 100644
--- a/Documentation/hwmon/tps40422
+++ b/Documentation/hwmon/tps40422.rst
@@ -2,9 +2,13 @@ Kernel driver tps40422
 ======================
 
 Supported chips:
+
   * TI TPS40422
+
     Prefix: 'tps40422'
+
     Addresses scanned: -
+
     Datasheet: http://www.ti.com/lit/gpn/tps40422
 
 Author: Zhu Laiwen <richard.zhu@nsn.com>
@@ -17,7 +21,7 @@ This driver supports TI TPS40422 Dual-Output or Two-Phase Synchronous Buck
 Controller with PMBus
 
 The driver is a client driver to the core PMBus driver.
-Please see Documentation/hwmon/pmbus for details on PMBus client drivers.
+Please see Documentation/hwmon/pmbus.rst for details on PMBus client drivers.
 
 
 Usage Notes
@@ -39,6 +43,7 @@ Sysfs entries
 
 The following attributes are supported.
 
+======================= =======================================================
 in[1-2]_label		"vout[1-2]"
 in[1-2]_input		Measured voltage. From READ_VOUT register.
 in[1-2]_alarm		voltage alarm.
@@ -46,19 +51,23 @@ in[1-2]_alarm		voltage alarm.
 curr[1-2]_input		Measured current. From READ_IOUT register.
 curr[1-2]_label		"iout[1-2]"
 curr1_max		Maximum current. From IOUT_OC_WARN_LIMIT register.
-curr1_crit		Critical maximum current. From IOUT_OC_FAULT_LIMIT register.
+curr1_crit		Critical maximum current. From IOUT_OC_FAULT_LIMIT
+			register.
 curr1_max_alarm		Current high alarm. From IOUT_OC_WARN_LIMIT status.
 curr1_crit_alarm	Current critical high alarm. From IOUT_OC_FAULT status.
 curr2_alarm		Current high alarm. From IOUT_OC_WARNING status.
 
-temp1_input		Measured temperature. From READ_TEMPERATURE_2 register on page 0.
+temp1_input		Measured temperature. From READ_TEMPERATURE_2 register
+			on page 0.
 temp1_max		Maximum temperature. From OT_WARN_LIMIT register.
 temp1_crit		Critical high temperature. From OT_FAULT_LIMIT register.
 temp1_max_alarm		Chip temperature high alarm. Set by comparing
-			READ_TEMPERATURE_2 on page 0 with OT_WARN_LIMIT if TEMP_OT_WARNING
-			status is set.
+			READ_TEMPERATURE_2 on page 0 with OT_WARN_LIMIT if
+			TEMP_OT_WARNING status is set.
 temp1_crit_alarm	Chip temperature critical high alarm. Set by comparing
-			READ_TEMPERATURE_2 on page 0 with OT_FAULT_LIMIT if TEMP_OT_FAULT
-			status is set.
-temp2_input		Measured temperature. From READ_TEMPERATURE_2 register on page 1.
+			READ_TEMPERATURE_2 on page 0 with OT_FAULT_LIMIT if
+			TEMP_OT_FAULT status is set.
+temp2_input		Measured temperature. From READ_TEMPERATURE_2 register
+			on page 1.
 temp2_alarm		Chip temperature alarm on page 1.
+======================= =======================================================
diff --git a/Documentation/hwmon/twl4030-madc-hwmon b/Documentation/hwmon/twl4030-madc-hwmon.rst
index c3a3a5be10ad..22c885383b11 100644
--- a/Documentation/hwmon/twl4030-madc-hwmon
+++ b/Documentation/hwmon/twl4030-madc-hwmon.rst
@@ -1,8 +1,10 @@
 Kernel driver twl4030-madc
-=========================
+==========================
 
 Supported chips:
+
 	* Texas Instruments TWL4030
+
 	Prefix: 'twl4030-madc'
 
 
@@ -19,8 +21,9 @@ channels which can be used in different modes.
 
 See this table for the meaning of the different channels
 
+======= ==========================================================
 Channel Signal
-------------------------------------------
+======= ==========================================================
 0	Battery type(BTYPE)
 1	BCI: Battery temperature (BTEMP)
 2	GP analog input
@@ -37,6 +40,7 @@ Channel Signal
 13	Reserved
 14	Reserved
 15	VRUSB Supply/Speaker left/Speaker right polarization level
+======= ==========================================================
 
 
 The Sysfs nodes will represent the voltage in the units of mV,
diff --git a/Documentation/hwmon/ucd9000 b/Documentation/hwmon/ucd9000.rst
index 262e713e60ff..ebc4f2b3bfea 100644
--- a/Documentation/hwmon/ucd9000
+++ b/Documentation/hwmon/ucd9000.rst
@@ -2,15 +2,20 @@ Kernel driver ucd9000
 =====================
 
 Supported chips:
+
   * TI UCD90120, UCD90124, UCD90160, UCD9090, and UCD90910
+
     Prefixes: 'ucd90120', 'ucd90124', 'ucd90160', 'ucd9090', 'ucd90910'
+
     Addresses scanned: -
+
     Datasheets:
-	http://focus.ti.com/lit/ds/symlink/ucd90120.pdf
-	http://focus.ti.com/lit/ds/symlink/ucd90124.pdf
-	http://focus.ti.com/lit/ds/symlink/ucd90160.pdf
-	http://focus.ti.com/lit/ds/symlink/ucd9090.pdf
-	http://focus.ti.com/lit/ds/symlink/ucd90910.pdf
+
+	- http://focus.ti.com/lit/ds/symlink/ucd90120.pdf
+	- http://focus.ti.com/lit/ds/symlink/ucd90124.pdf
+	- http://focus.ti.com/lit/ds/symlink/ucd90160.pdf
+	- http://focus.ti.com/lit/ds/symlink/ucd9090.pdf
+	- http://focus.ti.com/lit/ds/symlink/ucd90910.pdf
 
 Author: Guenter Roeck <linux@roeck-us.net>
 
@@ -52,7 +57,7 @@ system-health monitor. The device integrates a 12-bit ADC for monitoring up to
 13 power-supply voltage, current, or temperature inputs.
 
 This driver is a client driver to the core PMBus driver. Please see
-Documentation/hwmon/pmbus for details on PMBus client drivers.
+Documentation/hwmon/pmbus.rst for details on PMBus client drivers.
 
 
 Usage Notes
@@ -67,7 +72,7 @@ Platform data support
 ---------------------
 
 The driver supports standard PMBus driver platform data. Please see
-Documentation/hwmon/pmbus for details.
+Documentation/hwmon/pmbus.rst for details.
 
 
 Sysfs entries
@@ -76,23 +81,28 @@ Sysfs entries
 The following attributes are supported. Limits are read-write; all other
 attributes are read-only.
 
+======================= ========================================================
 in[1-12]_label		"vout[1-12]".
 in[1-12]_input		Measured voltage. From READ_VOUT register.
 in[1-12]_min		Minimum Voltage. From VOUT_UV_WARN_LIMIT register.
 in[1-12]_max		Maximum voltage. From VOUT_OV_WARN_LIMIT register.
 in[1-12]_lcrit		Critical minimum Voltage. VOUT_UV_FAULT_LIMIT register.
-in[1-12]_crit		Critical maximum voltage. From VOUT_OV_FAULT_LIMIT register.
+in[1-12]_crit		Critical maximum voltage. From VOUT_OV_FAULT_LIMIT
+			register.
 in[1-12]_min_alarm	Voltage low alarm. From VOLTAGE_UV_WARNING status.
 in[1-12]_max_alarm	Voltage high alarm. From VOLTAGE_OV_WARNING status.
-in[1-12]_lcrit_alarm	Voltage critical low alarm. From VOLTAGE_UV_FAULT status.
-in[1-12]_crit_alarm	Voltage critical high alarm. From VOLTAGE_OV_FAULT status.
+in[1-12]_lcrit_alarm	Voltage critical low alarm. From VOLTAGE_UV_FAULT
+			status.
+in[1-12]_crit_alarm	Voltage critical high alarm. From VOLTAGE_OV_FAULT
+			status.
 
 curr[1-12]_label	"iout[1-12]".
 curr[1-12]_input	Measured current. From READ_IOUT register.
 curr[1-12]_max		Maximum current. From IOUT_OC_WARN_LIMIT register.
-curr[1-12]_lcrit	Critical minimum output current. From IOUT_UC_FAULT_LIMIT
+curr[1-12]_lcrit	Critical minimum output current. From
+			IOUT_UC_FAULT_LIMIT register.
+curr[1-12]_crit		Critical maximum current. From IOUT_OC_FAULT_LIMIT
 			register.
-curr[1-12]_crit		Critical maximum current. From IOUT_OC_FAULT_LIMIT register.
 curr[1-12]_max_alarm	Current high alarm. From IOUT_OC_WARNING status.
 curr[1-12]_crit_alarm	Current critical high alarm. From IOUT_OC_FAULT status.
 
@@ -116,3 +126,4 @@ fan[1-4]_fault		Fan fault.
 			created only for enabled fans.
 			Note that even though UCD90910 supports up to 10 fans,
 			only up to four fans are currently supported.
+======================= ========================================================
diff --git a/Documentation/hwmon/ucd9200 b/Documentation/hwmon/ucd9200.rst
index 1e8060e631bd..b819dfd75f71 100644
--- a/Documentation/hwmon/ucd9200
+++ b/Documentation/hwmon/ucd9200.rst
@@ -2,18 +2,23 @@ Kernel driver ucd9200
 =====================
 
 Supported chips:
+
   * TI UCD9220, UCD9222, UCD9224, UCD9240, UCD9244, UCD9246, and UCD9248
+
     Prefixes: 'ucd9220', 'ucd9222', 'ucd9224', 'ucd9240', 'ucd9244', 'ucd9246',
-	'ucd9248'
+    'ucd9248'
+
     Addresses scanned: -
+
     Datasheets:
-	http://focus.ti.com/lit/ds/symlink/ucd9220.pdf
-	http://focus.ti.com/lit/ds/symlink/ucd9222.pdf
-	http://focus.ti.com/lit/ds/symlink/ucd9224.pdf
-	http://focus.ti.com/lit/ds/symlink/ucd9240.pdf
-	http://focus.ti.com/lit/ds/symlink/ucd9244.pdf
-	http://focus.ti.com/lit/ds/symlink/ucd9246.pdf
-	http://focus.ti.com/lit/ds/symlink/ucd9248.pdf
+
+	- http://focus.ti.com/lit/ds/symlink/ucd9220.pdf
+	- http://focus.ti.com/lit/ds/symlink/ucd9222.pdf
+	- http://focus.ti.com/lit/ds/symlink/ucd9224.pdf
+	- http://focus.ti.com/lit/ds/symlink/ucd9240.pdf
+	- http://focus.ti.com/lit/ds/symlink/ucd9244.pdf
+	- http://focus.ti.com/lit/ds/symlink/ucd9246.pdf
+	- http://focus.ti.com/lit/ds/symlink/ucd9248.pdf
 
 Author: Guenter Roeck <linux@roeck-us.net>
 
@@ -28,7 +33,7 @@ dedicated circuitry for DC/DC loop management with flash memory and a serial
 interface to support configuration, monitoring and management.
 
 This driver is a client driver to the core PMBus driver. Please see
-Documentation/hwmon/pmbus for details on PMBus client drivers.
+Documentation/hwmon/pmbus.rst for details on PMBus client drivers.
 
 
 Usage Notes
@@ -43,7 +48,7 @@ Platform data support
 ---------------------
 
 The driver supports standard PMBus driver platform data. Please see
-Documentation/hwmon/pmbus for details.
+Documentation/hwmon/pmbus.rst for details.
 
 
 Sysfs entries
@@ -52,12 +57,14 @@ Sysfs entries
 The following attributes are supported. Limits are read-write; all other
 attributes are read-only.
 
+======================= ========================================================
 in1_label		"vin".
 in1_input		Measured voltage. From READ_VIN register.
 in1_min			Minimum Voltage. From VIN_UV_WARN_LIMIT register.
 in1_max			Maximum voltage. From VIN_OV_WARN_LIMIT register.
 in1_lcrit		Critical minimum Voltage. VIN_UV_FAULT_LIMIT register.
-in1_crit		Critical maximum voltage. From VIN_OV_FAULT_LIMIT register.
+in1_crit		Critical maximum voltage. From VIN_OV_FAULT_LIMIT
+			register.
 in1_min_alarm		Voltage low alarm. From VIN_UV_WARNING status.
 in1_max_alarm		Voltage high alarm. From VIN_OV_WARNING status.
 in1_lcrit_alarm		Voltage critical low alarm. From VIN_UV_FAULT status.
@@ -68,11 +75,14 @@ in[2-5]_input		Measured voltage. From READ_VOUT register.
 in[2-5]_min		Minimum Voltage. From VOUT_UV_WARN_LIMIT register.
 in[2-5]_max		Maximum voltage. From VOUT_OV_WARN_LIMIT register.
 in[2-5]_lcrit		Critical minimum Voltage. VOUT_UV_FAULT_LIMIT register.
-in[2-5]_crit		Critical maximum voltage. From VOUT_OV_FAULT_LIMIT register.
+in[2-5]_crit		Critical maximum voltage. From VOUT_OV_FAULT_LIMIT
+			register.
 in[2-5]_min_alarm	Voltage low alarm. From VOLTAGE_UV_WARNING status.
 in[2-5]_max_alarm	Voltage high alarm. From VOLTAGE_OV_WARNING status.
-in[2-5]_lcrit_alarm	Voltage critical low alarm. From VOLTAGE_UV_FAULT status.
-in[2-5]_crit_alarm	Voltage critical high alarm. From VOLTAGE_OV_FAULT status.
+in[2-5]_lcrit_alarm	Voltage critical low alarm. From VOLTAGE_UV_FAULT
+			status.
+in[2-5]_crit_alarm	Voltage critical high alarm. From VOLTAGE_OV_FAULT
+			status.
 
 curr1_label		"iin".
 curr1_input		Measured current. From READ_IIN register.
@@ -80,9 +90,10 @@ curr1_input		Measured current. From READ_IIN register.
 curr[2-5]_label		"iout[1-4]".
 curr[2-5]_input		Measured current. From READ_IOUT register.
 curr[2-5]_max		Maximum current. From IOUT_OC_WARN_LIMIT register.
-curr[2-5]_lcrit		Critical minimum output current. From IOUT_UC_FAULT_LIMIT
+curr[2-5]_lcrit		Critical minimum output current. From
+			IOUT_UC_FAULT_LIMIT register.
+curr[2-5]_crit		Critical maximum current. From IOUT_OC_FAULT_LIMIT
 			register.
-curr[2-5]_crit		Critical maximum current. From IOUT_OC_FAULT_LIMIT register.
 curr[2-5]_max_alarm	Current high alarm. From IOUT_OC_WARNING status.
 curr[2-5]_crit_alarm	Current critical high alarm. From IOUT_OC_FAULT status.
 
@@ -97,7 +108,7 @@ power[2-5]_label	"pout[1-4]"
 			rails. See chip datasheets for details.
 
 temp[1-5]_input		Measured temperatures. From READ_TEMPERATURE_1 and
-		        READ_TEMPERATURE_2 registers.
+			READ_TEMPERATURE_2 registers.
 			temp1 is the chip internal temperature. temp[2-5] are
 			rail temperatures.  temp[2-5] attributes are only
 			created for enabled rails. See chip datasheets for
@@ -110,3 +121,4 @@ temp[1-5]_crit_alarm	Temperature critical high alarm.
 fan1_input		Fan RPM. ucd9240 only.
 fan1_alarm		Fan alarm. ucd9240 only.
 fan1_fault		Fan fault. ucd9240 only.
+======================= ========================================================
diff --git a/Documentation/hwmon/userspace-tools b/Documentation/hwmon/userspace-tools.rst
index 9865aeedc58f..bf3797c8e734 100644
--- a/Documentation/hwmon/userspace-tools
+++ b/Documentation/hwmon/userspace-tools.rst
@@ -1,3 +1,6 @@
+Userspace tools
+===============
+
 Introduction
 ------------
 
diff --git a/Documentation/hwmon/vexpress b/Documentation/hwmon/vexpress.rst
index 557d6d5ad90d..8c861c8151ac 100644
--- a/Documentation/hwmon/vexpress
+++ b/Documentation/hwmon/vexpress.rst
@@ -2,14 +2,21 @@ Kernel driver vexpress
 ======================
 
 Supported systems:
+
   * ARM Ltd. Versatile Express platform
+
     Prefix: 'vexpress'
+
     Datasheets:
+
       * "Hardware Description" sections of the Technical Reference Manuals
-        for the Versatile Express boards:
-        http://infocenter.arm.com/help/topic/com.arm.doc.subset.boards.express/index.html
+	for the Versatile Express boards:
+
+	- http://infocenter.arm.com/help/topic/com.arm.doc.subset.boards.express/index.html
+
       * Section "4.4.14. System Configuration registers" of the V2M-P1 TRM:
-        http://infocenter.arm.com/help/index.jsp?topic=/com.arm.doc.dui0447-/index.html
+
+	- http://infocenter.arm.com/help/index.jsp?topic=/com.arm.doc.dui0447-/index.html
 
 Author: Pawel Moll
 
diff --git a/Documentation/hwmon/via686a b/Documentation/hwmon/via686a.rst
index e5f90ab5c48d..a343c35df740 100644
--- a/Documentation/hwmon/via686a
+++ b/Documentation/hwmon/via686a.rst
@@ -2,29 +2,35 @@ Kernel driver via686a
 =====================
 
 Supported chips:
+
   * Via VT82C686A, VT82C686B  Southbridge Integrated Hardware Monitor
+
     Prefix: 'via686a'
+
     Addresses scanned: ISA in PCI-space encoded address
+
     Datasheet: On request through web form (http://www.via.com.tw/en/resources/download-center/)
 
 Authors:
-        Kyösti Mälkki <kmalkki@cc.hut.fi>,
-        Mark D. Studebaker <mdsxyz123@yahoo.com>
-        Bob Dougherty <bobd@stanford.edu>
-        (Some conversion-factor data were contributed by
-        Jonathan Teh Soon Yew <j.teh@iname.com>
-        and Alex van Kaam <darkside@chello.nl>.)
+	- Kyösti Mälkki <kmalkki@cc.hut.fi>,
+	- Mark D. Studebaker <mdsxyz123@yahoo.com>
+	- Bob Dougherty <bobd@stanford.edu>
+	- (Some conversion-factor data were contributed by
+	- Jonathan Teh Soon Yew <j.teh@iname.com>
+	- and Alex van Kaam <darkside@chello.nl>.)
 
 Module Parameters
 -----------------
 
+======================= =======================================================
 force_addr=0xaddr       Set the I/O base address. Useful for boards that
-                        don't set the address in the BIOS. Look for a BIOS
-                        upgrade before resorting to this. Does not do a
-                        PCI force; the via686a must still be present in lspci.
-                        Don't use this unless the driver complains that the
-                        base address is not set.
-                        Example: 'modprobe via686a force_addr=0x6000'
+			don't set the address in the BIOS. Look for a BIOS
+			upgrade before resorting to this. Does not do a
+			PCI force; the via686a must still be present in lspci.
+			Don't use this unless the driver complains that the
+			base address is not set.
+			Example: 'modprobe via686a force_addr=0x6000'
+======================= =======================================================
 
 Description
 -----------
diff --git a/Documentation/hwmon/vt1211 b/Documentation/hwmon/vt1211.rst
index 77fa633b97a8..ddbcde7dd642 100644
--- a/Documentation/hwmon/vt1211
+++ b/Documentation/hwmon/vt1211.rst
@@ -2,9 +2,13 @@ Kernel driver vt1211
 ====================
 
 Supported chips:
+
   * VIA VT1211
+
     Prefix: 'vt1211'
+
     Addresses scanned: none, address read from Super-I/O config space
+
     Datasheet: Provided by VIA upon request and under NDA
 
 Authors: Juerg Haefliger <juergh@gmail.com>
@@ -19,14 +23,17 @@ technical support.
 Module Parameters
 -----------------
 
-* uch_config: int	Override the BIOS default universal channel (UCH)
+
+* uch_config: int
+			Override the BIOS default universal channel (UCH)
 			configuration for channels 1-5.
 			Legal values are in the range of 0-31. Bit 0 maps to
 			UCH1, bit 1 maps to UCH2 and so on. Setting a bit to 1
 			enables the thermal input of that particular UCH and
 			setting a bit to 0 enables the voltage input.
 
-* int_mode: int		Override the BIOS default temperature interrupt mode.
+* int_mode: int
+			Override the BIOS default temperature interrupt mode.
 			The only possible value is 0 which forces interrupt
 			mode 0. In this mode, any pending interrupt is cleared
 			when the status register is read but is regenerated as
@@ -55,8 +62,9 @@ connected to the PWM outputs of the VT1211 :-().
 The following table shows the relationship between the vt1211 inputs and the
 sysfs nodes.
 
+=============== ============== =========== ================================
 Sensor          Voltage Mode   Temp Mode   Default Use (from the datasheet)
-------          ------------   ---------   --------------------------------
+=============== ============== =========== ================================
 Reading 1                      temp1       Intel thermal diode
 Reading 3                      temp2       Internal thermal diode
 UCH1/Reading2   in0            temp3       NTC type thermistor
@@ -65,6 +73,7 @@ UCH3            in2            temp5       VccP (processor core)
 UCH4            in3            temp6       +5V
 UCH5            in4            temp7       +12V
 +3.3V           in5                        Internal VCC (+3.3V)
+=============== ============== =========== ================================
 
 
 Voltage Monitoring
@@ -82,19 +91,22 @@ follows. And this is of course totally dependent on the actual board
 implementation :-) You will have to find documentation for your own
 motherboard and edit sensors.conf accordingly.
 
-                                      Expected
+============= ====== ====== ========= ============
+				      Expected
 Voltage       R1     R2     Divider   Raw Value
------------------------------------------------
+============= ====== ====== ========= ============
 +2.5V         2K     10K    1.2       2083 mV
-VccP          ---    ---    1.0       1400 mV (1)
+VccP          ---    ---    1.0       1400 mV [1]_
 +5V           14K    10K    2.4       2083 mV
 +12V          47K    10K    5.7       2105 mV
-+3.3V (int)   2K     3.4K   1.588     3300 mV (2)
++3.3V (int)   2K     3.4K   1.588     3300 mV [2]_
 +3.3V (ext)   6.8K   10K    1.68      1964 mV
+============= ====== ====== ========= ============
+
+.. [1] Depending on the CPU (1.4V is for a VIA C3 Nehemiah).
 
-(1) Depending on the CPU (1.4V is for a VIA C3 Nehemiah).
-(2) R1 and R2 for 3.3V (int) are internal to the VT1211 chip and the driver
-    performs the scaling and returns the properly scaled voltage value.
+.. [2] R1 and R2 for 3.3V (int) are internal to the VT1211 chip and the driver
+       performs the scaling and returns the properly scaled voltage value.
 
 Each measured voltage has an associated low and high limit which triggers an
 alarm when crossed.
@@ -124,35 +136,37 @@ compute temp1 (@-Offset)/Gain, (@*Gain)+Offset
 According to the VIA VT1211 BIOS porting guide, the following gain and offset
 values should be used:
 
+=============== ======== ===========
 Diode Type      Offset   Gain
-----------      ------   ----
+=============== ======== ===========
 Intel CPU       88.638   0.9528
-                65.000   0.9686   *)
+		65.000   0.9686 [3]_
 VIA C3 Ezra     83.869   0.9528
 VIA C3 Ezra-T   73.869   0.9528
+=============== ======== ===========
 
-*) This is the formula from the lm_sensors 2.10.0 sensors.conf file. I don't
-know where it comes from or how it was derived, it's just listed here for
-completeness.
+.. [3] This is the formula from the lm_sensors 2.10.0 sensors.conf file. I don't
+       know where it comes from or how it was derived, it's just listed here for
+       completeness.
 
 Temp3-temp7 support NTC thermistors. For these channels, the driver returns
 the voltages as seen at the individual pins of UCH1-UCH5. The voltage at the
 pin (Vpin) is formed by a voltage divider made of the thermistor (Rth) and a
-scaling resistor (Rs):
+scaling resistor (Rs)::
 
-Vpin = 2200 * Rth / (Rs + Rth)   (2200 is the ADC max limit of 2200 mV)
+  Vpin = 2200 * Rth / (Rs + Rth)   (2200 is the ADC max limit of 2200 mV)
 
 The equation for the thermistor is as follows (google it if you want to know
-more about it):
+more about it)::
 
-Rth = Ro * exp(B * (1 / T - 1 / To))   (To is 298.15K (25C) and Ro is the
-                                        nominal resistance at 25C)
+  Rth = Ro * exp(B * (1 / T - 1 / To))   (To is 298.15K (25C) and Ro is the
+					  nominal resistance at 25C)
 
 Mingling the above two equations and assuming Rs = Ro and B = 3435 yields the
-following formula for sensors.conf:
+following formula for sensors.conf::
 
-compute tempx 1 / (1 / 298.15 - (` (2200 / @ - 1)) / 3435) - 273.15,
-              2200 / (1 + (^ (3435 / 298.15 - 3435 / (273.15 + @))))
+  compute tempx 1 / (1 / 298.15 - (` (2200 / @ - 1)) / 3435) - 273.15,
+		2200 / (1 + (^ (3435 / 298.15 - 3435 / (273.15 + @))))
 
 
 Fan Speed Control
@@ -176,31 +190,37 @@ registers in the VT1211 and programming one set is sufficient (actually only
 the first set pwm1_auto_point[1-4]_temp is writable, the second set is
 read-only).
 
+========================== =========================================
 PWM Auto Point             PWM Output Duty-Cycle
-------------------------------------------------
+========================== =========================================
 pwm[1-2]_auto_point4_pwm   full speed duty-cycle (hard-wired to 255)
 pwm[1-2]_auto_point3_pwm   high speed duty-cycle
 pwm[1-2]_auto_point2_pwm   low speed duty-cycle
 pwm[1-2]_auto_point1_pwm   off duty-cycle (hard-wired to 0)
+========================== =========================================
 
+==========================  =================
 Temp Auto Point             Thermal Threshold
----------------------------------------------
+==========================  =================
 pwm[1-2]_auto_point4_temp   full speed temp
 pwm[1-2]_auto_point3_temp   high speed temp
 pwm[1-2]_auto_point2_temp   low speed temp
 pwm[1-2]_auto_point1_temp   off temp
+==========================  =================
 
 Long story short, the controller implements the following algorithm to set the
 PWM output duty-cycle based on the input temperature:
 
-Thermal Threshold             Output Duty-Cycle
-                    (Rising Temp)           (Falling Temp)
-----------------------------------------------------------
-                    full speed duty-cycle   full speed duty-cycle
+=================== ======================= ========================
+Thermal Threshold   Output Duty-Cycle       Output Duty-Cycle
+		    (Rising Temp)           (Falling Temp)
+=================== ======================= ========================
+-                   full speed duty-cycle   full speed duty-cycle
 full speed temp
-                    high speed duty-cycle   full speed duty-cycle
+-		    high speed duty-cycle   full speed duty-cycle
 high speed temp
-                    low speed duty-cycle    high speed duty-cycle
+-		    low speed duty-cycle    high speed duty-cycle
 low speed temp
-                    off duty-cycle          low speed duty-cycle
+-		    off duty-cycle          low speed duty-cycle
 off temp
+=================== ======================= ========================
diff --git a/Documentation/hwmon/w83627ehf b/Documentation/hwmon/w83627ehf.rst
index 735c42a85ead..74d19ef11e1f 100644
--- a/Documentation/hwmon/w83627ehf
+++ b/Documentation/hwmon/w83627ehf.rst
@@ -2,45 +2,79 @@ Kernel driver w83627ehf
 =======================
 
 Supported chips:
+
   * Winbond W83627EHF/EHG (ISA access ONLY)
+
     Prefix: 'w83627ehf'
+
     Addresses scanned: ISA address retrieved from Super I/O registers
+
     Datasheet: not available
+
   * Winbond W83627DHG
+
     Prefix: 'w83627dhg'
+
     Addresses scanned: ISA address retrieved from Super I/O registers
+
     Datasheet: not available
+
   * Winbond W83627DHG-P
+
     Prefix: 'w83627dhg'
+
     Addresses scanned: ISA address retrieved from Super I/O registers
+
     Datasheet: not available
+
   * Winbond W83627UHG
+
     Prefix: 'w83627uhg'
+
     Addresses scanned: ISA address retrieved from Super I/O registers
+
     Datasheet: available from www.nuvoton.com
+
   * Winbond W83667HG
+
     Prefix: 'w83667hg'
+
     Addresses scanned: ISA address retrieved from Super I/O registers
+
     Datasheet: not available
+
   * Winbond W83667HG-B
+
     Prefix: 'w83667hg'
+
     Addresses scanned: ISA address retrieved from Super I/O registers
+
     Datasheet: Available from Nuvoton upon request
+
   * Nuvoton NCT6775F/W83667HG-I
+
     Prefix: 'nct6775'
+
     Addresses scanned: ISA address retrieved from Super I/O registers
+
     Datasheet: Available from Nuvoton upon request
+
   * Nuvoton NCT6776F
+
     Prefix: 'nct6776'
+
     Addresses scanned: ISA address retrieved from Super I/O registers
+
     Datasheet: Available from Nuvoton upon request
 
+
 Authors:
-        Jean Delvare <jdelvare@suse.de>
-        Yuan Mu (Winbond)
-        Rudolf Marek <r.marek@assembler.cz>
-        David Hubbard <david.c.hubbard@gmail.com>
-        Gong Jun <JGong@nuvoton.com>
+
+	- Jean Delvare <jdelvare@suse.de>
+	- Yuan Mu (Winbond)
+	- Rudolf Marek <r.marek@assembler.cz>
+	- David Hubbard <david.c.hubbard@gmail.com>
+	- Gong Jun <JGong@nuvoton.com>
 
 Description
 -----------
@@ -85,25 +119,30 @@ predefined temperature range. If the temperature goes out of range, fan
 is driven slower/faster to reach the predefined range again.
 
 The mode works for fan1-fan4. Mapping of temperatures to pwm outputs is as
-follows:
+follows::
 
-temp1 -> pwm1
-temp2 -> pwm2
-temp3 -> pwm3 (not on 627UHG)
-prog  -> pwm4 (not on 667HG and 667HG-B; the programmable setting is not
-	       supported by the driver)
+  temp1 -> pwm1
+  temp2 -> pwm2
+  temp3 -> pwm3 (not on 627UHG)
+  prog  -> pwm4 (not on 667HG and 667HG-B; the programmable setting is not
+		 supported by the driver)
 
 /sys files
 ----------
 
-name - this is a standard hwmon device entry, it contains the name of
-       the device (see the prefix in the list of supported devices at
-       the top of this file)
+name
+	this is a standard hwmon device entry, it contains the name of
+	the device (see the prefix in the list of supported devices at
+	the top of this file)
+
+pwm[1-4]
+	this file stores PWM duty cycle or DC value (fan speed) in range:
 
-pwm[1-4] - this file stores PWM duty cycle or DC value (fan speed) in range:
 	   0 (stop) to 255 (full)
 
-pwm[1-4]_enable - this file controls mode of fan/temperature control:
+pwm[1-4]_enable
+	this file controls mode of fan/temperature control:
+
 	* 1 Manual mode, write to pwm file any value 0-255 (full speed)
 	* 2 "Thermal Cruise" mode
 	* 3 "Fan Speed Cruise" mode
@@ -121,33 +160,43 @@ pwm[1-4]_enable - this file controls mode of fan/temperature control:
 	returned when reading pwm attributes is unrelated to SmartFan IV
 	operation.
 
-pwm[1-4]_mode - controls if output is PWM or DC level
-        * 0 DC output (0 - 12v)
-        * 1 PWM output
+pwm[1-4]_mode
+	controls if output is PWM or DC level
+
+	* 0 DC output (0 - 12v)
+	* 1 PWM output
 
 Thermal Cruise mode
 -------------------
 
 If the temperature is in the range defined by:
 
-pwm[1-4]_target    - set target temperature, unit millidegree Celsius
-		     (range 0 - 127000)
-pwm[1-4]_tolerance - tolerance, unit millidegree Celsius (range 0 - 15000)
+pwm[1-4]_target
+		   set target temperature, unit millidegree Celsius
+		   (range 0 - 127000)
+pwm[1-4]_tolerance
+		   tolerance, unit millidegree Celsius (range 0 - 15000)
 
 there are no changes to fan speed. Once the temperature leaves the interval,
 fan speed increases (temp is higher) or decreases if lower than desired.
 There are defined steps and times, but not exported by the driver yet.
 
-pwm[1-4]_min_output - minimum fan speed (range 1 - 255), when the temperature
-                      is below defined range.
-pwm[1-4]_stop_time  - how many milliseconds [ms] must elapse to switch
-                      corresponding fan off. (when the temperature was below
-                      defined range).
-pwm[1-4]_start_output-minimum fan speed (range 1 - 255) when spinning up
-pwm[1-4]_step_output- rate of fan speed change (1 - 255)
-pwm[1-4]_stop_output- minimum fan speed (range 1 - 255) when spinning down
-pwm[1-4]_max_output - maximum fan speed (range 1 - 255), when the temperature
-                      is above defined range.
+pwm[1-4]_min_output
+		   minimum fan speed (range 1 - 255), when the temperature
+		   is below defined range.
+pwm[1-4]_stop_time
+		   how many milliseconds [ms] must elapse to switch
+		   corresponding fan off. (when the temperature was below
+		   defined range).
+pwm[1-4]_start_output
+		   minimum fan speed (range 1 - 255) when spinning up
+pwm[1-4]_step_output
+		   rate of fan speed change (1 - 255)
+pwm[1-4]_stop_output
+		   minimum fan speed (range 1 - 255) when spinning down
+pwm[1-4]_max_output
+		   maximum fan speed (range 1 - 255), when the temperature
+		   is above defined range.
 
 Note: last six functions are influenced by other control bits, not yet exported
       by the driver, so a change might not have any effect.
@@ -161,26 +210,35 @@ different power-on default values, but BIOS should already be loading
 appropriate defaults. Note that bank selection must be performed as is currently
 done in the driver for all register addresses.
 
-0x49:  only on DHG, selects temperature source for AUX fan, CPU fan0
-0x4a:  not completely documented for the EHF and the DHG documentation assigns
-       different behavior to bits 7 and 6, including extending the temperature
-       input selection to SmartFan I, not just SmartFan III. Testing on the EHF
-       will reveal whether they are compatible or not.
-
-0x58:  Chip ID: 0xa1=EHF 0xc1=DHG
-0x5e:  only on DHG, has bits to enable "current mode" temperature detection and
-       critical temperature protection
-0x45b: only on EHF, bit 3, vin4 alarm (EHF supports 10 inputs, only 9 on DHG)
-0x552: only on EHF, vin4
-0x558: only on EHF, vin4 high limit
-0x559: only on EHF, vin4 low limit
-0x6b:  only on DHG, SYS fan critical temperature
-0x6c:  only on DHG, CPU fan0 critical temperature
-0x6d:  only on DHG, AUX fan critical temperature
-0x6e:  only on DHG, CPU fan1 critical temperature
-
-0x50-0x55 and 0x650-0x657 are marked "Test Register" for the EHF, but "Reserved
-       Register" for the DHG
+========================= =====================================================
+Register(s)		  Meaning
+========================= =====================================================
+0x49                      only on DHG, selects temperature source for AUX fan,
+			  CPU fan0
+0x4a                      not completely documented for the EHF and the DHG
+			  documentation assigns different behavior to bits 7
+			  and 6, including extending the temperature input
+			  selection to SmartFan I, not just SmartFan III.
+			  Testing on the EHF will reveal whether they are
+			  compatible or not.
+0x58                      Chip ID: 0xa1=EHF 0xc1=DHG
+0x5e                      only on DHG, has bits to enable "current mode"
+			  temperature detection and critical temperature
+			  protection
+0x45b                     only on EHF, bit 3, vin4 alarm (EHF supports 10
+			  inputs, only 9 on DHG)
+0x552                     only on EHF, vin4
+0x558                     only on EHF, vin4 high limit
+0x559                     only on EHF, vin4 low limit
+0x6b                      only on DHG, SYS fan critical temperature
+0x6c                      only on DHG, CPU fan0 critical temperature
+0x6d                      only on DHG, AUX fan critical temperature
+0x6e                      only on DHG, CPU fan1 critical temperature
+0x50-0x55 and 0x650-0x657 marked as:
+
+			    - "Test Register" for the EHF
+			    - "Reserved Register" for the DHG
+========================= =====================================================
 
 The DHG also supports PECI, where the DHG queries Intel CPU temperatures, and
 the ICH8 southbridge gets that data via PECI from the DHG, so that the
diff --git a/Documentation/hwmon/w83627hf b/Documentation/hwmon/w83627hf.rst
index 8432e1118173..d1406c28dee7 100644
--- a/Documentation/hwmon/w83627hf
+++ b/Documentation/hwmon/w83627hf.rst
@@ -20,10 +20,10 @@ Supported chips:
     Datasheet: Provided by Winbond on request(http://www.winbond.com/hq/enu)
 
 Authors:
-        Frodo Looijaard <frodol@dds.nl>,
-        Philip Edelbrock <phil@netroedge.com>,
-        Mark Studebaker <mdsxyz123@yahoo.com>,
-        Bernhard C. Schrenk <clemy@clemy.org>
+	Frodo Looijaard <frodol@dds.nl>,
+	Philip Edelbrock <phil@netroedge.com>,
+	Mark Studebaker <mdsxyz123@yahoo.com>,
+	Bernhard C. Schrenk <clemy@clemy.org>
 
 Module Parameters
 -----------------
@@ -52,8 +52,8 @@ If you really want i2c accesses for these Super I/O chips,
 use the w83781d driver. However this is not the preferred method
 now that this ISA driver has been developed.
 
-The w83627_HF_ uses pins 110-106 as VID0-VID4. The w83627_THF_ uses the
-same pins as GPIO[0:4]. Technically, the w83627_THF_ does not support a
+The `w83627_HF_` uses pins 110-106 as VID0-VID4. The `w83627_THF_` uses the
+same pins as GPIO[0:4]. Technically, the `w83627_THF_` does not support a
 VID reading. However the two chips have the identical 128 pin package. So,
 it is possible or even likely for a w83627thf to have the VID signals routed
 to these pins despite their not being labeled for that purpose. Therefore,
@@ -75,19 +75,23 @@ module parameter is gone for technical reasons. If you need this feature,
 you can obtain the same result by using the isaset tool (part of
 lm-sensors) before loading the driver:
 
-# Enter the Super I/O config space
-isaset -y -f 0x2e 0x87
-isaset -y -f 0x2e 0x87
+# Enter the Super I/O config space::
 
-# Select the hwmon logical device
-isaset -y 0x2e 0x2f 0x07 0x0b
+	isaset -y -f 0x2e 0x87
+	isaset -y -f 0x2e 0x87
 
-# Set the base I/O address (to 0x290 in this example)
-isaset -y 0x2e 0x2f 0x60 0x02
-isaset -y 0x2e 0x2f 0x61 0x90
+# Select the hwmon logical device::
 
-# Exit the Super-I/O config space
-isaset -y -f 0x2e 0xaa
+	isaset -y 0x2e 0x2f 0x07 0x0b
+
+# Set the base I/O address (to 0x290 in this example)::
+
+	isaset -y 0x2e 0x2f 0x60 0x02
+	isaset -y 0x2e 0x2f 0x61 0x90
+
+# Exit the Super-I/O config space::
+
+	isaset -y -f 0x2e 0xaa
 
 The above sequence assumes a Super-I/O config space at 0x2e/0x2f, but
 0x4e/0x4f is also possible.
@@ -97,18 +101,23 @@ Voltage pin mapping
 
 Here is a summary of the voltage pin mapping for the W83627THF. This
 can be useful to convert data provided by board manufacturers into
-working libsensors configuration statements.
-
-    W83627THF		|
-  Pin	| Name		| Register	| Sysfs attribute
------------------------------------------------------
-  100	| CPUVCORE	| 20h		| in0
-   99	| VIN0		| 21h		| in1
-   98	| VIN1		| 22h		| in2
-   97	| VIN2		| 24h		| in4
-  114	| AVCC		| 23h		| in3
-   61	| 5VSB		| 50h (bank 5)	| in7
-   74	| VBAT		| 51h (bank 5)	| in8
+working libsensors configuration statements:
+
+
+- W83627THF
+
+
+  ======== =============== =============== ===============
+  Pin	   Name		   Register	   Sysfs attribute
+  ======== =============== =============== ===============
+    100	   CPUVCORE	   20h		   in0
+     99	   VIN0		   21h		   in1
+     98	   VIN1		   22h		   in2
+     97	   VIN2		   24h		   in4
+    114	   AVCC		   23h		   in3
+     61	   5VSB		   50h (bank 5)	   in7
+     74	   VBAT		   51h (bank 5)	   in8
+  ======== =============== =============== ===============
 
 For other supported devices, you'll have to take the hard path and
 look up the information in the datasheet yourself (and then add it
diff --git a/Documentation/hwmon/w83773g b/Documentation/hwmon/w83773g.rst
index 4cc6c0b8257f..cabaed391414 100644
--- a/Documentation/hwmon/w83773g
+++ b/Documentation/hwmon/w83773g.rst
@@ -1,13 +1,18 @@
 Kernel driver w83773g
-====================
+=====================
 
 Supported chips:
+
   * Nuvoton W83773G
+
     Prefix: 'w83773g'
+
     Addresses scanned: I2C 0x4c and 0x4d
+
     Datasheet: https://www.nuvoton.com/resource-files/W83773G_SG_DatasheetV1_2.pdf
 
 Authors:
+
 	Lei YU <mine260309@gmail.com>
 
 Description
@@ -27,7 +32,4 @@ Resolution for both the local and remote channels is 0.125 degree C.
 The chip supports only temperature measurement. The driver exports
 the temperature values via the following sysfs files:
 
-temp[1-3]_input
-temp[2-3]_fault
-temp[2-3]_offset
-update_interval
+**temp[1-3]_input, temp[2-3]_fault, temp[2-3]_offset, update_interval**
diff --git a/Documentation/hwmon/w83781d b/Documentation/hwmon/w83781d.rst
index 129b0a3b555b..f36d33dfb704 100644
--- a/Documentation/hwmon/w83781d
+++ b/Documentation/hwmon/w83781d.rst
@@ -2,44 +2,64 @@ Kernel driver w83781d
 =====================
 
 Supported chips:
+
   * Winbond W83781D
+
     Prefix: 'w83781d'
+
     Addresses scanned: I2C 0x28 - 0x2f, ISA 0x290 (8 I/O ports)
+
     Datasheet: http://www.winbond-usa.com/products/winbond_products/pdfs/PCIC/w83781d.pdf
+
   * Winbond W83782D
+
     Prefix: 'w83782d'
+
     Addresses scanned: I2C 0x28 - 0x2f, ISA 0x290 (8 I/O ports)
+
     Datasheet: http://www.winbond.com
+
   * Winbond W83783S
+
     Prefix: 'w83783s'
+
     Addresses scanned: I2C 0x2d
+
     Datasheet: http://www.winbond-usa.com/products/winbond_products/pdfs/PCIC/w83783s.pdf
+
   * Asus AS99127F
+
     Prefix: 'as99127f'
+
     Addresses scanned: I2C 0x28 - 0x2f
+
     Datasheet: Unavailable from Asus
 
+
+
 Authors:
-        Frodo Looijaard <frodol@dds.nl>,
-        Philip Edelbrock <phil@netroedge.com>,
-        Mark Studebaker <mdsxyz123@yahoo.com>
+
+      - Frodo Looijaard <frodol@dds.nl>,
+      - Philip Edelbrock <phil@netroedge.com>,
+      - Mark Studebaker <mdsxyz123@yahoo.com>
 
 Module parameters
 -----------------
 
 * init int
-  (default 1)
-  Use 'init=0' to bypass initializing the chip.
-  Try this if your computer crashes when you load the module.
+    (default 1)
+
+    Use 'init=0' to bypass initializing the chip.
+    Try this if your computer crashes when you load the module.
 
 * reset int
-  (default 0)
-  The driver used to reset the chip on load, but does no more. Use
-  'reset=1' to restore the old behavior. Report if you need to do this.
+    (default 0)
+    The driver used to reset the chip on load, but does no more. Use
+    'reset=1' to restore the old behavior. Report if you need to do this.
 
 force_subclients=bus,caddr,saddr,saddr
   This is used to force the i2c addresses for subclients of
-  a certain chip. Typical usage is `force_subclients=0,0x2d,0x4a,0x4b'
+  a certain chip. Typical usage is `force_subclients=0,0x2d,0x4a,0x4b`
   to force the subclients of chip 0x2d on bus 0 to i2c addresses
   0x4a and 0x4b. This parameter is useful for certain Tyan boards.
 
@@ -54,12 +74,19 @@ There is quite some difference between these chips, but they are similar
 enough that it was sensible to put them together in one driver.
 The Asus chips are similar to an I2C-only W83782D.
 
-Chip        #vin    #fanin  #pwm    #temp   wchipid vendid  i2c     ISA
-as99127f    7       3       0       3       0x31    0x12c3  yes     no
-as99127f rev.2 (type_name = as99127f)       0x31    0x5ca3  yes     no
-w83781d     7       3       0       3       0x10-1  0x5ca3  yes     yes
-w83782d     9       3       2-4     3       0x30    0x5ca3  yes     yes
-w83783s     5-6     3       2       1-2     0x40    0x5ca3  yes     no
++----------+---------+--------+-------+-------+---------+--------+------+-----+
+| Chip     | #vin    | #fanin | #pwm  | #temp | wchipid | vendid | i2c  | ISA |
++----------+---------+--------+-------+-------+---------+--------+------+-----+
+| as99127f | 7       | 3      | 0     | 3     | 0x31    | 0x12c3 | yes  |  no |
++----------+---------+--------+-------+-------+---------+--------+------+-----+
+| as99127f rev.2 (type_name = as99127f)       | 0x31    | 0x5ca3 | yes  |  no |
++----------+---------+--------+-------+-------+---------+--------+------+-----+
+| w83781d  | 7       | 3      | 0     | 3     | 0x10-1  | 0x5ca3 | yes  | yes |
++----------+---------+--------+-------+-------+---------+--------+------+-----+
+| w83782d  | 9       | 3      | 2-4   | 3     | 0x30    | 0x5ca3 | yes  | yes |
++----------+---------+--------+-------+-------+---------+--------+------+-----+
+| w83783s  | 5-6     | 3      | 2     |  1-2  | 0x40    | 0x5ca3 | yes  |  no |
++----------+---------+--------+-------+-------+---------+--------+------+-----+
 
 Detection of these chips can sometimes be foiled because they can be in
 an internal state that allows no clean access. If you know the address
@@ -124,22 +151,24 @@ or only the beeping for some alarms.
 
 Individual alarm and beep bits:
 
-0x000001: in0
-0x000002: in1
-0x000004: in2
-0x000008: in3
-0x000010: temp1
-0x000020: temp2 (+temp3 on W83781D)
-0x000040: fan1
-0x000080: fan2
-0x000100: in4
-0x000200: in5
-0x000400: in6
-0x000800: fan3
-0x001000: chassis
-0x002000: temp3 (W83782D only)
-0x010000: in7 (W83782D only)
-0x020000: in8 (W83782D only)
+======== ==========================
+0x000001 in0
+0x000002 in1
+0x000004 in2
+0x000008 in3
+0x000010 temp1
+0x000020 temp2 (+temp3 on W83781D)
+0x000040 fan1
+0x000080 fan2
+0x000100 in4
+0x000200 in5
+0x000400 in6
+0x000800 fan3
+0x001000 chassis
+0x002000 temp3 (W83782D only)
+0x010000 in7 (W83782D only)
+0x020000 in8 (W83782D only)
+======== ==========================
 
 If an alarm triggers, it will remain triggered until the hardware register
 is read at least once. This means that the cause for the alarm may
@@ -179,68 +208,74 @@ Please do not send mail to the author or the sensors group asking for
 a datasheet or ideas on how to convince Asus. We can't help.
 
 
-NOTES:
+NOTES
 -----
   783s has no in1 so that in[2-6] are compatible with the 781d/782d.
 
   783s pin is programmable for -5V or temp1; defaults to -5V,
-       no control in driver so temp1 doesn't work.
+  no control in driver so temp1 doesn't work.
 
   782d and 783s datasheets differ on which is pwm1 and which is pwm2.
-       We chose to follow 782d.
+  We chose to follow 782d.
 
   782d and 783s pin is programmable for fan3 input or pwm2 output;
-       defaults to fan3 input.
-       If pwm2 is enabled (with echo 255 1 > pwm2), then
-       fan3 will report 0.
+  defaults to fan3 input.
+  If pwm2 is enabled (with echo 255 1 > pwm2), then
+  fan3 will report 0.
 
   782d has pwm1-2 for ISA, pwm1-4 for i2c. (pwm3-4 share pins with
-       the ISA pins)
+  the ISA pins)
 
-Data sheet updates:
+Data sheet updates
 ------------------
 	- PWM clock registers:
-
-		000: master /  512
-		001: master / 1024
-		010: master / 2048
-		011: master / 4096
-		100: master / 8192
+		* 000: master /  512
+		* 001: master / 1024
+		* 010: master / 2048
+		* 011: master / 4096
+		* 100: master / 8192
 
 
 Answers from Winbond tech support
 ---------------------------------
->
-> 1) In the W83781D data sheet section 7.2 last paragraph, it talks about
->    reprogramming the R-T table if the Beta of the thermistor is not
->    3435K. The R-T table is described briefly in section 8.20.
->    What formulas do I use to program a new R-T table for a given Beta?
->
-	We are sorry that the calculation for R-T table value is
-confidential. If you have another Beta value of thermistor, we can help
-to calculate the R-T table for you. But you should give us real R-T
-Table which can be gotten by thermistor vendor. Therefore we will calculate
-them and obtain 32-byte data, and you can fill the 32-byte data to the
-register in Bank0.CR51 of W83781D.
 
+::
+
+  >
+  > 1) In the W83781D data sheet section 7.2 last paragraph, it talks about
+  >    reprogramming the R-T table if the Beta of the thermistor is not
+  >    3435K. The R-T table is described briefly in section 8.20.
+  >    What formulas do I use to program a new R-T table for a given Beta?
+  >
+
+  We are sorry that the calculation for R-T table value is
+  confidential. If you have another Beta value of thermistor, we can help
+  to calculate the R-T table for you. But you should give us real R-T
+  Table which can be gotten by thermistor vendor. Therefore we will calculate
+  them and obtain 32-byte data, and you can fill the 32-byte data to the
+  register in Bank0.CR51 of W83781D.
 
-> 2) In the W83782D data sheet, it mentions that pins 38, 39, and 40 are
->    programmable to be either thermistor or Pentium II diode inputs.
->    How do I program them for diode inputs? I can't find any register
->    to program these to be diode inputs.
- --> You may program Bank0 CR[5Dh] and CR[59h] registers.
 
- 	CR[5Dh]    		bit 1(VTIN1)    bit 2(VTIN2)   bit 3(VTIN3)
+  > 2) In the W83782D data sheet, it mentions that pins 38, 39, and 40 are
+  >    programmable to be either thermistor or Pentium II diode inputs.
+  >    How do I program them for diode inputs? I can't find any register
+  >    to program these to be diode inputs.
 
-      	thermistor                0		 0		0
- 	diode 		          1		 1		1
+  You may program Bank0 CR[5Dh] and CR[59h] registers.
 
+  =============================== =============== ============== ============
+	CR[5Dh]    		bit 1(VTIN1)    bit 2(VTIN2)   bit 3(VTIN3)
 
-(error) CR[59h] 		bit 4(VTIN1)	bit 2(VTIN2)   bit 3(VTIN3)
-(right) CR[59h] 		bit 4(VTIN1)	bit 5(VTIN2)   bit 6(VTIN3)
+		thermistor                0		 0		0
+	diode 			  1		 1		1
 
- 	PII thermal diode         1		 1		1
- 	2N3904	diode	          0		 0		0
+
+  (error) CR[59h] 		bit 4(VTIN1)	bit 2(VTIN2)   bit 3(VTIN3)
+  (right) CR[59h] 		bit 4(VTIN1)	bit 5(VTIN2)   bit 6(VTIN3)
+
+	PII thermal diode         1		 1		1
+	2N3904	diode		  0		 0		0
+  =============================== =============== ============== ============
 
 
 Asus Clones
@@ -251,18 +286,21 @@ Here are some very useful information that were given to us by Alex Van
 Kaam about how to detect these chips, and how to read their values. He
 also gives advice for another Asus chipset, the Mozart-2 (which we
 don't support yet). Thanks Alex!
+
 I reworded some parts and added personal comments.
 
-# Detection:
+Detection
+^^^^^^^^^
 
 AS99127F rev.1, AS99127F rev.2 and ASB100:
 - I2C address range: 0x29 - 0x2F
-- If register 0x58 holds 0x31 then we have an Asus (either ASB100 or
-  AS99127F)
+- If register 0x58 holds 0x31 then we have an Asus (either ASB100 or AS99127F)
 - Which one depends on register 0x4F (manufacturer ID):
-  0x06 or 0x94: ASB100
-  0x12 or 0xC3: AS99127F rev.1
-  0x5C or 0xA3: AS99127F rev.2
+
+  - 0x06 or 0x94: ASB100
+  - 0x12 or 0xC3: AS99127F rev.1
+  - 0x5C or 0xA3: AS99127F rev.2
+
   Note that 0x5CA3 is Winbond's ID (WEC), which let us think Asus get their
   AS99127F rev.2 direct from Winbond. The other codes mean ATT and DVC,
   respectively. ATT could stand for Asustek something (although it would be
@@ -273,88 +311,103 @@ Mozart-2:
 - I2C address: 0x77
 - If register 0x58 holds 0x56 or 0x10 then we have a Mozart-2
 - Of the Mozart there are 3 types:
-  0x58=0x56, 0x4E=0x94, 0x4F=0x36: Asus ASM58 Mozart-2
-  0x58=0x56, 0x4E=0x94, 0x4F=0x06: Asus AS2K129R Mozart-2
-  0x58=0x10, 0x4E=0x5C, 0x4F=0xA3: Asus ??? Mozart-2
+
+  - 0x58=0x56, 0x4E=0x94, 0x4F=0x36: Asus ASM58 Mozart-2
+  - 0x58=0x56, 0x4E=0x94, 0x4F=0x06: Asus AS2K129R Mozart-2
+  - 0x58=0x10, 0x4E=0x5C, 0x4F=0xA3: Asus ??? Mozart-2
+
   You can handle all 3 the exact same way :)
 
-# Temperature sensors:
+Temperature sensors
+^^^^^^^^^^^^^^^^^^^
 
 ASB100:
-- sensor 1: register 0x27
-- sensor 2 & 3 are the 2 LM75's on the SMBus
-- sensor 4: register 0x17
-Remark: I noticed that on Intel boards sensor 2 is used for the CPU
+  - sensor 1: register 0x27
+  - sensor 2 & 3 are the 2 LM75's on the SMBus
+  - sensor 4: register 0x17
+
+Remark:
+
+  I noticed that on Intel boards sensor 2 is used for the CPU
   and 4 is ignored/stuck, on AMD boards sensor 4 is the CPU and sensor 2 is
   either ignored or a socket temperature.
 
 AS99127F (rev.1 and 2 alike):
-- sensor 1: register 0x27
-- sensor 2 & 3 are the 2 LM75's on the SMBus
-Remark: Register 0x5b is suspected to be temperature type selector. Bit 1
+  - sensor 1: register 0x27
+  - sensor 2 & 3 are the 2 LM75's on the SMBus
+
+Remark:
+
+  Register 0x5b is suspected to be temperature type selector. Bit 1
   would control temp1, bit 3 temp2 and bit 5 temp3.
 
 Mozart-2:
-- sensor 1: register 0x27
-- sensor 2: register 0x13
+  - sensor 1: register 0x27
+  - sensor 2: register 0x13
 
-# Fan sensors:
+Fan sensors
+^^^^^^^^^^^
 
 ASB100, AS99127F (rev.1 and 2 alike):
-- 3 fans, identical to the W83781D
+  - 3 fans, identical to the W83781D
 
 Mozart-2:
-- 2 fans only, 1350000/RPM/div
-- fan 1: register 0x28,  divisor on register 0xA1 (bits 4-5)
-- fan 2: register 0x29,  divisor on register 0xA1 (bits 6-7)
+  - 2 fans only, 1350000/RPM/div
+  - fan 1: register 0x28,  divisor on register 0xA1 (bits 4-5)
+  - fan 2: register 0x29,  divisor on register 0xA1 (bits 6-7)
 
-# Voltages:
+Voltages
+^^^^^^^^
 
 This is where there is a difference between AS99127F rev.1 and 2.
-Remark: The difference is similar to the difference between
+
+Remark:
+
+  The difference is similar to the difference between
   W83781D and W83782D.
 
 ASB100:
-in0=r(0x20)*0.016
-in1=r(0x21)*0.016
-in2=r(0x22)*0.016
-in3=r(0x23)*0.016*1.68
-in4=r(0x24)*0.016*3.8
-in5=r(0x25)*(-0.016)*3.97
-in6=r(0x26)*(-0.016)*1.666
+  - in0=r(0x20)*0.016
+  - in1=r(0x21)*0.016
+  - in2=r(0x22)*0.016
+  - in3=r(0x23)*0.016*1.68
+  - in4=r(0x24)*0.016*3.8
+  - in5=r(0x25)*(-0.016)*3.97
+  - in6=r(0x26)*(-0.016)*1.666
 
 AS99127F rev.1:
-in0=r(0x20)*0.016
-in1=r(0x21)*0.016
-in2=r(0x22)*0.016
-in3=r(0x23)*0.016*1.68
-in4=r(0x24)*0.016*3.8
-in5=r(0x25)*(-0.016)*3.97
-in6=r(0x26)*(-0.016)*1.503
+  - in0=r(0x20)*0.016
+  - in1=r(0x21)*0.016
+  - in2=r(0x22)*0.016
+  - in3=r(0x23)*0.016*1.68
+  - in4=r(0x24)*0.016*3.8
+  - in5=r(0x25)*(-0.016)*3.97
+  - in6=r(0x26)*(-0.016)*1.503
 
 AS99127F rev.2:
-in0=r(0x20)*0.016
-in1=r(0x21)*0.016
-in2=r(0x22)*0.016
-in3=r(0x23)*0.016*1.68
-in4=r(0x24)*0.016*3.8
-in5=(r(0x25)*0.016-3.6)*5.14+3.6
-in6=(r(0x26)*0.016-3.6)*3.14+3.6
+  - in0=r(0x20)*0.016
+  - in1=r(0x21)*0.016
+  - in2=r(0x22)*0.016
+  - in3=r(0x23)*0.016*1.68
+  - in4=r(0x24)*0.016*3.8
+  - in5=(r(0x25)*0.016-3.6)*5.14+3.6
+  - in6=(r(0x26)*0.016-3.6)*3.14+3.6
 
 Mozart-2:
-in0=r(0x20)*0.016
-in1=255
-in2=r(0x22)*0.016
-in3=r(0x23)*0.016*1.68
-in4=r(0x24)*0.016*4
-in5=255
-in6=255
+  - in0=r(0x20)*0.016
+  - in1=255
+  - in2=r(0x22)*0.016
+  - in3=r(0x23)*0.016*1.68
+  - in4=r(0x24)*0.016*4
+  - in5=255
+  - in6=255
 
 
-# PWM
+PWM
+^^^
 
 * Additional info about PWM on the AS99127F (may apply to other Asus
-chips as well) by Jean Delvare as of 2004-04-09:
+  chips as well) by Jean Delvare as of 2004-04-09:
 
 AS99127F revision 2 seems to have two PWM registers at 0x59 and 0x5A,
 and a temperature sensor type selector at 0x5B (which basically means
@@ -401,15 +454,20 @@ AS99127F chips at all.
 I've been fiddling around with the (in)famous 0x59 register and
 found out the following values do work as a form of coarse pwm:
 
-0x80 - seems to turn fans off after some time(1-2 minutes)... might be
-some form of auto-fan-control based on temp? hmm (Qfan? this mobo is an
-old ASUS, it isn't marketed as Qfan. Maybe some beta pre-attempt at Qfan
-that was dropped at the BIOS)
-0x81 - off
-0x82 - slightly "on-ner" than off, but my fans do not get to move. I can
-hear the high-pitched PWM sound that motors give off at too-low-pwm.
-0x83 - now they do move. Estimate about 70% speed or so.
-0x84-0x8f - full on
+0x80
+ - seems to turn fans off after some time(1-2 minutes)... might be
+   some form of auto-fan-control based on temp? hmm (Qfan? this mobo is an
+   old ASUS, it isn't marketed as Qfan. Maybe some beta pre-attempt at Qfan
+   that was dropped at the BIOS)
+0x81
+ - off
+0x82
+ - slightly "on-ner" than off, but my fans do not get to move. I can
+   hear the high-pitched PWM sound that motors give off at too-low-pwm.
+0x83
+ - now they do move. Estimate about 70% speed or so.
+0x84-0x8f
+ - full on
 
 Changing the high nibble doesn't seem to do much except the high bit
 (0x80) must be set for PWM to work, else the current pwm doesn't seem to
@@ -435,6 +493,7 @@ looks like PWM is filtered on this motherboard.
 
 Here are some of measurements:
 
+==== =========
 0x80     20 mV
 0x81     20 mV
 0x82    232 mV
@@ -451,3 +510,4 @@ Here are some of measurements:
 0x8d  12.4  V
 0x8e  12.4  V
 0x8f  12.4  V
+==== =========
diff --git a/Documentation/hwmon/w83791d b/Documentation/hwmon/w83791d.rst
index f4021a285460..3adaed39b157 100644
--- a/Documentation/hwmon/w83791d
+++ b/Documentation/hwmon/w83791d.rst
@@ -2,9 +2,13 @@ Kernel driver w83791d
 =====================
 
 Supported chips:
+
   * Winbond W83791D
+
     Prefix: 'w83791d'
+
     Addresses scanned: I2C 0x2c - 0x2f
+
     Datasheet: http://www.winbond-usa.com/products/winbond_products/pdfs/PCIC/W83791D_W83791Gb.pdf
 
 Author: Charles Spirakis <bezaur@gmail.com>
@@ -12,39 +16,46 @@ Author: Charles Spirakis <bezaur@gmail.com>
 This driver was derived from the w83781d.c and w83792d.c source files.
 
 Credits:
+
   w83781d.c:
-    Frodo Looijaard <frodol@dds.nl>,
-    Philip Edelbrock <phil@netroedge.com>,
-    and Mark Studebaker <mdsxyz123@yahoo.com>
+
+    - Frodo Looijaard <frodol@dds.nl>,
+    - Philip Edelbrock <phil@netroedge.com>,
+    - Mark Studebaker <mdsxyz123@yahoo.com>
+
   w83792d.c:
-    Shane Huang (Winbond),
-    Rudolf Marek <r.marek@assembler.cz>
+
+    - Shane Huang (Winbond),
+    - Rudolf Marek <r.marek@assembler.cz>
 
 Additional contributors:
-    Sven Anders <anders@anduras.de>
-    Marc Hulsman <m.hulsman@tudelft.nl>
+
+    - Sven Anders <anders@anduras.de>
+    - Marc Hulsman <m.hulsman@tudelft.nl>
 
 Module Parameters
 -----------------
 
 * init boolean
-  (default 0)
-  Use 'init=1' to have the driver do extra software initializations.
-  The default behavior is to do the minimum initialization possible
-  and depend on the BIOS to properly setup the chip. If you know you
-  have a w83791d and you're having problems, try init=1 before trying
-  reset=1.
+    (default 0)
+
+    Use 'init=1' to have the driver do extra software initializations.
+    The default behavior is to do the minimum initialization possible
+    and depend on the BIOS to properly setup the chip. If you know you
+    have a w83791d and you're having problems, try init=1 before trying
+    reset=1.
 
 * reset boolean
-  (default 0)
-  Use 'reset=1' to reset the chip (via index 0x40, bit 7). The default
-  behavior is no chip reset to preserve BIOS settings.
+    (default 0)
+
+    Use 'reset=1' to reset the chip (via index 0x40, bit 7). The default
+    behavior is no chip reset to preserve BIOS settings.
 
 * force_subclients=bus,caddr,saddr,saddr
-  This is used to force the i2c addresses for subclients of
-  a certain chip. Example usage is `force_subclients=0,0x2f,0x4a,0x4b'
-  to force the subclients of chip 0x2f on bus 0 to i2c addresses
-  0x4a and 0x4b.
+    This is used to force the i2c addresses for subclients of
+    a certain chip. Example usage is `force_subclients=0,0x2f,0x4a,0x4b`
+    to force the subclients of chip 0x2f on bus 0 to i2c addresses
+    0x4a and 0x4b.
 
 
 Description
@@ -91,11 +102,11 @@ This file is used for both legacy and new code.
 
 The sysfs interface to the beep bitmask has migrated from the original legacy
 method of a single sysfs beep_mask file to a newer method using multiple
-*_beep files as described in .../Documentation/hwmon/sysfs-interface.
+`*_beep` files as described in `Documentation/hwmon/sysfs-interface.rst`.
 
 A similar change has occurred for the bitmap corresponding to the alarms. The
 original legacy method used a single sysfs alarms file containing a bitmap
-of triggered alarms. The newer method uses multiple sysfs *_alarm files
+of triggered alarms. The newer method uses multiple sysfs `*_alarm` files
 (again following the pattern described in sysfs-interface).
 
 Since both methods read and write the underlying hardware, they can be used
@@ -116,46 +127,54 @@ User mode code requesting values more often will receive cached values.
 The sysfs-interface is documented in the 'sysfs-interface' file. Only
 chip-specific options are documented here.
 
-pwm[1-3]_enable -	this file controls mode of fan/temperature control for
+======================= =======================================================
+pwm[1-3]_enable		this file controls mode of fan/temperature control for
 			fan 1-3. Fan/PWM 4-5 only support manual mode.
-		            * 1 Manual mode
-		            * 2 Thermal Cruise mode
-		            * 3 Fan Speed Cruise mode (no further support)
 
-temp[1-3]_target -	defines the target temperature for Thermal Cruise mode.
+			    * 1 Manual mode
+			    * 2 Thermal Cruise mode
+			    * 3 Fan Speed Cruise mode (no further support)
+
+temp[1-3]_target	defines the target temperature for Thermal Cruise mode.
 			Unit: millidegree Celsius
 			RW
 
-temp[1-3]_tolerance -	temperature tolerance for Thermal Cruise mode.
+temp[1-3]_tolerance	temperature tolerance for Thermal Cruise mode.
 			Specifies an interval around the target temperature
 			in which the fan speed is not changed.
 			Unit: millidegree Celsius
 			RW
+======================= =======================================================
 
 Alarms bitmap vs. beep_mask bitmask
-------------------------------------
+-----------------------------------
+
 For legacy code using the alarms and beep_mask files:
 
-in0 (VCORE)  :  alarms: 0x000001 beep_mask: 0x000001
-in1 (VINR0)  :  alarms: 0x000002 beep_mask: 0x002000 <== mismatch
-in2 (+3.3VIN):  alarms: 0x000004 beep_mask: 0x000004
-in3 (5VDD)   :  alarms: 0x000008 beep_mask: 0x000008
-in4 (+12VIN) :  alarms: 0x000100 beep_mask: 0x000100
-in5 (-12VIN) :  alarms: 0x000200 beep_mask: 0x000200
-in6 (-5VIN)  :  alarms: 0x000400 beep_mask: 0x000400
-in7 (VSB)    :  alarms: 0x080000 beep_mask: 0x010000 <== mismatch
-in8 (VBAT)   :  alarms: 0x100000 beep_mask: 0x020000 <== mismatch
-in9 (VINR1)  :  alarms: 0x004000 beep_mask: 0x004000
-temp1        :  alarms: 0x000010 beep_mask: 0x000010
-temp2        :  alarms: 0x000020 beep_mask: 0x000020
-temp3        :  alarms: 0x002000 beep_mask: 0x000002 <== mismatch
-fan1         :  alarms: 0x000040 beep_mask: 0x000040
-fan2         :  alarms: 0x000080 beep_mask: 0x000080
-fan3         :  alarms: 0x000800 beep_mask: 0x000800
-fan4         :  alarms: 0x200000 beep_mask: 0x200000
-fan5         :  alarms: 0x400000 beep_mask: 0x400000
-tart1        :  alarms: 0x010000 beep_mask: 0x040000 <== mismatch
-tart2        :  alarms: 0x020000 beep_mask: 0x080000 <== mismatch
-tart3        :  alarms: 0x040000 beep_mask: 0x100000 <== mismatch
-case_open    :  alarms: 0x001000 beep_mask: 0x001000
-global_enable:  alarms: -------- beep_mask: 0x800000 (modified via beep_enable)
+=============  ========  ========= ==========================
+Signal         Alarms    beep_mask Obs
+=============  ========  ========= ==========================
+in0 (VCORE)    0x000001  0x000001
+in1 (VINR0)    0x000002  0x002000  <== mismatch
+in2 (+3.3VIN)  0x000004  0x000004
+in3 (5VDD)     0x000008  0x000008
+in4 (+12VIN)   0x000100  0x000100
+in5 (-12VIN)   0x000200  0x000200
+in6 (-5VIN)    0x000400  0x000400
+in7 (VSB)      0x080000  0x010000  <== mismatch
+in8 (VBAT)     0x100000  0x020000  <== mismatch
+in9 (VINR1)    0x004000  0x004000
+temp1          0x000010  0x000010
+temp2          0x000020  0x000020
+temp3          0x002000  0x000002  <== mismatch
+fan1           0x000040  0x000040
+fan2           0x000080  0x000080
+fan3           0x000800  0x000800
+fan4           0x200000  0x200000
+fan5           0x400000  0x400000
+tart1          0x010000  0x040000  <== mismatch
+tart2          0x020000  0x080000  <== mismatch
+tart3          0x040000  0x100000  <== mismatch
+case_open      0x001000  0x001000
+global_enable  -         0x800000  (modified via beep_enable)
+=============  ========  ========= ==========================
diff --git a/Documentation/hwmon/w83792d b/Documentation/hwmon/w83792d.rst
index f2ffc402ea45..92c4bfe4968c 100644
--- a/Documentation/hwmon/w83792d
+++ b/Documentation/hwmon/w83792d.rst
@@ -2,9 +2,13 @@ Kernel driver w83792d
 =====================
 
 Supported chips:
+
   * Winbond W83792D
+
     Prefix: 'w83792d'
+
     Addresses scanned: I2C 0x2c - 0x2f
+
     Datasheet: http://www.winbond.com.tw
 
 Author: Shane Huang (Winbond)
@@ -15,15 +19,16 @@ Module Parameters
 -----------------
 
 * init int
-  (default 1)
-  Use 'init=0' to bypass initializing the chip.
-  Try this if your computer crashes when you load the module.
+    (default 1)
+
+    Use 'init=0' to bypass initializing the chip.
+    Try this if your computer crashes when you load the module.
 
 * force_subclients=bus,caddr,saddr,saddr
-  This is used to force the i2c addresses for subclients of
-  a certain chip. Example usage is `force_subclients=0,0x2f,0x4a,0x4b'
-  to force the subclients of chip 0x2f on bus 0 to i2c addresses
-  0x4a and 0x4b.
+    This is used to force the i2c addresses for subclients of
+    a certain chip. Example usage is `force_subclients=0,0x2f,0x4a,0x4b`
+    to force the subclients of chip 0x2f on bus 0 to i2c addresses
+    0x4a and 0x4b.
 
 
 Description
@@ -67,31 +72,34 @@ or maximum limit.
 Alarms are provided as output from "realtime status register". Following bits
 are defined:
 
-bit - alarm on:
-0  - in0
-1  - in1
-2  - temp1
-3  - temp2
-4  - temp3
-5  - fan1
-6  - fan2
-7  - fan3
-8  - in2
-9  - in3
-10 - in4
-11 - in5
-12 - in6
-13 - VID change
-14 - chassis
-15 - fan7
-16 - tart1
-17 - tart2
-18 - tart3
-19 - in7
-20 - in8
-21 - fan4
-22 - fan5
-23 - fan6
+==== ==========
+bit   alarm on
+==== ==========
+0    in0
+1    in1
+2    temp1
+3    temp2
+4    temp3
+5    fan1
+6    fan2
+7    fan3
+8    in2
+9    in3
+10   in4
+11   in5
+12   in6
+13   VID change
+14   chassis
+15   fan7
+16   tart1
+17   tart2
+18   tart3
+19   in7
+20   in8
+21   fan4
+22   fan5
+23   fan6
+==== ==========
 
 Tart will be asserted while target temperature cannot be achieved after 3 minutes
 of full speed rotation of corresponding fan.
@@ -114,7 +122,7 @@ Known problems:
 	  by CR[0x49h].
 	- The function of vid and vrm has not been finished, because I'm NOT
 	  very familiar with them. Adding support is welcome.
- 	- The function of chassis open detection needs more tests.
+	- The function of chassis open detection needs more tests.
 	- If you have ASUS server board and chip was not found: Then you will
 	  need to upgrade to latest (or beta) BIOS. If it does not help please
 	  contact us.
@@ -165,17 +173,27 @@ for each fan.
 /sys files
 ----------
 
-pwm[1-7] - this file stores PWM duty cycle or DC value (fan speed) in range:
-	0 (stop) to 255 (full)
-pwm[1-3]_enable - this file controls mode of fan/temperature control:
-            * 0 Disabled
-            * 1 Manual mode
-            * 2 Smart Fan II
-            * 3 Thermal Cruise
-pwm[1-7]_mode - Select PWM or DC mode
-            * 0 DC
-            * 1 PWM
-thermal_cruise[1-3] - Selects the desired temperature for cruise (degC)
-tolerance[1-3] - Value in degrees of Celsius (degC) for +- T
-sf2_point[1-4]_fan[1-3] - four temperature points for each fan for Smart Fan II
-sf2_level[1-3]_fan[1-3] - three PWM/DC levels for each fan for Smart Fan II
+pwm[1-7]
+	- this file stores PWM duty cycle or DC value (fan speed) in range:
+
+	    0 (stop) to 255 (full)
+pwm[1-3]_enable
+	- this file controls mode of fan/temperature control:
+
+	    * 0 Disabled
+	    * 1 Manual mode
+	    * 2 Smart Fan II
+	    * 3 Thermal Cruise
+pwm[1-7]_mode
+	- Select PWM or DC mode
+
+	    * 0 DC
+	    * 1 PWM
+thermal_cruise[1-3]
+	- Selects the desired temperature for cruise (degC)
+tolerance[1-3]
+	- Value in degrees of Celsius (degC) for +- T
+sf2_point[1-4]_fan[1-3]
+	- four temperature points for each fan for Smart Fan II
+sf2_level[1-3]_fan[1-3]
+	- three PWM/DC levels for each fan for Smart Fan II
diff --git a/Documentation/hwmon/w83793 b/Documentation/hwmon/w83793
deleted file mode 100644
index 6cc5f639b721..000000000000
--- a/Documentation/hwmon/w83793
+++ /dev/null
@@ -1,106 +0,0 @@
-Kernel driver w83793
-====================
-
-Supported chips:
-  * Winbond W83793G/W83793R
-    Prefix: 'w83793'
-    Addresses scanned: I2C 0x2c - 0x2f
-    Datasheet: Still not published
-
-Authors:
-    Yuan Mu (Winbond Electronics)
-    Rudolf Marek <r.marek@assembler.cz>
-
-
-Module parameters
------------------
-
-* reset int
-  (default 0)
-  This parameter is not recommended, it will lose motherboard specific
-  settings. Use 'reset=1' to reset the chip when loading this module.
-
-* force_subclients=bus,caddr,saddr1,saddr2
-  This is used to force the i2c addresses for subclients of
-  a certain chip. Typical usage is `force_subclients=0,0x2f,0x4a,0x4b'
-  to force the subclients of chip 0x2f on bus 0 to i2c addresses
-  0x4a and 0x4b.
-
-
-Description
------------
-
-This driver implements support for Winbond W83793G/W83793R chips.
-
-* Exported features
-  This driver exports 10 voltage sensors, up to 12 fan tachometer inputs,
-  6 remote temperatures, up to 8 sets of PWM fan controls, SmartFan
-  (automatic fan speed control) on all temperature/PWM combinations, 2
-  sets of 6-pin CPU VID input.
-
-* Sensor resolutions
-  If your motherboard maker used the reference design, the resolution of
-  voltage0-2 is 2mV, resolution of voltage3/4/5 is 16mV, 8mV for voltage6,
-  24mV for voltage7/8. Temp1-4 have a 0.25 degree Celsius resolution,
-  temp5-6 have a 1 degree Celsiis resolution.
-
-* Temperature sensor types
-  Temp1-4 have 2 possible types. It can be read from (and written to)
-  temp[1-4]_type.
-  - If the value is 3, it starts monitoring using a remote termal diode
-    (default).
-  - If the value is 6, it starts monitoring using the temperature sensor
-    in Intel CPU and get result by PECI.
-  Temp5-6 can be connected to external thermistors (value of
-  temp[5-6]_type is 4).
-
-* Alarm mechanism
-  For voltage sensors, an alarm triggers if the measured value is below
-  the low voltage limit or over the high voltage limit.
-  For temperature sensors, an alarm triggers if the measured value goes
-  above the high temperature limit, and wears off only after the measured
-  value drops below the hysteresis value.
-  For fan sensors, an alarm triggers if the measured value is below the
-  low speed limit.
-
-* SmartFan/PWM control
-  If you want to set a pwm fan to manual mode, you just need to make sure it
-  is not controlled by any temp channel, for example, you want to set fan1
-  to manual mode, you need to check the value of temp[1-6]_fan_map, make
-  sure bit 0 is cleared in the 6 values. And then set the pwm1 value to
-  control the fan.
-
-  Each temperature channel can control all the 8 PWM outputs (by setting the
-  corresponding bit in tempX_fan_map), you can set the temperature channel
-  mode using temp[1-6]_pwm_enable, 2 is Thermal Cruise mode and 3
-  is the SmartFanII mode. Temperature channels will try to speed up or
-  slow down all controlled fans, this means one fan can receive different
-  PWM value requests from different temperature channels, but the chip
-  will always pick the safest (max) PWM value for each fan.
-
-  In Thermal Cruise mode, the chip attempts to keep the temperature at a
-  predefined value, within a tolerance margin. So if tempX_input >
-  thermal_cruiseX + toleranceX, the chip will increase the PWM value,
-  if tempX_input < thermal_cruiseX - toleranceX, the chip will decrease
-  the PWM value. If the temperature is within the tolerance range, the PWM
-  value is left unchanged.
-
-  SmartFanII works differently, you have to define up to 7 PWM, temperature
-  trip points, defining a PWM/temperature curve which the chip will follow.
-  While not fundamentally different from the Thermal Cruise mode, the
-  implementation is quite different, giving you a finer-grained control.
-
-* Chassis
-  If the case open alarm triggers, it will stay in this state unless cleared
-  by writing 0 to the sysfs file "intrusion0_alarm".
-
-* VID and VRM
-  The VRM version is detected automatically, don't modify the it unless you
-  *do* know the cpu VRM version and it's not properly detected.
-
-
-Notes
------
-
-  Only Fan1-5 and PWM1-3 are guaranteed to always exist, other fan inputs and
-  PWM outputs may or may not exist depending on the chip pin configuration.
diff --git a/Documentation/hwmon/w83793.rst b/Documentation/hwmon/w83793.rst
new file mode 100644
index 000000000000..83bb40c48645
--- /dev/null
+++ b/Documentation/hwmon/w83793.rst
@@ -0,0 +1,113 @@
+Kernel driver w83793
+====================
+
+Supported chips:
+
+  * Winbond W83793G/W83793R
+
+    Prefix: 'w83793'
+
+    Addresses scanned: I2C 0x2c - 0x2f
+
+    Datasheet: Still not published
+
+Authors:
+    - Yuan Mu (Winbond Electronics)
+    - Rudolf Marek <r.marek@assembler.cz>
+
+
+Module parameters
+-----------------
+
+* reset int
+    (default 0)
+
+    This parameter is not recommended, it will lose motherboard specific
+    settings. Use 'reset=1' to reset the chip when loading this module.
+
+* force_subclients=bus,caddr,saddr1,saddr2
+    This is used to force the i2c addresses for subclients of
+    a certain chip. Typical usage is `force_subclients=0,0x2f,0x4a,0x4b`
+    to force the subclients of chip 0x2f on bus 0 to i2c addresses
+    0x4a and 0x4b.
+
+
+Description
+-----------
+
+This driver implements support for Winbond W83793G/W83793R chips.
+
+* Exported features
+    This driver exports 10 voltage sensors, up to 12 fan tachometer inputs,
+    6 remote temperatures, up to 8 sets of PWM fan controls, SmartFan
+    (automatic fan speed control) on all temperature/PWM combinations, 2
+    sets of 6-pin CPU VID input.
+
+* Sensor resolutions
+    If your motherboard maker used the reference design, the resolution of
+    voltage0-2 is 2mV, resolution of voltage3/4/5 is 16mV, 8mV for voltage6,
+    24mV for voltage7/8. Temp1-4 have a 0.25 degree Celsius resolution,
+    temp5-6 have a 1 degree Celsiis resolution.
+
+* Temperature sensor types
+    Temp1-4 have 2 possible types. It can be read from (and written to)
+    temp[1-4]_type.
+
+    - If the value is 3, it starts monitoring using a remote termal diode
+      (default).
+    - If the value is 6, it starts monitoring using the temperature sensor
+      in Intel CPU and get result by PECI.
+
+    Temp5-6 can be connected to external thermistors (value of
+    temp[5-6]_type is 4).
+
+* Alarm mechanism
+    For voltage sensors, an alarm triggers if the measured value is below
+    the low voltage limit or over the high voltage limit.
+    For temperature sensors, an alarm triggers if the measured value goes
+    above the high temperature limit, and wears off only after the measured
+    value drops below the hysteresis value.
+    For fan sensors, an alarm triggers if the measured value is below the
+    low speed limit.
+
+* SmartFan/PWM control
+    If you want to set a pwm fan to manual mode, you just need to make sure it
+    is not controlled by any temp channel, for example, you want to set fan1
+    to manual mode, you need to check the value of temp[1-6]_fan_map, make
+    sure bit 0 is cleared in the 6 values. And then set the pwm1 value to
+    control the fan.
+
+    Each temperature channel can control all the 8 PWM outputs (by setting the
+    corresponding bit in tempX_fan_map), you can set the temperature channel
+    mode using temp[1-6]_pwm_enable, 2 is Thermal Cruise mode and 3
+    is the SmartFanII mode. Temperature channels will try to speed up or
+    slow down all controlled fans, this means one fan can receive different
+    PWM value requests from different temperature channels, but the chip
+    will always pick the safest (max) PWM value for each fan.
+
+    In Thermal Cruise mode, the chip attempts to keep the temperature at a
+    predefined value, within a tolerance margin. So if tempX_input >
+    thermal_cruiseX + toleranceX, the chip will increase the PWM value,
+    if tempX_input < thermal_cruiseX - toleranceX, the chip will decrease
+    the PWM value. If the temperature is within the tolerance range, the PWM
+    value is left unchanged.
+
+    SmartFanII works differently, you have to define up to 7 PWM, temperature
+    trip points, defining a PWM/temperature curve which the chip will follow.
+    While not fundamentally different from the Thermal Cruise mode, the
+    implementation is quite different, giving you a finer-grained control.
+
+* Chassis
+    If the case open alarm triggers, it will stay in this state unless cleared
+    by writing 0 to the sysfs file "intrusion0_alarm".
+
+* VID and VRM
+    The VRM version is detected automatically, don't modify the it unless you
+    *do* know the cpu VRM version and it's not properly detected.
+
+
+Notes
+-----
+
+  Only Fan1-5 and PWM1-3 are guaranteed to always exist, other fan inputs and
+  PWM outputs may or may not exist depending on the chip pin configuration.
diff --git a/Documentation/hwmon/w83795 b/Documentation/hwmon/w83795
deleted file mode 100644
index d3e678216b9a..000000000000
--- a/Documentation/hwmon/w83795
+++ /dev/null
@@ -1,127 +0,0 @@
-Kernel driver w83795
-====================
-
-Supported chips:
-  * Winbond/Nuvoton W83795G
-    Prefix: 'w83795g'
-    Addresses scanned: I2C 0x2c - 0x2f
-    Datasheet: Available for download on nuvoton.com
-  * Winbond/Nuvoton W83795ADG
-    Prefix: 'w83795adg'
-    Addresses scanned: I2C 0x2c - 0x2f
-    Datasheet: Available for download on nuvoton.com
-
-Authors:
-    Wei Song (Nuvoton)
-    Jean Delvare <jdelvare@suse.de>
-
-
-Pin mapping
------------
-
-Here is a summary of the pin mapping for the W83795G and W83795ADG.
-This can be useful to convert data provided by board manufacturers
-into working libsensors configuration statements.
-
-    W83795G			|
-  Pin	| Name			| Register	| Sysfs attribute
-------------------------------------------------------------------
-   13	| VSEN1 (VCORE1)	| 10h		| in0
-   14	| VSEN2 (VCORE2)	| 11h		| in1
-   15	| VSEN3 (VCORE3)	| 12h		| in2
-   16	| VSEN4			| 13h		| in3
-   17	| VSEN5			| 14h		| in4
-   18	| VSEN6			| 15h		| in5
-   19	| VSEN7			| 16h		| in6
-   20	| VSEN8			| 17h		| in7
-   21	| VSEN9			| 18h		| in8
-   22	| VSEN10		| 19h		| in9
-   23	| VSEN11		| 1Ah		| in10
-   28	| VTT			| 1Bh		| in11
-   24	| 3VDD			| 1Ch		| in12
-   25	| 3VSB			| 1Dh		| in13
-   26	| VBAT			| 1Eh		| in14
-    3	| VSEN12/TR5		| 1Fh		| in15/temp5
-    4	| VSEN13/TR5		| 20h		| in16/temp6
-  5/  6	| VDSEN14/TR1/TD1	| 21h		| in17/temp1
-  7/  8	| VDSEN15/TR2/TD2	| 22h		| in18/temp2
-  9/ 10	| VDSEN16/TR3/TD3	| 23h		| in19/temp3
- 11/ 12	| VDSEN17/TR4/TD4	| 24h		| in20/temp4
-   40	| FANIN1		| 2Eh		| fan1
-   42	| FANIN2		| 2Fh		| fan2
-   44	| FANIN3		| 30h		| fan3
-   46	| FANIN4		| 31h		| fan4
-   48	| FANIN5		| 32h		| fan5
-   50	| FANIN6		| 33h		| fan6
-   52	| FANIN7		| 34h		| fan7
-   54	| FANIN8		| 35h		| fan8
-   57	| FANIN9		| 36h		| fan9
-   58	| FANIN10		| 37h		| fan10
-   59	| FANIN11		| 38h		| fan11
-   60	| FANIN12		| 39h		| fan12
-   31	| FANIN13		| 3Ah		| fan13
-   35	| FANIN14		| 3Bh		| fan14
-   41	| FANCTL1		| 10h (bank 2)	| pwm1
-   43	| FANCTL2		| 11h (bank 2)	| pwm2
-   45	| FANCTL3		| 12h (bank 2)	| pwm3
-   47	| FANCTL4		| 13h (bank 2)	| pwm4
-   49	| FANCTL5		| 14h (bank 2)	| pwm5
-   51	| FANCTL6		| 15h (bank 2)	| pwm6
-   53	| FANCTL7		| 16h (bank 2)	| pwm7
-   55	| FANCTL8		| 17h (bank 2)	| pwm8
- 29/ 30	| PECI/TSI (DTS1)	| 26h		| temp7
- 29/ 30	| PECI/TSI (DTS2)	| 27h		| temp8
- 29/ 30	| PECI/TSI (DTS3)	| 28h		| temp9
- 29/ 30	| PECI/TSI (DTS4)	| 29h		| temp10
- 29/ 30	| PECI/TSI (DTS5)	| 2Ah		| temp11
- 29/ 30	| PECI/TSI (DTS6)	| 2Bh		| temp12
- 29/ 30	| PECI/TSI (DTS7)	| 2Ch		| temp13
- 29/ 30	| PECI/TSI (DTS8)	| 2Dh		| temp14
-   27	| CASEOPEN#		| 46h		| intrusion0
-
-    W83795ADG			|
-  Pin	| Name			| Register	| Sysfs attribute
-------------------------------------------------------------------
-   10	| VSEN1 (VCORE1)	| 10h		| in0
-   11	| VSEN2 (VCORE2)	| 11h		| in1
-   12	| VSEN3 (VCORE3)	| 12h		| in2
-   13	| VSEN4			| 13h		| in3
-   14	| VSEN5			| 14h		| in4
-   15	| VSEN6			| 15h		| in5
-   16	| VSEN7			| 16h		| in6
-   17	| VSEN8			| 17h		| in7
-   22	| VTT			| 1Bh		| in11
-   18	| 3VDD			| 1Ch		| in12
-   19	| 3VSB			| 1Dh		| in13
-   20	| VBAT			| 1Eh		| in14
-   48	| VSEN12/TR5		| 1Fh		| in15/temp5
-    1	| VSEN13/TR5		| 20h		| in16/temp6
-  2/  3	| VDSEN14/TR1/TD1	| 21h		| in17/temp1
-  4/  5	| VDSEN15/TR2/TD2	| 22h		| in18/temp2
-  6/  7	| VDSEN16/TR3/TD3	| 23h		| in19/temp3
-  8/  9	| VDSEN17/TR4/TD4	| 24h		| in20/temp4
-   32	| FANIN1		| 2Eh		| fan1
-   34	| FANIN2		| 2Fh		| fan2
-   36	| FANIN3		| 30h		| fan3
-   37	| FANIN4		| 31h		| fan4
-   38	| FANIN5		| 32h		| fan5
-   39	| FANIN6		| 33h		| fan6
-   40	| FANIN7		| 34h		| fan7
-   41	| FANIN8		| 35h		| fan8
-   43	| FANIN9		| 36h		| fan9
-   44	| FANIN10		| 37h		| fan10
-   45	| FANIN11		| 38h		| fan11
-   46	| FANIN12		| 39h		| fan12
-   24	| FANIN13		| 3Ah		| fan13
-   28	| FANIN14		| 3Bh		| fan14
-   33	| FANCTL1		| 10h (bank 2)	| pwm1
-   35	| FANCTL2		| 11h (bank 2)	| pwm2
-   23	| PECI (DTS1)		| 26h		| temp7
-   23	| PECI (DTS2)		| 27h		| temp8
-   23	| PECI (DTS3)		| 28h		| temp9
-   23	| PECI (DTS4)		| 29h		| temp10
-   23	| PECI (DTS5)		| 2Ah		| temp11
-   23	| PECI (DTS6)		| 2Bh		| temp12
-   23	| PECI (DTS7)		| 2Ch		| temp13
-   23	| PECI (DTS8)		| 2Dh		| temp14
-   21	| CASEOPEN#		| 46h		| intrusion0
diff --git a/Documentation/hwmon/w83795.rst b/Documentation/hwmon/w83795.rst
new file mode 100644
index 000000000000..d0615e2fabb9
--- /dev/null
+++ b/Documentation/hwmon/w83795.rst
@@ -0,0 +1,142 @@
+Kernel driver w83795
+====================
+
+Supported chips:
+
+  * Winbond/Nuvoton W83795G
+
+    Prefix: 'w83795g'
+
+    Addresses scanned: I2C 0x2c - 0x2f
+
+    Datasheet: Available for download on nuvoton.com
+
+  * Winbond/Nuvoton W83795ADG
+
+    Prefix: 'w83795adg'
+
+    Addresses scanned: I2C 0x2c - 0x2f
+
+    Datasheet: Available for download on nuvoton.com
+
+Authors:
+    - Wei Song (Nuvoton)
+    - Jean Delvare <jdelvare@suse.de>
+
+
+Pin mapping
+-----------
+
+Here is a summary of the pin mapping for the W83795G and W83795ADG.
+This can be useful to convert data provided by board manufacturers
+into working libsensors configuration statements.
+
+
+- W83795G
+
+========= ======================= =============== ================
+Pin	  Name			  Register	  Sysfs attribute
+========= ======================= =============== ================
+   13	  VSEN1 (VCORE1)	  10h		  in0
+   14	  VSEN2 (VCORE2)	  11h		  in1
+   15	  VSEN3 (VCORE3)	  12h		  in2
+   16	  VSEN4			  13h		  in3
+   17	  VSEN5			  14h		  in4
+   18	  VSEN6			  15h		  in5
+   19	  VSEN7			  16h		  in6
+   20	  VSEN8			  17h		  in7
+   21	  VSEN9			  18h		  in8
+   22	  VSEN10		  19h		  in9
+   23	  VSEN11		  1Ah		  in10
+   28	  VTT			  1Bh		  in11
+   24	  3VDD			  1Ch		  in12
+   25	  3VSB			  1Dh		  in13
+   26	  VBAT			  1Eh		  in14
+    3	  VSEN12/TR5		  1Fh		  in15/temp5
+    4	  VSEN13/TR5		  20h		  in16/temp6
+  5/  6	  VDSEN14/TR1/TD1	  21h		  in17/temp1
+  7/  8	  VDSEN15/TR2/TD2	  22h		  in18/temp2
+  9/ 10	  VDSEN16/TR3/TD3	  23h		  in19/temp3
+ 11/ 12	  VDSEN17/TR4/TD4	  24h		  in20/temp4
+   40	  FANIN1		  2Eh		  fan1
+   42	  FANIN2		  2Fh		  fan2
+   44	  FANIN3		  30h		  fan3
+   46	  FANIN4		  31h		  fan4
+   48	  FANIN5		  32h		  fan5
+   50	  FANIN6		  33h		  fan6
+   52	  FANIN7		  34h		  fan7
+   54	  FANIN8		  35h		  fan8
+   57	  FANIN9		  36h		  fan9
+   58	  FANIN10		  37h		  fan10
+   59	  FANIN11		  38h		  fan11
+   60	  FANIN12		  39h		  fan12
+   31	  FANIN13		  3Ah		  fan13
+   35	  FANIN14		  3Bh		  fan14
+   41	  FANCTL1		  10h (bank 2)	  pwm1
+   43	  FANCTL2		  11h (bank 2)	  pwm2
+   45	  FANCTL3		  12h (bank 2)	  pwm3
+   47	  FANCTL4		  13h (bank 2)	  pwm4
+   49	  FANCTL5		  14h (bank 2)	  pwm5
+   51	  FANCTL6		  15h (bank 2)	  pwm6
+   53	  FANCTL7		  16h (bank 2)	  pwm7
+   55	  FANCTL8		  17h (bank 2)	  pwm8
+ 29/ 30	  PECI/TSI (DTS1)	  26h		  temp7
+ 29/ 30	  PECI/TSI (DTS2)	  27h		  temp8
+ 29/ 30	  PECI/TSI (DTS3)	  28h		  temp9
+ 29/ 30	  PECI/TSI (DTS4)	  29h		  temp10
+ 29/ 30	  PECI/TSI (DTS5)	  2Ah		  temp11
+ 29/ 30	  PECI/TSI (DTS6)	  2Bh		  temp12
+ 29/ 30	  PECI/TSI (DTS7)	  2Ch		  temp13
+ 29/ 30	  PECI/TSI (DTS8)	  2Dh		  temp14
+   27	  CASEOPEN#		  46h		  intrusion0
+========= ======================= =============== ================
+
+- W83795ADG
+
+========= ======================= =============== ================
+Pin	  Name			  Register	  Sysfs attribute
+========= ======================= =============== ================
+   10	  VSEN1 (VCORE1)	  10h		  in0
+   11	  VSEN2 (VCORE2)	  11h		  in1
+   12	  VSEN3 (VCORE3)	  12h		  in2
+   13	  VSEN4			  13h		  in3
+   14	  VSEN5			  14h		  in4
+   15	  VSEN6			  15h		  in5
+   16	  VSEN7			  16h		  in6
+   17	  VSEN8			  17h		  in7
+   22	  VTT			  1Bh		  in11
+   18	  3VDD			  1Ch		  in12
+   19	  3VSB			  1Dh		  in13
+   20	  VBAT			  1Eh		  in14
+   48	  VSEN12/TR5		  1Fh		  in15/temp5
+    1	  VSEN13/TR5		  20h		  in16/temp6
+  2/  3	  VDSEN14/TR1/TD1	  21h		  in17/temp1
+  4/  5	  VDSEN15/TR2/TD2	  22h		  in18/temp2
+  6/  7	  VDSEN16/TR3/TD3	  23h		  in19/temp3
+  8/  9	  VDSEN17/TR4/TD4	  24h		  in20/temp4
+   32	  FANIN1		  2Eh		  fan1
+   34	  FANIN2		  2Fh		  fan2
+   36	  FANIN3		  30h		  fan3
+   37	  FANIN4		  31h		  fan4
+   38	  FANIN5		  32h		  fan5
+   39	  FANIN6		  33h		  fan6
+   40	  FANIN7		  34h		  fan7
+   41	  FANIN8		  35h		  fan8
+   43	  FANIN9		  36h		  fan9
+   44	  FANIN10		  37h		  fan10
+   45	  FANIN11		  38h		  fan11
+   46	  FANIN12		  39h		  fan12
+   24	  FANIN13		  3Ah		  fan13
+   28	  FANIN14		  3Bh		  fan14
+   33	  FANCTL1		  10h (bank 2)	  pwm1
+   35	  FANCTL2		  11h (bank 2)	  pwm2
+   23	  PECI (DTS1)		  26h		  temp7
+   23	  PECI (DTS2)		  27h		  temp8
+   23	  PECI (DTS3)		  28h		  temp9
+   23	  PECI (DTS4)		  29h		  temp10
+   23	  PECI (DTS5)		  2Ah		  temp11
+   23	  PECI (DTS6)		  2Bh		  temp12
+   23	  PECI (DTS7)		  2Ch		  temp13
+   23	  PECI (DTS8)		  2Dh		  temp14
+   21	  CASEOPEN#		  46h		  intrusion0
+========= ======================= =============== ================
diff --git a/Documentation/hwmon/w83l785ts b/Documentation/hwmon/w83l785ts.rst
index c8978478871f..7fa5418fed11 100644
--- a/Documentation/hwmon/w83l785ts
+++ b/Documentation/hwmon/w83l785ts.rst
@@ -2,14 +2,19 @@ Kernel driver w83l785ts
 =======================
 
 Supported chips:
+
   * Winbond W83L785TS-S
+
     Prefix: 'w83l785ts'
+
     Addresses scanned: I2C 0x2e
+
     Datasheet: Publicly available at the Winbond USA website
-               http://www.winbond-usa.com/products/winbond_products/pdfs/PCIC/W83L785TS-S.pdf
+
+	       http://www.winbond-usa.com/products/winbond_products/pdfs/PCIC/W83L785TS-S.pdf
 
 Authors:
-        Jean Delvare <jdelvare@suse.de>
+	Jean Delvare <jdelvare@suse.de>
 
 Description
 -----------
diff --git a/Documentation/hwmon/w83l786ng b/Documentation/hwmon/w83l786ng.rst
index d8f55d7fff10..2b7776190de3 100644
--- a/Documentation/hwmon/w83l786ng
+++ b/Documentation/hwmon/w83l786ng.rst
@@ -1,10 +1,14 @@
 Kernel driver w83l786ng
-=====================
+=======================
 
 Supported chips:
+
   * Winbond W83L786NG/W83L786NR
+
     Prefix: 'w83l786ng'
+
     Addresses scanned: I2C 0x2e - 0x2f
+
     Datasheet: http://www.winbond-usa.com/products/winbond_products/pdfs/PCIC/W83L786NRNG09.pdf
 
 Author: Kevin Lo <kevlo@kevlo.org>
@@ -14,9 +18,10 @@ Module Parameters
 -----------------
 
 * reset boolean
-  (default 0)
-  Use 'reset=1' to reset the chip (via index 0x40, bit 7). The default
-  behavior is no chip reset to preserve BIOS settings
+    (default 0)
+
+    Use 'reset=1' to reset the chip (via index 0x40, bit 7). The default
+    behavior is no chip reset to preserve BIOS settings
 
 
 Description
@@ -41,14 +46,21 @@ or maximum limit.
 /sys files
 ----------
 
-pwm[1-2] - this file stores PWM duty cycle or DC value (fan speed) in range:
-	    0 (stop) to 255 (full)
-pwm[1-2]_enable - this file controls mode of fan/temperature control:
-            * 0 Manual Mode
-            * 1 Thermal Cruise
-            * 2 Smart Fan II
-            * 4 FAN_SET
-pwm[1-2]_mode - Select PWM of DC mode
-            * 0 DC
-            * 1 PWM
-tolerance[1-2] - Value in degrees of Celsius (degC) for +- T
+pwm[1-2]
+	    - this file stores PWM duty cycle or DC value (fan speed) in range:
+
+	      0 (stop) to 255 (full)
+pwm[1-2]_enable
+	    - this file controls mode of fan/temperature control:
+
+	    * 0 Manual Mode
+	    * 1 Thermal Cruise
+	    * 2 Smart Fan II
+	    * 4 FAN_SET
+pwm[1-2]_mode
+	    - Select PWM of DC mode
+
+	    * 0 DC
+	    * 1 PWM
+tolerance[1-2]
+	    - Value in degrees of Celsius (degC) for +- T
diff --git a/Documentation/hwmon/wm831x b/Documentation/hwmon/wm831x.rst
index 11446757c8c8..c56fb35a2fb3 100644
--- a/Documentation/hwmon/wm831x
+++ b/Documentation/hwmon/wm831x.rst
@@ -3,11 +3,14 @@ Kernel driver wm831x-hwmon
 
 Supported chips:
   * Wolfson Microelectronics WM831x PMICs
+
     Prefix: 'wm831x'
+
     Datasheet:
-	http://www.wolfsonmicro.com/products/WM8310
-	http://www.wolfsonmicro.com/products/WM8311
-	http://www.wolfsonmicro.com/products/WM8312
+
+	- http://www.wolfsonmicro.com/products/WM8310
+	- http://www.wolfsonmicro.com/products/WM8311
+	- http://www.wolfsonmicro.com/products/WM8312
 
 Authors: Mark Brown <broonie@opensource.wolfsonmicro.com>
 
diff --git a/Documentation/hwmon/wm8350 b/Documentation/hwmon/wm8350.rst
index 98f923bd2e92..cec044ca5900 100644
--- a/Documentation/hwmon/wm8350
+++ b/Documentation/hwmon/wm8350.rst
@@ -2,12 +2,16 @@ Kernel driver wm8350-hwmon
 ==========================
 
 Supported chips:
+
   * Wolfson Microelectronics WM835x PMICs
+
     Prefix: 'wm8350'
+
     Datasheet:
-	http://www.wolfsonmicro.com/products/WM8350
-	http://www.wolfsonmicro.com/products/WM8351
-	http://www.wolfsonmicro.com/products/WM8352
+
+	- http://www.wolfsonmicro.com/products/WM8350
+	- http://www.wolfsonmicro.com/products/WM8351
+	- http://www.wolfsonmicro.com/products/WM8352
 
 Authors: Mark Brown <broonie@opensource.wolfsonmicro.com>
 
diff --git a/Documentation/hwmon/xgene-hwmon b/Documentation/hwmon/xgene-hwmon.rst
index 6ec50ed7cc8f..439b30b881b6 100644
--- a/Documentation/hwmon/xgene-hwmon
+++ b/Documentation/hwmon/xgene-hwmon.rst
@@ -1,7 +1,8 @@
 Kernel driver xgene-hwmon
-========================
+=========================
 
 Supported chips:
+
  * APM X-Gene SoC
 
 Description
@@ -15,16 +16,21 @@ For ACPI, it is the PCC mailbox.
 The following sensors are supported
 
   * Temperature
-    - SoC on-die temperature in milli-degree C
-    - Alarm when high/over temperature occurs
+      - SoC on-die temperature in milli-degree C
+      - Alarm when high/over temperature occurs
+
   * Power
-    - CPU power in uW
-    - IO power in uW
+      - CPU power in uW
+      - IO power in uW
 
 sysfs-Interface
 ---------------
 
-temp0_input - SoC on-die temperature (milli-degree C)
-temp0_critical_alarm - An 1 would indicates on-die temperature exceeded threshold
-power0_input - CPU power in (uW)
-power1_input - IO power in (uW)
+temp0_input
+	- SoC on-die temperature (milli-degree C)
+temp0_critical_alarm
+	- An 1 would indicates on-die temperature exceeded threshold
+power0_input
+	- CPU power in (uW)
+power1_input
+	- IO power in (uW)
diff --git a/Documentation/hwmon/zl6100 b/Documentation/hwmon/zl6100.rst
index 477a94b131ae..41513bb7fe51 100644
--- a/Documentation/hwmon/zl6100
+++ b/Documentation/hwmon/zl6100.rst
@@ -2,57 +2,106 @@ Kernel driver zl6100
 ====================
 
 Supported chips:
+
   * Intersil / Zilker Labs ZL2004
+
     Prefix: 'zl2004'
+
     Addresses scanned: -
+
     Datasheet: http://www.intersil.com/data/fn/fn6847.pdf
+
   * Intersil / Zilker Labs ZL2005
+
     Prefix: 'zl2005'
+
     Addresses scanned: -
+
     Datasheet: http://www.intersil.com/data/fn/fn6848.pdf
+
   * Intersil / Zilker Labs ZL2006
+
     Prefix: 'zl2006'
+
     Addresses scanned: -
+
     Datasheet: http://www.intersil.com/data/fn/fn6850.pdf
+
   * Intersil / Zilker Labs ZL2008
+
     Prefix: 'zl2008'
+
     Addresses scanned: -
+
     Datasheet: http://www.intersil.com/data/fn/fn6859.pdf
+
   * Intersil / Zilker Labs ZL2105
+
     Prefix: 'zl2105'
+
     Addresses scanned: -
+
     Datasheet: http://www.intersil.com/data/fn/fn6851.pdf
+
   * Intersil / Zilker Labs ZL2106
+
     Prefix: 'zl2106'
+
     Addresses scanned: -
+
     Datasheet: http://www.intersil.com/data/fn/fn6852.pdf
+
   * Intersil / Zilker Labs ZL6100
+
     Prefix: 'zl6100'
+
     Addresses scanned: -
+
     Datasheet: http://www.intersil.com/data/fn/fn6876.pdf
+
   * Intersil / Zilker Labs ZL6105
+
     Prefix: 'zl6105'
+
     Addresses scanned: -
+
     Datasheet: http://www.intersil.com/data/fn/fn6906.pdf
+
   * Intersil / Zilker Labs ZL9101M
+
     Prefix: 'zl9101'
+
     Addresses scanned: -
+
     Datasheet: http://www.intersil.com/data/fn/fn7669.pdf
+
   * Intersil / Zilker Labs ZL9117M
+
     Prefix: 'zl9117'
+
     Addresses scanned: -
+
     Datasheet: http://www.intersil.com/data/fn/fn7914.pdf
+
   * Ericsson BMR450, BMR451
+
     Prefix: 'bmr450', 'bmr451'
+
     Addresses scanned: -
+
     Datasheet:
+
 http://archive.ericsson.net/service/internet/picov/get?DocNo=28701-EN/LZT146401
+
   * Ericsson BMR462, BMR463, BMR464
+
     Prefixes: 'bmr462', 'bmr463', 'bmr464'
+
     Addresses scanned: -
+
     Datasheet:
-http://archive.ericsson.net/service/internet/picov/get?DocNo=28701-EN/LZT146256
 
+	http://archive.ericsson.net/service/internet/picov/get?DocNo=28701-EN/LZT146256
 
 Author: Guenter Roeck <linux@roeck-us.net>
 
@@ -64,7 +113,7 @@ This driver supports hardware monitoring for Intersil / Zilker Labs ZL6100 and
 compatible digital DC-DC controllers.
 
 The driver is a client driver to the core PMBus driver. Please see
-Documentation/hwmon/pmbus and Documentation.hwmon/pmbus-core for details
+Documentation/hwmon/pmbus.rst and Documentation.hwmon/pmbus-core for details
 on PMBus client drivers.
 
 
@@ -75,13 +124,15 @@ This driver does not auto-detect devices. You will have to instantiate the
 devices explicitly. Please see Documentation/i2c/instantiating-devices for
 details.
 
-WARNING: Do not access chip registers using the i2cdump command, and do not use
-any of the i2ctools commands on a command register used to save and restore
-configuration data (0x11, 0x12, 0x15, 0x16, and 0xf4). The chips supported by
-this driver interpret any access to those command registers (including read
-commands) as request to execute the command in question. Unless write accesses
-to those registers are protected, this may result in power loss, board resets,
-and/or Flash corruption. Worst case, your board may turn into a brick.
+.. warning::
+
+  Do not access chip registers using the i2cdump command, and do not use
+  any of the i2ctools commands on a command register used to save and restore
+  configuration data (0x11, 0x12, 0x15, 0x16, and 0xf4). The chips supported by
+  this driver interpret any access to those command registers (including read
+  commands) as request to execute the command in question. Unless write accesses
+  to those registers are protected, this may result in power loss, board resets,
+  and/or Flash corruption. Worst case, your board may turn into a brick.
 
 
 Platform data support
@@ -110,6 +161,7 @@ Sysfs entries
 The following attributes are supported. Limits are read-write; all other
 attributes are read-only.
 
+======================= ========================================================
 in1_label		"vin"
 in1_input		Measured input voltage.
 in1_min			Minimum input voltage.
@@ -158,3 +210,4 @@ temp[12]_min_alarm	Chip temperature low alarm.
 temp[12]_max_alarm	Chip temperature high alarm.
 temp[12]_lcrit_alarm	Chip temperature critical low alarm.
 temp[12]_crit_alarm	Chip temperature critical high alarm.
+======================= ========================================================
diff --git a/Documentation/i2c/busses/i2c-i801 b/Documentation/i2c/busses/i2c-i801
index d1ee484a787d..ee9984f35868 100644
--- a/Documentation/i2c/busses/i2c-i801
+++ b/Documentation/i2c/busses/i2c-i801
@@ -36,6 +36,7 @@ Supported adapters:
   * Intel Cannon Lake (PCH)
   * Intel Cedar Fork (PCH)
   * Intel Ice Lake (PCH)
+  * Intel Comet Lake (PCH)
    Datasheets: Publicly available at the Intel website
 
 On Intel Patsburg and later chipsets, both the normal host SMBus controller
diff --git a/Documentation/index.rst b/Documentation/index.rst
index 80a421cb935e..fec80fee512a 100644
--- a/Documentation/index.rst
+++ b/Documentation/index.rst
@@ -35,6 +35,16 @@ trying to get it to work optimally on a given system.
 
    admin-guide/index
 
+Firmware-related documentation
+------------------------------
+The following holds information on the kernel's expectations regarding the
+platform firmwares.
+
+.. toctree::
+   :maxdepth: 2
+
+   firmware-guide/index
+
 Application-developer documentation
 -----------------------------------
 
@@ -83,6 +93,7 @@ needed).
    media/index
    networking/index
    input/index
+   hwmon/index
    gpu/index
    security/index
    sound/index
diff --git a/Documentation/kprobes.txt b/Documentation/kprobes.txt
index 10f4499e677c..ee60e519438a 100644
--- a/Documentation/kprobes.txt
+++ b/Documentation/kprobes.txt
@@ -243,10 +243,10 @@ Optimization
 ^^^^^^^^^^^^
 
 The Kprobe-optimizer doesn't insert the jump instruction immediately;
-rather, it calls synchronize_sched() for safety first, because it's
+rather, it calls synchronize_rcu() for safety first, because it's
 possible for a CPU to be interrupted in the middle of executing the
-optimized region [3]_.  As you know, synchronize_sched() can ensure
-that all interruptions that were active when synchronize_sched()
+optimized region [3]_.  As you know, synchronize_rcu() can ensure
+that all interruptions that were active when synchronize_rcu()
 was called are done, but only if CONFIG_PREEMPT=n.  So, this version
 of kprobe optimization supports only kernels with CONFIG_PREEMPT=n [4]_.
 
diff --git a/Documentation/lzo.txt b/Documentation/lzo.txt
index f79934225d8d..ca983328976b 100644
--- a/Documentation/lzo.txt
+++ b/Documentation/lzo.txt
@@ -102,9 +102,11 @@ Byte sequences
                 dictionary which is empty, and that it will always be
                 invalid at this place.
 
-      17      : bitstream version. If the first byte is 17, the next byte
-                gives the bitstream version (version 1 only). If the first byte
-                is not 17, the bitstream version is 0.
+      17      : bitstream version. If the first byte is 17, and compressed
+                stream length is at least 5 bytes (length of shortest possible
+                versioned bitstream), the next byte gives the bitstream version
+                (version 1 only).
+                Otherwise, the bitstream version is 0.
 
       18..21  : copy 0..3 literals
                 state = (byte - 17) = 0..3  [ copy <state> literals ]
diff --git a/Documentation/media/uapi/rc/rc-tables.rst b/Documentation/media/uapi/rc/rc-tables.rst
index f460031d8531..177ac44fa0fa 100644
--- a/Documentation/media/uapi/rc/rc-tables.rst
+++ b/Documentation/media/uapi/rc/rc-tables.rst
@@ -623,7 +623,7 @@ the remote via /dev/input/event devices.
 
     -  .. row 78
 
-       -  ``KEY_SCREEN``
+       -  ``KEY_ASPECT_RATIO``
 
        -  Select screen aspect ratio
 
@@ -631,7 +631,7 @@ the remote via /dev/input/event devices.
 
     -  .. row 79
 
-       -  ``KEY_ZOOM``
+       -  ``KEY_FULL_SCREEN``
 
        -  Put device into zoom/full screen mode
 
diff --git a/Documentation/memory-barriers.txt b/Documentation/memory-barriers.txt
index 1c22b21ae922..f70ebcdfe592 100644
--- a/Documentation/memory-barriers.txt
+++ b/Documentation/memory-barriers.txt
@@ -1937,21 +1937,6 @@ There are some more advanced barrier functions:
      information on consistent memory.
 
 
-MMIO WRITE BARRIER
-------------------
-
-The Linux kernel also has a special barrier for use with memory-mapped I/O
-writes:
-
-	mmiowb();
-
-This is a variation on the mandatory write barrier that causes writes to weakly
-ordered I/O regions to be partially ordered.  Its effects may go beyond the
-CPU->Hardware interface and actually affect the hardware at some level.
-
-See the subsection "Acquires vs I/O accesses" for more information.
-
-
 ===============================
 IMPLICIT KERNEL MEMORY BARRIERS
 ===============================
@@ -2317,75 +2302,6 @@ But it won't see any of:
 	*E, *F or *G following RELEASE Q
 
 
-
-ACQUIRES VS I/O ACCESSES
-------------------------
-
-Under certain circumstances (especially involving NUMA), I/O accesses within
-two spinlocked sections on two different CPUs may be seen as interleaved by the
-PCI bridge, because the PCI bridge does not necessarily participate in the
-cache-coherence protocol, and is therefore incapable of issuing the required
-read memory barriers.
-
-For example:
-
-	CPU 1				CPU 2
-	===============================	===============================
-	spin_lock(Q)
-	writel(0, ADDR)
-	writel(1, DATA);
-	spin_unlock(Q);
-					spin_lock(Q);
-					writel(4, ADDR);
-					writel(5, DATA);
-					spin_unlock(Q);
-
-may be seen by the PCI bridge as follows:
-
-	STORE *ADDR = 0, STORE *ADDR = 4, STORE *DATA = 1, STORE *DATA = 5
-
-which would probably cause the hardware to malfunction.
-
-
-What is necessary here is to intervene with an mmiowb() before dropping the
-spinlock, for example:
-
-	CPU 1				CPU 2
-	===============================	===============================
-	spin_lock(Q)
-	writel(0, ADDR)
-	writel(1, DATA);
-	mmiowb();
-	spin_unlock(Q);
-					spin_lock(Q);
-					writel(4, ADDR);
-					writel(5, DATA);
-					mmiowb();
-					spin_unlock(Q);
-
-this will ensure that the two stores issued on CPU 1 appear at the PCI bridge
-before either of the stores issued on CPU 2.
-
-
-Furthermore, following a store by a load from the same device obviates the need
-for the mmiowb(), because the load forces the store to complete before the load
-is performed:
-
-	CPU 1				CPU 2
-	===============================	===============================
-	spin_lock(Q)
-	writel(0, ADDR)
-	a = readl(DATA);
-	spin_unlock(Q);
-					spin_lock(Q);
-					writel(4, ADDR);
-					b = readl(DATA);
-					spin_unlock(Q);
-
-
-See Documentation/driver-api/device-io.rst for more information.
-
-
 =================================
 WHERE ARE MEMORY BARRIERS NEEDED?
 =================================
@@ -2532,16 +2448,9 @@ the device to malfunction.
 Inside of the Linux kernel, I/O should be done through the appropriate accessor
 routines - such as inb() or writel() - which know how to make such accesses
 appropriately sequential.  While this, for the most part, renders the explicit
-use of memory barriers unnecessary, there are a couple of situations where they
-might be needed:
-
- (1) On some systems, I/O stores are not strongly ordered across all CPUs, and
-     so for _all_ general drivers locks should be used and mmiowb() must be
-     issued prior to unlocking the critical section.
-
- (2) If the accessor functions are used to refer to an I/O memory window with
-     relaxed memory access properties, then _mandatory_ memory barriers are
-     required to enforce ordering.
+use of memory barriers unnecessary, if the accessor functions are used to refer
+to an I/O memory window with relaxed memory access properties, then _mandatory_
+memory barriers are required to enforce ordering.
 
 See Documentation/driver-api/device-io.rst for more information.
 
@@ -2586,8 +2495,7 @@ explicit barriers are used.
 
 Normally this won't be a problem because the I/O accesses done inside such
 sections will include synchronous load operations on strictly ordered I/O
-registers that form implicit I/O barriers.  If this isn't sufficient then an
-mmiowb() may need to be used explicitly.
+registers that form implicit I/O barriers.
 
 
 A similar situation may occur between an interrupt routine and two routines
@@ -2599,71 +2507,114 @@ likely, then interrupt-disabling locks should be used to guarantee ordering.
 KERNEL I/O BARRIER EFFECTS
 ==========================
 
-When accessing I/O memory, drivers should use the appropriate accessor
-functions:
-
- (*) inX(), outX():
-
-     These are intended to talk to I/O space rather than memory space, but
-     that's primarily a CPU-specific concept.  The i386 and x86_64 processors
-     do indeed have special I/O space access cycles and instructions, but many
-     CPUs don't have such a concept.
-
-     The PCI bus, amongst others, defines an I/O space concept which - on such
-     CPUs as i386 and x86_64 - readily maps to the CPU's concept of I/O
-     space.  However, it may also be mapped as a virtual I/O space in the CPU's
-     memory map, particularly on those CPUs that don't support alternate I/O
-     spaces.
-
-     Accesses to this space may be fully synchronous (as on i386), but
-     intermediary bridges (such as the PCI host bridge) may not fully honour
-     that.
-
-     They are guaranteed to be fully ordered with respect to each other.
-
-     They are not guaranteed to be fully ordered with respect to other types of
-     memory and I/O operation.
+Interfacing with peripherals via I/O accesses is deeply architecture and device
+specific. Therefore, drivers which are inherently non-portable may rely on
+specific behaviours of their target systems in order to achieve synchronization
+in the most lightweight manner possible. For drivers intending to be portable
+between multiple architectures and bus implementations, the kernel offers a
+series of accessor functions that provide various degrees of ordering
+guarantees:
 
  (*) readX(), writeX():
 
-     Whether these are guaranteed to be fully ordered and uncombined with
-     respect to each other on the issuing CPU depends on the characteristics
-     defined for the memory window through which they're accessing.  On later
-     i386 architecture machines, for example, this is controlled by way of the
-     MTRR registers.
+	The readX() and writeX() MMIO accessors take a pointer to the
+	peripheral being accessed as an __iomem * parameter. For pointers
+	mapped with the default I/O attributes (e.g. those returned by
+	ioremap()), the ordering guarantees are as follows:
+
+	1. All readX() and writeX() accesses to the same peripheral are ordered
+	   with respect to each other. This ensures that MMIO register accesses
+	   by the same CPU thread to a particular device will arrive in program
+	   order.
+
+	2. A writeX() issued by a CPU thread holding a spinlock is ordered
+	   before a writeX() to the same peripheral from another CPU thread
+	   issued after a later acquisition of the same spinlock. This ensures
+	   that MMIO register writes to a particular device issued while holding
+	   a spinlock will arrive in an order consistent with acquisitions of
+	   the lock.
+
+	3. A writeX() by a CPU thread to the peripheral will first wait for the
+	   completion of all prior writes to memory either issued by, or
+	   propagated to, the same thread. This ensures that writes by the CPU
+	   to an outbound DMA buffer allocated by dma_alloc_coherent() will be
+	   visible to a DMA engine when the CPU writes to its MMIO control
+	   register to trigger the transfer.
+
+	4. A readX() by a CPU thread from the peripheral will complete before
+	   any subsequent reads from memory by the same thread can begin. This
+	   ensures that reads by the CPU from an incoming DMA buffer allocated
+	   by dma_alloc_coherent() will not see stale data after reading from
+	   the DMA engine's MMIO status register to establish that the DMA
+	   transfer has completed.
+
+	5. A readX() by a CPU thread from the peripheral will complete before
+	   any subsequent delay() loop can begin execution on the same thread.
+	   This ensures that two MMIO register writes by the CPU to a peripheral
+	   will arrive at least 1us apart if the first write is immediately read
+	   back with readX() and udelay(1) is called prior to the second
+	   writeX():
+
+		writel(42, DEVICE_REGISTER_0); // Arrives at the device...
+		readl(DEVICE_REGISTER_0);
+		udelay(1);
+		writel(42, DEVICE_REGISTER_1); // ...at least 1us before this.
+
+	The ordering properties of __iomem pointers obtained with non-default
+	attributes (e.g. those returned by ioremap_wc()) are specific to the
+	underlying architecture and therefore the guarantees listed above cannot
+	generally be relied upon for accesses to these types of mappings.
+
+ (*) readX_relaxed(), writeX_relaxed():
+
+	These are similar to readX() and writeX(), but provide weaker memory
+	ordering guarantees. Specifically, they do not guarantee ordering with
+	respect to locking, normal memory accesses or delay() loops (i.e.
+	bullets 2-5 above) but they are still guaranteed to be ordered with
+	respect to other accesses from the same CPU thread to the same
+	peripheral when operating on __iomem pointers mapped with the default
+	I/O attributes.
+
+ (*) readsX(), writesX():
+
+	The readsX() and writesX() MMIO accessors are designed for accessing
+	register-based, memory-mapped FIFOs residing on peripherals that are not
+	capable of performing DMA. Consequently, they provide only the ordering
+	guarantees of readX_relaxed() and writeX_relaxed(), as documented above.
 
-     Ordinarily, these will be guaranteed to be fully ordered and uncombined,
-     provided they're not accessing a prefetchable device.
+ (*) inX(), outX():
 
-     However, intermediary hardware (such as a PCI bridge) may indulge in
-     deferral if it so wishes; to flush a store, a load from the same location
-     is preferred[*], but a load from the same device or from configuration
-     space should suffice for PCI.
+	The inX() and outX() accessors are intended to access legacy port-mapped
+	I/O peripherals, which may require special instructions on some
+	architectures (notably x86). The port number of the peripheral being
+	accessed is passed as an argument.
 
-     [*] NOTE! attempting to load from the same location as was written to may
-	 cause a malfunction - consider the 16550 Rx/Tx serial registers for
-	 example.
+	Since many CPU architectures ultimately access these peripherals via an
+	internal virtual memory mapping, the portable ordering guarantees
+	provided by inX() and outX() are the same as those provided by readX()
+	and writeX() respectively when accessing a mapping with the default I/O
+	attributes.
 
-     Used with prefetchable I/O memory, an mmiowb() barrier may be required to
-     force stores to be ordered.
+	Device drivers may expect outX() to emit a non-posted write transaction
+	that waits for a completion response from the I/O peripheral before
+	returning. This is not guaranteed by all architectures and is therefore
+	not part of the portable ordering semantics.
 
-     Please refer to the PCI specification for more information on interactions
-     between PCI transactions.
+ (*) insX(), outsX():
 
- (*) readX_relaxed(), writeX_relaxed()
+	As above, the insX() and outsX() accessors provide the same ordering
+	guarantees as readsX() and writesX() respectively when accessing a
+	mapping with the default I/O attributes.
 
-     These are similar to readX() and writeX(), but provide weaker memory
-     ordering guarantees.  Specifically, they do not guarantee ordering with
-     respect to normal memory accesses (e.g. DMA buffers) nor do they guarantee
-     ordering with respect to LOCK or UNLOCK operations.  If the latter is
-     required, an mmiowb() barrier can be used.  Note that relaxed accesses to
-     the same peripheral are guaranteed to be ordered with respect to each
-     other.
+ (*) ioreadX(), iowriteX():
 
- (*) ioreadX(), iowriteX()
+	These will perform appropriately for the type of access they're actually
+	doing, be it inX()/outX() or readX()/writeX().
 
-     These will perform appropriately for the type of access they're actually
-     doing, be it inX()/outX() or readX()/writeX().
+With the exception of the string accessors (insX(), outsX(), readsX() and
+writesX()), all of the above assume that the underlying peripheral is
+little-endian and will therefore perform byte-swapping operations on big-endian
+architectures.
 
 
 ========================================
diff --git a/Documentation/networking/bpf_flow_dissector.rst b/Documentation/networking/bpf_flow_dissector.rst
new file mode 100644
index 000000000000..b375ae2ec2c4
--- /dev/null
+++ b/Documentation/networking/bpf_flow_dissector.rst
@@ -0,0 +1,126 @@
+.. SPDX-License-Identifier: GPL-2.0
+
+==================
+BPF Flow Dissector
+==================
+
+Overview
+========
+
+Flow dissector is a routine that parses metadata out of the packets. It's
+used in the various places in the networking subsystem (RFS, flow hash, etc).
+
+BPF flow dissector is an attempt to reimplement C-based flow dissector logic
+in BPF to gain all the benefits of BPF verifier (namely, limits on the
+number of instructions and tail calls).
+
+API
+===
+
+BPF flow dissector programs operate on an ``__sk_buff``. However, only the
+limited set of fields is allowed: ``data``, ``data_end`` and ``flow_keys``.
+``flow_keys`` is ``struct bpf_flow_keys`` and contains flow dissector input
+and output arguments.
+
+The inputs are:
+  * ``nhoff`` - initial offset of the networking header
+  * ``thoff`` - initial offset of the transport header, initialized to nhoff
+  * ``n_proto`` - L3 protocol type, parsed out of L2 header
+
+Flow dissector BPF program should fill out the rest of the ``struct
+bpf_flow_keys`` fields. Input arguments ``nhoff/thoff/n_proto`` should be
+also adjusted accordingly.
+
+The return code of the BPF program is either BPF_OK to indicate successful
+dissection, or BPF_DROP to indicate parsing error.
+
+__sk_buff->data
+===============
+
+In the VLAN-less case, this is what the initial state of the BPF flow
+dissector looks like::
+
+  +------+------+------------+-----------+
+  | DMAC | SMAC | ETHER_TYPE | L3_HEADER |
+  +------+------+------------+-----------+
+                              ^
+                              |
+                              +-- flow dissector starts here
+
+
+.. code:: c
+
+  skb->data + flow_keys->nhoff point to the first byte of L3_HEADER
+  flow_keys->thoff = nhoff
+  flow_keys->n_proto = ETHER_TYPE
+
+In case of VLAN, flow dissector can be called with the two different states.
+
+Pre-VLAN parsing::
+
+  +------+------+------+-----+-----------+-----------+
+  | DMAC | SMAC | TPID | TCI |ETHER_TYPE | L3_HEADER |
+  +------+------+------+-----+-----------+-----------+
+                        ^
+                        |
+                        +-- flow dissector starts here
+
+.. code:: c
+
+  skb->data + flow_keys->nhoff point the to first byte of TCI
+  flow_keys->thoff = nhoff
+  flow_keys->n_proto = TPID
+
+Please note that TPID can be 802.1AD and, hence, BPF program would
+have to parse VLAN information twice for double tagged packets.
+
+
+Post-VLAN parsing::
+
+  +------+------+------+-----+-----------+-----------+
+  | DMAC | SMAC | TPID | TCI |ETHER_TYPE | L3_HEADER |
+  +------+------+------+-----+-----------+-----------+
+                                          ^
+                                          |
+                                          +-- flow dissector starts here
+
+.. code:: c
+
+  skb->data + flow_keys->nhoff point the to first byte of L3_HEADER
+  flow_keys->thoff = nhoff
+  flow_keys->n_proto = ETHER_TYPE
+
+In this case VLAN information has been processed before the flow dissector
+and BPF flow dissector is not required to handle it.
+
+
+The takeaway here is as follows: BPF flow dissector program can be called with
+the optional VLAN header and should gracefully handle both cases: when single
+or double VLAN is present and when it is not present. The same program
+can be called for both cases and would have to be written carefully to
+handle both cases.
+
+
+Reference Implementation
+========================
+
+See ``tools/testing/selftests/bpf/progs/bpf_flow.c`` for the reference
+implementation and ``tools/testing/selftests/bpf/flow_dissector_load.[hc]``
+for the loader. bpftool can be used to load BPF flow dissector program as well.
+
+The reference implementation is organized as follows:
+  * ``jmp_table`` map that contains sub-programs for each supported L3 protocol
+  * ``_dissect`` routine - entry point; it does input ``n_proto`` parsing and
+    does ``bpf_tail_call`` to the appropriate L3 handler
+
+Since BPF at this point doesn't support looping (or any jumping back),
+jmp_table is used instead to handle multiple levels of encapsulation (and
+IPv6 options).
+
+
+Current Limitations
+===================
+BPF flow dissector doesn't support exporting all the metadata that in-kernel
+C-based implementation can export. Notable example is single VLAN (802.1Q)
+and double VLAN (802.1AD) tags. Please refer to the ``struct bpf_flow_keys``
+for a set of information that's currently can be exported from the BPF context.
diff --git a/Documentation/networking/decnet.txt b/Documentation/networking/decnet.txt
index e12a4900cf72..d192f8b9948b 100644
--- a/Documentation/networking/decnet.txt
+++ b/Documentation/networking/decnet.txt
@@ -22,8 +22,6 @@ you'll need the following options as well...
     CONFIG_DECNET_ROUTER (to be able to add/delete routes)
     CONFIG_NETFILTER (will be required for the DECnet routing daemon)
 
-    CONFIG_DECNET_ROUTE_FWMARK is optional
-
 Don't turn on SIOCGIFCONF support for DECnet unless you are really sure
 that you need it, in general you won't and it can cause ifconfig to
 malfunction.
diff --git a/Documentation/networking/index.rst b/Documentation/networking/index.rst
index 5449149be496..984e68f9e026 100644
--- a/Documentation/networking/index.rst
+++ b/Documentation/networking/index.rst
@@ -9,6 +9,7 @@ Contents:
    netdev-FAQ
    af_xdp
    batman-adv
+   bpf_flow_dissector
    can
    can_ucan_protocol
    device_drivers/freescale/dpaa2/index
diff --git a/Documentation/networking/ip-sysctl.txt b/Documentation/networking/ip-sysctl.txt
index acdfb5d2bcaa..c4ac35234f05 100644
--- a/Documentation/networking/ip-sysctl.txt
+++ b/Documentation/networking/ip-sysctl.txt
@@ -422,6 +422,7 @@ tcp_min_rtt_wlen - INTEGER
 	minimum RTT when it is moved to a longer path (e.g., due to traffic
 	engineering). A longer window makes the filter more resistant to RTT
 	inflations such as transient congestion. The unit is seconds.
+	Possible values: 0 - 86400 (1 day)
 	Default: 300
 
 tcp_moderate_rcvbuf - BOOLEAN
@@ -1336,6 +1337,7 @@ tag - INTEGER
 	Default value is 0.
 
 xfrm4_gc_thresh - INTEGER
+	(Obsolete since linux-4.14)
 	The threshold at which we will start garbage collecting for IPv4
 	destination cache entries.  At twice this value the system will
 	refuse new allocations.
@@ -1919,6 +1921,7 @@ echo_ignore_all - BOOLEAN
 	Default: 0
 
 xfrm6_gc_thresh - INTEGER
+	(Obsolete since linux-4.14)
 	The threshold at which we will start garbage collecting for IPv6
 	destination cache entries.  At twice this value the system will
 	refuse new allocations.
diff --git a/Documentation/networking/msg_zerocopy.rst b/Documentation/networking/msg_zerocopy.rst
index 18c1415e7bfa..ace56204dd03 100644
--- a/Documentation/networking/msg_zerocopy.rst
+++ b/Documentation/networking/msg_zerocopy.rst
@@ -50,7 +50,7 @@ the excellent reporting over at LWN.net or read the original code.
 
   patchset
     [PATCH net-next v4 0/9] socket sendmsg MSG_ZEROCOPY
-    http://lkml.kernel.org/r/20170803202945.70750-1-willemdebruijn.kernel@gmail.com
+    https://lkml.kernel.org/netdev/20170803202945.70750-1-willemdebruijn.kernel@gmail.com
 
 
 Interface
diff --git a/Documentation/networking/netdev-FAQ.rst b/Documentation/networking/netdev-FAQ.rst
index 0ac5fa77f501..642fa963be3c 100644
--- a/Documentation/networking/netdev-FAQ.rst
+++ b/Documentation/networking/netdev-FAQ.rst
@@ -131,6 +131,19 @@ it to the maintainer to figure out what is the most recent and current
 version that should be applied. If there is any doubt, the maintainer
 will reply and ask what should be done.
 
+Q: I made changes to only a few patches in a patch series should I resend only those changed?
+---------------------------------------------------------------------------------------------
+A: No, please resend the entire patch series and make sure you do number your
+patches such that it is clear this is the latest and greatest set of patches
+that can be applied.
+
+Q: I submitted multiple versions of a patch series and it looks like a version other than the last one has been accepted, what should I do?
+-------------------------------------------------------------------------------------------------------------------------------------------
+A: There is no revert possible, once it is pushed out, it stays like that.
+Please send incremental versions on top of what has been merged in order to fix
+the patches the way they would look like if your latest patch series was to be
+merged.
+
 Q: How can I tell what patches are queued up for backporting to the various stable releases?
 --------------------------------------------------------------------------------------------
 A: Normally Greg Kroah-Hartman collects stable commits himself, but for
diff --git a/Documentation/networking/nf_flowtable.txt b/Documentation/networking/nf_flowtable.txt
index 54128c50d508..ca2136c76042 100644
--- a/Documentation/networking/nf_flowtable.txt
+++ b/Documentation/networking/nf_flowtable.txt
@@ -44,10 +44,10 @@ including the Netfilter hooks and the flowtable fastpath bypass.
      /         \    /          \     |Routing |   /            \
   -->  ingress  ---> prerouting ---> |decision|   | postrouting |--> neigh_xmit
      \_________/    \__________/     ----------   \____________/          ^
-       |      ^          |               |               ^                |
-   flowtable  |          |          ____\/___            |                |
-       |      |          |         /         \           |                |
-    __\/___   |          --------->| forward |------------                |
+       |      ^                          |               ^                |
+   flowtable  |                     ____\/___            |                |
+       |      |                    /         \           |                |
+    __\/___   |                    | forward |------------                |
     |-----|   |                    \_________/                            |
     |-----|   |                 'flow offload' rule                       |
     |-----|   |                   adds entry to                           |
diff --git a/Documentation/networking/rxrpc.txt b/Documentation/networking/rxrpc.txt
index 2df5894353d6..cd7303d7fa25 100644
--- a/Documentation/networking/rxrpc.txt
+++ b/Documentation/networking/rxrpc.txt
@@ -1009,16 +1009,18 @@ The kernel interface functions are as follows:
 
  (*) Check call still alive.
 
-	u32 rxrpc_kernel_check_life(struct socket *sock,
-				    struct rxrpc_call *call);
+	bool rxrpc_kernel_check_life(struct socket *sock,
+				     struct rxrpc_call *call,
+				     u32 *_life);
 	void rxrpc_kernel_probe_life(struct socket *sock,
 				     struct rxrpc_call *call);
 
-     The first function returns a number that is updated when ACKs are received
-     from the peer (notably including PING RESPONSE ACKs which we can elicit by
-     sending PING ACKs to see if the call still exists on the server).  The
-     caller should compare the numbers of two calls to see if the call is still
-     alive after waiting for a suitable interval.
+     The first function passes back in *_life a number that is updated when
+     ACKs are received from the peer (notably including PING RESPONSE ACKs
+     which we can elicit by sending PING ACKs to see if the call still exists
+     on the server).  The caller should compare the numbers of two calls to see
+     if the call is still alive after waiting for a suitable interval.  It also
+     returns true as long as the call hasn't yet reached the completed state.
 
      This allows the caller to work out if the server is still contactable and
      if the call is still alive on the server while waiting for the server to
diff --git a/Documentation/networking/snmp_counter.rst b/Documentation/networking/snmp_counter.rst
index 52b026be028f..38a4edc4522b 100644
--- a/Documentation/networking/snmp_counter.rst
+++ b/Documentation/networking/snmp_counter.rst
@@ -413,7 +413,7 @@ algorithm.
 .. _F-RTO: https://tools.ietf.org/html/rfc5682
 
 TCP Fast Path
-============
+=============
 When kernel receives a TCP packet, it has two paths to handler the
 packet, one is fast path, another is slow path. The comment in kernel
 code provides a good explanation of them, I pasted them below::
@@ -681,6 +681,7 @@ The TCP stack receives an out of order duplicate packet, so it sends a
 DSACK to the sender.
 
 * TcpExtTCPDSACKRecv
+
 The TCP stack receives a DSACK, which indicates an acknowledged
 duplicate packet is received.
 
@@ -690,7 +691,7 @@ The TCP stack receives a DSACK, which indicate an out of order
 duplicate packet is received.
 
 invalid SACK and DSACK
-====================
+======================
 When a SACK (or DSACK) block is invalid, a corresponding counter would
 be updated. The validation method is base on the start/end sequence
 number of the SACK block. For more details, please refer the comment
@@ -704,11 +705,13 @@ explaination:
 .. _Add counters for discarded SACK blocks: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?id=18f02545a9a16c9a89778b91a162ad16d510bb32
 
 * TcpExtTCPSACKDiscard
+
 This counter indicates how many SACK blocks are invalid. If the invalid
 SACK block is caused by ACK recording, the TCP stack will only ignore
 it and won't update this counter.
 
 * TcpExtTCPDSACKIgnoredOld and TcpExtTCPDSACKIgnoredNoUndo
+
 When a DSACK block is invalid, one of these two counters would be
 updated. Which counter will be updated depends on the undo_marker flag
 of the TCP socket. If the undo_marker is not set, the TCP stack isn't
@@ -719,7 +722,7 @@ will be updated. If the undo_marker is set, TcpExtTCPDSACKIgnoredOld
 will be updated. As implied in its name, it might be an old packet.
 
 SACK shift
-=========
+==========
 The linux networking stack stores data in sk_buff struct (skb for
 short). If a SACK block acrosses multiple skb, the TCP stack will try
 to re-arrange data in these skb. E.g. if a SACK block acknowledges seq
@@ -730,12 +733,15 @@ seq 14 to 20. All data in skb2 will be moved to skb1, and skb2 will be
 discard, this operation is 'merge'.
 
 * TcpExtTCPSackShifted
+
 A skb is shifted
 
 * TcpExtTCPSackMerged
+
 A skb is merged
 
 * TcpExtTCPSackShiftFallback
+
 A skb should be shifted or merged, but the TCP stack doesn't do it for
 some reasons.
 
diff --git a/Documentation/robust-futexes.txt b/Documentation/robust-futexes.txt
index 6c42c75103eb..6361fb01c9c1 100644
--- a/Documentation/robust-futexes.txt
+++ b/Documentation/robust-futexes.txt
@@ -218,5 +218,4 @@ All other architectures should build just fine too - but they won't have
 the new syscalls yet.
 
 Architectures need to implement the new futex_atomic_cmpxchg_inatomic()
-inline function before writing up the syscalls (that function returns
--ENOSYS right now).
+inline function before writing up the syscalls.
diff --git a/Documentation/spi/spi-summary b/Documentation/spi/spi-summary
index 1721c1b570c3..1a63194b74d7 100644
--- a/Documentation/spi/spi-summary
+++ b/Documentation/spi/spi-summary
@@ -572,6 +572,12 @@ SPI MASTER METHODS
 	0: transfer is finished
 	1: transfer is still in progress
 
+    master->set_cs_timing(struct spi_device *spi, u8 setup_clk_cycles,
+			      u8 hold_clk_cycles, u8 inactive_clk_cycles)
+	This method allows SPI client drivers to request SPI master controller
+	for configuring device specific CS setup, hold and inactive timing
+	requirements.
+
     DEPRECATED METHODS
 
     master->transfer(struct spi_device *spi, struct spi_message *message)
diff --git a/Documentation/sysctl/vm.txt b/Documentation/sysctl/vm.txt
index 6af24cdb25cc..3f13d8599337 100644
--- a/Documentation/sysctl/vm.txt
+++ b/Documentation/sysctl/vm.txt
@@ -866,14 +866,14 @@ The intent is that compaction has less work to do in the future and to
 increase the success rate of future high-order allocations such as SLUB
 allocations, THP and hugetlbfs pages.
 
-To make it sensible with respect to the watermark_scale_factor parameter,
-the unit is in fractions of 10,000. The default value of 15,000 means
-that up to 150% of the high watermark will be reclaimed in the event of
-a pageblock being mixed due to fragmentation. The level of reclaim is
-determined by the number of fragmentation events that occurred in the
-recent past. If this value is smaller than a pageblock then a pageblocks
-worth of pages will be reclaimed (e.g.  2MB on 64-bit x86). A boost factor
-of 0 will disable the feature.
+To make it sensible with respect to the watermark_scale_factor
+parameter, the unit is in fractions of 10,000. The default value of
+15,000 on !DISCONTIGMEM configurations means that up to 150% of the high
+watermark will be reclaimed in the event of a pageblock being mixed due
+to fragmentation. The level of reclaim is determined by the number of
+fragmentation events that occurred in the recent past. If this value is
+smaller than a pageblock then a pageblocks worth of pages will be reclaimed
+(e.g.  2MB on 64-bit x86). A boost factor of 0 will disable the feature.
 
 =============================================================
 
diff --git a/Documentation/thermal/sysfs-api.txt b/Documentation/thermal/sysfs-api.txt
index 911399730c1c..c3fa500df92c 100644
--- a/Documentation/thermal/sysfs-api.txt
+++ b/Documentation/thermal/sysfs-api.txt
@@ -316,7 +316,7 @@ ACPI thermal zones.
     |---temp[1-*]_input:	The current temperature of thermal zone [1-*]
     |---temp[1-*]_critical:	The critical trip point of thermal zone [1-*]
 
-Please read Documentation/hwmon/sysfs-interface for additional information.
+Please read Documentation/hwmon/sysfs-interface.rst for additional information.
 
 ***************************
 * Thermal zone attributes *
diff --git a/Documentation/translations/ko_KR/memory-barriers.txt b/Documentation/translations/ko_KR/memory-barriers.txt
index 7f01fb1c1084..db0b9d8619f1 100644
--- a/Documentation/translations/ko_KR/memory-barriers.txt
+++ b/Documentation/translations/ko_KR/memory-barriers.txt
@@ -493,10 +493,8 @@ CPU �게 기대할 수 있는 최소한� 보장사항 몇가지가 있습니
      � 타입� 오�레�션� 단방향� 투과성 배리어처럼 �작합니다.  ACQUIRE
      오�레�션 뒤� 모든 메모리 오�레�션들� ACQUIRE 오�레�션 후�
      �어난 것으로 시스템� 나머지 컴�넌트들� 보�게 � 것� 보장�니다.
-     LOCK 오�레�션과 smp_load_acquire(), smp_cond_acquire() 오�레�션�
-     ACQUIRE 오�레�션� �함�니다.  smp_cond_acquire() 오�레�션� 컨트롤
-     �존성과 smp_rmb() 를 사용해서 ACQUIRE � �미� 요구사항(semantic)�
-     충족시킵니다.
+     LOCK 오�레�션과 smp_load_acquire(), smp_cond_load_acquire() 오�레�션�
+     ACQUIRE 오�레�션� �함�니다.
 
      ACQUIRE 오�레�션 앞� 메모리 오�레�션들� ACQUIRE 오�레�션 완료 후�
      수행� 것처럼 보� 수 있습니다.
@@ -2146,33 +2144,40 @@ set_current_state() 는 다�� 것들로 �싸질 수� 있습니다:
 	event_indicated = 1;
 	wake_up_process(event_daemon);
 
-wake_up() 류� �해 쓰기 메모리 배리어가 내��니다.  만약 그것들� 뭔가를
-깨운다면요.  � 배리어는 태스� �태가 지워지기 전� 수행�므로, �벤트를
-알리기 위한 STORE 와 태스� �태를 TASK_RUNNING 으로 설정하는 STORE 사��
-위치하게 �니다.
+wake_up() � 무언가를 깨우게 �면, � 함수는 범용 메모리 배리어를 수행합니다.
+� 함수가 아무것� 깨우지 않는다면 메모리 배리어는 수행� 수�, 수행�지 않�
+수� 있습니다; � 경우� 메모리 배리어를 수행할 거� 오해해선 안�니다.  �
+배리어는 태스� �태가 접근�기 전� 수행�는�, �세히 �하면 � �벤트를
+알리기 위한 STORE 와 TASK_RUNNING 으로 �태를 쓰는 STORE 사�� 수행�니다:
 
-	CPU 1				CPU 2
+	CPU 1 (Sleeper)			CPU 2 (Waker)
 	===============================	===============================
 	set_current_state();		STORE event_indicated
 	  smp_store_mb();		wake_up();
-	    STORE current->state	  <쓰기 배리어>
-	    <범용 배리어>		  STORE current->state
-	LOAD event_indicated
+	    STORE current->state	  ...
+	    <범용 배리어>		  <범용 배리어>
+	LOAD event_indicated		  if ((LOAD task->state) & TASK_NORMAL)
+					    STORE task->state
 
-한번� �합니다만, � 쓰기 메모리 배리어는 � 코드가 정�로 뭔가를 깨울 때�만
-실행�니다.  �걸 설명하기 위해, X 와 Y 는 모� 0 으로 초기화 �어 있다는 가정
-하� 아래� �벤트 시퀀스를 ��해 봅시다:
+여기서 "task" 는 깨어나지는 쓰레드�고 CPU 1 � "current" 와 같습니다.
+
+반복하지만, wake_up() � 무언가를 정� 깨운다면 범용 메모리 배리어가 수행�
+것� 보장�지만, 그렇지 않다면 그런 보장� 없습니다.  �걸 �해하기 위해, X 와
+Y 는 모� 0 으로 초기화 �어 있다는 가정 하� 아래� �벤트 시퀀스를 ��해
+봅시다:
 
 	CPU 1				CPU 2
 	===============================	===============================
-	X = 1;				STORE event_indicated
+	X = 1;				Y = 1;
 	smp_mb();			wake_up();
-	Y = 1;				wait_event(wq, Y == 1);
-	wake_up();			  load from Y sees 1, no memory barrier
-					load from X might see 0
+	LOAD Y				LOAD X
+
+정�로 깨우기가 행해졌다면, � 로드 중 (최소한) 하나는 1 � 보게 �니다.
+반면�, 실제 깨우기가 행해지지 않았다면, � 로드 모� 0� 볼 수� 있습니다.
 
-위 예제�서� 경우와 달리 깨우기가 정�로 행해졌다면, CPU 2 � X 로드는 1 �
-본다고 보장� 수 있� �니다.
+wake_up_process() 는 항� 범용 메모리 배리어를 수행합니다.  � 배리어 역시
+태스� �태가 접근�기 전� 수행�니다.  특히, 앞� 예제 코드�서 wake_up() �
+wake_up_process() 로 대체�다면 � 로드 중 하나는 1� 볼 것� 보장�니다.
 
 사용 가능한 깨우기류 함수들로 다�과 같� 것들� 있습니다:
 
@@ -2192,6 +2197,8 @@ wake_up() 류ì—� ì�˜í•´ 쓰기 메모리 배리어가 ë‚´í�¬ë�©ë‹ˆë‹¤.  만약 ê
 	wake_up_poll();
 	wake_up_process();
 
+메모리 순서규칙 관��서, � 함수들� 모� wake_up() 과 같거나 보다 강한 순서
+보장� 제공합니다.
 
 [!] 잠재우는 코드와 깨우는 코드� 내��는 메모리 배리어들� 깨우기 전�
 �루어진 스토어를 잠재우는 코드가 set_current_state() 를 호출한 후� 행하는
diff --git a/Documentation/virtual/kvm/api.txt b/Documentation/virtual/kvm/api.txt
index 7de9eee73fcd..64b38dfcc243 100644
--- a/Documentation/virtual/kvm/api.txt
+++ b/Documentation/virtual/kvm/api.txt
@@ -5,25 +5,32 @@ The Definitive KVM (Kernel-based Virtual Machine) API Documentation
 ----------------------
 
 The kvm API is a set of ioctls that are issued to control various aspects
-of a virtual machine.  The ioctls belong to three classes
+of a virtual machine.  The ioctls belong to three classes:
 
  - System ioctls: These query and set global attributes which affect the
    whole kvm subsystem.  In addition a system ioctl is used to create
-   virtual machines
+   virtual machines.
 
  - VM ioctls: These query and set attributes that affect an entire virtual
    machine, for example memory layout.  In addition a VM ioctl is used to
-   create virtual cpus (vcpus).
+   create virtual cpus (vcpus) and devices.
 
-   Only run VM ioctls from the same process (address space) that was used
-   to create the VM.
+   VM ioctls must be issued from the same process (address space) that was
+   used to create the VM.
 
  - vcpu ioctls: These query and set attributes that control the operation
    of a single virtual cpu.
 
-   Only run vcpu ioctls from the same thread that was used to create the
-   vcpu.
+   vcpu ioctls should be issued from the same thread that was used to create
+   the vcpu, except for asynchronous vcpu ioctl that are marked as such in
+   the documentation.  Otherwise, the first ioctl after switching threads
+   could see a performance impact.
 
+ - device ioctls: These query and set attributes that control the operation
+   of a single device.
+
+   device ioctls must be issued from the same process (address space) that
+   was used to create the VM.
 
 2. File descriptors
 -------------------
@@ -32,17 +39,34 @@ The kvm API is centered around file descriptors.  An initial
 open("/dev/kvm") obtains a handle to the kvm subsystem; this handle
 can be used to issue system ioctls.  A KVM_CREATE_VM ioctl on this
 handle will create a VM file descriptor which can be used to issue VM
-ioctls.  A KVM_CREATE_VCPU ioctl on a VM fd will create a virtual cpu
-and return a file descriptor pointing to it.  Finally, ioctls on a vcpu
-fd can be used to control the vcpu, including the important task of
-actually running guest code.
+ioctls.  A KVM_CREATE_VCPU or KVM_CREATE_DEVICE ioctl on a VM fd will
+create a virtual cpu or device and return a file descriptor pointing to
+the new resource.  Finally, ioctls on a vcpu or device fd can be used
+to control the vcpu or device.  For vcpus, this includes the important
+task of actually running guest code.
 
 In general file descriptors can be migrated among processes by means
 of fork() and the SCM_RIGHTS facility of unix domain socket.  These
 kinds of tricks are explicitly not supported by kvm.  While they will
 not cause harm to the host, their actual behavior is not guaranteed by
-the API.  The only supported use is one virtual machine per process,
-and one vcpu per thread.
+the API.  See "General description" for details on the ioctl usage
+model that is supported by KVM.
+
+It is important to note that althought VM ioctls may only be issued from
+the process that created the VM, a VM's lifecycle is associated with its
+file descriptor, not its creator (process).  In other words, the VM and
+its resources, *including the associated address space*, are not freed
+until the last reference to the VM's file descriptor has been released.
+For example, if fork() is issued after ioctl(KVM_CREATE_VM), the VM will
+not be freed until both the parent (original) process and its child have
+put their references to the VM's file descriptor.
+
+Because a VM's resources are not freed until the last reference to its
+file descriptor is released, creating additional references to a VM via
+via fork(), dup(), etc... without careful consideration is strongly
+discouraged and may have unwanted side effects, e.g. memory allocated
+by and on behalf of the VM's process may not be freed/unaccounted when
+the VM is shut down.
 
 
 It is important to note that althought VM ioctls may only be issued from
@@ -297,7 +321,7 @@ cpu's hardware control block.
 4.8 KVM_GET_DIRTY_LOG (vm ioctl)
 
 Capability: basic
-Architectures: x86
+Architectures: all
 Type: vm ioctl
 Parameters: struct kvm_dirty_log (in/out)
 Returns: 0 on success, -1 on error
@@ -515,11 +539,15 @@ c) KVM_INTERRUPT_SET_LEVEL
 Note that any value for 'irq' other than the ones stated above is invalid
 and incurs unexpected behavior.
 
+This is an asynchronous vcpu ioctl and can be invoked from any thread.
+
 MIPS:
 
 Queues an external interrupt to be injected into the virtual CPU. A negative
 interrupt number dequeues the interrupt.
 
+This is an asynchronous vcpu ioctl and can be invoked from any thread.
+
 
 4.17 KVM_DEBUG_GUEST
 
@@ -1086,14 +1114,12 @@ struct kvm_userspace_memory_region {
 #define KVM_MEM_LOG_DIRTY_PAGES	(1UL << 0)
 #define KVM_MEM_READONLY	(1UL << 1)
 
-This ioctl allows the user to create or modify a guest physical memory
-slot.  When changing an existing slot, it may be moved in the guest
-physical memory space, or its flags may be modified.  It may not be
-resized.  Slots may not overlap in guest physical address space.
-Bits 0-15 of "slot" specifies the slot id and this value should be
-less than the maximum number of user memory slots supported per VM.
-The maximum allowed slots can be queried using KVM_CAP_NR_MEMSLOTS,
-if this capability is supported by the architecture.
+This ioctl allows the user to create, modify or delete a guest physical
+memory slot.  Bits 0-15 of "slot" specify the slot id and this value
+should be less than the maximum number of user memory slots supported per
+VM.  The maximum allowed slots can be queried using KVM_CAP_NR_MEMSLOTS,
+if this capability is supported by the architecture.  Slots may not
+overlap in guest physical address space.
 
 If KVM_CAP_MULTI_ADDRESS_SPACE is available, bits 16-31 of "slot"
 specifies the address space which is being modified.  They must be
@@ -1102,6 +1128,10 @@ KVM_CAP_MULTI_ADDRESS_SPACE capability.  Slots in separate address spaces
 are unrelated; the restriction on overlapping slots only applies within
 each address space.
 
+Deleting a slot is done by passing zero for memory_size.  When changing
+an existing slot, it may be moved in the guest physical memory space,
+or its flags may be modified, but it may not be resized.
+
 Memory for the region is taken starting at the address denoted by the
 field userspace_addr, which must point at user addressable memory for
 the entire memory slot size.  Any object may back this memory, including
@@ -2493,7 +2523,7 @@ KVM_S390_MCHK (vm, vcpu) - machine check interrupt; cr 14 bits in parm,
                            machine checks needing further payload are not
                            supported by this ioctl)
 
-Note that the vcpu ioctl is asynchronous to vcpu execution.
+This is an asynchronous vcpu ioctl and can be invoked from any thread.
 
 4.78 KVM_PPC_GET_HTAB_FD
 
@@ -3042,8 +3072,7 @@ KVM_S390_INT_EMERGENCY - sigp emergency; parameters in .emerg
 KVM_S390_INT_EXTERNAL_CALL - sigp external call; parameters in .extcall
 KVM_S390_MCHK - machine check interrupt; parameters in .mchk
 
-
-Note that the vcpu ioctl is asynchronous to vcpu execution.
+This is an asynchronous vcpu ioctl and can be invoked from any thread.
 
 4.94 KVM_S390_GET_IRQ_STATE
 
@@ -3781,7 +3810,7 @@ to I/O ports.
 4.117 KVM_CLEAR_DIRTY_LOG (vm ioctl)
 
 Capability: KVM_CAP_MANUAL_DIRTY_LOG_PROTECT
-Architectures: x86
+Architectures: x86, arm, arm64, mips
 Type: vm ioctl
 Parameters: struct kvm_dirty_log (in)
 Returns: 0 on success, -1 on error
@@ -3801,8 +3830,9 @@ The ioctl clears the dirty status of pages in a memory slot, according to
 the bitmap that is passed in struct kvm_clear_dirty_log's dirty_bitmap
 field.  Bit 0 of the bitmap corresponds to page "first_page" in the
 memory slot, and num_pages is the size in bits of the input bitmap.
-Both first_page and num_pages must be a multiple of 64.  For each bit
-that is set in the input bitmap, the corresponding page is marked "clean"
+first_page must be a multiple of 64; num_pages must also be a multiple of
+64 unless first_page + num_pages is the size of the memory slot.  For each
+bit that is set in the input bitmap, the corresponding page is marked "clean"
 in KVM's dirty bitmap, and dirty tracking is re-enabled for that page
 (for example via write-protection, or by clearing the dirty bit in
 a page table entry).
@@ -4770,7 +4800,7 @@ and injected exceptions.
 
 7.18 KVM_CAP_MANUAL_DIRTY_LOG_PROTECT
 
-Architectures: all
+Architectures: x86, arm, arm64, mips
 Parameters: args[0] whether feature should be enabled or not
 
 With this capability enabled, KVM_GET_DIRTY_LOG will not automatically
diff --git a/Documentation/virtual/kvm/mmu.txt b/Documentation/virtual/kvm/mmu.txt
index f365102c80f5..2efe0efc516e 100644
--- a/Documentation/virtual/kvm/mmu.txt
+++ b/Documentation/virtual/kvm/mmu.txt
@@ -142,7 +142,7 @@ Shadow pages contain the following information:
     If clear, this page corresponds to a guest page table denoted by the gfn
     field.
   role.quadrant:
-    When role.cr4_pae=0, the guest uses 32-bit gptes while the host uses 64-bit
+    When role.gpte_is_8_bytes=0, the guest uses 32-bit gptes while the host uses 64-bit
     sptes.  That means a guest page table contains more ptes than the host,
     so multiple shadow pages are needed to shadow one guest page.
     For first-level shadow pages, role.quadrant can be 0 or 1 and denotes the
@@ -158,9 +158,9 @@ Shadow pages contain the following information:
     The page is invalid and should not be used.  It is a root page that is
     currently pinned (by a cpu hardware register pointing to it); once it is
     unpinned it will be destroyed.
-  role.cr4_pae:
-    Contains the value of cr4.pae for which the page is valid (e.g. whether
-    32-bit or 64-bit gptes are in use).
+  role.gpte_is_8_bytes:
+    Reflects the size of the guest PTE for which the page is valid, i.e. '1'
+    if 64-bit gptes are in use, '0' if 32-bit gptes are in use.
   role.nxe:
     Contains the value of efer.nxe for which the page is valid.
   role.cr0_wp:
@@ -173,6 +173,9 @@ Shadow pages contain the following information:
     Contains the value of cr4.smap && !cr0.wp for which the page is valid
     (pages for which this is true are different from other pages; see the
     treatment of cr0.wp=0 below).
+  role.ept_sp:
+    This is a virtual flag to denote a shadowed nested EPT page.  ept_sp
+    is true if "cr0_wp && smap_andnot_wp", an otherwise invalid combination.
   role.smm:
     Is 1 if the page is valid in system management mode.  This field
     determines which of the kvm_memslots array was used to build this
diff --git a/Documentation/x86/kernel-stacks b/Documentation/x86/kernel-stacks
index 9a0aa4d3a866..d1bfb0b95ee0 100644
--- a/Documentation/x86/kernel-stacks
+++ b/Documentation/x86/kernel-stacks
@@ -59,7 +59,7 @@ If that assumption is ever broken then the stacks will become corrupt.
 
 The currently assigned IST stacks are :-
 
-* DOUBLEFAULT_STACK.  EXCEPTION_STKSZ (PAGE_SIZE).
+* ESTACK_DF.  EXCEPTION_STKSZ (PAGE_SIZE).
 
   Used for interrupt 8 - Double Fault Exception (#DF).
 
@@ -68,7 +68,7 @@ The currently assigned IST stacks are :-
   Using a separate stack allows the kernel to recover from it well enough
   in many cases to still output an oops.
 
-* NMI_STACK.  EXCEPTION_STKSZ (PAGE_SIZE).
+* ESTACK_NMI.  EXCEPTION_STKSZ (PAGE_SIZE).
 
   Used for non-maskable interrupts (NMI).
 
@@ -76,7 +76,7 @@ The currently assigned IST stacks are :-
   middle of switching stacks.  Using IST for NMI events avoids making
   assumptions about the previous state of the kernel stack.
 
-* DEBUG_STACK.  DEBUG_STKSZ
+* ESTACK_DB.  EXCEPTION_STKSZ (PAGE_SIZE).
 
   Used for hardware debug interrupts (interrupt 1) and for software
   debug interrupts (INT3).
@@ -86,7 +86,12 @@ The currently assigned IST stacks are :-
   avoids making assumptions about the previous state of the kernel
   stack.
 
-* MCE_STACK.  EXCEPTION_STKSZ (PAGE_SIZE).
+  To handle nested #DB correctly there exist two instances of DB stacks. On
+  #DB entry the IST stackpointer for #DB is switched to the second instance
+  so a nested #DB starts from a clean stack. The nested #DB switches
+  the IST stackpointer to a guard hole to catch triple nesting.
+
+* ESTACK_MCE.  EXCEPTION_STKSZ (PAGE_SIZE).
 
   Used for interrupt 18 - Machine Check Exception (#MC).
 
diff --git a/Documentation/x86/topology.txt b/Documentation/x86/topology.txt
index 2953e3ec9a02..06b3cdbc4048 100644
--- a/Documentation/x86/topology.txt
+++ b/Documentation/x86/topology.txt
@@ -51,7 +51,7 @@ The topology of a system is described in the units of:
     The physical ID of the package. This information is retrieved via CPUID
     and deduced from the APIC IDs of the cores in the package.
 
-  - cpuinfo_x86.logical_id:
+  - cpuinfo_x86.logical_proc_id:
 
     The logical ID of the package. As we do not trust BIOSes to enumerate the
     packages in a consistent way, we introduced the concept of logical package
diff --git a/Documentation/x86/x86_64/mm.txt b/Documentation/x86/x86_64/mm.txt
index 804f9426ed17..6cbe652d7a49 100644
--- a/Documentation/x86/x86_64/mm.txt
+++ b/Documentation/x86/x86_64/mm.txt
@@ -72,7 +72,7 @@ Complete virtual memory map with 5-level page tables
 Notes:
 
  - With 56-bit addresses, user-space memory gets expanded by a factor of 512x,
-   from 0.125 PB to 64 PB. All kernel mappings shift down to the -64 PT starting
+   from 0.125 PB to 64 PB. All kernel mappings shift down to the -64 PB starting
    offset and many of the regions expand to support the much larger physical
    memory supported.
 
@@ -83,7 +83,7 @@ Notes:
  0000000000000000 |    0       | 00ffffffffffffff |   64 PB | user-space virtual memory, different per mm
 __________________|____________|__________________|_________|___________________________________________________________
                   |            |                  |         |
- 0000800000000000 |  +64    PB | ffff7fffffffffff | ~16K PB | ... huge, still almost 64 bits wide hole of non-canonical
+ 0100000000000000 |  +64    PB | feffffffffffffff | ~16K PB | ... huge, still almost 64 bits wide hole of non-canonical
                   |            |                  |         |     virtual memory addresses up to the -64 PB
                   |            |                  |         |     starting offset of kernel mappings.
 __________________|____________|__________________|_________|___________________________________________________________
@@ -99,7 +99,7 @@ ____________________________________________________________|___________________
  ffd2000000000000 |  -11.5  PB | ffd3ffffffffffff |  0.5 PB | ... unused hole
  ffd4000000000000 |  -11    PB | ffd5ffffffffffff |  0.5 PB | virtual memory map (vmemmap_base)
  ffd6000000000000 |  -10.5  PB | ffdeffffffffffff | 2.25 PB | ... unused hole
- ffdf000000000000 |   -8.25 PB | fffffdffffffffff |   ~8 PB | KASAN shadow memory
+ ffdf000000000000 |   -8.25 PB | fffffbffffffffff |   ~8 PB | KASAN shadow memory
 __________________|____________|__________________|_________|____________________________________________________________
                                                             |
                                                             | Identical layout to the 47-bit one from here on:
diff --git a/MAINTAINERS b/MAINTAINERS
index 3e5a5d263f29..0a52061eacae 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -468,7 +468,7 @@ ADM1025 HARDWARE MONITOR DRIVER
 M:	Jean Delvare <jdelvare@suse.com>
 L:	linux-hwmon@vger.kernel.org
 S:	Maintained
-F:	Documentation/hwmon/adm1025
+F:	Documentation/hwmon/adm1025.rst
 F:	drivers/hwmon/adm1025.c
 
 ADM1029 HARDWARE MONITOR DRIVER
@@ -520,7 +520,7 @@ ADS1015 HARDWARE MONITOR DRIVER
 M:	Dirk Eibach <eibach@gdsys.de>
 L:	linux-hwmon@vger.kernel.org
 S:	Maintained
-F:	Documentation/hwmon/ads1015
+F:	Documentation/hwmon/ads1015.rst
 F:	drivers/hwmon/ads1015.c
 F:	include/linux/platform_data/ads1015.h
 
@@ -533,7 +533,7 @@ ADT7475 HARDWARE MONITOR DRIVER
 M:	Jean Delvare <jdelvare@suse.com>
 L:	linux-hwmon@vger.kernel.org
 S:	Maintained
-F:	Documentation/hwmon/adt7475
+F:	Documentation/hwmon/adt7475.rst
 F:	drivers/hwmon/adt7475.c
 
 ADVANSYS SCSI DRIVER
@@ -764,7 +764,7 @@ AMD FAM15H PROCESSOR POWER MONITORING DRIVER
 M:	Huang Rui <ray.huang@amd.com>
 L:	linux-hwmon@vger.kernel.org
 S:	Supported
-F:	Documentation/hwmon/fam15h_power
+F:	Documentation/hwmon/fam15h_power.rst
 F:	drivers/hwmon/fam15h_power.c
 
 AMD FCH GPIO DRIVER
@@ -1893,14 +1893,15 @@ T:	git git://git.kernel.org/pub/scm/linux/kernel/git/linusw/linux-nomadik.git
 ARM/NUVOTON NPCM ARCHITECTURE
 M:	Avi Fishman <avifishman70@gmail.com>
 M:	Tomer Maimon <tmaimon77@gmail.com>
+M:	Tali Perry <tali.perry1@gmail.com>
 R:	Patrick Venture <venture@google.com>
 R:	Nancy Yuen <yuenn@google.com>
-R:	Brendan Higgins <brendanhiggins@google.com>
+R:	Benjamin Fair <benjaminfair@google.com>
 L:	openbmc@lists.ozlabs.org (moderated for non-subscribers)
 S:	Supported
 F:	arch/arm/mach-npcm/
 F:	arch/arm/boot/dts/nuvoton-npcm*
-F:	include/dt-bindings/clock/nuvoton,npcm7xx-clks.h
+F:	include/dt-bindings/clock/nuvoton,npcm7xx-clock.h
 F:	drivers/*/*npcm*
 F:	Documentation/devicetree/bindings/*/*npcm*
 F:	Documentation/devicetree/bindings/*/*/*npcm*
@@ -2356,7 +2357,7 @@ F:	arch/arm/mm/cache-uniphier.c
 F:	arch/arm64/boot/dts/socionext/uniphier*
 F:	drivers/bus/uniphier-system-bus.c
 F:	drivers/clk/uniphier/
-F:	drivers/dmaengine/uniphier-mdmac.c
+F:	drivers/dma/uniphier-mdmac.c
 F:	drivers/gpio/gpio-uniphier.c
 F:	drivers/i2c/busses/i2c-uniphier*
 F:	drivers/irqchip/irq-uniphier-aidet.c
@@ -2512,7 +2513,7 @@ ASC7621 HARDWARE MONITOR DRIVER
 M:	George Joseph <george.joseph@fairview5.com>
 L:	linux-hwmon@vger.kernel.org
 S:	Maintained
-F:	Documentation/hwmon/asc7621
+F:	Documentation/hwmon/asc7621.rst
 F:	drivers/hwmon/asc7621.c
 
 ASPEED VIDEO ENGINE DRIVER
@@ -3120,6 +3121,7 @@ F:	drivers/cpufreq/bmips-cpufreq.c
 BROADCOM BMIPS MIPS ARCHITECTURE
 M:	Kevin Cernekee <cernekee@gmail.com>
 M:	Florian Fainelli <f.fainelli@gmail.com>
+L:	bcm-kernel-feedback-list@broadcom.com
 L:	linux-mips@vger.kernel.org
 T:	git git://github.com/broadcom/stblinux.git
 S:	Maintained
@@ -3796,6 +3798,7 @@ M:	Richard Fitzgerald <rf@opensource.cirrus.com>
 L:	patches@opensource.cirrus.com
 S:	Supported
 F:	drivers/clk/clk-lochnagar.c
+F:	drivers/hwmon/lochnagar-hwmon.c
 F:	drivers/mfd/lochnagar-i2c.c
 F:	drivers/pinctrl/cirrus/pinctrl-lochnagar.c
 F:	drivers/regulator/lochnagar-regulator.c
@@ -3804,8 +3807,10 @@ F:	include/dt-bindings/pinctrl/lochnagar.h
 F:	include/linux/mfd/lochnagar*
 F:	Documentation/devicetree/bindings/mfd/cirrus,lochnagar.txt
 F:	Documentation/devicetree/bindings/clock/cirrus,lochnagar.txt
+F:	Documentation/devicetree/bindings/hwmon/cirrus,lochnagar.txt
 F:	Documentation/devicetree/bindings/pinctrl/cirrus,lochnagar.txt
 F:	Documentation/devicetree/bindings/regulator/cirrus,lochnagar.txt
+F:	Documentation/hwmon/lochnagar
 
 CISCO FCOE HBA DRIVER
 M:	Satish Kharat <satishkh@cisco.com>
@@ -4043,7 +4048,7 @@ CORETEMP HARDWARE MONITORING DRIVER
 M:	Fenghua Yu <fenghua.yu@intel.com>
 L:	linux-hwmon@vger.kernel.org
 S:	Maintained
-F:	Documentation/hwmon/coretemp
+F:	Documentation/hwmon/coretemp.rst
 F:	drivers/hwmon/coretemp.c
 
 COSA/SRP SYNC SERIAL DRIVER
@@ -4129,7 +4134,7 @@ F:	drivers/cpuidle/*
 F:	include/linux/cpuidle.h
 
 CRAMFS FILESYSTEM
-M:	Nicolas Pitre <nico@linaro.org>
+M:	Nicolas Pitre <nico@fluxnic.net>
 S:	Maintained
 F:	Documentation/filesystems/cramfs.txt
 F:	fs/cramfs/
@@ -4551,6 +4556,7 @@ S:	Maintained
 F:	drivers/devfreq/
 F:	include/linux/devfreq.h
 F:	Documentation/devicetree/bindings/devfreq/
+F:	include/trace/events/devfreq.h
 
 DEVICE FREQUENCY EVENT (DEVFREQ-EVENT)
 M:	Chanwoo Choi <cw00.choi@samsung.com>
@@ -4598,7 +4604,7 @@ DIALOG SEMICONDUCTOR DRIVERS
 M:	Support Opensource <support.opensource@diasemi.com>
 W:	http://www.dialog-semiconductor.com/products
 S:	Supported
-F:	Documentation/hwmon/da90??
+F:	Documentation/hwmon/da90??.rst
 F:	Documentation/devicetree/bindings/mfd/da90*.txt
 F:	Documentation/devicetree/bindings/input/da90??-onkey.txt
 F:	Documentation/devicetree/bindings/thermal/da90??-thermal.txt
@@ -4749,7 +4755,7 @@ DME1737 HARDWARE MONITOR DRIVER
 M:	Juerg Haefliger <juergh@gmail.com>
 L:	linux-hwmon@vger.kernel.org
 S:	Maintained
-F:	Documentation/hwmon/dme1737
+F:	Documentation/hwmon/dme1737.rst
 F:	drivers/hwmon/dme1737.c
 
 DMI/SMBIOS SUPPORT
@@ -5596,6 +5602,12 @@ L:	linux-edac@vger.kernel.org
 S:	Maintained
 F:	drivers/edac/ghes_edac.c
 
+EDAC-I10NM
+M:	Tony Luck <tony.luck@intel.com>
+L:	linux-edac@vger.kernel.org
+S:	Maintained
+F:	drivers/edac/i10nm_base.c
+
 EDAC-I3000
 L:	linux-edac@vger.kernel.org
 S:	Orphan
@@ -5677,7 +5689,7 @@ EDAC-SKYLAKE
 M:	Tony Luck <tony.luck@intel.com>
 L:	linux-edac@vger.kernel.org
 S:	Maintained
-F:	drivers/edac/skx_edac.c
+F:	drivers/edac/skx_*.c
 
 EDAC-TI
 M:	Tero Kristo <t-kristo@ti.com>
@@ -5833,7 +5845,7 @@ L:	netdev@vger.kernel.org
 S:	Maintained
 F:	Documentation/ABI/testing/sysfs-bus-mdio
 F:	Documentation/devicetree/bindings/net/mdio*
-F:	Documentation/networking/phy.txt
+F:	Documentation/networking/phy.rst
 F:	drivers/net/phy/
 F:	drivers/of/of_mdio.c
 F:	drivers/of/of_net.c
@@ -5935,7 +5947,7 @@ F71805F HARDWARE MONITORING DRIVER
 M:	Jean Delvare <jdelvare@suse.com>
 L:	linux-hwmon@vger.kernel.org
 S:	Maintained
-F:	Documentation/hwmon/f71805f
+F:	Documentation/hwmon/f71805f.rst
 F:	drivers/hwmon/f71805f.c
 
 FADDR2LINE
@@ -6408,7 +6420,6 @@ L:	linux-kernel@vger.kernel.org
 T:	git git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git locking/core
 S:	Maintained
 F:	kernel/futex.c
-F:	kernel/futex_compat.c
 F:	include/asm-generic/futex.h
 F:	include/linux/futex.h
 F:	include/uapi/linux/futex.h
@@ -6461,7 +6472,7 @@ S:	Maintained
 F:	drivers/media/radio/radio-gemtek*
 
 GENERIC GPIO I2C DRIVER
-M:	Haavard Skinnemoen <hskinnemoen@gmail.com>
+M:	Wolfram Sang <wsa+renesas@sang-engineering.com>
 S:	Supported
 F:	drivers/i2c/busses/i2c-gpio.c
 F:	include/linux/platform_data/i2c-gpio.h
@@ -6593,7 +6604,7 @@ M:	Andy Shevchenko <andriy.shevchenko@linux.intel.com>
 L:	linux-gpio@vger.kernel.org
 L:	linux-acpi@vger.kernel.org
 S:	Maintained
-F:	Documentation/acpi/gpio-properties.txt
+F:	Documentation/firmware-guide/acpi/gpio-properties.rst
 F:	drivers/gpio/gpiolib-acpi.c
 
 GPIO IR Transmitter
@@ -7333,7 +7344,6 @@ F:	Documentation/devicetree/bindings/i3c/
 F:	Documentation/driver-api/i3c
 F:	drivers/i3c/
 F:	include/linux/i3c/
-F:	include/dt-bindings/i3c/
 
 I3C DRIVER FOR SYNOPSYS DESIGNWARE
 M:	Vitor Soares <vitor.soares@synopsys.com>
@@ -7516,7 +7526,7 @@ F:	include/net/mac802154.h
 F:	include/net/af_ieee802154.h
 F:	include/net/cfg802154.h
 F:	include/net/ieee802154_netdev.h
-F:	Documentation/networking/ieee802154.txt
+F:	Documentation/networking/ieee802154.rst
 
 IFE PROTOCOL
 M:	Yotam Gigi <yotam.gi@gmail.com>
@@ -7618,7 +7628,7 @@ INA209 HARDWARE MONITOR DRIVER
 M:	Guenter Roeck <linux@roeck-us.net>
 L:	linux-hwmon@vger.kernel.org
 S:	Maintained
-F:	Documentation/hwmon/ina209
+F:	Documentation/hwmon/ina209.rst
 F:	Documentation/devicetree/bindings/hwmon/ina2xx.txt
 F:	drivers/hwmon/ina209.c
 
@@ -7626,7 +7636,7 @@ INA2XX HARDWARE MONITOR DRIVER
 M:	Guenter Roeck <linux@roeck-us.net>
 L:	linux-hwmon@vger.kernel.org
 S:	Maintained
-F:	Documentation/hwmon/ina2xx
+F:	Documentation/hwmon/ina2xx.rst
 F:	drivers/hwmon/ina2xx.c
 F:	include/linux/platform_data/ina2xx.h
 
@@ -8254,7 +8264,7 @@ IT87 HARDWARE MONITORING DRIVER
 M:	Jean Delvare <jdelvare@suse.com>
 L:	linux-hwmon@vger.kernel.org
 S:	Maintained
-F:	Documentation/hwmon/it87
+F:	Documentation/hwmon/it87.rst
 F:	drivers/hwmon/it87.c
 
 IT913X MEDIA DRIVER
@@ -8298,7 +8308,7 @@ M:	Guenter Roeck <linux@roeck-us.net>
 L:	linux-hwmon@vger.kernel.org
 S:	Maintained
 F:	drivers/hwmon/jc42.c
-F:	Documentation/hwmon/jc42
+F:	Documentation/hwmon/jc42.rst
 
 JFS FILESYSTEM
 M:	Dave Kleikamp <shaggy@kernel.org>
@@ -8346,14 +8356,14 @@ K10TEMP HARDWARE MONITORING DRIVER
 M:	Clemens Ladisch <clemens@ladisch.de>
 L:	linux-hwmon@vger.kernel.org
 S:	Maintained
-F:	Documentation/hwmon/k10temp
+F:	Documentation/hwmon/k10temp.rst
 F:	drivers/hwmon/k10temp.c
 
 K8TEMP HARDWARE MONITORING DRIVER
 M:	Rudolf Marek <r.marek@assembler.cz>
 L:	linux-hwmon@vger.kernel.org
 S:	Maintained
-F:	Documentation/hwmon/k8temp
+F:	Documentation/hwmon/k8temp.rst
 F:	drivers/hwmon/k8temp.c
 
 KASAN
@@ -8708,6 +8718,7 @@ F:	scripts/leaking_addresses.pl
 LED SUBSYSTEM
 M:	Jacek Anaszewski <jacek.anaszewski@gmail.com>
 M:	Pavel Machek <pavel@ucw.cz>
+R:	Dan Murphy <dmurphy@ti.com>
 L:	linux-leds@vger.kernel.org
 T:	git git://git.kernel.org/pub/scm/linux/kernel/git/j.anaszewski/linux-leds.git
 S:	Maintained
@@ -8993,7 +9004,7 @@ R:	Daniel Lustig <dlustig@nvidia.com>
 L:	linux-kernel@vger.kernel.org
 L:	linux-arch@vger.kernel.org
 S:	Supported
-T:	git git://git.kernel.org/pub/scm/linux/kernel/git/paulmck/linux-rcu.git
+T:	git git://git.kernel.org/pub/scm/linux/kernel/git/paulmck/linux-rcu.git dev
 F:	tools/memory-model/
 F:	Documentation/atomic_bitops.txt
 F:	Documentation/atomic_t.txt
@@ -9044,21 +9055,21 @@ LM78 HARDWARE MONITOR DRIVER
 M:	Jean Delvare <jdelvare@suse.com>
 L:	linux-hwmon@vger.kernel.org
 S:	Maintained
-F:	Documentation/hwmon/lm78
+F:	Documentation/hwmon/lm78.rst
 F:	drivers/hwmon/lm78.c
 
 LM83 HARDWARE MONITOR DRIVER
 M:	Jean Delvare <jdelvare@suse.com>
 L:	linux-hwmon@vger.kernel.org
 S:	Maintained
-F:	Documentation/hwmon/lm83
+F:	Documentation/hwmon/lm83.rst
 F:	drivers/hwmon/lm83.c
 
 LM90 HARDWARE MONITOR DRIVER
 M:	Jean Delvare <jdelvare@suse.com>
 L:	linux-hwmon@vger.kernel.org
 S:	Maintained
-F:	Documentation/hwmon/lm90
+F:	Documentation/hwmon/lm90.rst
 F:	Documentation/devicetree/bindings/hwmon/lm90.txt
 F:	drivers/hwmon/lm90.c
 F:	include/dt-bindings/thermal/lm90.h
@@ -9067,7 +9078,7 @@ LM95234 HARDWARE MONITOR DRIVER
 M:	Guenter Roeck <linux@roeck-us.net>
 L:	linux-hwmon@vger.kernel.org
 S:	Maintained
-F:	Documentation/hwmon/lm95234
+F:	Documentation/hwmon/lm95234.rst
 F:	drivers/hwmon/lm95234.c
 
 LME2510 MEDIA DRIVER
@@ -9099,7 +9110,6 @@ F:	arch/*/include/asm/spinlock*.h
 F:	include/linux/rwlock*.h
 F:	include/linux/mutex*.h
 F:	include/linux/rwsem*.h
-F:	arch/*/include/asm/rwsem.h
 F:	include/linux/seqlock.h
 F:	lib/locking*.[ch]
 F:	kernel/locking/
@@ -9141,7 +9151,7 @@ LTC4261 HARDWARE MONITOR DRIVER
 M:	Guenter Roeck <linux@roeck-us.net>
 L:	linux-hwmon@vger.kernel.org
 S:	Maintained
-F:	Documentation/hwmon/ltc4261
+F:	Documentation/hwmon/ltc4261.rst
 F:	drivers/hwmon/ltc4261.c
 
 LTC4306 I2C MULTIPLEXER DRIVER
@@ -9372,7 +9382,7 @@ MAX16065 HARDWARE MONITOR DRIVER
 M:	Guenter Roeck <linux@roeck-us.net>
 L:	linux-hwmon@vger.kernel.org
 S:	Maintained
-F:	Documentation/hwmon/max16065
+F:	Documentation/hwmon/max16065.rst
 F:	drivers/hwmon/max16065.c
 
 MAX2175 SDR TUNER DRIVER
@@ -9388,14 +9398,14 @@ F:	include/uapi/linux/max2175.h
 MAX6650 HARDWARE MONITOR AND FAN CONTROLLER DRIVER
 L:	linux-hwmon@vger.kernel.org
 S:	Orphan
-F:	Documentation/hwmon/max6650
+F:	Documentation/hwmon/max6650.rst
 F:	drivers/hwmon/max6650.c
 
 MAX6697 HARDWARE MONITOR DRIVER
 M:	Guenter Roeck <linux@roeck-us.net>
 L:	linux-hwmon@vger.kernel.org
 S:	Maintained
-F:	Documentation/hwmon/max6697
+F:	Documentation/hwmon/max6697.rst
 F:	Documentation/devicetree/bindings/hwmon/max6697.txt
 F:	drivers/hwmon/max6697.c
 F:	include/linux/platform_data/max6697.h
@@ -10041,7 +10051,7 @@ F:	drivers/mfd/menf21bmc.c
 F:	drivers/watchdog/menf21bmc_wdt.c
 F:	drivers/leds/leds-menf21bmc.c
 F:	drivers/hwmon/menf21bmc_hwmon.c
-F:	Documentation/hwmon/menf21bmc
+F:	Documentation/hwmon/menf21bmc.rst
 
 MEN Z069 WATCHDOG DRIVER
 M:	Johannes Thumshirn <jth@kernel.org>
@@ -10145,7 +10155,7 @@ F:	drivers/spi/spi-at91-usart.c
 F:	Documentation/devicetree/bindings/mfd/atmel-usart.txt
 
 MICROCHIP KSZ SERIES ETHERNET SWITCH DRIVER
-M:	Woojung Huh <Woojung.Huh@microchip.com>
+M:	Woojung Huh <woojung.huh@microchip.com>
 M:	Microchip Linux Driver Support <UNGLinuxDriver@microchip.com>
 L:	netdev@vger.kernel.org
 S:	Maintained
@@ -10669,7 +10679,7 @@ NCT6775 HARDWARE MONITOR DRIVER
 M:	Guenter Roeck <linux@roeck-us.net>
 L:	linux-hwmon@vger.kernel.org
 S:	Maintained
-F:	Documentation/hwmon/nct6775
+F:	Documentation/hwmon/nct6775.rst
 F:	drivers/hwmon/nct6775.c
 
 NET_FAILOVER MODULE
@@ -11763,7 +11773,7 @@ PC87360 HARDWARE MONITORING DRIVER
 M:	Jim Cromie <jim.cromie@gmail.com>
 L:	linux-hwmon@vger.kernel.org
 S:	Maintained
-F:	Documentation/hwmon/pc87360
+F:	Documentation/hwmon/pc87360.rst
 F:	drivers/hwmon/pc87360.c
 
 PC8736x GPIO DRIVER
@@ -11775,7 +11785,7 @@ PC87427 HARDWARE MONITORING DRIVER
 M:	Jean Delvare <jdelvare@suse.com>
 L:	linux-hwmon@vger.kernel.org
 S:	Maintained
-F:	Documentation/hwmon/pc87427
+F:	Documentation/hwmon/pc87427.rst
 F:	drivers/hwmon/pc87427.c
 
 PCA9532 LED DRIVER
@@ -12175,6 +12185,7 @@ F:	arch/*/kernel/*/*/perf_event*.c
 F:	arch/*/include/asm/perf_event.h
 F:	arch/*/kernel/perf_callchain.c
 F:	arch/*/events/*
+F:	arch/*/events/*/*
 F:	tools/perf/
 
 PERSONALITY HANDLING
@@ -12343,23 +12354,23 @@ S:	Maintained
 F:	Documentation/devicetree/bindings/hwmon/ibm,cffps1.txt
 F:	Documentation/devicetree/bindings/hwmon/max31785.txt
 F:	Documentation/devicetree/bindings/hwmon/ltc2978.txt
-F:	Documentation/hwmon/adm1275
-F:	Documentation/hwmon/ibm-cffps
-F:	Documentation/hwmon/ir35221
-F:	Documentation/hwmon/lm25066
-F:	Documentation/hwmon/ltc2978
-F:	Documentation/hwmon/ltc3815
-F:	Documentation/hwmon/max16064
-F:	Documentation/hwmon/max20751
-F:	Documentation/hwmon/max31785
-F:	Documentation/hwmon/max34440
-F:	Documentation/hwmon/max8688
-F:	Documentation/hwmon/pmbus
-F:	Documentation/hwmon/pmbus-core
-F:	Documentation/hwmon/tps40422
-F:	Documentation/hwmon/ucd9000
-F:	Documentation/hwmon/ucd9200
-F:	Documentation/hwmon/zl6100
+F:	Documentation/hwmon/adm1275.rst
+F:	Documentation/hwmon/ibm-cffps.rst
+F:	Documentation/hwmon/ir35221.rst
+F:	Documentation/hwmon/lm25066.rst
+F:	Documentation/hwmon/ltc2978.rst
+F:	Documentation/hwmon/ltc3815.rst
+F:	Documentation/hwmon/max16064.rst
+F:	Documentation/hwmon/max20751.rst
+F:	Documentation/hwmon/max31785.rst
+F:	Documentation/hwmon/max34440.rst
+F:	Documentation/hwmon/max8688.rst
+F:	Documentation/hwmon/pmbus.rst
+F:	Documentation/hwmon/pmbus-core.rst
+F:	Documentation/hwmon/tps40422.rst
+F:	Documentation/hwmon/ucd9000.rst
+F:	Documentation/hwmon/ucd9200.rst
+F:	Documentation/hwmon/zl6100.rst
 F:	drivers/hwmon/pmbus/
 F:	include/linux/pmbus.h
 
@@ -12415,7 +12426,7 @@ M:	Mark Rutland <mark.rutland@arm.com>
 M:	Lorenzo Pieralisi <lorenzo.pieralisi@arm.com>
 L:	linux-arm-kernel@lists.infradead.org
 S:	Maintained
-F:	drivers/firmware/psci*.c
+F:	drivers/firmware/psci/
 F:	include/linux/psci.h
 F:	include/uapi/linux/psci.h
 
@@ -12623,7 +12634,7 @@ M:	Bartlomiej Zolnierkiewicz <b.zolnierkie@samsung.com>
 L:	linux-hwmon@vger.kernel.org
 S:	Supported
 F:	Documentation/devicetree/bindings/hwmon/pwm-fan.txt
-F:	Documentation/hwmon/pwm-fan
+F:	Documentation/hwmon/pwm-fan.rst
 F:	drivers/hwmon/pwm-fan.c
 
 PWM IR Transmitter
@@ -13041,9 +13052,9 @@ M:	Josh Triplett <josh@joshtriplett.org>
 R:	Steven Rostedt <rostedt@goodmis.org>
 R:	Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
 R:	Lai Jiangshan <jiangshanlai@gmail.com>
-L:	linux-kernel@vger.kernel.org
+L:	rcu@vger.kernel.org
 S:	Supported
-T:	git git://git.kernel.org/pub/scm/linux/kernel/git/paulmck/linux-rcu.git
+T:	git git://git.kernel.org/pub/scm/linux/kernel/git/paulmck/linux-rcu.git dev
 F:	tools/testing/selftests/rcutorture
 
 RDC R-321X SoC
@@ -13089,10 +13100,10 @@ R:	Steven Rostedt <rostedt@goodmis.org>
 R:	Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
 R:	Lai Jiangshan <jiangshanlai@gmail.com>
 R:	Joel Fernandes <joel@joelfernandes.org>
-L:	linux-kernel@vger.kernel.org
+L:	rcu@vger.kernel.org
 W:	http://www.rdrop.com/users/paulmck/RCU/
 S:	Supported
-T:	git git://git.kernel.org/pub/scm/linux/kernel/git/paulmck/linux-rcu.git
+T:	git git://git.kernel.org/pub/scm/linux/kernel/git/paulmck/linux-rcu.git dev
 F:	Documentation/RCU/
 X:	Documentation/RCU/torture.txt
 F:	include/linux/rcu*
@@ -13982,7 +13993,7 @@ F:	drivers/media/rc/serial_ir.c
 SFC NETWORK DRIVER
 M:	Solarflare linux maintainers <linux-net-drivers@solarflare.com>
 M:	Edward Cree <ecree@solarflare.com>
-M:	Bert Kenward <bkenward@solarflare.com>
+M:	Martin Habets <mhabets@solarflare.com>
 L:	netdev@vger.kernel.org
 S:	Supported
 F:	drivers/net/ethernet/sfc/
@@ -14244,10 +14255,10 @@ M:	"Paul E. McKenney" <paulmck@linux.ibm.com>
 M:	Josh Triplett <josh@joshtriplett.org>
 R:	Steven Rostedt <rostedt@goodmis.org>
 R:	Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
-L:	linux-kernel@vger.kernel.org
+L:	rcu@vger.kernel.org
 W:	http://www.rdrop.com/users/paulmck/RCU/
 S:	Supported
-T:	git git://git.kernel.org/pub/scm/linux/kernel/git/paulmck/linux-rcu.git
+T:	git git://git.kernel.org/pub/scm/linux/kernel/git/paulmck/linux-rcu.git dev
 F:	include/linux/srcu*.h
 F:	kernel/rcu/srcu*.c
 
@@ -14288,21 +14299,21 @@ SMM665 HARDWARE MONITOR DRIVER
 M:	Guenter Roeck <linux@roeck-us.net>
 L:	linux-hwmon@vger.kernel.org
 S:	Maintained
-F:	Documentation/hwmon/smm665
+F:	Documentation/hwmon/smm665.rst
 F:	drivers/hwmon/smm665.c
 
 SMSC EMC2103 HARDWARE MONITOR DRIVER
 M:	Steve Glendinning <steve.glendinning@shawell.net>
 L:	linux-hwmon@vger.kernel.org
 S:	Maintained
-F:	Documentation/hwmon/emc2103
+F:	Documentation/hwmon/emc2103.rst
 F:	drivers/hwmon/emc2103.c
 
 SMSC SCH5627 HARDWARE MONITOR DRIVER
 M:	Hans de Goede <hdegoede@redhat.com>
 L:	linux-hwmon@vger.kernel.org
 S:	Supported
-F:	Documentation/hwmon/sch5627
+F:	Documentation/hwmon/sch5627.rst
 F:	drivers/hwmon/sch5627.c
 
 SMSC UFX6000 and UFX7000 USB to VGA DRIVER
@@ -14315,7 +14326,7 @@ SMSC47B397 HARDWARE MONITOR DRIVER
 M:	Jean Delvare <jdelvare@suse.com>
 L:	linux-hwmon@vger.kernel.org
 S:	Maintained
-F:	Documentation/hwmon/smsc47b397
+F:	Documentation/hwmon/smsc47b397.rst
 F:	drivers/hwmon/smsc47b397.c
 
 SMSC911x ETHERNET DRIVER
@@ -15661,7 +15672,7 @@ TMP401 HARDWARE MONITOR DRIVER
 M:	Guenter Roeck <linux@roeck-us.net>
 L:	linux-hwmon@vger.kernel.org
 S:	Maintained
-F:	Documentation/hwmon/tmp401
+F:	Documentation/hwmon/tmp401.rst
 F:	drivers/hwmon/tmp401.c
 
 TMPFS (SHMEM FILESYSTEM)
@@ -15694,7 +15705,7 @@ M:	"Paul E. McKenney" <paulmck@linux.ibm.com>
 M:	Josh Triplett <josh@joshtriplett.org>
 L:	linux-kernel@vger.kernel.org
 S:	Supported
-T:	git git://git.kernel.org/pub/scm/linux/kernel/git/paulmck/linux-rcu.git
+T:	git git://git.kernel.org/pub/scm/linux/kernel/git/paulmck/linux-rcu.git dev
 F:	Documentation/RCU/torture.txt
 F:	kernel/torture.c
 F:	kernel/rcu/rcutorture.c
@@ -16509,7 +16520,7 @@ F:	drivers/char/virtio_console.c
 F:	include/linux/virtio_console.h
 F:	include/uapi/linux/virtio_console.h
 
-VIRTIO CORE, NET AND BLOCK DRIVERS
+VIRTIO CORE AND NET DRIVERS
 M:	"Michael S. Tsirkin" <mst@redhat.com>
 M:	Jason Wang <jasowang@redhat.com>
 L:	virtualization@lists.linux-foundation.org
@@ -16524,6 +16535,19 @@ F:	include/uapi/linux/virtio_*.h
 F:	drivers/crypto/virtio/
 F:	mm/balloon_compaction.c
 
+VIRTIO BLOCK AND SCSI DRIVERS
+M:	"Michael S. Tsirkin" <mst@redhat.com>
+M:	Jason Wang <jasowang@redhat.com>
+R:	Paolo Bonzini <pbonzini@redhat.com>
+R:	Stefan Hajnoczi <stefanha@redhat.com>
+L:	virtualization@lists.linux-foundation.org
+S:	Maintained
+F:	drivers/block/virtio_blk.c
+F:	drivers/scsi/virtio_scsi.c
+F:	include/uapi/linux/virtio_blk.h
+F:	include/uapi/linux/virtio_scsi.h
+F:	drivers/vhost/scsi.c
+
 VIRTIO CRYPTO DRIVER
 M:	Gonglei <arei.gonglei@huawei.com>
 L:	virtualization@lists.linux-foundation.org
@@ -16686,7 +16710,7 @@ VT1211 HARDWARE MONITOR DRIVER
 M:	Juerg Haefliger <juergh@gmail.com>
 L:	linux-hwmon@vger.kernel.org
 S:	Maintained
-F:	Documentation/hwmon/vt1211
+F:	Documentation/hwmon/vt1211.rst
 F:	drivers/hwmon/vt1211.c
 
 VT8231 HARDWARE MONITOR DRIVER
@@ -16714,14 +16738,14 @@ W83791D HARDWARE MONITORING DRIVER
 M:	Marc Hulsman <m.hulsman@tudelft.nl>
 L:	linux-hwmon@vger.kernel.org
 S:	Maintained
-F:	Documentation/hwmon/w83791d
+F:	Documentation/hwmon/w83791d.rst
 F:	drivers/hwmon/w83791d.c
 
 W83793 HARDWARE MONITORING DRIVER
 M:	Rudolf Marek <r.marek@assembler.cz>
 L:	linux-hwmon@vger.kernel.org
 S:	Maintained
-F:	Documentation/hwmon/w83793
+F:	Documentation/hwmon/w83793.rst
 F:	drivers/hwmon/w83793.c
 
 W83795 HARDWARE MONITORING DRIVER
@@ -16830,7 +16854,7 @@ L:	patches@opensource.cirrus.com
 T:	git https://github.com/CirrusLogic/linux-drivers.git
 W:	https://github.com/CirrusLogic/linux-drivers/wiki
 S:	Supported
-F:	Documentation/hwmon/wm83??
+F:	Documentation/hwmon/wm83??.rst
 F:	Documentation/devicetree/bindings/extcon/extcon-arizona.txt
 F:	Documentation/devicetree/bindings/regulator/arizona-regulator.txt
 F:	Documentation/devicetree/bindings/mfd/arizona.txt
@@ -16920,7 +16944,7 @@ M:	Tony Luck <tony.luck@intel.com>
 M:	Borislav Petkov <bp@alien8.de>
 L:	linux-edac@vger.kernel.org
 S:	Maintained
-F:	arch/x86/kernel/cpu/mcheck/*
+F:	arch/x86/kernel/cpu/mce/*
 
 X86 MICROCODE UPDATE SUPPORT
 M:	Borislav Petkov <bp@alien8.de>
diff --git a/Makefile b/Makefile
index c0a34064c574..26c92f892d24 100644
--- a/Makefile
+++ b/Makefile
@@ -2,7 +2,7 @@
 VERSION = 5
 PATCHLEVEL = 1
 SUBLEVEL = 0
-EXTRAVERSION = -rc2
+EXTRAVERSION =
 NAME = Shy Crocodile
 
 # *DOCUMENTATION*
@@ -31,26 +31,12 @@ _all:
 # descending is started. They are now explicitly listed as the
 # prepare rule.
 
-# Ugly workaround for Debian make-kpkg:
-# make-kpkg directly includes the top Makefile of Linux kernel. In such a case,
-# skip sub-make to support debian_* targets in ruleset/kernel_version.mk, but
-# displays warning to discourage such abusage.
-ifneq ($(word 2, $(MAKEFILE_LIST)),)
-$(warning Do not include top Makefile of Linux Kernel)
-sub-make-done := 1
-MAKEFLAGS += -rR
-endif
-
-ifneq ($(sub-make-done),1)
+ifneq ($(sub_make_done),1)
 
 # Do not use make's built-in rules and variables
 # (this increases performance and avoids hard-to-debug behaviour)
 MAKEFLAGS += -rR
 
-# 'MAKEFLAGS += -rR' does not become immediately effective for old
-# GNU Make versions. Cancel implicit rules for this Makefile.
-$(lastword $(MAKEFILE_LIST)): ;
-
 # Avoid funny character set dependencies
 unexport LC_ALL
 LC_COLLATE=C
@@ -153,6 +139,7 @@ $(if $(KBUILD_OUTPUT),, \
 # 'sub-make' below.
 MAKEFLAGS += --include-dir=$(CURDIR)
 
+need-sub-make := 1
 else
 
 # Do not print "Entering directory ..." at all for in-tree build.
@@ -160,6 +147,18 @@ MAKEFLAGS += --no-print-directory
 
 endif # ifneq ($(KBUILD_OUTPUT),)
 
+ifneq ($(filter 3.%,$(MAKE_VERSION)),)
+# 'MAKEFLAGS += -rR' does not immediately become effective for GNU Make 3.x
+# We need to invoke sub-make to avoid implicit rules in the top Makefile.
+need-sub-make := 1
+# Cancel implicit rules for this Makefile.
+$(lastword $(MAKEFILE_LIST)): ;
+endif
+
+export sub_make_done := 1
+
+ifeq ($(need-sub-make),1)
+
 PHONY += $(MAKECMDGOALS) sub-make
 
 $(filter-out _all sub-make $(CURDIR)/Makefile, $(MAKECMDGOALS)) _all: sub-make
@@ -167,12 +166,15 @@ $(filter-out _all sub-make $(CURDIR)/Makefile, $(MAKECMDGOALS)) _all: sub-make
 
 # Invoke a second make in the output directory, passing relevant variables
 sub-make:
-	$(Q)$(MAKE) sub-make-done=1 \
+	$(Q)$(MAKE) \
 	$(if $(KBUILD_OUTPUT),-C $(KBUILD_OUTPUT) KBUILD_SRC=$(CURDIR)) \
 	-f $(CURDIR)/Makefile $(filter-out _all sub-make,$(MAKECMDGOALS))
 
-else # sub-make-done
+endif # need-sub-make
+endif # sub_make_done
+
 # We process the rest of the Makefile if this is the final invocation of make
+ifeq ($(need-sub-make),)
 
 # Do not print "Entering directory ...",
 # but we want to display it when entering to the output directory
@@ -497,7 +499,8 @@ outputmakefile:
 ifneq ($(KBUILD_SRC),)
 	$(Q)ln -fsn $(srctree) source
 	$(Q)$(CONFIG_SHELL) $(srctree)/scripts/mkmakefile $(srctree)
-	$(Q){ echo "# this is build directory, ignore it"; echo "*"; } > .gitignore
+	$(Q)test -e .gitignore || \
+	{ echo "# this is build directory, ignore it"; echo "*"; } > .gitignore
 endif
 
 ifneq ($(shell $(CC) --version 2>&1 | head -n 1 | grep clang),)
@@ -675,9 +678,10 @@ KBUILD_CFLAGS	+= $(call cc-disable-warning,frame-address,)
 KBUILD_CFLAGS	+= $(call cc-disable-warning, format-truncation)
 KBUILD_CFLAGS	+= $(call cc-disable-warning, format-overflow)
 KBUILD_CFLAGS	+= $(call cc-disable-warning, int-in-bool-context)
+KBUILD_CFLAGS	+= $(call cc-disable-warning, address-of-packed-member)
 
 ifdef CONFIG_CC_OPTIMIZE_FOR_SIZE
-KBUILD_CFLAGS	+= $(call cc-option,-Oz,-Os)
+KBUILD_CFLAGS	+= -Os
 else
 KBUILD_CFLAGS   += -O2
 endif
@@ -716,7 +720,6 @@ ifdef CONFIG_CC_IS_CLANG
 KBUILD_CPPFLAGS += $(call cc-option,-Qunused-arguments,)
 KBUILD_CFLAGS += $(call cc-disable-warning, format-invalid-specifier)
 KBUILD_CFLAGS += $(call cc-disable-warning, gnu)
-KBUILD_CFLAGS += $(call cc-disable-warning, address-of-packed-member)
 # Quiet clang warning: comparison of unsigned expression < 0 is always false
 KBUILD_CFLAGS += $(call cc-disable-warning, tautological-compare)
 # CLANG uses a _MergedGlobals as optimization, but this breaks modpost, as the
@@ -950,9 +953,11 @@ mod_sign_cmd = true
 endif
 export mod_sign_cmd
 
+HOST_LIBELF_LIBS = $(shell pkg-config libelf --libs 2>/dev/null || echo -lelf)
+
 ifdef CONFIG_STACK_VALIDATION
   has_libelf := $(call try-run,\
-		echo "int main() {}" | $(HOSTCC) -xc -o /dev/null -lelf -,1,0)
+		echo "int main() {}" | $(HOSTCC) -xc -o /dev/null $(HOST_LIBELF_LIBS) -,1,0)
   ifeq ($(has_libelf),1)
     objtool_target := tools/objtool FORCE
   else
@@ -1757,7 +1762,7 @@ existing-targets := $(wildcard $(sort $(targets)))
 
 endif   # ifeq ($(config-targets),1)
 endif   # ifeq ($(mixed-targets),1)
-endif   # sub-make-done
+endif   # need-sub-make
 
 PHONY += FORCE
 FORCE:
diff --git a/arch/Kconfig b/arch/Kconfig
index 33687dddd86a..5e43fcbad4ca 100644
--- a/arch/Kconfig
+++ b/arch/Kconfig
@@ -249,6 +249,10 @@ config ARCH_HAS_FORTIFY_SOURCE
 config ARCH_HAS_SET_MEMORY
 	bool
 
+# Select if arch has all set_direct_map_invalid/default() functions
+config ARCH_HAS_SET_DIRECT_MAP
+	bool
+
 # Select if arch init_task must go in the __init_task_data section
 config ARCH_TASK_STRUCT_ON_STACK
        bool
@@ -383,7 +387,13 @@ config HAVE_ARCH_JUMP_LABEL_RELATIVE
 config HAVE_RCU_TABLE_FREE
 	bool
 
-config HAVE_RCU_TABLE_INVALIDATE
+config HAVE_RCU_TABLE_NO_INVALIDATE
+	bool
+
+config HAVE_MMU_GATHER_PAGE_SIZE
+	bool
+
+config HAVE_MMU_GATHER_NO_GATHER
 	bool
 
 config ARCH_HAVE_NMI_SAFE_CMPXCHG
@@ -901,6 +911,15 @@ config HAVE_ARCH_PREL32_RELOCATIONS
 config ARCH_USE_MEMREMAP_PROT
 	bool
 
+config LOCK_EVENT_COUNTS
+	bool "Locking event counts collection"
+	depends on DEBUG_FS
+	---help---
+	  Enable light-weight counting of various locking related events
+	  in the system with minimal performance impact. This reduces
+	  the chance of application behavior change because of timing
+	  differences. The counts are reported via debugfs.
+
 source "kernel/gcov/Kconfig"
 
 source "scripts/gcc-plugins/Kconfig"
diff --git a/arch/alpha/Kconfig b/arch/alpha/Kconfig
index 584a6e114853..f7b19b813a70 100644
--- a/arch/alpha/Kconfig
+++ b/arch/alpha/Kconfig
@@ -36,6 +36,7 @@ config ALPHA
 	select ODD_RT_SIGACTION
 	select OLD_SIGSUSPEND
 	select CPU_NO_EFFICIENT_FFS if !ALPHA_EV67
+	select MMU_GATHER_NO_RANGE
 	help
 	  The Alpha is a 64-bit general-purpose processor designed and
 	  marketed by the Digital Equipment Corporation of blessed memory,
@@ -49,13 +50,6 @@ config MMU
 	bool
 	default y
 
-config RWSEM_GENERIC_SPINLOCK
-	bool
-
-config RWSEM_XCHGADD_ALGORITHM
-	bool
-	default y
-
 config ARCH_HAS_ILOG2_U32
 	bool
 	default n
diff --git a/arch/alpha/include/asm/Kbuild b/arch/alpha/include/asm/Kbuild
index dc0ab28baca1..89e87bbc987f 100644
--- a/arch/alpha/include/asm/Kbuild
+++ b/arch/alpha/include/asm/Kbuild
@@ -6,8 +6,10 @@ generic-y += exec.h
 generic-y += export.h
 generic-y += fb.h
 generic-y += irq_work.h
+generic-y += kvm_para.h
 generic-y += mcs_spinlock.h
 generic-y += mm-arch-hooks.h
+generic-y += mmiowb.h
 generic-y += preempt.h
 generic-y += sections.h
 generic-y += trace_clock.h
diff --git a/arch/alpha/include/asm/io.h b/arch/alpha/include/asm/io.h
index 4c533fc94d62..ccf9d65166bb 100644
--- a/arch/alpha/include/asm/io.h
+++ b/arch/alpha/include/asm/io.h
@@ -513,8 +513,6 @@ extern inline void writeq(u64 b, volatile void __iomem *addr)
 #define writel_relaxed(b, addr)	__raw_writel(b, addr)
 #define writeq_relaxed(b, addr)	__raw_writeq(b, addr)
 
-#define mmiowb()
-
 /*
  * String version of IO memory access ops:
  */
diff --git a/arch/alpha/include/asm/rwsem.h b/arch/alpha/include/asm/rwsem.h
deleted file mode 100644
index cf8fc8f9a2ed..000000000000
--- a/arch/alpha/include/asm/rwsem.h
+++ /dev/null
@@ -1,211 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 */
-#ifndef _ALPHA_RWSEM_H
-#define _ALPHA_RWSEM_H
-
-/*
- * Written by Ivan Kokshaysky <ink@jurassic.park.msu.ru>, 2001.
- * Based on asm-alpha/semaphore.h and asm-i386/rwsem.h
- */
-
-#ifndef _LINUX_RWSEM_H
-#error "please don't include asm/rwsem.h directly, use linux/rwsem.h instead"
-#endif
-
-#ifdef __KERNEL__
-
-#include <linux/compiler.h>
-
-#define RWSEM_UNLOCKED_VALUE		0x0000000000000000L
-#define RWSEM_ACTIVE_BIAS		0x0000000000000001L
-#define RWSEM_ACTIVE_MASK		0x00000000ffffffffL
-#define RWSEM_WAITING_BIAS		(-0x0000000100000000L)
-#define RWSEM_ACTIVE_READ_BIAS		RWSEM_ACTIVE_BIAS
-#define RWSEM_ACTIVE_WRITE_BIAS		(RWSEM_WAITING_BIAS + RWSEM_ACTIVE_BIAS)
-
-static inline int ___down_read(struct rw_semaphore *sem)
-{
-	long oldcount;
-#ifndef	CONFIG_SMP
-	oldcount = sem->count.counter;
-	sem->count.counter += RWSEM_ACTIVE_READ_BIAS;
-#else
-	long temp;
-	__asm__ __volatile__(
-	"1:	ldq_l	%0,%1\n"
-	"	addq	%0,%3,%2\n"
-	"	stq_c	%2,%1\n"
-	"	beq	%2,2f\n"
-	"	mb\n"
-	".subsection 2\n"
-	"2:	br	1b\n"
-	".previous"
-	:"=&r" (oldcount), "=m" (sem->count), "=&r" (temp)
-	:"Ir" (RWSEM_ACTIVE_READ_BIAS), "m" (sem->count) : "memory");
-#endif
-	return (oldcount < 0);
-}
-
-static inline void __down_read(struct rw_semaphore *sem)
-{
-	if (unlikely(___down_read(sem)))
-		rwsem_down_read_failed(sem);
-}
-
-static inline int __down_read_killable(struct rw_semaphore *sem)
-{
-	if (unlikely(___down_read(sem)))
-		if (IS_ERR(rwsem_down_read_failed_killable(sem)))
-			return -EINTR;
-
-	return 0;
-}
-
-/*
- * trylock for reading -- returns 1 if successful, 0 if contention
- */
-static inline int __down_read_trylock(struct rw_semaphore *sem)
-{
-	long old, new, res;
-
-	res = atomic_long_read(&sem->count);
-	do {
-		new = res + RWSEM_ACTIVE_READ_BIAS;
-		if (new <= 0)
-			break;
-		old = res;
-		res = atomic_long_cmpxchg(&sem->count, old, new);
-	} while (res != old);
-	return res >= 0 ? 1 : 0;
-}
-
-static inline long ___down_write(struct rw_semaphore *sem)
-{
-	long oldcount;
-#ifndef	CONFIG_SMP
-	oldcount = sem->count.counter;
-	sem->count.counter += RWSEM_ACTIVE_WRITE_BIAS;
-#else
-	long temp;
-	__asm__ __volatile__(
-	"1:	ldq_l	%0,%1\n"
-	"	addq	%0,%3,%2\n"
-	"	stq_c	%2,%1\n"
-	"	beq	%2,2f\n"
-	"	mb\n"
-	".subsection 2\n"
-	"2:	br	1b\n"
-	".previous"
-	:"=&r" (oldcount), "=m" (sem->count), "=&r" (temp)
-	:"Ir" (RWSEM_ACTIVE_WRITE_BIAS), "m" (sem->count) : "memory");
-#endif
-	return oldcount;
-}
-
-static inline void __down_write(struct rw_semaphore *sem)
-{
-	if (unlikely(___down_write(sem)))
-		rwsem_down_write_failed(sem);
-}
-
-static inline int __down_write_killable(struct rw_semaphore *sem)
-{
-	if (unlikely(___down_write(sem))) {
-		if (IS_ERR(rwsem_down_write_failed_killable(sem)))
-			return -EINTR;
-	}
-
-	return 0;
-}
-
-/*
- * trylock for writing -- returns 1 if successful, 0 if contention
- */
-static inline int __down_write_trylock(struct rw_semaphore *sem)
-{
-	long ret = atomic_long_cmpxchg(&sem->count, RWSEM_UNLOCKED_VALUE,
-			   RWSEM_ACTIVE_WRITE_BIAS);
-	if (ret == RWSEM_UNLOCKED_VALUE)
-		return 1;
-	return 0;
-}
-
-static inline void __up_read(struct rw_semaphore *sem)
-{
-	long oldcount;
-#ifndef	CONFIG_SMP
-	oldcount = sem->count.counter;
-	sem->count.counter -= RWSEM_ACTIVE_READ_BIAS;
-#else
-	long temp;
-	__asm__ __volatile__(
-	"	mb\n"
-	"1:	ldq_l	%0,%1\n"
-	"	subq	%0,%3,%2\n"
-	"	stq_c	%2,%1\n"
-	"	beq	%2,2f\n"
-	".subsection 2\n"
-	"2:	br	1b\n"
-	".previous"
-	:"=&r" (oldcount), "=m" (sem->count), "=&r" (temp)
-	:"Ir" (RWSEM_ACTIVE_READ_BIAS), "m" (sem->count) : "memory");
-#endif
-	if (unlikely(oldcount < 0))
-		if ((int)oldcount - RWSEM_ACTIVE_READ_BIAS == 0)
-			rwsem_wake(sem);
-}
-
-static inline void __up_write(struct rw_semaphore *sem)
-{
-	long count;
-#ifndef	CONFIG_SMP
-	sem->count.counter -= RWSEM_ACTIVE_WRITE_BIAS;
-	count = sem->count.counter;
-#else
-	long temp;
-	__asm__ __volatile__(
-	"	mb\n"
-	"1:	ldq_l	%0,%1\n"
-	"	subq	%0,%3,%2\n"
-	"	stq_c	%2,%1\n"
-	"	beq	%2,2f\n"
-	"	subq	%0,%3,%0\n"
-	".subsection 2\n"
-	"2:	br	1b\n"
-	".previous"
-	:"=&r" (count), "=m" (sem->count), "=&r" (temp)
-	:"Ir" (RWSEM_ACTIVE_WRITE_BIAS), "m" (sem->count) : "memory");
-#endif
-	if (unlikely(count))
-		if ((int)count == 0)
-			rwsem_wake(sem);
-}
-
-/*
- * downgrade write lock to read lock
- */
-static inline void __downgrade_write(struct rw_semaphore *sem)
-{
-	long oldcount;
-#ifndef	CONFIG_SMP
-	oldcount = sem->count.counter;
-	sem->count.counter -= RWSEM_WAITING_BIAS;
-#else
-	long temp;
-	__asm__ __volatile__(
-	"1:	ldq_l	%0,%1\n"
-	"	addq	%0,%3,%2\n"
-	"	stq_c	%2,%1\n"
-	"	beq	%2,2f\n"
-	"	mb\n"
-	".subsection 2\n"
-	"2:	br	1b\n"
-	".previous"
-	:"=&r" (oldcount), "=m" (sem->count), "=&r" (temp)
-	:"Ir" (-RWSEM_WAITING_BIAS), "m" (sem->count) : "memory");
-#endif
-	if (unlikely(oldcount < 0))
-		rwsem_downgrade_wake(sem);
-}
-
-#endif /* __KERNEL__ */
-#endif /* _ALPHA_RWSEM_H */
diff --git a/arch/alpha/include/asm/tlb.h b/arch/alpha/include/asm/tlb.h
index 8f5042b61875..4f79e331af5e 100644
--- a/arch/alpha/include/asm/tlb.h
+++ b/arch/alpha/include/asm/tlb.h
@@ -2,12 +2,6 @@
 #ifndef _ALPHA_TLB_H
 #define _ALPHA_TLB_H
 
-#define tlb_start_vma(tlb, vma)			do { } while (0)
-#define tlb_end_vma(tlb, vma)			do { } while (0)
-#define __tlb_remove_tlb_entry(tlb, pte, addr)	do { } while (0)
-
-#define tlb_flush(tlb)				flush_tlb_mm((tlb)->mm)
-
 #include <asm-generic/tlb.h>
 
 #define __pte_free_tlb(tlb, pte, address)		pte_free((tlb)->mm, pte)
diff --git a/arch/alpha/include/uapi/asm/kvm_para.h b/arch/alpha/include/uapi/asm/kvm_para.h
deleted file mode 100644
index baacc4996d18..000000000000
--- a/arch/alpha/include/uapi/asm/kvm_para.h
+++ /dev/null
@@ -1,2 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
-#include <asm-generic/kvm_para.h>
diff --git a/arch/alpha/kernel/syscalls/syscall.tbl b/arch/alpha/kernel/syscalls/syscall.tbl
index 63ed39cbd3bd..165f268beafc 100644
--- a/arch/alpha/kernel/syscalls/syscall.tbl
+++ b/arch/alpha/kernel/syscalls/syscall.tbl
@@ -463,3 +463,7 @@
 532	common	getppid				sys_getppid
 # all other architectures have common numbers for new syscall, alpha
 # is the exception.
+534	common	pidfd_send_signal		sys_pidfd_send_signal
+535	common	io_uring_setup			sys_io_uring_setup
+536	common	io_uring_enter			sys_io_uring_enter
+537	common	io_uring_register		sys_io_uring_register
diff --git a/arch/arc/Kconfig b/arch/arc/Kconfig
index c781e45d1d99..23e063df5d2c 100644
--- a/arch/arc/Kconfig
+++ b/arch/arc/Kconfig
@@ -63,9 +63,6 @@ config SCHED_OMIT_FRAME_POINTER
 config GENERIC_CSUM
 	def_bool y
 
-config RWSEM_GENERIC_SPINLOCK
-	def_bool y
-
 config ARCH_DISCONTIGMEM_ENABLE
 	def_bool n
 
diff --git a/arch/arc/boot/dts/hsdk.dts b/arch/arc/boot/dts/hsdk.dts
index 69bc1c9e8e50..7425bb0f2d1b 100644
--- a/arch/arc/boot/dts/hsdk.dts
+++ b/arch/arc/boot/dts/hsdk.dts
@@ -18,8 +18,8 @@
 	model = "snps,hsdk";
 	compatible = "snps,hsdk";
 
-	#address-cells = <1>;
-	#size-cells = <1>;
+	#address-cells = <2>;
+	#size-cells = <2>;
 
 	chosen {
 		bootargs = "earlycon=uart8250,mmio32,0xf0005000,115200n8 console=ttyS0,115200n8 debug print-fatal-signals=1";
@@ -105,7 +105,7 @@
 		#size-cells = <1>;
 		interrupt-parent = <&idu_intc>;
 
-		ranges = <0x00000000 0xf0000000 0x10000000>;
+		ranges = <0x00000000 0x0 0xf0000000 0x10000000>;
 
 		cgu_rst: reset-controller@8a0 {
 			compatible = "snps,hsdk-reset";
@@ -269,9 +269,10 @@
 	};
 
 	memory@80000000 {
-		#address-cells = <1>;
-		#size-cells = <1>;
+		#address-cells = <2>;
+		#size-cells = <2>;
 		device_type = "memory";
-		reg = <0x80000000 0x40000000>;  /* 1 GiB */
+		reg = <0x0 0x80000000 0x0 0x40000000>;  /* 1 GB lowmem */
+		/*     0x1 0x00000000 0x0 0x40000000>;     1 GB highmem */
 	};
 };
diff --git a/arch/arc/include/asm/Kbuild b/arch/arc/include/asm/Kbuild
index b41f8881ecc8..393d4f5e1450 100644
--- a/arch/arc/include/asm/Kbuild
+++ b/arch/arc/include/asm/Kbuild
@@ -11,10 +11,12 @@ generic-y += hardirq.h
 generic-y += hw_irq.h
 generic-y += irq_regs.h
 generic-y += irq_work.h
+generic-y += kvm_para.h
 generic-y += local.h
 generic-y += local64.h
 generic-y += mcs_spinlock.h
 generic-y += mm-arch-hooks.h
+generic-y += mmiowb.h
 generic-y += msi.h
 generic-y += parport.h
 generic-y += percpu.h
diff --git a/arch/arc/include/asm/syscall.h b/arch/arc/include/asm/syscall.h
index 29de09804306..c7a4201ed62b 100644
--- a/arch/arc/include/asm/syscall.h
+++ b/arch/arc/include/asm/syscall.h
@@ -55,12 +55,11 @@ syscall_set_return_value(struct task_struct *task, struct pt_regs *regs,
  */
 static inline void
 syscall_get_arguments(struct task_struct *task, struct pt_regs *regs,
-		      unsigned int i, unsigned int n, unsigned long *args)
+		      unsigned long *args)
 {
 	unsigned long *inside_ptregs = &(regs->r0);
-	inside_ptregs -= i;
-
-	BUG_ON((i + n) > 6);
+	unsigned int n = 6;
+	unsigned int i = 0;
 
 	while (n--) {
 		args[i++] = (*inside_ptregs);
diff --git a/arch/arc/include/asm/tlb.h b/arch/arc/include/asm/tlb.h
index a9db5f62aaf3..90cac97643a4 100644
--- a/arch/arc/include/asm/tlb.h
+++ b/arch/arc/include/asm/tlb.h
@@ -9,38 +9,6 @@
 #ifndef _ASM_ARC_TLB_H
 #define _ASM_ARC_TLB_H
 
-#define tlb_flush(tlb)				\
-do {						\
-	if (tlb->fullmm)			\
-		flush_tlb_mm((tlb)->mm);	\
-} while (0)
-
-/*
- * This pair is called at time of munmap/exit to flush cache and TLB entries
- * for mappings being torn down.
- * 1) cache-flush part -implemented via tlb_start_vma( ) for VIPT aliasing D$
- * 2) tlb-flush part - implemted via tlb_end_vma( ) flushes the TLB range
- *
- * Note, read http://lkml.org/lkml/2004/1/15/6
- */
-#ifndef CONFIG_ARC_CACHE_VIPT_ALIASING
-#define tlb_start_vma(tlb, vma)
-#else
-#define tlb_start_vma(tlb, vma)						\
-do {									\
-	if (!tlb->fullmm)						\
-		flush_cache_range(vma, vma->vm_start, vma->vm_end);	\
-} while(0)
-#endif
-
-#define tlb_end_vma(tlb, vma)						\
-do {									\
-	if (!tlb->fullmm)						\
-		flush_tlb_range(vma, vma->vm_start, vma->vm_end);	\
-} while (0)
-
-#define __tlb_remove_tlb_entry(tlb, ptep, address)
-
 #include <linux/pagemap.h>
 #include <asm-generic/tlb.h>
 
diff --git a/arch/arc/include/uapi/asm/Kbuild b/arch/arc/include/uapi/asm/Kbuild
index 755bb11323d8..1c72f04ff75d 100644
--- a/arch/arc/include/uapi/asm/Kbuild
+++ b/arch/arc/include/uapi/asm/Kbuild
@@ -1,2 +1 @@
-generic-y += kvm_para.h
 generic-y += ucontext.h
diff --git a/arch/arc/lib/memset-archs.S b/arch/arc/lib/memset-archs.S
index f230bb7092fd..b3373f5c88e0 100644
--- a/arch/arc/lib/memset-archs.S
+++ b/arch/arc/lib/memset-archs.S
@@ -30,10 +30,10 @@
 
 #else
 
-.macro PREALLOC_INSTR
+.macro PREALLOC_INSTR	reg, off
 .endm
 
-.macro PREFETCHW_INSTR
+.macro PREFETCHW_INSTR	reg, off
 .endm
 
 #endif
diff --git a/arch/arc/mm/cache.c b/arch/arc/mm/cache.c
index 4135abec3fb0..63e6e6504699 100644
--- a/arch/arc/mm/cache.c
+++ b/arch/arc/mm/cache.c
@@ -113,10 +113,24 @@ static void read_decode_cache_bcr_arcv2(int cpu)
 	}
 
 	READ_BCR(ARC_REG_CLUSTER_BCR, cbcr);
-	if (cbcr.c)
+	if (cbcr.c) {
 		ioc_exists = 1;
-	else
+
+		/*
+		 * As for today we don't support both IOC and ZONE_HIGHMEM enabled
+		 * simultaneously. This happens because as of today IOC aperture covers
+		 * only ZONE_NORMAL (low mem) and any dma transactions outside this
+		 * region won't be HW coherent.
+		 * If we want to use both IOC and ZONE_HIGHMEM we can use
+		 * bounce_buffer to handle dma transactions to HIGHMEM.
+		 * Also it is possible to modify dma_direct cache ops or increase IOC
+		 * aperture size if we are planning to use HIGHMEM without PAE.
+		 */
+		if (IS_ENABLED(CONFIG_HIGHMEM) || is_pae40_enabled())
+			ioc_enable = 0;
+	} else {
 		ioc_enable = 0;
+	}
 
 	/* HS 2.0 didn't have AUX_VOL */
 	if (cpuinfo_arc700[cpu].core.family > 0x51) {
@@ -1158,19 +1172,6 @@ noinline void __init arc_ioc_setup(void)
 	if (!ioc_enable)
 		return;
 
-	/*
-	 * As for today we don't support both IOC and ZONE_HIGHMEM enabled
-	 * simultaneously. This happens because as of today IOC aperture covers
-	 * only ZONE_NORMAL (low mem) and any dma transactions outside this
-	 * region won't be HW coherent.
-	 * If we want to use both IOC and ZONE_HIGHMEM we can use
-	 * bounce_buffer to handle dma transactions to HIGHMEM.
-	 * Also it is possible to modify dma_direct cache ops or increase IOC
-	 * aperture size if we are planning to use HIGHMEM without PAE.
-	 */
-	if (IS_ENABLED(CONFIG_HIGHMEM))
-		panic("IOC and HIGHMEM can't be used simultaneously");
-
 	/* Flush + invalidate + disable L1 dcache */
 	__dc_disable();
 
diff --git a/arch/arm/Kconfig b/arch/arm/Kconfig
index 054ead960f98..dc9855c4a3b4 100644
--- a/arch/arm/Kconfig
+++ b/arch/arm/Kconfig
@@ -73,7 +73,7 @@ config ARM
 	select HAVE_EFFICIENT_UNALIGNED_ACCESS if (CPU_V6 || CPU_V6K || CPU_V7) && MMU
 	select HAVE_EXIT_THREAD
 	select HAVE_FTRACE_MCOUNT_RECORD if !XIP_KERNEL
-	select HAVE_FUNCTION_GRAPH_TRACER if !THUMB2_KERNEL
+	select HAVE_FUNCTION_GRAPH_TRACER if !THUMB2_KERNEL && !CC_IS_CLANG
 	select HAVE_FUNCTION_TRACER if !XIP_KERNEL
 	select HAVE_GCC_PLUGINS
 	select HAVE_HW_BREAKPOINT if PERF_EVENTS && (CPU_V6 || CPU_V6K || CPU_V7)
@@ -178,10 +178,6 @@ config TRACE_IRQFLAGS_SUPPORT
 	bool
 	default !CPU_V7M
 
-config RWSEM_XCHGADD_ALGORITHM
-	bool
-	default y
-
 config ARCH_HAS_ILOG2_U32
 	bool
 
@@ -596,6 +592,7 @@ config ARCH_DAVINCI
 	select HAVE_IDE
 	select PM_GENERIC_DOMAINS if PM
 	select PM_GENERIC_DOMAINS_OF if PM && OF
+	select REGMAP_MMIO
 	select RESET_CONTROLLER
 	select SPARSE_IRQ
 	select USE_OF
diff --git a/arch/arm/Kconfig.debug b/arch/arm/Kconfig.debug
index 6d6e0330930b..e388af4594a6 100644
--- a/arch/arm/Kconfig.debug
+++ b/arch/arm/Kconfig.debug
@@ -47,8 +47,8 @@ config DEBUG_WX
 
 choice
 	prompt "Choose kernel unwinder"
-	default UNWINDER_ARM if AEABI && !FUNCTION_GRAPH_TRACER
-	default UNWINDER_FRAME_POINTER if !AEABI || FUNCTION_GRAPH_TRACER
+	default UNWINDER_ARM if AEABI
+	default UNWINDER_FRAME_POINTER if !AEABI
 	help
 	  This determines which method will be used for unwinding kernel stack
 	  traces for panics, oopses, bugs, warnings, perf, /proc/<pid>/stack,
@@ -65,7 +65,7 @@ config UNWINDER_FRAME_POINTER
 
 config UNWINDER_ARM
 	bool "ARM EABI stack unwinder"
-	depends on AEABI
+	depends on AEABI && !FUNCTION_GRAPH_TRACER
 	select ARM_UNWIND
 	help
 	  This option enables stack unwinding support in the kernel
diff --git a/arch/arm/boot/compressed/head.S b/arch/arm/boot/compressed/head.S
index 6c7ccb428c07..7135820f76d4 100644
--- a/arch/arm/boot/compressed/head.S
+++ b/arch/arm/boot/compressed/head.S
@@ -1438,7 +1438,21 @@ ENTRY(efi_stub_entry)
 
 		@ Preserve return value of efi_entry() in r4
 		mov	r4, r0
-		bl	cache_clean_flush
+
+		@ our cache maintenance code relies on CP15 barrier instructions
+		@ but since we arrived here with the MMU and caches configured
+		@ by UEFI, we must check that the CP15BEN bit is set in SCTLR.
+		@ Note that this bit is RAO/WI on v6 and earlier, so the ISB in
+		@ the enable path will be executed on v7+ only.
+		mrc	p15, 0, r1, c1, c0, 0	@ read SCTLR
+		tst	r1, #(1 << 5)		@ CP15BEN bit set?
+		bne	0f
+		orr	r1, r1, #(1 << 5)	@ CP15 barrier instructions
+		mcr	p15, 0, r1, c1, c0, 0	@ write SCTLR
+ ARM(		.inst	0xf57ff06f		@ v7+ isb	)
+ THUMB(		isb						)
+
+0:		bl	cache_clean_flush
 		bl	cache_off
 
 		@ Set parameters for booting zImage according to boot protocol
diff --git a/arch/arm/boot/dts/am335x-evm.dts b/arch/arm/boot/dts/am335x-evm.dts
index dce5be5df97b..edcff79879e7 100644
--- a/arch/arm/boot/dts/am335x-evm.dts
+++ b/arch/arm/boot/dts/am335x-evm.dts
@@ -57,6 +57,24 @@
 		enable-active-high;
 	};
 
+	/* TPS79501 */
+	v1_8d_reg: fixedregulator-v1_8d {
+		compatible = "regulator-fixed";
+		regulator-name = "v1_8d";
+		vin-supply = <&vbat>;
+		regulator-min-microvolt = <1800000>;
+		regulator-max-microvolt = <1800000>;
+	};
+
+	/* TPS79501 */
+	v3_3d_reg: fixedregulator-v3_3d {
+		compatible = "regulator-fixed";
+		regulator-name = "v3_3d";
+		vin-supply = <&vbat>;
+		regulator-min-microvolt = <3300000>;
+		regulator-max-microvolt = <3300000>;
+	};
+
 	matrix_keypad: matrix_keypad0 {
 		compatible = "gpio-matrix-keypad";
 		debounce-delay-ms = <5>;
@@ -499,10 +517,10 @@
 		status = "okay";
 
 		/* Regulators */
-		AVDD-supply = <&vaux2_reg>;
-		IOVDD-supply = <&vaux2_reg>;
-		DRVDD-supply = <&vaux2_reg>;
-		DVDD-supply = <&vbat>;
+		AVDD-supply = <&v3_3d_reg>;
+		IOVDD-supply = <&v3_3d_reg>;
+		DRVDD-supply = <&v3_3d_reg>;
+		DVDD-supply = <&v1_8d_reg>;
 	};
 };
 
diff --git a/arch/arm/boot/dts/am335x-evmsk.dts b/arch/arm/boot/dts/am335x-evmsk.dts
index b128998097ce..2c2d8b5b8cf5 100644
--- a/arch/arm/boot/dts/am335x-evmsk.dts
+++ b/arch/arm/boot/dts/am335x-evmsk.dts
@@ -73,6 +73,24 @@
 		enable-active-high;
 	};
 
+	/* TPS79518 */
+	v1_8d_reg: fixedregulator-v1_8d {
+		compatible = "regulator-fixed";
+		regulator-name = "v1_8d";
+		vin-supply = <&vbat>;
+		regulator-min-microvolt = <1800000>;
+		regulator-max-microvolt = <1800000>;
+	};
+
+	/* TPS78633 */
+	v3_3d_reg: fixedregulator-v3_3d {
+		compatible = "regulator-fixed";
+		regulator-name = "v3_3d";
+		vin-supply = <&vbat>;
+		regulator-min-microvolt = <3300000>;
+		regulator-max-microvolt = <3300000>;
+	};
+
 	leds {
 		pinctrl-names = "default";
 		pinctrl-0 = <&user_leds_s0>;
@@ -501,10 +519,10 @@
 		status = "okay";
 
 		/* Regulators */
-		AVDD-supply = <&vaux2_reg>;
-		IOVDD-supply = <&vaux2_reg>;
-		DRVDD-supply = <&vaux2_reg>;
-		DVDD-supply = <&vbat>;
+		AVDD-supply = <&v3_3d_reg>;
+		IOVDD-supply = <&v3_3d_reg>;
+		DRVDD-supply = <&v3_3d_reg>;
+		DVDD-supply = <&v1_8d_reg>;
 	};
 };
 
diff --git a/arch/arm/boot/dts/am33xx-l4.dtsi b/arch/arm/boot/dts/am33xx-l4.dtsi
index f459ec316a22..ca6d9f02a800 100644
--- a/arch/arm/boot/dts/am33xx-l4.dtsi
+++ b/arch/arm/boot/dts/am33xx-l4.dtsi
@@ -1762,7 +1762,7 @@
 			reg = <0xcc000 0x4>;
 			reg-names = "rev";
 			/* Domains (P, C): per_pwrdm, l4ls_clkdm */
-			clocks = <&l4ls_clkctrl AM3_D_CAN0_CLKCTRL 0>;
+			clocks = <&l4ls_clkctrl AM3_L4LS_D_CAN0_CLKCTRL 0>;
 			clock-names = "fck";
 			#address-cells = <1>;
 			#size-cells = <1>;
@@ -1785,7 +1785,7 @@
 			reg = <0xd0000 0x4>;
 			reg-names = "rev";
 			/* Domains (P, C): per_pwrdm, l4ls_clkdm */
-			clocks = <&l4ls_clkctrl AM3_D_CAN1_CLKCTRL 0>;
+			clocks = <&l4ls_clkctrl AM3_L4LS_D_CAN1_CLKCTRL 0>;
 			clock-names = "fck";
 			#address-cells = <1>;
 			#size-cells = <1>;
diff --git a/arch/arm/boot/dts/bcm2835-rpi-b-rev2.dts b/arch/arm/boot/dts/bcm2835-rpi-b-rev2.dts
index 5641d162dfdb..28e7513ce617 100644
--- a/arch/arm/boot/dts/bcm2835-rpi-b-rev2.dts
+++ b/arch/arm/boot/dts/bcm2835-rpi-b-rev2.dts
@@ -93,7 +93,7 @@
 };
 
 &hdmi {
-	hpd-gpios = <&gpio 46 GPIO_ACTIVE_LOW>;
+	hpd-gpios = <&gpio 46 GPIO_ACTIVE_HIGH>;
 };
 
 &pwm {
diff --git a/arch/arm/boot/dts/imx6dl-yapp4-common.dtsi b/arch/arm/boot/dts/imx6dl-yapp4-common.dtsi
index b715ab0fa1ff..e8d800fec637 100644
--- a/arch/arm/boot/dts/imx6dl-yapp4-common.dtsi
+++ b/arch/arm/boot/dts/imx6dl-yapp4-common.dtsi
@@ -114,9 +114,9 @@
 			reg = <2>;
 		};
 
-		switch@0 {
+		switch@10 {
 			compatible = "qca,qca8334";
-			reg = <0>;
+			reg = <10>;
 
 			switch_ports: ports {
 				#address-cells = <1>;
@@ -125,7 +125,7 @@
 				ethphy0: port@0 {
 					reg = <0>;
 					label = "cpu";
-					phy-mode = "rgmii";
+					phy-mode = "rgmii-id";
 					ethernet = <&fec>;
 
 					fixed-link {
diff --git a/arch/arm/boot/dts/imx6qdl-icore-rqs.dtsi b/arch/arm/boot/dts/imx6qdl-icore-rqs.dtsi
index 1d1b4bd0670f..a4217f564a53 100644
--- a/arch/arm/boot/dts/imx6qdl-icore-rqs.dtsi
+++ b/arch/arm/boot/dts/imx6qdl-icore-rqs.dtsi
@@ -264,7 +264,7 @@
 	pinctrl-2 = <&pinctrl_usdhc3_200mhz>;
 	vmcc-supply = <&reg_sd3_vmmc>;
 	cd-gpios = <&gpio1 1 GPIO_ACTIVE_LOW>;
-	bus-witdh = <4>;
+	bus-width = <4>;
 	no-1-8-v;
 	status = "okay";
 };
@@ -275,7 +275,7 @@
 	pinctrl-1 = <&pinctrl_usdhc4_100mhz>;
 	pinctrl-2 = <&pinctrl_usdhc4_200mhz>;
 	vmcc-supply = <&reg_sd4_vmmc>;
-	bus-witdh = <8>;
+	bus-width = <8>;
 	no-1-8-v;
 	non-removable;
 	status = "okay";
diff --git a/arch/arm/boot/dts/imx6qdl-phytec-pfla02.dtsi b/arch/arm/boot/dts/imx6qdl-phytec-pfla02.dtsi
index 433bf09a1954..027df06c5dc7 100644
--- a/arch/arm/boot/dts/imx6qdl-phytec-pfla02.dtsi
+++ b/arch/arm/boot/dts/imx6qdl-phytec-pfla02.dtsi
@@ -91,6 +91,7 @@
 	pinctrl-0 = <&pinctrl_enet>;
 	phy-handle = <&ethphy>;
 	phy-mode = "rgmii";
+	phy-reset-duration = <10>; /* in msecs */
 	phy-reset-gpios = <&gpio3 23 GPIO_ACTIVE_LOW>;
 	phy-supply = <&vdd_eth_io_reg>;
 	status = "disabled";
diff --git a/arch/arm/boot/dts/imx6ull-pinfunc-snvs.h b/arch/arm/boot/dts/imx6ull-pinfunc-snvs.h
index f6fb6783c193..54cfe72295aa 100644
--- a/arch/arm/boot/dts/imx6ull-pinfunc-snvs.h
+++ b/arch/arm/boot/dts/imx6ull-pinfunc-snvs.h
@@ -1,4 +1,4 @@
-// SPDX-License-Identifier: GPL-2.0
+/* SPDX-License-Identifier: GPL-2.0 */
 /*
  * Copyright (C) 2016 Freescale Semiconductor, Inc.
  * Copyright (C) 2017 NXP
diff --git a/arch/arm/boot/dts/rk3288-tinker.dtsi b/arch/arm/boot/dts/rk3288-tinker.dtsi
index aa107ee41b8b..ef653c3209bc 100644
--- a/arch/arm/boot/dts/rk3288-tinker.dtsi
+++ b/arch/arm/boot/dts/rk3288-tinker.dtsi
@@ -254,6 +254,7 @@
 			};
 
 			vccio_sd: LDO_REG5 {
+				regulator-boot-on;
 				regulator-min-microvolt = <1800000>;
 				regulator-max-microvolt = <3300000>;
 				regulator-name = "vccio_sd";
@@ -430,7 +431,7 @@
 	bus-width = <4>;
 	cap-mmc-highspeed;
 	cap-sd-highspeed;
-	card-detect-delay = <200>;
+	broken-cd;
 	disable-wp;			/* wp not hooked up */
 	pinctrl-names = "default";
 	pinctrl-0 = <&sdmmc_clk &sdmmc_cmd &sdmmc_cd &sdmmc_bus4>;
diff --git a/arch/arm/boot/dts/rk3288-veyron.dtsi b/arch/arm/boot/dts/rk3288-veyron.dtsi
index 0bc2409f6903..192dbc089ade 100644
--- a/arch/arm/boot/dts/rk3288-veyron.dtsi
+++ b/arch/arm/boot/dts/rk3288-veyron.dtsi
@@ -25,8 +25,6 @@
 
 	gpio_keys: gpio-keys {
 		compatible = "gpio-keys";
-		#address-cells = <1>;
-		#size-cells = <0>;
 
 		pinctrl-names = "default";
 		pinctrl-0 = <&pwr_key_l>;
diff --git a/arch/arm/boot/dts/rk3288.dtsi b/arch/arm/boot/dts/rk3288.dtsi
index ca7d52daa8fb..a024d1e7e74c 100644
--- a/arch/arm/boot/dts/rk3288.dtsi
+++ b/arch/arm/boot/dts/rk3288.dtsi
@@ -70,7 +70,7 @@
 			compatible = "arm,cortex-a12";
 			reg = <0x501>;
 			resets = <&cru SRST_CORE1>;
-			operating-points = <&cpu_opp_table>;
+			operating-points-v2 = <&cpu_opp_table>;
 			#cooling-cells = <2>; /* min followed by max */
 			clock-latency = <40000>;
 			clocks = <&cru ARMCLK>;
@@ -80,7 +80,7 @@
 			compatible = "arm,cortex-a12";
 			reg = <0x502>;
 			resets = <&cru SRST_CORE2>;
-			operating-points = <&cpu_opp_table>;
+			operating-points-v2 = <&cpu_opp_table>;
 			#cooling-cells = <2>; /* min followed by max */
 			clock-latency = <40000>;
 			clocks = <&cru ARMCLK>;
@@ -90,7 +90,7 @@
 			compatible = "arm,cortex-a12";
 			reg = <0x503>;
 			resets = <&cru SRST_CORE3>;
-			operating-points = <&cpu_opp_table>;
+			operating-points-v2 = <&cpu_opp_table>;
 			#cooling-cells = <2>; /* min followed by max */
 			clock-latency = <40000>;
 			clocks = <&cru ARMCLK>;
@@ -1119,8 +1119,6 @@
 		clock-names = "ref", "pclk";
 		power-domains = <&power RK3288_PD_VIO>;
 		rockchip,grf = <&grf>;
-		#address-cells = <1>;
-		#size-cells = <0>;
 		status = "disabled";
 
 		ports {
@@ -1282,27 +1280,27 @@
 	gpu_opp_table: gpu-opp-table {
 		compatible = "operating-points-v2";
 
-		opp@100000000 {
+		opp-100000000 {
 			opp-hz = /bits/ 64 <100000000>;
 			opp-microvolt = <950000>;
 		};
-		opp@200000000 {
+		opp-200000000 {
 			opp-hz = /bits/ 64 <200000000>;
 			opp-microvolt = <950000>;
 		};
-		opp@300000000 {
+		opp-300000000 {
 			opp-hz = /bits/ 64 <300000000>;
 			opp-microvolt = <1000000>;
 		};
-		opp@400000000 {
+		opp-400000000 {
 			opp-hz = /bits/ 64 <400000000>;
 			opp-microvolt = <1100000>;
 		};
-		opp@500000000 {
+		opp-500000000 {
 			opp-hz = /bits/ 64 <500000000>;
 			opp-microvolt = <1200000>;
 		};
-		opp@600000000 {
+		opp-600000000 {
 			opp-hz = /bits/ 64 <600000000>;
 			opp-microvolt = <1250000>;
 		};
diff --git a/arch/arm/boot/dts/sama5d2-pinfunc.h b/arch/arm/boot/dts/sama5d2-pinfunc.h
index 1c01a6f843d8..28a2e45752fe 100644
--- a/arch/arm/boot/dts/sama5d2-pinfunc.h
+++ b/arch/arm/boot/dts/sama5d2-pinfunc.h
@@ -518,7 +518,7 @@
 #define PIN_PC9__GPIO			PINMUX_PIN(PIN_PC9, 0, 0)
 #define PIN_PC9__FIQ			PINMUX_PIN(PIN_PC9, 1, 3)
 #define PIN_PC9__GTSUCOMP		PINMUX_PIN(PIN_PC9, 2, 1)
-#define PIN_PC9__ISC_D0			PINMUX_PIN(PIN_PC9, 2, 1)
+#define PIN_PC9__ISC_D0			PINMUX_PIN(PIN_PC9, 3, 1)
 #define PIN_PC9__TIOA4			PINMUX_PIN(PIN_PC9, 4, 2)
 #define PIN_PC10			74
 #define PIN_PC10__GPIO			PINMUX_PIN(PIN_PC10, 0, 0)
diff --git a/arch/arm/configs/imx_v4_v5_defconfig b/arch/arm/configs/imx_v4_v5_defconfig
index 8661dd9b064a..b37f8e675e40 100644
--- a/arch/arm/configs/imx_v4_v5_defconfig
+++ b/arch/arm/configs/imx_v4_v5_defconfig
@@ -170,6 +170,9 @@ CONFIG_IMX_SDMA=y
 # CONFIG_IOMMU_SUPPORT is not set
 CONFIG_IIO=y
 CONFIG_FSL_MX25_ADC=y
+CONFIG_PWM=y
+CONFIG_PWM_IMX1=y
+CONFIG_PWM_IMX27=y
 CONFIG_EXT4_FS=y
 # CONFIG_DNOTIFY is not set
 CONFIG_VFAT_FS=y
diff --git a/arch/arm/configs/imx_v6_v7_defconfig b/arch/arm/configs/imx_v6_v7_defconfig
index 5586a5074a96..50fb01d70b10 100644
--- a/arch/arm/configs/imx_v6_v7_defconfig
+++ b/arch/arm/configs/imx_v6_v7_defconfig
@@ -398,7 +398,7 @@ CONFIG_MAG3110=y
 CONFIG_MPL3115=y
 CONFIG_PWM=y
 CONFIG_PWM_FSL_FTM=y
-CONFIG_PWM_IMX=y
+CONFIG_PWM_IMX27=y
 CONFIG_NVMEM_IMX_OCOTP=y
 CONFIG_NVMEM_VF610_OCOTP=y
 CONFIG_TEE=y
diff --git a/arch/arm/crypto/aes-neonbs-glue.c b/arch/arm/crypto/aes-neonbs-glue.c
index 07e31941dc67..617c2c99ebfb 100644
--- a/arch/arm/crypto/aes-neonbs-glue.c
+++ b/arch/arm/crypto/aes-neonbs-glue.c
@@ -278,6 +278,8 @@ static int __xts_crypt(struct skcipher_request *req,
 	int err;
 
 	err = skcipher_walk_virt(&walk, req, true);
+	if (err)
+		return err;
 
 	crypto_cipher_encrypt_one(ctx->tweak_tfm, walk.iv, walk.iv);
 
diff --git a/arch/arm/crypto/chacha-neon-glue.c b/arch/arm/crypto/chacha-neon-glue.c
index 9d6fda81986d..48a89537b828 100644
--- a/arch/arm/crypto/chacha-neon-glue.c
+++ b/arch/arm/crypto/chacha-neon-glue.c
@@ -21,6 +21,7 @@
 
 #include <crypto/algapi.h>
 #include <crypto/chacha.h>
+#include <crypto/internal/simd.h>
 #include <crypto/internal/skcipher.h>
 #include <linux/kernel.h>
 #include <linux/module.h>
@@ -93,7 +94,7 @@ static int chacha_neon(struct skcipher_request *req)
 	struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(req);
 	struct chacha_ctx *ctx = crypto_skcipher_ctx(tfm);
 
-	if (req->cryptlen <= CHACHA_BLOCK_SIZE || !may_use_simd())
+	if (req->cryptlen <= CHACHA_BLOCK_SIZE || !crypto_simd_usable())
 		return crypto_chacha_crypt(req);
 
 	return chacha_neon_stream_xor(req, ctx, req->iv);
@@ -107,7 +108,7 @@ static int xchacha_neon(struct skcipher_request *req)
 	u32 state[16];
 	u8 real_iv[16];
 
-	if (req->cryptlen <= CHACHA_BLOCK_SIZE || !may_use_simd())
+	if (req->cryptlen <= CHACHA_BLOCK_SIZE || !crypto_simd_usable())
 		return crypto_xchacha_crypt(req);
 
 	crypto_chacha_init(state, ctx, req->iv);
diff --git a/arch/arm/crypto/crc32-ce-glue.c b/arch/arm/crypto/crc32-ce-glue.c
index cd9e93b46c2d..e712c2a7d387 100644
--- a/arch/arm/crypto/crc32-ce-glue.c
+++ b/arch/arm/crypto/crc32-ce-glue.c
@@ -16,6 +16,7 @@
 #include <linux/string.h>
 
 #include <crypto/internal/hash.h>
+#include <crypto/internal/simd.h>
 
 #include <asm/hwcap.h>
 #include <asm/neon.h>
@@ -113,7 +114,7 @@ static int crc32_pmull_update(struct shash_desc *desc, const u8 *data,
 	u32 *crc = shash_desc_ctx(desc);
 	unsigned int l;
 
-	if (may_use_simd()) {
+	if (crypto_simd_usable()) {
 		if ((u32)data % SCALE_F) {
 			l = min_t(u32, length, SCALE_F - ((u32)data % SCALE_F));
 
@@ -147,7 +148,7 @@ static int crc32c_pmull_update(struct shash_desc *desc, const u8 *data,
 	u32 *crc = shash_desc_ctx(desc);
 	unsigned int l;
 
-	if (may_use_simd()) {
+	if (crypto_simd_usable()) {
 		if ((u32)data % SCALE_F) {
 			l = min_t(u32, length, SCALE_F - ((u32)data % SCALE_F));
 
diff --git a/arch/arm/crypto/crct10dif-ce-glue.c b/arch/arm/crypto/crct10dif-ce-glue.c
index 3d6b800b8396..3b24f2872592 100644
--- a/arch/arm/crypto/crct10dif-ce-glue.c
+++ b/arch/arm/crypto/crct10dif-ce-glue.c
@@ -15,6 +15,7 @@
 #include <linux/string.h>
 
 #include <crypto/internal/hash.h>
+#include <crypto/internal/simd.h>
 
 #include <asm/neon.h>
 #include <asm/simd.h>
@@ -36,7 +37,7 @@ static int crct10dif_update(struct shash_desc *desc, const u8 *data,
 {
 	u16 *crc = shash_desc_ctx(desc);
 
-	if (length >= CRC_T10DIF_PMULL_CHUNK_SIZE && may_use_simd()) {
+	if (length >= CRC_T10DIF_PMULL_CHUNK_SIZE && crypto_simd_usable()) {
 		kernel_neon_begin();
 		*crc = crc_t10dif_pmull(*crc, data, length);
 		kernel_neon_end();
diff --git a/arch/arm/crypto/ghash-ce-glue.c b/arch/arm/crypto/ghash-ce-glue.c
index b7d30b6cf49c..39d1ccec1aab 100644
--- a/arch/arm/crypto/ghash-ce-glue.c
+++ b/arch/arm/crypto/ghash-ce-glue.c
@@ -14,6 +14,7 @@
 #include <asm/unaligned.h>
 #include <crypto/cryptd.h>
 #include <crypto/internal/hash.h>
+#include <crypto/internal/simd.h>
 #include <crypto/gf128mul.h>
 #include <linux/cpufeature.h>
 #include <linux/crypto.h>
@@ -185,7 +186,6 @@ static int ghash_async_init(struct ahash_request *req)
 	struct crypto_shash *child = cryptd_ahash_child(cryptd_tfm);
 
 	desc->tfm = child;
-	desc->flags = req->base.flags;
 	return crypto_shash_init(desc);
 }
 
@@ -196,7 +196,7 @@ static int ghash_async_update(struct ahash_request *req)
 	struct ghash_async_ctx *ctx = crypto_ahash_ctx(tfm);
 	struct cryptd_ahash *cryptd_tfm = ctx->cryptd_tfm;
 
-	if (!may_use_simd() ||
+	if (!crypto_simd_usable() ||
 	    (in_atomic() && cryptd_ahash_queued(cryptd_tfm))) {
 		memcpy(cryptd_req, req, sizeof(*req));
 		ahash_request_set_tfm(cryptd_req, &cryptd_tfm->base);
@@ -214,7 +214,7 @@ static int ghash_async_final(struct ahash_request *req)
 	struct ghash_async_ctx *ctx = crypto_ahash_ctx(tfm);
 	struct cryptd_ahash *cryptd_tfm = ctx->cryptd_tfm;
 
-	if (!may_use_simd() ||
+	if (!crypto_simd_usable() ||
 	    (in_atomic() && cryptd_ahash_queued(cryptd_tfm))) {
 		memcpy(cryptd_req, req, sizeof(*req));
 		ahash_request_set_tfm(cryptd_req, &cryptd_tfm->base);
@@ -232,7 +232,7 @@ static int ghash_async_digest(struct ahash_request *req)
 	struct ahash_request *cryptd_req = ahash_request_ctx(req);
 	struct cryptd_ahash *cryptd_tfm = ctx->cryptd_tfm;
 
-	if (!may_use_simd() ||
+	if (!crypto_simd_usable() ||
 	    (in_atomic() && cryptd_ahash_queued(cryptd_tfm))) {
 		memcpy(cryptd_req, req, sizeof(*req));
 		ahash_request_set_tfm(cryptd_req, &cryptd_tfm->base);
@@ -242,7 +242,6 @@ static int ghash_async_digest(struct ahash_request *req)
 		struct crypto_shash *child = cryptd_ahash_child(cryptd_tfm);
 
 		desc->tfm = child;
-		desc->flags = req->base.flags;
 		return shash_ahash_digest(req, desc);
 	}
 }
@@ -255,7 +254,6 @@ static int ghash_async_import(struct ahash_request *req, const void *in)
 	struct shash_desc *desc = cryptd_shash_desc(cryptd_req);
 
 	desc->tfm = cryptd_ahash_child(ctx->cryptd_tfm);
-	desc->flags = req->base.flags;
 
 	return crypto_shash_import(desc, in);
 }
diff --git a/arch/arm/crypto/nhpoly1305-neon-glue.c b/arch/arm/crypto/nhpoly1305-neon-glue.c
index 49aae87cb2bc..ae5aefc44a4d 100644
--- a/arch/arm/crypto/nhpoly1305-neon-glue.c
+++ b/arch/arm/crypto/nhpoly1305-neon-glue.c
@@ -9,6 +9,7 @@
 #include <asm/neon.h>
 #include <asm/simd.h>
 #include <crypto/internal/hash.h>
+#include <crypto/internal/simd.h>
 #include <crypto/nhpoly1305.h>
 #include <linux/module.h>
 
@@ -25,7 +26,7 @@ static void _nh_neon(const u32 *key, const u8 *message, size_t message_len,
 static int nhpoly1305_neon_update(struct shash_desc *desc,
 				  const u8 *src, unsigned int srclen)
 {
-	if (srclen < 64 || !may_use_simd())
+	if (srclen < 64 || !crypto_simd_usable())
 		return crypto_nhpoly1305_update(desc, src, srclen);
 
 	do {
diff --git a/arch/arm/crypto/sha1-ce-glue.c b/arch/arm/crypto/sha1-ce-glue.c
index b732522e20f8..4c6c6900853c 100644
--- a/arch/arm/crypto/sha1-ce-glue.c
+++ b/arch/arm/crypto/sha1-ce-glue.c
@@ -9,6 +9,7 @@
  */
 
 #include <crypto/internal/hash.h>
+#include <crypto/internal/simd.h>
 #include <crypto/sha.h>
 #include <crypto/sha1_base.h>
 #include <linux/cpufeature.h>
@@ -33,7 +34,7 @@ static int sha1_ce_update(struct shash_desc *desc, const u8 *data,
 {
 	struct sha1_state *sctx = shash_desc_ctx(desc);
 
-	if (!may_use_simd() ||
+	if (!crypto_simd_usable() ||
 	    (sctx->count % SHA1_BLOCK_SIZE) + len < SHA1_BLOCK_SIZE)
 		return sha1_update_arm(desc, data, len);
 
@@ -47,7 +48,7 @@ static int sha1_ce_update(struct shash_desc *desc, const u8 *data,
 static int sha1_ce_finup(struct shash_desc *desc, const u8 *data,
 			 unsigned int len, u8 *out)
 {
-	if (!may_use_simd())
+	if (!crypto_simd_usable())
 		return sha1_finup_arm(desc, data, len, out);
 
 	kernel_neon_begin();
diff --git a/arch/arm/crypto/sha1_neon_glue.c b/arch/arm/crypto/sha1_neon_glue.c
index d15e0ea2c95e..d6c95c213d42 100644
--- a/arch/arm/crypto/sha1_neon_glue.c
+++ b/arch/arm/crypto/sha1_neon_glue.c
@@ -19,6 +19,7 @@
  */
 
 #include <crypto/internal/hash.h>
+#include <crypto/internal/simd.h>
 #include <linux/init.h>
 #include <linux/module.h>
 #include <linux/mm.h>
@@ -39,7 +40,7 @@ static int sha1_neon_update(struct shash_desc *desc, const u8 *data,
 {
 	struct sha1_state *sctx = shash_desc_ctx(desc);
 
-	if (!may_use_simd() ||
+	if (!crypto_simd_usable() ||
 	    (sctx->count % SHA1_BLOCK_SIZE) + len < SHA1_BLOCK_SIZE)
 		return sha1_update_arm(desc, data, len);
 
@@ -54,7 +55,7 @@ static int sha1_neon_update(struct shash_desc *desc, const u8 *data,
 static int sha1_neon_finup(struct shash_desc *desc, const u8 *data,
 			   unsigned int len, u8 *out)
 {
-	if (!may_use_simd())
+	if (!crypto_simd_usable())
 		return sha1_finup_arm(desc, data, len, out);
 
 	kernel_neon_begin();
diff --git a/arch/arm/crypto/sha2-ce-glue.c b/arch/arm/crypto/sha2-ce-glue.c
index 1211a5c129fc..a47a9d4b663e 100644
--- a/arch/arm/crypto/sha2-ce-glue.c
+++ b/arch/arm/crypto/sha2-ce-glue.c
@@ -9,6 +9,7 @@
  */
 
 #include <crypto/internal/hash.h>
+#include <crypto/internal/simd.h>
 #include <crypto/sha.h>
 #include <crypto/sha256_base.h>
 #include <linux/cpufeature.h>
@@ -34,7 +35,7 @@ static int sha2_ce_update(struct shash_desc *desc, const u8 *data,
 {
 	struct sha256_state *sctx = shash_desc_ctx(desc);
 
-	if (!may_use_simd() ||
+	if (!crypto_simd_usable() ||
 	    (sctx->count % SHA256_BLOCK_SIZE) + len < SHA256_BLOCK_SIZE)
 		return crypto_sha256_arm_update(desc, data, len);
 
@@ -49,7 +50,7 @@ static int sha2_ce_update(struct shash_desc *desc, const u8 *data,
 static int sha2_ce_finup(struct shash_desc *desc, const u8 *data,
 			 unsigned int len, u8 *out)
 {
-	if (!may_use_simd())
+	if (!crypto_simd_usable())
 		return crypto_sha256_arm_finup(desc, data, len, out);
 
 	kernel_neon_begin();
diff --git a/arch/arm/crypto/sha256_neon_glue.c b/arch/arm/crypto/sha256_neon_glue.c
index 1d82c6cd31a4..f3f6b1624fc3 100644
--- a/arch/arm/crypto/sha256_neon_glue.c
+++ b/arch/arm/crypto/sha256_neon_glue.c
@@ -15,6 +15,7 @@
  */
 
 #include <crypto/internal/hash.h>
+#include <crypto/internal/simd.h>
 #include <linux/cryptohash.h>
 #include <linux/types.h>
 #include <linux/string.h>
@@ -34,7 +35,7 @@ static int sha256_update(struct shash_desc *desc, const u8 *data,
 {
 	struct sha256_state *sctx = shash_desc_ctx(desc);
 
-	if (!may_use_simd() ||
+	if (!crypto_simd_usable() ||
 	    (sctx->count % SHA256_BLOCK_SIZE) + len < SHA256_BLOCK_SIZE)
 		return crypto_sha256_arm_update(desc, data, len);
 
@@ -49,7 +50,7 @@ static int sha256_update(struct shash_desc *desc, const u8 *data,
 static int sha256_finup(struct shash_desc *desc, const u8 *data,
 			unsigned int len, u8 *out)
 {
-	if (!may_use_simd())
+	if (!crypto_simd_usable())
 		return crypto_sha256_arm_finup(desc, data, len, out);
 
 	kernel_neon_begin();
diff --git a/arch/arm/crypto/sha512-neon-glue.c b/arch/arm/crypto/sha512-neon-glue.c
index 8a5642b41fd6..d33ab59c26c0 100644
--- a/arch/arm/crypto/sha512-neon-glue.c
+++ b/arch/arm/crypto/sha512-neon-glue.c
@@ -9,6 +9,7 @@
  */
 
 #include <crypto/internal/hash.h>
+#include <crypto/internal/simd.h>
 #include <crypto/sha.h>
 #include <crypto/sha512_base.h>
 #include <linux/crypto.h>
@@ -30,7 +31,7 @@ static int sha512_neon_update(struct shash_desc *desc, const u8 *data,
 {
 	struct sha512_state *sctx = shash_desc_ctx(desc);
 
-	if (!may_use_simd() ||
+	if (!crypto_simd_usable() ||
 	    (sctx->count[0] % SHA512_BLOCK_SIZE) + len < SHA512_BLOCK_SIZE)
 		return sha512_arm_update(desc, data, len);
 
@@ -45,7 +46,7 @@ static int sha512_neon_update(struct shash_desc *desc, const u8 *data,
 static int sha512_neon_finup(struct shash_desc *desc, const u8 *data,
 			     unsigned int len, u8 *out)
 {
-	if (!may_use_simd())
+	if (!crypto_simd_usable())
 		return sha512_arm_finup(desc, data, len, out);
 
 	kernel_neon_begin();
diff --git a/arch/arm/include/asm/Kbuild b/arch/arm/include/asm/Kbuild
index a8a4eb7f6dae..41deac2451af 100644
--- a/arch/arm/include/asm/Kbuild
+++ b/arch/arm/include/asm/Kbuild
@@ -9,10 +9,10 @@ generic-y += kdebug.h
 generic-y += local.h
 generic-y += local64.h
 generic-y += mm-arch-hooks.h
+generic-y += mmiowb.h
 generic-y += msi.h
 generic-y += parport.h
 generic-y += preempt.h
-generic-y += rwsem.h
 generic-y += seccomp.h
 generic-y += segment.h
 generic-y += serial.h
diff --git a/arch/arm/include/asm/arch_timer.h b/arch/arm/include/asm/arch_timer.h
index 0a8d7bba2cb0..4b66ecd6be99 100644
--- a/arch/arm/include/asm/arch_timer.h
+++ b/arch/arm/include/asm/arch_timer.h
@@ -11,6 +11,10 @@
 #include <clocksource/arm_arch_timer.h>
 
 #ifdef CONFIG_ARM_ARCH_TIMER
+/* 32bit ARM doesn't know anything about timer errata... */
+#define has_erratum_handler(h)		(false)
+#define erratum_handler(h)		(arch_timer_##h)
+
 int arch_timer_arch_init(void);
 
 /*
@@ -79,7 +83,7 @@ static inline u32 arch_timer_get_cntfrq(void)
 	return val;
 }
 
-static inline u64 arch_counter_get_cntpct(void)
+static inline u64 __arch_counter_get_cntpct(void)
 {
 	u64 cval;
 
@@ -88,7 +92,12 @@ static inline u64 arch_counter_get_cntpct(void)
 	return cval;
 }
 
-static inline u64 arch_counter_get_cntvct(void)
+static inline u64 __arch_counter_get_cntpct_stable(void)
+{
+	return __arch_counter_get_cntpct();
+}
+
+static inline u64 __arch_counter_get_cntvct(void)
 {
 	u64 cval;
 
@@ -97,6 +106,11 @@ static inline u64 arch_counter_get_cntvct(void)
 	return cval;
 }
 
+static inline u64 __arch_counter_get_cntvct_stable(void)
+{
+	return __arch_counter_get_cntvct();
+}
+
 static inline u32 arch_timer_get_cntkctl(void)
 {
 	u32 cntkctl;
diff --git a/arch/arm/include/asm/cp15.h b/arch/arm/include/asm/cp15.h
index 07e27f212dc7..d2453e2d3f1f 100644
--- a/arch/arm/include/asm/cp15.h
+++ b/arch/arm/include/asm/cp15.h
@@ -68,6 +68,8 @@
 #define BPIALL				__ACCESS_CP15(c7, 0, c5, 6)
 #define ICIALLU				__ACCESS_CP15(c7, 0, c5, 0)
 
+#define CNTVCT				__ACCESS_CP15_64(1, c14)
+
 extern unsigned long cr_alignment;	/* defined in entry-armv.S */
 
 static inline unsigned long get_cr(void)
diff --git a/arch/arm/include/asm/io.h b/arch/arm/include/asm/io.h
index 6b51826ab3d1..7e22c81398c4 100644
--- a/arch/arm/include/asm/io.h
+++ b/arch/arm/include/asm/io.h
@@ -281,8 +281,6 @@ extern void _memcpy_fromio(void *, const volatile void __iomem *, size_t);
 extern void _memcpy_toio(volatile void __iomem *, const void *, size_t);
 extern void _memset_io(volatile void __iomem *, int, size_t);
 
-#define mmiowb()
-
 /*
  *  Memory access primitives
  *  ------------------------
diff --git a/arch/arm/include/asm/kvm_mmu.h b/arch/arm/include/asm/kvm_mmu.h
index 2de96a180166..31de4ab93005 100644
--- a/arch/arm/include/asm/kvm_mmu.h
+++ b/arch/arm/include/asm/kvm_mmu.h
@@ -381,6 +381,17 @@ static inline int kvm_read_guest_lock(struct kvm *kvm,
 	return ret;
 }
 
+static inline int kvm_write_guest_lock(struct kvm *kvm, gpa_t gpa,
+				       const void *data, unsigned long len)
+{
+	int srcu_idx = srcu_read_lock(&kvm->srcu);
+	int ret = kvm_write_guest(kvm, gpa, data, len);
+
+	srcu_read_unlock(&kvm->srcu, srcu_idx);
+
+	return ret;
+}
+
 static inline void *kvm_get_hyp_vector(void)
 {
 	switch(read_cpuid_part()) {
diff --git a/arch/arm/include/asm/stage2_pgtable.h b/arch/arm/include/asm/stage2_pgtable.h
index de2089501b8b..9587517649bd 100644
--- a/arch/arm/include/asm/stage2_pgtable.h
+++ b/arch/arm/include/asm/stage2_pgtable.h
@@ -32,14 +32,14 @@
 #define stage2_pgd_present(kvm, pgd)		pgd_present(pgd)
 #define stage2_pgd_populate(kvm, pgd, pud)	pgd_populate(NULL, pgd, pud)
 #define stage2_pud_offset(kvm, pgd, address)	pud_offset(pgd, address)
-#define stage2_pud_free(kvm, pud)		pud_free(NULL, pud)
+#define stage2_pud_free(kvm, pud)		do { } while (0)
 
 #define stage2_pud_none(kvm, pud)		pud_none(pud)
 #define stage2_pud_clear(kvm, pud)		pud_clear(pud)
 #define stage2_pud_present(kvm, pud)		pud_present(pud)
 #define stage2_pud_populate(kvm, pud, pmd)	pud_populate(NULL, pud, pmd)
 #define stage2_pmd_offset(kvm, pud, address)	pmd_offset(pud, address)
-#define stage2_pmd_free(kvm, pmd)		pmd_free(NULL, pmd)
+#define stage2_pmd_free(kvm, pmd)		free_page((unsigned long)pmd)
 
 #define stage2_pud_huge(kvm, pud)		pud_huge(pud)
 
@@ -75,6 +75,8 @@ static inline bool kvm_stage2_has_pud(struct kvm *kvm)
 
 #define S2_PMD_MASK				PMD_MASK
 #define S2_PMD_SIZE				PMD_SIZE
+#define S2_PUD_MASK				PUD_MASK
+#define S2_PUD_SIZE				PUD_SIZE
 
 static inline bool kvm_stage2_has_pmd(struct kvm *kvm)
 {
diff --git a/arch/arm/include/asm/syscall.h b/arch/arm/include/asm/syscall.h
index 06dea6bce293..080ce70cab12 100644
--- a/arch/arm/include/asm/syscall.h
+++ b/arch/arm/include/asm/syscall.h
@@ -55,53 +55,22 @@ static inline void syscall_set_return_value(struct task_struct *task,
 
 static inline void syscall_get_arguments(struct task_struct *task,
 					 struct pt_regs *regs,
-					 unsigned int i, unsigned int n,
 					 unsigned long *args)
 {
-	if (n == 0)
-		return;
-
-	if (i + n > SYSCALL_MAX_ARGS) {
-		unsigned long *args_bad = args + SYSCALL_MAX_ARGS - i;
-		unsigned int n_bad = n + i - SYSCALL_MAX_ARGS;
-		pr_warn("%s called with max args %d, handling only %d\n",
-			__func__, i + n, SYSCALL_MAX_ARGS);
-		memset(args_bad, 0, n_bad * sizeof(args[0]));
-		n = SYSCALL_MAX_ARGS - i;
-	}
-
-	if (i == 0) {
-		args[0] = regs->ARM_ORIG_r0;
-		args++;
-		i++;
-		n--;
-	}
-
-	memcpy(args, &regs->ARM_r0 + i, n * sizeof(args[0]));
+	args[0] = regs->ARM_ORIG_r0;
+	args++;
+
+	memcpy(args, &regs->ARM_r0 + 1, 5 * sizeof(args[0]));
 }
 
 static inline void syscall_set_arguments(struct task_struct *task,
 					 struct pt_regs *regs,
-					 unsigned int i, unsigned int n,
 					 const unsigned long *args)
 {
-	if (n == 0)
-		return;
-
-	if (i + n > SYSCALL_MAX_ARGS) {
-		pr_warn("%s called with max args %d, handling only %d\n",
-			__func__, i + n, SYSCALL_MAX_ARGS);
-		n = SYSCALL_MAX_ARGS - i;
-	}
-
-	if (i == 0) {
-		regs->ARM_ORIG_r0 = args[0];
-		args++;
-		i++;
-		n--;
-	}
-
-	memcpy(&regs->ARM_r0 + i, args, n * sizeof(args[0]));
+	regs->ARM_ORIG_r0 = args[0];
+	args++;
+
+	memcpy(&regs->ARM_r0 + 1, args, 5 * sizeof(args[0]));
 }
 
 static inline int syscall_get_arch(void)
diff --git a/arch/arm/include/asm/tlb.h b/arch/arm/include/asm/tlb.h
index f854148c8d7c..bc6d04a09899 100644
--- a/arch/arm/include/asm/tlb.h
+++ b/arch/arm/include/asm/tlb.h
@@ -33,271 +33,42 @@
 #include <asm/pgalloc.h>
 #include <asm/tlbflush.h>
 
-#define MMU_GATHER_BUNDLE	8
-
-#ifdef CONFIG_HAVE_RCU_TABLE_FREE
 static inline void __tlb_remove_table(void *_table)
 {
 	free_page_and_swap_cache((struct page *)_table);
 }
 
-struct mmu_table_batch {
-	struct rcu_head		rcu;
-	unsigned int		nr;
-	void			*tables[0];
-};
-
-#define MAX_TABLE_BATCH		\
-	((PAGE_SIZE - sizeof(struct mmu_table_batch)) / sizeof(void *))
-
-extern void tlb_table_flush(struct mmu_gather *tlb);
-extern void tlb_remove_table(struct mmu_gather *tlb, void *table);
-
-#define tlb_remove_entry(tlb, entry)	tlb_remove_table(tlb, entry)
-#else
-#define tlb_remove_entry(tlb, entry)	tlb_remove_page(tlb, entry)
-#endif /* CONFIG_HAVE_RCU_TABLE_FREE */
-
-/*
- * TLB handling.  This allows us to remove pages from the page
- * tables, and efficiently handle the TLB issues.
- */
-struct mmu_gather {
-	struct mm_struct	*mm;
-#ifdef CONFIG_HAVE_RCU_TABLE_FREE
-	struct mmu_table_batch	*batch;
-	unsigned int		need_flush;
-#endif
-	unsigned int		fullmm;
-	struct vm_area_struct	*vma;
-	unsigned long		start, end;
-	unsigned long		range_start;
-	unsigned long		range_end;
-	unsigned int		nr;
-	unsigned int		max;
-	struct page		**pages;
-	struct page		*local[MMU_GATHER_BUNDLE];
-};
-
-DECLARE_PER_CPU(struct mmu_gather, mmu_gathers);
-
-/*
- * This is unnecessarily complex.  There's three ways the TLB shootdown
- * code is used:
- *  1. Unmapping a range of vmas.  See zap_page_range(), unmap_region().
- *     tlb->fullmm = 0, and tlb_start_vma/tlb_end_vma will be called.
- *     tlb->vma will be non-NULL.
- *  2. Unmapping all vmas.  See exit_mmap().
- *     tlb->fullmm = 1, and tlb_start_vma/tlb_end_vma will be called.
- *     tlb->vma will be non-NULL.  Additionally, page tables will be freed.
- *  3. Unmapping argument pages.  See shift_arg_pages().
- *     tlb->fullmm = 0, but tlb_start_vma/tlb_end_vma will not be called.
- *     tlb->vma will be NULL.
- */
-static inline void tlb_flush(struct mmu_gather *tlb)
-{
-	if (tlb->fullmm || !tlb->vma)
-		flush_tlb_mm(tlb->mm);
-	else if (tlb->range_end > 0) {
-		flush_tlb_range(tlb->vma, tlb->range_start, tlb->range_end);
-		tlb->range_start = TASK_SIZE;
-		tlb->range_end = 0;
-	}
-}
-
-static inline void tlb_add_flush(struct mmu_gather *tlb, unsigned long addr)
-{
-	if (!tlb->fullmm) {
-		if (addr < tlb->range_start)
-			tlb->range_start = addr;
-		if (addr + PAGE_SIZE > tlb->range_end)
-			tlb->range_end = addr + PAGE_SIZE;
-	}
-}
-
-static inline void __tlb_alloc_page(struct mmu_gather *tlb)
-{
-	unsigned long addr = __get_free_pages(GFP_NOWAIT | __GFP_NOWARN, 0);
-
-	if (addr) {
-		tlb->pages = (void *)addr;
-		tlb->max = PAGE_SIZE / sizeof(struct page *);
-	}
-}
-
-static inline void tlb_flush_mmu_tlbonly(struct mmu_gather *tlb)
-{
-	tlb_flush(tlb);
-#ifdef CONFIG_HAVE_RCU_TABLE_FREE
-	tlb_table_flush(tlb);
-#endif
-}
-
-static inline void tlb_flush_mmu_free(struct mmu_gather *tlb)
-{
-	free_pages_and_swap_cache(tlb->pages, tlb->nr);
-	tlb->nr = 0;
-	if (tlb->pages == tlb->local)
-		__tlb_alloc_page(tlb);
-}
-
-static inline void tlb_flush_mmu(struct mmu_gather *tlb)
-{
-	tlb_flush_mmu_tlbonly(tlb);
-	tlb_flush_mmu_free(tlb);
-}
-
-static inline void
-arch_tlb_gather_mmu(struct mmu_gather *tlb, struct mm_struct *mm,
-			unsigned long start, unsigned long end)
-{
-	tlb->mm = mm;
-	tlb->fullmm = !(start | (end+1));
-	tlb->start = start;
-	tlb->end = end;
-	tlb->vma = NULL;
-	tlb->max = ARRAY_SIZE(tlb->local);
-	tlb->pages = tlb->local;
-	tlb->nr = 0;
-	__tlb_alloc_page(tlb);
+#include <asm-generic/tlb.h>
 
-#ifdef CONFIG_HAVE_RCU_TABLE_FREE
-	tlb->batch = NULL;
+#ifndef CONFIG_HAVE_RCU_TABLE_FREE
+#define tlb_remove_table(tlb, entry) tlb_remove_page(tlb, entry)
 #endif
-}
-
-static inline void
-arch_tlb_finish_mmu(struct mmu_gather *tlb,
-			unsigned long start, unsigned long end, bool force)
-{
-	if (force) {
-		tlb->range_start = start;
-		tlb->range_end = end;
-	}
-
-	tlb_flush_mmu(tlb);
-
-	/* keep the page table cache within bounds */
-	check_pgt_cache();
-
-	if (tlb->pages != tlb->local)
-		free_pages((unsigned long)tlb->pages, 0);
-}
-
-/*
- * Memorize the range for the TLB flush.
- */
-static inline void
-tlb_remove_tlb_entry(struct mmu_gather *tlb, pte_t *ptep, unsigned long addr)
-{
-	tlb_add_flush(tlb, addr);
-}
-
-#define tlb_remove_huge_tlb_entry(h, tlb, ptep, address)	\
-	tlb_remove_tlb_entry(tlb, ptep, address)
-/*
- * In the case of tlb vma handling, we can optimise these away in the
- * case where we're doing a full MM flush.  When we're doing a munmap,
- * the vmas are adjusted to only cover the region to be torn down.
- */
-static inline void
-tlb_start_vma(struct mmu_gather *tlb, struct vm_area_struct *vma)
-{
-	if (!tlb->fullmm) {
-		flush_cache_range(vma, vma->vm_start, vma->vm_end);
-		tlb->vma = vma;
-		tlb->range_start = TASK_SIZE;
-		tlb->range_end = 0;
-	}
-}
 
 static inline void
-tlb_end_vma(struct mmu_gather *tlb, struct vm_area_struct *vma)
-{
-	if (!tlb->fullmm)
-		tlb_flush(tlb);
-}
-
-static inline bool __tlb_remove_page(struct mmu_gather *tlb, struct page *page)
-{
-	tlb->pages[tlb->nr++] = page;
-	VM_WARN_ON(tlb->nr > tlb->max);
-	if (tlb->nr == tlb->max)
-		return true;
-	return false;
-}
-
-static inline void tlb_remove_page(struct mmu_gather *tlb, struct page *page)
-{
-	if (__tlb_remove_page(tlb, page))
-		tlb_flush_mmu(tlb);
-}
-
-static inline bool __tlb_remove_page_size(struct mmu_gather *tlb,
-					  struct page *page, int page_size)
-{
-	return __tlb_remove_page(tlb, page);
-}
-
-static inline void tlb_remove_page_size(struct mmu_gather *tlb,
-					struct page *page, int page_size)
-{
-	return tlb_remove_page(tlb, page);
-}
-
-static inline void __pte_free_tlb(struct mmu_gather *tlb, pgtable_t pte,
-	unsigned long addr)
+__pte_free_tlb(struct mmu_gather *tlb, pgtable_t pte, unsigned long addr)
 {
 	pgtable_page_dtor(pte);
 
-#ifdef CONFIG_ARM_LPAE
-	tlb_add_flush(tlb, addr);
-#else
+#ifndef CONFIG_ARM_LPAE
 	/*
 	 * With the classic ARM MMU, a pte page has two corresponding pmd
 	 * entries, each covering 1MB.
 	 */
-	addr &= PMD_MASK;
-	tlb_add_flush(tlb, addr + SZ_1M - PAGE_SIZE);
-	tlb_add_flush(tlb, addr + SZ_1M);
+	addr = (addr & PMD_MASK) + SZ_1M;
+	__tlb_adjust_range(tlb, addr - PAGE_SIZE, 2 * PAGE_SIZE);
 #endif
 
-	tlb_remove_entry(tlb, pte);
-}
-
-static inline void __pmd_free_tlb(struct mmu_gather *tlb, pmd_t *pmdp,
-				  unsigned long addr)
-{
-#ifdef CONFIG_ARM_LPAE
-	tlb_add_flush(tlb, addr);
-	tlb_remove_entry(tlb, virt_to_page(pmdp));
-#endif
+	tlb_remove_table(tlb, pte);
 }
 
 static inline void
-tlb_remove_pmd_tlb_entry(struct mmu_gather *tlb, pmd_t *pmdp, unsigned long addr)
-{
-	tlb_add_flush(tlb, addr);
-}
-
-#define pte_free_tlb(tlb, ptep, addr)	__pte_free_tlb(tlb, ptep, addr)
-#define pmd_free_tlb(tlb, pmdp, addr)	__pmd_free_tlb(tlb, pmdp, addr)
-#define pud_free_tlb(tlb, pudp, addr)	pud_free((tlb)->mm, pudp)
-
-#define tlb_migrate_finish(mm)		do { } while (0)
-
-#define tlb_remove_check_page_size_change tlb_remove_check_page_size_change
-static inline void tlb_remove_check_page_size_change(struct mmu_gather *tlb,
-						     unsigned int page_size)
+__pmd_free_tlb(struct mmu_gather *tlb, pmd_t *pmdp, unsigned long addr)
 {
-}
-
-static inline void tlb_flush_remove_tables(struct mm_struct *mm)
-{
-}
+#ifdef CONFIG_ARM_LPAE
+	struct page *page = virt_to_page(pmdp);
 
-static inline void tlb_flush_remove_tables_local(void *arg)
-{
+	tlb_remove_table(tlb, page);
+#endif
 }
 
 #endif /* CONFIG_MMU */
diff --git a/arch/arm/include/uapi/asm/Kbuild b/arch/arm/include/uapi/asm/Kbuild
index 23b4464c0995..ce8573157774 100644
--- a/arch/arm/include/uapi/asm/Kbuild
+++ b/arch/arm/include/uapi/asm/Kbuild
@@ -3,3 +3,4 @@
 generated-y += unistd-common.h
 generated-y += unistd-oabi.h
 generated-y += unistd-eabi.h
+generic-y += kvm_para.h
diff --git a/arch/arm/include/uapi/asm/kvm_para.h b/arch/arm/include/uapi/asm/kvm_para.h
deleted file mode 100644
index baacc4996d18..000000000000
--- a/arch/arm/include/uapi/asm/kvm_para.h
+++ /dev/null
@@ -1,2 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
-#include <asm-generic/kvm_para.h>
diff --git a/arch/arm/kernel/head-nommu.S b/arch/arm/kernel/head-nommu.S
index c08d2d890f7b..b38bbd011b35 100644
--- a/arch/arm/kernel/head-nommu.S
+++ b/arch/arm/kernel/head-nommu.S
@@ -133,9 +133,9 @@ __secondary_data:
  */
 	.text
 __after_proc_init:
-#ifdef CONFIG_ARM_MPU
 M_CLASS(movw	r12, #:lower16:BASEADDR_V7M_SCB)
 M_CLASS(movt	r12, #:upper16:BASEADDR_V7M_SCB)
+#ifdef CONFIG_ARM_MPU
 M_CLASS(ldr	r3, [r12, 0x50])
 AR_CLASS(mrc	p15, 0, r3, c0, c1, 4)          @ Read ID_MMFR0
 	and	r3, r3, #(MMFR0_PMSA)           @ PMSA field
diff --git a/arch/arm/kernel/signal.c b/arch/arm/kernel/signal.c
index 76bb8de6bf6b..be5edfdde558 100644
--- a/arch/arm/kernel/signal.c
+++ b/arch/arm/kernel/signal.c
@@ -549,8 +549,7 @@ static void handle_signal(struct ksignal *ksig, struct pt_regs *regs)
 	int ret;
 
 	/*
-	 * Increment event counter and perform fixup for the pre-signal
-	 * frame.
+	 * Perform fixup for the pre-signal frame.
 	 */
 	rseq_signal_deliver(ksig, regs);
 
diff --git a/arch/arm/kernel/stacktrace.c b/arch/arm/kernel/stacktrace.c
index a56e7c856ab5..86870f40f9a0 100644
--- a/arch/arm/kernel/stacktrace.c
+++ b/arch/arm/kernel/stacktrace.c
@@ -115,8 +115,6 @@ static noinline void __save_stack_trace(struct task_struct *tsk,
 		 * running on another CPU?  For now, ignore it as we
 		 * can't guarantee we won't explode.
 		 */
-		if (trace->nr_entries < trace->max_entries)
-			trace->entries[trace->nr_entries++] = ULONG_MAX;
 		return;
 #else
 		frame.fp = thread_saved_fp(tsk);
@@ -134,8 +132,6 @@ static noinline void __save_stack_trace(struct task_struct *tsk,
 	}
 
 	walk_stackframe(&frame, save_trace, &data);
-	if (trace->nr_entries < trace->max_entries)
-		trace->entries[trace->nr_entries++] = ULONG_MAX;
 }
 
 void save_stack_trace_regs(struct pt_regs *regs, struct stack_trace *trace)
@@ -153,8 +149,6 @@ void save_stack_trace_regs(struct pt_regs *regs, struct stack_trace *trace)
 	frame.pc = regs->ARM_pc;
 
 	walk_stackframe(&frame, save_trace, &data);
-	if (trace->nr_entries < trace->max_entries)
-		trace->entries[trace->nr_entries++] = ULONG_MAX;
 }
 
 void save_stack_trace_tsk(struct task_struct *tsk, struct stack_trace *trace)
diff --git a/arch/arm/mach-at91/pm.c b/arch/arm/mach-at91/pm.c
index 51e808adb00c..2a757dcaa1a5 100644
--- a/arch/arm/mach-at91/pm.c
+++ b/arch/arm/mach-at91/pm.c
@@ -591,13 +591,13 @@ static int __init at91_pm_backup_init(void)
 
 	np = of_find_compatible_node(NULL, NULL, "atmel,sama5d2-securam");
 	if (!np)
-		goto securam_fail;
+		goto securam_fail_no_ref_dev;
 
 	pdev = of_find_device_by_node(np);
 	of_node_put(np);
 	if (!pdev) {
 		pr_warn("%s: failed to find securam device!\n", __func__);
-		goto securam_fail;
+		goto securam_fail_no_ref_dev;
 	}
 
 	sram_pool = gen_pool_get(&pdev->dev, NULL);
@@ -620,6 +620,8 @@ static int __init at91_pm_backup_init(void)
 	return 0;
 
 securam_fail:
+	put_device(&pdev->dev);
+securam_fail_no_ref_dev:
 	iounmap(pm_data.sfrbu);
 	pm_data.sfrbu = NULL;
 	return ret;
diff --git a/arch/arm/mach-ep93xx/edb93xx.c b/arch/arm/mach-ep93xx/edb93xx.c
index 8e89ec8b6f0f..34e18e9556d9 100644
--- a/arch/arm/mach-ep93xx/edb93xx.c
+++ b/arch/arm/mach-ep93xx/edb93xx.c
@@ -29,6 +29,7 @@
 #include <linux/platform_device.h>
 #include <linux/i2c.h>
 #include <linux/spi/spi.h>
+#include <linux/gpio/machine.h>
 
 #include <sound/cs4271.h>
 
@@ -105,13 +106,16 @@ static struct spi_board_info edb93xx_spi_board_info[] __initdata = {
 	},
 };
 
-static int edb93xx_spi_chipselects[] __initdata = {
-	EP93XX_GPIO_LINE_EGPIO6,
+static struct gpiod_lookup_table edb93xx_spi_cs_gpio_table = {
+	.dev_id = "ep93xx-spi.0",
+	.table = {
+		GPIO_LOOKUP("A", 6, "cs", GPIO_ACTIVE_LOW),
+		{ },
+	},
 };
 
 static struct ep93xx_spi_info edb93xx_spi_info __initdata = {
-	.chipselect	= edb93xx_spi_chipselects,
-	.num_chipselect	= ARRAY_SIZE(edb93xx_spi_chipselects),
+	/* Intentionally left blank */
 };
 
 static void __init edb93xx_register_spi(void)
@@ -123,6 +127,7 @@ static void __init edb93xx_register_spi(void)
 	else if (machine_is_edb9315a())
 		edb93xx_cs4271_data.gpio_nreset = EP93XX_GPIO_LINE_EGPIO14;
 
+	gpiod_add_lookup_table(&edb93xx_spi_cs_gpio_table);
 	ep93xx_register_spi(&edb93xx_spi_info, edb93xx_spi_board_info,
 			    ARRAY_SIZE(edb93xx_spi_board_info));
 }
diff --git a/arch/arm/mach-ep93xx/simone.c b/arch/arm/mach-ep93xx/simone.c
index 80ccb984d521..f0f38c0dba52 100644
--- a/arch/arm/mach-ep93xx/simone.c
+++ b/arch/arm/mach-ep93xx/simone.c
@@ -77,13 +77,15 @@ static struct spi_board_info simone_spi_devices[] __initdata = {
  * low between multi-message command blocks. From v1.4, it uses a GPIO instead.
  * v1.3 parts will still work, since the signal on SFRMOUT is automatic.
  */
-static int simone_spi_chipselects[] __initdata = {
-	EP93XX_GPIO_LINE_EGPIO1,
+static struct gpiod_lookup_table simone_spi_cs_gpio_table = {
+	.dev_id = "ep93xx-spi.0",
+	.table = {
+		GPIO_LOOKUP("A", 1, "cs", GPIO_ACTIVE_LOW),
+		{ },
+	},
 };
 
 static struct ep93xx_spi_info simone_spi_info __initdata = {
-	.chipselect	= simone_spi_chipselects,
-	.num_chipselect	= ARRAY_SIZE(simone_spi_chipselects),
 	.use_dma = 1,
 };
 
@@ -113,6 +115,7 @@ static void __init simone_init_machine(void)
 	ep93xx_register_i2c(simone_i2c_board_info,
 			    ARRAY_SIZE(simone_i2c_board_info));
 	gpiod_add_lookup_table(&simone_mmc_spi_gpio_table);
+	gpiod_add_lookup_table(&simone_spi_cs_gpio_table);
 	ep93xx_register_spi(&simone_spi_info, simone_spi_devices,
 			    ARRAY_SIZE(simone_spi_devices));
 	simone_register_audio();
diff --git a/arch/arm/mach-ep93xx/ts72xx.c b/arch/arm/mach-ep93xx/ts72xx.c
index 85b74ac943f0..a3a20c83c6b8 100644
--- a/arch/arm/mach-ep93xx/ts72xx.c
+++ b/arch/arm/mach-ep93xx/ts72xx.c
@@ -22,6 +22,7 @@
 #include <linux/spi/mmc_spi.h>
 #include <linux/mmc/host.h>
 #include <linux/platform_data/spi-ep93xx.h>
+#include <linux/gpio/machine.h>
 
 #include <mach/gpio-ep93xx.h>
 #include <mach/hardware.h>
@@ -269,13 +270,15 @@ static struct spi_board_info bk3_spi_board_info[] __initdata = {
  * The all work is performed automatically by !SPI_FRAME (SFRM1) and
  * goes through CPLD
  */
-static int bk3_spi_chipselects[] __initdata = {
-	EP93XX_GPIO_LINE_F(3),
+static struct gpiod_lookup_table bk3_spi_cs_gpio_table = {
+	.dev_id = "ep93xx-spi.0",
+	.table = {
+		GPIO_LOOKUP("F", 3, "cs", GPIO_ACTIVE_LOW),
+		{ },
+	},
 };
 
 static struct ep93xx_spi_info bk3_spi_master __initdata = {
-	.chipselect	= bk3_spi_chipselects,
-	.num_chipselect = ARRAY_SIZE(bk3_spi_chipselects),
 	.use_dma	= 1,
 };
 
@@ -316,13 +319,17 @@ static struct spi_board_info ts72xx_spi_devices[] __initdata = {
 	},
 };
 
-static int ts72xx_spi_chipselects[] __initdata = {
-	EP93XX_GPIO_LINE_F(2),		/* DIO_17 */
+static struct gpiod_lookup_table ts72xx_spi_cs_gpio_table = {
+	.dev_id = "ep93xx-spi.0",
+	.table = {
+		/* DIO_17 */
+		GPIO_LOOKUP("F", 2, "cs", GPIO_ACTIVE_LOW),
+		{ },
+	},
 };
 
 static struct ep93xx_spi_info ts72xx_spi_info __initdata = {
-	.chipselect	= ts72xx_spi_chipselects,
-	.num_chipselect	= ARRAY_SIZE(ts72xx_spi_chipselects),
+	/* Intentionally left blank */
 };
 
 static void __init ts72xx_init_machine(void)
@@ -339,6 +346,7 @@ static void __init ts72xx_init_machine(void)
 	if (board_is_ts7300())
 		platform_device_register(&ts73xx_fpga_device);
 #endif
+	gpiod_add_lookup_table(&ts72xx_spi_cs_gpio_table);
 	ep93xx_register_spi(&ts72xx_spi_info, ts72xx_spi_devices,
 			    ARRAY_SIZE(ts72xx_spi_devices));
 }
@@ -398,6 +406,7 @@ static void __init bk3_init_machine(void)
 
 	ep93xx_register_eth(&ts72xx_eth_data, 1);
 
+	gpiod_add_lookup_table(&bk3_spi_cs_gpio_table);
 	ep93xx_register_spi(&bk3_spi_master, bk3_spi_board_info,
 			    ARRAY_SIZE(bk3_spi_board_info));
 
diff --git a/arch/arm/mach-ep93xx/vision_ep9307.c b/arch/arm/mach-ep93xx/vision_ep9307.c
index 767ee64628dc..f95a644769e4 100644
--- a/arch/arm/mach-ep93xx/vision_ep9307.c
+++ b/arch/arm/mach-ep93xx/vision_ep9307.c
@@ -245,15 +245,17 @@ static struct spi_board_info vision_spi_board_info[] __initdata = {
 	},
 };
 
-static int vision_spi_chipselects[] __initdata = {
-	EP93XX_GPIO_LINE_EGPIO6,
-	EP93XX_GPIO_LINE_EGPIO7,
-	EP93XX_GPIO_LINE_G(2),
+static struct gpiod_lookup_table vision_spi_cs_gpio_table = {
+	.dev_id = "ep93xx-spi.0",
+	.table = {
+		GPIO_LOOKUP_IDX("A", 6, "cs", 0, GPIO_ACTIVE_LOW),
+		GPIO_LOOKUP_IDX("A", 7, "cs", 1, GPIO_ACTIVE_LOW),
+		GPIO_LOOKUP_IDX("G", 2, "cs", 2, GPIO_ACTIVE_LOW),
+		{ },
+	},
 };
 
 static struct ep93xx_spi_info vision_spi_master __initdata = {
-	.chipselect	= vision_spi_chipselects,
-	.num_chipselect	= ARRAY_SIZE(vision_spi_chipselects),
 	.use_dma	= 1,
 };
 
@@ -295,6 +297,7 @@ static void __init vision_init_machine(void)
 	ep93xx_register_i2c(vision_i2c_info,
 				ARRAY_SIZE(vision_i2c_info));
 	gpiod_add_lookup_table(&vision_spi_mmc_gpio_table);
+	gpiod_add_lookup_table(&vision_spi_cs_gpio_table);
 	ep93xx_register_spi(&vision_spi_master, vision_spi_board_info,
 				ARRAY_SIZE(vision_spi_board_info));
 	vision_register_i2s();
diff --git a/arch/arm/mach-imx/cpuidle-imx6q.c b/arch/arm/mach-imx/cpuidle-imx6q.c
index bfeb25aaf9a2..326e870d7123 100644
--- a/arch/arm/mach-imx/cpuidle-imx6q.c
+++ b/arch/arm/mach-imx/cpuidle-imx6q.c
@@ -16,30 +16,23 @@
 #include "cpuidle.h"
 #include "hardware.h"
 
-static atomic_t master = ATOMIC_INIT(0);
-static DEFINE_SPINLOCK(master_lock);
+static int num_idle_cpus = 0;
+static DEFINE_SPINLOCK(cpuidle_lock);
 
 static int imx6q_enter_wait(struct cpuidle_device *dev,
 			    struct cpuidle_driver *drv, int index)
 {
-	if (atomic_inc_return(&master) == num_online_cpus()) {
-		/*
-		 * With this lock, we prevent other cpu to exit and enter
-		 * this function again and become the master.
-		 */
-		if (!spin_trylock(&master_lock))
-			goto idle;
+	spin_lock(&cpuidle_lock);
+	if (++num_idle_cpus == num_online_cpus())
 		imx6_set_lpm(WAIT_UNCLOCKED);
-		cpu_do_idle();
-		imx6_set_lpm(WAIT_CLOCKED);
-		spin_unlock(&master_lock);
-		goto done;
-	}
+	spin_unlock(&cpuidle_lock);
 
-idle:
 	cpu_do_idle();
-done:
-	atomic_dec(&master);
+
+	spin_lock(&cpuidle_lock);
+	if (num_idle_cpus-- == num_online_cpus())
+		imx6_set_lpm(WAIT_CLOCKED);
+	spin_unlock(&cpuidle_lock);
 
 	return index;
 }
diff --git a/arch/arm/mach-imx/mach-imx51.c b/arch/arm/mach-imx/mach-imx51.c
index c7169c2f94c4..08c7892866c2 100644
--- a/arch/arm/mach-imx/mach-imx51.c
+++ b/arch/arm/mach-imx/mach-imx51.c
@@ -59,6 +59,7 @@ static void __init imx51_m4if_setup(void)
 		return;
 
 	m4if_base = of_iomap(np, 0);
+	of_node_put(np);
 	if (!m4if_base) {
 		pr_err("Unable to map M4IF registers\n");
 		return;
diff --git a/arch/arm/mach-iop13xx/setup.c b/arch/arm/mach-iop13xx/setup.c
index 53c316f7301e..fe4932fda01d 100644
--- a/arch/arm/mach-iop13xx/setup.c
+++ b/arch/arm/mach-iop13xx/setup.c
@@ -300,7 +300,7 @@ static struct resource iop13xx_adma_2_resources[] = {
 	}
 };
 
-static u64 iop13xx_adma_dmamask = DMA_BIT_MASK(64);
+static u64 iop13xx_adma_dmamask = DMA_BIT_MASK(32);
 static struct iop_adma_platform_data iop13xx_adma_0_data = {
 	.hw_id = 0,
 	.pool_size = PAGE_SIZE,
@@ -324,7 +324,7 @@ static struct platform_device iop13xx_adma_0_channel = {
 	.resource = iop13xx_adma_0_resources,
 	.dev = {
 		.dma_mask = &iop13xx_adma_dmamask,
-		.coherent_dma_mask = DMA_BIT_MASK(64),
+		.coherent_dma_mask = DMA_BIT_MASK(32),
 		.platform_data = (void *) &iop13xx_adma_0_data,
 	},
 };
@@ -336,7 +336,7 @@ static struct platform_device iop13xx_adma_1_channel = {
 	.resource = iop13xx_adma_1_resources,
 	.dev = {
 		.dma_mask = &iop13xx_adma_dmamask,
-		.coherent_dma_mask = DMA_BIT_MASK(64),
+		.coherent_dma_mask = DMA_BIT_MASK(32),
 		.platform_data = (void *) &iop13xx_adma_1_data,
 	},
 };
@@ -348,7 +348,7 @@ static struct platform_device iop13xx_adma_2_channel = {
 	.resource = iop13xx_adma_2_resources,
 	.dev = {
 		.dma_mask = &iop13xx_adma_dmamask,
-		.coherent_dma_mask = DMA_BIT_MASK(64),
+		.coherent_dma_mask = DMA_BIT_MASK(32),
 		.platform_data = (void *) &iop13xx_adma_2_data,
 	},
 };
diff --git a/arch/arm/mach-iop13xx/tpmi.c b/arch/arm/mach-iop13xx/tpmi.c
index db511ec2b1df..116feb6b261e 100644
--- a/arch/arm/mach-iop13xx/tpmi.c
+++ b/arch/arm/mach-iop13xx/tpmi.c
@@ -152,7 +152,7 @@ static struct resource iop13xx_tpmi_3_resources[] = {
 	}
 };
 
-u64 iop13xx_tpmi_mask = DMA_BIT_MASK(64);
+u64 iop13xx_tpmi_mask = DMA_BIT_MASK(32);
 static struct platform_device iop13xx_tpmi_0_device = {
 	.name = "iop-tpmi",
 	.id = 0,
@@ -160,7 +160,7 @@ static struct platform_device iop13xx_tpmi_0_device = {
 	.resource = iop13xx_tpmi_0_resources,
 	.dev = {
 		.dma_mask          = &iop13xx_tpmi_mask,
-		.coherent_dma_mask = DMA_BIT_MASK(64),
+		.coherent_dma_mask = DMA_BIT_MASK(32),
 	},
 };
 
@@ -171,7 +171,7 @@ static struct platform_device iop13xx_tpmi_1_device = {
 	.resource = iop13xx_tpmi_1_resources,
 	.dev = {
 		.dma_mask          = &iop13xx_tpmi_mask,
-		.coherent_dma_mask = DMA_BIT_MASK(64),
+		.coherent_dma_mask = DMA_BIT_MASK(32),
 	},
 };
 
@@ -182,7 +182,7 @@ static struct platform_device iop13xx_tpmi_2_device = {
 	.resource = iop13xx_tpmi_2_resources,
 	.dev = {
 		.dma_mask          = &iop13xx_tpmi_mask,
-		.coherent_dma_mask = DMA_BIT_MASK(64),
+		.coherent_dma_mask = DMA_BIT_MASK(32),
 	},
 };
 
@@ -193,7 +193,7 @@ static struct platform_device iop13xx_tpmi_3_device = {
 	.resource = iop13xx_tpmi_3_resources,
 	.dev = {
 		.dma_mask          = &iop13xx_tpmi_mask,
-		.coherent_dma_mask = DMA_BIT_MASK(64),
+		.coherent_dma_mask = DMA_BIT_MASK(32),
 	},
 };
 
diff --git a/arch/arm/mach-milbeaut/platsmp.c b/arch/arm/mach-milbeaut/platsmp.c
index 591543c81399..3ea880f5fcb7 100644
--- a/arch/arm/mach-milbeaut/platsmp.c
+++ b/arch/arm/mach-milbeaut/platsmp.c
@@ -65,6 +65,7 @@ static void m10v_smp_init(unsigned int max_cpus)
 		writel(KERNEL_UNBOOT_FLAG, m10v_smp_base + cpu * 4);
 }
 
+#ifdef CONFIG_HOTPLUG_CPU
 static void m10v_cpu_die(unsigned int l_cpu)
 {
 	gic_cpu_if_down(0);
@@ -83,12 +84,15 @@ static int m10v_cpu_kill(unsigned int l_cpu)
 
 	return 1;
 }
+#endif
 
 static struct smp_operations m10v_smp_ops __initdata = {
 	.smp_prepare_cpus	= m10v_smp_init,
 	.smp_boot_secondary	= m10v_boot_secondary,
+#ifdef CONFIG_HOTPLUG_CPU
 	.cpu_die		= m10v_cpu_die,
 	.cpu_kill		= m10v_cpu_kill,
+#endif
 };
 CPU_METHOD_OF_DECLARE(m10v_smp, "socionext,milbeaut-m10v-smp", &m10v_smp_ops);
 
diff --git a/arch/arm/mach-omap1/board-ams-delta.c b/arch/arm/mach-omap1/board-ams-delta.c
index be30c3c061b4..1b15d593837e 100644
--- a/arch/arm/mach-omap1/board-ams-delta.c
+++ b/arch/arm/mach-omap1/board-ams-delta.c
@@ -182,6 +182,7 @@ static struct resource latch1_resources[] = {
 
 static struct bgpio_pdata latch1_pdata = {
 	.label	= LATCH1_LABEL,
+	.base	= -1,
 	.ngpio	= LATCH1_NGPIO,
 };
 
@@ -219,6 +220,7 @@ static struct resource latch2_resources[] = {
 
 static struct bgpio_pdata latch2_pdata = {
 	.label	= LATCH2_LABEL,
+	.base	= -1,
 	.ngpio	= LATCH2_NGPIO,
 };
 
diff --git a/arch/arm/mach-omap2/display.c b/arch/arm/mach-omap2/display.c
index 1444b4b4bd9f..439e143cad7b 100644
--- a/arch/arm/mach-omap2/display.c
+++ b/arch/arm/mach-omap2/display.c
@@ -250,8 +250,10 @@ static int __init omapdss_init_of(void)
 	if (!node)
 		return 0;
 
-	if (!of_device_is_available(node))
+	if (!of_device_is_available(node)) {
+		of_node_put(node);
 		return 0;
+	}
 
 	pdev = of_find_device_by_node(node);
 
diff --git a/arch/arm/plat-iop/adma.c b/arch/arm/plat-iop/adma.c
index a4d1f8de3b5b..d9612221e484 100644
--- a/arch/arm/plat-iop/adma.c
+++ b/arch/arm/plat-iop/adma.c
@@ -143,7 +143,7 @@ struct platform_device iop3xx_dma_0_channel = {
 	.resource = iop3xx_dma_0_resources,
 	.dev = {
 		.dma_mask = &iop3xx_adma_dmamask,
-		.coherent_dma_mask = DMA_BIT_MASK(64),
+		.coherent_dma_mask = DMA_BIT_MASK(32),
 		.platform_data = (void *) &iop3xx_dma_0_data,
 	},
 };
@@ -155,7 +155,7 @@ struct platform_device iop3xx_dma_1_channel = {
 	.resource = iop3xx_dma_1_resources,
 	.dev = {
 		.dma_mask = &iop3xx_adma_dmamask,
-		.coherent_dma_mask = DMA_BIT_MASK(64),
+		.coherent_dma_mask = DMA_BIT_MASK(32),
 		.platform_data = (void *) &iop3xx_dma_1_data,
 	},
 };
@@ -167,7 +167,7 @@ struct platform_device iop3xx_aau_channel = {
 	.resource = iop3xx_aau_resources,
 	.dev = {
 		.dma_mask = &iop3xx_adma_dmamask,
-		.coherent_dma_mask = DMA_BIT_MASK(64),
+		.coherent_dma_mask = DMA_BIT_MASK(32),
 		.platform_data = (void *) &iop3xx_aau_data,
 	},
 };
diff --git a/arch/arm/plat-orion/common.c b/arch/arm/plat-orion/common.c
index a6c81ce00f52..8647cb80a93b 100644
--- a/arch/arm/plat-orion/common.c
+++ b/arch/arm/plat-orion/common.c
@@ -622,7 +622,7 @@ static struct platform_device orion_xor0_shared = {
 	.resource	= orion_xor0_shared_resources,
 	.dev            = {
 		.dma_mask               = &orion_xor_dmamask,
-		.coherent_dma_mask      = DMA_BIT_MASK(64),
+		.coherent_dma_mask      = DMA_BIT_MASK(32),
 		.platform_data          = &orion_xor0_pdata,
 	},
 };
@@ -683,7 +683,7 @@ static struct platform_device orion_xor1_shared = {
 	.resource	= orion_xor1_shared_resources,
 	.dev            = {
 		.dma_mask               = &orion_xor_dmamask,
-		.coherent_dma_mask      = DMA_BIT_MASK(64),
+		.coherent_dma_mask      = DMA_BIT_MASK(32),
 		.platform_data          = &orion_xor1_pdata,
 	},
 };
diff --git a/arch/arm/tools/syscall.tbl b/arch/arm/tools/syscall.tbl
index 9016f4081bb9..0393917eaa57 100644
--- a/arch/arm/tools/syscall.tbl
+++ b/arch/arm/tools/syscall.tbl
@@ -437,3 +437,7 @@
 421	common	rt_sigtimedwait_time64		sys_rt_sigtimedwait
 422	common	futex_time64			sys_futex
 423	common	sched_rr_get_interval_time64	sys_sched_rr_get_interval
+424	common	pidfd_send_signal		sys_pidfd_send_signal
+425	common	io_uring_setup			sys_io_uring_setup
+426	common	io_uring_enter			sys_io_uring_enter
+427	common	io_uring_register		sys_io_uring_register
diff --git a/arch/arm/vdso/vgettimeofday.c b/arch/arm/vdso/vgettimeofday.c
index a9dd619c6c29..7bdbf5d5c47d 100644
--- a/arch/arm/vdso/vgettimeofday.c
+++ b/arch/arm/vdso/vgettimeofday.c
@@ -18,9 +18,9 @@
 #include <linux/compiler.h>
 #include <linux/hrtimer.h>
 #include <linux/time.h>
-#include <asm/arch_timer.h>
 #include <asm/barrier.h>
 #include <asm/bug.h>
+#include <asm/cp15.h>
 #include <asm/page.h>
 #include <asm/unistd.h>
 #include <asm/vdso_datapage.h>
@@ -123,7 +123,8 @@ static notrace u64 get_ns(struct vdso_data *vdata)
 	u64 cycle_now;
 	u64 nsec;
 
-	cycle_now = arch_counter_get_cntvct();
+	isb();
+	cycle_now = read_sysreg(CNTVCT);
 
 	cycle_delta = (cycle_now - vdata->cs_cycle_last) & vdata->cs_mask;
 
diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig
index 7e34b9eba5de..df350f4e1e7a 100644
--- a/arch/arm64/Kconfig
+++ b/arch/arm64/Kconfig
@@ -90,6 +90,7 @@ config ARM64
 	select GENERIC_CLOCKEVENTS
 	select GENERIC_CLOCKEVENTS_BROADCAST
 	select GENERIC_CPU_AUTOPROBE
+	select GENERIC_CPU_VULNERABILITIES
 	select GENERIC_EARLY_IOREMAP
 	select GENERIC_IDLE_POLL_SETUP
 	select GENERIC_IRQ_MULTI_HANDLER
@@ -148,8 +149,8 @@ config ARM64
 	select HAVE_PERF_REGS
 	select HAVE_PERF_USER_STACK_DUMP
 	select HAVE_REGS_AND_STACK_ACCESS_API
+	select HAVE_FUNCTION_ARG_ACCESS_API
 	select HAVE_RCU_TABLE_FREE
-	select HAVE_RCU_TABLE_INVALIDATE
 	select HAVE_RSEQ
 	select HAVE_STACKPROTECTOR
 	select HAVE_SYSCALL_TRACEPOINTS
@@ -237,9 +238,6 @@ config LOCKDEP_SUPPORT
 config TRACE_IRQFLAGS_SUPPORT
 	def_bool y
 
-config RWSEM_XCHGADD_ALGORITHM
-	def_bool y
-
 config GENERIC_BUG
 	def_bool y
 	depends on BUG
@@ -297,7 +295,7 @@ menu "Kernel Features"
 menu "ARM errata workarounds via the alternatives framework"
 
 config ARM64_WORKAROUND_CLEAN_CACHE
-	def_bool n
+	bool
 
 config ARM64_ERRATUM_826319
 	bool "Cortex-A53: 826319: System might deadlock if a write cannot complete until read data is accepted"
@@ -464,26 +462,28 @@ config ARM64_ERRATUM_1024718
 	bool "Cortex-A55: 1024718: Update of DBM/AP bits without break before make might result in incorrect update"
 	default y
 	help
-	  This option adds work around for Arm Cortex-A55 Erratum 1024718.
+	  This option adds a workaround for ARM Cortex-A55 Erratum 1024718.
 
 	  Affected Cortex-A55 cores (r0p0, r0p1, r1p0) could cause incorrect
 	  update of the hardware dirty bit when the DBM/AP bits are updated
-	  without a break-before-make. The work around is to disable the usage
+	  without a break-before-make. The workaround is to disable the usage
 	  of hardware DBM locally on the affected cores. CPUs not affected by
-	  erratum will continue to use the feature.
+	  this erratum will continue to use the feature.
 
 	  If unsure, say Y.
 
 config ARM64_ERRATUM_1188873
-	bool "Cortex-A76: MRC read following MRRC read of specific Generic Timer in AArch32 might give incorrect result"
+	bool "Cortex-A76/Neoverse-N1: MRC read following MRRC read of specific Generic Timer in AArch32 might give incorrect result"
 	default y
+	depends on COMPAT
 	select ARM_ARCH_TIMER_OOL_WORKAROUND
 	help
-	  This option adds work arounds for ARM Cortex-A76 erratum 1188873
+	  This option adds a workaround for ARM Cortex-A76/Neoverse-N1
+	  erratum 1188873.
 
-	  Affected Cortex-A76 cores (r0p0, r1p0, r2p0) could cause
-	  register corruption when accessing the timer registers from
-	  AArch32 userspace.
+	  Affected Cortex-A76/Neoverse-N1 cores (r0p0, r1p0, r2p0) could
+	  cause register corruption when accessing the timer registers
+	  from AArch32 userspace.
 
 	  If unsure, say Y.
 
@@ -491,7 +491,7 @@ config ARM64_ERRATUM_1165522
 	bool "Cortex-A76: Speculative AT instruction using out-of-context translation regime could cause subsequent request to generate an incorrect translation"
 	default y
 	help
-	  This option adds work arounds for ARM Cortex-A76 erratum 1165522
+	  This option adds a workaround for ARM Cortex-A76 erratum 1165522.
 
 	  Affected Cortex-A76 cores (r0p0, r1p0, r2p0) could end-up with
 	  corrupted TLBs by speculating an AT instruction during a guest
@@ -504,7 +504,7 @@ config ARM64_ERRATUM_1286807
 	default y
 	select ARM64_WORKAROUND_REPEAT_TLBI
 	help
-	  This option adds workaround for ARM Cortex-A76 erratum 1286807
+	  This option adds a workaround for ARM Cortex-A76 erratum 1286807.
 
 	  On the affected Cortex-A76 cores (r0p0 to r3p0), if a virtual
 	  address for a cacheable mapping of a location is being
@@ -521,10 +521,10 @@ config CAVIUM_ERRATUM_22375
 	bool "Cavium erratum 22375, 24313"
 	default y
 	help
-	  Enable workaround for erratum 22375, 24313.
+	  Enable workaround for errata 22375 and 24313.
 
 	  This implements two gicv3-its errata workarounds for ThunderX. Both
-	  with small impact affecting only ITS table allocation.
+	  with a small impact affecting only ITS table allocation.
 
 	    erratum 22375: only alloc 8MB table size
 	    erratum 24313: ignore memory access type
@@ -588,9 +588,6 @@ config QCOM_FALKOR_ERRATUM_1003
 
 config ARM64_WORKAROUND_REPEAT_TLBI
 	bool
-	help
-	  Enable the repeat TLBI workaround for Falkor erratum 1009 and
-	  Cortex-A76 erratum 1286807.
 
 config QCOM_FALKOR_ERRATUM_1009
 	bool "Falkor E1009: Prematurely complete a DSB after a TLBI"
@@ -626,7 +623,7 @@ config HISILICON_ERRATUM_161600802
 	bool "Hip07 161600802: Erroneous redistributor VLPI base"
 	default y
 	help
-	  The HiSilicon Hip07 SoC usees the wrong redistributor base
+	  The HiSilicon Hip07 SoC uses the wrong redistributor base
 	  when issued ITS commands such as VMOVP and VMAPP, and requires
 	  a 128kB offset to be applied to the target address in this commands.
 
@@ -646,7 +643,7 @@ config FUJITSU_ERRATUM_010001
 	bool "Fujitsu-A64FX erratum E#010001: Undefined fault may occur wrongly"
 	default y
 	help
-	  This option adds workaround for Fujitsu-A64FX erratum E#010001.
+	  This option adds a workaround for Fujitsu-A64FX erratum E#010001.
 	  On some variants of the Fujitsu-A64FX cores ver(1.0, 1.1), memory
 	  accesses may cause undefined fault (Data abort, DFSC=0b111111).
 	  This fault occurs under a specific hardware condition when a
@@ -657,7 +654,7 @@ config FUJITSU_ERRATUM_010001
 	  case-4  TTBR1_EL2 with TCR_EL2.NFD1 == 1.
 
 	  The workaround is to ensure these bits are clear in TCR_ELx.
-	  The workaround only affect the Fujitsu-A64FX.
+	  The workaround only affects the Fujitsu-A64FX.
 
 	  If unsure, say Y.
 
@@ -889,6 +886,9 @@ config ARCH_WANT_HUGE_PMD_SHARE
 config ARCH_HAS_CACHE_LINE_SIZE
 	def_bool y
 
+config ARCH_ENABLE_SPLIT_PMD_PTLOCK
+	def_bool y if PGTABLE_LEVELS > 2
+
 config SECCOMP
 	bool "Enable seccomp to safely compute untrusted bytecode"
 	---help---
@@ -1078,9 +1078,65 @@ config RODATA_FULL_DEFAULT_ENABLED
 	  This requires the linear region to be mapped down to pages,
 	  which may adversely affect performance in some cases.
 
+config ARM64_SW_TTBR0_PAN
+	bool "Emulate Privileged Access Never using TTBR0_EL1 switching"
+	help
+	  Enabling this option prevents the kernel from accessing
+	  user-space memory directly by pointing TTBR0_EL1 to a reserved
+	  zeroed area and reserved ASID. The user access routines
+	  restore the valid TTBR0_EL1 temporarily.
+
+menuconfig COMPAT
+	bool "Kernel support for 32-bit EL0"
+	depends on ARM64_4K_PAGES || EXPERT
+	select COMPAT_BINFMT_ELF if BINFMT_ELF
+	select HAVE_UID16
+	select OLD_SIGSUSPEND3
+	select COMPAT_OLD_SIGACTION
+	help
+	  This option enables support for a 32-bit EL0 running under a 64-bit
+	  kernel at EL1. AArch32-specific components such as system calls,
+	  the user helper functions, VFP support and the ptrace interface are
+	  handled appropriately by the kernel.
+
+	  If you use a page size other than 4KB (i.e, 16KB or 64KB), please be aware
+	  that you will only be able to execute AArch32 binaries that were compiled
+	  with page size aligned segments.
+
+	  If you want to execute 32-bit userspace applications, say Y.
+
+if COMPAT
+
+config KUSER_HELPERS
+	bool "Enable kuser helpers page for 32 bit applications"
+	default y
+	help
+	  Warning: disabling this option may break 32-bit user programs.
+
+	  Provide kuser helpers to compat tasks. The kernel provides
+	  helper code to userspace in read only form at a fixed location
+	  to allow userspace to be independent of the CPU type fitted to
+	  the system. This permits binaries to be run on ARMv4 through
+	  to ARMv8 without modification.
+
+	  See Documentation/arm/kernel_user_helpers.txt for details.
+
+	  However, the fixed address nature of these helpers can be used
+	  by ROP (return orientated programming) authors when creating
+	  exploits.
+
+	  If all of the binaries and libraries which run on your platform
+	  are built specifically for your platform, and make no use of
+	  these helpers, then you can turn this option off to hinder
+	  such exploits. However, in that case, if a binary or library
+	  relying on those helpers is run, it will not function correctly.
+
+	  Say N here only if you are absolutely certain that you do not
+	  need these helpers; otherwise, the safe option is to say Y.
+
+
 menuconfig ARMV8_DEPRECATED
 	bool "Emulate deprecated/obsolete ARMv8 instructions"
-	depends on COMPAT
 	depends on SYSCTL
 	help
 	  Legacy software support may require certain instructions
@@ -1146,13 +1202,7 @@ config SETEND_EMULATION
 	  If unsure, say Y
 endif
 
-config ARM64_SW_TTBR0_PAN
-	bool "Emulate Privileged Access Never using TTBR0_EL1 switching"
-	help
-	  Enabling this option prevents the kernel from accessing
-	  user-space memory directly by pointing TTBR0_EL1 to a reserved
-	  zeroed area and reserved ASID. The user access routines
-	  restore the valid TTBR0_EL1 temporarily.
+endif
 
 menu "ARMv8.1 architectural features"
 
@@ -1318,6 +1368,9 @@ config ARM64_SVE
 
 	  To enable use of this extension on CPUs that implement it, say Y.
 
+	  On CPUs that support the SVE2 extensions, this option will enable
+	  those too.
+
 	  Note that for architectural reasons, firmware _must_ implement SVE
 	  support when running on SVE capable hardware.  The required support
 	  is present in:
@@ -1351,7 +1404,7 @@ config ARM64_PSEUDO_NMI
 	help
 	  Adds support for mimicking Non-Maskable Interrupts through the use of
 	  GIC interrupt priority. This support requires version 3 or later of
-	  Arm GIC.
+	  ARM GIC.
 
 	  This high priority configuration for interrupts needs to be
 	  explicitly enabled by setting the kernel parameter
@@ -1475,25 +1528,6 @@ config DMI
 
 endmenu
 
-config COMPAT
-	bool "Kernel support for 32-bit EL0"
-	depends on ARM64_4K_PAGES || EXPERT
-	select COMPAT_BINFMT_ELF if BINFMT_ELF
-	select HAVE_UID16
-	select OLD_SIGSUSPEND3
-	select COMPAT_OLD_SIGACTION
-	help
-	  This option enables support for a 32-bit EL0 running under a 64-bit
-	  kernel at EL1. AArch32-specific components such as system calls,
-	  the user helper functions, VFP support and the ptrace interface are
-	  handled appropriately by the kernel.
-
-	  If you use a page size other than 4KB (i.e, 16KB or 64KB), please be aware
-	  that you will only be able to execute AArch32 binaries that were compiled
-	  with page size aligned segments.
-
-	  If you want to execute 32-bit userspace applications, say Y.
-
 config SYSVIPC_COMPAT
 	def_bool y
 	depends on COMPAT && SYSVIPC
diff --git a/arch/arm64/Kconfig.platforms b/arch/arm64/Kconfig.platforms
index 70498a033cf5..b5ca9c50876d 100644
--- a/arch/arm64/Kconfig.platforms
+++ b/arch/arm64/Kconfig.platforms
@@ -27,6 +27,7 @@ config ARCH_BCM2835
 	bool "Broadcom BCM2835 family"
 	select TIMER_OF
 	select GPIOLIB
+	select MFD_CORE
 	select PINCTRL
 	select PINCTRL_BCM2835
 	select ARM_AMBA
diff --git a/arch/arm64/boot/dts/altera/socfpga_stratix10.dtsi b/arch/arm64/boot/dts/altera/socfpga_stratix10.dtsi
index 7c649f6b14cb..a2cec6218211 100644
--- a/arch/arm64/boot/dts/altera/socfpga_stratix10.dtsi
+++ b/arch/arm64/boot/dts/altera/socfpga_stratix10.dtsi
@@ -162,6 +162,7 @@
 			rx-fifo-depth = <16384>;
 			snps,multicast-filter-bins = <256>;
 			iommus = <&smmu 1>;
+			altr,sysmgr-syscon = <&sysmgr 0x44 0>;
 			status = "disabled";
 		};
 
@@ -179,6 +180,7 @@
 			rx-fifo-depth = <16384>;
 			snps,multicast-filter-bins = <256>;
 			iommus = <&smmu 2>;
+			altr,sysmgr-syscon = <&sysmgr 0x48 0>;
 			status = "disabled";
 		};
 
@@ -196,6 +198,7 @@
 			rx-fifo-depth = <16384>;
 			snps,multicast-filter-bins = <256>;
 			iommus = <&smmu 3>;
+			altr,sysmgr-syscon = <&sysmgr 0x4c 0>;
 			status = "disabled";
 		};
 
@@ -531,11 +534,12 @@
 		};
 
 		eccmgr {
-			compatible = "altr,socfpga-a10-ecc-manager";
+			compatible = "altr,socfpga-s10-ecc-manager",
+				     "altr,socfpga-a10-ecc-manager";
 			altr,sysmgr-syscon = <&sysmgr>;
 			#address-cells = <1>;
 			#size-cells = <1>;
-			interrupts = <0 15 4>, <0 95 4>;
+			interrupts = <0 15 4>;
 			interrupt-controller;
 			#interrupt-cells = <2>;
 			ranges;
@@ -543,31 +547,31 @@
 			sdramedac {
 				compatible = "altr,sdram-edac-s10";
 				altr,sdr-syscon = <&sdr>;
-				interrupts = <16 4>, <48 4>;
+				interrupts = <16 4>;
 			};
 
 			usb0-ecc@ff8c4000 {
-				compatible = "altr,socfpga-usb-ecc";
+				compatible = "altr,socfpga-s10-usb-ecc",
+					     "altr,socfpga-usb-ecc";
 				reg = <0xff8c4000 0x100>;
 				altr,ecc-parent = <&usb0>;
-				interrupts = <2 4>,
-					     <34 4>;
+				interrupts = <2 4>;
 			};
 
 			emac0-rx-ecc@ff8c0000 {
-				compatible = "altr,socfpga-eth-mac-ecc";
+				compatible = "altr,socfpga-s10-eth-mac-ecc",
+					     "altr,socfpga-eth-mac-ecc";
 				reg = <0xff8c0000 0x100>;
 				altr,ecc-parent = <&gmac0>;
-				interrupts = <4 4>,
-					     <36 4>;
+				interrupts = <4 4>;
 			};
 
 			emac0-tx-ecc@ff8c0400 {
-				compatible = "altr,socfpga-eth-mac-ecc";
+				compatible = "altr,socfpga-s10-eth-mac-ecc",
+					     "altr,socfpga-eth-mac-ecc";
 				reg = <0xff8c0400 0x100>;
 				altr,ecc-parent = <&gmac0>;
-				interrupts = <5 4>,
-					     <37 4>;
+				interrupts = <5 4>;
 			};
 
 		};
diff --git a/arch/arm64/boot/dts/mediatek/mt2712-pinfunc.h b/arch/arm64/boot/dts/mediatek/mt2712-pinfunc.h
index 1b4cb0c55744..385c455a7c98 100644
--- a/arch/arm64/boot/dts/mediatek/mt2712-pinfunc.h
+++ b/arch/arm64/boot/dts/mediatek/mt2712-pinfunc.h
@@ -1,4 +1,4 @@
-// SPDX-License-Identifier: GPL-2.0
+/* SPDX-License-Identifier: GPL-2.0 */
 /*
  * Copyright (C) 2018 MediaTek Inc.
  * Author: Zhiyong Tao <zhiyong.tao@mediatek.com>
diff --git a/arch/arm64/boot/dts/nvidia/tegra186.dtsi b/arch/arm64/boot/dts/nvidia/tegra186.dtsi
index bb2045be8814..97aeb946ed5e 100644
--- a/arch/arm64/boot/dts/nvidia/tegra186.dtsi
+++ b/arch/arm64/boot/dts/nvidia/tegra186.dtsi
@@ -321,7 +321,6 @@
 		nvidia,default-trim = <0x9>;
 		nvidia,dqs-trim = <63>;
 		mmc-hs400-1_8v;
-		supports-cqe;
 		status = "disabled";
 	};
 
diff --git a/arch/arm64/boot/dts/renesas/r8a774c0.dtsi b/arch/arm64/boot/dts/renesas/r8a774c0.dtsi
index 61a0afb74e63..1ea684af99c4 100644
--- a/arch/arm64/boot/dts/renesas/r8a774c0.dtsi
+++ b/arch/arm64/boot/dts/renesas/r8a774c0.dtsi
@@ -2,7 +2,7 @@
 /*
  * Device Tree Source for the RZ/G2E (R8A774C0) SoC
  *
- * Copyright (C) 2018 Renesas Electronics Corp.
+ * Copyright (C) 2018-2019 Renesas Electronics Corp.
  */
 
 #include <dt-bindings/clock/r8a774c0-cpg-mssr.h>
@@ -1150,9 +1150,8 @@
 				 <&cpg CPG_CORE R8A774C0_CLK_S3D1C>,
 				 <&scif_clk>;
 			clock-names = "fck", "brg_int", "scif_clk";
-			dmas = <&dmac1 0x5b>, <&dmac1 0x5a>,
-			       <&dmac2 0x5b>, <&dmac2 0x5a>;
-			dma-names = "tx", "rx", "tx", "rx";
+			dmas = <&dmac0 0x5b>, <&dmac0 0x5a>;
+			dma-names = "tx", "rx";
 			power-domains = <&sysc R8A774C0_PD_ALWAYS_ON>;
 			resets = <&cpg 202>;
 			status = "disabled";
diff --git a/arch/arm64/boot/dts/renesas/r8a77990.dtsi b/arch/arm64/boot/dts/renesas/r8a77990.dtsi
index a69faa60ea4d..d2ad665fe2d9 100644
--- a/arch/arm64/boot/dts/renesas/r8a77990.dtsi
+++ b/arch/arm64/boot/dts/renesas/r8a77990.dtsi
@@ -2,7 +2,7 @@
 /*
  * Device Tree Source for the R-Car E3 (R8A77990) SoC
  *
- * Copyright (C) 2018 Renesas Electronics Corp.
+ * Copyright (C) 2018-2019 Renesas Electronics Corp.
  */
 
 #include <dt-bindings/clock/r8a77990-cpg-mssr.h>
@@ -1067,9 +1067,8 @@
 				 <&cpg CPG_CORE R8A77990_CLK_S3D1C>,
 				 <&scif_clk>;
 			clock-names = "fck", "brg_int", "scif_clk";
-			dmas = <&dmac1 0x5b>, <&dmac1 0x5a>,
-			       <&dmac2 0x5b>, <&dmac2 0x5a>;
-			dma-names = "tx", "rx", "tx", "rx";
+			dmas = <&dmac0 0x5b>, <&dmac0 0x5a>;
+			dma-names = "tx", "rx";
 			power-domains = <&sysc R8A77990_PD_ALWAYS_ON>;
 			resets = <&cpg 202>;
 			status = "disabled";
diff --git a/arch/arm64/boot/dts/rockchip/rk3328-roc-cc.dts b/arch/arm64/boot/dts/rockchip/rk3328-roc-cc.dts
index 33c44e857247..0e34354b2092 100644
--- a/arch/arm64/boot/dts/rockchip/rk3328-roc-cc.dts
+++ b/arch/arm64/boot/dts/rockchip/rk3328-roc-cc.dts
@@ -108,8 +108,8 @@
 	snps,reset-gpio = <&gpio1 RK_PC2 GPIO_ACTIVE_LOW>;
 	snps,reset-active-low;
 	snps,reset-delays-us = <0 10000 50000>;
-	tx_delay = <0x25>;
-	rx_delay = <0x11>;
+	tx_delay = <0x24>;
+	rx_delay = <0x18>;
 	status = "okay";
 };
 
diff --git a/arch/arm64/boot/dts/rockchip/rk3328-rock64.dts b/arch/arm64/boot/dts/rockchip/rk3328-rock64.dts
index 2157a528276b..79b4d1d4b5d6 100644
--- a/arch/arm64/boot/dts/rockchip/rk3328-rock64.dts
+++ b/arch/arm64/boot/dts/rockchip/rk3328-rock64.dts
@@ -46,8 +46,7 @@
 
 	vcc_host1_5v: vcc_otg_5v: vcc-host1-5v-regulator {
 		compatible = "regulator-fixed";
-		enable-active-high;
-		gpio = <&gpio0 RK_PA2 GPIO_ACTIVE_HIGH>;
+		gpio = <&gpio0 RK_PA2 GPIO_ACTIVE_LOW>;
 		pinctrl-names = "default";
 		pinctrl-0 = <&usb20_host_drv>;
 		regulator-name = "vcc_host1_5v";
diff --git a/arch/arm64/boot/dts/rockchip/rk3328.dtsi b/arch/arm64/boot/dts/rockchip/rk3328.dtsi
index 84f14b132e8f..dabef1a21649 100644
--- a/arch/arm64/boot/dts/rockchip/rk3328.dtsi
+++ b/arch/arm64/boot/dts/rockchip/rk3328.dtsi
@@ -1445,11 +1445,11 @@
 
 		sdmmc0 {
 			sdmmc0_clk: sdmmc0-clk {
-				rockchip,pins = <1 RK_PA6 1 &pcfg_pull_none_4ma>;
+				rockchip,pins = <1 RK_PA6 1 &pcfg_pull_none_8ma>;
 			};
 
 			sdmmc0_cmd: sdmmc0-cmd {
-				rockchip,pins = <1 RK_PA4 1 &pcfg_pull_up_4ma>;
+				rockchip,pins = <1 RK_PA4 1 &pcfg_pull_up_8ma>;
 			};
 
 			sdmmc0_dectn: sdmmc0-dectn {
@@ -1461,14 +1461,14 @@
 			};
 
 			sdmmc0_bus1: sdmmc0-bus1 {
-				rockchip,pins = <1 RK_PA0 1 &pcfg_pull_up_4ma>;
+				rockchip,pins = <1 RK_PA0 1 &pcfg_pull_up_8ma>;
 			};
 
 			sdmmc0_bus4: sdmmc0-bus4 {
-				rockchip,pins = <1 RK_PA0 1 &pcfg_pull_up_4ma>,
-						<1 RK_PA1 1 &pcfg_pull_up_4ma>,
-						<1 RK_PA2 1 &pcfg_pull_up_4ma>,
-						<1 RK_PA3 1 &pcfg_pull_up_4ma>;
+				rockchip,pins = <1 RK_PA0 1 &pcfg_pull_up_8ma>,
+						<1 RK_PA1 1 &pcfg_pull_up_8ma>,
+						<1 RK_PA2 1 &pcfg_pull_up_8ma>,
+						<1 RK_PA3 1 &pcfg_pull_up_8ma>;
 			};
 
 			sdmmc0_gpio: sdmmc0-gpio {
@@ -1642,50 +1642,50 @@
 			rgmiim1_pins: rgmiim1-pins {
 				rockchip,pins =
 					/* mac_txclk */
-					<1 RK_PB4 2 &pcfg_pull_none_12ma>,
+					<1 RK_PB4 2 &pcfg_pull_none_8ma>,
 					/* mac_rxclk */
-					<1 RK_PB5 2 &pcfg_pull_none_2ma>,
+					<1 RK_PB5 2 &pcfg_pull_none_4ma>,
 					/* mac_mdio */
-					<1 RK_PC3 2 &pcfg_pull_none_2ma>,
+					<1 RK_PC3 2 &pcfg_pull_none_4ma>,
 					/* mac_txen */
-					<1 RK_PD1 2 &pcfg_pull_none_12ma>,
+					<1 RK_PD1 2 &pcfg_pull_none_8ma>,
 					/* mac_clk */
-					<1 RK_PC5 2 &pcfg_pull_none_2ma>,
+					<1 RK_PC5 2 &pcfg_pull_none_4ma>,
 					/* mac_rxdv */
-					<1 RK_PC6 2 &pcfg_pull_none_2ma>,
+					<1 RK_PC6 2 &pcfg_pull_none_4ma>,
 					/* mac_mdc */
-					<1 RK_PC7 2 &pcfg_pull_none_2ma>,
+					<1 RK_PC7 2 &pcfg_pull_none_4ma>,
 					/* mac_rxd1 */
-					<1 RK_PB2 2 &pcfg_pull_none_2ma>,
+					<1 RK_PB2 2 &pcfg_pull_none_4ma>,
 					/* mac_rxd0 */
-					<1 RK_PB3 2 &pcfg_pull_none_2ma>,
+					<1 RK_PB3 2 &pcfg_pull_none_4ma>,
 					/* mac_txd1 */
-					<1 RK_PB0 2 &pcfg_pull_none_12ma>,
+					<1 RK_PB0 2 &pcfg_pull_none_8ma>,
 					/* mac_txd0 */
-					<1 RK_PB1 2 &pcfg_pull_none_12ma>,
+					<1 RK_PB1 2 &pcfg_pull_none_8ma>,
 					/* mac_rxd3 */
-					<1 RK_PB6 2 &pcfg_pull_none_2ma>,
+					<1 RK_PB6 2 &pcfg_pull_none_4ma>,
 					/* mac_rxd2 */
-					<1 RK_PB7 2 &pcfg_pull_none_2ma>,
+					<1 RK_PB7 2 &pcfg_pull_none_4ma>,
 					/* mac_txd3 */
-					<1 RK_PC0 2 &pcfg_pull_none_12ma>,
+					<1 RK_PC0 2 &pcfg_pull_none_8ma>,
 					/* mac_txd2 */
-					<1 RK_PC1 2 &pcfg_pull_none_12ma>,
+					<1 RK_PC1 2 &pcfg_pull_none_8ma>,
 
 					/* mac_txclk */
-					<0 RK_PB0 1 &pcfg_pull_none>,
+					<0 RK_PB0 1 &pcfg_pull_none_8ma>,
 					/* mac_txen */
-					<0 RK_PB4 1 &pcfg_pull_none>,
+					<0 RK_PB4 1 &pcfg_pull_none_8ma>,
 					/* mac_clk */
-					<0 RK_PD0 1 &pcfg_pull_none>,
+					<0 RK_PD0 1 &pcfg_pull_none_4ma>,
 					/* mac_txd1 */
-					<0 RK_PC0 1 &pcfg_pull_none>,
+					<0 RK_PC0 1 &pcfg_pull_none_8ma>,
 					/* mac_txd0 */
-					<0 RK_PC1 1 &pcfg_pull_none>,
+					<0 RK_PC1 1 &pcfg_pull_none_8ma>,
 					/* mac_txd3 */
-					<0 RK_PC7 1 &pcfg_pull_none>,
+					<0 RK_PC7 1 &pcfg_pull_none_8ma>,
 					/* mac_txd2 */
-					<0 RK_PC6 1 &pcfg_pull_none>;
+					<0 RK_PC6 1 &pcfg_pull_none_8ma>;
 			};
 
 			rmiim1_pins: rmiim1-pins {
diff --git a/arch/arm64/boot/dts/rockchip/rk3399-rock-pi-4.dts b/arch/arm64/boot/dts/rockchip/rk3399-rock-pi-4.dts
index 4a543f2117d4..844eac939a97 100644
--- a/arch/arm64/boot/dts/rockchip/rk3399-rock-pi-4.dts
+++ b/arch/arm64/boot/dts/rockchip/rk3399-rock-pi-4.dts
@@ -158,6 +158,7 @@
 };
 
 &hdmi {
+	ddc-i2c-bus = <&i2c3>;
 	pinctrl-names = "default";
 	pinctrl-0 = <&hdmi_cec>;
 	status = "okay";
diff --git a/arch/arm64/crypto/aes-ce-ccm-glue.c b/arch/arm64/crypto/aes-ce-ccm-glue.c
index 5fc6f51908fd..cb89c80800b5 100644
--- a/arch/arm64/crypto/aes-ce-ccm-glue.c
+++ b/arch/arm64/crypto/aes-ce-ccm-glue.c
@@ -14,6 +14,7 @@
 #include <crypto/aes.h>
 #include <crypto/scatterwalk.h>
 #include <crypto/internal/aead.h>
+#include <crypto/internal/simd.h>
 #include <crypto/internal/skcipher.h>
 #include <linux/module.h>
 
@@ -109,7 +110,7 @@ static int ccm_init_mac(struct aead_request *req, u8 maciv[], u32 msglen)
 static void ccm_update_mac(struct crypto_aes_ctx *key, u8 mac[], u8 const in[],
 			   u32 abytes, u32 *macp)
 {
-	if (may_use_simd()) {
+	if (crypto_simd_usable()) {
 		kernel_neon_begin();
 		ce_aes_ccm_auth_data(mac, in, abytes, macp, key->key_enc,
 				     num_rounds(key));
@@ -255,7 +256,7 @@ static int ccm_encrypt(struct aead_request *req)
 
 	err = skcipher_walk_aead_encrypt(&walk, req, false);
 
-	if (may_use_simd()) {
+	if (crypto_simd_usable()) {
 		while (walk.nbytes) {
 			u32 tail = walk.nbytes % AES_BLOCK_SIZE;
 
@@ -313,7 +314,7 @@ static int ccm_decrypt(struct aead_request *req)
 
 	err = skcipher_walk_aead_decrypt(&walk, req, false);
 
-	if (may_use_simd()) {
+	if (crypto_simd_usable()) {
 		while (walk.nbytes) {
 			u32 tail = walk.nbytes % AES_BLOCK_SIZE;
 
@@ -372,7 +373,7 @@ static struct aead_alg ccm_aes_alg = {
 
 static int __init aes_mod_init(void)
 {
-	if (!(elf_hwcap & HWCAP_AES))
+	if (!cpu_have_named_feature(AES))
 		return -ENODEV;
 	return crypto_register_aead(&ccm_aes_alg);
 }
diff --git a/arch/arm64/crypto/aes-ce-glue.c b/arch/arm64/crypto/aes-ce-glue.c
index e6b3227bbf57..3213843fcb46 100644
--- a/arch/arm64/crypto/aes-ce-glue.c
+++ b/arch/arm64/crypto/aes-ce-glue.c
@@ -12,6 +12,7 @@
 #include <asm/simd.h>
 #include <asm/unaligned.h>
 #include <crypto/aes.h>
+#include <crypto/internal/simd.h>
 #include <linux/cpufeature.h>
 #include <linux/crypto.h>
 #include <linux/module.h>
@@ -52,7 +53,7 @@ static void aes_cipher_encrypt(struct crypto_tfm *tfm, u8 dst[], u8 const src[])
 {
 	struct crypto_aes_ctx *ctx = crypto_tfm_ctx(tfm);
 
-	if (!may_use_simd()) {
+	if (!crypto_simd_usable()) {
 		__aes_arm64_encrypt(ctx->key_enc, dst, src, num_rounds(ctx));
 		return;
 	}
@@ -66,7 +67,7 @@ static void aes_cipher_decrypt(struct crypto_tfm *tfm, u8 dst[], u8 const src[])
 {
 	struct crypto_aes_ctx *ctx = crypto_tfm_ctx(tfm);
 
-	if (!may_use_simd()) {
+	if (!crypto_simd_usable()) {
 		__aes_arm64_decrypt(ctx->key_dec, dst, src, num_rounds(ctx));
 		return;
 	}
diff --git a/arch/arm64/crypto/aes-glue.c b/arch/arm64/crypto/aes-glue.c
index 1e676625ef33..f0ceb545bd1e 100644
--- a/arch/arm64/crypto/aes-glue.c
+++ b/arch/arm64/crypto/aes-glue.c
@@ -405,7 +405,7 @@ static int ctr_encrypt_sync(struct skcipher_request *req)
 	struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(req);
 	struct crypto_aes_ctx *ctx = crypto_skcipher_ctx(tfm);
 
-	if (!may_use_simd())
+	if (!crypto_simd_usable())
 		return aes_ctr_encrypt_fallback(ctx, req);
 
 	return ctr_encrypt(req);
@@ -642,7 +642,7 @@ static void mac_do_update(struct crypto_aes_ctx *ctx, u8 const in[], int blocks,
 {
 	int rounds = 6 + ctx->key_length / 4;
 
-	if (may_use_simd()) {
+	if (crypto_simd_usable()) {
 		kernel_neon_begin();
 		aes_mac_update(in, ctx->key_enc, rounds, blocks, dg, enc_before,
 			       enc_after);
@@ -707,7 +707,7 @@ static int cbcmac_final(struct shash_desc *desc, u8 *out)
 	struct mac_tfm_ctx *tctx = crypto_shash_ctx(desc->tfm);
 	struct mac_desc_ctx *ctx = shash_desc_ctx(desc);
 
-	mac_do_update(&tctx->key, NULL, 0, ctx->dg, 1, 0);
+	mac_do_update(&tctx->key, NULL, 0, ctx->dg, (ctx->len != 0), 0);
 
 	memcpy(out, ctx->dg, AES_BLOCK_SIZE);
 
diff --git a/arch/arm64/crypto/aes-neonbs-glue.c b/arch/arm64/crypto/aes-neonbs-glue.c
index e7a95a566462..02b65d9eb947 100644
--- a/arch/arm64/crypto/aes-neonbs-glue.c
+++ b/arch/arm64/crypto/aes-neonbs-glue.c
@@ -288,7 +288,7 @@ static int ctr_encrypt_sync(struct skcipher_request *req)
 	struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(req);
 	struct aesbs_ctr_ctx *ctx = crypto_skcipher_ctx(tfm);
 
-	if (!may_use_simd())
+	if (!crypto_simd_usable())
 		return aes_ctr_encrypt_fallback(&ctx->fallback, req);
 
 	return ctr_encrypt(req);
@@ -304,6 +304,8 @@ static int __xts_crypt(struct skcipher_request *req,
 	int err;
 
 	err = skcipher_walk_virt(&walk, req, false);
+	if (err)
+		return err;
 
 	kernel_neon_begin();
 	neon_aes_ecb_encrypt(walk.iv, walk.iv, ctx->twkey, ctx->key.rounds, 1);
@@ -440,7 +442,7 @@ static int __init aes_init(void)
 	int err;
 	int i;
 
-	if (!(elf_hwcap & HWCAP_ASIMD))
+	if (!cpu_have_named_feature(ASIMD))
 		return -ENODEV;
 
 	err = crypto_register_skciphers(aes_algs, ARRAY_SIZE(aes_algs));
diff --git a/arch/arm64/crypto/chacha-neon-glue.c b/arch/arm64/crypto/chacha-neon-glue.c
index bece1d85bd81..82029cda2e77 100644
--- a/arch/arm64/crypto/chacha-neon-glue.c
+++ b/arch/arm64/crypto/chacha-neon-glue.c
@@ -21,6 +21,7 @@
 
 #include <crypto/algapi.h>
 #include <crypto/chacha.h>
+#include <crypto/internal/simd.h>
 #include <crypto/internal/skcipher.h>
 #include <linux/kernel.h>
 #include <linux/module.h>
@@ -90,7 +91,7 @@ static int chacha_neon(struct skcipher_request *req)
 	struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(req);
 	struct chacha_ctx *ctx = crypto_skcipher_ctx(tfm);
 
-	if (req->cryptlen <= CHACHA_BLOCK_SIZE || !may_use_simd())
+	if (req->cryptlen <= CHACHA_BLOCK_SIZE || !crypto_simd_usable())
 		return crypto_chacha_crypt(req);
 
 	return chacha_neon_stream_xor(req, ctx, req->iv);
@@ -104,7 +105,7 @@ static int xchacha_neon(struct skcipher_request *req)
 	u32 state[16];
 	u8 real_iv[16];
 
-	if (req->cryptlen <= CHACHA_BLOCK_SIZE || !may_use_simd())
+	if (req->cryptlen <= CHACHA_BLOCK_SIZE || !crypto_simd_usable())
 		return crypto_xchacha_crypt(req);
 
 	crypto_chacha_init(state, ctx, req->iv);
@@ -173,7 +174,7 @@ static struct skcipher_alg algs[] = {
 
 static int __init chacha_simd_mod_init(void)
 {
-	if (!(elf_hwcap & HWCAP_ASIMD))
+	if (!cpu_have_named_feature(ASIMD))
 		return -ENODEV;
 
 	return crypto_register_skciphers(algs, ARRAY_SIZE(algs));
diff --git a/arch/arm64/crypto/crct10dif-ce-glue.c b/arch/arm64/crypto/crct10dif-ce-glue.c
index dd325829ee44..2e0a7d2eee24 100644
--- a/arch/arm64/crypto/crct10dif-ce-glue.c
+++ b/arch/arm64/crypto/crct10dif-ce-glue.c
@@ -16,6 +16,7 @@
 #include <linux/string.h>
 
 #include <crypto/internal/hash.h>
+#include <crypto/internal/simd.h>
 
 #include <asm/neon.h>
 #include <asm/simd.h>
@@ -38,7 +39,7 @@ static int crct10dif_update_pmull_p8(struct shash_desc *desc, const u8 *data,
 {
 	u16 *crc = shash_desc_ctx(desc);
 
-	if (length >= CRC_T10DIF_PMULL_CHUNK_SIZE && may_use_simd()) {
+	if (length >= CRC_T10DIF_PMULL_CHUNK_SIZE && crypto_simd_usable()) {
 		kernel_neon_begin();
 		*crc = crc_t10dif_pmull_p8(*crc, data, length);
 		kernel_neon_end();
@@ -54,7 +55,7 @@ static int crct10dif_update_pmull_p64(struct shash_desc *desc, const u8 *data,
 {
 	u16 *crc = shash_desc_ctx(desc);
 
-	if (length >= CRC_T10DIF_PMULL_CHUNK_SIZE && may_use_simd()) {
+	if (length >= CRC_T10DIF_PMULL_CHUNK_SIZE && crypto_simd_usable()) {
 		kernel_neon_begin();
 		*crc = crc_t10dif_pmull_p64(*crc, data, length);
 		kernel_neon_end();
@@ -101,7 +102,7 @@ static struct shash_alg crc_t10dif_alg[] = {{
 
 static int __init crc_t10dif_mod_init(void)
 {
-	if (elf_hwcap & HWCAP_PMULL)
+	if (cpu_have_named_feature(PMULL))
 		return crypto_register_shashes(crc_t10dif_alg,
 					       ARRAY_SIZE(crc_t10dif_alg));
 	else
@@ -111,7 +112,7 @@ static int __init crc_t10dif_mod_init(void)
 
 static void __exit crc_t10dif_mod_exit(void)
 {
-	if (elf_hwcap & HWCAP_PMULL)
+	if (cpu_have_named_feature(PMULL))
 		crypto_unregister_shashes(crc_t10dif_alg,
 					  ARRAY_SIZE(crc_t10dif_alg));
 	else
diff --git a/arch/arm64/crypto/ghash-ce-glue.c b/arch/arm64/crypto/ghash-ce-glue.c
index 791ad422c427..b39ed99b06fb 100644
--- a/arch/arm64/crypto/ghash-ce-glue.c
+++ b/arch/arm64/crypto/ghash-ce-glue.c
@@ -17,6 +17,7 @@
 #include <crypto/gf128mul.h>
 #include <crypto/internal/aead.h>
 #include <crypto/internal/hash.h>
+#include <crypto/internal/simd.h>
 #include <crypto/internal/skcipher.h>
 #include <crypto/scatterwalk.h>
 #include <linux/cpufeature.h>
@@ -89,7 +90,7 @@ static void ghash_do_update(int blocks, u64 dg[], const char *src,
 						struct ghash_key const *k,
 						const char *head))
 {
-	if (likely(may_use_simd())) {
+	if (likely(crypto_simd_usable())) {
 		kernel_neon_begin();
 		simd_update(blocks, dg, src, key, head);
 		kernel_neon_end();
@@ -441,7 +442,7 @@ static int gcm_encrypt(struct aead_request *req)
 
 	err = skcipher_walk_aead_encrypt(&walk, req, false);
 
-	if (likely(may_use_simd() && walk.total >= 2 * AES_BLOCK_SIZE)) {
+	if (likely(crypto_simd_usable() && walk.total >= 2 * AES_BLOCK_SIZE)) {
 		u32 const *rk = NULL;
 
 		kernel_neon_begin();
@@ -473,9 +474,11 @@ static int gcm_encrypt(struct aead_request *req)
 		put_unaligned_be32(2, iv + GCM_IV_SIZE);
 
 		while (walk.nbytes >= (2 * AES_BLOCK_SIZE)) {
-			int blocks = walk.nbytes / AES_BLOCK_SIZE;
+			const int blocks =
+				walk.nbytes / (2 * AES_BLOCK_SIZE) * 2;
 			u8 *dst = walk.dst.virt.addr;
 			u8 *src = walk.src.virt.addr;
+			int remaining = blocks;
 
 			do {
 				__aes_arm64_encrypt(ctx->aes_key.key_enc,
@@ -485,9 +488,9 @@ static int gcm_encrypt(struct aead_request *req)
 
 				dst += AES_BLOCK_SIZE;
 				src += AES_BLOCK_SIZE;
-			} while (--blocks > 0);
+			} while (--remaining > 0);
 
-			ghash_do_update(walk.nbytes / AES_BLOCK_SIZE, dg,
+			ghash_do_update(blocks, dg,
 					walk.dst.virt.addr, &ctx->ghash_key,
 					NULL, pmull_ghash_update_p64);
 
@@ -563,7 +566,7 @@ static int gcm_decrypt(struct aead_request *req)
 
 	err = skcipher_walk_aead_decrypt(&walk, req, false);
 
-	if (likely(may_use_simd() && walk.total >= 2 * AES_BLOCK_SIZE)) {
+	if (likely(crypto_simd_usable() && walk.total >= 2 * AES_BLOCK_SIZE)) {
 		u32 const *rk = NULL;
 
 		kernel_neon_begin();
@@ -609,7 +612,7 @@ static int gcm_decrypt(struct aead_request *req)
 		put_unaligned_be32(2, iv + GCM_IV_SIZE);
 
 		while (walk.nbytes >= (2 * AES_BLOCK_SIZE)) {
-			int blocks = walk.nbytes / AES_BLOCK_SIZE;
+			int blocks = walk.nbytes / (2 * AES_BLOCK_SIZE) * 2;
 			u8 *dst = walk.dst.virt.addr;
 			u8 *src = walk.src.virt.addr;
 
@@ -704,10 +707,10 @@ static int __init ghash_ce_mod_init(void)
 {
 	int ret;
 
-	if (!(elf_hwcap & HWCAP_ASIMD))
+	if (!cpu_have_named_feature(ASIMD))
 		return -ENODEV;
 
-	if (elf_hwcap & HWCAP_PMULL)
+	if (cpu_have_named_feature(PMULL))
 		ret = crypto_register_shashes(ghash_alg,
 					      ARRAY_SIZE(ghash_alg));
 	else
@@ -717,7 +720,7 @@ static int __init ghash_ce_mod_init(void)
 	if (ret)
 		return ret;
 
-	if (elf_hwcap & HWCAP_PMULL) {
+	if (cpu_have_named_feature(PMULL)) {
 		ret = crypto_register_aead(&gcm_aes_alg);
 		if (ret)
 			crypto_unregister_shashes(ghash_alg,
@@ -728,7 +731,7 @@ static int __init ghash_ce_mod_init(void)
 
 static void __exit ghash_ce_mod_exit(void)
 {
-	if (elf_hwcap & HWCAP_PMULL)
+	if (cpu_have_named_feature(PMULL))
 		crypto_unregister_shashes(ghash_alg, ARRAY_SIZE(ghash_alg));
 	else
 		crypto_unregister_shash(ghash_alg);
diff --git a/arch/arm64/crypto/nhpoly1305-neon-glue.c b/arch/arm64/crypto/nhpoly1305-neon-glue.c
index 22cc32ac9448..895d3727c1fb 100644
--- a/arch/arm64/crypto/nhpoly1305-neon-glue.c
+++ b/arch/arm64/crypto/nhpoly1305-neon-glue.c
@@ -9,6 +9,7 @@
 #include <asm/neon.h>
 #include <asm/simd.h>
 #include <crypto/internal/hash.h>
+#include <crypto/internal/simd.h>
 #include <crypto/nhpoly1305.h>
 #include <linux/module.h>
 
@@ -25,7 +26,7 @@ static void _nh_neon(const u32 *key, const u8 *message, size_t message_len,
 static int nhpoly1305_neon_update(struct shash_desc *desc,
 				  const u8 *src, unsigned int srclen)
 {
-	if (srclen < 64 || !may_use_simd())
+	if (srclen < 64 || !crypto_simd_usable())
 		return crypto_nhpoly1305_update(desc, src, srclen);
 
 	do {
@@ -56,7 +57,7 @@ static struct shash_alg nhpoly1305_alg = {
 
 static int __init nhpoly1305_mod_init(void)
 {
-	if (!(elf_hwcap & HWCAP_ASIMD))
+	if (!cpu_have_named_feature(ASIMD))
 		return -ENODEV;
 
 	return crypto_register_shash(&nhpoly1305_alg);
diff --git a/arch/arm64/crypto/sha1-ce-glue.c b/arch/arm64/crypto/sha1-ce-glue.c
index 17fac2889f56..eaa7a8258f1c 100644
--- a/arch/arm64/crypto/sha1-ce-glue.c
+++ b/arch/arm64/crypto/sha1-ce-glue.c
@@ -12,6 +12,7 @@
 #include <asm/simd.h>
 #include <asm/unaligned.h>
 #include <crypto/internal/hash.h>
+#include <crypto/internal/simd.h>
 #include <crypto/sha.h>
 #include <crypto/sha1_base.h>
 #include <linux/cpufeature.h>
@@ -38,7 +39,7 @@ static int sha1_ce_update(struct shash_desc *desc, const u8 *data,
 {
 	struct sha1_ce_state *sctx = shash_desc_ctx(desc);
 
-	if (!may_use_simd())
+	if (!crypto_simd_usable())
 		return crypto_sha1_update(desc, data, len);
 
 	sctx->finalize = 0;
@@ -56,7 +57,7 @@ static int sha1_ce_finup(struct shash_desc *desc, const u8 *data,
 	struct sha1_ce_state *sctx = shash_desc_ctx(desc);
 	bool finalize = !sctx->sst.count && !(len % SHA1_BLOCK_SIZE);
 
-	if (!may_use_simd())
+	if (!crypto_simd_usable())
 		return crypto_sha1_finup(desc, data, len, out);
 
 	/*
@@ -78,7 +79,7 @@ static int sha1_ce_final(struct shash_desc *desc, u8 *out)
 {
 	struct sha1_ce_state *sctx = shash_desc_ctx(desc);
 
-	if (!may_use_simd())
+	if (!crypto_simd_usable())
 		return crypto_sha1_finup(desc, NULL, 0, out);
 
 	sctx->finalize = 0;
diff --git a/arch/arm64/crypto/sha2-ce-glue.c b/arch/arm64/crypto/sha2-ce-glue.c
index 261f5195cab7..a725997e55f2 100644
--- a/arch/arm64/crypto/sha2-ce-glue.c
+++ b/arch/arm64/crypto/sha2-ce-glue.c
@@ -12,6 +12,7 @@
 #include <asm/simd.h>
 #include <asm/unaligned.h>
 #include <crypto/internal/hash.h>
+#include <crypto/internal/simd.h>
 #include <crypto/sha.h>
 #include <crypto/sha256_base.h>
 #include <linux/cpufeature.h>
@@ -42,7 +43,7 @@ static int sha256_ce_update(struct shash_desc *desc, const u8 *data,
 {
 	struct sha256_ce_state *sctx = shash_desc_ctx(desc);
 
-	if (!may_use_simd())
+	if (!crypto_simd_usable())
 		return sha256_base_do_update(desc, data, len,
 				(sha256_block_fn *)sha256_block_data_order);
 
@@ -61,7 +62,7 @@ static int sha256_ce_finup(struct shash_desc *desc, const u8 *data,
 	struct sha256_ce_state *sctx = shash_desc_ctx(desc);
 	bool finalize = !sctx->sst.count && !(len % SHA256_BLOCK_SIZE);
 
-	if (!may_use_simd()) {
+	if (!crypto_simd_usable()) {
 		if (len)
 			sha256_base_do_update(desc, data, len,
 				(sha256_block_fn *)sha256_block_data_order);
@@ -90,7 +91,7 @@ static int sha256_ce_final(struct shash_desc *desc, u8 *out)
 {
 	struct sha256_ce_state *sctx = shash_desc_ctx(desc);
 
-	if (!may_use_simd()) {
+	if (!crypto_simd_usable()) {
 		sha256_base_do_finalize(desc,
 				(sha256_block_fn *)sha256_block_data_order);
 		return sha256_base_finish(desc, out);
diff --git a/arch/arm64/crypto/sha256-glue.c b/arch/arm64/crypto/sha256-glue.c
index 4aedeaefd61f..e62298740e31 100644
--- a/arch/arm64/crypto/sha256-glue.c
+++ b/arch/arm64/crypto/sha256-glue.c
@@ -14,6 +14,7 @@
 #include <asm/neon.h>
 #include <asm/simd.h>
 #include <crypto/internal/hash.h>
+#include <crypto/internal/simd.h>
 #include <crypto/sha.h>
 #include <crypto/sha256_base.h>
 #include <linux/cryptohash.h>
@@ -89,7 +90,7 @@ static int sha256_update_neon(struct shash_desc *desc, const u8 *data,
 {
 	struct sha256_state *sctx = shash_desc_ctx(desc);
 
-	if (!may_use_simd())
+	if (!crypto_simd_usable())
 		return sha256_base_do_update(desc, data, len,
 				(sha256_block_fn *)sha256_block_data_order);
 
@@ -119,7 +120,7 @@ static int sha256_update_neon(struct shash_desc *desc, const u8 *data,
 static int sha256_finup_neon(struct shash_desc *desc, const u8 *data,
 			     unsigned int len, u8 *out)
 {
-	if (!may_use_simd()) {
+	if (!crypto_simd_usable()) {
 		if (len)
 			sha256_base_do_update(desc, data, len,
 				(sha256_block_fn *)sha256_block_data_order);
@@ -173,7 +174,7 @@ static int __init sha256_mod_init(void)
 	if (ret)
 		return ret;
 
-	if (elf_hwcap & HWCAP_ASIMD) {
+	if (cpu_have_named_feature(ASIMD)) {
 		ret = crypto_register_shashes(neon_algs, ARRAY_SIZE(neon_algs));
 		if (ret)
 			crypto_unregister_shashes(algs, ARRAY_SIZE(algs));
@@ -183,7 +184,7 @@ static int __init sha256_mod_init(void)
 
 static void __exit sha256_mod_fini(void)
 {
-	if (elf_hwcap & HWCAP_ASIMD)
+	if (cpu_have_named_feature(ASIMD))
 		crypto_unregister_shashes(neon_algs, ARRAY_SIZE(neon_algs));
 	crypto_unregister_shashes(algs, ARRAY_SIZE(algs));
 }
diff --git a/arch/arm64/crypto/sha3-ce-glue.c b/arch/arm64/crypto/sha3-ce-glue.c
index a336feac0f59..9a4bbfc45f40 100644
--- a/arch/arm64/crypto/sha3-ce-glue.c
+++ b/arch/arm64/crypto/sha3-ce-glue.c
@@ -14,6 +14,7 @@
 #include <asm/simd.h>
 #include <asm/unaligned.h>
 #include <crypto/internal/hash.h>
+#include <crypto/internal/simd.h>
 #include <crypto/sha3.h>
 #include <linux/cpufeature.h>
 #include <linux/crypto.h>
@@ -32,7 +33,7 @@ static int sha3_update(struct shash_desc *desc, const u8 *data,
 	struct sha3_state *sctx = shash_desc_ctx(desc);
 	unsigned int digest_size = crypto_shash_digestsize(desc->tfm);
 
-	if (!may_use_simd())
+	if (!crypto_simd_usable())
 		return crypto_sha3_update(desc, data, len);
 
 	if ((sctx->partial + len) >= sctx->rsiz) {
@@ -76,7 +77,7 @@ static int sha3_final(struct shash_desc *desc, u8 *out)
 	__le64 *digest = (__le64 *)out;
 	int i;
 
-	if (!may_use_simd())
+	if (!crypto_simd_usable())
 		return crypto_sha3_final(desc, out);
 
 	sctx->buf[sctx->partial++] = 0x06;
diff --git a/arch/arm64/crypto/sha512-ce-glue.c b/arch/arm64/crypto/sha512-ce-glue.c
index f2c5f28c622a..2369540040aa 100644
--- a/arch/arm64/crypto/sha512-ce-glue.c
+++ b/arch/arm64/crypto/sha512-ce-glue.c
@@ -13,6 +13,7 @@
 #include <asm/simd.h>
 #include <asm/unaligned.h>
 #include <crypto/internal/hash.h>
+#include <crypto/internal/simd.h>
 #include <crypto/sha.h>
 #include <crypto/sha512_base.h>
 #include <linux/cpufeature.h>
@@ -31,7 +32,7 @@ asmlinkage void sha512_block_data_order(u64 *digest, u8 const *src, int blocks);
 static int sha512_ce_update(struct shash_desc *desc, const u8 *data,
 			    unsigned int len)
 {
-	if (!may_use_simd())
+	if (!crypto_simd_usable())
 		return sha512_base_do_update(desc, data, len,
 				(sha512_block_fn *)sha512_block_data_order);
 
@@ -46,7 +47,7 @@ static int sha512_ce_update(struct shash_desc *desc, const u8 *data,
 static int sha512_ce_finup(struct shash_desc *desc, const u8 *data,
 			   unsigned int len, u8 *out)
 {
-	if (!may_use_simd()) {
+	if (!crypto_simd_usable()) {
 		if (len)
 			sha512_base_do_update(desc, data, len,
 				(sha512_block_fn *)sha512_block_data_order);
@@ -65,7 +66,7 @@ static int sha512_ce_finup(struct shash_desc *desc, const u8 *data,
 
 static int sha512_ce_final(struct shash_desc *desc, u8 *out)
 {
-	if (!may_use_simd()) {
+	if (!crypto_simd_usable()) {
 		sha512_base_do_finalize(desc,
 				(sha512_block_fn *)sha512_block_data_order);
 		return sha512_base_finish(desc, out);
diff --git a/arch/arm64/crypto/sm3-ce-glue.c b/arch/arm64/crypto/sm3-ce-glue.c
index 88938a20d9b2..5d15533799a2 100644
--- a/arch/arm64/crypto/sm3-ce-glue.c
+++ b/arch/arm64/crypto/sm3-ce-glue.c
@@ -12,6 +12,7 @@
 #include <asm/simd.h>
 #include <asm/unaligned.h>
 #include <crypto/internal/hash.h>
+#include <crypto/internal/simd.h>
 #include <crypto/sm3.h>
 #include <crypto/sm3_base.h>
 #include <linux/cpufeature.h>
@@ -28,7 +29,7 @@ asmlinkage void sm3_ce_transform(struct sm3_state *sst, u8 const *src,
 static int sm3_ce_update(struct shash_desc *desc, const u8 *data,
 			 unsigned int len)
 {
-	if (!may_use_simd())
+	if (!crypto_simd_usable())
 		return crypto_sm3_update(desc, data, len);
 
 	kernel_neon_begin();
@@ -40,7 +41,7 @@ static int sm3_ce_update(struct shash_desc *desc, const u8 *data,
 
 static int sm3_ce_final(struct shash_desc *desc, u8 *out)
 {
-	if (!may_use_simd())
+	if (!crypto_simd_usable())
 		return crypto_sm3_finup(desc, NULL, 0, out);
 
 	kernel_neon_begin();
@@ -53,7 +54,7 @@ static int sm3_ce_final(struct shash_desc *desc, u8 *out)
 static int sm3_ce_finup(struct shash_desc *desc, const u8 *data,
 			unsigned int len, u8 *out)
 {
-	if (!may_use_simd())
+	if (!crypto_simd_usable())
 		return crypto_sm3_finup(desc, data, len, out);
 
 	kernel_neon_begin();
diff --git a/arch/arm64/crypto/sm4-ce-glue.c b/arch/arm64/crypto/sm4-ce-glue.c
index 0c4fc223f225..2754c875d39c 100644
--- a/arch/arm64/crypto/sm4-ce-glue.c
+++ b/arch/arm64/crypto/sm4-ce-glue.c
@@ -3,6 +3,7 @@
 #include <asm/neon.h>
 #include <asm/simd.h>
 #include <crypto/sm4.h>
+#include <crypto/internal/simd.h>
 #include <linux/module.h>
 #include <linux/cpufeature.h>
 #include <linux/crypto.h>
@@ -20,7 +21,7 @@ static void sm4_ce_encrypt(struct crypto_tfm *tfm, u8 *out, const u8 *in)
 {
 	const struct crypto_sm4_ctx *ctx = crypto_tfm_ctx(tfm);
 
-	if (!may_use_simd()) {
+	if (!crypto_simd_usable()) {
 		crypto_sm4_encrypt(tfm, out, in);
 	} else {
 		kernel_neon_begin();
@@ -33,7 +34,7 @@ static void sm4_ce_decrypt(struct crypto_tfm *tfm, u8 *out, const u8 *in)
 {
 	const struct crypto_sm4_ctx *ctx = crypto_tfm_ctx(tfm);
 
-	if (!may_use_simd()) {
+	if (!crypto_simd_usable()) {
 		crypto_sm4_decrypt(tfm, out, in);
 	} else {
 		kernel_neon_begin();
diff --git a/arch/arm64/include/asm/Kbuild b/arch/arm64/include/asm/Kbuild
index 1e17ea5c372b..eb0df239a759 100644
--- a/arch/arm64/include/asm/Kbuild
+++ b/arch/arm64/include/asm/Kbuild
@@ -13,10 +13,10 @@ generic-y += local.h
 generic-y += local64.h
 generic-y += mcs_spinlock.h
 generic-y += mm-arch-hooks.h
+generic-y += mmiowb.h
 generic-y += msi.h
 generic-y += qrwlock.h
 generic-y += qspinlock.h
-generic-y += rwsem.h
 generic-y += segment.h
 generic-y += serial.h
 generic-y += set_memory.h
diff --git a/arch/arm64/include/asm/arch_timer.h b/arch/arm64/include/asm/arch_timer.h
index f2a234d6516c..b7bca1ae09e6 100644
--- a/arch/arm64/include/asm/arch_timer.h
+++ b/arch/arm64/include/asm/arch_timer.h
@@ -31,11 +31,23 @@
 #include <clocksource/arm_arch_timer.h>
 
 #if IS_ENABLED(CONFIG_ARM_ARCH_TIMER_OOL_WORKAROUND)
-extern struct static_key_false arch_timer_read_ool_enabled;
-#define needs_unstable_timer_counter_workaround() \
-	static_branch_unlikely(&arch_timer_read_ool_enabled)
+#define has_erratum_handler(h)						\
+	({								\
+		const struct arch_timer_erratum_workaround *__wa;	\
+		__wa = __this_cpu_read(timer_unstable_counter_workaround); \
+		(__wa && __wa->h);					\
+	})
+
+#define erratum_handler(h)						\
+	({								\
+		const struct arch_timer_erratum_workaround *__wa;	\
+		__wa = __this_cpu_read(timer_unstable_counter_workaround); \
+		(__wa && __wa->h) ? __wa->h : arch_timer_##h;		\
+	})
+
 #else
-#define needs_unstable_timer_counter_workaround()  false
+#define has_erratum_handler(h)			   false
+#define erratum_handler(h)			   (arch_timer_##h)
 #endif
 
 enum arch_timer_erratum_match_type {
@@ -61,23 +73,37 @@ struct arch_timer_erratum_workaround {
 DECLARE_PER_CPU(const struct arch_timer_erratum_workaround *,
 		timer_unstable_counter_workaround);
 
+/* inline sysreg accessors that make erratum_handler() work */
+static inline notrace u32 arch_timer_read_cntp_tval_el0(void)
+{
+	return read_sysreg(cntp_tval_el0);
+}
+
+static inline notrace u32 arch_timer_read_cntv_tval_el0(void)
+{
+	return read_sysreg(cntv_tval_el0);
+}
+
+static inline notrace u64 arch_timer_read_cntpct_el0(void)
+{
+	return read_sysreg(cntpct_el0);
+}
+
+static inline notrace u64 arch_timer_read_cntvct_el0(void)
+{
+	return read_sysreg(cntvct_el0);
+}
+
 #define arch_timer_reg_read_stable(reg)					\
-({									\
-	u64 _val;							\
-	if (needs_unstable_timer_counter_workaround()) {		\
-		const struct arch_timer_erratum_workaround *wa;		\
+	({								\
+		u64 _val;						\
+									\
 		preempt_disable_notrace();				\
-		wa = __this_cpu_read(timer_unstable_counter_workaround); \
-		if (wa && wa->read_##reg)				\
-			_val = wa->read_##reg();			\
-		else							\
-			_val = read_sysreg(reg);			\
+		_val = erratum_handler(read_ ## reg)();			\
 		preempt_enable_notrace();				\
-	} else {							\
-		_val = read_sysreg(reg);				\
-	}								\
-	_val;								\
-})
+									\
+		_val;							\
+	})
 
 /*
  * These register accessors are marked inline so the compiler can
@@ -148,18 +174,67 @@ static inline void arch_timer_set_cntkctl(u32 cntkctl)
 	isb();
 }
 
-static inline u64 arch_counter_get_cntpct(void)
+/*
+ * Ensure that reads of the counter are treated the same as memory reads
+ * for the purposes of ordering by subsequent memory barriers.
+ *
+ * This insanity brought to you by speculative system register reads,
+ * out-of-order memory accesses, sequence locks and Thomas Gleixner.
+ *
+ * http://lists.infradead.org/pipermail/linux-arm-kernel/2019-February/631195.html
+ */
+#define arch_counter_enforce_ordering(val) do {				\
+	u64 tmp, _val = (val);						\
+									\
+	asm volatile(							\
+	"	eor	%0, %1, %1\n"					\
+	"	add	%0, sp, %0\n"					\
+	"	ldr	xzr, [%0]"					\
+	: "=r" (tmp) : "r" (_val));					\
+} while (0)
+
+static inline u64 __arch_counter_get_cntpct_stable(void)
+{
+	u64 cnt;
+
+	isb();
+	cnt = arch_timer_reg_read_stable(cntpct_el0);
+	arch_counter_enforce_ordering(cnt);
+	return cnt;
+}
+
+static inline u64 __arch_counter_get_cntpct(void)
 {
+	u64 cnt;
+
 	isb();
-	return arch_timer_reg_read_stable(cntpct_el0);
+	cnt = read_sysreg(cntpct_el0);
+	arch_counter_enforce_ordering(cnt);
+	return cnt;
 }
 
-static inline u64 arch_counter_get_cntvct(void)
+static inline u64 __arch_counter_get_cntvct_stable(void)
 {
+	u64 cnt;
+
 	isb();
-	return arch_timer_reg_read_stable(cntvct_el0);
+	cnt = arch_timer_reg_read_stable(cntvct_el0);
+	arch_counter_enforce_ordering(cnt);
+	return cnt;
 }
 
+static inline u64 __arch_counter_get_cntvct(void)
+{
+	u64 cnt;
+
+	isb();
+	cnt = read_sysreg(cntvct_el0);
+	arch_counter_enforce_ordering(cnt);
+	return cnt;
+}
+
+#undef arch_counter_enforce_ordering
+
 static inline int arch_timer_arch_init(void)
 {
 	return 0;
diff --git a/arch/arm64/include/asm/assembler.h b/arch/arm64/include/asm/assembler.h
index c5308d01e228..039fbd822ec6 100644
--- a/arch/arm64/include/asm/assembler.h
+++ b/arch/arm64/include/asm/assembler.h
@@ -407,10 +407,14 @@ alternative_endif
 	.ifc	\op, cvap
 	sys	3, c7, c12, 1, \kaddr	// dc cvap
 	.else
+	.ifc	\op, cvadp
+	sys	3, c7, c13, 1, \kaddr	// dc cvadp
+	.else
 	dc	\op, \kaddr
 	.endif
 	.endif
 	.endif
+	.endif
 	add	\kaddr, \kaddr, \tmp1
 	cmp	\kaddr, \size
 	b.lo	9998b
@@ -442,8 +446,8 @@ USER(\label, ic	ivau, \tmp2)			// invalidate I line PoU
  * reset_pmuserenr_el0 - reset PMUSERENR_EL0 if PMUv3 present
  */
 	.macro	reset_pmuserenr_el0, tmpreg
-	mrs	\tmpreg, id_aa64dfr0_el1	// Check ID_AA64DFR0_EL1 PMUVer
-	sbfx	\tmpreg, \tmpreg, #8, #4
+	mrs	\tmpreg, id_aa64dfr0_el1
+	sbfx	\tmpreg, \tmpreg, #ID_AA64DFR0_PMUVER_SHIFT, #4
 	cmp	\tmpreg, #1			// Skip if no PMU present
 	b.lt	9000f
 	msr	pmuserenr_el0, xzr		// Disable PMU access from EL0
diff --git a/arch/arm64/include/asm/barrier.h b/arch/arm64/include/asm/barrier.h
index f66bb04fdf2d..85b6bedbcc68 100644
--- a/arch/arm64/include/asm/barrier.h
+++ b/arch/arm64/include/asm/barrier.h
@@ -20,6 +20,8 @@
 
 #ifndef __ASSEMBLY__
 
+#include <linux/kasan-checks.h>
+
 #define __nops(n)	".rept	" #n "\nnop\n.endr\n"
 #define nops(n)		asm volatile(__nops(n))
 
@@ -72,31 +74,33 @@ static inline unsigned long array_index_mask_nospec(unsigned long idx,
 
 #define __smp_store_release(p, v)					\
 do {									\
+	typeof(p) __p = (p);						\
 	union { typeof(*p) __val; char __c[1]; } __u =			\
-		{ .__val = (__force typeof(*p)) (v) }; 			\
+		{ .__val = (__force typeof(*p)) (v) };			\
 	compiletime_assert_atomic_type(*p);				\
+	kasan_check_write(__p, sizeof(*p));				\
 	switch (sizeof(*p)) {						\
 	case 1:								\
 		asm volatile ("stlrb %w1, %0"				\
-				: "=Q" (*p)				\
+				: "=Q" (*__p)				\
 				: "r" (*(__u8 *)__u.__c)		\
 				: "memory");				\
 		break;							\
 	case 2:								\
 		asm volatile ("stlrh %w1, %0"				\
-				: "=Q" (*p)				\
+				: "=Q" (*__p)				\
 				: "r" (*(__u16 *)__u.__c)		\
 				: "memory");				\
 		break;							\
 	case 4:								\
 		asm volatile ("stlr %w1, %0"				\
-				: "=Q" (*p)				\
+				: "=Q" (*__p)				\
 				: "r" (*(__u32 *)__u.__c)		\
 				: "memory");				\
 		break;							\
 	case 8:								\
 		asm volatile ("stlr %1, %0"				\
-				: "=Q" (*p)				\
+				: "=Q" (*__p)				\
 				: "r" (*(__u64 *)__u.__c)		\
 				: "memory");				\
 		break;							\
@@ -106,27 +110,29 @@ do {									\
 #define __smp_load_acquire(p)						\
 ({									\
 	union { typeof(*p) __val; char __c[1]; } __u;			\
+	typeof(p) __p = (p);						\
 	compiletime_assert_atomic_type(*p);				\
+	kasan_check_read(__p, sizeof(*p));				\
 	switch (sizeof(*p)) {						\
 	case 1:								\
 		asm volatile ("ldarb %w0, %1"				\
 			: "=r" (*(__u8 *)__u.__c)			\
-			: "Q" (*p) : "memory");				\
+			: "Q" (*__p) : "memory");			\
 		break;							\
 	case 2:								\
 		asm volatile ("ldarh %w0, %1"				\
 			: "=r" (*(__u16 *)__u.__c)			\
-			: "Q" (*p) : "memory");				\
+			: "Q" (*__p) : "memory");			\
 		break;							\
 	case 4:								\
 		asm volatile ("ldar %w0, %1"				\
 			: "=r" (*(__u32 *)__u.__c)			\
-			: "Q" (*p) : "memory");				\
+			: "Q" (*__p) : "memory");			\
 		break;							\
 	case 8:								\
 		asm volatile ("ldar %0, %1"				\
 			: "=r" (*(__u64 *)__u.__c)			\
-			: "Q" (*p) : "memory");				\
+			: "Q" (*__p) : "memory");			\
 		break;							\
 	}								\
 	__u.__val;							\
diff --git a/arch/arm64/include/asm/brk-imm.h b/arch/arm64/include/asm/brk-imm.h
index 2945fe6cd863..d84294064e6a 100644
--- a/arch/arm64/include/asm/brk-imm.h
+++ b/arch/arm64/include/asm/brk-imm.h
@@ -11,6 +11,8 @@
 
 /*
  * #imm16 values used for BRK instruction generation
+ * 0x004: for installing kprobes
+ * 0x005: for installing uprobes
  * Allowed values for kgdb are 0x400 - 0x7ff
  * 0x100: for triggering a fault on purpose (reserved)
  * 0x400: for dynamic BRK instruction
@@ -18,10 +20,13 @@
  * 0x800: kernel-mode BUG() and WARN() traps
  * 0x9xx: tag-based KASAN trap (allowed values 0x900 - 0x9ff)
  */
+#define KPROBES_BRK_IMM			0x004
+#define UPROBES_BRK_IMM			0x005
 #define FAULT_BRK_IMM			0x100
 #define KGDB_DYN_DBG_BRK_IMM		0x400
 #define KGDB_COMPILED_DBG_BRK_IMM	0x401
 #define BUG_BRK_IMM			0x800
 #define KASAN_BRK_IMM			0x900
+#define KASAN_BRK_MASK			0x0ff
 
 #endif
diff --git a/arch/arm64/include/asm/cpucaps.h b/arch/arm64/include/asm/cpucaps.h
index f6a76e43f39e..defdc67d9ab4 100644
--- a/arch/arm64/include/asm/cpucaps.h
+++ b/arch/arm64/include/asm/cpucaps.h
@@ -61,7 +61,8 @@
 #define ARM64_HAS_GENERIC_AUTH_ARCH		40
 #define ARM64_HAS_GENERIC_AUTH_IMP_DEF		41
 #define ARM64_HAS_IRQ_PRIO_MASKING		42
+#define ARM64_HAS_DCPODP			43
 
-#define ARM64_NCAPS				43
+#define ARM64_NCAPS				44
 
 #endif /* __ASM_CPUCAPS_H */
diff --git a/arch/arm64/include/asm/cpufeature.h b/arch/arm64/include/asm/cpufeature.h
index e505e1fbd2b9..f210bcf096f7 100644
--- a/arch/arm64/include/asm/cpufeature.h
+++ b/arch/arm64/include/asm/cpufeature.h
@@ -14,15 +14,8 @@
 #include <asm/hwcap.h>
 #include <asm/sysreg.h>
 
-/*
- * In the arm64 world (as in the ARM world), elf_hwcap is used both internally
- * in the kernel and for user space to keep track of which optional features
- * are supported by the current system. So let's map feature 'x' to HWCAP_x.
- * Note that HWCAP_x constants are bit fields so we need to take the log.
- */
-
-#define MAX_CPU_FEATURES	(8 * sizeof(elf_hwcap))
-#define cpu_feature(x)		ilog2(HWCAP_ ## x)
+#define MAX_CPU_FEATURES	64
+#define cpu_feature(x)		KERNEL_HWCAP_ ## x
 
 #ifndef __ASSEMBLY__
 
@@ -399,11 +392,13 @@ extern DECLARE_BITMAP(boot_capabilities, ARM64_NPATCHABLE);
 	for_each_set_bit(cap, cpu_hwcaps, ARM64_NCAPS)
 
 bool this_cpu_has_cap(unsigned int cap);
+void cpu_set_feature(unsigned int num);
+bool cpu_have_feature(unsigned int num);
+unsigned long cpu_get_elf_hwcap(void);
+unsigned long cpu_get_elf_hwcap2(void);
 
-static inline bool cpu_have_feature(unsigned int num)
-{
-	return elf_hwcap & (1UL << num);
-}
+#define cpu_set_named_feature(name) cpu_set_feature(cpu_feature(name))
+#define cpu_have_named_feature(name) cpu_have_feature(cpu_feature(name))
 
 /* System capability check for constant caps */
 static inline bool __cpus_have_const_cap(int num)
@@ -638,11 +633,7 @@ static inline int arm64_get_ssbd_state(void)
 #endif
 }
 
-#ifdef CONFIG_ARM64_SSBD
 void arm64_set_ssbd_mitigation(bool state);
-#else
-static inline void arm64_set_ssbd_mitigation(bool state) {}
-#endif
 
 extern int do_emulate_mrs(struct pt_regs *regs, u32 sys_reg, u32 rt);
 
diff --git a/arch/arm64/include/asm/cputype.h b/arch/arm64/include/asm/cputype.h
index 5f1437099b99..2602bae334fb 100644
--- a/arch/arm64/include/asm/cputype.h
+++ b/arch/arm64/include/asm/cputype.h
@@ -89,6 +89,7 @@
 #define ARM_CPU_PART_CORTEX_A35		0xD04
 #define ARM_CPU_PART_CORTEX_A55		0xD05
 #define ARM_CPU_PART_CORTEX_A76		0xD0B
+#define ARM_CPU_PART_NEOVERSE_N1	0xD0C
 
 #define APM_CPU_PART_POTENZA		0x000
 
@@ -118,6 +119,7 @@
 #define MIDR_CORTEX_A35 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_A35)
 #define MIDR_CORTEX_A55 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_A55)
 #define MIDR_CORTEX_A76	MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_A76)
+#define MIDR_NEOVERSE_N1 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_NEOVERSE_N1)
 #define MIDR_THUNDERX	MIDR_CPU_MODEL(ARM_CPU_IMP_CAVIUM, CAVIUM_CPU_PART_THUNDERX)
 #define MIDR_THUNDERX_81XX MIDR_CPU_MODEL(ARM_CPU_IMP_CAVIUM, CAVIUM_CPU_PART_THUNDERX_81XX)
 #define MIDR_THUNDERX_83XX MIDR_CPU_MODEL(ARM_CPU_IMP_CAVIUM, CAVIUM_CPU_PART_THUNDERX_83XX)
diff --git a/arch/arm64/include/asm/debug-monitors.h b/arch/arm64/include/asm/debug-monitors.h
index a44cf5225429..0679f781696d 100644
--- a/arch/arm64/include/asm/debug-monitors.h
+++ b/arch/arm64/include/asm/debug-monitors.h
@@ -65,12 +65,9 @@
 #define CACHE_FLUSH_IS_SAFE		1
 
 /* kprobes BRK opcodes with ESR encoding  */
-#define BRK64_ESR_MASK		0xFFFF
-#define BRK64_ESR_KPROBES	0x0004
-#define BRK64_OPCODE_KPROBES	(AARCH64_BREAK_MON | (BRK64_ESR_KPROBES << 5))
+#define BRK64_OPCODE_KPROBES	(AARCH64_BREAK_MON | (KPROBES_BRK_IMM << 5))
 /* uprobes BRK opcodes with ESR encoding  */
-#define BRK64_ESR_UPROBES	0x0005
-#define BRK64_OPCODE_UPROBES	(AARCH64_BREAK_MON | (BRK64_ESR_UPROBES << 5))
+#define BRK64_OPCODE_UPROBES	(AARCH64_BREAK_MON | (UPROBES_BRK_IMM << 5))
 
 /* AArch32 */
 #define DBG_ESR_EVT_BKPT	0x4
@@ -94,18 +91,24 @@ struct step_hook {
 	int (*fn)(struct pt_regs *regs, unsigned int esr);
 };
 
-void register_step_hook(struct step_hook *hook);
-void unregister_step_hook(struct step_hook *hook);
+void register_user_step_hook(struct step_hook *hook);
+void unregister_user_step_hook(struct step_hook *hook);
+
+void register_kernel_step_hook(struct step_hook *hook);
+void unregister_kernel_step_hook(struct step_hook *hook);
 
 struct break_hook {
 	struct list_head node;
-	u32 esr_val;
-	u32 esr_mask;
 	int (*fn)(struct pt_regs *regs, unsigned int esr);
+	u16 imm;
+	u16 mask; /* These bits are ignored when comparing with imm */
 };
 
-void register_break_hook(struct break_hook *hook);
-void unregister_break_hook(struct break_hook *hook);
+void register_user_break_hook(struct break_hook *hook);
+void unregister_user_break_hook(struct break_hook *hook);
+
+void register_kernel_break_hook(struct break_hook *hook);
+void unregister_kernel_break_hook(struct break_hook *hook);
 
 u8 debug_monitors_arch(void);
 
diff --git a/arch/arm64/include/asm/elf.h b/arch/arm64/include/asm/elf.h
index 6adc1a90e7e6..355d120b78cb 100644
--- a/arch/arm64/include/asm/elf.h
+++ b/arch/arm64/include/asm/elf.h
@@ -214,10 +214,10 @@ typedef compat_elf_greg_t		compat_elf_gregset_t[COMPAT_ELF_NGREG];
 	set_thread_flag(TIF_32BIT);					\
  })
 #define COMPAT_ARCH_DLINFO
-extern int aarch32_setup_vectors_page(struct linux_binprm *bprm,
-				      int uses_interp);
+extern int aarch32_setup_additional_pages(struct linux_binprm *bprm,
+					  int uses_interp);
 #define compat_arch_setup_additional_pages \
-					aarch32_setup_vectors_page
+					aarch32_setup_additional_pages
 
 #endif /* CONFIG_COMPAT */
 
diff --git a/arch/arm64/include/asm/esr.h b/arch/arm64/include/asm/esr.h
index 52233f00d53d..0e27fe91d5ea 100644
--- a/arch/arm64/include/asm/esr.h
+++ b/arch/arm64/include/asm/esr.h
@@ -156,9 +156,7 @@
 				 ESR_ELx_WFx_ISS_WFI)
 
 /* BRK instruction trap from AArch64 state */
-#define ESR_ELx_VAL_BRK64(imm)					\
-	((ESR_ELx_EC_BRK64 << ESR_ELx_EC_SHIFT) | ESR_ELx_IL |	\
-	 ((imm) & 0xffff))
+#define ESR_ELx_BRK64_ISS_COMMENT_MASK	0xffff
 
 /* ISS field definitions for System instruction traps */
 #define ESR_ELx_SYS64_ISS_RES0_SHIFT	22
@@ -198,9 +196,10 @@
 /*
  * User space cache operations have the following sysreg encoding
  * in System instructions.
- * op0=1, op1=3, op2=1, crn=7, crm={ 5, 10, 11, 12, 14 }, WRITE (L=0)
+ * op0=1, op1=3, op2=1, crn=7, crm={ 5, 10, 11, 12, 13, 14 }, WRITE (L=0)
  */
 #define ESR_ELx_SYS64_ISS_CRM_DC_CIVAC	14
+#define ESR_ELx_SYS64_ISS_CRM_DC_CVADP	13
 #define ESR_ELx_SYS64_ISS_CRM_DC_CVAP	12
 #define ESR_ELx_SYS64_ISS_CRM_DC_CVAU	11
 #define ESR_ELx_SYS64_ISS_CRM_DC_CVAC	10
diff --git a/arch/arm64/include/asm/futex.h b/arch/arm64/include/asm/futex.h
index cccb83ad7fa8..a56efb5626fa 100644
--- a/arch/arm64/include/asm/futex.h
+++ b/arch/arm64/include/asm/futex.h
@@ -23,26 +23,34 @@
 
 #include <asm/errno.h>
 
+#define FUTEX_MAX_LOOPS	128 /* What's the largest number you can think of? */
+
 #define __futex_atomic_op(insn, ret, oldval, uaddr, tmp, oparg)		\
 do {									\
+	unsigned int loops = FUTEX_MAX_LOOPS;				\
+									\
 	uaccess_enable();						\
 	asm volatile(							\
 "	prfm	pstl1strm, %2\n"					\
 "1:	ldxr	%w1, %2\n"						\
 	insn "\n"							\
-"2:	stlxr	%w3, %w0, %2\n"						\
-"	cbnz	%w3, 1b\n"						\
-"	dmb	ish\n"							\
+"2:	stlxr	%w0, %w3, %2\n"						\
+"	cbz	%w0, 3f\n"						\
+"	sub	%w4, %w4, %w0\n"					\
+"	cbnz	%w4, 1b\n"						\
+"	mov	%w0, %w7\n"						\
 "3:\n"									\
+"	dmb	ish\n"							\
 "	.pushsection .fixup,\"ax\"\n"					\
 "	.align	2\n"							\
-"4:	mov	%w0, %w5\n"						\
+"4:	mov	%w0, %w6\n"						\
 "	b	3b\n"							\
 "	.popsection\n"							\
 	_ASM_EXTABLE(1b, 4b)						\
 	_ASM_EXTABLE(2b, 4b)						\
-	: "=&r" (ret), "=&r" (oldval), "+Q" (*uaddr), "=&r" (tmp)	\
-	: "r" (oparg), "Ir" (-EFAULT)					\
+	: "=&r" (ret), "=&r" (oldval), "+Q" (*uaddr), "=&r" (tmp),	\
+	  "+r" (loops)							\
+	: "r" (oparg), "Ir" (-EFAULT), "Ir" (-EAGAIN)			\
 	: "memory");							\
 	uaccess_disable();						\
 } while (0)
@@ -57,23 +65,23 @@ arch_futex_atomic_op_inuser(int op, int oparg, int *oval, u32 __user *_uaddr)
 
 	switch (op) {
 	case FUTEX_OP_SET:
-		__futex_atomic_op("mov	%w0, %w4",
+		__futex_atomic_op("mov	%w3, %w5",
 				  ret, oldval, uaddr, tmp, oparg);
 		break;
 	case FUTEX_OP_ADD:
-		__futex_atomic_op("add	%w0, %w1, %w4",
+		__futex_atomic_op("add	%w3, %w1, %w5",
 				  ret, oldval, uaddr, tmp, oparg);
 		break;
 	case FUTEX_OP_OR:
-		__futex_atomic_op("orr	%w0, %w1, %w4",
+		__futex_atomic_op("orr	%w3, %w1, %w5",
 				  ret, oldval, uaddr, tmp, oparg);
 		break;
 	case FUTEX_OP_ANDN:
-		__futex_atomic_op("and	%w0, %w1, %w4",
+		__futex_atomic_op("and	%w3, %w1, %w5",
 				  ret, oldval, uaddr, tmp, ~oparg);
 		break;
 	case FUTEX_OP_XOR:
-		__futex_atomic_op("eor	%w0, %w1, %w4",
+		__futex_atomic_op("eor	%w3, %w1, %w5",
 				  ret, oldval, uaddr, tmp, oparg);
 		break;
 	default:
@@ -93,6 +101,7 @@ futex_atomic_cmpxchg_inatomic(u32 *uval, u32 __user *_uaddr,
 			      u32 oldval, u32 newval)
 {
 	int ret = 0;
+	unsigned int loops = FUTEX_MAX_LOOPS;
 	u32 val, tmp;
 	u32 __user *uaddr;
 
@@ -104,24 +113,30 @@ futex_atomic_cmpxchg_inatomic(u32 *uval, u32 __user *_uaddr,
 	asm volatile("// futex_atomic_cmpxchg_inatomic\n"
 "	prfm	pstl1strm, %2\n"
 "1:	ldxr	%w1, %2\n"
-"	sub	%w3, %w1, %w4\n"
-"	cbnz	%w3, 3f\n"
-"2:	stlxr	%w3, %w5, %2\n"
-"	cbnz	%w3, 1b\n"
-"	dmb	ish\n"
+"	sub	%w3, %w1, %w5\n"
+"	cbnz	%w3, 4f\n"
+"2:	stlxr	%w3, %w6, %2\n"
+"	cbz	%w3, 3f\n"
+"	sub	%w4, %w4, %w3\n"
+"	cbnz	%w4, 1b\n"
+"	mov	%w0, %w8\n"
 "3:\n"
+"	dmb	ish\n"
+"4:\n"
 "	.pushsection .fixup,\"ax\"\n"
-"4:	mov	%w0, %w6\n"
-"	b	3b\n"
+"5:	mov	%w0, %w7\n"
+"	b	4b\n"
 "	.popsection\n"
-	_ASM_EXTABLE(1b, 4b)
-	_ASM_EXTABLE(2b, 4b)
-	: "+r" (ret), "=&r" (val), "+Q" (*uaddr), "=&r" (tmp)
-	: "r" (oldval), "r" (newval), "Ir" (-EFAULT)
+	_ASM_EXTABLE(1b, 5b)
+	_ASM_EXTABLE(2b, 5b)
+	: "+r" (ret), "=&r" (val), "+Q" (*uaddr), "=&r" (tmp), "+r" (loops)
+	: "r" (oldval), "r" (newval), "Ir" (-EFAULT), "Ir" (-EAGAIN)
 	: "memory");
 	uaccess_disable();
 
-	*uval = val;
+	if (!ret)
+		*uval = val;
+
 	return ret;
 }
 
diff --git a/arch/arm64/include/asm/hwcap.h b/arch/arm64/include/asm/hwcap.h
index 400b80b49595..b4bfb6672168 100644
--- a/arch/arm64/include/asm/hwcap.h
+++ b/arch/arm64/include/asm/hwcap.h
@@ -17,6 +17,7 @@
 #define __ASM_HWCAP_H
 
 #include <uapi/asm/hwcap.h>
+#include <asm/cpufeature.h>
 
 #define COMPAT_HWCAP_HALF	(1 << 1)
 #define COMPAT_HWCAP_THUMB	(1 << 2)
@@ -40,11 +41,67 @@
 #define COMPAT_HWCAP2_CRC32	(1 << 4)
 
 #ifndef __ASSEMBLY__
+#include <linux/log2.h>
+
+/*
+ * For userspace we represent hwcaps as a collection of HWCAP{,2}_x bitfields
+ * as described in uapi/asm/hwcap.h. For the kernel we represent hwcaps as
+ * natural numbers (in a single range of size MAX_CPU_FEATURES) defined here
+ * with prefix KERNEL_HWCAP_ mapped to their HWCAP{,2}_x counterpart.
+ *
+ * Hwcaps should be set and tested within the kernel via the
+ * cpu_{set,have}_named_feature(feature) where feature is the unique suffix
+ * of KERNEL_HWCAP_{feature}.
+ */
+#define __khwcap_feature(x)		const_ilog2(HWCAP_ ## x)
+#define KERNEL_HWCAP_FP			__khwcap_feature(FP)
+#define KERNEL_HWCAP_ASIMD		__khwcap_feature(ASIMD)
+#define KERNEL_HWCAP_EVTSTRM		__khwcap_feature(EVTSTRM)
+#define KERNEL_HWCAP_AES		__khwcap_feature(AES)
+#define KERNEL_HWCAP_PMULL		__khwcap_feature(PMULL)
+#define KERNEL_HWCAP_SHA1		__khwcap_feature(SHA1)
+#define KERNEL_HWCAP_SHA2		__khwcap_feature(SHA2)
+#define KERNEL_HWCAP_CRC32		__khwcap_feature(CRC32)
+#define KERNEL_HWCAP_ATOMICS		__khwcap_feature(ATOMICS)
+#define KERNEL_HWCAP_FPHP		__khwcap_feature(FPHP)
+#define KERNEL_HWCAP_ASIMDHP		__khwcap_feature(ASIMDHP)
+#define KERNEL_HWCAP_CPUID		__khwcap_feature(CPUID)
+#define KERNEL_HWCAP_ASIMDRDM		__khwcap_feature(ASIMDRDM)
+#define KERNEL_HWCAP_JSCVT		__khwcap_feature(JSCVT)
+#define KERNEL_HWCAP_FCMA		__khwcap_feature(FCMA)
+#define KERNEL_HWCAP_LRCPC		__khwcap_feature(LRCPC)
+#define KERNEL_HWCAP_DCPOP		__khwcap_feature(DCPOP)
+#define KERNEL_HWCAP_SHA3		__khwcap_feature(SHA3)
+#define KERNEL_HWCAP_SM3		__khwcap_feature(SM3)
+#define KERNEL_HWCAP_SM4		__khwcap_feature(SM4)
+#define KERNEL_HWCAP_ASIMDDP		__khwcap_feature(ASIMDDP)
+#define KERNEL_HWCAP_SHA512		__khwcap_feature(SHA512)
+#define KERNEL_HWCAP_SVE		__khwcap_feature(SVE)
+#define KERNEL_HWCAP_ASIMDFHM		__khwcap_feature(ASIMDFHM)
+#define KERNEL_HWCAP_DIT		__khwcap_feature(DIT)
+#define KERNEL_HWCAP_USCAT		__khwcap_feature(USCAT)
+#define KERNEL_HWCAP_ILRCPC		__khwcap_feature(ILRCPC)
+#define KERNEL_HWCAP_FLAGM		__khwcap_feature(FLAGM)
+#define KERNEL_HWCAP_SSBS		__khwcap_feature(SSBS)
+#define KERNEL_HWCAP_SB			__khwcap_feature(SB)
+#define KERNEL_HWCAP_PACA		__khwcap_feature(PACA)
+#define KERNEL_HWCAP_PACG		__khwcap_feature(PACG)
+
+#define __khwcap2_feature(x)		(const_ilog2(HWCAP2_ ## x) + 32)
+#define KERNEL_HWCAP_DCPODP		__khwcap2_feature(DCPODP)
+#define KERNEL_HWCAP_SVE2		__khwcap2_feature(SVE2)
+#define KERNEL_HWCAP_SVEAES		__khwcap2_feature(SVEAES)
+#define KERNEL_HWCAP_SVEPMULL		__khwcap2_feature(SVEPMULL)
+#define KERNEL_HWCAP_SVEBITPERM		__khwcap2_feature(SVEBITPERM)
+#define KERNEL_HWCAP_SVESHA3		__khwcap2_feature(SVESHA3)
+#define KERNEL_HWCAP_SVESM4		__khwcap2_feature(SVESM4)
+
 /*
  * This yields a mask that user programs can use to figure out what
  * instruction set this cpu supports.
  */
-#define ELF_HWCAP		(elf_hwcap)
+#define ELF_HWCAP		cpu_get_elf_hwcap()
+#define ELF_HWCAP2		cpu_get_elf_hwcap2()
 
 #ifdef CONFIG_COMPAT
 #define COMPAT_ELF_HWCAP	(compat_elf_hwcap)
@@ -60,6 +117,5 @@ enum {
 #endif
 };
 
-extern unsigned long elf_hwcap;
 #endif
 #endif
diff --git a/arch/arm64/include/asm/io.h b/arch/arm64/include/asm/io.h
index 8bb7210ac286..b807cb9b517d 100644
--- a/arch/arm64/include/asm/io.h
+++ b/arch/arm64/include/asm/io.h
@@ -124,8 +124,6 @@ static inline u64 __raw_readq(const volatile void __iomem *addr)
 #define __io_par(v)		__iormb(v)
 #define __iowmb()		wmb()
 
-#define mmiowb()		do { } while (0)
-
 /*
  * Relaxed I/O memory access primitives. These follow the Device memory
  * ordering rules but do not guarantee any ordering relative to Normal memory
diff --git a/arch/arm64/include/asm/irqflags.h b/arch/arm64/include/asm/irqflags.h
index 43d8366c1e87..629963189085 100644
--- a/arch/arm64/include/asm/irqflags.h
+++ b/arch/arm64/include/asm/irqflags.h
@@ -43,7 +43,7 @@ static inline void arch_local_irq_enable(void)
 	asm volatile(ALTERNATIVE(
 		"msr	daifclr, #2		// arch_local_irq_enable\n"
 		"nop",
-		"msr_s  " __stringify(SYS_ICC_PMR_EL1) ",%0\n"
+		__msr_s(SYS_ICC_PMR_EL1, "%0")
 		"dsb	sy",
 		ARM64_HAS_IRQ_PRIO_MASKING)
 		:
@@ -55,7 +55,7 @@ static inline void arch_local_irq_disable(void)
 {
 	asm volatile(ALTERNATIVE(
 		"msr	daifset, #2		// arch_local_irq_disable",
-		"msr_s  " __stringify(SYS_ICC_PMR_EL1) ", %0",
+		__msr_s(SYS_ICC_PMR_EL1, "%0"),
 		ARM64_HAS_IRQ_PRIO_MASKING)
 		:
 		: "r" ((unsigned long) GIC_PRIO_IRQOFF)
@@ -86,7 +86,7 @@ static inline unsigned long arch_local_save_flags(void)
 			"mov	%0, %1\n"
 			"nop\n"
 			"nop",
-			"mrs_s	%0, " __stringify(SYS_ICC_PMR_EL1) "\n"
+			__mrs_s("%0", SYS_ICC_PMR_EL1)
 			"ands	%1, %1, " __stringify(PSR_I_BIT) "\n"
 			"csel	%0, %0, %2, eq",
 			ARM64_HAS_IRQ_PRIO_MASKING)
@@ -116,7 +116,7 @@ static inline void arch_local_irq_restore(unsigned long flags)
 	asm volatile(ALTERNATIVE(
 			"msr	daif, %0\n"
 			"nop",
-			"msr_s	" __stringify(SYS_ICC_PMR_EL1) ", %0\n"
+			__msr_s(SYS_ICC_PMR_EL1, "%0")
 			"dsb	sy",
 			ARM64_HAS_IRQ_PRIO_MASKING)
 		: "+r" (flags)
diff --git a/arch/arm64/include/asm/kprobes.h b/arch/arm64/include/asm/kprobes.h
index d5a44cf859e9..21721fbf44e7 100644
--- a/arch/arm64/include/asm/kprobes.h
+++ b/arch/arm64/include/asm/kprobes.h
@@ -54,8 +54,6 @@ void arch_remove_kprobe(struct kprobe *);
 int kprobe_fault_handler(struct pt_regs *regs, unsigned int fsr);
 int kprobe_exceptions_notify(struct notifier_block *self,
 			     unsigned long val, void *data);
-int kprobe_breakpoint_handler(struct pt_regs *regs, unsigned int esr);
-int kprobe_single_step_handler(struct pt_regs *regs, unsigned int esr);
 void kretprobe_trampoline(void);
 void __kprobes *trampoline_probe_handler(struct pt_regs *regs);
 
diff --git a/arch/arm64/include/asm/kvm_hyp.h b/arch/arm64/include/asm/kvm_hyp.h
index 4da765f2cca5..c3060833b7a5 100644
--- a/arch/arm64/include/asm/kvm_hyp.h
+++ b/arch/arm64/include/asm/kvm_hyp.h
@@ -30,7 +30,7 @@
 	({								\
 		u64 reg;						\
 		asm volatile(ALTERNATIVE("mrs %0, " __stringify(r##nvh),\
-					 "mrs_s %0, " __stringify(r##vh),\
+					 __mrs_s("%0", r##vh),		\
 					 ARM64_HAS_VIRT_HOST_EXTN)	\
 			     : "=r" (reg));				\
 		reg;							\
@@ -40,7 +40,7 @@
 	do {								\
 		u64 __val = (u64)(v);					\
 		asm volatile(ALTERNATIVE("msr " __stringify(r##nvh) ", %x0",\
-					 "msr_s " __stringify(r##vh) ", %x0",\
+					 __msr_s(r##vh, "%x0"),		\
 					 ARM64_HAS_VIRT_HOST_EXTN)	\
 					 : : "rZ" (__val));		\
 	} while (0)
diff --git a/arch/arm64/include/asm/kvm_mmu.h b/arch/arm64/include/asm/kvm_mmu.h
index b0742a16c6c9..ebeefcf835e8 100644
--- a/arch/arm64/include/asm/kvm_mmu.h
+++ b/arch/arm64/include/asm/kvm_mmu.h
@@ -445,6 +445,17 @@ static inline int kvm_read_guest_lock(struct kvm *kvm,
 	return ret;
 }
 
+static inline int kvm_write_guest_lock(struct kvm *kvm, gpa_t gpa,
+				       const void *data, unsigned long len)
+{
+	int srcu_idx = srcu_read_lock(&kvm->srcu);
+	int ret = kvm_write_guest(kvm, gpa, data, len);
+
+	srcu_read_unlock(&kvm->srcu, srcu_idx);
+
+	return ret;
+}
+
 #ifdef CONFIG_KVM_INDIRECT_VECTORS
 /*
  * EL2 vectors can be mapped and rerouted in a number of ways,
diff --git a/arch/arm64/include/asm/memory.h b/arch/arm64/include/asm/memory.h
index 290195168bb3..2cb8248fa2c8 100644
--- a/arch/arm64/include/asm/memory.h
+++ b/arch/arm64/include/asm/memory.h
@@ -302,7 +302,7 @@ static inline void *phys_to_virt(phys_addr_t x)
  */
 #define ARCH_PFN_OFFSET		((unsigned long)PHYS_PFN_OFFSET)
 
-#ifndef CONFIG_SPARSEMEM_VMEMMAP
+#if !defined(CONFIG_SPARSEMEM_VMEMMAP) || defined(CONFIG_DEBUG_VIRTUAL)
 #define virt_to_page(kaddr)	pfn_to_page(__pa(kaddr) >> PAGE_SHIFT)
 #define _virt_addr_valid(kaddr)	pfn_valid(__pa(kaddr) >> PAGE_SHIFT)
 #else
diff --git a/arch/arm64/include/asm/module.h b/arch/arm64/include/asm/module.h
index 905e1bb0e7bd..cd9f4e9d04d3 100644
--- a/arch/arm64/include/asm/module.h
+++ b/arch/arm64/include/asm/module.h
@@ -73,4 +73,9 @@ static inline bool is_forbidden_offset_for_adrp(void *place)
 struct plt_entry get_plt_entry(u64 dst, void *pc);
 bool plt_entries_equal(const struct plt_entry *a, const struct plt_entry *b);
 
+static inline bool plt_entry_is_initialized(const struct plt_entry *e)
+{
+	return e->adrp || e->add || e->br;
+}
+
 #endif /* __ASM_MODULE_H */
diff --git a/arch/arm64/include/asm/pgalloc.h b/arch/arm64/include/asm/pgalloc.h
index 52fa47c73bf0..dabba4b2c61f 100644
--- a/arch/arm64/include/asm/pgalloc.h
+++ b/arch/arm64/include/asm/pgalloc.h
@@ -33,12 +33,22 @@
 
 static inline pmd_t *pmd_alloc_one(struct mm_struct *mm, unsigned long addr)
 {
-	return (pmd_t *)__get_free_page(PGALLOC_GFP);
+	struct page *page;
+
+	page = alloc_page(PGALLOC_GFP);
+	if (!page)
+		return NULL;
+	if (!pgtable_pmd_page_ctor(page)) {
+		__free_page(page);
+		return NULL;
+	}
+	return page_address(page);
 }
 
 static inline void pmd_free(struct mm_struct *mm, pmd_t *pmdp)
 {
 	BUG_ON((unsigned long)pmdp & (PAGE_SIZE-1));
+	pgtable_pmd_page_dtor(virt_to_page(pmdp));
 	free_page((unsigned long)pmdp);
 }
 
diff --git a/arch/arm64/include/asm/pgtable.h b/arch/arm64/include/asm/pgtable.h
index de70c1eabf33..2c41b04708fe 100644
--- a/arch/arm64/include/asm/pgtable.h
+++ b/arch/arm64/include/asm/pgtable.h
@@ -478,6 +478,8 @@ static inline phys_addr_t pmd_page_paddr(pmd_t pmd)
 	return __pmd_to_phys(pmd);
 }
 
+static inline void pte_unmap(pte_t *pte) { }
+
 /* Find an entry in the third-level page table. */
 #define pte_index(addr)		(((addr) >> PAGE_SHIFT) & (PTRS_PER_PTE - 1))
 
@@ -485,9 +487,6 @@ static inline phys_addr_t pmd_page_paddr(pmd_t pmd)
 #define pte_offset_kernel(dir,addr)	((pte_t *)__va(pte_offset_phys((dir), (addr))))
 
 #define pte_offset_map(dir,addr)	pte_offset_kernel((dir), (addr))
-#define pte_offset_map_nested(dir,addr)	pte_offset_kernel((dir), (addr))
-#define pte_unmap(pte)			do { } while (0)
-#define pte_unmap_nested(pte)		do { } while (0)
 
 #define pte_set_fixmap(addr)		((pte_t *)set_fixmap_offset(FIX_PTE, addr))
 #define pte_set_fixmap_offset(pmd, addr)	pte_set_fixmap(pte_offset_phys(pmd, addr))
diff --git a/arch/arm64/include/asm/pointer_auth.h b/arch/arm64/include/asm/pointer_auth.h
index 15d49515efdd..d328540cb85e 100644
--- a/arch/arm64/include/asm/pointer_auth.h
+++ b/arch/arm64/include/asm/pointer_auth.h
@@ -1,4 +1,4 @@
-// SPDX-License-Identifier: GPL-2.0
+/* SPDX-License-Identifier: GPL-2.0 */
 #ifndef __ASM_POINTER_AUTH_H
 #define __ASM_POINTER_AUTH_H
 
diff --git a/arch/arm64/include/asm/processor.h b/arch/arm64/include/asm/processor.h
index 5d9ce62bdebd..fcd0e691b1ea 100644
--- a/arch/arm64/include/asm/processor.h
+++ b/arch/arm64/include/asm/processor.h
@@ -57,7 +57,15 @@
 #define TASK_SIZE_64		(UL(1) << vabits_user)
 
 #ifdef CONFIG_COMPAT
+#if defined(CONFIG_ARM64_64K_PAGES) && defined(CONFIG_KUSER_HELPERS)
+/*
+ * With CONFIG_ARM64_64K_PAGES enabled, the last page is occupied
+ * by the compat vectors page.
+ */
 #define TASK_SIZE_32		UL(0x100000000)
+#else
+#define TASK_SIZE_32		(UL(0x100000000) - PAGE_SIZE)
+#endif /* CONFIG_ARM64_64K_PAGES */
 #define TASK_SIZE		(test_thread_flag(TIF_32BIT) ? \
 				TASK_SIZE_32 : TASK_SIZE_64)
 #define TASK_SIZE_OF(tsk)	(test_tsk_thread_flag(tsk, TIF_32BIT) ? \
diff --git a/arch/arm64/include/asm/ptrace.h b/arch/arm64/include/asm/ptrace.h
index ec60174c8c18..b2de32939ada 100644
--- a/arch/arm64/include/asm/ptrace.h
+++ b/arch/arm64/include/asm/ptrace.h
@@ -305,6 +305,28 @@ static inline unsigned long regs_return_value(struct pt_regs *regs)
 	return regs->regs[0];
 }
 
+/**
+ * regs_get_kernel_argument() - get Nth function argument in kernel
+ * @regs:	pt_regs of that context
+ * @n:		function argument number (start from 0)
+ *
+ * regs_get_argument() returns @n th argument of the function call.
+ *
+ * Note that this chooses the most likely register mapping. In very rare
+ * cases this may not return correct data, for example, if one of the
+ * function parameters is 16 bytes or bigger. In such cases, we cannot
+ * get access the parameter correctly and the register assignment of
+ * subsequent parameters will be shifted.
+ */
+static inline unsigned long regs_get_kernel_argument(struct pt_regs *regs,
+						     unsigned int n)
+{
+#define NR_REG_ARGUMENTS 8
+	if (n < NR_REG_ARGUMENTS)
+		return pt_regs_read_reg(regs, n);
+	return 0;
+}
+
 /* We must avoid circular header include via sched.h */
 struct task_struct;
 int valid_user_regs(struct user_pt_regs *regs, struct task_struct *task);
diff --git a/arch/arm64/include/asm/sdei.h b/arch/arm64/include/asm/sdei.h
index ffe47d766c25..63e0b92a5fbb 100644
--- a/arch/arm64/include/asm/sdei.h
+++ b/arch/arm64/include/asm/sdei.h
@@ -1,4 +1,4 @@
-// SPDX-License-Identifier: GPL-2.0
+/* SPDX-License-Identifier: GPL-2.0 */
 // Copyright (C) 2017 Arm Ltd.
 #ifndef __ASM_SDEI_H
 #define __ASM_SDEI_H
diff --git a/arch/arm64/include/asm/signal32.h b/arch/arm64/include/asm/signal32.h
index 81abea0b7650..58e288aaf0ba 100644
--- a/arch/arm64/include/asm/signal32.h
+++ b/arch/arm64/include/asm/signal32.h
@@ -20,8 +20,6 @@
 #ifdef CONFIG_COMPAT
 #include <linux/compat.h>
 
-#define AARCH32_KERN_SIGRET_CODE_OFFSET	0x500
-
 int compat_setup_frame(int usig, struct ksignal *ksig, sigset_t *set,
 		       struct pt_regs *regs);
 int compat_setup_rt_frame(int usig, struct ksignal *ksig, sigset_t *set,
diff --git a/arch/arm64/include/asm/stage2_pgtable.h b/arch/arm64/include/asm/stage2_pgtable.h
index 5412fa40825e..915809e4ac32 100644
--- a/arch/arm64/include/asm/stage2_pgtable.h
+++ b/arch/arm64/include/asm/stage2_pgtable.h
@@ -119,7 +119,7 @@ static inline pud_t *stage2_pud_offset(struct kvm *kvm,
 static inline void stage2_pud_free(struct kvm *kvm, pud_t *pud)
 {
 	if (kvm_stage2_has_pud(kvm))
-		pud_free(NULL, pud);
+		free_page((unsigned long)pud);
 }
 
 static inline bool stage2_pud_table_empty(struct kvm *kvm, pud_t *pudp)
@@ -192,7 +192,7 @@ static inline pmd_t *stage2_pmd_offset(struct kvm *kvm,
 static inline void stage2_pmd_free(struct kvm *kvm, pmd_t *pmd)
 {
 	if (kvm_stage2_has_pmd(kvm))
-		pmd_free(NULL, pmd);
+		free_page((unsigned long)pmd);
 }
 
 static inline bool stage2_pud_huge(struct kvm *kvm, pud_t pud)
diff --git a/arch/arm64/include/asm/syscall.h b/arch/arm64/include/asm/syscall.h
index ad8be16a39c9..a179df3674a1 100644
--- a/arch/arm64/include/asm/syscall.h
+++ b/arch/arm64/include/asm/syscall.h
@@ -65,52 +65,22 @@ static inline void syscall_set_return_value(struct task_struct *task,
 
 static inline void syscall_get_arguments(struct task_struct *task,
 					 struct pt_regs *regs,
-					 unsigned int i, unsigned int n,
 					 unsigned long *args)
 {
-	if (n == 0)
-		return;
-
-	if (i + n > SYSCALL_MAX_ARGS) {
-		unsigned long *args_bad = args + SYSCALL_MAX_ARGS - i;
-		unsigned int n_bad = n + i - SYSCALL_MAX_ARGS;
-		pr_warning("%s called with max args %d, handling only %d\n",
-			   __func__, i + n, SYSCALL_MAX_ARGS);
-		memset(args_bad, 0, n_bad * sizeof(args[0]));
-	}
-
-	if (i == 0) {
-		args[0] = regs->orig_x0;
-		args++;
-		i++;
-		n--;
-	}
-
-	memcpy(args, &regs->regs[i], n * sizeof(args[0]));
+	args[0] = regs->orig_x0;
+	args++;
+
+	memcpy(args, &regs->regs[1], 5 * sizeof(args[0]));
 }
 
 static inline void syscall_set_arguments(struct task_struct *task,
 					 struct pt_regs *regs,
-					 unsigned int i, unsigned int n,
 					 const unsigned long *args)
 {
-	if (n == 0)
-		return;
-
-	if (i + n > SYSCALL_MAX_ARGS) {
-		pr_warning("%s called with max args %d, handling only %d\n",
-			   __func__, i + n, SYSCALL_MAX_ARGS);
-		n = SYSCALL_MAX_ARGS - i;
-	}
-
-	if (i == 0) {
-		regs->orig_x0 = args[0];
-		args++;
-		i++;
-		n--;
-	}
-
-	memcpy(&regs->regs[i], args, n * sizeof(args[0]));
+	regs->orig_x0 = args[0];
+	args++;
+
+	memcpy(&regs->regs[1], args, 5 * sizeof(args[0]));
 }
 
 /*
diff --git a/arch/arm64/include/asm/sysreg.h b/arch/arm64/include/asm/sysreg.h
index 5b267dec6194..3f7b917e8f3a 100644
--- a/arch/arm64/include/asm/sysreg.h
+++ b/arch/arm64/include/asm/sysreg.h
@@ -606,6 +606,20 @@
 #define ID_AA64PFR1_SSBS_PSTATE_ONLY	1
 #define ID_AA64PFR1_SSBS_PSTATE_INSNS	2
 
+/* id_aa64zfr0 */
+#define ID_AA64ZFR0_SM4_SHIFT		40
+#define ID_AA64ZFR0_SHA3_SHIFT		32
+#define ID_AA64ZFR0_BITPERM_SHIFT	16
+#define ID_AA64ZFR0_AES_SHIFT		4
+#define ID_AA64ZFR0_SVEVER_SHIFT	0
+
+#define ID_AA64ZFR0_SM4			0x1
+#define ID_AA64ZFR0_SHA3		0x1
+#define ID_AA64ZFR0_BITPERM		0x1
+#define ID_AA64ZFR0_AES			0x1
+#define ID_AA64ZFR0_AES_PMULL		0x2
+#define ID_AA64ZFR0_SVEVER_SVE2		0x1
+
 /* id_aa64mmfr0 */
 #define ID_AA64MMFR0_TGRAN4_SHIFT	28
 #define ID_AA64MMFR0_TGRAN64_SHIFT	24
@@ -746,20 +760,39 @@
 #include <linux/build_bug.h>
 #include <linux/types.h>
 
-asm(
-"	.irp	num,0,1,2,3,4,5,6,7,8,9,10,11,12,13,14,15,16,17,18,19,20,21,22,23,24,25,26,27,28,29,30\n"
-"	.equ	.L__reg_num_x\\num, \\num\n"
-"	.endr\n"
+#define __DEFINE_MRS_MSR_S_REGNUM				\
+"	.irp	num,0,1,2,3,4,5,6,7,8,9,10,11,12,13,14,15,16,17,18,19,20,21,22,23,24,25,26,27,28,29,30\n" \
+"	.equ	.L__reg_num_x\\num, \\num\n"			\
+"	.endr\n"						\
 "	.equ	.L__reg_num_xzr, 31\n"
-"\n"
-"	.macro	mrs_s, rt, sreg\n"
-	__emit_inst(0xd5200000|(\\sreg)|(.L__reg_num_\\rt))
+
+#define DEFINE_MRS_S						\
+	__DEFINE_MRS_MSR_S_REGNUM				\
+"	.macro	mrs_s, rt, sreg\n"				\
+	__emit_inst(0xd5200000|(\\sreg)|(.L__reg_num_\\rt))	\
 "	.endm\n"
-"\n"
-"	.macro	msr_s, sreg, rt\n"
-	__emit_inst(0xd5000000|(\\sreg)|(.L__reg_num_\\rt))
+
+#define DEFINE_MSR_S						\
+	__DEFINE_MRS_MSR_S_REGNUM				\
+"	.macro	msr_s, sreg, rt\n"				\
+	__emit_inst(0xd5000000|(\\sreg)|(.L__reg_num_\\rt))	\
 "	.endm\n"
-);
+
+#define UNDEFINE_MRS_S						\
+"	.purgem	mrs_s\n"
+
+#define UNDEFINE_MSR_S						\
+"	.purgem	msr_s\n"
+
+#define __mrs_s(v, r)						\
+	DEFINE_MRS_S						\
+"	mrs_s " v ", " __stringify(r) "\n"			\
+	UNDEFINE_MRS_S
+
+#define __msr_s(r, v)						\
+	DEFINE_MSR_S						\
+"	msr_s " __stringify(r) ", " v "\n"			\
+	UNDEFINE_MSR_S
 
 /*
  * Unlike read_cpuid, calls to read_sysreg are never expected to be
@@ -787,13 +820,13 @@ asm(
  */
 #define read_sysreg_s(r) ({						\
 	u64 __val;							\
-	asm volatile("mrs_s %0, " __stringify(r) : "=r" (__val));	\
+	asm volatile(__mrs_s("%0", r) : "=r" (__val));			\
 	__val;								\
 })
 
 #define write_sysreg_s(v, r) do {					\
 	u64 __val = (u64)(v);						\
-	asm volatile("msr_s " __stringify(r) ", %x0" : : "rZ" (__val));	\
+	asm volatile(__msr_s(r, "%x0") : : "rZ" (__val));		\
 } while (0)
 
 /*
diff --git a/arch/arm64/include/asm/system_misc.h b/arch/arm64/include/asm/system_misc.h
index 32693f34f431..fca95424e873 100644
--- a/arch/arm64/include/asm/system_misc.h
+++ b/arch/arm64/include/asm/system_misc.h
@@ -41,7 +41,6 @@ void hook_debug_fault_code(int nr, int (*fn)(unsigned long, unsigned int,
 			   int sig, int code, const char *name);
 
 struct mm_struct;
-extern void show_pte(unsigned long addr);
 extern void __show_regs(struct pt_regs *);
 
 extern void (*arm_pm_restart)(enum reboot_mode reboot_mode, const char *cmd);
diff --git a/arch/arm64/include/asm/tlb.h b/arch/arm64/include/asm/tlb.h
index 106fdc951b6e..a287189ca8b4 100644
--- a/arch/arm64/include/asm/tlb.h
+++ b/arch/arm64/include/asm/tlb.h
@@ -27,6 +27,7 @@ static inline void __tlb_remove_table(void *_table)
 	free_page_and_swap_cache((struct page *)_table);
 }
 
+#define tlb_flush tlb_flush
 static void tlb_flush(struct mmu_gather *tlb);
 
 #include <asm-generic/tlb.h>
@@ -62,7 +63,10 @@ static inline void __pte_free_tlb(struct mmu_gather *tlb, pgtable_t pte,
 static inline void __pmd_free_tlb(struct mmu_gather *tlb, pmd_t *pmdp,
 				  unsigned long addr)
 {
-	tlb_remove_table(tlb, virt_to_page(pmdp));
+	struct page *page = virt_to_page(pmdp);
+
+	pgtable_pmd_page_dtor(page);
+	tlb_remove_table(tlb, page);
 }
 #endif
 
diff --git a/arch/arm64/include/asm/unistd.h b/arch/arm64/include/asm/unistd.h
index d1dd93436e1e..f2a83ff6b73c 100644
--- a/arch/arm64/include/asm/unistd.h
+++ b/arch/arm64/include/asm/unistd.h
@@ -44,7 +44,7 @@
 #define __ARM_NR_compat_set_tls		(__ARM_NR_COMPAT_BASE + 5)
 #define __ARM_NR_COMPAT_END		(__ARM_NR_COMPAT_BASE + 0x800)
 
-#define __NR_compat_syscalls		424
+#define __NR_compat_syscalls		428
 #endif
 
 #define __ARCH_WANT_SYS_CLONE
diff --git a/arch/arm64/include/asm/unistd32.h b/arch/arm64/include/asm/unistd32.h
index 5590f2623690..23f1a44acada 100644
--- a/arch/arm64/include/asm/unistd32.h
+++ b/arch/arm64/include/asm/unistd32.h
@@ -866,6 +866,14 @@ __SYSCALL(__NR_rt_sigtimedwait_time64, compat_sys_rt_sigtimedwait_time64)
 __SYSCALL(__NR_futex_time64, sys_futex)
 #define __NR_sched_rr_get_interval_time64 423
 __SYSCALL(__NR_sched_rr_get_interval_time64, sys_sched_rr_get_interval)
+#define __NR_pidfd_send_signal 424
+__SYSCALL(__NR_pidfd_send_signal, sys_pidfd_send_signal)
+#define __NR_io_uring_setup 425
+__SYSCALL(__NR_io_uring_setup, sys_io_uring_setup)
+#define __NR_io_uring_enter 426
+__SYSCALL(__NR_io_uring_enter, sys_io_uring_enter)
+#define __NR_io_uring_register 427
+__SYSCALL(__NR_io_uring_register, sys_io_uring_register)
 
 /*
  * Please add new compat syscalls above this comment and update
diff --git a/arch/arm64/include/asm/vdso_datapage.h b/arch/arm64/include/asm/vdso_datapage.h
index 2b9a63771eda..f89263c8e11a 100644
--- a/arch/arm64/include/asm/vdso_datapage.h
+++ b/arch/arm64/include/asm/vdso_datapage.h
@@ -38,6 +38,7 @@ struct vdso_data {
 	__u32 tz_minuteswest;	/* Whacky timezone stuff */
 	__u32 tz_dsttime;
 	__u32 use_syscall;
+	__u32 hrtimer_res;
 };
 
 #endif /* !__ASSEMBLY__ */
diff --git a/arch/arm64/include/asm/vmap_stack.h b/arch/arm64/include/asm/vmap_stack.h
index 0b5ec6e08c10..0a12115d9638 100644
--- a/arch/arm64/include/asm/vmap_stack.h
+++ b/arch/arm64/include/asm/vmap_stack.h
@@ -1,4 +1,4 @@
-// SPDX-License-Identifier: GPL-2.0
+/* SPDX-License-Identifier: GPL-2.0 */
 // Copyright (C) 2017 Arm Ltd.
 #ifndef __ASM_VMAP_STACK_H
 #define __ASM_VMAP_STACK_H
diff --git a/arch/arm64/include/uapi/asm/hwcap.h b/arch/arm64/include/uapi/asm/hwcap.h
index 5f0750c2199c..1a772b162191 100644
--- a/arch/arm64/include/uapi/asm/hwcap.h
+++ b/arch/arm64/include/uapi/asm/hwcap.h
@@ -18,7 +18,7 @@
 #define _UAPI__ASM_HWCAP_H
 
 /*
- * HWCAP flags - for elf_hwcap (in kernel) and AT_HWCAP
+ * HWCAP flags - for AT_HWCAP
  */
 #define HWCAP_FP		(1 << 0)
 #define HWCAP_ASIMD		(1 << 1)
@@ -53,4 +53,15 @@
 #define HWCAP_PACA		(1 << 30)
 #define HWCAP_PACG		(1UL << 31)
 
+/*
+ * HWCAP2 flags - for AT_HWCAP2
+ */
+#define HWCAP2_DCPODP		(1 << 0)
+#define HWCAP2_SVE2		(1 << 1)
+#define HWCAP2_SVEAES		(1 << 2)
+#define HWCAP2_SVEPMULL		(1 << 3)
+#define HWCAP2_SVEBITPERM	(1 << 4)
+#define HWCAP2_SVESHA3		(1 << 5)
+#define HWCAP2_SVESM4		(1 << 6)
+
 #endif /* _UAPI__ASM_HWCAP_H */
diff --git a/arch/arm64/kernel/Makefile b/arch/arm64/kernel/Makefile
index cd434d0719c1..9e7dcb2c31c7 100644
--- a/arch/arm64/kernel/Makefile
+++ b/arch/arm64/kernel/Makefile
@@ -7,9 +7,9 @@ CPPFLAGS_vmlinux.lds	:= -DTEXT_OFFSET=$(TEXT_OFFSET)
 AFLAGS_head.o		:= -DTEXT_OFFSET=$(TEXT_OFFSET)
 CFLAGS_armv8_deprecated.o := -I$(src)
 
-CFLAGS_REMOVE_ftrace.o = -pg
-CFLAGS_REMOVE_insn.o = -pg
-CFLAGS_REMOVE_return_address.o = -pg
+CFLAGS_REMOVE_ftrace.o = $(CC_FLAGS_FTRACE)
+CFLAGS_REMOVE_insn.o = $(CC_FLAGS_FTRACE)
+CFLAGS_REMOVE_return_address.o = $(CC_FLAGS_FTRACE)
 
 # Object file lists.
 obj-y			:= debug-monitors.o entry.o irq.o fpsimd.o		\
@@ -27,8 +27,9 @@ OBJCOPYFLAGS := --prefix-symbols=__efistub_
 $(obj)/%.stub.o: $(obj)/%.o FORCE
 	$(call if_changed,objcopy)
 
-obj-$(CONFIG_COMPAT)			+= sys32.o kuser32.o signal32.o 	\
-					   sys_compat.o
+obj-$(CONFIG_COMPAT)			+= sys32.o signal32.o			\
+					   sigreturn32.o sys_compat.o
+obj-$(CONFIG_KUSER_HELPERS)		+= kuser32.o
 obj-$(CONFIG_FUNCTION_TRACER)		+= ftrace.o entry-ftrace.o
 obj-$(CONFIG_MODULES)			+= module.o
 obj-$(CONFIG_ARM64_MODULE_PLTS)		+= module-plts.o
diff --git a/arch/arm64/kernel/asm-offsets.c b/arch/arm64/kernel/asm-offsets.c
index 7f40dcbdd51d..e10e2a5d9ddc 100644
--- a/arch/arm64/kernel/asm-offsets.c
+++ b/arch/arm64/kernel/asm-offsets.c
@@ -94,7 +94,7 @@ int main(void)
   DEFINE(CLOCK_REALTIME,	CLOCK_REALTIME);
   DEFINE(CLOCK_MONOTONIC,	CLOCK_MONOTONIC);
   DEFINE(CLOCK_MONOTONIC_RAW,	CLOCK_MONOTONIC_RAW);
-  DEFINE(CLOCK_REALTIME_RES,	MONOTONIC_RES_NSEC);
+  DEFINE(CLOCK_REALTIME_RES,	offsetof(struct vdso_data, hrtimer_res));
   DEFINE(CLOCK_REALTIME_COARSE,	CLOCK_REALTIME_COARSE);
   DEFINE(CLOCK_MONOTONIC_COARSE,CLOCK_MONOTONIC_COARSE);
   DEFINE(CLOCK_COARSE_RES,	LOW_RES_NSEC);
diff --git a/arch/arm64/kernel/cpu_errata.c b/arch/arm64/kernel/cpu_errata.c
index 9950bb0cbd52..e88d4e7bdfc7 100644
--- a/arch/arm64/kernel/cpu_errata.c
+++ b/arch/arm64/kernel/cpu_errata.c
@@ -19,6 +19,7 @@
 #include <linux/arm-smccc.h>
 #include <linux/psci.h>
 #include <linux/types.h>
+#include <linux/cpu.h>
 #include <asm/cpu.h>
 #include <asm/cputype.h>
 #include <asm/cpufeature.h>
@@ -109,7 +110,6 @@ cpu_enable_trap_ctr_access(const struct arm64_cpu_capabilities *__unused)
 
 atomic_t arm64_el2_vector_last_slot = ATOMIC_INIT(-1);
 
-#ifdef CONFIG_HARDEN_BRANCH_PREDICTOR
 #include <asm/mmu_context.h>
 #include <asm/cacheflush.h>
 
@@ -131,9 +131,9 @@ static void __copy_hyp_vect_bpi(int slot, const char *hyp_vecs_start,
 	__flush_icache_range((uintptr_t)dst, (uintptr_t)dst + SZ_2K);
 }
 
-static void __install_bp_hardening_cb(bp_hardening_cb_t fn,
-				      const char *hyp_vecs_start,
-				      const char *hyp_vecs_end)
+static void install_bp_hardening_cb(bp_hardening_cb_t fn,
+				    const char *hyp_vecs_start,
+				    const char *hyp_vecs_end)
 {
 	static DEFINE_RAW_SPINLOCK(bp_lock);
 	int cpu, slot = -1;
@@ -169,7 +169,7 @@ static void __install_bp_hardening_cb(bp_hardening_cb_t fn,
 #define __smccc_workaround_1_smc_start		NULL
 #define __smccc_workaround_1_smc_end		NULL
 
-static void __install_bp_hardening_cb(bp_hardening_cb_t fn,
+static void install_bp_hardening_cb(bp_hardening_cb_t fn,
 				      const char *hyp_vecs_start,
 				      const char *hyp_vecs_end)
 {
@@ -177,23 +177,6 @@ static void __install_bp_hardening_cb(bp_hardening_cb_t fn,
 }
 #endif	/* CONFIG_KVM_INDIRECT_VECTORS */
 
-static void  install_bp_hardening_cb(const struct arm64_cpu_capabilities *entry,
-				     bp_hardening_cb_t fn,
-				     const char *hyp_vecs_start,
-				     const char *hyp_vecs_end)
-{
-	u64 pfr0;
-
-	if (!entry->matches(entry, SCOPE_LOCAL_CPU))
-		return;
-
-	pfr0 = read_cpuid(ID_AA64PFR0_EL1);
-	if (cpuid_feature_extract_unsigned_field(pfr0, ID_AA64PFR0_CSV2_SHIFT))
-		return;
-
-	__install_bp_hardening_cb(fn, hyp_vecs_start, hyp_vecs_end);
-}
-
 #include <uapi/linux/psci.h>
 #include <linux/arm-smccc.h>
 #include <linux/psci.h>
@@ -220,60 +203,83 @@ static void qcom_link_stack_sanitization(void)
 		     : "=&r" (tmp));
 }
 
-static void
-enable_smccc_arch_workaround_1(const struct arm64_cpu_capabilities *entry)
+static bool __nospectre_v2;
+static int __init parse_nospectre_v2(char *str)
+{
+	__nospectre_v2 = true;
+	return 0;
+}
+early_param("nospectre_v2", parse_nospectre_v2);
+
+/*
+ * -1: No workaround
+ *  0: No workaround required
+ *  1: Workaround installed
+ */
+static int detect_harden_bp_fw(void)
 {
 	bp_hardening_cb_t cb;
 	void *smccc_start, *smccc_end;
 	struct arm_smccc_res res;
 	u32 midr = read_cpuid_id();
 
-	if (!entry->matches(entry, SCOPE_LOCAL_CPU))
-		return;
-
 	if (psci_ops.smccc_version == SMCCC_VERSION_1_0)
-		return;
+		return -1;
 
 	switch (psci_ops.conduit) {
 	case PSCI_CONDUIT_HVC:
 		arm_smccc_1_1_hvc(ARM_SMCCC_ARCH_FEATURES_FUNC_ID,
 				  ARM_SMCCC_ARCH_WORKAROUND_1, &res);
-		if ((int)res.a0 < 0)
-			return;
-		cb = call_hvc_arch_workaround_1;
-		/* This is a guest, no need to patch KVM vectors */
-		smccc_start = NULL;
-		smccc_end = NULL;
+		switch ((int)res.a0) {
+		case 1:
+			/* Firmware says we're just fine */
+			return 0;
+		case 0:
+			cb = call_hvc_arch_workaround_1;
+			/* This is a guest, no need to patch KVM vectors */
+			smccc_start = NULL;
+			smccc_end = NULL;
+			break;
+		default:
+			return -1;
+		}
 		break;
 
 	case PSCI_CONDUIT_SMC:
 		arm_smccc_1_1_smc(ARM_SMCCC_ARCH_FEATURES_FUNC_ID,
 				  ARM_SMCCC_ARCH_WORKAROUND_1, &res);
-		if ((int)res.a0 < 0)
-			return;
-		cb = call_smc_arch_workaround_1;
-		smccc_start = __smccc_workaround_1_smc_start;
-		smccc_end = __smccc_workaround_1_smc_end;
+		switch ((int)res.a0) {
+		case 1:
+			/* Firmware says we're just fine */
+			return 0;
+		case 0:
+			cb = call_smc_arch_workaround_1;
+			smccc_start = __smccc_workaround_1_smc_start;
+			smccc_end = __smccc_workaround_1_smc_end;
+			break;
+		default:
+			return -1;
+		}
 		break;
 
 	default:
-		return;
+		return -1;
 	}
 
 	if (((midr & MIDR_CPU_MODEL_MASK) == MIDR_QCOM_FALKOR) ||
 	    ((midr & MIDR_CPU_MODEL_MASK) == MIDR_QCOM_FALKOR_V1))
 		cb = qcom_link_stack_sanitization;
 
-	install_bp_hardening_cb(entry, cb, smccc_start, smccc_end);
+	if (IS_ENABLED(CONFIG_HARDEN_BRANCH_PREDICTOR))
+		install_bp_hardening_cb(cb, smccc_start, smccc_end);
 
-	return;
+	return 1;
 }
-#endif	/* CONFIG_HARDEN_BRANCH_PREDICTOR */
 
-#ifdef CONFIG_ARM64_SSBD
 DEFINE_PER_CPU_READ_MOSTLY(u64, arm64_ssbd_callback_required);
 
 int ssbd_state __read_mostly = ARM64_SSBD_KERNEL;
+static bool __ssb_safe = true;
 
 static const struct ssbd_options {
 	const char	*str;
@@ -343,6 +349,11 @@ void __init arm64_enable_wa2_handling(struct alt_instr *alt,
 
 void arm64_set_ssbd_mitigation(bool state)
 {
+	if (!IS_ENABLED(CONFIG_ARM64_SSBD)) {
+		pr_info_once("SSBD disabled by kernel configuration\n");
+		return;
+	}
+
 	if (this_cpu_has_cap(ARM64_SSBS)) {
 		if (state)
 			asm volatile(SET_PSTATE_SSBS(0));
@@ -372,16 +383,28 @@ static bool has_ssbd_mitigation(const struct arm64_cpu_capabilities *entry,
 	struct arm_smccc_res res;
 	bool required = true;
 	s32 val;
+	bool this_cpu_safe = false;
 
 	WARN_ON(scope != SCOPE_LOCAL_CPU || preemptible());
 
+	if (cpu_mitigations_off())
+		ssbd_state = ARM64_SSBD_FORCE_DISABLE;
+
+	/* delay setting __ssb_safe until we get a firmware response */
+	if (is_midr_in_range_list(read_cpuid_id(), entry->midr_range_list))
+		this_cpu_safe = true;
+
 	if (this_cpu_has_cap(ARM64_SSBS)) {
+		if (!this_cpu_safe)
+			__ssb_safe = false;
 		required = false;
 		goto out_printmsg;
 	}
 
 	if (psci_ops.smccc_version == SMCCC_VERSION_1_0) {
 		ssbd_state = ARM64_SSBD_UNKNOWN;
+		if (!this_cpu_safe)
+			__ssb_safe = false;
 		return false;
 	}
 
@@ -398,6 +421,8 @@ static bool has_ssbd_mitigation(const struct arm64_cpu_capabilities *entry,
 
 	default:
 		ssbd_state = ARM64_SSBD_UNKNOWN;
+		if (!this_cpu_safe)
+			__ssb_safe = false;
 		return false;
 	}
 
@@ -406,14 +431,18 @@ static bool has_ssbd_mitigation(const struct arm64_cpu_capabilities *entry,
 	switch (val) {
 	case SMCCC_RET_NOT_SUPPORTED:
 		ssbd_state = ARM64_SSBD_UNKNOWN;
+		if (!this_cpu_safe)
+			__ssb_safe = false;
 		return false;
 
+	/* machines with mixed mitigation requirements must not return this */
 	case SMCCC_RET_NOT_REQUIRED:
 		pr_info_once("%s mitigation not required\n", entry->desc);
 		ssbd_state = ARM64_SSBD_MITIGATED;
 		return false;
 
 	case SMCCC_RET_SUCCESS:
+		__ssb_safe = false;
 		required = true;
 		break;
 
@@ -423,6 +452,8 @@ static bool has_ssbd_mitigation(const struct arm64_cpu_capabilities *entry,
 
 	default:
 		WARN_ON(1);
+		if (!this_cpu_safe)
+			__ssb_safe = false;
 		return false;
 	}
 
@@ -462,7 +493,14 @@ out_printmsg:
 
 	return required;
 }
-#endif	/* CONFIG_ARM64_SSBD */
+
+/* known invulnerable cores */
+static const struct midr_range arm64_ssb_cpus[] = {
+	MIDR_ALL_VERSIONS(MIDR_CORTEX_A35),
+	MIDR_ALL_VERSIONS(MIDR_CORTEX_A53),
+	MIDR_ALL_VERSIONS(MIDR_CORTEX_A55),
+	{},
+};
 
 static void __maybe_unused
 cpu_enable_cache_maint_trap(const struct arm64_cpu_capabilities *__unused)
@@ -507,26 +545,67 @@ cpu_enable_cache_maint_trap(const struct arm64_cpu_capabilities *__unused)
 	.type = ARM64_CPUCAP_LOCAL_CPU_ERRATUM,			\
 	CAP_MIDR_RANGE_LIST(midr_list)
 
-#ifdef CONFIG_HARDEN_BRANCH_PREDICTOR
+/* Track overall mitigation state. We are only mitigated if all cores are ok */
+static bool __hardenbp_enab = true;
+static bool __spectrev2_safe = true;
 
 /*
- * List of CPUs where we need to issue a psci call to
- * harden the branch predictor.
+ * List of CPUs that do not need any Spectre-v2 mitigation at all.
  */
-static const struct midr_range arm64_bp_harden_smccc_cpus[] = {
-	MIDR_ALL_VERSIONS(MIDR_CORTEX_A57),
-	MIDR_ALL_VERSIONS(MIDR_CORTEX_A72),
-	MIDR_ALL_VERSIONS(MIDR_CORTEX_A73),
-	MIDR_ALL_VERSIONS(MIDR_CORTEX_A75),
-	MIDR_ALL_VERSIONS(MIDR_BRCM_VULCAN),
-	MIDR_ALL_VERSIONS(MIDR_CAVIUM_THUNDERX2),
-	MIDR_ALL_VERSIONS(MIDR_QCOM_FALKOR_V1),
-	MIDR_ALL_VERSIONS(MIDR_QCOM_FALKOR),
-	MIDR_ALL_VERSIONS(MIDR_NVIDIA_DENVER),
-	{},
+static const struct midr_range spectre_v2_safe_list[] = {
+	MIDR_ALL_VERSIONS(MIDR_CORTEX_A35),
+	MIDR_ALL_VERSIONS(MIDR_CORTEX_A53),
+	MIDR_ALL_VERSIONS(MIDR_CORTEX_A55),
+	{ /* sentinel */ }
 };
 
-#endif
+/*
+ * Track overall bp hardening for all heterogeneous cores in the machine.
+ * We are only considered "safe" if all booted cores are known safe.
+ */
+static bool __maybe_unused
+check_branch_predictor(const struct arm64_cpu_capabilities *entry, int scope)
+{
+	int need_wa;
+
+	WARN_ON(scope != SCOPE_LOCAL_CPU || preemptible());
+
+	/* If the CPU has CSV2 set, we're safe */
+	if (cpuid_feature_extract_unsigned_field(read_cpuid(ID_AA64PFR0_EL1),
+						 ID_AA64PFR0_CSV2_SHIFT))
+		return false;
+
+	/* Alternatively, we have a list of unaffected CPUs */
+	if (is_midr_in_range_list(read_cpuid_id(), spectre_v2_safe_list))
+		return false;
+
+	/* Fallback to firmware detection */
+	need_wa = detect_harden_bp_fw();
+	if (!need_wa)
+		return false;
+
+	__spectrev2_safe = false;
+
+	if (!IS_ENABLED(CONFIG_HARDEN_BRANCH_PREDICTOR)) {
+		pr_warn_once("spectrev2 mitigation disabled by kernel configuration\n");
+		__hardenbp_enab = false;
+		return false;
+	}
+
+	/* forced off */
+	if (__nospectre_v2 || cpu_mitigations_off()) {
+		pr_info_once("spectrev2 mitigation disabled by command line option\n");
+		__hardenbp_enab = false;
+		return false;
+	}
+
+	if (need_wa < 0) {
+		pr_warn_once("ARM_SMCCC_ARCH_WORKAROUND_1 missing from firmware\n");
+		__hardenbp_enab = false;
+	}
+
+	return (need_wa > 0);
+}
 
 #ifdef CONFIG_HARDEN_EL2_VECTORS
 
@@ -603,6 +682,16 @@ static const struct midr_range workaround_clean_cache[] = {
 };
 #endif
 
+#ifdef CONFIG_ARM64_ERRATUM_1188873
+static const struct midr_range erratum_1188873_list[] = {
+	/* Cortex-A76 r0p0 to r2p0 */
+	MIDR_RANGE(MIDR_CORTEX_A76, 0, 0, 2, 0),
+	/* Neoverse-N1 r0p0 to r2p0 */
+	MIDR_RANGE(MIDR_NEOVERSE_N1, 0, 0, 2, 0),
+	{},
+};
+#endif
+
 const struct arm64_cpu_capabilities arm64_errata[] = {
 #ifdef CONFIG_ARM64_WORKAROUND_CLEAN_CACHE
 	{
@@ -701,13 +790,11 @@ const struct arm64_cpu_capabilities arm64_errata[] = {
 		ERRATA_MIDR_ALL_VERSIONS(MIDR_CORTEX_A73),
 	},
 #endif
-#ifdef CONFIG_HARDEN_BRANCH_PREDICTOR
 	{
 		.capability = ARM64_HARDEN_BRANCH_PREDICTOR,
-		.cpu_enable = enable_smccc_arch_workaround_1,
-		ERRATA_MIDR_RANGE_LIST(arm64_bp_harden_smccc_cpus),
+		.type = ARM64_CPUCAP_LOCAL_CPU_ERRATUM,
+		.matches = check_branch_predictor,
 	},
-#endif
 #ifdef CONFIG_HARDEN_EL2_VECTORS
 	{
 		.desc = "EL2 vector hardening",
@@ -715,20 +802,18 @@ const struct arm64_cpu_capabilities arm64_errata[] = {
 		ERRATA_MIDR_RANGE_LIST(arm64_harden_el2_vectors),
 	},
 #endif
-#ifdef CONFIG_ARM64_SSBD
 	{
 		.desc = "Speculative Store Bypass Disable",
 		.capability = ARM64_SSBD,
 		.type = ARM64_CPUCAP_LOCAL_CPU_ERRATUM,
 		.matches = has_ssbd_mitigation,
+		.midr_range_list = arm64_ssb_cpus,
 	},
-#endif
 #ifdef CONFIG_ARM64_ERRATUM_1188873
 	{
-		/* Cortex-A76 r0p0 to r2p0 */
 		.desc = "ARM erratum 1188873",
 		.capability = ARM64_WORKAROUND_1188873,
-		ERRATA_MIDR_RANGE(MIDR_CORTEX_A76, 0, 0, 2, 0),
+		ERRATA_MIDR_RANGE_LIST(erratum_1188873_list),
 	},
 #endif
 #ifdef CONFIG_ARM64_ERRATUM_1165522
@@ -742,3 +827,38 @@ const struct arm64_cpu_capabilities arm64_errata[] = {
 	{
 	}
 };
+
+ssize_t cpu_show_spectre_v1(struct device *dev, struct device_attribute *attr,
+			    char *buf)
+{
+	return sprintf(buf, "Mitigation: __user pointer sanitization\n");
+}
+
+ssize_t cpu_show_spectre_v2(struct device *dev, struct device_attribute *attr,
+		char *buf)
+{
+	if (__spectrev2_safe)
+		return sprintf(buf, "Not affected\n");
+
+	if (__hardenbp_enab)
+		return sprintf(buf, "Mitigation: Branch predictor hardening\n");
+
+	return sprintf(buf, "Vulnerable\n");
+}
+
+ssize_t cpu_show_spec_store_bypass(struct device *dev,
+		struct device_attribute *attr, char *buf)
+{
+	if (__ssb_safe)
+		return sprintf(buf, "Not affected\n");
+
+	switch (ssbd_state) {
+	case ARM64_SSBD_KERNEL:
+	case ARM64_SSBD_FORCE_ENABLE:
+		if (IS_ENABLED(CONFIG_ARM64_SSBD))
+			return sprintf(buf,
+			    "Mitigation: Speculative Store Bypass disabled via prctl\n");
+	}
+
+	return sprintf(buf, "Vulnerable\n");
+}
diff --git a/arch/arm64/kernel/cpu_ops.c b/arch/arm64/kernel/cpu_ops.c
index ea001241bdd4..00f8b8612b69 100644
--- a/arch/arm64/kernel/cpu_ops.c
+++ b/arch/arm64/kernel/cpu_ops.c
@@ -85,6 +85,7 @@ static const char *__init cpu_read_enable_method(int cpu)
 				pr_err("%pOF: missing enable-method property\n",
 					dn);
 		}
+		of_node_put(dn);
 	} else {
 		enable_method = acpi_get_enable_method(cpu);
 		if (!enable_method) {
diff --git a/arch/arm64/kernel/cpufeature.c b/arch/arm64/kernel/cpufeature.c
index 4061de10cea6..2b807f129e60 100644
--- a/arch/arm64/kernel/cpufeature.c
+++ b/arch/arm64/kernel/cpufeature.c
@@ -25,6 +25,7 @@
 #include <linux/stop_machine.h>
 #include <linux/types.h>
 #include <linux/mm.h>
+#include <linux/cpu.h>
 #include <asm/cpu.h>
 #include <asm/cpufeature.h>
 #include <asm/cpu_ops.h>
@@ -35,8 +36,8 @@
 #include <asm/traps.h>
 #include <asm/virt.h>
 
-unsigned long elf_hwcap __read_mostly;
-EXPORT_SYMBOL_GPL(elf_hwcap);
+/* Kernel representation of AT_HWCAP and AT_HWCAP2 */
+static unsigned long elf_hwcap __read_mostly;
 
 #ifdef CONFIG_COMPAT
 #define COMPAT_ELF_HWCAP_DEFAULT	\
@@ -184,6 +185,15 @@ static const struct arm64_ftr_bits ftr_id_aa64pfr1[] = {
 	ARM64_FTR_END,
 };
 
+static const struct arm64_ftr_bits ftr_id_aa64zfr0[] = {
+	ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64ZFR0_SM4_SHIFT, 4, 0),
+	ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64ZFR0_SHA3_SHIFT, 4, 0),
+	ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64ZFR0_BITPERM_SHIFT, 4, 0),
+	ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64ZFR0_AES_SHIFT, 4, 0),
+	ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64ZFR0_SVEVER_SHIFT, 4, 0),
+	ARM64_FTR_END,
+};
+
 static const struct arm64_ftr_bits ftr_id_aa64mmfr0[] = {
 	S_ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64MMFR0_TGRAN4_SHIFT, 4, ID_AA64MMFR0_TGRAN4_NI),
 	S_ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64MMFR0_TGRAN64_SHIFT, 4, ID_AA64MMFR0_TGRAN64_NI),
@@ -392,7 +402,7 @@ static const struct __ftr_reg_entry {
 	/* Op1 = 0, CRn = 0, CRm = 4 */
 	ARM64_FTR_REG(SYS_ID_AA64PFR0_EL1, ftr_id_aa64pfr0),
 	ARM64_FTR_REG(SYS_ID_AA64PFR1_EL1, ftr_id_aa64pfr1),
-	ARM64_FTR_REG(SYS_ID_AA64ZFR0_EL1, ftr_raz),
+	ARM64_FTR_REG(SYS_ID_AA64ZFR0_EL1, ftr_id_aa64zfr0),
 
 	/* Op1 = 0, CRn = 0, CRm = 5 */
 	ARM64_FTR_REG(SYS_ID_AA64DFR0_EL1, ftr_id_aa64dfr0),
@@ -947,7 +957,7 @@ has_useable_cnp(const struct arm64_cpu_capabilities *entry, int scope)
 	return has_cpuid_feature(entry, scope);
 }
 
-#ifdef CONFIG_UNMAP_KERNEL_AT_EL0
+static bool __meltdown_safe = true;
 static int __kpti_forced; /* 0: not forced, >0: forced on, <0: forced off */
 
 static bool unmap_kernel_at_el0(const struct arm64_cpu_capabilities *entry,
@@ -966,7 +976,17 @@ static bool unmap_kernel_at_el0(const struct arm64_cpu_capabilities *entry,
 		MIDR_ALL_VERSIONS(MIDR_HISI_TSV110),
 		{ /* sentinel */ }
 	};
-	char const *str = "command line option";
+	char const *str = "kpti command line option";
+	bool meltdown_safe;
+
+	meltdown_safe = is_midr_in_range_list(read_cpuid_id(), kpti_safe_list);
+
+	/* Defer to CPU feature registers */
+	if (has_cpuid_feature(entry, scope))
+		meltdown_safe = true;
+
+	if (!meltdown_safe)
+		__meltdown_safe = false;
 
 	/*
 	 * For reasons that aren't entirely clear, enabling KPTI on Cavium
@@ -978,6 +998,24 @@ static bool unmap_kernel_at_el0(const struct arm64_cpu_capabilities *entry,
 		__kpti_forced = -1;
 	}
 
+	/* Useful for KASLR robustness */
+	if (IS_ENABLED(CONFIG_RANDOMIZE_BASE) && kaslr_offset() > 0) {
+		if (!__kpti_forced) {
+			str = "KASLR";
+			__kpti_forced = 1;
+		}
+	}
+
+	if (cpu_mitigations_off() && !__kpti_forced) {
+		str = "mitigations=off";
+		__kpti_forced = -1;
+	}
+
+	if (!IS_ENABLED(CONFIG_UNMAP_KERNEL_AT_EL0)) {
+		pr_info_once("kernel page table isolation disabled by kernel configuration\n");
+		return false;
+	}
+
 	/* Forced? */
 	if (__kpti_forced) {
 		pr_info_once("kernel page table isolation forced %s by %s\n",
@@ -985,18 +1023,10 @@ static bool unmap_kernel_at_el0(const struct arm64_cpu_capabilities *entry,
 		return __kpti_forced > 0;
 	}
 
-	/* Useful for KASLR robustness */
-	if (IS_ENABLED(CONFIG_RANDOMIZE_BASE))
-		return kaslr_offset() > 0;
-
-	/* Don't force KPTI for CPUs that are not vulnerable */
-	if (is_midr_in_range_list(read_cpuid_id(), kpti_safe_list))
-		return false;
-
-	/* Defer to CPU feature registers */
-	return !has_cpuid_feature(entry, scope);
+	return !meltdown_safe;
 }
 
+#ifdef CONFIG_UNMAP_KERNEL_AT_EL0
 static void
 kpti_install_ng_mappings(const struct arm64_cpu_capabilities *__unused)
 {
@@ -1026,6 +1056,12 @@ kpti_install_ng_mappings(const struct arm64_cpu_capabilities *__unused)
 
 	return;
 }
+#else
+static void
+kpti_install_ng_mappings(const struct arm64_cpu_capabilities *__unused)
+{
+}
+#endif	/* CONFIG_UNMAP_KERNEL_AT_EL0 */
 
 static int __init parse_kpti(char *str)
 {
@@ -1039,7 +1075,6 @@ static int __init parse_kpti(char *str)
 	return 0;
 }
 early_param("kpti", parse_kpti);
-#endif	/* CONFIG_UNMAP_KERNEL_AT_EL0 */
 
 #ifdef CONFIG_ARM64_HW_AFDBM
 static inline void __cpu_enable_hw_dbm(void)
@@ -1306,7 +1341,6 @@ static const struct arm64_cpu_capabilities arm64_features[] = {
 		.field_pos = ID_AA64PFR0_EL0_SHIFT,
 		.min_field_value = ID_AA64PFR0_EL0_32BIT_64BIT,
 	},
-#ifdef CONFIG_UNMAP_KERNEL_AT_EL0
 	{
 		.desc = "Kernel page table isolation (KPTI)",
 		.capability = ARM64_UNMAP_KERNEL_AT_EL0,
@@ -1322,7 +1356,6 @@ static const struct arm64_cpu_capabilities arm64_features[] = {
 		.matches = unmap_kernel_at_el0,
 		.cpu_enable = kpti_install_ng_mappings,
 	},
-#endif
 	{
 		/* FP/SIMD is not implemented */
 		.capability = ARM64_HAS_NO_FPSIMD,
@@ -1340,6 +1373,16 @@ static const struct arm64_cpu_capabilities arm64_features[] = {
 		.field_pos = ID_AA64ISAR1_DPB_SHIFT,
 		.min_field_value = 1,
 	},
+	{
+		.desc = "Data cache clean to Point of Deep Persistence",
+		.capability = ARM64_HAS_DCPODP,
+		.type = ARM64_CPUCAP_SYSTEM_FEATURE,
+		.matches = has_cpuid_feature,
+		.sys_reg = SYS_ID_AA64ISAR1_EL1,
+		.sign = FTR_UNSIGNED,
+		.field_pos = ID_AA64ISAR1_DPB_SHIFT,
+		.min_field_value = 2,
+	},
 #endif
 #ifdef CONFIG_ARM64_SVE
 	{
@@ -1571,39 +1614,46 @@ static const struct arm64_cpu_capabilities ptr_auth_hwcap_gen_matches[] = {
 #endif
 
 static const struct arm64_cpu_capabilities arm64_elf_hwcaps[] = {
-	HWCAP_CAP(SYS_ID_AA64ISAR0_EL1, ID_AA64ISAR0_AES_SHIFT, FTR_UNSIGNED, 2, CAP_HWCAP, HWCAP_PMULL),
-	HWCAP_CAP(SYS_ID_AA64ISAR0_EL1, ID_AA64ISAR0_AES_SHIFT, FTR_UNSIGNED, 1, CAP_HWCAP, HWCAP_AES),
-	HWCAP_CAP(SYS_ID_AA64ISAR0_EL1, ID_AA64ISAR0_SHA1_SHIFT, FTR_UNSIGNED, 1, CAP_HWCAP, HWCAP_SHA1),
-	HWCAP_CAP(SYS_ID_AA64ISAR0_EL1, ID_AA64ISAR0_SHA2_SHIFT, FTR_UNSIGNED, 1, CAP_HWCAP, HWCAP_SHA2),
-	HWCAP_CAP(SYS_ID_AA64ISAR0_EL1, ID_AA64ISAR0_SHA2_SHIFT, FTR_UNSIGNED, 2, CAP_HWCAP, HWCAP_SHA512),
-	HWCAP_CAP(SYS_ID_AA64ISAR0_EL1, ID_AA64ISAR0_CRC32_SHIFT, FTR_UNSIGNED, 1, CAP_HWCAP, HWCAP_CRC32),
-	HWCAP_CAP(SYS_ID_AA64ISAR0_EL1, ID_AA64ISAR0_ATOMICS_SHIFT, FTR_UNSIGNED, 2, CAP_HWCAP, HWCAP_ATOMICS),
-	HWCAP_CAP(SYS_ID_AA64ISAR0_EL1, ID_AA64ISAR0_RDM_SHIFT, FTR_UNSIGNED, 1, CAP_HWCAP, HWCAP_ASIMDRDM),
-	HWCAP_CAP(SYS_ID_AA64ISAR0_EL1, ID_AA64ISAR0_SHA3_SHIFT, FTR_UNSIGNED, 1, CAP_HWCAP, HWCAP_SHA3),
-	HWCAP_CAP(SYS_ID_AA64ISAR0_EL1, ID_AA64ISAR0_SM3_SHIFT, FTR_UNSIGNED, 1, CAP_HWCAP, HWCAP_SM3),
-	HWCAP_CAP(SYS_ID_AA64ISAR0_EL1, ID_AA64ISAR0_SM4_SHIFT, FTR_UNSIGNED, 1, CAP_HWCAP, HWCAP_SM4),
-	HWCAP_CAP(SYS_ID_AA64ISAR0_EL1, ID_AA64ISAR0_DP_SHIFT, FTR_UNSIGNED, 1, CAP_HWCAP, HWCAP_ASIMDDP),
-	HWCAP_CAP(SYS_ID_AA64ISAR0_EL1, ID_AA64ISAR0_FHM_SHIFT, FTR_UNSIGNED, 1, CAP_HWCAP, HWCAP_ASIMDFHM),
-	HWCAP_CAP(SYS_ID_AA64ISAR0_EL1, ID_AA64ISAR0_TS_SHIFT, FTR_UNSIGNED, 1, CAP_HWCAP, HWCAP_FLAGM),
-	HWCAP_CAP(SYS_ID_AA64PFR0_EL1, ID_AA64PFR0_FP_SHIFT, FTR_SIGNED, 0, CAP_HWCAP, HWCAP_FP),
-	HWCAP_CAP(SYS_ID_AA64PFR0_EL1, ID_AA64PFR0_FP_SHIFT, FTR_SIGNED, 1, CAP_HWCAP, HWCAP_FPHP),
-	HWCAP_CAP(SYS_ID_AA64PFR0_EL1, ID_AA64PFR0_ASIMD_SHIFT, FTR_SIGNED, 0, CAP_HWCAP, HWCAP_ASIMD),
-	HWCAP_CAP(SYS_ID_AA64PFR0_EL1, ID_AA64PFR0_ASIMD_SHIFT, FTR_SIGNED, 1, CAP_HWCAP, HWCAP_ASIMDHP),
-	HWCAP_CAP(SYS_ID_AA64PFR0_EL1, ID_AA64PFR0_DIT_SHIFT, FTR_SIGNED, 1, CAP_HWCAP, HWCAP_DIT),
-	HWCAP_CAP(SYS_ID_AA64ISAR1_EL1, ID_AA64ISAR1_DPB_SHIFT, FTR_UNSIGNED, 1, CAP_HWCAP, HWCAP_DCPOP),
-	HWCAP_CAP(SYS_ID_AA64ISAR1_EL1, ID_AA64ISAR1_JSCVT_SHIFT, FTR_UNSIGNED, 1, CAP_HWCAP, HWCAP_JSCVT),
-	HWCAP_CAP(SYS_ID_AA64ISAR1_EL1, ID_AA64ISAR1_FCMA_SHIFT, FTR_UNSIGNED, 1, CAP_HWCAP, HWCAP_FCMA),
-	HWCAP_CAP(SYS_ID_AA64ISAR1_EL1, ID_AA64ISAR1_LRCPC_SHIFT, FTR_UNSIGNED, 1, CAP_HWCAP, HWCAP_LRCPC),
-	HWCAP_CAP(SYS_ID_AA64ISAR1_EL1, ID_AA64ISAR1_LRCPC_SHIFT, FTR_UNSIGNED, 2, CAP_HWCAP, HWCAP_ILRCPC),
-	HWCAP_CAP(SYS_ID_AA64ISAR1_EL1, ID_AA64ISAR1_SB_SHIFT, FTR_UNSIGNED, 1, CAP_HWCAP, HWCAP_SB),
-	HWCAP_CAP(SYS_ID_AA64MMFR2_EL1, ID_AA64MMFR2_AT_SHIFT, FTR_UNSIGNED, 1, CAP_HWCAP, HWCAP_USCAT),
+	HWCAP_CAP(SYS_ID_AA64ISAR0_EL1, ID_AA64ISAR0_AES_SHIFT, FTR_UNSIGNED, 2, CAP_HWCAP, KERNEL_HWCAP_PMULL),
+	HWCAP_CAP(SYS_ID_AA64ISAR0_EL1, ID_AA64ISAR0_AES_SHIFT, FTR_UNSIGNED, 1, CAP_HWCAP, KERNEL_HWCAP_AES),
+	HWCAP_CAP(SYS_ID_AA64ISAR0_EL1, ID_AA64ISAR0_SHA1_SHIFT, FTR_UNSIGNED, 1, CAP_HWCAP, KERNEL_HWCAP_SHA1),
+	HWCAP_CAP(SYS_ID_AA64ISAR0_EL1, ID_AA64ISAR0_SHA2_SHIFT, FTR_UNSIGNED, 1, CAP_HWCAP, KERNEL_HWCAP_SHA2),
+	HWCAP_CAP(SYS_ID_AA64ISAR0_EL1, ID_AA64ISAR0_SHA2_SHIFT, FTR_UNSIGNED, 2, CAP_HWCAP, KERNEL_HWCAP_SHA512),
+	HWCAP_CAP(SYS_ID_AA64ISAR0_EL1, ID_AA64ISAR0_CRC32_SHIFT, FTR_UNSIGNED, 1, CAP_HWCAP, KERNEL_HWCAP_CRC32),
+	HWCAP_CAP(SYS_ID_AA64ISAR0_EL1, ID_AA64ISAR0_ATOMICS_SHIFT, FTR_UNSIGNED, 2, CAP_HWCAP, KERNEL_HWCAP_ATOMICS),
+	HWCAP_CAP(SYS_ID_AA64ISAR0_EL1, ID_AA64ISAR0_RDM_SHIFT, FTR_UNSIGNED, 1, CAP_HWCAP, KERNEL_HWCAP_ASIMDRDM),
+	HWCAP_CAP(SYS_ID_AA64ISAR0_EL1, ID_AA64ISAR0_SHA3_SHIFT, FTR_UNSIGNED, 1, CAP_HWCAP, KERNEL_HWCAP_SHA3),
+	HWCAP_CAP(SYS_ID_AA64ISAR0_EL1, ID_AA64ISAR0_SM3_SHIFT, FTR_UNSIGNED, 1, CAP_HWCAP, KERNEL_HWCAP_SM3),
+	HWCAP_CAP(SYS_ID_AA64ISAR0_EL1, ID_AA64ISAR0_SM4_SHIFT, FTR_UNSIGNED, 1, CAP_HWCAP, KERNEL_HWCAP_SM4),
+	HWCAP_CAP(SYS_ID_AA64ISAR0_EL1, ID_AA64ISAR0_DP_SHIFT, FTR_UNSIGNED, 1, CAP_HWCAP, KERNEL_HWCAP_ASIMDDP),
+	HWCAP_CAP(SYS_ID_AA64ISAR0_EL1, ID_AA64ISAR0_FHM_SHIFT, FTR_UNSIGNED, 1, CAP_HWCAP, KERNEL_HWCAP_ASIMDFHM),
+	HWCAP_CAP(SYS_ID_AA64ISAR0_EL1, ID_AA64ISAR0_TS_SHIFT, FTR_UNSIGNED, 1, CAP_HWCAP, KERNEL_HWCAP_FLAGM),
+	HWCAP_CAP(SYS_ID_AA64PFR0_EL1, ID_AA64PFR0_FP_SHIFT, FTR_SIGNED, 0, CAP_HWCAP, KERNEL_HWCAP_FP),
+	HWCAP_CAP(SYS_ID_AA64PFR0_EL1, ID_AA64PFR0_FP_SHIFT, FTR_SIGNED, 1, CAP_HWCAP, KERNEL_HWCAP_FPHP),
+	HWCAP_CAP(SYS_ID_AA64PFR0_EL1, ID_AA64PFR0_ASIMD_SHIFT, FTR_SIGNED, 0, CAP_HWCAP, KERNEL_HWCAP_ASIMD),
+	HWCAP_CAP(SYS_ID_AA64PFR0_EL1, ID_AA64PFR0_ASIMD_SHIFT, FTR_SIGNED, 1, CAP_HWCAP, KERNEL_HWCAP_ASIMDHP),
+	HWCAP_CAP(SYS_ID_AA64PFR0_EL1, ID_AA64PFR0_DIT_SHIFT, FTR_SIGNED, 1, CAP_HWCAP, KERNEL_HWCAP_DIT),
+	HWCAP_CAP(SYS_ID_AA64ISAR1_EL1, ID_AA64ISAR1_DPB_SHIFT, FTR_UNSIGNED, 1, CAP_HWCAP, KERNEL_HWCAP_DCPOP),
+	HWCAP_CAP(SYS_ID_AA64ISAR1_EL1, ID_AA64ISAR1_DPB_SHIFT, FTR_UNSIGNED, 2, CAP_HWCAP, KERNEL_HWCAP_DCPODP),
+	HWCAP_CAP(SYS_ID_AA64ISAR1_EL1, ID_AA64ISAR1_JSCVT_SHIFT, FTR_UNSIGNED, 1, CAP_HWCAP, KERNEL_HWCAP_JSCVT),
+	HWCAP_CAP(SYS_ID_AA64ISAR1_EL1, ID_AA64ISAR1_FCMA_SHIFT, FTR_UNSIGNED, 1, CAP_HWCAP, KERNEL_HWCAP_FCMA),
+	HWCAP_CAP(SYS_ID_AA64ISAR1_EL1, ID_AA64ISAR1_LRCPC_SHIFT, FTR_UNSIGNED, 1, CAP_HWCAP, KERNEL_HWCAP_LRCPC),
+	HWCAP_CAP(SYS_ID_AA64ISAR1_EL1, ID_AA64ISAR1_LRCPC_SHIFT, FTR_UNSIGNED, 2, CAP_HWCAP, KERNEL_HWCAP_ILRCPC),
+	HWCAP_CAP(SYS_ID_AA64ISAR1_EL1, ID_AA64ISAR1_SB_SHIFT, FTR_UNSIGNED, 1, CAP_HWCAP, KERNEL_HWCAP_SB),
+	HWCAP_CAP(SYS_ID_AA64MMFR2_EL1, ID_AA64MMFR2_AT_SHIFT, FTR_UNSIGNED, 1, CAP_HWCAP, KERNEL_HWCAP_USCAT),
 #ifdef CONFIG_ARM64_SVE
-	HWCAP_CAP(SYS_ID_AA64PFR0_EL1, ID_AA64PFR0_SVE_SHIFT, FTR_UNSIGNED, ID_AA64PFR0_SVE, CAP_HWCAP, HWCAP_SVE),
+	HWCAP_CAP(SYS_ID_AA64PFR0_EL1, ID_AA64PFR0_SVE_SHIFT, FTR_UNSIGNED, ID_AA64PFR0_SVE, CAP_HWCAP, KERNEL_HWCAP_SVE),
+	HWCAP_CAP(SYS_ID_AA64ZFR0_EL1, ID_AA64ZFR0_SVEVER_SHIFT, FTR_UNSIGNED, ID_AA64ZFR0_SVEVER_SVE2, CAP_HWCAP, KERNEL_HWCAP_SVE2),
+	HWCAP_CAP(SYS_ID_AA64ZFR0_EL1, ID_AA64ZFR0_AES_SHIFT, FTR_UNSIGNED, ID_AA64ZFR0_AES, CAP_HWCAP, KERNEL_HWCAP_SVEAES),
+	HWCAP_CAP(SYS_ID_AA64ZFR0_EL1, ID_AA64ZFR0_AES_SHIFT, FTR_UNSIGNED, ID_AA64ZFR0_AES_PMULL, CAP_HWCAP, KERNEL_HWCAP_SVEPMULL),
+	HWCAP_CAP(SYS_ID_AA64ZFR0_EL1, ID_AA64ZFR0_BITPERM_SHIFT, FTR_UNSIGNED, ID_AA64ZFR0_BITPERM, CAP_HWCAP, KERNEL_HWCAP_SVEBITPERM),
+	HWCAP_CAP(SYS_ID_AA64ZFR0_EL1, ID_AA64ZFR0_SHA3_SHIFT, FTR_UNSIGNED, ID_AA64ZFR0_SHA3, CAP_HWCAP, KERNEL_HWCAP_SVESHA3),
+	HWCAP_CAP(SYS_ID_AA64ZFR0_EL1, ID_AA64ZFR0_SM4_SHIFT, FTR_UNSIGNED, ID_AA64ZFR0_SM4, CAP_HWCAP, KERNEL_HWCAP_SVESM4),
 #endif
-	HWCAP_CAP(SYS_ID_AA64PFR1_EL1, ID_AA64PFR1_SSBS_SHIFT, FTR_UNSIGNED, ID_AA64PFR1_SSBS_PSTATE_INSNS, CAP_HWCAP, HWCAP_SSBS),
+	HWCAP_CAP(SYS_ID_AA64PFR1_EL1, ID_AA64PFR1_SSBS_SHIFT, FTR_UNSIGNED, ID_AA64PFR1_SSBS_PSTATE_INSNS, CAP_HWCAP, KERNEL_HWCAP_SSBS),
 #ifdef CONFIG_ARM64_PTR_AUTH
-	HWCAP_MULTI_CAP(ptr_auth_hwcap_addr_matches, CAP_HWCAP, HWCAP_PACA),
-	HWCAP_MULTI_CAP(ptr_auth_hwcap_gen_matches, CAP_HWCAP, HWCAP_PACG),
+	HWCAP_MULTI_CAP(ptr_auth_hwcap_addr_matches, CAP_HWCAP, KERNEL_HWCAP_PACA),
+	HWCAP_MULTI_CAP(ptr_auth_hwcap_gen_matches, CAP_HWCAP, KERNEL_HWCAP_PACG),
 #endif
 	{},
 };
@@ -1623,7 +1673,7 @@ static void __init cap_set_elf_hwcap(const struct arm64_cpu_capabilities *cap)
 {
 	switch (cap->hwcap_type) {
 	case CAP_HWCAP:
-		elf_hwcap |= cap->hwcap;
+		cpu_set_feature(cap->hwcap);
 		break;
 #ifdef CONFIG_COMPAT
 	case CAP_COMPAT_HWCAP:
@@ -1646,7 +1696,7 @@ static bool cpus_have_elf_hwcap(const struct arm64_cpu_capabilities *cap)
 
 	switch (cap->hwcap_type) {
 	case CAP_HWCAP:
-		rc = (elf_hwcap & cap->hwcap) != 0;
+		rc = cpu_have_feature(cap->hwcap);
 		break;
 #ifdef CONFIG_COMPAT
 	case CAP_COMPAT_HWCAP:
@@ -1667,7 +1717,7 @@ static bool cpus_have_elf_hwcap(const struct arm64_cpu_capabilities *cap)
 static void __init setup_elf_hwcaps(const struct arm64_cpu_capabilities *hwcaps)
 {
 	/* We support emulation of accesses to CPU ID feature registers */
-	elf_hwcap |= HWCAP_CPUID;
+	cpu_set_named_feature(CPUID);
 	for (; hwcaps->matches; hwcaps++)
 		if (hwcaps->matches(hwcaps, cpucap_default_scope(hwcaps)))
 			cap_set_elf_hwcap(hwcaps);
@@ -1947,6 +1997,35 @@ bool this_cpu_has_cap(unsigned int n)
 	return false;
 }
 
+void cpu_set_feature(unsigned int num)
+{
+	WARN_ON(num >= MAX_CPU_FEATURES);
+	elf_hwcap |= BIT(num);
+}
+EXPORT_SYMBOL_GPL(cpu_set_feature);
+
+bool cpu_have_feature(unsigned int num)
+{
+	WARN_ON(num >= MAX_CPU_FEATURES);
+	return elf_hwcap & BIT(num);
+}
+EXPORT_SYMBOL_GPL(cpu_have_feature);
+
+unsigned long cpu_get_elf_hwcap(void)
+{
+	/*
+	 * We currently only populate the first 32 bits of AT_HWCAP. Please
+	 * note that for userspace compatibility we guarantee that bits 62
+	 * and 63 will always be returned as 0.
+	 */
+	return lower_32_bits(elf_hwcap);
+}
+
+unsigned long cpu_get_elf_hwcap2(void)
+{
+	return upper_32_bits(elf_hwcap);
+}
+
 static void __init setup_system_capabilities(void)
 {
 	/*
@@ -2101,3 +2180,15 @@ static int __init enable_mrs_emulation(void)
 }
 
 core_initcall(enable_mrs_emulation);
+
+ssize_t cpu_show_meltdown(struct device *dev, struct device_attribute *attr,
+			  char *buf)
+{
+	if (__meltdown_safe)
+		return sprintf(buf, "Not affected\n");
+
+	if (arm64_kernel_unmapped_at_el0())
+		return sprintf(buf, "Mitigation: PTI\n");
+
+	return sprintf(buf, "Vulnerable\n");
+}
diff --git a/arch/arm64/kernel/cpuinfo.c b/arch/arm64/kernel/cpuinfo.c
index ca0685f33900..f6f7936be6e7 100644
--- a/arch/arm64/kernel/cpuinfo.c
+++ b/arch/arm64/kernel/cpuinfo.c
@@ -85,6 +85,13 @@ static const char *const hwcap_str[] = {
 	"sb",
 	"paca",
 	"pacg",
+	"dcpodp",
+	"sve2",
+	"sveaes",
+	"svepmull",
+	"svebitperm",
+	"svesha3",
+	"svesm4",
 	NULL
 };
 
@@ -167,7 +174,7 @@ static int c_show(struct seq_file *m, void *v)
 #endif /* CONFIG_COMPAT */
 		} else {
 			for (j = 0; hwcap_str[j]; j++)
-				if (elf_hwcap & (1 << j))
+				if (cpu_have_feature(j))
 					seq_printf(m, " %s", hwcap_str[j]);
 		}
 		seq_puts(m, "\n");
diff --git a/arch/arm64/kernel/debug-monitors.c b/arch/arm64/kernel/debug-monitors.c
index d7bb6aefae0a..555b6bd2f3d6 100644
--- a/arch/arm64/kernel/debug-monitors.c
+++ b/arch/arm64/kernel/debug-monitors.c
@@ -135,6 +135,7 @@ NOKPROBE_SYMBOL(disable_debug_monitors);
  */
 static int clear_os_lock(unsigned int cpu)
 {
+	write_sysreg(0, osdlr_el1);
 	write_sysreg(0, oslar_el1);
 	isb();
 	return 0;
@@ -163,25 +164,46 @@ static void clear_regs_spsr_ss(struct pt_regs *regs)
 }
 NOKPROBE_SYMBOL(clear_regs_spsr_ss);
 
-/* EL1 Single Step Handler hooks */
-static LIST_HEAD(step_hook);
-static DEFINE_SPINLOCK(step_hook_lock);
+static DEFINE_SPINLOCK(debug_hook_lock);
+static LIST_HEAD(user_step_hook);
+static LIST_HEAD(kernel_step_hook);
 
-void register_step_hook(struct step_hook *hook)
+static void register_debug_hook(struct list_head *node, struct list_head *list)
 {
-	spin_lock(&step_hook_lock);
-	list_add_rcu(&hook->node, &step_hook);
-	spin_unlock(&step_hook_lock);
+	spin_lock(&debug_hook_lock);
+	list_add_rcu(node, list);
+	spin_unlock(&debug_hook_lock);
+
 }
 
-void unregister_step_hook(struct step_hook *hook)
+static void unregister_debug_hook(struct list_head *node)
 {
-	spin_lock(&step_hook_lock);
-	list_del_rcu(&hook->node);
-	spin_unlock(&step_hook_lock);
+	spin_lock(&debug_hook_lock);
+	list_del_rcu(node);
+	spin_unlock(&debug_hook_lock);
 	synchronize_rcu();
 }
 
+void register_user_step_hook(struct step_hook *hook)
+{
+	register_debug_hook(&hook->node, &user_step_hook);
+}
+
+void unregister_user_step_hook(struct step_hook *hook)
+{
+	unregister_debug_hook(&hook->node);
+}
+
+void register_kernel_step_hook(struct step_hook *hook)
+{
+	register_debug_hook(&hook->node, &kernel_step_hook);
+}
+
+void unregister_kernel_step_hook(struct step_hook *hook)
+{
+	unregister_debug_hook(&hook->node);
+}
+
 /*
  * Call registered single step handlers
  * There is no Syndrome info to check for determining the handler.
@@ -191,11 +213,14 @@ void unregister_step_hook(struct step_hook *hook)
 static int call_step_hook(struct pt_regs *regs, unsigned int esr)
 {
 	struct step_hook *hook;
+	struct list_head *list;
 	int retval = DBG_HOOK_ERROR;
 
+	list = user_mode(regs) ? &user_step_hook : &kernel_step_hook;
+
 	rcu_read_lock();
 
-	list_for_each_entry_rcu(hook, &step_hook, node)	{
+	list_for_each_entry_rcu(hook, list, node)	{
 		retval = hook->fn(regs, esr);
 		if (retval == DBG_HOOK_HANDLED)
 			break;
@@ -222,7 +247,7 @@ static void send_user_sigtrap(int si_code)
 			     "User debug trap");
 }
 
-static int single_step_handler(unsigned long addr, unsigned int esr,
+static int single_step_handler(unsigned long unused, unsigned int esr,
 			       struct pt_regs *regs)
 {
 	bool handler_found = false;
@@ -234,10 +259,6 @@ static int single_step_handler(unsigned long addr, unsigned int esr,
 	if (!reinstall_suspended_bps(regs))
 		return 0;
 
-#ifdef	CONFIG_KPROBES
-	if (kprobe_single_step_handler(regs, esr) == DBG_HOOK_HANDLED)
-		handler_found = true;
-#endif
 	if (!handler_found && call_step_hook(regs, esr) == DBG_HOOK_HANDLED)
 		handler_found = true;
 
@@ -264,61 +285,59 @@ static int single_step_handler(unsigned long addr, unsigned int esr,
 }
 NOKPROBE_SYMBOL(single_step_handler);
 
-/*
- * Breakpoint handler is re-entrant as another breakpoint can
- * hit within breakpoint handler, especically in kprobes.
- * Use reader/writer locks instead of plain spinlock.
- */
-static LIST_HEAD(break_hook);
-static DEFINE_SPINLOCK(break_hook_lock);
+static LIST_HEAD(user_break_hook);
+static LIST_HEAD(kernel_break_hook);
 
-void register_break_hook(struct break_hook *hook)
+void register_user_break_hook(struct break_hook *hook)
 {
-	spin_lock(&break_hook_lock);
-	list_add_rcu(&hook->node, &break_hook);
-	spin_unlock(&break_hook_lock);
+	register_debug_hook(&hook->node, &user_break_hook);
 }
 
-void unregister_break_hook(struct break_hook *hook)
+void unregister_user_break_hook(struct break_hook *hook)
 {
-	spin_lock(&break_hook_lock);
-	list_del_rcu(&hook->node);
-	spin_unlock(&break_hook_lock);
-	synchronize_rcu();
+	unregister_debug_hook(&hook->node);
+}
+
+void register_kernel_break_hook(struct break_hook *hook)
+{
+	register_debug_hook(&hook->node, &kernel_break_hook);
+}
+
+void unregister_kernel_break_hook(struct break_hook *hook)
+{
+	unregister_debug_hook(&hook->node);
 }
 
 static int call_break_hook(struct pt_regs *regs, unsigned int esr)
 {
 	struct break_hook *hook;
+	struct list_head *list;
 	int (*fn)(struct pt_regs *regs, unsigned int esr) = NULL;
 
+	list = user_mode(regs) ? &user_break_hook : &kernel_break_hook;
+
 	rcu_read_lock();
-	list_for_each_entry_rcu(hook, &break_hook, node)
-		if ((esr & hook->esr_mask) == hook->esr_val)
+	list_for_each_entry_rcu(hook, list, node) {
+		unsigned int comment = esr & ESR_ELx_BRK64_ISS_COMMENT_MASK;
+
+		if ((comment & ~hook->mask) == hook->imm)
 			fn = hook->fn;
+	}
 	rcu_read_unlock();
 
 	return fn ? fn(regs, esr) : DBG_HOOK_ERROR;
 }
 NOKPROBE_SYMBOL(call_break_hook);
 
-static int brk_handler(unsigned long addr, unsigned int esr,
+static int brk_handler(unsigned long unused, unsigned int esr,
 		       struct pt_regs *regs)
 {
-	bool handler_found = false;
-
-#ifdef	CONFIG_KPROBES
-	if ((esr & BRK64_ESR_MASK) == BRK64_ESR_KPROBES) {
-		if (kprobe_breakpoint_handler(regs, esr) == DBG_HOOK_HANDLED)
-			handler_found = true;
-	}
-#endif
-	if (!handler_found && call_break_hook(regs, esr) == DBG_HOOK_HANDLED)
-		handler_found = true;
+	if (call_break_hook(regs, esr) == DBG_HOOK_HANDLED)
+		return 0;
 
-	if (!handler_found && user_mode(regs)) {
+	if (user_mode(regs)) {
 		send_user_sigtrap(TRAP_BRKPT);
-	} else if (!handler_found) {
+	} else {
 		pr_warn("Unexpected kernel BRK exception at EL1\n");
 		return -EFAULT;
 	}
diff --git a/arch/arm64/kernel/entry.S b/arch/arm64/kernel/entry.S
index c50a7a75f2e0..1a7811b7e3c4 100644
--- a/arch/arm64/kernel/entry.S
+++ b/arch/arm64/kernel/entry.S
@@ -336,6 +336,21 @@ alternative_if ARM64_WORKAROUND_845719
 alternative_else_nop_endif
 #endif
 3:
+#ifdef CONFIG_ARM64_ERRATUM_1188873
+alternative_if_not ARM64_WORKAROUND_1188873
+	b	4f
+alternative_else_nop_endif
+	/*
+	 * if (x22.mode32 == cntkctl_el1.el0vcten)
+	 *     cntkctl_el1.el0vcten = ~cntkctl_el1.el0vcten
+	 */
+	mrs	x1, cntkctl_el1
+	eon	x0, x1, x22, lsr #3
+	tbz	x0, #1, 4f
+	eor	x1, x1, #2	// ARCH_TIMER_USR_VCT_ACCESS_EN
+	msr	cntkctl_el1, x1
+4:
+#endif
 	apply_ssbd 0, x0, x1
 	.endif
 
@@ -362,11 +377,11 @@ alternative_else_nop_endif
 	.if	\el == 0
 alternative_insn eret, nop, ARM64_UNMAP_KERNEL_AT_EL0
 #ifdef CONFIG_UNMAP_KERNEL_AT_EL0
-	bne	4f
+	bne	5f
 	msr	far_el1, x30
 	tramp_alias	x30, tramp_exit_native
 	br	x30
-4:
+5:
 	tramp_alias	x30, tramp_exit_compat
 	br	x30
 #endif
diff --git a/arch/arm64/kernel/fpsimd.c b/arch/arm64/kernel/fpsimd.c
index 5ebe73b69961..735cf1f8b109 100644
--- a/arch/arm64/kernel/fpsimd.c
+++ b/arch/arm64/kernel/fpsimd.c
@@ -1258,14 +1258,14 @@ static inline void fpsimd_hotplug_init(void) { }
  */
 static int __init fpsimd_init(void)
 {
-	if (elf_hwcap & HWCAP_FP) {
+	if (cpu_have_named_feature(FP)) {
 		fpsimd_pm_init();
 		fpsimd_hotplug_init();
 	} else {
 		pr_notice("Floating-point is not implemented\n");
 	}
 
-	if (!(elf_hwcap & HWCAP_ASIMD))
+	if (!cpu_have_named_feature(ASIMD))
 		pr_notice("Advanced SIMD is not implemented\n");
 
 	return sve_sysctl_init();
diff --git a/arch/arm64/kernel/ftrace.c b/arch/arm64/kernel/ftrace.c
index 8e4431a8821f..65a51331088e 100644
--- a/arch/arm64/kernel/ftrace.c
+++ b/arch/arm64/kernel/ftrace.c
@@ -103,12 +103,16 @@ int ftrace_make_call(struct dyn_ftrace *rec, unsigned long addr)
 		 * to be revisited if support for multiple ftrace entry points
 		 * is added in the future, but for now, the pr_err() below
 		 * deals with a theoretical issue only.
+		 *
+		 * Note that PLTs are place relative, and plt_entries_equal()
+		 * checks whether they point to the same target. Here, we need
+		 * to check if the actual opcodes are in fact identical,
+		 * regardless of the offset in memory so use memcmp() instead.
 		 */
 		trampoline = get_plt_entry(addr, mod->arch.ftrace_trampoline);
-		if (!plt_entries_equal(mod->arch.ftrace_trampoline,
-				       &trampoline)) {
-			if (!plt_entries_equal(mod->arch.ftrace_trampoline,
-					       &(struct plt_entry){})) {
+		if (memcmp(mod->arch.ftrace_trampoline, &trampoline,
+			   sizeof(trampoline))) {
+			if (plt_entry_is_initialized(mod->arch.ftrace_trampoline)) {
 				pr_err("ftrace: far branches to multiple entry points unsupported inside a single module\n");
 				return -EINVAL;
 			}
diff --git a/arch/arm64/kernel/head.S b/arch/arm64/kernel/head.S
index eecf7927dab0..fcae3f85c6cd 100644
--- a/arch/arm64/kernel/head.S
+++ b/arch/arm64/kernel/head.S
@@ -505,7 +505,7 @@ ENTRY(el2_setup)
 	 * kernel is intended to run at EL2.
 	 */
 	mrs	x2, id_aa64mmfr1_el1
-	ubfx	x2, x2, #8, #4
+	ubfx	x2, x2, #ID_AA64MMFR1_VHE_SHIFT, #4
 #else
 	mov	x2, xzr
 #endif
@@ -538,7 +538,7 @@ set_hcr:
 #ifdef CONFIG_ARM_GIC_V3
 	/* GICv3 system register access */
 	mrs	x0, id_aa64pfr0_el1
-	ubfx	x0, x0, #24, #4
+	ubfx	x0, x0, #ID_AA64PFR0_GIC_SHIFT, #4
 	cbz	x0, 3f
 
 	mrs_s	x0, SYS_ICC_SRE_EL2
@@ -564,8 +564,8 @@ set_hcr:
 #endif
 
 	/* EL2 debug */
-	mrs	x1, id_aa64dfr0_el1		// Check ID_AA64DFR0_EL1 PMUVer
-	sbfx	x0, x1, #8, #4
+	mrs	x1, id_aa64dfr0_el1
+	sbfx	x0, x1, #ID_AA64DFR0_PMUVER_SHIFT, #4
 	cmp	x0, #1
 	b.lt	4f				// Skip if no PMU present
 	mrs	x0, pmcr_el0			// Disable debug access traps
@@ -574,7 +574,7 @@ set_hcr:
 	csel	x3, xzr, x0, lt			// all PMU counters from EL1
 
 	/* Statistical profiling */
-	ubfx	x0, x1, #32, #4			// Check ID_AA64DFR0_EL1 PMSVer
+	ubfx	x0, x1, #ID_AA64DFR0_PMSVER_SHIFT, #4
 	cbz	x0, 7f				// Skip if SPE not present
 	cbnz	x2, 6f				// VHE?
 	mrs_s	x4, SYS_PMBIDR_EL1		// If SPE available at EL2,
@@ -684,7 +684,7 @@ ENTRY(__boot_cpu_mode)
  * with MMU turned off.
  */
 ENTRY(__early_cpu_boot_status)
-	.long 	0
+	.quad 	0
 
 	.popsection
 
diff --git a/arch/arm64/kernel/kgdb.c b/arch/arm64/kernel/kgdb.c
index 691854b77c7f..30853d5b7859 100644
--- a/arch/arm64/kernel/kgdb.c
+++ b/arch/arm64/kernel/kgdb.c
@@ -244,9 +244,6 @@ int kgdb_arch_handle_exception(int exception_vector, int signo,
 
 static int kgdb_brk_fn(struct pt_regs *regs, unsigned int esr)
 {
-	if (user_mode(regs))
-		return DBG_HOOK_ERROR;
-
 	kgdb_handle_exception(1, SIGTRAP, 0, regs);
 	return DBG_HOOK_HANDLED;
 }
@@ -254,9 +251,6 @@ NOKPROBE_SYMBOL(kgdb_brk_fn)
 
 static int kgdb_compiled_brk_fn(struct pt_regs *regs, unsigned int esr)
 {
-	if (user_mode(regs))
-		return DBG_HOOK_ERROR;
-
 	compiled_break = 1;
 	kgdb_handle_exception(1, SIGTRAP, 0, regs);
 
@@ -266,7 +260,7 @@ NOKPROBE_SYMBOL(kgdb_compiled_brk_fn);
 
 static int kgdb_step_brk_fn(struct pt_regs *regs, unsigned int esr)
 {
-	if (user_mode(regs) || !kgdb_single_step)
+	if (!kgdb_single_step)
 		return DBG_HOOK_ERROR;
 
 	kgdb_handle_exception(1, SIGTRAP, 0, regs);
@@ -275,15 +269,13 @@ static int kgdb_step_brk_fn(struct pt_regs *regs, unsigned int esr)
 NOKPROBE_SYMBOL(kgdb_step_brk_fn);
 
 static struct break_hook kgdb_brkpt_hook = {
-	.esr_mask	= 0xffffffff,
-	.esr_val	= (u32)ESR_ELx_VAL_BRK64(KGDB_DYN_DBG_BRK_IMM),
-	.fn		= kgdb_brk_fn
+	.fn		= kgdb_brk_fn,
+	.imm		= KGDB_DYN_DBG_BRK_IMM,
 };
 
 static struct break_hook kgdb_compiled_brkpt_hook = {
-	.esr_mask	= 0xffffffff,
-	.esr_val	= (u32)ESR_ELx_VAL_BRK64(KGDB_COMPILED_DBG_BRK_IMM),
-	.fn		= kgdb_compiled_brk_fn
+	.fn		= kgdb_compiled_brk_fn,
+	.imm		= KGDB_COMPILED_DBG_BRK_IMM,
 };
 
 static struct step_hook kgdb_step_hook = {
@@ -332,9 +324,9 @@ int kgdb_arch_init(void)
 	if (ret != 0)
 		return ret;
 
-	register_break_hook(&kgdb_brkpt_hook);
-	register_break_hook(&kgdb_compiled_brkpt_hook);
-	register_step_hook(&kgdb_step_hook);
+	register_kernel_break_hook(&kgdb_brkpt_hook);
+	register_kernel_break_hook(&kgdb_compiled_brkpt_hook);
+	register_kernel_step_hook(&kgdb_step_hook);
 	return 0;
 }
 
@@ -345,9 +337,9 @@ int kgdb_arch_init(void)
  */
 void kgdb_arch_exit(void)
 {
-	unregister_break_hook(&kgdb_brkpt_hook);
-	unregister_break_hook(&kgdb_compiled_brkpt_hook);
-	unregister_step_hook(&kgdb_step_hook);
+	unregister_kernel_break_hook(&kgdb_brkpt_hook);
+	unregister_kernel_break_hook(&kgdb_compiled_brkpt_hook);
+	unregister_kernel_step_hook(&kgdb_step_hook);
 	unregister_die_notifier(&kgdb_notifier);
 }
 
diff --git a/arch/arm64/kernel/kuser32.S b/arch/arm64/kernel/kuser32.S
index 997e6b27ff6a..49825e9e421e 100644
--- a/arch/arm64/kernel/kuser32.S
+++ b/arch/arm64/kernel/kuser32.S
@@ -1,29 +1,14 @@
+/* SPDX-License-Identifier: GPL-2.0 */
 /*
- * Low-level user helpers placed in the vectors page for AArch32.
+ * AArch32 user helpers.
  * Based on the kuser helpers in arch/arm/kernel/entry-armv.S.
  *
  * Copyright (C) 2005-2011 Nicolas Pitre <nico@fluxnic.net>
- * Copyright (C) 2012 ARM Ltd.
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
+ * Copyright (C) 2012-2018 ARM Ltd.
  *
- * You should have received a copy of the GNU General Public License
- * along with this program.  If not, see <http://www.gnu.org/licenses/>.
- *
- *
- * AArch32 user helpers.
- *
- * Each segment is 32-byte aligned and will be moved to the top of the high
- * vector page.  New segments (if ever needed) must be added in front of
- * existing ones.  This mechanism should be used only for things that are
- * really small and justified, and not be abused freely.
+ * The kuser helpers below are mapped at a fixed address by
+ * aarch32_setup_additional_pages() and are provided for compatibility
+ * reasons with 32 bit (aarch32) applications that need them.
  *
  * See Documentation/arm/kernel_user_helpers.txt for formal definitions.
  */
@@ -77,42 +62,3 @@ __kuser_helper_version:			// 0xffff0ffc
 	.word	((__kuser_helper_end - __kuser_helper_start) >> 5)
 	.globl	__kuser_helper_end
 __kuser_helper_end:
-
-/*
- * AArch32 sigreturn code
- *
- * For ARM syscalls, the syscall number has to be loaded into r7.
- * We do not support an OABI userspace.
- *
- * For Thumb syscalls, we also pass the syscall number via r7. We therefore
- * need two 16-bit instructions.
- */
-	.globl __aarch32_sigret_code_start
-__aarch32_sigret_code_start:
-
-	/*
-	 * ARM Code
-	 */
-	.byte	__NR_compat_sigreturn, 0x70, 0xa0, 0xe3	// mov	r7, #__NR_compat_sigreturn
-	.byte	__NR_compat_sigreturn, 0x00, 0x00, 0xef	// svc	#__NR_compat_sigreturn
-
-	/*
-	 * Thumb code
-	 */
-	.byte	__NR_compat_sigreturn, 0x27			// svc	#__NR_compat_sigreturn
-	.byte	__NR_compat_sigreturn, 0xdf			// mov	r7, #__NR_compat_sigreturn
-
-	/*
-	 * ARM code
-	 */
-	.byte	__NR_compat_rt_sigreturn, 0x70, 0xa0, 0xe3	// mov	r7, #__NR_compat_rt_sigreturn
-	.byte	__NR_compat_rt_sigreturn, 0x00, 0x00, 0xef	// svc	#__NR_compat_rt_sigreturn
-
-	/*
-	 * Thumb code
-	 */
-	.byte	__NR_compat_rt_sigreturn, 0x27			// svc	#__NR_compat_rt_sigreturn
-	.byte	__NR_compat_rt_sigreturn, 0xdf			// mov	r7, #__NR_compat_rt_sigreturn
-
-        .globl __aarch32_sigret_code_end
-__aarch32_sigret_code_end:
diff --git a/arch/arm64/kernel/perf_event.c b/arch/arm64/kernel/perf_event.c
index 4addb38bc250..6164d389eed6 100644
--- a/arch/arm64/kernel/perf_event.c
+++ b/arch/arm64/kernel/perf_event.c
@@ -431,7 +431,7 @@ static inline u64 armv8pmu_read_hw_counter(struct perf_event *event)
 	return val;
 }
 
-static inline u64 armv8pmu_read_counter(struct perf_event *event)
+static u64 armv8pmu_read_counter(struct perf_event *event)
 {
 	struct arm_pmu *cpu_pmu = to_arm_pmu(event->pmu);
 	struct hw_perf_event *hwc = &event->hw;
@@ -468,7 +468,7 @@ static inline void armv8pmu_write_hw_counter(struct perf_event *event,
 	}
 }
 
-static inline void armv8pmu_write_counter(struct perf_event *event, u64 value)
+static void armv8pmu_write_counter(struct perf_event *event, u64 value)
 {
 	struct arm_pmu *cpu_pmu = to_arm_pmu(event->pmu);
 	struct hw_perf_event *hwc = &event->hw;
diff --git a/arch/arm64/kernel/probes/kprobes.c b/arch/arm64/kernel/probes/kprobes.c
index 7a679caf4585..2509fcb6d404 100644
--- a/arch/arm64/kernel/probes/kprobes.c
+++ b/arch/arm64/kernel/probes/kprobes.c
@@ -439,15 +439,12 @@ kprobe_ss_hit(struct kprobe_ctlblk *kcb, unsigned long addr)
 	return DBG_HOOK_ERROR;
 }
 
-int __kprobes
+static int __kprobes
 kprobe_single_step_handler(struct pt_regs *regs, unsigned int esr)
 {
 	struct kprobe_ctlblk *kcb = get_kprobe_ctlblk();
 	int retval;
 
-	if (user_mode(regs))
-		return DBG_HOOK_ERROR;
-
 	/* return error if this is not our step */
 	retval = kprobe_ss_hit(kcb, instruction_pointer(regs));
 
@@ -461,16 +458,22 @@ kprobe_single_step_handler(struct pt_regs *regs, unsigned int esr)
 	return retval;
 }
 
-int __kprobes
+static struct step_hook kprobes_step_hook = {
+	.fn = kprobe_single_step_handler,
+};
+
+static int __kprobes
 kprobe_breakpoint_handler(struct pt_regs *regs, unsigned int esr)
 {
-	if (user_mode(regs))
-		return DBG_HOOK_ERROR;
-
 	kprobe_handler(regs);
 	return DBG_HOOK_HANDLED;
 }
 
+static struct break_hook kprobes_break_hook = {
+	.imm = KPROBES_BRK_IMM,
+	.fn = kprobe_breakpoint_handler,
+};
+
 /*
  * Provide a blacklist of symbols identifying ranges which cannot be kprobed.
  * This blacklist is exposed to userspace via debugfs (kprobes/blacklist).
@@ -599,5 +602,8 @@ int __kprobes arch_trampoline_kprobe(struct kprobe *p)
 
 int __init arch_init_kprobes(void)
 {
+	register_kernel_break_hook(&kprobes_break_hook);
+	register_kernel_step_hook(&kprobes_step_hook);
+
 	return 0;
 }
diff --git a/arch/arm64/kernel/probes/uprobes.c b/arch/arm64/kernel/probes/uprobes.c
index 636ca0119c0e..605945eac1f8 100644
--- a/arch/arm64/kernel/probes/uprobes.c
+++ b/arch/arm64/kernel/probes/uprobes.c
@@ -171,7 +171,7 @@ int arch_uprobe_exception_notify(struct notifier_block *self,
 static int uprobe_breakpoint_handler(struct pt_regs *regs,
 		unsigned int esr)
 {
-	if (user_mode(regs) && uprobe_pre_sstep_notifier(regs))
+	if (uprobe_pre_sstep_notifier(regs))
 		return DBG_HOOK_HANDLED;
 
 	return DBG_HOOK_ERROR;
@@ -182,21 +182,16 @@ static int uprobe_single_step_handler(struct pt_regs *regs,
 {
 	struct uprobe_task *utask = current->utask;
 
-	if (user_mode(regs)) {
-		WARN_ON(utask &&
-			(instruction_pointer(regs) != utask->xol_vaddr + 4));
-
-		if (uprobe_post_sstep_notifier(regs))
-			return DBG_HOOK_HANDLED;
-	}
+	WARN_ON(utask && (instruction_pointer(regs) != utask->xol_vaddr + 4));
+	if (uprobe_post_sstep_notifier(regs))
+		return DBG_HOOK_HANDLED;
 
 	return DBG_HOOK_ERROR;
 }
 
 /* uprobe breakpoint handler hook */
 static struct break_hook uprobes_break_hook = {
-	.esr_mask = BRK64_ESR_MASK,
-	.esr_val = BRK64_ESR_UPROBES,
+	.imm = UPROBES_BRK_IMM,
 	.fn = uprobe_breakpoint_handler,
 };
 
@@ -207,8 +202,8 @@ static struct step_hook uprobes_step_hook = {
 
 static int __init arch_init_uprobes(void)
 {
-	register_break_hook(&uprobes_break_hook);
-	register_step_hook(&uprobes_step_hook);
+	register_user_break_hook(&uprobes_break_hook);
+	register_user_step_hook(&uprobes_step_hook);
 
 	return 0;
 }
diff --git a/arch/arm64/kernel/sdei.c b/arch/arm64/kernel/sdei.c
index 5ba4465e44f0..ea94cf8f9dc6 100644
--- a/arch/arm64/kernel/sdei.c
+++ b/arch/arm64/kernel/sdei.c
@@ -94,6 +94,9 @@ static bool on_sdei_normal_stack(unsigned long sp, struct stack_info *info)
 	unsigned long low = (unsigned long)raw_cpu_read(sdei_stack_normal_ptr);
 	unsigned long high = low + SDEI_STACK_SIZE;
 
+	if (!low)
+		return false;
+
 	if (sp < low || sp >= high)
 		return false;
 
@@ -111,6 +114,9 @@ static bool on_sdei_critical_stack(unsigned long sp, struct stack_info *info)
 	unsigned long low = (unsigned long)raw_cpu_read(sdei_stack_critical_ptr);
 	unsigned long high = low + SDEI_STACK_SIZE;
 
+	if (!low)
+		return false;
+
 	if (sp < low || sp >= high)
 		return false;
 
diff --git a/arch/arm64/kernel/setup.c b/arch/arm64/kernel/setup.c
index f8482fe5a190..413d566405d1 100644
--- a/arch/arm64/kernel/setup.c
+++ b/arch/arm64/kernel/setup.c
@@ -217,7 +217,7 @@ static void __init request_standard_resources(void)
 
 	num_standard_resources = memblock.memory.cnt;
 	res_size = num_standard_resources * sizeof(*standard_resources);
-	standard_resources = memblock_alloc_low(res_size, SMP_CACHE_BYTES);
+	standard_resources = memblock_alloc(res_size, SMP_CACHE_BYTES);
 	if (!standard_resources)
 		panic("%s: Failed to allocate %zu bytes\n", __func__, res_size);
 
diff --git a/arch/arm64/kernel/signal32.c b/arch/arm64/kernel/signal32.c
index cb7800acd19f..caea6e25db2a 100644
--- a/arch/arm64/kernel/signal32.c
+++ b/arch/arm64/kernel/signal32.c
@@ -403,8 +403,7 @@ static void compat_setup_return(struct pt_regs *regs, struct k_sigaction *ka,
 		if (ka->sa.sa_flags & SA_SIGINFO)
 			idx += 3;
 
-		retcode = AARCH32_VECTORS_BASE +
-			  AARCH32_KERN_SIGRET_CODE_OFFSET +
+		retcode = (unsigned long)current->mm->context.vdso +
 			  (idx << 2) + thumb;
 	}
 
diff --git a/arch/arm64/kernel/sigreturn32.S b/arch/arm64/kernel/sigreturn32.S
new file mode 100644
index 000000000000..475d30d471ac
--- /dev/null
+++ b/arch/arm64/kernel/sigreturn32.S
@@ -0,0 +1,46 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * AArch32 sigreturn code.
+ * Based on the kuser helpers in arch/arm/kernel/entry-armv.S.
+ *
+ * Copyright (C) 2005-2011 Nicolas Pitre <nico@fluxnic.net>
+ * Copyright (C) 2012-2018 ARM Ltd.
+ *
+ * For ARM syscalls, the syscall number has to be loaded into r7.
+ * We do not support an OABI userspace.
+ *
+ * For Thumb syscalls, we also pass the syscall number via r7. We therefore
+ * need two 16-bit instructions.
+ */
+
+#include <asm/unistd.h>
+
+	.globl __aarch32_sigret_code_start
+__aarch32_sigret_code_start:
+
+	/*
+	 * ARM Code
+	 */
+	.byte	__NR_compat_sigreturn, 0x70, 0xa0, 0xe3		// mov	r7, #__NR_compat_sigreturn
+	.byte	__NR_compat_sigreturn, 0x00, 0x00, 0xef		// svc	#__NR_compat_sigreturn
+
+	/*
+	 * Thumb code
+	 */
+	.byte	__NR_compat_sigreturn, 0x27			// svc	#__NR_compat_sigreturn
+	.byte	__NR_compat_sigreturn, 0xdf			// mov	r7, #__NR_compat_sigreturn
+
+	/*
+	 * ARM code
+	 */
+	.byte	__NR_compat_rt_sigreturn, 0x70, 0xa0, 0xe3	// mov	r7, #__NR_compat_rt_sigreturn
+	.byte	__NR_compat_rt_sigreturn, 0x00, 0x00, 0xef	// svc	#__NR_compat_rt_sigreturn
+
+	/*
+	 * Thumb code
+	 */
+	.byte	__NR_compat_rt_sigreturn, 0x27			// svc	#__NR_compat_rt_sigreturn
+	.byte	__NR_compat_rt_sigreturn, 0xdf			// mov	r7, #__NR_compat_rt_sigreturn
+
+        .globl __aarch32_sigret_code_end
+__aarch32_sigret_code_end:
diff --git a/arch/arm64/kernel/stacktrace.c b/arch/arm64/kernel/stacktrace.c
index d908b5e9e949..b00ec7d483d1 100644
--- a/arch/arm64/kernel/stacktrace.c
+++ b/arch/arm64/kernel/stacktrace.c
@@ -140,8 +140,6 @@ void save_stack_trace_regs(struct pt_regs *regs, struct stack_trace *trace)
 #endif
 
 	walk_stackframe(current, &frame, save_trace, &data);
-	if (trace->nr_entries < trace->max_entries)
-		trace->entries[trace->nr_entries++] = ULONG_MAX;
 }
 EXPORT_SYMBOL_GPL(save_stack_trace_regs);
 
@@ -172,8 +170,6 @@ static noinline void __save_stack_trace(struct task_struct *tsk,
 #endif
 
 	walk_stackframe(tsk, &frame, save_trace, &data);
-	if (trace->nr_entries < trace->max_entries)
-		trace->entries[trace->nr_entries++] = ULONG_MAX;
 
 	put_task_stack(tsk);
 }
diff --git a/arch/arm64/kernel/sys.c b/arch/arm64/kernel/sys.c
index b44065fb1616..6f91e8116514 100644
--- a/arch/arm64/kernel/sys.c
+++ b/arch/arm64/kernel/sys.c
@@ -31,7 +31,7 @@
 
 SYSCALL_DEFINE6(mmap, unsigned long, addr, unsigned long, len,
 		unsigned long, prot, unsigned long, flags,
-		unsigned long, fd, off_t, off)
+		unsigned long, fd, unsigned long, off)
 {
 	if (offset_in_page(off) != 0)
 		return -EINVAL;
diff --git a/arch/arm64/kernel/traps.c b/arch/arm64/kernel/traps.c
index 8ad119c3f665..ade32046f3fe 100644
--- a/arch/arm64/kernel/traps.c
+++ b/arch/arm64/kernel/traps.c
@@ -102,10 +102,16 @@ static void dump_instr(const char *lvl, struct pt_regs *regs)
 void dump_backtrace(struct pt_regs *regs, struct task_struct *tsk)
 {
 	struct stackframe frame;
-	int skip;
+	int skip = 0;
 
 	pr_debug("%s(regs = %p tsk = %p)\n", __func__, regs, tsk);
 
+	if (regs) {
+		if (user_mode(regs))
+			return;
+		skip = 1;
+	}
+
 	if (!tsk)
 		tsk = current;
 
@@ -126,7 +132,6 @@ void dump_backtrace(struct pt_regs *regs, struct task_struct *tsk)
 	frame.graph = 0;
 #endif
 
-	skip = !!regs;
 	printk("Call trace:\n");
 	do {
 		/* skip until specified stack frame */
@@ -176,15 +181,13 @@ static int __die(const char *str, int err, struct pt_regs *regs)
 		return ret;
 
 	print_modules();
-	__show_regs(regs);
 	pr_emerg("Process %.*s (pid: %d, stack limit = 0x%p)\n",
 		 TASK_COMM_LEN, tsk->comm, task_pid_nr(tsk),
 		 end_of_stack(tsk));
+	show_regs(regs);
 
-	if (!user_mode(regs)) {
-		dump_backtrace(regs, tsk);
+	if (!user_mode(regs))
 		dump_instr(KERN_EMERG, regs);
-	}
 
 	return ret;
 }
@@ -459,6 +462,9 @@ static void user_cache_maint_handler(unsigned int esr, struct pt_regs *regs)
 	case ESR_ELx_SYS64_ISS_CRM_DC_CVAC:	/* DC CVAC, gets promoted */
 		__user_cache_maint("dc civac", address, ret);
 		break;
+	case ESR_ELx_SYS64_ISS_CRM_DC_CVADP:	/* DC CVADP */
+		__user_cache_maint("sys 3, c7, c13, 1", address, ret);
+		break;
 	case ESR_ELx_SYS64_ISS_CRM_DC_CVAP:	/* DC CVAP */
 		__user_cache_maint("sys 3, c7, c12, 1", address, ret);
 		break;
@@ -493,7 +499,7 @@ static void cntvct_read_handler(unsigned int esr, struct pt_regs *regs)
 {
 	int rt = ESR_ELx_SYS64_ISS_RT(esr);
 
-	pt_regs_write_reg(regs, rt, arch_counter_get_cntvct());
+	pt_regs_write_reg(regs, rt, arch_timer_read_counter());
 	arm64_skip_faulting_instruction(regs, AARCH64_INSN_SIZE);
 }
 
@@ -665,7 +671,7 @@ static void compat_cntvct_read_handler(unsigned int esr, struct pt_regs *regs)
 {
 	int rt = (esr & ESR_ELx_CP15_64_ISS_RT_MASK) >> ESR_ELx_CP15_64_ISS_RT_SHIFT;
 	int rt2 = (esr & ESR_ELx_CP15_64_ISS_RT2_MASK) >> ESR_ELx_CP15_64_ISS_RT2_SHIFT;
-	u64 val = arch_counter_get_cntvct();
+	u64 val = arch_timer_read_counter();
 
 	pt_regs_write_reg(regs, rt, lower_32_bits(val));
 	pt_regs_write_reg(regs, rt2, upper_32_bits(val));
@@ -947,9 +953,6 @@ int is_valid_bugaddr(unsigned long addr)
 
 static int bug_handler(struct pt_regs *regs, unsigned int esr)
 {
-	if (user_mode(regs))
-		return DBG_HOOK_ERROR;
-
 	switch (report_bug(regs->pc, regs)) {
 	case BUG_TRAP_TYPE_BUG:
 		die("Oops - BUG", regs, 0);
@@ -969,9 +972,8 @@ static int bug_handler(struct pt_regs *regs, unsigned int esr)
 }
 
 static struct break_hook bug_break_hook = {
-	.esr_val = 0xf2000000 | BUG_BRK_IMM,
-	.esr_mask = 0xffffffff,
 	.fn = bug_handler,
+	.imm = BUG_BRK_IMM,
 };
 
 #ifdef CONFIG_KASAN_SW_TAGS
@@ -989,9 +991,6 @@ static int kasan_handler(struct pt_regs *regs, unsigned int esr)
 	u64 addr = regs->regs[0];
 	u64 pc = regs->pc;
 
-	if (user_mode(regs))
-		return DBG_HOOK_ERROR;
-
 	kasan_report(addr, size, write, pc);
 
 	/*
@@ -1016,13 +1015,10 @@ static int kasan_handler(struct pt_regs *regs, unsigned int esr)
 	return DBG_HOOK_HANDLED;
 }
 
-#define KASAN_ESR_VAL (0xf2000000 | KASAN_BRK_IMM)
-#define KASAN_ESR_MASK 0xffffff00
-
 static struct break_hook kasan_break_hook = {
-	.esr_val = KASAN_ESR_VAL,
-	.esr_mask = KASAN_ESR_MASK,
-	.fn = kasan_handler,
+	.fn	= kasan_handler,
+	.imm	= KASAN_BRK_IMM,
+	.mask	= KASAN_BRK_MASK,
 };
 #endif
 
@@ -1034,7 +1030,9 @@ int __init early_brk64(unsigned long addr, unsigned int esr,
 		struct pt_regs *regs)
 {
 #ifdef CONFIG_KASAN_SW_TAGS
-	if ((esr & KASAN_ESR_MASK) == KASAN_ESR_VAL)
+	unsigned int comment = esr & ESR_ELx_BRK64_ISS_COMMENT_MASK;
+
+	if ((comment & ~KASAN_BRK_MASK) == KASAN_BRK_IMM)
 		return kasan_handler(regs, esr) != DBG_HOOK_HANDLED;
 #endif
 	return bug_handler(regs, esr) != DBG_HOOK_HANDLED;
@@ -1043,8 +1041,8 @@ int __init early_brk64(unsigned long addr, unsigned int esr,
 /* This registration must happen early, before debug_traps_init(). */
 void __init trap_init(void)
 {
-	register_break_hook(&bug_break_hook);
+	register_kernel_break_hook(&bug_break_hook);
 #ifdef CONFIG_KASAN_SW_TAGS
-	register_break_hook(&kasan_break_hook);
+	register_kernel_break_hook(&kasan_break_hook);
 #endif
 }
diff --git a/arch/arm64/kernel/vdso.c b/arch/arm64/kernel/vdso.c
index 2d419006ad43..8074cbd3a3a8 100644
--- a/arch/arm64/kernel/vdso.c
+++ b/arch/arm64/kernel/vdso.c
@@ -1,5 +1,5 @@
 /*
- * VDSO implementation for AArch64 and vector page setup for AArch32.
+ * VDSO implementations.
  *
  * Copyright (C) 2012 ARM Limited
  *
@@ -53,61 +53,129 @@ struct vdso_data *vdso_data = &vdso_data_store.data;
 /*
  * Create and map the vectors page for AArch32 tasks.
  */
-static struct page *vectors_page[1] __ro_after_init;
+#define C_VECTORS	0
+#define C_SIGPAGE	1
+#define C_PAGES		(C_SIGPAGE + 1)
+static struct page *aarch32_vdso_pages[C_PAGES] __ro_after_init;
+static const struct vm_special_mapping aarch32_vdso_spec[C_PAGES] = {
+	{
+		.name	= "[vectors]", /* ABI */
+		.pages	= &aarch32_vdso_pages[C_VECTORS],
+	},
+	{
+		.name	= "[sigpage]", /* ABI */
+		.pages	= &aarch32_vdso_pages[C_SIGPAGE],
+	},
+};
 
-static int __init alloc_vectors_page(void)
+static int aarch32_alloc_kuser_vdso_page(void)
 {
 	extern char __kuser_helper_start[], __kuser_helper_end[];
-	extern char __aarch32_sigret_code_start[], __aarch32_sigret_code_end[];
-
 	int kuser_sz = __kuser_helper_end - __kuser_helper_start;
-	int sigret_sz = __aarch32_sigret_code_end - __aarch32_sigret_code_start;
-	unsigned long vpage;
+	unsigned long vdso_page;
 
-	vpage = get_zeroed_page(GFP_ATOMIC);
+	if (!IS_ENABLED(CONFIG_KUSER_HELPERS))
+		return 0;
 
-	if (!vpage)
+	vdso_page = get_zeroed_page(GFP_ATOMIC);
+	if (!vdso_page)
 		return -ENOMEM;
 
-	/* kuser helpers */
-	memcpy((void *)vpage + 0x1000 - kuser_sz, __kuser_helper_start,
-		kuser_sz);
+	memcpy((void *)(vdso_page + 0x1000 - kuser_sz), __kuser_helper_start,
+	       kuser_sz);
+	aarch32_vdso_pages[C_VECTORS] = virt_to_page(vdso_page);
+	flush_dcache_page(aarch32_vdso_pages[C_VECTORS]);
+	return 0;
+}
 
-	/* sigreturn code */
-	memcpy((void *)vpage + AARCH32_KERN_SIGRET_CODE_OFFSET,
-               __aarch32_sigret_code_start, sigret_sz);
+static int __init aarch32_alloc_vdso_pages(void)
+{
+	extern char __aarch32_sigret_code_start[], __aarch32_sigret_code_end[];
+	int sigret_sz = __aarch32_sigret_code_end - __aarch32_sigret_code_start;
+	unsigned long sigpage;
+	int ret;
 
-	flush_icache_range(vpage, vpage + PAGE_SIZE);
-	vectors_page[0] = virt_to_page(vpage);
+	sigpage = get_zeroed_page(GFP_ATOMIC);
+	if (!sigpage)
+		return -ENOMEM;
 
-	return 0;
+	memcpy((void *)sigpage, __aarch32_sigret_code_start, sigret_sz);
+	aarch32_vdso_pages[C_SIGPAGE] = virt_to_page(sigpage);
+	flush_dcache_page(aarch32_vdso_pages[C_SIGPAGE]);
+
+	ret = aarch32_alloc_kuser_vdso_page();
+	if (ret)
+		free_page(sigpage);
+
+	return ret;
 }
-arch_initcall(alloc_vectors_page);
+arch_initcall(aarch32_alloc_vdso_pages);
 
-int aarch32_setup_vectors_page(struct linux_binprm *bprm, int uses_interp)
+static int aarch32_kuser_helpers_setup(struct mm_struct *mm)
 {
-	struct mm_struct *mm = current->mm;
-	unsigned long addr = AARCH32_VECTORS_BASE;
-	static const struct vm_special_mapping spec = {
-		.name	= "[vectors]",
-		.pages	= vectors_page,
+	void *ret;
+
+	if (!IS_ENABLED(CONFIG_KUSER_HELPERS))
+		return 0;
+
+	/*
+	 * Avoid VM_MAYWRITE for compatibility with arch/arm/, where it's
+	 * not safe to CoW the page containing the CPU exception vectors.
+	 */
+	ret = _install_special_mapping(mm, AARCH32_VECTORS_BASE, PAGE_SIZE,
+				       VM_READ | VM_EXEC |
+				       VM_MAYREAD | VM_MAYEXEC,
+				       &aarch32_vdso_spec[C_VECTORS]);
 
-	};
+	return PTR_ERR_OR_ZERO(ret);
+}
+
+static int aarch32_sigreturn_setup(struct mm_struct *mm)
+{
+	unsigned long addr;
 	void *ret;
 
-	if (down_write_killable(&mm->mmap_sem))
-		return -EINTR;
-	current->mm->context.vdso = (void *)addr;
+	addr = get_unmapped_area(NULL, 0, PAGE_SIZE, 0, 0);
+	if (IS_ERR_VALUE(addr)) {
+		ret = ERR_PTR(addr);
+		goto out;
+	}
 
-	/* Map vectors page at the high address. */
+	/*
+	 * VM_MAYWRITE is required to allow gdb to Copy-on-Write and
+	 * set breakpoints.
+	 */
 	ret = _install_special_mapping(mm, addr, PAGE_SIZE,
-				       VM_READ|VM_EXEC|VM_MAYREAD|VM_MAYEXEC,
-				       &spec);
+				       VM_READ | VM_EXEC | VM_MAYREAD |
+				       VM_MAYWRITE | VM_MAYEXEC,
+				       &aarch32_vdso_spec[C_SIGPAGE]);
+	if (IS_ERR(ret))
+		goto out;
 
-	up_write(&mm->mmap_sem);
+	mm->context.vdso = (void *)addr;
 
+out:
 	return PTR_ERR_OR_ZERO(ret);
 }
+
+int aarch32_setup_additional_pages(struct linux_binprm *bprm, int uses_interp)
+{
+	struct mm_struct *mm = current->mm;
+	int ret;
+
+	if (down_write_killable(&mm->mmap_sem))
+		return -EINTR;
+
+	ret = aarch32_kuser_helpers_setup(mm);
+	if (ret)
+		goto out;
+
+	ret = aarch32_sigreturn_setup(mm);
+
+out:
+	up_write(&mm->mmap_sem);
+	return ret;
+}
 #endif /* CONFIG_COMPAT */
 
 static int vdso_mremap(const struct vm_special_mapping *sm,
@@ -146,8 +214,6 @@ static int __init vdso_init(void)
 	}
 
 	vdso_pages = (vdso_end - vdso_start) >> PAGE_SHIFT;
-	pr_info("vdso: %ld pages (%ld code @ %p, %ld data @ %p)\n",
-		vdso_pages + 1, vdso_pages, vdso_start, 1L, vdso_data);
 
 	/* Allocate the vDSO pagelist, plus a page for the data. */
 	vdso_pagelist = kcalloc(vdso_pages + 1, sizeof(struct page *),
@@ -232,6 +298,9 @@ void update_vsyscall(struct timekeeper *tk)
 	vdso_data->wtm_clock_sec		= tk->wall_to_monotonic.tv_sec;
 	vdso_data->wtm_clock_nsec		= tk->wall_to_monotonic.tv_nsec;
 
+	/* Read without the seqlock held by clock_getres() */
+	WRITE_ONCE(vdso_data->hrtimer_res, hrtimer_resolution);
+
 	if (!use_syscall) {
 		/* tkr_mono.cycle_last == tkr_raw.cycle_last */
 		vdso_data->cs_cycle_last	= tk->tkr_mono.cycle_last;
diff --git a/arch/arm64/kernel/vdso/Makefile b/arch/arm64/kernel/vdso/Makefile
index b215c712d897..744b9dbaba03 100644
--- a/arch/arm64/kernel/vdso/Makefile
+++ b/arch/arm64/kernel/vdso/Makefile
@@ -12,17 +12,12 @@ obj-vdso := gettimeofday.o note.o sigreturn.o
 targets := $(obj-vdso) vdso.so vdso.so.dbg
 obj-vdso := $(addprefix $(obj)/, $(obj-vdso))
 
-ccflags-y := -shared -fno-common -fno-builtin
-ccflags-y += -nostdlib -Wl,-soname=linux-vdso.so.1 \
-		$(call cc-ldoption, -Wl$(comma)--hash-style=sysv)
+ldflags-y := -shared -nostdlib -soname=linux-vdso.so.1 \
+		$(call ld-option, --hash-style=sysv) -n -T
 
 # Disable gcov profiling for VDSO code
 GCOV_PROFILE := n
 
-# Workaround for bare-metal (ELF) toolchains that neglect to pass -shared
-# down to collect2, resulting in silent corruption of the vDSO image.
-ccflags-y += -Wl,-shared
-
 obj-y += vdso.o
 extra-y += vdso.lds
 CPPFLAGS_vdso.lds += -P -C -U$(ARCH)
@@ -31,8 +26,8 @@ CPPFLAGS_vdso.lds += -P -C -U$(ARCH)
 $(obj)/vdso.o : $(obj)/vdso.so
 
 # Link rule for the .so file, .lds has to be first
-$(obj)/vdso.so.dbg: $(src)/vdso.lds $(obj-vdso)
-	$(call if_changed,vdsold)
+$(obj)/vdso.so.dbg: $(obj)/vdso.lds $(obj-vdso) FORCE
+	$(call if_changed,ld)
 
 # Strip rule for the .so file
 $(obj)/%.so: OBJCOPYFLAGS := -S
@@ -42,9 +37,7 @@ $(obj)/%.so: $(obj)/%.so.dbg FORCE
 # Generate VDSO offsets using helper script
 gen-vdsosym := $(srctree)/$(src)/gen_vdso_offsets.sh
 quiet_cmd_vdsosym = VDSOSYM $@
-define cmd_vdsosym
-	$(NM) $< | $(gen-vdsosym) | LC_ALL=C sort > $@
-endef
+      cmd_vdsosym = $(NM) $< | $(gen-vdsosym) | LC_ALL=C sort > $@
 
 include/generated/vdso-offsets.h: $(obj)/vdso.so.dbg FORCE
 	$(call if_changed,vdsosym)
@@ -54,8 +47,6 @@ $(obj-vdso): %.o: %.S FORCE
 	$(call if_changed_dep,vdsoas)
 
 # Actual build commands
-quiet_cmd_vdsold = VDSOL   $@
-      cmd_vdsold = $(CC) $(c_flags) -Wl,-n -Wl,-T $^ -o $@
 quiet_cmd_vdsoas = VDSOA   $@
       cmd_vdsoas = $(CC) $(a_flags) -c -o $@ $<
 
diff --git a/arch/arm64/kernel/vdso/gettimeofday.S b/arch/arm64/kernel/vdso/gettimeofday.S
index c39872a7b03c..856fee6d3512 100644
--- a/arch/arm64/kernel/vdso/gettimeofday.S
+++ b/arch/arm64/kernel/vdso/gettimeofday.S
@@ -73,6 +73,13 @@ x_tmp		.req	x8
 	movn	x_tmp, #0xff00, lsl #48
 	and	\res, x_tmp, \res
 	mul	\res, \res, \mult
+	/*
+	 * Fake address dependency from the value computed from the counter
+	 * register to subsequent data page accesses so that the sequence
+	 * locking also orders the read of the counter.
+	 */
+	and	x_tmp, \res, xzr
+	add	vdso_data, vdso_data, x_tmp
 	.endm
 
 	/*
@@ -147,12 +154,12 @@ ENTRY(__kernel_gettimeofday)
 	/* w11 = cs_mono_mult, w12 = cs_shift */
 	ldp	w11, w12, [vdso_data, #VDSO_CS_MONO_MULT]
 	ldp	x13, x14, [vdso_data, #VDSO_XTIME_CLK_SEC]
-	seqcnt_check fail=1b
 
 	get_nsec_per_sec res=x9
 	lsl	x9, x9, x12
 
 	get_clock_shifted_nsec res=x15, cycle_last=x10, mult=x11
+	seqcnt_check fail=1b
 	get_ts_realtime res_sec=x10, res_nsec=x11, \
 		clock_nsec=x15, xtime_sec=x13, xtime_nsec=x14, nsec_to_sec=x9
 
@@ -211,13 +218,13 @@ realtime:
 	/* w11 = cs_mono_mult, w12 = cs_shift */
 	ldp	w11, w12, [vdso_data, #VDSO_CS_MONO_MULT]
 	ldp	x13, x14, [vdso_data, #VDSO_XTIME_CLK_SEC]
-	seqcnt_check fail=realtime
 
 	/* All computations are done with left-shifted nsecs. */
 	get_nsec_per_sec res=x9
 	lsl	x9, x9, x12
 
 	get_clock_shifted_nsec res=x15, cycle_last=x10, mult=x11
+	seqcnt_check fail=realtime
 	get_ts_realtime res_sec=x10, res_nsec=x11, \
 		clock_nsec=x15, xtime_sec=x13, xtime_nsec=x14, nsec_to_sec=x9
 	clock_gettime_return, shift=1
@@ -231,7 +238,6 @@ monotonic:
 	ldp	w11, w12, [vdso_data, #VDSO_CS_MONO_MULT]
 	ldp	x13, x14, [vdso_data, #VDSO_XTIME_CLK_SEC]
 	ldp	x3, x4, [vdso_data, #VDSO_WTM_CLK_SEC]
-	seqcnt_check fail=monotonic
 
 	/* All computations are done with left-shifted nsecs. */
 	lsl	x4, x4, x12
@@ -239,6 +245,7 @@ monotonic:
 	lsl	x9, x9, x12
 
 	get_clock_shifted_nsec res=x15, cycle_last=x10, mult=x11
+	seqcnt_check fail=monotonic
 	get_ts_realtime res_sec=x10, res_nsec=x11, \
 		clock_nsec=x15, xtime_sec=x13, xtime_nsec=x14, nsec_to_sec=x9
 
@@ -253,13 +260,13 @@ monotonic_raw:
 	/* w11 = cs_raw_mult, w12 = cs_shift */
 	ldp	w12, w11, [vdso_data, #VDSO_CS_SHIFT]
 	ldp	x13, x14, [vdso_data, #VDSO_RAW_TIME_SEC]
-	seqcnt_check fail=monotonic_raw
 
 	/* All computations are done with left-shifted nsecs. */
 	get_nsec_per_sec res=x9
 	lsl	x9, x9, x12
 
 	get_clock_shifted_nsec res=x15, cycle_last=x10, mult=x11
+	seqcnt_check fail=monotonic_raw
 	get_ts_clock_raw res_sec=x10, res_nsec=x11, \
 		clock_nsec=x15, nsec_to_sec=x9
 
@@ -301,13 +308,14 @@ ENTRY(__kernel_clock_getres)
 	ccmp	w0, #CLOCK_MONOTONIC_RAW, #0x4, ne
 	b.ne	1f
 
-	ldr	x2, 5f
+	adr	vdso_data, _vdso_data
+	ldr	w2, [vdso_data, #CLOCK_REALTIME_RES]
 	b	2f
 1:
 	cmp	w0, #CLOCK_REALTIME_COARSE
 	ccmp	w0, #CLOCK_MONOTONIC_COARSE, #0x4, ne
 	b.ne	4f
-	ldr	x2, 6f
+	ldr	x2, 5f
 2:
 	cbz	x1, 3f
 	stp	xzr, x2, [x1]
@@ -321,8 +329,6 @@ ENTRY(__kernel_clock_getres)
 	svc	#0
 	ret
 5:
-	.quad	CLOCK_REALTIME_RES
-6:
 	.quad	CLOCK_COARSE_RES
 	.cfi_endproc
 ENDPROC(__kernel_clock_getres)
diff --git a/arch/arm64/kvm/reset.c b/arch/arm64/kvm/reset.c
index f16a5f8ff2b4..e2a0500cd7a2 100644
--- a/arch/arm64/kvm/reset.c
+++ b/arch/arm64/kvm/reset.c
@@ -123,6 +123,9 @@ int kvm_reset_vcpu(struct kvm_vcpu *vcpu)
 	int ret = -EINVAL;
 	bool loaded;
 
+	/* Reset PMU outside of the non-preemptible section */
+	kvm_pmu_vcpu_reset(vcpu);
+
 	preempt_disable();
 	loaded = (vcpu->cpu != -1);
 	if (loaded)
@@ -170,9 +173,6 @@ int kvm_reset_vcpu(struct kvm_vcpu *vcpu)
 		vcpu->arch.reset_state.reset = false;
 	}
 
-	/* Reset PMU */
-	kvm_pmu_vcpu_reset(vcpu);
-
 	/* Default workaround setup is enabled (if supported) */
 	if (kvm_arm_have_ssbd() == KVM_SSBD_KERNEL)
 		vcpu->arch.workaround_flags |= VCPU_WORKAROUND_2_FLAG;
diff --git a/arch/arm64/lib/Makefile b/arch/arm64/lib/Makefile
index 5540a1638baf..33c2a4abda04 100644
--- a/arch/arm64/lib/Makefile
+++ b/arch/arm64/lib/Makefile
@@ -24,7 +24,7 @@ CFLAGS_atomic_ll_sc.o	:= -ffixed-x1 -ffixed-x2        		\
 		   -fcall-saved-x10 -fcall-saved-x11 -fcall-saved-x12	\
 		   -fcall-saved-x13 -fcall-saved-x14 -fcall-saved-x15	\
 		   -fcall-saved-x18 -fomit-frame-pointer
-CFLAGS_REMOVE_atomic_ll_sc.o := -pg
+CFLAGS_REMOVE_atomic_ll_sc.o := $(CC_FLAGS_FTRACE)
 GCOV_PROFILE_atomic_ll_sc.o	:= n
 KASAN_SANITIZE_atomic_ll_sc.o	:= n
 KCOV_INSTRUMENT_atomic_ll_sc.o	:= n
diff --git a/arch/arm64/mm/fault.c b/arch/arm64/mm/fault.c
index 1a7e92ab69eb..0cb0e09995e1 100644
--- a/arch/arm64/mm/fault.c
+++ b/arch/arm64/mm/fault.c
@@ -148,7 +148,7 @@ static inline bool is_ttbr1_addr(unsigned long addr)
 /*
  * Dump out the page tables associated with 'addr' in the currently active mm.
  */
-void show_pte(unsigned long addr)
+static void show_pte(unsigned long addr)
 {
 	struct mm_struct *mm;
 	pgd_t *pgdp;
@@ -810,13 +810,12 @@ void __init hook_debug_fault_code(int nr,
 	debug_fault_info[nr].name	= name;
 }
 
-asmlinkage int __exception do_debug_exception(unsigned long addr_if_watchpoint,
-					      unsigned int esr,
-					      struct pt_regs *regs)
+asmlinkage void __exception do_debug_exception(unsigned long addr_if_watchpoint,
+					       unsigned int esr,
+					       struct pt_regs *regs)
 {
 	const struct fault_info *inf = esr_to_debug_fault_info(esr);
 	unsigned long pc = instruction_pointer(regs);
-	int rv;
 
 	/*
 	 * Tell lockdep we disabled irqs in entry.S. Do nothing if they were
@@ -828,17 +827,12 @@ asmlinkage int __exception do_debug_exception(unsigned long addr_if_watchpoint,
 	if (user_mode(regs) && !is_ttbr0_addr(pc))
 		arm64_apply_bp_hardening();
 
-	if (!inf->fn(addr_if_watchpoint, esr, regs)) {
-		rv = 1;
-	} else {
+	if (inf->fn(addr_if_watchpoint, esr, regs)) {
 		arm64_notify_die(inf->name, regs,
 				 inf->sig, inf->code, (void __user *)pc, esr);
-		rv = 0;
 	}
 
 	if (interrupts_enabled(regs))
 		trace_hardirqs_on();
-
-	return rv;
 }
 NOKPROBE_SYMBOL(do_debug_exception);
diff --git a/arch/arm64/mm/init.c b/arch/arm64/mm/init.c
index 6bc135042f5e..40e2d7e5efcb 100644
--- a/arch/arm64/mm/init.c
+++ b/arch/arm64/mm/init.c
@@ -363,7 +363,7 @@ void __init arm64_memblock_init(void)
 		 * Otherwise, this is a no-op
 		 */
 		u64 base = phys_initrd_start & PAGE_MASK;
-		u64 size = PAGE_ALIGN(phys_initrd_size);
+		u64 size = PAGE_ALIGN(phys_initrd_start + phys_initrd_size) - base;
 
 		/*
 		 * We can only add back the initrd memory if we don't end up
@@ -377,7 +377,7 @@ void __init arm64_memblock_init(void)
 			 base + size > memblock_start_of_DRAM() +
 				       linear_region_size,
 			"initrd not fully accessible via the linear mapping -- please check your bootloader ...\n")) {
-			initrd_start = 0;
+			phys_initrd_size = 0;
 		} else {
 			memblock_remove(base, size); /* clear MEMBLOCK_ flags */
 			memblock_add(base, size);
@@ -440,6 +440,7 @@ void __init bootmem_init(void)
 	early_memtest(min << PAGE_SHIFT, max << PAGE_SHIFT);
 
 	max_pfn = max_low_pfn = max;
+	min_low_pfn = min;
 
 	arm64_numa_init();
 	/*
@@ -535,7 +536,7 @@ void __init mem_init(void)
 	else
 		swiotlb_force = SWIOTLB_NO_FORCE;
 
-	set_max_mapnr(pfn_to_page(max_pfn) - mem_map);
+	set_max_mapnr(max_pfn - PHYS_PFN_OFFSET);
 
 #ifndef CONFIG_SPARSEMEM_VMEMMAP
 	free_unused_memmap();
diff --git a/arch/arm64/mm/mmu.c b/arch/arm64/mm/mmu.c
index e97f018ff740..ef82312860ac 100644
--- a/arch/arm64/mm/mmu.c
+++ b/arch/arm64/mm/mmu.c
@@ -97,7 +97,7 @@ pgprot_t phys_mem_access_prot(struct file *file, unsigned long pfn,
 }
 EXPORT_SYMBOL(phys_mem_access_prot);
 
-static phys_addr_t __init early_pgtable_alloc(void)
+static phys_addr_t __init early_pgtable_alloc(int shift)
 {
 	phys_addr_t phys;
 	void *ptr;
@@ -174,7 +174,7 @@ static void init_pte(pmd_t *pmdp, unsigned long addr, unsigned long end,
 static void alloc_init_cont_pte(pmd_t *pmdp, unsigned long addr,
 				unsigned long end, phys_addr_t phys,
 				pgprot_t prot,
-				phys_addr_t (*pgtable_alloc)(void),
+				phys_addr_t (*pgtable_alloc)(int),
 				int flags)
 {
 	unsigned long next;
@@ -184,7 +184,7 @@ static void alloc_init_cont_pte(pmd_t *pmdp, unsigned long addr,
 	if (pmd_none(pmd)) {
 		phys_addr_t pte_phys;
 		BUG_ON(!pgtable_alloc);
-		pte_phys = pgtable_alloc();
+		pte_phys = pgtable_alloc(PAGE_SHIFT);
 		__pmd_populate(pmdp, pte_phys, PMD_TYPE_TABLE);
 		pmd = READ_ONCE(*pmdp);
 	}
@@ -208,7 +208,7 @@ static void alloc_init_cont_pte(pmd_t *pmdp, unsigned long addr,
 
 static void init_pmd(pud_t *pudp, unsigned long addr, unsigned long end,
 		     phys_addr_t phys, pgprot_t prot,
-		     phys_addr_t (*pgtable_alloc)(void), int flags)
+		     phys_addr_t (*pgtable_alloc)(int), int flags)
 {
 	unsigned long next;
 	pmd_t *pmdp;
@@ -246,7 +246,7 @@ static void init_pmd(pud_t *pudp, unsigned long addr, unsigned long end,
 static void alloc_init_cont_pmd(pud_t *pudp, unsigned long addr,
 				unsigned long end, phys_addr_t phys,
 				pgprot_t prot,
-				phys_addr_t (*pgtable_alloc)(void), int flags)
+				phys_addr_t (*pgtable_alloc)(int), int flags)
 {
 	unsigned long next;
 	pud_t pud = READ_ONCE(*pudp);
@@ -258,7 +258,7 @@ static void alloc_init_cont_pmd(pud_t *pudp, unsigned long addr,
 	if (pud_none(pud)) {
 		phys_addr_t pmd_phys;
 		BUG_ON(!pgtable_alloc);
-		pmd_phys = pgtable_alloc();
+		pmd_phys = pgtable_alloc(PMD_SHIFT);
 		__pud_populate(pudp, pmd_phys, PUD_TYPE_TABLE);
 		pud = READ_ONCE(*pudp);
 	}
@@ -294,7 +294,7 @@ static inline bool use_1G_block(unsigned long addr, unsigned long next,
 
 static void alloc_init_pud(pgd_t *pgdp, unsigned long addr, unsigned long end,
 			   phys_addr_t phys, pgprot_t prot,
-			   phys_addr_t (*pgtable_alloc)(void),
+			   phys_addr_t (*pgtable_alloc)(int),
 			   int flags)
 {
 	unsigned long next;
@@ -304,7 +304,7 @@ static void alloc_init_pud(pgd_t *pgdp, unsigned long addr, unsigned long end,
 	if (pgd_none(pgd)) {
 		phys_addr_t pud_phys;
 		BUG_ON(!pgtable_alloc);
-		pud_phys = pgtable_alloc();
+		pud_phys = pgtable_alloc(PUD_SHIFT);
 		__pgd_populate(pgdp, pud_phys, PUD_TYPE_TABLE);
 		pgd = READ_ONCE(*pgdp);
 	}
@@ -345,7 +345,7 @@ static void alloc_init_pud(pgd_t *pgdp, unsigned long addr, unsigned long end,
 static void __create_pgd_mapping(pgd_t *pgdir, phys_addr_t phys,
 				 unsigned long virt, phys_addr_t size,
 				 pgprot_t prot,
-				 phys_addr_t (*pgtable_alloc)(void),
+				 phys_addr_t (*pgtable_alloc)(int),
 				 int flags)
 {
 	unsigned long addr, length, end, next;
@@ -371,17 +371,36 @@ static void __create_pgd_mapping(pgd_t *pgdir, phys_addr_t phys,
 	} while (pgdp++, addr = next, addr != end);
 }
 
-static phys_addr_t pgd_pgtable_alloc(void)
+static phys_addr_t __pgd_pgtable_alloc(int shift)
 {
 	void *ptr = (void *)__get_free_page(PGALLOC_GFP);
-	if (!ptr || !pgtable_page_ctor(virt_to_page(ptr)))
-		BUG();
+	BUG_ON(!ptr);
 
 	/* Ensure the zeroed page is visible to the page table walker */
 	dsb(ishst);
 	return __pa(ptr);
 }
 
+static phys_addr_t pgd_pgtable_alloc(int shift)
+{
+	phys_addr_t pa = __pgd_pgtable_alloc(shift);
+
+	/*
+	 * Call proper page table ctor in case later we need to
+	 * call core mm functions like apply_to_page_range() on
+	 * this pre-allocated page table.
+	 *
+	 * We don't select ARCH_ENABLE_SPLIT_PMD_PTLOCK if pmd is
+	 * folded, and if so pgtable_pmd_page_ctor() becomes nop.
+	 */
+	if (shift == PAGE_SHIFT)
+		BUG_ON(!pgtable_page_ctor(phys_to_page(pa)));
+	else if (shift == PMD_SHIFT)
+		BUG_ON(!pgtable_pmd_page_ctor(phys_to_page(pa)));
+
+	return pa;
+}
+
 /*
  * This function can only be used to modify existing table entries,
  * without allocating new levels of table. Note that this permits the
@@ -583,7 +602,7 @@ static int __init map_entry_trampoline(void)
 	/* Map only the text into the trampoline page table */
 	memset(tramp_pg_dir, 0, PGD_SIZE);
 	__create_pgd_mapping(tramp_pg_dir, pa_start, TRAMP_VALIAS, PAGE_SIZE,
-			     prot, pgd_pgtable_alloc, 0);
+			     prot, __pgd_pgtable_alloc, 0);
 
 	/* Map both the text and data into the kernel page table */
 	__set_fixmap(FIX_ENTRY_TRAMP_TEXT, pa_start, prot);
@@ -1055,7 +1074,7 @@ int arch_add_memory(int nid, u64 start, u64 size, struct vmem_altmap *altmap,
 		flags = NO_BLOCK_MAPPINGS | NO_CONT_MAPPINGS;
 
 	__create_pgd_mapping(swapper_pg_dir, start, __phys_to_virt(start),
-			     size, PAGE_KERNEL, pgd_pgtable_alloc, flags);
+			     size, PAGE_KERNEL, __pgd_pgtable_alloc, flags);
 
 	return __add_pages(nid, start >> PAGE_SHIFT, size >> PAGE_SHIFT,
 			   altmap, want_memblock);
diff --git a/arch/arm64/mm/numa.c b/arch/arm64/mm/numa.c
index 06a6f264f2dd..5202f63c29c9 100644
--- a/arch/arm64/mm/numa.c
+++ b/arch/arm64/mm/numa.c
@@ -124,7 +124,7 @@ static void __init setup_node_to_cpumask_map(void)
 }
 
 /*
- *  Set the cpu to node and mem mapping
+ * Set the cpu to node and mem mapping
  */
 void numa_store_cpu_info(unsigned int cpu)
 {
@@ -200,7 +200,7 @@ void __init setup_per_cpu_areas(void)
 #endif
 
 /**
- * numa_add_memblk - Set node id to memblk
+ * numa_add_memblk() - Set node id to memblk
  * @nid: NUMA node ID of the new memblk
  * @start: Start address of the new memblk
  * @end:  End address of the new memblk
@@ -223,7 +223,7 @@ int __init numa_add_memblk(int nid, u64 start, u64 end)
 	return ret;
 }
 
-/**
+/*
  * Initialize NODE_DATA for a node on the local memory
  */
 static void __init setup_node_data(int nid, u64 start_pfn, u64 end_pfn)
@@ -257,7 +257,7 @@ static void __init setup_node_data(int nid, u64 start_pfn, u64 end_pfn)
 	NODE_DATA(nid)->node_spanned_pages = end_pfn - start_pfn;
 }
 
-/**
+/*
  * numa_free_distance
  *
  * The current table is freed.
@@ -277,10 +277,8 @@ void __init numa_free_distance(void)
 	numa_distance = NULL;
 }
 
-/**
- *
+/*
  * Create a new NUMA distance table.
- *
  */
 static int __init numa_alloc_distance(void)
 {
@@ -311,7 +309,7 @@ static int __init numa_alloc_distance(void)
 }
 
 /**
- * numa_set_distance - Set inter node NUMA distance from node to node.
+ * numa_set_distance() - Set inter node NUMA distance from node to node.
  * @from: the 'from' node to set distance
  * @to: the 'to'  node to set distance
  * @distance: NUMA distance
@@ -321,7 +319,6 @@ static int __init numa_alloc_distance(void)
  *
  * If @from or @to is higher than the highest known node or lower than zero
  * or @distance doesn't make sense, the call is ignored.
- *
  */
 void __init numa_set_distance(int from, int to, int distance)
 {
@@ -347,7 +344,7 @@ void __init numa_set_distance(int from, int to, int distance)
 	numa_distance[from * numa_distance_cnt + to] = distance;
 }
 
-/**
+/*
  * Return NUMA distance @from to @to
  */
 int __node_distance(int from, int to)
@@ -422,13 +419,15 @@ out_free_distance:
 }
 
 /**
- * dummy_numa_init - Fallback dummy NUMA init
+ * dummy_numa_init() - Fallback dummy NUMA init
  *
  * Used if there's no underlying NUMA architecture, NUMA initialization
  * fails, or NUMA is disabled on the command line.
  *
  * Must online at least one node (node 0) and add memory blocks that cover all
  * allowed memory. It is unlikely that this function fails.
+ *
+ * Return: 0 on success, -errno on failure.
  */
 static int __init dummy_numa_init(void)
 {
@@ -454,9 +453,9 @@ static int __init dummy_numa_init(void)
 }
 
 /**
- * arm64_numa_init - Initialize NUMA
+ * arm64_numa_init() - Initialize NUMA
  *
- * Try each configured NUMA initialization method until one succeeds.  The
+ * Try each configured NUMA initialization method until one succeeds. The
  * last fallback is dummy single node config encomapssing whole memory.
  */
 void __init arm64_numa_init(void)
diff --git a/arch/arm64/mm/proc.S b/arch/arm64/mm/proc.S
index aa0817c9c4c3..fdd626d34274 100644
--- a/arch/arm64/mm/proc.S
+++ b/arch/arm64/mm/proc.S
@@ -65,24 +65,25 @@ ENTRY(cpu_do_suspend)
 	mrs	x2, tpidr_el0
 	mrs	x3, tpidrro_el0
 	mrs	x4, contextidr_el1
-	mrs	x5, cpacr_el1
-	mrs	x6, tcr_el1
-	mrs	x7, vbar_el1
-	mrs	x8, mdscr_el1
-	mrs	x9, oslsr_el1
-	mrs	x10, sctlr_el1
+	mrs	x5, osdlr_el1
+	mrs	x6, cpacr_el1
+	mrs	x7, tcr_el1
+	mrs	x8, vbar_el1
+	mrs	x9, mdscr_el1
+	mrs	x10, oslsr_el1
+	mrs	x11, sctlr_el1
 alternative_if_not ARM64_HAS_VIRT_HOST_EXTN
-	mrs	x11, tpidr_el1
+	mrs	x12, tpidr_el1
 alternative_else
-	mrs	x11, tpidr_el2
+	mrs	x12, tpidr_el2
 alternative_endif
-	mrs	x12, sp_el0
+	mrs	x13, sp_el0
 	stp	x2, x3, [x0]
-	stp	x4, xzr, [x0, #16]
-	stp	x5, x6, [x0, #32]
-	stp	x7, x8, [x0, #48]
-	stp	x9, x10, [x0, #64]
-	stp	x11, x12, [x0, #80]
+	stp	x4, x5, [x0, #16]
+	stp	x6, x7, [x0, #32]
+	stp	x8, x9, [x0, #48]
+	stp	x10, x11, [x0, #64]
+	stp	x12, x13, [x0, #80]
 	ret
 ENDPROC(cpu_do_suspend)
 
@@ -105,8 +106,8 @@ ENTRY(cpu_do_resume)
 	msr	cpacr_el1, x6
 
 	/* Don't change t0sz here, mask those bits when restoring */
-	mrs	x5, tcr_el1
-	bfi	x8, x5, TCR_T0SZ_OFFSET, TCR_TxSZ_WIDTH
+	mrs	x7, tcr_el1
+	bfi	x8, x7, TCR_T0SZ_OFFSET, TCR_TxSZ_WIDTH
 
 	msr	tcr_el1, x8
 	msr	vbar_el1, x9
@@ -130,6 +131,7 @@ alternative_endif
 	/*
 	 * Restore oslsr_el1 by writing oslar_el1
 	 */
+	msr	osdlr_el1, x5
 	ubfx	x11, x11, #1, #1
 	msr	oslar_el1, x11
 	reset_pmuserenr_el0 x0			// Disable PMU access from EL0
diff --git a/arch/c6x/Kconfig b/arch/c6x/Kconfig
index e5cd3c5f8399..eeb0471268a0 100644
--- a/arch/c6x/Kconfig
+++ b/arch/c6x/Kconfig
@@ -20,6 +20,7 @@ config C6X
 	select GENERIC_CLOCKEVENTS
 	select MODULES_USE_ELF_RELA
 	select ARCH_NO_COHERENT_DMA_MMAP
+	select MMU_GATHER_NO_RANGE if MMU
 
 config MMU
 	def_bool n
@@ -27,9 +28,6 @@ config MMU
 config FPU
 	def_bool n
 
-config RWSEM_GENERIC_SPINLOCK
-	def_bool y
-
 config GENERIC_CALIBRATE_DELAY
 	def_bool y
 
diff --git a/arch/c6x/include/asm/Kbuild b/arch/c6x/include/asm/Kbuild
index 63b4a1705182..6b168d32fbff 100644
--- a/arch/c6x/include/asm/Kbuild
+++ b/arch/c6x/include/asm/Kbuild
@@ -19,9 +19,11 @@ generic-y += irq_work.h
 generic-y += kdebug.h
 generic-y += kmap_types.h
 generic-y += kprobes.h
+generic-y += kvm_para.h
 generic-y += local.h
 generic-y += mcs_spinlock.h
 generic-y += mm-arch-hooks.h
+generic-y += mmiowb.h
 generic-y += mmu.h
 generic-y += mmu_context.h
 generic-y += pci.h
diff --git a/arch/c6x/include/asm/syscall.h b/arch/c6x/include/asm/syscall.h
index ae2be315ee9c..15ba8599858e 100644
--- a/arch/c6x/include/asm/syscall.h
+++ b/arch/c6x/include/asm/syscall.h
@@ -46,78 +46,27 @@ static inline void syscall_set_return_value(struct task_struct *task,
 }
 
 static inline void syscall_get_arguments(struct task_struct *task,
-					 struct pt_regs *regs, unsigned int i,
-					 unsigned int n, unsigned long *args)
+					 struct pt_regs *regs,
+					 unsigned long *args)
 {
-	switch (i) {
-	case 0:
-		if (!n--)
-			break;
-		*args++ = regs->a4;
-	case 1:
-		if (!n--)
-			break;
-		*args++ = regs->b4;
-	case 2:
-		if (!n--)
-			break;
-		*args++ = regs->a6;
-	case 3:
-		if (!n--)
-			break;
-		*args++ = regs->b6;
-	case 4:
-		if (!n--)
-			break;
-		*args++ = regs->a8;
-	case 5:
-		if (!n--)
-			break;
-		*args++ = regs->b8;
-	case 6:
-		if (!n--)
-			break;
-	default:
-		BUG();
-	}
+	*args++ = regs->a4;
+	*args++ = regs->b4;
+	*args++ = regs->a6;
+	*args++ = regs->b6;
+	*args++ = regs->a8;
+	*args   = regs->b8;
 }
 
 static inline void syscall_set_arguments(struct task_struct *task,
 					 struct pt_regs *regs,
-					 unsigned int i, unsigned int n,
 					 const unsigned long *args)
 {
-	switch (i) {
-	case 0:
-		if (!n--)
-			break;
-		regs->a4 = *args++;
-	case 1:
-		if (!n--)
-			break;
-		regs->b4 = *args++;
-	case 2:
-		if (!n--)
-			break;
-		regs->a6 = *args++;
-	case 3:
-		if (!n--)
-			break;
-		regs->b6 = *args++;
-	case 4:
-		if (!n--)
-			break;
-		regs->a8 = *args++;
-	case 5:
-		if (!n--)
-			break;
-		regs->a9 = *args++;
-	case 6:
-		if (!n)
-			break;
-	default:
-		BUG();
-	}
+	regs->a4 = *args++;
+	regs->b4 = *args++;
+	regs->a6 = *args++;
+	regs->b6 = *args++;
+	regs->a8 = *args++;
+	regs->a9 = *args;
 }
 
 #endif /* __ASM_C6X_SYSCALLS_H */
diff --git a/arch/c6x/include/asm/tlb.h b/arch/c6x/include/asm/tlb.h
index 34525dea1356..240ba0febb57 100644
--- a/arch/c6x/include/asm/tlb.h
+++ b/arch/c6x/include/asm/tlb.h
@@ -2,8 +2,6 @@
 #ifndef _ASM_C6X_TLB_H
 #define _ASM_C6X_TLB_H
 
-#define tlb_flush(tlb) flush_tlb_mm((tlb)->mm)
-
 #include <asm-generic/tlb.h>
 
 #endif /* _ASM_C6X_TLB_H */
diff --git a/arch/c6x/include/uapi/asm/Kbuild b/arch/c6x/include/uapi/asm/Kbuild
index 755bb11323d8..1c72f04ff75d 100644
--- a/arch/c6x/include/uapi/asm/Kbuild
+++ b/arch/c6x/include/uapi/asm/Kbuild
@@ -1,2 +1 @@
-generic-y += kvm_para.h
 generic-y += ucontext.h
diff --git a/arch/csky/Kconfig b/arch/csky/Kconfig
index 725a115759c9..6555d1781132 100644
--- a/arch/csky/Kconfig
+++ b/arch/csky/Kconfig
@@ -92,9 +92,6 @@ config GENERIC_HWEIGHT
 config MMU
 	def_bool y
 
-config RWSEM_GENERIC_SPINLOCK
-	def_bool y
-
 config STACKTRACE_SUPPORT
 	def_bool y
 
diff --git a/arch/csky/include/asm/Kbuild b/arch/csky/include/asm/Kbuild
index 2a0abe8f2a35..95f4e550db8a 100644
--- a/arch/csky/include/asm/Kbuild
+++ b/arch/csky/include/asm/Kbuild
@@ -28,6 +28,7 @@ generic-y += linkage.h
 generic-y += local.h
 generic-y += local64.h
 generic-y += mm-arch-hooks.h
+generic-y += mmiowb.h
 generic-y += module.h
 generic-y += mutex.h
 generic-y += pci.h
diff --git a/arch/csky/include/asm/syscall.h b/arch/csky/include/asm/syscall.h
index d637445737b7..bda0a446c63e 100644
--- a/arch/csky/include/asm/syscall.h
+++ b/arch/csky/include/asm/syscall.h
@@ -43,30 +43,20 @@ syscall_set_return_value(struct task_struct *task, struct pt_regs *regs,
 
 static inline void
 syscall_get_arguments(struct task_struct *task, struct pt_regs *regs,
-		      unsigned int i, unsigned int n, unsigned long *args)
+		      unsigned long *args)
 {
-	BUG_ON(i + n > 6);
-	if (i == 0) {
-		args[0] = regs->orig_a0;
-		args++;
-		i++;
-		n--;
-	}
-	memcpy(args, &regs->a1 + i * sizeof(regs->a1), n * sizeof(args[0]));
+	args[0] = regs->orig_a0;
+	args++;
+	memcpy(args, &regs->a1, 5 * sizeof(args[0]));
 }
 
 static inline void
 syscall_set_arguments(struct task_struct *task, struct pt_regs *regs,
-		      unsigned int i, unsigned int n, const unsigned long *args)
+		      const unsigned long *args)
 {
-	BUG_ON(i + n > 6);
-	if (i == 0) {
-		regs->orig_a0 = args[0];
-		args++;
-		i++;
-		n--;
-	}
-	memcpy(&regs->a1 + i * sizeof(regs->a1), args, n * sizeof(regs->a0));
+	regs->orig_a0 = args[0];
+	args++;
+	memcpy(&regs->a1, args, 5 * sizeof(regs->a1));
 }
 
 static inline int
diff --git a/arch/h8300/Kconfig b/arch/h8300/Kconfig
index c071da34e081..61c01db6c292 100644
--- a/arch/h8300/Kconfig
+++ b/arch/h8300/Kconfig
@@ -27,9 +27,6 @@ config H8300
 config CPU_BIG_ENDIAN
 	def_bool y
 
-config RWSEM_GENERIC_SPINLOCK
-	def_bool y
-
 config GENERIC_HWEIGHT
 	def_bool y
 
diff --git a/arch/h8300/include/asm/Kbuild b/arch/h8300/include/asm/Kbuild
index 3e7c8ecf151e..123d8f54be4a 100644
--- a/arch/h8300/include/asm/Kbuild
+++ b/arch/h8300/include/asm/Kbuild
@@ -23,11 +23,13 @@ generic-y += irq_work.h
 generic-y += kdebug.h
 generic-y += kmap_types.h
 generic-y += kprobes.h
+generic-y += kvm_para.h
 generic-y += linkage.h
 generic-y += local.h
 generic-y += local64.h
 generic-y += mcs_spinlock.h
 generic-y += mm-arch-hooks.h
+generic-y += mmiowb.h
 generic-y += mmu.h
 generic-y += mmu_context.h
 generic-y += module.h
diff --git a/arch/h8300/include/asm/syscall.h b/arch/h8300/include/asm/syscall.h
index 924990401237..ddd483c6ca95 100644
--- a/arch/h8300/include/asm/syscall.h
+++ b/arch/h8300/include/asm/syscall.h
@@ -17,34 +17,14 @@ syscall_get_nr(struct task_struct *task, struct pt_regs *regs)
 
 static inline void
 syscall_get_arguments(struct task_struct *task, struct pt_regs *regs,
-		      unsigned int i, unsigned int n, unsigned long *args)
+		      unsigned long *args)
 {
-	BUG_ON(i + n > 6);
-
-	while (n > 0) {
-		switch (i) {
-		case 0:
-			*args++ = regs->er1;
-			break;
-		case 1:
-			*args++ = regs->er2;
-			break;
-		case 2:
-			*args++ = regs->er3;
-			break;
-		case 3:
-			*args++ = regs->er4;
-			break;
-		case 4:
-			*args++ = regs->er5;
-			break;
-		case 5:
-			*args++ = regs->er6;
-			break;
-		}
-		i++;
-		n--;
-	}
+	*args++ = regs->er1;
+	*args++ = regs->er2;
+	*args++ = regs->er3;
+	*args++ = regs->er4;
+	*args++ = regs->er5;
+	*args   = regs->er6;
 }
 
 
diff --git a/arch/h8300/include/asm/tlb.h b/arch/h8300/include/asm/tlb.h
index 98f344279904..d8201ca31206 100644
--- a/arch/h8300/include/asm/tlb.h
+++ b/arch/h8300/include/asm/tlb.h
@@ -2,8 +2,6 @@
 #ifndef __H8300_TLB_H__
 #define __H8300_TLB_H__
 
-#define tlb_flush(tlb)	do { } while (0)
-
 #include <asm-generic/tlb.h>
 
 #endif
diff --git a/arch/h8300/include/uapi/asm/Kbuild b/arch/h8300/include/uapi/asm/Kbuild
index 755bb11323d8..1c72f04ff75d 100644
--- a/arch/h8300/include/uapi/asm/Kbuild
+++ b/arch/h8300/include/uapi/asm/Kbuild
@@ -1,2 +1 @@
-generic-y += kvm_para.h
 generic-y += ucontext.h
diff --git a/arch/hexagon/Kconfig b/arch/hexagon/Kconfig
index ac441680dcc0..3e54a53208d5 100644
--- a/arch/hexagon/Kconfig
+++ b/arch/hexagon/Kconfig
@@ -65,12 +65,6 @@ config GENERIC_CSUM
 config GENERIC_IRQ_PROBE
 	def_bool y
 
-config RWSEM_GENERIC_SPINLOCK
-	def_bool n
-
-config RWSEM_XCHGADD_ALGORITHM
-	def_bool y
-
 config GENERIC_HWEIGHT
 	def_bool y
 
diff --git a/arch/hexagon/include/asm/Kbuild b/arch/hexagon/include/asm/Kbuild
index b25fd42aa0f4..6234a303d2a3 100644
--- a/arch/hexagon/include/asm/Kbuild
+++ b/arch/hexagon/include/asm/Kbuild
@@ -19,14 +19,15 @@ generic-y += irq_work.h
 generic-y += kdebug.h
 generic-y += kmap_types.h
 generic-y += kprobes.h
+generic-y += kvm_para.h
 generic-y += local.h
 generic-y += local64.h
 generic-y += mcs_spinlock.h
 generic-y += mm-arch-hooks.h
+generic-y += mmiowb.h
 generic-y += pci.h
 generic-y += percpu.h
 generic-y += preempt.h
-generic-y += rwsem.h
 generic-y += sections.h
 generic-y += segment.h
 generic-y += serial.h
diff --git a/arch/hexagon/include/asm/io.h b/arch/hexagon/include/asm/io.h
index e17262ad125e..3d0ae09c2b8e 100644
--- a/arch/hexagon/include/asm/io.h
+++ b/arch/hexagon/include/asm/io.h
@@ -184,8 +184,6 @@ static inline void writel(u32 data, volatile void __iomem *addr)
 #define writew_relaxed __raw_writew
 #define writel_relaxed __raw_writel
 
-#define mmiowb()
-
 /*
  * Need an mtype somewhere in here, for cache type deals?
  * This is probably too long for an inline.
diff --git a/arch/hexagon/include/asm/syscall.h b/arch/hexagon/include/asm/syscall.h
index 4af9c7b6f13a..ae3a1e24fabd 100644
--- a/arch/hexagon/include/asm/syscall.h
+++ b/arch/hexagon/include/asm/syscall.h
@@ -37,10 +37,8 @@ static inline long syscall_get_nr(struct task_struct *task,
 
 static inline void syscall_get_arguments(struct task_struct *task,
 					 struct pt_regs *regs,
-					 unsigned int i, unsigned int n,
 					 unsigned long *args)
 {
-	BUG_ON(i + n > 6);
-	memcpy(args, &(&regs->r00)[i], n * sizeof(args[0]));
+	memcpy(args, &(&regs->r00)[0], 6 * sizeof(args[0]));
 }
 #endif
diff --git a/arch/hexagon/include/asm/tlb.h b/arch/hexagon/include/asm/tlb.h
index 2f00772cc08a..f71c4ba83614 100644
--- a/arch/hexagon/include/asm/tlb.h
+++ b/arch/hexagon/include/asm/tlb.h
@@ -22,18 +22,6 @@
 #include <linux/pagemap.h>
 #include <asm/tlbflush.h>
 
-/*
- * We don't need any special per-pte or per-vma handling...
- */
-#define tlb_start_vma(tlb, vma)				do { } while (0)
-#define tlb_end_vma(tlb, vma)				do { } while (0)
-#define __tlb_remove_tlb_entry(tlb, ptep, address)	do { } while (0)
-
-/*
- * .. because we flush the whole mm when it fills up
- */
-#define tlb_flush(tlb)		flush_tlb_mm((tlb)->mm)
-
 #include <asm-generic/tlb.h>
 
 #endif
diff --git a/arch/hexagon/include/uapi/asm/kvm_para.h b/arch/hexagon/include/uapi/asm/kvm_para.h
deleted file mode 100644
index baacc4996d18..000000000000
--- a/arch/hexagon/include/uapi/asm/kvm_para.h
+++ /dev/null
@@ -1,2 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
-#include <asm-generic/kvm_para.h>
diff --git a/arch/ia64/Kconfig b/arch/ia64/Kconfig
index 8d7396bd1790..73a26f04644e 100644
--- a/arch/ia64/Kconfig
+++ b/arch/ia64/Kconfig
@@ -83,10 +83,6 @@ config STACKTRACE_SUPPORT
 config GENERIC_LOCKBREAK
 	def_bool n
 
-config RWSEM_XCHGADD_ALGORITHM
-	bool
-	default y
-
 config HUGETLB_PAGE_SIZE_VARIABLE
 	bool
 	depends on HUGETLB_PAGE
diff --git a/arch/ia64/include/asm/Kbuild b/arch/ia64/include/asm/Kbuild
index 43e21fe3499c..11f191689c9e 100644
--- a/arch/ia64/include/asm/Kbuild
+++ b/arch/ia64/include/asm/Kbuild
@@ -2,6 +2,7 @@ generated-y += syscall_table.h
 generic-y += compat.h
 generic-y += exec.h
 generic-y += irq_work.h
+generic-y += kvm_para.h
 generic-y += mcs_spinlock.h
 generic-y += mm-arch-hooks.h
 generic-y += preempt.h
diff --git a/arch/ia64/include/asm/io.h b/arch/ia64/include/asm/io.h
index 1e6fef69bb01..a511d62d447a 100644
--- a/arch/ia64/include/asm/io.h
+++ b/arch/ia64/include/asm/io.h
@@ -113,20 +113,6 @@ extern int valid_mmap_phys_addr_range (unsigned long pfn, size_t count);
  */
 #define __ia64_mf_a()	ia64_mfa()
 
-/**
- * ___ia64_mmiowb - I/O write barrier
- *
- * Ensure ordering of I/O space writes.  This will make sure that writes
- * following the barrier will arrive after all previous writes.  For most
- * ia64 platforms, this is a simple 'mf.a' instruction.
- *
- * See Documentation/driver-api/device-io.rst for more information.
- */
-static inline void ___ia64_mmiowb(void)
-{
-	ia64_mfa();
-}
-
 static inline void*
 __ia64_mk_io_addr (unsigned long port)
 {
@@ -161,7 +147,6 @@ __ia64_mk_io_addr (unsigned long port)
 #define __ia64_writew	___ia64_writew
 #define __ia64_writel	___ia64_writel
 #define __ia64_writeq	___ia64_writeq
-#define __ia64_mmiowb	___ia64_mmiowb
 
 /*
  * For the in/out routines, we need to do "mf.a" _after_ doing the I/O access to ensure
@@ -296,7 +281,6 @@ __outsl (unsigned long port, const void *src, unsigned long count)
 #define __outb		platform_outb
 #define __outw		platform_outw
 #define __outl		platform_outl
-#define __mmiowb	platform_mmiowb
 
 #define inb(p)		__inb(p)
 #define inw(p)		__inw(p)
@@ -310,7 +294,6 @@ __outsl (unsigned long port, const void *src, unsigned long count)
 #define outsb(p,s,c)	__outsb(p,s,c)
 #define outsw(p,s,c)	__outsw(p,s,c)
 #define outsl(p,s,c)	__outsl(p,s,c)
-#define mmiowb()	__mmiowb()
 
 /*
  * The address passed to these functions are ioremap()ped already.
diff --git a/arch/ia64/include/asm/machvec.h b/arch/ia64/include/asm/machvec.h
index 5133739966bc..beae261fbcb4 100644
--- a/arch/ia64/include/asm/machvec.h
+++ b/arch/ia64/include/asm/machvec.h
@@ -30,7 +30,6 @@ typedef void ia64_mv_irq_init_t (void);
 typedef void ia64_mv_send_ipi_t (int, int, int, int);
 typedef void ia64_mv_timer_interrupt_t (int, void *);
 typedef void ia64_mv_global_tlb_purge_t (struct mm_struct *, unsigned long, unsigned long, unsigned long);
-typedef void ia64_mv_tlb_migrate_finish_t (struct mm_struct *);
 typedef u8 ia64_mv_irq_to_vector (int);
 typedef unsigned int ia64_mv_local_vector_to_irq (u8);
 typedef char *ia64_mv_pci_get_legacy_mem_t (struct pci_bus *);
@@ -80,11 +79,6 @@ machvec_noop (void)
 }
 
 static inline void
-machvec_noop_mm (struct mm_struct *mm)
-{
-}
-
-static inline void
 machvec_noop_task (struct task_struct *task)
 {
 }
@@ -96,7 +90,6 @@ machvec_noop_bus (struct pci_bus *bus)
 
 extern void machvec_setup (char **);
 extern void machvec_timer_interrupt (int, void *);
-extern void machvec_tlb_migrate_finish (struct mm_struct *);
 
 # if defined (CONFIG_IA64_HP_SIM)
 #  include <asm/machvec_hpsim.h>
@@ -124,7 +117,6 @@ extern void machvec_tlb_migrate_finish (struct mm_struct *);
 #  define platform_send_ipi	ia64_mv.send_ipi
 #  define platform_timer_interrupt	ia64_mv.timer_interrupt
 #  define platform_global_tlb_purge	ia64_mv.global_tlb_purge
-#  define platform_tlb_migrate_finish	ia64_mv.tlb_migrate_finish
 #  define platform_dma_init		ia64_mv.dma_init
 #  define platform_dma_get_ops		ia64_mv.dma_get_ops
 #  define platform_irq_to_vector	ia64_mv.irq_to_vector
@@ -167,7 +159,6 @@ struct ia64_machine_vector {
 	ia64_mv_send_ipi_t *send_ipi;
 	ia64_mv_timer_interrupt_t *timer_interrupt;
 	ia64_mv_global_tlb_purge_t *global_tlb_purge;
-	ia64_mv_tlb_migrate_finish_t *tlb_migrate_finish;
 	ia64_mv_dma_init *dma_init;
 	ia64_mv_dma_get_ops *dma_get_ops;
 	ia64_mv_irq_to_vector *irq_to_vector;
@@ -206,7 +197,6 @@ struct ia64_machine_vector {
 	platform_send_ipi,			\
 	platform_timer_interrupt,		\
 	platform_global_tlb_purge,		\
-	platform_tlb_migrate_finish,		\
 	platform_dma_init,			\
 	platform_dma_get_ops,			\
 	platform_irq_to_vector,			\
@@ -270,9 +260,6 @@ extern const struct dma_map_ops *dma_get_ops(struct device *);
 #ifndef platform_global_tlb_purge
 # define platform_global_tlb_purge	ia64_global_tlb_purge /* default to architected version */
 #endif
-#ifndef platform_tlb_migrate_finish
-# define platform_tlb_migrate_finish	machvec_noop_mm
-#endif
 #ifndef platform_kernel_launch_event
 # define platform_kernel_launch_event	machvec_noop
 #endif
diff --git a/arch/ia64/include/asm/machvec_sn2.h b/arch/ia64/include/asm/machvec_sn2.h
index b5153d300289..a243e4fb4877 100644
--- a/arch/ia64/include/asm/machvec_sn2.h
+++ b/arch/ia64/include/asm/machvec_sn2.h
@@ -34,7 +34,6 @@ extern ia64_mv_irq_init_t sn_irq_init;
 extern ia64_mv_send_ipi_t sn2_send_IPI;
 extern ia64_mv_timer_interrupt_t sn_timer_interrupt;
 extern ia64_mv_global_tlb_purge_t sn2_global_tlb_purge;
-extern ia64_mv_tlb_migrate_finish_t	sn_tlb_migrate_finish;
 extern ia64_mv_irq_to_vector sn_irq_to_vector;
 extern ia64_mv_local_vector_to_irq sn_local_vector_to_irq;
 extern ia64_mv_pci_get_legacy_mem_t sn_pci_get_legacy_mem;
@@ -77,7 +76,6 @@ extern ia64_mv_pci_fixup_bus_t		sn_pci_fixup_bus;
 #define platform_send_ipi		sn2_send_IPI
 #define platform_timer_interrupt	sn_timer_interrupt
 #define platform_global_tlb_purge       sn2_global_tlb_purge
-#define platform_tlb_migrate_finish	sn_tlb_migrate_finish
 #define platform_pci_fixup		sn_pci_fixup
 #define platform_inb			__sn_inb
 #define platform_inw			__sn_inw
diff --git a/arch/ia64/include/asm/mmiowb.h b/arch/ia64/include/asm/mmiowb.h
new file mode 100644
index 000000000000..297b85ac84a0
--- /dev/null
+++ b/arch/ia64/include/asm/mmiowb.h
@@ -0,0 +1,25 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+
+#ifndef _ASM_IA64_MMIOWB_H
+#define _ASM_IA64_MMIOWB_H
+
+#include <asm/machvec.h>
+
+/**
+ * ___ia64_mmiowb - I/O write barrier
+ *
+ * Ensure ordering of I/O space writes.  This will make sure that writes
+ * following the barrier will arrive after all previous writes.  For most
+ * ia64 platforms, this is a simple 'mf.a' instruction.
+ */
+static inline void ___ia64_mmiowb(void)
+{
+	ia64_mfa();
+}
+
+#define __ia64_mmiowb	___ia64_mmiowb
+#define mmiowb()	platform_mmiowb()
+
+#include <asm-generic/mmiowb.h>
+
+#endif	/* _ASM_IA64_MMIOWB_H */
diff --git a/arch/ia64/include/asm/rwsem.h b/arch/ia64/include/asm/rwsem.h
deleted file mode 100644
index 917910607e0e..000000000000
--- a/arch/ia64/include/asm/rwsem.h
+++ /dev/null
@@ -1,172 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 */
-/*
- * R/W semaphores for ia64
- *
- * Copyright (C) 2003 Ken Chen <kenneth.w.chen@intel.com>
- * Copyright (C) 2003 Asit Mallick <asit.k.mallick@intel.com>
- * Copyright (C) 2005 Christoph Lameter <cl@linux.com>
- *
- * Based on asm-i386/rwsem.h and other architecture implementation.
- *
- * The MSW of the count is the negated number of active writers and
- * waiting lockers, and the LSW is the total number of active locks.
- *
- * The lock count is initialized to 0 (no active and no waiting lockers).
- *
- * When a writer subtracts WRITE_BIAS, it'll get 0xffffffff00000001 for
- * the case of an uncontended lock. Readers increment by 1 and see a positive
- * value when uncontended, negative if there are writers (and maybe) readers
- * waiting (in which case it goes to sleep).
- */
-
-#ifndef _ASM_IA64_RWSEM_H
-#define _ASM_IA64_RWSEM_H
-
-#ifndef _LINUX_RWSEM_H
-#error "Please don't include <asm/rwsem.h> directly, use <linux/rwsem.h> instead."
-#endif
-
-#include <asm/intrinsics.h>
-
-#define RWSEM_UNLOCKED_VALUE		__IA64_UL_CONST(0x0000000000000000)
-#define RWSEM_ACTIVE_BIAS		(1L)
-#define RWSEM_ACTIVE_MASK		(0xffffffffL)
-#define RWSEM_WAITING_BIAS		(-0x100000000L)
-#define RWSEM_ACTIVE_READ_BIAS		RWSEM_ACTIVE_BIAS
-#define RWSEM_ACTIVE_WRITE_BIAS		(RWSEM_WAITING_BIAS + RWSEM_ACTIVE_BIAS)
-
-/*
- * lock for reading
- */
-static inline int
-___down_read (struct rw_semaphore *sem)
-{
-	long result = ia64_fetchadd8_acq((unsigned long *)&sem->count.counter, 1);
-
-	return (result < 0);
-}
-
-static inline void
-__down_read (struct rw_semaphore *sem)
-{
-	if (___down_read(sem))
-		rwsem_down_read_failed(sem);
-}
-
-static inline int
-__down_read_killable (struct rw_semaphore *sem)
-{
-	if (___down_read(sem))
-		if (IS_ERR(rwsem_down_read_failed_killable(sem)))
-			return -EINTR;
-
-	return 0;
-}
-
-/*
- * lock for writing
- */
-static inline long
-___down_write (struct rw_semaphore *sem)
-{
-	long old, new;
-
-	do {
-		old = atomic_long_read(&sem->count);
-		new = old + RWSEM_ACTIVE_WRITE_BIAS;
-	} while (atomic_long_cmpxchg_acquire(&sem->count, old, new) != old);
-
-	return old;
-}
-
-static inline void
-__down_write (struct rw_semaphore *sem)
-{
-	if (___down_write(sem))
-		rwsem_down_write_failed(sem);
-}
-
-static inline int
-__down_write_killable (struct rw_semaphore *sem)
-{
-	if (___down_write(sem)) {
-		if (IS_ERR(rwsem_down_write_failed_killable(sem)))
-			return -EINTR;
-	}
-
-	return 0;
-}
-
-/*
- * unlock after reading
- */
-static inline void
-__up_read (struct rw_semaphore *sem)
-{
-	long result = ia64_fetchadd8_rel((unsigned long *)&sem->count.counter, -1);
-
-	if (result < 0 && (--result & RWSEM_ACTIVE_MASK) == 0)
-		rwsem_wake(sem);
-}
-
-/*
- * unlock after writing
- */
-static inline void
-__up_write (struct rw_semaphore *sem)
-{
-	long old, new;
-
-	do {
-		old = atomic_long_read(&sem->count);
-		new = old - RWSEM_ACTIVE_WRITE_BIAS;
-	} while (atomic_long_cmpxchg_release(&sem->count, old, new) != old);
-
-	if (new < 0 && (new & RWSEM_ACTIVE_MASK) == 0)
-		rwsem_wake(sem);
-}
-
-/*
- * trylock for reading -- returns 1 if successful, 0 if contention
- */
-static inline int
-__down_read_trylock (struct rw_semaphore *sem)
-{
-	long tmp;
-	while ((tmp = atomic_long_read(&sem->count)) >= 0) {
-		if (tmp == atomic_long_cmpxchg_acquire(&sem->count, tmp, tmp+1)) {
-			return 1;
-		}
-	}
-	return 0;
-}
-
-/*
- * trylock for writing -- returns 1 if successful, 0 if contention
- */
-static inline int
-__down_write_trylock (struct rw_semaphore *sem)
-{
-	long tmp = atomic_long_cmpxchg_acquire(&sem->count,
-			RWSEM_UNLOCKED_VALUE, RWSEM_ACTIVE_WRITE_BIAS);
-	return tmp == RWSEM_UNLOCKED_VALUE;
-}
-
-/*
- * downgrade write lock to read lock
- */
-static inline void
-__downgrade_write (struct rw_semaphore *sem)
-{
-	long old, new;
-
-	do {
-		old = atomic_long_read(&sem->count);
-		new = old - RWSEM_WAITING_BIAS;
-	} while (atomic_long_cmpxchg_release(&sem->count, old, new) != old);
-
-	if (old < 0)
-		rwsem_downgrade_wake(sem);
-}
-
-#endif /* _ASM_IA64_RWSEM_H */
diff --git a/arch/ia64/include/asm/spinlock.h b/arch/ia64/include/asm/spinlock.h
index afd0b3121b4c..5f620e66384e 100644
--- a/arch/ia64/include/asm/spinlock.h
+++ b/arch/ia64/include/asm/spinlock.h
@@ -73,6 +73,8 @@ static __always_inline void __ticket_spin_unlock(arch_spinlock_t *lock)
 {
 	unsigned short	*p = (unsigned short *)&lock->lock + 1, tmp;
 
+	/* This could be optimised with ARCH_HAS_MMIOWB */
+	mmiowb();
 	asm volatile ("ld2.bias %0=[%1]" : "=r"(tmp) : "r"(p));
 	WRITE_ONCE(*p, (tmp + 2) & ~1);
 }
diff --git a/arch/ia64/include/asm/syscall.h b/arch/ia64/include/asm/syscall.h
index 1d0b875fec44..0d9e7fab4a79 100644
--- a/arch/ia64/include/asm/syscall.h
+++ b/arch/ia64/include/asm/syscall.h
@@ -59,26 +59,19 @@ static inline void syscall_set_return_value(struct task_struct *task,
 }
 
 extern void ia64_syscall_get_set_arguments(struct task_struct *task,
-	struct pt_regs *regs, unsigned int i, unsigned int n,
-	unsigned long *args, int rw);
+	struct pt_regs *regs, unsigned long *args, int rw);
 static inline void syscall_get_arguments(struct task_struct *task,
 					 struct pt_regs *regs,
-					 unsigned int i, unsigned int n,
 					 unsigned long *args)
 {
-	BUG_ON(i + n > 6);
-
-	ia64_syscall_get_set_arguments(task, regs, i, n, args, 0);
+	ia64_syscall_get_set_arguments(task, regs, args, 0);
 }
 
 static inline void syscall_set_arguments(struct task_struct *task,
 					 struct pt_regs *regs,
-					 unsigned int i, unsigned int n,
 					 unsigned long *args)
 {
-	BUG_ON(i + n > 6);
-
-	ia64_syscall_get_set_arguments(task, regs, i, n, args, 1);
+	ia64_syscall_get_set_arguments(task, regs, args, 1);
 }
 
 static inline int syscall_get_arch(void)
diff --git a/arch/ia64/include/asm/tlb.h b/arch/ia64/include/asm/tlb.h
index 516355a774bf..86ec034ba499 100644
--- a/arch/ia64/include/asm/tlb.h
+++ b/arch/ia64/include/asm/tlb.h
@@ -47,263 +47,6 @@
 #include <asm/tlbflush.h>
 #include <asm/machvec.h>
 
-/*
- * If we can't allocate a page to make a big batch of page pointers
- * to work on, then just handle a few from the on-stack structure.
- */
-#define	IA64_GATHER_BUNDLE	8
-
-struct mmu_gather {
-	struct mm_struct	*mm;
-	unsigned int		nr;
-	unsigned int		max;
-	unsigned char		fullmm;		/* non-zero means full mm flush */
-	unsigned char		need_flush;	/* really unmapped some PTEs? */
-	unsigned long		start, end;
-	unsigned long		start_addr;
-	unsigned long		end_addr;
-	struct page		**pages;
-	struct page		*local[IA64_GATHER_BUNDLE];
-};
-
-struct ia64_tr_entry {
-	u64 ifa;
-	u64 itir;
-	u64 pte;
-	u64 rr;
-}; /*Record for tr entry!*/
-
-extern int ia64_itr_entry(u64 target_mask, u64 va, u64 pte, u64 log_size);
-extern void ia64_ptr_entry(u64 target_mask, int slot);
-
-extern struct ia64_tr_entry *ia64_idtrs[NR_CPUS];
-
-/*
- region register macros
-*/
-#define RR_TO_VE(val)   (((val) >> 0) & 0x0000000000000001)
-#define RR_VE(val)	(((val) & 0x0000000000000001) << 0)
-#define RR_VE_MASK	0x0000000000000001L
-#define RR_VE_SHIFT	0
-#define RR_TO_PS(val)	(((val) >> 2) & 0x000000000000003f)
-#define RR_PS(val)	(((val) & 0x000000000000003f) << 2)
-#define RR_PS_MASK	0x00000000000000fcL
-#define RR_PS_SHIFT	2
-#define RR_RID_MASK	0x00000000ffffff00L
-#define RR_TO_RID(val) 	((val >> 8) & 0xffffff)
-
-static inline void
-ia64_tlb_flush_mmu_tlbonly(struct mmu_gather *tlb, unsigned long start, unsigned long end)
-{
-	tlb->need_flush = 0;
-
-	if (tlb->fullmm) {
-		/*
-		 * Tearing down the entire address space.  This happens both as a result
-		 * of exit() and execve().  The latter case necessitates the call to
-		 * flush_tlb_mm() here.
-		 */
-		flush_tlb_mm(tlb->mm);
-	} else if (unlikely (end - start >= 1024*1024*1024*1024UL
-			     || REGION_NUMBER(start) != REGION_NUMBER(end - 1)))
-	{
-		/*
-		 * If we flush more than a tera-byte or across regions, we're probably
-		 * better off just flushing the entire TLB(s).  This should be very rare
-		 * and is not worth optimizing for.
-		 */
-		flush_tlb_all();
-	} else {
-		/*
-		 * flush_tlb_range() takes a vma instead of a mm pointer because
-		 * some architectures want the vm_flags for ITLB/DTLB flush.
-		 */
-		struct vm_area_struct vma = TLB_FLUSH_VMA(tlb->mm, 0);
-
-		/* flush the address range from the tlb: */
-		flush_tlb_range(&vma, start, end);
-		/* now flush the virt. page-table area mapping the address range: */
-		flush_tlb_range(&vma, ia64_thash(start), ia64_thash(end));
-	}
-
-}
-
-static inline void
-ia64_tlb_flush_mmu_free(struct mmu_gather *tlb)
-{
-	unsigned long i;
-	unsigned int nr;
-
-	/* lastly, release the freed pages */
-	nr = tlb->nr;
-
-	tlb->nr = 0;
-	tlb->start_addr = ~0UL;
-	for (i = 0; i < nr; ++i)
-		free_page_and_swap_cache(tlb->pages[i]);
-}
-
-/*
- * Flush the TLB for address range START to END and, if not in fast mode, release the
- * freed pages that where gathered up to this point.
- */
-static inline void
-ia64_tlb_flush_mmu (struct mmu_gather *tlb, unsigned long start, unsigned long end)
-{
-	if (!tlb->need_flush)
-		return;
-	ia64_tlb_flush_mmu_tlbonly(tlb, start, end);
-	ia64_tlb_flush_mmu_free(tlb);
-}
-
-static inline void __tlb_alloc_page(struct mmu_gather *tlb)
-{
-	unsigned long addr = __get_free_pages(GFP_NOWAIT | __GFP_NOWARN, 0);
-
-	if (addr) {
-		tlb->pages = (void *)addr;
-		tlb->max = PAGE_SIZE / sizeof(void *);
-	}
-}
-
-
-static inline void
-arch_tlb_gather_mmu(struct mmu_gather *tlb, struct mm_struct *mm,
-			unsigned long start, unsigned long end)
-{
-	tlb->mm = mm;
-	tlb->max = ARRAY_SIZE(tlb->local);
-	tlb->pages = tlb->local;
-	tlb->nr = 0;
-	tlb->fullmm = !(start | (end+1));
-	tlb->start = start;
-	tlb->end = end;
-	tlb->start_addr = ~0UL;
-}
-
-/*
- * Called at the end of the shootdown operation to free up any resources that were
- * collected.
- */
-static inline void
-arch_tlb_finish_mmu(struct mmu_gather *tlb,
-			unsigned long start, unsigned long end, bool force)
-{
-	if (force)
-		tlb->need_flush = 1;
-	/*
-	 * Note: tlb->nr may be 0 at this point, so we can't rely on tlb->start_addr and
-	 * tlb->end_addr.
-	 */
-	ia64_tlb_flush_mmu(tlb, start, end);
-
-	/* keep the page table cache within bounds */
-	check_pgt_cache();
-
-	if (tlb->pages != tlb->local)
-		free_pages((unsigned long)tlb->pages, 0);
-}
-
-/*
- * Logically, this routine frees PAGE.  On MP machines, the actual freeing of the page
- * must be delayed until after the TLB has been flushed (see comments at the beginning of
- * this file).
- */
-static inline bool __tlb_remove_page(struct mmu_gather *tlb, struct page *page)
-{
-	tlb->need_flush = 1;
-
-	if (!tlb->nr && tlb->pages == tlb->local)
-		__tlb_alloc_page(tlb);
-
-	tlb->pages[tlb->nr++] = page;
-	VM_WARN_ON(tlb->nr > tlb->max);
-	if (tlb->nr == tlb->max)
-		return true;
-	return false;
-}
-
-static inline void tlb_flush_mmu_tlbonly(struct mmu_gather *tlb)
-{
-	ia64_tlb_flush_mmu_tlbonly(tlb, tlb->start_addr, tlb->end_addr);
-}
-
-static inline void tlb_flush_mmu_free(struct mmu_gather *tlb)
-{
-	ia64_tlb_flush_mmu_free(tlb);
-}
-
-static inline void tlb_flush_mmu(struct mmu_gather *tlb)
-{
-	ia64_tlb_flush_mmu(tlb, tlb->start_addr, tlb->end_addr);
-}
-
-static inline void tlb_remove_page(struct mmu_gather *tlb, struct page *page)
-{
-	if (__tlb_remove_page(tlb, page))
-		tlb_flush_mmu(tlb);
-}
-
-static inline bool __tlb_remove_page_size(struct mmu_gather *tlb,
-					  struct page *page, int page_size)
-{
-	return __tlb_remove_page(tlb, page);
-}
-
-static inline void tlb_remove_page_size(struct mmu_gather *tlb,
-					struct page *page, int page_size)
-{
-	return tlb_remove_page(tlb, page);
-}
-
-/*
- * Remove TLB entry for PTE mapped at virtual address ADDRESS.  This is called for any
- * PTE, not just those pointing to (normal) physical memory.
- */
-static inline void
-__tlb_remove_tlb_entry (struct mmu_gather *tlb, pte_t *ptep, unsigned long address)
-{
-	if (tlb->start_addr == ~0UL)
-		tlb->start_addr = address;
-	tlb->end_addr = address + PAGE_SIZE;
-}
-
-#define tlb_migrate_finish(mm)	platform_tlb_migrate_finish(mm)
-
-#define tlb_start_vma(tlb, vma)			do { } while (0)
-#define tlb_end_vma(tlb, vma)			do { } while (0)
-
-#define tlb_remove_tlb_entry(tlb, ptep, addr)		\
-do {							\
-	tlb->need_flush = 1;				\
-	__tlb_remove_tlb_entry(tlb, ptep, addr);	\
-} while (0)
-
-#define tlb_remove_huge_tlb_entry(h, tlb, ptep, address)	\
-	tlb_remove_tlb_entry(tlb, ptep, address)
-
-#define tlb_remove_check_page_size_change tlb_remove_check_page_size_change
-static inline void tlb_remove_check_page_size_change(struct mmu_gather *tlb,
-						     unsigned int page_size)
-{
-}
-
-#define pte_free_tlb(tlb, ptep, address)		\
-do {							\
-	tlb->need_flush = 1;				\
-	__pte_free_tlb(tlb, ptep, address);		\
-} while (0)
-
-#define pmd_free_tlb(tlb, ptep, address)		\
-do {							\
-	tlb->need_flush = 1;				\
-	__pmd_free_tlb(tlb, ptep, address);		\
-} while (0)
-
-#define pud_free_tlb(tlb, pudp, address)		\
-do {							\
-	tlb->need_flush = 1;				\
-	__pud_free_tlb(tlb, pudp, address);		\
-} while (0)
+#include <asm-generic/tlb.h>
 
 #endif /* _ASM_IA64_TLB_H */
diff --git a/arch/ia64/include/asm/tlbflush.h b/arch/ia64/include/asm/tlbflush.h
index 25e280810f6c..ceac10c4d6e2 100644
--- a/arch/ia64/include/asm/tlbflush.h
+++ b/arch/ia64/include/asm/tlbflush.h
@@ -14,6 +14,31 @@
 #include <asm/mmu_context.h>
 #include <asm/page.h>
 
+struct ia64_tr_entry {
+	u64 ifa;
+	u64 itir;
+	u64 pte;
+	u64 rr;
+}; /*Record for tr entry!*/
+
+extern int ia64_itr_entry(u64 target_mask, u64 va, u64 pte, u64 log_size);
+extern void ia64_ptr_entry(u64 target_mask, int slot);
+extern struct ia64_tr_entry *ia64_idtrs[NR_CPUS];
+
+/*
+ region register macros
+*/
+#define RR_TO_VE(val)   (((val) >> 0) & 0x0000000000000001)
+#define RR_VE(val)     (((val) & 0x0000000000000001) << 0)
+#define RR_VE_MASK     0x0000000000000001L
+#define RR_VE_SHIFT    0
+#define RR_TO_PS(val)  (((val) >> 2) & 0x000000000000003f)
+#define RR_PS(val)     (((val) & 0x000000000000003f) << 2)
+#define RR_PS_MASK     0x00000000000000fcL
+#define RR_PS_SHIFT    2
+#define RR_RID_MASK    0x00000000ffffff00L
+#define RR_TO_RID(val)         ((val >> 8) & 0xffffff)
+
 /*
  * Now for some TLB flushing routines.  This is the kind of stuff that
  * can be very expensive, so try to avoid them whenever possible.
diff --git a/arch/ia64/include/uapi/asm/Kbuild b/arch/ia64/include/uapi/asm/Kbuild
index 20018cb883a9..62a9522af51e 100644
--- a/arch/ia64/include/uapi/asm/Kbuild
+++ b/arch/ia64/include/uapi/asm/Kbuild
@@ -1,2 +1 @@
 generated-y += unistd_64.h
-generic-y += kvm_para.h
diff --git a/arch/ia64/kernel/ptrace.c b/arch/ia64/kernel/ptrace.c
index 6d50ede0ed69..bf9c24d9ce84 100644
--- a/arch/ia64/kernel/ptrace.c
+++ b/arch/ia64/kernel/ptrace.c
@@ -2179,12 +2179,11 @@ static void syscall_get_set_args_cb(struct unw_frame_info *info, void *data)
 }
 
 void ia64_syscall_get_set_arguments(struct task_struct *task,
-	struct pt_regs *regs, unsigned int i, unsigned int n,
-	unsigned long *args, int rw)
+	struct pt_regs *regs, unsigned long *args, int rw)
 {
 	struct syscall_get_set_args data = {
-		.i = i,
-		.n = n,
+		.i = 0,
+		.n = 6,
 		.args = args,
 		.regs = regs,
 		.rw = rw,
diff --git a/arch/ia64/kernel/setup.c b/arch/ia64/kernel/setup.c
index 583a3746d70b..c9cfa760cd57 100644
--- a/arch/ia64/kernel/setup.c
+++ b/arch/ia64/kernel/setup.c
@@ -1058,9 +1058,7 @@ check_bugs (void)
 
 static int __init run_dmi_scan(void)
 {
-	dmi_scan_machine();
-	dmi_memdev_walk();
-	dmi_set_dump_stack_arch_desc();
+	dmi_setup();
 	return 0;
 }
 core_initcall(run_dmi_scan);
diff --git a/arch/ia64/kernel/syscalls/syscall.tbl b/arch/ia64/kernel/syscalls/syscall.tbl
index ab9cda5f6136..56e3d0b685e1 100644
--- a/arch/ia64/kernel/syscalls/syscall.tbl
+++ b/arch/ia64/kernel/syscalls/syscall.tbl
@@ -344,3 +344,7 @@
 332	common	pkey_free			sys_pkey_free
 333	common	rseq				sys_rseq
 # 334 through 423 are reserved to sync up with other architectures
+424	common	pidfd_send_signal		sys_pidfd_send_signal
+425	common	io_uring_setup			sys_io_uring_setup
+426	common	io_uring_enter			sys_io_uring_enter
+427	common	io_uring_register		sys_io_uring_register
diff --git a/arch/ia64/mm/tlb.c b/arch/ia64/mm/tlb.c
index 5fc89aabdce1..5158bd28de05 100644
--- a/arch/ia64/mm/tlb.c
+++ b/arch/ia64/mm/tlb.c
@@ -305,8 +305,8 @@ local_flush_tlb_all (void)
 	ia64_srlz_i();			/* srlz.i implies srlz.d */
 }
 
-void
-flush_tlb_range (struct vm_area_struct *vma, unsigned long start,
+static void
+__flush_tlb_range (struct vm_area_struct *vma, unsigned long start,
 		 unsigned long end)
 {
 	struct mm_struct *mm = vma->vm_mm;
@@ -343,6 +343,25 @@ flush_tlb_range (struct vm_area_struct *vma, unsigned long start,
 	preempt_enable();
 	ia64_srlz_i();			/* srlz.i implies srlz.d */
 }
+
+void flush_tlb_range(struct vm_area_struct *vma,
+		unsigned long start, unsigned long end)
+{
+	if (unlikely(end - start >= 1024*1024*1024*1024UL
+			|| REGION_NUMBER(start) != REGION_NUMBER(end - 1))) {
+		/*
+		 * If we flush more than a tera-byte or across regions, we're
+		 * probably better off just flushing the entire TLB(s).  This
+		 * should be very rare and is not worth optimizing for.
+		 */
+		flush_tlb_all();
+	} else {
+		/* flush the address range from the tlb */
+		__flush_tlb_range(vma, start, end);
+		/* flush the virt. page-table area mapping the addr range */
+		__flush_tlb_range(vma, ia64_thash(start), ia64_thash(end));
+	}
+}
 EXPORT_SYMBOL(flush_tlb_range);
 
 void ia64_tlb_init(void)
diff --git a/arch/ia64/sn/kernel/sn2/sn2_smp.c b/arch/ia64/sn/kernel/sn2/sn2_smp.c
index b73b0ebf8214..b510f4f17fd4 100644
--- a/arch/ia64/sn/kernel/sn2/sn2_smp.c
+++ b/arch/ia64/sn/kernel/sn2/sn2_smp.c
@@ -120,13 +120,6 @@ void sn_migrate(struct task_struct *task)
 		cpu_relax();
 }
 
-void sn_tlb_migrate_finish(struct mm_struct *mm)
-{
-	/* flush_tlb_mm is inefficient if more than 1 users of mm */
-	if (mm == current->mm && mm && atomic_read(&mm->mm_users) == 1)
-		flush_tlb_mm(mm);
-}
-
 static void
 sn2_ipi_flush_all_tlb(struct mm_struct *mm)
 {
diff --git a/arch/m68k/Kconfig b/arch/m68k/Kconfig
index b54206408f91..fe5cc2da6d10 100644
--- a/arch/m68k/Kconfig
+++ b/arch/m68k/Kconfig
@@ -20,7 +20,6 @@ config M68K
 	select GENERIC_STRNCPY_FROM_USER if MMU
 	select GENERIC_STRNLEN_USER if MMU
 	select ARCH_WANT_IPC_PARSE_VERSION
-	select ARCH_USES_GETTIMEOFFSET if MMU && !COLDFIRE
 	select HAVE_FUTEX_CMPXCHG if MMU && FUTEX
 	select HAVE_MOD_ARCH_SPECIFIC
 	select MODULES_USE_ELF_REL
@@ -28,17 +27,11 @@ config M68K
 	select OLD_SIGSUSPEND3
 	select OLD_SIGACTION
 	select ARCH_DISCARD_MEMBLOCK
+	select MMU_GATHER_NO_RANGE if MMU
 
 config CPU_BIG_ENDIAN
 	def_bool y
 
-config RWSEM_GENERIC_SPINLOCK
-	bool
-	default y
-
-config RWSEM_XCHGADD_ALGORITHM
-	bool
-
 config ARCH_HAS_ILOG2_U32
 	bool
 
diff --git a/arch/m68k/amiga/cia.c b/arch/m68k/amiga/cia.c
index 2081b8cd5591..b9aee983e6f4 100644
--- a/arch/m68k/amiga/cia.c
+++ b/arch/m68k/amiga/cia.c
@@ -88,10 +88,19 @@ static irqreturn_t cia_handler(int irq, void *dev_id)
 	struct ciabase *base = dev_id;
 	int mach_irq;
 	unsigned char ints;
+	unsigned long flags;
 
+	/* Interrupts get disabled while the timer irq flag is cleared and
+	 * the timer interrupt serviced.
+	 */
 	mach_irq = base->cia_irq;
+	local_irq_save(flags);
 	ints = cia_set_irq(base, CIA_ICR_ALL);
 	amiga_custom.intreq = base->int_mask;
+	if (ints & 1)
+		generic_handle_irq(mach_irq);
+	local_irq_restore(flags);
+	mach_irq++, ints >>= 1;
 	for (; ints; mach_irq++, ints >>= 1) {
 		if (ints & 1)
 			generic_handle_irq(mach_irq);
diff --git a/arch/m68k/amiga/config.c b/arch/m68k/amiga/config.c
index 65f63a457130..c32ab8041cf6 100644
--- a/arch/m68k/amiga/config.c
+++ b/arch/m68k/amiga/config.c
@@ -17,6 +17,7 @@
 #include <linux/mm.h>
 #include <linux/seq_file.h>
 #include <linux/tty.h>
+#include <linux/clocksource.h>
 #include <linux/console.h>
 #include <linux/rtc.h>
 #include <linux/init.h>
@@ -95,8 +96,6 @@ static char amiga_model_name[13] = "Amiga ";
 static void amiga_sched_init(irq_handler_t handler);
 static void amiga_get_model(char *model);
 static void amiga_get_hardware_list(struct seq_file *m);
-/* amiga specific timer functions */
-static u32 amiga_gettimeoffset(void);
 extern void amiga_mksound(unsigned int count, unsigned int ticks);
 static void amiga_reset(void);
 extern void amiga_init_sound(void);
@@ -386,7 +385,6 @@ void __init config_amiga(void)
 	mach_init_IRQ        = amiga_init_IRQ;
 	mach_get_model       = amiga_get_model;
 	mach_get_hardware_list = amiga_get_hardware_list;
-	arch_gettimeoffset   = amiga_gettimeoffset;
 
 	/*
 	 * default MAX_DMA=0xffffffff on all machines. If we don't do so, the SCSI
@@ -464,7 +462,29 @@ void __init config_amiga(void)
 		*(unsigned char *)ZTWO_VADDR(0xde0002) |= 0x80;
 }
 
+static u64 amiga_read_clk(struct clocksource *cs);
+
+static struct clocksource amiga_clk = {
+	.name   = "ciab",
+	.rating = 250,
+	.read   = amiga_read_clk,
+	.mask   = CLOCKSOURCE_MASK(32),
+	.flags  = CLOCK_SOURCE_IS_CONTINUOUS,
+};
+
 static unsigned short jiffy_ticks;
+static u32 clk_total, clk_offset;
+
+static irqreturn_t ciab_timer_handler(int irq, void *dev_id)
+{
+	irq_handler_t timer_routine = dev_id;
+
+	clk_total += jiffy_ticks;
+	clk_offset = 0;
+	timer_routine(0, NULL);
+
+	return IRQ_HANDLED;
+}
 
 static void __init amiga_sched_init(irq_handler_t timer_routine)
 {
@@ -484,19 +504,22 @@ static void __init amiga_sched_init(irq_handler_t timer_routine)
 	 * Please don't change this to use ciaa, as it interferes with the
 	 * SCSI code. We'll have to take a look at this later
 	 */
-	if (request_irq(IRQ_AMIGA_CIAB_TA, timer_routine, 0, "timer", NULL))
+	if (request_irq(IRQ_AMIGA_CIAB_TA, ciab_timer_handler, IRQF_TIMER,
+			"timer", timer_routine))
 		pr_err("Couldn't register timer interrupt\n");
 	/* start timer */
 	ciab.cra |= 0x11;
-}
 
-#define TICK_SIZE 10000
+	clocksource_register_hz(&amiga_clk, amiga_eclock);
+}
 
-/* This is always executed with interrupts disabled.  */
-static u32 amiga_gettimeoffset(void)
+static u64 amiga_read_clk(struct clocksource *cs)
 {
 	unsigned short hi, lo, hi2;
-	u32 ticks, offset = 0;
+	unsigned long flags;
+	u32 ticks;
+
+	local_irq_save(flags);
 
 	/* read CIA B timer A current value */
 	hi  = ciab.tahi;
@@ -513,12 +536,14 @@ static u32 amiga_gettimeoffset(void)
 	if (ticks > jiffy_ticks / 2)
 		/* check for pending interrupt */
 		if (cia_set_irq(&ciab_base, 0) & CIA_ICR_TA)
-			offset = 10000;
+			clk_offset = jiffy_ticks;
 
 	ticks = jiffy_ticks - ticks;
-	ticks = (10000 * ticks) / jiffy_ticks;
+	ticks += clk_offset + clk_total;
+
+	local_irq_restore(flags);
 
-	return (ticks + offset) * 1000;
+	return ticks;
 }
 
 static void amiga_reset(void)  __noreturn;
diff --git a/arch/m68k/apollo/config.c b/arch/m68k/apollo/config.c
index aef8d42e078d..7d168e6dfb01 100644
--- a/arch/m68k/apollo/config.c
+++ b/arch/m68k/apollo/config.c
@@ -29,7 +29,6 @@ u_long apollo_model;
 
 extern void dn_sched_init(irq_handler_t handler);
 extern void dn_init_IRQ(void);
-extern u32 dn_gettimeoffset(void);
 extern int dn_dummy_hwclk(int, struct rtc_time *);
 extern void dn_dummy_reset(void);
 #ifdef CONFIG_HEARTBEAT
@@ -152,7 +151,6 @@ void __init config_apollo(void)
 
 	mach_sched_init=dn_sched_init; /* */
 	mach_init_IRQ=dn_init_IRQ;
-	arch_gettimeoffset   = dn_gettimeoffset;
 	mach_max_dma_address = 0xffffffff;
 	mach_hwclk           = dn_dummy_hwclk; /* */
 	mach_reset	     = dn_dummy_reset;  /* */
@@ -205,11 +203,6 @@ void dn_sched_init(irq_handler_t timer_routine)
 		pr_err("Couldn't register timer interrupt\n");
 }
 
-u32 dn_gettimeoffset(void)
-{
-	return 0xdeadbeef;
-}
-
 int dn_dummy_hwclk(int op, struct rtc_time *t) {
 
 
diff --git a/arch/m68k/atari/ataints.c b/arch/m68k/atari/ataints.c
index 3d2b63bedf05..56f02ea2c248 100644
--- a/arch/m68k/atari/ataints.c
+++ b/arch/m68k/atari/ataints.c
@@ -142,7 +142,7 @@ struct mfptimerbase {
 	.name		= "MFP Timer D"
 };
 
-static irqreturn_t mfptimer_handler(int irq, void *dev_id)
+static irqreturn_t mfp_timer_d_handler(int irq, void *dev_id)
 {
 	struct mfptimerbase *base = dev_id;
 	int mach_irq;
@@ -344,7 +344,7 @@ void __init atari_init_IRQ(void)
 	st_mfp.tim_ct_cd = (st_mfp.tim_ct_cd & 0xf0) | 0x6;
 
 	/* request timer D dispatch handler */
-	if (request_irq(IRQ_MFP_TIMD, mfptimer_handler, IRQF_SHARED,
+	if (request_irq(IRQ_MFP_TIMD, mfp_timer_d_handler, IRQF_SHARED,
 			stmfp_base.name, &stmfp_base))
 		pr_err("Couldn't register %s interrupt\n", stmfp_base.name);
 
diff --git a/arch/m68k/atari/config.c b/arch/m68k/atari/config.c
index 4fcc4b1df1c0..902255e7b5b2 100644
--- a/arch/m68k/atari/config.c
+++ b/arch/m68k/atari/config.c
@@ -78,7 +78,6 @@ static void atari_heartbeat(int on);
 
 /* atari specific timer functions (in time.c) */
 extern void atari_sched_init(irq_handler_t);
-extern u32 atari_gettimeoffset(void);
 extern int atari_mste_hwclk (int, struct rtc_time *);
 extern int atari_tt_hwclk (int, struct rtc_time *);
 
@@ -205,7 +204,6 @@ void __init config_atari(void)
 	mach_init_IRQ        = atari_init_IRQ;
 	mach_get_model	 = atari_get_model;
 	mach_get_hardware_list = atari_get_hardware_list;
-	arch_gettimeoffset   = atari_gettimeoffset;
 	mach_reset           = atari_reset;
 	mach_max_dma_address = 0xffffff;
 #if IS_ENABLED(CONFIG_INPUT_M68K_BEEP)
diff --git a/arch/m68k/atari/time.c b/arch/m68k/atari/time.c
index 9cca64286464..ce923a523695 100644
--- a/arch/m68k/atari/time.c
+++ b/arch/m68k/atari/time.c
@@ -16,6 +16,7 @@
 #include <linux/init.h>
 #include <linux/rtc.h>
 #include <linux/bcd.h>
+#include <linux/clocksource.h>
 #include <linux/delay.h>
 #include <linux/export.h>
 
@@ -24,6 +25,35 @@
 DEFINE_SPINLOCK(rtc_lock);
 EXPORT_SYMBOL_GPL(rtc_lock);
 
+static u64 atari_read_clk(struct clocksource *cs);
+
+static struct clocksource atari_clk = {
+	.name   = "mfp",
+	.rating = 100,
+	.read   = atari_read_clk,
+	.mask   = CLOCKSOURCE_MASK(32),
+	.flags  = CLOCK_SOURCE_IS_CONTINUOUS,
+};
+
+static u32 clk_total;
+static u8 last_timer_count;
+
+static irqreturn_t mfp_timer_c_handler(int irq, void *dev_id)
+{
+	irq_handler_t timer_routine = dev_id;
+	unsigned long flags;
+
+	local_irq_save(flags);
+	do {
+		last_timer_count = st_mfp.tim_dt_c;
+	} while (last_timer_count == 1);
+	clk_total += INT_TICKS;
+	timer_routine(0, NULL);
+	local_irq_restore(flags);
+
+	return IRQ_HANDLED;
+}
+
 void __init
 atari_sched_init(irq_handler_t timer_routine)
 {
@@ -32,31 +62,33 @@ atari_sched_init(irq_handler_t timer_routine)
     /* start timer C, div = 1:100 */
     st_mfp.tim_ct_cd = (st_mfp.tim_ct_cd & 15) | 0x60;
     /* install interrupt service routine for MFP Timer C */
-    if (request_irq(IRQ_MFP_TIMC, timer_routine, 0, "timer", timer_routine))
+    if (request_irq(IRQ_MFP_TIMC, mfp_timer_c_handler, IRQF_TIMER, "timer",
+                    timer_routine))
 	pr_err("Couldn't register timer interrupt\n");
+
+    clocksource_register_hz(&atari_clk, INT_CLK);
 }
 
 /* ++andreas: gettimeoffset fixed to check for pending interrupt */
 
-#define TICK_SIZE 10000
-
-/* This is always executed with interrupts disabled.  */
-u32 atari_gettimeoffset(void)
+static u64 atari_read_clk(struct clocksource *cs)
 {
-  u32 ticks, offset = 0;
-
-  /* read MFP timer C current value */
-  ticks = st_mfp.tim_dt_c;
-  /* The probability of underflow is less than 2% */
-  if (ticks > INT_TICKS - INT_TICKS / 50)
-    /* Check for pending timer interrupt */
-    if (st_mfp.int_pn_b & (1 << 5))
-      offset = TICK_SIZE;
-
-  ticks = INT_TICKS - ticks;
-  ticks = ticks * 10000L / INT_TICKS;
-
-  return (ticks + offset) * 1000;
+	unsigned long flags;
+	u8 count;
+	u32 ticks;
+
+	local_irq_save(flags);
+	/* Ensure that the count is monotonically decreasing, even though
+	 * the result may briefly stop changing after counter wrap-around.
+	 */
+	count = min(st_mfp.tim_dt_c, last_timer_count);
+	last_timer_count = count;
+
+	ticks = INT_TICKS - count;
+	ticks += clk_total;
+	local_irq_restore(flags);
+
+	return ticks;
 }
 
 
diff --git a/arch/m68k/bvme6000/config.c b/arch/m68k/bvme6000/config.c
index 143ee9fa3893..8ebaabc931cd 100644
--- a/arch/m68k/bvme6000/config.c
+++ b/arch/m68k/bvme6000/config.c
@@ -18,6 +18,7 @@
 #include <linux/kernel.h>
 #include <linux/mm.h>
 #include <linux/tty.h>
+#include <linux/clocksource.h>
 #include <linux/console.h>
 #include <linux/linkage.h>
 #include <linux/init.h>
@@ -39,16 +40,10 @@
 
 static void bvme6000_get_model(char *model);
 extern void bvme6000_sched_init(irq_handler_t handler);
-extern u32 bvme6000_gettimeoffset(void);
 extern int bvme6000_hwclk (int, struct rtc_time *);
 extern void bvme6000_reset (void);
 void bvme6000_set_vectors (void);
 
-/* Save tick handler routine pointer, will point to xtime_update() in
- * kernel/timer/timekeeping.c, called via bvme6000_process_int() */
-
-static irq_handler_t tick_handler;
-
 
 int __init bvme6000_parse_bootinfo(const struct bi_record *bi)
 {
@@ -110,7 +105,6 @@ void __init config_bvme6000(void)
     mach_max_dma_address = 0xffffffff;
     mach_sched_init      = bvme6000_sched_init;
     mach_init_IRQ        = bvme6000_init_IRQ;
-    arch_gettimeoffset   = bvme6000_gettimeoffset;
     mach_hwclk           = bvme6000_hwclk;
     mach_reset		 = bvme6000_reset;
     mach_get_model       = bvme6000_get_model;
@@ -154,15 +148,38 @@ irqreturn_t bvme6000_abort_int (int irq, void *dev_id)
 	return IRQ_HANDLED;
 }
 
+static u64 bvme6000_read_clk(struct clocksource *cs);
+
+static struct clocksource bvme6000_clk = {
+	.name   = "rtc",
+	.rating = 250,
+	.read   = bvme6000_read_clk,
+	.mask   = CLOCKSOURCE_MASK(32),
+	.flags  = CLOCK_SOURCE_IS_CONTINUOUS,
+};
+
+static u32 clk_total, clk_offset;
+
+#define RTC_TIMER_CLOCK_FREQ 8000000
+#define RTC_TIMER_CYCLES     (RTC_TIMER_CLOCK_FREQ / HZ)
+#define RTC_TIMER_COUNT      ((RTC_TIMER_CYCLES / 2) - 1)
 
 static irqreturn_t bvme6000_timer_int (int irq, void *dev_id)
 {
+    irq_handler_t timer_routine = dev_id;
+    unsigned long flags;
     volatile RtcPtr_t rtc = (RtcPtr_t)BVME_RTC_BASE;
-    unsigned char msr = rtc->msr & 0xc0;
+    unsigned char msr;
 
+    local_irq_save(flags);
+    msr = rtc->msr & 0xc0;
     rtc->msr = msr | 0x20;		/* Ack the interrupt */
+    clk_total += RTC_TIMER_CYCLES;
+    clk_offset = 0;
+    timer_routine(0, NULL);
+    local_irq_restore(flags);
 
-    return tick_handler(irq, dev_id);
+    return IRQ_HANDLED;
 }
 
 /*
@@ -181,14 +198,13 @@ void bvme6000_sched_init (irq_handler_t timer_routine)
 
     rtc->msr = 0;	/* Ensure timer registers accessible */
 
-    tick_handler = timer_routine;
-    if (request_irq(BVME_IRQ_RTC, bvme6000_timer_int, 0,
-				"timer", bvme6000_timer_int))
+    if (request_irq(BVME_IRQ_RTC, bvme6000_timer_int, IRQF_TIMER, "timer",
+                    timer_routine))
 	panic ("Couldn't register timer int");
 
     rtc->t1cr_omr = 0x04;	/* Mode 2, ext clk */
-    rtc->t1msb = 39999 >> 8;
-    rtc->t1lsb = 39999 & 0xff;
+    rtc->t1msb = RTC_TIMER_COUNT >> 8;
+    rtc->t1lsb = RTC_TIMER_COUNT & 0xff;
     rtc->irr_icr1 &= 0xef;	/* Route timer 1 to INTR pin */
     rtc->msr = 0x40;		/* Access int.cntrl, etc */
     rtc->pfr_icr0 = 0x80;	/* Just timer 1 ints enabled */
@@ -200,14 +216,14 @@ void bvme6000_sched_init (irq_handler_t timer_routine)
 
     rtc->msr = msr;
 
+    clocksource_register_hz(&bvme6000_clk, RTC_TIMER_CLOCK_FREQ);
+
     if (request_irq(BVME_IRQ_ABORT, bvme6000_abort_int, 0,
 				"abort", bvme6000_abort_int))
 	panic ("Couldn't register abort int");
 }
 
 
-/* This is always executed with interrupts disabled.  */
-
 /*
  * NOTE:  Don't accept any readings within 5us of rollover, as
  * the T1INT bit may be a little slow getting set.  There is also
@@ -215,14 +231,18 @@ void bvme6000_sched_init (irq_handler_t timer_routine)
  * results...
  */
 
-u32 bvme6000_gettimeoffset(void)
+static u64 bvme6000_read_clk(struct clocksource *cs)
 {
+    unsigned long flags;
     volatile RtcPtr_t rtc = (RtcPtr_t)BVME_RTC_BASE;
     volatile PitRegsPtr pit = (PitRegsPtr)BVME_PIT_BASE;
-    unsigned char msr = rtc->msr & 0xc0;
+    unsigned char msr, msb;
     unsigned char t1int, t1op;
     u32 v = 800000, ov;
 
+    local_irq_save(flags);
+
+    msr = rtc->msr & 0xc0;
     rtc->msr = 0;	/* Ensure timer registers accessible */
 
     do {
@@ -230,22 +250,25 @@ u32 bvme6000_gettimeoffset(void)
 	t1int = rtc->msr & 0x20;
 	t1op  = pit->pcdr & 0x04;
 	rtc->t1cr_omr |= 0x40;		/* Latch timer1 */
-	v = rtc->t1msb << 8;		/* Read timer1 */
-	v |= rtc->t1lsb;		/* Read timer1 */
+	msb = rtc->t1msb;		/* Read timer1 */
+	v = (msb << 8) | rtc->t1lsb;	/* Read timer1 */
     } while (t1int != (rtc->msr & 0x20) ||
 		t1op != (pit->pcdr & 0x04) ||
 			abs(ov-v) > 80 ||
-				v > 39960);
+				v > RTC_TIMER_COUNT - (RTC_TIMER_COUNT / 100));
 
-    v = 39999 - v;
+    v = RTC_TIMER_COUNT - v;
     if (!t1op)				/* If in second half cycle.. */
-	v += 40000;
-    v /= 8;				/* Convert ticks to microseconds */
-    if (t1int)
-	v += 10000;			/* Int pending, + 10ms */
+	v += RTC_TIMER_CYCLES / 2;
+    if (msb > 0 && t1int)
+	clk_offset = RTC_TIMER_CYCLES;
     rtc->msr = msr;
 
-    return v * 1000;
+    v += clk_offset + clk_total;
+
+    local_irq_restore(flags);
+
+    return v;
 }
 
 /*
diff --git a/arch/m68k/configs/amiga_defconfig b/arch/m68k/configs/amiga_defconfig
index 525421ae277d..fea392cfcf1b 100644
--- a/arch/m68k/configs/amiga_defconfig
+++ b/arch/m68k/configs/amiga_defconfig
@@ -56,6 +56,7 @@ CONFIG_TLS=m
 CONFIG_XFRM_MIGRATE=y
 CONFIG_NET_KEY=y
 CONFIG_XDP_SOCKETS=y
+CONFIG_XDP_SOCKETS_DIAG=m
 CONFIG_INET=y
 CONFIG_IP_PNP=y
 CONFIG_IP_PNP_DHCP=y
@@ -210,9 +211,6 @@ CONFIG_NFT_FIB_IPV4=m
 CONFIG_NF_TABLES_ARP=y
 CONFIG_NF_FLOW_TABLE_IPV4=m
 CONFIG_NF_LOG_ARP=m
-CONFIG_NFT_CHAIN_NAT_IPV4=m
-CONFIG_NFT_MASQ_IPV4=m
-CONFIG_NFT_REDIR_IPV4=m
 CONFIG_IP_NF_IPTABLES=m
 CONFIG_IP_NF_MATCH_AH=m
 CONFIG_IP_NF_MATCH_ECN=m
@@ -234,9 +232,6 @@ CONFIG_IP_NF_ARPTABLES=m
 CONFIG_IP_NF_ARPFILTER=m
 CONFIG_IP_NF_ARP_MANGLE=m
 CONFIG_NFT_CHAIN_ROUTE_IPV6=m
-CONFIG_NFT_CHAIN_NAT_IPV6=m
-CONFIG_NFT_MASQ_IPV6=m
-CONFIG_NFT_REDIR_IPV6=m
 CONFIG_NFT_DUP_IPV6=m
 CONFIG_NFT_FIB_IPV6=m
 CONFIG_NF_FLOW_TABLE_IPV6=m
@@ -313,7 +308,6 @@ CONFIG_AF_KCM=m
 # CONFIG_WIRELESS is not set
 CONFIG_PSAMPLE=m
 CONFIG_NET_IFE=m
-CONFIG_NET_DEVLINK=m
 # CONFIG_UEVENT_HELPER is not set
 CONFIG_DEVTMPFS=y
 CONFIG_DEVTMPFS_MOUNT=y
@@ -460,12 +454,12 @@ CONFIG_RTC_DRV_RP5C01=m
 # CONFIG_VIRTIO_MENU is not set
 # CONFIG_IOMMU_SUPPORT is not set
 CONFIG_DAX=m
+# CONFIG_VALIDATE_FS_PARSER is not set
 CONFIG_EXT4_FS=y
 CONFIG_REISERFS_FS=m
 CONFIG_JFS_FS=m
 CONFIG_OCFS2_FS=m
 # CONFIG_OCFS2_DEBUG_MASKLOG is not set
-CONFIG_FS_ENCRYPTION=m
 CONFIG_FANOTIFY=y
 CONFIG_QUOTA_NETLINK_INTERFACE=y
 # CONFIG_PRINT_QUOTA_WARNING is not set
@@ -573,9 +567,11 @@ CONFIG_CRYPTO_AEGIS256=m
 CONFIG_CRYPTO_MORUS640=m
 CONFIG_CRYPTO_MORUS1280=m
 CONFIG_CRYPTO_CFB=m
+CONFIG_CRYPTO_CTS=m
 CONFIG_CRYPTO_LRW=m
 CONFIG_CRYPTO_OFB=m
 CONFIG_CRYPTO_PCBC=m
+CONFIG_CRYPTO_XTS=m
 CONFIG_CRYPTO_KEYWRAP=m
 CONFIG_CRYPTO_ADIANTUM=m
 CONFIG_CRYPTO_XCBC=m
@@ -640,6 +636,7 @@ CONFIG_TEST_OVERFLOW=m
 CONFIG_TEST_RHASHTABLE=m
 CONFIG_TEST_HASH=m
 CONFIG_TEST_IDA=m
+CONFIG_TEST_VMALLOC=m
 CONFIG_TEST_USER_COPY=m
 CONFIG_TEST_BPF=m
 CONFIG_FIND_BIT_BENCHMARK=m
@@ -649,4 +646,5 @@ CONFIG_TEST_UDELAY=m
 CONFIG_TEST_STATIC_KEYS=m
 CONFIG_TEST_KMOD=m
 CONFIG_TEST_MEMCAT_P=m
+CONFIG_TEST_STACKINIT=m
 CONFIG_EARLY_PRINTK=y
diff --git a/arch/m68k/configs/apollo_defconfig b/arch/m68k/configs/apollo_defconfig
index db0e654a88d5..2474d267460e 100644
--- a/arch/m68k/configs/apollo_defconfig
+++ b/arch/m68k/configs/apollo_defconfig
@@ -52,6 +52,7 @@ CONFIG_TLS=m
 CONFIG_XFRM_MIGRATE=y
 CONFIG_NET_KEY=y
 CONFIG_XDP_SOCKETS=y
+CONFIG_XDP_SOCKETS_DIAG=m
 CONFIG_INET=y
 CONFIG_IP_PNP=y
 CONFIG_IP_PNP_DHCP=y
@@ -206,9 +207,6 @@ CONFIG_NFT_FIB_IPV4=m
 CONFIG_NF_TABLES_ARP=y
 CONFIG_NF_FLOW_TABLE_IPV4=m
 CONFIG_NF_LOG_ARP=m
-CONFIG_NFT_CHAIN_NAT_IPV4=m
-CONFIG_NFT_MASQ_IPV4=m
-CONFIG_NFT_REDIR_IPV4=m
 CONFIG_IP_NF_IPTABLES=m
 CONFIG_IP_NF_MATCH_AH=m
 CONFIG_IP_NF_MATCH_ECN=m
@@ -230,9 +228,6 @@ CONFIG_IP_NF_ARPTABLES=m
 CONFIG_IP_NF_ARPFILTER=m
 CONFIG_IP_NF_ARP_MANGLE=m
 CONFIG_NFT_CHAIN_ROUTE_IPV6=m
-CONFIG_NFT_CHAIN_NAT_IPV6=m
-CONFIG_NFT_MASQ_IPV6=m
-CONFIG_NFT_REDIR_IPV6=m
 CONFIG_NFT_DUP_IPV6=m
 CONFIG_NFT_FIB_IPV6=m
 CONFIG_NF_FLOW_TABLE_IPV6=m
@@ -309,7 +304,6 @@ CONFIG_AF_KCM=m
 # CONFIG_WIRELESS is not set
 CONFIG_PSAMPLE=m
 CONFIG_NET_IFE=m
-CONFIG_NET_DEVLINK=m
 # CONFIG_UEVENT_HELPER is not set
 CONFIG_DEVTMPFS=y
 CONFIG_DEVTMPFS_MOUNT=y
@@ -420,12 +414,12 @@ CONFIG_RTC_DRV_GENERIC=m
 # CONFIG_VIRTIO_MENU is not set
 # CONFIG_IOMMU_SUPPORT is not set
 CONFIG_DAX=m
+# CONFIG_VALIDATE_FS_PARSER is not set
 CONFIG_EXT4_FS=y
 CONFIG_REISERFS_FS=m
 CONFIG_JFS_FS=m
 CONFIG_OCFS2_FS=m
 # CONFIG_OCFS2_DEBUG_MASKLOG is not set
-CONFIG_FS_ENCRYPTION=m
 CONFIG_FANOTIFY=y
 CONFIG_QUOTA_NETLINK_INTERFACE=y
 # CONFIG_PRINT_QUOTA_WARNING is not set
@@ -533,9 +527,11 @@ CONFIG_CRYPTO_AEGIS256=m
 CONFIG_CRYPTO_MORUS640=m
 CONFIG_CRYPTO_MORUS1280=m
 CONFIG_CRYPTO_CFB=m
+CONFIG_CRYPTO_CTS=m
 CONFIG_CRYPTO_LRW=m
 CONFIG_CRYPTO_OFB=m
 CONFIG_CRYPTO_PCBC=m
+CONFIG_CRYPTO_XTS=m
 CONFIG_CRYPTO_KEYWRAP=m
 CONFIG_CRYPTO_ADIANTUM=m
 CONFIG_CRYPTO_XCBC=m
@@ -600,6 +596,7 @@ CONFIG_TEST_OVERFLOW=m
 CONFIG_TEST_RHASHTABLE=m
 CONFIG_TEST_HASH=m
 CONFIG_TEST_IDA=m
+CONFIG_TEST_VMALLOC=m
 CONFIG_TEST_USER_COPY=m
 CONFIG_TEST_BPF=m
 CONFIG_FIND_BIT_BENCHMARK=m
@@ -609,4 +606,5 @@ CONFIG_TEST_UDELAY=m
 CONFIG_TEST_STATIC_KEYS=m
 CONFIG_TEST_KMOD=m
 CONFIG_TEST_MEMCAT_P=m
+CONFIG_TEST_STACKINIT=m
 CONFIG_EARLY_PRINTK=y
diff --git a/arch/m68k/configs/atari_defconfig b/arch/m68k/configs/atari_defconfig
index 1451168eb789..0fc7d2992fe0 100644
--- a/arch/m68k/configs/atari_defconfig
+++ b/arch/m68k/configs/atari_defconfig
@@ -59,6 +59,7 @@ CONFIG_TLS=m
 CONFIG_XFRM_MIGRATE=y
 CONFIG_NET_KEY=y
 CONFIG_XDP_SOCKETS=y
+CONFIG_XDP_SOCKETS_DIAG=m
 CONFIG_INET=y
 CONFIG_IP_PNP=y
 CONFIG_IP_PNP_DHCP=y
@@ -213,9 +214,6 @@ CONFIG_NFT_FIB_IPV4=m
 CONFIG_NF_TABLES_ARP=y
 CONFIG_NF_FLOW_TABLE_IPV4=m
 CONFIG_NF_LOG_ARP=m
-CONFIG_NFT_CHAIN_NAT_IPV4=m
-CONFIG_NFT_MASQ_IPV4=m
-CONFIG_NFT_REDIR_IPV4=m
 CONFIG_IP_NF_IPTABLES=m
 CONFIG_IP_NF_MATCH_AH=m
 CONFIG_IP_NF_MATCH_ECN=m
@@ -237,9 +235,6 @@ CONFIG_IP_NF_ARPTABLES=m
 CONFIG_IP_NF_ARPFILTER=m
 CONFIG_IP_NF_ARP_MANGLE=m
 CONFIG_NFT_CHAIN_ROUTE_IPV6=m
-CONFIG_NFT_CHAIN_NAT_IPV6=m
-CONFIG_NFT_MASQ_IPV6=m
-CONFIG_NFT_REDIR_IPV6=m
 CONFIG_NFT_DUP_IPV6=m
 CONFIG_NFT_FIB_IPV6=m
 CONFIG_NF_FLOW_TABLE_IPV6=m
@@ -316,7 +311,6 @@ CONFIG_AF_KCM=m
 # CONFIG_WIRELESS is not set
 CONFIG_PSAMPLE=m
 CONFIG_NET_IFE=m
-CONFIG_NET_DEVLINK=m
 # CONFIG_UEVENT_HELPER is not set
 CONFIG_DEVTMPFS=y
 CONFIG_DEVTMPFS_MOUNT=y
@@ -442,12 +436,12 @@ CONFIG_RTC_DRV_GENERIC=m
 # CONFIG_VIRTIO_MENU is not set
 # CONFIG_IOMMU_SUPPORT is not set
 CONFIG_DAX=m
+# CONFIG_VALIDATE_FS_PARSER is not set
 CONFIG_EXT4_FS=y
 CONFIG_REISERFS_FS=m
 CONFIG_JFS_FS=m
 CONFIG_OCFS2_FS=m
 # CONFIG_OCFS2_DEBUG_MASKLOG is not set
-CONFIG_FS_ENCRYPTION=m
 CONFIG_FANOTIFY=y
 CONFIG_QUOTA_NETLINK_INTERFACE=y
 # CONFIG_PRINT_QUOTA_WARNING is not set
@@ -555,9 +549,11 @@ CONFIG_CRYPTO_AEGIS256=m
 CONFIG_CRYPTO_MORUS640=m
 CONFIG_CRYPTO_MORUS1280=m
 CONFIG_CRYPTO_CFB=m
+CONFIG_CRYPTO_CTS=m
 CONFIG_CRYPTO_LRW=m
 CONFIG_CRYPTO_OFB=m
 CONFIG_CRYPTO_PCBC=m
+CONFIG_CRYPTO_XTS=m
 CONFIG_CRYPTO_KEYWRAP=m
 CONFIG_CRYPTO_ADIANTUM=m
 CONFIG_CRYPTO_XCBC=m
@@ -622,6 +618,7 @@ CONFIG_TEST_OVERFLOW=m
 CONFIG_TEST_RHASHTABLE=m
 CONFIG_TEST_HASH=m
 CONFIG_TEST_IDA=m
+CONFIG_TEST_VMALLOC=m
 CONFIG_TEST_USER_COPY=m
 CONFIG_TEST_BPF=m
 CONFIG_FIND_BIT_BENCHMARK=m
@@ -631,4 +628,5 @@ CONFIG_TEST_UDELAY=m
 CONFIG_TEST_STATIC_KEYS=m
 CONFIG_TEST_KMOD=m
 CONFIG_TEST_MEMCAT_P=m
+CONFIG_TEST_STACKINIT=m
 CONFIG_EARLY_PRINTK=y
diff --git a/arch/m68k/configs/bvme6000_defconfig b/arch/m68k/configs/bvme6000_defconfig
index b0d3609f5bb3..699df9fdf866 100644
--- a/arch/m68k/configs/bvme6000_defconfig
+++ b/arch/m68k/configs/bvme6000_defconfig
@@ -49,6 +49,7 @@ CONFIG_TLS=m
 CONFIG_XFRM_MIGRATE=y
 CONFIG_NET_KEY=y
 CONFIG_XDP_SOCKETS=y
+CONFIG_XDP_SOCKETS_DIAG=m
 CONFIG_INET=y
 CONFIG_IP_PNP=y
 CONFIG_IP_PNP_DHCP=y
@@ -203,9 +204,6 @@ CONFIG_NFT_FIB_IPV4=m
 CONFIG_NF_TABLES_ARP=y
 CONFIG_NF_FLOW_TABLE_IPV4=m
 CONFIG_NF_LOG_ARP=m
-CONFIG_NFT_CHAIN_NAT_IPV4=m
-CONFIG_NFT_MASQ_IPV4=m
-CONFIG_NFT_REDIR_IPV4=m
 CONFIG_IP_NF_IPTABLES=m
 CONFIG_IP_NF_MATCH_AH=m
 CONFIG_IP_NF_MATCH_ECN=m
@@ -227,9 +225,6 @@ CONFIG_IP_NF_ARPTABLES=m
 CONFIG_IP_NF_ARPFILTER=m
 CONFIG_IP_NF_ARP_MANGLE=m
 CONFIG_NFT_CHAIN_ROUTE_IPV6=m
-CONFIG_NFT_CHAIN_NAT_IPV6=m
-CONFIG_NFT_MASQ_IPV6=m
-CONFIG_NFT_REDIR_IPV6=m
 CONFIG_NFT_DUP_IPV6=m
 CONFIG_NFT_FIB_IPV6=m
 CONFIG_NF_FLOW_TABLE_IPV6=m
@@ -306,7 +301,6 @@ CONFIG_AF_KCM=m
 # CONFIG_WIRELESS is not set
 CONFIG_PSAMPLE=m
 CONFIG_NET_IFE=m
-CONFIG_NET_DEVLINK=m
 # CONFIG_UEVENT_HELPER is not set
 CONFIG_DEVTMPFS=y
 CONFIG_DEVTMPFS_MOUNT=y
@@ -413,12 +407,12 @@ CONFIG_RTC_DRV_GENERIC=m
 # CONFIG_VIRTIO_MENU is not set
 # CONFIG_IOMMU_SUPPORT is not set
 CONFIG_DAX=m
+# CONFIG_VALIDATE_FS_PARSER is not set
 CONFIG_EXT4_FS=y
 CONFIG_REISERFS_FS=m
 CONFIG_JFS_FS=m
 CONFIG_OCFS2_FS=m
 # CONFIG_OCFS2_DEBUG_MASKLOG is not set
-CONFIG_FS_ENCRYPTION=m
 CONFIG_FANOTIFY=y
 CONFIG_QUOTA_NETLINK_INTERFACE=y
 # CONFIG_PRINT_QUOTA_WARNING is not set
@@ -526,9 +520,11 @@ CONFIG_CRYPTO_AEGIS256=m
 CONFIG_CRYPTO_MORUS640=m
 CONFIG_CRYPTO_MORUS1280=m
 CONFIG_CRYPTO_CFB=m
+CONFIG_CRYPTO_CTS=m
 CONFIG_CRYPTO_LRW=m
 CONFIG_CRYPTO_OFB=m
 CONFIG_CRYPTO_PCBC=m
+CONFIG_CRYPTO_XTS=m
 CONFIG_CRYPTO_KEYWRAP=m
 CONFIG_CRYPTO_ADIANTUM=m
 CONFIG_CRYPTO_XCBC=m
@@ -593,6 +589,7 @@ CONFIG_TEST_OVERFLOW=m
 CONFIG_TEST_RHASHTABLE=m
 CONFIG_TEST_HASH=m
 CONFIG_TEST_IDA=m
+CONFIG_TEST_VMALLOC=m
 CONFIG_TEST_USER_COPY=m
 CONFIG_TEST_BPF=m
 CONFIG_FIND_BIT_BENCHMARK=m
@@ -602,4 +599,5 @@ CONFIG_TEST_UDELAY=m
 CONFIG_TEST_STATIC_KEYS=m
 CONFIG_TEST_KMOD=m
 CONFIG_TEST_MEMCAT_P=m
+CONFIG_TEST_STACKINIT=m
 CONFIG_EARLY_PRINTK=y
diff --git a/arch/m68k/configs/hp300_defconfig b/arch/m68k/configs/hp300_defconfig
index 4ed7c151347c..b50802255324 100644
--- a/arch/m68k/configs/hp300_defconfig
+++ b/arch/m68k/configs/hp300_defconfig
@@ -51,6 +51,7 @@ CONFIG_TLS=m
 CONFIG_XFRM_MIGRATE=y
 CONFIG_NET_KEY=y
 CONFIG_XDP_SOCKETS=y
+CONFIG_XDP_SOCKETS_DIAG=m
 CONFIG_INET=y
 CONFIG_IP_PNP=y
 CONFIG_IP_PNP_DHCP=y
@@ -205,9 +206,6 @@ CONFIG_NFT_FIB_IPV4=m
 CONFIG_NF_TABLES_ARP=y
 CONFIG_NF_FLOW_TABLE_IPV4=m
 CONFIG_NF_LOG_ARP=m
-CONFIG_NFT_CHAIN_NAT_IPV4=m
-CONFIG_NFT_MASQ_IPV4=m
-CONFIG_NFT_REDIR_IPV4=m
 CONFIG_IP_NF_IPTABLES=m
 CONFIG_IP_NF_MATCH_AH=m
 CONFIG_IP_NF_MATCH_ECN=m
@@ -229,9 +227,6 @@ CONFIG_IP_NF_ARPTABLES=m
 CONFIG_IP_NF_ARPFILTER=m
 CONFIG_IP_NF_ARP_MANGLE=m
 CONFIG_NFT_CHAIN_ROUTE_IPV6=m
-CONFIG_NFT_CHAIN_NAT_IPV6=m
-CONFIG_NFT_MASQ_IPV6=m
-CONFIG_NFT_REDIR_IPV6=m
 CONFIG_NFT_DUP_IPV6=m
 CONFIG_NFT_FIB_IPV6=m
 CONFIG_NF_FLOW_TABLE_IPV6=m
@@ -308,7 +303,6 @@ CONFIG_AF_KCM=m
 # CONFIG_WIRELESS is not set
 CONFIG_PSAMPLE=m
 CONFIG_NET_IFE=m
-CONFIG_NET_DEVLINK=m
 # CONFIG_UEVENT_HELPER is not set
 CONFIG_DEVTMPFS=y
 CONFIG_DEVTMPFS_MOUNT=y
@@ -422,12 +416,12 @@ CONFIG_RTC_DRV_GENERIC=m
 # CONFIG_VIRTIO_MENU is not set
 # CONFIG_IOMMU_SUPPORT is not set
 CONFIG_DAX=m
+# CONFIG_VALIDATE_FS_PARSER is not set
 CONFIG_EXT4_FS=y
 CONFIG_REISERFS_FS=m
 CONFIG_JFS_FS=m
 CONFIG_OCFS2_FS=m
 # CONFIG_OCFS2_DEBUG_MASKLOG is not set
-CONFIG_FS_ENCRYPTION=m
 CONFIG_FANOTIFY=y
 CONFIG_QUOTA_NETLINK_INTERFACE=y
 # CONFIG_PRINT_QUOTA_WARNING is not set
@@ -535,9 +529,11 @@ CONFIG_CRYPTO_AEGIS256=m
 CONFIG_CRYPTO_MORUS640=m
 CONFIG_CRYPTO_MORUS1280=m
 CONFIG_CRYPTO_CFB=m
+CONFIG_CRYPTO_CTS=m
 CONFIG_CRYPTO_LRW=m
 CONFIG_CRYPTO_OFB=m
 CONFIG_CRYPTO_PCBC=m
+CONFIG_CRYPTO_XTS=m
 CONFIG_CRYPTO_KEYWRAP=m
 CONFIG_CRYPTO_ADIANTUM=m
 CONFIG_CRYPTO_XCBC=m
@@ -602,6 +598,7 @@ CONFIG_TEST_OVERFLOW=m
 CONFIG_TEST_RHASHTABLE=m
 CONFIG_TEST_HASH=m
 CONFIG_TEST_IDA=m
+CONFIG_TEST_VMALLOC=m
 CONFIG_TEST_USER_COPY=m
 CONFIG_TEST_BPF=m
 CONFIG_FIND_BIT_BENCHMARK=m
@@ -611,4 +608,5 @@ CONFIG_TEST_UDELAY=m
 CONFIG_TEST_STATIC_KEYS=m
 CONFIG_TEST_KMOD=m
 CONFIG_TEST_MEMCAT_P=m
+CONFIG_TEST_STACKINIT=m
 CONFIG_EARLY_PRINTK=y
diff --git a/arch/m68k/configs/mac_defconfig b/arch/m68k/configs/mac_defconfig
index 0dc544e1ce1f..04e7d70f6030 100644
--- a/arch/m68k/configs/mac_defconfig
+++ b/arch/m68k/configs/mac_defconfig
@@ -50,6 +50,7 @@ CONFIG_TLS=m
 CONFIG_XFRM_MIGRATE=y
 CONFIG_NET_KEY=y
 CONFIG_XDP_SOCKETS=y
+CONFIG_XDP_SOCKETS_DIAG=m
 CONFIG_INET=y
 CONFIG_IP_PNP=y
 CONFIG_IP_PNP_DHCP=y
@@ -204,9 +205,6 @@ CONFIG_NFT_FIB_IPV4=m
 CONFIG_NF_TABLES_ARP=y
 CONFIG_NF_FLOW_TABLE_IPV4=m
 CONFIG_NF_LOG_ARP=m
-CONFIG_NFT_CHAIN_NAT_IPV4=m
-CONFIG_NFT_MASQ_IPV4=m
-CONFIG_NFT_REDIR_IPV4=m
 CONFIG_IP_NF_IPTABLES=m
 CONFIG_IP_NF_MATCH_AH=m
 CONFIG_IP_NF_MATCH_ECN=m
@@ -228,9 +226,6 @@ CONFIG_IP_NF_ARPTABLES=m
 CONFIG_IP_NF_ARPFILTER=m
 CONFIG_IP_NF_ARP_MANGLE=m
 CONFIG_NFT_CHAIN_ROUTE_IPV6=m
-CONFIG_NFT_CHAIN_NAT_IPV6=m
-CONFIG_NFT_MASQ_IPV6=m
-CONFIG_NFT_REDIR_IPV6=m
 CONFIG_NFT_DUP_IPV6=m
 CONFIG_NFT_FIB_IPV6=m
 CONFIG_NF_FLOW_TABLE_IPV6=m
@@ -310,7 +305,6 @@ CONFIG_AF_KCM=m
 # CONFIG_WIRELESS is not set
 CONFIG_PSAMPLE=m
 CONFIG_NET_IFE=m
-CONFIG_NET_DEVLINK=m
 # CONFIG_UEVENT_HELPER is not set
 CONFIG_DEVTMPFS=y
 CONFIG_DEVTMPFS_MOUNT=y
@@ -444,12 +438,12 @@ CONFIG_RTC_DRV_GENERIC=m
 # CONFIG_VIRTIO_MENU is not set
 # CONFIG_IOMMU_SUPPORT is not set
 CONFIG_DAX=m
+# CONFIG_VALIDATE_FS_PARSER is not set
 CONFIG_EXT4_FS=y
 CONFIG_REISERFS_FS=m
 CONFIG_JFS_FS=m
 CONFIG_OCFS2_FS=m
 # CONFIG_OCFS2_DEBUG_MASKLOG is not set
-CONFIG_FS_ENCRYPTION=m
 CONFIG_FANOTIFY=y
 CONFIG_QUOTA_NETLINK_INTERFACE=y
 # CONFIG_PRINT_QUOTA_WARNING is not set
@@ -557,9 +551,11 @@ CONFIG_CRYPTO_AEGIS256=m
 CONFIG_CRYPTO_MORUS640=m
 CONFIG_CRYPTO_MORUS1280=m
 CONFIG_CRYPTO_CFB=m
+CONFIG_CRYPTO_CTS=m
 CONFIG_CRYPTO_LRW=m
 CONFIG_CRYPTO_OFB=m
 CONFIG_CRYPTO_PCBC=m
+CONFIG_CRYPTO_XTS=m
 CONFIG_CRYPTO_KEYWRAP=m
 CONFIG_CRYPTO_ADIANTUM=m
 CONFIG_CRYPTO_XCBC=m
@@ -624,6 +620,7 @@ CONFIG_TEST_OVERFLOW=m
 CONFIG_TEST_RHASHTABLE=m
 CONFIG_TEST_HASH=m
 CONFIG_TEST_IDA=m
+CONFIG_TEST_VMALLOC=m
 CONFIG_TEST_USER_COPY=m
 CONFIG_TEST_BPF=m
 CONFIG_FIND_BIT_BENCHMARK=m
@@ -633,4 +630,5 @@ CONFIG_TEST_UDELAY=m
 CONFIG_TEST_STATIC_KEYS=m
 CONFIG_TEST_KMOD=m
 CONFIG_TEST_MEMCAT_P=m
+CONFIG_TEST_STACKINIT=m
 CONFIG_EARLY_PRINTK=y
diff --git a/arch/m68k/configs/multi_defconfig b/arch/m68k/configs/multi_defconfig
index 5a7b7b0d6e72..5e1cc4c17852 100644
--- a/arch/m68k/configs/multi_defconfig
+++ b/arch/m68k/configs/multi_defconfig
@@ -70,6 +70,7 @@ CONFIG_TLS=m
 CONFIG_XFRM_MIGRATE=y
 CONFIG_NET_KEY=y
 CONFIG_XDP_SOCKETS=y
+CONFIG_XDP_SOCKETS_DIAG=m
 CONFIG_INET=y
 CONFIG_IP_PNP=y
 CONFIG_IP_PNP_DHCP=y
@@ -224,9 +225,6 @@ CONFIG_NFT_FIB_IPV4=m
 CONFIG_NF_TABLES_ARP=y
 CONFIG_NF_FLOW_TABLE_IPV4=m
 CONFIG_NF_LOG_ARP=m
-CONFIG_NFT_CHAIN_NAT_IPV4=m
-CONFIG_NFT_MASQ_IPV4=m
-CONFIG_NFT_REDIR_IPV4=m
 CONFIG_IP_NF_IPTABLES=m
 CONFIG_IP_NF_MATCH_AH=m
 CONFIG_IP_NF_MATCH_ECN=m
@@ -248,9 +246,6 @@ CONFIG_IP_NF_ARPTABLES=m
 CONFIG_IP_NF_ARPFILTER=m
 CONFIG_IP_NF_ARP_MANGLE=m
 CONFIG_NFT_CHAIN_ROUTE_IPV6=m
-CONFIG_NFT_CHAIN_NAT_IPV6=m
-CONFIG_NFT_MASQ_IPV6=m
-CONFIG_NFT_REDIR_IPV6=m
 CONFIG_NFT_DUP_IPV6=m
 CONFIG_NFT_FIB_IPV6=m
 CONFIG_NF_FLOW_TABLE_IPV6=m
@@ -330,7 +325,6 @@ CONFIG_AF_KCM=m
 # CONFIG_WIRELESS is not set
 CONFIG_PSAMPLE=m
 CONFIG_NET_IFE=m
-CONFIG_NET_DEVLINK=m
 # CONFIG_UEVENT_HELPER is not set
 CONFIG_DEVTMPFS=y
 CONFIG_DEVTMPFS_MOUNT=y
@@ -526,12 +520,12 @@ CONFIG_RTC_DRV_GENERIC=m
 # CONFIG_VIRTIO_MENU is not set
 # CONFIG_IOMMU_SUPPORT is not set
 CONFIG_DAX=m
+# CONFIG_VALIDATE_FS_PARSER is not set
 CONFIG_EXT4_FS=y
 CONFIG_REISERFS_FS=m
 CONFIG_JFS_FS=m
 CONFIG_OCFS2_FS=m
 # CONFIG_OCFS2_DEBUG_MASKLOG is not set
-CONFIG_FS_ENCRYPTION=m
 CONFIG_FANOTIFY=y
 CONFIG_QUOTA_NETLINK_INTERFACE=y
 # CONFIG_PRINT_QUOTA_WARNING is not set
@@ -639,9 +633,11 @@ CONFIG_CRYPTO_AEGIS256=m
 CONFIG_CRYPTO_MORUS640=m
 CONFIG_CRYPTO_MORUS1280=m
 CONFIG_CRYPTO_CFB=m
+CONFIG_CRYPTO_CTS=m
 CONFIG_CRYPTO_LRW=m
 CONFIG_CRYPTO_OFB=m
 CONFIG_CRYPTO_PCBC=m
+CONFIG_CRYPTO_XTS=m
 CONFIG_CRYPTO_KEYWRAP=m
 CONFIG_CRYPTO_ADIANTUM=m
 CONFIG_CRYPTO_XCBC=m
@@ -706,6 +702,7 @@ CONFIG_TEST_OVERFLOW=m
 CONFIG_TEST_RHASHTABLE=m
 CONFIG_TEST_HASH=m
 CONFIG_TEST_IDA=m
+CONFIG_TEST_VMALLOC=m
 CONFIG_TEST_USER_COPY=m
 CONFIG_TEST_BPF=m
 CONFIG_FIND_BIT_BENCHMARK=m
@@ -715,4 +712,5 @@ CONFIG_TEST_UDELAY=m
 CONFIG_TEST_STATIC_KEYS=m
 CONFIG_TEST_KMOD=m
 CONFIG_TEST_MEMCAT_P=m
+CONFIG_TEST_STACKINIT=m
 CONFIG_EARLY_PRINTK=y
diff --git a/arch/m68k/configs/mvme147_defconfig b/arch/m68k/configs/mvme147_defconfig
index 71eb9be1803b..170ac8792c2d 100644
--- a/arch/m68k/configs/mvme147_defconfig
+++ b/arch/m68k/configs/mvme147_defconfig
@@ -48,6 +48,7 @@ CONFIG_TLS=m
 CONFIG_XFRM_MIGRATE=y
 CONFIG_NET_KEY=y
 CONFIG_XDP_SOCKETS=y
+CONFIG_XDP_SOCKETS_DIAG=m
 CONFIG_INET=y
 CONFIG_IP_PNP=y
 CONFIG_IP_PNP_DHCP=y
@@ -202,9 +203,6 @@ CONFIG_NFT_FIB_IPV4=m
 CONFIG_NF_TABLES_ARP=y
 CONFIG_NF_FLOW_TABLE_IPV4=m
 CONFIG_NF_LOG_ARP=m
-CONFIG_NFT_CHAIN_NAT_IPV4=m
-CONFIG_NFT_MASQ_IPV4=m
-CONFIG_NFT_REDIR_IPV4=m
 CONFIG_IP_NF_IPTABLES=m
 CONFIG_IP_NF_MATCH_AH=m
 CONFIG_IP_NF_MATCH_ECN=m
@@ -226,9 +224,6 @@ CONFIG_IP_NF_ARPTABLES=m
 CONFIG_IP_NF_ARPFILTER=m
 CONFIG_IP_NF_ARP_MANGLE=m
 CONFIG_NFT_CHAIN_ROUTE_IPV6=m
-CONFIG_NFT_CHAIN_NAT_IPV6=m
-CONFIG_NFT_MASQ_IPV6=m
-CONFIG_NFT_REDIR_IPV6=m
 CONFIG_NFT_DUP_IPV6=m
 CONFIG_NFT_FIB_IPV6=m
 CONFIG_NF_FLOW_TABLE_IPV6=m
@@ -305,7 +300,6 @@ CONFIG_AF_KCM=m
 # CONFIG_WIRELESS is not set
 CONFIG_PSAMPLE=m
 CONFIG_NET_IFE=m
-CONFIG_NET_DEVLINK=m
 # CONFIG_UEVENT_HELPER is not set
 CONFIG_DEVTMPFS=y
 CONFIG_DEVTMPFS_MOUNT=y
@@ -412,12 +406,12 @@ CONFIG_RTC_DRV_GENERIC=m
 # CONFIG_VIRTIO_MENU is not set
 # CONFIG_IOMMU_SUPPORT is not set
 CONFIG_DAX=m
+# CONFIG_VALIDATE_FS_PARSER is not set
 CONFIG_EXT4_FS=y
 CONFIG_REISERFS_FS=m
 CONFIG_JFS_FS=m
 CONFIG_OCFS2_FS=m
 # CONFIG_OCFS2_DEBUG_MASKLOG is not set
-CONFIG_FS_ENCRYPTION=m
 CONFIG_FANOTIFY=y
 CONFIG_QUOTA_NETLINK_INTERFACE=y
 # CONFIG_PRINT_QUOTA_WARNING is not set
@@ -525,9 +519,11 @@ CONFIG_CRYPTO_AEGIS256=m
 CONFIG_CRYPTO_MORUS640=m
 CONFIG_CRYPTO_MORUS1280=m
 CONFIG_CRYPTO_CFB=m
+CONFIG_CRYPTO_CTS=m
 CONFIG_CRYPTO_LRW=m
 CONFIG_CRYPTO_OFB=m
 CONFIG_CRYPTO_PCBC=m
+CONFIG_CRYPTO_XTS=m
 CONFIG_CRYPTO_KEYWRAP=m
 CONFIG_CRYPTO_ADIANTUM=m
 CONFIG_CRYPTO_XCBC=m
@@ -592,6 +588,7 @@ CONFIG_TEST_OVERFLOW=m
 CONFIG_TEST_RHASHTABLE=m
 CONFIG_TEST_HASH=m
 CONFIG_TEST_IDA=m
+CONFIG_TEST_VMALLOC=m
 CONFIG_TEST_USER_COPY=m
 CONFIG_TEST_BPF=m
 CONFIG_FIND_BIT_BENCHMARK=m
@@ -601,4 +598,5 @@ CONFIG_TEST_UDELAY=m
 CONFIG_TEST_STATIC_KEYS=m
 CONFIG_TEST_KMOD=m
 CONFIG_TEST_MEMCAT_P=m
+CONFIG_TEST_STACKINIT=m
 CONFIG_EARLY_PRINTK=y
diff --git a/arch/m68k/configs/mvme16x_defconfig b/arch/m68k/configs/mvme16x_defconfig
index ea2ebd4241c0..d865592a423e 100644
--- a/arch/m68k/configs/mvme16x_defconfig
+++ b/arch/m68k/configs/mvme16x_defconfig
@@ -49,6 +49,7 @@ CONFIG_TLS=m
 CONFIG_XFRM_MIGRATE=y
 CONFIG_NET_KEY=y
 CONFIG_XDP_SOCKETS=y
+CONFIG_XDP_SOCKETS_DIAG=m
 CONFIG_INET=y
 CONFIG_IP_PNP=y
 CONFIG_IP_PNP_DHCP=y
@@ -203,9 +204,6 @@ CONFIG_NFT_FIB_IPV4=m
 CONFIG_NF_TABLES_ARP=y
 CONFIG_NF_FLOW_TABLE_IPV4=m
 CONFIG_NF_LOG_ARP=m
-CONFIG_NFT_CHAIN_NAT_IPV4=m
-CONFIG_NFT_MASQ_IPV4=m
-CONFIG_NFT_REDIR_IPV4=m
 CONFIG_IP_NF_IPTABLES=m
 CONFIG_IP_NF_MATCH_AH=m
 CONFIG_IP_NF_MATCH_ECN=m
@@ -227,9 +225,6 @@ CONFIG_IP_NF_ARPTABLES=m
 CONFIG_IP_NF_ARPFILTER=m
 CONFIG_IP_NF_ARP_MANGLE=m
 CONFIG_NFT_CHAIN_ROUTE_IPV6=m
-CONFIG_NFT_CHAIN_NAT_IPV6=m
-CONFIG_NFT_MASQ_IPV6=m
-CONFIG_NFT_REDIR_IPV6=m
 CONFIG_NFT_DUP_IPV6=m
 CONFIG_NFT_FIB_IPV6=m
 CONFIG_NF_FLOW_TABLE_IPV6=m
@@ -306,7 +301,6 @@ CONFIG_AF_KCM=m
 # CONFIG_WIRELESS is not set
 CONFIG_PSAMPLE=m
 CONFIG_NET_IFE=m
-CONFIG_NET_DEVLINK=m
 # CONFIG_UEVENT_HELPER is not set
 CONFIG_DEVTMPFS=y
 CONFIG_DEVTMPFS_MOUNT=y
@@ -413,12 +407,12 @@ CONFIG_RTC_DRV_GENERIC=m
 # CONFIG_VIRTIO_MENU is not set
 # CONFIG_IOMMU_SUPPORT is not set
 CONFIG_DAX=m
+# CONFIG_VALIDATE_FS_PARSER is not set
 CONFIG_EXT4_FS=y
 CONFIG_REISERFS_FS=m
 CONFIG_JFS_FS=m
 CONFIG_OCFS2_FS=m
 # CONFIG_OCFS2_DEBUG_MASKLOG is not set
-CONFIG_FS_ENCRYPTION=m
 CONFIG_FANOTIFY=y
 CONFIG_QUOTA_NETLINK_INTERFACE=y
 # CONFIG_PRINT_QUOTA_WARNING is not set
@@ -526,9 +520,11 @@ CONFIG_CRYPTO_AEGIS256=m
 CONFIG_CRYPTO_MORUS640=m
 CONFIG_CRYPTO_MORUS1280=m
 CONFIG_CRYPTO_CFB=m
+CONFIG_CRYPTO_CTS=m
 CONFIG_CRYPTO_LRW=m
 CONFIG_CRYPTO_OFB=m
 CONFIG_CRYPTO_PCBC=m
+CONFIG_CRYPTO_XTS=m
 CONFIG_CRYPTO_KEYWRAP=m
 CONFIG_CRYPTO_ADIANTUM=m
 CONFIG_CRYPTO_XCBC=m
@@ -593,6 +589,7 @@ CONFIG_TEST_OVERFLOW=m
 CONFIG_TEST_RHASHTABLE=m
 CONFIG_TEST_HASH=m
 CONFIG_TEST_IDA=m
+CONFIG_TEST_VMALLOC=m
 CONFIG_TEST_USER_COPY=m
 CONFIG_TEST_BPF=m
 CONFIG_FIND_BIT_BENCHMARK=m
@@ -602,4 +599,5 @@ CONFIG_TEST_UDELAY=m
 CONFIG_TEST_STATIC_KEYS=m
 CONFIG_TEST_KMOD=m
 CONFIG_TEST_MEMCAT_P=m
+CONFIG_TEST_STACKINIT=m
 CONFIG_EARLY_PRINTK=y
diff --git a/arch/m68k/configs/q40_defconfig b/arch/m68k/configs/q40_defconfig
index cef6dc47c725..034a9de90484 100644
--- a/arch/m68k/configs/q40_defconfig
+++ b/arch/m68k/configs/q40_defconfig
@@ -50,6 +50,7 @@ CONFIG_TLS=m
 CONFIG_XFRM_MIGRATE=y
 CONFIG_NET_KEY=y
 CONFIG_XDP_SOCKETS=y
+CONFIG_XDP_SOCKETS_DIAG=m
 CONFIG_INET=y
 CONFIG_IP_PNP=y
 CONFIG_IP_PNP_DHCP=y
@@ -204,9 +205,6 @@ CONFIG_NFT_FIB_IPV4=m
 CONFIG_NF_TABLES_ARP=y
 CONFIG_NF_FLOW_TABLE_IPV4=m
 CONFIG_NF_LOG_ARP=m
-CONFIG_NFT_CHAIN_NAT_IPV4=m
-CONFIG_NFT_MASQ_IPV4=m
-CONFIG_NFT_REDIR_IPV4=m
 CONFIG_IP_NF_IPTABLES=m
 CONFIG_IP_NF_MATCH_AH=m
 CONFIG_IP_NF_MATCH_ECN=m
@@ -228,9 +226,6 @@ CONFIG_IP_NF_ARPTABLES=m
 CONFIG_IP_NF_ARPFILTER=m
 CONFIG_IP_NF_ARP_MANGLE=m
 CONFIG_NFT_CHAIN_ROUTE_IPV6=m
-CONFIG_NFT_CHAIN_NAT_IPV6=m
-CONFIG_NFT_MASQ_IPV6=m
-CONFIG_NFT_REDIR_IPV6=m
 CONFIG_NFT_DUP_IPV6=m
 CONFIG_NFT_FIB_IPV6=m
 CONFIG_NF_FLOW_TABLE_IPV6=m
@@ -307,7 +302,6 @@ CONFIG_AF_KCM=m
 # CONFIG_WIRELESS is not set
 CONFIG_PSAMPLE=m
 CONFIG_NET_IFE=m
-CONFIG_NET_DEVLINK=m
 # CONFIG_UEVENT_HELPER is not set
 CONFIG_DEVTMPFS=y
 CONFIG_DEVTMPFS_MOUNT=y
@@ -431,12 +425,12 @@ CONFIG_RTC_DRV_GENERIC=m
 # CONFIG_VIRTIO_MENU is not set
 # CONFIG_IOMMU_SUPPORT is not set
 CONFIG_DAX=m
+# CONFIG_VALIDATE_FS_PARSER is not set
 CONFIG_EXT4_FS=y
 CONFIG_REISERFS_FS=m
 CONFIG_JFS_FS=m
 CONFIG_OCFS2_FS=m
 # CONFIG_OCFS2_DEBUG_MASKLOG is not set
-CONFIG_FS_ENCRYPTION=m
 CONFIG_FANOTIFY=y
 CONFIG_QUOTA_NETLINK_INTERFACE=y
 # CONFIG_PRINT_QUOTA_WARNING is not set
@@ -544,9 +538,11 @@ CONFIG_CRYPTO_AEGIS256=m
 CONFIG_CRYPTO_MORUS640=m
 CONFIG_CRYPTO_MORUS1280=m
 CONFIG_CRYPTO_CFB=m
+CONFIG_CRYPTO_CTS=m
 CONFIG_CRYPTO_LRW=m
 CONFIG_CRYPTO_OFB=m
 CONFIG_CRYPTO_PCBC=m
+CONFIG_CRYPTO_XTS=m
 CONFIG_CRYPTO_KEYWRAP=m
 CONFIG_CRYPTO_ADIANTUM=m
 CONFIG_CRYPTO_XCBC=m
@@ -611,6 +607,7 @@ CONFIG_TEST_OVERFLOW=m
 CONFIG_TEST_RHASHTABLE=m
 CONFIG_TEST_HASH=m
 CONFIG_TEST_IDA=m
+CONFIG_TEST_VMALLOC=m
 CONFIG_TEST_USER_COPY=m
 CONFIG_TEST_BPF=m
 CONFIG_FIND_BIT_BENCHMARK=m
@@ -620,4 +617,5 @@ CONFIG_TEST_UDELAY=m
 CONFIG_TEST_STATIC_KEYS=m
 CONFIG_TEST_KMOD=m
 CONFIG_TEST_MEMCAT_P=m
+CONFIG_TEST_STACKINIT=m
 CONFIG_EARLY_PRINTK=y
diff --git a/arch/m68k/configs/sun3_defconfig b/arch/m68k/configs/sun3_defconfig
index 69f2282dc4e9..49be0f9fcd8d 100644
--- a/arch/m68k/configs/sun3_defconfig
+++ b/arch/m68k/configs/sun3_defconfig
@@ -46,6 +46,7 @@ CONFIG_TLS=m
 CONFIG_XFRM_MIGRATE=y
 CONFIG_NET_KEY=y
 CONFIG_XDP_SOCKETS=y
+CONFIG_XDP_SOCKETS_DIAG=m
 CONFIG_INET=y
 CONFIG_IP_PNP=y
 CONFIG_IP_PNP_DHCP=y
@@ -200,9 +201,6 @@ CONFIG_NFT_FIB_IPV4=m
 CONFIG_NF_TABLES_ARP=y
 CONFIG_NF_FLOW_TABLE_IPV4=m
 CONFIG_NF_LOG_ARP=m
-CONFIG_NFT_CHAIN_NAT_IPV4=m
-CONFIG_NFT_MASQ_IPV4=m
-CONFIG_NFT_REDIR_IPV4=m
 CONFIG_IP_NF_IPTABLES=m
 CONFIG_IP_NF_MATCH_AH=m
 CONFIG_IP_NF_MATCH_ECN=m
@@ -224,9 +222,6 @@ CONFIG_IP_NF_ARPTABLES=m
 CONFIG_IP_NF_ARPFILTER=m
 CONFIG_IP_NF_ARP_MANGLE=m
 CONFIG_NFT_CHAIN_ROUTE_IPV6=m
-CONFIG_NFT_CHAIN_NAT_IPV6=m
-CONFIG_NFT_MASQ_IPV6=m
-CONFIG_NFT_REDIR_IPV6=m
 CONFIG_NFT_DUP_IPV6=m
 CONFIG_NFT_FIB_IPV6=m
 CONFIG_NF_FLOW_TABLE_IPV6=m
@@ -303,7 +298,6 @@ CONFIG_AF_KCM=m
 # CONFIG_WIRELESS is not set
 CONFIG_PSAMPLE=m
 CONFIG_NET_IFE=m
-CONFIG_NET_DEVLINK=m
 # CONFIG_UEVENT_HELPER is not set
 CONFIG_DEVTMPFS=y
 CONFIG_DEVTMPFS_MOUNT=y
@@ -415,12 +409,12 @@ CONFIG_RTC_DRV_GENERIC=m
 # CONFIG_VIRTIO_MENU is not set
 # CONFIG_IOMMU_SUPPORT is not set
 CONFIG_DAX=m
+# CONFIG_VALIDATE_FS_PARSER is not set
 CONFIG_EXT4_FS=y
 CONFIG_REISERFS_FS=m
 CONFIG_JFS_FS=m
 CONFIG_OCFS2_FS=m
 # CONFIG_OCFS2_DEBUG_MASKLOG is not set
-CONFIG_FS_ENCRYPTION=m
 CONFIG_FANOTIFY=y
 CONFIG_QUOTA_NETLINK_INTERFACE=y
 # CONFIG_PRINT_QUOTA_WARNING is not set
@@ -528,9 +522,11 @@ CONFIG_CRYPTO_AEGIS256=m
 CONFIG_CRYPTO_MORUS640=m
 CONFIG_CRYPTO_MORUS1280=m
 CONFIG_CRYPTO_CFB=m
+CONFIG_CRYPTO_CTS=m
 CONFIG_CRYPTO_LRW=m
 CONFIG_CRYPTO_OFB=m
 CONFIG_CRYPTO_PCBC=m
+CONFIG_CRYPTO_XTS=m
 CONFIG_CRYPTO_KEYWRAP=m
 CONFIG_CRYPTO_ADIANTUM=m
 CONFIG_CRYPTO_XCBC=m
@@ -595,6 +591,7 @@ CONFIG_TEST_OVERFLOW=m
 CONFIG_TEST_RHASHTABLE=m
 CONFIG_TEST_HASH=m
 CONFIG_TEST_IDA=m
+CONFIG_TEST_VMALLOC=m
 CONFIG_TEST_USER_COPY=m
 CONFIG_TEST_BPF=m
 CONFIG_FIND_BIT_BENCHMARK=m
@@ -604,3 +601,4 @@ CONFIG_TEST_UDELAY=m
 CONFIG_TEST_STATIC_KEYS=m
 CONFIG_TEST_KMOD=m
 CONFIG_TEST_MEMCAT_P=m
+CONFIG_TEST_STACKINIT=m
diff --git a/arch/m68k/configs/sun3x_defconfig b/arch/m68k/configs/sun3x_defconfig
index e91267e868b2..a71acf4a6004 100644
--- a/arch/m68k/configs/sun3x_defconfig
+++ b/arch/m68k/configs/sun3x_defconfig
@@ -46,6 +46,7 @@ CONFIG_TLS=m
 CONFIG_XFRM_MIGRATE=y
 CONFIG_NET_KEY=y
 CONFIG_XDP_SOCKETS=y
+CONFIG_XDP_SOCKETS_DIAG=m
 CONFIG_INET=y
 CONFIG_IP_PNP=y
 CONFIG_IP_PNP_DHCP=y
@@ -200,9 +201,6 @@ CONFIG_NFT_FIB_IPV4=m
 CONFIG_NF_TABLES_ARP=y
 CONFIG_NF_FLOW_TABLE_IPV4=m
 CONFIG_NF_LOG_ARP=m
-CONFIG_NFT_CHAIN_NAT_IPV4=m
-CONFIG_NFT_MASQ_IPV4=m
-CONFIG_NFT_REDIR_IPV4=m
 CONFIG_IP_NF_IPTABLES=m
 CONFIG_IP_NF_MATCH_AH=m
 CONFIG_IP_NF_MATCH_ECN=m
@@ -224,9 +222,6 @@ CONFIG_IP_NF_ARPTABLES=m
 CONFIG_IP_NF_ARPFILTER=m
 CONFIG_IP_NF_ARP_MANGLE=m
 CONFIG_NFT_CHAIN_ROUTE_IPV6=m
-CONFIG_NFT_CHAIN_NAT_IPV6=m
-CONFIG_NFT_MASQ_IPV6=m
-CONFIG_NFT_REDIR_IPV6=m
 CONFIG_NFT_DUP_IPV6=m
 CONFIG_NFT_FIB_IPV6=m
 CONFIG_NF_FLOW_TABLE_IPV6=m
@@ -303,7 +298,6 @@ CONFIG_AF_KCM=m
 # CONFIG_WIRELESS is not set
 CONFIG_PSAMPLE=m
 CONFIG_NET_IFE=m
-CONFIG_NET_DEVLINK=m
 # CONFIG_UEVENT_HELPER is not set
 CONFIG_DEVTMPFS=y
 CONFIG_DEVTMPFS_MOUNT=y
@@ -414,12 +408,12 @@ CONFIG_RTC_DRV_GENERIC=m
 # CONFIG_VIRTIO_MENU is not set
 # CONFIG_IOMMU_SUPPORT is not set
 CONFIG_DAX=m
+# CONFIG_VALIDATE_FS_PARSER is not set
 CONFIG_EXT4_FS=y
 CONFIG_REISERFS_FS=m
 CONFIG_JFS_FS=m
 CONFIG_OCFS2_FS=m
 # CONFIG_OCFS2_DEBUG_MASKLOG is not set
-CONFIG_FS_ENCRYPTION=m
 CONFIG_FANOTIFY=y
 CONFIG_QUOTA_NETLINK_INTERFACE=y
 # CONFIG_PRINT_QUOTA_WARNING is not set
@@ -527,9 +521,11 @@ CONFIG_CRYPTO_AEGIS256=m
 CONFIG_CRYPTO_MORUS640=m
 CONFIG_CRYPTO_MORUS1280=m
 CONFIG_CRYPTO_CFB=m
+CONFIG_CRYPTO_CTS=m
 CONFIG_CRYPTO_LRW=m
 CONFIG_CRYPTO_OFB=m
 CONFIG_CRYPTO_PCBC=m
+CONFIG_CRYPTO_XTS=m
 CONFIG_CRYPTO_KEYWRAP=m
 CONFIG_CRYPTO_ADIANTUM=m
 CONFIG_CRYPTO_XCBC=m
@@ -594,6 +590,7 @@ CONFIG_TEST_OVERFLOW=m
 CONFIG_TEST_RHASHTABLE=m
 CONFIG_TEST_HASH=m
 CONFIG_TEST_IDA=m
+CONFIG_TEST_VMALLOC=m
 CONFIG_TEST_USER_COPY=m
 CONFIG_TEST_BPF=m
 CONFIG_FIND_BIT_BENCHMARK=m
@@ -603,4 +600,5 @@ CONFIG_TEST_UDELAY=m
 CONFIG_TEST_STATIC_KEYS=m
 CONFIG_TEST_KMOD=m
 CONFIG_TEST_MEMCAT_P=m
+CONFIG_TEST_STACKINIT=m
 CONFIG_EARLY_PRINTK=y
diff --git a/arch/m68k/hp300/config.c b/arch/m68k/hp300/config.c
index a19bcd23f80b..a161d44fd20b 100644
--- a/arch/m68k/hp300/config.c
+++ b/arch/m68k/hp300/config.c
@@ -254,7 +254,6 @@ void __init config_hp300(void)
 	mach_sched_init      = hp300_sched_init;
 	mach_init_IRQ        = hp300_init_IRQ;
 	mach_get_model       = hp300_get_model;
-	arch_gettimeoffset   = hp300_gettimeoffset;
 	mach_hwclk	     = hp300_hwclk;
 	mach_get_ss	     = hp300_get_ss;
 	mach_reset           = hp300_reset;
diff --git a/arch/m68k/hp300/time.c b/arch/m68k/hp300/time.c
index 289d928a46cb..bfee13e1d0fe 100644
--- a/arch/m68k/hp300/time.c
+++ b/arch/m68k/hp300/time.c
@@ -8,6 +8,7 @@
  */
 
 #include <asm/ptrace.h>
+#include <linux/clocksource.h>
 #include <linux/types.h>
 #include <linux/init.h>
 #include <linux/sched.h>
@@ -19,6 +20,18 @@
 #include <asm/traps.h>
 #include <asm/blinken.h>
 
+static u64 hp300_read_clk(struct clocksource *cs);
+
+static struct clocksource hp300_clk = {
+	.name   = "timer",
+	.rating = 250,
+	.read   = hp300_read_clk,
+	.mask   = CLOCKSOURCE_MASK(32),
+	.flags  = CLOCK_SOURCE_IS_CONTINUOUS,
+};
+
+static u32 clk_total, clk_offset;
+
 /* Clock hardware definitions */
 
 #define CLOCKBASE	0xf05f8000
@@ -28,39 +41,61 @@
 #define	CLKCR3		CLKCR1
 #define	CLKSR		CLKCR2
 #define	CLKMSB1		0x5
+#define	CLKLSB1		0x7
 #define	CLKMSB2		0x9
 #define	CLKMSB3		0xD
 
+#define	CLKSR_INT1	BIT(0)
+
 /* This is for machines which generate the exact clock. */
-#define USECS_PER_JIFFY (1000000/HZ)
 
-#define INTVAL ((10000 / 4) - 1)
+#define HP300_TIMER_CLOCK_FREQ 250000
+#define HP300_TIMER_CYCLES     (HP300_TIMER_CLOCK_FREQ / HZ)
+#define INTVAL                 (HP300_TIMER_CYCLES - 1)
 
 static irqreturn_t hp300_tick(int irq, void *dev_id)
 {
+	irq_handler_t timer_routine = dev_id;
+	unsigned long flags;
 	unsigned long tmp;
-	irq_handler_t vector = dev_id;
+
+	local_irq_save(flags);
 	in_8(CLOCKBASE + CLKSR);
 	asm volatile ("movpw %1@(5),%0" : "=d" (tmp) : "a" (CLOCKBASE));
+	clk_total += INTVAL;
+	clk_offset = 0;
+	timer_routine(0, NULL);
+	local_irq_restore(flags);
+
 	/* Turn off the network and SCSI leds */
 	blinken_leds(0, 0xe0);
-	return vector(irq, NULL);
+	return IRQ_HANDLED;
 }
 
-u32 hp300_gettimeoffset(void)
+static u64 hp300_read_clk(struct clocksource *cs)
 {
-  /* Read current timer 1 value */
-  unsigned char lsb, msb1, msb2;
-  unsigned short ticks;
-
-  msb1 = in_8(CLOCKBASE + 5);
-  lsb = in_8(CLOCKBASE + 7);
-  msb2 = in_8(CLOCKBASE + 5);
-  if (msb1 != msb2)
-    /* A carry happened while we were reading.  Read it again */
-    lsb = in_8(CLOCKBASE + 7);
-  ticks = INTVAL - ((msb2 << 8) | lsb);
-  return ((USECS_PER_JIFFY * ticks) / INTVAL) * 1000;
+	unsigned long flags;
+	unsigned char lsb, msb, msb_new;
+	u32 ticks;
+
+	local_irq_save(flags);
+	/* Read current timer 1 value */
+	msb = in_8(CLOCKBASE + CLKMSB1);
+again:
+	if ((in_8(CLOCKBASE + CLKSR) & CLKSR_INT1) && msb > 0)
+		clk_offset = INTVAL;
+	lsb = in_8(CLOCKBASE + CLKLSB1);
+	msb_new = in_8(CLOCKBASE + CLKMSB1);
+	if (msb_new != msb) {
+		msb = msb_new;
+		goto again;
+	}
+
+	ticks = INTVAL - ((msb << 8) | lsb);
+	ticks += clk_offset + clk_total;
+	local_irq_restore(flags);
+
+	return ticks;
 }
 
 void __init hp300_sched_init(irq_handler_t vector)
@@ -70,9 +105,11 @@ void __init hp300_sched_init(irq_handler_t vector)
 
   asm volatile(" movpw %0,%1@(5)" : : "d" (INTVAL), "a" (CLOCKBASE));
 
-  if (request_irq(IRQ_AUTO_6, hp300_tick, 0, "timer tick", vector))
+  if (request_irq(IRQ_AUTO_6, hp300_tick, IRQF_TIMER, "timer tick", vector))
     pr_err("Couldn't register timer interrupt\n");
 
   out_8(CLOCKBASE + CLKCR2, 0x1);		/* select CR1 */
   out_8(CLOCKBASE + CLKCR1, 0x40);		/* enable irq */
+
+  clocksource_register_hz(&hp300_clk, HP300_TIMER_CLOCK_FREQ);
 }
diff --git a/arch/m68k/hp300/time.h b/arch/m68k/hp300/time.h
index f5583ec4033d..1d77b55cc72a 100644
--- a/arch/m68k/hp300/time.h
+++ b/arch/m68k/hp300/time.h
@@ -1,2 +1 @@
 extern void hp300_sched_init(irq_handler_t vector);
-extern u32 hp300_gettimeoffset(void);
diff --git a/arch/m68k/include/asm/Kbuild b/arch/m68k/include/asm/Kbuild
index 95f8f631c4df..0ddae4a74adb 100644
--- a/arch/m68k/include/asm/Kbuild
+++ b/arch/m68k/include/asm/Kbuild
@@ -13,10 +13,12 @@ generic-y += irq_work.h
 generic-y += kdebug.h
 generic-y += kmap_types.h
 generic-y += kprobes.h
+generic-y += kvm_para.h
 generic-y += local.h
 generic-y += local64.h
 generic-y += mcs_spinlock.h
 generic-y += mm-arch-hooks.h
+generic-y += mmiowb.h
 generic-y += percpu.h
 generic-y += preempt.h
 generic-y += sections.h
diff --git a/arch/m68k/include/asm/io_mm.h b/arch/m68k/include/asm/io_mm.h
index 782b78f8a048..6c03ca5bc436 100644
--- a/arch/m68k/include/asm/io_mm.h
+++ b/arch/m68k/include/asm/io_mm.h
@@ -377,8 +377,6 @@ static inline void isa_delay(void)
 #define writesw(port, buf, nr)    raw_outsw((port), (u16 *)(buf), (nr))
 #define writesl(port, buf, nr)    raw_outsl((port), (u32 *)(buf), (nr))
 
-#define mmiowb()
-
 #ifndef CONFIG_SUN3
 #define IO_SPACE_LIMIT 0xffff
 #else
diff --git a/arch/m68k/include/asm/mvme147hw.h b/arch/m68k/include/asm/mvme147hw.h
index 9c7ff67c5ffd..257b29184af9 100644
--- a/arch/m68k/include/asm/mvme147hw.h
+++ b/arch/m68k/include/asm/mvme147hw.h
@@ -66,7 +66,7 @@ struct pcc_regs {
 #define PCC_INT_ENAB		0x08
 
 #define PCC_TIMER_INT_CLR	0x80
-#define PCC_TIMER_PRELOAD	63936l
+#define PCC_TIMER_CLR_OVF	0x04
 
 #define PCC_LEVEL_ABORT		0x07
 #define PCC_LEVEL_SERIAL	0x04
diff --git a/arch/m68k/include/asm/tlb.h b/arch/m68k/include/asm/tlb.h
index b4b9efb6f963..3c81f6adfc8b 100644
--- a/arch/m68k/include/asm/tlb.h
+++ b/arch/m68k/include/asm/tlb.h
@@ -2,20 +2,6 @@
 #ifndef _M68K_TLB_H
 #define _M68K_TLB_H
 
-/*
- * m68k doesn't need any special per-pte or
- * per-vma handling..
- */
-#define tlb_start_vma(tlb, vma)	do { } while (0)
-#define tlb_end_vma(tlb, vma)	do { } while (0)
-#define __tlb_remove_tlb_entry(tlb, ptep, address)	do { } while (0)
-
-/*
- * .. because we flush the whole mm when it
- * fills up.
- */
-#define tlb_flush(tlb)		flush_tlb_mm((tlb)->mm)
-
 #include <asm-generic/tlb.h>
 
 #endif /* _M68K_TLB_H */
diff --git a/arch/m68k/include/uapi/asm/Kbuild b/arch/m68k/include/uapi/asm/Kbuild
index 8a7ad40be463..7417847dc438 100644
--- a/arch/m68k/include/uapi/asm/Kbuild
+++ b/arch/m68k/include/uapi/asm/Kbuild
@@ -1,2 +1 @@
 generated-y += unistd_32.h
-generic-y += kvm_para.h
diff --git a/arch/m68k/kernel/syscalls/syscall.tbl b/arch/m68k/kernel/syscalls/syscall.tbl
index 125c14178979..df4ec3ec71d1 100644
--- a/arch/m68k/kernel/syscalls/syscall.tbl
+++ b/arch/m68k/kernel/syscalls/syscall.tbl
@@ -423,3 +423,7 @@
 421	common	rt_sigtimedwait_time64		sys_rt_sigtimedwait
 422	common	futex_time64			sys_futex
 423	common	sched_rr_get_interval_time64	sys_sched_rr_get_interval
+424	common	pidfd_send_signal		sys_pidfd_send_signal
+425	common	io_uring_setup			sys_io_uring_setup
+426	common	io_uring_enter			sys_io_uring_enter
+427	common	io_uring_register		sys_io_uring_register
diff --git a/arch/m68k/mac/config.c b/arch/m68k/mac/config.c
index cd9317d53276..11be08f4f750 100644
--- a/arch/m68k/mac/config.c
+++ b/arch/m68k/mac/config.c
@@ -54,8 +54,6 @@ struct mac_booter_data mac_bi_data;
 /* The phys. video addr. - might be bogus on some machines */
 static unsigned long mac_orig_videoaddr;
 
-/* Mac specific timer functions */
-extern u32 mac_gettimeoffset(void);
 extern int mac_hwclk(int, struct rtc_time *);
 extern void iop_preinit(void);
 extern void iop_init(void);
@@ -155,7 +153,6 @@ void __init config_mac(void)
 	mach_sched_init = mac_sched_init;
 	mach_init_IRQ = mac_init_IRQ;
 	mach_get_model = mac_get_model;
-	arch_gettimeoffset = mac_gettimeoffset;
 	mach_hwclk = mac_hwclk;
 	mach_reset = mac_reset;
 	mach_halt = mac_poweroff;
diff --git a/arch/m68k/mac/via.c b/arch/m68k/mac/via.c
index 0b0289459173..3c2cfcb74982 100644
--- a/arch/m68k/mac/via.c
+++ b/arch/m68k/mac/via.c
@@ -23,6 +23,7 @@
  *
  */
 
+#include <linux/clocksource.h>
 #include <linux/types.h>
 #include <linux/kernel.h>
 #include <linux/mm.h>
@@ -55,16 +56,6 @@ static __u8 rbv_clear;
 static int gIER,gIFR,gBufA,gBufB;
 
 /*
- * Timer defs.
- */
-
-#define TICK_SIZE		10000
-#define MAC_CLOCK_TICK		(783300/HZ)		/* ticks per HZ */
-#define MAC_CLOCK_LOW		(MAC_CLOCK_TICK&0xFF)
-#define MAC_CLOCK_HIGH		(MAC_CLOCK_TICK>>8)
-
-
-/*
  * On Macs with a genuine VIA chip there is no way to mask an individual slot
  * interrupt. This limitation also seems to apply to VIA clone logic cores in
  * Quadra-like ASICs. (RBV and OSS machines don't have this limitation.)
@@ -272,22 +263,6 @@ void __init via_init(void)
 }
 
 /*
- * Start the 100 Hz clock
- */
-
-void __init via_init_clock(irq_handler_t func)
-{
-	via1[vACR] |= 0x40;
-	via1[vT1LL] = MAC_CLOCK_LOW;
-	via1[vT1LH] = MAC_CLOCK_HIGH;
-	via1[vT1CL] = MAC_CLOCK_LOW;
-	via1[vT1CH] = MAC_CLOCK_HIGH;
-
-	if (request_irq(IRQ_MAC_TIMER_1, func, 0, "timer", func))
-		pr_err("Couldn't register %s interrupt\n", "timer");
-}
-
-/*
  * Debugging dump, used in various places to see what's going on.
  */
 
@@ -315,29 +290,6 @@ void via_debug_dump(void)
 }
 
 /*
- * This is always executed with interrupts disabled.
- *
- * TBI: get time offset between scheduling timer ticks
- */
-
-u32 mac_gettimeoffset(void)
-{
-	unsigned long ticks, offset = 0;
-
-	/* read VIA1 timer 2 current value */
-	ticks = via1[vT1CL] | (via1[vT1CH] << 8);
-	/* The probability of underflow is less than 2% */
-	if (ticks > MAC_CLOCK_TICK - MAC_CLOCK_TICK / 50)
-		/* Check for pending timer interrupt in VIA1 IFR */
-		if (via1[vIFR] & 0x40) offset = TICK_SIZE;
-
-	ticks = MAC_CLOCK_TICK - ticks;
-	ticks = ticks * 10000L / MAC_CLOCK_TICK;
-
-	return (ticks + offset) * 1000;
-}
-
-/*
  * Flush the L2 cache on Macs that have it by flipping
  * the system into 24-bit mode for an instant.
  */
@@ -440,6 +392,8 @@ void via_nubus_irq_shutdown(int irq)
  * via6522.c :-), disable/pending masks added.
  */
 
+#define VIA_TIMER_1_INT BIT(6)
+
 void via1_irq(struct irq_desc *desc)
 {
 	int irq_num;
@@ -449,6 +403,21 @@ void via1_irq(struct irq_desc *desc)
 	if (!events)
 		return;
 
+	irq_num = IRQ_MAC_TIMER_1;
+	irq_bit = VIA_TIMER_1_INT;
+	if (events & irq_bit) {
+		unsigned long flags;
+
+		local_irq_save(flags);
+		via1[vIFR] = irq_bit;
+		generic_handle_irq(irq_num);
+		local_irq_restore(flags);
+
+		events &= ~irq_bit;
+		if (!events)
+			return;
+	}
+
 	irq_num = VIA1_SOURCE_BASE;
 	irq_bit = 1;
 	do {
@@ -605,3 +574,82 @@ int via2_scsi_drq_pending(void)
 	return via2[gIFR] & (1 << IRQ_IDX(IRQ_MAC_SCSIDRQ));
 }
 EXPORT_SYMBOL(via2_scsi_drq_pending);
+
+/* timer and clock source */
+
+#define VIA_CLOCK_FREQ     783360                /* VIA "phase 2" clock in Hz */
+#define VIA_TIMER_CYCLES   (VIA_CLOCK_FREQ / HZ) /* clock cycles per jiffy */
+
+#define VIA_TC             (VIA_TIMER_CYCLES - 2) /* including 0 and -1 */
+#define VIA_TC_LOW         (VIA_TC & 0xFF)
+#define VIA_TC_HIGH        (VIA_TC >> 8)
+
+static u64 mac_read_clk(struct clocksource *cs);
+
+static struct clocksource mac_clk = {
+	.name   = "via1",
+	.rating = 250,
+	.read   = mac_read_clk,
+	.mask   = CLOCKSOURCE_MASK(32),
+	.flags  = CLOCK_SOURCE_IS_CONTINUOUS,
+};
+
+static u32 clk_total, clk_offset;
+
+static irqreturn_t via_timer_handler(int irq, void *dev_id)
+{
+	irq_handler_t timer_routine = dev_id;
+
+	clk_total += VIA_TIMER_CYCLES;
+	clk_offset = 0;
+	timer_routine(0, NULL);
+
+	return IRQ_HANDLED;
+}
+
+void __init via_init_clock(irq_handler_t timer_routine)
+{
+	if (request_irq(IRQ_MAC_TIMER_1, via_timer_handler, IRQF_TIMER, "timer",
+			timer_routine)) {
+		pr_err("Couldn't register %s interrupt\n", "timer");
+		return;
+	}
+
+	via1[vT1LL] = VIA_TC_LOW;
+	via1[vT1LH] = VIA_TC_HIGH;
+	via1[vT1CL] = VIA_TC_LOW;
+	via1[vT1CH] = VIA_TC_HIGH;
+	via1[vACR] |= 0x40;
+
+	clocksource_register_hz(&mac_clk, VIA_CLOCK_FREQ);
+}
+
+static u64 mac_read_clk(struct clocksource *cs)
+{
+	unsigned long flags;
+	u8 count_high;
+	u16 count;
+	u32 ticks;
+
+	/*
+	 * Timer counter wrap-around is detected with the timer interrupt flag
+	 * but reading the counter low byte (vT1CL) would reset the flag.
+	 * Also, accessing both counter registers is essentially a data race.
+	 * These problems are avoided by ignoring the low byte. Clock accuracy
+	 * is 256 times worse (error can reach 0.327 ms) but CPU overhead is
+	 * reduced by avoiding slow VIA register accesses.
+	 */
+
+	local_irq_save(flags);
+	count_high = via1[vT1CH];
+	if (count_high == 0xFF)
+		count_high = 0;
+	if (count_high > 0 && (via1[vIFR] & VIA_TIMER_1_INT))
+		clk_offset = VIA_TIMER_CYCLES;
+	count = count_high << 8;
+	ticks = VIA_TIMER_CYCLES - count;
+	ticks += clk_offset + clk_total;
+	local_irq_restore(flags);
+
+	return ticks;
+}
diff --git a/arch/m68k/mvme147/config.c b/arch/m68k/mvme147/config.c
index adea549d240e..545a1fe0e119 100644
--- a/arch/m68k/mvme147/config.c
+++ b/arch/m68k/mvme147/config.c
@@ -17,6 +17,7 @@
 #include <linux/kernel.h>
 #include <linux/mm.h>
 #include <linux/tty.h>
+#include <linux/clocksource.h>
 #include <linux/console.h>
 #include <linux/linkage.h>
 #include <linux/init.h>
@@ -38,18 +39,12 @@
 
 static void mvme147_get_model(char *model);
 extern void mvme147_sched_init(irq_handler_t handler);
-extern u32 mvme147_gettimeoffset(void);
 extern int mvme147_hwclk (int, struct rtc_time *);
 extern void mvme147_reset (void);
 
 
 static int bcd2int (unsigned char b);
 
-/* Save tick handler routine pointer, will point to xtime_update() in
- * kernel/time/timekeeping.c, called via mvme147_process_int() */
-
-irq_handler_t tick_handler;
-
 
 int __init mvme147_parse_bootinfo(const struct bi_record *bi)
 {
@@ -89,7 +84,6 @@ void __init config_mvme147(void)
 	mach_max_dma_address	= 0x01000000;
 	mach_sched_init		= mvme147_sched_init;
 	mach_init_IRQ		= mvme147_init_IRQ;
-	arch_gettimeoffset	= mvme147_gettimeoffset;
 	mach_hwclk		= mvme147_hwclk;
 	mach_reset		= mvme147_reset;
 	mach_get_model		= mvme147_get_model;
@@ -99,45 +93,76 @@ void __init config_mvme147(void)
 		vme_brdtype = VME_TYPE_MVME147;
 }
 
+static u64 mvme147_read_clk(struct clocksource *cs);
+
+static struct clocksource mvme147_clk = {
+	.name   = "pcc",
+	.rating = 250,
+	.read   = mvme147_read_clk,
+	.mask   = CLOCKSOURCE_MASK(32),
+	.flags  = CLOCK_SOURCE_IS_CONTINUOUS,
+};
+
+static u32 clk_total;
+
+#define PCC_TIMER_CLOCK_FREQ 160000
+#define PCC_TIMER_CYCLES     (PCC_TIMER_CLOCK_FREQ / HZ)
+#define PCC_TIMER_PRELOAD    (0x10000 - PCC_TIMER_CYCLES)
 
 /* Using pcc tick timer 1 */
 
 static irqreturn_t mvme147_timer_int (int irq, void *dev_id)
 {
+	irq_handler_t timer_routine = dev_id;
+	unsigned long flags;
+
+	local_irq_save(flags);
 	m147_pcc->t1_int_cntrl = PCC_TIMER_INT_CLR;
-	m147_pcc->t1_int_cntrl = PCC_INT_ENAB|PCC_LEVEL_TIMER1;
-	return tick_handler(irq, dev_id);
+	m147_pcc->t1_cntrl = PCC_TIMER_CLR_OVF;
+	clk_total += PCC_TIMER_CYCLES;
+	timer_routine(0, NULL);
+	local_irq_restore(flags);
+
+	return IRQ_HANDLED;
 }
 
 
 void mvme147_sched_init (irq_handler_t timer_routine)
 {
-	tick_handler = timer_routine;
-	if (request_irq(PCC_IRQ_TIMER1, mvme147_timer_int, 0, "timer 1", NULL))
+	if (request_irq(PCC_IRQ_TIMER1, mvme147_timer_int, IRQF_TIMER,
+			"timer 1", timer_routine))
 		pr_err("Couldn't register timer interrupt\n");
 
 	/* Init the clock with a value */
-	/* our clock goes off every 6.25us */
+	/* The clock counter increments until 0xFFFF then reloads */
 	m147_pcc->t1_preload = PCC_TIMER_PRELOAD;
 	m147_pcc->t1_cntrl = 0x0;	/* clear timer */
 	m147_pcc->t1_cntrl = 0x3;	/* start timer */
 	m147_pcc->t1_int_cntrl = PCC_TIMER_INT_CLR;  /* clear pending ints */
 	m147_pcc->t1_int_cntrl = PCC_INT_ENAB|PCC_LEVEL_TIMER1;
+
+	clocksource_register_hz(&mvme147_clk, PCC_TIMER_CLOCK_FREQ);
 }
 
-/* This is always executed with interrupts disabled.  */
-/* XXX There are race hazards in this code XXX */
-u32 mvme147_gettimeoffset(void)
+static u64 mvme147_read_clk(struct clocksource *cs)
 {
-	volatile unsigned short *cp = (volatile unsigned short *)0xfffe1012;
-	unsigned short n;
-
-	n = *cp;
-	while (n != *cp)
-		n = *cp;
-
-	n -= PCC_TIMER_PRELOAD;
-	return ((unsigned long)n * 25 / 4) * 1000;
+	unsigned long flags;
+	u8 overflow, tmp;
+	u16 count;
+	u32 ticks;
+
+	local_irq_save(flags);
+	tmp = m147_pcc->t1_cntrl >> 4;
+	count = m147_pcc->t1_count;
+	overflow = m147_pcc->t1_cntrl >> 4;
+	if (overflow != tmp)
+		count = m147_pcc->t1_count;
+	count -= PCC_TIMER_PRELOAD;
+	ticks = count + overflow * PCC_TIMER_CYCLES;
+	ticks += clk_total;
+	local_irq_restore(flags);
+
+	return ticks;
 }
 
 static int bcd2int (unsigned char b)
diff --git a/arch/m68k/mvme16x/config.c b/arch/m68k/mvme16x/config.c
index 6ee36a5b528d..9bc2da69f80c 100644
--- a/arch/m68k/mvme16x/config.c
+++ b/arch/m68k/mvme16x/config.c
@@ -19,6 +19,7 @@
 #include <linux/mm.h>
 #include <linux/seq_file.h>
 #include <linux/tty.h>
+#include <linux/clocksource.h>
 #include <linux/console.h>
 #include <linux/linkage.h>
 #include <linux/init.h>
@@ -44,17 +45,11 @@ static MK48T08ptr_t volatile rtc = (MK48T08ptr_t)MVME_RTC_BASE;
 
 static void mvme16x_get_model(char *model);
 extern void mvme16x_sched_init(irq_handler_t handler);
-extern u32 mvme16x_gettimeoffset(void);
 extern int mvme16x_hwclk (int, struct rtc_time *);
 extern void mvme16x_reset (void);
 
 int bcd2int (unsigned char b);
 
-/* Save tick handler routine pointer, will point to xtime_update() in
- * kernel/time/timekeeping.c, called via mvme16x_process_int() */
-
-static irq_handler_t tick_handler;
-
 
 unsigned short mvme16x_config;
 EXPORT_SYMBOL(mvme16x_config);
@@ -120,11 +115,11 @@ static void __init mvme16x_init_IRQ (void)
 	m68k_setup_user_interrupt(VEC_USER, 192);
 }
 
-#define pcc2chip	((volatile u_char *)0xfff42000)
-#define PccSCCMICR	0x1d
-#define PccSCCTICR	0x1e
-#define PccSCCRICR	0x1f
-#define PccTPIACKR	0x25
+#define PCC2CHIP   (0xfff42000)
+#define PCCSCCMICR (PCC2CHIP + 0x1d)
+#define PCCSCCTICR (PCC2CHIP + 0x1e)
+#define PCCSCCRICR (PCC2CHIP + 0x1f)
+#define PCCTPIACKR (PCC2CHIP + 0x25)
 
 #ifdef CONFIG_EARLY_PRINTK
 
@@ -232,10 +227,10 @@ void mvme16x_cons_write(struct console *co, const char *str, unsigned count)
 	base_addr[CyIER] = CyTxMpty;
 
 	while (1) {
-		if (pcc2chip[PccSCCTICR] & 0x20)
+		if (in_8(PCCSCCTICR) & 0x20)
 		{
 			/* We have a Tx int. Acknowledge it */
-			sink = pcc2chip[PccTPIACKR];
+			sink = in_8(PCCTPIACKR);
 			if ((base_addr[CyLICR] >> 2) == port) {
 				if (i == count) {
 					/* Last char of string is now output */
@@ -277,7 +272,6 @@ void __init config_mvme16x(void)
     mach_max_dma_address = 0xffffffff;
     mach_sched_init      = mvme16x_sched_init;
     mach_init_IRQ        = mvme16x_init_IRQ;
-    arch_gettimeoffset   = mvme16x_gettimeoffset;
     mach_hwclk           = mvme16x_hwclk;
     mach_reset		 = mvme16x_reset;
     mach_get_model       = mvme16x_get_model;
@@ -350,10 +344,46 @@ static irqreturn_t mvme16x_abort_int (int irq, void *dev_id)
 	return IRQ_HANDLED;
 }
 
+static u64 mvme16x_read_clk(struct clocksource *cs);
+
+static struct clocksource mvme16x_clk = {
+	.name   = "pcc",
+	.rating = 250,
+	.read   = mvme16x_read_clk,
+	.mask   = CLOCKSOURCE_MASK(32),
+	.flags  = CLOCK_SOURCE_IS_CONTINUOUS,
+};
+
+static u32 clk_total;
+
+#define PCC_TIMER_CLOCK_FREQ 1000000
+#define PCC_TIMER_CYCLES     (PCC_TIMER_CLOCK_FREQ / HZ)
+
+#define PCCTCMP1             (PCC2CHIP + 0x04)
+#define PCCTCNT1             (PCC2CHIP + 0x08)
+#define PCCTOVR1             (PCC2CHIP + 0x17)
+#define PCCTIC1              (PCC2CHIP + 0x1b)
+
+#define PCCTOVR1_TIC_EN      0x01
+#define PCCTOVR1_COC_EN      0x02
+#define PCCTOVR1_OVR_CLR     0x04
+
+#define PCCTIC1_INT_CLR      0x08
+#define PCCTIC1_INT_EN       0x10
+
 static irqreturn_t mvme16x_timer_int (int irq, void *dev_id)
 {
-    *(volatile unsigned char *)0xfff4201b |= 8;
-    return tick_handler(irq, dev_id);
+	irq_handler_t timer_routine = dev_id;
+	unsigned long flags;
+
+	local_irq_save(flags);
+	out_8(PCCTIC1, in_8(PCCTIC1) | PCCTIC1_INT_CLR);
+	out_8(PCCTOVR1, PCCTOVR1_OVR_CLR);
+	clk_total += PCC_TIMER_CYCLES;
+	timer_routine(0, NULL);
+	local_irq_restore(flags);
+
+	return IRQ_HANDLED;
 }
 
 void mvme16x_sched_init (irq_handler_t timer_routine)
@@ -361,16 +391,17 @@ void mvme16x_sched_init (irq_handler_t timer_routine)
     uint16_t brdno = be16_to_cpu(mvme_bdid.brdno);
     int irq;
 
-    tick_handler = timer_routine;
     /* Using PCCchip2 or MC2 chip tick timer 1 */
-    *(volatile unsigned long *)0xfff42008 = 0;
-    *(volatile unsigned long *)0xfff42004 = 10000;	/* 10ms */
-    *(volatile unsigned char *)0xfff42017 |= 3;
-    *(volatile unsigned char *)0xfff4201b = 0x16;
-    if (request_irq(MVME16x_IRQ_TIMER, mvme16x_timer_int, 0,
-				"timer", mvme16x_timer_int))
+    out_be32(PCCTCNT1, 0);
+    out_be32(PCCTCMP1, PCC_TIMER_CYCLES);
+    out_8(PCCTOVR1, in_8(PCCTOVR1) | PCCTOVR1_TIC_EN | PCCTOVR1_COC_EN);
+    out_8(PCCTIC1, PCCTIC1_INT_EN | 6);
+    if (request_irq(MVME16x_IRQ_TIMER, mvme16x_timer_int, IRQF_TIMER, "timer",
+                    timer_routine))
 	panic ("Couldn't register timer int");
 
+    clocksource_register_hz(&mvme16x_clk, PCC_TIMER_CLOCK_FREQ);
+
     if (brdno == 0x0162 || brdno == 0x172)
 	irq = MVME162_IRQ_ABORT;
     else
@@ -380,11 +411,23 @@ void mvme16x_sched_init (irq_handler_t timer_routine)
 	panic ("Couldn't register abort int");
 }
 
-
-/* This is always executed with interrupts disabled.  */
-u32 mvme16x_gettimeoffset(void)
+static u64 mvme16x_read_clk(struct clocksource *cs)
 {
-    return (*(volatile u32 *)0xfff42008) * 1000;
+	unsigned long flags;
+	u8 overflow, tmp;
+	u32 ticks;
+
+	local_irq_save(flags);
+	tmp = in_8(PCCTOVR1) >> 4;
+	ticks = in_be32(PCCTCNT1);
+	overflow = in_8(PCCTOVR1) >> 4;
+	if (overflow != tmp)
+		ticks = in_be32(PCCTCNT1);
+	ticks += overflow * PCC_TIMER_CYCLES;
+	ticks += clk_total;
+	local_irq_restore(flags);
+
+	return ticks;
 }
 
 int bcd2int (unsigned char b)
diff --git a/arch/m68k/q40/config.c b/arch/m68k/q40/config.c
index 96810d91da2b..e63eb5f06999 100644
--- a/arch/m68k/q40/config.c
+++ b/arch/m68k/q40/config.c
@@ -40,7 +40,6 @@ extern void q40_init_IRQ(void);
 static void q40_get_model(char *model);
 extern void q40_sched_init(irq_handler_t handler);
 
-static u32 q40_gettimeoffset(void);
 static int q40_hwclk(int, struct rtc_time *);
 static unsigned int q40_get_ss(void);
 static int q40_get_rtc_pll(struct rtc_pll_info *pll);
@@ -169,7 +168,6 @@ void __init config_q40(void)
 	mach_sched_init = q40_sched_init;
 
 	mach_init_IRQ = q40_init_IRQ;
-	arch_gettimeoffset = q40_gettimeoffset;
 	mach_hwclk = q40_hwclk;
 	mach_get_ss = q40_get_ss;
 	mach_get_rtc_pll = q40_get_rtc_pll;
@@ -201,13 +199,6 @@ int __init q40_parse_bootinfo(const struct bi_record *rec)
 	return 1;
 }
 
-
-static u32 q40_gettimeoffset(void)
-{
-	return 5000 * (ql_ticks != 0) * 1000;
-}
-
-
 /*
  * Looks like op is non-zero for setting the clock, and zero for
  * reading the clock.
diff --git a/arch/m68k/q40/q40ints.c b/arch/m68k/q40/q40ints.c
index 3e7603202977..1c696906c159 100644
--- a/arch/m68k/q40/q40ints.c
+++ b/arch/m68k/q40/q40ints.c
@@ -127,10 +127,10 @@ void q40_mksound(unsigned int hz, unsigned int ticks)
 	sound_ticks = ticks << 1;
 }
 
-static irq_handler_t q40_timer_routine;
-
-static irqreturn_t q40_timer_int (int irq, void * dev)
+static irqreturn_t q40_timer_int(int irq, void *dev_id)
 {
+	irq_handler_t timer_routine = dev_id;
+
 	ql_ticks = ql_ticks ? 0 : 1;
 	if (sound_ticks) {
 		unsigned char sval=(sound_ticks & 1) ? 128-SVOL : 128+SVOL;
@@ -139,8 +139,13 @@ static irqreturn_t q40_timer_int (int irq, void * dev)
 		*DAC_RIGHT=sval;
 	}
 
-	if (!ql_ticks)
-		q40_timer_routine(irq, dev);
+	if (!ql_ticks) {
+		unsigned long flags;
+
+		local_irq_save(flags);
+		timer_routine(0, NULL);
+		local_irq_restore(flags);
+	}
 	return IRQ_HANDLED;
 }
 
@@ -148,11 +153,9 @@ void q40_sched_init (irq_handler_t timer_routine)
 {
 	int timer_irq;
 
-	q40_timer_routine = timer_routine;
 	timer_irq = Q40_IRQ_FRAME;
 
-	if (request_irq(timer_irq, q40_timer_int, 0,
-				"timer", q40_timer_int))
+	if (request_irq(timer_irq, q40_timer_int, 0, "timer", timer_routine))
 		panic("Couldn't register timer int");
 
 	master_outb(-1, FRAME_CLEAR_REG);
diff --git a/arch/m68k/sun3/config.c b/arch/m68k/sun3/config.c
index 542c4404861c..229ea37dfe1b 100644
--- a/arch/m68k/sun3/config.c
+++ b/arch/m68k/sun3/config.c
@@ -37,7 +37,6 @@
 
 char sun3_reserved_pmeg[SUN3_PMEGS_NUM];
 
-extern u32 sun3_gettimeoffset(void);
 static void sun3_sched_init(irq_handler_t handler);
 extern void sun3_get_model (char* model);
 extern int sun3_hwclk(int set, struct rtc_time *t);
@@ -138,7 +137,6 @@ void __init config_sun3(void)
         mach_sched_init      =  sun3_sched_init;
         mach_init_IRQ        =  sun3_init_IRQ;
         mach_reset           =  sun3_reboot;
-	arch_gettimeoffset   =  sun3_gettimeoffset;
 	mach_get_model	     =  sun3_get_model;
 	mach_hwclk           =  sun3_hwclk;
 	mach_halt	     =  sun3_halt;
diff --git a/arch/m68k/sun3/intersil.c b/arch/m68k/sun3/intersil.c
index d911070af02a..8fc74864de81 100644
--- a/arch/m68k/sun3/intersil.c
+++ b/arch/m68k/sun3/intersil.c
@@ -22,13 +22,6 @@
 #define STOP_VAL (INTERSIL_STOP | INTERSIL_INT_ENABLE | INTERSIL_24H_MODE)
 #define START_VAL (INTERSIL_RUN | INTERSIL_INT_ENABLE | INTERSIL_24H_MODE)
 
-/* does this need to be implemented? */
-u32 sun3_gettimeoffset(void)
-{
-  return 1000;
-}
-
-
 /* get/set hwclock */
 
 int sun3_hwclk(int set, struct rtc_time *t)
diff --git a/arch/m68k/sun3/sun3ints.c b/arch/m68k/sun3/sun3ints.c
index 6bbca30c9188..a5824abb4a39 100644
--- a/arch/m68k/sun3/sun3ints.c
+++ b/arch/m68k/sun3/sun3ints.c
@@ -61,8 +61,10 @@ static irqreturn_t sun3_int7(int irq, void *dev_id)
 
 static irqreturn_t sun3_int5(int irq, void *dev_id)
 {
+	unsigned long flags;
 	unsigned int cnt;
 
+	local_irq_save(flags);
 #ifdef CONFIG_SUN3
 	intersil_clear();
 #endif
@@ -76,6 +78,7 @@ static irqreturn_t sun3_int5(int irq, void *dev_id)
 	cnt = kstat_irqs_cpu(irq, 0);
 	if (!(cnt % 20))
 		sun3_leds(led_pattern[cnt % 160 / 20]);
+	local_irq_restore(flags);
 	return IRQ_HANDLED;
 }
 
diff --git a/arch/m68k/sun3x/config.c b/arch/m68k/sun3x/config.c
index 33d3a1c6fba0..03ce7f9facfe 100644
--- a/arch/m68k/sun3x/config.c
+++ b/arch/m68k/sun3x/config.c
@@ -49,7 +49,6 @@ void __init config_sun3x(void)
 	mach_sched_init      = sun3x_sched_init;
 	mach_init_IRQ        = sun3_init_IRQ;
 
-	arch_gettimeoffset   = sun3x_gettimeoffset;
 	mach_reset           = sun3x_reboot;
 
 	mach_hwclk           = sun3x_hwclk;
diff --git a/arch/m68k/sun3x/time.c b/arch/m68k/sun3x/time.c
index 047e2bcee3d7..9163294b0fb6 100644
--- a/arch/m68k/sun3x/time.c
+++ b/arch/m68k/sun3x/time.c
@@ -73,22 +73,21 @@ int sun3x_hwclk(int set, struct rtc_time *t)
 
 	return 0;
 }
-/* Not much we can do here */
-u32 sun3x_gettimeoffset(void)
-{
-    return 0L;
-}
 
 #if 0
-static void sun3x_timer_tick(int irq, void *dev_id, struct pt_regs *regs)
+static irqreturn_t sun3x_timer_tick(int irq, void *dev_id)
 {
-    void (*vector)(int, void *, struct pt_regs *) = dev_id;
+	irq_handler_t timer_routine = dev_id;
+	unsigned long flags;
 
-    /* Clear the pending interrupt - pulse the enable line low */
-    disable_irq(5);
-    enable_irq(5);
+	local_irq_save(flags);
+	/* Clear the pending interrupt - pulse the enable line low */
+	disable_irq(5);
+	enable_irq(5);
+	timer_routine(0, NULL);
+	local_irq_restore(flags);
 
-    vector(irq, NULL, regs);
+	return IRQ_HANDLED;
 }
 #endif
 
diff --git a/arch/m68k/sun3x/time.h b/arch/m68k/sun3x/time.h
index 496f406412ad..86ce78bb3c28 100644
--- a/arch/m68k/sun3x/time.h
+++ b/arch/m68k/sun3x/time.h
@@ -3,7 +3,6 @@
 #define SUN3X_TIME_H
 
 extern int sun3x_hwclk(int set, struct rtc_time *t);
-u32 sun3x_gettimeoffset(void);
 void sun3x_sched_init(irq_handler_t vector);
 
 struct mostek_dt {
diff --git a/arch/microblaze/Kconfig b/arch/microblaze/Kconfig
index a51b965b3b82..adb179f519f9 100644
--- a/arch/microblaze/Kconfig
+++ b/arch/microblaze/Kconfig
@@ -41,6 +41,7 @@ config MICROBLAZE
 	select TRACING_SUPPORT
 	select VIRT_TO_BUS
 	select CPU_NO_EFFICIENT_FFS
+	select MMU_GATHER_NO_RANGE if MMU
 
 # Endianness selection
 choice
@@ -58,15 +59,9 @@ config CPU_LITTLE_ENDIAN
 
 endchoice
 
-config RWSEM_GENERIC_SPINLOCK
-	def_bool y
-
 config ZONE_DMA
 	def_bool y
 
-config RWSEM_XCHGADD_ALGORITHM
-	bool
-
 config ARCH_HAS_ILOG2_U32
 	def_bool n
 
diff --git a/arch/microblaze/include/asm/Kbuild b/arch/microblaze/include/asm/Kbuild
index 791cc8d54d0a..17a8d0a62038 100644
--- a/arch/microblaze/include/asm/Kbuild
+++ b/arch/microblaze/include/asm/Kbuild
@@ -17,11 +17,13 @@ generic-y += irq_work.h
 generic-y += kdebug.h
 generic-y += kmap_types.h
 generic-y += kprobes.h
+generic-y += kvm_para.h
 generic-y += linkage.h
 generic-y += local.h
 generic-y += local64.h
 generic-y += mcs_spinlock.h
 generic-y += mm-arch-hooks.h
+generic-y += mmiowb.h
 generic-y += parport.h
 generic-y += percpu.h
 generic-y += preempt.h
diff --git a/arch/microblaze/include/asm/syscall.h b/arch/microblaze/include/asm/syscall.h
index 220decd605a4..833d3a53dab3 100644
--- a/arch/microblaze/include/asm/syscall.h
+++ b/arch/microblaze/include/asm/syscall.h
@@ -82,18 +82,22 @@ static inline void microblaze_set_syscall_arg(struct pt_regs *regs,
 
 static inline void syscall_get_arguments(struct task_struct *task,
 					 struct pt_regs *regs,
-					 unsigned int i, unsigned int n,
 					 unsigned long *args)
 {
+	unsigned int i = 0;
+	unsigned int n = 6;
+
 	while (n--)
 		*args++ = microblaze_get_syscall_arg(regs, i++);
 }
 
 static inline void syscall_set_arguments(struct task_struct *task,
 					 struct pt_regs *regs,
-					 unsigned int i, unsigned int n,
 					 const unsigned long *args)
 {
+	unsigned int i = 0;
+	unsigned int n = 6;
+
 	while (n--)
 		microblaze_set_syscall_arg(regs, i++, *args++);
 }
diff --git a/arch/microblaze/include/asm/tlb.h b/arch/microblaze/include/asm/tlb.h
index 99b6ded54849..628a78ee0a72 100644
--- a/arch/microblaze/include/asm/tlb.h
+++ b/arch/microblaze/include/asm/tlb.h
@@ -11,16 +11,7 @@
 #ifndef _ASM_MICROBLAZE_TLB_H
 #define _ASM_MICROBLAZE_TLB_H
 
-#define tlb_flush(tlb)	flush_tlb_mm((tlb)->mm)
-
 #include <linux/pagemap.h>
-
-#ifdef CONFIG_MMU
-#define tlb_start_vma(tlb, vma)		do { } while (0)
-#define tlb_end_vma(tlb, vma)		do { } while (0)
-#define __tlb_remove_tlb_entry(tlb, pte, address) do { } while (0)
-#endif
-
 #include <asm-generic/tlb.h>
 
 #endif /* _ASM_MICROBLAZE_TLB_H */
diff --git a/arch/microblaze/include/uapi/asm/Kbuild b/arch/microblaze/include/uapi/asm/Kbuild
index 3ce84fbb2678..13f59631c576 100644
--- a/arch/microblaze/include/uapi/asm/Kbuild
+++ b/arch/microblaze/include/uapi/asm/Kbuild
@@ -1,3 +1,2 @@
 generated-y += unistd_32.h
-generic-y += kvm_para.h
 generic-y += ucontext.h
diff --git a/arch/microblaze/kernel/syscalls/syscall.tbl b/arch/microblaze/kernel/syscalls/syscall.tbl
index 8ee3a8c18498..4964947732af 100644
--- a/arch/microblaze/kernel/syscalls/syscall.tbl
+++ b/arch/microblaze/kernel/syscalls/syscall.tbl
@@ -429,3 +429,7 @@
 421	common	rt_sigtimedwait_time64		sys_rt_sigtimedwait
 422	common	futex_time64			sys_futex
 423	common	sched_rr_get_interval_time64	sys_sched_rr_get_interval
+424	common	pidfd_send_signal		sys_pidfd_send_signal
+425	common	io_uring_setup			sys_io_uring_setup
+426	common	io_uring_enter			sys_io_uring_enter
+427	common	io_uring_register		sys_io_uring_register
diff --git a/arch/mips/Kconfig b/arch/mips/Kconfig
index 4a5f5b0ee9a9..b9c48b27162d 100644
--- a/arch/mips/Kconfig
+++ b/arch/mips/Kconfig
@@ -1037,13 +1037,6 @@ source "arch/mips/paravirt/Kconfig"
 
 endmenu
 
-config RWSEM_GENERIC_SPINLOCK
-	bool
-	default y
-
-config RWSEM_XCHGADD_ALGORITHM
-	bool
-
 config GENERIC_HWEIGHT
 	bool
 	default y
diff --git a/arch/mips/ath79/setup.c b/arch/mips/ath79/setup.c
index 4a70c5de8c92..25a57895a3a3 100644
--- a/arch/mips/ath79/setup.c
+++ b/arch/mips/ath79/setup.c
@@ -210,12 +210,6 @@ const char *get_system_type(void)
 	return ath79_sys_type;
 }
 
-int get_c0_perfcount_int(void)
-{
-	return ATH79_MISC_IRQ(5);
-}
-EXPORT_SYMBOL_GPL(get_c0_perfcount_int);
-
 unsigned int get_c0_compare_int(void)
 {
 	return CP0_LEGACY_COMPARE_IRQ;
diff --git a/arch/mips/configs/generic/board-ocelot.config b/arch/mips/configs/generic/board-ocelot.config
index f607888d2483..184eb65a6ba7 100644
--- a/arch/mips/configs/generic/board-ocelot.config
+++ b/arch/mips/configs/generic/board-ocelot.config
@@ -1,6 +1,10 @@
 # require CONFIG_CPU_MIPS32_R2=y
 
 CONFIG_LEGACY_BOARD_OCELOT=y
+CONFIG_FIT_IMAGE_FDT_OCELOT=y
+
+CONFIG_BRIDGE=y
+CONFIG_GENERIC_PHY=y
 
 CONFIG_MTD=y
 CONFIG_MTD_CMDLINE_PARTS=y
@@ -19,6 +23,8 @@ CONFIG_SERIAL_8250_CONSOLE=y
 CONFIG_SERIAL_OF_PLATFORM=y
 
 CONFIG_NETDEVICES=y
+CONFIG_NET_SWITCHDEV=y
+CONFIG_NET_DSA=y
 CONFIG_MSCC_OCELOT_SWITCH=y
 CONFIG_MSCC_OCELOT_SWITCH_OCELOT=y
 CONFIG_MDIO_MSCC_MIIM=y
@@ -35,6 +41,8 @@ CONFIG_SPI_DESIGNWARE=y
 CONFIG_SPI_DW_MMIO=y
 CONFIG_SPI_SPIDEV=y
 
+CONFIG_PINCTRL_OCELOT=y
+
 CONFIG_GPIO_SYSFS=y
 
 CONFIG_POWER_RESET=y
diff --git a/arch/mips/include/asm/io.h b/arch/mips/include/asm/io.h
index 845fbbc7a2e3..29997e42480e 100644
--- a/arch/mips/include/asm/io.h
+++ b/arch/mips/include/asm/io.h
@@ -102,9 +102,6 @@ static inline void set_io_port_base(unsigned long base)
 #define iobarrier_w() wmb()
 #define iobarrier_sync() iob()
 
-/* Some callers use this older API instead.  */
-#define mmiowb() iobarrier_w()
-
 /*
  *     virt_to_phys    -       map virtual addresses to physical
  *     @address: address to remap
diff --git a/arch/mips/include/asm/mmiowb.h b/arch/mips/include/asm/mmiowb.h
new file mode 100644
index 000000000000..a40824e3ef8e
--- /dev/null
+++ b/arch/mips/include/asm/mmiowb.h
@@ -0,0 +1,11 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _ASM_MMIOWB_H
+#define _ASM_MMIOWB_H
+
+#include <asm/io.h>
+
+#define mmiowb()	iobarrier_w()
+
+#include <asm-generic/mmiowb.h>
+
+#endif	/* _ASM_MMIOWB_H */
diff --git a/arch/mips/include/asm/spinlock.h b/arch/mips/include/asm/spinlock.h
index ee81297d9117..8a88eb265516 100644
--- a/arch/mips/include/asm/spinlock.h
+++ b/arch/mips/include/asm/spinlock.h
@@ -11,6 +11,21 @@
 
 #include <asm/processor.h>
 #include <asm/qrwlock.h>
+
+#include <asm-generic/qspinlock_types.h>
+
+#define	queued_spin_unlock queued_spin_unlock
+/**
+ * queued_spin_unlock - release a queued spinlock
+ * @lock : Pointer to queued spinlock structure
+ */
+static inline void queued_spin_unlock(struct qspinlock *lock)
+{
+	/* This could be optimised with ARCH_HAS_MMIOWB */
+	mmiowb();
+	smp_store_release(&lock->locked, 0);
+}
+
 #include <asm/qspinlock.h>
 
 #endif /* _ASM_SPINLOCK_H */
diff --git a/arch/mips/include/asm/syscall.h b/arch/mips/include/asm/syscall.h
index 6cf8ffb5367e..a2b4748655df 100644
--- a/arch/mips/include/asm/syscall.h
+++ b/arch/mips/include/asm/syscall.h
@@ -116,9 +116,10 @@ static inline void syscall_set_return_value(struct task_struct *task,
 
 static inline void syscall_get_arguments(struct task_struct *task,
 					 struct pt_regs *regs,
-					 unsigned int i, unsigned int n,
 					 unsigned long *args)
 {
+	unsigned int i = 0;
+	unsigned int n = 6;
 	int ret;
 
 	/* O32 ABI syscall() */
diff --git a/arch/mips/include/asm/tlb.h b/arch/mips/include/asm/tlb.h
index b6823b9e94da..90f3ad76d9e0 100644
--- a/arch/mips/include/asm/tlb.h
+++ b/arch/mips/include/asm/tlb.h
@@ -5,23 +5,6 @@
 #include <asm/cpu-features.h>
 #include <asm/mipsregs.h>
 
-/*
- * MIPS doesn't need any special per-pte or per-vma handling, except
- * we need to flush cache for area to be unmapped.
- */
-#define tlb_start_vma(tlb, vma)					\
-	do {							\
-		if (!tlb->fullmm)				\
-			flush_cache_range(vma, vma->vm_start, vma->vm_end); \
-	}  while (0)
-#define tlb_end_vma(tlb, vma) do { } while (0)
-#define __tlb_remove_tlb_entry(tlb, ptep, address) do { } while (0)
-
-/*
- * .. because we flush the whole mm when it fills up.
- */
-#define tlb_flush(tlb) flush_tlb_mm((tlb)->mm)
-
 #define _UNIQUE_ENTRYHI(base, idx)					\
 		(((base) + ((idx) << (PAGE_SHIFT + 1))) |		\
 		 (cpu_has_tlbinv ? MIPS_ENTRYHI_EHINV : 0))
diff --git a/arch/mips/kernel/kgdb.c b/arch/mips/kernel/kgdb.c
index 6e574c02e4c3..ea781b29f7f1 100644
--- a/arch/mips/kernel/kgdb.c
+++ b/arch/mips/kernel/kgdb.c
@@ -33,6 +33,7 @@
 #include <asm/processor.h>
 #include <asm/sigcontext.h>
 #include <linux/uaccess.h>
+#include <asm/irq_regs.h>
 
 static struct hard_trap_info {
 	unsigned char tt;	/* Trap type code for MIPS R3xxx and R4xxx */
@@ -214,7 +215,7 @@ void kgdb_call_nmi_hook(void *ignored)
 	old_fs = get_fs();
 	set_fs(KERNEL_DS);
 
-	kgdb_nmicallback(raw_smp_processor_id(), NULL);
+	kgdb_nmicallback(raw_smp_processor_id(), get_irq_regs());
 
 	set_fs(old_fs);
 }
diff --git a/arch/mips/kernel/ptrace.c b/arch/mips/kernel/ptrace.c
index 0057c910bc2f..3a62f80958e1 100644
--- a/arch/mips/kernel/ptrace.c
+++ b/arch/mips/kernel/ptrace.c
@@ -1419,7 +1419,7 @@ asmlinkage long syscall_trace_enter(struct pt_regs *regs, long syscall)
 
 		sd.nr = syscall;
 		sd.arch = syscall_get_arch();
-		syscall_get_arguments(current, regs, 0, 6, args);
+		syscall_get_arguments(current, regs, args);
 		for (i = 0; i < 6; i++)
 			sd.args[i] = args[i];
 		sd.instruction_pointer = KSTK_EIP(current);
diff --git a/arch/mips/kernel/scall64-o32.S b/arch/mips/kernel/scall64-o32.S
index f158c5894a9a..feb2653490df 100644
--- a/arch/mips/kernel/scall64-o32.S
+++ b/arch/mips/kernel/scall64-o32.S
@@ -125,7 +125,7 @@ trace_a_syscall:
 	subu	t1, v0,  __NR_O32_Linux
 	move	a1, v0
 	bnez	t1, 1f /* __NR_syscall at offset 0 */
-	lw	a1, PT_R4(sp) /* Arg1 for __NR_syscall case */
+	ld	a1, PT_R4(sp) /* Arg1 for __NR_syscall case */
 	.set	pop
 
 1:	jal	syscall_trace_enter
diff --git a/arch/mips/kernel/syscalls/syscall_n32.tbl b/arch/mips/kernel/syscalls/syscall_n32.tbl
index 15f4117900ee..9392dfe33f97 100644
--- a/arch/mips/kernel/syscalls/syscall_n32.tbl
+++ b/arch/mips/kernel/syscalls/syscall_n32.tbl
@@ -362,3 +362,7 @@
 421	n32	rt_sigtimedwait_time64		compat_sys_rt_sigtimedwait_time64
 422	n32	futex_time64			sys_futex
 423	n32	sched_rr_get_interval_time64	sys_sched_rr_get_interval
+424	n32	pidfd_send_signal		sys_pidfd_send_signal
+425	n32	io_uring_setup			sys_io_uring_setup
+426	n32	io_uring_enter			sys_io_uring_enter
+427	n32	io_uring_register		sys_io_uring_register
diff --git a/arch/mips/kernel/syscalls/syscall_n64.tbl b/arch/mips/kernel/syscalls/syscall_n64.tbl
index c85502e67b44..cd0c8aa21fba 100644
--- a/arch/mips/kernel/syscalls/syscall_n64.tbl
+++ b/arch/mips/kernel/syscalls/syscall_n64.tbl
@@ -338,3 +338,7 @@
 327	n64	rseq				sys_rseq
 328	n64	io_pgetevents			sys_io_pgetevents
 # 329 through 423 are reserved to sync up with other architectures
+424	n64	pidfd_send_signal		sys_pidfd_send_signal
+425	n64	io_uring_setup			sys_io_uring_setup
+426	n64	io_uring_enter			sys_io_uring_enter
+427	n64	io_uring_register		sys_io_uring_register
diff --git a/arch/mips/kernel/syscalls/syscall_o32.tbl b/arch/mips/kernel/syscalls/syscall_o32.tbl
index 2e063d0f837e..e849e8ffe4a2 100644
--- a/arch/mips/kernel/syscalls/syscall_o32.tbl
+++ b/arch/mips/kernel/syscalls/syscall_o32.tbl
@@ -411,3 +411,7 @@
 421	o32	rt_sigtimedwait_time64		sys_rt_sigtimedwait		compat_sys_rt_sigtimedwait_time64
 422	o32	futex_time64			sys_futex			sys_futex
 423	o32	sched_rr_get_interval_time64	sys_sched_rr_get_interval	sys_sched_rr_get_interval
+424	o32	pidfd_send_signal		sys_pidfd_send_signal
+425	o32	io_uring_setup			sys_io_uring_setup
+426	o32	io_uring_enter			sys_io_uring_enter
+427	o32	io_uring_register		sys_io_uring_register
diff --git a/arch/mips/net/ebpf_jit.c b/arch/mips/net/ebpf_jit.c
index 0effd3cba9a7..98bf0c222b5f 100644
--- a/arch/mips/net/ebpf_jit.c
+++ b/arch/mips/net/ebpf_jit.c
@@ -186,8 +186,9 @@ enum which_ebpf_reg {
  * separate frame pointer, so BPF_REG_10 relative accesses are
  * adjusted to be $sp relative.
  */
-int ebpf_to_mips_reg(struct jit_ctx *ctx, const struct bpf_insn *insn,
-		     enum which_ebpf_reg w)
+static int ebpf_to_mips_reg(struct jit_ctx *ctx,
+			    const struct bpf_insn *insn,
+			    enum which_ebpf_reg w)
 {
 	int ebpf_reg = (w == src_reg || w == src_reg_no_fp) ?
 		insn->src_reg : insn->dst_reg;
diff --git a/arch/mips/sgi-ip27/ip27-irq.c b/arch/mips/sgi-ip27/ip27-irq.c
index 710a59764b01..a32f843cdbe0 100644
--- a/arch/mips/sgi-ip27/ip27-irq.c
+++ b/arch/mips/sgi-ip27/ip27-irq.c
@@ -118,7 +118,6 @@ static void shutdown_bridge_irq(struct irq_data *d)
 {
 	struct hub_irq_data *hd = irq_data_get_irq_chip_data(d);
 	struct bridge_controller *bc;
-	int pin = hd->pin;
 
 	if (!hd)
 		return;
@@ -126,7 +125,7 @@ static void shutdown_bridge_irq(struct irq_data *d)
 	disable_hub_irq(d);
 
 	bc = hd->bc;
-	bridge_clr(bc, b_int_enable, (1 << pin));
+	bridge_clr(bc, b_int_enable, (1 << hd->pin));
 	bridge_read(bc, b_wid_tflush);
 }
 
diff --git a/arch/nds32/Kconfig b/arch/nds32/Kconfig
index addb7f5f5264..55559ca0efe4 100644
--- a/arch/nds32/Kconfig
+++ b/arch/nds32/Kconfig
@@ -60,9 +60,6 @@ config GENERIC_LOCKBREAK
         def_bool y
 	depends on PREEMPT
 
-config RWSEM_GENERIC_SPINLOCK
-	def_bool y
-
 config TRACE_IRQFLAGS_SUPPORT
 	def_bool y
 
diff --git a/arch/nds32/include/asm/Kbuild b/arch/nds32/include/asm/Kbuild
index 64ceff7ab99b..688b6ed26227 100644
--- a/arch/nds32/include/asm/Kbuild
+++ b/arch/nds32/include/asm/Kbuild
@@ -31,6 +31,7 @@ generic-y += limits.h
 generic-y += local.h
 generic-y += local64.h
 generic-y += mm-arch-hooks.h
+generic-y += mmiowb.h
 generic-y += parport.h
 generic-y += pci.h
 generic-y += percpu.h
diff --git a/arch/nds32/include/asm/io.h b/arch/nds32/include/asm/io.h
index 71cd226d6863..5ef8ae5ba833 100644
--- a/arch/nds32/include/asm/io.h
+++ b/arch/nds32/include/asm/io.h
@@ -55,8 +55,6 @@ static inline u32 __raw_readl(const volatile void __iomem *addr)
 #define __iormb()               rmb()
 #define __iowmb()               wmb()
 
-#define mmiowb()        __asm__ __volatile__ ("msync all" : : : "memory");
-
 /*
  * {read,write}{b,w,l,q}_relaxed() are like the regular version, but
  * are not guaranteed to provide ordering against spinlocks or memory
diff --git a/arch/nds32/include/asm/syscall.h b/arch/nds32/include/asm/syscall.h
index f7e5e86765fe..671ebd357496 100644
--- a/arch/nds32/include/asm/syscall.h
+++ b/arch/nds32/include/asm/syscall.h
@@ -108,81 +108,41 @@ void syscall_set_return_value(struct task_struct *task, struct pt_regs *regs,
  * syscall_get_arguments - extract system call parameter values
  * @task:	task of interest, must be blocked
  * @regs:	task_pt_regs() of @task
- * @i:		argument index [0,5]
- * @n:		number of arguments; n+i must be [1,6].
  * @args:	array filled with argument values
  *
- * Fetches @n arguments to the system call starting with the @i'th argument
- * (from 0 through 5).  Argument @i is stored in @args[0], and so on.
- * An arch inline version is probably optimal when @i and @n are constants.
+ * Fetches 6 arguments to the system call (from 0 through 5). The first
+ * argument is stored in @args[0], and so on.
  *
  * It's only valid to call this when @task is stopped for tracing on
  * entry to a system call, due to %TIF_SYSCALL_TRACE or %TIF_SYSCALL_AUDIT.
- * It's invalid to call this with @i + @n > 6; we only support system calls
- * taking up to 6 arguments.
  */
 #define SYSCALL_MAX_ARGS 6
 void syscall_get_arguments(struct task_struct *task, struct pt_regs *regs,
-			   unsigned int i, unsigned int n, unsigned long *args)
+			   unsigned long *args)
 {
-	if (n == 0)
-		return;
-	if (i + n > SYSCALL_MAX_ARGS) {
-		unsigned long *args_bad = args + SYSCALL_MAX_ARGS - i;
-		unsigned int n_bad = n + i - SYSCALL_MAX_ARGS;
-		pr_warning("%s called with max args %d, handling only %d\n",
-			   __func__, i + n, SYSCALL_MAX_ARGS);
-		memset(args_bad, 0, n_bad * sizeof(args[0]));
-		memset(args_bad, 0, n_bad * sizeof(args[0]));
-	}
-
-	if (i == 0) {
-		args[0] = regs->orig_r0;
-		args++;
-		i++;
-		n--;
-	}
-
-	memcpy(args, &regs->uregs[0] + i, n * sizeof(args[0]));
+	args[0] = regs->orig_r0;
+	args++;
+	memcpy(args, &regs->uregs[0] + 1, 5 * sizeof(args[0]));
 }
 
 /**
  * syscall_set_arguments - change system call parameter value
  * @task:	task of interest, must be in system call entry tracing
  * @regs:	task_pt_regs() of @task
- * @i:		argument index [0,5]
- * @n:		number of arguments; n+i must be [1,6].
  * @args:	array of argument values to store
  *
- * Changes @n arguments to the system call starting with the @i'th argument.
- * Argument @i gets value @args[0], and so on.
- * An arch inline version is probably optimal when @i and @n are constants.
+ * Changes 6 arguments to the system call. The first argument gets value
+ * @args[0], and so on.
  *
  * It's only valid to call this when @task is stopped for tracing on
  * entry to a system call, due to %TIF_SYSCALL_TRACE or %TIF_SYSCALL_AUDIT.
- * It's invalid to call this with @i + @n > 6; we only support system calls
- * taking up to 6 arguments.
  */
 void syscall_set_arguments(struct task_struct *task, struct pt_regs *regs,
-			   unsigned int i, unsigned int n,
 			   const unsigned long *args)
 {
-	if (n == 0)
-		return;
-
-	if (i + n > SYSCALL_MAX_ARGS) {
-		pr_warn("%s called with max args %d, handling only %d\n",
-			__func__, i + n, SYSCALL_MAX_ARGS);
-		n = SYSCALL_MAX_ARGS - i;
-	}
-
-	if (i == 0) {
-		regs->orig_r0 = args[0];
-		args++;
-		i++;
-		n--;
-	}
+	regs->orig_r0 = args[0];
+	args++;
 
-	memcpy(&regs->uregs[0] + i, args, n * sizeof(args[0]));
+	memcpy(&regs->uregs[0] + 1, args, 5 * sizeof(args[0]));
 }
 #endif /* _ASM_NDS32_SYSCALL_H */
diff --git a/arch/nds32/include/asm/tlb.h b/arch/nds32/include/asm/tlb.h
index b35ae5eae3ab..d5ae571c8d30 100644
--- a/arch/nds32/include/asm/tlb.h
+++ b/arch/nds32/include/asm/tlb.h
@@ -4,22 +4,6 @@
 #ifndef __ASMNDS32_TLB_H
 #define __ASMNDS32_TLB_H
 
-#define tlb_start_vma(tlb,vma)						\
-	do {								\
-		if (!tlb->fullmm)					\
-			flush_cache_range(vma, vma->vm_start, vma->vm_end); \
-	} while (0)
-
-#define tlb_end_vma(tlb,vma)				\
-	do { 						\
-		if(!tlb->fullmm)			\
-			flush_tlb_range(vma, vma->vm_start, vma->vm_end); \
-	} while (0)
-
-#define __tlb_remove_tlb_entry(tlb, pte, addr) do { } while (0)
-
-#define tlb_flush(tlb)	flush_tlb_mm((tlb)->mm)
-
 #include <asm-generic/tlb.h>
 
 #define __pte_free_tlb(tlb, pte, addr)	pte_free((tlb)->mm, pte)
diff --git a/arch/nds32/include/asm/tlbflush.h b/arch/nds32/include/asm/tlbflush.h
index 9b411f401903..38ee769b18d8 100644
--- a/arch/nds32/include/asm/tlbflush.h
+++ b/arch/nds32/include/asm/tlbflush.h
@@ -42,6 +42,5 @@ void local_flush_tlb_page(struct vm_area_struct *vma, unsigned long addr);
 
 void update_mmu_cache(struct vm_area_struct *vma,
 		      unsigned long address, pte_t * pte);
-void tlb_migrate_finish(struct mm_struct *mm);
 
 #endif
diff --git a/arch/nios2/Kconfig b/arch/nios2/Kconfig
index 4ef15a61b7bc..ea37394ff3ea 100644
--- a/arch/nios2/Kconfig
+++ b/arch/nios2/Kconfig
@@ -24,6 +24,7 @@ config NIOS2
 	select USB_ARCH_HAS_HCD if USB_SUPPORT
 	select CPU_NO_EFFICIENT_FFS
 	select ARCH_DISCARD_MEMBLOCK
+	select MMU_GATHER_NO_RANGE if MMU
 
 config GENERIC_CSUM
 	def_bool y
@@ -40,9 +41,6 @@ config NO_IOPORT_MAP
 config FPU
 	def_bool n
 
-config RWSEM_GENERIC_SPINLOCK
-	def_bool y
-
 config TRACE_IRQFLAGS_SUPPORT
 	def_bool n
 
diff --git a/arch/nios2/include/asm/Kbuild b/arch/nios2/include/asm/Kbuild
index 8fde4fa2c34f..d7ef3512504a 100644
--- a/arch/nios2/include/asm/Kbuild
+++ b/arch/nios2/include/asm/Kbuild
@@ -23,9 +23,11 @@ generic-y += irq_work.h
 generic-y += kdebug.h
 generic-y += kmap_types.h
 generic-y += kprobes.h
+generic-y += kvm_para.h
 generic-y += local.h
 generic-y += mcs_spinlock.h
 generic-y += mm-arch-hooks.h
+generic-y += mmiowb.h
 generic-y += module.h
 generic-y += pci.h
 generic-y += percpu.h
diff --git a/arch/nios2/include/asm/syscall.h b/arch/nios2/include/asm/syscall.h
index 9de220854c4a..d7624ed06efb 100644
--- a/arch/nios2/include/asm/syscall.h
+++ b/arch/nios2/include/asm/syscall.h
@@ -58,81 +58,25 @@ static inline void syscall_set_return_value(struct task_struct *task,
 }
 
 static inline void syscall_get_arguments(struct task_struct *task,
-	struct pt_regs *regs, unsigned int i, unsigned int n,
-	unsigned long *args)
+	struct pt_regs *regs, unsigned long *args)
 {
-	BUG_ON(i + n > 6);
-
-	switch (i) {
-	case 0:
-		if (!n--)
-			break;
-		*args++ = regs->r4;
-	case 1:
-		if (!n--)
-			break;
-		*args++ = regs->r5;
-	case 2:
-		if (!n--)
-			break;
-		*args++ = regs->r6;
-	case 3:
-		if (!n--)
-			break;
-		*args++ = regs->r7;
-	case 4:
-		if (!n--)
-			break;
-		*args++ = regs->r8;
-	case 5:
-		if (!n--)
-			break;
-		*args++ = regs->r9;
-	case 6:
-		if (!n--)
-			break;
-	default:
-		BUG();
-	}
+	*args++ = regs->r4;
+	*args++ = regs->r5;
+	*args++ = regs->r6;
+	*args++ = regs->r7;
+	*args++ = regs->r8;
+	*args   = regs->r9;
 }
 
 static inline void syscall_set_arguments(struct task_struct *task,
-	struct pt_regs *regs, unsigned int i, unsigned int n,
-	const unsigned long *args)
+	struct pt_regs *regs, const unsigned long *args)
 {
-	BUG_ON(i + n > 6);
-
-	switch (i) {
-	case 0:
-		if (!n--)
-			break;
-		regs->r4 = *args++;
-	case 1:
-		if (!n--)
-			break;
-		regs->r5 = *args++;
-	case 2:
-		if (!n--)
-			break;
-		regs->r6 = *args++;
-	case 3:
-		if (!n--)
-			break;
-		regs->r7 = *args++;
-	case 4:
-		if (!n--)
-			break;
-		regs->r8 = *args++;
-	case 5:
-		if (!n--)
-			break;
-		regs->r9 = *args++;
-	case 6:
-		if (!n)
-			break;
-	default:
-		BUG();
-	}
+	regs->r4 = *args++;
+	regs->r5 = *args++;
+	regs->r6 = *args++;
+	regs->r7 = *args++;
+	regs->r8 = *args++;
+	regs->r9 = *args;
 }
 
 #endif
diff --git a/arch/nios2/include/asm/tlb.h b/arch/nios2/include/asm/tlb.h
index d3bc648e08b5..f9f2e27e32dd 100644
--- a/arch/nios2/include/asm/tlb.h
+++ b/arch/nios2/include/asm/tlb.h
@@ -11,22 +11,12 @@
 #ifndef _ASM_NIOS2_TLB_H
 #define _ASM_NIOS2_TLB_H
 
-#define tlb_flush(tlb)	flush_tlb_mm((tlb)->mm)
-
 extern void set_mmu_pid(unsigned long pid);
 
 /*
- * NiosII doesn't need any special per-pte or per-vma handling, except
- * we need to flush cache for the area to be unmapped.
+ * NIOS32 does have flush_tlb_range(), but it lacks a limit and fallback to
+ * full mm invalidation. So use flush_tlb_mm() for everything.
  */
-#define tlb_start_vma(tlb, vma)					\
-	do {							\
-		if (!tlb->fullmm)				\
-			flush_cache_range(vma, vma->vm_start, vma->vm_end); \
-	}  while (0)
-
-#define tlb_end_vma(tlb, vma)	do { } while (0)
-#define __tlb_remove_tlb_entry(tlb, ptep, address)	do { } while (0)
 
 #include <linux/pagemap.h>
 #include <asm-generic/tlb.h>
diff --git a/arch/nios2/include/uapi/asm/Kbuild b/arch/nios2/include/uapi/asm/Kbuild
index 755bb11323d8..1c72f04ff75d 100644
--- a/arch/nios2/include/uapi/asm/Kbuild
+++ b/arch/nios2/include/uapi/asm/Kbuild
@@ -1,2 +1 @@
-generic-y += kvm_para.h
 generic-y += ucontext.h
diff --git a/arch/openrisc/Kconfig b/arch/openrisc/Kconfig
index a5e361fbb75a..7cfb20555b10 100644
--- a/arch/openrisc/Kconfig
+++ b/arch/openrisc/Kconfig
@@ -36,6 +36,7 @@ config OPENRISC
 	select OMPIC if SMP
 	select ARCH_WANT_FRAME_POINTERS
 	select GENERIC_IRQ_MULTI_HANDLER
+	select MMU_GATHER_NO_RANGE if MMU
 
 config CPU_BIG_ENDIAN
 	def_bool y
@@ -43,12 +44,6 @@ config CPU_BIG_ENDIAN
 config MMU
 	def_bool y
 
-config RWSEM_GENERIC_SPINLOCK
-	def_bool y
-
-config RWSEM_XCHGADD_ALGORITHM
-	def_bool n
-
 config GENERIC_HWEIGHT
 	def_bool y
 
diff --git a/arch/openrisc/include/asm/Kbuild b/arch/openrisc/include/asm/Kbuild
index 5a73e2956ac4..1919cc5e0f11 100644
--- a/arch/openrisc/include/asm/Kbuild
+++ b/arch/openrisc/include/asm/Kbuild
@@ -20,9 +20,11 @@ generic-y += irq_work.h
 generic-y += kdebug.h
 generic-y += kmap_types.h
 generic-y += kprobes.h
+generic-y += kvm_para.h
 generic-y += local.h
 generic-y += mcs_spinlock.h
 generic-y += mm-arch-hooks.h
+generic-y += mmiowb.h
 generic-y += module.h
 generic-y += pci.h
 generic-y += percpu.h
diff --git a/arch/openrisc/include/asm/syscall.h b/arch/openrisc/include/asm/syscall.h
index 2db9f1cf0694..b4ff07c1baed 100644
--- a/arch/openrisc/include/asm/syscall.h
+++ b/arch/openrisc/include/asm/syscall.h
@@ -56,20 +56,16 @@ syscall_set_return_value(struct task_struct *task, struct pt_regs *regs,
 
 static inline void
 syscall_get_arguments(struct task_struct *task, struct pt_regs *regs,
-		      unsigned int i, unsigned int n, unsigned long *args)
+		      unsigned long *args)
 {
-	BUG_ON(i + n > 6);
-
-	memcpy(args, &regs->gpr[3 + i], n * sizeof(args[0]));
+	memcpy(args, &regs->gpr[3], 6 * sizeof(args[0]));
 }
 
 static inline void
 syscall_set_arguments(struct task_struct *task, struct pt_regs *regs,
-		      unsigned int i, unsigned int n, const unsigned long *args)
+		      const unsigned long *args)
 {
-	BUG_ON(i + n > 6);
-
-	memcpy(&regs->gpr[3 + i], args, n * sizeof(args[0]));
+	memcpy(&regs->gpr[3], args, 6 * sizeof(args[0]));
 }
 
 static inline int syscall_get_arch(void)
diff --git a/arch/openrisc/include/asm/tlb.h b/arch/openrisc/include/asm/tlb.h
index fa4376a4515d..92d8a4209884 100644
--- a/arch/openrisc/include/asm/tlb.h
+++ b/arch/openrisc/include/asm/tlb.h
@@ -20,14 +20,10 @@
 #define __ASM_OPENRISC_TLB_H__
 
 /*
- * or32 doesn't need any special per-pte or
- * per-vma handling..
+ * OpenRISC doesn't have an efficient flush_tlb_range() so use flush_tlb_mm()
+ * for everything.
  */
-#define tlb_start_vma(tlb, vma) do { } while (0)
-#define tlb_end_vma(tlb, vma) do { } while (0)
-#define __tlb_remove_tlb_entry(tlb, ptep, address) do { } while (0)
 
-#define tlb_flush(tlb) flush_tlb_mm((tlb)->mm)
 #include <linux/pagemap.h>
 #include <asm-generic/tlb.h>
 
diff --git a/arch/openrisc/include/uapi/asm/Kbuild b/arch/openrisc/include/uapi/asm/Kbuild
index 755bb11323d8..1c72f04ff75d 100644
--- a/arch/openrisc/include/uapi/asm/Kbuild
+++ b/arch/openrisc/include/uapi/asm/Kbuild
@@ -1,2 +1 @@
-generic-y += kvm_para.h
 generic-y += ucontext.h
diff --git a/arch/parisc/Kconfig b/arch/parisc/Kconfig
index c8e621296092..f1ed8ddfe486 100644
--- a/arch/parisc/Kconfig
+++ b/arch/parisc/Kconfig
@@ -75,12 +75,6 @@ config GENERIC_LOCKBREAK
 	default y
 	depends on SMP && PREEMPT
 
-config RWSEM_GENERIC_SPINLOCK
-	def_bool y
-
-config RWSEM_XCHGADD_ALGORITHM
-	bool
-
 config ARCH_HAS_ILOG2_U32
 	bool
 	default n
diff --git a/arch/parisc/include/asm/Kbuild b/arch/parisc/include/asm/Kbuild
index 6f49e77d82a2..b8c7db777144 100644
--- a/arch/parisc/include/asm/Kbuild
+++ b/arch/parisc/include/asm/Kbuild
@@ -11,10 +11,12 @@ generic-y += irq_regs.h
 generic-y += irq_work.h
 generic-y += kdebug.h
 generic-y += kprobes.h
+generic-y += kvm_para.h
 generic-y += local.h
 generic-y += local64.h
 generic-y += mcs_spinlock.h
 generic-y += mm-arch-hooks.h
+generic-y += mmiowb.h
 generic-y += percpu.h
 generic-y += preempt.h
 generic-y += seccomp.h
diff --git a/arch/parisc/include/asm/io.h b/arch/parisc/include/asm/io.h
index 30a8315d5c07..93d37010b375 100644
--- a/arch/parisc/include/asm/io.h
+++ b/arch/parisc/include/asm/io.h
@@ -229,8 +229,6 @@ static inline void writeq(unsigned long long q, volatile void __iomem *addr)
 #define writel_relaxed(l, addr)	writel(l, addr)
 #define writeq_relaxed(q, addr)	writeq(q, addr)
 
-#define mmiowb() do { } while (0)
-
 void memset_io(volatile void __iomem *addr, unsigned char val, int count);
 void memcpy_fromio(void *dst, const volatile void __iomem *src, int count);
 void memcpy_toio(volatile void __iomem *dst, const void *src, int count);
diff --git a/arch/parisc/include/asm/ptrace.h b/arch/parisc/include/asm/ptrace.h
index 2a27b275ab09..9ff033d261ab 100644
--- a/arch/parisc/include/asm/ptrace.h
+++ b/arch/parisc/include/asm/ptrace.h
@@ -22,13 +22,14 @@ unsigned long profile_pc(struct pt_regs *);
 
 static inline unsigned long regs_return_value(struct pt_regs *regs)
 {
-	return regs->gr[20];
+	return regs->gr[28];
 }
 
 static inline void instruction_pointer_set(struct pt_regs *regs,
 						unsigned long val)
 {
-        regs->iaoq[0] = val;
+	regs->iaoq[0] = val;
+	regs->iaoq[1] = val + 4;
 }
 
 /* Query offset/name of register from its name/offset */
diff --git a/arch/parisc/include/asm/syscall.h b/arch/parisc/include/asm/syscall.h
index 8bff1a58c97f..62a6d477fae0 100644
--- a/arch/parisc/include/asm/syscall.h
+++ b/arch/parisc/include/asm/syscall.h
@@ -18,29 +18,15 @@ static inline long syscall_get_nr(struct task_struct *tsk,
 }
 
 static inline void syscall_get_arguments(struct task_struct *tsk,
-					 struct pt_regs *regs, unsigned int i,
-					 unsigned int n, unsigned long *args)
+					 struct pt_regs *regs,
+					 unsigned long *args)
 {
-	BUG_ON(i);
-
-	switch (n) {
-	case 6:
-		args[5] = regs->gr[21];
-	case 5:
-		args[4] = regs->gr[22];
-	case 4:
-		args[3] = regs->gr[23];
-	case 3:
-		args[2] = regs->gr[24];
-	case 2:
-		args[1] = regs->gr[25];
-	case 1:
-		args[0] = regs->gr[26];
-	case 0:
-		break;
-	default:
-		BUG();
-	}
+	args[5] = regs->gr[21];
+	args[4] = regs->gr[22];
+	args[3] = regs->gr[23];
+	args[2] = regs->gr[24];
+	args[1] = regs->gr[25];
+	args[0] = regs->gr[26];
 }
 
 static inline long syscall_get_return_value(struct task_struct *task,
diff --git a/arch/parisc/include/asm/tlb.h b/arch/parisc/include/asm/tlb.h
index 0c881e74d8a6..8c0446b04c9e 100644
--- a/arch/parisc/include/asm/tlb.h
+++ b/arch/parisc/include/asm/tlb.h
@@ -2,24 +2,6 @@
 #ifndef _PARISC_TLB_H
 #define _PARISC_TLB_H
 
-#define tlb_flush(tlb)			\
-do {	if ((tlb)->fullmm)		\
-		flush_tlb_mm((tlb)->mm);\
-} while (0)
-
-#define tlb_start_vma(tlb, vma) \
-do {	if (!(tlb)->fullmm)	\
-		flush_cache_range(vma, vma->vm_start, vma->vm_end); \
-} while (0)
-
-#define tlb_end_vma(tlb, vma)	\
-do {	if (!(tlb)->fullmm)	\
-		flush_tlb_range(vma, vma->vm_start, vma->vm_end); \
-} while (0)
-
-#define __tlb_remove_tlb_entry(tlb, pte, address) \
-	do { } while (0)
-
 #include <asm-generic/tlb.h>
 
 #define __pmd_free_tlb(tlb, pmd, addr)	pmd_free((tlb)->mm, pmd)
diff --git a/arch/parisc/include/uapi/asm/Kbuild b/arch/parisc/include/uapi/asm/Kbuild
index 22fdbd08cdc8..2bd5b392277c 100644
--- a/arch/parisc/include/uapi/asm/Kbuild
+++ b/arch/parisc/include/uapi/asm/Kbuild
@@ -1,3 +1,2 @@
 generated-y += unistd_32.h
 generated-y += unistd_64.h
-generic-y += kvm_para.h
diff --git a/arch/parisc/kernel/process.c b/arch/parisc/kernel/process.c
index eb39e7e380d7..841db71958cd 100644
--- a/arch/parisc/kernel/process.c
+++ b/arch/parisc/kernel/process.c
@@ -210,12 +210,6 @@ void __cpuidle arch_cpu_idle(void)
 
 static int __init parisc_idle_init(void)
 {
-	const char *marker;
-
-	/* check QEMU/SeaBIOS marker in PAGE0 */
-	marker = (char *) &PAGE0->pad0;
-	running_on_qemu = (memcmp(marker, "SeaBIOS", 8) == 0);
-
 	if (!running_on_qemu)
 		cpu_idle_poll_ctrl(1);
 
diff --git a/arch/parisc/kernel/setup.c b/arch/parisc/kernel/setup.c
index 15dd9e21be7e..d908058d05c1 100644
--- a/arch/parisc/kernel/setup.c
+++ b/arch/parisc/kernel/setup.c
@@ -397,6 +397,9 @@ void __init start_parisc(void)
 	int ret, cpunum;
 	struct pdc_coproc_cfg coproc_cfg;
 
+	/* check QEMU/SeaBIOS marker in PAGE0 */
+	running_on_qemu = (memcmp(&PAGE0->pad0, "SeaBIOS", 8) == 0);
+
 	cpunum = smp_processor_id();
 
 	init_cpu_topology();
diff --git a/arch/parisc/kernel/stacktrace.c b/arch/parisc/kernel/stacktrace.c
index ec5835e83a7a..6f0b9c8d8052 100644
--- a/arch/parisc/kernel/stacktrace.c
+++ b/arch/parisc/kernel/stacktrace.c
@@ -29,22 +29,17 @@ static void dump_trace(struct task_struct *task, struct stack_trace *trace)
 	}
 }
 
-
 /*
  * Save stack-backtrace addresses into a stack_trace buffer.
  */
 void save_stack_trace(struct stack_trace *trace)
 {
 	dump_trace(current, trace);
-	if (trace->nr_entries < trace->max_entries)
-		trace->entries[trace->nr_entries++] = ULONG_MAX;
 }
 EXPORT_SYMBOL_GPL(save_stack_trace);
 
 void save_stack_trace_tsk(struct task_struct *tsk, struct stack_trace *trace)
 {
 	dump_trace(tsk, trace);
-	if (trace->nr_entries < trace->max_entries)
-		trace->entries[trace->nr_entries++] = ULONG_MAX;
 }
 EXPORT_SYMBOL_GPL(save_stack_trace_tsk);
diff --git a/arch/parisc/kernel/syscalls/syscall.tbl b/arch/parisc/kernel/syscalls/syscall.tbl
index b26766c6647d..fe8ca623add8 100644
--- a/arch/parisc/kernel/syscalls/syscall.tbl
+++ b/arch/parisc/kernel/syscalls/syscall.tbl
@@ -420,3 +420,7 @@
 421	32	rt_sigtimedwait_time64		sys_rt_sigtimedwait		compat_sys_rt_sigtimedwait_time64
 422	32	futex_time64			sys_futex			sys_futex
 423	32	sched_rr_get_interval_time64	sys_sched_rr_get_interval	sys_sched_rr_get_interval
+424	common	pidfd_send_signal		sys_pidfd_send_signal
+425	common	io_uring_setup			sys_io_uring_setup
+426	common	io_uring_enter			sys_io_uring_enter
+427	common	io_uring_register		sys_io_uring_register
diff --git a/arch/powerpc/Kconfig b/arch/powerpc/Kconfig
index 2d0be82c3061..fa7219ffeadc 100644
--- a/arch/powerpc/Kconfig
+++ b/arch/powerpc/Kconfig
@@ -103,13 +103,6 @@ config LOCKDEP_SUPPORT
 	bool
 	default y
 
-config RWSEM_GENERIC_SPINLOCK
-	bool
-
-config RWSEM_XCHGADD_ALGORITHM
-	bool
-	default y
-
 config GENERIC_LOCKBREAK
 	bool
 	default y
@@ -132,6 +125,7 @@ config PPC
 	select ARCH_HAS_FORTIFY_SOURCE
 	select ARCH_HAS_GCOV_PROFILE_ALL
 	select ARCH_HAS_KCOV
+	select ARCH_HAS_MMIOWB			if PPC64
 	select ARCH_HAS_PHYS_TO_DMA
 	select ARCH_HAS_PMEM_API                if PPC64
 	select ARCH_HAS_PTE_SPECIAL
@@ -218,6 +212,8 @@ config PPC
 	select HAVE_PERF_REGS
 	select HAVE_PERF_USER_STACK_DUMP
 	select HAVE_RCU_TABLE_FREE		if SMP
+	select HAVE_RCU_TABLE_NO_INVALIDATE	if HAVE_RCU_TABLE_FREE
+	select HAVE_MMU_GATHER_PAGE_SIZE
 	select HAVE_REGS_AND_STACK_ACCESS_API
 	select HAVE_RELIABLE_STACKTRACE		if PPC_BOOK3S_64 && CPU_LITTLE_ENDIAN
 	select HAVE_SYSCALL_TRACEPOINTS
@@ -318,6 +314,10 @@ config ARCH_SUSPEND_POSSIBLE
 		   (PPC_85xx && !PPC_E500MC) || PPC_86xx || PPC_PSERIES \
 		   || 44x || 40x
 
+config ARCH_SUSPEND_NONZERO_CPU
+	def_bool y
+	depends on PPC_POWERNV || PPC_PSERIES
+
 config PPC_DCR_NATIVE
 	bool
 
diff --git a/arch/powerpc/configs/skiroot_defconfig b/arch/powerpc/configs/skiroot_defconfig
index 5ba131c30f6b..1bcd468ab422 100644
--- a/arch/powerpc/configs/skiroot_defconfig
+++ b/arch/powerpc/configs/skiroot_defconfig
@@ -266,6 +266,7 @@ CONFIG_UDF_FS=m
 CONFIG_MSDOS_FS=m
 CONFIG_VFAT_FS=m
 CONFIG_PROC_KCORE=y
+CONFIG_HUGETLBFS=y
 # CONFIG_MISC_FILESYSTEMS is not set
 # CONFIG_NETWORK_FILESYSTEMS is not set
 CONFIG_NLS=y
diff --git a/arch/powerpc/crypto/crc32c-vpmsum_glue.c b/arch/powerpc/crypto/crc32c-vpmsum_glue.c
index fd1d6c83f0c0..c4fa242dd652 100644
--- a/arch/powerpc/crypto/crc32c-vpmsum_glue.c
+++ b/arch/powerpc/crypto/crc32c-vpmsum_glue.c
@@ -1,10 +1,12 @@
 #include <linux/crc32.h>
 #include <crypto/internal/hash.h>
+#include <crypto/internal/simd.h>
 #include <linux/init.h>
 #include <linux/module.h>
 #include <linux/string.h>
 #include <linux/kernel.h>
 #include <linux/cpufeature.h>
+#include <asm/simd.h>
 #include <asm/switch_to.h>
 
 #define CHKSUM_BLOCK_SIZE	1
@@ -22,7 +24,7 @@ static u32 crc32c_vpmsum(u32 crc, unsigned char const *p, size_t len)
 	unsigned int prealign;
 	unsigned int tail;
 
-	if (len < (VECTOR_BREAKPOINT + VMX_ALIGN) || in_interrupt())
+	if (len < (VECTOR_BREAKPOINT + VMX_ALIGN) || !crypto_simd_usable())
 		return __crc32c_le(crc, p, len);
 
 	if ((unsigned long)p & VMX_ALIGN_MASK) {
diff --git a/arch/powerpc/crypto/crct10dif-vpmsum_glue.c b/arch/powerpc/crypto/crct10dif-vpmsum_glue.c
index 02ea277863d1..e27ff16573b5 100644
--- a/arch/powerpc/crypto/crct10dif-vpmsum_glue.c
+++ b/arch/powerpc/crypto/crct10dif-vpmsum_glue.c
@@ -12,11 +12,13 @@
 
 #include <linux/crc-t10dif.h>
 #include <crypto/internal/hash.h>
+#include <crypto/internal/simd.h>
 #include <linux/init.h>
 #include <linux/module.h>
 #include <linux/string.h>
 #include <linux/kernel.h>
 #include <linux/cpufeature.h>
+#include <asm/simd.h>
 #include <asm/switch_to.h>
 
 #define VMX_ALIGN		16
@@ -32,7 +34,7 @@ static u16 crct10dif_vpmsum(u16 crci, unsigned char const *p, size_t len)
 	unsigned int tail;
 	u32 crc = crci;
 
-	if (len < (VECTOR_BREAKPOINT + VMX_ALIGN) || in_interrupt())
+	if (len < (VECTOR_BREAKPOINT + VMX_ALIGN) || !crypto_simd_usable())
 		return crc_t10dif_generic(crc, p, len);
 
 	if ((unsigned long)p & VMX_ALIGN_MASK) {
diff --git a/arch/powerpc/include/asm/Kbuild b/arch/powerpc/include/asm/Kbuild
index a0c132bedfae..b9f6e72bf4e5 100644
--- a/arch/powerpc/include/asm/Kbuild
+++ b/arch/powerpc/include/asm/Kbuild
@@ -8,6 +8,6 @@ generic-y += irq_regs.h
 generic-y += local64.h
 generic-y += mcs_spinlock.h
 generic-y += preempt.h
-generic-y += rwsem.h
 generic-y += vtime.h
 generic-y += msi.h
+generic-y += simd.h
diff --git a/arch/powerpc/include/asm/io.h b/arch/powerpc/include/asm/io.h
index 4b73847e9b95..1fad67b46409 100644
--- a/arch/powerpc/include/asm/io.h
+++ b/arch/powerpc/include/asm/io.h
@@ -34,14 +34,11 @@ extern struct pci_dev *isa_bridge_pcidev;
 #include <asm/byteorder.h>
 #include <asm/synch.h>
 #include <asm/delay.h>
+#include <asm/mmiowb.h>
 #include <asm/mmu.h>
 #include <asm/ppc_asm.h>
 #include <asm/pgtable.h>
 
-#ifdef CONFIG_PPC64
-#include <asm/paca.h>
-#endif
-
 #define SIO_CONFIG_RA	0x398
 #define SIO_CONFIG_RD	0x399
 
@@ -107,12 +104,6 @@ extern bool isa_io_special;
  *
  */
 
-#ifdef CONFIG_PPC64
-#define IO_SET_SYNC_FLAG()	do { local_paca->io_sync = 1; } while(0)
-#else
-#define IO_SET_SYNC_FLAG()
-#endif
-
 #define DEF_MMIO_IN_X(name, size, insn)				\
 static inline u##size name(const volatile u##size __iomem *addr)	\
 {									\
@@ -127,7 +118,7 @@ static inline void name(volatile u##size __iomem *addr, u##size val)	\
 {									\
 	__asm__ __volatile__("sync;"#insn" %1,%y0"			\
 		: "=Z" (*addr) : "r" (val) : "memory");			\
-	IO_SET_SYNC_FLAG();						\
+	mmiowb_set_pending();						\
 }
 
 #define DEF_MMIO_IN_D(name, size, insn)				\
@@ -144,7 +135,7 @@ static inline void name(volatile u##size __iomem *addr, u##size val)	\
 {									\
 	__asm__ __volatile__("sync;"#insn"%U0%X0 %1,%0"			\
 		: "=m" (*addr) : "r" (val) : "memory");			\
-	IO_SET_SYNC_FLAG();						\
+	mmiowb_set_pending();						\
 }
 
 DEF_MMIO_IN_D(in_8,     8, lbz);
@@ -652,24 +643,6 @@ static inline void name at					\
 
 #include <asm-generic/iomap.h>
 
-#ifdef CONFIG_PPC32
-#define mmiowb()
-#else
-/*
- * Enforce synchronisation of stores vs. spin_unlock
- * (this does it explicitly, though our implementation of spin_unlock
- * does it implicitely too)
- */
-static inline void mmiowb(void)
-{
-	unsigned long tmp;
-
-	__asm__ __volatile__("sync; li %0,0; stb %0,%1(13)"
-	: "=&r" (tmp) : "i" (offsetof(struct paca_struct, io_sync))
-	: "memory");
-}
-#endif /* !CONFIG_PPC32 */
-
 static inline void iosync(void)
 {
         __asm__ __volatile__ ("sync" : : : "memory");
diff --git a/arch/powerpc/include/asm/mmiowb.h b/arch/powerpc/include/asm/mmiowb.h
new file mode 100644
index 000000000000..74a00127eb20
--- /dev/null
+++ b/arch/powerpc/include/asm/mmiowb.h
@@ -0,0 +1,18 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _ASM_POWERPC_MMIOWB_H
+#define _ASM_POWERPC_MMIOWB_H
+
+#ifdef CONFIG_MMIOWB
+
+#include <linux/compiler.h>
+#include <asm/barrier.h>
+#include <asm/paca.h>
+
+#define arch_mmiowb_state()	(&local_paca->mmiowb_state)
+#define mmiowb()		mb()
+
+#endif /* CONFIG_MMIOWB */
+
+#include <asm-generic/mmiowb.h>
+
+#endif	/* _ASM_POWERPC_MMIOWB_H */
diff --git a/arch/powerpc/include/asm/mmu.h b/arch/powerpc/include/asm/mmu.h
index 598cdcdd1355..8ddd4a91bdc1 100644
--- a/arch/powerpc/include/asm/mmu.h
+++ b/arch/powerpc/include/asm/mmu.h
@@ -352,7 +352,7 @@ static inline bool strict_kernel_rwx_enabled(void)
 #if defined(CONFIG_SPARSEMEM_VMEMMAP) && defined(CONFIG_SPARSEMEM_EXTREME) &&	\
 	defined (CONFIG_PPC_64K_PAGES)
 #define MAX_PHYSMEM_BITS        51
-#elif defined(CONFIG_SPARSEMEM)
+#elif defined(CONFIG_PPC64)
 #define MAX_PHYSMEM_BITS        46
 #endif
 
diff --git a/arch/powerpc/include/asm/paca.h b/arch/powerpc/include/asm/paca.h
index e843bc5d1a0f..134e912d403f 100644
--- a/arch/powerpc/include/asm/paca.h
+++ b/arch/powerpc/include/asm/paca.h
@@ -34,6 +34,8 @@
 #include <asm/cpuidle.h>
 #include <asm/atomic.h>
 
+#include <asm-generic/mmiowb_types.h>
+
 register struct paca_struct *local_paca asm("r13");
 
 #if defined(CONFIG_DEBUG_PREEMPT) && defined(CONFIG_SMP)
@@ -171,7 +173,6 @@ struct paca_struct {
 	u16 trap_save;			/* Used when bad stack is encountered */
 	u8 irq_soft_mask;		/* mask for irq soft masking */
 	u8 irq_happened;		/* irq happened while soft-disabled */
-	u8 io_sync;			/* writel() needs spin_unlock sync */
 	u8 irq_work_pending;		/* IRQ_WORK interrupt while soft-disable */
 	u8 nap_state_lost;		/* NV GPR values lost in power7_idle */
 #ifdef CONFIG_KVM_BOOK3S_HV_POSSIBLE
@@ -264,6 +265,9 @@ struct paca_struct {
 #ifdef CONFIG_STACKPROTECTOR
 	unsigned long canary;
 #endif
+#ifdef CONFIG_MMIOWB
+	struct mmiowb_state mmiowb_state;
+#endif
 } ____cacheline_aligned;
 
 extern void copy_mm_to_paca(struct mm_struct *mm);
diff --git a/arch/powerpc/include/asm/ppc-opcode.h b/arch/powerpc/include/asm/ppc-opcode.h
index c5698a523bb1..23f7ed796f38 100644
--- a/arch/powerpc/include/asm/ppc-opcode.h
+++ b/arch/powerpc/include/asm/ppc-opcode.h
@@ -302,6 +302,7 @@
 /* Misc instructions for BPF compiler */
 #define PPC_INST_LBZ			0x88000000
 #define PPC_INST_LD			0xe8000000
+#define PPC_INST_LDX			0x7c00002a
 #define PPC_INST_LHZ			0xa0000000
 #define PPC_INST_LWZ			0x80000000
 #define PPC_INST_LHBRX			0x7c00062c
@@ -309,6 +310,7 @@
 #define PPC_INST_STB			0x98000000
 #define PPC_INST_STH			0xb0000000
 #define PPC_INST_STD			0xf8000000
+#define PPC_INST_STDX			0x7c00012a
 #define PPC_INST_STDU			0xf8000001
 #define PPC_INST_STW			0x90000000
 #define PPC_INST_STWU			0x94000000
diff --git a/arch/powerpc/include/asm/spinlock.h b/arch/powerpc/include/asm/spinlock.h
index 685c72310f5d..15b39c407c4e 100644
--- a/arch/powerpc/include/asm/spinlock.h
+++ b/arch/powerpc/include/asm/spinlock.h
@@ -39,19 +39,6 @@
 #define LOCK_TOKEN	1
 #endif
 
-#if defined(CONFIG_PPC64) && defined(CONFIG_SMP)
-#define CLEAR_IO_SYNC	(get_paca()->io_sync = 0)
-#define SYNC_IO		do {						\
-				if (unlikely(get_paca()->io_sync)) {	\
-					mb();				\
-					get_paca()->io_sync = 0;	\
-				}					\
-			} while (0)
-#else
-#define CLEAR_IO_SYNC
-#define SYNC_IO
-#endif
-
 #ifdef CONFIG_PPC_PSERIES
 #define vcpu_is_preempted vcpu_is_preempted
 static inline bool vcpu_is_preempted(int cpu)
@@ -99,7 +86,6 @@ static inline unsigned long __arch_spin_trylock(arch_spinlock_t *lock)
 
 static inline int arch_spin_trylock(arch_spinlock_t *lock)
 {
-	CLEAR_IO_SYNC;
 	return __arch_spin_trylock(lock) == 0;
 }
 
@@ -130,7 +116,6 @@ extern void __rw_yield(arch_rwlock_t *lock);
 
 static inline void arch_spin_lock(arch_spinlock_t *lock)
 {
-	CLEAR_IO_SYNC;
 	while (1) {
 		if (likely(__arch_spin_trylock(lock) == 0))
 			break;
@@ -148,7 +133,6 @@ void arch_spin_lock_flags(arch_spinlock_t *lock, unsigned long flags)
 {
 	unsigned long flags_dis;
 
-	CLEAR_IO_SYNC;
 	while (1) {
 		if (likely(__arch_spin_trylock(lock) == 0))
 			break;
@@ -167,7 +151,6 @@ void arch_spin_lock_flags(arch_spinlock_t *lock, unsigned long flags)
 
 static inline void arch_spin_unlock(arch_spinlock_t *lock)
 {
-	SYNC_IO;
 	__asm__ __volatile__("# arch_spin_unlock\n\t"
 				PPC_RELEASE_BARRIER: : :"memory");
 	lock->slock = 0;
diff --git a/arch/powerpc/include/asm/syscall.h b/arch/powerpc/include/asm/syscall.h
index 1a0e7a8b1c81..1243045bad2d 100644
--- a/arch/powerpc/include/asm/syscall.h
+++ b/arch/powerpc/include/asm/syscall.h
@@ -65,22 +65,20 @@ static inline void syscall_set_return_value(struct task_struct *task,
 
 static inline void syscall_get_arguments(struct task_struct *task,
 					 struct pt_regs *regs,
-					 unsigned int i, unsigned int n,
 					 unsigned long *args)
 {
 	unsigned long val, mask = -1UL;
-
-	BUG_ON(i + n > 6);
+	unsigned int n = 6;
 
 #ifdef CONFIG_COMPAT
 	if (test_tsk_thread_flag(task, TIF_32BIT))
 		mask = 0xffffffff;
 #endif
 	while (n--) {
-		if (n == 0 && i == 0)
+		if (n == 0)
 			val = regs->orig_gpr3;
 		else
-			val = regs->gpr[3 + i + n];
+			val = regs->gpr[3 + n];
 
 		args[n] = val & mask;
 	}
@@ -88,15 +86,12 @@ static inline void syscall_get_arguments(struct task_struct *task,
 
 static inline void syscall_set_arguments(struct task_struct *task,
 					 struct pt_regs *regs,
-					 unsigned int i, unsigned int n,
 					 const unsigned long *args)
 {
-	BUG_ON(i + n > 6);
-	memcpy(&regs->gpr[3 + i], args, n * sizeof(args[0]));
+	memcpy(&regs->gpr[3], args, 6 * sizeof(args[0]));
 
 	/* Also copy the first argument into orig_gpr3 */
-	if (i == 0 && n > 0)
-		regs->orig_gpr3 = args[0];
+	regs->orig_gpr3 = args[0];
 }
 
 static inline int syscall_get_arch(void)
diff --git a/arch/powerpc/include/asm/tlb.h b/arch/powerpc/include/asm/tlb.h
index e24c67d5ba75..34fba1ce27f7 100644
--- a/arch/powerpc/include/asm/tlb.h
+++ b/arch/powerpc/include/asm/tlb.h
@@ -27,8 +27,8 @@
 #define tlb_start_vma(tlb, vma)	do { } while (0)
 #define tlb_end_vma(tlb, vma)	do { } while (0)
 #define __tlb_remove_tlb_entry	__tlb_remove_tlb_entry
-#define tlb_remove_check_page_size_change tlb_remove_check_page_size_change
 
+#define tlb_flush tlb_flush
 extern void tlb_flush(struct mmu_gather *tlb);
 
 /* Get the generic bits... */
@@ -46,22 +46,6 @@ static inline void __tlb_remove_tlb_entry(struct mmu_gather *tlb, pte_t *ptep,
 #endif
 }
 
-static inline void tlb_remove_check_page_size_change(struct mmu_gather *tlb,
-						     unsigned int page_size)
-{
-	if (!tlb->page_size)
-		tlb->page_size = page_size;
-	else if (tlb->page_size != page_size) {
-		if (!tlb->fullmm)
-			tlb_flush_mmu(tlb);
-		/*
-		 * update the page size after flush for the new
-		 * mmu_gather.
-		 */
-		tlb->page_size = page_size;
-	}
-}
-
 #ifdef CONFIG_SMP
 static inline int mm_is_core_local(struct mm_struct *mm)
 {
diff --git a/arch/powerpc/kernel/exceptions-64s.S b/arch/powerpc/kernel/exceptions-64s.S
index a5b8fbae56a0..9481a117e242 100644
--- a/arch/powerpc/kernel/exceptions-64s.S
+++ b/arch/powerpc/kernel/exceptions-64s.S
@@ -656,11 +656,17 @@ EXC_COMMON_BEGIN(data_access_slb_common)
 	ld	r4,PACA_EXSLB+EX_DAR(r13)
 	std	r4,_DAR(r1)
 	addi	r3,r1,STACK_FRAME_OVERHEAD
+BEGIN_MMU_FTR_SECTION
+	/* HPT case, do SLB fault */
 	bl	do_slb_fault
 	cmpdi	r3,0
 	bne-	1f
 	b	fast_exception_return
 1:	/* Error case */
+MMU_FTR_SECTION_ELSE
+	/* Radix case, access is outside page table range */
+	li	r3,-EFAULT
+ALT_MMU_FTR_SECTION_END_IFCLR(MMU_FTR_TYPE_RADIX)
 	std	r3,RESULT(r1)
 	bl	save_nvgprs
 	RECONCILE_IRQ_STATE(r10, r11)
@@ -705,11 +711,17 @@ EXC_COMMON_BEGIN(instruction_access_slb_common)
 	EXCEPTION_PROLOG_COMMON(0x480, PACA_EXSLB)
 	ld	r4,_NIP(r1)
 	addi	r3,r1,STACK_FRAME_OVERHEAD
+BEGIN_MMU_FTR_SECTION
+	/* HPT case, do SLB fault */
 	bl	do_slb_fault
 	cmpdi	r3,0
 	bne-	1f
 	b	fast_exception_return
 1:	/* Error case */
+MMU_FTR_SECTION_ELSE
+	/* Radix case, access is outside page table range */
+	li	r3,-EFAULT
+ALT_MMU_FTR_SECTION_END_IFCLR(MMU_FTR_TYPE_RADIX)
 	std	r3,RESULT(r1)
 	bl	save_nvgprs
 	RECONCILE_IRQ_STATE(r10, r11)
diff --git a/arch/powerpc/kernel/head_32.S b/arch/powerpc/kernel/head_32.S
index 48051c8977c5..e25b615e9f9e 100644
--- a/arch/powerpc/kernel/head_32.S
+++ b/arch/powerpc/kernel/head_32.S
@@ -851,10 +851,6 @@ __secondary_start:
 	tophys(r4,r2)
 	addi	r4,r4,THREAD	/* phys address of our thread_struct */
 	mtspr	SPRN_SPRG_THREAD,r4
-#ifdef CONFIG_PPC_RTAS
-	li	r3,0
-	stw	r3, RTAS_SP(r4)		/* 0 => not in RTAS */
-#endif
 	lis	r4, (swapper_pg_dir - PAGE_OFFSET)@h
 	ori	r4, r4, (swapper_pg_dir - PAGE_OFFSET)@l
 	mtspr	SPRN_SPRG_PGDIR, r4
@@ -941,10 +937,6 @@ start_here:
 	tophys(r4,r2)
 	addi	r4,r4,THREAD	/* init task's THREAD */
 	mtspr	SPRN_SPRG_THREAD,r4
-#ifdef CONFIG_PPC_RTAS
-	li	r3,0
-	stw	r3, RTAS_SP(r4)		/* 0 => not in RTAS */
-#endif
 	lis	r4, (swapper_pg_dir - PAGE_OFFSET)@h
 	ori	r4, r4, (swapper_pg_dir - PAGE_OFFSET)@l
 	mtspr	SPRN_SPRG_PGDIR, r4
diff --git a/arch/powerpc/kernel/kvm.c b/arch/powerpc/kernel/kvm.c
index 683b5b3805bd..cd381e2291df 100644
--- a/arch/powerpc/kernel/kvm.c
+++ b/arch/powerpc/kernel/kvm.c
@@ -22,6 +22,7 @@
 #include <linux/kvm_host.h>
 #include <linux/init.h>
 #include <linux/export.h>
+#include <linux/kmemleak.h>
 #include <linux/kvm_para.h>
 #include <linux/slab.h>
 #include <linux/of.h>
@@ -712,6 +713,12 @@ static void kvm_use_magic_page(void)
 
 static __init void kvm_free_tmp(void)
 {
+	/*
+	 * Inform kmemleak about the hole in the .bss section since the
+	 * corresponding pages will be unmapped with DEBUG_PAGEALLOC=y.
+	 */
+	kmemleak_free_part(&kvm_tmp[kvm_tmp_index],
+			   ARRAY_SIZE(kvm_tmp) - kvm_tmp_index);
 	free_reserved_area(&kvm_tmp[kvm_tmp_index],
 			   &kvm_tmp[ARRAY_SIZE(kvm_tmp)], -1, NULL);
 }
diff --git a/arch/powerpc/kernel/security.c b/arch/powerpc/kernel/security.c
index b33bafb8fcea..70568ccbd9fd 100644
--- a/arch/powerpc/kernel/security.c
+++ b/arch/powerpc/kernel/security.c
@@ -57,7 +57,7 @@ void setup_barrier_nospec(void)
 	enable = security_ftr_enabled(SEC_FTR_FAVOUR_SECURITY) &&
 		 security_ftr_enabled(SEC_FTR_BNDS_CHK_SPEC_BAR);
 
-	if (!no_nospec)
+	if (!no_nospec && !cpu_mitigations_off())
 		enable_barrier_nospec(enable);
 }
 
@@ -116,7 +116,7 @@ static int __init handle_nospectre_v2(char *p)
 early_param("nospectre_v2", handle_nospectre_v2);
 void setup_spectre_v2(void)
 {
-	if (no_spectrev2)
+	if (no_spectrev2 || cpu_mitigations_off())
 		do_btb_flush_fixups();
 	else
 		btb_flush_enabled = true;
@@ -300,7 +300,7 @@ void setup_stf_barrier(void)
 
 	stf_enabled_flush_types = type;
 
-	if (!no_stf_barrier)
+	if (!no_stf_barrier && !cpu_mitigations_off())
 		stf_barrier_enable(enable);
 }
 
diff --git a/arch/powerpc/kernel/setup_64.c b/arch/powerpc/kernel/setup_64.c
index ba404dd9ce1d..4f49e1a3594c 100644
--- a/arch/powerpc/kernel/setup_64.c
+++ b/arch/powerpc/kernel/setup_64.c
@@ -932,7 +932,7 @@ void setup_rfi_flush(enum l1d_flush_type types, bool enable)
 
 	enabled_flush_types = types;
 
-	if (!no_rfi_flush)
+	if (!no_rfi_flush && !cpu_mitigations_off())
 		rfi_flush_enable(enable);
 }
 
diff --git a/arch/powerpc/kernel/syscalls/syscall.tbl b/arch/powerpc/kernel/syscalls/syscall.tbl
index b18abb0c3dae..00f5a63c8d9a 100644
--- a/arch/powerpc/kernel/syscalls/syscall.tbl
+++ b/arch/powerpc/kernel/syscalls/syscall.tbl
@@ -505,3 +505,7 @@
 421	32	rt_sigtimedwait_time64		sys_rt_sigtimedwait		compat_sys_rt_sigtimedwait_time64
 422	32	futex_time64			sys_futex			sys_futex
 423	32	sched_rr_get_interval_time64	sys_sched_rr_get_interval	sys_sched_rr_get_interval
+424	common	pidfd_send_signal		sys_pidfd_send_signal
+425	common	io_uring_setup			sys_io_uring_setup
+426	common	io_uring_enter			sys_io_uring_enter
+427	common	io_uring_register		sys_io_uring_register
diff --git a/arch/powerpc/kernel/vdso32/gettimeofday.S b/arch/powerpc/kernel/vdso32/gettimeofday.S
index 1e0bc5955a40..afd516b572f8 100644
--- a/arch/powerpc/kernel/vdso32/gettimeofday.S
+++ b/arch/powerpc/kernel/vdso32/gettimeofday.S
@@ -98,7 +98,7 @@ V_FUNCTION_BEGIN(__kernel_clock_gettime)
 	 * can be used, r7 contains NSEC_PER_SEC.
 	 */
 
-	lwz	r5,WTOM_CLOCK_SEC(r9)
+	lwz	r5,(WTOM_CLOCK_SEC+LOPART)(r9)
 	lwz	r6,WTOM_CLOCK_NSEC(r9)
 
 	/* We now have our offset in r5,r6. We create a fake dependency
diff --git a/arch/powerpc/kvm/book3s_64_vio.c b/arch/powerpc/kvm/book3s_64_vio.c
index f02b04973710..f100e331e69b 100644
--- a/arch/powerpc/kvm/book3s_64_vio.c
+++ b/arch/powerpc/kvm/book3s_64_vio.c
@@ -543,14 +543,14 @@ long kvmppc_h_put_tce(struct kvm_vcpu *vcpu, unsigned long liobn,
 	if (ret != H_SUCCESS)
 		return ret;
 
+	idx = srcu_read_lock(&vcpu->kvm->srcu);
+
 	ret = kvmppc_tce_validate(stt, tce);
 	if (ret != H_SUCCESS)
-		return ret;
+		goto unlock_exit;
 
 	dir = iommu_tce_direction(tce);
 
-	idx = srcu_read_lock(&vcpu->kvm->srcu);
-
 	if ((dir != DMA_NONE) && kvmppc_tce_to_ua(vcpu->kvm, tce, &ua, NULL)) {
 		ret = H_PARAMETER;
 		goto unlock_exit;
diff --git a/arch/powerpc/kvm/book3s_hv.c b/arch/powerpc/kvm/book3s_hv.c
index 06964350b97a..b2b29d4f9842 100644
--- a/arch/powerpc/kvm/book3s_hv.c
+++ b/arch/powerpc/kvm/book3s_hv.c
@@ -3423,7 +3423,9 @@ static int kvmhv_load_hv_regs_and_go(struct kvm_vcpu *vcpu, u64 time_limit,
 	vcpu->arch.shregs.sprg2 = mfspr(SPRN_SPRG2);
 	vcpu->arch.shregs.sprg3 = mfspr(SPRN_SPRG3);
 
-	mtspr(SPRN_PSSCR, host_psscr);
+	/* Preserve PSSCR[FAKE_SUSPEND] until we've called kvmppc_save_tm_hv */
+	mtspr(SPRN_PSSCR, host_psscr |
+	      (local_paca->kvm_hstate.fake_suspend << PSSCR_FAKE_SUSPEND_LG));
 	mtspr(SPRN_HFSCR, host_hfscr);
 	mtspr(SPRN_CIABR, host_ciabr);
 	mtspr(SPRN_DAWR, host_dawr);
diff --git a/arch/powerpc/lib/memcmp_64.S b/arch/powerpc/lib/memcmp_64.S
index 844d8e774492..b7f6f6e0b6e8 100644
--- a/arch/powerpc/lib/memcmp_64.S
+++ b/arch/powerpc/lib/memcmp_64.S
@@ -215,11 +215,20 @@ _GLOBAL_TOC(memcmp)
 	beq	.Lzero
 
 .Lcmp_rest_lt8bytes:
-	/* Here we have only less than 8 bytes to compare with. at least s1
-	 * Address is aligned with 8 bytes.
-	 * The next double words are load and shift right with appropriate
-	 * bits.
+	/*
+	 * Here we have less than 8 bytes to compare. At least s1 is aligned to
+	 * 8 bytes, but s2 may not be. We must make sure s2 + 7 doesn't cross a
+	 * page boundary, otherwise we might read past the end of the buffer and
+	 * trigger a page fault. We use 4K as the conservative minimum page
+	 * size. If we detect that case we go to the byte-by-byte loop.
+	 *
+	 * Otherwise the next double word is loaded from s1 and s2, and shifted
+	 * right to compare the appropriate bits.
 	 */
+	clrldi	r6,r4,(64-12)	// r6 = r4 & 0xfff
+	cmpdi	r6,0xff8
+	bgt	.Lshort
+
 	subfic  r6,r5,8
 	slwi	r6,r6,3
 	LD	rA,0,r3
diff --git a/arch/powerpc/mm/mmu_context_iommu.c b/arch/powerpc/mm/mmu_context_iommu.c
index e7a9c4f6bfca..8330f135294f 100644
--- a/arch/powerpc/mm/mmu_context_iommu.c
+++ b/arch/powerpc/mm/mmu_context_iommu.c
@@ -95,28 +95,15 @@ static long mm_iommu_do_alloc(struct mm_struct *mm, unsigned long ua,
 			      unsigned long entries, unsigned long dev_hpa,
 			      struct mm_iommu_table_group_mem_t **pmem)
 {
-	struct mm_iommu_table_group_mem_t *mem;
-	long i, ret, locked_entries = 0;
+	struct mm_iommu_table_group_mem_t *mem, *mem2;
+	long i, ret, locked_entries = 0, pinned = 0;
 	unsigned int pageshift;
-
-	mutex_lock(&mem_list_mutex);
-
-	list_for_each_entry_rcu(mem, &mm->context.iommu_group_mem_list,
-			next) {
-		/* Overlap? */
-		if ((mem->ua < (ua + (entries << PAGE_SHIFT))) &&
-				(ua < (mem->ua +
-				       (mem->entries << PAGE_SHIFT)))) {
-			ret = -EINVAL;
-			goto unlock_exit;
-		}
-
-	}
+	unsigned long entry, chunk;
 
 	if (dev_hpa == MM_IOMMU_TABLE_INVALID_HPA) {
 		ret = mm_iommu_adjust_locked_vm(mm, entries, true);
 		if (ret)
-			goto unlock_exit;
+			return ret;
 
 		locked_entries = entries;
 	}
@@ -148,17 +135,27 @@ static long mm_iommu_do_alloc(struct mm_struct *mm, unsigned long ua,
 	}
 
 	down_read(&mm->mmap_sem);
-	ret = get_user_pages_longterm(ua, entries, FOLL_WRITE, mem->hpages, NULL);
+	chunk = (1UL << (PAGE_SHIFT + MAX_ORDER - 1)) /
+			sizeof(struct vm_area_struct *);
+	chunk = min(chunk, entries);
+	for (entry = 0; entry < entries; entry += chunk) {
+		unsigned long n = min(entries - entry, chunk);
+
+		ret = get_user_pages_longterm(ua + (entry << PAGE_SHIFT), n,
+				FOLL_WRITE, mem->hpages + entry, NULL);
+		if (ret == n) {
+			pinned += n;
+			continue;
+		}
+		if (ret > 0)
+			pinned += ret;
+		break;
+	}
 	up_read(&mm->mmap_sem);
-	if (ret != entries) {
-		/* free the reference taken */
-		for (i = 0; i < ret; i++)
-			put_page(mem->hpages[i]);
-
-		vfree(mem->hpas);
-		kfree(mem);
-		ret = -EFAULT;
-		goto unlock_exit;
+	if (pinned != entries) {
+		if (!ret)
+			ret = -EFAULT;
+		goto free_exit;
 	}
 
 	pageshift = PAGE_SHIFT;
@@ -183,21 +180,43 @@ static long mm_iommu_do_alloc(struct mm_struct *mm, unsigned long ua,
 	}
 
 good_exit:
-	ret = 0;
 	atomic64_set(&mem->mapped, 1);
 	mem->used = 1;
 	mem->ua = ua;
 	mem->entries = entries;
-	*pmem = mem;
 
-	list_add_rcu(&mem->next, &mm->context.iommu_group_mem_list);
+	mutex_lock(&mem_list_mutex);
 
-unlock_exit:
-	if (locked_entries && ret)
-		mm_iommu_adjust_locked_vm(mm, locked_entries, false);
+	list_for_each_entry_rcu(mem2, &mm->context.iommu_group_mem_list, next) {
+		/* Overlap? */
+		if ((mem2->ua < (ua + (entries << PAGE_SHIFT))) &&
+				(ua < (mem2->ua +
+				       (mem2->entries << PAGE_SHIFT)))) {
+			ret = -EINVAL;
+			mutex_unlock(&mem_list_mutex);
+			goto free_exit;
+		}
+	}
+
+	list_add_rcu(&mem->next, &mm->context.iommu_group_mem_list);
 
 	mutex_unlock(&mem_list_mutex);
 
+	*pmem = mem;
+
+	return 0;
+
+free_exit:
+	/* free the reference taken */
+	for (i = 0; i < pinned; i++)
+		put_page(mem->hpages[i]);
+
+	vfree(mem->hpas);
+	kfree(mem);
+
+unlock_exit:
+	mm_iommu_adjust_locked_vm(mm, locked_entries, false);
+
 	return ret;
 }
 
@@ -266,7 +285,7 @@ static void mm_iommu_release(struct mm_iommu_table_group_mem_t *mem)
 long mm_iommu_put(struct mm_struct *mm, struct mm_iommu_table_group_mem_t *mem)
 {
 	long ret = 0;
-	unsigned long entries, dev_hpa;
+	unsigned long unlock_entries = 0;
 
 	mutex_lock(&mem_list_mutex);
 
@@ -287,17 +306,17 @@ long mm_iommu_put(struct mm_struct *mm, struct mm_iommu_table_group_mem_t *mem)
 		goto unlock_exit;
 	}
 
+	if (mem->dev_hpa == MM_IOMMU_TABLE_INVALID_HPA)
+		unlock_entries = mem->entries;
+
 	/* @mapped became 0 so now mappings are disabled, release the region */
-	entries = mem->entries;
-	dev_hpa = mem->dev_hpa;
 	mm_iommu_release(mem);
 
-	if (dev_hpa == MM_IOMMU_TABLE_INVALID_HPA)
-		mm_iommu_adjust_locked_vm(mm, entries, false);
-
 unlock_exit:
 	mutex_unlock(&mem_list_mutex);
 
+	mm_iommu_adjust_locked_vm(mm, unlock_entries, false);
+
 	return ret;
 }
 EXPORT_SYMBOL_GPL(mm_iommu_put);
diff --git a/arch/powerpc/mm/ppc_mmu_32.c b/arch/powerpc/mm/ppc_mmu_32.c
index f29d2f118b44..5d9c3ff728c9 100644
--- a/arch/powerpc/mm/ppc_mmu_32.c
+++ b/arch/powerpc/mm/ppc_mmu_32.c
@@ -98,10 +98,20 @@ static int find_free_bat(void)
 	return -1;
 }
 
+/*
+ * This function calculates the size of the larger block usable to map the
+ * beginning of an area based on the start address and size of that area:
+ * - max block size is 8M on 601 and 256 on other 6xx.
+ * - base address must be aligned to the block size. So the maximum block size
+ *   is identified by the lowest bit set to 1 in the base address (for instance
+ *   if base is 0x16000000, max size is 0x02000000).
+ * - block size has to be a power of two. This is calculated by finding the
+ *   highest bit set to 1.
+ */
 static unsigned int block_size(unsigned long base, unsigned long top)
 {
 	unsigned int max_size = (cpu_has_feature(CPU_FTR_601) ? 8 : 256) << 20;
-	unsigned int base_shift = (fls(base) - 1) & 31;
+	unsigned int base_shift = (ffs(base) - 1) & 31;
 	unsigned int block_shift = (fls(top - base) - 1) & 31;
 
 	return min3(max_size, 1U << base_shift, 1U << block_shift);
@@ -157,7 +167,7 @@ static unsigned long __init __mmu_mapin_ram(unsigned long base, unsigned long to
 
 unsigned long __init mmu_mapin_ram(unsigned long base, unsigned long top)
 {
-	int done;
+	unsigned long done;
 	unsigned long border = (unsigned long)__init_begin - PAGE_OFFSET;
 
 	if (__map_without_bats) {
@@ -169,10 +179,10 @@ unsigned long __init mmu_mapin_ram(unsigned long base, unsigned long top)
 		return __mmu_mapin_ram(base, top);
 
 	done = __mmu_mapin_ram(base, border);
-	if (done != border - base)
+	if (done != border)
 		return done;
 
-	return done + __mmu_mapin_ram(border, top);
+	return __mmu_mapin_ram(border, top);
 }
 
 void mmu_mark_initmem_nx(void)
diff --git a/arch/powerpc/net/bpf_jit.h b/arch/powerpc/net/bpf_jit.h
index 549e9490ff2a..dcac37745b05 100644
--- a/arch/powerpc/net/bpf_jit.h
+++ b/arch/powerpc/net/bpf_jit.h
@@ -51,6 +51,8 @@
 #define PPC_LIS(r, i)		PPC_ADDIS(r, 0, i)
 #define PPC_STD(r, base, i)	EMIT(PPC_INST_STD | ___PPC_RS(r) |	      \
 				     ___PPC_RA(base) | ((i) & 0xfffc))
+#define PPC_STDX(r, base, b)	EMIT(PPC_INST_STDX | ___PPC_RS(r) |	      \
+				     ___PPC_RA(base) | ___PPC_RB(b))
 #define PPC_STDU(r, base, i)	EMIT(PPC_INST_STDU | ___PPC_RS(r) |	      \
 				     ___PPC_RA(base) | ((i) & 0xfffc))
 #define PPC_STW(r, base, i)	EMIT(PPC_INST_STW | ___PPC_RS(r) |	      \
@@ -65,7 +67,9 @@
 #define PPC_LBZ(r, base, i)	EMIT(PPC_INST_LBZ | ___PPC_RT(r) |	      \
 				     ___PPC_RA(base) | IMM_L(i))
 #define PPC_LD(r, base, i)	EMIT(PPC_INST_LD | ___PPC_RT(r) |	      \
-				     ___PPC_RA(base) | IMM_L(i))
+				     ___PPC_RA(base) | ((i) & 0xfffc))
+#define PPC_LDX(r, base, b)	EMIT(PPC_INST_LDX | ___PPC_RT(r) |	      \
+				     ___PPC_RA(base) | ___PPC_RB(b))
 #define PPC_LWZ(r, base, i)	EMIT(PPC_INST_LWZ | ___PPC_RT(r) |	      \
 				     ___PPC_RA(base) | IMM_L(i))
 #define PPC_LHZ(r, base, i)	EMIT(PPC_INST_LHZ | ___PPC_RT(r) |	      \
@@ -85,17 +89,6 @@
 					___PPC_RA(a) | ___PPC_RB(b))
 #define PPC_BPF_STDCX(s, a, b)	EMIT(PPC_INST_STDCX | ___PPC_RS(s) |	      \
 					___PPC_RA(a) | ___PPC_RB(b))
-
-#ifdef CONFIG_PPC64
-#define PPC_BPF_LL(r, base, i) do { PPC_LD(r, base, i); } while(0)
-#define PPC_BPF_STL(r, base, i) do { PPC_STD(r, base, i); } while(0)
-#define PPC_BPF_STLU(r, base, i) do { PPC_STDU(r, base, i); } while(0)
-#else
-#define PPC_BPF_LL(r, base, i) do { PPC_LWZ(r, base, i); } while(0)
-#define PPC_BPF_STL(r, base, i) do { PPC_STW(r, base, i); } while(0)
-#define PPC_BPF_STLU(r, base, i) do { PPC_STWU(r, base, i); } while(0)
-#endif
-
 #define PPC_CMPWI(a, i)		EMIT(PPC_INST_CMPWI | ___PPC_RA(a) | IMM_L(i))
 #define PPC_CMPDI(a, i)		EMIT(PPC_INST_CMPDI | ___PPC_RA(a) | IMM_L(i))
 #define PPC_CMPW(a, b)		EMIT(PPC_INST_CMPW | ___PPC_RA(a) |	      \
diff --git a/arch/powerpc/net/bpf_jit32.h b/arch/powerpc/net/bpf_jit32.h
index dc50a8d4b3b9..21744d8aa053 100644
--- a/arch/powerpc/net/bpf_jit32.h
+++ b/arch/powerpc/net/bpf_jit32.h
@@ -122,6 +122,10 @@ DECLARE_LOAD_FUNC(sk_load_byte_msh);
 #define PPC_NTOHS_OFFS(r, base, i)	PPC_LHZ_OFFS(r, base, i)
 #endif
 
+#define PPC_BPF_LL(r, base, i) do { PPC_LWZ(r, base, i); } while(0)
+#define PPC_BPF_STL(r, base, i) do { PPC_STW(r, base, i); } while(0)
+#define PPC_BPF_STLU(r, base, i) do { PPC_STWU(r, base, i); } while(0)
+
 #define SEEN_DATAREF 0x10000 /* might call external helpers */
 #define SEEN_XREG    0x20000 /* X reg is used */
 #define SEEN_MEM     0x40000 /* SEEN_MEM+(1<<n) = use mem[n] for temporary
diff --git a/arch/powerpc/net/bpf_jit64.h b/arch/powerpc/net/bpf_jit64.h
index 3609be4692b3..47f441f351a6 100644
--- a/arch/powerpc/net/bpf_jit64.h
+++ b/arch/powerpc/net/bpf_jit64.h
@@ -68,6 +68,26 @@ static const int b2p[] = {
 /* PPC NVR range -- update this if we ever use NVRs below r27 */
 #define BPF_PPC_NVR_MIN		27
 
+/*
+ * WARNING: These can use TMP_REG_2 if the offset is not at word boundary,
+ * so ensure that it isn't in use already.
+ */
+#define PPC_BPF_LL(r, base, i) do {					      \
+				if ((i) % 4) {				      \
+					PPC_LI(b2p[TMP_REG_2], (i));	      \
+					PPC_LDX(r, base, b2p[TMP_REG_2]);     \
+				} else					      \
+					PPC_LD(r, base, i);		      \
+				} while(0)
+#define PPC_BPF_STL(r, base, i) do {					      \
+				if ((i) % 4) {				      \
+					PPC_LI(b2p[TMP_REG_2], (i));	      \
+					PPC_STDX(r, base, b2p[TMP_REG_2]);    \
+				} else					      \
+					PPC_STD(r, base, i);		      \
+				} while(0)
+#define PPC_BPF_STLU(r, base, i) do { PPC_STDU(r, base, i); } while(0)
+
 #define SEEN_FUNC	0x1000 /* might call external helpers */
 #define SEEN_STACK	0x2000 /* uses BPF stack */
 #define SEEN_TAILCALL	0x4000 /* uses tail calls */
diff --git a/arch/powerpc/net/bpf_jit_comp64.c b/arch/powerpc/net/bpf_jit_comp64.c
index 4194d3cfb60c..21a1dcd4b156 100644
--- a/arch/powerpc/net/bpf_jit_comp64.c
+++ b/arch/powerpc/net/bpf_jit_comp64.c
@@ -252,7 +252,7 @@ static void bpf_jit_emit_tail_call(u32 *image, struct codegen_context *ctx, u32
 	 * if (tail_call_cnt > MAX_TAIL_CALL_CNT)
 	 *   goto out;
 	 */
-	PPC_LD(b2p[TMP_REG_1], 1, bpf_jit_stack_tailcallcnt(ctx));
+	PPC_BPF_LL(b2p[TMP_REG_1], 1, bpf_jit_stack_tailcallcnt(ctx));
 	PPC_CMPLWI(b2p[TMP_REG_1], MAX_TAIL_CALL_CNT);
 	PPC_BCC(COND_GT, out);
 
@@ -265,7 +265,7 @@ static void bpf_jit_emit_tail_call(u32 *image, struct codegen_context *ctx, u32
 	/* prog = array->ptrs[index]; */
 	PPC_MULI(b2p[TMP_REG_1], b2p_index, 8);
 	PPC_ADD(b2p[TMP_REG_1], b2p[TMP_REG_1], b2p_bpf_array);
-	PPC_LD(b2p[TMP_REG_1], b2p[TMP_REG_1], offsetof(struct bpf_array, ptrs));
+	PPC_BPF_LL(b2p[TMP_REG_1], b2p[TMP_REG_1], offsetof(struct bpf_array, ptrs));
 
 	/*
 	 * if (prog == NULL)
@@ -275,7 +275,7 @@ static void bpf_jit_emit_tail_call(u32 *image, struct codegen_context *ctx, u32
 	PPC_BCC(COND_EQ, out);
 
 	/* goto *(prog->bpf_func + prologue_size); */
-	PPC_LD(b2p[TMP_REG_1], b2p[TMP_REG_1], offsetof(struct bpf_prog, bpf_func));
+	PPC_BPF_LL(b2p[TMP_REG_1], b2p[TMP_REG_1], offsetof(struct bpf_prog, bpf_func));
 #ifdef PPC64_ELF_ABI_v1
 	/* skip past the function descriptor */
 	PPC_ADDI(b2p[TMP_REG_1], b2p[TMP_REG_1],
@@ -606,7 +606,7 @@ bpf_alu32_trunc:
 				 * the instructions generated will remain the
 				 * same across all passes
 				 */
-				PPC_STD(dst_reg, 1, bpf_jit_stack_local(ctx));
+				PPC_BPF_STL(dst_reg, 1, bpf_jit_stack_local(ctx));
 				PPC_ADDI(b2p[TMP_REG_1], 1, bpf_jit_stack_local(ctx));
 				PPC_LDBRX(dst_reg, 0, b2p[TMP_REG_1]);
 				break;
@@ -662,7 +662,7 @@ emit_clear:
 				PPC_LI32(b2p[TMP_REG_1], imm);
 				src_reg = b2p[TMP_REG_1];
 			}
-			PPC_STD(src_reg, dst_reg, off);
+			PPC_BPF_STL(src_reg, dst_reg, off);
 			break;
 
 		/*
@@ -709,7 +709,7 @@ emit_clear:
 			break;
 		/* dst = *(u64 *)(ul) (src + off) */
 		case BPF_LDX | BPF_MEM | BPF_DW:
-			PPC_LD(dst_reg, src_reg, off);
+			PPC_BPF_LL(dst_reg, src_reg, off);
 			break;
 
 		/*
diff --git a/arch/powerpc/platforms/Kconfig.cputype b/arch/powerpc/platforms/Kconfig.cputype
index 842b2c7e156a..50cd09b4e05d 100644
--- a/arch/powerpc/platforms/Kconfig.cputype
+++ b/arch/powerpc/platforms/Kconfig.cputype
@@ -324,7 +324,7 @@ config ARCH_ENABLE_SPLIT_PMD_PTLOCK
 
 config PPC_RADIX_MMU
 	bool "Radix MMU Support"
-	depends on PPC_BOOK3S_64
+	depends on PPC_BOOK3S_64 && HUGETLB_PAGE
 	select ARCH_HAS_GIGANTIC_PAGE if (MEMORY_ISOLATION && COMPACTION) || CMA
 	default y
 	help
diff --git a/arch/powerpc/platforms/pseries/pseries_energy.c b/arch/powerpc/platforms/pseries/pseries_energy.c
index 6ed22127391b..921f12182f3e 100644
--- a/arch/powerpc/platforms/pseries/pseries_energy.c
+++ b/arch/powerpc/platforms/pseries/pseries_energy.c
@@ -77,18 +77,27 @@ static u32 cpu_to_drc_index(int cpu)
 
 		ret = drc.drc_index_start + (thread_index * drc.sequential_inc);
 	} else {
-		const __be32 *indexes;
-
-		indexes = of_get_property(dn, "ibm,drc-indexes", NULL);
-		if (indexes == NULL)
-			goto err_of_node_put;
+		u32 nr_drc_indexes, thread_drc_index;
 
 		/*
-		 * The first element indexes[0] is the number of drc_indexes
-		 * returned in the list.  Hence thread_index+1 will get the
-		 * drc_index corresponding to core number thread_index.
+		 * The first element of ibm,drc-indexes array is the
+		 * number of drc_indexes returned in the list.  Hence
+		 * thread_index+1 will get the drc_index corresponding
+		 * to core number thread_index.
 		 */
-		ret = indexes[thread_index + 1];
+		rc = of_property_read_u32_index(dn, "ibm,drc-indexes",
+						0, &nr_drc_indexes);
+		if (rc)
+			goto err_of_node_put;
+
+		WARN_ON_ONCE(thread_index > nr_drc_indexes);
+		rc = of_property_read_u32_index(dn, "ibm,drc-indexes",
+						thread_index + 1,
+						&thread_drc_index);
+		if (rc)
+			goto err_of_node_put;
+
+		ret = thread_drc_index;
 	}
 
 	rc = 0;
diff --git a/arch/powerpc/platforms/pseries/ras.c b/arch/powerpc/platforms/pseries/ras.c
index d97d52772789..452dcfd7e5dd 100644
--- a/arch/powerpc/platforms/pseries/ras.c
+++ b/arch/powerpc/platforms/pseries/ras.c
@@ -550,6 +550,7 @@ static void pseries_print_mce_info(struct pt_regs *regs,
 		"UE",
 		"SLB",
 		"ERAT",
+		"Unknown",
 		"TLB",
 		"D-Cache",
 		"Unknown",
diff --git a/arch/powerpc/xmon/xmon.c b/arch/powerpc/xmon/xmon.c
index a0f44f992360..13c6a47e6150 100644
--- a/arch/powerpc/xmon/xmon.c
+++ b/arch/powerpc/xmon/xmon.c
@@ -2429,7 +2429,10 @@ static void dump_one_paca(int cpu)
 	DUMP(p, trap_save, "%#-*x");
 	DUMP(p, irq_soft_mask, "%#-*x");
 	DUMP(p, irq_happened, "%#-*x");
-	DUMP(p, io_sync, "%#-*x");
+#ifdef CONFIG_MMIOWB
+	DUMP(p, mmiowb_state.nesting_count, "%#-*x");
+	DUMP(p, mmiowb_state.mmiowb_pending, "%#-*x");
+#endif
 	DUMP(p, irq_work_pending, "%#-*x");
 	DUMP(p, nap_state_lost, "%#-*x");
 	DUMP(p, sprg_vdso, "%#-*llx");
diff --git a/arch/riscv/Kconfig b/arch/riscv/Kconfig
index eb56c82d8aa1..e66745decea1 100644
--- a/arch/riscv/Kconfig
+++ b/arch/riscv/Kconfig
@@ -48,6 +48,7 @@ config RISCV
 	select RISCV_TIMER
 	select GENERIC_IRQ_MULTI_HANDLER
 	select ARCH_HAS_PTE_SPECIAL
+	select ARCH_HAS_MMIOWB
 	select HAVE_EBPF_JIT if 64BIT
 
 config MMU
@@ -69,9 +70,6 @@ config STACKTRACE_SUPPORT
 config TRACE_IRQFLAGS_SUPPORT
 	def_bool y
 
-config RWSEM_GENERIC_SPINLOCK
-	def_bool y
-
 config GENERIC_BUG
 	def_bool y
 	depends on BUG
diff --git a/arch/riscv/configs/rv32_defconfig b/arch/riscv/configs/rv32_defconfig
new file mode 100644
index 000000000000..1a911ed8e772
--- /dev/null
+++ b/arch/riscv/configs/rv32_defconfig
@@ -0,0 +1,84 @@
+CONFIG_SYSVIPC=y
+CONFIG_POSIX_MQUEUE=y
+CONFIG_IKCONFIG=y
+CONFIG_IKCONFIG_PROC=y
+CONFIG_CGROUPS=y
+CONFIG_CGROUP_SCHED=y
+CONFIG_CFS_BANDWIDTH=y
+CONFIG_CGROUP_BPF=y
+CONFIG_NAMESPACES=y
+CONFIG_USER_NS=y
+CONFIG_CHECKPOINT_RESTORE=y
+CONFIG_BLK_DEV_INITRD=y
+CONFIG_EXPERT=y
+CONFIG_BPF_SYSCALL=y
+CONFIG_ARCH_RV32I=y
+CONFIG_SMP=y
+CONFIG_MODULES=y
+CONFIG_MODULE_UNLOAD=y
+CONFIG_NET=y
+CONFIG_PACKET=y
+CONFIG_UNIX=y
+CONFIG_INET=y
+CONFIG_IP_MULTICAST=y
+CONFIG_IP_ADVANCED_ROUTER=y
+CONFIG_IP_PNP=y
+CONFIG_IP_PNP_DHCP=y
+CONFIG_IP_PNP_BOOTP=y
+CONFIG_IP_PNP_RARP=y
+CONFIG_NETLINK_DIAG=y
+CONFIG_PCI=y
+CONFIG_PCIEPORTBUS=y
+CONFIG_PCI_HOST_GENERIC=y
+CONFIG_PCIE_XILINX=y
+CONFIG_DEVTMPFS=y
+CONFIG_BLK_DEV_LOOP=y
+CONFIG_VIRTIO_BLK=y
+CONFIG_BLK_DEV_SD=y
+CONFIG_BLK_DEV_SR=y
+CONFIG_ATA=y
+CONFIG_SATA_AHCI=y
+CONFIG_SATA_AHCI_PLATFORM=y
+CONFIG_NETDEVICES=y
+CONFIG_VIRTIO_NET=y
+CONFIG_MACB=y
+CONFIG_E1000E=y
+CONFIG_R8169=y
+CONFIG_MICROSEMI_PHY=y
+CONFIG_INPUT_MOUSEDEV=y
+CONFIG_SERIAL_8250=y
+CONFIG_SERIAL_8250_CONSOLE=y
+CONFIG_SERIAL_OF_PLATFORM=y
+CONFIG_SERIAL_EARLYCON_RISCV_SBI=y
+CONFIG_HVC_RISCV_SBI=y
+# CONFIG_PTP_1588_CLOCK is not set
+CONFIG_DRM=y
+CONFIG_DRM_RADEON=y
+CONFIG_FRAMEBUFFER_CONSOLE=y
+CONFIG_USB=y
+CONFIG_USB_XHCI_HCD=y
+CONFIG_USB_XHCI_PLATFORM=y
+CONFIG_USB_EHCI_HCD=y
+CONFIG_USB_EHCI_HCD_PLATFORM=y
+CONFIG_USB_OHCI_HCD=y
+CONFIG_USB_OHCI_HCD_PLATFORM=y
+CONFIG_USB_STORAGE=y
+CONFIG_USB_UAS=y
+CONFIG_VIRTIO_MMIO=y
+CONFIG_SIFIVE_PLIC=y
+CONFIG_EXT4_FS=y
+CONFIG_EXT4_FS_POSIX_ACL=y
+CONFIG_AUTOFS4_FS=y
+CONFIG_MSDOS_FS=y
+CONFIG_VFAT_FS=y
+CONFIG_TMPFS=y
+CONFIG_TMPFS_POSIX_ACL=y
+CONFIG_NFS_FS=y
+CONFIG_NFS_V4=y
+CONFIG_NFS_V4_1=y
+CONFIG_NFS_V4_2=y
+CONFIG_ROOT_NFS=y
+CONFIG_CRYPTO_USER_API_HASH=y
+CONFIG_CRYPTO_DEV_VIRTIO=y
+CONFIG_PRINTK_TIME=y
+# CONFIG_RCU_TRACE is not set
diff --git a/arch/riscv/include/asm/fixmap.h b/arch/riscv/include/asm/fixmap.h
index 57afe604b495..c207f6634b91 100644
--- a/arch/riscv/include/asm/fixmap.h
+++ b/arch/riscv/include/asm/fixmap.h
@@ -26,7 +26,7 @@ enum fixed_addresses {
 };
 
 #define FIXADDR_SIZE		(__end_of_fixed_addresses * PAGE_SIZE)
-#define FIXADDR_TOP		(PAGE_OFFSET)
+#define FIXADDR_TOP		(VMALLOC_START)
 #define FIXADDR_START		(FIXADDR_TOP - FIXADDR_SIZE)
 
 #define FIXMAP_PAGE_IO		PAGE_KERNEL
diff --git a/arch/riscv/include/asm/io.h b/arch/riscv/include/asm/io.h
index 1d9c1376dc64..744fd92e77bc 100644
--- a/arch/riscv/include/asm/io.h
+++ b/arch/riscv/include/asm/io.h
@@ -20,6 +20,7 @@
 #define _ASM_RISCV_IO_H
 
 #include <linux/types.h>
+#include <asm/mmiowb.h>
 
 extern void __iomem *ioremap(phys_addr_t offset, unsigned long size);
 
@@ -100,18 +101,6 @@ static inline u64 __raw_readq(const volatile void __iomem *addr)
 #endif
 
 /*
- * FIXME: I'm flip-flopping on whether or not we should keep this or enforce
- * the ordering with I/O on spinlocks like PowerPC does.  The worry is that
- * drivers won't get this correct, but I also don't want to introduce a fence
- * into the lock code that otherwise only uses AMOs (and is essentially defined
- * by the ISA to be correct).   For now I'm leaving this here: "o,w" is
- * sufficient to ensure that all writes to the device have completed before the
- * write to the spinlock is allowed to commit.  I surmised this from reading
- * "ACQUIRES VS I/O ACCESSES" in memory-barriers.txt.
- */
-#define mmiowb()	__asm__ __volatile__ ("fence o,w" : : : "memory");
-
-/*
  * Unordered I/O memory access primitives.  These are even more relaxed than
  * the relaxed versions, as they don't even order accesses between successive
  * operations to the I/O regions.
@@ -165,7 +154,7 @@ static inline u64 __raw_readq(const volatile void __iomem *addr)
 #define __io_br()	do {} while (0)
 #define __io_ar(v)	__asm__ __volatile__ ("fence i,r" : : : "memory");
 #define __io_bw()	__asm__ __volatile__ ("fence w,o" : : : "memory");
-#define __io_aw()	do {} while (0)
+#define __io_aw()	mmiowb_set_pending()
 
 #define readb(c)	({ u8  __v; __io_br(); __v = readb_cpu(c); __io_ar(__v); __v; })
 #define readw(c)	({ u16 __v; __io_br(); __v = readw_cpu(c); __io_ar(__v); __v; })
diff --git a/arch/riscv/include/asm/mmiowb.h b/arch/riscv/include/asm/mmiowb.h
new file mode 100644
index 000000000000..5d7e3a2b4e3b
--- /dev/null
+++ b/arch/riscv/include/asm/mmiowb.h
@@ -0,0 +1,14 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+
+#ifndef _ASM_RISCV_MMIOWB_H
+#define _ASM_RISCV_MMIOWB_H
+
+/*
+ * "o,w" is sufficient to ensure that all writes to the device have completed
+ * before the write to the spinlock is allowed to commit.
+ */
+#define mmiowb()	__asm__ __volatile__ ("fence o,w" : : : "memory");
+
+#include <asm-generic/mmiowb.h>
+
+#endif	/* ASM_RISCV_MMIOWB_H */
diff --git a/arch/riscv/include/asm/syscall.h b/arch/riscv/include/asm/syscall.h
index bba3da6ef157..a3d5273ded7c 100644
--- a/arch/riscv/include/asm/syscall.h
+++ b/arch/riscv/include/asm/syscall.h
@@ -72,32 +72,20 @@ static inline void syscall_set_return_value(struct task_struct *task,
 
 static inline void syscall_get_arguments(struct task_struct *task,
 					 struct pt_regs *regs,
-					 unsigned int i, unsigned int n,
 					 unsigned long *args)
 {
-	BUG_ON(i + n > 6);
-	if (i == 0) {
-		args[0] = regs->orig_a0;
-		args++;
-		i++;
-		n--;
-	}
-	memcpy(args, &regs->a1 + i * sizeof(regs->a1), n * sizeof(args[0]));
+	args[0] = regs->orig_a0;
+	args++;
+	memcpy(args, &regs->a1, 5 * sizeof(args[0]));
 }
 
 static inline void syscall_set_arguments(struct task_struct *task,
 					 struct pt_regs *regs,
-					 unsigned int i, unsigned int n,
 					 const unsigned long *args)
 {
-	BUG_ON(i + n > 6);
-        if (i == 0) {
-                regs->orig_a0 = args[0];
-                args++;
-                i++;
-                n--;
-        }
-	memcpy(&regs->a1 + i * sizeof(regs->a1), args, n * sizeof(regs->a0));
+	regs->orig_a0 = args[0];
+	args++;
+	memcpy(&regs->a1, args, 5 * sizeof(regs->a1));
 }
 
 static inline int syscall_get_arch(void)
diff --git a/arch/riscv/include/asm/tlb.h b/arch/riscv/include/asm/tlb.h
index 439dc7072e05..1ad8d093c58b 100644
--- a/arch/riscv/include/asm/tlb.h
+++ b/arch/riscv/include/asm/tlb.h
@@ -18,6 +18,7 @@ struct mmu_gather;
 
 static void tlb_flush(struct mmu_gather *tlb);
 
+#define tlb_flush tlb_flush
 #include <asm-generic/tlb.h>
 
 static inline void tlb_flush(struct mmu_gather *tlb)
diff --git a/arch/riscv/include/asm/uaccess.h b/arch/riscv/include/asm/uaccess.h
index a00168b980d2..fb53a8089e76 100644
--- a/arch/riscv/include/asm/uaccess.h
+++ b/arch/riscv/include/asm/uaccess.h
@@ -300,7 +300,7 @@ do {								\
 		"	.balign 4\n"				\
 		"4:\n"						\
 		"	li %0, %6\n"				\
-		"	jump 2b, %1\n"				\
+		"	jump 3b, %1\n"				\
 		"	.previous\n"				\
 		"	.section __ex_table,\"a\"\n"		\
 		"	.balign " RISCV_SZPTR "\n"			\
diff --git a/arch/riscv/kernel/Makefile b/arch/riscv/kernel/Makefile
index f13f7f276639..598568168d35 100644
--- a/arch/riscv/kernel/Makefile
+++ b/arch/riscv/kernel/Makefile
@@ -4,7 +4,6 @@
 
 ifdef CONFIG_FTRACE
 CFLAGS_REMOVE_ftrace.o = -pg
-CFLAGS_REMOVE_setup.o = -pg
 endif
 
 extra-y += head.o
@@ -29,8 +28,6 @@ obj-y	+= vdso.o
 obj-y	+= cacheinfo.o
 obj-y	+= vdso/
 
-CFLAGS_setup.o := -mcmodel=medany
-
 obj-$(CONFIG_FPU)		+= fpu.o
 obj-$(CONFIG_SMP)		+= smpboot.o
 obj-$(CONFIG_SMP)		+= smp.o
diff --git a/arch/riscv/kernel/module.c b/arch/riscv/kernel/module.c
index 7dd308129b40..2872edce894d 100644
--- a/arch/riscv/kernel/module.c
+++ b/arch/riscv/kernel/module.c
@@ -141,7 +141,7 @@ static int apply_r_riscv_hi20_rela(struct module *me, u32 *location,
 {
 	s32 hi20;
 
-	if (IS_ENABLED(CMODEL_MEDLOW)) {
+	if (IS_ENABLED(CONFIG_CMODEL_MEDLOW)) {
 		pr_err(
 		  "%s: target %016llx can not be addressed by the 32-bit offset from PC = %p\n",
 		  me->name, (long long)v, location);
diff --git a/arch/riscv/kernel/setup.c b/arch/riscv/kernel/setup.c
index ecb654f6a79e..540a331d1376 100644
--- a/arch/riscv/kernel/setup.c
+++ b/arch/riscv/kernel/setup.c
@@ -48,14 +48,6 @@ struct screen_info screen_info = {
 };
 #endif
 
-unsigned long va_pa_offset;
-EXPORT_SYMBOL(va_pa_offset);
-unsigned long pfn_base;
-EXPORT_SYMBOL(pfn_base);
-
-unsigned long empty_zero_page[PAGE_SIZE / sizeof(unsigned long)] __page_aligned_bss;
-EXPORT_SYMBOL(empty_zero_page);
-
 /* The lucky hart to first increment this variable will boot the other cores */
 atomic_t hart_lottery;
 unsigned long boot_cpu_hartid;
diff --git a/arch/riscv/kernel/stacktrace.c b/arch/riscv/kernel/stacktrace.c
index a4b1d94371a0..4d403274c2e8 100644
--- a/arch/riscv/kernel/stacktrace.c
+++ b/arch/riscv/kernel/stacktrace.c
@@ -169,8 +169,6 @@ static bool save_trace(unsigned long pc, void *arg)
 void save_stack_trace_tsk(struct task_struct *tsk, struct stack_trace *trace)
 {
 	walk_stackframe(tsk, NULL, save_trace, trace);
-	if (trace->nr_entries < trace->max_entries)
-		trace->entries[trace->nr_entries++] = ULONG_MAX;
 }
 EXPORT_SYMBOL_GPL(save_stack_trace_tsk);
 
diff --git a/arch/riscv/mm/Makefile b/arch/riscv/mm/Makefile
index eb22ab49b3e0..b68aac701803 100644
--- a/arch/riscv/mm/Makefile
+++ b/arch/riscv/mm/Makefile
@@ -1,3 +1,9 @@
+
+CFLAGS_init.o := -mcmodel=medany
+ifdef CONFIG_FTRACE
+CFLAGS_REMOVE_init.o = -pg
+endif
+
 obj-y += init.o
 obj-y += fault.o
 obj-y += extable.o
diff --git a/arch/riscv/mm/init.c b/arch/riscv/mm/init.c
index b379a75ac6a6..bc7b77e34d09 100644
--- a/arch/riscv/mm/init.c
+++ b/arch/riscv/mm/init.c
@@ -25,6 +25,10 @@
 #include <asm/pgtable.h>
 #include <asm/io.h>
 
+unsigned long empty_zero_page[PAGE_SIZE / sizeof(unsigned long)]
+							__page_aligned_bss;
+EXPORT_SYMBOL(empty_zero_page);
+
 static void __init zone_sizes_init(void)
 {
 	unsigned long max_zone_pfns[MAX_NR_ZONES] = { 0, };
@@ -117,6 +121,14 @@ void __init setup_bootmem(void)
 			 */
 			memblock_reserve(reg->base, vmlinux_end - reg->base);
 			mem_size = min(reg->size, (phys_addr_t)-PAGE_OFFSET);
+
+			/*
+			 * Remove memblock from the end of usable area to the
+			 * end of region
+			 */
+			if (reg->base + mem_size < end)
+				memblock_remove(reg->base + mem_size,
+						end - reg->base - mem_size);
 		}
 	}
 	BUG_ON(mem_size == 0);
@@ -143,6 +155,11 @@ void __init setup_bootmem(void)
 	}
 }
 
+unsigned long va_pa_offset;
+EXPORT_SYMBOL(va_pa_offset);
+unsigned long pfn_base;
+EXPORT_SYMBOL(pfn_base);
+
 pgd_t swapper_pg_dir[PTRS_PER_PGD] __page_aligned_bss;
 pgd_t trampoline_pg_dir[PTRS_PER_PGD] __initdata __aligned(PAGE_SIZE);
 
@@ -172,6 +189,25 @@ void __set_fixmap(enum fixed_addresses idx, phys_addr_t phys, pgprot_t prot)
 	}
 }
 
+/*
+ * setup_vm() is called from head.S with MMU-off.
+ *
+ * Following requirements should be honoured for setup_vm() to work
+ * correctly:
+ * 1) It should use PC-relative addressing for accessing kernel symbols.
+ *    To achieve this we always use GCC cmodel=medany.
+ * 2) The compiler instrumentation for FTRACE will not work for setup_vm()
+ *    so disable compiler instrumentation when FTRACE is enabled.
+ *
+ * Currently, the above requirements are honoured by using custom CFLAGS
+ * for init.o in mm/Makefile.
+ */
+
+#ifndef __riscv_cmodel_medany
+#error "setup_vm() is called from head.S before relocate so it should "
+	"not use absolute addressing."
+#endif
+
 asmlinkage void __init setup_vm(void)
 {
 	extern char _start;
diff --git a/arch/s390/Kconfig b/arch/s390/Kconfig
index b6e3d0653002..07485582d027 100644
--- a/arch/s390/Kconfig
+++ b/arch/s390/Kconfig
@@ -14,12 +14,6 @@ config LOCKDEP_SUPPORT
 config STACKTRACE_SUPPORT
 	def_bool y
 
-config RWSEM_GENERIC_SPINLOCK
-	bool
-
-config RWSEM_XCHGADD_ALGORITHM
-	def_bool y
-
 config ARCH_HAS_ILOG2_U32
 	def_bool n
 
@@ -149,6 +143,7 @@ config S390
 	select HAVE_FUNCTION_TRACER
 	select HAVE_FUTEX_CMPXCHG if FUTEX
 	select HAVE_GCC_PLUGINS
+	select HAVE_GENERIC_GUP
 	select HAVE_KERNEL_BZIP2
 	select HAVE_KERNEL_GZIP
 	select HAVE_KERNEL_LZ4
@@ -164,11 +159,13 @@ config S390
 	select HAVE_PERF_USER_STACK_DUMP
 	select HAVE_MEMBLOCK_NODE_MAP
 	select HAVE_MEMBLOCK_PHYS_MAP
+	select HAVE_MMU_GATHER_NO_GATHER
 	select HAVE_MOD_ARCH_SPECIFIC
 	select HAVE_NOP_MCOUNT
 	select HAVE_OPROFILE
 	select HAVE_PCI
 	select HAVE_PERF_EVENTS
+	select HAVE_RCU_TABLE_FREE
 	select HAVE_REGS_AND_STACK_ACCESS_API
 	select HAVE_RSEQ
 	select HAVE_SYSCALL_TRACEPOINTS
@@ -188,7 +185,6 @@ config S390
 	select TTY
 	select VIRT_CPU_ACCOUNTING
 	select ARCH_HAS_SCALED_CPUTIME
-	select VIRT_TO_BUS
 	select HAVE_NMI
 
 
@@ -240,6 +236,7 @@ choice
 
 config MARCH_Z900
 	bool "IBM zSeries model z800 and z900"
+	depends on !CC_IS_CLANG
 	select HAVE_MARCH_Z900_FEATURES
 	help
 	  Select this to enable optimizations for model z800/z900 (2064 and
@@ -248,6 +245,7 @@ config MARCH_Z900
 
 config MARCH_Z990
 	bool "IBM zSeries model z890 and z990"
+	depends on !CC_IS_CLANG
 	select HAVE_MARCH_Z990_FEATURES
 	help
 	  Select this to enable optimizations for model z890/z990 (2084 and
@@ -256,6 +254,7 @@ config MARCH_Z990
 
 config MARCH_Z9_109
 	bool "IBM System z9"
+	depends on !CC_IS_CLANG
 	select HAVE_MARCH_Z9_109_FEATURES
 	help
 	  Select this to enable optimizations for IBM System z9 (2094 and
@@ -347,12 +346,15 @@ config TUNE_DEFAULT
 
 config TUNE_Z900
 	bool "IBM zSeries model z800 and z900"
+	depends on !CC_IS_CLANG
 
 config TUNE_Z990
 	bool "IBM zSeries model z890 and z990"
+	depends on !CC_IS_CLANG
 
 config TUNE_Z9_109
 	bool "IBM System z9"
+	depends on !CC_IS_CLANG
 
 config TUNE_Z10
 	bool "IBM System z10"
@@ -388,6 +390,9 @@ config COMPAT
 	  (and some other stuff like libraries and such) is needed for
 	  executing 31 bit applications.  It is safe to say "Y".
 
+config COMPAT_VDSO
+	def_bool COMPAT && !CC_IS_CLANG
+
 config SYSVIPC_COMPAT
 	def_bool y if COMPAT && SYSVIPC
 
@@ -549,6 +554,17 @@ config ARCH_HAS_KEXEC_PURGATORY
 	def_bool y
 	depends on KEXEC_FILE
 
+config KEXEC_VERIFY_SIG
+	bool "Verify kernel signature during kexec_file_load() syscall"
+	depends on KEXEC_FILE && SYSTEM_DATA_VERIFICATION
+	help
+	  This option makes kernel signature verification mandatory for
+	  the kexec_file_load() syscall.
+
+	  In addition to that option, you need to enable signature
+	  verification for the corresponding kernel image type being
+	  loaded in order for this to work.
+
 config ARCH_RANDOM
 	def_bool y
 	prompt "s390 architectural random number generation API"
@@ -609,6 +625,29 @@ config EXPOLINE_FULL
 
 endchoice
 
+config RELOCATABLE
+	bool "Build a relocatable kernel"
+	select MODULE_REL_CRCS if MODVERSIONS
+	default y
+	help
+	  This builds a kernel image that retains relocation information
+	  so it can be loaded at an arbitrary address.
+	  The kernel is linked as a position-independent executable (PIE)
+	  and contains dynamic relocations which are processed early in the
+	  bootup process.
+	  The relocations make the kernel image about 15% larger (compressed
+	  10%), but are discarded at runtime.
+
+config RANDOMIZE_BASE
+	bool "Randomize the address of the kernel image (KASLR)"
+	depends on RELOCATABLE
+	default y
+	help
+	  In support of Kernel Address Space Layout Randomization (KASLR),
+	  this randomizes the address at which the kernel image is loaded,
+	  as a security feature that deters exploit attempts relying on
+	  knowledge of the location of kernel internals.
+
 endmenu
 
 menu "Memory setup"
@@ -837,6 +876,17 @@ config HAVE_PNETID
 
 menu "Virtualization"
 
+config PROTECTED_VIRTUALIZATION_GUEST
+	def_bool n
+	prompt "Protected virtualization guest support"
+	help
+	  Select this option, if you want to be able to run this
+	  kernel as a protected virtualization KVM guest.
+	  Protected virtualization capable machines have a mini hypervisor
+	  located at machine level (an ultravisor). With help of the
+	  Ultravisor, KVM will be able to run "protected" VMs, special
+	  VMs whose memory and management data are unavailable to KVM.
+
 config PFAULT
 	def_bool y
 	prompt "Pseudo page fault support"
diff --git a/arch/s390/Makefile b/arch/s390/Makefile
index e21053e5e0da..df1d6a150f30 100644
--- a/arch/s390/Makefile
+++ b/arch/s390/Makefile
@@ -16,10 +16,14 @@ KBUILD_AFLAGS_MODULE += -fPIC
 KBUILD_CFLAGS_MODULE += -fPIC
 KBUILD_AFLAGS	+= -m64
 KBUILD_CFLAGS	+= -m64
+ifeq ($(CONFIG_RELOCATABLE),y)
+KBUILD_CFLAGS	+= -fPIE
+LDFLAGS_vmlinux	:= -pie
+endif
 aflags_dwarf	:= -Wa,-gdwarf-2
-KBUILD_AFLAGS_DECOMPRESSOR := -m64 -D__ASSEMBLY__
+KBUILD_AFLAGS_DECOMPRESSOR := $(CLANG_FLAGS) -m64 -D__ASSEMBLY__
 KBUILD_AFLAGS_DECOMPRESSOR += $(if $(CONFIG_DEBUG_INFO),$(aflags_dwarf))
-KBUILD_CFLAGS_DECOMPRESSOR := -m64 -O2
+KBUILD_CFLAGS_DECOMPRESSOR := $(CLANG_FLAGS) -m64 -O2
 KBUILD_CFLAGS_DECOMPRESSOR += -DDISABLE_BRANCH_PROFILING -D__NO_FORTIFY
 KBUILD_CFLAGS_DECOMPRESSOR += -fno-delete-null-pointer-checks -msoft-float
 KBUILD_CFLAGS_DECOMPRESSOR += -fno-asynchronous-unwind-tables
@@ -111,7 +115,7 @@ endif
 cfi := $(call as-instr,.cfi_startproc\n.cfi_val_offset 15$(comma)-160\n.cfi_endproc,-DCONFIG_AS_CFI_VAL_OFFSET=1)
 
 KBUILD_CFLAGS	+= -mbackchain -msoft-float $(cflags-y)
-KBUILD_CFLAGS	+= -pipe -fno-strength-reduce -Wno-sign-compare
+KBUILD_CFLAGS	+= -pipe -Wno-sign-compare
 KBUILD_CFLAGS	+= -fno-asynchronous-unwind-tables $(cfi)
 KBUILD_AFLAGS	+= $(aflags-y) $(cfi)
 export KBUILD_AFLAGS_DECOMPRESSOR
diff --git a/arch/s390/boot/Makefile b/arch/s390/boot/Makefile
index c844eaf24ed7..c51496bbac19 100644
--- a/arch/s390/boot/Makefile
+++ b/arch/s390/boot/Makefile
@@ -12,25 +12,35 @@ KBUILD_AFLAGS := $(KBUILD_AFLAGS_DECOMPRESSOR)
 KBUILD_CFLAGS := $(KBUILD_CFLAGS_DECOMPRESSOR)
 
 #
-# Use -march=z900 for als.c to be able to print an error
+# Use minimum architecture for als.c to be able to print an error
 # message if the kernel is started on a machine which is too old
 #
-ifneq ($(CC_FLAGS_MARCH),-march=z900)
+ifndef CONFIG_CC_IS_CLANG
+CC_FLAGS_MARCH_MINIMUM := -march=z900
+else
+CC_FLAGS_MARCH_MINIMUM := -march=z10
+endif
+
+ifneq ($(CC_FLAGS_MARCH),$(CC_FLAGS_MARCH_MINIMUM))
 AFLAGS_REMOVE_head.o		+= $(CC_FLAGS_MARCH)
-AFLAGS_head.o			+= -march=z900
+AFLAGS_head.o			+= $(CC_FLAGS_MARCH_MINIMUM)
 AFLAGS_REMOVE_mem.o		+= $(CC_FLAGS_MARCH)
-AFLAGS_mem.o			+= -march=z900
+AFLAGS_mem.o			+= $(CC_FLAGS_MARCH_MINIMUM)
 CFLAGS_REMOVE_als.o		+= $(CC_FLAGS_MARCH)
-CFLAGS_als.o			+= -march=z900
+CFLAGS_als.o			+= $(CC_FLAGS_MARCH_MINIMUM)
 CFLAGS_REMOVE_sclp_early_core.o	+= $(CC_FLAGS_MARCH)
-CFLAGS_sclp_early_core.o	+= -march=z900
+CFLAGS_sclp_early_core.o	+= $(CC_FLAGS_MARCH_MINIMUM)
 endif
 
 CFLAGS_sclp_early_core.o += -I$(srctree)/drivers/s390/char
 
-obj-y	:= head.o als.o startup.o mem_detect.o ipl_parm.o string.o ebcdic.o
-obj-y	+= sclp_early_core.o mem.o ipl_vmparm.o cmdline.o ctype.o
-targets	:= bzImage startup.a section_cmp.boot.data $(obj-y)
+obj-y	:= head.o als.o startup.o mem_detect.o ipl_parm.o ipl_report.o
+obj-y	+= string.o ebcdic.o sclp_early_core.o mem.o ipl_vmparm.o cmdline.o
+obj-y	+= ctype.o text_dma.o
+obj-$(CONFIG_PROTECTED_VIRTUALIZATION_GUEST)	+= uv.o
+obj-$(CONFIG_RELOCATABLE)	+= machine_kexec_reloc.o
+obj-$(CONFIG_RANDOMIZE_BASE)	+= kaslr.o
+targets	:= bzImage startup.a section_cmp.boot.data section_cmp.boot.preserved.data $(obj-y)
 subdir-	:= compressed
 
 OBJECTS := $(addprefix $(obj)/,$(obj-y))
@@ -48,7 +58,8 @@ define cmd_section_cmp
 	touch $@
 endef
 
-$(obj)/bzImage: $(obj)/compressed/vmlinux $(obj)/section_cmp.boot.data FORCE
+OBJCOPYFLAGS_bzImage := --pad-to $$(readelf -s $(obj)/compressed/vmlinux | awk '/\<_end\>/ {print or(strtonum("0x"$$2),4095)+1}')
+$(obj)/bzImage: $(obj)/compressed/vmlinux $(obj)/section_cmp.boot.data $(obj)/section_cmp.boot.preserved.data FORCE
 	$(call if_changed,objcopy)
 
 $(obj)/section_cmp%: vmlinux $(obj)/compressed/vmlinux FORCE
diff --git a/arch/s390/boot/als.c b/arch/s390/boot/als.c
index f902215e9cd9..ff6801d401c4 100644
--- a/arch/s390/boot/als.c
+++ b/arch/s390/boot/als.c
@@ -99,7 +99,7 @@ static void facility_mismatch(void)
 	print_machine_type();
 	print_missing_facilities();
 	sclp_early_printk("See Principles of Operations for facility bits\n");
-	disabled_wait(0x8badcccc);
+	disabled_wait();
 }
 
 void verify_facilities(void)
diff --git a/arch/s390/boot/boot.h b/arch/s390/boot/boot.h
index 82bc06346e05..ad57c2205a71 100644
--- a/arch/s390/boot/boot.h
+++ b/arch/s390/boot/boot.h
@@ -9,5 +9,10 @@ void setup_boot_command_line(void);
 void parse_boot_command_line(void);
 void setup_memory_end(void);
 void print_missing_facilities(void);
+unsigned long get_random_base(unsigned long safe_addr);
+
+extern int kaslr_enabled;
+
+unsigned long read_ipl_report(unsigned long safe_offset);
 
 #endif /* BOOT_BOOT_H */
diff --git a/arch/s390/boot/compressed/decompressor.h b/arch/s390/boot/compressed/decompressor.h
index e1c1f2ec60f4..c15eb7114d83 100644
--- a/arch/s390/boot/compressed/decompressor.h
+++ b/arch/s390/boot/compressed/decompressor.h
@@ -17,6 +17,11 @@ struct vmlinux_info {
 	unsigned long bss_size;		/* uncompressed image .bss size */
 	unsigned long bootdata_off;
 	unsigned long bootdata_size;
+	unsigned long bootdata_preserved_off;
+	unsigned long bootdata_preserved_size;
+	unsigned long dynsym_start;
+	unsigned long rela_dyn_start;
+	unsigned long rela_dyn_end;
 };
 
 extern char _vmlinux_info[];
diff --git a/arch/s390/boot/compressed/vmlinux.lds.S b/arch/s390/boot/compressed/vmlinux.lds.S
index 7efc3938f595..112b8d9f1e4c 100644
--- a/arch/s390/boot/compressed/vmlinux.lds.S
+++ b/arch/s390/boot/compressed/vmlinux.lds.S
@@ -33,7 +33,29 @@ SECTIONS
 		*(.data.*)
 		_edata = . ;
 	}
+	/*
+	* .dma section for code, data, ex_table that need to stay below 2 GB,
+	* even when the kernel is relocate: above 2 GB.
+	*/
+	_sdma = .;
+	.dma.text : {
+		. = ALIGN(PAGE_SIZE);
+		_stext_dma = .;
+		*(.dma.text)
+		. = ALIGN(PAGE_SIZE);
+		_etext_dma = .;
+	}
+	. = ALIGN(16);
+	.dma.ex_table : {
+		_start_dma_ex_table = .;
+		KEEP(*(.dma.ex_table))
+		_stop_dma_ex_table = .;
+	}
+	.dma.data : { *(.dma.data) }
+	_edma = .;
+
 	BOOT_DATA
+	BOOT_DATA_PRESERVED
 
 	/*
 	 * uncompressed image info used by the decompressor it should match
diff --git a/arch/s390/boot/head.S b/arch/s390/boot/head.S
index ce2cbbc41742..028aab03a9e7 100644
--- a/arch/s390/boot/head.S
+++ b/arch/s390/boot/head.S
@@ -305,7 +305,7 @@ ENTRY(startup_kdump)
 	xc	0x300(256),0x300
 	xc	0xe00(256),0xe00
 	xc	0xf00(256),0xf00
-	lctlg	%c0,%c15,0x200(%r0)	# initialize control registers
+	lctlg	%c0,%c15,.Lctl-.LPG0(%r13)	# load control registers
 	stcke	__LC_BOOT_CLOCK
 	mvc	__LC_LAST_UPDATE_CLOCK(8),__LC_BOOT_CLOCK+1
 	spt	6f-.LPG0(%r13)
@@ -319,20 +319,54 @@ ENTRY(startup_kdump)
 	.align	8
 6:	.long	0x7fffffff,0xffffffff
 
+.Lctl:	.quad	0x04040000		# cr0: AFP registers & secondary space
+	.quad	0			# cr1: primary space segment table
+	.quad	.Lduct			# cr2: dispatchable unit control table
+	.quad	0			# cr3: instruction authorization
+	.quad	0xffff			# cr4: instruction authorization
+	.quad	.Lduct			# cr5: primary-aste origin
+	.quad	0			# cr6:	I/O interrupts
+	.quad	0			# cr7:	secondary space segment table
+	.quad	0			# cr8:	access registers translation
+	.quad	0			# cr9:	tracing off
+	.quad	0			# cr10: tracing off
+	.quad	0			# cr11: tracing off
+	.quad	0			# cr12: tracing off
+	.quad	0			# cr13: home space segment table
+	.quad	0xc0000000		# cr14: machine check handling off
+	.quad	.Llinkage_stack		# cr15: linkage stack operations
+
+	.section .dma.data,"aw",@progbits
+.Lduct: .long	0,.Laste,.Laste,0,.Lduald,0,0,0
+	.long	0,0,0,0,0,0,0,0
+.Llinkage_stack:
+	.long	0,0,0x89000000,0,0,0,0x8a000000,0
+	.align 64
+.Laste:	.quad	0,0xffffffffffffffff,0,0,0,0,0,0
+	.align	128
+.Lduald:.rept	8
+	.long	0x80000000,0,0,0	# invalid access-list entries
+	.endr
+	.previous
+
 #include "head_kdump.S"
 
 #
 # params at 10400 (setup.h)
+# Must be keept in sync with struct parmarea in setup.h
 #
 	.org	PARMAREA
-	.long	0,0			# IPL_DEVICE
-	.long	0,0			# INITRD_START
-	.long	0,0			# INITRD_SIZE
-	.long	0,0			# OLDMEM_BASE
-	.long	0,0			# OLDMEM_SIZE
+	.quad	0			# IPL_DEVICE
+	.quad	0			# INITRD_START
+	.quad	0			# INITRD_SIZE
+	.quad	0			# OLDMEM_BASE
+	.quad	0			# OLDMEM_SIZE
 
 	.org	COMMAND_LINE
 	.byte	"root=/dev/ram0 ro"
 	.byte	0
 
-	.org	0x11000
+	.org	EARLY_SCCB_OFFSET
+	.fill	4096
+
+	.org	HEAD_END
diff --git a/arch/s390/boot/ipl_parm.c b/arch/s390/boot/ipl_parm.c
index 36beb56de021..3c49bde8aa5e 100644
--- a/arch/s390/boot/ipl_parm.c
+++ b/arch/s390/boot/ipl_parm.c
@@ -7,16 +7,19 @@
 #include <asm/sections.h>
 #include <asm/boot_data.h>
 #include <asm/facility.h>
+#include <asm/uv.h>
 #include "boot.h"
 
 char __bootdata(early_command_line)[COMMAND_LINE_SIZE];
-struct ipl_parameter_block __bootdata(early_ipl_block);
-int __bootdata(early_ipl_block_valid);
+struct ipl_parameter_block __bootdata_preserved(ipl_block);
+int __bootdata_preserved(ipl_block_valid);
 
 unsigned long __bootdata(memory_end);
 int __bootdata(memory_end_set);
 int __bootdata(noexec_disabled);
 
+int kaslr_enabled __section(.data);
+
 static inline int __diag308(unsigned long subcode, void *addr)
 {
 	register unsigned long _addr asm("0") = (unsigned long)addr;
@@ -45,13 +48,15 @@ void store_ipl_parmblock(void)
 {
 	int rc;
 
-	rc = __diag308(DIAG308_STORE, &early_ipl_block);
+	uv_set_shared(__pa(&ipl_block));
+	rc = __diag308(DIAG308_STORE, &ipl_block);
+	uv_remove_shared(__pa(&ipl_block));
 	if (rc == DIAG308_RC_OK &&
-	    early_ipl_block.hdr.version <= IPL_MAX_SUPPORTED_VERSION)
-		early_ipl_block_valid = 1;
+	    ipl_block.hdr.version <= IPL_MAX_SUPPORTED_VERSION)
+		ipl_block_valid = 1;
 }
 
-static size_t scpdata_length(const char *buf, size_t count)
+static size_t scpdata_length(const u8 *buf, size_t count)
 {
 	while (count) {
 		if (buf[count - 1] != '\0' && buf[count - 1] != ' ')
@@ -68,26 +73,26 @@ static size_t ipl_block_get_ascii_scpdata(char *dest, size_t size,
 	size_t i;
 	int has_lowercase;
 
-	count = min(size - 1, scpdata_length(ipb->ipl_info.fcp.scp_data,
-					     ipb->ipl_info.fcp.scp_data_len));
+	count = min(size - 1, scpdata_length(ipb->fcp.scp_data,
+					     ipb->fcp.scp_data_len));
 	if (!count)
 		goto out;
 
 	has_lowercase = 0;
 	for (i = 0; i < count; i++) {
-		if (!isascii(ipb->ipl_info.fcp.scp_data[i])) {
+		if (!isascii(ipb->fcp.scp_data[i])) {
 			count = 0;
 			goto out;
 		}
-		if (!has_lowercase && islower(ipb->ipl_info.fcp.scp_data[i]))
+		if (!has_lowercase && islower(ipb->fcp.scp_data[i]))
 			has_lowercase = 1;
 	}
 
 	if (has_lowercase)
-		memcpy(dest, ipb->ipl_info.fcp.scp_data, count);
+		memcpy(dest, ipb->fcp.scp_data, count);
 	else
 		for (i = 0; i < count; i++)
-			dest[i] = tolower(ipb->ipl_info.fcp.scp_data[i]);
+			dest[i] = tolower(ipb->fcp.scp_data[i]);
 out:
 	dest[count] = '\0';
 	return count;
@@ -103,14 +108,14 @@ static void append_ipl_block_parm(void)
 	delim = early_command_line + len;    /* '\0' character position */
 	parm = early_command_line + len + 1; /* append right after '\0' */
 
-	switch (early_ipl_block.hdr.pbt) {
-	case DIAG308_IPL_TYPE_CCW:
+	switch (ipl_block.pb0_hdr.pbt) {
+	case IPL_PBT_CCW:
 		rc = ipl_block_get_ascii_vmparm(
-			parm, COMMAND_LINE_SIZE - len - 1, &early_ipl_block);
+			parm, COMMAND_LINE_SIZE - len - 1, &ipl_block);
 		break;
-	case DIAG308_IPL_TYPE_FCP:
+	case IPL_PBT_FCP:
 		rc = ipl_block_get_ascii_scpdata(
-			parm, COMMAND_LINE_SIZE - len - 1, &early_ipl_block);
+			parm, COMMAND_LINE_SIZE - len - 1, &ipl_block);
 		break;
 	}
 	if (rc) {
@@ -141,7 +146,7 @@ void setup_boot_command_line(void)
 	strcpy(early_command_line, strim(COMMAND_LINE));
 
 	/* append IPL PARM data to the boot command line */
-	if (early_ipl_block_valid)
+	if (!is_prot_virt_guest() && ipl_block_valid)
 		append_ipl_block_parm();
 }
 
@@ -211,6 +216,7 @@ void parse_boot_command_line(void)
 	char *args;
 	int rc;
 
+	kaslr_enabled = IS_ENABLED(CONFIG_RANDOMIZE_BASE);
 	args = strcpy(command_line_buf, early_command_line);
 	while (*args) {
 		args = next_arg(args, &param, &val);
@@ -228,15 +234,21 @@ void parse_boot_command_line(void)
 
 		if (!strcmp(param, "facilities"))
 			modify_fac_list(val);
+
+		if (!strcmp(param, "nokaslr"))
+			kaslr_enabled = 0;
 	}
 }
 
 void setup_memory_end(void)
 {
 #ifdef CONFIG_CRASH_DUMP
-	if (!OLDMEM_BASE && early_ipl_block_valid &&
-	    early_ipl_block.hdr.pbt == DIAG308_IPL_TYPE_FCP &&
-	    early_ipl_block.ipl_info.fcp.opt == DIAG308_IPL_OPT_DUMP) {
+	if (OLDMEM_BASE) {
+		kaslr_enabled = 0;
+	} else if (ipl_block_valid &&
+		   ipl_block.pb0_hdr.pbt == IPL_PBT_FCP &&
+		   ipl_block.fcp.opt == IPL_PB0_FCP_OPT_DUMP) {
+		kaslr_enabled = 0;
 		if (!sclp_early_get_hsa_size(&memory_end) && memory_end)
 			memory_end_set = 1;
 	}
diff --git a/arch/s390/boot/ipl_report.c b/arch/s390/boot/ipl_report.c
new file mode 100644
index 000000000000..0b4965573656
--- /dev/null
+++ b/arch/s390/boot/ipl_report.c
@@ -0,0 +1,165 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <linux/init.h>
+#include <linux/ctype.h>
+#include <asm/ebcdic.h>
+#include <asm/sclp.h>
+#include <asm/sections.h>
+#include <asm/boot_data.h>
+#include <uapi/asm/ipl.h>
+#include "boot.h"
+
+int __bootdata_preserved(ipl_secure_flag);
+
+unsigned long __bootdata_preserved(ipl_cert_list_addr);
+unsigned long __bootdata_preserved(ipl_cert_list_size);
+
+unsigned long __bootdata(early_ipl_comp_list_addr);
+unsigned long __bootdata(early_ipl_comp_list_size);
+
+#define for_each_rb_entry(entry, rb) \
+	for (entry = rb->entries; \
+	     (void *) entry + sizeof(*entry) <= (void *) rb + rb->len; \
+	     entry++)
+
+static inline bool intersects(unsigned long addr0, unsigned long size0,
+			      unsigned long addr1, unsigned long size1)
+{
+	return addr0 + size0 > addr1 && addr1 + size1 > addr0;
+}
+
+static unsigned long find_bootdata_space(struct ipl_rb_components *comps,
+					 struct ipl_rb_certificates *certs,
+					 unsigned long safe_addr)
+{
+	struct ipl_rb_certificate_entry *cert;
+	struct ipl_rb_component_entry *comp;
+	size_t size;
+
+	/*
+	 * Find the length for the IPL report boot data
+	 */
+	early_ipl_comp_list_size = 0;
+	for_each_rb_entry(comp, comps)
+		early_ipl_comp_list_size += sizeof(*comp);
+	ipl_cert_list_size = 0;
+	for_each_rb_entry(cert, certs)
+		ipl_cert_list_size += sizeof(unsigned int) + cert->len;
+	size = ipl_cert_list_size + early_ipl_comp_list_size;
+
+	/*
+	 * Start from safe_addr to find a free memory area large
+	 * enough for the IPL report boot data. This area is used
+	 * for ipl_cert_list_addr/ipl_cert_list_size and
+	 * early_ipl_comp_list_addr/early_ipl_comp_list_size. It must
+	 * not overlap with any component or any certificate.
+	 */
+repeat:
+	if (IS_ENABLED(CONFIG_BLK_DEV_INITRD) && INITRD_START && INITRD_SIZE &&
+	    intersects(INITRD_START, INITRD_SIZE, safe_addr, size))
+		safe_addr = INITRD_START + INITRD_SIZE;
+	for_each_rb_entry(comp, comps)
+		if (intersects(safe_addr, size, comp->addr, comp->len)) {
+			safe_addr = comp->addr + comp->len;
+			goto repeat;
+		}
+	for_each_rb_entry(cert, certs)
+		if (intersects(safe_addr, size, cert->addr, cert->len)) {
+			safe_addr = cert->addr + cert->len;
+			goto repeat;
+		}
+	early_ipl_comp_list_addr = safe_addr;
+	ipl_cert_list_addr = safe_addr + early_ipl_comp_list_size;
+
+	return safe_addr + size;
+}
+
+static void copy_components_bootdata(struct ipl_rb_components *comps)
+{
+	struct ipl_rb_component_entry *comp, *ptr;
+
+	ptr = (struct ipl_rb_component_entry *) early_ipl_comp_list_addr;
+	for_each_rb_entry(comp, comps)
+		memcpy(ptr++, comp, sizeof(*ptr));
+}
+
+static void copy_certificates_bootdata(struct ipl_rb_certificates *certs)
+{
+	struct ipl_rb_certificate_entry *cert;
+	void *ptr;
+
+	ptr = (void *) ipl_cert_list_addr;
+	for_each_rb_entry(cert, certs) {
+		*(unsigned int *) ptr = cert->len;
+		ptr += sizeof(unsigned int);
+		memcpy(ptr, (void *) cert->addr, cert->len);
+		ptr += cert->len;
+	}
+}
+
+unsigned long read_ipl_report(unsigned long safe_addr)
+{
+	struct ipl_rb_certificates *certs;
+	struct ipl_rb_components *comps;
+	struct ipl_pl_hdr *pl_hdr;
+	struct ipl_rl_hdr *rl_hdr;
+	struct ipl_rb_hdr *rb_hdr;
+	unsigned long tmp;
+	void *rl_end;
+
+	/*
+	 * Check if there is a IPL report by looking at the copy
+	 * of the IPL parameter information block.
+	 */
+	if (!ipl_block_valid ||
+	    !(ipl_block.hdr.flags & IPL_PL_FLAG_IPLSR))
+		return safe_addr;
+	ipl_secure_flag = !!(ipl_block.hdr.flags & IPL_PL_FLAG_SIPL);
+	/*
+	 * There is an IPL report, to find it load the pointer to the
+	 * IPL parameter information block from lowcore and skip past
+	 * the IPL parameter list, then align the address to a double
+	 * word boundary.
+	 */
+	tmp = (unsigned long) S390_lowcore.ipl_parmblock_ptr;
+	pl_hdr = (struct ipl_pl_hdr *) tmp;
+	tmp = (tmp + pl_hdr->len + 7) & -8UL;
+	rl_hdr = (struct ipl_rl_hdr *) tmp;
+	/* Walk through the IPL report blocks in the IPL Report list */
+	certs = NULL;
+	comps = NULL;
+	rl_end = (void *) rl_hdr + rl_hdr->len;
+	rb_hdr = (void *) rl_hdr + sizeof(*rl_hdr);
+	while ((void *) rb_hdr + sizeof(*rb_hdr) < rl_end &&
+	       (void *) rb_hdr + rb_hdr->len <= rl_end) {
+
+		switch (rb_hdr->rbt) {
+		case IPL_RBT_CERTIFICATES:
+			certs = (struct ipl_rb_certificates *) rb_hdr;
+			break;
+		case IPL_RBT_COMPONENTS:
+			comps = (struct ipl_rb_components *) rb_hdr;
+			break;
+		default:
+			break;
+		}
+
+		rb_hdr = (void *) rb_hdr + rb_hdr->len;
+	}
+
+	/*
+	 * With either the component list or the certificate list
+	 * missing the kernel will stay ignorant of secure IPL.
+	 */
+	if (!comps || !certs)
+		return safe_addr;
+
+	/*
+	 * Copy component and certificate list to a safe area
+	 * where the decompressed kernel can find them.
+	 */
+	safe_addr = find_bootdata_space(comps, certs, safe_addr);
+	copy_components_bootdata(comps);
+	copy_certificates_bootdata(certs);
+
+	return safe_addr;
+}
diff --git a/arch/s390/boot/kaslr.c b/arch/s390/boot/kaslr.c
new file mode 100644
index 000000000000..3bdd8132e56b
--- /dev/null
+++ b/arch/s390/boot/kaslr.c
@@ -0,0 +1,144 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright IBM Corp. 2019
+ */
+#include <asm/mem_detect.h>
+#include <asm/cpacf.h>
+#include <asm/timex.h>
+#include <asm/sclp.h>
+#include "compressed/decompressor.h"
+
+#define PRNG_MODE_TDES	 1
+#define PRNG_MODE_SHA512 2
+#define PRNG_MODE_TRNG	 3
+
+struct prno_parm {
+	u32 res;
+	u32 reseed_counter;
+	u64 stream_bytes;
+	u8  V[112];
+	u8  C[112];
+};
+
+struct prng_parm {
+	u8  parm_block[32];
+	u32 reseed_counter;
+	u64 byte_counter;
+};
+
+static int check_prng(void)
+{
+	if (!cpacf_query_func(CPACF_KMC, CPACF_KMC_PRNG)) {
+		sclp_early_printk("KASLR disabled: CPU has no PRNG\n");
+		return 0;
+	}
+	if (cpacf_query_func(CPACF_PRNO, CPACF_PRNO_TRNG))
+		return PRNG_MODE_TRNG;
+	if (cpacf_query_func(CPACF_PRNO, CPACF_PRNO_SHA512_DRNG_GEN))
+		return PRNG_MODE_SHA512;
+	else
+		return PRNG_MODE_TDES;
+}
+
+static unsigned long get_random(unsigned long limit)
+{
+	struct prng_parm prng = {
+		/* initial parameter block for tdes mode, copied from libica */
+		.parm_block = {
+			0x0F, 0x2B, 0x8E, 0x63, 0x8C, 0x8E, 0xD2, 0x52,
+			0x64, 0xB7, 0xA0, 0x7B, 0x75, 0x28, 0xB8, 0xF4,
+			0x75, 0x5F, 0xD2, 0xA6, 0x8D, 0x97, 0x11, 0xFF,
+			0x49, 0xD8, 0x23, 0xF3, 0x7E, 0x21, 0xEC, 0xA0
+		},
+	};
+	unsigned long seed, random;
+	struct prno_parm prno;
+	__u64 entropy[4];
+	int mode, i;
+
+	mode = check_prng();
+	seed = get_tod_clock_fast();
+	switch (mode) {
+	case PRNG_MODE_TRNG:
+		cpacf_trng(NULL, 0, (u8 *) &random, sizeof(random));
+		break;
+	case PRNG_MODE_SHA512:
+		cpacf_prno(CPACF_PRNO_SHA512_DRNG_SEED, &prno, NULL, 0,
+			   (u8 *) &seed, sizeof(seed));
+		cpacf_prno(CPACF_PRNO_SHA512_DRNG_GEN, &prno, (u8 *) &random,
+			   sizeof(random), NULL, 0);
+		break;
+	case PRNG_MODE_TDES:
+		/* add entropy */
+		*(unsigned long *) prng.parm_block ^= seed;
+		for (i = 0; i < 16; i++) {
+			cpacf_kmc(CPACF_KMC_PRNG, prng.parm_block,
+				  (char *) entropy, (char *) entropy,
+				  sizeof(entropy));
+			memcpy(prng.parm_block, entropy, sizeof(entropy));
+		}
+		random = seed;
+		cpacf_kmc(CPACF_KMC_PRNG, prng.parm_block, (u8 *) &random,
+			  (u8 *) &random, sizeof(random));
+		break;
+	default:
+		random = 0;
+	}
+	return random % limit;
+}
+
+unsigned long get_random_base(unsigned long safe_addr)
+{
+	unsigned long base, start, end, kernel_size;
+	unsigned long block_sum, offset;
+	int i;
+
+	if (IS_ENABLED(CONFIG_BLK_DEV_INITRD) && INITRD_START && INITRD_SIZE) {
+		if (safe_addr < INITRD_START + INITRD_SIZE)
+			safe_addr = INITRD_START + INITRD_SIZE;
+	}
+	safe_addr = ALIGN(safe_addr, THREAD_SIZE);
+
+	kernel_size = vmlinux.image_size + vmlinux.bss_size;
+	block_sum = 0;
+	for_each_mem_detect_block(i, &start, &end) {
+		if (memory_end_set) {
+			if (start >= memory_end)
+				break;
+			if (end > memory_end)
+				end = memory_end;
+		}
+		if (end - start < kernel_size)
+			continue;
+		block_sum += end - start - kernel_size;
+	}
+	if (!block_sum) {
+		sclp_early_printk("KASLR disabled: not enough memory\n");
+		return 0;
+	}
+
+	base = get_random(block_sum);
+	if (base == 0)
+		return 0;
+	if (base < safe_addr)
+		base = safe_addr;
+	block_sum = offset = 0;
+	for_each_mem_detect_block(i, &start, &end) {
+		if (memory_end_set) {
+			if (start >= memory_end)
+				break;
+			if (end > memory_end)
+				end = memory_end;
+		}
+		if (end - start < kernel_size)
+			continue;
+		block_sum += end - start - kernel_size;
+		if (base <= block_sum) {
+			base = start + base - offset;
+			base = ALIGN_DOWN(base, THREAD_SIZE);
+			break;
+		}
+		offset = block_sum;
+	}
+	return base;
+}
diff --git a/arch/s390/boot/machine_kexec_reloc.c b/arch/s390/boot/machine_kexec_reloc.c
new file mode 100644
index 000000000000..b7a5d0f72097
--- /dev/null
+++ b/arch/s390/boot/machine_kexec_reloc.c
@@ -0,0 +1,2 @@
+// SPDX-License-Identifier: GPL-2.0
+#include "../kernel/machine_kexec_reloc.c"
diff --git a/arch/s390/boot/mem_detect.c b/arch/s390/boot/mem_detect.c
index 4cb771ba13fa..5d316fe40480 100644
--- a/arch/s390/boot/mem_detect.c
+++ b/arch/s390/boot/mem_detect.c
@@ -25,7 +25,7 @@ static void *mem_detect_alloc_extended(void)
 {
 	unsigned long offset = ALIGN(mem_safe_offset(), sizeof(u64));
 
-	if (IS_ENABLED(BLK_DEV_INITRD) && INITRD_START && INITRD_SIZE &&
+	if (IS_ENABLED(CONFIG_BLK_DEV_INITRD) && INITRD_START && INITRD_SIZE &&
 	    INITRD_START < offset + ENTRIES_EXTENDED_MAX)
 		offset = ALIGN(INITRD_START + INITRD_SIZE, sizeof(u64));
 
diff --git a/arch/s390/boot/startup.c b/arch/s390/boot/startup.c
index bdfc5549a299..7b0d05414618 100644
--- a/arch/s390/boot/startup.c
+++ b/arch/s390/boot/startup.c
@@ -1,11 +1,55 @@
 // SPDX-License-Identifier: GPL-2.0
 #include <linux/string.h>
+#include <linux/elf.h>
+#include <asm/sections.h>
 #include <asm/setup.h>
+#include <asm/kexec.h>
 #include <asm/sclp.h>
+#include <asm/diag.h>
+#include <asm/uv.h>
 #include "compressed/decompressor.h"
 #include "boot.h"
 
 extern char __boot_data_start[], __boot_data_end[];
+extern char __boot_data_preserved_start[], __boot_data_preserved_end[];
+unsigned long __bootdata_preserved(__kaslr_offset);
+
+/*
+ * Some code and data needs to stay below 2 GB, even when the kernel would be
+ * relocated above 2 GB, because it has to use 31 bit addresses.
+ * Such code and data is part of the .dma section, and its location is passed
+ * over to the decompressed / relocated kernel via the .boot.preserved.data
+ * section.
+ */
+extern char _sdma[], _edma[];
+extern char _stext_dma[], _etext_dma[];
+extern struct exception_table_entry _start_dma_ex_table[];
+extern struct exception_table_entry _stop_dma_ex_table[];
+unsigned long __bootdata_preserved(__sdma) = __pa(&_sdma);
+unsigned long __bootdata_preserved(__edma) = __pa(&_edma);
+unsigned long __bootdata_preserved(__stext_dma) = __pa(&_stext_dma);
+unsigned long __bootdata_preserved(__etext_dma) = __pa(&_etext_dma);
+struct exception_table_entry *
+	__bootdata_preserved(__start_dma_ex_table) = _start_dma_ex_table;
+struct exception_table_entry *
+	__bootdata_preserved(__stop_dma_ex_table) = _stop_dma_ex_table;
+
+int _diag210_dma(struct diag210 *addr);
+int _diag26c_dma(void *req, void *resp, enum diag26c_sc subcode);
+int _diag14_dma(unsigned long rx, unsigned long ry1, unsigned long subcode);
+void _diag0c_dma(struct hypfs_diag0c_entry *entry);
+void _diag308_reset_dma(void);
+struct diag_ops __bootdata_preserved(diag_dma_ops) = {
+	.diag210 = _diag210_dma,
+	.diag26c = _diag26c_dma,
+	.diag14 = _diag14_dma,
+	.diag0c = _diag0c_dma,
+	.diag308_reset = _diag308_reset_dma
+};
+static struct diag210 _diag210_tmp_dma __section(".dma.data");
+struct diag210 *__bootdata_preserved(__diag210_tmp_dma) = &_diag210_tmp_dma;
+void _swsusp_reset_dma(void);
+unsigned long __bootdata_preserved(__swsusp_reset_dma) = __pa(_swsusp_reset_dma);
 
 void error(char *x)
 {
@@ -13,7 +57,7 @@ void error(char *x)
 	sclp_early_printk(x);
 	sclp_early_printk("\n\n -- System halted");
 
-	disabled_wait(0xdeadbeef);
+	disabled_wait();
 }
 
 #ifdef CONFIG_KERNEL_UNCOMPRESSED
@@ -23,19 +67,16 @@ unsigned long mem_safe_offset(void)
 }
 #endif
 
-static void rescue_initrd(void)
+static void rescue_initrd(unsigned long addr)
 {
-	unsigned long min_initrd_addr;
-
 	if (!IS_ENABLED(CONFIG_BLK_DEV_INITRD))
 		return;
 	if (!INITRD_START || !INITRD_SIZE)
 		return;
-	min_initrd_addr = mem_safe_offset();
-	if (min_initrd_addr <= INITRD_START)
+	if (addr <= INITRD_START)
 		return;
-	memmove((void *)min_initrd_addr, (void *)INITRD_START, INITRD_SIZE);
-	INITRD_START = min_initrd_addr;
+	memmove((void *)addr, (void *)INITRD_START, INITRD_SIZE);
+	INITRD_START = addr;
 }
 
 static void copy_bootdata(void)
@@ -43,23 +84,81 @@ static void copy_bootdata(void)
 	if (__boot_data_end - __boot_data_start != vmlinux.bootdata_size)
 		error(".boot.data section size mismatch");
 	memcpy((void *)vmlinux.bootdata_off, __boot_data_start, vmlinux.bootdata_size);
+	if (__boot_data_preserved_end - __boot_data_preserved_start != vmlinux.bootdata_preserved_size)
+		error(".boot.preserved.data section size mismatch");
+	memcpy((void *)vmlinux.bootdata_preserved_off, __boot_data_preserved_start, vmlinux.bootdata_preserved_size);
+}
+
+static void handle_relocs(unsigned long offset)
+{
+	Elf64_Rela *rela_start, *rela_end, *rela;
+	int r_type, r_sym, rc;
+	Elf64_Addr loc, val;
+	Elf64_Sym *dynsym;
+
+	rela_start = (Elf64_Rela *) vmlinux.rela_dyn_start;
+	rela_end = (Elf64_Rela *) vmlinux.rela_dyn_end;
+	dynsym = (Elf64_Sym *) vmlinux.dynsym_start;
+	for (rela = rela_start; rela < rela_end; rela++) {
+		loc = rela->r_offset + offset;
+		val = rela->r_addend + offset;
+		r_sym = ELF64_R_SYM(rela->r_info);
+		if (r_sym)
+			val += dynsym[r_sym].st_value;
+		r_type = ELF64_R_TYPE(rela->r_info);
+		rc = arch_kexec_do_relocs(r_type, (void *) loc, val, 0);
+		if (rc)
+			error("Unknown relocation type");
+	}
 }
 
 void startup_kernel(void)
 {
+	unsigned long random_lma;
+	unsigned long safe_addr;
 	void *img;
 
-	rescue_initrd();
-	sclp_early_read_info();
 	store_ipl_parmblock();
+	safe_addr = mem_safe_offset();
+	safe_addr = read_ipl_report(safe_addr);
+	uv_query_info();
+	rescue_initrd(safe_addr);
+	sclp_early_read_info();
 	setup_boot_command_line();
 	parse_boot_command_line();
 	setup_memory_end();
 	detect_memory();
+
+	random_lma = __kaslr_offset = 0;
+	if (IS_ENABLED(CONFIG_RANDOMIZE_BASE) && kaslr_enabled) {
+		random_lma = get_random_base(safe_addr);
+		if (random_lma) {
+			__kaslr_offset = random_lma - vmlinux.default_lma;
+			img = (void *)vmlinux.default_lma;
+			vmlinux.default_lma += __kaslr_offset;
+			vmlinux.entry += __kaslr_offset;
+			vmlinux.bootdata_off += __kaslr_offset;
+			vmlinux.bootdata_preserved_off += __kaslr_offset;
+			vmlinux.rela_dyn_start += __kaslr_offset;
+			vmlinux.rela_dyn_end += __kaslr_offset;
+			vmlinux.dynsym_start += __kaslr_offset;
+		}
+	}
+
 	if (!IS_ENABLED(CONFIG_KERNEL_UNCOMPRESSED)) {
 		img = decompress_kernel();
 		memmove((void *)vmlinux.default_lma, img, vmlinux.image_size);
-	}
+	} else if (__kaslr_offset)
+		memcpy((void *)vmlinux.default_lma, img, vmlinux.image_size);
+
 	copy_bootdata();
+	if (IS_ENABLED(CONFIG_RELOCATABLE))
+		handle_relocs(__kaslr_offset);
+
+	if (__kaslr_offset) {
+		/* Clear non-relocated kernel */
+		if (IS_ENABLED(CONFIG_KERNEL_UNCOMPRESSED))
+			memset(img, 0, vmlinux.image_size);
+	}
 	vmlinux.entry();
 }
diff --git a/arch/s390/boot/text_dma.S b/arch/s390/boot/text_dma.S
new file mode 100644
index 000000000000..9715715c4c28
--- /dev/null
+++ b/arch/s390/boot/text_dma.S
@@ -0,0 +1,184 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Code that needs to run below 2 GB.
+ *
+ * Copyright IBM Corp. 2019
+ */
+
+#include <linux/linkage.h>
+#include <asm/errno.h>
+#include <asm/sigp.h>
+
+#ifdef CC_USING_EXPOLINE
+	.pushsection .dma.text.__s390_indirect_jump_r14,"axG"
+__dma__s390_indirect_jump_r14:
+	larl	%r1,0f
+	ex	0,0(%r1)
+	j	.
+0:	br	%r14
+	.popsection
+#endif
+
+	.section .dma.text,"ax"
+/*
+ * Simplified version of expoline thunk. The normal thunks can not be used here,
+ * because they might be more than 2 GB away, and not reachable by the relative
+ * branch. No comdat, exrl, etc. optimizations used here, because it only
+ * affects a few functions that are not performance-relevant.
+ */
+	.macro BR_EX_DMA_r14
+#ifdef CC_USING_EXPOLINE
+	jg	__dma__s390_indirect_jump_r14
+#else
+	br	%r14
+#endif
+	.endm
+
+/*
+ * int _diag14_dma(unsigned long rx, unsigned long ry1, unsigned long subcode)
+ */
+ENTRY(_diag14_dma)
+	lgr	%r1,%r2
+	lgr	%r2,%r3
+	lgr	%r3,%r4
+	lhi	%r5,-EIO
+	sam31
+	diag	%r1,%r2,0x14
+.Ldiag14_ex:
+	ipm	%r5
+	srl	%r5,28
+.Ldiag14_fault:
+	sam64
+	lgfr	%r2,%r5
+	BR_EX_DMA_r14
+	EX_TABLE_DMA(.Ldiag14_ex, .Ldiag14_fault)
+ENDPROC(_diag14_dma)
+
+/*
+ * int _diag210_dma(struct diag210 *addr)
+ */
+ENTRY(_diag210_dma)
+	lgr	%r1,%r2
+	lhi	%r2,-1
+	sam31
+	diag	%r1,%r0,0x210
+.Ldiag210_ex:
+	ipm	%r2
+	srl	%r2,28
+.Ldiag210_fault:
+	sam64
+	lgfr	%r2,%r2
+	BR_EX_DMA_r14
+	EX_TABLE_DMA(.Ldiag210_ex, .Ldiag210_fault)
+ENDPROC(_diag210_dma)
+
+/*
+ * int _diag26c_dma(void *req, void *resp, enum diag26c_sc subcode)
+ */
+ENTRY(_diag26c_dma)
+	lghi	%r5,-EOPNOTSUPP
+	sam31
+	diag	%r2,%r4,0x26c
+.Ldiag26c_ex:
+	sam64
+	lgfr	%r2,%r5
+	BR_EX_DMA_r14
+	EX_TABLE_DMA(.Ldiag26c_ex, .Ldiag26c_ex)
+ENDPROC(_diag26c_dma)
+
+/*
+ * void _diag0c_dma(struct hypfs_diag0c_entry *entry)
+ */
+ENTRY(_diag0c_dma)
+	sam31
+	diag	%r2,%r2,0x0c
+	sam64
+	BR_EX_DMA_r14
+ENDPROC(_diag0c_dma)
+
+/*
+ * void _swsusp_reset_dma(void)
+ */
+ENTRY(_swsusp_reset_dma)
+	larl	%r1,restart_entry
+	larl	%r2,.Lrestart_diag308_psw
+	og	%r1,0(%r2)
+	stg	%r1,0(%r0)
+	lghi	%r0,0
+	diag	%r0,%r0,0x308
+restart_entry:
+	lhi	%r1,1
+	sigp	%r1,%r0,SIGP_SET_ARCHITECTURE
+	sam64
+	BR_EX_DMA_r14
+ENDPROC(_swsusp_reset_dma)
+
+/*
+ * void _diag308_reset_dma(void)
+ *
+ * Calls diag 308 subcode 1 and continues execution
+ */
+ENTRY(_diag308_reset_dma)
+	larl	%r4,.Lctlregs		# Save control registers
+	stctg	%c0,%c15,0(%r4)
+	lg	%r2,0(%r4)		# Disable lowcore protection
+	nilh	%r2,0xefff
+	larl	%r4,.Lctlreg0
+	stg	%r2,0(%r4)
+	lctlg	%c0,%c0,0(%r4)
+	larl	%r4,.Lfpctl		# Floating point control register
+	stfpc	0(%r4)
+	larl	%r4,.Lprefix		# Save prefix register
+	stpx	0(%r4)
+	larl	%r4,.Lprefix_zero	# Set prefix register to 0
+	spx	0(%r4)
+	larl	%r4,.Lcontinue_psw	# Save PSW flags
+	epsw	%r2,%r3
+	stm	%r2,%r3,0(%r4)
+	larl	%r4,restart_part2	# Setup restart PSW at absolute 0
+	larl	%r3,.Lrestart_diag308_psw
+	og	%r4,0(%r3)		# Save PSW
+	lghi	%r3,0
+	sturg	%r4,%r3			# Use sturg, because of large pages
+	lghi	%r1,1
+	lghi	%r0,0
+	diag	%r0,%r1,0x308
+restart_part2:
+	lhi	%r0,0			# Load r0 with zero
+	lhi	%r1,2			# Use mode 2 = ESAME (dump)
+	sigp	%r1,%r0,SIGP_SET_ARCHITECTURE	# Switch to ESAME mode
+	sam64				# Switch to 64 bit addressing mode
+	larl	%r4,.Lctlregs		# Restore control registers
+	lctlg	%c0,%c15,0(%r4)
+	larl	%r4,.Lfpctl		# Restore floating point ctl register
+	lfpc	0(%r4)
+	larl	%r4,.Lprefix		# Restore prefix register
+	spx	0(%r4)
+	larl	%r4,.Lcontinue_psw	# Restore PSW flags
+	lpswe	0(%r4)
+.Lcontinue:
+	BR_EX_DMA_r14
+ENDPROC(_diag308_reset_dma)
+
+	.section .dma.data,"aw",@progbits
+.align	8
+.Lrestart_diag308_psw:
+	.long	0x00080000,0x80000000
+
+.align 8
+.Lcontinue_psw:
+	.quad	0,.Lcontinue
+
+.align 8
+.Lctlreg0:
+	.quad	0
+.Lctlregs:
+	.rept	16
+	.quad	0
+	.endr
+.Lfpctl:
+	.long	0
+.Lprefix:
+	.long	0
+.Lprefix_zero:
+	.long	0
diff --git a/arch/s390/boot/uv.c b/arch/s390/boot/uv.c
new file mode 100644
index 000000000000..ed007f4a6444
--- /dev/null
+++ b/arch/s390/boot/uv.c
@@ -0,0 +1,24 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <asm/uv.h>
+#include <asm/facility.h>
+#include <asm/sections.h>
+
+int __bootdata_preserved(prot_virt_guest);
+
+void uv_query_info(void)
+{
+	struct uv_cb_qui uvcb = {
+		.header.cmd = UVC_CMD_QUI,
+		.header.len = sizeof(uvcb)
+	};
+
+	if (!test_facility(158))
+		return;
+
+	if (uv_call(0, (uint64_t)&uvcb))
+		return;
+
+	if (test_bit_inv(BIT_UVC_CMD_SET_SHARED_ACCESS, (unsigned long *)uvcb.inst_calls_list) &&
+	    test_bit_inv(BIT_UVC_CMD_REMOVE_SHARED_ACCESS, (unsigned long *)uvcb.inst_calls_list))
+		prot_virt_guest = 1;
+}
diff --git a/arch/s390/configs/debug_defconfig b/arch/s390/configs/debug_defconfig
index 9824c7bad9d4..b0920b35f87b 100644
--- a/arch/s390/configs/debug_defconfig
+++ b/arch/s390/configs/debug_defconfig
@@ -64,6 +64,7 @@ CONFIG_NUMA=y
 CONFIG_PREEMPT=y
 CONFIG_HZ_100=y
 CONFIG_KEXEC_FILE=y
+CONFIG_KEXEC_VERIFY_SIG=y
 CONFIG_EXPOLINE=y
 CONFIG_EXPOLINE_AUTO=y
 CONFIG_MEMORY_HOTPLUG=y
diff --git a/arch/s390/configs/performance_defconfig b/arch/s390/configs/performance_defconfig
index 4fcbe5792744..09aa5cb14873 100644
--- a/arch/s390/configs/performance_defconfig
+++ b/arch/s390/configs/performance_defconfig
@@ -65,6 +65,7 @@ CONFIG_NR_CPUS=512
 CONFIG_NUMA=y
 CONFIG_HZ_100=y
 CONFIG_KEXEC_FILE=y
+CONFIG_KEXEC_VERIFY_SIG=y
 CONFIG_EXPOLINE=y
 CONFIG_EXPOLINE_AUTO=y
 CONFIG_MEMORY_HOTPLUG=y
diff --git a/arch/s390/crypto/crc32be-vx.S b/arch/s390/crypto/crc32be-vx.S
index 2bf01ba44107..0099044e2c86 100644
--- a/arch/s390/crypto/crc32be-vx.S
+++ b/arch/s390/crypto/crc32be-vx.S
@@ -207,5 +207,6 @@ ENTRY(crc32_be_vgfm_16)
 .Ldone:
 	VLGVF	%r2,%v2,3
 	BR_EX	%r14
+ENDPROC(crc32_be_vgfm_16)
 
 .previous
diff --git a/arch/s390/crypto/crc32le-vx.S b/arch/s390/crypto/crc32le-vx.S
index 7d6f568bd3ad..71caf0f4ec08 100644
--- a/arch/s390/crypto/crc32le-vx.S
+++ b/arch/s390/crypto/crc32le-vx.S
@@ -105,13 +105,14 @@
 ENTRY(crc32_le_vgfm_16)
 	larl	%r5,.Lconstants_CRC_32_LE
 	j	crc32_le_vgfm_generic
+ENDPROC(crc32_le_vgfm_16)
 
 ENTRY(crc32c_le_vgfm_16)
 	larl	%r5,.Lconstants_CRC_32C_LE
 	j	crc32_le_vgfm_generic
+ENDPROC(crc32c_le_vgfm_16)
 
-
-crc32_le_vgfm_generic:
+ENTRY(crc32_le_vgfm_generic)
 	/* Load CRC-32 constants */
 	VLM	CONST_PERM_LE2BE,CONST_CRC_POLY,0,%r5
 
@@ -267,5 +268,6 @@ crc32_le_vgfm_generic:
 .Ldone:
 	VLGVF	%r2,%v2,2
 	BR_EX	%r14
+ENDPROC(crc32_le_vgfm_generic)
 
 .previous
diff --git a/arch/s390/crypto/des_s390.c b/arch/s390/crypto/des_s390.c
index 0d15383d0ff1..1f9ab24dc048 100644
--- a/arch/s390/crypto/des_s390.c
+++ b/arch/s390/crypto/des_s390.c
@@ -224,24 +224,11 @@ static int des3_setkey(struct crypto_tfm *tfm, const u8 *key,
 		       unsigned int key_len)
 {
 	struct s390_des_ctx *ctx = crypto_tfm_ctx(tfm);
+	int err;
 
-	if (!(crypto_memneq(key, &key[DES_KEY_SIZE], DES_KEY_SIZE) &&
-	    crypto_memneq(&key[DES_KEY_SIZE], &key[DES_KEY_SIZE * 2],
-			  DES_KEY_SIZE)) &&
-	    (tfm->crt_flags & CRYPTO_TFM_REQ_FORBID_WEAK_KEYS)) {
-		tfm->crt_flags |= CRYPTO_TFM_RES_WEAK_KEY;
-		return -EINVAL;
-	}
-
-	/* in fips mode, ensure k1 != k2 and k2 != k3 and k1 != k3 */
-	if (fips_enabled &&
-	    !(crypto_memneq(key, &key[DES_KEY_SIZE], DES_KEY_SIZE) &&
-	      crypto_memneq(&key[DES_KEY_SIZE], &key[DES_KEY_SIZE * 2],
-			    DES_KEY_SIZE) &&
-	      crypto_memneq(key, &key[DES_KEY_SIZE * 2], DES_KEY_SIZE))) {
-		tfm->crt_flags |= CRYPTO_TFM_RES_WEAK_KEY;
-		return -EINVAL;
-	}
+	err = __des3_verify_key(&tfm->crt_flags, key);
+	if (unlikely(err))
+		return err;
 
 	memcpy(ctx->key, key, key_len);
 	return 0;
diff --git a/arch/s390/crypto/prng.c b/arch/s390/crypto/prng.c
index a97a1802cfb4..12cca467af7d 100644
--- a/arch/s390/crypto/prng.c
+++ b/arch/s390/crypto/prng.c
@@ -61,6 +61,7 @@ static unsigned int prng_reseed_limit;
 module_param_named(reseed_limit, prng_reseed_limit, int, 0);
 MODULE_PARM_DESC(prng_reseed_limit, "PRNG reseed limit");
 
+static bool trng_available;
 
 /*
  * Any one who considers arithmetical methods of producing random digits is,
@@ -115,46 +116,68 @@ static const u8 initial_parm_block[32] __initconst = {
 
 /*
  * generate_entropy:
- * This algorithm produces 64 bytes of entropy data based on 1024
- * individual stckf() invocations assuming that each stckf() value
- * contributes 0.25 bits of entropy. So the caller gets 256 bit
- * entropy per 64 byte or 4 bits entropy per byte.
+ * This function fills a given buffer with random bytes. The entropy within
+ * the random bytes given back is assumed to have at least 50% - meaning
+ * a 64 bytes buffer has at least 64 * 8 / 2 = 256 bits of entropy.
+ * Within the function the entropy generation is done in junks of 64 bytes.
+ * So the caller should also ask for buffer fill in multiples of 64 bytes.
+ * The generation of the entropy is based on the assumption that every stckf()
+ * invocation produces 0.5 bits of entropy. To accumulate 256 bits of entropy
+ * at least 512 stckf() values are needed. The entropy relevant part of the
+ * stckf value is bit 51 (counting starts at the left with bit nr 0) so
+ * here we use the lower 4 bytes and exor the values into 2k of bufferspace.
+ * To be on the save side, if there is ever a problem with stckf() the
+ * other half of the page buffer is filled with bytes from urandom via
+ * get_random_bytes(), so this function consumes 2k of urandom for each
+ * requested 64 bytes output data. Finally the buffer page is condensed into
+ * a 64 byte value by hashing with a SHA512 hash.
  */
 static int generate_entropy(u8 *ebuf, size_t nbytes)
 {
 	int n, ret = 0;
-	u8 *pg, *h, hash[64];
-
-	/* allocate 2 pages */
-	pg = (u8 *) __get_free_pages(GFP_KERNEL, 1);
+	u8 *pg, pblock[80] = {
+		/* 8 x 64 bit init values */
+		0x6A, 0x09, 0xE6, 0x67, 0xF3, 0xBC, 0xC9, 0x08,
+		0xBB, 0x67, 0xAE, 0x85, 0x84, 0xCA, 0xA7, 0x3B,
+		0x3C, 0x6E, 0xF3, 0x72, 0xFE, 0x94, 0xF8, 0x2B,
+		0xA5, 0x4F, 0xF5, 0x3A, 0x5F, 0x1D, 0x36, 0xF1,
+		0x51, 0x0E, 0x52, 0x7F, 0xAD, 0xE6, 0x82, 0xD1,
+		0x9B, 0x05, 0x68, 0x8C, 0x2B, 0x3E, 0x6C, 0x1F,
+		0x1F, 0x83, 0xD9, 0xAB, 0xFB, 0x41, 0xBD, 0x6B,
+		0x5B, 0xE0, 0xCD, 0x19, 0x13, 0x7E, 0x21, 0x79,
+		/* 128 bit counter total message bit length */
+		0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+		0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x80, 0x00 };
+
+	/* allocate one page stckf buffer */
+	pg = (u8 *) __get_free_page(GFP_KERNEL);
 	if (!pg) {
 		prng_errorflag = PRNG_GEN_ENTROPY_FAILED;
 		return -ENOMEM;
 	}
 
+	/* fill the ebuf in chunks of 64 byte each */
 	while (nbytes) {
-		/* fill pages with urandom bytes */
-		get_random_bytes(pg, 2*PAGE_SIZE);
-		/* exor pages with 1024 stckf values */
-		for (n = 0; n < 2 * PAGE_SIZE / sizeof(u64); n++) {
-			u64 *p = ((u64 *)pg) + n;
+		/* fill lower 2k with urandom bytes */
+		get_random_bytes(pg, PAGE_SIZE / 2);
+		/* exor upper 2k with 512 stckf values, offset 4 bytes each */
+		for (n = 0; n < 512; n++) {
+			int offset = (PAGE_SIZE / 2) + (n * 4) - 4;
+			u64 *p = (u64 *)(pg + offset);
 			*p ^= get_tod_clock_fast();
 		}
-		n = (nbytes < sizeof(hash)) ? nbytes : sizeof(hash);
-		if (n < sizeof(hash))
-			h = hash;
-		else
-			h = ebuf;
-		/* hash over the filled pages */
-		cpacf_kimd(CPACF_KIMD_SHA_512, h, pg, 2*PAGE_SIZE);
-		if (n < sizeof(hash))
-			memcpy(ebuf, hash, n);
+		/* hash over the filled page */
+		cpacf_klmd(CPACF_KLMD_SHA_512, pblock, pg, PAGE_SIZE);
+		n = (nbytes < 64) ? nbytes : 64;
+		memcpy(ebuf, pblock, n);
 		ret += n;
 		ebuf += n;
 		nbytes -= n;
 	}
 
-	free_pages((unsigned long)pg, 1);
+	memzero_explicit(pblock, sizeof(pblock));
+	memzero_explicit(pg, PAGE_SIZE);
+	free_page((unsigned long)pg);
 	return ret;
 }
 
@@ -344,8 +367,8 @@ static int __init prng_sha512_selftest(void)
 
 static int __init prng_sha512_instantiate(void)
 {
-	int ret, datalen;
-	u8 seed[64 + 32 + 16];
+	int ret, datalen, seedlen;
+	u8 seed[128 + 16];
 
 	pr_debug("prng runs in SHA-512 mode "
 		 "with chunksize=%d and reseed_limit=%u\n",
@@ -368,16 +391,36 @@ static int __init prng_sha512_instantiate(void)
 	if (ret)
 		goto outfree;
 
-	/* generate initial seed bytestring, with 256 + 128 bits entropy */
-	ret = generate_entropy(seed, 64 + 32);
-	if (ret != 64 + 32)
-		goto outfree;
-	/* followed by 16 bytes of unique nonce */
-	get_tod_clock_ext(seed + 64 + 32);
+	/* generate initial seed, we need at least  256 + 128 bits entropy. */
+	if (trng_available) {
+		/*
+		 * Trng available, so use it. The trng works in chunks of
+		 * 32 bytes and produces 100% entropy. So we pull 64 bytes
+		 * which gives us 512 bits entropy.
+		 */
+		seedlen = 2 * 32;
+		cpacf_trng(NULL, 0, seed, seedlen);
+	} else {
+		/*
+		 * No trng available, so use the generate_entropy() function.
+		 * This function works in 64 byte junks and produces
+		 * 50% entropy. So we pull 2*64 bytes which gives us 512 bits
+		 * of entropy.
+		 */
+		seedlen = 2 * 64;
+		ret = generate_entropy(seed, seedlen);
+		if (ret != seedlen)
+			goto outfree;
+	}
+
+	/* append the seed by 16 bytes of unique nonce */
+	get_tod_clock_ext(seed + seedlen);
+	seedlen += 16;
 
-	/* initial seed of the prno drng */
+	/* now initial seed of the prno drng */
 	cpacf_prno(CPACF_PRNO_SHA512_DRNG_SEED,
-		   &prng_data->prnows, NULL, 0, seed, sizeof(seed));
+		   &prng_data->prnows, NULL, 0, seed, seedlen);
+	memzero_explicit(seed, sizeof(seed));
 
 	/* if fips mode is enabled, generate a first block of random
 	   bytes for the FIPS 140-2 Conditional Self Test */
@@ -405,17 +448,26 @@ static void prng_sha512_deinstantiate(void)
 
 static int prng_sha512_reseed(void)
 {
-	int ret;
+	int ret, seedlen;
 	u8 seed[64];
 
-	/* fetch 256 bits of fresh entropy */
-	ret = generate_entropy(seed, sizeof(seed));
-	if (ret != sizeof(seed))
-		return ret;
+	/* We need at least 256 bits of fresh entropy for reseeding */
+	if (trng_available) {
+		/* trng produces 256 bits entropy in 32 bytes */
+		seedlen = 32;
+		cpacf_trng(NULL, 0, seed, seedlen);
+	} else {
+		/* generate_entropy() produces 256 bits entropy in 64 bytes */
+		seedlen = 64;
+		ret = generate_entropy(seed, seedlen);
+		if (ret != sizeof(seed))
+			return ret;
+	}
 
 	/* do a reseed of the prno drng with this bytestring */
 	cpacf_prno(CPACF_PRNO_SHA512_DRNG_SEED,
-		   &prng_data->prnows, NULL, 0, seed, sizeof(seed));
+		   &prng_data->prnows, NULL, 0, seed, seedlen);
+	memzero_explicit(seed, sizeof(seed));
 
 	return 0;
 }
@@ -592,6 +644,7 @@ static ssize_t prng_sha512_read(struct file *file, char __user *ubuf,
 			ret = -EFAULT;
 			break;
 		}
+		memzero_explicit(p, n);
 		ubuf += n;
 		nbytes -= n;
 		ret += n;
@@ -773,6 +826,10 @@ static int __init prng_init(void)
 	if (!cpacf_query_func(CPACF_KMC, CPACF_KMC_PRNG))
 		return -EOPNOTSUPP;
 
+	/* check if TRNG subfunction is available */
+	if (cpacf_query_func(CPACF_PRNO, CPACF_PRNO_TRNG))
+		trng_available = true;
+
 	/* choose prng mode */
 	if (prng_mode != PRNG_MODE_TDES) {
 		/* check for MSA5 support for PRNO operations */
diff --git a/arch/s390/defconfig b/arch/s390/defconfig
index 4d58a92b5d97..c59b922cb6c5 100644
--- a/arch/s390/defconfig
+++ b/arch/s390/defconfig
@@ -39,6 +39,7 @@ CONFIG_NR_CPUS=256
 CONFIG_NUMA=y
 CONFIG_HZ_100=y
 CONFIG_KEXEC_FILE=y
+CONFIG_KEXEC_VERIFY_SIG=y
 CONFIG_CRASH_DUMP=y
 CONFIG_HIBERNATION=y
 CONFIG_PM_DEBUG=y
diff --git a/arch/s390/hypfs/hypfs_diag0c.c b/arch/s390/hypfs/hypfs_diag0c.c
index 72e3140fafb5..3235e4d82f2d 100644
--- a/arch/s390/hypfs/hypfs_diag0c.c
+++ b/arch/s390/hypfs/hypfs_diag0c.c
@@ -16,26 +16,12 @@
 #define DBFS_D0C_HDR_VERSION 0
 
 /*
- * Execute diagnose 0c in 31 bit mode
- */
-static void diag0c(struct hypfs_diag0c_entry *entry)
-{
-	diag_stat_inc(DIAG_STAT_X00C);
-	asm volatile (
-		"	sam31\n"
-		"	diag	%0,%0,0x0c\n"
-		"	sam64\n"
-		: /* no output register */
-		: "a" (entry)
-		: "memory");
-}
-
-/*
  * Get hypfs_diag0c_entry from CPU vector and store diag0c data
  */
 static void diag0c_fn(void *data)
 {
-	diag0c(((void **) data)[smp_processor_id()]);
+	diag_stat_inc(DIAG_STAT_X00C);
+	diag_dma_ops.diag0c(((void **) data)[smp_processor_id()]);
 }
 
 /*
diff --git a/arch/s390/include/asm/Kbuild b/arch/s390/include/asm/Kbuild
index 12d77cb11fe5..2531f673f099 100644
--- a/arch/s390/include/asm/Kbuild
+++ b/arch/s390/include/asm/Kbuild
@@ -20,7 +20,7 @@ generic-y += local.h
 generic-y += local64.h
 generic-y += mcs_spinlock.h
 generic-y += mm-arch-hooks.h
-generic-y += rwsem.h
+generic-y += mmiowb.h
 generic-y += trace_clock.h
 generic-y += unaligned.h
 generic-y += word-at-a-time.h
diff --git a/arch/s390/include/asm/airq.h b/arch/s390/include/asm/airq.h
index fcf539efb32f..c10d2ee2dfda 100644
--- a/arch/s390/include/asm/airq.h
+++ b/arch/s390/include/asm/airq.h
@@ -14,7 +14,7 @@
 
 struct airq_struct {
 	struct hlist_node list;		/* Handler queueing. */
-	void (*handler)(struct airq_struct *);	/* Thin-interrupt handler */
+	void (*handler)(struct airq_struct *airq, bool floating);
 	u8 *lsi_ptr;			/* Local-Summary-Indicator pointer */
 	u8 lsi_mask;			/* Local-Summary-Indicator mask */
 	u8 isc;				/* Interrupt-subclass */
@@ -35,13 +35,15 @@ struct airq_iv {
 	unsigned int *data;	/* 32 bit value associated with each bit */
 	unsigned long bits;	/* Number of bits in the vector */
 	unsigned long end;	/* Number of highest allocated bit + 1 */
+	unsigned long flags;	/* Allocation flags */
 	spinlock_t lock;	/* Lock to protect alloc & free */
 };
 
-#define AIRQ_IV_ALLOC	1	/* Use an allocation bit mask */
-#define AIRQ_IV_BITLOCK	2	/* Allocate the lock bit mask */
-#define AIRQ_IV_PTR	4	/* Allocate the ptr array */
-#define AIRQ_IV_DATA	8	/* Allocate the data array */
+#define AIRQ_IV_ALLOC		1	/* Use an allocation bit mask */
+#define AIRQ_IV_BITLOCK		2	/* Allocate the lock bit mask */
+#define AIRQ_IV_PTR		4	/* Allocate the ptr array */
+#define AIRQ_IV_DATA		8	/* Allocate the data array */
+#define AIRQ_IV_CACHELINE	16	/* Cacheline alignment for the vector */
 
 struct airq_iv *airq_iv_create(unsigned long bits, unsigned long flags);
 void airq_iv_release(struct airq_iv *iv);
diff --git a/arch/s390/include/asm/ap.h b/arch/s390/include/asm/ap.h
index 1a6a7092d942..e94a0a28b5eb 100644
--- a/arch/s390/include/asm/ap.h
+++ b/arch/s390/include/asm/ap.h
@@ -360,4 +360,15 @@ static inline struct ap_queue_status ap_dqap(ap_qid_t qid,
 	return reg1;
 }
 
+/*
+ * Interface to tell the AP bus code that a configuration
+ * change has happened. The bus code should at least do
+ * an ap bus resource rescan.
+ */
+#if IS_ENABLED(CONFIG_ZCRYPT)
+void ap_bus_cfg_chg(void);
+#else
+static inline void ap_bus_cfg_chg(void){};
+#endif
+
 #endif /* _ASM_S390_AP_H_ */
diff --git a/arch/s390/include/asm/bitops.h b/arch/s390/include/asm/bitops.h
index d1f8a4d94cca..9900d655014c 100644
--- a/arch/s390/include/asm/bitops.h
+++ b/arch/s390/include/asm/bitops.h
@@ -73,7 +73,7 @@ static inline void set_bit(unsigned long nr, volatile unsigned long *ptr)
 	}
 #endif
 	mask = 1UL << (nr & (BITS_PER_LONG - 1));
-	__atomic64_or(mask, addr);
+	__atomic64_or(mask, (long *)addr);
 }
 
 static inline void clear_bit(unsigned long nr, volatile unsigned long *ptr)
@@ -94,7 +94,7 @@ static inline void clear_bit(unsigned long nr, volatile unsigned long *ptr)
 	}
 #endif
 	mask = ~(1UL << (nr & (BITS_PER_LONG - 1)));
-	__atomic64_and(mask, addr);
+	__atomic64_and(mask, (long *)addr);
 }
 
 static inline void change_bit(unsigned long nr, volatile unsigned long *ptr)
@@ -115,7 +115,7 @@ static inline void change_bit(unsigned long nr, volatile unsigned long *ptr)
 	}
 #endif
 	mask = 1UL << (nr & (BITS_PER_LONG - 1));
-	__atomic64_xor(mask, addr);
+	__atomic64_xor(mask, (long *)addr);
 }
 
 static inline int
@@ -125,7 +125,7 @@ test_and_set_bit(unsigned long nr, volatile unsigned long *ptr)
 	unsigned long old, mask;
 
 	mask = 1UL << (nr & (BITS_PER_LONG - 1));
-	old = __atomic64_or_barrier(mask, addr);
+	old = __atomic64_or_barrier(mask, (long *)addr);
 	return (old & mask) != 0;
 }
 
@@ -136,7 +136,7 @@ test_and_clear_bit(unsigned long nr, volatile unsigned long *ptr)
 	unsigned long old, mask;
 
 	mask = ~(1UL << (nr & (BITS_PER_LONG - 1)));
-	old = __atomic64_and_barrier(mask, addr);
+	old = __atomic64_and_barrier(mask, (long *)addr);
 	return (old & ~mask) != 0;
 }
 
@@ -147,7 +147,7 @@ test_and_change_bit(unsigned long nr, volatile unsigned long *ptr)
 	unsigned long old, mask;
 
 	mask = 1UL << (nr & (BITS_PER_LONG - 1));
-	old = __atomic64_xor_barrier(mask, addr);
+	old = __atomic64_xor_barrier(mask, (long *)addr);
 	return (old & mask) != 0;
 }
 
diff --git a/arch/s390/include/asm/boot_data.h b/arch/s390/include/asm/boot_data.h
index 2d999ccb977a..f7eed27b3220 100644
--- a/arch/s390/include/asm/boot_data.h
+++ b/arch/s390/include/asm/boot_data.h
@@ -5,7 +5,14 @@
 #include <asm/ipl.h>
 
 extern char early_command_line[COMMAND_LINE_SIZE];
-extern struct ipl_parameter_block early_ipl_block;
-extern int early_ipl_block_valid;
+extern struct ipl_parameter_block ipl_block;
+extern int ipl_block_valid;
+extern int ipl_secure_flag;
+
+extern unsigned long ipl_cert_list_addr;
+extern unsigned long ipl_cert_list_size;
+
+extern unsigned long early_ipl_comp_list_addr;
+extern unsigned long early_ipl_comp_list_size;
 
 #endif /* _ASM_S390_BOOT_DATA_H */
diff --git a/arch/s390/include/asm/bug.h b/arch/s390/include/asm/bug.h
index 429f43a8a8e8..713fc9735ffb 100644
--- a/arch/s390/include/asm/bug.h
+++ b/arch/s390/include/asm/bug.h
@@ -15,7 +15,7 @@
 		".section .rodata.str,\"aMS\",@progbits,1\n"	\
 		"2:	.asciz	\""__FILE__"\"\n"		\
 		".previous\n"					\
-		".section __bug_table,\"aw\"\n"			\
+		".section __bug_table,\"awM\",@progbits,%2\n"	\
 		"3:	.long	1b-3b,2b-3b\n"			\
 		"	.short	%0,%1\n"			\
 		"	.org	3b+%2\n"			\
@@ -27,17 +27,17 @@
 
 #else /* CONFIG_DEBUG_BUGVERBOSE */
 
-#define __EMIT_BUG(x) do {				\
-	asm volatile(					\
-		"0:	j	0b+2\n"			\
-		"1:\n"					\
-		".section __bug_table,\"aw\"\n"		\
-		"2:	.long	1b-2b\n"		\
-		"	.short	%0\n"			\
-		"	.org	2b+%1\n"		\
-		".previous\n"				\
-		: : "i" (x),				\
-		    "i" (sizeof(struct bug_entry)));	\
+#define __EMIT_BUG(x) do {					\
+	asm volatile(						\
+		"0:	j	0b+2\n"				\
+		"1:\n"						\
+		".section __bug_table,\"awM\",@progbits,%1\n"	\
+		"2:	.long	1b-2b\n"			\
+		"	.short	%0\n"				\
+		"	.org	2b+%1\n"			\
+		".previous\n"					\
+		: : "i" (x),					\
+		    "i" (sizeof(struct bug_entry)));		\
 } while (0)
 
 #endif /* CONFIG_DEBUG_BUGVERBOSE */
diff --git a/arch/s390/include/asm/diag.h b/arch/s390/include/asm/diag.h
index 19562be22b7e..0036eab14391 100644
--- a/arch/s390/include/asm/diag.h
+++ b/arch/s390/include/asm/diag.h
@@ -308,4 +308,17 @@ union diag318_info {
 int diag204(unsigned long subcode, unsigned long size, void *addr);
 int diag224(void *ptr);
 int diag26c(void *req, void *resp, enum diag26c_sc subcode);
+
+struct hypfs_diag0c_entry;
+
+struct diag_ops {
+	int (*diag210)(struct diag210 *addr);
+	int (*diag26c)(void *req, void *resp, enum diag26c_sc subcode);
+	int (*diag14)(unsigned long rx, unsigned long ry1, unsigned long subcode);
+	void (*diag0c)(struct hypfs_diag0c_entry *entry);
+	void (*diag308_reset)(void);
+};
+
+extern struct diag_ops diag_dma_ops;
+extern struct diag210 *__diag210_tmp_dma;
 #endif /* _ASM_S390_DIAG_H */
diff --git a/arch/s390/include/asm/ebcdic.h b/arch/s390/include/asm/ebcdic.h
index 29441beb92e6..efb50fc6866c 100644
--- a/arch/s390/include/asm/ebcdic.h
+++ b/arch/s390/include/asm/ebcdic.h
@@ -20,7 +20,7 @@ extern __u8 _ebc_tolower[256]; /* EBCDIC -> lowercase */
 extern __u8 _ebc_toupper[256]; /* EBCDIC -> uppercase */
 
 static inline void
-codepage_convert(const __u8 *codepage, volatile __u8 * addr, unsigned long nr)
+codepage_convert(const __u8 *codepage, volatile char *addr, unsigned long nr)
 {
 	if (nr-- <= 0)
 		return;
diff --git a/arch/s390/include/asm/elf.h b/arch/s390/include/asm/elf.h
index 7d22a474a040..5775fc22f410 100644
--- a/arch/s390/include/asm/elf.h
+++ b/arch/s390/include/asm/elf.h
@@ -107,6 +107,10 @@
 #define HWCAP_S390_VXRS_BCD	4096
 #define HWCAP_S390_VXRS_EXT	8192
 #define HWCAP_S390_GS		16384
+#define HWCAP_S390_VXRS_EXT2	32768
+#define HWCAP_S390_VXRS_PDE	65536
+#define HWCAP_S390_SORT		131072
+#define HWCAP_S390_DFLT		262144
 
 /* Internal bits, not exposed via elf */
 #define HWCAP_INT_SIE		1UL
@@ -252,11 +256,14 @@ do {								\
 
 /*
  * Cache aliasing on the latest machines calls for a mapping granularity
- * of 512KB. For 64-bit processes use a 512KB alignment and a randomization
- * of up to 1GB. For 31-bit processes the virtual address space is limited,
- * use no alignment and limit the randomization to 8MB.
+ * of 512KB for the anonymous mapping base. For 64-bit processes use a
+ * 512KB alignment and a randomization of up to 1GB. For 31-bit processes
+ * the virtual address space is limited, use no alignment and limit the
+ * randomization to 8MB.
+ * For the additional randomization of the program break use 32MB for
+ * 64-bit and 8MB for 31-bit.
  */
-#define BRK_RND_MASK	(is_compat_task() ? 0x7ffUL : 0x3ffffUL)
+#define BRK_RND_MASK	(is_compat_task() ? 0x7ffUL : 0x1fffUL)
 #define MMAP_RND_MASK	(is_compat_task() ? 0x7ffUL : 0x3ff80UL)
 #define MMAP_ALIGN_MASK	(is_compat_task() ? 0 : 0x7fUL)
 #define STACK_RND_MASK	MMAP_RND_MASK
diff --git a/arch/s390/include/asm/extable.h b/arch/s390/include/asm/extable.h
index 80a4e5a9cb46..ae27f756b409 100644
--- a/arch/s390/include/asm/extable.h
+++ b/arch/s390/include/asm/extable.h
@@ -19,6 +19,11 @@ struct exception_table_entry
 	int insn, fixup;
 };
 
+extern struct exception_table_entry *__start_dma_ex_table;
+extern struct exception_table_entry *__stop_dma_ex_table;
+
+const struct exception_table_entry *s390_search_extables(unsigned long addr);
+
 static inline unsigned long extable_fixup(const struct exception_table_entry *x)
 {
 	return (unsigned long)&x->fixup + x->fixup;
diff --git a/arch/s390/include/asm/ftrace.h b/arch/s390/include/asm/ftrace.h
index 5a3c95b11952..68d362f8d6c1 100644
--- a/arch/s390/include/asm/ftrace.h
+++ b/arch/s390/include/asm/ftrace.h
@@ -11,9 +11,16 @@
 #define MCOUNT_RETURN_FIXUP	18
 #endif
 
+#define HAVE_FUNCTION_GRAPH_RET_ADDR_PTR
+
 #ifndef __ASSEMBLY__
 
+#ifdef CONFIG_CC_IS_CLANG
+/* https://bugs.llvm.org/show_bug.cgi?id=41424 */
+#define ftrace_return_address(n) 0UL
+#else
 #define ftrace_return_address(n) __builtin_return_address(n)
+#endif
 
 void _mcount(void);
 void ftrace_caller(void);
diff --git a/arch/s390/include/asm/io.h b/arch/s390/include/asm/io.h
index f34d729347e4..ca421614722f 100644
--- a/arch/s390/include/asm/io.h
+++ b/arch/s390/include/asm/io.h
@@ -30,14 +30,8 @@ void unxlate_dev_mem_ptr(phys_addr_t phys, void *addr);
 #define ioremap_wc			ioremap_nocache
 #define ioremap_wt			ioremap_nocache
 
-static inline void __iomem *ioremap(unsigned long offset, unsigned long size)
-{
-	return (void __iomem *) offset;
-}
-
-static inline void iounmap(volatile void __iomem *addr)
-{
-}
+void __iomem *ioremap(unsigned long offset, unsigned long size);
+void iounmap(volatile void __iomem *addr);
 
 static inline void __iomem *ioport_map(unsigned long port, unsigned int nr)
 {
@@ -57,14 +51,17 @@ static inline void ioport_unmap(void __iomem *p)
  * the corresponding device and create the mapping cookie.
  */
 #define pci_iomap pci_iomap
+#define pci_iomap_range pci_iomap_range
 #define pci_iounmap pci_iounmap
-#define pci_iomap_wc pci_iomap
-#define pci_iomap_wc_range pci_iomap_range
+#define pci_iomap_wc pci_iomap_wc
+#define pci_iomap_wc_range pci_iomap_wc_range
 
 #define memcpy_fromio(dst, src, count)	zpci_memcpy_fromio(dst, src, count)
 #define memcpy_toio(dst, src, count)	zpci_memcpy_toio(dst, src, count)
 #define memset_io(dst, val, count)	zpci_memset_io(dst, val, count)
 
+#define mmiowb()	zpci_barrier()
+
 #define __raw_readb	zpci_read_u8
 #define __raw_readw	zpci_read_u16
 #define __raw_readl	zpci_read_u32
diff --git a/arch/s390/include/asm/ipl.h b/arch/s390/include/asm/ipl.h
index a8389e2d2f03..084e71b7272a 100644
--- a/arch/s390/include/asm/ipl.h
+++ b/arch/s390/include/asm/ipl.h
@@ -12,74 +12,36 @@
 #include <asm/types.h>
 #include <asm/cio.h>
 #include <asm/setup.h>
+#include <uapi/asm/ipl.h>
 
-#define NSS_NAME_SIZE	8
-
-#define IPL_PARM_BLK_FCP_LEN (sizeof(struct ipl_list_hdr) + \
-			      sizeof(struct ipl_block_fcp))
-
-#define IPL_PARM_BLK0_FCP_LEN (sizeof(struct ipl_block_fcp) + 16)
+struct ipl_parameter_block {
+	struct ipl_pl_hdr hdr;
+	union {
+		struct ipl_pb_hdr pb0_hdr;
+		struct ipl_pb0_common common;
+		struct ipl_pb0_fcp fcp;
+		struct ipl_pb0_ccw ccw;
+		char raw[PAGE_SIZE - sizeof(struct ipl_pl_hdr)];
+	};
+} __packed __aligned(PAGE_SIZE);
 
-#define IPL_PARM_BLK_CCW_LEN (sizeof(struct ipl_list_hdr) + \
-			      sizeof(struct ipl_block_ccw))
+#define NSS_NAME_SIZE 8
 
-#define IPL_PARM_BLK0_CCW_LEN (sizeof(struct ipl_block_ccw) + 16)
+#define IPL_BP_FCP_LEN (sizeof(struct ipl_pl_hdr) + \
+			      sizeof(struct ipl_pb0_fcp))
+#define IPL_BP0_FCP_LEN (sizeof(struct ipl_pb0_fcp))
+#define IPL_BP_CCW_LEN (sizeof(struct ipl_pl_hdr) + \
+			      sizeof(struct ipl_pb0_ccw))
+#define IPL_BP0_CCW_LEN (sizeof(struct ipl_pb0_ccw))
 
 #define IPL_MAX_SUPPORTED_VERSION (0)
 
-struct ipl_list_hdr {
-	u32 len;
-	u8  reserved1[3];
-	u8  version;
-	u32 blk0_len;
-	u8  pbt;
-	u8  flags;
-	u16 reserved2;
-	u8  loadparm[8];
-} __attribute__((packed));
-
-struct ipl_block_fcp {
-	u8  reserved1[305-1];
-	u8  opt;
-	u8  reserved2[3];
-	u16 reserved3;
-	u16 devno;
-	u8  reserved4[4];
-	u64 wwpn;
-	u64 lun;
-	u32 bootprog;
-	u8  reserved5[12];
-	u64 br_lba;
-	u32 scp_data_len;
-	u8  reserved6[260];
-	u8  scp_data[];
-} __attribute__((packed));
-
-#define DIAG308_VMPARM_SIZE	64
-#define DIAG308_SCPDATA_SIZE	(PAGE_SIZE - (sizeof(struct ipl_list_hdr) + \
-				 offsetof(struct ipl_block_fcp, scp_data)))
-
-struct ipl_block_ccw {
-	u8  reserved1[84];
-	u16 reserved2 : 13;
-	u8  ssid : 3;
-	u16 devno;
-	u8  vm_flags;
-	u8  reserved3[3];
-	u32 vm_parm_len;
-	u8  nss_name[8];
-	u8  vm_parm[DIAG308_VMPARM_SIZE];
-	u8  reserved4[8];
-} __attribute__((packed));
+#define IPL_RB_CERT_UNKNOWN ((unsigned short)-1)
 
-struct ipl_parameter_block {
-	struct ipl_list_hdr hdr;
-	union {
-		struct ipl_block_fcp fcp;
-		struct ipl_block_ccw ccw;
-		char raw[PAGE_SIZE - sizeof(struct ipl_list_hdr)];
-	} ipl_info;
-} __packed __aligned(PAGE_SIZE);
+#define DIAG308_VMPARM_SIZE (64)
+#define DIAG308_SCPDATA_OFFSET offsetof(struct ipl_parameter_block, \
+					fcp.scp_data)
+#define DIAG308_SCPDATA_SIZE (PAGE_SIZE - DIAG308_SCPDATA_OFFSET)
 
 struct save_area;
 struct save_area * __init save_area_alloc(bool is_boot_cpu);
@@ -88,7 +50,6 @@ void __init save_area_add_regs(struct save_area *, void *regs);
 void __init save_area_add_vxrs(struct save_area *, __vector128 *vxrs);
 
 extern void s390_reset_system(void);
-extern void ipl_store_parameters(void);
 extern size_t ipl_block_get_ascii_vmparm(char *dest, size_t size,
 					 const struct ipl_parameter_block *ipb);
 
@@ -122,6 +83,33 @@ extern struct ipl_info ipl_info;
 extern void setup_ipl(void);
 extern void set_os_info_reipl_block(void);
 
+struct ipl_report {
+	struct ipl_parameter_block *ipib;
+	struct list_head components;
+	struct list_head certificates;
+	size_t size;
+};
+
+struct ipl_report_component {
+	struct list_head list;
+	struct ipl_rb_component_entry entry;
+};
+
+struct ipl_report_certificate {
+	struct list_head list;
+	struct ipl_rb_certificate_entry entry;
+	void *key;
+};
+
+struct kexec_buf;
+struct ipl_report *ipl_report_init(struct ipl_parameter_block *ipib);
+void *ipl_report_finish(struct ipl_report *report);
+int ipl_report_free(struct ipl_report *report);
+int ipl_report_add_component(struct ipl_report *report, struct kexec_buf *kbuf,
+			     unsigned char flags, unsigned short cert);
+int ipl_report_add_certificate(struct ipl_report *report, void *key,
+			       unsigned long addr, unsigned long len);
+
 /*
  * DIAG 308 support
  */
@@ -133,32 +121,12 @@ enum diag308_subcode  {
 	DIAG308_STORE = 6,
 };
 
-enum diag308_ipl_type {
-	DIAG308_IPL_TYPE_FCP	= 0,
-	DIAG308_IPL_TYPE_CCW	= 2,
-};
-
-enum diag308_opt {
-	DIAG308_IPL_OPT_IPL	= 0x10,
-	DIAG308_IPL_OPT_DUMP	= 0x20,
-};
-
-enum diag308_flags {
-	DIAG308_FLAGS_LP_VALID	= 0x80,
-};
-
-enum diag308_vm_flags {
-	DIAG308_VM_FLAGS_NSS_VALID	= 0x80,
-	DIAG308_VM_FLAGS_VP_VALID	= 0x40,
-};
-
 enum diag308_rc {
 	DIAG308_RC_OK		= 0x0001,
 	DIAG308_RC_NOCONFIG	= 0x0102,
 };
 
 extern int diag308(unsigned long subcode, void *addr);
-extern void diag308_reset(void);
 extern void store_status(void (*fn)(void *), void *data);
 extern void lgr_info_log(void);
 
diff --git a/arch/s390/include/asm/irq.h b/arch/s390/include/asm/irq.h
index afaf5e3c57fd..9f75d67b8c20 100644
--- a/arch/s390/include/asm/irq.h
+++ b/arch/s390/include/asm/irq.h
@@ -47,7 +47,6 @@ enum interruption_class {
 	IRQEXT_CMC,
 	IRQEXT_FTP,
 	IRQIO_CIO,
-	IRQIO_QAI,
 	IRQIO_DAS,
 	IRQIO_C15,
 	IRQIO_C70,
@@ -55,12 +54,14 @@ enum interruption_class {
 	IRQIO_VMR,
 	IRQIO_LCS,
 	IRQIO_CTC,
-	IRQIO_APB,
 	IRQIO_ADM,
 	IRQIO_CSC,
-	IRQIO_PCI,
-	IRQIO_MSI,
 	IRQIO_VIR,
+	IRQIO_QAI,
+	IRQIO_APB,
+	IRQIO_PCF,
+	IRQIO_PCD,
+	IRQIO_MSI,
 	IRQIO_VAI,
 	IRQIO_GAL,
 	NMI_NMI,
diff --git a/arch/s390/include/asm/kexec.h b/arch/s390/include/asm/kexec.h
index 825dd0f7f221..ea398a05f643 100644
--- a/arch/s390/include/asm/kexec.h
+++ b/arch/s390/include/asm/kexec.h
@@ -11,6 +11,7 @@
 
 #include <asm/processor.h>
 #include <asm/page.h>
+#include <asm/setup.h>
 /*
  * KEXEC_SOURCE_MEMORY_LIMIT maximum page get_free_page can return.
  * I.e. Maximum page that is mapped directly into kernel memory,
@@ -42,6 +43,9 @@
 /* The native architecture */
 #define KEXEC_ARCH KEXEC_ARCH_S390
 
+/* Allow kexec_file to load a segment to 0 */
+#define KEXEC_BUF_MEM_UNKNOWN -1
+
 /* Provide a dummy definition to avoid build failures. */
 static inline void crash_setup_regs(struct pt_regs *newregs,
 					struct pt_regs *oldregs) { }
@@ -51,20 +55,24 @@ struct s390_load_data {
 	/* Pointer to the kernel buffer. Used to register cmdline etc.. */
 	void *kernel_buf;
 
+	/* Load address of the kernel_buf. */
+	unsigned long kernel_mem;
+
+	/* Parmarea in the kernel buffer. */
+	struct parmarea *parm;
+
 	/* Total size of loaded segments in memory. Used as an offset. */
 	size_t memsz;
 
-	/* Load address of initrd. Used to register INITRD_START in kernel. */
-	unsigned long initrd_load_addr;
+	struct ipl_report *report;
 };
 
-int kexec_file_add_purgatory(struct kimage *image,
-			     struct s390_load_data *data);
-int kexec_file_add_initrd(struct kimage *image,
-			  struct s390_load_data *data,
-			  char *initrd, unsigned long initrd_len);
-int *kexec_file_update_kernel(struct kimage *iamge,
-			      struct s390_load_data *data);
+int s390_verify_sig(const char *kernel, unsigned long kernel_len);
+void *kexec_file_add_components(struct kimage *image,
+				int (*add_kernel)(struct kimage *image,
+						  struct s390_load_data *data));
+int arch_kexec_do_relocs(int r_type, void *loc, unsigned long val,
+			 unsigned long addr);
 
 extern const struct kexec_file_ops s390_kexec_image_ops;
 extern const struct kexec_file_ops s390_kexec_elf_ops;
diff --git a/arch/s390/include/asm/linkage.h b/arch/s390/include/asm/linkage.h
index 1b95da3fdd64..7f22262b0e46 100644
--- a/arch/s390/include/asm/linkage.h
+++ b/arch/s390/include/asm/linkage.h
@@ -28,5 +28,12 @@
 	.long	(_target) - . ;		\
 	.previous
 
+#define EX_TABLE_DMA(_fault, _target)	\
+	.section .dma.ex_table, "a" ;	\
+	.align	4 ;			\
+	.long	(_fault) - . ;		\
+	.long	(_target) - . ;		\
+	.previous
+
 #endif /* __ASSEMBLY__ */
 #endif
diff --git a/arch/s390/include/asm/lowcore.h b/arch/s390/include/asm/lowcore.h
index cc0947e08b6f..237ee0c4169f 100644
--- a/arch/s390/include/asm/lowcore.h
+++ b/arch/s390/include/asm/lowcore.h
@@ -91,52 +91,53 @@ struct lowcore {
 	__u64	hardirq_timer;			/* 0x02e8 */
 	__u64	softirq_timer;			/* 0x02f0 */
 	__u64	steal_timer;			/* 0x02f8 */
-	__u64	last_update_timer;		/* 0x0300 */
-	__u64	last_update_clock;		/* 0x0308 */
-	__u64	int_clock;			/* 0x0310 */
-	__u64	mcck_clock;			/* 0x0318 */
-	__u64	clock_comparator;		/* 0x0320 */
-	__u64	boot_clock[2];			/* 0x0328 */
+	__u64	avg_steal_timer;		/* 0x0300 */
+	__u64	last_update_timer;		/* 0x0308 */
+	__u64	last_update_clock;		/* 0x0310 */
+	__u64	int_clock;			/* 0x0318*/
+	__u64	mcck_clock;			/* 0x0320 */
+	__u64	clock_comparator;		/* 0x0328 */
+	__u64	boot_clock[2];			/* 0x0330 */
 
 	/* Current process. */
-	__u64	current_task;			/* 0x0338 */
-	__u64	kernel_stack;			/* 0x0340 */
+	__u64	current_task;			/* 0x0340 */
+	__u64	kernel_stack;			/* 0x0348 */
 
 	/* Interrupt, DAT-off and restartstack. */
-	__u64	async_stack;			/* 0x0348 */
-	__u64	nodat_stack;			/* 0x0350 */
-	__u64	restart_stack;			/* 0x0358 */
+	__u64	async_stack;			/* 0x0350 */
+	__u64	nodat_stack;			/* 0x0358 */
+	__u64	restart_stack;			/* 0x0360 */
 
 	/* Restart function and parameter. */
-	__u64	restart_fn;			/* 0x0360 */
-	__u64	restart_data;			/* 0x0368 */
-	__u64	restart_source;			/* 0x0370 */
+	__u64	restart_fn;			/* 0x0368 */
+	__u64	restart_data;			/* 0x0370 */
+	__u64	restart_source;			/* 0x0378 */
 
 	/* Address space pointer. */
-	__u64	kernel_asce;			/* 0x0378 */
-	__u64	user_asce;			/* 0x0380 */
-	__u64	vdso_asce;			/* 0x0388 */
+	__u64	kernel_asce;			/* 0x0380 */
+	__u64	user_asce;			/* 0x0388 */
+	__u64	vdso_asce;			/* 0x0390 */
 
 	/*
 	 * The lpp and current_pid fields form a
 	 * 64-bit value that is set as program
 	 * parameter with the LPP instruction.
 	 */
-	__u32	lpp;				/* 0x0390 */
-	__u32	current_pid;			/* 0x0394 */
+	__u32	lpp;				/* 0x0398 */
+	__u32	current_pid;			/* 0x039c */
 
 	/* SMP info area */
-	__u32	cpu_nr;				/* 0x0398 */
-	__u32	softirq_pending;		/* 0x039c */
-	__u32	preempt_count;			/* 0x03a0 */
-	__u32	spinlock_lockval;		/* 0x03a4 */
-	__u32	spinlock_index;			/* 0x03a8 */
-	__u32	fpu_flags;			/* 0x03ac */
-	__u64	percpu_offset;			/* 0x03b0 */
-	__u64	vdso_per_cpu_data;		/* 0x03b8 */
-	__u64	machine_flags;			/* 0x03c0 */
-	__u64	gmap;				/* 0x03c8 */
-	__u8	pad_0x03d0[0x0400-0x03d0];	/* 0x03d0 */
+	__u32	cpu_nr;				/* 0x03a0 */
+	__u32	softirq_pending;		/* 0x03a4 */
+	__s32	preempt_count;			/* 0x03a8 */
+	__u32	spinlock_lockval;		/* 0x03ac */
+	__u32	spinlock_index;			/* 0x03b0 */
+	__u32	fpu_flags;			/* 0x03b4 */
+	__u64	percpu_offset;			/* 0x03b8 */
+	__u64	vdso_per_cpu_data;		/* 0x03c0 */
+	__u64	machine_flags;			/* 0x03c8 */
+	__u64	gmap;				/* 0x03d0 */
+	__u8	pad_0x03d8[0x0400-0x03d8];	/* 0x03d8 */
 
 	/* br %r1 trampoline */
 	__u16	br_r1_trampoline;		/* 0x0400 */
diff --git a/arch/s390/include/asm/nospec-insn.h b/arch/s390/include/asm/nospec-insn.h
index 123dac3717b3..0033dcd663b1 100644
--- a/arch/s390/include/asm/nospec-insn.h
+++ b/arch/s390/include/asm/nospec-insn.h
@@ -32,23 +32,23 @@ _LC_BR_R1 = __LC_BR_R1
 	.endm
 
 	.macro __THUNK_PROLOG_BR r1,r2
-	__THUNK_PROLOG_NAME __s390x_indirect_jump_r\r2\()use_r\r1
+	__THUNK_PROLOG_NAME __s390_indirect_jump_r\r2\()use_r\r1
 	.endm
 
 	.macro __THUNK_PROLOG_BC d0,r1,r2
-	__THUNK_PROLOG_NAME __s390x_indirect_branch_\d0\()_\r2\()use_\r1
+	__THUNK_PROLOG_NAME __s390_indirect_branch_\d0\()_\r2\()use_\r1
 	.endm
 
 	.macro __THUNK_BR r1,r2
-	jg	__s390x_indirect_jump_r\r2\()use_r\r1
+	jg	__s390_indirect_jump_r\r2\()use_r\r1
 	.endm
 
 	.macro __THUNK_BC d0,r1,r2
-	jg	__s390x_indirect_branch_\d0\()_\r2\()use_\r1
+	jg	__s390_indirect_branch_\d0\()_\r2\()use_\r1
 	.endm
 
 	.macro __THUNK_BRASL r1,r2,r3
-	brasl	\r1,__s390x_indirect_jump_r\r3\()use_r\r2
+	brasl	\r1,__s390_indirect_jump_r\r3\()use_r\r2
 	.endm
 
 	.macro	__DECODE_RR expand,reg,ruse
diff --git a/arch/s390/include/asm/pci.h b/arch/s390/include/asm/pci.h
index 4e0efebc56a9..305befd55326 100644
--- a/arch/s390/include/asm/pci.h
+++ b/arch/s390/include/asm/pci.h
@@ -26,6 +26,9 @@ int pci_proc_domain(struct pci_bus *);
 #define ZPCI_BUS_NR			0	/* default bus number */
 #define ZPCI_DEVFN			0	/* default device number */
 
+#define ZPCI_NR_DMA_SPACES		1
+#define ZPCI_NR_DEVICES			CONFIG_PCI_NR_FUNCTIONS
+
 /* PCI Function Controls */
 #define ZPCI_FC_FN_ENABLED		0x80
 #define ZPCI_FC_ERROR			0x40
@@ -83,6 +86,8 @@ enum zpci_state {
 
 struct zpci_bar_struct {
 	struct resource *res;		/* bus resource */
+	void __iomem	*mio_wb;
+	void __iomem	*mio_wt;
 	u32		val;		/* bar start & 3 flag bits */
 	u16		map_idx;	/* index into bar mapping array */
 	u8		size;		/* order 2 exponent */
@@ -112,6 +117,8 @@ struct zpci_dev {
 	/* IRQ stuff */
 	u64		msi_addr;	/* MSI address */
 	unsigned int	max_msi;	/* maximum number of MSI's */
+	unsigned int	msi_first_bit;
+	unsigned int	msi_nr_irqs;
 	struct airq_iv *aibv;		/* adapter interrupt bit vector */
 	unsigned long	aisb;		/* number of the summary bit */
 
@@ -130,6 +137,7 @@ struct zpci_dev {
 	struct iommu_device iommu_dev;  /* IOMMU core handle */
 
 	char res_name[16];
+	bool mio_capable;
 	struct zpci_bar_struct bars[PCI_BAR_COUNT];
 
 	u64		start_dma;	/* Start of available DMA addresses */
@@ -158,6 +166,7 @@ static inline bool zdev_enabled(struct zpci_dev *zdev)
 }
 
 extern const struct attribute_group *zpci_attr_groups[];
+extern unsigned int s390_pci_force_floating __initdata;
 
 /* -----------------------------------------------------------------------------
   Prototypes
@@ -219,6 +228,9 @@ struct zpci_dev *get_zdev_by_fid(u32);
 int zpci_dma_init(void);
 void zpci_dma_exit(void);
 
+int __init zpci_irq_init(void);
+void __init zpci_irq_exit(void);
+
 /* FMB */
 int zpci_fmb_enable_device(struct zpci_dev *);
 int zpci_fmb_disable_device(struct zpci_dev *);
diff --git a/arch/s390/include/asm/pci_clp.h b/arch/s390/include/asm/pci_clp.h
index b3b31b31f0d3..3ec52a05d500 100644
--- a/arch/s390/include/asm/pci_clp.h
+++ b/arch/s390/include/asm/pci_clp.h
@@ -43,6 +43,8 @@ struct clp_fh_list_entry {
 
 #define CLP_SET_ENABLE_PCI_FN	0	/* Yes, 0 enables it */
 #define CLP_SET_DISABLE_PCI_FN	1	/* Yes, 1 disables it */
+#define CLP_SET_ENABLE_MIO	2
+#define CLP_SET_DISABLE_MIO	3
 
 #define CLP_UTIL_STR_LEN	64
 #define CLP_PFIP_NR_SEGMENTS	4
@@ -80,7 +82,8 @@ struct clp_req_query_pci {
 struct clp_rsp_query_pci {
 	struct clp_rsp_hdr hdr;
 	u16 vfn;			/* virtual fn number */
-	u16			:  7;
+	u16			:  6;
+	u16 mio_addr_avail	:  1;
 	u16 util_str_avail	:  1;	/* utility string available? */
 	u16 pfgid		:  8;	/* pci function group id */
 	u32 fid;			/* pci function id */
@@ -96,6 +99,15 @@ struct clp_rsp_query_pci {
 	u32 reserved[11];
 	u32 uid;			/* user defined id */
 	u8 util_str[CLP_UTIL_STR_LEN];	/* utility string */
+	u32 reserved2[16];
+	u32 mio_valid : 6;
+	u32 : 26;
+	u32 : 32;
+	struct {
+		u64 wb;
+		u64 wt;
+	} addr[PCI_BAR_COUNT];
+	u32 reserved3[6];
 } __packed;
 
 /* Query PCI function group request */
@@ -118,7 +130,11 @@ struct clp_rsp_query_pci_grp {
 	u8 refresh		:  1;	/* TLB refresh mode */
 	u16 reserved2;
 	u16 mui;
-	u64 reserved3;
+	u16			: 16;
+	u16 maxfaal;
+	u16			:  4;
+	u16 dnoi		: 12;
+	u16 maxcpu;
 	u64 dasm;			/* dma address space mask */
 	u64 msia;			/* MSI address */
 	u64 reserved4;
diff --git a/arch/s390/include/asm/pci_insn.h b/arch/s390/include/asm/pci_insn.h
index ba22a6ea51a1..ff81ed19c506 100644
--- a/arch/s390/include/asm/pci_insn.h
+++ b/arch/s390/include/asm/pci_insn.h
@@ -2,6 +2,8 @@
 #ifndef _ASM_S390_PCI_INSN_H
 #define _ASM_S390_PCI_INSN_H
 
+#include <linux/jump_label.h>
+
 /* Load/Store status codes */
 #define ZPCI_PCI_ST_FUNC_NOT_ENABLED		4
 #define ZPCI_PCI_ST_FUNC_IN_ERR			8
@@ -38,6 +40,8 @@
 #define ZPCI_MOD_FC_RESET_ERROR	7
 #define ZPCI_MOD_FC_RESET_BLOCK	9
 #define ZPCI_MOD_FC_SET_MEASURE	10
+#define ZPCI_MOD_FC_REG_INT_D	16
+#define ZPCI_MOD_FC_DEREG_INT_D	17
 
 /* FIB function controls */
 #define ZPCI_FIB_FC_ENABLED	0x80
@@ -51,16 +55,7 @@
 #define ZPCI_FIB_FC_LS_BLOCKED	0x20
 #define ZPCI_FIB_FC_DMAAS_REG	0x10
 
-/* Function Information Block */
-struct zpci_fib {
-	u32 fmt		:  8;	/* format */
-	u32		: 24;
-	u32		: 32;
-	u8 fc;			/* function controls */
-	u64		: 56;
-	u64 pba;		/* PCI base address */
-	u64 pal;		/* PCI address limit */
-	u64 iota;		/* I/O Translation Anchor */
+struct zpci_fib_fmt0 {
 	u32		:  1;
 	u32 isc		:  3;	/* Interrupt subclass */
 	u32 noi		: 12;	/* Number of interrupts */
@@ -72,16 +67,90 @@ struct zpci_fib {
 	u32		: 32;
 	u64 aibv;		/* Adapter int bit vector address */
 	u64 aisb;		/* Adapter int summary bit address */
+};
+
+struct zpci_fib_fmt1 {
+	u32		:  4;
+	u32 noi		: 12;
+	u32		: 16;
+	u32 dibvo	: 16;
+	u32		: 16;
+	u64		: 64;
+	u64		: 64;
+};
+
+/* Function Information Block */
+struct zpci_fib {
+	u32 fmt		:  8;	/* format */
+	u32		: 24;
+	u32		: 32;
+	u8 fc;			/* function controls */
+	u64		: 56;
+	u64 pba;		/* PCI base address */
+	u64 pal;		/* PCI address limit */
+	u64 iota;		/* I/O Translation Anchor */
+	union {
+		struct zpci_fib_fmt0 fmt0;
+		struct zpci_fib_fmt1 fmt1;
+	};
 	u64 fmb_addr;		/* Function measurement block address and key */
 	u32		: 32;
 	u32 gd;
 } __packed __aligned(8);
 
+/* directed interruption information block */
+struct zpci_diib {
+	u32 : 1;
+	u32 isc : 3;
+	u32 : 28;
+	u16 : 16;
+	u16 nr_cpus;
+	u64 disb_addr;
+	u64 : 64;
+	u64 : 64;
+} __packed __aligned(8);
+
+/* cpu directed interruption information block */
+struct zpci_cdiib {
+	u64 : 64;
+	u64 dibv_addr;
+	u64 : 64;
+	u64 : 64;
+	u64 : 64;
+} __packed __aligned(8);
+
+union zpci_sic_iib {
+	struct zpci_diib diib;
+	struct zpci_cdiib cdiib;
+};
+
+DECLARE_STATIC_KEY_FALSE(have_mio);
+
 u8 zpci_mod_fc(u64 req, struct zpci_fib *fib, u8 *status);
 int zpci_refresh_trans(u64 fn, u64 addr, u64 range);
-int zpci_load(u64 *data, u64 req, u64 offset);
-int zpci_store(u64 data, u64 req, u64 offset);
-int zpci_store_block(const u64 *data, u64 req, u64 offset);
-int zpci_set_irq_ctrl(u16 ctl, char *unused, u8 isc);
+int __zpci_load(u64 *data, u64 req, u64 offset);
+int zpci_load(u64 *data, const volatile void __iomem *addr, unsigned long len);
+int __zpci_store(u64 data, u64 req, u64 offset);
+int zpci_store(const volatile void __iomem *addr, u64 data, unsigned long len);
+int __zpci_store_block(const u64 *data, u64 req, u64 offset);
+void zpci_barrier(void);
+int __zpci_set_irq_ctrl(u16 ctl, u8 isc, union zpci_sic_iib *iib);
+
+static inline int zpci_set_irq_ctrl(u16 ctl, u8 isc)
+{
+	union zpci_sic_iib iib = {{0}};
+
+	return __zpci_set_irq_ctrl(ctl, isc, &iib);
+}
+
+#ifdef CONFIG_PCI
+static inline void enable_mio_ctl(void)
+{
+	if (static_branch_likely(&have_mio))
+		__ctl_set_bit(2, 5);
+}
+#else /* CONFIG_PCI */
+static inline void enable_mio_ctl(void) {}
+#endif /* CONFIG_PCI */
 
 #endif
diff --git a/arch/s390/include/asm/pci_io.h b/arch/s390/include/asm/pci_io.h
index cbb9cb9c6547..cd060b5dd8fd 100644
--- a/arch/s390/include/asm/pci_io.h
+++ b/arch/s390/include/asm/pci_io.h
@@ -37,12 +37,10 @@ extern struct zpci_iomap_entry *zpci_iomap_start;
 #define zpci_read(LENGTH, RETTYPE)						\
 static inline RETTYPE zpci_read_##RETTYPE(const volatile void __iomem *addr)	\
 {										\
-	struct zpci_iomap_entry *entry = &zpci_iomap_start[ZPCI_IDX(addr)];	\
-	u64 req = ZPCI_CREATE_REQ(entry->fh, entry->bar, LENGTH);		\
 	u64 data;								\
 	int rc;									\
 										\
-	rc = zpci_load(&data, req, ZPCI_OFFSET(addr));				\
+	rc = zpci_load(&data, addr, LENGTH);					\
 	if (rc)									\
 		data = -1ULL;							\
 	return (RETTYPE) data;							\
@@ -52,11 +50,9 @@ static inline RETTYPE zpci_read_##RETTYPE(const volatile void __iomem *addr)	\
 static inline void zpci_write_##VALTYPE(VALTYPE val,				\
 					const volatile void __iomem *addr)	\
 {										\
-	struct zpci_iomap_entry *entry = &zpci_iomap_start[ZPCI_IDX(addr)];	\
-	u64 req = ZPCI_CREATE_REQ(entry->fh, entry->bar, LENGTH);		\
 	u64 data = (VALTYPE) val;						\
 										\
-	zpci_store(data, req, ZPCI_OFFSET(addr));				\
+	zpci_store(addr, data, LENGTH);						\
 }
 
 zpci_read(8, u64)
@@ -68,36 +64,38 @@ zpci_write(4, u32)
 zpci_write(2, u16)
 zpci_write(1, u8)
 
-static inline int zpci_write_single(u64 req, const u64 *data, u64 offset, u8 len)
+static inline int zpci_write_single(volatile void __iomem *dst, const void *src,
+				    unsigned long len)
 {
 	u64 val;
 
 	switch (len) {
 	case 1:
-		val = (u64) *((u8 *) data);
+		val = (u64) *((u8 *) src);
 		break;
 	case 2:
-		val = (u64) *((u16 *) data);
+		val = (u64) *((u16 *) src);
 		break;
 	case 4:
-		val = (u64) *((u32 *) data);
+		val = (u64) *((u32 *) src);
 		break;
 	case 8:
-		val = (u64) *((u64 *) data);
+		val = (u64) *((u64 *) src);
 		break;
 	default:
 		val = 0;		/* let FW report error */
 		break;
 	}
-	return zpci_store(val, req, offset);
+	return zpci_store(dst, val, len);
 }
 
-static inline int zpci_read_single(u64 req, u64 *dst, u64 offset, u8 len)
+static inline int zpci_read_single(void *dst, const volatile void __iomem *src,
+				   unsigned long len)
 {
 	u64 data;
 	int cc;
 
-	cc = zpci_load(&data, req, offset);
+	cc = zpci_load(&data, src, len);
 	if (cc)
 		goto out;
 
@@ -119,10 +117,8 @@ out:
 	return cc;
 }
 
-static inline int zpci_write_block(u64 req, const u64 *data, u64 offset)
-{
-	return zpci_store_block(data, req, offset);
-}
+int zpci_write_block(volatile void __iomem *dst, const void *src,
+		     unsigned long len);
 
 static inline u8 zpci_get_max_write_size(u64 src, u64 dst, int len, int max)
 {
@@ -140,18 +136,15 @@ static inline int zpci_memcpy_fromio(void *dst,
 				     const volatile void __iomem *src,
 				     unsigned long n)
 {
-	struct zpci_iomap_entry *entry = &zpci_iomap_start[ZPCI_IDX(src)];
-	u64 req, offset = ZPCI_OFFSET(src);
 	int size, rc = 0;
 
 	while (n > 0) {
 		size = zpci_get_max_write_size((u64 __force) src,
 					       (u64) dst, n, 8);
-		req = ZPCI_CREATE_REQ(entry->fh, entry->bar, size);
-		rc = zpci_read_single(req, dst, offset, size);
+		rc = zpci_read_single(dst, src, size);
 		if (rc)
 			break;
-		offset += size;
+		src += size;
 		dst += size;
 		n -= size;
 	}
@@ -161,8 +154,6 @@ static inline int zpci_memcpy_fromio(void *dst,
 static inline int zpci_memcpy_toio(volatile void __iomem *dst,
 				   const void *src, unsigned long n)
 {
-	struct zpci_iomap_entry *entry = &zpci_iomap_start[ZPCI_IDX(dst)];
-	u64 req, offset = ZPCI_OFFSET(dst);
 	int size, rc = 0;
 
 	if (!src)
@@ -171,16 +162,14 @@ static inline int zpci_memcpy_toio(volatile void __iomem *dst,
 	while (n > 0) {
 		size = zpci_get_max_write_size((u64 __force) dst,
 					       (u64) src, n, 128);
-		req = ZPCI_CREATE_REQ(entry->fh, entry->bar, size);
-
 		if (size > 8) /* main path */
-			rc = zpci_write_block(req, src, offset);
+			rc = zpci_write_block(dst, src, size);
 		else
-			rc = zpci_write_single(req, src, offset, size);
+			rc = zpci_write_single(dst, src, size);
 		if (rc)
 			break;
-		offset += size;
 		src += size;
+		dst += size;
 		n -= size;
 	}
 	return rc;
diff --git a/arch/s390/include/asm/pgtable.h b/arch/s390/include/asm/pgtable.h
index 76dc344edb8c..9f0195d5fa16 100644
--- a/arch/s390/include/asm/pgtable.h
+++ b/arch/s390/include/asm/pgtable.h
@@ -238,7 +238,7 @@ static inline int is_module_addr(void *addr)
 #define _REGION_ENTRY_NOEXEC	0x100	/* region no-execute bit	    */
 #define _REGION_ENTRY_OFFSET	0xc0	/* region table offset		    */
 #define _REGION_ENTRY_INVALID	0x20	/* invalid region table entry	    */
-#define _REGION_ENTRY_TYPE_MASK	0x0c	/* region/segment table type mask   */
+#define _REGION_ENTRY_TYPE_MASK	0x0c	/* region table type mask	    */
 #define _REGION_ENTRY_TYPE_R1	0x0c	/* region first table type	    */
 #define _REGION_ENTRY_TYPE_R2	0x08	/* region second table type	    */
 #define _REGION_ENTRY_TYPE_R3	0x04	/* region third table type	    */
@@ -277,6 +277,7 @@ static inline int is_module_addr(void *addr)
 #define _SEGMENT_ENTRY_PROTECT	0x200	/* segment protection bit	    */
 #define _SEGMENT_ENTRY_NOEXEC	0x100	/* segment no-execute bit	    */
 #define _SEGMENT_ENTRY_INVALID	0x20	/* invalid segment table entry	    */
+#define _SEGMENT_ENTRY_TYPE_MASK 0x0c	/* segment table type mask	    */
 
 #define _SEGMENT_ENTRY		(0)
 #define _SEGMENT_ENTRY_EMPTY	(_SEGMENT_ENTRY_INVALID)
@@ -614,15 +615,9 @@ static inline int pgd_none(pgd_t pgd)
 
 static inline int pgd_bad(pgd_t pgd)
 {
-	/*
-	 * With dynamic page table levels the pgd can be a region table
-	 * entry or a segment table entry. Check for the bit that are
-	 * invalid for either table entry.
-	 */
-	unsigned long mask =
-		~_SEGMENT_ENTRY_ORIGIN & ~_REGION_ENTRY_INVALID &
-		~_REGION_ENTRY_TYPE_MASK & ~_REGION_ENTRY_LENGTH;
-	return (pgd_val(pgd) & mask) != 0;
+	if ((pgd_val(pgd) & _REGION_ENTRY_TYPE_MASK) < _REGION_ENTRY_TYPE_R1)
+		return 0;
+	return (pgd_val(pgd) & ~_REGION_ENTRY_BITS) != 0;
 }
 
 static inline unsigned long pgd_pfn(pgd_t pgd)
@@ -703,6 +698,8 @@ static inline int pmd_large(pmd_t pmd)
 
 static inline int pmd_bad(pmd_t pmd)
 {
+	if ((pmd_val(pmd) & _SEGMENT_ENTRY_TYPE_MASK) > 0)
+		return 1;
 	if (pmd_large(pmd))
 		return (pmd_val(pmd) & ~_SEGMENT_ENTRY_BITS_LARGE) != 0;
 	return (pmd_val(pmd) & ~_SEGMENT_ENTRY_BITS) != 0;
@@ -710,8 +707,12 @@ static inline int pmd_bad(pmd_t pmd)
 
 static inline int pud_bad(pud_t pud)
 {
-	if ((pud_val(pud) & _REGION_ENTRY_TYPE_MASK) < _REGION_ENTRY_TYPE_R3)
-		return pmd_bad(__pmd(pud_val(pud)));
+	unsigned long type = pud_val(pud) & _REGION_ENTRY_TYPE_MASK;
+
+	if (type > _REGION_ENTRY_TYPE_R3)
+		return 1;
+	if (type < _REGION_ENTRY_TYPE_R3)
+		return 0;
 	if (pud_large(pud))
 		return (pud_val(pud) & ~_REGION_ENTRY_BITS_LARGE) != 0;
 	return (pud_val(pud) & ~_REGION_ENTRY_BITS) != 0;
@@ -719,8 +720,12 @@ static inline int pud_bad(pud_t pud)
 
 static inline int p4d_bad(p4d_t p4d)
 {
-	if ((p4d_val(p4d) & _REGION_ENTRY_TYPE_MASK) < _REGION_ENTRY_TYPE_R2)
-		return pud_bad(__pud(p4d_val(p4d)));
+	unsigned long type = p4d_val(p4d) & _REGION_ENTRY_TYPE_MASK;
+
+	if (type > _REGION_ENTRY_TYPE_R2)
+		return 1;
+	if (type < _REGION_ENTRY_TYPE_R2)
+		return 0;
 	return (p4d_val(p4d) & ~_REGION_ENTRY_BITS) != 0;
 }
 
@@ -1204,41 +1209,78 @@ static inline pte_t mk_pte(struct page *page, pgprot_t pgprot)
 #define pmd_index(address) (((address) >> PMD_SHIFT) & (PTRS_PER_PMD-1))
 #define pte_index(address) (((address) >> PAGE_SHIFT) & (PTRS_PER_PTE-1))
 
-#define pgd_offset(mm, address) ((mm)->pgd + pgd_index(address))
-#define pgd_offset_k(address) pgd_offset(&init_mm, address)
-#define pgd_offset_raw(pgd, addr) ((pgd) + pgd_index(addr))
-
 #define pmd_deref(pmd) (pmd_val(pmd) & _SEGMENT_ENTRY_ORIGIN)
 #define pud_deref(pud) (pud_val(pud) & _REGION_ENTRY_ORIGIN)
 #define p4d_deref(pud) (p4d_val(pud) & _REGION_ENTRY_ORIGIN)
 #define pgd_deref(pgd) (pgd_val(pgd) & _REGION_ENTRY_ORIGIN)
 
-static inline p4d_t *p4d_offset(pgd_t *pgd, unsigned long address)
+/*
+ * The pgd_offset function *always* adds the index for the top-level
+ * region/segment table. This is done to get a sequence like the
+ * following to work:
+ *	pgdp = pgd_offset(current->mm, addr);
+ *	pgd = READ_ONCE(*pgdp);
+ *	p4dp = p4d_offset(&pgd, addr);
+ *	...
+ * The subsequent p4d_offset, pud_offset and pmd_offset functions
+ * only add an index if they dereferenced the pointer.
+ */
+static inline pgd_t *pgd_offset_raw(pgd_t *pgd, unsigned long address)
 {
-	p4d_t *p4d = (p4d_t *) pgd;
+	unsigned long rste;
+	unsigned int shift;
 
-	if ((pgd_val(*pgd) & _REGION_ENTRY_TYPE_MASK) == _REGION_ENTRY_TYPE_R1)
-		p4d = (p4d_t *) pgd_deref(*pgd);
-	return p4d + p4d_index(address);
+	/* Get the first entry of the top level table */
+	rste = pgd_val(*pgd);
+	/* Pick up the shift from the table type of the first entry */
+	shift = ((rste & _REGION_ENTRY_TYPE_MASK) >> 2) * 11 + 20;
+	return pgd + ((address >> shift) & (PTRS_PER_PGD - 1));
 }
 
-static inline pud_t *pud_offset(p4d_t *p4d, unsigned long address)
+#define pgd_offset(mm, address) pgd_offset_raw(READ_ONCE((mm)->pgd), address)
+#define pgd_offset_k(address) pgd_offset(&init_mm, address)
+
+static inline p4d_t *p4d_offset(pgd_t *pgd, unsigned long address)
 {
-	pud_t *pud = (pud_t *) p4d;
+	if ((pgd_val(*pgd) & _REGION_ENTRY_TYPE_MASK) >= _REGION_ENTRY_TYPE_R1)
+		return (p4d_t *) pgd_deref(*pgd) + p4d_index(address);
+	return (p4d_t *) pgd;
+}
 
-	if ((p4d_val(*p4d) & _REGION_ENTRY_TYPE_MASK) == _REGION_ENTRY_TYPE_R2)
-		pud = (pud_t *) p4d_deref(*p4d);
-	return pud + pud_index(address);
+static inline pud_t *pud_offset(p4d_t *p4d, unsigned long address)
+{
+	if ((p4d_val(*p4d) & _REGION_ENTRY_TYPE_MASK) >= _REGION_ENTRY_TYPE_R2)
+		return (pud_t *) p4d_deref(*p4d) + pud_index(address);
+	return (pud_t *) p4d;
 }
 
 static inline pmd_t *pmd_offset(pud_t *pud, unsigned long address)
 {
-	pmd_t *pmd = (pmd_t *) pud;
+	if ((pud_val(*pud) & _REGION_ENTRY_TYPE_MASK) >= _REGION_ENTRY_TYPE_R3)
+		return (pmd_t *) pud_deref(*pud) + pmd_index(address);
+	return (pmd_t *) pud;
+}
 
-	if ((pud_val(*pud) & _REGION_ENTRY_TYPE_MASK) == _REGION_ENTRY_TYPE_R3)
-		pmd = (pmd_t *) pud_deref(*pud);
-	return pmd + pmd_index(address);
+static inline pte_t *pte_offset(pmd_t *pmd, unsigned long address)
+{
+	return (pte_t *) pmd_deref(*pmd) + pte_index(address);
+}
+
+#define pte_offset_kernel(pmd, address) pte_offset(pmd, address)
+#define pte_offset_map(pmd, address) pte_offset_kernel(pmd, address)
+#define pte_unmap(pte) do { } while (0)
+
+static inline bool gup_fast_permitted(unsigned long start, int nr_pages)
+{
+	unsigned long len, end;
+
+	len = (unsigned long) nr_pages << PAGE_SHIFT;
+	end = start + len;
+	if (end < start)
+		return false;
+	return end <= current->mm->context.asce_limit;
 }
+#define gup_fast_permitted gup_fast_permitted
 
 #define pfn_pte(pfn,pgprot) mk_pte_phys(__pa((pfn) << PAGE_SHIFT),(pgprot))
 #define pte_pfn(x) (pte_val(x) >> PAGE_SHIFT)
@@ -1249,12 +1291,6 @@ static inline pmd_t *pmd_offset(pud_t *pud, unsigned long address)
 #define p4d_page(p4d) pfn_to_page(p4d_pfn(p4d))
 #define pgd_page(pgd) pfn_to_page(pgd_pfn(pgd))
 
-/* Find an entry in the lowest level page table.. */
-#define pte_offset(pmd, addr) ((pte_t *) pmd_deref(*(pmd)) + pte_index(addr))
-#define pte_offset_kernel(pmd, address) pte_offset(pmd,address)
-#define pte_offset_map(pmd, address) pte_offset_kernel(pmd, address)
-#define pte_unmap(pte) do { } while (0)
-
 static inline pmd_t pmd_wrprotect(pmd_t pmd)
 {
 	pmd_val(pmd) &= ~_SEGMENT_ENTRY_WRITE;
diff --git a/arch/s390/include/asm/processor.h b/arch/s390/include/asm/processor.h
index 81038ab357ce..b0fcbc37b637 100644
--- a/arch/s390/include/asm/processor.h
+++ b/arch/s390/include/asm/processor.h
@@ -156,25 +156,6 @@ struct thread_struct {
 
 typedef struct thread_struct thread_struct;
 
-/*
- * Stack layout of a C stack frame.
- */
-#ifndef __PACK_STACK
-struct stack_frame {
-	unsigned long back_chain;
-	unsigned long empty1[5];
-	unsigned long gprs[10];
-	unsigned int  empty2[8];
-};
-#else
-struct stack_frame {
-	unsigned long empty1[5];
-	unsigned int  empty2[8];
-	unsigned long gprs[10];
-	unsigned long back_chain;
-};
-#endif
-
 #define ARCH_MIN_TASKALIGN	8
 
 #define INIT_THREAD {							\
@@ -206,11 +187,7 @@ struct mm_struct;
 struct seq_file;
 struct pt_regs;
 
-typedef int (*dump_trace_func_t)(void *data, unsigned long address, int reliable);
-void dump_trace(dump_trace_func_t func, void *data,
-		struct task_struct *task, unsigned long sp);
 void show_registers(struct pt_regs *regs);
-
 void show_cacheinfo(struct seq_file *m);
 
 /* Free all resources held by a thread. */
@@ -244,55 +221,6 @@ static __no_kasan_or_inline unsigned short stap(void)
 	return cpu_address;
 }
 
-#define CALL_ARGS_0()							\
-	register unsigned long r2 asm("2")
-#define CALL_ARGS_1(arg1)						\
-	register unsigned long r2 asm("2") = (unsigned long)(arg1)
-#define CALL_ARGS_2(arg1, arg2)						\
-	CALL_ARGS_1(arg1);						\
-	register unsigned long r3 asm("3") = (unsigned long)(arg2)
-#define CALL_ARGS_3(arg1, arg2, arg3)					\
-	CALL_ARGS_2(arg1, arg2);					\
-	register unsigned long r4 asm("4") = (unsigned long)(arg3)
-#define CALL_ARGS_4(arg1, arg2, arg3, arg4)				\
-	CALL_ARGS_3(arg1, arg2, arg3);					\
-	register unsigned long r4 asm("5") = (unsigned long)(arg4)
-#define CALL_ARGS_5(arg1, arg2, arg3, arg4, arg5)			\
-	CALL_ARGS_4(arg1, arg2, arg3, arg4);				\
-	register unsigned long r4 asm("6") = (unsigned long)(arg5)
-
-#define CALL_FMT_0
-#define CALL_FMT_1 CALL_FMT_0, "0" (r2)
-#define CALL_FMT_2 CALL_FMT_1, "d" (r3)
-#define CALL_FMT_3 CALL_FMT_2, "d" (r4)
-#define CALL_FMT_4 CALL_FMT_3, "d" (r5)
-#define CALL_FMT_5 CALL_FMT_4, "d" (r6)
-
-#define CALL_CLOBBER_5 "0", "1", "14", "cc", "memory"
-#define CALL_CLOBBER_4 CALL_CLOBBER_5
-#define CALL_CLOBBER_3 CALL_CLOBBER_4, "5"
-#define CALL_CLOBBER_2 CALL_CLOBBER_3, "4"
-#define CALL_CLOBBER_1 CALL_CLOBBER_2, "3"
-#define CALL_CLOBBER_0 CALL_CLOBBER_1
-
-#define CALL_ON_STACK(fn, stack, nr, args...)				\
-({									\
-	CALL_ARGS_##nr(args);						\
-	unsigned long prev;						\
-									\
-	asm volatile(							\
-		"	la	%[_prev],0(15)\n"			\
-		"	la	15,0(%[_stack])\n"			\
-		"	stg	%[_prev],%[_bc](15)\n"			\
-		"	brasl	14,%[_fn]\n"				\
-		"	la	15,0(%[_prev])\n"			\
-		: "+&d" (r2), [_prev] "=&a" (prev)			\
-		: [_stack] "a" (stack),					\
-		  [_bc] "i" (offsetof(struct stack_frame, back_chain)),	\
-		  [_fn] "X" (fn) CALL_FMT_##nr : CALL_CLOBBER_##nr);	\
-	r2;								\
-})
-
 /*
  * Give up the time slice of the virtual PU.
  */
@@ -339,10 +267,10 @@ static __no_kasan_or_inline void __load_psw_mask(unsigned long mask)
 
 	asm volatile(
 		"	larl	%0,1f\n"
-		"	stg	%0,%O1+8(%R1)\n"
-		"	lpswe	%1\n"
+		"	stg	%0,%1\n"
+		"	lpswe	%2\n"
 		"1:"
-		: "=&d" (addr), "=Q" (psw) : "Q" (psw) : "memory", "cc");
+		: "=&d" (addr), "=Q" (psw.addr) : "Q" (psw) : "memory", "cc");
 }
 
 /*
@@ -387,12 +315,12 @@ void enabled_wait(void);
 /*
  * Function to drop a processor into disabled wait state
  */
-static inline void __noreturn disabled_wait(unsigned long code)
+static inline void __noreturn disabled_wait(void)
 {
 	psw_t psw;
 
 	psw.mask = PSW_MASK_BASE | PSW_MASK_WAIT | PSW_MASK_BA | PSW_MASK_EA;
-	psw.addr = code;
+	psw.addr = _THIS_IP_;
 	__load_psw(psw);
 	while (1);
 }
diff --git a/arch/s390/include/asm/sclp.h b/arch/s390/include/asm/sclp.h
index ef4c9dec06a4..f577c5f6031a 100644
--- a/arch/s390/include/asm/sclp.h
+++ b/arch/s390/include/asm/sclp.h
@@ -79,6 +79,9 @@ struct sclp_info {
 	unsigned char has_kss : 1;
 	unsigned char has_gisaf : 1;
 	unsigned char has_diag318 : 1;
+	unsigned char has_sipl : 1;
+	unsigned char has_sipl_g2 : 1;
+	unsigned char has_dirq : 1;
 	unsigned int ibc;
 	unsigned int mtid;
 	unsigned int mtid_cp;
diff --git a/arch/s390/include/asm/sections.h b/arch/s390/include/asm/sections.h
index 7afe4620685c..42de04ad9c07 100644
--- a/arch/s390/include/asm/sections.h
+++ b/arch/s390/include/asm/sections.h
@@ -2,8 +2,20 @@
 #ifndef _S390_SECTIONS_H
 #define _S390_SECTIONS_H
 
+#define arch_is_kernel_initmem_freed arch_is_kernel_initmem_freed
+
 #include <asm-generic/sections.h>
 
+extern bool initmem_freed;
+
+static inline int arch_is_kernel_initmem_freed(unsigned long addr)
+{
+	if (!initmem_freed)
+		return 0;
+	return addr >= (unsigned long)__init_begin &&
+	       addr < (unsigned long)__init_end;
+}
+
 /*
  * .boot.data section contains variables "shared" between the decompressor and
  * the decompressed kernel. The decompressor will store values in them, and
@@ -16,4 +28,14 @@
  */
 #define __bootdata(var) __section(.boot.data.var) var
 
+/*
+ * .boot.preserved.data is similar to .boot.data, but it is not part of the
+ * .init section and thus will be preserved for later use in the decompressed
+ * kernel.
+ */
+#define __bootdata_preserved(var) __section(.boot.preserved.data.var) var
+
+extern unsigned long __sdma, __edma;
+extern unsigned long __stext_dma, __etext_dma;
+
 #endif
diff --git a/arch/s390/include/asm/setup.h b/arch/s390/include/asm/setup.h
index efda97804aa4..925889d360c1 100644
--- a/arch/s390/include/asm/setup.h
+++ b/arch/s390/include/asm/setup.h
@@ -12,7 +12,10 @@
 #define EP_OFFSET		0x10008
 #define EP_STRING		"S390EP"
 #define PARMAREA		0x10400
-#define PARMAREA_END		0x11000
+#define EARLY_SCCB_OFFSET	0x11000
+#define HEAD_END		0x12000
+
+#define EARLY_SCCB_SIZE		PAGE_SIZE
 
 /*
  * Machine features detected in early.c
@@ -65,6 +68,16 @@
 #define OLDMEM_SIZE	(*(unsigned long *)  (OLDMEM_SIZE_OFFSET))
 #define COMMAND_LINE	((char *)	     (COMMAND_LINE_OFFSET))
 
+struct parmarea {
+	unsigned long ipl_device;			/* 0x10400 */
+	unsigned long initrd_start;			/* 0x10408 */
+	unsigned long initrd_size;			/* 0x10410 */
+	unsigned long oldmem_base;			/* 0x10418 */
+	unsigned long oldmem_size;			/* 0x10420 */
+	char pad1[0x10480 - 0x10428];			/* 0x10428 - 0x10480 */
+	char command_line[ARCH_COMMAND_LINE_SIZE];	/* 0x10480 */
+};
+
 extern int noexec_disabled;
 extern int memory_end_set;
 extern unsigned long memory_end;
@@ -134,6 +147,12 @@ extern void (*_machine_restart)(char *command);
 extern void (*_machine_halt)(void);
 extern void (*_machine_power_off)(void);
 
+extern unsigned long __kaslr_offset;
+static inline unsigned long kaslr_offset(void)
+{
+	return __kaslr_offset;
+}
+
 #else /* __ASSEMBLY__ */
 
 #define IPL_DEVICE	(IPL_DEVICE_OFFSET)
diff --git a/arch/s390/include/asm/stacktrace.h b/arch/s390/include/asm/stacktrace.h
new file mode 100644
index 000000000000..49634bfbecdd
--- /dev/null
+++ b/arch/s390/include/asm/stacktrace.h
@@ -0,0 +1,114 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _ASM_S390_STACKTRACE_H
+#define _ASM_S390_STACKTRACE_H
+
+#include <linux/uaccess.h>
+#include <linux/ptrace.h>
+#include <asm/switch_to.h>
+
+enum stack_type {
+	STACK_TYPE_UNKNOWN,
+	STACK_TYPE_TASK,
+	STACK_TYPE_IRQ,
+	STACK_TYPE_NODAT,
+	STACK_TYPE_RESTART,
+};
+
+struct stack_info {
+	enum stack_type type;
+	unsigned long begin, end;
+};
+
+const char *stack_type_name(enum stack_type type);
+int get_stack_info(unsigned long sp, struct task_struct *task,
+		   struct stack_info *info, unsigned long *visit_mask);
+
+static inline bool on_stack(struct stack_info *info,
+			    unsigned long addr, size_t len)
+{
+	if (info->type == STACK_TYPE_UNKNOWN)
+		return false;
+	if (addr + len < addr)
+		return false;
+	return addr >= info->begin && addr + len < info->end;
+}
+
+static inline unsigned long get_stack_pointer(struct task_struct *task,
+					      struct pt_regs *regs)
+{
+	if (regs)
+		return (unsigned long) kernel_stack_pointer(regs);
+	if (task == current)
+		return current_stack_pointer();
+	return (unsigned long) task->thread.ksp;
+}
+
+/*
+ * Stack layout of a C stack frame.
+ */
+#ifndef __PACK_STACK
+struct stack_frame {
+	unsigned long back_chain;
+	unsigned long empty1[5];
+	unsigned long gprs[10];
+	unsigned int  empty2[8];
+};
+#else
+struct stack_frame {
+	unsigned long empty1[5];
+	unsigned int  empty2[8];
+	unsigned long gprs[10];
+	unsigned long back_chain;
+};
+#endif
+
+#define CALL_ARGS_0()							\
+	register unsigned long r2 asm("2")
+#define CALL_ARGS_1(arg1)						\
+	register unsigned long r2 asm("2") = (unsigned long)(arg1)
+#define CALL_ARGS_2(arg1, arg2)						\
+	CALL_ARGS_1(arg1);						\
+	register unsigned long r3 asm("3") = (unsigned long)(arg2)
+#define CALL_ARGS_3(arg1, arg2, arg3)					\
+	CALL_ARGS_2(arg1, arg2);					\
+	register unsigned long r4 asm("4") = (unsigned long)(arg3)
+#define CALL_ARGS_4(arg1, arg2, arg3, arg4)				\
+	CALL_ARGS_3(arg1, arg2, arg3);					\
+	register unsigned long r4 asm("5") = (unsigned long)(arg4)
+#define CALL_ARGS_5(arg1, arg2, arg3, arg4, arg5)			\
+	CALL_ARGS_4(arg1, arg2, arg3, arg4);				\
+	register unsigned long r4 asm("6") = (unsigned long)(arg5)
+
+#define CALL_FMT_0 "=&d" (r2) :
+#define CALL_FMT_1 "+&d" (r2) :
+#define CALL_FMT_2 CALL_FMT_1 "d" (r3),
+#define CALL_FMT_3 CALL_FMT_2 "d" (r4),
+#define CALL_FMT_4 CALL_FMT_3 "d" (r5),
+#define CALL_FMT_5 CALL_FMT_4 "d" (r6),
+
+#define CALL_CLOBBER_5 "0", "1", "14", "cc", "memory"
+#define CALL_CLOBBER_4 CALL_CLOBBER_5
+#define CALL_CLOBBER_3 CALL_CLOBBER_4, "5"
+#define CALL_CLOBBER_2 CALL_CLOBBER_3, "4"
+#define CALL_CLOBBER_1 CALL_CLOBBER_2, "3"
+#define CALL_CLOBBER_0 CALL_CLOBBER_1
+
+#define CALL_ON_STACK(fn, stack, nr, args...)				\
+({									\
+	CALL_ARGS_##nr(args);						\
+	unsigned long prev;						\
+									\
+	asm volatile(							\
+		"	la	%[_prev],0(15)\n"			\
+		"	la	15,0(%[_stack])\n"			\
+		"	stg	%[_prev],%[_bc](15)\n"			\
+		"	brasl	14,%[_fn]\n"				\
+		"	la	15,0(%[_prev])\n"			\
+		: [_prev] "=&a" (prev), CALL_FMT_##nr			\
+		  [_stack] "a" (stack),					\
+		  [_bc] "i" (offsetof(struct stack_frame, back_chain)),	\
+		  [_fn] "X" (fn) : CALL_CLOBBER_##nr);			\
+	r2;								\
+})
+
+#endif /* _ASM_S390_STACKTRACE_H */
diff --git a/arch/s390/include/asm/syscall.h b/arch/s390/include/asm/syscall.h
index 96f9a9151fde..ab3407aa4fd8 100644
--- a/arch/s390/include/asm/syscall.h
+++ b/arch/s390/include/asm/syscall.h
@@ -14,13 +14,8 @@
 #include <linux/err.h>
 #include <asm/ptrace.h>
 
-/*
- * The syscall table always contains 32 bit pointers since we know that the
- * address of the function to be called is (way) below 4GB.  So the "int"
- * type here is what we want [need] for both 32 bit and 64 bit systems.
- */
-extern const unsigned int sys_call_table[];
-extern const unsigned int sys_call_table_emu[];
+extern const unsigned long sys_call_table[];
+extern const unsigned long sys_call_table_emu[];
 
 static inline long syscall_get_nr(struct task_struct *task,
 				  struct pt_regs *regs)
@@ -56,40 +51,32 @@ static inline void syscall_set_return_value(struct task_struct *task,
 
 static inline void syscall_get_arguments(struct task_struct *task,
 					 struct pt_regs *regs,
-					 unsigned int i, unsigned int n,
 					 unsigned long *args)
 {
 	unsigned long mask = -1UL;
+	unsigned int n = 6;
 
-	/*
-	 * No arguments for this syscall, there's nothing to do.
-	 */
-	if (!n)
-		return;
-
-	BUG_ON(i + n > 6);
 #ifdef CONFIG_COMPAT
 	if (test_tsk_thread_flag(task, TIF_31BIT))
 		mask = 0xffffffff;
 #endif
 	while (n-- > 0)
-		if (i + n > 0)
-			args[n] = regs->gprs[2 + i + n] & mask;
-	if (i == 0)
-		args[0] = regs->orig_gpr2 & mask;
+		if (n > 0)
+			args[n] = regs->gprs[2 + n] & mask;
+
+	args[0] = regs->orig_gpr2 & mask;
 }
 
 static inline void syscall_set_arguments(struct task_struct *task,
 					 struct pt_regs *regs,
-					 unsigned int i, unsigned int n,
 					 const unsigned long *args)
 {
-	BUG_ON(i + n > 6);
+	unsigned int n = 6;
+
 	while (n-- > 0)
-		if (i + n > 0)
-			regs->gprs[2 + i + n] = args[n];
-	if (i == 0)
-		regs->orig_gpr2 = args[0];
+		if (n > 0)
+			regs->gprs[2 + n] = args[n];
+	regs->orig_gpr2 = args[0];
 }
 
 static inline int syscall_get_arch(void)
diff --git a/arch/s390/include/asm/syscall_wrapper.h b/arch/s390/include/asm/syscall_wrapper.h
index 5596c5c625d2..3c3d6fe8e2f0 100644
--- a/arch/s390/include/asm/syscall_wrapper.h
+++ b/arch/s390/include/asm/syscall_wrapper.h
@@ -119,8 +119,8 @@
 		      "Type aliasing is used to sanitize syscall arguments");\
 	asmlinkage long __s390x_sys##name(__MAP(x,__SC_DECL,__VA_ARGS__))	\
 		__attribute__((alias(__stringify(__se_sys##name))));		\
-	ALLOW_ERROR_INJECTION(__s390x_sys##name, ERRNO);				\
-	static long __se_sys##name(__MAP(x,__SC_LONG,__VA_ARGS__));		\
+	ALLOW_ERROR_INJECTION(__s390x_sys##name, ERRNO);			\
+	long __se_sys##name(__MAP(x,__SC_LONG,__VA_ARGS__));			\
 	static inline long __do_sys##name(__MAP(x,__SC_DECL,__VA_ARGS__));	\
 	__S390_SYS_STUBx(x, name, __VA_ARGS__)					\
 	asmlinkage long __se_sys##name(__MAP(x,__SC_LONG,__VA_ARGS__))		\
diff --git a/arch/s390/include/asm/tlb.h b/arch/s390/include/asm/tlb.h
index b31c779cf581..aa406c05a350 100644
--- a/arch/s390/include/asm/tlb.h
+++ b/arch/s390/include/asm/tlb.h
@@ -22,98 +22,39 @@
  * Pages used for the page tables is a different story. FIXME: more
  */
 
-#include <linux/mm.h>
-#include <linux/pagemap.h>
-#include <linux/swap.h>
-#include <asm/processor.h>
-#include <asm/pgalloc.h>
-#include <asm/tlbflush.h>
-
-struct mmu_gather {
-	struct mm_struct *mm;
-	struct mmu_table_batch *batch;
-	unsigned int fullmm;
-	unsigned long start, end;
-};
-
-struct mmu_table_batch {
-	struct rcu_head		rcu;
-	unsigned int		nr;
-	void			*tables[0];
-};
-
-#define MAX_TABLE_BATCH		\
-	((PAGE_SIZE - sizeof(struct mmu_table_batch)) / sizeof(void *))
-
-extern void tlb_table_flush(struct mmu_gather *tlb);
-extern void tlb_remove_table(struct mmu_gather *tlb, void *table);
-
-static inline void
-arch_tlb_gather_mmu(struct mmu_gather *tlb, struct mm_struct *mm,
-			unsigned long start, unsigned long end)
-{
-	tlb->mm = mm;
-	tlb->start = start;
-	tlb->end = end;
-	tlb->fullmm = !(start | (end+1));
-	tlb->batch = NULL;
-}
-
-static inline void tlb_flush_mmu_tlbonly(struct mmu_gather *tlb)
-{
-	__tlb_flush_mm_lazy(tlb->mm);
-}
-
-static inline void tlb_flush_mmu_free(struct mmu_gather *tlb)
-{
-	tlb_table_flush(tlb);
-}
-
+void __tlb_remove_table(void *_table);
+static inline void tlb_flush(struct mmu_gather *tlb);
+static inline bool __tlb_remove_page_size(struct mmu_gather *tlb,
+					  struct page *page, int page_size);
 
-static inline void tlb_flush_mmu(struct mmu_gather *tlb)
-{
-	tlb_flush_mmu_tlbonly(tlb);
-	tlb_flush_mmu_free(tlb);
-}
+#define tlb_start_vma(tlb, vma)			do { } while (0)
+#define tlb_end_vma(tlb, vma)			do { } while (0)
 
-static inline void
-arch_tlb_finish_mmu(struct mmu_gather *tlb,
-		unsigned long start, unsigned long end, bool force)
-{
-	if (force) {
-		tlb->start = start;
-		tlb->end = end;
-	}
+#define tlb_flush tlb_flush
+#define pte_free_tlb pte_free_tlb
+#define pmd_free_tlb pmd_free_tlb
+#define p4d_free_tlb p4d_free_tlb
+#define pud_free_tlb pud_free_tlb
 
-	tlb_flush_mmu(tlb);
-}
+#include <asm/pgalloc.h>
+#include <asm/tlbflush.h>
+#include <asm-generic/tlb.h>
 
 /*
  * Release the page cache reference for a pte removed by
  * tlb_ptep_clear_flush. In both flush modes the tlb for a page cache page
  * has already been freed, so just do free_page_and_swap_cache.
  */
-static inline bool __tlb_remove_page(struct mmu_gather *tlb, struct page *page)
-{
-	free_page_and_swap_cache(page);
-	return false; /* avoid calling tlb_flush_mmu */
-}
-
-static inline void tlb_remove_page(struct mmu_gather *tlb, struct page *page)
-{
-	free_page_and_swap_cache(page);
-}
-
 static inline bool __tlb_remove_page_size(struct mmu_gather *tlb,
 					  struct page *page, int page_size)
 {
-	return __tlb_remove_page(tlb, page);
+	free_page_and_swap_cache(page);
+	return false;
 }
 
-static inline void tlb_remove_page_size(struct mmu_gather *tlb,
-					struct page *page, int page_size)
+static inline void tlb_flush(struct mmu_gather *tlb)
 {
-	return tlb_remove_page(tlb, page);
+	__tlb_flush_mm_lazy(tlb->mm);
 }
 
 /*
@@ -121,8 +62,17 @@ static inline void tlb_remove_page_size(struct mmu_gather *tlb,
  * page table from the tlb.
  */
 static inline void pte_free_tlb(struct mmu_gather *tlb, pgtable_t pte,
-				unsigned long address)
+                                unsigned long address)
 {
+	__tlb_adjust_range(tlb, address, PAGE_SIZE);
+	tlb->mm->context.flush_mm = 1;
+	tlb->freed_tables = 1;
+	tlb->cleared_ptes = 1;
+	/*
+	 * page_table_free_rcu takes care of the allocation bit masks
+	 * of the 2K table fragments in the 4K page table page,
+	 * then calls tlb_remove_table.
+	 */
 	page_table_free_rcu(tlb, (unsigned long *) pte, address);
 }
 
@@ -139,6 +89,10 @@ static inline void pmd_free_tlb(struct mmu_gather *tlb, pmd_t *pmd,
 	if (mm_pmd_folded(tlb->mm))
 		return;
 	pgtable_pmd_page_dtor(virt_to_page(pmd));
+	__tlb_adjust_range(tlb, address, PAGE_SIZE);
+	tlb->mm->context.flush_mm = 1;
+	tlb->freed_tables = 1;
+	tlb->cleared_puds = 1;
 	tlb_remove_table(tlb, pmd);
 }
 
@@ -154,6 +108,10 @@ static inline void p4d_free_tlb(struct mmu_gather *tlb, p4d_t *p4d,
 {
 	if (mm_p4d_folded(tlb->mm))
 		return;
+	__tlb_adjust_range(tlb, address, PAGE_SIZE);
+	tlb->mm->context.flush_mm = 1;
+	tlb->freed_tables = 1;
+	tlb->cleared_p4ds = 1;
 	tlb_remove_table(tlb, p4d);
 }
 
@@ -169,21 +127,11 @@ static inline void pud_free_tlb(struct mmu_gather *tlb, pud_t *pud,
 {
 	if (mm_pud_folded(tlb->mm))
 		return;
+	tlb->mm->context.flush_mm = 1;
+	tlb->freed_tables = 1;
+	tlb->cleared_puds = 1;
 	tlb_remove_table(tlb, pud);
 }
 
-#define tlb_start_vma(tlb, vma)			do { } while (0)
-#define tlb_end_vma(tlb, vma)			do { } while (0)
-#define tlb_remove_tlb_entry(tlb, ptep, addr)	do { } while (0)
-#define tlb_remove_pmd_tlb_entry(tlb, pmdp, addr)	do { } while (0)
-#define tlb_migrate_finish(mm)			do { } while (0)
-#define tlb_remove_huge_tlb_entry(h, tlb, ptep, address)	\
-	tlb_remove_tlb_entry(tlb, ptep, address)
-
-#define tlb_remove_check_page_size_change tlb_remove_check_page_size_change
-static inline void tlb_remove_check_page_size_change(struct mmu_gather *tlb,
-						     unsigned int page_size)
-{
-}
 
 #endif /* _S390_TLB_H */
diff --git a/arch/s390/include/asm/uaccess.h b/arch/s390/include/asm/uaccess.h
index 007fcb9aeeb8..bd2fd9a7821d 100644
--- a/arch/s390/include/asm/uaccess.h
+++ b/arch/s390/include/asm/uaccess.h
@@ -55,8 +55,10 @@ raw_copy_from_user(void *to, const void __user *from, unsigned long n);
 unsigned long __must_check
 raw_copy_to_user(void __user *to, const void *from, unsigned long n);
 
+#ifndef CONFIG_KASAN
 #define INLINE_COPY_FROM_USER
 #define INLINE_COPY_TO_USER
+#endif
 
 #ifdef CONFIG_HAVE_MARCH_Z10_FEATURES
 
diff --git a/arch/s390/include/asm/unwind.h b/arch/s390/include/asm/unwind.h
new file mode 100644
index 000000000000..6eb2ef105d87
--- /dev/null
+++ b/arch/s390/include/asm/unwind.h
@@ -0,0 +1,101 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _ASM_S390_UNWIND_H
+#define _ASM_S390_UNWIND_H
+
+#include <linux/sched.h>
+#include <linux/ftrace.h>
+#include <asm/ptrace.h>
+#include <asm/stacktrace.h>
+
+/*
+ * To use the stack unwinder it has to be initialized with unwind_start.
+ * There four combinations for task and regs:
+ * 1) task==NULL, regs==NULL: the unwind starts for the task that is currently
+ *    running, sp/ip picked up from the CPU registers
+ * 2) task==NULL, regs!=NULL: the unwind starts from the sp/ip found in
+ *    the struct pt_regs of an interrupt frame for the current task
+ * 3) task!=NULL, regs==NULL: the unwind starts for an inactive task with
+ *    the sp picked up from task->thread.ksp and the ip picked up from the
+ *    return address stored by __switch_to
+ * 4) task!=NULL, regs!=NULL: the sp/ip are picked up from the interrupt
+ *    frame 'regs' of a inactive task
+ * If 'first_frame' is not zero unwind_start skips unwind frames until it
+ * reaches the specified stack pointer.
+ * The end of the unwinding is indicated with unwind_done, this can be true
+ * right after unwind_start, e.g. with first_frame!=0 that can not be found.
+ * unwind_next_frame skips to the next frame.
+ * Once the unwind is completed unwind_error() can be used to check if there
+ * has been a situation where the unwinder could not correctly understand
+ * the tasks call chain.
+ */
+
+struct unwind_state {
+	struct stack_info stack_info;
+	unsigned long stack_mask;
+	struct task_struct *task;
+	struct pt_regs *regs;
+	unsigned long sp, ip;
+	int graph_idx;
+	bool reliable;
+	bool error;
+};
+
+void __unwind_start(struct unwind_state *state, struct task_struct *task,
+		    struct pt_regs *regs, unsigned long first_frame);
+bool unwind_next_frame(struct unwind_state *state);
+unsigned long unwind_get_return_address(struct unwind_state *state);
+
+static inline bool unwind_done(struct unwind_state *state)
+{
+	return state->stack_info.type == STACK_TYPE_UNKNOWN;
+}
+
+static inline bool unwind_error(struct unwind_state *state)
+{
+	return state->error;
+}
+
+static inline void unwind_start(struct unwind_state *state,
+				struct task_struct *task,
+				struct pt_regs *regs,
+				unsigned long sp)
+{
+	sp = sp ? : get_stack_pointer(task, regs);
+	__unwind_start(state, task, regs, sp);
+}
+
+static inline struct pt_regs *unwind_get_entry_regs(struct unwind_state *state)
+{
+	return unwind_done(state) ? NULL : state->regs;
+}
+
+#define unwind_for_each_frame(state, task, regs, first_frame)	\
+	for (unwind_start(state, task, regs, first_frame);	\
+	     !unwind_done(state);				\
+	     unwind_next_frame(state))
+
+static inline void unwind_init(void) {}
+static inline void unwind_module_init(struct module *mod, void *orc_ip,
+				      size_t orc_ip_size, void *orc,
+				      size_t orc_size) {}
+
+#ifdef CONFIG_KASAN
+/*
+ * This disables KASAN checking when reading a value from another task's stack,
+ * since the other task could be running on another CPU and could have poisoned
+ * the stack in the meantime.
+ */
+#define READ_ONCE_TASK_STACK(task, x)			\
+({							\
+	unsigned long val;				\
+	if (task == current)				\
+		val = READ_ONCE(x);			\
+	else						\
+		val = READ_ONCE_NOCHECK(x);		\
+	val;						\
+})
+#else
+#define READ_ONCE_TASK_STACK(task, x) READ_ONCE(x)
+#endif
+
+#endif /* _ASM_S390_UNWIND_H */
diff --git a/arch/s390/include/asm/uv.h b/arch/s390/include/asm/uv.h
new file mode 100644
index 000000000000..ef3c00b049ab
--- /dev/null
+++ b/arch/s390/include/asm/uv.h
@@ -0,0 +1,132 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Ultravisor Interfaces
+ *
+ * Copyright IBM Corp. 2019
+ *
+ * Author(s):
+ *	Vasily Gorbik <gor@linux.ibm.com>
+ *	Janosch Frank <frankja@linux.ibm.com>
+ */
+#ifndef _ASM_S390_UV_H
+#define _ASM_S390_UV_H
+
+#include <linux/types.h>
+#include <linux/errno.h>
+#include <linux/bug.h>
+#include <asm/page.h>
+
+#define UVC_RC_EXECUTED		0x0001
+#define UVC_RC_INV_CMD		0x0002
+#define UVC_RC_INV_STATE	0x0003
+#define UVC_RC_INV_LEN		0x0005
+#define UVC_RC_NO_RESUME	0x0007
+
+#define UVC_CMD_QUI			0x0001
+#define UVC_CMD_SET_SHARED_ACCESS	0x1000
+#define UVC_CMD_REMOVE_SHARED_ACCESS	0x1001
+
+/* Bits in installed uv calls */
+enum uv_cmds_inst {
+	BIT_UVC_CMD_QUI = 0,
+	BIT_UVC_CMD_SET_SHARED_ACCESS = 8,
+	BIT_UVC_CMD_REMOVE_SHARED_ACCESS = 9,
+};
+
+struct uv_cb_header {
+	u16 len;
+	u16 cmd;	/* Command Code */
+	u16 rc;		/* Response Code */
+	u16 rrc;	/* Return Reason Code */
+} __packed __aligned(8);
+
+struct uv_cb_qui {
+	struct uv_cb_header header;
+	u64 reserved08;
+	u64 inst_calls_list[4];
+	u64 reserved30[15];
+} __packed __aligned(8);
+
+struct uv_cb_share {
+	struct uv_cb_header header;
+	u64 reserved08[3];
+	u64 paddr;
+	u64 reserved28;
+} __packed __aligned(8);
+
+static inline int uv_call(unsigned long r1, unsigned long r2)
+{
+	int cc;
+
+	asm volatile(
+		"0:	.insn rrf,0xB9A40000,%[r1],%[r2],0,0\n"
+		"		brc	3,0b\n"
+		"		ipm	%[cc]\n"
+		"		srl	%[cc],28\n"
+		: [cc] "=d" (cc)
+		: [r1] "a" (r1), [r2] "a" (r2)
+		: "memory", "cc");
+	return cc;
+}
+
+#ifdef CONFIG_PROTECTED_VIRTUALIZATION_GUEST
+extern int prot_virt_guest;
+
+static inline int is_prot_virt_guest(void)
+{
+	return prot_virt_guest;
+}
+
+static inline int share(unsigned long addr, u16 cmd)
+{
+	struct uv_cb_share uvcb = {
+		.header.cmd = cmd,
+		.header.len = sizeof(uvcb),
+		.paddr = addr
+	};
+
+	if (!is_prot_virt_guest())
+		return -ENOTSUPP;
+	/*
+	 * Sharing is page wise, if we encounter addresses that are
+	 * not page aligned, we assume something went wrong. If
+	 * malloced structs are passed to this function, we could leak
+	 * data to the hypervisor.
+	 */
+	BUG_ON(addr & ~PAGE_MASK);
+
+	if (!uv_call(0, (u64)&uvcb))
+		return 0;
+	return -EINVAL;
+}
+
+/*
+ * Guest 2 request to the Ultravisor to make a page shared with the
+ * hypervisor for IO.
+ *
+ * @addr: Real or absolute address of the page to be shared
+ */
+static inline int uv_set_shared(unsigned long addr)
+{
+	return share(addr, UVC_CMD_SET_SHARED_ACCESS);
+}
+
+/*
+ * Guest 2 request to the Ultravisor to make a page unshared.
+ *
+ * @addr: Real or absolute address of the page to be unshared
+ */
+static inline int uv_remove_shared(unsigned long addr)
+{
+	return share(addr, UVC_CMD_REMOVE_SHARED_ACCESS);
+}
+
+void uv_query_info(void);
+#else
+#define is_prot_virt_guest() 0
+static inline int uv_set_shared(unsigned long addr) { return 0; }
+static inline int uv_remove_shared(unsigned long addr) { return 0; }
+static inline void uv_query_info(void) {}
+#endif
+
+#endif /* _ASM_S390_UV_H */
diff --git a/arch/s390/include/asm/vmlinux.lds.h b/arch/s390/include/asm/vmlinux.lds.h
index 2d127f900352..cbe670a6861b 100644
--- a/arch/s390/include/asm/vmlinux.lds.h
+++ b/arch/s390/include/asm/vmlinux.lds.h
@@ -18,3 +18,16 @@
 		*(SORT_BY_ALIGNMENT(SORT_BY_NAME(.boot.data*)))		\
 		__boot_data_end = .;					\
 	}
+
+/*
+ * .boot.preserved.data is similar to .boot.data, but it is not part of the
+ * .init section and thus will be preserved for later use in the decompressed
+ * kernel.
+ */
+#define BOOT_DATA_PRESERVED						\
+	. = ALIGN(PAGE_SIZE);						\
+	.boot.preserved.data : {					\
+		__boot_data_preserved_start = .;			\
+		*(SORT_BY_ALIGNMENT(SORT_BY_NAME(.boot.preserved.data*))) \
+		__boot_data_preserved_end = .;				\
+	}
diff --git a/arch/s390/include/uapi/asm/ipl.h b/arch/s390/include/uapi/asm/ipl.h
new file mode 100644
index 000000000000..fd32b1cd80d2
--- /dev/null
+++ b/arch/s390/include/uapi/asm/ipl.h
@@ -0,0 +1,154 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _ASM_S390_UAPI_IPL_H
+#define _ASM_S390_UAPI_IPL_H
+
+#include <linux/types.h>
+
+/* IPL Parameter List header */
+struct ipl_pl_hdr {
+	__u32 len;
+	__u8  flags;
+	__u8  reserved1[2];
+	__u8  version;
+} __packed;
+
+#define IPL_PL_FLAG_IPLPS	0x80
+#define IPL_PL_FLAG_SIPL	0x40
+#define IPL_PL_FLAG_IPLSR	0x20
+
+/* IPL Parameter Block header */
+struct ipl_pb_hdr {
+	__u32 len;
+	__u8  pbt;
+} __packed;
+
+/* IPL Parameter Block types */
+enum ipl_pbt {
+	IPL_PBT_FCP = 0,
+	IPL_PBT_SCP_DATA = 1,
+	IPL_PBT_CCW = 2,
+};
+
+/* IPL Parameter Block 0 with common fields */
+struct ipl_pb0_common {
+	__u32 len;
+	__u8  pbt;
+	__u8  flags;
+	__u8  reserved1[2];
+	__u8  loadparm[8];
+	__u8  reserved2[84];
+} __packed;
+
+#define IPL_PB0_FLAG_LOADPARM	0x80
+
+/* IPL Parameter Block 0 for FCP */
+struct ipl_pb0_fcp {
+	__u32 len;
+	__u8  pbt;
+	__u8  reserved1[3];
+	__u8  loadparm[8];
+	__u8  reserved2[304];
+	__u8  opt;
+	__u8  reserved3[3];
+	__u8  cssid;
+	__u8  reserved4[1];
+	__u16 devno;
+	__u8  reserved5[4];
+	__u64 wwpn;
+	__u64 lun;
+	__u32 bootprog;
+	__u8  reserved6[12];
+	__u64 br_lba;
+	__u32 scp_data_len;
+	__u8  reserved7[260];
+	__u8  scp_data[];
+} __packed;
+
+#define IPL_PB0_FCP_OPT_IPL	0x10
+#define IPL_PB0_FCP_OPT_DUMP	0x20
+
+/* IPL Parameter Block 0 for CCW */
+struct ipl_pb0_ccw {
+	__u32 len;
+	__u8  pbt;
+	__u8  flags;
+	__u8  reserved1[2];
+	__u8  loadparm[8];
+	__u8  reserved2[84];
+	__u16 reserved3 : 13;
+	__u8  ssid : 3;
+	__u16 devno;
+	__u8  vm_flags;
+	__u8  reserved4[3];
+	__u32 vm_parm_len;
+	__u8  nss_name[8];
+	__u8  vm_parm[64];
+	__u8  reserved5[8];
+} __packed;
+
+#define IPL_PB0_CCW_VM_FLAG_NSS		0x80
+#define IPL_PB0_CCW_VM_FLAG_VP		0x40
+
+/* IPL Parameter Block 1 for additional SCP data */
+struct ipl_pb1_scp_data {
+	__u32 len;
+	__u8  pbt;
+	__u8  scp_data[];
+} __packed;
+
+/* IPL Report List header */
+struct ipl_rl_hdr {
+	__u32 len;
+	__u8  flags;
+	__u8  reserved1[2];
+	__u8  version;
+	__u8  reserved2[8];
+} __packed;
+
+/* IPL Report Block header */
+struct ipl_rb_hdr {
+	__u32 len;
+	__u8  rbt;
+	__u8  reserved1[11];
+} __packed;
+
+/* IPL Report Block types */
+enum ipl_rbt {
+	IPL_RBT_CERTIFICATES = 1,
+	IPL_RBT_COMPONENTS = 2,
+};
+
+/* IPL Report Block for the certificate list */
+struct ipl_rb_certificate_entry {
+	__u64 addr;
+	__u64 len;
+} __packed;
+
+struct ipl_rb_certificates {
+	__u32 len;
+	__u8  rbt;
+	__u8  reserved1[11];
+	struct ipl_rb_certificate_entry entries[];
+} __packed;
+
+/* IPL Report Block for the component list */
+struct ipl_rb_component_entry {
+	__u64 addr;
+	__u64 len;
+	__u8  flags;
+	__u8  reserved1[5];
+	__u16 certificate_index;
+	__u8  reserved2[8];
+};
+
+#define IPL_RB_COMPONENT_FLAG_SIGNED	0x80
+#define IPL_RB_COMPONENT_FLAG_VERIFIED	0x40
+
+struct ipl_rb_components {
+	__u32 len;
+	__u8  rbt;
+	__u8  reserved1[11];
+	struct ipl_rb_component_entry entries[];
+} __packed;
+
+#endif
diff --git a/arch/s390/kernel/Makefile b/arch/s390/kernel/Makefile
index 8a62c7f72e1b..b0478d01a0c5 100644
--- a/arch/s390/kernel/Makefile
+++ b/arch/s390/kernel/Makefile
@@ -39,6 +39,7 @@ CFLAGS_smp.o		:= -Wno-nonnull
 #
 CFLAGS_stacktrace.o	+= -fno-optimize-sibling-calls
 CFLAGS_dumpstack.o	+= -fno-optimize-sibling-calls
+CFLAGS_unwind_bc.o	+= -fno-optimize-sibling-calls
 
 #
 # Pass UTS_MACHINE for user_regset definition
@@ -51,7 +52,7 @@ obj-y	+= debug.o irq.o ipl.o dis.o diag.o vdso.o early_nobss.o
 obj-y	+= sysinfo.o lgr.o os_info.o machine_kexec.o pgm_check.o
 obj-y	+= runtime_instr.o cache.o fpu.o dumpstack.o guarded_storage.o sthyi.o
 obj-y	+= entry.o reipl.o relocate_kernel.o kdebugfs.o alternative.o
-obj-y	+= nospec-branch.o ipl_vmparm.o
+obj-y	+= nospec-branch.o ipl_vmparm.o machine_kexec_reloc.o unwind_bc.o
 
 extra-y				+= head64.o vmlinux.lds
 
@@ -77,6 +78,8 @@ obj-$(CONFIG_JUMP_LABEL)	+= jump_label.o
 obj-$(CONFIG_KEXEC_FILE)	+= machine_kexec_file.o kexec_image.o
 obj-$(CONFIG_KEXEC_FILE)	+= kexec_elf.o
 
+obj-$(CONFIG_IMA)		+= ima_arch.o
+
 obj-$(CONFIG_PERF_EVENTS)	+= perf_event.o perf_cpum_cf_common.o
 obj-$(CONFIG_PERF_EVENTS)	+= perf_cpum_cf.o perf_cpum_sf.o
 obj-$(CONFIG_PERF_EVENTS)	+= perf_cpum_cf_events.o perf_regs.o
@@ -86,7 +89,7 @@ obj-$(CONFIG_TRACEPOINTS)	+= trace.o
 
 # vdso
 obj-y				+= vdso64/
-obj-$(CONFIG_COMPAT)		+= vdso32/
+obj-$(CONFIG_COMPAT_VDSO)	+= vdso32/
 
 chkbss := head64.o early_nobss.o
 include $(srctree)/arch/s390/scripts/Makefile.chkbss
diff --git a/arch/s390/kernel/asm-offsets.c b/arch/s390/kernel/asm-offsets.c
index 164bec175628..41ac4ad21311 100644
--- a/arch/s390/kernel/asm-offsets.c
+++ b/arch/s390/kernel/asm-offsets.c
@@ -16,6 +16,7 @@
 #include <asm/pgtable.h>
 #include <asm/gmap.h>
 #include <asm/nmi.h>
+#include <asm/stacktrace.h>
 
 int main(void)
 {
diff --git a/arch/s390/kernel/base.S b/arch/s390/kernel/base.S
index f268fca67e82..2f39ea57f358 100644
--- a/arch/s390/kernel/base.S
+++ b/arch/s390/kernel/base.S
@@ -28,6 +28,7 @@ ENTRY(s390_base_mcck_handler)
 1:	la	%r1,4095
 	lmg	%r0,%r15,__LC_GPREGS_SAVE_AREA-4095(%r1)
 	lpswe	__LC_MCK_OLD_PSW
+ENDPROC(s390_base_mcck_handler)
 
 	.section .bss
 	.align 8
@@ -48,6 +49,7 @@ ENTRY(s390_base_ext_handler)
 1:	lmg	%r0,%r15,__LC_SAVE_AREA_ASYNC
 	ni	__LC_EXT_OLD_PSW+1,0xfd	# clear wait state bit
 	lpswe	__LC_EXT_OLD_PSW
+ENDPROC(s390_base_ext_handler)
 
 	.section .bss
 	.align 8
@@ -68,6 +70,7 @@ ENTRY(s390_base_pgm_handler)
 	lmg	%r0,%r15,__LC_SAVE_AREA_SYNC
 	lpswe	__LC_PGM_OLD_PSW
 1:	lpswe	disabled_wait_psw-0b(%r13)
+ENDPROC(s390_base_pgm_handler)
 
 	.align	8
 disabled_wait_psw:
@@ -79,71 +82,3 @@ disabled_wait_psw:
 s390_base_pgm_handler_fn:
 	.quad	0
 	.previous
-
-#
-# Calls diag 308 subcode 1 and continues execution
-#
-ENTRY(diag308_reset)
-	larl	%r4,.Lctlregs		# Save control registers
-	stctg	%c0,%c15,0(%r4)
-	lg	%r2,0(%r4)		# Disable lowcore protection
-	nilh	%r2,0xefff
-	larl	%r4,.Lctlreg0
-	stg	%r2,0(%r4)
-	lctlg	%c0,%c0,0(%r4)
-	larl	%r4,.Lfpctl		# Floating point control register
-	stfpc	0(%r4)
-	larl	%r4,.Lprefix		# Save prefix register
-	stpx	0(%r4)
-	larl	%r4,.Lprefix_zero	# Set prefix register to 0
-	spx	0(%r4)
-	larl	%r4,.Lcontinue_psw	# Save PSW flags
-	epsw	%r2,%r3
-	stm	%r2,%r3,0(%r4)
-	larl	%r4,.Lrestart_psw	# Setup restart PSW at absolute 0
-	lghi	%r3,0
-	lg	%r4,0(%r4)		# Save PSW
-	sturg	%r4,%r3			# Use sturg, because of large pages
-	lghi	%r1,1
-	lghi	%r0,0
-	diag	%r0,%r1,0x308
-.Lrestart_part2:
-	lhi	%r0,0			# Load r0 with zero
-	lhi	%r1,2			# Use mode 2 = ESAME (dump)
-	sigp	%r1,%r0,SIGP_SET_ARCHITECTURE	# Switch to ESAME mode
-	sam64				# Switch to 64 bit addressing mode
-	larl	%r4,.Lctlregs		# Restore control registers
-	lctlg	%c0,%c15,0(%r4)
-	larl	%r4,.Lfpctl		# Restore floating point ctl register
-	lfpc	0(%r4)
-	larl	%r4,.Lprefix		# Restore prefix register
-	spx	0(%r4)
-	larl	%r4,.Lcontinue_psw	# Restore PSW flags
-	lpswe	0(%r4)
-.Lcontinue:
-	BR_EX	%r14
-.align 16
-.Lrestart_psw:
-	.long	0x00080000,0x80000000 + .Lrestart_part2
-
-	.section .data..nosave,"aw",@progbits
-.align 8
-.Lcontinue_psw:
-	.quad	0,.Lcontinue
-	.previous
-
-	.section .bss
-.align 8
-.Lctlreg0:
-	.quad	0
-.Lctlregs:
-	.rept	16
-	.quad	0
-	.endr
-.Lfpctl:
-	.long	0
-.Lprefix:
-	.long	0
-.Lprefix_zero:
-	.long	0
-	.previous
diff --git a/arch/s390/kernel/diag.c b/arch/s390/kernel/diag.c
index 7edaa733a77f..e9dac9a24d3f 100644
--- a/arch/s390/kernel/diag.c
+++ b/arch/s390/kernel/diag.c
@@ -13,6 +13,7 @@
 #include <linux/debugfs.h>
 #include <asm/diag.h>
 #include <asm/trace/diag.h>
+#include <asm/sections.h>
 
 struct diag_stat {
 	unsigned int counter[NR_DIAG_STAT];
@@ -49,6 +50,9 @@ static const struct diag_desc diag_map[NR_DIAG_STAT] = {
 	[DIAG_STAT_X500] = { .code = 0x500, .name = "Virtio Service" },
 };
 
+struct diag_ops __bootdata_preserved(diag_dma_ops);
+struct diag210 *__bootdata_preserved(__diag210_tmp_dma);
+
 static int show_diag_stat(struct seq_file *m, void *v)
 {
 	struct diag_stat *stat;
@@ -139,30 +143,10 @@ EXPORT_SYMBOL(diag_stat_inc_norecursion);
 /*
  * Diagnose 14: Input spool file manipulation
  */
-static inline int __diag14(unsigned long rx, unsigned long ry1,
-			   unsigned long subcode)
-{
-	register unsigned long _ry1 asm("2") = ry1;
-	register unsigned long _ry2 asm("3") = subcode;
-	int rc = 0;
-
-	asm volatile(
-		"   sam31\n"
-		"   diag    %2,2,0x14\n"
-		"   sam64\n"
-		"   ipm     %0\n"
-		"   srl     %0,28\n"
-		: "=d" (rc), "+d" (_ry2)
-		: "d" (rx), "d" (_ry1)
-		: "cc");
-
-	return rc;
-}
-
 int diag14(unsigned long rx, unsigned long ry1, unsigned long subcode)
 {
 	diag_stat_inc(DIAG_STAT_X014);
-	return __diag14(rx, ry1, subcode);
+	return diag_dma_ops.diag14(rx, ry1, subcode);
 }
 EXPORT_SYMBOL(diag14);
 
@@ -195,30 +179,17 @@ EXPORT_SYMBOL(diag204);
  */
 int diag210(struct diag210 *addr)
 {
-	/*
-	 * diag 210 needs its data below the 2GB border, so we
-	 * use a static data area to be sure
-	 */
-	static struct diag210 diag210_tmp;
 	static DEFINE_SPINLOCK(diag210_lock);
 	unsigned long flags;
 	int ccode;
 
 	spin_lock_irqsave(&diag210_lock, flags);
-	diag210_tmp = *addr;
+	*__diag210_tmp_dma = *addr;
 
 	diag_stat_inc(DIAG_STAT_X210);
-	asm volatile(
-		"	lhi	%0,-1\n"
-		"	sam31\n"
-		"	diag	%1,0,0x210\n"
-		"0:	ipm	%0\n"
-		"	srl	%0,28\n"
-		"1:	sam64\n"
-		EX_TABLE(0b, 1b)
-		: "=&d" (ccode) : "a" (&diag210_tmp) : "cc", "memory");
-
-	*addr = diag210_tmp;
+	ccode = diag_dma_ops.diag210(__diag210_tmp_dma);
+
+	*addr = *__diag210_tmp_dma;
 	spin_unlock_irqrestore(&diag210_lock, flags);
 
 	return ccode;
@@ -243,27 +214,9 @@ EXPORT_SYMBOL(diag224);
 /*
  * Diagnose 26C: Access Certain System Information
  */
-static inline int __diag26c(void *req, void *resp, enum diag26c_sc subcode)
-{
-	register unsigned long _req asm("2") = (addr_t) req;
-	register unsigned long _resp asm("3") = (addr_t) resp;
-	register unsigned long _subcode asm("4") = subcode;
-	register unsigned long _rc asm("5") = -EOPNOTSUPP;
-
-	asm volatile(
-		"	sam31\n"
-		"	diag	%[rx],%[ry],0x26c\n"
-		"0:	sam64\n"
-		EX_TABLE(0b,0b)
-		: "+d" (_rc)
-		: [rx] "d" (_req), "d" (_resp), [ry] "d" (_subcode)
-		: "cc", "memory");
-	return _rc;
-}
-
 int diag26c(void *req, void *resp, enum diag26c_sc subcode)
 {
 	diag_stat_inc(DIAG_STAT_X26C);
-	return __diag26c(req, resp, subcode);
+	return diag_dma_ops.diag26c(req, resp, subcode);
 }
 EXPORT_SYMBOL(diag26c);
diff --git a/arch/s390/kernel/dumpstack.c b/arch/s390/kernel/dumpstack.c
index cb7f55bbe06e..9e87b68be21c 100644
--- a/arch/s390/kernel/dumpstack.c
+++ b/arch/s390/kernel/dumpstack.c
@@ -21,95 +21,124 @@
 #include <asm/debug.h>
 #include <asm/dis.h>
 #include <asm/ipl.h>
+#include <asm/unwind.h>
 
-/*
- * For dump_trace we have tree different stack to consider:
- *   - the panic stack which is used if the kernel stack has overflown
- *   - the asynchronous interrupt stack (cpu related)
- *   - the synchronous kernel stack (process related)
- * The stack trace can start at any of the three stacks and can potentially
- * touch all of them. The order is: panic stack, async stack, sync stack.
- */
-static unsigned long __no_sanitize_address
-__dump_trace(dump_trace_func_t func, void *data, unsigned long sp,
-	     unsigned long low, unsigned long high)
+const char *stack_type_name(enum stack_type type)
 {
-	struct stack_frame *sf;
-	struct pt_regs *regs;
-
-	while (1) {
-		if (sp < low || sp > high - sizeof(*sf))
-			return sp;
-		sf = (struct stack_frame *) sp;
-		if (func(data, sf->gprs[8], 0))
-			return sp;
-		/* Follow the backchain. */
-		while (1) {
-			low = sp;
-			sp = sf->back_chain;
-			if (!sp)
-				break;
-			if (sp <= low || sp > high - sizeof(*sf))
-				return sp;
-			sf = (struct stack_frame *) sp;
-			if (func(data, sf->gprs[8], 1))
-				return sp;
-		}
-		/* Zero backchain detected, check for interrupt frame. */
-		sp = (unsigned long) (sf + 1);
-		if (sp <= low || sp > high - sizeof(*regs))
-			return sp;
-		regs = (struct pt_regs *) sp;
-		if (!user_mode(regs)) {
-			if (func(data, regs->psw.addr, 1))
-				return sp;
-		}
-		low = sp;
-		sp = regs->gprs[15];
+	switch (type) {
+	case STACK_TYPE_TASK:
+		return "task";
+	case STACK_TYPE_IRQ:
+		return "irq";
+	case STACK_TYPE_NODAT:
+		return "nodat";
+	case STACK_TYPE_RESTART:
+		return "restart";
+	default:
+		return "unknown";
 	}
 }
 
-void dump_trace(dump_trace_func_t func, void *data, struct task_struct *task,
-		unsigned long sp)
+static inline bool in_stack(unsigned long sp, struct stack_info *info,
+			    enum stack_type type, unsigned long low,
+			    unsigned long high)
+{
+	if (sp < low || sp >= high)
+		return false;
+	info->type = type;
+	info->begin = low;
+	info->end = high;
+	return true;
+}
+
+static bool in_task_stack(unsigned long sp, struct task_struct *task,
+			  struct stack_info *info)
+{
+	unsigned long stack;
+
+	stack = (unsigned long) task_stack_page(task);
+	return in_stack(sp, info, STACK_TYPE_TASK, stack, stack + THREAD_SIZE);
+}
+
+static bool in_irq_stack(unsigned long sp, struct stack_info *info)
 {
-	unsigned long frame_size;
+	unsigned long frame_size, top;
 
 	frame_size = STACK_FRAME_OVERHEAD + sizeof(struct pt_regs);
-#ifdef CONFIG_CHECK_STACK
-	sp = __dump_trace(func, data, sp,
-			  S390_lowcore.nodat_stack + frame_size - THREAD_SIZE,
-			  S390_lowcore.nodat_stack + frame_size);
-#endif
-	sp = __dump_trace(func, data, sp,
-			  S390_lowcore.async_stack + frame_size - THREAD_SIZE,
-			  S390_lowcore.async_stack + frame_size);
-	task = task ?: current;
-	__dump_trace(func, data, sp,
-		     (unsigned long)task_stack_page(task),
-		     (unsigned long)task_stack_page(task) + THREAD_SIZE);
+	top = S390_lowcore.async_stack + frame_size;
+	return in_stack(sp, info, STACK_TYPE_IRQ, top - THREAD_SIZE, top);
+}
+
+static bool in_nodat_stack(unsigned long sp, struct stack_info *info)
+{
+	unsigned long frame_size, top;
+
+	frame_size = STACK_FRAME_OVERHEAD + sizeof(struct pt_regs);
+	top = S390_lowcore.nodat_stack + frame_size;
+	return in_stack(sp, info, STACK_TYPE_NODAT, top - THREAD_SIZE, top);
 }
-EXPORT_SYMBOL_GPL(dump_trace);
 
-static int show_address(void *data, unsigned long address, int reliable)
+static bool in_restart_stack(unsigned long sp, struct stack_info *info)
 {
-	if (reliable)
-		printk(" [<%016lx>] %pSR \n", address, (void *)address);
-	else
-		printk("([<%016lx>] %pSR)\n", address, (void *)address);
+	unsigned long frame_size, top;
+
+	frame_size = STACK_FRAME_OVERHEAD + sizeof(struct pt_regs);
+	top = S390_lowcore.restart_stack + frame_size;
+	return in_stack(sp, info, STACK_TYPE_RESTART, top - THREAD_SIZE, top);
+}
+
+int get_stack_info(unsigned long sp, struct task_struct *task,
+		   struct stack_info *info, unsigned long *visit_mask)
+{
+	if (!sp)
+		goto unknown;
+
+	task = task ? : current;
+
+	/* Check per-task stack */
+	if (in_task_stack(sp, task, info))
+		goto recursion_check;
+
+	if (task != current)
+		goto unknown;
+
+	/* Check per-cpu stacks */
+	if (!in_irq_stack(sp, info) &&
+	    !in_nodat_stack(sp, info) &&
+	    !in_restart_stack(sp, info))
+		goto unknown;
+
+recursion_check:
+	/*
+	 * Make sure we don't iterate through any given stack more than once.
+	 * If it comes up a second time then there's something wrong going on:
+	 * just break out and report an unknown stack type.
+	 */
+	if (*visit_mask & (1UL << info->type)) {
+		printk_deferred_once(KERN_WARNING
+			"WARNING: stack recursion on stack type %d\n",
+			info->type);
+		goto unknown;
+	}
+	*visit_mask |= 1UL << info->type;
 	return 0;
+unknown:
+	info->type = STACK_TYPE_UNKNOWN;
+	return -EINVAL;
 }
 
 void show_stack(struct task_struct *task, unsigned long *stack)
 {
-	unsigned long sp = (unsigned long) stack;
+	struct unwind_state state;
 
-	if (!sp)
-		sp = task ? task->thread.ksp : current_stack_pointer();
 	printk("Call Trace:\n");
-	dump_trace(show_address, NULL, task, sp);
 	if (!task)
 		task = current;
-	debug_show_held_locks(task);
+	unwind_for_each_frame(&state, task, NULL, (unsigned long) stack)
+		printk(state.reliable ? " [<%016lx>] %pSR \n" :
+					"([<%016lx>] %pSR)\n",
+		       state.ip, (void *) state.ip);
+	debug_show_held_locks(task ? : current);
 }
 
 static void show_last_breaking_event(struct pt_regs *regs)
diff --git a/arch/s390/kernel/early.c b/arch/s390/kernel/early.c
index d6edf45f93b9..629f173f60cd 100644
--- a/arch/s390/kernel/early.c
+++ b/arch/s390/kernel/early.c
@@ -30,6 +30,7 @@
 #include <asm/sclp.h>
 #include <asm/facility.h>
 #include <asm/boot_data.h>
+#include <asm/pci_insn.h>
 #include "entry.h"
 
 /*
@@ -138,9 +139,9 @@ static void early_pgm_check_handler(void)
 	unsigned long addr;
 
 	addr = S390_lowcore.program_old_psw.addr;
-	fixup = search_exception_tables(addr);
+	fixup = s390_search_extables(addr);
 	if (!fixup)
-		disabled_wait(0);
+		disabled_wait();
 	/* Disable low address protection before storing into lowcore. */
 	__ctl_store(cr0, 0, 0);
 	cr0_new = cr0 & ~(1UL << 28);
@@ -235,6 +236,7 @@ static __init void detect_machine_facilities(void)
 		clock_comparator_max = -1ULL >> 1;
 		__ctl_set_bit(0, 53);
 	}
+	enable_mio_ctl();
 }
 
 static inline void save_vector_registers(void)
@@ -296,7 +298,7 @@ static void __init check_image_bootable(void)
 	sclp_early_printk("Linux kernel boot failure: An attempt to boot a vmlinux ELF image failed.\n");
 	sclp_early_printk("This image does not contain all parts necessary for starting up. Use\n");
 	sclp_early_printk("bzImage or arch/s390/boot/compressed/vmlinux instead.\n");
-	disabled_wait(0xbadb007);
+	disabled_wait();
 }
 
 void __init startup_init(void)
@@ -309,7 +311,6 @@ void __init startup_init(void)
 	setup_facility_list();
 	detect_machine_type();
 	setup_arch_string();
-	ipl_store_parameters();
 	setup_boot_command_line();
 	detect_diag9c();
 	detect_diag44();
diff --git a/arch/s390/kernel/early_nobss.c b/arch/s390/kernel/early_nobss.c
index 8d73f7fae16e..52a3ef959341 100644
--- a/arch/s390/kernel/early_nobss.c
+++ b/arch/s390/kernel/early_nobss.c
@@ -25,7 +25,7 @@ static void __init reset_tod_clock(void)
 		return;
 	/* TOD clock not running. Set the clock to Unix Epoch. */
 	if (set_tod_clock(TOD_UNIX_EPOCH) != 0 || store_tod_clock(&time) != 0)
-		disabled_wait(0);
+		disabled_wait();
 
 	memset(tod_clock_base, 0, 16);
 	*(__u64 *) &tod_clock_base[1] = TOD_UNIX_EPOCH;
diff --git a/arch/s390/kernel/entry.S b/arch/s390/kernel/entry.S
index 583d65ef5007..3f4d272577d3 100644
--- a/arch/s390/kernel/entry.S
+++ b/arch/s390/kernel/entry.S
@@ -224,6 +224,7 @@ ENTRY(__bpon)
 	.globl __bpon
 	BPON
 	BR_EX	%r14
+ENDPROC(__bpon)
 
 /*
  * Scheduler resume function, called by switch_to
@@ -248,6 +249,7 @@ ENTRY(__switch_to)
 	lmg	%r6,%r15,__SF_GPRS(%r15)	# load gprs of next task
 	ALTERNATIVE "", ".insn s,0xb2800000,_LPP_OFFSET", 40
 	BR_EX	%r14
+ENDPROC(__switch_to)
 
 .L__critical_start:
 
@@ -324,6 +326,7 @@ sie_exit:
 	EX_TABLE(.Lrewind_pad4,.Lsie_fault)
 	EX_TABLE(.Lrewind_pad2,.Lsie_fault)
 	EX_TABLE(sie_exit,.Lsie_fault)
+ENDPROC(sie64a)
 EXPORT_SYMBOL(sie64a)
 EXPORT_SYMBOL(sie_exit)
 #endif
@@ -358,19 +361,19 @@ ENTRY(system_call)
 	# load address of system call table
 	lg	%r10,__THREAD_sysc_table(%r13,%r12)
 	llgh	%r8,__PT_INT_CODE+2(%r11)
-	slag	%r8,%r8,2			# shift and test for svc 0
+	slag	%r8,%r8,3			# shift and test for svc 0
 	jnz	.Lsysc_nr_ok
 	# svc 0: system call number in %r1
 	llgfr	%r1,%r1				# clear high word in r1
 	cghi	%r1,NR_syscalls
 	jnl	.Lsysc_nr_ok
 	sth	%r1,__PT_INT_CODE+2(%r11)
-	slag	%r8,%r1,2
+	slag	%r8,%r1,3
 .Lsysc_nr_ok:
 	xc	__SF_BACKCHAIN(8,%r15),__SF_BACKCHAIN(%r15)
 	stg	%r2,__PT_ORIG_GPR2(%r11)
 	stg	%r7,STACK_FRAME_OVERHEAD(%r15)
-	lgf	%r9,0(%r8,%r10)			# get system call add.
+	lg	%r9,0(%r8,%r10)			# get system call add.
 	TSTMSK	__TI_flags(%r12),_TIF_TRACE
 	jnz	.Lsysc_tracesys
 	BASR_EX	%r14,%r9			# call sys_xxxx
@@ -556,8 +559,8 @@ ENTRY(system_call)
 	lghi	%r0,NR_syscalls
 	clgr	%r0,%r2
 	jnh	.Lsysc_tracenogo
-	sllg	%r8,%r2,2
-	lgf	%r9,0(%r8,%r10)
+	sllg	%r8,%r2,3
+	lg	%r9,0(%r8,%r10)
 .Lsysc_tracego:
 	lmg	%r3,%r7,__PT_R3(%r11)
 	stg	%r7,STACK_FRAME_OVERHEAD(%r15)
@@ -570,6 +573,7 @@ ENTRY(system_call)
 	lgr	%r2,%r11		# pass pointer to pt_regs
 	larl	%r14,.Lsysc_return
 	jg	do_syscall_trace_exit
+ENDPROC(system_call)
 
 #
 # a new process exits the kernel with ret_from_fork
@@ -584,10 +588,16 @@ ENTRY(ret_from_fork)
 	jne	.Lsysc_tracenogo
 	# it's a kernel thread
 	lmg	%r9,%r10,__PT_R9(%r11)	# load gprs
+	la	%r2,0(%r10)
+	BASR_EX	%r14,%r9
+	j	.Lsysc_tracenogo
+ENDPROC(ret_from_fork)
+
 ENTRY(kernel_thread_starter)
 	la	%r2,0(%r10)
 	BASR_EX	%r14,%r9
 	j	.Lsysc_tracenogo
+ENDPROC(kernel_thread_starter)
 
 /*
  * Program check handler routine
@@ -665,9 +675,9 @@ ENTRY(pgm_check_handler)
 	larl	%r1,pgm_check_table
 	llgh	%r10,__PT_INT_CODE+2(%r11)
 	nill	%r10,0x007f
-	sll	%r10,2
+	sll	%r10,3
 	je	.Lpgm_return
-	lgf	%r9,0(%r10,%r1)		# load address of handler routine
+	lg	%r9,0(%r10,%r1)		# load address of handler routine
 	lgr	%r2,%r11		# pass pointer to pt_regs
 	BASR_EX	%r14,%r9		# branch to interrupt-handler
 .Lpgm_return:
@@ -698,6 +708,7 @@ ENTRY(pgm_check_handler)
 	stg	%r14,__LC_RETURN_PSW+8
 	lghi	%r14,_PIF_SYSCALL | _PIF_PER_TRAP
 	lpswe	__LC_RETURN_PSW		# branch to .Lsysc_per and enable irqs
+ENDPROC(pgm_check_handler)
 
 /*
  * IO interrupt handler routine
@@ -926,6 +937,7 @@ ENTRY(io_int_handler)
 	ssm	__LC_PGM_NEW_PSW	# disable I/O and ext. interrupts
 	TRACE_IRQS_OFF
 	j	.Lio_return
+ENDPROC(io_int_handler)
 
 /*
  * External interrupt handler routine
@@ -965,6 +977,7 @@ ENTRY(ext_int_handler)
 	lghi	%r3,EXT_INTERRUPT
 	brasl	%r14,do_IRQ
 	j	.Lio_return
+ENDPROC(ext_int_handler)
 
 /*
  * Load idle PSW. The second "half" of this function is in .Lcleanup_idle.
@@ -989,6 +1002,7 @@ ENTRY(psw_idle)
 	lpswe	__SF_EMPTY(%r15)
 	BR_EX	%r14
 .Lpsw_idle_end:
+ENDPROC(psw_idle)
 
 /*
  * Store floating-point controls and floating-point or vector register
@@ -1031,6 +1045,7 @@ ENTRY(save_fpu_regs)
 .Lsave_fpu_regs_exit:
 	BR_EX	%r14
 .Lsave_fpu_regs_end:
+ENDPROC(save_fpu_regs)
 EXPORT_SYMBOL(save_fpu_regs)
 
 /*
@@ -1077,6 +1092,7 @@ load_fpu_regs:
 .Lload_fpu_regs_exit:
 	BR_EX	%r14
 .Lload_fpu_regs_end:
+ENDPROC(load_fpu_regs)
 
 .L__critical_end:
 
@@ -1206,6 +1222,7 @@ ENTRY(mcck_int_handler)
 	lg	%r15,__LC_NODAT_STACK
 	la	%r11,STACK_FRAME_OVERHEAD(%r15)
 	j	.Lmcck_skip
+ENDPROC(mcck_int_handler)
 
 #
 # PSW restart interrupt handler
@@ -1232,6 +1249,7 @@ ENTRY(restart_int_handler)
 2:	sigp	%r4,%r3,SIGP_STOP		# sigp stop to current cpu
 	brc	2,2b
 3:	j	3b
+ENDPROC(restart_int_handler)
 
 	.section .kprobes.text, "ax"
 
@@ -1241,7 +1259,7 @@ ENTRY(restart_int_handler)
  * No need to properly save the registers, we are going to panic anyway.
  * Setup a pt_regs so that show_trace can provide a good call trace.
  */
-stack_overflow:
+ENTRY(stack_overflow)
 	lg	%r15,__LC_NODAT_STACK	# change to panic stack
 	la	%r11,STACK_FRAME_OVERHEAD(%r15)
 	stmg	%r0,%r7,__PT_R0(%r11)
@@ -1251,9 +1269,10 @@ stack_overflow:
 	xc	__SF_BACKCHAIN(8,%r15),__SF_BACKCHAIN(%r15)
 	lgr	%r2,%r11		# pass pointer to pt_regs
 	jg	kernel_stack_overflow
+ENDPROC(stack_overflow)
 #endif
 
-cleanup_critical:
+ENTRY(cleanup_critical)
 #if IS_ENABLED(CONFIG_KVM)
 	clg	%r9,BASED(.Lcleanup_table_sie)	# .Lsie_gmap
 	jl	0f
@@ -1289,6 +1308,7 @@ cleanup_critical:
 	clg	%r9,BASED(.Lcleanup_table+104)	# .Lload_fpu_regs_end
 	jl	.Lcleanup_load_fpu_regs
 0:	BR_EX	%r14,%r11
+ENDPROC(cleanup_critical)
 
 	.align	8
 .Lcleanup_table:
@@ -1512,7 +1532,7 @@ cleanup_critical:
 	.quad   .Lsie_skip - .Lsie_entry
 #endif
 	.section .rodata, "a"
-#define SYSCALL(esame,emu)	.long __s390x_ ## esame
+#define SYSCALL(esame,emu)	.quad __s390x_ ## esame
 	.globl	sys_call_table
 sys_call_table:
 #include "asm/syscall_table.h"
@@ -1520,7 +1540,7 @@ sys_call_table:
 
 #ifdef CONFIG_COMPAT
 
-#define SYSCALL(esame,emu)	.long __s390_ ## emu
+#define SYSCALL(esame,emu)	.quad __s390_ ## emu
 	.globl	sys_call_table_emu
 sys_call_table_emu:
 #include "asm/syscall_table.h"
diff --git a/arch/s390/kernel/entry.h b/arch/s390/kernel/entry.h
index c3816ae108b0..20420c2b8a14 100644
--- a/arch/s390/kernel/entry.h
+++ b/arch/s390/kernel/entry.h
@@ -65,7 +65,7 @@ int setup_profiling_timer(unsigned int multiplier);
 void __init time_init(void);
 int pfn_is_nosave(unsigned long);
 void s390_early_resume(void);
-unsigned long prepare_ftrace_return(unsigned long parent, unsigned long ip);
+unsigned long prepare_ftrace_return(unsigned long parent, unsigned long sp, unsigned long ip);
 
 struct s390_mmap_arg_struct;
 struct fadvise64_64_args;
diff --git a/arch/s390/kernel/fpu.c b/arch/s390/kernel/fpu.c
index 594464f2129d..0da378e2eb25 100644
--- a/arch/s390/kernel/fpu.c
+++ b/arch/s390/kernel/fpu.c
@@ -23,7 +23,7 @@ void __kernel_fpu_begin(struct kernel_fpu *state, u32 flags)
 
 	if (flags & KERNEL_FPC)
 		/* Save floating point control */
-		asm volatile("stfpc %0" : "=m" (state->fpc));
+		asm volatile("stfpc %0" : "=Q" (state->fpc));
 
 	if (!MACHINE_HAS_VX) {
 		if (flags & KERNEL_VXR_V0V7) {
diff --git a/arch/s390/kernel/ftrace.c b/arch/s390/kernel/ftrace.c
index 39b13d71a8fe..1bb85f60c0dd 100644
--- a/arch/s390/kernel/ftrace.c
+++ b/arch/s390/kernel/ftrace.c
@@ -201,17 +201,18 @@ device_initcall(ftrace_plt_init);
  * Hook the return address and push it in the stack of return addresses
  * in current thread info.
  */
-unsigned long prepare_ftrace_return(unsigned long parent, unsigned long ip)
+unsigned long prepare_ftrace_return(unsigned long ra, unsigned long sp,
+				    unsigned long ip)
 {
 	if (unlikely(ftrace_graph_is_dead()))
 		goto out;
 	if (unlikely(atomic_read(&current->tracing_graph_pause)))
 		goto out;
 	ip -= MCOUNT_INSN_SIZE;
-	if (!function_graph_enter(parent, ip, 0, NULL))
-		parent = (unsigned long) return_to_handler;
+	if (!function_graph_enter(ra, ip, 0, (void *) sp))
+		ra = (unsigned long) return_to_handler;
 out:
-	return parent;
+	return ra;
 }
 NOKPROBE_SYMBOL(prepare_ftrace_return);
 
diff --git a/arch/s390/kernel/head64.S b/arch/s390/kernel/head64.S
index 56491e636eab..5aea1a527443 100644
--- a/arch/s390/kernel/head64.S
+++ b/arch/s390/kernel/head64.S
@@ -26,7 +26,6 @@ ENTRY(startup_continue)
 0:	larl	%r1,tod_clock_base
 	mvc	0(16,%r1),__LC_BOOT_CLOCK
 	larl	%r13,.LPG1		# get base
-	lctlg	%c0,%c15,.Lctl-.LPG1(%r13)	# load control registers
 	larl	%r0,boot_vdso_data
 	stg	%r0,__LC_VDSO_PER_CPU
 #
@@ -61,22 +60,6 @@ ENTRY(startup_continue)
 
 	.align	16
 .LPG1:
-.Lctl:	.quad	0x04040000		# cr0: AFP registers & secondary space
-	.quad	0			# cr1: primary space segment table
-	.quad	.Lduct			# cr2: dispatchable unit control table
-	.quad	0			# cr3: instruction authorization
-	.quad	0xffff			# cr4: instruction authorization
-	.quad	.Lduct			# cr5: primary-aste origin
-	.quad	0			# cr6:	I/O interrupts
-	.quad	0			# cr7:	secondary space segment table
-	.quad	0			# cr8:	access registers translation
-	.quad	0			# cr9:	tracing off
-	.quad	0			# cr10: tracing off
-	.quad	0			# cr11: tracing off
-	.quad	0			# cr12: tracing off
-	.quad	0			# cr13: home space segment table
-	.quad	0xc0000000		# cr14: machine check handling off
-	.quad	.Llinkage_stack		# cr15: linkage stack operations
 .Lpcmsk:.quad	0x0000000180000000
 .L4malign:.quad 0xffffffffffc00000
 .Lscan2g:.quad	0x80000000 + 0x20000 - 8	# 2GB + 128K - 8
@@ -84,14 +67,5 @@ ENTRY(startup_continue)
 .Lparmaddr:
 	.quad	PARMAREA
 	.align	64
-.Lduct: .long	0,.Laste,.Laste,0,.Lduald,0,0,0
-	.long	0,0,0,0,0,0,0,0
-.Laste:	.quad	0,0xffffffffffffffff,0,0,0,0,0,0
-	.align	128
-.Lduald:.rept	8
-	.long	0x80000000,0,0,0	# invalid access-list entries
-	.endr
-.Llinkage_stack:
-	.long	0,0,0x89000000,0,0,0,0x8a000000,0
 .Ldw:	.quad	0x0002000180000000,0x0000000000000000
 .Laregs:.long	0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0
diff --git a/arch/s390/kernel/ima_arch.c b/arch/s390/kernel/ima_arch.c
new file mode 100644
index 000000000000..f3c3e6e1c5d3
--- /dev/null
+++ b/arch/s390/kernel/ima_arch.c
@@ -0,0 +1,14 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#include <linux/ima.h>
+#include <asm/boot_data.h>
+
+bool arch_ima_get_secureboot(void)
+{
+	return ipl_secure_flag;
+}
+
+const char * const *arch_get_ima_policy(void)
+{
+	return NULL;
+}
diff --git a/arch/s390/kernel/ipl.c b/arch/s390/kernel/ipl.c
index 18a5d6317acc..d836af3ccc38 100644
--- a/arch/s390/kernel/ipl.c
+++ b/arch/s390/kernel/ipl.c
@@ -31,6 +31,7 @@
 #include <asm/os_info.h>
 #include <asm/sections.h>
 #include <asm/boot_data.h>
+#include <asm/uv.h>
 #include "entry.h"
 
 #define IPL_PARM_BLOCK_VERSION 0
@@ -119,11 +120,15 @@ static char *dump_type_str(enum dump_type type)
 	}
 }
 
-struct ipl_parameter_block __bootdata(early_ipl_block);
-int __bootdata(early_ipl_block_valid);
+int __bootdata_preserved(ipl_block_valid);
+struct ipl_parameter_block __bootdata_preserved(ipl_block);
+int __bootdata_preserved(ipl_secure_flag);
 
-static int ipl_block_valid;
-static struct ipl_parameter_block ipl_block;
+unsigned long __bootdata_preserved(ipl_cert_list_addr);
+unsigned long __bootdata_preserved(ipl_cert_list_size);
+
+unsigned long __bootdata(early_ipl_comp_list_addr);
+unsigned long __bootdata(early_ipl_comp_list_size);
 
 static int reipl_capabilities = IPL_TYPE_UNKNOWN;
 
@@ -246,11 +251,11 @@ static __init enum ipl_type get_ipl_type(void)
 	if (!ipl_block_valid)
 		return IPL_TYPE_UNKNOWN;
 
-	switch (ipl_block.hdr.pbt) {
-	case DIAG308_IPL_TYPE_CCW:
+	switch (ipl_block.pb0_hdr.pbt) {
+	case IPL_PBT_CCW:
 		return IPL_TYPE_CCW;
-	case DIAG308_IPL_TYPE_FCP:
-		if (ipl_block.ipl_info.fcp.opt == DIAG308_IPL_OPT_DUMP)
+	case IPL_PBT_FCP:
+		if (ipl_block.fcp.opt == IPL_PB0_FCP_OPT_DUMP)
 			return IPL_TYPE_FCP_DUMP;
 		else
 			return IPL_TYPE_FCP;
@@ -269,12 +274,35 @@ static ssize_t ipl_type_show(struct kobject *kobj, struct kobj_attribute *attr,
 
 static struct kobj_attribute sys_ipl_type_attr = __ATTR_RO(ipl_type);
 
+static ssize_t ipl_secure_show(struct kobject *kobj,
+			       struct kobj_attribute *attr, char *page)
+{
+	return sprintf(page, "%i\n", !!ipl_secure_flag);
+}
+
+static struct kobj_attribute sys_ipl_secure_attr =
+	__ATTR(secure, 0444, ipl_secure_show, NULL);
+
+static ssize_t ipl_has_secure_show(struct kobject *kobj,
+				   struct kobj_attribute *attr, char *page)
+{
+	if (MACHINE_IS_LPAR)
+		return sprintf(page, "%i\n", !!sclp.has_sipl);
+	else if (MACHINE_IS_VM)
+		return sprintf(page, "%i\n", !!sclp.has_sipl_g2);
+	else
+		return sprintf(page, "%i\n", 0);
+}
+
+static struct kobj_attribute sys_ipl_has_secure_attr =
+	__ATTR(has_secure, 0444, ipl_has_secure_show, NULL);
+
 static ssize_t ipl_vm_parm_show(struct kobject *kobj,
 				struct kobj_attribute *attr, char *page)
 {
 	char parm[DIAG308_VMPARM_SIZE + 1] = {};
 
-	if (ipl_block_valid && (ipl_block.hdr.pbt == DIAG308_IPL_TYPE_CCW))
+	if (ipl_block_valid && (ipl_block.pb0_hdr.pbt == IPL_PBT_CCW))
 		ipl_block_get_ascii_vmparm(parm, sizeof(parm), &ipl_block);
 	return sprintf(page, "%s\n", parm);
 }
@@ -287,12 +315,11 @@ static ssize_t sys_ipl_device_show(struct kobject *kobj,
 {
 	switch (ipl_info.type) {
 	case IPL_TYPE_CCW:
-		return sprintf(page, "0.%x.%04x\n", ipl_block.ipl_info.ccw.ssid,
-			       ipl_block.ipl_info.ccw.devno);
+		return sprintf(page, "0.%x.%04x\n", ipl_block.ccw.ssid,
+			       ipl_block.ccw.devno);
 	case IPL_TYPE_FCP:
 	case IPL_TYPE_FCP_DUMP:
-		return sprintf(page, "0.0.%04x\n",
-			       ipl_block.ipl_info.fcp.devno);
+		return sprintf(page, "0.0.%04x\n", ipl_block.fcp.devno);
 	default:
 		return 0;
 	}
@@ -316,8 +343,8 @@ static ssize_t ipl_scp_data_read(struct file *filp, struct kobject *kobj,
 				 struct bin_attribute *attr, char *buf,
 				 loff_t off, size_t count)
 {
-	unsigned int size = ipl_block.ipl_info.fcp.scp_data_len;
-	void *scp_data = &ipl_block.ipl_info.fcp.scp_data;
+	unsigned int size = ipl_block.fcp.scp_data_len;
+	void *scp_data = &ipl_block.fcp.scp_data;
 
 	return memory_read_from_buffer(buf, count, &off, scp_data, size);
 }
@@ -333,13 +360,13 @@ static struct bin_attribute *ipl_fcp_bin_attrs[] = {
 /* FCP ipl device attributes */
 
 DEFINE_IPL_ATTR_RO(ipl_fcp, wwpn, "0x%016llx\n",
-		   (unsigned long long)ipl_block.ipl_info.fcp.wwpn);
+		   (unsigned long long)ipl_block.fcp.wwpn);
 DEFINE_IPL_ATTR_RO(ipl_fcp, lun, "0x%016llx\n",
-		   (unsigned long long)ipl_block.ipl_info.fcp.lun);
+		   (unsigned long long)ipl_block.fcp.lun);
 DEFINE_IPL_ATTR_RO(ipl_fcp, bootprog, "%lld\n",
-		   (unsigned long long)ipl_block.ipl_info.fcp.bootprog);
+		   (unsigned long long)ipl_block.fcp.bootprog);
 DEFINE_IPL_ATTR_RO(ipl_fcp, br_lba, "%lld\n",
-		   (unsigned long long)ipl_block.ipl_info.fcp.br_lba);
+		   (unsigned long long)ipl_block.fcp.br_lba);
 
 static ssize_t ipl_ccw_loadparm_show(struct kobject *kobj,
 				     struct kobj_attribute *attr, char *page)
@@ -365,6 +392,8 @@ static struct attribute *ipl_fcp_attrs[] = {
 	&sys_ipl_fcp_bootprog_attr.attr,
 	&sys_ipl_fcp_br_lba_attr.attr,
 	&sys_ipl_ccw_loadparm_attr.attr,
+	&sys_ipl_secure_attr.attr,
+	&sys_ipl_has_secure_attr.attr,
 	NULL,
 };
 
@@ -380,6 +409,8 @@ static struct attribute *ipl_ccw_attrs_vm[] = {
 	&sys_ipl_device_attr.attr,
 	&sys_ipl_ccw_loadparm_attr.attr,
 	&sys_ipl_vm_parm_attr.attr,
+	&sys_ipl_secure_attr.attr,
+	&sys_ipl_has_secure_attr.attr,
 	NULL,
 };
 
@@ -387,6 +418,8 @@ static struct attribute *ipl_ccw_attrs_lpar[] = {
 	&sys_ipl_type_attr.attr,
 	&sys_ipl_device_attr.attr,
 	&sys_ipl_ccw_loadparm_attr.attr,
+	&sys_ipl_secure_attr.attr,
+	&sys_ipl_has_secure_attr.attr,
 	NULL,
 };
 
@@ -495,14 +528,14 @@ static ssize_t reipl_generic_vmparm_store(struct ipl_parameter_block *ipb,
 		if (!(isalnum(buf[i]) || isascii(buf[i]) || isprint(buf[i])))
 			return -EINVAL;
 
-	memset(ipb->ipl_info.ccw.vm_parm, 0, DIAG308_VMPARM_SIZE);
-	ipb->ipl_info.ccw.vm_parm_len = ip_len;
+	memset(ipb->ccw.vm_parm, 0, DIAG308_VMPARM_SIZE);
+	ipb->ccw.vm_parm_len = ip_len;
 	if (ip_len > 0) {
-		ipb->ipl_info.ccw.vm_flags |= DIAG308_VM_FLAGS_VP_VALID;
-		memcpy(ipb->ipl_info.ccw.vm_parm, buf, ip_len);
-		ASCEBC(ipb->ipl_info.ccw.vm_parm, ip_len);
+		ipb->ccw.vm_flags |= IPL_PB0_CCW_VM_FLAG_VP;
+		memcpy(ipb->ccw.vm_parm, buf, ip_len);
+		ASCEBC(ipb->ccw.vm_parm, ip_len);
 	} else {
-		ipb->ipl_info.ccw.vm_flags &= ~DIAG308_VM_FLAGS_VP_VALID;
+		ipb->ccw.vm_flags &= ~IPL_PB0_CCW_VM_FLAG_VP;
 	}
 
 	return len;
@@ -549,8 +582,8 @@ static ssize_t reipl_fcp_scpdata_read(struct file *filp, struct kobject *kobj,
 				      struct bin_attribute *attr,
 				      char *buf, loff_t off, size_t count)
 {
-	size_t size = reipl_block_fcp->ipl_info.fcp.scp_data_len;
-	void *scp_data = reipl_block_fcp->ipl_info.fcp.scp_data;
+	size_t size = reipl_block_fcp->fcp.scp_data_len;
+	void *scp_data = reipl_block_fcp->fcp.scp_data;
 
 	return memory_read_from_buffer(buf, count, &off, scp_data, size);
 }
@@ -566,17 +599,17 @@ static ssize_t reipl_fcp_scpdata_write(struct file *filp, struct kobject *kobj,
 	if (off)
 		return -EINVAL;
 
-	memcpy(reipl_block_fcp->ipl_info.fcp.scp_data, buf, count);
+	memcpy(reipl_block_fcp->fcp.scp_data, buf, count);
 	if (scpdata_len % 8) {
 		padding = 8 - (scpdata_len % 8);
-		memset(reipl_block_fcp->ipl_info.fcp.scp_data + scpdata_len,
+		memset(reipl_block_fcp->fcp.scp_data + scpdata_len,
 		       0, padding);
 		scpdata_len += padding;
 	}
 
-	reipl_block_fcp->ipl_info.fcp.scp_data_len = scpdata_len;
-	reipl_block_fcp->hdr.len = IPL_PARM_BLK_FCP_LEN + scpdata_len;
-	reipl_block_fcp->hdr.blk0_len = IPL_PARM_BLK0_FCP_LEN + scpdata_len;
+	reipl_block_fcp->hdr.len = IPL_BP_FCP_LEN + scpdata_len;
+	reipl_block_fcp->fcp.len = IPL_BP0_FCP_LEN + scpdata_len;
+	reipl_block_fcp->fcp.scp_data_len = scpdata_len;
 
 	return count;
 }
@@ -590,20 +623,20 @@ static struct bin_attribute *reipl_fcp_bin_attrs[] = {
 };
 
 DEFINE_IPL_ATTR_RW(reipl_fcp, wwpn, "0x%016llx\n", "%llx\n",
-		   reipl_block_fcp->ipl_info.fcp.wwpn);
+		   reipl_block_fcp->fcp.wwpn);
 DEFINE_IPL_ATTR_RW(reipl_fcp, lun, "0x%016llx\n", "%llx\n",
-		   reipl_block_fcp->ipl_info.fcp.lun);
+		   reipl_block_fcp->fcp.lun);
 DEFINE_IPL_ATTR_RW(reipl_fcp, bootprog, "%lld\n", "%lld\n",
-		   reipl_block_fcp->ipl_info.fcp.bootprog);
+		   reipl_block_fcp->fcp.bootprog);
 DEFINE_IPL_ATTR_RW(reipl_fcp, br_lba, "%lld\n", "%lld\n",
-		   reipl_block_fcp->ipl_info.fcp.br_lba);
+		   reipl_block_fcp->fcp.br_lba);
 DEFINE_IPL_ATTR_RW(reipl_fcp, device, "0.0.%04llx\n", "0.0.%llx\n",
-		   reipl_block_fcp->ipl_info.fcp.devno);
+		   reipl_block_fcp->fcp.devno);
 
 static void reipl_get_ascii_loadparm(char *loadparm,
 				     struct ipl_parameter_block *ibp)
 {
-	memcpy(loadparm, ibp->hdr.loadparm, LOADPARM_LEN);
+	memcpy(loadparm, ibp->common.loadparm, LOADPARM_LEN);
 	EBCASC(loadparm, LOADPARM_LEN);
 	loadparm[LOADPARM_LEN] = 0;
 	strim(loadparm);
@@ -638,11 +671,11 @@ static ssize_t reipl_generic_loadparm_store(struct ipl_parameter_block *ipb,
 		return -EINVAL;
 	}
 	/* initialize loadparm with blanks */
-	memset(ipb->hdr.loadparm, ' ', LOADPARM_LEN);
+	memset(ipb->common.loadparm, ' ', LOADPARM_LEN);
 	/* copy and convert to ebcdic */
-	memcpy(ipb->hdr.loadparm, buf, lp_len);
-	ASCEBC(ipb->hdr.loadparm, LOADPARM_LEN);
-	ipb->hdr.flags |= DIAG308_FLAGS_LP_VALID;
+	memcpy(ipb->common.loadparm, buf, lp_len);
+	ASCEBC(ipb->common.loadparm, LOADPARM_LEN);
+	ipb->common.flags |= IPL_PB0_FLAG_LOADPARM;
 	return len;
 }
 
@@ -680,7 +713,7 @@ static struct attribute_group reipl_fcp_attr_group = {
 };
 
 /* CCW reipl device attributes */
-DEFINE_IPL_CCW_ATTR_RW(reipl_ccw, device, reipl_block_ccw->ipl_info.ccw);
+DEFINE_IPL_CCW_ATTR_RW(reipl_ccw, device, reipl_block_ccw->ccw);
 
 /* NSS wrapper */
 static ssize_t reipl_nss_loadparm_show(struct kobject *kobj,
@@ -742,7 +775,7 @@ static struct attribute_group reipl_ccw_attr_group_lpar = {
 static void reipl_get_ascii_nss_name(char *dst,
 				     struct ipl_parameter_block *ipb)
 {
-	memcpy(dst, ipb->ipl_info.ccw.nss_name, NSS_NAME_SIZE);
+	memcpy(dst, ipb->ccw.nss_name, NSS_NAME_SIZE);
 	EBCASC(dst, NSS_NAME_SIZE);
 	dst[NSS_NAME_SIZE] = 0;
 }
@@ -770,16 +803,14 @@ static ssize_t reipl_nss_name_store(struct kobject *kobj,
 	if (nss_len > NSS_NAME_SIZE)
 		return -EINVAL;
 
-	memset(reipl_block_nss->ipl_info.ccw.nss_name, 0x40, NSS_NAME_SIZE);
+	memset(reipl_block_nss->ccw.nss_name, 0x40, NSS_NAME_SIZE);
 	if (nss_len > 0) {
-		reipl_block_nss->ipl_info.ccw.vm_flags |=
-			DIAG308_VM_FLAGS_NSS_VALID;
-		memcpy(reipl_block_nss->ipl_info.ccw.nss_name, buf, nss_len);
-		ASCEBC(reipl_block_nss->ipl_info.ccw.nss_name, nss_len);
-		EBC_TOUPPER(reipl_block_nss->ipl_info.ccw.nss_name, nss_len);
+		reipl_block_nss->ccw.vm_flags |= IPL_PB0_CCW_VM_FLAG_NSS;
+		memcpy(reipl_block_nss->ccw.nss_name, buf, nss_len);
+		ASCEBC(reipl_block_nss->ccw.nss_name, nss_len);
+		EBC_TOUPPER(reipl_block_nss->ccw.nss_name, nss_len);
 	} else {
-		reipl_block_nss->ipl_info.ccw.vm_flags &=
-			~DIAG308_VM_FLAGS_NSS_VALID;
+		reipl_block_nss->ccw.vm_flags &= ~IPL_PB0_CCW_VM_FLAG_NSS;
 	}
 
 	return len;
@@ -866,15 +897,21 @@ static void __reipl_run(void *unused)
 {
 	switch (reipl_type) {
 	case IPL_TYPE_CCW:
+		uv_set_shared(__pa(reipl_block_ccw));
 		diag308(DIAG308_SET, reipl_block_ccw);
+		uv_remove_shared(__pa(reipl_block_ccw));
 		diag308(DIAG308_LOAD_CLEAR, NULL);
 		break;
 	case IPL_TYPE_FCP:
+		uv_set_shared(__pa(reipl_block_fcp));
 		diag308(DIAG308_SET, reipl_block_fcp);
+		uv_remove_shared(__pa(reipl_block_fcp));
 		diag308(DIAG308_LOAD_CLEAR, NULL);
 		break;
 	case IPL_TYPE_NSS:
+		uv_set_shared(__pa(reipl_block_nss));
 		diag308(DIAG308_SET, reipl_block_nss);
+		uv_remove_shared(__pa(reipl_block_nss));
 		diag308(DIAG308_LOAD_CLEAR, NULL);
 		break;
 	case IPL_TYPE_UNKNOWN:
@@ -883,7 +920,7 @@ static void __reipl_run(void *unused)
 	case IPL_TYPE_FCP_DUMP:
 		break;
 	}
-	disabled_wait((unsigned long) __builtin_return_address(0));
+	disabled_wait();
 }
 
 static void reipl_run(struct shutdown_trigger *trigger)
@@ -893,10 +930,10 @@ static void reipl_run(struct shutdown_trigger *trigger)
 
 static void reipl_block_ccw_init(struct ipl_parameter_block *ipb)
 {
-	ipb->hdr.len = IPL_PARM_BLK_CCW_LEN;
+	ipb->hdr.len = IPL_BP_CCW_LEN;
 	ipb->hdr.version = IPL_PARM_BLOCK_VERSION;
-	ipb->hdr.blk0_len = IPL_PARM_BLK0_CCW_LEN;
-	ipb->hdr.pbt = DIAG308_IPL_TYPE_CCW;
+	ipb->pb0_hdr.len = IPL_BP0_CCW_LEN;
+	ipb->pb0_hdr.pbt = IPL_PBT_CCW;
 }
 
 static void reipl_block_ccw_fill_parms(struct ipl_parameter_block *ipb)
@@ -904,21 +941,20 @@ static void reipl_block_ccw_fill_parms(struct ipl_parameter_block *ipb)
 	/* LOADPARM */
 	/* check if read scp info worked and set loadparm */
 	if (sclp_ipl_info.is_valid)
-		memcpy(ipb->hdr.loadparm, &sclp_ipl_info.loadparm, LOADPARM_LEN);
+		memcpy(ipb->ccw.loadparm, &sclp_ipl_info.loadparm, LOADPARM_LEN);
 	else
 		/* read scp info failed: set empty loadparm (EBCDIC blanks) */
-		memset(ipb->hdr.loadparm, 0x40, LOADPARM_LEN);
-	ipb->hdr.flags = DIAG308_FLAGS_LP_VALID;
+		memset(ipb->ccw.loadparm, 0x40, LOADPARM_LEN);
+	ipb->ccw.flags = IPL_PB0_FLAG_LOADPARM;
 
 	/* VM PARM */
 	if (MACHINE_IS_VM && ipl_block_valid &&
-	    (ipl_block.ipl_info.ccw.vm_flags & DIAG308_VM_FLAGS_VP_VALID)) {
+	    (ipl_block.ccw.vm_flags & IPL_PB0_CCW_VM_FLAG_VP)) {
 
-		ipb->ipl_info.ccw.vm_flags |= DIAG308_VM_FLAGS_VP_VALID;
-		ipb->ipl_info.ccw.vm_parm_len =
-					ipl_block.ipl_info.ccw.vm_parm_len;
-		memcpy(ipb->ipl_info.ccw.vm_parm,
-		       ipl_block.ipl_info.ccw.vm_parm, DIAG308_VMPARM_SIZE);
+		ipb->ccw.vm_flags |= IPL_PB0_CCW_VM_FLAG_VP;
+		ipb->ccw.vm_parm_len = ipl_block.ccw.vm_parm_len;
+		memcpy(ipb->ccw.vm_parm,
+		       ipl_block.ccw.vm_parm, DIAG308_VMPARM_SIZE);
 	}
 }
 
@@ -958,8 +994,8 @@ static int __init reipl_ccw_init(void)
 
 	reipl_block_ccw_init(reipl_block_ccw);
 	if (ipl_info.type == IPL_TYPE_CCW) {
-		reipl_block_ccw->ipl_info.ccw.ssid = ipl_block.ipl_info.ccw.ssid;
-		reipl_block_ccw->ipl_info.ccw.devno = ipl_block.ipl_info.ccw.devno;
+		reipl_block_ccw->ccw.ssid = ipl_block.ccw.ssid;
+		reipl_block_ccw->ccw.devno = ipl_block.ccw.devno;
 		reipl_block_ccw_fill_parms(reipl_block_ccw);
 	}
 
@@ -997,14 +1033,14 @@ static int __init reipl_fcp_init(void)
 		 * is invalid in the SCSI IPL parameter block, so take it
 		 * always from sclp_ipl_info.
 		 */
-		memcpy(reipl_block_fcp->hdr.loadparm, sclp_ipl_info.loadparm,
+		memcpy(reipl_block_fcp->fcp.loadparm, sclp_ipl_info.loadparm,
 		       LOADPARM_LEN);
 	} else {
-		reipl_block_fcp->hdr.len = IPL_PARM_BLK_FCP_LEN;
+		reipl_block_fcp->hdr.len = IPL_BP_FCP_LEN;
 		reipl_block_fcp->hdr.version = IPL_PARM_BLOCK_VERSION;
-		reipl_block_fcp->hdr.blk0_len = IPL_PARM_BLK0_FCP_LEN;
-		reipl_block_fcp->hdr.pbt = DIAG308_IPL_TYPE_FCP;
-		reipl_block_fcp->ipl_info.fcp.opt = DIAG308_IPL_OPT_IPL;
+		reipl_block_fcp->fcp.len = IPL_BP0_FCP_LEN;
+		reipl_block_fcp->fcp.pbt = IPL_PBT_FCP;
+		reipl_block_fcp->fcp.opt = IPL_PB0_FCP_OPT_IPL;
 	}
 	reipl_capabilities |= IPL_TYPE_FCP;
 	return 0;
@@ -1022,10 +1058,10 @@ static int __init reipl_type_init(void)
 	/*
 	 * If we have an OS info reipl block, this will be used
 	 */
-	if (reipl_block->hdr.pbt == DIAG308_IPL_TYPE_FCP) {
+	if (reipl_block->pb0_hdr.pbt == IPL_PBT_FCP) {
 		memcpy(reipl_block_fcp, reipl_block, size);
 		reipl_type = IPL_TYPE_FCP;
-	} else if (reipl_block->hdr.pbt == DIAG308_IPL_TYPE_CCW) {
+	} else if (reipl_block->pb0_hdr.pbt == IPL_PBT_CCW) {
 		memcpy(reipl_block_ccw, reipl_block, size);
 		reipl_type = IPL_TYPE_CCW;
 	}
@@ -1070,15 +1106,15 @@ static struct shutdown_action __refdata reipl_action = {
 /* FCP dump device attributes */
 
 DEFINE_IPL_ATTR_RW(dump_fcp, wwpn, "0x%016llx\n", "%llx\n",
-		   dump_block_fcp->ipl_info.fcp.wwpn);
+		   dump_block_fcp->fcp.wwpn);
 DEFINE_IPL_ATTR_RW(dump_fcp, lun, "0x%016llx\n", "%llx\n",
-		   dump_block_fcp->ipl_info.fcp.lun);
+		   dump_block_fcp->fcp.lun);
 DEFINE_IPL_ATTR_RW(dump_fcp, bootprog, "%lld\n", "%lld\n",
-		   dump_block_fcp->ipl_info.fcp.bootprog);
+		   dump_block_fcp->fcp.bootprog);
 DEFINE_IPL_ATTR_RW(dump_fcp, br_lba, "%lld\n", "%lld\n",
-		   dump_block_fcp->ipl_info.fcp.br_lba);
+		   dump_block_fcp->fcp.br_lba);
 DEFINE_IPL_ATTR_RW(dump_fcp, device, "0.0.%04llx\n", "0.0.%llx\n",
-		   dump_block_fcp->ipl_info.fcp.devno);
+		   dump_block_fcp->fcp.devno);
 
 static struct attribute *dump_fcp_attrs[] = {
 	&sys_dump_fcp_device_attr.attr,
@@ -1095,7 +1131,7 @@ static struct attribute_group dump_fcp_attr_group = {
 };
 
 /* CCW dump device attributes */
-DEFINE_IPL_CCW_ATTR_RW(dump_ccw, device, dump_block_ccw->ipl_info.ccw);
+DEFINE_IPL_CCW_ATTR_RW(dump_ccw, device, dump_block_ccw->ccw);
 
 static struct attribute *dump_ccw_attrs[] = {
 	&sys_dump_ccw_device_attr.attr,
@@ -1145,7 +1181,9 @@ static struct kset *dump_kset;
 
 static void diag308_dump(void *dump_block)
 {
+	uv_set_shared(__pa(dump_block));
 	diag308(DIAG308_SET, dump_block);
+	uv_remove_shared(__pa(dump_block));
 	while (1) {
 		if (diag308(DIAG308_LOAD_NORMAL_DUMP, NULL) != 0x302)
 			break;
@@ -1187,10 +1225,10 @@ static int __init dump_ccw_init(void)
 		free_page((unsigned long)dump_block_ccw);
 		return rc;
 	}
-	dump_block_ccw->hdr.len = IPL_PARM_BLK_CCW_LEN;
+	dump_block_ccw->hdr.len = IPL_BP_CCW_LEN;
 	dump_block_ccw->hdr.version = IPL_PARM_BLOCK_VERSION;
-	dump_block_ccw->hdr.blk0_len = IPL_PARM_BLK0_CCW_LEN;
-	dump_block_ccw->hdr.pbt = DIAG308_IPL_TYPE_CCW;
+	dump_block_ccw->ccw.len = IPL_BP0_CCW_LEN;
+	dump_block_ccw->ccw.pbt = IPL_PBT_CCW;
 	dump_capabilities |= DUMP_TYPE_CCW;
 	return 0;
 }
@@ -1209,11 +1247,11 @@ static int __init dump_fcp_init(void)
 		free_page((unsigned long)dump_block_fcp);
 		return rc;
 	}
-	dump_block_fcp->hdr.len = IPL_PARM_BLK_FCP_LEN;
+	dump_block_fcp->hdr.len = IPL_BP_FCP_LEN;
 	dump_block_fcp->hdr.version = IPL_PARM_BLOCK_VERSION;
-	dump_block_fcp->hdr.blk0_len = IPL_PARM_BLK0_FCP_LEN;
-	dump_block_fcp->hdr.pbt = DIAG308_IPL_TYPE_FCP;
-	dump_block_fcp->ipl_info.fcp.opt = DIAG308_IPL_OPT_DUMP;
+	dump_block_fcp->fcp.len = IPL_BP0_FCP_LEN;
+	dump_block_fcp->fcp.pbt = IPL_PBT_FCP;
+	dump_block_fcp->fcp.opt = IPL_PB0_FCP_OPT_DUMP;
 	dump_capabilities |= DUMP_TYPE_FCP;
 	return 0;
 }
@@ -1337,7 +1375,7 @@ static void stop_run(struct shutdown_trigger *trigger)
 {
 	if (strcmp(trigger->name, ON_PANIC_STR) == 0 ||
 	    strcmp(trigger->name, ON_RESTART_STR) == 0)
-		disabled_wait((unsigned long) __builtin_return_address(0));
+		disabled_wait();
 	smp_stop_cpu();
 }
 
@@ -1572,7 +1610,7 @@ static int __init s390_ipl_init(void)
 	 * READ SCP info provides the correct value.
 	 */
 	if (memcmp(sclp_ipl_info.loadparm, str, sizeof(str)) == 0 && ipl_block_valid)
-		memcpy(sclp_ipl_info.loadparm, ipl_block.hdr.loadparm, LOADPARM_LEN);
+		memcpy(sclp_ipl_info.loadparm, ipl_block.ccw.loadparm, LOADPARM_LEN);
 	shutdown_actions_init();
 	shutdown_triggers_init();
 	return 0;
@@ -1657,15 +1695,15 @@ void __init setup_ipl(void)
 	ipl_info.type = get_ipl_type();
 	switch (ipl_info.type) {
 	case IPL_TYPE_CCW:
-		ipl_info.data.ccw.dev_id.ssid = ipl_block.ipl_info.ccw.ssid;
-		ipl_info.data.ccw.dev_id.devno = ipl_block.ipl_info.ccw.devno;
+		ipl_info.data.ccw.dev_id.ssid = ipl_block.ccw.ssid;
+		ipl_info.data.ccw.dev_id.devno = ipl_block.ccw.devno;
 		break;
 	case IPL_TYPE_FCP:
 	case IPL_TYPE_FCP_DUMP:
 		ipl_info.data.fcp.dev_id.ssid = 0;
-		ipl_info.data.fcp.dev_id.devno = ipl_block.ipl_info.fcp.devno;
-		ipl_info.data.fcp.wwpn = ipl_block.ipl_info.fcp.wwpn;
-		ipl_info.data.fcp.lun = ipl_block.ipl_info.fcp.lun;
+		ipl_info.data.fcp.dev_id.devno = ipl_block.fcp.devno;
+		ipl_info.data.fcp.wwpn = ipl_block.fcp.wwpn;
+		ipl_info.data.fcp.lun = ipl_block.fcp.lun;
 		break;
 	case IPL_TYPE_NSS:
 	case IPL_TYPE_UNKNOWN:
@@ -1675,14 +1713,6 @@ void __init setup_ipl(void)
 	atomic_notifier_chain_register(&panic_notifier_list, &on_panic_nb);
 }
 
-void __init ipl_store_parameters(void)
-{
-	if (early_ipl_block_valid) {
-		memcpy(&ipl_block, &early_ipl_block, sizeof(ipl_block));
-		ipl_block_valid = 1;
-	}
-}
-
 void s390_reset_system(void)
 {
 	/* Disable prefixing */
@@ -1690,5 +1720,139 @@ void s390_reset_system(void)
 
 	/* Disable lowcore protection */
 	__ctl_clear_bit(0, 28);
-	diag308_reset();
+	diag_dma_ops.diag308_reset();
+}
+
+#ifdef CONFIG_KEXEC_FILE
+
+int ipl_report_add_component(struct ipl_report *report, struct kexec_buf *kbuf,
+			     unsigned char flags, unsigned short cert)
+{
+	struct ipl_report_component *comp;
+
+	comp = vzalloc(sizeof(*comp));
+	if (!comp)
+		return -ENOMEM;
+	list_add_tail(&comp->list, &report->components);
+
+	comp->entry.addr = kbuf->mem;
+	comp->entry.len = kbuf->memsz;
+	comp->entry.flags = flags;
+	comp->entry.certificate_index = cert;
+
+	report->size += sizeof(comp->entry);
+
+	return 0;
+}
+
+int ipl_report_add_certificate(struct ipl_report *report, void *key,
+			       unsigned long addr, unsigned long len)
+{
+	struct ipl_report_certificate *cert;
+
+	cert = vzalloc(sizeof(*cert));
+	if (!cert)
+		return -ENOMEM;
+	list_add_tail(&cert->list, &report->certificates);
+
+	cert->entry.addr = addr;
+	cert->entry.len = len;
+	cert->key = key;
+
+	report->size += sizeof(cert->entry);
+	report->size += cert->entry.len;
+
+	return 0;
+}
+
+struct ipl_report *ipl_report_init(struct ipl_parameter_block *ipib)
+{
+	struct ipl_report *report;
+
+	report = vzalloc(sizeof(*report));
+	if (!report)
+		return ERR_PTR(-ENOMEM);
+
+	report->ipib = ipib;
+	INIT_LIST_HEAD(&report->components);
+	INIT_LIST_HEAD(&report->certificates);
+
+	report->size = ALIGN(ipib->hdr.len, 8);
+	report->size += sizeof(struct ipl_rl_hdr);
+	report->size += sizeof(struct ipl_rb_components);
+	report->size += sizeof(struct ipl_rb_certificates);
+
+	return report;
+}
+
+void *ipl_report_finish(struct ipl_report *report)
+{
+	struct ipl_report_certificate *cert;
+	struct ipl_report_component *comp;
+	struct ipl_rb_certificates *certs;
+	struct ipl_parameter_block *ipib;
+	struct ipl_rb_components *comps;
+	struct ipl_rl_hdr *rl_hdr;
+	void *buf, *ptr;
+
+	buf = vzalloc(report->size);
+	if (!buf)
+		return ERR_PTR(-ENOMEM);
+	ptr = buf;
+
+	memcpy(ptr, report->ipib, report->ipib->hdr.len);
+	ipib = ptr;
+	if (ipl_secure_flag)
+		ipib->hdr.flags |= IPL_PL_FLAG_SIPL;
+	ipib->hdr.flags |= IPL_PL_FLAG_IPLSR;
+	ptr += report->ipib->hdr.len;
+	ptr = PTR_ALIGN(ptr, 8);
+
+	rl_hdr = ptr;
+	ptr += sizeof(*rl_hdr);
+
+	comps = ptr;
+	comps->rbt = IPL_RBT_COMPONENTS;
+	ptr += sizeof(*comps);
+	list_for_each_entry(comp, &report->components, list) {
+		memcpy(ptr, &comp->entry, sizeof(comp->entry));
+		ptr += sizeof(comp->entry);
+	}
+	comps->len = ptr - (void *)comps;
+
+	certs = ptr;
+	certs->rbt = IPL_RBT_CERTIFICATES;
+	ptr += sizeof(*certs);
+	list_for_each_entry(cert, &report->certificates, list) {
+		memcpy(ptr, &cert->entry, sizeof(cert->entry));
+		ptr += sizeof(cert->entry);
+	}
+	certs->len = ptr - (void *)certs;
+	rl_hdr->len = ptr - (void *)rl_hdr;
+
+	list_for_each_entry(cert, &report->certificates, list) {
+		memcpy(ptr, cert->key, cert->entry.len);
+		ptr += cert->entry.len;
+	}
+
+	BUG_ON(ptr > buf + report->size);
+	return buf;
+}
+
+int ipl_report_free(struct ipl_report *report)
+{
+	struct ipl_report_component *comp, *ncomp;
+	struct ipl_report_certificate *cert, *ncert;
+
+	list_for_each_entry_safe(comp, ncomp, &report->components, list)
+		vfree(comp);
+
+	list_for_each_entry_safe(cert, ncert, &report->certificates, list)
+		vfree(cert);
+
+	vfree(report);
+
+	return 0;
 }
+
+#endif
diff --git a/arch/s390/kernel/ipl_vmparm.c b/arch/s390/kernel/ipl_vmparm.c
index 411838c0a0af..af43535a976d 100644
--- a/arch/s390/kernel/ipl_vmparm.c
+++ b/arch/s390/kernel/ipl_vmparm.c
@@ -11,11 +11,11 @@ size_t ipl_block_get_ascii_vmparm(char *dest, size_t size,
 	char has_lowercase = 0;
 
 	len = 0;
-	if ((ipb->ipl_info.ccw.vm_flags & DIAG308_VM_FLAGS_VP_VALID) &&
-	    (ipb->ipl_info.ccw.vm_parm_len > 0)) {
+	if ((ipb->ccw.vm_flags & IPL_PB0_CCW_VM_FLAG_VP) &&
+	    (ipb->ccw.vm_parm_len > 0)) {
 
-		len = min_t(size_t, size - 1, ipb->ipl_info.ccw.vm_parm_len);
-		memcpy(dest, ipb->ipl_info.ccw.vm_parm, len);
+		len = min_t(size_t, size - 1, ipb->ccw.vm_parm_len);
+		memcpy(dest, ipb->ccw.vm_parm, len);
 		/* If at least one character is lowercase, we assume mixed
 		 * case; otherwise we convert everything to lowercase.
 		 */
diff --git a/arch/s390/kernel/irq.c b/arch/s390/kernel/irq.c
index 0cd5a5f96729..8371855042dc 100644
--- a/arch/s390/kernel/irq.c
+++ b/arch/s390/kernel/irq.c
@@ -26,6 +26,7 @@
 #include <asm/lowcore.h>
 #include <asm/irq.h>
 #include <asm/hw_irq.h>
+#include <asm/stacktrace.h>
 #include "entry.h"
 
 DEFINE_PER_CPU_SHARED_ALIGNED(struct irq_stat, irq_stat);
@@ -73,7 +74,6 @@ static const struct irq_class irqclass_sub_desc[] = {
 	{.irq = IRQEXT_CMC, .name = "CMC", .desc = "[EXT] CPU-Measurement: Counter"},
 	{.irq = IRQEXT_FTP, .name = "FTP", .desc = "[EXT] HMC FTP Service"},
 	{.irq = IRQIO_CIO,  .name = "CIO", .desc = "[I/O] Common I/O Layer Interrupt"},
-	{.irq = IRQIO_QAI,  .name = "QAI", .desc = "[I/O] QDIO Adapter Interrupt"},
 	{.irq = IRQIO_DAS,  .name = "DAS", .desc = "[I/O] DASD"},
 	{.irq = IRQIO_C15,  .name = "C15", .desc = "[I/O] 3215"},
 	{.irq = IRQIO_C70,  .name = "C70", .desc = "[I/O] 3270"},
@@ -81,14 +81,16 @@ static const struct irq_class irqclass_sub_desc[] = {
 	{.irq = IRQIO_VMR,  .name = "VMR", .desc = "[I/O] Unit Record Devices"},
 	{.irq = IRQIO_LCS,  .name = "LCS", .desc = "[I/O] LCS"},
 	{.irq = IRQIO_CTC,  .name = "CTC", .desc = "[I/O] CTC"},
-	{.irq = IRQIO_APB,  .name = "APB", .desc = "[I/O] AP Bus"},
 	{.irq = IRQIO_ADM,  .name = "ADM", .desc = "[I/O] EADM Subchannel"},
 	{.irq = IRQIO_CSC,  .name = "CSC", .desc = "[I/O] CHSC Subchannel"},
-	{.irq = IRQIO_PCI,  .name = "PCI", .desc = "[I/O] PCI Interrupt" },
-	{.irq = IRQIO_MSI,  .name = "MSI", .desc = "[I/O] MSI Interrupt" },
 	{.irq = IRQIO_VIR,  .name = "VIR", .desc = "[I/O] Virtual I/O Devices"},
-	{.irq = IRQIO_VAI,  .name = "VAI", .desc = "[I/O] Virtual I/O Devices AI"},
-	{.irq = IRQIO_GAL,  .name = "GAL", .desc = "[I/O] GIB Alert"},
+	{.irq = IRQIO_QAI,  .name = "QAI", .desc = "[AIO] QDIO Adapter Interrupt"},
+	{.irq = IRQIO_APB,  .name = "APB", .desc = "[AIO] AP Bus"},
+	{.irq = IRQIO_PCF,  .name = "PCF", .desc = "[AIO] PCI Floating Interrupt"},
+	{.irq = IRQIO_PCD,  .name = "PCD", .desc = "[AIO] PCI Directed Interrupt"},
+	{.irq = IRQIO_MSI,  .name = "MSI", .desc = "[AIO] MSI Interrupt"},
+	{.irq = IRQIO_VAI,  .name = "VAI", .desc = "[AIO] Virtual I/O Devices AI"},
+	{.irq = IRQIO_GAL,  .name = "GAL", .desc = "[AIO] GIB Alert"},
 	{.irq = NMI_NMI,    .name = "NMI", .desc = "[NMI] Machine Check"},
 	{.irq = CPU_RST,    .name = "RST", .desc = "[CPU] CPU Restart"},
 };
@@ -116,6 +118,34 @@ void do_IRQ(struct pt_regs *regs, int irq)
 	set_irq_regs(old_regs);
 }
 
+static void show_msi_interrupt(struct seq_file *p, int irq)
+{
+	struct irq_desc *desc;
+	unsigned long flags;
+	int cpu;
+
+	irq_lock_sparse();
+	desc = irq_to_desc(irq);
+	if (!desc)
+		goto out;
+
+	raw_spin_lock_irqsave(&desc->lock, flags);
+	seq_printf(p, "%3d: ", irq);
+	for_each_online_cpu(cpu)
+		seq_printf(p, "%10u ", kstat_irqs_cpu(irq, cpu));
+
+	if (desc->irq_data.chip)
+		seq_printf(p, " %8s", desc->irq_data.chip->name);
+
+	if (desc->action)
+		seq_printf(p, "  %s", desc->action->name);
+
+	seq_putc(p, '\n');
+	raw_spin_unlock_irqrestore(&desc->lock, flags);
+out:
+	irq_unlock_sparse();
+}
+
 /*
  * show_interrupts is needed by /proc/interrupts.
  */
@@ -128,7 +158,7 @@ int show_interrupts(struct seq_file *p, void *v)
 	if (index == 0) {
 		seq_puts(p, "           ");
 		for_each_online_cpu(cpu)
-			seq_printf(p, "CPU%d       ", cpu);
+			seq_printf(p, "CPU%-8d", cpu);
 		seq_putc(p, '\n');
 	}
 	if (index < NR_IRQS_BASE) {
@@ -139,9 +169,10 @@ int show_interrupts(struct seq_file *p, void *v)
 		seq_putc(p, '\n');
 		goto out;
 	}
-	if (index > NR_IRQS_BASE)
+	if (index < nr_irqs) {
+		show_msi_interrupt(p, index);
 		goto out;
-
+	}
 	for (index = 0; index < NR_ARCH_IRQS; index++) {
 		seq_printf(p, "%s: ", irqclass_sub_desc[index].name);
 		irq = irqclass_sub_desc[index].irq;
diff --git a/arch/s390/kernel/kexec_elf.c b/arch/s390/kernel/kexec_elf.c
index 5a286b012043..6d0635ceddd0 100644
--- a/arch/s390/kernel/kexec_elf.c
+++ b/arch/s390/kernel/kexec_elf.c
@@ -10,19 +10,26 @@
 #include <linux/errno.h>
 #include <linux/kernel.h>
 #include <linux/kexec.h>
+#include <asm/ipl.h>
 #include <asm/setup.h>
 
-static int kexec_file_add_elf_kernel(struct kimage *image,
-				     struct s390_load_data *data,
-				     char *kernel, unsigned long kernel_len)
+static int kexec_file_add_kernel_elf(struct kimage *image,
+				     struct s390_load_data *data)
 {
 	struct kexec_buf buf;
 	const Elf_Ehdr *ehdr;
 	const Elf_Phdr *phdr;
+	Elf_Addr entry;
+	void *kernel;
 	int i, ret;
 
+	kernel = image->kernel_buf;
 	ehdr = (Elf_Ehdr *)kernel;
 	buf.image = image;
+	if (image->type == KEXEC_TYPE_CRASH)
+		entry = STARTUP_KDUMP_OFFSET;
+	else
+		entry = ehdr->e_entry;
 
 	phdr = (void *)ehdr + ehdr->e_phoff;
 	for (i = 0; i < ehdr->e_phnum; i++, phdr++) {
@@ -33,30 +40,27 @@ static int kexec_file_add_elf_kernel(struct kimage *image,
 		buf.bufsz = phdr->p_filesz;
 
 		buf.mem = ALIGN(phdr->p_paddr, phdr->p_align);
+		if (image->type == KEXEC_TYPE_CRASH)
+			buf.mem += crashk_res.start;
 		buf.memsz = phdr->p_memsz;
+		data->memsz = ALIGN(data->memsz, phdr->p_align) + buf.memsz;
 
-		if (phdr->p_paddr == 0) {
+		if (entry - phdr->p_paddr < phdr->p_memsz) {
 			data->kernel_buf = buf.buffer;
-			data->memsz += STARTUP_NORMAL_OFFSET;
-
-			buf.buffer += STARTUP_NORMAL_OFFSET;
-			buf.bufsz -= STARTUP_NORMAL_OFFSET;
-
-			buf.mem += STARTUP_NORMAL_OFFSET;
-			buf.memsz -= STARTUP_NORMAL_OFFSET;
+			data->kernel_mem = buf.mem;
+			data->parm = buf.buffer + PARMAREA;
 		}
 
-		if (image->type == KEXEC_TYPE_CRASH)
-			buf.mem += crashk_res.start;
-
+		ipl_report_add_component(data->report, &buf,
+					 IPL_RB_COMPONENT_FLAG_SIGNED |
+					 IPL_RB_COMPONENT_FLAG_VERIFIED,
+					 IPL_RB_CERT_UNKNOWN);
 		ret = kexec_add_buffer(&buf);
 		if (ret)
 			return ret;
-
-		data->memsz += buf.memsz;
 	}
 
-	return 0;
+	return data->memsz ? 0 : -EINVAL;
 }
 
 static void *s390_elf_load(struct kimage *image,
@@ -64,11 +68,10 @@ static void *s390_elf_load(struct kimage *image,
 			   char *initrd, unsigned long initrd_len,
 			   char *cmdline, unsigned long cmdline_len)
 {
-	struct s390_load_data data = {0};
 	const Elf_Ehdr *ehdr;
 	const Elf_Phdr *phdr;
 	size_t size;
-	int i, ret;
+	int i;
 
 	/* image->fobs->probe already checked for valid ELF magic number. */
 	ehdr = (Elf_Ehdr *)kernel;
@@ -101,24 +104,7 @@ static void *s390_elf_load(struct kimage *image,
 	if (size > kernel_len)
 		return ERR_PTR(-EINVAL);
 
-	ret = kexec_file_add_elf_kernel(image, &data, kernel, kernel_len);
-	if (ret)
-		return ERR_PTR(ret);
-
-	if (!data.memsz)
-		return ERR_PTR(-EINVAL);
-
-	if (initrd) {
-		ret = kexec_file_add_initrd(image, &data, initrd, initrd_len);
-		if (ret)
-			return ERR_PTR(ret);
-	}
-
-	ret = kexec_file_add_purgatory(image, &data);
-	if (ret)
-		return ERR_PTR(ret);
-
-	return kexec_file_update_kernel(image, &data);
+	return kexec_file_add_components(image, kexec_file_add_kernel_elf);
 }
 
 static int s390_elf_probe(const char *buf, unsigned long len)
@@ -144,4 +130,7 @@ static int s390_elf_probe(const char *buf, unsigned long len)
 const struct kexec_file_ops s390_kexec_elf_ops = {
 	.probe = s390_elf_probe,
 	.load = s390_elf_load,
+#ifdef CONFIG_KEXEC_VERIFY_SIG
+	.verify_sig = s390_verify_sig,
+#endif /* CONFIG_KEXEC_VERIFY_SIG */
 };
diff --git a/arch/s390/kernel/kexec_image.c b/arch/s390/kernel/kexec_image.c
index 3800852595e8..58318bf89fd9 100644
--- a/arch/s390/kernel/kexec_image.c
+++ b/arch/s390/kernel/kexec_image.c
@@ -10,31 +10,34 @@
 #include <linux/errno.h>
 #include <linux/kernel.h>
 #include <linux/kexec.h>
+#include <asm/ipl.h>
 #include <asm/setup.h>
 
-static int kexec_file_add_image_kernel(struct kimage *image,
-				       struct s390_load_data *data,
-				       char *kernel, unsigned long kernel_len)
+static int kexec_file_add_kernel_image(struct kimage *image,
+				       struct s390_load_data *data)
 {
 	struct kexec_buf buf;
-	int ret;
 
 	buf.image = image;
 
-	buf.buffer = kernel + STARTUP_NORMAL_OFFSET;
-	buf.bufsz = kernel_len - STARTUP_NORMAL_OFFSET;
+	buf.buffer = image->kernel_buf;
+	buf.bufsz = image->kernel_buf_len;
 
-	buf.mem = STARTUP_NORMAL_OFFSET;
+	buf.mem = 0;
 	if (image->type == KEXEC_TYPE_CRASH)
 		buf.mem += crashk_res.start;
 	buf.memsz = buf.bufsz;
 
-	ret = kexec_add_buffer(&buf);
+	data->kernel_buf = image->kernel_buf;
+	data->kernel_mem = buf.mem;
+	data->parm = image->kernel_buf + PARMAREA;
+	data->memsz += buf.memsz;
 
-	data->kernel_buf = kernel;
-	data->memsz += buf.memsz + STARTUP_NORMAL_OFFSET;
-
-	return ret;
+	ipl_report_add_component(data->report, &buf,
+				 IPL_RB_COMPONENT_FLAG_SIGNED |
+				 IPL_RB_COMPONENT_FLAG_VERIFIED,
+				 IPL_RB_CERT_UNKNOWN);
+	return kexec_add_buffer(&buf);
 }
 
 static void *s390_image_load(struct kimage *image,
@@ -42,24 +45,7 @@ static void *s390_image_load(struct kimage *image,
 			     char *initrd, unsigned long initrd_len,
 			     char *cmdline, unsigned long cmdline_len)
 {
-	struct s390_load_data data = {0};
-	int ret;
-
-	ret = kexec_file_add_image_kernel(image, &data, kernel, kernel_len);
-	if (ret)
-		return ERR_PTR(ret);
-
-	if (initrd) {
-		ret = kexec_file_add_initrd(image, &data, initrd, initrd_len);
-		if (ret)
-			return ERR_PTR(ret);
-	}
-
-	ret = kexec_file_add_purgatory(image, &data);
-	if (ret)
-		return ERR_PTR(ret);
-
-	return kexec_file_update_kernel(image, &data);
+	return kexec_file_add_components(image, kexec_file_add_kernel_image);
 }
 
 static int s390_image_probe(const char *buf, unsigned long len)
@@ -73,4 +59,7 @@ static int s390_image_probe(const char *buf, unsigned long len)
 const struct kexec_file_ops s390_kexec_image_ops = {
 	.probe = s390_image_probe,
 	.load = s390_image_load,
+#ifdef CONFIG_KEXEC_VERIFY_SIG
+	.verify_sig = s390_verify_sig,
+#endif /* CONFIG_KEXEC_VERIFY_SIG */
 };
diff --git a/arch/s390/kernel/kprobes.c b/arch/s390/kernel/kprobes.c
index 7c0a095e9c5f..6f1388391620 100644
--- a/arch/s390/kernel/kprobes.c
+++ b/arch/s390/kernel/kprobes.c
@@ -27,29 +27,30 @@ DEFINE_PER_CPU(struct kprobe_ctlblk, kprobe_ctlblk);
 
 struct kretprobe_blackpoint kretprobe_blacklist[] = { };
 
-DEFINE_INSN_CACHE_OPS(dmainsn);
+DEFINE_INSN_CACHE_OPS(s390_insn);
 
-static void *alloc_dmainsn_page(void)
-{
-	void *page;
+static int insn_page_in_use;
+static char insn_page[PAGE_SIZE] __aligned(PAGE_SIZE);
 
-	page = (void *) __get_free_page(GFP_KERNEL | GFP_DMA);
-	if (page)
-		set_memory_x((unsigned long) page, 1);
-	return page;
+static void *alloc_s390_insn_page(void)
+{
+	if (xchg(&insn_page_in_use, 1) == 1)
+		return NULL;
+	set_memory_x((unsigned long) &insn_page, 1);
+	return &insn_page;
 }
 
-static void free_dmainsn_page(void *page)
+static void free_s390_insn_page(void *page)
 {
 	set_memory_nx((unsigned long) page, 1);
-	free_page((unsigned long)page);
+	xchg(&insn_page_in_use, 0);
 }
 
-struct kprobe_insn_cache kprobe_dmainsn_slots = {
-	.mutex = __MUTEX_INITIALIZER(kprobe_dmainsn_slots.mutex),
-	.alloc = alloc_dmainsn_page,
-	.free = free_dmainsn_page,
-	.pages = LIST_HEAD_INIT(kprobe_dmainsn_slots.pages),
+struct kprobe_insn_cache kprobe_s390_insn_slots = {
+	.mutex = __MUTEX_INITIALIZER(kprobe_s390_insn_slots.mutex),
+	.alloc = alloc_s390_insn_page,
+	.free = free_s390_insn_page,
+	.pages = LIST_HEAD_INIT(kprobe_s390_insn_slots.pages),
 	.insn_size = MAX_INSN_SIZE,
 };
 
@@ -102,7 +103,7 @@ static int s390_get_insn_slot(struct kprobe *p)
 	 */
 	p->ainsn.insn = NULL;
 	if (is_kernel_addr(p->addr))
-		p->ainsn.insn = get_dmainsn_slot();
+		p->ainsn.insn = get_s390_insn_slot();
 	else if (is_module_addr(p->addr))
 		p->ainsn.insn = get_insn_slot();
 	return p->ainsn.insn ? 0 : -ENOMEM;
@@ -114,7 +115,7 @@ static void s390_free_insn_slot(struct kprobe *p)
 	if (!p->ainsn.insn)
 		return;
 	if (is_kernel_addr(p->addr))
-		free_dmainsn_slot(p->ainsn.insn, 0);
+		free_s390_insn_slot(p->ainsn.insn, 0);
 	else
 		free_insn_slot(p->ainsn.insn, 0);
 	p->ainsn.insn = NULL;
@@ -572,7 +573,7 @@ static int kprobe_trap_handler(struct pt_regs *regs, int trapnr)
 		 * In case the user-specified fault handler returned
 		 * zero, try to fix up.
 		 */
-		entry = search_exception_tables(regs->psw.addr);
+		entry = s390_search_extables(regs->psw.addr);
 		if (entry) {
 			regs->psw.addr = extable_fixup(entry);
 			return 1;
diff --git a/arch/s390/kernel/machine_kexec.c b/arch/s390/kernel/machine_kexec.c
index cb582649aba6..8a1ae140c5e2 100644
--- a/arch/s390/kernel/machine_kexec.c
+++ b/arch/s390/kernel/machine_kexec.c
@@ -27,6 +27,7 @@
 #include <asm/cacheflush.h>
 #include <asm/os_info.h>
 #include <asm/set_memory.h>
+#include <asm/stacktrace.h>
 #include <asm/switch_to.h>
 #include <asm/nmi.h>
 
@@ -95,7 +96,7 @@ static void __do_machine_kdump(void *image)
 	start_kdump(1);
 
 	/* Die if start_kdump returns */
-	disabled_wait((unsigned long) __builtin_return_address(0));
+	disabled_wait();
 }
 
 /*
@@ -253,6 +254,9 @@ void arch_crash_save_vmcoreinfo(void)
 	VMCOREINFO_SYMBOL(high_memory);
 	VMCOREINFO_LENGTH(lowcore_ptr, NR_CPUS);
 	mem_assign_absolute(S390_lowcore.vmcore_info, paddr_vmcoreinfo_note());
+	vmcoreinfo_append_str("SDMA=%lx\n", __sdma);
+	vmcoreinfo_append_str("EDMA=%lx\n", __edma);
+	vmcoreinfo_append_str("KERNELOFFSET=%lx\n", kaslr_offset());
 }
 
 void machine_shutdown(void)
@@ -280,7 +284,7 @@ static void __do_machine_kexec(void *data)
 	(*data_mover)(&image->head, image->start);
 
 	/* Die if kexec returns */
-	disabled_wait((unsigned long) __builtin_return_address(0));
+	disabled_wait();
 }
 
 /*
diff --git a/arch/s390/kernel/machine_kexec_file.c b/arch/s390/kernel/machine_kexec_file.c
index 32023b4f9dc0..fbdd3ea73667 100644
--- a/arch/s390/kernel/machine_kexec_file.c
+++ b/arch/s390/kernel/machine_kexec_file.c
@@ -8,7 +8,12 @@
  */
 
 #include <linux/elf.h>
+#include <linux/errno.h>
 #include <linux/kexec.h>
+#include <linux/module.h>
+#include <linux/verification.h>
+#include <asm/boot_data.h>
+#include <asm/ipl.h>
 #include <asm/setup.h>
 
 const struct kexec_file_ops * const kexec_file_loaders[] = {
@@ -17,38 +22,78 @@ const struct kexec_file_ops * const kexec_file_loaders[] = {
 	NULL,
 };
 
-int *kexec_file_update_kernel(struct kimage *image,
-			      struct s390_load_data *data)
-{
-	unsigned long *loc;
-
-	if (image->cmdline_buf_len >= ARCH_COMMAND_LINE_SIZE)
-		return ERR_PTR(-EINVAL);
-
-	if (image->cmdline_buf_len)
-		memcpy(data->kernel_buf + COMMAND_LINE_OFFSET,
-		       image->cmdline_buf, image->cmdline_buf_len);
-
-	if (image->type == KEXEC_TYPE_CRASH) {
-		loc = (unsigned long *)(data->kernel_buf + OLDMEM_BASE_OFFSET);
-		*loc = crashk_res.start;
-
-		loc = (unsigned long *)(data->kernel_buf + OLDMEM_SIZE_OFFSET);
-		*loc = crashk_res.end - crashk_res.start + 1;
-	}
+#ifdef CONFIG_KEXEC_VERIFY_SIG
+/*
+ * Module signature information block.
+ *
+ * The constituents of the signature section are, in order:
+ *
+ *	- Signer's name
+ *	- Key identifier
+ *	- Signature data
+ *	- Information block
+ */
+struct module_signature {
+	u8	algo;		/* Public-key crypto algorithm [0] */
+	u8	hash;		/* Digest algorithm [0] */
+	u8	id_type;	/* Key identifier type [PKEY_ID_PKCS7] */
+	u8	signer_len;	/* Length of signer's name [0] */
+	u8	key_id_len;	/* Length of key identifier [0] */
+	u8	__pad[3];
+	__be32	sig_len;	/* Length of signature data */
+};
 
-	if (image->initrd_buf) {
-		loc = (unsigned long *)(data->kernel_buf + INITRD_START_OFFSET);
-		*loc = data->initrd_load_addr;
+#define PKEY_ID_PKCS7 2
 
-		loc = (unsigned long *)(data->kernel_buf + INITRD_SIZE_OFFSET);
-		*loc = image->initrd_buf_len;
+int s390_verify_sig(const char *kernel, unsigned long kernel_len)
+{
+	const unsigned long marker_len = sizeof(MODULE_SIG_STRING) - 1;
+	struct module_signature *ms;
+	unsigned long sig_len;
+
+	/* Skip signature verification when not secure IPLed. */
+	if (!ipl_secure_flag)
+		return 0;
+
+	if (marker_len > kernel_len)
+		return -EKEYREJECTED;
+
+	if (memcmp(kernel + kernel_len - marker_len, MODULE_SIG_STRING,
+		   marker_len))
+		return -EKEYREJECTED;
+	kernel_len -= marker_len;
+
+	ms = (void *)kernel + kernel_len - sizeof(*ms);
+	kernel_len -= sizeof(*ms);
+
+	sig_len = be32_to_cpu(ms->sig_len);
+	if (sig_len >= kernel_len)
+		return -EKEYREJECTED;
+	kernel_len -= sig_len;
+
+	if (ms->id_type != PKEY_ID_PKCS7)
+		return -EKEYREJECTED;
+
+	if (ms->algo != 0 ||
+	    ms->hash != 0 ||
+	    ms->signer_len != 0 ||
+	    ms->key_id_len != 0 ||
+	    ms->__pad[0] != 0 ||
+	    ms->__pad[1] != 0 ||
+	    ms->__pad[2] != 0) {
+		return -EBADMSG;
 	}
 
-	return NULL;
+	return verify_pkcs7_signature(kernel, kernel_len,
+				      kernel + kernel_len, sig_len,
+				      VERIFY_USE_PLATFORM_KEYRING,
+				      VERIFYING_MODULE_SIGNATURE,
+				      NULL, NULL);
 }
+#endif /* CONFIG_KEXEC_VERIFY_SIG */
 
-static int kexec_file_update_purgatory(struct kimage *image)
+static int kexec_file_update_purgatory(struct kimage *image,
+				       struct s390_load_data *data)
 {
 	u64 entry, type;
 	int ret;
@@ -90,7 +135,8 @@ static int kexec_file_update_purgatory(struct kimage *image)
 	return ret;
 }
 
-int kexec_file_add_purgatory(struct kimage *image, struct s390_load_data *data)
+static int kexec_file_add_purgatory(struct kimage *image,
+				    struct s390_load_data *data)
 {
 	struct kexec_buf buf;
 	int ret;
@@ -105,21 +151,21 @@ int kexec_file_add_purgatory(struct kimage *image, struct s390_load_data *data)
 	ret = kexec_load_purgatory(image, &buf);
 	if (ret)
 		return ret;
+	data->memsz += buf.memsz;
 
-	ret = kexec_file_update_purgatory(image);
-	return ret;
+	return kexec_file_update_purgatory(image, data);
 }
 
-int kexec_file_add_initrd(struct kimage *image, struct s390_load_data *data,
-			  char *initrd, unsigned long initrd_len)
+static int kexec_file_add_initrd(struct kimage *image,
+				 struct s390_load_data *data)
 {
 	struct kexec_buf buf;
 	int ret;
 
 	buf.image = image;
 
-	buf.buffer = initrd;
-	buf.bufsz = initrd_len;
+	buf.buffer = image->initrd_buf;
+	buf.bufsz = image->initrd_buf_len;
 
 	data->memsz = ALIGN(data->memsz, PAGE_SIZE);
 	buf.mem = data->memsz;
@@ -127,11 +173,115 @@ int kexec_file_add_initrd(struct kimage *image, struct s390_load_data *data,
 		buf.mem += crashk_res.start;
 	buf.memsz = buf.bufsz;
 
-	data->initrd_load_addr = buf.mem;
+	data->parm->initrd_start = buf.mem;
+	data->parm->initrd_size = buf.memsz;
 	data->memsz += buf.memsz;
 
 	ret = kexec_add_buffer(&buf);
-	return ret;
+	if (ret)
+		return ret;
+
+	return ipl_report_add_component(data->report, &buf, 0, 0);
+}
+
+static int kexec_file_add_ipl_report(struct kimage *image,
+				     struct s390_load_data *data)
+{
+	__u32 *lc_ipl_parmblock_ptr;
+	unsigned int len, ncerts;
+	struct kexec_buf buf;
+	unsigned long addr;
+	void *ptr, *end;
+
+	buf.image = image;
+
+	data->memsz = ALIGN(data->memsz, PAGE_SIZE);
+	buf.mem = data->memsz;
+	if (image->type == KEXEC_TYPE_CRASH)
+		buf.mem += crashk_res.start;
+
+	ptr = (void *)ipl_cert_list_addr;
+	end = ptr + ipl_cert_list_size;
+	ncerts = 0;
+	while (ptr < end) {
+		ncerts++;
+		len = *(unsigned int *)ptr;
+		ptr += sizeof(len);
+		ptr += len;
+	}
+
+	addr = data->memsz + data->report->size;
+	addr += ncerts * sizeof(struct ipl_rb_certificate_entry);
+	ptr = (void *)ipl_cert_list_addr;
+	while (ptr < end) {
+		len = *(unsigned int *)ptr;
+		ptr += sizeof(len);
+		ipl_report_add_certificate(data->report, ptr, addr, len);
+		addr += len;
+		ptr += len;
+	}
+
+	buf.buffer = ipl_report_finish(data->report);
+	buf.bufsz = data->report->size;
+	buf.memsz = buf.bufsz;
+
+	data->memsz += buf.memsz;
+
+	lc_ipl_parmblock_ptr =
+		data->kernel_buf + offsetof(struct lowcore, ipl_parmblock_ptr);
+	*lc_ipl_parmblock_ptr = (__u32)buf.mem;
+
+	return kexec_add_buffer(&buf);
+}
+
+void *kexec_file_add_components(struct kimage *image,
+				int (*add_kernel)(struct kimage *image,
+						  struct s390_load_data *data))
+{
+	struct s390_load_data data = {0};
+	int ret;
+
+	data.report = ipl_report_init(&ipl_block);
+	if (IS_ERR(data.report))
+		return data.report;
+
+	ret = add_kernel(image, &data);
+	if (ret)
+		goto out;
+
+	if (image->cmdline_buf_len >= ARCH_COMMAND_LINE_SIZE) {
+		ret = -EINVAL;
+		goto out;
+	}
+	memcpy(data.parm->command_line, image->cmdline_buf,
+	       image->cmdline_buf_len);
+
+	if (image->type == KEXEC_TYPE_CRASH) {
+		data.parm->oldmem_base = crashk_res.start;
+		data.parm->oldmem_size = crashk_res.end - crashk_res.start + 1;
+	}
+
+	if (image->initrd_buf) {
+		ret = kexec_file_add_initrd(image, &data);
+		if (ret)
+			goto out;
+	}
+
+	ret = kexec_file_add_purgatory(image, &data);
+	if (ret)
+		goto out;
+
+	if (data.kernel_mem == 0) {
+		unsigned long restart_psw =  0x0008000080000000UL;
+		restart_psw += image->start;
+		memcpy(data.kernel_buf, &restart_psw, sizeof(restart_psw));
+		image->start = 0;
+	}
+
+	ret = kexec_file_add_ipl_report(image, &data);
+out:
+	ipl_report_free(data.report);
+	return ERR_PTR(ret);
 }
 
 int arch_kexec_apply_relocations_add(struct purgatory_info *pi,
@@ -140,7 +290,7 @@ int arch_kexec_apply_relocations_add(struct purgatory_info *pi,
 				     const Elf_Shdr *symtab)
 {
 	Elf_Rela *relas;
-	int i;
+	int i, r_type;
 
 	relas = (void *)pi->ehdr + relsec->sh_offset;
 
@@ -174,46 +324,8 @@ int arch_kexec_apply_relocations_add(struct purgatory_info *pi,
 
 		addr = section->sh_addr + relas[i].r_offset;
 
-		switch (ELF64_R_TYPE(relas[i].r_info)) {
-		case R_390_8:		/* Direct 8 bit.   */
-			*(u8 *)loc = val;
-			break;
-		case R_390_12:		/* Direct 12 bit.  */
-			*(u16 *)loc &= 0xf000;
-			*(u16 *)loc |= val & 0xfff;
-			break;
-		case R_390_16:		/* Direct 16 bit.  */
-			*(u16 *)loc = val;
-			break;
-		case R_390_20:		/* Direct 20 bit.  */
-			*(u32 *)loc &= 0xf00000ff;
-			*(u32 *)loc |= (val & 0xfff) << 16;	/* DL */
-			*(u32 *)loc |= (val & 0xff000) >> 4;	/* DH */
-			break;
-		case R_390_32:		/* Direct 32 bit.  */
-			*(u32 *)loc = val;
-			break;
-		case R_390_64:		/* Direct 64 bit.  */
-			*(u64 *)loc = val;
-			break;
-		case R_390_PC16:	/* PC relative 16 bit.	*/
-			*(u16 *)loc = (val - addr);
-			break;
-		case R_390_PC16DBL:	/* PC relative 16 bit shifted by 1.  */
-			*(u16 *)loc = (val - addr) >> 1;
-			break;
-		case R_390_PC32DBL:	/* PC relative 32 bit shifted by 1.  */
-			*(u32 *)loc = (val - addr) >> 1;
-			break;
-		case R_390_PC32:	/* PC relative 32 bit.	*/
-			*(u32 *)loc = (val - addr);
-			break;
-		case R_390_PC64:	/* PC relative 64 bit.	*/
-			*(u64 *)loc = (val - addr);
-			break;
-		default:
-			break;
-		}
+		r_type = ELF64_R_TYPE(relas[i].r_info);
+		arch_kexec_do_relocs(r_type, loc, val, addr);
 	}
 	return 0;
 }
@@ -225,10 +337,8 @@ int arch_kexec_kernel_image_probe(struct kimage *image, void *buf,
 	 * load memory in head.S will be accessed, e.g. to register the next
 	 * command line. If the next kernel were smaller the current kernel
 	 * will panic at load.
-	 *
-	 * 0x11000 = sizeof(head.S)
 	 */
-	if (buf_len < 0x11000)
+	if (buf_len < HEAD_END)
 		return -ENOEXEC;
 
 	return kexec_image_probe_default(image, buf, buf_len);
diff --git a/arch/s390/kernel/machine_kexec_reloc.c b/arch/s390/kernel/machine_kexec_reloc.c
new file mode 100644
index 000000000000..1dded39239f8
--- /dev/null
+++ b/arch/s390/kernel/machine_kexec_reloc.c
@@ -0,0 +1,53 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <linux/elf.h>
+
+int arch_kexec_do_relocs(int r_type, void *loc, unsigned long val,
+			 unsigned long addr)
+{
+	switch (r_type) {
+	case R_390_NONE:
+		break;
+	case R_390_8:		/* Direct 8 bit.   */
+		*(u8 *)loc = val;
+		break;
+	case R_390_12:		/* Direct 12 bit.  */
+		*(u16 *)loc &= 0xf000;
+		*(u16 *)loc |= val & 0xfff;
+		break;
+	case R_390_16:		/* Direct 16 bit.  */
+		*(u16 *)loc = val;
+		break;
+	case R_390_20:		/* Direct 20 bit.  */
+		*(u32 *)loc &= 0xf00000ff;
+		*(u32 *)loc |= (val & 0xfff) << 16;	/* DL */
+		*(u32 *)loc |= (val & 0xff000) >> 4;	/* DH */
+		break;
+	case R_390_32:		/* Direct 32 bit.  */
+		*(u32 *)loc = val;
+		break;
+	case R_390_64:		/* Direct 64 bit.  */
+		*(u64 *)loc = val;
+		break;
+	case R_390_PC16:	/* PC relative 16 bit.	*/
+		*(u16 *)loc = (val - addr);
+		break;
+	case R_390_PC16DBL:	/* PC relative 16 bit shifted by 1.  */
+		*(u16 *)loc = (val - addr) >> 1;
+		break;
+	case R_390_PC32DBL:	/* PC relative 32 bit shifted by 1.  */
+		*(u32 *)loc = (val - addr) >> 1;
+		break;
+	case R_390_PC32:	/* PC relative 32 bit.	*/
+		*(u32 *)loc = (val - addr);
+		break;
+	case R_390_PC64:	/* PC relative 64 bit.	*/
+		*(u64 *)loc = (val - addr);
+		break;
+	case R_390_RELATIVE:
+		*(unsigned long *) loc = val;
+		break;
+	default:
+		return 1;
+	}
+	return 0;
+}
diff --git a/arch/s390/kernel/mcount.S b/arch/s390/kernel/mcount.S
index e93fbf02490c..9e1660a6b9db 100644
--- a/arch/s390/kernel/mcount.S
+++ b/arch/s390/kernel/mcount.S
@@ -20,6 +20,7 @@
 
 ENTRY(ftrace_stub)
 	BR_EX	%r14
+ENDPROC(ftrace_stub)
 
 #define STACK_FRAME_SIZE  (STACK_FRAME_OVERHEAD + __PT_SIZE)
 #define STACK_PTREGS	  (STACK_FRAME_OVERHEAD)
@@ -28,7 +29,7 @@ ENTRY(ftrace_stub)
 
 ENTRY(_mcount)
 	BR_EX	%r14
-
+ENDPROC(_mcount)
 EXPORT_SYMBOL(_mcount)
 
 ENTRY(ftrace_caller)
@@ -61,10 +62,11 @@ ENTRY(ftrace_caller)
 #ifdef CONFIG_FUNCTION_GRAPH_TRACER
 # The j instruction gets runtime patched to a nop instruction.
 # See ftrace_enable_ftrace_graph_caller.
-ENTRY(ftrace_graph_caller)
+	.globl ftrace_graph_caller
+ftrace_graph_caller:
 	j	ftrace_graph_caller_end
-	lg	%r2,(STACK_PTREGS_GPRS+14*8)(%r15)
-	lg	%r3,(STACK_PTREGS_PSW+8)(%r15)
+	lmg	%r2,%r3,(STACK_PTREGS_GPRS+14*8)(%r15)
+	lg	%r4,(STACK_PTREGS_PSW+8)(%r15)
 	brasl	%r14,prepare_ftrace_return
 	stg	%r2,(STACK_PTREGS_GPRS+14*8)(%r15)
 ftrace_graph_caller_end:
@@ -73,6 +75,7 @@ ftrace_graph_caller_end:
 	lg	%r1,(STACK_PTREGS_PSW+8)(%r15)
 	lmg	%r2,%r15,(STACK_PTREGS_GPRS+2*8)(%r15)
 	BR_EX	%r1
+ENDPROC(ftrace_caller)
 
 #ifdef CONFIG_FUNCTION_GRAPH_TRACER
 
@@ -86,5 +89,6 @@ ENTRY(return_to_handler)
 	lgr	%r14,%r2
 	lmg	%r2,%r5,32(%r15)
 	BR_EX	%r14
+ENDPROC(return_to_handler)
 
 #endif
diff --git a/arch/s390/kernel/nmi.c b/arch/s390/kernel/nmi.c
index 8c867b43c8eb..0a487fae763e 100644
--- a/arch/s390/kernel/nmi.c
+++ b/arch/s390/kernel/nmi.c
@@ -125,7 +125,7 @@ void nmi_free_per_cpu(struct lowcore *lc)
 static notrace void s390_handle_damage(void)
 {
 	smp_emergency_stop();
-	disabled_wait((unsigned long) __builtin_return_address(0));
+	disabled_wait();
 	while (1);
 }
 NOKPROBE_SYMBOL(s390_handle_damage);
diff --git a/arch/s390/kernel/nospec-branch.c b/arch/s390/kernel/nospec-branch.c
index bdddaae96559..29e511f5bf06 100644
--- a/arch/s390/kernel/nospec-branch.c
+++ b/arch/s390/kernel/nospec-branch.c
@@ -1,6 +1,7 @@
 // SPDX-License-Identifier: GPL-2.0
 #include <linux/module.h>
 #include <linux/device.h>
+#include <linux/cpu.h>
 #include <asm/nospec-branch.h>
 
 static int __init nobp_setup_early(char *str)
@@ -37,7 +38,7 @@ static int __init nospec_report(void)
 {
 	if (test_facility(156))
 		pr_info("Spectre V2 mitigation: etokens\n");
-	if (IS_ENABLED(CC_USING_EXPOLINE) && !nospec_disable)
+	if (__is_defined(CC_USING_EXPOLINE) && !nospec_disable)
 		pr_info("Spectre V2 mitigation: execute trampolines\n");
 	if (__test_facility(82, S390_lowcore.alt_stfle_fac_list))
 		pr_info("Spectre V2 mitigation: limited branch prediction\n");
@@ -58,15 +59,15 @@ early_param("nospectre_v2", nospectre_v2_setup_early);
 
 void __init nospec_auto_detect(void)
 {
-	if (test_facility(156)) {
+	if (test_facility(156) || cpu_mitigations_off()) {
 		/*
 		 * The machine supports etokens.
 		 * Disable expolines and disable nobp.
 		 */
-		if (IS_ENABLED(CC_USING_EXPOLINE))
+		if (__is_defined(CC_USING_EXPOLINE))
 			nospec_disable = 1;
 		__clear_facility(82, S390_lowcore.alt_stfle_fac_list);
-	} else if (IS_ENABLED(CC_USING_EXPOLINE)) {
+	} else if (__is_defined(CC_USING_EXPOLINE)) {
 		/*
 		 * The kernel has been compiled with expolines.
 		 * Keep expolines enabled and disable nobp.
diff --git a/arch/s390/kernel/nospec-sysfs.c b/arch/s390/kernel/nospec-sysfs.c
index e30e580ae362..48f472bf9290 100644
--- a/arch/s390/kernel/nospec-sysfs.c
+++ b/arch/s390/kernel/nospec-sysfs.c
@@ -15,7 +15,7 @@ ssize_t cpu_show_spectre_v2(struct device *dev,
 {
 	if (test_facility(156))
 		return sprintf(buf, "Mitigation: etokens\n");
-	if (IS_ENABLED(CC_USING_EXPOLINE) && !nospec_disable)
+	if (__is_defined(CC_USING_EXPOLINE) && !nospec_disable)
 		return sprintf(buf, "Mitigation: execute trampolines\n");
 	if (__test_facility(82, S390_lowcore.alt_stfle_fac_list))
 		return sprintf(buf, "Mitigation: limited branch prediction\n");
diff --git a/arch/s390/kernel/perf_cpum_cf.c b/arch/s390/kernel/perf_cpum_cf.c
index e1c54d28713a..48d48b6187c0 100644
--- a/arch/s390/kernel/perf_cpum_cf.c
+++ b/arch/s390/kernel/perf_cpum_cf.c
@@ -2,8 +2,8 @@
 /*
  * Performance event support for s390x - CPU-measurement Counter Facility
  *
- *  Copyright IBM Corp. 2012, 2017
- *  Author(s): Hendrik Brueckner <brueckner@linux.vnet.ibm.com>
+ *  Copyright IBM Corp. 2012, 2019
+ *  Author(s): Hendrik Brueckner <brueckner@linux.ibm.com>
  */
 #define KMSG_COMPONENT	"cpum_cf"
 #define pr_fmt(fmt)	KMSG_COMPONENT ": " fmt
@@ -26,7 +26,7 @@ static enum cpumf_ctr_set get_counter_set(u64 event)
 		set = CPUMF_CTR_SET_USER;
 	else if (event < 128)
 		set = CPUMF_CTR_SET_CRYPTO;
-	else if (event < 256)
+	else if (event < 288)
 		set = CPUMF_CTR_SET_EXT;
 	else if (event >= 448 && event < 496)
 		set = CPUMF_CTR_SET_MT_DIAG;
@@ -50,12 +50,19 @@ static int validate_ctr_version(const struct hw_perf_event *hwc)
 			err = -EOPNOTSUPP;
 		break;
 	case CPUMF_CTR_SET_CRYPTO:
+		if ((cpuhw->info.csvn >= 1 && cpuhw->info.csvn <= 5 &&
+		     hwc->config > 79) ||
+		    (cpuhw->info.csvn >= 6 && hwc->config > 83))
+			err = -EOPNOTSUPP;
+		break;
 	case CPUMF_CTR_SET_EXT:
 		if (cpuhw->info.csvn < 1)
 			err = -EOPNOTSUPP;
 		if ((cpuhw->info.csvn == 1 && hwc->config > 159) ||
 		    (cpuhw->info.csvn == 2 && hwc->config > 175) ||
-		    (cpuhw->info.csvn  > 2 && hwc->config > 255))
+		    (cpuhw->info.csvn >= 3 && cpuhw->info.csvn <= 5
+		     && hwc->config > 255) ||
+		    (cpuhw->info.csvn >= 6 && hwc->config > 287))
 			err = -EOPNOTSUPP;
 		break;
 	case CPUMF_CTR_SET_MT_DIAG:
diff --git a/arch/s390/kernel/perf_cpum_cf_diag.c b/arch/s390/kernel/perf_cpum_cf_diag.c
index c6fad208c2fa..d4e031f7b9c8 100644
--- a/arch/s390/kernel/perf_cpum_cf_diag.c
+++ b/arch/s390/kernel/perf_cpum_cf_diag.c
@@ -196,23 +196,30 @@ static void cf_diag_perf_event_destroy(struct perf_event *event)
  */
 static int __hw_perf_event_init(struct perf_event *event)
 {
-	struct cpu_cf_events *cpuhw = this_cpu_ptr(&cpu_cf_events);
 	struct perf_event_attr *attr = &event->attr;
+	struct cpu_cf_events *cpuhw;
 	enum cpumf_ctr_set i;
 	int err = 0;
 
-	debug_sprintf_event(cf_diag_dbg, 5,
-			    "%s event %p cpu %d authorized %#x\n", __func__,
-			    event, event->cpu, cpuhw->info.auth_ctl);
+	debug_sprintf_event(cf_diag_dbg, 5, "%s event %p cpu %d\n", __func__,
+			    event, event->cpu);
 
 	event->hw.config = attr->config;
 	event->hw.config_base = 0;
-	local64_set(&event->count, 0);
 
-	/* Add all authorized counter sets to config_base */
+	/* Add all authorized counter sets to config_base. The
+	 * the hardware init function is either called per-cpu or just once
+	 * for all CPUS (event->cpu == -1).  This depends on the whether
+	 * counting is started for all CPUs or on a per workload base where
+	 * the perf event moves from one CPU to another CPU.
+	 * Checking the authorization on any CPU is fine as the hardware
+	 * applies the same authorization settings to all CPUs.
+	 */
+	cpuhw = &get_cpu_var(cpu_cf_events);
 	for (i = CPUMF_CTR_SET_BASIC; i < CPUMF_CTR_SET_MAX; ++i)
 		if (cpuhw->info.auth_ctl & cpumf_ctr_ctl[i])
 			event->hw.config_base |= cpumf_ctr_ctl[i];
+	put_cpu_var(cpu_cf_events);
 
 	/* No authorized counter sets, nothing to count/sample */
 	if (!event->hw.config_base) {
@@ -299,15 +306,20 @@ static size_t cf_diag_ctrset_size(enum cpumf_ctr_set ctrset,
 			ctrset_size = 2;
 		break;
 	case CPUMF_CTR_SET_CRYPTO:
-		ctrset_size = 16;
+		if (info->csvn >= 1 && info->csvn <= 5)
+			ctrset_size = 16;
+		else if (info->csvn == 6)
+			ctrset_size = 20;
 		break;
 	case CPUMF_CTR_SET_EXT:
 		if (info->csvn == 1)
 			ctrset_size = 32;
 		else if (info->csvn == 2)
 			ctrset_size = 48;
-		else if (info->csvn >= 3)
+		else if (info->csvn >= 3 && info->csvn <= 5)
 			ctrset_size = 128;
+		else if (info->csvn == 6)
+			ctrset_size = 160;
 		break;
 	case CPUMF_CTR_SET_MT_DIAG:
 		if (info->csvn > 3)
diff --git a/arch/s390/kernel/perf_cpum_cf_events.c b/arch/s390/kernel/perf_cpum_cf_events.c
index b45238c89728..34cc96449b30 100644
--- a/arch/s390/kernel/perf_cpum_cf_events.c
+++ b/arch/s390/kernel/perf_cpum_cf_events.c
@@ -31,22 +31,26 @@ CPUMF_EVENT_ATTR(cf_fvn3, PROBLEM_STATE_CPU_CYCLES, 0x0020);
 CPUMF_EVENT_ATTR(cf_fvn3, PROBLEM_STATE_INSTRUCTIONS, 0x0021);
 CPUMF_EVENT_ATTR(cf_fvn3, L1D_DIR_WRITES, 0x0004);
 CPUMF_EVENT_ATTR(cf_fvn3, L1D_PENALTY_CYCLES, 0x0005);
-CPUMF_EVENT_ATTR(cf_svn_generic, PRNG_FUNCTIONS, 0x0040);
-CPUMF_EVENT_ATTR(cf_svn_generic, PRNG_CYCLES, 0x0041);
-CPUMF_EVENT_ATTR(cf_svn_generic, PRNG_BLOCKED_FUNCTIONS, 0x0042);
-CPUMF_EVENT_ATTR(cf_svn_generic, PRNG_BLOCKED_CYCLES, 0x0043);
-CPUMF_EVENT_ATTR(cf_svn_generic, SHA_FUNCTIONS, 0x0044);
-CPUMF_EVENT_ATTR(cf_svn_generic, SHA_CYCLES, 0x0045);
-CPUMF_EVENT_ATTR(cf_svn_generic, SHA_BLOCKED_FUNCTIONS, 0x0046);
-CPUMF_EVENT_ATTR(cf_svn_generic, SHA_BLOCKED_CYCLES, 0x0047);
-CPUMF_EVENT_ATTR(cf_svn_generic, DEA_FUNCTIONS, 0x0048);
-CPUMF_EVENT_ATTR(cf_svn_generic, DEA_CYCLES, 0x0049);
-CPUMF_EVENT_ATTR(cf_svn_generic, DEA_BLOCKED_FUNCTIONS, 0x004a);
-CPUMF_EVENT_ATTR(cf_svn_generic, DEA_BLOCKED_CYCLES, 0x004b);
-CPUMF_EVENT_ATTR(cf_svn_generic, AES_FUNCTIONS, 0x004c);
-CPUMF_EVENT_ATTR(cf_svn_generic, AES_CYCLES, 0x004d);
-CPUMF_EVENT_ATTR(cf_svn_generic, AES_BLOCKED_FUNCTIONS, 0x004e);
-CPUMF_EVENT_ATTR(cf_svn_generic, AES_BLOCKED_CYCLES, 0x004f);
+CPUMF_EVENT_ATTR(cf_svn_12345, PRNG_FUNCTIONS, 0x0040);
+CPUMF_EVENT_ATTR(cf_svn_12345, PRNG_CYCLES, 0x0041);
+CPUMF_EVENT_ATTR(cf_svn_12345, PRNG_BLOCKED_FUNCTIONS, 0x0042);
+CPUMF_EVENT_ATTR(cf_svn_12345, PRNG_BLOCKED_CYCLES, 0x0043);
+CPUMF_EVENT_ATTR(cf_svn_12345, SHA_FUNCTIONS, 0x0044);
+CPUMF_EVENT_ATTR(cf_svn_12345, SHA_CYCLES, 0x0045);
+CPUMF_EVENT_ATTR(cf_svn_12345, SHA_BLOCKED_FUNCTIONS, 0x0046);
+CPUMF_EVENT_ATTR(cf_svn_12345, SHA_BLOCKED_CYCLES, 0x0047);
+CPUMF_EVENT_ATTR(cf_svn_12345, DEA_FUNCTIONS, 0x0048);
+CPUMF_EVENT_ATTR(cf_svn_12345, DEA_CYCLES, 0x0049);
+CPUMF_EVENT_ATTR(cf_svn_12345, DEA_BLOCKED_FUNCTIONS, 0x004a);
+CPUMF_EVENT_ATTR(cf_svn_12345, DEA_BLOCKED_CYCLES, 0x004b);
+CPUMF_EVENT_ATTR(cf_svn_12345, AES_FUNCTIONS, 0x004c);
+CPUMF_EVENT_ATTR(cf_svn_12345, AES_CYCLES, 0x004d);
+CPUMF_EVENT_ATTR(cf_svn_12345, AES_BLOCKED_FUNCTIONS, 0x004e);
+CPUMF_EVENT_ATTR(cf_svn_12345, AES_BLOCKED_CYCLES, 0x004f);
+CPUMF_EVENT_ATTR(cf_svn_6, ECC_FUNCTION_COUNT, 0x0050);
+CPUMF_EVENT_ATTR(cf_svn_6, ECC_CYCLES_COUNT, 0x0051);
+CPUMF_EVENT_ATTR(cf_svn_6, ECC_BLOCKED_FUNCTION_COUNT, 0x0052);
+CPUMF_EVENT_ATTR(cf_svn_6, ECC_BLOCKED_CYCLES_COUNT, 0x0053);
 CPUMF_EVENT_ATTR(cf_z10, L1I_L2_SOURCED_WRITES, 0x0080);
 CPUMF_EVENT_ATTR(cf_z10, L1D_L2_SOURCED_WRITES, 0x0081);
 CPUMF_EVENT_ATTR(cf_z10, L1I_L3_LOCAL_WRITES, 0x0082);
@@ -262,23 +266,47 @@ static struct attribute *cpumcf_fvn3_pmu_event_attr[] __initdata = {
 	NULL,
 };
 
-static struct attribute *cpumcf_svn_generic_pmu_event_attr[] __initdata = {
-	CPUMF_EVENT_PTR(cf_svn_generic, PRNG_FUNCTIONS),
-	CPUMF_EVENT_PTR(cf_svn_generic, PRNG_CYCLES),
-	CPUMF_EVENT_PTR(cf_svn_generic, PRNG_BLOCKED_FUNCTIONS),
-	CPUMF_EVENT_PTR(cf_svn_generic, PRNG_BLOCKED_CYCLES),
-	CPUMF_EVENT_PTR(cf_svn_generic, SHA_FUNCTIONS),
-	CPUMF_EVENT_PTR(cf_svn_generic, SHA_CYCLES),
-	CPUMF_EVENT_PTR(cf_svn_generic, SHA_BLOCKED_FUNCTIONS),
-	CPUMF_EVENT_PTR(cf_svn_generic, SHA_BLOCKED_CYCLES),
-	CPUMF_EVENT_PTR(cf_svn_generic, DEA_FUNCTIONS),
-	CPUMF_EVENT_PTR(cf_svn_generic, DEA_CYCLES),
-	CPUMF_EVENT_PTR(cf_svn_generic, DEA_BLOCKED_FUNCTIONS),
-	CPUMF_EVENT_PTR(cf_svn_generic, DEA_BLOCKED_CYCLES),
-	CPUMF_EVENT_PTR(cf_svn_generic, AES_FUNCTIONS),
-	CPUMF_EVENT_PTR(cf_svn_generic, AES_CYCLES),
-	CPUMF_EVENT_PTR(cf_svn_generic, AES_BLOCKED_FUNCTIONS),
-	CPUMF_EVENT_PTR(cf_svn_generic, AES_BLOCKED_CYCLES),
+static struct attribute *cpumcf_svn_12345_pmu_event_attr[] __initdata = {
+	CPUMF_EVENT_PTR(cf_svn_12345, PRNG_FUNCTIONS),
+	CPUMF_EVENT_PTR(cf_svn_12345, PRNG_CYCLES),
+	CPUMF_EVENT_PTR(cf_svn_12345, PRNG_BLOCKED_FUNCTIONS),
+	CPUMF_EVENT_PTR(cf_svn_12345, PRNG_BLOCKED_CYCLES),
+	CPUMF_EVENT_PTR(cf_svn_12345, SHA_FUNCTIONS),
+	CPUMF_EVENT_PTR(cf_svn_12345, SHA_CYCLES),
+	CPUMF_EVENT_PTR(cf_svn_12345, SHA_BLOCKED_FUNCTIONS),
+	CPUMF_EVENT_PTR(cf_svn_12345, SHA_BLOCKED_CYCLES),
+	CPUMF_EVENT_PTR(cf_svn_12345, DEA_FUNCTIONS),
+	CPUMF_EVENT_PTR(cf_svn_12345, DEA_CYCLES),
+	CPUMF_EVENT_PTR(cf_svn_12345, DEA_BLOCKED_FUNCTIONS),
+	CPUMF_EVENT_PTR(cf_svn_12345, DEA_BLOCKED_CYCLES),
+	CPUMF_EVENT_PTR(cf_svn_12345, AES_FUNCTIONS),
+	CPUMF_EVENT_PTR(cf_svn_12345, AES_CYCLES),
+	CPUMF_EVENT_PTR(cf_svn_12345, AES_BLOCKED_FUNCTIONS),
+	CPUMF_EVENT_PTR(cf_svn_12345, AES_BLOCKED_CYCLES),
+	NULL,
+};
+
+static struct attribute *cpumcf_svn_6_pmu_event_attr[] __initdata = {
+	CPUMF_EVENT_PTR(cf_svn_12345, PRNG_FUNCTIONS),
+	CPUMF_EVENT_PTR(cf_svn_12345, PRNG_CYCLES),
+	CPUMF_EVENT_PTR(cf_svn_12345, PRNG_BLOCKED_FUNCTIONS),
+	CPUMF_EVENT_PTR(cf_svn_12345, PRNG_BLOCKED_CYCLES),
+	CPUMF_EVENT_PTR(cf_svn_12345, SHA_FUNCTIONS),
+	CPUMF_EVENT_PTR(cf_svn_12345, SHA_CYCLES),
+	CPUMF_EVENT_PTR(cf_svn_12345, SHA_BLOCKED_FUNCTIONS),
+	CPUMF_EVENT_PTR(cf_svn_12345, SHA_BLOCKED_CYCLES),
+	CPUMF_EVENT_PTR(cf_svn_12345, DEA_FUNCTIONS),
+	CPUMF_EVENT_PTR(cf_svn_12345, DEA_CYCLES),
+	CPUMF_EVENT_PTR(cf_svn_12345, DEA_BLOCKED_FUNCTIONS),
+	CPUMF_EVENT_PTR(cf_svn_12345, DEA_BLOCKED_CYCLES),
+	CPUMF_EVENT_PTR(cf_svn_12345, AES_FUNCTIONS),
+	CPUMF_EVENT_PTR(cf_svn_12345, AES_CYCLES),
+	CPUMF_EVENT_PTR(cf_svn_12345, AES_BLOCKED_FUNCTIONS),
+	CPUMF_EVENT_PTR(cf_svn_12345, AES_BLOCKED_CYCLES),
+	CPUMF_EVENT_PTR(cf_svn_6, ECC_FUNCTION_COUNT),
+	CPUMF_EVENT_PTR(cf_svn_6, ECC_CYCLES_COUNT),
+	CPUMF_EVENT_PTR(cf_svn_6, ECC_BLOCKED_FUNCTION_COUNT),
+	CPUMF_EVENT_PTR(cf_svn_6, ECC_BLOCKED_CYCLES_COUNT),
 	NULL,
 };
 
@@ -562,7 +590,18 @@ __init const struct attribute_group **cpumf_cf_event_group(void)
 	default:
 		cfvn = none;
 	}
-	csvn = cpumcf_svn_generic_pmu_event_attr;
+
+	/* Determine version specific crypto set */
+	switch (ci.csvn) {
+	case 1 ... 5:
+		csvn = cpumcf_svn_12345_pmu_event_attr;
+		break;
+	case 6:
+		csvn = cpumcf_svn_6_pmu_event_attr;
+		break;
+	default:
+		csvn = none;
+	}
 
 	/* Determine model-specific counter set(s) */
 	get_cpu_id(&cpu_id);
diff --git a/arch/s390/kernel/perf_event.c b/arch/s390/kernel/perf_event.c
index 0d770e513abf..fcb6c2e92b07 100644
--- a/arch/s390/kernel/perf_event.c
+++ b/arch/s390/kernel/perf_event.c
@@ -21,6 +21,7 @@
 #include <asm/lowcore.h>
 #include <asm/processor.h>
 #include <asm/sysinfo.h>
+#include <asm/unwind.h>
 
 const char *perf_pmu_name(void)
 {
@@ -219,20 +220,13 @@ static int __init service_level_perf_register(void)
 }
 arch_initcall(service_level_perf_register);
 
-static int __perf_callchain_kernel(void *data, unsigned long address, int reliable)
-{
-	struct perf_callchain_entry_ctx *entry = data;
-
-	perf_callchain_store(entry, address);
-	return 0;
-}
-
 void perf_callchain_kernel(struct perf_callchain_entry_ctx *entry,
 			   struct pt_regs *regs)
 {
-	if (user_mode(regs))
-		return;
-	dump_trace(__perf_callchain_kernel, entry, NULL, regs->gprs[15]);
+	struct unwind_state state;
+
+	unwind_for_each_frame(&state, current, regs, 0)
+		perf_callchain_store(entry, state.ip);
 }
 
 /* Perf definitions for PMU event attributes in sysfs */
diff --git a/arch/s390/kernel/pgm_check.S b/arch/s390/kernel/pgm_check.S
index 3e62aae34ea3..59dee9d3bebf 100644
--- a/arch/s390/kernel/pgm_check.S
+++ b/arch/s390/kernel/pgm_check.S
@@ -7,7 +7,7 @@
 
 #include <linux/linkage.h>
 
-#define PGM_CHECK(handler)	.long handler
+#define PGM_CHECK(handler)	.quad handler
 #define PGM_CHECK_DEFAULT	PGM_CHECK(default_trap_handler)
 
 /*
diff --git a/arch/s390/kernel/process.c b/arch/s390/kernel/process.c
index 6e758bb6cd29..63873aa6693f 100644
--- a/arch/s390/kernel/process.c
+++ b/arch/s390/kernel/process.c
@@ -37,6 +37,7 @@
 #include <asm/irq.h>
 #include <asm/nmi.h>
 #include <asm/smp.h>
+#include <asm/stacktrace.h>
 #include <asm/switch_to.h>
 #include <asm/runtime_instr.h>
 #include "entry.h"
diff --git a/arch/s390/kernel/processor.c b/arch/s390/kernel/processor.c
index 6fe2e1875058..5de13307b703 100644
--- a/arch/s390/kernel/processor.c
+++ b/arch/s390/kernel/processor.c
@@ -109,7 +109,8 @@ static void show_cpu_summary(struct seq_file *m, void *v)
 {
 	static const char *hwcap_str[] = {
 		"esan3", "zarch", "stfle", "msa", "ldisp", "eimm", "dfp",
-		"edat", "etf3eh", "highgprs", "te", "vx", "vxd", "vxe", "gs"
+		"edat", "etf3eh", "highgprs", "te", "vx", "vxd", "vxe", "gs",
+		"vxe2", "vxp", "sort", "dflt"
 	};
 	static const char * const int_hwcap_str[] = {
 		"sie"
diff --git a/arch/s390/kernel/reipl.S b/arch/s390/kernel/reipl.S
index 7f14adf512c6..4a22163962eb 100644
--- a/arch/s390/kernel/reipl.S
+++ b/arch/s390/kernel/reipl.S
@@ -73,6 +73,7 @@ ENTRY(store_status)
 	lgr	%r9,%r2
 	lgr	%r2,%r3
 	BR_EX	%r9
+ENDPROC(store_status)
 
 	.section .bss
 	.align	8
diff --git a/arch/s390/kernel/relocate_kernel.S b/arch/s390/kernel/relocate_kernel.S
index c97c2d40fe15..fe396673e8a6 100644
--- a/arch/s390/kernel/relocate_kernel.S
+++ b/arch/s390/kernel/relocate_kernel.S
@@ -58,11 +58,15 @@ ENTRY(relocate_kernel)
 		j	.base
 	.done:
 		sgr	%r0,%r0		# clear register r0
+		cghi	%r3,0
+		je	.diag
 		la	%r4,load_psw-.base(%r13)	# load psw-address into the register
 		o	%r3,4(%r4)	# or load address into psw
 		st	%r3,4(%r4)
 		mvc	0(8,%r0),0(%r4)	# copy psw to absolute address 0
+	.diag:
 		diag	%r0,%r0,0x308
+ENDPROC(relocate_kernel)
 
 		.align	8
 	load_psw:
diff --git a/arch/s390/kernel/setup.c b/arch/s390/kernel/setup.c
index 2c642af526ce..f8544d517430 100644
--- a/arch/s390/kernel/setup.c
+++ b/arch/s390/kernel/setup.c
@@ -50,6 +50,7 @@
 #include <linux/compat.h>
 #include <linux/start_kernel.h>
 
+#include <asm/boot_data.h>
 #include <asm/ipl.h>
 #include <asm/facility.h>
 #include <asm/smp.h>
@@ -65,11 +66,13 @@
 #include <asm/diag.h>
 #include <asm/os_info.h>
 #include <asm/sclp.h>
+#include <asm/stacktrace.h>
 #include <asm/sysinfo.h>
 #include <asm/numa.h>
 #include <asm/alternative.h>
 #include <asm/nospec-branch.h>
 #include <asm/mem_detect.h>
+#include <asm/uv.h>
 #include "entry.h"
 
 /*
@@ -89,12 +92,25 @@ char elf_platform[ELF_PLATFORM_SIZE];
 
 unsigned long int_hwcap = 0;
 
+#ifdef CONFIG_PROTECTED_VIRTUALIZATION_GUEST
+int __bootdata_preserved(prot_virt_guest);
+#endif
+
 int __bootdata(noexec_disabled);
 int __bootdata(memory_end_set);
 unsigned long __bootdata(memory_end);
 unsigned long __bootdata(max_physmem_end);
 struct mem_detect_info __bootdata(mem_detect);
 
+struct exception_table_entry *__bootdata_preserved(__start_dma_ex_table);
+struct exception_table_entry *__bootdata_preserved(__stop_dma_ex_table);
+unsigned long __bootdata_preserved(__swsusp_reset_dma);
+unsigned long __bootdata_preserved(__stext_dma);
+unsigned long __bootdata_preserved(__etext_dma);
+unsigned long __bootdata_preserved(__sdma);
+unsigned long __bootdata_preserved(__edma);
+unsigned long __bootdata_preserved(__kaslr_offset);
+
 unsigned long VMALLOC_START;
 EXPORT_SYMBOL(VMALLOC_START);
 
@@ -736,6 +752,15 @@ static void __init reserve_initrd(void)
 #endif
 }
 
+/*
+ * Reserve the memory area used to pass the certificate lists
+ */
+static void __init reserve_certificate_list(void)
+{
+	if (ipl_cert_list_addr)
+		memblock_reserve(ipl_cert_list_addr, ipl_cert_list_size);
+}
+
 static void __init reserve_mem_detect_info(void)
 {
 	unsigned long start, size;
@@ -814,9 +839,10 @@ static void __init reserve_kernel(void)
 {
 	unsigned long start_pfn = PFN_UP(__pa(_end));
 
-	memblock_reserve(0, PARMAREA_END);
+	memblock_reserve(0, HEAD_END);
 	memblock_reserve((unsigned long)_stext, PFN_PHYS(start_pfn)
 			 - (unsigned long)_stext);
+	memblock_reserve(__sdma, __edma - __sdma);
 }
 
 static void __init setup_memory(void)
@@ -914,7 +940,15 @@ static int __init setup_hwcaps(void)
 			elf_hwcap |= HWCAP_S390_VXRS_EXT;
 		if (test_facility(135))
 			elf_hwcap |= HWCAP_S390_VXRS_BCD;
+		if (test_facility(148))
+			elf_hwcap |= HWCAP_S390_VXRS_EXT2;
+		if (test_facility(152))
+			elf_hwcap |= HWCAP_S390_VXRS_PDE;
 	}
+	if (test_facility(150))
+		elf_hwcap |= HWCAP_S390_SORT;
+	if (test_facility(151))
+		elf_hwcap |= HWCAP_S390_DFLT;
 
 	/*
 	 * Guarded storage support HWCAP_S390_GS is bit 12.
@@ -1023,6 +1057,38 @@ static void __init setup_control_program_code(void)
 }
 
 /*
+ * Print the component list from the IPL report
+ */
+static void __init log_component_list(void)
+{
+	struct ipl_rb_component_entry *ptr, *end;
+	char *str;
+
+	if (!early_ipl_comp_list_addr)
+		return;
+	if (ipl_block.hdr.flags & IPL_PL_FLAG_IPLSR)
+		pr_info("Linux is running with Secure-IPL enabled\n");
+	else
+		pr_info("Linux is running with Secure-IPL disabled\n");
+	ptr = (void *) early_ipl_comp_list_addr;
+	end = (void *) ptr + early_ipl_comp_list_size;
+	pr_info("The IPL report contains the following components:\n");
+	while (ptr < end) {
+		if (ptr->flags & IPL_RB_COMPONENT_FLAG_SIGNED) {
+			if (ptr->flags & IPL_RB_COMPONENT_FLAG_VERIFIED)
+				str = "signed, verified";
+			else
+				str = "signed, verification failed";
+		} else {
+			str = "not signed";
+		}
+		pr_info("%016llx - %016llx (%s)\n",
+			ptr->addr, ptr->addr + ptr->len, str);
+		ptr++;
+	}
+}
+
+/*
  * Setup function called from init/main.c just after the banner
  * was printed.
  */
@@ -1042,6 +1108,8 @@ void __init setup_arch(char **cmdline_p)
 	else
 		pr_info("Linux is running as a guest in 64-bit mode\n");
 
+	log_component_list();
+
 	/* Have one command line that is parsed and saved in /proc/cmdline */
 	/* boot_command_line has been already set up in early.c */
 	*cmdline_p = boot_command_line;
@@ -1073,6 +1141,7 @@ void __init setup_arch(char **cmdline_p)
 	reserve_oldmem();
 	reserve_kernel();
 	reserve_initrd();
+	reserve_certificate_list();
 	reserve_mem_detect_info();
 	memblock_allow_resize();
 
diff --git a/arch/s390/kernel/smp.c b/arch/s390/kernel/smp.c
index 3fe1c77c361b..35fafa2b91a8 100644
--- a/arch/s390/kernel/smp.c
+++ b/arch/s390/kernel/smp.c
@@ -53,6 +53,7 @@
 #include <asm/sigp.h>
 #include <asm/idle.h>
 #include <asm/nmi.h>
+#include <asm/stacktrace.h>
 #include <asm/topology.h>
 #include "entry.h"
 
@@ -266,7 +267,8 @@ static void pcpu_prepare_secondary(struct pcpu *pcpu, int cpu)
 	lc->percpu_offset = __per_cpu_offset[cpu];
 	lc->kernel_asce = S390_lowcore.kernel_asce;
 	lc->machine_flags = S390_lowcore.machine_flags;
-	lc->user_timer = lc->system_timer = lc->steal_timer = 0;
+	lc->user_timer = lc->system_timer =
+		lc->steal_timer = lc->avg_steal_timer = 0;
 	__ctl_store(lc->cregs_save_area, 0, 15);
 	save_access_regs((unsigned int *) lc->access_regs_save_area);
 	memcpy(lc->stfle_fac_list, S390_lowcore.stfle_fac_list,
@@ -688,7 +690,7 @@ void __init smp_save_dump_cpus(void)
 			smp_save_cpu_regs(sa, addr, is_boot_cpu, page);
 	}
 	memblock_free(page, PAGE_SIZE);
-	diag308_reset();
+	diag_dma_ops.diag308_reset();
 	pcpu_set_smt(0);
 }
 #endif /* CONFIG_CRASH_DUMP */
diff --git a/arch/s390/kernel/stacktrace.c b/arch/s390/kernel/stacktrace.c
index 460dcfba7d4e..f6a620f854e1 100644
--- a/arch/s390/kernel/stacktrace.c
+++ b/arch/s390/kernel/stacktrace.c
@@ -11,65 +11,52 @@
 #include <linux/stacktrace.h>
 #include <linux/kallsyms.h>
 #include <linux/export.h>
-
-static int __save_address(void *data, unsigned long address, int nosched)
-{
-	struct stack_trace *trace = data;
-
-	if (nosched && in_sched_functions(address))
-		return 0;
-	if (trace->skip > 0) {
-		trace->skip--;
-		return 0;
-	}
-	if (trace->nr_entries < trace->max_entries) {
-		trace->entries[trace->nr_entries++] = address;
-		return 0;
-	}
-	return 1;
-}
-
-static int save_address(void *data, unsigned long address, int reliable)
-{
-	return __save_address(data, address, 0);
-}
-
-static int save_address_nosched(void *data, unsigned long address, int reliable)
-{
-	return __save_address(data, address, 1);
-}
+#include <asm/stacktrace.h>
+#include <asm/unwind.h>
 
 void save_stack_trace(struct stack_trace *trace)
 {
-	unsigned long sp;
-
-	sp = current_stack_pointer();
-	dump_trace(save_address, trace, NULL, sp);
-	if (trace->nr_entries < trace->max_entries)
-		trace->entries[trace->nr_entries++] = ULONG_MAX;
+	struct unwind_state state;
+
+	unwind_for_each_frame(&state, current, NULL, 0) {
+		if (trace->nr_entries >= trace->max_entries)
+			break;
+		if (trace->skip > 0)
+			trace->skip--;
+		else
+			trace->entries[trace->nr_entries++] = state.ip;
+	}
 }
 EXPORT_SYMBOL_GPL(save_stack_trace);
 
 void save_stack_trace_tsk(struct task_struct *tsk, struct stack_trace *trace)
 {
-	unsigned long sp;
-
-	sp = tsk->thread.ksp;
-	if (tsk == current)
-		sp = current_stack_pointer();
-	dump_trace(save_address_nosched, trace, tsk, sp);
-	if (trace->nr_entries < trace->max_entries)
-		trace->entries[trace->nr_entries++] = ULONG_MAX;
+	struct unwind_state state;
+
+	unwind_for_each_frame(&state, tsk, NULL, 0) {
+		if (trace->nr_entries >= trace->max_entries)
+			break;
+		if (in_sched_functions(state.ip))
+			continue;
+		if (trace->skip > 0)
+			trace->skip--;
+		else
+			trace->entries[trace->nr_entries++] = state.ip;
+	}
 }
 EXPORT_SYMBOL_GPL(save_stack_trace_tsk);
 
 void save_stack_trace_regs(struct pt_regs *regs, struct stack_trace *trace)
 {
-	unsigned long sp;
-
-	sp = kernel_stack_pointer(regs);
-	dump_trace(save_address, trace, NULL, sp);
-	if (trace->nr_entries < trace->max_entries)
-		trace->entries[trace->nr_entries++] = ULONG_MAX;
+	struct unwind_state state;
+
+	unwind_for_each_frame(&state, current, regs, 0) {
+		if (trace->nr_entries >= trace->max_entries)
+			break;
+		if (trace->skip > 0)
+			trace->skip--;
+		else
+			trace->entries[trace->nr_entries++] = state.ip;
+	}
 }
 EXPORT_SYMBOL_GPL(save_stack_trace_regs);
diff --git a/arch/s390/kernel/swsusp.S b/arch/s390/kernel/swsusp.S
index 993100c31d65..19a3c427801a 100644
--- a/arch/s390/kernel/swsusp.S
+++ b/arch/s390/kernel/swsusp.S
@@ -108,6 +108,7 @@ ENTRY(swsusp_arch_suspend)
 	lmg	%r6,%r15,STACK_FRAME_OVERHEAD + __SF_GPRS(%r15)
 	lghi	%r2,0
 	BR_EX	%r14
+ENDPROC(swsusp_arch_suspend)
 
 /*
  * Restore saved memory image to correct place and restore register context.
@@ -154,20 +155,13 @@ ENTRY(swsusp_arch_resume)
 	ptlb				/* flush tlb */
 
 	/* Reset System */
-	larl	%r1,restart_entry
-	larl	%r2,.Lrestart_diag308_psw
-	og	%r1,0(%r2)
-	stg	%r1,0(%r0)
 	larl	%r1,.Lnew_pgm_check_psw
 	epsw	%r2,%r3
 	stm	%r2,%r3,0(%r1)
 	mvc	__LC_PGM_NEW_PSW(16,%r0),0(%r1)
-	lghi	%r0,0
-	diag	%r0,%r0,0x308
-restart_entry:
-	lhi	%r1,1
-	sigp	%r1,%r0,SIGP_SET_ARCHITECTURE
-	sam64
+	larl	%r1,__swsusp_reset_dma
+	lg	%r1,0(%r1)
+	BASR_EX	%r14,%r1
 #ifdef CONFIG_SMP
 	larl	%r1,smp_cpu_mt_shift
 	icm	%r1,15,0(%r1)
@@ -267,6 +261,7 @@ restore_registers:
 	lmg	%r6,%r15,STACK_FRAME_OVERHEAD + __SF_GPRS(%r15)
 	lghi	%r2,0
 	BR_EX	%r14
+ENDPROC(swsusp_arch_resume)
 
 	.section .data..nosave,"aw",@progbits
 	.align	8
@@ -275,8 +270,6 @@ restore_registers:
 .Lpanic_string:
 	.asciz	"Resume not possible because suspend CPU is no longer available\n"
 	.align	8
-.Lrestart_diag308_psw:
-	.long	0x00080000,0x80000000
 .Lrestart_suspend_psw:
 	.quad	0x0000000180000000,restart_suspend
 .Lnew_pgm_check_psw:
diff --git a/arch/s390/kernel/syscalls/syscall.tbl b/arch/s390/kernel/syscalls/syscall.tbl
index 02579f95f391..061418f787c3 100644
--- a/arch/s390/kernel/syscalls/syscall.tbl
+++ b/arch/s390/kernel/syscalls/syscall.tbl
@@ -426,3 +426,7 @@
 421	32	rt_sigtimedwait_time64	-				compat_sys_rt_sigtimedwait_time64
 422	32	futex_time64		-				sys_futex
 423	32	sched_rr_get_interval_time64	-			sys_sched_rr_get_interval
+424  common	pidfd_send_signal	sys_pidfd_send_signal		sys_pidfd_send_signal
+425  common	io_uring_setup		sys_io_uring_setup              sys_io_uring_setup
+426  common	io_uring_enter		sys_io_uring_enter              sys_io_uring_enter
+427  common	io_uring_register	sys_io_uring_register           sys_io_uring_register
diff --git a/arch/s390/kernel/traps.c b/arch/s390/kernel/traps.c
index 8003b38c1688..82e81a9f7112 100644
--- a/arch/s390/kernel/traps.c
+++ b/arch/s390/kernel/traps.c
@@ -49,7 +49,7 @@ void do_report_trap(struct pt_regs *regs, int si_signo, int si_code, char *str)
 		report_user_fault(regs, si_signo, 0);
         } else {
                 const struct exception_table_entry *fixup;
-		fixup = search_exception_tables(regs->psw.addr);
+		fixup = s390_search_extables(regs->psw.addr);
                 if (fixup)
 			regs->psw.addr = extable_fixup(fixup);
 		else {
@@ -263,5 +263,6 @@ NOKPROBE_SYMBOL(kernel_stack_overflow);
 
 void __init trap_init(void)
 {
+	sort_extable(__start_dma_ex_table, __stop_dma_ex_table);
 	local_mcck_enable();
 }
diff --git a/arch/s390/kernel/unwind_bc.c b/arch/s390/kernel/unwind_bc.c
new file mode 100644
index 000000000000..57fd4e902f1f
--- /dev/null
+++ b/arch/s390/kernel/unwind_bc.c
@@ -0,0 +1,155 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#include <linux/sched.h>
+#include <linux/sched/task.h>
+#include <linux/sched/task_stack.h>
+#include <linux/interrupt.h>
+#include <asm/sections.h>
+#include <asm/ptrace.h>
+#include <asm/bitops.h>
+#include <asm/stacktrace.h>
+#include <asm/unwind.h>
+
+unsigned long unwind_get_return_address(struct unwind_state *state)
+{
+	if (unwind_done(state))
+		return 0;
+	return __kernel_text_address(state->ip) ? state->ip : 0;
+}
+EXPORT_SYMBOL_GPL(unwind_get_return_address);
+
+static bool outside_of_stack(struct unwind_state *state, unsigned long sp)
+{
+	return (sp <= state->sp) ||
+		(sp + sizeof(struct stack_frame) > state->stack_info.end);
+}
+
+static bool update_stack_info(struct unwind_state *state, unsigned long sp)
+{
+	struct stack_info *info = &state->stack_info;
+	unsigned long *mask = &state->stack_mask;
+
+	/* New stack pointer leaves the current stack */
+	if (get_stack_info(sp, state->task, info, mask) != 0 ||
+	    !on_stack(info, sp, sizeof(struct stack_frame)))
+		/* 'sp' does not point to a valid stack */
+		return false;
+	return true;
+}
+
+bool unwind_next_frame(struct unwind_state *state)
+{
+	struct stack_info *info = &state->stack_info;
+	struct stack_frame *sf;
+	struct pt_regs *regs;
+	unsigned long sp, ip;
+	bool reliable;
+
+	regs = state->regs;
+	if (unlikely(regs)) {
+		sp = READ_ONCE_TASK_STACK(state->task, regs->gprs[15]);
+		if (unlikely(outside_of_stack(state, sp))) {
+			if (!update_stack_info(state, sp))
+				goto out_err;
+		}
+		sf = (struct stack_frame *) sp;
+		ip = READ_ONCE_TASK_STACK(state->task, sf->gprs[8]);
+		reliable = false;
+		regs = NULL;
+	} else {
+		sf = (struct stack_frame *) state->sp;
+		sp = READ_ONCE_TASK_STACK(state->task, sf->back_chain);
+		if (likely(sp)) {
+			/* Non-zero back-chain points to the previous frame */
+			if (unlikely(outside_of_stack(state, sp))) {
+				if (!update_stack_info(state, sp))
+					goto out_err;
+			}
+			sf = (struct stack_frame *) sp;
+			ip = READ_ONCE_TASK_STACK(state->task, sf->gprs[8]);
+			reliable = true;
+		} else {
+			/* No back-chain, look for a pt_regs structure */
+			sp = state->sp + STACK_FRAME_OVERHEAD;
+			if (!on_stack(info, sp, sizeof(struct pt_regs)))
+				goto out_stop;
+			regs = (struct pt_regs *) sp;
+			if (user_mode(regs))
+				goto out_stop;
+			ip = READ_ONCE_TASK_STACK(state->task, regs->psw.addr);
+			reliable = true;
+		}
+	}
+
+#ifdef CONFIG_FUNCTION_GRAPH_TRACER
+	/* Decode any ftrace redirection */
+	if (ip == (unsigned long) return_to_handler)
+		ip = ftrace_graph_ret_addr(state->task, &state->graph_idx,
+					   ip, (void *) sp);
+#endif
+
+	/* Update unwind state */
+	state->sp = sp;
+	state->ip = ip;
+	state->regs = regs;
+	state->reliable = reliable;
+	return true;
+
+out_err:
+	state->error = true;
+out_stop:
+	state->stack_info.type = STACK_TYPE_UNKNOWN;
+	return false;
+}
+EXPORT_SYMBOL_GPL(unwind_next_frame);
+
+void __unwind_start(struct unwind_state *state, struct task_struct *task,
+		    struct pt_regs *regs, unsigned long sp)
+{
+	struct stack_info *info = &state->stack_info;
+	unsigned long *mask = &state->stack_mask;
+	struct stack_frame *sf;
+	unsigned long ip;
+	bool reliable;
+
+	memset(state, 0, sizeof(*state));
+	state->task = task;
+	state->regs = regs;
+
+	/* Don't even attempt to start from user mode regs: */
+	if (regs && user_mode(regs)) {
+		info->type = STACK_TYPE_UNKNOWN;
+		return;
+	}
+
+	/* Get current stack pointer and initialize stack info */
+	if (get_stack_info(sp, task, info, mask) != 0 ||
+	    !on_stack(info, sp, sizeof(struct stack_frame))) {
+		/* Something is wrong with the stack pointer */
+		info->type = STACK_TYPE_UNKNOWN;
+		state->error = true;
+		return;
+	}
+
+	/* Get the instruction pointer from pt_regs or the stack frame */
+	if (regs) {
+		ip = READ_ONCE_TASK_STACK(state->task, regs->psw.addr);
+		reliable = true;
+	} else {
+		sf = (struct stack_frame *) sp;
+		ip = READ_ONCE_TASK_STACK(state->task, sf->gprs[8]);
+		reliable = false;
+	}
+
+#ifdef CONFIG_FUNCTION_GRAPH_TRACER
+	/* Decode any ftrace redirection */
+	if (ip == (unsigned long) return_to_handler)
+		ip = ftrace_graph_ret_addr(state->task, &state->graph_idx,
+					   ip, NULL);
+#endif
+
+	/* Update unwind state */
+	state->sp = sp;
+	state->ip = ip;
+	state->reliable = reliable;
+}
+EXPORT_SYMBOL_GPL(__unwind_start);
diff --git a/arch/s390/kernel/vdso.c b/arch/s390/kernel/vdso.c
index e7920a68a12e..243d8b1185bf 100644
--- a/arch/s390/kernel/vdso.c
+++ b/arch/s390/kernel/vdso.c
@@ -29,7 +29,7 @@
 #include <asm/vdso.h>
 #include <asm/facility.h>
 
-#ifdef CONFIG_COMPAT
+#ifdef CONFIG_COMPAT_VDSO
 extern char vdso32_start, vdso32_end;
 static void *vdso32_kbase = &vdso32_start;
 static unsigned int vdso32_pages;
@@ -55,7 +55,7 @@ static vm_fault_t vdso_fault(const struct vm_special_mapping *sm,
 
 	vdso_pagelist = vdso64_pagelist;
 	vdso_pages = vdso64_pages;
-#ifdef CONFIG_COMPAT
+#ifdef CONFIG_COMPAT_VDSO
 	if (vma->vm_mm->context.compat_mm) {
 		vdso_pagelist = vdso32_pagelist;
 		vdso_pages = vdso32_pages;
@@ -76,7 +76,7 @@ static int vdso_mremap(const struct vm_special_mapping *sm,
 	unsigned long vdso_pages;
 
 	vdso_pages = vdso64_pages;
-#ifdef CONFIG_COMPAT
+#ifdef CONFIG_COMPAT_VDSO
 	if (vma->vm_mm->context.compat_mm)
 		vdso_pages = vdso32_pages;
 #endif
@@ -223,7 +223,7 @@ int arch_setup_additional_pages(struct linux_binprm *bprm, int uses_interp)
 		return 0;
 
 	vdso_pages = vdso64_pages;
-#ifdef CONFIG_COMPAT
+#ifdef CONFIG_COMPAT_VDSO
 	mm->context.compat_mm = is_compat_task();
 	if (mm->context.compat_mm)
 		vdso_pages = vdso32_pages;
@@ -280,7 +280,7 @@ static int __init vdso_init(void)
 	int i;
 
 	vdso_init_data(vdso_data);
-#ifdef CONFIG_COMPAT
+#ifdef CONFIG_COMPAT_VDSO
 	/* Calculate the size of the 32 bit vDSO */
 	vdso32_pages = ((&vdso32_end - &vdso32_start
 			 + PAGE_SIZE - 1) >> PAGE_SHIFT) + 1;
diff --git a/arch/s390/kernel/vdso32/Makefile b/arch/s390/kernel/vdso32/Makefile
index e76309fbbcb3..aee9ffbccb54 100644
--- a/arch/s390/kernel/vdso32/Makefile
+++ b/arch/s390/kernel/vdso32/Makefile
@@ -19,7 +19,7 @@ KBUILD_AFLAGS_31 += -m31 -s
 KBUILD_CFLAGS_31 := $(filter-out -m64,$(KBUILD_CFLAGS))
 KBUILD_CFLAGS_31 += -m31 -fPIC -shared -fno-common -fno-builtin
 KBUILD_CFLAGS_31 += -nostdlib -Wl,-soname=linux-vdso32.so.1 \
-			$(call cc-ldoption, -Wl$(comma)--hash-style=both)
+		    -Wl,--hash-style=both
 
 $(targets:%=$(obj)/%.dbg): KBUILD_CFLAGS = $(KBUILD_CFLAGS_31)
 $(targets:%=$(obj)/%.dbg): KBUILD_AFLAGS = $(KBUILD_AFLAGS_31)
diff --git a/arch/s390/kernel/vdso64/Makefile b/arch/s390/kernel/vdso64/Makefile
index f849ac61c5da..bec19e7e6e1c 100644
--- a/arch/s390/kernel/vdso64/Makefile
+++ b/arch/s390/kernel/vdso64/Makefile
@@ -19,7 +19,7 @@ KBUILD_AFLAGS_64 += -m64 -s
 KBUILD_CFLAGS_64 := $(filter-out -m64,$(KBUILD_CFLAGS))
 KBUILD_CFLAGS_64 += -m64 -fPIC -shared -fno-common -fno-builtin
 KBUILD_CFLAGS_64 += -nostdlib -Wl,-soname=linux-vdso64.so.1 \
-			$(call cc-ldoption, -Wl$(comma)--hash-style=both)
+		    -Wl,--hash-style=both
 
 $(targets:%=$(obj)/%.dbg): KBUILD_CFLAGS = $(KBUILD_CFLAGS_64)
 $(targets:%=$(obj)/%.dbg): KBUILD_AFLAGS = $(KBUILD_AFLAGS_64)
diff --git a/arch/s390/kernel/vmlinux.lds.S b/arch/s390/kernel/vmlinux.lds.S
index 8429ab079715..49d55327de0b 100644
--- a/arch/s390/kernel/vmlinux.lds.S
+++ b/arch/s390/kernel/vmlinux.lds.S
@@ -72,6 +72,7 @@ SECTIONS
 	__end_ro_after_init = .;
 
 	RW_DATA_SECTION(0x100, PAGE_SIZE, THREAD_SIZE)
+	BOOT_DATA_PRESERVED
 
 	_edata = .;		/* End of data section */
 
@@ -143,6 +144,18 @@ SECTIONS
 	INIT_DATA_SECTION(0x100)
 
 	PERCPU_SECTION(0x100)
+
+	.dynsym ALIGN(8) : {
+		__dynsym_start = .;
+		*(.dynsym)
+		__dynsym_end = .;
+	}
+	.rela.dyn ALIGN(8) : {
+		__rela_dyn_start = .;
+		*(.rela*)
+		__rela_dyn_end = .;
+	}
+
 	. = ALIGN(PAGE_SIZE);
 	__init_end = .;		/* freed after init ends here */
 
@@ -161,6 +174,12 @@ SECTIONS
 		QUAD(__bss_stop - __bss_start)			/* bss_size */
 		QUAD(__boot_data_start)				/* bootdata_off */
 		QUAD(__boot_data_end - __boot_data_start)	/* bootdata_size */
+		QUAD(__boot_data_preserved_start)		/* bootdata_preserved_off */
+		QUAD(__boot_data_preserved_end -
+		     __boot_data_preserved_start)		/* bootdata_preserved_size */
+		QUAD(__dynsym_start)				/* dynsym_start */
+		QUAD(__rela_dyn_start)				/* rela_dyn_start */
+		QUAD(__rela_dyn_end)				/* rela_dyn_end */
 	} :NONE
 
 	/* Debugging sections.	*/
diff --git a/arch/s390/kernel/vtime.c b/arch/s390/kernel/vtime.c
index 98f850e00008..c475ca49cfc6 100644
--- a/arch/s390/kernel/vtime.c
+++ b/arch/s390/kernel/vtime.c
@@ -37,7 +37,7 @@ static inline u64 get_vtimer(void)
 {
 	u64 timer;
 
-	asm volatile("stpt %0" : "=m" (timer));
+	asm volatile("stpt %0" : "=Q" (timer));
 	return timer;
 }
 
@@ -48,7 +48,7 @@ static inline void set_vtimer(u64 expires)
 	asm volatile(
 		"	stpt	%0\n"	/* Store current cpu timer value */
 		"	spt	%1"	/* Set new value imm. afterwards */
-		: "=m" (timer) : "m" (expires));
+		: "=Q" (timer) : "Q" (expires));
 	S390_lowcore.system_timer += S390_lowcore.last_update_timer - timer;
 	S390_lowcore.last_update_timer = expires;
 }
@@ -124,7 +124,7 @@ static void account_system_index_scaled(struct task_struct *p, u64 cputime,
  */
 static int do_account_vtime(struct task_struct *tsk)
 {
-	u64 timer, clock, user, guest, system, hardirq, softirq, steal;
+	u64 timer, clock, user, guest, system, hardirq, softirq;
 
 	timer = S390_lowcore.last_update_timer;
 	clock = S390_lowcore.last_update_clock;
@@ -135,8 +135,8 @@ static int do_account_vtime(struct task_struct *tsk)
 #else
 		"	stck	%1"	/* Store current tod clock value */
 #endif
-		: "=m" (S390_lowcore.last_update_timer),
-		  "=m" (S390_lowcore.last_update_clock));
+		: "=Q" (S390_lowcore.last_update_timer),
+		  "=Q" (S390_lowcore.last_update_clock));
 	clock = S390_lowcore.last_update_clock - clock;
 	timer -= S390_lowcore.last_update_timer;
 
@@ -182,12 +182,6 @@ static int do_account_vtime(struct task_struct *tsk)
 	if (softirq)
 		account_system_index_scaled(tsk, softirq, CPUTIME_SOFTIRQ);
 
-	steal = S390_lowcore.steal_timer;
-	if ((s64) steal > 0) {
-		S390_lowcore.steal_timer = 0;
-		account_steal_time(cputime_to_nsecs(steal));
-	}
-
 	return virt_timer_forward(user + guest + system + hardirq + softirq);
 }
 
@@ -213,8 +207,19 @@ void vtime_task_switch(struct task_struct *prev)
  */
 void vtime_flush(struct task_struct *tsk)
 {
+	u64 steal, avg_steal;
+
 	if (do_account_vtime(tsk))
 		virt_timer_expire();
+
+	steal = S390_lowcore.steal_timer;
+	avg_steal = S390_lowcore.avg_steal_timer / 2;
+	if ((s64) steal > 0) {
+		S390_lowcore.steal_timer = 0;
+		account_steal_time(steal);
+		avg_steal += steal;
+	}
+	S390_lowcore.avg_steal_timer = avg_steal;
 }
 
 /*
diff --git a/arch/s390/kvm/interrupt.c b/arch/s390/kvm/interrupt.c
index 82162867f378..37503ae62486 100644
--- a/arch/s390/kvm/interrupt.c
+++ b/arch/s390/kvm/interrupt.c
@@ -3194,7 +3194,7 @@ out:
 }
 EXPORT_SYMBOL_GPL(kvm_s390_gisc_unregister);
 
-static void gib_alert_irq_handler(struct airq_struct *airq)
+static void gib_alert_irq_handler(struct airq_struct *airq, bool floating)
 {
 	inc_irq_stat(IRQIO_GAL);
 	process_gib_alert_list();
diff --git a/arch/s390/lib/mem.S b/arch/s390/lib/mem.S
index 53008da05190..dc0874f2e203 100644
--- a/arch/s390/lib/mem.S
+++ b/arch/s390/lib/mem.S
@@ -178,6 +178,7 @@ ENTRY(__memset\bits)
 	BR_EX	%r14
 .L__memset_mvc\bits:
 	mvc	\bytes(1,%r1),0(%r1)
+ENDPROC(__memset\bits)
 .endm
 
 __MEMSET 16,2,sth
diff --git a/arch/s390/mm/Makefile b/arch/s390/mm/Makefile
index f5880bfd1b0c..3175413186b9 100644
--- a/arch/s390/mm/Makefile
+++ b/arch/s390/mm/Makefile
@@ -4,7 +4,7 @@
 #
 
 obj-y		:= init.o fault.o extmem.o mmap.o vmem.o maccess.o
-obj-y		+= page-states.o gup.o pageattr.o pgtable.o pgalloc.o
+obj-y		+= page-states.o pageattr.o pgtable.o pgalloc.o
 
 obj-$(CONFIG_CMM)		+= cmm.o
 obj-$(CONFIG_HUGETLB_PAGE)	+= hugetlbpage.o
diff --git a/arch/s390/mm/fault.c b/arch/s390/mm/fault.c
index 11613362c4e7..c220399ae196 100644
--- a/arch/s390/mm/fault.c
+++ b/arch/s390/mm/fault.c
@@ -247,12 +247,24 @@ static noinline void do_sigsegv(struct pt_regs *regs, int si_code)
 			current);
 }
 
+const struct exception_table_entry *s390_search_extables(unsigned long addr)
+{
+	const struct exception_table_entry *fixup;
+
+	fixup = search_extable(__start_dma_ex_table,
+			       __stop_dma_ex_table - __start_dma_ex_table,
+			       addr);
+	if (!fixup)
+		fixup = search_exception_tables(addr);
+	return fixup;
+}
+
 static noinline void do_no_context(struct pt_regs *regs)
 {
 	const struct exception_table_entry *fixup;
 
 	/* Are we prepared to handle this kernel fault?  */
-	fixup = search_exception_tables(regs->psw.addr);
+	fixup = s390_search_extables(regs->psw.addr);
 	if (fixup) {
 		regs->psw.addr = extable_fixup(fixup);
 		return;
diff --git a/arch/s390/mm/gup.c b/arch/s390/mm/gup.c
deleted file mode 100644
index 2809d11c7a28..000000000000
--- a/arch/s390/mm/gup.c
+++ /dev/null
@@ -1,300 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0
-/*
- *  Lockless get_user_pages_fast for s390
- *
- *  Copyright IBM Corp. 2010
- *  Author(s): Martin Schwidefsky <schwidefsky@de.ibm.com>
- */
-#include <linux/sched.h>
-#include <linux/mm.h>
-#include <linux/hugetlb.h>
-#include <linux/vmstat.h>
-#include <linux/pagemap.h>
-#include <linux/rwsem.h>
-#include <asm/pgtable.h>
-
-/*
- * The performance critical leaf functions are made noinline otherwise gcc
- * inlines everything into a single function which results in too much
- * register pressure.
- */
-static inline int gup_pte_range(pmd_t *pmdp, pmd_t pmd, unsigned long addr,
-		unsigned long end, int write, struct page **pages, int *nr)
-{
-	struct page *head, *page;
-	unsigned long mask;
-	pte_t *ptep, pte;
-
-	mask = (write ? _PAGE_PROTECT : 0) | _PAGE_INVALID | _PAGE_SPECIAL;
-
-	ptep = ((pte_t *) pmd_deref(pmd)) + pte_index(addr);
-	do {
-		pte = *ptep;
-		barrier();
-		/* Similar to the PMD case, NUMA hinting must take slow path */
-		if (pte_protnone(pte))
-			return 0;
-		if ((pte_val(pte) & mask) != 0)
-			return 0;
-		VM_BUG_ON(!pfn_valid(pte_pfn(pte)));
-		page = pte_page(pte);
-		head = compound_head(page);
-		if (!page_cache_get_speculative(head))
-			return 0;
-		if (unlikely(pte_val(pte) != pte_val(*ptep))) {
-			put_page(head);
-			return 0;
-		}
-		VM_BUG_ON_PAGE(compound_head(page) != head, page);
-		pages[*nr] = page;
-		(*nr)++;
-
-	} while (ptep++, addr += PAGE_SIZE, addr != end);
-
-	return 1;
-}
-
-static inline int gup_huge_pmd(pmd_t *pmdp, pmd_t pmd, unsigned long addr,
-		unsigned long end, int write, struct page **pages, int *nr)
-{
-	struct page *head, *page;
-	unsigned long mask;
-	int refs;
-
-	mask = (write ? _SEGMENT_ENTRY_PROTECT : 0) | _SEGMENT_ENTRY_INVALID;
-	if ((pmd_val(pmd) & mask) != 0)
-		return 0;
-	VM_BUG_ON(!pfn_valid(pmd_val(pmd) >> PAGE_SHIFT));
-
-	refs = 0;
-	head = pmd_page(pmd);
-	page = head + ((addr & ~PMD_MASK) >> PAGE_SHIFT);
-	do {
-		VM_BUG_ON(compound_head(page) != head);
-		pages[*nr] = page;
-		(*nr)++;
-		page++;
-		refs++;
-	} while (addr += PAGE_SIZE, addr != end);
-
-	if (!page_cache_add_speculative(head, refs)) {
-		*nr -= refs;
-		return 0;
-	}
-
-	if (unlikely(pmd_val(pmd) != pmd_val(*pmdp))) {
-		*nr -= refs;
-		while (refs--)
-			put_page(head);
-		return 0;
-	}
-
-	return 1;
-}
-
-
-static inline int gup_pmd_range(pud_t *pudp, pud_t pud, unsigned long addr,
-		unsigned long end, int write, struct page **pages, int *nr)
-{
-	unsigned long next;
-	pmd_t *pmdp, pmd;
-
-	pmdp = (pmd_t *) pudp;
-	if ((pud_val(pud) & _REGION_ENTRY_TYPE_MASK) == _REGION_ENTRY_TYPE_R3)
-		pmdp = (pmd_t *) pud_deref(pud);
-	pmdp += pmd_index(addr);
-	do {
-		pmd = *pmdp;
-		barrier();
-		next = pmd_addr_end(addr, end);
-		if (pmd_none(pmd))
-			return 0;
-		if (unlikely(pmd_large(pmd))) {
-			/*
-			 * NUMA hinting faults need to be handled in the GUP
-			 * slowpath for accounting purposes and so that they
-			 * can be serialised against THP migration.
-			 */
-			if (pmd_protnone(pmd))
-				return 0;
-			if (!gup_huge_pmd(pmdp, pmd, addr, next,
-					  write, pages, nr))
-				return 0;
-		} else if (!gup_pte_range(pmdp, pmd, addr, next,
-					  write, pages, nr))
-			return 0;
-	} while (pmdp++, addr = next, addr != end);
-
-	return 1;
-}
-
-static int gup_huge_pud(pud_t *pudp, pud_t pud, unsigned long addr,
-		unsigned long end, int write, struct page **pages, int *nr)
-{
-	struct page *head, *page;
-	unsigned long mask;
-	int refs;
-
-	mask = (write ? _REGION_ENTRY_PROTECT : 0) | _REGION_ENTRY_INVALID;
-	if ((pud_val(pud) & mask) != 0)
-		return 0;
-	VM_BUG_ON(!pfn_valid(pud_pfn(pud)));
-
-	refs = 0;
-	head = pud_page(pud);
-	page = head + ((addr & ~PUD_MASK) >> PAGE_SHIFT);
-	do {
-		VM_BUG_ON_PAGE(compound_head(page) != head, page);
-		pages[*nr] = page;
-		(*nr)++;
-		page++;
-		refs++;
-	} while (addr += PAGE_SIZE, addr != end);
-
-	if (!page_cache_add_speculative(head, refs)) {
-		*nr -= refs;
-		return 0;
-	}
-
-	if (unlikely(pud_val(pud) != pud_val(*pudp))) {
-		*nr -= refs;
-		while (refs--)
-			put_page(head);
-		return 0;
-	}
-
-	return 1;
-}
-
-static inline int gup_pud_range(p4d_t *p4dp, p4d_t p4d, unsigned long addr,
-		unsigned long end, int write, struct page **pages, int *nr)
-{
-	unsigned long next;
-	pud_t *pudp, pud;
-
-	pudp = (pud_t *) p4dp;
-	if ((p4d_val(p4d) & _REGION_ENTRY_TYPE_MASK) == _REGION_ENTRY_TYPE_R2)
-		pudp = (pud_t *) p4d_deref(p4d);
-	pudp += pud_index(addr);
-	do {
-		pud = *pudp;
-		barrier();
-		next = pud_addr_end(addr, end);
-		if (pud_none(pud))
-			return 0;
-		if (unlikely(pud_large(pud))) {
-			if (!gup_huge_pud(pudp, pud, addr, next, write, pages,
-					  nr))
-				return 0;
-		} else if (!gup_pmd_range(pudp, pud, addr, next, write, pages,
-					  nr))
-			return 0;
-	} while (pudp++, addr = next, addr != end);
-
-	return 1;
-}
-
-static inline int gup_p4d_range(pgd_t *pgdp, pgd_t pgd, unsigned long addr,
-		unsigned long end, int write, struct page **pages, int *nr)
-{
-	unsigned long next;
-	p4d_t *p4dp, p4d;
-
-	p4dp = (p4d_t *) pgdp;
-	if ((pgd_val(pgd) & _REGION_ENTRY_TYPE_MASK) == _REGION_ENTRY_TYPE_R1)
-		p4dp = (p4d_t *) pgd_deref(pgd);
-	p4dp += p4d_index(addr);
-	do {
-		p4d = *p4dp;
-		barrier();
-		next = p4d_addr_end(addr, end);
-		if (p4d_none(p4d))
-			return 0;
-		if (!gup_pud_range(p4dp, p4d, addr, next, write, pages, nr))
-			return 0;
-	} while (p4dp++, addr = next, addr != end);
-
-	return 1;
-}
-
-/*
- * Like get_user_pages_fast() except its IRQ-safe in that it won't fall
- * back to the regular GUP.
- * Note a difference with get_user_pages_fast: this always returns the
- * number of pages pinned, 0 if no pages were pinned.
- */
-int __get_user_pages_fast(unsigned long start, int nr_pages, int write,
-			  struct page **pages)
-{
-	struct mm_struct *mm = current->mm;
-	unsigned long addr, len, end;
-	unsigned long next, flags;
-	pgd_t *pgdp, pgd;
-	int nr = 0;
-
-	start &= PAGE_MASK;
-	addr = start;
-	len = (unsigned long) nr_pages << PAGE_SHIFT;
-	end = start + len;
-	if ((end <= start) || (end > mm->context.asce_limit))
-		return 0;
-	/*
-	 * local_irq_save() doesn't prevent pagetable teardown, but does
-	 * prevent the pagetables from being freed on s390.
-	 *
-	 * So long as we atomically load page table pointers versus teardown,
-	 * we can follow the address down to the the page and take a ref on it.
-	 */
-	local_irq_save(flags);
-	pgdp = pgd_offset(mm, addr);
-	do {
-		pgd = *pgdp;
-		barrier();
-		next = pgd_addr_end(addr, end);
-		if (pgd_none(pgd))
-			break;
-		if (!gup_p4d_range(pgdp, pgd, addr, next, write, pages, &nr))
-			break;
-	} while (pgdp++, addr = next, addr != end);
-	local_irq_restore(flags);
-
-	return nr;
-}
-
-/**
- * get_user_pages_fast() - pin user pages in memory
- * @start:	starting user address
- * @nr_pages:	number of pages from start to pin
- * @write:	whether pages will be written to
- * @pages:	array that receives pointers to the pages pinned.
- *		Should be at least nr_pages long.
- *
- * Attempt to pin user pages in memory without taking mm->mmap_sem.
- * If not successful, it will fall back to taking the lock and
- * calling get_user_pages().
- *
- * Returns number of pages pinned. This may be fewer than the number
- * requested. If nr_pages is 0 or negative, returns 0. If no pages
- * were pinned, returns -errno.
- */
-int get_user_pages_fast(unsigned long start, int nr_pages, int write,
-			struct page **pages)
-{
-	int nr, ret;
-
-	might_sleep();
-	start &= PAGE_MASK;
-	nr = __get_user_pages_fast(start, nr_pages, write, pages);
-	if (nr == nr_pages)
-		return nr;
-
-	/* Try to get the remaining pages with get_user_pages */
-	start += nr << PAGE_SHIFT;
-	pages += nr;
-	ret = get_user_pages_unlocked(start, nr_pages - nr, pages,
-				      write ? FOLL_WRITE : 0);
-	/* Have to be a bit careful with return values */
-	if (nr > 0)
-		ret = (ret < 0) ? nr : ret + nr;
-	return ret;
-}
diff --git a/arch/s390/mm/init.c b/arch/s390/mm/init.c
index 3e82f66d5c61..7cf48eefec8f 100644
--- a/arch/s390/mm/init.c
+++ b/arch/s390/mm/init.c
@@ -49,6 +49,8 @@ unsigned long empty_zero_page, zero_page_mask;
 EXPORT_SYMBOL(empty_zero_page);
 EXPORT_SYMBOL(zero_page_mask);
 
+bool initmem_freed;
+
 static void __init setup_zero_pages(void)
 {
 	unsigned int order;
@@ -148,6 +150,7 @@ void __init mem_init(void)
 
 void free_initmem(void)
 {
+	initmem_freed = true;
 	__set_memory((unsigned long)_sinittext,
 		     (unsigned long)(_einittext - _sinittext) >> PAGE_SHIFT,
 		     SET_MEMORY_RW | SET_MEMORY_NX);
diff --git a/arch/s390/mm/maccess.c b/arch/s390/mm/maccess.c
index 97b3ee53852b..818deeb1ebc3 100644
--- a/arch/s390/mm/maccess.c
+++ b/arch/s390/mm/maccess.c
@@ -16,6 +16,7 @@
 #include <linux/cpu.h>
 #include <asm/ctl_reg.h>
 #include <asm/io.h>
+#include <asm/stacktrace.h>
 
 static notrace long s390_kernel_write_odd(void *dst, const void *src, size_t size)
 {
diff --git a/arch/s390/mm/pgalloc.c b/arch/s390/mm/pgalloc.c
index db6bb2f97a2c..99e06213a22b 100644
--- a/arch/s390/mm/pgalloc.c
+++ b/arch/s390/mm/pgalloc.c
@@ -290,7 +290,7 @@ void page_table_free_rcu(struct mmu_gather *tlb, unsigned long *table,
 	tlb_remove_table(tlb, table);
 }
 
-static void __tlb_remove_table(void *_table)
+void __tlb_remove_table(void *_table)
 {
 	unsigned int mask = (unsigned long) _table & 3;
 	void *table = (void *)((unsigned long) _table ^ mask);
@@ -316,67 +316,6 @@ static void __tlb_remove_table(void *_table)
 	}
 }
 
-static void tlb_remove_table_smp_sync(void *arg)
-{
-	/* Simply deliver the interrupt */
-}
-
-static void tlb_remove_table_one(void *table)
-{
-	/*
-	 * This isn't an RCU grace period and hence the page-tables cannot be
-	 * assumed to be actually RCU-freed.
-	 *
-	 * It is however sufficient for software page-table walkers that rely
-	 * on IRQ disabling. See the comment near struct mmu_table_batch.
-	 */
-	smp_call_function(tlb_remove_table_smp_sync, NULL, 1);
-	__tlb_remove_table(table);
-}
-
-static void tlb_remove_table_rcu(struct rcu_head *head)
-{
-	struct mmu_table_batch *batch;
-	int i;
-
-	batch = container_of(head, struct mmu_table_batch, rcu);
-
-	for (i = 0; i < batch->nr; i++)
-		__tlb_remove_table(batch->tables[i]);
-
-	free_page((unsigned long)batch);
-}
-
-void tlb_table_flush(struct mmu_gather *tlb)
-{
-	struct mmu_table_batch **batch = &tlb->batch;
-
-	if (*batch) {
-		call_rcu(&(*batch)->rcu, tlb_remove_table_rcu);
-		*batch = NULL;
-	}
-}
-
-void tlb_remove_table(struct mmu_gather *tlb, void *table)
-{
-	struct mmu_table_batch **batch = &tlb->batch;
-
-	tlb->mm->context.flush_mm = 1;
-	if (*batch == NULL) {
-		*batch = (struct mmu_table_batch *)
-			__get_free_page(GFP_NOWAIT | __GFP_NOWARN);
-		if (*batch == NULL) {
-			__tlb_flush_mm_lazy(tlb->mm);
-			tlb_remove_table_one(table);
-			return;
-		}
-		(*batch)->nr = 0;
-	}
-	(*batch)->tables[(*batch)->nr++] = table;
-	if ((*batch)->nr == MAX_TABLE_BATCH)
-		tlb_flush_mmu(tlb);
-}
-
 /*
  * Base infrastructure required to generate basic asces, region, segment,
  * and page tables that do not make use of enhanced features like EDAT1.
diff --git a/arch/s390/mm/pgtable.c b/arch/s390/mm/pgtable.c
index 8485d6dc2754..9ebd01219812 100644
--- a/arch/s390/mm/pgtable.c
+++ b/arch/s390/mm/pgtable.c
@@ -410,6 +410,7 @@ static inline pmd_t pmdp_flush_lazy(struct mm_struct *mm,
 	return old;
 }
 
+#ifdef CONFIG_PGSTE
 static pmd_t *pmd_alloc_map(struct mm_struct *mm, unsigned long addr)
 {
 	pgd_t *pgd;
@@ -427,6 +428,7 @@ static pmd_t *pmd_alloc_map(struct mm_struct *mm, unsigned long addr)
 	pmd = pmd_alloc(mm, pud, addr);
 	return pmd;
 }
+#endif
 
 pmd_t pmdp_xchg_direct(struct mm_struct *mm, unsigned long addr,
 		       pmd_t *pmdp, pmd_t new)
diff --git a/arch/s390/mm/vmem.c b/arch/s390/mm/vmem.c
index 0472e27febdf..b403fa14847d 100644
--- a/arch/s390/mm/vmem.c
+++ b/arch/s390/mm/vmem.c
@@ -413,6 +413,8 @@ void __init vmem_map_init(void)
 	__set_memory((unsigned long)_sinittext,
 		     (unsigned long)(_einittext - _sinittext) >> PAGE_SHIFT,
 		     SET_MEMORY_RO | SET_MEMORY_X);
+	__set_memory(__stext_dma, (__etext_dma - __stext_dma) >> PAGE_SHIFT,
+		     SET_MEMORY_RO | SET_MEMORY_X);
 	pr_info("Write protected kernel read-only data: %luk\n",
 		(unsigned long)(__end_rodata - _stext) >> 10);
 }
diff --git a/arch/s390/net/bpf_jit_comp.c b/arch/s390/net/bpf_jit_comp.c
index 51dd0267d014..5e7c63033159 100644
--- a/arch/s390/net/bpf_jit_comp.c
+++ b/arch/s390/net/bpf_jit_comp.c
@@ -455,7 +455,7 @@ static void bpf_jit_epilogue(struct bpf_jit *jit, u32 stack_depth)
 	EMIT4(0xb9040000, REG_2, BPF_REG_0);
 	/* Restore registers */
 	save_restore_regs(jit, REGS_RESTORE, stack_depth);
-	if (IS_ENABLED(CC_USING_EXPOLINE) && !nospec_disable) {
+	if (__is_defined(CC_USING_EXPOLINE) && !nospec_disable) {
 		jit->r14_thunk_ip = jit->prg;
 		/* Generate __s390_indirect_jump_r14 thunk */
 		if (test_facility(35)) {
@@ -473,7 +473,7 @@ static void bpf_jit_epilogue(struct bpf_jit *jit, u32 stack_depth)
 	/* br %r14 */
 	_EMIT2(0x07fe);
 
-	if (IS_ENABLED(CC_USING_EXPOLINE) && !nospec_disable &&
+	if (__is_defined(CC_USING_EXPOLINE) && !nospec_disable &&
 	    (jit->seen & SEEN_FUNC)) {
 		jit->r1_thunk_ip = jit->prg;
 		/* Generate __s390_indirect_jump_r1 thunk */
@@ -999,7 +999,7 @@ static noinline int bpf_jit_insn(struct bpf_jit *jit, struct bpf_prog *fp, int i
 		/* lg %w1,<d(imm)>(%l) */
 		EMIT6_DISP_LH(0xe3000000, 0x0004, REG_W1, REG_0, REG_L,
 			      EMIT_CONST_U64(func));
-		if (IS_ENABLED(CC_USING_EXPOLINE) && !nospec_disable) {
+		if (__is_defined(CC_USING_EXPOLINE) && !nospec_disable) {
 			/* brasl %r14,__s390_indirect_jump_r1 */
 			EMIT6_PCREL_RILB(0xc0050000, REG_14, jit->r1_thunk_ip);
 		} else {
diff --git a/arch/s390/oprofile/init.c b/arch/s390/oprofile/init.c
index 43d9525c36fc..7441857df51b 100644
--- a/arch/s390/oprofile/init.c
+++ b/arch/s390/oprofile/init.c
@@ -13,23 +13,17 @@
 #include <linux/oprofile.h>
 #include <linux/init.h>
 #include <asm/processor.h>
-
-static int __s390_backtrace(void *data, unsigned long address, int reliable)
-{
-	unsigned int *depth = data;
-
-	if (*depth == 0)
-		return 1;
-	(*depth)--;
-	oprofile_add_trace(address);
-	return 0;
-}
+#include <asm/unwind.h>
 
 static void s390_backtrace(struct pt_regs *regs, unsigned int depth)
 {
-	if (user_mode(regs))
-		return;
-	dump_trace(__s390_backtrace, &depth, NULL, regs->gprs[15]);
+	struct unwind_state state;
+
+	unwind_for_each_frame(&state, current, regs, 0) {
+		if (depth-- == 0)
+			break;
+		oprofile_add_trace(state.ip);
+	}
 }
 
 int __init oprofile_arch_init(struct oprofile_operations *ops)
diff --git a/arch/s390/pci/Makefile b/arch/s390/pci/Makefile
index 22d0871291ee..748626a33028 100644
--- a/arch/s390/pci/Makefile
+++ b/arch/s390/pci/Makefile
@@ -3,5 +3,5 @@
 # Makefile for the s390 PCI subsystem.
 #
 
-obj-$(CONFIG_PCI)	+= pci.o pci_dma.o pci_clp.o pci_sysfs.o \
+obj-$(CONFIG_PCI)	+= pci.o pci_irq.o pci_dma.o pci_clp.o pci_sysfs.o \
 			   pci_event.o pci_debug.o pci_insn.o pci_mmio.o
diff --git a/arch/s390/pci/pci.c b/arch/s390/pci/pci.c
index dc9bc82c072c..0ebb7c405a25 100644
--- a/arch/s390/pci/pci.c
+++ b/arch/s390/pci/pci.c
@@ -24,11 +24,9 @@
 #include <linux/err.h>
 #include <linux/export.h>
 #include <linux/delay.h>
-#include <linux/irq.h>
-#include <linux/kernel_stat.h>
 #include <linux/seq_file.h>
+#include <linux/jump_label.h>
 #include <linux/pci.h>
-#include <linux/msi.h>
 
 #include <asm/isc.h>
 #include <asm/airq.h>
@@ -37,30 +35,13 @@
 #include <asm/pci_clp.h>
 #include <asm/pci_dma.h>
 
-#define DEBUG				/* enable pr_debug */
-
-#define	SIC_IRQ_MODE_ALL		0
-#define	SIC_IRQ_MODE_SINGLE		1
-
-#define ZPCI_NR_DMA_SPACES		1
-#define ZPCI_NR_DEVICES			CONFIG_PCI_NR_FUNCTIONS
-
 /* list of all detected zpci devices */
 static LIST_HEAD(zpci_list);
 static DEFINE_SPINLOCK(zpci_list_lock);
 
-static struct irq_chip zpci_irq_chip = {
-	.name = "zPCI",
-	.irq_unmask = pci_msi_unmask_irq,
-	.irq_mask = pci_msi_mask_irq,
-};
-
 static DECLARE_BITMAP(zpci_domain, ZPCI_NR_DEVICES);
 static DEFINE_SPINLOCK(zpci_domain_lock);
 
-static struct airq_iv *zpci_aisb_iv;
-static struct airq_iv *zpci_aibv[ZPCI_NR_DEVICES];
-
 #define ZPCI_IOMAP_ENTRIES						\
 	min(((unsigned long) ZPCI_NR_DEVICES * PCI_BAR_COUNT / 2),	\
 	    ZPCI_IOMAP_MAX_ENTRIES)
@@ -70,6 +51,8 @@ static unsigned long *zpci_iomap_bitmap;
 struct zpci_iomap_entry *zpci_iomap_start;
 EXPORT_SYMBOL_GPL(zpci_iomap_start);
 
+DEFINE_STATIC_KEY_FALSE(have_mio);
+
 static struct kmem_cache *zdev_fmb_cache;
 
 struct zpci_dev *get_zdev_by_fid(u32 fid)
@@ -123,39 +106,6 @@ int pci_proc_domain(struct pci_bus *bus)
 }
 EXPORT_SYMBOL_GPL(pci_proc_domain);
 
-/* Modify PCI: Register adapter interruptions */
-static int zpci_set_airq(struct zpci_dev *zdev)
-{
-	u64 req = ZPCI_CREATE_REQ(zdev->fh, 0, ZPCI_MOD_FC_REG_INT);
-	struct zpci_fib fib = {0};
-	u8 status;
-
-	fib.isc = PCI_ISC;
-	fib.sum = 1;		/* enable summary notifications */
-	fib.noi = airq_iv_end(zdev->aibv);
-	fib.aibv = (unsigned long) zdev->aibv->vector;
-	fib.aibvo = 0;		/* each zdev has its own interrupt vector */
-	fib.aisb = (unsigned long) zpci_aisb_iv->vector + (zdev->aisb/64)*8;
-	fib.aisbo = zdev->aisb & 63;
-
-	return zpci_mod_fc(req, &fib, &status) ? -EIO : 0;
-}
-
-/* Modify PCI: Unregister adapter interruptions */
-static int zpci_clear_airq(struct zpci_dev *zdev)
-{
-	u64 req = ZPCI_CREATE_REQ(zdev->fh, 0, ZPCI_MOD_FC_DEREG_INT);
-	struct zpci_fib fib = {0};
-	u8 cc, status;
-
-	cc = zpci_mod_fc(req, &fib, &status);
-	if (cc == 3 || (cc == 1 && status == 24))
-		/* Function already gone or IRQs already deregistered. */
-		cc = 0;
-
-	return cc ? -EIO : 0;
-}
-
 /* Modify PCI: Register I/O address translation parameters */
 int zpci_register_ioat(struct zpci_dev *zdev, u8 dmaas,
 		       u64 base, u64 limit, u64 iota)
@@ -241,7 +191,7 @@ static int zpci_cfg_load(struct zpci_dev *zdev, int offset, u32 *val, u8 len)
 	u64 data;
 	int rc;
 
-	rc = zpci_load(&data, req, offset);
+	rc = __zpci_load(&data, req, offset);
 	if (!rc) {
 		data = le64_to_cpu((__force __le64) data);
 		data >>= (8 - len) * 8;
@@ -259,7 +209,7 @@ static int zpci_cfg_store(struct zpci_dev *zdev, int offset, u32 val, u8 len)
 
 	data <<= (8 - len) * 8;
 	data = (__force u64) cpu_to_le64(data);
-	rc = zpci_store(data, req, offset);
+	rc = __zpci_store(data, req, offset);
 	return rc;
 }
 
@@ -276,18 +226,48 @@ void __iowrite64_copy(void __iomem *to, const void *from, size_t count)
        zpci_memcpy_toio(to, from, count);
 }
 
+void __iomem *ioremap(unsigned long ioaddr, unsigned long size)
+{
+	struct vm_struct *area;
+	unsigned long offset;
+
+	if (!size)
+		return NULL;
+
+	if (!static_branch_unlikely(&have_mio))
+		return (void __iomem *) ioaddr;
+
+	offset = ioaddr & ~PAGE_MASK;
+	ioaddr &= PAGE_MASK;
+	size = PAGE_ALIGN(size + offset);
+	area = get_vm_area(size, VM_IOREMAP);
+	if (!area)
+		return NULL;
+
+	if (ioremap_page_range((unsigned long) area->addr,
+			       (unsigned long) area->addr + size,
+			       ioaddr, PAGE_KERNEL)) {
+		vunmap(area->addr);
+		return NULL;
+	}
+	return (void __iomem *) ((unsigned long) area->addr + offset);
+}
+EXPORT_SYMBOL(ioremap);
+
+void iounmap(volatile void __iomem *addr)
+{
+	if (static_branch_likely(&have_mio))
+		vunmap((__force void *) ((unsigned long) addr & PAGE_MASK));
+}
+EXPORT_SYMBOL(iounmap);
+
 /* Create a virtual mapping cookie for a PCI BAR */
-void __iomem *pci_iomap_range(struct pci_dev *pdev,
-			      int bar,
-			      unsigned long offset,
-			      unsigned long max)
+static void __iomem *pci_iomap_range_fh(struct pci_dev *pdev, int bar,
+					unsigned long offset, unsigned long max)
 {
 	struct zpci_dev *zdev =	to_zpci(pdev);
 	int idx;
 
-	if (!pci_resource_len(pdev, bar) || bar >= PCI_BAR_COUNT)
-		return NULL;
-
 	idx = zdev->bars[bar].map_idx;
 	spin_lock(&zpci_iomap_lock);
 	/* Detect overrun */
@@ -298,6 +278,30 @@ void __iomem *pci_iomap_range(struct pci_dev *pdev,
 
 	return (void __iomem *) ZPCI_ADDR(idx) + offset;
 }
+
+static void __iomem *pci_iomap_range_mio(struct pci_dev *pdev, int bar,
+					 unsigned long offset,
+					 unsigned long max)
+{
+	unsigned long barsize = pci_resource_len(pdev, bar);
+	struct zpci_dev *zdev = to_zpci(pdev);
+	void __iomem *iova;
+
+	iova = ioremap((unsigned long) zdev->bars[bar].mio_wt, barsize);
+	return iova ? iova + offset : iova;
+}
+
+void __iomem *pci_iomap_range(struct pci_dev *pdev, int bar,
+			      unsigned long offset, unsigned long max)
+{
+	if (!pci_resource_len(pdev, bar) || bar >= PCI_BAR_COUNT)
+		return NULL;
+
+	if (static_branch_likely(&have_mio))
+		return pci_iomap_range_mio(pdev, bar, offset, max);
+	else
+		return pci_iomap_range_fh(pdev, bar, offset, max);
+}
 EXPORT_SYMBOL(pci_iomap_range);
 
 void __iomem *pci_iomap(struct pci_dev *dev, int bar, unsigned long maxlen)
@@ -306,7 +310,37 @@ void __iomem *pci_iomap(struct pci_dev *dev, int bar, unsigned long maxlen)
 }
 EXPORT_SYMBOL(pci_iomap);
 
-void pci_iounmap(struct pci_dev *pdev, void __iomem *addr)
+static void __iomem *pci_iomap_wc_range_mio(struct pci_dev *pdev, int bar,
+					    unsigned long offset, unsigned long max)
+{
+	unsigned long barsize = pci_resource_len(pdev, bar);
+	struct zpci_dev *zdev = to_zpci(pdev);
+	void __iomem *iova;
+
+	iova = ioremap((unsigned long) zdev->bars[bar].mio_wb, barsize);
+	return iova ? iova + offset : iova;
+}
+
+void __iomem *pci_iomap_wc_range(struct pci_dev *pdev, int bar,
+				 unsigned long offset, unsigned long max)
+{
+	if (!pci_resource_len(pdev, bar) || bar >= PCI_BAR_COUNT)
+		return NULL;
+
+	if (static_branch_likely(&have_mio))
+		return pci_iomap_wc_range_mio(pdev, bar, offset, max);
+	else
+		return pci_iomap_range_fh(pdev, bar, offset, max);
+}
+EXPORT_SYMBOL(pci_iomap_wc_range);
+
+void __iomem *pci_iomap_wc(struct pci_dev *dev, int bar, unsigned long maxlen)
+{
+	return pci_iomap_wc_range(dev, bar, 0, maxlen);
+}
+EXPORT_SYMBOL(pci_iomap_wc);
+
+static void pci_iounmap_fh(struct pci_dev *pdev, void __iomem *addr)
 {
 	unsigned int idx = ZPCI_IDX(addr);
 
@@ -319,6 +353,19 @@ void pci_iounmap(struct pci_dev *pdev, void __iomem *addr)
 	}
 	spin_unlock(&zpci_iomap_lock);
 }
+
+static void pci_iounmap_mio(struct pci_dev *pdev, void __iomem *addr)
+{
+	iounmap(addr);
+}
+
+void pci_iounmap(struct pci_dev *pdev, void __iomem *addr)
+{
+	if (static_branch_likely(&have_mio))
+		pci_iounmap_mio(pdev, addr);
+	else
+		pci_iounmap_fh(pdev, addr);
+}
 EXPORT_SYMBOL(pci_iounmap);
 
 static int pci_read(struct pci_bus *bus, unsigned int devfn, int where,
@@ -354,136 +401,6 @@ static struct pci_ops pci_root_ops = {
 	.write = pci_write,
 };
 
-static void zpci_irq_handler(struct airq_struct *airq)
-{
-	unsigned long si, ai;
-	struct airq_iv *aibv;
-	int irqs_on = 0;
-
-	inc_irq_stat(IRQIO_PCI);
-	for (si = 0;;) {
-		/* Scan adapter summary indicator bit vector */
-		si = airq_iv_scan(zpci_aisb_iv, si, airq_iv_end(zpci_aisb_iv));
-		if (si == -1UL) {
-			if (irqs_on++)
-				/* End of second scan with interrupts on. */
-				break;
-			/* First scan complete, reenable interrupts. */
-			if (zpci_set_irq_ctrl(SIC_IRQ_MODE_SINGLE, NULL, PCI_ISC))
-				break;
-			si = 0;
-			continue;
-		}
-
-		/* Scan the adapter interrupt vector for this device. */
-		aibv = zpci_aibv[si];
-		for (ai = 0;;) {
-			ai = airq_iv_scan(aibv, ai, airq_iv_end(aibv));
-			if (ai == -1UL)
-				break;
-			inc_irq_stat(IRQIO_MSI);
-			airq_iv_lock(aibv, ai);
-			generic_handle_irq(airq_iv_get_data(aibv, ai));
-			airq_iv_unlock(aibv, ai);
-		}
-	}
-}
-
-int arch_setup_msi_irqs(struct pci_dev *pdev, int nvec, int type)
-{
-	struct zpci_dev *zdev = to_zpci(pdev);
-	unsigned int hwirq, msi_vecs;
-	unsigned long aisb;
-	struct msi_desc *msi;
-	struct msi_msg msg;
-	int rc, irq;
-
-	zdev->aisb = -1UL;
-	if (type == PCI_CAP_ID_MSI && nvec > 1)
-		return 1;
-	msi_vecs = min_t(unsigned int, nvec, zdev->max_msi);
-
-	/* Allocate adapter summary indicator bit */
-	aisb = airq_iv_alloc_bit(zpci_aisb_iv);
-	if (aisb == -1UL)
-		return -EIO;
-	zdev->aisb = aisb;
-
-	/* Create adapter interrupt vector */
-	zdev->aibv = airq_iv_create(msi_vecs, AIRQ_IV_DATA | AIRQ_IV_BITLOCK);
-	if (!zdev->aibv)
-		return -ENOMEM;
-
-	/* Wire up shortcut pointer */
-	zpci_aibv[aisb] = zdev->aibv;
-
-	/* Request MSI interrupts */
-	hwirq = 0;
-	for_each_pci_msi_entry(msi, pdev) {
-		if (hwirq >= msi_vecs)
-			break;
-		irq = irq_alloc_desc(0);	/* Alloc irq on node 0 */
-		if (irq < 0)
-			return -ENOMEM;
-		rc = irq_set_msi_desc(irq, msi);
-		if (rc)
-			return rc;
-		irq_set_chip_and_handler(irq, &zpci_irq_chip,
-					 handle_simple_irq);
-		msg.data = hwirq;
-		msg.address_lo = zdev->msi_addr & 0xffffffff;
-		msg.address_hi = zdev->msi_addr >> 32;
-		pci_write_msi_msg(irq, &msg);
-		airq_iv_set_data(zdev->aibv, hwirq, irq);
-		hwirq++;
-	}
-
-	/* Enable adapter interrupts */
-	rc = zpci_set_airq(zdev);
-	if (rc)
-		return rc;
-
-	return (msi_vecs == nvec) ? 0 : msi_vecs;
-}
-
-void arch_teardown_msi_irqs(struct pci_dev *pdev)
-{
-	struct zpci_dev *zdev = to_zpci(pdev);
-	struct msi_desc *msi;
-	int rc;
-
-	/* Disable adapter interrupts */
-	rc = zpci_clear_airq(zdev);
-	if (rc)
-		return;
-
-	/* Release MSI interrupts */
-	for_each_pci_msi_entry(msi, pdev) {
-		if (!msi->irq)
-			continue;
-		if (msi->msi_attrib.is_msix)
-			__pci_msix_desc_mask_irq(msi, 1);
-		else
-			__pci_msi_desc_mask_irq(msi, 1, 1);
-		irq_set_msi_desc(msi->irq, NULL);
-		irq_free_desc(msi->irq);
-		msi->msg.address_lo = 0;
-		msi->msg.address_hi = 0;
-		msi->msg.data = 0;
-		msi->irq = 0;
-	}
-
-	if (zdev->aisb != -1UL) {
-		zpci_aibv[zdev->aisb] = NULL;
-		airq_iv_free_bit(zpci_aisb_iv, zdev->aisb);
-		zdev->aisb = -1UL;
-	}
-	if (zdev->aibv) {
-		airq_iv_release(zdev->aibv);
-		zdev->aibv = NULL;
-	}
-}
-
 #ifdef CONFIG_PCI_IOV
 static struct resource iov_res = {
 	.name	= "PCI IOV res",
@@ -495,6 +412,7 @@ static struct resource iov_res = {
 
 static void zpci_map_resources(struct pci_dev *pdev)
 {
+	struct zpci_dev *zdev = to_zpci(pdev);
 	resource_size_t len;
 	int i;
 
@@ -502,8 +420,13 @@ static void zpci_map_resources(struct pci_dev *pdev)
 		len = pci_resource_len(pdev, i);
 		if (!len)
 			continue;
-		pdev->resource[i].start =
-			(resource_size_t __force) pci_iomap(pdev, i, 0);
+
+		if (static_branch_likely(&have_mio))
+			pdev->resource[i].start =
+				(resource_size_t __force) zdev->bars[i].mio_wb;
+		else
+			pdev->resource[i].start =
+				(resource_size_t __force) pci_iomap(pdev, i, 0);
 		pdev->resource[i].end = pdev->resource[i].start + len - 1;
 	}
 
@@ -524,6 +447,9 @@ static void zpci_unmap_resources(struct pci_dev *pdev)
 	resource_size_t len;
 	int i;
 
+	if (static_branch_likely(&have_mio))
+		return;
+
 	for (i = 0; i < PCI_BAR_COUNT; i++) {
 		len = pci_resource_len(pdev, i);
 		if (!len)
@@ -533,41 +459,6 @@ static void zpci_unmap_resources(struct pci_dev *pdev)
 	}
 }
 
-static struct airq_struct zpci_airq = {
-	.handler = zpci_irq_handler,
-	.isc = PCI_ISC,
-};
-
-static int __init zpci_irq_init(void)
-{
-	int rc;
-
-	rc = register_adapter_interrupt(&zpci_airq);
-	if (rc)
-		goto out;
-	/* Set summary to 1 to be called every time for the ISC. */
-	*zpci_airq.lsi_ptr = 1;
-
-	rc = -ENOMEM;
-	zpci_aisb_iv = airq_iv_create(ZPCI_NR_DEVICES, AIRQ_IV_ALLOC);
-	if (!zpci_aisb_iv)
-		goto out_airq;
-
-	zpci_set_irq_ctrl(SIC_IRQ_MODE_SINGLE, NULL, PCI_ISC);
-	return 0;
-
-out_airq:
-	unregister_adapter_interrupt(&zpci_airq);
-out:
-	return rc;
-}
-
-static void zpci_irq_exit(void)
-{
-	airq_iv_release(zpci_aisb_iv);
-	unregister_adapter_interrupt(&zpci_airq);
-}
-
 static int zpci_alloc_iomap(struct zpci_dev *zdev)
 {
 	unsigned long entry;
@@ -958,7 +849,9 @@ static void zpci_mem_exit(void)
 	kmem_cache_destroy(zdev_fmb_cache);
 }
 
-static unsigned int s390_pci_probe = 1;
+static unsigned int s390_pci_probe __initdata = 1;
+static unsigned int s390_pci_no_mio __initdata;
+unsigned int s390_pci_force_floating __initdata;
 static unsigned int s390_pci_initialized;
 
 char * __init pcibios_setup(char *str)
@@ -967,6 +860,14 @@ char * __init pcibios_setup(char *str)
 		s390_pci_probe = 0;
 		return NULL;
 	}
+	if (!strcmp(str, "nomio")) {
+		s390_pci_no_mio = 1;
+		return NULL;
+	}
+	if (!strcmp(str, "force_floating")) {
+		s390_pci_force_floating = 1;
+		return NULL;
+	}
 	return str;
 }
 
@@ -985,6 +886,9 @@ static int __init pci_base_init(void)
 	if (!test_facility(69) || !test_facility(71))
 		return 0;
 
+	if (test_facility(153) && !s390_pci_no_mio)
+		static_branch_enable(&have_mio);
+
 	rc = zpci_debug_init();
 	if (rc)
 		goto out;
diff --git a/arch/s390/pci/pci_clp.c b/arch/s390/pci/pci_clp.c
index eeb7450db18c..3a36b07a5571 100644
--- a/arch/s390/pci/pci_clp.c
+++ b/arch/s390/pci/pci_clp.c
@@ -163,7 +163,14 @@ static int clp_store_query_pci_fn(struct zpci_dev *zdev,
 		memcpy(zdev->util_str, response->util_str,
 		       sizeof(zdev->util_str));
 	}
+	zdev->mio_capable = response->mio_addr_avail;
+	for (i = 0; i < PCI_BAR_COUNT; i++) {
+		if (!(response->mio_valid & (1 << (PCI_BAR_COUNT - i - 1))))
+			continue;
 
+		zdev->bars[i].mio_wb = (void __iomem *) response->addr[i].wb;
+		zdev->bars[i].mio_wt = (void __iomem *) response->addr[i].wt;
+	}
 	return 0;
 }
 
@@ -279,11 +286,18 @@ int clp_enable_fh(struct zpci_dev *zdev, u8 nr_dma_as)
 	int rc;
 
 	rc = clp_set_pci_fn(&fh, nr_dma_as, CLP_SET_ENABLE_PCI_FN);
-	if (!rc)
-		/* Success -> store enabled handle in zdev */
-		zdev->fh = fh;
+	zpci_dbg(3, "ena fid:%x, fh:%x, rc:%d\n", zdev->fid, fh, rc);
+	if (rc)
+		goto out;
 
-	zpci_dbg(3, "ena fid:%x, fh:%x, rc:%d\n", zdev->fid, zdev->fh, rc);
+	zdev->fh = fh;
+	if (zdev->mio_capable) {
+		rc = clp_set_pci_fn(&fh, nr_dma_as, CLP_SET_ENABLE_MIO);
+		zpci_dbg(3, "ena mio fid:%x, fh:%x, rc:%d\n", zdev->fid, fh, rc);
+		if (rc)
+			clp_disable_fh(zdev);
+	}
+out:
 	return rc;
 }
 
@@ -296,11 +310,10 @@ int clp_disable_fh(struct zpci_dev *zdev)
 		return 0;
 
 	rc = clp_set_pci_fn(&fh, 0, CLP_SET_DISABLE_PCI_FN);
+	zpci_dbg(3, "dis fid:%x, fh:%x, rc:%d\n", zdev->fid, fh, rc);
 	if (!rc)
-		/* Success -> store disabled handle in zdev */
 		zdev->fh = fh;
 
-	zpci_dbg(3, "dis fid:%x, fh:%x, rc:%d\n", zdev->fid, zdev->fh, rc);
 	return rc;
 }
 
diff --git a/arch/s390/pci/pci_insn.c b/arch/s390/pci/pci_insn.c
index f069929e8211..02f9505c99a8 100644
--- a/arch/s390/pci/pci_insn.c
+++ b/arch/s390/pci/pci_insn.c
@@ -8,9 +8,11 @@
 #include <linux/export.h>
 #include <linux/errno.h>
 #include <linux/delay.h>
+#include <linux/jump_label.h>
 #include <asm/facility.h>
 #include <asm/pci_insn.h>
 #include <asm/pci_debug.h>
+#include <asm/pci_io.h>
 #include <asm/processor.h>
 
 #define ZPCI_INSN_BUSY_DELAY	1	/* 1 microsecond */
@@ -96,13 +98,15 @@ int zpci_refresh_trans(u64 fn, u64 addr, u64 range)
 }
 
 /* Set Interruption Controls */
-int zpci_set_irq_ctrl(u16 ctl, char *unused, u8 isc)
+int __zpci_set_irq_ctrl(u16 ctl, u8 isc, union zpci_sic_iib *iib)
 {
 	if (!test_facility(72))
 		return -EIO;
-	asm volatile (
-		"	.insn	rsy,0xeb00000000d1,%[ctl],%[isc],%[u]\n"
-		: : [ctl] "d" (ctl), [isc] "d" (isc << 27), [u] "Q" (*unused));
+
+	asm volatile(
+		".insn	rsy,0xeb00000000d1,%[ctl],%[isc],%[iib]\n"
+		: : [ctl] "d" (ctl), [isc] "d" (isc << 27), [iib] "Q" (*iib));
+
 	return 0;
 }
 
@@ -140,7 +144,7 @@ static inline int __pcilg(u64 *data, u64 req, u64 offset, u8 *status)
 	return cc;
 }
 
-int zpci_load(u64 *data, u64 req, u64 offset)
+int __zpci_load(u64 *data, u64 req, u64 offset)
 {
 	u8 status;
 	int cc;
@@ -156,6 +160,52 @@ int zpci_load(u64 *data, u64 req, u64 offset)
 
 	return (cc > 0) ? -EIO : cc;
 }
+EXPORT_SYMBOL_GPL(__zpci_load);
+
+static inline int zpci_load_fh(u64 *data, const volatile void __iomem *addr,
+			       unsigned long len)
+{
+	struct zpci_iomap_entry *entry = &zpci_iomap_start[ZPCI_IDX(addr)];
+	u64 req = ZPCI_CREATE_REQ(entry->fh, entry->bar, len);
+
+	return __zpci_load(data, req, ZPCI_OFFSET(addr));
+}
+
+static inline int __pcilg_mio(u64 *data, u64 ioaddr, u64 len, u8 *status)
+{
+	register u64 addr asm("2") = ioaddr;
+	register u64 r3 asm("3") = len;
+	int cc = -ENXIO;
+	u64 __data;
+
+	asm volatile (
+		"       .insn   rre,0xb9d60000,%[data],%[ioaddr]\n"
+		"0:     ipm     %[cc]\n"
+		"       srl     %[cc],28\n"
+		"1:\n"
+		EX_TABLE(0b, 1b)
+		: [cc] "+d" (cc), [data] "=d" (__data), "+d" (r3)
+		: [ioaddr] "d" (addr)
+		: "cc");
+	*status = r3 >> 24 & 0xff;
+	*data = __data;
+	return cc;
+}
+
+int zpci_load(u64 *data, const volatile void __iomem *addr, unsigned long len)
+{
+	u8 status;
+	int cc;
+
+	if (!static_branch_unlikely(&have_mio))
+		return zpci_load_fh(data, addr, len);
+
+	cc = __pcilg_mio(data, (__force u64) addr, len, &status);
+	if (cc)
+		zpci_err_insn(cc, status, 0, (__force u64) addr);
+
+	return (cc > 0) ? -EIO : cc;
+}
 EXPORT_SYMBOL_GPL(zpci_load);
 
 /* PCI Store */
@@ -178,7 +228,7 @@ static inline int __pcistg(u64 data, u64 req, u64 offset, u8 *status)
 	return cc;
 }
 
-int zpci_store(u64 data, u64 req, u64 offset)
+int __zpci_store(u64 data, u64 req, u64 offset)
 {
 	u8 status;
 	int cc;
@@ -194,6 +244,50 @@ int zpci_store(u64 data, u64 req, u64 offset)
 
 	return (cc > 0) ? -EIO : cc;
 }
+EXPORT_SYMBOL_GPL(__zpci_store);
+
+static inline int zpci_store_fh(const volatile void __iomem *addr, u64 data,
+				unsigned long len)
+{
+	struct zpci_iomap_entry *entry = &zpci_iomap_start[ZPCI_IDX(addr)];
+	u64 req = ZPCI_CREATE_REQ(entry->fh, entry->bar, len);
+
+	return __zpci_store(data, req, ZPCI_OFFSET(addr));
+}
+
+static inline int __pcistg_mio(u64 data, u64 ioaddr, u64 len, u8 *status)
+{
+	register u64 addr asm("2") = ioaddr;
+	register u64 r3 asm("3") = len;
+	int cc = -ENXIO;
+
+	asm volatile (
+		"       .insn   rre,0xb9d40000,%[data],%[ioaddr]\n"
+		"0:     ipm     %[cc]\n"
+		"       srl     %[cc],28\n"
+		"1:\n"
+		EX_TABLE(0b, 1b)
+		: [cc] "+d" (cc), "+d" (r3)
+		: [data] "d" (data), [ioaddr] "d" (addr)
+		: "cc");
+	*status = r3 >> 24 & 0xff;
+	return cc;
+}
+
+int zpci_store(const volatile void __iomem *addr, u64 data, unsigned long len)
+{
+	u8 status;
+	int cc;
+
+	if (!static_branch_unlikely(&have_mio))
+		return zpci_store_fh(addr, data, len);
+
+	cc = __pcistg_mio(data, (__force u64) addr, len, &status);
+	if (cc)
+		zpci_err_insn(cc, status, 0, (__force u64) addr);
+
+	return (cc > 0) ? -EIO : cc;
+}
 EXPORT_SYMBOL_GPL(zpci_store);
 
 /* PCI Store Block */
@@ -214,7 +308,7 @@ static inline int __pcistb(const u64 *data, u64 req, u64 offset, u8 *status)
 	return cc;
 }
 
-int zpci_store_block(const u64 *data, u64 req, u64 offset)
+int __zpci_store_block(const u64 *data, u64 req, u64 offset)
 {
 	u8 status;
 	int cc;
@@ -230,4 +324,63 @@ int zpci_store_block(const u64 *data, u64 req, u64 offset)
 
 	return (cc > 0) ? -EIO : cc;
 }
-EXPORT_SYMBOL_GPL(zpci_store_block);
+EXPORT_SYMBOL_GPL(__zpci_store_block);
+
+static inline int zpci_write_block_fh(volatile void __iomem *dst,
+				      const void *src, unsigned long len)
+{
+	struct zpci_iomap_entry *entry = &zpci_iomap_start[ZPCI_IDX(dst)];
+	u64 req = ZPCI_CREATE_REQ(entry->fh, entry->bar, len);
+	u64 offset = ZPCI_OFFSET(dst);
+
+	return __zpci_store_block(src, req, offset);
+}
+
+static inline int __pcistb_mio(const u64 *data, u64 ioaddr, u64 len, u8 *status)
+{
+	int cc = -ENXIO;
+
+	asm volatile (
+		"       .insn   rsy,0xeb00000000d4,%[len],%[ioaddr],%[data]\n"
+		"0:     ipm     %[cc]\n"
+		"       srl     %[cc],28\n"
+		"1:\n"
+		EX_TABLE(0b, 1b)
+		: [cc] "+d" (cc), [len] "+d" (len)
+		: [ioaddr] "d" (ioaddr), [data] "Q" (*data)
+		: "cc");
+	*status = len >> 24 & 0xff;
+	return cc;
+}
+
+int zpci_write_block(volatile void __iomem *dst,
+		     const void *src, unsigned long len)
+{
+	u8 status;
+	int cc;
+
+	if (!static_branch_unlikely(&have_mio))
+		return zpci_write_block_fh(dst, src, len);
+
+	cc = __pcistb_mio(src, (__force u64) dst, len, &status);
+	if (cc)
+		zpci_err_insn(cc, status, 0, (__force u64) dst);
+
+	return (cc > 0) ? -EIO : cc;
+}
+EXPORT_SYMBOL_GPL(zpci_write_block);
+
+static inline void __pciwb_mio(void)
+{
+	unsigned long unused = 0;
+
+	asm volatile (".insn    rre,0xb9d50000,%[op],%[op]\n"
+		      : [op] "+d" (unused));
+}
+
+void zpci_barrier(void)
+{
+	if (static_branch_likely(&have_mio))
+		__pciwb_mio();
+}
+EXPORT_SYMBOL_GPL(zpci_barrier);
diff --git a/arch/s390/pci/pci_irq.c b/arch/s390/pci/pci_irq.c
new file mode 100644
index 000000000000..d80616ae8dd8
--- /dev/null
+++ b/arch/s390/pci/pci_irq.c
@@ -0,0 +1,486 @@
+// SPDX-License-Identifier: GPL-2.0
+#define KMSG_COMPONENT "zpci"
+#define pr_fmt(fmt) KMSG_COMPONENT ": " fmt
+
+#include <linux/kernel.h>
+#include <linux/irq.h>
+#include <linux/kernel_stat.h>
+#include <linux/pci.h>
+#include <linux/msi.h>
+#include <linux/smp.h>
+
+#include <asm/isc.h>
+#include <asm/airq.h>
+
+static enum {FLOATING, DIRECTED} irq_delivery;
+
+#define	SIC_IRQ_MODE_ALL		0
+#define	SIC_IRQ_MODE_SINGLE		1
+#define	SIC_IRQ_MODE_DIRECT		4
+#define	SIC_IRQ_MODE_D_ALL		16
+#define	SIC_IRQ_MODE_D_SINGLE		17
+#define	SIC_IRQ_MODE_SET_CPU		18
+
+/*
+ * summary bit vector
+ * FLOATING - summary bit per function
+ * DIRECTED - summary bit per cpu (only used in fallback path)
+ */
+static struct airq_iv *zpci_sbv;
+
+/*
+ * interrupt bit vectors
+ * FLOATING - interrupt bit vector per function
+ * DIRECTED - interrupt bit vector per cpu
+ */
+static struct airq_iv **zpci_ibv;
+
+/* Modify PCI: Register adapter interruptions */
+static int zpci_set_airq(struct zpci_dev *zdev)
+{
+	u64 req = ZPCI_CREATE_REQ(zdev->fh, 0, ZPCI_MOD_FC_REG_INT);
+	struct zpci_fib fib = {0};
+	u8 status;
+
+	fib.fmt0.isc = PCI_ISC;
+	fib.fmt0.sum = 1;	/* enable summary notifications */
+	fib.fmt0.noi = airq_iv_end(zdev->aibv);
+	fib.fmt0.aibv = (unsigned long) zdev->aibv->vector;
+	fib.fmt0.aibvo = 0;	/* each zdev has its own interrupt vector */
+	fib.fmt0.aisb = (unsigned long) zpci_sbv->vector + (zdev->aisb/64)*8;
+	fib.fmt0.aisbo = zdev->aisb & 63;
+
+	return zpci_mod_fc(req, &fib, &status) ? -EIO : 0;
+}
+
+/* Modify PCI: Unregister adapter interruptions */
+static int zpci_clear_airq(struct zpci_dev *zdev)
+{
+	u64 req = ZPCI_CREATE_REQ(zdev->fh, 0, ZPCI_MOD_FC_DEREG_INT);
+	struct zpci_fib fib = {0};
+	u8 cc, status;
+
+	cc = zpci_mod_fc(req, &fib, &status);
+	if (cc == 3 || (cc == 1 && status == 24))
+		/* Function already gone or IRQs already deregistered. */
+		cc = 0;
+
+	return cc ? -EIO : 0;
+}
+
+/* Modify PCI: Register CPU directed interruptions */
+static int zpci_set_directed_irq(struct zpci_dev *zdev)
+{
+	u64 req = ZPCI_CREATE_REQ(zdev->fh, 0, ZPCI_MOD_FC_REG_INT_D);
+	struct zpci_fib fib = {0};
+	u8 status;
+
+	fib.fmt = 1;
+	fib.fmt1.noi = zdev->msi_nr_irqs;
+	fib.fmt1.dibvo = zdev->msi_first_bit;
+
+	return zpci_mod_fc(req, &fib, &status) ? -EIO : 0;
+}
+
+/* Modify PCI: Unregister CPU directed interruptions */
+static int zpci_clear_directed_irq(struct zpci_dev *zdev)
+{
+	u64 req = ZPCI_CREATE_REQ(zdev->fh, 0, ZPCI_MOD_FC_DEREG_INT_D);
+	struct zpci_fib fib = {0};
+	u8 cc, status;
+
+	fib.fmt = 1;
+	cc = zpci_mod_fc(req, &fib, &status);
+	if (cc == 3 || (cc == 1 && status == 24))
+		/* Function already gone or IRQs already deregistered. */
+		cc = 0;
+
+	return cc ? -EIO : 0;
+}
+
+static int zpci_set_irq_affinity(struct irq_data *data, const struct cpumask *dest,
+				 bool force)
+{
+	struct msi_desc *entry = irq_get_msi_desc(data->irq);
+	struct msi_msg msg = entry->msg;
+
+	msg.address_lo &= 0xff0000ff;
+	msg.address_lo |= (cpumask_first(dest) << 8);
+	pci_write_msi_msg(data->irq, &msg);
+
+	return IRQ_SET_MASK_OK;
+}
+
+static struct irq_chip zpci_irq_chip = {
+	.name = "PCI-MSI",
+	.irq_unmask = pci_msi_unmask_irq,
+	.irq_mask = pci_msi_mask_irq,
+	.irq_set_affinity = zpci_set_irq_affinity,
+};
+
+static void zpci_handle_cpu_local_irq(bool rescan)
+{
+	struct airq_iv *dibv = zpci_ibv[smp_processor_id()];
+	unsigned long bit;
+	int irqs_on = 0;
+
+	for (bit = 0;;) {
+		/* Scan the directed IRQ bit vector */
+		bit = airq_iv_scan(dibv, bit, airq_iv_end(dibv));
+		if (bit == -1UL) {
+			if (!rescan || irqs_on++)
+				/* End of second scan with interrupts on. */
+				break;
+			/* First scan complete, reenable interrupts. */
+			if (zpci_set_irq_ctrl(SIC_IRQ_MODE_D_SINGLE, PCI_ISC))
+				break;
+			bit = 0;
+			continue;
+		}
+		inc_irq_stat(IRQIO_MSI);
+		generic_handle_irq(airq_iv_get_data(dibv, bit));
+	}
+}
+
+struct cpu_irq_data {
+	call_single_data_t csd;
+	atomic_t scheduled;
+};
+static DEFINE_PER_CPU_SHARED_ALIGNED(struct cpu_irq_data, irq_data);
+
+static void zpci_handle_remote_irq(void *data)
+{
+	atomic_t *scheduled = data;
+
+	do {
+		zpci_handle_cpu_local_irq(false);
+	} while (atomic_dec_return(scheduled));
+}
+
+static void zpci_handle_fallback_irq(void)
+{
+	struct cpu_irq_data *cpu_data;
+	unsigned long cpu;
+	int irqs_on = 0;
+
+	for (cpu = 0;;) {
+		cpu = airq_iv_scan(zpci_sbv, cpu, airq_iv_end(zpci_sbv));
+		if (cpu == -1UL) {
+			if (irqs_on++)
+				/* End of second scan with interrupts on. */
+				break;
+			/* First scan complete, reenable interrupts. */
+			if (zpci_set_irq_ctrl(SIC_IRQ_MODE_SINGLE, PCI_ISC))
+				break;
+			cpu = 0;
+			continue;
+		}
+		cpu_data = &per_cpu(irq_data, cpu);
+		if (atomic_inc_return(&cpu_data->scheduled) > 1)
+			continue;
+
+		cpu_data->csd.func = zpci_handle_remote_irq;
+		cpu_data->csd.info = &cpu_data->scheduled;
+		cpu_data->csd.flags = 0;
+		smp_call_function_single_async(cpu, &cpu_data->csd);
+	}
+}
+
+static void zpci_directed_irq_handler(struct airq_struct *airq, bool floating)
+{
+	if (floating) {
+		inc_irq_stat(IRQIO_PCF);
+		zpci_handle_fallback_irq();
+	} else {
+		inc_irq_stat(IRQIO_PCD);
+		zpci_handle_cpu_local_irq(true);
+	}
+}
+
+static void zpci_floating_irq_handler(struct airq_struct *airq, bool floating)
+{
+	unsigned long si, ai;
+	struct airq_iv *aibv;
+	int irqs_on = 0;
+
+	inc_irq_stat(IRQIO_PCF);
+	for (si = 0;;) {
+		/* Scan adapter summary indicator bit vector */
+		si = airq_iv_scan(zpci_sbv, si, airq_iv_end(zpci_sbv));
+		if (si == -1UL) {
+			if (irqs_on++)
+				/* End of second scan with interrupts on. */
+				break;
+			/* First scan complete, reenable interrupts. */
+			if (zpci_set_irq_ctrl(SIC_IRQ_MODE_SINGLE, PCI_ISC))
+				break;
+			si = 0;
+			continue;
+		}
+
+		/* Scan the adapter interrupt vector for this device. */
+		aibv = zpci_ibv[si];
+		for (ai = 0;;) {
+			ai = airq_iv_scan(aibv, ai, airq_iv_end(aibv));
+			if (ai == -1UL)
+				break;
+			inc_irq_stat(IRQIO_MSI);
+			airq_iv_lock(aibv, ai);
+			generic_handle_irq(airq_iv_get_data(aibv, ai));
+			airq_iv_unlock(aibv, ai);
+		}
+	}
+}
+
+int arch_setup_msi_irqs(struct pci_dev *pdev, int nvec, int type)
+{
+	struct zpci_dev *zdev = to_zpci(pdev);
+	unsigned int hwirq, msi_vecs, cpu;
+	unsigned long bit;
+	struct msi_desc *msi;
+	struct msi_msg msg;
+	int rc, irq;
+
+	zdev->aisb = -1UL;
+	zdev->msi_first_bit = -1U;
+	if (type == PCI_CAP_ID_MSI && nvec > 1)
+		return 1;
+	msi_vecs = min_t(unsigned int, nvec, zdev->max_msi);
+
+	if (irq_delivery == DIRECTED) {
+		/* Allocate cpu vector bits */
+		bit = airq_iv_alloc(zpci_ibv[0], msi_vecs);
+		if (bit == -1UL)
+			return -EIO;
+	} else {
+		/* Allocate adapter summary indicator bit */
+		bit = airq_iv_alloc_bit(zpci_sbv);
+		if (bit == -1UL)
+			return -EIO;
+		zdev->aisb = bit;
+
+		/* Create adapter interrupt vector */
+		zdev->aibv = airq_iv_create(msi_vecs, AIRQ_IV_DATA | AIRQ_IV_BITLOCK);
+		if (!zdev->aibv)
+			return -ENOMEM;
+
+		/* Wire up shortcut pointer */
+		zpci_ibv[bit] = zdev->aibv;
+		/* Each function has its own interrupt vector */
+		bit = 0;
+	}
+
+	/* Request MSI interrupts */
+	hwirq = bit;
+	for_each_pci_msi_entry(msi, pdev) {
+		rc = -EIO;
+		if (hwirq - bit >= msi_vecs)
+			break;
+		irq = __irq_alloc_descs(-1, 0, 1, 0, THIS_MODULE, msi->affinity);
+		if (irq < 0)
+			return -ENOMEM;
+		rc = irq_set_msi_desc(irq, msi);
+		if (rc)
+			return rc;
+		irq_set_chip_and_handler(irq, &zpci_irq_chip,
+					 handle_percpu_irq);
+		msg.data = hwirq;
+		if (irq_delivery == DIRECTED) {
+			msg.address_lo = zdev->msi_addr & 0xff0000ff;
+			msg.address_lo |= msi->affinity ?
+				(cpumask_first(&msi->affinity->mask) << 8) : 0;
+			for_each_possible_cpu(cpu) {
+				airq_iv_set_data(zpci_ibv[cpu], hwirq, irq);
+			}
+		} else {
+			msg.address_lo = zdev->msi_addr & 0xffffffff;
+			airq_iv_set_data(zdev->aibv, hwirq, irq);
+		}
+		msg.address_hi = zdev->msi_addr >> 32;
+		pci_write_msi_msg(irq, &msg);
+		hwirq++;
+	}
+
+	zdev->msi_first_bit = bit;
+	zdev->msi_nr_irqs = msi_vecs;
+
+	if (irq_delivery == DIRECTED)
+		rc = zpci_set_directed_irq(zdev);
+	else
+		rc = zpci_set_airq(zdev);
+	if (rc)
+		return rc;
+
+	return (msi_vecs == nvec) ? 0 : msi_vecs;
+}
+
+void arch_teardown_msi_irqs(struct pci_dev *pdev)
+{
+	struct zpci_dev *zdev = to_zpci(pdev);
+	struct msi_desc *msi;
+	int rc;
+
+	/* Disable interrupts */
+	if (irq_delivery == DIRECTED)
+		rc = zpci_clear_directed_irq(zdev);
+	else
+		rc = zpci_clear_airq(zdev);
+	if (rc)
+		return;
+
+	/* Release MSI interrupts */
+	for_each_pci_msi_entry(msi, pdev) {
+		if (!msi->irq)
+			continue;
+		if (msi->msi_attrib.is_msix)
+			__pci_msix_desc_mask_irq(msi, 1);
+		else
+			__pci_msi_desc_mask_irq(msi, 1, 1);
+		irq_set_msi_desc(msi->irq, NULL);
+		irq_free_desc(msi->irq);
+		msi->msg.address_lo = 0;
+		msi->msg.address_hi = 0;
+		msi->msg.data = 0;
+		msi->irq = 0;
+	}
+
+	if (zdev->aisb != -1UL) {
+		zpci_ibv[zdev->aisb] = NULL;
+		airq_iv_free_bit(zpci_sbv, zdev->aisb);
+		zdev->aisb = -1UL;
+	}
+	if (zdev->aibv) {
+		airq_iv_release(zdev->aibv);
+		zdev->aibv = NULL;
+	}
+
+	if ((irq_delivery == DIRECTED) && zdev->msi_first_bit != -1U)
+		airq_iv_free(zpci_ibv[0], zdev->msi_first_bit, zdev->msi_nr_irqs);
+}
+
+static struct airq_struct zpci_airq = {
+	.handler = zpci_floating_irq_handler,
+	.isc = PCI_ISC,
+};
+
+static void __init cpu_enable_directed_irq(void *unused)
+{
+	union zpci_sic_iib iib = {{0}};
+
+	iib.cdiib.dibv_addr = (u64) zpci_ibv[smp_processor_id()]->vector;
+
+	__zpci_set_irq_ctrl(SIC_IRQ_MODE_SET_CPU, 0, &iib);
+	zpci_set_irq_ctrl(SIC_IRQ_MODE_D_SINGLE, PCI_ISC);
+}
+
+static int __init zpci_directed_irq_init(void)
+{
+	union zpci_sic_iib iib = {{0}};
+	unsigned int cpu;
+
+	zpci_sbv = airq_iv_create(num_possible_cpus(), 0);
+	if (!zpci_sbv)
+		return -ENOMEM;
+
+	iib.diib.isc = PCI_ISC;
+	iib.diib.nr_cpus = num_possible_cpus();
+	iib.diib.disb_addr = (u64) zpci_sbv->vector;
+	__zpci_set_irq_ctrl(SIC_IRQ_MODE_DIRECT, 0, &iib);
+
+	zpci_ibv = kcalloc(num_possible_cpus(), sizeof(*zpci_ibv),
+			   GFP_KERNEL);
+	if (!zpci_ibv)
+		return -ENOMEM;
+
+	for_each_possible_cpu(cpu) {
+		/*
+		 * Per CPU IRQ vectors look the same but bit-allocation
+		 * is only done on the first vector.
+		 */
+		zpci_ibv[cpu] = airq_iv_create(cache_line_size() * BITS_PER_BYTE,
+					       AIRQ_IV_DATA |
+					       AIRQ_IV_CACHELINE |
+					       (!cpu ? AIRQ_IV_ALLOC : 0));
+		if (!zpci_ibv[cpu])
+			return -ENOMEM;
+	}
+	on_each_cpu(cpu_enable_directed_irq, NULL, 1);
+
+	zpci_irq_chip.irq_set_affinity = zpci_set_irq_affinity;
+
+	return 0;
+}
+
+static int __init zpci_floating_irq_init(void)
+{
+	zpci_ibv = kcalloc(ZPCI_NR_DEVICES, sizeof(*zpci_ibv), GFP_KERNEL);
+	if (!zpci_ibv)
+		return -ENOMEM;
+
+	zpci_sbv = airq_iv_create(ZPCI_NR_DEVICES, AIRQ_IV_ALLOC);
+	if (!zpci_sbv)
+		goto out_free;
+
+	return 0;
+
+out_free:
+	kfree(zpci_ibv);
+	return -ENOMEM;
+}
+
+int __init zpci_irq_init(void)
+{
+	int rc;
+
+	irq_delivery = sclp.has_dirq ? DIRECTED : FLOATING;
+	if (s390_pci_force_floating)
+		irq_delivery = FLOATING;
+
+	if (irq_delivery == DIRECTED)
+		zpci_airq.handler = zpci_directed_irq_handler;
+
+	rc = register_adapter_interrupt(&zpci_airq);
+	if (rc)
+		goto out;
+	/* Set summary to 1 to be called every time for the ISC. */
+	*zpci_airq.lsi_ptr = 1;
+
+	switch (irq_delivery) {
+	case FLOATING:
+		rc = zpci_floating_irq_init();
+		break;
+	case DIRECTED:
+		rc = zpci_directed_irq_init();
+		break;
+	}
+
+	if (rc)
+		goto out_airq;
+
+	/*
+	 * Enable floating IRQs (with suppression after one IRQ). When using
+	 * directed IRQs this enables the fallback path.
+	 */
+	zpci_set_irq_ctrl(SIC_IRQ_MODE_SINGLE, PCI_ISC);
+
+	return 0;
+out_airq:
+	unregister_adapter_interrupt(&zpci_airq);
+out:
+	return rc;
+}
+
+void __init zpci_irq_exit(void)
+{
+	unsigned int cpu;
+
+	if (irq_delivery == DIRECTED) {
+		for_each_possible_cpu(cpu) {
+			airq_iv_release(zpci_ibv[cpu]);
+		}
+	}
+	kfree(zpci_ibv);
+	if (zpci_sbv)
+		airq_iv_release(zpci_sbv);
+	unregister_adapter_interrupt(&zpci_airq);
+}
diff --git a/arch/s390/purgatory/Makefile b/arch/s390/purgatory/Makefile
index ce6a3f75065b..dc1ae4ff79d7 100644
--- a/arch/s390/purgatory/Makefile
+++ b/arch/s390/purgatory/Makefile
@@ -4,7 +4,7 @@ OBJECT_FILES_NON_STANDARD := y
 
 purgatory-y := head.o purgatory.o string.o sha256.o mem.o
 
-targets += $(purgatory-y) purgatory.ro kexec-purgatory.c
+targets += $(purgatory-y) purgatory.lds purgatory purgatory.ro
 PURGATORY_OBJS = $(addprefix $(obj)/,$(purgatory-y))
 
 $(obj)/sha256.o: $(srctree)/lib/sha256.c FORCE
@@ -16,22 +16,26 @@ $(obj)/mem.o: $(srctree)/arch/s390/lib/mem.S FORCE
 $(obj)/string.o: $(srctree)/arch/s390/lib/string.c FORCE
 	$(call if_changed_rule,cc_o_c)
 
-LDFLAGS_purgatory.ro := -e purgatory_start -r --no-undefined -nostdlib
-LDFLAGS_purgatory.ro += -z nodefaultlib
 KBUILD_CFLAGS := -fno-strict-aliasing -Wall -Wstrict-prototypes
 KBUILD_CFLAGS += -Wno-pointer-sign -Wno-sign-compare
 KBUILD_CFLAGS += -fno-zero-initialized-in-bss -fno-builtin -ffreestanding
 KBUILD_CFLAGS += -c -MD -Os -m64 -msoft-float -fno-common
+KBUILD_CFLAGS += $(CLANG_FLAGS)
 KBUILD_CFLAGS += $(call cc-option,-fno-PIE)
 KBUILD_AFLAGS := $(filter-out -DCC_USING_EXPOLINE,$(KBUILD_AFLAGS))
 
-$(obj)/purgatory.ro: $(PURGATORY_OBJS) FORCE
+LDFLAGS_purgatory := -r --no-undefined -nostdlib -z nodefaultlib -T
+$(obj)/purgatory: $(obj)/purgatory.lds $(PURGATORY_OBJS) FORCE
 		$(call if_changed,ld)
 
-quiet_cmd_bin2c = BIN2C   $@
-      cmd_bin2c = $(objtree)/scripts/bin2c kexec_purgatory < $< > $@
+OBJCOPYFLAGS_purgatory.ro := -O elf64-s390
+OBJCOPYFLAGS_purgatory.ro += --remove-section='*debug*'
+OBJCOPYFLAGS_purgatory.ro += --remove-section='.comment'
+OBJCOPYFLAGS_purgatory.ro += --remove-section='.note.*'
+$(obj)/purgatory.ro: $(obj)/purgatory FORCE
+		$(call if_changed,objcopy)
 
-$(obj)/kexec-purgatory.c: $(obj)/purgatory.ro FORCE
-	$(call if_changed,bin2c)
+$(obj)/kexec-purgatory.o: $(obj)/kexec-purgatory.S $(obj)/purgatory.ro FORCE
+	$(call if_changed_rule,as_o_S)
 
 obj-$(CONFIG_ARCH_HAS_KEXEC_PURGATORY) += kexec-purgatory.o
diff --git a/arch/s390/purgatory/kexec-purgatory.S b/arch/s390/purgatory/kexec-purgatory.S
new file mode 100644
index 000000000000..8293753100ae
--- /dev/null
+++ b/arch/s390/purgatory/kexec-purgatory.S
@@ -0,0 +1,14 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+
+	.section .rodata, "a"
+
+	.align	8
+kexec_purgatory:
+	.globl	kexec_purgatory
+	.incbin	"arch/s390/purgatory/purgatory.ro"
+.Lkexec_purgatroy_end:
+
+	.align	8
+kexec_purgatory_size:
+	.globl	kexec_purgatory_size
+	.quad	.Lkexec_purgatroy_end - kexec_purgatory
diff --git a/arch/s390/purgatory/purgatory.lds.S b/arch/s390/purgatory/purgatory.lds.S
new file mode 100644
index 000000000000..482eb4fbcef1
--- /dev/null
+++ b/arch/s390/purgatory/purgatory.lds.S
@@ -0,0 +1,54 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+
+#include <asm-generic/vmlinux.lds.h>
+
+OUTPUT_FORMAT("elf64-s390", "elf64-s390", "elf64-s390")
+OUTPUT_ARCH(s390:64-bit)
+
+ENTRY(purgatory_start)
+
+SECTIONS
+{
+	. = 0;
+	.head.text : {
+		_head = . ;
+		HEAD_TEXT
+		_ehead = . ;
+	}
+	.text :	{
+		_text = .;	/* Text */
+		*(.text)
+		*(.text.*)
+		_etext = . ;
+	}
+	.rodata : {
+		_rodata = . ;
+		*(.rodata)	 /* read-only data */
+		*(.rodata.*)
+		_erodata = . ;
+	}
+	.data :	{
+		_data = . ;
+		*(.data)
+		*(.data.*)
+		_edata = . ;
+	}
+
+	. = ALIGN(256);
+	.bss : {
+		_bss = . ;
+		*(.bss)
+		*(.bss.*)
+		*(COMMON)
+		. = ALIGN(8);	/* For convenience during zeroing */
+		_ebss = .;
+	}
+	_end = .;
+
+	/* Sections to be discarded */
+	/DISCARD/ : {
+		*(.eh_frame)
+		*(*__ksymtab*)
+		*(___kcrctab*)
+	}
+}
diff --git a/arch/s390/scripts/Makefile.chkbss b/arch/s390/scripts/Makefile.chkbss
index cd7e8f4419f5..884a9caff5fb 100644
--- a/arch/s390/scripts/Makefile.chkbss
+++ b/arch/s390/scripts/Makefile.chkbss
@@ -11,7 +11,8 @@ chkbss: $(addprefix $(obj)/, $(chkbss-files))
 
 quiet_cmd_chkbss = CHKBSS  $<
       cmd_chkbss = \
-	if ! $(OBJDUMP) -j .bss -w -h $< | awk 'END { if ($$3) exit 1 }'; then \
+	if $(OBJDUMP) -h $< | grep -q "\.bss" && \
+	   ! $(OBJDUMP) -j .bss -w -h $< | awk 'END { if ($$3) exit 1 }'; then \
 		echo "error: $< .bss section is not empty" >&2; exit 1; \
 	fi; \
 	touch $@;
diff --git a/arch/s390/tools/opcodes.txt b/arch/s390/tools/opcodes.txt
index 1cbed82cd17b..64638b764d1c 100644
--- a/arch/s390/tools/opcodes.txt
+++ b/arch/s390/tools/opcodes.txt
@@ -1,3 +1,5 @@
+0000	illegal	E
+0002	brkpt	E
 0101	pr	E
 0102	upt	E
 0104	ptff	E
@@ -257,6 +259,7 @@ b258	bsg	RRE_RR
 b25a	bsa	RRE_RR
 b25d	clst	RRE_RR
 b25e	srst	RRE_RR
+b25f	chsc	RRE_R0
 b263	cmpsc	RRE_RR
 b274	siga	S_RD
 b276	xsch	S_00
@@ -277,6 +280,9 @@ b29d	lfpc	S_RD
 b2a5	tre	RRE_RR
 b2a6	cu21	RRF_U0RR
 b2a7	cu12	RRF_U0RR
+b2ad	nqap	RRE_RR
+b2ae	dqap	RRE_RR
+b2af	pqap	RRE_RR
 b2b0	stfle	S_RD
 b2b1	stfl	S_RD
 b2b2	lpswe	S_RD
@@ -290,6 +296,7 @@ b2e5	epctr	RRE_RR
 b2e8	ppa	RRF_U0RR
 b2ec	etnd	RRE_R0
 b2ed	ecpga	RRE_RR
+b2f0	iucv	RRE_RR
 b2f8	tend	S_00
 b2fa	niai	IE_UU
 b2fc	tabort	S_RD
@@ -559,12 +566,15 @@ b998	alcr	RRE_RR
 b999	slbr	RRE_RR
 b99a	epair	RRE_R0
 b99b	esair	RRE_R0
+b99c	eqbs	RRF_U0RR
 b99d	esea	RRE_R0
 b99e	pti	RRE_RR
 b99f	ssair	RRE_R0
+b9a0	clp	RRF_U0RR
 b9a1	tpei	RRE_RR
 b9a2	ptf	RRE_R0
 b9aa	lptea	RRF_RURR2
+b9ab	essa	RRF_U0RR
 b9ac	irbm	RRE_RR
 b9ae	rrbm	RRE_RR
 b9af	pfmf	RRE_RR
@@ -1039,6 +1049,7 @@ eb7a	agsi	SIY_IRD
 eb7e	algsi	SIY_IRD
 eb80	icmh	RSY_RURD
 eb81	icmy	RSY_RURD
+eb8a	sqbs	RSY_RDRU
 eb8e	mvclu	RSY_RRRD
 eb8f	clclu	RSY_RRRD
 eb90	stmy	RSY_RRRD
diff --git a/arch/sh/Kconfig b/arch/sh/Kconfig
index b1c91ea9a958..0be08d586d40 100644
--- a/arch/sh/Kconfig
+++ b/arch/sh/Kconfig
@@ -90,12 +90,6 @@ config ARCH_DEFCONFIG
 	default "arch/sh/configs/shx3_defconfig" if SUPERH32
 	default "arch/sh/configs/cayman_defconfig" if SUPERH64
 
-config RWSEM_GENERIC_SPINLOCK
-	def_bool y
-
-config RWSEM_XCHGADD_ALGORITHM
-	bool
-
 config GENERIC_BUG
 	def_bool y
 	depends on BUG && SUPERH32
diff --git a/arch/sh/boards/mach-ecovec24/setup.c b/arch/sh/boards/mach-ecovec24/setup.c
index 34e5414c5563..f402aa741bf3 100644
--- a/arch/sh/boards/mach-ecovec24/setup.c
+++ b/arch/sh/boards/mach-ecovec24/setup.c
@@ -806,7 +806,6 @@ static struct spi_board_info spi_bus[] = {
 		.platform_data	= &mmc_spi_info,
 		.max_speed_hz	= 5000000,
 		.mode		= SPI_MODE_0,
-		.controller_data = (void *) GPIO_PTM4,
 	},
 };
 
@@ -838,6 +837,14 @@ static struct platform_device msiof0_device = {
 	.resource	= msiof0_resources,
 };
 
+static struct gpiod_lookup_table msiof_gpio_table = {
+	.dev_id = "spi_sh_msiof.0",
+	.table = {
+		GPIO_LOOKUP("sh7724_pfc", GPIO_PTM4, "cs", GPIO_ACTIVE_HIGH),
+		{ },
+	},
+};
+
 #endif
 
 /* FSI */
@@ -1296,12 +1303,11 @@ static int __init arch_setup(void)
 	gpio_request(GPIO_FN_MSIOF0_TXD, NULL);
 	gpio_request(GPIO_FN_MSIOF0_RXD, NULL);
 	gpio_request(GPIO_FN_MSIOF0_TSCK, NULL);
-	gpio_request(GPIO_PTM4, NULL); /* software CS control of TSYNC pin */
-	gpio_direction_output(GPIO_PTM4, 1); /* active low CS */
 	gpio_request(GPIO_PTB6, NULL); /* 3.3V power control */
 	gpio_direction_output(GPIO_PTB6, 0); /* disable power by default */
 
 	gpiod_add_lookup_table(&mmc_spi_gpio_table);
+	gpiod_add_lookup_table(&msiof_gpio_table);
 	spi_register_board_info(spi_bus, ARRAY_SIZE(spi_bus));
 #endif
 
diff --git a/arch/sh/boards/of-generic.c b/arch/sh/boards/of-generic.c
index 958f46da3a79..d91065e81a4e 100644
--- a/arch/sh/boards/of-generic.c
+++ b/arch/sh/boards/of-generic.c
@@ -164,10 +164,10 @@ static struct sh_machine_vector __initmv sh_of_generic_mv = {
 
 struct sh_clk_ops;
 
-void __init arch_init_clk_ops(struct sh_clk_ops **ops, int idx)
+void __init __weak arch_init_clk_ops(struct sh_clk_ops **ops, int idx)
 {
 }
 
-void __init plat_irq_setup(void)
+void __init __weak plat_irq_setup(void)
 {
 }
diff --git a/arch/sh/include/asm/Kbuild b/arch/sh/include/asm/Kbuild
index a6ef3fee5f85..73fff39a0122 100644
--- a/arch/sh/include/asm/Kbuild
+++ b/arch/sh/include/asm/Kbuild
@@ -9,6 +9,7 @@ generic-y += emergency-restart.h
 generic-y += exec.h
 generic-y += irq_regs.h
 generic-y += irq_work.h
+generic-y += kvm_para.h
 generic-y += local.h
 generic-y += local64.h
 generic-y += mcs_spinlock.h
@@ -16,7 +17,6 @@ generic-y += mm-arch-hooks.h
 generic-y += parport.h
 generic-y += percpu.h
 generic-y += preempt.h
-generic-y += rwsem.h
 generic-y += serial.h
 generic-y += sizes.h
 generic-y += trace_clock.h
diff --git a/arch/sh/include/asm/io.h b/arch/sh/include/asm/io.h
index 4f7f235f15f8..c28e37a344ad 100644
--- a/arch/sh/include/asm/io.h
+++ b/arch/sh/include/asm/io.h
@@ -229,9 +229,6 @@ __BUILD_IOPORT_STRING(q, u64)
 
 #define IO_SPACE_LIMIT 0xffffffff
 
-/* synco on SH-4A, otherwise a nop */
-#define mmiowb()		wmb()
-
 /* We really want to try and get these to memcpy etc */
 void memcpy_fromio(void *, const volatile void __iomem *, unsigned long);
 void memcpy_toio(volatile void __iomem *, const void *, unsigned long);
diff --git a/arch/sh/include/asm/mmiowb.h b/arch/sh/include/asm/mmiowb.h
new file mode 100644
index 000000000000..535d59735f1d
--- /dev/null
+++ b/arch/sh/include/asm/mmiowb.h
@@ -0,0 +1,12 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef __ASM_SH_MMIOWB_H
+#define __ASM_SH_MMIOWB_H
+
+#include <asm/barrier.h>
+
+/* synco on SH-4A, otherwise a nop */
+#define mmiowb()			wmb()
+
+#include <asm-generic/mmiowb.h>
+
+#endif	/* __ASM_SH_MMIOWB_H */
diff --git a/arch/sh/include/asm/pgalloc.h b/arch/sh/include/asm/pgalloc.h
index 8ad73cb31121..b56f908b1395 100644
--- a/arch/sh/include/asm/pgalloc.h
+++ b/arch/sh/include/asm/pgalloc.h
@@ -70,6 +70,15 @@ do {							\
 	tlb_remove_page((tlb), (pte));			\
 } while (0)
 
+#if CONFIG_PGTABLE_LEVELS > 2
+#define __pmd_free_tlb(tlb, pmdp, addr)			\
+do {							\
+	struct page *page = virt_to_page(pmdp);		\
+	pgtable_pmd_page_dtor(page);			\
+	tlb_remove_page((tlb), page);			\
+} while (0);
+#endif
+
 static inline void check_pgt_cache(void)
 {
 	quicklist_trim(QUICK_PT, NULL, 25, 16);
diff --git a/arch/sh/include/asm/spinlock-llsc.h b/arch/sh/include/asm/spinlock-llsc.h
index 786ee0fde3b0..7fd929cd2e7a 100644
--- a/arch/sh/include/asm/spinlock-llsc.h
+++ b/arch/sh/include/asm/spinlock-llsc.h
@@ -47,6 +47,8 @@ static inline void arch_spin_unlock(arch_spinlock_t *lock)
 {
 	unsigned long tmp;
 
+	/* This could be optimised with ARCH_HAS_MMIOWB */
+	mmiowb();
 	__asm__ __volatile__ (
 		"mov		#1, %0 ! arch_spin_unlock	\n\t"
 		"mov.l		%0, @%1				\n\t"
diff --git a/arch/sh/include/asm/syscall_32.h b/arch/sh/include/asm/syscall_32.h
index 6e118799831c..8c9d7e5e5dcc 100644
--- a/arch/sh/include/asm/syscall_32.h
+++ b/arch/sh/include/asm/syscall_32.h
@@ -48,51 +48,28 @@ static inline void syscall_set_return_value(struct task_struct *task,
 
 static inline void syscall_get_arguments(struct task_struct *task,
 					 struct pt_regs *regs,
-					 unsigned int i, unsigned int n,
 					 unsigned long *args)
 {
-	/*
-	 * Do this simply for now. If we need to start supporting
-	 * fetching arguments from arbitrary indices, this will need some
-	 * extra logic. Presently there are no in-tree users that depend
-	 * on this behaviour.
-	 */
-	BUG_ON(i);
 
 	/* Argument pattern is: R4, R5, R6, R7, R0, R1 */
-	switch (n) {
-	case 6: args[5] = regs->regs[1];
-	case 5: args[4] = regs->regs[0];
-	case 4: args[3] = regs->regs[7];
-	case 3: args[2] = regs->regs[6];
-	case 2: args[1] = regs->regs[5];
-	case 1:	args[0] = regs->regs[4];
-	case 0:
-		break;
-	default:
-		BUG();
-	}
+	args[5] = regs->regs[1];
+	args[4] = regs->regs[0];
+	args[3] = regs->regs[7];
+	args[2] = regs->regs[6];
+	args[1] = regs->regs[5];
+	args[0] = regs->regs[4];
 }
 
 static inline void syscall_set_arguments(struct task_struct *task,
 					 struct pt_regs *regs,
-					 unsigned int i, unsigned int n,
 					 const unsigned long *args)
 {
-	/* Same note as above applies */
-	BUG_ON(i);
-
-	switch (n) {
-	case 6: regs->regs[1] = args[5];
-	case 5: regs->regs[0] = args[4];
-	case 4: regs->regs[7] = args[3];
-	case 3: regs->regs[6] = args[2];
-	case 2: regs->regs[5] = args[1];
-	case 1: regs->regs[4] = args[0];
-		break;
-	default:
-		BUG();
-	}
+	regs->regs[1] = args[5];
+	regs->regs[0] = args[4];
+	regs->regs[7] = args[3];
+	regs->regs[6] = args[2];
+	regs->regs[5] = args[1];
+	regs->regs[4] = args[0];
 }
 
 static inline int syscall_get_arch(void)
diff --git a/arch/sh/include/asm/syscall_64.h b/arch/sh/include/asm/syscall_64.h
index 43882580c7f9..22fad97da066 100644
--- a/arch/sh/include/asm/syscall_64.h
+++ b/arch/sh/include/asm/syscall_64.h
@@ -47,20 +47,16 @@ static inline void syscall_set_return_value(struct task_struct *task,
 
 static inline void syscall_get_arguments(struct task_struct *task,
 					 struct pt_regs *regs,
-					 unsigned int i, unsigned int n,
 					 unsigned long *args)
 {
-	BUG_ON(i + n > 6);
-	memcpy(args, &regs->regs[2 + i], n * sizeof(args[0]));
+	memcpy(args, &regs->regs[2], 6 * sizeof(args[0]));
 }
 
 static inline void syscall_set_arguments(struct task_struct *task,
 					 struct pt_regs *regs,
-					 unsigned int i, unsigned int n,
 					 const unsigned long *args)
 {
-	BUG_ON(i + n > 6);
-	memcpy(&regs->regs[2 + i], args, n * sizeof(args[0]));
+	memcpy(&regs->regs[2], args, 6 * sizeof(args[0]));
 }
 
 static inline int syscall_get_arch(void)
diff --git a/arch/sh/include/asm/tlb.h b/arch/sh/include/asm/tlb.h
index 77abe192fb43..bc77f3dd4261 100644
--- a/arch/sh/include/asm/tlb.h
+++ b/arch/sh/include/asm/tlb.h
@@ -11,133 +11,8 @@
 
 #ifdef CONFIG_MMU
 #include <linux/swap.h>
-#include <asm/pgalloc.h>
-#include <asm/tlbflush.h>
-#include <asm/mmu_context.h>
 
-/*
- * TLB handling.  This allows us to remove pages from the page
- * tables, and efficiently handle the TLB issues.
- */
-struct mmu_gather {
-	struct mm_struct	*mm;
-	unsigned int		fullmm;
-	unsigned long		start, end;
-};
-
-static inline void init_tlb_gather(struct mmu_gather *tlb)
-{
-	tlb->start = TASK_SIZE;
-	tlb->end = 0;
-
-	if (tlb->fullmm) {
-		tlb->start = 0;
-		tlb->end = TASK_SIZE;
-	}
-}
-
-static inline void
-arch_tlb_gather_mmu(struct mmu_gather *tlb, struct mm_struct *mm,
-		unsigned long start, unsigned long end)
-{
-	tlb->mm = mm;
-	tlb->start = start;
-	tlb->end = end;
-	tlb->fullmm = !(start | (end+1));
-
-	init_tlb_gather(tlb);
-}
-
-static inline void
-arch_tlb_finish_mmu(struct mmu_gather *tlb,
-		unsigned long start, unsigned long end, bool force)
-{
-	if (tlb->fullmm || force)
-		flush_tlb_mm(tlb->mm);
-
-	/* keep the page table cache within bounds */
-	check_pgt_cache();
-}
-
-static inline void
-tlb_remove_tlb_entry(struct mmu_gather *tlb, pte_t *ptep, unsigned long address)
-{
-	if (tlb->start > address)
-		tlb->start = address;
-	if (tlb->end < address + PAGE_SIZE)
-		tlb->end = address + PAGE_SIZE;
-}
-
-#define tlb_remove_huge_tlb_entry(h, tlb, ptep, address)	\
-	tlb_remove_tlb_entry(tlb, ptep, address)
-
-/*
- * In the case of tlb vma handling, we can optimise these away in the
- * case where we're doing a full MM flush.  When we're doing a munmap,
- * the vmas are adjusted to only cover the region to be torn down.
- */
-static inline void
-tlb_start_vma(struct mmu_gather *tlb, struct vm_area_struct *vma)
-{
-	if (!tlb->fullmm)
-		flush_cache_range(vma, vma->vm_start, vma->vm_end);
-}
-
-static inline void
-tlb_end_vma(struct mmu_gather *tlb, struct vm_area_struct *vma)
-{
-	if (!tlb->fullmm && tlb->end) {
-		flush_tlb_range(vma, tlb->start, tlb->end);
-		init_tlb_gather(tlb);
-	}
-}
-
-static inline void tlb_flush_mmu_tlbonly(struct mmu_gather *tlb)
-{
-}
-
-static inline void tlb_flush_mmu_free(struct mmu_gather *tlb)
-{
-}
-
-static inline void tlb_flush_mmu(struct mmu_gather *tlb)
-{
-}
-
-static inline int __tlb_remove_page(struct mmu_gather *tlb, struct page *page)
-{
-	free_page_and_swap_cache(page);
-	return false; /* avoid calling tlb_flush_mmu */
-}
-
-static inline void tlb_remove_page(struct mmu_gather *tlb, struct page *page)
-{
-	__tlb_remove_page(tlb, page);
-}
-
-static inline bool __tlb_remove_page_size(struct mmu_gather *tlb,
-					  struct page *page, int page_size)
-{
-	return __tlb_remove_page(tlb, page);
-}
-
-static inline void tlb_remove_page_size(struct mmu_gather *tlb,
-					struct page *page, int page_size)
-{
-	return tlb_remove_page(tlb, page);
-}
-
-#define tlb_remove_check_page_size_change tlb_remove_check_page_size_change
-static inline void tlb_remove_check_page_size_change(struct mmu_gather *tlb,
-						     unsigned int page_size)
-{
-}
-
-#define pte_free_tlb(tlb, ptep, addr)	pte_free((tlb)->mm, ptep)
-#define pmd_free_tlb(tlb, pmdp, addr)	pmd_free((tlb)->mm, pmdp)
-#define pud_free_tlb(tlb, pudp, addr)	pud_free((tlb)->mm, pudp)
-
-#define tlb_migrate_finish(mm)		do { } while (0)
+#include <asm-generic/tlb.h>
 
 #if defined(CONFIG_CPU_SH4) || defined(CONFIG_SUPERH64)
 extern void tlb_wire_entry(struct vm_area_struct *, unsigned long, pte_t);
@@ -157,11 +32,6 @@ static inline void tlb_unwire_entry(void)
 
 #else /* CONFIG_MMU */
 
-#define tlb_start_vma(tlb, vma)				do { } while (0)
-#define tlb_end_vma(tlb, vma)				do { } while (0)
-#define __tlb_remove_tlb_entry(tlb, pte, address)	do { } while (0)
-#define tlb_flush(tlb)					do { } while (0)
-
 #include <asm-generic/tlb.h>
 
 #endif /* CONFIG_MMU */
diff --git a/arch/sh/include/uapi/asm/Kbuild b/arch/sh/include/uapi/asm/Kbuild
index ecfbd40924dd..b8812c74c1de 100644
--- a/arch/sh/include/uapi/asm/Kbuild
+++ b/arch/sh/include/uapi/asm/Kbuild
@@ -1,5 +1,4 @@
 # SPDX-License-Identifier: GPL-2.0
 
 generated-y += unistd_32.h
-generic-y += kvm_para.h
 generic-y += ucontext.h
diff --git a/arch/sh/kernel/stacktrace.c b/arch/sh/kernel/stacktrace.c
index f3cb2cccb262..2950b19ad077 100644
--- a/arch/sh/kernel/stacktrace.c
+++ b/arch/sh/kernel/stacktrace.c
@@ -49,8 +49,6 @@ void save_stack_trace(struct stack_trace *trace)
 	unsigned long *sp = (unsigned long *)current_stack_pointer;
 
 	unwind_stack(current, NULL, sp,  &save_stack_ops, trace);
-	if (trace->nr_entries < trace->max_entries)
-		trace->entries[trace->nr_entries++] = ULONG_MAX;
 }
 EXPORT_SYMBOL_GPL(save_stack_trace);
 
@@ -84,7 +82,5 @@ void save_stack_trace_tsk(struct task_struct *tsk, struct stack_trace *trace)
 	unsigned long *sp = (unsigned long *)tsk->thread.sp;
 
 	unwind_stack(current, NULL, sp,  &save_stack_ops_nosched, trace);
-	if (trace->nr_entries < trace->max_entries)
-		trace->entries[trace->nr_entries++] = ULONG_MAX;
 }
 EXPORT_SYMBOL_GPL(save_stack_trace_tsk);
diff --git a/arch/sh/kernel/syscalls/syscall.tbl b/arch/sh/kernel/syscalls/syscall.tbl
index bfda678576e4..480b057556ee 100644
--- a/arch/sh/kernel/syscalls/syscall.tbl
+++ b/arch/sh/kernel/syscalls/syscall.tbl
@@ -426,3 +426,7 @@
 421	common	rt_sigtimedwait_time64		sys_rt_sigtimedwait
 422	common	futex_time64			sys_futex
 423	common	sched_rr_get_interval_time64	sys_sched_rr_get_interval
+424	common	pidfd_send_signal		sys_pidfd_send_signal
+425	common	io_uring_setup			sys_io_uring_setup
+426	common	io_uring_enter			sys_io_uring_enter
+427	common	io_uring_register		sys_io_uring_register
diff --git a/arch/sparc/Kconfig b/arch/sparc/Kconfig
index 40f8f4f73fe8..f6421c9ce5d3 100644
--- a/arch/sparc/Kconfig
+++ b/arch/sparc/Kconfig
@@ -63,6 +63,7 @@ config SPARC64
 	select HAVE_KRETPROBES
 	select HAVE_KPROBES
 	select HAVE_RCU_TABLE_FREE if SMP
+	select HAVE_RCU_TABLE_NO_INVALIDATE if HAVE_RCU_TABLE_FREE
 	select HAVE_MEMBLOCK_NODE_MAP
 	select HAVE_ARCH_TRANSPARENT_HUGEPAGE
 	select HAVE_DYNAMIC_FTRACE
@@ -191,14 +192,6 @@ config NR_CPUS
 
 source "kernel/Kconfig.hz"
 
-config RWSEM_GENERIC_SPINLOCK
-	bool
-	default y if SPARC32
-
-config RWSEM_XCHGADD_ALGORITHM
-	bool
-	default y if SPARC64
-
 config GENERIC_HWEIGHT
 	bool
 	default y
diff --git a/arch/sparc/crypto/des_glue.c b/arch/sparc/crypto/des_glue.c
index 4884315daff4..453a4cf5492a 100644
--- a/arch/sparc/crypto/des_glue.c
+++ b/arch/sparc/crypto/des_glue.c
@@ -201,18 +201,15 @@ static int des3_ede_set_key(struct crypto_tfm *tfm, const u8 *key,
 			    unsigned int keylen)
 {
 	struct des3_ede_sparc64_ctx *dctx = crypto_tfm_ctx(tfm);
-	const u32 *K = (const u32 *)key;
 	u32 *flags = &tfm->crt_flags;
 	u64 k1[DES_EXPKEY_WORDS / 2];
 	u64 k2[DES_EXPKEY_WORDS / 2];
 	u64 k3[DES_EXPKEY_WORDS / 2];
+	int err;
 
-	if (unlikely(!((K[0] ^ K[2]) | (K[1] ^ K[3])) ||
-		     !((K[2] ^ K[4]) | (K[3] ^ K[5]))) &&
-		     (*flags & CRYPTO_TFM_REQ_FORBID_WEAK_KEYS)) {
-		*flags |= CRYPTO_TFM_RES_WEAK_KEY;
-		return -EINVAL;
-	}
+	err = __des3_verify_key(flags, key);
+	if (unlikely(err))
+		return err;
 
 	des_sparc64_key_expand((const u32 *)key, k1);
 	key += DES_KEY_SIZE;
diff --git a/arch/sparc/include/asm/Kbuild b/arch/sparc/include/asm/Kbuild
index b82f64e28f55..95c44380b1d6 100644
--- a/arch/sparc/include/asm/Kbuild
+++ b/arch/sparc/include/asm/Kbuild
@@ -9,15 +9,16 @@ generic-y += exec.h
 generic-y += export.h
 generic-y += irq_regs.h
 generic-y += irq_work.h
+generic-y += kvm_para.h
 generic-y += linkage.h
 generic-y += local.h
 generic-y += local64.h
 generic-y += mcs_spinlock.h
 generic-y += mm-arch-hooks.h
+generic-y += mmiowb.h
 generic-y += module.h
 generic-y += msi.h
 generic-y += preempt.h
-generic-y += rwsem.h
 generic-y += serial.h
 generic-y += trace_clock.h
 generic-y += word-at-a-time.h
diff --git a/arch/sparc/include/asm/io_64.h b/arch/sparc/include/asm/io_64.h
index b162c23ae8c2..688911051b44 100644
--- a/arch/sparc/include/asm/io_64.h
+++ b/arch/sparc/include/asm/io_64.h
@@ -396,8 +396,6 @@ static inline void memcpy_toio(volatile void __iomem *dst, const void *src,
 	}
 }
 
-#define mmiowb()
-
 #ifdef __KERNEL__
 
 /* On sparc64 we have the whole physical IO address space accessible
diff --git a/arch/sparc/include/asm/syscall.h b/arch/sparc/include/asm/syscall.h
index 053989e3f6a6..4d075434e816 100644
--- a/arch/sparc/include/asm/syscall.h
+++ b/arch/sparc/include/asm/syscall.h
@@ -96,11 +96,11 @@ static inline void syscall_set_return_value(struct task_struct *task,
 
 static inline void syscall_get_arguments(struct task_struct *task,
 					 struct pt_regs *regs,
-					 unsigned int i, unsigned int n,
 					 unsigned long *args)
 {
 	int zero_extend = 0;
 	unsigned int j;
+	unsigned int n = 6;
 
 #ifdef CONFIG_SPARC64
 	if (test_tsk_thread_flag(task, TIF_32BIT))
@@ -108,7 +108,7 @@ static inline void syscall_get_arguments(struct task_struct *task,
 #endif
 
 	for (j = 0; j < n; j++) {
-		unsigned long val = regs->u_regs[UREG_I0 + i + j];
+		unsigned long val = regs->u_regs[UREG_I0 + j];
 
 		if (zero_extend)
 			args[j] = (u32) val;
@@ -119,13 +119,12 @@ static inline void syscall_get_arguments(struct task_struct *task,
 
 static inline void syscall_set_arguments(struct task_struct *task,
 					 struct pt_regs *regs,
-					 unsigned int i, unsigned int n,
 					 const unsigned long *args)
 {
-	unsigned int j;
+	unsigned int i;
 
-	for (j = 0; j < n; j++)
-		regs->u_regs[UREG_I0 + i + j] = args[j];
+	for (i = 0; i < 6; i++)
+		regs->u_regs[UREG_I0 + i] = args[i];
 }
 
 static inline int syscall_get_arch(void)
diff --git a/arch/sparc/include/asm/tlb_32.h b/arch/sparc/include/asm/tlb_32.h
index 343cea19e573..5cd28a8793e3 100644
--- a/arch/sparc/include/asm/tlb_32.h
+++ b/arch/sparc/include/asm/tlb_32.h
@@ -2,24 +2,6 @@
 #ifndef _SPARC_TLB_H
 #define _SPARC_TLB_H
 
-#define tlb_start_vma(tlb, vma) \
-do {								\
-	flush_cache_range(vma, vma->vm_start, vma->vm_end);	\
-} while (0)
-
-#define tlb_end_vma(tlb, vma) \
-do {								\
-	flush_tlb_range(vma, vma->vm_start, vma->vm_end);	\
-} while (0)
-
-#define __tlb_remove_tlb_entry(tlb, pte, address) \
-	do { } while (0)
-
-#define tlb_flush(tlb) \
-do {								\
-	flush_tlb_mm((tlb)->mm);				\
-} while (0)
-
 #include <asm-generic/tlb.h>
 
 #endif /* _SPARC_TLB_H */
diff --git a/arch/sparc/include/uapi/asm/kvm_para.h b/arch/sparc/include/uapi/asm/kvm_para.h
deleted file mode 100644
index baacc4996d18..000000000000
--- a/arch/sparc/include/uapi/asm/kvm_para.h
+++ /dev/null
@@ -1,2 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
-#include <asm-generic/kvm_para.h>
diff --git a/arch/sparc/kernel/pci_sun4v.c b/arch/sparc/kernel/pci_sun4v.c
index a8af6023c126..14b93c5564e3 100644
--- a/arch/sparc/kernel/pci_sun4v.c
+++ b/arch/sparc/kernel/pci_sun4v.c
@@ -73,6 +73,11 @@ static inline void iommu_batch_start(struct device *dev, unsigned long prot, uns
 	p->npages	= 0;
 }
 
+static inline bool iommu_use_atu(struct iommu *iommu, u64 mask)
+{
+	return iommu->atu && mask > DMA_BIT_MASK(32);
+}
+
 /* Interrupts must be disabled.  */
 static long iommu_batch_flush(struct iommu_batch *p, u64 mask)
 {
@@ -92,7 +97,7 @@ static long iommu_batch_flush(struct iommu_batch *p, u64 mask)
 		prot &= (HV_PCI_MAP_ATTR_READ | HV_PCI_MAP_ATTR_WRITE);
 
 	while (npages != 0) {
-		if (mask <= DMA_BIT_MASK(32) || !pbm->iommu->atu) {
+		if (!iommu_use_atu(pbm->iommu, mask)) {
 			num = pci_sun4v_iommu_map(devhandle,
 						  HV_PCI_TSBID(0, entry),
 						  npages,
@@ -179,7 +184,6 @@ static void *dma_4v_alloc_coherent(struct device *dev, size_t size,
 	unsigned long flags, order, first_page, npages, n;
 	unsigned long prot = 0;
 	struct iommu *iommu;
-	struct atu *atu;
 	struct iommu_map_table *tbl;
 	struct page *page;
 	void *ret;
@@ -205,13 +209,11 @@ static void *dma_4v_alloc_coherent(struct device *dev, size_t size,
 	memset((char *)first_page, 0, PAGE_SIZE << order);
 
 	iommu = dev->archdata.iommu;
-	atu = iommu->atu;
-
 	mask = dev->coherent_dma_mask;
-	if (mask <= DMA_BIT_MASK(32) || !atu)
+	if (!iommu_use_atu(iommu, mask))
 		tbl = &iommu->tbl;
 	else
-		tbl = &atu->tbl;
+		tbl = &iommu->atu->tbl;
 
 	entry = iommu_tbl_range_alloc(dev, tbl, npages, NULL,
 				      (unsigned long)(-1), 0);
@@ -333,7 +335,7 @@ static void dma_4v_free_coherent(struct device *dev, size_t size, void *cpu,
 	atu = iommu->atu;
 	devhandle = pbm->devhandle;
 
-	if (dvma <= DMA_BIT_MASK(32)) {
+	if (!iommu_use_atu(iommu, dvma)) {
 		tbl = &iommu->tbl;
 		iotsb_num = 0; /* we don't care for legacy iommu */
 	} else {
@@ -374,7 +376,7 @@ static dma_addr_t dma_4v_map_page(struct device *dev, struct page *page,
 	npages >>= IO_PAGE_SHIFT;
 
 	mask = *dev->dma_mask;
-	if (mask <= DMA_BIT_MASK(32))
+	if (!iommu_use_atu(iommu, mask))
 		tbl = &iommu->tbl;
 	else
 		tbl = &atu->tbl;
@@ -510,7 +512,7 @@ static int dma_4v_map_sg(struct device *dev, struct scatterlist *sglist,
 				  IO_PAGE_SIZE) >> IO_PAGE_SHIFT;
 
 	mask = *dev->dma_mask;
-	if (mask <= DMA_BIT_MASK(32))
+	if (!iommu_use_atu(iommu, mask))
 		tbl = &iommu->tbl;
 	else
 		tbl = &atu->tbl;
diff --git a/arch/sparc/kernel/syscalls/syscall.tbl b/arch/sparc/kernel/syscalls/syscall.tbl
index b9a5a04b2d2c..a1dd24307b00 100644
--- a/arch/sparc/kernel/syscalls/syscall.tbl
+++ b/arch/sparc/kernel/syscalls/syscall.tbl
@@ -469,3 +469,7 @@
 421	32	rt_sigtimedwait_time64		sys_rt_sigtimedwait		compat_sys_rt_sigtimedwait_time64
 422	32	futex_time64			sys_futex			sys_futex
 423	32	sched_rr_get_interval_time64	sys_sched_rr_get_interval	sys_sched_rr_get_interval
+424	common	pidfd_send_signal		sys_pidfd_send_signal
+425	common	io_uring_setup			sys_io_uring_setup
+426	common	io_uring_enter			sys_io_uring_enter
+427	common	io_uring_register		sys_io_uring_register
diff --git a/arch/um/include/asm/Kbuild b/arch/um/include/asm/Kbuild
index 00bcbe2326d9..b506ad06aefc 100644
--- a/arch/um/include/asm/Kbuild
+++ b/arch/um/include/asm/Kbuild
@@ -16,6 +16,7 @@ generic-y += irq_work.h
 generic-y += kdebug.h
 generic-y += mcs_spinlock.h
 generic-y += mm-arch-hooks.h
+generic-y += mmiowb.h
 generic-y += param.h
 generic-y += pci.h
 generic-y += percpu.h
diff --git a/arch/um/include/asm/syscall-generic.h b/arch/um/include/asm/syscall-generic.h
index 9fb9cf8cd39a..98e50c50c12e 100644
--- a/arch/um/include/asm/syscall-generic.h
+++ b/arch/um/include/asm/syscall-generic.h
@@ -53,84 +53,30 @@ static inline void syscall_set_return_value(struct task_struct *task,
 
 static inline void syscall_get_arguments(struct task_struct *task,
 					 struct pt_regs *regs,
-					 unsigned int i, unsigned int n,
 					 unsigned long *args)
 {
 	const struct uml_pt_regs *r = &regs->regs;
 
-	switch (i) {
-	case 0:
-		if (!n--)
-			break;
-		*args++ = UPT_SYSCALL_ARG1(r);
-	case 1:
-		if (!n--)
-			break;
-		*args++ = UPT_SYSCALL_ARG2(r);
-	case 2:
-		if (!n--)
-			break;
-		*args++ = UPT_SYSCALL_ARG3(r);
-	case 3:
-		if (!n--)
-			break;
-		*args++ = UPT_SYSCALL_ARG4(r);
-	case 4:
-		if (!n--)
-			break;
-		*args++ = UPT_SYSCALL_ARG5(r);
-	case 5:
-		if (!n--)
-			break;
-		*args++ = UPT_SYSCALL_ARG6(r);
-	case 6:
-		if (!n--)
-			break;
-	default:
-		BUG();
-		break;
-	}
+	*args++ = UPT_SYSCALL_ARG1(r);
+	*args++ = UPT_SYSCALL_ARG2(r);
+	*args++ = UPT_SYSCALL_ARG3(r);
+	*args++ = UPT_SYSCALL_ARG4(r);
+	*args++ = UPT_SYSCALL_ARG5(r);
+	*args   = UPT_SYSCALL_ARG6(r);
 }
 
 static inline void syscall_set_arguments(struct task_struct *task,
 					 struct pt_regs *regs,
-					 unsigned int i, unsigned int n,
 					 const unsigned long *args)
 {
 	struct uml_pt_regs *r = &regs->regs;
 
-	switch (i) {
-	case 0:
-		if (!n--)
-			break;
-		UPT_SYSCALL_ARG1(r) = *args++;
-	case 1:
-		if (!n--)
-			break;
-		UPT_SYSCALL_ARG2(r) = *args++;
-	case 2:
-		if (!n--)
-			break;
-		UPT_SYSCALL_ARG3(r) = *args++;
-	case 3:
-		if (!n--)
-			break;
-		UPT_SYSCALL_ARG4(r) = *args++;
-	case 4:
-		if (!n--)
-			break;
-		UPT_SYSCALL_ARG5(r) = *args++;
-	case 5:
-		if (!n--)
-			break;
-		UPT_SYSCALL_ARG6(r) = *args++;
-	case 6:
-		if (!n--)
-			break;
-	default:
-		BUG();
-		break;
-	}
+	UPT_SYSCALL_ARG1(r) = *args++;
+	UPT_SYSCALL_ARG2(r) = *args++;
+	UPT_SYSCALL_ARG3(r) = *args++;
+	UPT_SYSCALL_ARG4(r) = *args++;
+	UPT_SYSCALL_ARG5(r) = *args++;
+	UPT_SYSCALL_ARG6(r) = *args;
 }
 
 /* See arch/x86/um/asm/syscall.h for syscall_get_arch() definition. */
diff --git a/arch/um/include/asm/tlb.h b/arch/um/include/asm/tlb.h
index dce6db147f24..70ee60383900 100644
--- a/arch/um/include/asm/tlb.h
+++ b/arch/um/include/asm/tlb.h
@@ -2,162 +2,8 @@
 #ifndef __UM_TLB_H
 #define __UM_TLB_H
 
-#include <linux/pagemap.h>
-#include <linux/swap.h>
-#include <asm/percpu.h>
-#include <asm/pgalloc.h>
 #include <asm/tlbflush.h>
-
-#define tlb_start_vma(tlb, vma) do { } while (0)
-#define tlb_end_vma(tlb, vma) do { } while (0)
-#define tlb_flush(tlb) flush_tlb_mm((tlb)->mm)
-
-/* struct mmu_gather is an opaque type used by the mm code for passing around
- * any data needed by arch specific code for tlb_remove_page.
- */
-struct mmu_gather {
-	struct mm_struct	*mm;
-	unsigned int		need_flush; /* Really unmapped some ptes? */
-	unsigned long		start;
-	unsigned long		end;
-	unsigned int		fullmm; /* non-zero means full mm flush */
-};
-
-static inline void __tlb_remove_tlb_entry(struct mmu_gather *tlb, pte_t *ptep,
-					  unsigned long address)
-{
-	if (tlb->start > address)
-		tlb->start = address;
-	if (tlb->end < address + PAGE_SIZE)
-		tlb->end = address + PAGE_SIZE;
-}
-
-static inline void init_tlb_gather(struct mmu_gather *tlb)
-{
-	tlb->need_flush = 0;
-
-	tlb->start = TASK_SIZE;
-	tlb->end = 0;
-
-	if (tlb->fullmm) {
-		tlb->start = 0;
-		tlb->end = TASK_SIZE;
-	}
-}
-
-static inline void
-arch_tlb_gather_mmu(struct mmu_gather *tlb, struct mm_struct *mm,
-		unsigned long start, unsigned long end)
-{
-	tlb->mm = mm;
-	tlb->start = start;
-	tlb->end = end;
-	tlb->fullmm = !(start | (end+1));
-
-	init_tlb_gather(tlb);
-}
-
-extern void flush_tlb_mm_range(struct mm_struct *mm, unsigned long start,
-			       unsigned long end);
-
-static inline void
-tlb_flush_mmu_tlbonly(struct mmu_gather *tlb)
-{
-	flush_tlb_mm_range(tlb->mm, tlb->start, tlb->end);
-}
-
-static inline void
-tlb_flush_mmu_free(struct mmu_gather *tlb)
-{
-	init_tlb_gather(tlb);
-}
-
-static inline void
-tlb_flush_mmu(struct mmu_gather *tlb)
-{
-	if (!tlb->need_flush)
-		return;
-
-	tlb_flush_mmu_tlbonly(tlb);
-	tlb_flush_mmu_free(tlb);
-}
-
-/* arch_tlb_finish_mmu
- *	Called at the end of the shootdown operation to free up any resources
- *	that were required.
- */
-static inline void
-arch_tlb_finish_mmu(struct mmu_gather *tlb,
-		unsigned long start, unsigned long end, bool force)
-{
-	if (force) {
-		tlb->start = start;
-		tlb->end = end;
-		tlb->need_flush = 1;
-	}
-	tlb_flush_mmu(tlb);
-
-	/* keep the page table cache within bounds */
-	check_pgt_cache();
-}
-
-/* tlb_remove_page
- *	Must perform the equivalent to __free_pte(pte_get_and_clear(ptep)),
- *	while handling the additional races in SMP caused by other CPUs
- *	caching valid mappings in their TLBs.
- */
-static inline int __tlb_remove_page(struct mmu_gather *tlb, struct page *page)
-{
-	tlb->need_flush = 1;
-	free_page_and_swap_cache(page);
-	return false; /* avoid calling tlb_flush_mmu */
-}
-
-static inline void tlb_remove_page(struct mmu_gather *tlb, struct page *page)
-{
-	__tlb_remove_page(tlb, page);
-}
-
-static inline bool __tlb_remove_page_size(struct mmu_gather *tlb,
-					  struct page *page, int page_size)
-{
-	return __tlb_remove_page(tlb, page);
-}
-
-static inline void tlb_remove_page_size(struct mmu_gather *tlb,
-					struct page *page, int page_size)
-{
-	return tlb_remove_page(tlb, page);
-}
-
-/**
- * tlb_remove_tlb_entry - remember a pte unmapping for later tlb invalidation.
- *
- * Record the fact that pte's were really umapped in ->need_flush, so we can
- * later optimise away the tlb invalidate.   This helps when userspace is
- * unmapping already-unmapped pages, which happens quite a lot.
- */
-#define tlb_remove_tlb_entry(tlb, ptep, address)		\
-	do {							\
-		tlb->need_flush = 1;				\
-		__tlb_remove_tlb_entry(tlb, ptep, address);	\
-	} while (0)
-
-#define tlb_remove_huge_tlb_entry(h, tlb, ptep, address)	\
-	tlb_remove_tlb_entry(tlb, ptep, address)
-
-#define tlb_remove_check_page_size_change tlb_remove_check_page_size_change
-static inline void tlb_remove_check_page_size_change(struct mmu_gather *tlb,
-						     unsigned int page_size)
-{
-}
-
-#define pte_free_tlb(tlb, ptep, addr) __pte_free_tlb(tlb, ptep, addr)
-
-#define pud_free_tlb(tlb, pudp, addr) __pud_free_tlb(tlb, pudp, addr)
-
-#define pmd_free_tlb(tlb, pmdp, addr) __pmd_free_tlb(tlb, pmdp, addr)
-
-#define tlb_migrate_finish(mm) do {} while (0)
+#include <asm-generic/cacheflush.h>
+#include <asm-generic/tlb.h>
 
 #endif
diff --git a/arch/um/kernel/stacktrace.c b/arch/um/kernel/stacktrace.c
index ebe7bcf62684..bd95e020d509 100644
--- a/arch/um/kernel/stacktrace.c
+++ b/arch/um/kernel/stacktrace.c
@@ -63,8 +63,6 @@ static const struct stacktrace_ops dump_ops = {
 static void __save_stack_trace(struct task_struct *tsk, struct stack_trace *trace)
 {
 	dump_trace(tsk, &dump_ops, trace);
-	if (trace->nr_entries < trace->max_entries)
-		trace->entries[trace->nr_entries++] = ULONG_MAX;
 }
 
 void save_stack_trace(struct stack_trace *trace)
diff --git a/arch/unicore32/Kconfig b/arch/unicore32/Kconfig
index 817d82608712..2445dfcf6444 100644
--- a/arch/unicore32/Kconfig
+++ b/arch/unicore32/Kconfig
@@ -20,6 +20,7 @@ config UNICORE32
 	select GENERIC_IOMAP
 	select MODULES_USE_ELF_REL
 	select NEED_DMA_MAP_STATE
+	select MMU_GATHER_NO_RANGE if MMU
 	help
 	  UniCore-32 is 32-bit Instruction Set Architecture,
 	  including a series of low-power-consumption RISC chip
@@ -38,12 +39,6 @@ config STACKTRACE_SUPPORT
 config LOCKDEP_SUPPORT
 	def_bool y
 
-config RWSEM_GENERIC_SPINLOCK
-	def_bool y
-
-config RWSEM_XCHGADD_ALGORITHM
-	bool
-
 config ARCH_HAS_ILOG2_U32
 	bool
 
diff --git a/arch/unicore32/include/asm/Kbuild b/arch/unicore32/include/asm/Kbuild
index 1d1544b6ca74..b301a0b3c0b2 100644
--- a/arch/unicore32/include/asm/Kbuild
+++ b/arch/unicore32/include/asm/Kbuild
@@ -18,9 +18,11 @@ generic-y += irq_work.h
 generic-y += kdebug.h
 generic-y += kmap_types.h
 generic-y += kprobes.h
+generic-y += kvm_para.h
 generic-y += local.h
 generic-y += mcs_spinlock.h
 generic-y += mm-arch-hooks.h
+generic-y += mmiowb.h
 generic-y += module.h
 generic-y += parport.h
 generic-y += percpu.h
diff --git a/arch/unicore32/include/asm/tlb.h b/arch/unicore32/include/asm/tlb.h
index 9cca15cdae94..00a8477333f6 100644
--- a/arch/unicore32/include/asm/tlb.h
+++ b/arch/unicore32/include/asm/tlb.h
@@ -12,10 +12,9 @@
 #ifndef __UNICORE_TLB_H__
 #define __UNICORE_TLB_H__
 
-#define tlb_start_vma(tlb, vma)				do { } while (0)
-#define tlb_end_vma(tlb, vma)				do { } while (0)
-#define __tlb_remove_tlb_entry(tlb, ptep, address)	do { } while (0)
-#define tlb_flush(tlb) flush_tlb_mm((tlb)->mm)
+/*
+ * unicore32 lacks an efficient flush_tlb_range(), use flush_tlb_mm().
+ */
 
 #define __pte_free_tlb(tlb, pte, addr)				\
 	do {							\
diff --git a/arch/unicore32/include/uapi/asm/Kbuild b/arch/unicore32/include/uapi/asm/Kbuild
index 755bb11323d8..1c72f04ff75d 100644
--- a/arch/unicore32/include/uapi/asm/Kbuild
+++ b/arch/unicore32/include/uapi/asm/Kbuild
@@ -1,2 +1 @@
-generic-y += kvm_para.h
 generic-y += ucontext.h
diff --git a/arch/unicore32/kernel/stacktrace.c b/arch/unicore32/kernel/stacktrace.c
index 9976e767d51c..e37da8c6837b 100644
--- a/arch/unicore32/kernel/stacktrace.c
+++ b/arch/unicore32/kernel/stacktrace.c
@@ -120,8 +120,6 @@ void save_stack_trace_tsk(struct task_struct *tsk, struct stack_trace *trace)
 	}
 
 	walk_stackframe(&frame, save_trace, &data);
-	if (trace->nr_entries < trace->max_entries)
-		trace->entries[trace->nr_entries++] = ULONG_MAX;
 }
 
 void save_stack_trace(struct stack_trace *trace)
diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index c1f9b3cf437c..0a3cc347143f 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -14,6 +14,7 @@ config X86_32
 	select ARCH_WANT_IPC_PARSE_VERSION
 	select CLKSRC_I8253
 	select CLONE_BACKWARDS
+	select HAVE_DEBUG_STACKOVERFLOW
 	select MODULES_USE_ELF_REL
 	select OLD_SIGACTION
 
@@ -28,7 +29,6 @@ config X86_64
 	select MODULES_USE_ELF_RELA
 	select NEED_DMA_MAP_STATE
 	select SWIOTLB
-	select X86_DEV_DMA_OPS
 	select ARCH_HAS_SYSCALL_WRAPPER
 
 #
@@ -65,6 +65,7 @@ config X86
 	select ARCH_HAS_UACCESS_FLUSHCACHE	if X86_64
 	select ARCH_HAS_UACCESS_MCSAFE		if X86_64 && X86_MCE
 	select ARCH_HAS_SET_MEMORY
+	select ARCH_HAS_SET_DIRECT_MAP
 	select ARCH_HAS_STRICT_KERNEL_RWX
 	select ARCH_HAS_STRICT_MODULE_RWX
 	select ARCH_HAS_SYNC_CORE_BEFORE_USERMODE
@@ -74,6 +75,7 @@ config X86
 	select ARCH_MIGHT_HAVE_ACPI_PDC		if ACPI
 	select ARCH_MIGHT_HAVE_PC_PARPORT
 	select ARCH_MIGHT_HAVE_PC_SERIO
+	select ARCH_STACKWALK
 	select ARCH_SUPPORTS_ACPI
 	select ARCH_SUPPORTS_ATOMIC_RMW
 	select ARCH_SUPPORTS_NUMA_BALANCING	if X86_64
@@ -138,7 +140,6 @@ config X86
 	select HAVE_COPY_THREAD_TLS
 	select HAVE_C_RECORDMCOUNT
 	select HAVE_DEBUG_KMEMLEAK
-	select HAVE_DEBUG_STACKOVERFLOW
 	select HAVE_DMA_CONTIGUOUS
 	select HAVE_DYNAMIC_FTRACE
 	select HAVE_DYNAMIC_FTRACE_WITH_REGS
@@ -183,7 +184,6 @@ config X86
 	select HAVE_PERF_REGS
 	select HAVE_PERF_USER_STACK_DUMP
 	select HAVE_RCU_TABLE_FREE		if PARAVIRT
-	select HAVE_RCU_TABLE_INVALIDATE	if HAVE_RCU_TABLE_FREE
 	select HAVE_REGS_AND_STACK_ACCESS_API
 	select HAVE_RELIABLE_STACKTRACE		if X86_64 && (UNWINDER_FRAME_POINTER || UNWINDER_ORC) && STACK_VALIDATION
 	select HAVE_FUNCTION_ARG_ACCESS_API
@@ -268,9 +268,6 @@ config ARCH_MAY_HAVE_PC_FDC
 	def_bool y
 	depends on ISA_DMA_API
 
-config RWSEM_XCHGADD_ALGORITHM
-	def_bool y
-
 config GENERIC_CALIBRATE_DELAY
 	def_bool y
 
@@ -703,8 +700,6 @@ config STA2X11
 	bool "STA2X11 Companion Chip Support"
 	depends on X86_32_NON_STANDARD && PCI
 	select ARCH_HAS_PHYS_TO_DMA
-	select X86_DEV_DMA_OPS
-	select X86_DMA_REMAP
 	select SWIOTLB
 	select MFD_STA2X11
 	select GPIOLIB
@@ -783,14 +778,6 @@ config PARAVIRT_SPINLOCKS
 
 	  If you are unsure how to answer this question, answer Y.
 
-config QUEUED_LOCK_STAT
-	bool "Paravirt queued spinlock statistics"
-	depends on PARAVIRT_SPINLOCKS && DEBUG_FS
-	---help---
-	  Enable the collection of statistical data on the slowpath
-	  behavior of paravirtualized queued spinlocks and report
-	  them on debugfs.
-
 source "arch/x86/xen/Kconfig"
 
 config KVM_GUEST
@@ -1330,8 +1317,16 @@ config MICROCODE_AMD
 	  processors will be enabled.
 
 config MICROCODE_OLD_INTERFACE
-	def_bool y
+	bool "Ancient loading interface (DEPRECATED)"
+	default n
 	depends on MICROCODE
+	---help---
+	  DO NOT USE THIS! This is the ancient /dev/cpu/microcode interface
+	  which was used by userspace tools like iucode_tool and microcode.ctl.
+	  It is inadequate because it runs too late to be able to properly
+	  load microcode on a machine and it needs special tools. Instead, you
+	  should've switched to the early loading method with the initrd or
+	  builtin microcode by now: Documentation/x86/microcode.txt
 
 config X86_MSR
 	tristate "/dev/cpu/*/msr - Model-specific register support"
@@ -1499,7 +1494,7 @@ config X86_CPA_STATISTICS
 	depends on DEBUG_FS
 	---help---
 	  Expose statistics about the Change Page Attribute mechanims, which
-	  helps to determine the effectivness of preserving large and huge
+	  helps to determine the effectiveness of preserving large and huge
 	  page mappings when mapping protections are changed.
 
 config ARCH_HAS_MEM_ENCRYPT
@@ -1606,12 +1601,9 @@ config ARCH_FLATMEM_ENABLE
 	depends on X86_32 && !NUMA
 
 config ARCH_DISCONTIGMEM_ENABLE
-	def_bool y
-	depends on NUMA && X86_32
-
-config ARCH_DISCONTIGMEM_DEFAULT
-	def_bool y
+	def_bool n
 	depends on NUMA && X86_32
+	depends on BROKEN
 
 config ARCH_SPARSEMEM_ENABLE
 	def_bool y
@@ -1620,8 +1612,7 @@ config ARCH_SPARSEMEM_ENABLE
 	select SPARSEMEM_VMEMMAP_ENABLE if X86_64
 
 config ARCH_SPARSEMEM_DEFAULT
-	def_bool y
-	depends on X86_64
+	def_bool X86_64 || (NUMA && X86_32)
 
 config ARCH_SELECT_MEMORY_MODEL
 	def_bool y
@@ -2217,14 +2208,8 @@ config RANDOMIZE_MEMORY_PHYSICAL_PADDING
 	   If unsure, leave at the default value.
 
 config HOTPLUG_CPU
-	bool "Support for hot-pluggable CPUs"
+	def_bool y
 	depends on SMP
-	---help---
-	  Say Y here to allow turning CPUs off and on. CPUs can be
-	  controlled through /sys/devices/system/cpu.
-	  ( Note: power management support will enable this option
-	    automatically on SMP systems. )
-	  Say N if you want to disable CPU hotplug.
 
 config BOOTPARAM_HOTPLUG_CPU0
 	bool "Set default setting of cpu0_hotpluggable"
@@ -2884,11 +2869,6 @@ config HAVE_ATOMIC_IOMAP
 
 config X86_DEV_DMA_OPS
 	bool
-	depends on X86_64 || STA2X11
-
-config X86_DMA_REMAP
-	bool
-	depends on STA2X11
 
 config HAVE_GENERIC_GUP
 	def_bool y
diff --git a/arch/x86/Makefile b/arch/x86/Makefile
index 2d8b9d8ca4f8..56e748a7679f 100644
--- a/arch/x86/Makefile
+++ b/arch/x86/Makefile
@@ -47,7 +47,7 @@ export REALMODE_CFLAGS
 export BITS
 
 ifdef CONFIG_X86_NEED_RELOCS
-        LDFLAGS_vmlinux := --emit-relocs
+        LDFLAGS_vmlinux := --emit-relocs --discard-none
 endif
 
 #
@@ -219,8 +219,12 @@ ifdef CONFIG_RETPOLINE
   # Additionally, avoid generating expensive indirect jumps which
   # are subject to retpolines for small number of switch cases.
   # clang turns off jump table generation by default when under
-  # retpoline builds, however, gcc does not for x86.
-  KBUILD_CFLAGS += $(call cc-option,--param=case-values-threshold=20)
+  # retpoline builds, however, gcc does not for x86. This has
+  # only been fixed starting from gcc stable version 8.4.0 and
+  # onwards, but not for older ones. See gcc bug #86952.
+  ifndef CONFIG_CC_IS_CLANG
+    KBUILD_CFLAGS += $(call cc-option,-fno-jump-tables)
+  endif
 endif
 
 archscripts: scripts_basic
diff --git a/arch/x86/boot/compressed/acpi.c b/arch/x86/boot/compressed/acpi.c
index 0ef4ad55b29b..ad84239e595e 100644
--- a/arch/x86/boot/compressed/acpi.c
+++ b/arch/x86/boot/compressed/acpi.c
@@ -276,7 +276,7 @@ static unsigned long get_acpi_srat_table(void)
 		if (acpi_table) {
 			header = (struct acpi_table_header *)acpi_table;
 
-			if (ACPI_COMPARE_NAME(header->signature, ACPI_SIG_SRAT))
+			if (ACPI_COMPARE_NAMESEG(header->signature, ACPI_SIG_SRAT))
 				return acpi_table;
 		}
 		entry += size;
diff --git a/arch/x86/boot/compressed/misc.c b/arch/x86/boot/compressed/misc.c
index c0d6c560df69..5a237e8dbf8d 100644
--- a/arch/x86/boot/compressed/misc.c
+++ b/arch/x86/boot/compressed/misc.c
@@ -352,7 +352,7 @@ asmlinkage __visible void *extract_kernel(void *rmode, memptr heap,
 	boot_params->hdr.loadflags &= ~KASLR_FLAG;
 
 	/* Save RSDP address for later use. */
-	boot_params->acpi_rsdp_addr = get_rsdp_addr();
+	/* boot_params->acpi_rsdp_addr = get_rsdp_addr(); */
 
 	sanitize_boot_params(boot_params);
 
diff --git a/arch/x86/boot/compressed/misc.h b/arch/x86/boot/compressed/misc.h
index fd13655e0f9b..d2f184165934 100644
--- a/arch/x86/boot/compressed/misc.h
+++ b/arch/x86/boot/compressed/misc.h
@@ -120,8 +120,6 @@ static inline void console_init(void)
 
 void set_sev_encryption_mask(void);
 
-#endif
-
 /* acpi.c */
 #ifdef CONFIG_ACPI
 acpi_physical_address get_rsdp_addr(void);
@@ -135,3 +133,5 @@ int count_immovable_mem_regions(void);
 #else
 static inline int count_immovable_mem_regions(void) { return 0; }
 #endif
+
+#endif /* BOOT_COMPRESSED_MISC_H */
diff --git a/arch/x86/configs/i386_defconfig b/arch/x86/configs/i386_defconfig
index 9f908112bbb9..2b2481acc661 100644
--- a/arch/x86/configs/i386_defconfig
+++ b/arch/x86/configs/i386_defconfig
@@ -25,18 +25,6 @@ CONFIG_JUMP_LABEL=y
 CONFIG_MODULES=y
 CONFIG_MODULE_UNLOAD=y
 CONFIG_MODULE_FORCE_UNLOAD=y
-CONFIG_PARTITION_ADVANCED=y
-CONFIG_OSF_PARTITION=y
-CONFIG_AMIGA_PARTITION=y
-CONFIG_MAC_PARTITION=y
-CONFIG_BSD_DISKLABEL=y
-CONFIG_MINIX_SUBPARTITION=y
-CONFIG_SOLARIS_X86_PARTITION=y
-CONFIG_UNIXWARE_DISKLABEL=y
-CONFIG_SGI_PARTITION=y
-CONFIG_SUN_PARTITION=y
-CONFIG_KARMA_PARTITION=y
-CONFIG_EFI_PARTITION=y
 CONFIG_SMP=y
 CONFIG_X86_GENERIC=y
 CONFIG_HPET_TIMER=y
diff --git a/arch/x86/configs/x86_64_defconfig b/arch/x86/configs/x86_64_defconfig
index 1d3badfda09e..e8829abf063a 100644
--- a/arch/x86/configs/x86_64_defconfig
+++ b/arch/x86/configs/x86_64_defconfig
@@ -24,18 +24,6 @@ CONFIG_JUMP_LABEL=y
 CONFIG_MODULES=y
 CONFIG_MODULE_UNLOAD=y
 CONFIG_MODULE_FORCE_UNLOAD=y
-CONFIG_PARTITION_ADVANCED=y
-CONFIG_OSF_PARTITION=y
-CONFIG_AMIGA_PARTITION=y
-CONFIG_MAC_PARTITION=y
-CONFIG_BSD_DISKLABEL=y
-CONFIG_MINIX_SUBPARTITION=y
-CONFIG_SOLARIS_X86_PARTITION=y
-CONFIG_UNIXWARE_DISKLABEL=y
-CONFIG_SGI_PARTITION=y
-CONFIG_SUN_PARTITION=y
-CONFIG_KARMA_PARTITION=y
-CONFIG_EFI_PARTITION=y
 CONFIG_SMP=y
 CONFIG_CALGARY_IOMMU=y
 CONFIG_NR_CPUS=64
diff --git a/arch/x86/crypto/aegis128-aesni-glue.c b/arch/x86/crypto/aegis128-aesni-glue.c
index 3ea71b871813..bdeee1b830be 100644
--- a/arch/x86/crypto/aegis128-aesni-glue.c
+++ b/arch/x86/crypto/aegis128-aesni-glue.c
@@ -11,8 +11,8 @@
  * any later version.
  */
 
-#include <crypto/cryptd.h>
 #include <crypto/internal/aead.h>
+#include <crypto/internal/simd.h>
 #include <crypto/internal/skcipher.h>
 #include <crypto/scatterwalk.h>
 #include <linux/module.h>
@@ -242,131 +242,35 @@ static void crypto_aegis128_aesni_exit_tfm(struct crypto_aead *aead)
 {
 }
 
-static int cryptd_aegis128_aesni_setkey(struct crypto_aead *aead,
-					const u8 *key, unsigned int keylen)
-{
-	struct cryptd_aead **ctx = crypto_aead_ctx(aead);
-	struct cryptd_aead *cryptd_tfm = *ctx;
-
-	return crypto_aead_setkey(&cryptd_tfm->base, key, keylen);
-}
-
-static int cryptd_aegis128_aesni_setauthsize(struct crypto_aead *aead,
-					     unsigned int authsize)
-{
-	struct cryptd_aead **ctx = crypto_aead_ctx(aead);
-	struct cryptd_aead *cryptd_tfm = *ctx;
-
-	return crypto_aead_setauthsize(&cryptd_tfm->base, authsize);
-}
-
-static int cryptd_aegis128_aesni_encrypt(struct aead_request *req)
-{
-	struct crypto_aead *aead = crypto_aead_reqtfm(req);
-	struct cryptd_aead **ctx = crypto_aead_ctx(aead);
-	struct cryptd_aead *cryptd_tfm = *ctx;
-
-	aead = &cryptd_tfm->base;
-	if (irq_fpu_usable() && (!in_atomic() ||
-				 !cryptd_aead_queued(cryptd_tfm)))
-		aead = cryptd_aead_child(cryptd_tfm);
-
-	aead_request_set_tfm(req, aead);
-
-	return crypto_aead_encrypt(req);
-}
-
-static int cryptd_aegis128_aesni_decrypt(struct aead_request *req)
-{
-	struct crypto_aead *aead = crypto_aead_reqtfm(req);
-	struct cryptd_aead **ctx = crypto_aead_ctx(aead);
-	struct cryptd_aead *cryptd_tfm = *ctx;
-
-	aead = &cryptd_tfm->base;
-	if (irq_fpu_usable() && (!in_atomic() ||
-				 !cryptd_aead_queued(cryptd_tfm)))
-		aead = cryptd_aead_child(cryptd_tfm);
-
-	aead_request_set_tfm(req, aead);
-
-	return crypto_aead_decrypt(req);
-}
-
-static int cryptd_aegis128_aesni_init_tfm(struct crypto_aead *aead)
-{
-	struct cryptd_aead *cryptd_tfm;
-	struct cryptd_aead **ctx = crypto_aead_ctx(aead);
-
-	cryptd_tfm = cryptd_alloc_aead("__aegis128-aesni", CRYPTO_ALG_INTERNAL,
-				       CRYPTO_ALG_INTERNAL);
-	if (IS_ERR(cryptd_tfm))
-		return PTR_ERR(cryptd_tfm);
-
-	*ctx = cryptd_tfm;
-	crypto_aead_set_reqsize(aead, crypto_aead_reqsize(&cryptd_tfm->base));
-	return 0;
-}
-
-static void cryptd_aegis128_aesni_exit_tfm(struct crypto_aead *aead)
-{
-	struct cryptd_aead **ctx = crypto_aead_ctx(aead);
-
-	cryptd_free_aead(*ctx);
-}
-
-static struct aead_alg crypto_aegis128_aesni_alg[] = {
-	{
-		.setkey = crypto_aegis128_aesni_setkey,
-		.setauthsize = crypto_aegis128_aesni_setauthsize,
-		.encrypt = crypto_aegis128_aesni_encrypt,
-		.decrypt = crypto_aegis128_aesni_decrypt,
-		.init = crypto_aegis128_aesni_init_tfm,
-		.exit = crypto_aegis128_aesni_exit_tfm,
-
-		.ivsize = AEGIS128_NONCE_SIZE,
-		.maxauthsize = AEGIS128_MAX_AUTH_SIZE,
-		.chunksize = AEGIS128_BLOCK_SIZE,
-
-		.base = {
-			.cra_flags = CRYPTO_ALG_INTERNAL,
-			.cra_blocksize = 1,
-			.cra_ctxsize = sizeof(struct aegis_ctx) +
-				__alignof__(struct aegis_ctx),
-			.cra_alignmask = 0,
-
-			.cra_name = "__aegis128",
-			.cra_driver_name = "__aegis128-aesni",
-
-			.cra_module = THIS_MODULE,
-		}
-	}, {
-		.setkey = cryptd_aegis128_aesni_setkey,
-		.setauthsize = cryptd_aegis128_aesni_setauthsize,
-		.encrypt = cryptd_aegis128_aesni_encrypt,
-		.decrypt = cryptd_aegis128_aesni_decrypt,
-		.init = cryptd_aegis128_aesni_init_tfm,
-		.exit = cryptd_aegis128_aesni_exit_tfm,
-
-		.ivsize = AEGIS128_NONCE_SIZE,
-		.maxauthsize = AEGIS128_MAX_AUTH_SIZE,
-		.chunksize = AEGIS128_BLOCK_SIZE,
-
-		.base = {
-			.cra_flags = CRYPTO_ALG_ASYNC,
-			.cra_blocksize = 1,
-			.cra_ctxsize = sizeof(struct cryptd_aead *),
-			.cra_alignmask = 0,
-
-			.cra_priority = 400,
-
-			.cra_name = "aegis128",
-			.cra_driver_name = "aegis128-aesni",
-
-			.cra_module = THIS_MODULE,
-		}
+static struct aead_alg crypto_aegis128_aesni_alg = {
+	.setkey = crypto_aegis128_aesni_setkey,
+	.setauthsize = crypto_aegis128_aesni_setauthsize,
+	.encrypt = crypto_aegis128_aesni_encrypt,
+	.decrypt = crypto_aegis128_aesni_decrypt,
+	.init = crypto_aegis128_aesni_init_tfm,
+	.exit = crypto_aegis128_aesni_exit_tfm,
+
+	.ivsize = AEGIS128_NONCE_SIZE,
+	.maxauthsize = AEGIS128_MAX_AUTH_SIZE,
+	.chunksize = AEGIS128_BLOCK_SIZE,
+
+	.base = {
+		.cra_flags = CRYPTO_ALG_INTERNAL,
+		.cra_blocksize = 1,
+		.cra_ctxsize = sizeof(struct aegis_ctx) +
+			       __alignof__(struct aegis_ctx),
+		.cra_alignmask = 0,
+		.cra_priority = 400,
+
+		.cra_name = "__aegis128",
+		.cra_driver_name = "__aegis128-aesni",
+
+		.cra_module = THIS_MODULE,
 	}
 };
 
+static struct simd_aead_alg *simd_alg;
+
 static int __init crypto_aegis128_aesni_module_init(void)
 {
 	if (!boot_cpu_has(X86_FEATURE_XMM2) ||
@@ -374,14 +278,13 @@ static int __init crypto_aegis128_aesni_module_init(void)
 	    !cpu_has_xfeatures(XFEATURE_MASK_SSE, NULL))
 		return -ENODEV;
 
-	return crypto_register_aeads(crypto_aegis128_aesni_alg,
-				     ARRAY_SIZE(crypto_aegis128_aesni_alg));
+	return simd_register_aeads_compat(&crypto_aegis128_aesni_alg, 1,
+					  &simd_alg);
 }
 
 static void __exit crypto_aegis128_aesni_module_exit(void)
 {
-	crypto_unregister_aeads(crypto_aegis128_aesni_alg,
-				ARRAY_SIZE(crypto_aegis128_aesni_alg));
+	simd_unregister_aeads(&crypto_aegis128_aesni_alg, 1, &simd_alg);
 }
 
 module_init(crypto_aegis128_aesni_module_init);
diff --git a/arch/x86/crypto/aegis128l-aesni-glue.c b/arch/x86/crypto/aegis128l-aesni-glue.c
index 1b1b39c66c5e..80d917f7e467 100644
--- a/arch/x86/crypto/aegis128l-aesni-glue.c
+++ b/arch/x86/crypto/aegis128l-aesni-glue.c
@@ -11,8 +11,8 @@
  * any later version.
  */
 
-#include <crypto/cryptd.h>
 #include <crypto/internal/aead.h>
+#include <crypto/internal/simd.h>
 #include <crypto/internal/skcipher.h>
 #include <crypto/scatterwalk.h>
 #include <linux/module.h>
@@ -242,131 +242,35 @@ static void crypto_aegis128l_aesni_exit_tfm(struct crypto_aead *aead)
 {
 }
 
-static int cryptd_aegis128l_aesni_setkey(struct crypto_aead *aead,
-					 const u8 *key, unsigned int keylen)
-{
-	struct cryptd_aead **ctx = crypto_aead_ctx(aead);
-	struct cryptd_aead *cryptd_tfm = *ctx;
-
-	return crypto_aead_setkey(&cryptd_tfm->base, key, keylen);
-}
-
-static int cryptd_aegis128l_aesni_setauthsize(struct crypto_aead *aead,
-					      unsigned int authsize)
-{
-	struct cryptd_aead **ctx = crypto_aead_ctx(aead);
-	struct cryptd_aead *cryptd_tfm = *ctx;
-
-	return crypto_aead_setauthsize(&cryptd_tfm->base, authsize);
-}
-
-static int cryptd_aegis128l_aesni_encrypt(struct aead_request *req)
-{
-	struct crypto_aead *aead = crypto_aead_reqtfm(req);
-	struct cryptd_aead **ctx = crypto_aead_ctx(aead);
-	struct cryptd_aead *cryptd_tfm = *ctx;
-
-	aead = &cryptd_tfm->base;
-	if (irq_fpu_usable() && (!in_atomic() ||
-				 !cryptd_aead_queued(cryptd_tfm)))
-		aead = cryptd_aead_child(cryptd_tfm);
-
-	aead_request_set_tfm(req, aead);
-
-	return crypto_aead_encrypt(req);
-}
-
-static int cryptd_aegis128l_aesni_decrypt(struct aead_request *req)
-{
-	struct crypto_aead *aead = crypto_aead_reqtfm(req);
-	struct cryptd_aead **ctx = crypto_aead_ctx(aead);
-	struct cryptd_aead *cryptd_tfm = *ctx;
-
-	aead = &cryptd_tfm->base;
-	if (irq_fpu_usable() && (!in_atomic() ||
-				 !cryptd_aead_queued(cryptd_tfm)))
-		aead = cryptd_aead_child(cryptd_tfm);
-
-	aead_request_set_tfm(req, aead);
-
-	return crypto_aead_decrypt(req);
-}
-
-static int cryptd_aegis128l_aesni_init_tfm(struct crypto_aead *aead)
-{
-	struct cryptd_aead *cryptd_tfm;
-	struct cryptd_aead **ctx = crypto_aead_ctx(aead);
-
-	cryptd_tfm = cryptd_alloc_aead("__aegis128l-aesni", CRYPTO_ALG_INTERNAL,
-				       CRYPTO_ALG_INTERNAL);
-	if (IS_ERR(cryptd_tfm))
-		return PTR_ERR(cryptd_tfm);
-
-	*ctx = cryptd_tfm;
-	crypto_aead_set_reqsize(aead, crypto_aead_reqsize(&cryptd_tfm->base));
-	return 0;
-}
-
-static void cryptd_aegis128l_aesni_exit_tfm(struct crypto_aead *aead)
-{
-	struct cryptd_aead **ctx = crypto_aead_ctx(aead);
-
-	cryptd_free_aead(*ctx);
-}
-
-static struct aead_alg crypto_aegis128l_aesni_alg[] = {
-	{
-		.setkey = crypto_aegis128l_aesni_setkey,
-		.setauthsize = crypto_aegis128l_aesni_setauthsize,
-		.encrypt = crypto_aegis128l_aesni_encrypt,
-		.decrypt = crypto_aegis128l_aesni_decrypt,
-		.init = crypto_aegis128l_aesni_init_tfm,
-		.exit = crypto_aegis128l_aesni_exit_tfm,
-
-		.ivsize = AEGIS128L_NONCE_SIZE,
-		.maxauthsize = AEGIS128L_MAX_AUTH_SIZE,
-		.chunksize = AEGIS128L_BLOCK_SIZE,
-
-		.base = {
-			.cra_flags = CRYPTO_ALG_INTERNAL,
-			.cra_blocksize = 1,
-			.cra_ctxsize = sizeof(struct aegis_ctx) +
-				__alignof__(struct aegis_ctx),
-			.cra_alignmask = 0,
-
-			.cra_name = "__aegis128l",
-			.cra_driver_name = "__aegis128l-aesni",
-
-			.cra_module = THIS_MODULE,
-		}
-	}, {
-		.setkey = cryptd_aegis128l_aesni_setkey,
-		.setauthsize = cryptd_aegis128l_aesni_setauthsize,
-		.encrypt = cryptd_aegis128l_aesni_encrypt,
-		.decrypt = cryptd_aegis128l_aesni_decrypt,
-		.init = cryptd_aegis128l_aesni_init_tfm,
-		.exit = cryptd_aegis128l_aesni_exit_tfm,
-
-		.ivsize = AEGIS128L_NONCE_SIZE,
-		.maxauthsize = AEGIS128L_MAX_AUTH_SIZE,
-		.chunksize = AEGIS128L_BLOCK_SIZE,
-
-		.base = {
-			.cra_flags = CRYPTO_ALG_ASYNC,
-			.cra_blocksize = 1,
-			.cra_ctxsize = sizeof(struct cryptd_aead *),
-			.cra_alignmask = 0,
-
-			.cra_priority = 400,
-
-			.cra_name = "aegis128l",
-			.cra_driver_name = "aegis128l-aesni",
-
-			.cra_module = THIS_MODULE,
-		}
+static struct aead_alg crypto_aegis128l_aesni_alg = {
+	.setkey = crypto_aegis128l_aesni_setkey,
+	.setauthsize = crypto_aegis128l_aesni_setauthsize,
+	.encrypt = crypto_aegis128l_aesni_encrypt,
+	.decrypt = crypto_aegis128l_aesni_decrypt,
+	.init = crypto_aegis128l_aesni_init_tfm,
+	.exit = crypto_aegis128l_aesni_exit_tfm,
+
+	.ivsize = AEGIS128L_NONCE_SIZE,
+	.maxauthsize = AEGIS128L_MAX_AUTH_SIZE,
+	.chunksize = AEGIS128L_BLOCK_SIZE,
+
+	.base = {
+		.cra_flags = CRYPTO_ALG_INTERNAL,
+		.cra_blocksize = 1,
+		.cra_ctxsize = sizeof(struct aegis_ctx) +
+			       __alignof__(struct aegis_ctx),
+		.cra_alignmask = 0,
+		.cra_priority = 400,
+
+		.cra_name = "__aegis128l",
+		.cra_driver_name = "__aegis128l-aesni",
+
+		.cra_module = THIS_MODULE,
 	}
 };
 
+static struct simd_aead_alg *simd_alg;
+
 static int __init crypto_aegis128l_aesni_module_init(void)
 {
 	if (!boot_cpu_has(X86_FEATURE_XMM2) ||
@@ -374,14 +278,13 @@ static int __init crypto_aegis128l_aesni_module_init(void)
 	    !cpu_has_xfeatures(XFEATURE_MASK_SSE, NULL))
 		return -ENODEV;
 
-	return crypto_register_aeads(crypto_aegis128l_aesni_alg,
-				     ARRAY_SIZE(crypto_aegis128l_aesni_alg));
+	return simd_register_aeads_compat(&crypto_aegis128l_aesni_alg, 1,
+					  &simd_alg);
 }
 
 static void __exit crypto_aegis128l_aesni_module_exit(void)
 {
-	crypto_unregister_aeads(crypto_aegis128l_aesni_alg,
-				ARRAY_SIZE(crypto_aegis128l_aesni_alg));
+	simd_unregister_aeads(&crypto_aegis128l_aesni_alg, 1, &simd_alg);
 }
 
 module_init(crypto_aegis128l_aesni_module_init);
diff --git a/arch/x86/crypto/aegis256-aesni-glue.c b/arch/x86/crypto/aegis256-aesni-glue.c
index 6227ca3220a0..716eecb66bd5 100644
--- a/arch/x86/crypto/aegis256-aesni-glue.c
+++ b/arch/x86/crypto/aegis256-aesni-glue.c
@@ -11,8 +11,8 @@
  * any later version.
  */
 
-#include <crypto/cryptd.h>
 #include <crypto/internal/aead.h>
+#include <crypto/internal/simd.h>
 #include <crypto/internal/skcipher.h>
 #include <crypto/scatterwalk.h>
 #include <linux/module.h>
@@ -242,131 +242,35 @@ static void crypto_aegis256_aesni_exit_tfm(struct crypto_aead *aead)
 {
 }
 
-static int cryptd_aegis256_aesni_setkey(struct crypto_aead *aead,
-					const u8 *key, unsigned int keylen)
-{
-	struct cryptd_aead **ctx = crypto_aead_ctx(aead);
-	struct cryptd_aead *cryptd_tfm = *ctx;
-
-	return crypto_aead_setkey(&cryptd_tfm->base, key, keylen);
-}
-
-static int cryptd_aegis256_aesni_setauthsize(struct crypto_aead *aead,
-					     unsigned int authsize)
-{
-	struct cryptd_aead **ctx = crypto_aead_ctx(aead);
-	struct cryptd_aead *cryptd_tfm = *ctx;
-
-	return crypto_aead_setauthsize(&cryptd_tfm->base, authsize);
-}
-
-static int cryptd_aegis256_aesni_encrypt(struct aead_request *req)
-{
-	struct crypto_aead *aead = crypto_aead_reqtfm(req);
-	struct cryptd_aead **ctx = crypto_aead_ctx(aead);
-	struct cryptd_aead *cryptd_tfm = *ctx;
-
-	aead = &cryptd_tfm->base;
-	if (irq_fpu_usable() && (!in_atomic() ||
-				 !cryptd_aead_queued(cryptd_tfm)))
-		aead = cryptd_aead_child(cryptd_tfm);
-
-	aead_request_set_tfm(req, aead);
-
-	return crypto_aead_encrypt(req);
-}
-
-static int cryptd_aegis256_aesni_decrypt(struct aead_request *req)
-{
-	struct crypto_aead *aead = crypto_aead_reqtfm(req);
-	struct cryptd_aead **ctx = crypto_aead_ctx(aead);
-	struct cryptd_aead *cryptd_tfm = *ctx;
-
-	aead = &cryptd_tfm->base;
-	if (irq_fpu_usable() && (!in_atomic() ||
-				 !cryptd_aead_queued(cryptd_tfm)))
-		aead = cryptd_aead_child(cryptd_tfm);
-
-	aead_request_set_tfm(req, aead);
-
-	return crypto_aead_decrypt(req);
-}
-
-static int cryptd_aegis256_aesni_init_tfm(struct crypto_aead *aead)
-{
-	struct cryptd_aead *cryptd_tfm;
-	struct cryptd_aead **ctx = crypto_aead_ctx(aead);
-
-	cryptd_tfm = cryptd_alloc_aead("__aegis256-aesni", CRYPTO_ALG_INTERNAL,
-				       CRYPTO_ALG_INTERNAL);
-	if (IS_ERR(cryptd_tfm))
-		return PTR_ERR(cryptd_tfm);
-
-	*ctx = cryptd_tfm;
-	crypto_aead_set_reqsize(aead, crypto_aead_reqsize(&cryptd_tfm->base));
-	return 0;
-}
-
-static void cryptd_aegis256_aesni_exit_tfm(struct crypto_aead *aead)
-{
-	struct cryptd_aead **ctx = crypto_aead_ctx(aead);
-
-	cryptd_free_aead(*ctx);
-}
-
-static struct aead_alg crypto_aegis256_aesni_alg[] = {
-	{
-		.setkey = crypto_aegis256_aesni_setkey,
-		.setauthsize = crypto_aegis256_aesni_setauthsize,
-		.encrypt = crypto_aegis256_aesni_encrypt,
-		.decrypt = crypto_aegis256_aesni_decrypt,
-		.init = crypto_aegis256_aesni_init_tfm,
-		.exit = crypto_aegis256_aesni_exit_tfm,
-
-		.ivsize = AEGIS256_NONCE_SIZE,
-		.maxauthsize = AEGIS256_MAX_AUTH_SIZE,
-		.chunksize = AEGIS256_BLOCK_SIZE,
-
-		.base = {
-			.cra_flags = CRYPTO_ALG_INTERNAL,
-			.cra_blocksize = 1,
-			.cra_ctxsize = sizeof(struct aegis_ctx) +
-				__alignof__(struct aegis_ctx),
-			.cra_alignmask = 0,
-
-			.cra_name = "__aegis256",
-			.cra_driver_name = "__aegis256-aesni",
-
-			.cra_module = THIS_MODULE,
-		}
-	}, {
-		.setkey = cryptd_aegis256_aesni_setkey,
-		.setauthsize = cryptd_aegis256_aesni_setauthsize,
-		.encrypt = cryptd_aegis256_aesni_encrypt,
-		.decrypt = cryptd_aegis256_aesni_decrypt,
-		.init = cryptd_aegis256_aesni_init_tfm,
-		.exit = cryptd_aegis256_aesni_exit_tfm,
-
-		.ivsize = AEGIS256_NONCE_SIZE,
-		.maxauthsize = AEGIS256_MAX_AUTH_SIZE,
-		.chunksize = AEGIS256_BLOCK_SIZE,
-
-		.base = {
-			.cra_flags = CRYPTO_ALG_ASYNC,
-			.cra_blocksize = 1,
-			.cra_ctxsize = sizeof(struct cryptd_aead *),
-			.cra_alignmask = 0,
-
-			.cra_priority = 400,
-
-			.cra_name = "aegis256",
-			.cra_driver_name = "aegis256-aesni",
-
-			.cra_module = THIS_MODULE,
-		}
+static struct aead_alg crypto_aegis256_aesni_alg = {
+	.setkey = crypto_aegis256_aesni_setkey,
+	.setauthsize = crypto_aegis256_aesni_setauthsize,
+	.encrypt = crypto_aegis256_aesni_encrypt,
+	.decrypt = crypto_aegis256_aesni_decrypt,
+	.init = crypto_aegis256_aesni_init_tfm,
+	.exit = crypto_aegis256_aesni_exit_tfm,
+
+	.ivsize = AEGIS256_NONCE_SIZE,
+	.maxauthsize = AEGIS256_MAX_AUTH_SIZE,
+	.chunksize = AEGIS256_BLOCK_SIZE,
+
+	.base = {
+		.cra_flags = CRYPTO_ALG_INTERNAL,
+		.cra_blocksize = 1,
+		.cra_ctxsize = sizeof(struct aegis_ctx) +
+			       __alignof__(struct aegis_ctx),
+		.cra_alignmask = 0,
+		.cra_priority = 400,
+
+		.cra_name = "__aegis256",
+		.cra_driver_name = "__aegis256-aesni",
+
+		.cra_module = THIS_MODULE,
 	}
 };
 
+static struct simd_aead_alg *simd_alg;
+
 static int __init crypto_aegis256_aesni_module_init(void)
 {
 	if (!boot_cpu_has(X86_FEATURE_XMM2) ||
@@ -374,14 +278,13 @@ static int __init crypto_aegis256_aesni_module_init(void)
 	    !cpu_has_xfeatures(XFEATURE_MASK_SSE, NULL))
 		return -ENODEV;
 
-	return crypto_register_aeads(crypto_aegis256_aesni_alg,
-				    ARRAY_SIZE(crypto_aegis256_aesni_alg));
+	return simd_register_aeads_compat(&crypto_aegis256_aesni_alg, 1,
+					  &simd_alg);
 }
 
 static void __exit crypto_aegis256_aesni_module_exit(void)
 {
-	crypto_unregister_aeads(crypto_aegis256_aesni_alg,
-				ARRAY_SIZE(crypto_aegis256_aesni_alg));
+	simd_unregister_aeads(&crypto_aegis256_aesni_alg, 1, &simd_alg);
 }
 
 module_init(crypto_aegis256_aesni_module_init);
diff --git a/arch/x86/crypto/aesni-intel_glue.c b/arch/x86/crypto/aesni-intel_glue.c
index 1e3d2102033a..21c246799aa5 100644
--- a/arch/x86/crypto/aesni-intel_glue.c
+++ b/arch/x86/crypto/aesni-intel_glue.c
@@ -25,14 +25,13 @@
 #include <linux/err.h>
 #include <crypto/algapi.h>
 #include <crypto/aes.h>
-#include <crypto/cryptd.h>
 #include <crypto/ctr.h>
 #include <crypto/b128ops.h>
 #include <crypto/gcm.h>
 #include <crypto/xts.h>
 #include <asm/cpu_device_id.h>
-#include <asm/fpu/api.h>
 #include <asm/crypto/aes.h>
+#include <asm/simd.h>
 #include <crypto/scatterwalk.h>
 #include <crypto/internal/aead.h>
 #include <crypto/internal/simd.h>
@@ -333,7 +332,7 @@ static int aes_set_key_common(struct crypto_tfm *tfm, void *raw_ctx,
 		return -EINVAL;
 	}
 
-	if (!irq_fpu_usable())
+	if (!crypto_simd_usable())
 		err = crypto_aes_expand_key(ctx, in_key, key_len);
 	else {
 		kernel_fpu_begin();
@@ -354,7 +353,7 @@ static void aes_encrypt(struct crypto_tfm *tfm, u8 *dst, const u8 *src)
 {
 	struct crypto_aes_ctx *ctx = aes_ctx(crypto_tfm_ctx(tfm));
 
-	if (!irq_fpu_usable())
+	if (!crypto_simd_usable())
 		crypto_aes_encrypt_x86(ctx, dst, src);
 	else {
 		kernel_fpu_begin();
@@ -367,7 +366,7 @@ static void aes_decrypt(struct crypto_tfm *tfm, u8 *dst, const u8 *src)
 {
 	struct crypto_aes_ctx *ctx = aes_ctx(crypto_tfm_ctx(tfm));
 
-	if (!irq_fpu_usable())
+	if (!crypto_simd_usable())
 		crypto_aes_decrypt_x86(ctx, dst, src);
 	else {
 		kernel_fpu_begin();
@@ -643,29 +642,6 @@ static int xts_decrypt(struct skcipher_request *req)
 				   aes_ctx(ctx->raw_crypt_ctx));
 }
 
-static int rfc4106_init(struct crypto_aead *aead)
-{
-	struct cryptd_aead *cryptd_tfm;
-	struct cryptd_aead **ctx = crypto_aead_ctx(aead);
-
-	cryptd_tfm = cryptd_alloc_aead("__driver-gcm-aes-aesni",
-				       CRYPTO_ALG_INTERNAL,
-				       CRYPTO_ALG_INTERNAL);
-	if (IS_ERR(cryptd_tfm))
-		return PTR_ERR(cryptd_tfm);
-
-	*ctx = cryptd_tfm;
-	crypto_aead_set_reqsize(aead, crypto_aead_reqsize(&cryptd_tfm->base));
-	return 0;
-}
-
-static void rfc4106_exit(struct crypto_aead *aead)
-{
-	struct cryptd_aead **ctx = crypto_aead_ctx(aead);
-
-	cryptd_free_aead(*ctx);
-}
-
 static int
 rfc4106_set_hash_subkey(u8 *hash_subkey, const u8 *key, unsigned int key_len)
 {
@@ -710,15 +686,8 @@ static int common_rfc4106_set_key(struct crypto_aead *aead, const u8 *key,
 	       rfc4106_set_hash_subkey(ctx->hash_subkey, key, key_len);
 }
 
-static int gcmaes_wrapper_set_key(struct crypto_aead *parent, const u8 *key,
-				  unsigned int key_len)
-{
-	struct cryptd_aead **ctx = crypto_aead_ctx(parent);
-	struct cryptd_aead *cryptd_tfm = *ctx;
-
-	return crypto_aead_setkey(&cryptd_tfm->base, key, key_len);
-}
-
+/* This is the Integrity Check Value (aka the authentication tag) length and can
+ * be 8, 12 or 16 bytes long. */
 static int common_rfc4106_set_authsize(struct crypto_aead *aead,
 				       unsigned int authsize)
 {
@@ -734,17 +703,6 @@ static int common_rfc4106_set_authsize(struct crypto_aead *aead,
 	return 0;
 }
 
-/* This is the Integrity Check Value (aka the authentication tag length and can
- * be 8, 12 or 16 bytes long. */
-static int gcmaes_wrapper_set_authsize(struct crypto_aead *parent,
-				       unsigned int authsize)
-{
-	struct cryptd_aead **ctx = crypto_aead_ctx(parent);
-	struct cryptd_aead *cryptd_tfm = *ctx;
-
-	return crypto_aead_setauthsize(&cryptd_tfm->base, authsize);
-}
-
 static int generic_gcmaes_set_authsize(struct crypto_aead *tfm,
 				       unsigned int authsize)
 {
@@ -964,38 +922,6 @@ static int helper_rfc4106_decrypt(struct aead_request *req)
 	return gcmaes_decrypt(req, req->assoclen - 8, ctx->hash_subkey, iv,
 			      aes_ctx);
 }
-
-static int gcmaes_wrapper_encrypt(struct aead_request *req)
-{
-	struct crypto_aead *tfm = crypto_aead_reqtfm(req);
-	struct cryptd_aead **ctx = crypto_aead_ctx(tfm);
-	struct cryptd_aead *cryptd_tfm = *ctx;
-
-	tfm = &cryptd_tfm->base;
-	if (irq_fpu_usable() && (!in_atomic() ||
-				 !cryptd_aead_queued(cryptd_tfm)))
-		tfm = cryptd_aead_child(cryptd_tfm);
-
-	aead_request_set_tfm(req, tfm);
-
-	return crypto_aead_encrypt(req);
-}
-
-static int gcmaes_wrapper_decrypt(struct aead_request *req)
-{
-	struct crypto_aead *tfm = crypto_aead_reqtfm(req);
-	struct cryptd_aead **ctx = crypto_aead_ctx(tfm);
-	struct cryptd_aead *cryptd_tfm = *ctx;
-
-	tfm = &cryptd_tfm->base;
-	if (irq_fpu_usable() && (!in_atomic() ||
-				 !cryptd_aead_queued(cryptd_tfm)))
-		tfm = cryptd_aead_child(cryptd_tfm);
-
-	aead_request_set_tfm(req, tfm);
-
-	return crypto_aead_decrypt(req);
-}
 #endif
 
 static struct crypto_alg aesni_algs[] = { {
@@ -1148,31 +1074,7 @@ static int generic_gcmaes_decrypt(struct aead_request *req)
 			      aes_ctx);
 }
 
-static int generic_gcmaes_init(struct crypto_aead *aead)
-{
-	struct cryptd_aead *cryptd_tfm;
-	struct cryptd_aead **ctx = crypto_aead_ctx(aead);
-
-	cryptd_tfm = cryptd_alloc_aead("__driver-generic-gcm-aes-aesni",
-				       CRYPTO_ALG_INTERNAL,
-				       CRYPTO_ALG_INTERNAL);
-	if (IS_ERR(cryptd_tfm))
-		return PTR_ERR(cryptd_tfm);
-
-	*ctx = cryptd_tfm;
-	crypto_aead_set_reqsize(aead, crypto_aead_reqsize(&cryptd_tfm->base));
-
-	return 0;
-}
-
-static void generic_gcmaes_exit(struct crypto_aead *aead)
-{
-	struct cryptd_aead **ctx = crypto_aead_ctx(aead);
-
-	cryptd_free_aead(*ctx);
-}
-
-static struct aead_alg aesni_aead_algs[] = { {
+static struct aead_alg aesni_aeads[] = { {
 	.setkey			= common_rfc4106_set_key,
 	.setauthsize		= common_rfc4106_set_authsize,
 	.encrypt		= helper_rfc4106_encrypt,
@@ -1180,8 +1082,9 @@ static struct aead_alg aesni_aead_algs[] = { {
 	.ivsize			= GCM_RFC4106_IV_SIZE,
 	.maxauthsize		= 16,
 	.base = {
-		.cra_name		= "__gcm-aes-aesni",
-		.cra_driver_name	= "__driver-gcm-aes-aesni",
+		.cra_name		= "__rfc4106(gcm(aes))",
+		.cra_driver_name	= "__rfc4106-gcm-aesni",
+		.cra_priority		= 400,
 		.cra_flags		= CRYPTO_ALG_INTERNAL,
 		.cra_blocksize		= 1,
 		.cra_ctxsize		= sizeof(struct aesni_rfc4106_gcm_ctx),
@@ -1189,24 +1092,6 @@ static struct aead_alg aesni_aead_algs[] = { {
 		.cra_module		= THIS_MODULE,
 	},
 }, {
-	.init			= rfc4106_init,
-	.exit			= rfc4106_exit,
-	.setkey			= gcmaes_wrapper_set_key,
-	.setauthsize		= gcmaes_wrapper_set_authsize,
-	.encrypt		= gcmaes_wrapper_encrypt,
-	.decrypt		= gcmaes_wrapper_decrypt,
-	.ivsize			= GCM_RFC4106_IV_SIZE,
-	.maxauthsize		= 16,
-	.base = {
-		.cra_name		= "rfc4106(gcm(aes))",
-		.cra_driver_name	= "rfc4106-gcm-aesni",
-		.cra_priority		= 400,
-		.cra_flags		= CRYPTO_ALG_ASYNC,
-		.cra_blocksize		= 1,
-		.cra_ctxsize		= sizeof(struct cryptd_aead *),
-		.cra_module		= THIS_MODULE,
-	},
-}, {
 	.setkey			= generic_gcmaes_set_key,
 	.setauthsize		= generic_gcmaes_set_authsize,
 	.encrypt		= generic_gcmaes_encrypt,
@@ -1214,38 +1099,21 @@ static struct aead_alg aesni_aead_algs[] = { {
 	.ivsize			= GCM_AES_IV_SIZE,
 	.maxauthsize		= 16,
 	.base = {
-		.cra_name		= "__generic-gcm-aes-aesni",
-		.cra_driver_name	= "__driver-generic-gcm-aes-aesni",
-		.cra_priority		= 0,
+		.cra_name		= "__gcm(aes)",
+		.cra_driver_name	= "__generic-gcm-aesni",
+		.cra_priority		= 400,
 		.cra_flags		= CRYPTO_ALG_INTERNAL,
 		.cra_blocksize		= 1,
 		.cra_ctxsize		= sizeof(struct generic_gcmaes_ctx),
 		.cra_alignmask		= AESNI_ALIGN - 1,
 		.cra_module		= THIS_MODULE,
 	},
-}, {
-	.init			= generic_gcmaes_init,
-	.exit			= generic_gcmaes_exit,
-	.setkey			= gcmaes_wrapper_set_key,
-	.setauthsize		= gcmaes_wrapper_set_authsize,
-	.encrypt		= gcmaes_wrapper_encrypt,
-	.decrypt		= gcmaes_wrapper_decrypt,
-	.ivsize			= GCM_AES_IV_SIZE,
-	.maxauthsize		= 16,
-	.base = {
-		.cra_name		= "gcm(aes)",
-		.cra_driver_name	= "generic-gcm-aesni",
-		.cra_priority		= 400,
-		.cra_flags		= CRYPTO_ALG_ASYNC,
-		.cra_blocksize		= 1,
-		.cra_ctxsize		= sizeof(struct cryptd_aead *),
-		.cra_module		= THIS_MODULE,
-	},
 } };
 #else
-static struct aead_alg aesni_aead_algs[0];
+static struct aead_alg aesni_aeads[0];
 #endif
 
+static struct simd_aead_alg *aesni_simd_aeads[ARRAY_SIZE(aesni_aeads)];
 
 static const struct x86_cpu_id aesni_cpu_id[] = {
 	X86_FEATURE_MATCH(X86_FEATURE_AES),
@@ -1253,23 +1121,9 @@ static const struct x86_cpu_id aesni_cpu_id[] = {
 };
 MODULE_DEVICE_TABLE(x86cpu, aesni_cpu_id);
 
-static void aesni_free_simds(void)
-{
-	int i;
-
-	for (i = 0; i < ARRAY_SIZE(aesni_simd_skciphers) &&
-		    aesni_simd_skciphers[i]; i++)
-		simd_skcipher_free(aesni_simd_skciphers[i]);
-}
-
 static int __init aesni_init(void)
 {
-	struct simd_skcipher_alg *simd;
-	const char *basename;
-	const char *algname;
-	const char *drvname;
 	int err;
-	int i;
 
 	if (!x86_match_cpu(aesni_cpu_id))
 		return -ENODEV;
@@ -1304,36 +1158,22 @@ static int __init aesni_init(void)
 	if (err)
 		return err;
 
-	err = crypto_register_skciphers(aesni_skciphers,
-					ARRAY_SIZE(aesni_skciphers));
+	err = simd_register_skciphers_compat(aesni_skciphers,
+					     ARRAY_SIZE(aesni_skciphers),
+					     aesni_simd_skciphers);
 	if (err)
 		goto unregister_algs;
 
-	err = crypto_register_aeads(aesni_aead_algs,
-				    ARRAY_SIZE(aesni_aead_algs));
+	err = simd_register_aeads_compat(aesni_aeads, ARRAY_SIZE(aesni_aeads),
+					 aesni_simd_aeads);
 	if (err)
 		goto unregister_skciphers;
 
-	for (i = 0; i < ARRAY_SIZE(aesni_skciphers); i++) {
-		algname = aesni_skciphers[i].base.cra_name + 2;
-		drvname = aesni_skciphers[i].base.cra_driver_name + 2;
-		basename = aesni_skciphers[i].base.cra_driver_name;
-		simd = simd_skcipher_create_compat(algname, drvname, basename);
-		err = PTR_ERR(simd);
-		if (IS_ERR(simd))
-			goto unregister_simds;
-
-		aesni_simd_skciphers[i] = simd;
-	}
-
 	return 0;
 
-unregister_simds:
-	aesni_free_simds();
-	crypto_unregister_aeads(aesni_aead_algs, ARRAY_SIZE(aesni_aead_algs));
 unregister_skciphers:
-	crypto_unregister_skciphers(aesni_skciphers,
-				    ARRAY_SIZE(aesni_skciphers));
+	simd_unregister_skciphers(aesni_skciphers, ARRAY_SIZE(aesni_skciphers),
+				  aesni_simd_skciphers);
 unregister_algs:
 	crypto_unregister_algs(aesni_algs, ARRAY_SIZE(aesni_algs));
 	return err;
@@ -1341,10 +1181,10 @@ unregister_algs:
 
 static void __exit aesni_exit(void)
 {
-	aesni_free_simds();
-	crypto_unregister_aeads(aesni_aead_algs, ARRAY_SIZE(aesni_aead_algs));
-	crypto_unregister_skciphers(aesni_skciphers,
-				    ARRAY_SIZE(aesni_skciphers));
+	simd_unregister_aeads(aesni_aeads, ARRAY_SIZE(aesni_aeads),
+			      aesni_simd_aeads);
+	simd_unregister_skciphers(aesni_skciphers, ARRAY_SIZE(aesni_skciphers),
+				  aesni_simd_skciphers);
 	crypto_unregister_algs(aesni_algs, ARRAY_SIZE(aesni_algs));
 }
 
diff --git a/arch/x86/crypto/chacha_glue.c b/arch/x86/crypto/chacha_glue.c
index 45c1c4143176..4967ad620775 100644
--- a/arch/x86/crypto/chacha_glue.c
+++ b/arch/x86/crypto/chacha_glue.c
@@ -12,10 +12,10 @@
 
 #include <crypto/algapi.h>
 #include <crypto/chacha.h>
+#include <crypto/internal/simd.h>
 #include <crypto/internal/skcipher.h>
 #include <linux/kernel.h>
 #include <linux/module.h>
-#include <asm/fpu/api.h>
 #include <asm/simd.h>
 
 #define CHACHA_STATE_ALIGN 16
@@ -170,7 +170,7 @@ static int chacha_simd(struct skcipher_request *req)
 	struct skcipher_walk walk;
 	int err;
 
-	if (req->cryptlen <= CHACHA_BLOCK_SIZE || !irq_fpu_usable())
+	if (req->cryptlen <= CHACHA_BLOCK_SIZE || !crypto_simd_usable())
 		return crypto_chacha_crypt(req);
 
 	err = skcipher_walk_virt(&walk, req, true);
@@ -193,7 +193,7 @@ static int xchacha_simd(struct skcipher_request *req)
 	u8 real_iv[16];
 	int err;
 
-	if (req->cryptlen <= CHACHA_BLOCK_SIZE || !irq_fpu_usable())
+	if (req->cryptlen <= CHACHA_BLOCK_SIZE || !crypto_simd_usable())
 		return crypto_xchacha_crypt(req);
 
 	err = skcipher_walk_virt(&walk, req, true);
diff --git a/arch/x86/crypto/crc32-pclmul_glue.c b/arch/x86/crypto/crc32-pclmul_glue.c
index c8d9cdacbf10..cb4ab6645106 100644
--- a/arch/x86/crypto/crc32-pclmul_glue.c
+++ b/arch/x86/crypto/crc32-pclmul_glue.c
@@ -32,10 +32,11 @@
 #include <linux/kernel.h>
 #include <linux/crc32.h>
 #include <crypto/internal/hash.h>
+#include <crypto/internal/simd.h>
 
 #include <asm/cpufeatures.h>
 #include <asm/cpu_device_id.h>
-#include <asm/fpu/api.h>
+#include <asm/simd.h>
 
 #define CHKSUM_BLOCK_SIZE	1
 #define CHKSUM_DIGEST_SIZE	4
@@ -54,7 +55,7 @@ static u32 __attribute__((pure))
 	unsigned int iremainder;
 	unsigned int prealign;
 
-	if (len < PCLMUL_MIN_LEN + SCALE_F_MASK || !irq_fpu_usable())
+	if (len < PCLMUL_MIN_LEN + SCALE_F_MASK || !crypto_simd_usable())
 		return crc32_le(crc, p, len);
 
 	if ((long)p & SCALE_F_MASK) {
diff --git a/arch/x86/crypto/crc32c-intel_glue.c b/arch/x86/crypto/crc32c-intel_glue.c
index 5773e1161072..a58fe217c856 100644
--- a/arch/x86/crypto/crc32c-intel_glue.c
+++ b/arch/x86/crypto/crc32c-intel_glue.c
@@ -29,10 +29,11 @@
 #include <linux/string.h>
 #include <linux/kernel.h>
 #include <crypto/internal/hash.h>
+#include <crypto/internal/simd.h>
 
 #include <asm/cpufeatures.h>
 #include <asm/cpu_device_id.h>
-#include <asm/fpu/internal.h>
+#include <asm/simd.h>
 
 #define CHKSUM_BLOCK_SIZE	1
 #define CHKSUM_DIGEST_SIZE	4
@@ -177,7 +178,7 @@ static int crc32c_pcl_intel_update(struct shash_desc *desc, const u8 *data,
 	 * use faster PCL version if datasize is large enough to
 	 * overcome kernel fpu state save/restore overhead
 	 */
-	if (len >= CRC32C_PCL_BREAKEVEN && irq_fpu_usable()) {
+	if (len >= CRC32C_PCL_BREAKEVEN && crypto_simd_usable()) {
 		kernel_fpu_begin();
 		*crcp = crc_pcl(data, len, *crcp);
 		kernel_fpu_end();
@@ -189,7 +190,7 @@ static int crc32c_pcl_intel_update(struct shash_desc *desc, const u8 *data,
 static int __crc32c_pcl_intel_finup(u32 *crcp, const u8 *data, unsigned int len,
 				u8 *out)
 {
-	if (len >= CRC32C_PCL_BREAKEVEN && irq_fpu_usable()) {
+	if (len >= CRC32C_PCL_BREAKEVEN && crypto_simd_usable()) {
 		kernel_fpu_begin();
 		*(__le32 *)out = ~cpu_to_le32(crc_pcl(data, len, *crcp));
 		kernel_fpu_end();
diff --git a/arch/x86/crypto/crct10dif-pclmul_glue.c b/arch/x86/crypto/crct10dif-pclmul_glue.c
index 0e785c0b2354..3c81e15b0873 100644
--- a/arch/x86/crypto/crct10dif-pclmul_glue.c
+++ b/arch/x86/crypto/crct10dif-pclmul_glue.c
@@ -26,12 +26,13 @@
 #include <linux/module.h>
 #include <linux/crc-t10dif.h>
 #include <crypto/internal/hash.h>
+#include <crypto/internal/simd.h>
 #include <linux/init.h>
 #include <linux/string.h>
 #include <linux/kernel.h>
-#include <asm/fpu/api.h>
 #include <asm/cpufeatures.h>
 #include <asm/cpu_device_id.h>
+#include <asm/simd.h>
 
 asmlinkage u16 crc_t10dif_pcl(u16 init_crc, const u8 *buf, size_t len);
 
@@ -53,7 +54,7 @@ static int chksum_update(struct shash_desc *desc, const u8 *data,
 {
 	struct chksum_desc_ctx *ctx = shash_desc_ctx(desc);
 
-	if (length >= 16 && irq_fpu_usable()) {
+	if (length >= 16 && crypto_simd_usable()) {
 		kernel_fpu_begin();
 		ctx->crc = crc_t10dif_pcl(ctx->crc, data, length);
 		kernel_fpu_end();
@@ -70,15 +71,14 @@ static int chksum_final(struct shash_desc *desc, u8 *out)
 	return 0;
 }
 
-static int __chksum_finup(__u16 *crcp, const u8 *data, unsigned int len,
-			u8 *out)
+static int __chksum_finup(__u16 crc, const u8 *data, unsigned int len, u8 *out)
 {
-	if (len >= 16 && irq_fpu_usable()) {
+	if (len >= 16 && crypto_simd_usable()) {
 		kernel_fpu_begin();
-		*(__u16 *)out = crc_t10dif_pcl(*crcp, data, len);
+		*(__u16 *)out = crc_t10dif_pcl(crc, data, len);
 		kernel_fpu_end();
 	} else
-		*(__u16 *)out = crc_t10dif_generic(*crcp, data, len);
+		*(__u16 *)out = crc_t10dif_generic(crc, data, len);
 	return 0;
 }
 
@@ -87,15 +87,13 @@ static int chksum_finup(struct shash_desc *desc, const u8 *data,
 {
 	struct chksum_desc_ctx *ctx = shash_desc_ctx(desc);
 
-	return __chksum_finup(&ctx->crc, data, len, out);
+	return __chksum_finup(ctx->crc, data, len, out);
 }
 
 static int chksum_digest(struct shash_desc *desc, const u8 *data,
 			 unsigned int length, u8 *out)
 {
-	struct chksum_desc_ctx *ctx = shash_desc_ctx(desc);
-
-	return __chksum_finup(&ctx->crc, data, length, out);
+	return __chksum_finup(0, data, length, out);
 }
 
 static struct shash_alg alg = {
diff --git a/arch/x86/crypto/ghash-clmulni-intel_glue.c b/arch/x86/crypto/ghash-clmulni-intel_glue.c
index 3582ae885ee1..e3f3e6fd9d65 100644
--- a/arch/x86/crypto/ghash-clmulni-intel_glue.c
+++ b/arch/x86/crypto/ghash-clmulni-intel_glue.c
@@ -19,8 +19,9 @@
 #include <crypto/cryptd.h>
 #include <crypto/gf128mul.h>
 #include <crypto/internal/hash.h>
-#include <asm/fpu/api.h>
+#include <crypto/internal/simd.h>
 #include <asm/cpu_device_id.h>
+#include <asm/simd.h>
 
 #define GHASH_BLOCK_SIZE	16
 #define GHASH_DIGEST_SIZE	16
@@ -171,7 +172,6 @@ static int ghash_async_init(struct ahash_request *req)
 	struct crypto_shash *child = cryptd_ahash_child(cryptd_tfm);
 
 	desc->tfm = child;
-	desc->flags = req->base.flags;
 	return crypto_shash_init(desc);
 }
 
@@ -182,7 +182,7 @@ static int ghash_async_update(struct ahash_request *req)
 	struct ghash_async_ctx *ctx = crypto_ahash_ctx(tfm);
 	struct cryptd_ahash *cryptd_tfm = ctx->cryptd_tfm;
 
-	if (!irq_fpu_usable() ||
+	if (!crypto_simd_usable() ||
 	    (in_atomic() && cryptd_ahash_queued(cryptd_tfm))) {
 		memcpy(cryptd_req, req, sizeof(*req));
 		ahash_request_set_tfm(cryptd_req, &cryptd_tfm->base);
@@ -200,7 +200,7 @@ static int ghash_async_final(struct ahash_request *req)
 	struct ghash_async_ctx *ctx = crypto_ahash_ctx(tfm);
 	struct cryptd_ahash *cryptd_tfm = ctx->cryptd_tfm;
 
-	if (!irq_fpu_usable() ||
+	if (!crypto_simd_usable() ||
 	    (in_atomic() && cryptd_ahash_queued(cryptd_tfm))) {
 		memcpy(cryptd_req, req, sizeof(*req));
 		ahash_request_set_tfm(cryptd_req, &cryptd_tfm->base);
@@ -241,7 +241,7 @@ static int ghash_async_digest(struct ahash_request *req)
 	struct ahash_request *cryptd_req = ahash_request_ctx(req);
 	struct cryptd_ahash *cryptd_tfm = ctx->cryptd_tfm;
 
-	if (!irq_fpu_usable() ||
+	if (!crypto_simd_usable() ||
 	    (in_atomic() && cryptd_ahash_queued(cryptd_tfm))) {
 		memcpy(cryptd_req, req, sizeof(*req));
 		ahash_request_set_tfm(cryptd_req, &cryptd_tfm->base);
@@ -251,7 +251,6 @@ static int ghash_async_digest(struct ahash_request *req)
 		struct crypto_shash *child = cryptd_ahash_child(cryptd_tfm);
 
 		desc->tfm = child;
-		desc->flags = req->base.flags;
 		return shash_ahash_digest(req, desc);
 	}
 }
diff --git a/arch/x86/crypto/morus1280-avx2-glue.c b/arch/x86/crypto/morus1280-avx2-glue.c
index 6634907d6ccd..679627a2a824 100644
--- a/arch/x86/crypto/morus1280-avx2-glue.c
+++ b/arch/x86/crypto/morus1280-avx2-glue.c
@@ -12,6 +12,7 @@
  */
 
 #include <crypto/internal/aead.h>
+#include <crypto/internal/simd.h>
 #include <crypto/morus1280_glue.h>
 #include <linux/module.h>
 #include <asm/fpu/api.h>
@@ -35,7 +36,9 @@ asmlinkage void crypto_morus1280_avx2_dec_tail(void *state, const void *src,
 asmlinkage void crypto_morus1280_avx2_final(void *state, void *tag_xor,
 					    u64 assoclen, u64 cryptlen);
 
-MORUS1280_DECLARE_ALGS(avx2, "morus1280-avx2", 400);
+MORUS1280_DECLARE_ALG(avx2, "morus1280-avx2", 400);
+
+static struct simd_aead_alg *simd_alg;
 
 static int __init crypto_morus1280_avx2_module_init(void)
 {
@@ -44,14 +47,13 @@ static int __init crypto_morus1280_avx2_module_init(void)
 	    !cpu_has_xfeatures(XFEATURE_MASK_SSE | XFEATURE_MASK_YMM, NULL))
 		return -ENODEV;
 
-	return crypto_register_aeads(crypto_morus1280_avx2_algs,
-				     ARRAY_SIZE(crypto_morus1280_avx2_algs));
+	return simd_register_aeads_compat(&crypto_morus1280_avx2_alg, 1,
+					  &simd_alg);
 }
 
 static void __exit crypto_morus1280_avx2_module_exit(void)
 {
-	crypto_unregister_aeads(crypto_morus1280_avx2_algs,
-				ARRAY_SIZE(crypto_morus1280_avx2_algs));
+	simd_unregister_aeads(&crypto_morus1280_avx2_alg, 1, &simd_alg);
 }
 
 module_init(crypto_morus1280_avx2_module_init);
diff --git a/arch/x86/crypto/morus1280-sse2-glue.c b/arch/x86/crypto/morus1280-sse2-glue.c
index f40244eaf14d..c35c0638d0bb 100644
--- a/arch/x86/crypto/morus1280-sse2-glue.c
+++ b/arch/x86/crypto/morus1280-sse2-glue.c
@@ -12,6 +12,7 @@
  */
 
 #include <crypto/internal/aead.h>
+#include <crypto/internal/simd.h>
 #include <crypto/morus1280_glue.h>
 #include <linux/module.h>
 #include <asm/fpu/api.h>
@@ -35,7 +36,9 @@ asmlinkage void crypto_morus1280_sse2_dec_tail(void *state, const void *src,
 asmlinkage void crypto_morus1280_sse2_final(void *state, void *tag_xor,
 					    u64 assoclen, u64 cryptlen);
 
-MORUS1280_DECLARE_ALGS(sse2, "morus1280-sse2", 350);
+MORUS1280_DECLARE_ALG(sse2, "morus1280-sse2", 350);
+
+static struct simd_aead_alg *simd_alg;
 
 static int __init crypto_morus1280_sse2_module_init(void)
 {
@@ -43,14 +46,13 @@ static int __init crypto_morus1280_sse2_module_init(void)
 	    !cpu_has_xfeatures(XFEATURE_MASK_SSE, NULL))
 		return -ENODEV;
 
-	return crypto_register_aeads(crypto_morus1280_sse2_algs,
-				     ARRAY_SIZE(crypto_morus1280_sse2_algs));
+	return simd_register_aeads_compat(&crypto_morus1280_sse2_alg, 1,
+					  &simd_alg);
 }
 
 static void __exit crypto_morus1280_sse2_module_exit(void)
 {
-	crypto_unregister_aeads(crypto_morus1280_sse2_algs,
-				ARRAY_SIZE(crypto_morus1280_sse2_algs));
+	simd_unregister_aeads(&crypto_morus1280_sse2_alg, 1, &simd_alg);
 }
 
 module_init(crypto_morus1280_sse2_module_init);
diff --git a/arch/x86/crypto/morus1280_glue.c b/arch/x86/crypto/morus1280_glue.c
index 7e600f8bcdad..30fc1bd98ec3 100644
--- a/arch/x86/crypto/morus1280_glue.c
+++ b/arch/x86/crypto/morus1280_glue.c
@@ -11,7 +11,6 @@
  * any later version.
  */
 
-#include <crypto/cryptd.h>
 #include <crypto/internal/aead.h>
 #include <crypto/internal/skcipher.h>
 #include <crypto/morus1280_glue.h>
@@ -205,90 +204,6 @@ void crypto_morus1280_glue_init_ops(struct crypto_aead *aead,
 }
 EXPORT_SYMBOL_GPL(crypto_morus1280_glue_init_ops);
 
-int cryptd_morus1280_glue_setkey(struct crypto_aead *aead, const u8 *key,
-				 unsigned int keylen)
-{
-	struct cryptd_aead **ctx = crypto_aead_ctx(aead);
-	struct cryptd_aead *cryptd_tfm = *ctx;
-
-	return crypto_aead_setkey(&cryptd_tfm->base, key, keylen);
-}
-EXPORT_SYMBOL_GPL(cryptd_morus1280_glue_setkey);
-
-int cryptd_morus1280_glue_setauthsize(struct crypto_aead *aead,
-				      unsigned int authsize)
-{
-	struct cryptd_aead **ctx = crypto_aead_ctx(aead);
-	struct cryptd_aead *cryptd_tfm = *ctx;
-
-	return crypto_aead_setauthsize(&cryptd_tfm->base, authsize);
-}
-EXPORT_SYMBOL_GPL(cryptd_morus1280_glue_setauthsize);
-
-int cryptd_morus1280_glue_encrypt(struct aead_request *req)
-{
-	struct crypto_aead *aead = crypto_aead_reqtfm(req);
-	struct cryptd_aead **ctx = crypto_aead_ctx(aead);
-	struct cryptd_aead *cryptd_tfm = *ctx;
-
-	aead = &cryptd_tfm->base;
-	if (irq_fpu_usable() && (!in_atomic() ||
-				 !cryptd_aead_queued(cryptd_tfm)))
-		aead = cryptd_aead_child(cryptd_tfm);
-
-	aead_request_set_tfm(req, aead);
-
-	return crypto_aead_encrypt(req);
-}
-EXPORT_SYMBOL_GPL(cryptd_morus1280_glue_encrypt);
-
-int cryptd_morus1280_glue_decrypt(struct aead_request *req)
-{
-	struct crypto_aead *aead = crypto_aead_reqtfm(req);
-	struct cryptd_aead **ctx = crypto_aead_ctx(aead);
-	struct cryptd_aead *cryptd_tfm = *ctx;
-
-	aead = &cryptd_tfm->base;
-	if (irq_fpu_usable() && (!in_atomic() ||
-				 !cryptd_aead_queued(cryptd_tfm)))
-		aead = cryptd_aead_child(cryptd_tfm);
-
-	aead_request_set_tfm(req, aead);
-
-	return crypto_aead_decrypt(req);
-}
-EXPORT_SYMBOL_GPL(cryptd_morus1280_glue_decrypt);
-
-int cryptd_morus1280_glue_init_tfm(struct crypto_aead *aead)
-{
-	struct cryptd_aead *cryptd_tfm;
-	struct cryptd_aead **ctx = crypto_aead_ctx(aead);
-	const char *name = crypto_aead_alg(aead)->base.cra_driver_name;
-	char internal_name[CRYPTO_MAX_ALG_NAME];
-
-	if (snprintf(internal_name, CRYPTO_MAX_ALG_NAME, "__%s", name)
-			>= CRYPTO_MAX_ALG_NAME)
-		return -ENAMETOOLONG;
-
-	cryptd_tfm = cryptd_alloc_aead(internal_name, CRYPTO_ALG_INTERNAL,
-				       CRYPTO_ALG_INTERNAL);
-	if (IS_ERR(cryptd_tfm))
-		return PTR_ERR(cryptd_tfm);
-
-	*ctx = cryptd_tfm;
-	crypto_aead_set_reqsize(aead, crypto_aead_reqsize(&cryptd_tfm->base));
-	return 0;
-}
-EXPORT_SYMBOL_GPL(cryptd_morus1280_glue_init_tfm);
-
-void cryptd_morus1280_glue_exit_tfm(struct crypto_aead *aead)
-{
-	struct cryptd_aead **ctx = crypto_aead_ctx(aead);
-
-	cryptd_free_aead(*ctx);
-}
-EXPORT_SYMBOL_GPL(cryptd_morus1280_glue_exit_tfm);
-
 MODULE_LICENSE("GPL");
 MODULE_AUTHOR("Ondrej Mosnacek <omosnacek@gmail.com>");
 MODULE_DESCRIPTION("MORUS-1280 AEAD mode -- glue for x86 optimizations");
diff --git a/arch/x86/crypto/morus640-sse2-glue.c b/arch/x86/crypto/morus640-sse2-glue.c
index 9afaf8f8565a..32da56b3bdad 100644
--- a/arch/x86/crypto/morus640-sse2-glue.c
+++ b/arch/x86/crypto/morus640-sse2-glue.c
@@ -12,6 +12,7 @@
  */
 
 #include <crypto/internal/aead.h>
+#include <crypto/internal/simd.h>
 #include <crypto/morus640_glue.h>
 #include <linux/module.h>
 #include <asm/fpu/api.h>
@@ -35,7 +36,9 @@ asmlinkage void crypto_morus640_sse2_dec_tail(void *state, const void *src,
 asmlinkage void crypto_morus640_sse2_final(void *state, void *tag_xor,
 					   u64 assoclen, u64 cryptlen);
 
-MORUS640_DECLARE_ALGS(sse2, "morus640-sse2", 400);
+MORUS640_DECLARE_ALG(sse2, "morus640-sse2", 400);
+
+static struct simd_aead_alg *simd_alg;
 
 static int __init crypto_morus640_sse2_module_init(void)
 {
@@ -43,14 +46,13 @@ static int __init crypto_morus640_sse2_module_init(void)
 	    !cpu_has_xfeatures(XFEATURE_MASK_SSE, NULL))
 		return -ENODEV;
 
-	return crypto_register_aeads(crypto_morus640_sse2_algs,
-				     ARRAY_SIZE(crypto_morus640_sse2_algs));
+	return simd_register_aeads_compat(&crypto_morus640_sse2_alg, 1,
+					  &simd_alg);
 }
 
 static void __exit crypto_morus640_sse2_module_exit(void)
 {
-	crypto_unregister_aeads(crypto_morus640_sse2_algs,
-				ARRAY_SIZE(crypto_morus640_sse2_algs));
+	simd_unregister_aeads(&crypto_morus640_sse2_alg, 1, &simd_alg);
 }
 
 module_init(crypto_morus640_sse2_module_init);
diff --git a/arch/x86/crypto/morus640_glue.c b/arch/x86/crypto/morus640_glue.c
index cb3a81732016..1dea33d84426 100644
--- a/arch/x86/crypto/morus640_glue.c
+++ b/arch/x86/crypto/morus640_glue.c
@@ -11,7 +11,6 @@
  * any later version.
  */
 
-#include <crypto/cryptd.h>
 #include <crypto/internal/aead.h>
 #include <crypto/internal/skcipher.h>
 #include <crypto/morus640_glue.h>
@@ -200,90 +199,6 @@ void crypto_morus640_glue_init_ops(struct crypto_aead *aead,
 }
 EXPORT_SYMBOL_GPL(crypto_morus640_glue_init_ops);
 
-int cryptd_morus640_glue_setkey(struct crypto_aead *aead, const u8 *key,
-				unsigned int keylen)
-{
-	struct cryptd_aead **ctx = crypto_aead_ctx(aead);
-	struct cryptd_aead *cryptd_tfm = *ctx;
-
-	return crypto_aead_setkey(&cryptd_tfm->base, key, keylen);
-}
-EXPORT_SYMBOL_GPL(cryptd_morus640_glue_setkey);
-
-int cryptd_morus640_glue_setauthsize(struct crypto_aead *aead,
-				     unsigned int authsize)
-{
-	struct cryptd_aead **ctx = crypto_aead_ctx(aead);
-	struct cryptd_aead *cryptd_tfm = *ctx;
-
-	return crypto_aead_setauthsize(&cryptd_tfm->base, authsize);
-}
-EXPORT_SYMBOL_GPL(cryptd_morus640_glue_setauthsize);
-
-int cryptd_morus640_glue_encrypt(struct aead_request *req)
-{
-	struct crypto_aead *aead = crypto_aead_reqtfm(req);
-	struct cryptd_aead **ctx = crypto_aead_ctx(aead);
-	struct cryptd_aead *cryptd_tfm = *ctx;
-
-	aead = &cryptd_tfm->base;
-	if (irq_fpu_usable() && (!in_atomic() ||
-				 !cryptd_aead_queued(cryptd_tfm)))
-		aead = cryptd_aead_child(cryptd_tfm);
-
-	aead_request_set_tfm(req, aead);
-
-	return crypto_aead_encrypt(req);
-}
-EXPORT_SYMBOL_GPL(cryptd_morus640_glue_encrypt);
-
-int cryptd_morus640_glue_decrypt(struct aead_request *req)
-{
-	struct crypto_aead *aead = crypto_aead_reqtfm(req);
-	struct cryptd_aead **ctx = crypto_aead_ctx(aead);
-	struct cryptd_aead *cryptd_tfm = *ctx;
-
-	aead = &cryptd_tfm->base;
-	if (irq_fpu_usable() && (!in_atomic() ||
-				 !cryptd_aead_queued(cryptd_tfm)))
-		aead = cryptd_aead_child(cryptd_tfm);
-
-	aead_request_set_tfm(req, aead);
-
-	return crypto_aead_decrypt(req);
-}
-EXPORT_SYMBOL_GPL(cryptd_morus640_glue_decrypt);
-
-int cryptd_morus640_glue_init_tfm(struct crypto_aead *aead)
-{
-	struct cryptd_aead *cryptd_tfm;
-	struct cryptd_aead **ctx = crypto_aead_ctx(aead);
-	const char *name = crypto_aead_alg(aead)->base.cra_driver_name;
-	char internal_name[CRYPTO_MAX_ALG_NAME];
-
-	if (snprintf(internal_name, CRYPTO_MAX_ALG_NAME, "__%s", name)
-			>= CRYPTO_MAX_ALG_NAME)
-		return -ENAMETOOLONG;
-
-	cryptd_tfm = cryptd_alloc_aead(internal_name, CRYPTO_ALG_INTERNAL,
-				       CRYPTO_ALG_INTERNAL);
-	if (IS_ERR(cryptd_tfm))
-		return PTR_ERR(cryptd_tfm);
-
-	*ctx = cryptd_tfm;
-	crypto_aead_set_reqsize(aead, crypto_aead_reqsize(&cryptd_tfm->base));
-	return 0;
-}
-EXPORT_SYMBOL_GPL(cryptd_morus640_glue_init_tfm);
-
-void cryptd_morus640_glue_exit_tfm(struct crypto_aead *aead)
-{
-	struct cryptd_aead **ctx = crypto_aead_ctx(aead);
-
-	cryptd_free_aead(*ctx);
-}
-EXPORT_SYMBOL_GPL(cryptd_morus640_glue_exit_tfm);
-
 MODULE_LICENSE("GPL");
 MODULE_AUTHOR("Ondrej Mosnacek <omosnacek@gmail.com>");
 MODULE_DESCRIPTION("MORUS-640 AEAD mode -- glue for x86 optimizations");
diff --git a/arch/x86/crypto/nhpoly1305-avx2-glue.c b/arch/x86/crypto/nhpoly1305-avx2-glue.c
index 20d815ea4b6a..f7567cbd35b6 100644
--- a/arch/x86/crypto/nhpoly1305-avx2-glue.c
+++ b/arch/x86/crypto/nhpoly1305-avx2-glue.c
@@ -7,9 +7,10 @@
  */
 
 #include <crypto/internal/hash.h>
+#include <crypto/internal/simd.h>
 #include <crypto/nhpoly1305.h>
 #include <linux/module.h>
-#include <asm/fpu/api.h>
+#include <asm/simd.h>
 
 asmlinkage void nh_avx2(const u32 *key, const u8 *message, size_t message_len,
 			u8 hash[NH_HASH_BYTES]);
@@ -24,7 +25,7 @@ static void _nh_avx2(const u32 *key, const u8 *message, size_t message_len,
 static int nhpoly1305_avx2_update(struct shash_desc *desc,
 				  const u8 *src, unsigned int srclen)
 {
-	if (srclen < 64 || !irq_fpu_usable())
+	if (srclen < 64 || !crypto_simd_usable())
 		return crypto_nhpoly1305_update(desc, src, srclen);
 
 	do {
diff --git a/arch/x86/crypto/nhpoly1305-sse2-glue.c b/arch/x86/crypto/nhpoly1305-sse2-glue.c
index ed68d164ce14..a661ede3b5cf 100644
--- a/arch/x86/crypto/nhpoly1305-sse2-glue.c
+++ b/arch/x86/crypto/nhpoly1305-sse2-glue.c
@@ -7,9 +7,10 @@
  */
 
 #include <crypto/internal/hash.h>
+#include <crypto/internal/simd.h>
 #include <crypto/nhpoly1305.h>
 #include <linux/module.h>
-#include <asm/fpu/api.h>
+#include <asm/simd.h>
 
 asmlinkage void nh_sse2(const u32 *key, const u8 *message, size_t message_len,
 			u8 hash[NH_HASH_BYTES]);
@@ -24,7 +25,7 @@ static void _nh_sse2(const u32 *key, const u8 *message, size_t message_len,
 static int nhpoly1305_sse2_update(struct shash_desc *desc,
 				  const u8 *src, unsigned int srclen)
 {
-	if (srclen < 64 || !irq_fpu_usable())
+	if (srclen < 64 || !crypto_simd_usable())
 		return crypto_nhpoly1305_update(desc, src, srclen);
 
 	do {
diff --git a/arch/x86/crypto/poly1305-avx2-x86_64.S b/arch/x86/crypto/poly1305-avx2-x86_64.S
index 3b6e70d085da..8457cdd47f75 100644
--- a/arch/x86/crypto/poly1305-avx2-x86_64.S
+++ b/arch/x86/crypto/poly1305-avx2-x86_64.S
@@ -323,6 +323,12 @@ ENTRY(poly1305_4block_avx2)
 	vpaddq		t2,t1,t1
 	vmovq		t1x,d4
 
+	# Now do a partial reduction mod (2^130)-5, carrying h0 -> h1 -> h2 ->
+	# h3 -> h4 -> h0 -> h1 to get h0,h2,h3,h4 < 2^26 and h1 < 2^26 + a small
+	# amount.  Careful: we must not assume the carry bits 'd0 >> 26',
+	# 'd1 >> 26', 'd2 >> 26', 'd3 >> 26', and '(d4 >> 26) * 5' fit in 32-bit
+	# integers.  It's true in a single-block implementation, but not here.
+
 	# d1 += d0 >> 26
 	mov		d0,%rax
 	shr		$26,%rax
@@ -361,16 +367,16 @@ ENTRY(poly1305_4block_avx2)
 	# h0 += (d4 >> 26) * 5
 	mov		d4,%rax
 	shr		$26,%rax
-	lea		(%eax,%eax,4),%eax
-	add		%eax,%ebx
+	lea		(%rax,%rax,4),%rax
+	add		%rax,%rbx
 	# h4 = d4 & 0x3ffffff
 	mov		d4,%rax
 	and		$0x3ffffff,%eax
 	mov		%eax,h4
 
 	# h1 += h0 >> 26
-	mov		%ebx,%eax
-	shr		$26,%eax
+	mov		%rbx,%rax
+	shr		$26,%rax
 	add		%eax,h1
 	# h0 = h0 & 0x3ffffff
 	andl		$0x3ffffff,%ebx
diff --git a/arch/x86/crypto/poly1305-sse2-x86_64.S b/arch/x86/crypto/poly1305-sse2-x86_64.S
index e6add74d78a5..6f0be7a86964 100644
--- a/arch/x86/crypto/poly1305-sse2-x86_64.S
+++ b/arch/x86/crypto/poly1305-sse2-x86_64.S
@@ -253,16 +253,16 @@ ENTRY(poly1305_block_sse2)
 	# h0 += (d4 >> 26) * 5
 	mov		d4,%rax
 	shr		$26,%rax
-	lea		(%eax,%eax,4),%eax
-	add		%eax,%ebx
+	lea		(%rax,%rax,4),%rax
+	add		%rax,%rbx
 	# h4 = d4 & 0x3ffffff
 	mov		d4,%rax
 	and		$0x3ffffff,%eax
 	mov		%eax,h4
 
 	# h1 += h0 >> 26
-	mov		%ebx,%eax
-	shr		$26,%eax
+	mov		%rbx,%rax
+	shr		$26,%rax
 	add		%eax,h1
 	# h0 = h0 & 0x3ffffff
 	andl		$0x3ffffff,%ebx
@@ -524,6 +524,12 @@ ENTRY(poly1305_2block_sse2)
 	paddq		t2,t1
 	movq		t1,d4
 
+	# Now do a partial reduction mod (2^130)-5, carrying h0 -> h1 -> h2 ->
+	# h3 -> h4 -> h0 -> h1 to get h0,h2,h3,h4 < 2^26 and h1 < 2^26 + a small
+	# amount.  Careful: we must not assume the carry bits 'd0 >> 26',
+	# 'd1 >> 26', 'd2 >> 26', 'd3 >> 26', and '(d4 >> 26) * 5' fit in 32-bit
+	# integers.  It's true in a single-block implementation, but not here.
+
 	# d1 += d0 >> 26
 	mov		d0,%rax
 	shr		$26,%rax
@@ -562,16 +568,16 @@ ENTRY(poly1305_2block_sse2)
 	# h0 += (d4 >> 26) * 5
 	mov		d4,%rax
 	shr		$26,%rax
-	lea		(%eax,%eax,4),%eax
-	add		%eax,%ebx
+	lea		(%rax,%rax,4),%rax
+	add		%rax,%rbx
 	# h4 = d4 & 0x3ffffff
 	mov		d4,%rax
 	and		$0x3ffffff,%eax
 	mov		%eax,h4
 
 	# h1 += h0 >> 26
-	mov		%ebx,%eax
-	shr		$26,%eax
+	mov		%rbx,%rax
+	shr		$26,%rax
 	add		%eax,h1
 	# h0 = h0 & 0x3ffffff
 	andl		$0x3ffffff,%ebx
diff --git a/arch/x86/crypto/poly1305_glue.c b/arch/x86/crypto/poly1305_glue.c
index 88cc01506c84..6eb65b237b3c 100644
--- a/arch/x86/crypto/poly1305_glue.c
+++ b/arch/x86/crypto/poly1305_glue.c
@@ -11,11 +11,11 @@
 
 #include <crypto/algapi.h>
 #include <crypto/internal/hash.h>
+#include <crypto/internal/simd.h>
 #include <crypto/poly1305.h>
 #include <linux/crypto.h>
 #include <linux/kernel.h>
 #include <linux/module.h>
-#include <asm/fpu/api.h>
 #include <asm/simd.h>
 
 struct poly1305_simd_desc_ctx {
@@ -126,7 +126,7 @@ static int poly1305_simd_update(struct shash_desc *desc,
 	unsigned int bytes;
 
 	/* kernel_fpu_begin/end is costly, use fallback for small updates */
-	if (srclen <= 288 || !may_use_simd())
+	if (srclen <= 288 || !crypto_simd_usable())
 		return crypto_poly1305_update(desc, src, srclen);
 
 	kernel_fpu_begin();
diff --git a/arch/x86/crypto/sha1_ssse3_glue.c b/arch/x86/crypto/sha1_ssse3_glue.c
index 7391c7de72c7..42f177afc33a 100644
--- a/arch/x86/crypto/sha1_ssse3_glue.c
+++ b/arch/x86/crypto/sha1_ssse3_glue.c
@@ -22,6 +22,7 @@
 #define pr_fmt(fmt)	KBUILD_MODNAME ": " fmt
 
 #include <crypto/internal/hash.h>
+#include <crypto/internal/simd.h>
 #include <linux/init.h>
 #include <linux/module.h>
 #include <linux/mm.h>
@@ -29,7 +30,7 @@
 #include <linux/types.h>
 #include <crypto/sha.h>
 #include <crypto/sha1_base.h>
-#include <asm/fpu/api.h>
+#include <asm/simd.h>
 
 typedef void (sha1_transform_fn)(u32 *digest, const char *data,
 				unsigned int rounds);
@@ -39,7 +40,7 @@ static int sha1_update(struct shash_desc *desc, const u8 *data,
 {
 	struct sha1_state *sctx = shash_desc_ctx(desc);
 
-	if (!irq_fpu_usable() ||
+	if (!crypto_simd_usable() ||
 	    (sctx->count % SHA1_BLOCK_SIZE) + len < SHA1_BLOCK_SIZE)
 		return crypto_sha1_update(desc, data, len);
 
@@ -57,7 +58,7 @@ static int sha1_update(struct shash_desc *desc, const u8 *data,
 static int sha1_finup(struct shash_desc *desc, const u8 *data,
 		      unsigned int len, u8 *out, sha1_transform_fn *sha1_xform)
 {
-	if (!irq_fpu_usable())
+	if (!crypto_simd_usable())
 		return crypto_sha1_finup(desc, data, len, out);
 
 	kernel_fpu_begin();
diff --git a/arch/x86/crypto/sha256_ssse3_glue.c b/arch/x86/crypto/sha256_ssse3_glue.c
index 773a873d2b28..73867da3cbee 100644
--- a/arch/x86/crypto/sha256_ssse3_glue.c
+++ b/arch/x86/crypto/sha256_ssse3_glue.c
@@ -30,6 +30,7 @@
 #define pr_fmt(fmt)	KBUILD_MODNAME ": " fmt
 
 #include <crypto/internal/hash.h>
+#include <crypto/internal/simd.h>
 #include <linux/init.h>
 #include <linux/module.h>
 #include <linux/mm.h>
@@ -37,8 +38,8 @@
 #include <linux/types.h>
 #include <crypto/sha.h>
 #include <crypto/sha256_base.h>
-#include <asm/fpu/api.h>
 #include <linux/string.h>
+#include <asm/simd.h>
 
 asmlinkage void sha256_transform_ssse3(u32 *digest, const char *data,
 				       u64 rounds);
@@ -49,7 +50,7 @@ static int sha256_update(struct shash_desc *desc, const u8 *data,
 {
 	struct sha256_state *sctx = shash_desc_ctx(desc);
 
-	if (!irq_fpu_usable() ||
+	if (!crypto_simd_usable() ||
 	    (sctx->count % SHA256_BLOCK_SIZE) + len < SHA256_BLOCK_SIZE)
 		return crypto_sha256_update(desc, data, len);
 
@@ -67,7 +68,7 @@ static int sha256_update(struct shash_desc *desc, const u8 *data,
 static int sha256_finup(struct shash_desc *desc, const u8 *data,
 	      unsigned int len, u8 *out, sha256_transform_fn *sha256_xform)
 {
-	if (!irq_fpu_usable())
+	if (!crypto_simd_usable())
 		return crypto_sha256_finup(desc, data, len, out);
 
 	kernel_fpu_begin();
diff --git a/arch/x86/crypto/sha512_ssse3_glue.c b/arch/x86/crypto/sha512_ssse3_glue.c
index f1b811b60ba6..458356a3f124 100644
--- a/arch/x86/crypto/sha512_ssse3_glue.c
+++ b/arch/x86/crypto/sha512_ssse3_glue.c
@@ -28,16 +28,16 @@
 #define pr_fmt(fmt)	KBUILD_MODNAME ": " fmt
 
 #include <crypto/internal/hash.h>
+#include <crypto/internal/simd.h>
 #include <linux/init.h>
 #include <linux/module.h>
 #include <linux/mm.h>
 #include <linux/cryptohash.h>
+#include <linux/string.h>
 #include <linux/types.h>
 #include <crypto/sha.h>
 #include <crypto/sha512_base.h>
-#include <asm/fpu/api.h>
-
-#include <linux/string.h>
+#include <asm/simd.h>
 
 asmlinkage void sha512_transform_ssse3(u64 *digest, const char *data,
 				       u64 rounds);
@@ -49,7 +49,7 @@ static int sha512_update(struct shash_desc *desc, const u8 *data,
 {
 	struct sha512_state *sctx = shash_desc_ctx(desc);
 
-	if (!irq_fpu_usable() ||
+	if (!crypto_simd_usable() ||
 	    (sctx->count[0] % SHA512_BLOCK_SIZE) + len < SHA512_BLOCK_SIZE)
 		return crypto_sha512_update(desc, data, len);
 
@@ -67,7 +67,7 @@ static int sha512_update(struct shash_desc *desc, const u8 *data,
 static int sha512_finup(struct shash_desc *desc, const u8 *data,
 	      unsigned int len, u8 *out, sha512_transform_fn *sha512_xform)
 {
-	if (!irq_fpu_usable())
+	if (!crypto_simd_usable())
 		return crypto_sha512_finup(desc, data, len, out);
 
 	kernel_fpu_begin();
diff --git a/arch/x86/entry/entry_32.S b/arch/x86/entry/entry_32.S
index d309f30cf7af..7b23431be5cb 100644
--- a/arch/x86/entry/entry_32.S
+++ b/arch/x86/entry/entry_32.S
@@ -650,6 +650,7 @@ ENTRY(__switch_to_asm)
 	pushl	%ebx
 	pushl	%edi
 	pushl	%esi
+	pushfl
 
 	/* switch stack */
 	movl	%esp, TASK_threadsp(%eax)
@@ -672,6 +673,7 @@ ENTRY(__switch_to_asm)
 #endif
 
 	/* restore callee-saved registers */
+	popfl
 	popl	%esi
 	popl	%edi
 	popl	%ebx
@@ -766,13 +768,12 @@ END(ret_from_exception)
 #ifdef CONFIG_PREEMPT
 ENTRY(resume_kernel)
 	DISABLE_INTERRUPTS(CLBR_ANY)
-.Lneed_resched:
 	cmpl	$0, PER_CPU_VAR(__preempt_count)
 	jnz	restore_all_kernel
 	testl	$X86_EFLAGS_IF, PT_EFLAGS(%esp)	# interrupts off (exception path) ?
 	jz	restore_all_kernel
 	call	preempt_schedule_irq
-	jmp	.Lneed_resched
+	jmp	restore_all_kernel
 END(resume_kernel)
 #endif
 
diff --git a/arch/x86/entry/entry_64.S b/arch/x86/entry/entry_64.S
index 1f0efdb7b629..20e45d9b4e15 100644
--- a/arch/x86/entry/entry_64.S
+++ b/arch/x86/entry/entry_64.S
@@ -298,7 +298,7 @@ ENTRY(__switch_to_asm)
 
 #ifdef CONFIG_STACKPROTECTOR
 	movq	TASK_stack_canary(%rsi), %rbx
-	movq	%rbx, PER_CPU_VAR(irq_stack_union)+stack_canary_offset
+	movq	%rbx, PER_CPU_VAR(fixed_percpu_data) + stack_canary_offset
 #endif
 
 #ifdef CONFIG_RETPOLINE
@@ -430,8 +430,8 @@ END(irq_entries_start)
 	 * it before we actually move ourselves to the IRQ stack.
 	 */
 
-	movq	\old_rsp, PER_CPU_VAR(irq_stack_union + IRQ_STACK_SIZE - 8)
-	movq	PER_CPU_VAR(irq_stack_ptr), %rsp
+	movq	\old_rsp, PER_CPU_VAR(irq_stack_backing_store + IRQ_STACK_SIZE - 8)
+	movq	PER_CPU_VAR(hardirq_stack_ptr), %rsp
 
 #ifdef CONFIG_DEBUG_ENTRY
 	/*
@@ -645,10 +645,9 @@ retint_kernel:
 	/* Check if we need preemption */
 	btl	$9, EFLAGS(%rsp)		/* were interrupts off? */
 	jnc	1f
-0:	cmpl	$0, PER_CPU_VAR(__preempt_count)
+	cmpl	$0, PER_CPU_VAR(__preempt_count)
 	jnz	1f
 	call	preempt_schedule_irq
-	jmp	0b
 1:
 #endif
 	/*
@@ -841,7 +840,7 @@ apicinterrupt IRQ_WORK_VECTOR			irq_work_interrupt		smp_irq_work_interrupt
 /*
  * Exception entry points.
  */
-#define CPU_TSS_IST(x) PER_CPU_VAR(cpu_tss_rw) + (TSS_ist + ((x) - 1) * 8)
+#define CPU_TSS_IST(x) PER_CPU_VAR(cpu_tss_rw) + (TSS_ist + (x) * 8)
 
 /**
  * idtentry - Generate an IDT entry stub
@@ -879,7 +878,7 @@ apicinterrupt IRQ_WORK_VECTOR			irq_work_interrupt		smp_irq_work_interrupt
  * @paranoid == 2 is special: the stub will never switch stacks.  This is for
  * #DF: if the thread stack is somehow unusable, we'll still get a useful OOPS.
  */
-.macro idtentry sym do_sym has_error_code:req paranoid=0 shift_ist=-1
+.macro idtentry sym do_sym has_error_code:req paranoid=0 shift_ist=-1 ist_offset=0
 ENTRY(\sym)
 	UNWIND_HINT_IRET_REGS offset=\has_error_code*8
 
@@ -925,13 +924,13 @@ ENTRY(\sym)
 	.endif
 
 	.if \shift_ist != -1
-	subq	$EXCEPTION_STKSZ, CPU_TSS_IST(\shift_ist)
+	subq	$\ist_offset, CPU_TSS_IST(\shift_ist)
 	.endif
 
 	call	\do_sym
 
 	.if \shift_ist != -1
-	addq	$EXCEPTION_STKSZ, CPU_TSS_IST(\shift_ist)
+	addq	$\ist_offset, CPU_TSS_IST(\shift_ist)
 	.endif
 
 	/* these procedures expect "no swapgs" flag in ebx */
@@ -1129,7 +1128,7 @@ apicinterrupt3 HYPERV_STIMER0_VECTOR \
 	hv_stimer0_callback_vector hv_stimer0_vector_handler
 #endif /* CONFIG_HYPERV */
 
-idtentry debug			do_debug		has_error_code=0	paranoid=1 shift_ist=DEBUG_STACK
+idtentry debug			do_debug		has_error_code=0	paranoid=1 shift_ist=IST_INDEX_DB ist_offset=DB_STACK_OFFSET
 idtentry int3			do_int3			has_error_code=0
 idtentry stack_segment		do_stack_segment	has_error_code=1
 
diff --git a/arch/x86/entry/vdso/Makefile b/arch/x86/entry/vdso/Makefile
index 5bfe2243a08f..42fe42e82baf 100644
--- a/arch/x86/entry/vdso/Makefile
+++ b/arch/x86/entry/vdso/Makefile
@@ -116,7 +116,7 @@ $(obj)/%-x32.o: $(obj)/%.o FORCE
 targets += vdsox32.lds $(vobjx32s-y)
 
 $(obj)/%.so: OBJCOPYFLAGS := -S
-$(obj)/%.so: $(obj)/%.so.dbg
+$(obj)/%.so: $(obj)/%.so.dbg FORCE
 	$(call if_changed,objcopy)
 
 $(obj)/vdsox32.so.dbg: $(obj)/vdsox32.lds $(vobjx32s) FORCE
diff --git a/arch/x86/entry/vdso/vclock_gettime.c b/arch/x86/entry/vdso/vclock_gettime.c
index 007b3fe9d727..98c7d12b945c 100644
--- a/arch/x86/entry/vdso/vclock_gettime.c
+++ b/arch/x86/entry/vdso/vclock_gettime.c
@@ -29,12 +29,12 @@ extern int __vdso_gettimeofday(struct timeval *tv, struct timezone *tz);
 extern time_t __vdso_time(time_t *t);
 
 #ifdef CONFIG_PARAVIRT_CLOCK
-extern u8 pvclock_page
+extern u8 pvclock_page[PAGE_SIZE]
 	__attribute__((visibility("hidden")));
 #endif
 
 #ifdef CONFIG_HYPERV_TSCPAGE
-extern u8 hvclock_page
+extern u8 hvclock_page[PAGE_SIZE]
 	__attribute__((visibility("hidden")));
 #endif
 
diff --git a/arch/x86/entry/vdso/vdso2c.h b/arch/x86/entry/vdso/vdso2c.h
index fa847a620f40..a20b134de2a8 100644
--- a/arch/x86/entry/vdso/vdso2c.h
+++ b/arch/x86/entry/vdso/vdso2c.h
@@ -7,7 +7,7 @@
 
 static void BITSFUNC(go)(void *raw_addr, size_t raw_len,
 			 void *stripped_addr, size_t stripped_len,
-			 FILE *outfile, const char *name)
+			 FILE *outfile, const char *image_name)
 {
 	int found_load = 0;
 	unsigned long load_size = -1;  /* Work around bogus warning */
@@ -93,11 +93,12 @@ static void BITSFUNC(go)(void *raw_addr, size_t raw_len,
 		int k;
 		ELF(Sym) *sym = raw_addr + GET_LE(&symtab_hdr->sh_offset) +
 			GET_LE(&symtab_hdr->sh_entsize) * i;
-		const char *name = raw_addr + GET_LE(&strtab_hdr->sh_offset) +
-			GET_LE(&sym->st_name);
+		const char *sym_name = raw_addr +
+				       GET_LE(&strtab_hdr->sh_offset) +
+				       GET_LE(&sym->st_name);
 
 		for (k = 0; k < NSYMS; k++) {
-			if (!strcmp(name, required_syms[k].name)) {
+			if (!strcmp(sym_name, required_syms[k].name)) {
 				if (syms[k]) {
 					fail("duplicate symbol %s\n",
 					     required_syms[k].name);
@@ -134,7 +135,7 @@ static void BITSFUNC(go)(void *raw_addr, size_t raw_len,
 	if (syms[sym_vvar_start] % 4096)
 		fail("vvar_begin must be a multiple of 4096\n");
 
-	if (!name) {
+	if (!image_name) {
 		fwrite(stripped_addr, stripped_len, 1, outfile);
 		return;
 	}
@@ -157,7 +158,7 @@ static void BITSFUNC(go)(void *raw_addr, size_t raw_len,
 	}
 	fprintf(outfile, "\n};\n\n");
 
-	fprintf(outfile, "const struct vdso_image %s = {\n", name);
+	fprintf(outfile, "const struct vdso_image %s = {\n", image_name);
 	fprintf(outfile, "\t.data = raw_data,\n");
 	fprintf(outfile, "\t.size = %lu,\n", mapping_size);
 	if (alt_sec) {
diff --git a/arch/x86/events/amd/core.c b/arch/x86/events/amd/core.c
index 7d2d7c801dba..f15441b07dad 100644
--- a/arch/x86/events/amd/core.c
+++ b/arch/x86/events/amd/core.c
@@ -3,10 +3,14 @@
 #include <linux/types.h>
 #include <linux/init.h>
 #include <linux/slab.h>
+#include <linux/delay.h>
 #include <asm/apicdef.h>
+#include <asm/nmi.h>
 
 #include "../perf_event.h"
 
+static DEFINE_PER_CPU(unsigned int, perf_nmi_counter);
+
 static __initconst const u64 amd_hw_cache_event_ids
 				[PERF_COUNT_HW_CACHE_MAX]
 				[PERF_COUNT_HW_CACHE_OP_MAX]
@@ -112,23 +116,144 @@ static __initconst const u64 amd_hw_cache_event_ids
  },
 };
 
+static __initconst const u64 amd_hw_cache_event_ids_f17h
+				[PERF_COUNT_HW_CACHE_MAX]
+				[PERF_COUNT_HW_CACHE_OP_MAX]
+				[PERF_COUNT_HW_CACHE_RESULT_MAX] = {
+[C(L1D)] = {
+	[C(OP_READ)] = {
+		[C(RESULT_ACCESS)] = 0x0040, /* Data Cache Accesses */
+		[C(RESULT_MISS)]   = 0xc860, /* L2$ access from DC Miss */
+	},
+	[C(OP_WRITE)] = {
+		[C(RESULT_ACCESS)] = 0,
+		[C(RESULT_MISS)]   = 0,
+	},
+	[C(OP_PREFETCH)] = {
+		[C(RESULT_ACCESS)] = 0xff5a, /* h/w prefetch DC Fills */
+		[C(RESULT_MISS)]   = 0,
+	},
+},
+[C(L1I)] = {
+	[C(OP_READ)] = {
+		[C(RESULT_ACCESS)] = 0x0080, /* Instruction cache fetches  */
+		[C(RESULT_MISS)]   = 0x0081, /* Instruction cache misses   */
+	},
+	[C(OP_WRITE)] = {
+		[C(RESULT_ACCESS)] = -1,
+		[C(RESULT_MISS)]   = -1,
+	},
+	[C(OP_PREFETCH)] = {
+		[C(RESULT_ACCESS)] = 0,
+		[C(RESULT_MISS)]   = 0,
+	},
+},
+[C(LL)] = {
+	[C(OP_READ)] = {
+		[C(RESULT_ACCESS)] = 0,
+		[C(RESULT_MISS)]   = 0,
+	},
+	[C(OP_WRITE)] = {
+		[C(RESULT_ACCESS)] = 0,
+		[C(RESULT_MISS)]   = 0,
+	},
+	[C(OP_PREFETCH)] = {
+		[C(RESULT_ACCESS)] = 0,
+		[C(RESULT_MISS)]   = 0,
+	},
+},
+[C(DTLB)] = {
+	[C(OP_READ)] = {
+		[C(RESULT_ACCESS)] = 0xff45, /* All L2 DTLB accesses */
+		[C(RESULT_MISS)]   = 0xf045, /* L2 DTLB misses (PT walks) */
+	},
+	[C(OP_WRITE)] = {
+		[C(RESULT_ACCESS)] = 0,
+		[C(RESULT_MISS)]   = 0,
+	},
+	[C(OP_PREFETCH)] = {
+		[C(RESULT_ACCESS)] = 0,
+		[C(RESULT_MISS)]   = 0,
+	},
+},
+[C(ITLB)] = {
+	[C(OP_READ)] = {
+		[C(RESULT_ACCESS)] = 0x0084, /* L1 ITLB misses, L2 ITLB hits */
+		[C(RESULT_MISS)]   = 0xff85, /* L1 ITLB misses, L2 misses */
+	},
+	[C(OP_WRITE)] = {
+		[C(RESULT_ACCESS)] = -1,
+		[C(RESULT_MISS)]   = -1,
+	},
+	[C(OP_PREFETCH)] = {
+		[C(RESULT_ACCESS)] = -1,
+		[C(RESULT_MISS)]   = -1,
+	},
+},
+[C(BPU)] = {
+	[C(OP_READ)] = {
+		[C(RESULT_ACCESS)] = 0x00c2, /* Retired Branch Instr.      */
+		[C(RESULT_MISS)]   = 0x00c3, /* Retired Mispredicted BI    */
+	},
+	[C(OP_WRITE)] = {
+		[C(RESULT_ACCESS)] = -1,
+		[C(RESULT_MISS)]   = -1,
+	},
+	[C(OP_PREFETCH)] = {
+		[C(RESULT_ACCESS)] = -1,
+		[C(RESULT_MISS)]   = -1,
+	},
+},
+[C(NODE)] = {
+	[C(OP_READ)] = {
+		[C(RESULT_ACCESS)] = 0,
+		[C(RESULT_MISS)]   = 0,
+	},
+	[C(OP_WRITE)] = {
+		[C(RESULT_ACCESS)] = -1,
+		[C(RESULT_MISS)]   = -1,
+	},
+	[C(OP_PREFETCH)] = {
+		[C(RESULT_ACCESS)] = -1,
+		[C(RESULT_MISS)]   = -1,
+	},
+},
+};
+
 /*
- * AMD Performance Monitor K7 and later.
+ * AMD Performance Monitor K7 and later, up to and including Family 16h:
  */
 static const u64 amd_perfmon_event_map[PERF_COUNT_HW_MAX] =
 {
-  [PERF_COUNT_HW_CPU_CYCLES]			= 0x0076,
-  [PERF_COUNT_HW_INSTRUCTIONS]			= 0x00c0,
-  [PERF_COUNT_HW_CACHE_REFERENCES]		= 0x077d,
-  [PERF_COUNT_HW_CACHE_MISSES]			= 0x077e,
-  [PERF_COUNT_HW_BRANCH_INSTRUCTIONS]		= 0x00c2,
-  [PERF_COUNT_HW_BRANCH_MISSES]			= 0x00c3,
-  [PERF_COUNT_HW_STALLED_CYCLES_FRONTEND]	= 0x00d0, /* "Decoder empty" event */
-  [PERF_COUNT_HW_STALLED_CYCLES_BACKEND]	= 0x00d1, /* "Dispatch stalls" event */
+	[PERF_COUNT_HW_CPU_CYCLES]		= 0x0076,
+	[PERF_COUNT_HW_INSTRUCTIONS]		= 0x00c0,
+	[PERF_COUNT_HW_CACHE_REFERENCES]	= 0x077d,
+	[PERF_COUNT_HW_CACHE_MISSES]		= 0x077e,
+	[PERF_COUNT_HW_BRANCH_INSTRUCTIONS]	= 0x00c2,
+	[PERF_COUNT_HW_BRANCH_MISSES]		= 0x00c3,
+	[PERF_COUNT_HW_STALLED_CYCLES_FRONTEND]	= 0x00d0, /* "Decoder empty" event */
+	[PERF_COUNT_HW_STALLED_CYCLES_BACKEND]	= 0x00d1, /* "Dispatch stalls" event */
+};
+
+/*
+ * AMD Performance Monitor Family 17h and later:
+ */
+static const u64 amd_f17h_perfmon_event_map[PERF_COUNT_HW_MAX] =
+{
+	[PERF_COUNT_HW_CPU_CYCLES]		= 0x0076,
+	[PERF_COUNT_HW_INSTRUCTIONS]		= 0x00c0,
+	[PERF_COUNT_HW_CACHE_REFERENCES]	= 0xff60,
+	[PERF_COUNT_HW_BRANCH_INSTRUCTIONS]	= 0x00c2,
+	[PERF_COUNT_HW_BRANCH_MISSES]		= 0x00c3,
+	[PERF_COUNT_HW_STALLED_CYCLES_FRONTEND]	= 0x0287,
+	[PERF_COUNT_HW_STALLED_CYCLES_BACKEND]	= 0x0187,
 };
 
 static u64 amd_pmu_event_map(int hw_event)
 {
+	if (boot_cpu_data.x86 >= 0x17)
+		return amd_f17h_perfmon_event_map[hw_event];
+
 	return amd_perfmon_event_map[hw_event];
 }
 
@@ -429,6 +554,132 @@ static void amd_pmu_cpu_dead(int cpu)
 	}
 }
 
+/*
+ * When a PMC counter overflows, an NMI is used to process the event and
+ * reset the counter. NMI latency can result in the counter being updated
+ * before the NMI can run, which can result in what appear to be spurious
+ * NMIs. This function is intended to wait for the NMI to run and reset
+ * the counter to avoid possible unhandled NMI messages.
+ */
+#define OVERFLOW_WAIT_COUNT	50
+
+static void amd_pmu_wait_on_overflow(int idx)
+{
+	unsigned int i;
+	u64 counter;
+
+	/*
+	 * Wait for the counter to be reset if it has overflowed. This loop
+	 * should exit very, very quickly, but just in case, don't wait
+	 * forever...
+	 */
+	for (i = 0; i < OVERFLOW_WAIT_COUNT; i++) {
+		rdmsrl(x86_pmu_event_addr(idx), counter);
+		if (counter & (1ULL << (x86_pmu.cntval_bits - 1)))
+			break;
+
+		/* Might be in IRQ context, so can't sleep */
+		udelay(1);
+	}
+}
+
+static void amd_pmu_disable_all(void)
+{
+	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
+	int idx;
+
+	x86_pmu_disable_all();
+
+	/*
+	 * This shouldn't be called from NMI context, but add a safeguard here
+	 * to return, since if we're in NMI context we can't wait for an NMI
+	 * to reset an overflowed counter value.
+	 */
+	if (in_nmi())
+		return;
+
+	/*
+	 * Check each counter for overflow and wait for it to be reset by the
+	 * NMI if it has overflowed. This relies on the fact that all active
+	 * counters are always enabled when this function is caled and
+	 * ARCH_PERFMON_EVENTSEL_INT is always set.
+	 */
+	for (idx = 0; idx < x86_pmu.num_counters; idx++) {
+		if (!test_bit(idx, cpuc->active_mask))
+			continue;
+
+		amd_pmu_wait_on_overflow(idx);
+	}
+}
+
+static void amd_pmu_disable_event(struct perf_event *event)
+{
+	x86_pmu_disable_event(event);
+
+	/*
+	 * This can be called from NMI context (via x86_pmu_stop). The counter
+	 * may have overflowed, but either way, we'll never see it get reset
+	 * by the NMI if we're already in the NMI. And the NMI latency support
+	 * below will take care of any pending NMI that might have been
+	 * generated by the overflow.
+	 */
+	if (in_nmi())
+		return;
+
+	amd_pmu_wait_on_overflow(event->hw.idx);
+}
+
+/*
+ * Because of NMI latency, if multiple PMC counters are active or other sources
+ * of NMIs are received, the perf NMI handler can handle one or more overflowed
+ * PMC counters outside of the NMI associated with the PMC overflow. If the NMI
+ * doesn't arrive at the LAPIC in time to become a pending NMI, then the kernel
+ * back-to-back NMI support won't be active. This PMC handler needs to take into
+ * account that this can occur, otherwise this could result in unknown NMI
+ * messages being issued. Examples of this is PMC overflow while in the NMI
+ * handler when multiple PMCs are active or PMC overflow while handling some
+ * other source of an NMI.
+ *
+ * Attempt to mitigate this by using the number of active PMCs to determine
+ * whether to return NMI_HANDLED if the perf NMI handler did not handle/reset
+ * any PMCs. The per-CPU perf_nmi_counter variable is set to a minimum of the
+ * number of active PMCs or 2. The value of 2 is used in case an NMI does not
+ * arrive at the LAPIC in time to be collapsed into an already pending NMI.
+ */
+static int amd_pmu_handle_irq(struct pt_regs *regs)
+{
+	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
+	int active, handled;
+
+	/*
+	 * Obtain the active count before calling x86_pmu_handle_irq() since
+	 * it is possible that x86_pmu_handle_irq() may make a counter
+	 * inactive (through x86_pmu_stop).
+	 */
+	active = __bitmap_weight(cpuc->active_mask, X86_PMC_IDX_MAX);
+
+	/* Process any counter overflows */
+	handled = x86_pmu_handle_irq(regs);
+
+	/*
+	 * If a counter was handled, record the number of possible remaining
+	 * NMIs that can occur.
+	 */
+	if (handled) {
+		this_cpu_write(perf_nmi_counter,
+			       min_t(unsigned int, 2, active));
+
+		return handled;
+	}
+
+	if (!this_cpu_read(perf_nmi_counter))
+		return NMI_DONE;
+
+	this_cpu_dec(perf_nmi_counter);
+
+	return NMI_HANDLED;
+}
+
 static struct event_constraint *
 amd_get_event_constraints(struct cpu_hw_events *cpuc, int idx,
 			  struct perf_event *event)
@@ -621,11 +872,11 @@ static ssize_t amd_event_sysfs_show(char *page, u64 config)
 
 static __initconst const struct x86_pmu amd_pmu = {
 	.name			= "AMD",
-	.handle_irq		= x86_pmu_handle_irq,
-	.disable_all		= x86_pmu_disable_all,
+	.handle_irq		= amd_pmu_handle_irq,
+	.disable_all		= amd_pmu_disable_all,
 	.enable_all		= x86_pmu_enable_all,
 	.enable			= x86_pmu_enable_event,
-	.disable		= x86_pmu_disable_event,
+	.disable		= amd_pmu_disable_event,
 	.hw_config		= amd_pmu_hw_config,
 	.schedule_events	= x86_schedule_events,
 	.eventsel		= MSR_K7_EVNTSEL0,
@@ -718,9 +969,10 @@ __init int amd_pmu_init(void)
 		x86_pmu.amd_nb_constraints = 0;
 	}
 
-	/* Events are common for all AMDs */
-	memcpy(hw_cache_event_ids, amd_hw_cache_event_ids,
-	       sizeof(hw_cache_event_ids));
+	if (boot_cpu_data.x86 >= 0x17)
+		memcpy(hw_cache_event_ids, amd_hw_cache_event_ids_f17h, sizeof(hw_cache_event_ids));
+	else
+		memcpy(hw_cache_event_ids, amd_hw_cache_event_ids, sizeof(hw_cache_event_ids));
 
 	return 0;
 }
@@ -732,7 +984,7 @@ void amd_pmu_enable_virt(void)
 	cpuc->perf_ctr_virt_mask = 0;
 
 	/* Reload all events */
-	x86_pmu_disable_all();
+	amd_pmu_disable_all();
 	x86_pmu_enable_all(0);
 }
 EXPORT_SYMBOL_GPL(amd_pmu_enable_virt);
@@ -750,7 +1002,7 @@ void amd_pmu_disable_virt(void)
 	cpuc->perf_ctr_virt_mask = AMD64_EVENTSEL_HOSTONLY;
 
 	/* Reload all events */
-	x86_pmu_disable_all();
+	amd_pmu_disable_all();
 	x86_pmu_enable_all(0);
 }
 EXPORT_SYMBOL_GPL(amd_pmu_disable_virt);
diff --git a/arch/x86/events/core.c b/arch/x86/events/core.c
index e2b1447192a8..f315425d8468 100644
--- a/arch/x86/events/core.c
+++ b/arch/x86/events/core.c
@@ -560,6 +560,21 @@ int x86_pmu_hw_config(struct perf_event *event)
 			return -EINVAL;
 	}
 
+	/* sample_regs_user never support XMM registers */
+	if (unlikely(event->attr.sample_regs_user & PEBS_XMM_REGS))
+		return -EINVAL;
+	/*
+	 * Besides the general purpose registers, XMM registers may
+	 * be collected in PEBS on some platforms, e.g. Icelake
+	 */
+	if (unlikely(event->attr.sample_regs_intr & PEBS_XMM_REGS)) {
+		if (x86_pmu.pebs_no_xmm_regs)
+			return -EINVAL;
+
+		if (!event->attr.precise_ip)
+			return -EINVAL;
+	}
+
 	return x86_setup_perfctr(event);
 }
 
@@ -661,6 +676,10 @@ static inline int is_x86_event(struct perf_event *event)
 	return event->pmu == &pmu;
 }
 
+struct pmu *x86_get_pmu(void)
+{
+	return &pmu;
+}
 /*
  * Event scheduler state:
  *
@@ -849,18 +868,43 @@ int x86_schedule_events(struct cpu_hw_events *cpuc, int n, int *assign)
 	struct event_constraint *c;
 	unsigned long used_mask[BITS_TO_LONGS(X86_PMC_IDX_MAX)];
 	struct perf_event *e;
-	int i, wmin, wmax, unsched = 0;
+	int n0, i, wmin, wmax, unsched = 0;
 	struct hw_perf_event *hwc;
 
 	bitmap_zero(used_mask, X86_PMC_IDX_MAX);
 
+	/*
+	 * Compute the number of events already present; see x86_pmu_add(),
+	 * validate_group() and x86_pmu_commit_txn(). For the former two
+	 * cpuc->n_events hasn't been updated yet, while for the latter
+	 * cpuc->n_txn contains the number of events added in the current
+	 * transaction.
+	 */
+	n0 = cpuc->n_events;
+	if (cpuc->txn_flags & PERF_PMU_TXN_ADD)
+		n0 -= cpuc->n_txn;
+
 	if (x86_pmu.start_scheduling)
 		x86_pmu.start_scheduling(cpuc);
 
 	for (i = 0, wmin = X86_PMC_IDX_MAX, wmax = 0; i < n; i++) {
-		cpuc->event_constraint[i] = NULL;
-		c = x86_pmu.get_event_constraints(cpuc, i, cpuc->event_list[i]);
-		cpuc->event_constraint[i] = c;
+		c = cpuc->event_constraint[i];
+
+		/*
+		 * Previously scheduled events should have a cached constraint,
+		 * while new events should not have one.
+		 */
+		WARN_ON_ONCE((c && i >= n0) || (!c && i < n0));
+
+		/*
+		 * Request constraints for new events; or for those events that
+		 * have a dynamic constraint -- for those the constraint can
+		 * change due to external factors (sibling state, allow_tfa).
+		 */
+		if (!c || (c->flags & PERF_X86_EVENT_DYNAMIC)) {
+			c = x86_pmu.get_event_constraints(cpuc, i, cpuc->event_list[i]);
+			cpuc->event_constraint[i] = c;
+		}
 
 		wmin = min(wmin, c->weight);
 		wmax = max(wmax, c->weight);
@@ -925,25 +969,20 @@ int x86_schedule_events(struct cpu_hw_events *cpuc, int n, int *assign)
 	if (!unsched && assign) {
 		for (i = 0; i < n; i++) {
 			e = cpuc->event_list[i];
-			e->hw.flags |= PERF_X86_EVENT_COMMITTED;
 			if (x86_pmu.commit_scheduling)
 				x86_pmu.commit_scheduling(cpuc, i, assign[i]);
 		}
 	} else {
-		for (i = 0; i < n; i++) {
+		for (i = n0; i < n; i++) {
 			e = cpuc->event_list[i];
-			/*
-			 * do not put_constraint() on comitted events,
-			 * because they are good to go
-			 */
-			if ((e->hw.flags & PERF_X86_EVENT_COMMITTED))
-				continue;
 
 			/*
 			 * release events that failed scheduling
 			 */
 			if (x86_pmu.put_event_constraints)
 				x86_pmu.put_event_constraints(cpuc, e);
+
+			cpuc->event_constraint[i] = NULL;
 		}
 	}
 
@@ -1349,8 +1388,9 @@ void x86_pmu_stop(struct perf_event *event, int flags)
 	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
 	struct hw_perf_event *hwc = &event->hw;
 
-	if (__test_and_clear_bit(hwc->idx, cpuc->active_mask)) {
+	if (test_bit(hwc->idx, cpuc->active_mask)) {
 		x86_pmu.disable(event);
+		__clear_bit(hwc->idx, cpuc->active_mask);
 		cpuc->events[hwc->idx] = NULL;
 		WARN_ON_ONCE(hwc->state & PERF_HES_STOPPED);
 		hwc->state |= PERF_HES_STOPPED;
@@ -1372,11 +1412,6 @@ static void x86_pmu_del(struct perf_event *event, int flags)
 	int i;
 
 	/*
-	 * event is descheduled
-	 */
-	event->hw.flags &= ~PERF_X86_EVENT_COMMITTED;
-
-	/*
 	 * If we're called during a txn, we only need to undo x86_pmu.add.
 	 * The events never got scheduled and ->cancel_txn will truncate
 	 * the event_list.
@@ -1412,6 +1447,7 @@ static void x86_pmu_del(struct perf_event *event, int flags)
 		cpuc->event_list[i-1] = cpuc->event_list[i];
 		cpuc->event_constraint[i-1] = cpuc->event_constraint[i];
 	}
+	cpuc->event_constraint[i-1] = NULL;
 	--cpuc->n_events;
 
 	perf_event_update_userpage(event);
@@ -1447,16 +1483,8 @@ int x86_pmu_handle_irq(struct pt_regs *regs)
 	apic_write(APIC_LVTPC, APIC_DM_NMI);
 
 	for (idx = 0; idx < x86_pmu.num_counters; idx++) {
-		if (!test_bit(idx, cpuc->active_mask)) {
-			/*
-			 * Though we deactivated the counter some cpus
-			 * might still deliver spurious interrupts still
-			 * in flight. Catch them:
-			 */
-			if (__test_and_clear_bit(idx, cpuc->running))
-				handled++;
+		if (!test_bit(idx, cpuc->active_mask))
 			continue;
-		}
 
 		event = cpuc->events[idx];
 
@@ -2031,7 +2059,7 @@ static int validate_event(struct perf_event *event)
 	if (IS_ERR(fake_cpuc))
 		return PTR_ERR(fake_cpuc);
 
-	c = x86_pmu.get_event_constraints(fake_cpuc, -1, event);
+	c = x86_pmu.get_event_constraints(fake_cpuc, 0, event);
 
 	if (!c || !c->weight)
 		ret = -EINVAL;
@@ -2079,8 +2107,7 @@ static int validate_group(struct perf_event *event)
 	if (n < 0)
 		goto out;
 
-	fake_cpuc->n_events = n;
-
+	fake_cpuc->n_events = 0;
 	ret = x86_pmu.schedule_events(fake_cpuc, n, NULL);
 
 out:
@@ -2355,6 +2382,15 @@ void arch_perf_update_userpage(struct perf_event *event,
 	cyc2ns_read_end();
 }
 
+/*
+ * Determine whether the regs were taken from an irq/exception handler rather
+ * than from perf_arch_fetch_caller_regs().
+ */
+static bool perf_hw_regs(struct pt_regs *regs)
+{
+	return regs->flags & X86_EFLAGS_FIXED;
+}
+
 void
 perf_callchain_kernel(struct perf_callchain_entry_ctx *entry, struct pt_regs *regs)
 {
@@ -2366,11 +2402,15 @@ perf_callchain_kernel(struct perf_callchain_entry_ctx *entry, struct pt_regs *re
 		return;
 	}
 
-	if (perf_callchain_store(entry, regs->ip))
-		return;
+	if (perf_hw_regs(regs)) {
+		if (perf_callchain_store(entry, regs->ip))
+			return;
+		unwind_start(&state, current, regs, NULL);
+	} else {
+		unwind_start(&state, current, NULL, (void *)regs->sp);
+	}
 
-	for (unwind_start(&state, current, regs, NULL); !unwind_done(&state);
-	     unwind_next_frame(&state)) {
+	for (; !unwind_done(&state); unwind_next_frame(&state)) {
 		addr = unwind_get_return_address(&state);
 		if (!addr || perf_callchain_store(entry, addr))
 			return;
diff --git a/arch/x86/events/intel/core.c b/arch/x86/events/intel/core.c
index 8baa441d8000..ef763f535e3a 100644
--- a/arch/x86/events/intel/core.c
+++ b/arch/x86/events/intel/core.c
@@ -239,6 +239,35 @@ static struct extra_reg intel_skl_extra_regs[] __read_mostly = {
 	EVENT_EXTRA_END
 };
 
+static struct event_constraint intel_icl_event_constraints[] = {
+	FIXED_EVENT_CONSTRAINT(0x00c0, 0),	/* INST_RETIRED.ANY */
+	INTEL_UEVENT_CONSTRAINT(0x1c0, 0),	/* INST_RETIRED.PREC_DIST */
+	FIXED_EVENT_CONSTRAINT(0x003c, 1),	/* CPU_CLK_UNHALTED.CORE */
+	FIXED_EVENT_CONSTRAINT(0x0300, 2),	/* CPU_CLK_UNHALTED.REF */
+	FIXED_EVENT_CONSTRAINT(0x0400, 3),	/* SLOTS */
+	INTEL_EVENT_CONSTRAINT_RANGE(0x03, 0x0a, 0xf),
+	INTEL_EVENT_CONSTRAINT_RANGE(0x1f, 0x28, 0xf),
+	INTEL_EVENT_CONSTRAINT(0x32, 0xf),	/* SW_PREFETCH_ACCESS.* */
+	INTEL_EVENT_CONSTRAINT_RANGE(0x48, 0x54, 0xf),
+	INTEL_EVENT_CONSTRAINT_RANGE(0x60, 0x8b, 0xf),
+	INTEL_UEVENT_CONSTRAINT(0x04a3, 0xff),  /* CYCLE_ACTIVITY.STALLS_TOTAL */
+	INTEL_UEVENT_CONSTRAINT(0x10a3, 0xff),  /* CYCLE_ACTIVITY.STALLS_MEM_ANY */
+	INTEL_EVENT_CONSTRAINT(0xa3, 0xf),      /* CYCLE_ACTIVITY.* */
+	INTEL_EVENT_CONSTRAINT_RANGE(0xa8, 0xb0, 0xf),
+	INTEL_EVENT_CONSTRAINT_RANGE(0xb7, 0xbd, 0xf),
+	INTEL_EVENT_CONSTRAINT_RANGE(0xd0, 0xe6, 0xf),
+	INTEL_EVENT_CONSTRAINT_RANGE(0xf0, 0xf4, 0xf),
+	EVENT_CONSTRAINT_END
+};
+
+static struct extra_reg intel_icl_extra_regs[] __read_mostly = {
+	INTEL_UEVENT_EXTRA_REG(0x01b7, MSR_OFFCORE_RSP_0, 0x3fffff9fffull, RSP_0),
+	INTEL_UEVENT_EXTRA_REG(0x01bb, MSR_OFFCORE_RSP_1, 0x3fffff9fffull, RSP_1),
+	INTEL_UEVENT_PEBS_LDLAT_EXTRA_REG(0x01cd),
+	INTEL_UEVENT_EXTRA_REG(0x01c6, MSR_PEBS_FRONTEND, 0x7fff17, FE),
+	EVENT_EXTRA_END
+};
+
 EVENT_ATTR_STR(mem-loads,	mem_ld_nhm,	"event=0x0b,umask=0x10,ldlat=3");
 EVENT_ATTR_STR(mem-loads,	mem_ld_snb,	"event=0xcd,umask=0x1,ldlat=3");
 EVENT_ATTR_STR(mem-stores,	mem_st_snb,	"event=0xcd,umask=0x2");
@@ -1827,6 +1856,45 @@ static __initconst const u64 glp_hw_cache_extra_regs
 	},
 };
 
+#define TNT_LOCAL_DRAM			BIT_ULL(26)
+#define TNT_DEMAND_READ			GLM_DEMAND_DATA_RD
+#define TNT_DEMAND_WRITE		GLM_DEMAND_RFO
+#define TNT_LLC_ACCESS			GLM_ANY_RESPONSE
+#define TNT_SNP_ANY			(SNB_SNP_NOT_NEEDED|SNB_SNP_MISS| \
+					 SNB_NO_FWD|SNB_SNP_FWD|SNB_HITM)
+#define TNT_LLC_MISS			(TNT_SNP_ANY|SNB_NON_DRAM|TNT_LOCAL_DRAM)
+
+static __initconst const u64 tnt_hw_cache_extra_regs
+				[PERF_COUNT_HW_CACHE_MAX]
+				[PERF_COUNT_HW_CACHE_OP_MAX]
+				[PERF_COUNT_HW_CACHE_RESULT_MAX] = {
+	[C(LL)] = {
+		[C(OP_READ)] = {
+			[C(RESULT_ACCESS)]	= TNT_DEMAND_READ|
+						  TNT_LLC_ACCESS,
+			[C(RESULT_MISS)]	= TNT_DEMAND_READ|
+						  TNT_LLC_MISS,
+		},
+		[C(OP_WRITE)] = {
+			[C(RESULT_ACCESS)]	= TNT_DEMAND_WRITE|
+						  TNT_LLC_ACCESS,
+			[C(RESULT_MISS)]	= TNT_DEMAND_WRITE|
+						  TNT_LLC_MISS,
+		},
+		[C(OP_PREFETCH)] = {
+			[C(RESULT_ACCESS)]	= 0x0,
+			[C(RESULT_MISS)]	= 0x0,
+		},
+	},
+};
+
+static struct extra_reg intel_tnt_extra_regs[] __read_mostly = {
+	/* must define OFFCORE_RSP_X first, see intel_fixup_er() */
+	INTEL_UEVENT_EXTRA_REG(0x01b7, MSR_OFFCORE_RSP_0, 0xffffff9fffull, RSP_0),
+	INTEL_UEVENT_EXTRA_REG(0x02b7, MSR_OFFCORE_RSP_1, 0xffffff9fffull, RSP_1),
+	EVENT_EXTRA_END
+};
+
 #define KNL_OT_L2_HITE		BIT_ULL(19) /* Other Tile L2 Hit */
 #define KNL_OT_L2_HITF		BIT_ULL(20) /* Other Tile L2 Hit */
 #define KNL_MCDRAM_LOCAL	BIT_ULL(21)
@@ -2015,7 +2083,7 @@ static void intel_tfa_commit_scheduling(struct cpu_hw_events *cpuc, int idx, int
 	/*
 	 * We're going to use PMC3, make sure TFA is set before we touch it.
 	 */
-	if (cntr == 3 && !cpuc->is_fake)
+	if (cntr == 3)
 		intel_set_tfa(cpuc, true);
 }
 
@@ -2091,15 +2159,19 @@ static void intel_pmu_disable_event(struct perf_event *event)
 	cpuc->intel_ctrl_host_mask &= ~(1ull << hwc->idx);
 	cpuc->intel_cp_status &= ~(1ull << hwc->idx);
 
-	if (unlikely(event->attr.precise_ip))
-		intel_pmu_pebs_disable(event);
-
 	if (unlikely(hwc->config_base == MSR_ARCH_PERFMON_FIXED_CTR_CTRL)) {
 		intel_pmu_disable_fixed(hwc);
 		return;
 	}
 
 	x86_pmu_disable_event(event);
+
+	/*
+	 * Needs to be called after x86_pmu_disable_event,
+	 * so we don't trigger the event without PEBS bit set.
+	 */
+	if (unlikely(event->attr.precise_ip))
+		intel_pmu_pebs_disable(event);
 }
 
 static void intel_pmu_del_event(struct perf_event *event)
@@ -2145,6 +2217,11 @@ static void intel_pmu_enable_fixed(struct perf_event *event)
 	bits <<= (idx * 4);
 	mask = 0xfULL << (idx * 4);
 
+	if (x86_pmu.intel_cap.pebs_baseline && event->attr.precise_ip) {
+		bits |= ICL_FIXED_0_ADAPTIVE << (idx * 4);
+		mask |= ICL_FIXED_0_ADAPTIVE << (idx * 4);
+	}
+
 	rdmsrl(hwc->config_base, ctrl_val);
 	ctrl_val &= ~mask;
 	ctrl_val |= bits;
@@ -2688,7 +2765,7 @@ x86_get_event_constraints(struct cpu_hw_events *cpuc, int idx,
 
 	if (x86_pmu.event_constraints) {
 		for_each_event_constraint(c, x86_pmu.event_constraints) {
-			if ((event->hw.config & c->cmask) == c->code) {
+			if (constraint_match(c, event->hw.config)) {
 				event->hw.flags |= c->flags;
 				return c;
 			}
@@ -2838,7 +2915,7 @@ intel_get_excl_constraints(struct cpu_hw_events *cpuc, struct perf_event *event,
 	struct intel_excl_cntrs *excl_cntrs = cpuc->excl_cntrs;
 	struct intel_excl_states *xlo;
 	int tid = cpuc->excl_thread_id;
-	int is_excl, i;
+	int is_excl, i, w;
 
 	/*
 	 * validating a group does not require
@@ -2894,36 +2971,40 @@ intel_get_excl_constraints(struct cpu_hw_events *cpuc, struct perf_event *event,
 	 * SHARED   : sibling counter measuring non-exclusive event
 	 * UNUSED   : sibling counter unused
 	 */
+	w = c->weight;
 	for_each_set_bit(i, c->idxmsk, X86_PMC_IDX_MAX) {
 		/*
 		 * exclusive event in sibling counter
 		 * our corresponding counter cannot be used
 		 * regardless of our event
 		 */
-		if (xlo->state[i] == INTEL_EXCL_EXCLUSIVE)
+		if (xlo->state[i] == INTEL_EXCL_EXCLUSIVE) {
 			__clear_bit(i, c->idxmsk);
+			w--;
+			continue;
+		}
 		/*
 		 * if measuring an exclusive event, sibling
 		 * measuring non-exclusive, then counter cannot
 		 * be used
 		 */
-		if (is_excl && xlo->state[i] == INTEL_EXCL_SHARED)
+		if (is_excl && xlo->state[i] == INTEL_EXCL_SHARED) {
 			__clear_bit(i, c->idxmsk);
+			w--;
+			continue;
+		}
 	}
 
 	/*
-	 * recompute actual bit weight for scheduling algorithm
-	 */
-	c->weight = hweight64(c->idxmsk64);
-
-	/*
 	 * if we return an empty mask, then switch
 	 * back to static empty constraint to avoid
 	 * the cost of freeing later on
 	 */
-	if (c->weight == 0)
+	if (!w)
 		c = &emptyconstraint;
 
+	c->weight = w;
+
 	return c;
 }
 
@@ -2931,11 +3012,9 @@ static struct event_constraint *
 intel_get_event_constraints(struct cpu_hw_events *cpuc, int idx,
 			    struct perf_event *event)
 {
-	struct event_constraint *c1 = NULL;
-	struct event_constraint *c2;
+	struct event_constraint *c1, *c2;
 
-	if (idx >= 0) /* fake does < 0 */
-		c1 = cpuc->event_constraint[idx];
+	c1 = cpuc->event_constraint[idx];
 
 	/*
 	 * first time only
@@ -2943,7 +3022,8 @@ intel_get_event_constraints(struct cpu_hw_events *cpuc, int idx,
 	 * - dynamic constraint: handled by intel_get_excl_constraints()
 	 */
 	c2 = __intel_get_event_constraints(cpuc, idx, event);
-	if (c1 && (c1->flags & PERF_X86_EVENT_DYNAMIC)) {
+	if (c1) {
+	        WARN_ON_ONCE(!(c1->flags & PERF_X86_EVENT_DYNAMIC));
 		bitmap_copy(c1->idxmsk, c2->idxmsk, X86_PMC_IDX_MAX);
 		c1->weight = c2->weight;
 		c2 = c1;
@@ -3131,7 +3211,7 @@ static unsigned long intel_pmu_large_pebs_flags(struct perf_event *event)
 		flags &= ~PERF_SAMPLE_TIME;
 	if (!event->attr.exclude_kernel)
 		flags &= ~PERF_SAMPLE_REGS_USER;
-	if (event->attr.sample_regs_user & ~PEBS_REGS)
+	if (event->attr.sample_regs_user & ~PEBS_GP_REGS)
 		flags &= ~(PERF_SAMPLE_REGS_USER | PERF_SAMPLE_REGS_INTR);
 	return flags;
 }
@@ -3185,7 +3265,7 @@ static int intel_pmu_hw_config(struct perf_event *event)
 		return ret;
 
 	if (event->attr.precise_ip) {
-		if (!event->attr.freq) {
+		if (!(event->attr.freq || event->attr.wakeup_events)) {
 			event->hw.flags |= PERF_X86_EVENT_AUTO_RELOAD;
 			if (!(event->attr.sample_type &
 			      ~intel_pmu_large_pebs_flags(event)))
@@ -3366,6 +3446,12 @@ static struct event_constraint counter0_constraint =
 static struct event_constraint counter2_constraint =
 			EVENT_CONSTRAINT(0, 0x4, 0);
 
+static struct event_constraint fixed0_constraint =
+			FIXED_EVENT_CONSTRAINT(0x00c0, 0);
+
+static struct event_constraint fixed0_counter0_constraint =
+			INTEL_ALL_EVENT_CONSTRAINT(0, 0x100000001ULL);
+
 static struct event_constraint *
 hsw_get_event_constraints(struct cpu_hw_events *cpuc, int idx,
 			  struct perf_event *event)
@@ -3385,6 +3471,21 @@ hsw_get_event_constraints(struct cpu_hw_events *cpuc, int idx,
 }
 
 static struct event_constraint *
+icl_get_event_constraints(struct cpu_hw_events *cpuc, int idx,
+			  struct perf_event *event)
+{
+	/*
+	 * Fixed counter 0 has less skid.
+	 * Force instruction:ppp in Fixed counter 0
+	 */
+	if ((event->attr.precise_ip == 3) &&
+	    constraint_match(&fixed0_constraint, event->hw.config))
+		return &fixed0_constraint;
+
+	return hsw_get_event_constraints(cpuc, idx, event);
+}
+
+static struct event_constraint *
 glp_get_event_constraints(struct cpu_hw_events *cpuc, int idx,
 			  struct perf_event *event)
 {
@@ -3399,6 +3500,29 @@ glp_get_event_constraints(struct cpu_hw_events *cpuc, int idx,
 	return c;
 }
 
+static struct event_constraint *
+tnt_get_event_constraints(struct cpu_hw_events *cpuc, int idx,
+			  struct perf_event *event)
+{
+	struct event_constraint *c;
+
+	/*
+	 * :ppp means to do reduced skid PEBS,
+	 * which is available on PMC0 and fixed counter 0.
+	 */
+	if (event->attr.precise_ip == 3) {
+		/* Force instruction:ppp on PMC0 and Fixed counter 0 */
+		if (constraint_match(&fixed0_constraint, event->hw.config))
+			return &fixed0_counter0_constraint;
+
+		return &counter0_constraint;
+	}
+
+	c = intel_get_event_constraints(cpuc, idx, event);
+
+	return c;
+}
+
 static bool allow_tsx_force_abort = true;
 
 static struct event_constraint *
@@ -3410,7 +3534,7 @@ tfa_get_event_constraints(struct cpu_hw_events *cpuc, int idx,
 	/*
 	 * Without TFA we must not use PMC3.
 	 */
-	if (!allow_tsx_force_abort && test_bit(3, c->idxmsk) && idx >= 0) {
+	if (!allow_tsx_force_abort && test_bit(3, c->idxmsk)) {
 		c = dyn_constraint(cpuc, c, idx);
 		c->idxmsk64 &= ~(1ULL << 3);
 		c->weight--;
@@ -3507,6 +3631,8 @@ static struct intel_excl_cntrs *allocate_excl_cntrs(int cpu)
 
 int intel_cpuc_prepare(struct cpu_hw_events *cpuc, int cpu)
 {
+	cpuc->pebs_record_size = x86_pmu.pebs_record_size;
+
 	if (x86_pmu.extra_regs || x86_pmu.lbr_sel_map) {
 		cpuc->shared_regs = allocate_shared_regs(cpu);
 		if (!cpuc->shared_regs)
@@ -3575,6 +3701,12 @@ static void intel_pmu_cpu_starting(int cpu)
 
 	cpuc->lbr_sel = NULL;
 
+	if (x86_pmu.flags & PMU_FL_TFA) {
+		WARN_ON_ONCE(cpuc->tfa_shadow);
+		cpuc->tfa_shadow = ~0ULL;
+		intel_set_tfa(cpuc, false);
+	}
+
 	if (x86_pmu.version > 1)
 		flip_smm_bit(&x86_pmu.attr_freeze_on_smi);
 
@@ -4108,6 +4240,42 @@ static struct attribute *hsw_tsx_events_attrs[] = {
 	NULL
 };
 
+EVENT_ATTR_STR(tx-capacity-read,  tx_capacity_read,  "event=0x54,umask=0x80");
+EVENT_ATTR_STR(tx-capacity-write, tx_capacity_write, "event=0x54,umask=0x2");
+EVENT_ATTR_STR(el-capacity-read,  el_capacity_read,  "event=0x54,umask=0x80");
+EVENT_ATTR_STR(el-capacity-write, el_capacity_write, "event=0x54,umask=0x2");
+
+static struct attribute *icl_events_attrs[] = {
+	EVENT_PTR(mem_ld_hsw),
+	EVENT_PTR(mem_st_hsw),
+	NULL,
+};
+
+static struct attribute *icl_tsx_events_attrs[] = {
+	EVENT_PTR(tx_start),
+	EVENT_PTR(tx_abort),
+	EVENT_PTR(tx_commit),
+	EVENT_PTR(tx_capacity_read),
+	EVENT_PTR(tx_capacity_write),
+	EVENT_PTR(tx_conflict),
+	EVENT_PTR(el_start),
+	EVENT_PTR(el_abort),
+	EVENT_PTR(el_commit),
+	EVENT_PTR(el_capacity_read),
+	EVENT_PTR(el_capacity_write),
+	EVENT_PTR(el_conflict),
+	EVENT_PTR(cycles_t),
+	EVENT_PTR(cycles_ct),
+	NULL,
+};
+
+static __init struct attribute **get_icl_events_attrs(void)
+{
+	return boot_cpu_has(X86_FEATURE_RTM) ?
+		merge_attr(icl_events_attrs, icl_tsx_events_attrs) :
+		icl_events_attrs;
+}
+
 static ssize_t freeze_on_smi_show(struct device *cdev,
 				  struct device_attribute *attr,
 				  char *buf)
@@ -4147,6 +4315,50 @@ done:
 	return count;
 }
 
+static void update_tfa_sched(void *ignored)
+{
+	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
+
+	/*
+	 * check if PMC3 is used
+	 * and if so force schedule out for all event types all contexts
+	 */
+	if (test_bit(3, cpuc->active_mask))
+		perf_pmu_resched(x86_get_pmu());
+}
+
+static ssize_t show_sysctl_tfa(struct device *cdev,
+			      struct device_attribute *attr,
+			      char *buf)
+{
+	return snprintf(buf, 40, "%d\n", allow_tsx_force_abort);
+}
+
+static ssize_t set_sysctl_tfa(struct device *cdev,
+			      struct device_attribute *attr,
+			      const char *buf, size_t count)
+{
+	bool val;
+	ssize_t ret;
+
+	ret = kstrtobool(buf, &val);
+	if (ret)
+		return ret;
+
+	/* no change */
+	if (val == allow_tsx_force_abort)
+		return count;
+
+	allow_tsx_force_abort = val;
+
+	get_online_cpus();
+	on_each_cpu(update_tfa_sched, NULL, 1);
+	put_online_cpus();
+
+	return count;
+}
+
+
 static DEVICE_ATTR_RW(freeze_on_smi);
 
 static ssize_t branches_show(struct device *cdev,
@@ -4179,7 +4391,9 @@ static struct attribute *intel_pmu_caps_attrs[] = {
        NULL
 };
 
-static DEVICE_BOOL_ATTR(allow_tsx_force_abort, 0644, allow_tsx_force_abort);
+static DEVICE_ATTR(allow_tsx_force_abort, 0644,
+		   show_sysctl_tfa,
+		   set_sysctl_tfa);
 
 static struct attribute *intel_pmu_attrs[] = {
 	&dev_attr_freeze_on_smi.attr,
@@ -4440,6 +4654,32 @@ __init int intel_pmu_init(void)
 		name = "goldmont_plus";
 		break;
 
+	case INTEL_FAM6_ATOM_TREMONT_X:
+		x86_pmu.late_ack = true;
+		memcpy(hw_cache_event_ids, glp_hw_cache_event_ids,
+		       sizeof(hw_cache_event_ids));
+		memcpy(hw_cache_extra_regs, tnt_hw_cache_extra_regs,
+		       sizeof(hw_cache_extra_regs));
+		hw_cache_event_ids[C(ITLB)][C(OP_READ)][C(RESULT_ACCESS)] = -1;
+
+		intel_pmu_lbr_init_skl();
+
+		x86_pmu.event_constraints = intel_slm_event_constraints;
+		x86_pmu.extra_regs = intel_tnt_extra_regs;
+		/*
+		 * It's recommended to use CPU_CLK_UNHALTED.CORE_P + NPEBS
+		 * for precise cycles.
+		 */
+		x86_pmu.pebs_aliases = NULL;
+		x86_pmu.pebs_prec_dist = true;
+		x86_pmu.lbr_pt_coexist = true;
+		x86_pmu.flags |= PMU_FL_HAS_RSP_1;
+		x86_pmu.get_event_constraints = tnt_get_event_constraints;
+		extra_attr = slm_format_attr;
+		pr_cont("Tremont events, ");
+		name = "Tremont";
+		break;
+
 	case INTEL_FAM6_WESTMERE:
 	case INTEL_FAM6_WESTMERE_EP:
 	case INTEL_FAM6_WESTMERE_EX:
@@ -4688,13 +4928,41 @@ __init int intel_pmu_init(void)
 			x86_pmu.get_event_constraints = tfa_get_event_constraints;
 			x86_pmu.enable_all = intel_tfa_pmu_enable_all;
 			x86_pmu.commit_scheduling = intel_tfa_commit_scheduling;
-			intel_pmu_attrs[1] = &dev_attr_allow_tsx_force_abort.attr.attr;
+			intel_pmu_attrs[1] = &dev_attr_allow_tsx_force_abort.attr;
 		}
 
 		pr_cont("Skylake events, ");
 		name = "skylake";
 		break;
 
+	case INTEL_FAM6_ICELAKE_MOBILE:
+		x86_pmu.late_ack = true;
+		memcpy(hw_cache_event_ids, skl_hw_cache_event_ids, sizeof(hw_cache_event_ids));
+		memcpy(hw_cache_extra_regs, skl_hw_cache_extra_regs, sizeof(hw_cache_extra_regs));
+		hw_cache_event_ids[C(ITLB)][C(OP_READ)][C(RESULT_ACCESS)] = -1;
+		intel_pmu_lbr_init_skl();
+
+		x86_pmu.event_constraints = intel_icl_event_constraints;
+		x86_pmu.pebs_constraints = intel_icl_pebs_event_constraints;
+		x86_pmu.extra_regs = intel_icl_extra_regs;
+		x86_pmu.pebs_aliases = NULL;
+		x86_pmu.pebs_prec_dist = true;
+		x86_pmu.flags |= PMU_FL_HAS_RSP_1;
+		x86_pmu.flags |= PMU_FL_NO_HT_SHARING;
+
+		x86_pmu.hw_config = hsw_hw_config;
+		x86_pmu.get_event_constraints = icl_get_event_constraints;
+		extra_attr = boot_cpu_has(X86_FEATURE_RTM) ?
+			hsw_format_attr : nhm_format_attr;
+		extra_attr = merge_attr(extra_attr, skl_format_attr);
+		x86_pmu.cpu_events = get_icl_events_attrs();
+		x86_pmu.rtm_abort_event = X86_CONFIG(.event=0xca, .umask=0x02);
+		x86_pmu.lbr_pt_coexist = true;
+		intel_pmu_pebs_data_source_skl(false);
+		pr_cont("Icelake events, ");
+		name = "icelake";
+		break;
+
 	default:
 		switch (x86_pmu.version) {
 		case 1:
diff --git a/arch/x86/events/intel/cstate.c b/arch/x86/events/intel/cstate.c
index 94a4b7fc75d0..6072f92cb8ea 100644
--- a/arch/x86/events/intel/cstate.c
+++ b/arch/x86/events/intel/cstate.c
@@ -76,15 +76,15 @@
  *			       Scope: Package (physical package)
  *	MSR_PKG_C8_RESIDENCY:  Package C8 Residency Counter.
  *			       perf code: 0x04
- *			       Available model: HSW ULT,CNL
+ *			       Available model: HSW ULT,KBL,CNL
  *			       Scope: Package (physical package)
  *	MSR_PKG_C9_RESIDENCY:  Package C9 Residency Counter.
  *			       perf code: 0x05
- *			       Available model: HSW ULT,CNL
+ *			       Available model: HSW ULT,KBL,CNL
  *			       Scope: Package (physical package)
  *	MSR_PKG_C10_RESIDENCY: Package C10 Residency Counter.
  *			       perf code: 0x06
- *			       Available model: HSW ULT,GLM,CNL
+ *			       Available model: HSW ULT,KBL,GLM,CNL
  *			       Scope: Package (physical package)
  *
  */
@@ -566,8 +566,8 @@ static const struct x86_cpu_id intel_cstates_match[] __initconst = {
 	X86_CSTATES_MODEL(INTEL_FAM6_SKYLAKE_DESKTOP, snb_cstates),
 	X86_CSTATES_MODEL(INTEL_FAM6_SKYLAKE_X, snb_cstates),
 
-	X86_CSTATES_MODEL(INTEL_FAM6_KABYLAKE_MOBILE,  snb_cstates),
-	X86_CSTATES_MODEL(INTEL_FAM6_KABYLAKE_DESKTOP, snb_cstates),
+	X86_CSTATES_MODEL(INTEL_FAM6_KABYLAKE_MOBILE,  hswult_cstates),
+	X86_CSTATES_MODEL(INTEL_FAM6_KABYLAKE_DESKTOP, hswult_cstates),
 
 	X86_CSTATES_MODEL(INTEL_FAM6_CANNONLAKE_MOBILE, cnl_cstates),
 
@@ -578,6 +578,8 @@ static const struct x86_cpu_id intel_cstates_match[] __initconst = {
 	X86_CSTATES_MODEL(INTEL_FAM6_ATOM_GOLDMONT_X, glm_cstates),
 
 	X86_CSTATES_MODEL(INTEL_FAM6_ATOM_GOLDMONT_PLUS, glm_cstates),
+
+	X86_CSTATES_MODEL(INTEL_FAM6_ICELAKE_MOBILE, snb_cstates),
 	{ },
 };
 MODULE_DEVICE_TABLE(x86cpu, intel_cstates_match);
diff --git a/arch/x86/events/intel/ds.c b/arch/x86/events/intel/ds.c
index 10c99ce1fead..7a9f5dac5abe 100644
--- a/arch/x86/events/intel/ds.c
+++ b/arch/x86/events/intel/ds.c
@@ -849,6 +849,26 @@ struct event_constraint intel_skl_pebs_event_constraints[] = {
 	EVENT_CONSTRAINT_END
 };
 
+struct event_constraint intel_icl_pebs_event_constraints[] = {
+	INTEL_FLAGS_UEVENT_CONSTRAINT(0x1c0, 0x100000000ULL),	/* INST_RETIRED.PREC_DIST */
+	INTEL_FLAGS_UEVENT_CONSTRAINT(0x0400, 0x400000000ULL),	/* SLOTS */
+
+	INTEL_PLD_CONSTRAINT(0x1cd, 0xff),			/* MEM_TRANS_RETIRED.LOAD_LATENCY */
+	INTEL_FLAGS_UEVENT_CONSTRAINT_DATALA_LD(0x1d0, 0xf),	/* MEM_INST_RETIRED.LOAD */
+	INTEL_FLAGS_UEVENT_CONSTRAINT_DATALA_ST(0x2d0, 0xf),	/* MEM_INST_RETIRED.STORE */
+
+	INTEL_FLAGS_EVENT_CONSTRAINT_DATALA_LD_RANGE(0xd1, 0xd4, 0xf), /* MEM_LOAD_*_RETIRED.* */
+
+	INTEL_FLAGS_EVENT_CONSTRAINT(0xd0, 0xf),		/* MEM_INST_RETIRED.* */
+
+	/*
+	 * Everything else is handled by PMU_FL_PEBS_ALL, because we
+	 * need the full constraints from the main table.
+	 */
+
+	EVENT_CONSTRAINT_END
+};
+
 struct event_constraint *intel_pebs_constraints(struct perf_event *event)
 {
 	struct event_constraint *c;
@@ -858,7 +878,7 @@ struct event_constraint *intel_pebs_constraints(struct perf_event *event)
 
 	if (x86_pmu.pebs_constraints) {
 		for_each_event_constraint(c, x86_pmu.pebs_constraints) {
-			if ((event->hw.config & c->cmask) == c->code) {
+			if (constraint_match(c, event->hw.config)) {
 				event->hw.flags |= c->flags;
 				return c;
 			}
@@ -906,17 +926,87 @@ static inline void pebs_update_threshold(struct cpu_hw_events *cpuc)
 
 	if (cpuc->n_pebs == cpuc->n_large_pebs) {
 		threshold = ds->pebs_absolute_maximum -
-			reserved * x86_pmu.pebs_record_size;
+			reserved * cpuc->pebs_record_size;
 	} else {
-		threshold = ds->pebs_buffer_base + x86_pmu.pebs_record_size;
+		threshold = ds->pebs_buffer_base + cpuc->pebs_record_size;
 	}
 
 	ds->pebs_interrupt_threshold = threshold;
 }
 
+static void adaptive_pebs_record_size_update(void)
+{
+	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
+	u64 pebs_data_cfg = cpuc->pebs_data_cfg;
+	int sz = sizeof(struct pebs_basic);
+
+	if (pebs_data_cfg & PEBS_DATACFG_MEMINFO)
+		sz += sizeof(struct pebs_meminfo);
+	if (pebs_data_cfg & PEBS_DATACFG_GP)
+		sz += sizeof(struct pebs_gprs);
+	if (pebs_data_cfg & PEBS_DATACFG_XMMS)
+		sz += sizeof(struct pebs_xmm);
+	if (pebs_data_cfg & PEBS_DATACFG_LBRS)
+		sz += x86_pmu.lbr_nr * sizeof(struct pebs_lbr_entry);
+
+	cpuc->pebs_record_size = sz;
+}
+
+#define PERF_PEBS_MEMINFO_TYPE	(PERF_SAMPLE_ADDR | PERF_SAMPLE_DATA_SRC |   \
+				PERF_SAMPLE_PHYS_ADDR | PERF_SAMPLE_WEIGHT | \
+				PERF_SAMPLE_TRANSACTION)
+
+static u64 pebs_update_adaptive_cfg(struct perf_event *event)
+{
+	struct perf_event_attr *attr = &event->attr;
+	u64 sample_type = attr->sample_type;
+	u64 pebs_data_cfg = 0;
+	bool gprs, tsx_weight;
+
+	if (!(sample_type & ~(PERF_SAMPLE_IP|PERF_SAMPLE_TIME)) &&
+	    attr->precise_ip > 1)
+		return pebs_data_cfg;
+
+	if (sample_type & PERF_PEBS_MEMINFO_TYPE)
+		pebs_data_cfg |= PEBS_DATACFG_MEMINFO;
+
+	/*
+	 * We need GPRs when:
+	 * + user requested them
+	 * + precise_ip < 2 for the non event IP
+	 * + For RTM TSX weight we need GPRs for the abort code.
+	 */
+	gprs = (sample_type & PERF_SAMPLE_REGS_INTR) &&
+	       (attr->sample_regs_intr & PEBS_GP_REGS);
+
+	tsx_weight = (sample_type & PERF_SAMPLE_WEIGHT) &&
+		     ((attr->config & INTEL_ARCH_EVENT_MASK) ==
+		      x86_pmu.rtm_abort_event);
+
+	if (gprs || (attr->precise_ip < 2) || tsx_weight)
+		pebs_data_cfg |= PEBS_DATACFG_GP;
+
+	if ((sample_type & PERF_SAMPLE_REGS_INTR) &&
+	    (attr->sample_regs_intr & PEBS_XMM_REGS))
+		pebs_data_cfg |= PEBS_DATACFG_XMMS;
+
+	if (sample_type & PERF_SAMPLE_BRANCH_STACK) {
+		/*
+		 * For now always log all LBRs. Could configure this
+		 * later.
+		 */
+		pebs_data_cfg |= PEBS_DATACFG_LBRS |
+			((x86_pmu.lbr_nr-1) << PEBS_DATACFG_LBR_SHIFT);
+	}
+
+	return pebs_data_cfg;
+}
+
 static void
-pebs_update_state(bool needed_cb, struct cpu_hw_events *cpuc, struct pmu *pmu)
+pebs_update_state(bool needed_cb, struct cpu_hw_events *cpuc,
+		  struct perf_event *event, bool add)
 {
+	struct pmu *pmu = event->ctx->pmu;
 	/*
 	 * Make sure we get updated with the first PEBS
 	 * event. It will trigger also during removal, but
@@ -933,6 +1023,29 @@ pebs_update_state(bool needed_cb, struct cpu_hw_events *cpuc, struct pmu *pmu)
 		update = true;
 	}
 
+	/*
+	 * The PEBS record doesn't shrink on pmu::del(). Doing so would require
+	 * iterating all remaining PEBS events to reconstruct the config.
+	 */
+	if (x86_pmu.intel_cap.pebs_baseline && add) {
+		u64 pebs_data_cfg;
+
+		/* Clear pebs_data_cfg and pebs_record_size for first PEBS. */
+		if (cpuc->n_pebs == 1) {
+			cpuc->pebs_data_cfg = 0;
+			cpuc->pebs_record_size = sizeof(struct pebs_basic);
+		}
+
+		pebs_data_cfg = pebs_update_adaptive_cfg(event);
+
+		/* Update pebs_record_size if new event requires more data. */
+		if (pebs_data_cfg & ~cpuc->pebs_data_cfg) {
+			cpuc->pebs_data_cfg |= pebs_data_cfg;
+			adaptive_pebs_record_size_update();
+			update = true;
+		}
+	}
+
 	if (update)
 		pebs_update_threshold(cpuc);
 }
@@ -947,7 +1060,7 @@ void intel_pmu_pebs_add(struct perf_event *event)
 	if (hwc->flags & PERF_X86_EVENT_LARGE_PEBS)
 		cpuc->n_large_pebs++;
 
-	pebs_update_state(needed_cb, cpuc, event->ctx->pmu);
+	pebs_update_state(needed_cb, cpuc, event, true);
 }
 
 void intel_pmu_pebs_enable(struct perf_event *event)
@@ -960,11 +1073,19 @@ void intel_pmu_pebs_enable(struct perf_event *event)
 
 	cpuc->pebs_enabled |= 1ULL << hwc->idx;
 
-	if (event->hw.flags & PERF_X86_EVENT_PEBS_LDLAT)
+	if ((event->hw.flags & PERF_X86_EVENT_PEBS_LDLAT) && (x86_pmu.version < 5))
 		cpuc->pebs_enabled |= 1ULL << (hwc->idx + 32);
 	else if (event->hw.flags & PERF_X86_EVENT_PEBS_ST)
 		cpuc->pebs_enabled |= 1ULL << 63;
 
+	if (x86_pmu.intel_cap.pebs_baseline) {
+		hwc->config |= ICL_EVENTSEL_ADAPTIVE;
+		if (cpuc->pebs_data_cfg != cpuc->active_pebs_data_cfg) {
+			wrmsrl(MSR_PEBS_DATA_CFG, cpuc->pebs_data_cfg);
+			cpuc->active_pebs_data_cfg = cpuc->pebs_data_cfg;
+		}
+	}
+
 	/*
 	 * Use auto-reload if possible to save a MSR write in the PMI.
 	 * This must be done in pmu::start(), because PERF_EVENT_IOC_PERIOD.
@@ -991,7 +1112,7 @@ void intel_pmu_pebs_del(struct perf_event *event)
 	if (hwc->flags & PERF_X86_EVENT_LARGE_PEBS)
 		cpuc->n_large_pebs--;
 
-	pebs_update_state(needed_cb, cpuc, event->ctx->pmu);
+	pebs_update_state(needed_cb, cpuc, event, false);
 }
 
 void intel_pmu_pebs_disable(struct perf_event *event)
@@ -1004,7 +1125,8 @@ void intel_pmu_pebs_disable(struct perf_event *event)
 
 	cpuc->pebs_enabled &= ~(1ULL << hwc->idx);
 
-	if (event->hw.flags & PERF_X86_EVENT_PEBS_LDLAT)
+	if ((event->hw.flags & PERF_X86_EVENT_PEBS_LDLAT) &&
+	    (x86_pmu.version < 5))
 		cpuc->pebs_enabled &= ~(1ULL << (hwc->idx + 32));
 	else if (event->hw.flags & PERF_X86_EVENT_PEBS_ST)
 		cpuc->pebs_enabled &= ~(1ULL << 63);
@@ -1125,34 +1247,57 @@ static int intel_pmu_pebs_fixup_ip(struct pt_regs *regs)
 	return 0;
 }
 
-static inline u64 intel_hsw_weight(struct pebs_record_skl *pebs)
+static inline u64 intel_get_tsx_weight(u64 tsx_tuning)
 {
-	if (pebs->tsx_tuning) {
-		union hsw_tsx_tuning tsx = { .value = pebs->tsx_tuning };
+	if (tsx_tuning) {
+		union hsw_tsx_tuning tsx = { .value = tsx_tuning };
 		return tsx.cycles_last_block;
 	}
 	return 0;
 }
 
-static inline u64 intel_hsw_transaction(struct pebs_record_skl *pebs)
+static inline u64 intel_get_tsx_transaction(u64 tsx_tuning, u64 ax)
 {
-	u64 txn = (pebs->tsx_tuning & PEBS_HSW_TSX_FLAGS) >> 32;
+	u64 txn = (tsx_tuning & PEBS_HSW_TSX_FLAGS) >> 32;
 
 	/* For RTM XABORTs also log the abort code from AX */
-	if ((txn & PERF_TXN_TRANSACTION) && (pebs->ax & 1))
-		txn |= ((pebs->ax >> 24) & 0xff) << PERF_TXN_ABORT_SHIFT;
+	if ((txn & PERF_TXN_TRANSACTION) && (ax & 1))
+		txn |= ((ax >> 24) & 0xff) << PERF_TXN_ABORT_SHIFT;
 	return txn;
 }
 
-static void setup_pebs_sample_data(struct perf_event *event,
-				   struct pt_regs *iregs, void *__pebs,
-				   struct perf_sample_data *data,
-				   struct pt_regs *regs)
+static inline u64 get_pebs_status(void *n)
 {
+	if (x86_pmu.intel_cap.pebs_format < 4)
+		return ((struct pebs_record_nhm *)n)->status;
+	return ((struct pebs_basic *)n)->applicable_counters;
+}
+
 #define PERF_X86_EVENT_PEBS_HSW_PREC \
 		(PERF_X86_EVENT_PEBS_ST_HSW | \
 		 PERF_X86_EVENT_PEBS_LD_HSW | \
 		 PERF_X86_EVENT_PEBS_NA_HSW)
+
+static u64 get_data_src(struct perf_event *event, u64 aux)
+{
+	u64 val = PERF_MEM_NA;
+	int fl = event->hw.flags;
+	bool fst = fl & (PERF_X86_EVENT_PEBS_ST | PERF_X86_EVENT_PEBS_HSW_PREC);
+
+	if (fl & PERF_X86_EVENT_PEBS_LDLAT)
+		val = load_latency_data(aux);
+	else if (fst && (fl & PERF_X86_EVENT_PEBS_HSW_PREC))
+		val = precise_datala_hsw(event, aux);
+	else if (fst)
+		val = precise_store_data(aux);
+	return val;
+}
+
+static void setup_pebs_fixed_sample_data(struct perf_event *event,
+				   struct pt_regs *iregs, void *__pebs,
+				   struct perf_sample_data *data,
+				   struct pt_regs *regs)
+{
 	/*
 	 * We cast to the biggest pebs_record but are careful not to
 	 * unconditionally access the 'extra' entries.
@@ -1160,17 +1305,13 @@ static void setup_pebs_sample_data(struct perf_event *event,
 	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
 	struct pebs_record_skl *pebs = __pebs;
 	u64 sample_type;
-	int fll, fst, dsrc;
-	int fl = event->hw.flags;
+	int fll;
 
 	if (pebs == NULL)
 		return;
 
 	sample_type = event->attr.sample_type;
-	dsrc = sample_type & PERF_SAMPLE_DATA_SRC;
-
-	fll = fl & PERF_X86_EVENT_PEBS_LDLAT;
-	fst = fl & (PERF_X86_EVENT_PEBS_ST | PERF_X86_EVENT_PEBS_HSW_PREC);
+	fll = event->hw.flags & PERF_X86_EVENT_PEBS_LDLAT;
 
 	perf_sample_data_init(data, 0, event->hw.last_period);
 
@@ -1185,16 +1326,8 @@ static void setup_pebs_sample_data(struct perf_event *event,
 	/*
 	 * data.data_src encodes the data source
 	 */
-	if (dsrc) {
-		u64 val = PERF_MEM_NA;
-		if (fll)
-			val = load_latency_data(pebs->dse);
-		else if (fst && (fl & PERF_X86_EVENT_PEBS_HSW_PREC))
-			val = precise_datala_hsw(event, pebs->dse);
-		else if (fst)
-			val = precise_store_data(pebs->dse);
-		data->data_src.val = val;
-	}
+	if (sample_type & PERF_SAMPLE_DATA_SRC)
+		data->data_src.val = get_data_src(event, pebs->dse);
 
 	/*
 	 * We must however always use iregs for the unwinder to stay sane; the
@@ -1281,10 +1414,11 @@ static void setup_pebs_sample_data(struct perf_event *event,
 	if (x86_pmu.intel_cap.pebs_format >= 2) {
 		/* Only set the TSX weight when no memory weight. */
 		if ((sample_type & PERF_SAMPLE_WEIGHT) && !fll)
-			data->weight = intel_hsw_weight(pebs);
+			data->weight = intel_get_tsx_weight(pebs->tsx_tuning);
 
 		if (sample_type & PERF_SAMPLE_TRANSACTION)
-			data->txn = intel_hsw_transaction(pebs);
+			data->txn = intel_get_tsx_transaction(pebs->tsx_tuning,
+							      pebs->ax);
 	}
 
 	/*
@@ -1301,6 +1435,140 @@ static void setup_pebs_sample_data(struct perf_event *event,
 		data->br_stack = &cpuc->lbr_stack;
 }
 
+static void adaptive_pebs_save_regs(struct pt_regs *regs,
+				    struct pebs_gprs *gprs)
+{
+	regs->ax = gprs->ax;
+	regs->bx = gprs->bx;
+	regs->cx = gprs->cx;
+	regs->dx = gprs->dx;
+	regs->si = gprs->si;
+	regs->di = gprs->di;
+	regs->bp = gprs->bp;
+	regs->sp = gprs->sp;
+#ifndef CONFIG_X86_32
+	regs->r8 = gprs->r8;
+	regs->r9 = gprs->r9;
+	regs->r10 = gprs->r10;
+	regs->r11 = gprs->r11;
+	regs->r12 = gprs->r12;
+	regs->r13 = gprs->r13;
+	regs->r14 = gprs->r14;
+	regs->r15 = gprs->r15;
+#endif
+}
+
+/*
+ * With adaptive PEBS the layout depends on what fields are configured.
+ */
+
+static void setup_pebs_adaptive_sample_data(struct perf_event *event,
+					    struct pt_regs *iregs, void *__pebs,
+					    struct perf_sample_data *data,
+					    struct pt_regs *regs)
+{
+	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
+	struct pebs_basic *basic = __pebs;
+	void *next_record = basic + 1;
+	u64 sample_type;
+	u64 format_size;
+	struct pebs_meminfo *meminfo = NULL;
+	struct pebs_gprs *gprs = NULL;
+	struct x86_perf_regs *perf_regs;
+
+	if (basic == NULL)
+		return;
+
+	perf_regs = container_of(regs, struct x86_perf_regs, regs);
+	perf_regs->xmm_regs = NULL;
+
+	sample_type = event->attr.sample_type;
+	format_size = basic->format_size;
+	perf_sample_data_init(data, 0, event->hw.last_period);
+	data->period = event->hw.last_period;
+
+	if (event->attr.use_clockid == 0)
+		data->time = native_sched_clock_from_tsc(basic->tsc);
+
+	/*
+	 * We must however always use iregs for the unwinder to stay sane; the
+	 * record BP,SP,IP can point into thin air when the record is from a
+	 * previous PMI context or an (I)RET happened between the record and
+	 * PMI.
+	 */
+	if (sample_type & PERF_SAMPLE_CALLCHAIN)
+		data->callchain = perf_callchain(event, iregs);
+
+	*regs = *iregs;
+	/* The ip in basic is EventingIP */
+	set_linear_ip(regs, basic->ip);
+	regs->flags = PERF_EFLAGS_EXACT;
+
+	/*
+	 * The record for MEMINFO is in front of GP
+	 * But PERF_SAMPLE_TRANSACTION needs gprs->ax.
+	 * Save the pointer here but process later.
+	 */
+	if (format_size & PEBS_DATACFG_MEMINFO) {
+		meminfo = next_record;
+		next_record = meminfo + 1;
+	}
+
+	if (format_size & PEBS_DATACFG_GP) {
+		gprs = next_record;
+		next_record = gprs + 1;
+
+		if (event->attr.precise_ip < 2) {
+			set_linear_ip(regs, gprs->ip);
+			regs->flags &= ~PERF_EFLAGS_EXACT;
+		}
+
+		if (sample_type & PERF_SAMPLE_REGS_INTR)
+			adaptive_pebs_save_regs(regs, gprs);
+	}
+
+	if (format_size & PEBS_DATACFG_MEMINFO) {
+		if (sample_type & PERF_SAMPLE_WEIGHT)
+			data->weight = meminfo->latency ?:
+				intel_get_tsx_weight(meminfo->tsx_tuning);
+
+		if (sample_type & PERF_SAMPLE_DATA_SRC)
+			data->data_src.val = get_data_src(event, meminfo->aux);
+
+		if (sample_type & (PERF_SAMPLE_ADDR | PERF_SAMPLE_PHYS_ADDR))
+			data->addr = meminfo->address;
+
+		if (sample_type & PERF_SAMPLE_TRANSACTION)
+			data->txn = intel_get_tsx_transaction(meminfo->tsx_tuning,
+							  gprs ? gprs->ax : 0);
+	}
+
+	if (format_size & PEBS_DATACFG_XMMS) {
+		struct pebs_xmm *xmm = next_record;
+
+		next_record = xmm + 1;
+		perf_regs->xmm_regs = xmm->xmm;
+	}
+
+	if (format_size & PEBS_DATACFG_LBRS) {
+		struct pebs_lbr *lbr = next_record;
+		int num_lbr = ((format_size >> PEBS_DATACFG_LBR_SHIFT)
+					& 0xff) + 1;
+		next_record = next_record + num_lbr*sizeof(struct pebs_lbr_entry);
+
+		if (has_branch_stack(event)) {
+			intel_pmu_store_pebs_lbrs(lbr);
+			data->br_stack = &cpuc->lbr_stack;
+		}
+	}
+
+	WARN_ONCE(next_record != __pebs + (format_size >> 48),
+			"PEBS record size %llu, expected %llu, config %llx\n",
+			format_size >> 48,
+			(u64)(next_record - __pebs),
+			basic->format_size);
+}
+
 static inline void *
 get_next_pebs_record_by_bit(void *base, void *top, int bit)
 {
@@ -1318,19 +1586,19 @@ get_next_pebs_record_by_bit(void *base, void *top, int bit)
 	if (base == NULL)
 		return NULL;
 
-	for (at = base; at < top; at += x86_pmu.pebs_record_size) {
-		struct pebs_record_nhm *p = at;
+	for (at = base; at < top; at += cpuc->pebs_record_size) {
+		unsigned long status = get_pebs_status(at);
 
-		if (test_bit(bit, (unsigned long *)&p->status)) {
+		if (test_bit(bit, (unsigned long *)&status)) {
 			/* PEBS v3 has accurate status bits */
 			if (x86_pmu.intel_cap.pebs_format >= 3)
 				return at;
 
-			if (p->status == (1 << bit))
+			if (status == (1 << bit))
 				return at;
 
 			/* clear non-PEBS bit and re-check */
-			pebs_status = p->status & cpuc->pebs_enabled;
+			pebs_status = status & cpuc->pebs_enabled;
 			pebs_status &= PEBS_COUNTER_MASK;
 			if (pebs_status == (1 << bit))
 				return at;
@@ -1410,11 +1678,18 @@ intel_pmu_save_and_restart_reload(struct perf_event *event, int count)
 static void __intel_pmu_pebs_event(struct perf_event *event,
 				   struct pt_regs *iregs,
 				   void *base, void *top,
-				   int bit, int count)
+				   int bit, int count,
+				   void (*setup_sample)(struct perf_event *,
+						struct pt_regs *,
+						void *,
+						struct perf_sample_data *,
+						struct pt_regs *))
 {
+	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
 	struct hw_perf_event *hwc = &event->hw;
 	struct perf_sample_data data;
-	struct pt_regs regs;
+	struct x86_perf_regs perf_regs;
+	struct pt_regs *regs = &perf_regs.regs;
 	void *at = get_next_pebs_record_by_bit(base, top, bit);
 
 	if (hwc->flags & PERF_X86_EVENT_AUTO_RELOAD) {
@@ -1429,20 +1704,20 @@ static void __intel_pmu_pebs_event(struct perf_event *event,
 		return;
 
 	while (count > 1) {
-		setup_pebs_sample_data(event, iregs, at, &data, &regs);
-		perf_event_output(event, &data, &regs);
-		at += x86_pmu.pebs_record_size;
+		setup_sample(event, iregs, at, &data, regs);
+		perf_event_output(event, &data, regs);
+		at += cpuc->pebs_record_size;
 		at = get_next_pebs_record_by_bit(at, top, bit);
 		count--;
 	}
 
-	setup_pebs_sample_data(event, iregs, at, &data, &regs);
+	setup_sample(event, iregs, at, &data, regs);
 
 	/*
 	 * All but the last records are processed.
 	 * The last one is left to be able to call the overflow handler.
 	 */
-	if (perf_event_overflow(event, &data, &regs)) {
+	if (perf_event_overflow(event, &data, regs)) {
 		x86_pmu_stop(event, 0);
 		return;
 	}
@@ -1483,7 +1758,27 @@ static void intel_pmu_drain_pebs_core(struct pt_regs *iregs)
 		return;
 	}
 
-	__intel_pmu_pebs_event(event, iregs, at, top, 0, n);
+	__intel_pmu_pebs_event(event, iregs, at, top, 0, n,
+			       setup_pebs_fixed_sample_data);
+}
+
+static void intel_pmu_pebs_event_update_no_drain(struct cpu_hw_events *cpuc, int size)
+{
+	struct perf_event *event;
+	int bit;
+
+	/*
+	 * The drain_pebs() could be called twice in a short period
+	 * for auto-reload event in pmu::read(). There are no
+	 * overflows have happened in between.
+	 * It needs to call intel_pmu_save_and_restart_reload() to
+	 * update the event->count for this case.
+	 */
+	for_each_set_bit(bit, (unsigned long *)&cpuc->pebs_enabled, size) {
+		event = cpuc->events[bit];
+		if (event->hw.flags & PERF_X86_EVENT_AUTO_RELOAD)
+			intel_pmu_save_and_restart_reload(event, 0);
+	}
 }
 
 static void intel_pmu_drain_pebs_nhm(struct pt_regs *iregs)
@@ -1513,19 +1808,7 @@ static void intel_pmu_drain_pebs_nhm(struct pt_regs *iregs)
 	}
 
 	if (unlikely(base >= top)) {
-		/*
-		 * The drain_pebs() could be called twice in a short period
-		 * for auto-reload event in pmu::read(). There are no
-		 * overflows have happened in between.
-		 * It needs to call intel_pmu_save_and_restart_reload() to
-		 * update the event->count for this case.
-		 */
-		for_each_set_bit(bit, (unsigned long *)&cpuc->pebs_enabled,
-				 size) {
-			event = cpuc->events[bit];
-			if (event->hw.flags & PERF_X86_EVENT_AUTO_RELOAD)
-				intel_pmu_save_and_restart_reload(event, 0);
-		}
+		intel_pmu_pebs_event_update_no_drain(cpuc, size);
 		return;
 	}
 
@@ -1538,8 +1821,7 @@ static void intel_pmu_drain_pebs_nhm(struct pt_regs *iregs)
 
 		/* PEBS v3 has more accurate status bits */
 		if (x86_pmu.intel_cap.pebs_format >= 3) {
-			for_each_set_bit(bit, (unsigned long *)&pebs_status,
-					 size)
+			for_each_set_bit(bit, (unsigned long *)&pebs_status, size)
 				counts[bit]++;
 
 			continue;
@@ -1578,8 +1860,7 @@ static void intel_pmu_drain_pebs_nhm(struct pt_regs *iregs)
 		 * If collision happened, the record will be dropped.
 		 */
 		if (p->status != (1ULL << bit)) {
-			for_each_set_bit(i, (unsigned long *)&pebs_status,
-					 x86_pmu.max_pebs_events)
+			for_each_set_bit(i, (unsigned long *)&pebs_status, size)
 				error[i]++;
 			continue;
 		}
@@ -1587,7 +1868,7 @@ static void intel_pmu_drain_pebs_nhm(struct pt_regs *iregs)
 		counts[bit]++;
 	}
 
-	for (bit = 0; bit < size; bit++) {
+	for_each_set_bit(bit, (unsigned long *)&mask, size) {
 		if ((counts[bit] == 0) && (error[bit] == 0))
 			continue;
 
@@ -1608,11 +1889,66 @@ static void intel_pmu_drain_pebs_nhm(struct pt_regs *iregs)
 
 		if (counts[bit]) {
 			__intel_pmu_pebs_event(event, iregs, base,
-					       top, bit, counts[bit]);
+					       top, bit, counts[bit],
+					       setup_pebs_fixed_sample_data);
 		}
 	}
 }
 
+static void intel_pmu_drain_pebs_icl(struct pt_regs *iregs)
+{
+	short counts[INTEL_PMC_IDX_FIXED + MAX_FIXED_PEBS_EVENTS] = {};
+	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
+	struct debug_store *ds = cpuc->ds;
+	struct perf_event *event;
+	void *base, *at, *top;
+	int bit, size;
+	u64 mask;
+
+	if (!x86_pmu.pebs_active)
+		return;
+
+	base = (struct pebs_basic *)(unsigned long)ds->pebs_buffer_base;
+	top = (struct pebs_basic *)(unsigned long)ds->pebs_index;
+
+	ds->pebs_index = ds->pebs_buffer_base;
+
+	mask = ((1ULL << x86_pmu.max_pebs_events) - 1) |
+	       (((1ULL << x86_pmu.num_counters_fixed) - 1) << INTEL_PMC_IDX_FIXED);
+	size = INTEL_PMC_IDX_FIXED + x86_pmu.num_counters_fixed;
+
+	if (unlikely(base >= top)) {
+		intel_pmu_pebs_event_update_no_drain(cpuc, size);
+		return;
+	}
+
+	for (at = base; at < top; at += cpuc->pebs_record_size) {
+		u64 pebs_status;
+
+		pebs_status = get_pebs_status(at) & cpuc->pebs_enabled;
+		pebs_status &= mask;
+
+		for_each_set_bit(bit, (unsigned long *)&pebs_status, size)
+			counts[bit]++;
+	}
+
+	for_each_set_bit(bit, (unsigned long *)&mask, size) {
+		if (counts[bit] == 0)
+			continue;
+
+		event = cpuc->events[bit];
+		if (WARN_ON_ONCE(!event))
+			continue;
+
+		if (WARN_ON_ONCE(!event->attr.precise_ip))
+			continue;
+
+		__intel_pmu_pebs_event(event, iregs, base,
+				       top, bit, counts[bit],
+				       setup_pebs_adaptive_sample_data);
+	}
+}
+
 /*
  * BTS, PEBS probe and setup
  */
@@ -1628,12 +1964,18 @@ void __init intel_ds_init(void)
 	x86_pmu.bts  = boot_cpu_has(X86_FEATURE_BTS);
 	x86_pmu.pebs = boot_cpu_has(X86_FEATURE_PEBS);
 	x86_pmu.pebs_buffer_size = PEBS_BUFFER_SIZE;
-	if (x86_pmu.version <= 4)
+	if (x86_pmu.version <= 4) {
 		x86_pmu.pebs_no_isolation = 1;
+		x86_pmu.pebs_no_xmm_regs = 1;
+	}
 	if (x86_pmu.pebs) {
 		char pebs_type = x86_pmu.intel_cap.pebs_trap ?  '+' : '-';
+		char *pebs_qual = "";
 		int format = x86_pmu.intel_cap.pebs_format;
 
+		if (format < 4)
+			x86_pmu.intel_cap.pebs_baseline = 0;
+
 		switch (format) {
 		case 0:
 			pr_cont("PEBS fmt0%c, ", pebs_type);
@@ -1669,6 +2011,29 @@ void __init intel_ds_init(void)
 			x86_pmu.large_pebs_flags |= PERF_SAMPLE_TIME;
 			break;
 
+		case 4:
+			x86_pmu.drain_pebs = intel_pmu_drain_pebs_icl;
+			x86_pmu.pebs_record_size = sizeof(struct pebs_basic);
+			if (x86_pmu.intel_cap.pebs_baseline) {
+				x86_pmu.large_pebs_flags |=
+					PERF_SAMPLE_BRANCH_STACK |
+					PERF_SAMPLE_TIME;
+				x86_pmu.flags |= PMU_FL_PEBS_ALL;
+				pebs_qual = "-baseline";
+			} else {
+				/* Only basic record supported */
+				x86_pmu.pebs_no_xmm_regs = 1;
+				x86_pmu.large_pebs_flags &=
+					~(PERF_SAMPLE_ADDR |
+					  PERF_SAMPLE_TIME |
+					  PERF_SAMPLE_DATA_SRC |
+					  PERF_SAMPLE_TRANSACTION |
+					  PERF_SAMPLE_REGS_USER |
+					  PERF_SAMPLE_REGS_INTR);
+			}
+			pr_cont("PEBS fmt4%c%s, ", pebs_type, pebs_qual);
+			break;
+
 		default:
 			pr_cont("no PEBS fmt%d%c, ", format, pebs_type);
 			x86_pmu.pebs = 0;
diff --git a/arch/x86/events/intel/lbr.c b/arch/x86/events/intel/lbr.c
index 580c1b91c454..6f814a27416b 100644
--- a/arch/x86/events/intel/lbr.c
+++ b/arch/x86/events/intel/lbr.c
@@ -488,6 +488,8 @@ void intel_pmu_lbr_add(struct perf_event *event)
 	 * be 'new'. Conversely, a new event can get installed through the
 	 * context switch path for the first time.
 	 */
+	if (x86_pmu.intel_cap.pebs_baseline && event->attr.precise_ip > 0)
+		cpuc->lbr_pebs_users++;
 	perf_sched_cb_inc(event->ctx->pmu);
 	if (!cpuc->lbr_users++ && !event->total_time_running)
 		intel_pmu_lbr_reset();
@@ -507,8 +509,11 @@ void intel_pmu_lbr_del(struct perf_event *event)
 		task_ctx->lbr_callstack_users--;
 	}
 
+	if (x86_pmu.intel_cap.pebs_baseline && event->attr.precise_ip > 0)
+		cpuc->lbr_pebs_users--;
 	cpuc->lbr_users--;
 	WARN_ON_ONCE(cpuc->lbr_users < 0);
+	WARN_ON_ONCE(cpuc->lbr_pebs_users < 0);
 	perf_sched_cb_dec(event->ctx->pmu);
 }
 
@@ -658,7 +663,13 @@ void intel_pmu_lbr_read(void)
 {
 	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
 
-	if (!cpuc->lbr_users)
+	/*
+	 * Don't read when all LBRs users are using adaptive PEBS.
+	 *
+	 * This could be smarter and actually check the event,
+	 * but this simple approach seems to work for now.
+	 */
+	if (!cpuc->lbr_users || cpuc->lbr_users == cpuc->lbr_pebs_users)
 		return;
 
 	if (x86_pmu.intel_cap.lbr_format == LBR_FORMAT_32)
@@ -1080,6 +1091,28 @@ intel_pmu_lbr_filter(struct cpu_hw_events *cpuc)
 	}
 }
 
+void intel_pmu_store_pebs_lbrs(struct pebs_lbr *lbr)
+{
+	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
+	int i;
+
+	cpuc->lbr_stack.nr = x86_pmu.lbr_nr;
+	for (i = 0; i < x86_pmu.lbr_nr; i++) {
+		u64 info = lbr->lbr[i].info;
+		struct perf_branch_entry *e = &cpuc->lbr_entries[i];
+
+		e->from		= lbr->lbr[i].from;
+		e->to		= lbr->lbr[i].to;
+		e->mispred	= !!(info & LBR_INFO_MISPRED);
+		e->predicted	= !(info & LBR_INFO_MISPRED);
+		e->in_tx	= !!(info & LBR_INFO_IN_TX);
+		e->abort	= !!(info & LBR_INFO_ABORT);
+		e->cycles	= info & LBR_INFO_CYCLES;
+		e->reserved	= 0;
+	}
+	intel_pmu_lbr_filter(cpuc);
+}
+
 /*
  * Map interface branch filters onto LBR filters
  */
diff --git a/arch/x86/events/intel/pt.c b/arch/x86/events/intel/pt.c
index fb3a2f13fc70..339d7628080c 100644
--- a/arch/x86/events/intel/pt.c
+++ b/arch/x86/events/intel/pt.c
@@ -1525,8 +1525,7 @@ static __init int pt_init(void)
 	}
 
 	if (!intel_pt_validate_hw_cap(PT_CAP_topa_multiple_entries))
-		pt_pmu.pmu.capabilities =
-			PERF_PMU_CAP_AUX_NO_SG | PERF_PMU_CAP_AUX_SW_DOUBLEBUF;
+		pt_pmu.pmu.capabilities = PERF_PMU_CAP_AUX_NO_SG;
 
 	pt_pmu.pmu.capabilities	|= PERF_PMU_CAP_EXCLUSIVE | PERF_PMU_CAP_ITRACE;
 	pt_pmu.pmu.attr_groups		 = pt_attr_groups;
diff --git a/arch/x86/events/intel/rapl.c b/arch/x86/events/intel/rapl.c
index 94dc564146ca..37ebf6fc5415 100644
--- a/arch/x86/events/intel/rapl.c
+++ b/arch/x86/events/intel/rapl.c
@@ -775,6 +775,8 @@ static const struct x86_cpu_id rapl_cpu_match[] __initconst = {
 	X86_RAPL_MODEL_MATCH(INTEL_FAM6_ATOM_GOLDMONT_X, hsw_rapl_init),
 
 	X86_RAPL_MODEL_MATCH(INTEL_FAM6_ATOM_GOLDMONT_PLUS, hsw_rapl_init),
+
+	X86_RAPL_MODEL_MATCH(INTEL_FAM6_ICELAKE_MOBILE,  skl_rapl_init),
 	{},
 };
 
diff --git a/arch/x86/events/intel/uncore.c b/arch/x86/events/intel/uncore.c
index 9fe64c01a2e5..fc40a1473058 100644
--- a/arch/x86/events/intel/uncore.c
+++ b/arch/x86/events/intel/uncore.c
@@ -1367,6 +1367,11 @@ static const struct intel_uncore_init_fun skx_uncore_init __initconst = {
 	.pci_init = skx_uncore_pci_init,
 };
 
+static const struct intel_uncore_init_fun icl_uncore_init __initconst = {
+	.cpu_init = icl_uncore_cpu_init,
+	.pci_init = skl_uncore_pci_init,
+};
+
 static const struct x86_cpu_id intel_uncore_match[] __initconst = {
 	X86_UNCORE_MODEL_MATCH(INTEL_FAM6_NEHALEM_EP,	  nhm_uncore_init),
 	X86_UNCORE_MODEL_MATCH(INTEL_FAM6_NEHALEM,	  nhm_uncore_init),
@@ -1393,6 +1398,7 @@ static const struct x86_cpu_id intel_uncore_match[] __initconst = {
 	X86_UNCORE_MODEL_MATCH(INTEL_FAM6_SKYLAKE_X,      skx_uncore_init),
 	X86_UNCORE_MODEL_MATCH(INTEL_FAM6_KABYLAKE_MOBILE, skl_uncore_init),
 	X86_UNCORE_MODEL_MATCH(INTEL_FAM6_KABYLAKE_DESKTOP, skl_uncore_init),
+	X86_UNCORE_MODEL_MATCH(INTEL_FAM6_ICELAKE_MOBILE, icl_uncore_init),
 	{},
 };
 
diff --git a/arch/x86/events/intel/uncore.h b/arch/x86/events/intel/uncore.h
index 853a49a8ccf6..79eb2e21e4f0 100644
--- a/arch/x86/events/intel/uncore.h
+++ b/arch/x86/events/intel/uncore.h
@@ -512,6 +512,7 @@ int skl_uncore_pci_init(void);
 void snb_uncore_cpu_init(void);
 void nhm_uncore_cpu_init(void);
 void skl_uncore_cpu_init(void);
+void icl_uncore_cpu_init(void);
 int snb_pci2phy_map_init(int devid);
 
 /* uncore_snbep.c */
diff --git a/arch/x86/events/intel/uncore_snb.c b/arch/x86/events/intel/uncore_snb.c
index 13493f43b247..f8431819b3e1 100644
--- a/arch/x86/events/intel/uncore_snb.c
+++ b/arch/x86/events/intel/uncore_snb.c
@@ -34,6 +34,8 @@
 #define PCI_DEVICE_ID_INTEL_CFL_4S_S_IMC	0x3e33
 #define PCI_DEVICE_ID_INTEL_CFL_6S_S_IMC	0x3eca
 #define PCI_DEVICE_ID_INTEL_CFL_8S_S_IMC	0x3e32
+#define PCI_DEVICE_ID_INTEL_ICL_U_IMC		0x8a02
+#define PCI_DEVICE_ID_INTEL_ICL_U2_IMC		0x8a12
 
 /* SNB event control */
 #define SNB_UNC_CTL_EV_SEL_MASK			0x000000ff
@@ -93,6 +95,12 @@
 #define SKL_UNC_PERF_GLOBAL_CTL			0xe01
 #define SKL_UNC_GLOBAL_CTL_CORE_ALL		((1 << 5) - 1)
 
+/* ICL Cbo register */
+#define ICL_UNC_CBO_CONFIG			0x396
+#define ICL_UNC_NUM_CBO_MASK			0xf
+#define ICL_UNC_CBO_0_PER_CTR0			0x702
+#define ICL_UNC_CBO_MSR_OFFSET			0x8
+
 DEFINE_UNCORE_FORMAT_ATTR(event, event, "config:0-7");
 DEFINE_UNCORE_FORMAT_ATTR(umask, umask, "config:8-15");
 DEFINE_UNCORE_FORMAT_ATTR(edge, edge, "config:18");
@@ -280,6 +288,70 @@ void skl_uncore_cpu_init(void)
 	snb_uncore_arb.ops = &skl_uncore_msr_ops;
 }
 
+static struct intel_uncore_type icl_uncore_cbox = {
+	.name		= "cbox",
+	.num_counters   = 4,
+	.perf_ctr_bits	= 44,
+	.perf_ctr	= ICL_UNC_CBO_0_PER_CTR0,
+	.event_ctl	= SNB_UNC_CBO_0_PERFEVTSEL0,
+	.event_mask	= SNB_UNC_RAW_EVENT_MASK,
+	.msr_offset	= ICL_UNC_CBO_MSR_OFFSET,
+	.ops		= &skl_uncore_msr_ops,
+	.format_group	= &snb_uncore_format_group,
+};
+
+static struct uncore_event_desc icl_uncore_events[] = {
+	INTEL_UNCORE_EVENT_DESC(clockticks, "event=0xff"),
+	{ /* end: all zeroes */ },
+};
+
+static struct attribute *icl_uncore_clock_formats_attr[] = {
+	&format_attr_event.attr,
+	NULL,
+};
+
+static struct attribute_group icl_uncore_clock_format_group = {
+	.name = "format",
+	.attrs = icl_uncore_clock_formats_attr,
+};
+
+static struct intel_uncore_type icl_uncore_clockbox = {
+	.name		= "clock",
+	.num_counters	= 1,
+	.num_boxes	= 1,
+	.fixed_ctr_bits	= 48,
+	.fixed_ctr	= SNB_UNC_FIXED_CTR,
+	.fixed_ctl	= SNB_UNC_FIXED_CTR_CTRL,
+	.single_fixed	= 1,
+	.event_mask	= SNB_UNC_CTL_EV_SEL_MASK,
+	.format_group	= &icl_uncore_clock_format_group,
+	.ops		= &skl_uncore_msr_ops,
+	.event_descs	= icl_uncore_events,
+};
+
+static struct intel_uncore_type *icl_msr_uncores[] = {
+	&icl_uncore_cbox,
+	&snb_uncore_arb,
+	&icl_uncore_clockbox,
+	NULL,
+};
+
+static int icl_get_cbox_num(void)
+{
+	u64 num_boxes;
+
+	rdmsrl(ICL_UNC_CBO_CONFIG, num_boxes);
+
+	return num_boxes & ICL_UNC_NUM_CBO_MASK;
+}
+
+void icl_uncore_cpu_init(void)
+{
+	uncore_msr_uncores = icl_msr_uncores;
+	icl_uncore_cbox.num_boxes = icl_get_cbox_num();
+	snb_uncore_arb.ops = &skl_uncore_msr_ops;
+}
+
 enum {
 	SNB_PCI_UNCORE_IMC,
 };
@@ -668,6 +740,18 @@ static const struct pci_device_id skl_uncore_pci_ids[] = {
 	{ /* end: all zeroes */ },
 };
 
+static const struct pci_device_id icl_uncore_pci_ids[] = {
+	{ /* IMC */
+		PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_ICL_U_IMC),
+		.driver_data = UNCORE_PCI_DEV_DATA(SNB_PCI_UNCORE_IMC, 0),
+	},
+	{ /* IMC */
+		PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_ICL_U2_IMC),
+		.driver_data = UNCORE_PCI_DEV_DATA(SNB_PCI_UNCORE_IMC, 0),
+	},
+	{ /* end: all zeroes */ },
+};
+
 static struct pci_driver snb_uncore_pci_driver = {
 	.name		= "snb_uncore",
 	.id_table	= snb_uncore_pci_ids,
@@ -693,6 +777,11 @@ static struct pci_driver skl_uncore_pci_driver = {
 	.id_table	= skl_uncore_pci_ids,
 };
 
+static struct pci_driver icl_uncore_pci_driver = {
+	.name		= "icl_uncore",
+	.id_table	= icl_uncore_pci_ids,
+};
+
 struct imc_uncore_pci_dev {
 	__u32 pci_id;
 	struct pci_driver *driver;
@@ -732,6 +821,8 @@ static const struct imc_uncore_pci_dev desktop_imc_pci_ids[] = {
 	IMC_DEV(CFL_4S_S_IMC, &skl_uncore_pci_driver),  /* 8th Gen Core S 4 Cores Server */
 	IMC_DEV(CFL_6S_S_IMC, &skl_uncore_pci_driver),  /* 8th Gen Core S 6 Cores Server */
 	IMC_DEV(CFL_8S_S_IMC, &skl_uncore_pci_driver),  /* 8th Gen Core S 8 Cores Server */
+	IMC_DEV(ICL_U_IMC, &icl_uncore_pci_driver),	/* 10th Gen Core Mobile */
+	IMC_DEV(ICL_U2_IMC, &icl_uncore_pci_driver),	/* 10th Gen Core Mobile */
 	{  /* end marker */ }
 };
 
diff --git a/arch/x86/events/msr.c b/arch/x86/events/msr.c
index a878e6286e4a..f3f4c2263501 100644
--- a/arch/x86/events/msr.c
+++ b/arch/x86/events/msr.c
@@ -89,6 +89,7 @@ static bool test_intel(int idx)
 	case INTEL_FAM6_SKYLAKE_X:
 	case INTEL_FAM6_KABYLAKE_MOBILE:
 	case INTEL_FAM6_KABYLAKE_DESKTOP:
+	case INTEL_FAM6_ICELAKE_MOBILE:
 		if (idx == PERF_MSR_SMI || idx == PERF_MSR_PPERF)
 			return true;
 		break;
diff --git a/arch/x86/events/perf_event.h b/arch/x86/events/perf_event.h
index a75955741c50..07fc84bb85c1 100644
--- a/arch/x86/events/perf_event.h
+++ b/arch/x86/events/perf_event.h
@@ -49,28 +49,33 @@ struct event_constraint {
 		unsigned long	idxmsk[BITS_TO_LONGS(X86_PMC_IDX_MAX)];
 		u64		idxmsk64;
 	};
-	u64	code;
-	u64	cmask;
-	int	weight;
-	int	overlap;
-	int	flags;
+	u64		code;
+	u64		cmask;
+	int		weight;
+	int		overlap;
+	int		flags;
+	unsigned int	size;
 };
+
+static inline bool constraint_match(struct event_constraint *c, u64 ecode)
+{
+	return ((ecode & c->cmask) - c->code) <= (u64)c->size;
+}
+
 /*
  * struct hw_perf_event.flags flags
  */
 #define PERF_X86_EVENT_PEBS_LDLAT	0x0001 /* ld+ldlat data address sampling */
 #define PERF_X86_EVENT_PEBS_ST		0x0002 /* st data address sampling */
 #define PERF_X86_EVENT_PEBS_ST_HSW	0x0004 /* haswell style datala, store */
-#define PERF_X86_EVENT_COMMITTED	0x0008 /* event passed commit_txn */
-#define PERF_X86_EVENT_PEBS_LD_HSW	0x0010 /* haswell style datala, load */
-#define PERF_X86_EVENT_PEBS_NA_HSW	0x0020 /* haswell style datala, unknown */
-#define PERF_X86_EVENT_EXCL		0x0040 /* HT exclusivity on counter */
-#define PERF_X86_EVENT_DYNAMIC		0x0080 /* dynamic alloc'd constraint */
-#define PERF_X86_EVENT_RDPMC_ALLOWED	0x0100 /* grant rdpmc permission */
-#define PERF_X86_EVENT_EXCL_ACCT	0x0200 /* accounted EXCL event */
-#define PERF_X86_EVENT_AUTO_RELOAD	0x0400 /* use PEBS auto-reload */
-#define PERF_X86_EVENT_LARGE_PEBS	0x0800 /* use large PEBS */
-
+#define PERF_X86_EVENT_PEBS_LD_HSW	0x0008 /* haswell style datala, load */
+#define PERF_X86_EVENT_PEBS_NA_HSW	0x0010 /* haswell style datala, unknown */
+#define PERF_X86_EVENT_EXCL		0x0020 /* HT exclusivity on counter */
+#define PERF_X86_EVENT_DYNAMIC		0x0040 /* dynamic alloc'd constraint */
+#define PERF_X86_EVENT_RDPMC_ALLOWED	0x0080 /* grant rdpmc permission */
+#define PERF_X86_EVENT_EXCL_ACCT	0x0100 /* accounted EXCL event */
+#define PERF_X86_EVENT_AUTO_RELOAD	0x0200 /* use PEBS auto-reload */
+#define PERF_X86_EVENT_LARGE_PEBS	0x0400 /* use large PEBS */
 
 struct amd_nb {
 	int nb_id;  /* NorthBridge id */
@@ -96,25 +101,43 @@ struct amd_nb {
 	PERF_SAMPLE_REGS_INTR | PERF_SAMPLE_REGS_USER | \
 	PERF_SAMPLE_PERIOD)
 
-#define PEBS_REGS \
-	(PERF_REG_X86_AX | \
-	 PERF_REG_X86_BX | \
-	 PERF_REG_X86_CX | \
-	 PERF_REG_X86_DX | \
-	 PERF_REG_X86_DI | \
-	 PERF_REG_X86_SI | \
-	 PERF_REG_X86_SP | \
-	 PERF_REG_X86_BP | \
-	 PERF_REG_X86_IP | \
-	 PERF_REG_X86_FLAGS | \
-	 PERF_REG_X86_R8 | \
-	 PERF_REG_X86_R9 | \
-	 PERF_REG_X86_R10 | \
-	 PERF_REG_X86_R11 | \
-	 PERF_REG_X86_R12 | \
-	 PERF_REG_X86_R13 | \
-	 PERF_REG_X86_R14 | \
-	 PERF_REG_X86_R15)
+#define PEBS_GP_REGS			\
+	((1ULL << PERF_REG_X86_AX)    | \
+	 (1ULL << PERF_REG_X86_BX)    | \
+	 (1ULL << PERF_REG_X86_CX)    | \
+	 (1ULL << PERF_REG_X86_DX)    | \
+	 (1ULL << PERF_REG_X86_DI)    | \
+	 (1ULL << PERF_REG_X86_SI)    | \
+	 (1ULL << PERF_REG_X86_SP)    | \
+	 (1ULL << PERF_REG_X86_BP)    | \
+	 (1ULL << PERF_REG_X86_IP)    | \
+	 (1ULL << PERF_REG_X86_FLAGS) | \
+	 (1ULL << PERF_REG_X86_R8)    | \
+	 (1ULL << PERF_REG_X86_R9)    | \
+	 (1ULL << PERF_REG_X86_R10)   | \
+	 (1ULL << PERF_REG_X86_R11)   | \
+	 (1ULL << PERF_REG_X86_R12)   | \
+	 (1ULL << PERF_REG_X86_R13)   | \
+	 (1ULL << PERF_REG_X86_R14)   | \
+	 (1ULL << PERF_REG_X86_R15))
+
+#define PEBS_XMM_REGS                   \
+	((1ULL << PERF_REG_X86_XMM0)  | \
+	 (1ULL << PERF_REG_X86_XMM1)  | \
+	 (1ULL << PERF_REG_X86_XMM2)  | \
+	 (1ULL << PERF_REG_X86_XMM3)  | \
+	 (1ULL << PERF_REG_X86_XMM4)  | \
+	 (1ULL << PERF_REG_X86_XMM5)  | \
+	 (1ULL << PERF_REG_X86_XMM6)  | \
+	 (1ULL << PERF_REG_X86_XMM7)  | \
+	 (1ULL << PERF_REG_X86_XMM8)  | \
+	 (1ULL << PERF_REG_X86_XMM9)  | \
+	 (1ULL << PERF_REG_X86_XMM10) | \
+	 (1ULL << PERF_REG_X86_XMM11) | \
+	 (1ULL << PERF_REG_X86_XMM12) | \
+	 (1ULL << PERF_REG_X86_XMM13) | \
+	 (1ULL << PERF_REG_X86_XMM14) | \
+	 (1ULL << PERF_REG_X86_XMM15))
 
 /*
  * Per register state.
@@ -207,10 +230,16 @@ struct cpu_hw_events {
 	int			n_pebs;
 	int			n_large_pebs;
 
+	/* Current super set of events hardware configuration */
+	u64			pebs_data_cfg;
+	u64			active_pebs_data_cfg;
+	int			pebs_record_size;
+
 	/*
 	 * Intel LBR bits
 	 */
 	int				lbr_users;
+	int				lbr_pebs_users;
 	struct perf_branch_stack	lbr_stack;
 	struct perf_branch_entry	lbr_entries[MAX_LBR_ENTRIES];
 	struct er_account		*lbr_sel;
@@ -257,18 +286,29 @@ struct cpu_hw_events {
 	void				*kfree_on_online[X86_PERF_KFREE_MAX];
 };
 
-#define __EVENT_CONSTRAINT(c, n, m, w, o, f) {\
+#define __EVENT_CONSTRAINT_RANGE(c, e, n, m, w, o, f) {	\
 	{ .idxmsk64 = (n) },		\
 	.code = (c),			\
+	.size = (e) - (c),		\
 	.cmask = (m),			\
 	.weight = (w),			\
 	.overlap = (o),			\
 	.flags = f,			\
 }
 
+#define __EVENT_CONSTRAINT(c, n, m, w, o, f) \
+	__EVENT_CONSTRAINT_RANGE(c, c, n, m, w, o, f)
+
 #define EVENT_CONSTRAINT(c, n, m)	\
 	__EVENT_CONSTRAINT(c, n, m, HWEIGHT(n), 0, 0)
 
+/*
+ * The constraint_match() function only works for 'simple' event codes
+ * and not for extended (AMD64_EVENTSEL_EVENT) events codes.
+ */
+#define EVENT_CONSTRAINT_RANGE(c, e, n, m) \
+	__EVENT_CONSTRAINT_RANGE(c, e, n, m, HWEIGHT(n), 0, 0)
+
 #define INTEL_EXCLEVT_CONSTRAINT(c, n)	\
 	__EVENT_CONSTRAINT(c, n, ARCH_PERFMON_EVENTSEL_EVENT, HWEIGHT(n),\
 			   0, PERF_X86_EVENT_EXCL)
@@ -304,6 +344,12 @@ struct cpu_hw_events {
 	EVENT_CONSTRAINT(c, n, ARCH_PERFMON_EVENTSEL_EVENT)
 
 /*
+ * Constraint on a range of Event codes
+ */
+#define INTEL_EVENT_CONSTRAINT_RANGE(c, e, n)			\
+	EVENT_CONSTRAINT_RANGE(c, e, n, ARCH_PERFMON_EVENTSEL_EVENT)
+
+/*
  * Constraint on the Event code + UMask + fixed-mask
  *
  * filter mask to validate fixed counter events.
@@ -350,6 +396,9 @@ struct cpu_hw_events {
 #define INTEL_FLAGS_EVENT_CONSTRAINT(c, n) \
 	EVENT_CONSTRAINT(c, n, INTEL_ARCH_EVENT_MASK|X86_ALL_EVENT_FLAGS)
 
+#define INTEL_FLAGS_EVENT_CONSTRAINT_RANGE(c, e, n)			\
+	EVENT_CONSTRAINT_RANGE(c, e, n, INTEL_ARCH_EVENT_MASK|X86_ALL_EVENT_FLAGS)
+
 /* Check only flags, but allow all event/umask */
 #define INTEL_ALL_EVENT_CONSTRAINT(code, n)	\
 	EVENT_CONSTRAINT(code, n, X86_ALL_EVENT_FLAGS)
@@ -366,6 +415,11 @@ struct cpu_hw_events {
 			  ARCH_PERFMON_EVENTSEL_EVENT|X86_ALL_EVENT_FLAGS, \
 			  HWEIGHT(n), 0, PERF_X86_EVENT_PEBS_LD_HSW)
 
+#define INTEL_FLAGS_EVENT_CONSTRAINT_DATALA_LD_RANGE(code, end, n) \
+	__EVENT_CONSTRAINT_RANGE(code, end, n,				\
+			  ARCH_PERFMON_EVENTSEL_EVENT|X86_ALL_EVENT_FLAGS, \
+			  HWEIGHT(n), 0, PERF_X86_EVENT_PEBS_LD_HSW)
+
 #define INTEL_FLAGS_EVENT_CONSTRAINT_DATALA_XLD(code, n) \
 	__EVENT_CONSTRAINT(code, n,			\
 			  ARCH_PERFMON_EVENTSEL_EVENT|X86_ALL_EVENT_FLAGS, \
@@ -473,6 +527,7 @@ union perf_capabilities {
 		 * values > 32bit.
 		 */
 		u64	full_width_write:1;
+		u64     pebs_baseline:1;
 	};
 	u64	capabilities;
 };
@@ -613,14 +668,16 @@ struct x86_pmu {
 			pebs_broken		:1,
 			pebs_prec_dist		:1,
 			pebs_no_tlb		:1,
-			pebs_no_isolation	:1;
+			pebs_no_isolation	:1,
+			pebs_no_xmm_regs	:1;
 	int		pebs_record_size;
 	int		pebs_buffer_size;
+	int		max_pebs_events;
 	void		(*drain_pebs)(struct pt_regs *regs);
 	struct event_constraint *pebs_constraints;
 	void		(*pebs_aliases)(struct perf_event *event);
-	int 		max_pebs_events;
 	unsigned long	large_pebs_flags;
+	u64		rtm_abort_event;
 
 	/*
 	 * Intel LBR
@@ -714,6 +771,7 @@ static struct perf_pmu_events_ht_attr event_attr_##v = {		\
 	.event_str_ht	= ht,						\
 }
 
+struct pmu *x86_get_pmu(void);
 extern struct x86_pmu x86_pmu __read_mostly;
 
 static inline bool x86_pmu_has_lbr_callstack(void)
@@ -941,6 +999,8 @@ extern struct event_constraint intel_bdw_pebs_event_constraints[];
 
 extern struct event_constraint intel_skl_pebs_event_constraints[];
 
+extern struct event_constraint intel_icl_pebs_event_constraints[];
+
 struct event_constraint *intel_pebs_constraints(struct perf_event *event);
 
 void intel_pmu_pebs_add(struct perf_event *event);
@@ -959,6 +1019,8 @@ void intel_pmu_pebs_sched_task(struct perf_event_context *ctx, bool sched_in);
 
 void intel_pmu_auto_reload_read(struct perf_event *event);
 
+void intel_pmu_store_pebs_lbrs(struct pebs_lbr *lbr);
+
 void intel_ds_init(void);
 
 void intel_pmu_lbr_sched_task(struct perf_event_context *ctx, bool sched_in);
diff --git a/arch/x86/hyperv/hv_apic.c b/arch/x86/hyperv/hv_apic.c
index 8eb6fbee8e13..5c056b8aebef 100644
--- a/arch/x86/hyperv/hv_apic.c
+++ b/arch/x86/hyperv/hv_apic.c
@@ -86,6 +86,11 @@ static void hv_apic_write(u32 reg, u32 val)
 
 static void hv_apic_eoi_write(u32 reg, u32 val)
 {
+	struct hv_vp_assist_page *hvp = hv_vp_assist_page[smp_processor_id()];
+
+	if (hvp && (xchg(&hvp->apic_assist, 0) & 0x1))
+		return;
+
 	wrmsr(HV_X64_MSR_EOI, val, 0);
 }
 
diff --git a/arch/x86/hyperv/hv_spinlock.c b/arch/x86/hyperv/hv_spinlock.c
index a861b0456b1a..07f21a06392f 100644
--- a/arch/x86/hyperv/hv_spinlock.c
+++ b/arch/x86/hyperv/hv_spinlock.c
@@ -56,7 +56,7 @@ static void hv_qlock_wait(u8 *byte, u8 val)
 /*
  * Hyper-V does not support this so far.
  */
-bool hv_vcpu_is_preempted(int vcpu)
+__visible bool hv_vcpu_is_preempted(int vcpu)
 {
 	return false;
 }
diff --git a/arch/x86/ia32/ia32_signal.c b/arch/x86/ia32/ia32_signal.c
index 321fe5f5d0e9..4d5fcd47ab75 100644
--- a/arch/x86/ia32/ia32_signal.c
+++ b/arch/x86/ia32/ia32_signal.c
@@ -61,9 +61,8 @@
 } while (0)
 
 #define RELOAD_SEG(seg)		{		\
-	unsigned int pre = GET_SEG(seg);	\
+	unsigned int pre = (seg) | 3;		\
 	unsigned int cur = get_user_seg(seg);	\
-	pre |= 3;				\
 	if (pre != cur)				\
 		set_user_seg(seg, pre);		\
 }
@@ -72,6 +71,7 @@ static int ia32_restore_sigcontext(struct pt_regs *regs,
 				   struct sigcontext_32 __user *sc)
 {
 	unsigned int tmpflags, err = 0;
+	u16 gs, fs, es, ds;
 	void __user *buf;
 	u32 tmp;
 
@@ -79,16 +79,10 @@ static int ia32_restore_sigcontext(struct pt_regs *regs,
 	current->restart_block.fn = do_no_restart_syscall;
 
 	get_user_try {
-		/*
-		 * Reload fs and gs if they have changed in the signal
-		 * handler.  This does not handle long fs/gs base changes in
-		 * the handler, but does not clobber them at least in the
-		 * normal case.
-		 */
-		RELOAD_SEG(gs);
-		RELOAD_SEG(fs);
-		RELOAD_SEG(ds);
-		RELOAD_SEG(es);
+		gs = GET_SEG(gs);
+		fs = GET_SEG(fs);
+		ds = GET_SEG(ds);
+		es = GET_SEG(es);
 
 		COPY(di); COPY(si); COPY(bp); COPY(sp); COPY(bx);
 		COPY(dx); COPY(cx); COPY(ip); COPY(ax);
@@ -106,6 +100,17 @@ static int ia32_restore_sigcontext(struct pt_regs *regs,
 		buf = compat_ptr(tmp);
 	} get_user_catch(err);
 
+	/*
+	 * Reload fs and gs if they have changed in the signal
+	 * handler.  This does not handle long fs/gs base changes in
+	 * the handler, but does not clobber them at least in the
+	 * normal case.
+	 */
+	RELOAD_SEG(gs);
+	RELOAD_SEG(fs);
+	RELOAD_SEG(ds);
+	RELOAD_SEG(es);
+
 	err |= fpu__restore_sig(buf, 1);
 
 	force_iret();
diff --git a/arch/x86/include/asm/Kbuild b/arch/x86/include/asm/Kbuild
index a0ab9ab61c75..eebd05942e6c 100644
--- a/arch/x86/include/asm/Kbuild
+++ b/arch/x86/include/asm/Kbuild
@@ -11,3 +11,4 @@ generic-y += early_ioremap.h
 generic-y += export.h
 generic-y += mcs_spinlock.h
 generic-y += mm-arch-hooks.h
+generic-y += mmiowb.h
diff --git a/arch/x86/include/asm/alternative-asm.h b/arch/x86/include/asm/alternative-asm.h
index 31b627b43a8e..464034db299f 100644
--- a/arch/x86/include/asm/alternative-asm.h
+++ b/arch/x86/include/asm/alternative-asm.h
@@ -20,6 +20,17 @@
 #endif
 
 /*
+ * objtool annotation to ignore the alternatives and only consider the original
+ * instruction(s).
+ */
+.macro ANNOTATE_IGNORE_ALTERNATIVE
+	.Lannotate_\@:
+	.pushsection .discard.ignore_alts
+	.long .Lannotate_\@ - .
+	.popsection
+.endm
+
+/*
  * Issue one struct alt_instr descriptor entry (need to put it into
  * the section .altinstructions, see below). This entry contains
  * enough information for the alternatives patching code to patch an
diff --git a/arch/x86/include/asm/alternative.h b/arch/x86/include/asm/alternative.h
index 4c74073a19cc..094fbc9c0b1c 100644
--- a/arch/x86/include/asm/alternative.h
+++ b/arch/x86/include/asm/alternative.h
@@ -45,6 +45,16 @@
 #define LOCK_PREFIX ""
 #endif
 
+/*
+ * objtool annotation to ignore the alternatives and only consider the original
+ * instruction(s).
+ */
+#define ANNOTATE_IGNORE_ALTERNATIVE				\
+	"999:\n\t"						\
+	".pushsection .discard.ignore_alts\n\t"			\
+	".long 999b - .\n\t"					\
+	".popsection\n\t"
+
 struct alt_instr {
 	s32 instr_offset;	/* original instruction */
 	s32 repl_offset;	/* offset to replacement instruction */
diff --git a/arch/x86/include/asm/asm.h b/arch/x86/include/asm/asm.h
index 6467757bb39f..3ff577c0b102 100644
--- a/arch/x86/include/asm/asm.h
+++ b/arch/x86/include/asm/asm.h
@@ -148,30 +148,6 @@
 	_ASM_PTR (entry);					\
 	.popsection
 
-.macro ALIGN_DESTINATION
-	/* check for bad alignment of destination */
-	movl %edi,%ecx
-	andl $7,%ecx
-	jz 102f				/* already aligned */
-	subl $8,%ecx
-	negl %ecx
-	subl %ecx,%edx
-100:	movb (%rsi),%al
-101:	movb %al,(%rdi)
-	incq %rsi
-	incq %rdi
-	decl %ecx
-	jnz 100b
-102:
-	.section .fixup,"ax"
-103:	addl %ecx,%edx			/* ecx is zerorest also */
-	jmp copy_user_handle_tail
-	.previous
-
-	_ASM_EXTABLE_UA(100b, 103b)
-	_ASM_EXTABLE_UA(101b, 103b)
-	.endm
-
 #else
 # define _EXPAND_EXTABLE_HANDLE(x) #x
 # define _ASM_EXTABLE_HANDLE(from, to, handler)			\
diff --git a/arch/x86/include/asm/bitops.h b/arch/x86/include/asm/bitops.h
index d153d570bb04..8e790ec219a5 100644
--- a/arch/x86/include/asm/bitops.h
+++ b/arch/x86/include/asm/bitops.h
@@ -36,16 +36,17 @@
  * bit 0 is the LSB of addr; bit 32 is the LSB of (addr+1).
  */
 
-#define BITOP_ADDR(x) "+m" (*(volatile long *) (x))
+#define RLONG_ADDR(x)			 "m" (*(volatile long *) (x))
+#define WBYTE_ADDR(x)			"+m" (*(volatile char *) (x))
 
-#define ADDR				BITOP_ADDR(addr)
+#define ADDR				RLONG_ADDR(addr)
 
 /*
  * We do the locked ops that don't return the old value as
  * a mask operation on a byte.
  */
 #define IS_IMMEDIATE(nr)		(__builtin_constant_p(nr))
-#define CONST_MASK_ADDR(nr, addr)	BITOP_ADDR((void *)(addr) + ((nr)>>3))
+#define CONST_MASK_ADDR(nr, addr)	WBYTE_ADDR((void *)(addr) + ((nr)>>3))
 #define CONST_MASK(nr)			(1 << ((nr) & 7))
 
 /**
@@ -73,7 +74,7 @@ set_bit(long nr, volatile unsigned long *addr)
 			: "memory");
 	} else {
 		asm volatile(LOCK_PREFIX __ASM_SIZE(bts) " %1,%0"
-			: BITOP_ADDR(addr) : "Ir" (nr) : "memory");
+			: : RLONG_ADDR(addr), "Ir" (nr) : "memory");
 	}
 }
 
@@ -88,7 +89,7 @@ set_bit(long nr, volatile unsigned long *addr)
  */
 static __always_inline void __set_bit(long nr, volatile unsigned long *addr)
 {
-	asm volatile(__ASM_SIZE(bts) " %1,%0" : ADDR : "Ir" (nr) : "memory");
+	asm volatile(__ASM_SIZE(bts) " %1,%0" : : ADDR, "Ir" (nr) : "memory");
 }
 
 /**
@@ -110,8 +111,7 @@ clear_bit(long nr, volatile unsigned long *addr)
 			: "iq" ((u8)~CONST_MASK(nr)));
 	} else {
 		asm volatile(LOCK_PREFIX __ASM_SIZE(btr) " %1,%0"
-			: BITOP_ADDR(addr)
-			: "Ir" (nr));
+			: : RLONG_ADDR(addr), "Ir" (nr) : "memory");
 	}
 }
 
@@ -131,7 +131,7 @@ static __always_inline void clear_bit_unlock(long nr, volatile unsigned long *ad
 
 static __always_inline void __clear_bit(long nr, volatile unsigned long *addr)
 {
-	asm volatile(__ASM_SIZE(btr) " %1,%0" : ADDR : "Ir" (nr));
+	asm volatile(__ASM_SIZE(btr) " %1,%0" : : ADDR, "Ir" (nr) : "memory");
 }
 
 static __always_inline bool clear_bit_unlock_is_negative_byte(long nr, volatile unsigned long *addr)
@@ -139,7 +139,7 @@ static __always_inline bool clear_bit_unlock_is_negative_byte(long nr, volatile
 	bool negative;
 	asm volatile(LOCK_PREFIX "andb %2,%1"
 		CC_SET(s)
-		: CC_OUT(s) (negative), ADDR
+		: CC_OUT(s) (negative), WBYTE_ADDR(addr)
 		: "ir" ((char) ~(1 << nr)) : "memory");
 	return negative;
 }
@@ -155,13 +155,9 @@ static __always_inline bool clear_bit_unlock_is_negative_byte(long nr, volatile
  * __clear_bit() is non-atomic and implies release semantics before the memory
  * operation. It can be used for an unlock if no other CPUs can concurrently
  * modify other bits in the word.
- *
- * No memory barrier is required here, because x86 cannot reorder stores past
- * older loads. Same principle as spin_unlock.
  */
 static __always_inline void __clear_bit_unlock(long nr, volatile unsigned long *addr)
 {
-	barrier();
 	__clear_bit(nr, addr);
 }
 
@@ -176,7 +172,7 @@ static __always_inline void __clear_bit_unlock(long nr, volatile unsigned long *
  */
 static __always_inline void __change_bit(long nr, volatile unsigned long *addr)
 {
-	asm volatile(__ASM_SIZE(btc) " %1,%0" : ADDR : "Ir" (nr));
+	asm volatile(__ASM_SIZE(btc) " %1,%0" : : ADDR, "Ir" (nr) : "memory");
 }
 
 /**
@@ -196,8 +192,7 @@ static __always_inline void change_bit(long nr, volatile unsigned long *addr)
 			: "iq" ((u8)CONST_MASK(nr)));
 	} else {
 		asm volatile(LOCK_PREFIX __ASM_SIZE(btc) " %1,%0"
-			: BITOP_ADDR(addr)
-			: "Ir" (nr));
+			: : RLONG_ADDR(addr), "Ir" (nr) : "memory");
 	}
 }
 
@@ -242,8 +237,8 @@ static __always_inline bool __test_and_set_bit(long nr, volatile unsigned long *
 
 	asm(__ASM_SIZE(bts) " %2,%1"
 	    CC_SET(c)
-	    : CC_OUT(c) (oldbit), ADDR
-	    : "Ir" (nr));
+	    : CC_OUT(c) (oldbit)
+	    : ADDR, "Ir" (nr) : "memory");
 	return oldbit;
 }
 
@@ -282,8 +277,8 @@ static __always_inline bool __test_and_clear_bit(long nr, volatile unsigned long
 
 	asm volatile(__ASM_SIZE(btr) " %2,%1"
 		     CC_SET(c)
-		     : CC_OUT(c) (oldbit), ADDR
-		     : "Ir" (nr));
+		     : CC_OUT(c) (oldbit)
+		     : ADDR, "Ir" (nr) : "memory");
 	return oldbit;
 }
 
@@ -294,8 +289,8 @@ static __always_inline bool __test_and_change_bit(long nr, volatile unsigned lon
 
 	asm volatile(__ASM_SIZE(btc) " %2,%1"
 		     CC_SET(c)
-		     : CC_OUT(c) (oldbit), ADDR
-		     : "Ir" (nr) : "memory");
+		     : CC_OUT(c) (oldbit)
+		     : ADDR, "Ir" (nr) : "memory");
 
 	return oldbit;
 }
@@ -326,7 +321,7 @@ static __always_inline bool variable_test_bit(long nr, volatile const unsigned l
 	asm volatile(__ASM_SIZE(bt) " %2,%1"
 		     CC_SET(c)
 		     : CC_OUT(c) (oldbit)
-		     : "m" (*(unsigned long *)addr), "Ir" (nr));
+		     : "m" (*(unsigned long *)addr), "Ir" (nr) : "memory");
 
 	return oldbit;
 }
diff --git a/arch/x86/include/asm/cpu_entry_area.h b/arch/x86/include/asm/cpu_entry_area.h
index 29c706415443..cff3f3f3bfe0 100644
--- a/arch/x86/include/asm/cpu_entry_area.h
+++ b/arch/x86/include/asm/cpu_entry_area.h
@@ -7,6 +7,64 @@
 #include <asm/processor.h>
 #include <asm/intel_ds.h>
 
+#ifdef CONFIG_X86_64
+
+/* Macro to enforce the same ordering and stack sizes */
+#define ESTACKS_MEMBERS(guardsize, db2_holesize)\
+	char	DF_stack_guard[guardsize];	\
+	char	DF_stack[EXCEPTION_STKSZ];	\
+	char	NMI_stack_guard[guardsize];	\
+	char	NMI_stack[EXCEPTION_STKSZ];	\
+	char	DB2_stack_guard[guardsize];	\
+	char	DB2_stack[db2_holesize];	\
+	char	DB1_stack_guard[guardsize];	\
+	char	DB1_stack[EXCEPTION_STKSZ];	\
+	char	DB_stack_guard[guardsize];	\
+	char	DB_stack[EXCEPTION_STKSZ];	\
+	char	MCE_stack_guard[guardsize];	\
+	char	MCE_stack[EXCEPTION_STKSZ];	\
+	char	IST_top_guard[guardsize];	\
+
+/* The exception stacks' physical storage. No guard pages required */
+struct exception_stacks {
+	ESTACKS_MEMBERS(0, 0)
+};
+
+/* The effective cpu entry area mapping with guard pages. */
+struct cea_exception_stacks {
+	ESTACKS_MEMBERS(PAGE_SIZE, EXCEPTION_STKSZ)
+};
+
+/*
+ * The exception stack ordering in [cea_]exception_stacks
+ */
+enum exception_stack_ordering {
+	ESTACK_DF,
+	ESTACK_NMI,
+	ESTACK_DB2,
+	ESTACK_DB1,
+	ESTACK_DB,
+	ESTACK_MCE,
+	N_EXCEPTION_STACKS
+};
+
+#define CEA_ESTACK_SIZE(st)					\
+	sizeof(((struct cea_exception_stacks *)0)->st## _stack)
+
+#define CEA_ESTACK_BOT(ceastp, st)				\
+	((unsigned long)&(ceastp)->st## _stack)
+
+#define CEA_ESTACK_TOP(ceastp, st)				\
+	(CEA_ESTACK_BOT(ceastp, st) + CEA_ESTACK_SIZE(st))
+
+#define CEA_ESTACK_OFFS(st)					\
+	offsetof(struct cea_exception_stacks, st## _stack)
+
+#define CEA_ESTACK_PAGES					\
+	(sizeof(struct cea_exception_stacks) / PAGE_SIZE)
+
+#endif
+
 /*
  * cpu_entry_area is a percpu region that contains things needed by the CPU
  * and early entry/exit code.  Real types aren't used for all fields here
@@ -32,12 +90,9 @@ struct cpu_entry_area {
 
 #ifdef CONFIG_X86_64
 	/*
-	 * Exception stacks used for IST entries.
-	 *
-	 * In the future, this should have a separate slot for each stack
-	 * with guard pages between them.
+	 * Exception stacks used for IST entries with guard pages.
 	 */
-	char exception_stacks[(N_EXCEPTION_STACKS - 1) * EXCEPTION_STKSZ + DEBUG_STKSZ];
+	struct cea_exception_stacks estacks;
 #endif
 #ifdef CONFIG_CPU_SUP_INTEL
 	/*
@@ -57,6 +112,7 @@ struct cpu_entry_area {
 #define CPU_ENTRY_AREA_TOT_SIZE	(CPU_ENTRY_AREA_SIZE * NR_CPUS)
 
 DECLARE_PER_CPU(struct cpu_entry_area *, cpu_entry_area);
+DECLARE_PER_CPU(struct cea_exception_stacks *, cea_exception_stacks);
 
 extern void setup_cpu_entry_areas(void);
 extern void cea_set_pte(void *cea_vaddr, phys_addr_t pa, pgprot_t flags);
@@ -76,4 +132,7 @@ static inline struct entry_stack *cpu_entry_stack(int cpu)
 	return &get_cpu_entry_area(cpu)->entry_stack_page.stack;
 }
 
+#define __this_cpu_ist_top_va(name)					\
+	CEA_ESTACK_TOP(__this_cpu_read(cea_exception_stacks), name)
+
 #endif
diff --git a/arch/x86/include/asm/cpufeature.h b/arch/x86/include/asm/cpufeature.h
index ce95b8cbd229..1d337c51f7e6 100644
--- a/arch/x86/include/asm/cpufeature.h
+++ b/arch/x86/include/asm/cpufeature.h
@@ -112,8 +112,9 @@ extern const char * const x86_bug_flags[NBUGINTS*32];
 	 test_cpu_cap(c, bit))
 
 #define this_cpu_has(bit)						\
-	(__builtin_constant_p(bit) && REQUIRED_MASK_BIT_SET(bit) ? 1 : 	\
-	 x86_this_cpu_test_bit(bit, (unsigned long *)&cpu_info.x86_capability))
+	(__builtin_constant_p(bit) && REQUIRED_MASK_BIT_SET(bit) ? 1 :	\
+	 x86_this_cpu_test_bit(bit,					\
+		(unsigned long __percpu *)&cpu_info.x86_capability))
 
 /*
  * This macro is for detection of features which need kernel
@@ -155,11 +156,14 @@ extern void clear_cpu_cap(struct cpuinfo_x86 *c, unsigned int bit);
 #else
 
 /*
- * Static testing of CPU features.  Used the same as boot_cpu_has().
- * These will statically patch the target code for additional
- * performance.
+ * Static testing of CPU features. Used the same as boot_cpu_has(). It
+ * statically patches the target code for additional performance. Use
+ * static_cpu_has() only in fast paths, where every cycle counts. Which
+ * means that the boot_cpu_has() variant is already fast enough for the
+ * majority of cases and you should stick to using it as it is generally
+ * only two instructions: a RIP-relative MOV and a TEST.
  */
-static __always_inline __pure bool _static_cpu_has(u16 bit)
+static __always_inline bool _static_cpu_has(u16 bit)
 {
 	asm_volatile_goto("1: jmp 6f\n"
 		 "2:\n"
diff --git a/arch/x86/include/asm/debugreg.h b/arch/x86/include/asm/debugreg.h
index 9e5ca30738e5..1a8609a15856 100644
--- a/arch/x86/include/asm/debugreg.h
+++ b/arch/x86/include/asm/debugreg.h
@@ -104,11 +104,9 @@ static inline void debug_stack_usage_dec(void)
 {
 	__this_cpu_dec(debug_stack_usage);
 }
-int is_debug_stack(unsigned long addr);
 void debug_stack_set_zero(void);
 void debug_stack_reset(void);
 #else /* !X86_64 */
-static inline int is_debug_stack(unsigned long addr) { return 0; }
 static inline void debug_stack_set_zero(void) { }
 static inline void debug_stack_reset(void) { }
 static inline void debug_stack_usage_inc(void) { }
diff --git a/arch/x86/include/asm/fixmap.h b/arch/x86/include/asm/fixmap.h
index 50ba74a34a37..9da8cccdf3fb 100644
--- a/arch/x86/include/asm/fixmap.h
+++ b/arch/x86/include/asm/fixmap.h
@@ -103,8 +103,6 @@ enum fixed_addresses {
 #ifdef CONFIG_PARAVIRT
 	FIX_PARAVIRT_BOOTMAP,
 #endif
-	FIX_TEXT_POKE1,	/* reserve 2 pages for text_poke() */
-	FIX_TEXT_POKE0, /* first page is last, because allocation is backward */
 #ifdef	CONFIG_X86_INTEL_MID
 	FIX_LNW_VRTC,
 #endif
diff --git a/arch/x86/include/asm/fpu/internal.h b/arch/x86/include/asm/fpu/internal.h
index fb04a3ded7dd..745a19d34f23 100644
--- a/arch/x86/include/asm/fpu/internal.h
+++ b/arch/x86/include/asm/fpu/internal.h
@@ -253,7 +253,7 @@ static inline void copy_xregs_to_kernel_booting(struct xregs_state *xstate)
 
 	WARN_ON(system_state != SYSTEM_BOOTING);
 
-	if (static_cpu_has(X86_FEATURE_XSAVES))
+	if (boot_cpu_has(X86_FEATURE_XSAVES))
 		XSTATE_OP(XSAVES, xstate, lmask, hmask, err);
 	else
 		XSTATE_OP(XSAVE, xstate, lmask, hmask, err);
@@ -275,7 +275,7 @@ static inline void copy_kernel_to_xregs_booting(struct xregs_state *xstate)
 
 	WARN_ON(system_state != SYSTEM_BOOTING);
 
-	if (static_cpu_has(X86_FEATURE_XSAVES))
+	if (boot_cpu_has(X86_FEATURE_XSAVES))
 		XSTATE_OP(XRSTORS, xstate, lmask, hmask, err);
 	else
 		XSTATE_OP(XRSTOR, xstate, lmask, hmask, err);
@@ -497,8 +497,7 @@ static inline void fpregs_activate(struct fpu *fpu)
  *  - switch_fpu_finish() restores the new state as
  *    necessary.
  */
-static inline void
-switch_fpu_prepare(struct fpu *old_fpu, int cpu)
+static inline void switch_fpu_prepare(struct fpu *old_fpu, int cpu)
 {
 	if (static_cpu_has(X86_FEATURE_FPU) && old_fpu->initialized) {
 		if (!copy_fpregs_to_fpstate(old_fpu))
diff --git a/arch/x86/include/asm/intel_ds.h b/arch/x86/include/asm/intel_ds.h
index ae26df1c2789..8380c3ddd4b2 100644
--- a/arch/x86/include/asm/intel_ds.h
+++ b/arch/x86/include/asm/intel_ds.h
@@ -8,7 +8,7 @@
 
 /* The maximal number of PEBS events: */
 #define MAX_PEBS_EVENTS		8
-#define MAX_FIXED_PEBS_EVENTS	3
+#define MAX_FIXED_PEBS_EVENTS	4
 
 /*
  * A debug store configuration.
diff --git a/arch/x86/include/asm/io.h b/arch/x86/include/asm/io.h
index 686247db3106..a06a9f8294ea 100644
--- a/arch/x86/include/asm/io.h
+++ b/arch/x86/include/asm/io.h
@@ -90,8 +90,6 @@ build_mmio_write(__writel, "l", unsigned int, "r", )
 #define __raw_writew __writew
 #define __raw_writel __writel
 
-#define mmiowb() barrier()
-
 #ifdef CONFIG_X86_64
 
 build_mmio_read(readq, "q", u64, "=r", :"memory")
diff --git a/arch/x86/include/asm/irq.h b/arch/x86/include/asm/irq.h
index fbb16e6b6c18..8f95686ec27e 100644
--- a/arch/x86/include/asm/irq.h
+++ b/arch/x86/include/asm/irq.h
@@ -16,11 +16,7 @@ static inline int irq_canonicalize(int irq)
 	return ((irq == 2) ? 9 : irq);
 }
 
-#ifdef CONFIG_X86_32
-extern void irq_ctx_init(int cpu);
-#else
-# define irq_ctx_init(cpu) do { } while (0)
-#endif
+extern int irq_init_percpu_irqstack(unsigned int cpu);
 
 #define __ARCH_HAS_DO_SOFTIRQ
 
diff --git a/arch/x86/include/asm/irq_vectors.h b/arch/x86/include/asm/irq_vectors.h
index 548d90bbf919..889f8b1b5b7f 100644
--- a/arch/x86/include/asm/irq_vectors.h
+++ b/arch/x86/include/asm/irq_vectors.h
@@ -18,8 +18,8 @@
  *  Vectors   0 ...  31 : system traps and exceptions - hardcoded events
  *  Vectors  32 ... 127 : device interrupts
  *  Vector  128         : legacy int80 syscall interface
- *  Vectors 129 ... INVALIDATE_TLB_VECTOR_START-1 except 204 : device interrupts
- *  Vectors INVALIDATE_TLB_VECTOR_START ... 255 : special interrupts
+ *  Vectors 129 ... LOCAL_TIMER_VECTOR-1
+ *  Vectors LOCAL_TIMER_VECTOR ... 255 : special interrupts
  *
  * 64-bit x86 has per CPU IDT tables, 32-bit has one shared IDT table.
  *
diff --git a/arch/x86/include/asm/kvm_emulate.h b/arch/x86/include/asm/kvm_emulate.h
index 93c4bf598fb0..feab24cac610 100644
--- a/arch/x86/include/asm/kvm_emulate.h
+++ b/arch/x86/include/asm/kvm_emulate.h
@@ -226,7 +226,9 @@ struct x86_emulate_ops {
 
 	unsigned (*get_hflags)(struct x86_emulate_ctxt *ctxt);
 	void (*set_hflags)(struct x86_emulate_ctxt *ctxt, unsigned hflags);
-	int (*pre_leave_smm)(struct x86_emulate_ctxt *ctxt, u64 smbase);
+	int (*pre_leave_smm)(struct x86_emulate_ctxt *ctxt,
+			     const char *smstate);
+	void (*post_leave_smm)(struct x86_emulate_ctxt *ctxt);
 
 };
 
diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
index a5db4475e72d..c79abe7ca093 100644
--- a/arch/x86/include/asm/kvm_host.h
+++ b/arch/x86/include/asm/kvm_host.h
@@ -126,7 +126,7 @@ static inline gfn_t gfn_to_index(gfn_t gfn, gfn_t base_gfn, int level)
 }
 
 #define KVM_PERMILLE_MMU_PAGES 20
-#define KVM_MIN_ALLOC_MMU_PAGES 64
+#define KVM_MIN_ALLOC_MMU_PAGES 64UL
 #define KVM_MMU_HASH_SHIFT 12
 #define KVM_NUM_MMU_PAGES (1 << KVM_MMU_HASH_SHIFT)
 #define KVM_MIN_FREE_MMU_PAGES 5
@@ -253,14 +253,14 @@ struct kvm_mmu_memory_cache {
  * kvm_memory_slot.arch.gfn_track which is 16 bits, so the role bits used
  * by indirect shadow page can not be more than 15 bits.
  *
- * Currently, we used 14 bits that are @level, @cr4_pae, @quadrant, @access,
+ * Currently, we used 14 bits that are @level, @gpte_is_8_bytes, @quadrant, @access,
  * @nxe, @cr0_wp, @smep_andnot_wp and @smap_andnot_wp.
  */
 union kvm_mmu_page_role {
 	u32 word;
 	struct {
 		unsigned level:4;
-		unsigned cr4_pae:1;
+		unsigned gpte_is_8_bytes:1;
 		unsigned quadrant:2;
 		unsigned direct:1;
 		unsigned access:3;
@@ -295,6 +295,7 @@ union kvm_mmu_extended_role {
 		unsigned int valid:1;
 		unsigned int execonly:1;
 		unsigned int cr0_pg:1;
+		unsigned int cr4_pae:1;
 		unsigned int cr4_pse:1;
 		unsigned int cr4_pke:1;
 		unsigned int cr4_smap:1;
@@ -350,6 +351,7 @@ struct kvm_mmu_page {
 };
 
 struct kvm_pio_request {
+	unsigned long linear_rip;
 	unsigned long count;
 	int in;
 	int port;
@@ -568,6 +570,7 @@ struct kvm_vcpu_arch {
 	bool tpr_access_reporting;
 	u64 ia32_xss;
 	u64 microcode_version;
+	u64 arch_capabilities;
 
 	/*
 	 * Paging state of the vcpu
@@ -842,9 +845,9 @@ enum kvm_irqchip_mode {
 };
 
 struct kvm_arch {
-	unsigned int n_used_mmu_pages;
-	unsigned int n_requested_mmu_pages;
-	unsigned int n_max_mmu_pages;
+	unsigned long n_used_mmu_pages;
+	unsigned long n_requested_mmu_pages;
+	unsigned long n_max_mmu_pages;
 	unsigned int indirect_shadow_pages;
 	struct hlist_head mmu_page_hash[KVM_NUM_MMU_PAGES];
 	/*
@@ -1180,7 +1183,7 @@ struct kvm_x86_ops {
 
 	int (*smi_allowed)(struct kvm_vcpu *vcpu);
 	int (*pre_enter_smm)(struct kvm_vcpu *vcpu, char *smstate);
-	int (*pre_leave_smm)(struct kvm_vcpu *vcpu, u64 smbase);
+	int (*pre_leave_smm)(struct kvm_vcpu *vcpu, const char *smstate);
 	int (*enable_smi_window)(struct kvm_vcpu *vcpu);
 
 	int (*mem_enc_op)(struct kvm *kvm, void __user *argp);
@@ -1192,6 +1195,8 @@ struct kvm_x86_ops {
 	int (*nested_enable_evmcs)(struct kvm_vcpu *vcpu,
 				   uint16_t *vmcs_version);
 	uint16_t (*nested_get_evmcs_version)(struct kvm_vcpu *vcpu);
+
+	bool (*need_emulation_on_page_fault)(struct kvm_vcpu *vcpu);
 };
 
 struct kvm_arch_async_pf {
@@ -1252,8 +1257,8 @@ void kvm_mmu_clear_dirty_pt_masked(struct kvm *kvm,
 				   gfn_t gfn_offset, unsigned long mask);
 void kvm_mmu_zap_all(struct kvm *kvm);
 void kvm_mmu_invalidate_mmio_sptes(struct kvm *kvm, u64 gen);
-unsigned int kvm_mmu_calculate_mmu_pages(struct kvm *kvm);
-void kvm_mmu_change_mmu_pages(struct kvm *kvm, unsigned int kvm_nr_mmu_pages);
+unsigned long kvm_mmu_calculate_default_mmu_pages(struct kvm *kvm);
+void kvm_mmu_change_mmu_pages(struct kvm *kvm, unsigned long kvm_nr_mmu_pages);
 
 int load_pdptrs(struct kvm_vcpu *vcpu, struct kvm_mmu *mmu, unsigned long cr3);
 bool pdptrs_changed(struct kvm_vcpu *vcpu);
@@ -1588,4 +1593,7 @@ static inline int kvm_cpu_get_apicid(int mps_cpu)
 #define put_smstate(type, buf, offset, val)                      \
 	*(type *)((buf) + (offset) - 0x7e00) = val
 
+#define GET_SMSTATE(type, buf, offset)		\
+	(*(type *)((buf) + (offset) - 0x7e00))
+
 #endif /* _ASM_X86_KVM_HOST_H */
diff --git a/arch/x86/include/asm/mce.h b/arch/x86/include/asm/mce.h
index 22d05e3835f0..dc2d4b206ab7 100644
--- a/arch/x86/include/asm/mce.h
+++ b/arch/x86/include/asm/mce.h
@@ -210,16 +210,6 @@ static inline void cmci_rediscover(void) {}
 static inline void cmci_recheck(void) {}
 #endif
 
-#ifdef CONFIG_X86_MCE_AMD
-void mce_amd_feature_init(struct cpuinfo_x86 *c);
-int umc_normaddr_to_sysaddr(u64 norm_addr, u16 nid, u8 umc, u64 *sys_addr);
-#else
-static inline void mce_amd_feature_init(struct cpuinfo_x86 *c) { }
-static inline int umc_normaddr_to_sysaddr(u64 norm_addr, u16 nid, u8 umc, u64 *sys_addr) { return -EINVAL; };
-#endif
-
-static inline void mce_hygon_feature_init(struct cpuinfo_x86 *c) { return mce_amd_feature_init(c); }
-
 int mce_available(struct cpuinfo_x86 *c);
 bool mce_is_memory_error(struct mce *m);
 bool mce_is_correctable(struct mce *m);
@@ -345,12 +335,19 @@ extern bool amd_mce_is_memory_error(struct mce *m);
 extern int mce_threshold_create_device(unsigned int cpu);
 extern int mce_threshold_remove_device(unsigned int cpu);
 
-#else
+void mce_amd_feature_init(struct cpuinfo_x86 *c);
+int umc_normaddr_to_sysaddr(u64 norm_addr, u16 nid, u8 umc, u64 *sys_addr);
 
-static inline int mce_threshold_create_device(unsigned int cpu) { return 0; };
-static inline int mce_threshold_remove_device(unsigned int cpu) { return 0; };
-static inline bool amd_mce_is_memory_error(struct mce *m) { return false; };
+#else
 
+static inline int mce_threshold_create_device(unsigned int cpu)		{ return 0; };
+static inline int mce_threshold_remove_device(unsigned int cpu)		{ return 0; };
+static inline bool amd_mce_is_memory_error(struct mce *m)		{ return false; };
+static inline void mce_amd_feature_init(struct cpuinfo_x86 *c)		{ }
+static inline int
+umc_normaddr_to_sysaddr(u64 norm_addr, u16 nid, u8 umc, u64 *sys_addr)	{ return -EINVAL; };
 #endif
 
+static inline void mce_hygon_feature_init(struct cpuinfo_x86 *c)	{ return mce_amd_feature_init(c); }
+
 #endif /* _ASM_X86_MCE_H */
diff --git a/arch/x86/include/asm/mmu_context.h b/arch/x86/include/asm/mmu_context.h
index 19d18fae6ec6..93dff1963337 100644
--- a/arch/x86/include/asm/mmu_context.h
+++ b/arch/x86/include/asm/mmu_context.h
@@ -13,6 +13,7 @@
 #include <asm/tlbflush.h>
 #include <asm/paravirt.h>
 #include <asm/mpx.h>
+#include <asm/debugreg.h>
 
 extern atomic64_t last_mm_ctx_id;
 
@@ -356,4 +357,59 @@ static inline unsigned long __get_current_cr3_fast(void)
 	return cr3;
 }
 
+typedef struct {
+	struct mm_struct *mm;
+} temp_mm_state_t;
+
+/*
+ * Using a temporary mm allows to set temporary mappings that are not accessible
+ * by other CPUs. Such mappings are needed to perform sensitive memory writes
+ * that override the kernel memory protections (e.g., W^X), without exposing the
+ * temporary page-table mappings that are required for these write operations to
+ * other CPUs. Using a temporary mm also allows to avoid TLB shootdowns when the
+ * mapping is torn down.
+ *
+ * Context: The temporary mm needs to be used exclusively by a single core. To
+ *          harden security IRQs must be disabled while the temporary mm is
+ *          loaded, thereby preventing interrupt handler bugs from overriding
+ *          the kernel memory protection.
+ */
+static inline temp_mm_state_t use_temporary_mm(struct mm_struct *mm)
+{
+	temp_mm_state_t temp_state;
+
+	lockdep_assert_irqs_disabled();
+	temp_state.mm = this_cpu_read(cpu_tlbstate.loaded_mm);
+	switch_mm_irqs_off(NULL, mm, current);
+
+	/*
+	 * If breakpoints are enabled, disable them while the temporary mm is
+	 * used. Userspace might set up watchpoints on addresses that are used
+	 * in the temporary mm, which would lead to wrong signals being sent or
+	 * crashes.
+	 *
+	 * Note that breakpoints are not disabled selectively, which also causes
+	 * kernel breakpoints (e.g., perf's) to be disabled. This might be
+	 * undesirable, but still seems reasonable as the code that runs in the
+	 * temporary mm should be short.
+	 */
+	if (hw_breakpoint_active())
+		hw_breakpoint_disable();
+
+	return temp_state;
+}
+
+static inline void unuse_temporary_mm(temp_mm_state_t prev_state)
+{
+	lockdep_assert_irqs_disabled();
+	switch_mm_irqs_off(NULL, prev_state.mm, current);
+
+	/*
+	 * Restore the breakpoints if they were disabled before the temporary mm
+	 * was loaded.
+	 */
+	if (hw_breakpoint_active())
+		hw_breakpoint_restore();
+}
+
 #endif /* _ASM_X86_MMU_CONTEXT_H */
diff --git a/arch/x86/include/asm/msr-index.h b/arch/x86/include/asm/msr-index.h
index ca5bc0eacb95..1378518cf63f 100644
--- a/arch/x86/include/asm/msr-index.h
+++ b/arch/x86/include/asm/msr-index.h
@@ -116,6 +116,7 @@
 #define LBR_INFO_CYCLES			0xffff
 
 #define MSR_IA32_PEBS_ENABLE		0x000003f1
+#define MSR_PEBS_DATA_CFG		0x000003f2
 #define MSR_IA32_DS_AREA		0x00000600
 #define MSR_IA32_PERF_CAPABILITIES	0x00000345
 #define MSR_PEBS_LD_LAT_THRESHOLD	0x000003f6
diff --git a/arch/x86/include/asm/nospec-branch.h b/arch/x86/include/asm/nospec-branch.h
index dad12b767ba0..daf25b60c9e3 100644
--- a/arch/x86/include/asm/nospec-branch.h
+++ b/arch/x86/include/asm/nospec-branch.h
@@ -11,6 +11,15 @@
 #include <asm/msr-index.h>
 
 /*
+ * This should be used immediately before a retpoline alternative. It tells
+ * objtool where the retpolines are so that it can make sense of the control
+ * flow by just reading the original instruction(s) and ignoring the
+ * alternatives.
+ */
+#define ANNOTATE_NOSPEC_ALTERNATIVE \
+	ANNOTATE_IGNORE_ALTERNATIVE
+
+/*
  * Fill the CPU return stack buffer.
  *
  * Each entry in the RSB, if used for a speculative 'ret', contains an
@@ -57,19 +66,6 @@
 #ifdef __ASSEMBLY__
 
 /*
- * This should be used immediately before a retpoline alternative.  It tells
- * objtool where the retpolines are so that it can make sense of the control
- * flow by just reading the original instruction(s) and ignoring the
- * alternatives.
- */
-.macro ANNOTATE_NOSPEC_ALTERNATIVE
-	.Lannotate_\@:
-	.pushsection .discard.nospec
-	.long .Lannotate_\@ - .
-	.popsection
-.endm
-
-/*
  * This should be used immediately before an indirect jump/call. It tells
  * objtool the subsequent indirect jump/call is vouched safe for retpoline
  * builds.
@@ -152,12 +148,6 @@
 
 #else /* __ASSEMBLY__ */
 
-#define ANNOTATE_NOSPEC_ALTERNATIVE				\
-	"999:\n\t"						\
-	".pushsection .discard.nospec\n\t"			\
-	".long 999b - .\n\t"					\
-	".popsection\n\t"
-
 #define ANNOTATE_RETPOLINE_SAFE					\
 	"999:\n\t"						\
 	".pushsection .discard.retpoline_safe\n\t"		\
diff --git a/arch/x86/include/asm/page_32_types.h b/arch/x86/include/asm/page_32_types.h
index 0d5c739eebd7..565ad755c785 100644
--- a/arch/x86/include/asm/page_32_types.h
+++ b/arch/x86/include/asm/page_32_types.h
@@ -22,11 +22,9 @@
 #define THREAD_SIZE_ORDER	1
 #define THREAD_SIZE		(PAGE_SIZE << THREAD_SIZE_ORDER)
 
-#define DOUBLEFAULT_STACK 1
-#define NMI_STACK 0
-#define DEBUG_STACK 0
-#define MCE_STACK 0
-#define N_EXCEPTION_STACKS 1
+#define IRQ_STACK_SIZE		THREAD_SIZE
+
+#define N_EXCEPTION_STACKS	1
 
 #ifdef CONFIG_X86_PAE
 /*
diff --git a/arch/x86/include/asm/page_64_types.h b/arch/x86/include/asm/page_64_types.h
index 8f657286d599..793c14c372cb 100644
--- a/arch/x86/include/asm/page_64_types.h
+++ b/arch/x86/include/asm/page_64_types.h
@@ -14,22 +14,20 @@
 
 #define THREAD_SIZE_ORDER	(2 + KASAN_STACK_ORDER)
 #define THREAD_SIZE  (PAGE_SIZE << THREAD_SIZE_ORDER)
-#define CURRENT_MASK (~(THREAD_SIZE - 1))
 
 #define EXCEPTION_STACK_ORDER (0 + KASAN_STACK_ORDER)
 #define EXCEPTION_STKSZ (PAGE_SIZE << EXCEPTION_STACK_ORDER)
 
-#define DEBUG_STACK_ORDER (EXCEPTION_STACK_ORDER + 1)
-#define DEBUG_STKSZ (PAGE_SIZE << DEBUG_STACK_ORDER)
-
 #define IRQ_STACK_ORDER (2 + KASAN_STACK_ORDER)
 #define IRQ_STACK_SIZE (PAGE_SIZE << IRQ_STACK_ORDER)
 
-#define DOUBLEFAULT_STACK 1
-#define NMI_STACK 2
-#define DEBUG_STACK 3
-#define MCE_STACK 4
-#define N_EXCEPTION_STACKS 4  /* hw limit: 7 */
+/*
+ * The index for the tss.ist[] array. The hardware limit is 7 entries.
+ */
+#define	IST_INDEX_DF		0
+#define	IST_INDEX_NMI		1
+#define	IST_INDEX_DB		2
+#define	IST_INDEX_MCE		3
 
 /*
  * Set __PAGE_OFFSET to the most negative possible address +
diff --git a/arch/x86/include/asm/perf_event.h b/arch/x86/include/asm/perf_event.h
index 8bdf74902293..1392d5e6e8d6 100644
--- a/arch/x86/include/asm/perf_event.h
+++ b/arch/x86/include/asm/perf_event.h
@@ -7,7 +7,7 @@
  */
 
 #define INTEL_PMC_MAX_GENERIC				       32
-#define INTEL_PMC_MAX_FIXED					3
+#define INTEL_PMC_MAX_FIXED					4
 #define INTEL_PMC_IDX_FIXED				       32
 
 #define X86_PMC_IDX_MAX					       64
@@ -32,6 +32,8 @@
 
 #define HSW_IN_TX					(1ULL << 32)
 #define HSW_IN_TX_CHECKPOINTED				(1ULL << 33)
+#define ICL_EVENTSEL_ADAPTIVE				(1ULL << 34)
+#define ICL_FIXED_0_ADAPTIVE				(1ULL << 32)
 
 #define AMD64_EVENTSEL_INT_CORE_ENABLE			(1ULL << 36)
 #define AMD64_EVENTSEL_GUESTONLY			(1ULL << 40)
@@ -87,6 +89,12 @@
 #define ARCH_PERFMON_BRANCH_MISSES_RETIRED		6
 #define ARCH_PERFMON_EVENTS_COUNT			7
 
+#define PEBS_DATACFG_MEMINFO	BIT_ULL(0)
+#define PEBS_DATACFG_GP	BIT_ULL(1)
+#define PEBS_DATACFG_XMMS	BIT_ULL(2)
+#define PEBS_DATACFG_LBRS	BIT_ULL(3)
+#define PEBS_DATACFG_LBR_SHIFT	24
+
 /*
  * Intel "Architectural Performance Monitoring" CPUID
  * detection/enumeration details:
@@ -177,6 +185,41 @@ struct x86_pmu_capability {
 #define GLOBAL_STATUS_TRACE_TOPAPMI			BIT_ULL(55)
 
 /*
+ * Adaptive PEBS v4
+ */
+
+struct pebs_basic {
+	u64 format_size;
+	u64 ip;
+	u64 applicable_counters;
+	u64 tsc;
+};
+
+struct pebs_meminfo {
+	u64 address;
+	u64 aux;
+	u64 latency;
+	u64 tsx_tuning;
+};
+
+struct pebs_gprs {
+	u64 flags, ip, ax, cx, dx, bx, sp, bp, si, di;
+	u64 r8, r9, r10, r11, r12, r13, r14, r15;
+};
+
+struct pebs_xmm {
+	u64 xmm[16*2];	/* two entries for each register */
+};
+
+struct pebs_lbr_entry {
+	u64 from, to, info;
+};
+
+struct pebs_lbr {
+	struct pebs_lbr_entry lbr[0]; /* Variable length */
+};
+
+/*
  * IBS cpuid feature detection
  */
 
@@ -248,6 +291,11 @@ extern void perf_events_lapic_init(void);
 #define PERF_EFLAGS_VM		(1UL << 5)
 
 struct pt_regs;
+struct x86_perf_regs {
+	struct pt_regs	regs;
+	u64		*xmm_regs;
+};
+
 extern unsigned long perf_instruction_pointer(struct pt_regs *regs);
 extern unsigned long perf_misc_flags(struct pt_regs *regs);
 #define perf_misc_flags(regs)	perf_misc_flags(regs)
@@ -260,14 +308,9 @@ extern unsigned long perf_misc_flags(struct pt_regs *regs);
  */
 #define perf_arch_fetch_caller_regs(regs, __ip)		{	\
 	(regs)->ip = (__ip);					\
-	(regs)->bp = caller_frame_pointer();			\
+	(regs)->sp = (unsigned long)__builtin_frame_address(0);	\
 	(regs)->cs = __KERNEL_CS;				\
 	regs->flags = 0;					\
-	asm volatile(						\
-		_ASM_MOV "%%"_ASM_SP ", %0\n"			\
-		: "=m" ((regs)->sp)				\
-		:: "memory"					\
-	);							\
 }
 
 struct perf_guest_switch_msr {
diff --git a/arch/x86/include/asm/pgtable.h b/arch/x86/include/asm/pgtable.h
index 2779ace16d23..3a221942f805 100644
--- a/arch/x86/include/asm/pgtable.h
+++ b/arch/x86/include/asm/pgtable.h
@@ -46,7 +46,7 @@ void ptdump_walk_user_pgd_level_checkwx(void);
  */
 extern unsigned long empty_zero_page[PAGE_SIZE / sizeof(unsigned long)]
 	__visible;
-#define ZERO_PAGE(vaddr) (virt_to_page(empty_zero_page))
+#define ZERO_PAGE(vaddr) ((void)(vaddr),virt_to_page(empty_zero_page))
 
 extern spinlock_t pgd_lock;
 extern struct list_head pgd_list;
@@ -1021,6 +1021,9 @@ static inline void __meminit init_trampoline_default(void)
 	/* Default trampoline pgd value */
 	trampoline_pgd_entry = init_top_pgt[pgd_index(__PAGE_OFFSET)];
 }
+
+void __init poking_init(void);
+
 # ifdef CONFIG_RANDOMIZE_MEMORY
 void __meminit init_trampoline(void);
 # else
diff --git a/arch/x86/include/asm/processor.h b/arch/x86/include/asm/processor.h
index 2bb3a648fc12..7e99ef67bff0 100644
--- a/arch/x86/include/asm/processor.h
+++ b/arch/x86/include/asm/processor.h
@@ -367,6 +367,13 @@ DECLARE_PER_CPU_PAGE_ALIGNED(struct tss_struct, cpu_tss_rw);
 #define __KERNEL_TSS_LIMIT	\
 	(IO_BITMAP_OFFSET + IO_BITMAP_BYTES + sizeof(unsigned long) - 1)
 
+/* Per CPU interrupt stacks */
+struct irq_stack {
+	char		stack[IRQ_STACK_SIZE];
+} __aligned(IRQ_STACK_SIZE);
+
+DECLARE_PER_CPU(struct irq_stack *, hardirq_stack_ptr);
+
 #ifdef CONFIG_X86_32
 DECLARE_PER_CPU(unsigned long, cpu_current_top_of_stack);
 #else
@@ -374,38 +381,25 @@ DECLARE_PER_CPU(unsigned long, cpu_current_top_of_stack);
 #define cpu_current_top_of_stack cpu_tss_rw.x86_tss.sp1
 #endif
 
-/*
- * Save the original ist values for checking stack pointers during debugging
- */
-struct orig_ist {
-	unsigned long		ist[7];
-};
-
 #ifdef CONFIG_X86_64
-DECLARE_PER_CPU(struct orig_ist, orig_ist);
-
-union irq_stack_union {
-	char irq_stack[IRQ_STACK_SIZE];
+struct fixed_percpu_data {
 	/*
 	 * GCC hardcodes the stack canary as %gs:40.  Since the
 	 * irq_stack is the object at %gs:0, we reserve the bottom
 	 * 48 bytes of the irq stack for the canary.
 	 */
-	struct {
-		char gs_base[40];
-		unsigned long stack_canary;
-	};
+	char		gs_base[40];
+	unsigned long	stack_canary;
 };
 
-DECLARE_PER_CPU_FIRST(union irq_stack_union, irq_stack_union) __visible;
-DECLARE_INIT_PER_CPU(irq_stack_union);
+DECLARE_PER_CPU_FIRST(struct fixed_percpu_data, fixed_percpu_data) __visible;
+DECLARE_INIT_PER_CPU(fixed_percpu_data);
 
 static inline unsigned long cpu_kernelmode_gs_base(int cpu)
 {
-	return (unsigned long)per_cpu(irq_stack_union.gs_base, cpu);
+	return (unsigned long)per_cpu(fixed_percpu_data.gs_base, cpu);
 }
 
-DECLARE_PER_CPU(char *, irq_stack_ptr);
 DECLARE_PER_CPU(unsigned int, irq_count);
 extern asmlinkage void ignore_sysret(void);
 
@@ -427,15 +421,8 @@ struct stack_canary {
 };
 DECLARE_PER_CPU_ALIGNED(struct stack_canary, stack_canary);
 #endif
-/*
- * per-CPU IRQ handling stacks
- */
-struct irq_stack {
-	u32                     stack[THREAD_SIZE/sizeof(u32)];
-} __aligned(THREAD_SIZE);
-
-DECLARE_PER_CPU(struct irq_stack *, hardirq_stack);
-DECLARE_PER_CPU(struct irq_stack *, softirq_stack);
+/* Per CPU softirq stack pointer */
+DECLARE_PER_CPU(struct irq_stack *, softirq_stack_ptr);
 #endif	/* X86_64 */
 
 extern unsigned int fpu_kernel_xstate_size;
diff --git a/arch/x86/include/asm/realmode.h b/arch/x86/include/asm/realmode.h
index 63b3393bd98e..c53682303c9c 100644
--- a/arch/x86/include/asm/realmode.h
+++ b/arch/x86/include/asm/realmode.h
@@ -77,7 +77,11 @@ static inline size_t real_mode_size_needed(void)
 	return ALIGN(real_mode_blob_end - real_mode_blob, PAGE_SIZE);
 }
 
-void set_real_mode_mem(phys_addr_t mem, size_t size);
+static inline void set_real_mode_mem(phys_addr_t mem)
+{
+	real_mode_header = (struct real_mode_header *) __va(mem);
+}
+
 void reserve_real_mode(void);
 
 #endif /* __ASSEMBLY__ */
diff --git a/arch/x86/include/asm/rwsem.h b/arch/x86/include/asm/rwsem.h
deleted file mode 100644
index 4c25cf6caefa..000000000000
--- a/arch/x86/include/asm/rwsem.h
+++ /dev/null
@@ -1,237 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 */
-/* rwsem.h: R/W semaphores implemented using XADD/CMPXCHG for i486+
- *
- * Written by David Howells (dhowells@redhat.com).
- *
- * Derived from asm-x86/semaphore.h
- *
- *
- * The MSW of the count is the negated number of active writers and waiting
- * lockers, and the LSW is the total number of active locks
- *
- * The lock count is initialized to 0 (no active and no waiting lockers).
- *
- * When a writer subtracts WRITE_BIAS, it'll get 0xffff0001 for the case of an
- * uncontended lock. This can be determined because XADD returns the old value.
- * Readers increment by 1 and see a positive value when uncontended, negative
- * if there are writers (and maybe) readers waiting (in which case it goes to
- * sleep).
- *
- * The value of WAITING_BIAS supports up to 32766 waiting processes. This can
- * be extended to 65534 by manually checking the whole MSW rather than relying
- * on the S flag.
- *
- * The value of ACTIVE_BIAS supports up to 65535 active processes.
- *
- * This should be totally fair - if anything is waiting, a process that wants a
- * lock will go to the back of the queue. When the currently active lock is
- * released, if there's a writer at the front of the queue, then that and only
- * that will be woken up; if there's a bunch of consecutive readers at the
- * front, then they'll all be woken up, but no other readers will be.
- */
-
-#ifndef _ASM_X86_RWSEM_H
-#define _ASM_X86_RWSEM_H
-
-#ifndef _LINUX_RWSEM_H
-#error "please don't include asm/rwsem.h directly, use linux/rwsem.h instead"
-#endif
-
-#ifdef __KERNEL__
-#include <asm/asm.h>
-
-/*
- * The bias values and the counter type limits the number of
- * potential readers/writers to 32767 for 32 bits and 2147483647
- * for 64 bits.
- */
-
-#ifdef CONFIG_X86_64
-# define RWSEM_ACTIVE_MASK		0xffffffffL
-#else
-# define RWSEM_ACTIVE_MASK		0x0000ffffL
-#endif
-
-#define RWSEM_UNLOCKED_VALUE		0x00000000L
-#define RWSEM_ACTIVE_BIAS		0x00000001L
-#define RWSEM_WAITING_BIAS		(-RWSEM_ACTIVE_MASK-1)
-#define RWSEM_ACTIVE_READ_BIAS		RWSEM_ACTIVE_BIAS
-#define RWSEM_ACTIVE_WRITE_BIAS		(RWSEM_WAITING_BIAS + RWSEM_ACTIVE_BIAS)
-
-/*
- * lock for reading
- */
-#define ____down_read(sem, slow_path)					\
-({									\
-	struct rw_semaphore* ret;					\
-	asm volatile("# beginning down_read\n\t"			\
-		     LOCK_PREFIX _ASM_INC "(%[sem])\n\t"		\
-		     /* adds 0x00000001 */				\
-		     "  jns        1f\n"				\
-		     "  call " slow_path "\n"				\
-		     "1:\n\t"						\
-		     "# ending down_read\n\t"				\
-		     : "+m" (sem->count), "=a" (ret),			\
-			ASM_CALL_CONSTRAINT				\
-		     : [sem] "a" (sem)					\
-		     : "memory", "cc");					\
-	ret;								\
-})
-
-static inline void __down_read(struct rw_semaphore *sem)
-{
-	____down_read(sem, "call_rwsem_down_read_failed");
-}
-
-static inline int __down_read_killable(struct rw_semaphore *sem)
-{
-	if (IS_ERR(____down_read(sem, "call_rwsem_down_read_failed_killable")))
-		return -EINTR;
-	return 0;
-}
-
-/*
- * trylock for reading -- returns 1 if successful, 0 if contention
- */
-static inline bool __down_read_trylock(struct rw_semaphore *sem)
-{
-	long result, tmp;
-	asm volatile("# beginning __down_read_trylock\n\t"
-		     "  mov          %[count],%[result]\n\t"
-		     "1:\n\t"
-		     "  mov          %[result],%[tmp]\n\t"
-		     "  add          %[inc],%[tmp]\n\t"
-		     "  jle	     2f\n\t"
-		     LOCK_PREFIX "  cmpxchg  %[tmp],%[count]\n\t"
-		     "  jnz	     1b\n\t"
-		     "2:\n\t"
-		     "# ending __down_read_trylock\n\t"
-		     : [count] "+m" (sem->count), [result] "=&a" (result),
-		       [tmp] "=&r" (tmp)
-		     : [inc] "i" (RWSEM_ACTIVE_READ_BIAS)
-		     : "memory", "cc");
-	return result >= 0;
-}
-
-/*
- * lock for writing
- */
-#define ____down_write(sem, slow_path)			\
-({							\
-	long tmp;					\
-	struct rw_semaphore* ret;			\
-							\
-	asm volatile("# beginning down_write\n\t"	\
-		     LOCK_PREFIX "  xadd      %[tmp],(%[sem])\n\t"	\
-		     /* adds 0xffff0001, returns the old value */ \
-		     "  test " __ASM_SEL(%w1,%k1) "," __ASM_SEL(%w1,%k1) "\n\t" \
-		     /* was the active mask 0 before? */\
-		     "  jz        1f\n"			\
-		     "  call " slow_path "\n"		\
-		     "1:\n"				\
-		     "# ending down_write"		\
-		     : "+m" (sem->count), [tmp] "=d" (tmp),	\
-		       "=a" (ret), ASM_CALL_CONSTRAINT	\
-		     : [sem] "a" (sem), "[tmp]" (RWSEM_ACTIVE_WRITE_BIAS) \
-		     : "memory", "cc");			\
-	ret;						\
-})
-
-static inline void __down_write(struct rw_semaphore *sem)
-{
-	____down_write(sem, "call_rwsem_down_write_failed");
-}
-
-static inline int __down_write_killable(struct rw_semaphore *sem)
-{
-	if (IS_ERR(____down_write(sem, "call_rwsem_down_write_failed_killable")))
-		return -EINTR;
-
-	return 0;
-}
-
-/*
- * trylock for writing -- returns 1 if successful, 0 if contention
- */
-static inline bool __down_write_trylock(struct rw_semaphore *sem)
-{
-	bool result;
-	long tmp0, tmp1;
-	asm volatile("# beginning __down_write_trylock\n\t"
-		     "  mov          %[count],%[tmp0]\n\t"
-		     "1:\n\t"
-		     "  test " __ASM_SEL(%w1,%k1) "," __ASM_SEL(%w1,%k1) "\n\t"
-		     /* was the active mask 0 before? */
-		     "  jnz          2f\n\t"
-		     "  mov          %[tmp0],%[tmp1]\n\t"
-		     "  add          %[inc],%[tmp1]\n\t"
-		     LOCK_PREFIX "  cmpxchg  %[tmp1],%[count]\n\t"
-		     "  jnz	     1b\n\t"
-		     "2:\n\t"
-		     CC_SET(e)
-		     "# ending __down_write_trylock\n\t"
-		     : [count] "+m" (sem->count), [tmp0] "=&a" (tmp0),
-		       [tmp1] "=&r" (tmp1), CC_OUT(e) (result)
-		     : [inc] "er" (RWSEM_ACTIVE_WRITE_BIAS)
-		     : "memory");
-	return result;
-}
-
-/*
- * unlock after reading
- */
-static inline void __up_read(struct rw_semaphore *sem)
-{
-	long tmp;
-	asm volatile("# beginning __up_read\n\t"
-		     LOCK_PREFIX "  xadd      %[tmp],(%[sem])\n\t"
-		     /* subtracts 1, returns the old value */
-		     "  jns        1f\n\t"
-		     "  call call_rwsem_wake\n" /* expects old value in %edx */
-		     "1:\n"
-		     "# ending __up_read\n"
-		     : "+m" (sem->count), [tmp] "=d" (tmp)
-		     : [sem] "a" (sem), "[tmp]" (-RWSEM_ACTIVE_READ_BIAS)
-		     : "memory", "cc");
-}
-
-/*
- * unlock after writing
- */
-static inline void __up_write(struct rw_semaphore *sem)
-{
-	long tmp;
-	asm volatile("# beginning __up_write\n\t"
-		     LOCK_PREFIX "  xadd      %[tmp],(%[sem])\n\t"
-		     /* subtracts 0xffff0001, returns the old value */
-		     "  jns        1f\n\t"
-		     "  call call_rwsem_wake\n" /* expects old value in %edx */
-		     "1:\n\t"
-		     "# ending __up_write\n"
-		     : "+m" (sem->count), [tmp] "=d" (tmp)
-		     : [sem] "a" (sem), "[tmp]" (-RWSEM_ACTIVE_WRITE_BIAS)
-		     : "memory", "cc");
-}
-
-/*
- * downgrade write lock to read lock
- */
-static inline void __downgrade_write(struct rw_semaphore *sem)
-{
-	asm volatile("# beginning __downgrade_write\n\t"
-		     LOCK_PREFIX _ASM_ADD "%[inc],(%[sem])\n\t"
-		     /*
-		      * transitions 0xZZZZ0001 -> 0xYYYY0001 (i386)
-		      *     0xZZZZZZZZ00000001 -> 0xYYYYYYYY00000001 (x86_64)
-		      */
-		     "  jns       1f\n\t"
-		     "  call call_rwsem_downgrade_wake\n"
-		     "1:\n\t"
-		     "# ending __downgrade_write\n"
-		     : "+m" (sem->count)
-		     : [sem] "a" (sem), [inc] "er" (-RWSEM_WAITING_BIAS)
-		     : "memory", "cc");
-}
-
-#endif /* __KERNEL__ */
-#endif /* _ASM_X86_RWSEM_H */
diff --git a/arch/x86/include/asm/set_memory.h b/arch/x86/include/asm/set_memory.h
index 07a25753e85c..ae7b909dc242 100644
--- a/arch/x86/include/asm/set_memory.h
+++ b/arch/x86/include/asm/set_memory.h
@@ -85,6 +85,9 @@ int set_pages_nx(struct page *page, int numpages);
 int set_pages_ro(struct page *page, int numpages);
 int set_pages_rw(struct page *page, int numpages);
 
+int set_direct_map_invalid_noflush(struct page *page);
+int set_direct_map_default_noflush(struct page *page);
+
 extern int kernel_set_to_readonly;
 void set_kernel_text_rw(void);
 void set_kernel_text_ro(void);
diff --git a/arch/x86/include/asm/smap.h b/arch/x86/include/asm/smap.h
index db333300bd4b..f94a7d0ddd49 100644
--- a/arch/x86/include/asm/smap.h
+++ b/arch/x86/include/asm/smap.h
@@ -13,13 +13,12 @@
 #ifndef _ASM_X86_SMAP_H
 #define _ASM_X86_SMAP_H
 
-#include <linux/stringify.h>
 #include <asm/nops.h>
 #include <asm/cpufeatures.h>
 
 /* "Raw" instruction opcodes */
-#define __ASM_CLAC	.byte 0x0f,0x01,0xca
-#define __ASM_STAC	.byte 0x0f,0x01,0xcb
+#define __ASM_CLAC	".byte 0x0f,0x01,0xca"
+#define __ASM_STAC	".byte 0x0f,0x01,0xcb"
 
 #ifdef __ASSEMBLY__
 
@@ -28,10 +27,10 @@
 #ifdef CONFIG_X86_SMAP
 
 #define ASM_CLAC \
-	ALTERNATIVE "", __stringify(__ASM_CLAC), X86_FEATURE_SMAP
+	ALTERNATIVE "", __ASM_CLAC, X86_FEATURE_SMAP
 
 #define ASM_STAC \
-	ALTERNATIVE "", __stringify(__ASM_STAC), X86_FEATURE_SMAP
+	ALTERNATIVE "", __ASM_STAC, X86_FEATURE_SMAP
 
 #else /* CONFIG_X86_SMAP */
 
@@ -49,26 +48,46 @@
 static __always_inline void clac(void)
 {
 	/* Note: a barrier is implicit in alternative() */
-	alternative("", __stringify(__ASM_CLAC), X86_FEATURE_SMAP);
+	alternative("", __ASM_CLAC, X86_FEATURE_SMAP);
 }
 
 static __always_inline void stac(void)
 {
 	/* Note: a barrier is implicit in alternative() */
-	alternative("", __stringify(__ASM_STAC), X86_FEATURE_SMAP);
+	alternative("", __ASM_STAC, X86_FEATURE_SMAP);
+}
+
+static __always_inline unsigned long smap_save(void)
+{
+	unsigned long flags;
+
+	asm volatile (ALTERNATIVE("", "pushf; pop %0; " __ASM_CLAC,
+				  X86_FEATURE_SMAP)
+		      : "=rm" (flags) : : "memory", "cc");
+
+	return flags;
+}
+
+static __always_inline void smap_restore(unsigned long flags)
+{
+	asm volatile (ALTERNATIVE("", "push %0; popf", X86_FEATURE_SMAP)
+		      : : "g" (flags) : "memory", "cc");
 }
 
 /* These macros can be used in asm() statements */
 #define ASM_CLAC \
-	ALTERNATIVE("", __stringify(__ASM_CLAC), X86_FEATURE_SMAP)
+	ALTERNATIVE("", __ASM_CLAC, X86_FEATURE_SMAP)
 #define ASM_STAC \
-	ALTERNATIVE("", __stringify(__ASM_STAC), X86_FEATURE_SMAP)
+	ALTERNATIVE("", __ASM_STAC, X86_FEATURE_SMAP)
 
 #else /* CONFIG_X86_SMAP */
 
 static inline void clac(void) { }
 static inline void stac(void) { }
 
+static inline unsigned long smap_save(void) { return 0; }
+static inline void smap_restore(unsigned long flags) { }
+
 #define ASM_CLAC
 #define ASM_STAC
 
diff --git a/arch/x86/include/asm/smp.h b/arch/x86/include/asm/smp.h
index 2e95b6c1bca3..da545df207b2 100644
--- a/arch/x86/include/asm/smp.h
+++ b/arch/x86/include/asm/smp.h
@@ -131,7 +131,7 @@ void native_smp_prepare_boot_cpu(void);
 void native_smp_prepare_cpus(unsigned int max_cpus);
 void calculate_max_logical_packages(void);
 void native_smp_cpus_done(unsigned int max_cpus);
-void common_cpu_up(unsigned int cpunum, struct task_struct *tidle);
+int common_cpu_up(unsigned int cpunum, struct task_struct *tidle);
 int native_cpu_up(unsigned int cpunum, struct task_struct *tidle);
 int native_cpu_disable(void);
 int common_cpu_die(unsigned int cpu);
diff --git a/arch/x86/include/asm/stackprotector.h b/arch/x86/include/asm/stackprotector.h
index 8ec97a62c245..91e29b6a86a5 100644
--- a/arch/x86/include/asm/stackprotector.h
+++ b/arch/x86/include/asm/stackprotector.h
@@ -13,7 +13,7 @@
  * On x86_64, %gs is shared by percpu area and stack canary.  All
  * percpu symbols are zero based and %gs points to the base of percpu
  * area.  The first occupant of the percpu area is always
- * irq_stack_union which contains stack_canary at offset 40.  Userland
+ * fixed_percpu_data which contains stack_canary at offset 40.  Userland
  * %gs is always saved and restored on kernel entry and exit using
  * swapgs, so stack protector doesn't add any complexity there.
  *
@@ -64,7 +64,7 @@ static __always_inline void boot_init_stack_canary(void)
 	u64 tsc;
 
 #ifdef CONFIG_X86_64
-	BUILD_BUG_ON(offsetof(union irq_stack_union, stack_canary) != 40);
+	BUILD_BUG_ON(offsetof(struct fixed_percpu_data, stack_canary) != 40);
 #endif
 	/*
 	 * We both use the random pool and the current TSC as a source
@@ -79,7 +79,7 @@ static __always_inline void boot_init_stack_canary(void)
 
 	current->stack_canary = canary;
 #ifdef CONFIG_X86_64
-	this_cpu_write(irq_stack_union.stack_canary, canary);
+	this_cpu_write(fixed_percpu_data.stack_canary, canary);
 #else
 	this_cpu_write(stack_canary.canary, canary);
 #endif
diff --git a/arch/x86/include/asm/stacktrace.h b/arch/x86/include/asm/stacktrace.h
index f335aad404a4..a8d0cdf48616 100644
--- a/arch/x86/include/asm/stacktrace.h
+++ b/arch/x86/include/asm/stacktrace.h
@@ -9,6 +9,8 @@
 
 #include <linux/uaccess.h>
 #include <linux/ptrace.h>
+
+#include <asm/cpu_entry_area.h>
 #include <asm/switch_to.h>
 
 enum stack_type {
@@ -98,19 +100,6 @@ struct stack_frame_ia32 {
     u32 return_address;
 };
 
-static inline unsigned long caller_frame_pointer(void)
-{
-	struct stack_frame *frame;
-
-	frame = __builtin_frame_address(0);
-
-#ifdef CONFIG_FRAME_POINTER
-	frame = frame->next_frame;
-#endif
-
-	return (unsigned long)frame;
-}
-
 void show_opcodes(struct pt_regs *regs, const char *loglvl);
 void show_ip(struct pt_regs *regs, const char *loglvl);
 #endif /* _ASM_X86_STACKTRACE_H */
diff --git a/arch/x86/include/asm/switch_to.h b/arch/x86/include/asm/switch_to.h
index 7cf1a270d891..18a4b6890fa8 100644
--- a/arch/x86/include/asm/switch_to.h
+++ b/arch/x86/include/asm/switch_to.h
@@ -46,6 +46,7 @@ struct inactive_task_frame {
 	unsigned long r13;
 	unsigned long r12;
 #else
+	unsigned long flags;
 	unsigned long si;
 	unsigned long di;
 #endif
diff --git a/arch/x86/include/asm/sync_bitops.h b/arch/x86/include/asm/sync_bitops.h
index 2fe745356fb1..6d8d6bc183b7 100644
--- a/arch/x86/include/asm/sync_bitops.h
+++ b/arch/x86/include/asm/sync_bitops.h
@@ -14,6 +14,8 @@
  * bit 0 is the LSB of addr; bit 32 is the LSB of (addr+1).
  */
 
+#include <asm/rmwcc.h>
+
 #define ADDR (*(volatile long *)addr)
 
 /**
@@ -29,7 +31,7 @@
  */
 static inline void sync_set_bit(long nr, volatile unsigned long *addr)
 {
-	asm volatile("lock; bts %1,%0"
+	asm volatile("lock; " __ASM_SIZE(bts) " %1,%0"
 		     : "+m" (ADDR)
 		     : "Ir" (nr)
 		     : "memory");
@@ -47,7 +49,7 @@ static inline void sync_set_bit(long nr, volatile unsigned long *addr)
  */
 static inline void sync_clear_bit(long nr, volatile unsigned long *addr)
 {
-	asm volatile("lock; btr %1,%0"
+	asm volatile("lock; " __ASM_SIZE(btr) " %1,%0"
 		     : "+m" (ADDR)
 		     : "Ir" (nr)
 		     : "memory");
@@ -64,7 +66,7 @@ static inline void sync_clear_bit(long nr, volatile unsigned long *addr)
  */
 static inline void sync_change_bit(long nr, volatile unsigned long *addr)
 {
-	asm volatile("lock; btc %1,%0"
+	asm volatile("lock; " __ASM_SIZE(btc) " %1,%0"
 		     : "+m" (ADDR)
 		     : "Ir" (nr)
 		     : "memory");
@@ -78,14 +80,9 @@ static inline void sync_change_bit(long nr, volatile unsigned long *addr)
  * This operation is atomic and cannot be reordered.
  * It also implies a memory barrier.
  */
-static inline int sync_test_and_set_bit(long nr, volatile unsigned long *addr)
+static inline bool sync_test_and_set_bit(long nr, volatile unsigned long *addr)
 {
-	unsigned char oldbit;
-
-	asm volatile("lock; bts %2,%1\n\tsetc %0"
-		     : "=qm" (oldbit), "+m" (ADDR)
-		     : "Ir" (nr) : "memory");
-	return oldbit;
+	return GEN_BINARY_RMWcc("lock; " __ASM_SIZE(bts), *addr, c, "Ir", nr);
 }
 
 /**
@@ -98,12 +95,7 @@ static inline int sync_test_and_set_bit(long nr, volatile unsigned long *addr)
  */
 static inline int sync_test_and_clear_bit(long nr, volatile unsigned long *addr)
 {
-	unsigned char oldbit;
-
-	asm volatile("lock; btr %2,%1\n\tsetc %0"
-		     : "=qm" (oldbit), "+m" (ADDR)
-		     : "Ir" (nr) : "memory");
-	return oldbit;
+	return GEN_BINARY_RMWcc("lock; " __ASM_SIZE(btr), *addr, c, "Ir", nr);
 }
 
 /**
@@ -116,12 +108,7 @@ static inline int sync_test_and_clear_bit(long nr, volatile unsigned long *addr)
  */
 static inline int sync_test_and_change_bit(long nr, volatile unsigned long *addr)
 {
-	unsigned char oldbit;
-
-	asm volatile("lock; btc %2,%1\n\tsetc %0"
-		     : "=qm" (oldbit), "+m" (ADDR)
-		     : "Ir" (nr) : "memory");
-	return oldbit;
+	return GEN_BINARY_RMWcc("lock; " __ASM_SIZE(btc), *addr, c, "Ir", nr);
 }
 
 #define sync_test_bit(nr, addr) test_bit(nr, addr)
diff --git a/arch/x86/include/asm/syscall.h b/arch/x86/include/asm/syscall.h
index d653139857af..4c305471ec33 100644
--- a/arch/x86/include/asm/syscall.h
+++ b/arch/x86/include/asm/syscall.h
@@ -91,11 +91,9 @@ static inline void syscall_set_return_value(struct task_struct *task,
 
 static inline void syscall_get_arguments(struct task_struct *task,
 					 struct pt_regs *regs,
-					 unsigned int i, unsigned int n,
 					 unsigned long *args)
 {
-	BUG_ON(i + n > 6);
-	memcpy(args, &regs->bx + i, n * sizeof(args[0]));
+	memcpy(args, &regs->bx, 6 * sizeof(args[0]));
 }
 
 static inline void syscall_set_arguments(struct task_struct *task,
@@ -116,124 +114,50 @@ static inline int syscall_get_arch(void)
 
 static inline void syscall_get_arguments(struct task_struct *task,
 					 struct pt_regs *regs,
-					 unsigned int i, unsigned int n,
 					 unsigned long *args)
 {
 # ifdef CONFIG_IA32_EMULATION
-	if (task->thread_info.status & TS_COMPAT)
-		switch (i) {
-		case 0:
-			if (!n--) break;
-			*args++ = regs->bx;
-		case 1:
-			if (!n--) break;
-			*args++ = regs->cx;
-		case 2:
-			if (!n--) break;
-			*args++ = regs->dx;
-		case 3:
-			if (!n--) break;
-			*args++ = regs->si;
-		case 4:
-			if (!n--) break;
-			*args++ = regs->di;
-		case 5:
-			if (!n--) break;
-			*args++ = regs->bp;
-		case 6:
-			if (!n--) break;
-		default:
-			BUG();
-			break;
-		}
-	else
+	if (task->thread_info.status & TS_COMPAT) {
+		*args++ = regs->bx;
+		*args++ = regs->cx;
+		*args++ = regs->dx;
+		*args++ = regs->si;
+		*args++ = regs->di;
+		*args   = regs->bp;
+	} else
 # endif
-		switch (i) {
-		case 0:
-			if (!n--) break;
-			*args++ = regs->di;
-		case 1:
-			if (!n--) break;
-			*args++ = regs->si;
-		case 2:
-			if (!n--) break;
-			*args++ = regs->dx;
-		case 3:
-			if (!n--) break;
-			*args++ = regs->r10;
-		case 4:
-			if (!n--) break;
-			*args++ = regs->r8;
-		case 5:
-			if (!n--) break;
-			*args++ = regs->r9;
-		case 6:
-			if (!n--) break;
-		default:
-			BUG();
-			break;
-		}
+	{
+		*args++ = regs->di;
+		*args++ = regs->si;
+		*args++ = regs->dx;
+		*args++ = regs->r10;
+		*args++ = regs->r8;
+		*args   = regs->r9;
+	}
 }
 
 static inline void syscall_set_arguments(struct task_struct *task,
 					 struct pt_regs *regs,
-					 unsigned int i, unsigned int n,
 					 const unsigned long *args)
 {
 # ifdef CONFIG_IA32_EMULATION
-	if (task->thread_info.status & TS_COMPAT)
-		switch (i) {
-		case 0:
-			if (!n--) break;
-			regs->bx = *args++;
-		case 1:
-			if (!n--) break;
-			regs->cx = *args++;
-		case 2:
-			if (!n--) break;
-			regs->dx = *args++;
-		case 3:
-			if (!n--) break;
-			regs->si = *args++;
-		case 4:
-			if (!n--) break;
-			regs->di = *args++;
-		case 5:
-			if (!n--) break;
-			regs->bp = *args++;
-		case 6:
-			if (!n--) break;
-		default:
-			BUG();
-			break;
-		}
-	else
+	if (task->thread_info.status & TS_COMPAT) {
+		regs->bx = *args++;
+		regs->cx = *args++;
+		regs->dx = *args++;
+		regs->si = *args++;
+		regs->di = *args++;
+		regs->bp = *args;
+	} else
 # endif
-		switch (i) {
-		case 0:
-			if (!n--) break;
-			regs->di = *args++;
-		case 1:
-			if (!n--) break;
-			regs->si = *args++;
-		case 2:
-			if (!n--) break;
-			regs->dx = *args++;
-		case 3:
-			if (!n--) break;
-			regs->r10 = *args++;
-		case 4:
-			if (!n--) break;
-			regs->r8 = *args++;
-		case 5:
-			if (!n--) break;
-			regs->r9 = *args++;
-		case 6:
-			if (!n--) break;
-		default:
-			BUG();
-			break;
-		}
+	{
+		regs->di = *args++;
+		regs->si = *args++;
+		regs->dx = *args++;
+		regs->r10 = *args++;
+		regs->r8 = *args++;
+		regs->r9 = *args;
+	}
 }
 
 static inline int syscall_get_arch(void)
diff --git a/arch/x86/include/asm/text-patching.h b/arch/x86/include/asm/text-patching.h
index e85ff65c43c3..c90678fd391a 100644
--- a/arch/x86/include/asm/text-patching.h
+++ b/arch/x86/include/asm/text-patching.h
@@ -18,7 +18,7 @@ static inline void apply_paravirt(struct paravirt_patch_site *start,
 #define __parainstructions_end	NULL
 #endif
 
-extern void *text_poke_early(void *addr, const void *opcode, size_t len);
+extern void text_poke_early(void *addr, const void *opcode, size_t len);
 
 /*
  * Clear and restore the kernel write-protection flag on the local CPU.
@@ -35,8 +35,11 @@ extern void *text_poke_early(void *addr, const void *opcode, size_t len);
  * inconsistent instruction while you patch.
  */
 extern void *text_poke(void *addr, const void *opcode, size_t len);
+extern void *text_poke_kgdb(void *addr, const void *opcode, size_t len);
 extern int poke_int3_handler(struct pt_regs *regs);
-extern void *text_poke_bp(void *addr, const void *opcode, size_t len, void *handler);
+extern void text_poke_bp(void *addr, const void *opcode, size_t len, void *handler);
 extern int after_bootmem;
+extern __ro_after_init struct mm_struct *poking_mm;
+extern __ro_after_init unsigned long poking_addr;
 
 #endif /* _ASM_X86_TEXT_PATCHING_H */
diff --git a/arch/x86/include/asm/tlb.h b/arch/x86/include/asm/tlb.h
index 404b8b1d44f5..f23e7aaff4cd 100644
--- a/arch/x86/include/asm/tlb.h
+++ b/arch/x86/include/asm/tlb.h
@@ -6,6 +6,7 @@
 #define tlb_end_vma(tlb, vma) do { } while (0)
 #define __tlb_remove_tlb_entry(tlb, ptep, address) do { } while (0)
 
+#define tlb_flush tlb_flush
 static inline void tlb_flush(struct mmu_gather *tlb);
 
 #include <asm-generic/tlb.h>
diff --git a/arch/x86/include/asm/tlbflush.h b/arch/x86/include/asm/tlbflush.h
index f4204bf377fc..dee375831962 100644
--- a/arch/x86/include/asm/tlbflush.h
+++ b/arch/x86/include/asm/tlbflush.h
@@ -167,7 +167,7 @@ struct tlb_state {
 	 */
 	struct mm_struct *loaded_mm;
 
-#define LOADED_MM_SWITCHING ((struct mm_struct *)1)
+#define LOADED_MM_SWITCHING ((struct mm_struct *)1UL)
 
 	/* Last user mm for optimizing IBPB */
 	union {
@@ -274,6 +274,8 @@ static inline bool nmi_uaccess_okay(void)
 	return true;
 }
 
+#define nmi_uaccess_okay nmi_uaccess_okay
+
 /* Initialize cr4 shadow for this CPU. */
 static inline void cr4_init_shadow(void)
 {
diff --git a/arch/x86/include/asm/uaccess.h b/arch/x86/include/asm/uaccess.h
index 1954dd5552a2..c82abd6e4ca3 100644
--- a/arch/x86/include/asm/uaccess.h
+++ b/arch/x86/include/asm/uaccess.h
@@ -427,10 +427,11 @@ do {									\
 ({								\
 	__label__ __pu_label;					\
 	int __pu_err = -EFAULT;					\
-	__typeof__(*(ptr)) __pu_val;				\
-	__pu_val = x;						\
+	__typeof__(*(ptr)) __pu_val = (x);			\
+	__typeof__(ptr) __pu_ptr = (ptr);			\
+	__typeof__(size) __pu_size = (size);			\
 	__uaccess_begin();					\
-	__put_user_size(__pu_val, (ptr), (size), __pu_label);	\
+	__put_user_size(__pu_val, __pu_ptr, __pu_size, __pu_label);	\
 	__pu_err = 0;						\
 __pu_label:							\
 	__uaccess_end();					\
@@ -585,7 +586,6 @@ extern void __cmpxchg_wrong_size(void)
 #define __user_atomic_cmpxchg_inatomic(uval, ptr, old, new, size)	\
 ({									\
 	int __ret = 0;							\
-	__typeof__(ptr) __uval = (uval);				\
 	__typeof__(*(ptr)) __old = (old);				\
 	__typeof__(*(ptr)) __new = (new);				\
 	__uaccess_begin_nospec();					\
@@ -661,7 +661,7 @@ extern void __cmpxchg_wrong_size(void)
 		__cmpxchg_wrong_size();					\
 	}								\
 	__uaccess_end();						\
-	*__uval = __old;						\
+	*(uval) = __old;						\
 	__ret;								\
 })
 
@@ -705,7 +705,7 @@ extern struct movsl_mask {
  * checking before using them, but you have to surround them with the
  * user_access_begin/end() pair.
  */
-static __must_check inline bool user_access_begin(const void __user *ptr, size_t len)
+static __must_check __always_inline bool user_access_begin(const void __user *ptr, size_t len)
 {
 	if (unlikely(!access_ok(ptr,len)))
 		return 0;
@@ -715,6 +715,9 @@ static __must_check inline bool user_access_begin(const void __user *ptr, size_t
 #define user_access_begin(a,b)	user_access_begin(a,b)
 #define user_access_end()	__uaccess_end()
 
+#define user_access_save()	smap_save()
+#define user_access_restore(x)	smap_restore(x)
+
 #define unsafe_put_user(x, ptr, label)	\
 	__put_user_size((__typeof__(*(ptr)))(x), (ptr), sizeof(*(ptr)), label)
 
diff --git a/arch/x86/include/asm/uaccess_64.h b/arch/x86/include/asm/uaccess_64.h
index a9d637bc301d..5cd1caa8bc65 100644
--- a/arch/x86/include/asm/uaccess_64.h
+++ b/arch/x86/include/asm/uaccess_64.h
@@ -208,9 +208,6 @@ __copy_from_user_flushcache(void *dst, const void __user *src, unsigned size)
 }
 
 unsigned long
-copy_user_handle_tail(char *to, char *from, unsigned len);
-
-unsigned long
 mcsafe_handle_tail(char *to, char *from, unsigned len);
 
 #endif /* _ASM_X86_UACCESS_64_H */
diff --git a/arch/x86/include/asm/xen/hypercall.h b/arch/x86/include/asm/xen/hypercall.h
index de6f0d59a24f..d50c7b747d8b 100644
--- a/arch/x86/include/asm/xen/hypercall.h
+++ b/arch/x86/include/asm/xen/hypercall.h
@@ -206,6 +206,9 @@ xen_single_call(unsigned int call,
 	__HYPERCALL_DECLS;
 	__HYPERCALL_5ARG(a1, a2, a3, a4, a5);
 
+	if (call >= PAGE_SIZE / sizeof(hypercall_page[0]))
+		return -EINVAL;
+
 	asm volatile(CALL_NOSPEC
 		     : __HYPERCALL_5PARAM
 		     : [thunk_target] "a" (&hypercall_page[call])
@@ -214,6 +217,22 @@ xen_single_call(unsigned int call,
 	return (long)__res;
 }
 
+static __always_inline void __xen_stac(void)
+{
+	/*
+	 * Suppress objtool seeing the STAC/CLAC and getting confused about it
+	 * calling random code with AC=1.
+	 */
+	asm volatile(ANNOTATE_IGNORE_ALTERNATIVE
+		     ASM_STAC ::: "memory", "flags");
+}
+
+static __always_inline void __xen_clac(void)
+{
+	asm volatile(ANNOTATE_IGNORE_ALTERNATIVE
+		     ASM_CLAC ::: "memory", "flags");
+}
+
 static inline long
 privcmd_call(unsigned int call,
 	     unsigned long a1, unsigned long a2,
@@ -222,9 +241,9 @@ privcmd_call(unsigned int call,
 {
 	long res;
 
-	stac();
+	__xen_stac();
 	res = xen_single_call(call, a1, a2, a3, a4, a5);
-	clac();
+	__xen_clac();
 
 	return res;
 }
@@ -421,9 +440,9 @@ HYPERVISOR_dm_op(
 	domid_t dom, unsigned int nr_bufs, struct xen_dm_op_buf *bufs)
 {
 	int ret;
-	stac();
+	__xen_stac();
 	ret = _hypercall3(int, dm_op, dom, nr_bufs, bufs);
-	clac();
+	__xen_clac();
 	return ret;
 }
 
diff --git a/arch/x86/include/uapi/asm/kvm.h b/arch/x86/include/uapi/asm/kvm.h
index dabfcf7c3941..7a0e64ccd6ff 100644
--- a/arch/x86/include/uapi/asm/kvm.h
+++ b/arch/x86/include/uapi/asm/kvm.h
@@ -381,6 +381,7 @@ struct kvm_sync_regs {
 #define KVM_X86_QUIRK_LINT0_REENABLED	(1 << 0)
 #define KVM_X86_QUIRK_CD_NW_CLEARED	(1 << 1)
 #define KVM_X86_QUIRK_LAPIC_MMIO_HOLE	(1 << 2)
+#define KVM_X86_QUIRK_OUT_7E_INC_RIP	(1 << 3)
 
 #define KVM_STATE_NESTED_GUEST_MODE	0x00000001
 #define KVM_STATE_NESTED_RUN_PENDING	0x00000002
diff --git a/arch/x86/include/uapi/asm/perf_regs.h b/arch/x86/include/uapi/asm/perf_regs.h
index f3329cabce5c..ac67bbea10ca 100644
--- a/arch/x86/include/uapi/asm/perf_regs.h
+++ b/arch/x86/include/uapi/asm/perf_regs.h
@@ -27,8 +27,29 @@ enum perf_event_x86_regs {
 	PERF_REG_X86_R13,
 	PERF_REG_X86_R14,
 	PERF_REG_X86_R15,
-
+	/* These are the limits for the GPRs. */
 	PERF_REG_X86_32_MAX = PERF_REG_X86_GS + 1,
 	PERF_REG_X86_64_MAX = PERF_REG_X86_R15 + 1,
+
+	/* These all need two bits set because they are 128bit */
+	PERF_REG_X86_XMM0  = 32,
+	PERF_REG_X86_XMM1  = 34,
+	PERF_REG_X86_XMM2  = 36,
+	PERF_REG_X86_XMM3  = 38,
+	PERF_REG_X86_XMM4  = 40,
+	PERF_REG_X86_XMM5  = 42,
+	PERF_REG_X86_XMM6  = 44,
+	PERF_REG_X86_XMM7  = 46,
+	PERF_REG_X86_XMM8  = 48,
+	PERF_REG_X86_XMM9  = 50,
+	PERF_REG_X86_XMM10 = 52,
+	PERF_REG_X86_XMM11 = 54,
+	PERF_REG_X86_XMM12 = 56,
+	PERF_REG_X86_XMM13 = 58,
+	PERF_REG_X86_XMM14 = 60,
+	PERF_REG_X86_XMM15 = 62,
+
+	/* These include both GPRs and XMMX registers */
+	PERF_REG_X86_XMM_MAX = PERF_REG_X86_XMM15 + 2,
 };
 #endif /* _ASM_X86_PERF_REGS_H */
diff --git a/arch/x86/include/uapi/asm/vmx.h b/arch/x86/include/uapi/asm/vmx.h
index f0b0c90dd398..d213ec5c3766 100644
--- a/arch/x86/include/uapi/asm/vmx.h
+++ b/arch/x86/include/uapi/asm/vmx.h
@@ -146,6 +146,7 @@
 
 #define VMX_ABORT_SAVE_GUEST_MSR_FAIL        1
 #define VMX_ABORT_LOAD_HOST_PDPTE_FAIL       2
+#define VMX_ABORT_VMCS_CORRUPTED             3
 #define VMX_ABORT_LOAD_HOST_MSR_FAIL         4
 
 #endif /* _UAPIVMX_H */
diff --git a/arch/x86/kernel/acpi/cstate.c b/arch/x86/kernel/acpi/cstate.c
index 158ad1483c43..cb6e076a6d39 100644
--- a/arch/x86/kernel/acpi/cstate.c
+++ b/arch/x86/kernel/acpi/cstate.c
@@ -51,6 +51,18 @@ void acpi_processor_power_init_bm_check(struct acpi_processor_flags *flags,
 	if (c->x86_vendor == X86_VENDOR_INTEL &&
 	    (c->x86 > 0xf || (c->x86 == 6 && c->x86_model >= 0x0f)))
 			flags->bm_control = 0;
+	/*
+	 * For all recent Centaur CPUs, the ucode will make sure that each
+	 * core can keep cache coherence with each other while entering C3
+	 * type state. So, set bm_check to 1 to indicate that the kernel
+	 * doesn't need to execute a cache flush operation (WBINVD) when
+	 * entering C3 type state.
+	 */
+	if (c->x86_vendor == X86_VENDOR_CENTAUR) {
+		if (c->x86 > 6 || (c->x86 == 6 && c->x86_model == 0x0f &&
+		    c->x86_stepping >= 0x0e))
+			flags->bm_check = 1;
+	}
 }
 EXPORT_SYMBOL(acpi_processor_power_init_bm_check);
 
diff --git a/arch/x86/kernel/alternative.c b/arch/x86/kernel/alternative.c
index 9a79c7808f9c..7b9b49dfc05a 100644
--- a/arch/x86/kernel/alternative.c
+++ b/arch/x86/kernel/alternative.c
@@ -12,6 +12,7 @@
 #include <linux/slab.h>
 #include <linux/kdebug.h>
 #include <linux/kprobes.h>
+#include <linux/mmu_context.h>
 #include <asm/text-patching.h>
 #include <asm/alternative.h>
 #include <asm/sections.h>
@@ -264,7 +265,7 @@ static void __init_or_module add_nops(void *insns, unsigned int len)
 
 extern struct alt_instr __alt_instructions[], __alt_instructions_end[];
 extern s32 __smp_locks[], __smp_locks_end[];
-void *text_poke_early(void *addr, const void *opcode, size_t len);
+void text_poke_early(void *addr, const void *opcode, size_t len);
 
 /*
  * Are we looking at a near JMP with a 1 or 4-byte displacement.
@@ -666,16 +667,136 @@ void __init alternative_instructions(void)
  * instructions. And on the local CPU you need to be protected again NMI or MCE
  * handlers seeing an inconsistent instruction while you patch.
  */
-void *__init_or_module text_poke_early(void *addr, const void *opcode,
-					      size_t len)
+void __init_or_module text_poke_early(void *addr, const void *opcode,
+				      size_t len)
 {
 	unsigned long flags;
+
+	if (boot_cpu_has(X86_FEATURE_NX) &&
+	    is_module_text_address((unsigned long)addr)) {
+		/*
+		 * Modules text is marked initially as non-executable, so the
+		 * code cannot be running and speculative code-fetches are
+		 * prevented. Just change the code.
+		 */
+		memcpy(addr, opcode, len);
+	} else {
+		local_irq_save(flags);
+		memcpy(addr, opcode, len);
+		local_irq_restore(flags);
+		sync_core();
+
+		/*
+		 * Could also do a CLFLUSH here to speed up CPU recovery; but
+		 * that causes hangs on some VIA CPUs.
+		 */
+	}
+}
+
+__ro_after_init struct mm_struct *poking_mm;
+__ro_after_init unsigned long poking_addr;
+
+static void *__text_poke(void *addr, const void *opcode, size_t len)
+{
+	bool cross_page_boundary = offset_in_page(addr) + len > PAGE_SIZE;
+	struct page *pages[2] = {NULL};
+	temp_mm_state_t prev;
+	unsigned long flags;
+	pte_t pte, *ptep;
+	spinlock_t *ptl;
+	pgprot_t pgprot;
+
+	/*
+	 * While boot memory allocator is running we cannot use struct pages as
+	 * they are not yet initialized. There is no way to recover.
+	 */
+	BUG_ON(!after_bootmem);
+
+	if (!core_kernel_text((unsigned long)addr)) {
+		pages[0] = vmalloc_to_page(addr);
+		if (cross_page_boundary)
+			pages[1] = vmalloc_to_page(addr + PAGE_SIZE);
+	} else {
+		pages[0] = virt_to_page(addr);
+		WARN_ON(!PageReserved(pages[0]));
+		if (cross_page_boundary)
+			pages[1] = virt_to_page(addr + PAGE_SIZE);
+	}
+	/*
+	 * If something went wrong, crash and burn since recovery paths are not
+	 * implemented.
+	 */
+	BUG_ON(!pages[0] || (cross_page_boundary && !pages[1]));
+
 	local_irq_save(flags);
-	memcpy(addr, opcode, len);
+
+	/*
+	 * Map the page without the global bit, as TLB flushing is done with
+	 * flush_tlb_mm_range(), which is intended for non-global PTEs.
+	 */
+	pgprot = __pgprot(pgprot_val(PAGE_KERNEL) & ~_PAGE_GLOBAL);
+
+	/*
+	 * The lock is not really needed, but this allows to avoid open-coding.
+	 */
+	ptep = get_locked_pte(poking_mm, poking_addr, &ptl);
+
+	/*
+	 * This must not fail; preallocated in poking_init().
+	 */
+	VM_BUG_ON(!ptep);
+
+	pte = mk_pte(pages[0], pgprot);
+	set_pte_at(poking_mm, poking_addr, ptep, pte);
+
+	if (cross_page_boundary) {
+		pte = mk_pte(pages[1], pgprot);
+		set_pte_at(poking_mm, poking_addr + PAGE_SIZE, ptep + 1, pte);
+	}
+
+	/*
+	 * Loading the temporary mm behaves as a compiler barrier, which
+	 * guarantees that the PTE will be set at the time memcpy() is done.
+	 */
+	prev = use_temporary_mm(poking_mm);
+
+	kasan_disable_current();
+	memcpy((u8 *)poking_addr + offset_in_page(addr), opcode, len);
+	kasan_enable_current();
+
+	/*
+	 * Ensure that the PTE is only cleared after the instructions of memcpy
+	 * were issued by using a compiler barrier.
+	 */
+	barrier();
+
+	pte_clear(poking_mm, poking_addr, ptep);
+	if (cross_page_boundary)
+		pte_clear(poking_mm, poking_addr + PAGE_SIZE, ptep + 1);
+
+	/*
+	 * Loading the previous page-table hierarchy requires a serializing
+	 * instruction that already allows the core to see the updated version.
+	 * Xen-PV is assumed to serialize execution in a similar manner.
+	 */
+	unuse_temporary_mm(prev);
+
+	/*
+	 * Flushing the TLB might involve IPIs, which would require enabled
+	 * IRQs, but not if the mm is not used, as it is in this point.
+	 */
+	flush_tlb_mm_range(poking_mm, poking_addr, poking_addr +
+			   (cross_page_boundary ? 2 : 1) * PAGE_SIZE,
+			   PAGE_SHIFT, false);
+
+	/*
+	 * If the text does not match what we just wrote then something is
+	 * fundamentally screwy; there's nothing we can really do about that.
+	 */
+	BUG_ON(memcmp(addr, opcode, len));
+
+	pte_unmap_unlock(ptep, ptl);
 	local_irq_restore(flags);
-	sync_core();
-	/* Could also do a CLFLUSH here to speed up CPU recovery; but
-	   that causes hangs on some VIA CPUs. */
 	return addr;
 }
 
@@ -689,48 +810,36 @@ void *__init_or_module text_poke_early(void *addr, const void *opcode,
  * It means the size must be writable atomically and the address must be aligned
  * in a way that permits an atomic write. It also makes sure we fit on a single
  * page.
+ *
+ * Note that the caller must ensure that if the modified code is part of a
+ * module, the module would not be removed during poking. This can be achieved
+ * by registering a module notifier, and ordering module removal and patching
+ * trough a mutex.
  */
 void *text_poke(void *addr, const void *opcode, size_t len)
 {
-	unsigned long flags;
-	char *vaddr;
-	struct page *pages[2];
-	int i;
-
-	/*
-	 * While boot memory allocator is runnig we cannot use struct
-	 * pages as they are not yet initialized.
-	 */
-	BUG_ON(!after_bootmem);
-
 	lockdep_assert_held(&text_mutex);
 
-	if (!core_kernel_text((unsigned long)addr)) {
-		pages[0] = vmalloc_to_page(addr);
-		pages[1] = vmalloc_to_page(addr + PAGE_SIZE);
-	} else {
-		pages[0] = virt_to_page(addr);
-		WARN_ON(!PageReserved(pages[0]));
-		pages[1] = virt_to_page(addr + PAGE_SIZE);
-	}
-	BUG_ON(!pages[0]);
-	local_irq_save(flags);
-	set_fixmap(FIX_TEXT_POKE0, page_to_phys(pages[0]));
-	if (pages[1])
-		set_fixmap(FIX_TEXT_POKE1, page_to_phys(pages[1]));
-	vaddr = (char *)fix_to_virt(FIX_TEXT_POKE0);
-	memcpy(&vaddr[(unsigned long)addr & ~PAGE_MASK], opcode, len);
-	clear_fixmap(FIX_TEXT_POKE0);
-	if (pages[1])
-		clear_fixmap(FIX_TEXT_POKE1);
-	local_flush_tlb();
-	sync_core();
-	/* Could also do a CLFLUSH here to speed up CPU recovery; but
-	   that causes hangs on some VIA CPUs. */
-	for (i = 0; i < len; i++)
-		BUG_ON(((char *)addr)[i] != ((char *)opcode)[i]);
-	local_irq_restore(flags);
-	return addr;
+	return __text_poke(addr, opcode, len);
+}
+
+/**
+ * text_poke_kgdb - Update instructions on a live kernel by kgdb
+ * @addr: address to modify
+ * @opcode: source of the copy
+ * @len: length to copy
+ *
+ * Only atomic text poke/set should be allowed when not doing early patching.
+ * It means the size must be writable atomically and the address must be aligned
+ * in a way that permits an atomic write. It also makes sure we fit on a single
+ * page.
+ *
+ * Context: should only be used by kgdb, which ensures no other core is running,
+ *	    despite the fact it does not hold the text_mutex.
+ */
+void *text_poke_kgdb(void *addr, const void *opcode, size_t len)
+{
+	return __text_poke(addr, opcode, len);
 }
 
 static void do_sync_core(void *info)
@@ -788,7 +897,7 @@ NOKPROBE_SYMBOL(poke_int3_handler);
  *	  replacing opcode
  *	- sync cores
  */
-void *text_poke_bp(void *addr, const void *opcode, size_t len, void *handler)
+void text_poke_bp(void *addr, const void *opcode, size_t len, void *handler)
 {
 	unsigned char int3 = 0xcc;
 
@@ -830,7 +939,5 @@ void *text_poke_bp(void *addr, const void *opcode, size_t len, void *handler)
 	 * the writing of the new instruction.
 	 */
 	bp_patching_in_progress = false;
-
-	return addr;
 }
 
diff --git a/arch/x86/kernel/apic/apic.c b/arch/x86/kernel/apic/apic.c
index b7bcdd781651..ab6af775f06c 100644
--- a/arch/x86/kernel/apic/apic.c
+++ b/arch/x86/kernel/apic/apic.c
@@ -802,6 +802,24 @@ calibrate_by_pmtimer(long deltapm, long *delta, long *deltatsc)
 	return 0;
 }
 
+static int __init lapic_init_clockevent(void)
+{
+	if (!lapic_timer_frequency)
+		return -1;
+
+	/* Calculate the scaled math multiplication factor */
+	lapic_clockevent.mult = div_sc(lapic_timer_frequency/APIC_DIVISOR,
+					TICK_NSEC, lapic_clockevent.shift);
+	lapic_clockevent.max_delta_ns =
+		clockevent_delta2ns(0x7FFFFFFF, &lapic_clockevent);
+	lapic_clockevent.max_delta_ticks = 0x7FFFFFFF;
+	lapic_clockevent.min_delta_ns =
+		clockevent_delta2ns(0xF, &lapic_clockevent);
+	lapic_clockevent.min_delta_ticks = 0xF;
+
+	return 0;
+}
+
 static int __init calibrate_APIC_clock(void)
 {
 	struct clock_event_device *levt = this_cpu_ptr(&lapic_events);
@@ -810,25 +828,21 @@ static int __init calibrate_APIC_clock(void)
 	long delta, deltatsc;
 	int pm_referenced = 0;
 
-	/**
-	 * check if lapic timer has already been calibrated by platform
-	 * specific routine, such as tsc calibration code. if so, we just fill
+	if (boot_cpu_has(X86_FEATURE_TSC_DEADLINE_TIMER))
+		return 0;
+
+	/*
+	 * Check if lapic timer has already been calibrated by platform
+	 * specific routine, such as tsc calibration code. If so just fill
 	 * in the clockevent structure and return.
 	 */
-
-	if (boot_cpu_has(X86_FEATURE_TSC_DEADLINE_TIMER)) {
-		return 0;
-	} else if (lapic_timer_frequency) {
+	if (!lapic_init_clockevent()) {
 		apic_printk(APIC_VERBOSE, "lapic timer already calibrated %d\n",
-				lapic_timer_frequency);
-		lapic_clockevent.mult = div_sc(lapic_timer_frequency/APIC_DIVISOR,
-					TICK_NSEC, lapic_clockevent.shift);
-		lapic_clockevent.max_delta_ns =
-			clockevent_delta2ns(0x7FFFFF, &lapic_clockevent);
-		lapic_clockevent.max_delta_ticks = 0x7FFFFF;
-		lapic_clockevent.min_delta_ns =
-			clockevent_delta2ns(0xF, &lapic_clockevent);
-		lapic_clockevent.min_delta_ticks = 0xF;
+			    lapic_timer_frequency);
+		/*
+		 * Direct calibration methods must have an always running
+		 * local APIC timer, no need for broadcast timer.
+		 */
 		lapic_clockevent.features &= ~CLOCK_EVT_FEAT_DUMMY;
 		return 0;
 	}
@@ -869,17 +883,8 @@ static int __init calibrate_APIC_clock(void)
 	pm_referenced = !calibrate_by_pmtimer(lapic_cal_pm2 - lapic_cal_pm1,
 					&delta, &deltatsc);
 
-	/* Calculate the scaled math multiplication factor */
-	lapic_clockevent.mult = div_sc(delta, TICK_NSEC * LAPIC_CAL_LOOPS,
-				       lapic_clockevent.shift);
-	lapic_clockevent.max_delta_ns =
-		clockevent_delta2ns(0x7FFFFFFF, &lapic_clockevent);
-	lapic_clockevent.max_delta_ticks = 0x7FFFFFFF;
-	lapic_clockevent.min_delta_ns =
-		clockevent_delta2ns(0xF, &lapic_clockevent);
-	lapic_clockevent.min_delta_ticks = 0xF;
-
 	lapic_timer_frequency = (delta * APIC_DIVISOR) / LAPIC_CAL_LOOPS;
+	lapic_init_clockevent();
 
 	apic_printk(APIC_VERBOSE, "..... delta %ld\n", delta);
 	apic_printk(APIC_VERBOSE, "..... mult: %u\n", lapic_clockevent.mult);
diff --git a/arch/x86/kernel/apic/apic_numachip.c b/arch/x86/kernel/apic/apic_numachip.c
index 78778b54f904..a5464b8b6c46 100644
--- a/arch/x86/kernel/apic/apic_numachip.c
+++ b/arch/x86/kernel/apic/apic_numachip.c
@@ -175,7 +175,7 @@ static void fixup_cpu_id(struct cpuinfo_x86 *c, int node)
 	this_cpu_write(cpu_llc_id, node);
 
 	/* Account for nodes per socket in multi-core-module processors */
-	if (static_cpu_has(X86_FEATURE_NODEID_MSR)) {
+	if (boot_cpu_has(X86_FEATURE_NODEID_MSR)) {
 		rdmsrl(MSR_FAM10H_NODE_ID, val);
 		nodes = ((val >> 3) & 7) + 1;
 	}
diff --git a/arch/x86/kernel/asm-offsets_64.c b/arch/x86/kernel/asm-offsets_64.c
index ddced33184b5..d3d075226c0a 100644
--- a/arch/x86/kernel/asm-offsets_64.c
+++ b/arch/x86/kernel/asm-offsets_64.c
@@ -68,10 +68,12 @@ int main(void)
 #undef ENTRY
 
 	OFFSET(TSS_ist, tss_struct, x86_tss.ist);
+	DEFINE(DB_STACK_OFFSET, offsetof(struct cea_exception_stacks, DB_stack) -
+	       offsetof(struct cea_exception_stacks, DB1_stack));
 	BLANK();
 
 #ifdef CONFIG_STACKPROTECTOR
-	DEFINE(stack_canary_offset, offsetof(union irq_stack_union, stack_canary));
+	DEFINE(stack_canary_offset, offsetof(struct fixed_percpu_data, stack_canary));
 	BLANK();
 #endif
 
diff --git a/arch/x86/kernel/cpu/Makefile b/arch/x86/kernel/cpu/Makefile
index cfd24f9f7614..1796d2bdcaaa 100644
--- a/arch/x86/kernel/cpu/Makefile
+++ b/arch/x86/kernel/cpu/Makefile
@@ -28,7 +28,7 @@ obj-y			+= cpuid-deps.o
 obj-$(CONFIG_PROC_FS)	+= proc.o
 obj-$(CONFIG_X86_FEATURE_NAMES) += capflags.o powerflags.o
 
-obj-$(CONFIG_CPU_SUP_INTEL)		+= intel.o intel_pconfig.o
+obj-$(CONFIG_CPU_SUP_INTEL)		+= intel.o intel_pconfig.o intel_epb.o
 obj-$(CONFIG_CPU_SUP_AMD)		+= amd.o
 obj-$(CONFIG_CPU_SUP_HYGON)		+= hygon.o
 obj-$(CONFIG_CPU_SUP_CYRIX_32)		+= cyrix.o
diff --git a/arch/x86/kernel/cpu/amd.c b/arch/x86/kernel/cpu/amd.c
index 01004bfb1a1b..fb6a64bd765f 100644
--- a/arch/x86/kernel/cpu/amd.c
+++ b/arch/x86/kernel/cpu/amd.c
@@ -82,11 +82,14 @@ static inline int wrmsrl_amd_safe(unsigned msr, unsigned long long val)
  *	performance at the same time..
  */
 
+#ifdef CONFIG_X86_32
 extern __visible void vide(void);
-__asm__(".globl vide\n"
+__asm__(".text\n"
+	".globl vide\n"
 	".type vide, @function\n"
 	".align 4\n"
 	"vide: ret\n");
+#endif
 
 static void init_amd_k5(struct cpuinfo_x86 *c)
 {
diff --git a/arch/x86/kernel/cpu/aperfmperf.c b/arch/x86/kernel/cpu/aperfmperf.c
index 804c49493938..64d5aec24203 100644
--- a/arch/x86/kernel/cpu/aperfmperf.c
+++ b/arch/x86/kernel/cpu/aperfmperf.c
@@ -83,7 +83,7 @@ unsigned int aperfmperf_get_khz(int cpu)
 	if (!cpu_khz)
 		return 0;
 
-	if (!static_cpu_has(X86_FEATURE_APERFMPERF))
+	if (!boot_cpu_has(X86_FEATURE_APERFMPERF))
 		return 0;
 
 	aperfmperf_snapshot_cpu(cpu, ktime_get(), true);
@@ -99,7 +99,7 @@ void arch_freq_prepare_all(void)
 	if (!cpu_khz)
 		return;
 
-	if (!static_cpu_has(X86_FEATURE_APERFMPERF))
+	if (!boot_cpu_has(X86_FEATURE_APERFMPERF))
 		return;
 
 	for_each_online_cpu(cpu)
@@ -115,7 +115,7 @@ unsigned int arch_freq_get_on_cpu(int cpu)
 	if (!cpu_khz)
 		return 0;
 
-	if (!static_cpu_has(X86_FEATURE_APERFMPERF))
+	if (!boot_cpu_has(X86_FEATURE_APERFMPERF))
 		return 0;
 
 	if (aperfmperf_snapshot_cpu(cpu, ktime_get(), true))
diff --git a/arch/x86/kernel/cpu/bugs.c b/arch/x86/kernel/cpu/bugs.c
index 2da82eff0eb4..29630393f300 100644
--- a/arch/x86/kernel/cpu/bugs.c
+++ b/arch/x86/kernel/cpu/bugs.c
@@ -275,7 +275,7 @@ static const struct {
 	const char			*option;
 	enum spectre_v2_user_cmd	cmd;
 	bool				secure;
-} v2_user_options[] __initdata = {
+} v2_user_options[] __initconst = {
 	{ "auto",		SPECTRE_V2_USER_CMD_AUTO,		false },
 	{ "off",		SPECTRE_V2_USER_CMD_NONE,		false },
 	{ "on",			SPECTRE_V2_USER_CMD_FORCE,		true  },
@@ -419,7 +419,7 @@ static const struct {
 	const char *option;
 	enum spectre_v2_mitigation_cmd cmd;
 	bool secure;
-} mitigation_options[] __initdata = {
+} mitigation_options[] __initconst = {
 	{ "off",		SPECTRE_V2_CMD_NONE,		  false },
 	{ "on",			SPECTRE_V2_CMD_FORCE,		  true  },
 	{ "retpoline",		SPECTRE_V2_CMD_RETPOLINE,	  false },
@@ -440,7 +440,8 @@ static enum spectre_v2_mitigation_cmd __init spectre_v2_parse_cmdline(void)
 	char arg[20];
 	int ret, i;
 
-	if (cmdline_find_option_bool(boot_command_line, "nospectre_v2"))
+	if (cmdline_find_option_bool(boot_command_line, "nospectre_v2") ||
+	    cpu_mitigations_off())
 		return SPECTRE_V2_CMD_NONE;
 
 	ret = cmdline_find_option(boot_command_line, "spectre_v2", arg, sizeof(arg));
@@ -658,7 +659,7 @@ static const char * const ssb_strings[] = {
 static const struct {
 	const char *option;
 	enum ssb_mitigation_cmd cmd;
-} ssb_mitigation_options[]  __initdata = {
+} ssb_mitigation_options[]  __initconst = {
 	{ "auto",	SPEC_STORE_BYPASS_CMD_AUTO },    /* Platform decides */
 	{ "on",		SPEC_STORE_BYPASS_CMD_ON },      /* Disable Speculative Store Bypass */
 	{ "off",	SPEC_STORE_BYPASS_CMD_NONE },    /* Don't touch Speculative Store Bypass */
@@ -672,7 +673,8 @@ static enum ssb_mitigation_cmd __init ssb_parse_cmdline(void)
 	char arg[20];
 	int ret, i;
 
-	if (cmdline_find_option_bool(boot_command_line, "nospec_store_bypass_disable")) {
+	if (cmdline_find_option_bool(boot_command_line, "nospec_store_bypass_disable") ||
+	    cpu_mitigations_off()) {
 		return SPEC_STORE_BYPASS_CMD_NONE;
 	} else {
 		ret = cmdline_find_option(boot_command_line, "spec_store_bypass_disable",
@@ -1008,6 +1010,11 @@ static void __init l1tf_select_mitigation(void)
 	if (!boot_cpu_has_bug(X86_BUG_L1TF))
 		return;
 
+	if (cpu_mitigations_off())
+		l1tf_mitigation = L1TF_MITIGATION_OFF;
+	else if (cpu_mitigations_auto_nosmt())
+		l1tf_mitigation = L1TF_MITIGATION_FLUSH_NOSMT;
+
 	override_cache_bits(&boot_cpu_data);
 
 	switch (l1tf_mitigation) {
diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c
index cb28e98a0659..37640544e12f 100644
--- a/arch/x86/kernel/cpu/common.c
+++ b/arch/x86/kernel/cpu/common.c
@@ -507,19 +507,6 @@ void load_percpu_segment(int cpu)
 DEFINE_PER_CPU(struct cpu_entry_area *, cpu_entry_area);
 #endif
 
-#ifdef CONFIG_X86_64
-/*
- * Special IST stacks which the CPU switches to when it calls
- * an IST-marked descriptor entry. Up to 7 stacks (hardware
- * limit), all of them are 4K, except the debug stack which
- * is 8K.
- */
-static const unsigned int exception_stack_sizes[N_EXCEPTION_STACKS] = {
-	  [0 ... N_EXCEPTION_STACKS - 1]	= EXCEPTION_STKSZ,
-	  [DEBUG_STACK - 1]			= DEBUG_STKSZ
-};
-#endif
-
 /* Load the original GDT from the per-cpu structure */
 void load_direct_gdt(int cpu)
 {
@@ -1511,9 +1498,9 @@ static __init int setup_clearcpuid(char *arg)
 __setup("clearcpuid=", setup_clearcpuid);
 
 #ifdef CONFIG_X86_64
-DEFINE_PER_CPU_FIRST(union irq_stack_union,
-		     irq_stack_union) __aligned(PAGE_SIZE) __visible;
-EXPORT_PER_CPU_SYMBOL_GPL(irq_stack_union);
+DEFINE_PER_CPU_FIRST(struct fixed_percpu_data,
+		     fixed_percpu_data) __aligned(PAGE_SIZE) __visible;
+EXPORT_PER_CPU_SYMBOL_GPL(fixed_percpu_data);
 
 /*
  * The following percpu variables are hot.  Align current_task to
@@ -1523,9 +1510,7 @@ DEFINE_PER_CPU(struct task_struct *, current_task) ____cacheline_aligned =
 	&init_task;
 EXPORT_PER_CPU_SYMBOL(current_task);
 
-DEFINE_PER_CPU(char *, irq_stack_ptr) =
-	init_per_cpu_var(irq_stack_union.irq_stack) + IRQ_STACK_SIZE;
-
+DEFINE_PER_CPU(struct irq_stack *, hardirq_stack_ptr);
 DEFINE_PER_CPU(unsigned int, irq_count) __visible = -1;
 
 DEFINE_PER_CPU(int, __preempt_count) = INIT_PREEMPT_COUNT;
@@ -1562,23 +1547,7 @@ void syscall_init(void)
 	       X86_EFLAGS_IOPL|X86_EFLAGS_AC|X86_EFLAGS_NT);
 }
 
-/*
- * Copies of the original ist values from the tss are only accessed during
- * debugging, no special alignment required.
- */
-DEFINE_PER_CPU(struct orig_ist, orig_ist);
-
-static DEFINE_PER_CPU(unsigned long, debug_stack_addr);
 DEFINE_PER_CPU(int, debug_stack_usage);
-
-int is_debug_stack(unsigned long addr)
-{
-	return __this_cpu_read(debug_stack_usage) ||
-		(addr <= __this_cpu_read(debug_stack_addr) &&
-		 addr > (__this_cpu_read(debug_stack_addr) - DEBUG_STKSZ));
-}
-NOKPROBE_SYMBOL(is_debug_stack);
-
 DEFINE_PER_CPU(u32, debug_idt_ctr);
 
 void debug_stack_set_zero(void)
@@ -1668,7 +1637,7 @@ static void setup_getcpu(int cpu)
 	unsigned long cpudata = vdso_encode_cpunode(cpu, early_cpu_to_node(cpu));
 	struct desc_struct d = { };
 
-	if (static_cpu_has(X86_FEATURE_RDTSCP))
+	if (boot_cpu_has(X86_FEATURE_RDTSCP))
 		write_rdtscp_aux(cpudata);
 
 	/* Store CPU and node number in limit. */
@@ -1690,17 +1659,14 @@ static void setup_getcpu(int cpu)
  * initialized (naturally) in the bootstrap process, such as the GDT
  * and IDT. We reload them nevertheless, this function acts as a
  * 'CPU state barrier', nothing should get across.
- * A lot of state is already set up in PDA init for 64 bit
  */
 #ifdef CONFIG_X86_64
 
 void cpu_init(void)
 {
-	struct orig_ist *oist;
+	int cpu = raw_smp_processor_id();
 	struct task_struct *me;
 	struct tss_struct *t;
-	unsigned long v;
-	int cpu = raw_smp_processor_id();
 	int i;
 
 	wait_for_master_cpu(cpu);
@@ -1715,7 +1681,6 @@ void cpu_init(void)
 		load_ucode_ap();
 
 	t = &per_cpu(cpu_tss_rw, cpu);
-	oist = &per_cpu(orig_ist, cpu);
 
 #ifdef CONFIG_NUMA
 	if (this_cpu_read(numa_node) == 0 &&
@@ -1753,16 +1718,11 @@ void cpu_init(void)
 	/*
 	 * set up and load the per-CPU TSS
 	 */
-	if (!oist->ist[0]) {
-		char *estacks = get_cpu_entry_area(cpu)->exception_stacks;
-
-		for (v = 0; v < N_EXCEPTION_STACKS; v++) {
-			estacks += exception_stack_sizes[v];
-			oist->ist[v] = t->x86_tss.ist[v] =
-					(unsigned long)estacks;
-			if (v == DEBUG_STACK-1)
-				per_cpu(debug_stack_addr, cpu) = (unsigned long)estacks;
-		}
+	if (!t->x86_tss.ist[0]) {
+		t->x86_tss.ist[IST_INDEX_DF] = __this_cpu_ist_top_va(DF);
+		t->x86_tss.ist[IST_INDEX_NMI] = __this_cpu_ist_top_va(NMI);
+		t->x86_tss.ist[IST_INDEX_DB] = __this_cpu_ist_top_va(DB);
+		t->x86_tss.ist[IST_INDEX_MCE] = __this_cpu_ist_top_va(MCE);
 	}
 
 	t->x86_tss.io_bitmap_base = IO_BITMAP_OFFSET;
@@ -1864,23 +1824,6 @@ void cpu_init(void)
 }
 #endif
 
-static void bsp_resume(void)
-{
-	if (this_cpu->c_bsp_resume)
-		this_cpu->c_bsp_resume(&boot_cpu_data);
-}
-
-static struct syscore_ops cpu_syscore_ops = {
-	.resume		= bsp_resume,
-};
-
-static int __init init_cpu_syscore(void)
-{
-	register_syscore_ops(&cpu_syscore_ops);
-	return 0;
-}
-core_initcall(init_cpu_syscore);
-
 /*
  * The microcode loader calls this upon late microcode load to recheck features,
  * only when microcode has been updated. Caller holds microcode_mutex and CPU
diff --git a/arch/x86/kernel/cpu/cpu.h b/arch/x86/kernel/cpu/cpu.h
index 5eb946b9a9f3..c0e2407abdd6 100644
--- a/arch/x86/kernel/cpu/cpu.h
+++ b/arch/x86/kernel/cpu/cpu.h
@@ -14,7 +14,6 @@ struct cpu_dev {
 	void		(*c_init)(struct cpuinfo_x86 *);
 	void		(*c_identify)(struct cpuinfo_x86 *);
 	void		(*c_detect_tlb)(struct cpuinfo_x86 *);
-	void		(*c_bsp_resume)(struct cpuinfo_x86 *);
 	int		c_x86_vendor;
 #ifdef CONFIG_X86_32
 	/* Optional vendor specific routine to obtain the cache size. */
diff --git a/arch/x86/kernel/cpu/hygon.c b/arch/x86/kernel/cpu/hygon.c
index cf25405444ab..415621ddb8a2 100644
--- a/arch/x86/kernel/cpu/hygon.c
+++ b/arch/x86/kernel/cpu/hygon.c
@@ -19,6 +19,8 @@
 
 #include "cpu.h"
 
+#define APICID_SOCKET_ID_BIT 6
+
 /*
  * nodes_per_socket: Stores the number of nodes per socket.
  * Refer to CPUID Fn8000_001E_ECX Node Identifiers[10:8]
@@ -87,6 +89,9 @@ static void hygon_get_topology(struct cpuinfo_x86 *c)
 		if (!err)
 			c->x86_coreid_bits = get_count_order(c->x86_max_cores);
 
+		/* Socket ID is ApicId[6] for these processors. */
+		c->phys_proc_id = c->apicid >> APICID_SOCKET_ID_BIT;
+
 		cacheinfo_hygon_init_llc_id(c, cpu, node_id);
 	} else if (cpu_has(c, X86_FEATURE_NODEID_MSR)) {
 		u64 value;
diff --git a/arch/x86/kernel/cpu/intel.c b/arch/x86/kernel/cpu/intel.c
index fc3c07fe7df5..f17c1a714779 100644
--- a/arch/x86/kernel/cpu/intel.c
+++ b/arch/x86/kernel/cpu/intel.c
@@ -596,36 +596,6 @@ detect_keyid_bits:
 	c->x86_phys_bits -= keyid_bits;
 }
 
-static void init_intel_energy_perf(struct cpuinfo_x86 *c)
-{
-	u64 epb;
-
-	/*
-	 * Initialize MSR_IA32_ENERGY_PERF_BIAS if not already initialized.
-	 * (x86_energy_perf_policy(8) is available to change it at run-time.)
-	 */
-	if (!cpu_has(c, X86_FEATURE_EPB))
-		return;
-
-	rdmsrl(MSR_IA32_ENERGY_PERF_BIAS, epb);
-	if ((epb & 0xF) != ENERGY_PERF_BIAS_PERFORMANCE)
-		return;
-
-	pr_warn_once("ENERGY_PERF_BIAS: Set to 'normal', was 'performance'\n");
-	pr_warn_once("ENERGY_PERF_BIAS: View and update with x86_energy_perf_policy(8)\n");
-	epb = (epb & ~0xF) | ENERGY_PERF_BIAS_NORMAL;
-	wrmsrl(MSR_IA32_ENERGY_PERF_BIAS, epb);
-}
-
-static void intel_bsp_resume(struct cpuinfo_x86 *c)
-{
-	/*
-	 * MSR_IA32_ENERGY_PERF_BIAS is lost across suspend/resume,
-	 * so reinitialize it properly like during bootup:
-	 */
-	init_intel_energy_perf(c);
-}
-
 static void init_cpuid_fault(struct cpuinfo_x86 *c)
 {
 	u64 msr;
@@ -763,8 +733,6 @@ static void init_intel(struct cpuinfo_x86 *c)
 	if (cpu_has(c, X86_FEATURE_TME))
 		detect_tme(c);
 
-	init_intel_energy_perf(c);
-
 	init_intel_misc_features(c);
 }
 
@@ -1023,9 +991,7 @@ static const struct cpu_dev intel_cpu_dev = {
 	.c_detect_tlb	= intel_detect_tlb,
 	.c_early_init   = early_init_intel,
 	.c_init		= init_intel,
-	.c_bsp_resume	= intel_bsp_resume,
 	.c_x86_vendor	= X86_VENDOR_INTEL,
 };
 
 cpu_dev_register(intel_cpu_dev);
-
diff --git a/arch/x86/kernel/cpu/intel_epb.c b/arch/x86/kernel/cpu/intel_epb.c
new file mode 100644
index 000000000000..f4dd73396f28
--- /dev/null
+++ b/arch/x86/kernel/cpu/intel_epb.c
@@ -0,0 +1,216 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Intel Performance and Energy Bias Hint support.
+ *
+ * Copyright (C) 2019 Intel Corporation
+ *
+ * Author:
+ *	Rafael J. Wysocki <rafael.j.wysocki@intel.com>
+ */
+
+#include <linux/cpuhotplug.h>
+#include <linux/cpu.h>
+#include <linux/device.h>
+#include <linux/kernel.h>
+#include <linux/string.h>
+#include <linux/syscore_ops.h>
+#include <linux/pm.h>
+
+#include <asm/cpufeature.h>
+#include <asm/msr.h>
+
+/**
+ * DOC: overview
+ *
+ * The Performance and Energy Bias Hint (EPB) allows software to specify its
+ * preference with respect to the power-performance tradeoffs present in the
+ * processor.  Generally, the EPB is expected to be set by user space (directly
+ * via sysfs or with the help of the x86_energy_perf_policy tool), but there are
+ * two reasons for the kernel to update it.
+ *
+ * First, there are systems where the platform firmware resets the EPB during
+ * system-wide transitions from sleep states back into the working state
+ * effectively causing the previous EPB updates by user space to be lost.
+ * Thus the kernel needs to save the current EPB values for all CPUs during
+ * system-wide transitions to sleep states and restore them on the way back to
+ * the working state.  That can be achieved by saving EPB for secondary CPUs
+ * when they are taken offline during transitions into system sleep states and
+ * for the boot CPU in a syscore suspend operation, so that it can be restored
+ * for the boot CPU in a syscore resume operation and for the other CPUs when
+ * they are brought back online.  However, CPUs that are already offline when
+ * a system-wide PM transition is started are not taken offline again, but their
+ * EPB values may still be reset by the platform firmware during the transition,
+ * so in fact it is necessary to save the EPB of any CPU taken offline and to
+ * restore it when the given CPU goes back online at all times.
+ *
+ * Second, on many systems the initial EPB value coming from the platform
+ * firmware is 0 ('performance') and at least on some of them that is because
+ * the platform firmware does not initialize EPB at all with the assumption that
+ * the OS will do that anyway.  That sometimes is problematic, as it may cause
+ * the system battery to drain too fast, for example, so it is better to adjust
+ * it on CPU bring-up and if the initial EPB value for a given CPU is 0, the
+ * kernel changes it to 6 ('normal').
+ */
+
+static DEFINE_PER_CPU(u8, saved_epb);
+
+#define EPB_MASK	0x0fULL
+#define EPB_SAVED	0x10ULL
+#define MAX_EPB		EPB_MASK
+
+static int intel_epb_save(void)
+{
+	u64 epb;
+
+	rdmsrl(MSR_IA32_ENERGY_PERF_BIAS, epb);
+	/*
+	 * Ensure that saved_epb will always be nonzero after this write even if
+	 * the EPB value read from the MSR is 0.
+	 */
+	this_cpu_write(saved_epb, (epb & EPB_MASK) | EPB_SAVED);
+
+	return 0;
+}
+
+static void intel_epb_restore(void)
+{
+	u64 val = this_cpu_read(saved_epb);
+	u64 epb;
+
+	rdmsrl(MSR_IA32_ENERGY_PERF_BIAS, epb);
+	if (val) {
+		val &= EPB_MASK;
+	} else {
+		/*
+		 * Because intel_epb_save() has not run for the current CPU yet,
+		 * it is going online for the first time, so if its EPB value is
+		 * 0 ('performance') at this point, assume that it has not been
+		 * initialized by the platform firmware and set it to 6
+		 * ('normal').
+		 */
+		val = epb & EPB_MASK;
+		if (val == ENERGY_PERF_BIAS_PERFORMANCE) {
+			val = ENERGY_PERF_BIAS_NORMAL;
+			pr_warn_once("ENERGY_PERF_BIAS: Set to 'normal', was 'performance'\n");
+		}
+	}
+	wrmsrl(MSR_IA32_ENERGY_PERF_BIAS, (epb & ~EPB_MASK) | val);
+}
+
+static struct syscore_ops intel_epb_syscore_ops = {
+	.suspend = intel_epb_save,
+	.resume = intel_epb_restore,
+};
+
+static const char * const energy_perf_strings[] = {
+	"performance",
+	"balance-performance",
+	"normal",
+	"balance-power",
+	"power"
+};
+static const u8 energ_perf_values[] = {
+	ENERGY_PERF_BIAS_PERFORMANCE,
+	ENERGY_PERF_BIAS_BALANCE_PERFORMANCE,
+	ENERGY_PERF_BIAS_NORMAL,
+	ENERGY_PERF_BIAS_BALANCE_POWERSAVE,
+	ENERGY_PERF_BIAS_POWERSAVE
+};
+
+static ssize_t energy_perf_bias_show(struct device *dev,
+				     struct device_attribute *attr,
+				     char *buf)
+{
+	unsigned int cpu = dev->id;
+	u64 epb;
+	int ret;
+
+	ret = rdmsrl_on_cpu(cpu, MSR_IA32_ENERGY_PERF_BIAS, &epb);
+	if (ret < 0)
+		return ret;
+
+	return sprintf(buf, "%llu\n", epb);
+}
+
+static ssize_t energy_perf_bias_store(struct device *dev,
+				      struct device_attribute *attr,
+				      const char *buf, size_t count)
+{
+	unsigned int cpu = dev->id;
+	u64 epb, val;
+	int ret;
+
+	ret = __sysfs_match_string(energy_perf_strings,
+				   ARRAY_SIZE(energy_perf_strings), buf);
+	if (ret >= 0)
+		val = energ_perf_values[ret];
+	else if (kstrtou64(buf, 0, &val) || val > MAX_EPB)
+		return -EINVAL;
+
+	ret = rdmsrl_on_cpu(cpu, MSR_IA32_ENERGY_PERF_BIAS, &epb);
+	if (ret < 0)
+		return ret;
+
+	ret = wrmsrl_on_cpu(cpu, MSR_IA32_ENERGY_PERF_BIAS,
+			    (epb & ~EPB_MASK) | val);
+	if (ret < 0)
+		return ret;
+
+	return count;
+}
+
+static DEVICE_ATTR_RW(energy_perf_bias);
+
+static struct attribute *intel_epb_attrs[] = {
+	&dev_attr_energy_perf_bias.attr,
+	NULL
+};
+
+static const struct attribute_group intel_epb_attr_group = {
+	.name = power_group_name,
+	.attrs =  intel_epb_attrs
+};
+
+static int intel_epb_online(unsigned int cpu)
+{
+	struct device *cpu_dev = get_cpu_device(cpu);
+
+	intel_epb_restore();
+	if (!cpuhp_tasks_frozen)
+		sysfs_merge_group(&cpu_dev->kobj, &intel_epb_attr_group);
+
+	return 0;
+}
+
+static int intel_epb_offline(unsigned int cpu)
+{
+	struct device *cpu_dev = get_cpu_device(cpu);
+
+	if (!cpuhp_tasks_frozen)
+		sysfs_unmerge_group(&cpu_dev->kobj, &intel_epb_attr_group);
+
+	intel_epb_save();
+	return 0;
+}
+
+static __init int intel_epb_init(void)
+{
+	int ret;
+
+	if (!boot_cpu_has(X86_FEATURE_EPB))
+		return -ENODEV;
+
+	ret = cpuhp_setup_state(CPUHP_AP_X86_INTEL_EPB_ONLINE,
+				"x86/intel/epb:online", intel_epb_online,
+				intel_epb_offline);
+	if (ret < 0)
+		goto err_out_online;
+
+	register_syscore_ops(&intel_epb_syscore_ops);
+	return 0;
+
+err_out_online:
+	cpuhp_remove_state(CPUHP_AP_X86_INTEL_EPB_ONLINE);
+	return ret;
+}
+subsys_initcall(intel_epb_init);
diff --git a/arch/x86/kernel/cpu/mce/amd.c b/arch/x86/kernel/cpu/mce/amd.c
index e64de5149e50..d904aafe6409 100644
--- a/arch/x86/kernel/cpu/mce/amd.c
+++ b/arch/x86/kernel/cpu/mce/amd.c
@@ -563,33 +563,59 @@ out:
 	return offset;
 }
 
+bool amd_filter_mce(struct mce *m)
+{
+	enum smca_bank_types bank_type = smca_get_bank_type(m->bank);
+	struct cpuinfo_x86 *c = &boot_cpu_data;
+	u8 xec = (m->status >> 16) & 0x3F;
+
+	/* See Family 17h Models 10h-2Fh Erratum #1114. */
+	if (c->x86 == 0x17 &&
+	    c->x86_model >= 0x10 && c->x86_model <= 0x2F &&
+	    bank_type == SMCA_IF && xec == 10)
+		return true;
+
+	return false;
+}
+
 /*
- * Turn off MC4_MISC thresholding banks on all family 0x15 models since
- * they're not supported there.
+ * Turn off thresholding banks for the following conditions:
+ * - MC4_MISC thresholding is not supported on Family 0x15.
+ * - Prevent possible spurious interrupts from the IF bank on Family 0x17
+ *   Models 0x10-0x2F due to Erratum #1114.
  */
-void disable_err_thresholding(struct cpuinfo_x86 *c)
+void disable_err_thresholding(struct cpuinfo_x86 *c, unsigned int bank)
 {
-	int i;
+	int i, num_msrs;
 	u64 hwcr;
 	bool need_toggle;
-	u32 msrs[] = {
-		0x00000413, /* MC4_MISC0 */
-		0xc0000408, /* MC4_MISC1 */
-	};
+	u32 msrs[NR_BLOCKS];
+
+	if (c->x86 == 0x15 && bank == 4) {
+		msrs[0] = 0x00000413; /* MC4_MISC0 */
+		msrs[1] = 0xc0000408; /* MC4_MISC1 */
+		num_msrs = 2;
+	} else if (c->x86 == 0x17 &&
+		   (c->x86_model >= 0x10 && c->x86_model <= 0x2F)) {
 
-	if (c->x86 != 0x15)
+		if (smca_get_bank_type(bank) != SMCA_IF)
+			return;
+
+		msrs[0] = MSR_AMD64_SMCA_MCx_MISC(bank);
+		num_msrs = 1;
+	} else {
 		return;
+	}
 
 	rdmsrl(MSR_K7_HWCR, hwcr);
 
 	/* McStatusWrEn has to be set */
 	need_toggle = !(hwcr & BIT(18));
-
 	if (need_toggle)
 		wrmsrl(MSR_K7_HWCR, hwcr | BIT(18));
 
 	/* Clear CntP bit safely */
-	for (i = 0; i < ARRAY_SIZE(msrs); i++)
+	for (i = 0; i < num_msrs; i++)
 		msr_clear_bit(msrs[i], 62);
 
 	/* restore old settings */
@@ -604,12 +630,12 @@ void mce_amd_feature_init(struct cpuinfo_x86 *c)
 	unsigned int bank, block, cpu = smp_processor_id();
 	int offset = -1;
 
-	disable_err_thresholding(c);
-
 	for (bank = 0; bank < mca_cfg.banks; ++bank) {
 		if (mce_flags.smca)
 			smca_configure(bank, cpu);
 
+		disable_err_thresholding(c, bank);
+
 		for (block = 0; block < NR_BLOCKS; ++block) {
 			address = get_block_address(address, low, high, bank, block);
 			if (!address)
diff --git a/arch/x86/kernel/cpu/mce/core.c b/arch/x86/kernel/cpu/mce/core.c
index b7fb541a4873..5112a50e6486 100644
--- a/arch/x86/kernel/cpu/mce/core.c
+++ b/arch/x86/kernel/cpu/mce/core.c
@@ -460,23 +460,6 @@ static void mce_irq_work_cb(struct irq_work *entry)
 	mce_schedule_work();
 }
 
-static void mce_report_event(struct pt_regs *regs)
-{
-	if (regs->flags & (X86_VM_MASK|X86_EFLAGS_IF)) {
-		mce_notify_irq();
-		/*
-		 * Triggering the work queue here is just an insurance
-		 * policy in case the syscall exit notify handler
-		 * doesn't run soon enough or ends up running on the
-		 * wrong CPU (can happen when audit sleeps)
-		 */
-		mce_schedule_work();
-		return;
-	}
-
-	irq_work_queue(&mce_irq_work);
-}
-
 /*
  * Check if the address reported by the CPU is in a format we can parse.
  * It would be possible to add code for most other cases, but all would
@@ -712,19 +695,49 @@ bool machine_check_poll(enum mcp_flags flags, mce_banks_t *b)
 
 		barrier();
 		m.status = mce_rdmsrl(msr_ops.status(i));
+
+		/* If this entry is not valid, ignore it */
 		if (!(m.status & MCI_STATUS_VAL))
 			continue;
 
 		/*
-		 * Uncorrected or signalled events are handled by the exception
-		 * handler when it is enabled, so don't process those here.
-		 *
-		 * TBD do the same check for MCI_STATUS_EN here?
+		 * If we are logging everything (at CPU online) or this
+		 * is a corrected error, then we must log it.
 		 */
-		if (!(flags & MCP_UC) &&
-		    (m.status & (mca_cfg.ser ? MCI_STATUS_S : MCI_STATUS_UC)))
-			continue;
+		if ((flags & MCP_UC) || !(m.status & MCI_STATUS_UC))
+			goto log_it;
+
+		/*
+		 * Newer Intel systems that support software error
+		 * recovery need to make additional checks. Other
+		 * CPUs should skip over uncorrected errors, but log
+		 * everything else.
+		 */
+		if (!mca_cfg.ser) {
+			if (m.status & MCI_STATUS_UC)
+				continue;
+			goto log_it;
+		}
 
+		/* Log "not enabled" (speculative) errors */
+		if (!(m.status & MCI_STATUS_EN))
+			goto log_it;
+
+		/*
+		 * Log UCNA (SDM: 15.6.3 "UCR Error Classification")
+		 * UC == 1 && PCC == 0 && S == 0
+		 */
+		if (!(m.status & MCI_STATUS_PCC) && !(m.status & MCI_STATUS_S))
+			goto log_it;
+
+		/*
+		 * Skip anything else. Presumption is that our read of this
+		 * bank is racing with a machine check. Leave the log alone
+		 * for do_machine_check() to deal with it.
+		 */
+		continue;
+
+log_it:
 		error_seen = true;
 
 		mce_read_aux(&m, i);
@@ -1301,7 +1314,8 @@ void do_machine_check(struct pt_regs *regs, long error_code)
 		mce_panic("Fatal machine check on current CPU", &m, msg);
 
 	if (worst > 0)
-		mce_report_event(regs);
+		irq_work_queue(&mce_irq_work);
+
 	mce_wrmsrl(MSR_IA32_MCG_STATUS, 0);
 
 	sync_core();
@@ -1451,13 +1465,12 @@ EXPORT_SYMBOL_GPL(mce_notify_irq);
 static int __mcheck_cpu_mce_banks_init(void)
 {
 	int i;
-	u8 num_banks = mca_cfg.banks;
 
-	mce_banks = kcalloc(num_banks, sizeof(struct mce_bank), GFP_KERNEL);
+	mce_banks = kcalloc(MAX_NR_BANKS, sizeof(struct mce_bank), GFP_KERNEL);
 	if (!mce_banks)
 		return -ENOMEM;
 
-	for (i = 0; i < num_banks; i++) {
+	for (i = 0; i < MAX_NR_BANKS; i++) {
 		struct mce_bank *b = &mce_banks[i];
 
 		b->ctl = -1ULL;
@@ -1471,28 +1484,19 @@ static int __mcheck_cpu_mce_banks_init(void)
  */
 static int __mcheck_cpu_cap_init(void)
 {
-	unsigned b;
 	u64 cap;
+	u8 b;
 
 	rdmsrl(MSR_IA32_MCG_CAP, cap);
 
 	b = cap & MCG_BANKCNT_MASK;
-	if (!mca_cfg.banks)
-		pr_info("CPU supports %d MCE banks\n", b);
-
-	if (b > MAX_NR_BANKS) {
-		pr_warn("Using only %u machine check banks out of %u\n",
-			MAX_NR_BANKS, b);
+	if (WARN_ON_ONCE(b > MAX_NR_BANKS))
 		b = MAX_NR_BANKS;
-	}
 
-	/* Don't support asymmetric configurations today */
-	WARN_ON(mca_cfg.banks != 0 && b != mca_cfg.banks);
-	mca_cfg.banks = b;
+	mca_cfg.banks = max(mca_cfg.banks, b);
 
 	if (!mce_banks) {
 		int err = __mcheck_cpu_mce_banks_init();
-
 		if (err)
 			return err;
 	}
@@ -1771,6 +1775,14 @@ static void __mcheck_cpu_init_timer(void)
 	mce_start_timer(t);
 }
 
+bool filter_mce(struct mce *m)
+{
+	if (boot_cpu_data.x86_vendor == X86_VENDOR_AMD)
+		return amd_filter_mce(m);
+
+	return false;
+}
+
 /* Handle unconfigured int18 (should never happen) */
 static void unexpected_machine_check(struct pt_regs *regs, long error_code)
 {
@@ -2425,8 +2437,8 @@ static int fake_panic_set(void *data, u64 val)
 	return 0;
 }
 
-DEFINE_SIMPLE_ATTRIBUTE(fake_panic_fops, fake_panic_get,
-			fake_panic_set, "%llu\n");
+DEFINE_DEBUGFS_ATTRIBUTE(fake_panic_fops, fake_panic_get, fake_panic_set,
+			 "%llu\n");
 
 static int __init mcheck_debugfs_init(void)
 {
@@ -2435,8 +2447,8 @@ static int __init mcheck_debugfs_init(void)
 	dmce = mce_get_debugfs_dir();
 	if (!dmce)
 		return -ENOMEM;
-	ffake_panic = debugfs_create_file("fake_panic", 0444, dmce, NULL,
-					  &fake_panic_fops);
+	ffake_panic = debugfs_create_file_unsafe("fake_panic", 0444, dmce,
+						 NULL, &fake_panic_fops);
 	if (!ffake_panic)
 		return -ENOMEM;
 
@@ -2451,6 +2463,8 @@ EXPORT_SYMBOL_GPL(mcsafe_key);
 
 static int __init mcheck_late_init(void)
 {
+	pr_info("Using %d MCE banks\n", mca_cfg.banks);
+
 	if (mca_cfg.recovery)
 		static_branch_inc(&mcsafe_key);
 
diff --git a/arch/x86/kernel/cpu/mce/genpool.c b/arch/x86/kernel/cpu/mce/genpool.c
index 3395549c51d3..64d1d5a00f39 100644
--- a/arch/x86/kernel/cpu/mce/genpool.c
+++ b/arch/x86/kernel/cpu/mce/genpool.c
@@ -99,6 +99,9 @@ int mce_gen_pool_add(struct mce *mce)
 {
 	struct mce_evt_llist *node;
 
+	if (filter_mce(mce))
+		return -EINVAL;
+
 	if (!mce_evt_pool)
 		return -EINVAL;
 
diff --git a/arch/x86/kernel/cpu/mce/inject.c b/arch/x86/kernel/cpu/mce/inject.c
index 8492ef7d9015..a6026170af92 100644
--- a/arch/x86/kernel/cpu/mce/inject.c
+++ b/arch/x86/kernel/cpu/mce/inject.c
@@ -46,8 +46,6 @@
 static struct mce i_mce;
 static struct dentry *dfs_inj;
 
-static u8 n_banks;
-
 #define MAX_FLAG_OPT_SIZE	4
 #define NBCFG			0x44
 
@@ -528,7 +526,7 @@ static void do_inject(void)
 	 * only on the node base core. Refer to D18F3x44[NbMcaToMstCpuEn] for
 	 * Fam10h and later BKDGs.
 	 */
-	if (static_cpu_has(X86_FEATURE_AMD_DCM) &&
+	if (boot_cpu_has(X86_FEATURE_AMD_DCM) &&
 	    b == 4 &&
 	    boot_cpu_data.x86 < 0x17) {
 		toggle_nb_mca_mst_cpu(amd_get_nb_id(cpu));
@@ -570,9 +568,15 @@ err:
 static int inj_bank_set(void *data, u64 val)
 {
 	struct mce *m = (struct mce *)data;
+	u8 n_banks;
+	u64 cap;
+
+	/* Get bank count on target CPU so we can handle non-uniform values. */
+	rdmsrl_on_cpu(m->extcpu, MSR_IA32_MCG_CAP, &cap);
+	n_banks = cap & MCG_BANKCNT_MASK;
 
 	if (val >= n_banks) {
-		pr_err("Non-existent MCE bank: %llu\n", val);
+		pr_err("MCA bank %llu non-existent on CPU%d\n", val, m->extcpu);
 		return -EINVAL;
 	}
 
@@ -665,10 +669,6 @@ static struct dfs_node {
 static int __init debugfs_init(void)
 {
 	unsigned int i;
-	u64 cap;
-
-	rdmsrl(MSR_IA32_MCG_CAP, cap);
-	n_banks = cap & MCG_BANKCNT_MASK;
 
 	dfs_inj = debugfs_create_dir("mce-inject", NULL);
 	if (!dfs_inj)
diff --git a/arch/x86/kernel/cpu/mce/internal.h b/arch/x86/kernel/cpu/mce/internal.h
index af5eab1e65e2..a34b55baa7aa 100644
--- a/arch/x86/kernel/cpu/mce/internal.h
+++ b/arch/x86/kernel/cpu/mce/internal.h
@@ -173,4 +173,13 @@ struct mca_msr_regs {
 
 extern struct mca_msr_regs msr_ops;
 
+/* Decide whether to add MCE record to MCE event pool or filter it out. */
+extern bool filter_mce(struct mce *m);
+
+#ifdef CONFIG_X86_MCE_AMD
+extern bool amd_filter_mce(struct mce *m);
+#else
+static inline bool amd_filter_mce(struct mce *m)			{ return false; };
+#endif
+
 #endif /* __X86_MCE_INTERNAL_H__ */
diff --git a/arch/x86/kernel/cpu/microcode/core.c b/arch/x86/kernel/cpu/microcode/core.c
index 5260185cbf7b..8a4a7823451a 100644
--- a/arch/x86/kernel/cpu/microcode/core.c
+++ b/arch/x86/kernel/cpu/microcode/core.c
@@ -418,8 +418,9 @@ static int do_microcode_update(const void __user *buf, size_t size)
 		if (ustate == UCODE_ERROR) {
 			error = -1;
 			break;
-		} else if (ustate == UCODE_OK)
+		} else if (ustate == UCODE_NEW) {
 			apply_microcode_on_target(cpu);
+		}
 	}
 
 	return error;
diff --git a/arch/x86/kernel/cpu/microcode/intel.c b/arch/x86/kernel/cpu/microcode/intel.c
index 16936a24795c..a44bdbe7c55e 100644
--- a/arch/x86/kernel/cpu/microcode/intel.c
+++ b/arch/x86/kernel/cpu/microcode/intel.c
@@ -31,6 +31,7 @@
 #include <linux/kernel.h>
 #include <linux/slab.h>
 #include <linux/cpu.h>
+#include <linux/uio.h>
 #include <linux/mm.h>
 
 #include <asm/microcode_intel.h>
@@ -861,32 +862,33 @@ out:
 	return ret;
 }
 
-static enum ucode_state generic_load_microcode(int cpu, void *data, size_t size,
-				int (*get_ucode_data)(void *, const void *, size_t))
+static enum ucode_state generic_load_microcode(int cpu, struct iov_iter *iter)
 {
 	struct ucode_cpu_info *uci = ucode_cpu_info + cpu;
-	u8 *ucode_ptr = data, *new_mc = NULL, *mc = NULL;
-	int new_rev = uci->cpu_sig.rev;
-	unsigned int leftover = size;
 	unsigned int curr_mc_size = 0, new_mc_size = 0;
-	unsigned int csig, cpf;
 	enum ucode_state ret = UCODE_OK;
+	int new_rev = uci->cpu_sig.rev;
+	u8 *new_mc = NULL, *mc = NULL;
+	unsigned int csig, cpf;
 
-	while (leftover) {
+	while (iov_iter_count(iter)) {
 		struct microcode_header_intel mc_header;
-		unsigned int mc_size;
+		unsigned int mc_size, data_size;
+		u8 *data;
 
-		if (leftover < sizeof(mc_header)) {
-			pr_err("error! Truncated header in microcode data file\n");
+		if (!copy_from_iter_full(&mc_header, sizeof(mc_header), iter)) {
+			pr_err("error! Truncated or inaccessible header in microcode data file\n");
 			break;
 		}
 
-		if (get_ucode_data(&mc_header, ucode_ptr, sizeof(mc_header)))
-			break;
-
 		mc_size = get_totalsize(&mc_header);
-		if (!mc_size || mc_size > leftover) {
-			pr_err("error! Bad data in microcode data file\n");
+		if (mc_size < sizeof(mc_header)) {
+			pr_err("error! Bad data in microcode data file (totalsize too small)\n");
+			break;
+		}
+		data_size = mc_size - sizeof(mc_header);
+		if (data_size > iov_iter_count(iter)) {
+			pr_err("error! Bad data in microcode data file (truncated file?)\n");
 			break;
 		}
 
@@ -899,7 +901,9 @@ static enum ucode_state generic_load_microcode(int cpu, void *data, size_t size,
 			curr_mc_size = mc_size;
 		}
 
-		if (get_ucode_data(mc, ucode_ptr, mc_size) ||
+		memcpy(mc, &mc_header, sizeof(mc_header));
+		data = mc + sizeof(mc_header);
+		if (!copy_from_iter_full(data, data_size, iter) ||
 		    microcode_sanity_check(mc, 1) < 0) {
 			break;
 		}
@@ -914,14 +918,11 @@ static enum ucode_state generic_load_microcode(int cpu, void *data, size_t size,
 			mc = NULL;	/* trigger new vmalloc */
 			ret = UCODE_NEW;
 		}
-
-		ucode_ptr += mc_size;
-		leftover  -= mc_size;
 	}
 
 	vfree(mc);
 
-	if (leftover) {
+	if (iov_iter_count(iter)) {
 		vfree(new_mc);
 		return UCODE_ERROR;
 	}
@@ -945,12 +946,6 @@ static enum ucode_state generic_load_microcode(int cpu, void *data, size_t size,
 	return ret;
 }
 
-static int get_ucode_fw(void *to, const void *from, size_t n)
-{
-	memcpy(to, from, n);
-	return 0;
-}
-
 static bool is_blacklisted(unsigned int cpu)
 {
 	struct cpuinfo_x86 *c = &cpu_data(cpu);
@@ -977,10 +972,12 @@ static bool is_blacklisted(unsigned int cpu)
 static enum ucode_state request_microcode_fw(int cpu, struct device *device,
 					     bool refresh_fw)
 {
-	char name[30];
 	struct cpuinfo_x86 *c = &cpu_data(cpu);
 	const struct firmware *firmware;
+	struct iov_iter iter;
 	enum ucode_state ret;
+	struct kvec kvec;
+	char name[30];
 
 	if (is_blacklisted(cpu))
 		return UCODE_NFOUND;
@@ -993,26 +990,30 @@ static enum ucode_state request_microcode_fw(int cpu, struct device *device,
 		return UCODE_NFOUND;
 	}
 
-	ret = generic_load_microcode(cpu, (void *)firmware->data,
-				     firmware->size, &get_ucode_fw);
+	kvec.iov_base = (void *)firmware->data;
+	kvec.iov_len = firmware->size;
+	iov_iter_kvec(&iter, WRITE, &kvec, 1, firmware->size);
+	ret = generic_load_microcode(cpu, &iter);
 
 	release_firmware(firmware);
 
 	return ret;
 }
 
-static int get_ucode_user(void *to, const void *from, size_t n)
-{
-	return copy_from_user(to, from, n);
-}
-
 static enum ucode_state
 request_microcode_user(int cpu, const void __user *buf, size_t size)
 {
+	struct iov_iter iter;
+	struct iovec iov;
+
 	if (is_blacklisted(cpu))
 		return UCODE_NFOUND;
 
-	return generic_load_microcode(cpu, (void *)buf, size, &get_ucode_user);
+	iov.iov_base = (void __user *)buf;
+	iov.iov_len = size;
+	iov_iter_init(&iter, WRITE, &iov, 1, size);
+
+	return generic_load_microcode(cpu, &iter);
 }
 
 static struct microcode_ops microcode_intel_ops = {
diff --git a/arch/x86/kernel/cpu/proc.c b/arch/x86/kernel/cpu/proc.c
index 2c8522a39ed5..cb2e49810d68 100644
--- a/arch/x86/kernel/cpu/proc.c
+++ b/arch/x86/kernel/cpu/proc.c
@@ -35,11 +35,11 @@ static void show_cpuinfo_misc(struct seq_file *m, struct cpuinfo_x86 *c)
 		   "fpu_exception\t: %s\n"
 		   "cpuid level\t: %d\n"
 		   "wp\t\t: yes\n",
-		   static_cpu_has_bug(X86_BUG_FDIV) ? "yes" : "no",
-		   static_cpu_has_bug(X86_BUG_F00F) ? "yes" : "no",
-		   static_cpu_has_bug(X86_BUG_COMA) ? "yes" : "no",
-		   static_cpu_has(X86_FEATURE_FPU) ? "yes" : "no",
-		   static_cpu_has(X86_FEATURE_FPU) ? "yes" : "no",
+		   boot_cpu_has_bug(X86_BUG_FDIV) ? "yes" : "no",
+		   boot_cpu_has_bug(X86_BUG_F00F) ? "yes" : "no",
+		   boot_cpu_has_bug(X86_BUG_COMA) ? "yes" : "no",
+		   boot_cpu_has(X86_FEATURE_FPU) ? "yes" : "no",
+		   boot_cpu_has(X86_FEATURE_FPU) ? "yes" : "no",
 		   c->cpuid_level);
 }
 #else
diff --git a/arch/x86/kernel/cpu/resctrl/ctrlmondata.c b/arch/x86/kernel/cpu/resctrl/ctrlmondata.c
index 2dbd990a2eb7..89320c0396b1 100644
--- a/arch/x86/kernel/cpu/resctrl/ctrlmondata.c
+++ b/arch/x86/kernel/cpu/resctrl/ctrlmondata.c
@@ -342,10 +342,10 @@ int update_domains(struct rdt_resource *r, int closid)
 	if (cpumask_empty(cpu_mask) || mba_sc)
 		goto done;
 	cpu = get_cpu();
-	/* Update CBM on this cpu if it's in cpu_mask. */
+	/* Update resource control msr on this CPU if it's in cpu_mask. */
 	if (cpumask_test_cpu(cpu, cpu_mask))
 		rdt_ctrl_update(&msr_param);
-	/* Update CBM on other cpus. */
+	/* Update resource control msr on other CPUs. */
 	smp_call_function_many(cpu_mask, rdt_ctrl_update, &msr_param, 1);
 	put_cpu();
 
diff --git a/arch/x86/kernel/cpu/resctrl/monitor.c b/arch/x86/kernel/cpu/resctrl/monitor.c
index f33f11f69078..1573a0a6b525 100644
--- a/arch/x86/kernel/cpu/resctrl/monitor.c
+++ b/arch/x86/kernel/cpu/resctrl/monitor.c
@@ -501,11 +501,8 @@ out_unlock:
 void cqm_setup_limbo_handler(struct rdt_domain *dom, unsigned long delay_ms)
 {
 	unsigned long delay = msecs_to_jiffies(delay_ms);
-	struct rdt_resource *r;
 	int cpu;
 
-	r = &rdt_resources_all[RDT_RESOURCE_L3];
-
 	cpu = cpumask_any(&dom->cpu_mask);
 	dom->cqm_work_cpu = cpu;
 
diff --git a/arch/x86/kernel/cpu/resctrl/rdtgroup.c b/arch/x86/kernel/cpu/resctrl/rdtgroup.c
index 399601eda8e4..333c177a2471 100644
--- a/arch/x86/kernel/cpu/resctrl/rdtgroup.c
+++ b/arch/x86/kernel/cpu/resctrl/rdtgroup.c
@@ -2039,14 +2039,14 @@ out:
 enum rdt_param {
 	Opt_cdp,
 	Opt_cdpl2,
-	Opt_mba_mpbs,
+	Opt_mba_mbps,
 	nr__rdt_params
 };
 
 static const struct fs_parameter_spec rdt_param_specs[] = {
 	fsparam_flag("cdp",		Opt_cdp),
 	fsparam_flag("cdpl2",		Opt_cdpl2),
-	fsparam_flag("mba_mpbs",	Opt_mba_mpbs),
+	fsparam_flag("mba_MBps",	Opt_mba_mbps),
 	{}
 };
 
@@ -2072,7 +2072,7 @@ static int rdt_parse_param(struct fs_context *fc, struct fs_parameter *param)
 	case Opt_cdpl2:
 		ctx->enable_cdpl2 = true;
 		return 0;
-	case Opt_mba_mpbs:
+	case Opt_mba_mbps:
 		if (boot_cpu_data.x86_vendor != X86_VENDOR_INTEL)
 			return -EINVAL;
 		ctx->enable_mba_mbps = true;
@@ -2516,103 +2516,131 @@ static void cbm_ensure_valid(u32 *_val, struct rdt_resource *r)
 	bitmap_clear(val, zero_bit, cbm_len - zero_bit);
 }
 
-/**
- * rdtgroup_init_alloc - Initialize the new RDT group's allocations
- *
- * A new RDT group is being created on an allocation capable (CAT)
- * supporting system. Set this group up to start off with all usable
- * allocations. That is, all shareable and unused bits.
+/*
+ * Initialize cache resources per RDT domain
  *
- * All-zero CBM is invalid. If there are no more shareable bits available
- * on any domain then the entire allocation will fail.
+ * Set the RDT domain up to start off with all usable allocations. That is,
+ * all shareable and unused bits. All-zero CBM is invalid.
  */
-static int rdtgroup_init_alloc(struct rdtgroup *rdtgrp)
+static int __init_one_rdt_domain(struct rdt_domain *d, struct rdt_resource *r,
+				 u32 closid)
 {
 	struct rdt_resource *r_cdp = NULL;
 	struct rdt_domain *d_cdp = NULL;
 	u32 used_b = 0, unused_b = 0;
-	u32 closid = rdtgrp->closid;
-	struct rdt_resource *r;
 	unsigned long tmp_cbm;
 	enum rdtgrp_mode mode;
-	struct rdt_domain *d;
 	u32 peer_ctl, *ctrl;
-	int i, ret;
+	int i;
 
-	for_each_alloc_enabled_rdt_resource(r) {
-		/*
-		 * Only initialize default allocations for CBM cache
-		 * resources
-		 */
-		if (r->rid == RDT_RESOURCE_MBA)
-			continue;
-		list_for_each_entry(d, &r->domains, list) {
-			rdt_cdp_peer_get(r, d, &r_cdp, &d_cdp);
-			d->have_new_ctrl = false;
-			d->new_ctrl = r->cache.shareable_bits;
-			used_b = r->cache.shareable_bits;
-			ctrl = d->ctrl_val;
-			for (i = 0; i < closids_supported(); i++, ctrl++) {
-				if (closid_allocated(i) && i != closid) {
-					mode = rdtgroup_mode_by_closid(i);
-					if (mode == RDT_MODE_PSEUDO_LOCKSETUP)
-						break;
-					/*
-					 * If CDP is active include peer
-					 * domain's usage to ensure there
-					 * is no overlap with an exclusive
-					 * group.
-					 */
-					if (d_cdp)
-						peer_ctl = d_cdp->ctrl_val[i];
-					else
-						peer_ctl = 0;
-					used_b |= *ctrl | peer_ctl;
-					if (mode == RDT_MODE_SHAREABLE)
-						d->new_ctrl |= *ctrl | peer_ctl;
-				}
-			}
-			if (d->plr && d->plr->cbm > 0)
-				used_b |= d->plr->cbm;
-			unused_b = used_b ^ (BIT_MASK(r->cache.cbm_len) - 1);
-			unused_b &= BIT_MASK(r->cache.cbm_len) - 1;
-			d->new_ctrl |= unused_b;
-			/*
-			 * Force the initial CBM to be valid, user can
-			 * modify the CBM based on system availability.
-			 */
-			cbm_ensure_valid(&d->new_ctrl, r);
+	rdt_cdp_peer_get(r, d, &r_cdp, &d_cdp);
+	d->have_new_ctrl = false;
+	d->new_ctrl = r->cache.shareable_bits;
+	used_b = r->cache.shareable_bits;
+	ctrl = d->ctrl_val;
+	for (i = 0; i < closids_supported(); i++, ctrl++) {
+		if (closid_allocated(i) && i != closid) {
+			mode = rdtgroup_mode_by_closid(i);
+			if (mode == RDT_MODE_PSEUDO_LOCKSETUP)
+				break;
 			/*
-			 * Assign the u32 CBM to an unsigned long to ensure
-			 * that bitmap_weight() does not access out-of-bound
-			 * memory.
+			 * If CDP is active include peer domain's
+			 * usage to ensure there is no overlap
+			 * with an exclusive group.
 			 */
-			tmp_cbm = d->new_ctrl;
-			if (bitmap_weight(&tmp_cbm, r->cache.cbm_len) <
-			    r->cache.min_cbm_bits) {
-				rdt_last_cmd_printf("No space on %s:%d\n",
-						    r->name, d->id);
-				return -ENOSPC;
-			}
-			d->have_new_ctrl = true;
+			if (d_cdp)
+				peer_ctl = d_cdp->ctrl_val[i];
+			else
+				peer_ctl = 0;
+			used_b |= *ctrl | peer_ctl;
+			if (mode == RDT_MODE_SHAREABLE)
+				d->new_ctrl |= *ctrl | peer_ctl;
 		}
 	}
+	if (d->plr && d->plr->cbm > 0)
+		used_b |= d->plr->cbm;
+	unused_b = used_b ^ (BIT_MASK(r->cache.cbm_len) - 1);
+	unused_b &= BIT_MASK(r->cache.cbm_len) - 1;
+	d->new_ctrl |= unused_b;
+	/*
+	 * Force the initial CBM to be valid, user can
+	 * modify the CBM based on system availability.
+	 */
+	cbm_ensure_valid(&d->new_ctrl, r);
+	/*
+	 * Assign the u32 CBM to an unsigned long to ensure that
+	 * bitmap_weight() does not access out-of-bound memory.
+	 */
+	tmp_cbm = d->new_ctrl;
+	if (bitmap_weight(&tmp_cbm, r->cache.cbm_len) < r->cache.min_cbm_bits) {
+		rdt_last_cmd_printf("No space on %s:%d\n", r->name, d->id);
+		return -ENOSPC;
+	}
+	d->have_new_ctrl = true;
+
+	return 0;
+}
+
+/*
+ * Initialize cache resources with default values.
+ *
+ * A new RDT group is being created on an allocation capable (CAT)
+ * supporting system. Set this group up to start off with all usable
+ * allocations.
+ *
+ * If there are no more shareable bits available on any domain then
+ * the entire allocation will fail.
+ */
+static int rdtgroup_init_cat(struct rdt_resource *r, u32 closid)
+{
+	struct rdt_domain *d;
+	int ret;
+
+	list_for_each_entry(d, &r->domains, list) {
+		ret = __init_one_rdt_domain(d, r, closid);
+		if (ret < 0)
+			return ret;
+	}
+
+	return 0;
+}
+
+/* Initialize MBA resource with default values. */
+static void rdtgroup_init_mba(struct rdt_resource *r)
+{
+	struct rdt_domain *d;
+
+	list_for_each_entry(d, &r->domains, list) {
+		d->new_ctrl = is_mba_sc(r) ? MBA_MAX_MBPS : r->default_ctrl;
+		d->have_new_ctrl = true;
+	}
+}
+
+/* Initialize the RDT group's allocations. */
+static int rdtgroup_init_alloc(struct rdtgroup *rdtgrp)
+{
+	struct rdt_resource *r;
+	int ret;
 
 	for_each_alloc_enabled_rdt_resource(r) {
-		/*
-		 * Only initialize default allocations for CBM cache
-		 * resources
-		 */
-		if (r->rid == RDT_RESOURCE_MBA)
-			continue;
+		if (r->rid == RDT_RESOURCE_MBA) {
+			rdtgroup_init_mba(r);
+		} else {
+			ret = rdtgroup_init_cat(r, rdtgrp->closid);
+			if (ret < 0)
+				return ret;
+		}
+
 		ret = update_domains(r, rdtgrp->closid);
 		if (ret < 0) {
 			rdt_last_cmd_puts("Failed to initialize allocations\n");
 			return ret;
 		}
-		rdtgrp->mode = RDT_MODE_SHAREABLE;
+
 	}
 
+	rdtgrp->mode = RDT_MODE_SHAREABLE;
+
 	return 0;
 }
 
diff --git a/arch/x86/kernel/crash.c b/arch/x86/kernel/crash.c
index 17ffc869cab8..a96ca8584803 100644
--- a/arch/x86/kernel/crash.c
+++ b/arch/x86/kernel/crash.c
@@ -204,8 +204,7 @@ static struct crash_mem *fill_up_crash_elf_data(void)
 	 * another range split. So add extra two slots here.
 	 */
 	nr_ranges += 2;
-	cmem = vzalloc(sizeof(struct crash_mem) +
-			sizeof(struct crash_mem_range) * nr_ranges);
+	cmem = vzalloc(struct_size(cmem, ranges, nr_ranges));
 	if (!cmem)
 		return NULL;
 
diff --git a/arch/x86/kernel/dumpstack_32.c b/arch/x86/kernel/dumpstack_32.c
index cd53f3030e40..64a59d726639 100644
--- a/arch/x86/kernel/dumpstack_32.c
+++ b/arch/x86/kernel/dumpstack_32.c
@@ -34,14 +34,14 @@ const char *stack_type_name(enum stack_type type)
 
 static bool in_hardirq_stack(unsigned long *stack, struct stack_info *info)
 {
-	unsigned long *begin = (unsigned long *)this_cpu_read(hardirq_stack);
+	unsigned long *begin = (unsigned long *)this_cpu_read(hardirq_stack_ptr);
 	unsigned long *end   = begin + (THREAD_SIZE / sizeof(long));
 
 	/*
 	 * This is a software stack, so 'end' can be a valid stack pointer.
 	 * It just means the stack is empty.
 	 */
-	if (stack <= begin || stack > end)
+	if (stack < begin || stack > end)
 		return false;
 
 	info->type	= STACK_TYPE_IRQ;
@@ -59,14 +59,14 @@ static bool in_hardirq_stack(unsigned long *stack, struct stack_info *info)
 
 static bool in_softirq_stack(unsigned long *stack, struct stack_info *info)
 {
-	unsigned long *begin = (unsigned long *)this_cpu_read(softirq_stack);
+	unsigned long *begin = (unsigned long *)this_cpu_read(softirq_stack_ptr);
 	unsigned long *end   = begin + (THREAD_SIZE / sizeof(long));
 
 	/*
 	 * This is a software stack, so 'end' can be a valid stack pointer.
 	 * It just means the stack is empty.
 	 */
-	if (stack <= begin || stack > end)
+	if (stack < begin || stack > end)
 		return false;
 
 	info->type	= STACK_TYPE_SOFTIRQ;
diff --git a/arch/x86/kernel/dumpstack_64.c b/arch/x86/kernel/dumpstack_64.c
index 5cdb9e84da57..753b8cfe8b8a 100644
--- a/arch/x86/kernel/dumpstack_64.c
+++ b/arch/x86/kernel/dumpstack_64.c
@@ -16,23 +16,21 @@
 #include <linux/bug.h>
 #include <linux/nmi.h>
 
+#include <asm/cpu_entry_area.h>
 #include <asm/stacktrace.h>
 
-static char *exception_stack_names[N_EXCEPTION_STACKS] = {
-		[ DOUBLEFAULT_STACK-1	]	= "#DF",
-		[ NMI_STACK-1		]	= "NMI",
-		[ DEBUG_STACK-1		]	= "#DB",
-		[ MCE_STACK-1		]	= "#MC",
-};
-
-static unsigned long exception_stack_sizes[N_EXCEPTION_STACKS] = {
-	[0 ... N_EXCEPTION_STACKS - 1]		= EXCEPTION_STKSZ,
-	[DEBUG_STACK - 1]			= DEBUG_STKSZ
+static const char * const exception_stack_names[] = {
+		[ ESTACK_DF	]	= "#DF",
+		[ ESTACK_NMI	]	= "NMI",
+		[ ESTACK_DB2	]	= "#DB2",
+		[ ESTACK_DB1	]	= "#DB1",
+		[ ESTACK_DB	]	= "#DB",
+		[ ESTACK_MCE	]	= "#MC",
 };
 
 const char *stack_type_name(enum stack_type type)
 {
-	BUILD_BUG_ON(N_EXCEPTION_STACKS != 4);
+	BUILD_BUG_ON(N_EXCEPTION_STACKS != 6);
 
 	if (type == STACK_TYPE_IRQ)
 		return "IRQ";
@@ -52,43 +50,84 @@ const char *stack_type_name(enum stack_type type)
 	return NULL;
 }
 
+/**
+ * struct estack_pages - Page descriptor for exception stacks
+ * @offs:	Offset from the start of the exception stack area
+ * @size:	Size of the exception stack
+ * @type:	Type to store in the stack_info struct
+ */
+struct estack_pages {
+	u32	offs;
+	u16	size;
+	u16	type;
+};
+
+#define EPAGERANGE(st)							\
+	[PFN_DOWN(CEA_ESTACK_OFFS(st)) ...				\
+	 PFN_DOWN(CEA_ESTACK_OFFS(st) + CEA_ESTACK_SIZE(st) - 1)] = {	\
+		.offs	= CEA_ESTACK_OFFS(st),				\
+		.size	= CEA_ESTACK_SIZE(st),				\
+		.type	= STACK_TYPE_EXCEPTION + ESTACK_ ##st, }
+
+/*
+ * Array of exception stack page descriptors. If the stack is larger than
+ * PAGE_SIZE, all pages covering a particular stack will have the same
+ * info. The guard pages including the not mapped DB2 stack are zeroed
+ * out.
+ */
+static const
+struct estack_pages estack_pages[CEA_ESTACK_PAGES] ____cacheline_aligned = {
+	EPAGERANGE(DF),
+	EPAGERANGE(NMI),
+	EPAGERANGE(DB1),
+	EPAGERANGE(DB),
+	EPAGERANGE(MCE),
+};
+
 static bool in_exception_stack(unsigned long *stack, struct stack_info *info)
 {
-	unsigned long *begin, *end;
+	unsigned long begin, end, stk = (unsigned long)stack;
+	const struct estack_pages *ep;
 	struct pt_regs *regs;
-	unsigned k;
+	unsigned int k;
 
-	BUILD_BUG_ON(N_EXCEPTION_STACKS != 4);
+	BUILD_BUG_ON(N_EXCEPTION_STACKS != 6);
 
-	for (k = 0; k < N_EXCEPTION_STACKS; k++) {
-		end   = (unsigned long *)raw_cpu_ptr(&orig_ist)->ist[k];
-		begin = end - (exception_stack_sizes[k] / sizeof(long));
-		regs  = (struct pt_regs *)end - 1;
-
-		if (stack <= begin || stack >= end)
-			continue;
+	begin = (unsigned long)__this_cpu_read(cea_exception_stacks);
+	end = begin + sizeof(struct cea_exception_stacks);
+	/* Bail if @stack is outside the exception stack area. */
+	if (stk < begin || stk >= end)
+		return false;
 
-		info->type	= STACK_TYPE_EXCEPTION + k;
-		info->begin	= begin;
-		info->end	= end;
-		info->next_sp	= (unsigned long *)regs->sp;
+	/* Calc page offset from start of exception stacks */
+	k = (stk - begin) >> PAGE_SHIFT;
+	/* Lookup the page descriptor */
+	ep = &estack_pages[k];
+	/* Guard page? */
+	if (!ep->size)
+		return false;
 
-		return true;
-	}
+	begin += (unsigned long)ep->offs;
+	end = begin + (unsigned long)ep->size;
+	regs = (struct pt_regs *)end - 1;
 
-	return false;
+	info->type	= ep->type;
+	info->begin	= (unsigned long *)begin;
+	info->end	= (unsigned long *)end;
+	info->next_sp	= (unsigned long *)regs->sp;
+	return true;
 }
 
 static bool in_irq_stack(unsigned long *stack, struct stack_info *info)
 {
-	unsigned long *end   = (unsigned long *)this_cpu_read(irq_stack_ptr);
+	unsigned long *end   = (unsigned long *)this_cpu_read(hardirq_stack_ptr);
 	unsigned long *begin = end - (IRQ_STACK_SIZE / sizeof(long));
 
 	/*
 	 * This is a software stack, so 'end' can be a valid stack pointer.
 	 * It just means the stack is empty.
 	 */
-	if (stack <= begin || stack > end)
+	if (stack < begin || stack >= end)
 		return false;
 
 	info->type	= STACK_TYPE_IRQ;
diff --git a/arch/x86/kernel/ftrace.c b/arch/x86/kernel/ftrace.c
index ef49517f6bb2..0caf8122d680 100644
--- a/arch/x86/kernel/ftrace.c
+++ b/arch/x86/kernel/ftrace.c
@@ -678,12 +678,8 @@ static inline void *alloc_tramp(unsigned long size)
 {
 	return module_alloc(size);
 }
-static inline void tramp_free(void *tramp, int size)
+static inline void tramp_free(void *tramp)
 {
-	int npages = PAGE_ALIGN(size) >> PAGE_SHIFT;
-
-	set_memory_nx((unsigned long)tramp, npages);
-	set_memory_rw((unsigned long)tramp, npages);
 	module_memfree(tramp);
 }
 #else
@@ -692,7 +688,7 @@ static inline void *alloc_tramp(unsigned long size)
 {
 	return NULL;
 }
-static inline void tramp_free(void *tramp, int size) { }
+static inline void tramp_free(void *tramp) { }
 #endif
 
 /* Defined as markers to the end of the ftrace default trampolines */
@@ -730,6 +726,7 @@ create_trampoline(struct ftrace_ops *ops, unsigned int *tramp_size)
 	unsigned long end_offset;
 	unsigned long op_offset;
 	unsigned long offset;
+	unsigned long npages;
 	unsigned long size;
 	unsigned long retq;
 	unsigned long *ptr;
@@ -762,6 +759,7 @@ create_trampoline(struct ftrace_ops *ops, unsigned int *tramp_size)
 		return 0;
 
 	*tramp_size = size + RET_SIZE + sizeof(void *);
+	npages = DIV_ROUND_UP(*tramp_size, PAGE_SIZE);
 
 	/* Copy ftrace_caller onto the trampoline memory */
 	ret = probe_kernel_read(trampoline, (void *)start_offset, size);
@@ -806,9 +804,17 @@ create_trampoline(struct ftrace_ops *ops, unsigned int *tramp_size)
 	/* ALLOC_TRAMP flags lets us know we created it */
 	ops->flags |= FTRACE_OPS_FL_ALLOC_TRAMP;
 
+	set_vm_flush_reset_perms(trampoline);
+
+	/*
+	 * Module allocation needs to be completed by making the page
+	 * executable. The page is still writable, which is a security hazard,
+	 * but anyhow ftrace breaks W^X completely.
+	 */
+	set_memory_x((unsigned long)trampoline, npages);
 	return (unsigned long)trampoline;
 fail:
-	tramp_free(trampoline, *tramp_size);
+	tramp_free(trampoline);
 	return 0;
 }
 
@@ -939,7 +945,7 @@ void arch_ftrace_trampoline_free(struct ftrace_ops *ops)
 	if (!ops || !(ops->flags & FTRACE_OPS_FL_ALLOC_TRAMP))
 		return;
 
-	tramp_free((void *)ops->trampoline, ops->trampoline_size);
+	tramp_free((void *)ops->trampoline);
 	ops->trampoline = 0;
 }
 
diff --git a/arch/x86/kernel/head_64.S b/arch/x86/kernel/head_64.S
index d1dbe8e4eb82..bcd206c8ac90 100644
--- a/arch/x86/kernel/head_64.S
+++ b/arch/x86/kernel/head_64.S
@@ -265,7 +265,7 @@ ENDPROC(start_cpu0)
 	GLOBAL(initial_code)
 	.quad	x86_64_start_kernel
 	GLOBAL(initial_gs)
-	.quad	INIT_PER_CPU_VAR(irq_stack_union)
+	.quad	INIT_PER_CPU_VAR(fixed_percpu_data)
 	GLOBAL(initial_stack)
 	/*
 	 * The SIZEOF_PTREGS gap is a convention which helps the in-kernel
diff --git a/arch/x86/kernel/idt.c b/arch/x86/kernel/idt.c
index 01adea278a71..6d8917875f44 100644
--- a/arch/x86/kernel/idt.c
+++ b/arch/x86/kernel/idt.c
@@ -41,13 +41,12 @@ struct idt_data {
 #define SYSG(_vector, _addr)				\
 	G(_vector, _addr, DEFAULT_STACK, GATE_INTERRUPT, DPL3, __KERNEL_CS)
 
-/* Interrupt gate with interrupt stack */
+/*
+ * Interrupt gate with interrupt stack. The _ist index is the index in
+ * the tss.ist[] array, but for the descriptor it needs to start at 1.
+ */
 #define ISTG(_vector, _addr, _ist)			\
-	G(_vector, _addr, _ist, GATE_INTERRUPT, DPL0, __KERNEL_CS)
-
-/* System interrupt gate with interrupt stack */
-#define SISTG(_vector, _addr, _ist)			\
-	G(_vector, _addr, _ist, GATE_INTERRUPT, DPL3, __KERNEL_CS)
+	G(_vector, _addr, _ist + 1, GATE_INTERRUPT, DPL0, __KERNEL_CS)
 
 /* Task gate */
 #define TSKG(_vector, _gdt)				\
@@ -184,11 +183,11 @@ gate_desc debug_idt_table[IDT_ENTRIES] __page_aligned_bss;
  * cpu_init() when the TSS has been initialized.
  */
 static const __initconst struct idt_data ist_idts[] = {
-	ISTG(X86_TRAP_DB,	debug,		DEBUG_STACK),
-	ISTG(X86_TRAP_NMI,	nmi,		NMI_STACK),
-	ISTG(X86_TRAP_DF,	double_fault,	DOUBLEFAULT_STACK),
+	ISTG(X86_TRAP_DB,	debug,		IST_INDEX_DB),
+	ISTG(X86_TRAP_NMI,	nmi,		IST_INDEX_NMI),
+	ISTG(X86_TRAP_DF,	double_fault,	IST_INDEX_DF),
 #ifdef CONFIG_X86_MCE
-	ISTG(X86_TRAP_MC,	&machine_check,	MCE_STACK),
+	ISTG(X86_TRAP_MC,	&machine_check,	IST_INDEX_MCE),
 #endif
 };
 
diff --git a/arch/x86/kernel/irq_32.c b/arch/x86/kernel/irq_32.c
index 95600a99ae93..fc34816c6f04 100644
--- a/arch/x86/kernel/irq_32.c
+++ b/arch/x86/kernel/irq_32.c
@@ -51,8 +51,8 @@ static inline int check_stack_overflow(void) { return 0; }
 static inline void print_stack_overflow(void) { }
 #endif
 
-DEFINE_PER_CPU(struct irq_stack *, hardirq_stack);
-DEFINE_PER_CPU(struct irq_stack *, softirq_stack);
+DEFINE_PER_CPU(struct irq_stack *, hardirq_stack_ptr);
+DEFINE_PER_CPU(struct irq_stack *, softirq_stack_ptr);
 
 static void call_on_stack(void *func, void *stack)
 {
@@ -76,7 +76,7 @@ static inline int execute_on_irq_stack(int overflow, struct irq_desc *desc)
 	u32 *isp, *prev_esp, arg1;
 
 	curstk = (struct irq_stack *) current_stack();
-	irqstk = __this_cpu_read(hardirq_stack);
+	irqstk = __this_cpu_read(hardirq_stack_ptr);
 
 	/*
 	 * this is where we switch to the IRQ stack. However, if we are
@@ -107,27 +107,28 @@ static inline int execute_on_irq_stack(int overflow, struct irq_desc *desc)
 }
 
 /*
- * allocate per-cpu stacks for hardirq and for softirq processing
+ * Allocate per-cpu stacks for hardirq and softirq processing
  */
-void irq_ctx_init(int cpu)
+int irq_init_percpu_irqstack(unsigned int cpu)
 {
-	struct irq_stack *irqstk;
-
-	if (per_cpu(hardirq_stack, cpu))
-		return;
+	int node = cpu_to_node(cpu);
+	struct page *ph, *ps;
 
-	irqstk = page_address(alloc_pages_node(cpu_to_node(cpu),
-					       THREADINFO_GFP,
-					       THREAD_SIZE_ORDER));
-	per_cpu(hardirq_stack, cpu) = irqstk;
+	if (per_cpu(hardirq_stack_ptr, cpu))
+		return 0;
 
-	irqstk = page_address(alloc_pages_node(cpu_to_node(cpu),
-					       THREADINFO_GFP,
-					       THREAD_SIZE_ORDER));
-	per_cpu(softirq_stack, cpu) = irqstk;
+	ph = alloc_pages_node(node, THREADINFO_GFP, THREAD_SIZE_ORDER);
+	if (!ph)
+		return -ENOMEM;
+	ps = alloc_pages_node(node, THREADINFO_GFP, THREAD_SIZE_ORDER);
+	if (!ps) {
+		__free_pages(ph, THREAD_SIZE_ORDER);
+		return -ENOMEM;
+	}
 
-	printk(KERN_DEBUG "CPU %u irqstacks, hard=%p soft=%p\n",
-	       cpu, per_cpu(hardirq_stack, cpu),  per_cpu(softirq_stack, cpu));
+	per_cpu(hardirq_stack_ptr, cpu) = page_address(ph);
+	per_cpu(softirq_stack_ptr, cpu) = page_address(ps);
+	return 0;
 }
 
 void do_softirq_own_stack(void)
@@ -135,7 +136,7 @@ void do_softirq_own_stack(void)
 	struct irq_stack *irqstk;
 	u32 *isp, *prev_esp;
 
-	irqstk = __this_cpu_read(softirq_stack);
+	irqstk = __this_cpu_read(softirq_stack_ptr);
 
 	/* build the stack frame on the softirq stack */
 	isp = (u32 *) ((char *)irqstk + sizeof(*irqstk));
diff --git a/arch/x86/kernel/irq_64.c b/arch/x86/kernel/irq_64.c
index 0469cd078db1..6bf6517a05bb 100644
--- a/arch/x86/kernel/irq_64.c
+++ b/arch/x86/kernel/irq_64.c
@@ -18,63 +18,64 @@
 #include <linux/uaccess.h>
 #include <linux/smp.h>
 #include <linux/sched/task_stack.h>
+
+#include <asm/cpu_entry_area.h>
 #include <asm/io_apic.h>
 #include <asm/apic.h>
 
-int sysctl_panic_on_stackoverflow;
+DEFINE_PER_CPU_PAGE_ALIGNED(struct irq_stack, irq_stack_backing_store) __visible;
+DECLARE_INIT_PER_CPU(irq_stack_backing_store);
 
-/*
- * Probabilistic stack overflow check:
- *
- * Only check the stack in process context, because everything else
- * runs on the big interrupt stacks. Checking reliably is too expensive,
- * so we just check from interrupts.
- */
-static inline void stack_overflow_check(struct pt_regs *regs)
+bool handle_irq(struct irq_desc *desc, struct pt_regs *regs)
 {
-#ifdef CONFIG_DEBUG_STACKOVERFLOW
-#define STACK_TOP_MARGIN	128
-	struct orig_ist *oist;
-	u64 irq_stack_top, irq_stack_bottom;
-	u64 estack_top, estack_bottom;
-	u64 curbase = (u64)task_stack_page(current);
+	if (IS_ERR_OR_NULL(desc))
+		return false;
 
-	if (user_mode(regs))
-		return;
+	generic_handle_irq_desc(desc);
+	return true;
+}
 
-	if (regs->sp >= curbase + sizeof(struct pt_regs) + STACK_TOP_MARGIN &&
-	    regs->sp <= curbase + THREAD_SIZE)
-		return;
+#ifdef CONFIG_VMAP_STACK
+/*
+ * VMAP the backing store with guard pages
+ */
+static int map_irq_stack(unsigned int cpu)
+{
+	char *stack = (char *)per_cpu_ptr(&irq_stack_backing_store, cpu);
+	struct page *pages[IRQ_STACK_SIZE / PAGE_SIZE];
+	void *va;
+	int i;
 
-	irq_stack_top = (u64)this_cpu_ptr(irq_stack_union.irq_stack) +
-			STACK_TOP_MARGIN;
-	irq_stack_bottom = (u64)__this_cpu_read(irq_stack_ptr);
-	if (regs->sp >= irq_stack_top && regs->sp <= irq_stack_bottom)
-		return;
+	for (i = 0; i < IRQ_STACK_SIZE / PAGE_SIZE; i++) {
+		phys_addr_t pa = per_cpu_ptr_to_phys(stack + (i << PAGE_SHIFT));
 
-	oist = this_cpu_ptr(&orig_ist);
-	estack_top = (u64)oist->ist[0] - EXCEPTION_STKSZ + STACK_TOP_MARGIN;
-	estack_bottom = (u64)oist->ist[N_EXCEPTION_STACKS - 1];
-	if (regs->sp >= estack_top && regs->sp <= estack_bottom)
-		return;
+		pages[i] = pfn_to_page(pa >> PAGE_SHIFT);
+	}
 
-	WARN_ONCE(1, "do_IRQ(): %s has overflown the kernel stack (cur:%Lx,sp:%lx,irq stk top-bottom:%Lx-%Lx,exception stk top-bottom:%Lx-%Lx,ip:%pF)\n",
-		current->comm, curbase, regs->sp,
-		irq_stack_top, irq_stack_bottom,
-		estack_top, estack_bottom, (void *)regs->ip);
+	va = vmap(pages, IRQ_STACK_SIZE / PAGE_SIZE, GFP_KERNEL, PAGE_KERNEL);
+	if (!va)
+		return -ENOMEM;
 
-	if (sysctl_panic_on_stackoverflow)
-		panic("low stack detected by irq handler - check messages\n");
-#endif
+	per_cpu(hardirq_stack_ptr, cpu) = va + IRQ_STACK_SIZE;
+	return 0;
 }
-
-bool handle_irq(struct irq_desc *desc, struct pt_regs *regs)
+#else
+/*
+ * If VMAP stacks are disabled due to KASAN, just use the per cpu
+ * backing store without guard pages.
+ */
+static int map_irq_stack(unsigned int cpu)
 {
-	stack_overflow_check(regs);
+	void *va = per_cpu_ptr(&irq_stack_backing_store, cpu);
 
-	if (IS_ERR_OR_NULL(desc))
-		return false;
+	per_cpu(hardirq_stack_ptr, cpu) = va + IRQ_STACK_SIZE;
+	return 0;
+}
+#endif
 
-	generic_handle_irq_desc(desc);
-	return true;
+int irq_init_percpu_irqstack(unsigned int cpu)
+{
+	if (per_cpu(hardirq_stack_ptr, cpu))
+		return 0;
+	return map_irq_stack(cpu);
 }
diff --git a/arch/x86/kernel/irqinit.c b/arch/x86/kernel/irqinit.c
index a0693b71cfc1..16919a9671fa 100644
--- a/arch/x86/kernel/irqinit.c
+++ b/arch/x86/kernel/irqinit.c
@@ -91,6 +91,8 @@ void __init init_IRQ(void)
 	for (i = 0; i < nr_legacy_irqs(); i++)
 		per_cpu(vector_irq, 0)[ISA_IRQ_VECTOR(i)] = irq_to_desc(i);
 
+	BUG_ON(irq_init_percpu_irqstack(smp_processor_id()));
+
 	x86_init.irqs.intr_init();
 }
 
@@ -104,6 +106,4 @@ void __init native_init_IRQ(void)
 
 	if (!acpi_ioapic && !of_ioapic && nr_legacy_irqs())
 		setup_irq(2, &irq2);
-
-	irq_ctx_init(smp_processor_id());
 }
diff --git a/arch/x86/kernel/jump_label.c b/arch/x86/kernel/jump_label.c
index f99bd26bd3f1..e631c358f7f4 100644
--- a/arch/x86/kernel/jump_label.c
+++ b/arch/x86/kernel/jump_label.c
@@ -37,7 +37,6 @@ static void bug_at(unsigned char *ip, int line)
 
 static void __ref __jump_label_transform(struct jump_entry *entry,
 					 enum jump_label_type type,
-					 void *(*poker)(void *, const void *, size_t),
 					 int init)
 {
 	union jump_code_union jmp;
@@ -50,9 +49,6 @@ static void __ref __jump_label_transform(struct jump_entry *entry,
 	jmp.offset = jump_entry_target(entry) -
 		     (jump_entry_code(entry) + JUMP_LABEL_NOP_SIZE);
 
-	if (early_boot_irqs_disabled)
-		poker = text_poke_early;
-
 	if (type == JUMP_LABEL_JMP) {
 		if (init) {
 			expect = default_nop; line = __LINE__;
@@ -75,16 +71,19 @@ static void __ref __jump_label_transform(struct jump_entry *entry,
 		bug_at((void *)jump_entry_code(entry), line);
 
 	/*
-	 * Make text_poke_bp() a default fallback poker.
+	 * As long as only a single processor is running and the code is still
+	 * not marked as RO, text_poke_early() can be used; Checking that
+	 * system_state is SYSTEM_BOOTING guarantees it. It will be set to
+	 * SYSTEM_SCHEDULING before other cores are awaken and before the
+	 * code is write-protected.
 	 *
 	 * At the time the change is being done, just ignore whether we
 	 * are doing nop -> jump or jump -> nop transition, and assume
 	 * always nop being the 'currently valid' instruction
-	 *
 	 */
-	if (poker) {
-		(*poker)((void *)jump_entry_code(entry), code,
-			 JUMP_LABEL_NOP_SIZE);
+	if (init || system_state == SYSTEM_BOOTING) {
+		text_poke_early((void *)jump_entry_code(entry), code,
+				JUMP_LABEL_NOP_SIZE);
 		return;
 	}
 
@@ -96,7 +95,7 @@ void arch_jump_label_transform(struct jump_entry *entry,
 			       enum jump_label_type type)
 {
 	mutex_lock(&text_mutex);
-	__jump_label_transform(entry, type, NULL, 0);
+	__jump_label_transform(entry, type, 0);
 	mutex_unlock(&text_mutex);
 }
 
@@ -126,5 +125,5 @@ __init_or_module void arch_jump_label_transform_static(struct jump_entry *entry,
 			jlstate = JL_STATE_NO_UPDATE;
 	}
 	if (jlstate == JL_STATE_UPDATE)
-		__jump_label_transform(entry, type, text_poke_early, 1);
+		__jump_label_transform(entry, type, 1);
 }
diff --git a/arch/x86/kernel/kgdb.c b/arch/x86/kernel/kgdb.c
index 4ff6b4cdb941..13b13311b792 100644
--- a/arch/x86/kernel/kgdb.c
+++ b/arch/x86/kernel/kgdb.c
@@ -747,7 +747,6 @@ void kgdb_arch_set_pc(struct pt_regs *regs, unsigned long ip)
 int kgdb_arch_set_breakpoint(struct kgdb_bkpt *bpt)
 {
 	int err;
-	char opc[BREAK_INSTR_SIZE];
 
 	bpt->type = BP_BREAKPOINT;
 	err = probe_kernel_read(bpt->saved_instr, (char *)bpt->bpt_addr,
@@ -759,18 +758,13 @@ int kgdb_arch_set_breakpoint(struct kgdb_bkpt *bpt)
 	if (!err)
 		return err;
 	/*
-	 * It is safe to call text_poke() because normal kernel execution
+	 * It is safe to call text_poke_kgdb() because normal kernel execution
 	 * is stopped on all cores, so long as the text_mutex is not locked.
 	 */
 	if (mutex_is_locked(&text_mutex))
 		return -EBUSY;
-	text_poke((void *)bpt->bpt_addr, arch_kgdb_ops.gdb_bpt_instr,
-		  BREAK_INSTR_SIZE);
-	err = probe_kernel_read(opc, (char *)bpt->bpt_addr, BREAK_INSTR_SIZE);
-	if (err)
-		return err;
-	if (memcmp(opc, arch_kgdb_ops.gdb_bpt_instr, BREAK_INSTR_SIZE))
-		return -EINVAL;
+	text_poke_kgdb((void *)bpt->bpt_addr, arch_kgdb_ops.gdb_bpt_instr,
+		       BREAK_INSTR_SIZE);
 	bpt->type = BP_POKE_BREAKPOINT;
 
 	return err;
@@ -778,22 +772,17 @@ int kgdb_arch_set_breakpoint(struct kgdb_bkpt *bpt)
 
 int kgdb_arch_remove_breakpoint(struct kgdb_bkpt *bpt)
 {
-	int err;
-	char opc[BREAK_INSTR_SIZE];
-
 	if (bpt->type != BP_POKE_BREAKPOINT)
 		goto knl_write;
 	/*
-	 * It is safe to call text_poke() because normal kernel execution
+	 * It is safe to call text_poke_kgdb() because normal kernel execution
 	 * is stopped on all cores, so long as the text_mutex is not locked.
 	 */
 	if (mutex_is_locked(&text_mutex))
 		goto knl_write;
-	text_poke((void *)bpt->bpt_addr, bpt->saved_instr, BREAK_INSTR_SIZE);
-	err = probe_kernel_read(opc, (char *)bpt->bpt_addr, BREAK_INSTR_SIZE);
-	if (err || memcmp(opc, bpt->saved_instr, BREAK_INSTR_SIZE))
-		goto knl_write;
-	return err;
+	text_poke_kgdb((void *)bpt->bpt_addr, bpt->saved_instr,
+		       BREAK_INSTR_SIZE);
+	return 0;
 
 knl_write:
 	return probe_kernel_write((char *)bpt->bpt_addr,
diff --git a/arch/x86/kernel/kprobes/core.c b/arch/x86/kernel/kprobes/core.c
index a034cb808e7e..cf52ee0d8711 100644
--- a/arch/x86/kernel/kprobes/core.c
+++ b/arch/x86/kernel/kprobes/core.c
@@ -431,8 +431,21 @@ void *alloc_insn_page(void)
 	void *page;
 
 	page = module_alloc(PAGE_SIZE);
-	if (page)
-		set_memory_ro((unsigned long)page & PAGE_MASK, 1);
+	if (!page)
+		return NULL;
+
+	set_vm_flush_reset_perms(page);
+	/*
+	 * First make the page read-only, and only then make it executable to
+	 * prevent it from being W+X in between.
+	 */
+	set_memory_ro((unsigned long)page, 1);
+
+	/*
+	 * TODO: Once additional kernel code protection mechanisms are set, ensure
+	 * that the page was not maliciously altered and it is still zeroed.
+	 */
+	set_memory_x((unsigned long)page, 1);
 
 	return page;
 }
@@ -440,8 +453,6 @@ void *alloc_insn_page(void)
 /* Recover page to RW mode before releasing it */
 void free_insn_page(void *page)
 {
-	set_memory_nx((unsigned long)page & PAGE_MASK, 1);
-	set_memory_rw((unsigned long)page & PAGE_MASK, 1);
 	module_memfree(page);
 }
 
@@ -569,6 +580,7 @@ void arch_prepare_kretprobe(struct kretprobe_instance *ri, struct pt_regs *regs)
 	unsigned long *sara = stack_addr(regs);
 
 	ri->ret_addr = (kprobe_opcode_t *) *sara;
+	ri->fp = sara;
 
 	/* Replace the return addr with trampoline addr */
 	*sara = (unsigned long) &kretprobe_trampoline;
@@ -715,6 +727,7 @@ NOKPROBE_SYMBOL(kprobe_int3_handler);
  * calls trampoline_handler() runs, which calls the kretprobe's handler.
  */
 asm(
+	".text\n"
 	".global kretprobe_trampoline\n"
 	".type kretprobe_trampoline, @function\n"
 	"kretprobe_trampoline:\n"
@@ -748,26 +761,48 @@ asm(
 NOKPROBE_SYMBOL(kretprobe_trampoline);
 STACK_FRAME_NON_STANDARD(kretprobe_trampoline);
 
+static struct kprobe kretprobe_kprobe = {
+	.addr = (void *)kretprobe_trampoline,
+};
+
 /*
  * Called from kretprobe_trampoline
  */
 static __used void *trampoline_handler(struct pt_regs *regs)
 {
+	struct kprobe_ctlblk *kcb;
 	struct kretprobe_instance *ri = NULL;
 	struct hlist_head *head, empty_rp;
 	struct hlist_node *tmp;
 	unsigned long flags, orig_ret_address = 0;
 	unsigned long trampoline_address = (unsigned long)&kretprobe_trampoline;
 	kprobe_opcode_t *correct_ret_addr = NULL;
+	void *frame_pointer;
+	bool skipped = false;
+
+	preempt_disable();
+
+	/*
+	 * Set a dummy kprobe for avoiding kretprobe recursion.
+	 * Since kretprobe never run in kprobe handler, kprobe must not
+	 * be running at this point.
+	 */
+	kcb = get_kprobe_ctlblk();
+	__this_cpu_write(current_kprobe, &kretprobe_kprobe);
+	kcb->kprobe_status = KPROBE_HIT_ACTIVE;
 
 	INIT_HLIST_HEAD(&empty_rp);
 	kretprobe_hash_lock(current, &head, &flags);
 	/* fixup registers */
 #ifdef CONFIG_X86_64
 	regs->cs = __KERNEL_CS;
+	/* On x86-64, we use pt_regs->sp for return address holder. */
+	frame_pointer = &regs->sp;
 #else
 	regs->cs = __KERNEL_CS | get_kernel_rpl();
 	regs->gs = 0;
+	/* On x86-32, we use pt_regs->flags for return address holder. */
+	frame_pointer = &regs->flags;
 #endif
 	regs->ip = trampoline_address;
 	regs->orig_ax = ~0UL;
@@ -789,8 +824,25 @@ static __used void *trampoline_handler(struct pt_regs *regs)
 		if (ri->task != current)
 			/* another task is sharing our hash bucket */
 			continue;
+		/*
+		 * Return probes must be pushed on this hash list correct
+		 * order (same as return order) so that it can be poped
+		 * correctly. However, if we find it is pushed it incorrect
+		 * order, this means we find a function which should not be
+		 * probed, because the wrong order entry is pushed on the
+		 * path of processing other kretprobe itself.
+		 */
+		if (ri->fp != frame_pointer) {
+			if (!skipped)
+				pr_warn("kretprobe is stacked incorrectly. Trying to fixup.\n");
+			skipped = true;
+			continue;
+		}
 
 		orig_ret_address = (unsigned long)ri->ret_addr;
+		if (skipped)
+			pr_warn("%ps must be blacklisted because of incorrect kretprobe order\n",
+				ri->rp->kp.addr);
 
 		if (orig_ret_address != trampoline_address)
 			/*
@@ -808,14 +860,15 @@ static __used void *trampoline_handler(struct pt_regs *regs)
 		if (ri->task != current)
 			/* another task is sharing our hash bucket */
 			continue;
+		if (ri->fp != frame_pointer)
+			continue;
 
 		orig_ret_address = (unsigned long)ri->ret_addr;
 		if (ri->rp && ri->rp->handler) {
 			__this_cpu_write(current_kprobe, &ri->rp->kp);
-			get_kprobe_ctlblk()->kprobe_status = KPROBE_HIT_ACTIVE;
 			ri->ret_addr = correct_ret_addr;
 			ri->rp->handler(ri, regs);
-			__this_cpu_write(current_kprobe, NULL);
+			__this_cpu_write(current_kprobe, &kretprobe_kprobe);
 		}
 
 		recycle_rp_inst(ri, &empty_rp);
@@ -831,6 +884,9 @@ static __used void *trampoline_handler(struct pt_regs *regs)
 
 	kretprobe_hash_unlock(current, &flags);
 
+	__this_cpu_write(current_kprobe, NULL);
+	preempt_enable();
+
 	hlist_for_each_entry_safe(ri, tmp, &empty_rp, hlist) {
 		hlist_del(&ri->hlist);
 		kfree(ri);
diff --git a/arch/x86/kernel/kvm.c b/arch/x86/kernel/kvm.c
index 5c93a65ee1e5..3f0cc828cc36 100644
--- a/arch/x86/kernel/kvm.c
+++ b/arch/x86/kernel/kvm.c
@@ -67,7 +67,7 @@ static int __init parse_no_stealacc(char *arg)
 early_param("no-steal-acc", parse_no_stealacc);
 
 static DEFINE_PER_CPU_DECRYPTED(struct kvm_vcpu_pv_apf_data, apf_reason) __aligned(64);
-static DEFINE_PER_CPU_DECRYPTED(struct kvm_steal_time, steal_time) __aligned(64);
+DEFINE_PER_CPU_DECRYPTED(struct kvm_steal_time, steal_time) __aligned(64) __visible;
 static int has_steal_clock = 0;
 
 /*
diff --git a/arch/x86/kernel/ldt.c b/arch/x86/kernel/ldt.c
index 6135ae8ce036..b2463fcb20a8 100644
--- a/arch/x86/kernel/ldt.c
+++ b/arch/x86/kernel/ldt.c
@@ -113,7 +113,7 @@ static void do_sanity_check(struct mm_struct *mm,
 		 * tables.
 		 */
 		WARN_ON(!had_kernel_mapping);
-		if (static_cpu_has(X86_FEATURE_PTI))
+		if (boot_cpu_has(X86_FEATURE_PTI))
 			WARN_ON(!had_user_mapping);
 	} else {
 		/*
@@ -121,7 +121,7 @@ static void do_sanity_check(struct mm_struct *mm,
 		 * Sync the pgd to the usermode tables.
 		 */
 		WARN_ON(had_kernel_mapping);
-		if (static_cpu_has(X86_FEATURE_PTI))
+		if (boot_cpu_has(X86_FEATURE_PTI))
 			WARN_ON(had_user_mapping);
 	}
 }
@@ -156,7 +156,7 @@ static void map_ldt_struct_to_user(struct mm_struct *mm)
 	k_pmd = pgd_to_pmd_walk(k_pgd, LDT_BASE_ADDR);
 	u_pmd = pgd_to_pmd_walk(u_pgd, LDT_BASE_ADDR);
 
-	if (static_cpu_has(X86_FEATURE_PTI) && !mm->context.ldt)
+	if (boot_cpu_has(X86_FEATURE_PTI) && !mm->context.ldt)
 		set_pmd(u_pmd, *k_pmd);
 }
 
@@ -181,7 +181,7 @@ static void map_ldt_struct_to_user(struct mm_struct *mm)
 {
 	pgd_t *pgd = pgd_offset(mm, LDT_BASE_ADDR);
 
-	if (static_cpu_has(X86_FEATURE_PTI) && !mm->context.ldt)
+	if (boot_cpu_has(X86_FEATURE_PTI) && !mm->context.ldt)
 		set_pgd(kernel_to_user_pgdp(pgd), *pgd);
 }
 
@@ -208,7 +208,7 @@ map_ldt_struct(struct mm_struct *mm, struct ldt_struct *ldt, int slot)
 	spinlock_t *ptl;
 	int i, nr_pages;
 
-	if (!static_cpu_has(X86_FEATURE_PTI))
+	if (!boot_cpu_has(X86_FEATURE_PTI))
 		return 0;
 
 	/*
@@ -271,7 +271,7 @@ static void unmap_ldt_struct(struct mm_struct *mm, struct ldt_struct *ldt)
 		return;
 
 	/* LDT map/unmap is only required for PTI */
-	if (!static_cpu_has(X86_FEATURE_PTI))
+	if (!boot_cpu_has(X86_FEATURE_PTI))
 		return;
 
 	nr_pages = DIV_ROUND_UP(ldt->nr_entries * LDT_ENTRY_SIZE, PAGE_SIZE);
@@ -311,7 +311,7 @@ static void free_ldt_pgtables(struct mm_struct *mm)
 	unsigned long start = LDT_BASE_ADDR;
 	unsigned long end = LDT_END_ADDR;
 
-	if (!static_cpu_has(X86_FEATURE_PTI))
+	if (!boot_cpu_has(X86_FEATURE_PTI))
 		return;
 
 	tlb_gather_mmu(&tlb, mm, start, end);
diff --git a/arch/x86/kernel/module.c b/arch/x86/kernel/module.c
index b052e883dd8c..cfa3106faee4 100644
--- a/arch/x86/kernel/module.c
+++ b/arch/x86/kernel/module.c
@@ -87,7 +87,7 @@ void *module_alloc(unsigned long size)
 	p = __vmalloc_node_range(size, MODULE_ALIGN,
 				    MODULES_VADDR + get_module_load_offset(),
 				    MODULES_END, GFP_KERNEL,
-				    PAGE_KERNEL_EXEC, 0, NUMA_NO_NODE,
+				    PAGE_KERNEL, 0, NUMA_NO_NODE,
 				    __builtin_return_address(0));
 	if (p && (kasan_module_alloc(p, size) < 0)) {
 		vfree(p);
diff --git a/arch/x86/kernel/nmi.c b/arch/x86/kernel/nmi.c
index 18bc9b51ac9b..3755d0310026 100644
--- a/arch/x86/kernel/nmi.c
+++ b/arch/x86/kernel/nmi.c
@@ -21,13 +21,14 @@
 #include <linux/ratelimit.h>
 #include <linux/slab.h>
 #include <linux/export.h>
+#include <linux/atomic.h>
 #include <linux/sched/clock.h>
 
 #if defined(CONFIG_EDAC)
 #include <linux/edac.h>
 #endif
 
-#include <linux/atomic.h>
+#include <asm/cpu_entry_area.h>
 #include <asm/traps.h>
 #include <asm/mach_traps.h>
 #include <asm/nmi.h>
@@ -487,6 +488,23 @@ static DEFINE_PER_CPU(unsigned long, nmi_cr2);
  * switch back to the original IDT.
  */
 static DEFINE_PER_CPU(int, update_debug_stack);
+
+static bool notrace is_debug_stack(unsigned long addr)
+{
+	struct cea_exception_stacks *cs = __this_cpu_read(cea_exception_stacks);
+	unsigned long top = CEA_ESTACK_TOP(cs, DB);
+	unsigned long bot = CEA_ESTACK_BOT(cs, DB1);
+
+	if (__this_cpu_read(debug_stack_usage))
+		return true;
+	/*
+	 * Note, this covers the guard page between DB and DB1 as well to
+	 * avoid two checks. But by all means @addr can never point into
+	 * the guard page.
+	 */
+	return addr >= bot && addr < top;
+}
+NOKPROBE_SYMBOL(is_debug_stack);
 #endif
 
 dotraplinkage notrace void
diff --git a/arch/x86/kernel/paravirt.c b/arch/x86/kernel/paravirt.c
index c0e0101133f3..7bbaa6baf37f 100644
--- a/arch/x86/kernel/paravirt.c
+++ b/arch/x86/kernel/paravirt.c
@@ -121,7 +121,7 @@ DEFINE_STATIC_KEY_TRUE(virt_spin_lock_key);
 
 void __init native_pv_lock_init(void)
 {
-	if (!static_cpu_has(X86_FEATURE_HYPERVISOR))
+	if (!boot_cpu_has(X86_FEATURE_HYPERVISOR))
 		static_branch_disable(&virt_spin_lock_key);
 }
 
diff --git a/arch/x86/kernel/perf_regs.c b/arch/x86/kernel/perf_regs.c
index c06c4c16c6b6..07c30ee17425 100644
--- a/arch/x86/kernel/perf_regs.c
+++ b/arch/x86/kernel/perf_regs.c
@@ -59,18 +59,34 @@ static unsigned int pt_regs_offset[PERF_REG_X86_MAX] = {
 
 u64 perf_reg_value(struct pt_regs *regs, int idx)
 {
+	struct x86_perf_regs *perf_regs;
+
+	if (idx >= PERF_REG_X86_XMM0 && idx < PERF_REG_X86_XMM_MAX) {
+		perf_regs = container_of(regs, struct x86_perf_regs, regs);
+		if (!perf_regs->xmm_regs)
+			return 0;
+		return perf_regs->xmm_regs[idx - PERF_REG_X86_XMM0];
+	}
+
 	if (WARN_ON_ONCE(idx >= ARRAY_SIZE(pt_regs_offset)))
 		return 0;
 
 	return regs_get_register(regs, pt_regs_offset[idx]);
 }
 
-#define REG_RESERVED (~((1ULL << PERF_REG_X86_MAX) - 1ULL))
-
 #ifdef CONFIG_X86_32
+#define REG_NOSUPPORT ((1ULL << PERF_REG_X86_R8) | \
+		       (1ULL << PERF_REG_X86_R9) | \
+		       (1ULL << PERF_REG_X86_R10) | \
+		       (1ULL << PERF_REG_X86_R11) | \
+		       (1ULL << PERF_REG_X86_R12) | \
+		       (1ULL << PERF_REG_X86_R13) | \
+		       (1ULL << PERF_REG_X86_R14) | \
+		       (1ULL << PERF_REG_X86_R15))
+
 int perf_reg_validate(u64 mask)
 {
-	if (!mask || mask & REG_RESERVED)
+	if (!mask || (mask & REG_NOSUPPORT))
 		return -EINVAL;
 
 	return 0;
@@ -96,10 +112,7 @@ void perf_get_regs_user(struct perf_regs *regs_user,
 
 int perf_reg_validate(u64 mask)
 {
-	if (!mask || mask & REG_RESERVED)
-		return -EINVAL;
-
-	if (mask & REG_NOSUPPORT)
+	if (!mask || (mask & REG_NOSUPPORT))
 		return -EINVAL;
 
 	return 0;
diff --git a/arch/x86/kernel/process.c b/arch/x86/kernel/process.c
index 58ac7be52c7a..d1d312d012a6 100644
--- a/arch/x86/kernel/process.c
+++ b/arch/x86/kernel/process.c
@@ -236,7 +236,7 @@ static int get_cpuid_mode(void)
 
 static int set_cpuid_mode(struct task_struct *task, unsigned long cpuid_enabled)
 {
-	if (!static_cpu_has(X86_FEATURE_CPUID_FAULT))
+	if (!boot_cpu_has(X86_FEATURE_CPUID_FAULT))
 		return -ENODEV;
 
 	if (cpuid_enabled)
@@ -426,6 +426,8 @@ static __always_inline void __speculation_ctrl_update(unsigned long tifp,
 	u64 msr = x86_spec_ctrl_base;
 	bool updmsr = false;
 
+	lockdep_assert_irqs_disabled();
+
 	/*
 	 * If TIF_SSBD is different, select the proper mitigation
 	 * method. Note that if SSBD mitigation is disabled or permanentely
@@ -477,10 +479,12 @@ static unsigned long speculation_ctrl_update_tif(struct task_struct *tsk)
 
 void speculation_ctrl_update(unsigned long tif)
 {
+	unsigned long flags;
+
 	/* Forced update. Make sure all relevant TIF flags are different */
-	preempt_disable();
+	local_irq_save(flags);
 	__speculation_ctrl_update(~tif, tif);
-	preempt_enable();
+	local_irq_restore(flags);
 }
 
 /* Called from seccomp/prctl update */
@@ -666,7 +670,7 @@ static int prefer_mwait_c1_over_halt(const struct cpuinfo_x86 *c)
 	if (c->x86_vendor != X86_VENDOR_INTEL)
 		return 0;
 
-	if (!cpu_has(c, X86_FEATURE_MWAIT) || static_cpu_has_bug(X86_BUG_MONITOR))
+	if (!cpu_has(c, X86_FEATURE_MWAIT) || boot_cpu_has_bug(X86_BUG_MONITOR))
 		return 0;
 
 	return 1;
diff --git a/arch/x86/kernel/process_32.c b/arch/x86/kernel/process_32.c
index e471d8e6f0b2..70933193878c 100644
--- a/arch/x86/kernel/process_32.c
+++ b/arch/x86/kernel/process_32.c
@@ -127,6 +127,13 @@ int copy_thread_tls(unsigned long clone_flags, unsigned long sp,
 	struct task_struct *tsk;
 	int err;
 
+	/*
+	 * For a new task use the RESET flags value since there is no before.
+	 * All the status flags are zero; DF and all the system flags must also
+	 * be 0, specifically IF must be 0 because we context switch to the new
+	 * task with interrupts disabled.
+	 */
+	frame->flags = X86_EFLAGS_FIXED;
 	frame->bp = 0;
 	frame->ret_addr = (unsigned long) ret_from_fork;
 	p->thread.sp = (unsigned long) fork_frame;
diff --git a/arch/x86/kernel/process_64.c b/arch/x86/kernel/process_64.c
index 6a62f4af9fcf..844a28b29967 100644
--- a/arch/x86/kernel/process_64.c
+++ b/arch/x86/kernel/process_64.c
@@ -392,6 +392,7 @@ int copy_thread_tls(unsigned long clone_flags, unsigned long sp,
 	childregs = task_pt_regs(p);
 	fork_frame = container_of(childregs, struct fork_frame, regs);
 	frame = &fork_frame->frame;
+
 	frame->bp = 0;
 	frame->ret_addr = (unsigned long) ret_from_fork;
 	p->thread.sp = (unsigned long) fork_frame;
diff --git a/arch/x86/kernel/reboot.c b/arch/x86/kernel/reboot.c
index 725624b6c0c0..09d6bded3c1e 100644
--- a/arch/x86/kernel/reboot.c
+++ b/arch/x86/kernel/reboot.c
@@ -81,6 +81,19 @@ static int __init set_bios_reboot(const struct dmi_system_id *d)
 	return 0;
 }
 
+/*
+ * Some machines don't handle the default ACPI reboot method and
+ * require the EFI reboot method:
+ */
+static int __init set_efi_reboot(const struct dmi_system_id *d)
+{
+	if (reboot_type != BOOT_EFI && !efi_runtime_disabled()) {
+		reboot_type = BOOT_EFI;
+		pr_info("%s series board detected. Selecting EFI-method for reboot.\n", d->ident);
+	}
+	return 0;
+}
+
 void __noreturn machine_real_restart(unsigned int type)
 {
 	local_irq_disable();
@@ -108,7 +121,7 @@ void __noreturn machine_real_restart(unsigned int type)
 	write_cr3(real_mode_header->trampoline_pgd);
 
 	/* Exiting long mode will fail if CR4.PCIDE is set. */
-	if (static_cpu_has(X86_FEATURE_PCID))
+	if (boot_cpu_has(X86_FEATURE_PCID))
 		cr4_clear_bits(X86_CR4_PCIDE);
 #endif
 
@@ -166,6 +179,14 @@ static const struct dmi_system_id reboot_dmi_table[] __initconst = {
 			DMI_MATCH(DMI_PRODUCT_NAME, "AOA110"),
 		},
 	},
+	{	/* Handle reboot issue on Acer TravelMate X514-51T */
+		.callback = set_efi_reboot,
+		.ident = "Acer TravelMate X514-51T",
+		.matches = {
+			DMI_MATCH(DMI_SYS_VENDOR, "Acer"),
+			DMI_MATCH(DMI_PRODUCT_NAME, "TravelMate X514-51T"),
+		},
+	},
 
 	/* Apple */
 	{	/* Handle problems with rebooting on Apple MacBook5 */
diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c
index 3d872a527cd9..905dae880563 100644
--- a/arch/x86/kernel/setup.c
+++ b/arch/x86/kernel/setup.c
@@ -71,6 +71,7 @@
 #include <linux/tboot.h>
 #include <linux/jiffies.h>
 #include <linux/mem_encrypt.h>
+#include <linux/sizes.h>
 
 #include <linux/usb/xhci-dbgp.h>
 #include <video/edid.h>
@@ -448,18 +449,17 @@ static void __init memblock_x86_reserve_range_setup_data(void)
 #ifdef CONFIG_KEXEC_CORE
 
 /* 16M alignment for crash kernel regions */
-#define CRASH_ALIGN		(16 << 20)
+#define CRASH_ALIGN		SZ_16M
 
 /*
  * Keep the crash kernel below this limit.  On 32 bits earlier kernels
  * would limit the kernel to the low 512 MiB due to mapping restrictions.
- * On 64bit, old kexec-tools need to under 896MiB.
  */
 #ifdef CONFIG_X86_32
-# define CRASH_ADDR_LOW_MAX	(512 << 20)
-# define CRASH_ADDR_HIGH_MAX	(512 << 20)
+# define CRASH_ADDR_LOW_MAX	SZ_512M
+# define CRASH_ADDR_HIGH_MAX	SZ_512M
 #else
-# define CRASH_ADDR_LOW_MAX	(896UL << 20)
+# define CRASH_ADDR_LOW_MAX	SZ_4G
 # define CRASH_ADDR_HIGH_MAX	MAXMEM
 #endif
 
@@ -541,21 +541,27 @@ static void __init reserve_crashkernel(void)
 	}
 
 	/* 0 means: find the address automatically */
-	if (crash_base <= 0) {
+	if (!crash_base) {
 		/*
 		 * Set CRASH_ADDR_LOW_MAX upper bound for crash memory,
-		 * as old kexec-tools loads bzImage below that, unless
-		 * "crashkernel=size[KMG],high" is specified.
+		 * crashkernel=x,high reserves memory over 4G, also allocates
+		 * 256M extra low memory for DMA buffers and swiotlb.
+		 * But the extra memory is not required for all machines.
+		 * So try low memory first and fall back to high memory
+		 * unless "crashkernel=size[KMG],high" is specified.
 		 */
-		crash_base = memblock_find_in_range(CRASH_ALIGN,
-						    high ? CRASH_ADDR_HIGH_MAX
-							 : CRASH_ADDR_LOW_MAX,
-						    crash_size, CRASH_ALIGN);
+		if (!high)
+			crash_base = memblock_find_in_range(CRASH_ALIGN,
+						CRASH_ADDR_LOW_MAX,
+						crash_size, CRASH_ALIGN);
+		if (!crash_base)
+			crash_base = memblock_find_in_range(CRASH_ALIGN,
+						CRASH_ADDR_HIGH_MAX,
+						crash_size, CRASH_ALIGN);
 		if (!crash_base) {
 			pr_info("crashkernel reservation failed - No suitable area found.\n");
 			return;
 		}
-
 	} else {
 		unsigned long long start;
 
@@ -1005,13 +1011,11 @@ void __init setup_arch(char **cmdline_p)
 	if (efi_enabled(EFI_BOOT))
 		efi_init();
 
-	dmi_scan_machine();
-	dmi_memdev_walk();
-	dmi_set_dump_stack_arch_desc();
+	dmi_setup();
 
 	/*
 	 * VMware detection requires dmi to be available, so this
-	 * needs to be done after dmi_scan_machine(), for the boot CPU.
+	 * needs to be done after dmi_setup(), for the boot CPU.
 	 */
 	init_hypervisor_platform();
 
diff --git a/arch/x86/kernel/setup_percpu.c b/arch/x86/kernel/setup_percpu.c
index 4bf46575568a..86663874ef04 100644
--- a/arch/x86/kernel/setup_percpu.c
+++ b/arch/x86/kernel/setup_percpu.c
@@ -244,11 +244,6 @@ void __init setup_per_cpu_areas(void)
 		per_cpu(x86_cpu_to_logical_apicid, cpu) =
 			early_per_cpu_map(x86_cpu_to_logical_apicid, cpu);
 #endif
-#ifdef CONFIG_X86_64
-		per_cpu(irq_stack_ptr, cpu) =
-			per_cpu(irq_stack_union.irq_stack, cpu) +
-			IRQ_STACK_SIZE;
-#endif
 #ifdef CONFIG_NUMA
 		per_cpu(x86_cpu_to_node_map, cpu) =
 			early_per_cpu_map(x86_cpu_to_node_map, cpu);
diff --git a/arch/x86/kernel/signal.c b/arch/x86/kernel/signal.c
index 08dfd4c1a4f9..dff90fb6a9af 100644
--- a/arch/x86/kernel/signal.c
+++ b/arch/x86/kernel/signal.c
@@ -132,16 +132,6 @@ static int restore_sigcontext(struct pt_regs *regs,
 		COPY_SEG_CPL3(cs);
 		COPY_SEG_CPL3(ss);
 
-#ifdef CONFIG_X86_64
-		/*
-		 * Fix up SS if needed for the benefit of old DOSEMU and
-		 * CRIU.
-		 */
-		if (unlikely(!(uc_flags & UC_STRICT_RESTORE_SS) &&
-			     user_64bit_mode(regs)))
-			force_valid_ss(regs);
-#endif
-
 		get_user_ex(tmpflags, &sc->flags);
 		regs->flags = (regs->flags & ~FIX_EFLAGS) | (tmpflags & FIX_EFLAGS);
 		regs->orig_ax = -1;		/* disable syscall checks */
@@ -150,6 +140,15 @@ static int restore_sigcontext(struct pt_regs *regs,
 		buf = (void __user *)buf_val;
 	} get_user_catch(err);
 
+#ifdef CONFIG_X86_64
+	/*
+	 * Fix up SS if needed for the benefit of old DOSEMU and
+	 * CRIU.
+	 */
+	if (unlikely(!(uc_flags & UC_STRICT_RESTORE_SS) && user_64bit_mode(regs)))
+		force_valid_ss(regs);
+#endif
+
 	err |= fpu__restore_sig(buf, IS_ENABLED(CONFIG_X86_32));
 
 	force_iret();
@@ -461,6 +460,7 @@ static int __setup_rt_frame(int sig, struct ksignal *ksig,
 {
 	struct rt_sigframe __user *frame;
 	void __user *fp = NULL;
+	unsigned long uc_flags;
 	int err = 0;
 
 	frame = get_sigframe(&ksig->ka, regs, sizeof(struct rt_sigframe), &fp);
@@ -473,9 +473,11 @@ static int __setup_rt_frame(int sig, struct ksignal *ksig,
 			return -EFAULT;
 	}
 
+	uc_flags = frame_uc_flags(regs);
+
 	put_user_try {
 		/* Create the ucontext.  */
-		put_user_ex(frame_uc_flags(regs), &frame->uc.uc_flags);
+		put_user_ex(uc_flags, &frame->uc.uc_flags);
 		put_user_ex(0, &frame->uc.uc_link);
 		save_altstack_ex(&frame->uc.uc_stack, regs->sp);
 
@@ -541,6 +543,7 @@ static int x32_setup_rt_frame(struct ksignal *ksig,
 {
 #ifdef CONFIG_X86_X32_ABI
 	struct rt_sigframe_x32 __user *frame;
+	unsigned long uc_flags;
 	void __user *restorer;
 	int err = 0;
 	void __user *fpstate = NULL;
@@ -555,9 +558,11 @@ static int x32_setup_rt_frame(struct ksignal *ksig,
 			return -EFAULT;
 	}
 
+	uc_flags = frame_uc_flags(regs);
+
 	put_user_try {
 		/* Create the ucontext.  */
-		put_user_ex(frame_uc_flags(regs), &frame->uc.uc_flags);
+		put_user_ex(uc_flags, &frame->uc.uc_flags);
 		put_user_ex(0, &frame->uc.uc_link);
 		compat_save_altstack_ex(&frame->uc.uc_stack, regs->sp);
 		put_user_ex(0, &frame->uc.uc__pad0);
@@ -688,10 +693,7 @@ setup_rt_frame(struct ksignal *ksig, struct pt_regs *regs)
 	sigset_t *set = sigmask_to_save();
 	compat_sigset_t *cset = (compat_sigset_t *) set;
 
-	/*
-	 * Increment event counter and perform fixup for the pre-signal
-	 * frame.
-	 */
+	/* Perform fixup for the pre-signal frame. */
 	rseq_signal_deliver(ksig, regs);
 
 	/* Set up the stack frame */
diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c
index ce1a67b70168..73e69aaaa117 100644
--- a/arch/x86/kernel/smpboot.c
+++ b/arch/x86/kernel/smpboot.c
@@ -455,7 +455,7 @@ static bool match_llc(struct cpuinfo_x86 *c, struct cpuinfo_x86 *o)
  * multicore group inside a NUMA node.  If this happens, we will
  * discard the MC level of the topology later.
  */
-static bool match_die(struct cpuinfo_x86 *c, struct cpuinfo_x86 *o)
+static bool match_pkg(struct cpuinfo_x86 *c, struct cpuinfo_x86 *o)
 {
 	if (c->phys_proc_id == o->phys_proc_id)
 		return true;
@@ -546,7 +546,7 @@ void set_cpu_sibling_map(int cpu)
 	for_each_cpu(i, cpu_sibling_setup_mask) {
 		o = &cpu_data(i);
 
-		if ((i == cpu) || (has_mp && match_die(c, o))) {
+		if ((i == cpu) || (has_mp && match_pkg(c, o))) {
 			link_mask(topology_core_cpumask, cpu, i);
 
 			/*
@@ -570,7 +570,7 @@ void set_cpu_sibling_map(int cpu)
 			} else if (i != cpu && !c->booted_cores)
 				c->booted_cores = cpu_data(i).booted_cores;
 		}
-		if (match_die(c, o) && !topology_same_node(c, o))
+		if (match_pkg(c, o) && !topology_same_node(c, o))
 			x86_has_numa_in_package = true;
 	}
 
@@ -935,20 +935,27 @@ out:
 	return boot_error;
 }
 
-void common_cpu_up(unsigned int cpu, struct task_struct *idle)
+int common_cpu_up(unsigned int cpu, struct task_struct *idle)
 {
+	int ret;
+
 	/* Just in case we booted with a single CPU. */
 	alternatives_enable_smp();
 
 	per_cpu(current_task, cpu) = idle;
 
+	/* Initialize the interrupt stack(s) */
+	ret = irq_init_percpu_irqstack(cpu);
+	if (ret)
+		return ret;
+
 #ifdef CONFIG_X86_32
 	/* Stack for startup_32 can be just as for start_secondary onwards */
-	irq_ctx_init(cpu);
 	per_cpu(cpu_current_top_of_stack, cpu) = task_top_of_stack(idle);
 #else
 	initial_gs = per_cpu_offset(cpu);
 #endif
+	return 0;
 }
 
 /*
@@ -1106,7 +1113,9 @@ int native_cpu_up(unsigned int cpu, struct task_struct *tidle)
 	/* the FPU context is blank, nobody can own it */
 	per_cpu(fpu_fpregs_owner_ctx, cpu) = NULL;
 
-	common_cpu_up(cpu, tidle);
+	err = common_cpu_up(cpu, tidle);
+	if (err)
+		return err;
 
 	err = do_boot_cpu(apicid, cpu, tidle, &cpu0_nmi_registered);
 	if (err) {
diff --git a/arch/x86/kernel/stacktrace.c b/arch/x86/kernel/stacktrace.c
index 5c2d71a1dc06..2abf27d7df6b 100644
--- a/arch/x86/kernel/stacktrace.c
+++ b/arch/x86/kernel/stacktrace.c
@@ -12,78 +12,31 @@
 #include <asm/stacktrace.h>
 #include <asm/unwind.h>
 
-static int save_stack_address(struct stack_trace *trace, unsigned long addr,
-			      bool nosched)
-{
-	if (nosched && in_sched_functions(addr))
-		return 0;
-
-	if (trace->skip > 0) {
-		trace->skip--;
-		return 0;
-	}
-
-	if (trace->nr_entries >= trace->max_entries)
-		return -1;
-
-	trace->entries[trace->nr_entries++] = addr;
-	return 0;
-}
-
-static void noinline __save_stack_trace(struct stack_trace *trace,
-			       struct task_struct *task, struct pt_regs *regs,
-			       bool nosched)
+void arch_stack_walk(stack_trace_consume_fn consume_entry, void *cookie,
+		     struct task_struct *task, struct pt_regs *regs)
 {
 	struct unwind_state state;
 	unsigned long addr;
 
-	if (regs)
-		save_stack_address(trace, regs->ip, nosched);
+	if (regs && !consume_entry(cookie, regs->ip, false))
+		return;
 
 	for (unwind_start(&state, task, regs, NULL); !unwind_done(&state);
 	     unwind_next_frame(&state)) {
 		addr = unwind_get_return_address(&state);
-		if (!addr || save_stack_address(trace, addr, nosched))
+		if (!addr || !consume_entry(cookie, addr, false))
 			break;
 	}
-
-	if (trace->nr_entries < trace->max_entries)
-		trace->entries[trace->nr_entries++] = ULONG_MAX;
 }
 
 /*
- * Save stack-backtrace addresses into a stack_trace buffer.
+ * This function returns an error if it detects any unreliable features of the
+ * stack.  Otherwise it guarantees that the stack trace is reliable.
+ *
+ * If the task is not 'current', the caller *must* ensure the task is inactive.
  */
-void save_stack_trace(struct stack_trace *trace)
-{
-	trace->skip++;
-	__save_stack_trace(trace, current, NULL, false);
-}
-EXPORT_SYMBOL_GPL(save_stack_trace);
-
-void save_stack_trace_regs(struct pt_regs *regs, struct stack_trace *trace)
-{
-	__save_stack_trace(trace, current, regs, false);
-}
-
-void save_stack_trace_tsk(struct task_struct *tsk, struct stack_trace *trace)
-{
-	if (!try_get_task_stack(tsk))
-		return;
-
-	if (tsk == current)
-		trace->skip++;
-	__save_stack_trace(trace, tsk, NULL, true);
-
-	put_task_stack(tsk);
-}
-EXPORT_SYMBOL_GPL(save_stack_trace_tsk);
-
-#ifdef CONFIG_HAVE_RELIABLE_STACKTRACE
-
-static int __always_inline
-__save_stack_trace_reliable(struct stack_trace *trace,
-			    struct task_struct *task)
+int arch_stack_walk_reliable(stack_trace_consume_fn consume_entry,
+			     void *cookie, struct task_struct *task)
 {
 	struct unwind_state state;
 	struct pt_regs *regs;
@@ -97,7 +50,7 @@ __save_stack_trace_reliable(struct stack_trace *trace,
 		if (regs) {
 			/* Success path for user tasks */
 			if (user_mode(regs))
-				goto success;
+				return 0;
 
 			/*
 			 * Kernel mode registers on the stack indicate an
@@ -120,7 +73,7 @@ __save_stack_trace_reliable(struct stack_trace *trace,
 		if (!addr)
 			return -EINVAL;
 
-		if (save_stack_address(trace, addr, false))
+		if (!consume_entry(cookie, addr, false))
 			return -EINVAL;
 	}
 
@@ -132,39 +85,9 @@ __save_stack_trace_reliable(struct stack_trace *trace,
 	if (!(task->flags & (PF_KTHREAD | PF_IDLE)))
 		return -EINVAL;
 
-success:
-	if (trace->nr_entries < trace->max_entries)
-		trace->entries[trace->nr_entries++] = ULONG_MAX;
-
 	return 0;
 }
 
-/*
- * This function returns an error if it detects any unreliable features of the
- * stack.  Otherwise it guarantees that the stack trace is reliable.
- *
- * If the task is not 'current', the caller *must* ensure the task is inactive.
- */
-int save_stack_trace_tsk_reliable(struct task_struct *tsk,
-				  struct stack_trace *trace)
-{
-	int ret;
-
-	/*
-	 * If the task doesn't have a stack (e.g., a zombie), the stack is
-	 * "reliably" empty.
-	 */
-	if (!try_get_task_stack(tsk))
-		return 0;
-
-	ret = __save_stack_trace_reliable(trace, tsk);
-
-	put_task_stack(tsk);
-
-	return ret;
-}
-#endif /* CONFIG_HAVE_RELIABLE_STACKTRACE */
-
 /* Userspace stacktrace - based on kernel/trace/trace_sysprof.c */
 
 struct stack_frame_user {
@@ -189,15 +112,15 @@ copy_stack_frame(const void __user *fp, struct stack_frame_user *frame)
 	return ret;
 }
 
-static inline void __save_stack_trace_user(struct stack_trace *trace)
+void arch_stack_walk_user(stack_trace_consume_fn consume_entry, void *cookie,
+			  const struct pt_regs *regs)
 {
-	const struct pt_regs *regs = task_pt_regs(current);
 	const void __user *fp = (const void __user *)regs->bp;
 
-	if (trace->nr_entries < trace->max_entries)
-		trace->entries[trace->nr_entries++] = regs->ip;
+	if (!consume_entry(cookie, regs->ip, false))
+		return;
 
-	while (trace->nr_entries < trace->max_entries) {
+	while (1) {
 		struct stack_frame_user frame;
 
 		frame.next_fp = NULL;
@@ -207,8 +130,8 @@ static inline void __save_stack_trace_user(struct stack_trace *trace)
 		if ((unsigned long)fp < regs->sp)
 			break;
 		if (frame.ret_addr) {
-			trace->entries[trace->nr_entries++] =
-				frame.ret_addr;
+			if (!consume_entry(cookie, frame.ret_addr, false))
+				return;
 		}
 		if (fp == frame.next_fp)
 			break;
@@ -216,14 +139,3 @@ static inline void __save_stack_trace_user(struct stack_trace *trace)
 	}
 }
 
-void save_stack_trace_user(struct stack_trace *trace)
-{
-	/*
-	 * Trace user stack if we are not a kernel thread
-	 */
-	if (current->mm) {
-		__save_stack_trace_user(trace);
-	}
-	if (trace->nr_entries < trace->max_entries)
-		trace->entries[trace->nr_entries++] = ULONG_MAX;
-}
diff --git a/arch/x86/kernel/topology.c b/arch/x86/kernel/topology.c
index 738bf42b0218..be5bc2e47c71 100644
--- a/arch/x86/kernel/topology.c
+++ b/arch/x86/kernel/topology.c
@@ -71,7 +71,7 @@ int _debug_hotplug_cpu(int cpu, int action)
 	case 0:
 		ret = cpu_down(cpu);
 		if (!ret) {
-			pr_info("CPU %u is now offline\n", cpu);
+			pr_info("DEBUG_HOTPLUG_CPU0: CPU %u is now offline\n", cpu);
 			dev->offline = true;
 			kobject_uevent(&dev->kobj, KOBJ_OFFLINE);
 		} else
diff --git a/arch/x86/kernel/tsc.c b/arch/x86/kernel/tsc.c
index 3fae23834069..15b5e98a86f9 100644
--- a/arch/x86/kernel/tsc.c
+++ b/arch/x86/kernel/tsc.c
@@ -185,8 +185,7 @@ static void __init cyc2ns_init_boot_cpu(void)
 /*
  * Secondary CPUs do not run through tsc_init(), so set up
  * all the scale factors for all CPUs, assuming the same
- * speed as the bootup CPU. (cpufreq notifiers will fix this
- * up if their speed diverges)
+ * speed as the bootup CPU.
  */
 static void __init cyc2ns_init_secondary_cpus(void)
 {
@@ -283,6 +282,7 @@ int __init notsc_setup(char *str)
 __setup("notsc", notsc_setup);
 
 static int no_sched_irq_time;
+static int no_tsc_watchdog;
 
 static int __init tsc_setup(char *str)
 {
@@ -292,6 +292,8 @@ static int __init tsc_setup(char *str)
 		no_sched_irq_time = 1;
 	if (!strcmp(str, "unstable"))
 		mark_tsc_unstable("boot parameter");
+	if (!strcmp(str, "nowatchdog"))
+		no_tsc_watchdog = 1;
 	return 1;
 }
 
@@ -937,12 +939,12 @@ void tsc_restore_sched_clock_state(void)
 }
 
 #ifdef CONFIG_CPU_FREQ
-/* Frequency scaling support. Adjust the TSC based timer when the cpu frequency
+/*
+ * Frequency scaling support. Adjust the TSC based timer when the CPU frequency
  * changes.
  *
- * RED-PEN: On SMP we assume all CPUs run with the same frequency.  It's
- * not that important because current Opteron setups do not support
- * scaling on SMP anyroads.
+ * NOTE: On SMP the situation is not fixable in general, so simply mark the TSC
+ * as unstable and give up in those cases.
  *
  * Should fix up last_tsc too. Currently gettimeofday in the
  * first tick after the change will be slightly wrong.
@@ -956,22 +958,22 @@ static int time_cpufreq_notifier(struct notifier_block *nb, unsigned long val,
 				void *data)
 {
 	struct cpufreq_freqs *freq = data;
-	unsigned long *lpj;
 
-	lpj = &boot_cpu_data.loops_per_jiffy;
-#ifdef CONFIG_SMP
-	if (!(freq->flags & CPUFREQ_CONST_LOOPS))
-		lpj = &cpu_data(freq->cpu).loops_per_jiffy;
-#endif
+	if (num_online_cpus() > 1) {
+		mark_tsc_unstable("cpufreq changes on SMP");
+		return 0;
+	}
 
 	if (!ref_freq) {
 		ref_freq = freq->old;
-		loops_per_jiffy_ref = *lpj;
+		loops_per_jiffy_ref = boot_cpu_data.loops_per_jiffy;
 		tsc_khz_ref = tsc_khz;
 	}
+
 	if ((val == CPUFREQ_PRECHANGE  && freq->old < freq->new) ||
-			(val == CPUFREQ_POSTCHANGE && freq->old > freq->new)) {
-		*lpj = cpufreq_scale(loops_per_jiffy_ref, ref_freq, freq->new);
+	    (val == CPUFREQ_POSTCHANGE && freq->old > freq->new)) {
+		boot_cpu_data.loops_per_jiffy =
+			cpufreq_scale(loops_per_jiffy_ref, ref_freq, freq->new);
 
 		tsc_khz = cpufreq_scale(tsc_khz_ref, ref_freq, freq->new);
 		if (!(freq->flags & CPUFREQ_CONST_LOOPS))
@@ -1349,7 +1351,7 @@ static int __init init_tsc_clocksource(void)
 	if (tsc_unstable)
 		goto unreg;
 
-	if (tsc_clocksource_reliable)
+	if (tsc_clocksource_reliable || no_tsc_watchdog)
 		clocksource_tsc.flags &= ~CLOCK_SOURCE_MUST_VERIFY;
 
 	if (boot_cpu_has(X86_FEATURE_NONSTOP_TSC_S3))
diff --git a/arch/x86/kernel/vm86_32.c b/arch/x86/kernel/vm86_32.c
index a092b6b40c6b..6a38717d179c 100644
--- a/arch/x86/kernel/vm86_32.c
+++ b/arch/x86/kernel/vm86_32.c
@@ -369,7 +369,7 @@ static long do_sys_vm86(struct vm86plus_struct __user *user_vm86, bool plus)
 	preempt_disable();
 	tsk->thread.sp0 += 16;
 
-	if (static_cpu_has(X86_FEATURE_SEP)) {
+	if (boot_cpu_has(X86_FEATURE_SEP)) {
 		tsk->thread.sysenter_cs = 0;
 		refresh_sysenter_cs(&tsk->thread);
 	}
diff --git a/arch/x86/kernel/vmlinux.lds.S b/arch/x86/kernel/vmlinux.lds.S
index bad8c51fee6e..0850b5149345 100644
--- a/arch/x86/kernel/vmlinux.lds.S
+++ b/arch/x86/kernel/vmlinux.lds.S
@@ -141,11 +141,11 @@ SECTIONS
 		*(.text.__x86.indirect_thunk)
 		__indirect_thunk_end = .;
 #endif
-
-		/* End of text section */
-		_etext = .;
 	} :text = 0x9090
 
+	/* End of text section */
+	_etext = .;
+
 	NOTES :text :note
 
 	EXCEPTION_TABLE(16) :text = 0x9090
@@ -362,7 +362,7 @@ SECTIONS
 	.bss : AT(ADDR(.bss) - LOAD_OFFSET) {
 		__bss_start = .;
 		*(.bss..page_aligned)
-		*(.bss)
+		*(BSS_MAIN)
 		BSS_DECRYPTED
 		. = ALIGN(PAGE_SIZE);
 		__bss_stop = .;
@@ -403,7 +403,8 @@ SECTIONS
  */
 #define INIT_PER_CPU(x) init_per_cpu__##x = ABSOLUTE(x) + __per_cpu_load
 INIT_PER_CPU(gdt_page);
-INIT_PER_CPU(irq_stack_union);
+INIT_PER_CPU(fixed_percpu_data);
+INIT_PER_CPU(irq_stack_backing_store);
 
 /*
  * Build-time check on the image size:
@@ -412,8 +413,8 @@ INIT_PER_CPU(irq_stack_union);
 	   "kernel image bigger than KERNEL_IMAGE_SIZE");
 
 #ifdef CONFIG_SMP
-. = ASSERT((irq_stack_union == 0),
-           "irq_stack_union is not at start of per-cpu area");
+. = ASSERT((fixed_percpu_data == 0),
+           "fixed_percpu_data is not at start of per-cpu area");
 #endif
 
 #endif /* CONFIG_X86_32 */
diff --git a/arch/x86/kvm/emulate.c b/arch/x86/kvm/emulate.c
index c338984c850d..d0d5dd44b4f4 100644
--- a/arch/x86/kvm/emulate.c
+++ b/arch/x86/kvm/emulate.c
@@ -2331,24 +2331,18 @@ static int em_lseg(struct x86_emulate_ctxt *ctxt)
 
 static int emulator_has_longmode(struct x86_emulate_ctxt *ctxt)
 {
+#ifdef CONFIG_X86_64
 	u32 eax, ebx, ecx, edx;
 
 	eax = 0x80000001;
 	ecx = 0;
 	ctxt->ops->get_cpuid(ctxt, &eax, &ebx, &ecx, &edx, false);
 	return edx & bit(X86_FEATURE_LM);
+#else
+	return false;
+#endif
 }
 
-#define GET_SMSTATE(type, smbase, offset)				  \
-	({								  \
-	 type __val;							  \
-	 int r = ctxt->ops->read_phys(ctxt, smbase + offset, &__val,      \
-				      sizeof(__val));			  \
-	 if (r != X86EMUL_CONTINUE)					  \
-		 return X86EMUL_UNHANDLEABLE;				  \
-	 __val;								  \
-	})
-
 static void rsm_set_desc_flags(struct desc_struct *desc, u32 flags)
 {
 	desc->g    = (flags >> 23) & 1;
@@ -2361,27 +2355,30 @@ static void rsm_set_desc_flags(struct desc_struct *desc, u32 flags)
 	desc->type = (flags >>  8) & 15;
 }
 
-static int rsm_load_seg_32(struct x86_emulate_ctxt *ctxt, u64 smbase, int n)
+static int rsm_load_seg_32(struct x86_emulate_ctxt *ctxt, const char *smstate,
+			   int n)
 {
 	struct desc_struct desc;
 	int offset;
 	u16 selector;
 
-	selector = GET_SMSTATE(u32, smbase, 0x7fa8 + n * 4);
+	selector = GET_SMSTATE(u32, smstate, 0x7fa8 + n * 4);
 
 	if (n < 3)
 		offset = 0x7f84 + n * 12;
 	else
 		offset = 0x7f2c + (n - 3) * 12;
 
-	set_desc_base(&desc,      GET_SMSTATE(u32, smbase, offset + 8));
-	set_desc_limit(&desc,     GET_SMSTATE(u32, smbase, offset + 4));
-	rsm_set_desc_flags(&desc, GET_SMSTATE(u32, smbase, offset));
+	set_desc_base(&desc,      GET_SMSTATE(u32, smstate, offset + 8));
+	set_desc_limit(&desc,     GET_SMSTATE(u32, smstate, offset + 4));
+	rsm_set_desc_flags(&desc, GET_SMSTATE(u32, smstate, offset));
 	ctxt->ops->set_segment(ctxt, selector, &desc, 0, n);
 	return X86EMUL_CONTINUE;
 }
 
-static int rsm_load_seg_64(struct x86_emulate_ctxt *ctxt, u64 smbase, int n)
+#ifdef CONFIG_X86_64
+static int rsm_load_seg_64(struct x86_emulate_ctxt *ctxt, const char *smstate,
+			   int n)
 {
 	struct desc_struct desc;
 	int offset;
@@ -2390,15 +2387,16 @@ static int rsm_load_seg_64(struct x86_emulate_ctxt *ctxt, u64 smbase, int n)
 
 	offset = 0x7e00 + n * 16;
 
-	selector =                GET_SMSTATE(u16, smbase, offset);
-	rsm_set_desc_flags(&desc, GET_SMSTATE(u16, smbase, offset + 2) << 8);
-	set_desc_limit(&desc,     GET_SMSTATE(u32, smbase, offset + 4));
-	set_desc_base(&desc,      GET_SMSTATE(u32, smbase, offset + 8));
-	base3 =                   GET_SMSTATE(u32, smbase, offset + 12);
+	selector =                GET_SMSTATE(u16, smstate, offset);
+	rsm_set_desc_flags(&desc, GET_SMSTATE(u16, smstate, offset + 2) << 8);
+	set_desc_limit(&desc,     GET_SMSTATE(u32, smstate, offset + 4));
+	set_desc_base(&desc,      GET_SMSTATE(u32, smstate, offset + 8));
+	base3 =                   GET_SMSTATE(u32, smstate, offset + 12);
 
 	ctxt->ops->set_segment(ctxt, selector, &desc, base3, n);
 	return X86EMUL_CONTINUE;
 }
+#endif
 
 static int rsm_enter_protected_mode(struct x86_emulate_ctxt *ctxt,
 				    u64 cr0, u64 cr3, u64 cr4)
@@ -2445,7 +2443,8 @@ static int rsm_enter_protected_mode(struct x86_emulate_ctxt *ctxt,
 	return X86EMUL_CONTINUE;
 }
 
-static int rsm_load_state_32(struct x86_emulate_ctxt *ctxt, u64 smbase)
+static int rsm_load_state_32(struct x86_emulate_ctxt *ctxt,
+			     const char *smstate)
 {
 	struct desc_struct desc;
 	struct desc_ptr dt;
@@ -2453,53 +2452,55 @@ static int rsm_load_state_32(struct x86_emulate_ctxt *ctxt, u64 smbase)
 	u32 val, cr0, cr3, cr4;
 	int i;
 
-	cr0 =                      GET_SMSTATE(u32, smbase, 0x7ffc);
-	cr3 =                      GET_SMSTATE(u32, smbase, 0x7ff8);
-	ctxt->eflags =             GET_SMSTATE(u32, smbase, 0x7ff4) | X86_EFLAGS_FIXED;
-	ctxt->_eip =               GET_SMSTATE(u32, smbase, 0x7ff0);
+	cr0 =                      GET_SMSTATE(u32, smstate, 0x7ffc);
+	cr3 =                      GET_SMSTATE(u32, smstate, 0x7ff8);
+	ctxt->eflags =             GET_SMSTATE(u32, smstate, 0x7ff4) | X86_EFLAGS_FIXED;
+	ctxt->_eip =               GET_SMSTATE(u32, smstate, 0x7ff0);
 
 	for (i = 0; i < 8; i++)
-		*reg_write(ctxt, i) = GET_SMSTATE(u32, smbase, 0x7fd0 + i * 4);
+		*reg_write(ctxt, i) = GET_SMSTATE(u32, smstate, 0x7fd0 + i * 4);
 
-	val = GET_SMSTATE(u32, smbase, 0x7fcc);
+	val = GET_SMSTATE(u32, smstate, 0x7fcc);
 	ctxt->ops->set_dr(ctxt, 6, (val & DR6_VOLATILE) | DR6_FIXED_1);
-	val = GET_SMSTATE(u32, smbase, 0x7fc8);
+	val = GET_SMSTATE(u32, smstate, 0x7fc8);
 	ctxt->ops->set_dr(ctxt, 7, (val & DR7_VOLATILE) | DR7_FIXED_1);
 
-	selector =                 GET_SMSTATE(u32, smbase, 0x7fc4);
-	set_desc_base(&desc,       GET_SMSTATE(u32, smbase, 0x7f64));
-	set_desc_limit(&desc,      GET_SMSTATE(u32, smbase, 0x7f60));
-	rsm_set_desc_flags(&desc,  GET_SMSTATE(u32, smbase, 0x7f5c));
+	selector =                 GET_SMSTATE(u32, smstate, 0x7fc4);
+	set_desc_base(&desc,       GET_SMSTATE(u32, smstate, 0x7f64));
+	set_desc_limit(&desc,      GET_SMSTATE(u32, smstate, 0x7f60));
+	rsm_set_desc_flags(&desc,  GET_SMSTATE(u32, smstate, 0x7f5c));
 	ctxt->ops->set_segment(ctxt, selector, &desc, 0, VCPU_SREG_TR);
 
-	selector =                 GET_SMSTATE(u32, smbase, 0x7fc0);
-	set_desc_base(&desc,       GET_SMSTATE(u32, smbase, 0x7f80));
-	set_desc_limit(&desc,      GET_SMSTATE(u32, smbase, 0x7f7c));
-	rsm_set_desc_flags(&desc,  GET_SMSTATE(u32, smbase, 0x7f78));
+	selector =                 GET_SMSTATE(u32, smstate, 0x7fc0);
+	set_desc_base(&desc,       GET_SMSTATE(u32, smstate, 0x7f80));
+	set_desc_limit(&desc,      GET_SMSTATE(u32, smstate, 0x7f7c));
+	rsm_set_desc_flags(&desc,  GET_SMSTATE(u32, smstate, 0x7f78));
 	ctxt->ops->set_segment(ctxt, selector, &desc, 0, VCPU_SREG_LDTR);
 
-	dt.address =               GET_SMSTATE(u32, smbase, 0x7f74);
-	dt.size =                  GET_SMSTATE(u32, smbase, 0x7f70);
+	dt.address =               GET_SMSTATE(u32, smstate, 0x7f74);
+	dt.size =                  GET_SMSTATE(u32, smstate, 0x7f70);
 	ctxt->ops->set_gdt(ctxt, &dt);
 
-	dt.address =               GET_SMSTATE(u32, smbase, 0x7f58);
-	dt.size =                  GET_SMSTATE(u32, smbase, 0x7f54);
+	dt.address =               GET_SMSTATE(u32, smstate, 0x7f58);
+	dt.size =                  GET_SMSTATE(u32, smstate, 0x7f54);
 	ctxt->ops->set_idt(ctxt, &dt);
 
 	for (i = 0; i < 6; i++) {
-		int r = rsm_load_seg_32(ctxt, smbase, i);
+		int r = rsm_load_seg_32(ctxt, smstate, i);
 		if (r != X86EMUL_CONTINUE)
 			return r;
 	}
 
-	cr4 = GET_SMSTATE(u32, smbase, 0x7f14);
+	cr4 = GET_SMSTATE(u32, smstate, 0x7f14);
 
-	ctxt->ops->set_smbase(ctxt, GET_SMSTATE(u32, smbase, 0x7ef8));
+	ctxt->ops->set_smbase(ctxt, GET_SMSTATE(u32, smstate, 0x7ef8));
 
 	return rsm_enter_protected_mode(ctxt, cr0, cr3, cr4);
 }
 
-static int rsm_load_state_64(struct x86_emulate_ctxt *ctxt, u64 smbase)
+#ifdef CONFIG_X86_64
+static int rsm_load_state_64(struct x86_emulate_ctxt *ctxt,
+			     const char *smstate)
 {
 	struct desc_struct desc;
 	struct desc_ptr dt;
@@ -2509,43 +2510,43 @@ static int rsm_load_state_64(struct x86_emulate_ctxt *ctxt, u64 smbase)
 	int i, r;
 
 	for (i = 0; i < 16; i++)
-		*reg_write(ctxt, i) = GET_SMSTATE(u64, smbase, 0x7ff8 - i * 8);
+		*reg_write(ctxt, i) = GET_SMSTATE(u64, smstate, 0x7ff8 - i * 8);
 
-	ctxt->_eip   = GET_SMSTATE(u64, smbase, 0x7f78);
-	ctxt->eflags = GET_SMSTATE(u32, smbase, 0x7f70) | X86_EFLAGS_FIXED;
+	ctxt->_eip   = GET_SMSTATE(u64, smstate, 0x7f78);
+	ctxt->eflags = GET_SMSTATE(u32, smstate, 0x7f70) | X86_EFLAGS_FIXED;
 
-	val = GET_SMSTATE(u32, smbase, 0x7f68);
+	val = GET_SMSTATE(u32, smstate, 0x7f68);
 	ctxt->ops->set_dr(ctxt, 6, (val & DR6_VOLATILE) | DR6_FIXED_1);
-	val = GET_SMSTATE(u32, smbase, 0x7f60);
+	val = GET_SMSTATE(u32, smstate, 0x7f60);
 	ctxt->ops->set_dr(ctxt, 7, (val & DR7_VOLATILE) | DR7_FIXED_1);
 
-	cr0 =                       GET_SMSTATE(u64, smbase, 0x7f58);
-	cr3 =                       GET_SMSTATE(u64, smbase, 0x7f50);
-	cr4 =                       GET_SMSTATE(u64, smbase, 0x7f48);
-	ctxt->ops->set_smbase(ctxt, GET_SMSTATE(u32, smbase, 0x7f00));
-	val =                       GET_SMSTATE(u64, smbase, 0x7ed0);
+	cr0 =                       GET_SMSTATE(u64, smstate, 0x7f58);
+	cr3 =                       GET_SMSTATE(u64, smstate, 0x7f50);
+	cr4 =                       GET_SMSTATE(u64, smstate, 0x7f48);
+	ctxt->ops->set_smbase(ctxt, GET_SMSTATE(u32, smstate, 0x7f00));
+	val =                       GET_SMSTATE(u64, smstate, 0x7ed0);
 	ctxt->ops->set_msr(ctxt, MSR_EFER, val & ~EFER_LMA);
 
-	selector =                  GET_SMSTATE(u32, smbase, 0x7e90);
-	rsm_set_desc_flags(&desc,   GET_SMSTATE(u32, smbase, 0x7e92) << 8);
-	set_desc_limit(&desc,       GET_SMSTATE(u32, smbase, 0x7e94));
-	set_desc_base(&desc,        GET_SMSTATE(u32, smbase, 0x7e98));
-	base3 =                     GET_SMSTATE(u32, smbase, 0x7e9c);
+	selector =                  GET_SMSTATE(u32, smstate, 0x7e90);
+	rsm_set_desc_flags(&desc,   GET_SMSTATE(u32, smstate, 0x7e92) << 8);
+	set_desc_limit(&desc,       GET_SMSTATE(u32, smstate, 0x7e94));
+	set_desc_base(&desc,        GET_SMSTATE(u32, smstate, 0x7e98));
+	base3 =                     GET_SMSTATE(u32, smstate, 0x7e9c);
 	ctxt->ops->set_segment(ctxt, selector, &desc, base3, VCPU_SREG_TR);
 
-	dt.size =                   GET_SMSTATE(u32, smbase, 0x7e84);
-	dt.address =                GET_SMSTATE(u64, smbase, 0x7e88);
+	dt.size =                   GET_SMSTATE(u32, smstate, 0x7e84);
+	dt.address =                GET_SMSTATE(u64, smstate, 0x7e88);
 	ctxt->ops->set_idt(ctxt, &dt);
 
-	selector =                  GET_SMSTATE(u32, smbase, 0x7e70);
-	rsm_set_desc_flags(&desc,   GET_SMSTATE(u32, smbase, 0x7e72) << 8);
-	set_desc_limit(&desc,       GET_SMSTATE(u32, smbase, 0x7e74));
-	set_desc_base(&desc,        GET_SMSTATE(u32, smbase, 0x7e78));
-	base3 =                     GET_SMSTATE(u32, smbase, 0x7e7c);
+	selector =                  GET_SMSTATE(u32, smstate, 0x7e70);
+	rsm_set_desc_flags(&desc,   GET_SMSTATE(u32, smstate, 0x7e72) << 8);
+	set_desc_limit(&desc,       GET_SMSTATE(u32, smstate, 0x7e74));
+	set_desc_base(&desc,        GET_SMSTATE(u32, smstate, 0x7e78));
+	base3 =                     GET_SMSTATE(u32, smstate, 0x7e7c);
 	ctxt->ops->set_segment(ctxt, selector, &desc, base3, VCPU_SREG_LDTR);
 
-	dt.size =                   GET_SMSTATE(u32, smbase, 0x7e64);
-	dt.address =                GET_SMSTATE(u64, smbase, 0x7e68);
+	dt.size =                   GET_SMSTATE(u32, smstate, 0x7e64);
+	dt.address =                GET_SMSTATE(u64, smstate, 0x7e68);
 	ctxt->ops->set_gdt(ctxt, &dt);
 
 	r = rsm_enter_protected_mode(ctxt, cr0, cr3, cr4);
@@ -2553,37 +2554,49 @@ static int rsm_load_state_64(struct x86_emulate_ctxt *ctxt, u64 smbase)
 		return r;
 
 	for (i = 0; i < 6; i++) {
-		r = rsm_load_seg_64(ctxt, smbase, i);
+		r = rsm_load_seg_64(ctxt, smstate, i);
 		if (r != X86EMUL_CONTINUE)
 			return r;
 	}
 
 	return X86EMUL_CONTINUE;
 }
+#endif
 
 static int em_rsm(struct x86_emulate_ctxt *ctxt)
 {
 	unsigned long cr0, cr4, efer;
+	char buf[512];
 	u64 smbase;
 	int ret;
 
 	if ((ctxt->ops->get_hflags(ctxt) & X86EMUL_SMM_MASK) == 0)
 		return emulate_ud(ctxt);
 
+	smbase = ctxt->ops->get_smbase(ctxt);
+
+	ret = ctxt->ops->read_phys(ctxt, smbase + 0xfe00, buf, sizeof(buf));
+	if (ret != X86EMUL_CONTINUE)
+		return X86EMUL_UNHANDLEABLE;
+
+	if ((ctxt->ops->get_hflags(ctxt) & X86EMUL_SMM_INSIDE_NMI_MASK) == 0)
+		ctxt->ops->set_nmi_mask(ctxt, false);
+
+	ctxt->ops->set_hflags(ctxt, ctxt->ops->get_hflags(ctxt) &
+		~(X86EMUL_SMM_INSIDE_NMI_MASK | X86EMUL_SMM_MASK));
+
 	/*
 	 * Get back to real mode, to prepare a safe state in which to load
 	 * CR0/CR3/CR4/EFER.  It's all a bit more complicated if the vCPU
 	 * supports long mode.
 	 */
-	cr4 = ctxt->ops->get_cr(ctxt, 4);
 	if (emulator_has_longmode(ctxt)) {
 		struct desc_struct cs_desc;
 
 		/* Zero CR4.PCIDE before CR0.PG.  */
-		if (cr4 & X86_CR4_PCIDE) {
+		cr4 = ctxt->ops->get_cr(ctxt, 4);
+		if (cr4 & X86_CR4_PCIDE)
 			ctxt->ops->set_cr(ctxt, 4, cr4 & ~X86_CR4_PCIDE);
-			cr4 &= ~X86_CR4_PCIDE;
-		}
 
 		/* A 32-bit code segment is required to clear EFER.LMA.  */
 		memset(&cs_desc, 0, sizeof(cs_desc));
@@ -2597,39 +2610,39 @@ static int em_rsm(struct x86_emulate_ctxt *ctxt)
 	if (cr0 & X86_CR0_PE)
 		ctxt->ops->set_cr(ctxt, 0, cr0 & ~(X86_CR0_PG | X86_CR0_PE));
 
-	/* Now clear CR4.PAE (which must be done before clearing EFER.LME).  */
-	if (cr4 & X86_CR4_PAE)
-		ctxt->ops->set_cr(ctxt, 4, cr4 & ~X86_CR4_PAE);
-
-	/* And finally go back to 32-bit mode.  */
-	efer = 0;
-	ctxt->ops->set_msr(ctxt, MSR_EFER, efer);
+	if (emulator_has_longmode(ctxt)) {
+		/* Clear CR4.PAE before clearing EFER.LME. */
+		cr4 = ctxt->ops->get_cr(ctxt, 4);
+		if (cr4 & X86_CR4_PAE)
+			ctxt->ops->set_cr(ctxt, 4, cr4 & ~X86_CR4_PAE);
 
-	smbase = ctxt->ops->get_smbase(ctxt);
+		/* And finally go back to 32-bit mode.  */
+		efer = 0;
+		ctxt->ops->set_msr(ctxt, MSR_EFER, efer);
+	}
 
 	/*
 	 * Give pre_leave_smm() a chance to make ISA-specific changes to the
 	 * vCPU state (e.g. enter guest mode) before loading state from the SMM
 	 * state-save area.
 	 */
-	if (ctxt->ops->pre_leave_smm(ctxt, smbase))
+	if (ctxt->ops->pre_leave_smm(ctxt, buf))
 		return X86EMUL_UNHANDLEABLE;
 
+#ifdef CONFIG_X86_64
 	if (emulator_has_longmode(ctxt))
-		ret = rsm_load_state_64(ctxt, smbase + 0x8000);
+		ret = rsm_load_state_64(ctxt, buf);
 	else
-		ret = rsm_load_state_32(ctxt, smbase + 0x8000);
+#endif
+		ret = rsm_load_state_32(ctxt, buf);
 
 	if (ret != X86EMUL_CONTINUE) {
 		/* FIXME: should triple fault */
 		return X86EMUL_UNHANDLEABLE;
 	}
 
-	if ((ctxt->ops->get_hflags(ctxt) & X86EMUL_SMM_INSIDE_NMI_MASK) == 0)
-		ctxt->ops->set_nmi_mask(ctxt, false);
+	ctxt->ops->post_leave_smm(ctxt);
 
-	ctxt->ops->set_hflags(ctxt, ctxt->ops->get_hflags(ctxt) &
-		~(X86EMUL_SMM_INSIDE_NMI_MASK | X86EMUL_SMM_MASK));
 	return X86EMUL_CONTINUE;
 }
 
diff --git a/arch/x86/kvm/hyperv.c b/arch/x86/kvm/hyperv.c
index 27c43525a05f..cc24b3a32c44 100644
--- a/arch/x86/kvm/hyperv.c
+++ b/arch/x86/kvm/hyperv.c
@@ -526,7 +526,9 @@ static int stimer_set_config(struct kvm_vcpu_hv_stimer *stimer, u64 config,
 		new_config.enable = 0;
 	stimer->config.as_uint64 = new_config.as_uint64;
 
-	stimer_mark_pending(stimer, false);
+	if (stimer->config.enable)
+		stimer_mark_pending(stimer, false);
+
 	return 0;
 }
 
@@ -542,7 +544,10 @@ static int stimer_set_count(struct kvm_vcpu_hv_stimer *stimer, u64 count,
 		stimer->config.enable = 0;
 	else if (stimer->config.auto_enable)
 		stimer->config.enable = 1;
-	stimer_mark_pending(stimer, false);
+
+	if (stimer->config.enable)
+		stimer_mark_pending(stimer, false);
+
 	return 0;
 }
 
@@ -1366,7 +1371,16 @@ static u64 kvm_hv_flush_tlb(struct kvm_vcpu *current_vcpu, u64 ingpa,
 
 		valid_bank_mask = BIT_ULL(0);
 		sparse_banks[0] = flush.processor_mask;
-		all_cpus = flush.flags & HV_FLUSH_ALL_PROCESSORS;
+
+		/*
+		 * Work around possible WS2012 bug: it sends hypercalls
+		 * with processor_mask = 0x0 and HV_FLUSH_ALL_PROCESSORS clear,
+		 * while also expecting us to flush something and crashing if
+		 * we don't. Let's treat processor_mask == 0 same as
+		 * HV_FLUSH_ALL_PROCESSORS.
+		 */
+		all_cpus = (flush.flags & HV_FLUSH_ALL_PROCESSORS) ||
+			flush.processor_mask == 0;
 	} else {
 		if (unlikely(kvm_read_guest(kvm, ingpa, &flush_ex,
 					    sizeof(flush_ex))))
diff --git a/arch/x86/kvm/lapic.c b/arch/x86/kvm/lapic.c
index 991fdf7fc17f..bd13fdddbdc4 100644
--- a/arch/x86/kvm/lapic.c
+++ b/arch/x86/kvm/lapic.c
@@ -70,7 +70,6 @@
 #define APIC_BROADCAST			0xFF
 #define X2APIC_BROADCAST		0xFFFFFFFFul
 
-static bool lapic_timer_advance_adjust_done = false;
 #define LAPIC_TIMER_ADVANCE_ADJUST_DONE 100
 /* step-by-step approximation to mitigate fluctuation */
 #define LAPIC_TIMER_ADVANCE_ADJUST_STEP 8
@@ -138,6 +137,7 @@ static inline bool kvm_apic_map_get_logical_dest(struct kvm_apic_map *map,
 		if (offset <= max_apic_id) {
 			u8 cluster_size = min(max_apic_id - offset + 1, 16U);
 
+			offset = array_index_nospec(offset, map->max_apic_id + 1);
 			*cluster = &map->phys_map[offset];
 			*mask = dest_id & (0xffff >> (16 - cluster_size));
 		} else {
@@ -901,7 +901,8 @@ static inline bool kvm_apic_map_get_dest_lapic(struct kvm *kvm,
 		if (irq->dest_id > map->max_apic_id) {
 			*bitmap = 0;
 		} else {
-			*dst = &map->phys_map[irq->dest_id];
+			u32 dest_id = array_index_nospec(irq->dest_id, map->max_apic_id + 1);
+			*dst = &map->phys_map[dest_id];
 			*bitmap = 1;
 		}
 		return true;
@@ -1480,14 +1481,32 @@ static bool lapic_timer_int_injected(struct kvm_vcpu *vcpu)
 	return false;
 }
 
+static inline void __wait_lapic_expire(struct kvm_vcpu *vcpu, u64 guest_cycles)
+{
+	u64 timer_advance_ns = vcpu->arch.apic->lapic_timer.timer_advance_ns;
+
+	/*
+	 * If the guest TSC is running at a different ratio than the host, then
+	 * convert the delay to nanoseconds to achieve an accurate delay.  Note
+	 * that __delay() uses delay_tsc whenever the hardware has TSC, thus
+	 * always for VMX enabled hardware.
+	 */
+	if (vcpu->arch.tsc_scaling_ratio == kvm_default_tsc_scaling_ratio) {
+		__delay(min(guest_cycles,
+			nsec_to_cycles(vcpu, timer_advance_ns)));
+	} else {
+		u64 delay_ns = guest_cycles * 1000000ULL;
+		do_div(delay_ns, vcpu->arch.virtual_tsc_khz);
+		ndelay(min_t(u32, delay_ns, timer_advance_ns));
+	}
+}
+
 void wait_lapic_expire(struct kvm_vcpu *vcpu)
 {
 	struct kvm_lapic *apic = vcpu->arch.apic;
+	u32 timer_advance_ns = apic->lapic_timer.timer_advance_ns;
 	u64 guest_tsc, tsc_deadline, ns;
 
-	if (!lapic_in_kernel(vcpu))
-		return;
-
 	if (apic->lapic_timer.expired_tscdeadline == 0)
 		return;
 
@@ -1499,33 +1518,37 @@ void wait_lapic_expire(struct kvm_vcpu *vcpu)
 	guest_tsc = kvm_read_l1_tsc(vcpu, rdtsc());
 	trace_kvm_wait_lapic_expire(vcpu->vcpu_id, guest_tsc - tsc_deadline);
 
-	/* __delay is delay_tsc whenever the hardware has TSC, thus always.  */
 	if (guest_tsc < tsc_deadline)
-		__delay(min(tsc_deadline - guest_tsc,
-			nsec_to_cycles(vcpu, lapic_timer_advance_ns)));
+		__wait_lapic_expire(vcpu, tsc_deadline - guest_tsc);
 
-	if (!lapic_timer_advance_adjust_done) {
+	if (!apic->lapic_timer.timer_advance_adjust_done) {
 		/* too early */
 		if (guest_tsc < tsc_deadline) {
 			ns = (tsc_deadline - guest_tsc) * 1000000ULL;
 			do_div(ns, vcpu->arch.virtual_tsc_khz);
-			lapic_timer_advance_ns -= min((unsigned int)ns,
-				lapic_timer_advance_ns / LAPIC_TIMER_ADVANCE_ADJUST_STEP);
+			timer_advance_ns -= min((u32)ns,
+				timer_advance_ns / LAPIC_TIMER_ADVANCE_ADJUST_STEP);
 		} else {
 		/* too late */
 			ns = (guest_tsc - tsc_deadline) * 1000000ULL;
 			do_div(ns, vcpu->arch.virtual_tsc_khz);
-			lapic_timer_advance_ns += min((unsigned int)ns,
-				lapic_timer_advance_ns / LAPIC_TIMER_ADVANCE_ADJUST_STEP);
+			timer_advance_ns += min((u32)ns,
+				timer_advance_ns / LAPIC_TIMER_ADVANCE_ADJUST_STEP);
 		}
 		if (abs(guest_tsc - tsc_deadline) < LAPIC_TIMER_ADVANCE_ADJUST_DONE)
-			lapic_timer_advance_adjust_done = true;
+			apic->lapic_timer.timer_advance_adjust_done = true;
+		if (unlikely(timer_advance_ns > 5000)) {
+			timer_advance_ns = 0;
+			apic->lapic_timer.timer_advance_adjust_done = true;
+		}
+		apic->lapic_timer.timer_advance_ns = timer_advance_ns;
 	}
 }
 
 static void start_sw_tscdeadline(struct kvm_lapic *apic)
 {
-	u64 guest_tsc, tscdeadline = apic->lapic_timer.tscdeadline;
+	struct kvm_timer *ktimer = &apic->lapic_timer;
+	u64 guest_tsc, tscdeadline = ktimer->tscdeadline;
 	u64 ns = 0;
 	ktime_t expire;
 	struct kvm_vcpu *vcpu = apic->vcpu;
@@ -1540,13 +1563,15 @@ static void start_sw_tscdeadline(struct kvm_lapic *apic)
 
 	now = ktime_get();
 	guest_tsc = kvm_read_l1_tsc(vcpu, rdtsc());
-	if (likely(tscdeadline > guest_tsc)) {
-		ns = (tscdeadline - guest_tsc) * 1000000ULL;
-		do_div(ns, this_tsc_khz);
+
+	ns = (tscdeadline - guest_tsc) * 1000000ULL;
+	do_div(ns, this_tsc_khz);
+
+	if (likely(tscdeadline > guest_tsc) &&
+	    likely(ns > apic->lapic_timer.timer_advance_ns)) {
 		expire = ktime_add_ns(now, ns);
-		expire = ktime_sub_ns(expire, lapic_timer_advance_ns);
-		hrtimer_start(&apic->lapic_timer.timer,
-				expire, HRTIMER_MODE_ABS_PINNED);
+		expire = ktime_sub_ns(expire, ktimer->timer_advance_ns);
+		hrtimer_start(&ktimer->timer, expire, HRTIMER_MODE_ABS_PINNED);
 	} else
 		apic_timer_expired(apic);
 
@@ -2253,7 +2278,7 @@ static enum hrtimer_restart apic_timer_fn(struct hrtimer *data)
 		return HRTIMER_NORESTART;
 }
 
-int kvm_create_lapic(struct kvm_vcpu *vcpu)
+int kvm_create_lapic(struct kvm_vcpu *vcpu, int timer_advance_ns)
 {
 	struct kvm_lapic *apic;
 
@@ -2277,6 +2302,14 @@ int kvm_create_lapic(struct kvm_vcpu *vcpu)
 	hrtimer_init(&apic->lapic_timer.timer, CLOCK_MONOTONIC,
 		     HRTIMER_MODE_ABS_PINNED);
 	apic->lapic_timer.timer.function = apic_timer_fn;
+	if (timer_advance_ns == -1) {
+		apic->lapic_timer.timer_advance_ns = 1000;
+		apic->lapic_timer.timer_advance_adjust_done = false;
+	} else {
+		apic->lapic_timer.timer_advance_ns = timer_advance_ns;
+		apic->lapic_timer.timer_advance_adjust_done = true;
+	}
+
 
 	/*
 	 * APIC is created enabled. This will prevent kvm_lapic_set_base from
diff --git a/arch/x86/kvm/lapic.h b/arch/x86/kvm/lapic.h
index ff6ef9c3d760..d6d049ba3045 100644
--- a/arch/x86/kvm/lapic.h
+++ b/arch/x86/kvm/lapic.h
@@ -31,8 +31,10 @@ struct kvm_timer {
 	u32 timer_mode_mask;
 	u64 tscdeadline;
 	u64 expired_tscdeadline;
+	u32 timer_advance_ns;
 	atomic_t pending;			/* accumulated triggered timers */
 	bool hv_timer_in_use;
+	bool timer_advance_adjust_done;
 };
 
 struct kvm_lapic {
@@ -62,7 +64,7 @@ struct kvm_lapic {
 
 struct dest_map;
 
-int kvm_create_lapic(struct kvm_vcpu *vcpu);
+int kvm_create_lapic(struct kvm_vcpu *vcpu, int timer_advance_ns);
 void kvm_free_lapic(struct kvm_vcpu *vcpu);
 
 int kvm_apic_has_interrupt(struct kvm_vcpu *vcpu);
diff --git a/arch/x86/kvm/mmu.c b/arch/x86/kvm/mmu.c
index 7837ab001d80..d9c7b45d231f 100644
--- a/arch/x86/kvm/mmu.c
+++ b/arch/x86/kvm/mmu.c
@@ -182,7 +182,7 @@ struct kvm_shadow_walk_iterator {
 
 static const union kvm_mmu_page_role mmu_base_role_mask = {
 	.cr0_wp = 1,
-	.cr4_pae = 1,
+	.gpte_is_8_bytes = 1,
 	.nxe = 1,
 	.smep_andnot_wp = 1,
 	.smap_andnot_wp = 1,
@@ -2007,7 +2007,7 @@ static int is_empty_shadow_page(u64 *spt)
  * aggregate version in order to make the slab shrinker
  * faster
  */
-static inline void kvm_mod_used_mmu_pages(struct kvm *kvm, int nr)
+static inline void kvm_mod_used_mmu_pages(struct kvm *kvm, unsigned long nr)
 {
 	kvm->arch.n_used_mmu_pages += nr;
 	percpu_counter_add(&kvm_total_used_mmu_pages, nr);
@@ -2205,6 +2205,7 @@ static bool kvm_mmu_prepare_zap_page(struct kvm *kvm, struct kvm_mmu_page *sp,
 static void kvm_mmu_commit_zap_page(struct kvm *kvm,
 				    struct list_head *invalid_list);
 
+
 #define for_each_valid_sp(_kvm, _sp, _gfn)				\
 	hlist_for_each_entry(_sp,					\
 	  &(_kvm)->arch.mmu_page_hash[kvm_page_table_hashfn(_gfn)], hash_link) \
@@ -2215,12 +2216,17 @@ static void kvm_mmu_commit_zap_page(struct kvm *kvm,
 	for_each_valid_sp(_kvm, _sp, _gfn)				\
 		if ((_sp)->gfn != (_gfn) || (_sp)->role.direct) {} else
 
+static inline bool is_ept_sp(struct kvm_mmu_page *sp)
+{
+	return sp->role.cr0_wp && sp->role.smap_andnot_wp;
+}
+
 /* @sp->gfn should be write-protected at the call site */
 static bool __kvm_sync_page(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp,
 			    struct list_head *invalid_list)
 {
-	if (sp->role.cr4_pae != !!is_pae(vcpu)
-	    || vcpu->arch.mmu->sync_page(vcpu, sp) == 0) {
+	if ((!is_ept_sp(sp) && sp->role.gpte_is_8_bytes != !!is_pae(vcpu)) ||
+	    vcpu->arch.mmu->sync_page(vcpu, sp) == 0) {
 		kvm_mmu_prepare_zap_page(vcpu->kvm, sp, invalid_list);
 		return false;
 	}
@@ -2232,7 +2238,7 @@ static bool kvm_mmu_remote_flush_or_zap(struct kvm *kvm,
 					struct list_head *invalid_list,
 					bool remote_flush)
 {
-	if (!remote_flush && !list_empty(invalid_list))
+	if (!remote_flush && list_empty(invalid_list))
 		return false;
 
 	if (!list_empty(invalid_list))
@@ -2423,7 +2429,7 @@ static struct kvm_mmu_page *kvm_mmu_get_page(struct kvm_vcpu *vcpu,
 	role.level = level;
 	role.direct = direct;
 	if (role.direct)
-		role.cr4_pae = 0;
+		role.gpte_is_8_bytes = true;
 	role.access = access;
 	if (!vcpu->arch.mmu->direct_map
 	    && vcpu->arch.mmu->root_level <= PT32_ROOT_LEVEL) {
@@ -2757,7 +2763,7 @@ static bool prepare_zap_oldest_mmu_page(struct kvm *kvm,
  * Changing the number of mmu pages allocated to the vm
  * Note: if goal_nr_mmu_pages is too small, you will get dead lock
  */
-void kvm_mmu_change_mmu_pages(struct kvm *kvm, unsigned int goal_nr_mmu_pages)
+void kvm_mmu_change_mmu_pages(struct kvm *kvm, unsigned long goal_nr_mmu_pages)
 {
 	LIST_HEAD(invalid_list);
 
@@ -4775,6 +4781,7 @@ static union kvm_mmu_extended_role kvm_calc_mmu_role_ext(struct kvm_vcpu *vcpu)
 	union kvm_mmu_extended_role ext = {0};
 
 	ext.cr0_pg = !!is_paging(vcpu);
+	ext.cr4_pae = !!is_pae(vcpu);
 	ext.cr4_smep = !!kvm_read_cr4_bits(vcpu, X86_CR4_SMEP);
 	ext.cr4_smap = !!kvm_read_cr4_bits(vcpu, X86_CR4_SMAP);
 	ext.cr4_pse = !!is_pse(vcpu);
@@ -4794,7 +4801,6 @@ static union kvm_mmu_role kvm_calc_mmu_role_common(struct kvm_vcpu *vcpu,
 
 	role.base.access = ACC_ALL;
 	role.base.nxe = !!is_nx(vcpu);
-	role.base.cr4_pae = !!is_pae(vcpu);
 	role.base.cr0_wp = is_write_protection(vcpu);
 	role.base.smm = is_smm(vcpu);
 	role.base.guest_mode = is_guest_mode(vcpu);
@@ -4815,6 +4821,7 @@ kvm_calc_tdp_mmu_root_page_role(struct kvm_vcpu *vcpu, bool base_only)
 	role.base.ad_disabled = (shadow_accessed_mask == 0);
 	role.base.level = kvm_x86_ops->get_tdp_level(vcpu);
 	role.base.direct = true;
+	role.base.gpte_is_8_bytes = true;
 
 	return role;
 }
@@ -4879,6 +4886,7 @@ kvm_calc_shadow_mmu_root_page_role(struct kvm_vcpu *vcpu, bool base_only)
 	role.base.smap_andnot_wp = role.ext.cr4_smap &&
 		!is_write_protection(vcpu);
 	role.base.direct = !is_paging(vcpu);
+	role.base.gpte_is_8_bytes = !!is_pae(vcpu);
 
 	if (!is_long_mode(vcpu))
 		role.base.level = PT32E_ROOT_LEVEL;
@@ -4918,18 +4926,26 @@ static union kvm_mmu_role
 kvm_calc_shadow_ept_root_page_role(struct kvm_vcpu *vcpu, bool accessed_dirty,
 				   bool execonly)
 {
-	union kvm_mmu_role role;
+	union kvm_mmu_role role = {0};
 
-	/* Base role is inherited from root_mmu */
-	role.base.word = vcpu->arch.root_mmu.mmu_role.base.word;
-	role.ext = kvm_calc_mmu_role_ext(vcpu);
+	/* SMM flag is inherited from root_mmu */
+	role.base.smm = vcpu->arch.root_mmu.mmu_role.base.smm;
 
 	role.base.level = PT64_ROOT_4LEVEL;
+	role.base.gpte_is_8_bytes = true;
 	role.base.direct = false;
 	role.base.ad_disabled = !accessed_dirty;
 	role.base.guest_mode = true;
 	role.base.access = ACC_ALL;
 
+	/*
+	 * WP=1 and NOT_WP=1 is an impossible combination, use WP and the
+	 * SMAP variation to denote shadow EPT entries.
+	 */
+	role.base.cr0_wp = true;
+	role.base.smap_andnot_wp = true;
+
+	role.ext = kvm_calc_mmu_role_ext(vcpu);
 	role.ext.execonly = execonly;
 
 	return role;
@@ -5179,7 +5195,7 @@ static bool detect_write_misaligned(struct kvm_mmu_page *sp, gpa_t gpa,
 		 gpa, bytes, sp->role.word);
 
 	offset = offset_in_page(gpa);
-	pte_size = sp->role.cr4_pae ? 8 : 4;
+	pte_size = sp->role.gpte_is_8_bytes ? 8 : 4;
 
 	/*
 	 * Sometimes, the OS only writes the last one bytes to update status
@@ -5203,7 +5219,7 @@ static u64 *get_written_sptes(struct kvm_mmu_page *sp, gpa_t gpa, int *nspte)
 	page_offset = offset_in_page(gpa);
 	level = sp->role.level;
 	*nspte = 1;
-	if (!sp->role.cr4_pae) {
+	if (!sp->role.gpte_is_8_bytes) {
 		page_offset <<= 1;	/* 32->64 */
 		/*
 		 * A 32-bit pde maps 4MB while the shadow pdes map
@@ -5393,10 +5409,12 @@ emulate:
 	 * This can happen if a guest gets a page-fault on data access but the HW
 	 * table walker is not able to read the instruction page (e.g instruction
 	 * page is not present in memory). In those cases we simply restart the
-	 * guest.
+	 * guest, with the exception of AMD Erratum 1096 which is unrecoverable.
 	 */
-	if (unlikely(insn && !insn_len))
-		return 1;
+	if (unlikely(insn && !insn_len)) {
+		if (!kvm_x86_ops->need_emulation_on_page_fault(vcpu))
+			return 1;
+	}
 
 	er = x86_emulate_instruction(vcpu, cr2, emulation_type, insn, insn_len);
 
@@ -5509,7 +5527,9 @@ slot_handle_level_range(struct kvm *kvm, struct kvm_memory_slot *memslot,
 
 		if (need_resched() || spin_needbreak(&kvm->mmu_lock)) {
 			if (flush && lock_flush_tlb) {
-				kvm_flush_remote_tlbs(kvm);
+				kvm_flush_remote_tlbs_with_address(kvm,
+						start_gfn,
+						iterator.gfn - start_gfn + 1);
 				flush = false;
 			}
 			cond_resched_lock(&kvm->mmu_lock);
@@ -5517,7 +5537,8 @@ slot_handle_level_range(struct kvm *kvm, struct kvm_memory_slot *memslot,
 	}
 
 	if (flush && lock_flush_tlb) {
-		kvm_flush_remote_tlbs(kvm);
+		kvm_flush_remote_tlbs_with_address(kvm, start_gfn,
+						   end_gfn - start_gfn + 1);
 		flush = false;
 	}
 
@@ -6011,10 +6032,10 @@ out:
 /*
  * Calculate mmu pages needed for kvm.
  */
-unsigned int kvm_mmu_calculate_mmu_pages(struct kvm *kvm)
+unsigned long kvm_mmu_calculate_default_mmu_pages(struct kvm *kvm)
 {
-	unsigned int nr_mmu_pages;
-	unsigned int  nr_pages = 0;
+	unsigned long nr_mmu_pages;
+	unsigned long nr_pages = 0;
 	struct kvm_memslots *slots;
 	struct kvm_memory_slot *memslot;
 	int i;
@@ -6027,8 +6048,7 @@ unsigned int kvm_mmu_calculate_mmu_pages(struct kvm *kvm)
 	}
 
 	nr_mmu_pages = nr_pages * KVM_PERMILLE_MMU_PAGES / 1000;
-	nr_mmu_pages = max(nr_mmu_pages,
-			   (unsigned int) KVM_MIN_ALLOC_MMU_PAGES);
+	nr_mmu_pages = max(nr_mmu_pages, KVM_MIN_ALLOC_MMU_PAGES);
 
 	return nr_mmu_pages;
 }
diff --git a/arch/x86/kvm/mmu.h b/arch/x86/kvm/mmu.h
index bbdc60f2fae8..54c2a377795b 100644
--- a/arch/x86/kvm/mmu.h
+++ b/arch/x86/kvm/mmu.h
@@ -64,7 +64,7 @@ bool kvm_can_do_async_pf(struct kvm_vcpu *vcpu);
 int kvm_handle_page_fault(struct kvm_vcpu *vcpu, u64 error_code,
 				u64 fault_address, char *insn, int insn_len);
 
-static inline unsigned int kvm_mmu_available_pages(struct kvm *kvm)
+static inline unsigned long kvm_mmu_available_pages(struct kvm *kvm)
 {
 	if (kvm->arch.n_max_mmu_pages > kvm->arch.n_used_mmu_pages)
 		return kvm->arch.n_max_mmu_pages -
diff --git a/arch/x86/kvm/mmutrace.h b/arch/x86/kvm/mmutrace.h
index 9f6c855a0043..dd30dccd2ad5 100644
--- a/arch/x86/kvm/mmutrace.h
+++ b/arch/x86/kvm/mmutrace.h
@@ -29,10 +29,10 @@
 								        \
 	role.word = __entry->role;					\
 									\
-	trace_seq_printf(p, "sp gfn %llx l%u%s q%u%s %s%s"		\
+	trace_seq_printf(p, "sp gfn %llx l%u %u-byte q%u%s %s%s"	\
 			 " %snxe %sad root %u %s%c",			\
 			 __entry->gfn, role.level,			\
-			 role.cr4_pae ? " pae" : "",			\
+			 role.gpte_is_8_bytes ? 8 : 4,			\
 			 role.quadrant,					\
 			 role.direct ? " direct" : "",			\
 			 access_str[role.access],			\
diff --git a/arch/x86/kvm/pmu.c b/arch/x86/kvm/pmu.c
index 58ead7db71a3..e39741997893 100644
--- a/arch/x86/kvm/pmu.c
+++ b/arch/x86/kvm/pmu.c
@@ -281,9 +281,13 @@ static int kvm_pmu_rdpmc_vmware(struct kvm_vcpu *vcpu, unsigned idx, u64 *data)
 int kvm_pmu_rdpmc(struct kvm_vcpu *vcpu, unsigned idx, u64 *data)
 {
 	bool fast_mode = idx & (1u << 31);
+	struct kvm_pmu *pmu = vcpu_to_pmu(vcpu);
 	struct kvm_pmc *pmc;
 	u64 ctr_val;
 
+	if (!pmu->version)
+		return 1;
+
 	if (is_vmware_backdoor_pmc(idx))
 		return kvm_pmu_rdpmc_vmware(vcpu, idx, data);
 
diff --git a/arch/x86/kvm/svm.c b/arch/x86/kvm/svm.c
index b5b128a0a051..406b558abfef 100644
--- a/arch/x86/kvm/svm.c
+++ b/arch/x86/kvm/svm.c
@@ -262,6 +262,7 @@ struct amd_svm_iommu_ir {
 };
 
 #define AVIC_LOGICAL_ID_ENTRY_GUEST_PHYSICAL_ID_MASK	(0xFF)
+#define AVIC_LOGICAL_ID_ENTRY_VALID_BIT			31
 #define AVIC_LOGICAL_ID_ENTRY_VALID_MASK		(1 << 31)
 
 #define AVIC_PHYSICAL_ID_ENTRY_HOST_PHYSICAL_ID_MASK	(0xFFULL)
@@ -2692,6 +2693,7 @@ static int npf_interception(struct vcpu_svm *svm)
 static int db_interception(struct vcpu_svm *svm)
 {
 	struct kvm_run *kvm_run = svm->vcpu.run;
+	struct kvm_vcpu *vcpu = &svm->vcpu;
 
 	if (!(svm->vcpu.guest_debug &
 	      (KVM_GUESTDBG_SINGLESTEP | KVM_GUESTDBG_USE_HW_BP)) &&
@@ -2702,6 +2704,8 @@ static int db_interception(struct vcpu_svm *svm)
 
 	if (svm->nmi_singlestep) {
 		disable_nmi_singlestep(svm);
+		/* Make sure we check for pending NMIs upon entry */
+		kvm_make_request(KVM_REQ_EVENT, vcpu);
 	}
 
 	if (svm->vcpu.guest_debug &
@@ -4517,14 +4521,25 @@ static int avic_incomplete_ipi_interception(struct vcpu_svm *svm)
 		kvm_lapic_reg_write(apic, APIC_ICR, icrl);
 		break;
 	case AVIC_IPI_FAILURE_TARGET_NOT_RUNNING: {
+		int i;
+		struct kvm_vcpu *vcpu;
+		struct kvm *kvm = svm->vcpu.kvm;
 		struct kvm_lapic *apic = svm->vcpu.arch.apic;
 
 		/*
-		 * Update ICR high and low, then emulate sending IPI,
-		 * which is handled when writing APIC_ICR.
+		 * At this point, we expect that the AVIC HW has already
+		 * set the appropriate IRR bits on the valid target
+		 * vcpus. So, we just need to kick the appropriate vcpu.
 		 */
-		kvm_lapic_reg_write(apic, APIC_ICR2, icrh);
-		kvm_lapic_reg_write(apic, APIC_ICR, icrl);
+		kvm_for_each_vcpu(i, vcpu, kvm) {
+			bool m = kvm_apic_match_dest(vcpu, apic,
+						     icrl & KVM_APIC_SHORT_MASK,
+						     GET_APIC_DEST_FIELD(icrh),
+						     icrl & KVM_APIC_DEST_MASK);
+
+			if (m && !avic_vcpu_is_running(vcpu))
+				kvm_vcpu_wake_up(vcpu);
+		}
 		break;
 	}
 	case AVIC_IPI_FAILURE_INVALID_TARGET:
@@ -4596,7 +4611,7 @@ static void avic_invalidate_logical_id_entry(struct kvm_vcpu *vcpu)
 	u32 *entry = avic_get_logical_id_entry(vcpu, svm->ldr_reg, flat);
 
 	if (entry)
-		WRITE_ONCE(*entry, (u32) ~AVIC_LOGICAL_ID_ENTRY_VALID_MASK);
+		clear_bit(AVIC_LOGICAL_ID_ENTRY_VALID_BIT, (unsigned long *)entry);
 }
 
 static int avic_handle_ldr_update(struct kvm_vcpu *vcpu)
@@ -5621,6 +5636,7 @@ static void svm_vcpu_run(struct kvm_vcpu *vcpu)
 	svm->vmcb->save.cr2 = vcpu->arch.cr2;
 
 	clgi();
+	kvm_load_guest_xcr0(vcpu);
 
 	/*
 	 * If this vCPU has touched SPEC_CTRL, restore the guest's value if
@@ -5766,6 +5782,7 @@ static void svm_vcpu_run(struct kvm_vcpu *vcpu)
 	if (unlikely(svm->vmcb->control.exit_code == SVM_EXIT_NMI))
 		kvm_before_interrupt(&svm->vcpu);
 
+	kvm_put_guest_xcr0(vcpu);
 	stgi();
 
 	/* Any pending NMI will happen here */
@@ -6215,32 +6232,24 @@ static int svm_pre_enter_smm(struct kvm_vcpu *vcpu, char *smstate)
 	return 0;
 }
 
-static int svm_pre_leave_smm(struct kvm_vcpu *vcpu, u64 smbase)
+static int svm_pre_leave_smm(struct kvm_vcpu *vcpu, const char *smstate)
 {
 	struct vcpu_svm *svm = to_svm(vcpu);
 	struct vmcb *nested_vmcb;
 	struct page *page;
-	struct {
-		u64 guest;
-		u64 vmcb;
-	} svm_state_save;
-	int ret;
+	u64 guest;
+	u64 vmcb;
 
-	ret = kvm_vcpu_read_guest(vcpu, smbase + 0xfed8, &svm_state_save,
-				  sizeof(svm_state_save));
-	if (ret)
-		return ret;
+	guest = GET_SMSTATE(u64, smstate, 0x7ed8);
+	vmcb = GET_SMSTATE(u64, smstate, 0x7ee0);
 
-	if (svm_state_save.guest) {
-		vcpu->arch.hflags &= ~HF_SMM_MASK;
-		nested_vmcb = nested_svm_map(svm, svm_state_save.vmcb, &page);
-		if (nested_vmcb)
-			enter_svm_guest_mode(svm, svm_state_save.vmcb, nested_vmcb, page);
-		else
-			ret = 1;
-		vcpu->arch.hflags |= HF_SMM_MASK;
+	if (guest) {
+		nested_vmcb = nested_svm_map(svm, vmcb, &page);
+		if (!nested_vmcb)
+			return 1;
+		enter_svm_guest_mode(svm, vmcb, nested_vmcb, page);
 	}
-	return ret;
+	return 0;
 }
 
 static int enable_smi_window(struct kvm_vcpu *vcpu)
@@ -6422,11 +6431,11 @@ e_free:
 	return ret;
 }
 
-static int get_num_contig_pages(int idx, struct page **inpages,
-				unsigned long npages)
+static unsigned long get_num_contig_pages(unsigned long idx,
+				struct page **inpages, unsigned long npages)
 {
 	unsigned long paddr, next_paddr;
-	int i = idx + 1, pages = 1;
+	unsigned long i = idx + 1, pages = 1;
 
 	/* find the number of contiguous pages starting from idx */
 	paddr = __sme_page_pa(inpages[idx]);
@@ -6445,12 +6454,12 @@ static int get_num_contig_pages(int idx, struct page **inpages,
 
 static int sev_launch_update_data(struct kvm *kvm, struct kvm_sev_cmd *argp)
 {
-	unsigned long vaddr, vaddr_end, next_vaddr, npages, size;
+	unsigned long vaddr, vaddr_end, next_vaddr, npages, pages, size, i;
 	struct kvm_sev_info *sev = &to_kvm_svm(kvm)->sev_info;
 	struct kvm_sev_launch_update_data params;
 	struct sev_data_launch_update_data *data;
 	struct page **inpages;
-	int i, ret, pages;
+	int ret;
 
 	if (!sev_guest(kvm))
 		return -ENOTTY;
@@ -6799,7 +6808,8 @@ static int sev_dbg_crypt(struct kvm *kvm, struct kvm_sev_cmd *argp, bool dec)
 	struct page **src_p, **dst_p;
 	struct kvm_sev_dbg debug;
 	unsigned long n;
-	int ret, size;
+	unsigned int size;
+	int ret;
 
 	if (!sev_guest(kvm))
 		return -ENOTTY;
@@ -6807,6 +6817,11 @@ static int sev_dbg_crypt(struct kvm *kvm, struct kvm_sev_cmd *argp, bool dec)
 	if (copy_from_user(&debug, (void __user *)(uintptr_t)argp->data, sizeof(debug)))
 		return -EFAULT;
 
+	if (!debug.len || debug.src_uaddr + debug.len < debug.src_uaddr)
+		return -EINVAL;
+	if (!debug.dst_uaddr)
+		return -EINVAL;
+
 	vaddr = debug.src_uaddr;
 	size = debug.len;
 	vaddr_end = vaddr + size;
@@ -6857,8 +6872,8 @@ static int sev_dbg_crypt(struct kvm *kvm, struct kvm_sev_cmd *argp, bool dec)
 						     dst_vaddr,
 						     len, &argp->error);
 
-		sev_unpin_memory(kvm, src_p, 1);
-		sev_unpin_memory(kvm, dst_p, 1);
+		sev_unpin_memory(kvm, src_p, n);
+		sev_unpin_memory(kvm, dst_p, n);
 
 		if (ret)
 			goto err;
@@ -7098,6 +7113,36 @@ static int nested_enable_evmcs(struct kvm_vcpu *vcpu,
 	return -ENODEV;
 }
 
+static bool svm_need_emulation_on_page_fault(struct kvm_vcpu *vcpu)
+{
+	bool is_user, smap;
+
+	is_user = svm_get_cpl(vcpu) == 3;
+	smap = !kvm_read_cr4_bits(vcpu, X86_CR4_SMAP);
+
+	/*
+	 * Detect and workaround Errata 1096 Fam_17h_00_0Fh
+	 *
+	 * In non SEV guest, hypervisor will be able to read the guest
+	 * memory to decode the instruction pointer when insn_len is zero
+	 * so we return true to indicate that decoding is possible.
+	 *
+	 * But in the SEV guest, the guest memory is encrypted with the
+	 * guest specific key and hypervisor will not be able to decode the
+	 * instruction pointer so we will not able to workaround it. Lets
+	 * print the error and request to kill the guest.
+	 */
+	if (is_user && smap) {
+		if (!sev_guest(vcpu->kvm))
+			return true;
+
+		pr_err_ratelimited("KVM: Guest triggered AMD Erratum 1096\n");
+		kvm_make_request(KVM_REQ_TRIPLE_FAULT, vcpu);
+	}
+
+	return false;
+}
+
 static struct kvm_x86_ops svm_x86_ops __ro_after_init = {
 	.cpu_has_kvm_support = has_svm,
 	.disabled_by_bios = is_disabled,
@@ -7231,6 +7276,8 @@ static struct kvm_x86_ops svm_x86_ops __ro_after_init = {
 
 	.nested_enable_evmcs = nested_enable_evmcs,
 	.nested_get_evmcs_version = nested_get_evmcs_version,
+
+	.need_emulation_on_page_fault = svm_need_emulation_on_page_fault,
 };
 
 static int __init svm_init(void)
diff --git a/arch/x86/kvm/trace.h b/arch/x86/kvm/trace.h
index 6432d08c7de7..4d47a2631d1f 100644
--- a/arch/x86/kvm/trace.h
+++ b/arch/x86/kvm/trace.h
@@ -438,13 +438,13 @@ TRACE_EVENT(kvm_apic_ipi,
 );
 
 TRACE_EVENT(kvm_apic_accept_irq,
-	    TP_PROTO(__u32 apicid, __u16 dm, __u8 tm, __u8 vec),
+	    TP_PROTO(__u32 apicid, __u16 dm, __u16 tm, __u8 vec),
 	    TP_ARGS(apicid, dm, tm, vec),
 
 	TP_STRUCT__entry(
 		__field(	__u32,		apicid		)
 		__field(	__u16,		dm		)
-		__field(	__u8,		tm		)
+		__field(	__u16,		tm		)
 		__field(	__u8,		vec		)
 	),
 
diff --git a/arch/x86/kvm/vmx/nested.c b/arch/x86/kvm/vmx/nested.c
index f24a2c225070..0c601d079cd2 100644
--- a/arch/x86/kvm/vmx/nested.c
+++ b/arch/x86/kvm/vmx/nested.c
@@ -500,6 +500,17 @@ static void nested_vmx_disable_intercept_for_msr(unsigned long *msr_bitmap_l1,
 	}
 }
 
+static inline void enable_x2apic_msr_intercepts(unsigned long *msr_bitmap) {
+	int msr;
+
+	for (msr = 0x800; msr <= 0x8ff; msr += BITS_PER_LONG) {
+		unsigned word = msr / BITS_PER_LONG;
+
+		msr_bitmap[word] = ~0;
+		msr_bitmap[word + (0x800 / sizeof(long))] = ~0;
+	}
+}
+
 /*
  * Merge L0's and L1's MSR bitmap, return false to indicate that
  * we do not use the hardware.
@@ -541,39 +552,44 @@ static inline bool nested_vmx_prepare_msr_bitmap(struct kvm_vcpu *vcpu,
 		return false;
 
 	msr_bitmap_l1 = (unsigned long *)kmap(page);
-	if (nested_cpu_has_apic_reg_virt(vmcs12)) {
-		/*
-		 * L0 need not intercept reads for MSRs between 0x800 and 0x8ff, it
-		 * just lets the processor take the value from the virtual-APIC page;
-		 * take those 256 bits directly from the L1 bitmap.
-		 */
-		for (msr = 0x800; msr <= 0x8ff; msr += BITS_PER_LONG) {
-			unsigned word = msr / BITS_PER_LONG;
-			msr_bitmap_l0[word] = msr_bitmap_l1[word];
-			msr_bitmap_l0[word + (0x800 / sizeof(long))] = ~0;
-		}
-	} else {
-		for (msr = 0x800; msr <= 0x8ff; msr += BITS_PER_LONG) {
-			unsigned word = msr / BITS_PER_LONG;
-			msr_bitmap_l0[word] = ~0;
-			msr_bitmap_l0[word + (0x800 / sizeof(long))] = ~0;
-		}
-	}
 
-	nested_vmx_disable_intercept_for_msr(
-		msr_bitmap_l1, msr_bitmap_l0,
-		X2APIC_MSR(APIC_TASKPRI),
-		MSR_TYPE_W);
+	/*
+	 * To keep the control flow simple, pay eight 8-byte writes (sixteen
+	 * 4-byte writes on 32-bit systems) up front to enable intercepts for
+	 * the x2APIC MSR range and selectively disable them below.
+	 */
+	enable_x2apic_msr_intercepts(msr_bitmap_l0);
+
+	if (nested_cpu_has_virt_x2apic_mode(vmcs12)) {
+		if (nested_cpu_has_apic_reg_virt(vmcs12)) {
+			/*
+			 * L0 need not intercept reads for MSRs between 0x800
+			 * and 0x8ff, it just lets the processor take the value
+			 * from the virtual-APIC page; take those 256 bits
+			 * directly from the L1 bitmap.
+			 */
+			for (msr = 0x800; msr <= 0x8ff; msr += BITS_PER_LONG) {
+				unsigned word = msr / BITS_PER_LONG;
+
+				msr_bitmap_l0[word] = msr_bitmap_l1[word];
+			}
+		}
 
-	if (nested_cpu_has_vid(vmcs12)) {
-		nested_vmx_disable_intercept_for_msr(
-			msr_bitmap_l1, msr_bitmap_l0,
-			X2APIC_MSR(APIC_EOI),
-			MSR_TYPE_W);
 		nested_vmx_disable_intercept_for_msr(
 			msr_bitmap_l1, msr_bitmap_l0,
-			X2APIC_MSR(APIC_SELF_IPI),
-			MSR_TYPE_W);
+			X2APIC_MSR(APIC_TASKPRI),
+			MSR_TYPE_R | MSR_TYPE_W);
+
+		if (nested_cpu_has_vid(vmcs12)) {
+			nested_vmx_disable_intercept_for_msr(
+				msr_bitmap_l1, msr_bitmap_l0,
+				X2APIC_MSR(APIC_EOI),
+				MSR_TYPE_W);
+			nested_vmx_disable_intercept_for_msr(
+				msr_bitmap_l1, msr_bitmap_l0,
+				X2APIC_MSR(APIC_SELF_IPI),
+				MSR_TYPE_W);
+		}
 	}
 
 	if (spec_ctrl)
@@ -2585,6 +2601,11 @@ static int nested_check_host_control_regs(struct kvm_vcpu *vcpu,
 	    !nested_host_cr4_valid(vcpu, vmcs12->host_cr4) ||
 	    !nested_cr3_valid(vcpu, vmcs12->host_cr3))
 		return -EINVAL;
+
+	if (is_noncanonical_address(vmcs12->host_ia32_sysenter_esp, vcpu) ||
+	    is_noncanonical_address(vmcs12->host_ia32_sysenter_eip, vcpu))
+		return -EINVAL;
+
 	/*
 	 * If the load IA32_EFER VM-exit control is 1, bits reserved in the
 	 * IA32_EFER MSR must be 0 in the field for that register. In addition,
@@ -2852,20 +2873,27 @@ static void nested_get_vmcs12_pages(struct kvm_vcpu *vcpu)
 		/*
 		 * If translation failed, VM entry will fail because
 		 * prepare_vmcs02 set VIRTUAL_APIC_PAGE_ADDR to -1ull.
-		 * Failing the vm entry is _not_ what the processor
-		 * does but it's basically the only possibility we
-		 * have.  We could still enter the guest if CR8 load
-		 * exits are enabled, CR8 store exits are enabled, and
-		 * virtualize APIC access is disabled; in this case
-		 * the processor would never use the TPR shadow and we
-		 * could simply clear the bit from the execution
-		 * control.  But such a configuration is useless, so
-		 * let's keep the code simple.
 		 */
 		if (!is_error_page(page)) {
 			vmx->nested.virtual_apic_page = page;
 			hpa = page_to_phys(vmx->nested.virtual_apic_page);
 			vmcs_write64(VIRTUAL_APIC_PAGE_ADDR, hpa);
+		} else if (nested_cpu_has(vmcs12, CPU_BASED_CR8_LOAD_EXITING) &&
+		           nested_cpu_has(vmcs12, CPU_BASED_CR8_STORE_EXITING) &&
+			   !nested_cpu_has2(vmcs12, SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES)) {
+			/*
+			 * The processor will never use the TPR shadow, simply
+			 * clear the bit from the execution control.  Such a
+			 * configuration is useless, but it happens in tests.
+			 * For any other configuration, failing the vm entry is
+			 * _not_ what the processor does but it's basically the
+			 * only possibility we have.
+			 */
+			vmcs_clear_bits(CPU_BASED_VM_EXEC_CONTROL,
+					CPU_BASED_TPR_SHADOW);
+		} else {
+			printk("bad virtual-APIC page address\n");
+			dump_vmcs();
 		}
 	}
 
@@ -3768,8 +3796,18 @@ static void nested_vmx_restore_host_state(struct kvm_vcpu *vcpu)
 	vmx_set_cr4(vcpu, vmcs_readl(CR4_READ_SHADOW));
 
 	nested_ept_uninit_mmu_context(vcpu);
-	vcpu->arch.cr3 = vmcs_readl(GUEST_CR3);
-	__set_bit(VCPU_EXREG_CR3, (ulong *)&vcpu->arch.regs_avail);
+
+	/*
+	 * This is only valid if EPT is in use, otherwise the vmcs01 GUEST_CR3
+	 * points to shadow pages!  Fortunately we only get here after a WARN_ON
+	 * if EPT is disabled, so a VMabort is perfectly fine.
+	 */
+	if (enable_ept) {
+		vcpu->arch.cr3 = vmcs_readl(GUEST_CR3);
+		__set_bit(VCPU_EXREG_CR3, (ulong *)&vcpu->arch.regs_avail);
+	} else {
+		nested_vmx_abort(vcpu, VMX_ABORT_VMCS_CORRUPTED);
+	}
 
 	/*
 	 * Use ept_save_pdptrs(vcpu) to load the MMU's cached PDPTRs
@@ -5385,7 +5423,7 @@ static int vmx_set_nested_state(struct kvm_vcpu *vcpu,
 		return ret;
 
 	/* Empty 'VMXON' state is permitted */
-	if (kvm_state->size < sizeof(kvm_state) + sizeof(*vmcs12))
+	if (kvm_state->size < sizeof(*kvm_state) + sizeof(*vmcs12))
 		return 0;
 
 	if (kvm_state->vmx.vmcs_pa != -1ull) {
@@ -5429,7 +5467,7 @@ static int vmx_set_nested_state(struct kvm_vcpu *vcpu,
 	    vmcs12->vmcs_link_pointer != -1ull) {
 		struct vmcs12 *shadow_vmcs12 = get_shadow_vmcs12(vcpu);
 
-		if (kvm_state->size < sizeof(kvm_state) + 2 * sizeof(*vmcs12))
+		if (kvm_state->size < sizeof(*kvm_state) + 2 * sizeof(*vmcs12))
 			return -EINVAL;
 
 		if (copy_from_user(shadow_vmcs12,
@@ -5717,6 +5755,14 @@ __init int nested_vmx_hardware_setup(int (*exit_handlers[])(struct kvm_vcpu *))
 {
 	int i;
 
+	/*
+	 * Without EPT it is not possible to restore L1's CR3 and PDPTR on
+	 * VMfail, because they are not available in vmcs01.  Just always
+	 * use hardware checks.
+	 */
+	if (!enable_ept)
+		nested_early_check = 1;
+
 	if (!cpu_has_vmx_shadow_vmcs())
 		enable_shadow_vmcs = 0;
 	if (enable_shadow_vmcs) {
diff --git a/arch/x86/kvm/vmx/vmenter.S b/arch/x86/kvm/vmx/vmenter.S
index 7b272738c576..d4cb1945b2e3 100644
--- a/arch/x86/kvm/vmx/vmenter.S
+++ b/arch/x86/kvm/vmx/vmenter.S
@@ -3,6 +3,7 @@
 #include <asm/asm.h>
 #include <asm/bitsperlong.h>
 #include <asm/kvm_vcpu_regs.h>
+#include <asm/nospec-branch.h>
 
 #define WORD_SIZE (BITS_PER_LONG / 8)
 
@@ -77,6 +78,17 @@ ENDPROC(vmx_vmenter)
  * referred to by VMCS.HOST_RIP.
  */
 ENTRY(vmx_vmexit)
+#ifdef CONFIG_RETPOLINE
+	ALTERNATIVE "jmp .Lvmexit_skip_rsb", "", X86_FEATURE_RETPOLINE
+	/* Preserve guest's RAX, it's used to stuff the RSB. */
+	push %_ASM_AX
+
+	/* IMPORTANT: Stuff the RSB immediately after VM-Exit, before RET! */
+	FILL_RETURN_BUFFER %_ASM_AX, RSB_CLEAR_LOOPS, X86_FEATURE_RETPOLINE
+
+	pop %_ASM_AX
+.Lvmexit_skip_rsb:
+#endif
 	ret
 ENDPROC(vmx_vmexit)
 
diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c
index c73375e01ab8..0c955bb286ff 100644
--- a/arch/x86/kvm/vmx/vmx.c
+++ b/arch/x86/kvm/vmx/vmx.c
@@ -1683,12 +1683,6 @@ static int vmx_get_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
 
 		msr_info->data = to_vmx(vcpu)->spec_ctrl;
 		break;
-	case MSR_IA32_ARCH_CAPABILITIES:
-		if (!msr_info->host_initiated &&
-		    !guest_cpuid_has(vcpu, X86_FEATURE_ARCH_CAPABILITIES))
-			return 1;
-		msr_info->data = to_vmx(vcpu)->arch_capabilities;
-		break;
 	case MSR_IA32_SYSENTER_CS:
 		msr_info->data = vmcs_read32(GUEST_SYSENTER_CS);
 		break;
@@ -1895,11 +1889,6 @@ static int vmx_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
 		vmx_disable_intercept_for_msr(vmx->vmcs01.msr_bitmap, MSR_IA32_PRED_CMD,
 					      MSR_TYPE_W);
 		break;
-	case MSR_IA32_ARCH_CAPABILITIES:
-		if (!msr_info->host_initiated)
-			return 1;
-		vmx->arch_capabilities = data;
-		break;
 	case MSR_IA32_CR_PAT:
 		if (vmcs_config.vmentry_ctrl & VM_ENTRY_LOAD_IA32_PAT) {
 			if (!kvm_mtrr_valid(vcpu, MSR_IA32_CR_PAT, data))
@@ -4088,8 +4077,6 @@ static void vmx_vcpu_setup(struct vcpu_vmx *vmx)
 		++vmx->nmsrs;
 	}
 
-	vmx->arch_capabilities = kvm_get_arch_capabilities();
-
 	vm_exit_controls_init(vmx, vmx_vmexit_ctrl());
 
 	/* 22.2.1, 20.8.1 */
@@ -5616,7 +5603,7 @@ static void vmx_dump_dtsel(char *name, uint32_t limit)
 	       vmcs_readl(limit + GUEST_GDTR_BASE - GUEST_GDTR_LIMIT));
 }
 
-static void dump_vmcs(void)
+void dump_vmcs(void)
 {
 	u32 vmentry_ctl = vmcs_read32(VM_ENTRY_CONTROLS);
 	u32 vmexit_ctl = vmcs_read32(VM_EXIT_CONTROLS);
@@ -6423,6 +6410,8 @@ static void vmx_vcpu_run(struct kvm_vcpu *vcpu)
 	if (vcpu->guest_debug & KVM_GUESTDBG_SINGLESTEP)
 		vmx_set_interrupt_shadow(vcpu, 0);
 
+	kvm_load_guest_xcr0(vcpu);
+
 	if (static_cpu_has(X86_FEATURE_PKU) &&
 	    kvm_read_cr4_bits(vcpu, X86_CR4_PKE) &&
 	    vcpu->arch.pkru != vmx->host_pkru)
@@ -6473,9 +6462,6 @@ static void vmx_vcpu_run(struct kvm_vcpu *vcpu)
 
 	x86_spec_ctrl_restore_host(vmx->spec_ctrl, 0);
 
-	/* Eliminate branch target predictions from guest mode */
-	vmexit_fill_RSB();
-
 	/* All fields are clean at this point */
 	if (static_branch_unlikely(&enable_evmcs))
 		current_evmcs->hv_clean_fields |=
@@ -6519,6 +6505,8 @@ static void vmx_vcpu_run(struct kvm_vcpu *vcpu)
 			__write_pkru(vmx->host_pkru);
 	}
 
+	kvm_put_guest_xcr0(vcpu);
+
 	vmx->nested.nested_run_pending = 0;
 	vmx->idt_vectoring_info = 0;
 
@@ -6865,6 +6853,30 @@ static void nested_vmx_entry_exit_ctls_update(struct kvm_vcpu *vcpu)
 	}
 }
 
+static bool guest_cpuid_has_pmu(struct kvm_vcpu *vcpu)
+{
+	struct kvm_cpuid_entry2 *entry;
+	union cpuid10_eax eax;
+
+	entry = kvm_find_cpuid_entry(vcpu, 0xa, 0);
+	if (!entry)
+		return false;
+
+	eax.full = entry->eax;
+	return (eax.split.version_id > 0);
+}
+
+static void nested_vmx_procbased_ctls_update(struct kvm_vcpu *vcpu)
+{
+	struct vcpu_vmx *vmx = to_vmx(vcpu);
+	bool pmu_enabled = guest_cpuid_has_pmu(vcpu);
+
+	if (pmu_enabled)
+		vmx->nested.msrs.procbased_ctls_high |= CPU_BASED_RDPMC_EXITING;
+	else
+		vmx->nested.msrs.procbased_ctls_high &= ~CPU_BASED_RDPMC_EXITING;
+}
+
 static void update_intel_pt_cfg(struct kvm_vcpu *vcpu)
 {
 	struct vcpu_vmx *vmx = to_vmx(vcpu);
@@ -6953,6 +6965,7 @@ static void vmx_cpuid_update(struct kvm_vcpu *vcpu)
 	if (nested_vmx_allowed(vcpu)) {
 		nested_vmx_cr_fixed1_bits_update(vcpu);
 		nested_vmx_entry_exit_ctls_update(vcpu);
+		nested_vmx_procbased_ctls_update(vcpu);
 	}
 
 	if (boot_cpu_has(X86_FEATURE_INTEL_PT) &&
@@ -7016,6 +7029,7 @@ static int vmx_set_hv_timer(struct kvm_vcpu *vcpu, u64 guest_deadline_tsc)
 {
 	struct vcpu_vmx *vmx;
 	u64 tscl, guest_tscl, delta_tsc, lapic_timer_advance_cycles;
+	struct kvm_timer *ktimer = &vcpu->arch.apic->lapic_timer;
 
 	if (kvm_mwait_in_guest(vcpu->kvm))
 		return -EOPNOTSUPP;
@@ -7024,7 +7038,8 @@ static int vmx_set_hv_timer(struct kvm_vcpu *vcpu, u64 guest_deadline_tsc)
 	tscl = rdtsc();
 	guest_tscl = kvm_read_l1_tsc(vcpu, tscl);
 	delta_tsc = max(guest_deadline_tsc, guest_tscl) - guest_tscl;
-	lapic_timer_advance_cycles = nsec_to_cycles(vcpu, lapic_timer_advance_ns);
+	lapic_timer_advance_cycles = nsec_to_cycles(vcpu,
+						    ktimer->timer_advance_ns);
 
 	if (delta_tsc > lapic_timer_advance_cycles)
 		delta_tsc -= lapic_timer_advance_cycles;
@@ -7382,7 +7397,7 @@ static int vmx_pre_enter_smm(struct kvm_vcpu *vcpu, char *smstate)
 	return 0;
 }
 
-static int vmx_pre_leave_smm(struct kvm_vcpu *vcpu, u64 smbase)
+static int vmx_pre_leave_smm(struct kvm_vcpu *vcpu, const char *smstate)
 {
 	struct vcpu_vmx *vmx = to_vmx(vcpu);
 	int ret;
@@ -7393,9 +7408,7 @@ static int vmx_pre_leave_smm(struct kvm_vcpu *vcpu, u64 smbase)
 	}
 
 	if (vmx->nested.smm.guest_mode) {
-		vcpu->arch.hflags &= ~HF_SMM_MASK;
 		ret = nested_vmx_enter_non_root_mode(vcpu, false);
-		vcpu->arch.hflags |= HF_SMM_MASK;
 		if (ret)
 			return ret;
 
@@ -7409,6 +7422,11 @@ static int enable_smi_window(struct kvm_vcpu *vcpu)
 	return 0;
 }
 
+static bool vmx_need_emulation_on_page_fault(struct kvm_vcpu *vcpu)
+{
+	return 0;
+}
+
 static __init int hardware_setup(void)
 {
 	unsigned long host_bndcfgs;
@@ -7711,6 +7729,7 @@ static struct kvm_x86_ops vmx_x86_ops __ro_after_init = {
 	.set_nested_state = NULL,
 	.get_vmcs12_pages = NULL,
 	.nested_enable_evmcs = NULL,
+	.need_emulation_on_page_fault = vmx_need_emulation_on_page_fault,
 };
 
 static void vmx_cleanup_l1d_flush(void)
diff --git a/arch/x86/kvm/vmx/vmx.h b/arch/x86/kvm/vmx/vmx.h
index 1554cb45b393..f879529906b4 100644
--- a/arch/x86/kvm/vmx/vmx.h
+++ b/arch/x86/kvm/vmx/vmx.h
@@ -190,7 +190,6 @@ struct vcpu_vmx {
 	u64		      msr_guest_kernel_gs_base;
 #endif
 
-	u64		      arch_capabilities;
 	u64		      spec_ctrl;
 
 	u32 vm_entry_controls_shadow;
@@ -518,4 +517,6 @@ static inline void decache_tsc_multiplier(struct vcpu_vmx *vmx)
 	vmcs_write64(TSC_MULTIPLIER, vmx->current_tsc_ratio);
 }
 
+void dump_vmcs(void);
+
 #endif /* __KVM_X86_VMX_H */
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 65e4559eef2f..b5edc8e3ce1d 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -136,10 +136,14 @@ EXPORT_SYMBOL_GPL(kvm_default_tsc_scaling_ratio);
 static u32 __read_mostly tsc_tolerance_ppm = 250;
 module_param(tsc_tolerance_ppm, uint, S_IRUGO | S_IWUSR);
 
-/* lapic timer advance (tscdeadline mode only) in nanoseconds */
-unsigned int __read_mostly lapic_timer_advance_ns = 1000;
+/*
+ * lapic timer advance (tscdeadline mode only) in nanoseconds.  '-1' enables
+ * adaptive tuning starting from default advancment of 1000ns.  '0' disables
+ * advancement entirely.  Any other value is used as-is and disables adaptive
+ * tuning, i.e. allows priveleged userspace to set an exact advancement time.
+ */
+static int __read_mostly lapic_timer_advance_ns = -1;
 module_param(lapic_timer_advance_ns, uint, S_IRUGO | S_IWUSR);
-EXPORT_SYMBOL_GPL(lapic_timer_advance_ns);
 
 static bool __read_mostly vector_hashing = true;
 module_param(vector_hashing, bool, S_IRUGO);
@@ -800,7 +804,7 @@ void kvm_lmsw(struct kvm_vcpu *vcpu, unsigned long msw)
 }
 EXPORT_SYMBOL_GPL(kvm_lmsw);
 
-static void kvm_load_guest_xcr0(struct kvm_vcpu *vcpu)
+void kvm_load_guest_xcr0(struct kvm_vcpu *vcpu)
 {
 	if (kvm_read_cr4_bits(vcpu, X86_CR4_OSXSAVE) &&
 			!vcpu->guest_xcr0_loaded) {
@@ -810,8 +814,9 @@ static void kvm_load_guest_xcr0(struct kvm_vcpu *vcpu)
 		vcpu->guest_xcr0_loaded = 1;
 	}
 }
+EXPORT_SYMBOL_GPL(kvm_load_guest_xcr0);
 
-static void kvm_put_guest_xcr0(struct kvm_vcpu *vcpu)
+void kvm_put_guest_xcr0(struct kvm_vcpu *vcpu)
 {
 	if (vcpu->guest_xcr0_loaded) {
 		if (vcpu->arch.xcr0 != host_xcr0)
@@ -819,6 +824,7 @@ static void kvm_put_guest_xcr0(struct kvm_vcpu *vcpu)
 		vcpu->guest_xcr0_loaded = 0;
 	}
 }
+EXPORT_SYMBOL_GPL(kvm_put_guest_xcr0);
 
 static int __kvm_set_xcr(struct kvm_vcpu *vcpu, u32 index, u64 xcr)
 {
@@ -1125,7 +1131,7 @@ static u32 msrs_to_save[] = {
 #endif
 	MSR_IA32_TSC, MSR_IA32_CR_PAT, MSR_VM_HSAVE_PA,
 	MSR_IA32_FEATURE_CONTROL, MSR_IA32_BNDCFGS, MSR_TSC_AUX,
-	MSR_IA32_SPEC_CTRL, MSR_IA32_ARCH_CAPABILITIES,
+	MSR_IA32_SPEC_CTRL,
 	MSR_IA32_RTIT_CTL, MSR_IA32_RTIT_STATUS, MSR_IA32_RTIT_CR3_MATCH,
 	MSR_IA32_RTIT_OUTPUT_BASE, MSR_IA32_RTIT_OUTPUT_MASK,
 	MSR_IA32_RTIT_ADDR0_A, MSR_IA32_RTIT_ADDR0_B,
@@ -1158,6 +1164,7 @@ static u32 emulated_msrs[] = {
 
 	MSR_IA32_TSC_ADJUST,
 	MSR_IA32_TSCDEADLINE,
+	MSR_IA32_ARCH_CAPABILITIES,
 	MSR_IA32_MISC_ENABLE,
 	MSR_IA32_MCG_STATUS,
 	MSR_IA32_MCG_CTL,
@@ -2443,6 +2450,11 @@ int kvm_set_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
 		if (msr_info->host_initiated)
 			vcpu->arch.microcode_version = data;
 		break;
+	case MSR_IA32_ARCH_CAPABILITIES:
+		if (!msr_info->host_initiated)
+			return 1;
+		vcpu->arch.arch_capabilities = data;
+		break;
 	case MSR_EFER:
 		return set_efer(vcpu, data);
 	case MSR_K7_HWCR:
@@ -2747,6 +2759,12 @@ int kvm_get_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
 	case MSR_IA32_UCODE_REV:
 		msr_info->data = vcpu->arch.microcode_version;
 		break;
+	case MSR_IA32_ARCH_CAPABILITIES:
+		if (!msr_info->host_initiated &&
+		    !guest_cpuid_has(vcpu, X86_FEATURE_ARCH_CAPABILITIES))
+			return 1;
+		msr_info->data = vcpu->arch.arch_capabilities;
+		break;
 	case MSR_IA32_TSC:
 		msr_info->data = kvm_scale_tsc(vcpu, rdtsc()) + vcpu->arch.tsc_offset;
 		break;
@@ -3081,7 +3099,7 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext)
 		break;
 	case KVM_CAP_NESTED_STATE:
 		r = kvm_x86_ops->get_nested_state ?
-			kvm_x86_ops->get_nested_state(NULL, 0, 0) : 0;
+			kvm_x86_ops->get_nested_state(NULL, NULL, 0) : 0;
 		break;
 	default:
 		break;
@@ -3516,7 +3534,7 @@ static void kvm_vcpu_ioctl_x86_get_vcpu_events(struct kvm_vcpu *vcpu,
 	memset(&events->reserved, 0, sizeof(events->reserved));
 }
 
-static void kvm_set_hflags(struct kvm_vcpu *vcpu, unsigned emul_flags);
+static void kvm_smm_changed(struct kvm_vcpu *vcpu);
 
 static int kvm_vcpu_ioctl_x86_set_vcpu_events(struct kvm_vcpu *vcpu,
 					      struct kvm_vcpu_events *events)
@@ -3576,12 +3594,13 @@ static int kvm_vcpu_ioctl_x86_set_vcpu_events(struct kvm_vcpu *vcpu,
 		vcpu->arch.apic->sipi_vector = events->sipi_vector;
 
 	if (events->flags & KVM_VCPUEVENT_VALID_SMM) {
-		u32 hflags = vcpu->arch.hflags;
-		if (events->smi.smm)
-			hflags |= HF_SMM_MASK;
-		else
-			hflags &= ~HF_SMM_MASK;
-		kvm_set_hflags(vcpu, hflags);
+		if (!!(vcpu->arch.hflags & HF_SMM_MASK) != events->smi.smm) {
+			if (events->smi.smm)
+				vcpu->arch.hflags |= HF_SMM_MASK;
+			else
+				vcpu->arch.hflags &= ~HF_SMM_MASK;
+			kvm_smm_changed(vcpu);
+		}
 
 		vcpu->arch.smi_pending = events->smi.pending;
 
@@ -4258,7 +4277,7 @@ static int kvm_vm_ioctl_set_identity_map_addr(struct kvm *kvm,
 }
 
 static int kvm_vm_ioctl_set_nr_mmu_pages(struct kvm *kvm,
-					  u32 kvm_nr_mmu_pages)
+					 unsigned long kvm_nr_mmu_pages)
 {
 	if (kvm_nr_mmu_pages < KVM_MIN_ALLOC_MMU_PAGES)
 		return -EINVAL;
@@ -4272,7 +4291,7 @@ static int kvm_vm_ioctl_set_nr_mmu_pages(struct kvm *kvm,
 	return 0;
 }
 
-static int kvm_vm_ioctl_get_nr_mmu_pages(struct kvm *kvm)
+static unsigned long kvm_vm_ioctl_get_nr_mmu_pages(struct kvm *kvm)
 {
 	return kvm->arch.n_max_mmu_pages;
 }
@@ -5946,12 +5965,18 @@ static unsigned emulator_get_hflags(struct x86_emulate_ctxt *ctxt)
 
 static void emulator_set_hflags(struct x86_emulate_ctxt *ctxt, unsigned emul_flags)
 {
-	kvm_set_hflags(emul_to_vcpu(ctxt), emul_flags);
+	emul_to_vcpu(ctxt)->arch.hflags = emul_flags;
 }
 
-static int emulator_pre_leave_smm(struct x86_emulate_ctxt *ctxt, u64 smbase)
+static int emulator_pre_leave_smm(struct x86_emulate_ctxt *ctxt,
+				  const char *smstate)
 {
-	return kvm_x86_ops->pre_leave_smm(emul_to_vcpu(ctxt), smbase);
+	return kvm_x86_ops->pre_leave_smm(emul_to_vcpu(ctxt), smstate);
+}
+
+static void emulator_post_leave_smm(struct x86_emulate_ctxt *ctxt)
+{
+	kvm_smm_changed(emul_to_vcpu(ctxt));
 }
 
 static const struct x86_emulate_ops emulate_ops = {
@@ -5994,6 +6019,7 @@ static const struct x86_emulate_ops emulate_ops = {
 	.get_hflags          = emulator_get_hflags,
 	.set_hflags          = emulator_set_hflags,
 	.pre_leave_smm       = emulator_pre_leave_smm,
+	.post_leave_smm      = emulator_post_leave_smm,
 };
 
 static void toggle_interruptibility(struct kvm_vcpu *vcpu, u32 mask)
@@ -6235,16 +6261,6 @@ static void kvm_smm_changed(struct kvm_vcpu *vcpu)
 	kvm_mmu_reset_context(vcpu);
 }
 
-static void kvm_set_hflags(struct kvm_vcpu *vcpu, unsigned emul_flags)
-{
-	unsigned changed = vcpu->arch.hflags ^ emul_flags;
-
-	vcpu->arch.hflags = emul_flags;
-
-	if (changed & HF_SMM_MASK)
-		kvm_smm_changed(vcpu);
-}
-
 static int kvm_vcpu_check_hw_bp(unsigned long addr, u32 type, u32 dr7,
 				unsigned long *db)
 {
@@ -6523,15 +6539,45 @@ int kvm_emulate_instruction_from_buffer(struct kvm_vcpu *vcpu,
 }
 EXPORT_SYMBOL_GPL(kvm_emulate_instruction_from_buffer);
 
+static int complete_fast_pio_out_port_0x7e(struct kvm_vcpu *vcpu)
+{
+	vcpu->arch.pio.count = 0;
+	return 1;
+}
+
+static int complete_fast_pio_out(struct kvm_vcpu *vcpu)
+{
+	vcpu->arch.pio.count = 0;
+
+	if (unlikely(!kvm_is_linear_rip(vcpu, vcpu->arch.pio.linear_rip)))
+		return 1;
+
+	return kvm_skip_emulated_instruction(vcpu);
+}
+
 static int kvm_fast_pio_out(struct kvm_vcpu *vcpu, int size,
 			    unsigned short port)
 {
 	unsigned long val = kvm_register_read(vcpu, VCPU_REGS_RAX);
 	int ret = emulator_pio_out_emulated(&vcpu->arch.emulate_ctxt,
 					    size, port, &val, 1);
-	/* do not return to emulator after return from userspace */
-	vcpu->arch.pio.count = 0;
-	return ret;
+	if (ret)
+		return ret;
+
+	/*
+	 * Workaround userspace that relies on old KVM behavior of %rip being
+	 * incremented prior to exiting to userspace to handle "OUT 0x7e".
+	 */
+	if (port == 0x7e &&
+	    kvm_check_has_quirk(vcpu->kvm, KVM_X86_QUIRK_OUT_7E_INC_RIP)) {
+		vcpu->arch.complete_userspace_io =
+			complete_fast_pio_out_port_0x7e;
+		kvm_skip_emulated_instruction(vcpu);
+	} else {
+		vcpu->arch.pio.linear_rip = kvm_get_linear_rip(vcpu);
+		vcpu->arch.complete_userspace_io = complete_fast_pio_out;
+	}
+	return 0;
 }
 
 static int complete_fast_pio_in(struct kvm_vcpu *vcpu)
@@ -6541,6 +6587,11 @@ static int complete_fast_pio_in(struct kvm_vcpu *vcpu)
 	/* We should only ever be called with arch.pio.count equal to 1 */
 	BUG_ON(vcpu->arch.pio.count != 1);
 
+	if (unlikely(!kvm_is_linear_rip(vcpu, vcpu->arch.pio.linear_rip))) {
+		vcpu->arch.pio.count = 0;
+		return 1;
+	}
+
 	/* For size less than 4 we merge, else we zero extend */
 	val = (vcpu->arch.pio.size < 4) ? kvm_register_read(vcpu, VCPU_REGS_RAX)
 					: 0;
@@ -6553,7 +6604,7 @@ static int complete_fast_pio_in(struct kvm_vcpu *vcpu)
 				 vcpu->arch.pio.port, &val, 1);
 	kvm_register_write(vcpu, VCPU_REGS_RAX, val);
 
-	return 1;
+	return kvm_skip_emulated_instruction(vcpu);
 }
 
 static int kvm_fast_pio_in(struct kvm_vcpu *vcpu, int size,
@@ -6572,6 +6623,7 @@ static int kvm_fast_pio_in(struct kvm_vcpu *vcpu, int size,
 		return ret;
 	}
 
+	vcpu->arch.pio.linear_rip = kvm_get_linear_rip(vcpu);
 	vcpu->arch.complete_userspace_io = complete_fast_pio_in;
 
 	return 0;
@@ -6579,16 +6631,13 @@ static int kvm_fast_pio_in(struct kvm_vcpu *vcpu, int size,
 
 int kvm_fast_pio(struct kvm_vcpu *vcpu, int size, unsigned short port, int in)
 {
-	int ret = kvm_skip_emulated_instruction(vcpu);
+	int ret;
 
-	/*
-	 * TODO: we might be squashing a KVM_GUESTDBG_SINGLESTEP-triggered
-	 * KVM_EXIT_DEBUG here.
-	 */
 	if (in)
-		return kvm_fast_pio_in(vcpu, size, port) && ret;
+		ret = kvm_fast_pio_in(vcpu, size, port);
 	else
-		return kvm_fast_pio_out(vcpu, size, port) && ret;
+		ret = kvm_fast_pio_out(vcpu, size, port);
+	return ret && kvm_skip_emulated_instruction(vcpu);
 }
 EXPORT_SYMBOL_GPL(kvm_fast_pio);
 
@@ -7413,9 +7462,9 @@ static void enter_smm_save_state_32(struct kvm_vcpu *vcpu, char *buf)
 	put_smstate(u32, buf, 0x7ef8, vcpu->arch.smbase);
 }
 
+#ifdef CONFIG_X86_64
 static void enter_smm_save_state_64(struct kvm_vcpu *vcpu, char *buf)
 {
-#ifdef CONFIG_X86_64
 	struct desc_ptr dt;
 	struct kvm_segment seg;
 	unsigned long val;
@@ -7465,10 +7514,8 @@ static void enter_smm_save_state_64(struct kvm_vcpu *vcpu, char *buf)
 
 	for (i = 0; i < 6; i++)
 		enter_smm_save_seg_64(vcpu, buf, i);
-#else
-	WARN_ON_ONCE(1);
-#endif
 }
+#endif
 
 static void enter_smm(struct kvm_vcpu *vcpu)
 {
@@ -7479,9 +7526,11 @@ static void enter_smm(struct kvm_vcpu *vcpu)
 
 	trace_kvm_enter_smm(vcpu->vcpu_id, vcpu->arch.smbase, true);
 	memset(buf, 0, 512);
+#ifdef CONFIG_X86_64
 	if (guest_cpuid_has(vcpu, X86_FEATURE_LM))
 		enter_smm_save_state_64(vcpu, buf);
 	else
+#endif
 		enter_smm_save_state_32(vcpu, buf);
 
 	/*
@@ -7539,8 +7588,10 @@ static void enter_smm(struct kvm_vcpu *vcpu)
 	kvm_set_segment(vcpu, &ds, VCPU_SREG_GS);
 	kvm_set_segment(vcpu, &ds, VCPU_SREG_SS);
 
+#ifdef CONFIG_X86_64
 	if (guest_cpuid_has(vcpu, X86_FEATURE_LM))
 		kvm_x86_ops->set_efer(vcpu, 0);
+#endif
 
 	kvm_update_cpuid(vcpu);
 	kvm_mmu_reset_context(vcpu);
@@ -7837,15 +7888,14 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu)
 		goto cancel_injection;
 	}
 
-	kvm_load_guest_xcr0(vcpu);
-
 	if (req_immediate_exit) {
 		kvm_make_request(KVM_REQ_EVENT, vcpu);
 		kvm_x86_ops->request_immediate_exit(vcpu);
 	}
 
 	trace_kvm_entry(vcpu->vcpu_id);
-	if (lapic_timer_advance_ns)
+	if (lapic_in_kernel(vcpu) &&
+	    vcpu->arch.apic->lapic_timer.timer_advance_ns)
 		wait_lapic_expire(vcpu);
 	guest_enter_irqoff();
 
@@ -7891,8 +7941,6 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu)
 	vcpu->mode = OUTSIDE_GUEST_MODE;
 	smp_wmb();
 
-	kvm_put_guest_xcr0(vcpu);
-
 	kvm_before_interrupt(vcpu);
 	kvm_x86_ops->handle_external_intr(vcpu);
 	kvm_after_interrupt(vcpu);
@@ -8733,6 +8781,7 @@ struct kvm_vcpu *kvm_arch_vcpu_create(struct kvm *kvm,
 
 int kvm_arch_vcpu_setup(struct kvm_vcpu *vcpu)
 {
+	vcpu->arch.arch_capabilities = kvm_get_arch_capabilities();
 	vcpu->arch.msr_platform_info = MSR_PLATFORM_INFO_CPUID_FAULT;
 	kvm_vcpu_mtrr_init(vcpu);
 	vcpu_load(vcpu);
@@ -9034,7 +9083,7 @@ int kvm_arch_vcpu_init(struct kvm_vcpu *vcpu)
 
 	if (irqchip_in_kernel(vcpu->kvm)) {
 		vcpu->arch.apicv_active = kvm_x86_ops->get_enable_apicv(vcpu);
-		r = kvm_create_lapic(vcpu);
+		r = kvm_create_lapic(vcpu, lapic_timer_advance_ns);
 		if (r < 0)
 			goto fail_mmu_destroy;
 	} else
@@ -9429,13 +9478,9 @@ void kvm_arch_commit_memory_region(struct kvm *kvm,
 				const struct kvm_memory_slot *new,
 				enum kvm_mr_change change)
 {
-	int nr_mmu_pages = 0;
-
 	if (!kvm->arch.n_requested_mmu_pages)
-		nr_mmu_pages = kvm_mmu_calculate_mmu_pages(kvm);
-
-	if (nr_mmu_pages)
-		kvm_mmu_change_mmu_pages(kvm, nr_mmu_pages);
+		kvm_mmu_change_mmu_pages(kvm,
+				kvm_mmu_calculate_default_mmu_pages(kvm));
 
 	/*
 	 * Dirty logging tracks sptes in 4k granularity, meaning that large
diff --git a/arch/x86/kvm/x86.h b/arch/x86/kvm/x86.h
index 28406aa1136d..534d3f28bb01 100644
--- a/arch/x86/kvm/x86.h
+++ b/arch/x86/kvm/x86.h
@@ -294,8 +294,6 @@ extern u64 kvm_supported_xcr0(void);
 
 extern unsigned int min_timer_period_us;
 
-extern unsigned int lapic_timer_advance_ns;
-
 extern bool enable_vmware_backdoor;
 
 extern struct static_key kvm_no_apic_vcpu;
@@ -347,4 +345,6 @@ static inline void kvm_after_interrupt(struct kvm_vcpu *vcpu)
 	__this_cpu_write(current_vcpu, NULL);
 }
 
+void kvm_load_guest_xcr0(struct kvm_vcpu *vcpu);
+void kvm_put_guest_xcr0(struct kvm_vcpu *vcpu);
 #endif
diff --git a/arch/x86/lib/Makefile b/arch/x86/lib/Makefile
index 140e61843a07..5246db42de45 100644
--- a/arch/x86/lib/Makefile
+++ b/arch/x86/lib/Makefile
@@ -6,6 +6,18 @@
 # Produces uninteresting flaky coverage.
 KCOV_INSTRUMENT_delay.o	:= n
 
+# Early boot use of cmdline; don't instrument it
+ifdef CONFIG_AMD_MEM_ENCRYPT
+KCOV_INSTRUMENT_cmdline.o := n
+KASAN_SANITIZE_cmdline.o  := n
+
+ifdef CONFIG_FUNCTION_TRACER
+CFLAGS_REMOVE_cmdline.o = -pg
+endif
+
+CFLAGS_cmdline.o := $(call cc-option, -fno-stack-protector)
+endif
+
 inat_tables_script = $(srctree)/arch/x86/tools/gen-insn-attr-x86.awk
 inat_tables_maps = $(srctree)/arch/x86/lib/x86-opcode-map.txt
 quiet_cmd_inat_tables = GEN     $@
@@ -23,7 +35,6 @@ obj-$(CONFIG_SMP) += msr-smp.o cache-smp.o
 lib-y := delay.o misc.o cmdline.o cpu.o
 lib-y += usercopy_$(BITS).o usercopy.o getuser.o putuser.o
 lib-y += memcpy_$(BITS).o
-lib-$(CONFIG_RWSEM_XCHGADD_ALGORITHM) += rwsem.o
 lib-$(CONFIG_INSTRUCTION_DECODER) += insn.o inat.o insn-eval.o
 lib-$(CONFIG_RANDOMIZE_BASE) += kaslr.o
 lib-$(CONFIG_FUNCTION_ERROR_INJECTION)	+= error-inject.o
diff --git a/arch/x86/lib/copy_user_64.S b/arch/x86/lib/copy_user_64.S
index db4e5aa0858b..b2f1822084ae 100644
--- a/arch/x86/lib/copy_user_64.S
+++ b/arch/x86/lib/copy_user_64.S
@@ -16,6 +16,30 @@
 #include <asm/smap.h>
 #include <asm/export.h>
 
+.macro ALIGN_DESTINATION
+	/* check for bad alignment of destination */
+	movl %edi,%ecx
+	andl $7,%ecx
+	jz 102f				/* already aligned */
+	subl $8,%ecx
+	negl %ecx
+	subl %ecx,%edx
+100:	movb (%rsi),%al
+101:	movb %al,(%rdi)
+	incq %rsi
+	incq %rdi
+	decl %ecx
+	jnz 100b
+102:
+	.section .fixup,"ax"
+103:	addl %ecx,%edx			/* ecx is zerorest also */
+	jmp copy_user_handle_tail
+	.previous
+
+	_ASM_EXTABLE_UA(100b, 103b)
+	_ASM_EXTABLE_UA(101b, 103b)
+	.endm
+
 /*
  * copy_user_generic_unrolled - memory copy with exception handling.
  * This version is for CPUs like P4 that don't have efficient micro
@@ -194,6 +218,30 @@ ENDPROC(copy_user_enhanced_fast_string)
 EXPORT_SYMBOL(copy_user_enhanced_fast_string)
 
 /*
+ * Try to copy last bytes and clear the rest if needed.
+ * Since protection fault in copy_from/to_user is not a normal situation,
+ * it is not necessary to optimize tail handling.
+ *
+ * Input:
+ * rdi destination
+ * rsi source
+ * rdx count
+ *
+ * Output:
+ * eax uncopied bytes or 0 if successful.
+ */
+ALIGN;
+copy_user_handle_tail:
+	movl %edx,%ecx
+1:	rep movsb
+2:	mov %ecx,%eax
+	ASM_CLAC
+	ret
+
+	_ASM_EXTABLE_UA(1b, 2b)
+ENDPROC(copy_user_handle_tail)
+
+/*
  * copy_user_nocache - Uncached memory copy with exception handling
  * This will force destination out of cache for more performance.
  *
diff --git a/arch/x86/lib/delay.c b/arch/x86/lib/delay.c
index f5b7f1b3b6d7..b7375dc6898f 100644
--- a/arch/x86/lib/delay.c
+++ b/arch/x86/lib/delay.c
@@ -162,7 +162,7 @@ void __delay(unsigned long loops)
 }
 EXPORT_SYMBOL(__delay);
 
-void __const_udelay(unsigned long xloops)
+noinline void __const_udelay(unsigned long xloops)
 {
 	unsigned long lpj = this_cpu_read(cpu_info.loops_per_jiffy) ? : loops_per_jiffy;
 	int d0;
diff --git a/arch/x86/lib/error-inject.c b/arch/x86/lib/error-inject.c
index 3cdf06128d13..be5b5fb1598b 100644
--- a/arch/x86/lib/error-inject.c
+++ b/arch/x86/lib/error-inject.c
@@ -6,6 +6,7 @@
 asmlinkage void just_return_func(void);
 
 asm(
+	".text\n"
 	".type just_return_func, @function\n"
 	".globl just_return_func\n"
 	"just_return_func:\n"
diff --git a/arch/x86/lib/memcpy_64.S b/arch/x86/lib/memcpy_64.S
index 3b24dc05251c..9d05572370ed 100644
--- a/arch/x86/lib/memcpy_64.S
+++ b/arch/x86/lib/memcpy_64.S
@@ -257,6 +257,7 @@ ENTRY(__memcpy_mcsafe)
 	/* Copy successful. Return zero */
 .L_done_memcpy_trap:
 	xorl %eax, %eax
+.L_done:
 	ret
 ENDPROC(__memcpy_mcsafe)
 EXPORT_SYMBOL_GPL(__memcpy_mcsafe)
@@ -273,7 +274,7 @@ EXPORT_SYMBOL_GPL(__memcpy_mcsafe)
 	addl	%edx, %ecx
 .E_trailing_bytes:
 	mov	%ecx, %eax
-	ret
+	jmp	.L_done
 
 	/*
 	 * For write fault handling, given the destination is unaligned,
diff --git a/arch/x86/lib/rwsem.S b/arch/x86/lib/rwsem.S
deleted file mode 100644
index dc2ab6ea6768..000000000000
--- a/arch/x86/lib/rwsem.S
+++ /dev/null
@@ -1,156 +0,0 @@
-/*
- * x86 semaphore implementation.
- *
- * (C) Copyright 1999 Linus Torvalds
- *
- * Portions Copyright 1999 Red Hat, Inc.
- *
- *	This program is free software; you can redistribute it and/or
- *	modify it under the terms of the GNU General Public License
- *	as published by the Free Software Foundation; either version
- *	2 of the License, or (at your option) any later version.
- *
- * rw semaphores implemented November 1999 by Benjamin LaHaise <bcrl@kvack.org>
- */
-
-#include <linux/linkage.h>
-#include <asm/alternative-asm.h>
-#include <asm/frame.h>
-
-#define __ASM_HALF_REG(reg)	__ASM_SEL(reg, e##reg)
-#define __ASM_HALF_SIZE(inst)	__ASM_SEL(inst##w, inst##l)
-
-#ifdef CONFIG_X86_32
-
-/*
- * The semaphore operations have a special calling sequence that
- * allow us to do a simpler in-line version of them. These routines
- * need to convert that sequence back into the C sequence when
- * there is contention on the semaphore.
- *
- * %eax contains the semaphore pointer on entry. Save the C-clobbered
- * registers (%eax, %edx and %ecx) except %eax which is either a return
- * value or just gets clobbered. Same is true for %edx so make sure GCC
- * reloads it after the slow path, by making it hold a temporary, for
- * example see ____down_write().
- */
-
-#define save_common_regs \
-	pushl %ecx
-
-#define restore_common_regs \
-	popl %ecx
-
-	/* Avoid uglifying the argument copying x86-64 needs to do. */
-	.macro movq src, dst
-	.endm
-
-#else
-
-/*
- * x86-64 rwsem wrappers
- *
- * This interfaces the inline asm code to the slow-path
- * C routines. We need to save the call-clobbered regs
- * that the asm does not mark as clobbered, and move the
- * argument from %rax to %rdi.
- *
- * NOTE! We don't need to save %rax, because the functions
- * will always return the semaphore pointer in %rax (which
- * is also the input argument to these helpers)
- *
- * The following can clobber %rdx because the asm clobbers it:
- *   call_rwsem_down_write_failed
- *   call_rwsem_wake
- * but %rdi, %rsi, %rcx, %r8-r11 always need saving.
- */
-
-#define save_common_regs \
-	pushq %rdi; \
-	pushq %rsi; \
-	pushq %rcx; \
-	pushq %r8;  \
-	pushq %r9;  \
-	pushq %r10; \
-	pushq %r11
-
-#define restore_common_regs \
-	popq %r11; \
-	popq %r10; \
-	popq %r9; \
-	popq %r8; \
-	popq %rcx; \
-	popq %rsi; \
-	popq %rdi
-
-#endif
-
-/* Fix up special calling conventions */
-ENTRY(call_rwsem_down_read_failed)
-	FRAME_BEGIN
-	save_common_regs
-	__ASM_SIZE(push,) %__ASM_REG(dx)
-	movq %rax,%rdi
-	call rwsem_down_read_failed
-	__ASM_SIZE(pop,) %__ASM_REG(dx)
-	restore_common_regs
-	FRAME_END
-	ret
-ENDPROC(call_rwsem_down_read_failed)
-
-ENTRY(call_rwsem_down_read_failed_killable)
-	FRAME_BEGIN
-	save_common_regs
-	__ASM_SIZE(push,) %__ASM_REG(dx)
-	movq %rax,%rdi
-	call rwsem_down_read_failed_killable
-	__ASM_SIZE(pop,) %__ASM_REG(dx)
-	restore_common_regs
-	FRAME_END
-	ret
-ENDPROC(call_rwsem_down_read_failed_killable)
-
-ENTRY(call_rwsem_down_write_failed)
-	FRAME_BEGIN
-	save_common_regs
-	movq %rax,%rdi
-	call rwsem_down_write_failed
-	restore_common_regs
-	FRAME_END
-	ret
-ENDPROC(call_rwsem_down_write_failed)
-
-ENTRY(call_rwsem_down_write_failed_killable)
-	FRAME_BEGIN
-	save_common_regs
-	movq %rax,%rdi
-	call rwsem_down_write_failed_killable
-	restore_common_regs
-	FRAME_END
-	ret
-ENDPROC(call_rwsem_down_write_failed_killable)
-
-ENTRY(call_rwsem_wake)
-	FRAME_BEGIN
-	/* do nothing if still outstanding active readers */
-	__ASM_HALF_SIZE(dec) %__ASM_HALF_REG(dx)
-	jnz 1f
-	save_common_regs
-	movq %rax,%rdi
-	call rwsem_wake
-	restore_common_regs
-1:	FRAME_END
-	ret
-ENDPROC(call_rwsem_wake)
-
-ENTRY(call_rwsem_downgrade_wake)
-	FRAME_BEGIN
-	save_common_regs
-	__ASM_SIZE(push,) %__ASM_REG(dx)
-	movq %rax,%rdi
-	call rwsem_downgrade_wake
-	__ASM_SIZE(pop,) %__ASM_REG(dx)
-	restore_common_regs
-	FRAME_END
-	ret
-ENDPROC(call_rwsem_downgrade_wake)
diff --git a/arch/x86/lib/usercopy_64.c b/arch/x86/lib/usercopy_64.c
index ee42bb0cbeb3..9952a01cad24 100644
--- a/arch/x86/lib/usercopy_64.c
+++ b/arch/x86/lib/usercopy_64.c
@@ -55,26 +55,6 @@ unsigned long clear_user(void __user *to, unsigned long n)
 EXPORT_SYMBOL(clear_user);
 
 /*
- * Try to copy last bytes and clear the rest if needed.
- * Since protection fault in copy_from/to_user is not a normal situation,
- * it is not necessary to optimize tail handling.
- */
-__visible unsigned long
-copy_user_handle_tail(char *to, char *from, unsigned len)
-{
-	for (; len; --len, to++) {
-		char c;
-
-		if (__get_user_nocheck(c, from++, sizeof(char)))
-			break;
-		if (__put_user_nocheck(c, to, sizeof(char)))
-			break;
-	}
-	clac();
-	return len;
-}
-
-/*
  * Similar to copy_user_handle_tail, probe for the write fault point,
  * but reuse __memcpy_mcsafe in case a new read error is encountered.
  * clac() is handled in _copy_to_iter_mcsafe().
diff --git a/arch/x86/mm/cpu_entry_area.c b/arch/x86/mm/cpu_entry_area.c
index 19c6abf9ea31..752ad11d6868 100644
--- a/arch/x86/mm/cpu_entry_area.c
+++ b/arch/x86/mm/cpu_entry_area.c
@@ -13,8 +13,8 @@
 static DEFINE_PER_CPU_PAGE_ALIGNED(struct entry_stack_page, entry_stack_storage);
 
 #ifdef CONFIG_X86_64
-static DEFINE_PER_CPU_PAGE_ALIGNED(char, exception_stacks
-	[(N_EXCEPTION_STACKS - 1) * EXCEPTION_STKSZ + DEBUG_STKSZ]);
+static DEFINE_PER_CPU_PAGE_ALIGNED(struct exception_stacks, exception_stacks);
+DEFINE_PER_CPU(struct cea_exception_stacks*, cea_exception_stacks);
 #endif
 
 struct cpu_entry_area *get_cpu_entry_area(int cpu)
@@ -52,10 +52,10 @@ cea_map_percpu_pages(void *cea_vaddr, void *ptr, int pages, pgprot_t prot)
 		cea_set_pte(cea_vaddr, per_cpu_ptr_to_phys(ptr), prot);
 }
 
-static void __init percpu_setup_debug_store(int cpu)
+static void __init percpu_setup_debug_store(unsigned int cpu)
 {
 #ifdef CONFIG_CPU_SUP_INTEL
-	int npages;
+	unsigned int npages;
 	void *cea;
 
 	if (boot_cpu_data.x86_vendor != X86_VENDOR_INTEL)
@@ -78,9 +78,43 @@ static void __init percpu_setup_debug_store(int cpu)
 #endif
 }
 
+#ifdef CONFIG_X86_64
+
+#define cea_map_stack(name) do {					\
+	npages = sizeof(estacks->name## _stack) / PAGE_SIZE;		\
+	cea_map_percpu_pages(cea->estacks.name## _stack,		\
+			estacks->name## _stack, npages, PAGE_KERNEL);	\
+	} while (0)
+
+static void __init percpu_setup_exception_stacks(unsigned int cpu)
+{
+	struct exception_stacks *estacks = per_cpu_ptr(&exception_stacks, cpu);
+	struct cpu_entry_area *cea = get_cpu_entry_area(cpu);
+	unsigned int npages;
+
+	BUILD_BUG_ON(sizeof(exception_stacks) % PAGE_SIZE != 0);
+
+	per_cpu(cea_exception_stacks, cpu) = &cea->estacks;
+
+	/*
+	 * The exceptions stack mappings in the per cpu area are protected
+	 * by guard pages so each stack must be mapped separately. DB2 is
+	 * not mapped; it just exists to catch triple nesting of #DB.
+	 */
+	cea_map_stack(DF);
+	cea_map_stack(NMI);
+	cea_map_stack(DB1);
+	cea_map_stack(DB);
+	cea_map_stack(MCE);
+}
+#else
+static inline void percpu_setup_exception_stacks(unsigned int cpu) {}
+#endif
+
 /* Setup the fixmap mappings only once per-processor */
-static void __init setup_cpu_entry_area(int cpu)
+static void __init setup_cpu_entry_area(unsigned int cpu)
 {
+	struct cpu_entry_area *cea = get_cpu_entry_area(cpu);
 #ifdef CONFIG_X86_64
 	/* On 64-bit systems, we use a read-only fixmap GDT and TSS. */
 	pgprot_t gdt_prot = PAGE_KERNEL_RO;
@@ -101,10 +135,9 @@ static void __init setup_cpu_entry_area(int cpu)
 	pgprot_t tss_prot = PAGE_KERNEL;
 #endif
 
-	cea_set_pte(&get_cpu_entry_area(cpu)->gdt, get_cpu_gdt_paddr(cpu),
-		    gdt_prot);
+	cea_set_pte(&cea->gdt, get_cpu_gdt_paddr(cpu), gdt_prot);
 
-	cea_map_percpu_pages(&get_cpu_entry_area(cpu)->entry_stack_page,
+	cea_map_percpu_pages(&cea->entry_stack_page,
 			     per_cpu_ptr(&entry_stack_storage, cpu), 1,
 			     PAGE_KERNEL);
 
@@ -128,22 +161,15 @@ static void __init setup_cpu_entry_area(int cpu)
 	BUILD_BUG_ON((offsetof(struct tss_struct, x86_tss) ^
 		      offsetofend(struct tss_struct, x86_tss)) & PAGE_MASK);
 	BUILD_BUG_ON(sizeof(struct tss_struct) % PAGE_SIZE != 0);
-	cea_map_percpu_pages(&get_cpu_entry_area(cpu)->tss,
-			     &per_cpu(cpu_tss_rw, cpu),
+	cea_map_percpu_pages(&cea->tss, &per_cpu(cpu_tss_rw, cpu),
 			     sizeof(struct tss_struct) / PAGE_SIZE, tss_prot);
 
 #ifdef CONFIG_X86_32
-	per_cpu(cpu_entry_area, cpu) = get_cpu_entry_area(cpu);
+	per_cpu(cpu_entry_area, cpu) = cea;
 #endif
 
-#ifdef CONFIG_X86_64
-	BUILD_BUG_ON(sizeof(exception_stacks) % PAGE_SIZE != 0);
-	BUILD_BUG_ON(sizeof(exception_stacks) !=
-		     sizeof(((struct cpu_entry_area *)0)->exception_stacks));
-	cea_map_percpu_pages(&get_cpu_entry_area(cpu)->exception_stacks,
-			     &per_cpu(exception_stacks, cpu),
-			     sizeof(exception_stacks) / PAGE_SIZE, PAGE_KERNEL);
-#endif
+	percpu_setup_exception_stacks(cpu);
+
 	percpu_setup_debug_store(cpu);
 }
 
diff --git a/arch/x86/mm/dump_pagetables.c b/arch/x86/mm/dump_pagetables.c
index ee8f8ab46941..6a7302d1161f 100644
--- a/arch/x86/mm/dump_pagetables.c
+++ b/arch/x86/mm/dump_pagetables.c
@@ -259,7 +259,8 @@ static void note_wx(struct pg_state *st)
 #endif
 	/* Account the WX pages */
 	st->wx_pages += npages;
-	WARN_ONCE(1, "x86/mm: Found insecure W+X mapping at address %pS\n",
+	WARN_ONCE(__supported_pte_mask & _PAGE_NX,
+		  "x86/mm: Found insecure W+X mapping at address %pS\n",
 		  (void *)st->start_address);
 }
 
@@ -577,7 +578,7 @@ void ptdump_walk_pgd_level(struct seq_file *m, pgd_t *pgd)
 void ptdump_walk_pgd_level_debugfs(struct seq_file *m, pgd_t *pgd, bool user)
 {
 #ifdef CONFIG_PAGE_TABLE_ISOLATION
-	if (user && static_cpu_has(X86_FEATURE_PTI))
+	if (user && boot_cpu_has(X86_FEATURE_PTI))
 		pgd = kernel_to_user_pgdp(pgd);
 #endif
 	ptdump_walk_pgd_level_core(m, pgd, false, false);
@@ -590,7 +591,7 @@ void ptdump_walk_user_pgd_level_checkwx(void)
 	pgd_t *pgd = INIT_PGD;
 
 	if (!(__supported_pte_mask & _PAGE_NX) ||
-	    !static_cpu_has(X86_FEATURE_PTI))
+	    !boot_cpu_has(X86_FEATURE_PTI))
 		return;
 
 	pr_info("x86/mm: Checking user space page tables\n");
diff --git a/arch/x86/mm/fault.c b/arch/x86/mm/fault.c
index 667f1da36208..46df4c6aae46 100644
--- a/arch/x86/mm/fault.c
+++ b/arch/x86/mm/fault.c
@@ -28,6 +28,7 @@
 #include <asm/mmu_context.h>		/* vma_pkey()			*/
 #include <asm/efi.h>			/* efi_recover_from_page_fault()*/
 #include <asm/desc.h>			/* store_idt(), ...		*/
+#include <asm/cpu_entry_area.h>		/* exception stack		*/
 
 #define CREATE_TRACE_POINTS
 #include <asm/trace/exceptions.h>
@@ -359,8 +360,6 @@ static noinline int vmalloc_fault(unsigned long address)
 	if (!(address >= VMALLOC_START && address < VMALLOC_END))
 		return -1;
 
-	WARN_ON_ONCE(in_nmi());
-
 	/*
 	 * Copy kernel mappings over when needed. This can also
 	 * happen within a race in page table update. In the later
@@ -603,24 +602,9 @@ static void show_ldttss(const struct desc_ptr *gdt, const char *name, u16 index)
 		 name, index, addr, (desc.limit0 | (desc.limit1 << 16)));
 }
 
-/*
- * This helper function transforms the #PF error_code bits into
- * "[PROT] [USER]" type of descriptive, almost human-readable error strings:
- */
-static void err_str_append(unsigned long error_code, char *buf, unsigned long mask, const char *txt)
-{
-	if (error_code & mask) {
-		if (buf[0])
-			strcat(buf, " ");
-		strcat(buf, txt);
-	}
-}
-
 static void
 show_fault_oops(struct pt_regs *regs, unsigned long error_code, unsigned long address)
 {
-	char err_txt[64];
-
 	if (!oops_may_print())
 		return;
 
@@ -644,31 +628,29 @@ show_fault_oops(struct pt_regs *regs, unsigned long error_code, unsigned long ad
 				from_kuid(&init_user_ns, current_uid()));
 	}
 
-	pr_alert("BUG: unable to handle kernel %s at %px\n",
-		 address < PAGE_SIZE ? "NULL pointer dereference" : "paging request",
-		 (void *)address);
-
-	err_txt[0] = 0;
-
-	/*
-	 * Note: length of these appended strings including the separation space and the
-	 * zero delimiter must fit into err_txt[].
-	 */
-	err_str_append(error_code, err_txt, X86_PF_PROT,  "[PROT]" );
-	err_str_append(error_code, err_txt, X86_PF_WRITE, "[WRITE]");
-	err_str_append(error_code, err_txt, X86_PF_USER,  "[USER]" );
-	err_str_append(error_code, err_txt, X86_PF_RSVD,  "[RSVD]" );
-	err_str_append(error_code, err_txt, X86_PF_INSTR, "[INSTR]");
-	err_str_append(error_code, err_txt, X86_PF_PK,    "[PK]"   );
-
-	pr_alert("#PF error: %s\n", error_code ? err_txt : "[normal kernel read fault]");
+	if (address < PAGE_SIZE && !user_mode(regs))
+		pr_alert("BUG: kernel NULL pointer dereference, address: %px\n",
+			(void *)address);
+	else
+		pr_alert("BUG: unable to handle page fault for address: %px\n",
+			(void *)address);
+
+	pr_alert("#PF: %s %s in %s mode\n",
+		 (error_code & X86_PF_USER)  ? "user" : "supervisor",
+		 (error_code & X86_PF_INSTR) ? "instruction fetch" :
+		 (error_code & X86_PF_WRITE) ? "write access" :
+					       "read access",
+			     user_mode(regs) ? "user" : "kernel");
+	pr_alert("#PF: error_code(0x%04lx) - %s\n", error_code,
+		 !(error_code & X86_PF_PROT) ? "not-present page" :
+		 (error_code & X86_PF_RSVD)  ? "reserved bit violation" :
+		 (error_code & X86_PF_PK)    ? "protection keys violation" :
+					       "permissions violation");
 
 	if (!(error_code & X86_PF_USER) && user_mode(regs)) {
 		struct desc_ptr idt, gdt;
 		u16 ldtr, tr;
 
-		pr_alert("This was a system access from user code\n");
-
 		/*
 		 * This can happen for quite a few reasons.  The more obvious
 		 * ones are faults accessing the GDT, or LDT.  Perhaps
@@ -793,7 +775,7 @@ no_context(struct pt_regs *regs, unsigned long error_code,
 	if (is_vmalloc_addr((void *)address) &&
 	    (((unsigned long)tsk->stack - 1 - address < PAGE_SIZE) ||
 	     address - ((unsigned long)tsk->stack + THREAD_SIZE) < PAGE_SIZE)) {
-		unsigned long stack = this_cpu_read(orig_ist.ist[DOUBLEFAULT_STACK]) - sizeof(void *);
+		unsigned long stack = __this_cpu_ist_top_va(DF) - sizeof(void *);
 		/*
 		 * We're likely to be running with very little stack space
 		 * left.  It's plausible that we'd hit this condition but
diff --git a/arch/x86/mm/init.c b/arch/x86/mm/init.c
index f905a2371080..fd10d91a6115 100644
--- a/arch/x86/mm/init.c
+++ b/arch/x86/mm/init.c
@@ -5,6 +5,8 @@
 #include <linux/memblock.h>
 #include <linux/swapfile.h>
 #include <linux/swapops.h>
+#include <linux/kmemleak.h>
+#include <linux/sched/task.h>
 
 #include <asm/set_memory.h>
 #include <asm/e820/api.h>
@@ -22,6 +24,7 @@
 #include <asm/hypervisor.h>
 #include <asm/cpufeature.h>
 #include <asm/pti.h>
+#include <asm/text-patching.h>
 
 /*
  * We need to define the tracepoints somewhere, and tlb.c
@@ -701,6 +704,41 @@ void __init init_mem_mapping(void)
 }
 
 /*
+ * Initialize an mm_struct to be used during poking and a pointer to be used
+ * during patching.
+ */
+void __init poking_init(void)
+{
+	spinlock_t *ptl;
+	pte_t *ptep;
+
+	poking_mm = copy_init_mm();
+	BUG_ON(!poking_mm);
+
+	/*
+	 * Randomize the poking address, but make sure that the following page
+	 * will be mapped at the same PMD. We need 2 pages, so find space for 3,
+	 * and adjust the address if the PMD ends after the first one.
+	 */
+	poking_addr = TASK_UNMAPPED_BASE;
+	if (IS_ENABLED(CONFIG_RANDOMIZE_BASE))
+		poking_addr += (kaslr_get_random_long("Poking") & PAGE_MASK) %
+			(TASK_SIZE - TASK_UNMAPPED_BASE - 3 * PAGE_SIZE);
+
+	if (((poking_addr + PAGE_SIZE) & ~PMD_MASK) == 0)
+		poking_addr += PAGE_SIZE;
+
+	/*
+	 * We need to trigger the allocation of the page-tables that will be
+	 * needed for poking now. Later, poking may be performed in an atomic
+	 * section, which might cause allocation to fail.
+	 */
+	ptep = get_locked_pte(poking_mm, poking_addr, &ptl);
+	BUG_ON(!ptep);
+	pte_unmap_unlock(ptep, ptl);
+}
+
+/*
  * devmem_is_allowed() checks to see if /dev/mem access to a certain address
  * is valid. The argument is a physical page number.
  *
@@ -766,6 +804,11 @@ void free_init_pages(const char *what, unsigned long begin, unsigned long end)
 	if (debug_pagealloc_enabled()) {
 		pr_info("debug: unmapping init [mem %#010lx-%#010lx]\n",
 			begin, end - 1);
+		/*
+		 * Inform kmemleak about the hole in the memory since the
+		 * corresponding pages will be unmapped.
+		 */
+		kmemleak_free_part((void *)begin, end - begin);
 		set_memory_np(begin, (end - begin) >> PAGE_SHIFT);
 	} else {
 		/*
diff --git a/arch/x86/mm/ioremap.c b/arch/x86/mm/ioremap.c
index 0029604af8a4..dd73d5d74393 100644
--- a/arch/x86/mm/ioremap.c
+++ b/arch/x86/mm/ioremap.c
@@ -825,7 +825,7 @@ void __init __early_set_fixmap(enum fixed_addresses idx,
 	pte = early_ioremap_pte(addr);
 
 	/* Sanitize 'prot' against any unsupported bits: */
-	pgprot_val(flags) &= __default_kernel_pte_mask;
+	pgprot_val(flags) &= __supported_pte_mask;
 
 	if (pgprot_val(flags))
 		set_pte(pte, pfn_pte(phys >> PAGE_SHIFT, flags));
diff --git a/arch/x86/mm/kaslr.c b/arch/x86/mm/kaslr.c
index 3f452ffed7e9..dc3f058bdf9b 100644
--- a/arch/x86/mm/kaslr.c
+++ b/arch/x86/mm/kaslr.c
@@ -94,7 +94,7 @@ void __init kernel_randomize_memory(void)
 	if (!kaslr_memory_enabled())
 		return;
 
-	kaslr_regions[0].size_tb = 1 << (__PHYSICAL_MASK_SHIFT - TB_SHIFT);
+	kaslr_regions[0].size_tb = 1 << (MAX_PHYSMEM_BITS - TB_SHIFT);
 	kaslr_regions[1].size_tb = VMALLOC_SIZE_TB;
 
 	/*
@@ -125,10 +125,7 @@ void __init kernel_randomize_memory(void)
 		 */
 		entropy = remain_entropy / (ARRAY_SIZE(kaslr_regions) - i);
 		prandom_bytes_state(&rand_state, &rand, sizeof(rand));
-		if (pgtable_l5_enabled())
-			entropy = (rand % (entropy + 1)) & P4D_MASK;
-		else
-			entropy = (rand % (entropy + 1)) & PUD_MASK;
+		entropy = (rand % (entropy + 1)) & PUD_MASK;
 		vaddr += entropy;
 		*kaslr_regions[i].base = vaddr;
 
@@ -137,84 +134,71 @@ void __init kernel_randomize_memory(void)
 		 * randomization alignment.
 		 */
 		vaddr += get_padding(&kaslr_regions[i]);
-		if (pgtable_l5_enabled())
-			vaddr = round_up(vaddr + 1, P4D_SIZE);
-		else
-			vaddr = round_up(vaddr + 1, PUD_SIZE);
+		vaddr = round_up(vaddr + 1, PUD_SIZE);
 		remain_entropy -= entropy;
 	}
 }
 
 static void __meminit init_trampoline_pud(void)
 {
-	unsigned long paddr, paddr_next;
+	pud_t *pud_page_tramp, *pud, *pud_tramp;
+	p4d_t *p4d_page_tramp, *p4d, *p4d_tramp;
+	unsigned long paddr, vaddr;
 	pgd_t *pgd;
-	pud_t *pud_page, *pud_page_tramp;
-	int i;
 
 	pud_page_tramp = alloc_low_page();
 
+	/*
+	 * There are two mappings for the low 1MB area, the direct mapping
+	 * and the 1:1 mapping for the real mode trampoline:
+	 *
+	 * Direct mapping: virt_addr = phys_addr + PAGE_OFFSET
+	 * 1:1 mapping:    virt_addr = phys_addr
+	 */
 	paddr = 0;
-	pgd = pgd_offset_k((unsigned long)__va(paddr));
-	pud_page = (pud_t *) pgd_page_vaddr(*pgd);
-
-	for (i = pud_index(paddr); i < PTRS_PER_PUD; i++, paddr = paddr_next) {
-		pud_t *pud, *pud_tramp;
-		unsigned long vaddr = (unsigned long)__va(paddr);
+	vaddr = (unsigned long)__va(paddr);
+	pgd = pgd_offset_k(vaddr);
 
-		pud_tramp = pud_page_tramp + pud_index(paddr);
-		pud = pud_page + pud_index(vaddr);
-		paddr_next = (paddr & PUD_MASK) + PUD_SIZE;
-
-		*pud_tramp = *pud;
-	}
+	p4d = p4d_offset(pgd, vaddr);
+	pud = pud_offset(p4d, vaddr);
 
-	set_pgd(&trampoline_pgd_entry,
-		__pgd(_KERNPG_TABLE | __pa(pud_page_tramp)));
-}
-
-static void __meminit init_trampoline_p4d(void)
-{
-	unsigned long paddr, paddr_next;
-	pgd_t *pgd;
-	p4d_t *p4d_page, *p4d_page_tramp;
-	int i;
+	pud_tramp = pud_page_tramp + pud_index(paddr);
+	*pud_tramp = *pud;
 
-	p4d_page_tramp = alloc_low_page();
-
-	paddr = 0;
-	pgd = pgd_offset_k((unsigned long)__va(paddr));
-	p4d_page = (p4d_t *) pgd_page_vaddr(*pgd);
-
-	for (i = p4d_index(paddr); i < PTRS_PER_P4D; i++, paddr = paddr_next) {
-		p4d_t *p4d, *p4d_tramp;
-		unsigned long vaddr = (unsigned long)__va(paddr);
+	if (pgtable_l5_enabled()) {
+		p4d_page_tramp = alloc_low_page();
 
 		p4d_tramp = p4d_page_tramp + p4d_index(paddr);
-		p4d = p4d_page + p4d_index(vaddr);
-		paddr_next = (paddr & P4D_MASK) + P4D_SIZE;
 
-		*p4d_tramp = *p4d;
-	}
+		set_p4d(p4d_tramp,
+			__p4d(_KERNPG_TABLE | __pa(pud_page_tramp)));
 
-	set_pgd(&trampoline_pgd_entry,
-		__pgd(_KERNPG_TABLE | __pa(p4d_page_tramp)));
+		set_pgd(&trampoline_pgd_entry,
+			__pgd(_KERNPG_TABLE | __pa(p4d_page_tramp)));
+	} else {
+		set_pgd(&trampoline_pgd_entry,
+			__pgd(_KERNPG_TABLE | __pa(pud_page_tramp)));
+	}
 }
 
 /*
- * Create PGD aligned trampoline table to allow real mode initialization
- * of additional CPUs. Consume only 1 low memory page.
+ * The real mode trampoline, which is required for bootstrapping CPUs
+ * occupies only a small area under the low 1MB.  See reserve_real_mode()
+ * for details.
+ *
+ * If KASLR is disabled the first PGD entry of the direct mapping is copied
+ * to map the real mode trampoline.
+ *
+ * If KASLR is enabled, copy only the PUD which covers the low 1MB
+ * area. This limits the randomization granularity to 1GB for both 4-level
+ * and 5-level paging.
  */
 void __meminit init_trampoline(void)
 {
-
 	if (!kaslr_memory_enabled()) {
 		init_trampoline_default();
 		return;
 	}
 
-	if (pgtable_l5_enabled())
-		init_trampoline_p4d();
-	else
-		init_trampoline_pud();
+	init_trampoline_pud();
 }
diff --git a/arch/x86/mm/mmap.c b/arch/x86/mm/mmap.c
index db3165714521..dc726e07d8ba 100644
--- a/arch/x86/mm/mmap.c
+++ b/arch/x86/mm/mmap.c
@@ -230,7 +230,7 @@ bool mmap_address_hint_valid(unsigned long addr, unsigned long len)
 /* Can we access it for direct reading/writing? Must be RAM: */
 int valid_phys_addr_range(phys_addr_t addr, size_t count)
 {
-	return addr + count <= __pa(high_memory);
+	return addr + count - 1 <= __pa(high_memory - 1);
 }
 
 /* Can we access it through mmap? Must be a valid physical address: */
diff --git a/arch/x86/mm/pageattr.c b/arch/x86/mm/pageattr.c
index 4c570612e24e..daf4d645e537 100644
--- a/arch/x86/mm/pageattr.c
+++ b/arch/x86/mm/pageattr.c
@@ -2209,8 +2209,6 @@ int set_pages_rw(struct page *page, int numpages)
 	return set_memory_rw(addr, numpages);
 }
 
-#ifdef CONFIG_DEBUG_PAGEALLOC
-
 static int __set_pages_p(struct page *page, int numpages)
 {
 	unsigned long tempaddr = (unsigned long) page_address(page);
@@ -2249,6 +2247,16 @@ static int __set_pages_np(struct page *page, int numpages)
 	return __change_page_attr_set_clr(&cpa, 0);
 }
 
+int set_direct_map_invalid_noflush(struct page *page)
+{
+	return __set_pages_np(page, 1);
+}
+
+int set_direct_map_default_noflush(struct page *page)
+{
+	return __set_pages_p(page, 1);
+}
+
 void __kernel_map_pages(struct page *page, int numpages, int enable)
 {
 	if (PageHighMem(page))
@@ -2282,7 +2290,6 @@ void __kernel_map_pages(struct page *page, int numpages, int enable)
 }
 
 #ifdef CONFIG_HIBERNATION
-
 bool kernel_page_present(struct page *page)
 {
 	unsigned int level;
@@ -2294,11 +2301,8 @@ bool kernel_page_present(struct page *page)
 	pte = lookup_address((unsigned long)page_address(page), &level);
 	return (pte_val(*pte) & _PAGE_PRESENT);
 }
-
 #endif /* CONFIG_HIBERNATION */
 
-#endif /* CONFIG_DEBUG_PAGEALLOC */
-
 int __init kernel_map_pages_in_pgd(pgd_t *pgd, u64 pfn, unsigned long address,
 				   unsigned numpages, unsigned long page_flags)
 {
diff --git a/arch/x86/mm/pgtable.c b/arch/x86/mm/pgtable.c
index 7bd01709a091..1f67b1e15bf6 100644
--- a/arch/x86/mm/pgtable.c
+++ b/arch/x86/mm/pgtable.c
@@ -190,7 +190,7 @@ static void pgd_dtor(pgd_t *pgd)
  * when PTI is enabled. We need them to map the per-process LDT into the
  * user-space page-table.
  */
-#define PREALLOCATED_USER_PMDS	 (static_cpu_has(X86_FEATURE_PTI) ? \
+#define PREALLOCATED_USER_PMDS	 (boot_cpu_has(X86_FEATURE_PTI) ? \
 					KERNEL_PGD_PTRS : 0)
 #define MAX_PREALLOCATED_USER_PMDS KERNEL_PGD_PTRS
 
@@ -292,7 +292,7 @@ static void pgd_mop_up_pmds(struct mm_struct *mm, pgd_t *pgdp)
 
 #ifdef CONFIG_PAGE_TABLE_ISOLATION
 
-	if (!static_cpu_has(X86_FEATURE_PTI))
+	if (!boot_cpu_has(X86_FEATURE_PTI))
 		return;
 
 	pgdp = kernel_to_user_pgdp(pgdp);
@@ -373,14 +373,14 @@ static void pgd_prepopulate_user_pmd(struct mm_struct *mm,
 
 static struct kmem_cache *pgd_cache;
 
-static int __init pgd_cache_init(void)
+void __init pgd_cache_init(void)
 {
 	/*
 	 * When PAE kernel is running as a Xen domain, it does not use
 	 * shared kernel pmd. And this requires a whole page for pgd.
 	 */
 	if (!SHARED_KERNEL_PMD)
-		return 0;
+		return;
 
 	/*
 	 * when PAE kernel is not running as a Xen domain, it uses
@@ -390,9 +390,7 @@ static int __init pgd_cache_init(void)
 	 */
 	pgd_cache = kmem_cache_create("pgd_cache", PGD_SIZE, PGD_ALIGN,
 				      SLAB_PANIC, NULL);
-	return 0;
 }
-core_initcall(pgd_cache_init);
 
 static inline pgd_t *_pgd_alloc(void)
 {
@@ -420,6 +418,10 @@ static inline void _pgd_free(pgd_t *pgd)
 }
 #else
 
+void __init pgd_cache_init(void)
+{
+}
+
 static inline pgd_t *_pgd_alloc(void)
 {
 	return (pgd_t *)__get_free_pages(PGALLOC_GFP, PGD_ALLOCATION_ORDER);
diff --git a/arch/x86/mm/pti.c b/arch/x86/mm/pti.c
index 139b28a01ce4..9c2463bc158f 100644
--- a/arch/x86/mm/pti.c
+++ b/arch/x86/mm/pti.c
@@ -35,6 +35,7 @@
 #include <linux/spinlock.h>
 #include <linux/mm.h>
 #include <linux/uaccess.h>
+#include <linux/cpu.h>
 
 #include <asm/cpufeature.h>
 #include <asm/hypervisor.h>
@@ -115,7 +116,8 @@ void __init pti_check_boottime_disable(void)
 		}
 	}
 
-	if (cmdline_find_option_bool(boot_command_line, "nopti")) {
+	if (cmdline_find_option_bool(boot_command_line, "nopti") ||
+	    cpu_mitigations_off()) {
 		pti_mode = PTI_FORCE_OFF;
 		pti_print_if_insecure("disabled on command line.");
 		return;
@@ -626,7 +628,7 @@ static void pti_set_kernel_image_nonglobal(void)
  */
 void __init pti_init(void)
 {
-	if (!static_cpu_has(X86_FEATURE_PTI))
+	if (!boot_cpu_has(X86_FEATURE_PTI))
 		return;
 
 	pr_info("enabled\n");
diff --git a/arch/x86/mm/tlb.c b/arch/x86/mm/tlb.c
index bc4bc7b2f075..7f61431c75fb 100644
--- a/arch/x86/mm/tlb.c
+++ b/arch/x86/mm/tlb.c
@@ -634,7 +634,7 @@ static void flush_tlb_func_common(const struct flush_tlb_info *f,
 	this_cpu_write(cpu_tlbstate.ctxs[loaded_mm_asid].tlb_gen, mm_tlb_gen);
 }
 
-static void flush_tlb_func_local(void *info, enum tlb_flush_reason reason)
+static void flush_tlb_func_local(const void *info, enum tlb_flush_reason reason)
 {
 	const struct flush_tlb_info *f = info;
 
@@ -722,43 +722,81 @@ void native_flush_tlb_others(const struct cpumask *cpumask,
  */
 unsigned long tlb_single_page_flush_ceiling __read_mostly = 33;
 
+static DEFINE_PER_CPU_SHARED_ALIGNED(struct flush_tlb_info, flush_tlb_info);
+
+#ifdef CONFIG_DEBUG_VM
+static DEFINE_PER_CPU(unsigned int, flush_tlb_info_idx);
+#endif
+
+static inline struct flush_tlb_info *get_flush_tlb_info(struct mm_struct *mm,
+			unsigned long start, unsigned long end,
+			unsigned int stride_shift, bool freed_tables,
+			u64 new_tlb_gen)
+{
+	struct flush_tlb_info *info = this_cpu_ptr(&flush_tlb_info);
+
+#ifdef CONFIG_DEBUG_VM
+	/*
+	 * Ensure that the following code is non-reentrant and flush_tlb_info
+	 * is not overwritten. This means no TLB flushing is initiated by
+	 * interrupt handlers and machine-check exception handlers.
+	 */
+	BUG_ON(this_cpu_inc_return(flush_tlb_info_idx) != 1);
+#endif
+
+	info->start		= start;
+	info->end		= end;
+	info->mm		= mm;
+	info->stride_shift	= stride_shift;
+	info->freed_tables	= freed_tables;
+	info->new_tlb_gen	= new_tlb_gen;
+
+	return info;
+}
+
+static inline void put_flush_tlb_info(void)
+{
+#ifdef CONFIG_DEBUG_VM
+	/* Complete reentrency prevention checks */
+	barrier();
+	this_cpu_dec(flush_tlb_info_idx);
+#endif
+}
+
 void flush_tlb_mm_range(struct mm_struct *mm, unsigned long start,
 				unsigned long end, unsigned int stride_shift,
 				bool freed_tables)
 {
+	struct flush_tlb_info *info;
+	u64 new_tlb_gen;
 	int cpu;
 
-	struct flush_tlb_info info __aligned(SMP_CACHE_BYTES) = {
-		.mm = mm,
-		.stride_shift = stride_shift,
-		.freed_tables = freed_tables,
-	};
-
 	cpu = get_cpu();
 
-	/* This is also a barrier that synchronizes with switch_mm(). */
-	info.new_tlb_gen = inc_mm_tlb_gen(mm);
-
 	/* Should we flush just the requested range? */
-	if ((end != TLB_FLUSH_ALL) &&
-	    ((end - start) >> stride_shift) <= tlb_single_page_flush_ceiling) {
-		info.start = start;
-		info.end = end;
-	} else {
-		info.start = 0UL;
-		info.end = TLB_FLUSH_ALL;
+	if ((end == TLB_FLUSH_ALL) ||
+	    ((end - start) >> stride_shift) > tlb_single_page_flush_ceiling) {
+		start = 0;
+		end = TLB_FLUSH_ALL;
 	}
 
+	/* This is also a barrier that synchronizes with switch_mm(). */
+	new_tlb_gen = inc_mm_tlb_gen(mm);
+
+	info = get_flush_tlb_info(mm, start, end, stride_shift, freed_tables,
+				  new_tlb_gen);
+
 	if (mm == this_cpu_read(cpu_tlbstate.loaded_mm)) {
-		VM_WARN_ON(irqs_disabled());
+		lockdep_assert_irqs_enabled();
 		local_irq_disable();
-		flush_tlb_func_local(&info, TLB_LOCAL_MM_SHOOTDOWN);
+		flush_tlb_func_local(info, TLB_LOCAL_MM_SHOOTDOWN);
 		local_irq_enable();
 	}
 
 	if (cpumask_any_but(mm_cpumask(mm), cpu) < nr_cpu_ids)
-		flush_tlb_others(mm_cpumask(mm), &info);
+		flush_tlb_others(mm_cpumask(mm), info);
 
+	put_flush_tlb_info();
 	put_cpu();
 }
 
@@ -787,38 +825,48 @@ static void do_kernel_range_flush(void *info)
 
 void flush_tlb_kernel_range(unsigned long start, unsigned long end)
 {
-
 	/* Balance as user space task's flush, a bit conservative */
 	if (end == TLB_FLUSH_ALL ||
 	    (end - start) > tlb_single_page_flush_ceiling << PAGE_SHIFT) {
 		on_each_cpu(do_flush_tlb_all, NULL, 1);
 	} else {
-		struct flush_tlb_info info;
-		info.start = start;
-		info.end = end;
-		on_each_cpu(do_kernel_range_flush, &info, 1);
+		struct flush_tlb_info *info;
+
+		preempt_disable();
+		info = get_flush_tlb_info(NULL, start, end, 0, false, 0);
+
+		on_each_cpu(do_kernel_range_flush, info, 1);
+
+		put_flush_tlb_info();
+		preempt_enable();
 	}
 }
 
+/*
+ * arch_tlbbatch_flush() performs a full TLB flush regardless of the active mm.
+ * This means that the 'struct flush_tlb_info' that describes which mappings to
+ * flush is actually fixed. We therefore set a single fixed struct and use it in
+ * arch_tlbbatch_flush().
+ */
+static const struct flush_tlb_info full_flush_tlb_info = {
+	.mm = NULL,
+	.start = 0,
+	.end = TLB_FLUSH_ALL,
+};
+
 void arch_tlbbatch_flush(struct arch_tlbflush_unmap_batch *batch)
 {
-	struct flush_tlb_info info = {
-		.mm = NULL,
-		.start = 0UL,
-		.end = TLB_FLUSH_ALL,
-	};
-
 	int cpu = get_cpu();
 
 	if (cpumask_test_cpu(cpu, &batch->cpumask)) {
-		VM_WARN_ON(irqs_disabled());
+		lockdep_assert_irqs_enabled();
 		local_irq_disable();
-		flush_tlb_func_local(&info, TLB_LOCAL_SHOOTDOWN);
+		flush_tlb_func_local(&full_flush_tlb_info, TLB_LOCAL_SHOOTDOWN);
 		local_irq_enable();
 	}
 
 	if (cpumask_any_but(&batch->cpumask, cpu) < nr_cpu_ids)
-		flush_tlb_others(&batch->cpumask, &info);
+		flush_tlb_others(&batch->cpumask, &full_flush_tlb_info);
 
 	cpumask_clear(&batch->cpumask);
 
diff --git a/arch/x86/platform/efi/quirks.c b/arch/x86/platform/efi/quirks.c
index 458a0e2bcc57..a25a9fd987a9 100644
--- a/arch/x86/platform/efi/quirks.c
+++ b/arch/x86/platform/efi/quirks.c
@@ -449,7 +449,7 @@ void __init efi_free_boot_services(void)
 		 */
 		rm_size = real_mode_size_needed();
 		if (rm_size && (start + rm_size) < (1<<20) && size >= rm_size) {
-			set_real_mode_mem(start, rm_size);
+			set_real_mode_mem(start);
 			start += rm_size;
 			size -= rm_size;
 		}
diff --git a/arch/x86/platform/uv/tlb_uv.c b/arch/x86/platform/uv/tlb_uv.c
index 2c53b0f19329..1297e185b8c8 100644
--- a/arch/x86/platform/uv/tlb_uv.c
+++ b/arch/x86/platform/uv/tlb_uv.c
@@ -2133,14 +2133,19 @@ static int __init summarize_uvhub_sockets(int nuvhubs,
  */
 static int __init init_per_cpu(int nuvhubs, int base_part_pnode)
 {
-	unsigned char *uvhub_mask;
 	struct uvhub_desc *uvhub_descs;
+	unsigned char *uvhub_mask = NULL;
 
 	if (is_uv3_hub() || is_uv2_hub() || is_uv1_hub())
 		timeout_us = calculate_destination_timeout();
 
 	uvhub_descs = kcalloc(nuvhubs, sizeof(struct uvhub_desc), GFP_KERNEL);
+	if (!uvhub_descs)
+		goto fail;
+
 	uvhub_mask = kzalloc((nuvhubs+7)/8, GFP_KERNEL);
+	if (!uvhub_mask)
+		goto fail;
 
 	if (get_cpu_topology(base_part_pnode, uvhub_descs, uvhub_mask))
 		goto fail;
diff --git a/arch/x86/power/hibernate.c b/arch/x86/power/hibernate.c
index bcddf09b5aa3..4845b8c7be7f 100644
--- a/arch/x86/power/hibernate.c
+++ b/arch/x86/power/hibernate.c
@@ -90,7 +90,6 @@ static int get_e820_md5(struct e820_table *table, void *buf)
 	}
 
 	desc->tfm = tfm;
-	desc->flags = 0;
 
 	size = offsetof(struct e820_table, entries) +
 		sizeof(struct e820_entry) * table->nr_entries;
diff --git a/arch/x86/realmode/init.c b/arch/x86/realmode/init.c
index d10105825d57..7dce39c8c034 100644
--- a/arch/x86/realmode/init.c
+++ b/arch/x86/realmode/init.c
@@ -15,15 +15,6 @@ u32 *trampoline_cr4_features;
 /* Hold the pgd entry used on booting additional CPUs */
 pgd_t trampoline_pgd_entry;
 
-void __init set_real_mode_mem(phys_addr_t mem, size_t size)
-{
-	void *base = __va(mem);
-
-	real_mode_header = (struct real_mode_header *) base;
-	printk(KERN_DEBUG "Base memory trampoline at [%p] %llx size %zu\n",
-	       base, (unsigned long long)mem, size);
-}
-
 void __init reserve_real_mode(void)
 {
 	phys_addr_t mem;
@@ -42,7 +33,7 @@ void __init reserve_real_mode(void)
 	}
 
 	memblock_reserve(mem, size);
-	set_real_mode_mem(mem, size);
+	set_real_mode_mem(mem);
 }
 
 static void __init setup_real_mode(void)
diff --git a/arch/x86/tools/relocs.c b/arch/x86/tools/relocs.c
index b629f6992d9f..ce7188cbdae5 100644
--- a/arch/x86/tools/relocs.c
+++ b/arch/x86/tools/relocs.c
@@ -11,7 +11,9 @@
 #define Elf_Shdr		ElfW(Shdr)
 #define Elf_Sym			ElfW(Sym)
 
-static Elf_Ehdr ehdr;
+static Elf_Ehdr		ehdr;
+static unsigned long	shnum;
+static unsigned int	shstrndx;
 
 struct relocs {
 	uint32_t	*offset;
@@ -241,9 +243,9 @@ static const char *sec_name(unsigned shndx)
 {
 	const char *sec_strtab;
 	const char *name;
-	sec_strtab = secs[ehdr.e_shstrndx].strtab;
+	sec_strtab = secs[shstrndx].strtab;
 	name = "<noname>";
-	if (shndx < ehdr.e_shnum) {
+	if (shndx < shnum) {
 		name = sec_strtab + secs[shndx].shdr.sh_name;
 	}
 	else if (shndx == SHN_ABS) {
@@ -271,7 +273,7 @@ static const char *sym_name(const char *sym_strtab, Elf_Sym *sym)
 static Elf_Sym *sym_lookup(const char *symname)
 {
 	int i;
-	for (i = 0; i < ehdr.e_shnum; i++) {
+	for (i = 0; i < shnum; i++) {
 		struct section *sec = &secs[i];
 		long nsyms;
 		char *strtab;
@@ -366,27 +368,41 @@ static void read_ehdr(FILE *fp)
 	ehdr.e_shnum     = elf_half_to_cpu(ehdr.e_shnum);
 	ehdr.e_shstrndx  = elf_half_to_cpu(ehdr.e_shstrndx);
 
-	if ((ehdr.e_type != ET_EXEC) && (ehdr.e_type != ET_DYN)) {
+	shnum = ehdr.e_shnum;
+	shstrndx = ehdr.e_shstrndx;
+
+	if ((ehdr.e_type != ET_EXEC) && (ehdr.e_type != ET_DYN))
 		die("Unsupported ELF header type\n");
-	}
-	if (ehdr.e_machine != ELF_MACHINE) {
+	if (ehdr.e_machine != ELF_MACHINE)
 		die("Not for %s\n", ELF_MACHINE_NAME);
-	}
-	if (ehdr.e_version != EV_CURRENT) {
+	if (ehdr.e_version != EV_CURRENT)
 		die("Unknown ELF version\n");
-	}
-	if (ehdr.e_ehsize != sizeof(Elf_Ehdr)) {
+	if (ehdr.e_ehsize != sizeof(Elf_Ehdr))
 		die("Bad Elf header size\n");
-	}
-	if (ehdr.e_phentsize != sizeof(Elf_Phdr)) {
+	if (ehdr.e_phentsize != sizeof(Elf_Phdr))
 		die("Bad program header entry\n");
-	}
-	if (ehdr.e_shentsize != sizeof(Elf_Shdr)) {
+	if (ehdr.e_shentsize != sizeof(Elf_Shdr))
 		die("Bad section header entry\n");
+
+
+	if (shnum == SHN_UNDEF || shstrndx == SHN_XINDEX) {
+		Elf_Shdr shdr;
+
+		if (fseek(fp, ehdr.e_shoff, SEEK_SET) < 0)
+			die("Seek to %d failed: %s\n", ehdr.e_shoff, strerror(errno));
+
+		if (fread(&shdr, sizeof(shdr), 1, fp) != 1)
+			die("Cannot read initial ELF section header: %s\n", strerror(errno));
+
+		if (shnum == SHN_UNDEF)
+			shnum = elf_xword_to_cpu(shdr.sh_size);
+
+		if (shstrndx == SHN_XINDEX)
+			shstrndx = elf_word_to_cpu(shdr.sh_link);
 	}
-	if (ehdr.e_shstrndx >= ehdr.e_shnum) {
+
+	if (shstrndx >= shnum)
 		die("String table index out of bounds\n");
-	}
 }
 
 static void read_shdrs(FILE *fp)
@@ -394,20 +410,20 @@ static void read_shdrs(FILE *fp)
 	int i;
 	Elf_Shdr shdr;
 
-	secs = calloc(ehdr.e_shnum, sizeof(struct section));
+	secs = calloc(shnum, sizeof(struct section));
 	if (!secs) {
 		die("Unable to allocate %d section headers\n",
-		    ehdr.e_shnum);
+		    shnum);
 	}
 	if (fseek(fp, ehdr.e_shoff, SEEK_SET) < 0) {
 		die("Seek to %d failed: %s\n",
 			ehdr.e_shoff, strerror(errno));
 	}
-	for (i = 0; i < ehdr.e_shnum; i++) {
+	for (i = 0; i < shnum; i++) {
 		struct section *sec = &secs[i];
 		if (fread(&shdr, sizeof(shdr), 1, fp) != 1)
 			die("Cannot read ELF section headers %d/%d: %s\n",
-			    i, ehdr.e_shnum, strerror(errno));
+			    i, shnum, strerror(errno));
 		sec->shdr.sh_name      = elf_word_to_cpu(shdr.sh_name);
 		sec->shdr.sh_type      = elf_word_to_cpu(shdr.sh_type);
 		sec->shdr.sh_flags     = elf_xword_to_cpu(shdr.sh_flags);
@@ -418,7 +434,7 @@ static void read_shdrs(FILE *fp)
 		sec->shdr.sh_info      = elf_word_to_cpu(shdr.sh_info);
 		sec->shdr.sh_addralign = elf_xword_to_cpu(shdr.sh_addralign);
 		sec->shdr.sh_entsize   = elf_xword_to_cpu(shdr.sh_entsize);
-		if (sec->shdr.sh_link < ehdr.e_shnum)
+		if (sec->shdr.sh_link < shnum)
 			sec->link = &secs[sec->shdr.sh_link];
 	}
 
@@ -427,7 +443,7 @@ static void read_shdrs(FILE *fp)
 static void read_strtabs(FILE *fp)
 {
 	int i;
-	for (i = 0; i < ehdr.e_shnum; i++) {
+	for (i = 0; i < shnum; i++) {
 		struct section *sec = &secs[i];
 		if (sec->shdr.sh_type != SHT_STRTAB) {
 			continue;
@@ -452,7 +468,7 @@ static void read_strtabs(FILE *fp)
 static void read_symtabs(FILE *fp)
 {
 	int i,j;
-	for (i = 0; i < ehdr.e_shnum; i++) {
+	for (i = 0; i < shnum; i++) {
 		struct section *sec = &secs[i];
 		if (sec->shdr.sh_type != SHT_SYMTAB) {
 			continue;
@@ -485,7 +501,7 @@ static void read_symtabs(FILE *fp)
 static void read_relocs(FILE *fp)
 {
 	int i,j;
-	for (i = 0; i < ehdr.e_shnum; i++) {
+	for (i = 0; i < shnum; i++) {
 		struct section *sec = &secs[i];
 		if (sec->shdr.sh_type != SHT_REL_TYPE) {
 			continue;
@@ -528,7 +544,7 @@ static void print_absolute_symbols(void)
 
 	printf("Absolute symbols\n");
 	printf(" Num:    Value Size  Type       Bind        Visibility  Name\n");
-	for (i = 0; i < ehdr.e_shnum; i++) {
+	for (i = 0; i < shnum; i++) {
 		struct section *sec = &secs[i];
 		char *sym_strtab;
 		int j;
@@ -566,7 +582,7 @@ static void print_absolute_relocs(void)
 	else
 		format = "%08"PRIx32" %08"PRIx32" %10s %08"PRIx32"  %s\n";
 
-	for (i = 0; i < ehdr.e_shnum; i++) {
+	for (i = 0; i < shnum; i++) {
 		struct section *sec = &secs[i];
 		struct section *sec_applies, *sec_symtab;
 		char *sym_strtab;
@@ -650,7 +666,7 @@ static void walk_relocs(int (*process)(struct section *sec, Elf_Rel *rel,
 {
 	int i;
 	/* Walk through the relocations */
-	for (i = 0; i < ehdr.e_shnum; i++) {
+	for (i = 0; i < shnum; i++) {
 		char *sym_strtab;
 		Elf_Sym *sh_symtab;
 		struct section *sec_applies, *sec_symtab;
@@ -706,7 +722,7 @@ static Elf_Addr per_cpu_load_addr;
 static void percpu_init(void)
 {
 	int i;
-	for (i = 0; i < ehdr.e_shnum; i++) {
+	for (i = 0; i < shnum; i++) {
 		ElfW(Sym) *sym;
 		if (strcmp(sec_name(i), ".data..percpu"))
 			continue;
@@ -738,7 +754,7 @@ static void percpu_init(void)
  *	__per_cpu_load
  *
  * The "gold" linker incorrectly associates:
- *	init_per_cpu__irq_stack_union
+ *	init_per_cpu__fixed_percpu_data
  *	init_per_cpu__gdt_page
  */
 static int is_percpu_sym(ElfW(Sym) *sym, const char *symname)
diff --git a/arch/x86/um/Kconfig b/arch/x86/um/Kconfig
index a9e80e44178c..a8985e1f7432 100644
--- a/arch/x86/um/Kconfig
+++ b/arch/x86/um/Kconfig
@@ -32,12 +32,6 @@ config ARCH_DEFCONFIG
 	default "arch/um/configs/i386_defconfig" if X86_32
 	default "arch/um/configs/x86_64_defconfig" if X86_64
 
-config RWSEM_XCHGADD_ALGORITHM
-	def_bool 64BIT
-
-config RWSEM_GENERIC_SPINLOCK
-	def_bool !RWSEM_XCHGADD_ALGORITHM
-
 config 3_LEVEL_PGTABLES
 	bool "Three-level pagetables" if !64BIT
 	default 64BIT
diff --git a/arch/x86/um/Makefile b/arch/x86/um/Makefile
index 2d686ae54681..33c51c064c77 100644
--- a/arch/x86/um/Makefile
+++ b/arch/x86/um/Makefile
@@ -21,14 +21,12 @@ obj-y += checksum_32.o syscalls_32.o
 obj-$(CONFIG_ELF_CORE) += elfcore.o
 
 subarch-y = ../lib/string_32.o ../lib/atomic64_32.o ../lib/atomic64_cx8_32.o
-subarch-$(CONFIG_RWSEM_XCHGADD_ALGORITHM) += ../lib/rwsem.o
 
 else
 
 obj-y += syscalls_64.o vdso/
 
-subarch-y = ../lib/csum-partial_64.o ../lib/memcpy_64.o ../entry/thunk_64.o \
-		../lib/rwsem.o
+subarch-y = ../lib/csum-partial_64.o ../lib/memcpy_64.o ../entry/thunk_64.o
 
 endif
 
diff --git a/arch/x86/um/vdso/Makefile b/arch/x86/um/vdso/Makefile
index bf94060fc06f..0caddd6acb22 100644
--- a/arch/x86/um/vdso/Makefile
+++ b/arch/x86/um/vdso/Makefile
@@ -62,7 +62,7 @@ quiet_cmd_vdso = VDSO    $@
 		       -Wl,-T,$(filter %.lds,$^) $(filter %.o,$^) && \
 		 sh $(srctree)/$(src)/checkundef.sh '$(NM)' '$@'
 
-VDSO_LDFLAGS = -fPIC -shared $(call cc-ldoption, -Wl$(comma)--hash-style=sysv)
+VDSO_LDFLAGS = -fPIC -shared -Wl,--hash-style=sysv
 GCOV_PROFILE := n
 
 #
diff --git a/arch/x86/xen/mmu_pv.c b/arch/x86/xen/mmu_pv.c
index a21e1734fc1f..beb44e22afdf 100644
--- a/arch/x86/xen/mmu_pv.c
+++ b/arch/x86/xen/mmu_pv.c
@@ -2318,8 +2318,6 @@ static void xen_set_fixmap(unsigned idx, phys_addr_t phys, pgprot_t prot)
 #elif defined(CONFIG_X86_VSYSCALL_EMULATION)
 	case VSYSCALL_PAGE:
 #endif
-	case FIX_TEXT_POKE0:
-	case FIX_TEXT_POKE1:
 		/* All local page mappings */
 		pte = pfn_pte(phys, prot);
 		break;
diff --git a/arch/x86/xen/smp_pv.c b/arch/x86/xen/smp_pv.c
index 145506f9fdbe..590fcf863006 100644
--- a/arch/x86/xen/smp_pv.c
+++ b/arch/x86/xen/smp_pv.c
@@ -361,7 +361,9 @@ static int xen_pv_cpu_up(unsigned int cpu, struct task_struct *idle)
 {
 	int rc;
 
-	common_cpu_up(cpu, idle);
+	rc = common_cpu_up(cpu, idle);
+	if (rc)
+		return rc;
 
 	xen_setup_runstate_info(cpu);
 
diff --git a/arch/x86/xen/xen-head.S b/arch/x86/xen/xen-head.S
index 5077ead5e59c..c1d8b90aa4e2 100644
--- a/arch/x86/xen/xen-head.S
+++ b/arch/x86/xen/xen-head.S
@@ -40,13 +40,13 @@ ENTRY(startup_xen)
 #ifdef CONFIG_X86_64
 	/* Set up %gs.
 	 *
-	 * The base of %gs always points to the bottom of the irqstack
-	 * union.  If the stack protector canary is enabled, it is
-	 * located at %gs:40.  Note that, on SMP, the boot cpu uses
-	 * init data section till per cpu areas are set up.
+	 * The base of %gs always points to fixed_percpu_data.  If the
+	 * stack protector canary is enabled, it is located at %gs:40.
+	 * Note that, on SMP, the boot cpu uses init data section until
+	 * the per cpu areas are set up.
 	 */
 	movl	$MSR_GS_BASE,%ecx
-	movq	$INIT_PER_CPU_VAR(irq_stack_union),%rax
+	movq	$INIT_PER_CPU_VAR(fixed_percpu_data),%rax
 	cdq
 	wrmsr
 #endif
diff --git a/arch/xtensa/Kconfig b/arch/xtensa/Kconfig
index 4b9aafe766c5..35c8d91e6106 100644
--- a/arch/xtensa/Kconfig
+++ b/arch/xtensa/Kconfig
@@ -46,9 +46,6 @@ config XTENSA
 	  with reasonable minimum requirements.  The Xtensa Linux project has
 	  a home page at <http://www.linux-xtensa.org/>.
 
-config RWSEM_XCHGADD_ALGORITHM
-	def_bool y
-
 config GENERIC_HWEIGHT
 	def_bool y
 
diff --git a/arch/xtensa/include/asm/Kbuild b/arch/xtensa/include/asm/Kbuild
index 42b6cb3d16f7..35f83c4bf239 100644
--- a/arch/xtensa/include/asm/Kbuild
+++ b/arch/xtensa/include/asm/Kbuild
@@ -15,16 +15,17 @@ generic-y += irq_work.h
 generic-y += kdebug.h
 generic-y += kmap_types.h
 generic-y += kprobes.h
+generic-y += kvm_para.h
 generic-y += local.h
 generic-y += local64.h
 generic-y += mcs_spinlock.h
 generic-y += mm-arch-hooks.h
+generic-y += mmiowb.h
 generic-y += param.h
 generic-y += percpu.h
 generic-y += preempt.h
 generic-y += qrwlock.h
 generic-y += qspinlock.h
-generic-y += rwsem.h
 generic-y += sections.h
 generic-y += socket.h
 generic-y += topology.h
diff --git a/arch/xtensa/include/asm/processor.h b/arch/xtensa/include/asm/processor.h
index f7dd895b2353..0c14018d1c26 100644
--- a/arch/xtensa/include/asm/processor.h
+++ b/arch/xtensa/include/asm/processor.h
@@ -187,15 +187,18 @@ struct thread_struct {
 
 /* Clearing a0 terminates the backtrace. */
 #define start_thread(regs, new_pc, new_sp) \
-	memset(regs, 0, sizeof(*regs)); \
-	regs->pc = new_pc; \
-	regs->ps = USER_PS_VALUE; \
-	regs->areg[1] = new_sp; \
-	regs->areg[0] = 0; \
-	regs->wmask = 1; \
-	regs->depc = 0; \
-	regs->windowbase = 0; \
-	regs->windowstart = 1;
+	do { \
+		memset((regs), 0, sizeof(*(regs))); \
+		(regs)->pc = (new_pc); \
+		(regs)->ps = USER_PS_VALUE; \
+		(regs)->areg[1] = (new_sp); \
+		(regs)->areg[0] = 0; \
+		(regs)->wmask = 1; \
+		(regs)->depc = 0; \
+		(regs)->windowbase = 0; \
+		(regs)->windowstart = 1; \
+		(regs)->syscall = NO_SYSCALL; \
+	} while (0)
 
 /* Forward declaration */
 struct task_struct;
diff --git a/arch/xtensa/include/asm/syscall.h b/arch/xtensa/include/asm/syscall.h
index a168bf81c7f4..91dc06d58060 100644
--- a/arch/xtensa/include/asm/syscall.h
+++ b/arch/xtensa/include/asm/syscall.h
@@ -59,45 +59,24 @@ static inline void syscall_set_return_value(struct task_struct *task,
 
 static inline void syscall_get_arguments(struct task_struct *task,
 					 struct pt_regs *regs,
-					 unsigned int i, unsigned int n,
 					 unsigned long *args)
 {
 	static const unsigned int reg[] = XTENSA_SYSCALL_ARGUMENT_REGS;
-	unsigned int j;
+	unsigned int i;
 
-	if (n == 0)
-		return;
-
-	WARN_ON_ONCE(i + n > SYSCALL_MAX_ARGS);
-
-	for (j = 0; j < n; ++j) {
-		if (i + j < SYSCALL_MAX_ARGS)
-			args[j] = regs->areg[reg[i + j]];
-		else
-			args[j] = 0;
-	}
+	for (i = 0; i < 6; ++i)
+		args[i] = regs->areg[reg[i]];
 }
 
 static inline void syscall_set_arguments(struct task_struct *task,
 					 struct pt_regs *regs,
-					 unsigned int i, unsigned int n,
 					 const unsigned long *args)
 {
 	static const unsigned int reg[] = XTENSA_SYSCALL_ARGUMENT_REGS;
-	unsigned int j;
-
-	if (n == 0)
-		return;
-
-	if (WARN_ON_ONCE(i + n > SYSCALL_MAX_ARGS)) {
-		if (i < SYSCALL_MAX_ARGS)
-			n = SYSCALL_MAX_ARGS - i;
-		else
-			return;
-	}
+	unsigned int i;
 
-	for (j = 0; j < n; ++j)
-		regs->areg[reg[i + j]] = args[j];
+	for (i = 0; i < 6; ++i)
+		regs->areg[reg[i]] = args[i];
 }
 
 asmlinkage long xtensa_rt_sigreturn(struct pt_regs*);
diff --git a/arch/xtensa/include/asm/tlb.h b/arch/xtensa/include/asm/tlb.h
index 0d766f9c1083..50889935138a 100644
--- a/arch/xtensa/include/asm/tlb.h
+++ b/arch/xtensa/include/asm/tlb.h
@@ -14,32 +14,6 @@
 #include <asm/cache.h>
 #include <asm/page.h>
 
-#if (DCACHE_WAY_SIZE <= PAGE_SIZE)
-
-/* Note, read http://lkml.org/lkml/2004/1/15/6 */
-
-# define tlb_start_vma(tlb,vma)			do { } while (0)
-# define tlb_end_vma(tlb,vma)			do { } while (0)
-
-#else
-
-# define tlb_start_vma(tlb, vma)					      \
-	do {								      \
-		if (!tlb->fullmm)					      \
-			flush_cache_range(vma, vma->vm_start, vma->vm_end);   \
-	} while(0)
-
-# define tlb_end_vma(tlb, vma)						      \
-	do {								      \
-		if (!tlb->fullmm)					      \
-			flush_tlb_range(vma, vma->vm_start, vma->vm_end);     \
-	} while(0)
-
-#endif
-
-#define __tlb_remove_tlb_entry(tlb,pte,addr)	do { } while (0)
-#define tlb_flush(tlb)				flush_tlb_mm((tlb)->mm)
-
 #include <asm-generic/tlb.h>
 
 #define __pte_free_tlb(tlb, pte, address)	pte_free((tlb)->mm, pte)
diff --git a/arch/xtensa/include/uapi/asm/Kbuild b/arch/xtensa/include/uapi/asm/Kbuild
index 8a7ad40be463..7417847dc438 100644
--- a/arch/xtensa/include/uapi/asm/Kbuild
+++ b/arch/xtensa/include/uapi/asm/Kbuild
@@ -1,2 +1 @@
 generated-y += unistd_32.h
-generic-y += kvm_para.h
diff --git a/arch/xtensa/kernel/entry.S b/arch/xtensa/kernel/entry.S
index e50f5124dc6f..e54af8b7e0f8 100644
--- a/arch/xtensa/kernel/entry.S
+++ b/arch/xtensa/kernel/entry.S
@@ -1860,6 +1860,8 @@ ENTRY(system_call)
 	l32i	a7, a2, PT_SYSCALL
 
 1:
+	s32i	a7, a1, 4
+
 	/* syscall = sys_call_table[syscall_nr] */
 
 	movi	a4, sys_call_table
@@ -1893,8 +1895,12 @@ ENTRY(system_call)
 	retw
 
 1:
+	l32i	a4, a1, 4
+	l32i	a3, a2, PT_SYSCALL
+	s32i	a4, a2, PT_SYSCALL
 	mov	a6, a2
 	call4	do_syscall_trace_leave
+	s32i	a3, a2, PT_SYSCALL
 	retw
 
 ENDPROC(system_call)
diff --git a/arch/xtensa/kernel/stacktrace.c b/arch/xtensa/kernel/stacktrace.c
index 174c11f13bba..b9f82510c650 100644
--- a/arch/xtensa/kernel/stacktrace.c
+++ b/arch/xtensa/kernel/stacktrace.c
@@ -253,10 +253,14 @@ static int return_address_cb(struct stackframe *frame, void *data)
 	return 1;
 }
 
+/*
+ * level == 0 is for the return address from the caller of this function,
+ * not from this function itself.
+ */
 unsigned long return_address(unsigned level)
 {
 	struct return_addr_data r = {
-		.skip = level + 1,
+		.skip = level,
 	};
 	walk_stackframe(stack_pointer(NULL), return_address_cb, &r);
 	return r.addr;
diff --git a/arch/xtensa/kernel/syscalls/syscall.tbl b/arch/xtensa/kernel/syscalls/syscall.tbl
index 6af49929de85..30084eaf8422 100644
--- a/arch/xtensa/kernel/syscalls/syscall.tbl
+++ b/arch/xtensa/kernel/syscalls/syscall.tbl
@@ -394,3 +394,7 @@
 421	common	rt_sigtimedwait_time64		sys_rt_sigtimedwait
 422	common	futex_time64			sys_futex
 423	common	sched_rr_get_interval_time64	sys_sched_rr_get_interval
+424	common	pidfd_send_signal		sys_pidfd_send_signal
+425	common	io_uring_setup			sys_io_uring_setup
+426	common	io_uring_enter			sys_io_uring_enter
+427	common	io_uring_register		sys_io_uring_register
diff --git a/arch/xtensa/mm/mmu.c b/arch/xtensa/mm/mmu.c
index 2fb7d1172228..03678c4afc39 100644
--- a/arch/xtensa/mm/mmu.c
+++ b/arch/xtensa/mm/mmu.c
@@ -33,7 +33,7 @@ static void * __init init_pmd(unsigned long vaddr, unsigned long n_pages)
 
 	pte = memblock_alloc_low(n_pages * sizeof(pte_t), PAGE_SIZE);
 	if (!pte)
-		panic("%s: Failed to allocate %zu bytes align=%lx\n",
+		panic("%s: Failed to allocate %lu bytes align=%lx\n",
 		      __func__, n_pages * sizeof(pte_t), PAGE_SIZE);
 
 	for (i = 0; i < n_pages; ++i)
diff --git a/block/bfq-iosched.c b/block/bfq-iosched.c
index 4c592496a16a..5ba1e0d841b4 100644
--- a/block/bfq-iosched.c
+++ b/block/bfq-iosched.c
@@ -674,7 +674,7 @@ static bool bfq_symmetric_scenario(struct bfq_data *bfqd)
 	 * at least two nodes.
 	 */
 	return !(varied_queue_weights || multiple_classes_busy
-#ifdef BFQ_GROUP_IOSCHED_ENABLED
+#ifdef CONFIG_BFQ_GROUP_IOSCHED
 	       || bfqd->num_groups_with_pending_reqs > 0
 #endif
 		);
@@ -2822,7 +2822,7 @@ static void bfq_dispatch_remove(struct request_queue *q, struct request *rq)
 	bfq_remove_request(q, rq);
 }
 
-static void __bfq_bfqq_expire(struct bfq_data *bfqd, struct bfq_queue *bfqq)
+static bool __bfq_bfqq_expire(struct bfq_data *bfqd, struct bfq_queue *bfqq)
 {
 	/*
 	 * If this bfqq is shared between multiple processes, check
@@ -2855,9 +2855,11 @@ static void __bfq_bfqq_expire(struct bfq_data *bfqd, struct bfq_queue *bfqq)
 	/*
 	 * All in-service entities must have been properly deactivated
 	 * or requeued before executing the next function, which
-	 * resets all in-service entites as no more in service.
+	 * resets all in-service entities as no more in service. This
+	 * may cause bfqq to be freed. If this happens, the next
+	 * function returns true.
 	 */
-	__bfq_bfqd_reset_in_service(bfqd);
+	return __bfq_bfqd_reset_in_service(bfqd);
 }
 
 /**
@@ -3262,7 +3264,6 @@ void bfq_bfqq_expire(struct bfq_data *bfqd,
 	bool slow;
 	unsigned long delta = 0;
 	struct bfq_entity *entity = &bfqq->entity;
-	int ref;
 
 	/*
 	 * Check whether the process is slow (see bfq_bfqq_is_slow).
@@ -3347,10 +3348,8 @@ void bfq_bfqq_expire(struct bfq_data *bfqd,
 	 * reason.
 	 */
 	__bfq_bfqq_recalc_budget(bfqd, bfqq, reason);
-	ref = bfqq->ref;
-	__bfq_bfqq_expire(bfqd, bfqq);
-
-	if (ref == 1) /* bfqq is gone, no more actions on it */
+	if (__bfq_bfqq_expire(bfqd, bfqq))
+		/* bfqq is gone, no more actions on it */
 		return;
 
 	bfqq->injected_service = 0;
@@ -5397,7 +5396,7 @@ static unsigned int bfq_update_depths(struct bfq_data *bfqd,
 	return min_shallow;
 }
 
-static int bfq_init_hctx(struct blk_mq_hw_ctx *hctx, unsigned int index)
+static void bfq_depth_updated(struct blk_mq_hw_ctx *hctx)
 {
 	struct bfq_data *bfqd = hctx->queue->elevator->elevator_data;
 	struct blk_mq_tags *tags = hctx->sched_tags;
@@ -5405,6 +5404,11 @@ static int bfq_init_hctx(struct blk_mq_hw_ctx *hctx, unsigned int index)
 
 	min_shallow = bfq_update_depths(bfqd, &tags->bitmap_tags);
 	sbitmap_queue_min_shallow_depth(&tags->bitmap_tags, min_shallow);
+}
+
+static int bfq_init_hctx(struct blk_mq_hw_ctx *hctx, unsigned int index)
+{
+	bfq_depth_updated(hctx);
 	return 0;
 }
 
@@ -5827,6 +5831,7 @@ static struct elevator_type iosched_bfq_mq = {
 		.requests_merged	= bfq_requests_merged,
 		.request_merged		= bfq_request_merged,
 		.has_work		= bfq_has_work,
+		.depth_updated		= bfq_depth_updated,
 		.init_hctx		= bfq_init_hctx,
 		.init_sched		= bfq_init_queue,
 		.exit_sched		= bfq_exit_queue,
diff --git a/block/bfq-iosched.h b/block/bfq-iosched.h
index 062e1c4787f4..86394e503ca9 100644
--- a/block/bfq-iosched.h
+++ b/block/bfq-iosched.h
@@ -995,7 +995,7 @@ bool __bfq_deactivate_entity(struct bfq_entity *entity,
 			     bool ins_into_idle_tree);
 bool next_queue_may_preempt(struct bfq_data *bfqd);
 struct bfq_queue *bfq_get_next_queue(struct bfq_data *bfqd);
-void __bfq_bfqd_reset_in_service(struct bfq_data *bfqd);
+bool __bfq_bfqd_reset_in_service(struct bfq_data *bfqd);
 void bfq_deactivate_bfqq(struct bfq_data *bfqd, struct bfq_queue *bfqq,
 			 bool ins_into_idle_tree, bool expiration);
 void bfq_activate_bfqq(struct bfq_data *bfqd, struct bfq_queue *bfqq);
diff --git a/block/bfq-wf2q.c b/block/bfq-wf2q.c
index 63311d1ff1ed..ae4d000ac0af 100644
--- a/block/bfq-wf2q.c
+++ b/block/bfq-wf2q.c
@@ -1012,7 +1012,7 @@ static void __bfq_activate_entity(struct bfq_entity *entity,
 		entity->on_st = true;
 	}
 
-#ifdef BFQ_GROUP_IOSCHED_ENABLED
+#ifdef CONFIG_BFQ_GROUP_IOSCHED
 	if (!bfq_entity_to_bfqq(entity)) { /* bfq_group */
 		struct bfq_group *bfqg =
 			container_of(entity, struct bfq_group, entity);
@@ -1605,7 +1605,8 @@ struct bfq_queue *bfq_get_next_queue(struct bfq_data *bfqd)
 	return bfqq;
 }
 
-void __bfq_bfqd_reset_in_service(struct bfq_data *bfqd)
+/* returns true if the in-service queue gets freed */
+bool __bfq_bfqd_reset_in_service(struct bfq_data *bfqd)
 {
 	struct bfq_queue *in_serv_bfqq = bfqd->in_service_queue;
 	struct bfq_entity *in_serv_entity = &in_serv_bfqq->entity;
@@ -1629,8 +1630,20 @@ void __bfq_bfqd_reset_in_service(struct bfq_data *bfqd)
 	 * service tree either, then release the service reference to
 	 * the queue it represents (taken with bfq_get_entity).
 	 */
-	if (!in_serv_entity->on_st)
+	if (!in_serv_entity->on_st) {
+		/*
+		 * If no process is referencing in_serv_bfqq any
+		 * longer, then the service reference may be the only
+		 * reference to the queue. If this is the case, then
+		 * bfqq gets freed here.
+		 */
+		int ref = in_serv_bfqq->ref;
 		bfq_put_queue(in_serv_bfqq);
+		if (ref == 1)
+			return true;
+	}
+
+	return false;
 }
 
 void bfq_deactivate_bfqq(struct bfq_data *bfqd, struct bfq_queue *bfqq,
diff --git a/block/bio.c b/block/bio.c
index b64cedc7f87c..716510ecd7ff 100644
--- a/block/bio.c
+++ b/block/bio.c
@@ -1298,8 +1298,11 @@ struct bio *bio_copy_user_iov(struct request_queue *q,
 			}
 		}
 
-		if (bio_add_pc_page(q, bio, page, bytes, offset) < bytes)
+		if (bio_add_pc_page(q, bio, page, bytes, offset) < bytes) {
+			if (!map_data)
+				__free_page(page);
 			break;
+		}
 
 		len -= bytes;
 		offset = 0;
diff --git a/block/blk-core.c b/block/blk-core.c
index 4673ebe42255..a55389ba8779 100644
--- a/block/blk-core.c
+++ b/block/blk-core.c
@@ -1245,8 +1245,6 @@ static int blk_cloned_rq_check_limits(struct request_queue *q,
  */
 blk_status_t blk_insert_cloned_request(struct request_queue *q, struct request *rq)
 {
-	blk_qc_t unused;
-
 	if (blk_cloned_rq_check_limits(q, rq))
 		return BLK_STS_IOERR;
 
@@ -1262,7 +1260,7 @@ blk_status_t blk_insert_cloned_request(struct request_queue *q, struct request *
 	 * bypass a potential scheduler on the bottom device for
 	 * insert.
 	 */
-	return blk_mq_try_issue_directly(rq->mq_hctx, rq, &unused, true, true);
+	return blk_mq_request_issue_directly(rq, true);
 }
 EXPORT_SYMBOL_GPL(blk_insert_cloned_request);
 
diff --git a/block/blk-flush.c b/block/blk-flush.c
index 6e0f2d97fc6d..d95f94892015 100644
--- a/block/blk-flush.c
+++ b/block/blk-flush.c
@@ -220,7 +220,7 @@ static void flush_end_io(struct request *flush_rq, blk_status_t error)
 		blk_mq_tag_set_rq(hctx, flush_rq->tag, fq->orig_rq);
 		flush_rq->tag = -1;
 	} else {
-		blk_mq_put_driver_tag_hctx(hctx, flush_rq);
+		blk_mq_put_driver_tag(flush_rq);
 		flush_rq->internal_tag = -1;
 	}
 
@@ -324,7 +324,7 @@ static void mq_flush_data_end_io(struct request *rq, blk_status_t error)
 
 	if (q->elevator) {
 		WARN_ON(rq->tag < 0);
-		blk_mq_put_driver_tag_hctx(hctx, rq);
+		blk_mq_put_driver_tag(rq);
 	}
 
 	/*
diff --git a/block/blk-mq-sched.c b/block/blk-mq-sched.c
index 40905539afed..aa6bc5c02643 100644
--- a/block/blk-mq-sched.c
+++ b/block/blk-mq-sched.c
@@ -423,10 +423,12 @@ void blk_mq_sched_insert_requests(struct blk_mq_hw_ctx *hctx,
 		 * busy in case of 'none' scheduler, and this way may save
 		 * us one extra enqueue & dequeue to sw queue.
 		 */
-		if (!hctx->dispatch_busy && !e && !run_queue_async)
+		if (!hctx->dispatch_busy && !e && !run_queue_async) {
 			blk_mq_try_issue_list_directly(hctx, list);
-		else
-			blk_mq_insert_requests(hctx, ctx, list);
+			if (list_empty(list))
+				return;
+		}
+		blk_mq_insert_requests(hctx, ctx, list);
 	}
 
 	blk_mq_run_hw_queue(hctx, run_queue_async);
diff --git a/block/blk-mq.c b/block/blk-mq.c
index 70b210a308c4..fc60ed7e940e 100644
--- a/block/blk-mq.c
+++ b/block/blk-mq.c
@@ -59,7 +59,8 @@ static int blk_mq_poll_stats_bkt(const struct request *rq)
 }
 
 /*
- * Check if any of the ctx's have pending work in this hardware queue
+ * Check if any of the ctx, dispatch list or elevator
+ * have pending work in this hardware queue.
  */
 static bool blk_mq_hctx_has_pending(struct blk_mq_hw_ctx *hctx)
 {
@@ -653,6 +654,13 @@ bool blk_mq_complete_request(struct request *rq)
 }
 EXPORT_SYMBOL(blk_mq_complete_request);
 
+void blk_mq_complete_request_sync(struct request *rq)
+{
+	WRITE_ONCE(rq->state, MQ_RQ_COMPLETE);
+	rq->q->mq_ops->complete(rq);
+}
+EXPORT_SYMBOL_GPL(blk_mq_complete_request_sync);
+
 int blk_mq_request_started(struct request *rq)
 {
 	return blk_mq_rq_state(rq) != MQ_RQ_IDLE;
@@ -1071,7 +1079,13 @@ static int blk_mq_dispatch_wake(wait_queue_entry_t *wait, unsigned mode,
 	hctx = container_of(wait, struct blk_mq_hw_ctx, dispatch_wait);
 
 	spin_lock(&hctx->dispatch_wait_lock);
-	list_del_init(&wait->entry);
+	if (!list_empty(&wait->entry)) {
+		struct sbitmap_queue *sbq;
+
+		list_del_init(&wait->entry);
+		sbq = &hctx->tags->bitmap_tags;
+		atomic_dec(&sbq->ws_active);
+	}
 	spin_unlock(&hctx->dispatch_wait_lock);
 
 	blk_mq_run_hw_queue(hctx, true);
@@ -1087,6 +1101,7 @@ static int blk_mq_dispatch_wake(wait_queue_entry_t *wait, unsigned mode,
 static bool blk_mq_mark_tag_wait(struct blk_mq_hw_ctx *hctx,
 				 struct request *rq)
 {
+	struct sbitmap_queue *sbq = &hctx->tags->bitmap_tags;
 	struct wait_queue_head *wq;
 	wait_queue_entry_t *wait;
 	bool ret;
@@ -1109,7 +1124,7 @@ static bool blk_mq_mark_tag_wait(struct blk_mq_hw_ctx *hctx,
 	if (!list_empty_careful(&wait->entry))
 		return false;
 
-	wq = &bt_wait_ptr(&hctx->tags->bitmap_tags, hctx)->wait;
+	wq = &bt_wait_ptr(sbq, hctx)->wait;
 
 	spin_lock_irq(&wq->lock);
 	spin_lock(&hctx->dispatch_wait_lock);
@@ -1119,6 +1134,7 @@ static bool blk_mq_mark_tag_wait(struct blk_mq_hw_ctx *hctx,
 		return false;
 	}
 
+	atomic_inc(&sbq->ws_active);
 	wait->flags &= ~WQ_FLAG_EXCLUSIVE;
 	__add_wait_queue(wq, wait);
 
@@ -1139,6 +1155,7 @@ static bool blk_mq_mark_tag_wait(struct blk_mq_hw_ctx *hctx,
 	 * someone else gets the wakeup.
 	 */
 	list_del_init(&wait->entry);
+	atomic_dec(&sbq->ws_active);
 	spin_unlock(&hctx->dispatch_wait_lock);
 	spin_unlock_irq(&wq->lock);
 
@@ -1701,11 +1718,12 @@ void blk_mq_flush_plug_list(struct blk_plug *plug, bool from_schedule)
 	unsigned int depth;
 
 	list_splice_init(&plug->mq_list, &list);
-	plug->rq_count = 0;
 
 	if (plug->rq_count > 2 && plug->multiple_queues)
 		list_sort(NULL, &list, plug_rq_cmp);
 
+	plug->rq_count = 0;
+
 	this_q = NULL;
 	this_hctx = NULL;
 	this_ctx = NULL;
@@ -1790,74 +1808,76 @@ static blk_status_t __blk_mq_issue_directly(struct blk_mq_hw_ctx *hctx,
 	return ret;
 }
 
-blk_status_t blk_mq_try_issue_directly(struct blk_mq_hw_ctx *hctx,
+static blk_status_t __blk_mq_try_issue_directly(struct blk_mq_hw_ctx *hctx,
 						struct request *rq,
 						blk_qc_t *cookie,
-						bool bypass, bool last)
+						bool bypass_insert, bool last)
 {
 	struct request_queue *q = rq->q;
 	bool run_queue = true;
-	blk_status_t ret = BLK_STS_RESOURCE;
-	int srcu_idx;
-	bool force = false;
 
-	hctx_lock(hctx, &srcu_idx);
 	/*
-	 * hctx_lock is needed before checking quiesced flag.
+	 * RCU or SRCU read lock is needed before checking quiesced flag.
 	 *
-	 * When queue is stopped or quiesced, ignore 'bypass', insert
-	 * and return BLK_STS_OK to caller, and avoid driver to try to
-	 * dispatch again.
+	 * When queue is stopped or quiesced, ignore 'bypass_insert' from
+	 * blk_mq_request_issue_directly(), and return BLK_STS_OK to caller,
+	 * and avoid driver to try to dispatch again.
 	 */
-	if (unlikely(blk_mq_hctx_stopped(hctx) || blk_queue_quiesced(q))) {
+	if (blk_mq_hctx_stopped(hctx) || blk_queue_quiesced(q)) {
 		run_queue = false;
-		bypass = false;
-		goto out_unlock;
+		bypass_insert = false;
+		goto insert;
 	}
 
-	if (unlikely(q->elevator && !bypass))
-		goto out_unlock;
+	if (q->elevator && !bypass_insert)
+		goto insert;
 
 	if (!blk_mq_get_dispatch_budget(hctx))
-		goto out_unlock;
+		goto insert;
 
 	if (!blk_mq_get_driver_tag(rq)) {
 		blk_mq_put_dispatch_budget(hctx);
-		goto out_unlock;
+		goto insert;
 	}
 
-	/*
-	 * Always add a request that has been through
-	 *.queue_rq() to the hardware dispatch list.
-	 */
-	force = true;
-	ret = __blk_mq_issue_directly(hctx, rq, cookie, last);
-out_unlock:
+	return __blk_mq_issue_directly(hctx, rq, cookie, last);
+insert:
+	if (bypass_insert)
+		return BLK_STS_RESOURCE;
+
+	blk_mq_request_bypass_insert(rq, run_queue);
+	return BLK_STS_OK;
+}
+
+static void blk_mq_try_issue_directly(struct blk_mq_hw_ctx *hctx,
+		struct request *rq, blk_qc_t *cookie)
+{
+	blk_status_t ret;
+	int srcu_idx;
+
+	might_sleep_if(hctx->flags & BLK_MQ_F_BLOCKING);
+
+	hctx_lock(hctx, &srcu_idx);
+
+	ret = __blk_mq_try_issue_directly(hctx, rq, cookie, false, true);
+	if (ret == BLK_STS_RESOURCE || ret == BLK_STS_DEV_RESOURCE)
+		blk_mq_request_bypass_insert(rq, true);
+	else if (ret != BLK_STS_OK)
+		blk_mq_end_request(rq, ret);
+
+	hctx_unlock(hctx, srcu_idx);
+}
+
+blk_status_t blk_mq_request_issue_directly(struct request *rq, bool last)
+{
+	blk_status_t ret;
+	int srcu_idx;
+	blk_qc_t unused_cookie;
+	struct blk_mq_hw_ctx *hctx = rq->mq_hctx;
+
+	hctx_lock(hctx, &srcu_idx);
+	ret = __blk_mq_try_issue_directly(hctx, rq, &unused_cookie, true, last);
 	hctx_unlock(hctx, srcu_idx);
-	switch (ret) {
-	case BLK_STS_OK:
-		break;
-	case BLK_STS_DEV_RESOURCE:
-	case BLK_STS_RESOURCE:
-		if (force) {
-			blk_mq_request_bypass_insert(rq, run_queue);
-			/*
-			 * We have to return BLK_STS_OK for the DM
-			 * to avoid livelock. Otherwise, we return
-			 * the real result to indicate whether the
-			 * request is direct-issued successfully.
-			 */
-			ret = bypass ? BLK_STS_OK : ret;
-		} else if (!bypass) {
-			blk_mq_sched_insert_request(rq, false,
-						    run_queue, false);
-		}
-		break;
-	default:
-		if (!bypass)
-			blk_mq_end_request(rq, ret);
-		break;
-	}
 
 	return ret;
 }
@@ -1865,20 +1885,22 @@ out_unlock:
 void blk_mq_try_issue_list_directly(struct blk_mq_hw_ctx *hctx,
 		struct list_head *list)
 {
-	blk_qc_t unused;
-	blk_status_t ret = BLK_STS_OK;
-
 	while (!list_empty(list)) {
+		blk_status_t ret;
 		struct request *rq = list_first_entry(list, struct request,
 				queuelist);
 
 		list_del_init(&rq->queuelist);
-		if (ret == BLK_STS_OK)
-			ret = blk_mq_try_issue_directly(hctx, rq, &unused,
-							false,
+		ret = blk_mq_request_issue_directly(rq, list_empty(list));
+		if (ret != BLK_STS_OK) {
+			if (ret == BLK_STS_RESOURCE ||
+					ret == BLK_STS_DEV_RESOURCE) {
+				blk_mq_request_bypass_insert(rq,
 							list_empty(list));
-		else
-			blk_mq_sched_insert_request(rq, false, true, false);
+				break;
+			}
+			blk_mq_end_request(rq, ret);
+		}
 	}
 
 	/*
@@ -1886,7 +1908,7 @@ void blk_mq_try_issue_list_directly(struct blk_mq_hw_ctx *hctx,
 	 * the driver there was more coming, but that turned out to
 	 * be a lie.
 	 */
-	if (ret != BLK_STS_OK && hctx->queue->mq_ops->commit_rqs)
+	if (!list_empty(list) && hctx->queue->mq_ops->commit_rqs)
 		hctx->queue->mq_ops->commit_rqs(hctx);
 }
 
@@ -1993,19 +2015,21 @@ static blk_qc_t blk_mq_make_request(struct request_queue *q, struct bio *bio)
 			plug->rq_count--;
 		}
 		blk_add_rq_to_plug(plug, rq);
+		trace_block_plug(q);
 
 		blk_mq_put_ctx(data.ctx);
 
 		if (same_queue_rq) {
 			data.hctx = same_queue_rq->mq_hctx;
+			trace_block_unplug(q, 1, true);
 			blk_mq_try_issue_directly(data.hctx, same_queue_rq,
-					&cookie, false, true);
+					&cookie);
 		}
 	} else if ((q->nr_hw_queues > 1 && is_sync) || (!q->elevator &&
 			!data.hctx->dispatch_busy)) {
 		blk_mq_put_ctx(data.ctx);
 		blk_mq_bio_to_request(rq, bio);
-		blk_mq_try_issue_directly(data.hctx, rq, &cookie, false, true);
+		blk_mq_try_issue_directly(data.hctx, rq, &cookie);
 	} else {
 		blk_mq_put_ctx(data.ctx);
 		blk_mq_bio_to_request(rq, bio);
@@ -2322,7 +2346,7 @@ static int blk_mq_init_hctx(struct request_queue *q,
 	return 0;
 
  free_fq:
-	kfree(hctx->fq);
+	blk_free_flush_queue(hctx->fq);
  exit_hctx:
 	if (set->ops->exit_hctx)
 		set->ops->exit_hctx(hctx, hctx_idx);
@@ -3111,6 +3135,8 @@ int blk_mq_update_nr_requests(struct request_queue *q, unsigned int nr)
 		}
 		if (ret)
 			break;
+		if (q->elevator && q->elevator->type->ops.depth_updated)
+			q->elevator->type->ops.depth_updated(hctx);
 	}
 
 	if (!ret)
diff --git a/block/blk-mq.h b/block/blk-mq.h
index 0ed8e5a8729f..423ea88ab6fb 100644
--- a/block/blk-mq.h
+++ b/block/blk-mq.h
@@ -70,10 +70,8 @@ void blk_mq_request_bypass_insert(struct request *rq, bool run_queue);
 void blk_mq_insert_requests(struct blk_mq_hw_ctx *hctx, struct blk_mq_ctx *ctx,
 				struct list_head *list);
 
-blk_status_t blk_mq_try_issue_directly(struct blk_mq_hw_ctx *hctx,
-						struct request *rq,
-						blk_qc_t *cookie,
-						bool bypass, bool last);
+/* Used by blk_insert_cloned_request() to issue request directly */
+blk_status_t blk_mq_request_issue_directly(struct request *rq, bool last);
 void blk_mq_try_issue_list_directly(struct blk_mq_hw_ctx *hctx,
 				    struct list_head *list);
 
@@ -224,15 +222,6 @@ static inline void __blk_mq_put_driver_tag(struct blk_mq_hw_ctx *hctx,
 	}
 }
 
-static inline void blk_mq_put_driver_tag_hctx(struct blk_mq_hw_ctx *hctx,
-				       struct request *rq)
-{
-	if (rq->tag == -1 || rq->internal_tag == -1)
-		return;
-
-	__blk_mq_put_driver_tag(hctx, rq);
-}
-
 static inline void blk_mq_put_driver_tag(struct request *rq)
 {
 	if (rq->tag == -1 || rq->internal_tag == -1)
diff --git a/crypto/842.c b/crypto/842.c
index bc26dc942821..5f98393b65d1 100644
--- a/crypto/842.c
+++ b/crypto/842.c
@@ -144,7 +144,7 @@ static int __init crypto842_mod_init(void)
 
 	return ret;
 }
-module_init(crypto842_mod_init);
+subsys_initcall(crypto842_mod_init);
 
 static void __exit crypto842_mod_exit(void)
 {
diff --git a/crypto/Kconfig b/crypto/Kconfig
index bbab6bf33519..3d056e7da65f 100644
--- a/crypto/Kconfig
+++ b/crypto/Kconfig
@@ -27,8 +27,8 @@ config CRYPTO_FIPS
 	depends on (CRYPTO_ANSI_CPRNG || CRYPTO_DRBG) && !CRYPTO_MANAGER_DISABLE_TESTS
 	depends on (MODULE_SIG || !MODULES)
 	help
-	  This options enables the fips boot option which is
-	  required if you want to system to operate in a FIPS 200
+	  This option enables the fips boot option which is
+	  required if you want the system to operate in a FIPS 200
 	  certification.  You should say no unless you know what
 	  this is.
 
@@ -113,29 +113,6 @@ config CRYPTO_ACOMP
 	select CRYPTO_ALGAPI
 	select CRYPTO_ACOMP2
 
-config CRYPTO_RSA
-	tristate "RSA algorithm"
-	select CRYPTO_AKCIPHER
-	select CRYPTO_MANAGER
-	select MPILIB
-	select ASN1
-	help
-	  Generic implementation of the RSA public key algorithm.
-
-config CRYPTO_DH
-	tristate "Diffie-Hellman algorithm"
-	select CRYPTO_KPP
-	select MPILIB
-	help
-	  Generic implementation of the Diffie-Hellman algorithm.
-
-config CRYPTO_ECDH
-	tristate "ECDH algorithm"
-	select CRYPTO_KPP
-	select CRYPTO_RNG_DEFAULT
-	help
-	  Generic implementation of the ECDH algorithm
-
 config CRYPTO_MANAGER
 	tristate "Cryptographic algorithm manager"
 	select CRYPTO_MANAGER2
@@ -253,6 +230,48 @@ config CRYPTO_GLUE_HELPER_X86
 config CRYPTO_ENGINE
 	tristate
 
+comment "Public-key cryptography"
+
+config CRYPTO_RSA
+	tristate "RSA algorithm"
+	select CRYPTO_AKCIPHER
+	select CRYPTO_MANAGER
+	select MPILIB
+	select ASN1
+	help
+	  Generic implementation of the RSA public key algorithm.
+
+config CRYPTO_DH
+	tristate "Diffie-Hellman algorithm"
+	select CRYPTO_KPP
+	select MPILIB
+	help
+	  Generic implementation of the Diffie-Hellman algorithm.
+
+config CRYPTO_ECC
+	tristate
+
+config CRYPTO_ECDH
+	tristate "ECDH algorithm"
+	select CRYPTO_ECC
+	select CRYPTO_KPP
+	select CRYPTO_RNG_DEFAULT
+	help
+	  Generic implementation of the ECDH algorithm
+
+config CRYPTO_ECRDSA
+	tristate "EC-RDSA (GOST 34.10) algorithm"
+	select CRYPTO_ECC
+	select CRYPTO_AKCIPHER
+	select CRYPTO_STREEBOG
+	select OID_REGISTRY
+	select ASN1
+	help
+	  Elliptic Curve Russian Digital Signature Algorithm (GOST R 34.10-2012,
+	  RFC 7091, ISO/IEC 14888-3:2018) is one of the Russian cryptographic
+	  standard algorithms (called GOST algorithms). Only signature verification
+	  is implemented.
+
 comment "Authenticated Encryption with Associated Data"
 
 config CRYPTO_CCM
@@ -310,25 +329,25 @@ config CRYPTO_AEGIS128_AESNI_SSE2
 	tristate "AEGIS-128 AEAD algorithm (x86_64 AESNI+SSE2 implementation)"
 	depends on X86 && 64BIT
 	select CRYPTO_AEAD
-	select CRYPTO_CRYPTD
+	select CRYPTO_SIMD
 	help
-	 AESNI+SSE2 implementation of the AEGSI-128 dedicated AEAD algorithm.
+	 AESNI+SSE2 implementation of the AEGIS-128 dedicated AEAD algorithm.
 
 config CRYPTO_AEGIS128L_AESNI_SSE2
 	tristate "AEGIS-128L AEAD algorithm (x86_64 AESNI+SSE2 implementation)"
 	depends on X86 && 64BIT
 	select CRYPTO_AEAD
-	select CRYPTO_CRYPTD
+	select CRYPTO_SIMD
 	help
-	 AESNI+SSE2 implementation of the AEGSI-128L dedicated AEAD algorithm.
+	 AESNI+SSE2 implementation of the AEGIS-128L dedicated AEAD algorithm.
 
 config CRYPTO_AEGIS256_AESNI_SSE2
 	tristate "AEGIS-256 AEAD algorithm (x86_64 AESNI+SSE2 implementation)"
 	depends on X86 && 64BIT
 	select CRYPTO_AEAD
-	select CRYPTO_CRYPTD
+	select CRYPTO_SIMD
 	help
-	 AESNI+SSE2 implementation of the AEGSI-256 dedicated AEAD algorithm.
+	 AESNI+SSE2 implementation of the AEGIS-256 dedicated AEAD algorithm.
 
 config CRYPTO_MORUS640
 	tristate "MORUS-640 AEAD algorithm"
@@ -340,7 +359,7 @@ config CRYPTO_MORUS640_GLUE
 	tristate
 	depends on X86
 	select CRYPTO_AEAD
-	select CRYPTO_CRYPTD
+	select CRYPTO_SIMD
 	help
 	  Common glue for SIMD optimizations of the MORUS-640 dedicated AEAD
 	  algorithm.
@@ -363,7 +382,7 @@ config CRYPTO_MORUS1280_GLUE
 	tristate
 	depends on X86
 	select CRYPTO_AEAD
-	select CRYPTO_CRYPTD
+	select CRYPTO_SIMD
 	help
 	  Common glue for SIMD optimizations of the MORUS-1280 dedicated AEAD
 	  algorithm.
diff --git a/crypto/Makefile b/crypto/Makefile
index fb5bf2a3a666..266a4cdbb9e2 100644
--- a/crypto/Makefile
+++ b/crypto/Makefile
@@ -147,12 +147,20 @@ obj-$(CONFIG_CRYPTO_USER_API_RNG) += algif_rng.o
 obj-$(CONFIG_CRYPTO_USER_API_AEAD) += algif_aead.o
 obj-$(CONFIG_CRYPTO_ZSTD) += zstd.o
 obj-$(CONFIG_CRYPTO_OFB) += ofb.o
+obj-$(CONFIG_CRYPTO_ECC) += ecc.o
 
-ecdh_generic-y := ecc.o
 ecdh_generic-y += ecdh.o
 ecdh_generic-y += ecdh_helper.o
 obj-$(CONFIG_CRYPTO_ECDH) += ecdh_generic.o
 
+$(obj)/ecrdsa_params.asn1.o: $(obj)/ecrdsa_params.asn1.c $(obj)/ecrdsa_params.asn1.h
+$(obj)/ecrdsa_pub_key.asn1.o: $(obj)/ecrdsa_pub_key.asn1.c $(obj)/ecrdsa_pub_key.asn1.h
+$(obj)/ecrdsa.o: $(obj)/ecrdsa_params.asn1.h $(obj)/ecrdsa_pub_key.asn1.h
+ecrdsa_generic-y += ecrdsa.o
+ecrdsa_generic-y += ecrdsa_params.asn1.o
+ecrdsa_generic-y += ecrdsa_pub_key.asn1.o
+obj-$(CONFIG_CRYPTO_ECRDSA) += ecrdsa_generic.o
+
 #
 # generic algorithms and the async_tx api
 #
diff --git a/crypto/adiantum.c b/crypto/adiantum.c
index 5564e73266a6..395a3ddd3707 100644
--- a/crypto/adiantum.c
+++ b/crypto/adiantum.c
@@ -265,7 +265,6 @@ static int adiantum_hash_message(struct skcipher_request *req,
 	int err;
 
 	hash_desc->tfm = tctx->hash;
-	hash_desc->flags = 0;
 
 	err = crypto_shash_init(hash_desc);
 	if (err)
@@ -659,7 +658,7 @@ static void __exit adiantum_module_exit(void)
 	crypto_unregister_template(&adiantum_tmpl);
 }
 
-module_init(adiantum_module_init);
+subsys_initcall(adiantum_module_init);
 module_exit(adiantum_module_exit);
 
 MODULE_DESCRIPTION("Adiantum length-preserving encryption mode");
diff --git a/crypto/aegis128.c b/crypto/aegis128.c
index 3718a8341303..d78f77fc5dd1 100644
--- a/crypto/aegis128.c
+++ b/crypto/aegis128.c
@@ -448,7 +448,7 @@ static void __exit crypto_aegis128_module_exit(void)
 	crypto_unregister_aead(&crypto_aegis128_alg);
 }
 
-module_init(crypto_aegis128_module_init);
+subsys_initcall(crypto_aegis128_module_init);
 module_exit(crypto_aegis128_module_exit);
 
 MODULE_LICENSE("GPL");
diff --git a/crypto/aegis128l.c b/crypto/aegis128l.c
index 275a8616d71b..9bca3d619a22 100644
--- a/crypto/aegis128l.c
+++ b/crypto/aegis128l.c
@@ -512,7 +512,7 @@ static void __exit crypto_aegis128l_module_exit(void)
 	crypto_unregister_aead(&crypto_aegis128l_alg);
 }
 
-module_init(crypto_aegis128l_module_init);
+subsys_initcall(crypto_aegis128l_module_init);
 module_exit(crypto_aegis128l_module_exit);
 
 MODULE_LICENSE("GPL");
diff --git a/crypto/aegis256.c b/crypto/aegis256.c
index ecd6b7f34a2d..b47fd39595ad 100644
--- a/crypto/aegis256.c
+++ b/crypto/aegis256.c
@@ -463,7 +463,7 @@ static void __exit crypto_aegis256_module_exit(void)
 	crypto_unregister_aead(&crypto_aegis256_alg);
 }
 
-module_init(crypto_aegis256_module_init);
+subsys_initcall(crypto_aegis256_module_init);
 module_exit(crypto_aegis256_module_exit);
 
 MODULE_LICENSE("GPL");
diff --git a/crypto/aes_generic.c b/crypto/aes_generic.c
index 13df33aca463..f217568917e4 100644
--- a/crypto/aes_generic.c
+++ b/crypto/aes_generic.c
@@ -64,7 +64,7 @@ static inline u8 byte(const u32 x, const unsigned n)
 static const u32 rco_tab[10] = { 1, 2, 4, 8, 16, 32, 64, 128, 27, 54 };
 
 /* cacheline-aligned to facilitate prefetching into cache */
-__visible const u32 crypto_ft_tab[4][256] __cacheline_aligned = {
+__visible const u32 crypto_ft_tab[4][256] ____cacheline_aligned = {
 	{
 		0xa56363c6, 0x847c7cf8, 0x997777ee, 0x8d7b7bf6,
 		0x0df2f2ff, 0xbd6b6bd6, 0xb16f6fde, 0x54c5c591,
@@ -328,7 +328,7 @@ __visible const u32 crypto_ft_tab[4][256] __cacheline_aligned = {
 	}
 };
 
-__visible const u32 crypto_fl_tab[4][256] __cacheline_aligned = {
+__visible const u32 crypto_fl_tab[4][256] ____cacheline_aligned = {
 	{
 		0x00000063, 0x0000007c, 0x00000077, 0x0000007b,
 		0x000000f2, 0x0000006b, 0x0000006f, 0x000000c5,
@@ -592,7 +592,7 @@ __visible const u32 crypto_fl_tab[4][256] __cacheline_aligned = {
 	}
 };
 
-__visible const u32 crypto_it_tab[4][256] __cacheline_aligned = {
+__visible const u32 crypto_it_tab[4][256] ____cacheline_aligned = {
 	{
 		0x50a7f451, 0x5365417e, 0xc3a4171a, 0x965e273a,
 		0xcb6bab3b, 0xf1459d1f, 0xab58faac, 0x9303e34b,
@@ -856,7 +856,7 @@ __visible const u32 crypto_it_tab[4][256] __cacheline_aligned = {
 	}
 };
 
-__visible const u32 crypto_il_tab[4][256] __cacheline_aligned = {
+__visible const u32 crypto_il_tab[4][256] ____cacheline_aligned = {
 	{
 		0x00000052, 0x00000009, 0x0000006a, 0x000000d5,
 		0x00000030, 0x00000036, 0x000000a5, 0x00000038,
@@ -1470,7 +1470,7 @@ static void __exit aes_fini(void)
 	crypto_unregister_alg(&aes_alg);
 }
 
-module_init(aes_init);
+subsys_initcall(aes_init);
 module_exit(aes_fini);
 
 MODULE_DESCRIPTION("Rijndael (AES) Cipher Algorithm");
diff --git a/crypto/akcipher.c b/crypto/akcipher.c
index 0cbeae137e0a..780daa436dac 100644
--- a/crypto/akcipher.c
+++ b/crypto/akcipher.c
@@ -119,10 +119,24 @@ static void akcipher_prepare_alg(struct akcipher_alg *alg)
 	base->cra_flags |= CRYPTO_ALG_TYPE_AKCIPHER;
 }
 
+static int akcipher_default_op(struct akcipher_request *req)
+{
+	return -ENOSYS;
+}
+
 int crypto_register_akcipher(struct akcipher_alg *alg)
 {
 	struct crypto_alg *base = &alg->base;
 
+	if (!alg->sign)
+		alg->sign = akcipher_default_op;
+	if (!alg->verify)
+		alg->verify = akcipher_default_op;
+	if (!alg->encrypt)
+		alg->encrypt = akcipher_default_op;
+	if (!alg->decrypt)
+		alg->decrypt = akcipher_default_op;
+
 	akcipher_prepare_alg(alg);
 	return crypto_register_alg(base);
 }
diff --git a/crypto/algboss.c b/crypto/algboss.c
index 527b44d0af21..bb97cfb38836 100644
--- a/crypto/algboss.c
+++ b/crypto/algboss.c
@@ -296,7 +296,13 @@ static void __exit cryptomgr_exit(void)
 	BUG_ON(err);
 }
 
-subsys_initcall(cryptomgr_init);
+/*
+ * This is arch_initcall() so that the crypto self-tests are run on algorithms
+ * registered early by subsys_initcall().  subsys_initcall() is needed for
+ * generic implementations so that they're available for comparison tests when
+ * other implementations are registered later by module_init().
+ */
+arch_initcall(cryptomgr_init);
 module_exit(cryptomgr_exit);
 
 MODULE_LICENSE("GPL");
diff --git a/crypto/ansi_cprng.c b/crypto/ansi_cprng.c
index eff337ce9003..e7c43ea4ce9d 100644
--- a/crypto/ansi_cprng.c
+++ b/crypto/ansi_cprng.c
@@ -472,7 +472,7 @@ MODULE_DESCRIPTION("Software Pseudo Random Number Generator");
 MODULE_AUTHOR("Neil Horman <nhorman@tuxdriver.com>");
 module_param(dbg, int, 0);
 MODULE_PARM_DESC(dbg, "Boolean to enable debugging (0/1 == off/on)");
-module_init(prng_mod_init);
+subsys_initcall(prng_mod_init);
 module_exit(prng_mod_fini);
 MODULE_ALIAS_CRYPTO("stdrng");
 MODULE_ALIAS_CRYPTO("ansi_cprng");
diff --git a/crypto/anubis.c b/crypto/anubis.c
index 4bb187c2a902..673927de0eb9 100644
--- a/crypto/anubis.c
+++ b/crypto/anubis.c
@@ -699,7 +699,7 @@ static void __exit anubis_mod_fini(void)
 	crypto_unregister_alg(&anubis_alg);
 }
 
-module_init(anubis_mod_init);
+subsys_initcall(anubis_mod_init);
 module_exit(anubis_mod_fini);
 
 MODULE_LICENSE("GPL");
diff --git a/crypto/arc4.c b/crypto/arc4.c
index 6c93342e3405..2233d36456e2 100644
--- a/crypto/arc4.c
+++ b/crypto/arc4.c
@@ -163,7 +163,7 @@ static void __exit arc4_exit(void)
 	crypto_unregister_skcipher(&arc4_skcipher);
 }
 
-module_init(arc4_init);
+subsys_initcall(arc4_init);
 module_exit(arc4_exit);
 
 MODULE_LICENSE("GPL");
diff --git a/crypto/asymmetric_keys/asym_tpm.c b/crypto/asymmetric_keys/asym_tpm.c
index 5d4c270463f6..76d2ce3a1b5b 100644
--- a/crypto/asymmetric_keys/asym_tpm.c
+++ b/crypto/asymmetric_keys/asym_tpm.c
@@ -276,6 +276,10 @@ static int tpm_sign(struct tpm_buf *tb,
 
 	return datalen;
 }
+
+/* Room to fit two u32 zeros for algo id and parameters length. */
+#define SETKEY_PARAMS_SIZE (sizeof(u32) * 2)
+
 /*
  * Maximum buffer size for the BER/DER encoded public key.  The public key
  * is of the form SEQUENCE { INTEGER n, INTEGER e } where n is a maximum 2048
@@ -286,8 +290,9 @@ static int tpm_sign(struct tpm_buf *tb,
  *     - 257 bytes of n
  *   - max 2 bytes for INTEGER e type/length
  *     - 3 bytes of e
+ * - 4+4 of zeros for set_pub_key parameters (SETKEY_PARAMS_SIZE)
  */
-#define PUB_KEY_BUF_SIZE (4 + 4 + 257 + 2 + 3)
+#define PUB_KEY_BUF_SIZE (4 + 4 + 257 + 2 + 3 + SETKEY_PARAMS_SIZE)
 
 /*
  * Provide a part of a description of the key for /proc/keys.
@@ -364,6 +369,8 @@ static uint32_t derive_pub_key(const void *pub_key, uint32_t len, uint8_t *buf)
 	cur = encode_tag_length(cur, 0x02, sizeof(e));
 	memcpy(cur, e, sizeof(e));
 	cur += sizeof(e);
+	/* Zero parameters to satisfy set_pub_key ABI. */
+	memset(cur, 0, SETKEY_PARAMS_SIZE);
 
 	return cur - buf;
 }
@@ -744,12 +751,10 @@ static int tpm_key_verify_signature(const struct key *key,
 	struct crypto_wait cwait;
 	struct crypto_akcipher *tfm;
 	struct akcipher_request *req;
-	struct scatterlist sig_sg, digest_sg;
+	struct scatterlist src_sg[2];
 	char alg_name[CRYPTO_MAX_ALG_NAME];
 	uint8_t der_pub_key[PUB_KEY_BUF_SIZE];
 	uint32_t der_pub_key_len;
-	void *output;
-	unsigned int outlen;
 	int ret;
 
 	pr_devel("==>%s()\n", __func__);
@@ -781,37 +786,17 @@ static int tpm_key_verify_signature(const struct key *key,
 	if (!req)
 		goto error_free_tfm;
 
-	ret = -ENOMEM;
-	outlen = crypto_akcipher_maxsize(tfm);
-	output = kmalloc(outlen, GFP_KERNEL);
-	if (!output)
-		goto error_free_req;
-
-	sg_init_one(&sig_sg, sig->s, sig->s_size);
-	sg_init_one(&digest_sg, output, outlen);
-	akcipher_request_set_crypt(req, &sig_sg, &digest_sg, sig->s_size,
-				   outlen);
+	sg_init_table(src_sg, 2);
+	sg_set_buf(&src_sg[0], sig->s, sig->s_size);
+	sg_set_buf(&src_sg[1], sig->digest, sig->digest_size);
+	akcipher_request_set_crypt(req, src_sg, NULL, sig->s_size,
+				   sig->digest_size);
 	crypto_init_wait(&cwait);
 	akcipher_request_set_callback(req, CRYPTO_TFM_REQ_MAY_BACKLOG |
 				      CRYPTO_TFM_REQ_MAY_SLEEP,
 				      crypto_req_done, &cwait);
-
-	/* Perform the verification calculation.  This doesn't actually do the
-	 * verification, but rather calculates the hash expected by the
-	 * signature and returns that to us.
-	 */
 	ret = crypto_wait_req(crypto_akcipher_verify(req), &cwait);
-	if (ret)
-		goto out_free_output;
-
-	/* Do the actual verification step. */
-	if (req->dst_len != sig->digest_size ||
-	    memcmp(sig->digest, output, sig->digest_size) != 0)
-		ret = -EKEYREJECTED;
 
-out_free_output:
-	kfree(output);
-error_free_req:
 	akcipher_request_free(req);
 error_free_tfm:
 	crypto_free_akcipher(tfm);
diff --git a/crypto/asymmetric_keys/pkcs7_verify.c b/crypto/asymmetric_keys/pkcs7_verify.c
index 97c77f66b20d..f7b0980bf02d 100644
--- a/crypto/asymmetric_keys/pkcs7_verify.c
+++ b/crypto/asymmetric_keys/pkcs7_verify.c
@@ -56,7 +56,6 @@ static int pkcs7_digest(struct pkcs7_message *pkcs7,
 		goto error_no_desc;
 
 	desc->tfm   = tfm;
-	desc->flags = CRYPTO_TFM_REQ_MAY_SLEEP;
 
 	/* Digest the message [RFC2315 9.3] */
 	ret = crypto_shash_digest(desc, pkcs7->data, pkcs7->data_len,
diff --git a/crypto/asymmetric_keys/public_key.c b/crypto/asymmetric_keys/public_key.c
index f5d85b47fcc6..77e0ae7840ff 100644
--- a/crypto/asymmetric_keys/public_key.c
+++ b/crypto/asymmetric_keys/public_key.c
@@ -45,6 +45,7 @@ void public_key_free(struct public_key *key)
 {
 	if (key) {
 		kfree(key->key);
+		kfree(key->params);
 		kfree(key);
 	}
 }
@@ -94,6 +95,12 @@ int software_key_determine_akcipher(const char *encoding,
 	return -ENOPKG;
 }
 
+static u8 *pkey_pack_u32(u8 *dst, u32 val)
+{
+	memcpy(dst, &val, sizeof(val));
+	return dst + sizeof(val);
+}
+
 /*
  * Query information about a key.
  */
@@ -103,6 +110,7 @@ static int software_key_query(const struct kernel_pkey_params *params,
 	struct crypto_akcipher *tfm;
 	struct public_key *pkey = params->key->payload.data[asym_crypto];
 	char alg_name[CRYPTO_MAX_ALG_NAME];
+	u8 *key, *ptr;
 	int ret, len;
 
 	ret = software_key_determine_akcipher(params->encoding,
@@ -115,14 +123,22 @@ static int software_key_query(const struct kernel_pkey_params *params,
 	if (IS_ERR(tfm))
 		return PTR_ERR(tfm);
 
+	key = kmalloc(pkey->keylen + sizeof(u32) * 2 + pkey->paramlen,
+		      GFP_KERNEL);
+	if (!key)
+		goto error_free_tfm;
+	memcpy(key, pkey->key, pkey->keylen);
+	ptr = key + pkey->keylen;
+	ptr = pkey_pack_u32(ptr, pkey->algo);
+	ptr = pkey_pack_u32(ptr, pkey->paramlen);
+	memcpy(ptr, pkey->params, pkey->paramlen);
+
 	if (pkey->key_is_private)
-		ret = crypto_akcipher_set_priv_key(tfm,
-						   pkey->key, pkey->keylen);
+		ret = crypto_akcipher_set_priv_key(tfm, key, pkey->keylen);
 	else
-		ret = crypto_akcipher_set_pub_key(tfm,
-						  pkey->key, pkey->keylen);
+		ret = crypto_akcipher_set_pub_key(tfm, key, pkey->keylen);
 	if (ret < 0)
-		goto error_free_tfm;
+		goto error_free_key;
 
 	len = crypto_akcipher_maxsize(tfm);
 	info->key_size = len * 8;
@@ -137,6 +153,8 @@ static int software_key_query(const struct kernel_pkey_params *params,
 					KEYCTL_SUPPORTS_SIGN);
 	ret = 0;
 
+error_free_key:
+	kfree(key);
 error_free_tfm:
 	crypto_free_akcipher(tfm);
 	pr_devel("<==%s() = %d\n", __func__, ret);
@@ -155,6 +173,7 @@ static int software_key_eds_op(struct kernel_pkey_params *params,
 	struct crypto_wait cwait;
 	struct scatterlist in_sg, out_sg;
 	char alg_name[CRYPTO_MAX_ALG_NAME];
+	char *key, *ptr;
 	int ret;
 
 	pr_devel("==>%s()\n", __func__);
@@ -173,14 +192,23 @@ static int software_key_eds_op(struct kernel_pkey_params *params,
 	if (!req)
 		goto error_free_tfm;
 
+	key = kmalloc(pkey->keylen + sizeof(u32) * 2 + pkey->paramlen,
+		      GFP_KERNEL);
+	if (!key)
+		goto error_free_req;
+
+	memcpy(key, pkey->key, pkey->keylen);
+	ptr = key + pkey->keylen;
+	ptr = pkey_pack_u32(ptr, pkey->algo);
+	ptr = pkey_pack_u32(ptr, pkey->paramlen);
+	memcpy(ptr, pkey->params, pkey->paramlen);
+
 	if (pkey->key_is_private)
-		ret = crypto_akcipher_set_priv_key(tfm,
-						   pkey->key, pkey->keylen);
+		ret = crypto_akcipher_set_priv_key(tfm, key, pkey->keylen);
 	else
-		ret = crypto_akcipher_set_pub_key(tfm,
-						  pkey->key, pkey->keylen);
+		ret = crypto_akcipher_set_pub_key(tfm, key, pkey->keylen);
 	if (ret)
-		goto error_free_req;
+		goto error_free_key;
 
 	sg_init_one(&in_sg, in, params->in_len);
 	sg_init_one(&out_sg, out, params->out_len);
@@ -210,6 +238,8 @@ static int software_key_eds_op(struct kernel_pkey_params *params,
 	if (ret == 0)
 		ret = req->dst_len;
 
+error_free_key:
+	kfree(key);
 error_free_req:
 	akcipher_request_free(req);
 error_free_tfm:
@@ -227,10 +257,9 @@ int public_key_verify_signature(const struct public_key *pkey,
 	struct crypto_wait cwait;
 	struct crypto_akcipher *tfm;
 	struct akcipher_request *req;
-	struct scatterlist sig_sg, digest_sg;
+	struct scatterlist src_sg[2];
 	char alg_name[CRYPTO_MAX_ALG_NAME];
-	void *output;
-	unsigned int outlen;
+	char *key, *ptr;
 	int ret;
 
 	pr_devel("==>%s()\n", __func__);
@@ -254,45 +283,37 @@ int public_key_verify_signature(const struct public_key *pkey,
 	if (!req)
 		goto error_free_tfm;
 
+	key = kmalloc(pkey->keylen + sizeof(u32) * 2 + pkey->paramlen,
+		      GFP_KERNEL);
+	if (!key)
+		goto error_free_req;
+
+	memcpy(key, pkey->key, pkey->keylen);
+	ptr = key + pkey->keylen;
+	ptr = pkey_pack_u32(ptr, pkey->algo);
+	ptr = pkey_pack_u32(ptr, pkey->paramlen);
+	memcpy(ptr, pkey->params, pkey->paramlen);
+
 	if (pkey->key_is_private)
-		ret = crypto_akcipher_set_priv_key(tfm,
-						   pkey->key, pkey->keylen);
+		ret = crypto_akcipher_set_priv_key(tfm, key, pkey->keylen);
 	else
-		ret = crypto_akcipher_set_pub_key(tfm,
-						  pkey->key, pkey->keylen);
+		ret = crypto_akcipher_set_pub_key(tfm, key, pkey->keylen);
 	if (ret)
-		goto error_free_req;
-
-	ret = -ENOMEM;
-	outlen = crypto_akcipher_maxsize(tfm);
-	output = kmalloc(outlen, GFP_KERNEL);
-	if (!output)
-		goto error_free_req;
+		goto error_free_key;
 
-	sg_init_one(&sig_sg, sig->s, sig->s_size);
-	sg_init_one(&digest_sg, output, outlen);
-	akcipher_request_set_crypt(req, &sig_sg, &digest_sg, sig->s_size,
-				   outlen);
+	sg_init_table(src_sg, 2);
+	sg_set_buf(&src_sg[0], sig->s, sig->s_size);
+	sg_set_buf(&src_sg[1], sig->digest, sig->digest_size);
+	akcipher_request_set_crypt(req, src_sg, NULL, sig->s_size,
+				   sig->digest_size);
 	crypto_init_wait(&cwait);
 	akcipher_request_set_callback(req, CRYPTO_TFM_REQ_MAY_BACKLOG |
 				      CRYPTO_TFM_REQ_MAY_SLEEP,
 				      crypto_req_done, &cwait);
-
-	/* Perform the verification calculation.  This doesn't actually do the
-	 * verification, but rather calculates the hash expected by the
-	 * signature and returns that to us.
-	 */
 	ret = crypto_wait_req(crypto_akcipher_verify(req), &cwait);
-	if (ret)
-		goto out_free_output;
-
-	/* Do the actual verification step. */
-	if (req->dst_len != sig->digest_size ||
-	    memcmp(sig->digest, output, sig->digest_size) != 0)
-		ret = -EKEYREJECTED;
 
-out_free_output:
-	kfree(output);
+error_free_key:
+	kfree(key);
 error_free_req:
 	akcipher_request_free(req);
 error_free_tfm:
diff --git a/crypto/asymmetric_keys/verify_pefile.c b/crypto/asymmetric_keys/verify_pefile.c
index d178650fd524..f8e4a932bcfb 100644
--- a/crypto/asymmetric_keys/verify_pefile.c
+++ b/crypto/asymmetric_keys/verify_pefile.c
@@ -354,7 +354,6 @@ static int pefile_digest_pe(const void *pebuf, unsigned int pelen,
 		goto error_no_desc;
 
 	desc->tfm   = tfm;
-	desc->flags = CRYPTO_TFM_REQ_MAY_SLEEP;
 	ret = crypto_shash_init(desc);
 	if (ret < 0)
 		goto error;
diff --git a/crypto/asymmetric_keys/x509.asn1 b/crypto/asymmetric_keys/x509.asn1
index aae0cde414e2..5c9f4e4a5231 100644
--- a/crypto/asymmetric_keys/x509.asn1
+++ b/crypto/asymmetric_keys/x509.asn1
@@ -22,7 +22,7 @@ CertificateSerialNumber ::= INTEGER
 
 AlgorithmIdentifier ::= SEQUENCE {
 	algorithm		OBJECT IDENTIFIER ({ x509_note_OID }),
-	parameters		ANY OPTIONAL
+	parameters		ANY OPTIONAL ({ x509_note_params })
 }
 
 Name ::= SEQUENCE OF RelativeDistinguishedName
diff --git a/crypto/asymmetric_keys/x509_cert_parser.c b/crypto/asymmetric_keys/x509_cert_parser.c
index 991f4d735a4e..5b7bfd95c334 100644
--- a/crypto/asymmetric_keys/x509_cert_parser.c
+++ b/crypto/asymmetric_keys/x509_cert_parser.c
@@ -26,6 +26,9 @@ struct x509_parse_context {
 	const void	*cert_start;		/* Start of cert content */
 	const void	*key;			/* Key data */
 	size_t		key_size;		/* Size of key data */
+	const void	*params;		/* Key parameters */
+	size_t		params_size;		/* Size of key parameters */
+	enum OID	key_algo;		/* Public key algorithm */
 	enum OID	last_oid;		/* Last OID encountered */
 	enum OID	algo_oid;		/* Algorithm OID */
 	unsigned char	nr_mpi;			/* Number of MPIs stored */
@@ -109,6 +112,13 @@ struct x509_certificate *x509_cert_parse(const void *data, size_t datalen)
 
 	cert->pub->keylen = ctx->key_size;
 
+	cert->pub->params = kmemdup(ctx->params, ctx->params_size, GFP_KERNEL);
+	if (!cert->pub->params)
+		goto error_decode;
+
+	cert->pub->paramlen = ctx->params_size;
+	cert->pub->algo = ctx->key_algo;
+
 	/* Grab the signature bits */
 	ret = x509_get_sig_params(cert);
 	if (ret < 0)
@@ -220,6 +230,14 @@ int x509_note_pkey_algo(void *context, size_t hdrlen,
 	case OID_sha224WithRSAEncryption:
 		ctx->cert->sig->hash_algo = "sha224";
 		goto rsa_pkcs1;
+
+	case OID_gost2012Signature256:
+		ctx->cert->sig->hash_algo = "streebog256";
+		goto ecrdsa;
+
+	case OID_gost2012Signature512:
+		ctx->cert->sig->hash_algo = "streebog512";
+		goto ecrdsa;
 	}
 
 rsa_pkcs1:
@@ -227,6 +245,11 @@ rsa_pkcs1:
 	ctx->cert->sig->encoding = "pkcs1";
 	ctx->algo_oid = ctx->last_oid;
 	return 0;
+ecrdsa:
+	ctx->cert->sig->pkey_algo = "ecrdsa";
+	ctx->cert->sig->encoding = "raw";
+	ctx->algo_oid = ctx->last_oid;
+	return 0;
 }
 
 /*
@@ -246,7 +269,8 @@ int x509_note_signature(void *context, size_t hdrlen,
 		return -EINVAL;
 	}
 
-	if (strcmp(ctx->cert->sig->pkey_algo, "rsa") == 0) {
+	if (strcmp(ctx->cert->sig->pkey_algo, "rsa") == 0 ||
+	    strcmp(ctx->cert->sig->pkey_algo, "ecrdsa") == 0) {
 		/* Discard the BIT STRING metadata */
 		if (vlen < 1 || *(const u8 *)value != 0)
 			return -EBADMSG;
@@ -401,6 +425,27 @@ int x509_note_subject(void *context, size_t hdrlen,
 }
 
 /*
+ * Extract the parameters for the public key
+ */
+int x509_note_params(void *context, size_t hdrlen,
+		     unsigned char tag,
+		     const void *value, size_t vlen)
+{
+	struct x509_parse_context *ctx = context;
+
+	/*
+	 * AlgorithmIdentifier is used three times in the x509, we should skip
+	 * first and ignore third, using second one which is after subject and
+	 * before subjectPublicKey.
+	 */
+	if (!ctx->cert->raw_subject || ctx->key)
+		return 0;
+	ctx->params = value - hdrlen;
+	ctx->params_size = vlen + hdrlen;
+	return 0;
+}
+
+/*
  * Extract the data for the public key algorithm
  */
 int x509_extract_key_data(void *context, size_t hdrlen,
@@ -409,11 +454,15 @@ int x509_extract_key_data(void *context, size_t hdrlen,
 {
 	struct x509_parse_context *ctx = context;
 
-	if (ctx->last_oid != OID_rsaEncryption)
+	ctx->key_algo = ctx->last_oid;
+	if (ctx->last_oid == OID_rsaEncryption)
+		ctx->cert->pub->pkey_algo = "rsa";
+	else if (ctx->last_oid == OID_gost2012PKey256 ||
+		 ctx->last_oid == OID_gost2012PKey512)
+		ctx->cert->pub->pkey_algo = "ecrdsa";
+	else
 		return -ENOPKG;
 
-	ctx->cert->pub->pkey_algo = "rsa";
-
 	/* Discard the BIT STRING metadata */
 	if (vlen < 1 || *(const u8 *)value != 0)
 		return -EBADMSG;
diff --git a/crypto/asymmetric_keys/x509_public_key.c b/crypto/asymmetric_keys/x509_public_key.c
index 9338b4558cdc..bd96683d8cde 100644
--- a/crypto/asymmetric_keys/x509_public_key.c
+++ b/crypto/asymmetric_keys/x509_public_key.c
@@ -77,7 +77,6 @@ int x509_get_sig_params(struct x509_certificate *cert)
 		goto error;
 
 	desc->tfm = tfm;
-	desc->flags = CRYPTO_TFM_REQ_MAY_SLEEP;
 
 	ret = crypto_shash_digest(desc, cert->tbs, cert->tbs_size, sig->digest);
 	if (ret < 0)
diff --git a/crypto/authenc.c b/crypto/authenc.c
index 4be293a4b5f0..b3eddac7fa3a 100644
--- a/crypto/authenc.c
+++ b/crypto/authenc.c
@@ -508,7 +508,7 @@ static void __exit crypto_authenc_module_exit(void)
 	crypto_unregister_template(&crypto_authenc_tmpl);
 }
 
-module_init(crypto_authenc_module_init);
+subsys_initcall(crypto_authenc_module_init);
 module_exit(crypto_authenc_module_exit);
 
 MODULE_LICENSE("GPL");
diff --git a/crypto/authencesn.c b/crypto/authencesn.c
index 4741fe89ba2c..58074308e535 100644
--- a/crypto/authencesn.c
+++ b/crypto/authencesn.c
@@ -523,7 +523,7 @@ static void __exit crypto_authenc_esn_module_exit(void)
 	crypto_unregister_template(&crypto_authenc_esn_tmpl);
 }
 
-module_init(crypto_authenc_esn_module_init);
+subsys_initcall(crypto_authenc_esn_module_init);
 module_exit(crypto_authenc_esn_module_exit);
 
 MODULE_LICENSE("GPL");
diff --git a/crypto/blowfish_generic.c b/crypto/blowfish_generic.c
index 87b392a77a93..8548ced8b074 100644
--- a/crypto/blowfish_generic.c
+++ b/crypto/blowfish_generic.c
@@ -133,7 +133,7 @@ static void __exit blowfish_mod_fini(void)
 	crypto_unregister_alg(&alg);
 }
 
-module_init(blowfish_mod_init);
+subsys_initcall(blowfish_mod_init);
 module_exit(blowfish_mod_fini);
 
 MODULE_LICENSE("GPL");
diff --git a/crypto/camellia_generic.c b/crypto/camellia_generic.c
index 32ddd4836ff5..15ce1281f5d9 100644
--- a/crypto/camellia_generic.c
+++ b/crypto/camellia_generic.c
@@ -1092,7 +1092,7 @@ static void __exit camellia_fini(void)
 	crypto_unregister_alg(&camellia_alg);
 }
 
-module_init(camellia_init);
+subsys_initcall(camellia_init);
 module_exit(camellia_fini);
 
 MODULE_DESCRIPTION("Camellia Cipher Algorithm");
diff --git a/crypto/cast5_generic.c b/crypto/cast5_generic.c
index 66169c178314..24bc7d4e33be 100644
--- a/crypto/cast5_generic.c
+++ b/crypto/cast5_generic.c
@@ -543,7 +543,7 @@ static void __exit cast5_mod_fini(void)
 	crypto_unregister_alg(&alg);
 }
 
-module_init(cast5_mod_init);
+subsys_initcall(cast5_mod_init);
 module_exit(cast5_mod_fini);
 
 MODULE_LICENSE("GPL");
diff --git a/crypto/cast6_generic.c b/crypto/cast6_generic.c
index c8e5ec69790e..edd59cc34991 100644
--- a/crypto/cast6_generic.c
+++ b/crypto/cast6_generic.c
@@ -285,7 +285,7 @@ static void __exit cast6_mod_fini(void)
 	crypto_unregister_alg(&alg);
 }
 
-module_init(cast6_mod_init);
+subsys_initcall(cast6_mod_init);
 module_exit(cast6_mod_fini);
 
 MODULE_LICENSE("GPL");
diff --git a/crypto/cbc.c b/crypto/cbc.c
index d12efaac9230..129f79d03365 100644
--- a/crypto/cbc.c
+++ b/crypto/cbc.c
@@ -98,7 +98,7 @@ static void __exit crypto_cbc_module_exit(void)
 	crypto_unregister_template(&crypto_cbc_tmpl);
 }
 
-module_init(crypto_cbc_module_init);
+subsys_initcall(crypto_cbc_module_init);
 module_exit(crypto_cbc_module_exit);
 
 MODULE_LICENSE("GPL");
diff --git a/crypto/ccm.c b/crypto/ccm.c
index 50df8f001c1c..c1ef9d0b4271 100644
--- a/crypto/ccm.c
+++ b/crypto/ccm.c
@@ -458,7 +458,6 @@ static void crypto_ccm_free(struct aead_instance *inst)
 
 static int crypto_ccm_create_common(struct crypto_template *tmpl,
 				    struct rtattr **tb,
-				    const char *full_name,
 				    const char *ctr_name,
 				    const char *mac_name)
 {
@@ -486,7 +485,8 @@ static int crypto_ccm_create_common(struct crypto_template *tmpl,
 
 	mac = __crypto_hash_alg_common(mac_alg);
 	err = -EINVAL;
-	if (mac->digestsize != 16)
+	if (strncmp(mac->base.cra_name, "cbcmac(", 7) != 0 ||
+	    mac->digestsize != 16)
 		goto out_put_mac;
 
 	inst = kzalloc(sizeof(*inst) + sizeof(*ictx), GFP_KERNEL);
@@ -509,23 +509,27 @@ static int crypto_ccm_create_common(struct crypto_template *tmpl,
 
 	ctr = crypto_spawn_skcipher_alg(&ictx->ctr);
 
-	/* Not a stream cipher? */
+	/* The skcipher algorithm must be CTR mode, using 16-byte blocks. */
 	err = -EINVAL;
-	if (ctr->base.cra_blocksize != 1)
+	if (strncmp(ctr->base.cra_name, "ctr(", 4) != 0 ||
+	    crypto_skcipher_alg_ivsize(ctr) != 16 ||
+	    ctr->base.cra_blocksize != 1)
 		goto err_drop_ctr;
 
-	/* We want the real thing! */
-	if (crypto_skcipher_alg_ivsize(ctr) != 16)
+	/* ctr and cbcmac must use the same underlying block cipher. */
+	if (strcmp(ctr->base.cra_name + 4, mac->base.cra_name + 7) != 0)
 		goto err_drop_ctr;
 
 	err = -ENAMETOOLONG;
+	if (snprintf(inst->alg.base.cra_name, CRYPTO_MAX_ALG_NAME,
+		     "ccm(%s", ctr->base.cra_name + 4) >= CRYPTO_MAX_ALG_NAME)
+		goto err_drop_ctr;
+
 	if (snprintf(inst->alg.base.cra_driver_name, CRYPTO_MAX_ALG_NAME,
 		     "ccm_base(%s,%s)", ctr->base.cra_driver_name,
 		     mac->base.cra_driver_name) >= CRYPTO_MAX_ALG_NAME)
 		goto err_drop_ctr;
 
-	memcpy(inst->alg.base.cra_name, full_name, CRYPTO_MAX_ALG_NAME);
-
 	inst->alg.base.cra_flags = ctr->base.cra_flags & CRYPTO_ALG_ASYNC;
 	inst->alg.base.cra_priority = (mac->base.cra_priority +
 				       ctr->base.cra_priority) / 2;
@@ -567,7 +571,6 @@ static int crypto_ccm_create(struct crypto_template *tmpl, struct rtattr **tb)
 	const char *cipher_name;
 	char ctr_name[CRYPTO_MAX_ALG_NAME];
 	char mac_name[CRYPTO_MAX_ALG_NAME];
-	char full_name[CRYPTO_MAX_ALG_NAME];
 
 	cipher_name = crypto_attr_alg_name(tb[1]);
 	if (IS_ERR(cipher_name))
@@ -581,35 +584,24 @@ static int crypto_ccm_create(struct crypto_template *tmpl, struct rtattr **tb)
 		     cipher_name) >= CRYPTO_MAX_ALG_NAME)
 		return -ENAMETOOLONG;
 
-	if (snprintf(full_name, CRYPTO_MAX_ALG_NAME, "ccm(%s)", cipher_name) >=
-	    CRYPTO_MAX_ALG_NAME)
-		return -ENAMETOOLONG;
-
-	return crypto_ccm_create_common(tmpl, tb, full_name, ctr_name,
-					mac_name);
+	return crypto_ccm_create_common(tmpl, tb, ctr_name, mac_name);
 }
 
 static int crypto_ccm_base_create(struct crypto_template *tmpl,
 				  struct rtattr **tb)
 {
 	const char *ctr_name;
-	const char *cipher_name;
-	char full_name[CRYPTO_MAX_ALG_NAME];
+	const char *mac_name;
 
 	ctr_name = crypto_attr_alg_name(tb[1]);
 	if (IS_ERR(ctr_name))
 		return PTR_ERR(ctr_name);
 
-	cipher_name = crypto_attr_alg_name(tb[2]);
-	if (IS_ERR(cipher_name))
-		return PTR_ERR(cipher_name);
-
-	if (snprintf(full_name, CRYPTO_MAX_ALG_NAME, "ccm_base(%s,%s)",
-		     ctr_name, cipher_name) >= CRYPTO_MAX_ALG_NAME)
-		return -ENAMETOOLONG;
+	mac_name = crypto_attr_alg_name(tb[2]);
+	if (IS_ERR(mac_name))
+		return PTR_ERR(mac_name);
 
-	return crypto_ccm_create_common(tmpl, tb, full_name, ctr_name,
-					cipher_name);
+	return crypto_ccm_create_common(tmpl, tb, ctr_name, mac_name);
 }
 
 static int crypto_rfc4309_setkey(struct crypto_aead *parent, const u8 *key,
@@ -1014,7 +1006,7 @@ static void __exit crypto_ccm_module_exit(void)
 				    ARRAY_SIZE(crypto_ccm_tmpls));
 }
 
-module_init(crypto_ccm_module_init);
+subsys_initcall(crypto_ccm_module_init);
 module_exit(crypto_ccm_module_exit);
 
 MODULE_LICENSE("GPL");
diff --git a/crypto/cfb.c b/crypto/cfb.c
index 03ac847f6d6a..7b68fbb61732 100644
--- a/crypto/cfb.c
+++ b/crypto/cfb.c
@@ -243,7 +243,7 @@ static void __exit crypto_cfb_module_exit(void)
 	crypto_unregister_template(&crypto_cfb_tmpl);
 }
 
-module_init(crypto_cfb_module_init);
+subsys_initcall(crypto_cfb_module_init);
 module_exit(crypto_cfb_module_exit);
 
 MODULE_LICENSE("GPL");
diff --git a/crypto/chacha20poly1305.c b/crypto/chacha20poly1305.c
index ed2e12e26dd8..e38a2d61819a 100644
--- a/crypto/chacha20poly1305.c
+++ b/crypto/chacha20poly1305.c
@@ -645,8 +645,8 @@ static int chachapoly_create(struct crypto_template *tmpl, struct rtattr **tb,
 
 	err = -ENAMETOOLONG;
 	if (snprintf(inst->alg.base.cra_name, CRYPTO_MAX_ALG_NAME,
-		     "%s(%s,%s)", name, chacha_name,
-		     poly_name) >= CRYPTO_MAX_ALG_NAME)
+		     "%s(%s,%s)", name, chacha->base.cra_name,
+		     poly->cra_name) >= CRYPTO_MAX_ALG_NAME)
 		goto out_drop_chacha;
 	if (snprintf(inst->alg.base.cra_driver_name, CRYPTO_MAX_ALG_NAME,
 		     "%s(%s,%s)", name, chacha->base.cra_driver_name,
@@ -725,7 +725,7 @@ static void __exit chacha20poly1305_module_exit(void)
 				    ARRAY_SIZE(rfc7539_tmpls));
 }
 
-module_init(chacha20poly1305_module_init);
+subsys_initcall(chacha20poly1305_module_init);
 module_exit(chacha20poly1305_module_exit);
 
 MODULE_LICENSE("GPL");
diff --git a/crypto/chacha_generic.c b/crypto/chacha_generic.c
index 35b583101f4f..d2ec04997832 100644
--- a/crypto/chacha_generic.c
+++ b/crypto/chacha_generic.c
@@ -22,18 +22,16 @@ static void chacha_docrypt(u32 *state, u8 *dst, const u8 *src,
 	/* aligned to potentially speed up crypto_xor() */
 	u8 stream[CHACHA_BLOCK_SIZE] __aligned(sizeof(long));
 
-	if (dst != src)
-		memcpy(dst, src, bytes);
-
 	while (bytes >= CHACHA_BLOCK_SIZE) {
 		chacha_block(state, stream, nrounds);
-		crypto_xor(dst, stream, CHACHA_BLOCK_SIZE);
+		crypto_xor_cpy(dst, src, stream, CHACHA_BLOCK_SIZE);
 		bytes -= CHACHA_BLOCK_SIZE;
 		dst += CHACHA_BLOCK_SIZE;
+		src += CHACHA_BLOCK_SIZE;
 	}
 	if (bytes) {
 		chacha_block(state, stream, nrounds);
-		crypto_xor(dst, stream, bytes);
+		crypto_xor_cpy(dst, src, stream, bytes);
 	}
 }
 
@@ -52,7 +50,7 @@ static int chacha_stream_xor(struct skcipher_request *req,
 		unsigned int nbytes = walk.nbytes;
 
 		if (nbytes < walk.total)
-			nbytes = round_down(nbytes, walk.stride);
+			nbytes = round_down(nbytes, CHACHA_BLOCK_SIZE);
 
 		chacha_docrypt(state, walk.dst.virt.addr, walk.src.virt.addr,
 			       nbytes, ctx->nrounds);
@@ -203,7 +201,7 @@ static void __exit chacha_generic_mod_fini(void)
 	crypto_unregister_skciphers(algs, ARRAY_SIZE(algs));
 }
 
-module_init(chacha_generic_mod_init);
+subsys_initcall(chacha_generic_mod_init);
 module_exit(chacha_generic_mod_fini);
 
 MODULE_LICENSE("GPL");
diff --git a/crypto/cmac.c b/crypto/cmac.c
index 16301f52858c..c60b6c011ec6 100644
--- a/crypto/cmac.c
+++ b/crypto/cmac.c
@@ -313,7 +313,7 @@ static void __exit crypto_cmac_module_exit(void)
 	crypto_unregister_template(&crypto_cmac_tmpl);
 }
 
-module_init(crypto_cmac_module_init);
+subsys_initcall(crypto_cmac_module_init);
 module_exit(crypto_cmac_module_exit);
 
 MODULE_LICENSE("GPL");
diff --git a/crypto/crc32_generic.c b/crypto/crc32_generic.c
index 00facd27bcc2..9e97912280bd 100644
--- a/crypto/crc32_generic.c
+++ b/crypto/crc32_generic.c
@@ -146,7 +146,7 @@ static void __exit crc32_mod_fini(void)
 	crypto_unregister_shash(&alg);
 }
 
-module_init(crc32_mod_init);
+subsys_initcall(crc32_mod_init);
 module_exit(crc32_mod_fini);
 
 MODULE_AUTHOR("Alexander Boyko <alexander_boyko@xyratex.com>");
diff --git a/crypto/crc32c_generic.c b/crypto/crc32c_generic.c
index 7283066ecc98..ad26f15d4c7b 100644
--- a/crypto/crc32c_generic.c
+++ b/crypto/crc32c_generic.c
@@ -165,7 +165,7 @@ static void __exit crc32c_mod_fini(void)
 	crypto_unregister_shash(&alg);
 }
 
-module_init(crc32c_mod_init);
+subsys_initcall(crc32c_mod_init);
 module_exit(crc32c_mod_fini);
 
 MODULE_AUTHOR("Clay Haapala <chaapala@cisco.com>");
diff --git a/crypto/crct10dif_generic.c b/crypto/crct10dif_generic.c
index 8e94e29dc6fc..d90c0070710e 100644
--- a/crypto/crct10dif_generic.c
+++ b/crypto/crct10dif_generic.c
@@ -65,10 +65,9 @@ static int chksum_final(struct shash_desc *desc, u8 *out)
 	return 0;
 }
 
-static int __chksum_finup(__u16 *crcp, const u8 *data, unsigned int len,
-			u8 *out)
+static int __chksum_finup(__u16 crc, const u8 *data, unsigned int len, u8 *out)
 {
-	*(__u16 *)out = crc_t10dif_generic(*crcp, data, len);
+	*(__u16 *)out = crc_t10dif_generic(crc, data, len);
 	return 0;
 }
 
@@ -77,15 +76,13 @@ static int chksum_finup(struct shash_desc *desc, const u8 *data,
 {
 	struct chksum_desc_ctx *ctx = shash_desc_ctx(desc);
 
-	return __chksum_finup(&ctx->crc, data, len, out);
+	return __chksum_finup(ctx->crc, data, len, out);
 }
 
 static int chksum_digest(struct shash_desc *desc, const u8 *data,
 			 unsigned int length, u8 *out)
 {
-	struct chksum_desc_ctx *ctx = shash_desc_ctx(desc);
-
-	return __chksum_finup(&ctx->crc, data, length, out);
+	return __chksum_finup(0, data, length, out);
 }
 
 static struct shash_alg alg = {
@@ -115,7 +112,7 @@ static void __exit crct10dif_mod_fini(void)
 	crypto_unregister_shash(&alg);
 }
 
-module_init(crct10dif_mod_init);
+subsys_initcall(crct10dif_mod_init);
 module_exit(crct10dif_mod_fini);
 
 MODULE_AUTHOR("Tim Chen <tim.c.chen@linux.intel.com>");
diff --git a/crypto/cryptd.c b/crypto/cryptd.c
index 5640e5db7bdb..b3bb99390ae7 100644
--- a/crypto/cryptd.c
+++ b/crypto/cryptd.c
@@ -65,15 +65,6 @@ struct aead_instance_ctx {
 	struct cryptd_queue *queue;
 };
 
-struct cryptd_blkcipher_ctx {
-	atomic_t refcnt;
-	struct crypto_blkcipher *child;
-};
-
-struct cryptd_blkcipher_request_ctx {
-	crypto_completion_t complete;
-};
-
 struct cryptd_skcipher_ctx {
 	atomic_t refcnt;
 	struct crypto_sync_skcipher *child;
@@ -216,129 +207,6 @@ static inline void cryptd_check_internal(struct rtattr **tb, u32 *type,
 	*mask |= algt->mask & CRYPTO_ALG_INTERNAL;
 }
 
-static int cryptd_blkcipher_setkey(struct crypto_ablkcipher *parent,
-				   const u8 *key, unsigned int keylen)
-{
-	struct cryptd_blkcipher_ctx *ctx = crypto_ablkcipher_ctx(parent);
-	struct crypto_blkcipher *child = ctx->child;
-	int err;
-
-	crypto_blkcipher_clear_flags(child, CRYPTO_TFM_REQ_MASK);
-	crypto_blkcipher_set_flags(child, crypto_ablkcipher_get_flags(parent) &
-					  CRYPTO_TFM_REQ_MASK);
-	err = crypto_blkcipher_setkey(child, key, keylen);
-	crypto_ablkcipher_set_flags(parent, crypto_blkcipher_get_flags(child) &
-					    CRYPTO_TFM_RES_MASK);
-	return err;
-}
-
-static void cryptd_blkcipher_crypt(struct ablkcipher_request *req,
-				   struct crypto_blkcipher *child,
-				   int err,
-				   int (*crypt)(struct blkcipher_desc *desc,
-						struct scatterlist *dst,
-						struct scatterlist *src,
-						unsigned int len))
-{
-	struct cryptd_blkcipher_request_ctx *rctx;
-	struct cryptd_blkcipher_ctx *ctx;
-	struct crypto_ablkcipher *tfm;
-	struct blkcipher_desc desc;
-	int refcnt;
-
-	rctx = ablkcipher_request_ctx(req);
-
-	if (unlikely(err == -EINPROGRESS))
-		goto out;
-
-	desc.tfm = child;
-	desc.info = req->info;
-	desc.flags = CRYPTO_TFM_REQ_MAY_SLEEP;
-
-	err = crypt(&desc, req->dst, req->src, req->nbytes);
-
-	req->base.complete = rctx->complete;
-
-out:
-	tfm = crypto_ablkcipher_reqtfm(req);
-	ctx = crypto_ablkcipher_ctx(tfm);
-	refcnt = atomic_read(&ctx->refcnt);
-
-	local_bh_disable();
-	rctx->complete(&req->base, err);
-	local_bh_enable();
-
-	if (err != -EINPROGRESS && refcnt && atomic_dec_and_test(&ctx->refcnt))
-		crypto_free_ablkcipher(tfm);
-}
-
-static void cryptd_blkcipher_encrypt(struct crypto_async_request *req, int err)
-{
-	struct cryptd_blkcipher_ctx *ctx = crypto_tfm_ctx(req->tfm);
-	struct crypto_blkcipher *child = ctx->child;
-
-	cryptd_blkcipher_crypt(ablkcipher_request_cast(req), child, err,
-			       crypto_blkcipher_crt(child)->encrypt);
-}
-
-static void cryptd_blkcipher_decrypt(struct crypto_async_request *req, int err)
-{
-	struct cryptd_blkcipher_ctx *ctx = crypto_tfm_ctx(req->tfm);
-	struct crypto_blkcipher *child = ctx->child;
-
-	cryptd_blkcipher_crypt(ablkcipher_request_cast(req), child, err,
-			       crypto_blkcipher_crt(child)->decrypt);
-}
-
-static int cryptd_blkcipher_enqueue(struct ablkcipher_request *req,
-				    crypto_completion_t compl)
-{
-	struct cryptd_blkcipher_request_ctx *rctx = ablkcipher_request_ctx(req);
-	struct crypto_ablkcipher *tfm = crypto_ablkcipher_reqtfm(req);
-	struct cryptd_queue *queue;
-
-	queue = cryptd_get_queue(crypto_ablkcipher_tfm(tfm));
-	rctx->complete = req->base.complete;
-	req->base.complete = compl;
-
-	return cryptd_enqueue_request(queue, &req->base);
-}
-
-static int cryptd_blkcipher_encrypt_enqueue(struct ablkcipher_request *req)
-{
-	return cryptd_blkcipher_enqueue(req, cryptd_blkcipher_encrypt);
-}
-
-static int cryptd_blkcipher_decrypt_enqueue(struct ablkcipher_request *req)
-{
-	return cryptd_blkcipher_enqueue(req, cryptd_blkcipher_decrypt);
-}
-
-static int cryptd_blkcipher_init_tfm(struct crypto_tfm *tfm)
-{
-	struct crypto_instance *inst = crypto_tfm_alg_instance(tfm);
-	struct cryptd_instance_ctx *ictx = crypto_instance_ctx(inst);
-	struct crypto_spawn *spawn = &ictx->spawn;
-	struct cryptd_blkcipher_ctx *ctx = crypto_tfm_ctx(tfm);
-	struct crypto_blkcipher *cipher;
-
-	cipher = crypto_spawn_blkcipher(spawn);
-	if (IS_ERR(cipher))
-		return PTR_ERR(cipher);
-
-	ctx->child = cipher;
-	tfm->crt_ablkcipher.reqsize =
-		sizeof(struct cryptd_blkcipher_request_ctx);
-	return 0;
-}
-
-static void cryptd_blkcipher_exit_tfm(struct crypto_tfm *tfm)
-{
-	struct cryptd_blkcipher_ctx *ctx = crypto_tfm_ctx(tfm);
-
-	crypto_free_blkcipher(ctx->child);
-}
-
 static int cryptd_init_instance(struct crypto_instance *inst,
 				struct crypto_alg *alg)
 {
@@ -382,67 +250,6 @@ out_free_inst:
 	goto out;
 }
 
-static int cryptd_create_blkcipher(struct crypto_template *tmpl,
-				   struct rtattr **tb,
-				   struct cryptd_queue *queue)
-{
-	struct cryptd_instance_ctx *ctx;
-	struct crypto_instance *inst;
-	struct crypto_alg *alg;
-	u32 type = CRYPTO_ALG_TYPE_BLKCIPHER;
-	u32 mask = CRYPTO_ALG_TYPE_MASK;
-	int err;
-
-	cryptd_check_internal(tb, &type, &mask);
-
-	alg = crypto_get_attr_alg(tb, type, mask);
-	if (IS_ERR(alg))
-		return PTR_ERR(alg);
-
-	inst = cryptd_alloc_instance(alg, 0, sizeof(*ctx));
-	err = PTR_ERR(inst);
-	if (IS_ERR(inst))
-		goto out_put_alg;
-
-	ctx = crypto_instance_ctx(inst);
-	ctx->queue = queue;
-
-	err = crypto_init_spawn(&ctx->spawn, alg, inst,
-				CRYPTO_ALG_TYPE_MASK | CRYPTO_ALG_ASYNC);
-	if (err)
-		goto out_free_inst;
-
-	type = CRYPTO_ALG_TYPE_ABLKCIPHER | CRYPTO_ALG_ASYNC;
-	if (alg->cra_flags & CRYPTO_ALG_INTERNAL)
-		type |= CRYPTO_ALG_INTERNAL;
-	inst->alg.cra_flags = type;
-	inst->alg.cra_type = &crypto_ablkcipher_type;
-
-	inst->alg.cra_ablkcipher.ivsize = alg->cra_blkcipher.ivsize;
-	inst->alg.cra_ablkcipher.min_keysize = alg->cra_blkcipher.min_keysize;
-	inst->alg.cra_ablkcipher.max_keysize = alg->cra_blkcipher.max_keysize;
-
-	inst->alg.cra_ctxsize = sizeof(struct cryptd_blkcipher_ctx);
-
-	inst->alg.cra_init = cryptd_blkcipher_init_tfm;
-	inst->alg.cra_exit = cryptd_blkcipher_exit_tfm;
-
-	inst->alg.cra_ablkcipher.setkey = cryptd_blkcipher_setkey;
-	inst->alg.cra_ablkcipher.encrypt = cryptd_blkcipher_encrypt_enqueue;
-	inst->alg.cra_ablkcipher.decrypt = cryptd_blkcipher_decrypt_enqueue;
-
-	err = crypto_register_instance(tmpl, inst);
-	if (err) {
-		crypto_drop_spawn(&ctx->spawn);
-out_free_inst:
-		kfree(inst);
-	}
-
-out_put_alg:
-	crypto_mod_put(alg);
-	return err;
-}
-
 static int cryptd_skcipher_setkey(struct crypto_skcipher *parent,
 				  const u8 *key, unsigned int keylen)
 {
@@ -738,7 +545,6 @@ static void cryptd_hash_init(struct crypto_async_request *req_async, int err)
 		goto out;
 
 	desc->tfm = child;
-	desc->flags = CRYPTO_TFM_REQ_MAY_SLEEP;
 
 	err = crypto_shash_init(desc);
 
@@ -830,7 +636,6 @@ static void cryptd_hash_digest(struct crypto_async_request *req_async, int err)
 		goto out;
 
 	desc->tfm = child;
-	desc->flags = CRYPTO_TFM_REQ_MAY_SLEEP;
 
 	err = shash_ahash_digest(req, desc);
 
@@ -859,7 +664,6 @@ static int cryptd_hash_import(struct ahash_request *req, const void *in)
 	struct shash_desc *desc = cryptd_shash_desc(req);
 
 	desc->tfm = ctx->child;
-	desc->flags = req->base.flags;
 
 	return crypto_shash_import(desc, in);
 }
@@ -1118,10 +922,6 @@ static int cryptd_create(struct crypto_template *tmpl, struct rtattr **tb)
 
 	switch (algt->type & algt->mask & CRYPTO_ALG_TYPE_MASK) {
 	case CRYPTO_ALG_TYPE_BLKCIPHER:
-		if ((algt->type & CRYPTO_ALG_TYPE_MASK) ==
-		    CRYPTO_ALG_TYPE_BLKCIPHER)
-			return cryptd_create_blkcipher(tmpl, tb, &queue);
-
 		return cryptd_create_skcipher(tmpl, tb, &queue);
 	case CRYPTO_ALG_TYPE_DIGEST:
 		return cryptd_create_hash(tmpl, tb, &queue);
@@ -1160,58 +960,6 @@ static struct crypto_template cryptd_tmpl = {
 	.module = THIS_MODULE,
 };
 
-struct cryptd_ablkcipher *cryptd_alloc_ablkcipher(const char *alg_name,
-						  u32 type, u32 mask)
-{
-	char cryptd_alg_name[CRYPTO_MAX_ALG_NAME];
-	struct cryptd_blkcipher_ctx *ctx;
-	struct crypto_tfm *tfm;
-
-	if (snprintf(cryptd_alg_name, CRYPTO_MAX_ALG_NAME,
-		     "cryptd(%s)", alg_name) >= CRYPTO_MAX_ALG_NAME)
-		return ERR_PTR(-EINVAL);
-	type = crypto_skcipher_type(type);
-	mask &= ~CRYPTO_ALG_TYPE_MASK;
-	mask |= CRYPTO_ALG_TYPE_BLKCIPHER_MASK;
-	tfm = crypto_alloc_base(cryptd_alg_name, type, mask);
-	if (IS_ERR(tfm))
-		return ERR_CAST(tfm);
-	if (tfm->__crt_alg->cra_module != THIS_MODULE) {
-		crypto_free_tfm(tfm);
-		return ERR_PTR(-EINVAL);
-	}
-
-	ctx = crypto_tfm_ctx(tfm);
-	atomic_set(&ctx->refcnt, 1);
-
-	return __cryptd_ablkcipher_cast(__crypto_ablkcipher_cast(tfm));
-}
-EXPORT_SYMBOL_GPL(cryptd_alloc_ablkcipher);
-
-struct crypto_blkcipher *cryptd_ablkcipher_child(struct cryptd_ablkcipher *tfm)
-{
-	struct cryptd_blkcipher_ctx *ctx = crypto_ablkcipher_ctx(&tfm->base);
-	return ctx->child;
-}
-EXPORT_SYMBOL_GPL(cryptd_ablkcipher_child);
-
-bool cryptd_ablkcipher_queued(struct cryptd_ablkcipher *tfm)
-{
-	struct cryptd_blkcipher_ctx *ctx = crypto_ablkcipher_ctx(&tfm->base);
-
-	return atomic_read(&ctx->refcnt) - 1;
-}
-EXPORT_SYMBOL_GPL(cryptd_ablkcipher_queued);
-
-void cryptd_free_ablkcipher(struct cryptd_ablkcipher *tfm)
-{
-	struct cryptd_blkcipher_ctx *ctx = crypto_ablkcipher_ctx(&tfm->base);
-
-	if (atomic_dec_and_test(&ctx->refcnt))
-		crypto_free_ablkcipher(&tfm->base);
-}
-EXPORT_SYMBOL_GPL(cryptd_free_ablkcipher);
-
 struct cryptd_skcipher *cryptd_alloc_skcipher(const char *alg_name,
 					      u32 type, u32 mask)
 {
diff --git a/crypto/crypto_null.c b/crypto/crypto_null.c
index 01630a9c7e01..9320d4eaa4a8 100644
--- a/crypto/crypto_null.c
+++ b/crypto/crypto_null.c
@@ -220,7 +220,7 @@ static void __exit crypto_null_mod_fini(void)
 	crypto_unregister_skcipher(&skcipher_null);
 }
 
-module_init(crypto_null_mod_init);
+subsys_initcall(crypto_null_mod_init);
 module_exit(crypto_null_mod_fini);
 
 MODULE_LICENSE("GPL");
diff --git a/crypto/ctr.c b/crypto/ctr.c
index ec8f8b67473a..52cdf2c5605f 100644
--- a/crypto/ctr.c
+++ b/crypto/ctr.c
@@ -384,7 +384,7 @@ static void __exit crypto_ctr_module_exit(void)
 				    ARRAY_SIZE(crypto_ctr_tmpls));
 }
 
-module_init(crypto_ctr_module_init);
+subsys_initcall(crypto_ctr_module_init);
 module_exit(crypto_ctr_module_exit);
 
 MODULE_LICENSE("GPL");
diff --git a/crypto/cts.c b/crypto/cts.c
index 4e28d83ae37d..6b6087dbb62a 100644
--- a/crypto/cts.c
+++ b/crypto/cts.c
@@ -152,12 +152,14 @@ static int crypto_cts_encrypt(struct skcipher_request *req)
 	struct skcipher_request *subreq = &rctx->subreq;
 	int bsize = crypto_skcipher_blocksize(tfm);
 	unsigned int nbytes = req->cryptlen;
-	int cbc_blocks = (nbytes + bsize - 1) / bsize - 1;
 	unsigned int offset;
 
 	skcipher_request_set_tfm(subreq, ctx->child);
 
-	if (cbc_blocks <= 0) {
+	if (nbytes < bsize)
+		return -EINVAL;
+
+	if (nbytes == bsize) {
 		skcipher_request_set_callback(subreq, req->base.flags,
 					      req->base.complete,
 					      req->base.data);
@@ -166,7 +168,7 @@ static int crypto_cts_encrypt(struct skcipher_request *req)
 		return crypto_skcipher_encrypt(subreq);
 	}
 
-	offset = cbc_blocks * bsize;
+	offset = rounddown(nbytes - 1, bsize);
 	rctx->offset = offset;
 
 	skcipher_request_set_callback(subreq, req->base.flags,
@@ -244,13 +246,15 @@ static int crypto_cts_decrypt(struct skcipher_request *req)
 	struct skcipher_request *subreq = &rctx->subreq;
 	int bsize = crypto_skcipher_blocksize(tfm);
 	unsigned int nbytes = req->cryptlen;
-	int cbc_blocks = (nbytes + bsize - 1) / bsize - 1;
 	unsigned int offset;
 	u8 *space;
 
 	skcipher_request_set_tfm(subreq, ctx->child);
 
-	if (cbc_blocks <= 0) {
+	if (nbytes < bsize)
+		return -EINVAL;
+
+	if (nbytes == bsize) {
 		skcipher_request_set_callback(subreq, req->base.flags,
 					      req->base.complete,
 					      req->base.data);
@@ -264,10 +268,10 @@ static int crypto_cts_decrypt(struct skcipher_request *req)
 
 	space = crypto_cts_reqctx_space(req);
 
-	offset = cbc_blocks * bsize;
+	offset = rounddown(nbytes - 1, bsize);
 	rctx->offset = offset;
 
-	if (cbc_blocks <= 1)
+	if (offset <= bsize)
 		memcpy(space, req->iv, bsize);
 	else
 		scatterwalk_map_and_copy(space, req->src, offset - 2 * bsize,
@@ -419,7 +423,7 @@ static void __exit crypto_cts_module_exit(void)
 	crypto_unregister_template(&crypto_cts_tmpl);
 }
 
-module_init(crypto_cts_module_init);
+subsys_initcall(crypto_cts_module_init);
 module_exit(crypto_cts_module_exit);
 
 MODULE_LICENSE("Dual BSD/GPL");
diff --git a/crypto/deflate.c b/crypto/deflate.c
index 94ec3b36a8e8..aab089cde1bf 100644
--- a/crypto/deflate.c
+++ b/crypto/deflate.c
@@ -334,7 +334,7 @@ static void __exit deflate_mod_fini(void)
 	crypto_unregister_scomps(scomp, ARRAY_SIZE(scomp));
 }
 
-module_init(deflate_mod_init);
+subsys_initcall(deflate_mod_init);
 module_exit(deflate_mod_fini);
 
 MODULE_LICENSE("GPL");
diff --git a/crypto/des_generic.c b/crypto/des_generic.c
index 1e6621665dd9..d7a88b4fa611 100644
--- a/crypto/des_generic.c
+++ b/crypto/des_generic.c
@@ -862,14 +862,11 @@ static void des_decrypt(struct crypto_tfm *tfm, u8 *dst, const u8 *src)
 int __des3_ede_setkey(u32 *expkey, u32 *flags, const u8 *key,
 		      unsigned int keylen)
 {
-	const u32 *K = (const u32 *)key;
+	int err;
 
-	if (unlikely(!((K[0] ^ K[2]) | (K[1] ^ K[3])) ||
-		     !((K[2] ^ K[4]) | (K[3] ^ K[5]))) &&
-		     (*flags & CRYPTO_TFM_REQ_FORBID_WEAK_KEYS)) {
-		*flags |= CRYPTO_TFM_RES_WEAK_KEY;
-		return -EINVAL;
-	}
+	err = __des3_verify_key(flags, key);
+	if (unlikely(err))
+		return err;
 
 	des_ekey(expkey, key); expkey += DES_EXPKEY_WORDS; key += DES_KEY_SIZE;
 	dkey(expkey, key); expkey += DES_EXPKEY_WORDS; key += DES_KEY_SIZE;
@@ -993,7 +990,7 @@ static void __exit des_generic_mod_fini(void)
 	crypto_unregister_algs(des_algs, ARRAY_SIZE(des_algs));
 }
 
-module_init(des_generic_mod_init);
+subsys_initcall(des_generic_mod_init);
 module_exit(des_generic_mod_fini);
 
 MODULE_LICENSE("GPL");
diff --git a/crypto/dh.c b/crypto/dh.c
index 09a44de4209d..ce77fb4ee8b3 100644
--- a/crypto/dh.c
+++ b/crypto/dh.c
@@ -236,7 +236,7 @@ static void dh_exit(void)
 	crypto_unregister_kpp(&dh);
 }
 
-module_init(dh_init);
+subsys_initcall(dh_init);
 module_exit(dh_exit);
 MODULE_ALIAS_CRYPTO("dh");
 MODULE_LICENSE("GPL");
diff --git a/crypto/drbg.c b/crypto/drbg.c
index bc52d9562611..2a5b16bb000c 100644
--- a/crypto/drbg.c
+++ b/crypto/drbg.c
@@ -1587,7 +1587,6 @@ static int drbg_init_hash_kernel(struct drbg_state *drbg)
 	}
 
 	sdesc->shash.tfm = tfm;
-	sdesc->shash.flags = 0;
 	drbg->priv_data = sdesc;
 
 	return crypto_shash_alignmask(tfm);
@@ -2039,7 +2038,7 @@ static void __exit drbg_exit(void)
 	crypto_unregister_rngs(drbg_algs, (ARRAY_SIZE(drbg_cores) * 2));
 }
 
-module_init(drbg_init);
+subsys_initcall(drbg_init);
 module_exit(drbg_exit);
 #ifndef CRYPTO_DRBG_HASH_STRING
 #define CRYPTO_DRBG_HASH_STRING ""
diff --git a/crypto/ecb.c b/crypto/ecb.c
index 0732715c8d91..de839129d151 100644
--- a/crypto/ecb.c
+++ b/crypto/ecb.c
@@ -101,7 +101,7 @@ static void __exit crypto_ecb_module_exit(void)
 	crypto_unregister_template(&crypto_ecb_tmpl);
 }
 
-module_init(crypto_ecb_module_init);
+subsys_initcall(crypto_ecb_module_init);
 module_exit(crypto_ecb_module_exit);
 
 MODULE_LICENSE("GPL");
diff --git a/crypto/ecc.c b/crypto/ecc.c
index ed1237115066..dfe114bc0c4a 100644
--- a/crypto/ecc.c
+++ b/crypto/ecc.c
@@ -1,6 +1,6 @@
 /*
- * Copyright (c) 2013, Kenneth MacKay
- * All rights reserved.
+ * Copyright (c) 2013, 2014 Kenneth MacKay. All rights reserved.
+ * Copyright (c) 2019 Vitaly Chikunov <vt@altlinux.org>
  *
  * Redistribution and use in source and binary forms, with or without
  * modification, are permitted provided that the following conditions are
@@ -24,12 +24,15 @@
  * OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
  */
 
+#include <linux/module.h>
 #include <linux/random.h>
 #include <linux/slab.h>
 #include <linux/swab.h>
 #include <linux/fips.h>
 #include <crypto/ecdh.h>
 #include <crypto/rng.h>
+#include <asm/unaligned.h>
+#include <linux/ratelimit.h>
 
 #include "ecc.h"
 #include "ecc_curve_defs.h"
@@ -112,7 +115,7 @@ static void vli_clear(u64 *vli, unsigned int ndigits)
 }
 
 /* Returns true if vli == 0, false otherwise. */
-static bool vli_is_zero(const u64 *vli, unsigned int ndigits)
+bool vli_is_zero(const u64 *vli, unsigned int ndigits)
 {
 	int i;
 
@@ -123,6 +126,7 @@ static bool vli_is_zero(const u64 *vli, unsigned int ndigits)
 
 	return true;
 }
+EXPORT_SYMBOL(vli_is_zero);
 
 /* Returns nonzero if bit bit of vli is set. */
 static u64 vli_test_bit(const u64 *vli, unsigned int bit)
@@ -130,6 +134,11 @@ static u64 vli_test_bit(const u64 *vli, unsigned int bit)
 	return (vli[bit / 64] & ((u64)1 << (bit % 64)));
 }
 
+static bool vli_is_negative(const u64 *vli, unsigned int ndigits)
+{
+	return vli_test_bit(vli, ndigits * 64 - 1);
+}
+
 /* Counts the number of 64-bit "digits" in vli. */
 static unsigned int vli_num_digits(const u64 *vli, unsigned int ndigits)
 {
@@ -161,6 +170,27 @@ static unsigned int vli_num_bits(const u64 *vli, unsigned int ndigits)
 	return ((num_digits - 1) * 64 + i);
 }
 
+/* Set dest from unaligned bit string src. */
+void vli_from_be64(u64 *dest, const void *src, unsigned int ndigits)
+{
+	int i;
+	const u64 *from = src;
+
+	for (i = 0; i < ndigits; i++)
+		dest[i] = get_unaligned_be64(&from[ndigits - 1 - i]);
+}
+EXPORT_SYMBOL(vli_from_be64);
+
+void vli_from_le64(u64 *dest, const void *src, unsigned int ndigits)
+{
+	int i;
+	const u64 *from = src;
+
+	for (i = 0; i < ndigits; i++)
+		dest[i] = get_unaligned_le64(&from[i]);
+}
+EXPORT_SYMBOL(vli_from_le64);
+
 /* Sets dest = src. */
 static void vli_set(u64 *dest, const u64 *src, unsigned int ndigits)
 {
@@ -171,7 +201,7 @@ static void vli_set(u64 *dest, const u64 *src, unsigned int ndigits)
 }
 
 /* Returns sign of left - right. */
-static int vli_cmp(const u64 *left, const u64 *right, unsigned int ndigits)
+int vli_cmp(const u64 *left, const u64 *right, unsigned int ndigits)
 {
 	int i;
 
@@ -184,6 +214,7 @@ static int vli_cmp(const u64 *left, const u64 *right, unsigned int ndigits)
 
 	return 0;
 }
+EXPORT_SYMBOL(vli_cmp);
 
 /* Computes result = in << c, returning carry. Can modify in place
  * (if result == in). 0 < shift < 64.
@@ -239,8 +270,30 @@ static u64 vli_add(u64 *result, const u64 *left, const u64 *right,
 	return carry;
 }
 
+/* Computes result = left + right, returning carry. Can modify in place. */
+static u64 vli_uadd(u64 *result, const u64 *left, u64 right,
+		    unsigned int ndigits)
+{
+	u64 carry = right;
+	int i;
+
+	for (i = 0; i < ndigits; i++) {
+		u64 sum;
+
+		sum = left[i] + carry;
+		if (sum != left[i])
+			carry = (sum < left[i]);
+		else
+			carry = !!carry;
+
+		result[i] = sum;
+	}
+
+	return carry;
+}
+
 /* Computes result = left - right, returning borrow. Can modify in place. */
-static u64 vli_sub(u64 *result, const u64 *left, const u64 *right,
+u64 vli_sub(u64 *result, const u64 *left, const u64 *right,
 		   unsigned int ndigits)
 {
 	u64 borrow = 0;
@@ -258,9 +311,37 @@ static u64 vli_sub(u64 *result, const u64 *left, const u64 *right,
 
 	return borrow;
 }
+EXPORT_SYMBOL(vli_sub);
+
+/* Computes result = left - right, returning borrow. Can modify in place. */
+static u64 vli_usub(u64 *result, const u64 *left, u64 right,
+	     unsigned int ndigits)
+{
+	u64 borrow = right;
+	int i;
+
+	for (i = 0; i < ndigits; i++) {
+		u64 diff;
+
+		diff = left[i] - borrow;
+		if (diff != left[i])
+			borrow = (diff > left[i]);
+
+		result[i] = diff;
+	}
+
+	return borrow;
+}
 
 static uint128_t mul_64_64(u64 left, u64 right)
 {
+	uint128_t result;
+#if defined(CONFIG_ARCH_SUPPORTS_INT128) && defined(__SIZEOF_INT128__)
+	unsigned __int128 m = (unsigned __int128)left * right;
+
+	result.m_low  = m;
+	result.m_high = m >> 64;
+#else
 	u64 a0 = left & 0xffffffffull;
 	u64 a1 = left >> 32;
 	u64 b0 = right & 0xffffffffull;
@@ -269,7 +350,6 @@ static uint128_t mul_64_64(u64 left, u64 right)
 	u64 m1 = a0 * b1;
 	u64 m2 = a1 * b0;
 	u64 m3 = a1 * b1;
-	uint128_t result;
 
 	m2 += (m0 >> 32);
 	m2 += m1;
@@ -280,7 +360,7 @@ static uint128_t mul_64_64(u64 left, u64 right)
 
 	result.m_low = (m0 & 0xffffffffull) | (m2 << 32);
 	result.m_high = m3 + (m2 >> 32);
-
+#endif
 	return result;
 }
 
@@ -330,6 +410,28 @@ static void vli_mult(u64 *result, const u64 *left, const u64 *right,
 	result[ndigits * 2 - 1] = r01.m_low;
 }
 
+/* Compute product = left * right, for a small right value. */
+static void vli_umult(u64 *result, const u64 *left, u32 right,
+		      unsigned int ndigits)
+{
+	uint128_t r01 = { 0 };
+	unsigned int k;
+
+	for (k = 0; k < ndigits; k++) {
+		uint128_t product;
+
+		product = mul_64_64(left[k], right);
+		r01 = add_128_128(r01, product);
+		/* no carry */
+		result[k] = r01.m_low;
+		r01.m_low = r01.m_high;
+		r01.m_high = 0;
+	}
+	result[k] = r01.m_low;
+	for (++k; k < ndigits * 2; k++)
+		result[k] = 0;
+}
+
 static void vli_square(u64 *result, const u64 *left, unsigned int ndigits)
 {
 	uint128_t r01 = { 0, 0 };
@@ -402,6 +504,170 @@ static void vli_mod_sub(u64 *result, const u64 *left, const u64 *right,
 		vli_add(result, result, mod, ndigits);
 }
 
+/*
+ * Computes result = product % mod
+ * for special form moduli: p = 2^k-c, for small c (note the minus sign)
+ *
+ * References:
+ * R. Crandall, C. Pomerance. Prime Numbers: A Computational Perspective.
+ * 9 Fast Algorithms for Large-Integer Arithmetic. 9.2.3 Moduli of special form
+ * Algorithm 9.2.13 (Fast mod operation for special-form moduli).
+ */
+static void vli_mmod_special(u64 *result, const u64 *product,
+			      const u64 *mod, unsigned int ndigits)
+{
+	u64 c = -mod[0];
+	u64 t[ECC_MAX_DIGITS * 2];
+	u64 r[ECC_MAX_DIGITS * 2];
+
+	vli_set(r, product, ndigits * 2);
+	while (!vli_is_zero(r + ndigits, ndigits)) {
+		vli_umult(t, r + ndigits, c, ndigits);
+		vli_clear(r + ndigits, ndigits);
+		vli_add(r, r, t, ndigits * 2);
+	}
+	vli_set(t, mod, ndigits);
+	vli_clear(t + ndigits, ndigits);
+	while (vli_cmp(r, t, ndigits * 2) >= 0)
+		vli_sub(r, r, t, ndigits * 2);
+	vli_set(result, r, ndigits);
+}
+
+/*
+ * Computes result = product % mod
+ * for special form moduli: p = 2^{k-1}+c, for small c (note the plus sign)
+ * where k-1 does not fit into qword boundary by -1 bit (such as 255).
+
+ * References (loosely based on):
+ * A. Menezes, P. van Oorschot, S. Vanstone. Handbook of Applied Cryptography.
+ * 14.3.4 Reduction methods for moduli of special form. Algorithm 14.47.
+ * URL: http://cacr.uwaterloo.ca/hac/about/chap14.pdf
+ *
+ * H. Cohen, G. Frey, R. Avanzi, C. Doche, T. Lange, K. Nguyen, F. Vercauteren.
+ * Handbook of Elliptic and Hyperelliptic Curve Cryptography.
+ * Algorithm 10.25 Fast reduction for special form moduli
+ */
+static void vli_mmod_special2(u64 *result, const u64 *product,
+			       const u64 *mod, unsigned int ndigits)
+{
+	u64 c2 = mod[0] * 2;
+	u64 q[ECC_MAX_DIGITS];
+	u64 r[ECC_MAX_DIGITS * 2];
+	u64 m[ECC_MAX_DIGITS * 2]; /* expanded mod */
+	int carry; /* last bit that doesn't fit into q */
+	int i;
+
+	vli_set(m, mod, ndigits);
+	vli_clear(m + ndigits, ndigits);
+
+	vli_set(r, product, ndigits);
+	/* q and carry are top bits */
+	vli_set(q, product + ndigits, ndigits);
+	vli_clear(r + ndigits, ndigits);
+	carry = vli_is_negative(r, ndigits);
+	if (carry)
+		r[ndigits - 1] &= (1ull << 63) - 1;
+	for (i = 1; carry || !vli_is_zero(q, ndigits); i++) {
+		u64 qc[ECC_MAX_DIGITS * 2];
+
+		vli_umult(qc, q, c2, ndigits);
+		if (carry)
+			vli_uadd(qc, qc, mod[0], ndigits * 2);
+		vli_set(q, qc + ndigits, ndigits);
+		vli_clear(qc + ndigits, ndigits);
+		carry = vli_is_negative(qc, ndigits);
+		if (carry)
+			qc[ndigits - 1] &= (1ull << 63) - 1;
+		if (i & 1)
+			vli_sub(r, r, qc, ndigits * 2);
+		else
+			vli_add(r, r, qc, ndigits * 2);
+	}
+	while (vli_is_negative(r, ndigits * 2))
+		vli_add(r, r, m, ndigits * 2);
+	while (vli_cmp(r, m, ndigits * 2) >= 0)
+		vli_sub(r, r, m, ndigits * 2);
+
+	vli_set(result, r, ndigits);
+}
+
+/*
+ * Computes result = product % mod, where product is 2N words long.
+ * Reference: Ken MacKay's micro-ecc.
+ * Currently only designed to work for curve_p or curve_n.
+ */
+static void vli_mmod_slow(u64 *result, u64 *product, const u64 *mod,
+			  unsigned int ndigits)
+{
+	u64 mod_m[2 * ECC_MAX_DIGITS];
+	u64 tmp[2 * ECC_MAX_DIGITS];
+	u64 *v[2] = { tmp, product };
+	u64 carry = 0;
+	unsigned int i;
+	/* Shift mod so its highest set bit is at the maximum position. */
+	int shift = (ndigits * 2 * 64) - vli_num_bits(mod, ndigits);
+	int word_shift = shift / 64;
+	int bit_shift = shift % 64;
+
+	vli_clear(mod_m, word_shift);
+	if (bit_shift > 0) {
+		for (i = 0; i < ndigits; ++i) {
+			mod_m[word_shift + i] = (mod[i] << bit_shift) | carry;
+			carry = mod[i] >> (64 - bit_shift);
+		}
+	} else
+		vli_set(mod_m + word_shift, mod, ndigits);
+
+	for (i = 1; shift >= 0; --shift) {
+		u64 borrow = 0;
+		unsigned int j;
+
+		for (j = 0; j < ndigits * 2; ++j) {
+			u64 diff = v[i][j] - mod_m[j] - borrow;
+
+			if (diff != v[i][j])
+				borrow = (diff > v[i][j]);
+			v[1 - i][j] = diff;
+		}
+		i = !(i ^ borrow); /* Swap the index if there was no borrow */
+		vli_rshift1(mod_m, ndigits);
+		mod_m[ndigits - 1] |= mod_m[ndigits] << (64 - 1);
+		vli_rshift1(mod_m + ndigits, ndigits);
+	}
+	vli_set(result, v[i], ndigits);
+}
+
+/* Computes result = product % mod using Barrett's reduction with precomputed
+ * value mu appended to the mod after ndigits, mu = (2^{2w} / mod) and have
+ * length ndigits + 1, where mu * (2^w - 1) should not overflow ndigits
+ * boundary.
+ *
+ * Reference:
+ * R. Brent, P. Zimmermann. Modern Computer Arithmetic. 2010.
+ * 2.4.1 Barrett's algorithm. Algorithm 2.5.
+ */
+static void vli_mmod_barrett(u64 *result, u64 *product, const u64 *mod,
+			     unsigned int ndigits)
+{
+	u64 q[ECC_MAX_DIGITS * 2];
+	u64 r[ECC_MAX_DIGITS * 2];
+	const u64 *mu = mod + ndigits;
+
+	vli_mult(q, product + ndigits, mu, ndigits);
+	if (mu[ndigits])
+		vli_add(q + ndigits, q + ndigits, product + ndigits, ndigits);
+	vli_mult(r, mod, q + ndigits, ndigits);
+	vli_sub(r, product, r, ndigits * 2);
+	while (!vli_is_zero(r + ndigits, ndigits) ||
+	       vli_cmp(r, mod, ndigits) != -1) {
+		u64 carry;
+
+		carry = vli_sub(r, r, mod, ndigits);
+		vli_usub(r + ndigits, r + ndigits, carry, ndigits);
+	}
+	vli_set(result, r, ndigits);
+}
+
 /* Computes p_result = p_product % curve_p.
  * See algorithm 5 and 6 from
  * http://www.isys.uni-klu.ac.at/PDF/2001-0126-MT.pdf
@@ -509,14 +775,33 @@ static void vli_mmod_fast_256(u64 *result, const u64 *product,
 	}
 }
 
-/* Computes result = product % curve_prime
- *  from http://www.nsa.gov/ia/_files/nist-routines.pdf
-*/
+/* Computes result = product % curve_prime for different curve_primes.
+ *
+ * Note that curve_primes are distinguished just by heuristic check and
+ * not by complete conformance check.
+ */
 static bool vli_mmod_fast(u64 *result, u64 *product,
 			  const u64 *curve_prime, unsigned int ndigits)
 {
 	u64 tmp[2 * ECC_MAX_DIGITS];
 
+	/* Currently, both NIST primes have -1 in lowest qword. */
+	if (curve_prime[0] != -1ull) {
+		/* Try to handle Pseudo-Marsenne primes. */
+		if (curve_prime[ndigits - 1] == -1ull) {
+			vli_mmod_special(result, product, curve_prime,
+					 ndigits);
+			return true;
+		} else if (curve_prime[ndigits - 1] == 1ull << 63 &&
+			   curve_prime[ndigits - 2] == 0) {
+			vli_mmod_special2(result, product, curve_prime,
+					  ndigits);
+			return true;
+		}
+		vli_mmod_barrett(result, product, curve_prime, ndigits);
+		return true;
+	}
+
 	switch (ndigits) {
 	case 3:
 		vli_mmod_fast_192(result, product, curve_prime, tmp);
@@ -525,13 +810,26 @@ static bool vli_mmod_fast(u64 *result, u64 *product,
 		vli_mmod_fast_256(result, product, curve_prime, tmp);
 		break;
 	default:
-		pr_err("unsupports digits size!\n");
+		pr_err_ratelimited("ecc: unsupported digits size!\n");
 		return false;
 	}
 
 	return true;
 }
 
+/* Computes result = (left * right) % mod.
+ * Assumes that mod is big enough curve order.
+ */
+void vli_mod_mult_slow(u64 *result, const u64 *left, const u64 *right,
+		       const u64 *mod, unsigned int ndigits)
+{
+	u64 product[ECC_MAX_DIGITS * 2];
+
+	vli_mult(product, left, right, ndigits);
+	vli_mmod_slow(result, product, mod, ndigits);
+}
+EXPORT_SYMBOL(vli_mod_mult_slow);
+
 /* Computes result = (left * right) % curve_prime. */
 static void vli_mod_mult_fast(u64 *result, const u64 *left, const u64 *right,
 			      const u64 *curve_prime, unsigned int ndigits)
@@ -557,7 +855,7 @@ static void vli_mod_square_fast(u64 *result, const u64 *left,
  * See "From Euclid's GCD to Montgomery Multiplication to the Great Divide"
  * https://labs.oracle.com/techrep/2001/smli_tr-2001-95.pdf
  */
-static void vli_mod_inv(u64 *result, const u64 *input, const u64 *mod,
+void vli_mod_inv(u64 *result, const u64 *input, const u64 *mod,
 			unsigned int ndigits)
 {
 	u64 a[ECC_MAX_DIGITS], b[ECC_MAX_DIGITS];
@@ -630,6 +928,7 @@ static void vli_mod_inv(u64 *result, const u64 *input, const u64 *mod,
 
 	vli_set(result, u, ndigits);
 }
+EXPORT_SYMBOL(vli_mod_inv);
 
 /* ------ Point operations ------ */
 
@@ -903,6 +1202,85 @@ static void ecc_point_mult(struct ecc_point *result,
 	vli_set(result->y, ry[0], ndigits);
 }
 
+/* Computes R = P + Q mod p */
+static void ecc_point_add(const struct ecc_point *result,
+		   const struct ecc_point *p, const struct ecc_point *q,
+		   const struct ecc_curve *curve)
+{
+	u64 z[ECC_MAX_DIGITS];
+	u64 px[ECC_MAX_DIGITS];
+	u64 py[ECC_MAX_DIGITS];
+	unsigned int ndigits = curve->g.ndigits;
+
+	vli_set(result->x, q->x, ndigits);
+	vli_set(result->y, q->y, ndigits);
+	vli_mod_sub(z, result->x, p->x, curve->p, ndigits);
+	vli_set(px, p->x, ndigits);
+	vli_set(py, p->y, ndigits);
+	xycz_add(px, py, result->x, result->y, curve->p, ndigits);
+	vli_mod_inv(z, z, curve->p, ndigits);
+	apply_z(result->x, result->y, z, curve->p, ndigits);
+}
+
+/* Computes R = u1P + u2Q mod p using Shamir's trick.
+ * Based on: Kenneth MacKay's micro-ecc (2014).
+ */
+void ecc_point_mult_shamir(const struct ecc_point *result,
+			   const u64 *u1, const struct ecc_point *p,
+			   const u64 *u2, const struct ecc_point *q,
+			   const struct ecc_curve *curve)
+{
+	u64 z[ECC_MAX_DIGITS];
+	u64 sump[2][ECC_MAX_DIGITS];
+	u64 *rx = result->x;
+	u64 *ry = result->y;
+	unsigned int ndigits = curve->g.ndigits;
+	unsigned int num_bits;
+	struct ecc_point sum = ECC_POINT_INIT(sump[0], sump[1], ndigits);
+	const struct ecc_point *points[4];
+	const struct ecc_point *point;
+	unsigned int idx;
+	int i;
+
+	ecc_point_add(&sum, p, q, curve);
+	points[0] = NULL;
+	points[1] = p;
+	points[2] = q;
+	points[3] = &sum;
+
+	num_bits = max(vli_num_bits(u1, ndigits),
+		       vli_num_bits(u2, ndigits));
+	i = num_bits - 1;
+	idx = (!!vli_test_bit(u1, i)) | ((!!vli_test_bit(u2, i)) << 1);
+	point = points[idx];
+
+	vli_set(rx, point->x, ndigits);
+	vli_set(ry, point->y, ndigits);
+	vli_clear(z + 1, ndigits - 1);
+	z[0] = 1;
+
+	for (--i; i >= 0; i--) {
+		ecc_point_double_jacobian(rx, ry, z, curve->p, ndigits);
+		idx = (!!vli_test_bit(u1, i)) | ((!!vli_test_bit(u2, i)) << 1);
+		point = points[idx];
+		if (point) {
+			u64 tx[ECC_MAX_DIGITS];
+			u64 ty[ECC_MAX_DIGITS];
+			u64 tz[ECC_MAX_DIGITS];
+
+			vli_set(tx, point->x, ndigits);
+			vli_set(ty, point->y, ndigits);
+			apply_z(tx, ty, z, curve->p, ndigits);
+			vli_mod_sub(tz, rx, tx, curve->p, ndigits);
+			xycz_add(tx, ty, rx, ry, curve->p, ndigits);
+			vli_mod_mult_fast(z, z, tz, curve->p, ndigits);
+		}
+	}
+	vli_mod_inv(z, z, curve->p, ndigits);
+	apply_z(rx, ry, z, curve->p, ndigits);
+}
+EXPORT_SYMBOL(ecc_point_mult_shamir);
+
 static inline void ecc_swap_digits(const u64 *in, u64 *out,
 				   unsigned int ndigits)
 {
@@ -948,6 +1326,7 @@ int ecc_is_key_valid(unsigned int curve_id, unsigned int ndigits,
 
 	return __ecc_is_key_valid(curve, private_key, ndigits);
 }
+EXPORT_SYMBOL(ecc_is_key_valid);
 
 /*
  * ECC private keys are generated using the method of extra random bits,
@@ -1000,6 +1379,7 @@ int ecc_gen_privkey(unsigned int curve_id, unsigned int ndigits, u64 *privkey)
 
 	return 0;
 }
+EXPORT_SYMBOL(ecc_gen_privkey);
 
 int ecc_make_pub_key(unsigned int curve_id, unsigned int ndigits,
 		     const u64 *private_key, u64 *public_key)
@@ -1036,13 +1416,17 @@ err_free_point:
 out:
 	return ret;
 }
+EXPORT_SYMBOL(ecc_make_pub_key);
 
 /* SP800-56A section 5.6.2.3.4 partial verification: ephemeral keys only */
-static int ecc_is_pubkey_valid_partial(const struct ecc_curve *curve,
-				       struct ecc_point *pk)
+int ecc_is_pubkey_valid_partial(const struct ecc_curve *curve,
+				struct ecc_point *pk)
 {
 	u64 yy[ECC_MAX_DIGITS], xxx[ECC_MAX_DIGITS], w[ECC_MAX_DIGITS];
 
+	if (WARN_ON(pk->ndigits != curve->g.ndigits))
+		return -EINVAL;
+
 	/* Check 1: Verify key is not the zero point. */
 	if (ecc_point_is_zero(pk))
 		return -EINVAL;
@@ -1064,8 +1448,8 @@ static int ecc_is_pubkey_valid_partial(const struct ecc_curve *curve,
 		return -EINVAL;
 
 	return 0;
-
 }
+EXPORT_SYMBOL(ecc_is_pubkey_valid_partial);
 
 int crypto_ecdh_shared_secret(unsigned int curve_id, unsigned int ndigits,
 			      const u64 *private_key, const u64 *public_key,
@@ -1121,3 +1505,6 @@ err_alloc_product:
 out:
 	return ret;
 }
+EXPORT_SYMBOL(crypto_ecdh_shared_secret);
+
+MODULE_LICENSE("Dual BSD/GPL");
diff --git a/crypto/ecc.h b/crypto/ecc.h
index f75a86baa3bd..ab0eb70b9c09 100644
--- a/crypto/ecc.h
+++ b/crypto/ecc.h
@@ -26,13 +26,51 @@
 #ifndef _CRYPTO_ECC_H
 #define _CRYPTO_ECC_H
 
+/* One digit is u64 qword. */
 #define ECC_CURVE_NIST_P192_DIGITS  3
 #define ECC_CURVE_NIST_P256_DIGITS  4
-#define ECC_MAX_DIGITS              ECC_CURVE_NIST_P256_DIGITS
+#define ECC_MAX_DIGITS             (512 / 64)
 
 #define ECC_DIGITS_TO_BYTES_SHIFT 3
 
 /**
+ * struct ecc_point - elliptic curve point in affine coordinates
+ *
+ * @x:		X coordinate in vli form.
+ * @y:		Y coordinate in vli form.
+ * @ndigits:	Length of vlis in u64 qwords.
+ */
+struct ecc_point {
+	u64 *x;
+	u64 *y;
+	u8 ndigits;
+};
+
+#define ECC_POINT_INIT(x, y, ndigits)	(struct ecc_point) { x, y, ndigits }
+
+/**
+ * struct ecc_curve - definition of elliptic curve
+ *
+ * @name:	Short name of the curve.
+ * @g:		Generator point of the curve.
+ * @p:		Prime number, if Barrett's reduction is used for this curve
+ *		pre-calculated value 'mu' is appended to the @p after ndigits.
+ *		Use of Barrett's reduction is heuristically determined in
+ *		vli_mmod_fast().
+ * @n:		Order of the curve group.
+ * @a:		Curve parameter a.
+ * @b:		Curve parameter b.
+ */
+struct ecc_curve {
+	char *name;
+	struct ecc_point g;
+	u64 *p;
+	u64 *n;
+	u64 *a;
+	u64 *b;
+};
+
+/**
  * ecc_is_key_valid() - Validate a given ECDH private key
  *
  * @curve_id:		id representing the curve to use
@@ -91,4 +129,117 @@ int ecc_make_pub_key(const unsigned int curve_id, unsigned int ndigits,
 int crypto_ecdh_shared_secret(unsigned int curve_id, unsigned int ndigits,
 			      const u64 *private_key, const u64 *public_key,
 			      u64 *secret);
+
+/**
+ * ecc_is_pubkey_valid_partial() - Partial public key validation
+ *
+ * @curve:		elliptic curve domain parameters
+ * @pk:			public key as a point
+ *
+ * Valdiate public key according to SP800-56A section 5.6.2.3.4 ECC Partial
+ * Public-Key Validation Routine.
+ *
+ * Note: There is no check that the public key is in the correct elliptic curve
+ * subgroup.
+ *
+ * Return: 0 if validation is successful, -EINVAL if validation is failed.
+ */
+int ecc_is_pubkey_valid_partial(const struct ecc_curve *curve,
+				struct ecc_point *pk);
+
+/**
+ * vli_is_zero() - Determine is vli is zero
+ *
+ * @vli:		vli to check.
+ * @ndigits:		length of the @vli
+ */
+bool vli_is_zero(const u64 *vli, unsigned int ndigits);
+
+/**
+ * vli_cmp() - compare left and right vlis
+ *
+ * @left:		vli
+ * @right:		vli
+ * @ndigits:		length of both vlis
+ *
+ * Returns sign of @left - @right, i.e. -1 if @left < @right,
+ * 0 if @left == @right, 1 if @left > @right.
+ */
+int vli_cmp(const u64 *left, const u64 *right, unsigned int ndigits);
+
+/**
+ * vli_sub() - Subtracts right from left
+ *
+ * @result:		where to write result
+ * @left:		vli
+ * @right		vli
+ * @ndigits:		length of all vlis
+ *
+ * Note: can modify in-place.
+ *
+ * Return: carry bit.
+ */
+u64 vli_sub(u64 *result, const u64 *left, const u64 *right,
+	    unsigned int ndigits);
+
+/**
+ * vli_from_be64() - Load vli from big-endian u64 array
+ *
+ * @dest:		destination vli
+ * @src:		source array of u64 BE values
+ * @ndigits:		length of both vli and array
+ */
+void vli_from_be64(u64 *dest, const void *src, unsigned int ndigits);
+
+/**
+ * vli_from_le64() - Load vli from little-endian u64 array
+ *
+ * @dest:		destination vli
+ * @src:		source array of u64 LE values
+ * @ndigits:		length of both vli and array
+ */
+void vli_from_le64(u64 *dest, const void *src, unsigned int ndigits);
+
+/**
+ * vli_mod_inv() - Modular inversion
+ *
+ * @result:		where to write vli number
+ * @input:		vli value to operate on
+ * @mod:		modulus
+ * @ndigits:		length of all vlis
+ */
+void vli_mod_inv(u64 *result, const u64 *input, const u64 *mod,
+		 unsigned int ndigits);
+
+/**
+ * vli_mod_mult_slow() - Modular multiplication
+ *
+ * @result:		where to write result value
+ * @left:		vli number to multiply with @right
+ * @right:		vli number to multiply with @left
+ * @mod:		modulus
+ * @ndigits:		length of all vlis
+ *
+ * Note: Assumes that mod is big enough curve order.
+ */
+void vli_mod_mult_slow(u64 *result, const u64 *left, const u64 *right,
+		       const u64 *mod, unsigned int ndigits);
+
+/**
+ * ecc_point_mult_shamir() - Add two points multiplied by scalars
+ *
+ * @result:		resulting point
+ * @x:			scalar to multiply with @p
+ * @p:			point to multiply with @x
+ * @y:			scalar to multiply with @q
+ * @q:			point to multiply with @y
+ * @curve:		curve
+ *
+ * Returns result = x * p + x * q over the curve.
+ * This works faster than two multiplications and addition.
+ */
+void ecc_point_mult_shamir(const struct ecc_point *result,
+			   const u64 *x, const struct ecc_point *p,
+			   const u64 *y, const struct ecc_point *q,
+			   const struct ecc_curve *curve);
 #endif
diff --git a/crypto/ecc_curve_defs.h b/crypto/ecc_curve_defs.h
index 336ab1805639..69be6c7d228f 100644
--- a/crypto/ecc_curve_defs.h
+++ b/crypto/ecc_curve_defs.h
@@ -2,21 +2,6 @@
 #ifndef _CRYTO_ECC_CURVE_DEFS_H
 #define _CRYTO_ECC_CURVE_DEFS_H
 
-struct ecc_point {
-	u64 *x;
-	u64 *y;
-	u8 ndigits;
-};
-
-struct ecc_curve {
-	char *name;
-	struct ecc_point g;
-	u64 *p;
-	u64 *n;
-	u64 *a;
-	u64 *b;
-};
-
 /* NIST P-192: a = p - 3 */
 static u64 nist_p192_g_x[] = { 0xF4FF0AFD82FF1012ull, 0x7CBF20EB43A18800ull,
 				0x188DA80EB03090F6ull };
diff --git a/crypto/ecdh.c b/crypto/ecdh.c
index bf6300175b9c..890092bd8989 100644
--- a/crypto/ecdh.c
+++ b/crypto/ecdh.c
@@ -166,7 +166,7 @@ static void ecdh_exit(void)
 	crypto_unregister_kpp(&ecdh);
 }
 
-module_init(ecdh_init);
+subsys_initcall(ecdh_init);
 module_exit(ecdh_exit);
 MODULE_ALIAS_CRYPTO("ecdh");
 MODULE_LICENSE("GPL");
diff --git a/crypto/echainiv.c b/crypto/echainiv.c
index 77e607fdbfb7..e71d1bc8d850 100644
--- a/crypto/echainiv.c
+++ b/crypto/echainiv.c
@@ -174,7 +174,7 @@ static void __exit echainiv_module_exit(void)
 	crypto_unregister_template(&echainiv_tmpl);
 }
 
-module_init(echainiv_module_init);
+subsys_initcall(echainiv_module_init);
 module_exit(echainiv_module_exit);
 
 MODULE_LICENSE("GPL");
diff --git a/crypto/ecrdsa.c b/crypto/ecrdsa.c
new file mode 100644
index 000000000000..887ec21aee49
--- /dev/null
+++ b/crypto/ecrdsa.c
@@ -0,0 +1,296 @@
+// SPDX-License-Identifier: GPL-2.0+
+/*
+ * Elliptic Curve (Russian) Digital Signature Algorithm for Cryptographic API
+ *
+ * Copyright (c) 2019 Vitaly Chikunov <vt@altlinux.org>
+ *
+ * References:
+ * GOST 34.10-2018, GOST R 34.10-2012, RFC 7091, ISO/IEC 14888-3:2018.
+ *
+ * Historical references:
+ * GOST R 34.10-2001, RFC 4357, ISO/IEC 14888-3:2006/Amd 1:2010.
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms of the GNU General Public License as published by the Free
+ * Software Foundation; either version 2 of the License, or (at your option)
+ * any later version.
+ */
+
+#include <linux/module.h>
+#include <linux/crypto.h>
+#include <crypto/streebog.h>
+#include <crypto/internal/akcipher.h>
+#include <crypto/akcipher.h>
+#include <linux/oid_registry.h>
+#include "ecrdsa_params.asn1.h"
+#include "ecrdsa_pub_key.asn1.h"
+#include "ecc.h"
+#include "ecrdsa_defs.h"
+
+#define ECRDSA_MAX_SIG_SIZE (2 * 512 / 8)
+#define ECRDSA_MAX_DIGITS (512 / 64)
+
+struct ecrdsa_ctx {
+	enum OID algo_oid; /* overall public key oid */
+	enum OID curve_oid; /* parameter */
+	enum OID digest_oid; /* parameter */
+	const struct ecc_curve *curve; /* curve from oid */
+	unsigned int digest_len; /* parameter (bytes) */
+	const char *digest; /* digest name from oid */
+	unsigned int key_len; /* @key length (bytes) */
+	const char *key; /* raw public key */
+	struct ecc_point pub_key;
+	u64 _pubp[2][ECRDSA_MAX_DIGITS]; /* point storage for @pub_key */
+};
+
+static const struct ecc_curve *get_curve_by_oid(enum OID oid)
+{
+	switch (oid) {
+	case OID_gostCPSignA:
+	case OID_gostTC26Sign256B:
+		return &gost_cp256a;
+	case OID_gostCPSignB:
+	case OID_gostTC26Sign256C:
+		return &gost_cp256b;
+	case OID_gostCPSignC:
+	case OID_gostTC26Sign256D:
+		return &gost_cp256c;
+	case OID_gostTC26Sign512A:
+		return &gost_tc512a;
+	case OID_gostTC26Sign512B:
+		return &gost_tc512b;
+	/* The following two aren't implemented: */
+	case OID_gostTC26Sign256A:
+	case OID_gostTC26Sign512C:
+	default:
+		return NULL;
+	}
+}
+
+static int ecrdsa_verify(struct akcipher_request *req)
+{
+	struct crypto_akcipher *tfm = crypto_akcipher_reqtfm(req);
+	struct ecrdsa_ctx *ctx = akcipher_tfm_ctx(tfm);
+	unsigned char sig[ECRDSA_MAX_SIG_SIZE];
+	unsigned char digest[STREEBOG512_DIGEST_SIZE];
+	unsigned int ndigits = req->dst_len / sizeof(u64);
+	u64 r[ECRDSA_MAX_DIGITS]; /* witness (r) */
+	u64 _r[ECRDSA_MAX_DIGITS]; /* -r */
+	u64 s[ECRDSA_MAX_DIGITS]; /* second part of sig (s) */
+	u64 e[ECRDSA_MAX_DIGITS]; /* h \mod q */
+	u64 *v = e;		  /* e^{-1} \mod q */
+	u64 z1[ECRDSA_MAX_DIGITS];
+	u64 *z2 = _r;
+	struct ecc_point cc = ECC_POINT_INIT(s, e, ndigits); /* reuse s, e */
+
+	/*
+	 * Digest value, digest algorithm, and curve (modulus) should have the
+	 * same length (256 or 512 bits), public key and signature should be
+	 * twice bigger.
+	 */
+	if (!ctx->curve ||
+	    !ctx->digest ||
+	    !req->src ||
+	    !ctx->pub_key.x ||
+	    req->dst_len != ctx->digest_len ||
+	    req->dst_len != ctx->curve->g.ndigits * sizeof(u64) ||
+	    ctx->pub_key.ndigits != ctx->curve->g.ndigits ||
+	    req->dst_len * 2 != req->src_len ||
+	    WARN_ON(req->src_len > sizeof(sig)) ||
+	    WARN_ON(req->dst_len > sizeof(digest)))
+		return -EBADMSG;
+
+	sg_copy_to_buffer(req->src, sg_nents_for_len(req->src, req->src_len),
+			  sig, req->src_len);
+	sg_pcopy_to_buffer(req->src,
+			   sg_nents_for_len(req->src,
+					    req->src_len + req->dst_len),
+			   digest, req->dst_len, req->src_len);
+
+	vli_from_be64(s, sig, ndigits);
+	vli_from_be64(r, sig + ndigits * sizeof(u64), ndigits);
+
+	/* Step 1: verify that 0 < r < q, 0 < s < q */
+	if (vli_is_zero(r, ndigits) ||
+	    vli_cmp(r, ctx->curve->n, ndigits) == 1 ||
+	    vli_is_zero(s, ndigits) ||
+	    vli_cmp(s, ctx->curve->n, ndigits) == 1)
+		return -EKEYREJECTED;
+
+	/* Step 2: calculate hash (h) of the message (passed as input) */
+	/* Step 3: calculate e = h \mod q */
+	vli_from_le64(e, digest, ndigits);
+	if (vli_cmp(e, ctx->curve->n, ndigits) == 1)
+		vli_sub(e, e, ctx->curve->n, ndigits);
+	if (vli_is_zero(e, ndigits))
+		e[0] = 1;
+
+	/* Step 4: calculate v = e^{-1} \mod q */
+	vli_mod_inv(v, e, ctx->curve->n, ndigits);
+
+	/* Step 5: calculate z_1 = sv \mod q, z_2 = -rv \mod q */
+	vli_mod_mult_slow(z1, s, v, ctx->curve->n, ndigits);
+	vli_sub(_r, ctx->curve->n, r, ndigits);
+	vli_mod_mult_slow(z2, _r, v, ctx->curve->n, ndigits);
+
+	/* Step 6: calculate point C = z_1P + z_2Q, and R = x_c \mod q */
+	ecc_point_mult_shamir(&cc, z1, &ctx->curve->g, z2, &ctx->pub_key,
+			      ctx->curve);
+	if (vli_cmp(cc.x, ctx->curve->n, ndigits) == 1)
+		vli_sub(cc.x, cc.x, ctx->curve->n, ndigits);
+
+	/* Step 7: if R == r signature is valid */
+	if (!vli_cmp(cc.x, r, ndigits))
+		return 0;
+	else
+		return -EKEYREJECTED;
+}
+
+int ecrdsa_param_curve(void *context, size_t hdrlen, unsigned char tag,
+		       const void *value, size_t vlen)
+{
+	struct ecrdsa_ctx *ctx = context;
+
+	ctx->curve_oid = look_up_OID(value, vlen);
+	if (!ctx->curve_oid)
+		return -EINVAL;
+	ctx->curve = get_curve_by_oid(ctx->curve_oid);
+	return 0;
+}
+
+/* Optional. If present should match expected digest algo OID. */
+int ecrdsa_param_digest(void *context, size_t hdrlen, unsigned char tag,
+			const void *value, size_t vlen)
+{
+	struct ecrdsa_ctx *ctx = context;
+	int digest_oid = look_up_OID(value, vlen);
+
+	if (digest_oid != ctx->digest_oid)
+		return -EINVAL;
+	return 0;
+}
+
+int ecrdsa_parse_pub_key(void *context, size_t hdrlen, unsigned char tag,
+			 const void *value, size_t vlen)
+{
+	struct ecrdsa_ctx *ctx = context;
+
+	ctx->key = value;
+	ctx->key_len = vlen;
+	return 0;
+}
+
+static u8 *ecrdsa_unpack_u32(u32 *dst, void *src)
+{
+	memcpy(dst, src, sizeof(u32));
+	return src + sizeof(u32);
+}
+
+/* Parse BER encoded subjectPublicKey. */
+static int ecrdsa_set_pub_key(struct crypto_akcipher *tfm, const void *key,
+			      unsigned int keylen)
+{
+	struct ecrdsa_ctx *ctx = akcipher_tfm_ctx(tfm);
+	unsigned int ndigits;
+	u32 algo, paramlen;
+	u8 *params;
+	int err;
+
+	err = asn1_ber_decoder(&ecrdsa_pub_key_decoder, ctx, key, keylen);
+	if (err < 0)
+		return err;
+
+	/* Key parameters is in the key after keylen. */
+	params = ecrdsa_unpack_u32(&paramlen,
+			  ecrdsa_unpack_u32(&algo, (u8 *)key + keylen));
+
+	if (algo == OID_gost2012PKey256) {
+		ctx->digest	= "streebog256";
+		ctx->digest_oid	= OID_gost2012Digest256;
+		ctx->digest_len	= 256 / 8;
+	} else if (algo == OID_gost2012PKey512) {
+		ctx->digest	= "streebog512";
+		ctx->digest_oid	= OID_gost2012Digest512;
+		ctx->digest_len	= 512 / 8;
+	} else
+		return -ENOPKG;
+	ctx->algo_oid = algo;
+
+	/* Parse SubjectPublicKeyInfo.AlgorithmIdentifier.parameters. */
+	err = asn1_ber_decoder(&ecrdsa_params_decoder, ctx, params, paramlen);
+	if (err < 0)
+		return err;
+	/*
+	 * Sizes of algo (set in digest_len) and curve should match
+	 * each other.
+	 */
+	if (!ctx->curve ||
+	    ctx->curve->g.ndigits * sizeof(u64) != ctx->digest_len)
+		return -ENOPKG;
+	/*
+	 * Key is two 256- or 512-bit coordinates which should match
+	 * curve size.
+	 */
+	if ((ctx->key_len != (2 * 256 / 8) &&
+	     ctx->key_len != (2 * 512 / 8)) ||
+	    ctx->key_len != ctx->curve->g.ndigits * sizeof(u64) * 2)
+		return -ENOPKG;
+
+	ndigits = ctx->key_len / sizeof(u64) / 2;
+	ctx->pub_key = ECC_POINT_INIT(ctx->_pubp[0], ctx->_pubp[1], ndigits);
+	vli_from_le64(ctx->pub_key.x, ctx->key, ndigits);
+	vli_from_le64(ctx->pub_key.y, ctx->key + ndigits * sizeof(u64),
+		      ndigits);
+
+	if (ecc_is_pubkey_valid_partial(ctx->curve, &ctx->pub_key))
+		return -EKEYREJECTED;
+
+	return 0;
+}
+
+static unsigned int ecrdsa_max_size(struct crypto_akcipher *tfm)
+{
+	struct ecrdsa_ctx *ctx = akcipher_tfm_ctx(tfm);
+
+	/*
+	 * Verify doesn't need any output, so it's just informational
+	 * for keyctl to determine the key bit size.
+	 */
+	return ctx->pub_key.ndigits * sizeof(u64);
+}
+
+static void ecrdsa_exit_tfm(struct crypto_akcipher *tfm)
+{
+}
+
+static struct akcipher_alg ecrdsa_alg = {
+	.verify		= ecrdsa_verify,
+	.set_pub_key	= ecrdsa_set_pub_key,
+	.max_size	= ecrdsa_max_size,
+	.exit		= ecrdsa_exit_tfm,
+	.base = {
+		.cra_name	 = "ecrdsa",
+		.cra_driver_name = "ecrdsa-generic",
+		.cra_priority	 = 100,
+		.cra_module	 = THIS_MODULE,
+		.cra_ctxsize	 = sizeof(struct ecrdsa_ctx),
+	},
+};
+
+static int __init ecrdsa_mod_init(void)
+{
+	return crypto_register_akcipher(&ecrdsa_alg);
+}
+
+static void __exit ecrdsa_mod_fini(void)
+{
+	crypto_unregister_akcipher(&ecrdsa_alg);
+}
+
+module_init(ecrdsa_mod_init);
+module_exit(ecrdsa_mod_fini);
+
+MODULE_LICENSE("GPL");
+MODULE_AUTHOR("Vitaly Chikunov <vt@altlinux.org>");
+MODULE_DESCRIPTION("EC-RDSA generic algorithm");
+MODULE_ALIAS_CRYPTO("ecrdsa-generic");
diff --git a/crypto/ecrdsa_defs.h b/crypto/ecrdsa_defs.h
new file mode 100644
index 000000000000..170baf039007
--- /dev/null
+++ b/crypto/ecrdsa_defs.h
@@ -0,0 +1,225 @@
+/* SPDX-License-Identifier: GPL-2.0+ */
+/*
+ * Definitions of EC-RDSA Curve Parameters
+ *
+ * Copyright (c) 2019 Vitaly Chikunov <vt@altlinux.org>
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms of the GNU General Public License as published by the Free
+ * Software Foundation; either version 2 of the License, or (at your option)
+ * any later version.
+ */
+
+#ifndef _CRYTO_ECRDSA_DEFS_H
+#define _CRYTO_ECRDSA_DEFS_H
+
+#include "ecc.h"
+
+#define ECRDSA_MAX_SIG_SIZE (2 * 512 / 8)
+#define ECRDSA_MAX_DIGITS (512 / 64)
+
+/*
+ * EC-RDSA uses its own set of curves.
+ *
+ * cp256{a,b,c} curves first defined for GOST R 34.10-2001 in RFC 4357 (as
+ * 256-bit {A,B,C}-ParamSet), but inherited for GOST R 34.10-2012 and
+ * proposed for use in R 50.1.114-2016 and RFC 7836 as the 256-bit curves.
+ */
+/* OID_gostCPSignA 1.2.643.2.2.35.1 */
+static u64 cp256a_g_x[] = {
+	0x0000000000000001ull, 0x0000000000000000ull,
+	0x0000000000000000ull, 0x0000000000000000ull, };
+static u64 cp256a_g_y[] = {
+	0x22ACC99C9E9F1E14ull, 0x35294F2DDF23E3B1ull,
+	0x27DF505A453F2B76ull, 0x8D91E471E0989CDAull, };
+static u64 cp256a_p[] = { /* p = 2^256 - 617 */
+	0xFFFFFFFFFFFFFD97ull, 0xFFFFFFFFFFFFFFFFull,
+	0xFFFFFFFFFFFFFFFFull, 0xFFFFFFFFFFFFFFFFull };
+static u64 cp256a_n[] = {
+	0x45841B09B761B893ull, 0x6C611070995AD100ull,
+	0xFFFFFFFFFFFFFFFFull, 0xFFFFFFFFFFFFFFFFull };
+static u64 cp256a_a[] = { /* a = p - 3 */
+	0xFFFFFFFFFFFFFD94ull, 0xFFFFFFFFFFFFFFFFull,
+	0xFFFFFFFFFFFFFFFFull, 0xFFFFFFFFFFFFFFFFull };
+static u64 cp256a_b[] = {
+	0x00000000000000a6ull, 0x0000000000000000ull,
+	0x0000000000000000ull, 0x0000000000000000ull };
+
+static struct ecc_curve gost_cp256a = {
+	.name = "cp256a",
+	.g = {
+		.x = cp256a_g_x,
+		.y = cp256a_g_y,
+		.ndigits = 256 / 64,
+	},
+	.p = cp256a_p,
+	.n = cp256a_n,
+	.a = cp256a_a,
+	.b = cp256a_b
+};
+
+/* OID_gostCPSignB 1.2.643.2.2.35.2 */
+static u64 cp256b_g_x[] = {
+	0x0000000000000001ull, 0x0000000000000000ull,
+	0x0000000000000000ull, 0x0000000000000000ull, };
+static u64 cp256b_g_y[] = {
+	0x744BF8D717717EFCull, 0xC545C9858D03ECFBull,
+	0xB83D1C3EB2C070E5ull, 0x3FA8124359F96680ull, };
+static u64 cp256b_p[] = { /* p = 2^255 + 3225 */
+	0x0000000000000C99ull, 0x0000000000000000ull,
+	0x0000000000000000ull, 0x8000000000000000ull, };
+static u64 cp256b_n[] = {
+	0xE497161BCC8A198Full, 0x5F700CFFF1A624E5ull,
+	0x0000000000000001ull, 0x8000000000000000ull, };
+static u64 cp256b_a[] = { /* a = p - 3 */
+	0x0000000000000C96ull, 0x0000000000000000ull,
+	0x0000000000000000ull, 0x8000000000000000ull, };
+static u64 cp256b_b[] = {
+	0x2F49D4CE7E1BBC8Bull, 0xE979259373FF2B18ull,
+	0x66A7D3C25C3DF80Aull, 0x3E1AF419A269A5F8ull, };
+
+static struct ecc_curve gost_cp256b = {
+	.name = "cp256b",
+	.g = {
+		.x = cp256b_g_x,
+		.y = cp256b_g_y,
+		.ndigits = 256 / 64,
+	},
+	.p = cp256b_p,
+	.n = cp256b_n,
+	.a = cp256b_a,
+	.b = cp256b_b
+};
+
+/* OID_gostCPSignC 1.2.643.2.2.35.3 */
+static u64 cp256c_g_x[] = {
+	0x0000000000000000ull, 0x0000000000000000ull,
+	0x0000000000000000ull, 0x0000000000000000ull, };
+static u64 cp256c_g_y[] = {
+	0x366E550DFDB3BB67ull, 0x4D4DC440D4641A8Full,
+	0x3CBF3783CD08C0EEull, 0x41ECE55743711A8Cull, };
+static u64 cp256c_p[] = {
+	0x7998F7B9022D759Bull, 0xCF846E86789051D3ull,
+	0xAB1EC85E6B41C8AAull, 0x9B9F605F5A858107ull,
+	/* pre-computed value for Barrett's reduction */
+	0xedc283cdd217b5a2ull, 0xbac48fc06398ae59ull,
+	0x405384d55f9f3b73ull, 0xa51f176161f1d734ull,
+	0x0000000000000001ull, };
+static u64 cp256c_n[] = {
+	0xF02F3A6598980BB9ull, 0x582CA3511EDDFB74ull,
+	0xAB1EC85E6B41C8AAull, 0x9B9F605F5A858107ull, };
+static u64 cp256c_a[] = { /* a = p - 3 */
+	0x7998F7B9022D7598ull, 0xCF846E86789051D3ull,
+	0xAB1EC85E6B41C8AAull, 0x9B9F605F5A858107ull, };
+static u64 cp256c_b[] = {
+	0x000000000000805aull, 0x0000000000000000ull,
+	0x0000000000000000ull, 0x0000000000000000ull, };
+
+static struct ecc_curve gost_cp256c = {
+	.name = "cp256c",
+	.g = {
+		.x = cp256c_g_x,
+		.y = cp256c_g_y,
+		.ndigits = 256 / 64,
+	},
+	.p = cp256c_p,
+	.n = cp256c_n,
+	.a = cp256c_a,
+	.b = cp256c_b
+};
+
+/* tc512{a,b} curves first recommended in 2013 and then standardized in
+ * R 50.1.114-2016 and RFC 7836 for use with GOST R 34.10-2012 (as TC26
+ * 512-bit ParamSet{A,B}).
+ */
+/* OID_gostTC26Sign512A 1.2.643.7.1.2.1.2.1 */
+static u64 tc512a_g_x[] = {
+	0x0000000000000003ull, 0x0000000000000000ull,
+	0x0000000000000000ull, 0x0000000000000000ull,
+	0x0000000000000000ull, 0x0000000000000000ull,
+	0x0000000000000000ull, 0x0000000000000000ull, };
+static u64 tc512a_g_y[] = {
+	0x89A589CB5215F2A4ull, 0x8028FE5FC235F5B8ull,
+	0x3D75E6A50E3A41E9ull, 0xDF1626BE4FD036E9ull,
+	0x778064FDCBEFA921ull, 0xCE5E1C93ACF1ABC1ull,
+	0xA61B8816E25450E6ull, 0x7503CFE87A836AE3ull, };
+static u64 tc512a_p[] = { /* p = 2^512 - 569 */
+	0xFFFFFFFFFFFFFDC7ull, 0xFFFFFFFFFFFFFFFFull,
+	0xFFFFFFFFFFFFFFFFull, 0xFFFFFFFFFFFFFFFFull,
+	0xFFFFFFFFFFFFFFFFull, 0xFFFFFFFFFFFFFFFFull,
+	0xFFFFFFFFFFFFFFFFull, 0xFFFFFFFFFFFFFFFFull, };
+static u64 tc512a_n[] = {
+	0xCACDB1411F10B275ull, 0x9B4B38ABFAD2B85Dull,
+	0x6FF22B8D4E056060ull, 0x27E69532F48D8911ull,
+	0xFFFFFFFFFFFFFFFFull, 0xFFFFFFFFFFFFFFFFull,
+	0xFFFFFFFFFFFFFFFFull, 0xFFFFFFFFFFFFFFFFull, };
+static u64 tc512a_a[] = { /* a = p - 3 */
+	0xFFFFFFFFFFFFFDC4ull, 0xFFFFFFFFFFFFFFFFull,
+	0xFFFFFFFFFFFFFFFFull, 0xFFFFFFFFFFFFFFFFull,
+	0xFFFFFFFFFFFFFFFFull, 0xFFFFFFFFFFFFFFFFull,
+	0xFFFFFFFFFFFFFFFFull, 0xFFFFFFFFFFFFFFFFull, };
+static u64 tc512a_b[] = {
+	0x503190785A71C760ull, 0x862EF9D4EBEE4761ull,
+	0x4CB4574010DA90DDull, 0xEE3CB090F30D2761ull,
+	0x79BD081CFD0B6265ull, 0x34B82574761CB0E8ull,
+	0xC1BD0B2B6667F1DAull, 0xE8C2505DEDFC86DDull, };
+
+static struct ecc_curve gost_tc512a = {
+	.name = "tc512a",
+	.g = {
+		.x = tc512a_g_x,
+		.y = tc512a_g_y,
+		.ndigits = 512 / 64,
+	},
+	.p = tc512a_p,
+	.n = tc512a_n,
+	.a = tc512a_a,
+	.b = tc512a_b
+};
+
+/* OID_gostTC26Sign512B 1.2.643.7.1.2.1.2.2 */
+static u64 tc512b_g_x[] = {
+	0x0000000000000002ull, 0x0000000000000000ull,
+	0x0000000000000000ull, 0x0000000000000000ull,
+	0x0000000000000000ull, 0x0000000000000000ull,
+	0x0000000000000000ull, 0x0000000000000000ull, };
+static u64 tc512b_g_y[] = {
+	0x7E21340780FE41BDull, 0x28041055F94CEEECull,
+	0x152CBCAAF8C03988ull, 0xDCB228FD1EDF4A39ull,
+	0xBE6DD9E6C8EC7335ull, 0x3C123B697578C213ull,
+	0x2C071E3647A8940Full, 0x1A8F7EDA389B094Cull, };
+static u64 tc512b_p[] = { /* p = 2^511 + 111 */
+	0x000000000000006Full, 0x0000000000000000ull,
+	0x0000000000000000ull, 0x0000000000000000ull,
+	0x0000000000000000ull, 0x0000000000000000ull,
+	0x0000000000000000ull, 0x8000000000000000ull, };
+static u64 tc512b_n[] = {
+	0xC6346C54374F25BDull, 0x8B996712101BEA0Eull,
+	0xACFDB77BD9D40CFAull, 0x49A1EC142565A545ull,
+	0x0000000000000001ull, 0x0000000000000000ull,
+	0x0000000000000000ull, 0x8000000000000000ull, };
+static u64 tc512b_a[] = { /* a = p - 3 */
+	0x000000000000006Cull, 0x0000000000000000ull,
+	0x0000000000000000ull, 0x0000000000000000ull,
+	0x0000000000000000ull, 0x0000000000000000ull,
+	0x0000000000000000ull, 0x8000000000000000ull, };
+static u64 tc512b_b[] = {
+	0xFB8CCBC7C5140116ull, 0x50F78BEE1FA3106Eull,
+	0x7F8B276FAD1AB69Cull, 0x3E965D2DB1416D21ull,
+	0xBF85DC806C4B289Full, 0xB97C7D614AF138BCull,
+	0x7E3E06CF6F5E2517ull, 0x687D1B459DC84145ull, };
+
+static struct ecc_curve gost_tc512b = {
+	.name = "tc512b",
+	.g = {
+		.x = tc512b_g_x,
+		.y = tc512b_g_y,
+		.ndigits = 512 / 64,
+	},
+	.p = tc512b_p,
+	.n = tc512b_n,
+	.a = tc512b_a,
+	.b = tc512b_b
+};
+
+#endif
diff --git a/crypto/ecrdsa_params.asn1 b/crypto/ecrdsa_params.asn1
new file mode 100644
index 000000000000..aba99c3763cf
--- /dev/null
+++ b/crypto/ecrdsa_params.asn1
@@ -0,0 +1,4 @@
+EcrdsaParams ::= SEQUENCE {
+	curve	OBJECT IDENTIFIER ({ ecrdsa_param_curve }),
+	digest	OBJECT IDENTIFIER OPTIONAL ({ ecrdsa_param_digest })
+}
diff --git a/crypto/ecrdsa_pub_key.asn1 b/crypto/ecrdsa_pub_key.asn1
new file mode 100644
index 000000000000..048cb646bce4
--- /dev/null
+++ b/crypto/ecrdsa_pub_key.asn1
@@ -0,0 +1 @@
+EcrdsaPubKey ::= OCTET STRING ({ ecrdsa_parse_pub_key })
diff --git a/crypto/fcrypt.c b/crypto/fcrypt.c
index 77286ea28865..4e8704405a3b 100644
--- a/crypto/fcrypt.c
+++ b/crypto/fcrypt.c
@@ -414,7 +414,7 @@ static void __exit fcrypt_mod_fini(void)
 	crypto_unregister_alg(&fcrypt_alg);
 }
 
-module_init(fcrypt_mod_init);
+subsys_initcall(fcrypt_mod_init);
 module_exit(fcrypt_mod_fini);
 
 MODULE_LICENSE("Dual BSD/GPL");
diff --git a/crypto/fips.c b/crypto/fips.c
index 9d627c1cf8bc..9dfed122d6da 100644
--- a/crypto/fips.c
+++ b/crypto/fips.c
@@ -74,5 +74,5 @@ static void __exit fips_exit(void)
 	crypto_proc_fips_exit();
 }
 
-module_init(fips_init);
+subsys_initcall(fips_init);
 module_exit(fips_exit);
diff --git a/crypto/gcm.c b/crypto/gcm.c
index e1a11f529d25..33f45a980967 100644
--- a/crypto/gcm.c
+++ b/crypto/gcm.c
@@ -597,7 +597,6 @@ static void crypto_gcm_free(struct aead_instance *inst)
 
 static int crypto_gcm_create_common(struct crypto_template *tmpl,
 				    struct rtattr **tb,
-				    const char *full_name,
 				    const char *ctr_name,
 				    const char *ghash_name)
 {
@@ -638,7 +637,8 @@ static int crypto_gcm_create_common(struct crypto_template *tmpl,
 		goto err_free_inst;
 
 	err = -EINVAL;
-	if (ghash->digestsize != 16)
+	if (strcmp(ghash->base.cra_name, "ghash") != 0 ||
+	    ghash->digestsize != 16)
 		goto err_drop_ghash;
 
 	crypto_set_skcipher_spawn(&ctx->ctr, aead_crypto_instance(inst));
@@ -650,24 +650,24 @@ static int crypto_gcm_create_common(struct crypto_template *tmpl,
 
 	ctr = crypto_spawn_skcipher_alg(&ctx->ctr);
 
-	/* We only support 16-byte blocks. */
+	/* The skcipher algorithm must be CTR mode, using 16-byte blocks. */
 	err = -EINVAL;
-	if (crypto_skcipher_alg_ivsize(ctr) != 16)
+	if (strncmp(ctr->base.cra_name, "ctr(", 4) != 0 ||
+	    crypto_skcipher_alg_ivsize(ctr) != 16 ||
+	    ctr->base.cra_blocksize != 1)
 		goto out_put_ctr;
 
-	/* Not a stream cipher? */
-	if (ctr->base.cra_blocksize != 1)
+	err = -ENAMETOOLONG;
+	if (snprintf(inst->alg.base.cra_name, CRYPTO_MAX_ALG_NAME,
+		     "gcm(%s", ctr->base.cra_name + 4) >= CRYPTO_MAX_ALG_NAME)
 		goto out_put_ctr;
 
-	err = -ENAMETOOLONG;
 	if (snprintf(inst->alg.base.cra_driver_name, CRYPTO_MAX_ALG_NAME,
 		     "gcm_base(%s,%s)", ctr->base.cra_driver_name,
 		     ghash_alg->cra_driver_name) >=
 	    CRYPTO_MAX_ALG_NAME)
 		goto out_put_ctr;
 
-	memcpy(inst->alg.base.cra_name, full_name, CRYPTO_MAX_ALG_NAME);
-
 	inst->alg.base.cra_flags = (ghash->base.cra_flags |
 				    ctr->base.cra_flags) & CRYPTO_ALG_ASYNC;
 	inst->alg.base.cra_priority = (ghash->base.cra_priority +
@@ -709,7 +709,6 @@ static int crypto_gcm_create(struct crypto_template *tmpl, struct rtattr **tb)
 {
 	const char *cipher_name;
 	char ctr_name[CRYPTO_MAX_ALG_NAME];
-	char full_name[CRYPTO_MAX_ALG_NAME];
 
 	cipher_name = crypto_attr_alg_name(tb[1]);
 	if (IS_ERR(cipher_name))
@@ -719,12 +718,7 @@ static int crypto_gcm_create(struct crypto_template *tmpl, struct rtattr **tb)
 	    CRYPTO_MAX_ALG_NAME)
 		return -ENAMETOOLONG;
 
-	if (snprintf(full_name, CRYPTO_MAX_ALG_NAME, "gcm(%s)", cipher_name) >=
-	    CRYPTO_MAX_ALG_NAME)
-		return -ENAMETOOLONG;
-
-	return crypto_gcm_create_common(tmpl, tb, full_name,
-					ctr_name, "ghash");
+	return crypto_gcm_create_common(tmpl, tb, ctr_name, "ghash");
 }
 
 static int crypto_gcm_base_create(struct crypto_template *tmpl,
@@ -732,7 +726,6 @@ static int crypto_gcm_base_create(struct crypto_template *tmpl,
 {
 	const char *ctr_name;
 	const char *ghash_name;
-	char full_name[CRYPTO_MAX_ALG_NAME];
 
 	ctr_name = crypto_attr_alg_name(tb[1]);
 	if (IS_ERR(ctr_name))
@@ -742,12 +735,7 @@ static int crypto_gcm_base_create(struct crypto_template *tmpl,
 	if (IS_ERR(ghash_name))
 		return PTR_ERR(ghash_name);
 
-	if (snprintf(full_name, CRYPTO_MAX_ALG_NAME, "gcm_base(%s,%s)",
-		     ctr_name, ghash_name) >= CRYPTO_MAX_ALG_NAME)
-		return -ENAMETOOLONG;
-
-	return crypto_gcm_create_common(tmpl, tb, full_name,
-					ctr_name, ghash_name);
+	return crypto_gcm_create_common(tmpl, tb, ctr_name, ghash_name);
 }
 
 static int crypto_rfc4106_setkey(struct crypto_aead *parent, const u8 *key,
@@ -1258,7 +1246,7 @@ static void __exit crypto_gcm_module_exit(void)
 				    ARRAY_SIZE(crypto_gcm_tmpls));
 }
 
-module_init(crypto_gcm_module_init);
+subsys_initcall(crypto_gcm_module_init);
 module_exit(crypto_gcm_module_exit);
 
 MODULE_LICENSE("GPL");
diff --git a/crypto/ghash-generic.c b/crypto/ghash-generic.c
index d9f192b953b2..e6307935413c 100644
--- a/crypto/ghash-generic.c
+++ b/crypto/ghash-generic.c
@@ -149,7 +149,7 @@ static void __exit ghash_mod_exit(void)
 	crypto_unregister_shash(&ghash_alg);
 }
 
-module_init(ghash_mod_init);
+subsys_initcall(ghash_mod_init);
 module_exit(ghash_mod_exit);
 
 MODULE_LICENSE("GPL");
diff --git a/crypto/hmac.c b/crypto/hmac.c
index e74730224f0a..a68c1266121f 100644
--- a/crypto/hmac.c
+++ b/crypto/hmac.c
@@ -57,8 +57,6 @@ static int hmac_setkey(struct crypto_shash *parent,
 	unsigned int i;
 
 	shash->tfm = hash;
-	shash->flags = crypto_shash_get_flags(parent)
-		& CRYPTO_TFM_REQ_MAY_SLEEP;
 
 	if (keylen > bs) {
 		int err;
@@ -91,8 +89,6 @@ static int hmac_export(struct shash_desc *pdesc, void *out)
 {
 	struct shash_desc *desc = shash_desc_ctx(pdesc);
 
-	desc->flags = pdesc->flags & CRYPTO_TFM_REQ_MAY_SLEEP;
-
 	return crypto_shash_export(desc, out);
 }
 
@@ -102,7 +98,6 @@ static int hmac_import(struct shash_desc *pdesc, const void *in)
 	struct hmac_ctx *ctx = hmac_ctx(pdesc->tfm);
 
 	desc->tfm = ctx->hash;
-	desc->flags = pdesc->flags & CRYPTO_TFM_REQ_MAY_SLEEP;
 
 	return crypto_shash_import(desc, in);
 }
@@ -117,8 +112,6 @@ static int hmac_update(struct shash_desc *pdesc,
 {
 	struct shash_desc *desc = shash_desc_ctx(pdesc);
 
-	desc->flags = pdesc->flags & CRYPTO_TFM_REQ_MAY_SLEEP;
-
 	return crypto_shash_update(desc, data, nbytes);
 }
 
@@ -130,8 +123,6 @@ static int hmac_final(struct shash_desc *pdesc, u8 *out)
 	char *opad = crypto_shash_ctx_aligned(parent) + ss;
 	struct shash_desc *desc = shash_desc_ctx(pdesc);
 
-	desc->flags = pdesc->flags & CRYPTO_TFM_REQ_MAY_SLEEP;
-
 	return crypto_shash_final(desc, out) ?:
 	       crypto_shash_import(desc, opad) ?:
 	       crypto_shash_finup(desc, out, ds, out);
@@ -147,8 +138,6 @@ static int hmac_finup(struct shash_desc *pdesc, const u8 *data,
 	char *opad = crypto_shash_ctx_aligned(parent) + ss;
 	struct shash_desc *desc = shash_desc_ctx(pdesc);
 
-	desc->flags = pdesc->flags & CRYPTO_TFM_REQ_MAY_SLEEP;
-
 	return crypto_shash_finup(desc, data, nbytes, out) ?:
 	       crypto_shash_import(desc, opad) ?:
 	       crypto_shash_finup(desc, out, ds, out);
@@ -268,7 +257,7 @@ static void __exit hmac_module_exit(void)
 	crypto_unregister_template(&hmac_tmpl);
 }
 
-module_init(hmac_module_init);
+subsys_initcall(hmac_module_init);
 module_exit(hmac_module_exit);
 
 MODULE_LICENSE("GPL");
diff --git a/crypto/jitterentropy-kcapi.c b/crypto/jitterentropy-kcapi.c
index 787dccca3715..6ea1a270b8dc 100644
--- a/crypto/jitterentropy-kcapi.c
+++ b/crypto/jitterentropy-kcapi.c
@@ -198,7 +198,7 @@ static void __exit jent_mod_exit(void)
 	crypto_unregister_rng(&jent_alg);
 }
 
-module_init(jent_mod_init);
+subsys_initcall(jent_mod_init);
 module_exit(jent_mod_exit);
 
 MODULE_LICENSE("Dual BSD/GPL");
diff --git a/crypto/keywrap.c b/crypto/keywrap.c
index a5cfe610d8f4..a155c88105ea 100644
--- a/crypto/keywrap.c
+++ b/crypto/keywrap.c
@@ -310,7 +310,7 @@ static void __exit crypto_kw_exit(void)
 	crypto_unregister_template(&crypto_kw_tmpl);
 }
 
-module_init(crypto_kw_init);
+subsys_initcall(crypto_kw_init);
 module_exit(crypto_kw_exit);
 
 MODULE_LICENSE("Dual BSD/GPL");
diff --git a/crypto/khazad.c b/crypto/khazad.c
index 873eb5ded6d7..b50aa8a3ab4c 100644
--- a/crypto/khazad.c
+++ b/crypto/khazad.c
@@ -875,7 +875,7 @@ static void __exit khazad_mod_fini(void)
 }
 
 
-module_init(khazad_mod_init);
+subsys_initcall(khazad_mod_init);
 module_exit(khazad_mod_fini);
 
 MODULE_LICENSE("GPL");
diff --git a/crypto/lrw.c b/crypto/lrw.c
index 0430ccd08728..fa302f3f161e 100644
--- a/crypto/lrw.c
+++ b/crypto/lrw.c
@@ -162,8 +162,10 @@ static int xor_tweak(struct skcipher_request *req, bool second_pass)
 	}
 
 	err = skcipher_walk_virt(&w, req, false);
-	iv = (__be32 *)w.iv;
+	if (err)
+		return err;
 
+	iv = (__be32 *)w.iv;
 	counter[0] = be32_to_cpu(iv[3]);
 	counter[1] = be32_to_cpu(iv[2]);
 	counter[2] = be32_to_cpu(iv[1]);
@@ -212,8 +214,12 @@ static void crypt_done(struct crypto_async_request *areq, int err)
 {
 	struct skcipher_request *req = areq->data;
 
-	if (!err)
+	if (!err) {
+		struct rctx *rctx = skcipher_request_ctx(req);
+
+		rctx->subreq.base.flags &= ~CRYPTO_TFM_REQ_MAY_SLEEP;
 		err = xor_tweak_post(req);
+	}
 
 	skcipher_request_complete(req, err);
 }
@@ -431,7 +437,7 @@ static void __exit crypto_module_exit(void)
 	crypto_unregister_template(&crypto_tmpl);
 }
 
-module_init(crypto_module_init);
+subsys_initcall(crypto_module_init);
 module_exit(crypto_module_exit);
 
 MODULE_LICENSE("GPL");
diff --git a/crypto/lz4.c b/crypto/lz4.c
index c160dfdbf2e0..1e35134d0a98 100644
--- a/crypto/lz4.c
+++ b/crypto/lz4.c
@@ -164,7 +164,7 @@ static void __exit lz4_mod_fini(void)
 	crypto_unregister_scomp(&scomp);
 }
 
-module_init(lz4_mod_init);
+subsys_initcall(lz4_mod_init);
 module_exit(lz4_mod_fini);
 
 MODULE_LICENSE("GPL");
diff --git a/crypto/lz4hc.c b/crypto/lz4hc.c
index 583b5e013d7a..4a220b628fe7 100644
--- a/crypto/lz4hc.c
+++ b/crypto/lz4hc.c
@@ -165,7 +165,7 @@ static void __exit lz4hc_mod_fini(void)
 	crypto_unregister_scomp(&scomp);
 }
 
-module_init(lz4hc_mod_init);
+subsys_initcall(lz4hc_mod_init);
 module_exit(lz4hc_mod_fini);
 
 MODULE_LICENSE("GPL");
diff --git a/crypto/lzo-rle.c b/crypto/lzo-rle.c
index ea9c75b1db49..4c82bf18440f 100644
--- a/crypto/lzo-rle.c
+++ b/crypto/lzo-rle.c
@@ -167,7 +167,7 @@ static void __exit lzorle_mod_fini(void)
 	crypto_unregister_scomp(&scomp);
 }
 
-module_init(lzorle_mod_init);
+subsys_initcall(lzorle_mod_init);
 module_exit(lzorle_mod_fini);
 
 MODULE_LICENSE("GPL");
diff --git a/crypto/lzo.c b/crypto/lzo.c
index 218567d717d6..4a6ac8f247d0 100644
--- a/crypto/lzo.c
+++ b/crypto/lzo.c
@@ -167,7 +167,7 @@ static void __exit lzo_mod_fini(void)
 	crypto_unregister_scomp(&scomp);
 }
 
-module_init(lzo_mod_init);
+subsys_initcall(lzo_mod_init);
 module_exit(lzo_mod_fini);
 
 MODULE_LICENSE("GPL");
diff --git a/crypto/md4.c b/crypto/md4.c
index 9965ec40d9f9..9a1a228a0c69 100644
--- a/crypto/md4.c
+++ b/crypto/md4.c
@@ -232,7 +232,7 @@ static void __exit md4_mod_fini(void)
 	crypto_unregister_shash(&alg);
 }
 
-module_init(md4_mod_init);
+subsys_initcall(md4_mod_init);
 module_exit(md4_mod_fini);
 
 MODULE_LICENSE("GPL");
diff --git a/crypto/md5.c b/crypto/md5.c
index 94dd78144ba3..221c2c0932f8 100644
--- a/crypto/md5.c
+++ b/crypto/md5.c
@@ -244,7 +244,7 @@ static void __exit md5_mod_fini(void)
 	crypto_unregister_shash(&alg);
 }
 
-module_init(md5_mod_init);
+subsys_initcall(md5_mod_init);
 module_exit(md5_mod_fini);
 
 MODULE_LICENSE("GPL");
diff --git a/crypto/michael_mic.c b/crypto/michael_mic.c
index 46195e0d0f4d..538ae7933795 100644
--- a/crypto/michael_mic.c
+++ b/crypto/michael_mic.c
@@ -178,7 +178,7 @@ static void __exit michael_mic_exit(void)
 }
 
 
-module_init(michael_mic_init);
+subsys_initcall(michael_mic_init);
 module_exit(michael_mic_exit);
 
 MODULE_LICENSE("GPL v2");
diff --git a/crypto/morus1280.c b/crypto/morus1280.c
index 0747732d5b78..f8734c6576af 100644
--- a/crypto/morus1280.c
+++ b/crypto/morus1280.c
@@ -532,7 +532,7 @@ static void __exit crypto_morus1280_module_exit(void)
 	crypto_unregister_aead(&crypto_morus1280_alg);
 }
 
-module_init(crypto_morus1280_module_init);
+subsys_initcall(crypto_morus1280_module_init);
 module_exit(crypto_morus1280_module_exit);
 
 MODULE_LICENSE("GPL");
diff --git a/crypto/morus640.c b/crypto/morus640.c
index 1617a1eb8be1..ae5aa9482cb4 100644
--- a/crypto/morus640.c
+++ b/crypto/morus640.c
@@ -523,7 +523,7 @@ static void __exit crypto_morus640_module_exit(void)
 	crypto_unregister_aead(&crypto_morus640_alg);
 }
 
-module_init(crypto_morus640_module_init);
+subsys_initcall(crypto_morus640_module_init);
 module_exit(crypto_morus640_module_exit);
 
 MODULE_LICENSE("GPL");
diff --git a/crypto/nhpoly1305.c b/crypto/nhpoly1305.c
index ec831a5594d8..9ab4e07cde4d 100644
--- a/crypto/nhpoly1305.c
+++ b/crypto/nhpoly1305.c
@@ -244,7 +244,7 @@ static void __exit nhpoly1305_mod_exit(void)
 	crypto_unregister_shash(&nhpoly1305_alg);
 }
 
-module_init(nhpoly1305_mod_init);
+subsys_initcall(nhpoly1305_mod_init);
 module_exit(nhpoly1305_mod_exit);
 
 MODULE_DESCRIPTION("NHPoly1305 ε-almost-∆-universal hash function");
diff --git a/crypto/ofb.c b/crypto/ofb.c
index 34b6e1f426f7..133ff4c7f2c6 100644
--- a/crypto/ofb.c
+++ b/crypto/ofb.c
@@ -95,7 +95,7 @@ static void __exit crypto_ofb_module_exit(void)
 	crypto_unregister_template(&crypto_ofb_tmpl);
 }
 
-module_init(crypto_ofb_module_init);
+subsys_initcall(crypto_ofb_module_init);
 module_exit(crypto_ofb_module_exit);
 
 MODULE_LICENSE("GPL");
diff --git a/crypto/pcbc.c b/crypto/pcbc.c
index 2fa03fc576fe..31b3ce948474 100644
--- a/crypto/pcbc.c
+++ b/crypto/pcbc.c
@@ -191,7 +191,7 @@ static void __exit crypto_pcbc_module_exit(void)
 	crypto_unregister_template(&crypto_pcbc_tmpl);
 }
 
-module_init(crypto_pcbc_module_init);
+subsys_initcall(crypto_pcbc_module_init);
 module_exit(crypto_pcbc_module_exit);
 
 MODULE_LICENSE("GPL");
diff --git a/crypto/pcrypt.c b/crypto/pcrypt.c
index d47cfc47b1b1..0e9ce329fd47 100644
--- a/crypto/pcrypt.c
+++ b/crypto/pcrypt.c
@@ -512,7 +512,7 @@ static void __exit pcrypt_exit(void)
 	crypto_unregister_template(&pcrypt_tmpl);
 }
 
-module_init(pcrypt_init);
+subsys_initcall(pcrypt_init);
 module_exit(pcrypt_exit);
 
 MODULE_LICENSE("GPL");
diff --git a/crypto/poly1305_generic.c b/crypto/poly1305_generic.c
index 2a06874204e8..adc40298c749 100644
--- a/crypto/poly1305_generic.c
+++ b/crypto/poly1305_generic.c
@@ -318,7 +318,7 @@ static void __exit poly1305_mod_exit(void)
 	crypto_unregister_shash(&poly1305_alg);
 }
 
-module_init(poly1305_mod_init);
+subsys_initcall(poly1305_mod_init);
 module_exit(poly1305_mod_exit);
 
 MODULE_LICENSE("GPL");
diff --git a/crypto/rmd128.c b/crypto/rmd128.c
index 5f4472256e27..faf4252c4b85 100644
--- a/crypto/rmd128.c
+++ b/crypto/rmd128.c
@@ -318,7 +318,7 @@ static void __exit rmd128_mod_fini(void)
 	crypto_unregister_shash(&alg);
 }
 
-module_init(rmd128_mod_init);
+subsys_initcall(rmd128_mod_init);
 module_exit(rmd128_mod_fini);
 
 MODULE_LICENSE("GPL");
diff --git a/crypto/rmd160.c b/crypto/rmd160.c
index 737645344d1c..b33309916d4f 100644
--- a/crypto/rmd160.c
+++ b/crypto/rmd160.c
@@ -362,7 +362,7 @@ static void __exit rmd160_mod_fini(void)
 	crypto_unregister_shash(&alg);
 }
 
-module_init(rmd160_mod_init);
+subsys_initcall(rmd160_mod_init);
 module_exit(rmd160_mod_fini);
 
 MODULE_LICENSE("GPL");
diff --git a/crypto/rmd256.c b/crypto/rmd256.c
index 0e9d30676a01..2a643250c9a5 100644
--- a/crypto/rmd256.c
+++ b/crypto/rmd256.c
@@ -337,7 +337,7 @@ static void __exit rmd256_mod_fini(void)
 	crypto_unregister_shash(&alg);
 }
 
-module_init(rmd256_mod_init);
+subsys_initcall(rmd256_mod_init);
 module_exit(rmd256_mod_fini);
 
 MODULE_LICENSE("GPL");
diff --git a/crypto/rmd320.c b/crypto/rmd320.c
index 3ae1df5bb48c..2f062574fc8c 100644
--- a/crypto/rmd320.c
+++ b/crypto/rmd320.c
@@ -386,7 +386,7 @@ static void __exit rmd320_mod_fini(void)
 	crypto_unregister_shash(&alg);
 }
 
-module_init(rmd320_mod_init);
+subsys_initcall(rmd320_mod_init);
 module_exit(rmd320_mod_fini);
 
 MODULE_LICENSE("GPL");
diff --git a/crypto/rsa-pkcs1pad.c b/crypto/rsa-pkcs1pad.c
index 0a6680ca8cb6..29c336068dc0 100644
--- a/crypto/rsa-pkcs1pad.c
+++ b/crypto/rsa-pkcs1pad.c
@@ -429,7 +429,7 @@ static int pkcs1pad_sign(struct akcipher_request *req)
 	akcipher_request_set_crypt(&req_ctx->child_req, req_ctx->in_sg,
 				   req->dst, ctx->key_size - 1, req->dst_len);
 
-	err = crypto_akcipher_sign(&req_ctx->child_req);
+	err = crypto_akcipher_decrypt(&req_ctx->child_req);
 	if (err != -EINPROGRESS && err != -EBUSY)
 		return pkcs1pad_encrypt_sign_complete(req, err);
 
@@ -488,14 +488,21 @@ static int pkcs1pad_verify_complete(struct akcipher_request *req, int err)
 
 	err = 0;
 
-	if (req->dst_len < dst_len - pos)
-		err = -EOVERFLOW;
-	req->dst_len = dst_len - pos;
-
-	if (!err)
-		sg_copy_from_buffer(req->dst,
-				sg_nents_for_len(req->dst, req->dst_len),
-				out_buf + pos, req->dst_len);
+	if (req->dst_len != dst_len - pos) {
+		err = -EKEYREJECTED;
+		req->dst_len = dst_len - pos;
+		goto done;
+	}
+	/* Extract appended digest. */
+	sg_pcopy_to_buffer(req->src,
+			   sg_nents_for_len(req->src,
+					    req->src_len + req->dst_len),
+			   req_ctx->out_buf + ctx->key_size,
+			   req->dst_len, ctx->key_size);
+	/* Do the actual verification step. */
+	if (memcmp(req_ctx->out_buf + ctx->key_size, out_buf + pos,
+		   req->dst_len) != 0)
+		err = -EKEYREJECTED;
 done:
 	kzfree(req_ctx->out_buf);
 
@@ -532,10 +539,12 @@ static int pkcs1pad_verify(struct akcipher_request *req)
 	struct pkcs1pad_request *req_ctx = akcipher_request_ctx(req);
 	int err;
 
-	if (!ctx->key_size || req->src_len < ctx->key_size)
+	if (WARN_ON(req->dst) ||
+	    WARN_ON(!req->dst_len) ||
+	    !ctx->key_size || req->src_len < ctx->key_size)
 		return -EINVAL;
 
-	req_ctx->out_buf = kmalloc(ctx->key_size, GFP_KERNEL);
+	req_ctx->out_buf = kmalloc(ctx->key_size + req->dst_len, GFP_KERNEL);
 	if (!req_ctx->out_buf)
 		return -ENOMEM;
 
@@ -551,7 +560,7 @@ static int pkcs1pad_verify(struct akcipher_request *req)
 				   req_ctx->out_sg, req->src_len,
 				   ctx->key_size);
 
-	err = crypto_akcipher_verify(&req_ctx->child_req);
+	err = crypto_akcipher_encrypt(&req_ctx->child_req);
 	if (err != -EINPROGRESS && err != -EBUSY)
 		return pkcs1pad_verify_complete(req, err);
 
diff --git a/crypto/rsa.c b/crypto/rsa.c
index 4167980c243d..dcbb03431778 100644
--- a/crypto/rsa.c
+++ b/crypto/rsa.c
@@ -50,34 +50,6 @@ static int _rsa_dec(const struct rsa_mpi_key *key, MPI m, MPI c)
 	return mpi_powm(m, c, key->d, key->n);
 }
 
-/*
- * RSASP1 function [RFC3447 sec 5.2.1]
- * s = m^d mod n
- */
-static int _rsa_sign(const struct rsa_mpi_key *key, MPI s, MPI m)
-{
-	/* (1) Validate 0 <= m < n */
-	if (mpi_cmp_ui(m, 0) < 0 || mpi_cmp(m, key->n) >= 0)
-		return -EINVAL;
-
-	/* (2) s = m^d mod n */
-	return mpi_powm(s, m, key->d, key->n);
-}
-
-/*
- * RSAVP1 function [RFC3447 sec 5.2.2]
- * m = s^e mod n;
- */
-static int _rsa_verify(const struct rsa_mpi_key *key, MPI m, MPI s)
-{
-	/* (1) Validate 0 <= s < n */
-	if (mpi_cmp_ui(s, 0) < 0 || mpi_cmp(s, key->n) >= 0)
-		return -EINVAL;
-
-	/* (2) m = s^e mod n */
-	return mpi_powm(m, s, key->e, key->n);
-}
-
 static inline struct rsa_mpi_key *rsa_get_key(struct crypto_akcipher *tfm)
 {
 	return akcipher_tfm_ctx(tfm);
@@ -160,85 +132,6 @@ err_free_m:
 	return ret;
 }
 
-static int rsa_sign(struct akcipher_request *req)
-{
-	struct crypto_akcipher *tfm = crypto_akcipher_reqtfm(req);
-	const struct rsa_mpi_key *pkey = rsa_get_key(tfm);
-	MPI m, s = mpi_alloc(0);
-	int ret = 0;
-	int sign;
-
-	if (!s)
-		return -ENOMEM;
-
-	if (unlikely(!pkey->n || !pkey->d)) {
-		ret = -EINVAL;
-		goto err_free_s;
-	}
-
-	ret = -ENOMEM;
-	m = mpi_read_raw_from_sgl(req->src, req->src_len);
-	if (!m)
-		goto err_free_s;
-
-	ret = _rsa_sign(pkey, s, m);
-	if (ret)
-		goto err_free_m;
-
-	ret = mpi_write_to_sgl(s, req->dst, req->dst_len, &sign);
-	if (ret)
-		goto err_free_m;
-
-	if (sign < 0)
-		ret = -EBADMSG;
-
-err_free_m:
-	mpi_free(m);
-err_free_s:
-	mpi_free(s);
-	return ret;
-}
-
-static int rsa_verify(struct akcipher_request *req)
-{
-	struct crypto_akcipher *tfm = crypto_akcipher_reqtfm(req);
-	const struct rsa_mpi_key *pkey = rsa_get_key(tfm);
-	MPI s, m = mpi_alloc(0);
-	int ret = 0;
-	int sign;
-
-	if (!m)
-		return -ENOMEM;
-
-	if (unlikely(!pkey->n || !pkey->e)) {
-		ret = -EINVAL;
-		goto err_free_m;
-	}
-
-	s = mpi_read_raw_from_sgl(req->src, req->src_len);
-	if (!s) {
-		ret = -ENOMEM;
-		goto err_free_m;
-	}
-
-	ret = _rsa_verify(pkey, m, s);
-	if (ret)
-		goto err_free_s;
-
-	ret = mpi_write_to_sgl(m, req->dst, req->dst_len, &sign);
-	if (ret)
-		goto err_free_s;
-
-	if (sign < 0)
-		ret = -EBADMSG;
-
-err_free_s:
-	mpi_free(s);
-err_free_m:
-	mpi_free(m);
-	return ret;
-}
-
 static void rsa_free_mpi_key(struct rsa_mpi_key *key)
 {
 	mpi_free(key->d);
@@ -353,8 +246,6 @@ static void rsa_exit_tfm(struct crypto_akcipher *tfm)
 static struct akcipher_alg rsa = {
 	.encrypt = rsa_enc,
 	.decrypt = rsa_dec,
-	.sign = rsa_sign,
-	.verify = rsa_verify,
 	.set_priv_key = rsa_set_priv_key,
 	.set_pub_key = rsa_set_pub_key,
 	.max_size = rsa_max_size,
@@ -391,7 +282,7 @@ static void rsa_exit(void)
 	crypto_unregister_akcipher(&rsa);
 }
 
-module_init(rsa_init);
+subsys_initcall(rsa_init);
 module_exit(rsa_exit);
 MODULE_ALIAS_CRYPTO("rsa");
 MODULE_LICENSE("GPL");
diff --git a/crypto/salsa20_generic.c b/crypto/salsa20_generic.c
index 00fce32ae17a..c81a44404086 100644
--- a/crypto/salsa20_generic.c
+++ b/crypto/salsa20_generic.c
@@ -86,18 +86,17 @@ static void salsa20_docrypt(u32 *state, u8 *dst, const u8 *src,
 {
 	__le32 stream[SALSA20_BLOCK_SIZE / sizeof(__le32)];
 
-	if (dst != src)
-		memcpy(dst, src, bytes);
-
 	while (bytes >= SALSA20_BLOCK_SIZE) {
 		salsa20_block(state, stream);
-		crypto_xor(dst, (const u8 *)stream, SALSA20_BLOCK_SIZE);
+		crypto_xor_cpy(dst, src, (const u8 *)stream,
+			       SALSA20_BLOCK_SIZE);
 		bytes -= SALSA20_BLOCK_SIZE;
 		dst += SALSA20_BLOCK_SIZE;
+		src += SALSA20_BLOCK_SIZE;
 	}
 	if (bytes) {
 		salsa20_block(state, stream);
-		crypto_xor(dst, (const u8 *)stream, bytes);
+		crypto_xor_cpy(dst, src, (const u8 *)stream, bytes);
 	}
 }
 
@@ -161,7 +160,7 @@ static int salsa20_crypt(struct skcipher_request *req)
 
 	err = skcipher_walk_virt(&walk, req, false);
 
-	salsa20_init(state, ctx, walk.iv);
+	salsa20_init(state, ctx, req->iv);
 
 	while (walk.nbytes > 0) {
 		unsigned int nbytes = walk.nbytes;
@@ -204,7 +203,7 @@ static void __exit salsa20_generic_mod_fini(void)
 	crypto_unregister_skcipher(&alg);
 }
 
-module_init(salsa20_generic_mod_init);
+subsys_initcall(salsa20_generic_mod_init);
 module_exit(salsa20_generic_mod_fini);
 
 MODULE_LICENSE("GPL");
diff --git a/crypto/scompress.c b/crypto/scompress.c
index 6f8305f8c300..712b4c2ea021 100644
--- a/crypto/scompress.c
+++ b/crypto/scompress.c
@@ -29,9 +29,17 @@
 #include <crypto/internal/scompress.h>
 #include "internal.h"
 
+struct scomp_scratch {
+	spinlock_t	lock;
+	void		*src;
+	void		*dst;
+};
+
+static DEFINE_PER_CPU(struct scomp_scratch, scomp_scratch) = {
+	.lock = __SPIN_LOCK_UNLOCKED(scomp_scratch.lock),
+};
+
 static const struct crypto_type crypto_scomp_type;
-static void * __percpu *scomp_src_scratches;
-static void * __percpu *scomp_dst_scratches;
 static int scomp_scratch_users;
 static DEFINE_MUTEX(scomp_lock);
 
@@ -62,76 +70,53 @@ static void crypto_scomp_show(struct seq_file *m, struct crypto_alg *alg)
 	seq_puts(m, "type         : scomp\n");
 }
 
-static void crypto_scomp_free_scratches(void * __percpu *scratches)
+static void crypto_scomp_free_scratches(void)
 {
+	struct scomp_scratch *scratch;
 	int i;
 
-	if (!scratches)
-		return;
-
-	for_each_possible_cpu(i)
-		vfree(*per_cpu_ptr(scratches, i));
+	for_each_possible_cpu(i) {
+		scratch = per_cpu_ptr(&scomp_scratch, i);
 
-	free_percpu(scratches);
+		vfree(scratch->src);
+		vfree(scratch->dst);
+		scratch->src = NULL;
+		scratch->dst = NULL;
+	}
 }
 
-static void * __percpu *crypto_scomp_alloc_scratches(void)
+static int crypto_scomp_alloc_scratches(void)
 {
-	void * __percpu *scratches;
+	struct scomp_scratch *scratch;
 	int i;
 
-	scratches = alloc_percpu(void *);
-	if (!scratches)
-		return NULL;
-
 	for_each_possible_cpu(i) {
-		void *scratch;
-
-		scratch = vmalloc_node(SCOMP_SCRATCH_SIZE, cpu_to_node(i));
-		if (!scratch)
-			goto error;
-		*per_cpu_ptr(scratches, i) = scratch;
-	}
-
-	return scratches;
-
-error:
-	crypto_scomp_free_scratches(scratches);
-	return NULL;
-}
+		void *mem;
 
-static void crypto_scomp_free_all_scratches(void)
-{
-	if (!--scomp_scratch_users) {
-		crypto_scomp_free_scratches(scomp_src_scratches);
-		crypto_scomp_free_scratches(scomp_dst_scratches);
-		scomp_src_scratches = NULL;
-		scomp_dst_scratches = NULL;
-	}
-}
+		scratch = per_cpu_ptr(&scomp_scratch, i);
 
-static int crypto_scomp_alloc_all_scratches(void)
-{
-	if (!scomp_scratch_users++) {
-		scomp_src_scratches = crypto_scomp_alloc_scratches();
-		if (!scomp_src_scratches)
-			return -ENOMEM;
-		scomp_dst_scratches = crypto_scomp_alloc_scratches();
-		if (!scomp_dst_scratches) {
-			crypto_scomp_free_scratches(scomp_src_scratches);
-			scomp_src_scratches = NULL;
-			return -ENOMEM;
-		}
+		mem = vmalloc_node(SCOMP_SCRATCH_SIZE, cpu_to_node(i));
+		if (!mem)
+			goto error;
+		scratch->src = mem;
+		mem = vmalloc_node(SCOMP_SCRATCH_SIZE, cpu_to_node(i));
+		if (!mem)
+			goto error;
+		scratch->dst = mem;
 	}
 	return 0;
+error:
+	crypto_scomp_free_scratches();
+	return -ENOMEM;
 }
 
 static int crypto_scomp_init_tfm(struct crypto_tfm *tfm)
 {
-	int ret;
+	int ret = 0;
 
 	mutex_lock(&scomp_lock);
-	ret = crypto_scomp_alloc_all_scratches();
+	if (!scomp_scratch_users++)
+		ret = crypto_scomp_alloc_scratches();
 	mutex_unlock(&scomp_lock);
 
 	return ret;
@@ -143,42 +128,41 @@ static int scomp_acomp_comp_decomp(struct acomp_req *req, int dir)
 	void **tfm_ctx = acomp_tfm_ctx(tfm);
 	struct crypto_scomp *scomp = *tfm_ctx;
 	void **ctx = acomp_request_ctx(req);
-	const int cpu = get_cpu();
-	u8 *scratch_src = *per_cpu_ptr(scomp_src_scratches, cpu);
-	u8 *scratch_dst = *per_cpu_ptr(scomp_dst_scratches, cpu);
+	struct scomp_scratch *scratch;
 	int ret;
 
-	if (!req->src || !req->slen || req->slen > SCOMP_SCRATCH_SIZE) {
-		ret = -EINVAL;
-		goto out;
-	}
+	if (!req->src || !req->slen || req->slen > SCOMP_SCRATCH_SIZE)
+		return -EINVAL;
 
-	if (req->dst && !req->dlen) {
-		ret = -EINVAL;
-		goto out;
-	}
+	if (req->dst && !req->dlen)
+		return -EINVAL;
 
 	if (!req->dlen || req->dlen > SCOMP_SCRATCH_SIZE)
 		req->dlen = SCOMP_SCRATCH_SIZE;
 
-	scatterwalk_map_and_copy(scratch_src, req->src, 0, req->slen, 0);
+	scratch = raw_cpu_ptr(&scomp_scratch);
+	spin_lock(&scratch->lock);
+
+	scatterwalk_map_and_copy(scratch->src, req->src, 0, req->slen, 0);
 	if (dir)
-		ret = crypto_scomp_compress(scomp, scratch_src, req->slen,
-					    scratch_dst, &req->dlen, *ctx);
+		ret = crypto_scomp_compress(scomp, scratch->src, req->slen,
+					    scratch->dst, &req->dlen, *ctx);
 	else
-		ret = crypto_scomp_decompress(scomp, scratch_src, req->slen,
-					      scratch_dst, &req->dlen, *ctx);
+		ret = crypto_scomp_decompress(scomp, scratch->src, req->slen,
+					      scratch->dst, &req->dlen, *ctx);
 	if (!ret) {
 		if (!req->dst) {
 			req->dst = sgl_alloc(req->dlen, GFP_ATOMIC, NULL);
-			if (!req->dst)
+			if (!req->dst) {
+				ret = -ENOMEM;
 				goto out;
+			}
 		}
-		scatterwalk_map_and_copy(scratch_dst, req->dst, 0, req->dlen,
+		scatterwalk_map_and_copy(scratch->dst, req->dst, 0, req->dlen,
 					 1);
 	}
 out:
-	put_cpu();
+	spin_unlock(&scratch->lock);
 	return ret;
 }
 
@@ -199,7 +183,8 @@ static void crypto_exit_scomp_ops_async(struct crypto_tfm *tfm)
 	crypto_free_scomp(*ctx);
 
 	mutex_lock(&scomp_lock);
-	crypto_scomp_free_all_scratches();
+	if (!--scomp_scratch_users)
+		crypto_scomp_free_scratches();
 	mutex_unlock(&scomp_lock);
 }
 
diff --git a/crypto/seed.c b/crypto/seed.c
index c6ba8438be43..a75ac50fa4fd 100644
--- a/crypto/seed.c
+++ b/crypto/seed.c
@@ -470,7 +470,7 @@ static void __exit seed_fini(void)
 	crypto_unregister_alg(&seed_alg);
 }
 
-module_init(seed_init);
+subsys_initcall(seed_init);
 module_exit(seed_fini);
 
 MODULE_DESCRIPTION("SEED Cipher Algorithm");
diff --git a/crypto/seqiv.c b/crypto/seqiv.c
index ed1b0e9f2436..3f2fad615d26 100644
--- a/crypto/seqiv.c
+++ b/crypto/seqiv.c
@@ -211,7 +211,7 @@ static void __exit seqiv_module_exit(void)
 	crypto_unregister_template(&seqiv_tmpl);
 }
 
-module_init(seqiv_module_init);
+subsys_initcall(seqiv_module_init);
 module_exit(seqiv_module_exit);
 
 MODULE_LICENSE("GPL");
diff --git a/crypto/serpent_generic.c b/crypto/serpent_generic.c
index 7c3382facc82..ec4ec89ad108 100644
--- a/crypto/serpent_generic.c
+++ b/crypto/serpent_generic.c
@@ -664,7 +664,7 @@ static void __exit serpent_mod_fini(void)
 	crypto_unregister_algs(srp_algs, ARRAY_SIZE(srp_algs));
 }
 
-module_init(serpent_mod_init);
+subsys_initcall(serpent_mod_init);
 module_exit(serpent_mod_fini);
 
 MODULE_LICENSE("GPL");
diff --git a/crypto/sha1_generic.c b/crypto/sha1_generic.c
index 2af64ef81f40..1b806d4584b2 100644
--- a/crypto/sha1_generic.c
+++ b/crypto/sha1_generic.c
@@ -92,7 +92,7 @@ static void __exit sha1_generic_mod_fini(void)
 	crypto_unregister_shash(&alg);
 }
 
-module_init(sha1_generic_mod_init);
+subsys_initcall(sha1_generic_mod_init);
 module_exit(sha1_generic_mod_fini);
 
 MODULE_LICENSE("GPL");
diff --git a/crypto/sha256_generic.c b/crypto/sha256_generic.c
index 1e5ba6649e8d..5844e9a469e8 100644
--- a/crypto/sha256_generic.c
+++ b/crypto/sha256_generic.c
@@ -301,7 +301,7 @@ static void __exit sha256_generic_mod_fini(void)
 	crypto_unregister_shashes(sha256_algs, ARRAY_SIZE(sha256_algs));
 }
 
-module_init(sha256_generic_mod_init);
+subsys_initcall(sha256_generic_mod_init);
 module_exit(sha256_generic_mod_fini);
 
 MODULE_LICENSE("GPL");
diff --git a/crypto/sha3_generic.c b/crypto/sha3_generic.c
index 7ed98367d4fb..60fd2be609d8 100644
--- a/crypto/sha3_generic.c
+++ b/crypto/sha3_generic.c
@@ -294,7 +294,7 @@ static void __exit sha3_generic_mod_fini(void)
 	crypto_unregister_shashes(algs, ARRAY_SIZE(algs));
 }
 
-module_init(sha3_generic_mod_init);
+subsys_initcall(sha3_generic_mod_init);
 module_exit(sha3_generic_mod_fini);
 
 MODULE_LICENSE("GPL");
diff --git a/crypto/sha512_generic.c b/crypto/sha512_generic.c
index 4097cd555eb6..0193ecb8ae10 100644
--- a/crypto/sha512_generic.c
+++ b/crypto/sha512_generic.c
@@ -223,7 +223,7 @@ static void __exit sha512_generic_mod_fini(void)
 	crypto_unregister_shashes(sha512_algs, ARRAY_SIZE(sha512_algs));
 }
 
-module_init(sha512_generic_mod_init);
+subsys_initcall(sha512_generic_mod_init);
 module_exit(sha512_generic_mod_fini);
 
 MODULE_LICENSE("GPL");
diff --git a/crypto/shash.c b/crypto/shash.c
index 15b369c4745f..e55c1f558bc3 100644
--- a/crypto/shash.c
+++ b/crypto/shash.c
@@ -238,7 +238,6 @@ static int shash_async_init(struct ahash_request *req)
 	struct shash_desc *desc = ahash_request_ctx(req);
 
 	desc->tfm = *ctx;
-	desc->flags = req->base.flags;
 
 	return crypto_shash_init(desc);
 }
@@ -293,7 +292,6 @@ static int shash_async_finup(struct ahash_request *req)
 	struct shash_desc *desc = ahash_request_ctx(req);
 
 	desc->tfm = *ctx;
-	desc->flags = req->base.flags;
 
 	return shash_ahash_finup(req, desc);
 }
@@ -307,14 +305,13 @@ int shash_ahash_digest(struct ahash_request *req, struct shash_desc *desc)
 
 	if (nbytes &&
 	    (sg = req->src, offset = sg->offset,
-	     nbytes < min(sg->length, ((unsigned int)(PAGE_SIZE)) - offset))) {
+	     nbytes <= min(sg->length, ((unsigned int)(PAGE_SIZE)) - offset))) {
 		void *data;
 
 		data = kmap_atomic(sg_page(sg));
 		err = crypto_shash_digest(desc, data + offset, nbytes,
 					  req->result);
 		kunmap_atomic(data);
-		crypto_yield(desc->flags);
 	} else
 		err = crypto_shash_init(desc) ?:
 		      shash_ahash_finup(req, desc);
@@ -329,7 +326,6 @@ static int shash_async_digest(struct ahash_request *req)
 	struct shash_desc *desc = ahash_request_ctx(req);
 
 	desc->tfm = *ctx;
-	desc->flags = req->base.flags;
 
 	return shash_ahash_digest(req, desc);
 }
@@ -345,7 +341,6 @@ static int shash_async_import(struct ahash_request *req, const void *in)
 	struct shash_desc *desc = ahash_request_ctx(req);
 
 	desc->tfm = *ctx;
-	desc->flags = req->base.flags;
 
 	return crypto_shash_import(desc, in);
 }
diff --git a/crypto/simd.c b/crypto/simd.c
index 78e8d037ae2b..3e3b1d1a6b1f 100644
--- a/crypto/simd.c
+++ b/crypto/simd.c
@@ -3,6 +3,7 @@
  *
  * Copyright (c) 2012 Jussi Kivilinna <jussi.kivilinna@mbnet.fi>
  * Copyright (c) 2016 Herbert Xu <herbert@gondor.apana.org.au>
+ * Copyright (c) 2019 Google LLC
  *
  * Based on aesni-intel_glue.c by:
  *  Copyright (C) 2008, Intel Corp.
@@ -20,10 +21,26 @@
  *
  * You should have received a copy of the GNU General Public License
  * along with this program.  If not, see <http://www.gnu.org/licenses/>.
+ */
+
+/*
+ * Shared crypto SIMD helpers.  These functions dynamically create and register
+ * an skcipher or AEAD algorithm that wraps another, internal algorithm.  The
+ * wrapper ensures that the internal algorithm is only executed in a context
+ * where SIMD instructions are usable, i.e. where may_use_simd() returns true.
+ * If SIMD is already usable, the wrapper directly calls the internal algorithm.
+ * Otherwise it defers execution to a workqueue via cryptd.
  *
+ * This is an alternative to the internal algorithm implementing a fallback for
+ * the !may_use_simd() case itself.
+ *
+ * Note that the wrapper algorithm is asynchronous, i.e. it has the
+ * CRYPTO_ALG_ASYNC flag set.  Therefore it won't be found by users who
+ * explicitly allocate a synchronous algorithm.
  */
 
 #include <crypto/cryptd.h>
+#include <crypto/internal/aead.h>
 #include <crypto/internal/simd.h>
 #include <crypto/internal/skcipher.h>
 #include <linux/kernel.h>
@@ -31,6 +48,8 @@
 #include <linux/preempt.h>
 #include <asm/simd.h>
 
+/* skcipher support */
+
 struct simd_skcipher_alg {
 	const char *ialg_name;
 	struct skcipher_alg alg;
@@ -66,7 +85,7 @@ static int simd_skcipher_encrypt(struct skcipher_request *req)
 	subreq = skcipher_request_ctx(req);
 	*subreq = *req;
 
-	if (!may_use_simd() ||
+	if (!crypto_simd_usable() ||
 	    (in_atomic() && cryptd_skcipher_queued(ctx->cryptd_tfm)))
 		child = &ctx->cryptd_tfm->base;
 	else
@@ -87,7 +106,7 @@ static int simd_skcipher_decrypt(struct skcipher_request *req)
 	subreq = skcipher_request_ctx(req);
 	*subreq = *req;
 
-	if (!may_use_simd() ||
+	if (!crypto_simd_usable() ||
 	    (in_atomic() && cryptd_skcipher_queued(ctx->cryptd_tfm)))
 		child = &ctx->cryptd_tfm->base;
 	else
@@ -272,4 +291,254 @@ void simd_unregister_skciphers(struct skcipher_alg *algs, int count,
 }
 EXPORT_SYMBOL_GPL(simd_unregister_skciphers);
 
+/* AEAD support */
+
+struct simd_aead_alg {
+	const char *ialg_name;
+	struct aead_alg alg;
+};
+
+struct simd_aead_ctx {
+	struct cryptd_aead *cryptd_tfm;
+};
+
+static int simd_aead_setkey(struct crypto_aead *tfm, const u8 *key,
+				unsigned int key_len)
+{
+	struct simd_aead_ctx *ctx = crypto_aead_ctx(tfm);
+	struct crypto_aead *child = &ctx->cryptd_tfm->base;
+	int err;
+
+	crypto_aead_clear_flags(child, CRYPTO_TFM_REQ_MASK);
+	crypto_aead_set_flags(child, crypto_aead_get_flags(tfm) &
+				     CRYPTO_TFM_REQ_MASK);
+	err = crypto_aead_setkey(child, key, key_len);
+	crypto_aead_set_flags(tfm, crypto_aead_get_flags(child) &
+				   CRYPTO_TFM_RES_MASK);
+	return err;
+}
+
+static int simd_aead_setauthsize(struct crypto_aead *tfm, unsigned int authsize)
+{
+	struct simd_aead_ctx *ctx = crypto_aead_ctx(tfm);
+	struct crypto_aead *child = &ctx->cryptd_tfm->base;
+
+	return crypto_aead_setauthsize(child, authsize);
+}
+
+static int simd_aead_encrypt(struct aead_request *req)
+{
+	struct crypto_aead *tfm = crypto_aead_reqtfm(req);
+	struct simd_aead_ctx *ctx = crypto_aead_ctx(tfm);
+	struct aead_request *subreq;
+	struct crypto_aead *child;
+
+	subreq = aead_request_ctx(req);
+	*subreq = *req;
+
+	if (!crypto_simd_usable() ||
+	    (in_atomic() && cryptd_aead_queued(ctx->cryptd_tfm)))
+		child = &ctx->cryptd_tfm->base;
+	else
+		child = cryptd_aead_child(ctx->cryptd_tfm);
+
+	aead_request_set_tfm(subreq, child);
+
+	return crypto_aead_encrypt(subreq);
+}
+
+static int simd_aead_decrypt(struct aead_request *req)
+{
+	struct crypto_aead *tfm = crypto_aead_reqtfm(req);
+	struct simd_aead_ctx *ctx = crypto_aead_ctx(tfm);
+	struct aead_request *subreq;
+	struct crypto_aead *child;
+
+	subreq = aead_request_ctx(req);
+	*subreq = *req;
+
+	if (!crypto_simd_usable() ||
+	    (in_atomic() && cryptd_aead_queued(ctx->cryptd_tfm)))
+		child = &ctx->cryptd_tfm->base;
+	else
+		child = cryptd_aead_child(ctx->cryptd_tfm);
+
+	aead_request_set_tfm(subreq, child);
+
+	return crypto_aead_decrypt(subreq);
+}
+
+static void simd_aead_exit(struct crypto_aead *tfm)
+{
+	struct simd_aead_ctx *ctx = crypto_aead_ctx(tfm);
+
+	cryptd_free_aead(ctx->cryptd_tfm);
+}
+
+static int simd_aead_init(struct crypto_aead *tfm)
+{
+	struct simd_aead_ctx *ctx = crypto_aead_ctx(tfm);
+	struct cryptd_aead *cryptd_tfm;
+	struct simd_aead_alg *salg;
+	struct aead_alg *alg;
+	unsigned reqsize;
+
+	alg = crypto_aead_alg(tfm);
+	salg = container_of(alg, struct simd_aead_alg, alg);
+
+	cryptd_tfm = cryptd_alloc_aead(salg->ialg_name, CRYPTO_ALG_INTERNAL,
+				       CRYPTO_ALG_INTERNAL);
+	if (IS_ERR(cryptd_tfm))
+		return PTR_ERR(cryptd_tfm);
+
+	ctx->cryptd_tfm = cryptd_tfm;
+
+	reqsize = crypto_aead_reqsize(cryptd_aead_child(cryptd_tfm));
+	reqsize = max(reqsize, crypto_aead_reqsize(&cryptd_tfm->base));
+	reqsize += sizeof(struct aead_request);
+
+	crypto_aead_set_reqsize(tfm, reqsize);
+
+	return 0;
+}
+
+struct simd_aead_alg *simd_aead_create_compat(const char *algname,
+					      const char *drvname,
+					      const char *basename)
+{
+	struct simd_aead_alg *salg;
+	struct crypto_aead *tfm;
+	struct aead_alg *ialg;
+	struct aead_alg *alg;
+	int err;
+
+	tfm = crypto_alloc_aead(basename, CRYPTO_ALG_INTERNAL,
+				CRYPTO_ALG_INTERNAL | CRYPTO_ALG_ASYNC);
+	if (IS_ERR(tfm))
+		return ERR_CAST(tfm);
+
+	ialg = crypto_aead_alg(tfm);
+
+	salg = kzalloc(sizeof(*salg), GFP_KERNEL);
+	if (!salg) {
+		salg = ERR_PTR(-ENOMEM);
+		goto out_put_tfm;
+	}
+
+	salg->ialg_name = basename;
+	alg = &salg->alg;
+
+	err = -ENAMETOOLONG;
+	if (snprintf(alg->base.cra_name, CRYPTO_MAX_ALG_NAME, "%s", algname) >=
+	    CRYPTO_MAX_ALG_NAME)
+		goto out_free_salg;
+
+	if (snprintf(alg->base.cra_driver_name, CRYPTO_MAX_ALG_NAME, "%s",
+		     drvname) >= CRYPTO_MAX_ALG_NAME)
+		goto out_free_salg;
+
+	alg->base.cra_flags = CRYPTO_ALG_ASYNC;
+	alg->base.cra_priority = ialg->base.cra_priority;
+	alg->base.cra_blocksize = ialg->base.cra_blocksize;
+	alg->base.cra_alignmask = ialg->base.cra_alignmask;
+	alg->base.cra_module = ialg->base.cra_module;
+	alg->base.cra_ctxsize = sizeof(struct simd_aead_ctx);
+
+	alg->ivsize = ialg->ivsize;
+	alg->maxauthsize = ialg->maxauthsize;
+	alg->chunksize = ialg->chunksize;
+
+	alg->init = simd_aead_init;
+	alg->exit = simd_aead_exit;
+
+	alg->setkey = simd_aead_setkey;
+	alg->setauthsize = simd_aead_setauthsize;
+	alg->encrypt = simd_aead_encrypt;
+	alg->decrypt = simd_aead_decrypt;
+
+	err = crypto_register_aead(alg);
+	if (err)
+		goto out_free_salg;
+
+out_put_tfm:
+	crypto_free_aead(tfm);
+	return salg;
+
+out_free_salg:
+	kfree(salg);
+	salg = ERR_PTR(err);
+	goto out_put_tfm;
+}
+EXPORT_SYMBOL_GPL(simd_aead_create_compat);
+
+struct simd_aead_alg *simd_aead_create(const char *algname,
+				       const char *basename)
+{
+	char drvname[CRYPTO_MAX_ALG_NAME];
+
+	if (snprintf(drvname, CRYPTO_MAX_ALG_NAME, "simd-%s", basename) >=
+	    CRYPTO_MAX_ALG_NAME)
+		return ERR_PTR(-ENAMETOOLONG);
+
+	return simd_aead_create_compat(algname, drvname, basename);
+}
+EXPORT_SYMBOL_GPL(simd_aead_create);
+
+void simd_aead_free(struct simd_aead_alg *salg)
+{
+	crypto_unregister_aead(&salg->alg);
+	kfree(salg);
+}
+EXPORT_SYMBOL_GPL(simd_aead_free);
+
+int simd_register_aeads_compat(struct aead_alg *algs, int count,
+			       struct simd_aead_alg **simd_algs)
+{
+	int err;
+	int i;
+	const char *algname;
+	const char *drvname;
+	const char *basename;
+	struct simd_aead_alg *simd;
+
+	err = crypto_register_aeads(algs, count);
+	if (err)
+		return err;
+
+	for (i = 0; i < count; i++) {
+		WARN_ON(strncmp(algs[i].base.cra_name, "__", 2));
+		WARN_ON(strncmp(algs[i].base.cra_driver_name, "__", 2));
+		algname = algs[i].base.cra_name + 2;
+		drvname = algs[i].base.cra_driver_name + 2;
+		basename = algs[i].base.cra_driver_name;
+		simd = simd_aead_create_compat(algname, drvname, basename);
+		err = PTR_ERR(simd);
+		if (IS_ERR(simd))
+			goto err_unregister;
+		simd_algs[i] = simd;
+	}
+	return 0;
+
+err_unregister:
+	simd_unregister_aeads(algs, count, simd_algs);
+	return err;
+}
+EXPORT_SYMBOL_GPL(simd_register_aeads_compat);
+
+void simd_unregister_aeads(struct aead_alg *algs, int count,
+			   struct simd_aead_alg **simd_algs)
+{
+	int i;
+
+	crypto_unregister_aeads(algs, count);
+
+	for (i = 0; i < count; i++) {
+		if (simd_algs[i]) {
+			simd_aead_free(simd_algs[i]);
+			simd_algs[i] = NULL;
+		}
+	}
+}
+EXPORT_SYMBOL_GPL(simd_unregister_aeads);
+
 MODULE_LICENSE("GPL");
diff --git a/crypto/skcipher.c b/crypto/skcipher.c
index bcf13d95f54a..2e66f312e2c4 100644
--- a/crypto/skcipher.c
+++ b/crypto/skcipher.c
@@ -131,8 +131,13 @@ unmap_src:
 		memcpy(walk->dst.virt.addr, walk->page, n);
 		skcipher_unmap_dst(walk);
 	} else if (unlikely(walk->flags & SKCIPHER_WALK_SLOW)) {
-		if (WARN_ON(err)) {
-			/* unexpected case; didn't process all bytes */
+		if (err) {
+			/*
+			 * Didn't process all bytes.  Either the algorithm is
+			 * broken, or this was the last step and it turned out
+			 * the message wasn't evenly divisible into blocks but
+			 * the algorithm requires it.
+			 */
 			err = -EINVAL;
 			goto finish;
 		}
diff --git a/crypto/sm3_generic.c b/crypto/sm3_generic.c
index c0cf87ae7ef6..e227bcada2a2 100644
--- a/crypto/sm3_generic.c
+++ b/crypto/sm3_generic.c
@@ -199,7 +199,7 @@ static void __exit sm3_generic_mod_fini(void)
 	crypto_unregister_shash(&sm3_alg);
 }
 
-module_init(sm3_generic_mod_init);
+subsys_initcall(sm3_generic_mod_init);
 module_exit(sm3_generic_mod_fini);
 
 MODULE_LICENSE("GPL v2");
diff --git a/crypto/sm4_generic.c b/crypto/sm4_generic.c
index c18eebfd5edd..71ffb343709a 100644
--- a/crypto/sm4_generic.c
+++ b/crypto/sm4_generic.c
@@ -237,7 +237,7 @@ static void __exit sm4_fini(void)
 	crypto_unregister_alg(&sm4_alg);
 }
 
-module_init(sm4_init);
+subsys_initcall(sm4_init);
 module_exit(sm4_fini);
 
 MODULE_DESCRIPTION("SM4 Cipher Algorithm");
diff --git a/crypto/streebog_generic.c b/crypto/streebog_generic.c
index 5a2eafed9c29..63663c3bab7e 100644
--- a/crypto/streebog_generic.c
+++ b/crypto/streebog_generic.c
@@ -996,7 +996,7 @@ static void streebog_add512(const struct streebog_uint512 *x,
 
 static void streebog_g(struct streebog_uint512 *h,
 		       const struct streebog_uint512 *N,
-		       const u8 *m)
+		       const struct streebog_uint512 *m)
 {
 	struct streebog_uint512 Ki, data;
 	unsigned int i;
@@ -1005,7 +1005,7 @@ static void streebog_g(struct streebog_uint512 *h,
 
 	/* Starting E() */
 	Ki = data;
-	streebog_xlps(&Ki, (const struct streebog_uint512 *)&m[0], &data);
+	streebog_xlps(&Ki, m, &data);
 
 	for (i = 0; i < 11; i++)
 		streebog_round(i, &Ki, &data);
@@ -1015,16 +1015,19 @@ static void streebog_g(struct streebog_uint512 *h,
 	/* E() done */
 
 	streebog_xor(&data, h, &data);
-	streebog_xor(&data, (const struct streebog_uint512 *)&m[0], h);
+	streebog_xor(&data, m, h);
 }
 
 static void streebog_stage2(struct streebog_state *ctx, const u8 *data)
 {
-	streebog_g(&ctx->h, &ctx->N, data);
+	struct streebog_uint512 m;
+
+	memcpy(&m, data, sizeof(m));
+
+	streebog_g(&ctx->h, &ctx->N, &m);
 
 	streebog_add512(&ctx->N, &buffer512, &ctx->N);
-	streebog_add512(&ctx->Sigma, (const struct streebog_uint512 *)data,
-			&ctx->Sigma);
+	streebog_add512(&ctx->Sigma, &m, &ctx->Sigma);
 }
 
 static void streebog_stage3(struct streebog_state *ctx)
@@ -1034,13 +1037,11 @@ static void streebog_stage3(struct streebog_state *ctx)
 	buf.qword[0] = cpu_to_le64(ctx->fillsize << 3);
 	streebog_pad(ctx);
 
-	streebog_g(&ctx->h, &ctx->N, (const u8 *)&ctx->buffer);
+	streebog_g(&ctx->h, &ctx->N, &ctx->m);
 	streebog_add512(&ctx->N, &buf, &ctx->N);
-	streebog_add512(&ctx->Sigma,
-			(const struct streebog_uint512 *)&ctx->buffer[0],
-			&ctx->Sigma);
-	streebog_g(&ctx->h, &buffer0, (const u8 *)&ctx->N);
-	streebog_g(&ctx->h, &buffer0, (const u8 *)&ctx->Sigma);
+	streebog_add512(&ctx->Sigma, &ctx->m, &ctx->Sigma);
+	streebog_g(&ctx->h, &buffer0, &ctx->N);
+	streebog_g(&ctx->h, &buffer0, &ctx->Sigma);
 	memcpy(&ctx->hash, &ctx->h, sizeof(struct streebog_uint512));
 }
 
@@ -1127,7 +1128,7 @@ static void __exit streebog_mod_fini(void)
 	crypto_unregister_shashes(algs, ARRAY_SIZE(algs));
 }
 
-module_init(streebog_mod_init);
+subsys_initcall(streebog_mod_init);
 module_exit(streebog_mod_fini);
 
 MODULE_LICENSE("GPL");
diff --git a/crypto/tcrypt.c b/crypto/tcrypt.c
index 1ea2d5007ff5..798253f05203 100644
--- a/crypto/tcrypt.c
+++ b/crypto/tcrypt.c
@@ -3053,7 +3053,7 @@ err_free_tv:
  */
 static void __exit tcrypt_mod_fini(void) { }
 
-module_init(tcrypt_mod_init);
+subsys_initcall(tcrypt_mod_init);
 module_exit(tcrypt_mod_fini);
 
 module_param(alg, charp, 0);
diff --git a/crypto/tea.c b/crypto/tea.c
index b70b441c7d1e..786b589e1399 100644
--- a/crypto/tea.c
+++ b/crypto/tea.c
@@ -274,7 +274,7 @@ MODULE_ALIAS_CRYPTO("tea");
 MODULE_ALIAS_CRYPTO("xtea");
 MODULE_ALIAS_CRYPTO("xeta");
 
-module_init(tea_mod_init);
+subsys_initcall(tea_mod_init);
 module_exit(tea_mod_fini);
 
 MODULE_LICENSE("GPL");
diff --git a/crypto/testmgr.c b/crypto/testmgr.c
index 8386038d67c7..c9e67c2bd725 100644
--- a/crypto/testmgr.c
+++ b/crypto/testmgr.c
@@ -37,6 +37,7 @@
 #include <crypto/akcipher.h>
 #include <crypto/kpp.h>
 #include <crypto/acompress.h>
+#include <crypto/internal/simd.h>
 
 #include "internal.h"
 
@@ -44,6 +45,9 @@ static bool notests;
 module_param(notests, bool, 0644);
 MODULE_PARM_DESC(notests, "disable crypto self-tests");
 
+static bool panic_on_fail;
+module_param(panic_on_fail, bool, 0444);
+
 #ifdef CONFIG_CRYPTO_MANAGER_EXTRA_TESTS
 static bool noextratests;
 module_param(noextratests, bool, 0644);
@@ -52,6 +56,9 @@ MODULE_PARM_DESC(noextratests, "disable expensive crypto self-tests");
 static unsigned int fuzz_iterations = 100;
 module_param(fuzz_iterations, uint, 0644);
 MODULE_PARM_DESC(fuzz_iterations, "number of fuzz test iterations");
+
+DEFINE_PER_CPU(bool, crypto_simd_disabled_for_test);
+EXPORT_PER_CPU_SYMBOL_GPL(crypto_simd_disabled_for_test);
 #endif
 
 #ifdef CONFIG_CRYPTO_MANAGER_DISABLE_TESTS
@@ -121,6 +128,7 @@ struct kpp_test_suite {
 
 struct alg_test_desc {
 	const char *alg;
+	const char *generic_driver;
 	int (*test)(const struct alg_test_desc *desc, const char *driver,
 		    u32 type, u32 mask);
 	int fips_allowed;	/* set if alg is allowed in fips mode */
@@ -230,12 +238,14 @@ enum finalization_type {
  *				  @offset
  * @flush_type: for hashes, whether an update() should be done now vs.
  *		continuing to accumulate data
+ * @nosimd: if doing the pending update(), do it with SIMD disabled?
  */
 struct test_sg_division {
 	unsigned int proportion_of_total;
 	unsigned int offset;
 	bool offset_relative_to_alignmask;
 	enum flush_type flush_type;
+	bool nosimd;
 };
 
 /**
@@ -255,6 +265,7 @@ struct test_sg_division {
  * @iv_offset_relative_to_alignmask: if true, add the algorithm's alignmask to
  *				     the @iv_offset
  * @finalization_type: what finalization function to use for hashes
+ * @nosimd: execute with SIMD disabled?  Requires !CRYPTO_TFM_REQ_MAY_SLEEP.
  */
 struct testvec_config {
 	const char *name;
@@ -265,6 +276,7 @@ struct testvec_config {
 	unsigned int iv_offset;
 	bool iv_offset_relative_to_alignmask;
 	enum finalization_type finalization_type;
+	bool nosimd;
 };
 
 #define TESTVEC_CONFIG_NAMELEN	192
@@ -416,8 +428,11 @@ static unsigned int count_test_sg_divisions(const struct test_sg_division *divs)
 	return ndivs;
 }
 
+#define SGDIVS_HAVE_FLUSHES	BIT(0)
+#define SGDIVS_HAVE_NOSIMD	BIT(1)
+
 static bool valid_sg_divisions(const struct test_sg_division *divs,
-			       unsigned int count, bool *any_flushes_ret)
+			       unsigned int count, int *flags_ret)
 {
 	unsigned int total = 0;
 	unsigned int i;
@@ -428,7 +443,9 @@ static bool valid_sg_divisions(const struct test_sg_division *divs,
 			return false;
 		total += divs[i].proportion_of_total;
 		if (divs[i].flush_type != FLUSH_TYPE_NONE)
-			*any_flushes_ret = true;
+			*flags_ret |= SGDIVS_HAVE_FLUSHES;
+		if (divs[i].nosimd)
+			*flags_ret |= SGDIVS_HAVE_NOSIMD;
 	}
 	return total == TEST_SG_TOTAL &&
 		memchr_inv(&divs[i], 0, (count - i) * sizeof(divs[0])) == NULL;
@@ -441,19 +458,18 @@ static bool valid_sg_divisions(const struct test_sg_division *divs,
  */
 static bool valid_testvec_config(const struct testvec_config *cfg)
 {
-	bool any_flushes = false;
+	int flags = 0;
 
 	if (cfg->name == NULL)
 		return false;
 
 	if (!valid_sg_divisions(cfg->src_divs, ARRAY_SIZE(cfg->src_divs),
-				&any_flushes))
+				&flags))
 		return false;
 
 	if (cfg->dst_divs[0].proportion_of_total) {
 		if (!valid_sg_divisions(cfg->dst_divs,
-					ARRAY_SIZE(cfg->dst_divs),
-					&any_flushes))
+					ARRAY_SIZE(cfg->dst_divs), &flags))
 			return false;
 	} else {
 		if (memchr_inv(cfg->dst_divs, 0, sizeof(cfg->dst_divs)))
@@ -466,7 +482,12 @@ static bool valid_testvec_config(const struct testvec_config *cfg)
 	    MAX_ALGAPI_ALIGNMASK + 1)
 		return false;
 
-	if (any_flushes && cfg->finalization_type == FINALIZATION_TYPE_DIGEST)
+	if ((flags & (SGDIVS_HAVE_FLUSHES | SGDIVS_HAVE_NOSIMD)) &&
+	    cfg->finalization_type == FINALIZATION_TYPE_DIGEST)
+		return false;
+
+	if ((cfg->nosimd || (flags & SGDIVS_HAVE_NOSIMD)) &&
+	    (cfg->req_flags & CRYPTO_TFM_REQ_MAY_SLEEP))
 		return false;
 
 	return true;
@@ -725,15 +746,101 @@ static int build_cipher_test_sglists(struct cipher_test_sglists *tsgls,
 }
 
 #ifdef CONFIG_CRYPTO_MANAGER_EXTRA_TESTS
+
+/* Generate a random length in range [0, max_len], but prefer smaller values */
+static unsigned int generate_random_length(unsigned int max_len)
+{
+	unsigned int len = prandom_u32() % (max_len + 1);
+
+	switch (prandom_u32() % 4) {
+	case 0:
+		return len % 64;
+	case 1:
+		return len % 256;
+	case 2:
+		return len % 1024;
+	default:
+		return len;
+	}
+}
+
+/* Sometimes make some random changes to the given data buffer */
+static void mutate_buffer(u8 *buf, size_t count)
+{
+	size_t num_flips;
+	size_t i;
+	size_t pos;
+
+	/* Sometimes flip some bits */
+	if (prandom_u32() % 4 == 0) {
+		num_flips = min_t(size_t, 1 << (prandom_u32() % 8), count * 8);
+		for (i = 0; i < num_flips; i++) {
+			pos = prandom_u32() % (count * 8);
+			buf[pos / 8] ^= 1 << (pos % 8);
+		}
+	}
+
+	/* Sometimes flip some bytes */
+	if (prandom_u32() % 4 == 0) {
+		num_flips = min_t(size_t, 1 << (prandom_u32() % 8), count);
+		for (i = 0; i < num_flips; i++)
+			buf[prandom_u32() % count] ^= 0xff;
+	}
+}
+
+/* Randomly generate 'count' bytes, but sometimes make them "interesting" */
+static void generate_random_bytes(u8 *buf, size_t count)
+{
+	u8 b;
+	u8 increment;
+	size_t i;
+
+	if (count == 0)
+		return;
+
+	switch (prandom_u32() % 8) { /* Choose a generation strategy */
+	case 0:
+	case 1:
+		/* All the same byte, plus optional mutations */
+		switch (prandom_u32() % 4) {
+		case 0:
+			b = 0x00;
+			break;
+		case 1:
+			b = 0xff;
+			break;
+		default:
+			b = (u8)prandom_u32();
+			break;
+		}
+		memset(buf, b, count);
+		mutate_buffer(buf, count);
+		break;
+	case 2:
+		/* Ascending or descending bytes, plus optional mutations */
+		increment = (u8)prandom_u32();
+		b = (u8)prandom_u32();
+		for (i = 0; i < count; i++, b += increment)
+			buf[i] = b;
+		mutate_buffer(buf, count);
+		break;
+	default:
+		/* Fully random bytes */
+		for (i = 0; i < count; i++)
+			buf[i] = (u8)prandom_u32();
+	}
+}
+
 static char *generate_random_sgl_divisions(struct test_sg_division *divs,
 					   size_t max_divs, char *p, char *end,
-					   bool gen_flushes)
+					   bool gen_flushes, u32 req_flags)
 {
 	struct test_sg_division *div = divs;
 	unsigned int remaining = TEST_SG_TOTAL;
 
 	do {
 		unsigned int this_len;
+		const char *flushtype_str;
 
 		if (div == &divs[max_divs - 1] || prandom_u32() % 2 == 0)
 			this_len = remaining;
@@ -762,11 +869,31 @@ static char *generate_random_sgl_divisions(struct test_sg_division *divs,
 			}
 		}
 
+		if (div->flush_type != FLUSH_TYPE_NONE &&
+		    !(req_flags & CRYPTO_TFM_REQ_MAY_SLEEP) &&
+		    prandom_u32() % 2 == 0)
+			div->nosimd = true;
+
+		switch (div->flush_type) {
+		case FLUSH_TYPE_FLUSH:
+			if (div->nosimd)
+				flushtype_str = "<flush,nosimd>";
+			else
+				flushtype_str = "<flush>";
+			break;
+		case FLUSH_TYPE_REIMPORT:
+			if (div->nosimd)
+				flushtype_str = "<reimport,nosimd>";
+			else
+				flushtype_str = "<reimport>";
+			break;
+		default:
+			flushtype_str = "";
+			break;
+		}
+
 		BUILD_BUG_ON(TEST_SG_TOTAL != 10000); /* for "%u.%u%%" */
-		p += scnprintf(p, end - p, "%s%u.%u%%@%s+%u%s",
-			       div->flush_type == FLUSH_TYPE_NONE ? "" :
-			       div->flush_type == FLUSH_TYPE_FLUSH ?
-			       "<flush> " : "<reimport> ",
+		p += scnprintf(p, end - p, "%s%u.%u%%@%s+%u%s", flushtype_str,
 			       this_len / 100, this_len % 100,
 			       div->offset_relative_to_alignmask ?
 					"alignmask" : "",
@@ -816,18 +943,26 @@ static void generate_random_testvec_config(struct testvec_config *cfg,
 		break;
 	}
 
+	if (!(cfg->req_flags & CRYPTO_TFM_REQ_MAY_SLEEP) &&
+	    prandom_u32() % 2 == 0) {
+		cfg->nosimd = true;
+		p += scnprintf(p, end - p, " nosimd");
+	}
+
 	p += scnprintf(p, end - p, " src_divs=[");
 	p = generate_random_sgl_divisions(cfg->src_divs,
 					  ARRAY_SIZE(cfg->src_divs), p, end,
 					  (cfg->finalization_type !=
-					   FINALIZATION_TYPE_DIGEST));
+					   FINALIZATION_TYPE_DIGEST),
+					  cfg->req_flags);
 	p += scnprintf(p, end - p, "]");
 
 	if (!cfg->inplace && prandom_u32() % 2 == 0) {
 		p += scnprintf(p, end - p, " dst_divs=[");
 		p = generate_random_sgl_divisions(cfg->dst_divs,
 						  ARRAY_SIZE(cfg->dst_divs),
-						  p, end, false);
+						  p, end, false,
+						  cfg->req_flags);
 		p += scnprintf(p, end - p, "]");
 	}
 
@@ -838,21 +973,100 @@ static void generate_random_testvec_config(struct testvec_config *cfg,
 
 	WARN_ON_ONCE(!valid_testvec_config(cfg));
 }
-#endif /* CONFIG_CRYPTO_MANAGER_EXTRA_TESTS */
+
+static void crypto_disable_simd_for_test(void)
+{
+	preempt_disable();
+	__this_cpu_write(crypto_simd_disabled_for_test, true);
+}
+
+static void crypto_reenable_simd_for_test(void)
+{
+	__this_cpu_write(crypto_simd_disabled_for_test, false);
+	preempt_enable();
+}
+
+/*
+ * Given an algorithm name, build the name of the generic implementation of that
+ * algorithm, assuming the usual naming convention.  Specifically, this appends
+ * "-generic" to every part of the name that is not a template name.  Examples:
+ *
+ *	aes => aes-generic
+ *	cbc(aes) => cbc(aes-generic)
+ *	cts(cbc(aes)) => cts(cbc(aes-generic))
+ *	rfc7539(chacha20,poly1305) => rfc7539(chacha20-generic,poly1305-generic)
+ *
+ * Return: 0 on success, or -ENAMETOOLONG if the generic name would be too long
+ */
+static int build_generic_driver_name(const char *algname,
+				     char driver_name[CRYPTO_MAX_ALG_NAME])
+{
+	const char *in = algname;
+	char *out = driver_name;
+	size_t len = strlen(algname);
+
+	if (len >= CRYPTO_MAX_ALG_NAME)
+		goto too_long;
+	do {
+		const char *in_saved = in;
+
+		while (*in && *in != '(' && *in != ')' && *in != ',')
+			*out++ = *in++;
+		if (*in != '(' && in > in_saved) {
+			len += 8;
+			if (len >= CRYPTO_MAX_ALG_NAME)
+				goto too_long;
+			memcpy(out, "-generic", 8);
+			out += 8;
+		}
+	} while ((*out++ = *in++) != '\0');
+	return 0;
+
+too_long:
+	pr_err("alg: generic driver name for \"%s\" would be too long\n",
+	       algname);
+	return -ENAMETOOLONG;
+}
+#else /* !CONFIG_CRYPTO_MANAGER_EXTRA_TESTS */
+static void crypto_disable_simd_for_test(void)
+{
+}
+
+static void crypto_reenable_simd_for_test(void)
+{
+}
+#endif /* !CONFIG_CRYPTO_MANAGER_EXTRA_TESTS */
+
+static int do_ahash_op(int (*op)(struct ahash_request *req),
+		       struct ahash_request *req,
+		       struct crypto_wait *wait, bool nosimd)
+{
+	int err;
+
+	if (nosimd)
+		crypto_disable_simd_for_test();
+
+	err = op(req);
+
+	if (nosimd)
+		crypto_reenable_simd_for_test();
+
+	return crypto_wait_req(err, wait);
+}
 
 static int check_nonfinal_hash_op(const char *op, int err,
 				  u8 *result, unsigned int digestsize,
-				  const char *driver, unsigned int vec_num,
+				  const char *driver, const char *vec_name,
 				  const struct testvec_config *cfg)
 {
 	if (err) {
-		pr_err("alg: hash: %s %s() failed with err %d on test vector %u, cfg=\"%s\"\n",
-		       driver, op, err, vec_num, cfg->name);
+		pr_err("alg: hash: %s %s() failed with err %d on test vector %s, cfg=\"%s\"\n",
+		       driver, op, err, vec_name, cfg->name);
 		return err;
 	}
 	if (!testmgr_is_poison(result, digestsize)) {
-		pr_err("alg: hash: %s %s() used result buffer on test vector %u, cfg=\"%s\"\n",
-		       driver, op, vec_num, cfg->name);
+		pr_err("alg: hash: %s %s() used result buffer on test vector %s, cfg=\"%s\"\n",
+		       driver, op, vec_name, cfg->name);
 		return -EINVAL;
 	}
 	return 0;
@@ -860,7 +1074,7 @@ static int check_nonfinal_hash_op(const char *op, int err,
 
 static int test_hash_vec_cfg(const char *driver,
 			     const struct hash_testvec *vec,
-			     unsigned int vec_num,
+			     const char *vec_name,
 			     const struct testvec_config *cfg,
 			     struct ahash_request *req,
 			     struct test_sglist *tsgl,
@@ -885,11 +1099,18 @@ static int test_hash_vec_cfg(const char *driver,
 	if (vec->ksize) {
 		err = crypto_ahash_setkey(tfm, vec->key, vec->ksize);
 		if (err) {
-			pr_err("alg: hash: %s setkey failed with err %d on test vector %u; flags=%#x\n",
-			       driver, err, vec_num,
+			if (err == vec->setkey_error)
+				return 0;
+			pr_err("alg: hash: %s setkey failed on test vector %s; expected_error=%d, actual_error=%d, flags=%#x\n",
+			       driver, vec_name, vec->setkey_error, err,
 			       crypto_ahash_get_flags(tfm));
 			return err;
 		}
+		if (vec->setkey_error) {
+			pr_err("alg: hash: %s setkey unexpectedly succeeded on test vector %s; expected_error=%d\n",
+			       driver, vec_name, vec->setkey_error);
+			return -EINVAL;
+		}
 	}
 
 	/* Build the scatterlist for the source data */
@@ -899,8 +1120,8 @@ static int test_hash_vec_cfg(const char *driver,
 	err = build_test_sglist(tsgl, cfg->src_divs, alignmask, vec->psize,
 				&input, divs);
 	if (err) {
-		pr_err("alg: hash: %s: error preparing scatterlist for test vector %u, cfg=\"%s\"\n",
-		       driver, vec_num, cfg->name);
+		pr_err("alg: hash: %s: error preparing scatterlist for test vector %s, cfg=\"%s\"\n",
+		       driver, vec_name, cfg->name);
 		return err;
 	}
 
@@ -909,17 +1130,26 @@ static int test_hash_vec_cfg(const char *driver,
 	testmgr_poison(req->__ctx, crypto_ahash_reqsize(tfm));
 	testmgr_poison(result, digestsize + TESTMGR_POISON_LEN);
 
-	if (cfg->finalization_type == FINALIZATION_TYPE_DIGEST) {
+	if (cfg->finalization_type == FINALIZATION_TYPE_DIGEST ||
+	    vec->digest_error) {
 		/* Just using digest() */
 		ahash_request_set_callback(req, req_flags, crypto_req_done,
 					   &wait);
 		ahash_request_set_crypt(req, tsgl->sgl, result, vec->psize);
-		err = crypto_wait_req(crypto_ahash_digest(req), &wait);
+		err = do_ahash_op(crypto_ahash_digest, req, &wait, cfg->nosimd);
 		if (err) {
-			pr_err("alg: hash: %s digest() failed with err %d on test vector %u, cfg=\"%s\"\n",
-			       driver, err, vec_num, cfg->name);
+			if (err == vec->digest_error)
+				return 0;
+			pr_err("alg: hash: %s digest() failed on test vector %s; expected_error=%d, actual_error=%d, cfg=\"%s\"\n",
+			       driver, vec_name, vec->digest_error, err,
+			       cfg->name);
 			return err;
 		}
+		if (vec->digest_error) {
+			pr_err("alg: hash: %s digest() unexpectedly succeeded on test vector %s; expected_error=%d, cfg=\"%s\"\n",
+			       driver, vec_name, vec->digest_error, cfg->name);
+			return -EINVAL;
+		}
 		goto result_ready;
 	}
 
@@ -927,9 +1157,9 @@ static int test_hash_vec_cfg(const char *driver,
 
 	ahash_request_set_callback(req, req_flags, crypto_req_done, &wait);
 	ahash_request_set_crypt(req, NULL, result, 0);
-	err = crypto_wait_req(crypto_ahash_init(req), &wait);
+	err = do_ahash_op(crypto_ahash_init, req, &wait, cfg->nosimd);
 	err = check_nonfinal_hash_op("init", err, result, digestsize,
-				     driver, vec_num, cfg);
+				     driver, vec_name, cfg);
 	if (err)
 		return err;
 
@@ -943,10 +1173,11 @@ static int test_hash_vec_cfg(const char *driver,
 						   crypto_req_done, &wait);
 			ahash_request_set_crypt(req, pending_sgl, result,
 						pending_len);
-			err = crypto_wait_req(crypto_ahash_update(req), &wait);
+			err = do_ahash_op(crypto_ahash_update, req, &wait,
+					  divs[i]->nosimd);
 			err = check_nonfinal_hash_op("update", err,
 						     result, digestsize,
-						     driver, vec_num, cfg);
+						     driver, vec_name, cfg);
 			if (err)
 				return err;
 			pending_sgl = NULL;
@@ -959,13 +1190,13 @@ static int test_hash_vec_cfg(const char *driver,
 			err = crypto_ahash_export(req, hashstate);
 			err = check_nonfinal_hash_op("export", err,
 						     result, digestsize,
-						     driver, vec_num, cfg);
+						     driver, vec_name, cfg);
 			if (err)
 				return err;
 			if (!testmgr_is_poison(hashstate + statesize,
 					       TESTMGR_POISON_LEN)) {
-				pr_err("alg: hash: %s export() overran state buffer on test vector %u, cfg=\"%s\"\n",
-				       driver, vec_num, cfg->name);
+				pr_err("alg: hash: %s export() overran state buffer on test vector %s, cfg=\"%s\"\n",
+				       driver, vec_name, cfg->name);
 				return -EOVERFLOW;
 			}
 
@@ -973,7 +1204,7 @@ static int test_hash_vec_cfg(const char *driver,
 			err = crypto_ahash_import(req, hashstate);
 			err = check_nonfinal_hash_op("import", err,
 						     result, digestsize,
-						     driver, vec_num, cfg);
+						     driver, vec_name, cfg);
 			if (err)
 				return err;
 		}
@@ -986,23 +1217,23 @@ static int test_hash_vec_cfg(const char *driver,
 	ahash_request_set_crypt(req, pending_sgl, result, pending_len);
 	if (cfg->finalization_type == FINALIZATION_TYPE_FINAL) {
 		/* finish with update() and final() */
-		err = crypto_wait_req(crypto_ahash_update(req), &wait);
+		err = do_ahash_op(crypto_ahash_update, req, &wait, cfg->nosimd);
 		err = check_nonfinal_hash_op("update", err, result, digestsize,
-					     driver, vec_num, cfg);
+					     driver, vec_name, cfg);
 		if (err)
 			return err;
-		err = crypto_wait_req(crypto_ahash_final(req), &wait);
+		err = do_ahash_op(crypto_ahash_final, req, &wait, cfg->nosimd);
 		if (err) {
-			pr_err("alg: hash: %s final() failed with err %d on test vector %u, cfg=\"%s\"\n",
-			       driver, err, vec_num, cfg->name);
+			pr_err("alg: hash: %s final() failed with err %d on test vector %s, cfg=\"%s\"\n",
+			       driver, err, vec_name, cfg->name);
 			return err;
 		}
 	} else {
 		/* finish with finup() */
-		err = crypto_wait_req(crypto_ahash_finup(req), &wait);
+		err = do_ahash_op(crypto_ahash_finup, req, &wait, cfg->nosimd);
 		if (err) {
-			pr_err("alg: hash: %s finup() failed with err %d on test vector %u, cfg=\"%s\"\n",
-			       driver, err, vec_num, cfg->name);
+			pr_err("alg: hash: %s finup() failed with err %d on test vector %s, cfg=\"%s\"\n",
+			       driver, err, vec_name, cfg->name);
 			return err;
 		}
 	}
@@ -1010,13 +1241,13 @@ static int test_hash_vec_cfg(const char *driver,
 result_ready:
 	/* Check that the algorithm produced the correct digest */
 	if (memcmp(result, vec->digest, digestsize) != 0) {
-		pr_err("alg: hash: %s test failed (wrong result) on test vector %u, cfg=\"%s\"\n",
-		       driver, vec_num, cfg->name);
+		pr_err("alg: hash: %s test failed (wrong result) on test vector %s, cfg=\"%s\"\n",
+		       driver, vec_name, cfg->name);
 		return -EINVAL;
 	}
 	if (!testmgr_is_poison(&result[digestsize], TESTMGR_POISON_LEN)) {
-		pr_err("alg: hash: %s overran result buffer on test vector %u, cfg=\"%s\"\n",
-		       driver, vec_num, cfg->name);
+		pr_err("alg: hash: %s overran result buffer on test vector %s, cfg=\"%s\"\n",
+		       driver, vec_name, cfg->name);
 		return -EOVERFLOW;
 	}
 
@@ -1027,11 +1258,14 @@ static int test_hash_vec(const char *driver, const struct hash_testvec *vec,
 			 unsigned int vec_num, struct ahash_request *req,
 			 struct test_sglist *tsgl, u8 *hashstate)
 {
+	char vec_name[16];
 	unsigned int i;
 	int err;
 
+	sprintf(vec_name, "%u", vec_num);
+
 	for (i = 0; i < ARRAY_SIZE(default_hash_testvec_configs); i++) {
-		err = test_hash_vec_cfg(driver, vec, vec_num,
+		err = test_hash_vec_cfg(driver, vec, vec_name,
 					&default_hash_testvec_configs[i],
 					req, tsgl, hashstate);
 		if (err)
@@ -1046,7 +1280,7 @@ static int test_hash_vec(const char *driver, const struct hash_testvec *vec,
 		for (i = 0; i < fuzz_iterations; i++) {
 			generate_random_testvec_config(&cfg, cfgname,
 						       sizeof(cfgname));
-			err = test_hash_vec_cfg(driver, vec, vec_num, &cfg,
+			err = test_hash_vec_cfg(driver, vec, vec_name, &cfg,
 						req, tsgl, hashstate);
 			if (err)
 				return err;
@@ -1056,9 +1290,168 @@ static int test_hash_vec(const char *driver, const struct hash_testvec *vec,
 	return 0;
 }
 
+#ifdef CONFIG_CRYPTO_MANAGER_EXTRA_TESTS
+/*
+ * Generate a hash test vector from the given implementation.
+ * Assumes the buffers in 'vec' were already allocated.
+ */
+static void generate_random_hash_testvec(struct crypto_shash *tfm,
+					 struct hash_testvec *vec,
+					 unsigned int maxkeysize,
+					 unsigned int maxdatasize,
+					 char *name, size_t max_namelen)
+{
+	SHASH_DESC_ON_STACK(desc, tfm);
+
+	/* Data */
+	vec->psize = generate_random_length(maxdatasize);
+	generate_random_bytes((u8 *)vec->plaintext, vec->psize);
+
+	/*
+	 * Key: length in range [1, maxkeysize], but usually choose maxkeysize.
+	 * If algorithm is unkeyed, then maxkeysize == 0 and set ksize = 0.
+	 */
+	vec->setkey_error = 0;
+	vec->ksize = 0;
+	if (maxkeysize) {
+		vec->ksize = maxkeysize;
+		if (prandom_u32() % 4 == 0)
+			vec->ksize = 1 + (prandom_u32() % maxkeysize);
+		generate_random_bytes((u8 *)vec->key, vec->ksize);
+
+		vec->setkey_error = crypto_shash_setkey(tfm, vec->key,
+							vec->ksize);
+		/* If the key couldn't be set, no need to continue to digest. */
+		if (vec->setkey_error)
+			goto done;
+	}
+
+	/* Digest */
+	desc->tfm = tfm;
+	vec->digest_error = crypto_shash_digest(desc, vec->plaintext,
+						vec->psize, (u8 *)vec->digest);
+done:
+	snprintf(name, max_namelen, "\"random: psize=%u ksize=%u\"",
+		 vec->psize, vec->ksize);
+}
+
+/*
+ * Test the hash algorithm represented by @req against the corresponding generic
+ * implementation, if one is available.
+ */
+static int test_hash_vs_generic_impl(const char *driver,
+				     const char *generic_driver,
+				     unsigned int maxkeysize,
+				     struct ahash_request *req,
+				     struct test_sglist *tsgl,
+				     u8 *hashstate)
+{
+	struct crypto_ahash *tfm = crypto_ahash_reqtfm(req);
+	const unsigned int digestsize = crypto_ahash_digestsize(tfm);
+	const unsigned int blocksize = crypto_ahash_blocksize(tfm);
+	const unsigned int maxdatasize = (2 * PAGE_SIZE) - TESTMGR_POISON_LEN;
+	const char *algname = crypto_hash_alg_common(tfm)->base.cra_name;
+	char _generic_driver[CRYPTO_MAX_ALG_NAME];
+	struct crypto_shash *generic_tfm = NULL;
+	unsigned int i;
+	struct hash_testvec vec = { 0 };
+	char vec_name[64];
+	struct testvec_config cfg;
+	char cfgname[TESTVEC_CONFIG_NAMELEN];
+	int err;
+
+	if (noextratests)
+		return 0;
+
+	if (!generic_driver) { /* Use default naming convention? */
+		err = build_generic_driver_name(algname, _generic_driver);
+		if (err)
+			return err;
+		generic_driver = _generic_driver;
+	}
+
+	if (strcmp(generic_driver, driver) == 0) /* Already the generic impl? */
+		return 0;
+
+	generic_tfm = crypto_alloc_shash(generic_driver, 0, 0);
+	if (IS_ERR(generic_tfm)) {
+		err = PTR_ERR(generic_tfm);
+		if (err == -ENOENT) {
+			pr_warn("alg: hash: skipping comparison tests for %s because %s is unavailable\n",
+				driver, generic_driver);
+			return 0;
+		}
+		pr_err("alg: hash: error allocating %s (generic impl of %s): %d\n",
+		       generic_driver, algname, err);
+		return err;
+	}
+
+	/* Check the algorithm properties for consistency. */
+
+	if (digestsize != crypto_shash_digestsize(generic_tfm)) {
+		pr_err("alg: hash: digestsize for %s (%u) doesn't match generic impl (%u)\n",
+		       driver, digestsize,
+		       crypto_shash_digestsize(generic_tfm));
+		err = -EINVAL;
+		goto out;
+	}
+
+	if (blocksize != crypto_shash_blocksize(generic_tfm)) {
+		pr_err("alg: hash: blocksize for %s (%u) doesn't match generic impl (%u)\n",
+		       driver, blocksize, crypto_shash_blocksize(generic_tfm));
+		err = -EINVAL;
+		goto out;
+	}
+
+	/*
+	 * Now generate test vectors using the generic implementation, and test
+	 * the other implementation against them.
+	 */
+
+	vec.key = kmalloc(maxkeysize, GFP_KERNEL);
+	vec.plaintext = kmalloc(maxdatasize, GFP_KERNEL);
+	vec.digest = kmalloc(digestsize, GFP_KERNEL);
+	if (!vec.key || !vec.plaintext || !vec.digest) {
+		err = -ENOMEM;
+		goto out;
+	}
+
+	for (i = 0; i < fuzz_iterations * 8; i++) {
+		generate_random_hash_testvec(generic_tfm, &vec,
+					     maxkeysize, maxdatasize,
+					     vec_name, sizeof(vec_name));
+		generate_random_testvec_config(&cfg, cfgname, sizeof(cfgname));
+
+		err = test_hash_vec_cfg(driver, &vec, vec_name, &cfg,
+					req, tsgl, hashstate);
+		if (err)
+			goto out;
+		cond_resched();
+	}
+	err = 0;
+out:
+	kfree(vec.key);
+	kfree(vec.plaintext);
+	kfree(vec.digest);
+	crypto_free_shash(generic_tfm);
+	return err;
+}
+#else /* !CONFIG_CRYPTO_MANAGER_EXTRA_TESTS */
+static int test_hash_vs_generic_impl(const char *driver,
+				     const char *generic_driver,
+				     unsigned int maxkeysize,
+				     struct ahash_request *req,
+				     struct test_sglist *tsgl,
+				     u8 *hashstate)
+{
+	return 0;
+}
+#endif /* !CONFIG_CRYPTO_MANAGER_EXTRA_TESTS */
+
 static int __alg_test_hash(const struct hash_testvec *vecs,
 			   unsigned int num_vecs, const char *driver,
-			   u32 type, u32 mask)
+			   u32 type, u32 mask,
+			   const char *generic_driver, unsigned int maxkeysize)
 {
 	struct crypto_ahash *tfm;
 	struct ahash_request *req = NULL;
@@ -1106,7 +1499,8 @@ static int __alg_test_hash(const struct hash_testvec *vecs,
 		if (err)
 			goto out;
 	}
-	err = 0;
+	err = test_hash_vs_generic_impl(driver, generic_driver, maxkeysize, req,
+					tsgl, hashstate);
 out:
 	kfree(hashstate);
 	if (tsgl) {
@@ -1124,6 +1518,7 @@ static int alg_test_hash(const struct alg_test_desc *desc, const char *driver,
 	const struct hash_testvec *template = desc->suite.hash.vecs;
 	unsigned int tcount = desc->suite.hash.count;
 	unsigned int nr_unkeyed, nr_keyed;
+	unsigned int maxkeysize = 0;
 	int err;
 
 	/*
@@ -1142,23 +1537,27 @@ static int alg_test_hash(const struct alg_test_desc *desc, const char *driver,
 			       "unkeyed ones must come first\n", desc->alg);
 			return -EINVAL;
 		}
+		maxkeysize = max_t(unsigned int, maxkeysize,
+				   template[nr_unkeyed + nr_keyed].ksize);
 	}
 
 	err = 0;
 	if (nr_unkeyed) {
-		err = __alg_test_hash(template, nr_unkeyed, driver, type, mask);
+		err = __alg_test_hash(template, nr_unkeyed, driver, type, mask,
+				      desc->generic_driver, maxkeysize);
 		template += nr_unkeyed;
 	}
 
 	if (!err && nr_keyed)
-		err = __alg_test_hash(template, nr_keyed, driver, type, mask);
+		err = __alg_test_hash(template, nr_keyed, driver, type, mask,
+				      desc->generic_driver, maxkeysize);
 
 	return err;
 }
 
 static int test_aead_vec_cfg(const char *driver, int enc,
 			     const struct aead_testvec *vec,
-			     unsigned int vec_num,
+			     const char *vec_name,
 			     const struct testvec_config *cfg,
 			     struct aead_request *req,
 			     struct cipher_test_sglists *tsgls)
@@ -1175,6 +1574,7 @@ static int test_aead_vec_cfg(const char *driver, int enc,
 		 cfg->iv_offset +
 		 (cfg->iv_offset_relative_to_alignmask ? alignmask : 0);
 	struct kvec input[2];
+	int expected_error;
 	int err;
 
 	/* Set the key */
@@ -1183,26 +1583,33 @@ static int test_aead_vec_cfg(const char *driver, int enc,
 	else
 		crypto_aead_clear_flags(tfm, CRYPTO_TFM_REQ_FORBID_WEAK_KEYS);
 	err = crypto_aead_setkey(tfm, vec->key, vec->klen);
-	if (err) {
-		if (vec->fail) /* expectedly failed to set key? */
-			return 0;
-		pr_err("alg: aead: %s setkey failed with err %d on test vector %u; flags=%#x\n",
-		       driver, err, vec_num, crypto_aead_get_flags(tfm));
+	if (err && err != vec->setkey_error) {
+		pr_err("alg: aead: %s setkey failed on test vector %s; expected_error=%d, actual_error=%d, flags=%#x\n",
+		       driver, vec_name, vec->setkey_error, err,
+		       crypto_aead_get_flags(tfm));
 		return err;
 	}
-	if (vec->fail) {
-		pr_err("alg: aead: %s setkey unexpectedly succeeded on test vector %u\n",
-		       driver, vec_num);
+	if (!err && vec->setkey_error) {
+		pr_err("alg: aead: %s setkey unexpectedly succeeded on test vector %s; expected_error=%d\n",
+		       driver, vec_name, vec->setkey_error);
 		return -EINVAL;
 	}
 
 	/* Set the authentication tag size */
 	err = crypto_aead_setauthsize(tfm, authsize);
-	if (err) {
-		pr_err("alg: aead: %s setauthsize failed with err %d on test vector %u\n",
-		       driver, err, vec_num);
+	if (err && err != vec->setauthsize_error) {
+		pr_err("alg: aead: %s setauthsize failed on test vector %s; expected_error=%d, actual_error=%d\n",
+		       driver, vec_name, vec->setauthsize_error, err);
 		return err;
 	}
+	if (!err && vec->setauthsize_error) {
+		pr_err("alg: aead: %s setauthsize unexpectedly succeeded on test vector %s; expected_error=%d\n",
+		       driver, vec_name, vec->setauthsize_error);
+		return -EINVAL;
+	}
+
+	if (vec->setkey_error || vec->setauthsize_error)
+		return 0;
 
 	/* The IV must be copied to a buffer, as the algorithm may modify it */
 	if (WARN_ON(ivsize > MAX_IVLEN))
@@ -1224,8 +1631,8 @@ static int test_aead_vec_cfg(const char *driver, int enc,
 						     vec->plen),
 					input, 2);
 	if (err) {
-		pr_err("alg: aead: %s %s: error preparing scatterlists for test vector %u, cfg=\"%s\"\n",
-		       driver, op, vec_num, cfg->name);
+		pr_err("alg: aead: %s %s: error preparing scatterlists for test vector %s, cfg=\"%s\"\n",
+		       driver, op, vec_name, cfg->name);
 		return err;
 	}
 
@@ -1235,23 +1642,12 @@ static int test_aead_vec_cfg(const char *driver, int enc,
 	aead_request_set_crypt(req, tsgls->src.sgl_ptr, tsgls->dst.sgl_ptr,
 			       enc ? vec->plen : vec->clen, iv);
 	aead_request_set_ad(req, vec->alen);
-	err = crypto_wait_req(enc ? crypto_aead_encrypt(req) :
-			      crypto_aead_decrypt(req), &wait);
-
-	aead_request_set_tfm(req, tfm); /* TODO: get rid of this */
-
-	if (err) {
-		if (err == -EBADMSG && vec->novrfy)
-			return 0;
-		pr_err("alg: aead: %s %s failed with err %d on test vector %u, cfg=\"%s\"\n",
-		       driver, op, err, vec_num, cfg->name);
-		return err;
-	}
-	if (vec->novrfy) {
-		pr_err("alg: aead: %s %s unexpectedly succeeded on test vector %u, cfg=\"%s\"\n",
-		       driver, op, vec_num, cfg->name);
-		return -EINVAL;
-	}
+	if (cfg->nosimd)
+		crypto_disable_simd_for_test();
+	err = enc ? crypto_aead_encrypt(req) : crypto_aead_decrypt(req);
+	if (cfg->nosimd)
+		crypto_reenable_simd_for_test();
+	err = crypto_wait_req(err, &wait);
 
 	/* Check that the algorithm didn't overwrite things it shouldn't have */
 	if (req->cryptlen != (enc ? vec->plen : vec->clen) ||
@@ -1263,8 +1659,8 @@ static int test_aead_vec_cfg(const char *driver, int enc,
 	    req->base.complete != crypto_req_done ||
 	    req->base.flags != req_flags ||
 	    req->base.data != &wait) {
-		pr_err("alg: aead: %s %s corrupted request struct on test vector %u, cfg=\"%s\"\n",
-		       driver, op, vec_num, cfg->name);
+		pr_err("alg: aead: %s %s corrupted request struct on test vector %s, cfg=\"%s\"\n",
+		       driver, op, vec_name, cfg->name);
 		if (req->cryptlen != (enc ? vec->plen : vec->clen))
 			pr_err("alg: aead: changed 'req->cryptlen'\n");
 		if (req->assoclen != vec->alen)
@@ -1286,14 +1682,29 @@ static int test_aead_vec_cfg(const char *driver, int enc,
 		return -EINVAL;
 	}
 	if (is_test_sglist_corrupted(&tsgls->src)) {
-		pr_err("alg: aead: %s %s corrupted src sgl on test vector %u, cfg=\"%s\"\n",
-		       driver, op, vec_num, cfg->name);
+		pr_err("alg: aead: %s %s corrupted src sgl on test vector %s, cfg=\"%s\"\n",
+		       driver, op, vec_name, cfg->name);
 		return -EINVAL;
 	}
 	if (tsgls->dst.sgl_ptr != tsgls->src.sgl &&
 	    is_test_sglist_corrupted(&tsgls->dst)) {
-		pr_err("alg: aead: %s %s corrupted dst sgl on test vector %u, cfg=\"%s\"\n",
-		       driver, op, vec_num, cfg->name);
+		pr_err("alg: aead: %s %s corrupted dst sgl on test vector %s, cfg=\"%s\"\n",
+		       driver, op, vec_name, cfg->name);
+		return -EINVAL;
+	}
+
+	/* Check for success or failure */
+	expected_error = vec->novrfy ? -EBADMSG : vec->crypt_error;
+	if (err) {
+		if (err == expected_error)
+			return 0;
+		pr_err("alg: aead: %s %s failed on test vector %s; expected_error=%d, actual_error=%d, cfg=\"%s\"\n",
+		       driver, op, vec_name, expected_error, err, cfg->name);
+		return err;
+	}
+	if (expected_error) {
+		pr_err("alg: aead: %s %s unexpectedly succeeded on test vector %s; expected_error=%d, cfg=\"%s\"\n",
+		       driver, op, vec_name, expected_error, cfg->name);
 		return -EINVAL;
 	}
 
@@ -1302,13 +1713,13 @@ static int test_aead_vec_cfg(const char *driver, int enc,
 				    enc ? vec->clen : vec->plen,
 				    vec->alen, enc || !cfg->inplace);
 	if (err == -EOVERFLOW) {
-		pr_err("alg: aead: %s %s overran dst buffer on test vector %u, cfg=\"%s\"\n",
-		       driver, op, vec_num, cfg->name);
+		pr_err("alg: aead: %s %s overran dst buffer on test vector %s, cfg=\"%s\"\n",
+		       driver, op, vec_name, cfg->name);
 		return err;
 	}
 	if (err) {
-		pr_err("alg: aead: %s %s test failed (wrong result) on test vector %u, cfg=\"%s\"\n",
-		       driver, op, vec_num, cfg->name);
+		pr_err("alg: aead: %s %s test failed (wrong result) on test vector %s, cfg=\"%s\"\n",
+		       driver, op, vec_name, cfg->name);
 		return err;
 	}
 
@@ -1320,14 +1731,17 @@ static int test_aead_vec(const char *driver, int enc,
 			 struct aead_request *req,
 			 struct cipher_test_sglists *tsgls)
 {
+	char vec_name[16];
 	unsigned int i;
 	int err;
 
 	if (enc && vec->novrfy)
 		return 0;
 
+	sprintf(vec_name, "%u", vec_num);
+
 	for (i = 0; i < ARRAY_SIZE(default_cipher_testvec_configs); i++) {
-		err = test_aead_vec_cfg(driver, enc, vec, vec_num,
+		err = test_aead_vec_cfg(driver, enc, vec, vec_name,
 					&default_cipher_testvec_configs[i],
 					req, tsgls);
 		if (err)
@@ -1342,7 +1756,7 @@ static int test_aead_vec(const char *driver, int enc,
 		for (i = 0; i < fuzz_iterations; i++) {
 			generate_random_testvec_config(&cfg, cfgname,
 						       sizeof(cfgname));
-			err = test_aead_vec_cfg(driver, enc, vec, vec_num,
+			err = test_aead_vec_cfg(driver, enc, vec, vec_name,
 						&cfg, req, tsgls);
 			if (err)
 				return err;
@@ -1352,6 +1766,226 @@ static int test_aead_vec(const char *driver, int enc,
 	return 0;
 }
 
+#ifdef CONFIG_CRYPTO_MANAGER_EXTRA_TESTS
+/*
+ * Generate an AEAD test vector from the given implementation.
+ * Assumes the buffers in 'vec' were already allocated.
+ */
+static void generate_random_aead_testvec(struct aead_request *req,
+					 struct aead_testvec *vec,
+					 unsigned int maxkeysize,
+					 unsigned int maxdatasize,
+					 char *name, size_t max_namelen)
+{
+	struct crypto_aead *tfm = crypto_aead_reqtfm(req);
+	const unsigned int ivsize = crypto_aead_ivsize(tfm);
+	unsigned int maxauthsize = crypto_aead_alg(tfm)->maxauthsize;
+	unsigned int authsize;
+	unsigned int total_len;
+	int i;
+	struct scatterlist src[2], dst;
+	u8 iv[MAX_IVLEN];
+	DECLARE_CRYPTO_WAIT(wait);
+
+	/* Key: length in [0, maxkeysize], but usually choose maxkeysize */
+	vec->klen = maxkeysize;
+	if (prandom_u32() % 4 == 0)
+		vec->klen = prandom_u32() % (maxkeysize + 1);
+	generate_random_bytes((u8 *)vec->key, vec->klen);
+	vec->setkey_error = crypto_aead_setkey(tfm, vec->key, vec->klen);
+
+	/* IV */
+	generate_random_bytes((u8 *)vec->iv, ivsize);
+
+	/* Tag length: in [0, maxauthsize], but usually choose maxauthsize */
+	authsize = maxauthsize;
+	if (prandom_u32() % 4 == 0)
+		authsize = prandom_u32() % (maxauthsize + 1);
+	if (WARN_ON(authsize > maxdatasize))
+		authsize = maxdatasize;
+	maxdatasize -= authsize;
+	vec->setauthsize_error = crypto_aead_setauthsize(tfm, authsize);
+
+	/* Plaintext and associated data */
+	total_len = generate_random_length(maxdatasize);
+	if (prandom_u32() % 4 == 0)
+		vec->alen = 0;
+	else
+		vec->alen = generate_random_length(total_len);
+	vec->plen = total_len - vec->alen;
+	generate_random_bytes((u8 *)vec->assoc, vec->alen);
+	generate_random_bytes((u8 *)vec->ptext, vec->plen);
+
+	vec->clen = vec->plen + authsize;
+
+	/*
+	 * If the key or authentication tag size couldn't be set, no need to
+	 * continue to encrypt.
+	 */
+	if (vec->setkey_error || vec->setauthsize_error)
+		goto done;
+
+	/* Ciphertext */
+	sg_init_table(src, 2);
+	i = 0;
+	if (vec->alen)
+		sg_set_buf(&src[i++], vec->assoc, vec->alen);
+	if (vec->plen)
+		sg_set_buf(&src[i++], vec->ptext, vec->plen);
+	sg_init_one(&dst, vec->ctext, vec->alen + vec->clen);
+	memcpy(iv, vec->iv, ivsize);
+	aead_request_set_callback(req, 0, crypto_req_done, &wait);
+	aead_request_set_crypt(req, src, &dst, vec->plen, iv);
+	aead_request_set_ad(req, vec->alen);
+	vec->crypt_error = crypto_wait_req(crypto_aead_encrypt(req), &wait);
+	if (vec->crypt_error == 0)
+		memmove((u8 *)vec->ctext, vec->ctext + vec->alen, vec->clen);
+done:
+	snprintf(name, max_namelen,
+		 "\"random: alen=%u plen=%u authsize=%u klen=%u\"",
+		 vec->alen, vec->plen, authsize, vec->klen);
+}
+
+/*
+ * Test the AEAD algorithm represented by @req against the corresponding generic
+ * implementation, if one is available.
+ */
+static int test_aead_vs_generic_impl(const char *driver,
+				     const struct alg_test_desc *test_desc,
+				     struct aead_request *req,
+				     struct cipher_test_sglists *tsgls)
+{
+	struct crypto_aead *tfm = crypto_aead_reqtfm(req);
+	const unsigned int ivsize = crypto_aead_ivsize(tfm);
+	const unsigned int maxauthsize = crypto_aead_alg(tfm)->maxauthsize;
+	const unsigned int blocksize = crypto_aead_blocksize(tfm);
+	const unsigned int maxdatasize = (2 * PAGE_SIZE) - TESTMGR_POISON_LEN;
+	const char *algname = crypto_aead_alg(tfm)->base.cra_name;
+	const char *generic_driver = test_desc->generic_driver;
+	char _generic_driver[CRYPTO_MAX_ALG_NAME];
+	struct crypto_aead *generic_tfm = NULL;
+	struct aead_request *generic_req = NULL;
+	unsigned int maxkeysize;
+	unsigned int i;
+	struct aead_testvec vec = { 0 };
+	char vec_name[64];
+	struct testvec_config cfg;
+	char cfgname[TESTVEC_CONFIG_NAMELEN];
+	int err;
+
+	if (noextratests)
+		return 0;
+
+	if (!generic_driver) { /* Use default naming convention? */
+		err = build_generic_driver_name(algname, _generic_driver);
+		if (err)
+			return err;
+		generic_driver = _generic_driver;
+	}
+
+	if (strcmp(generic_driver, driver) == 0) /* Already the generic impl? */
+		return 0;
+
+	generic_tfm = crypto_alloc_aead(generic_driver, 0, 0);
+	if (IS_ERR(generic_tfm)) {
+		err = PTR_ERR(generic_tfm);
+		if (err == -ENOENT) {
+			pr_warn("alg: aead: skipping comparison tests for %s because %s is unavailable\n",
+				driver, generic_driver);
+			return 0;
+		}
+		pr_err("alg: aead: error allocating %s (generic impl of %s): %d\n",
+		       generic_driver, algname, err);
+		return err;
+	}
+
+	generic_req = aead_request_alloc(generic_tfm, GFP_KERNEL);
+	if (!generic_req) {
+		err = -ENOMEM;
+		goto out;
+	}
+
+	/* Check the algorithm properties for consistency. */
+
+	if (maxauthsize != crypto_aead_alg(generic_tfm)->maxauthsize) {
+		pr_err("alg: aead: maxauthsize for %s (%u) doesn't match generic impl (%u)\n",
+		       driver, maxauthsize,
+		       crypto_aead_alg(generic_tfm)->maxauthsize);
+		err = -EINVAL;
+		goto out;
+	}
+
+	if (ivsize != crypto_aead_ivsize(generic_tfm)) {
+		pr_err("alg: aead: ivsize for %s (%u) doesn't match generic impl (%u)\n",
+		       driver, ivsize, crypto_aead_ivsize(generic_tfm));
+		err = -EINVAL;
+		goto out;
+	}
+
+	if (blocksize != crypto_aead_blocksize(generic_tfm)) {
+		pr_err("alg: aead: blocksize for %s (%u) doesn't match generic impl (%u)\n",
+		       driver, blocksize, crypto_aead_blocksize(generic_tfm));
+		err = -EINVAL;
+		goto out;
+	}
+
+	/*
+	 * Now generate test vectors using the generic implementation, and test
+	 * the other implementation against them.
+	 */
+
+	maxkeysize = 0;
+	for (i = 0; i < test_desc->suite.aead.count; i++)
+		maxkeysize = max_t(unsigned int, maxkeysize,
+				   test_desc->suite.aead.vecs[i].klen);
+
+	vec.key = kmalloc(maxkeysize, GFP_KERNEL);
+	vec.iv = kmalloc(ivsize, GFP_KERNEL);
+	vec.assoc = kmalloc(maxdatasize, GFP_KERNEL);
+	vec.ptext = kmalloc(maxdatasize, GFP_KERNEL);
+	vec.ctext = kmalloc(maxdatasize, GFP_KERNEL);
+	if (!vec.key || !vec.iv || !vec.assoc || !vec.ptext || !vec.ctext) {
+		err = -ENOMEM;
+		goto out;
+	}
+
+	for (i = 0; i < fuzz_iterations * 8; i++) {
+		generate_random_aead_testvec(generic_req, &vec,
+					     maxkeysize, maxdatasize,
+					     vec_name, sizeof(vec_name));
+		generate_random_testvec_config(&cfg, cfgname, sizeof(cfgname));
+
+		err = test_aead_vec_cfg(driver, ENCRYPT, &vec, vec_name, &cfg,
+					req, tsgls);
+		if (err)
+			goto out;
+		err = test_aead_vec_cfg(driver, DECRYPT, &vec, vec_name, &cfg,
+					req, tsgls);
+		if (err)
+			goto out;
+		cond_resched();
+	}
+	err = 0;
+out:
+	kfree(vec.key);
+	kfree(vec.iv);
+	kfree(vec.assoc);
+	kfree(vec.ptext);
+	kfree(vec.ctext);
+	crypto_free_aead(generic_tfm);
+	aead_request_free(generic_req);
+	return err;
+}
+#else /* !CONFIG_CRYPTO_MANAGER_EXTRA_TESTS */
+static int test_aead_vs_generic_impl(const char *driver,
+				     const struct alg_test_desc *test_desc,
+				     struct aead_request *req,
+				     struct cipher_test_sglists *tsgls)
+{
+	return 0;
+}
+#endif /* !CONFIG_CRYPTO_MANAGER_EXTRA_TESTS */
+
 static int test_aead(const char *driver, int enc,
 		     const struct aead_test_suite *suite,
 		     struct aead_request *req,
@@ -1411,6 +2045,10 @@ static int alg_test_aead(const struct alg_test_desc *desc, const char *driver,
 		goto out;
 
 	err = test_aead(driver, DECRYPT, suite, req, tsgls);
+	if (err)
+		goto out;
+
+	err = test_aead_vs_generic_impl(driver, desc, req, tsgls);
 out:
 	free_cipher_test_sglists(tsgls);
 	aead_request_free(req);
@@ -1462,13 +2100,20 @@ static int test_cipher(struct crypto_cipher *tfm, int enc,
 
 		ret = crypto_cipher_setkey(tfm, template[i].key,
 					   template[i].klen);
-		if (template[i].fail == !ret) {
-			printk(KERN_ERR "alg: cipher: setkey failed "
-			       "on test %d for %s: flags=%x\n", j,
-			       algo, crypto_cipher_get_flags(tfm));
+		if (ret) {
+			if (ret == template[i].setkey_error)
+				continue;
+			pr_err("alg: cipher: %s setkey failed on test vector %u; expected_error=%d, actual_error=%d, flags=%#x\n",
+			       algo, j, template[i].setkey_error, ret,
+			       crypto_cipher_get_flags(tfm));
 			goto out;
-		} else if (ret)
-			continue;
+		}
+		if (template[i].setkey_error) {
+			pr_err("alg: cipher: %s setkey unexpectedly succeeded on test vector %u; expected_error=%d\n",
+			       algo, j, template[i].setkey_error);
+			ret = -EINVAL;
+			goto out;
+		}
 
 		for (k = 0; k < template[i].len;
 		     k += crypto_cipher_blocksize(tfm)) {
@@ -1500,7 +2145,7 @@ out_nobuf:
 
 static int test_skcipher_vec_cfg(const char *driver, int enc,
 				 const struct cipher_testvec *vec,
-				 unsigned int vec_num,
+				 const char *vec_name,
 				 const struct testvec_config *cfg,
 				 struct skcipher_request *req,
 				 struct cipher_test_sglists *tsgls)
@@ -1526,15 +2171,16 @@ static int test_skcipher_vec_cfg(const char *driver, int enc,
 					    CRYPTO_TFM_REQ_FORBID_WEAK_KEYS);
 	err = crypto_skcipher_setkey(tfm, vec->key, vec->klen);
 	if (err) {
-		if (vec->fail) /* expectedly failed to set key? */
+		if (err == vec->setkey_error)
 			return 0;
-		pr_err("alg: skcipher: %s setkey failed with err %d on test vector %u; flags=%#x\n",
-		       driver, err, vec_num, crypto_skcipher_get_flags(tfm));
+		pr_err("alg: skcipher: %s setkey failed on test vector %s; expected_error=%d, actual_error=%d, flags=%#x\n",
+		       driver, vec_name, vec->setkey_error, err,
+		       crypto_skcipher_get_flags(tfm));
 		return err;
 	}
-	if (vec->fail) {
-		pr_err("alg: skcipher: %s setkey unexpectedly succeeded on test vector %u\n",
-		       driver, vec_num);
+	if (vec->setkey_error) {
+		pr_err("alg: skcipher: %s setkey unexpectedly succeeded on test vector %s; expected_error=%d\n",
+		       driver, vec_name, vec->setkey_error);
 		return -EINVAL;
 	}
 
@@ -1550,8 +2196,8 @@ static int test_skcipher_vec_cfg(const char *driver, int enc,
 			memset(iv, 0, ivsize);
 	} else {
 		if (vec->generates_iv) {
-			pr_err("alg: skcipher: %s has ivsize=0 but test vector %u generates IV!\n",
-			       driver, vec_num);
+			pr_err("alg: skcipher: %s has ivsize=0 but test vector %s generates IV!\n",
+			       driver, vec_name);
 			return -EINVAL;
 		}
 		iv = NULL;
@@ -1563,8 +2209,8 @@ static int test_skcipher_vec_cfg(const char *driver, int enc,
 	err = build_cipher_test_sglists(tsgls, cfg, alignmask,
 					vec->len, vec->len, &input, 1);
 	if (err) {
-		pr_err("alg: skcipher: %s %s: error preparing scatterlists for test vector %u, cfg=\"%s\"\n",
-		       driver, op, vec_num, cfg->name);
+		pr_err("alg: skcipher: %s %s: error preparing scatterlists for test vector %s, cfg=\"%s\"\n",
+		       driver, op, vec_name, cfg->name);
 		return err;
 	}
 
@@ -1573,13 +2219,12 @@ static int test_skcipher_vec_cfg(const char *driver, int enc,
 	skcipher_request_set_callback(req, req_flags, crypto_req_done, &wait);
 	skcipher_request_set_crypt(req, tsgls->src.sgl_ptr, tsgls->dst.sgl_ptr,
 				   vec->len, iv);
-	err = crypto_wait_req(enc ? crypto_skcipher_encrypt(req) :
-			      crypto_skcipher_decrypt(req), &wait);
-	if (err) {
-		pr_err("alg: skcipher: %s %s failed with err %d on test vector %u, cfg=\"%s\"\n",
-		       driver, op, err, vec_num, cfg->name);
-		return err;
-	}
+	if (cfg->nosimd)
+		crypto_disable_simd_for_test();
+	err = enc ? crypto_skcipher_encrypt(req) : crypto_skcipher_decrypt(req);
+	if (cfg->nosimd)
+		crypto_reenable_simd_for_test();
+	err = crypto_wait_req(err, &wait);
 
 	/* Check that the algorithm didn't overwrite things it shouldn't have */
 	if (req->cryptlen != vec->len ||
@@ -1590,8 +2235,8 @@ static int test_skcipher_vec_cfg(const char *driver, int enc,
 	    req->base.complete != crypto_req_done ||
 	    req->base.flags != req_flags ||
 	    req->base.data != &wait) {
-		pr_err("alg: skcipher: %s %s corrupted request struct on test vector %u, cfg=\"%s\"\n",
-		       driver, op, vec_num, cfg->name);
+		pr_err("alg: skcipher: %s %s corrupted request struct on test vector %s, cfg=\"%s\"\n",
+		       driver, op, vec_name, cfg->name);
 		if (req->cryptlen != vec->len)
 			pr_err("alg: skcipher: changed 'req->cryptlen'\n");
 		if (req->iv != iv)
@@ -1611,14 +2256,28 @@ static int test_skcipher_vec_cfg(const char *driver, int enc,
 		return -EINVAL;
 	}
 	if (is_test_sglist_corrupted(&tsgls->src)) {
-		pr_err("alg: skcipher: %s %s corrupted src sgl on test vector %u, cfg=\"%s\"\n",
-		       driver, op, vec_num, cfg->name);
+		pr_err("alg: skcipher: %s %s corrupted src sgl on test vector %s, cfg=\"%s\"\n",
+		       driver, op, vec_name, cfg->name);
 		return -EINVAL;
 	}
 	if (tsgls->dst.sgl_ptr != tsgls->src.sgl &&
 	    is_test_sglist_corrupted(&tsgls->dst)) {
-		pr_err("alg: skcipher: %s %s corrupted dst sgl on test vector %u, cfg=\"%s\"\n",
-		       driver, op, vec_num, cfg->name);
+		pr_err("alg: skcipher: %s %s corrupted dst sgl on test vector %s, cfg=\"%s\"\n",
+		       driver, op, vec_name, cfg->name);
+		return -EINVAL;
+	}
+
+	/* Check for success or failure */
+	if (err) {
+		if (err == vec->crypt_error)
+			return 0;
+		pr_err("alg: skcipher: %s %s failed on test vector %s; expected_error=%d, actual_error=%d, cfg=\"%s\"\n",
+		       driver, op, vec_name, vec->crypt_error, err, cfg->name);
+		return err;
+	}
+	if (vec->crypt_error) {
+		pr_err("alg: skcipher: %s %s unexpectedly succeeded on test vector %s; expected_error=%d, cfg=\"%s\"\n",
+		       driver, op, vec_name, vec->crypt_error, cfg->name);
 		return -EINVAL;
 	}
 
@@ -1626,20 +2285,20 @@ static int test_skcipher_vec_cfg(const char *driver, int enc,
 	err = verify_correct_output(&tsgls->dst, enc ? vec->ctext : vec->ptext,
 				    vec->len, 0, true);
 	if (err == -EOVERFLOW) {
-		pr_err("alg: skcipher: %s %s overran dst buffer on test vector %u, cfg=\"%s\"\n",
-		       driver, op, vec_num, cfg->name);
+		pr_err("alg: skcipher: %s %s overran dst buffer on test vector %s, cfg=\"%s\"\n",
+		       driver, op, vec_name, cfg->name);
 		return err;
 	}
 	if (err) {
-		pr_err("alg: skcipher: %s %s test failed (wrong result) on test vector %u, cfg=\"%s\"\n",
-		       driver, op, vec_num, cfg->name);
+		pr_err("alg: skcipher: %s %s test failed (wrong result) on test vector %s, cfg=\"%s\"\n",
+		       driver, op, vec_name, cfg->name);
 		return err;
 	}
 
 	/* If applicable, check that the algorithm generated the correct IV */
 	if (vec->iv_out && memcmp(iv, vec->iv_out, ivsize) != 0) {
-		pr_err("alg: skcipher: %s %s test failed (wrong output IV) on test vector %u, cfg=\"%s\"\n",
-		       driver, op, vec_num, cfg->name);
+		pr_err("alg: skcipher: %s %s test failed (wrong output IV) on test vector %s, cfg=\"%s\"\n",
+		       driver, op, vec_name, cfg->name);
 		hexdump(iv, ivsize);
 		return -EINVAL;
 	}
@@ -1653,14 +2312,17 @@ static int test_skcipher_vec(const char *driver, int enc,
 			     struct skcipher_request *req,
 			     struct cipher_test_sglists *tsgls)
 {
+	char vec_name[16];
 	unsigned int i;
 	int err;
 
 	if (fips_enabled && vec->fips_skip)
 		return 0;
 
+	sprintf(vec_name, "%u", vec_num);
+
 	for (i = 0; i < ARRAY_SIZE(default_cipher_testvec_configs); i++) {
-		err = test_skcipher_vec_cfg(driver, enc, vec, vec_num,
+		err = test_skcipher_vec_cfg(driver, enc, vec, vec_name,
 					    &default_cipher_testvec_configs[i],
 					    req, tsgls);
 		if (err)
@@ -1675,7 +2337,7 @@ static int test_skcipher_vec(const char *driver, int enc,
 		for (i = 0; i < fuzz_iterations; i++) {
 			generate_random_testvec_config(&cfg, cfgname,
 						       sizeof(cfgname));
-			err = test_skcipher_vec_cfg(driver, enc, vec, vec_num,
+			err = test_skcipher_vec_cfg(driver, enc, vec, vec_name,
 						    &cfg, req, tsgls);
 			if (err)
 				return err;
@@ -1685,6 +2347,186 @@ static int test_skcipher_vec(const char *driver, int enc,
 	return 0;
 }
 
+#ifdef CONFIG_CRYPTO_MANAGER_EXTRA_TESTS
+/*
+ * Generate a symmetric cipher test vector from the given implementation.
+ * Assumes the buffers in 'vec' were already allocated.
+ */
+static void generate_random_cipher_testvec(struct skcipher_request *req,
+					   struct cipher_testvec *vec,
+					   unsigned int maxdatasize,
+					   char *name, size_t max_namelen)
+{
+	struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(req);
+	const unsigned int maxkeysize = tfm->keysize;
+	const unsigned int ivsize = crypto_skcipher_ivsize(tfm);
+	struct scatterlist src, dst;
+	u8 iv[MAX_IVLEN];
+	DECLARE_CRYPTO_WAIT(wait);
+
+	/* Key: length in [0, maxkeysize], but usually choose maxkeysize */
+	vec->klen = maxkeysize;
+	if (prandom_u32() % 4 == 0)
+		vec->klen = prandom_u32() % (maxkeysize + 1);
+	generate_random_bytes((u8 *)vec->key, vec->klen);
+	vec->setkey_error = crypto_skcipher_setkey(tfm, vec->key, vec->klen);
+
+	/* IV */
+	generate_random_bytes((u8 *)vec->iv, ivsize);
+
+	/* Plaintext */
+	vec->len = generate_random_length(maxdatasize);
+	generate_random_bytes((u8 *)vec->ptext, vec->len);
+
+	/* If the key couldn't be set, no need to continue to encrypt. */
+	if (vec->setkey_error)
+		goto done;
+
+	/* Ciphertext */
+	sg_init_one(&src, vec->ptext, vec->len);
+	sg_init_one(&dst, vec->ctext, vec->len);
+	memcpy(iv, vec->iv, ivsize);
+	skcipher_request_set_callback(req, 0, crypto_req_done, &wait);
+	skcipher_request_set_crypt(req, &src, &dst, vec->len, iv);
+	vec->crypt_error = crypto_wait_req(crypto_skcipher_encrypt(req), &wait);
+done:
+	snprintf(name, max_namelen, "\"random: len=%u klen=%u\"",
+		 vec->len, vec->klen);
+}
+
+/*
+ * Test the skcipher algorithm represented by @req against the corresponding
+ * generic implementation, if one is available.
+ */
+static int test_skcipher_vs_generic_impl(const char *driver,
+					 const char *generic_driver,
+					 struct skcipher_request *req,
+					 struct cipher_test_sglists *tsgls)
+{
+	struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(req);
+	const unsigned int ivsize = crypto_skcipher_ivsize(tfm);
+	const unsigned int blocksize = crypto_skcipher_blocksize(tfm);
+	const unsigned int maxdatasize = (2 * PAGE_SIZE) - TESTMGR_POISON_LEN;
+	const char *algname = crypto_skcipher_alg(tfm)->base.cra_name;
+	char _generic_driver[CRYPTO_MAX_ALG_NAME];
+	struct crypto_skcipher *generic_tfm = NULL;
+	struct skcipher_request *generic_req = NULL;
+	unsigned int i;
+	struct cipher_testvec vec = { 0 };
+	char vec_name[64];
+	struct testvec_config cfg;
+	char cfgname[TESTVEC_CONFIG_NAMELEN];
+	int err;
+
+	if (noextratests)
+		return 0;
+
+	/* Keywrap isn't supported here yet as it handles its IV differently. */
+	if (strncmp(algname, "kw(", 3) == 0)
+		return 0;
+
+	if (!generic_driver) { /* Use default naming convention? */
+		err = build_generic_driver_name(algname, _generic_driver);
+		if (err)
+			return err;
+		generic_driver = _generic_driver;
+	}
+
+	if (strcmp(generic_driver, driver) == 0) /* Already the generic impl? */
+		return 0;
+
+	generic_tfm = crypto_alloc_skcipher(generic_driver, 0, 0);
+	if (IS_ERR(generic_tfm)) {
+		err = PTR_ERR(generic_tfm);
+		if (err == -ENOENT) {
+			pr_warn("alg: skcipher: skipping comparison tests for %s because %s is unavailable\n",
+				driver, generic_driver);
+			return 0;
+		}
+		pr_err("alg: skcipher: error allocating %s (generic impl of %s): %d\n",
+		       generic_driver, algname, err);
+		return err;
+	}
+
+	generic_req = skcipher_request_alloc(generic_tfm, GFP_KERNEL);
+	if (!generic_req) {
+		err = -ENOMEM;
+		goto out;
+	}
+
+	/* Check the algorithm properties for consistency. */
+
+	if (tfm->keysize != generic_tfm->keysize) {
+		pr_err("alg: skcipher: max keysize for %s (%u) doesn't match generic impl (%u)\n",
+		       driver, tfm->keysize, generic_tfm->keysize);
+		err = -EINVAL;
+		goto out;
+	}
+
+	if (ivsize != crypto_skcipher_ivsize(generic_tfm)) {
+		pr_err("alg: skcipher: ivsize for %s (%u) doesn't match generic impl (%u)\n",
+		       driver, ivsize, crypto_skcipher_ivsize(generic_tfm));
+		err = -EINVAL;
+		goto out;
+	}
+
+	if (blocksize != crypto_skcipher_blocksize(generic_tfm)) {
+		pr_err("alg: skcipher: blocksize for %s (%u) doesn't match generic impl (%u)\n",
+		       driver, blocksize,
+		       crypto_skcipher_blocksize(generic_tfm));
+		err = -EINVAL;
+		goto out;
+	}
+
+	/*
+	 * Now generate test vectors using the generic implementation, and test
+	 * the other implementation against them.
+	 */
+
+	vec.key = kmalloc(tfm->keysize, GFP_KERNEL);
+	vec.iv = kmalloc(ivsize, GFP_KERNEL);
+	vec.ptext = kmalloc(maxdatasize, GFP_KERNEL);
+	vec.ctext = kmalloc(maxdatasize, GFP_KERNEL);
+	if (!vec.key || !vec.iv || !vec.ptext || !vec.ctext) {
+		err = -ENOMEM;
+		goto out;
+	}
+
+	for (i = 0; i < fuzz_iterations * 8; i++) {
+		generate_random_cipher_testvec(generic_req, &vec, maxdatasize,
+					       vec_name, sizeof(vec_name));
+		generate_random_testvec_config(&cfg, cfgname, sizeof(cfgname));
+
+		err = test_skcipher_vec_cfg(driver, ENCRYPT, &vec, vec_name,
+					    &cfg, req, tsgls);
+		if (err)
+			goto out;
+		err = test_skcipher_vec_cfg(driver, DECRYPT, &vec, vec_name,
+					    &cfg, req, tsgls);
+		if (err)
+			goto out;
+		cond_resched();
+	}
+	err = 0;
+out:
+	kfree(vec.key);
+	kfree(vec.iv);
+	kfree(vec.ptext);
+	kfree(vec.ctext);
+	crypto_free_skcipher(generic_tfm);
+	skcipher_request_free(generic_req);
+	return err;
+}
+#else /* !CONFIG_CRYPTO_MANAGER_EXTRA_TESTS */
+static int test_skcipher_vs_generic_impl(const char *driver,
+					 const char *generic_driver,
+					 struct skcipher_request *req,
+					 struct cipher_test_sglists *tsgls)
+{
+	return 0;
+}
+#endif /* !CONFIG_CRYPTO_MANAGER_EXTRA_TESTS */
+
 static int test_skcipher(const char *driver, int enc,
 			 const struct cipher_test_suite *suite,
 			 struct skcipher_request *req,
@@ -1744,6 +2586,11 @@ static int alg_test_skcipher(const struct alg_test_desc *desc,
 		goto out;
 
 	err = test_skcipher(driver, DECRYPT, suite, req, tsgls);
+	if (err)
+		goto out;
+
+	err = test_skcipher_vs_generic_impl(driver, desc->generic_driver, req,
+					    tsgls);
 out:
 	free_cipher_test_sglists(tsgls);
 	skcipher_request_free(req);
@@ -2179,7 +3026,6 @@ static int alg_test_crc32c(const struct alg_test_desc *desc,
 		u32 *ctx = (u32 *)shash_desc_ctx(shash);
 
 		shash->tfm = tfm;
-		shash->flags = 0;
 
 		*ctx = 420553207;
 		err = crypto_shash_final(shash, (u8 *)&val);
@@ -2493,6 +3339,12 @@ static int alg_test_kpp(const struct alg_test_desc *desc, const char *driver,
 	return err;
 }
 
+static u8 *test_pack_u32(u8 *dst, u32 val)
+{
+	memcpy(dst, &val, sizeof(val));
+	return dst + sizeof(val);
+}
+
 static int test_akcipher_one(struct crypto_akcipher *tfm,
 			     const struct akcipher_testvec *vecs)
 {
@@ -2503,10 +3355,11 @@ static int test_akcipher_one(struct crypto_akcipher *tfm,
 	struct crypto_wait wait;
 	unsigned int out_len_max, out_len = 0;
 	int err = -ENOMEM;
-	struct scatterlist src, dst, src_tab[2];
+	struct scatterlist src, dst, src_tab[3];
 	const char *m, *c;
 	unsigned int m_size, c_size;
 	const char *op;
+	u8 *key, *ptr;
 
 	if (testmgr_alloc_buf(xbuf))
 		return err;
@@ -2517,22 +3370,29 @@ static int test_akcipher_one(struct crypto_akcipher *tfm,
 
 	crypto_init_wait(&wait);
 
+	key = kmalloc(vecs->key_len + sizeof(u32) * 2 + vecs->param_len,
+		      GFP_KERNEL);
+	if (!key)
+		goto free_xbuf;
+	memcpy(key, vecs->key, vecs->key_len);
+	ptr = key + vecs->key_len;
+	ptr = test_pack_u32(ptr, vecs->algo);
+	ptr = test_pack_u32(ptr, vecs->param_len);
+	memcpy(ptr, vecs->params, vecs->param_len);
+
 	if (vecs->public_key_vec)
-		err = crypto_akcipher_set_pub_key(tfm, vecs->key,
-						  vecs->key_len);
+		err = crypto_akcipher_set_pub_key(tfm, key, vecs->key_len);
 	else
-		err = crypto_akcipher_set_priv_key(tfm, vecs->key,
-						   vecs->key_len);
+		err = crypto_akcipher_set_priv_key(tfm, key, vecs->key_len);
 	if (err)
 		goto free_req;
 
-	err = -ENOMEM;
-	out_len_max = crypto_akcipher_maxsize(tfm);
-
 	/*
 	 * First run test which do not require a private key, such as
 	 * encrypt or verify.
 	 */
+	err = -ENOMEM;
+	out_len_max = crypto_akcipher_maxsize(tfm);
 	outbuf_enc = kzalloc(out_len_max, GFP_KERNEL);
 	if (!outbuf_enc)
 		goto free_req;
@@ -2558,12 +3418,20 @@ static int test_akcipher_one(struct crypto_akcipher *tfm,
 		goto free_all;
 	memcpy(xbuf[0], m, m_size);
 
-	sg_init_table(src_tab, 2);
+	sg_init_table(src_tab, 3);
 	sg_set_buf(&src_tab[0], xbuf[0], 8);
 	sg_set_buf(&src_tab[1], xbuf[0] + 8, m_size - 8);
-	sg_init_one(&dst, outbuf_enc, out_len_max);
-	akcipher_request_set_crypt(req, src_tab, &dst, m_size,
-				   out_len_max);
+	if (vecs->siggen_sigver_test) {
+		if (WARN_ON(c_size > PAGE_SIZE))
+			goto free_all;
+		memcpy(xbuf[1], c, c_size);
+		sg_set_buf(&src_tab[2], xbuf[1], c_size);
+		akcipher_request_set_crypt(req, src_tab, NULL, m_size, c_size);
+	} else {
+		sg_init_one(&dst, outbuf_enc, out_len_max);
+		akcipher_request_set_crypt(req, src_tab, &dst, m_size,
+					   out_len_max);
+	}
 	akcipher_request_set_callback(req, CRYPTO_TFM_REQ_MAY_BACKLOG,
 				      crypto_req_done, &wait);
 
@@ -2576,18 +3444,21 @@ static int test_akcipher_one(struct crypto_akcipher *tfm,
 		pr_err("alg: akcipher: %s test failed. err %d\n", op, err);
 		goto free_all;
 	}
-	if (req->dst_len != c_size) {
-		pr_err("alg: akcipher: %s test failed. Invalid output len\n",
-		       op);
-		err = -EINVAL;
-		goto free_all;
-	}
-	/* verify that encrypted message is equal to expected */
-	if (memcmp(c, outbuf_enc, c_size)) {
-		pr_err("alg: akcipher: %s test failed. Invalid output\n", op);
-		hexdump(outbuf_enc, c_size);
-		err = -EINVAL;
-		goto free_all;
+	if (!vecs->siggen_sigver_test) {
+		if (req->dst_len != c_size) {
+			pr_err("alg: akcipher: %s test failed. Invalid output len\n",
+			       op);
+			err = -EINVAL;
+			goto free_all;
+		}
+		/* verify that encrypted message is equal to expected */
+		if (memcmp(c, outbuf_enc, c_size) != 0) {
+			pr_err("alg: akcipher: %s test failed. Invalid output\n",
+			       op);
+			hexdump(outbuf_enc, c_size);
+			err = -EINVAL;
+			goto free_all;
+		}
 	}
 
 	/*
@@ -2642,6 +3513,7 @@ free_all:
 	kfree(outbuf_enc);
 free_req:
 	akcipher_request_free(req);
+	kfree(key);
 free_xbuf:
 	testmgr_free_buf(xbuf);
 	return err;
@@ -2699,12 +3571,14 @@ static int alg_test_null(const struct alg_test_desc *desc,
 static const struct alg_test_desc alg_test_descs[] = {
 	{
 		.alg = "adiantum(xchacha12,aes)",
+		.generic_driver = "adiantum(xchacha12-generic,aes-generic,nhpoly1305-generic)",
 		.test = alg_test_skcipher,
 		.suite = {
 			.cipher = __VECS(adiantum_xchacha12_aes_tv_template)
 		},
 	}, {
 		.alg = "adiantum(xchacha20,aes)",
+		.generic_driver = "adiantum(xchacha20-generic,aes-generic,nhpoly1305-generic)",
 		.test = alg_test_skcipher,
 		.suite = {
 			.cipher = __VECS(adiantum_xchacha20_aes_tv_template)
@@ -2921,6 +3795,12 @@ static const struct alg_test_desc alg_test_descs[] = {
 		.test = alg_test_null,
 		.fips_allowed = 1,
 	}, {
+		/* Same as cbc(sm4) except the key is stored in
+		 * hardware secure memory which we reference by index
+		 */
+		.alg = "cbc(psm4)",
+		.test = alg_test_null,
+	}, {
 		.alg = "cbc(serpent)",
 		.test = alg_test_skcipher,
 		.suite = {
@@ -2947,6 +3827,7 @@ static const struct alg_test_desc alg_test_descs[] = {
 		}
 	}, {
 		.alg = "ccm(aes)",
+		.generic_driver = "ccm_base(ctr(aes-generic),cbcmac(aes-generic))",
 		.test = alg_test_aead,
 		.fips_allowed = 1,
 		.suite = {
@@ -3055,6 +3936,13 @@ static const struct alg_test_desc alg_test_descs[] = {
 		.test = alg_test_null,
 		.fips_allowed = 1,
 	}, {
+
+		/* Same as ctr(sm4) except the key is stored in
+		 * hardware secure memory which we reference by index
+		 */
+		.alg = "ctr(psm4)",
+		.test = alg_test_null,
+	}, {
 		.alg = "ctr(serpent)",
 		.test = alg_test_skcipher,
 		.suite = {
@@ -3080,6 +3968,13 @@ static const struct alg_test_desc alg_test_descs[] = {
 			.cipher = __VECS(cts_mode_tv_template)
 		}
 	}, {
+		/* Same as cts(cbc((aes)) except the key is stored in
+		 * hardware secure memory which we reference by index
+		 */
+		.alg = "cts(cbc(paes))",
+		.test = alg_test_null,
+		.fips_allowed = 1,
+	}, {
 		.alg = "deflate",
 		.test = alg_test_comp,
 		.fips_allowed = 1,
@@ -3358,7 +4253,14 @@ static const struct alg_test_desc alg_test_descs[] = {
 			.kpp = __VECS(ecdh_tv_template)
 		}
 	}, {
+		.alg = "ecrdsa",
+		.test = alg_test_akcipher,
+		.suite = {
+			.akcipher = __VECS(ecrdsa_tv_template)
+		}
+	}, {
 		.alg = "gcm(aes)",
+		.generic_driver = "gcm_base(ctr(aes-generic),ghash-generic)",
 		.test = alg_test_aead,
 		.fips_allowed = 1,
 		.suite = {
@@ -3477,30 +4379,35 @@ static const struct alg_test_desc alg_test_descs[] = {
 		}
 	}, {
 		.alg = "lrw(aes)",
+		.generic_driver = "lrw(ecb(aes-generic))",
 		.test = alg_test_skcipher,
 		.suite = {
 			.cipher = __VECS(aes_lrw_tv_template)
 		}
 	}, {
 		.alg = "lrw(camellia)",
+		.generic_driver = "lrw(ecb(camellia-generic))",
 		.test = alg_test_skcipher,
 		.suite = {
 			.cipher = __VECS(camellia_lrw_tv_template)
 		}
 	}, {
 		.alg = "lrw(cast6)",
+		.generic_driver = "lrw(ecb(cast6-generic))",
 		.test = alg_test_skcipher,
 		.suite = {
 			.cipher = __VECS(cast6_lrw_tv_template)
 		}
 	}, {
 		.alg = "lrw(serpent)",
+		.generic_driver = "lrw(ecb(serpent-generic))",
 		.test = alg_test_skcipher,
 		.suite = {
 			.cipher = __VECS(serpent_lrw_tv_template)
 		}
 	}, {
 		.alg = "lrw(twofish)",
+		.generic_driver = "lrw(ecb(twofish-generic))",
 		.test = alg_test_skcipher,
 		.suite = {
 			.cipher = __VECS(tf_lrw_tv_template)
@@ -3625,6 +4532,7 @@ static const struct alg_test_desc alg_test_descs[] = {
 		}
 	}, {
 		.alg = "rfc4106(gcm(aes))",
+		.generic_driver = "rfc4106(gcm_base(ctr(aes-generic),ghash-generic))",
 		.test = alg_test_aead,
 		.fips_allowed = 1,
 		.suite = {
@@ -3632,6 +4540,7 @@ static const struct alg_test_desc alg_test_descs[] = {
 		}
 	}, {
 		.alg = "rfc4309(ccm(aes))",
+		.generic_driver = "rfc4309(ccm_base(ctr(aes-generic),cbcmac(aes-generic)))",
 		.test = alg_test_aead,
 		.fips_allowed = 1,
 		.suite = {
@@ -3639,6 +4548,7 @@ static const struct alg_test_desc alg_test_descs[] = {
 		}
 	}, {
 		.alg = "rfc4543(gcm(aes))",
+		.generic_driver = "rfc4543(gcm_base(ctr(aes-generic),ghash-generic))",
 		.test = alg_test_aead,
 		.suite = {
 			.aead = __VECS(aes_gcm_rfc4543_tv_template)
@@ -3835,6 +4745,7 @@ static const struct alg_test_desc alg_test_descs[] = {
 		},
 	}, {
 		.alg = "xts(aes)",
+		.generic_driver = "xts(ecb(aes-generic))",
 		.test = alg_test_skcipher,
 		.fips_allowed = 1,
 		.suite = {
@@ -3842,12 +4753,14 @@ static const struct alg_test_desc alg_test_descs[] = {
 		}
 	}, {
 		.alg = "xts(camellia)",
+		.generic_driver = "xts(ecb(camellia-generic))",
 		.test = alg_test_skcipher,
 		.suite = {
 			.cipher = __VECS(camellia_xts_tv_template)
 		}
 	}, {
 		.alg = "xts(cast6)",
+		.generic_driver = "xts(ecb(cast6-generic))",
 		.test = alg_test_skcipher,
 		.suite = {
 			.cipher = __VECS(cast6_xts_tv_template)
@@ -3861,12 +4774,14 @@ static const struct alg_test_desc alg_test_descs[] = {
 		.fips_allowed = 1,
 	}, {
 		.alg = "xts(serpent)",
+		.generic_driver = "xts(ecb(serpent-generic))",
 		.test = alg_test_skcipher,
 		.suite = {
 			.cipher = __VECS(serpent_xts_tv_template)
 		}
 	}, {
 		.alg = "xts(twofish)",
+		.generic_driver = "xts(ecb(twofish-generic))",
 		.test = alg_test_skcipher,
 		.suite = {
 			.cipher = __VECS(tf_xts_tv_template)
@@ -4020,8 +4935,9 @@ int alg_test(const char *driver, const char *alg, u32 type, u32 mask)
 					     type, mask);
 
 test_done:
-	if (fips_enabled && rc)
-		panic("%s: %s alg self test failed in fips mode!\n", driver, alg);
+	if (rc && (fips_enabled || panic_on_fail))
+		panic("alg: self-tests for %s (%s) failed in %s mode!\n",
+		      driver, alg, fips_enabled ? "fips" : "panic_on_fail");
 
 	if (fips_enabled && !rc)
 		pr_info("alg: self-tests for %s (%s) passed\n", driver, alg);
diff --git a/crypto/testmgr.h b/crypto/testmgr.h
index f267633cf13a..b6daae1f6a1d 100644
--- a/crypto/testmgr.h
+++ b/crypto/testmgr.h
@@ -25,6 +25,8 @@
 #ifndef _CRYPTO_TESTMGR_H
 #define _CRYPTO_TESTMGR_H
 
+#include <linux/oid_registry.h>
+
 #define MAX_IVLEN		32
 
 /*
@@ -34,6 +36,8 @@
  * @digest:	Pointer to expected digest
  * @psize:	Length of source data in bytes
  * @ksize:	Length of @key in bytes (0 if no key)
+ * @setkey_error: Expected error from setkey()
+ * @digest_error: Expected error from digest()
  */
 struct hash_testvec {
 	const char *key;
@@ -41,6 +45,8 @@ struct hash_testvec {
 	const char *digest;
 	unsigned short psize;
 	unsigned short ksize;
+	int setkey_error;
+	int digest_error;
 };
 
 /*
@@ -52,12 +58,13 @@ struct hash_testvec {
  * @ptext:	Pointer to plaintext
  * @ctext:	Pointer to ciphertext
  * @len:	Length of @ptext and @ctext in bytes
- * @fail:	If set to one, the test need to fail
  * @wk:		Does the test need CRYPTO_TFM_REQ_FORBID_WEAK_KEYS?
  * 		( e.g. test needs to fail due to a weak key )
  * @fips_skip:	Skip the test vector in FIPS mode
  * @generates_iv: Encryption should ignore the given IV, and output @iv_out.
  *		  Decryption takes @iv_out.  Needed for AES Keywrap ("kw(aes)").
+ * @setkey_error: Expected error from setkey()
+ * @crypt_error: Expected error from encrypt() and decrypt()
  */
 struct cipher_testvec {
 	const char *key;
@@ -65,12 +72,13 @@ struct cipher_testvec {
 	const char *iv_out;
 	const char *ptext;
 	const char *ctext;
-	bool fail;
 	unsigned char wk; /* weak key flag */
-	unsigned char klen;
+	unsigned short klen;
 	unsigned short len;
 	bool fips_skip;
 	bool generates_iv;
+	int setkey_error;
+	int crypt_error;
 };
 
 /*
@@ -82,7 +90,6 @@ struct cipher_testvec {
  * @ctext:	Pointer to the full authenticated ciphertext.  For AEADs that
  *		produce a separate "ciphertext" and "authentication tag", these
  *		two parts are concatenated: ciphertext || tag.
- * @fail:	setkey() failure expected?
  * @novrfy:	Decryption verification failure expected?
  * @wk:		Does the test need CRYPTO_TFM_REQ_FORBID_WEAK_KEYS?
  *		(e.g. setkey() needs to fail due to a weak key)
@@ -90,6 +97,9 @@ struct cipher_testvec {
  * @plen:	Length of @ptext in bytes
  * @alen:	Length of @assoc in bytes
  * @clen:	Length of @ctext in bytes
+ * @setkey_error: Expected error from setkey()
+ * @setauthsize_error: Expected error from setauthsize()
+ * @crypt_error: Expected error from encrypt() and decrypt()
  */
 struct aead_testvec {
 	const char *key;
@@ -97,13 +107,15 @@ struct aead_testvec {
 	const char *ptext;
 	const char *assoc;
 	const char *ctext;
-	bool fail;
 	unsigned char novrfy;
 	unsigned char wk;
 	unsigned char klen;
 	unsigned short plen;
 	unsigned short clen;
 	unsigned short alen;
+	int setkey_error;
+	int setauthsize_error;
+	int crypt_error;
 };
 
 struct cprng_testvec {
@@ -135,13 +147,16 @@ struct drbg_testvec {
 
 struct akcipher_testvec {
 	const unsigned char *key;
+	const unsigned char *params;
 	const unsigned char *m;
 	const unsigned char *c;
 	unsigned int key_len;
+	unsigned int param_len;
 	unsigned int m_size;
 	unsigned int c_size;
 	bool public_key_vec;
 	bool siggen_sigver_test;
+	enum OID algo;
 };
 
 struct kpp_testvec {
@@ -551,6 +566,160 @@ static const struct akcipher_testvec rsa_tv_template[] = {
 };
 
 /*
+ * EC-RDSA test vectors are generated by gost-engine.
+ */
+static const struct akcipher_testvec ecrdsa_tv_template[] = {
+	{
+	.key =
+	"\x04\x40\xd5\xa7\x77\xf9\x26\x2f\x8c\xbd\xcc\xe3\x1f\x01\x94\x05"
+	"\x3d\x2f\xec\xb5\x00\x34\xf5\x51\x6d\x3b\x90\x4b\x23\x28\x6f\x1d"
+	"\xc8\x36\x61\x60\x36\xec\xbb\xb4\x0b\x95\x4e\x54\x4f\x15\x21\x05"
+	"\xd8\x52\x66\x44\x31\x7e\x5d\xc5\xd1\x26\x00\x5f\x60\xd8\xf0\xc7"
+	"\x27\xfc",
+	.key_len = 66,
+	.params = /* OID_gostCPSignA */
+	"\x30\x13\x06\x07\x2a\x85\x03\x02\x02\x23\x01\x06\x08\x2a\x85\x03"
+	"\x07\x01\x01\x02\x02",
+	.param_len = 21,
+	.c =
+	"\x41\x32\x09\x73\xa4\xc1\x38\xd6\x63\x7d\x8b\xf7\x50\x3f\xda\x9f"
+	"\x68\x48\xc1\x50\xe3\x42\x3a\x9b\x2b\x28\x12\x2a\xa7\xc2\x75\x31"
+	"\x65\x77\x8c\x3c\x9e\x0d\x56\xb2\xf9\xdc\x04\x33\x3e\xb0\x9e\xf9"
+	"\x74\x4e\x59\xb3\x83\xf2\x91\x27\xda\x5e\xc7\x33\xc0\xc1\x8f\x41",
+	.c_size = 64,
+	.algo = OID_gost2012PKey256,
+	.m =
+	"\x75\x1b\x9b\x40\x25\xb9\x96\xd2\x9b\x00\x41\xb3\x58\xbf\x23\x14"
+	"\x79\xd2\x76\x64\xa3\xbd\x66\x10\x79\x05\x5a\x06\x42\xec\xb9\xc9",
+	.m_size = 32,
+	.public_key_vec = true,
+	.siggen_sigver_test = true,
+	},
+	{
+	.key =
+	"\x04\x40\x66\x6f\xd6\xb7\x06\xd0\xf5\xa5\x6f\x69\x5c\xa5\x13\x45"
+	"\x14\xdd\xcb\x12\x9c\x1b\xf5\x28\x64\x7a\x49\x48\x29\x14\x66\x42"
+	"\xb8\x1b\x5c\xf9\x56\x6d\x08\x3b\xce\xbb\x62\x2f\xc2\x3c\xc5\x49"
+	"\x93\x27\x70\x20\xcc\x79\xeb\xdc\x76\x8e\x48\x6e\x04\x96\xc3\x29"
+	"\xa0\x73",
+	.key_len = 66,
+	.params = /* OID_gostCPSignB */
+	"\x30\x13\x06\x07\x2a\x85\x03\x02\x02\x23\x02\x06\x08\x2a\x85\x03"
+	"\x07\x01\x01\x02\x02",
+	.param_len = 21,
+	.c =
+	"\x45\x6d\x4a\x03\x1d\x5c\x0b\x17\x79\xe7\x19\xdb\xbf\x81\x9f\x82"
+	"\xae\x06\xda\xf5\x47\x00\x05\x80\xc3\x16\x06\x9a\x8e\x7c\xb2\x8e"
+	"\x7f\x74\xaa\xec\x6b\x7b\x7f\x8b\xc6\x0b\x10\x42\x4e\x91\x2c\xdf"
+	"\x7b\x8b\x15\xf4\x9e\x59\x0f\xc7\xa4\x68\x2e\xce\x89\xdf\x84\xe9",
+	.c_size = 64,
+	.algo = OID_gost2012PKey256,
+	.m =
+	"\xd0\x54\x00\x27\x6a\xeb\xce\x6c\xf5\xf6\xfb\x57\x18\x18\x21\x13"
+	"\x11\x23\x4a\x70\x43\x52\x7a\x68\x11\x65\x45\x37\xbb\x25\xb7\x40",
+	.m_size = 32,
+	.public_key_vec = true,
+	.siggen_sigver_test = true,
+	},
+	{
+	.key =
+	"\x04\x40\x05\x91\xa9\x7d\xcb\x87\xdc\x98\xa1\xbf\xff\xdd\x20\x61"
+	"\xaa\x58\x3b\x2d\x8e\x9c\x41\x9d\x4f\xc6\x23\x17\xf9\xca\x60\x65"
+	"\xbc\x97\x97\xf6\x6b\x24\xe8\xac\xb1\xa7\x61\x29\x3c\x71\xdc\xad"
+	"\xcb\x20\xbe\x96\xe8\xf4\x44\x2e\x49\xd5\x2c\xb9\xc9\x3b\x9c\xaa"
+	"\xba\x15",
+	.key_len = 66,
+	.params = /* OID_gostCPSignC */
+	"\x30\x13\x06\x07\x2a\x85\x03\x02\x02\x23\x03\x06\x08\x2a\x85\x03"
+	"\x07\x01\x01\x02\x02",
+	.param_len = 21,
+	.c =
+	"\x3b\x2e\x2e\x74\x74\x47\xda\xea\x93\x90\x6a\xe2\xf5\xf5\xe6\x46"
+	"\x11\xfc\xab\xdc\x52\xbc\x58\xdb\x45\x44\x12\x4a\xf7\xd0\xab\xc9"
+	"\x73\xba\x64\xab\x0d\xac\x4e\x72\x10\xa8\x04\xf6\x1e\xe0\x48\x6a"
+	"\xcd\xe8\xe3\x78\x73\x77\x82\x24\x8d\xf1\xd3\xeb\x4c\x25\x7e\xc0",
+	.c_size = 64,
+	.algo = OID_gost2012PKey256,
+	.m =
+	"\x52\x33\xf4\x3f\x7b\x5d\xcf\x20\xee\xe4\x5c\xab\x0b\x3f\x14\xd6"
+	"\x9f\x16\xc6\x1c\xb1\x3f\x84\x41\x69\xec\x34\xfd\xf1\xf9\xa3\x39",
+	.m_size = 32,
+	.public_key_vec = true,
+	.siggen_sigver_test = true,
+	},
+	{
+	.key =
+	"\x04\x81\x80\x85\x46\x8f\x16\xf8\x7a\x7e\x4a\xc3\x81\x9e\xf1\x6e"
+	"\x94\x1e\x5d\x02\x87\xea\xfa\xa0\x0a\x17\x70\x49\x64\xad\x95\x68"
+	"\x60\x0a\xf0\x57\x29\x41\x79\x30\x3c\x61\x69\xf2\xa6\x94\x87\x17"
+	"\x54\xfa\x97\x2c\xe6\x1e\x0a\xbb\x55\x10\x57\xbe\xf7\xc1\x77\x2b"
+	"\x11\x74\x0a\x50\x37\x14\x10\x2a\x45\xfc\x7a\xae\x1c\x4c\xce\x08"
+	"\x05\xb7\xa4\x50\xc8\x3d\x39\x3d\xdc\x5c\x8f\x96\x6c\xe7\xfc\x21"
+	"\xc3\x2d\x1e\x9f\x11\xb3\xec\x22\x18\x8a\x8c\x08\x6b\x8b\xed\xf5"
+	"\xc5\x47\x3c\x7e\x73\x59\x44\x1e\x77\x83\x84\x52\x9e\x3b\x7d\xff"
+	"\x9d\x86\x1a",
+	.key_len = 131,
+	.params = /* OID_gostTC26Sign512A */
+	"\x30\x0b\x06\x09\x2a\x85\x03\x07\x01\x02\x01\x02\x01",
+	.param_len = 13,
+	.c =
+	"\x92\x81\x74\x5f\x95\x48\x38\x87\xd9\x8f\x5e\xc8\x8a\xbb\x01\x4e"
+	"\xb0\x75\x3c\x2f\xc7\x5a\x08\x4c\x68\xab\x75\x01\x32\x75\x75\xb5"
+	"\x37\xe0\x74\x6d\x94\x84\x31\x2a\x6b\xf4\xf7\xb7\xa7\x39\x7b\x46"
+	"\x07\xf0\x98\xbd\x33\x18\xa1\x72\xb2\x6d\x54\xe3\xde\x91\xc2\x2e"
+	"\x4f\x6a\xf8\xb7\xec\xa8\x83\xc9\x8f\xd9\xce\x7c\x45\x06\x02\xf4"
+	"\x4f\x21\xb5\x24\x3d\xb4\xb5\xd8\x58\x42\xbe\x2d\x29\xae\x93\xc0"
+	"\x13\x41\x96\x35\x08\x69\xe8\x36\xc7\xd1\x83\x81\xd7\xca\xfb\xc0"
+	"\xd2\xb7\x78\x32\x3e\x30\x1a\x1e\xce\xdc\x34\x35\xc6\xad\x68\x24",
+	.c_size = 128,
+	.algo = OID_gost2012PKey512,
+	.m =
+	"\x1f\x70\xb5\xe9\x55\x12\xd6\x88\xcc\x55\xb9\x0c\x7f\xc4\x94\xf2"
+	"\x04\x77\x41\x12\x02\xd6\xf1\x1f\x83\x56\xe9\xd6\x5a\x6a\x72\xb9"
+	"\x6e\x8e\x24\x2a\x84\xf1\xba\x67\xe8\xbf\xff\xc1\xd3\xde\xfb\xc6"
+	"\xa8\xf6\x80\x01\xb9\x27\xac\xd8\x45\x96\x66\xa1\xee\x48\x08\x3f",
+	.m_size = 64,
+	.public_key_vec = true,
+	.siggen_sigver_test = true,
+	},
+	{
+	.key =
+	"\x04\x81\x80\x28\xf3\x2b\x92\x04\x32\xea\x66\x20\xde\xa0\x2f\x74"
+	"\xbf\x2d\xf7\xb5\x30\x76\xb1\xc8\xee\x38\x9f\xea\xe5\xad\xc6\xa3"
+	"\x28\x1e\x51\x3d\x67\xa3\x41\xcc\x6b\x81\xe2\xe2\x9e\x82\xf3\x78"
+	"\x56\xd7\x2e\xb2\xb5\xbe\xb4\x50\x21\x05\xe5\x29\x82\xef\x15\x1b"
+	"\xc0\xd7\x30\xd6\x2f\x96\xe8\xff\x99\x4c\x25\xcf\x9a\xfc\x54\x30"
+	"\xce\xdf\x59\xe9\xc6\x45\xce\xe4\x22\xe8\x01\xd5\xcd\x2f\xaa\x78"
+	"\x99\xc6\x04\x1e\x6f\x4c\x25\x6a\x76\xad\xff\x48\xf3\xb3\xb4\xd6"
+	"\x14\x5c\x2c\x0e\xea\xa2\x4b\xb9\x7e\x89\x77\x02\x3a\x29\xc8\x16"
+	"\x8e\x78\x48",
+	.key_len = 131,
+	.params = /* OID_gostTC26Sign512B */
+	"\x30\x0b\x06\x09\x2a\x85\x03\x07\x01\x02\x01\x02\x02",
+	.param_len = 13,
+	.c =
+	"\x0a\xed\xb6\x27\xea\xa7\xa6\x7e\x2f\xc1\x02\x21\x74\xce\x27\xd2"
+	"\xee\x8a\x92\x4d\xa9\x43\x2d\xa4\x5b\xdc\x23\x02\xfc\x3a\xf3\xb2"
+	"\x10\x93\x0b\x40\x1b\x75\x95\x3e\x39\x41\x37\xb9\xab\x51\x09\xeb"
+	"\xf1\xb9\x49\x58\xec\x58\xc7\xf9\x2e\xb9\xc9\x40\xf2\x00\x39\x7e"
+	"\x3f\xde\x72\xe3\x85\x67\x06\xbe\xd8\xb8\xc1\x81\x1e\xe3\x0a\xfe"
+	"\xce\xd3\x77\x92\x56\x8c\x58\xf9\x37\x60\x2d\xe6\x8b\x66\xa3\xdd"
+	"\xd2\xf0\xf8\xda\x1b\x20\xbc\x9c\xec\x29\x5d\xd1\x8f\xcc\x37\xd1"
+	"\x3b\x8d\xb7\xc1\xe0\xb8\x3b\xef\x14\x1b\x87\xbc\xc1\x03\x9a\x93",
+	.c_size = 128,
+	.algo = OID_gost2012PKey512,
+	.m =
+	"\x11\x24\x21\x27\xf2\x42\x9f\xce\x5a\xf9\x01\x70\xe0\x07\x2b\x57"
+	"\xfb\x7d\x77\x5e\x74\x66\xe6\xa5\x40\x4c\x1a\x85\x18\xff\xd0\x63"
+	"\xe0\x39\xd3\xd6\xe5\x17\xf8\xc3\x4b\xc6\x1c\x33\x1a\xca\xa6\x66"
+	"\x6d\xf4\xd2\x45\xc2\x83\xa0\x42\x95\x05\x9d\x89\x8e\x0a\xca\xcc",
+	.m_size = 64,
+	.public_key_vec = true,
+	.siggen_sigver_test = true,
+	},
+};
+
+/*
  * PKCS#1 RSA test vectors. Obtained from CAVS testing.
  */
 static const struct akcipher_testvec pkcs1pad_rsa_tv_template[] = {
@@ -5634,7 +5803,49 @@ static const struct hash_testvec poly1305_tv_template[] = {
 		.psize		= 80,
 		.digest		= "\x13\x00\x00\x00\x00\x00\x00\x00"
 				  "\x00\x00\x00\x00\x00\x00\x00\x00",
-	},
+	}, { /* Regression test for overflow in AVX2 implementation */
+		.plaintext	= "\xff\xff\xff\xff\xff\xff\xff\xff"
+				  "\xff\xff\xff\xff\xff\xff\xff\xff"
+				  "\xff\xff\xff\xff\xff\xff\xff\xff"
+				  "\xff\xff\xff\xff\xff\xff\xff\xff"
+				  "\xff\xff\xff\xff\xff\xff\xff\xff"
+				  "\xff\xff\xff\xff\xff\xff\xff\xff"
+				  "\xff\xff\xff\xff\xff\xff\xff\xff"
+				  "\xff\xff\xff\xff\xff\xff\xff\xff"
+				  "\xff\xff\xff\xff\xff\xff\xff\xff"
+				  "\xff\xff\xff\xff\xff\xff\xff\xff"
+				  "\xff\xff\xff\xff\xff\xff\xff\xff"
+				  "\xff\xff\xff\xff\xff\xff\xff\xff"
+				  "\xff\xff\xff\xff\xff\xff\xff\xff"
+				  "\xff\xff\xff\xff\xff\xff\xff\xff"
+				  "\xff\xff\xff\xff\xff\xff\xff\xff"
+				  "\xff\xff\xff\xff\xff\xff\xff\xff"
+				  "\xff\xff\xff\xff\xff\xff\xff\xff"
+				  "\xff\xff\xff\xff\xff\xff\xff\xff"
+				  "\xff\xff\xff\xff\xff\xff\xff\xff"
+				  "\xff\xff\xff\xff\xff\xff\xff\xff"
+				  "\xff\xff\xff\xff\xff\xff\xff\xff"
+				  "\xff\xff\xff\xff\xff\xff\xff\xff"
+				  "\xff\xff\xff\xff\xff\xff\xff\xff"
+				  "\xff\xff\xff\xff\xff\xff\xff\xff"
+				  "\xff\xff\xff\xff\xff\xff\xff\xff"
+				  "\xff\xff\xff\xff\xff\xff\xff\xff"
+				  "\xff\xff\xff\xff\xff\xff\xff\xff"
+				  "\xff\xff\xff\xff\xff\xff\xff\xff"
+				  "\xff\xff\xff\xff\xff\xff\xff\xff"
+				  "\xff\xff\xff\xff\xff\xff\xff\xff"
+				  "\xff\xff\xff\xff\xff\xff\xff\xff"
+				  "\xff\xff\xff\xff\xff\xff\xff\xff"
+				  "\xff\xff\xff\xff\xff\xff\xff\xff"
+				  "\xff\xff\xff\xff\xff\xff\xff\xff"
+				  "\xff\xff\xff\xff\xff\xff\xff\xff"
+				  "\xff\xff\xff\xff\xff\xff\xff\xff"
+				  "\xff\xff\xff\xff\xff\xff\xff\xff"
+				  "\xff\xff\xff\xff",
+		.psize		= 300,
+		.digest		= "\xfb\x5e\x96\xd8\x61\xd5\xc7\xc8"
+				  "\x78\xe5\x87\xcc\x2d\x5a\x22\xe1",
+	}
 };
 
 /* NHPoly1305 test vectors from https://github.com/google/adiantum */
@@ -7042,7 +7253,7 @@ static const struct cipher_testvec des_tv_template[] = {
 			  "\xb4\x99\x26\xf7\x1f\xe1\xd4\x90",
 		.len	= 24,
 	}, { /* Weak key */
-		.fail	= true,
+		.setkey_error = -EINVAL,
 		.wk	= 1,
 		.key	= "\x01\x01\x01\x01\x01\x01\x01\x01",
 		.klen	= 8,
diff --git a/crypto/tgr192.c b/crypto/tgr192.c
index f8e1d9f9938f..40020f8adc46 100644
--- a/crypto/tgr192.c
+++ b/crypto/tgr192.c
@@ -677,7 +677,7 @@ MODULE_ALIAS_CRYPTO("tgr192");
 MODULE_ALIAS_CRYPTO("tgr160");
 MODULE_ALIAS_CRYPTO("tgr128");
 
-module_init(tgr192_mod_init);
+subsys_initcall(tgr192_mod_init);
 module_exit(tgr192_mod_fini);
 
 MODULE_LICENSE("GPL");
diff --git a/crypto/twofish_generic.c b/crypto/twofish_generic.c
index 07e62433fbfb..dbac6e233285 100644
--- a/crypto/twofish_generic.c
+++ b/crypto/twofish_generic.c
@@ -205,7 +205,7 @@ static void __exit twofish_mod_fini(void)
 	crypto_unregister_alg(&alg);
 }
 
-module_init(twofish_mod_init);
+subsys_initcall(twofish_mod_init);
 module_exit(twofish_mod_fini);
 
 MODULE_LICENSE("GPL");
diff --git a/crypto/vmac.c b/crypto/vmac.c
index 5f436dfdfc61..f50a85060b39 100644
--- a/crypto/vmac.c
+++ b/crypto/vmac.c
@@ -690,7 +690,7 @@ static void __exit vmac_module_exit(void)
 	crypto_unregister_template(&vmac64_tmpl);
 }
 
-module_init(vmac_module_init);
+subsys_initcall(vmac_module_init);
 module_exit(vmac_module_exit);
 
 MODULE_LICENSE("GPL");
diff --git a/crypto/wp512.c b/crypto/wp512.c
index 149e577fb772..1b8e502d999f 100644
--- a/crypto/wp512.c
+++ b/crypto/wp512.c
@@ -1168,7 +1168,7 @@ MODULE_ALIAS_CRYPTO("wp512");
 MODULE_ALIAS_CRYPTO("wp384");
 MODULE_ALIAS_CRYPTO("wp256");
 
-module_init(wp512_mod_init);
+subsys_initcall(wp512_mod_init);
 module_exit(wp512_mod_fini);
 
 MODULE_LICENSE("GPL");
diff --git a/crypto/xcbc.c b/crypto/xcbc.c
index c055f57fab11..94ca694ef091 100644
--- a/crypto/xcbc.c
+++ b/crypto/xcbc.c
@@ -282,7 +282,7 @@ static void __exit crypto_xcbc_module_exit(void)
 	crypto_unregister_template(&crypto_xcbc_tmpl);
 }
 
-module_init(crypto_xcbc_module_init);
+subsys_initcall(crypto_xcbc_module_init);
 module_exit(crypto_xcbc_module_exit);
 
 MODULE_LICENSE("GPL");
diff --git a/crypto/xts.c b/crypto/xts.c
index 847f54f76789..33cf726df4ac 100644
--- a/crypto/xts.c
+++ b/crypto/xts.c
@@ -137,8 +137,12 @@ static void crypt_done(struct crypto_async_request *areq, int err)
 {
 	struct skcipher_request *req = areq->data;
 
-	if (!err)
+	if (!err) {
+		struct rctx *rctx = skcipher_request_ctx(req);
+
+		rctx->subreq.base.flags &= ~CRYPTO_TFM_REQ_MAY_SLEEP;
 		err = xor_tweak_post(req);
+	}
 
 	skcipher_request_complete(req, err);
 }
@@ -359,7 +363,7 @@ static void __exit crypto_module_exit(void)
 	crypto_unregister_template(&crypto_tmpl);
 }
 
-module_init(crypto_module_init);
+subsys_initcall(crypto_module_init);
 module_exit(crypto_module_exit);
 
 MODULE_LICENSE("GPL");
diff --git a/crypto/zstd.c b/crypto/zstd.c
index 9a76b3ed8b8b..2c04055e407f 100644
--- a/crypto/zstd.c
+++ b/crypto/zstd.c
@@ -257,7 +257,7 @@ static void __exit zstd_mod_fini(void)
 	crypto_unregister_scomp(&scomp);
 }
 
-module_init(zstd_mod_init);
+subsys_initcall(zstd_mod_init);
 module_exit(zstd_mod_fini);
 
 MODULE_LICENSE("GPL");
diff --git a/drivers/acpi/acpi_configfs.c b/drivers/acpi/acpi_configfs.c
index 81bfc6197293..f92033661239 100644
--- a/drivers/acpi/acpi_configfs.c
+++ b/drivers/acpi/acpi_configfs.c
@@ -109,7 +109,7 @@ static ssize_t acpi_table_signature_show(struct config_item *cfg, char *str)
 	if (!h)
 		return -EINVAL;
 
-	return sprintf(str, "%.*s\n", ACPI_NAME_SIZE, h->signature);
+	return sprintf(str, "%.*s\n", ACPI_NAMESEG_SIZE, h->signature);
 }
 
 static ssize_t acpi_table_length_show(struct config_item *cfg, char *str)
@@ -170,7 +170,7 @@ static ssize_t acpi_table_asl_compiler_id_show(struct config_item *cfg,
 	if (!h)
 		return -EINVAL;
 
-	return sprintf(str, "%.*s\n", ACPI_NAME_SIZE, h->asl_compiler_id);
+	return sprintf(str, "%.*s\n", ACPI_NAMESEG_SIZE, h->asl_compiler_id);
 }
 
 static ssize_t acpi_table_asl_compiler_revision_show(struct config_item *cfg,
diff --git a/drivers/acpi/acpi_dbg.c b/drivers/acpi/acpi_dbg.c
index 4a434c23a196..d18246a2a65e 100644
--- a/drivers/acpi/acpi_dbg.c
+++ b/drivers/acpi/acpi_dbg.c
@@ -390,7 +390,7 @@ again:
 	return size > 0 ? size : ret;
 }
 
-static int acpi_aml_thread(void *unsed)
+static int acpi_aml_thread(void *unused)
 {
 	acpi_osd_exec_callback function = NULL;
 	void *context;
diff --git a/drivers/acpi/acpi_lpat.c b/drivers/acpi/acpi_lpat.c
index 2cd9f738812b..43f1b99c86ca 100644
--- a/drivers/acpi/acpi_lpat.c
+++ b/drivers/acpi/acpi_lpat.c
@@ -22,7 +22,7 @@
  * LPAT conversion table
  *
  * @lpat_table: the temperature_raw mapping table structure
- * @raw: the raw value, used as a key to get the temerature from the
+ * @raw: the raw value, used as a key to get the temperature from the
  *       above mapping table
  *
  * A positive converted temperature value will be returned on success,
diff --git a/drivers/acpi/acpi_lpss.c b/drivers/acpi/acpi_lpss.c
index 1e2a10a06b9d..cf768608437e 100644
--- a/drivers/acpi/acpi_lpss.c
+++ b/drivers/acpi/acpi_lpss.c
@@ -1142,8 +1142,8 @@ static struct dev_pm_domain acpi_lpss_pm_domain = {
 		.thaw_noirq = acpi_subsys_thaw_noirq,
 		.poweroff = acpi_subsys_suspend,
 		.poweroff_late = acpi_lpss_suspend_late,
-		.poweroff_noirq = acpi_subsys_suspend_noirq,
-		.restore_noirq = acpi_subsys_resume_noirq,
+		.poweroff_noirq = acpi_lpss_suspend_noirq,
+		.restore_noirq = acpi_lpss_resume_noirq,
 		.restore_early = acpi_lpss_resume_early,
 #endif
 		.runtime_suspend = acpi_lpss_runtime_suspend,
diff --git a/drivers/acpi/acpica/aclocal.h b/drivers/acpi/acpica/aclocal.h
index a2dfbf6b004e..13d513b81589 100644
--- a/drivers/acpi/acpica/aclocal.h
+++ b/drivers/acpi/acpica/aclocal.h
@@ -293,7 +293,7 @@ acpi_status (*acpi_internal_method) (struct acpi_walk_state * walk_state);
  * expected_return_btypes - Allowed type(s) for the return value
  */
 struct acpi_name_info {
-	char name[ACPI_NAME_SIZE];
+	char name[ACPI_NAMESEG_SIZE];
 	u16 argument_list;
 	u8 expected_btypes;
 };
@@ -370,7 +370,7 @@ typedef acpi_status (*acpi_object_converter) (struct acpi_namespace_node *
 					      converted_object);
 
 struct acpi_simple_repair_info {
-	char name[ACPI_NAME_SIZE];
+	char name[ACPI_NAMESEG_SIZE];
 	u32 unexpected_btypes;
 	u32 package_index;
 	acpi_object_converter object_converter;
diff --git a/drivers/acpi/acpica/dbexec.c b/drivers/acpi/acpica/dbexec.c
index bb43305cb215..4027eaab18a4 100644
--- a/drivers/acpi/acpica/dbexec.c
+++ b/drivers/acpi/acpica/dbexec.c
@@ -453,7 +453,7 @@ acpi_db_execute(char *name, char **args, acpi_object_type *types, u32 flags)
 
 			/* Dump a _PLD buffer if present */
 
-			if (ACPI_COMPARE_NAME
+			if (ACPI_COMPARE_NAMESEG
 			    ((ACPI_CAST_PTR
 			      (struct acpi_namespace_node,
 			       acpi_gbl_db_method_info.method)->name.ascii),
diff --git a/drivers/acpi/acpica/dbnames.c b/drivers/acpi/acpica/dbnames.c
index 004d34d9369b..63fe30e86807 100644
--- a/drivers/acpi/acpica/dbnames.c
+++ b/drivers/acpi/acpica/dbnames.c
@@ -354,7 +354,7 @@ acpi_status acpi_db_find_name_in_namespace(char *name_arg)
 	char acpi_name[5] = "____";
 	char *acpi_name_ptr = acpi_name;
 
-	if (strlen(name_arg) > ACPI_NAME_SIZE) {
+	if (strlen(name_arg) > ACPI_NAMESEG_SIZE) {
 		acpi_os_printf("Name must be no longer than 4 characters\n");
 		return (AE_OK);
 	}
diff --git a/drivers/acpi/acpica/dsinit.c b/drivers/acpi/acpica/dsinit.c
index a4a24ffe5fae..4ebd23700bbc 100644
--- a/drivers/acpi/acpica/dsinit.c
+++ b/drivers/acpi/acpica/dsinit.c
@@ -200,7 +200,7 @@ acpi_ds_initialize_objects(u32 table_index,
 
 	/* DSDT is always the first AML table */
 
-	if (ACPI_COMPARE_NAME(table->signature, ACPI_SIG_DSDT)) {
+	if (ACPI_COMPARE_NAMESEG(table->signature, ACPI_SIG_DSDT)) {
 		ACPI_DEBUG_PRINT_RAW((ACPI_DB_INIT,
 				      "\nInitializing Namespace objects:\n"));
 	}
diff --git a/drivers/acpi/acpica/evgpeinit.c b/drivers/acpi/acpica/evgpeinit.c
index c92d2f6ebe01..b04f982e59fa 100644
--- a/drivers/acpi/acpica/evgpeinit.c
+++ b/drivers/acpi/acpica/evgpeinit.c
@@ -292,7 +292,7 @@ acpi_ev_match_gpe_method(acpi_handle obj_handle,
 	acpi_status status;
 	u32 gpe_number;
 	u8 temp_gpe_number;
-	char name[ACPI_NAME_SIZE + 1];
+	char name[ACPI_NAMESEG_SIZE + 1];
 	u8 type;
 
 	ACPI_FUNCTION_TRACE(ev_match_gpe_method);
@@ -310,7 +310,7 @@ acpi_ev_match_gpe_method(acpi_handle obj_handle,
 	 * 1) Extract the method name and null terminate it
 	 */
 	ACPI_MOVE_32_TO_32(name, &method_node->name.integer);
-	name[ACPI_NAME_SIZE] = 0;
+	name[ACPI_NAMESEG_SIZE] = 0;
 
 	/* 2) Name must begin with an underscore */
 
diff --git a/drivers/acpi/acpica/exnames.c b/drivers/acpi/acpica/exnames.c
index bd68d66e89f0..6b76be5212a4 100644
--- a/drivers/acpi/acpica/exnames.c
+++ b/drivers/acpi/acpica/exnames.c
@@ -53,10 +53,10 @@ static char *acpi_ex_allocate_name_string(u32 prefix_count, u32 num_name_segs)
 
 		/* Special case for root */
 
-		size_needed = 1 + (ACPI_NAME_SIZE * num_name_segs) + 2 + 1;
+		size_needed = 1 + (ACPI_NAMESEG_SIZE * num_name_segs) + 2 + 1;
 	} else {
 		size_needed =
-		    prefix_count + (ACPI_NAME_SIZE * num_name_segs) + 2 + 1;
+		    prefix_count + (ACPI_NAMESEG_SIZE * num_name_segs) + 2 + 1;
 	}
 
 	/*
@@ -141,7 +141,7 @@ static acpi_status acpi_ex_name_segment(u8 ** in_aml_address, char *name_string)
 	}
 
 	for (index = 0;
-	     (index < ACPI_NAME_SIZE)
+	     (index < ACPI_NAMESEG_SIZE)
 	     && (acpi_ut_valid_name_char(*aml_address, 0)); index++) {
 		char_buf[index] = *aml_address++;
 	}
diff --git a/drivers/acpi/acpica/nsaccess.c b/drivers/acpi/acpica/nsaccess.c
index 75192b958544..7b855603f81a 100644
--- a/drivers/acpi/acpica/nsaccess.c
+++ b/drivers/acpi/acpica/nsaccess.c
@@ -683,7 +683,7 @@ acpi_ns_lookup(union acpi_generic_state *scope_info,
 
 		/* Point to next name segment and make this node current */
 
-		path += ACPI_NAME_SIZE;
+		path += ACPI_NAMESEG_SIZE;
 		current_node = this_node;
 	}
 
diff --git a/drivers/acpi/acpica/nsalloc.c b/drivers/acpi/acpica/nsalloc.c
index 5470213b8e64..6eb63db72249 100644
--- a/drivers/acpi/acpica/nsalloc.c
+++ b/drivers/acpi/acpica/nsalloc.c
@@ -74,6 +74,10 @@ void acpi_ns_delete_node(struct acpi_namespace_node *node)
 
 	ACPI_FUNCTION_NAME(ns_delete_node);
 
+	if (!node) {
+		return_VOID;
+	}
+
 	/* Detach an object if there is one */
 
 	acpi_ns_detach_object(node);
diff --git a/drivers/acpi/acpica/nsdump.c b/drivers/acpi/acpica/nsdump.c
index 15070bd0c28a..1b12c172e115 100644
--- a/drivers/acpi/acpica/nsdump.c
+++ b/drivers/acpi/acpica/nsdump.c
@@ -70,7 +70,7 @@ void acpi_ns_print_pathname(u32 num_segments, const char *pathname)
 			    acpi_os_printf("?");
 		}
 
-		pathname += ACPI_NAME_SIZE;
+		pathname += ACPI_NAMESEG_SIZE;
 		num_segments--;
 		if (num_segments) {
 			acpi_os_printf(".");
diff --git a/drivers/acpi/acpica/nsinit.c b/drivers/acpi/acpica/nsinit.c
index 19fb8dda870f..53e5d00d3a5e 100644
--- a/drivers/acpi/acpica/nsinit.c
+++ b/drivers/acpi/acpica/nsinit.c
@@ -478,7 +478,7 @@ acpi_ns_find_ini_methods(acpi_handle obj_handle,
 
 	/* We are only looking for methods named _INI */
 
-	if (!ACPI_COMPARE_NAME(node->name.ascii, METHOD_NAME__INI)) {
+	if (!ACPI_COMPARE_NAMESEG(node->name.ascii, METHOD_NAME__INI)) {
 		return (AE_OK);
 	}
 
@@ -641,7 +641,7 @@ acpi_ns_init_one_device(acpi_handle obj_handle,
 	 * Note: We know there is an _INI within this subtree, but it may not be
 	 * under this particular device, it may be lower in the branch.
 	 */
-	if (!ACPI_COMPARE_NAME(device_node->name.ascii, "_SB_") ||
+	if (!ACPI_COMPARE_NAMESEG(device_node->name.ascii, "_SB_") ||
 	    device_node->parent != acpi_gbl_root_node) {
 		ACPI_DEBUG_EXEC(acpi_ut_display_init_pathname
 				(ACPI_TYPE_METHOD, device_node,
diff --git a/drivers/acpi/acpica/nsnames.c b/drivers/acpi/acpica/nsnames.c
index 289c15bb8c6a..370bbc867745 100644
--- a/drivers/acpi/acpica/nsnames.c
+++ b/drivers/acpi/acpica/nsnames.c
@@ -108,8 +108,8 @@ acpi_ns_handle_to_name(acpi_handle target_handle, struct acpi_buffer *buffer)
 	/* Just copy the ACPI name from the Node and zero terminate it */
 
 	node_name = acpi_ut_get_node_name(node);
-	ACPI_MOVE_NAME(buffer->pointer, node_name);
-	((char *)buffer->pointer)[ACPI_NAME_SIZE] = 0;
+	ACPI_COPY_NAMESEG(buffer->pointer, node_name);
+	((char *)buffer->pointer)[ACPI_NAMESEG_SIZE] = 0;
 
 	ACPI_DEBUG_PRINT((ACPI_DB_EXEC, "%4.4s\n", (char *)buffer->pointer));
 	return_ACPI_STATUS(AE_OK);
@@ -198,7 +198,7 @@ acpi_ns_build_normalized_path(struct acpi_namespace_node *node,
 			      char *full_path, u32 path_size, u8 no_trailing)
 {
 	u32 length = 0, i;
-	char name[ACPI_NAME_SIZE];
+	char name[ACPI_NAMESEG_SIZE];
 	u8 do_no_trailing;
 	char c, *left, *right;
 	struct acpi_namespace_node *next_node;
@@ -446,7 +446,7 @@ static void acpi_ns_normalize_pathname(char *original_path)
 
 		/* Do one nameseg at a time */
 
-		for (i = 0; (i < ACPI_NAME_SIZE) && *input_path; i++) {
+		for (i = 0; (i < ACPI_NAMESEG_SIZE) && *input_path; i++) {
 			if ((i == 0) || (*input_path != '_')) {	/* First char is allowed to be underscore */
 				*new_path = *input_path;
 				new_path++;
diff --git a/drivers/acpi/acpica/nsobject.c b/drivers/acpi/acpica/nsobject.c
index 8638f43cfc3d..79d86da1c892 100644
--- a/drivers/acpi/acpica/nsobject.c
+++ b/drivers/acpi/acpica/nsobject.c
@@ -186,6 +186,10 @@ void acpi_ns_detach_object(struct acpi_namespace_node *node)
 		}
 	}
 
+	if (obj_desc->common.type == ACPI_TYPE_REGION) {
+		acpi_ut_remove_address_range(obj_desc->region.space_id, node);
+	}
+
 	/* Clear the Node entry in all cases */
 
 	node->object = NULL;
diff --git a/drivers/acpi/acpica/nsparse.c b/drivers/acpi/acpica/nsparse.c
index c0b4f7bedfab..f16cf5e4742c 100644
--- a/drivers/acpi/acpica/nsparse.c
+++ b/drivers/acpi/acpica/nsparse.c
@@ -203,7 +203,7 @@ acpi_ns_one_complete_parse(u32 pass_number,
 
 	/* Found OSDT table, enable the namespace override feature */
 
-	if (ACPI_COMPARE_NAME(table->signature, ACPI_SIG_OSDT) &&
+	if (ACPI_COMPARE_NAMESEG(table->signature, ACPI_SIG_OSDT) &&
 	    pass_number == ACPI_IMODE_LOAD_PASS1) {
 		walk_state->namespace_override = TRUE;
 	}
diff --git a/drivers/acpi/acpica/nsrepair.c b/drivers/acpi/acpica/nsrepair.c
index 0aacfa48e20d..be86fea8e4d4 100644
--- a/drivers/acpi/acpica/nsrepair.c
+++ b/drivers/acpi/acpica/nsrepair.c
@@ -316,7 +316,7 @@ static const struct acpi_simple_repair_info *acpi_ns_match_simple_repair(struct
 
 	this_name = acpi_object_repair_info;
 	while (this_name->object_converter) {
-		if (ACPI_COMPARE_NAME(node->name.ascii, this_name->name)) {
+		if (ACPI_COMPARE_NAMESEG(node->name.ascii, this_name->name)) {
 
 			/* Check if we can actually repair this name/type combination */
 
diff --git a/drivers/acpi/acpica/nsrepair2.c b/drivers/acpi/acpica/nsrepair2.c
index d5804a6d1d65..8d776256b213 100644
--- a/drivers/acpi/acpica/nsrepair2.c
+++ b/drivers/acpi/acpica/nsrepair2.c
@@ -25,7 +25,7 @@ acpi_status (*acpi_repair_function) (struct acpi_evaluate_info * info,
 				     return_object_ptr);
 
 typedef struct acpi_repair_info {
-	char name[ACPI_NAME_SIZE];
+	char name[ACPI_NAMESEG_SIZE];
 	acpi_repair_function repair_function;
 
 } acpi_repair_info;
@@ -188,7 +188,7 @@ static const struct acpi_repair_info *acpi_ns_match_complex_repair(struct
 
 	this_name = acpi_ns_repairable_names;
 	while (this_name->repair_function) {
-		if (ACPI_COMPARE_NAME(node->name.ascii, this_name->name)) {
+		if (ACPI_COMPARE_NAMESEG(node->name.ascii, this_name->name)) {
 			return (this_name);
 		}
 
diff --git a/drivers/acpi/acpica/nsutils.c b/drivers/acpi/acpica/nsutils.c
index e5cef1edf49f..6bc90d46db5c 100644
--- a/drivers/acpi/acpica/nsutils.c
+++ b/drivers/acpi/acpica/nsutils.c
@@ -178,7 +178,7 @@ void acpi_ns_get_internal_name_length(struct acpi_namestring_info *info)
 		}
 	}
 
-	info->length = (ACPI_NAME_SIZE * info->num_segments) +
+	info->length = (ACPI_NAMESEG_SIZE * info->num_segments) +
 	    4 + info->num_carats;
 
 	info->next_external_char = next_external_char;
@@ -249,7 +249,7 @@ acpi_status acpi_ns_build_internal_name(struct acpi_namestring_info *info)
 	/* Build the name (minus path separators) */
 
 	for (; num_segments; num_segments--) {
-		for (i = 0; i < ACPI_NAME_SIZE; i++) {
+		for (i = 0; i < ACPI_NAMESEG_SIZE; i++) {
 			if (ACPI_IS_PATH_SEPARATOR(*external_name) ||
 			    (*external_name == 0)) {
 
@@ -274,7 +274,7 @@ acpi_status acpi_ns_build_internal_name(struct acpi_namestring_info *info)
 		/* Move on the next segment */
 
 		external_name++;
-		result += ACPI_NAME_SIZE;
+		result += ACPI_NAMESEG_SIZE;
 	}
 
 	/* Terminate the string */
@@ -489,12 +489,12 @@ acpi_ns_externalize_name(u32 internal_name_length,
 
 			/* Copy and validate the 4-char name segment */
 
-			ACPI_MOVE_NAME(&(*converted_name)[j],
-				       &internal_name[names_index]);
+			ACPI_COPY_NAMESEG(&(*converted_name)[j],
+					  &internal_name[names_index]);
 			acpi_ut_repair_name(&(*converted_name)[j]);
 
-			j += ACPI_NAME_SIZE;
-			names_index += ACPI_NAME_SIZE;
+			j += ACPI_NAMESEG_SIZE;
+			names_index += ACPI_NAMESEG_SIZE;
 		}
 	}
 
diff --git a/drivers/acpi/acpica/nsxfname.c b/drivers/acpi/acpica/nsxfname.c
index de2d3135d6a9..55b4a5b3331f 100644
--- a/drivers/acpi/acpica/nsxfname.c
+++ b/drivers/acpi/acpica/nsxfname.c
@@ -495,8 +495,8 @@ acpi_status acpi_install_method(u8 *buffer)
 
 	/* Table must be a DSDT or SSDT */
 
-	if (!ACPI_COMPARE_NAME(table->signature, ACPI_SIG_DSDT) &&
-	    !ACPI_COMPARE_NAME(table->signature, ACPI_SIG_SSDT)) {
+	if (!ACPI_COMPARE_NAMESEG(table->signature, ACPI_SIG_DSDT) &&
+	    !ACPI_COMPARE_NAMESEG(table->signature, ACPI_SIG_SSDT)) {
 		return (AE_BAD_HEADER);
 	}
 
diff --git a/drivers/acpi/acpica/psargs.c b/drivers/acpi/acpica/psargs.c
index 9d9d442cd999..e62c7897fdf1 100644
--- a/drivers/acpi/acpica/psargs.c
+++ b/drivers/acpi/acpica/psargs.c
@@ -150,21 +150,21 @@ char *acpi_ps_get_next_namestring(struct acpi_parse_state *parser_state)
 
 		/* Two name segments */
 
-		end += 1 + (2 * ACPI_NAME_SIZE);
+		end += 1 + (2 * ACPI_NAMESEG_SIZE);
 		break;
 
 	case AML_MULTI_NAME_PREFIX:
 
 		/* Multiple name segments, 4 chars each, count in next byte */
 
-		end += 2 + (*(end + 1) * ACPI_NAME_SIZE);
+		end += 2 + (*(end + 1) * ACPI_NAMESEG_SIZE);
 		break;
 
 	default:
 
 		/* Single name segment */
 
-		end += ACPI_NAME_SIZE;
+		end += ACPI_NAMESEG_SIZE;
 		break;
 	}
 
@@ -522,7 +522,7 @@ static union acpi_parse_object *acpi_ps_get_next_field(struct acpi_parse_state
 
 		ACPI_MOVE_32_TO_32(&name, parser_state->aml);
 		acpi_ps_set_name(field, name);
-		parser_state->aml += ACPI_NAME_SIZE;
+		parser_state->aml += ACPI_NAMESEG_SIZE;
 
 		ASL_CV_CAPTURE_COMMENTS_ONLY(parser_state);
 
diff --git a/drivers/acpi/acpica/rsxface.c b/drivers/acpi/acpica/rsxface.c
index 1d6f136e4068..c62be3d91712 100644
--- a/drivers/acpi/acpica/rsxface.c
+++ b/drivers/acpi/acpica/rsxface.c
@@ -603,10 +603,10 @@ acpi_walk_resources(acpi_handle device_handle,
 	/* Parameter validation */
 
 	if (!device_handle || !user_function || !name ||
-	    (!ACPI_COMPARE_NAME(name, METHOD_NAME__CRS) &&
-	     !ACPI_COMPARE_NAME(name, METHOD_NAME__PRS) &&
-	     !ACPI_COMPARE_NAME(name, METHOD_NAME__AEI) &&
-	     !ACPI_COMPARE_NAME(name, METHOD_NAME__DMA))) {
+	    (!ACPI_COMPARE_NAMESEG(name, METHOD_NAME__CRS) &&
+	     !ACPI_COMPARE_NAMESEG(name, METHOD_NAME__PRS) &&
+	     !ACPI_COMPARE_NAMESEG(name, METHOD_NAME__AEI) &&
+	     !ACPI_COMPARE_NAMESEG(name, METHOD_NAME__DMA))) {
 		return_ACPI_STATUS(AE_BAD_PARAMETER);
 	}
 
diff --git a/drivers/acpi/acpica/tbdata.c b/drivers/acpi/acpica/tbdata.c
index 0cecd0039acf..933f81316ad2 100644
--- a/drivers/acpi/acpica/tbdata.c
+++ b/drivers/acpi/acpica/tbdata.c
@@ -480,7 +480,8 @@ acpi_tb_verify_temp_table(struct acpi_table_desc *table_desc,
 
 	/* If a particular signature is expected (DSDT/FACS), it must match */
 
-	if (signature && !ACPI_COMPARE_NAME(&table_desc->signature, signature)) {
+	if (signature &&
+	    !ACPI_COMPARE_NAMESEG(&table_desc->signature, signature)) {
 		ACPI_BIOS_ERROR((AE_INFO,
 				 "Invalid signature 0x%X for ACPI table, expected [%s]",
 				 table_desc->signature.integer, signature));
diff --git a/drivers/acpi/acpica/tbfind.c b/drivers/acpi/acpica/tbfind.c
index 951bd8e1c50a..b2abb40023a6 100644
--- a/drivers/acpi/acpica/tbfind.c
+++ b/drivers/acpi/acpica/tbfind.c
@@ -56,7 +56,7 @@ acpi_tb_find_table(char *signature,
 	/* Normalize the input strings */
 
 	memset(&header, 0, sizeof(struct acpi_table_header));
-	ACPI_MOVE_NAME(header.signature, signature);
+	ACPI_COPY_NAMESEG(header.signature, signature);
 	strncpy(header.oem_id, oem_id, ACPI_OEM_ID_SIZE);
 	strncpy(header.oem_table_id, oem_table_id, ACPI_OEM_TABLE_ID_SIZE);
 
@@ -65,7 +65,7 @@ acpi_tb_find_table(char *signature,
 	(void)acpi_ut_acquire_mutex(ACPI_MTX_TABLES);
 	for (i = 0; i < acpi_gbl_root_table_list.current_table_count; ++i) {
 		if (memcmp(&(acpi_gbl_root_table_list.tables[i].signature),
-			   header.signature, ACPI_NAME_SIZE)) {
+			   header.signature, ACPI_NAMESEG_SIZE)) {
 
 			/* Not the requested table */
 
@@ -94,14 +94,14 @@ acpi_tb_find_table(char *signature,
 
 		if (!memcmp
 		    (acpi_gbl_root_table_list.tables[i].pointer->signature,
-		     header.signature, ACPI_NAME_SIZE) && (!oem_id[0]
-							   ||
-							   !memcmp
-							   (acpi_gbl_root_table_list.
-							    tables[i].pointer->
-							    oem_id,
-							    header.oem_id,
-							    ACPI_OEM_ID_SIZE))
+		     header.signature, ACPI_NAMESEG_SIZE) && (!oem_id[0]
+							      ||
+							      !memcmp
+							      (acpi_gbl_root_table_list.
+							       tables[i].
+							       pointer->oem_id,
+							       header.oem_id,
+							       ACPI_OEM_ID_SIZE))
 		    && (!oem_table_id[0]
 			|| !memcmp(acpi_gbl_root_table_list.tables[i].pointer->
 				   oem_table_id, header.oem_table_id,
diff --git a/drivers/acpi/acpica/tbinstal.c b/drivers/acpi/acpica/tbinstal.c
index be6642bf6366..ef1ffd36ab3f 100644
--- a/drivers/acpi/acpica/tbinstal.c
+++ b/drivers/acpi/acpica/tbinstal.c
@@ -120,7 +120,7 @@ acpi_tb_install_standard_table(acpi_physical_address address,
 	 */
 	if (!reload &&
 	    acpi_gbl_disable_ssdt_table_install &&
-	    ACPI_COMPARE_NAME(&new_table_desc.signature, ACPI_SIG_SSDT)) {
+	    ACPI_COMPARE_NAMESEG(&new_table_desc.signature, ACPI_SIG_SSDT)) {
 		ACPI_INFO(("Ignoring installation of %4.4s at %8.8X%8.8X",
 			   new_table_desc.signature.ascii,
 			   ACPI_FORMAT_UINT64(address)));
diff --git a/drivers/acpi/acpica/tbprint.c b/drivers/acpi/acpica/tbprint.c
index 9b5df95d881b..4764f849cb78 100644
--- a/drivers/acpi/acpica/tbprint.c
+++ b/drivers/acpi/acpica/tbprint.c
@@ -69,10 +69,10 @@ acpi_tb_cleanup_table_header(struct acpi_table_header *out_header,
 
 	memcpy(out_header, header, sizeof(struct acpi_table_header));
 
-	acpi_tb_fix_string(out_header->signature, ACPI_NAME_SIZE);
+	acpi_tb_fix_string(out_header->signature, ACPI_NAMESEG_SIZE);
 	acpi_tb_fix_string(out_header->oem_id, ACPI_OEM_ID_SIZE);
 	acpi_tb_fix_string(out_header->oem_table_id, ACPI_OEM_TABLE_ID_SIZE);
-	acpi_tb_fix_string(out_header->asl_compiler_id, ACPI_NAME_SIZE);
+	acpi_tb_fix_string(out_header->asl_compiler_id, ACPI_NAMESEG_SIZE);
 }
 
 /*******************************************************************************
@@ -94,7 +94,7 @@ acpi_tb_print_table_header(acpi_physical_address address,
 {
 	struct acpi_table_header local_header;
 
-	if (ACPI_COMPARE_NAME(header->signature, ACPI_SIG_FACS)) {
+	if (ACPI_COMPARE_NAMESEG(header->signature, ACPI_SIG_FACS)) {
 
 		/* FACS only has signature and length fields */
 
@@ -158,8 +158,8 @@ acpi_status acpi_tb_verify_checksum(struct acpi_table_header *table, u32 length)
 	 * They are the odd tables, have no standard ACPI header and no checksum
 	 */
 
-	if (ACPI_COMPARE_NAME(table->signature, ACPI_SIG_S3PT) ||
-	    ACPI_COMPARE_NAME(table->signature, ACPI_SIG_FACS)) {
+	if (ACPI_COMPARE_NAMESEG(table->signature, ACPI_SIG_S3PT) ||
+	    ACPI_COMPARE_NAMESEG(table->signature, ACPI_SIG_FACS)) {
 		return (AE_OK);
 	}
 
diff --git a/drivers/acpi/acpica/tbutils.c b/drivers/acpi/acpica/tbutils.c
index 2469e01310e2..c5f0b8ec70cc 100644
--- a/drivers/acpi/acpica/tbutils.c
+++ b/drivers/acpi/acpica/tbutils.c
@@ -332,9 +332,9 @@ acpi_tb_parse_root_table(acpi_physical_address rsdp_address)
 							&table_index);
 
 		if (ACPI_SUCCESS(status) &&
-		    ACPI_COMPARE_NAME(&acpi_gbl_root_table_list.
-				      tables[table_index].signature,
-				      ACPI_SIG_FADT)) {
+		    ACPI_COMPARE_NAMESEG(&acpi_gbl_root_table_list.
+					 tables[table_index].signature,
+					 ACPI_SIG_FADT)) {
 			acpi_gbl_fadt_index = table_index;
 			acpi_tb_parse_fadt();
 		}
diff --git a/drivers/acpi/acpica/tbxface.c b/drivers/acpi/acpica/tbxface.c
index 36592888f0e7..1640685bf4ae 100644
--- a/drivers/acpi/acpica/tbxface.c
+++ b/drivers/acpi/acpica/tbxface.c
@@ -230,7 +230,7 @@ acpi_get_table_header(char *signature,
 
 	for (i = 0, j = 0; i < acpi_gbl_root_table_list.current_table_count;
 	     i++) {
-		if (!ACPI_COMPARE_NAME
+		if (!ACPI_COMPARE_NAMESEG
 		    (&(acpi_gbl_root_table_list.tables[i].signature),
 		     signature)) {
 			continue;
@@ -323,7 +323,7 @@ acpi_get_table(char *signature,
 	     i++) {
 		table_desc = &acpi_gbl_root_table_list.tables[i];
 
-		if (!ACPI_COMPARE_NAME(&table_desc->signature, signature)) {
+		if (!ACPI_COMPARE_NAMESEG(&table_desc->signature, signature)) {
 			continue;
 		}
 
diff --git a/drivers/acpi/acpica/tbxfload.c b/drivers/acpi/acpica/tbxfload.c
index 1a2592cc3245..4f30f06a6f78 100644
--- a/drivers/acpi/acpica/tbxfload.c
+++ b/drivers/acpi/acpica/tbxfload.c
@@ -118,7 +118,7 @@ acpi_status acpi_tb_load_namespace(void)
 	table = &acpi_gbl_root_table_list.tables[acpi_gbl_dsdt_index];
 
 	if (!acpi_gbl_root_table_list.current_table_count ||
-	    !ACPI_COMPARE_NAME(table->signature.ascii, ACPI_SIG_DSDT) ||
+	    !ACPI_COMPARE_NAMESEG(table->signature.ascii, ACPI_SIG_DSDT) ||
 	    ACPI_FAILURE(acpi_tb_validate_table(table))) {
 		status = AE_NO_ACPI_TABLES;
 		goto unlock_and_exit;
@@ -170,11 +170,12 @@ acpi_status acpi_tb_load_namespace(void)
 		table = &acpi_gbl_root_table_list.tables[i];
 
 		if (!table->address ||
-		    (!ACPI_COMPARE_NAME(table->signature.ascii, ACPI_SIG_SSDT)
-		     && !ACPI_COMPARE_NAME(table->signature.ascii,
-					   ACPI_SIG_PSDT)
-		     && !ACPI_COMPARE_NAME(table->signature.ascii,
-					   ACPI_SIG_OSDT))
+		    (!ACPI_COMPARE_NAMESEG
+		     (table->signature.ascii, ACPI_SIG_SSDT)
+		     && !ACPI_COMPARE_NAMESEG(table->signature.ascii,
+					      ACPI_SIG_PSDT)
+		     && !ACPI_COMPARE_NAMESEG(table->signature.ascii,
+					      ACPI_SIG_OSDT))
 		    || ACPI_FAILURE(acpi_tb_validate_table(table))) {
 			continue;
 		}
@@ -364,7 +365,7 @@ acpi_status acpi_unload_parent_table(acpi_handle object)
 		 * only these types can contain AML and thus are the only types
 		 * that can create namespace objects.
 		 */
-		if (ACPI_COMPARE_NAME
+		if (ACPI_COMPARE_NAMESEG
 		    (acpi_gbl_root_table_list.tables[i].signature.ascii,
 		     ACPI_SIG_DSDT)) {
 			status = AE_TYPE;
diff --git a/drivers/acpi/acpica/utascii.c b/drivers/acpi/acpica/utascii.c
index 79d7426fd7bf..f6cd7d4f698b 100644
--- a/drivers/acpi/acpica/utascii.c
+++ b/drivers/acpi/acpica/utascii.c
@@ -30,7 +30,7 @@ u8 acpi_ut_valid_nameseg(char *name)
 
 	/* Validate each character in the signature */
 
-	for (i = 0; i < ACPI_NAME_SIZE; i++) {
+	for (i = 0; i < ACPI_NAMESEG_SIZE; i++) {
 		if (!acpi_ut_valid_name_char(name[i], i)) {
 			return (FALSE);
 		}
diff --git a/drivers/acpi/acpica/utdecode.c b/drivers/acpi/acpica/utdecode.c
index ad9f77eb554f..65beaa237669 100644
--- a/drivers/acpi/acpica/utdecode.c
+++ b/drivers/acpi/acpica/utdecode.c
@@ -78,7 +78,7 @@ const char *acpi_gbl_region_types[ACPI_NUM_PREDEFINED_REGIONS] = {
 	"IPMI",			/* 0x07 */
 	"GeneralPurposeIo",	/* 0x08 */
 	"GenericSerialBus",	/* 0x09 */
-	"PCC"			/* 0x0A */
+	"PlatformCommChannel"	/* 0x0A */
 };
 
 const char *acpi_ut_get_region_name(u8 space_id)
@@ -239,7 +239,7 @@ const char *acpi_ut_get_node_name(void *object)
 {
 	struct acpi_namespace_node *node = (struct acpi_namespace_node *)object;
 
-	/* Must return a string of exactly 4 characters == ACPI_NAME_SIZE */
+	/* Must return a string of exactly 4 characters == ACPI_NAMESEG_SIZE */
 
 	if (!object) {
 		return ("NULL");
diff --git a/drivers/acpi/acpica/utmisc.c b/drivers/acpi/acpica/utmisc.c
index afaadc73196b..8638efacdbf4 100644
--- a/drivers/acpi/acpica/utmisc.c
+++ b/drivers/acpi/acpica/utmisc.c
@@ -59,10 +59,10 @@ u8 acpi_ut_is_aml_table(struct acpi_table_header *table)
 
 	/* These are the only tables that contain executable AML */
 
-	if (ACPI_COMPARE_NAME(table->signature, ACPI_SIG_DSDT) ||
-	    ACPI_COMPARE_NAME(table->signature, ACPI_SIG_PSDT) ||
-	    ACPI_COMPARE_NAME(table->signature, ACPI_SIG_SSDT) ||
-	    ACPI_COMPARE_NAME(table->signature, ACPI_SIG_OSDT) ||
+	if (ACPI_COMPARE_NAMESEG(table->signature, ACPI_SIG_DSDT) ||
+	    ACPI_COMPARE_NAMESEG(table->signature, ACPI_SIG_PSDT) ||
+	    ACPI_COMPARE_NAMESEG(table->signature, ACPI_SIG_SSDT) ||
+	    ACPI_COMPARE_NAMESEG(table->signature, ACPI_SIG_OSDT) ||
 	    ACPI_IS_OEM_SIG(table->signature)) {
 		return (TRUE);
 	}
diff --git a/drivers/acpi/acpica/utpredef.c b/drivers/acpi/acpica/utpredef.c
index a9f08f43c685..1b0f68f5ed8c 100644
--- a/drivers/acpi/acpica/utpredef.c
+++ b/drivers/acpi/acpica/utpredef.c
@@ -84,7 +84,7 @@ const union acpi_predefined_info *acpi_ut_match_predefined_method(char *name)
 
 	this_name = acpi_gbl_predefined_methods;
 	while (this_name->info.name[0]) {
-		if (ACPI_COMPARE_NAME(name, this_name->info.name)) {
+		if (ACPI_COMPARE_NAMESEG(name, this_name->info.name)) {
 			return (this_name);
 		}
 
@@ -201,7 +201,7 @@ const union acpi_predefined_info *acpi_ut_match_resource_name(char *name)
 
 	this_name = acpi_gbl_resource_names;
 	while (this_name->info.name[0]) {
-		if (ACPI_COMPARE_NAME(name, this_name->info.name)) {
+		if (ACPI_COMPARE_NAMESEG(name, this_name->info.name)) {
 			return (this_name);
 		}
 
diff --git a/drivers/acpi/acpica/utstring.c b/drivers/acpi/acpica/utstring.c
index 5bef0b059406..c39b5483045d 100644
--- a/drivers/acpi/acpica/utstring.c
+++ b/drivers/acpi/acpica/utstring.c
@@ -141,15 +141,15 @@ void acpi_ut_repair_name(char *name)
 	 * Special case for the root node. This can happen if we get an
 	 * error during the execution of module-level code.
 	 */
-	if (ACPI_COMPARE_NAME(name, ACPI_ROOT_PATHNAME)) {
+	if (ACPI_COMPARE_NAMESEG(name, ACPI_ROOT_PATHNAME)) {
 		return;
 	}
 
-	ACPI_MOVE_NAME(&original_name, name);
+	ACPI_COPY_NAMESEG(&original_name, name);
 
 	/* Check each character in the name */
 
-	for (i = 0; i < ACPI_NAME_SIZE; i++) {
+	for (i = 0; i < ACPI_NAMESEG_SIZE; i++) {
 		if (acpi_ut_valid_name_char(name[i], i)) {
 			continue;
 		}
diff --git a/drivers/acpi/arm64/iort.c b/drivers/acpi/arm64/iort.c
index e48894e002ba..adbf7cbedf80 100644
--- a/drivers/acpi/arm64/iort.c
+++ b/drivers/acpi/arm64/iort.c
@@ -356,7 +356,8 @@ static struct acpi_iort_node *iort_node_get_id(struct acpi_iort_node *node,
 	if (map->flags & ACPI_IORT_ID_SINGLE_MAPPING) {
 		if (node->type == ACPI_IORT_NODE_NAMED_COMPONENT ||
 		    node->type == ACPI_IORT_NODE_PCI_ROOT_COMPLEX ||
-		    node->type == ACPI_IORT_NODE_SMMU_V3) {
+		    node->type == ACPI_IORT_NODE_SMMU_V3 ||
+		    node->type == ACPI_IORT_NODE_PMCG) {
 			*id_out = map->output_base;
 			return parent;
 		}
@@ -394,6 +395,8 @@ static int iort_get_id_mapping_index(struct acpi_iort_node *node)
 		}
 
 		return smmu->id_mapping_index;
+	case ACPI_IORT_NODE_PMCG:
+		return 0;
 	default:
 		return -EINVAL;
 	}
@@ -1218,32 +1221,47 @@ static void __init arm_smmu_v3_init_resources(struct resource *res,
 	}
 }
 
-static bool __init arm_smmu_v3_is_coherent(struct acpi_iort_node *node)
+static void __init arm_smmu_v3_dma_configure(struct device *dev,
+					     struct acpi_iort_node *node)
 {
 	struct acpi_iort_smmu_v3 *smmu;
+	enum dev_dma_attr attr;
 
 	/* Retrieve SMMUv3 specific data */
 	smmu = (struct acpi_iort_smmu_v3 *)node->node_data;
 
-	return smmu->flags & ACPI_IORT_SMMU_V3_COHACC_OVERRIDE;
+	attr = (smmu->flags & ACPI_IORT_SMMU_V3_COHACC_OVERRIDE) ?
+			DEV_DMA_COHERENT : DEV_DMA_NON_COHERENT;
+
+	/* We expect the dma masks to be equivalent for all SMMUv3 set-ups */
+	dev->dma_mask = &dev->coherent_dma_mask;
+
+	/* Configure DMA for the page table walker */
+	acpi_dma_configure(dev, attr);
 }
 
 #if defined(CONFIG_ACPI_NUMA)
 /*
  * set numa proximity domain for smmuv3 device
  */
-static void  __init arm_smmu_v3_set_proximity(struct device *dev,
+static int  __init arm_smmu_v3_set_proximity(struct device *dev,
 					      struct acpi_iort_node *node)
 {
 	struct acpi_iort_smmu_v3 *smmu;
 
 	smmu = (struct acpi_iort_smmu_v3 *)node->node_data;
 	if (smmu->flags & ACPI_IORT_SMMU_V3_PXM_VALID) {
-		set_dev_node(dev, acpi_map_pxm_to_node(smmu->pxm));
+		int node = acpi_map_pxm_to_node(smmu->pxm);
+
+		if (node != NUMA_NO_NODE && !node_online(node))
+			return -EINVAL;
+
+		set_dev_node(dev, node);
 		pr_info("SMMU-v3[%llx] Mapped to Proximity domain %d\n",
 			smmu->base_address,
 			smmu->pxm);
 	}
+	return 0;
 }
 #else
 #define arm_smmu_v3_set_proximity NULL
@@ -1301,30 +1319,96 @@ static void __init arm_smmu_init_resources(struct resource *res,
 	}
 }
 
-static bool __init arm_smmu_is_coherent(struct acpi_iort_node *node)
+static void __init arm_smmu_dma_configure(struct device *dev,
+					  struct acpi_iort_node *node)
 {
 	struct acpi_iort_smmu *smmu;
+	enum dev_dma_attr attr;
 
 	/* Retrieve SMMU specific data */
 	smmu = (struct acpi_iort_smmu *)node->node_data;
 
-	return smmu->flags & ACPI_IORT_SMMU_COHERENT_WALK;
+	attr = (smmu->flags & ACPI_IORT_SMMU_COHERENT_WALK) ?
+			DEV_DMA_COHERENT : DEV_DMA_NON_COHERENT;
+
+	/* We expect the dma masks to be equivalent for SMMU set-ups */
+	dev->dma_mask = &dev->coherent_dma_mask;
+
+	/* Configure DMA for the page table walker */
+	acpi_dma_configure(dev, attr);
+}
+
+static int __init arm_smmu_v3_pmcg_count_resources(struct acpi_iort_node *node)
+{
+	struct acpi_iort_pmcg *pmcg;
+
+	/* Retrieve PMCG specific data */
+	pmcg = (struct acpi_iort_pmcg *)node->node_data;
+
+	/*
+	 * There are always 2 memory resources.
+	 * If the overflow_gsiv is present then add that for a total of 3.
+	 */
+	return pmcg->overflow_gsiv ? 3 : 2;
+}
+
+static void __init arm_smmu_v3_pmcg_init_resources(struct resource *res,
+						   struct acpi_iort_node *node)
+{
+	struct acpi_iort_pmcg *pmcg;
+
+	/* Retrieve PMCG specific data */
+	pmcg = (struct acpi_iort_pmcg *)node->node_data;
+
+	res[0].start = pmcg->page0_base_address;
+	res[0].end = pmcg->page0_base_address + SZ_4K - 1;
+	res[0].flags = IORESOURCE_MEM;
+	res[1].start = pmcg->page1_base_address;
+	res[1].end = pmcg->page1_base_address + SZ_4K - 1;
+	res[1].flags = IORESOURCE_MEM;
+
+	if (pmcg->overflow_gsiv)
+		acpi_iort_register_irq(pmcg->overflow_gsiv, "overflow",
+				       ACPI_EDGE_SENSITIVE, &res[2]);
+}
+
+static struct acpi_platform_list pmcg_plat_info[] __initdata = {
+	/* HiSilicon Hip08 Platform */
+	{"HISI  ", "HIP08   ", 0, ACPI_SIG_IORT, greater_than_or_equal,
+	 "Erratum #162001800", IORT_SMMU_V3_PMCG_HISI_HIP08},
+	{ }
+};
+
+static int __init arm_smmu_v3_pmcg_add_platdata(struct platform_device *pdev)
+{
+	u32 model;
+	int idx;
+
+	idx = acpi_match_platform_list(pmcg_plat_info);
+	if (idx >= 0)
+		model = pmcg_plat_info[idx].data;
+	else
+		model = IORT_SMMU_V3_PMCG_GENERIC;
+
+	return platform_device_add_data(pdev, &model, sizeof(model));
 }
 
 struct iort_dev_config {
 	const char *name;
 	int (*dev_init)(struct acpi_iort_node *node);
-	bool (*dev_is_coherent)(struct acpi_iort_node *node);
+	void (*dev_dma_configure)(struct device *dev,
+				  struct acpi_iort_node *node);
 	int (*dev_count_resources)(struct acpi_iort_node *node);
 	void (*dev_init_resources)(struct resource *res,
 				     struct acpi_iort_node *node);
-	void (*dev_set_proximity)(struct device *dev,
+	int (*dev_set_proximity)(struct device *dev,
 				    struct acpi_iort_node *node);
+	int (*dev_add_platdata)(struct platform_device *pdev);
 };
 
 static const struct iort_dev_config iort_arm_smmu_v3_cfg __initconst = {
 	.name = "arm-smmu-v3",
-	.dev_is_coherent = arm_smmu_v3_is_coherent,
+	.dev_dma_configure = arm_smmu_v3_dma_configure,
 	.dev_count_resources = arm_smmu_v3_count_resources,
 	.dev_init_resources = arm_smmu_v3_init_resources,
 	.dev_set_proximity = arm_smmu_v3_set_proximity,
@@ -1332,9 +1416,16 @@ static const struct iort_dev_config iort_arm_smmu_v3_cfg __initconst = {
 
 static const struct iort_dev_config iort_arm_smmu_cfg __initconst = {
 	.name = "arm-smmu",
-	.dev_is_coherent = arm_smmu_is_coherent,
+	.dev_dma_configure = arm_smmu_dma_configure,
 	.dev_count_resources = arm_smmu_count_resources,
-	.dev_init_resources = arm_smmu_init_resources
+	.dev_init_resources = arm_smmu_init_resources,
+};
+
+static const struct iort_dev_config iort_arm_smmu_v3_pmcg_cfg __initconst = {
+	.name = "arm-smmu-v3-pmcg",
+	.dev_count_resources = arm_smmu_v3_pmcg_count_resources,
+	.dev_init_resources = arm_smmu_v3_pmcg_init_resources,
+	.dev_add_platdata = arm_smmu_v3_pmcg_add_platdata,
 };
 
 static __init const struct iort_dev_config *iort_get_dev_cfg(
@@ -1345,6 +1436,8 @@ static __init const struct iort_dev_config *iort_get_dev_cfg(
 		return &iort_arm_smmu_v3_cfg;
 	case ACPI_IORT_NODE_SMMU:
 		return &iort_arm_smmu_cfg;
+	case ACPI_IORT_NODE_PMCG:
+		return &iort_arm_smmu_v3_pmcg_cfg;
 	default:
 		return NULL;
 	}
@@ -1362,15 +1455,17 @@ static int __init iort_add_platform_device(struct acpi_iort_node *node,
 	struct fwnode_handle *fwnode;
 	struct platform_device *pdev;
 	struct resource *r;
-	enum dev_dma_attr attr;
 	int ret, count;
 
 	pdev = platform_device_alloc(ops->name, PLATFORM_DEVID_AUTO);
 	if (!pdev)
 		return -ENOMEM;
 
-	if (ops->dev_set_proximity)
-		ops->dev_set_proximity(&pdev->dev, node);
+	if (ops->dev_set_proximity) {
+		ret = ops->dev_set_proximity(&pdev->dev, node);
+		if (ret)
+			goto dev_put;
+	}
 
 	count = ops->dev_count_resources(node);
 
@@ -1393,19 +1488,19 @@ static int __init iort_add_platform_device(struct acpi_iort_node *node,
 		goto dev_put;
 
 	/*
-	 * Add a copy of IORT node pointer to platform_data to
-	 * be used to retrieve IORT data information.
+	 * Platform devices based on PMCG nodes uses platform_data to
+	 * pass the hardware model info to the driver. For others, add
+	 * a copy of IORT node pointer to platform_data to be used to
+	 * retrieve IORT data information.
 	 */
-	ret = platform_device_add_data(pdev, &node, sizeof(node));
+	if (ops->dev_add_platdata)
+		ret = ops->dev_add_platdata(pdev);
+	else
+		ret = platform_device_add_data(pdev, &node, sizeof(node));
+
 	if (ret)
 		goto dev_put;
 
-	/*
-	 * We expect the dma masks to be equivalent for
-	 * all SMMUs set-ups
-	 */
-	pdev->dev.dma_mask = &pdev->dev.coherent_dma_mask;
-
 	fwnode = iort_get_fwnode(node);
 
 	if (!fwnode) {
@@ -1415,11 +1510,8 @@ static int __init iort_add_platform_device(struct acpi_iort_node *node,
 
 	pdev->dev.fwnode = fwnode;
 
-	attr = ops->dev_is_coherent && ops->dev_is_coherent(node) ?
-			DEV_DMA_COHERENT : DEV_DMA_NON_COHERENT;
-
-	/* Configure DMA for the page table walker */
-	acpi_dma_configure(&pdev->dev, attr);
+	if (ops->dev_dma_configure)
+		ops->dev_dma_configure(&pdev->dev, node);
 
 	iort_set_device_domain(&pdev->dev, node);
 
diff --git a/drivers/acpi/bus.c b/drivers/acpi/bus.c
index 6ecbbabf1233..eec263c9019e 100644
--- a/drivers/acpi/bus.c
+++ b/drivers/acpi/bus.c
@@ -1043,9 +1043,6 @@ void __init acpi_early_init(void)
 
 	acpi_permanent_mmap = true;
 
-	/* Initialize debug output. Linux does not use ACPICA defaults */
-	acpi_dbg_level = ACPI_LV_INFO | ACPI_LV_REPAIR;
-
 #ifdef CONFIG_X86
 	/*
 	 * If the machine falls into the DMI check table,
diff --git a/drivers/acpi/button.c b/drivers/acpi/button.c
index a19ff3977ac4..623998a8d722 100644
--- a/drivers/acpi/button.c
+++ b/drivers/acpi/button.c
@@ -456,8 +456,11 @@ static int acpi_button_resume(struct device *dev)
 	struct acpi_button *button = acpi_driver_data(device);
 
 	button->suspended = false;
-	if (button->type == ACPI_BUTTON_TYPE_LID && button->input->users)
+	if (button->type == ACPI_BUTTON_TYPE_LID && button->input->users) {
+		button->last_state = !!acpi_lid_evaluate_state(device);
+		button->last_time = ktime_get();
 		acpi_lid_initialize_state(device);
+	}
 	return 0;
 }
 #endif
diff --git a/drivers/acpi/cppc_acpi.c b/drivers/acpi/cppc_acpi.c
index 1b207fca1420..653642a4cbdd 100644
--- a/drivers/acpi/cppc_acpi.c
+++ b/drivers/acpi/cppc_acpi.c
@@ -81,9 +81,9 @@ struct cppc_pcc_data {
 	int refcount;
 };
 
-/* Array  to represent the PCC channel per subspace id */
+/* Array to represent the PCC channel per subspace ID */
 static struct cppc_pcc_data *pcc_data[MAX_PCC_SUBSPACES];
-/* The cpu_pcc_subspace_idx containsper CPU subspace id */
+/* The cpu_pcc_subspace_idx contains per CPU subspace ID */
 static DEFINE_PER_CPU(int, cpu_pcc_subspace_idx);
 
 /*
@@ -436,7 +436,7 @@ int acpi_get_psd_map(struct cppc_cpudata **all_cpu_data)
 		return -ENOMEM;
 
 	/*
-	 * Now that we have _PSD data from all CPUs, lets setup P-state
+	 * Now that we have _PSD data from all CPUs, let's setup P-state
 	 * domain info.
 	 */
 	for_each_possible_cpu(i) {
@@ -588,7 +588,7 @@ static int register_pcc_channel(int pcc_ss_idx)
 			return -ENOMEM;
 		}
 
-		/* Set flag so that we dont come here for each CPU. */
+		/* Set flag so that we don't come here for each CPU. */
 		pcc_data[pcc_ss_idx]->pcc_channel_acquired = true;
 	}
 
@@ -613,7 +613,7 @@ bool __weak cpc_ffh_supported(void)
  *
  * Check and allocate the cppc_pcc_data memory.
  * In some processor configurations it is possible that same subspace
- * is shared between multiple CPU's. This is seen especially in CPU's
+ * is shared between multiple CPUs. This is seen especially in CPUs
  * with hardware multi-threading support.
  *
  * Return: 0 for success, errno for failure
@@ -711,7 +711,7 @@ static bool is_cppc_supported(int revision, int num_ent)
 
 /**
  * acpi_cppc_processor_probe - Search for per CPU _CPC objects.
- * @pr: Ptr to acpi_processor containing this CPUs logical Id.
+ * @pr: Ptr to acpi_processor containing this CPU's logical ID.
  *
  *	Return: 0 for success or negative value for err.
  */
@@ -728,7 +728,7 @@ int acpi_cppc_processor_probe(struct acpi_processor *pr)
 	acpi_status status;
 	int ret = -EFAULT;
 
-	/* Parse the ACPI _CPC table for this cpu. */
+	/* Parse the ACPI _CPC table for this CPU. */
 	status = acpi_evaluate_object_typed(handle, "_CPC", NULL, &output,
 			ACPI_TYPE_PACKAGE);
 	if (ACPI_FAILURE(status)) {
@@ -840,7 +840,7 @@ int acpi_cppc_processor_probe(struct acpi_processor *pr)
 	if (ret)
 		goto out_free;
 
-	/* Register PCC channel once for all PCC subspace id. */
+	/* Register PCC channel once for all PCC subspace ID. */
 	if (pcc_subspace_id >= 0 && !pcc_data[pcc_subspace_id]->pcc_channel_acquired) {
 		ret = register_pcc_channel(pcc_subspace_id);
 		if (ret)
@@ -860,7 +860,7 @@ int acpi_cppc_processor_probe(struct acpi_processor *pr)
 		goto out_free;
 	}
 
-	/* Plug PSD data into this CPUs CPC descriptor. */
+	/* Plug PSD data into this CPU's CPC descriptor. */
 	per_cpu(cpc_desc_ptr, pr->id) = cpc_ptr;
 
 	ret = kobject_init_and_add(&cpc_ptr->kobj, &cppc_ktype, &cpu_dev->kobj,
@@ -891,7 +891,7 @@ EXPORT_SYMBOL_GPL(acpi_cppc_processor_probe);
 
 /**
  * acpi_cppc_processor_exit - Cleanup CPC structs.
- * @pr: Ptr to acpi_processor containing this CPUs logical Id.
+ * @pr: Ptr to acpi_processor containing this CPU's logical ID.
  *
  * Return: Void
  */
@@ -931,7 +931,7 @@ EXPORT_SYMBOL_GPL(acpi_cppc_processor_exit);
 
 /**
  * cpc_read_ffh() - Read FFH register
- * @cpunum:	cpu number to read
+ * @cpunum:	CPU number to read
  * @reg:	cppc register information
  * @val:	place holder for return value
  *
@@ -946,7 +946,7 @@ int __weak cpc_read_ffh(int cpunum, struct cpc_reg *reg, u64 *val)
 
 /**
  * cpc_write_ffh() - Write FFH register
- * @cpunum:	cpu number to write
+ * @cpunum:	CPU number to write
  * @reg:	cppc register information
  * @val:	value to write
  *
@@ -1093,7 +1093,7 @@ int cppc_get_desired_perf(int cpunum, u64 *desired_perf)
 EXPORT_SYMBOL_GPL(cppc_get_desired_perf);
 
 /**
- * cppc_get_perf_caps - Get a CPUs performance capabilities.
+ * cppc_get_perf_caps - Get a CPU's performance capabilities.
  * @cpunum: CPU from which to get capabilities info.
  * @perf_caps: ptr to cppc_perf_caps. See cppc_acpi.h
  *
@@ -1150,8 +1150,13 @@ int cppc_get_perf_caps(int cpunum, struct cppc_perf_caps *perf_caps)
 	cpc_read(cpunum, nominal_reg, &nom);
 	perf_caps->nominal_perf = nom;
 
-	cpc_read(cpunum, guaranteed_reg, &guaranteed);
-	perf_caps->guaranteed_perf = guaranteed;
+	if (guaranteed_reg->type != ACPI_TYPE_BUFFER  ||
+	    IS_NULL_REG(&guaranteed_reg->cpc_entry.reg)) {
+		perf_caps->guaranteed_perf = 0;
+	} else {
+		cpc_read(cpunum, guaranteed_reg, &guaranteed);
+		perf_caps->guaranteed_perf = guaranteed;
+	}
 
 	cpc_read(cpunum, lowest_non_linear_reg, &min_nonlinear);
 	perf_caps->lowest_nonlinear_perf = min_nonlinear;
@@ -1178,7 +1183,7 @@ out_err:
 EXPORT_SYMBOL_GPL(cppc_get_perf_caps);
 
 /**
- * cppc_get_perf_ctrs - Read a CPUs performance feedback counters.
+ * cppc_get_perf_ctrs - Read a CPU's performance feedback counters.
  * @cpunum: CPU from which to read counters.
  * @perf_fb_ctrs: ptr to cppc_perf_fb_ctrs. See cppc_acpi.h
  *
@@ -1205,7 +1210,7 @@ int cppc_get_perf_ctrs(int cpunum, struct cppc_perf_fb_ctrs *perf_fb_ctrs)
 	ctr_wrap_reg = &cpc_desc->cpc_regs[CTR_WRAP_TIME];
 
 	/*
-	 * If refernce perf register is not supported then we should
+	 * If reference perf register is not supported then we should
 	 * use the nominal perf value
 	 */
 	if (!CPC_SUPPORTED(ref_perf_reg))
@@ -1258,7 +1263,7 @@ out_err:
 EXPORT_SYMBOL_GPL(cppc_get_perf_ctrs);
 
 /**
- * cppc_set_perf - Set a CPUs performance controls.
+ * cppc_set_perf - Set a CPU's performance controls.
  * @cpu: CPU for which to set performance controls.
  * @perf_ctrls: ptr to cppc_perf_ctrls. See cppc_acpi.h
  *
@@ -1339,7 +1344,7 @@ int cppc_set_perf(int cpu, struct cppc_perf_ctrls *perf_ctrls)
 	 * executing the Phase-II.
 	 *     2. Some other CPU has beaten this CPU to successfully execute the
 	 * write_trylock and has already acquired the write_lock. We know for a
-	 * fact it(other CPU acquiring the write_lock) couldn't have happened
+	 * fact it (other CPU acquiring the write_lock) couldn't have happened
 	 * before this CPU's Phase-I as we held the read_lock.
 	 *     3. Some other CPU executing pcc CMD_READ has stolen the
 	 * down_write, in which case, send_pcc_cmd will check for pending
diff --git a/drivers/acpi/device_pm.c b/drivers/acpi/device_pm.c
index 824ae985ad93..5b50f884712c 100644
--- a/drivers/acpi/device_pm.c
+++ b/drivers/acpi/device_pm.c
@@ -728,6 +728,9 @@ static int __acpi_device_wakeup_enable(struct acpi_device *adev,
 		goto out;
 	}
 
+	acpi_handle_debug(adev->handle, "GPE%2X enabled for wakeup\n",
+			  (unsigned int)wakeup->gpe_number);
+
 inc:
 	wakeup->enable_count++;
 
diff --git a/drivers/acpi/dptf/dptf_power.c b/drivers/acpi/dptf/dptf_power.c
index e1c242568341..0c081390930a 100644
--- a/drivers/acpi/dptf/dptf_power.c
+++ b/drivers/acpi/dptf/dptf_power.c
@@ -31,8 +31,7 @@ static ssize_t name##_show(struct device *dev,\
 			   struct device_attribute *attr,\
 			   char *buf)\
 {\
-	struct platform_device *pdev = to_platform_device(dev);\
-	struct acpi_device *acpi_dev = platform_get_drvdata(pdev);\
+	struct acpi_device *acpi_dev = dev_get_drvdata(dev);\
 	unsigned long long val;\
 	acpi_status status;\
 \
diff --git a/drivers/acpi/event.c b/drivers/acpi/event.c
index 5a127f3f2d5c..47f21599f2ab 100644
--- a/drivers/acpi/event.c
+++ b/drivers/acpi/event.c
@@ -131,8 +131,8 @@ int acpi_bus_generate_netlink_event(const char *device_class,
 	event = nla_data(attr);
 	memset(event, 0, sizeof(struct acpi_genl_event));
 
-	strcpy(event->device_class, device_class);
-	strcpy(event->bus_id, bus_id);
+	strscpy(event->device_class, device_class, sizeof(event->device_class));
+	strscpy(event->bus_id, bus_id, sizeof(event->bus_id));
 	event->type = type;
 	event->data = data;
 
diff --git a/drivers/acpi/nfit/core.c b/drivers/acpi/nfit/core.c
index 5a389a4f4f65..f1ed0befe303 100644
--- a/drivers/acpi/nfit/core.c
+++ b/drivers/acpi/nfit/core.c
@@ -567,6 +567,12 @@ int acpi_nfit_ctl(struct nvdimm_bus_descriptor *nd_desc, struct nvdimm *nvdimm,
 		goto out;
 	}
 
+	dev_dbg(dev, "%s cmd: %s output length: %d\n", dimm_name,
+			cmd_name, out_obj->buffer.length);
+	print_hex_dump_debug(cmd_name, DUMP_PREFIX_OFFSET, 4, 4,
+			out_obj->buffer.pointer,
+			min_t(u32, 128, out_obj->buffer.length), true);
+
 	if (call_pkg) {
 		call_pkg->nd_fw_size = out_obj->buffer.length;
 		memcpy(call_pkg->nd_payload + call_pkg->nd_size_in,
@@ -585,12 +591,6 @@ int acpi_nfit_ctl(struct nvdimm_bus_descriptor *nd_desc, struct nvdimm *nvdimm,
 		return 0;
 	}
 
-	dev_dbg(dev, "%s cmd: %s output length: %d\n", dimm_name,
-			cmd_name, out_obj->buffer.length);
-	print_hex_dump_debug(cmd_name, DUMP_PREFIX_OFFSET, 4, 4,
-			out_obj->buffer.pointer,
-			min_t(u32, 128, out_obj->buffer.length), true);
-
 	for (i = 0, offset = 0; i < desc->out_num; i++) {
 		u32 out_size = nd_cmd_out_size(nvdimm, cmd, desc, i, buf,
 				(u32 *) out_obj->buffer.pointer,
diff --git a/drivers/acpi/nfit/intel.c b/drivers/acpi/nfit/intel.c
index f70de71f79d6..cddd0fcf622c 100644
--- a/drivers/acpi/nfit/intel.c
+++ b/drivers/acpi/nfit/intel.c
@@ -122,9 +122,8 @@ static int intel_security_change_key(struct nvdimm *nvdimm,
 	if (!test_bit(cmd, &nfit_mem->dsm_mask))
 		return -ENOTTY;
 
-	if (old_data)
-		memcpy(nd_cmd.cmd.old_pass, old_data->data,
-				sizeof(nd_cmd.cmd.old_pass));
+	memcpy(nd_cmd.cmd.old_pass, old_data->data,
+			sizeof(nd_cmd.cmd.old_pass));
 	memcpy(nd_cmd.cmd.new_pass, new_data->data,
 			sizeof(nd_cmd.cmd.new_pass));
 	rc = nvdimm_ctl(nvdimm, ND_CMD_CALL, &nd_cmd, sizeof(nd_cmd), NULL);
@@ -336,9 +335,8 @@ static int __maybe_unused intel_security_overwrite(struct nvdimm *nvdimm,
 
 	/* flush all cache before we erase DIMM */
 	nvdimm_invalidate_cache();
-	if (nkey)
-		memcpy(nd_cmd.cmd.passphrase, nkey->data,
-				sizeof(nd_cmd.cmd.passphrase));
+	memcpy(nd_cmd.cmd.passphrase, nkey->data,
+			sizeof(nd_cmd.cmd.passphrase));
 	rc = nvdimm_ctl(nvdimm, ND_CMD_CALL, &nd_cmd, sizeof(nd_cmd), NULL);
 	if (rc < 0)
 		return rc;
diff --git a/drivers/acpi/power.c b/drivers/acpi/power.c
index 665e93ca0b40..87db3e124725 100644
--- a/drivers/acpi/power.c
+++ b/drivers/acpi/power.c
@@ -535,12 +535,12 @@ int acpi_device_sleep_wake(struct acpi_device *dev,
 	/*
 	 * Try to execute _DSW first.
 	 *
-	 * Three agruments are needed for the _DSW object:
+	 * Three arguments are needed for the _DSW object:
 	 * Argument 0: enable/disable the wake capabilities
 	 * Argument 1: target system state
 	 * Argument 2: target device state
 	 * When _DSW object is called to disable the wake capabilities, maybe
-	 * the first argument is filled. The values of the other two agruments
+	 * the first argument is filled. The values of the other two arguments
 	 * are meaningless.
 	 */
 	in_arg[0].type = ACPI_TYPE_INTEGER;
diff --git a/drivers/acpi/pptt.c b/drivers/acpi/pptt.c
index 065c4fc245d1..b72e6afaa8fb 100644
--- a/drivers/acpi/pptt.c
+++ b/drivers/acpi/pptt.c
@@ -164,7 +164,7 @@ static struct acpi_pptt_cache *acpi_find_cache_level(struct acpi_table_header *t
 }
 
 /**
- * acpi_count_levels() - Given a PPTT table, and a cpu node, count the caches
+ * acpi_count_levels() - Given a PPTT table, and a CPU node, count the caches
  * @table_hdr: Pointer to the head of the PPTT table
  * @cpu_node: processor node we wish to count caches for
  *
@@ -235,7 +235,7 @@ static int acpi_pptt_leaf_node(struct acpi_table_header *table_hdr,
 /**
  * acpi_find_processor_node() - Given a PPTT table find the requested processor
  * @table_hdr:  Pointer to the head of the PPTT table
- * @acpi_cpu_id: cpu we are searching for
+ * @acpi_cpu_id: CPU we are searching for
  *
  * Find the subtable entry describing the provided processor.
  * This is done by iterating the PPTT table looking for processor nodes
@@ -456,21 +456,21 @@ static struct acpi_pptt_processor *acpi_find_processor_package_id(struct acpi_ta
 
 static void acpi_pptt_warn_missing(void)
 {
-	pr_warn_once("No PPTT table found, cpu and cache topology may be inaccurate\n");
+	pr_warn_once("No PPTT table found, CPU and cache topology may be inaccurate\n");
 }
 
 /**
  * topology_get_acpi_cpu_tag() - Find a unique topology value for a feature
  * @table: Pointer to the head of the PPTT table
- * @cpu: Kernel logical cpu number
+ * @cpu: Kernel logical CPU number
  * @level: A level that terminates the search
  * @flag: A flag which terminates the search
  *
- * Get a unique value given a cpu, and a topology level, that can be
+ * Get a unique value given a CPU, and a topology level, that can be
  * matched to determine which cpus share common topological features
  * at that level.
  *
- * Return: Unique value, or -ENOENT if unable to locate cpu
+ * Return: Unique value, or -ENOENT if unable to locate CPU
  */
 static int topology_get_acpi_cpu_tag(struct acpi_table_header *table,
 				     unsigned int cpu, int level, int flag)
@@ -510,7 +510,7 @@ static int find_acpi_cpu_topology_tag(unsigned int cpu, int level, int flag)
 		return -ENOENT;
 	}
 	retval = topology_get_acpi_cpu_tag(table, cpu, level, flag);
-	pr_debug("Topology Setup ACPI cpu %d, level %d ret = %d\n",
+	pr_debug("Topology Setup ACPI CPU %d, level %d ret = %d\n",
 		 cpu, level, retval);
 	acpi_put_table(table);
 
@@ -519,9 +519,9 @@ static int find_acpi_cpu_topology_tag(unsigned int cpu, int level, int flag)
 
 /**
  * acpi_find_last_cache_level() - Determines the number of cache levels for a PE
- * @cpu: Kernel logical cpu number
+ * @cpu: Kernel logical CPU number
  *
- * Given a logical cpu number, returns the number of levels of cache represented
+ * Given a logical CPU number, returns the number of levels of cache represented
  * in the PPTT. Errors caused by lack of a PPTT table, or otherwise, return 0
  * indicating we didn't find any cache levels.
  *
@@ -534,7 +534,7 @@ int acpi_find_last_cache_level(unsigned int cpu)
 	int number_of_levels = 0;
 	acpi_status status;
 
-	pr_debug("Cache Setup find last level cpu=%d\n", cpu);
+	pr_debug("Cache Setup find last level CPU=%d\n", cpu);
 
 	acpi_cpu_id = get_acpi_id_for_cpu(cpu);
 	status = acpi_get_table(ACPI_SIG_PPTT, 0, &table);
@@ -551,14 +551,14 @@ int acpi_find_last_cache_level(unsigned int cpu)
 
 /**
  * cache_setup_acpi() - Override CPU cache topology with data from the PPTT
- * @cpu: Kernel logical cpu number
+ * @cpu: Kernel logical CPU number
  *
  * Updates the global cache info provided by cpu_get_cacheinfo()
  * when there are valid properties in the acpi_pptt_cache nodes. A
  * successful parse may not result in any updates if none of the
- * cache levels have any valid flags set.  Futher, a unique value is
+ * cache levels have any valid flags set.  Further, a unique value is
  * associated with each known CPU cache entry. This unique value
- * can be used to determine whether caches are shared between cpus.
+ * can be used to determine whether caches are shared between CPUs.
  *
  * Return: -ENOENT on failure to find table, or 0 on success
  */
@@ -567,7 +567,7 @@ int cache_setup_acpi(unsigned int cpu)
 	struct acpi_table_header *table;
 	acpi_status status;
 
-	pr_debug("Cache Setup ACPI cpu %d\n", cpu);
+	pr_debug("Cache Setup ACPI CPU %d\n", cpu);
 
 	status = acpi_get_table(ACPI_SIG_PPTT, 0, &table);
 	if (ACPI_FAILURE(status)) {
@@ -582,8 +582,8 @@ int cache_setup_acpi(unsigned int cpu)
 }
 
 /**
- * find_acpi_cpu_topology() - Determine a unique topology value for a given cpu
- * @cpu: Kernel logical cpu number
+ * find_acpi_cpu_topology() - Determine a unique topology value for a given CPU
+ * @cpu: Kernel logical CPU number
  * @level: The topological level for which we would like a unique ID
  *
  * Determine a topology unique ID for each thread/core/cluster/mc_grouping
@@ -596,7 +596,7 @@ int cache_setup_acpi(unsigned int cpu)
  * other levels beyond this use a generated value to uniquely identify
  * a topological feature.
  *
- * Return: -ENOENT if the PPTT doesn't exist, or the cpu cannot be found.
+ * Return: -ENOENT if the PPTT doesn't exist, or the CPU cannot be found.
  * Otherwise returns a value which represents a unique topological feature.
  */
 int find_acpi_cpu_topology(unsigned int cpu, int level)
@@ -606,12 +606,12 @@ int find_acpi_cpu_topology(unsigned int cpu, int level)
 
 /**
  * find_acpi_cpu_cache_topology() - Determine a unique cache topology value
- * @cpu: Kernel logical cpu number
+ * @cpu: Kernel logical CPU number
  * @level: The cache level for which we would like a unique ID
  *
  * Determine a unique ID for each unified cache in the system
  *
- * Return: -ENOENT if the PPTT doesn't exist, or the cpu cannot be found.
+ * Return: -ENOENT if the PPTT doesn't exist, or the CPU cannot be found.
  * Otherwise returns a value which represents a unique topological feature.
  */
 int find_acpi_cpu_cache_topology(unsigned int cpu, int level)
@@ -643,17 +643,17 @@ int find_acpi_cpu_cache_topology(unsigned int cpu, int level)
 
 
 /**
- * find_acpi_cpu_topology_package() - Determine a unique cpu package value
- * @cpu: Kernel logical cpu number
+ * find_acpi_cpu_topology_package() - Determine a unique CPU package value
+ * @cpu: Kernel logical CPU number
  *
- * Determine a topology unique package ID for the given cpu.
+ * Determine a topology unique package ID for the given CPU.
  * This ID can then be used to group peers, which will have matching ids.
  *
  * The search terminates when either a level is found with the PHYSICAL_PACKAGE
  * flag set or we reach a root node.
  *
- * Return: -ENOENT if the PPTT doesn't exist, or the cpu cannot be found.
- * Otherwise returns a value which represents the package for this cpu.
+ * Return: -ENOENT if the PPTT doesn't exist, or the CPU cannot be found.
+ * Otherwise returns a value which represents the package for this CPU.
  */
 int find_acpi_cpu_topology_package(unsigned int cpu)
 {
diff --git a/drivers/acpi/processor_perflib.c b/drivers/acpi/processor_perflib.c
index a303fd0e108c..c73d3a62799a 100644
--- a/drivers/acpi/processor_perflib.c
+++ b/drivers/acpi/processor_perflib.c
@@ -181,7 +181,7 @@ void acpi_processor_ppc_has_changed(struct acpi_processor *pr, int event_flag)
 			acpi_processor_ppc_ost(pr->handle, 0);
 	}
 	if (ret >= 0)
-		cpufreq_update_policy(pr->id);
+		cpufreq_update_limits(pr->id);
 }
 
 int acpi_processor_get_bios_limit(int cpu, unsigned int *limit)
diff --git a/drivers/acpi/property.c b/drivers/acpi/property.c
index 77abe0ec4043..9d460a859be0 100644
--- a/drivers/acpi/property.c
+++ b/drivers/acpi/property.c
@@ -44,6 +44,7 @@ static const guid_t prp_guids[] = {
 		  0xbf, 0xf0, 0x76, 0x14, 0x38, 0x07, 0xc3, 0x89),
 };
 
+/* ACPI _DSD data subnodes GUID: dbb8e3e6-5886-4ba6-8795-1319f52a966b */
 static const guid_t ads_guid =
 	GUID_INIT(0xdbb8e3e6, 0x5886, 0x4ba6,
 		  0x87, 0x95, 0x13, 0x19, 0xf5, 0x2a, 0x96, 0x6b);
@@ -1031,6 +1032,14 @@ struct fwnode_handle *acpi_get_next_subnode(const struct fwnode_handle *fwnode,
 		const struct acpi_data_node *data = to_acpi_data_node(fwnode);
 		struct acpi_data_node *dn;
 
+		/*
+		 * We can have a combination of device and data nodes, e.g. with
+		 * hierarchical _DSD properties. Make sure the adev pointer is
+		 * restored before going through data nodes, otherwise we will
+		 * be looking for data_nodes below the last device found instead
+		 * of the common fwnode shared by device_nodes and data_nodes.
+		 */
+		adev = to_acpi_device_node(fwnode);
 		if (adev)
 			head = &adev->data.subnodes;
 		else if (data)
diff --git a/drivers/acpi/scan.c b/drivers/acpi/scan.c
index 446c959a8f08..b845dc3e0ba9 100644
--- a/drivers/acpi/scan.c
+++ b/drivers/acpi/scan.c
@@ -763,18 +763,16 @@ acpi_bus_get_ejd(acpi_handle handle, acpi_handle *ejd)
 }
 EXPORT_SYMBOL_GPL(acpi_bus_get_ejd);
 
-static int acpi_bus_extract_wakeup_device_power_package(acpi_handle handle,
-					struct acpi_device_wakeup *wakeup)
+static int acpi_bus_extract_wakeup_device_power_package(struct acpi_device *dev)
 {
+	acpi_handle handle = dev->handle;
+	struct acpi_device_wakeup *wakeup = &dev->wakeup;
 	struct acpi_buffer buffer = { ACPI_ALLOCATE_BUFFER, NULL };
 	union acpi_object *package = NULL;
 	union acpi_object *element = NULL;
 	acpi_status status;
 	int err = -ENODATA;
 
-	if (!wakeup)
-		return -EINVAL;
-
 	INIT_LIST_HEAD(&wakeup->resources);
 
 	/* _PRW */
@@ -848,9 +846,9 @@ static int acpi_bus_extract_wakeup_device_power_package(acpi_handle handle,
 static bool acpi_wakeup_gpe_init(struct acpi_device *device)
 {
 	static const struct acpi_device_id button_device_ids[] = {
-		{"PNP0C0C", 0},
-		{"PNP0C0D", 0},
-		{"PNP0C0E", 0},
+		{"PNP0C0C", 0},		/* Power button */
+		{"PNP0C0D", 0},		/* Lid */
+		{"PNP0C0E", 0},		/* Sleep button */
 		{"", 0},
 	};
 	struct acpi_device_wakeup *wakeup = &device->wakeup;
@@ -883,8 +881,7 @@ static void acpi_bus_get_wakeup_device_flags(struct acpi_device *device)
 	if (!acpi_has_method(device->handle, "_PRW"))
 		return;
 
-	err = acpi_bus_extract_wakeup_device_power_package(device->handle,
-							   &device->wakeup);
+	err = acpi_bus_extract_wakeup_device_power_package(device);
 	if (err) {
 		dev_err(&device->dev, "_PRW evaluation error: %d\n", err);
 		return;
@@ -895,7 +892,7 @@ static void acpi_bus_get_wakeup_device_flags(struct acpi_device *device)
 	/*
 	 * Call _PSW/_DSW object to disable its ability to wake the sleeping
 	 * system for the ACPI device with the _PRW object.
-	 * The _PSW object is depreciated in ACPI 3.0 and is replaced by _DSW.
+	 * The _PSW object is deprecated in ACPI 3.0 and is replaced by _DSW.
 	 * So it is necessary to call _DSW object first. Only when it is not
 	 * present will the _PSW object used.
 	 */
@@ -2260,7 +2257,7 @@ int __init __acpi_probe_device_table(struct acpi_probe_entry *ap_head, int nr)
 
 	mutex_lock(&acpi_probe_mutex);
 	for (ape = ap_head; nr; ape++, nr--) {
-		if (ACPI_COMPARE_NAME(ACPI_SIG_MADT, ape->id)) {
+		if (ACPI_COMPARE_NAMESEG(ACPI_SIG_MADT, ape->id)) {
 			acpi_probe_count = 0;
 			acpi_table_parse_madt(ape->type, acpi_match_madt, 0);
 			count += acpi_probe_count;
diff --git a/drivers/acpi/spcr.c b/drivers/acpi/spcr.c
index c336784d0bcb..b34d05e365b7 100644
--- a/drivers/acpi/spcr.c
+++ b/drivers/acpi/spcr.c
@@ -28,7 +28,7 @@ EXPORT_SYMBOL(qdf2400_e44_present);
 
 /*
  * Some Qualcomm Datacenter Technologies SoCs have a defective UART BUSY bit.
- * Detect them by examining the OEM fields in the SPCR header, similiar to PCI
+ * Detect them by examining the OEM fields in the SPCR header, similar to PCI
  * quirk detection in pci_mcfg.c.
  */
 static bool qdf2400_erratum_44_present(struct acpi_table_header *h)
diff --git a/drivers/acpi/sysfs.c b/drivers/acpi/sysfs.c
index fa76f5e41b5c..75948a3f1a20 100644
--- a/drivers/acpi/sysfs.c
+++ b/drivers/acpi/sysfs.c
@@ -327,9 +327,9 @@ static struct kobject *hotplug_kobj;
 
 struct acpi_table_attr {
 	struct bin_attribute attr;
-	char name[ACPI_NAME_SIZE];
+	char name[ACPI_NAMESEG_SIZE];
 	int instance;
-	char filename[ACPI_NAME_SIZE+ACPI_INST_SIZE];
+	char filename[ACPI_NAMESEG_SIZE+ACPI_INST_SIZE];
 	struct list_head node;
 };
 
@@ -368,10 +368,10 @@ static int acpi_table_attr_init(struct kobject *tables_obj,
 	char instance_str[ACPI_INST_SIZE];
 
 	sysfs_attr_init(&table_attr->attr.attr);
-	ACPI_MOVE_NAME(table_attr->name, table_header->signature);
+	ACPI_COPY_NAMESEG(table_attr->name, table_header->signature);
 
 	list_for_each_entry(attr, &acpi_table_attr_list, node) {
-		if (ACPI_COMPARE_NAME(table_attr->name, attr->name))
+		if (ACPI_COMPARE_NAMESEG(table_attr->name, attr->name))
 			if (table_attr->instance < attr->instance)
 				table_attr->instance = attr->instance;
 	}
@@ -382,8 +382,8 @@ static int acpi_table_attr_init(struct kobject *tables_obj,
 		return -ERANGE;
 	}
 
-	ACPI_MOVE_NAME(table_attr->filename, table_header->signature);
-	table_attr->filename[ACPI_NAME_SIZE] = '\0';
+	ACPI_COPY_NAMESEG(table_attr->filename, table_header->signature);
+	table_attr->filename[ACPI_NAMESEG_SIZE] = '\0';
 	if (table_attr->instance > 1 || (table_attr->instance == 1 &&
 					 !acpi_get_table
 					 (table_header->signature, 2, &header))) {
@@ -484,7 +484,7 @@ static int acpi_table_data_init(struct acpi_table_header *th)
 	int i;
 
 	for (i = 0; i < NUM_ACPI_DATA_OBJS; i++) {
-		if (ACPI_COMPARE_NAME(th->signature, acpi_data_objs[i].name)) {
+		if (ACPI_COMPARE_NAMESEG(th->signature, acpi_data_objs[i].name)) {
 			data_attr = kzalloc(sizeof(*data_attr), GFP_KERNEL);
 			if (!data_attr)
 				return -ENOMEM;
diff --git a/drivers/acpi/tables.c b/drivers/acpi/tables.c
index 8fccbe49612a..d7bf936b1646 100644
--- a/drivers/acpi/tables.c
+++ b/drivers/acpi/tables.c
@@ -240,8 +240,7 @@ void acpi_table_print_madt_entry(struct acpi_subtable_header *header)
  * On success returns sum of all matching entries for all proc handlers.
  * Otherwise, -ENODEV or -EINVAL is returned.
  */
-static int __init
-acpi_parse_entries_array(char *id, unsigned long table_size,
+static int __init acpi_parse_entries_array(char *id, unsigned long table_size,
 		struct acpi_table_header *table_header,
 		struct acpi_subtable_proc *proc, int proc_num,
 		unsigned int max_entries)
@@ -314,8 +313,7 @@ acpi_parse_entries_array(char *id, unsigned long table_size,
 	return errs ? -EINVAL : count;
 }
 
-int __init
-acpi_table_parse_entries_array(char *id,
+int __init acpi_table_parse_entries_array(char *id,
 			 unsigned long table_size,
 			 struct acpi_subtable_proc *proc, int proc_num,
 			 unsigned int max_entries)
@@ -346,8 +344,7 @@ acpi_table_parse_entries_array(char *id,
 	return count;
 }
 
-int __init
-acpi_table_parse_entries(char *id,
+int __init acpi_table_parse_entries(char *id,
 			unsigned long table_size,
 			int entry_id,
 			acpi_tbl_entry_handler handler,
@@ -362,8 +359,7 @@ acpi_table_parse_entries(char *id,
 						max_entries);
 }
 
-int __init
-acpi_table_parse_madt(enum acpi_madt_type id,
+int __init acpi_table_parse_madt(enum acpi_madt_type id,
 		      acpi_tbl_entry_handler handler, unsigned int max_entries)
 {
 	return acpi_table_parse_entries(ACPI_SIG_MADT,
@@ -670,8 +666,8 @@ static void __init acpi_table_initrd_scan(void)
 		table_length = table->length;
 
 		/* Skip RSDT/XSDT which should only be used for override */
-		if (ACPI_COMPARE_NAME(table->signature, ACPI_SIG_RSDT) ||
-		    ACPI_COMPARE_NAME(table->signature, ACPI_SIG_XSDT)) {
+		if (ACPI_COMPARE_NAMESEG(table->signature, ACPI_SIG_RSDT) ||
+		    ACPI_COMPARE_NAMESEG(table->signature, ACPI_SIG_XSDT)) {
 			acpi_os_unmap_memory(table, ACPI_HEADER_SIZE);
 			goto next_table;
 		}
@@ -725,8 +721,7 @@ static void *amlcode __attribute__ ((weakref("AmlCode")));
 static void *dsdt_amlcode __attribute__ ((weakref("dsdt_aml_code")));
 #endif
 
-acpi_status
-acpi_os_table_override(struct acpi_table_header *existing_table,
+acpi_status acpi_os_table_override(struct acpi_table_header *existing_table,
 		       struct acpi_table_header **new_table)
 {
 	if (!existing_table || !new_table)
@@ -788,7 +783,6 @@ static int __init acpi_parse_apic_instance(char *str)
 
 	return 0;
 }
-
 early_param("acpi_apic_instance", acpi_parse_apic_instance);
 
 static int __init acpi_force_table_verification_setup(char *s)
@@ -797,7 +791,6 @@ static int __init acpi_force_table_verification_setup(char *s)
 
 	return 0;
 }
-
 early_param("acpi_force_table_verification", acpi_force_table_verification_setup);
 
 static int __init acpi_force_32bit_fadt_addr(char *s)
@@ -807,5 +800,4 @@ static int __init acpi_force_32bit_fadt_addr(char *s)
 
 	return 0;
 }
-
 early_param("acpi_force_32bit_fadt_addr", acpi_force_32bit_fadt_addr);
diff --git a/drivers/acpi/utils.c b/drivers/acpi/utils.c
index c4b06cc075f9..89363b245489 100644
--- a/drivers/acpi/utils.c
+++ b/drivers/acpi/utils.c
@@ -739,6 +739,7 @@ EXPORT_SYMBOL(acpi_dev_found);
 
 struct acpi_dev_match_info {
 	const char *dev_name;
+	struct acpi_device *adev;
 	struct acpi_device_id hid[2];
 	const char *uid;
 	s64 hrv;
@@ -759,6 +760,7 @@ static int acpi_dev_match_cb(struct device *dev, void *data)
 		return 0;
 
 	match->dev_name = acpi_dev_name(adev);
+	match->adev = adev;
 
 	if (match->hrv == -1)
 		return 1;
@@ -806,18 +808,20 @@ bool acpi_dev_present(const char *hid, const char *uid, s64 hrv)
 EXPORT_SYMBOL(acpi_dev_present);
 
 /**
- * acpi_dev_get_first_match_name - Return name of first match of ACPI device
+ * acpi_dev_get_first_match_dev - Return the first match of ACPI device
  * @hid: Hardware ID of the device.
  * @uid: Unique ID of the device, pass NULL to not check _UID
  * @hrv: Hardware Revision of the device, pass -1 to not check _HRV
  *
- * Return device name if a matching device was present
+ * Return the first match of ACPI device if a matching device was present
  * at the moment of invocation, or NULL otherwise.
  *
+ * The caller is responsible to call put_device() on the returned device.
+ *
  * See additional information in acpi_dev_present() as well.
  */
-const char *
-acpi_dev_get_first_match_name(const char *hid, const char *uid, s64 hrv)
+struct acpi_device *
+acpi_dev_get_first_match_dev(const char *hid, const char *uid, s64 hrv)
 {
 	struct acpi_dev_match_info match = {};
 	struct device *dev;
@@ -827,9 +831,9 @@ acpi_dev_get_first_match_name(const char *hid, const char *uid, s64 hrv)
 	match.hrv = hrv;
 
 	dev = bus_find_device(&acpi_bus_type, NULL, &match, acpi_dev_match_cb);
-	return dev ? match.dev_name : NULL;
+	return dev ? match.adev : NULL;
 }
-EXPORT_SYMBOL(acpi_dev_get_first_match_name);
+EXPORT_SYMBOL(acpi_dev_get_first_match_dev);
 
 /*
  * acpi_backlight= handling, this is done here rather then in video_detect.c
diff --git a/drivers/acpi/video_detect.c b/drivers/acpi/video_detect.c
index 43587ac680e4..31014c7d3793 100644
--- a/drivers/acpi/video_detect.c
+++ b/drivers/acpi/video_detect.c
@@ -112,7 +112,7 @@ static int video_detect_force_none(const struct dmi_system_id *d)
 static const struct dmi_system_id video_detect_dmi_table[] = {
 	/* On Samsung X360, the BIOS will set a flag (VDRV) if generic
 	 * ACPI backlight device is used. This flag will definitively break
-	 * the backlight interface (even the vendor interface) untill next
+	 * the backlight interface (even the vendor interface) until next
 	 * reboot. It's why we should prevent video.ko from being used here
 	 * and we can't rely on a later call to acpi_video_unregister().
 	 */
@@ -141,6 +141,14 @@ static const struct dmi_system_id video_detect_dmi_table[] = {
 		DMI_MATCH(DMI_PRODUCT_NAME, "UL30A"),
 		},
 	},
+	{
+	.callback = video_detect_force_vendor,
+	.ident = "Sony VPCEH3U1E",
+	.matches = {
+		DMI_MATCH(DMI_SYS_VENDOR, "Sony Corporation"),
+		DMI_MATCH(DMI_PRODUCT_NAME, "VPCEH3U1E"),
+		},
+	},
 
 	/*
 	 * These models have a working acpi_video backlight control, and using
diff --git a/drivers/android/binder.c b/drivers/android/binder.c
index 8685882da64c..4b9c7ca492e6 100644
--- a/drivers/android/binder.c
+++ b/drivers/android/binder.c
@@ -2057,7 +2057,8 @@ static size_t binder_get_object(struct binder_proc *proc,
 	size_t object_size = 0;
 
 	read_size = min_t(size_t, sizeof(*object), buffer->data_size - offset);
-	if (read_size < sizeof(*hdr) || !IS_ALIGNED(offset, sizeof(u32)))
+	if (offset > buffer->data_size || read_size < sizeof(*hdr) ||
+	    !IS_ALIGNED(offset, sizeof(u32)))
 		return 0;
 	binder_alloc_copy_from_buffer(&proc->alloc, object, buffer,
 				      offset, read_size);
diff --git a/drivers/android/binder_alloc.c b/drivers/android/binder_alloc.c
index 6389467670a0..195f120c4e8c 100644
--- a/drivers/android/binder_alloc.c
+++ b/drivers/android/binder_alloc.c
@@ -927,14 +927,13 @@ enum lru_status binder_alloc_free_page(struct list_head *item,
 
 	index = page - alloc->pages;
 	page_addr = (uintptr_t)alloc->buffer + index * PAGE_SIZE;
+
+	mm = alloc->vma_vm_mm;
+	if (!mmget_not_zero(mm))
+		goto err_mmget;
+	if (!down_write_trylock(&mm->mmap_sem))
+		goto err_down_write_mmap_sem_failed;
 	vma = binder_alloc_get_vma(alloc);
-	if (vma) {
-		if (!mmget_not_zero(alloc->vma_vm_mm))
-			goto err_mmget;
-		mm = alloc->vma_vm_mm;
-		if (!down_read_trylock(&mm->mmap_sem))
-			goto err_down_write_mmap_sem_failed;
-	}
 
 	list_lru_isolate(lru, item);
 	spin_unlock(lock);
@@ -945,10 +944,9 @@ enum lru_status binder_alloc_free_page(struct list_head *item,
 		zap_page_range(vma, page_addr, PAGE_SIZE);
 
 		trace_binder_unmap_user_end(alloc, index);
-
-		up_read(&mm->mmap_sem);
-		mmput(mm);
 	}
+	up_write(&mm->mmap_sem);
+	mmput(mm);
 
 	trace_binder_unmap_kernel_start(alloc, index);
 
diff --git a/drivers/ata/libata-zpodd.c b/drivers/ata/libata-zpodd.c
index b3ed8f9953a8..173e6f2dd9af 100644
--- a/drivers/ata/libata-zpodd.c
+++ b/drivers/ata/libata-zpodd.c
@@ -52,38 +52,52 @@ static int eject_tray(struct ata_device *dev)
 /* Per the spec, only slot type and drawer type ODD can be supported */
 static enum odd_mech_type zpodd_get_mech_type(struct ata_device *dev)
 {
-	char buf[16];
+	char *buf;
 	unsigned int ret;
-	struct rm_feature_desc *desc = (void *)(buf + 8);
+	struct rm_feature_desc *desc;
 	struct ata_taskfile tf;
 	static const char cdb[] = {  GPCMD_GET_CONFIGURATION,
 			2,      /* only 1 feature descriptor requested */
 			0, 3,   /* 3, removable medium feature */
 			0, 0, 0,/* reserved */
-			0, sizeof(buf),
+			0, 16,
 			0, 0, 0,
 	};
 
+	buf = kzalloc(16, GFP_KERNEL);
+	if (!buf)
+		return ODD_MECH_TYPE_UNSUPPORTED;
+	desc = (void *)(buf + 8);
+
 	ata_tf_init(dev, &tf);
 	tf.flags = ATA_TFLAG_ISADDR | ATA_TFLAG_DEVICE;
 	tf.command = ATA_CMD_PACKET;
 	tf.protocol = ATAPI_PROT_PIO;
-	tf.lbam = sizeof(buf);
+	tf.lbam = 16;
 
 	ret = ata_exec_internal(dev, &tf, cdb, DMA_FROM_DEVICE,
-				buf, sizeof(buf), 0);
-	if (ret)
+				buf, 16, 0);
+	if (ret) {
+		kfree(buf);
 		return ODD_MECH_TYPE_UNSUPPORTED;
+	}
 
-	if (be16_to_cpu(desc->feature_code) != 3)
+	if (be16_to_cpu(desc->feature_code) != 3) {
+		kfree(buf);
 		return ODD_MECH_TYPE_UNSUPPORTED;
+	}
 
-	if (desc->mech_type == 0 && desc->load == 0 && desc->eject == 1)
+	if (desc->mech_type == 0 && desc->load == 0 && desc->eject == 1) {
+		kfree(buf);
 		return ODD_MECH_TYPE_SLOT;
-	else if (desc->mech_type == 1 && desc->load == 0 && desc->eject == 1)
+	} else if (desc->mech_type == 1 && desc->load == 0 &&
+		   desc->eject == 1) {
+		kfree(buf);
 		return ODD_MECH_TYPE_DRAWER;
-	else
+	} else {
+		kfree(buf);
 		return ODD_MECH_TYPE_UNSUPPORTED;
+	}
 }
 
 /* Test if ODD is zero power ready by sense code */
diff --git a/drivers/atm/firestream.c b/drivers/atm/firestream.c
index 11e1663bdc4d..b2c06da4f62e 100644
--- a/drivers/atm/firestream.c
+++ b/drivers/atm/firestream.c
@@ -1646,7 +1646,7 @@ static irqreturn_t fs_irq (int irq, void *dev_id)
 	}
 
 	if (status & ISR_TBRQ_W) {
-		fs_dprintk (FS_DEBUG_IRQ, "Data tramsitted!\n");
+		fs_dprintk (FS_DEBUG_IRQ, "Data transmitted!\n");
 		process_txdone_queue (dev, &dev->tx_relq);
 	}
 
diff --git a/drivers/base/memory.c b/drivers/base/memory.c
index cb8347500ce2..e49028a60429 100644
--- a/drivers/base/memory.c
+++ b/drivers/base/memory.c
@@ -506,7 +506,7 @@ static ssize_t probe_store(struct device *dev, struct device_attribute *attr,
 
 	ret = lock_device_hotplug_sysfs();
 	if (ret)
-		goto out;
+		return ret;
 
 	nid = memory_add_physaddr_to_nid(phys_addr);
 	ret = __add_memory(nid, phys_addr,
diff --git a/drivers/base/power/domain.c b/drivers/base/power/domain.c
index 96a6dc9d305c..3d899e8abd58 100644
--- a/drivers/base/power/domain.c
+++ b/drivers/base/power/domain.c
@@ -22,6 +22,7 @@
 #include <linux/sched.h>
 #include <linux/suspend.h>
 #include <linux/export.h>
+#include <linux/cpu.h>
 
 #include "power.h"
 
@@ -128,6 +129,7 @@ static const struct genpd_lock_ops genpd_spin_ops = {
 #define genpd_is_irq_safe(genpd)	(genpd->flags & GENPD_FLAG_IRQ_SAFE)
 #define genpd_is_always_on(genpd)	(genpd->flags & GENPD_FLAG_ALWAYS_ON)
 #define genpd_is_active_wakeup(genpd)	(genpd->flags & GENPD_FLAG_ACTIVE_WAKEUP)
+#define genpd_is_cpu_domain(genpd)	(genpd->flags & GENPD_FLAG_CPU_DOMAIN)
 
 static inline bool irq_safe_dev_in_no_sleep_domain(struct device *dev,
 		const struct generic_pm_domain *genpd)
@@ -391,11 +393,9 @@ int dev_pm_genpd_set_performance_state(struct device *dev, unsigned int state)
 	if (unlikely(!genpd->set_performance_state))
 		return -EINVAL;
 
-	if (unlikely(!dev->power.subsys_data ||
-		     !dev->power.subsys_data->domain_data)) {
-		WARN_ON(1);
+	if (WARN_ON(!dev->power.subsys_data ||
+		     !dev->power.subsys_data->domain_data))
 		return -EINVAL;
-	}
 
 	genpd_lock(genpd);
 
@@ -1396,8 +1396,7 @@ EXPORT_SYMBOL_GPL(pm_genpd_syscore_poweron);
 
 #endif /* CONFIG_PM_SLEEP */
 
-static struct generic_pm_domain_data *genpd_alloc_dev_data(struct device *dev,
-					struct gpd_timing_data *td)
+static struct generic_pm_domain_data *genpd_alloc_dev_data(struct device *dev)
 {
 	struct generic_pm_domain_data *gpd_data;
 	int ret;
@@ -1412,9 +1411,6 @@ static struct generic_pm_domain_data *genpd_alloc_dev_data(struct device *dev,
 		goto err_put;
 	}
 
-	if (td)
-		gpd_data->td = *td;
-
 	gpd_data->base.dev = dev;
 	gpd_data->td.constraint_changed = true;
 	gpd_data->td.effective_constraint_ns = PM_QOS_RESUME_LATENCY_NO_CONSTRAINT_NS;
@@ -1454,8 +1450,57 @@ static void genpd_free_dev_data(struct device *dev,
 	dev_pm_put_subsys_data(dev);
 }
 
+static void genpd_update_cpumask(struct generic_pm_domain *genpd,
+				 int cpu, bool set, unsigned int depth)
+{
+	struct gpd_link *link;
+
+	if (!genpd_is_cpu_domain(genpd))
+		return;
+
+	list_for_each_entry(link, &genpd->slave_links, slave_node) {
+		struct generic_pm_domain *master = link->master;
+
+		genpd_lock_nested(master, depth + 1);
+		genpd_update_cpumask(master, cpu, set, depth + 1);
+		genpd_unlock(master);
+	}
+
+	if (set)
+		cpumask_set_cpu(cpu, genpd->cpus);
+	else
+		cpumask_clear_cpu(cpu, genpd->cpus);
+}
+
+static void genpd_set_cpumask(struct generic_pm_domain *genpd, int cpu)
+{
+	if (cpu >= 0)
+		genpd_update_cpumask(genpd, cpu, true, 0);
+}
+
+static void genpd_clear_cpumask(struct generic_pm_domain *genpd, int cpu)
+{
+	if (cpu >= 0)
+		genpd_update_cpumask(genpd, cpu, false, 0);
+}
+
+static int genpd_get_cpu(struct generic_pm_domain *genpd, struct device *dev)
+{
+	int cpu;
+
+	if (!genpd_is_cpu_domain(genpd))
+		return -1;
+
+	for_each_possible_cpu(cpu) {
+		if (get_cpu_device(cpu) == dev)
+			return cpu;
+	}
+
+	return -1;
+}
+
 static int genpd_add_device(struct generic_pm_domain *genpd, struct device *dev,
-			    struct gpd_timing_data *td)
+			    struct device *base_dev)
 {
 	struct generic_pm_domain_data *gpd_data;
 	int ret;
@@ -1465,16 +1510,19 @@ static int genpd_add_device(struct generic_pm_domain *genpd, struct device *dev,
 	if (IS_ERR_OR_NULL(genpd) || IS_ERR_OR_NULL(dev))
 		return -EINVAL;
 
-	gpd_data = genpd_alloc_dev_data(dev, td);
+	gpd_data = genpd_alloc_dev_data(dev);
 	if (IS_ERR(gpd_data))
 		return PTR_ERR(gpd_data);
 
+	gpd_data->cpu = genpd_get_cpu(genpd, base_dev);
+
 	ret = genpd->attach_dev ? genpd->attach_dev(genpd, dev) : 0;
 	if (ret)
 		goto out;
 
 	genpd_lock(genpd);
 
+	genpd_set_cpumask(genpd, gpd_data->cpu);
 	dev_pm_domain_set(dev, &genpd->domain);
 
 	genpd->device_count++;
@@ -1502,7 +1550,7 @@ int pm_genpd_add_device(struct generic_pm_domain *genpd, struct device *dev)
 	int ret;
 
 	mutex_lock(&gpd_list_lock);
-	ret = genpd_add_device(genpd, dev, NULL);
+	ret = genpd_add_device(genpd, dev, dev);
 	mutex_unlock(&gpd_list_lock);
 
 	return ret;
@@ -1532,6 +1580,7 @@ static int genpd_remove_device(struct generic_pm_domain *genpd,
 	genpd->device_count--;
 	genpd->max_off_time_changed = true;
 
+	genpd_clear_cpumask(genpd, gpd_data->cpu);
 	dev_pm_domain_set(dev, NULL);
 
 	list_del_init(&pdd->list_node);
@@ -1686,6 +1735,12 @@ out:
 }
 EXPORT_SYMBOL_GPL(pm_genpd_remove_subdomain);
 
+static void genpd_free_default_power_state(struct genpd_power_state *states,
+					   unsigned int state_count)
+{
+	kfree(states);
+}
+
 static int genpd_set_default_power_state(struct generic_pm_domain *genpd)
 {
 	struct genpd_power_state *state;
@@ -1696,7 +1751,7 @@ static int genpd_set_default_power_state(struct generic_pm_domain *genpd)
 
 	genpd->states = state;
 	genpd->state_count = 1;
-	genpd->free = state;
+	genpd->free_states = genpd_free_default_power_state;
 
 	return 0;
 }
@@ -1762,11 +1817,18 @@ int pm_genpd_init(struct generic_pm_domain *genpd,
 	if (genpd_is_always_on(genpd) && !genpd_status_on(genpd))
 		return -EINVAL;
 
+	if (genpd_is_cpu_domain(genpd) &&
+	    !zalloc_cpumask_var(&genpd->cpus, GFP_KERNEL))
+		return -ENOMEM;
+
 	/* Use only one "off" state if there were no states declared */
 	if (genpd->state_count == 0) {
 		ret = genpd_set_default_power_state(genpd);
-		if (ret)
+		if (ret) {
+			if (genpd_is_cpu_domain(genpd))
+				free_cpumask_var(genpd->cpus);
 			return ret;
+		}
 	} else if (!gov && genpd->state_count > 1) {
 		pr_warn("%s: no governor for states\n", genpd->name);
 	}
@@ -1812,7 +1874,11 @@ static int genpd_remove(struct generic_pm_domain *genpd)
 	list_del(&genpd->gpd_list_node);
 	genpd_unlock(genpd);
 	cancel_work_sync(&genpd->power_off_work);
-	kfree(genpd->free);
+	if (genpd_is_cpu_domain(genpd))
+		free_cpumask_var(genpd->cpus);
+	if (genpd->free_states)
+		genpd->free_states(genpd->states, genpd->state_count);
+
 	pr_debug("%s: removed %s\n", __func__, genpd->name);
 
 	return 0;
@@ -2190,7 +2256,7 @@ int of_genpd_add_device(struct of_phandle_args *genpdspec, struct device *dev)
 		goto out;
 	}
 
-	ret = genpd_add_device(genpd, dev, NULL);
+	ret = genpd_add_device(genpd, dev, dev);
 
 out:
 	mutex_unlock(&gpd_list_lock);
@@ -2274,6 +2340,7 @@ EXPORT_SYMBOL_GPL(of_genpd_remove_last);
 
 static void genpd_release_dev(struct device *dev)
 {
+	of_node_put(dev->of_node);
 	kfree(dev);
 }
 
@@ -2335,14 +2402,14 @@ static void genpd_dev_pm_sync(struct device *dev)
 	genpd_queue_power_off_work(pd);
 }
 
-static int __genpd_dev_pm_attach(struct device *dev, struct device_node *np,
+static int __genpd_dev_pm_attach(struct device *dev, struct device *base_dev,
 				 unsigned int index, bool power_on)
 {
 	struct of_phandle_args pd_args;
 	struct generic_pm_domain *pd;
 	int ret;
 
-	ret = of_parse_phandle_with_args(np, "power-domains",
+	ret = of_parse_phandle_with_args(dev->of_node, "power-domains",
 				"#power-domain-cells", index, &pd_args);
 	if (ret < 0)
 		return ret;
@@ -2354,12 +2421,12 @@ static int __genpd_dev_pm_attach(struct device *dev, struct device_node *np,
 		mutex_unlock(&gpd_list_lock);
 		dev_dbg(dev, "%s() failed to find PM domain: %ld\n",
 			__func__, PTR_ERR(pd));
-		return driver_deferred_probe_check_state(dev);
+		return driver_deferred_probe_check_state(base_dev);
 	}
 
 	dev_dbg(dev, "adding to PM domain %s\n", pd->name);
 
-	ret = genpd_add_device(pd, dev, NULL);
+	ret = genpd_add_device(pd, dev, base_dev);
 	mutex_unlock(&gpd_list_lock);
 
 	if (ret < 0) {
@@ -2410,7 +2477,7 @@ int genpd_dev_pm_attach(struct device *dev)
 				       "#power-domain-cells") != 1)
 		return 0;
 
-	return __genpd_dev_pm_attach(dev, dev->of_node, 0, true);
+	return __genpd_dev_pm_attach(dev, dev, 0, true);
 }
 EXPORT_SYMBOL_GPL(genpd_dev_pm_attach);
 
@@ -2440,10 +2507,10 @@ struct device *genpd_dev_pm_attach_by_id(struct device *dev,
 	if (!dev->of_node)
 		return NULL;
 
-	/* Deal only with devices using multiple PM domains. */
+	/* Verify that the index is within a valid range. */
 	num_domains = of_count_phandle_with_args(dev->of_node, "power-domains",
 						 "#power-domain-cells");
-	if (num_domains < 2 || index >= num_domains)
+	if (index >= num_domains)
 		return NULL;
 
 	/* Allocate and register device on the genpd bus. */
@@ -2454,15 +2521,16 @@ struct device *genpd_dev_pm_attach_by_id(struct device *dev,
 	dev_set_name(virt_dev, "genpd:%u:%s", index, dev_name(dev));
 	virt_dev->bus = &genpd_bus_type;
 	virt_dev->release = genpd_release_dev;
+	virt_dev->of_node = of_node_get(dev->of_node);
 
 	ret = device_register(virt_dev);
 	if (ret) {
-		kfree(virt_dev);
+		put_device(virt_dev);
 		return ERR_PTR(ret);
 	}
 
 	/* Try to attach the device to the PM domain at the specified index. */
-	ret = __genpd_dev_pm_attach(virt_dev, dev->of_node, index, false);
+	ret = __genpd_dev_pm_attach(virt_dev, dev, index, false);
 	if (ret < 1) {
 		device_unregister(virt_dev);
 		return ret ? ERR_PTR(ret) : NULL;
diff --git a/drivers/base/power/domain_governor.c b/drivers/base/power/domain_governor.c
index 4d07e38a8247..7912bc957244 100644
--- a/drivers/base/power/domain_governor.c
+++ b/drivers/base/power/domain_governor.c
@@ -10,6 +10,9 @@
 #include <linux/pm_domain.h>
 #include <linux/pm_qos.h>
 #include <linux/hrtimer.h>
+#include <linux/cpuidle.h>
+#include <linux/cpumask.h>
+#include <linux/ktime.h>
 
 static int dev_update_qos_constraint(struct device *dev, void *data)
 {
@@ -210,8 +213,10 @@ static bool default_power_down_ok(struct dev_pm_domain *pd)
 	struct generic_pm_domain *genpd = pd_to_genpd(pd);
 	struct gpd_link *link;
 
-	if (!genpd->max_off_time_changed)
+	if (!genpd->max_off_time_changed) {
+		genpd->state_idx = genpd->cached_power_down_state_idx;
 		return genpd->cached_power_down_ok;
+	}
 
 	/*
 	 * We have to invalidate the cached results for the masters, so
@@ -236,6 +241,7 @@ static bool default_power_down_ok(struct dev_pm_domain *pd)
 		genpd->state_idx--;
 	}
 
+	genpd->cached_power_down_state_idx = genpd->state_idx;
 	return genpd->cached_power_down_ok;
 }
 
@@ -244,6 +250,65 @@ static bool always_on_power_down_ok(struct dev_pm_domain *domain)
 	return false;
 }
 
+#ifdef CONFIG_CPU_IDLE
+static bool cpu_power_down_ok(struct dev_pm_domain *pd)
+{
+	struct generic_pm_domain *genpd = pd_to_genpd(pd);
+	struct cpuidle_device *dev;
+	ktime_t domain_wakeup, next_hrtimer;
+	s64 idle_duration_ns;
+	int cpu, i;
+
+	/* Validate dev PM QoS constraints. */
+	if (!default_power_down_ok(pd))
+		return false;
+
+	if (!(genpd->flags & GENPD_FLAG_CPU_DOMAIN))
+		return true;
+
+	/*
+	 * Find the next wakeup for any of the online CPUs within the PM domain
+	 * and its subdomains. Note, we only need the genpd->cpus, as it already
+	 * contains a mask of all CPUs from subdomains.
+	 */
+	domain_wakeup = ktime_set(KTIME_SEC_MAX, 0);
+	for_each_cpu_and(cpu, genpd->cpus, cpu_online_mask) {
+		dev = per_cpu(cpuidle_devices, cpu);
+		if (dev) {
+			next_hrtimer = READ_ONCE(dev->next_hrtimer);
+			if (ktime_before(next_hrtimer, domain_wakeup))
+				domain_wakeup = next_hrtimer;
+		}
+	}
+
+	/* The minimum idle duration is from now - until the next wakeup. */
+	idle_duration_ns = ktime_to_ns(ktime_sub(domain_wakeup, ktime_get()));
+	if (idle_duration_ns <= 0)
+		return false;
+
+	/*
+	 * Find the deepest idle state that has its residency value satisfied
+	 * and by also taking into account the power off latency for the state.
+	 * Start at the state picked by the dev PM QoS constraint validation.
+	 */
+	i = genpd->state_idx;
+	do {
+		if (idle_duration_ns >= (genpd->states[i].residency_ns +
+		    genpd->states[i].power_off_latency_ns)) {
+			genpd->state_idx = i;
+			return true;
+		}
+	} while (--i >= 0);
+
+	return false;
+}
+
+struct dev_power_governor pm_domain_cpu_gov = {
+	.suspend_ok = default_suspend_ok,
+	.power_down_ok = cpu_power_down_ok,
+};
+#endif
+
 struct dev_power_governor simple_qos_governor = {
 	.suspend_ok = default_suspend_ok,
 	.power_down_ok = default_power_down_ok,
diff --git a/drivers/base/power/main.c b/drivers/base/power/main.c
index f80d298de3fa..43e863cc0c1b 100644
--- a/drivers/base/power/main.c
+++ b/drivers/base/power/main.c
@@ -478,7 +478,7 @@ struct dpm_watchdog {
 
 /**
  * dpm_watchdog_handler - Driver suspend / resume watchdog handler.
- * @data: Watchdog object address.
+ * @t: The timer that PM watchdog depends on.
  *
  * Called when a driver has timed out suspending or resuming.
  * There's not much we can do here to recover so panic() to
@@ -706,6 +706,19 @@ static bool is_async(struct device *dev)
 		&& !pm_trace_is_enabled();
 }
 
+static bool dpm_async_fn(struct device *dev, async_func_t func)
+{
+	reinit_completion(&dev->power.completion);
+
+	if (is_async(dev)) {
+		get_device(dev);
+		async_schedule(func, dev);
+		return true;
+	}
+
+	return false;
+}
+
 static void async_resume_noirq(void *data, async_cookie_t cookie)
 {
 	struct device *dev = (struct device *)data;
@@ -732,13 +745,8 @@ void dpm_noirq_resume_devices(pm_message_t state)
 	 * in case the starting of async threads is
 	 * delayed by non-async resuming devices.
 	 */
-	list_for_each_entry(dev, &dpm_noirq_list, power.entry) {
-		reinit_completion(&dev->power.completion);
-		if (is_async(dev)) {
-			get_device(dev);
-			async_schedule_dev(async_resume_noirq, dev);
-		}
-	}
+	list_for_each_entry(dev, &dpm_noirq_list, power.entry)
+		dpm_async_fn(dev, async_resume_noirq);
 
 	while (!list_empty(&dpm_noirq_list)) {
 		dev = to_device(dpm_noirq_list.next);
@@ -889,13 +897,8 @@ void dpm_resume_early(pm_message_t state)
 	 * in case the starting of async threads is
 	 * delayed by non-async resuming devices.
 	 */
-	list_for_each_entry(dev, &dpm_late_early_list, power.entry) {
-		reinit_completion(&dev->power.completion);
-		if (is_async(dev)) {
-			get_device(dev);
-			async_schedule_dev(async_resume_early, dev);
-		}
-	}
+	list_for_each_entry(dev, &dpm_late_early_list, power.entry)
+		dpm_async_fn(dev, async_resume_early);
 
 	while (!list_empty(&dpm_late_early_list)) {
 		dev = to_device(dpm_late_early_list.next);
@@ -1053,13 +1056,8 @@ void dpm_resume(pm_message_t state)
 	pm_transition = state;
 	async_error = 0;
 
-	list_for_each_entry(dev, &dpm_suspended_list, power.entry) {
-		reinit_completion(&dev->power.completion);
-		if (is_async(dev)) {
-			get_device(dev);
-			async_schedule_dev(async_resume, dev);
-		}
-	}
+	list_for_each_entry(dev, &dpm_suspended_list, power.entry)
+		dpm_async_fn(dev, async_resume);
 
 	while (!list_empty(&dpm_suspended_list)) {
 		dev = to_device(dpm_suspended_list.next);
@@ -1373,13 +1371,9 @@ static void async_suspend_noirq(void *data, async_cookie_t cookie)
 
 static int device_suspend_noirq(struct device *dev)
 {
-	reinit_completion(&dev->power.completion);
-
-	if (is_async(dev)) {
-		get_device(dev);
-		async_schedule_dev(async_suspend_noirq, dev);
+	if (dpm_async_fn(dev, async_suspend_noirq))
 		return 0;
-	}
+
 	return __device_suspend_noirq(dev, pm_transition, false);
 }
 
@@ -1576,13 +1570,8 @@ static void async_suspend_late(void *data, async_cookie_t cookie)
 
 static int device_suspend_late(struct device *dev)
 {
-	reinit_completion(&dev->power.completion);
-
-	if (is_async(dev)) {
-		get_device(dev);
-		async_schedule_dev(async_suspend_late, dev);
+	if (dpm_async_fn(dev, async_suspend_late))
 		return 0;
-	}
 
 	return __device_suspend_late(dev, pm_transition, false);
 }
@@ -1747,6 +1736,10 @@ static int __device_suspend(struct device *dev, pm_message_t state, bool async)
 	if (dev->power.syscore)
 		goto Complete;
 
+	/* Avoid direct_complete to let wakeup_path propagate. */
+	if (device_may_wakeup(dev) || dev->power.wakeup_path)
+		dev->power.direct_complete = false;
+
 	if (dev->power.direct_complete) {
 		if (pm_runtime_status_suspended(dev)) {
 			pm_runtime_disable(dev);
@@ -1842,13 +1835,8 @@ static void async_suspend(void *data, async_cookie_t cookie)
 
 static int device_suspend(struct device *dev)
 {
-	reinit_completion(&dev->power.completion);
-
-	if (is_async(dev)) {
-		get_device(dev);
-		async_schedule_dev(async_suspend, dev);
+	if (dpm_async_fn(dev, async_suspend))
 		return 0;
-	}
 
 	return __device_suspend(dev, pm_transition, false);
 }
@@ -2069,8 +2057,8 @@ EXPORT_SYMBOL_GPL(__suspend_report_result);
 
 /**
  * device_pm_wait_for_dev - Wait for suspend/resume of a device to complete.
- * @dev: Device to wait for.
  * @subordinate: Device that needs to wait for @dev.
+ * @dev: Device to wait for.
  */
 int device_pm_wait_for_dev(struct device *subordinate, struct device *dev)
 {
diff --git a/drivers/base/power/wakeup.c b/drivers/base/power/wakeup.c
index bb1ae175fae1..23c243a4c675 100644
--- a/drivers/base/power/wakeup.c
+++ b/drivers/base/power/wakeup.c
@@ -804,7 +804,7 @@ void pm_print_active_wakeup_sources(void)
 	srcuidx = srcu_read_lock(&wakeup_srcu);
 	list_for_each_entry_rcu(ws, &wakeup_sources, entry) {
 		if (ws->active) {
-			pr_debug("active wakeup source: %s\n", ws->name);
+			pm_pr_dbg("active wakeup source: %s\n", ws->name);
 			active = 1;
 		} else if (!active &&
 			   (!last_activity_ws ||
@@ -815,7 +815,7 @@ void pm_print_active_wakeup_sources(void)
 	}
 
 	if (!active && last_activity_ws)
-		pr_debug("last active wakeup source: %s\n",
+		pm_pr_dbg("last active wakeup source: %s\n",
 			last_activity_ws->name);
 	srcu_read_unlock(&wakeup_srcu, srcuidx);
 }
@@ -845,7 +845,7 @@ bool pm_wakeup_pending(void)
 	raw_spin_unlock_irqrestore(&events_lock, flags);
 
 	if (ret) {
-		pr_debug("Wakeup pending, aborting suspend\n");
+		pm_pr_dbg("Wakeup pending, aborting suspend\n");
 		pm_print_active_wakeup_sources();
 	}
 
diff --git a/drivers/base/property.c b/drivers/base/property.c
index 8b91ab380d14..348b37e64944 100644
--- a/drivers/base/property.c
+++ b/drivers/base/property.c
@@ -984,6 +984,81 @@ fwnode_graph_get_remote_node(const struct fwnode_handle *fwnode, u32 port_id,
 EXPORT_SYMBOL_GPL(fwnode_graph_get_remote_node);
 
 /**
+ * fwnode_graph_get_endpoint_by_id - get endpoint by port and endpoint numbers
+ * @fwnode: parent fwnode_handle containing the graph
+ * @port: identifier of the port node
+ * @endpoint: identifier of the endpoint node under the port node
+ * @flags: fwnode lookup flags
+ *
+ * Return the fwnode handle of the local endpoint corresponding the port and
+ * endpoint IDs or NULL if not found.
+ *
+ * If FWNODE_GRAPH_ENDPOINT_NEXT is passed in @flags and the specified endpoint
+ * has not been found, look for the closest endpoint ID greater than the
+ * specified one and return the endpoint that corresponds to it, if present.
+ *
+ * Do not return endpoints that belong to disabled devices, unless
+ * FWNODE_GRAPH_DEVICE_DISABLED is passed in @flags.
+ *
+ * The returned endpoint needs to be released by calling fwnode_handle_put() on
+ * it when it is not needed any more.
+ */
+struct fwnode_handle *
+fwnode_graph_get_endpoint_by_id(const struct fwnode_handle *fwnode,
+				u32 port, u32 endpoint, unsigned long flags)
+{
+	struct fwnode_handle *ep = NULL, *best_ep = NULL;
+	unsigned int best_ep_id = 0;
+	bool endpoint_next = flags & FWNODE_GRAPH_ENDPOINT_NEXT;
+	bool enabled_only = !(flags & FWNODE_GRAPH_DEVICE_DISABLED);
+
+	while ((ep = fwnode_graph_get_next_endpoint(fwnode, ep))) {
+		struct fwnode_endpoint fwnode_ep = { 0 };
+		int ret;
+
+		if (enabled_only) {
+			struct fwnode_handle *dev_node;
+			bool available;
+
+			dev_node = fwnode_graph_get_remote_port_parent(ep);
+			available = fwnode_device_is_available(dev_node);
+			fwnode_handle_put(dev_node);
+			if (!available)
+				continue;
+		}
+
+		ret = fwnode_graph_parse_endpoint(ep, &fwnode_ep);
+		if (ret < 0)
+			continue;
+
+		if (fwnode_ep.port != port)
+			continue;
+
+		if (fwnode_ep.id == endpoint)
+			return ep;
+
+		if (!endpoint_next)
+			continue;
+
+		/*
+		 * If the endpoint that has just been found is not the first
+		 * matching one and the ID of the one found previously is closer
+		 * to the requested endpoint ID, skip it.
+		 */
+		if (fwnode_ep.id < endpoint ||
+		    (best_ep && best_ep_id < fwnode_ep.id))
+			continue;
+
+		fwnode_handle_put(best_ep);
+		best_ep = fwnode_handle_get(ep);
+		best_ep_id = fwnode_ep.id;
+	}
+
+	return best_ep;
+}
+EXPORT_SYMBOL_GPL(fwnode_graph_get_endpoint_by_id);
+
+/**
  * fwnode_graph_parse_endpoint - parse common endpoint node properties
  * @fwnode: pointer to endpoint fwnode_handle
  * @endpoint: pointer to the fwnode endpoint data structure
diff --git a/drivers/base/regmap/internal.h b/drivers/base/regmap/internal.h
index a98fced9bff8..3d80c4b43f72 100644
--- a/drivers/base/regmap/internal.h
+++ b/drivers/base/regmap/internal.h
@@ -1,13 +1,10 @@
+/* SPDX-License-Identifier: GPL-2.0 */
 /*
  * Register map access API internal header
  *
  * Copyright 2011 Wolfson Microelectronics plc
  *
  * Author: Mark Brown <broonie@opensource.wolfsonmicro.com>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
  */
 
 #ifndef _REGMAP_INTERNAL_H
diff --git a/drivers/base/regmap/regcache-flat.c b/drivers/base/regmap/regcache-flat.c
index bc6cd88b8cc6..b7e4b2464102 100644
--- a/drivers/base/regmap/regcache-flat.c
+++ b/drivers/base/regmap/regcache-flat.c
@@ -1,14 +1,10 @@
-/*
- * Register cache access API - flat caching support
- *
- * Copyright 2012 Wolfson Microelectronics plc
- *
- * Author: Mark Brown <broonie@opensource.wolfsonmicro.com>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- */
+// SPDX-License-Identifier: GPL-2.0
+//
+// Register cache access API - flat caching support
+//
+// Copyright 2012 Wolfson Microelectronics plc
+//
+// Author: Mark Brown <broonie@opensource.wolfsonmicro.com>
 
 #include <linux/device.h>
 #include <linux/seq_file.h>
diff --git a/drivers/base/regmap/regcache-lzo.c b/drivers/base/regmap/regcache-lzo.c
index 4ff311374c4a..fc14e8b9344f 100644
--- a/drivers/base/regmap/regcache-lzo.c
+++ b/drivers/base/regmap/regcache-lzo.c
@@ -1,14 +1,10 @@
-/*
- * Register cache access API - LZO caching support
- *
- * Copyright 2011 Wolfson Microelectronics plc
- *
- * Author: Dimitris Papastamos <dp@opensource.wolfsonmicro.com>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- */
+// SPDX-License-Identifier: GPL-2.0
+//
+// Register cache access API - LZO caching support
+//
+// Copyright 2011 Wolfson Microelectronics plc
+//
+// Author: Dimitris Papastamos <dp@opensource.wolfsonmicro.com>
 
 #include <linux/device.h>
 #include <linux/lzo.h>
diff --git a/drivers/base/regmap/regcache-rbtree.c b/drivers/base/regmap/regcache-rbtree.c
index 9cbb4b0cd01b..cfa29dc89bbf 100644
--- a/drivers/base/regmap/regcache-rbtree.c
+++ b/drivers/base/regmap/regcache-rbtree.c
@@ -1,14 +1,10 @@
-/*
- * Register cache access API - rbtree caching support
- *
- * Copyright 2011 Wolfson Microelectronics plc
- *
- * Author: Dimitris Papastamos <dp@opensource.wolfsonmicro.com>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- */
+// SPDX-License-Identifier: GPL-2.0
+//
+// Register cache access API - rbtree caching support
+//
+// Copyright 2011 Wolfson Microelectronics plc
+//
+// Author: Dimitris Papastamos <dp@opensource.wolfsonmicro.com>
 
 #include <linux/debugfs.h>
 #include <linux/device.h>
diff --git a/drivers/base/regmap/regcache.c b/drivers/base/regmap/regcache.c
index 773560348337..a93cafd7be4f 100644
--- a/drivers/base/regmap/regcache.c
+++ b/drivers/base/regmap/regcache.c
@@ -1,14 +1,10 @@
-/*
- * Register cache access API
- *
- * Copyright 2011 Wolfson Microelectronics plc
- *
- * Author: Dimitris Papastamos <dp@opensource.wolfsonmicro.com>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- */
+// SPDX-License-Identifier: GPL-2.0
+//
+// Register cache access API
+//
+// Copyright 2011 Wolfson Microelectronics plc
+//
+// Author: Dimitris Papastamos <dp@opensource.wolfsonmicro.com>
 
 #include <linux/bsearch.h>
 #include <linux/device.h>
diff --git a/drivers/base/regmap/regmap-ac97.c b/drivers/base/regmap/regmap-ac97.c
index c03ebfd4c731..b9f76bdf74a9 100644
--- a/drivers/base/regmap/regmap-ac97.c
+++ b/drivers/base/regmap/regmap-ac97.c
@@ -1,20 +1,8 @@
-/*
- * Register map access API - AC'97 support
- *
- * Copyright 2013 Linaro Ltd.  All rights reserved.
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms and conditions of the GNU General Public License,
- * version 2, as published by the Free Software Foundation.
- *
- * This program is distributed in the hope it will be useful, but WITHOUT
- * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
- * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
- * more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program.  If not, see <http://www.gnu.org/licenses/>.
- */
+// SPDX-License-Identifier: GPL-2.0
+//
+// Register map access API - AC'97 support
+//
+// Copyright 2013 Linaro Ltd.  All rights reserved.
 
 #include <linux/clk.h>
 #include <linux/err.h>
diff --git a/drivers/base/regmap/regmap-debugfs.c b/drivers/base/regmap/regmap-debugfs.c
index 19eb454f26c3..263f82516ff4 100644
--- a/drivers/base/regmap/regmap-debugfs.c
+++ b/drivers/base/regmap/regmap-debugfs.c
@@ -1,14 +1,10 @@
-/*
- * Register map access API - debugfs
- *
- * Copyright 2011 Wolfson Microelectronics plc
- *
- * Author: Mark Brown <broonie@opensource.wolfsonmicro.com>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- */
+// SPDX-License-Identifier: GPL-2.0
+//
+// Register map access API - debugfs
+//
+// Copyright 2011 Wolfson Microelectronics plc
+//
+// Author: Mark Brown <broonie@opensource.wolfsonmicro.com>
 
 #include <linux/slab.h>
 #include <linux/mutex.h>
@@ -195,6 +191,28 @@ static inline void regmap_calc_tot_len(struct regmap *map,
 	}
 }
 
+static int regmap_next_readable_reg(struct regmap *map, int reg)
+{
+	struct regmap_debugfs_off_cache *c;
+	int ret = -EINVAL;
+
+	if (regmap_printable(map, reg + map->reg_stride)) {
+		ret = reg + map->reg_stride;
+	} else {
+		mutex_lock(&map->cache_lock);
+		list_for_each_entry(c, &map->debugfs_off_cache, list) {
+			if (reg > c->max_reg)
+				continue;
+			if (reg < c->base_reg) {
+				ret = c->base_reg;
+				break;
+			}
+		}
+		mutex_unlock(&map->cache_lock);
+	}
+	return ret;
+}
+
 static ssize_t regmap_read_debugfs(struct regmap *map, unsigned int from,
 				   unsigned int to, char __user *user_buf,
 				   size_t count, loff_t *ppos)
@@ -218,12 +236,8 @@ static ssize_t regmap_read_debugfs(struct regmap *map, unsigned int from,
 	/* Work out which register we're starting at */
 	start_reg = regmap_debugfs_get_dump_start(map, from, *ppos, &p);
 
-	for (i = start_reg; i <= to; i += map->reg_stride) {
-		if (!regmap_readable(map, i) && !regmap_cached(map, i))
-			continue;
-
-		if (regmap_precious(map, i))
-			continue;
+	for (i = start_reg; i >= 0 && i <= to;
+	     i = regmap_next_readable_reg(map, i)) {
 
 		/* If we're in the region the user is trying to read */
 		if (p >= *ppos) {
diff --git a/drivers/base/regmap/regmap-i2c.c b/drivers/base/regmap/regmap-i2c.c
index 056acde5e7d3..ac9b31c57967 100644
--- a/drivers/base/regmap/regmap-i2c.c
+++ b/drivers/base/regmap/regmap-i2c.c
@@ -1,14 +1,10 @@
-/*
- * Register map access API - I2C support
- *
- * Copyright 2011 Wolfson Microelectronics plc
- *
- * Author: Mark Brown <broonie@opensource.wolfsonmicro.com>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- */
+// SPDX-License-Identifier: GPL-2.0
+//
+// Register map access API - I2C support
+//
+// Copyright 2011 Wolfson Microelectronics plc
+//
+// Author: Mark Brown <broonie@opensource.wolfsonmicro.com>
 
 #include <linux/regmap.h>
 #include <linux/i2c.h>
diff --git a/drivers/base/regmap/regmap-irq.c b/drivers/base/regmap/regmap-irq.c
index 5059748afd4c..c9dc70ceca5f 100644
--- a/drivers/base/regmap/regmap-irq.c
+++ b/drivers/base/regmap/regmap-irq.c
@@ -1,14 +1,10 @@
-/*
- * regmap based irq_chip
- *
- * Copyright 2011 Wolfson Microelectronics plc
- *
- * Author: Mark Brown <broonie@opensource.wolfsonmicro.com>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- */
+// SPDX-License-Identifier: GPL-2.0
+//
+// regmap based irq_chip
+//
+// Copyright 2011 Wolfson Microelectronics plc
+//
+// Author: Mark Brown <broonie@opensource.wolfsonmicro.com>
 
 #include <linux/device.h>
 #include <linux/export.h>
@@ -761,9 +757,6 @@ int regmap_add_irq_chip(struct regmap *map, int irq, int irq_flags,
 
 	if (chip->num_type_reg && !chip->type_in_mask) {
 		for (i = 0; i < chip->num_type_reg; ++i) {
-			if (!d->type_buf_def[i])
-				continue;
-
 			reg = chip->type_base +
 				(i * map->reg_stride * d->type_reg_stride);
 
diff --git a/drivers/base/regmap/regmap-mmio.c b/drivers/base/regmap/regmap-mmio.c
index 8741fb5f8f54..af967d8f975e 100644
--- a/drivers/base/regmap/regmap-mmio.c
+++ b/drivers/base/regmap/regmap-mmio.c
@@ -1,20 +1,8 @@
-/*
- * Register map access API - MMIO support
- *
- * Copyright (c) 2012, NVIDIA CORPORATION.  All rights reserved.
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms and conditions of the GNU General Public License,
- * version 2, as published by the Free Software Foundation.
- *
- * This program is distributed in the hope it will be useful, but WITHOUT
- * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
- * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
- * more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program.  If not, see <http://www.gnu.org/licenses/>.
- */
+// SPDX-License-Identifier: GPL-2.0
+//
+// Register map access API - MMIO support
+//
+// Copyright (c) 2012, NVIDIA CORPORATION.  All rights reserved.
 
 #include <linux/clk.h>
 #include <linux/err.h>
diff --git a/drivers/base/regmap/regmap-spi.c b/drivers/base/regmap/regmap-spi.c
index c7150dd264d5..c1894e93c378 100644
--- a/drivers/base/regmap/regmap-spi.c
+++ b/drivers/base/regmap/regmap-spi.c
@@ -1,14 +1,10 @@
-/*
- * Register map access API - SPI support
- *
- * Copyright 2011 Wolfson Microelectronics plc
- *
- * Author: Mark Brown <broonie@opensource.wolfsonmicro.com>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- */
+// SPDX-License-Identifier: GPL-2.0
+//
+// Register map access API - SPI support
+//
+// Copyright 2011 Wolfson Microelectronics plc
+//
+// Author: Mark Brown <broonie@opensource.wolfsonmicro.com>
 
 #include <linux/regmap.h>
 #include <linux/spi/spi.h>
diff --git a/drivers/base/regmap/regmap-spmi.c b/drivers/base/regmap/regmap-spmi.c
index 0bfb8ed244d5..cdf12d2aa3a1 100644
--- a/drivers/base/regmap/regmap-spmi.c
+++ b/drivers/base/regmap/regmap-spmi.c
@@ -1,22 +1,13 @@
-/*
- * Register map access API - SPMI support
- *
- * Copyright (c) 2012-2013, The Linux Foundation. All rights reserved.
- *
- * Based on regmap-i2c.c:
- * Copyright 2011 Wolfson Microelectronics plc
- * Author: Mark Brown <broonie@opensource.wolfsonmicro.com>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 and
- * only version 2 as published by the Free Software Foundation.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- *
- */
+// SPDX-License-Identifier: GPL-2.0
+//
+// Register map access API - SPMI support
+//
+// Copyright (c) 2012-2013, The Linux Foundation. All rights reserved.
+//
+// Based on regmap-i2c.c:
+// Copyright 2011 Wolfson Microelectronics plc
+// Author: Mark Brown <broonie@opensource.wolfsonmicro.com>
+
 #include <linux/regmap.h>
 #include <linux/spmi.h>
 #include <linux/module.h>
diff --git a/drivers/base/regmap/regmap-w1.c b/drivers/base/regmap/regmap-w1.c
index e6c64b0be5b2..3a7d30b8c3ac 100644
--- a/drivers/base/regmap/regmap-w1.c
+++ b/drivers/base/regmap/regmap-w1.c
@@ -1,13 +1,9 @@
-/*
- * Register map access API - W1 (1-Wire) support
- *
- * Copyright (c) 2017 Radioavionica Corporation
- * Author: Alex A. Mihaylov <minimumlaw@rambler.ru>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation
- */
+// SPDX-License-Identifier: GPL-2.0
+//
+// Register map access API - W1 (1-Wire) support
+//
+// Copyright (c) 2017 Radioavionica Corporation
+// Author: Alex A. Mihaylov <minimumlaw@rambler.ru>
 
 #include <linux/regmap.h>
 #include <linux/module.h>
diff --git a/drivers/base/regmap/regmap.c b/drivers/base/regmap/regmap.c
index 4f822e087def..f1025452bb39 100644
--- a/drivers/base/regmap/regmap.c
+++ b/drivers/base/regmap/regmap.c
@@ -1,14 +1,10 @@
-/*
- * Register map access API
- *
- * Copyright 2011 Wolfson Microelectronics plc
- *
- * Author: Mark Brown <broonie@opensource.wolfsonmicro.com>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- */
+// SPDX-License-Identifier: GPL-2.0
+//
+// Register map access API
+//
+// Copyright 2011 Wolfson Microelectronics plc
+//
+// Author: Mark Brown <broonie@opensource.wolfsonmicro.com>
 
 #include <linux/device.h>
 #include <linux/slab.h>
@@ -1493,11 +1489,10 @@ static int _regmap_raw_write_impl(struct regmap *map, unsigned int reg,
 	WARN_ON(!map->bus);
 
 	/* Check for unwritable registers before we start */
-	if (map->writeable_reg)
-		for (i = 0; i < val_len / map->format.val_bytes; i++)
-			if (!map->writeable_reg(map->dev,
-					       reg + regmap_get_offset(map, i)))
-				return -EINVAL;
+	for (i = 0; i < val_len / map->format.val_bytes; i++)
+		if (!regmap_writeable(map,
+				     reg + regmap_get_offset(map, i)))
+			return -EINVAL;
 
 	if (!map->cache_bypass && map->format.parse_val) {
 		unsigned int ival;
diff --git a/drivers/block/drbd/drbd_receiver.c b/drivers/block/drbd/drbd_receiver.c
index c7ad88d91a09..843a9b9b3d74 100644
--- a/drivers/block/drbd/drbd_receiver.c
+++ b/drivers/block/drbd/drbd_receiver.c
@@ -5443,7 +5443,6 @@ static int drbd_do_auth(struct drbd_connection *connection)
 	rcu_read_unlock();
 
 	desc->tfm = connection->cram_hmac_tfm;
-	desc->flags = 0;
 
 	rv = crypto_shash_setkey(connection->cram_hmac_tfm, (u8 *)secret, key_len);
 	if (rv) {
diff --git a/drivers/block/drbd/drbd_worker.c b/drivers/block/drbd/drbd_worker.c
index 268ef0c5d4ab..6781bcf3ec26 100644
--- a/drivers/block/drbd/drbd_worker.c
+++ b/drivers/block/drbd/drbd_worker.c
@@ -304,7 +304,6 @@ void drbd_csum_ee(struct crypto_shash *tfm, struct drbd_peer_request *peer_req,
 	void *src;
 
 	desc->tfm = tfm;
-	desc->flags = 0;
 
 	crypto_shash_init(desc);
 
@@ -332,7 +331,6 @@ void drbd_csum_bio(struct crypto_shash *tfm, struct bio *bio, void *digest)
 	struct bvec_iter iter;
 
 	desc->tfm = tfm;
-	desc->flags = 0;
 
 	crypto_shash_init(desc);
 
diff --git a/drivers/block/null_blk_main.c b/drivers/block/null_blk_main.c
index 417a9f15c116..d7ac09c092f2 100644
--- a/drivers/block/null_blk_main.c
+++ b/drivers/block/null_blk_main.c
@@ -1748,6 +1748,11 @@ static int __init null_init(void)
 		return -EINVAL;
 	}
 
+	if (g_home_node != NUMA_NO_NODE && g_home_node >= nr_online_nodes) {
+		pr_err("null_blk: invalid home_node value\n");
+		g_home_node = NUMA_NO_NODE;
+	}
+
 	if (g_queue_mode == NULL_Q_RQ) {
 		pr_err("null_blk: legacy IO path no longer available\n");
 		return -EINVAL;
diff --git a/drivers/block/paride/pcd.c b/drivers/block/paride/pcd.c
index 377a694dc228..6d415b20fb70 100644
--- a/drivers/block/paride/pcd.c
+++ b/drivers/block/paride/pcd.c
@@ -314,6 +314,7 @@ static void pcd_init_units(void)
 		disk->queue = blk_mq_init_sq_queue(&cd->tag_set, &pcd_mq_ops,
 						   1, BLK_MQ_F_SHOULD_MERGE);
 		if (IS_ERR(disk->queue)) {
+			put_disk(disk);
 			disk->queue = NULL;
 			continue;
 		}
@@ -750,6 +751,8 @@ static int pcd_detect(void)
 
 	printk("%s: No CD-ROM drive found\n", name);
 	for (unit = 0, cd = pcd; unit < PCD_UNITS; unit++, cd++) {
+		if (!cd->disk)
+			continue;
 		blk_cleanup_queue(cd->disk->queue);
 		cd->disk->queue = NULL;
 		blk_mq_free_tag_set(&cd->tag_set);
@@ -1010,8 +1013,14 @@ static int __init pcd_init(void)
 	pcd_probe_capabilities();
 
 	if (register_blkdev(major, name)) {
-		for (unit = 0, cd = pcd; unit < PCD_UNITS; unit++, cd++)
+		for (unit = 0, cd = pcd; unit < PCD_UNITS; unit++, cd++) {
+			if (!cd->disk)
+				continue;
+
+			blk_cleanup_queue(cd->disk->queue);
+			blk_mq_free_tag_set(&cd->tag_set);
 			put_disk(cd->disk);
+		}
 		return -EBUSY;
 	}
 
@@ -1032,6 +1041,9 @@ static void __exit pcd_exit(void)
 	int unit;
 
 	for (unit = 0, cd = pcd; unit < PCD_UNITS; unit++, cd++) {
+		if (!cd->disk)
+			continue;
+
 		if (cd->present) {
 			del_gendisk(cd->disk);
 			pi_release(cd->pi);
diff --git a/drivers/block/paride/pf.c b/drivers/block/paride/pf.c
index 103b617cdc31..35e6e271b219 100644
--- a/drivers/block/paride/pf.c
+++ b/drivers/block/paride/pf.c
@@ -762,6 +762,8 @@ static int pf_detect(void)
 
 	printk("%s: No ATAPI disk detected\n", name);
 	for (pf = units, unit = 0; unit < PF_UNITS; pf++, unit++) {
+		if (!pf->disk)
+			continue;
 		blk_cleanup_queue(pf->disk->queue);
 		pf->disk->queue = NULL;
 		blk_mq_free_tag_set(&pf->tag_set);
@@ -1029,8 +1031,13 @@ static int __init pf_init(void)
 	pf_busy = 0;
 
 	if (register_blkdev(major, name)) {
-		for (pf = units, unit = 0; unit < PF_UNITS; pf++, unit++)
+		for (pf = units, unit = 0; unit < PF_UNITS; pf++, unit++) {
+			if (!pf->disk)
+				continue;
+			blk_cleanup_queue(pf->disk->queue);
+			blk_mq_free_tag_set(&pf->tag_set);
 			put_disk(pf->disk);
+		}
 		return -EBUSY;
 	}
 
@@ -1051,6 +1058,9 @@ static void __exit pf_exit(void)
 	int unit;
 	unregister_blkdev(major, name);
 	for (pf = units, unit = 0; unit < PF_UNITS; pf++, unit++) {
+		if (!pf->disk)
+			continue;
+
 		if (pf->present)
 			del_gendisk(pf->disk);
 
diff --git a/drivers/block/virtio_blk.c b/drivers/block/virtio_blk.c
index 4bc083b7c9b5..2a7ca4a1e6f7 100644
--- a/drivers/block/virtio_blk.c
+++ b/drivers/block/virtio_blk.c
@@ -513,6 +513,8 @@ static int init_vq(struct virtio_blk *vblk)
 	if (err)
 		num_vqs = 1;
 
+	num_vqs = min_t(unsigned int, nr_cpu_ids, num_vqs);
+
 	vblk->vqs = kmalloc_array(num_vqs, sizeof(*vblk->vqs), GFP_KERNEL);
 	if (!vblk->vqs)
 		return -ENOMEM;
diff --git a/drivers/block/xsysace.c b/drivers/block/xsysace.c
index 87ccef4bd69e..32a21b8d1d85 100644
--- a/drivers/block/xsysace.c
+++ b/drivers/block/xsysace.c
@@ -1090,6 +1090,8 @@ static int ace_setup(struct ace_device *ace)
 	return 0;
 
 err_read:
+	/* prevent double queue cleanup */
+	ace->gd->queue = NULL;
 	put_disk(ace->gd);
 err_alloc_disk:
 	blk_cleanup_queue(ace->queue);
diff --git a/drivers/block/zram/zram_drv.c b/drivers/block/zram/zram_drv.c
index e7a5f1d1c314..d58a359a6622 100644
--- a/drivers/block/zram/zram_drv.c
+++ b/drivers/block/zram/zram_drv.c
@@ -290,18 +290,8 @@ static ssize_t idle_store(struct device *dev,
 	struct zram *zram = dev_to_zram(dev);
 	unsigned long nr_pages = zram->disksize >> PAGE_SHIFT;
 	int index;
-	char mode_buf[8];
-	ssize_t sz;
 
-	sz = strscpy(mode_buf, buf, sizeof(mode_buf));
-	if (sz <= 0)
-		return -EINVAL;
-
-	/* ignore trailing new line */
-	if (mode_buf[sz - 1] == '\n')
-		mode_buf[sz - 1] = 0x00;
-
-	if (strcmp(mode_buf, "all"))
+	if (!sysfs_streq(buf, "all"))
 		return -EINVAL;
 
 	down_read(&zram->init_lock);
@@ -635,25 +625,15 @@ static ssize_t writeback_store(struct device *dev,
 	struct bio bio;
 	struct bio_vec bio_vec;
 	struct page *page;
-	ssize_t ret, sz;
-	char mode_buf[8];
-	int mode = -1;
+	ssize_t ret;
+	int mode;
 	unsigned long blk_idx = 0;
 
-	sz = strscpy(mode_buf, buf, sizeof(mode_buf));
-	if (sz <= 0)
-		return -EINVAL;
-
-	/* ignore trailing newline */
-	if (mode_buf[sz - 1] == '\n')
-		mode_buf[sz - 1] = 0x00;
-
-	if (!strcmp(mode_buf, "idle"))
+	if (sysfs_streq(buf, "idle"))
 		mode = IDLE_WRITEBACK;
-	else if (!strcmp(mode_buf, "huge"))
+	else if (sysfs_streq(buf, "huge"))
 		mode = HUGE_WRITEBACK;
-
-	if (mode == -1)
+	else
 		return -EINVAL;
 
 	down_read(&zram->init_lock);
@@ -794,18 +774,18 @@ struct zram_work {
 	struct zram *zram;
 	unsigned long entry;
 	struct bio *bio;
+	struct bio_vec bvec;
 };
 
 #if PAGE_SIZE != 4096
 static void zram_sync_read(struct work_struct *work)
 {
-	struct bio_vec bvec;
 	struct zram_work *zw = container_of(work, struct zram_work, work);
 	struct zram *zram = zw->zram;
 	unsigned long entry = zw->entry;
 	struct bio *bio = zw->bio;
 
-	read_from_bdev_async(zram, &bvec, entry, bio);
+	read_from_bdev_async(zram, &zw->bvec, entry, bio);
 }
 
 /*
@@ -818,6 +798,7 @@ static int read_from_bdev_sync(struct zram *zram, struct bio_vec *bvec,
 {
 	struct zram_work work;
 
+	work.bvec = *bvec;
 	work.zram = zram;
 	work.entry = entry;
 	work.bio = bio;
diff --git a/drivers/bluetooth/btusb.c b/drivers/bluetooth/btusb.c
index ded198328f21..7db48ae65cd2 100644
--- a/drivers/bluetooth/btusb.c
+++ b/drivers/bluetooth/btusb.c
@@ -2942,6 +2942,7 @@ static int btusb_config_oob_wake(struct hci_dev *hdev)
 		return 0;
 	}
 
+	irq_set_status_flags(irq, IRQ_NOAUTOEN);
 	ret = devm_request_irq(&hdev->dev, irq, btusb_oob_wake_handler,
 			       0, "OOB Wake-on-BT", data);
 	if (ret) {
@@ -2956,7 +2957,6 @@ static int btusb_config_oob_wake(struct hci_dev *hdev)
 	}
 
 	data->oob_wake_irq = irq;
-	disable_irq(irq);
 	bt_dev_info(hdev, "OOB Wake-on-BT configured at IRQ %u", irq);
 	return 0;
 }
diff --git a/drivers/char/Kconfig b/drivers/char/Kconfig
index 72866a004f07..466ebd84ad17 100644
--- a/drivers/char/Kconfig
+++ b/drivers/char/Kconfig
@@ -348,7 +348,7 @@ config XILINX_HWICAP
 
 config R3964
 	tristate "Siemens R3964 line discipline"
-	depends on TTY
+	depends on TTY && BROKEN
 	---help---
 	  This driver allows synchronous communication with devices using the
 	  Siemens R3964 packet protocol. Unless you are dealing with special
diff --git a/drivers/char/hw_random/omap-rng.c b/drivers/char/hw_random/omap-rng.c
index b65ff6962899..e9b6ac61fb7f 100644
--- a/drivers/char/hw_random/omap-rng.c
+++ b/drivers/char/hw_random/omap-rng.c
@@ -443,6 +443,7 @@ static int omap_rng_probe(struct platform_device *pdev)
 	priv->rng.read = omap_rng_do_read;
 	priv->rng.init = omap_rng_init;
 	priv->rng.cleanup = omap_rng_cleanup;
+	priv->rng.quality = 900;
 
 	priv->rng.priv = (unsigned long)priv;
 	platform_set_drvdata(pdev, priv);
diff --git a/drivers/char/hw_random/stm32-rng.c b/drivers/char/hw_random/stm32-rng.c
index 042860d97b15..0ef5b6a3f560 100644
--- a/drivers/char/hw_random/stm32-rng.c
+++ b/drivers/char/hw_random/stm32-rng.c
@@ -161,6 +161,7 @@ static int stm32_rng_probe(struct platform_device *ofdev)
 #endif
 	priv->rng.read = stm32_rng_read,
 	priv->rng.priv = (unsigned long) dev;
+	priv->rng.quality = 900;
 
 	pm_runtime_set_autosuspend_delay(dev, 100);
 	pm_runtime_use_autosuspend(dev);
@@ -169,6 +170,13 @@ static int stm32_rng_probe(struct platform_device *ofdev)
 	return devm_hwrng_register(dev, &priv->rng);
 }
 
+static int stm32_rng_remove(struct platform_device *ofdev)
+{
+	pm_runtime_disable(&ofdev->dev);
+
+	return 0;
+}
+
 #ifdef CONFIG_PM
 static int stm32_rng_runtime_suspend(struct device *dev)
 {
@@ -210,6 +218,7 @@ static struct platform_driver stm32_rng_driver = {
 		.of_match_table = stm32_rng_match,
 	},
 	.probe = stm32_rng_probe,
+	.remove = stm32_rng_remove,
 };
 
 module_platform_driver(stm32_rng_driver);
diff --git a/drivers/char/ipmi/ipmi_dmi.c b/drivers/char/ipmi/ipmi_dmi.c
index ff0b199be472..f2411468f33f 100644
--- a/drivers/char/ipmi/ipmi_dmi.c
+++ b/drivers/char/ipmi/ipmi_dmi.c
@@ -66,7 +66,6 @@ static void __init dmi_add_platform_ipmi(unsigned long base_addr,
 		return;
 	}
 
-	memset(&p, 0, sizeof(p));
 	p.addr = base_addr;
 	p.space = space;
 	p.regspacing = offset;
diff --git a/drivers/char/ipmi/ipmi_msghandler.c b/drivers/char/ipmi/ipmi_msghandler.c
index e8ba67834746..00bf4b17edbf 100644
--- a/drivers/char/ipmi/ipmi_msghandler.c
+++ b/drivers/char/ipmi/ipmi_msghandler.c
@@ -214,6 +214,9 @@ struct ipmi_user {
 
 	/* Does this interface receive IPMI events? */
 	bool gets_events;
+
+	/* Free must run in process context for RCU cleanup. */
+	struct work_struct remove_work;
 };
 
 static struct ipmi_user *acquire_ipmi_user(struct ipmi_user *user, int *index)
@@ -1157,6 +1160,15 @@ static int intf_err_seq(struct ipmi_smi *intf,
 	return rv;
 }
 
+static void free_user_work(struct work_struct *work)
+{
+	struct ipmi_user *user = container_of(work, struct ipmi_user,
+					      remove_work);
+
+	cleanup_srcu_struct(&user->release_barrier);
+	kfree(user);
+}
+
 int ipmi_create_user(unsigned int          if_num,
 		     const struct ipmi_user_hndl *handler,
 		     void                  *handler_data,
@@ -1200,6 +1212,8 @@ int ipmi_create_user(unsigned int          if_num,
 	goto out_kfree;
 
  found:
+	INIT_WORK(&new_user->remove_work, free_user_work);
+
 	rv = init_srcu_struct(&new_user->release_barrier);
 	if (rv)
 		goto out_kfree;
@@ -1260,8 +1274,9 @@ EXPORT_SYMBOL(ipmi_get_smi_info);
 static void free_user(struct kref *ref)
 {
 	struct ipmi_user *user = container_of(ref, struct ipmi_user, refcount);
-	cleanup_srcu_struct(&user->release_barrier);
-	kfree(user);
+
+	/* SRCU cleanup must happen in task context. */
+	schedule_work(&user->remove_work);
 }
 
 static void _ipmi_destroy_user(struct ipmi_user *user)
diff --git a/drivers/char/ipmi/ipmi_si_hardcode.c b/drivers/char/ipmi/ipmi_si_hardcode.c
index 01946cad3d13..682221eebd66 100644
--- a/drivers/char/ipmi/ipmi_si_hardcode.c
+++ b/drivers/char/ipmi/ipmi_si_hardcode.c
@@ -118,6 +118,8 @@ void __init ipmi_hardcode_init(void)
 	char *str;
 	char *si_type[SI_MAX_PARMS];
 
+	memset(si_type, 0, sizeof(si_type));
+
 	/* Parse out the si_type string into its components. */
 	str = si_type_str;
 	if (*str != '\0') {
diff --git a/drivers/char/tpm/eventlog/tpm2.c b/drivers/char/tpm/eventlog/tpm2.c
index d8b77133a83a..f824563fc28d 100644
--- a/drivers/char/tpm/eventlog/tpm2.c
+++ b/drivers/char/tpm/eventlog/tpm2.c
@@ -37,8 +37,8 @@
  *
  * Returns size of the event. If it is an invalid event, returns 0.
  */
-static int calc_tpm2_event_size(struct tcg_pcr_event2_head *event,
-				struct tcg_pcr_event *event_header)
+static size_t calc_tpm2_event_size(struct tcg_pcr_event2_head *event,
+				   struct tcg_pcr_event *event_header)
 {
 	struct tcg_efi_specid_event_head *efispecid;
 	struct tcg_event_field *event_field;
diff --git a/drivers/char/tpm/tpm-dev-common.c b/drivers/char/tpm/tpm-dev-common.c
index 8856cce5a23b..817ae09a369e 100644
--- a/drivers/char/tpm/tpm-dev-common.c
+++ b/drivers/char/tpm/tpm-dev-common.c
@@ -233,12 +233,19 @@ __poll_t tpm_common_poll(struct file *file, poll_table *wait)
 	__poll_t mask = 0;
 
 	poll_wait(file, &priv->async_wait, wait);
+	mutex_lock(&priv->buffer_mutex);
 
-	if (!priv->response_read || priv->response_length)
+	/*
+	 * The response_length indicates if there is still response
+	 * (or part of it) to be consumed. Partial reads decrease it
+	 * by the number of bytes read, and write resets it the zero.
+	 */
+	if (priv->response_length)
 		mask = EPOLLIN | EPOLLRDNORM;
 	else
 		mask = EPOLLOUT | EPOLLWRNORM;
 
+	mutex_unlock(&priv->buffer_mutex);
 	return mask;
 }
 
diff --git a/drivers/char/tpm/tpm-interface.c b/drivers/char/tpm/tpm-interface.c
index 83ece5639f86..ae1030c9b086 100644
--- a/drivers/char/tpm/tpm-interface.c
+++ b/drivers/char/tpm/tpm-interface.c
@@ -402,15 +402,13 @@ int tpm_pm_suspend(struct device *dev)
 	if (chip->flags & TPM_CHIP_FLAG_ALWAYS_POWERED)
 		return 0;
 
-	if (chip->flags & TPM_CHIP_FLAG_TPM2) {
-		mutex_lock(&chip->tpm_mutex);
-		if (!tpm_chip_start(chip)) {
+	if (!tpm_chip_start(chip)) {
+		if (chip->flags & TPM_CHIP_FLAG_TPM2)
 			tpm2_shutdown(chip, TPM2_SU_STATE);
-			tpm_chip_stop(chip);
-		}
-		mutex_unlock(&chip->tpm_mutex);
-	} else {
-		rc = tpm1_pm_suspend(chip, tpm_suspend_pcr);
+		else
+			rc = tpm1_pm_suspend(chip, tpm_suspend_pcr);
+
+		tpm_chip_stop(chip);
 	}
 
 	return rc;
diff --git a/drivers/clk/at91/clk-programmable.c b/drivers/clk/at91/clk-programmable.c
index 89d6f3736dbf..f8edbb65eda3 100644
--- a/drivers/clk/at91/clk-programmable.c
+++ b/drivers/clk/at91/clk-programmable.c
@@ -20,8 +20,7 @@
 #define PROG_ID_MAX		7
 
 #define PROG_STATUS_MASK(id)	(1 << ((id) + 8))
-#define PROG_PRES_MASK		0x7
-#define PROG_PRES(layout, pckr)	((pckr >> layout->pres_shift) & PROG_PRES_MASK)
+#define PROG_PRES(layout, pckr)	((pckr >> layout->pres_shift) & layout->pres_mask)
 #define PROG_MAX_RM9200_CSS	3
 
 struct clk_programmable {
@@ -37,20 +36,29 @@ static unsigned long clk_programmable_recalc_rate(struct clk_hw *hw,
 						  unsigned long parent_rate)
 {
 	struct clk_programmable *prog = to_clk_programmable(hw);
+	const struct clk_programmable_layout *layout = prog->layout;
 	unsigned int pckr;
+	unsigned long rate;
 
 	regmap_read(prog->regmap, AT91_PMC_PCKR(prog->id), &pckr);
 
-	return parent_rate >> PROG_PRES(prog->layout, pckr);
+	if (layout->is_pres_direct)
+		rate = parent_rate / (PROG_PRES(layout, pckr) + 1);
+	else
+		rate = parent_rate >> PROG_PRES(layout, pckr);
+
+	return rate;
 }
 
 static int clk_programmable_determine_rate(struct clk_hw *hw,
 					   struct clk_rate_request *req)
 {
+	struct clk_programmable *prog = to_clk_programmable(hw);
+	const struct clk_programmable_layout *layout = prog->layout;
 	struct clk_hw *parent;
 	long best_rate = -EINVAL;
 	unsigned long parent_rate;
-	unsigned long tmp_rate;
+	unsigned long tmp_rate = 0;
 	int shift;
 	int i;
 
@@ -60,10 +68,18 @@ static int clk_programmable_determine_rate(struct clk_hw *hw,
 			continue;
 
 		parent_rate = clk_hw_get_rate(parent);
-		for (shift = 0; shift < PROG_PRES_MASK; shift++) {
-			tmp_rate = parent_rate >> shift;
-			if (tmp_rate <= req->rate)
-				break;
+		if (layout->is_pres_direct) {
+			for (shift = 0; shift <= layout->pres_mask; shift++) {
+				tmp_rate = parent_rate / (shift + 1);
+				if (tmp_rate <= req->rate)
+					break;
+			}
+		} else {
+			for (shift = 0; shift < layout->pres_mask; shift++) {
+				tmp_rate = parent_rate >> shift;
+				if (tmp_rate <= req->rate)
+					break;
+			}
 		}
 
 		if (tmp_rate > req->rate)
@@ -137,16 +153,23 @@ static int clk_programmable_set_rate(struct clk_hw *hw, unsigned long rate,
 	if (!div)
 		return -EINVAL;
 
-	shift = fls(div) - 1;
+	if (layout->is_pres_direct) {
+		shift = div - 1;
 
-	if (div != (1 << shift))
-		return -EINVAL;
+		if (shift > layout->pres_mask)
+			return -EINVAL;
+	} else {
+		shift = fls(div) - 1;
 
-	if (shift >= PROG_PRES_MASK)
-		return -EINVAL;
+		if (div != (1 << shift))
+			return -EINVAL;
+
+		if (shift >= layout->pres_mask)
+			return -EINVAL;
+	}
 
 	regmap_update_bits(prog->regmap, AT91_PMC_PCKR(prog->id),
-			   PROG_PRES_MASK << layout->pres_shift,
+			   layout->pres_mask << layout->pres_shift,
 			   shift << layout->pres_shift);
 
 	return 0;
@@ -202,19 +225,25 @@ at91_clk_register_programmable(struct regmap *regmap,
 }
 
 const struct clk_programmable_layout at91rm9200_programmable_layout = {
+	.pres_mask = 0x7,
 	.pres_shift = 2,
 	.css_mask = 0x3,
 	.have_slck_mck = 0,
+	.is_pres_direct = 0,
 };
 
 const struct clk_programmable_layout at91sam9g45_programmable_layout = {
+	.pres_mask = 0x7,
 	.pres_shift = 2,
 	.css_mask = 0x3,
 	.have_slck_mck = 1,
+	.is_pres_direct = 0,
 };
 
 const struct clk_programmable_layout at91sam9x5_programmable_layout = {
+	.pres_mask = 0x7,
 	.pres_shift = 4,
 	.css_mask = 0x7,
 	.have_slck_mck = 0,
+	.is_pres_direct = 0,
 };
diff --git a/drivers/clk/at91/pmc.h b/drivers/clk/at91/pmc.h
index 672a79bda88c..a0e5ce9c9b9e 100644
--- a/drivers/clk/at91/pmc.h
+++ b/drivers/clk/at91/pmc.h
@@ -71,9 +71,11 @@ struct clk_pll_characteristics {
 };
 
 struct clk_programmable_layout {
+	u8 pres_mask;
 	u8 pres_shift;
 	u8 css_mask;
 	u8 have_slck_mck;
+	u8 is_pres_direct;
 };
 
 extern const struct clk_programmable_layout at91rm9200_programmable_layout;
diff --git a/drivers/clk/at91/sama5d2.c b/drivers/clk/at91/sama5d2.c
index 1f70cb164b06..81943fac4537 100644
--- a/drivers/clk/at91/sama5d2.c
+++ b/drivers/clk/at91/sama5d2.c
@@ -125,6 +125,14 @@ static const struct {
 	  .pll = true },
 };
 
+static const struct clk_programmable_layout sama5d2_programmable_layout = {
+	.pres_mask = 0xff,
+	.pres_shift = 4,
+	.css_mask = 0x7,
+	.have_slck_mck = 0,
+	.is_pres_direct = 1,
+};
+
 static void __init sama5d2_pmc_setup(struct device_node *np)
 {
 	struct clk_range range = CLK_RANGE(0, 0);
@@ -249,7 +257,7 @@ static void __init sama5d2_pmc_setup(struct device_node *np)
 
 		hw = at91_clk_register_programmable(regmap, name,
 						    parent_names, 6, i,
-						    &at91sam9x5_programmable_layout);
+						    &sama5d2_programmable_layout);
 		if (IS_ERR(hw))
 			goto err_free;
 	}
diff --git a/drivers/clk/clkdev.c b/drivers/clk/clkdev.c
index 8c4435c53f09..6e787cc9e5b9 100644
--- a/drivers/clk/clkdev.c
+++ b/drivers/clk/clkdev.c
@@ -46,6 +46,8 @@ static struct clk_lookup *clk_find(const char *dev_id, const char *con_id)
 	if (con_id)
 		best_possible += 1;
 
+	lockdep_assert_held(&clocks_mutex);
+
 	list_for_each_entry(p, &clocks, node) {
 		match = 0;
 		if (p->dev_id) {
@@ -402,7 +404,10 @@ void devm_clk_release_clkdev(struct device *dev, const char *con_id,
 	struct clk_lookup *cl;
 	int rval;
 
+	mutex_lock(&clocks_mutex);
 	cl = clk_find(dev_id, con_id);
+	mutex_unlock(&clocks_mutex);
+
 	WARN_ON(!cl);
 	rval = devres_release(dev, devm_clkdev_release,
 			      devm_clk_match_clkdev, cl);
diff --git a/drivers/clk/imx/clk-pll14xx.c b/drivers/clk/imx/clk-pll14xx.c
index 1acfa3e3cfb4..113d71042199 100644
--- a/drivers/clk/imx/clk-pll14xx.c
+++ b/drivers/clk/imx/clk-pll14xx.c
@@ -362,7 +362,7 @@ struct clk *imx_clk_pll14xx(const char *name, const char *parent_name,
 
 	switch (pll_clk->type) {
 	case PLL_1416X:
-		if (!pll->rate_table)
+		if (!pll_clk->rate_table)
 			init.ops = &clk_pll1416x_min_ops;
 		else
 			init.ops = &clk_pll1416x_ops;
diff --git a/drivers/clk/mediatek/clk-gate.c b/drivers/clk/mediatek/clk-gate.c
index 9628d4e7690b..85daf826619a 100644
--- a/drivers/clk/mediatek/clk-gate.c
+++ b/drivers/clk/mediatek/clk-gate.c
@@ -169,11 +169,10 @@ struct clk *mtk_clk_register_gate(
 		return ERR_PTR(-ENOMEM);
 
 	init.name = name;
-	init.flags = CLK_SET_RATE_PARENT;
+	init.flags = flags | CLK_SET_RATE_PARENT;
 	init.parent_names = parent_name ? &parent_name : NULL;
 	init.num_parents = parent_name ? 1 : 0;
 	init.ops = ops;
-	init.flags = flags;
 
 	cg->regmap = regmap;
 	cg->set_ofs = set_ofs;
diff --git a/drivers/clk/meson/clk-pll.c b/drivers/clk/meson/clk-pll.c
index 41e16dd7272a..7a14ac9b2fec 100644
--- a/drivers/clk/meson/clk-pll.c
+++ b/drivers/clk/meson/clk-pll.c
@@ -120,7 +120,7 @@ static bool meson_clk_pll_is_better(unsigned long rate,
 			return true;
 	} else {
 		/* Round down */
-		if (now < rate && best < now)
+		if (now <= rate && best < now)
 			return true;
 	}
 
diff --git a/drivers/clk/meson/g12a.c b/drivers/clk/meson/g12a.c
index 0e1ce8c03259..f7b11e1eeebe 100644
--- a/drivers/clk/meson/g12a.c
+++ b/drivers/clk/meson/g12a.c
@@ -960,14 +960,14 @@ static struct clk_regmap g12a_sd_emmc_c_clk0 = {
 /* VPU Clock */
 
 static const char * const g12a_vpu_parent_names[] = {
-	"fclk_div4", "fclk_div3", "fclk_div5", "fclk_div7",
+	"fclk_div3", "fclk_div4", "fclk_div5", "fclk_div7",
 	"mpll1", "vid_pll", "hifi_pll", "gp0_pll",
 };
 
 static struct clk_regmap g12a_vpu_0_sel = {
 	.data = &(struct clk_regmap_mux_data){
 		.offset = HHI_VPU_CLK_CNTL,
-		.mask = 0x3,
+		.mask = 0x7,
 		.shift = 9,
 	},
 	.hw.init = &(struct clk_init_data){
@@ -1011,7 +1011,7 @@ static struct clk_regmap g12a_vpu_0 = {
 static struct clk_regmap g12a_vpu_1_sel = {
 	.data = &(struct clk_regmap_mux_data){
 		.offset = HHI_VPU_CLK_CNTL,
-		.mask = 0x3,
+		.mask = 0x7,
 		.shift = 25,
 	},
 	.hw.init = &(struct clk_init_data){
diff --git a/drivers/clk/meson/gxbb.c b/drivers/clk/meson/gxbb.c
index 04df2e208ed6..29ffb4fde714 100644
--- a/drivers/clk/meson/gxbb.c
+++ b/drivers/clk/meson/gxbb.c
@@ -2216,6 +2216,7 @@ static struct clk_regmap gxbb_vdec_1_div = {
 		.offset = HHI_VDEC_CLK_CNTL,
 		.shift = 0,
 		.width = 7,
+		.flags = CLK_DIVIDER_ROUND_CLOSEST,
 	},
 	.hw.init = &(struct clk_init_data){
 		.name = "vdec_1_div",
@@ -2261,6 +2262,7 @@ static struct clk_regmap gxbb_vdec_hevc_div = {
 		.offset = HHI_VDEC2_CLK_CNTL,
 		.shift = 16,
 		.width = 7,
+		.flags = CLK_DIVIDER_ROUND_CLOSEST,
 	},
 	.hw.init = &(struct clk_init_data){
 		.name = "vdec_hevc_div",
diff --git a/drivers/clk/meson/vid-pll-div.c b/drivers/clk/meson/vid-pll-div.c
index 08bcc01c0923..daff235bc763 100644
--- a/drivers/clk/meson/vid-pll-div.c
+++ b/drivers/clk/meson/vid-pll-div.c
@@ -82,8 +82,8 @@ static unsigned long meson_vid_pll_div_recalc_rate(struct clk_hw *hw,
 	div = _get_table_val(meson_parm_read(clk->map, &pll_div->val),
 			     meson_parm_read(clk->map, &pll_div->sel));
 	if (!div || !div->divider) {
-		pr_info("%s: Invalid config value for vid_pll_div\n", __func__);
-		return parent_rate;
+		pr_debug("%s: Invalid config value for vid_pll_div\n", __func__);
+		return 0;
 	}
 
 	return DIV_ROUND_UP_ULL(parent_rate * div->multiplier, div->divider);
diff --git a/drivers/clk/sunxi-ng/ccu_nkmp.c b/drivers/clk/sunxi-ng/ccu_nkmp.c
index 9b49adb20d07..cbcdf664f336 100644
--- a/drivers/clk/sunxi-ng/ccu_nkmp.c
+++ b/drivers/clk/sunxi-ng/ccu_nkmp.c
@@ -167,7 +167,7 @@ static int ccu_nkmp_set_rate(struct clk_hw *hw, unsigned long rate,
 			   unsigned long parent_rate)
 {
 	struct ccu_nkmp *nkmp = hw_to_ccu_nkmp(hw);
-	u32 n_mask, k_mask, m_mask, p_mask;
+	u32 n_mask = 0, k_mask = 0, m_mask = 0, p_mask = 0;
 	struct _ccu_nkmp _nkmp;
 	unsigned long flags;
 	u32 reg;
@@ -186,10 +186,24 @@ static int ccu_nkmp_set_rate(struct clk_hw *hw, unsigned long rate,
 
 	ccu_nkmp_find_best(parent_rate, rate, &_nkmp);
 
-	n_mask = GENMASK(nkmp->n.width + nkmp->n.shift - 1, nkmp->n.shift);
-	k_mask = GENMASK(nkmp->k.width + nkmp->k.shift - 1, nkmp->k.shift);
-	m_mask = GENMASK(nkmp->m.width + nkmp->m.shift - 1, nkmp->m.shift);
-	p_mask = GENMASK(nkmp->p.width + nkmp->p.shift - 1, nkmp->p.shift);
+	/*
+	 * If width is 0, GENMASK() macro may not generate expected mask (0)
+	 * as it falls under undefined behaviour by C standard due to shifts
+	 * which are equal or greater than width of left operand. This can
+	 * be easily avoided by explicitly checking if width is 0.
+	 */
+	if (nkmp->n.width)
+		n_mask = GENMASK(nkmp->n.width + nkmp->n.shift - 1,
+				 nkmp->n.shift);
+	if (nkmp->k.width)
+		k_mask = GENMASK(nkmp->k.width + nkmp->k.shift - 1,
+				 nkmp->k.shift);
+	if (nkmp->m.width)
+		m_mask = GENMASK(nkmp->m.width + nkmp->m.shift - 1,
+				 nkmp->m.shift);
+	if (nkmp->p.width)
+		p_mask = GENMASK(nkmp->p.width + nkmp->p.shift - 1,
+				 nkmp->p.shift);
 
 	spin_lock_irqsave(nkmp->common.lock, flags);
 
diff --git a/drivers/clk/x86/clk-pmc-atom.c b/drivers/clk/x86/clk-pmc-atom.c
index d977193842df..19174835693b 100644
--- a/drivers/clk/x86/clk-pmc-atom.c
+++ b/drivers/clk/x86/clk-pmc-atom.c
@@ -165,7 +165,7 @@ static const struct clk_ops plt_clk_ops = {
 };
 
 static struct clk_plt *plt_clk_register(struct platform_device *pdev, int id,
-					void __iomem *base,
+					const struct pmc_clk_data *pmc_data,
 					const char **parent_names,
 					int num_parents)
 {
@@ -184,9 +184,17 @@ static struct clk_plt *plt_clk_register(struct platform_device *pdev, int id,
 	init.num_parents = num_parents;
 
 	pclk->hw.init = &init;
-	pclk->reg = base + PMC_CLK_CTL_OFFSET + id * PMC_CLK_CTL_SIZE;
+	pclk->reg = pmc_data->base + PMC_CLK_CTL_OFFSET + id * PMC_CLK_CTL_SIZE;
 	spin_lock_init(&pclk->lock);
 
+	/*
+	 * On some systems, the pmc_plt_clocks already enabled by the
+	 * firmware are being marked as critical to avoid them being
+	 * gated by the clock framework.
+	 */
+	if (pmc_data->critical && plt_clk_is_enabled(&pclk->hw))
+		init.flags |= CLK_IS_CRITICAL;
+
 	ret = devm_clk_hw_register(&pdev->dev, &pclk->hw);
 	if (ret) {
 		pclk = ERR_PTR(ret);
@@ -332,7 +340,7 @@ static int plt_clk_probe(struct platform_device *pdev)
 		return PTR_ERR(parent_names);
 
 	for (i = 0; i < PMC_CLK_NUM; i++) {
-		data->clks[i] = plt_clk_register(pdev, i, pmc_data->base,
+		data->clks[i] = plt_clk_register(pdev, i, pmc_data,
 						 parent_names, data->nparents);
 		if (IS_ERR(data->clks[i])) {
 			err = PTR_ERR(data->clks[i]);
diff --git a/drivers/clocksource/Kconfig b/drivers/clocksource/Kconfig
index 171502a356aa..4b3d143f0f8a 100644
--- a/drivers/clocksource/Kconfig
+++ b/drivers/clocksource/Kconfig
@@ -145,6 +145,7 @@ config VT8500_TIMER
 config NPCM7XX_TIMER
 	bool "NPCM7xx timer driver" if COMPILE_TEST
 	depends on HAS_IOMEM
+	select TIMER_OF
 	select CLKSRC_MMIO
 	help
 	  Enable 24-bit TIMER0 and TIMER1 counters in the NPCM7xx architecture,
diff --git a/drivers/clocksource/arm_arch_timer.c b/drivers/clocksource/arm_arch_timer.c
index aa4ec53281ce..b2a951a798e2 100644
--- a/drivers/clocksource/arm_arch_timer.c
+++ b/drivers/clocksource/arm_arch_timer.c
@@ -9,7 +9,7 @@
  * published by the Free Software Foundation.
  */
 
-#define pr_fmt(fmt)	"arm_arch_timer: " fmt
+#define pr_fmt(fmt) 	"arch_timer: " fmt
 
 #include <linux/init.h>
 #include <linux/kernel.h>
@@ -33,9 +33,6 @@
 
 #include <clocksource/arm_arch_timer.h>
 
-#undef pr_fmt
-#define pr_fmt(fmt) "arch_timer: " fmt
-
 #define CNTTIDR		0x08
 #define CNTTIDR_VIRT(n)	(BIT(1) << ((n) * 4))
 
@@ -152,6 +149,26 @@ u32 arch_timer_reg_read(int access, enum arch_timer_reg reg,
 	return val;
 }
 
+static u64 arch_counter_get_cntpct_stable(void)
+{
+	return __arch_counter_get_cntpct_stable();
+}
+
+static u64 arch_counter_get_cntpct(void)
+{
+	return __arch_counter_get_cntpct();
+}
+
+static u64 arch_counter_get_cntvct_stable(void)
+{
+	return __arch_counter_get_cntvct_stable();
+}
+
+static u64 arch_counter_get_cntvct(void)
+{
+	return __arch_counter_get_cntvct();
+}
+
 /*
  * Default to cp15 based access because arm64 uses this function for
  * sched_clock() before DT is probed and the cp15 method is guaranteed
@@ -319,13 +336,6 @@ static u64 notrace arm64_858921_read_cntvct_el0(void)
 }
 #endif
 
-#ifdef CONFIG_ARM64_ERRATUM_1188873
-static u64 notrace arm64_1188873_read_cntvct_el0(void)
-{
-	return read_sysreg(cntvct_el0);
-}
-#endif
-
 #ifdef CONFIG_SUN50I_ERRATUM_UNKNOWN1
 /*
  * The low bits of the counter registers are indeterminate while bit 10 or
@@ -372,8 +382,7 @@ static u32 notrace sun50i_a64_read_cntv_tval_el0(void)
 DEFINE_PER_CPU(const struct arch_timer_erratum_workaround *, timer_unstable_counter_workaround);
 EXPORT_SYMBOL_GPL(timer_unstable_counter_workaround);
 
-DEFINE_STATIC_KEY_FALSE(arch_timer_read_ool_enabled);
-EXPORT_SYMBOL_GPL(arch_timer_read_ool_enabled);
+static atomic_t timer_unstable_counter_workaround_in_use = ATOMIC_INIT(0);
 
 static void erratum_set_next_event_tval_generic(const int access, unsigned long evt,
 						struct clock_event_device *clk)
@@ -457,14 +466,6 @@ static const struct arch_timer_erratum_workaround ool_workarounds[] = {
 		.read_cntvct_el0 = arm64_858921_read_cntvct_el0,
 	},
 #endif
-#ifdef CONFIG_ARM64_ERRATUM_1188873
-	{
-		.match_type = ate_match_local_cap_id,
-		.id = (void *)ARM64_WORKAROUND_1188873,
-		.desc = "ARM erratum 1188873",
-		.read_cntvct_el0 = arm64_1188873_read_cntvct_el0,
-	},
-#endif
 #ifdef CONFIG_SUN50I_ERRATUM_UNKNOWN1
 	{
 		.match_type = ate_match_dt,
@@ -552,11 +553,8 @@ void arch_timer_enable_workaround(const struct arch_timer_erratum_workaround *wa
 			per_cpu(timer_unstable_counter_workaround, i) = wa;
 	}
 
-	/*
-	 * Use the locked version, as we're called from the CPU
-	 * hotplug framework. Otherwise, we end-up in deadlock-land.
-	 */
-	static_branch_enable_cpuslocked(&arch_timer_read_ool_enabled);
+	if (wa->read_cntvct_el0 || wa->read_cntpct_el0)
+		atomic_set(&timer_unstable_counter_workaround_in_use, 1);
 
 	/*
 	 * Don't use the vdso fastpath if errata require using the
@@ -573,7 +571,7 @@ void arch_timer_enable_workaround(const struct arch_timer_erratum_workaround *wa
 static void arch_timer_check_ool_workaround(enum arch_timer_erratum_match_type type,
 					    void *arg)
 {
-	const struct arch_timer_erratum_workaround *wa;
+	const struct arch_timer_erratum_workaround *wa, *__wa;
 	ate_match_fn_t match_fn = NULL;
 	bool local = false;
 
@@ -597,53 +595,32 @@ static void arch_timer_check_ool_workaround(enum arch_timer_erratum_match_type t
 	if (!wa)
 		return;
 
-	if (needs_unstable_timer_counter_workaround()) {
-		const struct arch_timer_erratum_workaround *__wa;
-		__wa = __this_cpu_read(timer_unstable_counter_workaround);
-		if (__wa && wa != __wa)
-			pr_warn("Can't enable workaround for %s (clashes with %s\n)",
-				wa->desc, __wa->desc);
+	__wa = __this_cpu_read(timer_unstable_counter_workaround);
+	if (__wa && wa != __wa)
+		pr_warn("Can't enable workaround for %s (clashes with %s\n)",
+			wa->desc, __wa->desc);
 
-		if (__wa)
-			return;
-	}
+	if (__wa)
+		return;
 
 	arch_timer_enable_workaround(wa, local);
 	pr_info("Enabling %s workaround for %s\n",
 		local ? "local" : "global", wa->desc);
 }
 
-#define erratum_handler(fn, r, ...)					\
-({									\
-	bool __val;							\
-	if (needs_unstable_timer_counter_workaround()) {		\
-		const struct arch_timer_erratum_workaround *__wa;	\
-		__wa = __this_cpu_read(timer_unstable_counter_workaround); \
-		if (__wa && __wa->fn) {					\
-			r = __wa->fn(__VA_ARGS__);			\
-			__val = true;					\
-		} else {						\
-			__val = false;					\
-		}							\
-	} else {							\
-		__val = false;						\
-	}								\
-	__val;								\
-})
-
 static bool arch_timer_this_cpu_has_cntvct_wa(void)
 {
-	const struct arch_timer_erratum_workaround *wa;
+	return has_erratum_handler(read_cntvct_el0);
+}
 
-	wa = __this_cpu_read(timer_unstable_counter_workaround);
-	return wa && wa->read_cntvct_el0;
+static bool arch_timer_counter_has_wa(void)
+{
+	return atomic_read(&timer_unstable_counter_workaround_in_use);
 }
 #else
 #define arch_timer_check_ool_workaround(t,a)		do { } while(0)
-#define erratum_set_next_event_tval_virt(...)		({BUG(); 0;})
-#define erratum_set_next_event_tval_phys(...)		({BUG(); 0;})
-#define erratum_handler(fn, r, ...)			({false;})
 #define arch_timer_this_cpu_has_cntvct_wa()		({false;})
+#define arch_timer_counter_has_wa()			({false;})
 #endif /* CONFIG_ARM_ARCH_TIMER_OOL_WORKAROUND */
 
 static __always_inline irqreturn_t timer_handler(const int access,
@@ -736,11 +713,6 @@ static __always_inline void set_next_event(const int access, unsigned long evt,
 static int arch_timer_set_next_event_virt(unsigned long evt,
 					  struct clock_event_device *clk)
 {
-	int ret;
-
-	if (erratum_handler(set_next_event_virt, ret, evt, clk))
-		return ret;
-
 	set_next_event(ARCH_TIMER_VIRT_ACCESS, evt, clk);
 	return 0;
 }
@@ -748,11 +720,6 @@ static int arch_timer_set_next_event_virt(unsigned long evt,
 static int arch_timer_set_next_event_phys(unsigned long evt,
 					  struct clock_event_device *clk)
 {
-	int ret;
-
-	if (erratum_handler(set_next_event_phys, ret, evt, clk))
-		return ret;
-
 	set_next_event(ARCH_TIMER_PHYS_ACCESS, evt, clk);
 	return 0;
 }
@@ -777,6 +744,10 @@ static void __arch_timer_setup(unsigned type,
 	clk->features = CLOCK_EVT_FEAT_ONESHOT;
 
 	if (type == ARCH_TIMER_TYPE_CP15) {
+		typeof(clk->set_next_event) sne;
+
+		arch_timer_check_ool_workaround(ate_match_local_cap_id, NULL);
+
 		if (arch_timer_c3stop)
 			clk->features |= CLOCK_EVT_FEAT_C3STOP;
 		clk->name = "arch_sys_timer";
@@ -787,20 +758,20 @@ static void __arch_timer_setup(unsigned type,
 		case ARCH_TIMER_VIRT_PPI:
 			clk->set_state_shutdown = arch_timer_shutdown_virt;
 			clk->set_state_oneshot_stopped = arch_timer_shutdown_virt;
-			clk->set_next_event = arch_timer_set_next_event_virt;
+			sne = erratum_handler(set_next_event_virt);
 			break;
 		case ARCH_TIMER_PHYS_SECURE_PPI:
 		case ARCH_TIMER_PHYS_NONSECURE_PPI:
 		case ARCH_TIMER_HYP_PPI:
 			clk->set_state_shutdown = arch_timer_shutdown_phys;
 			clk->set_state_oneshot_stopped = arch_timer_shutdown_phys;
-			clk->set_next_event = arch_timer_set_next_event_phys;
+			sne = erratum_handler(set_next_event_phys);
 			break;
 		default:
 			BUG();
 		}
 
-		arch_timer_check_ool_workaround(ate_match_local_cap_id, NULL);
+		clk->set_next_event = sne;
 	} else {
 		clk->features |= CLOCK_EVT_FEAT_DYNIRQ;
 		clk->name = "arch_mem_timer";
@@ -833,7 +804,11 @@ static void arch_timer_evtstrm_enable(int divider)
 	cntkctl |= (divider << ARCH_TIMER_EVT_TRIGGER_SHIFT)
 			| ARCH_TIMER_VIRT_EVT_EN;
 	arch_timer_set_cntkctl(cntkctl);
+#ifdef CONFIG_ARM64
+	cpu_set_named_feature(EVTSTRM);
+#else
 	elf_hwcap |= HWCAP_EVTSTRM;
+#endif
 #ifdef CONFIG_COMPAT
 	compat_elf_hwcap |= COMPAT_HWCAP_EVTSTRM;
 #endif
@@ -998,12 +973,22 @@ static void __init arch_counter_register(unsigned type)
 
 	/* Register the CP15 based counter if we have one */
 	if (type & ARCH_TIMER_TYPE_CP15) {
+		u64 (*rd)(void);
+
 		if ((IS_ENABLED(CONFIG_ARM64) && !is_hyp_mode_available()) ||
-		    arch_timer_uses_ppi == ARCH_TIMER_VIRT_PPI)
-			arch_timer_read_counter = arch_counter_get_cntvct;
-		else
-			arch_timer_read_counter = arch_counter_get_cntpct;
+		    arch_timer_uses_ppi == ARCH_TIMER_VIRT_PPI) {
+			if (arch_timer_counter_has_wa())
+				rd = arch_counter_get_cntvct_stable;
+			else
+				rd = arch_counter_get_cntvct;
+		} else {
+			if (arch_timer_counter_has_wa())
+				rd = arch_counter_get_cntpct_stable;
+			else
+				rd = arch_counter_get_cntpct;
+		}
 
+		arch_timer_read_counter = rd;
 		clocksource_counter.archdata.vdso_direct = vdso_default;
 	} else {
 		arch_timer_read_counter = arch_counter_get_cntvct_mem;
@@ -1055,7 +1040,11 @@ static int arch_timer_cpu_pm_notify(struct notifier_block *self,
 	} else if (action == CPU_PM_ENTER_FAILED || action == CPU_PM_EXIT) {
 		arch_timer_set_cntkctl(__this_cpu_read(saved_cntkctl));
 
+#ifdef CONFIG_ARM64
+		if (cpu_have_named_feature(EVTSTRM))
+#else
 		if (elf_hwcap & HWCAP_EVTSTRM)
+#endif
 			cpumask_set_cpu(smp_processor_id(), &evtstrm_available);
 	}
 	return NOTIFY_OK;
diff --git a/drivers/clocksource/timer-oxnas-rps.c b/drivers/clocksource/timer-oxnas-rps.c
index eed6feff8b5f..30c6f4ce672b 100644
--- a/drivers/clocksource/timer-oxnas-rps.c
+++ b/drivers/clocksource/timer-oxnas-rps.c
@@ -296,4 +296,4 @@ err_alloc:
 TIMER_OF_DECLARE(ox810se_rps,
 		       "oxsemi,ox810se-rps-timer", oxnas_rps_timer_init);
 TIMER_OF_DECLARE(ox820_rps,
-		       "oxsemi,ox820se-rps-timer", oxnas_rps_timer_init);
+		       "oxsemi,ox820-rps-timer", oxnas_rps_timer_init);
diff --git a/drivers/clocksource/timer-ti-dm.c b/drivers/clocksource/timer-ti-dm.c
index 3352da6ed61f..ee8ec5a8cb16 100644
--- a/drivers/clocksource/timer-ti-dm.c
+++ b/drivers/clocksource/timer-ti-dm.c
@@ -585,34 +585,6 @@ static int omap_dm_timer_set_load(struct omap_dm_timer *timer, int autoreload,
 	return 0;
 }
 
-/* Optimized set_load which removes costly spin wait in timer_start */
-static int omap_dm_timer_set_load_start(struct omap_dm_timer *timer,
-					int autoreload, unsigned int load)
-{
-	u32 l;
-
-	if (unlikely(!timer))
-		return -EINVAL;
-
-	omap_dm_timer_enable(timer);
-
-	l = omap_dm_timer_read_reg(timer, OMAP_TIMER_CTRL_REG);
-	if (autoreload) {
-		l |= OMAP_TIMER_CTRL_AR;
-		omap_dm_timer_write_reg(timer, OMAP_TIMER_LOAD_REG, load);
-	} else {
-		l &= ~OMAP_TIMER_CTRL_AR;
-	}
-	l |= OMAP_TIMER_CTRL_ST;
-
-	__omap_dm_timer_load_start(timer, l, load, timer->posted);
-
-	/* Save the context */
-	timer->context.tclr = l;
-	timer->context.tldr = load;
-	timer->context.tcrr = load;
-	return 0;
-}
 static int omap_dm_timer_set_match(struct omap_dm_timer *timer, int enable,
 				   unsigned int match)
 {
diff --git a/drivers/cpufreq/Kconfig b/drivers/cpufreq/Kconfig
index b22e6bba71f1..4d2b33a30292 100644
--- a/drivers/cpufreq/Kconfig
+++ b/drivers/cpufreq/Kconfig
@@ -26,10 +26,6 @@ config CPU_FREQ_GOV_COMMON
 	select IRQ_WORK
 	bool
 
-config CPU_FREQ_BOOST_SW
-	bool
-	depends on THERMAL
-
 config CPU_FREQ_STAT
 	bool "CPU frequency transition statistics"
 	help
diff --git a/drivers/cpufreq/acpi-cpufreq.c b/drivers/cpufreq/acpi-cpufreq.c
index c72258a44ba4..73bb2aafb1a8 100644
--- a/drivers/cpufreq/acpi-cpufreq.c
+++ b/drivers/cpufreq/acpi-cpufreq.c
@@ -366,7 +366,7 @@ static u32 get_cur_val(const struct cpumask *mask, struct acpi_cpufreq_data *dat
 
 	val = drv_read(data, mask);
 
-	pr_debug("get_cur_val = %u\n", val);
+	pr_debug("%s = %u\n", __func__, val);
 
 	return val;
 }
@@ -378,7 +378,7 @@ static unsigned int get_cur_freq_on_cpu(unsigned int cpu)
 	unsigned int freq;
 	unsigned int cached_freq;
 
-	pr_debug("get_cur_freq_on_cpu (%d)\n", cpu);
+	pr_debug("%s (%d)\n", __func__, cpu);
 
 	policy = cpufreq_cpu_get_raw(cpu);
 	if (unlikely(!policy))
@@ -458,8 +458,7 @@ static int acpi_cpufreq_target(struct cpufreq_policy *policy,
 	if (acpi_pstate_strict) {
 		if (!check_freqs(policy, mask,
 				 policy->freq_table[index].frequency)) {
-			pr_debug("acpi_cpufreq_target failed (%d)\n",
-				policy->cpu);
+			pr_debug("%s (%d)\n", __func__, policy->cpu);
 			result = -EAGAIN;
 		}
 	}
@@ -573,7 +572,7 @@ static int cpufreq_boost_down_prep(unsigned int cpu)
 static int __init acpi_cpufreq_early_init(void)
 {
 	unsigned int i;
-	pr_debug("acpi_cpufreq_early_init\n");
+	pr_debug("%s\n", __func__);
 
 	acpi_perf_data = alloc_percpu(struct acpi_processor_performance);
 	if (!acpi_perf_data) {
@@ -657,7 +656,7 @@ static int acpi_cpufreq_cpu_init(struct cpufreq_policy *policy)
 	static int blacklisted;
 #endif
 
-	pr_debug("acpi_cpufreq_cpu_init\n");
+	pr_debug("%s\n", __func__);
 
 #ifdef CONFIG_SMP
 	if (blacklisted)
@@ -856,7 +855,7 @@ static int acpi_cpufreq_cpu_exit(struct cpufreq_policy *policy)
 {
 	struct acpi_cpufreq_data *data = policy->driver_data;
 
-	pr_debug("acpi_cpufreq_cpu_exit\n");
+	pr_debug("%s\n", __func__);
 
 	policy->fast_switch_possible = false;
 	policy->driver_data = NULL;
@@ -881,7 +880,7 @@ static int acpi_cpufreq_resume(struct cpufreq_policy *policy)
 {
 	struct acpi_cpufreq_data *data = policy->driver_data;
 
-	pr_debug("acpi_cpufreq_resume\n");
+	pr_debug("%s\n", __func__);
 
 	data->resume = 1;
 
@@ -954,7 +953,7 @@ static int __init acpi_cpufreq_init(void)
 	if (cpufreq_get_current_driver())
 		return -EEXIST;
 
-	pr_debug("acpi_cpufreq_init\n");
+	pr_debug("%s\n", __func__);
 
 	ret = acpi_cpufreq_early_init();
 	if (ret)
@@ -991,7 +990,7 @@ static int __init acpi_cpufreq_init(void)
 
 static void __exit acpi_cpufreq_exit(void)
 {
-	pr_debug("acpi_cpufreq_exit\n");
+	pr_debug("%s\n", __func__);
 
 	acpi_cpufreq_boost_exit();
 
diff --git a/drivers/cpufreq/amd_freq_sensitivity.c b/drivers/cpufreq/amd_freq_sensitivity.c
index 4ac7c3cf34be..6927a8c0e748 100644
--- a/drivers/cpufreq/amd_freq_sensitivity.c
+++ b/drivers/cpufreq/amd_freq_sensitivity.c
@@ -124,7 +124,7 @@ static int __init amd_freq_sensitivity_init(void)
 			PCI_DEVICE_ID_AMD_KERNCZ_SMBUS, NULL);
 
 	if (!pcidev) {
-		if (!static_cpu_has(X86_FEATURE_PROC_FEEDBACK))
+		if (!boot_cpu_has(X86_FEATURE_PROC_FEEDBACK))
 			return -ENODEV;
 	}
 
diff --git a/drivers/cpufreq/armada-37xx-cpufreq.c b/drivers/cpufreq/armada-37xx-cpufreq.c
index 75491fc841a6..0df16eb1eb3c 100644
--- a/drivers/cpufreq/armada-37xx-cpufreq.c
+++ b/drivers/cpufreq/armada-37xx-cpufreq.c
@@ -359,11 +359,11 @@ static int __init armada37xx_cpufreq_driver_init(void)
 	struct armada_37xx_dvfs *dvfs;
 	struct platform_device *pdev;
 	unsigned long freq;
-	unsigned int cur_frequency;
+	unsigned int cur_frequency, base_frequency;
 	struct regmap *nb_pm_base, *avs_base;
 	struct device *cpu_dev;
 	int load_lvl, ret;
-	struct clk *clk;
+	struct clk *clk, *parent;
 
 	nb_pm_base =
 		syscon_regmap_lookup_by_compatible("marvell,armada-3700-nb-pm");
@@ -399,6 +399,22 @@ static int __init armada37xx_cpufreq_driver_init(void)
 		return PTR_ERR(clk);
 	}
 
+	parent = clk_get_parent(clk);
+	if (IS_ERR(parent)) {
+		dev_err(cpu_dev, "Cannot get parent clock for CPU0\n");
+		clk_put(clk);
+		return PTR_ERR(parent);
+	}
+
+	/* Get parent CPU frequency */
+	base_frequency =  clk_get_rate(parent);
+
+	if (!base_frequency) {
+		dev_err(cpu_dev, "Failed to get parent clock rate for CPU\n");
+		clk_put(clk);
+		return -EINVAL;
+	}
+
 	/* Get nominal (current) CPU frequency */
 	cur_frequency = clk_get_rate(clk);
 	if (!cur_frequency) {
@@ -431,7 +447,7 @@ static int __init armada37xx_cpufreq_driver_init(void)
 	for (load_lvl = ARMADA_37XX_DVFS_LOAD_0; load_lvl < LOAD_LEVEL_NR;
 	     load_lvl++) {
 		unsigned long u_volt = avs_map[dvfs->avs[load_lvl]] * 1000;
-		freq = cur_frequency / dvfs->divider[load_lvl];
+		freq = base_frequency / dvfs->divider[load_lvl];
 		ret = dev_pm_opp_add(cpu_dev, freq, u_volt);
 		if (ret)
 			goto remove_opp;
diff --git a/drivers/cpufreq/armada-8k-cpufreq.c b/drivers/cpufreq/armada-8k-cpufreq.c
index b3f4bd647e9b..988ebc326bdb 100644
--- a/drivers/cpufreq/armada-8k-cpufreq.c
+++ b/drivers/cpufreq/armada-8k-cpufreq.c
@@ -132,6 +132,7 @@ static int __init armada_8k_cpufreq_init(void)
 		of_node_put(node);
 		return -ENODEV;
 	}
+	of_node_put(node);
 
 	nb_cpus = num_possible_cpus();
 	freq_tables = kcalloc(nb_cpus, sizeof(*freq_tables), GFP_KERNEL);
diff --git a/drivers/cpufreq/cpufreq.c b/drivers/cpufreq/cpufreq.c
index e10922709d13..7ea217c88c2e 100644
--- a/drivers/cpufreq/cpufreq.c
+++ b/drivers/cpufreq/cpufreq.c
@@ -34,11 +34,6 @@
 
 static LIST_HEAD(cpufreq_policy_list);
 
-static inline bool policy_is_inactive(struct cpufreq_policy *policy)
-{
-	return cpumask_empty(policy->cpus);
-}
-
 /* Macros to iterate over CPU policies */
 #define for_each_suitable_policy(__policy, __active)			 \
 	list_for_each_entry(__policy, &cpufreq_policy_list, policy_list) \
@@ -250,6 +245,51 @@ void cpufreq_cpu_put(struct cpufreq_policy *policy)
 }
 EXPORT_SYMBOL_GPL(cpufreq_cpu_put);
 
+/**
+ * cpufreq_cpu_release - Unlock a policy and decrement its usage counter.
+ * @policy: cpufreq policy returned by cpufreq_cpu_acquire().
+ */
+void cpufreq_cpu_release(struct cpufreq_policy *policy)
+{
+	if (WARN_ON(!policy))
+		return;
+
+	lockdep_assert_held(&policy->rwsem);
+
+	up_write(&policy->rwsem);
+
+	cpufreq_cpu_put(policy);
+}
+
+/**
+ * cpufreq_cpu_acquire - Find policy for a CPU, mark it as busy and lock it.
+ * @cpu: CPU to find the policy for.
+ *
+ * Call cpufreq_cpu_get() to get a reference on the cpufreq policy for @cpu and
+ * if the policy returned by it is not NULL, acquire its rwsem for writing.
+ * Return the policy if it is active or release it and return NULL otherwise.
+ *
+ * The policy returned by this function has to be released with the help of
+ * cpufreq_cpu_release() in order to release its rwsem and balance its usage
+ * counter properly.
+ */
+struct cpufreq_policy *cpufreq_cpu_acquire(unsigned int cpu)
+{
+	struct cpufreq_policy *policy = cpufreq_cpu_get(cpu);
+
+	if (!policy)
+		return NULL;
+
+	down_write(&policy->rwsem);
+
+	if (policy_is_inactive(policy)) {
+		cpufreq_cpu_release(policy);
+		return NULL;
+	}
+
+	return policy;
+}
+
 /*********************************************************************
  *            EXTERNALLY AFFECTING FREQUENCY CHANGES                 *
  *********************************************************************/
@@ -669,9 +709,6 @@ static ssize_t show_scaling_cur_freq(struct cpufreq_policy *policy, char *buf)
 	return ret;
 }
 
-static int cpufreq_set_policy(struct cpufreq_policy *policy,
-				struct cpufreq_policy *new_policy);
-
 /**
  * cpufreq_per_cpu_attr_write() / store_##file_name() - sysfs write access
  */
@@ -857,11 +894,9 @@ static ssize_t show_bios_limit(struct cpufreq_policy *policy, char *buf)
 {
 	unsigned int limit;
 	int ret;
-	if (cpufreq_driver->bios_limit) {
-		ret = cpufreq_driver->bios_limit(policy->cpu, &limit);
-		if (!ret)
-			return sprintf(buf, "%u\n", limit);
-	}
+	ret = cpufreq_driver->bios_limit(policy->cpu, &limit);
+	if (!ret)
+		return sprintf(buf, "%u\n", limit);
 	return sprintf(buf, "%u\n", policy->cpuinfo.max_freq);
 }
 
@@ -1098,6 +1133,7 @@ static struct cpufreq_policy *cpufreq_policy_alloc(unsigned int cpu)
 				   cpufreq_global_kobject, "policy%u", cpu);
 	if (ret) {
 		pr_err("%s: failed to init policy->kobj: %d\n", __func__, ret);
+		kobject_put(&policy->kobj);
 		goto err_free_real_cpus;
 	}
 
@@ -1550,7 +1586,7 @@ static unsigned int __cpufreq_get(struct cpufreq_policy *policy)
 {
 	unsigned int ret_freq = 0;
 
-	if (unlikely(policy_is_inactive(policy)) || !cpufreq_driver->get)
+	if (unlikely(policy_is_inactive(policy)))
 		return ret_freq;
 
 	ret_freq = cpufreq_driver->get(policy->cpu);
@@ -1588,7 +1624,8 @@ unsigned int cpufreq_get(unsigned int cpu)
 
 	if (policy) {
 		down_read(&policy->rwsem);
-		ret_freq = __cpufreq_get(policy);
+		if (cpufreq_driver->get)
+			ret_freq = __cpufreq_get(policy);
 		up_read(&policy->rwsem);
 
 		cpufreq_cpu_put(policy);
@@ -2229,8 +2266,8 @@ EXPORT_SYMBOL(cpufreq_get_policy);
  *
  * The cpuinfo part of @policy is not updated by this function.
  */
-static int cpufreq_set_policy(struct cpufreq_policy *policy,
-			      struct cpufreq_policy *new_policy)
+int cpufreq_set_policy(struct cpufreq_policy *policy,
+		       struct cpufreq_policy *new_policy)
 {
 	struct cpufreq_governor *old_gov;
 	int ret;
@@ -2337,17 +2374,12 @@ static int cpufreq_set_policy(struct cpufreq_policy *policy,
  */
 void cpufreq_update_policy(unsigned int cpu)
 {
-	struct cpufreq_policy *policy = cpufreq_cpu_get(cpu);
+	struct cpufreq_policy *policy = cpufreq_cpu_acquire(cpu);
 	struct cpufreq_policy new_policy;
 
 	if (!policy)
 		return;
 
-	down_write(&policy->rwsem);
-
-	if (policy_is_inactive(policy))
-		goto unlock;
-
 	/*
 	 * BIOS might change freq behind our back
 	 * -> ask driver for current freq and notify governors about a change
@@ -2364,12 +2396,26 @@ void cpufreq_update_policy(unsigned int cpu)
 	cpufreq_set_policy(policy, &new_policy);
 
 unlock:
-	up_write(&policy->rwsem);
-
-	cpufreq_cpu_put(policy);
+	cpufreq_cpu_release(policy);
 }
 EXPORT_SYMBOL(cpufreq_update_policy);
 
+/**
+ * cpufreq_update_limits - Update policy limits for a given CPU.
+ * @cpu: CPU to update the policy limits for.
+ *
+ * Invoke the driver's ->update_limits callback if present or call
+ * cpufreq_update_policy() for @cpu.
+ */
+void cpufreq_update_limits(unsigned int cpu)
+{
+	if (cpufreq_driver->update_limits)
+		cpufreq_driver->update_limits(cpu);
+	else
+		cpufreq_update_policy(cpu);
+}
+EXPORT_SYMBOL_GPL(cpufreq_update_limits);
+
 /*********************************************************************
  *               BOOST						     *
  *********************************************************************/
@@ -2426,7 +2472,7 @@ int cpufreq_boost_trigger_state(int state)
 
 static bool cpufreq_boost_supported(void)
 {
-	return likely(cpufreq_driver) && cpufreq_driver->set_boost;
+	return cpufreq_driver->set_boost;
 }
 
 static int create_boost_sysfs_file(void)
diff --git a/drivers/cpufreq/cpufreq_governor.c b/drivers/cpufreq/cpufreq_governor.c
index ffa9adeaba31..9d1d9bf02710 100644
--- a/drivers/cpufreq/cpufreq_governor.c
+++ b/drivers/cpufreq/cpufreq_governor.c
@@ -459,6 +459,8 @@ int cpufreq_dbs_governor_init(struct cpufreq_policy *policy)
 	/* Failure, so roll back. */
 	pr_err("initialization failed (dbs_data kobject init error %d)\n", ret);
 
+	kobject_put(&dbs_data->attr_set.kobj);
+
 	policy->governor_data = NULL;
 
 	if (!have_governor_per_policy())
diff --git a/drivers/cpufreq/cpufreq_stats.c b/drivers/cpufreq/cpufreq_stats.c
index e2db5581489a..08b192eb22c6 100644
--- a/drivers/cpufreq/cpufreq_stats.c
+++ b/drivers/cpufreq/cpufreq_stats.c
@@ -14,7 +14,6 @@
 #include <linux/module.h>
 #include <linux/slab.h>
 
-static DEFINE_SPINLOCK(cpufreq_stats_lock);
 
 struct cpufreq_stats {
 	unsigned int total_trans;
@@ -23,6 +22,7 @@ struct cpufreq_stats {
 	unsigned int state_num;
 	unsigned int last_index;
 	u64 *time_in_state;
+	spinlock_t lock;
 	unsigned int *freq_table;
 	unsigned int *trans_table;
 };
@@ -39,12 +39,12 @@ static void cpufreq_stats_clear_table(struct cpufreq_stats *stats)
 {
 	unsigned int count = stats->max_state;
 
-	spin_lock(&cpufreq_stats_lock);
+	spin_lock(&stats->lock);
 	memset(stats->time_in_state, 0, count * sizeof(u64));
 	memset(stats->trans_table, 0, count * count * sizeof(int));
 	stats->last_time = get_jiffies_64();
 	stats->total_trans = 0;
-	spin_unlock(&cpufreq_stats_lock);
+	spin_unlock(&stats->lock);
 }
 
 static ssize_t show_total_trans(struct cpufreq_policy *policy, char *buf)
@@ -62,9 +62,9 @@ static ssize_t show_time_in_state(struct cpufreq_policy *policy, char *buf)
 	if (policy->fast_switch_enabled)
 		return 0;
 
-	spin_lock(&cpufreq_stats_lock);
+	spin_lock(&stats->lock);
 	cpufreq_stats_update(stats);
-	spin_unlock(&cpufreq_stats_lock);
+	spin_unlock(&stats->lock);
 
 	for (i = 0; i < stats->state_num; i++) {
 		len += sprintf(buf + len, "%u %llu\n", stats->freq_table[i],
@@ -211,6 +211,7 @@ void cpufreq_stats_create_table(struct cpufreq_policy *policy)
 	stats->state_num = i;
 	stats->last_time = get_jiffies_64();
 	stats->last_index = freq_table_get_index(stats, policy->cur);
+	spin_lock_init(&stats->lock);
 
 	policy->stats = stats;
 	ret = sysfs_create_group(&policy->kobj, &stats_attr_group);
@@ -242,11 +243,11 @@ void cpufreq_stats_record_transition(struct cpufreq_policy *policy,
 	if (old_index == -1 || new_index == -1 || old_index == new_index)
 		return;
 
-	spin_lock(&cpufreq_stats_lock);
+	spin_lock(&stats->lock);
 	cpufreq_stats_update(stats);
 
 	stats->last_index = new_index;
 	stats->trans_table[old_index * stats->max_state + new_index]++;
 	stats->total_trans++;
-	spin_unlock(&cpufreq_stats_lock);
+	spin_unlock(&stats->lock);
 }
diff --git a/drivers/cpufreq/freq_table.c b/drivers/cpufreq/freq_table.c
index 3a8cc99e6815..e7be0af3199f 100644
--- a/drivers/cpufreq/freq_table.c
+++ b/drivers/cpufreq/freq_table.c
@@ -290,9 +290,6 @@ EXPORT_SYMBOL_GPL(cpufreq_freq_attr_scaling_boost_freqs);
 
 struct freq_attr *cpufreq_generic_attr[] = {
 	&cpufreq_freq_attr_scaling_available_freqs,
-#ifdef CONFIG_CPU_FREQ_BOOST_SW
-	&cpufreq_freq_attr_scaling_boost_freqs,
-#endif
 	NULL,
 };
 EXPORT_SYMBOL_GPL(cpufreq_generic_attr);
diff --git a/drivers/cpufreq/imx6q-cpufreq.c b/drivers/cpufreq/imx6q-cpufreq.c
index a4ff09f91c8f..3e17560b1efe 100644
--- a/drivers/cpufreq/imx6q-cpufreq.c
+++ b/drivers/cpufreq/imx6q-cpufreq.c
@@ -388,11 +388,11 @@ static int imx6q_cpufreq_probe(struct platform_device *pdev)
 		ret = imx6ul_opp_check_speed_grading(cpu_dev);
 		if (ret) {
 			if (ret == -EPROBE_DEFER)
-				return ret;
+				goto put_node;
 
 			dev_err(cpu_dev, "failed to read ocotp: %d\n",
 				ret);
-			return ret;
+			goto put_node;
 		}
 	} else {
 		imx6q_opp_check_speed_grading(cpu_dev);
diff --git a/drivers/cpufreq/intel_pstate.c b/drivers/cpufreq/intel_pstate.c
index e22f0dbaebb1..34b54df41aaa 100644
--- a/drivers/cpufreq/intel_pstate.c
+++ b/drivers/cpufreq/intel_pstate.c
@@ -179,6 +179,7 @@ struct vid_data {
  *			based on the MSR_IA32_MISC_ENABLE value and whether or
  *			not the maximum reported turbo P-state is different from
  *			the maximum reported non-turbo one.
+ * @turbo_disabled_mf:	The @turbo_disabled value reflected by cpuinfo.max_freq.
  * @min_perf_pct:	Minimum capacity limit in percent of the maximum turbo
  *			P-state capacity.
  * @max_perf_pct:	Maximum capacity limit in percent of the maximum turbo
@@ -187,6 +188,7 @@ struct vid_data {
 struct global_params {
 	bool no_turbo;
 	bool turbo_disabled;
+	bool turbo_disabled_mf;
 	int max_perf_pct;
 	int min_perf_pct;
 };
@@ -385,7 +387,10 @@ static int intel_pstate_get_cppc_guranteed(int cpu)
 	if (ret)
 		return ret;
 
-	return cppc_perf.guaranteed_perf;
+	if (cppc_perf.guaranteed_perf)
+		return cppc_perf.guaranteed_perf;
+
+	return cppc_perf.nominal_perf;
 }
 
 #else /* CONFIG_ACPI_CPPC_LIB */
@@ -522,7 +527,7 @@ static s16 intel_pstate_get_epb(struct cpudata *cpu_data)
 	u64 epb;
 	int ret;
 
-	if (!static_cpu_has(X86_FEATURE_EPB))
+	if (!boot_cpu_has(X86_FEATURE_EPB))
 		return -ENXIO;
 
 	ret = rdmsrl_on_cpu(cpu_data->cpu, MSR_IA32_ENERGY_PERF_BIAS, &epb);
@@ -536,7 +541,7 @@ static s16 intel_pstate_get_epp(struct cpudata *cpu_data, u64 hwp_req_data)
 {
 	s16 epp;
 
-	if (static_cpu_has(X86_FEATURE_HWP_EPP)) {
+	if (boot_cpu_has(X86_FEATURE_HWP_EPP)) {
 		/*
 		 * When hwp_req_data is 0, means that caller didn't read
 		 * MSR_HWP_REQUEST, so need to read and get EPP.
@@ -561,7 +566,7 @@ static int intel_pstate_set_epb(int cpu, s16 pref)
 	u64 epb;
 	int ret;
 
-	if (!static_cpu_has(X86_FEATURE_EPB))
+	if (!boot_cpu_has(X86_FEATURE_EPB))
 		return -ENXIO;
 
 	ret = rdmsrl_on_cpu(cpu, MSR_IA32_ENERGY_PERF_BIAS, &epb);
@@ -609,7 +614,7 @@ static int intel_pstate_get_energy_pref_index(struct cpudata *cpu_data)
 	if (epp < 0)
 		return epp;
 
-	if (static_cpu_has(X86_FEATURE_HWP_EPP)) {
+	if (boot_cpu_has(X86_FEATURE_HWP_EPP)) {
 		if (epp == HWP_EPP_PERFORMANCE)
 			return 1;
 		if (epp <= HWP_EPP_BALANCE_PERFORMANCE)
@@ -618,7 +623,7 @@ static int intel_pstate_get_energy_pref_index(struct cpudata *cpu_data)
 			return 3;
 		else
 			return 4;
-	} else if (static_cpu_has(X86_FEATURE_EPB)) {
+	} else if (boot_cpu_has(X86_FEATURE_EPB)) {
 		/*
 		 * Range:
 		 *	0x00-0x03	:	Performance
@@ -646,7 +651,7 @@ static int intel_pstate_set_energy_pref_index(struct cpudata *cpu_data,
 
 	mutex_lock(&intel_pstate_limits_lock);
 
-	if (static_cpu_has(X86_FEATURE_HWP_EPP)) {
+	if (boot_cpu_has(X86_FEATURE_HWP_EPP)) {
 		u64 value;
 
 		ret = rdmsrl_on_cpu(cpu_data->cpu, MSR_HWP_REQUEST, &value);
@@ -821,7 +826,7 @@ static void intel_pstate_hwp_set(unsigned int cpu)
 		epp = cpu_data->epp_powersave;
 	}
 update_epp:
-	if (static_cpu_has(X86_FEATURE_HWP_EPP)) {
+	if (boot_cpu_has(X86_FEATURE_HWP_EPP)) {
 		value &= ~GENMASK_ULL(31, 24);
 		value |= (u64)epp << 24;
 	} else {
@@ -846,7 +851,7 @@ static void intel_pstate_hwp_force_min_perf(int cpu)
 	value |= HWP_MIN_PERF(min_perf);
 
 	/* Set EPP/EPB to min */
-	if (static_cpu_has(X86_FEATURE_HWP_EPP))
+	if (boot_cpu_has(X86_FEATURE_HWP_EPP))
 		value |= HWP_ENERGY_PERF_PREFERENCE(HWP_EPP_POWERSAVE);
 	else
 		intel_pstate_set_epb(cpu, HWP_EPP_BALANCE_POWERSAVE);
@@ -894,6 +899,48 @@ static void intel_pstate_update_policies(void)
 		cpufreq_update_policy(cpu);
 }
 
+static void intel_pstate_update_max_freq(unsigned int cpu)
+{
+	struct cpufreq_policy *policy = cpufreq_cpu_acquire(cpu);
+	struct cpufreq_policy new_policy;
+	struct cpudata *cpudata;
+
+	if (!policy)
+		return;
+
+	cpudata = all_cpu_data[cpu];
+	policy->cpuinfo.max_freq = global.turbo_disabled_mf ?
+			cpudata->pstate.max_freq : cpudata->pstate.turbo_freq;
+
+	memcpy(&new_policy, policy, sizeof(*policy));
+	new_policy.max = min(policy->user_policy.max, policy->cpuinfo.max_freq);
+	new_policy.min = min(policy->user_policy.min, new_policy.max);
+
+	cpufreq_set_policy(policy, &new_policy);
+
+	cpufreq_cpu_release(policy);
+}
+
+static void intel_pstate_update_limits(unsigned int cpu)
+{
+	mutex_lock(&intel_pstate_driver_lock);
+
+	update_turbo_state();
+	/*
+	 * If turbo has been turned on or off globally, policy limits for
+	 * all CPUs need to be updated to reflect that.
+	 */
+	if (global.turbo_disabled_mf != global.turbo_disabled) {
+		global.turbo_disabled_mf = global.turbo_disabled;
+		for_each_possible_cpu(cpu)
+			intel_pstate_update_max_freq(cpu);
+	} else {
+		cpufreq_update_policy(cpu);
+	}
+
+	mutex_unlock(&intel_pstate_driver_lock);
+}
+
 /************************** sysfs begin ************************/
 #define show_one(file_name, object)					\
 	static ssize_t show_##file_name					\
@@ -1194,7 +1241,7 @@ static void __init intel_pstate_sysfs_expose_params(void)
 static void intel_pstate_hwp_enable(struct cpudata *cpudata)
 {
 	/* First disable HWP notification interrupt as we don't process them */
-	if (static_cpu_has(X86_FEATURE_HWP_NOTIFY))
+	if (boot_cpu_has(X86_FEATURE_HWP_NOTIFY))
 		wrmsrl_on_cpu(cpudata->cpu, MSR_HWP_INTERRUPT, 0x00);
 
 	wrmsrl_on_cpu(cpudata->cpu, MSR_PM_ENABLE, 0x1);
@@ -2135,6 +2182,7 @@ static int __intel_pstate_cpu_init(struct cpufreq_policy *policy)
 	/* cpuinfo and default policy values */
 	policy->cpuinfo.min_freq = cpu->pstate.min_pstate * cpu->pstate.scaling;
 	update_turbo_state();
+	global.turbo_disabled_mf = global.turbo_disabled;
 	policy->cpuinfo.max_freq = global.turbo_disabled ?
 			cpu->pstate.max_pstate : cpu->pstate.turbo_pstate;
 	policy->cpuinfo.max_freq *= cpu->pstate.scaling;
@@ -2179,6 +2227,7 @@ static struct cpufreq_driver intel_pstate = {
 	.init		= intel_pstate_cpu_init,
 	.exit		= intel_pstate_cpu_exit,
 	.stop_cpu	= intel_pstate_stop_cpu,
+	.update_limits	= intel_pstate_update_limits,
 	.name		= "intel_pstate",
 };
 
@@ -2313,6 +2362,7 @@ static struct cpufreq_driver intel_cpufreq = {
 	.init		= intel_cpufreq_cpu_init,
 	.exit		= intel_pstate_cpu_exit,
 	.stop_cpu	= intel_cpufreq_stop_cpu,
+	.update_limits	= intel_pstate_update_limits,
 	.name		= "intel_cpufreq",
 };
 
@@ -2593,6 +2643,9 @@ static int __init intel_pstate_init(void)
 	const struct x86_cpu_id *id;
 	int rc;
 
+	if (boot_cpu_data.x86_vendor != X86_VENDOR_INTEL)
+		return -ENODEV;
+
 	if (no_load)
 		return -ENODEV;
 
@@ -2608,7 +2661,7 @@ static int __init intel_pstate_init(void)
 	} else {
 		id = x86_match_cpu(intel_pstate_cpu_ids);
 		if (!id) {
-			pr_info("CPU ID not supported\n");
+			pr_info("CPU model not supported\n");
 			return -ENODEV;
 		}
 
diff --git a/drivers/cpufreq/kirkwood-cpufreq.c b/drivers/cpufreq/kirkwood-cpufreq.c
index c2dd43f3f5d8..8d63a6dc8383 100644
--- a/drivers/cpufreq/kirkwood-cpufreq.c
+++ b/drivers/cpufreq/kirkwood-cpufreq.c
@@ -124,13 +124,14 @@ static int kirkwood_cpufreq_probe(struct platform_device *pdev)
 	priv.cpu_clk = of_clk_get_by_name(np, "cpu_clk");
 	if (IS_ERR(priv.cpu_clk)) {
 		dev_err(priv.dev, "Unable to get cpuclk\n");
-		return PTR_ERR(priv.cpu_clk);
+		err = PTR_ERR(priv.cpu_clk);
+		goto out_node;
 	}
 
 	err = clk_prepare_enable(priv.cpu_clk);
 	if (err) {
 		dev_err(priv.dev, "Unable to prepare cpuclk\n");
-		return err;
+		goto out_node;
 	}
 
 	kirkwood_freq_table[0].frequency = clk_get_rate(priv.cpu_clk) / 1000;
@@ -161,20 +162,22 @@ static int kirkwood_cpufreq_probe(struct platform_device *pdev)
 		goto out_ddr;
 	}
 
-	of_node_put(np);
-	np = NULL;
-
 	err = cpufreq_register_driver(&kirkwood_cpufreq_driver);
-	if (!err)
-		return 0;
+	if (err) {
+		dev_err(priv.dev, "Failed to register cpufreq driver\n");
+		goto out_powersave;
+	}
 
-	dev_err(priv.dev, "Failed to register cpufreq driver\n");
+	of_node_put(np);
+	return 0;
 
+out_powersave:
 	clk_disable_unprepare(priv.powersave_clk);
 out_ddr:
 	clk_disable_unprepare(priv.ddr_clk);
 out_cpu:
 	clk_disable_unprepare(priv.cpu_clk);
+out_node:
 	of_node_put(np);
 
 	return err;
diff --git a/drivers/cpufreq/maple-cpufreq.c b/drivers/cpufreq/maple-cpufreq.c
index d9df89392b84..a94355723ef8 100644
--- a/drivers/cpufreq/maple-cpufreq.c
+++ b/drivers/cpufreq/maple-cpufreq.c
@@ -210,7 +210,7 @@ static int __init maple_cpufreq_init(void)
 	 */
 	valp = of_get_property(cpunode, "clock-frequency", NULL);
 	if (!valp)
-		return -ENODEV;
+		goto bail_noprops;
 	max_freq = (*valp)/1000;
 	maple_cpu_freqs[0].frequency = max_freq;
 	maple_cpu_freqs[1].frequency = max_freq/2;
@@ -231,10 +231,6 @@ static int __init maple_cpufreq_init(void)
 
 	rc = cpufreq_register_driver(&maple_cpufreq_driver);
 
-	of_node_put(cpunode);
-
-	return rc;
-
 bail_noprops:
 	of_node_put(cpunode);
 
diff --git a/drivers/cpufreq/pasemi-cpufreq.c b/drivers/cpufreq/pasemi-cpufreq.c
index 75dfbd2a58ea..c7710c149de8 100644
--- a/drivers/cpufreq/pasemi-cpufreq.c
+++ b/drivers/cpufreq/pasemi-cpufreq.c
@@ -146,6 +146,7 @@ static int pas_cpufreq_cpu_init(struct cpufreq_policy *policy)
 
 	cpu = of_get_cpu_node(policy->cpu, NULL);
 
+	of_node_put(cpu);
 	if (!cpu)
 		goto out;
 
diff --git a/drivers/cpufreq/pmac32-cpufreq.c b/drivers/cpufreq/pmac32-cpufreq.c
index 52f0d91d30c1..9b4ce2eb8222 100644
--- a/drivers/cpufreq/pmac32-cpufreq.c
+++ b/drivers/cpufreq/pmac32-cpufreq.c
@@ -552,6 +552,7 @@ static int pmac_cpufreq_init_7447A(struct device_node *cpunode)
 	volt_gpio_np = of_find_node_by_name(NULL, "cpu-vcore-select");
 	if (volt_gpio_np)
 		voltage_gpio = read_gpio(volt_gpio_np);
+	of_node_put(volt_gpio_np);
 	if (!voltage_gpio){
 		pr_err("missing cpu-vcore-select gpio\n");
 		return 1;
@@ -588,6 +589,7 @@ static int pmac_cpufreq_init_750FX(struct device_node *cpunode)
 	if (volt_gpio_np)
 		voltage_gpio = read_gpio(volt_gpio_np);
 
+	of_node_put(volt_gpio_np);
 	pvr = mfspr(SPRN_PVR);
 	has_cpu_l2lve = !((pvr & 0xf00) == 0x100);
 
diff --git a/drivers/cpufreq/powernow-k8.c b/drivers/cpufreq/powernow-k8.c
index fb77b39a4ce3..3c12e03fa343 100644
--- a/drivers/cpufreq/powernow-k8.c
+++ b/drivers/cpufreq/powernow-k8.c
@@ -1178,7 +1178,7 @@ static int powernowk8_init(void)
 	unsigned int i, supported_cpus = 0;
 	int ret;
 
-	if (static_cpu_has(X86_FEATURE_HW_PSTATE)) {
+	if (boot_cpu_has(X86_FEATURE_HW_PSTATE)) {
 		__request_acpi_cpufreq();
 		return -ENODEV;
 	}
diff --git a/drivers/cpufreq/ppc_cbe_cpufreq.c b/drivers/cpufreq/ppc_cbe_cpufreq.c
index 41a0f0be3f9f..8414c3a4ea08 100644
--- a/drivers/cpufreq/ppc_cbe_cpufreq.c
+++ b/drivers/cpufreq/ppc_cbe_cpufreq.c
@@ -86,6 +86,7 @@ static int cbe_cpufreq_cpu_init(struct cpufreq_policy *policy)
 	if (!cbe_get_cpu_pmd_regs(policy->cpu) ||
 	    !cbe_get_cpu_mic_tm_regs(policy->cpu)) {
 		pr_info("invalid CBE regs pointers for cpufreq\n");
+		of_node_put(cpu);
 		return -EINVAL;
 	}
 
diff --git a/drivers/cpufreq/qoriq-cpufreq.c b/drivers/cpufreq/qoriq-cpufreq.c
index 4295e5476264..71b640c8c1a5 100644
--- a/drivers/cpufreq/qoriq-cpufreq.c
+++ b/drivers/cpufreq/qoriq-cpufreq.c
@@ -280,10 +280,12 @@ static const struct of_device_id node_matches[] __initconst = {
 
 	{ .compatible = "fsl,ls1012a-clockgen", },
 	{ .compatible = "fsl,ls1021a-clockgen", },
+	{ .compatible = "fsl,ls1028a-clockgen", },
 	{ .compatible = "fsl,ls1043a-clockgen", },
 	{ .compatible = "fsl,ls1046a-clockgen", },
 	{ .compatible = "fsl,ls1088a-clockgen", },
 	{ .compatible = "fsl,ls2080a-clockgen", },
+	{ .compatible = "fsl,lx2160a-clockgen", },
 	{ .compatible = "fsl,p4080-clockgen", },
 	{ .compatible = "fsl,qoriq-clockgen-1.0", },
 	{ .compatible = "fsl,qoriq-clockgen-2.0", },
diff --git a/drivers/cpufreq/scpi-cpufreq.c b/drivers/cpufreq/scpi-cpufreq.c
index 3f49427766b8..2b51e0718c9f 100644
--- a/drivers/cpufreq/scpi-cpufreq.c
+++ b/drivers/cpufreq/scpi-cpufreq.c
@@ -189,8 +189,8 @@ static int scpi_cpufreq_exit(struct cpufreq_policy *policy)
 
 	clk_put(priv->clk);
 	dev_pm_opp_free_cpufreq_table(priv->cpu_dev, &policy->freq_table);
-	kfree(priv);
 	dev_pm_opp_remove_all_dynamic(priv->cpu_dev);
+	kfree(priv);
 
 	return 0;
 }
diff --git a/drivers/cpufreq/speedstep-centrino.c b/drivers/cpufreq/speedstep-centrino.c
index a1fb735685db..e086b2dd4072 100644
--- a/drivers/cpufreq/speedstep-centrino.c
+++ b/drivers/cpufreq/speedstep-centrino.c
@@ -412,7 +412,7 @@ static int centrino_cpu_exit(struct cpufreq_policy *policy)
 }
 
 /**
- * centrino_setpolicy - set a new CPUFreq policy
+ * centrino_target - set a new CPUFreq policy
  * @policy: new policy
  * @index: index of target frequency
  *
diff --git a/drivers/cpuidle/cpuidle-exynos.c b/drivers/cpuidle/cpuidle-exynos.c
index 0171a6e190d7..f7199a35cbb6 100644
--- a/drivers/cpuidle/cpuidle-exynos.c
+++ b/drivers/cpuidle/cpuidle-exynos.c
@@ -84,7 +84,7 @@ static struct cpuidle_driver exynos_idle_driver = {
 		[1] = {
 			.enter			= exynos_enter_lowpower,
 			.exit_latency		= 300,
-			.target_residency	= 100000,
+			.target_residency	= 10000,
 			.name			= "C1",
 			.desc			= "ARM power down",
 		},
diff --git a/drivers/cpuidle/cpuidle.c b/drivers/cpuidle/cpuidle.c
index 7f108309e871..0f4b7c45df3e 100644
--- a/drivers/cpuidle/cpuidle.c
+++ b/drivers/cpuidle/cpuidle.c
@@ -328,9 +328,23 @@ int cpuidle_select(struct cpuidle_driver *drv, struct cpuidle_device *dev,
 int cpuidle_enter(struct cpuidle_driver *drv, struct cpuidle_device *dev,
 		  int index)
 {
+	int ret = 0;
+
+	/*
+	 * Store the next hrtimer, which becomes either next tick or the next
+	 * timer event, whatever expires first. Additionally, to make this data
+	 * useful for consumers outside cpuidle, we rely on that the governor's
+	 * ->select() callback have decided, whether to stop the tick or not.
+	 */
+	WRITE_ONCE(dev->next_hrtimer, tick_nohz_get_next_hrtimer());
+
 	if (cpuidle_state_is_coupled(drv, index))
-		return cpuidle_enter_state_coupled(dev, drv, index);
-	return cpuidle_enter_state(dev, drv, index);
+		ret = cpuidle_enter_state_coupled(dev, drv, index);
+	else
+		ret = cpuidle_enter_state(dev, drv, index);
+
+	WRITE_ONCE(dev->next_hrtimer, 0);
+	return ret;
 }
 
 /**
@@ -511,6 +525,7 @@ static void __cpuidle_device_init(struct cpuidle_device *dev)
 {
 	memset(dev->states_usage, 0, sizeof(dev->states_usage));
 	dev->last_residency = 0;
+	dev->next_hrtimer = 0;
 }
 
 /**
diff --git a/drivers/crypto/Kconfig b/drivers/crypto/Kconfig
index 0be55fcc19ba..177b7713bd2d 100644
--- a/drivers/crypto/Kconfig
+++ b/drivers/crypto/Kconfig
@@ -404,15 +404,6 @@ config CRYPTO_DEV_SAHARA
 	  This option enables support for the SAHARA HW crypto accelerator
 	  found in some Freescale i.MX chips.
 
-config CRYPTO_DEV_MXC_SCC
-	tristate "Support for Freescale Security Controller (SCC)"
-	depends on ARCH_MXC && OF
-	select CRYPTO_BLKCIPHER
-	select CRYPTO_DES
-	help
-	  This option enables support for the Security Controller (SCC)
-	  found in Freescale i.MX25 chips.
-
 config CRYPTO_DEV_EXYNOS_RNG
 	tristate "EXYNOS HW pseudo random number generator support"
 	depends on ARCH_EXYNOS || COMPILE_TEST
diff --git a/drivers/crypto/Makefile b/drivers/crypto/Makefile
index 8e7e225d2446..a23a7197fcd7 100644
--- a/drivers/crypto/Makefile
+++ b/drivers/crypto/Makefile
@@ -18,7 +18,6 @@ obj-$(CONFIG_CRYPTO_DEV_IXP4XX) += ixp4xx_crypto.o
 obj-$(CONFIG_CRYPTO_DEV_MARVELL_CESA) += marvell/
 obj-$(CONFIG_CRYPTO_DEV_MEDIATEK) += mediatek/
 obj-$(CONFIG_CRYPTO_DEV_MXS_DCP) += mxs-dcp.o
-obj-$(CONFIG_CRYPTO_DEV_MXC_SCC) += mxc-scc.o
 obj-$(CONFIG_CRYPTO_DEV_NIAGARA2) += n2_crypto.o
 n2_crypto-y := n2_core.o n2_asm.o
 obj-$(CONFIG_CRYPTO_DEV_NX) += nx/
diff --git a/drivers/crypto/amcc/crypto4xx_alg.c b/drivers/crypto/amcc/crypto4xx_alg.c
index 4092c2aad8e2..307f5cfa9ba4 100644
--- a/drivers/crypto/amcc/crypto4xx_alg.c
+++ b/drivers/crypto/amcc/crypto4xx_alg.c
@@ -141,9 +141,10 @@ static int crypto4xx_setkey_aes(struct crypto_skcipher *cipher,
 	/* Setup SA */
 	sa = ctx->sa_in;
 
-	set_dynamic_sa_command_0(sa, SA_NOT_SAVE_HASH, (cm == CRYPTO_MODE_CBC ?
-				 SA_SAVE_IV : SA_NOT_SAVE_IV),
-				 SA_LOAD_HASH_FROM_SA, SA_LOAD_IV_FROM_STATE,
+	set_dynamic_sa_command_0(sa, SA_NOT_SAVE_HASH, (cm == CRYPTO_MODE_ECB ?
+				 SA_NOT_SAVE_IV : SA_SAVE_IV),
+				 SA_NOT_LOAD_HASH, (cm == CRYPTO_MODE_ECB ?
+				 SA_LOAD_IV_FROM_SA : SA_LOAD_IV_FROM_STATE),
 				 SA_NO_HEADER_PROC, SA_HASH_ALG_NULL,
 				 SA_CIPHER_ALG_AES, SA_PAD_TYPE_ZERO,
 				 SA_OP_GROUP_BASIC, SA_OPCODE_DECRYPT,
@@ -162,6 +163,11 @@ static int crypto4xx_setkey_aes(struct crypto_skcipher *cipher,
 	memcpy(ctx->sa_out, ctx->sa_in, ctx->sa_len * 4);
 	sa = ctx->sa_out;
 	sa->sa_command_0.bf.dir = DIR_OUTBOUND;
+	/*
+	 * SA_OPCODE_ENCRYPT is the same value as SA_OPCODE_DECRYPT.
+	 * it's the DIR_(IN|OUT)BOUND that matters
+	 */
+	sa->sa_command_0.bf.opcode = SA_OPCODE_ENCRYPT;
 
 	return 0;
 }
@@ -258,10 +264,10 @@ crypto4xx_ctr_crypt(struct skcipher_request *req, bool encrypt)
 	 * overlow.
 	 */
 	if (counter + nblks < counter) {
-		struct skcipher_request *subreq = skcipher_request_ctx(req);
+		SYNC_SKCIPHER_REQUEST_ON_STACK(subreq, ctx->sw_cipher.cipher);
 		int ret;
 
-		skcipher_request_set_tfm(subreq, ctx->sw_cipher.cipher);
+		skcipher_request_set_sync_tfm(subreq, ctx->sw_cipher.cipher);
 		skcipher_request_set_callback(subreq, req->base.flags,
 			NULL, NULL);
 		skcipher_request_set_crypt(subreq, req->src, req->dst,
@@ -283,14 +289,14 @@ static int crypto4xx_sk_setup_fallback(struct crypto4xx_ctx *ctx,
 {
 	int rc;
 
-	crypto_skcipher_clear_flags(ctx->sw_cipher.cipher,
+	crypto_sync_skcipher_clear_flags(ctx->sw_cipher.cipher,
 				    CRYPTO_TFM_REQ_MASK);
-	crypto_skcipher_set_flags(ctx->sw_cipher.cipher,
+	crypto_sync_skcipher_set_flags(ctx->sw_cipher.cipher,
 		crypto_skcipher_get_flags(cipher) & CRYPTO_TFM_REQ_MASK);
-	rc = crypto_skcipher_setkey(ctx->sw_cipher.cipher, key, keylen);
+	rc = crypto_sync_skcipher_setkey(ctx->sw_cipher.cipher, key, keylen);
 	crypto_skcipher_clear_flags(cipher, CRYPTO_TFM_RES_MASK);
 	crypto_skcipher_set_flags(cipher,
-		crypto_skcipher_get_flags(ctx->sw_cipher.cipher) &
+		crypto_sync_skcipher_get_flags(ctx->sw_cipher.cipher) &
 			CRYPTO_TFM_RES_MASK);
 
 	return rc;
diff --git a/drivers/crypto/amcc/crypto4xx_core.c b/drivers/crypto/amcc/crypto4xx_core.c
index 06574a884715..3934c2523762 100644
--- a/drivers/crypto/amcc/crypto4xx_core.c
+++ b/drivers/crypto/amcc/crypto4xx_core.c
@@ -539,7 +539,7 @@ static void crypto4xx_cipher_done(struct crypto4xx_device *dev,
 
 	req = skcipher_request_cast(pd_uinfo->async_req);
 
-	if (pd_uinfo->using_sd) {
+	if (pd_uinfo->sa_va->sa_command_0.bf.scatter) {
 		crypto4xx_copy_pkt_to_dst(dev, pd, pd_uinfo,
 					  req->cryptlen, req->dst);
 	} else {
@@ -593,7 +593,7 @@ static void crypto4xx_aead_done(struct crypto4xx_device *dev,
 	u32 icv[AES_BLOCK_SIZE];
 	int err = 0;
 
-	if (pd_uinfo->using_sd) {
+	if (pd_uinfo->sa_va->sa_command_0.bf.scatter) {
 		crypto4xx_copy_pkt_to_dst(dev, pd, pd_uinfo,
 					  pd->pd_ctl_len.bf.pkt_len,
 					  dst);
@@ -714,7 +714,23 @@ int crypto4xx_build_pd(struct crypto_async_request *req,
 	size_t offset_to_sr_ptr;
 	u32 gd_idx = 0;
 	int tmp;
-	bool is_busy;
+	bool is_busy, force_sd;
+
+	/*
+	 * There's a very subtile/disguised "bug" in the hardware that
+	 * gets indirectly mentioned in 18.1.3.5 Encryption/Decryption
+	 * of the hardware spec:
+	 * *drum roll* the AES/(T)DES OFB and CFB modes are listed as
+	 * operation modes for >>> "Block ciphers" <<<.
+	 *
+	 * To workaround this issue and stop the hardware from causing
+	 * "overran dst buffer" on crypttexts that are not a multiple
+	 * of 16 (AES_BLOCK_SIZE), we force the driver to use the
+	 * scatter buffers.
+	 */
+	force_sd = (req_sa->sa_command_1.bf.crypto_mode9_8 == CRYPTO_MODE_CFB
+		|| req_sa->sa_command_1.bf.crypto_mode9_8 == CRYPTO_MODE_OFB)
+		&& (datalen % AES_BLOCK_SIZE);
 
 	/* figure how many gd are needed */
 	tmp = sg_nents_for_len(src, assoclen + datalen);
@@ -732,7 +748,7 @@ int crypto4xx_build_pd(struct crypto_async_request *req,
 	}
 
 	/* figure how many sd are needed */
-	if (sg_is_last(dst)) {
+	if (sg_is_last(dst) && force_sd == false) {
 		num_sd = 0;
 	} else {
 		if (datalen > PPC4XX_SD_BUFFER_SIZE) {
@@ -807,9 +823,10 @@ int crypto4xx_build_pd(struct crypto_async_request *req,
 	pd->sa_len = sa_len;
 
 	pd_uinfo = &dev->pdr_uinfo[pd_entry];
-	pd_uinfo->async_req = req;
 	pd_uinfo->num_gd = num_gd;
 	pd_uinfo->num_sd = num_sd;
+	pd_uinfo->dest_va = dst;
+	pd_uinfo->async_req = req;
 
 	if (iv_len)
 		memcpy(pd_uinfo->sr_va->save_iv, iv, iv_len);
@@ -828,7 +845,6 @@ int crypto4xx_build_pd(struct crypto_async_request *req,
 		/* get first gd we are going to use */
 		gd_idx = fst_gd;
 		pd_uinfo->first_gd = fst_gd;
-		pd_uinfo->num_gd = num_gd;
 		gd = crypto4xx_get_gdp(dev, &gd_dma, gd_idx);
 		pd->src = gd_dma;
 		/* enable gather */
@@ -865,17 +881,13 @@ int crypto4xx_build_pd(struct crypto_async_request *req,
 		 * Indicate gather array is not used
 		 */
 		pd_uinfo->first_gd = 0xffffffff;
-		pd_uinfo->num_gd = 0;
 	}
-	if (sg_is_last(dst)) {
+	if (!num_sd) {
 		/*
 		 * we know application give us dst a whole piece of memory
 		 * no need to use scatter ring.
 		 */
-		pd_uinfo->using_sd = 0;
 		pd_uinfo->first_sd = 0xffffffff;
-		pd_uinfo->num_sd = 0;
-		pd_uinfo->dest_va = dst;
 		sa->sa_command_0.bf.scatter = 0;
 		pd->dest = (u32)dma_map_page(dev->core_dev->device,
 					     sg_page(dst), dst->offset,
@@ -888,10 +900,7 @@ int crypto4xx_build_pd(struct crypto_async_request *req,
 		u32 sd_idx = fst_sd;
 		nbytes = datalen;
 		sa->sa_command_0.bf.scatter = 1;
-		pd_uinfo->using_sd = 1;
-		pd_uinfo->dest_va = dst;
 		pd_uinfo->first_sd = fst_sd;
-		pd_uinfo->num_sd = num_sd;
 		sd = crypto4xx_get_sdp(dev, &sd_dma, sd_idx);
 		pd->dest = sd_dma;
 		/* setup scatter descriptor */
@@ -954,15 +963,10 @@ static int crypto4xx_sk_init(struct crypto_skcipher *sk)
 
 	if (alg->base.cra_flags & CRYPTO_ALG_NEED_FALLBACK) {
 		ctx->sw_cipher.cipher =
-			crypto_alloc_skcipher(alg->base.cra_name, 0,
-					      CRYPTO_ALG_NEED_FALLBACK |
-					      CRYPTO_ALG_ASYNC);
+			crypto_alloc_sync_skcipher(alg->base.cra_name, 0,
+					      CRYPTO_ALG_NEED_FALLBACK);
 		if (IS_ERR(ctx->sw_cipher.cipher))
 			return PTR_ERR(ctx->sw_cipher.cipher);
-
-		crypto_skcipher_set_reqsize(sk,
-			sizeof(struct skcipher_request) + 32 +
-			crypto_skcipher_reqsize(ctx->sw_cipher.cipher));
 	}
 
 	amcc_alg = container_of(alg, struct crypto4xx_alg, alg.u.cipher);
@@ -981,7 +985,7 @@ static void crypto4xx_sk_exit(struct crypto_skcipher *sk)
 
 	crypto4xx_common_exit(ctx);
 	if (ctx->sw_cipher.cipher)
-		crypto_free_skcipher(ctx->sw_cipher.cipher);
+		crypto_free_sync_skcipher(ctx->sw_cipher.cipher);
 }
 
 static int crypto4xx_aead_init(struct crypto_aead *tfm)
diff --git a/drivers/crypto/amcc/crypto4xx_core.h b/drivers/crypto/amcc/crypto4xx_core.h
index 18df695ca6b1..c624f8cd3d2e 100644
--- a/drivers/crypto/amcc/crypto4xx_core.h
+++ b/drivers/crypto/amcc/crypto4xx_core.h
@@ -64,7 +64,6 @@ union shadow_sa_buf {
 struct pd_uinfo {
 	struct crypto4xx_device *dev;
 	u32   state;
-	u32 using_sd;
 	u32 first_gd;		/* first gather discriptor
 				used by this packet */
 	u32 num_gd;             /* number of gather discriptor
@@ -131,7 +130,7 @@ struct crypto4xx_ctx {
 	__le32 iv_nonce;
 	u32 sa_len;
 	union {
-		struct crypto_skcipher *cipher;
+		struct crypto_sync_skcipher *cipher;
 		struct crypto_aead *aead;
 	} sw_cipher;
 };
diff --git a/drivers/crypto/atmel-tdes.c b/drivers/crypto/atmel-tdes.c
index 65bf1a299562..fa76620281e8 100644
--- a/drivers/crypto/atmel-tdes.c
+++ b/drivers/crypto/atmel-tdes.c
@@ -800,20 +800,14 @@ static int atmel_tdes_setkey(struct crypto_ablkcipher *tfm, const u8 *key,
 			   unsigned int keylen)
 {
 	struct atmel_tdes_ctx *ctx = crypto_ablkcipher_ctx(tfm);
-	const char *alg_name;
-
-	alg_name = crypto_tfm_alg_name(crypto_ablkcipher_tfm(tfm));
+	u32 flags;
+	int err;
 
-	/*
-	 * HW bug in cfb 3-keys mode.
-	 */
-	if (!ctx->dd->caps.has_cfb_3keys && strstr(alg_name, "cfb")
-			&& (keylen != 2*DES_KEY_SIZE)) {
-		crypto_ablkcipher_set_flags(tfm, CRYPTO_TFM_RES_BAD_KEY_LEN);
-		return -EINVAL;
-	} else if ((keylen != 2*DES_KEY_SIZE) && (keylen != 3*DES_KEY_SIZE)) {
-		crypto_ablkcipher_set_flags(tfm, CRYPTO_TFM_RES_BAD_KEY_LEN);
-		return -EINVAL;
+	flags = crypto_ablkcipher_get_flags(tfm);
+	err = __des3_verify_key(&flags, key);
+	if (unlikely(err)) {
+		crypto_ablkcipher_set_flags(tfm, flags);
+		return err;
 	}
 
 	memcpy(ctx->key, key, keylen);
@@ -1060,7 +1054,7 @@ static struct crypto_alg tdes_algs[] = {
 	.cra_module		= THIS_MODULE,
 	.cra_init		= atmel_tdes_cra_init,
 	.cra_u.ablkcipher = {
-		.min_keysize	= 2 * DES_KEY_SIZE,
+		.min_keysize	= 3 * DES_KEY_SIZE,
 		.max_keysize	= 3 * DES_KEY_SIZE,
 		.setkey		= atmel_tdes_setkey,
 		.encrypt	= atmel_tdes_ecb_encrypt,
@@ -1079,7 +1073,7 @@ static struct crypto_alg tdes_algs[] = {
 	.cra_module		= THIS_MODULE,
 	.cra_init		= atmel_tdes_cra_init,
 	.cra_u.ablkcipher = {
-		.min_keysize	= 2*DES_KEY_SIZE,
+		.min_keysize	= 3*DES_KEY_SIZE,
 		.max_keysize	= 3*DES_KEY_SIZE,
 		.ivsize		= DES_BLOCK_SIZE,
 		.setkey		= atmel_tdes_setkey,
@@ -1088,86 +1082,6 @@ static struct crypto_alg tdes_algs[] = {
 	}
 },
 {
-	.cra_name		= "cfb(des3_ede)",
-	.cra_driver_name	= "atmel-cfb-tdes",
-	.cra_priority		= 100,
-	.cra_flags		= CRYPTO_ALG_TYPE_ABLKCIPHER | CRYPTO_ALG_ASYNC,
-	.cra_blocksize		= DES_BLOCK_SIZE,
-	.cra_ctxsize		= sizeof(struct atmel_tdes_ctx),
-	.cra_alignmask		= 0x7,
-	.cra_type		= &crypto_ablkcipher_type,
-	.cra_module		= THIS_MODULE,
-	.cra_init		= atmel_tdes_cra_init,
-	.cra_u.ablkcipher = {
-		.min_keysize	= 2*DES_KEY_SIZE,
-		.max_keysize	= 2*DES_KEY_SIZE,
-		.ivsize		= DES_BLOCK_SIZE,
-		.setkey		= atmel_tdes_setkey,
-		.encrypt	= atmel_tdes_cfb_encrypt,
-		.decrypt	= atmel_tdes_cfb_decrypt,
-	}
-},
-{
-	.cra_name		= "cfb8(des3_ede)",
-	.cra_driver_name	= "atmel-cfb8-tdes",
-	.cra_priority		= 100,
-	.cra_flags		= CRYPTO_ALG_TYPE_ABLKCIPHER | CRYPTO_ALG_ASYNC,
-	.cra_blocksize		= CFB8_BLOCK_SIZE,
-	.cra_ctxsize		= sizeof(struct atmel_tdes_ctx),
-	.cra_alignmask		= 0,
-	.cra_type		= &crypto_ablkcipher_type,
-	.cra_module		= THIS_MODULE,
-	.cra_init		= atmel_tdes_cra_init,
-	.cra_u.ablkcipher = {
-		.min_keysize	= 2*DES_KEY_SIZE,
-		.max_keysize	= 2*DES_KEY_SIZE,
-		.ivsize		= DES_BLOCK_SIZE,
-		.setkey		= atmel_tdes_setkey,
-		.encrypt	= atmel_tdes_cfb8_encrypt,
-		.decrypt	= atmel_tdes_cfb8_decrypt,
-	}
-},
-{
-	.cra_name		= "cfb16(des3_ede)",
-	.cra_driver_name	= "atmel-cfb16-tdes",
-	.cra_priority		= 100,
-	.cra_flags		= CRYPTO_ALG_TYPE_ABLKCIPHER | CRYPTO_ALG_ASYNC,
-	.cra_blocksize		= CFB16_BLOCK_SIZE,
-	.cra_ctxsize		= sizeof(struct atmel_tdes_ctx),
-	.cra_alignmask		= 0x1,
-	.cra_type		= &crypto_ablkcipher_type,
-	.cra_module		= THIS_MODULE,
-	.cra_init		= atmel_tdes_cra_init,
-	.cra_u.ablkcipher = {
-		.min_keysize	= 2*DES_KEY_SIZE,
-		.max_keysize	= 2*DES_KEY_SIZE,
-		.ivsize		= DES_BLOCK_SIZE,
-		.setkey		= atmel_tdes_setkey,
-		.encrypt	= atmel_tdes_cfb16_encrypt,
-		.decrypt	= atmel_tdes_cfb16_decrypt,
-	}
-},
-{
-	.cra_name		= "cfb32(des3_ede)",
-	.cra_driver_name	= "atmel-cfb32-tdes",
-	.cra_priority		= 100,
-	.cra_flags		= CRYPTO_ALG_TYPE_ABLKCIPHER | CRYPTO_ALG_ASYNC,
-	.cra_blocksize		= CFB32_BLOCK_SIZE,
-	.cra_ctxsize		= sizeof(struct atmel_tdes_ctx),
-	.cra_alignmask		= 0x3,
-	.cra_type		= &crypto_ablkcipher_type,
-	.cra_module		= THIS_MODULE,
-	.cra_init		= atmel_tdes_cra_init,
-	.cra_u.ablkcipher = {
-		.min_keysize	= 2*DES_KEY_SIZE,
-		.max_keysize	= 2*DES_KEY_SIZE,
-		.ivsize		= DES_BLOCK_SIZE,
-		.setkey		= atmel_tdes_setkey,
-		.encrypt	= atmel_tdes_cfb32_encrypt,
-		.decrypt	= atmel_tdes_cfb32_decrypt,
-	}
-},
-{
 	.cra_name		= "ofb(des3_ede)",
 	.cra_driver_name	= "atmel-ofb-tdes",
 	.cra_priority		= 100,
@@ -1179,7 +1093,7 @@ static struct crypto_alg tdes_algs[] = {
 	.cra_module		= THIS_MODULE,
 	.cra_init		= atmel_tdes_cra_init,
 	.cra_u.ablkcipher = {
-		.min_keysize	= 2*DES_KEY_SIZE,
+		.min_keysize	= 3*DES_KEY_SIZE,
 		.max_keysize	= 3*DES_KEY_SIZE,
 		.ivsize		= DES_BLOCK_SIZE,
 		.setkey		= atmel_tdes_setkey,
diff --git a/drivers/crypto/axis/artpec6_crypto.c b/drivers/crypto/axis/artpec6_crypto.c
index 57e5dca3253f..d2fb72811442 100644
--- a/drivers/crypto/axis/artpec6_crypto.c
+++ b/drivers/crypto/axis/artpec6_crypto.c
@@ -2247,8 +2247,6 @@ artpec6_crypto_hash_set_key(struct crypto_ahash *tfm,
 		SHASH_DESC_ON_STACK(hdesc, tfm_ctx->child_hash);
 
 		hdesc->tfm = tfm_ctx->child_hash;
-		hdesc->flags = crypto_ahash_get_flags(tfm) &
-			       CRYPTO_TFM_REQ_MAY_SLEEP;
 
 		tfm_ctx->hmac_key_length = blocksize;
 		ret = crypto_shash_digest(hdesc, key, keylen,
diff --git a/drivers/crypto/bcm/cipher.c b/drivers/crypto/bcm/cipher.c
index 28f592f7e1b7..25f8d3913ceb 100644
--- a/drivers/crypto/bcm/cipher.c
+++ b/drivers/crypto/bcm/cipher.c
@@ -1840,13 +1840,14 @@ static int threedes_setkey(struct crypto_ablkcipher *cipher, const u8 *key,
 	struct iproc_ctx_s *ctx = crypto_ablkcipher_ctx(cipher);
 
 	if (keylen == (DES_KEY_SIZE * 3)) {
-		const u32 *K = (const u32 *)key;
-		u32 flags = CRYPTO_TFM_RES_BAD_KEY_SCHED;
+		u32 flags;
+		int ret;
 
-		if (!((K[0] ^ K[2]) | (K[1] ^ K[3])) ||
-		    !((K[2] ^ K[4]) | (K[3] ^ K[5]))) {
+		flags = crypto_ablkcipher_get_flags(cipher);
+		ret = __des3_verify_key(&flags, key);
+		if (unlikely(ret)) {
 			crypto_ablkcipher_set_flags(cipher, flags);
-			return -EINVAL;
+			return ret;
 		}
 
 		ctx->cipher_type = CIPHER_TYPE_3DES;
@@ -2139,7 +2140,6 @@ static int ahash_init(struct ahash_request *req)
 			goto err_hash;
 		}
 		ctx->shash->tfm = hash;
-		ctx->shash->flags = 0;
 
 		/* Set the key using data we already have from setkey */
 		if (ctx->authkeylen > 0) {
@@ -2885,13 +2885,13 @@ static int aead_authenc_setkey(struct crypto_aead *cipher,
 		break;
 	case CIPHER_ALG_3DES:
 		if (ctx->enckeylen == (DES_KEY_SIZE * 3)) {
-			const u32 *K = (const u32 *)keys.enckey;
-			u32 flags = CRYPTO_TFM_RES_BAD_KEY_SCHED;
+			u32 flags;
 
-			if (!((K[0] ^ K[2]) | (K[1] ^ K[3])) ||
-			    !((K[2] ^ K[4]) | (K[3] ^ K[5]))) {
+			flags = crypto_aead_get_flags(cipher);
+			ret = __des3_verify_key(&flags, keys.enckey);
+			if (unlikely(ret)) {
 				crypto_aead_set_flags(cipher, flags);
-				return -EINVAL;
+				return ret;
 			}
 
 			ctx->cipher_type = CIPHER_TYPE_3DES;
diff --git a/drivers/crypto/bcm/spu.c b/drivers/crypto/bcm/spu.c
index dbb5c03dde49..2baf6d7f2c1d 100644
--- a/drivers/crypto/bcm/spu.c
+++ b/drivers/crypto/bcm/spu.c
@@ -22,9 +22,6 @@
 #include "spum.h"
 #include "cipher.h"
 
-/* This array is based on the hash algo type supported in spu.h */
-char *tag_to_hash_idx[] = { "none", "md5", "sha1", "sha224", "sha256" };
-
 char *hash_alg_name[] = { "None", "md5", "sha1", "sha224", "sha256", "aes",
 	"sha384", "sha512", "sha3_224", "sha3_256", "sha3_384", "sha3_512" };
 
diff --git a/drivers/crypto/bcm/util.c b/drivers/crypto/bcm/util.c
index d8cda5fb75ad..91ec56399d84 100644
--- a/drivers/crypto/bcm/util.c
+++ b/drivers/crypto/bcm/util.c
@@ -242,7 +242,6 @@ int do_shash(unsigned char *name, unsigned char *result,
 		goto do_shash_err;
 	}
 	sdesc->shash.tfm = hash;
-	sdesc->shash.flags = 0x0;
 
 	if (key_len > 0) {
 		rc = crypto_shash_setkey(hash, key, key_len);
diff --git a/drivers/crypto/caam/caamalg.c b/drivers/crypto/caam/caamalg.c
index 579578498deb..3e23d4b2cce2 100644
--- a/drivers/crypto/caam/caamalg.c
+++ b/drivers/crypto/caam/caamalg.c
@@ -638,6 +638,39 @@ badkey:
 	return -EINVAL;
 }
 
+static int des3_aead_setkey(struct crypto_aead *aead, const u8 *key,
+			    unsigned int keylen)
+{
+	struct crypto_authenc_keys keys;
+	u32 flags;
+	int err;
+
+	err = crypto_authenc_extractkeys(&keys, key, keylen);
+	if (unlikely(err))
+		goto badkey;
+
+	err = -EINVAL;
+	if (keys.enckeylen != DES3_EDE_KEY_SIZE)
+		goto badkey;
+
+	flags = crypto_aead_get_flags(aead);
+	err = __des3_verify_key(&flags, keys.enckey);
+	if (unlikely(err)) {
+		crypto_aead_set_flags(aead, flags);
+		goto out;
+	}
+
+	err = aead_setkey(aead, key, keylen);
+
+out:
+	memzero_explicit(&keys, sizeof(keys));
+	return err;
+
+badkey:
+	crypto_aead_set_flags(aead, CRYPTO_TFM_RES_BAD_KEY_LEN);
+	goto out;
+}
+
 static int gcm_setkey(struct crypto_aead *aead,
 		      const u8 *key, unsigned int keylen)
 {
@@ -2457,7 +2490,7 @@ static struct caam_aead_alg driver_aeads[] = {
 						   "cbc-des3_ede-caam",
 				.cra_blocksize = DES3_EDE_BLOCK_SIZE,
 			},
-			.setkey = aead_setkey,
+			.setkey = des3_aead_setkey,
 			.setauthsize = aead_setauthsize,
 			.encrypt = aead_encrypt,
 			.decrypt = aead_decrypt,
@@ -2479,7 +2512,7 @@ static struct caam_aead_alg driver_aeads[] = {
 						   "cbc-des3_ede-caam",
 				.cra_blocksize = DES3_EDE_BLOCK_SIZE,
 			},
-			.setkey = aead_setkey,
+			.setkey = des3_aead_setkey,
 			.setauthsize = aead_setauthsize,
 			.encrypt = aead_encrypt,
 			.decrypt = aead_decrypt,
@@ -2502,7 +2535,7 @@ static struct caam_aead_alg driver_aeads[] = {
 						   "cbc-des3_ede-caam",
 				.cra_blocksize = DES3_EDE_BLOCK_SIZE,
 			},
-			.setkey = aead_setkey,
+			.setkey = des3_aead_setkey,
 			.setauthsize = aead_setauthsize,
 			.encrypt = aead_encrypt,
 			.decrypt = aead_decrypt,
@@ -2525,7 +2558,7 @@ static struct caam_aead_alg driver_aeads[] = {
 						   "cbc-des3_ede-caam",
 				.cra_blocksize = DES3_EDE_BLOCK_SIZE,
 			},
-			.setkey = aead_setkey,
+			.setkey = des3_aead_setkey,
 			.setauthsize = aead_setauthsize,
 			.encrypt = aead_encrypt,
 			.decrypt = aead_decrypt,
@@ -2548,7 +2581,7 @@ static struct caam_aead_alg driver_aeads[] = {
 						   "cbc-des3_ede-caam",
 				.cra_blocksize = DES3_EDE_BLOCK_SIZE,
 			},
-			.setkey = aead_setkey,
+			.setkey = des3_aead_setkey,
 			.setauthsize = aead_setauthsize,
 			.encrypt = aead_encrypt,
 			.decrypt = aead_decrypt,
@@ -2571,7 +2604,7 @@ static struct caam_aead_alg driver_aeads[] = {
 						   "cbc-des3_ede-caam",
 				.cra_blocksize = DES3_EDE_BLOCK_SIZE,
 			},
-			.setkey = aead_setkey,
+			.setkey = des3_aead_setkey,
 			.setauthsize = aead_setauthsize,
 			.encrypt = aead_encrypt,
 			.decrypt = aead_decrypt,
@@ -2594,7 +2627,7 @@ static struct caam_aead_alg driver_aeads[] = {
 						   "cbc-des3_ede-caam",
 				.cra_blocksize = DES3_EDE_BLOCK_SIZE,
 			},
-			.setkey = aead_setkey,
+			.setkey = des3_aead_setkey,
 			.setauthsize = aead_setauthsize,
 			.encrypt = aead_encrypt,
 			.decrypt = aead_decrypt,
@@ -2617,7 +2650,7 @@ static struct caam_aead_alg driver_aeads[] = {
 						   "cbc-des3_ede-caam",
 				.cra_blocksize = DES3_EDE_BLOCK_SIZE,
 			},
-			.setkey = aead_setkey,
+			.setkey = des3_aead_setkey,
 			.setauthsize = aead_setauthsize,
 			.encrypt = aead_encrypt,
 			.decrypt = aead_decrypt,
@@ -2640,7 +2673,7 @@ static struct caam_aead_alg driver_aeads[] = {
 						   "cbc-des3_ede-caam",
 				.cra_blocksize = DES3_EDE_BLOCK_SIZE,
 			},
-			.setkey = aead_setkey,
+			.setkey = des3_aead_setkey,
 			.setauthsize = aead_setauthsize,
 			.encrypt = aead_encrypt,
 			.decrypt = aead_decrypt,
@@ -2663,7 +2696,7 @@ static struct caam_aead_alg driver_aeads[] = {
 						   "cbc-des3_ede-caam",
 				.cra_blocksize = DES3_EDE_BLOCK_SIZE,
 			},
-			.setkey = aead_setkey,
+			.setkey = des3_aead_setkey,
 			.setauthsize = aead_setauthsize,
 			.encrypt = aead_encrypt,
 			.decrypt = aead_decrypt,
@@ -2686,7 +2719,7 @@ static struct caam_aead_alg driver_aeads[] = {
 						   "cbc-des3_ede-caam",
 				.cra_blocksize = DES3_EDE_BLOCK_SIZE,
 			},
-			.setkey = aead_setkey,
+			.setkey = des3_aead_setkey,
 			.setauthsize = aead_setauthsize,
 			.encrypt = aead_encrypt,
 			.decrypt = aead_decrypt,
@@ -2709,7 +2742,7 @@ static struct caam_aead_alg driver_aeads[] = {
 						   "cbc-des3_ede-caam",
 				.cra_blocksize = DES3_EDE_BLOCK_SIZE,
 			},
-			.setkey = aead_setkey,
+			.setkey = des3_aead_setkey,
 			.setauthsize = aead_setauthsize,
 			.encrypt = aead_encrypt,
 			.decrypt = aead_decrypt,
@@ -3460,7 +3493,7 @@ static int __init caam_algapi_init(void)
 	u32 aes_vid, aes_inst, des_inst, md_vid, md_inst, ccha_inst, ptha_inst;
 	u32 arc4_inst;
 	unsigned int md_limit = SHA512_DIGEST_SIZE;
-	bool registered = false;
+	bool registered = false, gcm_support;
 
 	dev_node = of_find_compatible_node(NULL, NULL, "fsl,sec-v4.0");
 	if (!dev_node) {
@@ -3493,7 +3526,7 @@ static int __init caam_algapi_init(void)
 	 * First, detect presence and attributes of DES, AES, and MD blocks.
 	 */
 	if (priv->era < 10) {
-		u32 cha_vid, cha_inst;
+		u32 cha_vid, cha_inst, aes_rn;
 
 		cha_vid = rd_reg32(&priv->ctrl->perfmon.cha_id_ls);
 		aes_vid = cha_vid & CHA_ID_LS_AES_MASK;
@@ -3508,6 +3541,10 @@ static int __init caam_algapi_init(void)
 			    CHA_ID_LS_ARC4_SHIFT;
 		ccha_inst = 0;
 		ptha_inst = 0;
+
+		aes_rn = rd_reg32(&priv->ctrl->perfmon.cha_rev_ls) &
+			 CHA_ID_LS_AES_MASK;
+		gcm_support = !(aes_vid == CHA_VER_VID_AES_LP && aes_rn < 8);
 	} else {
 		u32 aesa, mdha;
 
@@ -3523,6 +3560,8 @@ static int __init caam_algapi_init(void)
 		ccha_inst = rd_reg32(&priv->ctrl->vreg.ccha) & CHA_VER_NUM_MASK;
 		ptha_inst = rd_reg32(&priv->ctrl->vreg.ptha) & CHA_VER_NUM_MASK;
 		arc4_inst = rd_reg32(&priv->ctrl->vreg.afha) & CHA_VER_NUM_MASK;
+
+		gcm_support = aesa & CHA_VER_MISC_AES_GCM;
 	}
 
 	/* If MD is present, limit digest size based on LP256 */
@@ -3595,11 +3634,9 @@ static int __init caam_algapi_init(void)
 		if (c2_alg_sel == OP_ALG_ALGSEL_POLY1305 && !ptha_inst)
 			continue;
 
-		/*
-		 * Check support for AES algorithms not available
-		 * on LP devices.
-		 */
-		if (aes_vid  == CHA_VER_VID_AES_LP && alg_aai == OP_ALG_AAI_GCM)
+		/* Skip GCM algorithms if not supported by device */
+		if (c1_alg_sel == OP_ALG_ALGSEL_AES &&
+		    alg_aai == OP_ALG_AAI_GCM && !gcm_support)
 			continue;
 
 		/*
diff --git a/drivers/crypto/caam/caamalg_qi.c b/drivers/crypto/caam/caamalg_qi.c
index c61921d32489..70af211d2d01 100644
--- a/drivers/crypto/caam/caamalg_qi.c
+++ b/drivers/crypto/caam/caamalg_qi.c
@@ -292,6 +292,39 @@ badkey:
 	return -EINVAL;
 }
 
+static int des3_aead_setkey(struct crypto_aead *aead, const u8 *key,
+			    unsigned int keylen)
+{
+	struct crypto_authenc_keys keys;
+	u32 flags;
+	int err;
+
+	err = crypto_authenc_extractkeys(&keys, key, keylen);
+	if (unlikely(err))
+		goto badkey;
+
+	err = -EINVAL;
+	if (keys.enckeylen != DES3_EDE_KEY_SIZE)
+		goto badkey;
+
+	flags = crypto_aead_get_flags(aead);
+	err = __des3_verify_key(&flags, keys.enckey);
+	if (unlikely(err)) {
+		crypto_aead_set_flags(aead, flags);
+		goto out;
+	}
+
+	err = aead_setkey(aead, key, keylen);
+
+out:
+	memzero_explicit(&keys, sizeof(keys));
+	return err;
+
+badkey:
+	crypto_aead_set_flags(aead, CRYPTO_TFM_RES_BAD_KEY_LEN);
+	goto out;
+}
+
 static int gcm_set_sh_desc(struct crypto_aead *aead)
 {
 	struct caam_ctx *ctx = crypto_aead_ctx(aead);
@@ -667,6 +700,13 @@ badkey:
 	return -EINVAL;
 }
 
+static int des3_skcipher_setkey(struct crypto_skcipher *skcipher,
+				const u8 *key, unsigned int keylen)
+{
+	return unlikely(des3_verify_key(skcipher, key)) ?:
+	       skcipher_setkey(skcipher, key, keylen);
+}
+
 static int xts_skcipher_setkey(struct crypto_skcipher *skcipher, const u8 *key,
 			       unsigned int keylen)
 {
@@ -1382,7 +1422,7 @@ static struct caam_skcipher_alg driver_algs[] = {
 				.cra_driver_name = "cbc-3des-caam-qi",
 				.cra_blocksize = DES3_EDE_BLOCK_SIZE,
 			},
-			.setkey = skcipher_setkey,
+			.setkey = des3_skcipher_setkey,
 			.encrypt = skcipher_encrypt,
 			.decrypt = skcipher_decrypt,
 			.min_keysize = DES3_EDE_KEY_SIZE,
@@ -1798,7 +1838,7 @@ static struct caam_aead_alg driver_aeads[] = {
 						   "cbc-des3_ede-caam-qi",
 				.cra_blocksize = DES3_EDE_BLOCK_SIZE,
 			},
-			.setkey = aead_setkey,
+			.setkey = des3_aead_setkey,
 			.setauthsize = aead_setauthsize,
 			.encrypt = aead_encrypt,
 			.decrypt = aead_decrypt,
@@ -1820,7 +1860,7 @@ static struct caam_aead_alg driver_aeads[] = {
 						   "cbc-des3_ede-caam-qi",
 				.cra_blocksize = DES3_EDE_BLOCK_SIZE,
 			},
-			.setkey = aead_setkey,
+			.setkey = des3_aead_setkey,
 			.setauthsize = aead_setauthsize,
 			.encrypt = aead_encrypt,
 			.decrypt = aead_decrypt,
@@ -1843,7 +1883,7 @@ static struct caam_aead_alg driver_aeads[] = {
 						   "cbc-des3_ede-caam-qi",
 				.cra_blocksize = DES3_EDE_BLOCK_SIZE,
 			},
-			.setkey = aead_setkey,
+			.setkey = des3_aead_setkey,
 			.setauthsize = aead_setauthsize,
 			.encrypt = aead_encrypt,
 			.decrypt = aead_decrypt,
@@ -1866,7 +1906,7 @@ static struct caam_aead_alg driver_aeads[] = {
 						   "cbc-des3_ede-caam-qi",
 				.cra_blocksize = DES3_EDE_BLOCK_SIZE,
 			},
-			.setkey = aead_setkey,
+			.setkey = des3_aead_setkey,
 			.setauthsize = aead_setauthsize,
 			.encrypt = aead_encrypt,
 			.decrypt = aead_decrypt,
@@ -1889,7 +1929,7 @@ static struct caam_aead_alg driver_aeads[] = {
 						   "cbc-des3_ede-caam-qi",
 				.cra_blocksize = DES3_EDE_BLOCK_SIZE,
 			},
-			.setkey = aead_setkey,
+			.setkey = des3_aead_setkey,
 			.setauthsize = aead_setauthsize,
 			.encrypt = aead_encrypt,
 			.decrypt = aead_decrypt,
@@ -1912,7 +1952,7 @@ static struct caam_aead_alg driver_aeads[] = {
 						   "cbc-des3_ede-caam-qi",
 				.cra_blocksize = DES3_EDE_BLOCK_SIZE,
 			},
-			.setkey = aead_setkey,
+			.setkey = des3_aead_setkey,
 			.setauthsize = aead_setauthsize,
 			.encrypt = aead_encrypt,
 			.decrypt = aead_decrypt,
@@ -1935,7 +1975,7 @@ static struct caam_aead_alg driver_aeads[] = {
 						   "cbc-des3_ede-caam-qi",
 				.cra_blocksize = DES3_EDE_BLOCK_SIZE,
 			},
-			.setkey = aead_setkey,
+			.setkey = des3_aead_setkey,
 			.setauthsize = aead_setauthsize,
 			.encrypt = aead_encrypt,
 			.decrypt = aead_decrypt,
@@ -1958,7 +1998,7 @@ static struct caam_aead_alg driver_aeads[] = {
 						   "cbc-des3_ede-caam-qi",
 				.cra_blocksize = DES3_EDE_BLOCK_SIZE,
 			},
-			.setkey = aead_setkey,
+			.setkey = des3_aead_setkey,
 			.setauthsize = aead_setauthsize,
 			.encrypt = aead_encrypt,
 			.decrypt = aead_decrypt,
@@ -1981,7 +2021,7 @@ static struct caam_aead_alg driver_aeads[] = {
 						   "cbc-des3_ede-caam-qi",
 				.cra_blocksize = DES3_EDE_BLOCK_SIZE,
 			},
-			.setkey = aead_setkey,
+			.setkey = des3_aead_setkey,
 			.setauthsize = aead_setauthsize,
 			.encrypt = aead_encrypt,
 			.decrypt = aead_decrypt,
@@ -2004,7 +2044,7 @@ static struct caam_aead_alg driver_aeads[] = {
 						   "cbc-des3_ede-caam-qi",
 				.cra_blocksize = DES3_EDE_BLOCK_SIZE,
 			},
-			.setkey = aead_setkey,
+			.setkey = des3_aead_setkey,
 			.setauthsize = aead_setauthsize,
 			.encrypt = aead_encrypt,
 			.decrypt = aead_decrypt,
@@ -2027,7 +2067,7 @@ static struct caam_aead_alg driver_aeads[] = {
 						   "cbc-des3_ede-caam-qi",
 				.cra_blocksize = DES3_EDE_BLOCK_SIZE,
 			},
-			.setkey = aead_setkey,
+			.setkey = des3_aead_setkey,
 			.setauthsize = aead_setauthsize,
 			.encrypt = aead_encrypt,
 			.decrypt = aead_decrypt,
@@ -2050,7 +2090,7 @@ static struct caam_aead_alg driver_aeads[] = {
 						   "cbc-des3_ede-caam-qi",
 				.cra_blocksize = DES3_EDE_BLOCK_SIZE,
 			},
-			.setkey = aead_setkey,
+			.setkey = des3_aead_setkey,
 			.setauthsize = aead_setauthsize,
 			.encrypt = aead_encrypt,
 			.decrypt = aead_decrypt,
diff --git a/drivers/crypto/caam/caamalg_qi2.c b/drivers/crypto/caam/caamalg_qi2.c
index c2c1abc68f81..33a4df6b81de 100644
--- a/drivers/crypto/caam/caamalg_qi2.c
+++ b/drivers/crypto/caam/caamalg_qi2.c
@@ -323,6 +323,39 @@ badkey:
 	return -EINVAL;
 }
 
+static int des3_aead_setkey(struct crypto_aead *aead, const u8 *key,
+			    unsigned int keylen)
+{
+	struct crypto_authenc_keys keys;
+	u32 flags;
+	int err;
+
+	err = crypto_authenc_extractkeys(&keys, key, keylen);
+	if (unlikely(err))
+		goto badkey;
+
+	err = -EINVAL;
+	if (keys.enckeylen != DES3_EDE_KEY_SIZE)
+		goto badkey;
+
+	flags = crypto_aead_get_flags(aead);
+	err = __des3_verify_key(&flags, keys.enckey);
+	if (unlikely(err)) {
+		crypto_aead_set_flags(aead, flags);
+		goto out;
+	}
+
+	err = aead_setkey(aead, key, keylen);
+
+out:
+	memzero_explicit(&keys, sizeof(keys));
+	return err;
+
+badkey:
+	crypto_aead_set_flags(aead, CRYPTO_TFM_RES_BAD_KEY_LEN);
+	goto out;
+}
+
 static struct aead_edesc *aead_edesc_alloc(struct aead_request *req,
 					   bool encrypt)
 {
@@ -938,6 +971,13 @@ static int skcipher_setkey(struct crypto_skcipher *skcipher, const u8 *key,
 	return 0;
 }
 
+static int des3_skcipher_setkey(struct crypto_skcipher *skcipher,
+				const u8 *key, unsigned int keylen)
+{
+	return unlikely(des3_verify_key(skcipher, key)) ?:
+	       skcipher_setkey(skcipher, key, keylen);
+}
+
 static int xts_skcipher_setkey(struct crypto_skcipher *skcipher, const u8 *key,
 			       unsigned int keylen)
 {
@@ -1484,7 +1524,7 @@ static struct caam_skcipher_alg driver_algs[] = {
 				.cra_driver_name = "cbc-3des-caam-qi2",
 				.cra_blocksize = DES3_EDE_BLOCK_SIZE,
 			},
-			.setkey = skcipher_setkey,
+			.setkey = des3_skcipher_setkey,
 			.encrypt = skcipher_encrypt,
 			.decrypt = skcipher_decrypt,
 			.min_keysize = DES3_EDE_KEY_SIZE,
@@ -1916,7 +1956,7 @@ static struct caam_aead_alg driver_aeads[] = {
 						   "cbc-des3_ede-caam-qi2",
 				.cra_blocksize = DES3_EDE_BLOCK_SIZE,
 			},
-			.setkey = aead_setkey,
+			.setkey = des3_aead_setkey,
 			.setauthsize = aead_setauthsize,
 			.encrypt = aead_encrypt,
 			.decrypt = aead_decrypt,
@@ -1938,7 +1978,7 @@ static struct caam_aead_alg driver_aeads[] = {
 						   "cbc-des3_ede-caam-qi2",
 				.cra_blocksize = DES3_EDE_BLOCK_SIZE,
 			},
-			.setkey = aead_setkey,
+			.setkey = des3_aead_setkey,
 			.setauthsize = aead_setauthsize,
 			.encrypt = aead_encrypt,
 			.decrypt = aead_decrypt,
@@ -1961,7 +2001,7 @@ static struct caam_aead_alg driver_aeads[] = {
 						   "cbc-des3_ede-caam-qi2",
 				.cra_blocksize = DES3_EDE_BLOCK_SIZE,
 			},
-			.setkey = aead_setkey,
+			.setkey = des3_aead_setkey,
 			.setauthsize = aead_setauthsize,
 			.encrypt = aead_encrypt,
 			.decrypt = aead_decrypt,
@@ -1984,7 +2024,7 @@ static struct caam_aead_alg driver_aeads[] = {
 						   "cbc-des3_ede-caam-qi2",
 				.cra_blocksize = DES3_EDE_BLOCK_SIZE,
 			},
-			.setkey = aead_setkey,
+			.setkey = des3_aead_setkey,
 			.setauthsize = aead_setauthsize,
 			.encrypt = aead_encrypt,
 			.decrypt = aead_decrypt,
@@ -2007,7 +2047,7 @@ static struct caam_aead_alg driver_aeads[] = {
 						   "cbc-des3_ede-caam-qi2",
 				.cra_blocksize = DES3_EDE_BLOCK_SIZE,
 			},
-			.setkey = aead_setkey,
+			.setkey = des3_aead_setkey,
 			.setauthsize = aead_setauthsize,
 			.encrypt = aead_encrypt,
 			.decrypt = aead_decrypt,
@@ -2030,7 +2070,7 @@ static struct caam_aead_alg driver_aeads[] = {
 						   "cbc-des3_ede-caam-qi2",
 				.cra_blocksize = DES3_EDE_BLOCK_SIZE,
 			},
-			.setkey = aead_setkey,
+			.setkey = des3_aead_setkey,
 			.setauthsize = aead_setauthsize,
 			.encrypt = aead_encrypt,
 			.decrypt = aead_decrypt,
@@ -2053,7 +2093,7 @@ static struct caam_aead_alg driver_aeads[] = {
 						   "cbc-des3_ede-caam-qi2",
 				.cra_blocksize = DES3_EDE_BLOCK_SIZE,
 			},
-			.setkey = aead_setkey,
+			.setkey = des3_aead_setkey,
 			.setauthsize = aead_setauthsize,
 			.encrypt = aead_encrypt,
 			.decrypt = aead_decrypt,
@@ -2076,7 +2116,7 @@ static struct caam_aead_alg driver_aeads[] = {
 						   "cbc-des3_ede-caam-qi2",
 				.cra_blocksize = DES3_EDE_BLOCK_SIZE,
 			},
-			.setkey = aead_setkey,
+			.setkey = des3_aead_setkey,
 			.setauthsize = aead_setauthsize,
 			.encrypt = aead_encrypt,
 			.decrypt = aead_decrypt,
@@ -2099,7 +2139,7 @@ static struct caam_aead_alg driver_aeads[] = {
 						   "cbc-des3_ede-caam-qi2",
 				.cra_blocksize = DES3_EDE_BLOCK_SIZE,
 			},
-			.setkey = aead_setkey,
+			.setkey = des3_aead_setkey,
 			.setauthsize = aead_setauthsize,
 			.encrypt = aead_encrypt,
 			.decrypt = aead_decrypt,
@@ -2122,7 +2162,7 @@ static struct caam_aead_alg driver_aeads[] = {
 						   "cbc-des3_ede-caam-qi2",
 				.cra_blocksize = DES3_EDE_BLOCK_SIZE,
 			},
-			.setkey = aead_setkey,
+			.setkey = des3_aead_setkey,
 			.setauthsize = aead_setauthsize,
 			.encrypt = aead_encrypt,
 			.decrypt = aead_decrypt,
@@ -2145,7 +2185,7 @@ static struct caam_aead_alg driver_aeads[] = {
 						   "cbc-des3_ede-caam-qi2",
 				.cra_blocksize = DES3_EDE_BLOCK_SIZE,
 			},
-			.setkey = aead_setkey,
+			.setkey = des3_aead_setkey,
 			.setauthsize = aead_setauthsize,
 			.encrypt = aead_encrypt,
 			.decrypt = aead_decrypt,
@@ -2168,7 +2208,7 @@ static struct caam_aead_alg driver_aeads[] = {
 						   "cbc-des3_ede-caam-qi2",
 				.cra_blocksize = DES3_EDE_BLOCK_SIZE,
 			},
-			.setkey = aead_setkey,
+			.setkey = des3_aead_setkey,
 			.setauthsize = aead_setauthsize,
 			.encrypt = aead_encrypt,
 			.decrypt = aead_decrypt,
@@ -2854,6 +2894,7 @@ struct caam_hash_state {
 	struct caam_request caam_req;
 	dma_addr_t buf_dma;
 	dma_addr_t ctx_dma;
+	int ctx_dma_len;
 	u8 buf_0[CAAM_MAX_HASH_BLOCK_SIZE] ____cacheline_aligned;
 	int buflen_0;
 	u8 buf_1[CAAM_MAX_HASH_BLOCK_SIZE] ____cacheline_aligned;
@@ -2927,6 +2968,7 @@ static inline int ctx_map_to_qm_sg(struct device *dev,
 				   struct caam_hash_state *state, int ctx_len,
 				   struct dpaa2_sg_entry *qm_sg, u32 flag)
 {
+	state->ctx_dma_len = ctx_len;
 	state->ctx_dma = dma_map_single(dev, state->caam_ctx, ctx_len, flag);
 	if (dma_mapping_error(dev, state->ctx_dma)) {
 		dev_err(dev, "unable to map ctx\n");
@@ -3018,13 +3060,13 @@ static void split_key_sh_done(void *cbk_ctx, u32 err)
 }
 
 /* Digest hash size if it is too large */
-static int hash_digest_key(struct caam_hash_ctx *ctx, const u8 *key_in,
-			   u32 *keylen, u8 *key_out, u32 digestsize)
+static int hash_digest_key(struct caam_hash_ctx *ctx, u32 *keylen, u8 *key,
+			   u32 digestsize)
 {
 	struct caam_request *req_ctx;
 	u32 *desc;
 	struct split_key_sh_result result;
-	dma_addr_t src_dma, dst_dma;
+	dma_addr_t key_dma;
 	struct caam_flc *flc;
 	dma_addr_t flc_dma;
 	int ret = -ENOMEM;
@@ -3041,17 +3083,10 @@ static int hash_digest_key(struct caam_hash_ctx *ctx, const u8 *key_in,
 	if (!flc)
 		goto err_flc;
 
-	src_dma = dma_map_single(ctx->dev, (void *)key_in, *keylen,
-				 DMA_TO_DEVICE);
-	if (dma_mapping_error(ctx->dev, src_dma)) {
-		dev_err(ctx->dev, "unable to map key input memory\n");
-		goto err_src_dma;
-	}
-	dst_dma = dma_map_single(ctx->dev, (void *)key_out, digestsize,
-				 DMA_FROM_DEVICE);
-	if (dma_mapping_error(ctx->dev, dst_dma)) {
-		dev_err(ctx->dev, "unable to map key output memory\n");
-		goto err_dst_dma;
+	key_dma = dma_map_single(ctx->dev, key, *keylen, DMA_BIDIRECTIONAL);
+	if (dma_mapping_error(ctx->dev, key_dma)) {
+		dev_err(ctx->dev, "unable to map key memory\n");
+		goto err_key_dma;
 	}
 
 	desc = flc->sh_desc;
@@ -3076,14 +3111,14 @@ static int hash_digest_key(struct caam_hash_ctx *ctx, const u8 *key_in,
 
 	dpaa2_fl_set_final(in_fle, true);
 	dpaa2_fl_set_format(in_fle, dpaa2_fl_single);
-	dpaa2_fl_set_addr(in_fle, src_dma);
+	dpaa2_fl_set_addr(in_fle, key_dma);
 	dpaa2_fl_set_len(in_fle, *keylen);
 	dpaa2_fl_set_format(out_fle, dpaa2_fl_single);
-	dpaa2_fl_set_addr(out_fle, dst_dma);
+	dpaa2_fl_set_addr(out_fle, key_dma);
 	dpaa2_fl_set_len(out_fle, digestsize);
 
 	print_hex_dump_debug("key_in@" __stringify(__LINE__)": ",
-			     DUMP_PREFIX_ADDRESS, 16, 4, key_in, *keylen, 1);
+			     DUMP_PREFIX_ADDRESS, 16, 4, key, *keylen, 1);
 	print_hex_dump_debug("shdesc@" __stringify(__LINE__)": ",
 			     DUMP_PREFIX_ADDRESS, 16, 4, desc, desc_bytes(desc),
 			     1);
@@ -3103,17 +3138,15 @@ static int hash_digest_key(struct caam_hash_ctx *ctx, const u8 *key_in,
 		wait_for_completion(&result.completion);
 		ret = result.err;
 		print_hex_dump_debug("digested key@" __stringify(__LINE__)": ",
-				     DUMP_PREFIX_ADDRESS, 16, 4, key_in,
+				     DUMP_PREFIX_ADDRESS, 16, 4, key,
 				     digestsize, 1);
 	}
 
 	dma_unmap_single(ctx->dev, flc_dma, sizeof(flc->flc) + desc_bytes(desc),
 			 DMA_TO_DEVICE);
 err_flc_dma:
-	dma_unmap_single(ctx->dev, dst_dma, digestsize, DMA_FROM_DEVICE);
-err_dst_dma:
-	dma_unmap_single(ctx->dev, src_dma, *keylen, DMA_TO_DEVICE);
-err_src_dma:
+	dma_unmap_single(ctx->dev, key_dma, *keylen, DMA_BIDIRECTIONAL);
+err_key_dma:
 	kfree(flc);
 err_flc:
 	kfree(req_ctx);
@@ -3135,12 +3168,10 @@ static int ahash_setkey(struct crypto_ahash *ahash, const u8 *key,
 	dev_dbg(ctx->dev, "keylen %d blocksize %d\n", keylen, blocksize);
 
 	if (keylen > blocksize) {
-		hashed_key = kmalloc_array(digestsize, sizeof(*hashed_key),
-					   GFP_KERNEL | GFP_DMA);
+		hashed_key = kmemdup(key, keylen, GFP_KERNEL | GFP_DMA);
 		if (!hashed_key)
 			return -ENOMEM;
-		ret = hash_digest_key(ctx, key, &keylen, hashed_key,
-				      digestsize);
+		ret = hash_digest_key(ctx, &keylen, hashed_key, digestsize);
 		if (ret)
 			goto bad_free_key;
 		key = hashed_key;
@@ -3165,14 +3196,12 @@ bad_free_key:
 }
 
 static inline void ahash_unmap(struct device *dev, struct ahash_edesc *edesc,
-			       struct ahash_request *req, int dst_len)
+			       struct ahash_request *req)
 {
 	struct caam_hash_state *state = ahash_request_ctx(req);
 
 	if (edesc->src_nents)
 		dma_unmap_sg(dev, req->src, edesc->src_nents, DMA_TO_DEVICE);
-	if (edesc->dst_dma)
-		dma_unmap_single(dev, edesc->dst_dma, dst_len, DMA_FROM_DEVICE);
 
 	if (edesc->qm_sg_bytes)
 		dma_unmap_single(dev, edesc->qm_sg_dma, edesc->qm_sg_bytes,
@@ -3187,18 +3216,15 @@ static inline void ahash_unmap(struct device *dev, struct ahash_edesc *edesc,
 
 static inline void ahash_unmap_ctx(struct device *dev,
 				   struct ahash_edesc *edesc,
-				   struct ahash_request *req, int dst_len,
-				   u32 flag)
+				   struct ahash_request *req, u32 flag)
 {
-	struct crypto_ahash *ahash = crypto_ahash_reqtfm(req);
-	struct caam_hash_ctx *ctx = crypto_ahash_ctx(ahash);
 	struct caam_hash_state *state = ahash_request_ctx(req);
 
 	if (state->ctx_dma) {
-		dma_unmap_single(dev, state->ctx_dma, ctx->ctx_len, flag);
+		dma_unmap_single(dev, state->ctx_dma, state->ctx_dma_len, flag);
 		state->ctx_dma = 0;
 	}
-	ahash_unmap(dev, edesc, req, dst_len);
+	ahash_unmap(dev, edesc, req);
 }
 
 static void ahash_done(void *cbk_ctx, u32 status)
@@ -3219,16 +3245,13 @@ static void ahash_done(void *cbk_ctx, u32 status)
 		ecode = -EIO;
 	}
 
-	ahash_unmap(ctx->dev, edesc, req, digestsize);
+	ahash_unmap_ctx(ctx->dev, edesc, req, DMA_FROM_DEVICE);
+	memcpy(req->result, state->caam_ctx, digestsize);
 	qi_cache_free(edesc);
 
 	print_hex_dump_debug("ctx@" __stringify(__LINE__)": ",
 			     DUMP_PREFIX_ADDRESS, 16, 4, state->caam_ctx,
 			     ctx->ctx_len, 1);
-	if (req->result)
-		print_hex_dump_debug("result@" __stringify(__LINE__)": ",
-				     DUMP_PREFIX_ADDRESS, 16, 4, req->result,
-				     digestsize, 1);
 
 	req->base.complete(&req->base, ecode);
 }
@@ -3250,7 +3273,7 @@ static void ahash_done_bi(void *cbk_ctx, u32 status)
 		ecode = -EIO;
 	}
 
-	ahash_unmap_ctx(ctx->dev, edesc, req, ctx->ctx_len, DMA_BIDIRECTIONAL);
+	ahash_unmap_ctx(ctx->dev, edesc, req, DMA_BIDIRECTIONAL);
 	switch_buf(state);
 	qi_cache_free(edesc);
 
@@ -3283,16 +3306,13 @@ static void ahash_done_ctx_src(void *cbk_ctx, u32 status)
 		ecode = -EIO;
 	}
 
-	ahash_unmap_ctx(ctx->dev, edesc, req, digestsize, DMA_TO_DEVICE);
+	ahash_unmap_ctx(ctx->dev, edesc, req, DMA_BIDIRECTIONAL);
+	memcpy(req->result, state->caam_ctx, digestsize);
 	qi_cache_free(edesc);
 
 	print_hex_dump_debug("ctx@" __stringify(__LINE__)": ",
 			     DUMP_PREFIX_ADDRESS, 16, 4, state->caam_ctx,
 			     ctx->ctx_len, 1);
-	if (req->result)
-		print_hex_dump_debug("result@" __stringify(__LINE__)": ",
-				     DUMP_PREFIX_ADDRESS, 16, 4, req->result,
-				     digestsize, 1);
 
 	req->base.complete(&req->base, ecode);
 }
@@ -3314,7 +3334,7 @@ static void ahash_done_ctx_dst(void *cbk_ctx, u32 status)
 		ecode = -EIO;
 	}
 
-	ahash_unmap_ctx(ctx->dev, edesc, req, ctx->ctx_len, DMA_FROM_DEVICE);
+	ahash_unmap_ctx(ctx->dev, edesc, req, DMA_FROM_DEVICE);
 	switch_buf(state);
 	qi_cache_free(edesc);
 
@@ -3452,7 +3472,7 @@ static int ahash_update_ctx(struct ahash_request *req)
 
 	return ret;
 unmap_ctx:
-	ahash_unmap_ctx(ctx->dev, edesc, req, ctx->ctx_len, DMA_BIDIRECTIONAL);
+	ahash_unmap_ctx(ctx->dev, edesc, req, DMA_BIDIRECTIONAL);
 	qi_cache_free(edesc);
 	return ret;
 }
@@ -3484,7 +3504,7 @@ static int ahash_final_ctx(struct ahash_request *req)
 	sg_table = &edesc->sgt[0];
 
 	ret = ctx_map_to_qm_sg(ctx->dev, state, ctx->ctx_len, sg_table,
-			       DMA_TO_DEVICE);
+			       DMA_BIDIRECTIONAL);
 	if (ret)
 		goto unmap_ctx;
 
@@ -3503,22 +3523,13 @@ static int ahash_final_ctx(struct ahash_request *req)
 	}
 	edesc->qm_sg_bytes = qm_sg_bytes;
 
-	edesc->dst_dma = dma_map_single(ctx->dev, req->result, digestsize,
-					DMA_FROM_DEVICE);
-	if (dma_mapping_error(ctx->dev, edesc->dst_dma)) {
-		dev_err(ctx->dev, "unable to map dst\n");
-		edesc->dst_dma = 0;
-		ret = -ENOMEM;
-		goto unmap_ctx;
-	}
-
 	memset(&req_ctx->fd_flt, 0, sizeof(req_ctx->fd_flt));
 	dpaa2_fl_set_final(in_fle, true);
 	dpaa2_fl_set_format(in_fle, dpaa2_fl_sg);
 	dpaa2_fl_set_addr(in_fle, edesc->qm_sg_dma);
 	dpaa2_fl_set_len(in_fle, ctx->ctx_len + buflen);
 	dpaa2_fl_set_format(out_fle, dpaa2_fl_single);
-	dpaa2_fl_set_addr(out_fle, edesc->dst_dma);
+	dpaa2_fl_set_addr(out_fle, state->ctx_dma);
 	dpaa2_fl_set_len(out_fle, digestsize);
 
 	req_ctx->flc = &ctx->flc[FINALIZE];
@@ -3533,7 +3544,7 @@ static int ahash_final_ctx(struct ahash_request *req)
 		return ret;
 
 unmap_ctx:
-	ahash_unmap_ctx(ctx->dev, edesc, req, digestsize, DMA_FROM_DEVICE);
+	ahash_unmap_ctx(ctx->dev, edesc, req, DMA_BIDIRECTIONAL);
 	qi_cache_free(edesc);
 	return ret;
 }
@@ -3586,7 +3597,7 @@ static int ahash_finup_ctx(struct ahash_request *req)
 	sg_table = &edesc->sgt[0];
 
 	ret = ctx_map_to_qm_sg(ctx->dev, state, ctx->ctx_len, sg_table,
-			       DMA_TO_DEVICE);
+			       DMA_BIDIRECTIONAL);
 	if (ret)
 		goto unmap_ctx;
 
@@ -3605,22 +3616,13 @@ static int ahash_finup_ctx(struct ahash_request *req)
 	}
 	edesc->qm_sg_bytes = qm_sg_bytes;
 
-	edesc->dst_dma = dma_map_single(ctx->dev, req->result, digestsize,
-					DMA_FROM_DEVICE);
-	if (dma_mapping_error(ctx->dev, edesc->dst_dma)) {
-		dev_err(ctx->dev, "unable to map dst\n");
-		edesc->dst_dma = 0;
-		ret = -ENOMEM;
-		goto unmap_ctx;
-	}
-
 	memset(&req_ctx->fd_flt, 0, sizeof(req_ctx->fd_flt));
 	dpaa2_fl_set_final(in_fle, true);
 	dpaa2_fl_set_format(in_fle, dpaa2_fl_sg);
 	dpaa2_fl_set_addr(in_fle, edesc->qm_sg_dma);
 	dpaa2_fl_set_len(in_fle, ctx->ctx_len + buflen + req->nbytes);
 	dpaa2_fl_set_format(out_fle, dpaa2_fl_single);
-	dpaa2_fl_set_addr(out_fle, edesc->dst_dma);
+	dpaa2_fl_set_addr(out_fle, state->ctx_dma);
 	dpaa2_fl_set_len(out_fle, digestsize);
 
 	req_ctx->flc = &ctx->flc[FINALIZE];
@@ -3635,7 +3637,7 @@ static int ahash_finup_ctx(struct ahash_request *req)
 		return ret;
 
 unmap_ctx:
-	ahash_unmap_ctx(ctx->dev, edesc, req, digestsize, DMA_FROM_DEVICE);
+	ahash_unmap_ctx(ctx->dev, edesc, req, DMA_BIDIRECTIONAL);
 	qi_cache_free(edesc);
 	return ret;
 }
@@ -3704,18 +3706,19 @@ static int ahash_digest(struct ahash_request *req)
 		dpaa2_fl_set_addr(in_fle, sg_dma_address(req->src));
 	}
 
-	edesc->dst_dma = dma_map_single(ctx->dev, req->result, digestsize,
+	state->ctx_dma_len = digestsize;
+	state->ctx_dma = dma_map_single(ctx->dev, state->caam_ctx, digestsize,
 					DMA_FROM_DEVICE);
-	if (dma_mapping_error(ctx->dev, edesc->dst_dma)) {
-		dev_err(ctx->dev, "unable to map dst\n");
-		edesc->dst_dma = 0;
+	if (dma_mapping_error(ctx->dev, state->ctx_dma)) {
+		dev_err(ctx->dev, "unable to map ctx\n");
+		state->ctx_dma = 0;
 		goto unmap;
 	}
 
 	dpaa2_fl_set_final(in_fle, true);
 	dpaa2_fl_set_len(in_fle, req->nbytes);
 	dpaa2_fl_set_format(out_fle, dpaa2_fl_single);
-	dpaa2_fl_set_addr(out_fle, edesc->dst_dma);
+	dpaa2_fl_set_addr(out_fle, state->ctx_dma);
 	dpaa2_fl_set_len(out_fle, digestsize);
 
 	req_ctx->flc = &ctx->flc[DIGEST];
@@ -3729,7 +3732,7 @@ static int ahash_digest(struct ahash_request *req)
 		return ret;
 
 unmap:
-	ahash_unmap(ctx->dev, edesc, req, digestsize);
+	ahash_unmap_ctx(ctx->dev, edesc, req, DMA_FROM_DEVICE);
 	qi_cache_free(edesc);
 	return ret;
 }
@@ -3755,27 +3758,39 @@ static int ahash_final_no_ctx(struct ahash_request *req)
 	if (!edesc)
 		return ret;
 
-	state->buf_dma = dma_map_single(ctx->dev, buf, buflen, DMA_TO_DEVICE);
-	if (dma_mapping_error(ctx->dev, state->buf_dma)) {
-		dev_err(ctx->dev, "unable to map src\n");
-		goto unmap;
+	if (buflen) {
+		state->buf_dma = dma_map_single(ctx->dev, buf, buflen,
+						DMA_TO_DEVICE);
+		if (dma_mapping_error(ctx->dev, state->buf_dma)) {
+			dev_err(ctx->dev, "unable to map src\n");
+			goto unmap;
+		}
 	}
 
-	edesc->dst_dma = dma_map_single(ctx->dev, req->result, digestsize,
+	state->ctx_dma_len = digestsize;
+	state->ctx_dma = dma_map_single(ctx->dev, state->caam_ctx, digestsize,
 					DMA_FROM_DEVICE);
-	if (dma_mapping_error(ctx->dev, edesc->dst_dma)) {
-		dev_err(ctx->dev, "unable to map dst\n");
-		edesc->dst_dma = 0;
+	if (dma_mapping_error(ctx->dev, state->ctx_dma)) {
+		dev_err(ctx->dev, "unable to map ctx\n");
+		state->ctx_dma = 0;
 		goto unmap;
 	}
 
 	memset(&req_ctx->fd_flt, 0, sizeof(req_ctx->fd_flt));
 	dpaa2_fl_set_final(in_fle, true);
-	dpaa2_fl_set_format(in_fle, dpaa2_fl_single);
-	dpaa2_fl_set_addr(in_fle, state->buf_dma);
-	dpaa2_fl_set_len(in_fle, buflen);
+	/*
+	 * crypto engine requires the input entry to be present when
+	 * "frame list" FD is used.
+	 * Since engine does not support FMT=2'b11 (unused entry type), leaving
+	 * in_fle zeroized (except for "Final" flag) is the best option.
+	 */
+	if (buflen) {
+		dpaa2_fl_set_format(in_fle, dpaa2_fl_single);
+		dpaa2_fl_set_addr(in_fle, state->buf_dma);
+		dpaa2_fl_set_len(in_fle, buflen);
+	}
 	dpaa2_fl_set_format(out_fle, dpaa2_fl_single);
-	dpaa2_fl_set_addr(out_fle, edesc->dst_dma);
+	dpaa2_fl_set_addr(out_fle, state->ctx_dma);
 	dpaa2_fl_set_len(out_fle, digestsize);
 
 	req_ctx->flc = &ctx->flc[DIGEST];
@@ -3790,7 +3805,7 @@ static int ahash_final_no_ctx(struct ahash_request *req)
 		return ret;
 
 unmap:
-	ahash_unmap(ctx->dev, edesc, req, digestsize);
+	ahash_unmap_ctx(ctx->dev, edesc, req, DMA_FROM_DEVICE);
 	qi_cache_free(edesc);
 	return ret;
 }
@@ -3870,6 +3885,7 @@ static int ahash_update_no_ctx(struct ahash_request *req)
 		}
 		edesc->qm_sg_bytes = qm_sg_bytes;
 
+		state->ctx_dma_len = ctx->ctx_len;
 		state->ctx_dma = dma_map_single(ctx->dev, state->caam_ctx,
 						ctx->ctx_len, DMA_FROM_DEVICE);
 		if (dma_mapping_error(ctx->dev, state->ctx_dma)) {
@@ -3918,7 +3934,7 @@ static int ahash_update_no_ctx(struct ahash_request *req)
 
 	return ret;
 unmap_ctx:
-	ahash_unmap_ctx(ctx->dev, edesc, req, ctx->ctx_len, DMA_TO_DEVICE);
+	ahash_unmap_ctx(ctx->dev, edesc, req, DMA_TO_DEVICE);
 	qi_cache_free(edesc);
 	return ret;
 }
@@ -3983,11 +3999,12 @@ static int ahash_finup_no_ctx(struct ahash_request *req)
 	}
 	edesc->qm_sg_bytes = qm_sg_bytes;
 
-	edesc->dst_dma = dma_map_single(ctx->dev, req->result, digestsize,
+	state->ctx_dma_len = digestsize;
+	state->ctx_dma = dma_map_single(ctx->dev, state->caam_ctx, digestsize,
 					DMA_FROM_DEVICE);
-	if (dma_mapping_error(ctx->dev, edesc->dst_dma)) {
-		dev_err(ctx->dev, "unable to map dst\n");
-		edesc->dst_dma = 0;
+	if (dma_mapping_error(ctx->dev, state->ctx_dma)) {
+		dev_err(ctx->dev, "unable to map ctx\n");
+		state->ctx_dma = 0;
 		ret = -ENOMEM;
 		goto unmap;
 	}
@@ -3998,7 +4015,7 @@ static int ahash_finup_no_ctx(struct ahash_request *req)
 	dpaa2_fl_set_addr(in_fle, edesc->qm_sg_dma);
 	dpaa2_fl_set_len(in_fle, buflen + req->nbytes);
 	dpaa2_fl_set_format(out_fle, dpaa2_fl_single);
-	dpaa2_fl_set_addr(out_fle, edesc->dst_dma);
+	dpaa2_fl_set_addr(out_fle, state->ctx_dma);
 	dpaa2_fl_set_len(out_fle, digestsize);
 
 	req_ctx->flc = &ctx->flc[DIGEST];
@@ -4013,7 +4030,7 @@ static int ahash_finup_no_ctx(struct ahash_request *req)
 
 	return ret;
 unmap:
-	ahash_unmap(ctx->dev, edesc, req, digestsize);
+	ahash_unmap_ctx(ctx->dev, edesc, req, DMA_FROM_DEVICE);
 	qi_cache_free(edesc);
 	return -ENOMEM;
 }
@@ -4100,6 +4117,7 @@ static int ahash_update_first(struct ahash_request *req)
 			scatterwalk_map_and_copy(next_buf, req->src, to_hash,
 						 *next_buflen, 0);
 
+		state->ctx_dma_len = ctx->ctx_len;
 		state->ctx_dma = dma_map_single(ctx->dev, state->caam_ctx,
 						ctx->ctx_len, DMA_FROM_DEVICE);
 		if (dma_mapping_error(ctx->dev, state->ctx_dma)) {
@@ -4143,7 +4161,7 @@ static int ahash_update_first(struct ahash_request *req)
 
 	return ret;
 unmap_ctx:
-	ahash_unmap_ctx(ctx->dev, edesc, req, ctx->ctx_len, DMA_TO_DEVICE);
+	ahash_unmap_ctx(ctx->dev, edesc, req, DMA_TO_DEVICE);
 	qi_cache_free(edesc);
 	return ret;
 }
@@ -4162,6 +4180,7 @@ static int ahash_init(struct ahash_request *req)
 	state->final = ahash_final_no_ctx;
 
 	state->ctx_dma = 0;
+	state->ctx_dma_len = 0;
 	state->current_buf = 0;
 	state->buf_dma = 0;
 	state->buflen_0 = 0;
diff --git a/drivers/crypto/caam/caamalg_qi2.h b/drivers/crypto/caam/caamalg_qi2.h
index 20890780fb82..be5085451053 100644
--- a/drivers/crypto/caam/caamalg_qi2.h
+++ b/drivers/crypto/caam/caamalg_qi2.h
@@ -162,14 +162,12 @@ struct skcipher_edesc {
 
 /*
  * ahash_edesc - s/w-extended ahash descriptor
- * @dst_dma: I/O virtual address of req->result
  * @qm_sg_dma: I/O virtual address of h/w link table
  * @src_nents: number of segments in input scatterlist
  * @qm_sg_bytes: length of dma mapped qm_sg space
  * @sgt: pointer to h/w link table
  */
 struct ahash_edesc {
-	dma_addr_t dst_dma;
 	dma_addr_t qm_sg_dma;
 	int src_nents;
 	int qm_sg_bytes;
diff --git a/drivers/crypto/caam/caamhash.c b/drivers/crypto/caam/caamhash.c
index b1eadc6652b5..7205d9f4029e 100644
--- a/drivers/crypto/caam/caamhash.c
+++ b/drivers/crypto/caam/caamhash.c
@@ -865,19 +865,18 @@ static int ahash_update_ctx(struct ahash_request *req)
 		if (ret)
 			goto unmap_ctx;
 
-		if (mapped_nents) {
+		if (mapped_nents)
 			sg_to_sec4_sg_last(req->src, mapped_nents,
 					   edesc->sec4_sg + sec4_sg_src_index,
 					   0);
-			if (*next_buflen)
-				scatterwalk_map_and_copy(next_buf, req->src,
-							 to_hash - *buflen,
-							 *next_buflen, 0);
-		} else {
+		else
 			sg_to_sec4_set_last(edesc->sec4_sg + sec4_sg_src_index -
 					    1);
-		}
 
+		if (*next_buflen)
+			scatterwalk_map_and_copy(next_buf, req->src,
+						 to_hash - *buflen,
+						 *next_buflen, 0);
 		desc = edesc->hw_desc;
 
 		edesc->sec4_sg_dma = dma_map_single(jrdev, edesc->sec4_sg,
diff --git a/drivers/crypto/caam/caampkc.c b/drivers/crypto/caam/caampkc.c
index 58285642306e..fe24485274e1 100644
--- a/drivers/crypto/caam/caampkc.c
+++ b/drivers/crypto/caam/caampkc.c
@@ -994,8 +994,6 @@ static void caam_rsa_exit_tfm(struct crypto_akcipher *tfm)
 static struct akcipher_alg caam_rsa = {
 	.encrypt = caam_rsa_enc,
 	.decrypt = caam_rsa_dec,
-	.sign = caam_rsa_dec,
-	.verify = caam_rsa_enc,
 	.set_pub_key = caam_rsa_set_pub_key,
 	.set_priv_key = caam_rsa_set_priv_key,
 	.max_size = caam_rsa_max_size,
diff --git a/drivers/crypto/caam/ctrl.c b/drivers/crypto/caam/ctrl.c
index 858bdc9ab4a3..e2ba3d202da5 100644
--- a/drivers/crypto/caam/ctrl.c
+++ b/drivers/crypto/caam/ctrl.c
@@ -468,6 +468,24 @@ static int caam_get_era(struct caam_ctrl __iomem *ctrl)
 		return caam_get_era_from_hw(ctrl);
 }
 
+/*
+ * ERRATA: imx6 devices (imx6D, imx6Q, imx6DL, imx6S, imx6DP and imx6DQ)
+ * have an issue wherein AXI bus transactions may not occur in the correct
+ * order. This isn't a problem running single descriptors, but can be if
+ * running multiple concurrent descriptors. Reworking the driver to throttle
+ * to single requests is impractical, thus the workaround is to limit the AXI
+ * pipeline to a depth of 1 (from it's default of 4) to preclude this situation
+ * from occurring.
+ */
+static void handle_imx6_err005766(u32 *mcr)
+{
+	if (of_machine_is_compatible("fsl,imx6q") ||
+	    of_machine_is_compatible("fsl,imx6dl") ||
+	    of_machine_is_compatible("fsl,imx6qp"))
+		clrsetbits_32(mcr, MCFGR_AXIPIPE_MASK,
+			      1 << MCFGR_AXIPIPE_SHIFT);
+}
+
 static const struct of_device_id caam_match[] = {
 	{
 		.compatible = "fsl,sec-v4.0",
@@ -640,6 +658,8 @@ static int caam_probe(struct platform_device *pdev)
 			      (sizeof(dma_addr_t) == sizeof(u64) ?
 			       MCFGR_LONG_PTR : 0));
 
+	handle_imx6_err005766(&ctrl->mcr);
+
 	/*
 	 *  Read the Compile Time paramters and SCFGR to determine
 	 * if Virtualization is enabled for this platform
diff --git a/drivers/crypto/caam/error.c b/drivers/crypto/caam/error.c
index 21a70fd32f5d..a4129a35a330 100644
--- a/drivers/crypto/caam/error.c
+++ b/drivers/crypto/caam/error.c
@@ -138,7 +138,7 @@ static const struct {
 	{ 0x46, "Annotation length exceeds offset (reuse mode)"},
 	{ 0x48, "Annotation output enabled but ASA limited by ASAR (reuse mode)"},
 	{ 0x49, "Data offset correction exceeds input frame data length (reuse mode)"},
-	{ 0x4B, "Annotation output enabled but ASA cannote be expanded (frame list)"},
+	{ 0x4B, "Annotation output enabled but ASA cannot be expanded (frame list)"},
 	{ 0x51, "Unsupported IF reuse mode"},
 	{ 0x52, "Unsupported FL use mode"},
 	{ 0x53, "Unsupported RJD use mode"},
diff --git a/drivers/crypto/caam/intern.h b/drivers/crypto/caam/intern.h
index 5869ad58d497..3392615dc91b 100644
--- a/drivers/crypto/caam/intern.h
+++ b/drivers/crypto/caam/intern.h
@@ -49,13 +49,11 @@ struct caam_drv_private_jr {
 	atomic_t tfm_count ____cacheline_aligned;
 
 	/* Job ring info */
-	int ringsize;	/* Size of rings (assume input = output) */
 	struct caam_jrentry_info *entinfo;	/* Alloc'ed 1 per ring entry */
 	spinlock_t inplock ____cacheline_aligned; /* Input ring index lock */
-	int inp_ring_write_index;	/* Input index "tail" */
+	u32 inpring_avail;	/* Number of free entries in input ring */
 	int head;			/* entinfo (s/w ring) head index */
 	dma_addr_t *inpring;	/* Base of input ring, alloc DMA-safe */
-	spinlock_t outlock ____cacheline_aligned; /* Output ring index lock */
 	int out_ring_read_index;	/* Output index "tail" */
 	int tail;			/* entinfo (s/w ring) tail index */
 	struct jr_outentry *outring;	/* Base of output ring, DMA-safe */
diff --git a/drivers/crypto/caam/jr.c b/drivers/crypto/caam/jr.c
index d50085a03597..044a69b526f7 100644
--- a/drivers/crypto/caam/jr.c
+++ b/drivers/crypto/caam/jr.c
@@ -170,13 +170,13 @@ static void caam_jr_dequeue(unsigned long devarg)
 	void (*usercall)(struct device *dev, u32 *desc, u32 status, void *arg);
 	u32 *userdesc, userstatus;
 	void *userarg;
+	u32 outring_used = 0;
 
-	while (rd_reg32(&jrp->rregs->outring_used)) {
+	while (outring_used ||
+	       (outring_used = rd_reg32(&jrp->rregs->outring_used))) {
 
 		head = READ_ONCE(jrp->head);
 
-		spin_lock(&jrp->outlock);
-
 		sw_idx = tail = jrp->tail;
 		hw_idx = jrp->out_ring_read_index;
 
@@ -199,7 +199,7 @@ static void caam_jr_dequeue(unsigned long devarg)
 		/* mark completed, avoid matching on a recycled desc addr */
 		jrp->entinfo[sw_idx].desc_addr_dma = 0;
 
-		/* Stash callback params for use outside of lock */
+		/* Stash callback params */
 		usercall = jrp->entinfo[sw_idx].callbk;
 		userarg = jrp->entinfo[sw_idx].cbkarg;
 		userdesc = jrp->entinfo[sw_idx].desc_addr_virt;
@@ -213,7 +213,7 @@ static void caam_jr_dequeue(unsigned long devarg)
 		mb();
 
 		/* set done */
-		wr_reg32(&jrp->rregs->outring_rmvd, 1);
+		wr_reg32_relaxed(&jrp->rregs->outring_rmvd, 1);
 
 		jrp->out_ring_read_index = (jrp->out_ring_read_index + 1) &
 					   (JOBR_DEPTH - 1);
@@ -232,10 +232,9 @@ static void caam_jr_dequeue(unsigned long devarg)
 			jrp->tail = tail;
 		}
 
-		spin_unlock(&jrp->outlock);
-
 		/* Finally, execute user's callback */
 		usercall(dev, userdesc, userstatus, userarg);
+		outring_used--;
 	}
 
 	/* reenable / unmask IRQs */
@@ -345,7 +344,7 @@ int caam_jr_enqueue(struct device *dev, u32 *desc,
 	head = jrp->head;
 	tail = READ_ONCE(jrp->tail);
 
-	if (!rd_reg32(&jrp->rregs->inpring_avail) ||
+	if (!jrp->inpring_avail ||
 	    CIRC_SPACE(head, tail, JOBR_DEPTH) <= 0) {
 		spin_unlock_bh(&jrp->inplock);
 		dma_unmap_single(dev, desc_dma, desc_size, DMA_TO_DEVICE);
@@ -359,7 +358,7 @@ int caam_jr_enqueue(struct device *dev, u32 *desc,
 	head_entry->cbkarg = areq;
 	head_entry->desc_addr_dma = desc_dma;
 
-	jrp->inpring[jrp->inp_ring_write_index] = cpu_to_caam_dma(desc_dma);
+	jrp->inpring[head] = cpu_to_caam_dma(desc_dma);
 
 	/*
 	 * Guarantee that the descriptor's DMA address has been written to
@@ -368,18 +367,22 @@ int caam_jr_enqueue(struct device *dev, u32 *desc,
 	 */
 	smp_wmb();
 
-	jrp->inp_ring_write_index = (jrp->inp_ring_write_index + 1) &
-				    (JOBR_DEPTH - 1);
 	jrp->head = (head + 1) & (JOBR_DEPTH - 1);
 
 	/*
 	 * Ensure that all job information has been written before
-	 * notifying CAAM that a new job was added to the input ring.
+	 * notifying CAAM that a new job was added to the input ring
+	 * using a memory barrier. The wr_reg32() uses api iowrite32()
+	 * to do the register write. iowrite32() issues a memory barrier
+	 * before the write operation.
 	 */
-	wmb();
 
 	wr_reg32(&jrp->rregs->inpring_jobadd, 1);
 
+	jrp->inpring_avail--;
+	if (!jrp->inpring_avail)
+		jrp->inpring_avail = rd_reg32(&jrp->rregs->inpring_avail);
+
 	spin_unlock_bh(&jrp->inplock);
 
 	return 0;
@@ -431,7 +434,6 @@ static int caam_jr_init(struct device *dev)
 		jrp->entinfo[i].desc_addr_dma = !0;
 
 	/* Setup rings */
-	jrp->inp_ring_write_index = 0;
 	jrp->out_ring_read_index = 0;
 	jrp->head = 0;
 	jrp->tail = 0;
@@ -441,10 +443,9 @@ static int caam_jr_init(struct device *dev)
 	wr_reg32(&jrp->rregs->inpring_size, JOBR_DEPTH);
 	wr_reg32(&jrp->rregs->outring_size, JOBR_DEPTH);
 
-	jrp->ringsize = JOBR_DEPTH;
+	jrp->inpring_avail = JOBR_DEPTH;
 
 	spin_lock_init(&jrp->inplock);
-	spin_lock_init(&jrp->outlock);
 
 	/* Select interrupt coalescing parameters */
 	clrsetbits_32(&jrp->rregs->rconfig_lo, 0, JOBR_INTC |
diff --git a/drivers/crypto/caam/qi.c b/drivers/crypto/caam/qi.c
index 7cb8b1755e57..9f08f84cca59 100644
--- a/drivers/crypto/caam/qi.c
+++ b/drivers/crypto/caam/qi.c
@@ -318,7 +318,7 @@ int caam_drv_ctx_update(struct caam_drv_ctx *drv_ctx, u32 *sh_desc)
 	/* Create a new req FQ in parked state */
 	new_fq = create_caam_req_fq(drv_ctx->qidev, drv_ctx->rsp_fq,
 				    drv_ctx->context_a, 0);
-	if (IS_ERR_OR_NULL(new_fq)) {
+	if (IS_ERR(new_fq)) {
 		dev_err(qidev, "FQ allocation for shdesc update failed\n");
 		return PTR_ERR(new_fq);
 	}
@@ -431,7 +431,7 @@ struct caam_drv_ctx *caam_drv_ctx_init(struct device *qidev,
 	/* Attach request FQ */
 	drv_ctx->req_fq = create_caam_req_fq(qidev, drv_ctx->rsp_fq, hwdesc,
 					     QMAN_INITFQ_FLAG_SCHED);
-	if (IS_ERR_OR_NULL(drv_ctx->req_fq)) {
+	if (IS_ERR(drv_ctx->req_fq)) {
 		dev_err(qidev, "create_caam_req_fq failed\n");
 		dma_unmap_single(qidev, hwdesc, size, DMA_BIDIRECTIONAL);
 		kfree(drv_ctx);
diff --git a/drivers/crypto/caam/regs.h b/drivers/crypto/caam/regs.h
index 3cd0822ea819..c1fa1ec701d9 100644
--- a/drivers/crypto/caam/regs.h
+++ b/drivers/crypto/caam/regs.h
@@ -96,6 +96,14 @@ cpu_to_caam(16)
 cpu_to_caam(32)
 cpu_to_caam(64)
 
+static inline void wr_reg32_relaxed(void __iomem *reg, u32 data)
+{
+	if (caam_little_end)
+		writel_relaxed(data, reg);
+	else
+		writel_relaxed(cpu_to_be32(data), reg);
+}
+
 static inline void wr_reg32(void __iomem *reg, u32 data)
 {
 	if (caam_little_end)
@@ -253,6 +261,9 @@ struct version_regs {
 #define CHA_VER_VID_SHIFT	24
 #define CHA_VER_VID_MASK	(0xffull << CHA_VER_VID_SHIFT)
 
+/* CHA Miscellaneous Information - AESA_MISC specific */
+#define CHA_VER_MISC_AES_GCM	BIT(1 + CHA_VER_MISC_SHIFT)
+
 /*
  * caam_perfmon - Performance Monitor/Secure Memory Status/
  *                CAAM Global Status/Component Version IDs
diff --git a/drivers/crypto/cavium/cpt/cptvf_algs.c b/drivers/crypto/cavium/cpt/cptvf_algs.c
index 600336d169a9..9810ad8ac519 100644
--- a/drivers/crypto/cavium/cpt/cptvf_algs.c
+++ b/drivers/crypto/cavium/cpt/cptvf_algs.c
@@ -10,7 +10,6 @@
 #include <crypto/aes.h>
 #include <crypto/algapi.h>
 #include <crypto/authenc.h>
-#include <crypto/cryptd.h>
 #include <crypto/crypto_wq.h>
 #include <crypto/des.h>
 #include <crypto/xts.h>
@@ -327,27 +326,36 @@ static int cvm_cfb_aes_setkey(struct crypto_ablkcipher *cipher, const u8 *key,
 static int cvm_cbc_des3_setkey(struct crypto_ablkcipher *cipher, const u8 *key,
 			       u32 keylen)
 {
+	u32 flags = crypto_ablkcipher_get_flags(cipher);
+	int err;
+
+	err = __des3_verify_key(&flags, key);
+	if (unlikely(err)) {
+		crypto_ablkcipher_set_flags(cipher, flags);
+		return err;
+	}
+
 	return cvm_setkey(cipher, key, keylen, DES3_CBC);
 }
 
 static int cvm_ecb_des3_setkey(struct crypto_ablkcipher *cipher, const u8 *key,
 			       u32 keylen)
 {
+	u32 flags = crypto_ablkcipher_get_flags(cipher);
+	int err;
+
+	err = __des3_verify_key(&flags, key);
+	if (unlikely(err)) {
+		crypto_ablkcipher_set_flags(cipher, flags);
+		return err;
+	}
+
 	return cvm_setkey(cipher, key, keylen, DES3_ECB);
 }
 
 static int cvm_enc_dec_init(struct crypto_tfm *tfm)
 {
-	struct cvm_enc_ctx *ctx = crypto_tfm_ctx(tfm);
-
-	memset(ctx, 0, sizeof(*ctx));
-	tfm->crt_ablkcipher.reqsize = sizeof(struct cvm_req_ctx) +
-					sizeof(struct ablkcipher_request);
-	/* Additional memory for ablkcipher_request is
-	 * allocated since the cryptd daemon uses
-	 * this memory for request_ctx information
-	 */
-
+	tfm->crt_ablkcipher.reqsize = sizeof(struct cvm_req_ctx);
 	return 0;
 }
 
diff --git a/drivers/crypto/cavium/cpt/cptvf_main.c b/drivers/crypto/cavium/cpt/cptvf_main.c
index 2ca431ed1db8..88a0166f5477 100644
--- a/drivers/crypto/cavium/cpt/cptvf_main.c
+++ b/drivers/crypto/cavium/cpt/cptvf_main.c
@@ -641,7 +641,7 @@ static void cptvf_write_vq_saddr(struct cpt_vf *cptvf, u64 val)
 	cpt_write_csr64(cptvf->reg_base, CPTX_VQX_SADDR(0, 0), vqx_saddr.u);
 }
 
-void cptvf_device_init(struct cpt_vf *cptvf)
+static void cptvf_device_init(struct cpt_vf *cptvf)
 {
 	u64 base_addr = 0;
 
diff --git a/drivers/crypto/cavium/cpt/cptvf_mbox.c b/drivers/crypto/cavium/cpt/cptvf_mbox.c
index d5ec3b8a9e61..4f438eceb506 100644
--- a/drivers/crypto/cavium/cpt/cptvf_mbox.c
+++ b/drivers/crypto/cavium/cpt/cptvf_mbox.c
@@ -17,23 +17,6 @@ static void cptvf_send_msg_to_pf(struct cpt_vf *cptvf, struct cpt_mbox *mbx)
 			mbx->data);
 }
 
-/* ACKs PF's mailbox message
- */
-void cptvf_mbox_send_ack(struct cpt_vf *cptvf, struct cpt_mbox *mbx)
-{
-	mbx->msg = CPT_MBOX_MSG_TYPE_ACK;
-	cptvf_send_msg_to_pf(cptvf, mbx);
-}
-
-/* NACKs PF's mailbox message that VF is not able to
- * complete the action
- */
-void cptvf_mbox_send_nack(struct cpt_vf *cptvf, struct cpt_mbox *mbx)
-{
-	mbx->msg = CPT_MBOX_MSG_TYPE_NACK;
-	cptvf_send_msg_to_pf(cptvf, mbx);
-}
-
 /* Interrupt handler to handle mailbox messages from VFs */
 void cptvf_handle_mbox_intr(struct cpt_vf *cptvf)
 {
diff --git a/drivers/crypto/cavium/cpt/cptvf_reqmanager.c b/drivers/crypto/cavium/cpt/cptvf_reqmanager.c
index ca549c5dc08e..f16f61504241 100644
--- a/drivers/crypto/cavium/cpt/cptvf_reqmanager.c
+++ b/drivers/crypto/cavium/cpt/cptvf_reqmanager.c
@@ -223,7 +223,7 @@ scatter_gather_clean:
 	return ret;
 }
 
-int send_cpt_command(struct cpt_vf *cptvf, union cpt_inst_s *cmd,
+static int send_cpt_command(struct cpt_vf *cptvf, union cpt_inst_s *cmd,
 		     u32 qno)
 {
 	struct pci_dev *pdev = cptvf->pdev;
@@ -270,7 +270,7 @@ int send_cpt_command(struct cpt_vf *cptvf, union cpt_inst_s *cmd,
 	return ret;
 }
 
-void do_request_cleanup(struct cpt_vf *cptvf,
+static void do_request_cleanup(struct cpt_vf *cptvf,
 			struct cpt_info_buffer *info)
 {
 	int i;
@@ -316,7 +316,7 @@ void do_request_cleanup(struct cpt_vf *cptvf,
 	kzfree(info);
 }
 
-void do_post_process(struct cpt_vf *cptvf, struct cpt_info_buffer *info)
+static void do_post_process(struct cpt_vf *cptvf, struct cpt_info_buffer *info)
 {
 	struct pci_dev *pdev = cptvf->pdev;
 
diff --git a/drivers/crypto/cavium/nitrox/nitrox_aead.c b/drivers/crypto/cavium/nitrox/nitrox_aead.c
index 4f43eacd2557..e4841eb2a09f 100644
--- a/drivers/crypto/cavium/nitrox/nitrox_aead.c
+++ b/drivers/crypto/cavium/nitrox/nitrox_aead.c
@@ -18,26 +18,6 @@
 
 #define GCM_AES_SALT_SIZE	4
 
-/**
- * struct nitrox_crypt_params - Params to set nitrox crypto request.
- * @cryptlen: Encryption/Decryption data length
- * @authlen: Assoc data length + Cryptlen
- * @srclen: Input buffer length
- * @dstlen: Output buffer length
- * @iv: IV data
- * @ivsize: IV data length
- * @ctrl_arg: Identifies the request type (ENCRYPT/DECRYPT)
- */
-struct nitrox_crypt_params {
-	unsigned int cryptlen;
-	unsigned int authlen;
-	unsigned int srclen;
-	unsigned int dstlen;
-	u8 *iv;
-	int ivsize;
-	u8 ctrl_arg;
-};
-
 union gph_p3 {
 	struct {
 #ifdef __BIG_ENDIAN_BITFIELD
@@ -94,36 +74,40 @@ static int nitrox_aead_setauthsize(struct crypto_aead *aead,
 	return 0;
 }
 
-static int alloc_src_sglist(struct aead_request *areq, char *iv, int ivsize,
+static int alloc_src_sglist(struct nitrox_kcrypt_request *nkreq,
+			    struct scatterlist *src, char *iv, int ivsize,
 			    int buflen)
 {
-	struct nitrox_kcrypt_request *nkreq = aead_request_ctx(areq);
-	int nents = sg_nents_for_len(areq->src, buflen) + 1;
+	int nents = sg_nents_for_len(src, buflen);
 	int ret;
 
 	if (nents < 0)
 		return nents;
 
+	/* IV entry */
+	nents += 1;
 	/* Allocate buffer to hold IV and input scatterlist array */
 	ret = alloc_src_req_buf(nkreq, nents, ivsize);
 	if (ret)
 		return ret;
 
 	nitrox_creq_copy_iv(nkreq->src, iv, ivsize);
-	nitrox_creq_set_src_sg(nkreq, nents, ivsize, areq->src, buflen);
+	nitrox_creq_set_src_sg(nkreq, nents, ivsize, src, buflen);
 
 	return 0;
 }
 
-static int alloc_dst_sglist(struct aead_request *areq, int ivsize, int buflen)
+static int alloc_dst_sglist(struct nitrox_kcrypt_request *nkreq,
+			    struct scatterlist *dst, int ivsize, int buflen)
 {
-	struct nitrox_kcrypt_request *nkreq = aead_request_ctx(areq);
-	int nents = sg_nents_for_len(areq->dst, buflen) + 3;
+	int nents = sg_nents_for_len(dst, buflen);
 	int ret;
 
 	if (nents < 0)
 		return nents;
 
+	/* IV, ORH, COMPLETION entries */
+	nents += 3;
 	/* Allocate buffer to hold ORH, COMPLETION and output scatterlist
 	 * array
 	 */
@@ -133,61 +117,54 @@ static int alloc_dst_sglist(struct aead_request *areq, int ivsize, int buflen)
 
 	nitrox_creq_set_orh(nkreq);
 	nitrox_creq_set_comp(nkreq);
-	nitrox_creq_set_dst_sg(nkreq, nents, ivsize, areq->dst, buflen);
+	nitrox_creq_set_dst_sg(nkreq, nents, ivsize, dst, buflen);
 
 	return 0;
 }
 
-static void free_src_sglist(struct aead_request *areq)
+static void free_src_sglist(struct nitrox_kcrypt_request *nkreq)
 {
-	struct nitrox_kcrypt_request *nkreq = aead_request_ctx(areq);
-
 	kfree(nkreq->src);
 }
 
-static void free_dst_sglist(struct aead_request *areq)
+static void free_dst_sglist(struct nitrox_kcrypt_request *nkreq)
 {
-	struct nitrox_kcrypt_request *nkreq = aead_request_ctx(areq);
-
 	kfree(nkreq->dst);
 }
 
-static int nitrox_set_creq(struct aead_request *areq,
-			   struct nitrox_crypt_params *params)
+static int nitrox_set_creq(struct nitrox_aead_rctx *rctx)
 {
-	struct nitrox_kcrypt_request *nkreq = aead_request_ctx(areq);
-	struct se_crypto_request *creq = &nkreq->creq;
-	struct crypto_aead *aead = crypto_aead_reqtfm(areq);
+	struct se_crypto_request *creq = &rctx->nkreq.creq;
 	union gph_p3 param3;
-	struct nitrox_crypto_ctx *nctx = crypto_aead_ctx(aead);
 	int ret;
 
-	creq->flags = areq->base.flags;
-	creq->gfp = (areq->base.flags & CRYPTO_TFM_REQ_MAY_SLEEP) ?
-		GFP_KERNEL : GFP_ATOMIC;
+	creq->flags = rctx->flags;
+	creq->gfp = (rctx->flags & CRYPTO_TFM_REQ_MAY_SLEEP) ? GFP_KERNEL :
+							       GFP_ATOMIC;
 
 	creq->ctrl.value = 0;
 	creq->opcode = FLEXI_CRYPTO_ENCRYPT_HMAC;
-	creq->ctrl.s.arg = params->ctrl_arg;
+	creq->ctrl.s.arg = rctx->ctrl_arg;
 
-	creq->gph.param0 = cpu_to_be16(params->cryptlen);
-	creq->gph.param1 = cpu_to_be16(params->authlen);
-	creq->gph.param2 = cpu_to_be16(params->ivsize + areq->assoclen);
+	creq->gph.param0 = cpu_to_be16(rctx->cryptlen);
+	creq->gph.param1 = cpu_to_be16(rctx->cryptlen + rctx->assoclen);
+	creq->gph.param2 = cpu_to_be16(rctx->ivsize + rctx->assoclen);
 	param3.iv_offset = 0;
-	param3.auth_offset = params->ivsize;
+	param3.auth_offset = rctx->ivsize;
 	creq->gph.param3 = cpu_to_be16(param3.param);
 
-	creq->ctx_handle = nctx->u.ctx_handle;
+	creq->ctx_handle = rctx->ctx_handle;
 	creq->ctrl.s.ctxl = sizeof(struct flexi_crypto_context);
 
-	ret = alloc_src_sglist(areq, params->iv, params->ivsize,
-			       params->srclen);
+	ret = alloc_src_sglist(&rctx->nkreq, rctx->src, rctx->iv, rctx->ivsize,
+			       rctx->srclen);
 	if (ret)
 		return ret;
 
-	ret = alloc_dst_sglist(areq, params->ivsize, params->dstlen);
+	ret = alloc_dst_sglist(&rctx->nkreq, rctx->dst, rctx->ivsize,
+			       rctx->dstlen);
 	if (ret) {
-		free_src_sglist(areq);
+		free_src_sglist(&rctx->nkreq);
 		return ret;
 	}
 
@@ -197,9 +174,10 @@ static int nitrox_set_creq(struct aead_request *areq,
 static void nitrox_aead_callback(void *arg, int err)
 {
 	struct aead_request *areq = arg;
+	struct nitrox_aead_rctx *rctx = aead_request_ctx(areq);
 
-	free_src_sglist(areq);
-	free_dst_sglist(areq);
+	free_src_sglist(&rctx->nkreq);
+	free_dst_sglist(&rctx->nkreq);
 	if (err) {
 		pr_err_ratelimited("request failed status 0x%0x\n", err);
 		err = -EINVAL;
@@ -212,23 +190,25 @@ static int nitrox_aes_gcm_enc(struct aead_request *areq)
 {
 	struct crypto_aead *aead = crypto_aead_reqtfm(areq);
 	struct nitrox_crypto_ctx *nctx = crypto_aead_ctx(aead);
-	struct nitrox_kcrypt_request *nkreq = aead_request_ctx(areq);
-	struct se_crypto_request *creq = &nkreq->creq;
+	struct nitrox_aead_rctx *rctx = aead_request_ctx(areq);
+	struct se_crypto_request *creq = &rctx->nkreq.creq;
 	struct flexi_crypto_context *fctx = nctx->u.fctx;
-	struct nitrox_crypt_params params;
 	int ret;
 
 	memcpy(fctx->crypto.iv, areq->iv, GCM_AES_SALT_SIZE);
 
-	memset(&params, 0, sizeof(params));
-	params.cryptlen = areq->cryptlen;
-	params.authlen = areq->assoclen + params.cryptlen;
-	params.srclen = params.authlen;
-	params.dstlen = params.srclen + aead->authsize;
-	params.iv = &areq->iv[GCM_AES_SALT_SIZE];
-	params.ivsize = GCM_AES_IV_SIZE - GCM_AES_SALT_SIZE;
-	params.ctrl_arg = ENCRYPT;
-	ret = nitrox_set_creq(areq, &params);
+	rctx->cryptlen = areq->cryptlen;
+	rctx->assoclen = areq->assoclen;
+	rctx->srclen = areq->assoclen + areq->cryptlen;
+	rctx->dstlen = rctx->srclen + aead->authsize;
+	rctx->iv = &areq->iv[GCM_AES_SALT_SIZE];
+	rctx->ivsize = GCM_AES_IV_SIZE - GCM_AES_SALT_SIZE;
+	rctx->flags = areq->base.flags;
+	rctx->ctx_handle = nctx->u.ctx_handle;
+	rctx->src = areq->src;
+	rctx->dst = areq->dst;
+	rctx->ctrl_arg = ENCRYPT;
+	ret = nitrox_set_creq(rctx);
 	if (ret)
 		return ret;
 
@@ -241,23 +221,25 @@ static int nitrox_aes_gcm_dec(struct aead_request *areq)
 {
 	struct crypto_aead *aead = crypto_aead_reqtfm(areq);
 	struct nitrox_crypto_ctx *nctx = crypto_aead_ctx(aead);
-	struct nitrox_kcrypt_request *nkreq = aead_request_ctx(areq);
-	struct se_crypto_request *creq = &nkreq->creq;
+	struct nitrox_aead_rctx *rctx = aead_request_ctx(areq);
+	struct se_crypto_request *creq = &rctx->nkreq.creq;
 	struct flexi_crypto_context *fctx = nctx->u.fctx;
-	struct nitrox_crypt_params params;
 	int ret;
 
 	memcpy(fctx->crypto.iv, areq->iv, GCM_AES_SALT_SIZE);
 
-	memset(&params, 0, sizeof(params));
-	params.cryptlen = areq->cryptlen - aead->authsize;
-	params.authlen = areq->assoclen + params.cryptlen;
-	params.srclen = areq->cryptlen + areq->assoclen;
-	params.dstlen = params.srclen - aead->authsize;
-	params.iv = &areq->iv[GCM_AES_SALT_SIZE];
-	params.ivsize = GCM_AES_IV_SIZE - GCM_AES_SALT_SIZE;
-	params.ctrl_arg = DECRYPT;
-	ret = nitrox_set_creq(areq, &params);
+	rctx->cryptlen = areq->cryptlen - aead->authsize;
+	rctx->assoclen = areq->assoclen;
+	rctx->srclen = areq->cryptlen + areq->assoclen;
+	rctx->dstlen = rctx->srclen - aead->authsize;
+	rctx->iv = &areq->iv[GCM_AES_SALT_SIZE];
+	rctx->ivsize = GCM_AES_IV_SIZE - GCM_AES_SALT_SIZE;
+	rctx->flags = areq->base.flags;
+	rctx->ctx_handle = nctx->u.ctx_handle;
+	rctx->src = areq->src;
+	rctx->dst = areq->dst;
+	rctx->ctrl_arg = DECRYPT;
+	ret = nitrox_set_creq(rctx);
 	if (ret)
 		return ret;
 
@@ -290,7 +272,7 @@ static int nitrox_aead_init(struct crypto_aead *aead)
 	return 0;
 }
 
-static int nitrox_aes_gcm_init(struct crypto_aead *aead)
+static int nitrox_gcm_common_init(struct crypto_aead *aead)
 {
 	int ret;
 	struct nitrox_crypto_ctx *nctx = crypto_aead_ctx(aead);
@@ -308,8 +290,20 @@ static int nitrox_aes_gcm_init(struct crypto_aead *aead)
 	flags->w0.auth_input_type = 1;
 	flags->f = be64_to_cpu(flags->f);
 
-	crypto_aead_set_reqsize(aead, sizeof(struct aead_request) +
-				sizeof(struct nitrox_kcrypt_request));
+	return 0;
+}
+
+static int nitrox_aes_gcm_init(struct crypto_aead *aead)
+{
+	int ret;
+
+	ret = nitrox_gcm_common_init(aead);
+	if (ret)
+		return ret;
+
+	crypto_aead_set_reqsize(aead,
+				sizeof(struct aead_request) +
+					sizeof(struct nitrox_aead_rctx));
 
 	return 0;
 }
@@ -332,6 +326,166 @@ static void nitrox_aead_exit(struct crypto_aead *aead)
 	nctx->ndev = NULL;
 }
 
+static int nitrox_rfc4106_setkey(struct crypto_aead *aead, const u8 *key,
+				 unsigned int keylen)
+{
+	struct nitrox_crypto_ctx *nctx = crypto_aead_ctx(aead);
+	struct flexi_crypto_context *fctx = nctx->u.fctx;
+	int ret;
+
+	if (keylen < GCM_AES_SALT_SIZE)
+		return -EINVAL;
+
+	keylen -= GCM_AES_SALT_SIZE;
+	ret = nitrox_aes_gcm_setkey(aead, key, keylen);
+	if (ret)
+		return ret;
+
+	memcpy(fctx->crypto.iv, key + keylen, GCM_AES_SALT_SIZE);
+	return 0;
+}
+
+static int nitrox_rfc4106_setauthsize(struct crypto_aead *aead,
+				      unsigned int authsize)
+{
+	switch (authsize) {
+	case 8:
+	case 12:
+	case 16:
+		break;
+	default:
+		return -EINVAL;
+	}
+
+	return nitrox_aead_setauthsize(aead, authsize);
+}
+
+static int nitrox_rfc4106_set_aead_rctx_sglist(struct aead_request *areq)
+{
+	struct nitrox_rfc4106_rctx *rctx = aead_request_ctx(areq);
+	struct nitrox_aead_rctx *aead_rctx = &rctx->base;
+	unsigned int assoclen = areq->assoclen - GCM_RFC4106_IV_SIZE;
+	struct scatterlist *sg;
+
+	if (areq->assoclen != 16 && areq->assoclen != 20)
+		return -EINVAL;
+
+	scatterwalk_map_and_copy(rctx->assoc, areq->src, 0, assoclen, 0);
+	sg_init_table(rctx->src, 3);
+	sg_set_buf(rctx->src, rctx->assoc, assoclen);
+	sg = scatterwalk_ffwd(rctx->src + 1, areq->src, areq->assoclen);
+	if (sg != rctx->src + 1)
+		sg_chain(rctx->src, 2, sg);
+
+	if (areq->src != areq->dst) {
+		sg_init_table(rctx->dst, 3);
+		sg_set_buf(rctx->dst, rctx->assoc, assoclen);
+		sg = scatterwalk_ffwd(rctx->dst + 1, areq->dst, areq->assoclen);
+		if (sg != rctx->dst + 1)
+			sg_chain(rctx->dst, 2, sg);
+	}
+
+	aead_rctx->src = rctx->src;
+	aead_rctx->dst = (areq->src == areq->dst) ? rctx->src : rctx->dst;
+
+	return 0;
+}
+
+static void nitrox_rfc4106_callback(void *arg, int err)
+{
+	struct aead_request *areq = arg;
+	struct nitrox_rfc4106_rctx *rctx = aead_request_ctx(areq);
+	struct nitrox_kcrypt_request *nkreq = &rctx->base.nkreq;
+
+	free_src_sglist(nkreq);
+	free_dst_sglist(nkreq);
+	if (err) {
+		pr_err_ratelimited("request failed status 0x%0x\n", err);
+		err = -EINVAL;
+	}
+
+	areq->base.complete(&areq->base, err);
+}
+
+static int nitrox_rfc4106_enc(struct aead_request *areq)
+{
+	struct crypto_aead *aead = crypto_aead_reqtfm(areq);
+	struct nitrox_crypto_ctx *nctx = crypto_aead_ctx(aead);
+	struct nitrox_rfc4106_rctx *rctx = aead_request_ctx(areq);
+	struct nitrox_aead_rctx *aead_rctx = &rctx->base;
+	struct se_crypto_request *creq = &aead_rctx->nkreq.creq;
+	int ret;
+
+	aead_rctx->cryptlen = areq->cryptlen;
+	aead_rctx->assoclen = areq->assoclen - GCM_RFC4106_IV_SIZE;
+	aead_rctx->srclen = aead_rctx->assoclen + aead_rctx->cryptlen;
+	aead_rctx->dstlen = aead_rctx->srclen + aead->authsize;
+	aead_rctx->iv = areq->iv;
+	aead_rctx->ivsize = GCM_RFC4106_IV_SIZE;
+	aead_rctx->flags = areq->base.flags;
+	aead_rctx->ctx_handle = nctx->u.ctx_handle;
+	aead_rctx->ctrl_arg = ENCRYPT;
+
+	ret = nitrox_rfc4106_set_aead_rctx_sglist(areq);
+	if (ret)
+		return ret;
+
+	ret = nitrox_set_creq(aead_rctx);
+	if (ret)
+		return ret;
+
+	/* send the crypto request */
+	return nitrox_process_se_request(nctx->ndev, creq,
+					 nitrox_rfc4106_callback, areq);
+}
+
+static int nitrox_rfc4106_dec(struct aead_request *areq)
+{
+	struct crypto_aead *aead = crypto_aead_reqtfm(areq);
+	struct nitrox_crypto_ctx *nctx = crypto_aead_ctx(aead);
+	struct nitrox_rfc4106_rctx *rctx = aead_request_ctx(areq);
+	struct nitrox_aead_rctx *aead_rctx = &rctx->base;
+	struct se_crypto_request *creq = &aead_rctx->nkreq.creq;
+	int ret;
+
+	aead_rctx->cryptlen = areq->cryptlen - aead->authsize;
+	aead_rctx->assoclen = areq->assoclen - GCM_RFC4106_IV_SIZE;
+	aead_rctx->srclen =
+		areq->cryptlen - GCM_RFC4106_IV_SIZE + areq->assoclen;
+	aead_rctx->dstlen = aead_rctx->srclen - aead->authsize;
+	aead_rctx->iv = areq->iv;
+	aead_rctx->ivsize = GCM_RFC4106_IV_SIZE;
+	aead_rctx->flags = areq->base.flags;
+	aead_rctx->ctx_handle = nctx->u.ctx_handle;
+	aead_rctx->ctrl_arg = DECRYPT;
+
+	ret = nitrox_rfc4106_set_aead_rctx_sglist(areq);
+	if (ret)
+		return ret;
+
+	ret = nitrox_set_creq(aead_rctx);
+	if (ret)
+		return ret;
+
+	/* send the crypto request */
+	return nitrox_process_se_request(nctx->ndev, creq,
+					 nitrox_rfc4106_callback, areq);
+}
+
+static int nitrox_rfc4106_init(struct crypto_aead *aead)
+{
+	int ret;
+
+	ret = nitrox_gcm_common_init(aead);
+	if (ret)
+		return ret;
+
+	crypto_aead_set_reqsize(aead, sizeof(struct aead_request) +
+				sizeof(struct nitrox_rfc4106_rctx));
+
+	return 0;
+}
+
 static struct aead_alg nitrox_aeads[] = { {
 	.base = {
 		.cra_name = "gcm(aes)",
@@ -351,6 +505,25 @@ static struct aead_alg nitrox_aeads[] = { {
 	.exit = nitrox_aead_exit,
 	.ivsize = GCM_AES_IV_SIZE,
 	.maxauthsize = AES_BLOCK_SIZE,
+}, {
+	.base = {
+		.cra_name = "rfc4106(gcm(aes))",
+		.cra_driver_name = "n5_rfc4106",
+		.cra_priority = PRIO,
+		.cra_flags = CRYPTO_ALG_ASYNC,
+		.cra_blocksize = AES_BLOCK_SIZE,
+		.cra_ctxsize = sizeof(struct nitrox_crypto_ctx),
+		.cra_alignmask = 0,
+		.cra_module = THIS_MODULE,
+	},
+	.setkey = nitrox_rfc4106_setkey,
+	.setauthsize = nitrox_rfc4106_setauthsize,
+	.encrypt = nitrox_rfc4106_enc,
+	.decrypt = nitrox_rfc4106_dec,
+	.init = nitrox_rfc4106_init,
+	.exit = nitrox_aead_exit,
+	.ivsize = GCM_RFC4106_IV_SIZE,
+	.maxauthsize = AES_BLOCK_SIZE,
 } };
 
 int nitrox_register_aeads(void)
diff --git a/drivers/crypto/cavium/nitrox/nitrox_hal.c b/drivers/crypto/cavium/nitrox/nitrox_hal.c
index c08d9f33a3b1..3f0df60267a9 100644
--- a/drivers/crypto/cavium/nitrox/nitrox_hal.c
+++ b/drivers/crypto/cavium/nitrox/nitrox_hal.c
@@ -437,6 +437,45 @@ void config_nps_core_vfcfg_mode(struct nitrox_device *ndev, enum vf_mode mode)
 	nitrox_write_csr(ndev, NPS_CORE_GBL_VFCFG, vfcfg.value);
 }
 
+static const char *get_core_option(u8 se_cores, u8 ae_cores)
+{
+	const char *option = "";
+
+	if (ae_cores == AE_MAX_CORES) {
+		switch (se_cores) {
+		case SE_MAX_CORES:
+			option = "60";
+			break;
+		case 40:
+			option = "60s";
+			break;
+		}
+	} else if (ae_cores == (AE_MAX_CORES / 2)) {
+		option = "30";
+	} else {
+		option = "60i";
+	}
+
+	return option;
+}
+
+static const char *get_feature_option(u8 zip_cores, int core_freq)
+{
+	if (zip_cores == 0)
+		return "";
+	else if (zip_cores < ZIP_MAX_CORES)
+		return "-C15";
+
+	if (core_freq >= 850)
+		return "-C45";
+	else if (core_freq >= 750)
+		return "-C35";
+	else if (core_freq >= 550)
+		return "-C25";
+
+	return "";
+}
+
 void nitrox_get_hwinfo(struct nitrox_device *ndev)
 {
 	union emu_fuse_map emu_fuse;
@@ -469,24 +508,14 @@ void nitrox_get_hwinfo(struct nitrox_device *ndev)
 		ndev->hw.zip_cores = ZIP_MAX_CORES - dead_cores;
 	}
 
-	/* determine the partname CNN55<cores>-<freq><pincount>-<rev>*/
-	if (ndev->hw.ae_cores == AE_MAX_CORES) {
-		switch (ndev->hw.se_cores) {
-		case SE_MAX_CORES:
-			i = snprintf(name, sizeof(name), "CNN5560");
-			break;
-		case 40:
-			i = snprintf(name, sizeof(name), "CNN5560s");
-			break;
-		}
-	} else if (ndev->hw.ae_cores == (AE_MAX_CORES / 2)) {
-		i = snprintf(name, sizeof(name), "CNN5530");
-	} else {
-		i = snprintf(name, sizeof(name), "CNN5560i");
-	}
-
-	snprintf(name + i, sizeof(name) - i, "-%3dBG676-1.%u",
-		 ndev->hw.freq, ndev->hw.revision_id);
+	/* determine the partname
+	 * CNN55<core option>-<freq><pincount>-<feature option>-<rev>
+	 */
+	snprintf(name, sizeof(name), "CNN55%s-%3dBG676%s-1.%u",
+		 get_core_option(ndev->hw.se_cores, ndev->hw.ae_cores),
+		 ndev->hw.freq,
+		 get_feature_option(ndev->hw.zip_cores, ndev->hw.freq),
+		 ndev->hw.revision_id);
 
 	/* copy partname */
 	strncpy(ndev->hw.partname, name, sizeof(ndev->hw.partname));
diff --git a/drivers/crypto/cavium/nitrox/nitrox_req.h b/drivers/crypto/cavium/nitrox/nitrox_req.h
index 76c0f0be7233..efdbd0fc3e3b 100644
--- a/drivers/crypto/cavium/nitrox/nitrox_req.h
+++ b/drivers/crypto/cavium/nitrox/nitrox_req.h
@@ -212,6 +212,50 @@ struct nitrox_kcrypt_request {
 };
 
 /**
+ * struct nitrox_aead_rctx - AEAD request context
+ * @nkreq: Base request context
+ * @cryptlen: Encryption/Decryption data length
+ * @assoclen: AAD length
+ * @srclen: Input buffer length
+ * @dstlen: Output buffer length
+ * @iv: IV data
+ * @ivsize: IV data length
+ * @flags: AEAD req flags
+ * @ctx_handle: Device context handle
+ * @src: Source sglist
+ * @dst: Destination sglist
+ * @ctrl_arg: Identifies the request type (ENCRYPT/DECRYPT)
+ */
+struct nitrox_aead_rctx {
+	struct nitrox_kcrypt_request nkreq;
+	unsigned int cryptlen;
+	unsigned int assoclen;
+	unsigned int srclen;
+	unsigned int dstlen;
+	u8 *iv;
+	int ivsize;
+	u32 flags;
+	u64 ctx_handle;
+	struct scatterlist *src;
+	struct scatterlist *dst;
+	u8 ctrl_arg;
+};
+
+/**
+ * struct nitrox_rfc4106_rctx - rfc4106 cipher request context
+ * @base: AEAD request context
+ * @src: Source sglist
+ * @dst: Destination sglist
+ * @assoc: AAD
+ */
+struct nitrox_rfc4106_rctx {
+	struct nitrox_aead_rctx base;
+	struct scatterlist src[3];
+	struct scatterlist dst[3];
+	u8 assoc[20];
+};
+
+/**
  * struct pkt_instr_hdr - Packet Instruction Header
  * @g: Gather used
  *   When [G] is set and [GSZ] != 0, the instruction is
@@ -512,7 +556,7 @@ static inline struct scatterlist *create_multi_sg(struct scatterlist *to_sg,
 	struct scatterlist *sg = to_sg;
 	unsigned int sglen;
 
-	for (; buflen; buflen -= sglen) {
+	for (; buflen && from_sg; buflen -= sglen) {
 		sglen = from_sg->length;
 		if (sglen > buflen)
 			sglen = buflen;
diff --git a/drivers/crypto/cavium/nitrox/nitrox_reqmgr.c b/drivers/crypto/cavium/nitrox/nitrox_reqmgr.c
index 4c97478d44bd..5826c2c98a50 100644
--- a/drivers/crypto/cavium/nitrox/nitrox_reqmgr.c
+++ b/drivers/crypto/cavium/nitrox/nitrox_reqmgr.c
@@ -303,8 +303,6 @@ static void post_se_instr(struct nitrox_softreq *sr,
 
 	/* Ring doorbell with count 1 */
 	writeq(1, cmdq->dbell_csr_addr);
-	/* orders the doorbell rings */
-	mmiowb();
 
 	cmdq->write_idx = incr_index(idx, 1, ndev->qlen);
 
@@ -599,8 +597,6 @@ void pkt_slc_resp_tasklet(unsigned long data)
 	 * MSI-X interrupt generates if Completion count > Threshold
 	 */
 	writeq(slc_cnts.value, cmdq->compl_cnt_csr_addr);
-	/* order the writes */
-	mmiowb();
 
 	if (atomic_read(&cmdq->backlog_count))
 		schedule_work(&cmdq->backlog_qflush);
diff --git a/drivers/crypto/cavium/nitrox/nitrox_skcipher.c b/drivers/crypto/cavium/nitrox/nitrox_skcipher.c
index d4935d6cefdd..7e4a5e69085e 100644
--- a/drivers/crypto/cavium/nitrox/nitrox_skcipher.c
+++ b/drivers/crypto/cavium/nitrox/nitrox_skcipher.c
@@ -257,12 +257,8 @@ static int nitrox_aes_decrypt(struct skcipher_request *skreq)
 static int nitrox_3des_setkey(struct crypto_skcipher *cipher,
 			      const u8 *key, unsigned int keylen)
 {
-	if (keylen != DES3_EDE_KEY_SIZE) {
-		crypto_skcipher_set_flags(cipher, CRYPTO_TFM_RES_BAD_KEY_LEN);
-		return -EINVAL;
-	}
-
-	return nitrox_skcipher_setkey(cipher, 0, key, keylen);
+	return unlikely(des3_verify_key(cipher, key)) ?:
+	       nitrox_skcipher_setkey(cipher, 0, key, keylen);
 }
 
 static int nitrox_3des_encrypt(struct skcipher_request *skreq)
diff --git a/drivers/crypto/cavium/zip/zip_crypto.c b/drivers/crypto/cavium/zip/zip_crypto.c
index b92b6e7e100f..4985bc812b0e 100644
--- a/drivers/crypto/cavium/zip/zip_crypto.c
+++ b/drivers/crypto/cavium/zip/zip_crypto.c
@@ -69,7 +69,7 @@ static void zip_static_init_zip_ops(struct zip_operation *zip_ops,
 	zip_ops->csum	      = 1; /* Adler checksum desired */
 }
 
-int zip_ctx_init(struct zip_kernel_ctx *zip_ctx, int lzs_flag)
+static int zip_ctx_init(struct zip_kernel_ctx *zip_ctx, int lzs_flag)
 {
 	struct zip_operation  *comp_ctx   = &zip_ctx->zip_comp;
 	struct zip_operation  *decomp_ctx = &zip_ctx->zip_decomp;
@@ -107,7 +107,7 @@ err_comp_input:
 	return -ENOMEM;
 }
 
-void zip_ctx_exit(struct zip_kernel_ctx *zip_ctx)
+static void zip_ctx_exit(struct zip_kernel_ctx *zip_ctx)
 {
 	struct zip_operation  *comp_ctx   = &zip_ctx->zip_comp;
 	struct zip_operation  *dec_ctx = &zip_ctx->zip_decomp;
@@ -119,7 +119,7 @@ void zip_ctx_exit(struct zip_kernel_ctx *zip_ctx)
 	zip_data_buf_free(dec_ctx->output, MAX_OUTPUT_BUFFER_SIZE);
 }
 
-int zip_compress(const u8 *src, unsigned int slen,
+static int zip_compress(const u8 *src, unsigned int slen,
 		 u8 *dst, unsigned int *dlen,
 		 struct zip_kernel_ctx *zip_ctx)
 {
@@ -155,7 +155,7 @@ int zip_compress(const u8 *src, unsigned int slen,
 	return ret;
 }
 
-int zip_decompress(const u8 *src, unsigned int slen,
+static int zip_decompress(const u8 *src, unsigned int slen,
 		   u8 *dst, unsigned int *dlen,
 		   struct zip_kernel_ctx *zip_ctx)
 {
diff --git a/drivers/crypto/ccp/ccp-crypto-des3.c b/drivers/crypto/ccp/ccp-crypto-des3.c
index c2ff551d215b..91482ffcac59 100644
--- a/drivers/crypto/ccp/ccp-crypto-des3.c
+++ b/drivers/crypto/ccp/ccp-crypto-des3.c
@@ -43,24 +43,11 @@ static int ccp_des3_setkey(struct crypto_ablkcipher *tfm, const u8 *key,
 	struct ccp_crypto_ablkcipher_alg *alg =
 		ccp_crypto_ablkcipher_alg(crypto_ablkcipher_tfm(tfm));
 	u32 *flags = &tfm->base.crt_flags;
+	int err;
 
-
-	/* From des_generic.c:
-	 *
-	 * RFC2451:
-	 *   If the first two or last two independent 64-bit keys are
-	 *   equal (k1 == k2 or k2 == k3), then the DES3 operation is simply the
-	 *   same as DES.  Implementers MUST reject keys that exhibit this
-	 *   property.
-	 */
-	const u32 *K = (const u32 *)key;
-
-	if (unlikely(!((K[0] ^ K[2]) | (K[1] ^ K[3])) ||
-		     !((K[2] ^ K[4]) | (K[3] ^ K[5]))) &&
-		     (*flags & CRYPTO_TFM_REQ_FORBID_WEAK_KEYS)) {
-		*flags |= CRYPTO_TFM_RES_WEAK_KEY;
-		return -EINVAL;
-	}
+	err = __des3_verify_key(flags, key);
+	if (unlikely(err))
+		return err;
 
 	/* It's not clear that there is any support for a keysize of 112.
 	 * If needed, the caller should make K1 == K3
diff --git a/drivers/crypto/ccp/ccp-crypto-rsa.c b/drivers/crypto/ccp/ccp-crypto-rsa.c
index 05850dfd7940..a2570c0c8cdc 100644
--- a/drivers/crypto/ccp/ccp-crypto-rsa.c
+++ b/drivers/crypto/ccp/ccp-crypto-rsa.c
@@ -37,10 +37,9 @@ static inline int ccp_copy_and_save_keypart(u8 **kpbuf, unsigned int *kplen,
 		if (buf[nskip])
 			break;
 	*kplen = sz - nskip;
-	*kpbuf = kzalloc(*kplen, GFP_KERNEL);
+	*kpbuf = kmemdup(buf + nskip, *kplen, GFP_KERNEL);
 	if (!*kpbuf)
 		return -ENOMEM;
-	memcpy(*kpbuf, buf + nskip, *kplen);
 
 	return 0;
 }
@@ -214,8 +213,6 @@ static void ccp_rsa_exit_tfm(struct crypto_akcipher *tfm)
 static struct akcipher_alg ccp_rsa_defaults = {
 	.encrypt = ccp_rsa_encrypt,
 	.decrypt = ccp_rsa_decrypt,
-	.sign = ccp_rsa_decrypt,
-	.verify = ccp_rsa_encrypt,
 	.set_pub_key = ccp_rsa_setpubkey,
 	.set_priv_key = ccp_rsa_setprivkey,
 	.max_size = ccp_rsa_maxsize,
@@ -248,7 +245,8 @@ static struct ccp_rsa_def rsa_algs[] = {
 	}
 };
 
-int ccp_register_rsa_alg(struct list_head *head, const struct ccp_rsa_def *def)
+static int ccp_register_rsa_alg(struct list_head *head,
+			        const struct ccp_rsa_def *def)
 {
 	struct ccp_crypto_akcipher_alg *ccp_alg;
 	struct akcipher_alg *alg;
diff --git a/drivers/crypto/ccp/ccp-crypto-sha.c b/drivers/crypto/ccp/ccp-crypto-sha.c
index 10a61cd54fce..3e10573f589e 100644
--- a/drivers/crypto/ccp/ccp-crypto-sha.c
+++ b/drivers/crypto/ccp/ccp-crypto-sha.c
@@ -293,8 +293,6 @@ static int ccp_sha_setkey(struct crypto_ahash *tfm, const u8 *key,
 	if (key_len > block_size) {
 		/* Must hash the input key */
 		sdesc->tfm = shash;
-		sdesc->flags = crypto_ahash_get_flags(tfm) &
-			CRYPTO_TFM_REQ_MAY_SLEEP;
 
 		ret = crypto_shash_digest(sdesc, key, key_len,
 					  ctx->u.sha.key);
diff --git a/drivers/crypto/ccp/psp-dev.c b/drivers/crypto/ccp/psp-dev.c
index fadf859a14b8..656838433f2f 100644
--- a/drivers/crypto/ccp/psp-dev.c
+++ b/drivers/crypto/ccp/psp-dev.c
@@ -583,6 +583,69 @@ e_free:
 	return ret;
 }
 
+static int sev_ioctl_do_get_id2(struct sev_issue_cmd *argp)
+{
+	struct sev_user_data_get_id2 input;
+	struct sev_data_get_id *data;
+	void *id_blob = NULL;
+	int ret;
+
+	/* SEV GET_ID is available from SEV API v0.16 and up */
+	if (!SEV_VERSION_GREATER_OR_EQUAL(0, 16))
+		return -ENOTSUPP;
+
+	if (copy_from_user(&input, (void __user *)argp->data, sizeof(input)))
+		return -EFAULT;
+
+	/* Check if we have write access to the userspace buffer */
+	if (input.address &&
+	    input.length &&
+	    !access_ok(input.address, input.length))
+		return -EFAULT;
+
+	data = kzalloc(sizeof(*data), GFP_KERNEL);
+	if (!data)
+		return -ENOMEM;
+
+	if (input.address && input.length) {
+		id_blob = kmalloc(input.length, GFP_KERNEL);
+		if (!id_blob) {
+			kfree(data);
+			return -ENOMEM;
+		}
+
+		data->address = __psp_pa(id_blob);
+		data->len = input.length;
+	}
+
+	ret = __sev_do_cmd_locked(SEV_CMD_GET_ID, data, &argp->error);
+
+	/*
+	 * Firmware will return the length of the ID value (either the minimum
+	 * required length or the actual length written), return it to the user.
+	 */
+	input.length = data->len;
+
+	if (copy_to_user((void __user *)argp->data, &input, sizeof(input))) {
+		ret = -EFAULT;
+		goto e_free;
+	}
+
+	if (id_blob) {
+		if (copy_to_user((void __user *)input.address,
+				 id_blob, data->len)) {
+			ret = -EFAULT;
+			goto e_free;
+		}
+	}
+
+e_free:
+	kfree(id_blob);
+	kfree(data);
+
+	return ret;
+}
+
 static int sev_ioctl_do_get_id(struct sev_issue_cmd *argp)
 {
 	struct sev_data_get_id *data;
@@ -761,8 +824,12 @@ static long sev_ioctl(struct file *file, unsigned int ioctl, unsigned long arg)
 		ret = sev_ioctl_do_pdh_export(&input);
 		break;
 	case SEV_GET_ID:
+		pr_warn_once("SEV_GET_ID command is deprecated, use SEV_GET_ID2\n");
 		ret = sev_ioctl_do_get_id(&input);
 		break;
+	case SEV_GET_ID2:
+		ret = sev_ioctl_do_get_id2(&input);
+		break;
 	default:
 		ret = -EINVAL;
 		goto out;
@@ -997,7 +1064,7 @@ void psp_pci_init(void)
 	rc = sev_platform_init(&error);
 	if (rc) {
 		dev_err(sp->dev, "SEV: failed to INIT error %#x\n", error);
-		goto err;
+		return;
 	}
 
 	dev_info(sp->dev, "SEV API:%d.%d build:%d\n", psp_master->api_major,
diff --git a/drivers/crypto/ccree/Makefile b/drivers/crypto/ccree/Makefile
index bdc27970f95f..145e50bdbf16 100644
--- a/drivers/crypto/ccree/Makefile
+++ b/drivers/crypto/ccree/Makefile
@@ -1,4 +1,5 @@
 # SPDX-License-Identifier: GPL-2.0
+# Copyright (C) 2012-2019 ARM Limited (or its affiliates).
 
 obj-$(CONFIG_CRYPTO_DEV_CCREE) := ccree.o
 ccree-y := cc_driver.o cc_buffer_mgr.o cc_request_mgr.o cc_cipher.o cc_hash.o cc_aead.o cc_ivgen.o cc_sram_mgr.o
diff --git a/drivers/crypto/ccree/cc_aead.c b/drivers/crypto/ccree/cc_aead.c
index a3527c00b29a..7aa4cbe19a86 100644
--- a/drivers/crypto/ccree/cc_aead.c
+++ b/drivers/crypto/ccree/cc_aead.c
@@ -1,5 +1,5 @@
 // SPDX-License-Identifier: GPL-2.0
-/* Copyright (C) 2012-2018 ARM Limited or its affiliates. */
+/* Copyright (C) 2012-2019 ARM Limited (or its affiliates). */
 
 #include <linux/kernel.h>
 #include <linux/module.h>
@@ -23,12 +23,8 @@
 #define MAX_HMAC_DIGEST_SIZE (SHA256_DIGEST_SIZE)
 #define MAX_HMAC_BLOCK_SIZE (SHA256_BLOCK_SIZE)
 
-#define AES_CCM_RFC4309_NONCE_SIZE 3
 #define MAX_NONCE_SIZE CTR_RFC3686_NONCE_SIZE
 
-/* Value of each ICV_CMP byte (of 8) in case of success */
-#define ICV_VERIF_OK 0x01
-
 struct cc_aead_handle {
 	cc_sram_addr_t sram_workspace_addr;
 	struct list_head aead_list;
@@ -220,6 +216,10 @@ static void cc_aead_complete(struct device *dev, void *cc_req, int err)
 	struct crypto_aead *tfm = crypto_aead_reqtfm(cc_req);
 	struct cc_aead_ctx *ctx = crypto_aead_ctx(tfm);
 
+	/* BACKLOG notification */
+	if (err == -EINPROGRESS)
+		goto done;
+
 	cc_unmap_aead_request(dev, areq);
 
 	/* Restore ordinary iv pointer */
@@ -424,7 +424,7 @@ static int validate_keys_sizes(struct cc_aead_ctx *ctx)
 /* This function prepers the user key so it can pass to the hmac processing
  * (copy to intenral buffer or hash in case of key longer than block
  */
-static int cc_get_plain_hmac_key(struct crypto_aead *tfm, const u8 *key,
+static int cc_get_plain_hmac_key(struct crypto_aead *tfm, const u8 *authkey,
 				 unsigned int keylen)
 {
 	dma_addr_t key_dma_addr = 0;
@@ -437,6 +437,7 @@ static int cc_get_plain_hmac_key(struct crypto_aead *tfm, const u8 *key,
 	unsigned int hashmode;
 	unsigned int idx = 0;
 	int rc = 0;
+	u8 *key = NULL;
 	struct cc_hw_desc desc[MAX_AEAD_SETKEY_SEQ];
 	dma_addr_t padded_authkey_dma_addr =
 		ctx->auth_state.hmac.padded_authkey_dma_addr;
@@ -455,11 +456,17 @@ static int cc_get_plain_hmac_key(struct crypto_aead *tfm, const u8 *key,
 	}
 
 	if (keylen != 0) {
+
+		key = kmemdup(authkey, keylen, GFP_KERNEL);
+		if (!key)
+			return -ENOMEM;
+
 		key_dma_addr = dma_map_single(dev, (void *)key, keylen,
 					      DMA_TO_DEVICE);
 		if (dma_mapping_error(dev, key_dma_addr)) {
 			dev_err(dev, "Mapping key va=0x%p len=%u for DMA failed\n",
 				key, keylen);
+			kzfree(key);
 			return -ENOMEM;
 		}
 		if (keylen > blocksize) {
@@ -542,6 +549,8 @@ static int cc_get_plain_hmac_key(struct crypto_aead *tfm, const u8 *key,
 	if (key_dma_addr)
 		dma_unmap_single(dev, key_dma_addr, keylen, DMA_TO_DEVICE);
 
+	kzfree(key);
+
 	return rc;
 }
 
@@ -650,6 +659,39 @@ setkey_error:
 	return rc;
 }
 
+static int cc_des3_aead_setkey(struct crypto_aead *aead, const u8 *key,
+			       unsigned int keylen)
+{
+	struct crypto_authenc_keys keys;
+	u32 flags;
+	int err;
+
+	err = crypto_authenc_extractkeys(&keys, key, keylen);
+	if (unlikely(err))
+		goto badkey;
+
+	err = -EINVAL;
+	if (keys.enckeylen != DES3_EDE_KEY_SIZE)
+		goto badkey;
+
+	flags = crypto_aead_get_flags(aead);
+	err = __des3_verify_key(&flags, keys.enckey);
+	if (unlikely(err)) {
+		crypto_aead_set_flags(aead, flags);
+		goto out;
+	}
+
+	err = cc_aead_setkey(aead, key, keylen);
+
+out:
+	memzero_explicit(&keys, sizeof(keys));
+	return err;
+
+badkey:
+	crypto_aead_set_flags(aead, CRYPTO_TFM_RES_BAD_KEY_LEN);
+	goto out;
+}
+
 static int cc_rfc4309_ccm_setkey(struct crypto_aead *tfm, const u8 *key,
 				 unsigned int keylen)
 {
@@ -731,7 +773,7 @@ static void cc_set_assoc_desc(struct aead_request *areq, unsigned int flow_mode,
 		dev_dbg(dev, "ASSOC buffer type DLLI\n");
 		hw_desc_init(&desc[idx]);
 		set_din_type(&desc[idx], DMA_DLLI, sg_dma_address(areq->src),
-			     areq->assoclen, NS_BIT);
+			     areq_ctx->assoclen, NS_BIT);
 		set_flow_mode(&desc[idx], flow_mode);
 		if (ctx->auth_mode == DRV_HASH_XCBC_MAC &&
 		    areq_ctx->cryptlen > 0)
@@ -1080,9 +1122,11 @@ static void cc_proc_header_desc(struct aead_request *req,
 				struct cc_hw_desc desc[],
 				unsigned int *seq_size)
 {
+	struct aead_req_ctx *areq_ctx = aead_request_ctx(req);
 	unsigned int idx = *seq_size;
+
 	/* Hash associated data */
-	if (req->assoclen > 0)
+	if (areq_ctx->assoclen > 0)
 		cc_set_assoc_desc(req, DIN_HASH, desc, &idx);
 
 	/* Hash IV */
@@ -1159,9 +1203,9 @@ static void cc_mlli_to_sram(struct aead_request *req,
 	struct cc_aead_ctx *ctx = crypto_aead_ctx(tfm);
 	struct device *dev = drvdata_to_dev(ctx->drvdata);
 
-	if (req_ctx->assoc_buff_type == CC_DMA_BUF_MLLI ||
+	if ((req_ctx->assoc_buff_type == CC_DMA_BUF_MLLI ||
 	    req_ctx->data_buff_type == CC_DMA_BUF_MLLI ||
-	    !req_ctx->is_single_pass) {
+	    !req_ctx->is_single_pass) && req_ctx->mlli_params.mlli_len) {
 		dev_dbg(dev, "Copy-to-sram: mlli_dma=%08x, mlli_size=%u\n",
 			(unsigned int)ctx->drvdata->mlli_sram_addr,
 			req_ctx->mlli_params.mlli_len);
@@ -1310,7 +1354,7 @@ static int validate_data_size(struct cc_aead_ctx *ctx,
 {
 	struct aead_req_ctx *areq_ctx = aead_request_ctx(req);
 	struct device *dev = drvdata_to_dev(ctx->drvdata);
-	unsigned int assoclen = req->assoclen;
+	unsigned int assoclen = areq_ctx->assoclen;
 	unsigned int cipherlen = (direct == DRV_CRYPTO_DIRECTION_DECRYPT) ?
 			(req->cryptlen - ctx->authsize) : req->cryptlen;
 
@@ -1469,7 +1513,7 @@ static int cc_ccm(struct aead_request *req, struct cc_hw_desc desc[],
 	idx++;
 
 	/* process assoc data */
-	if (req->assoclen > 0) {
+	if (req_ctx->assoclen > 0) {
 		cc_set_assoc_desc(req, DIN_HASH, desc, &idx);
 	} else {
 		hw_desc_init(&desc[idx]);
@@ -1561,7 +1605,7 @@ static int config_ccm_adata(struct aead_request *req)
 	 * NIST Special Publication 800-38C
 	 */
 	*b0 |= (8 * ((m - 2) / 2));
-	if (req->assoclen > 0)
+	if (req_ctx->assoclen > 0)
 		*b0 |= 64;  /* Enable bit 6 if Adata exists. */
 
 	rc = set_msg_len(b0 + 16 - l, cryptlen, l);  /* Write L'. */
@@ -1572,7 +1616,7 @@ static int config_ccm_adata(struct aead_request *req)
 	 /* END of "taken from crypto/ccm.c" */
 
 	/* l(a) - size of associated data. */
-	req_ctx->ccm_hdr_size = format_ccm_a0(a0, req->assoclen);
+	req_ctx->ccm_hdr_size = format_ccm_a0(a0, req_ctx->assoclen);
 
 	memset(req->iv + 15 - req->iv[0], 0, req->iv[0] + 1);
 	req->iv[15] = 1;
@@ -1604,7 +1648,7 @@ static void cc_proc_rfc4309_ccm(struct aead_request *req)
 	memcpy(areq_ctx->ctr_iv + CCM_BLOCK_IV_OFFSET, req->iv,
 	       CCM_BLOCK_IV_SIZE);
 	req->iv = areq_ctx->ctr_iv;
-	req->assoclen -= CCM_BLOCK_IV_SIZE;
+	areq_ctx->assoclen -= CCM_BLOCK_IV_SIZE;
 }
 
 static void cc_set_ghash_desc(struct aead_request *req,
@@ -1812,7 +1856,7 @@ static int cc_gcm(struct aead_request *req, struct cc_hw_desc desc[],
 	// for gcm and rfc4106.
 	cc_set_ghash_desc(req, desc, seq_size);
 	/* process(ghash) assoc data */
-	if (req->assoclen > 0)
+	if (req_ctx->assoclen > 0)
 		cc_set_assoc_desc(req, DIN_HASH, desc, seq_size);
 	cc_set_gctr_desc(req, desc, seq_size);
 	/* process(gctr+ghash) */
@@ -1836,8 +1880,8 @@ static int config_gcm_context(struct aead_request *req)
 				(req->cryptlen - ctx->authsize);
 	__be32 counter = cpu_to_be32(2);
 
-	dev_dbg(dev, "%s() cryptlen = %d, req->assoclen = %d ctx->authsize = %d\n",
-		__func__, cryptlen, req->assoclen, ctx->authsize);
+	dev_dbg(dev, "%s() cryptlen = %d, req_ctx->assoclen = %d ctx->authsize = %d\n",
+		__func__, cryptlen, req_ctx->assoclen, ctx->authsize);
 
 	memset(req_ctx->hkey, 0, AES_BLOCK_SIZE);
 
@@ -1853,7 +1897,7 @@ static int config_gcm_context(struct aead_request *req)
 	if (!req_ctx->plaintext_authenticate_only) {
 		__be64 temp64;
 
-		temp64 = cpu_to_be64(req->assoclen * 8);
+		temp64 = cpu_to_be64(req_ctx->assoclen * 8);
 		memcpy(&req_ctx->gcm_len_block.len_a, &temp64, sizeof(temp64));
 		temp64 = cpu_to_be64(cryptlen * 8);
 		memcpy(&req_ctx->gcm_len_block.len_c, &temp64, 8);
@@ -1863,8 +1907,8 @@ static int config_gcm_context(struct aead_request *req)
 		 */
 		__be64 temp64;
 
-		temp64 = cpu_to_be64((req->assoclen + GCM_BLOCK_RFC4_IV_SIZE +
-				      cryptlen) * 8);
+		temp64 = cpu_to_be64((req_ctx->assoclen +
+				      GCM_BLOCK_RFC4_IV_SIZE + cryptlen) * 8);
 		memcpy(&req_ctx->gcm_len_block.len_a, &temp64, sizeof(temp64));
 		temp64 = 0;
 		memcpy(&req_ctx->gcm_len_block.len_c, &temp64, 8);
@@ -1884,7 +1928,7 @@ static void cc_proc_rfc4_gcm(struct aead_request *req)
 	memcpy(areq_ctx->ctr_iv + GCM_BLOCK_RFC4_IV_OFFSET, req->iv,
 	       GCM_BLOCK_RFC4_IV_SIZE);
 	req->iv = areq_ctx->ctr_iv;
-	req->assoclen -= GCM_BLOCK_RFC4_IV_SIZE;
+	areq_ctx->assoclen -= GCM_BLOCK_RFC4_IV_SIZE;
 }
 
 static int cc_proc_aead(struct aead_request *req,
@@ -1909,7 +1953,7 @@ static int cc_proc_aead(struct aead_request *req,
 	/* Check data length according to mode */
 	if (validate_data_size(ctx, direct, req)) {
 		dev_err(dev, "Unsupported crypt/assoc len %d/%d.\n",
-			req->cryptlen, req->assoclen);
+			req->cryptlen, areq_ctx->assoclen);
 		crypto_aead_set_flags(tfm, CRYPTO_TFM_RES_BAD_BLOCK_LEN);
 		return -EINVAL;
 	}
@@ -2058,8 +2102,11 @@ static int cc_aead_encrypt(struct aead_request *req)
 	struct aead_req_ctx *areq_ctx = aead_request_ctx(req);
 	int rc;
 
+	memset(areq_ctx, 0, sizeof(*areq_ctx));
+
 	/* No generated IV required */
 	areq_ctx->backup_iv = req->iv;
+	areq_ctx->assoclen = req->assoclen;
 	areq_ctx->backup_giv = NULL;
 	areq_ctx->is_gcm4543 = false;
 
@@ -2087,8 +2134,11 @@ static int cc_rfc4309_ccm_encrypt(struct aead_request *req)
 		goto out;
 	}
 
+	memset(areq_ctx, 0, sizeof(*areq_ctx));
+
 	/* No generated IV required */
 	areq_ctx->backup_iv = req->iv;
+	areq_ctx->assoclen = req->assoclen;
 	areq_ctx->backup_giv = NULL;
 	areq_ctx->is_gcm4543 = true;
 
@@ -2106,8 +2156,11 @@ static int cc_aead_decrypt(struct aead_request *req)
 	struct aead_req_ctx *areq_ctx = aead_request_ctx(req);
 	int rc;
 
+	memset(areq_ctx, 0, sizeof(*areq_ctx));
+
 	/* No generated IV required */
 	areq_ctx->backup_iv = req->iv;
+	areq_ctx->assoclen = req->assoclen;
 	areq_ctx->backup_giv = NULL;
 	areq_ctx->is_gcm4543 = false;
 
@@ -2133,8 +2186,11 @@ static int cc_rfc4309_ccm_decrypt(struct aead_request *req)
 		goto out;
 	}
 
+	memset(areq_ctx, 0, sizeof(*areq_ctx));
+
 	/* No generated IV required */
 	areq_ctx->backup_iv = req->iv;
+	areq_ctx->assoclen = req->assoclen;
 	areq_ctx->backup_giv = NULL;
 
 	areq_ctx->is_gcm4543 = true;
@@ -2250,8 +2306,11 @@ static int cc_rfc4106_gcm_encrypt(struct aead_request *req)
 		goto out;
 	}
 
+	memset(areq_ctx, 0, sizeof(*areq_ctx));
+
 	/* No generated IV required */
 	areq_ctx->backup_iv = req->iv;
+	areq_ctx->assoclen = req->assoclen;
 	areq_ctx->backup_giv = NULL;
 
 	areq_ctx->plaintext_authenticate_only = false;
@@ -2273,11 +2332,14 @@ static int cc_rfc4543_gcm_encrypt(struct aead_request *req)
 	struct aead_req_ctx *areq_ctx = aead_request_ctx(req);
 	int rc;
 
+	memset(areq_ctx, 0, sizeof(*areq_ctx));
+
 	//plaintext is not encryped with rfc4543
 	areq_ctx->plaintext_authenticate_only = true;
 
 	/* No generated IV required */
 	areq_ctx->backup_iv = req->iv;
+	areq_ctx->assoclen = req->assoclen;
 	areq_ctx->backup_giv = NULL;
 
 	cc_proc_rfc4_gcm(req);
@@ -2305,8 +2367,11 @@ static int cc_rfc4106_gcm_decrypt(struct aead_request *req)
 		goto out;
 	}
 
+	memset(areq_ctx, 0, sizeof(*areq_ctx));
+
 	/* No generated IV required */
 	areq_ctx->backup_iv = req->iv;
+	areq_ctx->assoclen = req->assoclen;
 	areq_ctx->backup_giv = NULL;
 
 	areq_ctx->plaintext_authenticate_only = false;
@@ -2328,11 +2393,14 @@ static int cc_rfc4543_gcm_decrypt(struct aead_request *req)
 	struct aead_req_ctx *areq_ctx = aead_request_ctx(req);
 	int rc;
 
+	memset(areq_ctx, 0, sizeof(*areq_ctx));
+
 	//plaintext is not decryped with rfc4543
 	areq_ctx->plaintext_authenticate_only = true;
 
 	/* No generated IV required */
 	areq_ctx->backup_iv = req->iv;
+	areq_ctx->assoclen = req->assoclen;
 	areq_ctx->backup_giv = NULL;
 
 	cc_proc_rfc4_gcm(req);
@@ -2372,7 +2440,7 @@ static struct cc_alg_template aead_algs[] = {
 		.driver_name = "authenc-hmac-sha1-cbc-des3-ccree",
 		.blocksize = DES3_EDE_BLOCK_SIZE,
 		.template_aead = {
-			.setkey = cc_aead_setkey,
+			.setkey = cc_des3_aead_setkey,
 			.setauthsize = cc_aead_setauthsize,
 			.encrypt = cc_aead_encrypt,
 			.decrypt = cc_aead_decrypt,
@@ -2412,7 +2480,7 @@ static struct cc_alg_template aead_algs[] = {
 		.driver_name = "authenc-hmac-sha256-cbc-des3-ccree",
 		.blocksize = DES3_EDE_BLOCK_SIZE,
 		.template_aead = {
-			.setkey = cc_aead_setkey,
+			.setkey = cc_des3_aead_setkey,
 			.setauthsize = cc_aead_setauthsize,
 			.encrypt = cc_aead_encrypt,
 			.decrypt = cc_aead_decrypt,
diff --git a/drivers/crypto/ccree/cc_aead.h b/drivers/crypto/ccree/cc_aead.h
index 5edf3b351fa4..e51724b96c56 100644
--- a/drivers/crypto/ccree/cc_aead.h
+++ b/drivers/crypto/ccree/cc_aead.h
@@ -1,5 +1,5 @@
 /* SPDX-License-Identifier: GPL-2.0 */
-/* Copyright (C) 2012-2018 ARM Limited or its affiliates. */
+/* Copyright (C) 2012-2019 ARM Limited (or its affiliates). */
 
 /* \file cc_aead.h
  * ARM CryptoCell AEAD Crypto API
@@ -67,6 +67,7 @@ struct aead_req_ctx {
 	u8 backup_mac[MAX_MAC_SIZE];
 	u8 *backup_iv; /*store iv for generated IV flow*/
 	u8 *backup_giv; /*store iv for rfc3686(ctr) flow*/
+	u32 assoclen; /* internal assoclen */
 	dma_addr_t mac_buf_dma_addr; /* internal ICV DMA buffer */
 	/* buffer for internal ccm configurations */
 	dma_addr_t ccm_iv0_dma_addr;
diff --git a/drivers/crypto/ccree/cc_buffer_mgr.c b/drivers/crypto/ccree/cc_buffer_mgr.c
index 0ee1c52da0a4..c81ad33f9115 100644
--- a/drivers/crypto/ccree/cc_buffer_mgr.c
+++ b/drivers/crypto/ccree/cc_buffer_mgr.c
@@ -1,5 +1,5 @@
 // SPDX-License-Identifier: GPL-2.0
-/* Copyright (C) 2012-2018 ARM Limited or its affiliates. */
+/* Copyright (C) 2012-2019 ARM Limited (or its affiliates). */
 
 #include <crypto/internal/aead.h>
 #include <crypto/authenc.h>
@@ -65,7 +65,7 @@ static void cc_copy_mac(struct device *dev, struct aead_request *req,
 {
 	struct aead_req_ctx *areq_ctx = aead_request_ctx(req);
 	struct crypto_aead *tfm = crypto_aead_reqtfm(req);
-	u32 skip = req->assoclen + req->cryptlen;
+	u32 skip = areq_ctx->assoclen + req->cryptlen;
 
 	if (areq_ctx->is_gcm4543)
 		skip += crypto_aead_ivsize(tfm);
@@ -83,24 +83,17 @@ static void cc_copy_mac(struct device *dev, struct aead_request *req,
  */
 static unsigned int cc_get_sgl_nents(struct device *dev,
 				     struct scatterlist *sg_list,
-				     unsigned int nbytes, u32 *lbytes,
-				     bool *is_chained)
+				     unsigned int nbytes, u32 *lbytes)
 {
 	unsigned int nents = 0;
 
 	while (nbytes && sg_list) {
-		if (sg_list->length) {
-			nents++;
-			/* get the number of bytes in the last entry */
-			*lbytes = nbytes;
-			nbytes -= (sg_list->length > nbytes) ?
-					nbytes : sg_list->length;
-			sg_list = sg_next(sg_list);
-		} else {
-			sg_list = (struct scatterlist *)sg_page(sg_list);
-			if (is_chained)
-				*is_chained = true;
-		}
+		nents++;
+		/* get the number of bytes in the last entry */
+		*lbytes = nbytes;
+		nbytes -= (sg_list->length > nbytes) ?
+				nbytes : sg_list->length;
+		sg_list = sg_next(sg_list);
 	}
 	dev_dbg(dev, "nents %d last bytes %d\n", nents, *lbytes);
 	return nents;
@@ -140,9 +133,9 @@ void cc_zero_sgl(struct scatterlist *sgl, u32 data_len)
 void cc_copy_sg_portion(struct device *dev, u8 *dest, struct scatterlist *sg,
 			u32 to_skip, u32 end, enum cc_sg_cpy_direct direct)
 {
-	u32 nents, lbytes;
+	u32 nents;
 
-	nents = cc_get_sgl_nents(dev, sg, end, &lbytes, NULL);
+	nents = sg_nents_for_len(sg, end);
 	sg_copy_buffer(sg, nents, (void *)dest, (end - to_skip + 1), to_skip,
 		       (direct == CC_SG_TO_BUF));
 }
@@ -314,40 +307,10 @@ static void cc_add_sg_entry(struct device *dev, struct buffer_array *sgl_data,
 	sgl_data->num_of_buffers++;
 }
 
-static int cc_dma_map_sg(struct device *dev, struct scatterlist *sg, u32 nents,
-			 enum dma_data_direction direction)
-{
-	u32 i, j;
-	struct scatterlist *l_sg = sg;
-
-	for (i = 0; i < nents; i++) {
-		if (!l_sg)
-			break;
-		if (dma_map_sg(dev, l_sg, 1, direction) != 1) {
-			dev_err(dev, "dma_map_page() sg buffer failed\n");
-			goto err;
-		}
-		l_sg = sg_next(l_sg);
-	}
-	return nents;
-
-err:
-	/* Restore mapped parts */
-	for (j = 0; j < i; j++) {
-		if (!sg)
-			break;
-		dma_unmap_sg(dev, sg, 1, direction);
-		sg = sg_next(sg);
-	}
-	return 0;
-}
-
 static int cc_map_sg(struct device *dev, struct scatterlist *sg,
 		     unsigned int nbytes, int direction, u32 *nents,
 		     u32 max_sg_nents, u32 *lbytes, u32 *mapped_nents)
 {
-	bool is_chained = false;
-
 	if (sg_is_last(sg)) {
 		/* One entry only case -set to DLLI */
 		if (dma_map_sg(dev, sg, 1, direction) != 1) {
@@ -361,35 +324,21 @@ static int cc_map_sg(struct device *dev, struct scatterlist *sg,
 		*nents = 1;
 		*mapped_nents = 1;
 	} else {  /*sg_is_last*/
-		*nents = cc_get_sgl_nents(dev, sg, nbytes, lbytes,
-					  &is_chained);
+		*nents = cc_get_sgl_nents(dev, sg, nbytes, lbytes);
 		if (*nents > max_sg_nents) {
 			*nents = 0;
 			dev_err(dev, "Too many fragments. current %d max %d\n",
 				*nents, max_sg_nents);
 			return -ENOMEM;
 		}
-		if (!is_chained) {
-			/* In case of mmu the number of mapped nents might
-			 * be changed from the original sgl nents
-			 */
-			*mapped_nents = dma_map_sg(dev, sg, *nents, direction);
-			if (*mapped_nents == 0) {
-				*nents = 0;
-				dev_err(dev, "dma_map_sg() sg buffer failed\n");
-				return -ENOMEM;
-			}
-		} else {
-			/*In this case the driver maps entry by entry so it
-			 * must have the same nents before and after map
-			 */
-			*mapped_nents = cc_dma_map_sg(dev, sg, *nents,
-						      direction);
-			if (*mapped_nents != *nents) {
-				*nents = *mapped_nents;
-				dev_err(dev, "dma_map_sg() sg buffer failed\n");
-				return -ENOMEM;
-			}
+		/* In case of mmu the number of mapped nents might
+		 * be changed from the original sgl nents
+		 */
+		*mapped_nents = dma_map_sg(dev, sg, *nents, direction);
+		if (*mapped_nents == 0) {
+			*nents = 0;
+			dev_err(dev, "dma_map_sg() sg buffer failed\n");
+			return -ENOMEM;
 		}
 	}
 
@@ -457,7 +406,7 @@ void cc_unmap_cipher_request(struct device *dev, void *ctx,
 		dev_dbg(dev, "Unmapped iv: iv_dma_addr=%pad iv_size=%u\n",
 			&req_ctx->gen_ctx.iv_dma_addr, ivsize);
 		dma_unmap_single(dev, req_ctx->gen_ctx.iv_dma_addr,
-				 ivsize, DMA_TO_DEVICE);
+				 ivsize, DMA_BIDIRECTIONAL);
 	}
 	/* Release pool */
 	if (req_ctx->dma_buf_type == CC_DMA_BUF_MLLI &&
@@ -499,7 +448,7 @@ int cc_map_cipher_request(struct cc_drvdata *drvdata, void *ctx,
 		dump_byte_array("iv", (u8 *)info, ivsize);
 		req_ctx->gen_ctx.iv_dma_addr =
 			dma_map_single(dev, (void *)info,
-				       ivsize, DMA_TO_DEVICE);
+				       ivsize, DMA_BIDIRECTIONAL);
 		if (dma_mapping_error(dev, req_ctx->gen_ctx.iv_dma_addr)) {
 			dev_err(dev, "Mapping iv %u B at va=%pK for DMA failed\n",
 				ivsize, info);
@@ -568,11 +517,7 @@ void cc_unmap_aead_request(struct device *dev, struct aead_request *req)
 {
 	struct aead_req_ctx *areq_ctx = aead_request_ctx(req);
 	unsigned int hw_iv_size = areq_ctx->hw_iv_size;
-	struct crypto_aead *tfm = crypto_aead_reqtfm(req);
 	struct cc_drvdata *drvdata = dev_get_drvdata(dev);
-	u32 dummy;
-	bool chained;
-	u32 size_to_unmap = 0;
 
 	if (areq_ctx->mac_buf_dma_addr) {
 		dma_unmap_single(dev, areq_ctx->mac_buf_dma_addr,
@@ -612,6 +557,7 @@ void cc_unmap_aead_request(struct device *dev, struct aead_request *req)
 	if (areq_ctx->gen_ctx.iv_dma_addr) {
 		dma_unmap_single(dev, areq_ctx->gen_ctx.iv_dma_addr,
 				 hw_iv_size, DMA_BIDIRECTIONAL);
+		kzfree(areq_ctx->gen_ctx.iv);
 	}
 
 	/* Release pool */
@@ -628,23 +574,13 @@ void cc_unmap_aead_request(struct device *dev, struct aead_request *req)
 
 	dev_dbg(dev, "Unmapping src sgl: req->src=%pK areq_ctx->src.nents=%u areq_ctx->assoc.nents=%u assoclen:%u cryptlen=%u\n",
 		sg_virt(req->src), areq_ctx->src.nents, areq_ctx->assoc.nents,
-		req->assoclen, req->cryptlen);
-	size_to_unmap = req->assoclen + req->cryptlen;
-	if (areq_ctx->gen_ctx.op_type == DRV_CRYPTO_DIRECTION_ENCRYPT)
-		size_to_unmap += areq_ctx->req_authsize;
-	if (areq_ctx->is_gcm4543)
-		size_to_unmap += crypto_aead_ivsize(tfm);
+		areq_ctx->assoclen, req->cryptlen);
 
-	dma_unmap_sg(dev, req->src,
-		     cc_get_sgl_nents(dev, req->src, size_to_unmap,
-				      &dummy, &chained),
-		     DMA_BIDIRECTIONAL);
+	dma_unmap_sg(dev, req->src, sg_nents(req->src), DMA_BIDIRECTIONAL);
 	if (req->src != req->dst) {
 		dev_dbg(dev, "Unmapping dst sgl: req->dst=%pK\n",
 			sg_virt(req->dst));
-		dma_unmap_sg(dev, req->dst,
-			     cc_get_sgl_nents(dev, req->dst, size_to_unmap,
-					      &dummy, &chained),
+		dma_unmap_sg(dev, req->dst, sg_nents(req->dst),
 			     DMA_BIDIRECTIONAL);
 	}
 	if (drvdata->coherent &&
@@ -658,55 +594,10 @@ void cc_unmap_aead_request(struct device *dev, struct aead_request *req)
 	}
 }
 
-static int cc_get_aead_icv_nents(struct device *dev, struct scatterlist *sgl,
-				 unsigned int sgl_nents, unsigned int authsize,
-				 u32 last_entry_data_size,
-				 bool *is_icv_fragmented)
+static bool cc_is_icv_frag(unsigned int sgl_nents, unsigned int authsize,
+			   u32 last_entry_data_size)
 {
-	unsigned int icv_max_size = 0;
-	unsigned int icv_required_size = authsize > last_entry_data_size ?
-					(authsize - last_entry_data_size) :
-					authsize;
-	unsigned int nents;
-	unsigned int i;
-
-	if (sgl_nents < MAX_ICV_NENTS_SUPPORTED) {
-		*is_icv_fragmented = false;
-		return 0;
-	}
-
-	for (i = 0 ; i < (sgl_nents - MAX_ICV_NENTS_SUPPORTED) ; i++) {
-		if (!sgl)
-			break;
-		sgl = sg_next(sgl);
-	}
-
-	if (sgl)
-		icv_max_size = sgl->length;
-
-	if (last_entry_data_size > authsize) {
-		/* ICV attached to data in last entry (not fragmented!) */
-		nents = 0;
-		*is_icv_fragmented = false;
-	} else if (last_entry_data_size == authsize) {
-		/* ICV placed in whole last entry (not fragmented!) */
-		nents = 1;
-		*is_icv_fragmented = false;
-	} else if (icv_max_size > icv_required_size) {
-		nents = 1;
-		*is_icv_fragmented = true;
-	} else if (icv_max_size == icv_required_size) {
-		nents = 2;
-		*is_icv_fragmented = true;
-	} else {
-		dev_err(dev, "Unsupported num. of ICV fragments (> %d)\n",
-			MAX_ICV_NENTS_SUPPORTED);
-		nents = -1; /*unsupported*/
-	}
-	dev_dbg(dev, "is_frag=%s icv_nents=%u\n",
-		(*is_icv_fragmented ? "true" : "false"), nents);
-
-	return nents;
+	return ((sgl_nents > 1) && (last_entry_data_size < authsize));
 }
 
 static int cc_aead_chain_iv(struct cc_drvdata *drvdata,
@@ -717,19 +608,27 @@ static int cc_aead_chain_iv(struct cc_drvdata *drvdata,
 	struct aead_req_ctx *areq_ctx = aead_request_ctx(req);
 	unsigned int hw_iv_size = areq_ctx->hw_iv_size;
 	struct device *dev = drvdata_to_dev(drvdata);
+	gfp_t flags = cc_gfp_flags(&req->base);
 	int rc = 0;
 
 	if (!req->iv) {
 		areq_ctx->gen_ctx.iv_dma_addr = 0;
+		areq_ctx->gen_ctx.iv = NULL;
 		goto chain_iv_exit;
 	}
 
-	areq_ctx->gen_ctx.iv_dma_addr = dma_map_single(dev, req->iv,
-						       hw_iv_size,
-						       DMA_BIDIRECTIONAL);
+	areq_ctx->gen_ctx.iv = kmemdup(req->iv, hw_iv_size, flags);
+	if (!areq_ctx->gen_ctx.iv)
+		return -ENOMEM;
+
+	areq_ctx->gen_ctx.iv_dma_addr =
+		dma_map_single(dev, areq_ctx->gen_ctx.iv, hw_iv_size,
+			       DMA_BIDIRECTIONAL);
 	if (dma_mapping_error(dev, areq_ctx->gen_ctx.iv_dma_addr)) {
 		dev_err(dev, "Mapping iv %u B at va=%pK for DMA failed\n",
 			hw_iv_size, req->iv);
+		kzfree(areq_ctx->gen_ctx.iv);
+		areq_ctx->gen_ctx.iv = NULL;
 		rc = -ENOMEM;
 		goto chain_iv_exit;
 	}
@@ -760,11 +659,9 @@ static int cc_aead_chain_assoc(struct cc_drvdata *drvdata,
 {
 	struct aead_req_ctx *areq_ctx = aead_request_ctx(req);
 	int rc = 0;
-	u32 mapped_nents = 0;
-	struct scatterlist *current_sg = req->src;
+	int mapped_nents = 0;
 	struct crypto_aead *tfm = crypto_aead_reqtfm(req);
-	unsigned int sg_index = 0;
-	u32 size_of_assoc = req->assoclen;
+	unsigned int size_of_assoc = areq_ctx->assoclen;
 	struct device *dev = drvdata_to_dev(drvdata);
 
 	if (areq_ctx->is_gcm4543)
@@ -775,7 +672,7 @@ static int cc_aead_chain_assoc(struct cc_drvdata *drvdata,
 		goto chain_assoc_exit;
 	}
 
-	if (req->assoclen == 0) {
+	if (areq_ctx->assoclen == 0) {
 		areq_ctx->assoc_buff_type = CC_DMA_BUF_NULL;
 		areq_ctx->assoc.nents = 0;
 		areq_ctx->assoc.mlli_nents = 0;
@@ -785,26 +682,10 @@ static int cc_aead_chain_assoc(struct cc_drvdata *drvdata,
 		goto chain_assoc_exit;
 	}
 
-	//iterate over the sgl to see how many entries are for associated data
-	//it is assumed that if we reach here , the sgl is already mapped
-	sg_index = current_sg->length;
-	//the first entry in the scatter list contains all the associated data
-	if (sg_index > size_of_assoc) {
-		mapped_nents++;
-	} else {
-		while (sg_index <= size_of_assoc) {
-			current_sg = sg_next(current_sg);
-			/* if have reached the end of the sgl, then this is
-			 * unexpected
-			 */
-			if (!current_sg) {
-				dev_err(dev, "reached end of sg list. unexpected\n");
-				return -EINVAL;
-			}
-			sg_index += current_sg->length;
-			mapped_nents++;
-		}
-	}
+	mapped_nents = sg_nents_for_len(req->src, size_of_assoc);
+	if (mapped_nents < 0)
+		return mapped_nents;
+
 	if (mapped_nents > LLI_MAX_NUM_OF_ASSOC_DATA_ENTRIES) {
 		dev_err(dev, "Too many fragments. current %d max %d\n",
 			mapped_nents, LLI_MAX_NUM_OF_ASSOC_DATA_ENTRIES);
@@ -835,7 +716,7 @@ static int cc_aead_chain_assoc(struct cc_drvdata *drvdata,
 			cc_dma_buf_type(areq_ctx->assoc_buff_type),
 			areq_ctx->assoc.nents);
 		cc_add_sg_entry(dev, sg_data, areq_ctx->assoc.nents, req->src,
-				req->assoclen, 0, is_last,
+				areq_ctx->assoclen, 0, is_last,
 				&areq_ctx->assoc.mlli_nents);
 		areq_ctx->assoc_buff_type = CC_DMA_BUF_MLLI;
 	}
@@ -850,39 +731,32 @@ static void cc_prepare_aead_data_dlli(struct aead_request *req,
 	struct aead_req_ctx *areq_ctx = aead_request_ctx(req);
 	enum drv_crypto_direction direct = areq_ctx->gen_ctx.op_type;
 	unsigned int authsize = areq_ctx->req_authsize;
+	struct scatterlist *sg;
+	ssize_t offset;
 
 	areq_ctx->is_icv_fragmented = false;
-	if (req->src == req->dst) {
-		/*INPLACE*/
-		areq_ctx->icv_dma_addr = sg_dma_address(areq_ctx->src_sgl) +
-			(*src_last_bytes - authsize);
-		areq_ctx->icv_virt_addr = sg_virt(areq_ctx->src_sgl) +
-			(*src_last_bytes - authsize);
-	} else if (direct == DRV_CRYPTO_DIRECTION_DECRYPT) {
-		/*NON-INPLACE and DECRYPT*/
-		areq_ctx->icv_dma_addr = sg_dma_address(areq_ctx->src_sgl) +
-			(*src_last_bytes - authsize);
-		areq_ctx->icv_virt_addr = sg_virt(areq_ctx->src_sgl) +
-			(*src_last_bytes - authsize);
+
+	if ((req->src == req->dst) || direct == DRV_CRYPTO_DIRECTION_DECRYPT) {
+		sg = areq_ctx->src_sgl;
+		offset = *src_last_bytes - authsize;
 	} else {
-		/*NON-INPLACE and ENCRYPT*/
-		areq_ctx->icv_dma_addr = sg_dma_address(areq_ctx->dst_sgl) +
-			(*dst_last_bytes - authsize);
-		areq_ctx->icv_virt_addr = sg_virt(areq_ctx->dst_sgl) +
-			(*dst_last_bytes - authsize);
+		sg = areq_ctx->dst_sgl;
+		offset = *dst_last_bytes - authsize;
 	}
+
+	areq_ctx->icv_dma_addr = sg_dma_address(sg) + offset;
+	areq_ctx->icv_virt_addr = sg_virt(sg) + offset;
 }
 
-static int cc_prepare_aead_data_mlli(struct cc_drvdata *drvdata,
-				     struct aead_request *req,
-				     struct buffer_array *sg_data,
-				     u32 *src_last_bytes, u32 *dst_last_bytes,
-				     bool is_last_table)
+static void cc_prepare_aead_data_mlli(struct cc_drvdata *drvdata,
+				      struct aead_request *req,
+				      struct buffer_array *sg_data,
+				      u32 *src_last_bytes, u32 *dst_last_bytes,
+				      bool is_last_table)
 {
 	struct aead_req_ctx *areq_ctx = aead_request_ctx(req);
 	enum drv_crypto_direction direct = areq_ctx->gen_ctx.op_type;
 	unsigned int authsize = areq_ctx->req_authsize;
-	int rc = 0, icv_nents;
 	struct device *dev = drvdata_to_dev(drvdata);
 	struct scatterlist *sg;
 
@@ -893,14 +767,9 @@ static int cc_prepare_aead_data_mlli(struct cc_drvdata *drvdata,
 				areq_ctx->src_offset, is_last_table,
 				&areq_ctx->src.mlli_nents);
 
-		icv_nents = cc_get_aead_icv_nents(dev, areq_ctx->src_sgl,
-						  areq_ctx->src.nents,
-						  authsize, *src_last_bytes,
-						  &areq_ctx->is_icv_fragmented);
-		if (icv_nents < 0) {
-			rc = -ENOTSUPP;
-			goto prepare_data_mlli_exit;
-		}
+		areq_ctx->is_icv_fragmented =
+			cc_is_icv_frag(areq_ctx->src.nents, authsize,
+				       *src_last_bytes);
 
 		if (areq_ctx->is_icv_fragmented) {
 			/* Backup happens only when ICV is fragmented, ICV
@@ -942,16 +811,11 @@ static int cc_prepare_aead_data_mlli(struct cc_drvdata *drvdata,
 				areq_ctx->dst_offset, is_last_table,
 				&areq_ctx->dst.mlli_nents);
 
-		icv_nents = cc_get_aead_icv_nents(dev, areq_ctx->src_sgl,
-						  areq_ctx->src.nents,
-						  authsize, *src_last_bytes,
-						  &areq_ctx->is_icv_fragmented);
-		if (icv_nents < 0) {
-			rc = -ENOTSUPP;
-			goto prepare_data_mlli_exit;
-		}
-
+		areq_ctx->is_icv_fragmented =
+			cc_is_icv_frag(areq_ctx->src.nents, authsize,
+				       *src_last_bytes);
 		/* Backup happens only when ICV is fragmented, ICV
+
 		 * verification is made by CPU compare in order to simplify
 		 * MAC verification upon request completion
 		 */
@@ -979,14 +843,9 @@ static int cc_prepare_aead_data_mlli(struct cc_drvdata *drvdata,
 				areq_ctx->src_offset, is_last_table,
 				&areq_ctx->src.mlli_nents);
 
-		icv_nents = cc_get_aead_icv_nents(dev, areq_ctx->dst_sgl,
-						  areq_ctx->dst.nents,
-						  authsize, *dst_last_bytes,
-						  &areq_ctx->is_icv_fragmented);
-		if (icv_nents < 0) {
-			rc = -ENOTSUPP;
-			goto prepare_data_mlli_exit;
-		}
+		areq_ctx->is_icv_fragmented =
+			cc_is_icv_frag(areq_ctx->dst.nents, authsize,
+				       *dst_last_bytes);
 
 		if (!areq_ctx->is_icv_fragmented) {
 			sg = &areq_ctx->dst_sgl[areq_ctx->dst.nents - 1];
@@ -1000,9 +859,6 @@ static int cc_prepare_aead_data_mlli(struct cc_drvdata *drvdata,
 			areq_ctx->icv_virt_addr = areq_ctx->mac_buf;
 		}
 	}
-
-prepare_data_mlli_exit:
-	return rc;
 }
 
 static int cc_aead_chain_data(struct cc_drvdata *drvdata,
@@ -1019,12 +875,12 @@ static int cc_aead_chain_data(struct cc_drvdata *drvdata,
 	u32 src_mapped_nents = 0, dst_mapped_nents = 0;
 	u32 offset = 0;
 	/* non-inplace mode */
-	unsigned int size_for_map = req->assoclen + req->cryptlen;
+	unsigned int size_for_map = areq_ctx->assoclen + req->cryptlen;
 	struct crypto_aead *tfm = crypto_aead_reqtfm(req);
 	u32 sg_index = 0;
-	bool chained = false;
 	bool is_gcm4543 = areq_ctx->is_gcm4543;
-	u32 size_to_skip = req->assoclen;
+	u32 size_to_skip = areq_ctx->assoclen;
+	struct scatterlist *sgl;
 
 	if (is_gcm4543)
 		size_to_skip += crypto_aead_ivsize(tfm);
@@ -1043,19 +899,17 @@ static int cc_aead_chain_data(struct cc_drvdata *drvdata,
 	size_for_map += (direct == DRV_CRYPTO_DIRECTION_ENCRYPT) ?
 			authsize : 0;
 	src_mapped_nents = cc_get_sgl_nents(dev, req->src, size_for_map,
-					    &src_last_bytes, &chained);
+					    &src_last_bytes);
 	sg_index = areq_ctx->src_sgl->length;
 	//check where the data starts
 	while (sg_index <= size_to_skip) {
+		src_mapped_nents--;
 		offset -= areq_ctx->src_sgl->length;
-		areq_ctx->src_sgl = sg_next(areq_ctx->src_sgl);
-		//if have reached the end of the sgl, then this is unexpected
-		if (!areq_ctx->src_sgl) {
-			dev_err(dev, "reached end of sg list. unexpected\n");
-			return -EINVAL;
-		}
+		sgl = sg_next(areq_ctx->src_sgl);
+		if (!sgl)
+			break;
+		areq_ctx->src_sgl = sgl;
 		sg_index += areq_ctx->src_sgl->length;
-		src_mapped_nents--;
 	}
 	if (src_mapped_nents > LLI_MAX_NUM_OF_DATA_ENTRIES) {
 		dev_err(dev, "Too many fragments. current %d max %d\n",
@@ -1068,7 +922,7 @@ static int cc_aead_chain_data(struct cc_drvdata *drvdata,
 	areq_ctx->src_offset = offset;
 
 	if (req->src != req->dst) {
-		size_for_map = req->assoclen + req->cryptlen;
+		size_for_map = areq_ctx->assoclen + req->cryptlen;
 		size_for_map += (direct == DRV_CRYPTO_DIRECTION_ENCRYPT) ?
 				authsize : 0;
 		if (is_gcm4543)
@@ -1083,21 +937,19 @@ static int cc_aead_chain_data(struct cc_drvdata *drvdata,
 	}
 
 	dst_mapped_nents = cc_get_sgl_nents(dev, req->dst, size_for_map,
-					    &dst_last_bytes, &chained);
+					    &dst_last_bytes);
 	sg_index = areq_ctx->dst_sgl->length;
 	offset = size_to_skip;
 
 	//check where the data starts
 	while (sg_index <= size_to_skip) {
+		dst_mapped_nents--;
 		offset -= areq_ctx->dst_sgl->length;
-		areq_ctx->dst_sgl = sg_next(areq_ctx->dst_sgl);
-		//if have reached the end of the sgl, then this is unexpected
-		if (!areq_ctx->dst_sgl) {
-			dev_err(dev, "reached end of sg list. unexpected\n");
-			return -EINVAL;
-		}
+		sgl = sg_next(areq_ctx->dst_sgl);
+		if (!sgl)
+			break;
+		areq_ctx->dst_sgl = sgl;
 		sg_index += areq_ctx->dst_sgl->length;
-		dst_mapped_nents--;
 	}
 	if (dst_mapped_nents > LLI_MAX_NUM_OF_DATA_ENTRIES) {
 		dev_err(dev, "Too many fragments. current %d max %d\n",
@@ -1110,9 +962,9 @@ static int cc_aead_chain_data(struct cc_drvdata *drvdata,
 	    dst_mapped_nents  > 1 ||
 	    do_chain) {
 		areq_ctx->data_buff_type = CC_DMA_BUF_MLLI;
-		rc = cc_prepare_aead_data_mlli(drvdata, req, sg_data,
-					       &src_last_bytes,
-					       &dst_last_bytes, is_last_table);
+		cc_prepare_aead_data_mlli(drvdata, req, sg_data,
+					  &src_last_bytes, &dst_last_bytes,
+					  is_last_table);
 	} else {
 		areq_ctx->data_buff_type = CC_DMA_BUF_DLLI;
 		cc_prepare_aead_data_dlli(req, &src_last_bytes,
@@ -1234,7 +1086,7 @@ int cc_map_aead_request(struct cc_drvdata *drvdata, struct aead_request *req)
 		areq_ctx->ccm_iv0_dma_addr = dma_addr;
 
 		rc = cc_set_aead_conf_buf(dev, areq_ctx, areq_ctx->ccm_config,
-					  &sg_data, req->assoclen);
+					  &sg_data, areq_ctx->assoclen);
 		if (rc)
 			goto aead_map_failure;
 	}
@@ -1285,7 +1137,7 @@ int cc_map_aead_request(struct cc_drvdata *drvdata, struct aead_request *req)
 		areq_ctx->gcm_iv_inc2_dma_addr = dma_addr;
 	}
 
-	size_to_map = req->cryptlen + req->assoclen;
+	size_to_map = req->cryptlen + areq_ctx->assoclen;
 	if (areq_ctx->gen_ctx.op_type == DRV_CRYPTO_DIRECTION_ENCRYPT)
 		size_to_map += authsize;
 
@@ -1483,8 +1335,7 @@ int cc_map_hash_request_update(struct cc_drvdata *drvdata, void *ctx,
 	if (total_in_len < block_size) {
 		dev_dbg(dev, " less than one block: curr_buff=%pK *curr_buff_cnt=0x%X copy_to=%pK\n",
 			curr_buff, *curr_buff_cnt, &curr_buff[*curr_buff_cnt]);
-		areq_ctx->in_nents =
-			cc_get_sgl_nents(dev, src, nbytes, &dummy, NULL);
+		areq_ctx->in_nents = sg_nents_for_len(src, nbytes);
 		sg_copy_to_buffer(src, areq_ctx->in_nents,
 				  &curr_buff[*curr_buff_cnt], nbytes);
 		*curr_buff_cnt += nbytes;
diff --git a/drivers/crypto/ccree/cc_buffer_mgr.h b/drivers/crypto/ccree/cc_buffer_mgr.h
index 3ec4b4db5247..a726016bdbc1 100644
--- a/drivers/crypto/ccree/cc_buffer_mgr.h
+++ b/drivers/crypto/ccree/cc_buffer_mgr.h
@@ -1,5 +1,5 @@
 /* SPDX-License-Identifier: GPL-2.0 */
-/* Copyright (C) 2012-2018 ARM Limited or its affiliates. */
+/* Copyright (C) 2012-2019 ARM Limited (or its affiliates). */
 
 /* \file cc_buffer_mgr.h
  * Buffer Manager
diff --git a/drivers/crypto/ccree/cc_cipher.c b/drivers/crypto/ccree/cc_cipher.c
index d9c17078517b..5b58226ea24d 100644
--- a/drivers/crypto/ccree/cc_cipher.c
+++ b/drivers/crypto/ccree/cc_cipher.c
@@ -1,5 +1,5 @@
 // SPDX-License-Identifier: GPL-2.0
-/* Copyright (C) 2012-2018 ARM Limited or its affiliates. */
+/* Copyright (C) 2012-2019 ARM Limited (or its affiliates). */
 
 #include <linux/kernel.h>
 #include <linux/module.h>
@@ -34,6 +34,18 @@ struct cc_hw_key_info {
 	enum cc_hw_crypto_key key2_slot;
 };
 
+struct cc_cpp_key_info {
+	u8 slot;
+	enum cc_cpp_alg alg;
+};
+
+enum cc_key_type {
+	CC_UNPROTECTED_KEY,		/* User key */
+	CC_HW_PROTECTED_KEY,		/* HW (FDE) key */
+	CC_POLICY_PROTECTED_KEY,	/* CPP key */
+	CC_INVALID_PROTECTED_KEY	/* Invalid key */
+};
+
 struct cc_cipher_ctx {
 	struct cc_drvdata *drvdata;
 	int keylen;
@@ -41,19 +53,22 @@ struct cc_cipher_ctx {
 	int cipher_mode;
 	int flow_mode;
 	unsigned int flags;
-	bool hw_key;
+	enum cc_key_type key_type;
 	struct cc_user_key_info user;
-	struct cc_hw_key_info hw;
+	union {
+		struct cc_hw_key_info hw;
+		struct cc_cpp_key_info cpp;
+	};
 	struct crypto_shash *shash_tfm;
 };
 
 static void cc_cipher_complete(struct device *dev, void *cc_req, int err);
 
-static inline bool cc_is_hw_key(struct crypto_tfm *tfm)
+static inline enum cc_key_type cc_key_type(struct crypto_tfm *tfm)
 {
 	struct cc_cipher_ctx *ctx_p = crypto_tfm_ctx(tfm);
 
-	return ctx_p->hw_key;
+	return ctx_p->key_type;
 }
 
 static int validate_keys_sizes(struct cc_cipher_ctx *ctx_p, u32 size)
@@ -232,7 +247,7 @@ struct tdes_keys {
 	u8	key3[DES_KEY_SIZE];
 };
 
-static enum cc_hw_crypto_key cc_slot_to_hw_key(int slot_num)
+static enum cc_hw_crypto_key cc_slot_to_hw_key(u8 slot_num)
 {
 	switch (slot_num) {
 	case 0:
@@ -247,6 +262,22 @@ static enum cc_hw_crypto_key cc_slot_to_hw_key(int slot_num)
 	return END_OF_KEYS;
 }
 
+static u8 cc_slot_to_cpp_key(u8 slot_num)
+{
+	return (slot_num - CC_FIRST_CPP_KEY_SLOT);
+}
+
+static inline enum cc_key_type cc_slot_to_key_type(u8 slot_num)
+{
+	if (slot_num >= CC_FIRST_HW_KEY_SLOT && slot_num <= CC_LAST_HW_KEY_SLOT)
+		return CC_HW_PROTECTED_KEY;
+	else if (slot_num >=  CC_FIRST_CPP_KEY_SLOT &&
+		 slot_num <=  CC_LAST_CPP_KEY_SLOT)
+		return CC_POLICY_PROTECTED_KEY;
+	else
+		return CC_INVALID_PROTECTED_KEY;
+}
+
 static int cc_cipher_sethkey(struct crypto_skcipher *sktfm, const u8 *key,
 			     unsigned int keylen)
 {
@@ -261,18 +292,13 @@ static int cc_cipher_sethkey(struct crypto_skcipher *sktfm, const u8 *key,
 
 	/* STAT_PHASE_0: Init and sanity checks */
 
-	/* This check the size of the hardware key token */
+	/* This check the size of the protected key token */
 	if (keylen != sizeof(hki)) {
-		dev_err(dev, "Unsupported HW key size %d.\n", keylen);
+		dev_err(dev, "Unsupported protected key size %d.\n", keylen);
 		crypto_tfm_set_flags(tfm, CRYPTO_TFM_RES_BAD_KEY_LEN);
 		return -EINVAL;
 	}
 
-	if (ctx_p->flow_mode != S_DIN_to_AES) {
-		dev_err(dev, "HW key not supported for non-AES flows\n");
-		return -EINVAL;
-	}
-
 	memcpy(&hki, key, keylen);
 
 	/* The real key len for crypto op is the size of the HW key
@@ -286,31 +312,70 @@ static int cc_cipher_sethkey(struct crypto_skcipher *sktfm, const u8 *key,
 		return -EINVAL;
 	}
 
-	ctx_p->hw.key1_slot = cc_slot_to_hw_key(hki.hw_key1);
-	if (ctx_p->hw.key1_slot == END_OF_KEYS) {
-		dev_err(dev, "Unsupported hw key1 number (%d)\n", hki.hw_key1);
-		return -EINVAL;
-	}
+	ctx_p->keylen = keylen;
 
-	if (ctx_p->cipher_mode == DRV_CIPHER_XTS ||
-	    ctx_p->cipher_mode == DRV_CIPHER_ESSIV ||
-	    ctx_p->cipher_mode == DRV_CIPHER_BITLOCKER) {
-		if (hki.hw_key1 == hki.hw_key2) {
-			dev_err(dev, "Illegal hw key numbers (%d,%d)\n",
-				hki.hw_key1, hki.hw_key2);
+	switch (cc_slot_to_key_type(hki.hw_key1)) {
+	case CC_HW_PROTECTED_KEY:
+		if (ctx_p->flow_mode == S_DIN_to_SM4) {
+			dev_err(dev, "Only AES HW protected keys are supported\n");
 			return -EINVAL;
 		}
-		ctx_p->hw.key2_slot = cc_slot_to_hw_key(hki.hw_key2);
-		if (ctx_p->hw.key2_slot == END_OF_KEYS) {
-			dev_err(dev, "Unsupported hw key2 number (%d)\n",
-				hki.hw_key2);
+
+		ctx_p->hw.key1_slot = cc_slot_to_hw_key(hki.hw_key1);
+		if (ctx_p->hw.key1_slot == END_OF_KEYS) {
+			dev_err(dev, "Unsupported hw key1 number (%d)\n",
+				hki.hw_key1);
 			return -EINVAL;
 		}
-	}
 
-	ctx_p->keylen = keylen;
-	ctx_p->hw_key = true;
-	dev_dbg(dev, "cc_is_hw_key ret 0");
+		if (ctx_p->cipher_mode == DRV_CIPHER_XTS ||
+		    ctx_p->cipher_mode == DRV_CIPHER_ESSIV ||
+		    ctx_p->cipher_mode == DRV_CIPHER_BITLOCKER) {
+			if (hki.hw_key1 == hki.hw_key2) {
+				dev_err(dev, "Illegal hw key numbers (%d,%d)\n",
+					hki.hw_key1, hki.hw_key2);
+				return -EINVAL;
+			}
+
+			ctx_p->hw.key2_slot = cc_slot_to_hw_key(hki.hw_key2);
+			if (ctx_p->hw.key2_slot == END_OF_KEYS) {
+				dev_err(dev, "Unsupported hw key2 number (%d)\n",
+					hki.hw_key2);
+				return -EINVAL;
+			}
+		}
+
+		ctx_p->key_type = CC_HW_PROTECTED_KEY;
+		dev_dbg(dev, "HW protected key  %d/%d set\n.",
+			ctx_p->hw.key1_slot, ctx_p->hw.key2_slot);
+		break;
+
+	case CC_POLICY_PROTECTED_KEY:
+		if (ctx_p->drvdata->hw_rev < CC_HW_REV_713) {
+			dev_err(dev, "CPP keys not supported in this hardware revision.\n");
+			return -EINVAL;
+		}
+
+		if (ctx_p->cipher_mode != DRV_CIPHER_CBC &&
+		    ctx_p->cipher_mode != DRV_CIPHER_CTR) {
+			dev_err(dev, "CPP keys only supported in CBC or CTR modes.\n");
+			return -EINVAL;
+		}
+
+		ctx_p->cpp.slot = cc_slot_to_cpp_key(hki.hw_key1);
+		if (ctx_p->flow_mode == S_DIN_to_AES)
+			ctx_p->cpp.alg = CC_CPP_AES;
+		else /* Must be SM4 since due to sethkey registration */
+			ctx_p->cpp.alg = CC_CPP_SM4;
+		ctx_p->key_type = CC_POLICY_PROTECTED_KEY;
+		dev_dbg(dev, "policy protected key alg: %d slot: %d.\n",
+			ctx_p->cpp.alg, ctx_p->cpp.slot);
+		break;
+
+	default:
+		dev_err(dev, "Unsupported protected key (%d)\n", hki.hw_key1);
+		return -EINVAL;
+	}
 
 	return 0;
 }
@@ -321,7 +386,6 @@ static int cc_cipher_setkey(struct crypto_skcipher *sktfm, const u8 *key,
 	struct crypto_tfm *tfm = crypto_skcipher_tfm(sktfm);
 	struct cc_cipher_ctx *ctx_p = crypto_tfm_ctx(tfm);
 	struct device *dev = drvdata_to_dev(ctx_p->drvdata);
-	u32 tmp[DES3_EDE_EXPKEY_WORDS];
 	struct cc_crypto_alg *cc_alg =
 			container_of(tfm->__crt_alg, struct cc_crypto_alg,
 				     skcipher_alg.base);
@@ -339,7 +403,7 @@ static int cc_cipher_setkey(struct crypto_skcipher *sktfm, const u8 *key,
 		return -EINVAL;
 	}
 
-	ctx_p->hw_key = false;
+	ctx_p->key_type = CC_UNPROTECTED_KEY;
 
 	/*
 	 * Verify DES weak keys
@@ -347,6 +411,7 @@ static int cc_cipher_setkey(struct crypto_skcipher *sktfm, const u8 *key,
 	 * HW does the expansion on its own.
 	 */
 	if (ctx_p->flow_mode == S_DIN_to_DES) {
+		u32 tmp[DES3_EDE_EXPKEY_WORDS];
 		if (keylen == DES3_EDE_KEY_SIZE &&
 		    __des3_ede_setkey(tmp, &tfm->crt_flags, key,
 				      DES3_EDE_KEY_SIZE)) {
@@ -399,7 +464,77 @@ static int cc_cipher_setkey(struct crypto_skcipher *sktfm, const u8 *key,
 	return 0;
 }
 
-static void cc_setup_cipher_desc(struct crypto_tfm *tfm,
+static int cc_out_setup_mode(struct cc_cipher_ctx *ctx_p)
+{
+	switch (ctx_p->flow_mode) {
+	case S_DIN_to_AES:
+		return S_AES_to_DOUT;
+	case S_DIN_to_DES:
+		return S_DES_to_DOUT;
+	case S_DIN_to_SM4:
+		return S_SM4_to_DOUT;
+	default:
+		return ctx_p->flow_mode;
+	}
+}
+
+static void cc_setup_readiv_desc(struct crypto_tfm *tfm,
+				 struct cipher_req_ctx *req_ctx,
+				 unsigned int ivsize, struct cc_hw_desc desc[],
+				 unsigned int *seq_size)
+{
+	struct cc_cipher_ctx *ctx_p = crypto_tfm_ctx(tfm);
+	struct device *dev = drvdata_to_dev(ctx_p->drvdata);
+	int cipher_mode = ctx_p->cipher_mode;
+	int flow_mode = cc_out_setup_mode(ctx_p);
+	int direction = req_ctx->gen_ctx.op_type;
+	dma_addr_t iv_dma_addr = req_ctx->gen_ctx.iv_dma_addr;
+
+	if (ctx_p->key_type == CC_POLICY_PROTECTED_KEY)
+		return;
+
+	switch (cipher_mode) {
+	case DRV_CIPHER_ECB:
+		break;
+	case DRV_CIPHER_CBC:
+	case DRV_CIPHER_CBC_CTS:
+	case DRV_CIPHER_CTR:
+	case DRV_CIPHER_OFB:
+		/* Read next IV */
+		hw_desc_init(&desc[*seq_size]);
+		set_dout_dlli(&desc[*seq_size], iv_dma_addr, ivsize, NS_BIT, 1);
+		set_cipher_config0(&desc[*seq_size], direction);
+		set_flow_mode(&desc[*seq_size], flow_mode);
+		set_cipher_mode(&desc[*seq_size], cipher_mode);
+		if (cipher_mode == DRV_CIPHER_CTR ||
+		    cipher_mode == DRV_CIPHER_OFB) {
+			set_setup_mode(&desc[*seq_size], SETUP_WRITE_STATE1);
+		} else {
+			set_setup_mode(&desc[*seq_size], SETUP_WRITE_STATE0);
+		}
+		set_queue_last_ind(ctx_p->drvdata, &desc[*seq_size]);
+		(*seq_size)++;
+		break;
+	case DRV_CIPHER_XTS:
+	case DRV_CIPHER_ESSIV:
+	case DRV_CIPHER_BITLOCKER:
+		/*  IV */
+		hw_desc_init(&desc[*seq_size]);
+		set_setup_mode(&desc[*seq_size], SETUP_WRITE_STATE1);
+		set_cipher_mode(&desc[*seq_size], cipher_mode);
+		set_cipher_config0(&desc[*seq_size], direction);
+		set_flow_mode(&desc[*seq_size], flow_mode);
+		set_dout_dlli(&desc[*seq_size], iv_dma_addr, CC_AES_BLOCK_SIZE,
+			     NS_BIT, 1);
+		set_queue_last_ind(ctx_p->drvdata, &desc[*seq_size]);
+		(*seq_size)++;
+		break;
+	default:
+		dev_err(dev, "Unsupported cipher mode (%d)\n", cipher_mode);
+	}
+}
+
+static void cc_setup_state_desc(struct crypto_tfm *tfm,
 				 struct cipher_req_ctx *req_ctx,
 				 unsigned int ivsize, unsigned int nbytes,
 				 struct cc_hw_desc desc[],
@@ -423,11 +558,13 @@ static void cc_setup_cipher_desc(struct crypto_tfm *tfm,
 		du_size = cc_alg->data_unit;
 
 	switch (cipher_mode) {
+	case DRV_CIPHER_ECB:
+		break;
 	case DRV_CIPHER_CBC:
 	case DRV_CIPHER_CBC_CTS:
 	case DRV_CIPHER_CTR:
 	case DRV_CIPHER_OFB:
-		/* Load cipher state */
+		/* Load IV */
 		hw_desc_init(&desc[*seq_size]);
 		set_din_type(&desc[*seq_size], DMA_DLLI, iv_dma_addr, ivsize,
 			     NS_BIT);
@@ -441,57 +578,15 @@ static void cc_setup_cipher_desc(struct crypto_tfm *tfm,
 			set_setup_mode(&desc[*seq_size], SETUP_LOAD_STATE0);
 		}
 		(*seq_size)++;
-		/*FALLTHROUGH*/
-	case DRV_CIPHER_ECB:
-		/* Load key */
-		hw_desc_init(&desc[*seq_size]);
-		set_cipher_mode(&desc[*seq_size], cipher_mode);
-		set_cipher_config0(&desc[*seq_size], direction);
-		if (flow_mode == S_DIN_to_AES) {
-			if (cc_is_hw_key(tfm)) {
-				set_hw_crypto_key(&desc[*seq_size],
-						  ctx_p->hw.key1_slot);
-			} else {
-				set_din_type(&desc[*seq_size], DMA_DLLI,
-					     key_dma_addr, ((key_len == 24) ?
-							    AES_MAX_KEY_SIZE :
-							    key_len), NS_BIT);
-			}
-			set_key_size_aes(&desc[*seq_size], key_len);
-		} else {
-			/*des*/
-			set_din_type(&desc[*seq_size], DMA_DLLI, key_dma_addr,
-				     key_len, NS_BIT);
-			set_key_size_des(&desc[*seq_size], key_len);
-		}
-		set_flow_mode(&desc[*seq_size], flow_mode);
-		set_setup_mode(&desc[*seq_size], SETUP_LOAD_KEY0);
-		(*seq_size)++;
 		break;
 	case DRV_CIPHER_XTS:
 	case DRV_CIPHER_ESSIV:
 	case DRV_CIPHER_BITLOCKER:
-		/* Load AES key */
-		hw_desc_init(&desc[*seq_size]);
-		set_cipher_mode(&desc[*seq_size], cipher_mode);
-		set_cipher_config0(&desc[*seq_size], direction);
-		if (cc_is_hw_key(tfm)) {
-			set_hw_crypto_key(&desc[*seq_size],
-					  ctx_p->hw.key1_slot);
-		} else {
-			set_din_type(&desc[*seq_size], DMA_DLLI, key_dma_addr,
-				     (key_len / 2), NS_BIT);
-		}
-		set_key_size_aes(&desc[*seq_size], (key_len / 2));
-		set_flow_mode(&desc[*seq_size], flow_mode);
-		set_setup_mode(&desc[*seq_size], SETUP_LOAD_KEY0);
-		(*seq_size)++;
-
 		/* load XEX key */
 		hw_desc_init(&desc[*seq_size]);
 		set_cipher_mode(&desc[*seq_size], cipher_mode);
 		set_cipher_config0(&desc[*seq_size], direction);
-		if (cc_is_hw_key(tfm)) {
+		if (cc_key_type(tfm) == CC_HW_PROTECTED_KEY) {
 			set_hw_crypto_key(&desc[*seq_size],
 					  ctx_p->hw.key2_slot);
 		} else {
@@ -505,7 +600,7 @@ static void cc_setup_cipher_desc(struct crypto_tfm *tfm,
 		set_setup_mode(&desc[*seq_size], SETUP_LOAD_XEX_KEY);
 		(*seq_size)++;
 
-		/* Set state */
+		/* Load IV */
 		hw_desc_init(&desc[*seq_size]);
 		set_setup_mode(&desc[*seq_size], SETUP_LOAD_STATE1);
 		set_cipher_mode(&desc[*seq_size], cipher_mode);
@@ -521,48 +616,113 @@ static void cc_setup_cipher_desc(struct crypto_tfm *tfm,
 	}
 }
 
-static void cc_setup_cipher_data(struct crypto_tfm *tfm,
-				 struct cipher_req_ctx *req_ctx,
-				 struct scatterlist *dst,
-				 struct scatterlist *src, unsigned int nbytes,
-				 void *areq, struct cc_hw_desc desc[],
-				 unsigned int *seq_size)
+static int cc_out_flow_mode(struct cc_cipher_ctx *ctx_p)
 {
-	struct cc_cipher_ctx *ctx_p = crypto_tfm_ctx(tfm);
-	struct device *dev = drvdata_to_dev(ctx_p->drvdata);
-	unsigned int flow_mode = ctx_p->flow_mode;
-
 	switch (ctx_p->flow_mode) {
 	case S_DIN_to_AES:
-		flow_mode = DIN_AES_DOUT;
-		break;
+		return DIN_AES_DOUT;
 	case S_DIN_to_DES:
-		flow_mode = DIN_DES_DOUT;
-		break;
+		return DIN_DES_DOUT;
 	case S_DIN_to_SM4:
-		flow_mode = DIN_SM4_DOUT;
-		break;
+		return DIN_SM4_DOUT;
 	default:
-		dev_err(dev, "invalid flow mode, flow_mode = %d\n", flow_mode);
-		return;
+		return ctx_p->flow_mode;
 	}
-	/* Process */
-	if (req_ctx->dma_buf_type == CC_DMA_BUF_DLLI) {
-		dev_dbg(dev, " data params addr %pad length 0x%X\n",
-			&sg_dma_address(src), nbytes);
-		dev_dbg(dev, " data params addr %pad length 0x%X\n",
-			&sg_dma_address(dst), nbytes);
+}
+
+static void cc_setup_key_desc(struct crypto_tfm *tfm,
+			      struct cipher_req_ctx *req_ctx,
+			      unsigned int nbytes, struct cc_hw_desc desc[],
+			      unsigned int *seq_size)
+{
+	struct cc_cipher_ctx *ctx_p = crypto_tfm_ctx(tfm);
+	struct device *dev = drvdata_to_dev(ctx_p->drvdata);
+	int cipher_mode = ctx_p->cipher_mode;
+	int flow_mode = ctx_p->flow_mode;
+	int direction = req_ctx->gen_ctx.op_type;
+	dma_addr_t key_dma_addr = ctx_p->user.key_dma_addr;
+	unsigned int key_len = ctx_p->keylen;
+	unsigned int din_size;
+
+	switch (cipher_mode) {
+	case DRV_CIPHER_CBC:
+	case DRV_CIPHER_CBC_CTS:
+	case DRV_CIPHER_CTR:
+	case DRV_CIPHER_OFB:
+	case DRV_CIPHER_ECB:
+		/* Load key */
 		hw_desc_init(&desc[*seq_size]);
-		set_din_type(&desc[*seq_size], DMA_DLLI, sg_dma_address(src),
-			     nbytes, NS_BIT);
-		set_dout_dlli(&desc[*seq_size], sg_dma_address(dst),
-			      nbytes, NS_BIT, (!areq ? 0 : 1));
-		if (areq)
-			set_queue_last_ind(ctx_p->drvdata, &desc[*seq_size]);
+		set_cipher_mode(&desc[*seq_size], cipher_mode);
+		set_cipher_config0(&desc[*seq_size], direction);
 
+		if (cc_key_type(tfm) == CC_POLICY_PROTECTED_KEY) {
+			/* We use the AES key size coding for all CPP algs */
+			set_key_size_aes(&desc[*seq_size], key_len);
+			set_cpp_crypto_key(&desc[*seq_size], ctx_p->cpp.slot);
+			flow_mode = cc_out_flow_mode(ctx_p);
+		} else {
+			if (flow_mode == S_DIN_to_AES) {
+				if (cc_key_type(tfm) == CC_HW_PROTECTED_KEY) {
+					set_hw_crypto_key(&desc[*seq_size],
+							  ctx_p->hw.key1_slot);
+				} else {
+					/* CC_POLICY_UNPROTECTED_KEY
+					 * Invalid keys are filtered out in
+					 * sethkey()
+					 */
+					din_size = (key_len == 24) ?
+						AES_MAX_KEY_SIZE : key_len;
+
+					set_din_type(&desc[*seq_size], DMA_DLLI,
+						     key_dma_addr, din_size,
+						     NS_BIT);
+				}
+				set_key_size_aes(&desc[*seq_size], key_len);
+			} else {
+				/*des*/
+				set_din_type(&desc[*seq_size], DMA_DLLI,
+					     key_dma_addr, key_len, NS_BIT);
+				set_key_size_des(&desc[*seq_size], key_len);
+			}
+			set_setup_mode(&desc[*seq_size], SETUP_LOAD_KEY0);
+		}
 		set_flow_mode(&desc[*seq_size], flow_mode);
 		(*seq_size)++;
-	} else {
+		break;
+	case DRV_CIPHER_XTS:
+	case DRV_CIPHER_ESSIV:
+	case DRV_CIPHER_BITLOCKER:
+		/* Load AES key */
+		hw_desc_init(&desc[*seq_size]);
+		set_cipher_mode(&desc[*seq_size], cipher_mode);
+		set_cipher_config0(&desc[*seq_size], direction);
+		if (cc_key_type(tfm) == CC_HW_PROTECTED_KEY) {
+			set_hw_crypto_key(&desc[*seq_size],
+					  ctx_p->hw.key1_slot);
+		} else {
+			set_din_type(&desc[*seq_size], DMA_DLLI, key_dma_addr,
+				     (key_len / 2), NS_BIT);
+		}
+		set_key_size_aes(&desc[*seq_size], (key_len / 2));
+		set_flow_mode(&desc[*seq_size], flow_mode);
+		set_setup_mode(&desc[*seq_size], SETUP_LOAD_KEY0);
+		(*seq_size)++;
+		break;
+	default:
+		dev_err(dev, "Unsupported cipher mode (%d)\n", cipher_mode);
+	}
+}
+
+static void cc_setup_mlli_desc(struct crypto_tfm *tfm,
+			       struct cipher_req_ctx *req_ctx,
+			       struct scatterlist *dst, struct scatterlist *src,
+			       unsigned int nbytes, void *areq,
+			       struct cc_hw_desc desc[], unsigned int *seq_size)
+{
+	struct cc_cipher_ctx *ctx_p = crypto_tfm_ctx(tfm);
+	struct device *dev = drvdata_to_dev(ctx_p->drvdata);
+
+	if (req_ctx->dma_buf_type == CC_DMA_BUF_MLLI) {
 		/* bypass */
 		dev_dbg(dev, " bypass params addr %pad length 0x%X addr 0x%08X\n",
 			&req_ctx->mlli_params.mlli_dma_addr,
@@ -577,7 +737,38 @@ static void cc_setup_cipher_data(struct crypto_tfm *tfm,
 			      req_ctx->mlli_params.mlli_len);
 		set_flow_mode(&desc[*seq_size], BYPASS);
 		(*seq_size)++;
+	}
+}
+
+static void cc_setup_flow_desc(struct crypto_tfm *tfm,
+			       struct cipher_req_ctx *req_ctx,
+			       struct scatterlist *dst, struct scatterlist *src,
+			       unsigned int nbytes, struct cc_hw_desc desc[],
+			       unsigned int *seq_size)
+{
+	struct cc_cipher_ctx *ctx_p = crypto_tfm_ctx(tfm);
+	struct device *dev = drvdata_to_dev(ctx_p->drvdata);
+	unsigned int flow_mode = cc_out_flow_mode(ctx_p);
+	bool last_desc = (ctx_p->key_type == CC_POLICY_PROTECTED_KEY ||
+			  ctx_p->cipher_mode == DRV_CIPHER_ECB);
 
+	/* Process */
+	if (req_ctx->dma_buf_type == CC_DMA_BUF_DLLI) {
+		dev_dbg(dev, " data params addr %pad length 0x%X\n",
+			&sg_dma_address(src), nbytes);
+		dev_dbg(dev, " data params addr %pad length 0x%X\n",
+			&sg_dma_address(dst), nbytes);
+		hw_desc_init(&desc[*seq_size]);
+		set_din_type(&desc[*seq_size], DMA_DLLI, sg_dma_address(src),
+			     nbytes, NS_BIT);
+		set_dout_dlli(&desc[*seq_size], sg_dma_address(dst),
+			      nbytes, NS_BIT, (!last_desc ? 0 : 1));
+		if (last_desc)
+			set_queue_last_ind(ctx_p->drvdata, &desc[*seq_size]);
+
+		set_flow_mode(&desc[*seq_size], flow_mode);
+		(*seq_size)++;
+	} else {
 		hw_desc_init(&desc[*seq_size]);
 		set_din_type(&desc[*seq_size], DMA_MLLI,
 			     ctx_p->drvdata->mlli_sram_addr,
@@ -589,7 +780,7 @@ static void cc_setup_cipher_data(struct crypto_tfm *tfm,
 			set_dout_mlli(&desc[*seq_size],
 				      ctx_p->drvdata->mlli_sram_addr,
 				      req_ctx->in_mlli_nents, NS_BIT,
-				      (!areq ? 0 : 1));
+				      (!last_desc ? 0 : 1));
 		} else {
 			dev_dbg(dev, " din/dout params addr 0x%08X addr 0x%08X\n",
 				(unsigned int)ctx_p->drvdata->mlli_sram_addr,
@@ -600,9 +791,9 @@ static void cc_setup_cipher_data(struct crypto_tfm *tfm,
 				       (LLI_ENTRY_BYTE_SIZE *
 					req_ctx->in_mlli_nents)),
 				      req_ctx->out_mlli_nents, NS_BIT,
-				      (!areq ? 0 : 1));
+				      (!last_desc ? 0 : 1));
 		}
-		if (areq)
+		if (last_desc)
 			set_queue_last_ind(ctx_p->drvdata, &desc[*seq_size]);
 
 		set_flow_mode(&desc[*seq_size], flow_mode);
@@ -610,38 +801,6 @@ static void cc_setup_cipher_data(struct crypto_tfm *tfm,
 	}
 }
 
-/*
- * Update a CTR-AES 128 bit counter
- */
-static void cc_update_ctr(u8 *ctr, unsigned int increment)
-{
-	if (IS_ENABLED(CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS) ||
-	    IS_ALIGNED((unsigned long)ctr, 8)) {
-
-		__be64 *high_be = (__be64 *)ctr;
-		__be64 *low_be = high_be + 1;
-		u64 orig_low = __be64_to_cpu(*low_be);
-		u64 new_low = orig_low + (u64)increment;
-
-		*low_be = __cpu_to_be64(new_low);
-
-		if (new_low < orig_low)
-			*high_be = __cpu_to_be64(__be64_to_cpu(*high_be) + 1);
-	} else {
-		u8 *pos = (ctr + AES_BLOCK_SIZE);
-		u8 val;
-		unsigned int size;
-
-		for (; increment; increment--)
-			for (size = AES_BLOCK_SIZE; size; size--) {
-				val = *--pos + 1;
-				*pos = val;
-				if (val)
-					break;
-			}
-	}
-}
-
 static void cc_cipher_complete(struct device *dev, void *cc_req, int err)
 {
 	struct skcipher_request *req = (struct skcipher_request *)cc_req;
@@ -649,44 +808,15 @@ static void cc_cipher_complete(struct device *dev, void *cc_req, int err)
 	struct scatterlist *src = req->src;
 	struct cipher_req_ctx *req_ctx = skcipher_request_ctx(req);
 	struct crypto_skcipher *sk_tfm = crypto_skcipher_reqtfm(req);
-	struct crypto_tfm *tfm = crypto_skcipher_tfm(sk_tfm);
-	struct cc_cipher_ctx *ctx_p = crypto_tfm_ctx(tfm);
 	unsigned int ivsize = crypto_skcipher_ivsize(sk_tfm);
-	unsigned int len;
 
-	cc_unmap_cipher_request(dev, req_ctx, ivsize, src, dst);
-
-	switch (ctx_p->cipher_mode) {
-	case DRV_CIPHER_CBC:
-		/*
-		 * The crypto API expects us to set the req->iv to the last
-		 * ciphertext block. For encrypt, simply copy from the result.
-		 * For decrypt, we must copy from a saved buffer since this
-		 * could be an in-place decryption operation and the src is
-		 * lost by this point.
-		 */
-		if (req_ctx->gen_ctx.op_type == DRV_CRYPTO_DIRECTION_DECRYPT)  {
-			memcpy(req->iv, req_ctx->backup_info, ivsize);
-			kzfree(req_ctx->backup_info);
-		} else if (!err) {
-			len = req->cryptlen - ivsize;
-			scatterwalk_map_and_copy(req->iv, req->dst, len,
-						 ivsize, 0);
-		}
-		break;
-
-	case DRV_CIPHER_CTR:
-		/* Compute the counter of the last block */
-		len = ALIGN(req->cryptlen, AES_BLOCK_SIZE) / AES_BLOCK_SIZE;
-		cc_update_ctr((u8 *)req->iv, len);
-		break;
-
-	default:
-		break;
+	if (err != -EINPROGRESS) {
+		/* Not a BACKLOG notification */
+		cc_unmap_cipher_request(dev, req_ctx, ivsize, src, dst);
+		memcpy(req->iv, req_ctx->iv, ivsize);
+		kzfree(req_ctx->iv);
 	}
 
-	kzfree(req_ctx->iv);
-
 	skcipher_request_complete(req, err);
 }
 
@@ -741,6 +871,13 @@ static int cc_cipher_process(struct skcipher_request *req,
 	cc_req.user_cb = (void *)cc_cipher_complete;
 	cc_req.user_arg = (void *)req;
 
+	/* Setup CPP operation details */
+	if (ctx_p->key_type == CC_POLICY_PROTECTED_KEY) {
+		cc_req.cpp.is_cpp = true;
+		cc_req.cpp.alg = ctx_p->cpp.alg;
+		cc_req.cpp.slot = ctx_p->cpp.slot;
+	}
+
 	/* Setup request context */
 	req_ctx->gen_ctx.op_type = direction;
 
@@ -755,11 +892,16 @@ static int cc_cipher_process(struct skcipher_request *req,
 
 	/* STAT_PHASE_2: Create sequence */
 
-	/* Setup processing */
-	cc_setup_cipher_desc(tfm, req_ctx, ivsize, nbytes, desc, &seq_len);
+	/* Setup IV and XEX key used */
+	cc_setup_state_desc(tfm, req_ctx, ivsize, nbytes, desc, &seq_len);
+	/* Setup MLLI line, if needed */
+	cc_setup_mlli_desc(tfm, req_ctx, dst, src, nbytes, req, desc, &seq_len);
+	/* Setup key */
+	cc_setup_key_desc(tfm, req_ctx, nbytes, desc, &seq_len);
 	/* Data processing */
-	cc_setup_cipher_data(tfm, req_ctx, dst, src, nbytes, req, desc,
-			     &seq_len);
+	cc_setup_flow_desc(tfm, req_ctx, dst, src, nbytes, desc, &seq_len);
+	/* Read next IV */
+	cc_setup_readiv_desc(tfm, req_ctx, ivsize, desc, &seq_len);
 
 	/* STAT_PHASE_3: Lock HW and push sequence */
 
@@ -774,7 +916,6 @@ static int cc_cipher_process(struct skcipher_request *req,
 
 exit_process:
 	if (rc != -EINPROGRESS && rc != -EBUSY) {
-		kzfree(req_ctx->backup_info);
 		kzfree(req_ctx->iv);
 	}
 
@@ -792,31 +933,10 @@ static int cc_cipher_encrypt(struct skcipher_request *req)
 
 static int cc_cipher_decrypt(struct skcipher_request *req)
 {
-	struct crypto_skcipher *sk_tfm = crypto_skcipher_reqtfm(req);
-	struct crypto_tfm *tfm = crypto_skcipher_tfm(sk_tfm);
-	struct cc_cipher_ctx *ctx_p = crypto_tfm_ctx(tfm);
 	struct cipher_req_ctx *req_ctx = skcipher_request_ctx(req);
-	unsigned int ivsize = crypto_skcipher_ivsize(sk_tfm);
-	gfp_t flags = cc_gfp_flags(&req->base);
-	unsigned int len;
 
 	memset(req_ctx, 0, sizeof(*req_ctx));
 
-	if ((ctx_p->cipher_mode == DRV_CIPHER_CBC) &&
-	    (req->cryptlen >= ivsize)) {
-
-		/* Allocate and save the last IV sized bytes of the source,
-		 * which will be lost in case of in-place decryption.
-		 */
-		req_ctx->backup_info = kzalloc(ivsize, flags);
-		if (!req_ctx->backup_info)
-			return -ENOMEM;
-
-		len = req->cryptlen - ivsize;
-		scatterwalk_map_and_copy(req_ctx->backup_info, req->src, len,
-					 ivsize, 0);
-	}
-
 	return cc_cipher_process(req, DRV_CRYPTO_DIRECTION_DECRYPT);
 }
 
@@ -838,6 +958,7 @@ static const struct cc_alg_template skcipher_algs[] = {
 		.flow_mode = S_DIN_to_AES,
 		.min_hw_rev = CC_HW_REV_630,
 		.std_body = CC_STD_NIST,
+		.sec_func = true,
 	},
 	{
 		.name = "xts512(paes)",
@@ -856,6 +977,7 @@ static const struct cc_alg_template skcipher_algs[] = {
 		.data_unit = 512,
 		.min_hw_rev = CC_HW_REV_712,
 		.std_body = CC_STD_NIST,
+		.sec_func = true,
 	},
 	{
 		.name = "xts4096(paes)",
@@ -874,6 +996,7 @@ static const struct cc_alg_template skcipher_algs[] = {
 		.data_unit = 4096,
 		.min_hw_rev = CC_HW_REV_712,
 		.std_body = CC_STD_NIST,
+		.sec_func = true,
 	},
 	{
 		.name = "essiv(paes)",
@@ -891,6 +1014,7 @@ static const struct cc_alg_template skcipher_algs[] = {
 		.flow_mode = S_DIN_to_AES,
 		.min_hw_rev = CC_HW_REV_712,
 		.std_body = CC_STD_NIST,
+		.sec_func = true,
 	},
 	{
 		.name = "essiv512(paes)",
@@ -909,6 +1033,7 @@ static const struct cc_alg_template skcipher_algs[] = {
 		.data_unit = 512,
 		.min_hw_rev = CC_HW_REV_712,
 		.std_body = CC_STD_NIST,
+		.sec_func = true,
 	},
 	{
 		.name = "essiv4096(paes)",
@@ -927,6 +1052,7 @@ static const struct cc_alg_template skcipher_algs[] = {
 		.data_unit = 4096,
 		.min_hw_rev = CC_HW_REV_712,
 		.std_body = CC_STD_NIST,
+		.sec_func = true,
 	},
 	{
 		.name = "bitlocker(paes)",
@@ -944,6 +1070,7 @@ static const struct cc_alg_template skcipher_algs[] = {
 		.flow_mode = S_DIN_to_AES,
 		.min_hw_rev = CC_HW_REV_712,
 		.std_body = CC_STD_NIST,
+		.sec_func = true,
 	},
 	{
 		.name = "bitlocker512(paes)",
@@ -962,6 +1089,7 @@ static const struct cc_alg_template skcipher_algs[] = {
 		.data_unit = 512,
 		.min_hw_rev = CC_HW_REV_712,
 		.std_body = CC_STD_NIST,
+		.sec_func = true,
 	},
 	{
 		.name = "bitlocker4096(paes)",
@@ -980,6 +1108,7 @@ static const struct cc_alg_template skcipher_algs[] = {
 		.data_unit = 4096,
 		.min_hw_rev = CC_HW_REV_712,
 		.std_body = CC_STD_NIST,
+		.sec_func = true,
 	},
 	{
 		.name = "ecb(paes)",
@@ -997,6 +1126,7 @@ static const struct cc_alg_template skcipher_algs[] = {
 		.flow_mode = S_DIN_to_AES,
 		.min_hw_rev = CC_HW_REV_712,
 		.std_body = CC_STD_NIST,
+		.sec_func = true,
 	},
 	{
 		.name = "cbc(paes)",
@@ -1014,6 +1144,7 @@ static const struct cc_alg_template skcipher_algs[] = {
 		.flow_mode = S_DIN_to_AES,
 		.min_hw_rev = CC_HW_REV_712,
 		.std_body = CC_STD_NIST,
+		.sec_func = true,
 	},
 	{
 		.name = "ofb(paes)",
@@ -1031,6 +1162,7 @@ static const struct cc_alg_template skcipher_algs[] = {
 		.flow_mode = S_DIN_to_AES,
 		.min_hw_rev = CC_HW_REV_712,
 		.std_body = CC_STD_NIST,
+		.sec_func = true,
 	},
 	{
 		.name = "cts(cbc(paes))",
@@ -1048,6 +1180,7 @@ static const struct cc_alg_template skcipher_algs[] = {
 		.flow_mode = S_DIN_to_AES,
 		.min_hw_rev = CC_HW_REV_712,
 		.std_body = CC_STD_NIST,
+		.sec_func = true,
 	},
 	{
 		.name = "ctr(paes)",
@@ -1065,6 +1198,7 @@ static const struct cc_alg_template skcipher_algs[] = {
 		.flow_mode = S_DIN_to_AES,
 		.min_hw_rev = CC_HW_REV_712,
 		.std_body = CC_STD_NIST,
+		.sec_func = true,
 	},
 	{
 		.name = "xts(aes)",
@@ -1429,6 +1563,42 @@ static const struct cc_alg_template skcipher_algs[] = {
 		.min_hw_rev = CC_HW_REV_713,
 		.std_body = CC_STD_OSCCA,
 	},
+	{
+		.name = "cbc(psm4)",
+		.driver_name = "cbc-psm4-ccree",
+		.blocksize = SM4_BLOCK_SIZE,
+		.template_skcipher = {
+			.setkey = cc_cipher_sethkey,
+			.encrypt = cc_cipher_encrypt,
+			.decrypt = cc_cipher_decrypt,
+			.min_keysize = CC_HW_KEY_SIZE,
+			.max_keysize = CC_HW_KEY_SIZE,
+			.ivsize = SM4_BLOCK_SIZE,
+			},
+		.cipher_mode = DRV_CIPHER_CBC,
+		.flow_mode = S_DIN_to_SM4,
+		.min_hw_rev = CC_HW_REV_713,
+		.std_body = CC_STD_OSCCA,
+		.sec_func = true,
+	},
+	{
+		.name = "ctr(psm4)",
+		.driver_name = "ctr-psm4-ccree",
+		.blocksize = SM4_BLOCK_SIZE,
+		.template_skcipher = {
+			.setkey = cc_cipher_sethkey,
+			.encrypt = cc_cipher_encrypt,
+			.decrypt = cc_cipher_decrypt,
+			.min_keysize = CC_HW_KEY_SIZE,
+			.max_keysize = CC_HW_KEY_SIZE,
+			.ivsize = SM4_BLOCK_SIZE,
+			},
+		.cipher_mode = DRV_CIPHER_CTR,
+		.flow_mode = S_DIN_to_SM4,
+		.min_hw_rev = CC_HW_REV_713,
+		.std_body = CC_STD_OSCCA,
+		.sec_func = true,
+	},
 };
 
 static struct cc_crypto_alg *cc_create_alg(const struct cc_alg_template *tmpl,
@@ -1504,7 +1674,8 @@ int cc_cipher_alloc(struct cc_drvdata *drvdata)
 		ARRAY_SIZE(skcipher_algs));
 	for (alg = 0; alg < ARRAY_SIZE(skcipher_algs); alg++) {
 		if ((skcipher_algs[alg].min_hw_rev > drvdata->hw_rev) ||
-		    !(drvdata->std_bodies & skcipher_algs[alg].std_body))
+		    !(drvdata->std_bodies & skcipher_algs[alg].std_body) ||
+		    (drvdata->sec_disabled && skcipher_algs[alg].sec_func))
 			continue;
 
 		dev_dbg(dev, "creating %s\n", skcipher_algs[alg].driver_name);
diff --git a/drivers/crypto/ccree/cc_cipher.h b/drivers/crypto/ccree/cc_cipher.h
index 4dbc0a1e6d5c..da3a38707fae 100644
--- a/drivers/crypto/ccree/cc_cipher.h
+++ b/drivers/crypto/ccree/cc_cipher.h
@@ -1,5 +1,5 @@
 /* SPDX-License-Identifier: GPL-2.0 */
-/* Copyright (C) 2012-2018 ARM Limited or its affiliates. */
+/* Copyright (C) 2012-2019 ARM Limited (or its affiliates). */
 
 /* \file cc_cipher.h
  * ARM CryptoCell Cipher Crypto API
@@ -20,7 +20,6 @@ struct cipher_req_ctx {
 	u32 in_mlli_nents;
 	u32 out_nents;
 	u32 out_mlli_nents;
-	u8 *backup_info; /*store iv for generated IV flow*/
 	u8 *iv;
 	struct mlli_params mlli_params;
 };
diff --git a/drivers/crypto/ccree/cc_crypto_ctx.h b/drivers/crypto/ccree/cc_crypto_ctx.h
index c8dac273c563..ccf960a0d989 100644
--- a/drivers/crypto/ccree/cc_crypto_ctx.h
+++ b/drivers/crypto/ccree/cc_crypto_ctx.h
@@ -1,5 +1,5 @@
 /* SPDX-License-Identifier: GPL-2.0 */
-/* Copyright (C) 2012-2018 ARM Limited or its affiliates. */
+/* Copyright (C) 2012-2019 ARM Limited (or its affiliates). */
 
 #ifndef _CC_CRYPTO_CTX_H_
 #define _CC_CRYPTO_CTX_H_
@@ -55,6 +55,14 @@
 
 #define CC_DRV_ALG_MAX_BLOCK_SIZE CC_HASH_BLOCK_SIZE_MAX
 
+#define CC_CPP_NUM_SLOTS	8
+#define CC_CPP_NUM_ALGS		2
+
+enum cc_cpp_alg {
+	CC_CPP_SM4 = 1,
+	CC_CPP_AES = 0
+};
+
 enum drv_engine_type {
 	DRV_ENGINE_NULL = 0,
 	DRV_ENGINE_AES = 1,
diff --git a/drivers/crypto/ccree/cc_debugfs.c b/drivers/crypto/ccree/cc_debugfs.c
index 5fa05a7bcf36..566999738698 100644
--- a/drivers/crypto/ccree/cc_debugfs.c
+++ b/drivers/crypto/ccree/cc_debugfs.c
@@ -1,5 +1,5 @@
 // SPDX-License-Identifier: GPL-2.0
-/* Copyright (C) 2012-2018 ARM Limited or its affiliates. */
+/* Copyright (C) 2012-2019 ARM Limited or its affiliates. */
 
 #include <linux/kernel.h>
 #include <linux/debugfs.h>
@@ -25,9 +25,24 @@ struct cc_debugfs_ctx {
  */
 static struct dentry *cc_debugfs_dir;
 
-static struct debugfs_reg32 debug_regs[] = {
+static struct debugfs_reg32 ver_sig_regs[] = {
 	{ .name = "SIGNATURE" }, /* Must be 0th */
 	{ .name = "VERSION" }, /* Must be 1st */
+};
+
+static struct debugfs_reg32 pid_cid_regs[] = {
+	CC_DEBUG_REG(PERIPHERAL_ID_0),
+	CC_DEBUG_REG(PERIPHERAL_ID_1),
+	CC_DEBUG_REG(PERIPHERAL_ID_2),
+	CC_DEBUG_REG(PERIPHERAL_ID_3),
+	CC_DEBUG_REG(PERIPHERAL_ID_4),
+	CC_DEBUG_REG(COMPONENT_ID_0),
+	CC_DEBUG_REG(COMPONENT_ID_1),
+	CC_DEBUG_REG(COMPONENT_ID_2),
+	CC_DEBUG_REG(COMPONENT_ID_3),
+};
+
+static struct debugfs_reg32 debug_regs[] = {
 	CC_DEBUG_REG(HOST_IRR),
 	CC_DEBUG_REG(HOST_POWER_DOWN_EN),
 	CC_DEBUG_REG(AXIM_MON_ERR),
@@ -53,10 +68,7 @@ int cc_debugfs_init(struct cc_drvdata *drvdata)
 {
 	struct device *dev = drvdata_to_dev(drvdata);
 	struct cc_debugfs_ctx *ctx;
-	struct debugfs_regset32 *regset;
-
-	debug_regs[0].offset = drvdata->sig_offset;
-	debug_regs[1].offset = drvdata->ver_offset;
+	struct debugfs_regset32 *regset, *verset;
 
 	ctx = devm_kzalloc(dev, sizeof(*ctx), GFP_KERNEL);
 	if (!ctx)
@@ -75,8 +87,26 @@ int cc_debugfs_init(struct cc_drvdata *drvdata)
 	debugfs_create_regset32("regs", 0400, ctx->dir, regset);
 	debugfs_create_bool("coherent", 0400, ctx->dir, &drvdata->coherent);
 
-	drvdata->debugfs = ctx;
+	verset = devm_kzalloc(dev, sizeof(*verset), GFP_KERNEL);
+	/* Failing here is not important enough to fail the module load */
+	if (!verset)
+		goto out;
+
+	if (drvdata->hw_rev <= CC_HW_REV_712) {
+		ver_sig_regs[0].offset = drvdata->sig_offset;
+		ver_sig_regs[1].offset = drvdata->ver_offset;
+		verset->regs = ver_sig_regs;
+		verset->nregs = ARRAY_SIZE(ver_sig_regs);
+	} else {
+		verset->regs = pid_cid_regs;
+		verset->nregs = ARRAY_SIZE(pid_cid_regs);
+	}
+	verset->base = drvdata->cc_base;
 
+	debugfs_create_regset32("version", 0400, ctx->dir, verset);
+
+out:
+	drvdata->debugfs = ctx;
 	return 0;
 }
 
diff --git a/drivers/crypto/ccree/cc_debugfs.h b/drivers/crypto/ccree/cc_debugfs.h
index 01cbd9a95659..664ff402e0e9 100644
--- a/drivers/crypto/ccree/cc_debugfs.h
+++ b/drivers/crypto/ccree/cc_debugfs.h
@@ -1,5 +1,5 @@
 /* SPDX-License-Identifier: GPL-2.0 */
-/* Copyright (C) 2012-2018 ARM Limited or its affiliates. */
+/* Copyright (C) 2012-2019 ARM Limited (or its affiliates). */
 
 #ifndef __CC_DEBUGFS_H__
 #define __CC_DEBUGFS_H__
diff --git a/drivers/crypto/ccree/cc_driver.c b/drivers/crypto/ccree/cc_driver.c
index 3bcc6c76e090..86ac7b443355 100644
--- a/drivers/crypto/ccree/cc_driver.c
+++ b/drivers/crypto/ccree/cc_driver.c
@@ -1,5 +1,5 @@
 // SPDX-License-Identifier: GPL-2.0
-/* Copyright (C) 2012-2018 ARM Limited or its affiliates. */
+/* Copyright (C) 2012-2019 ARM Limited or its affiliates. */
 
 #include <linux/kernel.h>
 #include <linux/module.h>
@@ -30,27 +30,47 @@
 bool cc_dump_desc;
 module_param_named(dump_desc, cc_dump_desc, bool, 0600);
 MODULE_PARM_DESC(cc_dump_desc, "Dump descriptors to kernel log as debugging aid");
-
 bool cc_dump_bytes;
 module_param_named(dump_bytes, cc_dump_bytes, bool, 0600);
 MODULE_PARM_DESC(cc_dump_bytes, "Dump buffers to kernel log as debugging aid");
 
+static bool cc_sec_disable;
+module_param_named(sec_disable, cc_sec_disable, bool, 0600);
+MODULE_PARM_DESC(cc_sec_disable, "Disable security functions");
+
 struct cc_hw_data {
 	char *name;
 	enum cc_hw_rev rev;
 	u32 sig;
+	u32 cidr_0123;
+	u32 pidr_0124;
 	int std_bodies;
 };
 
+#define CC_NUM_IDRS 4
+
+/* Note: PIDR3 holds CMOD/Rev so ignored for HW identification purposes */
+static const u32 pidr_0124_offsets[CC_NUM_IDRS] = {
+	CC_REG(PERIPHERAL_ID_0), CC_REG(PERIPHERAL_ID_1),
+	CC_REG(PERIPHERAL_ID_2), CC_REG(PERIPHERAL_ID_4)
+};
+
+static const u32 cidr_0123_offsets[CC_NUM_IDRS] = {
+	CC_REG(COMPONENT_ID_0), CC_REG(COMPONENT_ID_1),
+	CC_REG(COMPONENT_ID_2), CC_REG(COMPONENT_ID_3)
+};
+
 /* Hardware revisions defs. */
 
 /* The 703 is a OSCCA only variant of the 713 */
 static const struct cc_hw_data cc703_hw = {
-	.name = "703", .rev = CC_HW_REV_713, .std_bodies = CC_STD_OSCCA
+	.name = "703", .rev = CC_HW_REV_713, .cidr_0123 = 0xB105F00DU,
+	.pidr_0124 = 0x040BB0D0U, .std_bodies = CC_STD_OSCCA
 };
 
 static const struct cc_hw_data cc713_hw = {
-	.name = "713", .rev = CC_HW_REV_713, .std_bodies = CC_STD_ALL
+	.name = "713", .rev = CC_HW_REV_713, .cidr_0123 = 0xB105F00DU,
+	.pidr_0124 = 0x040BB0D0U, .std_bodies = CC_STD_ALL
 };
 
 static const struct cc_hw_data cc712_hw = {
@@ -78,6 +98,20 @@ static const struct of_device_id arm_ccree_dev_of_match[] = {
 };
 MODULE_DEVICE_TABLE(of, arm_ccree_dev_of_match);
 
+static u32 cc_read_idr(struct cc_drvdata *drvdata, const u32 *idr_offsets)
+{
+	int i;
+	union {
+		u8 regs[CC_NUM_IDRS];
+		__le32 val;
+	} idr;
+
+	for (i = 0; i < CC_NUM_IDRS; ++i)
+		idr.regs[i] = cc_ioread(drvdata, idr_offsets[i]);
+
+	return le32_to_cpu(idr.val);
+}
+
 void __dump_byte_array(const char *name, const u8 *buf, size_t len)
 {
 	char prefix[64];
@@ -114,12 +148,12 @@ static irqreturn_t cc_isr(int irq, void *dev_id)
 
 	drvdata->irq = irr;
 	/* Completion interrupt - most probable */
-	if (irr & CC_COMP_IRQ_MASK) {
-		/* Mask AXI completion interrupt - will be unmasked in
-		 * Deferred service handler
+	if (irr & drvdata->comp_mask) {
+		/* Mask all completion interrupts - will be unmasked in
+		 * deferred service handler
 		 */
-		cc_iowrite(drvdata, CC_REG(HOST_IMR), imr | CC_COMP_IRQ_MASK);
-		irr &= ~CC_COMP_IRQ_MASK;
+		cc_iowrite(drvdata, CC_REG(HOST_IMR), imr | drvdata->comp_mask);
+		irr &= ~drvdata->comp_mask;
 		complete_request(drvdata);
 	}
 #ifdef CONFIG_CRYPTO_FIPS
@@ -159,11 +193,14 @@ int init_cc_regs(struct cc_drvdata *drvdata, bool is_probe)
 	unsigned int val, cache_params;
 	struct device *dev = drvdata_to_dev(drvdata);
 
-	/* Unmask all AXI interrupt sources AXI_CFG1 register */
-	val = cc_ioread(drvdata, CC_REG(AXIM_CFG));
-	cc_iowrite(drvdata, CC_REG(AXIM_CFG), val & ~CC_AXI_IRQ_MASK);
-	dev_dbg(dev, "AXIM_CFG=0x%08X\n",
-		cc_ioread(drvdata, CC_REG(AXIM_CFG)));
+	/* Unmask all AXI interrupt sources AXI_CFG1 register   */
+	/* AXI interrupt config are obsoleted startign at cc7x3 */
+	if (drvdata->hw_rev <= CC_HW_REV_712) {
+		val = cc_ioread(drvdata, CC_REG(AXIM_CFG));
+		cc_iowrite(drvdata, CC_REG(AXIM_CFG), val & ~CC_AXI_IRQ_MASK);
+		dev_dbg(dev, "AXIM_CFG=0x%08X\n",
+			cc_ioread(drvdata, CC_REG(AXIM_CFG)));
+	}
 
 	/* Clear all pending interrupts */
 	val = cc_ioread(drvdata, CC_REG(HOST_IRR));
@@ -171,7 +208,7 @@ int init_cc_regs(struct cc_drvdata *drvdata, bool is_probe)
 	cc_iowrite(drvdata, CC_REG(HOST_ICR), val);
 
 	/* Unmask relevant interrupt cause */
-	val = CC_COMP_IRQ_MASK | CC_AXI_ERR_IRQ_MASK;
+	val = drvdata->comp_mask | CC_AXI_ERR_IRQ_MASK;
 
 	if (drvdata->hw_rev >= CC_HW_REV_712)
 		val |= CC_GPR0_IRQ_MASK;
@@ -201,7 +238,7 @@ static int init_cc_resources(struct platform_device *plat_dev)
 	struct cc_drvdata *new_drvdata;
 	struct device *dev = &plat_dev->dev;
 	struct device_node *np = dev->of_node;
-	u32 signature_val;
+	u32 val, hw_rev_pidr, sig_cidr;
 	u64 dma_mask;
 	const struct cc_hw_data *hw_rev;
 	const struct of_device_id *dev_id;
@@ -231,6 +268,8 @@ static int init_cc_resources(struct platform_device *plat_dev)
 		new_drvdata->ver_offset = CC_REG(HOST_VERSION_630);
 	}
 
+	new_drvdata->comp_mask = CC_COMP_IRQ_MASK;
+
 	platform_set_drvdata(plat_dev, new_drvdata);
 	new_drvdata->plat_dev = plat_dev;
 
@@ -311,22 +350,57 @@ static int init_cc_resources(struct platform_device *plat_dev)
 		return rc;
 	}
 
+	new_drvdata->sec_disabled = cc_sec_disable;
+
 	if (hw_rev->rev <= CC_HW_REV_712) {
 		/* Verify correct mapping */
-		signature_val = cc_ioread(new_drvdata, new_drvdata->sig_offset);
-		if (signature_val != hw_rev->sig) {
+		val = cc_ioread(new_drvdata, new_drvdata->sig_offset);
+		if (val != hw_rev->sig) {
 			dev_err(dev, "Invalid CC signature: SIGNATURE=0x%08X != expected=0x%08X\n",
-				signature_val, hw_rev->sig);
+				val, hw_rev->sig);
+			rc = -EINVAL;
+			goto post_clk_err;
+		}
+		sig_cidr = val;
+		hw_rev_pidr = cc_ioread(new_drvdata, new_drvdata->ver_offset);
+	} else {
+		/* Verify correct mapping */
+		val = cc_read_idr(new_drvdata, pidr_0124_offsets);
+		if (val != hw_rev->pidr_0124) {
+			dev_err(dev, "Invalid CC PIDR: PIDR0124=0x%08X != expected=0x%08X\n",
+				val,  hw_rev->pidr_0124);
+			rc = -EINVAL;
+			goto post_clk_err;
+		}
+		hw_rev_pidr = val;
+
+		val = cc_read_idr(new_drvdata, cidr_0123_offsets);
+		if (val != hw_rev->cidr_0123) {
+			dev_err(dev, "Invalid CC CIDR: CIDR0123=0x%08X != expected=0x%08X\n",
+			val,  hw_rev->cidr_0123);
 			rc = -EINVAL;
 			goto post_clk_err;
 		}
-		dev_dbg(dev, "CC SIGNATURE=0x%08X\n", signature_val);
+		sig_cidr = val;
+
+		/* Check security disable state */
+		val = cc_ioread(new_drvdata, CC_REG(SECURITY_DISABLED));
+		val &= CC_SECURITY_DISABLED_MASK;
+		new_drvdata->sec_disabled |= !!val;
+
+		if (!new_drvdata->sec_disabled) {
+			new_drvdata->comp_mask |= CC_CPP_SM4_ABORT_MASK;
+			if (new_drvdata->std_bodies & CC_STD_NIST)
+				new_drvdata->comp_mask |= CC_CPP_AES_ABORT_MASK;
+		}
 	}
 
+	if (new_drvdata->sec_disabled)
+		dev_info(dev, "Security Disabled mode is in effect. Security functions disabled.\n");
+
 	/* Display HW versions */
-	dev_info(dev, "ARM CryptoCell %s Driver: HW version 0x%08X, Driver version %s\n",
-		 hw_rev->name, cc_ioread(new_drvdata, new_drvdata->ver_offset),
-		 DRV_MODULE_VERSION);
+	dev_info(dev, "ARM CryptoCell %s Driver: HW version 0x%08X/0x%8X, Driver version %s\n",
+		 hw_rev->name, hw_rev_pidr, sig_cidr, DRV_MODULE_VERSION);
 
 	rc = init_cc_regs(new_drvdata, true);
 	if (rc) {
diff --git a/drivers/crypto/ccree/cc_driver.h b/drivers/crypto/ccree/cc_driver.h
index 33dbf3e6d15d..b76181335c08 100644
--- a/drivers/crypto/ccree/cc_driver.h
+++ b/drivers/crypto/ccree/cc_driver.h
@@ -1,5 +1,5 @@
 /* SPDX-License-Identifier: GPL-2.0 */
-/* Copyright (C) 2012-2018 ARM Limited or its affiliates. */
+/* Copyright (C) 2012-2019 ARM Limited (or its affiliates). */
 
 /* \file cc_driver.h
  * ARM CryptoCell Linux Crypto Driver
@@ -65,10 +65,32 @@ enum cc_std_body {
 
 #define CC_COMP_IRQ_MASK BIT(CC_HOST_IRR_AXIM_COMP_INT_BIT_SHIFT)
 
+#define CC_SECURITY_DISABLED_MASK BIT(CC_SECURITY_DISABLED_VALUE_BIT_SHIFT)
+
 #define AXIM_MON_COMP_VALUE GENMASK(CC_AXIM_MON_COMP_VALUE_BIT_SIZE + \
 				    CC_AXIM_MON_COMP_VALUE_BIT_SHIFT, \
 				    CC_AXIM_MON_COMP_VALUE_BIT_SHIFT)
 
+#define CC_CPP_AES_ABORT_MASK ( \
+	BIT(CC_HOST_IMR_REE_OP_ABORTED_AES_0_MASK_BIT_SHIFT) | \
+	BIT(CC_HOST_IMR_REE_OP_ABORTED_AES_1_MASK_BIT_SHIFT) | \
+	BIT(CC_HOST_IMR_REE_OP_ABORTED_AES_2_MASK_BIT_SHIFT) | \
+	BIT(CC_HOST_IMR_REE_OP_ABORTED_AES_3_MASK_BIT_SHIFT) | \
+	BIT(CC_HOST_IMR_REE_OP_ABORTED_AES_4_MASK_BIT_SHIFT) | \
+	BIT(CC_HOST_IMR_REE_OP_ABORTED_AES_5_MASK_BIT_SHIFT) | \
+	BIT(CC_HOST_IMR_REE_OP_ABORTED_AES_6_MASK_BIT_SHIFT) | \
+	BIT(CC_HOST_IMR_REE_OP_ABORTED_AES_7_MASK_BIT_SHIFT))
+
+#define CC_CPP_SM4_ABORT_MASK ( \
+	BIT(CC_HOST_IMR_REE_OP_ABORTED_SM_0_MASK_BIT_SHIFT) | \
+	BIT(CC_HOST_IMR_REE_OP_ABORTED_SM_1_MASK_BIT_SHIFT) | \
+	BIT(CC_HOST_IMR_REE_OP_ABORTED_SM_2_MASK_BIT_SHIFT) | \
+	BIT(CC_HOST_IMR_REE_OP_ABORTED_SM_3_MASK_BIT_SHIFT) | \
+	BIT(CC_HOST_IMR_REE_OP_ABORTED_SM_4_MASK_BIT_SHIFT) | \
+	BIT(CC_HOST_IMR_REE_OP_ABORTED_SM_5_MASK_BIT_SHIFT) | \
+	BIT(CC_HOST_IMR_REE_OP_ABORTED_SM_6_MASK_BIT_SHIFT) | \
+	BIT(CC_HOST_IMR_REE_OP_ABORTED_SM_7_MASK_BIT_SHIFT))
+
 /* Register name mangling macro */
 #define CC_REG(reg_name) CC_ ## reg_name ## _REG_OFFSET
 
@@ -81,7 +103,6 @@ enum cc_std_body {
 
 #define MAX_REQUEST_QUEUE_SIZE 4096
 #define MAX_MLLI_BUFF_SIZE 2080
-#define MAX_ICV_NENTS_SUPPORTED 2
 
 /* Definitions for HW descriptors DIN/DOUT fields */
 #define NS_BIT 1
@@ -90,6 +111,12 @@ enum cc_std_body {
  * field in the HW descriptor. The DMA engine +8 that value.
  */
 
+struct cc_cpp_req {
+	bool is_cpp;
+	enum cc_cpp_alg alg;
+	u8 slot;
+};
+
 #define CC_MAX_IVGEN_DMA_ADDRESSES	3
 struct cc_crypto_req {
 	void (*user_cb)(struct device *dev, void *req, int err);
@@ -104,6 +131,7 @@ struct cc_crypto_req {
 	/* The generated IV size required, 8/16 B allowed. */
 	unsigned int ivgen_size;
 	struct completion seq_compl; /* request completion */
+	struct cc_cpp_req cpp;
 };
 
 /**
@@ -136,6 +164,8 @@ struct cc_drvdata {
 	u32 sig_offset;
 	u32 ver_offset;
 	int std_bodies;
+	bool sec_disabled;
+	u32 comp_mask;
 };
 
 struct cc_crypto_alg {
@@ -162,12 +192,14 @@ struct cc_alg_template {
 	int auth_mode;
 	u32 min_hw_rev;
 	enum cc_std_body std_body;
+	bool sec_func;
 	unsigned int data_unit;
 	struct cc_drvdata *drvdata;
 };
 
 struct async_gen_req_ctx {
 	dma_addr_t iv_dma_addr;
+	u8 *iv;
 	enum drv_crypto_direction op_type;
 };
 
diff --git a/drivers/crypto/ccree/cc_fips.c b/drivers/crypto/ccree/cc_fips.c
index b4d0a6d983e0..5ad3ffb7acaa 100644
--- a/drivers/crypto/ccree/cc_fips.c
+++ b/drivers/crypto/ccree/cc_fips.c
@@ -1,5 +1,5 @@
 // SPDX-License-Identifier: GPL-2.0
-/* Copyright (C) 2012-2018 ARM Limited or its affiliates. */
+/* Copyright (C) 2012-2019 ARM Limited (or its affiliates). */
 
 #include <linux/kernel.h>
 #include <linux/fips.h>
@@ -49,8 +49,6 @@ void cc_fips_fini(struct cc_drvdata *drvdata)
 
 	/* Kill tasklet */
 	tasklet_kill(&fips_h->tasklet);
-
-	kfree(fips_h);
 	drvdata->fips_handle = NULL;
 }
 
@@ -72,20 +70,28 @@ static inline void tee_fips_error(struct device *dev)
 		dev_err(dev, "TEE reported error!\n");
 }
 
+/*
+ * This function check if cryptocell tee fips error occurred
+ * and in such case triggers system error
+ */
+void cc_tee_handle_fips_error(struct cc_drvdata *p_drvdata)
+{
+	struct device *dev = drvdata_to_dev(p_drvdata);
+
+	if (!cc_get_tee_fips_status(p_drvdata))
+		tee_fips_error(dev);
+}
+
 /* Deferred service handler, run as interrupt-fired tasklet */
 static void fips_dsr(unsigned long devarg)
 {
 	struct cc_drvdata *drvdata = (struct cc_drvdata *)devarg;
-	struct device *dev = drvdata_to_dev(drvdata);
-	u32 irq, state, val;
+	u32 irq, val;
 
 	irq = (drvdata->irq & (CC_GPR0_IRQ_MASK));
 
 	if (irq) {
-		state = cc_ioread(drvdata, CC_REG(GPR_HOST));
-
-		if (state != (CC_FIPS_SYNC_TEE_STATUS | CC_FIPS_SYNC_MODULE_OK))
-			tee_fips_error(dev);
+		cc_tee_handle_fips_error(drvdata);
 	}
 
 	/* after verifing that there is nothing to do,
@@ -104,7 +110,7 @@ int cc_fips_init(struct cc_drvdata *p_drvdata)
 	if (p_drvdata->hw_rev < CC_HW_REV_712)
 		return 0;
 
-	fips_h = kzalloc(sizeof(*fips_h), GFP_KERNEL);
+	fips_h = devm_kzalloc(dev, sizeof(*fips_h), GFP_KERNEL);
 	if (!fips_h)
 		return -ENOMEM;
 
@@ -113,8 +119,7 @@ int cc_fips_init(struct cc_drvdata *p_drvdata)
 	dev_dbg(dev, "Initializing fips tasklet\n");
 	tasklet_init(&fips_h->tasklet, fips_dsr, (unsigned long)p_drvdata);
 
-	if (!cc_get_tee_fips_status(p_drvdata))
-		tee_fips_error(dev);
+	cc_tee_handle_fips_error(p_drvdata);
 
 	return 0;
 }
diff --git a/drivers/crypto/ccree/cc_fips.h b/drivers/crypto/ccree/cc_fips.h
index 645e096a7a82..fc33eeb4d566 100644
--- a/drivers/crypto/ccree/cc_fips.h
+++ b/drivers/crypto/ccree/cc_fips.h
@@ -1,5 +1,5 @@
 /* SPDX-License-Identifier: GPL-2.0 */
-/* Copyright (C) 2012-2018 ARM Limited or its affiliates. */
+/* Copyright (C) 2012-2019 ARM Limited (or its affiliates). */
 
 #ifndef __CC_FIPS_H__
 #define __CC_FIPS_H__
@@ -18,6 +18,7 @@ int cc_fips_init(struct cc_drvdata *p_drvdata);
 void cc_fips_fini(struct cc_drvdata *drvdata);
 void fips_handler(struct cc_drvdata *drvdata);
 void cc_set_ree_fips_status(struct cc_drvdata *drvdata, bool ok);
+void cc_tee_handle_fips_error(struct cc_drvdata *p_drvdata);
 
 #else  /* CONFIG_CRYPTO_FIPS */
 
@@ -30,6 +31,7 @@ static inline void cc_fips_fini(struct cc_drvdata *drvdata) {}
 static inline void cc_set_ree_fips_status(struct cc_drvdata *drvdata,
 					  bool ok) {}
 static inline void fips_handler(struct cc_drvdata *drvdata) {}
+static inline void cc_tee_handle_fips_error(struct cc_drvdata *p_drvdata) {}
 
 #endif /* CONFIG_CRYPTO_FIPS */
 
diff --git a/drivers/crypto/ccree/cc_hash.c b/drivers/crypto/ccree/cc_hash.c
index 2c4ddc8fb76b..a6abe4e3bb0e 100644
--- a/drivers/crypto/ccree/cc_hash.c
+++ b/drivers/crypto/ccree/cc_hash.c
@@ -1,5 +1,5 @@
 // SPDX-License-Identifier: GPL-2.0
-/* Copyright (C) 2012-2018 ARM Limited or its affiliates. */
+/* Copyright (C) 2012-2019 ARM Limited (or its affiliates). */
 
 #include <linux/kernel.h>
 #include <linux/module.h>
@@ -69,6 +69,7 @@ struct cc_hash_alg {
 struct hash_key_req_ctx {
 	u32 keylen;
 	dma_addr_t key_dma_addr;
+	u8 *key;
 };
 
 /* hash per-session context */
@@ -280,9 +281,13 @@ static void cc_update_complete(struct device *dev, void *cc_req, int err)
 
 	dev_dbg(dev, "req=%pK\n", req);
 
-	cc_unmap_hash_request(dev, state, req->src, false);
-	cc_unmap_req(dev, state, ctx);
-	req->base.complete(&req->base, err);
+	if (err != -EINPROGRESS) {
+		/* Not a BACKLOG notification */
+		cc_unmap_hash_request(dev, state, req->src, false);
+		cc_unmap_req(dev, state, ctx);
+	}
+
+	ahash_request_complete(req, err);
 }
 
 static void cc_digest_complete(struct device *dev, void *cc_req, int err)
@@ -295,10 +300,14 @@ static void cc_digest_complete(struct device *dev, void *cc_req, int err)
 
 	dev_dbg(dev, "req=%pK\n", req);
 
-	cc_unmap_hash_request(dev, state, req->src, false);
-	cc_unmap_result(dev, state, digestsize, req->result);
-	cc_unmap_req(dev, state, ctx);
-	req->base.complete(&req->base, err);
+	if (err != -EINPROGRESS) {
+		/* Not a BACKLOG notification */
+		cc_unmap_hash_request(dev, state, req->src, false);
+		cc_unmap_result(dev, state, digestsize, req->result);
+		cc_unmap_req(dev, state, ctx);
+	}
+
+	ahash_request_complete(req, err);
 }
 
 static void cc_hash_complete(struct device *dev, void *cc_req, int err)
@@ -311,10 +320,14 @@ static void cc_hash_complete(struct device *dev, void *cc_req, int err)
 
 	dev_dbg(dev, "req=%pK\n", req);
 
-	cc_unmap_hash_request(dev, state, req->src, false);
-	cc_unmap_result(dev, state, digestsize, req->result);
-	cc_unmap_req(dev, state, ctx);
-	req->base.complete(&req->base, err);
+	if (err != -EINPROGRESS) {
+		/* Not a BACKLOG notification */
+		cc_unmap_hash_request(dev, state, req->src, false);
+		cc_unmap_result(dev, state, digestsize, req->result);
+		cc_unmap_req(dev, state, ctx);
+	}
+
+	ahash_request_complete(req, err);
 }
 
 static int cc_fin_result(struct cc_hw_desc *desc, struct ahash_request *req,
@@ -730,13 +743,20 @@ static int cc_hash_setkey(struct crypto_ahash *ahash, const u8 *key,
 	ctx->key_params.keylen = keylen;
 	ctx->key_params.key_dma_addr = 0;
 	ctx->is_hmac = true;
+	ctx->key_params.key = NULL;
 
 	if (keylen) {
+		ctx->key_params.key = kmemdup(key, keylen, GFP_KERNEL);
+		if (!ctx->key_params.key)
+			return -ENOMEM;
+
 		ctx->key_params.key_dma_addr =
-			dma_map_single(dev, (void *)key, keylen, DMA_TO_DEVICE);
+			dma_map_single(dev, (void *)ctx->key_params.key, keylen,
+				       DMA_TO_DEVICE);
 		if (dma_mapping_error(dev, ctx->key_params.key_dma_addr)) {
 			dev_err(dev, "Mapping key va=0x%p len=%u for DMA failed\n",
-				key, keylen);
+				ctx->key_params.key, keylen);
+			kzfree(ctx->key_params.key);
 			return -ENOMEM;
 		}
 		dev_dbg(dev, "mapping key-buffer: key_dma_addr=%pad keylen=%u\n",
@@ -887,6 +907,9 @@ out:
 		dev_dbg(dev, "Unmapped key-buffer: key_dma_addr=%pad keylen=%u\n",
 			&ctx->key_params.key_dma_addr, ctx->key_params.keylen);
 	}
+
+	kzfree(ctx->key_params.key);
+
 	return rc;
 }
 
@@ -913,11 +936,16 @@ static int cc_xcbc_setkey(struct crypto_ahash *ahash,
 
 	ctx->key_params.keylen = keylen;
 
+	ctx->key_params.key = kmemdup(key, keylen, GFP_KERNEL);
+	if (!ctx->key_params.key)
+		return -ENOMEM;
+
 	ctx->key_params.key_dma_addr =
-		dma_map_single(dev, (void *)key, keylen, DMA_TO_DEVICE);
+		dma_map_single(dev, ctx->key_params.key, keylen, DMA_TO_DEVICE);
 	if (dma_mapping_error(dev, ctx->key_params.key_dma_addr)) {
 		dev_err(dev, "Mapping key va=0x%p len=%u for DMA failed\n",
 			key, keylen);
+		kzfree(ctx->key_params.key);
 		return -ENOMEM;
 	}
 	dev_dbg(dev, "mapping key-buffer: key_dma_addr=%pad keylen=%u\n",
@@ -969,6 +997,8 @@ static int cc_xcbc_setkey(struct crypto_ahash *ahash,
 	dev_dbg(dev, "Unmapped key-buffer: key_dma_addr=%pad keylen=%u\n",
 		&ctx->key_params.key_dma_addr, ctx->key_params.keylen);
 
+	kzfree(ctx->key_params.key);
+
 	return rc;
 }
 
@@ -1621,7 +1651,7 @@ static struct cc_hash_template driver_hash[] = {
 			.setkey = cc_hash_setkey,
 			.halg = {
 				.digestsize = SHA224_DIGEST_SIZE,
-				.statesize = CC_STATE_SIZE(SHA224_DIGEST_SIZE),
+				.statesize = CC_STATE_SIZE(SHA256_DIGEST_SIZE),
 			},
 		},
 		.hash_mode = DRV_HASH_SHA224,
@@ -1648,7 +1678,7 @@ static struct cc_hash_template driver_hash[] = {
 			.setkey = cc_hash_setkey,
 			.halg = {
 				.digestsize = SHA384_DIGEST_SIZE,
-				.statesize = CC_STATE_SIZE(SHA384_DIGEST_SIZE),
+				.statesize = CC_STATE_SIZE(SHA512_DIGEST_SIZE),
 			},
 		},
 		.hash_mode = DRV_HASH_SHA384,
diff --git a/drivers/crypto/ccree/cc_hash.h b/drivers/crypto/ccree/cc_hash.h
index 2e5bf8b0bbb6..0d6dc61484d7 100644
--- a/drivers/crypto/ccree/cc_hash.h
+++ b/drivers/crypto/ccree/cc_hash.h
@@ -1,5 +1,5 @@
 /* SPDX-License-Identifier: GPL-2.0 */
-/* Copyright (C) 2012-2018 ARM Limited or its affiliates. */
+/* Copyright (C) 2012-2019 ARM Limited (or its affiliates). */
 
 /* \file cc_hash.h
  * ARM CryptoCell Hash Crypto API
diff --git a/drivers/crypto/ccree/cc_host_regs.h b/drivers/crypto/ccree/cc_host_regs.h
index 616b2e1c41ba..d0764147573f 100644
--- a/drivers/crypto/ccree/cc_host_regs.h
+++ b/drivers/crypto/ccree/cc_host_regs.h
@@ -1,5 +1,5 @@
 /* SPDX-License-Identifier: GPL-2.0 */
-/* Copyright (C) 2012-2018 ARM Limited or its affiliates. */
+/* Copyright (C) 2012-2019 ARM Limited or its affiliates. */
 
 #ifndef __CC_HOST_H__
 #define __CC_HOST_H__
@@ -7,33 +7,102 @@
 // --------------------------------------
 // BLOCK: HOST_P
 // --------------------------------------
+
+
+/* IRR */
 #define CC_HOST_IRR_REG_OFFSET	0xA00UL
+#define CC_HOST_IRR_REE_OP_ABORTED_AES_0_INT_BIT_SHIFT	0x1UL
+#define CC_HOST_IRR_REE_OP_ABORTED_AES_0_INT_BIT_SIZE	0x1UL
 #define CC_HOST_IRR_DSCRPTR_COMPLETION_LOW_INT_BIT_SHIFT	0x2UL
 #define CC_HOST_IRR_DSCRPTR_COMPLETION_LOW_INT_BIT_SIZE	0x1UL
+#define CC_HOST_IRR_REE_OP_ABORTED_AES_1_INT_BIT_SHIFT	0x3UL
+#define CC_HOST_IRR_REE_OP_ABORTED_AES_1_INT_BIT_SIZE	0x1UL
+#define CC_HOST_IRR_REE_OP_ABORTED_AES_2_INT_BIT_SHIFT	0x4UL
+#define CC_HOST_IRR_REE_OP_ABORTED_AES_2_INT_BIT_SIZE	0x1UL
+#define CC_HOST_IRR_REE_OP_ABORTED_AES_3_INT_BIT_SHIFT	0x5UL
+#define CC_HOST_IRR_REE_OP_ABORTED_AES_3_INT_BIT_SIZE	0x1UL
+#define CC_HOST_IRR_REE_OP_ABORTED_AES_4_INT_BIT_SHIFT	0x6UL
+#define CC_HOST_IRR_REE_OP_ABORTED_AES_4_INT_BIT_SIZE	0x1UL
+#define CC_HOST_IRR_REE_OP_ABORTED_AES_5_INT_BIT_SHIFT	0x7UL
+#define CC_HOST_IRR_REE_OP_ABORTED_AES_5_INT_BIT_SIZE	0x1UL
 #define CC_HOST_IRR_AXI_ERR_INT_BIT_SHIFT	0x8UL
 #define CC_HOST_IRR_AXI_ERR_INT_BIT_SIZE	0x1UL
+#define CC_HOST_IRR_REE_OP_ABORTED_AES_6_INT_BIT_SHIFT	0x9UL
+#define CC_HOST_IRR_REE_OP_ABORTED_AES_6_INT_BIT_SIZE	0x1UL
+#define CC_HOST_IRR_REE_OP_ABORTED_AES_7_INT_BIT_SHIFT	0xAUL
+#define CC_HOST_IRR_REE_OP_ABORTED_AES_7_INT_BIT_SIZE	0x1UL
 #define CC_HOST_IRR_GPR0_BIT_SHIFT	0xBUL
 #define CC_HOST_IRR_GPR0_BIT_SIZE	0x1UL
+#define CC_HOST_IRR_REE_OP_ABORTED_SM_0_INT_BIT_SHIFT	0xCUL
+#define CC_HOST_IRR_REE_OP_ABORTED_SM_0_INT_BIT_SIZE	0x1UL
+#define CC_HOST_IRR_REE_OP_ABORTED_SM_1_INT_BIT_SHIFT	0xDUL
+#define CC_HOST_IRR_REE_OP_ABORTED_SM_1_INT_BIT_SIZE	0x1UL
+#define CC_HOST_IRR_REE_OP_ABORTED_SM_2_INT_BIT_SHIFT	0xEUL
+#define CC_HOST_IRR_REE_OP_ABORTED_SM_2_INT_BIT_SIZE	0x1UL
+#define CC_HOST_IRR_REE_OP_ABORTED_SM_3_INT_BIT_SHIFT	0xFUL
+#define CC_HOST_IRR_REE_OP_ABORTED_SM_3_INT_BIT_SIZE	0x1UL
+#define CC_HOST_IRR_REE_OP_ABORTED_SM_4_INT_BIT_SHIFT	0x10UL
+#define CC_HOST_IRR_REE_OP_ABORTED_SM_4_INT_BIT_SIZE	0x1UL
+#define CC_HOST_IRR_REE_OP_ABORTED_SM_5_INT_BIT_SHIFT	0x11UL
+#define CC_HOST_IRR_REE_OP_ABORTED_SM_5_INT_BIT_SIZE	0x1UL
+#define CC_HOST_IRR_REE_OP_ABORTED_SM_6_INT_BIT_SHIFT	0x12UL
+#define CC_HOST_IRR_REE_OP_ABORTED_SM_6_INT_BIT_SIZE	0x1UL
 #define CC_HOST_IRR_DSCRPTR_WATERMARK_INT_BIT_SHIFT	0x13UL
 #define CC_HOST_IRR_DSCRPTR_WATERMARK_INT_BIT_SIZE	0x1UL
+#define CC_HOST_IRR_REE_OP_ABORTED_SM_7_INT_BIT_SHIFT	0x14UL
+#define CC_HOST_IRR_REE_OP_ABORTED_SM_7_INT_BIT_SIZE	0x1UL
 #define CC_HOST_IRR_AXIM_COMP_INT_BIT_SHIFT	0x17UL
 #define CC_HOST_IRR_AXIM_COMP_INT_BIT_SIZE	0x1UL
 #define CC_HOST_SEP_SRAM_THRESHOLD_REG_OFFSET	0xA10UL
 #define CC_HOST_SEP_SRAM_THRESHOLD_VALUE_BIT_SHIFT	0x0UL
 #define CC_HOST_SEP_SRAM_THRESHOLD_VALUE_BIT_SIZE	0xCUL
-#define CC_HOST_IMR_REG_OFFSET	0xA04UL
-#define CC_HOST_IMR_NOT_USED_MASK_BIT_SHIFT	0x1UL
-#define CC_HOST_IMR_NOT_USED_MASK_BIT_SIZE	0x1UL
+
+/* IMR */
+#define CC_HOST_IMR_REG_OFFSET	0x0A04UL
+#define CC_HOST_IMR_REE_OP_ABORTED_AES_0_MASK_BIT_SHIFT	0x1UL
+#define CC_HOST_IMR_REE_OP_ABORTED_AES_0_MASK_BIT_SIZE	0x1UL
 #define CC_HOST_IMR_DSCRPTR_COMPLETION_MASK_BIT_SHIFT	0x2UL
 #define CC_HOST_IMR_DSCRPTR_COMPLETION_MASK_BIT_SIZE	0x1UL
+#define CC_HOST_IMR_REE_OP_ABORTED_AES_1_MASK_BIT_SHIFT	0x3UL
+#define CC_HOST_IMR_REE_OP_ABORTED_AES_1_MASK_BIT_SIZE	0x1UL
+#define CC_HOST_IMR_REE_OP_ABORTED_AES_2_MASK_BIT_SHIFT	0x4UL
+#define CC_HOST_IMR_REE_OP_ABORTED_AES_2_MASK_BIT_SIZE	0x1UL
+#define CC_HOST_IMR_REE_OP_ABORTED_AES_3_MASK_BIT_SHIFT	0x5UL
+#define CC_HOST_IMR_REE_OP_ABORTED_AES_3_MASK_BIT_SIZE	0x1UL
+#define CC_HOST_IMR_REE_OP_ABORTED_AES_4_MASK_BIT_SHIFT	0x6UL
+#define CC_HOST_IMR_REE_OP_ABORTED_AES_4_MASK_BIT_SIZE	0x1UL
+#define CC_HOST_IMR_REE_OP_ABORTED_AES_5_MASK_BIT_SHIFT	0x7UL
+#define CC_HOST_IMR_REE_OP_ABORTED_AES_5_MASK_BIT_SIZE	0x1UL
 #define CC_HOST_IMR_AXI_ERR_MASK_BIT_SHIFT	0x8UL
 #define CC_HOST_IMR_AXI_ERR_MASK_BIT_SIZE	0x1UL
+#define CC_HOST_IMR_REE_OP_ABORTED_AES_6_MASK_BIT_SHIFT	0x9UL
+#define CC_HOST_IMR_REE_OP_ABORTED_AES_6_MASK_BIT_SIZE	0x1UL
+#define CC_HOST_IMR_REE_OP_ABORTED_AES_7_MASK_BIT_SHIFT	0xAUL
+#define CC_HOST_IMR_REE_OP_ABORTED_AES_7_MASK_BIT_SIZE	0x1UL
 #define CC_HOST_IMR_GPR0_BIT_SHIFT	0xBUL
 #define CC_HOST_IMR_GPR0_BIT_SIZE	0x1UL
+#define CC_HOST_IMR_REE_OP_ABORTED_SM_0_MASK_BIT_SHIFT	0xCUL
+#define CC_HOST_IMR_REE_OP_ABORTED_SM_0_MASK_BIT_SIZE	0x1UL
+#define CC_HOST_IMR_REE_OP_ABORTED_SM_1_MASK_BIT_SHIFT	0xDUL
+#define CC_HOST_IMR_REE_OP_ABORTED_SM_1_MASK_BIT_SIZE	0x1UL
+#define CC_HOST_IMR_REE_OP_ABORTED_SM_2_MASK_BIT_SHIFT	0xEUL
+#define CC_HOST_IMR_REE_OP_ABORTED_SM_2_MASK_BIT_SIZE	0x1UL
+#define CC_HOST_IMR_REE_OP_ABORTED_SM_3_MASK_BIT_SHIFT	0xFUL
+#define CC_HOST_IMR_REE_OP_ABORTED_SM_3_MASK_BIT_SIZE	0x1UL
+#define CC_HOST_IMR_REE_OP_ABORTED_SM_4_MASK_BIT_SHIFT	0x10UL
+#define CC_HOST_IMR_REE_OP_ABORTED_SM_4_MASK_BIT_SIZE	0x1UL
+#define CC_HOST_IMR_REE_OP_ABORTED_SM_5_MASK_BIT_SHIFT	0x11UL
+#define CC_HOST_IMR_REE_OP_ABORTED_SM_5_MASK_BIT_SIZE	0x1UL
+#define CC_HOST_IMR_REE_OP_ABORTED_SM_6_MASK_BIT_SHIFT	0x12UL
+#define CC_HOST_IMR_REE_OP_ABORTED_SM_6_MASK_BIT_SIZE	0x1UL
 #define CC_HOST_IMR_DSCRPTR_WATERMARK_MASK0_BIT_SHIFT	0x13UL
 #define CC_HOST_IMR_DSCRPTR_WATERMARK_MASK0_BIT_SIZE	0x1UL
+#define CC_HOST_IMR_REE_OP_ABORTED_SM_7_MASK_BIT_SHIFT	0x14UL
+#define CC_HOST_IMR_REE_OP_ABORTED_SM_7_MASK_BIT_SIZE	0x1UL
 #define CC_HOST_IMR_AXIM_COMP_INT_MASK_BIT_SHIFT	0x17UL
 #define CC_HOST_IMR_AXIM_COMP_INT_MASK_BIT_SIZE	0x1UL
+
+/* ICR */
 #define CC_HOST_ICR_REG_OFFSET	0xA08UL
 #define CC_HOST_ICR_DSCRPTR_COMPLETION_BIT_SHIFT	0x2UL
 #define CC_HOST_ICR_DSCRPTR_COMPLETION_BIT_SIZE	0x1UL
@@ -45,6 +114,9 @@
 #define CC_HOST_ICR_DSCRPTR_WATERMARK_QUEUE0_CLEAR_BIT_SIZE	0x1UL
 #define CC_HOST_ICR_AXIM_COMP_INT_CLEAR_BIT_SHIFT	0x17UL
 #define CC_HOST_ICR_AXIM_COMP_INT_CLEAR_BIT_SIZE	0x1UL
+#define CC_SECURITY_DISABLED_REG_OFFSET		0x0A1CUL
+#define CC_SECURITY_DISABLED_VALUE_BIT_SHIFT	0x0UL
+#define CC_SECURITY_DISABLED_VALUE_BIT_SIZE	0x1UL
 #define CC_HOST_SIGNATURE_712_REG_OFFSET	0xA24UL
 #define CC_HOST_SIGNATURE_630_REG_OFFSET	0xAC8UL
 #define CC_HOST_SIGNATURE_VALUE_BIT_SHIFT	0x0UL
@@ -132,6 +204,49 @@
 #define CC_HOST_POWER_DOWN_EN_VALUE_BIT_SHIFT	0x0UL
 #define CC_HOST_POWER_DOWN_EN_VALUE_BIT_SIZE	0x1UL
 // --------------------------------------
+// BLOCK: ID_REGISTERS
+// --------------------------------------
+#define CC_PERIPHERAL_ID_4_REG_OFFSET	0x0FD0UL
+#define CC_PERIPHERAL_ID_4_VALUE_BIT_SHIFT	0x0UL
+#define CC_PERIPHERAL_ID_4_VALUE_BIT_SIZE	0x4UL
+#define CC_PIDRESERVED0_REG_OFFSET	0x0FD4UL
+#define CC_PIDRESERVED1_REG_OFFSET	0x0FD8UL
+#define CC_PIDRESERVED2_REG_OFFSET	0x0FDCUL
+#define CC_PERIPHERAL_ID_0_REG_OFFSET	0x0FE0UL
+#define CC_PERIPHERAL_ID_0_VALUE_BIT_SHIFT	0x0UL
+#define CC_PERIPHERAL_ID_0_VALUE_BIT_SIZE	0x8UL
+#define CC_PERIPHERAL_ID_1_REG_OFFSET	0x0FE4UL
+#define CC_PERIPHERAL_ID_1_PART_1_BIT_SHIFT	0x0UL
+#define CC_PERIPHERAL_ID_1_PART_1_BIT_SIZE	0x4UL
+#define CC_PERIPHERAL_ID_1_DES_0_JEP106_BIT_SHIFT	0x4UL
+#define CC_PERIPHERAL_ID_1_DES_0_JEP106_BIT_SIZE	0x4UL
+#define CC_PERIPHERAL_ID_2_REG_OFFSET	0x0FE8UL
+#define CC_PERIPHERAL_ID_2_DES_1_JEP106_BIT_SHIFT	0x0UL
+#define CC_PERIPHERAL_ID_2_DES_1_JEP106_BIT_SIZE	0x3UL
+#define CC_PERIPHERAL_ID_2_JEDEC_BIT_SHIFT	0x3UL
+#define CC_PERIPHERAL_ID_2_JEDEC_BIT_SIZE	0x1UL
+#define CC_PERIPHERAL_ID_2_REVISION_BIT_SHIFT	0x4UL
+#define CC_PERIPHERAL_ID_2_REVISION_BIT_SIZE	0x4UL
+#define CC_PERIPHERAL_ID_3_REG_OFFSET	0x0FECUL
+#define CC_PERIPHERAL_ID_3_CMOD_BIT_SHIFT	0x0UL
+#define CC_PERIPHERAL_ID_3_CMOD_BIT_SIZE	0x4UL
+#define CC_PERIPHERAL_ID_3_REVAND_BIT_SHIFT	0x4UL
+#define CC_PERIPHERAL_ID_3_REVAND_BIT_SIZE	0x4UL
+#define CC_COMPONENT_ID_0_REG_OFFSET	0x0FF0UL
+#define CC_COMPONENT_ID_0_VALUE_BIT_SHIFT	0x0UL
+#define CC_COMPONENT_ID_0_VALUE_BIT_SIZE	0x8UL
+#define CC_COMPONENT_ID_1_REG_OFFSET	0x0FF4UL
+#define CC_COMPONENT_ID_1_PRMBL_1_BIT_SHIFT	0x0UL
+#define CC_COMPONENT_ID_1_PRMBL_1_BIT_SIZE	0x4UL
+#define CC_COMPONENT_ID_1_CLASS_BIT_SHIFT	0x4UL
+#define CC_COMPONENT_ID_1_CLASS_BIT_SIZE	0x4UL
+#define CC_COMPONENT_ID_2_REG_OFFSET	0x0FF8UL
+#define CC_COMPONENT_ID_2_VALUE_BIT_SHIFT	0x0UL
+#define CC_COMPONENT_ID_2_VALUE_BIT_SIZE	0x8UL
+#define CC_COMPONENT_ID_3_REG_OFFSET	0x0FFCUL
+#define CC_COMPONENT_ID_3_VALUE_BIT_SHIFT	0x0UL
+#define CC_COMPONENT_ID_3_VALUE_BIT_SIZE	0x8UL
+// --------------------------------------
 // BLOCK: HOST_SRAM
 // --------------------------------------
 #define CC_SRAM_DATA_REG_OFFSET	0xF00UL
diff --git a/drivers/crypto/ccree/cc_hw_queue_defs.h b/drivers/crypto/ccree/cc_hw_queue_defs.h
index 7a9b90db7db7..9f4db9956e91 100644
--- a/drivers/crypto/ccree/cc_hw_queue_defs.h
+++ b/drivers/crypto/ccree/cc_hw_queue_defs.h
@@ -1,5 +1,5 @@
 /* SPDX-License-Identifier: GPL-2.0 */
-/* Copyright (C) 2012-2018 ARM Limited or its affiliates. */
+/* Copyright (C) 2012-2019 ARM Limited (or its affiliates). */
 
 #ifndef __CC_HW_QUEUE_DEFS_H__
 #define __CC_HW_QUEUE_DEFS_H__
@@ -28,11 +28,13 @@
 	GENMASK(CC_REG_HIGH(word, name), CC_REG_LOW(word, name))
 
 #define WORD0_VALUE		CC_GENMASK(0, VALUE)
+#define	WORD0_CPP_CIPHER_MODE	CC_GENMASK(0, CPP_CIPHER_MODE)
 #define WORD1_DIN_CONST_VALUE	CC_GENMASK(1, DIN_CONST_VALUE)
 #define WORD1_DIN_DMA_MODE	CC_GENMASK(1, DIN_DMA_MODE)
 #define WORD1_DIN_SIZE		CC_GENMASK(1, DIN_SIZE)
 #define WORD1_NOT_LAST		CC_GENMASK(1, NOT_LAST)
 #define WORD1_NS_BIT		CC_GENMASK(1, NS_BIT)
+#define WORD1_LOCK_QUEUE	CC_GENMASK(1, LOCK_QUEUE)
 #define WORD2_VALUE		CC_GENMASK(2, VALUE)
 #define WORD3_DOUT_DMA_MODE	CC_GENMASK(3, DOUT_DMA_MODE)
 #define WORD3_DOUT_LAST_IND	CC_GENMASK(3, DOUT_LAST_IND)
@@ -176,6 +178,15 @@ enum cc_hw_crypto_key {
 	END_OF_KEYS = S32_MAX,
 };
 
+#define CC_NUM_HW_KEY_SLOTS	4
+#define CC_FIRST_HW_KEY_SLOT	0
+#define CC_LAST_HW_KEY_SLOT	(CC_FIRST_HW_KEY_SLOT + CC_NUM_HW_KEY_SLOTS - 1)
+
+#define CC_NUM_CPP_KEY_SLOTS	8
+#define CC_FIRST_CPP_KEY_SLOT	16
+#define CC_LAST_CPP_KEY_SLOT	(CC_FIRST_CPP_KEY_SLOT + \
+					CC_NUM_CPP_KEY_SLOTS - 1)
+
 enum cc_hw_aes_key_size {
 	AES_128_KEY = 0,
 	AES_192_KEY = 1,
@@ -189,6 +200,9 @@ enum cc_hash_cipher_pad {
 	HASH_CIPHER_DO_PADDING_RESERVE32 = S32_MAX,
 };
 
+#define CC_CPP_DIN_ADDR	0xFF00FF00UL
+#define CC_CPP_DIN_SIZE 0xFF00FFUL
+
 /*****************************/
 /* Descriptor packing macros */
 /*****************************/
@@ -249,6 +263,25 @@ static inline void set_din_no_dma(struct cc_hw_desc *pdesc, u32 addr, u32 size)
 }
 
 /*
+ * Setup the special CPP descriptor
+ *
+ * @pdesc: pointer HW descriptor struct
+ * @alg: cipher used (AES / SM4)
+ * @mode: mode used (CTR or CBC)
+ * @slot: slot number
+ * @ksize: key size
+ */
+static inline void set_cpp_crypto_key(struct cc_hw_desc *pdesc, u8 slot)
+{
+	pdesc->word[0] |= CC_CPP_DIN_ADDR;
+
+	pdesc->word[1] |= FIELD_PREP(WORD1_DIN_SIZE, CC_CPP_DIN_SIZE);
+	pdesc->word[1] |= FIELD_PREP(WORD1_LOCK_QUEUE, 1);
+
+	pdesc->word[4] |= FIELD_PREP(WORD4_SETUP_OPERATION, slot);
+}
+
+/*
  * Set the DIN field of a HW descriptors to SRAM mode.
  * Note: No need to check SRAM alignment since host requests do not use SRAM and
  * adaptor will enforce alignment check.
diff --git a/drivers/crypto/ccree/cc_ivgen.c b/drivers/crypto/ccree/cc_ivgen.c
index 769458323394..99dc69383e20 100644
--- a/drivers/crypto/ccree/cc_ivgen.c
+++ b/drivers/crypto/ccree/cc_ivgen.c
@@ -1,5 +1,5 @@
 // SPDX-License-Identifier: GPL-2.0
-/* Copyright (C) 2012-2018 ARM Limited or its affiliates. */
+/* Copyright (C) 2012-2019 ARM Limited (or its affiliates). */
 
 #include <crypto/ctr.h>
 #include "cc_driver.h"
@@ -154,9 +154,6 @@ void cc_ivgen_fini(struct cc_drvdata *drvdata)
 	}
 
 	ivgen_ctx->pool = NULL_SRAM_ADDR;
-
-	/* release "this" context */
-	kfree(ivgen_ctx);
 }
 
 /*!
@@ -174,10 +171,12 @@ int cc_ivgen_init(struct cc_drvdata *drvdata)
 	int rc;
 
 	/* Allocate "this" context */
-	ivgen_ctx = kzalloc(sizeof(*ivgen_ctx), GFP_KERNEL);
+	ivgen_ctx = devm_kzalloc(device, sizeof(*ivgen_ctx), GFP_KERNEL);
 	if (!ivgen_ctx)
 		return -ENOMEM;
 
+	drvdata->ivgen_handle = ivgen_ctx;
+
 	/* Allocate pool's header for initial enc. key/IV */
 	ivgen_ctx->pool_meta = dma_alloc_coherent(device, CC_IVPOOL_META_SIZE,
 						  &ivgen_ctx->pool_meta_dma,
@@ -196,8 +195,6 @@ int cc_ivgen_init(struct cc_drvdata *drvdata)
 		goto out;
 	}
 
-	drvdata->ivgen_handle = ivgen_ctx;
-
 	return cc_init_iv_sram(drvdata);
 
 out:
diff --git a/drivers/crypto/ccree/cc_ivgen.h b/drivers/crypto/ccree/cc_ivgen.h
index b6ac16903dda..a9f5e8bba4f1 100644
--- a/drivers/crypto/ccree/cc_ivgen.h
+++ b/drivers/crypto/ccree/cc_ivgen.h
@@ -1,5 +1,5 @@
 /* SPDX-License-Identifier: GPL-2.0 */
-/* Copyright (C) 2012-2018 ARM Limited or its affiliates. */
+/* Copyright (C) 2012-2019 ARM Limited (or its affiliates). */
 
 #ifndef __CC_IVGEN_H__
 #define __CC_IVGEN_H__
diff --git a/drivers/crypto/ccree/cc_kernel_regs.h b/drivers/crypto/ccree/cc_kernel_regs.h
index 8d7262a35156..582bae450596 100644
--- a/drivers/crypto/ccree/cc_kernel_regs.h
+++ b/drivers/crypto/ccree/cc_kernel_regs.h
@@ -1,5 +1,5 @@
 /* SPDX-License-Identifier: GPL-2.0 */
-/* Copyright (C) 2012-2018 ARM Limited or its affiliates. */
+/* Copyright (C) 2012-2019 ARM Limited (or its affiliates). */
 
 #ifndef __CC_CRYS_KERNEL_H__
 #define __CC_CRYS_KERNEL_H__
diff --git a/drivers/crypto/ccree/cc_lli_defs.h b/drivers/crypto/ccree/cc_lli_defs.h
index 64b15ac9f1d3..f891ab813f41 100644
--- a/drivers/crypto/ccree/cc_lli_defs.h
+++ b/drivers/crypto/ccree/cc_lli_defs.h
@@ -1,5 +1,5 @@
 /* SPDX-License-Identifier: GPL-2.0 */
-/* Copyright (C) 2012-2018 ARM Limited or its affiliates. */
+/* Copyright (C) 2012-2019 ARM Limited (or its affiliates). */
 
 #ifndef _CC_LLI_DEFS_H_
 #define _CC_LLI_DEFS_H_
@@ -14,7 +14,7 @@
 #define CC_MAX_MLLI_ENTRY_SIZE 0xFFFF
 
 #define LLI_MAX_NUM_OF_DATA_ENTRIES 128
-#define LLI_MAX_NUM_OF_ASSOC_DATA_ENTRIES 4
+#define LLI_MAX_NUM_OF_ASSOC_DATA_ENTRIES 8
 #define MLLI_TABLE_MIN_ALIGNMENT 4 /* 32 bit alignment */
 #define MAX_NUM_OF_BUFFERS_IN_MLLI 4
 #define MAX_NUM_OF_TOTAL_MLLI_ENTRIES \
diff --git a/drivers/crypto/ccree/cc_pm.c b/drivers/crypto/ccree/cc_pm.c
index 6ff7e75ad90e..2dad9c9543c6 100644
--- a/drivers/crypto/ccree/cc_pm.c
+++ b/drivers/crypto/ccree/cc_pm.c
@@ -1,5 +1,5 @@
 // SPDX-License-Identifier: GPL-2.0
-/* Copyright (C) 2012-2018 ARM Limited or its affiliates. */
+/* Copyright (C) 2012-2019 ARM Limited (or its affiliates). */
 
 #include <linux/kernel.h>
 #include <linux/interrupt.h>
@@ -11,6 +11,7 @@
 #include "cc_ivgen.h"
 #include "cc_hash.h"
 #include "cc_pm.h"
+#include "cc_fips.h"
 
 #define POWER_DOWN_ENABLE 0x01
 #define POWER_DOWN_DISABLE 0x00
@@ -25,13 +26,13 @@ int cc_pm_suspend(struct device *dev)
 	int rc;
 
 	dev_dbg(dev, "set HOST_POWER_DOWN_EN\n");
-	cc_iowrite(drvdata, CC_REG(HOST_POWER_DOWN_EN), POWER_DOWN_ENABLE);
 	rc = cc_suspend_req_queue(drvdata);
 	if (rc) {
 		dev_err(dev, "cc_suspend_req_queue (%x)\n", rc);
 		return rc;
 	}
 	fini_cc_regs(drvdata);
+	cc_iowrite(drvdata, CC_REG(HOST_POWER_DOWN_EN), POWER_DOWN_ENABLE);
 	cc_clk_off(drvdata);
 	return 0;
 }
@@ -42,19 +43,21 @@ int cc_pm_resume(struct device *dev)
 	struct cc_drvdata *drvdata = dev_get_drvdata(dev);
 
 	dev_dbg(dev, "unset HOST_POWER_DOWN_EN\n");
-	cc_iowrite(drvdata, CC_REG(HOST_POWER_DOWN_EN), POWER_DOWN_DISABLE);
-
+	/* Enables the device source clk */
 	rc = cc_clk_on(drvdata);
 	if (rc) {
 		dev_err(dev, "failed getting clock back on. We're toast.\n");
 		return rc;
 	}
 
+	cc_iowrite(drvdata, CC_REG(HOST_POWER_DOWN_EN), POWER_DOWN_DISABLE);
 	rc = init_cc_regs(drvdata, false);
 	if (rc) {
 		dev_err(dev, "init_cc_regs (%x)\n", rc);
 		return rc;
 	}
+	/* check if tee fips error occurred during power down */
+	cc_tee_handle_fips_error(drvdata);
 
 	rc = cc_resume_req_queue(drvdata);
 	if (rc) {
diff --git a/drivers/crypto/ccree/cc_pm.h b/drivers/crypto/ccree/cc_pm.h
index 907a6db4d6c0..6190cdba5dad 100644
--- a/drivers/crypto/ccree/cc_pm.h
+++ b/drivers/crypto/ccree/cc_pm.h
@@ -1,5 +1,5 @@
 /* SPDX-License-Identifier: GPL-2.0 */
-/* Copyright (C) 2012-2018 ARM Limited or its affiliates. */
+/* Copyright (C) 2012-2019 ARM Limited (or its affiliates). */
 
 /* \file cc_pm.h
  */
diff --git a/drivers/crypto/ccree/cc_request_mgr.c b/drivers/crypto/ccree/cc_request_mgr.c
index 83a8aaae61c7..0bc6ccb0b899 100644
--- a/drivers/crypto/ccree/cc_request_mgr.c
+++ b/drivers/crypto/ccree/cc_request_mgr.c
@@ -1,7 +1,8 @@
 // SPDX-License-Identifier: GPL-2.0
-/* Copyright (C) 2012-2018 ARM Limited or its affiliates. */
+/* Copyright (C) 2012-2019 ARM Limited (or its affiliates). */
 
 #include <linux/kernel.h>
+#include <linux/nospec.h>
 #include "cc_driver.h"
 #include "cc_buffer_mgr.h"
 #include "cc_request_mgr.h"
@@ -52,11 +53,38 @@ struct cc_bl_item {
 	bool notif;
 };
 
+static const u32 cc_cpp_int_masks[CC_CPP_NUM_ALGS][CC_CPP_NUM_SLOTS] = {
+	{ BIT(CC_HOST_IRR_REE_OP_ABORTED_AES_0_INT_BIT_SHIFT),
+	  BIT(CC_HOST_IRR_REE_OP_ABORTED_AES_1_INT_BIT_SHIFT),
+	  BIT(CC_HOST_IRR_REE_OP_ABORTED_AES_2_INT_BIT_SHIFT),
+	  BIT(CC_HOST_IRR_REE_OP_ABORTED_AES_3_INT_BIT_SHIFT),
+	  BIT(CC_HOST_IRR_REE_OP_ABORTED_AES_4_INT_BIT_SHIFT),
+	  BIT(CC_HOST_IRR_REE_OP_ABORTED_AES_5_INT_BIT_SHIFT),
+	  BIT(CC_HOST_IRR_REE_OP_ABORTED_AES_6_INT_BIT_SHIFT),
+	  BIT(CC_HOST_IRR_REE_OP_ABORTED_AES_7_INT_BIT_SHIFT) },
+	{ BIT(CC_HOST_IRR_REE_OP_ABORTED_SM_0_INT_BIT_SHIFT),
+	  BIT(CC_HOST_IRR_REE_OP_ABORTED_SM_1_INT_BIT_SHIFT),
+	  BIT(CC_HOST_IRR_REE_OP_ABORTED_SM_2_INT_BIT_SHIFT),
+	  BIT(CC_HOST_IRR_REE_OP_ABORTED_SM_3_INT_BIT_SHIFT),
+	  BIT(CC_HOST_IRR_REE_OP_ABORTED_SM_4_INT_BIT_SHIFT),
+	  BIT(CC_HOST_IRR_REE_OP_ABORTED_SM_5_INT_BIT_SHIFT),
+	  BIT(CC_HOST_IRR_REE_OP_ABORTED_SM_6_INT_BIT_SHIFT),
+	  BIT(CC_HOST_IRR_REE_OP_ABORTED_SM_7_INT_BIT_SHIFT) }
+};
+
 static void comp_handler(unsigned long devarg);
 #ifdef COMP_IN_WQ
 static void comp_work_handler(struct work_struct *work);
 #endif
 
+static inline u32 cc_cpp_int_mask(enum cc_cpp_alg alg, int slot)
+{
+	alg = array_index_nospec(alg, CC_CPP_NUM_ALGS);
+	slot = array_index_nospec(slot, CC_CPP_NUM_SLOTS);
+
+	return cc_cpp_int_masks[alg][slot];
+}
+
 void cc_req_mgr_fini(struct cc_drvdata *drvdata)
 {
 	struct cc_req_mgr_handle *req_mgr_h = drvdata->request_mgr_handle;
@@ -336,10 +364,12 @@ static void cc_enqueue_backlog(struct cc_drvdata *drvdata,
 			       struct cc_bl_item *bli)
 {
 	struct cc_req_mgr_handle *mgr = drvdata->request_mgr_handle;
+	struct device *dev = drvdata_to_dev(drvdata);
 
 	spin_lock_bh(&mgr->bl_lock);
 	list_add_tail(&bli->list, &mgr->backlog);
 	++mgr->bl_len;
+	dev_dbg(dev, "+++bl len: %d\n", mgr->bl_len);
 	spin_unlock_bh(&mgr->bl_lock);
 	tasklet_schedule(&mgr->comptask);
 }
@@ -349,7 +379,7 @@ static void cc_proc_backlog(struct cc_drvdata *drvdata)
 	struct cc_req_mgr_handle *mgr = drvdata->request_mgr_handle;
 	struct cc_bl_item *bli;
 	struct cc_crypto_req *creq;
-	struct crypto_async_request *req;
+	void *req;
 	bool ivgen;
 	unsigned int total_len;
 	struct device *dev = drvdata_to_dev(drvdata);
@@ -359,17 +389,20 @@ static void cc_proc_backlog(struct cc_drvdata *drvdata)
 
 	while (mgr->bl_len) {
 		bli = list_first_entry(&mgr->backlog, struct cc_bl_item, list);
+		dev_dbg(dev, "---bl len: %d\n", mgr->bl_len);
+
 		spin_unlock(&mgr->bl_lock);
 
+
 		creq = &bli->creq;
-		req = (struct crypto_async_request *)creq->user_arg;
+		req = creq->user_arg;
 
 		/*
 		 * Notify the request we're moving out of the backlog
 		 * but only if we haven't done so already.
 		 */
 		if (!bli->notif) {
-			req->complete(req, -EINPROGRESS);
+			creq->user_cb(dev, req, -EINPROGRESS);
 			bli->notif = true;
 		}
 
@@ -579,6 +612,8 @@ static void proc_completions(struct cc_drvdata *drvdata)
 						drvdata->request_mgr_handle;
 	unsigned int *tail = &request_mgr_handle->req_queue_tail;
 	unsigned int *head = &request_mgr_handle->req_queue_head;
+	int rc;
+	u32 mask;
 
 	while (request_mgr_handle->axi_completed) {
 		request_mgr_handle->axi_completed--;
@@ -596,8 +631,22 @@ static void proc_completions(struct cc_drvdata *drvdata)
 
 		cc_req = &request_mgr_handle->req_queue[*tail];
 
+		if (cc_req->cpp.is_cpp) {
+
+			dev_dbg(dev, "CPP request completion slot: %d alg:%d\n",
+				cc_req->cpp.slot, cc_req->cpp.alg);
+			mask = cc_cpp_int_mask(cc_req->cpp.alg,
+					       cc_req->cpp.slot);
+			rc = (drvdata->irq & mask ? -EPERM : 0);
+			dev_dbg(dev, "Got mask: %x irq: %x rc: %d\n", mask,
+				drvdata->irq, rc);
+		} else {
+			dev_dbg(dev, "None CPP request completion\n");
+			rc = 0;
+		}
+
 		if (cc_req->user_cb)
-			cc_req->user_cb(dev, cc_req->user_arg, 0);
+			cc_req->user_cb(dev, cc_req->user_arg, rc);
 		*tail = (*tail + 1) & (MAX_REQUEST_QUEUE_SIZE - 1);
 		dev_dbg(dev, "Dequeue request tail=%u\n", *tail);
 		dev_dbg(dev, "Request completed. axi_completed=%d\n",
@@ -618,47 +667,50 @@ static void comp_handler(unsigned long devarg)
 	struct cc_drvdata *drvdata = (struct cc_drvdata *)devarg;
 	struct cc_req_mgr_handle *request_mgr_handle =
 						drvdata->request_mgr_handle;
-
+	struct device *dev = drvdata_to_dev(drvdata);
 	u32 irq;
 
-	irq = (drvdata->irq & CC_COMP_IRQ_MASK);
+	dev_dbg(dev, "Completion handler called!\n");
+	irq = (drvdata->irq & drvdata->comp_mask);
 
-	if (irq & CC_COMP_IRQ_MASK) {
-		/* To avoid the interrupt from firing as we unmask it,
-		 * we clear it now
-		 */
-		cc_iowrite(drvdata, CC_REG(HOST_ICR), CC_COMP_IRQ_MASK);
+	/* To avoid the interrupt from firing as we unmask it,
+	 * we clear it now
+	 */
+	cc_iowrite(drvdata, CC_REG(HOST_ICR), irq);
 
-		/* Avoid race with above clear: Test completion counter
-		 * once more
-		 */
-		request_mgr_handle->axi_completed +=
-				cc_axi_comp_count(drvdata);
-
-		while (request_mgr_handle->axi_completed) {
-			do {
-				proc_completions(drvdata);
-				/* At this point (after proc_completions()),
-				 * request_mgr_handle->axi_completed is 0.
-				 */
-				request_mgr_handle->axi_completed =
-						cc_axi_comp_count(drvdata);
-			} while (request_mgr_handle->axi_completed > 0);
+	/* Avoid race with above clear: Test completion counter once more */
 
-			cc_iowrite(drvdata, CC_REG(HOST_ICR),
-				   CC_COMP_IRQ_MASK);
+	request_mgr_handle->axi_completed += cc_axi_comp_count(drvdata);
+
+	dev_dbg(dev, "AXI completion after updated: %d\n",
+		request_mgr_handle->axi_completed);
+
+	while (request_mgr_handle->axi_completed) {
+		do {
+			drvdata->irq |= cc_ioread(drvdata, CC_REG(HOST_IRR));
+			irq = (drvdata->irq & drvdata->comp_mask);
+			proc_completions(drvdata);
 
+			/* At this point (after proc_completions()),
+			 * request_mgr_handle->axi_completed is 0.
+			 */
 			request_mgr_handle->axi_completed +=
-					cc_axi_comp_count(drvdata);
-		}
+						cc_axi_comp_count(drvdata);
+		} while (request_mgr_handle->axi_completed > 0);
+
+		cc_iowrite(drvdata, CC_REG(HOST_ICR), irq);
+
+		request_mgr_handle->axi_completed += cc_axi_comp_count(drvdata);
 	}
+
 	/* after verifing that there is nothing to do,
 	 * unmask AXI completion interrupt
 	 */
 	cc_iowrite(drvdata, CC_REG(HOST_IMR),
-		   cc_ioread(drvdata, CC_REG(HOST_IMR)) & ~irq);
+		   cc_ioread(drvdata, CC_REG(HOST_IMR)) & ~drvdata->comp_mask);
 
 	cc_proc_backlog(drvdata);
+	dev_dbg(dev, "Comp. handler done.\n");
 }
 
 /*
diff --git a/drivers/crypto/ccree/cc_request_mgr.h b/drivers/crypto/ccree/cc_request_mgr.h
index 573cb97af085..f46cf766fe4d 100644
--- a/drivers/crypto/ccree/cc_request_mgr.h
+++ b/drivers/crypto/ccree/cc_request_mgr.h
@@ -1,5 +1,5 @@
 /* SPDX-License-Identifier: GPL-2.0 */
-/* Copyright (C) 2012-2018 ARM Limited or its affiliates. */
+/* Copyright (C) 2012-2019 ARM Limited (or its affiliates). */
 
 /* \file cc_request_mgr.h
  * Request Manager
diff --git a/drivers/crypto/ccree/cc_sram_mgr.c b/drivers/crypto/ccree/cc_sram_mgr.c
index c8c276f6dee9..62c885e6e791 100644
--- a/drivers/crypto/ccree/cc_sram_mgr.c
+++ b/drivers/crypto/ccree/cc_sram_mgr.c
@@ -1,5 +1,5 @@
 // SPDX-License-Identifier: GPL-2.0
-/* Copyright (C) 2012-2018 ARM Limited or its affiliates. */
+/* Copyright (C) 2012-2019 ARM Limited (or its affiliates). */
 
 #include "cc_driver.h"
 #include "cc_sram_mgr.h"
@@ -19,8 +19,7 @@ struct cc_sram_ctx {
  */
 void cc_sram_mgr_fini(struct cc_drvdata *drvdata)
 {
-	/* Free "this" context */
-	kfree(drvdata->sram_mgr_handle);
+	/* Nothing needed */
 }
 
 /**
@@ -48,7 +47,7 @@ int cc_sram_mgr_init(struct cc_drvdata *drvdata)
 	}
 
 	/* Allocate "this" context */
-	ctx = kzalloc(sizeof(*ctx), GFP_KERNEL);
+	ctx = devm_kzalloc(dev, sizeof(*ctx), GFP_KERNEL);
 
 	if (!ctx)
 		return -ENOMEM;
diff --git a/drivers/crypto/ccree/cc_sram_mgr.h b/drivers/crypto/ccree/cc_sram_mgr.h
index d48649fb3323..1d14de9ee8c3 100644
--- a/drivers/crypto/ccree/cc_sram_mgr.h
+++ b/drivers/crypto/ccree/cc_sram_mgr.h
@@ -1,5 +1,5 @@
 /* SPDX-License-Identifier: GPL-2.0 */
-/* Copyright (C) 2012-2018 ARM Limited or its affiliates. */
+/* Copyright (C) 2012-2019 ARM Limited (or its affiliates). */
 
 #ifndef __CC_SRAM_MGR_H__
 #define __CC_SRAM_MGR_H__
diff --git a/drivers/crypto/chelsio/chcr_algo.c b/drivers/crypto/chelsio/chcr_algo.c
index 8d8cf80b9294..8a76fce22943 100644
--- a/drivers/crypto/chelsio/chcr_algo.c
+++ b/drivers/crypto/chelsio/chcr_algo.c
@@ -2130,7 +2130,6 @@ static int chcr_ahash_setkey(struct crypto_ahash *tfm, const u8 *key,
 	 * ipad in hmacctx->ipad and opad in hmacctx->opad location
 	 */
 	shash->tfm = hmacctx->base_hash;
-	shash->flags = crypto_shash_get_flags(hmacctx->base_hash);
 	if (keylen > bs) {
 		err = crypto_shash_digest(shash, key, keylen,
 					  hmacctx->ipad);
@@ -3517,7 +3516,6 @@ static int chcr_authenc_setkey(struct crypto_aead *authenc, const u8 *key,
 		SHASH_DESC_ON_STACK(shash, base_hash);
 
 		shash->tfm = base_hash;
-		shash->flags = crypto_shash_get_flags(base_hash);
 		bs = crypto_shash_blocksize(base_hash);
 		align = KEYCTX_ALIGN_PAD(max_authsize);
 		o_ptr =  actx->h_iopad + param.result_size + align;
diff --git a/drivers/crypto/hifn_795x.c b/drivers/crypto/hifn_795x.c
index dad212cabe63..d656be0a142b 100644
--- a/drivers/crypto/hifn_795x.c
+++ b/drivers/crypto/hifn_795x.c
@@ -1976,6 +1976,29 @@ static int hifn_setkey(struct crypto_ablkcipher *cipher, const u8 *key,
 	return 0;
 }
 
+static int hifn_des3_setkey(struct crypto_ablkcipher *cipher, const u8 *key,
+			    unsigned int len)
+{
+	struct hifn_context *ctx = crypto_ablkcipher_ctx(cipher);
+	struct hifn_device *dev = ctx->dev;
+	u32 flags;
+	int err;
+
+	flags = crypto_ablkcipher_get_flags(cipher);
+	err = __des3_verify_key(&flags, key);
+	if (unlikely(err)) {
+		crypto_ablkcipher_set_flags(cipher, flags);
+		return err;
+	}
+
+	dev->flags &= ~HIFN_FLAG_OLD_KEY;
+
+	memcpy(ctx->key, key, len);
+	ctx->keysize = len;
+
+	return 0;
+}
+
 static int hifn_handle_req(struct ablkcipher_request *req)
 {
 	struct hifn_context *ctx = crypto_tfm_ctx(req->base.tfm);
@@ -2240,7 +2263,7 @@ static struct hifn_alg_template hifn_alg_templates[] = {
 		.ablkcipher = {
 			.min_keysize	=	HIFN_3DES_KEY_LENGTH,
 			.max_keysize	=	HIFN_3DES_KEY_LENGTH,
-			.setkey		=	hifn_setkey,
+			.setkey		=	hifn_des3_setkey,
 			.encrypt	=	hifn_encrypt_3des_cfb,
 			.decrypt	=	hifn_decrypt_3des_cfb,
 		},
@@ -2250,7 +2273,7 @@ static struct hifn_alg_template hifn_alg_templates[] = {
 		.ablkcipher = {
 			.min_keysize	=	HIFN_3DES_KEY_LENGTH,
 			.max_keysize	=	HIFN_3DES_KEY_LENGTH,
-			.setkey		=	hifn_setkey,
+			.setkey		=	hifn_des3_setkey,
 			.encrypt	=	hifn_encrypt_3des_ofb,
 			.decrypt	=	hifn_decrypt_3des_ofb,
 		},
@@ -2261,7 +2284,7 @@ static struct hifn_alg_template hifn_alg_templates[] = {
 			.ivsize		=	HIFN_IV_LENGTH,
 			.min_keysize	=	HIFN_3DES_KEY_LENGTH,
 			.max_keysize	=	HIFN_3DES_KEY_LENGTH,
-			.setkey		=	hifn_setkey,
+			.setkey		=	hifn_des3_setkey,
 			.encrypt	=	hifn_encrypt_3des_cbc,
 			.decrypt	=	hifn_decrypt_3des_cbc,
 		},
@@ -2271,7 +2294,7 @@ static struct hifn_alg_template hifn_alg_templates[] = {
 		.ablkcipher = {
 			.min_keysize	=	HIFN_3DES_KEY_LENGTH,
 			.max_keysize	=	HIFN_3DES_KEY_LENGTH,
-			.setkey		=	hifn_setkey,
+			.setkey		=	hifn_des3_setkey,
 			.encrypt	=	hifn_encrypt_3des_ecb,
 			.decrypt	=	hifn_decrypt_3des_ecb,
 		},
diff --git a/drivers/crypto/hisilicon/sec/sec_algs.c b/drivers/crypto/hisilicon/sec/sec_algs.c
index adc0cd8ae97b..02768af0dccd 100644
--- a/drivers/crypto/hisilicon/sec/sec_algs.c
+++ b/drivers/crypto/hisilicon/sec/sec_algs.c
@@ -365,20 +365,16 @@ static int sec_alg_skcipher_setkey_des_cbc(struct crypto_skcipher *tfm,
 static int sec_alg_skcipher_setkey_3des_ecb(struct crypto_skcipher *tfm,
 					    const u8 *key, unsigned int keylen)
 {
-	if (keylen != DES_KEY_SIZE * 3)
-		return -EINVAL;
-
-	return sec_alg_skcipher_setkey(tfm, key, keylen,
+	return unlikely(des3_verify_key(tfm, key)) ?:
+	       sec_alg_skcipher_setkey(tfm, key, keylen,
 				       SEC_C_3DES_ECB_192_3KEY);
 }
 
 static int sec_alg_skcipher_setkey_3des_cbc(struct crypto_skcipher *tfm,
 					    const u8 *key, unsigned int keylen)
 {
-	if (keylen != DES3_EDE_KEY_SIZE)
-		return -EINVAL;
-
-	return sec_alg_skcipher_setkey(tfm, key, keylen,
+	return unlikely(des3_verify_key(tfm, key)) ?:
+	       sec_alg_skcipher_setkey(tfm, key, keylen,
 				       SEC_C_3DES_CBC_192_3KEY);
 }
 
diff --git a/drivers/crypto/inside-secure/safexcel_cipher.c b/drivers/crypto/inside-secure/safexcel_cipher.c
index 7ef30a98cb24..de4be10b172f 100644
--- a/drivers/crypto/inside-secure/safexcel_cipher.c
+++ b/drivers/crypto/inside-secure/safexcel_cipher.c
@@ -1039,13 +1039,12 @@ static int safexcel_cbc_des3_ede_decrypt(struct skcipher_request *req)
 static int safexcel_des3_ede_setkey(struct crypto_skcipher *ctfm,
 				   const u8 *key, unsigned int len)
 {
-	struct crypto_tfm *tfm = crypto_skcipher_tfm(ctfm);
-	struct safexcel_cipher_ctx *ctx = crypto_tfm_ctx(tfm);
+	struct safexcel_cipher_ctx *ctx = crypto_skcipher_ctx(ctfm);
+	int err;
 
-	if (len != DES3_EDE_KEY_SIZE) {
-		crypto_skcipher_set_flags(ctfm, CRYPTO_TFM_RES_BAD_KEY_LEN);
-		return -EINVAL;
-	}
+	err = des3_verify_key(ctfm, key);
+	if (unlikely(err))
+		return err;
 
 	/* if context exits and key changed, need to invalidate it */
 	if (ctx->base.ctxr_dma) {
diff --git a/drivers/crypto/ixp4xx_crypto.c b/drivers/crypto/ixp4xx_crypto.c
index 5c4659b04d70..9bbde2f26cac 100644
--- a/drivers/crypto/ixp4xx_crypto.c
+++ b/drivers/crypto/ixp4xx_crypto.c
@@ -758,14 +758,6 @@ static int setup_cipher(struct crypto_tfm *tfm, int encrypt,
 			return -EINVAL;
 		}
 		cipher_cfg |= keylen_cfg;
-	} else if (cipher_cfg & MOD_3DES) {
-		const u32 *K = (const u32 *)key;
-		if (unlikely(!((K[0] ^ K[2]) | (K[1] ^ K[3])) ||
-			     !((K[2] ^ K[4]) | (K[3] ^ K[5]))))
-		{
-			*flags |= CRYPTO_TFM_RES_BAD_KEY_SCHED;
-			return -EINVAL;
-		}
 	} else {
 		u32 tmp[DES_EXPKEY_WORDS];
 		if (des_ekey(tmp, key) == 0) {
@@ -859,6 +851,19 @@ out:
 	return ret;
 }
 
+static int ablk_des3_setkey(struct crypto_ablkcipher *tfm, const u8 *key,
+			    unsigned int key_len)
+{
+	u32 flags = crypto_ablkcipher_get_flags(tfm);
+	int err;
+
+	err = __des3_verify_key(&flags, key);
+	if (unlikely(err))
+		crypto_ablkcipher_set_flags(tfm, flags);
+
+	return ablk_setkey(tfm, key, key_len);
+}
+
 static int ablk_rfc3686_setkey(struct crypto_ablkcipher *tfm, const u8 *key,
 		unsigned int key_len)
 {
@@ -1175,6 +1180,43 @@ badkey:
 	return -EINVAL;
 }
 
+static int des3_aead_setkey(struct crypto_aead *tfm, const u8 *key,
+			    unsigned int keylen)
+{
+	struct ixp_ctx *ctx = crypto_aead_ctx(tfm);
+	u32 flags = CRYPTO_TFM_RES_BAD_KEY_LEN;
+	struct crypto_authenc_keys keys;
+	int err;
+
+	err = crypto_authenc_extractkeys(&keys, key, keylen);
+	if (unlikely(err))
+		goto badkey;
+
+	err = -EINVAL;
+	if (keys.authkeylen > sizeof(ctx->authkey))
+		goto badkey;
+
+	if (keys.enckeylen != DES3_EDE_KEY_SIZE)
+		goto badkey;
+
+	flags = crypto_aead_get_flags(tfm);
+	err = __des3_verify_key(&flags, keys.enckey);
+	if (unlikely(err))
+		goto badkey;
+
+	memcpy(ctx->authkey, keys.authkey, keys.authkeylen);
+	memcpy(ctx->enckey, keys.enckey, keys.enckeylen);
+	ctx->authkey_len = keys.authkeylen;
+	ctx->enckey_len = keys.enckeylen;
+
+	memzero_explicit(&keys, sizeof(keys));
+	return aead_setup(tfm, crypto_aead_authsize(tfm));
+badkey:
+	crypto_aead_set_flags(tfm, flags);
+	memzero_explicit(&keys, sizeof(keys));
+	return err;
+}
+
 static int aead_encrypt(struct aead_request *req)
 {
 	return aead_perform(req, 1, req->assoclen, req->cryptlen, req->iv);
@@ -1220,6 +1262,7 @@ static struct ixp_alg ixp4xx_algos[] = {
 			.min_keysize	= DES3_EDE_KEY_SIZE,
 			.max_keysize	= DES3_EDE_KEY_SIZE,
 			.ivsize		= DES3_EDE_BLOCK_SIZE,
+			.setkey		= ablk_des3_setkey,
 			}
 		}
 	},
@@ -1232,6 +1275,7 @@ static struct ixp_alg ixp4xx_algos[] = {
 		.cra_u		= { .ablkcipher = {
 			.min_keysize	= DES3_EDE_KEY_SIZE,
 			.max_keysize	= DES3_EDE_KEY_SIZE,
+			.setkey		= ablk_des3_setkey,
 			}
 		}
 	},
@@ -1313,6 +1357,7 @@ static struct ixp_aead_alg ixp4xx_aeads[] = {
 		},
 		.ivsize		= DES3_EDE_BLOCK_SIZE,
 		.maxauthsize	= MD5_DIGEST_SIZE,
+		.setkey		= des3_aead_setkey,
 	},
 	.hash = &hash_alg_md5,
 	.cfg_enc = CIPH_ENCR | MOD_3DES | MOD_CBC_ENC | KEYLEN_192,
@@ -1337,6 +1382,7 @@ static struct ixp_aead_alg ixp4xx_aeads[] = {
 		},
 		.ivsize		= DES3_EDE_BLOCK_SIZE,
 		.maxauthsize	= SHA1_DIGEST_SIZE,
+		.setkey		= des3_aead_setkey,
 	},
 	.hash = &hash_alg_sha1,
 	.cfg_enc = CIPH_ENCR | MOD_3DES | MOD_CBC_ENC | KEYLEN_192,
@@ -1443,7 +1489,7 @@ static int __init ixp_module_init(void)
 		/* authenc */
 		cra->base.cra_flags = CRYPTO_ALG_KERN_DRIVER_ONLY |
 				      CRYPTO_ALG_ASYNC;
-		cra->setkey = aead_setkey;
+		cra->setkey = cra->setkey ?: aead_setkey;
 		cra->setauthsize = aead_setauthsize;
 		cra->encrypt = aead_encrypt;
 		cra->decrypt = aead_decrypt;
diff --git a/drivers/crypto/marvell/cipher.c b/drivers/crypto/marvell/cipher.c
index fb279b3a1ca1..2fd936b19c6d 100644
--- a/drivers/crypto/marvell/cipher.c
+++ b/drivers/crypto/marvell/cipher.c
@@ -299,13 +299,12 @@ static int mv_cesa_des_setkey(struct crypto_skcipher *cipher, const u8 *key,
 static int mv_cesa_des3_ede_setkey(struct crypto_skcipher *cipher,
 				   const u8 *key, unsigned int len)
 {
-	struct crypto_tfm *tfm = crypto_skcipher_tfm(cipher);
-	struct mv_cesa_des_ctx *ctx = crypto_tfm_ctx(tfm);
+	struct mv_cesa_des_ctx *ctx = crypto_skcipher_ctx(cipher);
+	int err;
 
-	if (len != DES3_EDE_KEY_SIZE) {
-		crypto_skcipher_set_flags(cipher, CRYPTO_TFM_RES_BAD_KEY_LEN);
-		return -EINVAL;
-	}
+	err = des3_verify_key(cipher, key);
+	if (unlikely(err))
+		return err;
 
 	memcpy(ctx->key, key, DES3_EDE_KEY_SIZE);
 
diff --git a/drivers/crypto/marvell/hash.c b/drivers/crypto/marvell/hash.c
index 99ff54cc8a15..fd456dd703bf 100644
--- a/drivers/crypto/marvell/hash.c
+++ b/drivers/crypto/marvell/hash.c
@@ -135,11 +135,10 @@ static int mv_cesa_ahash_pad_len(struct mv_cesa_ahash_req *creq)
 
 static int mv_cesa_ahash_pad_req(struct mv_cesa_ahash_req *creq, u8 *buf)
 {
-	unsigned int index, padlen;
+	unsigned int padlen;
 
 	buf[0] = 0x80;
 	/* Pad out to 56 mod 64 */
-	index = creq->len & CESA_HASH_BLOCK_SIZE_MSK;
 	padlen = mv_cesa_ahash_pad_len(creq);
 	memset(buf + 1, 0, padlen - 1);
 
diff --git a/drivers/crypto/mediatek/mtk-sha.c b/drivers/crypto/mediatek/mtk-sha.c
index 5f4f845adbb8..a0806ba40c68 100644
--- a/drivers/crypto/mediatek/mtk-sha.c
+++ b/drivers/crypto/mediatek/mtk-sha.c
@@ -365,7 +365,6 @@ static int mtk_sha_finish_hmac(struct ahash_request *req)
 	SHASH_DESC_ON_STACK(shash, bctx->shash);
 
 	shash->tfm = bctx->shash;
-	shash->flags = 0; /* not CRYPTO_TFM_REQ_MAY_SLEEP */
 
 	return crypto_shash_init(shash) ?:
 	       crypto_shash_update(shash, bctx->opad, ctx->bs) ?:
@@ -810,8 +809,6 @@ static int mtk_sha_setkey(struct crypto_ahash *tfm, const u8 *key,
 	SHASH_DESC_ON_STACK(shash, bctx->shash);
 
 	shash->tfm = bctx->shash;
-	shash->flags = crypto_shash_get_flags(bctx->shash) &
-		       CRYPTO_TFM_REQ_MAY_SLEEP;
 
 	if (keylen > bs) {
 		err = crypto_shash_digest(shash, key, keylen, bctx->ipad);
diff --git a/drivers/crypto/mxc-scc.c b/drivers/crypto/mxc-scc.c
deleted file mode 100644
index 519086730791..000000000000
--- a/drivers/crypto/mxc-scc.c
+++ /dev/null
@@ -1,767 +0,0 @@
-/*
- * Copyright (C) 2016 Pengutronix, Steffen Trumtrar <kernel@pengutronix.de>
- *
- * The driver is based on information gathered from
- * drivers/mxc/security/mxc_scc.c which can be found in
- * the Freescale linux-2.6-imx.git in the imx_2.6.35_maintain branch.
- *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of the GNU General Public License
- * version 2, as published by the Free Software Foundation.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- *
- */
-#include <linux/clk.h>
-#include <linux/crypto.h>
-#include <linux/interrupt.h>
-#include <linux/io.h>
-#include <linux/irq.h>
-#include <linux/kernel.h>
-#include <linux/module.h>
-#include <linux/mutex.h>
-#include <linux/of.h>
-#include <linux/of_device.h>
-#include <linux/platform_device.h>
-
-#include <crypto/algapi.h>
-#include <crypto/des.h>
-
-/* Secure Memory (SCM) registers */
-#define SCC_SCM_RED_START		0x0000
-#define SCC_SCM_BLACK_START		0x0004
-#define SCC_SCM_LENGTH			0x0008
-#define SCC_SCM_CTRL			0x000C
-#define SCC_SCM_STATUS			0x0010
-#define SCC_SCM_ERROR_STATUS		0x0014
-#define SCC_SCM_INTR_CTRL		0x0018
-#define SCC_SCM_CFG			0x001C
-#define SCC_SCM_INIT_VECTOR_0		0x0020
-#define SCC_SCM_INIT_VECTOR_1		0x0024
-#define SCC_SCM_RED_MEMORY		0x0400
-#define SCC_SCM_BLACK_MEMORY		0x0800
-
-/* Security Monitor (SMN) Registers */
-#define SCC_SMN_STATUS			0x1000
-#define SCC_SMN_COMMAND		0x1004
-#define SCC_SMN_SEQ_START		0x1008
-#define SCC_SMN_SEQ_END		0x100C
-#define SCC_SMN_SEQ_CHECK		0x1010
-#define SCC_SMN_BIT_COUNT		0x1014
-#define SCC_SMN_BITBANK_INC_SIZE	0x1018
-#define SCC_SMN_BITBANK_DECREMENT	0x101C
-#define SCC_SMN_COMPARE_SIZE		0x1020
-#define SCC_SMN_PLAINTEXT_CHECK	0x1024
-#define SCC_SMN_CIPHERTEXT_CHECK	0x1028
-#define SCC_SMN_TIMER_IV		0x102C
-#define SCC_SMN_TIMER_CONTROL		0x1030
-#define SCC_SMN_DEBUG_DETECT_STAT	0x1034
-#define SCC_SMN_TIMER			0x1038
-
-#define SCC_SCM_CTRL_START_CIPHER	BIT(2)
-#define SCC_SCM_CTRL_CBC_MODE		BIT(1)
-#define SCC_SCM_CTRL_DECRYPT_MODE	BIT(0)
-
-#define SCC_SCM_STATUS_LEN_ERR		BIT(12)
-#define SCC_SCM_STATUS_SMN_UNBLOCKED	BIT(11)
-#define SCC_SCM_STATUS_CIPHERING_DONE	BIT(10)
-#define SCC_SCM_STATUS_ZEROIZING_DONE	BIT(9)
-#define SCC_SCM_STATUS_INTR_STATUS	BIT(8)
-#define SCC_SCM_STATUS_SEC_KEY		BIT(7)
-#define SCC_SCM_STATUS_INTERNAL_ERR	BIT(6)
-#define SCC_SCM_STATUS_BAD_SEC_KEY	BIT(5)
-#define SCC_SCM_STATUS_ZEROIZE_FAIL	BIT(4)
-#define SCC_SCM_STATUS_SMN_BLOCKED	BIT(3)
-#define SCC_SCM_STATUS_CIPHERING	BIT(2)
-#define SCC_SCM_STATUS_ZEROIZING	BIT(1)
-#define SCC_SCM_STATUS_BUSY		BIT(0)
-
-#define SCC_SMN_STATUS_STATE_MASK	0x0000001F
-#define SCC_SMN_STATE_START		0x0
-/* The SMN is zeroizing its RAM during reset */
-#define SCC_SMN_STATE_ZEROIZE_RAM	0x5
-/* SMN has passed internal checks */
-#define SCC_SMN_STATE_HEALTH_CHECK	0x6
-/* Fatal Security Violation. SMN is locked, SCM is inoperative. */
-#define SCC_SMN_STATE_FAIL		0x9
-/* SCC is in secure state. SCM is using secret key. */
-#define SCC_SMN_STATE_SECURE		0xA
-/* SCC is not secure. SCM is using default key. */
-#define SCC_SMN_STATE_NON_SECURE	0xC
-
-#define SCC_SCM_INTR_CTRL_ZEROIZE_MEM	BIT(2)
-#define SCC_SCM_INTR_CTRL_CLR_INTR	BIT(1)
-#define SCC_SCM_INTR_CTRL_MASK_INTR	BIT(0)
-
-/* Size, in blocks, of Red memory. */
-#define SCC_SCM_CFG_BLACK_SIZE_MASK	0x07fe0000
-#define SCC_SCM_CFG_BLACK_SIZE_SHIFT	17
-/* Size, in blocks, of Black memory. */
-#define SCC_SCM_CFG_RED_SIZE_MASK	0x0001ff80
-#define SCC_SCM_CFG_RED_SIZE_SHIFT	7
-/* Number of bytes per block. */
-#define SCC_SCM_CFG_BLOCK_SIZE_MASK	0x0000007f
-
-#define SCC_SMN_COMMAND_TAMPER_LOCK	BIT(4)
-#define SCC_SMN_COMMAND_CLR_INTR	BIT(3)
-#define SCC_SMN_COMMAND_CLR_BIT_BANK	BIT(2)
-#define SCC_SMN_COMMAND_EN_INTR	BIT(1)
-#define SCC_SMN_COMMAND_SET_SOFTWARE_ALARM  BIT(0)
-
-#define SCC_KEY_SLOTS			20
-#define SCC_MAX_KEY_SIZE		32
-#define SCC_KEY_SLOT_SIZE		32
-
-#define SCC_CRC_CCITT_START		0xFFFF
-
-/*
- * Offset into each RAM of the base of the area which is not
- * used for Stored Keys.
- */
-#define SCC_NON_RESERVED_OFFSET	(SCC_KEY_SLOTS * SCC_KEY_SLOT_SIZE)
-
-/* Fixed padding for appending to plaintext to fill out a block */
-static char scc_block_padding[8] = { 0x80, 0, 0, 0, 0, 0, 0, 0 };
-
-enum mxc_scc_state {
-	SCC_STATE_OK,
-	SCC_STATE_UNIMPLEMENTED,
-	SCC_STATE_FAILED
-};
-
-struct mxc_scc {
-	struct device		*dev;
-	void __iomem		*base;
-	struct clk		*clk;
-	bool			hw_busy;
-	spinlock_t		lock;
-	struct crypto_queue	queue;
-	struct crypto_async_request *req;
-	int			block_size_bytes;
-	int			black_ram_size_blocks;
-	int			memory_size_bytes;
-	int			bytes_remaining;
-
-	void __iomem		*red_memory;
-	void __iomem		*black_memory;
-};
-
-struct mxc_scc_ctx {
-	struct mxc_scc		*scc;
-	struct scatterlist	*sg_src;
-	size_t			src_nents;
-	struct scatterlist	*sg_dst;
-	size_t			dst_nents;
-	unsigned int		offset;
-	unsigned int		size;
-	unsigned int		ctrl;
-};
-
-struct mxc_scc_crypto_tmpl {
-	struct mxc_scc *scc;
-	struct crypto_alg alg;
-};
-
-static int mxc_scc_get_data(struct mxc_scc_ctx *ctx,
-			    struct crypto_async_request *req)
-{
-	struct ablkcipher_request *ablkreq = ablkcipher_request_cast(req);
-	struct mxc_scc *scc = ctx->scc;
-	size_t len;
-	void __iomem *from;
-
-	if (ctx->ctrl & SCC_SCM_CTRL_DECRYPT_MODE)
-		from = scc->red_memory;
-	else
-		from = scc->black_memory;
-
-	dev_dbg(scc->dev, "pcopy: from 0x%p %zu bytes\n", from,
-		ctx->dst_nents * 8);
-	len = sg_pcopy_from_buffer(ablkreq->dst, ctx->dst_nents,
-				   from, ctx->size, ctx->offset);
-	if (!len) {
-		dev_err(scc->dev, "pcopy err from 0x%p (len=%zu)\n", from, len);
-		return -EINVAL;
-	}
-
-#ifdef DEBUG
-	print_hex_dump(KERN_ERR,
-		       "red memory@"__stringify(__LINE__)": ",
-		       DUMP_PREFIX_ADDRESS, 16, 4,
-		       scc->red_memory, ctx->size, 1);
-	print_hex_dump(KERN_ERR,
-		       "black memory@"__stringify(__LINE__)": ",
-		       DUMP_PREFIX_ADDRESS, 16, 4,
-		       scc->black_memory, ctx->size, 1);
-#endif
-
-	ctx->offset += len;
-
-	if (ctx->offset < ablkreq->nbytes)
-		return -EINPROGRESS;
-
-	return 0;
-}
-
-static int mxc_scc_ablkcipher_req_init(struct ablkcipher_request *req,
-				       struct mxc_scc_ctx *ctx)
-{
-	struct mxc_scc *scc = ctx->scc;
-	int nents;
-
-	nents = sg_nents_for_len(req->src, req->nbytes);
-	if (nents < 0) {
-		dev_err(scc->dev, "Invalid number of src SC");
-		return nents;
-	}
-	ctx->src_nents = nents;
-
-	nents = sg_nents_for_len(req->dst, req->nbytes);
-	if (nents < 0) {
-		dev_err(scc->dev, "Invalid number of dst SC");
-		return nents;
-	}
-	ctx->dst_nents = nents;
-
-	ctx->size = 0;
-	ctx->offset = 0;
-
-	return 0;
-}
-
-static int mxc_scc_ablkcipher_req_complete(struct crypto_async_request *req,
-					   struct mxc_scc_ctx *ctx,
-					   int result)
-{
-	struct ablkcipher_request *ablkreq = ablkcipher_request_cast(req);
-	struct mxc_scc *scc = ctx->scc;
-
-	scc->req = NULL;
-	scc->bytes_remaining = scc->memory_size_bytes;
-
-	if (ctx->ctrl & SCC_SCM_CTRL_CBC_MODE)
-		memcpy(ablkreq->info, scc->base + SCC_SCM_INIT_VECTOR_0,
-		       scc->block_size_bytes);
-
-	req->complete(req, result);
-	scc->hw_busy = false;
-
-	return 0;
-}
-
-static int mxc_scc_put_data(struct mxc_scc_ctx *ctx,
-			     struct ablkcipher_request *req)
-{
-	u8 padding_buffer[sizeof(u16) + sizeof(scc_block_padding)];
-	size_t len = min_t(size_t, req->nbytes - ctx->offset,
-			   ctx->scc->bytes_remaining);
-	unsigned int padding_byte_count = 0;
-	struct mxc_scc *scc = ctx->scc;
-	void __iomem *to;
-
-	if (ctx->ctrl & SCC_SCM_CTRL_DECRYPT_MODE)
-		to = scc->black_memory;
-	else
-		to = scc->red_memory;
-
-	if (ctx->ctrl & SCC_SCM_CTRL_CBC_MODE && req->info)
-		memcpy(scc->base + SCC_SCM_INIT_VECTOR_0, req->info,
-		       scc->block_size_bytes);
-
-	len = sg_pcopy_to_buffer(req->src, ctx->src_nents,
-				 to, len, ctx->offset);
-	if (!len) {
-		dev_err(scc->dev, "pcopy err to 0x%p (len=%zu)\n", to, len);
-		return -EINVAL;
-	}
-
-	ctx->size = len;
-
-#ifdef DEBUG
-	dev_dbg(scc->dev, "copied %d bytes to 0x%p\n", len, to);
-	print_hex_dump(KERN_ERR,
-		       "init vector0@"__stringify(__LINE__)": ",
-		       DUMP_PREFIX_ADDRESS, 16, 4,
-		       scc->base + SCC_SCM_INIT_VECTOR_0, scc->block_size_bytes,
-		       1);
-	print_hex_dump(KERN_ERR,
-		       "red memory@"__stringify(__LINE__)": ",
-		       DUMP_PREFIX_ADDRESS, 16, 4,
-		       scc->red_memory, ctx->size, 1);
-	print_hex_dump(KERN_ERR,
-		       "black memory@"__stringify(__LINE__)": ",
-		       DUMP_PREFIX_ADDRESS, 16, 4,
-		       scc->black_memory, ctx->size, 1);
-#endif
-
-	scc->bytes_remaining -= len;
-
-	padding_byte_count = len % scc->block_size_bytes;
-
-	if (padding_byte_count) {
-		memcpy(padding_buffer, scc_block_padding, padding_byte_count);
-		memcpy(to + len, padding_buffer, padding_byte_count);
-		ctx->size += padding_byte_count;
-	}
-
-#ifdef DEBUG
-	print_hex_dump(KERN_ERR,
-		       "data to encrypt@"__stringify(__LINE__)": ",
-		       DUMP_PREFIX_ADDRESS, 16, 4,
-		       to, ctx->size, 1);
-#endif
-
-	return 0;
-}
-
-static void mxc_scc_ablkcipher_next(struct mxc_scc_ctx *ctx,
-				    struct crypto_async_request *req)
-{
-	struct ablkcipher_request *ablkreq = ablkcipher_request_cast(req);
-	struct mxc_scc *scc = ctx->scc;
-	int err;
-
-	dev_dbg(scc->dev, "dispatch request (nbytes=%d, src=%p, dst=%p)\n",
-		ablkreq->nbytes, ablkreq->src, ablkreq->dst);
-
-	writel(0, scc->base + SCC_SCM_ERROR_STATUS);
-
-	err = mxc_scc_put_data(ctx, ablkreq);
-	if (err) {
-		mxc_scc_ablkcipher_req_complete(req, ctx, err);
-		return;
-	}
-
-	dev_dbg(scc->dev, "Start encryption (0x%x/0x%x)\n",
-		readl(scc->base + SCC_SCM_RED_START),
-		readl(scc->base + SCC_SCM_BLACK_START));
-
-	/* clear interrupt control registers */
-	writel(SCC_SCM_INTR_CTRL_CLR_INTR,
-	       scc->base + SCC_SCM_INTR_CTRL);
-
-	writel((ctx->size / ctx->scc->block_size_bytes) - 1,
-	       scc->base + SCC_SCM_LENGTH);
-
-	dev_dbg(scc->dev, "Process %d block(s) in 0x%p\n",
-		ctx->size / ctx->scc->block_size_bytes,
-		(ctx->ctrl & SCC_SCM_CTRL_DECRYPT_MODE) ? scc->black_memory :
-		scc->red_memory);
-
-	writel(ctx->ctrl, scc->base + SCC_SCM_CTRL);
-}
-
-static irqreturn_t mxc_scc_int(int irq, void *priv)
-{
-	struct crypto_async_request *req;
-	struct mxc_scc_ctx *ctx;
-	struct mxc_scc *scc = priv;
-	int status;
-	int ret;
-
-	status = readl(scc->base + SCC_SCM_STATUS);
-
-	/* clear interrupt control registers */
-	writel(SCC_SCM_INTR_CTRL_CLR_INTR, scc->base + SCC_SCM_INTR_CTRL);
-
-	if (status & SCC_SCM_STATUS_BUSY)
-		return IRQ_NONE;
-
-	req = scc->req;
-	if (req) {
-		ctx = crypto_tfm_ctx(req->tfm);
-		ret = mxc_scc_get_data(ctx, req);
-		if (ret != -EINPROGRESS)
-			mxc_scc_ablkcipher_req_complete(req, ctx, ret);
-		else
-			mxc_scc_ablkcipher_next(ctx, req);
-	}
-
-	return IRQ_HANDLED;
-}
-
-static int mxc_scc_cra_init(struct crypto_tfm *tfm)
-{
-	struct mxc_scc_ctx *ctx = crypto_tfm_ctx(tfm);
-	struct crypto_alg *alg = tfm->__crt_alg;
-	struct mxc_scc_crypto_tmpl *algt;
-
-	algt = container_of(alg, struct mxc_scc_crypto_tmpl, alg);
-
-	ctx->scc = algt->scc;
-	return 0;
-}
-
-static void mxc_scc_dequeue_req_unlocked(struct mxc_scc_ctx *ctx)
-{
-	struct crypto_async_request *req, *backlog;
-
-	if (ctx->scc->hw_busy)
-		return;
-
-	spin_lock_bh(&ctx->scc->lock);
-	backlog = crypto_get_backlog(&ctx->scc->queue);
-	req = crypto_dequeue_request(&ctx->scc->queue);
-	ctx->scc->req = req;
-	ctx->scc->hw_busy = true;
-	spin_unlock_bh(&ctx->scc->lock);
-
-	if (!req)
-		return;
-
-	if (backlog)
-		backlog->complete(backlog, -EINPROGRESS);
-
-	mxc_scc_ablkcipher_next(ctx, req);
-}
-
-static int mxc_scc_queue_req(struct mxc_scc_ctx *ctx,
-			     struct crypto_async_request *req)
-{
-	int ret;
-
-	spin_lock_bh(&ctx->scc->lock);
-	ret = crypto_enqueue_request(&ctx->scc->queue, req);
-	spin_unlock_bh(&ctx->scc->lock);
-
-	if (ret != -EINPROGRESS)
-		return ret;
-
-	mxc_scc_dequeue_req_unlocked(ctx);
-
-	return -EINPROGRESS;
-}
-
-static int mxc_scc_des3_op(struct mxc_scc_ctx *ctx,
-			   struct ablkcipher_request *req)
-{
-	int err;
-
-	err = mxc_scc_ablkcipher_req_init(req, ctx);
-	if (err)
-		return err;
-
-	return mxc_scc_queue_req(ctx, &req->base);
-}
-
-static int mxc_scc_ecb_des_encrypt(struct ablkcipher_request *req)
-{
-	struct crypto_ablkcipher *cipher = crypto_ablkcipher_reqtfm(req);
-	struct mxc_scc_ctx *ctx = crypto_ablkcipher_ctx(cipher);
-
-	ctx->ctrl = SCC_SCM_CTRL_START_CIPHER;
-
-	return mxc_scc_des3_op(ctx, req);
-}
-
-static int mxc_scc_ecb_des_decrypt(struct ablkcipher_request *req)
-{
-	struct crypto_ablkcipher *cipher = crypto_ablkcipher_reqtfm(req);
-	struct mxc_scc_ctx *ctx = crypto_ablkcipher_ctx(cipher);
-
-	ctx->ctrl = SCC_SCM_CTRL_START_CIPHER;
-	ctx->ctrl |= SCC_SCM_CTRL_DECRYPT_MODE;
-
-	return mxc_scc_des3_op(ctx, req);
-}
-
-static int mxc_scc_cbc_des_encrypt(struct ablkcipher_request *req)
-{
-	struct crypto_ablkcipher *cipher = crypto_ablkcipher_reqtfm(req);
-	struct mxc_scc_ctx *ctx = crypto_ablkcipher_ctx(cipher);
-
-	ctx->ctrl = SCC_SCM_CTRL_START_CIPHER;
-	ctx->ctrl |= SCC_SCM_CTRL_CBC_MODE;
-
-	return mxc_scc_des3_op(ctx, req);
-}
-
-static int mxc_scc_cbc_des_decrypt(struct ablkcipher_request *req)
-{
-	struct crypto_ablkcipher *cipher = crypto_ablkcipher_reqtfm(req);
-	struct mxc_scc_ctx *ctx = crypto_ablkcipher_ctx(cipher);
-
-	ctx->ctrl = SCC_SCM_CTRL_START_CIPHER;
-	ctx->ctrl |= SCC_SCM_CTRL_CBC_MODE;
-	ctx->ctrl |= SCC_SCM_CTRL_DECRYPT_MODE;
-
-	return mxc_scc_des3_op(ctx, req);
-}
-
-static void mxc_scc_hw_init(struct mxc_scc *scc)
-{
-	int offset;
-
-	offset = SCC_NON_RESERVED_OFFSET / scc->block_size_bytes;
-
-	/* Fill the RED_START register */
-	writel(offset, scc->base + SCC_SCM_RED_START);
-
-	/* Fill the BLACK_START register */
-	writel(offset, scc->base + SCC_SCM_BLACK_START);
-
-	scc->red_memory = scc->base + SCC_SCM_RED_MEMORY +
-			  SCC_NON_RESERVED_OFFSET;
-
-	scc->black_memory = scc->base + SCC_SCM_BLACK_MEMORY +
-			    SCC_NON_RESERVED_OFFSET;
-
-	scc->bytes_remaining = scc->memory_size_bytes;
-}
-
-static int mxc_scc_get_config(struct mxc_scc *scc)
-{
-	int config;
-
-	config = readl(scc->base + SCC_SCM_CFG);
-
-	scc->block_size_bytes = config & SCC_SCM_CFG_BLOCK_SIZE_MASK;
-
-	scc->black_ram_size_blocks = config & SCC_SCM_CFG_BLACK_SIZE_MASK;
-
-	scc->memory_size_bytes = (scc->block_size_bytes *
-				  scc->black_ram_size_blocks) -
-				  SCC_NON_RESERVED_OFFSET;
-
-	return 0;
-}
-
-static enum mxc_scc_state mxc_scc_get_state(struct mxc_scc *scc)
-{
-	enum mxc_scc_state state;
-	int status;
-
-	status = readl(scc->base + SCC_SMN_STATUS) &
-		       SCC_SMN_STATUS_STATE_MASK;
-
-	/* If in Health Check, try to bringup to secure state */
-	if (status & SCC_SMN_STATE_HEALTH_CHECK) {
-		/*
-		 * Write a simple algorithm to the Algorithm Sequence
-		 * Checker (ASC)
-		 */
-		writel(0xaaaa, scc->base + SCC_SMN_SEQ_START);
-		writel(0x5555, scc->base + SCC_SMN_SEQ_END);
-		writel(0x5555, scc->base + SCC_SMN_SEQ_CHECK);
-
-		status = readl(scc->base + SCC_SMN_STATUS) &
-			       SCC_SMN_STATUS_STATE_MASK;
-	}
-
-	switch (status) {
-	case SCC_SMN_STATE_NON_SECURE:
-	case SCC_SMN_STATE_SECURE:
-		state = SCC_STATE_OK;
-		break;
-	case SCC_SMN_STATE_FAIL:
-		state = SCC_STATE_FAILED;
-		break;
-	default:
-		state = SCC_STATE_UNIMPLEMENTED;
-		break;
-	}
-
-	return state;
-}
-
-static struct mxc_scc_crypto_tmpl scc_ecb_des = {
-	.alg = {
-		.cra_name = "ecb(des3_ede)",
-		.cra_driver_name = "ecb-des3-scc",
-		.cra_priority = 300,
-		.cra_flags = CRYPTO_ALG_TYPE_ABLKCIPHER,
-		.cra_blocksize = DES3_EDE_BLOCK_SIZE,
-		.cra_ctxsize = sizeof(struct mxc_scc_ctx),
-		.cra_alignmask = 0,
-		.cra_type = &crypto_ablkcipher_type,
-		.cra_module = THIS_MODULE,
-		.cra_init = mxc_scc_cra_init,
-		.cra_u.ablkcipher = {
-			.min_keysize = DES3_EDE_KEY_SIZE,
-			.max_keysize = DES3_EDE_KEY_SIZE,
-			.encrypt = mxc_scc_ecb_des_encrypt,
-			.decrypt = mxc_scc_ecb_des_decrypt,
-		}
-	}
-};
-
-static struct mxc_scc_crypto_tmpl scc_cbc_des = {
-	.alg = {
-		.cra_name = "cbc(des3_ede)",
-		.cra_driver_name = "cbc-des3-scc",
-		.cra_priority = 300,
-		.cra_flags = CRYPTO_ALG_TYPE_ABLKCIPHER,
-		.cra_blocksize = DES3_EDE_BLOCK_SIZE,
-		.cra_ctxsize = sizeof(struct mxc_scc_ctx),
-		.cra_alignmask = 0,
-		.cra_type = &crypto_ablkcipher_type,
-		.cra_module = THIS_MODULE,
-		.cra_init = mxc_scc_cra_init,
-		.cra_u.ablkcipher = {
-			.min_keysize = DES3_EDE_KEY_SIZE,
-			.max_keysize = DES3_EDE_KEY_SIZE,
-			.encrypt = mxc_scc_cbc_des_encrypt,
-			.decrypt = mxc_scc_cbc_des_decrypt,
-		}
-	}
-};
-
-static struct mxc_scc_crypto_tmpl *scc_crypto_algs[] = {
-	&scc_ecb_des,
-	&scc_cbc_des,
-};
-
-static int mxc_scc_crypto_register(struct mxc_scc *scc)
-{
-	int i;
-	int err = 0;
-
-	for (i = 0; i < ARRAY_SIZE(scc_crypto_algs); i++) {
-		scc_crypto_algs[i]->scc = scc;
-		err = crypto_register_alg(&scc_crypto_algs[i]->alg);
-		if (err)
-			goto err_out;
-	}
-
-	return 0;
-
-err_out:
-	while (--i >= 0)
-		crypto_unregister_alg(&scc_crypto_algs[i]->alg);
-
-	return err;
-}
-
-static void mxc_scc_crypto_unregister(void)
-{
-	unsigned int i;
-
-	for (i = 0; i < ARRAY_SIZE(scc_crypto_algs); i++)
-		crypto_unregister_alg(&scc_crypto_algs[i]->alg);
-}
-
-static int mxc_scc_probe(struct platform_device *pdev)
-{
-	struct device *dev = &pdev->dev;
-	struct resource *res;
-	struct mxc_scc *scc;
-	enum mxc_scc_state state;
-	int irq;
-	int ret;
-	int i;
-
-	scc = devm_kzalloc(dev, sizeof(*scc), GFP_KERNEL);
-	if (!scc)
-		return -ENOMEM;
-
-	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
-	scc->base = devm_ioremap_resource(dev, res);
-	if (IS_ERR(scc->base))
-		return PTR_ERR(scc->base);
-
-	scc->clk = devm_clk_get(&pdev->dev, "ipg");
-	if (IS_ERR(scc->clk)) {
-		dev_err(dev, "Could not get ipg clock\n");
-		return PTR_ERR(scc->clk);
-	}
-
-	ret = clk_prepare_enable(scc->clk);
-	if (ret)
-		return ret;
-
-	/* clear error status register */
-	writel(0x0, scc->base + SCC_SCM_ERROR_STATUS);
-
-	/* clear interrupt control registers */
-	writel(SCC_SCM_INTR_CTRL_CLR_INTR |
-	       SCC_SCM_INTR_CTRL_MASK_INTR,
-	       scc->base + SCC_SCM_INTR_CTRL);
-
-	writel(SCC_SMN_COMMAND_CLR_INTR |
-	       SCC_SMN_COMMAND_EN_INTR,
-	       scc->base + SCC_SMN_COMMAND);
-
-	scc->dev = dev;
-	platform_set_drvdata(pdev, scc);
-
-	ret = mxc_scc_get_config(scc);
-	if (ret)
-		goto err_out;
-
-	state = mxc_scc_get_state(scc);
-
-	if (state != SCC_STATE_OK) {
-		dev_err(dev, "SCC in unusable state %d\n", state);
-		ret = -EINVAL;
-		goto err_out;
-	}
-
-	mxc_scc_hw_init(scc);
-
-	spin_lock_init(&scc->lock);
-	/* FIXME: calculate queue from RAM slots */
-	crypto_init_queue(&scc->queue, 50);
-
-	for (i = 0; i < 2; i++) {
-		irq = platform_get_irq(pdev, i);
-		if (irq < 0) {
-			dev_err(dev, "failed to get irq resource: %d\n", irq);
-			ret = irq;
-			goto err_out;
-		}
-
-		ret = devm_request_threaded_irq(dev, irq, NULL, mxc_scc_int,
-						IRQF_ONESHOT, dev_name(dev), scc);
-		if (ret)
-			goto err_out;
-	}
-
-	ret = mxc_scc_crypto_register(scc);
-	if (ret) {
-		dev_err(dev, "could not register algorithms");
-		goto err_out;
-	}
-
-	dev_info(dev, "registered successfully.\n");
-
-	return 0;
-
-err_out:
-	clk_disable_unprepare(scc->clk);
-
-	return ret;
-}
-
-static int mxc_scc_remove(struct platform_device *pdev)
-{
-	struct mxc_scc *scc = platform_get_drvdata(pdev);
-
-	mxc_scc_crypto_unregister();
-
-	clk_disable_unprepare(scc->clk);
-
-	return 0;
-}
-
-static const struct of_device_id mxc_scc_dt_ids[] = {
-	{ .compatible = "fsl,imx25-scc", .data = NULL, },
-	{ /* sentinel */ }
-};
-MODULE_DEVICE_TABLE(of, mxc_scc_dt_ids);
-
-static struct platform_driver mxc_scc_driver = {
-	.probe	= mxc_scc_probe,
-	.remove	= mxc_scc_remove,
-	.driver	= {
-		.name		= "mxc-scc",
-		.of_match_table	= mxc_scc_dt_ids,
-	},
-};
-
-module_platform_driver(mxc_scc_driver);
-MODULE_AUTHOR("Steffen Trumtrar <kernel@pengutronix.de>");
-MODULE_DESCRIPTION("Freescale i.MX25 SCC Crypto driver");
-MODULE_LICENSE("GPL v2");
diff --git a/drivers/crypto/mxs-dcp.c b/drivers/crypto/mxs-dcp.c
index a2105cf33abb..b4429891e368 100644
--- a/drivers/crypto/mxs-dcp.c
+++ b/drivers/crypto/mxs-dcp.c
@@ -471,7 +471,7 @@ static int mxs_dcp_aes_enqueue(struct ablkcipher_request *req, int enc, int ecb)
 
 	wake_up_process(sdcp->thread[actx->chan]);
 
-	return -EINPROGRESS;
+	return ret;
 }
 
 static int mxs_dcp_aes_ecb_decrypt(struct ablkcipher_request *req)
@@ -700,11 +700,7 @@ static int dcp_chan_thread_sha(void *data)
 
 	struct crypto_async_request *backlog;
 	struct crypto_async_request *arq;
-
-	struct dcp_sha_req_ctx *rctx;
-
-	struct ahash_request *req;
-	int ret, fini;
+	int ret;
 
 	while (!kthread_should_stop()) {
 		set_current_state(TASK_INTERRUPTIBLE);
@@ -725,11 +721,7 @@ static int dcp_chan_thread_sha(void *data)
 			backlog->complete(backlog, -EINPROGRESS);
 
 		if (arq) {
-			req = ahash_request_cast(arq);
-			rctx = ahash_request_ctx(req);
-
 			ret = dcp_sha_req_to_buf(arq);
-			fini = rctx->fini;
 			arq->complete(arq, ret);
 		}
 	}
@@ -797,7 +789,7 @@ static int dcp_sha_update_fx(struct ahash_request *req, int fini)
 	wake_up_process(sdcp->thread[actx->chan]);
 	mutex_unlock(&actx->mutex);
 
-	return -EINPROGRESS;
+	return ret;
 }
 
 static int dcp_sha_update(struct ahash_request *req)
diff --git a/drivers/crypto/n2_core.c b/drivers/crypto/n2_core.c
index 9450c41211b2..0d5d3d8eb680 100644
--- a/drivers/crypto/n2_core.c
+++ b/drivers/crypto/n2_core.c
@@ -469,8 +469,6 @@ static int n2_hmac_async_setkey(struct crypto_ahash *tfm, const u8 *key,
 		return err;
 
 	shash->tfm = child_shash;
-	shash->flags = crypto_ahash_get_flags(tfm) &
-		CRYPTO_TFM_REQ_MAY_SLEEP;
 
 	bs = crypto_shash_blocksize(child_shash);
 	ds = crypto_shash_digestsize(child_shash);
@@ -788,13 +786,18 @@ static int n2_3des_setkey(struct crypto_ablkcipher *cipher, const u8 *key,
 	struct crypto_tfm *tfm = crypto_ablkcipher_tfm(cipher);
 	struct n2_cipher_context *ctx = crypto_tfm_ctx(tfm);
 	struct n2_cipher_alg *n2alg = n2_cipher_alg(tfm);
+	u32 flags;
+	int err;
+
+	flags = crypto_ablkcipher_get_flags(cipher);
+	err = __des3_verify_key(&flags, key);
+	if (unlikely(err)) {
+		crypto_ablkcipher_set_flags(cipher, flags);
+		return err;
+	}
 
 	ctx->enc_type = n2alg->enc_type;
 
-	if (keylen != (3 * DES_KEY_SIZE)) {
-		crypto_ablkcipher_set_flags(cipher, CRYPTO_TFM_RES_BAD_KEY_LEN);
-		return -EINVAL;
-	}
 	ctx->key_len = keylen;
 	memcpy(ctx->key.des3, key, keylen);
 	return 0;
diff --git a/drivers/crypto/nx/nx-842-pseries.c b/drivers/crypto/nx/nx-842-pseries.c
index 66869976cfa2..57932848361b 100644
--- a/drivers/crypto/nx/nx-842-pseries.c
+++ b/drivers/crypto/nx/nx-842-pseries.c
@@ -296,7 +296,7 @@ static int nx842_pseries_compress(const unsigned char *in, unsigned int inlen,
 	struct nx842_workmem *workmem;
 	struct nx842_scatterlist slin, slout;
 	struct nx_csbcpb *csbcpb;
-	int ret = 0, max_sync_size;
+	int ret = 0;
 	unsigned long inbuf, outbuf;
 	struct vio_pfo_op op = {
 		.done = NULL,
@@ -319,7 +319,6 @@ static int nx842_pseries_compress(const unsigned char *in, unsigned int inlen,
 		rcu_read_unlock();
 		return -ENODEV;
 	}
-	max_sync_size = local_devdata->max_sync_size;
 	dev = local_devdata->dev;
 
 	/* Init scatterlist */
@@ -427,7 +426,7 @@ static int nx842_pseries_decompress(const unsigned char *in, unsigned int inlen,
 	struct nx842_workmem *workmem;
 	struct nx842_scatterlist slin, slout;
 	struct nx_csbcpb *csbcpb;
-	int ret = 0, max_sync_size;
+	int ret = 0;
 	unsigned long inbuf, outbuf;
 	struct vio_pfo_op op = {
 		.done = NULL,
@@ -451,7 +450,6 @@ static int nx842_pseries_decompress(const unsigned char *in, unsigned int inlen,
 		rcu_read_unlock();
 		return -ENODEV;
 	}
-	max_sync_size = local_devdata->max_sync_size;
 	dev = local_devdata->dev;
 
 	workmem = PTR_ALIGN(wmem, WORKMEM_ALIGN);
diff --git a/drivers/crypto/nx/nx-842.c b/drivers/crypto/nx/nx-842.c
index d94e25df503b..f06565df2a12 100644
--- a/drivers/crypto/nx/nx-842.c
+++ b/drivers/crypto/nx/nx-842.c
@@ -353,7 +353,7 @@ static int decompress(struct nx842_crypto_ctx *ctx,
 	unsigned int adj_slen = slen;
 	u8 *src = p->in, *dst = p->out;
 	u16 padding = be16_to_cpu(g->padding);
-	int ret, spadding = 0, dpadding = 0;
+	int ret, spadding = 0;
 	ktime_t timeout;
 
 	if (!slen || !required_len)
@@ -413,7 +413,6 @@ usesw:
 		spadding = 0;
 		dst = p->out;
 		dlen = p->oremain;
-		dpadding = 0;
 		if (dlen < required_len) { /* have ignore bytes */
 			dst = ctx->dbounce;
 			dlen = BOUNCE_BUFFER_SIZE;
diff --git a/drivers/crypto/nx/nx-aes-xcbc.c b/drivers/crypto/nx/nx-aes-xcbc.c
index ad3358e74f5c..8f5820b78a83 100644
--- a/drivers/crypto/nx/nx-aes-xcbc.c
+++ b/drivers/crypto/nx/nx-aes-xcbc.c
@@ -105,8 +105,7 @@ static int nx_xcbc_empty(struct shash_desc *desc, u8 *out)
 	nx_ctx->op.inlen = (nx_ctx->in_sg - in_sg) * sizeof(struct nx_sg);
 	nx_ctx->op.outlen = (nx_ctx->out_sg - out_sg) * sizeof(struct nx_sg);
 
-	rc = nx_hcall_sync(nx_ctx, &nx_ctx->op,
-			   desc->flags & CRYPTO_TFM_REQ_MAY_SLEEP);
+	rc = nx_hcall_sync(nx_ctx, &nx_ctx->op, 0);
 	if (rc)
 		goto out;
 	atomic_inc(&(nx_ctx->stats->aes_ops));
@@ -134,8 +133,7 @@ static int nx_xcbc_empty(struct shash_desc *desc, u8 *out)
 	nx_ctx->op.inlen = (nx_ctx->in_sg - in_sg) * sizeof(struct nx_sg);
 	nx_ctx->op.outlen = (nx_ctx->out_sg - out_sg) * sizeof(struct nx_sg);
 
-	rc = nx_hcall_sync(nx_ctx, &nx_ctx->op,
-			   desc->flags & CRYPTO_TFM_REQ_MAY_SLEEP);
+	rc = nx_hcall_sync(nx_ctx, &nx_ctx->op, 0);
 	if (rc)
 		goto out;
 	atomic_inc(&(nx_ctx->stats->aes_ops));
@@ -279,8 +277,7 @@ static int nx_xcbc_update(struct shash_desc *desc,
 			goto out;
 		}
 
-		rc = nx_hcall_sync(nx_ctx, &nx_ctx->op,
-			   desc->flags & CRYPTO_TFM_REQ_MAY_SLEEP);
+		rc = nx_hcall_sync(nx_ctx, &nx_ctx->op, 0);
 		if (rc)
 			goto out;
 
@@ -361,8 +358,7 @@ static int nx_xcbc_final(struct shash_desc *desc, u8 *out)
 		goto out;
 	}
 
-	rc = nx_hcall_sync(nx_ctx, &nx_ctx->op,
-			   desc->flags & CRYPTO_TFM_REQ_MAY_SLEEP);
+	rc = nx_hcall_sync(nx_ctx, &nx_ctx->op, 0);
 	if (rc)
 		goto out;
 
diff --git a/drivers/crypto/nx/nx-sha256.c b/drivers/crypto/nx/nx-sha256.c
index a6764af83c6d..e06f0431dee5 100644
--- a/drivers/crypto/nx/nx-sha256.c
+++ b/drivers/crypto/nx/nx-sha256.c
@@ -162,8 +162,7 @@ static int nx_sha256_update(struct shash_desc *desc, const u8 *data,
 			goto out;
 		}
 
-		rc = nx_hcall_sync(nx_ctx, &nx_ctx->op,
-				   desc->flags & CRYPTO_TFM_REQ_MAY_SLEEP);
+		rc = nx_hcall_sync(nx_ctx, &nx_ctx->op, 0);
 		if (rc)
 			goto out;
 
@@ -243,8 +242,7 @@ static int nx_sha256_final(struct shash_desc *desc, u8 *out)
 		goto out;
 	}
 
-	rc = nx_hcall_sync(nx_ctx, &nx_ctx->op,
-			   desc->flags & CRYPTO_TFM_REQ_MAY_SLEEP);
+	rc = nx_hcall_sync(nx_ctx, &nx_ctx->op, 0);
 	if (rc)
 		goto out;
 
diff --git a/drivers/crypto/nx/nx-sha512.c b/drivers/crypto/nx/nx-sha512.c
index 92956bc6e45e..0293b17903d0 100644
--- a/drivers/crypto/nx/nx-sha512.c
+++ b/drivers/crypto/nx/nx-sha512.c
@@ -166,8 +166,7 @@ static int nx_sha512_update(struct shash_desc *desc, const u8 *data,
 			goto out;
 		}
 
-		rc = nx_hcall_sync(nx_ctx, &nx_ctx->op,
-				   desc->flags & CRYPTO_TFM_REQ_MAY_SLEEP);
+		rc = nx_hcall_sync(nx_ctx, &nx_ctx->op, 0);
 		if (rc)
 			goto out;
 
@@ -249,8 +248,7 @@ static int nx_sha512_final(struct shash_desc *desc, u8 *out)
 		goto out;
 	}
 
-	rc = nx_hcall_sync(nx_ctx, &nx_ctx->op,
-			   desc->flags & CRYPTO_TFM_REQ_MAY_SLEEP);
+	rc = nx_hcall_sync(nx_ctx, &nx_ctx->op, 0);
 	if (rc)
 		goto out;
 
diff --git a/drivers/crypto/omap-des.c b/drivers/crypto/omap-des.c
index 1ba2633e90d6..3d82d18ff810 100644
--- a/drivers/crypto/omap-des.c
+++ b/drivers/crypto/omap-des.c
@@ -656,9 +656,6 @@ static int omap_des_setkey(struct crypto_ablkcipher *cipher, const u8 *key,
 	struct omap_des_ctx *ctx = crypto_ablkcipher_ctx(cipher);
 	struct crypto_tfm *tfm = crypto_ablkcipher_tfm(cipher);
 
-	if (keylen != DES_KEY_SIZE && keylen != (3*DES_KEY_SIZE))
-		return -EINVAL;
-
 	pr_debug("enter, keylen: %d\n", keylen);
 
 	/* Do we need to test against weak key? */
@@ -678,6 +675,28 @@ static int omap_des_setkey(struct crypto_ablkcipher *cipher, const u8 *key,
 	return 0;
 }
 
+static int omap_des3_setkey(struct crypto_ablkcipher *cipher, const u8 *key,
+			   unsigned int keylen)
+{
+	struct omap_des_ctx *ctx = crypto_ablkcipher_ctx(cipher);
+	u32 flags;
+	int err;
+
+	pr_debug("enter, keylen: %d\n", keylen);
+
+	flags = crypto_ablkcipher_get_flags(cipher);
+	err = __des3_verify_key(&flags, key);
+	if (unlikely(err)) {
+		crypto_ablkcipher_set_flags(cipher, flags);
+		return err;
+	}
+
+	memcpy(ctx->key, key, keylen);
+	ctx->keylen = keylen;
+
+	return 0;
+}
+
 static int omap_des_ecb_encrypt(struct ablkcipher_request *req)
 {
 	return omap_des_crypt(req, FLAGS_ENCRYPT);
@@ -788,7 +807,7 @@ static struct crypto_alg algs_ecb_cbc[] = {
 	.cra_u.ablkcipher = {
 		.min_keysize	= 3*DES_KEY_SIZE,
 		.max_keysize	= 3*DES_KEY_SIZE,
-		.setkey		= omap_des_setkey,
+		.setkey		= omap_des3_setkey,
 		.encrypt	= omap_des_ecb_encrypt,
 		.decrypt	= omap_des_ecb_decrypt,
 	}
@@ -811,7 +830,7 @@ static struct crypto_alg algs_ecb_cbc[] = {
 		.min_keysize	= 3*DES_KEY_SIZE,
 		.max_keysize	= 3*DES_KEY_SIZE,
 		.ivsize		= DES_BLOCK_SIZE,
-		.setkey		= omap_des_setkey,
+		.setkey		= omap_des3_setkey,
 		.encrypt	= omap_des_cbc_encrypt,
 		.decrypt	= omap_des_cbc_decrypt,
 	}
diff --git a/drivers/crypto/omap-sham.c b/drivers/crypto/omap-sham.c
index 0641185bd82f..51b20abac464 100644
--- a/drivers/crypto/omap-sham.c
+++ b/drivers/crypto/omap-sham.c
@@ -1055,7 +1055,6 @@ static int omap_sham_finish_hmac(struct ahash_request *req)
 	SHASH_DESC_ON_STACK(shash, bctx->shash);
 
 	shash->tfm = bctx->shash;
-	shash->flags = 0; /* not CRYPTO_TFM_REQ_MAY_SLEEP */
 
 	return crypto_shash_init(shash) ?:
 	       crypto_shash_update(shash, bctx->opad, bs) ?:
@@ -1226,7 +1225,6 @@ static int omap_sham_shash_digest(struct crypto_shash *tfm, u32 flags,
 	SHASH_DESC_ON_STACK(shash, tfm);
 
 	shash->tfm = tfm;
-	shash->flags = flags & CRYPTO_TFM_REQ_MAY_SLEEP;
 
 	return crypto_shash_digest(shash, data, len, out);
 }
diff --git a/drivers/crypto/padlock-sha.c b/drivers/crypto/padlock-sha.c
index 21e5cae0a1e0..e641481a3cd9 100644
--- a/drivers/crypto/padlock-sha.c
+++ b/drivers/crypto/padlock-sha.c
@@ -39,7 +39,6 @@ static int padlock_sha_init(struct shash_desc *desc)
 	struct padlock_sha_ctx *ctx = crypto_shash_ctx(desc->tfm);
 
 	dctx->fallback.tfm = ctx->fallback;
-	dctx->fallback.flags = desc->flags & CRYPTO_TFM_REQ_MAY_SLEEP;
 	return crypto_shash_init(&dctx->fallback);
 }
 
@@ -48,7 +47,6 @@ static int padlock_sha_update(struct shash_desc *desc,
 {
 	struct padlock_sha_desc *dctx = shash_desc_ctx(desc);
 
-	dctx->fallback.flags = desc->flags & CRYPTO_TFM_REQ_MAY_SLEEP;
 	return crypto_shash_update(&dctx->fallback, data, length);
 }
 
@@ -65,7 +63,6 @@ static int padlock_sha_import(struct shash_desc *desc, const void *in)
 	struct padlock_sha_ctx *ctx = crypto_shash_ctx(desc->tfm);
 
 	dctx->fallback.tfm = ctx->fallback;
-	dctx->fallback.flags = desc->flags & CRYPTO_TFM_REQ_MAY_SLEEP;
 	return crypto_shash_import(&dctx->fallback, in);
 }
 
@@ -91,7 +88,6 @@ static int padlock_sha1_finup(struct shash_desc *desc, const u8 *in,
 	unsigned int leftover;
 	int err;
 
-	dctx->fallback.flags = desc->flags & CRYPTO_TFM_REQ_MAY_SLEEP;
 	err = crypto_shash_export(&dctx->fallback, &state);
 	if (err)
 		goto out;
@@ -153,7 +149,6 @@ static int padlock_sha256_finup(struct shash_desc *desc, const u8 *in,
 	unsigned int leftover;
 	int err;
 
-	dctx->fallback.flags = desc->flags & CRYPTO_TFM_REQ_MAY_SLEEP;
 	err = crypto_shash_export(&dctx->fallback, &state);
 	if (err)
 		goto out;
diff --git a/drivers/crypto/picoxcell_crypto.c b/drivers/crypto/picoxcell_crypto.c
index 1b3acdeffede..05b89e703903 100644
--- a/drivers/crypto/picoxcell_crypto.c
+++ b/drivers/crypto/picoxcell_crypto.c
@@ -753,11 +753,6 @@ static int spacc_des_setkey(struct crypto_ablkcipher *cipher, const u8 *key,
 	struct spacc_ablk_ctx *ctx = crypto_tfm_ctx(tfm);
 	u32 tmp[DES_EXPKEY_WORDS];
 
-	if (len > DES3_EDE_KEY_SIZE) {
-		crypto_ablkcipher_set_flags(cipher, CRYPTO_TFM_RES_BAD_KEY_LEN);
-		return -EINVAL;
-	}
-
 	if (unlikely(!des_ekey(tmp, key)) &&
 	    (crypto_ablkcipher_get_flags(cipher) &
 	     CRYPTO_TFM_REQ_FORBID_WEAK_KEYS)) {
@@ -772,6 +767,30 @@ static int spacc_des_setkey(struct crypto_ablkcipher *cipher, const u8 *key,
 }
 
 /*
+ * Set the 3DES key for a block cipher transform. This also performs weak key
+ * checking if the transform has requested it.
+ */
+static int spacc_des3_setkey(struct crypto_ablkcipher *cipher, const u8 *key,
+			     unsigned int len)
+{
+	struct spacc_ablk_ctx *ctx = crypto_ablkcipher_ctx(cipher);
+	u32 flags;
+	int err;
+
+	flags = crypto_ablkcipher_get_flags(cipher);
+	err = __des3_verify_key(&flags, key);
+	if (unlikely(err)) {
+		crypto_ablkcipher_set_flags(cipher, flags);
+		return err;
+	}
+
+	memcpy(ctx->key, key, len);
+	ctx->key_len = len;
+
+	return 0;
+}
+
+/*
  * Set the key for an AES block cipher. Some key lengths are not supported in
  * hardware so this must also check whether a fallback is needed.
  */
@@ -1196,7 +1215,7 @@ static const struct dev_pm_ops spacc_pm_ops = {
 
 static inline struct spacc_engine *spacc_dev_to_engine(struct device *dev)
 {
-	return dev ? platform_get_drvdata(to_platform_device(dev)) : NULL;
+	return dev ? dev_get_drvdata(dev) : NULL;
 }
 
 static ssize_t spacc_stat_irq_thresh_show(struct device *dev,
@@ -1353,7 +1372,7 @@ static struct spacc_alg ipsec_engine_algs[] = {
 			.cra_type = &crypto_ablkcipher_type,
 			.cra_module = THIS_MODULE,
 			.cra_ablkcipher = {
-				.setkey = spacc_des_setkey,
+				.setkey = spacc_des3_setkey,
 				.encrypt = spacc_ablk_encrypt,
 				.decrypt = spacc_ablk_decrypt,
 				.min_keysize = DES3_EDE_KEY_SIZE,
@@ -1380,7 +1399,7 @@ static struct spacc_alg ipsec_engine_algs[] = {
 			.cra_type = &crypto_ablkcipher_type,
 			.cra_module = THIS_MODULE,
 			.cra_ablkcipher = {
-				.setkey = spacc_des_setkey,
+				.setkey = spacc_des3_setkey,
 				.encrypt = spacc_ablk_encrypt,
 				.decrypt = spacc_ablk_decrypt,
 				.min_keysize = DES3_EDE_KEY_SIZE,
diff --git a/drivers/crypto/qat/qat_common/qat_algs.c b/drivers/crypto/qat/qat_common/qat_algs.c
index 975c75198f56..c8d401646902 100644
--- a/drivers/crypto/qat/qat_common/qat_algs.c
+++ b/drivers/crypto/qat/qat_common/qat_algs.c
@@ -164,7 +164,6 @@ static int qat_alg_do_precomputes(struct icp_qat_hw_auth_algo_blk *hash,
 	memset(ctx->ipad, 0, block_size);
 	memset(ctx->opad, 0, block_size);
 	shash->tfm = ctx->hash_tfm;
-	shash->flags = 0x0;
 
 	if (auth_keylen > block_size) {
 		int ret = crypto_shash_digest(shash, auth_key,
diff --git a/drivers/crypto/qat/qat_common/qat_asym_algs.c b/drivers/crypto/qat/qat_common/qat_asym_algs.c
index c9f324730d71..692a7aaee749 100644
--- a/drivers/crypto/qat/qat_common/qat_asym_algs.c
+++ b/drivers/crypto/qat/qat_common/qat_asym_algs.c
@@ -1300,8 +1300,6 @@ static void qat_rsa_exit_tfm(struct crypto_akcipher *tfm)
 static struct akcipher_alg rsa = {
 	.encrypt = qat_rsa_enc,
 	.decrypt = qat_rsa_dec,
-	.sign = qat_rsa_dec,
-	.verify = qat_rsa_enc,
 	.set_pub_key = qat_rsa_setpubkey,
 	.set_priv_key = qat_rsa_setprivkey,
 	.max_size = qat_rsa_max_size,
diff --git a/drivers/crypto/qce/ablkcipher.c b/drivers/crypto/qce/ablkcipher.c
index 154b6baa124e..8d3493855a70 100644
--- a/drivers/crypto/qce/ablkcipher.c
+++ b/drivers/crypto/qce/ablkcipher.c
@@ -198,6 +198,25 @@ weakkey:
 	return -EINVAL;
 }
 
+static int qce_des3_setkey(struct crypto_ablkcipher *ablk, const u8 *key,
+			   unsigned int keylen)
+{
+	struct qce_cipher_ctx *ctx = crypto_ablkcipher_ctx(ablk);
+	u32 flags;
+	int err;
+
+	flags = crypto_ablkcipher_get_flags(ablk);
+	err = __des3_verify_key(&flags, key);
+	if (unlikely(err)) {
+		crypto_ablkcipher_set_flags(ablk, flags);
+		return err;
+	}
+
+	ctx->enc_keylen = keylen;
+	memcpy(ctx->enc_key, key, keylen);
+	return 0;
+}
+
 static int qce_ablkcipher_crypt(struct ablkcipher_request *req, int encrypt)
 {
 	struct crypto_tfm *tfm =
@@ -363,7 +382,8 @@ static int qce_ablkcipher_register_one(const struct qce_ablkcipher_def *def,
 	alg->cra_ablkcipher.ivsize = def->ivsize;
 	alg->cra_ablkcipher.min_keysize = def->min_keysize;
 	alg->cra_ablkcipher.max_keysize = def->max_keysize;
-	alg->cra_ablkcipher.setkey = qce_ablkcipher_setkey;
+	alg->cra_ablkcipher.setkey = IS_3DES(def->flags) ?
+				     qce_des3_setkey : qce_ablkcipher_setkey;
 	alg->cra_ablkcipher.encrypt = qce_ablkcipher_encrypt;
 	alg->cra_ablkcipher.decrypt = qce_ablkcipher_decrypt;
 
diff --git a/drivers/crypto/rockchip/rk3288_crypto_ablkcipher.c b/drivers/crypto/rockchip/rk3288_crypto_ablkcipher.c
index 02dac6ae7e53..313759521a0f 100644
--- a/drivers/crypto/rockchip/rk3288_crypto_ablkcipher.c
+++ b/drivers/crypto/rockchip/rk3288_crypto_ablkcipher.c
@@ -46,24 +46,36 @@ static int rk_aes_setkey(struct crypto_ablkcipher *cipher,
 	return 0;
 }
 
-static int rk_tdes_setkey(struct crypto_ablkcipher *cipher,
-			  const u8 *key, unsigned int keylen)
+static int rk_des_setkey(struct crypto_ablkcipher *cipher,
+			 const u8 *key, unsigned int keylen)
 {
 	struct crypto_tfm *tfm = crypto_ablkcipher_tfm(cipher);
 	struct rk_cipher_ctx *ctx = crypto_tfm_ctx(tfm);
 	u32 tmp[DES_EXPKEY_WORDS];
 
-	if (keylen != DES_KEY_SIZE && keylen != DES3_EDE_KEY_SIZE) {
-		crypto_ablkcipher_set_flags(cipher, CRYPTO_TFM_RES_BAD_KEY_LEN);
+	if (!des_ekey(tmp, key) &&
+	    (tfm->crt_flags & CRYPTO_TFM_REQ_FORBID_WEAK_KEYS)) {
+		tfm->crt_flags |= CRYPTO_TFM_RES_WEAK_KEY;
 		return -EINVAL;
 	}
 
-	if (keylen == DES_KEY_SIZE) {
-		if (!des_ekey(tmp, key) &&
-		    (tfm->crt_flags & CRYPTO_TFM_REQ_FORBID_WEAK_KEYS)) {
-			tfm->crt_flags |= CRYPTO_TFM_RES_WEAK_KEY;
-			return -EINVAL;
-		}
+	ctx->keylen = keylen;
+	memcpy_toio(ctx->dev->reg + RK_CRYPTO_TDES_KEY1_0, key, keylen);
+	return 0;
+}
+
+static int rk_tdes_setkey(struct crypto_ablkcipher *cipher,
+			  const u8 *key, unsigned int keylen)
+{
+	struct rk_cipher_ctx *ctx = crypto_ablkcipher_ctx(cipher);
+	u32 flags;
+	int err;
+
+	flags = crypto_ablkcipher_get_flags(cipher);
+	err = __des3_verify_key(&flags, key);
+	if (unlikely(err)) {
+		crypto_ablkcipher_set_flags(cipher, flags);
+		return err;
 	}
 
 	ctx->keylen = keylen;
@@ -250,9 +262,14 @@ static int rk_set_data_start(struct rk_crypto_info *dev)
 	u8 *src_last_blk = page_address(sg_page(dev->sg_src)) +
 		dev->sg_src->offset + dev->sg_src->length - ivsize;
 
-	/* store the iv that need to be updated in chain mode */
-	if (ctx->mode & RK_CRYPTO_DEC)
+	/* Store the iv that need to be updated in chain mode.
+	 * And update the IV buffer to contain the next IV for decryption mode.
+	 */
+	if (ctx->mode & RK_CRYPTO_DEC) {
 		memcpy(ctx->iv, src_last_blk, ivsize);
+		sg_pcopy_to_buffer(dev->first, dev->src_nents, req->info,
+				   ivsize, dev->total - ivsize);
+	}
 
 	err = dev->load_data(dev, dev->sg_src, dev->sg_dst);
 	if (!err)
@@ -288,13 +305,19 @@ static void rk_iv_copyback(struct rk_crypto_info *dev)
 	struct ablkcipher_request *req =
 		ablkcipher_request_cast(dev->async_req);
 	struct crypto_ablkcipher *tfm = crypto_ablkcipher_reqtfm(req);
+	struct rk_cipher_ctx *ctx = crypto_ablkcipher_ctx(tfm);
 	u32 ivsize = crypto_ablkcipher_ivsize(tfm);
 
-	if (ivsize == DES_BLOCK_SIZE)
-		memcpy_fromio(req->info, dev->reg + RK_CRYPTO_TDES_IV_0,
-			      ivsize);
-	else if (ivsize == AES_BLOCK_SIZE)
-		memcpy_fromio(req->info, dev->reg + RK_CRYPTO_AES_IV_0, ivsize);
+	/* Update the IV buffer to contain the next IV for encryption mode. */
+	if (!(ctx->mode & RK_CRYPTO_DEC)) {
+		if (dev->aligned) {
+			memcpy(req->info, sg_virt(dev->sg_dst) +
+				dev->sg_dst->length - ivsize, ivsize);
+		} else {
+			memcpy(req->info, dev->addr_vir +
+				dev->count - ivsize, ivsize);
+		}
+	}
 }
 
 static void rk_update_iv(struct rk_crypto_info *dev)
@@ -457,7 +480,7 @@ struct rk_crypto_tmp rk_ecb_des_alg = {
 		.cra_u.ablkcipher	= {
 			.min_keysize	= DES_KEY_SIZE,
 			.max_keysize	= DES_KEY_SIZE,
-			.setkey		= rk_tdes_setkey,
+			.setkey		= rk_des_setkey,
 			.encrypt	= rk_des_ecb_encrypt,
 			.decrypt	= rk_des_ecb_decrypt,
 		}
@@ -483,7 +506,7 @@ struct rk_crypto_tmp rk_cbc_des_alg = {
 			.min_keysize	= DES_KEY_SIZE,
 			.max_keysize	= DES_KEY_SIZE,
 			.ivsize		= DES_BLOCK_SIZE,
-			.setkey		= rk_tdes_setkey,
+			.setkey		= rk_des_setkey,
 			.encrypt	= rk_des_cbc_encrypt,
 			.decrypt	= rk_des_cbc_decrypt,
 		}
diff --git a/drivers/crypto/s5p-sss.c b/drivers/crypto/s5p-sss.c
index 1afdcb81d8ed..9ef25230c199 100644
--- a/drivers/crypto/s5p-sss.c
+++ b/drivers/crypto/s5p-sss.c
@@ -1534,7 +1534,6 @@ static int s5p_hash_shash_digest(struct crypto_shash *tfm, u32 flags,
 	SHASH_DESC_ON_STACK(shash, tfm);
 
 	shash->tfm = tfm;
-	shash->flags = flags & ~CRYPTO_TFM_REQ_MAY_SLEEP;
 
 	return crypto_shash_digest(shash, data, len, out);
 }
diff --git a/drivers/crypto/sahara.c b/drivers/crypto/sahara.c
index 8c32a3059b4a..fd11162a915e 100644
--- a/drivers/crypto/sahara.c
+++ b/drivers/crypto/sahara.c
@@ -354,7 +354,7 @@ static void sahara_decode_status(struct sahara_dev *dev, unsigned int status)
 {
 	u8 state;
 
-	if (!IS_ENABLED(DEBUG))
+	if (!__is_defined(DEBUG))
 		return;
 
 	state = SAHARA_STATUS_GET_STATE(status);
@@ -406,7 +406,7 @@ static void sahara_dump_descriptors(struct sahara_dev *dev)
 {
 	int i;
 
-	if (!IS_ENABLED(DEBUG))
+	if (!__is_defined(DEBUG))
 		return;
 
 	for (i = 0; i < SAHARA_MAX_HW_DESC; i++) {
@@ -427,7 +427,7 @@ static void sahara_dump_links(struct sahara_dev *dev)
 {
 	int i;
 
-	if (!IS_ENABLED(DEBUG))
+	if (!__is_defined(DEBUG))
 		return;
 
 	for (i = 0; i < SAHARA_MAX_HW_LINK; i++) {
diff --git a/drivers/crypto/stm32/Kconfig b/drivers/crypto/stm32/Kconfig
index 63aa78c0b12b..4491e2197d9f 100644
--- a/drivers/crypto/stm32/Kconfig
+++ b/drivers/crypto/stm32/Kconfig
@@ -24,6 +24,7 @@ config CRYPTO_DEV_STM32_CRYP
 	depends on ARCH_STM32
 	select CRYPTO_HASH
 	select CRYPTO_ENGINE
+	select CRYPTO_DES
 	help
           This enables support for the CRYP (AES/DES/TDES) hw accelerator which
 	  can be found on STMicroelectronics STM32 SOC.
diff --git a/drivers/crypto/stm32/stm32-cryp.c b/drivers/crypto/stm32/stm32-cryp.c
index 23b0b7bd64c7..cddcc97875b2 100644
--- a/drivers/crypto/stm32/stm32-cryp.c
+++ b/drivers/crypto/stm32/stm32-cryp.c
@@ -137,7 +137,6 @@ struct stm32_cryp {
 
 	struct crypto_engine    *engine;
 
-	struct mutex            lock; /* protects req / areq */
 	struct ablkcipher_request *req;
 	struct aead_request     *areq;
 
@@ -394,6 +393,23 @@ static void stm32_cryp_hw_write_iv(struct stm32_cryp *cryp, u32 *iv)
 	}
 }
 
+static void stm32_cryp_get_iv(struct stm32_cryp *cryp)
+{
+	struct ablkcipher_request *req = cryp->req;
+	u32 *tmp = req->info;
+
+	if (!tmp)
+		return;
+
+	*tmp++ = cpu_to_be32(stm32_cryp_read(cryp, CRYP_IV0LR));
+	*tmp++ = cpu_to_be32(stm32_cryp_read(cryp, CRYP_IV0RR));
+
+	if (is_aes(cryp)) {
+		*tmp++ = cpu_to_be32(stm32_cryp_read(cryp, CRYP_IV1LR));
+		*tmp++ = cpu_to_be32(stm32_cryp_read(cryp, CRYP_IV1RR));
+	}
+}
+
 static void stm32_cryp_hw_write_key(struct stm32_cryp *c)
 {
 	unsigned int i;
@@ -623,6 +639,9 @@ static void stm32_cryp_finish_req(struct stm32_cryp *cryp, int err)
 		/* Phase 4 : output tag */
 		err = stm32_cryp_read_auth_tag(cryp);
 
+	if (!err && (!(is_gcm(cryp) || is_ccm(cryp))))
+		stm32_cryp_get_iv(cryp);
+
 	if (cryp->sgs_copied) {
 		void *buf_in, *buf_out;
 		int pages, len;
@@ -645,18 +664,13 @@ static void stm32_cryp_finish_req(struct stm32_cryp *cryp, int err)
 	pm_runtime_mark_last_busy(cryp->dev);
 	pm_runtime_put_autosuspend(cryp->dev);
 
-	if (is_gcm(cryp) || is_ccm(cryp)) {
+	if (is_gcm(cryp) || is_ccm(cryp))
 		crypto_finalize_aead_request(cryp->engine, cryp->areq, err);
-		cryp->areq = NULL;
-	} else {
+	else
 		crypto_finalize_ablkcipher_request(cryp->engine, cryp->req,
 						   err);
-		cryp->req = NULL;
-	}
 
 	memset(cryp->ctx->key, 0, cryp->ctx->keylen);
-
-	mutex_unlock(&cryp->lock);
 }
 
 static int stm32_cryp_cpu_start(struct stm32_cryp *cryp)
@@ -753,19 +767,35 @@ static int stm32_cryp_aes_setkey(struct crypto_ablkcipher *tfm, const u8 *key,
 static int stm32_cryp_des_setkey(struct crypto_ablkcipher *tfm, const u8 *key,
 				 unsigned int keylen)
 {
+	u32 tmp[DES_EXPKEY_WORDS];
+
 	if (keylen != DES_KEY_SIZE)
 		return -EINVAL;
-	else
-		return stm32_cryp_setkey(tfm, key, keylen);
+
+	if ((crypto_ablkcipher_get_flags(tfm) &
+	     CRYPTO_TFM_REQ_FORBID_WEAK_KEYS) &&
+	    unlikely(!des_ekey(tmp, key))) {
+		crypto_ablkcipher_set_flags(tfm, CRYPTO_TFM_RES_WEAK_KEY);
+		return -EINVAL;
+	}
+
+	return stm32_cryp_setkey(tfm, key, keylen);
 }
 
 static int stm32_cryp_tdes_setkey(struct crypto_ablkcipher *tfm, const u8 *key,
 				  unsigned int keylen)
 {
-	if (keylen != (3 * DES_KEY_SIZE))
-		return -EINVAL;
-	else
-		return stm32_cryp_setkey(tfm, key, keylen);
+	u32 flags;
+	int err;
+
+	flags = crypto_ablkcipher_get_flags(tfm);
+	err = __des3_verify_key(&flags, key);
+	if (unlikely(err)) {
+		crypto_ablkcipher_set_flags(tfm, flags);
+		return err;
+	}
+
+	return stm32_cryp_setkey(tfm, key, keylen);
 }
 
 static int stm32_cryp_aes_aead_setkey(struct crypto_aead *tfm, const u8 *key,
@@ -917,8 +947,6 @@ static int stm32_cryp_prepare_req(struct ablkcipher_request *req,
 	if (!cryp)
 		return -ENODEV;
 
-	mutex_lock(&cryp->lock);
-
 	rctx = req ? ablkcipher_request_ctx(req) : aead_request_ctx(areq);
 	rctx->mode &= FLG_MODE_MASK;
 
@@ -930,6 +958,7 @@ static int stm32_cryp_prepare_req(struct ablkcipher_request *req,
 
 	if (req) {
 		cryp->req = req;
+		cryp->areq = NULL;
 		cryp->total_in = req->nbytes;
 		cryp->total_out = cryp->total_in;
 	} else {
@@ -955,6 +984,7 @@ static int stm32_cryp_prepare_req(struct ablkcipher_request *req,
 		 *          <---------- total_out ----------------->
 		 */
 		cryp->areq = areq;
+		cryp->req = NULL;
 		cryp->authsize = crypto_aead_authsize(crypto_aead_reqtfm(areq));
 		cryp->total_in = areq->assoclen + areq->cryptlen;
 		if (is_encrypt(cryp))
@@ -976,19 +1006,19 @@ static int stm32_cryp_prepare_req(struct ablkcipher_request *req,
 	if (cryp->in_sg_len < 0) {
 		dev_err(cryp->dev, "Cannot get in_sg_len\n");
 		ret = cryp->in_sg_len;
-		goto out;
+		return ret;
 	}
 
 	cryp->out_sg_len = sg_nents_for_len(cryp->out_sg, cryp->total_out);
 	if (cryp->out_sg_len < 0) {
 		dev_err(cryp->dev, "Cannot get out_sg_len\n");
 		ret = cryp->out_sg_len;
-		goto out;
+		return ret;
 	}
 
 	ret = stm32_cryp_copy_sgs(cryp);
 	if (ret)
-		goto out;
+		return ret;
 
 	scatterwalk_start(&cryp->in_walk, cryp->in_sg);
 	scatterwalk_start(&cryp->out_walk, cryp->out_sg);
@@ -1000,10 +1030,6 @@ static int stm32_cryp_prepare_req(struct ablkcipher_request *req,
 	}
 
 	ret = stm32_cryp_hw_init(cryp);
-out:
-	if (ret)
-		mutex_unlock(&cryp->lock);
-
 	return ret;
 }
 
@@ -1943,8 +1969,6 @@ static int stm32_cryp_probe(struct platform_device *pdev)
 
 	cryp->dev = dev;
 
-	mutex_init(&cryp->lock);
-
 	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
 	cryp->regs = devm_ioremap_resource(dev, res);
 	if (IS_ERR(cryp->regs))
diff --git a/drivers/crypto/stm32/stm32-hash.c b/drivers/crypto/stm32/stm32-hash.c
index 4a6cc8a3045d..bfc49e67124b 100644
--- a/drivers/crypto/stm32/stm32-hash.c
+++ b/drivers/crypto/stm32/stm32-hash.c
@@ -181,8 +181,6 @@ struct stm32_hash_dev {
 	u32			dma_mode;
 	u32			dma_maxburst;
 
-	spinlock_t		lock; /* lock to protect queue */
-
 	struct ahash_request	*req;
 	struct crypto_engine	*engine;
 
@@ -977,7 +975,7 @@ static int stm32_hash_export(struct ahash_request *req, void *out)
 
 	pm_runtime_get_sync(hdev->dev);
 
-	while (!(stm32_hash_read(hdev, HASH_SR) & HASH_SR_DATA_INPUT_READY))
+	while ((stm32_hash_read(hdev, HASH_SR) & HASH_SR_BUSY))
 		cpu_relax();
 
 	rctx->hw_context = kmalloc_array(3 + HASH_CSR_REGISTER_NUMBER,
diff --git a/drivers/crypto/sunxi-ss/sun4i-ss-cipher.c b/drivers/crypto/sunxi-ss/sun4i-ss-cipher.c
index 54fd714d53ca..b060a0810934 100644
--- a/drivers/crypto/sunxi-ss/sun4i-ss-cipher.c
+++ b/drivers/crypto/sunxi-ss/sun4i-ss-cipher.c
@@ -41,11 +41,6 @@ static int sun4i_ss_opti_poll(struct skcipher_request *areq)
 	if (!areq->cryptlen)
 		return 0;
 
-	if (!areq->iv) {
-		dev_err_ratelimited(ss->dev, "ERROR: Empty IV\n");
-		return -EINVAL;
-	}
-
 	if (!areq->src || !areq->dst) {
 		dev_err_ratelimited(ss->dev, "ERROR: Some SGs are NULL\n");
 		return -EINVAL;
@@ -134,6 +129,8 @@ static int sun4i_ss_cipher_poll(struct skcipher_request *areq)
 	struct scatterlist *out_sg = areq->dst;
 	unsigned int ivsize = crypto_skcipher_ivsize(tfm);
 	struct sun4i_cipher_req_ctx *ctx = skcipher_request_ctx(areq);
+	struct skcipher_alg *alg = crypto_skcipher_alg(tfm);
+	struct sun4i_ss_alg_template *algt;
 	u32 mode = ctx->mode;
 	/* when activating SS, the default FIFO space is SS_RX_DEFAULT(32) */
 	u32 rx_cnt = SS_RX_DEFAULT;
@@ -153,20 +150,20 @@ static int sun4i_ss_cipher_poll(struct skcipher_request *areq)
 	unsigned int obo = 0;	/* offset in bufo*/
 	unsigned int obl = 0;	/* length of data in bufo */
 	unsigned long flags;
+	bool need_fallback;
 
 	if (!areq->cryptlen)
 		return 0;
 
-	if (!areq->iv) {
-		dev_err_ratelimited(ss->dev, "ERROR: Empty IV\n");
-		return -EINVAL;
-	}
-
 	if (!areq->src || !areq->dst) {
 		dev_err_ratelimited(ss->dev, "ERROR: Some SGs are NULL\n");
 		return -EINVAL;
 	}
 
+	algt = container_of(alg, struct sun4i_ss_alg_template, alg.crypto);
+	if (areq->cryptlen % algt->alg.crypto.base.cra_blocksize)
+		need_fallback = true;
+
 	/*
 	 * if we have only SGs with size multiple of 4,
 	 * we can use the SS optimized function
@@ -182,9 +179,24 @@ static int sun4i_ss_cipher_poll(struct skcipher_request *areq)
 		out_sg = sg_next(out_sg);
 	}
 
-	if (no_chunk == 1)
+	if (no_chunk == 1 && !need_fallback)
 		return sun4i_ss_opti_poll(areq);
 
+	if (need_fallback) {
+		SYNC_SKCIPHER_REQUEST_ON_STACK(subreq, op->fallback_tfm);
+		skcipher_request_set_sync_tfm(subreq, op->fallback_tfm);
+		skcipher_request_set_callback(subreq, areq->base.flags, NULL,
+					      NULL);
+		skcipher_request_set_crypt(subreq, areq->src, areq->dst,
+					   areq->cryptlen, areq->iv);
+		if (ctx->mode & SS_DECRYPTION)
+			err = crypto_skcipher_decrypt(subreq);
+		else
+			err = crypto_skcipher_encrypt(subreq);
+		skcipher_request_zero(subreq);
+		return err;
+	}
+
 	spin_lock_irqsave(&ss->slock, flags);
 
 	for (i = 0; i < op->keylen; i += 4)
@@ -458,6 +470,7 @@ int sun4i_ss_cipher_init(struct crypto_tfm *tfm)
 {
 	struct sun4i_tfm_ctx *op = crypto_tfm_ctx(tfm);
 	struct sun4i_ss_alg_template *algt;
+	const char *name = crypto_tfm_alg_name(tfm);
 
 	memset(op, 0, sizeof(struct sun4i_tfm_ctx));
 
@@ -468,9 +481,22 @@ int sun4i_ss_cipher_init(struct crypto_tfm *tfm)
 	crypto_skcipher_set_reqsize(__crypto_skcipher_cast(tfm),
 				    sizeof(struct sun4i_cipher_req_ctx));
 
+	op->fallback_tfm = crypto_alloc_sync_skcipher(name, 0, CRYPTO_ALG_NEED_FALLBACK);
+	if (IS_ERR(op->fallback_tfm)) {
+		dev_err(op->ss->dev, "ERROR: Cannot allocate fallback for %s %ld\n",
+			name, PTR_ERR(op->fallback_tfm));
+		return PTR_ERR(op->fallback_tfm);
+	}
+
 	return 0;
 }
 
+void sun4i_ss_cipher_exit(struct crypto_tfm *tfm)
+{
+	struct sun4i_tfm_ctx *op = crypto_tfm_ctx(tfm);
+	crypto_free_sync_skcipher(op->fallback_tfm);
+}
+
 /* check and set the AES key, prepare the mode to be used */
 int sun4i_ss_aes_setkey(struct crypto_skcipher *tfm, const u8 *key,
 			unsigned int keylen)
@@ -495,7 +521,11 @@ int sun4i_ss_aes_setkey(struct crypto_skcipher *tfm, const u8 *key,
 	}
 	op->keylen = keylen;
 	memcpy(op->key, key, keylen);
-	return 0;
+
+	crypto_sync_skcipher_clear_flags(op->fallback_tfm, CRYPTO_TFM_REQ_MASK);
+	crypto_sync_skcipher_set_flags(op->fallback_tfm, tfm->base.crt_flags & CRYPTO_TFM_REQ_MASK);
+
+	return crypto_sync_skcipher_setkey(op->fallback_tfm, key, keylen);
 }
 
 /* check and set the DES key, prepare the mode to be used */
@@ -525,7 +555,11 @@ int sun4i_ss_des_setkey(struct crypto_skcipher *tfm, const u8 *key,
 
 	op->keylen = keylen;
 	memcpy(op->key, key, keylen);
-	return 0;
+
+	crypto_sync_skcipher_clear_flags(op->fallback_tfm, CRYPTO_TFM_REQ_MASK);
+	crypto_sync_skcipher_set_flags(op->fallback_tfm, tfm->base.crt_flags & CRYPTO_TFM_REQ_MASK);
+
+	return crypto_sync_skcipher_setkey(op->fallback_tfm, key, keylen);
 }
 
 /* check and set the 3DES key, prepare the mode to be used */
@@ -533,14 +567,18 @@ int sun4i_ss_des3_setkey(struct crypto_skcipher *tfm, const u8 *key,
 			 unsigned int keylen)
 {
 	struct sun4i_tfm_ctx *op = crypto_skcipher_ctx(tfm);
-	struct sun4i_ss_ctx *ss = op->ss;
+	int err;
+
+	err = des3_verify_key(tfm, key);
+	if (unlikely(err))
+		return err;
 
-	if (unlikely(keylen != 3 * DES_KEY_SIZE)) {
-		dev_err(ss->dev, "Invalid keylen %u\n", keylen);
-		crypto_skcipher_set_flags(tfm, CRYPTO_TFM_RES_BAD_KEY_LEN);
-		return -EINVAL;
-	}
 	op->keylen = keylen;
 	memcpy(op->key, key, keylen);
-	return 0;
+
+	crypto_sync_skcipher_clear_flags(op->fallback_tfm, CRYPTO_TFM_REQ_MASK);
+	crypto_sync_skcipher_set_flags(op->fallback_tfm, tfm->base.crt_flags & CRYPTO_TFM_REQ_MASK);
+
+	return crypto_sync_skcipher_setkey(op->fallback_tfm, key, keylen);
+
 }
diff --git a/drivers/crypto/sunxi-ss/sun4i-ss-core.c b/drivers/crypto/sunxi-ss/sun4i-ss-core.c
index 89adf9e0fed2..05b3d3c32f6d 100644
--- a/drivers/crypto/sunxi-ss/sun4i-ss-core.c
+++ b/drivers/crypto/sunxi-ss/sun4i-ss-core.c
@@ -92,11 +92,12 @@ static struct sun4i_ss_alg_template ss_algs[] = {
 			.cra_driver_name = "cbc-aes-sun4i-ss",
 			.cra_priority = 300,
 			.cra_blocksize = AES_BLOCK_SIZE,
-			.cra_flags = CRYPTO_ALG_KERN_DRIVER_ONLY,
+			.cra_flags = CRYPTO_ALG_KERN_DRIVER_ONLY | CRYPTO_ALG_NEED_FALLBACK,
 			.cra_ctxsize = sizeof(struct sun4i_tfm_ctx),
 			.cra_module = THIS_MODULE,
 			.cra_alignmask = 3,
 			.cra_init = sun4i_ss_cipher_init,
+			.cra_exit = sun4i_ss_cipher_exit,
 		}
 	}
 },
@@ -107,17 +108,17 @@ static struct sun4i_ss_alg_template ss_algs[] = {
 		.decrypt        = sun4i_ss_ecb_aes_decrypt,
 		.min_keysize	= AES_MIN_KEY_SIZE,
 		.max_keysize	= AES_MAX_KEY_SIZE,
-		.ivsize		= AES_BLOCK_SIZE,
 		.base = {
 			.cra_name = "ecb(aes)",
 			.cra_driver_name = "ecb-aes-sun4i-ss",
 			.cra_priority = 300,
 			.cra_blocksize = AES_BLOCK_SIZE,
-			.cra_flags = CRYPTO_ALG_KERN_DRIVER_ONLY,
+			.cra_flags = CRYPTO_ALG_KERN_DRIVER_ONLY | CRYPTO_ALG_NEED_FALLBACK,
 			.cra_ctxsize = sizeof(struct sun4i_tfm_ctx),
 			.cra_module = THIS_MODULE,
 			.cra_alignmask = 3,
 			.cra_init = sun4i_ss_cipher_init,
+			.cra_exit = sun4i_ss_cipher_exit,
 		}
 	}
 },
@@ -134,11 +135,12 @@ static struct sun4i_ss_alg_template ss_algs[] = {
 			.cra_driver_name = "cbc-des-sun4i-ss",
 			.cra_priority = 300,
 			.cra_blocksize = DES_BLOCK_SIZE,
-			.cra_flags = CRYPTO_ALG_KERN_DRIVER_ONLY,
+			.cra_flags = CRYPTO_ALG_KERN_DRIVER_ONLY | CRYPTO_ALG_NEED_FALLBACK,
 			.cra_ctxsize = sizeof(struct sun4i_req_ctx),
 			.cra_module = THIS_MODULE,
 			.cra_alignmask = 3,
 			.cra_init = sun4i_ss_cipher_init,
+			.cra_exit = sun4i_ss_cipher_exit,
 		}
 	}
 },
@@ -154,11 +156,12 @@ static struct sun4i_ss_alg_template ss_algs[] = {
 			.cra_driver_name = "ecb-des-sun4i-ss",
 			.cra_priority = 300,
 			.cra_blocksize = DES_BLOCK_SIZE,
-			.cra_flags = CRYPTO_ALG_KERN_DRIVER_ONLY,
+			.cra_flags = CRYPTO_ALG_KERN_DRIVER_ONLY | CRYPTO_ALG_NEED_FALLBACK,
 			.cra_ctxsize = sizeof(struct sun4i_req_ctx),
 			.cra_module = THIS_MODULE,
 			.cra_alignmask = 3,
 			.cra_init = sun4i_ss_cipher_init,
+			.cra_exit = sun4i_ss_cipher_exit,
 		}
 	}
 },
@@ -175,11 +178,12 @@ static struct sun4i_ss_alg_template ss_algs[] = {
 			.cra_driver_name = "cbc-des3-sun4i-ss",
 			.cra_priority = 300,
 			.cra_blocksize = DES3_EDE_BLOCK_SIZE,
-			.cra_flags = CRYPTO_ALG_KERN_DRIVER_ONLY,
+			.cra_flags = CRYPTO_ALG_KERN_DRIVER_ONLY | CRYPTO_ALG_NEED_FALLBACK,
 			.cra_ctxsize = sizeof(struct sun4i_req_ctx),
 			.cra_module = THIS_MODULE,
 			.cra_alignmask = 3,
 			.cra_init = sun4i_ss_cipher_init,
+			.cra_exit = sun4i_ss_cipher_exit,
 		}
 	}
 },
@@ -190,16 +194,17 @@ static struct sun4i_ss_alg_template ss_algs[] = {
 		.decrypt        = sun4i_ss_ecb_des3_decrypt,
 		.min_keysize    = DES3_EDE_KEY_SIZE,
 		.max_keysize    = DES3_EDE_KEY_SIZE,
-		.ivsize         = DES3_EDE_BLOCK_SIZE,
 		.base = {
 			.cra_name = "ecb(des3_ede)",
 			.cra_driver_name = "ecb-des3-sun4i-ss",
 			.cra_priority = 300,
 			.cra_blocksize = DES3_EDE_BLOCK_SIZE,
+			.cra_flags = CRYPTO_ALG_KERN_DRIVER_ONLY | CRYPTO_ALG_NEED_FALLBACK,
 			.cra_ctxsize = sizeof(struct sun4i_req_ctx),
 			.cra_module = THIS_MODULE,
 			.cra_alignmask = 3,
 			.cra_init = sun4i_ss_cipher_init,
+			.cra_exit = sun4i_ss_cipher_exit,
 		}
 	}
 },
diff --git a/drivers/crypto/sunxi-ss/sun4i-ss-hash.c b/drivers/crypto/sunxi-ss/sun4i-ss-hash.c
index a4b5ff2b72f8..f6936bb3b7be 100644
--- a/drivers/crypto/sunxi-ss/sun4i-ss-hash.c
+++ b/drivers/crypto/sunxi-ss/sun4i-ss-hash.c
@@ -240,7 +240,10 @@ static int sun4i_hash(struct ahash_request *areq)
 		}
 	} else {
 		/* Since we have the flag final, we can go up to modulo 4 */
-		end = ((areq->nbytes + op->len) / 4) * 4 - op->len;
+		if (areq->nbytes < 4)
+			end = 0;
+		else
+			end = ((areq->nbytes + op->len) / 4) * 4 - op->len;
 	}
 
 	/* TODO if SGlen % 4 and !op->len then DMA */
diff --git a/drivers/crypto/sunxi-ss/sun4i-ss.h b/drivers/crypto/sunxi-ss/sun4i-ss.h
index f3ac90692ac6..8c4ec9e93565 100644
--- a/drivers/crypto/sunxi-ss/sun4i-ss.h
+++ b/drivers/crypto/sunxi-ss/sun4i-ss.h
@@ -161,6 +161,7 @@ struct sun4i_tfm_ctx {
 	u32 keylen;
 	u32 keymode;
 	struct sun4i_ss_ctx *ss;
+	struct crypto_sync_skcipher *fallback_tfm;
 };
 
 struct sun4i_cipher_req_ctx {
@@ -203,6 +204,7 @@ int sun4i_ss_ecb_des3_encrypt(struct skcipher_request *areq);
 int sun4i_ss_ecb_des3_decrypt(struct skcipher_request *areq);
 
 int sun4i_ss_cipher_init(struct crypto_tfm *tfm);
+void sun4i_ss_cipher_exit(struct crypto_tfm *tfm);
 int sun4i_ss_aes_setkey(struct crypto_skcipher *tfm, const u8 *key,
 			unsigned int keylen);
 int sun4i_ss_des_setkey(struct crypto_skcipher *tfm, const u8 *key,
diff --git a/drivers/crypto/talitos.c b/drivers/crypto/talitos.c
index de78b54bcfb1..1d429fc073d1 100644
--- a/drivers/crypto/talitos.c
+++ b/drivers/crypto/talitos.c
@@ -913,6 +913,54 @@ badkey:
 	return -EINVAL;
 }
 
+static int aead_des3_setkey(struct crypto_aead *authenc,
+			    const u8 *key, unsigned int keylen)
+{
+	struct talitos_ctx *ctx = crypto_aead_ctx(authenc);
+	struct device *dev = ctx->dev;
+	struct crypto_authenc_keys keys;
+	u32 flags;
+	int err;
+
+	err = crypto_authenc_extractkeys(&keys, key, keylen);
+	if (unlikely(err))
+		goto badkey;
+
+	err = -EINVAL;
+	if (keys.authkeylen + keys.enckeylen > TALITOS_MAX_KEY_SIZE)
+		goto badkey;
+
+	if (keys.enckeylen != DES3_EDE_KEY_SIZE)
+		goto badkey;
+
+	flags = crypto_aead_get_flags(authenc);
+	err = __des3_verify_key(&flags, keys.enckey);
+	if (unlikely(err)) {
+		crypto_aead_set_flags(authenc, flags);
+		goto out;
+	}
+
+	if (ctx->keylen)
+		dma_unmap_single(dev, ctx->dma_key, ctx->keylen, DMA_TO_DEVICE);
+
+	memcpy(ctx->key, keys.authkey, keys.authkeylen);
+	memcpy(&ctx->key[keys.authkeylen], keys.enckey, keys.enckeylen);
+
+	ctx->keylen = keys.authkeylen + keys.enckeylen;
+	ctx->enckeylen = keys.enckeylen;
+	ctx->authkeylen = keys.authkeylen;
+	ctx->dma_key = dma_map_single(dev, ctx->key, ctx->keylen,
+				      DMA_TO_DEVICE);
+
+out:
+	memzero_explicit(&keys, sizeof(keys));
+	return err;
+
+badkey:
+	crypto_aead_set_flags(authenc, CRYPTO_TFM_RES_BAD_KEY_LEN);
+	goto out;
+}
+
 /*
  * talitos_edesc - s/w-extended descriptor
  * @src_nents: number of segments in input scatterlist
@@ -1527,12 +1575,22 @@ static int ablkcipher_setkey(struct crypto_ablkcipher *cipher,
 {
 	struct talitos_ctx *ctx = crypto_ablkcipher_ctx(cipher);
 	struct device *dev = ctx->dev;
-	u32 tmp[DES_EXPKEY_WORDS];
 
-	if (keylen > TALITOS_MAX_KEY_SIZE) {
-		crypto_ablkcipher_set_flags(cipher, CRYPTO_TFM_RES_BAD_KEY_LEN);
-		return -EINVAL;
-	}
+	if (ctx->keylen)
+		dma_unmap_single(dev, ctx->dma_key, ctx->keylen, DMA_TO_DEVICE);
+
+	memcpy(&ctx->key, key, keylen);
+	ctx->keylen = keylen;
+
+	ctx->dma_key = dma_map_single(dev, ctx->key, keylen, DMA_TO_DEVICE);
+
+	return 0;
+}
+
+static int ablkcipher_des_setkey(struct crypto_ablkcipher *cipher,
+				 const u8 *key, unsigned int keylen)
+{
+	u32 tmp[DES_EXPKEY_WORDS];
 
 	if (unlikely(crypto_ablkcipher_get_flags(cipher) &
 		     CRYPTO_TFM_REQ_FORBID_WEAK_KEYS) &&
@@ -1541,15 +1599,23 @@ static int ablkcipher_setkey(struct crypto_ablkcipher *cipher,
 		return -EINVAL;
 	}
 
-	if (ctx->keylen)
-		dma_unmap_single(dev, ctx->dma_key, ctx->keylen, DMA_TO_DEVICE);
+	return ablkcipher_setkey(cipher, key, keylen);
+}
 
-	memcpy(&ctx->key, key, keylen);
-	ctx->keylen = keylen;
+static int ablkcipher_des3_setkey(struct crypto_ablkcipher *cipher,
+				  const u8 *key, unsigned int keylen)
+{
+	u32 flags;
+	int err;
 
-	ctx->dma_key = dma_map_single(dev, ctx->key, keylen, DMA_TO_DEVICE);
+	flags = crypto_ablkcipher_get_flags(cipher);
+	err = __des3_verify_key(&flags, key);
+	if (unlikely(err)) {
+		crypto_ablkcipher_set_flags(cipher, flags);
+		return err;
+	}
 
-	return 0;
+	return ablkcipher_setkey(cipher, key, keylen);
 }
 
 static void common_nonsnoop_unmap(struct device *dev,
@@ -2313,6 +2379,7 @@ static struct talitos_alg_template driver_algs[] = {
 			},
 			.ivsize = DES3_EDE_BLOCK_SIZE,
 			.maxauthsize = SHA1_DIGEST_SIZE,
+			.setkey = aead_des3_setkey,
 		},
 		.desc_hdr_template = DESC_HDR_TYPE_IPSEC_ESP |
 			             DESC_HDR_SEL0_DEU |
@@ -2336,6 +2403,7 @@ static struct talitos_alg_template driver_algs[] = {
 			},
 			.ivsize = DES3_EDE_BLOCK_SIZE,
 			.maxauthsize = SHA1_DIGEST_SIZE,
+			.setkey = aead_des3_setkey,
 		},
 		.desc_hdr_template = DESC_HDR_TYPE_HMAC_SNOOP_NO_AFEU |
 				     DESC_HDR_SEL0_DEU |
@@ -2399,6 +2467,7 @@ static struct talitos_alg_template driver_algs[] = {
 			},
 			.ivsize = DES3_EDE_BLOCK_SIZE,
 			.maxauthsize = SHA224_DIGEST_SIZE,
+			.setkey = aead_des3_setkey,
 		},
 		.desc_hdr_template = DESC_HDR_TYPE_IPSEC_ESP |
 			             DESC_HDR_SEL0_DEU |
@@ -2422,6 +2491,7 @@ static struct talitos_alg_template driver_algs[] = {
 			},
 			.ivsize = DES3_EDE_BLOCK_SIZE,
 			.maxauthsize = SHA224_DIGEST_SIZE,
+			.setkey = aead_des3_setkey,
 		},
 		.desc_hdr_template = DESC_HDR_TYPE_HMAC_SNOOP_NO_AFEU |
 				     DESC_HDR_SEL0_DEU |
@@ -2485,6 +2555,7 @@ static struct talitos_alg_template driver_algs[] = {
 			},
 			.ivsize = DES3_EDE_BLOCK_SIZE,
 			.maxauthsize = SHA256_DIGEST_SIZE,
+			.setkey = aead_des3_setkey,
 		},
 		.desc_hdr_template = DESC_HDR_TYPE_IPSEC_ESP |
 			             DESC_HDR_SEL0_DEU |
@@ -2508,6 +2579,7 @@ static struct talitos_alg_template driver_algs[] = {
 			},
 			.ivsize = DES3_EDE_BLOCK_SIZE,
 			.maxauthsize = SHA256_DIGEST_SIZE,
+			.setkey = aead_des3_setkey,
 		},
 		.desc_hdr_template = DESC_HDR_TYPE_HMAC_SNOOP_NO_AFEU |
 				     DESC_HDR_SEL0_DEU |
@@ -2550,6 +2622,7 @@ static struct talitos_alg_template driver_algs[] = {
 			},
 			.ivsize = DES3_EDE_BLOCK_SIZE,
 			.maxauthsize = SHA384_DIGEST_SIZE,
+			.setkey = aead_des3_setkey,
 		},
 		.desc_hdr_template = DESC_HDR_TYPE_IPSEC_ESP |
 			             DESC_HDR_SEL0_DEU |
@@ -2592,6 +2665,7 @@ static struct talitos_alg_template driver_algs[] = {
 			},
 			.ivsize = DES3_EDE_BLOCK_SIZE,
 			.maxauthsize = SHA512_DIGEST_SIZE,
+			.setkey = aead_des3_setkey,
 		},
 		.desc_hdr_template = DESC_HDR_TYPE_IPSEC_ESP |
 			             DESC_HDR_SEL0_DEU |
@@ -2654,6 +2728,7 @@ static struct talitos_alg_template driver_algs[] = {
 			},
 			.ivsize = DES3_EDE_BLOCK_SIZE,
 			.maxauthsize = MD5_DIGEST_SIZE,
+			.setkey = aead_des3_setkey,
 		},
 		.desc_hdr_template = DESC_HDR_TYPE_IPSEC_ESP |
 			             DESC_HDR_SEL0_DEU |
@@ -2676,6 +2751,7 @@ static struct talitos_alg_template driver_algs[] = {
 			},
 			.ivsize = DES3_EDE_BLOCK_SIZE,
 			.maxauthsize = MD5_DIGEST_SIZE,
+			.setkey = aead_des3_setkey,
 		},
 		.desc_hdr_template = DESC_HDR_TYPE_HMAC_SNOOP_NO_AFEU |
 				     DESC_HDR_SEL0_DEU |
@@ -2748,6 +2824,7 @@ static struct talitos_alg_template driver_algs[] = {
 				.min_keysize = DES_KEY_SIZE,
 				.max_keysize = DES_KEY_SIZE,
 				.ivsize = DES_BLOCK_SIZE,
+				.setkey = ablkcipher_des_setkey,
 			}
 		},
 		.desc_hdr_template = DESC_HDR_TYPE_COMMON_NONSNOOP_NO_AFEU |
@@ -2764,6 +2841,7 @@ static struct talitos_alg_template driver_algs[] = {
 				.min_keysize = DES_KEY_SIZE,
 				.max_keysize = DES_KEY_SIZE,
 				.ivsize = DES_BLOCK_SIZE,
+				.setkey = ablkcipher_des_setkey,
 			}
 		},
 		.desc_hdr_template = DESC_HDR_TYPE_COMMON_NONSNOOP_NO_AFEU |
@@ -2781,6 +2859,7 @@ static struct talitos_alg_template driver_algs[] = {
 				.min_keysize = DES3_EDE_KEY_SIZE,
 				.max_keysize = DES3_EDE_KEY_SIZE,
 				.ivsize = DES3_EDE_BLOCK_SIZE,
+				.setkey = ablkcipher_des3_setkey,
 			}
 		},
 		.desc_hdr_template = DESC_HDR_TYPE_COMMON_NONSNOOP_NO_AFEU |
@@ -2798,6 +2877,7 @@ static struct talitos_alg_template driver_algs[] = {
 				.min_keysize = DES3_EDE_KEY_SIZE,
 				.max_keysize = DES3_EDE_KEY_SIZE,
 				.ivsize = DES3_EDE_BLOCK_SIZE,
+				.setkey = ablkcipher_des3_setkey,
 			}
 		},
 		.desc_hdr_template = DESC_HDR_TYPE_COMMON_NONSNOOP_NO_AFEU |
@@ -3144,7 +3224,8 @@ static struct talitos_crypto_alg *talitos_alg_alloc(struct device *dev,
 		alg->cra_init = talitos_cra_init;
 		alg->cra_exit = talitos_cra_exit;
 		alg->cra_type = &crypto_ablkcipher_type;
-		alg->cra_ablkcipher.setkey = ablkcipher_setkey;
+		alg->cra_ablkcipher.setkey = alg->cra_ablkcipher.setkey ?:
+					     ablkcipher_setkey;
 		alg->cra_ablkcipher.encrypt = ablkcipher_encrypt;
 		alg->cra_ablkcipher.decrypt = ablkcipher_decrypt;
 		break;
@@ -3152,7 +3233,8 @@ static struct talitos_crypto_alg *talitos_alg_alloc(struct device *dev,
 		alg = &t_alg->algt.alg.aead.base;
 		alg->cra_exit = talitos_cra_exit;
 		t_alg->algt.alg.aead.init = talitos_cra_init_aead;
-		t_alg->algt.alg.aead.setkey = aead_setkey;
+		t_alg->algt.alg.aead.setkey = t_alg->algt.alg.aead.setkey ?:
+					      aead_setkey;
 		t_alg->algt.alg.aead.encrypt = aead_encrypt;
 		t_alg->algt.alg.aead.decrypt = aead_decrypt;
 		if (!(priv->features & TALITOS_FTR_SHA224_HWINIT) &&
diff --git a/drivers/crypto/ux500/cryp/Makefile b/drivers/crypto/ux500/cryp/Makefile
index b497ae3dde07..dc8fff29c4b3 100644
--- a/drivers/crypto/ux500/cryp/Makefile
+++ b/drivers/crypto/ux500/cryp/Makefile
@@ -3,11 +3,7 @@
 # * Author: shujuan.chen@stericsson.com for ST-Ericsson.
 # * License terms: GNU General Public License (GPL) version 2  */
 
-ifdef CONFIG_CRYPTO_DEV_UX500_DEBUG
-CFLAGS_cryp_core.o := -DDEBUG
-CFLAGS_cryp.o := -DDEBUG
-CFLAGS_cryp_irq.o := -DDEBUG
-endif
+ccflags-$(CONFIG_CRYPTO_DEV_UX500_DEBUG) += -DDEBUG
 
 obj-$(CONFIG_CRYPTO_DEV_UX500_CRYP) += ux500_cryp.o
 ux500_cryp-objs :=  cryp.o cryp_irq.o cryp_core.o
diff --git a/drivers/crypto/ux500/cryp/cryp_core.c b/drivers/crypto/ux500/cryp/cryp_core.c
index 3235611928f2..7a93cba0877f 100644
--- a/drivers/crypto/ux500/cryp/cryp_core.c
+++ b/drivers/crypto/ux500/cryp/cryp_core.c
@@ -1019,37 +1019,16 @@ static int des3_ablkcipher_setkey(struct crypto_ablkcipher *cipher,
 				  const u8 *key, unsigned int keylen)
 {
 	struct cryp_ctx *ctx = crypto_ablkcipher_ctx(cipher);
-	u32 *flags = &cipher->base.crt_flags;
-	const u32 *K = (const u32 *)key;
-	u32 tmp[DES3_EDE_EXPKEY_WORDS];
-	int i, ret;
+	u32 flags;
+	int err;
 
 	pr_debug(DEV_DBG_NAME " [%s]", __func__);
-	if (keylen != DES3_EDE_KEY_SIZE) {
-		*flags |= CRYPTO_TFM_RES_BAD_KEY_LEN;
-		pr_debug(DEV_DBG_NAME " [%s]: CRYPTO_TFM_RES_BAD_KEY_LEN",
-				__func__);
-		return -EINVAL;
-	}
 
-	/* Checking key interdependency for weak key detection. */
-	if (unlikely(!((K[0] ^ K[2]) | (K[1] ^ K[3])) ||
-				!((K[2] ^ K[4]) | (K[3] ^ K[5]))) &&
-			(*flags & CRYPTO_TFM_REQ_FORBID_WEAK_KEYS)) {
-		*flags |= CRYPTO_TFM_RES_WEAK_KEY;
-		pr_debug(DEV_DBG_NAME " [%s]: CRYPTO_TFM_RES_WEAK_KEY",
-			 __func__);
-		return -EINVAL;
-	}
-	for (i = 0; i < 3; i++) {
-		ret = des_ekey(tmp, key + i*DES_KEY_SIZE);
-		if (unlikely(ret == 0) &&
-		    (*flags & CRYPTO_TFM_REQ_FORBID_WEAK_KEYS)) {
-			*flags |= CRYPTO_TFM_RES_WEAK_KEY;
-			pr_debug(DEV_DBG_NAME " [%s]: CRYPTO_TFM_RES_WEAK_KEY",
-				 __func__);
-			return -EINVAL;
-		}
+	flags = crypto_ablkcipher_get_flags(cipher);
+	err = __des3_verify_key(&flags, key);
+	if (unlikely(err)) {
+		crypto_ablkcipher_set_flags(cipher, flags);
+		return err;
 	}
 
 	memcpy(ctx->key, key, keylen);
@@ -1219,57 +1198,6 @@ static struct cryp_algo_template cryp_algs[] = {
 	{
 		.algomode = CRYP_ALGO_DES_ECB,
 		.crypto = {
-			.cra_name = "des",
-			.cra_driver_name = "des-ux500",
-			.cra_priority = 300,
-			.cra_flags = CRYPTO_ALG_TYPE_ABLKCIPHER |
-						CRYPTO_ALG_ASYNC,
-			.cra_blocksize = DES_BLOCK_SIZE,
-			.cra_ctxsize = sizeof(struct cryp_ctx),
-			.cra_alignmask = 3,
-			.cra_type = &crypto_ablkcipher_type,
-			.cra_init = cryp_cra_init,
-			.cra_module = THIS_MODULE,
-			.cra_u = {
-				.ablkcipher = {
-					.min_keysize = DES_KEY_SIZE,
-					.max_keysize = DES_KEY_SIZE,
-					.setkey = des_ablkcipher_setkey,
-					.encrypt = cryp_blk_encrypt,
-					.decrypt = cryp_blk_decrypt
-				}
-			}
-		}
-
-	},
-	{
-		.algomode = CRYP_ALGO_TDES_ECB,
-		.crypto = {
-			.cra_name = "des3_ede",
-			.cra_driver_name = "des3_ede-ux500",
-			.cra_priority = 300,
-			.cra_flags = CRYPTO_ALG_TYPE_ABLKCIPHER |
-						CRYPTO_ALG_ASYNC,
-			.cra_blocksize = DES3_EDE_BLOCK_SIZE,
-			.cra_ctxsize = sizeof(struct cryp_ctx),
-			.cra_alignmask = 3,
-			.cra_type = &crypto_ablkcipher_type,
-			.cra_init = cryp_cra_init,
-			.cra_module = THIS_MODULE,
-			.cra_u = {
-				.ablkcipher = {
-					.min_keysize = DES3_EDE_KEY_SIZE,
-					.max_keysize = DES3_EDE_KEY_SIZE,
-					.setkey = des_ablkcipher_setkey,
-					.encrypt = cryp_blk_encrypt,
-					.decrypt = cryp_blk_decrypt
-				}
-			}
-		}
-	},
-	{
-		.algomode = CRYP_ALGO_DES_ECB,
-		.crypto = {
 			.cra_name = "ecb(des)",
 			.cra_driver_name = "ecb-des-ux500",
 			.cra_priority = 300,
diff --git a/drivers/crypto/vmx/aes.c b/drivers/crypto/vmx/aes.c
index d7316f7a3a69..603a62081994 100644
--- a/drivers/crypto/vmx/aes.c
+++ b/drivers/crypto/vmx/aes.c
@@ -23,9 +23,10 @@
 #include <linux/err.h>
 #include <linux/crypto.h>
 #include <linux/delay.h>
-#include <linux/hardirq.h>
+#include <asm/simd.h>
 #include <asm/switch_to.h>
 #include <crypto/aes.h>
+#include <crypto/internal/simd.h>
 
 #include "aesp8-ppc.h"
 
@@ -78,20 +79,21 @@ static int p8_aes_setkey(struct crypto_tfm *tfm, const u8 *key,
 	pagefault_disable();
 	enable_kernel_vsx();
 	ret = aes_p8_set_encrypt_key(key, keylen * 8, &ctx->enc_key);
-	ret += aes_p8_set_decrypt_key(key, keylen * 8, &ctx->dec_key);
+	ret |= aes_p8_set_decrypt_key(key, keylen * 8, &ctx->dec_key);
 	disable_kernel_vsx();
 	pagefault_enable();
 	preempt_enable();
 
-	ret += crypto_cipher_setkey(ctx->fallback, key, keylen);
-	return ret;
+	ret |= crypto_cipher_setkey(ctx->fallback, key, keylen);
+
+	return ret ? -EINVAL : 0;
 }
 
 static void p8_aes_encrypt(struct crypto_tfm *tfm, u8 *dst, const u8 *src)
 {
 	struct p8_aes_ctx *ctx = crypto_tfm_ctx(tfm);
 
-	if (in_interrupt()) {
+	if (!crypto_simd_usable()) {
 		crypto_cipher_encrypt_one(ctx->fallback, dst, src);
 	} else {
 		preempt_disable();
@@ -108,7 +110,7 @@ static void p8_aes_decrypt(struct crypto_tfm *tfm, u8 *dst, const u8 *src)
 {
 	struct p8_aes_ctx *ctx = crypto_tfm_ctx(tfm);
 
-	if (in_interrupt()) {
+	if (!crypto_simd_usable()) {
 		crypto_cipher_decrypt_one(ctx->fallback, dst, src);
 	} else {
 		preempt_disable();
diff --git a/drivers/crypto/vmx/aes_cbc.c b/drivers/crypto/vmx/aes_cbc.c
index c5c5ff82b52e..a1a9a6f0d42c 100644
--- a/drivers/crypto/vmx/aes_cbc.c
+++ b/drivers/crypto/vmx/aes_cbc.c
@@ -23,9 +23,10 @@
 #include <linux/err.h>
 #include <linux/crypto.h>
 #include <linux/delay.h>
-#include <linux/hardirq.h>
+#include <asm/simd.h>
 #include <asm/switch_to.h>
 #include <crypto/aes.h>
+#include <crypto/internal/simd.h>
 #include <crypto/scatterwalk.h>
 #include <crypto/skcipher.h>
 
@@ -81,13 +82,14 @@ static int p8_aes_cbc_setkey(struct crypto_tfm *tfm, const u8 *key,
 	pagefault_disable();
 	enable_kernel_vsx();
 	ret = aes_p8_set_encrypt_key(key, keylen * 8, &ctx->enc_key);
-	ret += aes_p8_set_decrypt_key(key, keylen * 8, &ctx->dec_key);
+	ret |= aes_p8_set_decrypt_key(key, keylen * 8, &ctx->dec_key);
 	disable_kernel_vsx();
 	pagefault_enable();
 	preempt_enable();
 
-	ret += crypto_sync_skcipher_setkey(ctx->fallback, key, keylen);
-	return ret;
+	ret |= crypto_sync_skcipher_setkey(ctx->fallback, key, keylen);
+
+	return ret ? -EINVAL : 0;
 }
 
 static int p8_aes_cbc_encrypt(struct blkcipher_desc *desc,
@@ -99,7 +101,7 @@ static int p8_aes_cbc_encrypt(struct blkcipher_desc *desc,
 	struct p8_aes_cbc_ctx *ctx =
 		crypto_tfm_ctx(crypto_blkcipher_tfm(desc->tfm));
 
-	if (in_interrupt()) {
+	if (!crypto_simd_usable()) {
 		SYNC_SKCIPHER_REQUEST_ON_STACK(req, ctx->fallback);
 		skcipher_request_set_sync_tfm(req, ctx->fallback);
 		skcipher_request_set_callback(req, desc->flags, NULL, NULL);
@@ -138,7 +140,7 @@ static int p8_aes_cbc_decrypt(struct blkcipher_desc *desc,
 	struct p8_aes_cbc_ctx *ctx =
 		crypto_tfm_ctx(crypto_blkcipher_tfm(desc->tfm));
 
-	if (in_interrupt()) {
+	if (!crypto_simd_usable()) {
 		SYNC_SKCIPHER_REQUEST_ON_STACK(req, ctx->fallback);
 		skcipher_request_set_sync_tfm(req, ctx->fallback);
 		skcipher_request_set_callback(req, desc->flags, NULL, NULL);
diff --git a/drivers/crypto/vmx/aes_ctr.c b/drivers/crypto/vmx/aes_ctr.c
index 8a2fe092cb8e..192a53512f5e 100644
--- a/drivers/crypto/vmx/aes_ctr.c
+++ b/drivers/crypto/vmx/aes_ctr.c
@@ -23,9 +23,10 @@
 #include <linux/err.h>
 #include <linux/crypto.h>
 #include <linux/delay.h>
-#include <linux/hardirq.h>
+#include <asm/simd.h>
 #include <asm/switch_to.h>
 #include <crypto/aes.h>
+#include <crypto/internal/simd.h>
 #include <crypto/scatterwalk.h>
 #include <crypto/skcipher.h>
 
@@ -83,8 +84,9 @@ static int p8_aes_ctr_setkey(struct crypto_tfm *tfm, const u8 *key,
 	pagefault_enable();
 	preempt_enable();
 
-	ret += crypto_sync_skcipher_setkey(ctx->fallback, key, keylen);
-	return ret;
+	ret |= crypto_sync_skcipher_setkey(ctx->fallback, key, keylen);
+
+	return ret ? -EINVAL : 0;
 }
 
 static void p8_aes_ctr_final(struct p8_aes_ctr_ctx *ctx,
@@ -118,7 +120,7 @@ static int p8_aes_ctr_crypt(struct blkcipher_desc *desc,
 	struct p8_aes_ctr_ctx *ctx =
 		crypto_tfm_ctx(crypto_blkcipher_tfm(desc->tfm));
 
-	if (in_interrupt()) {
+	if (!crypto_simd_usable()) {
 		SYNC_SKCIPHER_REQUEST_ON_STACK(req, ctx->fallback);
 		skcipher_request_set_sync_tfm(req, ctx->fallback);
 		skcipher_request_set_callback(req, desc->flags, NULL, NULL);
diff --git a/drivers/crypto/vmx/aes_xts.c b/drivers/crypto/vmx/aes_xts.c
index ecd64e5cc5bb..00d412d811ae 100644
--- a/drivers/crypto/vmx/aes_xts.c
+++ b/drivers/crypto/vmx/aes_xts.c
@@ -23,9 +23,10 @@
 #include <linux/err.h>
 #include <linux/crypto.h>
 #include <linux/delay.h>
-#include <linux/hardirq.h>
+#include <asm/simd.h>
 #include <asm/switch_to.h>
 #include <crypto/aes.h>
+#include <crypto/internal/simd.h>
 #include <crypto/scatterwalk.h>
 #include <crypto/xts.h>
 #include <crypto/skcipher.h>
@@ -86,14 +87,15 @@ static int p8_aes_xts_setkey(struct crypto_tfm *tfm, const u8 *key,
 	pagefault_disable();
 	enable_kernel_vsx();
 	ret = aes_p8_set_encrypt_key(key + keylen/2, (keylen/2) * 8, &ctx->tweak_key);
-	ret += aes_p8_set_encrypt_key(key, (keylen/2) * 8, &ctx->enc_key);
-	ret += aes_p8_set_decrypt_key(key, (keylen/2) * 8, &ctx->dec_key);
+	ret |= aes_p8_set_encrypt_key(key, (keylen/2) * 8, &ctx->enc_key);
+	ret |= aes_p8_set_decrypt_key(key, (keylen/2) * 8, &ctx->dec_key);
 	disable_kernel_vsx();
 	pagefault_enable();
 	preempt_enable();
 
-	ret += crypto_sync_skcipher_setkey(ctx->fallback, key, keylen);
-	return ret;
+	ret |= crypto_sync_skcipher_setkey(ctx->fallback, key, keylen);
+
+	return ret ? -EINVAL : 0;
 }
 
 static int p8_aes_xts_crypt(struct blkcipher_desc *desc,
@@ -108,7 +110,7 @@ static int p8_aes_xts_crypt(struct blkcipher_desc *desc,
 	struct p8_aes_xts_ctx *ctx =
 		crypto_tfm_ctx(crypto_blkcipher_tfm(desc->tfm));
 
-	if (in_interrupt()) {
+	if (!crypto_simd_usable()) {
 		SYNC_SKCIPHER_REQUEST_ON_STACK(req, ctx->fallback);
 		skcipher_request_set_sync_tfm(req, ctx->fallback);
 		skcipher_request_set_callback(req, desc->flags, NULL, NULL);
diff --git a/drivers/crypto/vmx/aesp8-ppc.pl b/drivers/crypto/vmx/aesp8-ppc.pl
index d6a9f63d65ba..de78282b8f44 100644
--- a/drivers/crypto/vmx/aesp8-ppc.pl
+++ b/drivers/crypto/vmx/aesp8-ppc.pl
@@ -1854,7 +1854,7 @@ Lctr32_enc8x_three:
 	stvx_u		$out1,$x10,$out
 	stvx_u		$out2,$x20,$out
 	addi		$out,$out,0x30
-	b		Lcbc_dec8x_done
+	b		Lctr32_enc8x_done
 
 .align	5
 Lctr32_enc8x_two:
@@ -1866,7 +1866,7 @@ Lctr32_enc8x_two:
 	stvx_u		$out0,$x00,$out
 	stvx_u		$out1,$x10,$out
 	addi		$out,$out,0x20
-	b		Lcbc_dec8x_done
+	b		Lctr32_enc8x_done
 
 .align	5
 Lctr32_enc8x_one:
diff --git a/drivers/crypto/vmx/ghash.c b/drivers/crypto/vmx/ghash.c
index dd8b8716467a..b5a6883bb09e 100644
--- a/drivers/crypto/vmx/ghash.c
+++ b/drivers/crypto/vmx/ghash.c
@@ -23,16 +23,15 @@
 #include <linux/err.h>
 #include <linux/crypto.h>
 #include <linux/delay.h>
-#include <linux/hardirq.h>
+#include <asm/simd.h>
 #include <asm/switch_to.h>
 #include <crypto/aes.h>
 #include <crypto/ghash.h>
 #include <crypto/scatterwalk.h>
 #include <crypto/internal/hash.h>
+#include <crypto/internal/simd.h>
 #include <crypto/b128ops.h>
 
-#define IN_INTERRUPT in_interrupt()
-
 void gcm_init_p8(u128 htable[16], const u64 Xi[2]);
 void gcm_gmult_p8(u64 Xi[2], const u128 htable[16]);
 void gcm_ghash_p8(u64 Xi[2], const u128 htable[16],
@@ -102,7 +101,6 @@ static int p8_ghash_init(struct shash_desc *desc)
 	dctx->bytes = 0;
 	memset(dctx->shash, 0, GHASH_DIGEST_SIZE);
 	dctx->fallback_desc.tfm = ctx->fallback;
-	dctx->fallback_desc.flags = desc->flags;
 	return crypto_shash_init(&dctx->fallback_desc);
 }
 
@@ -131,7 +129,7 @@ static int p8_ghash_update(struct shash_desc *desc,
 	struct p8_ghash_ctx *ctx = crypto_tfm_ctx(crypto_shash_tfm(desc->tfm));
 	struct p8_ghash_desc_ctx *dctx = shash_desc_ctx(desc);
 
-	if (IN_INTERRUPT) {
+	if (!crypto_simd_usable()) {
 		return crypto_shash_update(&dctx->fallback_desc, src,
 					   srclen);
 	} else {
@@ -182,7 +180,7 @@ static int p8_ghash_final(struct shash_desc *desc, u8 *out)
 	struct p8_ghash_ctx *ctx = crypto_tfm_ctx(crypto_shash_tfm(desc->tfm));
 	struct p8_ghash_desc_ctx *dctx = shash_desc_ctx(desc);
 
-	if (IN_INTERRUPT) {
+	if (!crypto_simd_usable()) {
 		return crypto_shash_final(&dctx->fallback_desc, out);
 	} else {
 		if (dctx->bytes) {
diff --git a/drivers/crypto/vmx/vmx.c b/drivers/crypto/vmx/vmx.c
index 31a98dc6f849..a9f519830615 100644
--- a/drivers/crypto/vmx/vmx.c
+++ b/drivers/crypto/vmx/vmx.c
@@ -41,7 +41,7 @@ static struct crypto_alg *algs[] = {
 	NULL,
 };
 
-int __init p8_init(void)
+static int __init p8_init(void)
 {
 	int ret = 0;
 	struct crypto_alg **alg_it;
@@ -67,7 +67,7 @@ int __init p8_init(void)
 	return ret;
 }
 
-void __exit p8_exit(void)
+static void __exit p8_exit(void)
 {
 	struct crypto_alg **alg_it;
 
diff --git a/drivers/devfreq/devfreq-event.c b/drivers/devfreq/devfreq-event.c
index d67242d87744..87e93406d7cd 100644
--- a/drivers/devfreq/devfreq-event.c
+++ b/drivers/devfreq/devfreq-event.c
@@ -240,7 +240,7 @@ struct devfreq_event_dev *devfreq_event_get_edev_by_phandle(struct device *dev,
 	}
 
 	list_for_each_entry(edev, &devfreq_event_list, node) {
-		if (!strcmp(edev->desc->name, node->name))
+		if (of_node_name_eq(node, edev->desc->name))
 			goto out;
 	}
 	edev = NULL;
diff --git a/drivers/devfreq/devfreq.c b/drivers/devfreq/devfreq.c
index 0ae3de76833b..6b6991f0e873 100644
--- a/drivers/devfreq/devfreq.c
+++ b/drivers/devfreq/devfreq.c
@@ -29,6 +29,9 @@
 #include <linux/of.h>
 #include "governor.h"
 
+#define CREATE_TRACE_POINTS
+#include <trace/events/devfreq.h>
+
 static struct class *devfreq_class;
 
 /*
@@ -228,7 +231,7 @@ static struct devfreq_governor *find_devfreq_governor(const char *name)
  * if is not found. This can happen when both drivers (the governor driver
  * and the driver that call devfreq_add_device) are built as modules.
  * devfreq_list_lock should be held by the caller. Returns the matched
- * governor's pointer.
+ * governor's pointer or an error pointer.
  */
 static struct devfreq_governor *try_then_request_governor(const char *name)
 {
@@ -254,7 +257,7 @@ static struct devfreq_governor *try_then_request_governor(const char *name)
 		/* Restore previous state before return */
 		mutex_lock(&devfreq_list_lock);
 		if (err)
-			return NULL;
+			return ERR_PTR(err);
 
 		governor = find_devfreq_governor(name);
 	}
@@ -394,6 +397,8 @@ static void devfreq_monitor(struct work_struct *work)
 	queue_delayed_work(devfreq_wq, &devfreq->work,
 				msecs_to_jiffies(devfreq->profile->polling_ms));
 	mutex_unlock(&devfreq->lock);
+
+	trace_devfreq_monitor(devfreq);
 }
 
 /**
@@ -528,7 +533,7 @@ void devfreq_interval_update(struct devfreq *devfreq, unsigned int *delay)
 		mutex_lock(&devfreq->lock);
 		if (!devfreq->stop_polling)
 			queue_delayed_work(devfreq_wq, &devfreq->work,
-			      msecs_to_jiffies(devfreq->profile->polling_ms));
+				msecs_to_jiffies(devfreq->profile->polling_ms));
 	}
 out:
 	mutex_unlock(&devfreq->lock);
@@ -537,7 +542,7 @@ EXPORT_SYMBOL(devfreq_interval_update);
 
 /**
  * devfreq_notifier_call() - Notify that the device frequency requirements
- *			   has been changed out of devfreq framework.
+ *			     has been changed out of devfreq framework.
  * @nb:		the notifier_block (supposed to be devfreq->nb)
  * @type:	not used
  * @devp:	not used
@@ -651,7 +656,7 @@ struct devfreq *devfreq_add_device(struct device *dev,
 		mutex_unlock(&devfreq->lock);
 		err = set_freq_table(devfreq);
 		if (err < 0)
-			goto err_out;
+			goto err_dev;
 		mutex_lock(&devfreq->lock);
 	}
 
@@ -683,16 +688,27 @@ struct devfreq *devfreq_add_device(struct device *dev,
 		goto err_out;
 	}
 
-	devfreq->trans_table =
-		devm_kzalloc(&devfreq->dev,
-			     array3_size(sizeof(unsigned int),
-					 devfreq->profile->max_state,
-					 devfreq->profile->max_state),
-			     GFP_KERNEL);
+	devfreq->trans_table = devm_kzalloc(&devfreq->dev,
+			array3_size(sizeof(unsigned int),
+				    devfreq->profile->max_state,
+				    devfreq->profile->max_state),
+			GFP_KERNEL);
+	if (!devfreq->trans_table) {
+		mutex_unlock(&devfreq->lock);
+		err = -ENOMEM;
+		goto err_devfreq;
+	}
+
 	devfreq->time_in_state = devm_kcalloc(&devfreq->dev,
-						devfreq->profile->max_state,
-						sizeof(unsigned long),
-						GFP_KERNEL);
+			devfreq->profile->max_state,
+			sizeof(unsigned long),
+			GFP_KERNEL);
+	if (!devfreq->time_in_state) {
+		mutex_unlock(&devfreq->lock);
+		err = -ENOMEM;
+		goto err_devfreq;
+	}
+
 	devfreq->last_stat_updated = jiffies;
 
 	srcu_init_notifier_head(&devfreq->transition_notifier_list);
@@ -726,7 +742,7 @@ struct devfreq *devfreq_add_device(struct device *dev,
 
 err_init:
 	mutex_unlock(&devfreq_list_lock);
-
+err_devfreq:
 	devfreq_remove_device(devfreq);
 	devfreq = NULL;
 err_dev:
@@ -1113,7 +1129,7 @@ static ssize_t governor_store(struct device *dev, struct device_attribute *attr,
 	struct devfreq *df = to_devfreq(dev);
 	int ret;
 	char str_governor[DEVFREQ_NAME_LEN + 1];
-	struct devfreq_governor *governor;
+	const struct devfreq_governor *governor, *prev_governor;
 
 	ret = sscanf(buf, "%" __stringify(DEVFREQ_NAME_LEN) "s", str_governor);
 	if (ret != 1)
@@ -1142,12 +1158,24 @@ static ssize_t governor_store(struct device *dev, struct device_attribute *attr,
 			goto out;
 		}
 	}
+	prev_governor = df->governor;
 	df->governor = governor;
 	strncpy(df->governor_name, governor->name, DEVFREQ_NAME_LEN);
 	ret = df->governor->event_handler(df, DEVFREQ_GOV_START, NULL);
-	if (ret)
+	if (ret) {
 		dev_warn(dev, "%s: Governor %s not started(%d)\n",
 			 __func__, df->governor->name, ret);
+		df->governor = prev_governor;
+		strncpy(df->governor_name, prev_governor->name,
+			DEVFREQ_NAME_LEN);
+		ret = df->governor->event_handler(df, DEVFREQ_GOV_START, NULL);
+		if (ret) {
+			dev_err(dev,
+				"%s: reverting to Governor %s failed (%d)\n",
+				__func__, df->governor_name, ret);
+			df->governor = NULL;
+		}
+	}
 out:
 	mutex_unlock(&devfreq_list_lock);
 
@@ -1172,7 +1200,7 @@ static ssize_t available_governors_show(struct device *d,
 	 */
 	if (df->governor->immutable) {
 		count = scnprintf(&buf[count], DEVFREQ_NAME_LEN,
-				   "%s ", df->governor_name);
+				  "%s ", df->governor_name);
 	/*
 	 * The devfreq device shows the registered governor except for
 	 * immutable governors such as passive governor .
@@ -1485,8 +1513,8 @@ EXPORT_SYMBOL(devfreq_recommended_opp);
 
 /**
  * devfreq_register_opp_notifier() - Helper function to get devfreq notified
- *				   for any changes in the OPP availability
- *				   changes
+ *				     for any changes in the OPP availability
+ *				     changes
  * @dev:	The devfreq user device. (parent of devfreq)
  * @devfreq:	The devfreq object.
  */
@@ -1498,8 +1526,8 @@ EXPORT_SYMBOL(devfreq_register_opp_notifier);
 
 /**
  * devfreq_unregister_opp_notifier() - Helper function to stop getting devfreq
- *				     notified for any changes in the OPP
- *				     availability changes anymore.
+ *				       notified for any changes in the OPP
+ *				       availability changes anymore.
  * @dev:	The devfreq user device. (parent of devfreq)
  * @devfreq:	The devfreq object.
  *
@@ -1518,8 +1546,8 @@ static void devm_devfreq_opp_release(struct device *dev, void *res)
 }
 
 /**
- * devm_ devfreq_register_opp_notifier()
- *		- Resource-managed devfreq_register_opp_notifier()
+ * devm_devfreq_register_opp_notifier() - Resource-managed
+ *					  devfreq_register_opp_notifier()
  * @dev:	The devfreq user device. (parent of devfreq)
  * @devfreq:	The devfreq object.
  */
@@ -1547,8 +1575,8 @@ int devm_devfreq_register_opp_notifier(struct device *dev,
 EXPORT_SYMBOL(devm_devfreq_register_opp_notifier);
 
 /**
- * devm_devfreq_unregister_opp_notifier()
- *		- Resource-managed devfreq_unregister_opp_notifier()
+ * devm_devfreq_unregister_opp_notifier() - Resource-managed
+ *					    devfreq_unregister_opp_notifier()
  * @dev:	The devfreq user device. (parent of devfreq)
  * @devfreq:	The devfreq object.
  */
@@ -1567,8 +1595,8 @@ EXPORT_SYMBOL(devm_devfreq_unregister_opp_notifier);
  * @list:	DEVFREQ_TRANSITION_NOTIFIER.
  */
 int devfreq_register_notifier(struct devfreq *devfreq,
-				struct notifier_block *nb,
-				unsigned int list)
+			      struct notifier_block *nb,
+			      unsigned int list)
 {
 	int ret = 0;
 
@@ -1674,9 +1702,9 @@ EXPORT_SYMBOL(devm_devfreq_register_notifier);
  * @list:	DEVFREQ_TRANSITION_NOTIFIER.
  */
 void devm_devfreq_unregister_notifier(struct device *dev,
-				struct devfreq *devfreq,
-				struct notifier_block *nb,
-				unsigned int list)
+				      struct devfreq *devfreq,
+				      struct notifier_block *nb,
+				      unsigned int list)
 {
 	WARN_ON(devres_release(dev, devm_devfreq_notifier_release,
 			       devm_devfreq_dev_match, devfreq));
diff --git a/drivers/devfreq/event/exynos-ppmu.c b/drivers/devfreq/event/exynos-ppmu.c
index c61de0bdf053..c2ea94957501 100644
--- a/drivers/devfreq/event/exynos-ppmu.c
+++ b/drivers/devfreq/event/exynos-ppmu.c
@@ -529,7 +529,7 @@ static int of_get_devfreq_events(struct device_node *np,
 			if (!ppmu_events[i].name)
 				continue;
 
-			if (!of_node_cmp(node->name, ppmu_events[i].name))
+			if (of_node_name_eq(node, ppmu_events[i].name))
 				break;
 		}
 
diff --git a/drivers/devfreq/event/rockchip-dfi.c b/drivers/devfreq/event/rockchip-dfi.c
index 22b113363ffc..a436ec4901bb 100644
--- a/drivers/devfreq/event/rockchip-dfi.c
+++ b/drivers/devfreq/event/rockchip-dfi.c
@@ -26,6 +26,8 @@
 #include <linux/list.h>
 #include <linux/of.h>
 
+#include <soc/rockchip/rk3399_grf.h>
+
 #define RK3399_DMC_NUM_CH	2
 
 /* DDRMON_CTRL */
@@ -43,18 +45,6 @@
 #define DDRMON_CH1_COUNT_NUM		0x3c
 #define DDRMON_CH1_DFI_ACCESS_NUM	0x40
 
-/* pmu grf */
-#define PMUGRF_OS_REG2	0x308
-#define DDRTYPE_SHIFT	13
-#define DDRTYPE_MASK	7
-
-enum {
-	DDR3 = 3,
-	LPDDR3 = 6,
-	LPDDR4 = 7,
-	UNUSED = 0xFF
-};
-
 struct dmc_usage {
 	u32 access;
 	u32 total;
@@ -83,16 +73,17 @@ static void rockchip_dfi_start_hardware_counter(struct devfreq_event_dev *edev)
 	u32 ddr_type;
 
 	/* get ddr type */
-	regmap_read(info->regmap_pmu, PMUGRF_OS_REG2, &val);
-	ddr_type = (val >> DDRTYPE_SHIFT) & DDRTYPE_MASK;
+	regmap_read(info->regmap_pmu, RK3399_PMUGRF_OS_REG2, &val);
+	ddr_type = (val >> RK3399_PMUGRF_DDRTYPE_SHIFT) &
+		    RK3399_PMUGRF_DDRTYPE_MASK;
 
 	/* clear DDRMON_CTRL setting */
 	writel_relaxed(CLR_DDRMON_CTRL, dfi_regs + DDRMON_CTRL);
 
 	/* set ddr type to dfi */
-	if (ddr_type == LPDDR3)
+	if (ddr_type == RK3399_PMUGRF_DDRTYPE_LPDDR3)
 		writel_relaxed(LPDDR3_EN, dfi_regs + DDRMON_CTRL);
-	else if (ddr_type == LPDDR4)
+	else if (ddr_type == RK3399_PMUGRF_DDRTYPE_LPDDR4)
 		writel_relaxed(LPDDR4_EN, dfi_regs + DDRMON_CTRL);
 
 	/* enable count, use software mode */
@@ -211,7 +202,7 @@ static int rockchip_dfi_probe(struct platform_device *pdev)
 	if (IS_ERR(data->clk)) {
 		dev_err(dev, "Cannot get the clk dmc_clk\n");
 		return PTR_ERR(data->clk);
-	};
+	}
 
 	/* try to find the optional reference to the pmu syscon */
 	node = of_parse_phandle(np, "rockchip,pmu", 0);
diff --git a/drivers/devfreq/exynos-bus.c b/drivers/devfreq/exynos-bus.c
index c25658b26598..486cc5b422f1 100644
--- a/drivers/devfreq/exynos-bus.c
+++ b/drivers/devfreq/exynos-bus.c
@@ -514,6 +514,13 @@ err:
 	return ret;
 }
 
+static void exynos_bus_shutdown(struct platform_device *pdev)
+{
+	struct exynos_bus *bus = dev_get_drvdata(&pdev->dev);
+
+	devfreq_suspend_device(bus->devfreq);
+}
+
 #ifdef CONFIG_PM_SLEEP
 static int exynos_bus_resume(struct device *dev)
 {
@@ -556,6 +563,7 @@ MODULE_DEVICE_TABLE(of, exynos_bus_of_match);
 
 static struct platform_driver exynos_bus_platdrv = {
 	.probe		= exynos_bus_probe,
+	.shutdown	= exynos_bus_shutdown,
 	.driver = {
 		.name	= "exynos-bus",
 		.pm	= &exynos_bus_pm,
diff --git a/drivers/devfreq/rk3399_dmc.c b/drivers/devfreq/rk3399_dmc.c
index e795ad2b3f6b..567c034d0301 100644
--- a/drivers/devfreq/rk3399_dmc.c
+++ b/drivers/devfreq/rk3399_dmc.c
@@ -18,14 +18,17 @@
 #include <linux/devfreq.h>
 #include <linux/devfreq-event.h>
 #include <linux/interrupt.h>
+#include <linux/mfd/syscon.h>
 #include <linux/module.h>
 #include <linux/of.h>
 #include <linux/platform_device.h>
 #include <linux/pm_opp.h>
+#include <linux/regmap.h>
 #include <linux/regulator/consumer.h>
 #include <linux/rwsem.h>
 #include <linux/suspend.h>
 
+#include <soc/rockchip/rk3399_grf.h>
 #include <soc/rockchip/rockchip_sip.h>
 
 struct dram_timing {
@@ -69,8 +72,11 @@ struct rk3399_dmcfreq {
 	struct mutex lock;
 	struct dram_timing timing;
 	struct regulator *vdd_center;
+	struct regmap *regmap_pmu;
 	unsigned long rate, target_rate;
 	unsigned long volt, target_volt;
+	unsigned int odt_dis_freq;
+	int odt_pd_arg0, odt_pd_arg1;
 };
 
 static int rk3399_dmcfreq_target(struct device *dev, unsigned long *freq,
@@ -80,6 +86,8 @@ static int rk3399_dmcfreq_target(struct device *dev, unsigned long *freq,
 	struct dev_pm_opp *opp;
 	unsigned long old_clk_rate = dmcfreq->rate;
 	unsigned long target_volt, target_rate;
+	struct arm_smccc_res res;
+	bool odt_enable = false;
 	int err;
 
 	opp = devfreq_recommended_opp(dev, freq, flags);
@@ -95,6 +103,19 @@ static int rk3399_dmcfreq_target(struct device *dev, unsigned long *freq,
 
 	mutex_lock(&dmcfreq->lock);
 
+	if (target_rate >= dmcfreq->odt_dis_freq)
+		odt_enable = true;
+
+	/*
+	 * This makes a SMC call to the TF-A to set the DDR PD (power-down)
+	 * timings and to enable or disable the ODT (on-die termination)
+	 * resistors.
+	 */
+	arm_smccc_smc(ROCKCHIP_SIP_DRAM_FREQ, dmcfreq->odt_pd_arg0,
+		      dmcfreq->odt_pd_arg1,
+		      ROCKCHIP_SIP_CONFIG_DRAM_SET_ODT_PD,
+		      odt_enable, 0, 0, 0, &res);
+
 	/*
 	 * If frequency scaling from low to high, adjust voltage first.
 	 * If frequency scaling from high to low, adjust frequency first.
@@ -294,11 +315,13 @@ static int rk3399_dmcfreq_probe(struct platform_device *pdev)
 {
 	struct arm_smccc_res res;
 	struct device *dev = &pdev->dev;
-	struct device_node *np = pdev->dev.of_node;
+	struct device_node *np = pdev->dev.of_node, *node;
 	struct rk3399_dmcfreq *data;
 	int ret, index, size;
 	uint32_t *timing;
 	struct dev_pm_opp *opp;
+	u32 ddr_type;
+	u32 val;
 
 	data = devm_kzalloc(dev, sizeof(struct rk3399_dmcfreq), GFP_KERNEL);
 	if (!data)
@@ -322,7 +345,7 @@ static int rk3399_dmcfreq_probe(struct platform_device *pdev)
 
 		dev_err(dev, "Cannot get the clk dmc_clk\n");
 		return PTR_ERR(data->dmc_clk);
-	};
+	}
 
 	data->edev = devfreq_event_get_edev_by_phandle(dev, 0);
 	if (IS_ERR(data->edev))
@@ -354,11 +377,57 @@ static int rk3399_dmcfreq_probe(struct platform_device *pdev)
 		}
 	}
 
+	node = of_parse_phandle(np, "rockchip,pmu", 0);
+	if (node) {
+		data->regmap_pmu = syscon_node_to_regmap(node);
+		if (IS_ERR(data->regmap_pmu))
+			return PTR_ERR(data->regmap_pmu);
+	}
+
+	regmap_read(data->regmap_pmu, RK3399_PMUGRF_OS_REG2, &val);
+	ddr_type = (val >> RK3399_PMUGRF_DDRTYPE_SHIFT) &
+		    RK3399_PMUGRF_DDRTYPE_MASK;
+
+	switch (ddr_type) {
+	case RK3399_PMUGRF_DDRTYPE_DDR3:
+		data->odt_dis_freq = data->timing.ddr3_odt_dis_freq;
+		break;
+	case RK3399_PMUGRF_DDRTYPE_LPDDR3:
+		data->odt_dis_freq = data->timing.lpddr3_odt_dis_freq;
+		break;
+	case RK3399_PMUGRF_DDRTYPE_LPDDR4:
+		data->odt_dis_freq = data->timing.lpddr4_odt_dis_freq;
+		break;
+	default:
+		return -EINVAL;
+	};
+
 	arm_smccc_smc(ROCKCHIP_SIP_DRAM_FREQ, 0, 0,
 		      ROCKCHIP_SIP_CONFIG_DRAM_INIT,
 		      0, 0, 0, 0, &res);
 
 	/*
+	 * In TF-A there is a platform SIP call to set the PD (power-down)
+	 * timings and to enable or disable the ODT (on-die termination).
+	 * This call needs three arguments as follows:
+	 *
+	 * arg0:
+	 *     bit[0-7]   : sr_idle
+	 *     bit[8-15]  : sr_mc_gate_idle
+	 *     bit[16-31] : standby idle
+	 * arg1:
+	 *     bit[0-11]  : pd_idle
+	 *     bit[16-27] : srpd_lite_idle
+	 * arg2:
+	 *     bit[0]     : odt enable
+	 */
+	data->odt_pd_arg0 = (data->timing.sr_idle & 0xff) |
+			    ((data->timing.sr_mc_gate_idle & 0xff) << 8) |
+			    ((data->timing.standby_idle & 0xffff) << 16);
+	data->odt_pd_arg1 = (data->timing.pd_idle & 0xfff) |
+			    ((data->timing.srpd_lite_idle & 0xfff) << 16);
+
+	/*
 	 * We add a devfreq driver to our parent since it has a device tree node
 	 * with operating points.
 	 */
diff --git a/drivers/devfreq/tegra-devfreq.c b/drivers/devfreq/tegra-devfreq.c
index c59d2eee5d30..c89ba7b834ff 100644
--- a/drivers/devfreq/tegra-devfreq.c
+++ b/drivers/devfreq/tegra-devfreq.c
@@ -573,10 +573,7 @@ static int tegra_governor_get_target(struct devfreq *devfreq,
 static int tegra_governor_event_handler(struct devfreq *devfreq,
 					unsigned int event, void *data)
 {
-	struct tegra_devfreq *tegra;
-	int ret = 0;
-
-	tegra = dev_get_drvdata(devfreq->dev.parent);
+	struct tegra_devfreq *tegra = dev_get_drvdata(devfreq->dev.parent);
 
 	switch (event) {
 	case DEVFREQ_GOV_START:
@@ -600,7 +597,7 @@ static int tegra_governor_event_handler(struct devfreq *devfreq,
 		break;
 	}
 
-	return ret;
+	return 0;
 }
 
 static struct devfreq_governor tegra_devfreq_governor = {
diff --git a/drivers/dma/bcm2835-dma.c b/drivers/dma/bcm2835-dma.c
index ec8a291d62ba..54093ffd0aef 100644
--- a/drivers/dma/bcm2835-dma.c
+++ b/drivers/dma/bcm2835-dma.c
@@ -671,7 +671,7 @@ static struct dma_async_tx_descriptor *bcm2835_dma_prep_slave_sg(
 	d = bcm2835_dma_create_cb_chain(chan, direction, false,
 					info, extra,
 					frames, src, dst, 0, 0,
-					GFP_KERNEL);
+					GFP_NOWAIT);
 	if (!d)
 		return NULL;
 
diff --git a/drivers/dma/mediatek/mtk-cqdma.c b/drivers/dma/mediatek/mtk-cqdma.c
index 131f3974740d..814853842e29 100644
--- a/drivers/dma/mediatek/mtk-cqdma.c
+++ b/drivers/dma/mediatek/mtk-cqdma.c
@@ -253,7 +253,7 @@ static void mtk_cqdma_start(struct mtk_cqdma_pchan *pc,
 #ifdef CONFIG_ARCH_DMA_ADDR_T_64BIT
 	mtk_dma_set(pc, MTK_CQDMA_DST2, cvd->dest >> MTK_CQDMA_ADDR2_SHFIT);
 #else
-	mtk_dma_set(pc, MTK_CQDMA_SRC2, 0);
+	mtk_dma_set(pc, MTK_CQDMA_DST2, 0);
 #endif
 
 	/* setup the length */
diff --git a/drivers/dma/sh/rcar-dmac.c b/drivers/dma/sh/rcar-dmac.c
index 2b4f25698169..e2a5398f89b5 100644
--- a/drivers/dma/sh/rcar-dmac.c
+++ b/drivers/dma/sh/rcar-dmac.c
@@ -1282,6 +1282,9 @@ static unsigned int rcar_dmac_chan_get_residue(struct rcar_dmac_chan *chan,
 	enum dma_status status;
 	unsigned int residue = 0;
 	unsigned int dptr = 0;
+	unsigned int chcrb;
+	unsigned int tcrb;
+	unsigned int i;
 
 	if (!desc)
 		return 0;
@@ -1330,14 +1333,31 @@ static unsigned int rcar_dmac_chan_get_residue(struct rcar_dmac_chan *chan,
 	}
 
 	/*
+	 * We need to read two registers.
+	 * Make sure the control register does not skip to next chunk
+	 * while reading the counter.
+	 * Trying it 3 times should be enough: Initial read, retry, retry
+	 * for the paranoid.
+	 */
+	for (i = 0; i < 3; i++) {
+		chcrb = rcar_dmac_chan_read(chan, RCAR_DMACHCRB) &
+					    RCAR_DMACHCRB_DPTR_MASK;
+		tcrb = rcar_dmac_chan_read(chan, RCAR_DMATCRB);
+		/* Still the same? */
+		if (chcrb == (rcar_dmac_chan_read(chan, RCAR_DMACHCRB) &
+			      RCAR_DMACHCRB_DPTR_MASK))
+			break;
+	}
+	WARN_ONCE(i >= 3, "residue might be not continuous!");
+
+	/*
 	 * In descriptor mode the descriptor running pointer is not maintained
 	 * by the interrupt handler, find the running descriptor from the
 	 * descriptor pointer field in the CHCRB register. In non-descriptor
 	 * mode just use the running descriptor pointer.
 	 */
 	if (desc->hwdescs.use) {
-		dptr = (rcar_dmac_chan_read(chan, RCAR_DMACHCRB) &
-			RCAR_DMACHCRB_DPTR_MASK) >> RCAR_DMACHCRB_DPTR_SHIFT;
+		dptr = chcrb >> RCAR_DMACHCRB_DPTR_SHIFT;
 		if (dptr == 0)
 			dptr = desc->nchunks;
 		dptr--;
@@ -1355,7 +1375,7 @@ static unsigned int rcar_dmac_chan_get_residue(struct rcar_dmac_chan *chan,
 	}
 
 	/* Add the residue for the current chunk. */
-	residue += rcar_dmac_chan_read(chan, RCAR_DMATCRB) << desc->xfer_shift;
+	residue += tcrb << desc->xfer_shift;
 
 	return residue;
 }
@@ -1368,6 +1388,7 @@ static enum dma_status rcar_dmac_tx_status(struct dma_chan *chan,
 	enum dma_status status;
 	unsigned long flags;
 	unsigned int residue;
+	bool cyclic;
 
 	status = dma_cookie_status(chan, cookie, txstate);
 	if (status == DMA_COMPLETE || !txstate)
@@ -1375,10 +1396,11 @@ static enum dma_status rcar_dmac_tx_status(struct dma_chan *chan,
 
 	spin_lock_irqsave(&rchan->lock, flags);
 	residue = rcar_dmac_chan_get_residue(rchan, cookie);
+	cyclic = rchan->desc.running ? rchan->desc.running->cyclic : false;
 	spin_unlock_irqrestore(&rchan->lock, flags);
 
 	/* if there's no residue, the cookie is complete */
-	if (!residue)
+	if (!residue && !cyclic)
 		return DMA_COMPLETE;
 
 	dma_set_residue(txstate, residue);
diff --git a/drivers/dma/stm32-mdma.c b/drivers/dma/stm32-mdma.c
index 4e0eede599a8..ac0301b69593 100644
--- a/drivers/dma/stm32-mdma.c
+++ b/drivers/dma/stm32-mdma.c
@@ -1578,11 +1578,9 @@ static int stm32_mdma_probe(struct platform_device *pdev)
 
 	dmadev->nr_channels = nr_channels;
 	dmadev->nr_requests = nr_requests;
-	ret = device_property_read_u32_array(&pdev->dev, "st,ahb-addr-masks",
+	device_property_read_u32_array(&pdev->dev, "st,ahb-addr-masks",
 				       dmadev->ahb_addr_masks,
 				       count);
-	if (ret)
-		return ret;
 	dmadev->nr_ahb_addr_masks = count;
 
 	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
diff --git a/drivers/dma/txx9dmac.c b/drivers/dma/txx9dmac.c
index eb45af71d3a3..e8d0881b64d8 100644
--- a/drivers/dma/txx9dmac.c
+++ b/drivers/dma/txx9dmac.c
@@ -327,7 +327,6 @@ static void txx9dmac_reset_chan(struct txx9dmac_chan *dc)
 	channel_writel(dc, SAIR, 0);
 	channel_writel(dc, DAIR, 0);
 	channel_writel(dc, CCR, 0);
-	mmiowb();
 }
 
 /* Called with dc->lock held and bh disabled */
@@ -954,7 +953,6 @@ static void txx9dmac_chain_dynamic(struct txx9dmac_chan *dc,
 	dma_sync_single_for_device(chan2parent(&dc->chan),
 				   prev->txd.phys, ddev->descsize,
 				   DMA_TO_DEVICE);
-	mmiowb();
 	if (!(channel_readl(dc, CSR) & TXX9_DMA_CSR_CHNEN) &&
 	    channel_read_CHAR(dc) == prev->txd.phys)
 		/* Restart chain DMA */
@@ -1080,7 +1078,6 @@ static void txx9dmac_free_chan_resources(struct dma_chan *chan)
 static void txx9dmac_off(struct txx9dmac_dev *ddev)
 {
 	dma_writel(ddev, MCR, 0);
-	mmiowb();
 }
 
 static int __init txx9dmac_chan_probe(struct platform_device *pdev)
diff --git a/drivers/edac/altera_edac.c b/drivers/edac/altera_edac.c
index 1bcf9aea0cdf..8816f74a22b4 100644
--- a/drivers/edac/altera_edac.c
+++ b/drivers/edac/altera_edac.c
@@ -9,6 +9,7 @@
 #include <linux/ctype.h>
 #include <linux/delay.h>
 #include <linux/edac.h>
+#include <linux/firmware/intel/stratix10-smc.h>
 #include <linux/genalloc.h>
 #include <linux/interrupt.h>
 #include <linux/irqchip/chained_irq.h>
@@ -1361,8 +1362,19 @@ static const struct edac_device_prv_data a10_l2ecc_data = {
 
 #ifdef CONFIG_EDAC_ALTERA_ETHERNET
 
+static int __init socfpga_init_ethernet_ecc(struct altr_edac_device_dev *dev)
+{
+	int ret;
+
+	ret = altr_init_a10_ecc_device_type("altr,socfpga-eth-mac-ecc");
+	if (ret)
+		return ret;
+
+	return altr_check_ecc_deps(dev);
+}
+
 static const struct edac_device_prv_data a10_enetecc_data = {
-	.setup = altr_check_ecc_deps,
+	.setup = socfpga_init_ethernet_ecc,
 	.ce_clear_mask = ALTR_A10_ECC_SERRPENA,
 	.ue_clear_mask = ALTR_A10_ECC_DERRPENA,
 	.ecc_enable_mask = ALTR_A10_COMMON_ECC_EN_CTL,
@@ -1374,21 +1386,25 @@ static const struct edac_device_prv_data a10_enetecc_data = {
 	.inject_fops = &altr_edac_a10_device_inject2_fops,
 };
 
-static int __init socfpga_init_ethernet_ecc(void)
-{
-	return altr_init_a10_ecc_device_type("altr,socfpga-eth-mac-ecc");
-}
-
-early_initcall(socfpga_init_ethernet_ecc);
-
 #endif	/* CONFIG_EDAC_ALTERA_ETHERNET */
 
 /********************** NAND Device Functions **********************/
 
 #ifdef CONFIG_EDAC_ALTERA_NAND
 
+static int __init socfpga_init_nand_ecc(struct altr_edac_device_dev *device)
+{
+	int ret;
+
+	ret = altr_init_a10_ecc_device_type("altr,socfpga-nand-ecc");
+	if (ret)
+		return ret;
+
+	return altr_check_ecc_deps(device);
+}
+
 static const struct edac_device_prv_data a10_nandecc_data = {
-	.setup = altr_check_ecc_deps,
+	.setup = socfpga_init_nand_ecc,
 	.ce_clear_mask = ALTR_A10_ECC_SERRPENA,
 	.ue_clear_mask = ALTR_A10_ECC_DERRPENA,
 	.ecc_enable_mask = ALTR_A10_COMMON_ECC_EN_CTL,
@@ -1400,21 +1416,25 @@ static const struct edac_device_prv_data a10_nandecc_data = {
 	.inject_fops = &altr_edac_a10_device_inject_fops,
 };
 
-static int __init socfpga_init_nand_ecc(void)
-{
-	return altr_init_a10_ecc_device_type("altr,socfpga-nand-ecc");
-}
-
-early_initcall(socfpga_init_nand_ecc);
-
 #endif	/* CONFIG_EDAC_ALTERA_NAND */
 
 /********************** DMA Device Functions **********************/
 
 #ifdef CONFIG_EDAC_ALTERA_DMA
 
+static int __init socfpga_init_dma_ecc(struct altr_edac_device_dev *device)
+{
+	int ret;
+
+	ret = altr_init_a10_ecc_device_type("altr,socfpga-dma-ecc");
+	if (ret)
+		return ret;
+
+	return altr_check_ecc_deps(device);
+}
+
 static const struct edac_device_prv_data a10_dmaecc_data = {
-	.setup = altr_check_ecc_deps,
+	.setup = socfpga_init_dma_ecc,
 	.ce_clear_mask = ALTR_A10_ECC_SERRPENA,
 	.ue_clear_mask = ALTR_A10_ECC_DERRPENA,
 	.ecc_enable_mask = ALTR_A10_COMMON_ECC_EN_CTL,
@@ -1426,21 +1446,25 @@ static const struct edac_device_prv_data a10_dmaecc_data = {
 	.inject_fops = &altr_edac_a10_device_inject_fops,
 };
 
-static int __init socfpga_init_dma_ecc(void)
-{
-	return altr_init_a10_ecc_device_type("altr,socfpga-dma-ecc");
-}
-
-early_initcall(socfpga_init_dma_ecc);
-
 #endif	/* CONFIG_EDAC_ALTERA_DMA */
 
 /********************** USB Device Functions **********************/
 
 #ifdef CONFIG_EDAC_ALTERA_USB
 
+static int __init socfpga_init_usb_ecc(struct altr_edac_device_dev *device)
+{
+	int ret;
+
+	ret = altr_init_a10_ecc_device_type("altr,socfpga-usb-ecc");
+	if (ret)
+		return ret;
+
+	return altr_check_ecc_deps(device);
+}
+
 static const struct edac_device_prv_data a10_usbecc_data = {
-	.setup = altr_check_ecc_deps,
+	.setup = socfpga_init_usb_ecc,
 	.ce_clear_mask = ALTR_A10_ECC_SERRPENA,
 	.ue_clear_mask = ALTR_A10_ECC_DERRPENA,
 	.ecc_enable_mask = ALTR_A10_COMMON_ECC_EN_CTL,
@@ -1452,21 +1476,25 @@ static const struct edac_device_prv_data a10_usbecc_data = {
 	.inject_fops = &altr_edac_a10_device_inject2_fops,
 };
 
-static int __init socfpga_init_usb_ecc(void)
-{
-	return altr_init_a10_ecc_device_type("altr,socfpga-usb-ecc");
-}
-
-early_initcall(socfpga_init_usb_ecc);
-
 #endif	/* CONFIG_EDAC_ALTERA_USB */
 
 /********************** QSPI Device Functions **********************/
 
 #ifdef CONFIG_EDAC_ALTERA_QSPI
 
+static int __init socfpga_init_qspi_ecc(struct altr_edac_device_dev *device)
+{
+	int ret;
+
+	ret = altr_init_a10_ecc_device_type("altr,socfpga-qspi-ecc");
+	if (ret)
+		return ret;
+
+	return altr_check_ecc_deps(device);
+}
+
 static const struct edac_device_prv_data a10_qspiecc_data = {
-	.setup = altr_check_ecc_deps,
+	.setup = socfpga_init_qspi_ecc,
 	.ce_clear_mask = ALTR_A10_ECC_SERRPENA,
 	.ue_clear_mask = ALTR_A10_ECC_DERRPENA,
 	.ecc_enable_mask = ALTR_A10_COMMON_ECC_EN_CTL,
@@ -1478,13 +1506,6 @@ static const struct edac_device_prv_data a10_qspiecc_data = {
 	.inject_fops = &altr_edac_a10_device_inject_fops,
 };
 
-static int __init socfpga_init_qspi_ecc(void)
-{
-	return altr_init_a10_ecc_device_type("altr,socfpga-qspi-ecc");
-}
-
-early_initcall(socfpga_init_qspi_ecc);
-
 #endif	/* CONFIG_EDAC_ALTERA_QSPI */
 
 /********************* SDMMC Device Functions **********************/
@@ -1593,6 +1614,35 @@ err_release_group_1:
 	return rc;
 }
 
+static int __init socfpga_init_sdmmc_ecc(struct altr_edac_device_dev *device)
+{
+	int rc = -ENODEV;
+	struct device_node *child;
+
+	child = of_find_compatible_node(NULL, NULL, "altr,socfpga-sdmmc-ecc");
+	if (!child)
+		return -ENODEV;
+
+	if (!of_device_is_available(child))
+		goto exit;
+
+	if (validate_parent_available(child))
+		goto exit;
+
+	/* Init portB */
+	rc = altr_init_a10_ecc_block(child, ALTR_A10_SDMMC_IRQ_MASK,
+				     a10_sdmmceccb_data.ecc_enable_mask, 1);
+	if (rc)
+		goto exit;
+
+	/* Setup portB */
+	return altr_portb_setup(device);
+
+exit:
+	of_node_put(child);
+	return rc;
+}
+
 static irqreturn_t altr_edac_a10_ecc_irq_portb(int irq, void *dev_id)
 {
 	struct altr_edac_device_dev *ad = dev_id;
@@ -1617,7 +1667,7 @@ static irqreturn_t altr_edac_a10_ecc_irq_portb(int irq, void *dev_id)
 }
 
 static const struct edac_device_prv_data a10_sdmmcecca_data = {
-	.setup = altr_portb_setup,
+	.setup = socfpga_init_sdmmc_ecc,
 	.ce_clear_mask = ALTR_A10_ECC_SERRPENA,
 	.ue_clear_mask = ALTR_A10_ECC_DERRPENA,
 	.ecc_enable_mask = ALTR_A10_COMMON_ECC_EN_CTL,
@@ -1630,7 +1680,7 @@ static const struct edac_device_prv_data a10_sdmmcecca_data = {
 };
 
 static const struct edac_device_prv_data a10_sdmmceccb_data = {
-	.setup = altr_portb_setup,
+	.setup = socfpga_init_sdmmc_ecc,
 	.ce_clear_mask = ALTR_A10_ECC_SERRPENB,
 	.ue_clear_mask = ALTR_A10_ECC_DERRPENB,
 	.ecc_enable_mask = ALTR_A10_COMMON_ECC_EN_CTL,
@@ -1642,35 +1692,6 @@ static const struct edac_device_prv_data a10_sdmmceccb_data = {
 	.inject_fops = &altr_edac_a10_device_inject_fops,
 };
 
-static int __init socfpga_init_sdmmc_ecc(void)
-{
-	int rc = -ENODEV;
-	struct device_node *child;
-
-	if (!socfpga_is_a10() && !socfpga_is_s10())
-		return -ENODEV;
-
-	child = of_find_compatible_node(NULL, NULL, "altr,socfpga-sdmmc-ecc");
-	if (!child) {
-		edac_printk(KERN_WARNING, EDAC_DEVICE, "SDMMC node not found\n");
-		return -ENODEV;
-	}
-
-	if (!of_device_is_available(child))
-		goto exit;
-
-	if (validate_parent_available(child))
-		goto exit;
-
-	rc = altr_init_a10_ecc_block(child, ALTR_A10_SDMMC_IRQ_MASK,
-				     a10_sdmmcecca_data.ecc_enable_mask, 1);
-exit:
-	of_node_put(child);
-	return rc;
-}
-
-early_initcall(socfpga_init_sdmmc_ecc);
-
 #endif	/* CONFIG_EDAC_ALTERA_SDMMC */
 
 /********************* Arria10 EDAC Device Functions *************************/
@@ -1762,28 +1783,24 @@ static ssize_t altr_edac_a10_device_trig2(struct file *file,
 	if (trig_type == ALTR_UE_TRIGGER_CHAR) {
 		writel(priv->ue_set_mask, set_addr);
 	} else {
-		/* Setup write of 0 to first 4 bytes */
-		writel(0x0, drvdata->base + ECC_BLK_WDATA0_OFST);
-		writel(0x0, drvdata->base + ECC_BLK_WDATA1_OFST);
-		writel(0x0, drvdata->base + ECC_BLK_WDATA2_OFST);
-		writel(0x0, drvdata->base + ECC_BLK_WDATA3_OFST);
-		/* Setup write of 4 bytes */
+		/* Setup read/write of 4 bytes */
 		writel(ECC_WORD_WRITE, drvdata->base + ECC_BLK_DBYTECTRL_OFST);
 		/* Setup Address to 0 */
-		writel(0x0, drvdata->base + ECC_BLK_ADDRESS_OFST);
-		/* Setup accctrl to write & data override */
-		writel(ECC_WRITE_DOVR, drvdata->base + ECC_BLK_ACCCTRL_OFST);
-		/* Kick it. */
-		writel(ECC_XACT_KICK, drvdata->base + ECC_BLK_STARTACC_OFST);
-		/* Setup accctrl to read & ecc override */
-		writel(ECC_READ_EOVR, drvdata->base + ECC_BLK_ACCCTRL_OFST);
+		writel(0, drvdata->base + ECC_BLK_ADDRESS_OFST);
+		/* Setup accctrl to read & ecc & data override */
+		writel(ECC_READ_EDOVR, drvdata->base + ECC_BLK_ACCCTRL_OFST);
 		/* Kick it. */
 		writel(ECC_XACT_KICK, drvdata->base + ECC_BLK_STARTACC_OFST);
 		/* Setup write for single bit change */
-		writel(0x1, drvdata->base + ECC_BLK_WDATA0_OFST);
-		writel(0x0, drvdata->base + ECC_BLK_WDATA1_OFST);
-		writel(0x0, drvdata->base + ECC_BLK_WDATA2_OFST);
-		writel(0x0, drvdata->base + ECC_BLK_WDATA3_OFST);
+		writel(readl(drvdata->base + ECC_BLK_RDATA0_OFST) ^ 0x1,
+		       drvdata->base + ECC_BLK_WDATA0_OFST);
+		writel(readl(drvdata->base + ECC_BLK_RDATA1_OFST),
+		       drvdata->base + ECC_BLK_WDATA1_OFST);
+		writel(readl(drvdata->base + ECC_BLK_RDATA2_OFST),
+		       drvdata->base + ECC_BLK_WDATA2_OFST);
+		writel(readl(drvdata->base + ECC_BLK_RDATA3_OFST),
+		       drvdata->base + ECC_BLK_WDATA3_OFST);
+
 		/* Copy Read ECC to Write ECC */
 		writel(readl(drvdata->base + ECC_BLK_RECC0_OFST),
 		       drvdata->base + ECC_BLK_WECC0_OFST);
@@ -1930,6 +1947,15 @@ static int altr_edac_a10_device_add(struct altr_arria10_edac *edac,
 		goto err_release_group1;
 	}
 
+#ifdef CONFIG_ARCH_STRATIX10
+	/* Use IRQ to determine SError origin instead of assigning IRQ */
+	rc = of_property_read_u32_index(np, "interrupts", 0, &altdev->db_irq);
+	if (rc) {
+		edac_printk(KERN_ERR, EDAC_DEVICE,
+			    "Unable to parse DB IRQ index\n");
+		goto err_release_group1;
+	}
+#else
 	altdev->db_irq = irq_of_parse_and_map(np, 1);
 	if (!altdev->db_irq) {
 		edac_printk(KERN_ERR, EDAC_DEVICE, "Error allocating DBIRQ\n");
@@ -1943,6 +1969,7 @@ static int altr_edac_a10_device_add(struct altr_arria10_edac *edac,
 		edac_printk(KERN_ERR, EDAC_DEVICE, "No DBERR IRQ resource\n");
 		goto err_release_group1;
 	}
+#endif
 
 	rc = edac_device_add_device(dci);
 	if (rc) {
@@ -2005,6 +2032,10 @@ static const struct irq_domain_ops a10_eccmgr_ic_ops = {
 /************** Stratix 10 EDAC Double Bit Error Handler ************/
 #define to_a10edac(p, m) container_of(p, struct altr_arria10_edac, m)
 
+#ifdef CONFIG_ARCH_STRATIX10
+/* panic routine issues reboot on non-zero panic_timeout */
+extern int panic_timeout;
+
 /*
  * The double bit error is handled through SError which is fatal. This is
  * called as a panic notifier to printout ECC error info as part of the panic.
@@ -2018,17 +2049,37 @@ static int s10_edac_dberr_handler(struct notifier_block *this,
 	regmap_read(edac->ecc_mgr_map, S10_SYSMGR_ECC_INTSTAT_DERR_OFST,
 		    &dberror);
 	regmap_write(edac->ecc_mgr_map, S10_SYSMGR_UE_VAL_OFST, dberror);
-	if (dberror & S10_DDR0_IRQ_MASK) {
-		regmap_read(edac->ecc_mgr_map, A10_DERRADDR_OFST, &err_addr);
-		regmap_write(edac->ecc_mgr_map, S10_SYSMGR_UE_ADDR_OFST,
-			     err_addr);
-		edac_printk(KERN_ERR, EDAC_MC,
-			    "EDAC: [Uncorrectable errors @ 0x%08X]\n\n",
-			    err_addr);
+	if (dberror & S10_DBE_IRQ_MASK) {
+		struct list_head *position;
+		struct altr_edac_device_dev *ed;
+		struct arm_smccc_res result;
+
+		/* Find the matching DBE in the list of devices */
+		list_for_each(position, &edac->a10_ecc_devices) {
+			ed = list_entry(position, struct altr_edac_device_dev,
+					next);
+			if (!(BIT(ed->db_irq) & dberror))
+				continue;
+
+			writel(ALTR_A10_ECC_DERRPENA,
+			       ed->base + ALTR_A10_ECC_INTSTAT_OFST);
+			err_addr = readl(ed->base + ALTR_S10_DERR_ADDRA_OFST);
+			regmap_write(edac->ecc_mgr_map,
+				     S10_SYSMGR_UE_ADDR_OFST, err_addr);
+			edac_printk(KERN_ERR, EDAC_DEVICE,
+				    "EDAC: [Fatal DBE on %s @ 0x%08X]\n",
+				    ed->edac_dev_name, err_addr);
+			break;
+		}
+		/* Notify the System through SMC. Reboot delay = 1 second */
+		panic_timeout = 1;
+		arm_smccc_smc(INTEL_SIP_SMC_ECC_DBE, dberror, 0, 0, 0, 0,
+			      0, 0, &result);
 	}
 
 	return NOTIFY_DONE;
 }
+#endif
 
 /****************** Arria 10 EDAC Probe Function *********************/
 static int altr_edac_a10_probe(struct platform_device *pdev)
@@ -2098,16 +2149,8 @@ static int altr_edac_a10_probe(struct platform_device *pdev)
 					 altr_edac_a10_irq_handler,
 					 edac);
 
-	if (socfpga_is_a10()) {
-		edac->db_irq = platform_get_irq(pdev, 1);
-		if (edac->db_irq < 0) {
-			dev_err(&pdev->dev, "No DBERR IRQ resource\n");
-			return edac->db_irq;
-		}
-		irq_set_chained_handler_and_data(edac->db_irq,
-						 altr_edac_a10_irq_handler,
-						 edac);
-	} else {
+#ifdef CONFIG_ARCH_STRATIX10
+	{
 		int dberror, err_addr;
 
 		edac->panic_notifier.notifier_call = s10_edac_dberr_handler;
@@ -2130,6 +2173,15 @@ static int altr_edac_a10_probe(struct platform_device *pdev)
 				     S10_SYSMGR_UE_ADDR_OFST, 0);
 		}
 	}
+#else
+	edac->db_irq = platform_get_irq(pdev, 1);
+	if (edac->db_irq < 0) {
+		dev_err(&pdev->dev, "No DBERR IRQ resource\n");
+		return edac->db_irq;
+	}
+	irq_set_chained_handler_and_data(edac->db_irq,
+					 altr_edac_a10_irq_handler, edac);
+#endif
 
 	for_each_child_of_node(pdev->dev.of_node, child) {
 		if (!of_device_is_available(child))
diff --git a/drivers/edac/altera_edac.h b/drivers/edac/altera_edac.h
index f8664bac9fa8..55654cc4bcdf 100644
--- a/drivers/edac/altera_edac.h
+++ b/drivers/edac/altera_edac.h
@@ -289,6 +289,7 @@ struct altr_sdram_mc_data {
 #define ALTR_A10_ECC_INIT_WATCHDOG_10US      10000
 
 /************* Stratix10 Defines **************/
+#define ALTR_S10_DERR_ADDRA_OFST          0x2C
 
 /* Stratix10 ECC Manager Defines */
 #define S10_SYSMGR_ECC_INTMASK_CLR_OFST   0x98
@@ -299,6 +300,7 @@ struct altr_sdram_mc_data {
 #define S10_SYSMGR_UE_ADDR_OFST           0x224
 
 #define S10_DDR0_IRQ_MASK                 BIT(16)
+#define S10_DBE_IRQ_MASK                  0x3FE
 
 /* Define ECC Block Offsets for peripherals */
 #define ECC_BLK_ADDRESS_OFST              0x40
@@ -319,7 +321,7 @@ struct altr_sdram_mc_data {
 #define ECC_BLK_STARTACC_OFST             0x7C
 
 #define ECC_XACT_KICK                     0x10000
-#define ECC_WORD_WRITE                    0xF
+#define ECC_WORD_WRITE                    0xFF
 #define ECC_WRITE_DOVR                    0x101
 #define ECC_WRITE_EDOVR                   0x103
 #define ECC_READ_EOVR                     0x2
@@ -370,69 +372,4 @@ struct altr_arria10_edac {
 	struct notifier_block	panic_notifier;
 };
 
-/*
- * Functions specified by ARM SMC Calling convention:
- *
- * FAST call executes atomic operations, returns when the requested operation
- * has completed.
- * STD call starts a operation which can be preempted by a non-secure
- * interrupt. The call can return before the requested operation has
- * completed.
- *
- * a0..a7 is used as register names in the descriptions below, on arm32
- * that translates to r0..r7 and on arm64 to w0..w7.
- */
-
-#define INTEL_SIP_SMC_STD_CALL_VAL(func_num) \
-	ARM_SMCCC_CALL_VAL(ARM_SMCCC_STD_CALL, ARM_SMCCC_SMC_64, \
-	ARM_SMCCC_OWNER_SIP, (func_num))
-
-#define INTEL_SIP_SMC_FAST_CALL_VAL(func_num) \
-	ARM_SMCCC_CALL_VAL(ARM_SMCCC_FAST_CALL, ARM_SMCCC_SMC_64, \
-	ARM_SMCCC_OWNER_SIP, (func_num))
-
-#define INTEL_SIP_SMC_RETURN_UNKNOWN_FUNCTION		0xFFFFFFFF
-#define INTEL_SIP_SMC_STATUS_OK				0x0
-#define INTEL_SIP_SMC_REG_ERROR				0x5
-
-/*
- * Request INTEL_SIP_SMC_REG_READ
- *
- * Read a protected register using SMCCC
- *
- * Call register usage:
- * a0: INTEL_SIP_SMC_REG_READ.
- * a1: register address.
- * a2-7: not used.
- *
- * Return status:
- * a0: INTEL_SIP_SMC_STATUS_OK, INTEL_SIP_SMC_REG_ERROR, or
- *     INTEL_SIP_SMC_RETURN_UNKNOWN_FUNCTION
- * a1: Value in the register
- * a2-3: not used.
- */
-#define INTEL_SIP_SMC_FUNCID_REG_READ 7
-#define INTEL_SIP_SMC_REG_READ \
-	INTEL_SIP_SMC_FAST_CALL_VAL(INTEL_SIP_SMC_FUNCID_REG_READ)
-
-/*
- * Request INTEL_SIP_SMC_REG_WRITE
- *
- * Write a protected register using SMCCC
- *
- * Call register usage:
- * a0: INTEL_SIP_SMC_REG_WRITE.
- * a1: register address
- * a2: value to program into register.
- * a3-7: not used.
- *
- * Return status:
- * a0: INTEL_SIP_SMC_STATUS_OK, INTEL_SIP_SMC_REG_ERROR, or
- *     INTEL_SIP_SMC_RETURN_UNKNOWN_FUNCTION
- * a1-3: not used.
- */
-#define INTEL_SIP_SMC_FUNCID_REG_WRITE 8
-#define INTEL_SIP_SMC_REG_WRITE \
-	INTEL_SIP_SMC_FAST_CALL_VAL(INTEL_SIP_SMC_FUNCID_REG_WRITE)
-
 #endif	/* #ifndef _ALTERA_EDAC_H */
diff --git a/drivers/edac/amd64_edac.c b/drivers/edac/amd64_edac.c
index 6ea98575a402..e2a99466faaa 100644
--- a/drivers/edac/amd64_edac.c
+++ b/drivers/edac/amd64_edac.c
@@ -18,6 +18,9 @@ static struct msr __percpu *msrs;
 /* Per-node stuff */
 static struct ecc_settings **ecc_stngs;
 
+/* Number of Unified Memory Controllers */
+static u8 num_umcs;
+
 /*
  * Valid scrub rates for the K8 hardware memory scrubber. We map the scrubbing
  * bandwidth to a valid bit pattern. The 'set' operation finds the 'matching-
@@ -449,6 +452,9 @@ static void get_cs_base_and_mask(struct amd64_pvt *pvt, int csrow, u8 dct,
 #define for_each_chip_select_mask(i, dct, pvt) \
 	for (i = 0; i < pvt->csels[dct].m_cnt; i++)
 
+#define for_each_umc(i) \
+	for (i = 0; i < num_umcs; i++)
+
 /*
  * @input_addr is an InputAddr associated with the node given by mci. Return the
  * csrow that input_addr maps to, or -1 on failure (no csrow claims input_addr).
@@ -722,7 +728,7 @@ static unsigned long determine_edac_cap(struct amd64_pvt *pvt)
 	if (pvt->umc) {
 		u8 i, umc_en_mask = 0, dimm_ecc_en_mask = 0;
 
-		for (i = 0; i < NUM_UMCS; i++) {
+		for_each_umc(i) {
 			if (!(pvt->umc[i].sdp_ctrl & UMC_SDP_INIT))
 				continue;
 
@@ -781,6 +787,22 @@ static void debug_dump_dramcfg_low(struct amd64_pvt *pvt, u32 dclr, int chan)
 		 (dclr & BIT(15)) ?  "yes" : "no");
 }
 
+/*
+ * The Address Mask should be a contiguous set of bits in the non-interleaved
+ * case. So to check for CS interleaving, find the most- and least-significant
+ * bits of the mask, generate a contiguous bitmask, and compare the two.
+ */
+static bool f17_cs_interleaved(struct amd64_pvt *pvt, u8 ctrl, int cs)
+{
+	u32 mask = pvt->csels[ctrl].csmasks[cs >> 1];
+	u32 msb = fls(mask) - 1, lsb = ffs(mask) - 1;
+	u32 test_mask = GENMASK(msb, lsb);
+
+	edac_dbg(1, "mask=0x%08x test_mask=0x%08x\n", mask, test_mask);
+
+	return mask ^ test_mask;
+}
+
 static void debug_display_dimm_sizes_df(struct amd64_pvt *pvt, u8 ctrl)
 {
 	int dimm, size0, size1, cs0, cs1;
@@ -797,8 +819,19 @@ static void debug_display_dimm_sizes_df(struct amd64_pvt *pvt, u8 ctrl)
 		size1 = 0;
 		cs1 = dimm * 2 + 1;
 
-		if (csrow_enabled(cs1, ctrl, pvt))
-			size1 = pvt->ops->dbam_to_cs(pvt, ctrl, 0, cs1);
+		if (csrow_enabled(cs1, ctrl, pvt)) {
+			/*
+			 * CS interleaving is only supported if both CSes have
+			 * the same amount of memory. Because they are
+			 * interleaved, it will look like both CSes have the
+			 * full amount of memory. Save the size for both as
+			 * half the amount we found on CS0, if interleaved.
+			 */
+			if (f17_cs_interleaved(pvt, ctrl, cs1))
+				size1 = size0 = (size0 >> 1);
+			else
+				size1 = pvt->ops->dbam_to_cs(pvt, ctrl, 0, cs1);
+		}
 
 		amd64_info(EDAC_MC ": %d: %5dMB %d: %5dMB\n",
 				cs0,	size0,
@@ -811,7 +844,7 @@ static void __dump_misc_regs_df(struct amd64_pvt *pvt)
 	struct amd64_umc *umc;
 	u32 i, tmp, umc_base;
 
-	for (i = 0; i < NUM_UMCS; i++) {
+	for_each_umc(i) {
 		umc_base = get_umc_base(i);
 		umc = &pvt->umc[i];
 
@@ -894,8 +927,7 @@ static void dump_misc_regs(struct amd64_pvt *pvt)
 
 	edac_dbg(1, "  DramHoleValid: %s\n", dhar_valid(pvt) ? "yes" : "no");
 
-	amd64_info("using %s syndromes.\n",
-			((pvt->ecc_sym_sz == 8) ? "x8" : "x4"));
+	amd64_info("using x%u syndromes.\n", pvt->ecc_sym_sz);
 }
 
 /*
@@ -1388,7 +1420,7 @@ static int f17_early_channel_count(struct amd64_pvt *pvt)
 	int i, channels = 0;
 
 	/* SDP Control bit 31 (SdpInit) is clear for unused UMC channels */
-	for (i = 0; i < NUM_UMCS; i++)
+	for_each_umc(i)
 		channels += !!(pvt->umc[i].sdp_ctrl & UMC_SDP_INIT);
 
 	amd64_info("MCT channel count: %d\n", channels);
@@ -2211,6 +2243,15 @@ static struct amd64_family_type family_types[] = {
 			.dbam_to_cs		= f17_base_addr_to_cs_size,
 		}
 	},
+	[F17_M30H_CPUS] = {
+		.ctl_name = "F17h_M30h",
+		.f0_id = PCI_DEVICE_ID_AMD_17H_M30H_DF_F0,
+		.f6_id = PCI_DEVICE_ID_AMD_17H_M30H_DF_F6,
+		.ops = {
+			.early_channel_count	= f17_early_channel_count,
+			.dbam_to_cs		= f17_base_addr_to_cs_size,
+		}
+	},
 };
 
 /*
@@ -2464,18 +2505,14 @@ static inline void decode_bus_error(int node_id, struct mce *m)
  * To find the UMC channel represented by this bank we need to match on its
  * instance_id. The instance_id of a bank is held in the lower 32 bits of its
  * IPID.
+ *
+ * Currently, we can derive the channel number by looking at the 6th nibble in
+ * the instance_id. For example, instance_id=0xYXXXXX where Y is the channel
+ * number.
  */
-static int find_umc_channel(struct amd64_pvt *pvt, struct mce *m)
+static int find_umc_channel(struct mce *m)
 {
-	u32 umc_instance_id[] = {0x50f00, 0x150f00};
-	u32 instance_id = m->ipid & GENMASK(31, 0);
-	int i, channel = -1;
-
-	for (i = 0; i < ARRAY_SIZE(umc_instance_id); i++)
-		if (umc_instance_id[i] == instance_id)
-			channel = i;
-
-	return channel;
+	return (m->ipid & GENMASK(31, 0)) >> 20;
 }
 
 static void decode_umc_error(int node_id, struct mce *m)
@@ -2497,11 +2534,7 @@ static void decode_umc_error(int node_id, struct mce *m)
 	if (m->status & MCI_STATUS_DEFERRED)
 		ecc_type = 3;
 
-	err.channel = find_umc_channel(pvt, m);
-	if (err.channel < 0) {
-		err.err_code = ERR_CHANNEL;
-		goto log_error;
-	}
+	err.channel = find_umc_channel(m);
 
 	if (umc_normaddr_to_sysaddr(m->addr, pvt->mc_node_id, err.channel, &sys_addr)) {
 		err.err_code = ERR_NORM_ADDR;
@@ -2603,19 +2636,19 @@ static void determine_ecc_sym_sz(struct amd64_pvt *pvt)
 	if (pvt->umc) {
 		u8 i;
 
-		for (i = 0; i < NUM_UMCS; i++) {
+		for_each_umc(i) {
 			/* Check enabled channels only: */
-			if ((pvt->umc[i].sdp_ctrl & UMC_SDP_INIT) &&
-			    (pvt->umc[i].ecc_ctrl & BIT(7))) {
-				pvt->ecc_sym_sz = 8;
-				break;
+			if (pvt->umc[i].sdp_ctrl & UMC_SDP_INIT) {
+				if (pvt->umc[i].ecc_ctrl & BIT(9)) {
+					pvt->ecc_sym_sz = 16;
+					return;
+				} else if (pvt->umc[i].ecc_ctrl & BIT(7)) {
+					pvt->ecc_sym_sz = 8;
+					return;
+				}
 			}
 		}
-
-		return;
-	}
-
-	if (pvt->fam >= 0x10) {
+	} else if (pvt->fam >= 0x10) {
 		u32 tmp;
 
 		amd64_read_pci_cfg(pvt->F3, EXT_NB_MCA_CFG, &tmp);
@@ -2639,7 +2672,7 @@ static void __read_mc_regs_df(struct amd64_pvt *pvt)
 	u32 i, umc_base;
 
 	/* Read registers from each UMC */
-	for (i = 0; i < NUM_UMCS; i++) {
+	for_each_umc(i) {
 
 		umc_base = get_umc_base(i);
 		umc = &pvt->umc[i];
@@ -3052,7 +3085,7 @@ static bool ecc_enabled(struct pci_dev *F3, u16 nid)
 	if (boot_cpu_data.x86 >= 0x17) {
 		u8 umc_en_mask = 0, ecc_en_mask = 0;
 
-		for (i = 0; i < NUM_UMCS; i++) {
+		for_each_umc(i) {
 			u32 base = get_umc_base(i);
 
 			/* Only check enabled UMCs. */
@@ -3105,7 +3138,7 @@ f17h_determine_edac_ctl_cap(struct mem_ctl_info *mci, struct amd64_pvt *pvt)
 {
 	u8 i, ecc_en = 1, cpk_en = 1;
 
-	for (i = 0; i < NUM_UMCS; i++) {
+	for_each_umc(i) {
 		if (pvt->umc[i].sdp_ctrl & UMC_SDP_INIT) {
 			ecc_en &= !!(pvt->umc[i].umc_cap_hi & UMC_ECC_ENABLED);
 			cpk_en &= !!(pvt->umc[i].umc_cap_hi & UMC_ECC_CHIPKILL_CAP);
@@ -3203,6 +3236,10 @@ static struct amd64_family_type *per_family_init(struct amd64_pvt *pvt)
 			fam_type = &family_types[F17_M10H_CPUS];
 			pvt->ops = &family_types[F17_M10H_CPUS].ops;
 			break;
+		} else if (pvt->model >= 0x30 && pvt->model <= 0x3f) {
+			fam_type = &family_types[F17_M30H_CPUS];
+			pvt->ops = &family_types[F17_M30H_CPUS].ops;
+			break;
 		}
 		/* fall through */
 	case 0x18:
@@ -3236,6 +3273,22 @@ static const struct attribute_group *amd64_edac_attr_groups[] = {
 	NULL
 };
 
+/* Set the number of Unified Memory Controllers in the system. */
+static void compute_num_umcs(void)
+{
+	u8 model = boot_cpu_data.x86_model;
+
+	if (boot_cpu_data.x86 < 0x17)
+		return;
+
+	if (model >= 0x30 && model <= 0x3f)
+		num_umcs = 8;
+	else
+		num_umcs = 2;
+
+	edac_dbg(1, "Number of UMCs: %x", num_umcs);
+}
+
 static int init_one_instance(unsigned int nid)
 {
 	struct pci_dev *F3 = node_to_amd_nb(nid)->misc;
@@ -3260,7 +3313,7 @@ static int init_one_instance(unsigned int nid)
 		goto err_free;
 
 	if (pvt->fam >= 0x17) {
-		pvt->umc = kcalloc(NUM_UMCS, sizeof(struct amd64_umc), GFP_KERNEL);
+		pvt->umc = kcalloc(num_umcs, sizeof(struct amd64_umc), GFP_KERNEL);
 		if (!pvt->umc) {
 			ret = -ENOMEM;
 			goto err_free;
@@ -3299,8 +3352,14 @@ static int init_one_instance(unsigned int nid)
 	 * Always allocate two channels since we can have setups with DIMMs on
 	 * only one channel. Also, this simplifies handling later for the price
 	 * of a couple of KBs tops.
+	 *
+	 * On Fam17h+, the number of controllers may be greater than two. So set
+	 * the size equal to the maximum number of UMCs.
 	 */
-	layers[1].size = 2;
+	if (pvt->fam >= 0x17)
+		layers[1].size = num_umcs;
+	else
+		layers[1].size = 2;
 	layers[1].is_virt_csrow = false;
 
 	mci = edac_mc_alloc(nid, ARRAY_SIZE(layers), layers, 0);
@@ -3481,6 +3540,8 @@ static int __init amd64_edac_init(void)
 	if (!msrs)
 		goto err_free;
 
+	compute_num_umcs();
+
 	for (i = 0; i < amd_nb_num(); i++) {
 		err = probe_one_instance(i);
 		if (err) {
diff --git a/drivers/edac/amd64_edac.h b/drivers/edac/amd64_edac.h
index 4242f8e39c18..8f66472f7adc 100644
--- a/drivers/edac/amd64_edac.h
+++ b/drivers/edac/amd64_edac.h
@@ -117,6 +117,8 @@
 #define PCI_DEVICE_ID_AMD_17H_DF_F6	0x1466
 #define PCI_DEVICE_ID_AMD_17H_M10H_DF_F0 0x15e8
 #define PCI_DEVICE_ID_AMD_17H_M10H_DF_F6 0x15ee
+#define PCI_DEVICE_ID_AMD_17H_M30H_DF_F0 0x1490
+#define PCI_DEVICE_ID_AMD_17H_M30H_DF_F6 0x1496
 
 /*
  * Function 1 - Address Map
@@ -272,8 +274,6 @@
 
 #define UMC_SDP_INIT			BIT(31)
 
-#define NUM_UMCS			2
-
 enum amd_families {
 	K8_CPUS = 0,
 	F10_CPUS,
@@ -284,6 +284,7 @@ enum amd_families {
 	F16_M30H_CPUS,
 	F17_CPUS,
 	F17_M10H_CPUS,
+	F17_M30H_CPUS,
 	NUM_FAMILIES,
 };
 
@@ -363,7 +364,7 @@ struct amd64_pvt {
 	u32 dct_sel_hi;		/* DRAM Controller Select High */
 	u32 online_spare;	/* On-Line spare Reg */
 
-	/* x4 or x8 syndromes in use */
+	/* x4, x8, or x16 syndromes in use */
 	u8 ecc_sym_sz;
 
 	/* place to store error injection parameters prior to issue */
@@ -396,8 +397,8 @@ struct err_info {
 
 static inline u32 get_umc_base(u8 channel)
 {
-	/* ch0: 0x50000, ch1: 0x150000 */
-	return 0x50000 + (!!channel << 20);
+	/* chY: 0xY50000 */
+	return 0x50000 + (channel << 20);
 }
 
 static inline u64 get_dram_base(struct amd64_pvt *pvt, u8 i)
diff --git a/drivers/edac/i10nm_base.c b/drivers/edac/i10nm_base.c
index c334fb7c63df..6f06aec4877c 100644
--- a/drivers/edac/i10nm_base.c
+++ b/drivers/edac/i10nm_base.c
@@ -181,6 +181,54 @@ static struct notifier_block i10nm_mce_dec = {
 	.priority	= MCE_PRIO_EDAC,
 };
 
+#ifdef CONFIG_EDAC_DEBUG
+/*
+ * Debug feature.
+ * Exercise the address decode logic by writing an address to
+ * /sys/kernel/debug/edac/i10nm_test/addr.
+ */
+static struct dentry *i10nm_test;
+
+static int debugfs_u64_set(void *data, u64 val)
+{
+	struct mce m;
+
+	pr_warn_once("Fake error to 0x%llx injected via debugfs\n", val);
+
+	memset(&m, 0, sizeof(m));
+	/* ADDRV + MemRd + Unknown channel */
+	m.status = MCI_STATUS_ADDRV + 0x90;
+	/* One corrected error */
+	m.status |= BIT_ULL(MCI_STATUS_CEC_SHIFT);
+	m.addr = val;
+	skx_mce_check_error(NULL, 0, &m);
+
+	return 0;
+}
+DEFINE_SIMPLE_ATTRIBUTE(fops_u64_wo, NULL, debugfs_u64_set, "%llu\n");
+
+static void setup_i10nm_debug(void)
+{
+	i10nm_test = edac_debugfs_create_dir("i10nm_test");
+	if (!i10nm_test)
+		return;
+
+	if (!edac_debugfs_create_file("addr", 0200, i10nm_test,
+				      NULL, &fops_u64_wo)) {
+		debugfs_remove(i10nm_test);
+		i10nm_test = NULL;
+	}
+}
+
+static void teardown_i10nm_debug(void)
+{
+	debugfs_remove_recursive(i10nm_test);
+}
+#else
+static inline void setup_i10nm_debug(void) {}
+static inline void teardown_i10nm_debug(void) {}
+#endif /*CONFIG_EDAC_DEBUG*/
+
 static int __init i10nm_init(void)
 {
 	u8 mc = 0, src_id = 0, node_id = 0;
@@ -249,7 +297,7 @@ static int __init i10nm_init(void)
 
 	opstate_init();
 	mce_register_decode_chain(&i10nm_mce_dec);
-	setup_skx_debug("i10nm_test");
+	setup_i10nm_debug();
 
 	i10nm_printk(KERN_INFO, "%s\n", I10NM_REVISION);
 
@@ -262,7 +310,7 @@ fail:
 static void __exit i10nm_exit(void)
 {
 	edac_dbg(2, "\n");
-	teardown_skx_debug();
+	teardown_i10nm_debug();
 	mce_unregister_decode_chain(&i10nm_mce_dec);
 	skx_adxl_put();
 	skx_remove();
diff --git a/drivers/edac/mce_amd.c b/drivers/edac/mce_amd.c
index 0a1814dad6cf..bb0202ad7a13 100644
--- a/drivers/edac/mce_amd.c
+++ b/drivers/edac/mce_amd.c
@@ -1004,7 +1004,7 @@ static inline void amd_decode_err_code(u16 ec)
 /*
  * Filter out unwanted MCE signatures here.
  */
-static bool amd_filter_mce(struct mce *m)
+static bool ignore_mce(struct mce *m)
 {
 	/*
 	 * NB GART TLB error reporting is disabled by default.
@@ -1038,7 +1038,7 @@ amd_decode_mce(struct notifier_block *nb, unsigned long val, void *data)
 	unsigned int fam = x86_family(m->cpuid);
 	int ecc;
 
-	if (amd_filter_mce(m))
+	if (ignore_mce(m))
 		return NOTIFY_STOP;
 
 	pr_emerg(HW_ERR "%s\n", decode_error_status(m));
diff --git a/drivers/edac/skx_base.c b/drivers/edac/skx_base.c
index adae4c848ca1..a5c8fa3a249a 100644
--- a/drivers/edac/skx_base.c
+++ b/drivers/edac/skx_base.c
@@ -540,6 +540,54 @@ static struct notifier_block skx_mce_dec = {
 	.priority	= MCE_PRIO_EDAC,
 };
 
+#ifdef CONFIG_EDAC_DEBUG
+/*
+ * Debug feature.
+ * Exercise the address decode logic by writing an address to
+ * /sys/kernel/debug/edac/skx_test/addr.
+ */
+static struct dentry *skx_test;
+
+static int debugfs_u64_set(void *data, u64 val)
+{
+	struct mce m;
+
+	pr_warn_once("Fake error to 0x%llx injected via debugfs\n", val);
+
+	memset(&m, 0, sizeof(m));
+	/* ADDRV + MemRd + Unknown channel */
+	m.status = MCI_STATUS_ADDRV + 0x90;
+	/* One corrected error */
+	m.status |= BIT_ULL(MCI_STATUS_CEC_SHIFT);
+	m.addr = val;
+	skx_mce_check_error(NULL, 0, &m);
+
+	return 0;
+}
+DEFINE_SIMPLE_ATTRIBUTE(fops_u64_wo, NULL, debugfs_u64_set, "%llu\n");
+
+static void setup_skx_debug(void)
+{
+	skx_test = edac_debugfs_create_dir("skx_test");
+	if (!skx_test)
+		return;
+
+	if (!edac_debugfs_create_file("addr", 0200, skx_test,
+				      NULL, &fops_u64_wo)) {
+		debugfs_remove(skx_test);
+		skx_test = NULL;
+	}
+}
+
+static void teardown_skx_debug(void)
+{
+	debugfs_remove_recursive(skx_test);
+}
+#else
+static inline void setup_skx_debug(void) {}
+static inline void teardown_skx_debug(void) {}
+#endif /*CONFIG_EDAC_DEBUG*/
+
 /*
  * skx_init:
  *	make sure we are running on the correct cpu model
@@ -619,7 +667,7 @@ static int __init skx_init(void)
 	/* Ensure that the OPSTATE is set correctly for POLL or NMI */
 	opstate_init();
 
-	setup_skx_debug("skx_test");
+	setup_skx_debug();
 
 	mce_register_decode_chain(&skx_mce_dec);
 
diff --git a/drivers/edac/skx_common.c b/drivers/edac/skx_common.c
index 0e96e7b5b0a7..b0dddcfa9baa 100644
--- a/drivers/edac/skx_common.c
+++ b/drivers/edac/skx_common.c
@@ -1,7 +1,15 @@
 // SPDX-License-Identifier: GPL-2.0
 /*
- * Common codes for both the skx_edac driver and Intel 10nm server EDAC driver.
- * Originally split out from the skx_edac driver.
+ *
+ * Shared code by both skx_edac and i10nm_edac. Originally split out
+ * from the skx_edac driver.
+ *
+ * This file is linked into both skx_edac and i10nm_edac drivers. In
+ * order to avoid link errors, this file must be like a pure library
+ * without including symbols and defines which would otherwise conflict,
+ * when linked once into a module and into a built-in object, at the
+ * same time. For example, __this_module symbol references when that
+ * file is being linked into a built-in object.
  *
  * Copyright (c) 2018, Intel Corporation.
  */
@@ -644,48 +652,3 @@ void skx_remove(void)
 		kfree(d);
 	}
 }
-
-#ifdef CONFIG_EDAC_DEBUG
-/*
- * Debug feature.
- * Exercise the address decode logic by writing an address to
- * /sys/kernel/debug/edac/dirname/addr.
- */
-static struct dentry *skx_test;
-
-static int debugfs_u64_set(void *data, u64 val)
-{
-	struct mce m;
-
-	pr_warn_once("Fake error to 0x%llx injected via debugfs\n", val);
-
-	memset(&m, 0, sizeof(m));
-	/* ADDRV + MemRd + Unknown channel */
-	m.status = MCI_STATUS_ADDRV + 0x90;
-	/* One corrected error */
-	m.status |= BIT_ULL(MCI_STATUS_CEC_SHIFT);
-	m.addr = val;
-	skx_mce_check_error(NULL, 0, &m);
-
-	return 0;
-}
-DEFINE_SIMPLE_ATTRIBUTE(fops_u64_wo, NULL, debugfs_u64_set, "%llu\n");
-
-void setup_skx_debug(const char *dirname)
-{
-	skx_test = edac_debugfs_create_dir(dirname);
-	if (!skx_test)
-		return;
-
-	if (!edac_debugfs_create_file("addr", 0200, skx_test,
-				      NULL, &fops_u64_wo)) {
-		debugfs_remove(skx_test);
-		skx_test = NULL;
-	}
-}
-
-void teardown_skx_debug(void)
-{
-	debugfs_remove_recursive(skx_test);
-}
-#endif /*CONFIG_EDAC_DEBUG*/
diff --git a/drivers/edac/skx_common.h b/drivers/edac/skx_common.h
index d25374e34d4f..d18fa98669af 100644
--- a/drivers/edac/skx_common.h
+++ b/drivers/edac/skx_common.h
@@ -141,12 +141,4 @@ int skx_mce_check_error(struct notifier_block *nb, unsigned long val,
 
 void skx_remove(void);
 
-#ifdef CONFIG_EDAC_DEBUG
-void setup_skx_debug(const char *dirname);
-void teardown_skx_debug(void);
-#else
-static inline void setup_skx_debug(const char *dirname) {}
-static inline void teardown_skx_debug(void) {}
-#endif /*CONFIG_EDAC_DEBUG*/
-
 #endif /* _SKX_COMM_EDAC_H */
diff --git a/drivers/extcon/Kconfig b/drivers/extcon/Kconfig
index 8e17149655f0..540e8cd16ee6 100644
--- a/drivers/extcon/Kconfig
+++ b/drivers/extcon/Kconfig
@@ -116,7 +116,7 @@ config EXTCON_PALMAS
 
 config EXTCON_PTN5150
 	tristate "NXP PTN5150 CC LOGIC USB EXTCON support"
-	depends on I2C && GPIOLIB || COMPILE_TEST
+	depends on I2C && (GPIOLIB || COMPILE_TEST)
 	select REGMAP_I2C
 	help
 	  Say Y here to enable support for USB peripheral and USB host
diff --git a/drivers/extcon/extcon-axp288.c b/drivers/extcon/extcon-axp288.c
index a983708b77a6..50f9402fb325 100644
--- a/drivers/extcon/extcon-axp288.c
+++ b/drivers/extcon/extcon-axp288.c
@@ -333,7 +333,7 @@ static int axp288_extcon_probe(struct platform_device *pdev)
 	struct axp288_extcon_info *info;
 	struct axp20x_dev *axp20x = dev_get_drvdata(pdev->dev.parent);
 	struct device *dev = &pdev->dev;
-	const char *name;
+	struct acpi_device *adev;
 	int ret, i, pirq;
 
 	info = devm_kzalloc(&pdev->dev, sizeof(*info), GFP_KERNEL);
@@ -357,9 +357,10 @@ static int axp288_extcon_probe(struct platform_device *pdev)
 		if (ret)
 			return ret;
 
-		name = acpi_dev_get_first_match_name("INT3496", NULL, -1);
-		if (name) {
-			info->id_extcon = extcon_get_extcon_dev(name);
+		adev = acpi_dev_get_first_match_dev("INT3496", NULL, -1);
+		if (adev) {
+			info->id_extcon = extcon_get_extcon_dev(acpi_dev_name(adev));
+			put_device(&adev->dev);
 			if (!info->id_extcon)
 				return -EPROBE_DEFER;
 
diff --git a/drivers/firewire/ohci.c b/drivers/firewire/ohci.c
index 45c048751f3b..7183ab34269e 100644
--- a/drivers/firewire/ohci.c
+++ b/drivers/firewire/ohci.c
@@ -2939,7 +2939,6 @@ static void set_multichannel_mask(struct fw_ohci *ohci, u64 channels)
 	reg_write(ohci, OHCI1394_IRMultiChanMaskLoClear, ~lo);
 	reg_write(ohci, OHCI1394_IRMultiChanMaskHiSet, hi);
 	reg_write(ohci, OHCI1394_IRMultiChanMaskLoSet, lo);
-	mmiowb();
 	ohci->mc_channels = channels;
 }
 
diff --git a/drivers/firmware/Kconfig b/drivers/firmware/Kconfig
index cac16c4b0df3..7b655f6156fb 100644
--- a/drivers/firmware/Kconfig
+++ b/drivers/firmware/Kconfig
@@ -5,20 +5,6 @@
 
 menu "Firmware Drivers"
 
-config ARM_PSCI_FW
-	bool
-
-config ARM_PSCI_CHECKER
-	bool "ARM PSCI checker"
-	depends on ARM_PSCI_FW && HOTPLUG_CPU && CPU_IDLE && !TORTURE_TEST
-	help
-	  Run the PSCI checker during startup. This checks that hotplug and
-	  suspend operations work correctly when using PSCI.
-
-	  The torture tests may interfere with the PSCI checker by turning CPUs
-	  on and off through hotplug, so for now torture tests and PSCI checker
-	  are mutually exclusive.
-
 config ARM_SCMI_PROTOCOL
 	bool "ARM System Control and Management Interface (SCMI) Message Protocol"
 	depends on ARM || ARM64 || COMPILE_TEST
@@ -270,6 +256,7 @@ config TI_SCI_PROTOCOL
 config HAVE_ARM_SMCCC
 	bool
 
+source "drivers/firmware/psci/Kconfig"
 source "drivers/firmware/broadcom/Kconfig"
 source "drivers/firmware/google/Kconfig"
 source "drivers/firmware/efi/Kconfig"
diff --git a/drivers/firmware/Makefile b/drivers/firmware/Makefile
index 80feb635120f..9a3909a22682 100644
--- a/drivers/firmware/Makefile
+++ b/drivers/firmware/Makefile
@@ -2,8 +2,6 @@
 #
 # Makefile for the linux kernel.
 #
-obj-$(CONFIG_ARM_PSCI_FW)	+= psci.o
-obj-$(CONFIG_ARM_PSCI_CHECKER)	+= psci_checker.o
 obj-$(CONFIG_ARM_SCPI_PROTOCOL)	+= arm_scpi.o
 obj-$(CONFIG_ARM_SCPI_POWER_DOMAIN) += scpi_pm_domain.o
 obj-$(CONFIG_ARM_SDE_INTERFACE)	+= arm_sdei.o
@@ -25,6 +23,7 @@ CFLAGS_qcom_scm-32.o :=$(call as-instr,.arch armv7-a\n.arch_extension sec,-DREQU
 obj-$(CONFIG_TI_SCI_PROTOCOL)	+= ti_sci.o
 
 obj-$(CONFIG_ARM_SCMI_PROTOCOL)	+= arm_scmi/
+obj-y				+= psci/
 obj-y				+= broadcom/
 obj-y				+= meson/
 obj-$(CONFIG_GOOGLE_FIRMWARE)	+= google/
diff --git a/drivers/firmware/arm_sdei.c b/drivers/firmware/arm_sdei.c
index e6376f985ef7..9cd70d1a5622 100644
--- a/drivers/firmware/arm_sdei.c
+++ b/drivers/firmware/arm_sdei.c
@@ -165,6 +165,7 @@ static int invoke_sdei_fn(unsigned long function_id, unsigned long arg0,
 
 	return err;
 }
+NOKPROBE_SYMBOL(invoke_sdei_fn);
 
 static struct sdei_event *sdei_event_find(u32 event_num)
 {
@@ -879,6 +880,7 @@ static void sdei_smccc_smc(unsigned long function_id,
 {
 	arm_smccc_smc(function_id, arg0, arg1, arg2, arg3, arg4, 0, 0, res);
 }
+NOKPROBE_SYMBOL(sdei_smccc_smc);
 
 static void sdei_smccc_hvc(unsigned long function_id,
 			   unsigned long arg0, unsigned long arg1,
@@ -887,6 +889,7 @@ static void sdei_smccc_hvc(unsigned long function_id,
 {
 	arm_smccc_hvc(function_id, arg0, arg1, arg2, arg3, arg4, 0, 0, res);
 }
+NOKPROBE_SYMBOL(sdei_smccc_hvc);
 
 int sdei_register_ghes(struct ghes *ghes, sdei_event_callback *normal_cb,
 		       sdei_event_callback *critical_cb)
diff --git a/drivers/firmware/dmi_scan.c b/drivers/firmware/dmi_scan.c
index 099d83e4e910..fae2d5c43314 100644
--- a/drivers/firmware/dmi_scan.c
+++ b/drivers/firmware/dmi_scan.c
@@ -416,11 +416,8 @@ static void __init save_mem_devices(const struct dmi_header *dm, void *v)
 	nr++;
 }
 
-void __init dmi_memdev_walk(void)
+static void __init dmi_memdev_walk(void)
 {
-	if (!dmi_available)
-		return;
-
 	if (dmi_walk_early(count_mem_devices) == 0 && dmi_memdev_nr) {
 		dmi_memdev = dmi_alloc(sizeof(*dmi_memdev) * dmi_memdev_nr);
 		if (dmi_memdev)
@@ -614,7 +611,7 @@ static int __init dmi_smbios3_present(const u8 *buf)
 	return 1;
 }
 
-void __init dmi_scan_machine(void)
+static void __init dmi_scan_machine(void)
 {
 	char __iomem *p, *q;
 	char buf[32];
@@ -769,15 +766,20 @@ static int __init dmi_init(void)
 subsys_initcall(dmi_init);
 
 /**
- * dmi_set_dump_stack_arch_desc - set arch description for dump_stack()
+ *	dmi_setup - scan and setup DMI system information
  *
- * Invoke dump_stack_set_arch_desc() with DMI system information so that
- * DMI identifiers are printed out on task dumps.  Arch boot code should
- * call this function after dmi_scan_machine() if it wants to print out DMI
- * identifiers on task dumps.
+ *	Scan the DMI system information. This setups DMI identifiers
+ *	(dmi_system_id) for printing it out on task dumps and prepares
+ *	DIMM entry information (dmi_memdev_info) from the SMBIOS table
+ *	for using this when reporting memory errors.
  */
-void __init dmi_set_dump_stack_arch_desc(void)
+void __init dmi_setup(void)
 {
+	dmi_scan_machine();
+	if (!dmi_available)
+		return;
+
+	dmi_memdev_walk();
 	dump_stack_set_arch_desc("%s", dmi_ids_string);
 }
 
@@ -841,7 +843,7 @@ static bool dmi_is_end_of_table(const struct dmi_system_id *dmi)
  *	returns non zero or we hit the end. Callback function is called for
  *	each successful match. Returns the number of matches.
  *
- *	dmi_scan_machine must be called before this function is called.
+ *	dmi_setup must be called before this function is called.
  */
 int dmi_check_system(const struct dmi_system_id *list)
 {
@@ -871,7 +873,7 @@ EXPORT_SYMBOL(dmi_check_system);
  *	Walk the blacklist table until the first match is found.  Return the
  *	pointer to the matching entry or NULL if there's no match.
  *
- *	dmi_scan_machine must be called before this function is called.
+ *	dmi_setup must be called before this function is called.
  */
 const struct dmi_system_id *dmi_first_match(const struct dmi_system_id *list)
 {
diff --git a/drivers/firmware/efi/arm-runtime.c b/drivers/firmware/efi/arm-runtime.c
index 0c1af675c338..e2ac5fa5531b 100644
--- a/drivers/firmware/efi/arm-runtime.c
+++ b/drivers/firmware/efi/arm-runtime.c
@@ -162,13 +162,11 @@ void efi_virtmap_unload(void)
 static int __init arm_dmi_init(void)
 {
 	/*
-	 * On arm64/ARM, DMI depends on UEFI, and dmi_scan_machine() needs to
+	 * On arm64/ARM, DMI depends on UEFI, and dmi_setup() needs to
 	 * be called early because dmi_id_init(), which is an arch_initcall
 	 * itself, depends on dmi_scan_machine() having been called already.
 	 */
-	dmi_scan_machine();
-	if (dmi_available)
-		dmi_set_dump_stack_arch_desc();
+	dmi_setup();
 	return 0;
 }
 core_initcall(arm_dmi_init);
diff --git a/drivers/firmware/efi/libstub/Makefile b/drivers/firmware/efi/libstub/Makefile
index b0103e16fc1b..0460c7581220 100644
--- a/drivers/firmware/efi/libstub/Makefile
+++ b/drivers/firmware/efi/libstub/Makefile
@@ -16,9 +16,9 @@ cflags-$(CONFIG_X86)		+= -m$(BITS) -D__KERNEL__ -O2 \
 
 # arm64 uses the full KBUILD_CFLAGS so it's necessary to explicitly
 # disable the stackleak plugin
-cflags-$(CONFIG_ARM64)		:= $(subst -pg,,$(KBUILD_CFLAGS)) -fpie \
-				   $(DISABLE_STACKLEAK_PLUGIN)
-cflags-$(CONFIG_ARM)		:= $(subst -pg,,$(KBUILD_CFLAGS)) \
+cflags-$(CONFIG_ARM64)		:= $(subst $(CC_FLAGS_FTRACE),,$(KBUILD_CFLAGS)) \
+				   -fpie $(DISABLE_STACKLEAK_PLUGIN)
+cflags-$(CONFIG_ARM)		:= $(subst $(CC_FLAGS_FTRACE),,$(KBUILD_CFLAGS)) \
 				   -fno-builtin -fpic \
 				   $(call cc-option,-mno-single-pic-base)
 
@@ -71,7 +71,6 @@ CFLAGS_arm64-stub.o		:= -DTEXT_OFFSET=$(TEXT_OFFSET)
 extra-$(CONFIG_EFI_ARMSTUB)	:= $(lib-y)
 lib-$(CONFIG_EFI_ARMSTUB)	:= $(patsubst %.o,%.stub.o,$(lib-y))
 
-STUBCOPY_RM-y			:= -R *ksymtab* -R *kcrctab*
 STUBCOPY_FLAGS-$(CONFIG_ARM64)	+= --prefix-alloc-sections=.init \
 				   --prefix-symbols=__efistub_
 STUBCOPY_RELOC-$(CONFIG_ARM64)	:= R_AARCH64_ABS
@@ -86,12 +85,13 @@ $(obj)/%.stub.o: $(obj)/%.o FORCE
 # this time, use objcopy and leave all sections in place.
 #
 quiet_cmd_stubcopy = STUBCPY $@
-      cmd_stubcopy = if $(STRIP) --strip-debug $(STUBCOPY_RM-y) -o $@ $<; \
-		     then if $(OBJDUMP) -r $@ | grep $(STUBCOPY_RELOC-y); \
-		     then (echo >&2 "$@: absolute symbol references not allowed in the EFI stub"; \
-			   rm -f $@; /bin/false);			  \
-		     else $(OBJCOPY) $(STUBCOPY_FLAGS-y) $< $@; fi	  \
-		     else /bin/false; fi
+      cmd_stubcopy =							\
+	$(STRIP) --strip-debug -o $@ $<;				\
+	if $(OBJDUMP) -r $@ | grep $(STUBCOPY_RELOC-y); then		\
+		echo "$@: absolute symbol references not allowed in the EFI stub" >&2; \
+		/bin/false;						\
+	fi;								\
+	$(OBJCOPY) $(STUBCOPY_FLAGS-y) $< $@
 
 #
 # ARM discards the .data section because it disallows r/w data in the
diff --git a/drivers/firmware/iscsi_ibft.c b/drivers/firmware/iscsi_ibft.c
index c51462f5aa1e..a5dc0629f225 100644
--- a/drivers/firmware/iscsi_ibft.c
+++ b/drivers/firmware/iscsi_ibft.c
@@ -425,7 +425,7 @@ static ssize_t ibft_attr_show_acpitbl(void *data, int type, char *buf)
 
 	switch (type) {
 	case ISCSI_BOOT_ACPITBL_SIGNATURE:
-		str += sprintf_string(str, ACPI_NAME_SIZE,
+		str += sprintf_string(str, ACPI_NAMESEG_SIZE,
 				      entry->header->header.signature);
 		break;
 	case ISCSI_BOOT_ACPITBL_OEM_ID:
diff --git a/drivers/firmware/psci/Kconfig b/drivers/firmware/psci/Kconfig
new file mode 100644
index 000000000000..26a3b32bf7ab
--- /dev/null
+++ b/drivers/firmware/psci/Kconfig
@@ -0,0 +1,13 @@
+config ARM_PSCI_FW
+	bool
+
+config ARM_PSCI_CHECKER
+	bool "ARM PSCI checker"
+	depends on ARM_PSCI_FW && HOTPLUG_CPU && CPU_IDLE && !TORTURE_TEST
+	help
+	  Run the PSCI checker during startup. This checks that hotplug and
+	  suspend operations work correctly when using PSCI.
+
+	  The torture tests may interfere with the PSCI checker by turning CPUs
+	  on and off through hotplug, so for now torture tests and PSCI checker
+	  are mutually exclusive.
diff --git a/drivers/firmware/psci/Makefile b/drivers/firmware/psci/Makefile
new file mode 100644
index 000000000000..1956b882470f
--- /dev/null
+++ b/drivers/firmware/psci/Makefile
@@ -0,0 +1,4 @@
+# SPDX-License-Identifier: GPL-2.0
+#
+obj-$(CONFIG_ARM_PSCI_FW)	+= psci.o
+obj-$(CONFIG_ARM_PSCI_CHECKER)	+= psci_checker.o
diff --git a/drivers/firmware/psci.c b/drivers/firmware/psci/psci.c
index c80ec1d03274..fe090ef43d28 100644
--- a/drivers/firmware/psci.c
+++ b/drivers/firmware/psci/psci.c
@@ -88,6 +88,7 @@ static u32 psci_function_id[PSCI_FN_MAX];
 				PSCI_1_0_EXT_POWER_STATE_TYPE_MASK)
 
 static u32 psci_cpu_suspend_feature;
+static bool psci_system_reset2_supported;
 
 static inline bool psci_has_ext_power_state(void)
 {
@@ -95,6 +96,11 @@ static inline bool psci_has_ext_power_state(void)
 				PSCI_1_0_FEATURES_CPU_SUSPEND_PF_MASK;
 }
 
+static inline bool psci_has_osi_support(void)
+{
+	return psci_cpu_suspend_feature & PSCI_1_0_OS_INITIATED;
+}
+
 static inline bool psci_power_state_loses_context(u32 state)
 {
 	const u32 mask = psci_has_ext_power_state() ?
@@ -253,7 +259,17 @@ static int get_set_conduit_method(struct device_node *np)
 
 static void psci_sys_reset(enum reboot_mode reboot_mode, const char *cmd)
 {
-	invoke_psci_fn(PSCI_0_2_FN_SYSTEM_RESET, 0, 0, 0);
+	if ((reboot_mode == REBOOT_WARM || reboot_mode == REBOOT_SOFT) &&
+	    psci_system_reset2_supported) {
+		/*
+		 * reset_type[31] = 0 (architectural)
+		 * reset_type[30:0] = 0 (SYSTEM_WARM_RESET)
+		 * cookie = 0 (ignored by the implementation)
+		 */
+		invoke_psci_fn(PSCI_FN_NATIVE(1_1, SYSTEM_RESET2), 0, 0, 0);
+	} else {
+		invoke_psci_fn(PSCI_0_2_FN_SYSTEM_RESET, 0, 0, 0);
+	}
 }
 
 static void psci_sys_poweroff(void)
@@ -270,9 +286,26 @@ static int __init psci_features(u32 psci_func_id)
 #ifdef CONFIG_CPU_IDLE
 static DEFINE_PER_CPU_READ_MOSTLY(u32 *, psci_power_state);
 
+static int psci_dt_parse_state_node(struct device_node *np, u32 *state)
+{
+	int err = of_property_read_u32(np, "arm,psci-suspend-param", state);
+
+	if (err) {
+		pr_warn("%pOF missing arm,psci-suspend-param property\n", np);
+		return err;
+	}
+
+	if (!psci_power_state_is_valid(*state)) {
+		pr_warn("Invalid PSCI power state %#x\n", *state);
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
 static int psci_dt_cpu_init_idle(struct device_node *cpu_node, int cpu)
 {
-	int i, ret, count = 0;
+	int i, ret = 0, count = 0;
 	u32 *psci_states;
 	struct device_node *state_node;
 
@@ -291,29 +324,16 @@ static int psci_dt_cpu_init_idle(struct device_node *cpu_node, int cpu)
 		return -ENOMEM;
 
 	for (i = 0; i < count; i++) {
-		u32 state;
-
 		state_node = of_parse_phandle(cpu_node, "cpu-idle-states", i);
+		ret = psci_dt_parse_state_node(state_node, &psci_states[i]);
+		of_node_put(state_node);
 
-		ret = of_property_read_u32(state_node,
-					   "arm,psci-suspend-param",
-					   &state);
-		if (ret) {
-			pr_warn(" * %pOF missing arm,psci-suspend-param property\n",
-				state_node);
-			of_node_put(state_node);
+		if (ret)
 			goto free_mem;
-		}
 
-		of_node_put(state_node);
-		pr_debug("psci-power-state %#x index %d\n", state, i);
-		if (!psci_power_state_is_valid(state)) {
-			pr_warn("Invalid PSCI power state %#x\n", state);
-			ret = -EINVAL;
-			goto free_mem;
-		}
-		psci_states[i] = state;
+		pr_debug("psci-power-state %#x index %d\n", psci_states[i], i);
 	}
+
 	/* Idle states parsed correctly, initialize per-cpu pointer */
 	per_cpu(psci_power_state, cpu) = psci_states;
 	return 0;
@@ -451,6 +471,16 @@ static const struct platform_suspend_ops psci_suspend_ops = {
 	.enter          = psci_system_suspend_enter,
 };
 
+static void __init psci_init_system_reset2(void)
+{
+	int ret;
+
+	ret = psci_features(PSCI_FN_NATIVE(1_1, SYSTEM_RESET2));
+
+	if (ret != PSCI_RET_NOT_SUPPORTED)
+		psci_system_reset2_supported = true;
+}
+
 static void __init psci_init_system_suspend(void)
 {
 	int ret;
@@ -588,6 +618,7 @@ static int __init psci_probe(void)
 		psci_init_smccc();
 		psci_init_cpu_suspend();
 		psci_init_system_suspend();
+		psci_init_system_reset2();
 	}
 
 	return 0;
@@ -605,9 +636,9 @@ static int __init psci_0_2_init(struct device_node *np)
 	int err;
 
 	err = get_set_conduit_method(np);
-
 	if (err)
-		goto out_put_node;
+		return err;
+
 	/*
 	 * Starting with v0.2, the PSCI specification introduced a call
 	 * (PSCI_VERSION) that allows probing the firmware version, so
@@ -615,11 +646,7 @@ static int __init psci_0_2_init(struct device_node *np)
 	 * can be carried out according to the specific version reported
 	 * by firmware
 	 */
-	err = psci_probe();
-
-out_put_node:
-	of_node_put(np);
-	return err;
+	return psci_probe();
 }
 
 /*
@@ -631,9 +658,8 @@ static int __init psci_0_1_init(struct device_node *np)
 	int err;
 
 	err = get_set_conduit_method(np);
-
 	if (err)
-		goto out_put_node;
+		return err;
 
 	pr_info("Using PSCI v0.1 Function IDs from DT\n");
 
@@ -657,15 +683,27 @@ static int __init psci_0_1_init(struct device_node *np)
 		psci_ops.migrate = psci_migrate;
 	}
 
-out_put_node:
-	of_node_put(np);
-	return err;
+	return 0;
+}
+
+static int __init psci_1_0_init(struct device_node *np)
+{
+	int err;
+
+	err = psci_0_2_init(np);
+	if (err)
+		return err;
+
+	if (psci_has_osi_support())
+		pr_info("OSI mode supported.\n");
+
+	return 0;
 }
 
 static const struct of_device_id psci_of_match[] __initconst = {
 	{ .compatible = "arm,psci",	.data = psci_0_1_init},
 	{ .compatible = "arm,psci-0.2",	.data = psci_0_2_init},
-	{ .compatible = "arm,psci-1.0",	.data = psci_0_2_init},
+	{ .compatible = "arm,psci-1.0",	.data = psci_1_0_init},
 	{},
 };
 
@@ -674,6 +712,7 @@ int __init psci_dt_init(void)
 	struct device_node *np;
 	const struct of_device_id *matched_np;
 	psci_initcall_t init_fn;
+	int ret;
 
 	np = of_find_matching_node_and_match(NULL, psci_of_match, &matched_np);
 
@@ -681,7 +720,10 @@ int __init psci_dt_init(void)
 		return -ENODEV;
 
 	init_fn = (psci_initcall_t)matched_np->data;
-	return init_fn(np);
+	ret = init_fn(np);
+
+	of_node_put(np);
+	return ret;
 }
 
 #ifdef CONFIG_ACPI
diff --git a/drivers/firmware/psci_checker.c b/drivers/firmware/psci/psci_checker.c
index 346943657962..346943657962 100644
--- a/drivers/firmware/psci_checker.c
+++ b/drivers/firmware/psci/psci_checker.c
diff --git a/drivers/gpio/gpio-adnp.c b/drivers/gpio/gpio-adnp.c
index 91b90c0cea73..12acdac85820 100644
--- a/drivers/gpio/gpio-adnp.c
+++ b/drivers/gpio/gpio-adnp.c
@@ -132,8 +132,10 @@ static int adnp_gpio_direction_input(struct gpio_chip *chip, unsigned offset)
 	if (err < 0)
 		goto out;
 
-	if (err & BIT(pos))
-		err = -EACCES;
+	if (value & BIT(pos)) {
+		err = -EPERM;
+		goto out;
+	}
 
 	err = 0;
 
diff --git a/drivers/gpio/gpio-aspeed.c b/drivers/gpio/gpio-aspeed.c
index 854bce4fb9e7..217507002dbc 100644
--- a/drivers/gpio/gpio-aspeed.c
+++ b/drivers/gpio/gpio-aspeed.c
@@ -1224,6 +1224,8 @@ static int __init aspeed_gpio_probe(struct platform_device *pdev)
 
 	gpio->offset_timer =
 		devm_kzalloc(&pdev->dev, gpio->chip.ngpio, GFP_KERNEL);
+	if (!gpio->offset_timer)
+		return -ENOMEM;
 
 	return aspeed_gpio_setup_irqs(gpio, pdev);
 }
diff --git a/drivers/gpio/gpio-eic-sprd.c b/drivers/gpio/gpio-eic-sprd.c
index f0223cee9774..77092268ee95 100644
--- a/drivers/gpio/gpio-eic-sprd.c
+++ b/drivers/gpio/gpio-eic-sprd.c
@@ -414,6 +414,7 @@ static int sprd_eic_irq_set_type(struct irq_data *data, unsigned int flow_type)
 			irq_set_handler_locked(data, handle_edge_irq);
 			break;
 		case IRQ_TYPE_EDGE_BOTH:
+			sprd_eic_update(chip, offset, SPRD_EIC_SYNC_INTMODE, 0);
 			sprd_eic_update(chip, offset, SPRD_EIC_SYNC_INTBOTH, 1);
 			irq_set_handler_locked(data, handle_edge_irq);
 			break;
diff --git a/drivers/gpio/gpio-exar.c b/drivers/gpio/gpio-exar.c
index 0ecd2369c2ca..a09d2f9ebacc 100644
--- a/drivers/gpio/gpio-exar.c
+++ b/drivers/gpio/gpio-exar.c
@@ -148,6 +148,8 @@ static int gpio_exar_probe(struct platform_device *pdev)
 	mutex_init(&exar_gpio->lock);
 
 	index = ida_simple_get(&ida_index, 0, 0, GFP_KERNEL);
+	if (index < 0)
+		goto err_destroy;
 
 	sprintf(exar_gpio->name, "exar_gpio%d", index);
 	exar_gpio->gpio_chip.label = exar_gpio->name;
diff --git a/drivers/gpio/gpio-merrifield.c b/drivers/gpio/gpio-merrifield.c
index 7c659fdaa6d5..3302125e5265 100644
--- a/drivers/gpio/gpio-merrifield.c
+++ b/drivers/gpio/gpio-merrifield.c
@@ -377,10 +377,20 @@ static void mrfld_irq_init_hw(struct mrfld_gpio *priv)
 	}
 }
 
-static const char *mrfld_gpio_get_pinctrl_dev_name(void)
+static const char *mrfld_gpio_get_pinctrl_dev_name(struct mrfld_gpio *priv)
 {
-	const char *dev_name = acpi_dev_get_first_match_name("INTC1002", NULL, -1);
-	return dev_name ? dev_name : "pinctrl-merrifield";
+	struct acpi_device *adev;
+	const char *name;
+
+	adev = acpi_dev_get_first_match_dev("INTC1002", NULL, -1);
+	if (adev) {
+		name = devm_kstrdup(priv->dev, acpi_dev_name(adev), GFP_KERNEL);
+		acpi_dev_put(adev);
+	} else {
+		name = "pinctrl-merrifield";
+	}
+
+	return name;
 }
 
 static int mrfld_gpio_probe(struct pci_dev *pdev, const struct pci_device_id *id)
@@ -441,7 +451,7 @@ static int mrfld_gpio_probe(struct pci_dev *pdev, const struct pci_device_id *id
 		return retval;
 	}
 
-	pinctrl_dev_name = mrfld_gpio_get_pinctrl_dev_name();
+	pinctrl_dev_name = mrfld_gpio_get_pinctrl_dev_name(priv);
 	for (i = 0; i < ARRAY_SIZE(mrfld_gpio_ranges); i++) {
 		range = &mrfld_gpio_ranges[i];
 		retval = gpiochip_add_pin_range(&priv->chip,
diff --git a/drivers/gpio/gpio-mockup.c b/drivers/gpio/gpio-mockup.c
index 154d959e8993..b6a4efce7c92 100644
--- a/drivers/gpio/gpio-mockup.c
+++ b/drivers/gpio/gpio-mockup.c
@@ -204,8 +204,8 @@ static ssize_t gpio_mockup_debugfs_read(struct file *file,
 	struct gpio_mockup_chip *chip;
 	struct seq_file *sfile;
 	struct gpio_chip *gc;
+	int val, cnt;
 	char buf[3];
-	int val, rv;
 
 	if (*ppos != 0)
 		return 0;
@@ -216,13 +216,9 @@ static ssize_t gpio_mockup_debugfs_read(struct file *file,
 	gc = &chip->gc;
 
 	val = gpio_mockup_get(gc, priv->offset);
-	snprintf(buf, sizeof(buf), "%d\n", val);
+	cnt = snprintf(buf, sizeof(buf), "%d\n", val);
 
-	rv = copy_to_user(usr_buf, buf, sizeof(buf));
-	if (rv)
-		return rv;
-
-	return sizeof(buf) - 1;
+	return simple_read_from_buffer(usr_buf, size, ppos, buf, cnt);
 }
 
 static ssize_t gpio_mockup_debugfs_write(struct file *file,
diff --git a/drivers/gpio/gpiolib-of.c b/drivers/gpio/gpiolib-of.c
index 8b9c3ab70f6e..6a3ec575a404 100644
--- a/drivers/gpio/gpiolib-of.c
+++ b/drivers/gpio/gpiolib-of.c
@@ -120,7 +120,8 @@ static void of_gpio_flags_quirks(struct device_node *np,
 	 * to determine if the flags should have inverted semantics.
 	 */
 	if (IS_ENABLED(CONFIG_SPI_MASTER) &&
-	    of_property_read_bool(np, "cs-gpios")) {
+	    of_property_read_bool(np, "cs-gpios") &&
+	    !strcmp(propname, "cs-gpios")) {
 		struct device_node *child;
 		u32 cs;
 		int ret;
@@ -142,16 +143,16 @@ static void of_gpio_flags_quirks(struct device_node *np,
 				 * conflict and the "spi-cs-high" flag will
 				 * take precedence.
 				 */
-				if (of_property_read_bool(np, "spi-cs-high")) {
+				if (of_property_read_bool(child, "spi-cs-high")) {
 					if (*flags & OF_GPIO_ACTIVE_LOW) {
 						pr_warn("%s GPIO handle specifies active low - ignored\n",
-							of_node_full_name(np));
+							of_node_full_name(child));
 						*flags &= ~OF_GPIO_ACTIVE_LOW;
 					}
 				} else {
 					if (!(*flags & OF_GPIO_ACTIVE_LOW))
 						pr_info("%s enforce active low on chipselect handle\n",
-							of_node_full_name(np));
+							of_node_full_name(child));
 					*flags |= OF_GPIO_ACTIVE_LOW;
 				}
 				break;
@@ -717,7 +718,13 @@ int of_gpiochip_add(struct gpio_chip *chip)
 
 	of_node_get(chip->of_node);
 
-	return of_gpiochip_scan_gpios(chip);
+	status = of_gpiochip_scan_gpios(chip);
+	if (status) {
+		of_node_put(chip->of_node);
+		gpiochip_remove_pin_ranges(chip);
+	}
+
+	return status;
 }
 
 void of_gpiochip_remove(struct gpio_chip *chip)
diff --git a/drivers/gpio/gpiolib.c b/drivers/gpio/gpiolib.c
index 144af0733581..bca3e7740ef6 100644
--- a/drivers/gpio/gpiolib.c
+++ b/drivers/gpio/gpiolib.c
@@ -1379,7 +1379,7 @@ int gpiochip_add_data_with_key(struct gpio_chip *chip, void *data,
 
 	status = gpiochip_add_irqchip(chip, lock_key, request_key);
 	if (status)
-		goto err_remove_chip;
+		goto err_free_gpiochip_mask;
 
 	status = of_gpiochip_add(chip);
 	if (status)
@@ -1387,7 +1387,7 @@ int gpiochip_add_data_with_key(struct gpio_chip *chip, void *data,
 
 	status = gpiochip_init_valid_mask(chip);
 	if (status)
-		goto err_remove_chip;
+		goto err_remove_of_chip;
 
 	for (i = 0; i < chip->ngpio; i++) {
 		struct gpio_desc *desc = &gdev->descs[i];
@@ -1415,14 +1415,18 @@ int gpiochip_add_data_with_key(struct gpio_chip *chip, void *data,
 	if (gpiolib_initialized) {
 		status = gpiochip_setup_dev(gdev);
 		if (status)
-			goto err_remove_chip;
+			goto err_remove_acpi_chip;
 	}
 	return 0;
 
-err_remove_chip:
+err_remove_acpi_chip:
 	acpi_gpiochip_remove(chip);
+err_remove_of_chip:
 	gpiochip_free_hogs(chip);
 	of_gpiochip_remove(chip);
+err_remove_chip:
+	gpiochip_irqchip_remove(chip);
+err_free_gpiochip_mask:
 	gpiochip_free_valid_mask(chip);
 err_remove_irqchip_mask:
 	gpiochip_irqchip_free_valid_mask(chip);
@@ -2776,7 +2780,7 @@ int gpiod_set_debounce(struct gpio_desc *desc, unsigned debounce)
 	}
 
 	config = pinconf_to_config_packed(PIN_CONFIG_INPUT_DEBOUNCE, debounce);
-	return gpio_set_config(chip, gpio_chip_hwgpio(desc), config);
+	return chip->set_config(chip, gpio_chip_hwgpio(desc), config);
 }
 EXPORT_SYMBOL_GPL(gpiod_set_debounce);
 
@@ -2813,7 +2817,7 @@ int gpiod_set_transitory(struct gpio_desc *desc, bool transitory)
 	packed = pinconf_to_config_packed(PIN_CONFIG_PERSIST_STATE,
 					  !transitory);
 	gpio = gpio_chip_hwgpio(desc);
-	rc = gpio_set_config(chip, gpio, packed);
+	rc = chip->set_config(chip, gpio, packed);
 	if (rc == -ENOTSUPP) {
 		dev_dbg(&desc->gdev->dev, "Persistence not supported for GPIO %d\n",
 				gpio);
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
index 4f8fb4ecde34..79fb302fb954 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
@@ -3165,6 +3165,7 @@ static int amdgpu_device_recover_vram(struct amdgpu_device *adev)
 
 		/* No need to recover an evicted BO */
 		if (shadow->tbo.mem.mem_type != TTM_PL_TT ||
+		    shadow->tbo.mem.start == AMDGPU_BO_INVALID_OFFSET ||
 		    shadow->parent->tbo.mem.mem_type != TTM_PL_VRAM)
 			continue;
 
@@ -3173,11 +3174,16 @@ static int amdgpu_device_recover_vram(struct amdgpu_device *adev)
 			break;
 
 		if (fence) {
-			r = dma_fence_wait_timeout(fence, false, tmo);
+			tmo = dma_fence_wait_timeout(fence, false, tmo);
 			dma_fence_put(fence);
 			fence = next;
-			if (r <= 0)
+			if (tmo == 0) {
+				r = -ETIMEDOUT;
 				break;
+			} else if (tmo < 0) {
+				r = tmo;
+				break;
+			}
 		} else {
 			fence = next;
 		}
@@ -3188,8 +3194,8 @@ static int amdgpu_device_recover_vram(struct amdgpu_device *adev)
 		tmo = dma_fence_wait_timeout(fence, false, tmo);
 	dma_fence_put(fence);
 
-	if (r <= 0 || tmo <= 0) {
-		DRM_ERROR("recover vram bo from shadow failed\n");
+	if (r < 0 || tmo <= 0) {
+		DRM_ERROR("recover vram bo from shadow failed, r is %ld, tmo is %ld\n", r, tmo);
 		return -EIO;
 	}
 
@@ -3625,6 +3631,7 @@ static void amdgpu_device_get_min_pci_speed_width(struct amdgpu_device *adev,
 	struct pci_dev *pdev = adev->pdev;
 	enum pci_bus_speed cur_speed;
 	enum pcie_link_width cur_width;
+	u32 ret = 1;
 
 	*speed = PCI_SPEED_UNKNOWN;
 	*width = PCIE_LNK_WIDTH_UNKNOWN;
@@ -3632,6 +3639,10 @@ static void amdgpu_device_get_min_pci_speed_width(struct amdgpu_device *adev,
 	while (pdev) {
 		cur_speed = pcie_get_speed_cap(pdev);
 		cur_width = pcie_get_width_cap(pdev);
+		ret = pcie_bandwidth_available(adev->pdev, NULL,
+						       NULL, &cur_width);
+		if (!ret)
+			cur_width = PCIE_LNK_WIDTH_RESRV;
 
 		if (cur_speed != PCI_SPEED_UNKNOWN) {
 			if (*speed == PCI_SPEED_UNKNOWN)
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ib.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ib.c
index 0b8ef2d27d6b..fe393a46f881 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ib.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ib.c
@@ -35,6 +35,7 @@
 #include "amdgpu_trace.h"
 
 #define AMDGPU_IB_TEST_TIMEOUT	msecs_to_jiffies(1000)
+#define AMDGPU_IB_TEST_GFX_XGMI_TIMEOUT	msecs_to_jiffies(2000)
 
 /*
  * IB
@@ -344,6 +345,8 @@ int amdgpu_ib_ring_tests(struct amdgpu_device *adev)
 		 * cost waiting for it coming back under RUNTIME only
 		*/
 		tmo_gfx = 8 * AMDGPU_IB_TEST_TIMEOUT;
+	} else if (adev->gmc.xgmi.hive_id) {
+		tmo_gfx = AMDGPU_IB_TEST_GFX_XGMI_TIMEOUT;
 	}
 
 	for (i = 0; i < adev->num_rings; ++i) {
diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c
index d0309e8c9d12..a11db2b1a63f 100644
--- a/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c
@@ -2405,8 +2405,6 @@ static int gfx_v9_0_rlc_resume(struct amdgpu_device *adev)
 	/* disable CG */
 	WREG32_SOC15(GC, 0, mmRLC_CGCG_CGLS_CTRL, 0);
 
-	adev->gfx.rlc.funcs->reset(adev);
-
 	gfx_v9_0_init_pg(adev);
 
 	if (adev->firmware.load_type != AMDGPU_FW_LOAD_PSP) {
diff --git a/drivers/gpu/drm/amd/amdgpu/mmhub_v1_0.c b/drivers/gpu/drm/amd/amdgpu/mmhub_v1_0.c
index d0d966d6080a..1696644ec022 100644
--- a/drivers/gpu/drm/amd/amdgpu/mmhub_v1_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/mmhub_v1_0.c
@@ -182,6 +182,7 @@ static void mmhub_v1_0_init_cache_regs(struct amdgpu_device *adev)
 		tmp = REG_SET_FIELD(tmp, VM_L2_CNTL3,
 				    L2_CACHE_BIGK_FRAGMENT_SIZE, 6);
 	}
+	WREG32_SOC15(MMHUB, 0, mmVM_L2_CNTL3, tmp);
 
 	tmp = mmVM_L2_CNTL4_DEFAULT;
 	tmp = REG_SET_FIELD(tmp, VM_L2_CNTL4, VMC_TAP_PDE_REQUEST_PHYSICAL, 0);
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_device.c b/drivers/gpu/drm/amd/amdkfd/kfd_device.c
index 8be9677c0c07..cf9a49f49d3a 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_device.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_device.c
@@ -320,6 +320,7 @@ static const struct kfd_deviceid supported_devices[] = {
 	{ 0x9876, &carrizo_device_info },	/* Carrizo */
 	{ 0x9877, &carrizo_device_info },	/* Carrizo */
 	{ 0x15DD, &raven_device_info },		/* Raven */
+	{ 0x15D8, &raven_device_info },		/* Raven */
 #endif
 	{ 0x67A0, &hawaii_device_info },	/* Hawaii */
 	{ 0x67A1, &hawaii_device_info },	/* Hawaii */
diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
index fb27783d7a54..3082b55b1e77 100644
--- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
+++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
@@ -4533,6 +4533,7 @@ static void handle_cursor_update(struct drm_plane *plane,
 	amdgpu_crtc->cursor_width = plane->state->crtc_w;
 	amdgpu_crtc->cursor_height = plane->state->crtc_h;
 
+	memset(&attributes, 0, sizeof(attributes));
 	attributes.address.high_part = upper_32_bits(address);
 	attributes.address.low_part  = lower_32_bits(address);
 	attributes.width             = plane->state->crtc_w;
@@ -5429,9 +5430,11 @@ static void get_freesync_config_for_crtc(
 	struct amdgpu_dm_connector *aconnector =
 			to_amdgpu_dm_connector(new_con_state->base.connector);
 	struct drm_display_mode *mode = &new_crtc_state->base.mode;
+	int vrefresh = drm_mode_vrefresh(mode);
 
 	new_crtc_state->vrr_supported = new_con_state->freesync_capable &&
-		aconnector->min_vfreq <= drm_mode_vrefresh(mode);
+					vrefresh >= aconnector->min_vfreq &&
+					vrefresh <= aconnector->max_vfreq;
 
 	if (new_crtc_state->vrr_supported) {
 		new_crtc_state->stream->ignore_msa_timing_param = true;
diff --git a/drivers/gpu/drm/amd/display/dc/core/dc.c b/drivers/gpu/drm/amd/display/dc/core/dc.c
index c68fbd55db3c..a6cda201c964 100644
--- a/drivers/gpu/drm/amd/display/dc/core/dc.c
+++ b/drivers/gpu/drm/amd/display/dc/core/dc.c
@@ -1377,6 +1377,11 @@ static enum surface_update_type det_surface_update(const struct dc *dc,
 		return UPDATE_TYPE_FULL;
 	}
 
+	if (u->surface->force_full_update) {
+		update_flags->bits.full_update = 1;
+		return UPDATE_TYPE_FULL;
+	}
+
 	type = get_plane_info_update_type(u);
 	elevate_update_type(&overall_type, type);
 
@@ -1802,6 +1807,14 @@ void dc_commit_updates_for_stream(struct dc *dc,
 		}
 
 		dc_resource_state_copy_construct(state, context);
+
+		for (i = 0; i < dc->res_pool->pipe_count; i++) {
+			struct pipe_ctx *new_pipe = &context->res_ctx.pipe_ctx[i];
+			struct pipe_ctx *old_pipe = &dc->current_state->res_ctx.pipe_ctx[i];
+
+			if (new_pipe->plane_state && new_pipe->plane_state != old_pipe->plane_state)
+				new_pipe->plane_state->force_full_update = true;
+		}
 	}
 
 
@@ -1838,6 +1851,12 @@ void dc_commit_updates_for_stream(struct dc *dc,
 		dc->current_state = context;
 		dc_release_state(old);
 
+		for (i = 0; i < dc->res_pool->pipe_count; i++) {
+			struct pipe_ctx *pipe_ctx = &context->res_ctx.pipe_ctx[i];
+
+			if (pipe_ctx->plane_state && pipe_ctx->stream == stream)
+				pipe_ctx->plane_state->force_full_update = false;
+		}
 	}
 	/*let's use current_state to update watermark etc*/
 	if (update_type >= UPDATE_TYPE_FULL)
diff --git a/drivers/gpu/drm/amd/display/dc/core/dc_link.c b/drivers/gpu/drm/amd/display/dc/core/dc_link.c
index 4eba3c4800b6..ea18e9c2d8ce 100644
--- a/drivers/gpu/drm/amd/display/dc/core/dc_link.c
+++ b/drivers/gpu/drm/amd/display/dc/core/dc_link.c
@@ -2660,12 +2660,18 @@ void core_link_enable_stream(
 void core_link_disable_stream(struct pipe_ctx *pipe_ctx, int option)
 {
 	struct dc  *core_dc = pipe_ctx->stream->ctx->dc;
+	struct dc_stream_state *stream = pipe_ctx->stream;
 
 	core_dc->hwss.blank_stream(pipe_ctx);
 
 	if (pipe_ctx->stream->signal == SIGNAL_TYPE_DISPLAY_PORT_MST)
 		deallocate_mst_payload(pipe_ctx);
 
+	if (dc_is_hdmi_signal(pipe_ctx->stream->signal))
+		dal_ddc_service_write_scdc_data(
+			stream->link->ddc, 0,
+			stream->timing.flags.LTE_340MCSC_SCRAMBLE);
+
 	core_dc->hwss.disable_stream(pipe_ctx, option);
 
 	disable_link(pipe_ctx->stream->link, pipe_ctx->stream->signal);
diff --git a/drivers/gpu/drm/amd/display/dc/dc.h b/drivers/gpu/drm/amd/display/dc/dc.h
index 1a7fd6aa77eb..0515095574e7 100644
--- a/drivers/gpu/drm/amd/display/dc/dc.h
+++ b/drivers/gpu/drm/amd/display/dc/dc.h
@@ -503,6 +503,9 @@ struct dc_plane_state {
 	struct dc_plane_status status;
 	struct dc_context *ctx;
 
+	/* HACK: Workaround for forcing full reprogramming under some conditions */
+	bool force_full_update;
+
 	/* private to dc_surface.c */
 	enum dc_irq_source irq_source;
 	struct kref refcount;
diff --git a/drivers/gpu/drm/amd/display/dc/dce/dce_aux.c b/drivers/gpu/drm/amd/display/dc/dce/dce_aux.c
index 4febf4ef7240..4fe3664fb495 100644
--- a/drivers/gpu/drm/amd/display/dc/dce/dce_aux.c
+++ b/drivers/gpu/drm/amd/display/dc/dce/dce_aux.c
@@ -190,6 +190,12 @@ static void submit_channel_request(
 				1,
 				0);
 	}
+
+	REG_UPDATE(AUX_INTERRUPT_CONTROL, AUX_SW_DONE_ACK, 1);
+
+	REG_WAIT(AUX_SW_STATUS, AUX_SW_DONE, 0,
+				10, aux110->timeout_period/10);
+
 	/* set the delay and the number of bytes to write */
 
 	/* The length include
@@ -242,9 +248,6 @@ static void submit_channel_request(
 		}
 	}
 
-	REG_UPDATE(AUX_INTERRUPT_CONTROL, AUX_SW_DONE_ACK, 1);
-	REG_WAIT(AUX_SW_STATUS, AUX_SW_DONE, 0,
-				10, aux110->timeout_period/10);
 	REG_UPDATE(AUX_SW_CONTROL, AUX_SW_GO, 1);
 }
 
diff --git a/drivers/gpu/drm/amd/display/dc/dce/dce_aux.h b/drivers/gpu/drm/amd/display/dc/dce/dce_aux.h
index d27f22c05e4b..e28ed6a00ff4 100644
--- a/drivers/gpu/drm/amd/display/dc/dce/dce_aux.h
+++ b/drivers/gpu/drm/amd/display/dc/dce/dce_aux.h
@@ -71,11 +71,11 @@ enum {	/* This is the timeout as defined in DP 1.2a,
 	 * at most within ~240usec. That means,
 	 * increasing this timeout will not affect normal operation,
 	 * and we'll timeout after
-	 * SW_AUX_TIMEOUT_PERIOD_MULTIPLIER * AUX_TIMEOUT_PERIOD = 1600usec.
+	 * SW_AUX_TIMEOUT_PERIOD_MULTIPLIER * AUX_TIMEOUT_PERIOD = 2400usec.
 	 * This timeout is especially important for
-	 * resume from S3 and CTS.
+	 * converters, resume from S3, and CTS.
 	 */
-	SW_AUX_TIMEOUT_PERIOD_MULTIPLIER = 4
+	SW_AUX_TIMEOUT_PERIOD_MULTIPLIER = 6
 };
 
 struct dce_aux {
diff --git a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hubp.c b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hubp.c
index 683829466a44..0ba68d41b9c3 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hubp.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hubp.c
@@ -1150,28 +1150,9 @@ void hubp1_cursor_set_position(
 	REG_UPDATE(CURSOR_CONTROL,
 			CURSOR_ENABLE, cur_en);
 
-	//account for cases where we see negative offset relative to overlay plane
-	if (src_x_offset < 0 && src_y_offset < 0) {
-		REG_SET_2(CURSOR_POSITION, 0,
-			CURSOR_X_POSITION, 0,
-			CURSOR_Y_POSITION, 0);
-		x_hotspot -= src_x_offset;
-		y_hotspot -= src_y_offset;
-	} else if (src_x_offset < 0) {
-		REG_SET_2(CURSOR_POSITION, 0,
-			CURSOR_X_POSITION, 0,
-			CURSOR_Y_POSITION, pos->y);
-		x_hotspot -= src_x_offset;
-	} else if (src_y_offset < 0) {
-		REG_SET_2(CURSOR_POSITION, 0,
+	REG_SET_2(CURSOR_POSITION, 0,
 			CURSOR_X_POSITION, pos->x,
-			CURSOR_Y_POSITION, 0);
-		y_hotspot -= src_y_offset;
-	} else {
-		REG_SET_2(CURSOR_POSITION, 0,
-				CURSOR_X_POSITION, pos->x,
-				CURSOR_Y_POSITION, pos->y);
-	}
+			CURSOR_Y_POSITION, pos->y);
 
 	REG_SET_2(CURSOR_HOT_SPOT, 0,
 			CURSOR_HOT_SPOT_X, x_hotspot,
diff --git a/drivers/gpu/drm/amd/powerplay/hwmgr/vega20_hwmgr.c b/drivers/gpu/drm/amd/powerplay/hwmgr/vega20_hwmgr.c
index 9aa7bec1b5fe..23b5b94a4939 100644
--- a/drivers/gpu/drm/amd/powerplay/hwmgr/vega20_hwmgr.c
+++ b/drivers/gpu/drm/amd/powerplay/hwmgr/vega20_hwmgr.c
@@ -91,6 +91,12 @@ static void vega20_set_default_registry_data(struct pp_hwmgr *hwmgr)
 	 *   MP0CLK DS
 	 */
 	data->registry_data.disallowed_features = 0xE0041C00;
+	/* ECC feature should be disabled on old SMUs */
+	smum_send_msg_to_smc(hwmgr, PPSMC_MSG_GetSmuVersion);
+	hwmgr->smu_version = smum_get_argument(hwmgr);
+	if (hwmgr->smu_version < 0x282100)
+		data->registry_data.disallowed_features |= FEATURE_ECC_MASK;
+
 	data->registry_data.od_state_in_dc_support = 0;
 	data->registry_data.thermal_support = 1;
 	data->registry_data.skip_baco_hardware = 0;
@@ -357,6 +363,7 @@ static void vega20_init_dpm_defaults(struct pp_hwmgr *hwmgr)
 	data->smu_features[GNLD_DS_MP1CLK].smu_feature_id = FEATURE_DS_MP1CLK_BIT;
 	data->smu_features[GNLD_DS_MP0CLK].smu_feature_id = FEATURE_DS_MP0CLK_BIT;
 	data->smu_features[GNLD_XGMI].smu_feature_id = FEATURE_XGMI_BIT;
+	data->smu_features[GNLD_ECC].smu_feature_id = FEATURE_ECC_BIT;
 
 	for (i = 0; i < GNLD_FEATURES_MAX; i++) {
 		data->smu_features[i].smu_feature_bitmap =
@@ -3020,7 +3027,8 @@ static int vega20_get_ppfeature_status(struct pp_hwmgr *hwmgr, char *buf)
 				"FCLK_DS",
 				"MP1CLK_DS",
 				"MP0CLK_DS",
-				"XGMI"};
+				"XGMI",
+				"ECC"};
 	static const char *output_title[] = {
 				"FEATURES",
 				"BITMASK",
@@ -3462,6 +3470,7 @@ static int vega20_apply_clocks_adjust_rules(struct pp_hwmgr *hwmgr)
 	struct vega20_single_dpm_table *dpm_table;
 	bool vblank_too_short = false;
 	bool disable_mclk_switching;
+	bool disable_fclk_switching;
 	uint32_t i, latency;
 
 	disable_mclk_switching = ((1 < hwmgr->display_config->num_display) &&
@@ -3537,13 +3546,20 @@ static int vega20_apply_clocks_adjust_rules(struct pp_hwmgr *hwmgr)
 	if (hwmgr->display_config->nb_pstate_switch_disable)
 		dpm_table->dpm_state.hard_min_level = dpm_table->dpm_levels[dpm_table->count - 1].value;
 
+	if ((disable_mclk_switching &&
+	    (dpm_table->dpm_state.hard_min_level == dpm_table->dpm_levels[dpm_table->count - 1].value)) ||
+	     hwmgr->display_config->min_mem_set_clock / 100 >= dpm_table->dpm_levels[dpm_table->count - 1].value)
+		disable_fclk_switching = true;
+	else
+		disable_fclk_switching = false;
+
 	/* fclk */
 	dpm_table = &(data->dpm_table.fclk_table);
 	dpm_table->dpm_state.soft_min_level = dpm_table->dpm_levels[0].value;
 	dpm_table->dpm_state.soft_max_level = VG20_CLOCK_MAX_DEFAULT;
 	dpm_table->dpm_state.hard_min_level = dpm_table->dpm_levels[0].value;
 	dpm_table->dpm_state.hard_max_level = VG20_CLOCK_MAX_DEFAULT;
-	if (hwmgr->display_config->nb_pstate_switch_disable)
+	if (hwmgr->display_config->nb_pstate_switch_disable || disable_fclk_switching)
 		dpm_table->dpm_state.soft_min_level = dpm_table->dpm_levels[dpm_table->count - 1].value;
 
 	/* vclk */
diff --git a/drivers/gpu/drm/amd/powerplay/hwmgr/vega20_hwmgr.h b/drivers/gpu/drm/amd/powerplay/hwmgr/vega20_hwmgr.h
index a5bc758ae097..ac2a3118a0ae 100644
--- a/drivers/gpu/drm/amd/powerplay/hwmgr/vega20_hwmgr.h
+++ b/drivers/gpu/drm/amd/powerplay/hwmgr/vega20_hwmgr.h
@@ -80,6 +80,7 @@ enum {
 	GNLD_DS_MP1CLK,
 	GNLD_DS_MP0CLK,
 	GNLD_XGMI,
+	GNLD_ECC,
 
 	GNLD_FEATURES_MAX
 };
diff --git a/drivers/gpu/drm/amd/powerplay/inc/smu11_driver_if.h b/drivers/gpu/drm/amd/powerplay/inc/smu11_driver_if.h
index 63d5cf691549..195c4ae67058 100644
--- a/drivers/gpu/drm/amd/powerplay/inc/smu11_driver_if.h
+++ b/drivers/gpu/drm/amd/powerplay/inc/smu11_driver_if.h
@@ -99,7 +99,7 @@
 #define FEATURE_DS_MP1CLK_BIT           30
 #define FEATURE_DS_MP0CLK_BIT           31
 #define FEATURE_XGMI_BIT                32
-#define FEATURE_SPARE_33_BIT            33
+#define FEATURE_ECC_BIT                 33
 #define FEATURE_SPARE_34_BIT            34
 #define FEATURE_SPARE_35_BIT            35
 #define FEATURE_SPARE_36_BIT            36
@@ -165,7 +165,8 @@
 #define FEATURE_DS_FCLK_MASK            (1 << FEATURE_DS_FCLK_BIT            )
 #define FEATURE_DS_MP1CLK_MASK          (1 << FEATURE_DS_MP1CLK_BIT          )
 #define FEATURE_DS_MP0CLK_MASK          (1 << FEATURE_DS_MP0CLK_BIT          )
-#define FEATURE_XGMI_MASK               (1 << FEATURE_XGMI_BIT               )
+#define FEATURE_XGMI_MASK               (1ULL << FEATURE_XGMI_BIT               )
+#define FEATURE_ECC_MASK                (1ULL << FEATURE_ECC_BIT                )
 
 #define DPM_OVERRIDE_DISABLE_SOCCLK_PID             0x00000001
 #define DPM_OVERRIDE_DISABLE_UCLK_PID               0x00000002
diff --git a/drivers/gpu/drm/bridge/synopsys/dw-hdmi.c b/drivers/gpu/drm/bridge/synopsys/dw-hdmi.c
index a63e5f0dae56..ab7968c8f6a2 100644
--- a/drivers/gpu/drm/bridge/synopsys/dw-hdmi.c
+++ b/drivers/gpu/drm/bridge/synopsys/dw-hdmi.c
@@ -1037,6 +1037,35 @@ void dw_hdmi_phy_i2c_write(struct dw_hdmi *hdmi, unsigned short data,
 }
 EXPORT_SYMBOL_GPL(dw_hdmi_phy_i2c_write);
 
+/* Filter out invalid setups to avoid configuring SCDC and scrambling */
+static bool dw_hdmi_support_scdc(struct dw_hdmi *hdmi)
+{
+	struct drm_display_info *display = &hdmi->connector.display_info;
+
+	/* Completely disable SCDC support for older controllers */
+	if (hdmi->version < 0x200a)
+		return false;
+
+	/* Disable if no DDC bus */
+	if (!hdmi->ddc)
+		return false;
+
+	/* Disable if SCDC is not supported, or if an HF-VSDB block is absent */
+	if (!display->hdmi.scdc.supported ||
+	    !display->hdmi.scdc.scrambling.supported)
+		return false;
+
+	/*
+	 * Disable if display only support low TMDS rates and scrambling
+	 * for low rates is not supported either
+	 */
+	if (!display->hdmi.scdc.scrambling.low_rates &&
+	    display->max_tmds_clock <= 340000)
+		return false;
+
+	return true;
+}
+
 /*
  * HDMI2.0 Specifies the following procedure for High TMDS Bit Rates:
  * - The Source shall suspend transmission of the TMDS clock and data
@@ -1055,7 +1084,7 @@ void dw_hdmi_set_high_tmds_clock_ratio(struct dw_hdmi *hdmi)
 	unsigned long mtmdsclock = hdmi->hdmi_data.video_mode.mtmdsclock;
 
 	/* Control for TMDS Bit Period/TMDS Clock-Period Ratio */
-	if (hdmi->connector.display_info.hdmi.scdc.supported) {
+	if (dw_hdmi_support_scdc(hdmi)) {
 		if (mtmdsclock > HDMI14_MAX_TMDSCLK)
 			drm_scdc_set_high_tmds_clock_ratio(hdmi->ddc, 1);
 		else
@@ -1579,8 +1608,9 @@ static void hdmi_av_composer(struct dw_hdmi *hdmi,
 
 	/* Set up HDMI_FC_INVIDCONF */
 	inv_val = (hdmi->hdmi_data.hdcp_enable ||
-		   vmode->mtmdsclock > HDMI14_MAX_TMDSCLK ||
-		   hdmi_info->scdc.scrambling.low_rates ?
+		   (dw_hdmi_support_scdc(hdmi) &&
+		    (vmode->mtmdsclock > HDMI14_MAX_TMDSCLK ||
+		     hdmi_info->scdc.scrambling.low_rates)) ?
 		HDMI_FC_INVIDCONF_HDCP_KEEPOUT_ACTIVE :
 		HDMI_FC_INVIDCONF_HDCP_KEEPOUT_INACTIVE);
 
@@ -1646,7 +1676,7 @@ static void hdmi_av_composer(struct dw_hdmi *hdmi,
 	}
 
 	/* Scrambling Control */
-	if (hdmi_info->scdc.supported) {
+	if (dw_hdmi_support_scdc(hdmi)) {
 		if (vmode->mtmdsclock > HDMI14_MAX_TMDSCLK ||
 		    hdmi_info->scdc.scrambling.low_rates) {
 			/*
@@ -1658,13 +1688,13 @@ static void hdmi_av_composer(struct dw_hdmi *hdmi,
 			 * Source Devices compliant shall set the
 			 * Source Version = 1.
 			 */
-			drm_scdc_readb(&hdmi->i2c->adap, SCDC_SINK_VERSION,
+			drm_scdc_readb(hdmi->ddc, SCDC_SINK_VERSION,
 				       &bytes);
-			drm_scdc_writeb(&hdmi->i2c->adap, SCDC_SOURCE_VERSION,
+			drm_scdc_writeb(hdmi->ddc, SCDC_SOURCE_VERSION,
 				min_t(u8, bytes, SCDC_MIN_SOURCE_VERSION));
 
 			/* Enabled Scrambling in the Sink */
-			drm_scdc_set_scrambling(&hdmi->i2c->adap, 1);
+			drm_scdc_set_scrambling(hdmi->ddc, 1);
 
 			/*
 			 * To activate the scrambler feature, you must ensure
@@ -1680,7 +1710,7 @@ static void hdmi_av_composer(struct dw_hdmi *hdmi,
 			hdmi_writeb(hdmi, 0, HDMI_FC_SCRAMBLER_CTRL);
 			hdmi_writeb(hdmi, (u8)~HDMI_MC_SWRSTZ_TMDSSWRST_REQ,
 				    HDMI_MC_SWRSTZ);
-			drm_scdc_set_scrambling(&hdmi->i2c->adap, 0);
+			drm_scdc_set_scrambling(hdmi->ddc, 0);
 		}
 	}
 
@@ -1774,6 +1804,8 @@ static void dw_hdmi_clear_overflow(struct dw_hdmi *hdmi)
 	 * iteration for others.
 	 * The Amlogic Meson GX SoCs (v2.01a) have been identified as needing
 	 * the workaround with a single iteration.
+	 * The Rockchip RK3288 SoC (v2.00a) and RK3328/RK3399 SoCs (v2.11a) have
+	 * been identified as needing the workaround with a single iteration.
 	 */
 
 	switch (hdmi->version) {
@@ -1782,7 +1814,9 @@ static void dw_hdmi_clear_overflow(struct dw_hdmi *hdmi)
 		break;
 	case 0x131a:
 	case 0x132a:
+	case 0x200a:
 	case 0x201a:
+	case 0x211a:
 	case 0x212a:
 		count = 1;
 		break;
diff --git a/drivers/gpu/drm/drm_atomic_helper.c b/drivers/gpu/drm/drm_atomic_helper.c
index 40ac19848034..fbb76332cc9f 100644
--- a/drivers/gpu/drm/drm_atomic_helper.c
+++ b/drivers/gpu/drm/drm_atomic_helper.c
@@ -1034,7 +1034,7 @@ disable_outputs(struct drm_device *dev, struct drm_atomic_state *old_state)
 			funcs->atomic_disable(crtc, old_crtc_state);
 		else if (funcs->disable)
 			funcs->disable(crtc);
-		else
+		else if (funcs->dpms)
 			funcs->dpms(crtc, DRM_MODE_DPMS_OFF);
 
 		if (!(dev->irq_enabled && dev->num_crtcs))
@@ -1277,10 +1277,9 @@ void drm_atomic_helper_commit_modeset_enables(struct drm_device *dev,
 		if (new_crtc_state->enable) {
 			DRM_DEBUG_ATOMIC("enabling [CRTC:%d:%s]\n",
 					 crtc->base.id, crtc->name);
-
 			if (funcs->atomic_enable)
 				funcs->atomic_enable(crtc, old_crtc_state);
-			else
+			else if (funcs->commit)
 				funcs->commit(crtc);
 		}
 	}
diff --git a/drivers/gpu/drm/drm_drv.c b/drivers/gpu/drm/drm_drv.c
index 381581b01d48..05bbc2b622fc 100644
--- a/drivers/gpu/drm/drm_drv.c
+++ b/drivers/gpu/drm/drm_drv.c
@@ -376,11 +376,7 @@ void drm_dev_unplug(struct drm_device *dev)
 	synchronize_srcu(&drm_unplug_srcu);
 
 	drm_dev_unregister(dev);
-
-	mutex_lock(&drm_global_mutex);
-	if (dev->open_count == 0)
-		drm_dev_put(dev);
-	mutex_unlock(&drm_global_mutex);
+	drm_dev_put(dev);
 }
 EXPORT_SYMBOL(drm_dev_unplug);
 
diff --git a/drivers/gpu/drm/drm_fb_helper.c b/drivers/gpu/drm/drm_fb_helper.c
index 0e9349ff2d16..af2ab640cadb 100644
--- a/drivers/gpu/drm/drm_fb_helper.c
+++ b/drivers/gpu/drm/drm_fb_helper.c
@@ -1963,7 +1963,7 @@ static int drm_fb_helper_single_fb_probe(struct drm_fb_helper *fb_helper,
 				best_depth = fmt->depth;
 		}
 	}
-	if (sizes.surface_depth != best_depth) {
+	if (sizes.surface_depth != best_depth && best_depth) {
 		DRM_INFO("requested bpp %d, scaled depth down to %d",
 			 sizes.surface_bpp, best_depth);
 		sizes.surface_depth = best_depth;
diff --git a/drivers/gpu/drm/drm_file.c b/drivers/gpu/drm/drm_file.c
index 83a5bbca6e7e..7caa3c7ed978 100644
--- a/drivers/gpu/drm/drm_file.c
+++ b/drivers/gpu/drm/drm_file.c
@@ -489,11 +489,9 @@ int drm_release(struct inode *inode, struct file *filp)
 
 	drm_close_helper(filp);
 
-	if (!--dev->open_count) {
+	if (!--dev->open_count)
 		drm_lastclose(dev);
-		if (drm_dev_is_unplugged(dev))
-			drm_put_dev(dev);
-	}
+
 	mutex_unlock(&drm_global_mutex);
 
 	drm_minor_release(minor);
diff --git a/drivers/gpu/drm/drm_mm.c b/drivers/gpu/drm/drm_mm.c
index 2b4f373736c7..8b4cd31ce7bd 100644
--- a/drivers/gpu/drm/drm_mm.c
+++ b/drivers/gpu/drm/drm_mm.c
@@ -106,25 +106,19 @@
 static noinline void save_stack(struct drm_mm_node *node)
 {
 	unsigned long entries[STACKDEPTH];
-	struct stack_trace trace = {
-		.entries = entries,
-		.max_entries = STACKDEPTH,
-		.skip = 1
-	};
+	unsigned int n;
 
-	save_stack_trace(&trace);
-	if (trace.nr_entries != 0 &&
-	    trace.entries[trace.nr_entries-1] == ULONG_MAX)
-		trace.nr_entries--;
+	n = stack_trace_save(entries, ARRAY_SIZE(entries), 1);
 
 	/* May be called under spinlock, so avoid sleeping */
-	node->stack = depot_save_stack(&trace, GFP_NOWAIT);
+	node->stack = stack_depot_save(entries, n, GFP_NOWAIT);
 }
 
 static void show_leaks(struct drm_mm *mm)
 {
 	struct drm_mm_node *node;
-	unsigned long entries[STACKDEPTH];
+	unsigned long *entries;
+	unsigned int nr_entries;
 	char *buf;
 
 	buf = kmalloc(BUFSZ, GFP_KERNEL);
@@ -132,19 +126,14 @@ static void show_leaks(struct drm_mm *mm)
 		return;
 
 	list_for_each_entry(node, drm_mm_nodes(mm), node_list) {
-		struct stack_trace trace = {
-			.entries = entries,
-			.max_entries = STACKDEPTH
-		};
-
 		if (!node->stack) {
 			DRM_ERROR("node [%08llx + %08llx]: unknown owner\n",
 				  node->start, node->size);
 			continue;
 		}
 
-		depot_fetch_stack(node->stack, &trace);
-		snprint_stack_trace(buf, BUFSZ, &trace, 0);
+		nr_entries = stack_depot_fetch(node->stack, &entries);
+		stack_trace_snprint(buf, BUFSZ, entries, nr_entries, 0);
 		DRM_ERROR("node [%08llx + %08llx]: inserted at\n%s",
 			  node->start, node->size, buf);
 	}
diff --git a/drivers/gpu/drm/i915/gvt/cmd_parser.c b/drivers/gpu/drm/i915/gvt/cmd_parser.c
index 35b4ec3f7618..3592d04c33b2 100644
--- a/drivers/gpu/drm/i915/gvt/cmd_parser.c
+++ b/drivers/gpu/drm/i915/gvt/cmd_parser.c
@@ -1441,7 +1441,7 @@ static inline int cmd_address_audit(struct parser_exec_state *s,
 	}
 
 	if (index_mode)	{
-		if (guest_gma >= I915_GTT_PAGE_SIZE / sizeof(u64)) {
+		if (guest_gma >= I915_GTT_PAGE_SIZE) {
 			ret = -EFAULT;
 			goto err;
 		}
diff --git a/drivers/gpu/drm/i915/gvt/display.c b/drivers/gpu/drm/i915/gvt/display.c
index 035479e273be..e3f9caa7839f 100644
--- a/drivers/gpu/drm/i915/gvt/display.c
+++ b/drivers/gpu/drm/i915/gvt/display.c
@@ -448,7 +448,7 @@ void intel_gvt_emulate_vblank(struct intel_gvt *gvt)
 /**
  * intel_vgpu_emulate_hotplug - trigger hotplug event for vGPU
  * @vgpu: a vGPU
- * @conncted: link state
+ * @connected: link state
  *
  * This function is used to trigger hotplug interrupt for vGPU
  *
diff --git a/drivers/gpu/drm/i915/gvt/dmabuf.c b/drivers/gpu/drm/i915/gvt/dmabuf.c
index 3e7e2b80c857..69a9a1b2ea4a 100644
--- a/drivers/gpu/drm/i915/gvt/dmabuf.c
+++ b/drivers/gpu/drm/i915/gvt/dmabuf.c
@@ -209,7 +209,7 @@ static int vgpu_get_plane_info(struct drm_device *dev,
 	struct drm_i915_private *dev_priv = to_i915(dev);
 	struct intel_vgpu_primary_plane_format p;
 	struct intel_vgpu_cursor_plane_format c;
-	int ret;
+	int ret, tile_height = 1;
 
 	if (plane_id == DRM_PLANE_TYPE_PRIMARY) {
 		ret = intel_vgpu_decode_primary_plane(vgpu, &p);
@@ -228,19 +228,19 @@ static int vgpu_get_plane_info(struct drm_device *dev,
 			break;
 		case PLANE_CTL_TILED_X:
 			info->drm_format_mod = I915_FORMAT_MOD_X_TILED;
+			tile_height = 8;
 			break;
 		case PLANE_CTL_TILED_Y:
 			info->drm_format_mod = I915_FORMAT_MOD_Y_TILED;
+			tile_height = 32;
 			break;
 		case PLANE_CTL_TILED_YF:
 			info->drm_format_mod = I915_FORMAT_MOD_Yf_TILED;
+			tile_height = 32;
 			break;
 		default:
 			gvt_vgpu_err("invalid tiling mode: %x\n", p.tiled);
 		}
-
-		info->size = (((p.stride * p.height * p.bpp) / 8) +
-			      (PAGE_SIZE - 1)) >> PAGE_SHIFT;
 	} else if (plane_id == DRM_PLANE_TYPE_CURSOR) {
 		ret = intel_vgpu_decode_cursor_plane(vgpu, &c);
 		if (ret)
@@ -262,14 +262,13 @@ static int vgpu_get_plane_info(struct drm_device *dev,
 			info->x_hot = UINT_MAX;
 			info->y_hot = UINT_MAX;
 		}
-
-		info->size = (((info->stride * c.height * c.bpp) / 8)
-				+ (PAGE_SIZE - 1)) >> PAGE_SHIFT;
 	} else {
 		gvt_vgpu_err("invalid plane id:%d\n", plane_id);
 		return -EINVAL;
 	}
 
+	info->size = (info->stride * roundup(info->height, tile_height)
+		      + PAGE_SIZE - 1) >> PAGE_SHIFT;
 	if (info->size == 0) {
 		gvt_vgpu_err("fb size is zero\n");
 		return -EINVAL;
diff --git a/drivers/gpu/drm/i915/gvt/gtt.c b/drivers/gpu/drm/i915/gvt/gtt.c
index c7103dd2d8d5..9814773882ec 100644
--- a/drivers/gpu/drm/i915/gvt/gtt.c
+++ b/drivers/gpu/drm/i915/gvt/gtt.c
@@ -750,14 +750,20 @@ static void ppgtt_free_spt(struct intel_vgpu_ppgtt_spt *spt)
 
 static void ppgtt_free_all_spt(struct intel_vgpu *vgpu)
 {
-	struct intel_vgpu_ppgtt_spt *spt;
+	struct intel_vgpu_ppgtt_spt *spt, *spn;
 	struct radix_tree_iter iter;
-	void **slot;
+	LIST_HEAD(all_spt);
+	void __rcu **slot;
 
+	rcu_read_lock();
 	radix_tree_for_each_slot(slot, &vgpu->gtt.spt_tree, &iter, 0) {
 		spt = radix_tree_deref_slot(slot);
-		ppgtt_free_spt(spt);
+		list_move(&spt->post_shadow_list, &all_spt);
 	}
+	rcu_read_unlock();
+
+	list_for_each_entry_safe(spt, spn, &all_spt, post_shadow_list)
+		ppgtt_free_spt(spt);
 }
 
 static int ppgtt_handle_guest_write_page_table_bytes(
@@ -1882,7 +1888,11 @@ struct intel_vgpu_mm *intel_vgpu_create_ppgtt_mm(struct intel_vgpu *vgpu,
 	}
 
 	list_add_tail(&mm->ppgtt_mm.list, &vgpu->gtt.ppgtt_mm_list_head);
+
+	mutex_lock(&gvt->gtt.ppgtt_mm_lock);
 	list_add_tail(&mm->ppgtt_mm.lru_list, &gvt->gtt.ppgtt_mm_lru_list_head);
+	mutex_unlock(&gvt->gtt.ppgtt_mm_lock);
+
 	return mm;
 }
 
@@ -1942,7 +1952,7 @@ void _intel_vgpu_mm_release(struct kref *mm_ref)
  */
 void intel_vgpu_unpin_mm(struct intel_vgpu_mm *mm)
 {
-	atomic_dec(&mm->pincount);
+	atomic_dec_if_positive(&mm->pincount);
 }
 
 /**
@@ -1967,9 +1977,10 @@ int intel_vgpu_pin_mm(struct intel_vgpu_mm *mm)
 		if (ret)
 			return ret;
 
+		mutex_lock(&mm->vgpu->gvt->gtt.ppgtt_mm_lock);
 		list_move_tail(&mm->ppgtt_mm.lru_list,
 			       &mm->vgpu->gvt->gtt.ppgtt_mm_lru_list_head);
-
+		mutex_unlock(&mm->vgpu->gvt->gtt.ppgtt_mm_lock);
 	}
 
 	return 0;
@@ -1980,6 +1991,8 @@ static int reclaim_one_ppgtt_mm(struct intel_gvt *gvt)
 	struct intel_vgpu_mm *mm;
 	struct list_head *pos, *n;
 
+	mutex_lock(&gvt->gtt.ppgtt_mm_lock);
+
 	list_for_each_safe(pos, n, &gvt->gtt.ppgtt_mm_lru_list_head) {
 		mm = container_of(pos, struct intel_vgpu_mm, ppgtt_mm.lru_list);
 
@@ -1987,9 +2000,11 @@ static int reclaim_one_ppgtt_mm(struct intel_gvt *gvt)
 			continue;
 
 		list_del_init(&mm->ppgtt_mm.lru_list);
+		mutex_unlock(&gvt->gtt.ppgtt_mm_lock);
 		invalidate_ppgtt_mm(mm);
 		return 1;
 	}
+	mutex_unlock(&gvt->gtt.ppgtt_mm_lock);
 	return 0;
 }
 
@@ -2659,6 +2674,7 @@ int intel_gvt_init_gtt(struct intel_gvt *gvt)
 		}
 	}
 	INIT_LIST_HEAD(&gvt->gtt.ppgtt_mm_lru_list_head);
+	mutex_init(&gvt->gtt.ppgtt_mm_lock);
 	return 0;
 }
 
@@ -2699,7 +2715,9 @@ void intel_vgpu_invalidate_ppgtt(struct intel_vgpu *vgpu)
 	list_for_each_safe(pos, n, &vgpu->gtt.ppgtt_mm_list_head) {
 		mm = container_of(pos, struct intel_vgpu_mm, ppgtt_mm.list);
 		if (mm->type == INTEL_GVT_MM_PPGTT) {
+			mutex_lock(&vgpu->gvt->gtt.ppgtt_mm_lock);
 			list_del_init(&mm->ppgtt_mm.lru_list);
+			mutex_unlock(&vgpu->gvt->gtt.ppgtt_mm_lock);
 			if (mm->ppgtt_mm.shadowed)
 				invalidate_ppgtt_mm(mm);
 		}
diff --git a/drivers/gpu/drm/i915/gvt/gtt.h b/drivers/gpu/drm/i915/gvt/gtt.h
index d8cb04cc946d..edb610dc5d86 100644
--- a/drivers/gpu/drm/i915/gvt/gtt.h
+++ b/drivers/gpu/drm/i915/gvt/gtt.h
@@ -88,6 +88,7 @@ struct intel_gvt_gtt {
 	void (*mm_free_page_table)(struct intel_vgpu_mm *mm);
 	struct list_head oos_page_use_list_head;
 	struct list_head oos_page_free_list_head;
+	struct mutex ppgtt_mm_lock;
 	struct list_head ppgtt_mm_lru_list_head;
 
 	struct page *scratch_page;
diff --git a/drivers/gpu/drm/i915/gvt/kvmgt.c b/drivers/gpu/drm/i915/gvt/kvmgt.c
index d5fcc447d22f..a68addf95c23 100644
--- a/drivers/gpu/drm/i915/gvt/kvmgt.c
+++ b/drivers/gpu/drm/i915/gvt/kvmgt.c
@@ -905,7 +905,7 @@ static inline bool intel_vgpu_in_aperture(struct intel_vgpu *vgpu, u64 off)
 static int intel_vgpu_aperture_rw(struct intel_vgpu *vgpu, u64 off,
 		void *buf, unsigned long count, bool is_write)
 {
-	void *aperture_va;
+	void __iomem *aperture_va;
 
 	if (!intel_vgpu_in_aperture(vgpu, off) ||
 	    !intel_vgpu_in_aperture(vgpu, off + count)) {
@@ -920,9 +920,9 @@ static int intel_vgpu_aperture_rw(struct intel_vgpu *vgpu, u64 off,
 		return -EIO;
 
 	if (is_write)
-		memcpy(aperture_va + offset_in_page(off), buf, count);
+		memcpy_toio(aperture_va + offset_in_page(off), buf, count);
 	else
-		memcpy(buf, aperture_va + offset_in_page(off), count);
+		memcpy_fromio(buf, aperture_va + offset_in_page(off), count);
 
 	io_mapping_unmap(aperture_va);
 
diff --git a/drivers/gpu/drm/i915/gvt/mmio_context.c b/drivers/gpu/drm/i915/gvt/mmio_context.c
index 7d84cfb9051a..7902fb162d09 100644
--- a/drivers/gpu/drm/i915/gvt/mmio_context.c
+++ b/drivers/gpu/drm/i915/gvt/mmio_context.c
@@ -132,6 +132,7 @@ static struct engine_mmio gen9_engine_mmio_list[] __cacheline_aligned = {
 
 	{RCS, GEN9_GAMT_ECO_REG_RW_IA, 0x0, false}, /* 0x4ab0 */
 	{RCS, GEN9_CSFE_CHICKEN1_RCS, 0xffff, false}, /* 0x20d4 */
+	{RCS, _MMIO(0x20D8), 0xffff, true}, /* 0x20d8 */
 
 	{RCS, GEN8_GARBCNTL, 0x0, false}, /* 0xb004 */
 	{RCS, GEN7_FF_THREAD_MODE, 0x0, false}, /* 0x20a0 */
diff --git a/drivers/gpu/drm/i915/gvt/scheduler.c b/drivers/gpu/drm/i915/gvt/scheduler.c
index 1bb8f936fdaa..05b953793316 100644
--- a/drivers/gpu/drm/i915/gvt/scheduler.c
+++ b/drivers/gpu/drm/i915/gvt/scheduler.c
@@ -346,7 +346,7 @@ static int set_context_ppgtt_from_shadow(struct intel_vgpu_workload *workload,
 	int i = 0;
 
 	if (mm->type != INTEL_GVT_MM_PPGTT || !mm->ppgtt_mm.shadowed)
-		return -1;
+		return -EINVAL;
 
 	if (mm->ppgtt_mm.root_entry_type == GTT_TYPE_PPGTT_ROOT_L4_ENTRY) {
 		px_dma(&ppgtt->pml4) = mm->ppgtt_mm.shadow_pdps[0];
@@ -410,12 +410,6 @@ int intel_gvt_scan_and_shadow_workload(struct intel_vgpu_workload *workload)
 	if (workload->shadow)
 		return 0;
 
-	ret = set_context_ppgtt_from_shadow(workload, shadow_ctx);
-	if (ret < 0) {
-		gvt_vgpu_err("workload shadow ppgtt isn't ready\n");
-		return ret;
-	}
-
 	/* pin shadow context by gvt even the shadow context will be pinned
 	 * when i915 alloc request. That is because gvt will update the guest
 	 * context from shadow context when workload is completed, and at that
@@ -678,6 +672,9 @@ static int dispatch_workload(struct intel_vgpu_workload *workload)
 {
 	struct intel_vgpu *vgpu = workload->vgpu;
 	struct drm_i915_private *dev_priv = vgpu->gvt->dev_priv;
+	struct intel_vgpu_submission *s = &vgpu->submission;
+	struct i915_gem_context *shadow_ctx = s->shadow_ctx;
+	struct i915_request *rq;
 	int ring_id = workload->ring_id;
 	int ret;
 
@@ -687,6 +684,12 @@ static int dispatch_workload(struct intel_vgpu_workload *workload)
 	mutex_lock(&vgpu->vgpu_lock);
 	mutex_lock(&dev_priv->drm.struct_mutex);
 
+	ret = set_context_ppgtt_from_shadow(workload, shadow_ctx);
+	if (ret < 0) {
+		gvt_vgpu_err("workload shadow ppgtt isn't ready\n");
+		goto err_req;
+	}
+
 	ret = intel_gvt_workload_req_alloc(workload);
 	if (ret)
 		goto err_req;
@@ -703,6 +706,14 @@ static int dispatch_workload(struct intel_vgpu_workload *workload)
 
 	ret = prepare_workload(workload);
 out:
+	if (ret) {
+		/* We might still need to add request with
+		 * clean ctx to retire it properly..
+		 */
+		rq = fetch_and_zero(&workload->req);
+		i915_request_put(rq);
+	}
+
 	if (!IS_ERR_OR_NULL(workload->req)) {
 		gvt_dbg_sched("ring id %d submit workload to i915 %p\n",
 				ring_id, workload->req);
@@ -739,7 +750,8 @@ static struct intel_vgpu_workload *pick_next_workload(
 		goto out;
 	}
 
-	if (list_empty(workload_q_head(scheduler->current_vgpu, ring_id)))
+	if (!scheduler->current_vgpu->active ||
+	    list_empty(workload_q_head(scheduler->current_vgpu, ring_id)))
 		goto out;
 
 	/*
@@ -1474,8 +1486,9 @@ intel_vgpu_create_workload(struct intel_vgpu *vgpu, int ring_id,
 		intel_runtime_pm_put_unchecked(dev_priv);
 	}
 
-	if (ret && (vgpu_is_vm_unhealthy(ret))) {
-		enter_failsafe_mode(vgpu, GVT_FAILSAFE_GUEST_ERR);
+	if (ret) {
+		if (vgpu_is_vm_unhealthy(ret))
+			enter_failsafe_mode(vgpu, GVT_FAILSAFE_GUEST_ERR);
 		intel_vgpu_destroy_workload(workload);
 		return ERR_PTR(ret);
 	}
diff --git a/drivers/gpu/drm/i915/i915_debugfs.c b/drivers/gpu/drm/i915/i915_debugfs.c
index 0bd890c04fe4..f6f6e5b78e97 100644
--- a/drivers/gpu/drm/i915/i915_debugfs.c
+++ b/drivers/gpu/drm/i915/i915_debugfs.c
@@ -4830,7 +4830,10 @@ static int i915_dsc_fec_support_show(struct seq_file *m, void *data)
 		ret = drm_modeset_lock(&dev->mode_config.connection_mutex,
 				       &ctx);
 		if (ret) {
-			ret = -EINTR;
+			if (ret == -EDEADLK && !drm_modeset_backoff(&ctx)) {
+				try_again = true;
+				continue;
+			}
 			break;
 		}
 		crtc = connector->state->crtc;
diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h
index 9adc7bb9e69c..a67a63b5aa84 100644
--- a/drivers/gpu/drm/i915/i915_drv.h
+++ b/drivers/gpu/drm/i915/i915_drv.h
@@ -2346,7 +2346,8 @@ static inline unsigned int i915_sg_segment_size(void)
 				 INTEL_DEVID(dev_priv) == 0x5915 || \
 				 INTEL_DEVID(dev_priv) == 0x591E)
 #define IS_AML_ULX(dev_priv)	(INTEL_DEVID(dev_priv) == 0x591C || \
-				 INTEL_DEVID(dev_priv) == 0x87C0)
+				 INTEL_DEVID(dev_priv) == 0x87C0 || \
+				 INTEL_DEVID(dev_priv) == 0x87CA)
 #define IS_SKL_GT2(dev_priv)	(IS_SKYLAKE(dev_priv) && \
 				 INTEL_INFO(dev_priv)->gt == 2)
 #define IS_SKL_GT3(dev_priv)	(IS_SKYLAKE(dev_priv) && \
diff --git a/drivers/gpu/drm/i915/i915_gem_execbuffer.c b/drivers/gpu/drm/i915/i915_gem_execbuffer.c
index 02adcaf6ebea..16f80a448820 100644
--- a/drivers/gpu/drm/i915/i915_gem_execbuffer.c
+++ b/drivers/gpu/drm/i915/i915_gem_execbuffer.c
@@ -1667,6 +1667,7 @@ static int eb_copy_relocations(const struct i915_execbuffer *eb)
 					     len)) {
 end_user:
 				user_access_end();
+end:
 				kvfree(relocs);
 				err = -EFAULT;
 				goto err;
@@ -1686,7 +1687,7 @@ end_user:
 		 * relocations were valid.
 		 */
 		if (!user_access_begin(urelocs, size))
-			goto end_user;
+			goto end;
 
 		for (copied = 0; copied < nreloc; copied++)
 			unsafe_put_user(-1,
@@ -2695,7 +2696,7 @@ i915_gem_execbuffer2_ioctl(struct drm_device *dev, void *data,
 		 * when we did the "copy_from_user()" above.
 		 */
 		if (!user_access_begin(user_exec_list, count * sizeof(*user_exec_list)))
-			goto end_user;
+			goto end;
 
 		for (i = 0; i < args->buffer_count; i++) {
 			if (!(exec2_list[i].offset & UPDATE))
@@ -2709,6 +2710,7 @@ i915_gem_execbuffer2_ioctl(struct drm_device *dev, void *data,
 		}
 end_user:
 		user_access_end();
+end:;
 	}
 
 	args->flags &= ~__I915_EXEC_UNKNOWN_FLAGS;
diff --git a/drivers/gpu/drm/i915/i915_reg.h b/drivers/gpu/drm/i915/i915_reg.h
index 638a586469f9..047855dd8c6b 100644
--- a/drivers/gpu/drm/i915/i915_reg.h
+++ b/drivers/gpu/drm/i915/i915_reg.h
@@ -2863,7 +2863,7 @@ enum i915_power_well_id {
 #define GEN11_GT_VEBOX_VDBOX_DISABLE	_MMIO(0x9140)
 #define   GEN11_GT_VDBOX_DISABLE_MASK	0xff
 #define   GEN11_GT_VEBOX_DISABLE_SHIFT	16
-#define   GEN11_GT_VEBOX_DISABLE_MASK	(0xff << GEN11_GT_VEBOX_DISABLE_SHIFT)
+#define   GEN11_GT_VEBOX_DISABLE_MASK	(0x0f << GEN11_GT_VEBOX_DISABLE_SHIFT)
 
 #define GEN11_EU_DISABLE _MMIO(0x9134)
 #define GEN11_EU_DIS_MASK 0xFF
@@ -9243,7 +9243,7 @@ enum skl_power_gate {
 #define TRANS_DDI_FUNC_CTL2(tran)	_MMIO_TRANS2(tran, \
 						     _TRANS_DDI_FUNC_CTL2_A)
 #define  PORT_SYNC_MODE_ENABLE			(1 << 4)
-#define  PORT_SYNC_MODE_MASTER_SELECT(x)	((x) < 0)
+#define  PORT_SYNC_MODE_MASTER_SELECT(x)	((x) << 0)
 #define  PORT_SYNC_MODE_MASTER_SELECT_MASK	(0x7 << 0)
 #define  PORT_SYNC_MODE_MASTER_SELECT_SHIFT	0
 
diff --git a/drivers/gpu/drm/i915/i915_vma.c b/drivers/gpu/drm/i915/i915_vma.c
index b713bed20c38..41b5bcb803cb 100644
--- a/drivers/gpu/drm/i915/i915_vma.c
+++ b/drivers/gpu/drm/i915/i915_vma.c
@@ -36,11 +36,8 @@
 
 static void vma_print_allocator(struct i915_vma *vma, const char *reason)
 {
-	unsigned long entries[12];
-	struct stack_trace trace = {
-		.entries = entries,
-		.max_entries = ARRAY_SIZE(entries),
-	};
+	unsigned long *entries;
+	unsigned int nr_entries;
 	char buf[512];
 
 	if (!vma->node.stack) {
@@ -49,8 +46,8 @@ static void vma_print_allocator(struct i915_vma *vma, const char *reason)
 		return;
 	}
 
-	depot_fetch_stack(vma->node.stack, &trace);
-	snprint_stack_trace(buf, sizeof(buf), &trace, 0);
+	nr_entries = stack_depot_fetch(vma->node.stack, &entries);
+	stack_trace_snprint(buf, sizeof(buf), entries, nr_entries, 0);
 	DRM_DEBUG_DRIVER("vma.node [%08llx + %08llx] %s: inserted at %s\n",
 			 vma->node.start, vma->node.size, reason, buf);
 }
diff --git a/drivers/gpu/drm/i915/icl_dsi.c b/drivers/gpu/drm/i915/icl_dsi.c
index 73a7bee24a66..641e0778fa9c 100644
--- a/drivers/gpu/drm/i915/icl_dsi.c
+++ b/drivers/gpu/drm/i915/icl_dsi.c
@@ -323,6 +323,21 @@ static void gen11_dsi_program_esc_clk_div(struct intel_encoder *encoder)
 	}
 }
 
+static void get_dsi_io_power_domains(struct drm_i915_private *dev_priv,
+				     struct intel_dsi *intel_dsi)
+{
+	enum port port;
+
+	for_each_dsi_port(port, intel_dsi->ports) {
+		WARN_ON(intel_dsi->io_wakeref[port]);
+		intel_dsi->io_wakeref[port] =
+			intel_display_power_get(dev_priv,
+						port == PORT_A ?
+						POWER_DOMAIN_PORT_DDI_A_IO :
+						POWER_DOMAIN_PORT_DDI_B_IO);
+	}
+}
+
 static void gen11_dsi_enable_io_power(struct intel_encoder *encoder)
 {
 	struct drm_i915_private *dev_priv = to_i915(encoder->base.dev);
@@ -336,13 +351,7 @@ static void gen11_dsi_enable_io_power(struct intel_encoder *encoder)
 		I915_WRITE(ICL_DSI_IO_MODECTL(port), tmp);
 	}
 
-	for_each_dsi_port(port, intel_dsi->ports) {
-		intel_dsi->io_wakeref[port] =
-			intel_display_power_get(dev_priv,
-						port == PORT_A ?
-						POWER_DOMAIN_PORT_DDI_A_IO :
-						POWER_DOMAIN_PORT_DDI_B_IO);
-	}
+	get_dsi_io_power_domains(dev_priv, intel_dsi);
 }
 
 static void gen11_dsi_power_up_lanes(struct intel_encoder *encoder)
@@ -589,6 +598,12 @@ static void gen11_dsi_map_pll(struct intel_encoder *encoder,
 		val |= DPCLKA_CFGCR0_DDI_CLK_SEL(pll->info->id, port);
 	}
 	I915_WRITE(DPCLKA_CFGCR0_ICL, val);
+
+	for_each_dsi_port(port, intel_dsi->ports) {
+		val &= ~DPCLKA_CFGCR0_DDI_CLK_OFF(port);
+	}
+	I915_WRITE(DPCLKA_CFGCR0_ICL, val);
+
 	POSTING_READ(DPCLKA_CFGCR0_ICL);
 
 	mutex_unlock(&dev_priv->dpll_lock);
@@ -1117,7 +1132,7 @@ static void gen11_dsi_disable_port(struct intel_encoder *encoder)
 			DRM_ERROR("DDI port:%c buffer not idle\n",
 				  port_name(port));
 	}
-	gen11_dsi_ungate_clocks(encoder);
+	gen11_dsi_gate_clocks(encoder);
 }
 
 static void gen11_dsi_disable_io_power(struct intel_encoder *encoder)
@@ -1218,20 +1233,11 @@ static int gen11_dsi_compute_config(struct intel_encoder *encoder,
 	return 0;
 }
 
-static u64 gen11_dsi_get_power_domains(struct intel_encoder *encoder,
-				       struct intel_crtc_state *crtc_state)
+static void gen11_dsi_get_power_domains(struct intel_encoder *encoder,
+					struct intel_crtc_state *crtc_state)
 {
-	struct intel_dsi *intel_dsi = enc_to_intel_dsi(&encoder->base);
-	u64 domains = 0;
-	enum port port;
-
-	for_each_dsi_port(port, intel_dsi->ports)
-		if (port == PORT_A)
-			domains |= BIT_ULL(POWER_DOMAIN_PORT_DDI_A_IO);
-		else
-			domains |= BIT_ULL(POWER_DOMAIN_PORT_DDI_B_IO);
-
-	return domains;
+	get_dsi_io_power_domains(to_i915(encoder->base.dev),
+				 enc_to_intel_dsi(&encoder->base));
 }
 
 static bool gen11_dsi_get_hw_state(struct intel_encoder *encoder,
diff --git a/drivers/gpu/drm/i915/intel_ddi.c b/drivers/gpu/drm/i915/intel_ddi.c
index 14d580cdefd3..98cea1f4b3bf 100644
--- a/drivers/gpu/drm/i915/intel_ddi.c
+++ b/drivers/gpu/drm/i915/intel_ddi.c
@@ -2075,12 +2075,11 @@ intel_ddi_main_link_aux_domain(struct intel_digital_port *dig_port)
 					      intel_aux_power_domain(dig_port);
 }
 
-static u64 intel_ddi_get_power_domains(struct intel_encoder *encoder,
-				       struct intel_crtc_state *crtc_state)
+static void intel_ddi_get_power_domains(struct intel_encoder *encoder,
+					struct intel_crtc_state *crtc_state)
 {
 	struct drm_i915_private *dev_priv = to_i915(encoder->base.dev);
 	struct intel_digital_port *dig_port;
-	u64 domains;
 
 	/*
 	 * TODO: Add support for MST encoders. Atm, the following should never
@@ -2088,10 +2087,10 @@ static u64 intel_ddi_get_power_domains(struct intel_encoder *encoder,
 	 * hook.
 	 */
 	if (WARN_ON(intel_crtc_has_type(crtc_state, INTEL_OUTPUT_DP_MST)))
-		return 0;
+		return;
 
 	dig_port = enc_to_dig_port(&encoder->base);
-	domains = BIT_ULL(dig_port->ddi_io_power_domain);
+	intel_display_power_get(dev_priv, dig_port->ddi_io_power_domain);
 
 	/*
 	 * AUX power is only needed for (e)DP mode, and for HDMI mode on TC
@@ -2099,15 +2098,15 @@ static u64 intel_ddi_get_power_domains(struct intel_encoder *encoder,
 	 */
 	if (intel_crtc_has_dp_encoder(crtc_state) ||
 	    intel_port_is_tc(dev_priv, encoder->port))
-		domains |= BIT_ULL(intel_ddi_main_link_aux_domain(dig_port));
+		intel_display_power_get(dev_priv,
+					intel_ddi_main_link_aux_domain(dig_port));
 
 	/*
 	 * VDSC power is needed when DSC is enabled
 	 */
 	if (crtc_state->dsc_params.compression_enable)
-		domains |= BIT_ULL(intel_dsc_power_domain(crtc_state));
-
-	return domains;
+		intel_display_power_get(dev_priv,
+					intel_dsc_power_domain(crtc_state));
 }
 
 void intel_ddi_enable_pipe_clock(const struct intel_crtc_state *crtc_state)
@@ -2825,10 +2824,10 @@ void icl_sanitize_encoder_pll_mapping(struct intel_encoder *encoder)
 				return;
 		}
 		/*
-		 * DSI ports should have their DDI clock ungated when disabled
-		 * and gated when enabled.
+		 * For DSI we keep the ddi clocks gated
+		 * except during enable/disable sequence.
 		 */
-		ddi_clk_needed = !encoder->base.crtc;
+		ddi_clk_needed = false;
 	}
 
 	val = I915_READ(DPCLKA_CFGCR0_ICL);
@@ -3863,14 +3862,16 @@ static int intel_ddi_compute_config(struct intel_encoder *encoder,
 		ret = intel_hdmi_compute_config(encoder, pipe_config, conn_state);
 	else
 		ret = intel_dp_compute_config(encoder, pipe_config, conn_state);
+	if (ret)
+		return ret;
 
-	if (IS_GEN9_LP(dev_priv) && ret)
+	if (IS_GEN9_LP(dev_priv))
 		pipe_config->lane_lat_optim_mask =
 			bxt_ddi_phy_calc_lane_lat_optim_mask(pipe_config->lane_count);
 
 	intel_ddi_compute_min_voltage_level(dev_priv, pipe_config);
 
-	return ret;
+	return 0;
 
 }
 
diff --git a/drivers/gpu/drm/i915/intel_display.c b/drivers/gpu/drm/i915/intel_display.c
index ccb616351bba..421aac80a838 100644
--- a/drivers/gpu/drm/i915/intel_display.c
+++ b/drivers/gpu/drm/i915/intel_display.c
@@ -15986,8 +15986,6 @@ get_encoder_power_domains(struct drm_i915_private *dev_priv)
 	struct intel_encoder *encoder;
 
 	for_each_intel_encoder(&dev_priv->drm, encoder) {
-		u64 get_domains;
-		enum intel_display_power_domain domain;
 		struct intel_crtc_state *crtc_state;
 
 		if (!encoder->get_power_domains)
@@ -16001,9 +15999,7 @@ get_encoder_power_domains(struct drm_i915_private *dev_priv)
 			continue;
 
 		crtc_state = to_intel_crtc_state(encoder->base.crtc->state);
-		get_domains = encoder->get_power_domains(encoder, crtc_state);
-		for_each_power_domain(domain, get_domains)
-			intel_display_power_get(dev_priv, domain);
+		encoder->get_power_domains(encoder, crtc_state);
 	}
 }
 
diff --git a/drivers/gpu/drm/i915/intel_dp.c b/drivers/gpu/drm/i915/intel_dp.c
index cf709835fb9a..48da4a969a0a 100644
--- a/drivers/gpu/drm/i915/intel_dp.c
+++ b/drivers/gpu/drm/i915/intel_dp.c
@@ -1859,42 +1859,6 @@ intel_dp_compute_link_config_wide(struct intel_dp *intel_dp,
 	return -EINVAL;
 }
 
-/* Optimize link config in order: max bpp, min lanes, min clock */
-static int
-intel_dp_compute_link_config_fast(struct intel_dp *intel_dp,
-				  struct intel_crtc_state *pipe_config,
-				  const struct link_config_limits *limits)
-{
-	struct drm_display_mode *adjusted_mode = &pipe_config->base.adjusted_mode;
-	int bpp, clock, lane_count;
-	int mode_rate, link_clock, link_avail;
-
-	for (bpp = limits->max_bpp; bpp >= limits->min_bpp; bpp -= 2 * 3) {
-		mode_rate = intel_dp_link_required(adjusted_mode->crtc_clock,
-						   bpp);
-
-		for (lane_count = limits->min_lane_count;
-		     lane_count <= limits->max_lane_count;
-		     lane_count <<= 1) {
-			for (clock = limits->min_clock; clock <= limits->max_clock; clock++) {
-				link_clock = intel_dp->common_rates[clock];
-				link_avail = intel_dp_max_data_rate(link_clock,
-								    lane_count);
-
-				if (mode_rate <= link_avail) {
-					pipe_config->lane_count = lane_count;
-					pipe_config->pipe_bpp = bpp;
-					pipe_config->port_clock = link_clock;
-
-					return 0;
-				}
-			}
-		}
-	}
-
-	return -EINVAL;
-}
-
 static int intel_dp_dsc_compute_bpp(struct intel_dp *intel_dp, u8 dsc_max_bpc)
 {
 	int i, num_bpc;
@@ -1922,6 +1886,9 @@ static int intel_dp_dsc_compute_config(struct intel_dp *intel_dp,
 	int pipe_bpp;
 	int ret;
 
+	pipe_config->fec_enable = !intel_dp_is_edp(intel_dp) &&
+		intel_dp_supports_fec(intel_dp, pipe_config);
+
 	if (!intel_dp_supports_dsc(intel_dp, pipe_config))
 		return -EINVAL;
 
@@ -2031,15 +1998,13 @@ intel_dp_compute_link_config(struct intel_encoder *encoder,
 	limits.min_bpp = 6 * 3;
 	limits.max_bpp = intel_dp_compute_bpp(intel_dp, pipe_config);
 
-	if (intel_dp_is_edp(intel_dp) && intel_dp->edp_dpcd[0] < DP_EDP_14) {
+	if (intel_dp_is_edp(intel_dp)) {
 		/*
 		 * Use the maximum clock and number of lanes the eDP panel
-		 * advertizes being capable of. The eDP 1.3 and earlier panels
-		 * are generally designed to support only a single clock and
-		 * lane configuration, and typically these values correspond to
-		 * the native resolution of the panel. With eDP 1.4 rate select
-		 * and DSC, this is decreasingly the case, and we need to be
-		 * able to select less than maximum link config.
+		 * advertizes being capable of. The panels are generally
+		 * designed to support only a single clock and lane
+		 * configuration, and typically these values correspond to the
+		 * native resolution of the panel.
 		 */
 		limits.min_lane_count = limits.max_lane_count;
 		limits.min_clock = limits.max_clock;
@@ -2053,22 +2018,11 @@ intel_dp_compute_link_config(struct intel_encoder *encoder,
 		      intel_dp->common_rates[limits.max_clock],
 		      limits.max_bpp, adjusted_mode->crtc_clock);
 
-	if (intel_dp_is_edp(intel_dp))
-		/*
-		 * Optimize for fast and narrow. eDP 1.3 section 3.3 and eDP 1.4
-		 * section A.1: "It is recommended that the minimum number of
-		 * lanes be used, using the minimum link rate allowed for that
-		 * lane configuration."
-		 *
-		 * Note that we use the max clock and lane count for eDP 1.3 and
-		 * earlier, and fast vs. wide is irrelevant.
-		 */
-		ret = intel_dp_compute_link_config_fast(intel_dp, pipe_config,
-							&limits);
-	else
-		/* Optimize for slow and wide. */
-		ret = intel_dp_compute_link_config_wide(intel_dp, pipe_config,
-							&limits);
+	/*
+	 * Optimize for slow and wide. This is the place to add alternative
+	 * optimization policy.
+	 */
+	ret = intel_dp_compute_link_config_wide(intel_dp, pipe_config, &limits);
 
 	/* enable compression if the mode doesn't fit available BW */
 	DRM_DEBUG_KMS("Force DSC en = %d\n", intel_dp->force_dsc_en);
@@ -2165,9 +2119,6 @@ intel_dp_compute_config(struct intel_encoder *encoder,
 	if (adjusted_mode->flags & DRM_MODE_FLAG_DBLCLK)
 		return -EINVAL;
 
-	pipe_config->fec_enable = !intel_dp_is_edp(intel_dp) &&
-				  intel_dp_supports_fec(intel_dp, pipe_config);
-
 	ret = intel_dp_compute_link_config(encoder, pipe_config, conn_state);
 	if (ret < 0)
 		return ret;
diff --git a/drivers/gpu/drm/i915/intel_drv.h b/drivers/gpu/drm/i915/intel_drv.h
index 15db41394b9e..d5660ac1b0d6 100644
--- a/drivers/gpu/drm/i915/intel_drv.h
+++ b/drivers/gpu/drm/i915/intel_drv.h
@@ -270,10 +270,12 @@ struct intel_encoder {
 	 * be set correctly before calling this function. */
 	void (*get_config)(struct intel_encoder *,
 			   struct intel_crtc_state *pipe_config);
-	/* Returns a mask of power domains that need to be referenced as part
-	 * of the hardware state readout code. */
-	u64 (*get_power_domains)(struct intel_encoder *encoder,
-				 struct intel_crtc_state *crtc_state);
+	/*
+	 * Acquires the power domains needed for an active encoder during
+	 * hardware state readout.
+	 */
+	void (*get_power_domains)(struct intel_encoder *encoder,
+				  struct intel_crtc_state *crtc_state);
 	/*
 	 * Called during system suspend after all pending requests for the
 	 * encoder are flushed (for example for DP AUX transactions) and
diff --git a/drivers/gpu/drm/i915/intel_fbdev.c b/drivers/gpu/drm/i915/intel_fbdev.c
index e8f694b57b8a..376ffe842e26 100644
--- a/drivers/gpu/drm/i915/intel_fbdev.c
+++ b/drivers/gpu/drm/i915/intel_fbdev.c
@@ -338,8 +338,8 @@ static bool intel_fb_initial_config(struct drm_fb_helper *fb_helper,
 				    bool *enabled, int width, int height)
 {
 	struct drm_i915_private *dev_priv = to_i915(fb_helper->dev);
+	unsigned long conn_configured, conn_seq, mask;
 	unsigned int count = min(fb_helper->connector_count, BITS_PER_LONG);
-	unsigned long conn_configured, conn_seq;
 	int i, j;
 	bool *save_enabled;
 	bool fallback = true, ret = true;
@@ -357,9 +357,10 @@ static bool intel_fb_initial_config(struct drm_fb_helper *fb_helper,
 		drm_modeset_backoff(&ctx);
 
 	memcpy(save_enabled, enabled, count);
-	conn_seq = GENMASK(count - 1, 0);
+	mask = GENMASK(count - 1, 0);
 	conn_configured = 0;
 retry:
+	conn_seq = conn_configured;
 	for (i = 0; i < count; i++) {
 		struct drm_fb_helper_connector *fb_conn;
 		struct drm_connector *connector;
@@ -372,8 +373,7 @@ retry:
 		if (conn_configured & BIT(i))
 			continue;
 
-		/* First pass, only consider tiled connectors */
-		if (conn_seq == GENMASK(count - 1, 0) && !connector->has_tile)
+		if (conn_seq == 0 && !connector->has_tile)
 			continue;
 
 		if (connector->status == connector_status_connected)
@@ -477,10 +477,8 @@ retry:
 		conn_configured |= BIT(i);
 	}
 
-	if (conn_configured != conn_seq) { /* repeat until no more are found */
-		conn_seq = conn_configured;
+	if ((conn_configured & mask) != mask && conn_configured != conn_seq)
 		goto retry;
-	}
 
 	/*
 	 * If the BIOS didn't enable everything it could, fall back to have the
diff --git a/drivers/gpu/drm/i915/intel_hdmi.c b/drivers/gpu/drm/i915/intel_hdmi.c
index f125a62eba8c..a46bffe2b288 100644
--- a/drivers/gpu/drm/i915/intel_hdmi.c
+++ b/drivers/gpu/drm/i915/intel_hdmi.c
@@ -182,7 +182,6 @@ static void g4x_write_infoframe(struct intel_encoder *encoder,
 
 	I915_WRITE(VIDEO_DIP_CTL, val);
 
-	mmiowb();
 	for (i = 0; i < len; i += 4) {
 		I915_WRITE(VIDEO_DIP_DATA, *data);
 		data++;
@@ -190,7 +189,6 @@ static void g4x_write_infoframe(struct intel_encoder *encoder,
 	/* Write every possible data byte to force correct ECC calculation. */
 	for (; i < VIDEO_DIP_DATA_SIZE; i += 4)
 		I915_WRITE(VIDEO_DIP_DATA, 0);
-	mmiowb();
 
 	val |= g4x_infoframe_enable(type);
 	val &= ~VIDEO_DIP_FREQ_MASK;
@@ -237,7 +235,6 @@ static void ibx_write_infoframe(struct intel_encoder *encoder,
 
 	I915_WRITE(reg, val);
 
-	mmiowb();
 	for (i = 0; i < len; i += 4) {
 		I915_WRITE(TVIDEO_DIP_DATA(intel_crtc->pipe), *data);
 		data++;
@@ -245,7 +242,6 @@ static void ibx_write_infoframe(struct intel_encoder *encoder,
 	/* Write every possible data byte to force correct ECC calculation. */
 	for (; i < VIDEO_DIP_DATA_SIZE; i += 4)
 		I915_WRITE(TVIDEO_DIP_DATA(intel_crtc->pipe), 0);
-	mmiowb();
 
 	val |= g4x_infoframe_enable(type);
 	val &= ~VIDEO_DIP_FREQ_MASK;
@@ -298,7 +294,6 @@ static void cpt_write_infoframe(struct intel_encoder *encoder,
 
 	I915_WRITE(reg, val);
 
-	mmiowb();
 	for (i = 0; i < len; i += 4) {
 		I915_WRITE(TVIDEO_DIP_DATA(intel_crtc->pipe), *data);
 		data++;
@@ -306,7 +301,6 @@ static void cpt_write_infoframe(struct intel_encoder *encoder,
 	/* Write every possible data byte to force correct ECC calculation. */
 	for (; i < VIDEO_DIP_DATA_SIZE; i += 4)
 		I915_WRITE(TVIDEO_DIP_DATA(intel_crtc->pipe), 0);
-	mmiowb();
 
 	val |= g4x_infoframe_enable(type);
 	val &= ~VIDEO_DIP_FREQ_MASK;
@@ -352,7 +346,6 @@ static void vlv_write_infoframe(struct intel_encoder *encoder,
 
 	I915_WRITE(reg, val);
 
-	mmiowb();
 	for (i = 0; i < len; i += 4) {
 		I915_WRITE(VLV_TVIDEO_DIP_DATA(intel_crtc->pipe), *data);
 		data++;
@@ -360,7 +353,6 @@ static void vlv_write_infoframe(struct intel_encoder *encoder,
 	/* Write every possible data byte to force correct ECC calculation. */
 	for (; i < VIDEO_DIP_DATA_SIZE; i += 4)
 		I915_WRITE(VLV_TVIDEO_DIP_DATA(intel_crtc->pipe), 0);
-	mmiowb();
 
 	val |= g4x_infoframe_enable(type);
 	val &= ~VIDEO_DIP_FREQ_MASK;
@@ -406,7 +398,6 @@ static void hsw_write_infoframe(struct intel_encoder *encoder,
 	val &= ~hsw_infoframe_enable(type);
 	I915_WRITE(ctl_reg, val);
 
-	mmiowb();
 	for (i = 0; i < len; i += 4) {
 		I915_WRITE(hsw_dip_data_reg(dev_priv, cpu_transcoder,
 					    type, i >> 2), *data);
@@ -416,7 +407,6 @@ static void hsw_write_infoframe(struct intel_encoder *encoder,
 	for (; i < data_size; i += 4)
 		I915_WRITE(hsw_dip_data_reg(dev_priv, cpu_transcoder,
 					    type, i >> 2), 0);
-	mmiowb();
 
 	val |= hsw_infoframe_enable(type);
 	I915_WRITE(ctl_reg, val);
diff --git a/drivers/gpu/drm/i915/intel_runtime_pm.c b/drivers/gpu/drm/i915/intel_runtime_pm.c
index a017a4232c0f..20c4434474e3 100644
--- a/drivers/gpu/drm/i915/intel_runtime_pm.c
+++ b/drivers/gpu/drm/i915/intel_runtime_pm.c
@@ -60,31 +60,20 @@
 static noinline depot_stack_handle_t __save_depot_stack(void)
 {
 	unsigned long entries[STACKDEPTH];
-	struct stack_trace trace = {
-		.entries = entries,
-		.max_entries = ARRAY_SIZE(entries),
-		.skip = 1,
-	};
+	unsigned int n;
 
-	save_stack_trace(&trace);
-	if (trace.nr_entries &&
-	    trace.entries[trace.nr_entries - 1] == ULONG_MAX)
-		trace.nr_entries--;
-
-	return depot_save_stack(&trace, GFP_NOWAIT | __GFP_NOWARN);
+	n = stack_trace_save(entries, ARRAY_SIZE(entries), 1);
+	return stack_depot_save(entries, n, GFP_NOWAIT | __GFP_NOWARN);
 }
 
 static void __print_depot_stack(depot_stack_handle_t stack,
 				char *buf, int sz, int indent)
 {
-	unsigned long entries[STACKDEPTH];
-	struct stack_trace trace = {
-		.entries = entries,
-		.max_entries = ARRAY_SIZE(entries),
-	};
+	unsigned long *entries;
+	unsigned int nr_entries;
 
-	depot_fetch_stack(stack, &trace);
-	snprint_stack_trace(buf, sz, &trace, indent);
+	nr_entries = stack_depot_fetch(stack, &entries);
+	stack_trace_snprint(buf, sz, entries, nr_entries, indent);
 }
 
 static void init_intel_runtime_pm_wakeref(struct drm_i915_private *i915)
diff --git a/drivers/gpu/drm/i915/selftests/i915_gem_evict.c b/drivers/gpu/drm/i915/selftests/i915_gem_evict.c
index 32dce7176f63..b9b0ea4e2404 100644
--- a/drivers/gpu/drm/i915/selftests/i915_gem_evict.c
+++ b/drivers/gpu/drm/i915/selftests/i915_gem_evict.c
@@ -455,7 +455,7 @@ static int igt_evict_contexts(void *arg)
 			struct i915_gem_context *ctx;
 
 			ctx = live_context(i915, file);
-			if (!ctx)
+			if (IS_ERR(ctx))
 				break;
 
 			/* We will need some GGTT space for the rq's context */
diff --git a/drivers/gpu/drm/i915/vlv_dsi.c b/drivers/gpu/drm/i915/vlv_dsi.c
index 6403728fe778..31c93c3ccd00 100644
--- a/drivers/gpu/drm/i915/vlv_dsi.c
+++ b/drivers/gpu/drm/i915/vlv_dsi.c
@@ -256,6 +256,28 @@ static void band_gap_reset(struct drm_i915_private *dev_priv)
 	mutex_unlock(&dev_priv->sb_lock);
 }
 
+static int bdw_get_pipemisc_bpp(struct intel_crtc *crtc)
+{
+	struct drm_i915_private *dev_priv = to_i915(crtc->base.dev);
+	u32 tmp;
+
+	tmp = I915_READ(PIPEMISC(crtc->pipe));
+
+	switch (tmp & PIPEMISC_DITHER_BPC_MASK) {
+	case PIPEMISC_DITHER_6_BPC:
+		return 18;
+	case PIPEMISC_DITHER_8_BPC:
+		return 24;
+	case PIPEMISC_DITHER_10_BPC:
+		return 30;
+	case PIPEMISC_DITHER_12_BPC:
+		return 36;
+	default:
+		MISSING_CASE(tmp);
+		return 0;
+	}
+}
+
 static int intel_dsi_compute_config(struct intel_encoder *encoder,
 				    struct intel_crtc_state *pipe_config,
 				    struct drm_connector_state *conn_state)
@@ -1071,6 +1093,8 @@ static void bxt_dsi_get_pipe_config(struct intel_encoder *encoder,
 	bpp = mipi_dsi_pixel_format_to_bpp(
 			pixel_format_from_register_bits(fmt));
 
+	pipe_config->pipe_bpp = bdw_get_pipemisc_bpp(crtc);
+
 	/* Enable Frame time stamo based scanline reporting */
 	adjusted_mode->private_flags |=
 			I915_MODE_FLAG_GET_SCANLINE_FROM_TIMESTAMP;
diff --git a/drivers/gpu/drm/imx/ipuv3-crtc.c b/drivers/gpu/drm/imx/ipuv3-crtc.c
index ec3602ebbc1c..54011df8c2e8 100644
--- a/drivers/gpu/drm/imx/ipuv3-crtc.c
+++ b/drivers/gpu/drm/imx/ipuv3-crtc.c
@@ -71,7 +71,7 @@ static void ipu_crtc_disable_planes(struct ipu_crtc *ipu_crtc,
 	if (disable_partial)
 		ipu_plane_disable(ipu_crtc->plane[1], true);
 	if (disable_full)
-		ipu_plane_disable(ipu_crtc->plane[0], false);
+		ipu_plane_disable(ipu_crtc->plane[0], true);
 }
 
 static void ipu_crtc_atomic_disable(struct drm_crtc *crtc,
diff --git a/drivers/gpu/drm/mediatek/mtk_dpi.c b/drivers/gpu/drm/mediatek/mtk_dpi.c
index 22e68a100e7b..5d333138f913 100644
--- a/drivers/gpu/drm/mediatek/mtk_dpi.c
+++ b/drivers/gpu/drm/mediatek/mtk_dpi.c
@@ -662,13 +662,11 @@ static unsigned int mt8173_calculate_factor(int clock)
 static unsigned int mt2701_calculate_factor(int clock)
 {
 	if (clock <= 64000)
-		return 16;
-	else if (clock <= 128000)
-		return 8;
-	else if (clock <= 256000)
 		return 4;
-	else
+	else if (clock <= 128000)
 		return 2;
+	else
+		return 1;
 }
 
 static const struct mtk_dpi_conf mt8173_conf = {
diff --git a/drivers/gpu/drm/mediatek/mtk_drm_drv.c b/drivers/gpu/drm/mediatek/mtk_drm_drv.c
index cf59ea9bccfd..57ce4708ef1b 100644
--- a/drivers/gpu/drm/mediatek/mtk_drm_drv.c
+++ b/drivers/gpu/drm/mediatek/mtk_drm_drv.c
@@ -15,6 +15,7 @@
 #include <drm/drmP.h>
 #include <drm/drm_atomic.h>
 #include <drm/drm_atomic_helper.h>
+#include <drm/drm_fb_helper.h>
 #include <drm/drm_gem.h>
 #include <drm/drm_gem_cma_helper.h>
 #include <drm/drm_of.h>
@@ -341,6 +342,8 @@ static struct drm_driver mtk_drm_driver = {
 	.gem_prime_get_sg_table = mtk_gem_prime_get_sg_table,
 	.gem_prime_import_sg_table = mtk_gem_prime_import_sg_table,
 	.gem_prime_mmap = mtk_drm_gem_mmap_buf,
+	.gem_prime_vmap = mtk_drm_gem_prime_vmap,
+	.gem_prime_vunmap = mtk_drm_gem_prime_vunmap,
 	.fops = &mtk_drm_fops,
 
 	.name = DRIVER_NAME,
@@ -376,6 +379,10 @@ static int mtk_drm_bind(struct device *dev)
 	if (ret < 0)
 		goto err_deinit;
 
+	ret = drm_fbdev_generic_setup(drm, 32);
+	if (ret)
+		DRM_ERROR("Failed to initialize fbdev: %d\n", ret);
+
 	return 0;
 
 err_deinit:
diff --git a/drivers/gpu/drm/mediatek/mtk_drm_gem.c b/drivers/gpu/drm/mediatek/mtk_drm_gem.c
index 259b7b0de1d2..38483e9ee071 100644
--- a/drivers/gpu/drm/mediatek/mtk_drm_gem.c
+++ b/drivers/gpu/drm/mediatek/mtk_drm_gem.c
@@ -241,3 +241,49 @@ err_gem_free:
 	kfree(mtk_gem);
 	return ERR_PTR(ret);
 }
+
+void *mtk_drm_gem_prime_vmap(struct drm_gem_object *obj)
+{
+	struct mtk_drm_gem_obj *mtk_gem = to_mtk_gem_obj(obj);
+	struct sg_table *sgt;
+	struct sg_page_iter iter;
+	unsigned int npages;
+	unsigned int i = 0;
+
+	if (mtk_gem->kvaddr)
+		return mtk_gem->kvaddr;
+
+	sgt = mtk_gem_prime_get_sg_table(obj);
+	if (IS_ERR(sgt))
+		return NULL;
+
+	npages = obj->size >> PAGE_SHIFT;
+	mtk_gem->pages = kcalloc(npages, sizeof(*mtk_gem->pages), GFP_KERNEL);
+	if (!mtk_gem->pages)
+		goto out;
+
+	for_each_sg_page(sgt->sgl, &iter, sgt->orig_nents, 0) {
+		mtk_gem->pages[i++] = sg_page_iter_page(&iter);
+		if (i > npages)
+			break;
+	}
+	mtk_gem->kvaddr = vmap(mtk_gem->pages, npages, VM_MAP,
+			       pgprot_writecombine(PAGE_KERNEL));
+
+out:
+	kfree((void *)sgt);
+
+	return mtk_gem->kvaddr;
+}
+
+void mtk_drm_gem_prime_vunmap(struct drm_gem_object *obj, void *vaddr)
+{
+	struct mtk_drm_gem_obj *mtk_gem = to_mtk_gem_obj(obj);
+
+	if (!mtk_gem->pages)
+		return;
+
+	vunmap(vaddr);
+	mtk_gem->kvaddr = 0;
+	kfree((void *)mtk_gem->pages);
+}
diff --git a/drivers/gpu/drm/mediatek/mtk_drm_gem.h b/drivers/gpu/drm/mediatek/mtk_drm_gem.h
index 534639b43a1c..c047a7ef294f 100644
--- a/drivers/gpu/drm/mediatek/mtk_drm_gem.h
+++ b/drivers/gpu/drm/mediatek/mtk_drm_gem.h
@@ -37,6 +37,7 @@ struct mtk_drm_gem_obj {
 	dma_addr_t		dma_addr;
 	unsigned long		dma_attrs;
 	struct sg_table		*sg;
+	struct page		**pages;
 };
 
 #define to_mtk_gem_obj(x)	container_of(x, struct mtk_drm_gem_obj, base)
@@ -52,5 +53,7 @@ int mtk_drm_gem_mmap_buf(struct drm_gem_object *obj,
 struct sg_table *mtk_gem_prime_get_sg_table(struct drm_gem_object *obj);
 struct drm_gem_object *mtk_gem_prime_import_sg_table(struct drm_device *dev,
 			struct dma_buf_attachment *attach, struct sg_table *sg);
+void *mtk_drm_gem_prime_vmap(struct drm_gem_object *obj);
+void mtk_drm_gem_prime_vunmap(struct drm_gem_object *obj, void *vaddr);
 
 #endif
diff --git a/drivers/gpu/drm/mediatek/mtk_hdmi.c b/drivers/gpu/drm/mediatek/mtk_hdmi.c
index 915cc84621ae..e04e6c293d39 100644
--- a/drivers/gpu/drm/mediatek/mtk_hdmi.c
+++ b/drivers/gpu/drm/mediatek/mtk_hdmi.c
@@ -1480,7 +1480,6 @@ static int mtk_hdmi_dt_parse_pdata(struct mtk_hdmi *hdmi,
 	if (IS_ERR(regmap))
 		ret = PTR_ERR(regmap);
 	if (ret) {
-		ret = PTR_ERR(regmap);
 		dev_err(dev,
 			"Failed to get system configuration registers: %d\n",
 			ret);
@@ -1516,6 +1515,7 @@ static int mtk_hdmi_dt_parse_pdata(struct mtk_hdmi *hdmi,
 	of_node_put(remote);
 
 	hdmi->ddc_adpt = of_find_i2c_adapter_by_node(i2c_np);
+	of_node_put(i2c_np);
 	if (!hdmi->ddc_adpt) {
 		dev_err(dev, "Failed to get ddc i2c adapter by node\n");
 		return -EINVAL;
diff --git a/drivers/gpu/drm/mediatek/mtk_hdmi_phy.c b/drivers/gpu/drm/mediatek/mtk_hdmi_phy.c
index 4ef9c57ffd44..5223498502c4 100644
--- a/drivers/gpu/drm/mediatek/mtk_hdmi_phy.c
+++ b/drivers/gpu/drm/mediatek/mtk_hdmi_phy.c
@@ -15,28 +15,6 @@ static const struct phy_ops mtk_hdmi_phy_dev_ops = {
 	.owner = THIS_MODULE,
 };
 
-long mtk_hdmi_pll_round_rate(struct clk_hw *hw, unsigned long rate,
-			     unsigned long *parent_rate)
-{
-	struct mtk_hdmi_phy *hdmi_phy = to_mtk_hdmi_phy(hw);
-
-	hdmi_phy->pll_rate = rate;
-	if (rate <= 74250000)
-		*parent_rate = rate;
-	else
-		*parent_rate = rate / 2;
-
-	return rate;
-}
-
-unsigned long mtk_hdmi_pll_recalc_rate(struct clk_hw *hw,
-				       unsigned long parent_rate)
-{
-	struct mtk_hdmi_phy *hdmi_phy = to_mtk_hdmi_phy(hw);
-
-	return hdmi_phy->pll_rate;
-}
-
 void mtk_hdmi_phy_clear_bits(struct mtk_hdmi_phy *hdmi_phy, u32 offset,
 			     u32 bits)
 {
@@ -110,13 +88,11 @@ mtk_hdmi_phy_dev_get_ops(const struct mtk_hdmi_phy *hdmi_phy)
 		return NULL;
 }
 
-static void mtk_hdmi_phy_clk_get_ops(struct mtk_hdmi_phy *hdmi_phy,
-				     const struct clk_ops **ops)
+static void mtk_hdmi_phy_clk_get_data(struct mtk_hdmi_phy *hdmi_phy,
+				      struct clk_init_data *clk_init)
 {
-	if (hdmi_phy && hdmi_phy->conf && hdmi_phy->conf->hdmi_phy_clk_ops)
-		*ops = hdmi_phy->conf->hdmi_phy_clk_ops;
-	else
-		dev_err(hdmi_phy->dev, "Failed to get clk ops of phy\n");
+	clk_init->flags = hdmi_phy->conf->flags;
+	clk_init->ops = hdmi_phy->conf->hdmi_phy_clk_ops;
 }
 
 static int mtk_hdmi_phy_probe(struct platform_device *pdev)
@@ -129,7 +105,6 @@ static int mtk_hdmi_phy_probe(struct platform_device *pdev)
 	struct clk_init_data clk_init = {
 		.num_parents = 1,
 		.parent_names = (const char * const *)&ref_clk_name,
-		.flags = CLK_SET_RATE_PARENT | CLK_SET_RATE_GATE,
 	};
 
 	struct phy *phy;
@@ -167,7 +142,7 @@ static int mtk_hdmi_phy_probe(struct platform_device *pdev)
 	hdmi_phy->dev = dev;
 	hdmi_phy->conf =
 		(struct mtk_hdmi_phy_conf *)of_device_get_match_data(dev);
-	mtk_hdmi_phy_clk_get_ops(hdmi_phy, &clk_init.ops);
+	mtk_hdmi_phy_clk_get_data(hdmi_phy, &clk_init);
 	hdmi_phy->pll_hw.init = &clk_init;
 	hdmi_phy->pll = devm_clk_register(dev, &hdmi_phy->pll_hw);
 	if (IS_ERR(hdmi_phy->pll)) {
diff --git a/drivers/gpu/drm/mediatek/mtk_hdmi_phy.h b/drivers/gpu/drm/mediatek/mtk_hdmi_phy.h
index f39b1fc66612..2d8b3182470d 100644
--- a/drivers/gpu/drm/mediatek/mtk_hdmi_phy.h
+++ b/drivers/gpu/drm/mediatek/mtk_hdmi_phy.h
@@ -21,6 +21,7 @@ struct mtk_hdmi_phy;
 
 struct mtk_hdmi_phy_conf {
 	bool tz_disabled;
+	unsigned long flags;
 	const struct clk_ops *hdmi_phy_clk_ops;
 	void (*hdmi_phy_enable_tmds)(struct mtk_hdmi_phy *hdmi_phy);
 	void (*hdmi_phy_disable_tmds)(struct mtk_hdmi_phy *hdmi_phy);
@@ -48,10 +49,6 @@ void mtk_hdmi_phy_set_bits(struct mtk_hdmi_phy *hdmi_phy, u32 offset,
 void mtk_hdmi_phy_mask(struct mtk_hdmi_phy *hdmi_phy, u32 offset,
 		       u32 val, u32 mask);
 struct mtk_hdmi_phy *to_mtk_hdmi_phy(struct clk_hw *hw);
-long mtk_hdmi_pll_round_rate(struct clk_hw *hw, unsigned long rate,
-			     unsigned long *parent_rate);
-unsigned long mtk_hdmi_pll_recalc_rate(struct clk_hw *hw,
-				       unsigned long parent_rate);
 
 extern struct platform_driver mtk_hdmi_phy_driver;
 extern struct mtk_hdmi_phy_conf mtk_hdmi_phy_8173_conf;
diff --git a/drivers/gpu/drm/mediatek/mtk_mt2701_hdmi_phy.c b/drivers/gpu/drm/mediatek/mtk_mt2701_hdmi_phy.c
index fcc42dc6ea7f..d3cc4022e988 100644
--- a/drivers/gpu/drm/mediatek/mtk_mt2701_hdmi_phy.c
+++ b/drivers/gpu/drm/mediatek/mtk_mt2701_hdmi_phy.c
@@ -79,7 +79,6 @@ static int mtk_hdmi_pll_prepare(struct clk_hw *hw)
 	mtk_hdmi_phy_set_bits(hdmi_phy, HDMI_CON0, RG_HDMITX_EN_SLDO_MASK);
 	usleep_range(80, 100);
 	mtk_hdmi_phy_set_bits(hdmi_phy, HDMI_CON2, RG_HDMITX_MBIAS_LPF_EN);
-	mtk_hdmi_phy_set_bits(hdmi_phy, HDMI_CON2, RG_HDMITX_EN_TX_POSDIV);
 	mtk_hdmi_phy_set_bits(hdmi_phy, HDMI_CON0, RG_HDMITX_EN_SER_MASK);
 	mtk_hdmi_phy_set_bits(hdmi_phy, HDMI_CON0, RG_HDMITX_EN_PRED_MASK);
 	mtk_hdmi_phy_set_bits(hdmi_phy, HDMI_CON0, RG_HDMITX_EN_DRV_MASK);
@@ -94,7 +93,6 @@ static void mtk_hdmi_pll_unprepare(struct clk_hw *hw)
 	mtk_hdmi_phy_clear_bits(hdmi_phy, HDMI_CON0, RG_HDMITX_EN_DRV_MASK);
 	mtk_hdmi_phy_clear_bits(hdmi_phy, HDMI_CON0, RG_HDMITX_EN_PRED_MASK);
 	mtk_hdmi_phy_clear_bits(hdmi_phy, HDMI_CON0, RG_HDMITX_EN_SER_MASK);
-	mtk_hdmi_phy_clear_bits(hdmi_phy, HDMI_CON2, RG_HDMITX_EN_TX_POSDIV);
 	mtk_hdmi_phy_clear_bits(hdmi_phy, HDMI_CON2, RG_HDMITX_MBIAS_LPF_EN);
 	usleep_range(80, 100);
 	mtk_hdmi_phy_clear_bits(hdmi_phy, HDMI_CON0, RG_HDMITX_EN_SLDO_MASK);
@@ -108,6 +106,12 @@ static void mtk_hdmi_pll_unprepare(struct clk_hw *hw)
 	usleep_range(80, 100);
 }
 
+static long mtk_hdmi_pll_round_rate(struct clk_hw *hw, unsigned long rate,
+				    unsigned long *parent_rate)
+{
+	return rate;
+}
+
 static int mtk_hdmi_pll_set_rate(struct clk_hw *hw, unsigned long rate,
 				 unsigned long parent_rate)
 {
@@ -116,13 +120,14 @@ static int mtk_hdmi_pll_set_rate(struct clk_hw *hw, unsigned long rate,
 
 	if (rate <= 64000000)
 		pos_div = 3;
-	else if (rate <= 12800000)
-		pos_div = 1;
+	else if (rate <= 128000000)
+		pos_div = 2;
 	else
 		pos_div = 1;
 
 	mtk_hdmi_phy_set_bits(hdmi_phy, HDMI_CON6, RG_HTPLL_PREDIV_MASK);
 	mtk_hdmi_phy_set_bits(hdmi_phy, HDMI_CON6, RG_HTPLL_POSDIV_MASK);
+	mtk_hdmi_phy_set_bits(hdmi_phy, HDMI_CON2, RG_HDMITX_EN_TX_POSDIV);
 	mtk_hdmi_phy_mask(hdmi_phy, HDMI_CON6, (0x1 << RG_HTPLL_IC),
 			  RG_HTPLL_IC_MASK);
 	mtk_hdmi_phy_mask(hdmi_phy, HDMI_CON6, (0x1 << RG_HTPLL_IR),
@@ -154,6 +159,39 @@ static int mtk_hdmi_pll_set_rate(struct clk_hw *hw, unsigned long rate,
 	return 0;
 }
 
+static unsigned long mtk_hdmi_pll_recalc_rate(struct clk_hw *hw,
+					      unsigned long parent_rate)
+{
+	struct mtk_hdmi_phy *hdmi_phy = to_mtk_hdmi_phy(hw);
+	unsigned long out_rate, val;
+
+	val = (readl(hdmi_phy->regs + HDMI_CON6)
+	       & RG_HTPLL_PREDIV_MASK) >> RG_HTPLL_PREDIV;
+	switch (val) {
+	case 0x00:
+		out_rate = parent_rate;
+		break;
+	case 0x01:
+		out_rate = parent_rate / 2;
+		break;
+	default:
+		out_rate = parent_rate / 4;
+		break;
+	}
+
+	val = (readl(hdmi_phy->regs + HDMI_CON6)
+	       & RG_HTPLL_FBKDIV_MASK) >> RG_HTPLL_FBKDIV;
+	out_rate *= (val + 1) * 2;
+	val = (readl(hdmi_phy->regs + HDMI_CON2)
+	       & RG_HDMITX_TX_POSDIV_MASK);
+	out_rate >>= (val >> RG_HDMITX_TX_POSDIV);
+
+	if (readl(hdmi_phy->regs + HDMI_CON2) & RG_HDMITX_EN_TX_POSDIV)
+		out_rate /= 5;
+
+	return out_rate;
+}
+
 static const struct clk_ops mtk_hdmi_phy_pll_ops = {
 	.prepare = mtk_hdmi_pll_prepare,
 	.unprepare = mtk_hdmi_pll_unprepare,
@@ -174,7 +212,6 @@ static void mtk_hdmi_phy_enable_tmds(struct mtk_hdmi_phy *hdmi_phy)
 	mtk_hdmi_phy_set_bits(hdmi_phy, HDMI_CON0, RG_HDMITX_EN_SLDO_MASK);
 	usleep_range(80, 100);
 	mtk_hdmi_phy_set_bits(hdmi_phy, HDMI_CON2, RG_HDMITX_MBIAS_LPF_EN);
-	mtk_hdmi_phy_set_bits(hdmi_phy, HDMI_CON2, RG_HDMITX_EN_TX_POSDIV);
 	mtk_hdmi_phy_set_bits(hdmi_phy, HDMI_CON0, RG_HDMITX_EN_SER_MASK);
 	mtk_hdmi_phy_set_bits(hdmi_phy, HDMI_CON0, RG_HDMITX_EN_PRED_MASK);
 	mtk_hdmi_phy_set_bits(hdmi_phy, HDMI_CON0, RG_HDMITX_EN_DRV_MASK);
@@ -186,7 +223,6 @@ static void mtk_hdmi_phy_disable_tmds(struct mtk_hdmi_phy *hdmi_phy)
 	mtk_hdmi_phy_clear_bits(hdmi_phy, HDMI_CON0, RG_HDMITX_EN_DRV_MASK);
 	mtk_hdmi_phy_clear_bits(hdmi_phy, HDMI_CON0, RG_HDMITX_EN_PRED_MASK);
 	mtk_hdmi_phy_clear_bits(hdmi_phy, HDMI_CON0, RG_HDMITX_EN_SER_MASK);
-	mtk_hdmi_phy_clear_bits(hdmi_phy, HDMI_CON2, RG_HDMITX_EN_TX_POSDIV);
 	mtk_hdmi_phy_clear_bits(hdmi_phy, HDMI_CON2, RG_HDMITX_MBIAS_LPF_EN);
 	usleep_range(80, 100);
 	mtk_hdmi_phy_clear_bits(hdmi_phy, HDMI_CON0, RG_HDMITX_EN_SLDO_MASK);
@@ -202,6 +238,7 @@ static void mtk_hdmi_phy_disable_tmds(struct mtk_hdmi_phy *hdmi_phy)
 
 struct mtk_hdmi_phy_conf mtk_hdmi_phy_2701_conf = {
 	.tz_disabled = true,
+	.flags = CLK_SET_RATE_GATE,
 	.hdmi_phy_clk_ops = &mtk_hdmi_phy_pll_ops,
 	.hdmi_phy_enable_tmds = mtk_hdmi_phy_enable_tmds,
 	.hdmi_phy_disable_tmds = mtk_hdmi_phy_disable_tmds,
diff --git a/drivers/gpu/drm/mediatek/mtk_mt8173_hdmi_phy.c b/drivers/gpu/drm/mediatek/mtk_mt8173_hdmi_phy.c
index ed5916b27658..47f8a2951682 100644
--- a/drivers/gpu/drm/mediatek/mtk_mt8173_hdmi_phy.c
+++ b/drivers/gpu/drm/mediatek/mtk_mt8173_hdmi_phy.c
@@ -199,6 +199,20 @@ static void mtk_hdmi_pll_unprepare(struct clk_hw *hw)
 	usleep_range(100, 150);
 }
 
+static long mtk_hdmi_pll_round_rate(struct clk_hw *hw, unsigned long rate,
+				    unsigned long *parent_rate)
+{
+	struct mtk_hdmi_phy *hdmi_phy = to_mtk_hdmi_phy(hw);
+
+	hdmi_phy->pll_rate = rate;
+	if (rate <= 74250000)
+		*parent_rate = rate;
+	else
+		*parent_rate = rate / 2;
+
+	return rate;
+}
+
 static int mtk_hdmi_pll_set_rate(struct clk_hw *hw, unsigned long rate,
 				 unsigned long parent_rate)
 {
@@ -285,6 +299,14 @@ static int mtk_hdmi_pll_set_rate(struct clk_hw *hw, unsigned long rate,
 	return 0;
 }
 
+static unsigned long mtk_hdmi_pll_recalc_rate(struct clk_hw *hw,
+					      unsigned long parent_rate)
+{
+	struct mtk_hdmi_phy *hdmi_phy = to_mtk_hdmi_phy(hw);
+
+	return hdmi_phy->pll_rate;
+}
+
 static const struct clk_ops mtk_hdmi_phy_pll_ops = {
 	.prepare = mtk_hdmi_pll_prepare,
 	.unprepare = mtk_hdmi_pll_unprepare,
@@ -309,6 +331,7 @@ static void mtk_hdmi_phy_disable_tmds(struct mtk_hdmi_phy *hdmi_phy)
 }
 
 struct mtk_hdmi_phy_conf mtk_hdmi_phy_8173_conf = {
+	.flags = CLK_SET_RATE_PARENT | CLK_SET_RATE_GATE,
 	.hdmi_phy_clk_ops = &mtk_hdmi_phy_pll_ops,
 	.hdmi_phy_enable_tmds = mtk_hdmi_phy_enable_tmds,
 	.hdmi_phy_disable_tmds = mtk_hdmi_phy_disable_tmds,
diff --git a/drivers/gpu/drm/meson/meson_drv.c b/drivers/gpu/drm/meson/meson_drv.c
index 2281ed3eb774..8a4ebcb6405c 100644
--- a/drivers/gpu/drm/meson/meson_drv.c
+++ b/drivers/gpu/drm/meson/meson_drv.c
@@ -337,12 +337,14 @@ static int meson_drv_bind_master(struct device *dev, bool has_components)
 
 	ret = drm_dev_register(drm, 0);
 	if (ret)
-		goto free_drm;
+		goto uninstall_irq;
 
 	drm_fbdev_generic_setup(drm, 32);
 
 	return 0;
 
+uninstall_irq:
+	drm_irq_uninstall(drm);
 free_drm:
 	drm_dev_put(drm);
 
@@ -356,8 +358,8 @@ static int meson_drv_bind(struct device *dev)
 
 static void meson_drv_unbind(struct device *dev)
 {
-	struct drm_device *drm = dev_get_drvdata(dev);
-	struct meson_drm *priv = drm->dev_private;
+	struct meson_drm *priv = dev_get_drvdata(dev);
+	struct drm_device *drm = priv->drm;
 
 	if (priv->canvas) {
 		meson_canvas_free(priv->canvas, priv->canvas_id_osd1);
@@ -367,6 +369,7 @@ static void meson_drv_unbind(struct device *dev)
 	}
 
 	drm_dev_unregister(drm);
+	drm_irq_uninstall(drm);
 	drm_kms_helper_poll_fini(drm);
 	drm_mode_config_cleanup(drm);
 	drm_dev_put(drm);
diff --git a/drivers/gpu/drm/meson/meson_dw_hdmi.c b/drivers/gpu/drm/meson/meson_dw_hdmi.c
index e28814f4ea6c..563953ec6ad0 100644
--- a/drivers/gpu/drm/meson/meson_dw_hdmi.c
+++ b/drivers/gpu/drm/meson/meson_dw_hdmi.c
@@ -569,7 +569,8 @@ dw_hdmi_mode_valid(struct drm_connector *connector,
 	DRM_DEBUG_DRIVER("Modeline " DRM_MODE_FMT "\n", DRM_MODE_ARG(mode));
 
 	/* If sink max TMDS clock, we reject the mode */
-	if (mode->clock > connector->display_info.max_tmds_clock)
+	if (connector->display_info.max_tmds_clock &&
+	    mode->clock > connector->display_info.max_tmds_clock)
 		return MODE_BAD;
 
 	/* Check against non-VIC supported modes */
diff --git a/drivers/gpu/drm/omapdrm/dss/hdmi4_cec.c b/drivers/gpu/drm/omapdrm/dss/hdmi4_cec.c
index 340383150fb9..ebf9c96d43ee 100644
--- a/drivers/gpu/drm/omapdrm/dss/hdmi4_cec.c
+++ b/drivers/gpu/drm/omapdrm/dss/hdmi4_cec.c
@@ -175,6 +175,7 @@ static int hdmi_cec_adap_enable(struct cec_adapter *adap, bool enable)
 		REG_FLD_MOD(core->base, HDMI_CORE_SYS_INTR_UNMASK4, 0, 3, 3);
 		hdmi_wp_clear_irqenable(core->wp, HDMI_IRQ_CORE);
 		hdmi_wp_set_irqstatus(core->wp, HDMI_IRQ_CORE);
+		REG_FLD_MOD(core->wp->base, HDMI_WP_CLK, 0, 5, 0);
 		hdmi4_core_disable(core);
 		return 0;
 	}
@@ -182,16 +183,24 @@ static int hdmi_cec_adap_enable(struct cec_adapter *adap, bool enable)
 	if (err)
 		return err;
 
+	/*
+	 * Initialize CEC clock divider: CEC needs 2MHz clock hence
+	 * set the divider to 24 to get 48/24=2MHz clock
+	 */
+	REG_FLD_MOD(core->wp->base, HDMI_WP_CLK, 0x18, 5, 0);
+
 	/* Clear TX FIFO */
 	if (!hdmi_cec_clear_tx_fifo(adap)) {
 		pr_err("cec-%s: could not clear TX FIFO\n", adap->name);
-		return -EIO;
+		err = -EIO;
+		goto err_disable_clk;
 	}
 
 	/* Clear RX FIFO */
 	if (!hdmi_cec_clear_rx_fifo(adap)) {
 		pr_err("cec-%s: could not clear RX FIFO\n", adap->name);
-		return -EIO;
+		err = -EIO;
+		goto err_disable_clk;
 	}
 
 	/* Clear CEC interrupts */
@@ -236,6 +245,12 @@ static int hdmi_cec_adap_enable(struct cec_adapter *adap, bool enable)
 		hdmi_write_reg(core->base, HDMI_CEC_INT_STATUS_1, temp);
 	}
 	return 0;
+
+err_disable_clk:
+	REG_FLD_MOD(core->wp->base, HDMI_WP_CLK, 0, 5, 0);
+	hdmi4_core_disable(core);
+
+	return err;
 }
 
 static int hdmi_cec_adap_log_addr(struct cec_adapter *adap, u8 log_addr)
@@ -333,11 +348,8 @@ int hdmi4_cec_init(struct platform_device *pdev, struct hdmi_core_data *core,
 		return ret;
 	core->wp = wp;
 
-	/*
-	 * Initialize CEC clock divider: CEC needs 2MHz clock hence
-	 * set the devider to 24 to get 48/24=2MHz clock
-	 */
-	REG_FLD_MOD(core->wp->base, HDMI_WP_CLK, 0x18, 5, 0);
+	/* Disable clock initially, hdmi_cec_adap_enable() manages it */
+	REG_FLD_MOD(core->wp->base, HDMI_WP_CLK, 0, 5, 0);
 
 	ret = cec_register_adapter(core->adap, &pdev->dev);
 	if (ret < 0) {
diff --git a/drivers/gpu/drm/omapdrm/dss/hdmi4_core.c b/drivers/gpu/drm/omapdrm/dss/hdmi4_core.c
index 813ba42f2753..e384b95ad857 100644
--- a/drivers/gpu/drm/omapdrm/dss/hdmi4_core.c
+++ b/drivers/gpu/drm/omapdrm/dss/hdmi4_core.c
@@ -708,7 +708,7 @@ int hdmi4_audio_config(struct hdmi_core_data *core, struct hdmi_wp_data *wp,
 	else
 		acore.i2s_cfg.justification = HDMI_AUDIO_JUSTIFY_RIGHT;
 	/*
-	 * The I2S input word length is twice the lenght given in the IEC-60958
+	 * The I2S input word length is twice the length given in the IEC-60958
 	 * status word. If the word size is greater than
 	 * 20 bits, increment by one.
 	 */
diff --git a/drivers/gpu/drm/qxl/qxl_drv.c b/drivers/gpu/drm/qxl/qxl_drv.c
index 578d867a81d5..f33e349c4ec5 100644
--- a/drivers/gpu/drm/qxl/qxl_drv.c
+++ b/drivers/gpu/drm/qxl/qxl_drv.c
@@ -255,10 +255,14 @@ static struct drm_driver qxl_driver = {
 #if defined(CONFIG_DEBUG_FS)
 	.debugfs_init = qxl_debugfs_init,
 #endif
+	.prime_handle_to_fd = drm_gem_prime_handle_to_fd,
+	.prime_fd_to_handle = drm_gem_prime_fd_to_handle,
 	.gem_prime_export = drm_gem_prime_export,
 	.gem_prime_import = drm_gem_prime_import,
 	.gem_prime_pin = qxl_gem_prime_pin,
 	.gem_prime_unpin = qxl_gem_prime_unpin,
+	.gem_prime_get_sg_table = qxl_gem_prime_get_sg_table,
+	.gem_prime_import_sg_table = qxl_gem_prime_import_sg_table,
 	.gem_prime_vmap = qxl_gem_prime_vmap,
 	.gem_prime_vunmap = qxl_gem_prime_vunmap,
 	.gem_prime_mmap = qxl_gem_prime_mmap,
diff --git a/drivers/gpu/drm/qxl/qxl_prime.c b/drivers/gpu/drm/qxl/qxl_prime.c
index 8b448eca1cd9..114653b471c6 100644
--- a/drivers/gpu/drm/qxl/qxl_prime.c
+++ b/drivers/gpu/drm/qxl/qxl_prime.c
@@ -42,6 +42,18 @@ void qxl_gem_prime_unpin(struct drm_gem_object *obj)
 	qxl_bo_unpin(bo);
 }
 
+struct sg_table *qxl_gem_prime_get_sg_table(struct drm_gem_object *obj)
+{
+	return ERR_PTR(-ENOSYS);
+}
+
+struct drm_gem_object *qxl_gem_prime_import_sg_table(
+	struct drm_device *dev, struct dma_buf_attachment *attach,
+	struct sg_table *table)
+{
+	return ERR_PTR(-ENOSYS);
+}
+
 void *qxl_gem_prime_vmap(struct drm_gem_object *obj)
 {
 	struct qxl_bo *bo = gem_to_qxl_bo(obj);
diff --git a/drivers/gpu/drm/rockchip/rockchip_drm_vop.c b/drivers/gpu/drm/rockchip/rockchip_drm_vop.c
index c7d4c6073ea5..0d4ade9d4722 100644
--- a/drivers/gpu/drm/rockchip/rockchip_drm_vop.c
+++ b/drivers/gpu/drm/rockchip/rockchip_drm_vop.c
@@ -541,6 +541,18 @@ static void vop_core_clks_disable(struct vop *vop)
 	clk_disable(vop->hclk);
 }
 
+static void vop_win_disable(struct vop *vop, const struct vop_win_data *win)
+{
+	if (win->phy->scl && win->phy->scl->ext) {
+		VOP_SCL_SET_EXT(vop, win, yrgb_hor_scl_mode, SCALE_NONE);
+		VOP_SCL_SET_EXT(vop, win, yrgb_ver_scl_mode, SCALE_NONE);
+		VOP_SCL_SET_EXT(vop, win, cbcr_hor_scl_mode, SCALE_NONE);
+		VOP_SCL_SET_EXT(vop, win, cbcr_ver_scl_mode, SCALE_NONE);
+	}
+
+	VOP_WIN_SET(vop, win, enable, 0);
+}
+
 static int vop_enable(struct drm_crtc *crtc)
 {
 	struct vop *vop = to_vop(crtc);
@@ -586,7 +598,7 @@ static int vop_enable(struct drm_crtc *crtc)
 		struct vop_win *vop_win = &vop->win[i];
 		const struct vop_win_data *win = vop_win->data;
 
-		VOP_WIN_SET(vop, win, enable, 0);
+		vop_win_disable(vop, win);
 	}
 	spin_unlock(&vop->reg_lock);
 
@@ -735,7 +747,7 @@ static void vop_plane_atomic_disable(struct drm_plane *plane,
 
 	spin_lock(&vop->reg_lock);
 
-	VOP_WIN_SET(vop, win, enable, 0);
+	vop_win_disable(vop, win);
 
 	spin_unlock(&vop->reg_lock);
 }
@@ -1622,7 +1634,7 @@ static int vop_initial(struct vop *vop)
 		int channel = i * 2 + 1;
 
 		VOP_WIN_SET(vop, win, channel, (channel + 1) << 4 | channel);
-		VOP_WIN_SET(vop, win, enable, 0);
+		vop_win_disable(vop, win);
 		VOP_WIN_SET(vop, win, gate, 1);
 	}
 
diff --git a/drivers/gpu/drm/scheduler/sched_main.c b/drivers/gpu/drm/scheduler/sched_main.c
index 19fc601c9eeb..a1bec2779e76 100644
--- a/drivers/gpu/drm/scheduler/sched_main.c
+++ b/drivers/gpu/drm/scheduler/sched_main.c
@@ -366,10 +366,9 @@ void drm_sched_increase_karma(struct drm_sched_job *bad)
 EXPORT_SYMBOL(drm_sched_increase_karma);
 
 /**
- * drm_sched_hw_job_reset - stop the scheduler if it contains the bad job
+ * drm_sched_stop - stop the scheduler
  *
  * @sched: scheduler instance
- * @bad: bad scheduler job
  *
  */
 void drm_sched_stop(struct drm_gpu_scheduler *sched)
diff --git a/drivers/gpu/drm/sun4i/sun4i_drv.c b/drivers/gpu/drm/sun4i/sun4i_drv.c
index 3ebd9f5e2719..29258b404e54 100644
--- a/drivers/gpu/drm/sun4i/sun4i_drv.c
+++ b/drivers/gpu/drm/sun4i/sun4i_drv.c
@@ -16,6 +16,7 @@
 #include <linux/of_reserved_mem.h>
 
 #include <drm/drmP.h>
+#include <drm/drm_atomic_helper.h>
 #include <drm/drm_fb_cma_helper.h>
 #include <drm/drm_fb_helper.h>
 #include <drm/drm_gem_cma_helper.h>
@@ -85,6 +86,8 @@ static int sun4i_drv_bind(struct device *dev)
 		ret = -ENOMEM;
 		goto free_drm;
 	}
+
+	dev_set_drvdata(dev, drm);
 	drm->dev_private = drv;
 	INIT_LIST_HEAD(&drv->frontend_list);
 	INIT_LIST_HEAD(&drv->engine_list);
@@ -144,8 +147,12 @@ static void sun4i_drv_unbind(struct device *dev)
 
 	drm_dev_unregister(drm);
 	drm_kms_helper_poll_fini(drm);
+	drm_atomic_helper_shutdown(drm);
 	drm_mode_config_cleanup(drm);
+
+	component_unbind_all(dev, NULL);
 	of_reserved_mem_device_release(dev);
+
 	drm_dev_put(drm);
 }
 
@@ -395,6 +402,8 @@ static int sun4i_drv_probe(struct platform_device *pdev)
 
 static int sun4i_drv_remove(struct platform_device *pdev)
 {
+	component_master_del(&pdev->dev, &sun4i_drv_master_ops);
+
 	return 0;
 }
 
diff --git a/drivers/gpu/drm/sun4i/sun8i_dw_hdmi.c b/drivers/gpu/drm/sun4i/sun8i_dw_hdmi.c
index dc47720c99ba..39d8509d96a0 100644
--- a/drivers/gpu/drm/sun4i/sun8i_dw_hdmi.c
+++ b/drivers/gpu/drm/sun4i/sun8i_dw_hdmi.c
@@ -48,8 +48,13 @@ static enum drm_mode_status
 sun8i_dw_hdmi_mode_valid_h6(struct drm_connector *connector,
 			    const struct drm_display_mode *mode)
 {
-	/* This is max for HDMI 2.0b (4K@60Hz) */
-	if (mode->clock > 594000)
+	/*
+	 * Controller support maximum of 594 MHz, which correlates to
+	 * 4K@60Hz 4:4:4 or RGB. However, for frequencies greater than
+	 * 340 MHz scrambling has to be enabled. Because scrambling is
+	 * not yet implemented, just limit to 340 MHz for now.
+	 */
+	if (mode->clock > 340000)
 		return MODE_CLOCK_HIGH;
 
 	return MODE_OK;
diff --git a/drivers/gpu/drm/sun4i/sun8i_tcon_top.c b/drivers/gpu/drm/sun4i/sun8i_tcon_top.c
index fc36e0c10a37..b1e7c76e9c17 100644
--- a/drivers/gpu/drm/sun4i/sun8i_tcon_top.c
+++ b/drivers/gpu/drm/sun4i/sun8i_tcon_top.c
@@ -227,7 +227,7 @@ static int sun8i_tcon_top_bind(struct device *dev, struct device *master,
 
 err_unregister_gates:
 	for (i = 0; i < CLK_NUM; i++)
-		if (clk_data->hws[i])
+		if (!IS_ERR_OR_NULL(clk_data->hws[i]))
 			clk_hw_unregister_gate(clk_data->hws[i]);
 	clk_disable_unprepare(tcon_top->bus);
 err_assert_reset:
@@ -245,7 +245,8 @@ static void sun8i_tcon_top_unbind(struct device *dev, struct device *master,
 
 	of_clk_del_provider(dev->of_node);
 	for (i = 0; i < CLK_NUM; i++)
-		clk_hw_unregister_gate(clk_data->hws[i]);
+		if (clk_data->hws[i])
+			clk_hw_unregister_gate(clk_data->hws[i]);
 
 	clk_disable_unprepare(tcon_top->bus);
 	reset_control_assert(tcon_top->rst);
diff --git a/drivers/gpu/drm/tegra/hdmi.c b/drivers/gpu/drm/tegra/hdmi.c
index 47c55974756d..d23c4bfde790 100644
--- a/drivers/gpu/drm/tegra/hdmi.c
+++ b/drivers/gpu/drm/tegra/hdmi.c
@@ -1260,9 +1260,15 @@ static void tegra_hdmi_encoder_enable(struct drm_encoder *encoder)
 
 	hdmi->dvi = !tegra_output_is_hdmi(output);
 	if (!hdmi->dvi) {
-		err = tegra_hdmi_setup_audio(hdmi);
-		if (err < 0)
-			hdmi->dvi = true;
+		/*
+		 * Make sure that the audio format has been configured before
+		 * enabling audio, otherwise we may try to divide by zero.
+		*/
+		if (hdmi->format.sample_rate > 0) {
+			err = tegra_hdmi_setup_audio(hdmi);
+			if (err < 0)
+				hdmi->dvi = true;
+		}
 	}
 
 	if (hdmi->config->has_hda)
diff --git a/drivers/gpu/drm/tegra/hub.c b/drivers/gpu/drm/tegra/hub.c
index ba9b3cfb8c3d..b3436c2aed68 100644
--- a/drivers/gpu/drm/tegra/hub.c
+++ b/drivers/gpu/drm/tegra/hub.c
@@ -378,14 +378,16 @@ static int tegra_shared_plane_atomic_check(struct drm_plane *plane,
 static void tegra_shared_plane_atomic_disable(struct drm_plane *plane,
 					      struct drm_plane_state *old_state)
 {
-	struct tegra_dc *dc = to_tegra_dc(old_state->crtc);
 	struct tegra_plane *p = to_tegra_plane(plane);
+	struct tegra_dc *dc;
 	u32 value;
 
 	/* rien ne va plus */
 	if (!old_state || !old_state->crtc)
 		return;
 
+	dc = to_tegra_dc(old_state->crtc);
+
 	/*
 	 * XXX Legacy helpers seem to sometimes call ->atomic_disable() even
 	 * on planes that are already disabled. Make sure we fallback to the
diff --git a/drivers/gpu/drm/tegra/vic.c b/drivers/gpu/drm/tegra/vic.c
index 39bfed9623de..982ce37ecde1 100644
--- a/drivers/gpu/drm/tegra/vic.c
+++ b/drivers/gpu/drm/tegra/vic.c
@@ -106,6 +106,7 @@ static int vic_boot(struct vic *vic)
 	if (vic->booted)
 		return 0;
 
+#ifdef CONFIG_IOMMU_API
 	if (vic->config->supports_sid) {
 		struct iommu_fwspec *spec = dev_iommu_fwspec_get(vic->dev);
 		u32 value;
@@ -121,6 +122,7 @@ static int vic_boot(struct vic *vic)
 			vic_writel(vic, value, VIC_THI_STREAMID1);
 		}
 	}
+#endif
 
 	/* setup clockgating registers */
 	vic_writel(vic, CG_IDLE_CG_DLY_CNT(4) |
diff --git a/drivers/gpu/drm/ttm/ttm_bo.c b/drivers/gpu/drm/ttm/ttm_bo.c
index 3f56647cdb35..1a01669b159a 100644
--- a/drivers/gpu/drm/ttm/ttm_bo.c
+++ b/drivers/gpu/drm/ttm/ttm_bo.c
@@ -49,9 +49,8 @@ static void ttm_bo_global_kobj_release(struct kobject *kobj);
  * ttm_global_mutex - protecting the global BO state
  */
 DEFINE_MUTEX(ttm_global_mutex);
-struct ttm_bo_global ttm_bo_glob = {
-	.use_count = 0
-};
+unsigned ttm_bo_glob_use_count;
+struct ttm_bo_global ttm_bo_glob;
 
 static struct attribute ttm_bo_count = {
 	.name = "bo_count",
@@ -876,8 +875,10 @@ static int ttm_bo_add_move_fence(struct ttm_buffer_object *bo,
 		reservation_object_add_shared_fence(bo->resv, fence);
 
 		ret = reservation_object_reserve_shared(bo->resv, 1);
-		if (unlikely(ret))
+		if (unlikely(ret)) {
+			dma_fence_put(fence);
 			return ret;
+		}
 
 		dma_fence_put(bo->moving);
 		bo->moving = fence;
@@ -1529,12 +1530,13 @@ static void ttm_bo_global_release(void)
 	struct ttm_bo_global *glob = &ttm_bo_glob;
 
 	mutex_lock(&ttm_global_mutex);
-	if (--glob->use_count > 0)
+	if (--ttm_bo_glob_use_count > 0)
 		goto out;
 
 	kobject_del(&glob->kobj);
 	kobject_put(&glob->kobj);
 	ttm_mem_global_release(&ttm_mem_glob);
+	memset(glob, 0, sizeof(*glob));
 out:
 	mutex_unlock(&ttm_global_mutex);
 }
@@ -1546,7 +1548,7 @@ static int ttm_bo_global_init(void)
 	unsigned i;
 
 	mutex_lock(&ttm_global_mutex);
-	if (++glob->use_count > 1)
+	if (++ttm_bo_glob_use_count > 1)
 		goto out;
 
 	ret = ttm_mem_global_init(&ttm_mem_glob);
diff --git a/drivers/gpu/drm/ttm/ttm_memory.c b/drivers/gpu/drm/ttm/ttm_memory.c
index f1567c353b54..9a0909decb36 100644
--- a/drivers/gpu/drm/ttm/ttm_memory.c
+++ b/drivers/gpu/drm/ttm/ttm_memory.c
@@ -461,8 +461,8 @@ out_no_zone:
 
 void ttm_mem_global_release(struct ttm_mem_global *glob)
 {
-	unsigned int i;
 	struct ttm_mem_zone *zone;
+	unsigned int i;
 
 	/* let the page allocator first stop the shrink work. */
 	ttm_page_alloc_fini();
@@ -475,9 +475,10 @@ void ttm_mem_global_release(struct ttm_mem_global *glob)
 		zone = glob->zones[i];
 		kobject_del(&zone->kobj);
 		kobject_put(&zone->kobj);
-			}
+	}
 	kobject_del(&glob->kobj);
 	kobject_put(&glob->kobj);
+	memset(glob, 0, sizeof(*glob));
 }
 
 static void ttm_check_swapping(struct ttm_mem_global *glob)
diff --git a/drivers/gpu/drm/ttm/ttm_page_alloc.c b/drivers/gpu/drm/ttm/ttm_page_alloc.c
index f841accc2c00..627f8dc91d0e 100644
--- a/drivers/gpu/drm/ttm/ttm_page_alloc.c
+++ b/drivers/gpu/drm/ttm/ttm_page_alloc.c
@@ -730,9 +730,10 @@ static void ttm_put_pages(struct page **pages, unsigned npages, int flags,
 			}
 
 #ifdef CONFIG_TRANSPARENT_HUGEPAGE
-			if (!(flags & TTM_PAGE_FLAG_DMA32)) {
-				for (j = 0; j < HPAGE_PMD_NR; ++j)
-					if (p++ != pages[i + j])
+			if (!(flags & TTM_PAGE_FLAG_DMA32) &&
+			    (npages - i) >= HPAGE_PMD_NR) {
+				for (j = 1; j < HPAGE_PMD_NR; ++j)
+					if (++p != pages[i + j])
 					    break;
 
 				if (j == HPAGE_PMD_NR)
@@ -759,15 +760,15 @@ static void ttm_put_pages(struct page **pages, unsigned npages, int flags,
 		unsigned max_size, n2free;
 
 		spin_lock_irqsave(&huge->lock, irq_flags);
-		while (i < npages) {
+		while ((npages - i) >= HPAGE_PMD_NR) {
 			struct page *p = pages[i];
 			unsigned j;
 
 			if (!p)
 				break;
 
-			for (j = 0; j < HPAGE_PMD_NR; ++j)
-				if (p++ != pages[i + j])
+			for (j = 1; j < HPAGE_PMD_NR; ++j)
+				if (++p != pages[i + j])
 				    break;
 
 			if (j != HPAGE_PMD_NR)
diff --git a/drivers/gpu/drm/udl/udl_connector.c b/drivers/gpu/drm/udl/udl_connector.c
index 66885c24590f..c1bd5e3d9e4a 100644
--- a/drivers/gpu/drm/udl/udl_connector.c
+++ b/drivers/gpu/drm/udl/udl_connector.c
@@ -18,18 +18,19 @@
 #include "udl_connector.h"
 #include "udl_drv.h"
 
-static bool udl_get_edid_block(struct udl_device *udl, int block_idx,
-							   u8 *buff)
+static int udl_get_edid_block(void *data, u8 *buf, unsigned int block,
+			       size_t len)
 {
 	int ret, i;
 	u8 *read_buff;
+	struct udl_device *udl = data;
 
 	read_buff = kmalloc(2, GFP_KERNEL);
 	if (!read_buff)
-		return false;
+		return -1;
 
-	for (i = 0; i < EDID_LENGTH; i++) {
-		int bval = (i + block_idx * EDID_LENGTH) << 8;
+	for (i = 0; i < len; i++) {
+		int bval = (i + block * EDID_LENGTH) << 8;
 		ret = usb_control_msg(udl->udev,
 				      usb_rcvctrlpipe(udl->udev, 0),
 					  (0x02), (0x80 | (0x02 << 5)), bval,
@@ -37,60 +38,13 @@ static bool udl_get_edid_block(struct udl_device *udl, int block_idx,
 		if (ret < 1) {
 			DRM_ERROR("Read EDID byte %d failed err %x\n", i, ret);
 			kfree(read_buff);
-			return false;
+			return -1;
 		}
-		buff[i] = read_buff[1];
+		buf[i] = read_buff[1];
 	}
 
 	kfree(read_buff);
-	return true;
-}
-
-static bool udl_get_edid(struct udl_device *udl, u8 **result_buff,
-			 int *result_buff_size)
-{
-	int i, extensions;
-	u8 *block_buff = NULL, *buff_ptr;
-
-	block_buff = kmalloc(EDID_LENGTH, GFP_KERNEL);
-	if (block_buff == NULL)
-		return false;
-
-	if (udl_get_edid_block(udl, 0, block_buff) &&
-	    memchr_inv(block_buff, 0, EDID_LENGTH)) {
-		extensions = ((struct edid *)block_buff)->extensions;
-		if (extensions > 0) {
-			/* we have to read all extensions one by one */
-			*result_buff_size = EDID_LENGTH * (extensions + 1);
-			*result_buff = kmalloc(*result_buff_size, GFP_KERNEL);
-			buff_ptr = *result_buff;
-			if (buff_ptr == NULL) {
-				kfree(block_buff);
-				return false;
-			}
-			memcpy(buff_ptr, block_buff, EDID_LENGTH);
-			kfree(block_buff);
-			buff_ptr += EDID_LENGTH;
-			for (i = 1; i < extensions; ++i) {
-				if (udl_get_edid_block(udl, i, buff_ptr)) {
-					buff_ptr += EDID_LENGTH;
-				} else {
-					kfree(*result_buff);
-					*result_buff = NULL;
-					return false;
-				}
-			}
-			return true;
-		}
-		/* we have only base edid block */
-		*result_buff = block_buff;
-		*result_buff_size = EDID_LENGTH;
-		return true;
-	}
-
-	kfree(block_buff);
-
-	return false;
+	return 0;
 }
 
 static int udl_get_modes(struct drm_connector *connector)
@@ -122,8 +76,6 @@ static enum drm_mode_status udl_mode_valid(struct drm_connector *connector,
 static enum drm_connector_status
 udl_detect(struct drm_connector *connector, bool force)
 {
-	u8 *edid_buff = NULL;
-	int edid_buff_size = 0;
 	struct udl_device *udl = connector->dev->dev_private;
 	struct udl_drm_connector *udl_connector =
 					container_of(connector,
@@ -136,12 +88,10 @@ udl_detect(struct drm_connector *connector, bool force)
 		udl_connector->edid = NULL;
 	}
 
-
-	if (!udl_get_edid(udl, &edid_buff, &edid_buff_size))
+	udl_connector->edid = drm_do_get_edid(connector, udl_get_edid_block, udl);
+	if (!udl_connector->edid)
 		return connector_status_disconnected;
 
-	udl_connector->edid = (struct edid *)edid_buff;
-	
 	return connector_status_connected;
 }
 
diff --git a/drivers/gpu/drm/udl/udl_drv.c b/drivers/gpu/drm/udl/udl_drv.c
index 22cd2d13e272..ff47f890e6ad 100644
--- a/drivers/gpu/drm/udl/udl_drv.c
+++ b/drivers/gpu/drm/udl/udl_drv.c
@@ -52,6 +52,7 @@ static struct drm_driver driver = {
 	.driver_features = DRIVER_MODESET | DRIVER_GEM | DRIVER_PRIME,
 	.load = udl_driver_load,
 	.unload = udl_driver_unload,
+	.release = udl_driver_release,
 
 	/* gem hooks */
 	.gem_free_object_unlocked = udl_gem_free_object,
diff --git a/drivers/gpu/drm/udl/udl_drv.h b/drivers/gpu/drm/udl/udl_drv.h
index e9e9b1ff678e..4ae67d882eae 100644
--- a/drivers/gpu/drm/udl/udl_drv.h
+++ b/drivers/gpu/drm/udl/udl_drv.h
@@ -104,6 +104,7 @@ void udl_urb_completion(struct urb *urb);
 
 int udl_driver_load(struct drm_device *dev, unsigned long flags);
 void udl_driver_unload(struct drm_device *dev);
+void udl_driver_release(struct drm_device *dev);
 
 int udl_fbdev_init(struct drm_device *dev);
 void udl_fbdev_cleanup(struct drm_device *dev);
diff --git a/drivers/gpu/drm/udl/udl_main.c b/drivers/gpu/drm/udl/udl_main.c
index 9086d0d1b880..1f8ef34ade24 100644
--- a/drivers/gpu/drm/udl/udl_main.c
+++ b/drivers/gpu/drm/udl/udl_main.c
@@ -379,6 +379,12 @@ void udl_driver_unload(struct drm_device *dev)
 		udl_free_urb_list(dev);
 
 	udl_fbdev_cleanup(dev);
-	udl_modeset_cleanup(dev);
 	kfree(udl);
 }
+
+void udl_driver_release(struct drm_device *dev)
+{
+	udl_modeset_cleanup(dev);
+	drm_dev_fini(dev);
+	kfree(dev);
+}
diff --git a/drivers/gpu/drm/vc4/vc4_crtc.c b/drivers/gpu/drm/vc4/vc4_crtc.c
index 730008d3da76..1baa10e94484 100644
--- a/drivers/gpu/drm/vc4/vc4_crtc.c
+++ b/drivers/gpu/drm/vc4/vc4_crtc.c
@@ -1042,7 +1042,7 @@ static void
 vc4_crtc_reset(struct drm_crtc *crtc)
 {
 	if (crtc->state)
-		__drm_atomic_helper_crtc_destroy_state(crtc->state);
+		vc4_crtc_destroy_state(crtc, crtc->state);
 
 	crtc->state = kzalloc(sizeof(struct vc4_crtc_state), GFP_KERNEL);
 	if (crtc->state)
diff --git a/drivers/gpu/drm/vgem/vgem_drv.c b/drivers/gpu/drm/vgem/vgem_drv.c
index 5930facd6d2d..11a8f99ba18c 100644
--- a/drivers/gpu/drm/vgem/vgem_drv.c
+++ b/drivers/gpu/drm/vgem/vgem_drv.c
@@ -191,13 +191,9 @@ static struct drm_gem_object *vgem_gem_create(struct drm_device *dev,
 	ret = drm_gem_handle_create(file, &obj->base, handle);
 	drm_gem_object_put_unlocked(&obj->base);
 	if (ret)
-		goto err;
+		return ERR_PTR(ret);
 
 	return &obj->base;
-
-err:
-	__vgem_gem_destroy(obj);
-	return ERR_PTR(ret);
 }
 
 static int vgem_gem_dumb_create(struct drm_file *file, struct drm_device *dev,
diff --git a/drivers/gpu/drm/virtio/virtgpu_drv.c b/drivers/gpu/drm/virtio/virtgpu_drv.c
index b996ac1d4fcc..af92964b6889 100644
--- a/drivers/gpu/drm/virtio/virtgpu_drv.c
+++ b/drivers/gpu/drm/virtio/virtgpu_drv.c
@@ -205,10 +205,14 @@ static struct drm_driver driver = {
 #if defined(CONFIG_DEBUG_FS)
 	.debugfs_init = virtio_gpu_debugfs_init,
 #endif
+	.prime_handle_to_fd = drm_gem_prime_handle_to_fd,
+	.prime_fd_to_handle = drm_gem_prime_fd_to_handle,
 	.gem_prime_export = drm_gem_prime_export,
 	.gem_prime_import = drm_gem_prime_import,
 	.gem_prime_pin = virtgpu_gem_prime_pin,
 	.gem_prime_unpin = virtgpu_gem_prime_unpin,
+	.gem_prime_get_sg_table = virtgpu_gem_prime_get_sg_table,
+	.gem_prime_import_sg_table = virtgpu_gem_prime_import_sg_table,
 	.gem_prime_vmap = virtgpu_gem_prime_vmap,
 	.gem_prime_vunmap = virtgpu_gem_prime_vunmap,
 	.gem_prime_mmap = virtgpu_gem_prime_mmap,
diff --git a/drivers/gpu/drm/virtio/virtgpu_drv.h b/drivers/gpu/drm/virtio/virtgpu_drv.h
index 3238fdf58eb4..d577cb76f5ad 100644
--- a/drivers/gpu/drm/virtio/virtgpu_drv.h
+++ b/drivers/gpu/drm/virtio/virtgpu_drv.h
@@ -354,6 +354,10 @@ int virtio_gpu_object_wait(struct virtio_gpu_object *bo, bool no_wait);
 /* virtgpu_prime.c */
 int virtgpu_gem_prime_pin(struct drm_gem_object *obj);
 void virtgpu_gem_prime_unpin(struct drm_gem_object *obj);
+struct sg_table *virtgpu_gem_prime_get_sg_table(struct drm_gem_object *obj);
+struct drm_gem_object *virtgpu_gem_prime_import_sg_table(
+	struct drm_device *dev, struct dma_buf_attachment *attach,
+	struct sg_table *sgt);
 void *virtgpu_gem_prime_vmap(struct drm_gem_object *obj);
 void virtgpu_gem_prime_vunmap(struct drm_gem_object *obj, void *vaddr);
 int virtgpu_gem_prime_mmap(struct drm_gem_object *obj,
diff --git a/drivers/gpu/drm/virtio/virtgpu_prime.c b/drivers/gpu/drm/virtio/virtgpu_prime.c
index c59ec34c80a5..eb51a78e1199 100644
--- a/drivers/gpu/drm/virtio/virtgpu_prime.c
+++ b/drivers/gpu/drm/virtio/virtgpu_prime.c
@@ -39,6 +39,18 @@ void virtgpu_gem_prime_unpin(struct drm_gem_object *obj)
 	WARN_ONCE(1, "not implemented");
 }
 
+struct sg_table *virtgpu_gem_prime_get_sg_table(struct drm_gem_object *obj)
+{
+	return ERR_PTR(-ENODEV);
+}
+
+struct drm_gem_object *virtgpu_gem_prime_import_sg_table(
+	struct drm_device *dev, struct dma_buf_attachment *attach,
+	struct sg_table *table)
+{
+	return ERR_PTR(-ENODEV);
+}
+
 void *virtgpu_gem_prime_vmap(struct drm_gem_object *obj)
 {
 	struct virtio_gpu_object *bo = gem_to_virtio_gpu_obj(obj);
diff --git a/drivers/gpu/drm/vkms/vkms_gem.c b/drivers/gpu/drm/vkms/vkms_gem.c
index 138b0bb325cf..69048e73377d 100644
--- a/drivers/gpu/drm/vkms/vkms_gem.c
+++ b/drivers/gpu/drm/vkms/vkms_gem.c
@@ -111,11 +111,8 @@ struct drm_gem_object *vkms_gem_create(struct drm_device *dev,
 
 	ret = drm_gem_handle_create(file, &obj->gem, handle);
 	drm_gem_object_put_unlocked(&obj->gem);
-	if (ret) {
-		drm_gem_object_release(&obj->gem);
-		kfree(obj);
+	if (ret)
 		return ERR_PTR(ret);
-	}
 
 	return &obj->gem;
 }
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_drv.c b/drivers/gpu/drm/vmwgfx/vmwgfx_drv.c
index 6165fe2c4504..1bfa353d995c 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_drv.c
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_drv.c
@@ -546,29 +546,13 @@ static void vmw_get_initial_size(struct vmw_private *dev_priv)
 }
 
 /**
- * vmw_assume_iommu - Figure out whether coherent dma-remapping might be
- * taking place.
- * @dev: Pointer to the struct drm_device.
- *
- * Return: true if iommu present, false otherwise.
- */
-static bool vmw_assume_iommu(struct drm_device *dev)
-{
-	const struct dma_map_ops *ops = get_dma_ops(dev->dev);
-
-	return !dma_is_direct(ops) && ops &&
-		ops->map_page != dma_direct_map_page;
-}
-
-/**
  * vmw_dma_select_mode - Determine how DMA mappings should be set up for this
  * system.
  *
  * @dev_priv: Pointer to a struct vmw_private
  *
- * This functions tries to determine the IOMMU setup and what actions
- * need to be taken by the driver to make system pages visible to the
- * device.
+ * This functions tries to determine what actions need to be taken by the
+ * driver to make system pages visible to the device.
  * If this function decides that DMA is not possible, it returns -EINVAL.
  * The driver may then try to disable features of the device that require
  * DMA.
@@ -578,23 +562,16 @@ static int vmw_dma_select_mode(struct vmw_private *dev_priv)
 	static const char *names[vmw_dma_map_max] = {
 		[vmw_dma_phys] = "Using physical TTM page addresses.",
 		[vmw_dma_alloc_coherent] = "Using coherent TTM pages.",
-		[vmw_dma_map_populate] = "Keeping DMA mappings.",
+		[vmw_dma_map_populate] = "Caching DMA mappings.",
 		[vmw_dma_map_bind] = "Giving up DMA mappings early."};
 
 	if (vmw_force_coherent)
 		dev_priv->map_mode = vmw_dma_alloc_coherent;
-	else if (vmw_assume_iommu(dev_priv->dev))
-		dev_priv->map_mode = vmw_dma_map_populate;
-	else if (!vmw_force_iommu)
-		dev_priv->map_mode = vmw_dma_phys;
-	else if (IS_ENABLED(CONFIG_SWIOTLB) && swiotlb_nr_tbl())
-		dev_priv->map_mode = vmw_dma_alloc_coherent;
+	else if (vmw_restrict_iommu)
+		dev_priv->map_mode = vmw_dma_map_bind;
 	else
 		dev_priv->map_mode = vmw_dma_map_populate;
 
-	if (dev_priv->map_mode == vmw_dma_map_populate && vmw_restrict_iommu)
-		dev_priv->map_mode = vmw_dma_map_bind;
-
 	/* No TTM coherent page pool? FIXME: Ask TTM instead! */
         if (!(IS_ENABLED(CONFIG_SWIOTLB) || IS_ENABLED(CONFIG_INTEL_IOMMU)) &&
 	    (dev_priv->map_mode == vmw_dma_alloc_coherent))
diff --git a/drivers/gpu/host1x/hw/channel_hw.c b/drivers/gpu/host1x/hw/channel_hw.c
index 27101c04a827..0c0eb43abf65 100644
--- a/drivers/gpu/host1x/hw/channel_hw.c
+++ b/drivers/gpu/host1x/hw/channel_hw.c
@@ -115,8 +115,12 @@ static inline void synchronize_syncpt_base(struct host1x_job *job)
 static void host1x_channel_set_streamid(struct host1x_channel *channel)
 {
 #if HOST1X_HW >= 6
+	u32 sid = 0x7f;
+#ifdef CONFIG_IOMMU_API
 	struct iommu_fwspec *spec = dev_iommu_fwspec_get(channel->dev->parent);
-	u32 sid = spec ? spec->ids[0] & 0xffff : 0x7f;
+	if (spec)
+		sid = spec->ids[0] & 0xffff;
+#endif
 
 	host1x_ch_writel(channel, sid, HOST1X_CHANNEL_SMMU_STREAMID);
 #endif
diff --git a/drivers/gpu/ipu-v3/ipu-dp.c b/drivers/gpu/ipu-v3/ipu-dp.c
index 9b2b3fa479c4..5e44ff1f2085 100644
--- a/drivers/gpu/ipu-v3/ipu-dp.c
+++ b/drivers/gpu/ipu-v3/ipu-dp.c
@@ -195,7 +195,8 @@ int ipu_dp_setup_channel(struct ipu_dp *dp,
 		ipu_dp_csc_init(flow, flow->foreground.in_cs, flow->out_cs,
 				DP_COM_CONF_CSC_DEF_BOTH);
 	} else {
-		if (flow->foreground.in_cs == flow->out_cs)
+		if (flow->foreground.in_cs == IPUV3_COLORSPACE_UNKNOWN ||
+		    flow->foreground.in_cs == flow->out_cs)
 			/*
 			 * foreground identical to output, apply color
 			 * conversion on background
@@ -261,6 +262,8 @@ void ipu_dp_disable_channel(struct ipu_dp *dp, bool sync)
 	struct ipu_dp_priv *priv = flow->priv;
 	u32 reg, csc;
 
+	dp->in_cs = IPUV3_COLORSPACE_UNKNOWN;
+
 	if (!dp->foreground)
 		return;
 
@@ -268,8 +271,9 @@ void ipu_dp_disable_channel(struct ipu_dp *dp, bool sync)
 
 	reg = readl(flow->base + DP_COM_CONF);
 	csc = reg & DP_COM_CONF_CSC_DEF_MASK;
-	if (csc == DP_COM_CONF_CSC_DEF_FG)
-		reg &= ~DP_COM_CONF_CSC_DEF_MASK;
+	reg &= ~DP_COM_CONF_CSC_DEF_MASK;
+	if (csc == DP_COM_CONF_CSC_DEF_BOTH || csc == DP_COM_CONF_CSC_DEF_BG)
+		reg |= DP_COM_CONF_CSC_DEF_BG;
 
 	reg &= ~DP_COM_CONF_FG_EN;
 	writel(reg, flow->base + DP_COM_CONF);
@@ -347,6 +351,8 @@ int ipu_dp_init(struct ipu_soc *ipu, struct device *dev, unsigned long base)
 	mutex_init(&priv->mutex);
 
 	for (i = 0; i < IPUV3_NUM_FLOWS; i++) {
+		priv->flow[i].background.in_cs = IPUV3_COLORSPACE_UNKNOWN;
+		priv->flow[i].foreground.in_cs = IPUV3_COLORSPACE_UNKNOWN;
 		priv->flow[i].foreground.foreground = true;
 		priv->flow[i].base = priv->base + ipu_dp_flow_base[i];
 		priv->flow[i].priv = priv;
diff --git a/drivers/hid/Kconfig b/drivers/hid/Kconfig
index 6ca8d322b487..4ca0cdfa6b33 100644
--- a/drivers/hid/Kconfig
+++ b/drivers/hid/Kconfig
@@ -150,6 +150,7 @@ config HID_ASUS
 	tristate "Asus"
 	depends on LEDS_CLASS
 	depends on ASUS_WMI || ASUS_WMI=n
+	select POWER_SUPPLY
 	---help---
 	Support for Asus notebook built-in keyboard and touchpad via i2c, and
 	the Asus Republic of Gamers laptop keyboard special keys.
diff --git a/drivers/hid/hid-core.c b/drivers/hid/hid-core.c
index 9993b692598f..860e21ec6a49 100644
--- a/drivers/hid/hid-core.c
+++ b/drivers/hid/hid-core.c
@@ -1301,10 +1301,10 @@ static u32 __extract(u8 *report, unsigned offset, int n)
 u32 hid_field_extract(const struct hid_device *hid, u8 *report,
 			unsigned offset, unsigned n)
 {
-	if (n > 32) {
-		hid_warn(hid, "hid_field_extract() called with n (%d) > 32! (%s)\n",
+	if (n > 256) {
+		hid_warn(hid, "hid_field_extract() called with n (%d) > 256! (%s)\n",
 			 n, current->comm);
-		n = 32;
+		n = 256;
 	}
 
 	return __extract(report, offset, n);
diff --git a/drivers/hid/hid-debug.c b/drivers/hid/hid-debug.c
index ac9fda1b5a72..1384e57182af 100644
--- a/drivers/hid/hid-debug.c
+++ b/drivers/hid/hid-debug.c
@@ -1060,10 +1060,15 @@ static int hid_debug_rdesc_show(struct seq_file *f, void *p)
 	seq_printf(f, "\n\n");
 
 	/* dump parsed data and input mappings */
+	if (down_interruptible(&hdev->driver_input_lock))
+		return 0;
+
 	hid_dump_device(hdev, f);
 	seq_printf(f, "\n");
 	hid_dump_input_mapping(hdev, f);
 
+	up(&hdev->driver_input_lock);
+
 	return 0;
 }
 
diff --git a/drivers/hid/hid-ids.h b/drivers/hid/hid-ids.h
index b6d93f4ad037..adce58f24f76 100644
--- a/drivers/hid/hid-ids.h
+++ b/drivers/hid/hid-ids.h
@@ -1083,6 +1083,7 @@
 #define USB_DEVICE_ID_SYNAPTICS_HD	0x0ac3
 #define USB_DEVICE_ID_SYNAPTICS_QUAD_HD	0x1ac3
 #define USB_DEVICE_ID_SYNAPTICS_TP_V103	0x5710
+#define I2C_DEVICE_ID_SYNAPTICS_7E7E	0x7e7e
 
 #define USB_VENDOR_ID_TEXAS_INSTRUMENTS	0x2047
 #define USB_DEVICE_ID_TEXAS_INSTRUMENTS_LENOVO_YOGA	0x0855
diff --git a/drivers/hid/hid-input.c b/drivers/hid/hid-input.c
index b10b1922c5bd..b607286a0bc8 100644
--- a/drivers/hid/hid-input.c
+++ b/drivers/hid/hid-input.c
@@ -680,6 +680,14 @@ static void hidinput_configure_usage(struct hid_input *hidinput, struct hid_fiel
 			break;
 		}
 
+		if ((usage->hid & 0xf0) == 0xb0) {	/* SC - Display */
+			switch (usage->hid & 0xf) {
+			case 0x05: map_key_clear(KEY_SWITCHVIDEOMODE); break;
+			default: goto ignore;
+			}
+			break;
+		}
+
 		/*
 		 * Some lazy vendors declare 255 usages for System Control,
 		 * leading to the creation of ABS_X|Y axis and too many others.
@@ -902,7 +910,7 @@ static void hidinput_configure_usage(struct hid_input *hidinput, struct hid_fiel
 		case 0x06a: map_key_clear(KEY_GREEN);		break;
 		case 0x06b: map_key_clear(KEY_BLUE);		break;
 		case 0x06c: map_key_clear(KEY_YELLOW);		break;
-		case 0x06d: map_key_clear(KEY_ZOOM);		break;
+		case 0x06d: map_key_clear(KEY_ASPECT_RATIO);	break;
 
 		case 0x06f: map_key_clear(KEY_BRIGHTNESSUP);		break;
 		case 0x070: map_key_clear(KEY_BRIGHTNESSDOWN);		break;
@@ -911,6 +919,10 @@ static void hidinput_configure_usage(struct hid_input *hidinput, struct hid_fiel
 		case 0x074: map_key_clear(KEY_BRIGHTNESS_MAX);		break;
 		case 0x075: map_key_clear(KEY_BRIGHTNESS_AUTO);		break;
 
+		case 0x079: map_key_clear(KEY_KBDILLUMUP);	break;
+		case 0x07a: map_key_clear(KEY_KBDILLUMDOWN);	break;
+		case 0x07c: map_key_clear(KEY_KBDILLUMTOGGLE);	break;
+
 		case 0x082: map_key_clear(KEY_VIDEO_NEXT);	break;
 		case 0x083: map_key_clear(KEY_LAST);		break;
 		case 0x084: map_key_clear(KEY_ENTER);		break;
@@ -998,6 +1010,7 @@ static void hidinput_configure_usage(struct hid_input *hidinput, struct hid_fiel
 		case 0x1b8: map_key_clear(KEY_VIDEO);		break;
 		case 0x1bc: map_key_clear(KEY_MESSENGER);	break;
 		case 0x1bd: map_key_clear(KEY_INFO);		break;
+		case 0x1cb: map_key_clear(KEY_ASSISTANT);	break;
 		case 0x201: map_key_clear(KEY_NEW);		break;
 		case 0x202: map_key_clear(KEY_OPEN);		break;
 		case 0x203: map_key_clear(KEY_CLOSE);		break;
@@ -1021,6 +1034,7 @@ static void hidinput_configure_usage(struct hid_input *hidinput, struct hid_fiel
 		case 0x22d: map_key_clear(KEY_ZOOMIN);		break;
 		case 0x22e: map_key_clear(KEY_ZOOMOUT);		break;
 		case 0x22f: map_key_clear(KEY_ZOOMRESET);	break;
+		case 0x232: map_key_clear(KEY_FULL_SCREEN);	break;
 		case 0x233: map_key_clear(KEY_SCROLLUP);	break;
 		case 0x234: map_key_clear(KEY_SCROLLDOWN);	break;
 		case 0x238: /* AC Pan */
@@ -1044,6 +1058,8 @@ static void hidinput_configure_usage(struct hid_input *hidinput, struct hid_fiel
 		case 0x2cb: map_key_clear(KEY_KBDINPUTASSIST_ACCEPT);	break;
 		case 0x2cc: map_key_clear(KEY_KBDINPUTASSIST_CANCEL);	break;
 
+		case 0x29f: map_key_clear(KEY_SCALE);		break;
+
 		default: map_key_clear(KEY_UNKNOWN);
 		}
 		break;
diff --git a/drivers/hid/hid-logitech-hidpp.c b/drivers/hid/hid-logitech-hidpp.c
index 15ed6177a7a3..199cc256e9d9 100644
--- a/drivers/hid/hid-logitech-hidpp.c
+++ b/drivers/hid/hid-logitech-hidpp.c
@@ -2111,6 +2111,13 @@ static int hidpp_ff_init(struct hidpp_device *hidpp, u8 feature_index)
 		kfree(data);
 		return -ENOMEM;
 	}
+	data->wq = create_singlethread_workqueue("hidpp-ff-sendqueue");
+	if (!data->wq) {
+		kfree(data->effect_ids);
+		kfree(data);
+		return -ENOMEM;
+	}
+
 	data->hidpp = hidpp;
 	data->feature_index = feature_index;
 	data->version = version;
@@ -2155,7 +2162,6 @@ static int hidpp_ff_init(struct hidpp_device *hidpp, u8 feature_index)
 	/* ignore boost value at response.fap.params[2] */
 
 	/* init the hardware command queue */
-	data->wq = create_singlethread_workqueue("hidpp-ff-sendqueue");
 	atomic_set(&data->workqueue_size, 0);
 
 	/* initialize with zero autocenter to get wheel in usable state */
@@ -2608,8 +2614,9 @@ static int m560_raw_event(struct hid_device *hdev, u8 *data, int size)
 		input_report_rel(mydata->input, REL_Y, v);
 
 		v = hid_snto32(data[6], 8);
-		hidpp_scroll_counter_handle_scroll(
-				&hidpp->vertical_wheel_counter, v);
+		if (v != 0)
+			hidpp_scroll_counter_handle_scroll(
+					&hidpp->vertical_wheel_counter, v);
 
 		input_sync(mydata->input);
 	}
diff --git a/drivers/hid/hid-quirks.c b/drivers/hid/hid-quirks.c
index 953908f2267c..77ffba48cc73 100644
--- a/drivers/hid/hid-quirks.c
+++ b/drivers/hid/hid-quirks.c
@@ -715,7 +715,6 @@ static const struct hid_device_id hid_ignore_list[] = {
 	{ HID_USB_DEVICE(USB_VENDOR_ID_DEALEXTREAME, USB_DEVICE_ID_DEALEXTREAME_RADIO_SI4701) },
 	{ HID_USB_DEVICE(USB_VENDOR_ID_DELORME, USB_DEVICE_ID_DELORME_EARTHMATE) },
 	{ HID_USB_DEVICE(USB_VENDOR_ID_DELORME, USB_DEVICE_ID_DELORME_EM_LT20) },
-	{ HID_I2C_DEVICE(USB_VENDOR_ID_ELAN, 0x0400) },
 	{ HID_USB_DEVICE(USB_VENDOR_ID_ESSENTIAL_REALITY, USB_DEVICE_ID_ESSENTIAL_REALITY_P5) },
 	{ HID_USB_DEVICE(USB_VENDOR_ID_ETT, USB_DEVICE_ID_TC5UH) },
 	{ HID_USB_DEVICE(USB_VENDOR_ID_ETT, USB_DEVICE_ID_TC4UM) },
@@ -855,7 +854,7 @@ static const struct hid_device_id hid_ignore_list[] = {
 	{ }
 };
 
-/**
+/*
  * hid_mouse_ignore_list - mouse devices which should not be handled by the hid layer
  *
  * There are composite devices for which we want to ignore only a certain
@@ -996,6 +995,10 @@ bool hid_ignore(struct hid_device *hdev)
 		if (hdev->product == 0x0401 &&
 		    strncmp(hdev->name, "ELAN0800", 8) != 0)
 			return true;
+		/* Same with product id 0x0400 */
+		if (hdev->product == 0x0400 &&
+		    strncmp(hdev->name, "QTEC0001", 8) != 0)
+			return true;
 		break;
 	}
 
@@ -1042,7 +1045,7 @@ static struct hid_device_id *hid_exists_dquirk(const struct hid_device *hdev)
 	}
 
 	if (bl_entry != NULL)
-		dbg_hid("Found dynamic quirk 0x%lx for HID device 0x%hx:0x%hx\n",
+		dbg_hid("Found dynamic quirk 0x%lx for HID device 0x%04x:0x%04x\n",
 			bl_entry->driver_data, bl_entry->vendor,
 			bl_entry->product);
 
@@ -1209,7 +1212,7 @@ static unsigned long hid_gets_squirk(const struct hid_device *hdev)
 		quirks |= bl_entry->driver_data;
 
 	if (quirks)
-		dbg_hid("Found squirk 0x%lx for HID device 0x%hx:0x%hx\n",
+		dbg_hid("Found squirk 0x%lx for HID device 0x%04x:0x%04x\n",
 			quirks, hdev->vendor, hdev->product);
 	return quirks;
 }
diff --git a/drivers/hid/hid-steam.c b/drivers/hid/hid-steam.c
index 8141cadfca0e..8dae0f9b819e 100644
--- a/drivers/hid/hid-steam.c
+++ b/drivers/hid/hid-steam.c
@@ -499,6 +499,7 @@ static void steam_battery_unregister(struct steam_device *steam)
 static int steam_register(struct steam_device *steam)
 {
 	int ret;
+	bool client_opened;
 
 	/*
 	 * This function can be called several times in a row with the
@@ -511,9 +512,11 @@ static int steam_register(struct steam_device *steam)
 		 * Unlikely, but getting the serial could fail, and it is not so
 		 * important, so make up a serial number and go on.
 		 */
+		mutex_lock(&steam->mutex);
 		if (steam_get_serial(steam) < 0)
 			strlcpy(steam->serial_no, "XXXXXXXXXX",
 					sizeof(steam->serial_no));
+		mutex_unlock(&steam->mutex);
 
 		hid_info(steam->hdev, "Steam Controller '%s' connected",
 				steam->serial_no);
@@ -528,13 +531,15 @@ static int steam_register(struct steam_device *steam)
 	}
 
 	mutex_lock(&steam->mutex);
-	if (!steam->client_opened) {
+	client_opened = steam->client_opened;
+	if (!client_opened)
 		steam_set_lizard_mode(steam, lizard_mode);
+	mutex_unlock(&steam->mutex);
+
+	if (!client_opened)
 		ret = steam_input_register(steam);
-	} else {
+	else
 		ret = 0;
-	}
-	mutex_unlock(&steam->mutex);
 
 	return ret;
 }
@@ -630,14 +635,21 @@ static void steam_client_ll_close(struct hid_device *hdev)
 {
 	struct steam_device *steam = hdev->driver_data;
 
+	unsigned long flags;
+	bool connected;
+
+	spin_lock_irqsave(&steam->lock, flags);
+	connected = steam->connected;
+	spin_unlock_irqrestore(&steam->lock, flags);
+
 	mutex_lock(&steam->mutex);
 	steam->client_opened = false;
+	if (connected)
+		steam_set_lizard_mode(steam, lizard_mode);
 	mutex_unlock(&steam->mutex);
 
-	if (steam->connected) {
-		steam_set_lizard_mode(steam, lizard_mode);
+	if (connected)
 		steam_input_register(steam);
-	}
 }
 
 static int steam_client_ll_raw_request(struct hid_device *hdev,
diff --git a/drivers/hid/hid-uclogic-params.c b/drivers/hid/hid-uclogic-params.c
index 7710d9f957da..0187c9f8fc22 100644
--- a/drivers/hid/hid-uclogic-params.c
+++ b/drivers/hid/hid-uclogic-params.c
@@ -735,10 +735,6 @@ static int uclogic_params_huion_init(struct uclogic_params *params,
 		goto cleanup;
 	}
 	rc = usb_string(udev, 201, ver_ptr, ver_len);
-	if (ver_ptr == NULL) {
-		rc = -ENOMEM;
-		goto cleanup;
-	}
 	if (rc == -EPIPE) {
 		*ver_ptr = '\0';
 	} else if (rc < 0) {
diff --git a/drivers/hid/i2c-hid/i2c-hid-core.c b/drivers/hid/i2c-hid/i2c-hid-core.c
index 90164fed08d3..4d1f24ee249c 100644
--- a/drivers/hid/i2c-hid/i2c-hid-core.c
+++ b/drivers/hid/i2c-hid/i2c-hid-core.c
@@ -184,6 +184,8 @@ static const struct i2c_hid_quirks {
 		I2C_HID_QUIRK_NO_RUNTIME_PM },
 	{ USB_VENDOR_ID_ELAN, HID_ANY_ID,
 		 I2C_HID_QUIRK_BOGUS_IRQ },
+	{ USB_VENDOR_ID_SYNAPTICS, I2C_DEVICE_ID_SYNAPTICS_7E7E,
+		I2C_HID_QUIRK_NO_RUNTIME_PM },
 	{ 0, 0 }
 };
 
diff --git a/drivers/hwmon/Kconfig b/drivers/hwmon/Kconfig
index 6f929bfa9fcd..1915a18b537b 100644
--- a/drivers/hwmon/Kconfig
+++ b/drivers/hwmon/Kconfig
@@ -17,7 +17,7 @@ menuconfig HWMON
 
 	  To find out which specific driver(s) you need, use the
 	  sensors-detect script from the lm_sensors package.  Read
-	  <file:Documentation/hwmon/userspace-tools> for details.
+	  <file:Documentation/hwmon/userspace-tools.rst> for details.
 
 	  This support can also be built as a module. If so, the module
 	  will be called hwmon.
@@ -59,7 +59,7 @@ config SENSORS_ABITUGURU
 	  chip can be found on Abit uGuru featuring motherboards (most modern
 	  Abit motherboards from before end 2005). For more info and a list
 	  of which motherboards have which revision see
-	  Documentation/hwmon/abituguru
+	  Documentation/hwmon/abituguru.rst
 
 	  This driver can also be built as a module. If so, the module
 	  will be called abituguru.
@@ -73,7 +73,7 @@ config SENSORS_ABITUGURU3
 	  and their settings is supported. The third revision of the Abit
 	  uGuru chip can be found on recent Abit motherboards (since end
 	  2005). For more info and a list of which motherboards have which
-	  revision see Documentation/hwmon/abituguru3
+	  revision see Documentation/hwmon/abituguru3.rst
 
 	  This driver can also be built as a module. If so, the module
 	  will be called abituguru3.
@@ -643,7 +643,7 @@ config SENSORS_CORETEMP
 	help
 	  If you say yes here you get support for the temperature
 	  sensor inside your CPU. Most of the family 6 CPUs
-	  are supported. Check Documentation/hwmon/coretemp for details.
+	  are supported. Check Documentation/hwmon/coretemp.rst for details.
 
 config SENSORS_IT87
 	tristate "ITE IT87xx and compatibles"
@@ -705,6 +705,16 @@ config SENSORS_LINEAGE
 	  This driver can also be built as a module. If so, the module
 	  will be called lineage-pem.
 
+config SENSORS_LOCHNAGAR
+	tristate "Lochnagar Hardware Monitor"
+	depends on MFD_LOCHNAGAR
+	help
+	  If you say yes here you get support for Lochnagar 2 temperature,
+	  voltage and current sensors abilities.
+
+	  This driver can also be built as a module.  If so, the module
+	  will be called lochnagar-hwmon.
+
 config SENSORS_LTC2945
 	tristate "Linear Technology LTC2945"
 	depends on I2C
@@ -898,6 +908,7 @@ config SENSORS_MAX6642
 config SENSORS_MAX6650
 	tristate "Maxim MAX6650 sensor chip"
 	depends on I2C
+	depends on THERMAL || THERMAL=n
 	help
 	  If you say yes here you get support for the MAX6650 / MAX6651
 	  sensor chips.
@@ -1759,6 +1770,7 @@ config SENSORS_VT8231
 config SENSORS_W83773G
 	tristate "Nuvoton W83773G"
 	depends on I2C
+	select REGMAP_I2C
 	help
 	  If you say yes here you get support for the Nuvoton W83773G hardware
 	  monitoring chip.
diff --git a/drivers/hwmon/Makefile b/drivers/hwmon/Makefile
index f5c7b442e69e..8db472ea04f0 100644
--- a/drivers/hwmon/Makefile
+++ b/drivers/hwmon/Makefile
@@ -89,6 +89,7 @@ obj-$(CONFIG_SENSORS_JZ4740)	+= jz4740-hwmon.o
 obj-$(CONFIG_SENSORS_K8TEMP)	+= k8temp.o
 obj-$(CONFIG_SENSORS_K10TEMP)	+= k10temp.o
 obj-$(CONFIG_SENSORS_LINEAGE)	+= lineage-pem.o
+obj-$(CONFIG_SENSORS_LOCHNAGAR)	+= lochnagar-hwmon.o
 obj-$(CONFIG_SENSORS_LM63)	+= lm63.o
 obj-$(CONFIG_SENSORS_LM70)	+= lm70.o
 obj-$(CONFIG_SENSORS_LM73)	+= lm73.o
diff --git a/drivers/hwmon/ad7414.c b/drivers/hwmon/ad7414.c
index f13806d731fa..b176da8e92a7 100644
--- a/drivers/hwmon/ad7414.c
+++ b/drivers/hwmon/ad7414.c
@@ -215,7 +215,7 @@ static const struct i2c_device_id ad7414_id[] = {
 };
 MODULE_DEVICE_TABLE(i2c, ad7414_id);
 
-static const struct of_device_id ad7414_of_match[] = {
+static const struct of_device_id __maybe_unused ad7414_of_match[] = {
 	{ .compatible = "ad,ad7414" },
 	{ },
 };
diff --git a/drivers/hwmon/adc128d818.c b/drivers/hwmon/adc128d818.c
index ca794bf904de..e640be442dae 100644
--- a/drivers/hwmon/adc128d818.c
+++ b/drivers/hwmon/adc128d818.c
@@ -521,7 +521,7 @@ static const struct i2c_device_id adc128_id[] = {
 };
 MODULE_DEVICE_TABLE(i2c, adc128_id);
 
-static const struct of_device_id adc128_of_match[] = {
+static const struct of_device_id __maybe_unused adc128_of_match[] = {
 	{ .compatible = "ti,adc128d818" },
 	{ },
 };
diff --git a/drivers/hwmon/adm1025.c b/drivers/hwmon/adm1025.c
index 1e4dad36f5ef..ec437cc9e739 100644
--- a/drivers/hwmon/adm1025.c
+++ b/drivers/hwmon/adm1025.c
@@ -174,7 +174,7 @@ static struct adm1025_data *adm1025_update_device(struct device *dev)
  */
 
 static ssize_t
-show_in(struct device *dev, struct device_attribute *attr, char *buf)
+in_show(struct device *dev, struct device_attribute *attr, char *buf)
 {
 	int index = to_sensor_dev_attr(attr)->index;
 	struct adm1025_data *data = adm1025_update_device(dev);
@@ -183,7 +183,7 @@ show_in(struct device *dev, struct device_attribute *attr, char *buf)
 }
 
 static ssize_t
-show_in_min(struct device *dev, struct device_attribute *attr, char *buf)
+in_min_show(struct device *dev, struct device_attribute *attr, char *buf)
 {
 	int index = to_sensor_dev_attr(attr)->index;
 	struct adm1025_data *data = adm1025_update_device(dev);
@@ -192,7 +192,7 @@ show_in_min(struct device *dev, struct device_attribute *attr, char *buf)
 }
 
 static ssize_t
-show_in_max(struct device *dev, struct device_attribute *attr, char *buf)
+in_max_show(struct device *dev, struct device_attribute *attr, char *buf)
 {
 	int index = to_sensor_dev_attr(attr)->index;
 	struct adm1025_data *data = adm1025_update_device(dev);
@@ -201,7 +201,7 @@ show_in_max(struct device *dev, struct device_attribute *attr, char *buf)
 }
 
 static ssize_t
-show_temp(struct device *dev, struct device_attribute *attr, char *buf)
+temp_show(struct device *dev, struct device_attribute *attr, char *buf)
 {
 	int index = to_sensor_dev_attr(attr)->index;
 	struct adm1025_data *data = adm1025_update_device(dev);
@@ -209,7 +209,7 @@ show_temp(struct device *dev, struct device_attribute *attr, char *buf)
 }
 
 static ssize_t
-show_temp_min(struct device *dev, struct device_attribute *attr, char *buf)
+temp_min_show(struct device *dev, struct device_attribute *attr, char *buf)
 {
 	int index = to_sensor_dev_attr(attr)->index;
 	struct adm1025_data *data = adm1025_update_device(dev);
@@ -217,15 +217,15 @@ show_temp_min(struct device *dev, struct device_attribute *attr, char *buf)
 }
 
 static ssize_t
-show_temp_max(struct device *dev, struct device_attribute *attr, char *buf)
+temp_max_show(struct device *dev, struct device_attribute *attr, char *buf)
 {
 	int index = to_sensor_dev_attr(attr)->index;
 	struct adm1025_data *data = adm1025_update_device(dev);
 	return sprintf(buf, "%d\n", TEMP_FROM_REG(data->temp_max[index]));
 }
 
-static ssize_t set_in_min(struct device *dev, struct device_attribute *attr,
-			  const char *buf, size_t count)
+static ssize_t in_min_store(struct device *dev, struct device_attribute *attr,
+			    const char *buf, size_t count)
 {
 	int index = to_sensor_dev_attr(attr)->index;
 	struct adm1025_data *data = dev_get_drvdata(dev);
@@ -245,8 +245,8 @@ static ssize_t set_in_min(struct device *dev, struct device_attribute *attr,
 	return count;
 }
 
-static ssize_t set_in_max(struct device *dev, struct device_attribute *attr,
-			  const char *buf, size_t count)
+static ssize_t in_max_store(struct device *dev, struct device_attribute *attr,
+			    const char *buf, size_t count)
 {
 	int index = to_sensor_dev_attr(attr)->index;
 	struct adm1025_data *data = dev_get_drvdata(dev);
@@ -266,22 +266,28 @@ static ssize_t set_in_max(struct device *dev, struct device_attribute *attr,
 	return count;
 }
 
-#define set_in(offset) \
-static SENSOR_DEVICE_ATTR(in##offset##_input, S_IRUGO, \
-	show_in, NULL, offset); \
-static SENSOR_DEVICE_ATTR(in##offset##_min, S_IWUSR | S_IRUGO, \
-	show_in_min, set_in_min, offset); \
-static SENSOR_DEVICE_ATTR(in##offset##_max, S_IWUSR | S_IRUGO, \
-	show_in_max, set_in_max, offset)
-set_in(0);
-set_in(1);
-set_in(2);
-set_in(3);
-set_in(4);
-set_in(5);
-
-static ssize_t set_temp_min(struct device *dev, struct device_attribute *attr,
-			    const char *buf, size_t count)
+static SENSOR_DEVICE_ATTR_RO(in0_input, in, 0);
+static SENSOR_DEVICE_ATTR_RW(in0_min, in_min, 0);
+static SENSOR_DEVICE_ATTR_RW(in0_max, in_max, 0);
+static SENSOR_DEVICE_ATTR_RO(in1_input, in, 1);
+static SENSOR_DEVICE_ATTR_RW(in1_min, in_min, 1);
+static SENSOR_DEVICE_ATTR_RW(in1_max, in_max, 1);
+static SENSOR_DEVICE_ATTR_RO(in2_input, in, 2);
+static SENSOR_DEVICE_ATTR_RW(in2_min, in_min, 2);
+static SENSOR_DEVICE_ATTR_RW(in2_max, in_max, 2);
+static SENSOR_DEVICE_ATTR_RO(in3_input, in, 3);
+static SENSOR_DEVICE_ATTR_RW(in3_min, in_min, 3);
+static SENSOR_DEVICE_ATTR_RW(in3_max, in_max, 3);
+static SENSOR_DEVICE_ATTR_RO(in4_input, in, 4);
+static SENSOR_DEVICE_ATTR_RW(in4_min, in_min, 4);
+static SENSOR_DEVICE_ATTR_RW(in4_max, in_max, 4);
+static SENSOR_DEVICE_ATTR_RO(in5_input, in, 5);
+static SENSOR_DEVICE_ATTR_RW(in5_min, in_min, 5);
+static SENSOR_DEVICE_ATTR_RW(in5_max, in_max, 5);
+
+static ssize_t temp_min_store(struct device *dev,
+			      struct device_attribute *attr, const char *buf,
+			      size_t count)
 {
 	int index = to_sensor_dev_attr(attr)->index;
 	struct adm1025_data *data = dev_get_drvdata(dev);
@@ -301,8 +307,9 @@ static ssize_t set_temp_min(struct device *dev, struct device_attribute *attr,
 	return count;
 }
 
-static ssize_t set_temp_max(struct device *dev, struct device_attribute *attr,
-	const char *buf, size_t count)
+static ssize_t temp_max_store(struct device *dev,
+			      struct device_attribute *attr, const char *buf,
+			      size_t count)
 {
 	int index = to_sensor_dev_attr(attr)->index;
 	struct adm1025_data *data = dev_get_drvdata(dev);
@@ -322,15 +329,12 @@ static ssize_t set_temp_max(struct device *dev, struct device_attribute *attr,
 	return count;
 }
 
-#define set_temp(offset) \
-static SENSOR_DEVICE_ATTR(temp##offset##_input, S_IRUGO, \
-	show_temp, NULL, offset - 1); \
-static SENSOR_DEVICE_ATTR(temp##offset##_min, S_IWUSR | S_IRUGO, \
-	show_temp_min, set_temp_min, offset - 1); \
-static SENSOR_DEVICE_ATTR(temp##offset##_max, S_IWUSR | S_IRUGO, \
-	show_temp_max, set_temp_max, offset - 1)
-set_temp(1);
-set_temp(2);
+static SENSOR_DEVICE_ATTR_RO(temp1_input, temp, 0);
+static SENSOR_DEVICE_ATTR_RW(temp1_min, temp_min, 0);
+static SENSOR_DEVICE_ATTR_RW(temp1_max, temp_max, 0);
+static SENSOR_DEVICE_ATTR_RO(temp2_input, temp, 1);
+static SENSOR_DEVICE_ATTR_RW(temp2_min, temp_min, 1);
+static SENSOR_DEVICE_ATTR_RW(temp2_max, temp_max, 1);
 
 static ssize_t
 alarms_show(struct device *dev, struct device_attribute *attr, char *buf)
@@ -341,21 +345,21 @@ alarms_show(struct device *dev, struct device_attribute *attr, char *buf)
 static DEVICE_ATTR_RO(alarms);
 
 static ssize_t
-show_alarm(struct device *dev, struct device_attribute *attr, char *buf)
+alarm_show(struct device *dev, struct device_attribute *attr, char *buf)
 {
 	int bitnr = to_sensor_dev_attr(attr)->index;
 	struct adm1025_data *data = adm1025_update_device(dev);
 	return sprintf(buf, "%u\n", (data->alarms >> bitnr) & 1);
 }
-static SENSOR_DEVICE_ATTR(in0_alarm, S_IRUGO, show_alarm, NULL, 0);
-static SENSOR_DEVICE_ATTR(in1_alarm, S_IRUGO, show_alarm, NULL, 1);
-static SENSOR_DEVICE_ATTR(in2_alarm, S_IRUGO, show_alarm, NULL, 2);
-static SENSOR_DEVICE_ATTR(in3_alarm, S_IRUGO, show_alarm, NULL, 3);
-static SENSOR_DEVICE_ATTR(in4_alarm, S_IRUGO, show_alarm, NULL, 8);
-static SENSOR_DEVICE_ATTR(in5_alarm, S_IRUGO, show_alarm, NULL, 9);
-static SENSOR_DEVICE_ATTR(temp1_alarm, S_IRUGO, show_alarm, NULL, 5);
-static SENSOR_DEVICE_ATTR(temp2_alarm, S_IRUGO, show_alarm, NULL, 4);
-static SENSOR_DEVICE_ATTR(temp1_fault, S_IRUGO, show_alarm, NULL, 14);
+static SENSOR_DEVICE_ATTR_RO(in0_alarm, alarm, 0);
+static SENSOR_DEVICE_ATTR_RO(in1_alarm, alarm, 1);
+static SENSOR_DEVICE_ATTR_RO(in2_alarm, alarm, 2);
+static SENSOR_DEVICE_ATTR_RO(in3_alarm, alarm, 3);
+static SENSOR_DEVICE_ATTR_RO(in4_alarm, alarm, 8);
+static SENSOR_DEVICE_ATTR_RO(in5_alarm, alarm, 9);
+static SENSOR_DEVICE_ATTR_RO(temp1_alarm, alarm, 5);
+static SENSOR_DEVICE_ATTR_RO(temp2_alarm, alarm, 4);
+static SENSOR_DEVICE_ATTR_RO(temp1_fault, alarm, 14);
 
 static ssize_t
 cpu0_vid_show(struct device *dev, struct device_attribute *attr, char *buf)
diff --git a/drivers/hwmon/adm1026.c b/drivers/hwmon/adm1026.c
index e43f09a07cd0..d34a68a11036 100644
--- a/drivers/hwmon/adm1026.c
+++ b/drivers/hwmon/adm1026.c
@@ -477,24 +477,24 @@ static struct adm1026_data *adm1026_update_device(struct device *dev)
 	return data;
 }
 
-static ssize_t show_in(struct device *dev, struct device_attribute *attr,
-		char *buf)
+static ssize_t in_show(struct device *dev, struct device_attribute *attr,
+		       char *buf)
 {
 	struct sensor_device_attribute *sensor_attr = to_sensor_dev_attr(attr);
 	int nr = sensor_attr->index;
 	struct adm1026_data *data = adm1026_update_device(dev);
 	return sprintf(buf, "%d\n", INS_FROM_REG(nr, data->in[nr]));
 }
-static ssize_t show_in_min(struct device *dev, struct device_attribute *attr,
-		char *buf)
+static ssize_t in_min_show(struct device *dev, struct device_attribute *attr,
+			   char *buf)
 {
 	struct sensor_device_attribute *sensor_attr = to_sensor_dev_attr(attr);
 	int nr = sensor_attr->index;
 	struct adm1026_data *data = adm1026_update_device(dev);
 	return sprintf(buf, "%d\n", INS_FROM_REG(nr, data->in_min[nr]));
 }
-static ssize_t set_in_min(struct device *dev, struct device_attribute *attr,
-		const char *buf, size_t count)
+static ssize_t in_min_store(struct device *dev, struct device_attribute *attr,
+			    const char *buf, size_t count)
 {
 	struct sensor_device_attribute *sensor_attr = to_sensor_dev_attr(attr);
 	int nr = sensor_attr->index;
@@ -513,16 +513,16 @@ static ssize_t set_in_min(struct device *dev, struct device_attribute *attr,
 	mutex_unlock(&data->update_lock);
 	return count;
 }
-static ssize_t show_in_max(struct device *dev, struct device_attribute *attr,
-		char *buf)
+static ssize_t in_max_show(struct device *dev, struct device_attribute *attr,
+			   char *buf)
 {
 	struct sensor_device_attribute *sensor_attr = to_sensor_dev_attr(attr);
 	int nr = sensor_attr->index;
 	struct adm1026_data *data = adm1026_update_device(dev);
 	return sprintf(buf, "%d\n", INS_FROM_REG(nr, data->in_max[nr]));
 }
-static ssize_t set_in_max(struct device *dev, struct device_attribute *attr,
-		const char *buf, size_t count)
+static ssize_t in_max_store(struct device *dev, struct device_attribute *attr,
+			    const char *buf, size_t count)
 {
 	struct sensor_device_attribute *sensor_attr = to_sensor_dev_attr(attr);
 	int nr = sensor_attr->index;
@@ -542,48 +542,72 @@ static ssize_t set_in_max(struct device *dev, struct device_attribute *attr,
 	return count;
 }
 
-#define in_reg(offset)						\
-static SENSOR_DEVICE_ATTR(in##offset##_input, S_IRUGO, show_in,	\
-		NULL, offset);					\
-static SENSOR_DEVICE_ATTR(in##offset##_min, S_IRUGO | S_IWUSR,	\
-		show_in_min, set_in_min, offset);		\
-static SENSOR_DEVICE_ATTR(in##offset##_max, S_IRUGO | S_IWUSR,	\
-		show_in_max, set_in_max, offset);
-
-
-in_reg(0);
-in_reg(1);
-in_reg(2);
-in_reg(3);
-in_reg(4);
-in_reg(5);
-in_reg(6);
-in_reg(7);
-in_reg(8);
-in_reg(9);
-in_reg(10);
-in_reg(11);
-in_reg(12);
-in_reg(13);
-in_reg(14);
-in_reg(15);
-
-static ssize_t show_in16(struct device *dev, struct device_attribute *attr,
+static SENSOR_DEVICE_ATTR_RO(in0_input, in, 0);
+static SENSOR_DEVICE_ATTR_RW(in0_min, in_min, 0);
+static SENSOR_DEVICE_ATTR_RW(in0_max, in_max, 0);
+static SENSOR_DEVICE_ATTR_RO(in1_input, in, 1);
+static SENSOR_DEVICE_ATTR_RW(in1_min, in_min, 1);
+static SENSOR_DEVICE_ATTR_RW(in1_max, in_max, 1);
+static SENSOR_DEVICE_ATTR_RO(in2_input, in, 2);
+static SENSOR_DEVICE_ATTR_RW(in2_min, in_min, 2);
+static SENSOR_DEVICE_ATTR_RW(in2_max, in_max, 2);
+static SENSOR_DEVICE_ATTR_RO(in3_input, in, 3);
+static SENSOR_DEVICE_ATTR_RW(in3_min, in_min, 3);
+static SENSOR_DEVICE_ATTR_RW(in3_max, in_max, 3);
+static SENSOR_DEVICE_ATTR_RO(in4_input, in, 4);
+static SENSOR_DEVICE_ATTR_RW(in4_min, in_min, 4);
+static SENSOR_DEVICE_ATTR_RW(in4_max, in_max, 4);
+static SENSOR_DEVICE_ATTR_RO(in5_input, in, 5);
+static SENSOR_DEVICE_ATTR_RW(in5_min, in_min, 5);
+static SENSOR_DEVICE_ATTR_RW(in5_max, in_max, 5);
+static SENSOR_DEVICE_ATTR_RO(in6_input, in, 6);
+static SENSOR_DEVICE_ATTR_RW(in6_min, in_min, 6);
+static SENSOR_DEVICE_ATTR_RW(in6_max, in_max, 6);
+static SENSOR_DEVICE_ATTR_RO(in7_input, in, 7);
+static SENSOR_DEVICE_ATTR_RW(in7_min, in_min, 7);
+static SENSOR_DEVICE_ATTR_RW(in7_max, in_max, 7);
+static SENSOR_DEVICE_ATTR_RO(in8_input, in, 8);
+static SENSOR_DEVICE_ATTR_RW(in8_min, in_min, 8);
+static SENSOR_DEVICE_ATTR_RW(in8_max, in_max, 8);
+static SENSOR_DEVICE_ATTR_RO(in9_input, in, 9);
+static SENSOR_DEVICE_ATTR_RW(in9_min, in_min, 9);
+static SENSOR_DEVICE_ATTR_RW(in9_max, in_max, 9);
+static SENSOR_DEVICE_ATTR_RO(in10_input, in, 10);
+static SENSOR_DEVICE_ATTR_RW(in10_min, in_min, 10);
+static SENSOR_DEVICE_ATTR_RW(in10_max, in_max, 10);
+static SENSOR_DEVICE_ATTR_RO(in11_input, in, 11);
+static SENSOR_DEVICE_ATTR_RW(in11_min, in_min, 11);
+static SENSOR_DEVICE_ATTR_RW(in11_max, in_max, 11);
+static SENSOR_DEVICE_ATTR_RO(in12_input, in, 12);
+static SENSOR_DEVICE_ATTR_RW(in12_min, in_min, 12);
+static SENSOR_DEVICE_ATTR_RW(in12_max, in_max, 12);
+static SENSOR_DEVICE_ATTR_RO(in13_input, in, 13);
+static SENSOR_DEVICE_ATTR_RW(in13_min, in_min, 13);
+static SENSOR_DEVICE_ATTR_RW(in13_max, in_max, 13);
+static SENSOR_DEVICE_ATTR_RO(in14_input, in, 14);
+static SENSOR_DEVICE_ATTR_RW(in14_min, in_min, 14);
+static SENSOR_DEVICE_ATTR_RW(in14_max, in_max, 14);
+static SENSOR_DEVICE_ATTR_RO(in15_input, in, 15);
+static SENSOR_DEVICE_ATTR_RW(in15_min, in_min, 15);
+static SENSOR_DEVICE_ATTR_RW(in15_max, in_max, 15);
+
+static ssize_t in16_show(struct device *dev, struct device_attribute *attr,
 			 char *buf)
 {
 	struct adm1026_data *data = adm1026_update_device(dev);
 	return sprintf(buf, "%d\n", INS_FROM_REG(16, data->in[16]) -
 		NEG12_OFFSET);
 }
-static ssize_t show_in16_min(struct device *dev, struct device_attribute *attr,
-			     char *buf)
+static ssize_t in16_min_show(struct device *dev,
+			     struct device_attribute *attr, char *buf)
 {
 	struct adm1026_data *data = adm1026_update_device(dev);
 	return sprintf(buf, "%d\n", INS_FROM_REG(16, data->in_min[16])
 		- NEG12_OFFSET);
 }
-static ssize_t set_in16_min(struct device *dev, struct device_attribute *attr,
-			    const char *buf, size_t count)
+static ssize_t in16_min_store(struct device *dev,
+			      struct device_attribute *attr, const char *buf,
+			      size_t count)
 {
 	struct adm1026_data *data = dev_get_drvdata(dev);
 	struct i2c_client *client = data->client;
@@ -603,15 +627,16 @@ static ssize_t set_in16_min(struct device *dev, struct device_attribute *attr,
 	mutex_unlock(&data->update_lock);
 	return count;
 }
-static ssize_t show_in16_max(struct device *dev, struct device_attribute *attr,
-			     char *buf)
+static ssize_t in16_max_show(struct device *dev,
+			     struct device_attribute *attr, char *buf)
 {
 	struct adm1026_data *data = adm1026_update_device(dev);
 	return sprintf(buf, "%d\n", INS_FROM_REG(16, data->in_max[16])
 			- NEG12_OFFSET);
 }
-static ssize_t set_in16_max(struct device *dev, struct device_attribute *attr,
-			    const char *buf, size_t count)
+static ssize_t in16_max_store(struct device *dev,
+			      struct device_attribute *attr, const char *buf,
+			      size_t count)
 {
 	struct adm1026_data *data = dev_get_drvdata(dev);
 	struct i2c_client *client = data->client;
@@ -632,17 +657,14 @@ static ssize_t set_in16_max(struct device *dev, struct device_attribute *attr,
 	return count;
 }
 
-static SENSOR_DEVICE_ATTR(in16_input, S_IRUGO, show_in16, NULL, 16);
-static SENSOR_DEVICE_ATTR(in16_min, S_IRUGO | S_IWUSR, show_in16_min,
-			  set_in16_min, 16);
-static SENSOR_DEVICE_ATTR(in16_max, S_IRUGO | S_IWUSR, show_in16_max,
-			  set_in16_max, 16);
-
+static SENSOR_DEVICE_ATTR_RO(in16_input, in16, 16);
+static SENSOR_DEVICE_ATTR_RW(in16_min, in16_min, 16);
+static SENSOR_DEVICE_ATTR_RW(in16_max, in16_max, 16);
 
 /* Now add fan read/write functions */
 
-static ssize_t show_fan(struct device *dev, struct device_attribute *attr,
-		char *buf)
+static ssize_t fan_show(struct device *dev, struct device_attribute *attr,
+			char *buf)
 {
 	struct sensor_device_attribute *sensor_attr = to_sensor_dev_attr(attr);
 	int nr = sensor_attr->index;
@@ -650,8 +672,8 @@ static ssize_t show_fan(struct device *dev, struct device_attribute *attr,
 	return sprintf(buf, "%d\n", FAN_FROM_REG(data->fan[nr],
 		data->fan_div[nr]));
 }
-static ssize_t show_fan_min(struct device *dev, struct device_attribute *attr,
-		char *buf)
+static ssize_t fan_min_show(struct device *dev, struct device_attribute *attr,
+			    char *buf)
 {
 	struct sensor_device_attribute *sensor_attr = to_sensor_dev_attr(attr);
 	int nr = sensor_attr->index;
@@ -659,8 +681,9 @@ static ssize_t show_fan_min(struct device *dev, struct device_attribute *attr,
 	return sprintf(buf, "%d\n", FAN_FROM_REG(data->fan_min[nr],
 		data->fan_div[nr]));
 }
-static ssize_t set_fan_min(struct device *dev, struct device_attribute *attr,
-		const char *buf, size_t count)
+static ssize_t fan_min_store(struct device *dev,
+			     struct device_attribute *attr, const char *buf,
+			     size_t count)
 {
 	struct sensor_device_attribute *sensor_attr = to_sensor_dev_attr(attr);
 	int nr = sensor_attr->index;
@@ -681,20 +704,22 @@ static ssize_t set_fan_min(struct device *dev, struct device_attribute *attr,
 	return count;
 }
 
-#define fan_offset(offset)						\
-static SENSOR_DEVICE_ATTR(fan##offset##_input, S_IRUGO, show_fan, NULL,	\
-		offset - 1);						\
-static SENSOR_DEVICE_ATTR(fan##offset##_min, S_IRUGO | S_IWUSR,		\
-		show_fan_min, set_fan_min, offset - 1);
-
-fan_offset(1);
-fan_offset(2);
-fan_offset(3);
-fan_offset(4);
-fan_offset(5);
-fan_offset(6);
-fan_offset(7);
-fan_offset(8);
+static SENSOR_DEVICE_ATTR_RO(fan1_input, fan, 0);
+static SENSOR_DEVICE_ATTR_RW(fan1_min, fan_min, 0);
+static SENSOR_DEVICE_ATTR_RO(fan2_input, fan, 1);
+static SENSOR_DEVICE_ATTR_RW(fan2_min, fan_min, 1);
+static SENSOR_DEVICE_ATTR_RO(fan3_input, fan, 2);
+static SENSOR_DEVICE_ATTR_RW(fan3_min, fan_min, 2);
+static SENSOR_DEVICE_ATTR_RO(fan4_input, fan, 3);
+static SENSOR_DEVICE_ATTR_RW(fan4_min, fan_min, 3);
+static SENSOR_DEVICE_ATTR_RO(fan5_input, fan, 4);
+static SENSOR_DEVICE_ATTR_RW(fan5_min, fan_min, 4);
+static SENSOR_DEVICE_ATTR_RO(fan6_input, fan, 5);
+static SENSOR_DEVICE_ATTR_RW(fan6_min, fan_min, 5);
+static SENSOR_DEVICE_ATTR_RO(fan7_input, fan, 6);
+static SENSOR_DEVICE_ATTR_RW(fan7_min, fan_min, 6);
+static SENSOR_DEVICE_ATTR_RO(fan8_input, fan, 7);
+static SENSOR_DEVICE_ATTR_RW(fan8_min, fan_min, 7);
 
 /* Adjust fan_min to account for new fan divisor */
 static void fixup_fan_min(struct device *dev, int fan, int old_div)
@@ -715,16 +740,17 @@ static void fixup_fan_min(struct device *dev, int fan, int old_div)
 }
 
 /* Now add fan_div read/write functions */
-static ssize_t show_fan_div(struct device *dev, struct device_attribute *attr,
-		char *buf)
+static ssize_t fan_div_show(struct device *dev, struct device_attribute *attr,
+			    char *buf)
 {
 	struct sensor_device_attribute *sensor_attr = to_sensor_dev_attr(attr);
 	int nr = sensor_attr->index;
 	struct adm1026_data *data = adm1026_update_device(dev);
 	return sprintf(buf, "%d\n", data->fan_div[nr]);
 }
-static ssize_t set_fan_div(struct device *dev, struct device_attribute *attr,
-		const char *buf, size_t count)
+static ssize_t fan_div_store(struct device *dev,
+			     struct device_attribute *attr, const char *buf,
+			     size_t count)
 {
 	struct sensor_device_attribute *sensor_attr = to_sensor_dev_attr(attr);
 	int nr = sensor_attr->index;
@@ -765,38 +791,35 @@ static ssize_t set_fan_div(struct device *dev, struct device_attribute *attr,
 	return count;
 }
 
-#define fan_offset_div(offset)						\
-static SENSOR_DEVICE_ATTR(fan##offset##_div, S_IRUGO | S_IWUSR,		\
-		show_fan_div, set_fan_div, offset - 1);
-
-fan_offset_div(1);
-fan_offset_div(2);
-fan_offset_div(3);
-fan_offset_div(4);
-fan_offset_div(5);
-fan_offset_div(6);
-fan_offset_div(7);
-fan_offset_div(8);
+static SENSOR_DEVICE_ATTR_RW(fan1_div, fan_div, 0);
+static SENSOR_DEVICE_ATTR_RW(fan2_div, fan_div, 1);
+static SENSOR_DEVICE_ATTR_RW(fan3_div, fan_div, 2);
+static SENSOR_DEVICE_ATTR_RW(fan4_div, fan_div, 3);
+static SENSOR_DEVICE_ATTR_RW(fan5_div, fan_div, 4);
+static SENSOR_DEVICE_ATTR_RW(fan6_div, fan_div, 5);
+static SENSOR_DEVICE_ATTR_RW(fan7_div, fan_div, 6);
+static SENSOR_DEVICE_ATTR_RW(fan8_div, fan_div, 7);
 
 /* Temps */
-static ssize_t show_temp(struct device *dev, struct device_attribute *attr,
-		char *buf)
+static ssize_t temp_show(struct device *dev, struct device_attribute *attr,
+			 char *buf)
 {
 	struct sensor_device_attribute *sensor_attr = to_sensor_dev_attr(attr);
 	int nr = sensor_attr->index;
 	struct adm1026_data *data = adm1026_update_device(dev);
 	return sprintf(buf, "%d\n", TEMP_FROM_REG(data->temp[nr]));
 }
-static ssize_t show_temp_min(struct device *dev, struct device_attribute *attr,
-		char *buf)
+static ssize_t temp_min_show(struct device *dev,
+			     struct device_attribute *attr, char *buf)
 {
 	struct sensor_device_attribute *sensor_attr = to_sensor_dev_attr(attr);
 	int nr = sensor_attr->index;
 	struct adm1026_data *data = adm1026_update_device(dev);
 	return sprintf(buf, "%d\n", TEMP_FROM_REG(data->temp_min[nr]));
 }
-static ssize_t set_temp_min(struct device *dev, struct device_attribute *attr,
-		const char *buf, size_t count)
+static ssize_t temp_min_store(struct device *dev,
+			      struct device_attribute *attr, const char *buf,
+			      size_t count)
 {
 	struct sensor_device_attribute *sensor_attr = to_sensor_dev_attr(attr);
 	int nr = sensor_attr->index;
@@ -816,16 +839,17 @@ static ssize_t set_temp_min(struct device *dev, struct device_attribute *attr,
 	mutex_unlock(&data->update_lock);
 	return count;
 }
-static ssize_t show_temp_max(struct device *dev, struct device_attribute *attr,
-		char *buf)
+static ssize_t temp_max_show(struct device *dev,
+			     struct device_attribute *attr, char *buf)
 {
 	struct sensor_device_attribute *sensor_attr = to_sensor_dev_attr(attr);
 	int nr = sensor_attr->index;
 	struct adm1026_data *data = adm1026_update_device(dev);
 	return sprintf(buf, "%d\n", TEMP_FROM_REG(data->temp_max[nr]));
 }
-static ssize_t set_temp_max(struct device *dev, struct device_attribute *attr,
-		const char *buf, size_t count)
+static ssize_t temp_max_store(struct device *dev,
+			      struct device_attribute *attr, const char *buf,
+			      size_t count)
 {
 	struct sensor_device_attribute *sensor_attr = to_sensor_dev_attr(attr);
 	int nr = sensor_attr->index;
@@ -846,30 +870,27 @@ static ssize_t set_temp_max(struct device *dev, struct device_attribute *attr,
 	return count;
 }
 
-#define temp_reg(offset)						\
-static SENSOR_DEVICE_ATTR(temp##offset##_input, S_IRUGO, show_temp,	\
-		NULL, offset - 1);					\
-static SENSOR_DEVICE_ATTR(temp##offset##_min, S_IRUGO | S_IWUSR,	\
-		show_temp_min, set_temp_min, offset - 1);		\
-static SENSOR_DEVICE_ATTR(temp##offset##_max, S_IRUGO | S_IWUSR,	\
-		show_temp_max, set_temp_max, offset - 1);
-
-
-temp_reg(1);
-temp_reg(2);
-temp_reg(3);
-
-static ssize_t show_temp_offset(struct device *dev,
-		struct device_attribute *attr, char *buf)
+static SENSOR_DEVICE_ATTR_RO(temp1_input, temp, 0);
+static SENSOR_DEVICE_ATTR_RW(temp1_min, temp_min, 0);
+static SENSOR_DEVICE_ATTR_RW(temp1_max, temp_max, 0);
+static SENSOR_DEVICE_ATTR_RO(temp2_input, temp, 1);
+static SENSOR_DEVICE_ATTR_RW(temp2_min, temp_min, 1);
+static SENSOR_DEVICE_ATTR_RW(temp2_max, temp_max, 1);
+static SENSOR_DEVICE_ATTR_RO(temp3_input, temp, 2);
+static SENSOR_DEVICE_ATTR_RW(temp3_min, temp_min, 2);
+static SENSOR_DEVICE_ATTR_RW(temp3_max, temp_max, 2);
+
+static ssize_t temp_offset_show(struct device *dev,
+				struct device_attribute *attr, char *buf)
 {
 	struct sensor_device_attribute *sensor_attr = to_sensor_dev_attr(attr);
 	int nr = sensor_attr->index;
 	struct adm1026_data *data = adm1026_update_device(dev);
 	return sprintf(buf, "%d\n", TEMP_FROM_REG(data->temp_offset[nr]));
 }
-static ssize_t set_temp_offset(struct device *dev,
-		struct device_attribute *attr, const char *buf,
-		size_t count)
+static ssize_t temp_offset_store(struct device *dev,
+				 struct device_attribute *attr,
+				 const char *buf, size_t count)
 {
 	struct sensor_device_attribute *sensor_attr = to_sensor_dev_attr(attr);
 	int nr = sensor_attr->index;
@@ -890,16 +911,13 @@ static ssize_t set_temp_offset(struct device *dev,
 	return count;
 }
 
-#define temp_offset_reg(offset)						\
-static SENSOR_DEVICE_ATTR(temp##offset##_offset, S_IRUGO | S_IWUSR,	\
-		show_temp_offset, set_temp_offset, offset - 1);
-
-temp_offset_reg(1);
-temp_offset_reg(2);
-temp_offset_reg(3);
+static SENSOR_DEVICE_ATTR_RW(temp1_offset, temp_offset, 0);
+static SENSOR_DEVICE_ATTR_RW(temp2_offset, temp_offset, 1);
+static SENSOR_DEVICE_ATTR_RW(temp3_offset, temp_offset, 2);
 
-static ssize_t show_temp_auto_point1_temp_hyst(struct device *dev,
-		struct device_attribute *attr, char *buf)
+static ssize_t temp_auto_point1_temp_hyst_show(struct device *dev,
+					       struct device_attribute *attr,
+					       char *buf)
 {
 	struct sensor_device_attribute *sensor_attr = to_sensor_dev_attr(attr);
 	int nr = sensor_attr->index;
@@ -907,8 +925,9 @@ static ssize_t show_temp_auto_point1_temp_hyst(struct device *dev,
 	return sprintf(buf, "%d\n", TEMP_FROM_REG(
 		ADM1026_FAN_ACTIVATION_TEMP_HYST + data->temp_tmin[nr]));
 }
-static ssize_t show_temp_auto_point2_temp(struct device *dev,
-		struct device_attribute *attr, char *buf)
+static ssize_t temp_auto_point2_temp_show(struct device *dev,
+					  struct device_attribute *attr,
+					  char *buf)
 {
 	struct sensor_device_attribute *sensor_attr = to_sensor_dev_attr(attr);
 	int nr = sensor_attr->index;
@@ -916,16 +935,18 @@ static ssize_t show_temp_auto_point2_temp(struct device *dev,
 	return sprintf(buf, "%d\n", TEMP_FROM_REG(data->temp_tmin[nr] +
 		ADM1026_FAN_CONTROL_TEMP_RANGE));
 }
-static ssize_t show_temp_auto_point1_temp(struct device *dev,
-		struct device_attribute *attr, char *buf)
+static ssize_t temp_auto_point1_temp_show(struct device *dev,
+					  struct device_attribute *attr,
+					  char *buf)
 {
 	struct sensor_device_attribute *sensor_attr = to_sensor_dev_attr(attr);
 	int nr = sensor_attr->index;
 	struct adm1026_data *data = adm1026_update_device(dev);
 	return sprintf(buf, "%d\n", TEMP_FROM_REG(data->temp_tmin[nr]));
 }
-static ssize_t set_temp_auto_point1_temp(struct device *dev,
-		struct device_attribute *attr, const char *buf, size_t count)
+static ssize_t temp_auto_point1_temp_store(struct device *dev,
+					   struct device_attribute *attr,
+					   const char *buf, size_t count)
 {
 	struct sensor_device_attribute *sensor_attr = to_sensor_dev_attr(attr);
 	int nr = sensor_attr->index;
@@ -946,18 +967,18 @@ static ssize_t set_temp_auto_point1_temp(struct device *dev,
 	return count;
 }
 
-#define temp_auto_point(offset)						\
-static SENSOR_DEVICE_ATTR(temp##offset##_auto_point1_temp,		\
-		S_IRUGO | S_IWUSR, show_temp_auto_point1_temp,		\
-		set_temp_auto_point1_temp, offset - 1);			\
-static SENSOR_DEVICE_ATTR(temp##offset##_auto_point1_temp_hyst, S_IRUGO,\
-		show_temp_auto_point1_temp_hyst, NULL, offset - 1);	\
-static SENSOR_DEVICE_ATTR(temp##offset##_auto_point2_temp, S_IRUGO,	\
-		show_temp_auto_point2_temp, NULL, offset - 1);
-
-temp_auto_point(1);
-temp_auto_point(2);
-temp_auto_point(3);
+static SENSOR_DEVICE_ATTR_RW(temp1_auto_point1_temp, temp_auto_point1_temp, 0);
+static SENSOR_DEVICE_ATTR_RO(temp1_auto_point1_temp_hyst,
+			     temp_auto_point1_temp_hyst, 0);
+static SENSOR_DEVICE_ATTR_RO(temp1_auto_point2_temp, temp_auto_point2_temp, 0);
+static SENSOR_DEVICE_ATTR_RW(temp2_auto_point1_temp, temp_auto_point1_temp, 1);
+static SENSOR_DEVICE_ATTR_RO(temp2_auto_point1_temp_hyst,
+			     temp_auto_point1_temp_hyst, 1);
+static SENSOR_DEVICE_ATTR_RO(temp2_auto_point2_temp, temp_auto_point2_temp, 1);
+static SENSOR_DEVICE_ATTR_RW(temp3_auto_point1_temp, temp_auto_point1_temp, 2);
+static SENSOR_DEVICE_ATTR_RO(temp3_auto_point1_temp_hyst,
+			     temp_auto_point1_temp_hyst, 2);
+static SENSOR_DEVICE_ATTR_RO(temp3_auto_point2_temp, temp_auto_point2_temp, 2);
 
 static ssize_t show_temp_crit_enable(struct device *dev,
 		struct device_attribute *attr, char *buf)
@@ -988,24 +1009,24 @@ static ssize_t set_temp_crit_enable(struct device *dev,
 	return count;
 }
 
-#define temp_crit_enable(offset)				\
-static DEVICE_ATTR(temp##offset##_crit_enable, S_IRUGO | S_IWUSR, \
-	show_temp_crit_enable, set_temp_crit_enable);
+static DEVICE_ATTR(temp1_crit_enable, 0644, show_temp_crit_enable,
+		   set_temp_crit_enable);
+static DEVICE_ATTR(temp2_crit_enable, 0644, show_temp_crit_enable,
+		   set_temp_crit_enable);
+static DEVICE_ATTR(temp3_crit_enable, 0644, show_temp_crit_enable,
+		   set_temp_crit_enable);
 
-temp_crit_enable(1);
-temp_crit_enable(2);
-temp_crit_enable(3);
-
-static ssize_t show_temp_crit(struct device *dev,
-		struct device_attribute *attr, char *buf)
+static ssize_t temp_crit_show(struct device *dev,
+			      struct device_attribute *attr, char *buf)
 {
 	struct sensor_device_attribute *sensor_attr = to_sensor_dev_attr(attr);
 	int nr = sensor_attr->index;
 	struct adm1026_data *data = adm1026_update_device(dev);
 	return sprintf(buf, "%d\n", TEMP_FROM_REG(data->temp_crit[nr]));
 }
-static ssize_t set_temp_crit(struct device *dev, struct device_attribute *attr,
-		const char *buf, size_t count)
+static ssize_t temp_crit_store(struct device *dev,
+			       struct device_attribute *attr, const char *buf,
+			       size_t count)
 {
 	struct sensor_device_attribute *sensor_attr = to_sensor_dev_attr(attr);
 	int nr = sensor_attr->index;
@@ -1026,13 +1047,9 @@ static ssize_t set_temp_crit(struct device *dev, struct device_attribute *attr,
 	return count;
 }
 
-#define temp_crit_reg(offset)						\
-static SENSOR_DEVICE_ATTR(temp##offset##_crit, S_IRUGO | S_IWUSR,	\
-		show_temp_crit, set_temp_crit, offset - 1);
-
-temp_crit_reg(1);
-temp_crit_reg(2);
-temp_crit_reg(3);
+static SENSOR_DEVICE_ATTR_RW(temp1_crit, temp_crit, 0);
+static SENSOR_DEVICE_ATTR_RW(temp2_crit, temp_crit, 1);
+static SENSOR_DEVICE_ATTR_RW(temp3_crit, temp_crit, 2);
 
 static ssize_t analog_out_show(struct device *dev,
 			       struct device_attribute *attr, char *buf)
@@ -1110,7 +1127,7 @@ static ssize_t alarms_show(struct device *dev, struct device_attribute *attr,
 
 static DEVICE_ATTR_RO(alarms);
 
-static ssize_t show_alarm(struct device *dev, struct device_attribute *attr,
+static ssize_t alarm_show(struct device *dev, struct device_attribute *attr,
 			  char *buf)
 {
 	struct adm1026_data *data = adm1026_update_device(dev);
@@ -1118,34 +1135,34 @@ static ssize_t show_alarm(struct device *dev, struct device_attribute *attr,
 	return sprintf(buf, "%ld\n", (data->alarms >> bitnr) & 1);
 }
 
-static SENSOR_DEVICE_ATTR(temp2_alarm, S_IRUGO, show_alarm, NULL, 0);
-static SENSOR_DEVICE_ATTR(temp3_alarm, S_IRUGO, show_alarm, NULL, 1);
-static SENSOR_DEVICE_ATTR(in9_alarm, S_IRUGO, show_alarm, NULL, 1);
-static SENSOR_DEVICE_ATTR(in11_alarm, S_IRUGO, show_alarm, NULL, 2);
-static SENSOR_DEVICE_ATTR(in12_alarm, S_IRUGO, show_alarm, NULL, 3);
-static SENSOR_DEVICE_ATTR(in13_alarm, S_IRUGO, show_alarm, NULL, 4);
-static SENSOR_DEVICE_ATTR(in14_alarm, S_IRUGO, show_alarm, NULL, 5);
-static SENSOR_DEVICE_ATTR(in15_alarm, S_IRUGO, show_alarm, NULL, 6);
-static SENSOR_DEVICE_ATTR(in16_alarm, S_IRUGO, show_alarm, NULL, 7);
-static SENSOR_DEVICE_ATTR(in0_alarm, S_IRUGO, show_alarm, NULL, 8);
-static SENSOR_DEVICE_ATTR(in1_alarm, S_IRUGO, show_alarm, NULL, 9);
-static SENSOR_DEVICE_ATTR(in2_alarm, S_IRUGO, show_alarm, NULL, 10);
-static SENSOR_DEVICE_ATTR(in3_alarm, S_IRUGO, show_alarm, NULL, 11);
-static SENSOR_DEVICE_ATTR(in4_alarm, S_IRUGO, show_alarm, NULL, 12);
-static SENSOR_DEVICE_ATTR(in5_alarm, S_IRUGO, show_alarm, NULL, 13);
-static SENSOR_DEVICE_ATTR(in6_alarm, S_IRUGO, show_alarm, NULL, 14);
-static SENSOR_DEVICE_ATTR(in7_alarm, S_IRUGO, show_alarm, NULL, 15);
-static SENSOR_DEVICE_ATTR(fan1_alarm, S_IRUGO, show_alarm, NULL, 16);
-static SENSOR_DEVICE_ATTR(fan2_alarm, S_IRUGO, show_alarm, NULL, 17);
-static SENSOR_DEVICE_ATTR(fan3_alarm, S_IRUGO, show_alarm, NULL, 18);
-static SENSOR_DEVICE_ATTR(fan4_alarm, S_IRUGO, show_alarm, NULL, 19);
-static SENSOR_DEVICE_ATTR(fan5_alarm, S_IRUGO, show_alarm, NULL, 20);
-static SENSOR_DEVICE_ATTR(fan6_alarm, S_IRUGO, show_alarm, NULL, 21);
-static SENSOR_DEVICE_ATTR(fan7_alarm, S_IRUGO, show_alarm, NULL, 22);
-static SENSOR_DEVICE_ATTR(fan8_alarm, S_IRUGO, show_alarm, NULL, 23);
-static SENSOR_DEVICE_ATTR(temp1_alarm, S_IRUGO, show_alarm, NULL, 24);
-static SENSOR_DEVICE_ATTR(in10_alarm, S_IRUGO, show_alarm, NULL, 25);
-static SENSOR_DEVICE_ATTR(in8_alarm, S_IRUGO, show_alarm, NULL, 26);
+static SENSOR_DEVICE_ATTR_RO(temp2_alarm, alarm, 0);
+static SENSOR_DEVICE_ATTR_RO(temp3_alarm, alarm, 1);
+static SENSOR_DEVICE_ATTR_RO(in9_alarm, alarm, 1);
+static SENSOR_DEVICE_ATTR_RO(in11_alarm, alarm, 2);
+static SENSOR_DEVICE_ATTR_RO(in12_alarm, alarm, 3);
+static SENSOR_DEVICE_ATTR_RO(in13_alarm, alarm, 4);
+static SENSOR_DEVICE_ATTR_RO(in14_alarm, alarm, 5);
+static SENSOR_DEVICE_ATTR_RO(in15_alarm, alarm, 6);
+static SENSOR_DEVICE_ATTR_RO(in16_alarm, alarm, 7);
+static SENSOR_DEVICE_ATTR_RO(in0_alarm, alarm, 8);
+static SENSOR_DEVICE_ATTR_RO(in1_alarm, alarm, 9);
+static SENSOR_DEVICE_ATTR_RO(in2_alarm, alarm, 10);
+static SENSOR_DEVICE_ATTR_RO(in3_alarm, alarm, 11);
+static SENSOR_DEVICE_ATTR_RO(in4_alarm, alarm, 12);
+static SENSOR_DEVICE_ATTR_RO(in5_alarm, alarm, 13);
+static SENSOR_DEVICE_ATTR_RO(in6_alarm, alarm, 14);
+static SENSOR_DEVICE_ATTR_RO(in7_alarm, alarm, 15);
+static SENSOR_DEVICE_ATTR_RO(fan1_alarm, alarm, 16);
+static SENSOR_DEVICE_ATTR_RO(fan2_alarm, alarm, 17);
+static SENSOR_DEVICE_ATTR_RO(fan3_alarm, alarm, 18);
+static SENSOR_DEVICE_ATTR_RO(fan4_alarm, alarm, 19);
+static SENSOR_DEVICE_ATTR_RO(fan5_alarm, alarm, 20);
+static SENSOR_DEVICE_ATTR_RO(fan6_alarm, alarm, 21);
+static SENSOR_DEVICE_ATTR_RO(fan7_alarm, alarm, 22);
+static SENSOR_DEVICE_ATTR_RO(fan8_alarm, alarm, 23);
+static SENSOR_DEVICE_ATTR_RO(temp1_alarm, alarm, 24);
+static SENSOR_DEVICE_ATTR_RO(in10_alarm, alarm, 25);
+static SENSOR_DEVICE_ATTR_RO(in8_alarm, alarm, 26);
 
 static ssize_t alarm_mask_show(struct device *dev,
 			       struct device_attribute *attr, char *buf)
@@ -1188,7 +1205,6 @@ static ssize_t alarm_mask_store(struct device *dev,
 
 static DEVICE_ATTR_RW(alarm_mask);
 
-
 static ssize_t gpio_show(struct device *dev, struct device_attribute *attr,
 			 char *buf)
 {
@@ -1371,23 +1387,23 @@ static ssize_t pwm1_enable_store(struct device *dev,
 
 /* enable PWM fan control */
 static DEVICE_ATTR_RW(pwm1);
-static DEVICE_ATTR(pwm2, S_IRUGO | S_IWUSR, pwm1_show, pwm1_store);
-static DEVICE_ATTR(pwm3, S_IRUGO | S_IWUSR, pwm1_show, pwm1_store);
+static DEVICE_ATTR(pwm2, 0644, pwm1_show, pwm1_store);
+static DEVICE_ATTR(pwm3, 0644, pwm1_show, pwm1_store);
 static DEVICE_ATTR_RW(pwm1_enable);
-static DEVICE_ATTR(pwm2_enable, S_IRUGO | S_IWUSR, pwm1_enable_show,
+static DEVICE_ATTR(pwm2_enable, 0644, pwm1_enable_show,
 		   pwm1_enable_store);
-static DEVICE_ATTR(pwm3_enable, S_IRUGO | S_IWUSR, pwm1_enable_show,
+static DEVICE_ATTR(pwm3_enable, 0644, pwm1_enable_show,
 		   pwm1_enable_store);
 static DEVICE_ATTR_RW(temp1_auto_point1_pwm);
-static DEVICE_ATTR(temp2_auto_point1_pwm, S_IRUGO | S_IWUSR,
-	temp1_auto_point1_pwm_show, temp1_auto_point1_pwm_store);
-static DEVICE_ATTR(temp3_auto_point1_pwm, S_IRUGO | S_IWUSR,
-	temp1_auto_point1_pwm_show, temp1_auto_point1_pwm_store);
+static DEVICE_ATTR(temp2_auto_point1_pwm, 0644,
+		   temp1_auto_point1_pwm_show, temp1_auto_point1_pwm_store);
+static DEVICE_ATTR(temp3_auto_point1_pwm, 0644,
+		   temp1_auto_point1_pwm_show, temp1_auto_point1_pwm_store);
 
 static DEVICE_ATTR_RO(temp1_auto_point2_pwm);
-static DEVICE_ATTR(temp2_auto_point2_pwm, S_IRUGO, temp1_auto_point2_pwm_show,
+static DEVICE_ATTR(temp2_auto_point2_pwm, 0444, temp1_auto_point2_pwm_show,
 		   NULL);
-static DEVICE_ATTR(temp3_auto_point2_pwm, S_IRUGO, temp1_auto_point2_pwm_show,
+static DEVICE_ATTR(temp3_auto_point2_pwm, 0444, temp1_auto_point2_pwm_show,
 		   NULL);
 
 static struct attribute *adm1026_attributes[] = {
diff --git a/drivers/hwmon/adm1029.c b/drivers/hwmon/adm1029.c
index e561279aea21..388060ff85e7 100644
--- a/drivers/hwmon/adm1029.c
+++ b/drivers/hwmon/adm1029.c
@@ -166,7 +166,7 @@ static struct adm1029_data *adm1029_update_device(struct device *dev)
  */
 
 static ssize_t
-show_temp(struct device *dev, struct device_attribute *devattr, char *buf)
+temp_show(struct device *dev, struct device_attribute *devattr, char *buf)
 {
 	struct sensor_device_attribute *attr = to_sensor_dev_attr(devattr);
 	struct adm1029_data *data = adm1029_update_device(dev);
@@ -175,7 +175,7 @@ show_temp(struct device *dev, struct device_attribute *devattr, char *buf)
 }
 
 static ssize_t
-show_fan(struct device *dev, struct device_attribute *devattr, char *buf)
+fan_show(struct device *dev, struct device_attribute *devattr, char *buf)
 {
 	struct sensor_device_attribute *attr = to_sensor_dev_attr(devattr);
 	struct adm1029_data *data = adm1029_update_device(dev);
@@ -193,7 +193,7 @@ show_fan(struct device *dev, struct device_attribute *devattr, char *buf)
 }
 
 static ssize_t
-show_fan_div(struct device *dev, struct device_attribute *devattr, char *buf)
+fan_div_show(struct device *dev, struct device_attribute *devattr, char *buf)
 {
 	struct sensor_device_attribute *attr = to_sensor_dev_attr(devattr);
 	struct adm1029_data *data = adm1029_update_device(dev);
@@ -203,8 +203,9 @@ show_fan_div(struct device *dev, struct device_attribute *devattr, char *buf)
 	return sprintf(buf, "%d\n", DIV_FROM_REG(data->fan_div[attr->index]));
 }
 
-static ssize_t set_fan_div(struct device *dev, struct device_attribute *devattr,
-			   const char *buf, size_t count)
+static ssize_t fan_div_store(struct device *dev,
+			     struct device_attribute *devattr,
+			     const char *buf, size_t count)
 {
 	struct adm1029_data *data = dev_get_drvdata(dev);
 	struct i2c_client *client = data->client;
@@ -254,26 +255,26 @@ static ssize_t set_fan_div(struct device *dev, struct device_attribute *devattr,
 }
 
 /* Access rights on sysfs. */
-static SENSOR_DEVICE_ATTR(temp1_input, 0444, show_temp, NULL, 0);
-static SENSOR_DEVICE_ATTR(temp2_input, 0444, show_temp, NULL, 1);
-static SENSOR_DEVICE_ATTR(temp3_input, 0444, show_temp, NULL, 2);
+static SENSOR_DEVICE_ATTR_RO(temp1_input, temp, 0);
+static SENSOR_DEVICE_ATTR_RO(temp2_input, temp, 1);
+static SENSOR_DEVICE_ATTR_RO(temp3_input, temp, 2);
 
-static SENSOR_DEVICE_ATTR(temp1_max, 0444, show_temp, NULL, 3);
-static SENSOR_DEVICE_ATTR(temp2_max, 0444, show_temp, NULL, 4);
-static SENSOR_DEVICE_ATTR(temp3_max, 0444, show_temp, NULL, 5);
+static SENSOR_DEVICE_ATTR_RO(temp1_max, temp, 3);
+static SENSOR_DEVICE_ATTR_RO(temp2_max, temp, 4);
+static SENSOR_DEVICE_ATTR_RO(temp3_max, temp, 5);
 
-static SENSOR_DEVICE_ATTR(temp1_min, 0444, show_temp, NULL, 6);
-static SENSOR_DEVICE_ATTR(temp2_min, 0444, show_temp, NULL, 7);
-static SENSOR_DEVICE_ATTR(temp3_min, 0444, show_temp, NULL, 8);
+static SENSOR_DEVICE_ATTR_RO(temp1_min, temp, 6);
+static SENSOR_DEVICE_ATTR_RO(temp2_min, temp, 7);
+static SENSOR_DEVICE_ATTR_RO(temp3_min, temp, 8);
 
-static SENSOR_DEVICE_ATTR(fan1_input, 0444, show_fan, NULL, 0);
-static SENSOR_DEVICE_ATTR(fan2_input, 0444, show_fan, NULL, 1);
+static SENSOR_DEVICE_ATTR_RO(fan1_input, fan, 0);
+static SENSOR_DEVICE_ATTR_RO(fan2_input, fan, 1);
 
-static SENSOR_DEVICE_ATTR(fan1_min, 0444, show_fan, NULL, 2);
-static SENSOR_DEVICE_ATTR(fan2_min, 0444, show_fan, NULL, 3);
+static SENSOR_DEVICE_ATTR_RO(fan1_min, fan, 2);
+static SENSOR_DEVICE_ATTR_RO(fan2_min, fan, 3);
 
-static SENSOR_DEVICE_ATTR(fan1_div, 0644, show_fan_div, set_fan_div, 0);
-static SENSOR_DEVICE_ATTR(fan2_div, 0644, show_fan_div, set_fan_div, 1);
+static SENSOR_DEVICE_ATTR_RW(fan1_div, fan_div, 0);
+static SENSOR_DEVICE_ATTR_RW(fan2_div, fan_div, 1);
 
 static struct attribute *adm1029_attrs[] = {
 	&sensor_dev_attr_temp1_input.dev_attr.attr,
diff --git a/drivers/hwmon/adm1031.c b/drivers/hwmon/adm1031.c
index bcf508269fd6..6b46d8eaa775 100644
--- a/drivers/hwmon/adm1031.c
+++ b/drivers/hwmon/adm1031.c
@@ -331,7 +331,7 @@ get_fan_auto_nearest(struct adm1031_data *data, int chan, u8 val, u8 reg)
 	return -EINVAL;
 }
 
-static ssize_t show_fan_auto_channel(struct device *dev,
+static ssize_t fan_auto_channel_show(struct device *dev,
 				     struct device_attribute *attr, char *buf)
 {
 	int nr = to_sensor_dev_attr(attr)->index;
@@ -340,8 +340,8 @@ static ssize_t show_fan_auto_channel(struct device *dev,
 }
 
 static ssize_t
-set_fan_auto_channel(struct device *dev, struct device_attribute *attr,
-		     const char *buf, size_t count)
+fan_auto_channel_store(struct device *dev, struct device_attribute *attr,
+		       const char *buf, size_t count)
 {
 	struct adm1031_data *data = dev_get_drvdata(dev);
 	struct i2c_client *client = data->client;
@@ -392,13 +392,11 @@ set_fan_auto_channel(struct device *dev, struct device_attribute *attr,
 	return count;
 }
 
-static SENSOR_DEVICE_ATTR(auto_fan1_channel, S_IRUGO | S_IWUSR,
-		show_fan_auto_channel, set_fan_auto_channel, 0);
-static SENSOR_DEVICE_ATTR(auto_fan2_channel, S_IRUGO | S_IWUSR,
-		show_fan_auto_channel, set_fan_auto_channel, 1);
+static SENSOR_DEVICE_ATTR_RW(auto_fan1_channel, fan_auto_channel, 0);
+static SENSOR_DEVICE_ATTR_RW(auto_fan2_channel, fan_auto_channel, 1);
 
 /* Auto Temps */
-static ssize_t show_auto_temp_off(struct device *dev,
+static ssize_t auto_temp_off_show(struct device *dev,
 				  struct device_attribute *attr, char *buf)
 {
 	int nr = to_sensor_dev_attr(attr)->index;
@@ -406,7 +404,7 @@ static ssize_t show_auto_temp_off(struct device *dev,
 	return sprintf(buf, "%d\n",
 		       AUTO_TEMP_OFF_FROM_REG(data->auto_temp[nr]));
 }
-static ssize_t show_auto_temp_min(struct device *dev,
+static ssize_t auto_temp_min_show(struct device *dev,
 				  struct device_attribute *attr, char *buf)
 {
 	int nr = to_sensor_dev_attr(attr)->index;
@@ -415,8 +413,8 @@ static ssize_t show_auto_temp_min(struct device *dev,
 		       AUTO_TEMP_MIN_FROM_REG(data->auto_temp[nr]));
 }
 static ssize_t
-set_auto_temp_min(struct device *dev, struct device_attribute *attr,
-		  const char *buf, size_t count)
+auto_temp_min_store(struct device *dev, struct device_attribute *attr,
+		    const char *buf, size_t count)
 {
 	struct adm1031_data *data = dev_get_drvdata(dev);
 	struct i2c_client *client = data->client;
@@ -436,7 +434,7 @@ set_auto_temp_min(struct device *dev, struct device_attribute *attr,
 	mutex_unlock(&data->update_lock);
 	return count;
 }
-static ssize_t show_auto_temp_max(struct device *dev,
+static ssize_t auto_temp_max_show(struct device *dev,
 				  struct device_attribute *attr, char *buf)
 {
 	int nr = to_sensor_dev_attr(attr)->index;
@@ -445,8 +443,8 @@ static ssize_t show_auto_temp_max(struct device *dev,
 		       AUTO_TEMP_MAX_FROM_REG(data->auto_temp[nr]));
 }
 static ssize_t
-set_auto_temp_max(struct device *dev, struct device_attribute *attr,
-		  const char *buf, size_t count)
+auto_temp_max_store(struct device *dev, struct device_attribute *attr,
+		    const char *buf, size_t count)
 {
 	struct adm1031_data *data = dev_get_drvdata(dev);
 	struct i2c_client *client = data->client;
@@ -468,28 +466,26 @@ set_auto_temp_max(struct device *dev, struct device_attribute *attr,
 	return count;
 }
 
-#define auto_temp_reg(offset)						\
-static SENSOR_DEVICE_ATTR(auto_temp##offset##_off, S_IRUGO,		\
-		show_auto_temp_off, NULL, offset - 1);			\
-static SENSOR_DEVICE_ATTR(auto_temp##offset##_min, S_IRUGO | S_IWUSR,	\
-		show_auto_temp_min, set_auto_temp_min, offset - 1);	\
-static SENSOR_DEVICE_ATTR(auto_temp##offset##_max, S_IRUGO | S_IWUSR,	\
-		show_auto_temp_max, set_auto_temp_max, offset - 1)
-
-auto_temp_reg(1);
-auto_temp_reg(2);
-auto_temp_reg(3);
+static SENSOR_DEVICE_ATTR_RO(auto_temp1_off, auto_temp_off, 0);
+static SENSOR_DEVICE_ATTR_RW(auto_temp1_min, auto_temp_min, 0);
+static SENSOR_DEVICE_ATTR_RW(auto_temp1_max, auto_temp_max, 0);
+static SENSOR_DEVICE_ATTR_RO(auto_temp2_off, auto_temp_off, 1);
+static SENSOR_DEVICE_ATTR_RW(auto_temp2_min, auto_temp_min, 1);
+static SENSOR_DEVICE_ATTR_RW(auto_temp2_max, auto_temp_max, 1);
+static SENSOR_DEVICE_ATTR_RO(auto_temp3_off, auto_temp_off, 2);
+static SENSOR_DEVICE_ATTR_RW(auto_temp3_min, auto_temp_min, 2);
+static SENSOR_DEVICE_ATTR_RW(auto_temp3_max, auto_temp_max, 2);
 
 /* pwm */
-static ssize_t show_pwm(struct device *dev,
-			struct device_attribute *attr, char *buf)
+static ssize_t pwm_show(struct device *dev, struct device_attribute *attr,
+			char *buf)
 {
 	int nr = to_sensor_dev_attr(attr)->index;
 	struct adm1031_data *data = adm1031_update_device(dev);
 	return sprintf(buf, "%d\n", PWM_FROM_REG(data->pwm[nr]));
 }
-static ssize_t set_pwm(struct device *dev, struct device_attribute *attr,
-		       const char *buf, size_t count)
+static ssize_t pwm_store(struct device *dev, struct device_attribute *attr,
+			 const char *buf, size_t count)
 {
 	struct adm1031_data *data = dev_get_drvdata(dev);
 	struct i2c_client *client = data->client;
@@ -517,12 +513,10 @@ static ssize_t set_pwm(struct device *dev, struct device_attribute *attr,
 	return count;
 }
 
-static SENSOR_DEVICE_ATTR(pwm1, S_IRUGO | S_IWUSR, show_pwm, set_pwm, 0);
-static SENSOR_DEVICE_ATTR(pwm2, S_IRUGO | S_IWUSR, show_pwm, set_pwm, 1);
-static SENSOR_DEVICE_ATTR(auto_fan1_min_pwm, S_IRUGO | S_IWUSR,
-		show_pwm, set_pwm, 0);
-static SENSOR_DEVICE_ATTR(auto_fan2_min_pwm, S_IRUGO | S_IWUSR,
-		show_pwm, set_pwm, 1);
+static SENSOR_DEVICE_ATTR_RW(pwm1, pwm, 0);
+static SENSOR_DEVICE_ATTR_RW(pwm2, pwm, 1);
+static SENSOR_DEVICE_ATTR_RW(auto_fan1_min_pwm, pwm, 0);
+static SENSOR_DEVICE_ATTR_RW(auto_fan2_min_pwm, pwm, 1);
 
 /* Fans */
 
@@ -572,9 +566,8 @@ static int trust_fan_readings(struct adm1031_data *data, int chan)
 	return res;
 }
 
-
-static ssize_t show_fan(struct device *dev,
-			struct device_attribute *attr, char *buf)
+static ssize_t fan_show(struct device *dev, struct device_attribute *attr,
+			char *buf)
 {
 	int nr = to_sensor_dev_attr(attr)->index;
 	struct adm1031_data *data = adm1031_update_device(dev);
@@ -585,15 +578,15 @@ static ssize_t show_fan(struct device *dev,
 	return sprintf(buf, "%d\n", value);
 }
 
-static ssize_t show_fan_div(struct device *dev,
-			    struct device_attribute *attr, char *buf)
+static ssize_t fan_div_show(struct device *dev, struct device_attribute *attr,
+			    char *buf)
 {
 	int nr = to_sensor_dev_attr(attr)->index;
 	struct adm1031_data *data = adm1031_update_device(dev);
 	return sprintf(buf, "%d\n", FAN_DIV_FROM_REG(data->fan_div[nr]));
 }
-static ssize_t show_fan_min(struct device *dev,
-			    struct device_attribute *attr, char *buf)
+static ssize_t fan_min_show(struct device *dev, struct device_attribute *attr,
+			    char *buf)
 {
 	int nr = to_sensor_dev_attr(attr)->index;
 	struct adm1031_data *data = adm1031_update_device(dev);
@@ -601,8 +594,9 @@ static ssize_t show_fan_min(struct device *dev,
 		       FAN_FROM_REG(data->fan_min[nr],
 				    FAN_DIV_FROM_REG(data->fan_div[nr])));
 }
-static ssize_t set_fan_min(struct device *dev, struct device_attribute *attr,
-			   const char *buf, size_t count)
+static ssize_t fan_min_store(struct device *dev,
+			     struct device_attribute *attr, const char *buf,
+			     size_t count)
 {
 	struct adm1031_data *data = dev_get_drvdata(dev);
 	struct i2c_client *client = data->client;
@@ -625,8 +619,9 @@ static ssize_t set_fan_min(struct device *dev, struct device_attribute *attr,
 	mutex_unlock(&data->update_lock);
 	return count;
 }
-static ssize_t set_fan_div(struct device *dev, struct device_attribute *attr,
-			   const char *buf, size_t count)
+static ssize_t fan_div_store(struct device *dev,
+			     struct device_attribute *attr, const char *buf,
+			     size_t count)
 {
 	struct adm1031_data *data = dev_get_drvdata(dev);
 	struct i2c_client *client = data->client;
@@ -673,21 +668,16 @@ static ssize_t set_fan_div(struct device *dev, struct device_attribute *attr,
 	return count;
 }
 
-#define fan_offset(offset)						\
-static SENSOR_DEVICE_ATTR(fan##offset##_input, S_IRUGO,			\
-		show_fan, NULL, offset - 1);				\
-static SENSOR_DEVICE_ATTR(fan##offset##_min, S_IRUGO | S_IWUSR,		\
-		show_fan_min, set_fan_min, offset - 1);			\
-static SENSOR_DEVICE_ATTR(fan##offset##_div, S_IRUGO | S_IWUSR,		\
-		show_fan_div, set_fan_div, offset - 1)
-
-fan_offset(1);
-fan_offset(2);
-
+static SENSOR_DEVICE_ATTR_RO(fan1_input, fan, 0);
+static SENSOR_DEVICE_ATTR_RW(fan1_min, fan_min, 0);
+static SENSOR_DEVICE_ATTR_RW(fan1_div, fan_div, 0);
+static SENSOR_DEVICE_ATTR_RO(fan2_input, fan, 1);
+static SENSOR_DEVICE_ATTR_RW(fan2_min, fan_min, 1);
+static SENSOR_DEVICE_ATTR_RW(fan2_div, fan_div, 1);
 
 /* Temps */
-static ssize_t show_temp(struct device *dev,
-			 struct device_attribute *attr, char *buf)
+static ssize_t temp_show(struct device *dev, struct device_attribute *attr,
+			 char *buf)
 {
 	int nr = to_sensor_dev_attr(attr)->index;
 	struct adm1031_data *data = adm1031_update_device(dev);
@@ -697,7 +687,7 @@ static ssize_t show_temp(struct device *dev,
 	    (((data->ext_temp[nr] >> ((nr - 1) * 3)) & 7));
 	return sprintf(buf, "%d\n", TEMP_FROM_REG_EXT(data->temp[nr], ext));
 }
-static ssize_t show_temp_offset(struct device *dev,
+static ssize_t temp_offset_show(struct device *dev,
 				struct device_attribute *attr, char *buf)
 {
 	int nr = to_sensor_dev_attr(attr)->index;
@@ -705,30 +695,30 @@ static ssize_t show_temp_offset(struct device *dev,
 	return sprintf(buf, "%d\n",
 		       TEMP_OFFSET_FROM_REG(data->temp_offset[nr]));
 }
-static ssize_t show_temp_min(struct device *dev,
+static ssize_t temp_min_show(struct device *dev,
 			     struct device_attribute *attr, char *buf)
 {
 	int nr = to_sensor_dev_attr(attr)->index;
 	struct adm1031_data *data = adm1031_update_device(dev);
 	return sprintf(buf, "%d\n", TEMP_FROM_REG(data->temp_min[nr]));
 }
-static ssize_t show_temp_max(struct device *dev,
+static ssize_t temp_max_show(struct device *dev,
 			     struct device_attribute *attr, char *buf)
 {
 	int nr = to_sensor_dev_attr(attr)->index;
 	struct adm1031_data *data = adm1031_update_device(dev);
 	return sprintf(buf, "%d\n", TEMP_FROM_REG(data->temp_max[nr]));
 }
-static ssize_t show_temp_crit(struct device *dev,
+static ssize_t temp_crit_show(struct device *dev,
 			      struct device_attribute *attr, char *buf)
 {
 	int nr = to_sensor_dev_attr(attr)->index;
 	struct adm1031_data *data = adm1031_update_device(dev);
 	return sprintf(buf, "%d\n", TEMP_FROM_REG(data->temp_crit[nr]));
 }
-static ssize_t set_temp_offset(struct device *dev,
-			       struct device_attribute *attr, const char *buf,
-			       size_t count)
+static ssize_t temp_offset_store(struct device *dev,
+				 struct device_attribute *attr,
+				 const char *buf, size_t count)
 {
 	struct adm1031_data *data = dev_get_drvdata(dev);
 	struct i2c_client *client = data->client;
@@ -748,8 +738,9 @@ static ssize_t set_temp_offset(struct device *dev,
 	mutex_unlock(&data->update_lock);
 	return count;
 }
-static ssize_t set_temp_min(struct device *dev, struct device_attribute *attr,
-			    const char *buf, size_t count)
+static ssize_t temp_min_store(struct device *dev,
+			      struct device_attribute *attr, const char *buf,
+			      size_t count)
 {
 	struct adm1031_data *data = dev_get_drvdata(dev);
 	struct i2c_client *client = data->client;
@@ -769,8 +760,9 @@ static ssize_t set_temp_min(struct device *dev, struct device_attribute *attr,
 	mutex_unlock(&data->update_lock);
 	return count;
 }
-static ssize_t set_temp_max(struct device *dev, struct device_attribute *attr,
-			    const char *buf, size_t count)
+static ssize_t temp_max_store(struct device *dev,
+			      struct device_attribute *attr, const char *buf,
+			      size_t count)
 {
 	struct adm1031_data *data = dev_get_drvdata(dev);
 	struct i2c_client *client = data->client;
@@ -790,8 +782,9 @@ static ssize_t set_temp_max(struct device *dev, struct device_attribute *attr,
 	mutex_unlock(&data->update_lock);
 	return count;
 }
-static ssize_t set_temp_crit(struct device *dev, struct device_attribute *attr,
-			     const char *buf, size_t count)
+static ssize_t temp_crit_store(struct device *dev,
+			       struct device_attribute *attr, const char *buf,
+			       size_t count)
 {
 	struct adm1031_data *data = dev_get_drvdata(dev);
 	struct i2c_client *client = data->client;
@@ -812,21 +805,21 @@ static ssize_t set_temp_crit(struct device *dev, struct device_attribute *attr,
 	return count;
 }
 
-#define temp_reg(offset)						\
-static SENSOR_DEVICE_ATTR(temp##offset##_input, S_IRUGO,		\
-		show_temp, NULL, offset - 1);				\
-static SENSOR_DEVICE_ATTR(temp##offset##_offset, S_IRUGO | S_IWUSR,	\
-		show_temp_offset, set_temp_offset, offset - 1);		\
-static SENSOR_DEVICE_ATTR(temp##offset##_min, S_IRUGO | S_IWUSR,	\
-		show_temp_min, set_temp_min, offset - 1);		\
-static SENSOR_DEVICE_ATTR(temp##offset##_max, S_IRUGO | S_IWUSR,	\
-		show_temp_max, set_temp_max, offset - 1);		\
-static SENSOR_DEVICE_ATTR(temp##offset##_crit, S_IRUGO | S_IWUSR,	\
-		show_temp_crit, set_temp_crit, offset - 1)
-
-temp_reg(1);
-temp_reg(2);
-temp_reg(3);
+static SENSOR_DEVICE_ATTR_RO(temp1_input, temp, 0);
+static SENSOR_DEVICE_ATTR_RW(temp1_offset, temp_offset, 0);
+static SENSOR_DEVICE_ATTR_RW(temp1_min, temp_min, 0);
+static SENSOR_DEVICE_ATTR_RW(temp1_max, temp_max, 0);
+static SENSOR_DEVICE_ATTR_RW(temp1_crit, temp_crit, 0);
+static SENSOR_DEVICE_ATTR_RO(temp2_input, temp, 1);
+static SENSOR_DEVICE_ATTR_RW(temp2_offset, temp_offset, 1);
+static SENSOR_DEVICE_ATTR_RW(temp2_min, temp_min, 1);
+static SENSOR_DEVICE_ATTR_RW(temp2_max, temp_max, 1);
+static SENSOR_DEVICE_ATTR_RW(temp2_crit, temp_crit, 1);
+static SENSOR_DEVICE_ATTR_RO(temp3_input, temp, 2);
+static SENSOR_DEVICE_ATTR_RW(temp3_offset, temp_offset, 2);
+static SENSOR_DEVICE_ATTR_RW(temp3_min, temp_min, 2);
+static SENSOR_DEVICE_ATTR_RW(temp3_max, temp_max, 2);
+static SENSOR_DEVICE_ATTR_RW(temp3_crit, temp_crit, 2);
 
 /* Alarms */
 static ssize_t alarms_show(struct device *dev, struct device_attribute *attr,
@@ -838,29 +831,29 @@ static ssize_t alarms_show(struct device *dev, struct device_attribute *attr,
 
 static DEVICE_ATTR_RO(alarms);
 
-static ssize_t show_alarm(struct device *dev,
-			  struct device_attribute *attr, char *buf)
+static ssize_t alarm_show(struct device *dev, struct device_attribute *attr,
+			  char *buf)
 {
 	int bitnr = to_sensor_dev_attr(attr)->index;
 	struct adm1031_data *data = adm1031_update_device(dev);
 	return sprintf(buf, "%d\n", (data->alarm >> bitnr) & 1);
 }
 
-static SENSOR_DEVICE_ATTR(fan1_alarm, S_IRUGO, show_alarm, NULL, 0);
-static SENSOR_DEVICE_ATTR(fan1_fault, S_IRUGO, show_alarm, NULL, 1);
-static SENSOR_DEVICE_ATTR(temp2_max_alarm, S_IRUGO, show_alarm, NULL, 2);
-static SENSOR_DEVICE_ATTR(temp2_min_alarm, S_IRUGO, show_alarm, NULL, 3);
-static SENSOR_DEVICE_ATTR(temp2_crit_alarm, S_IRUGO, show_alarm, NULL, 4);
-static SENSOR_DEVICE_ATTR(temp2_fault, S_IRUGO, show_alarm, NULL, 5);
-static SENSOR_DEVICE_ATTR(temp1_max_alarm, S_IRUGO, show_alarm, NULL, 6);
-static SENSOR_DEVICE_ATTR(temp1_min_alarm, S_IRUGO, show_alarm, NULL, 7);
-static SENSOR_DEVICE_ATTR(fan2_alarm, S_IRUGO, show_alarm, NULL, 8);
-static SENSOR_DEVICE_ATTR(fan2_fault, S_IRUGO, show_alarm, NULL, 9);
-static SENSOR_DEVICE_ATTR(temp3_max_alarm, S_IRUGO, show_alarm, NULL, 10);
-static SENSOR_DEVICE_ATTR(temp3_min_alarm, S_IRUGO, show_alarm, NULL, 11);
-static SENSOR_DEVICE_ATTR(temp3_crit_alarm, S_IRUGO, show_alarm, NULL, 12);
-static SENSOR_DEVICE_ATTR(temp3_fault, S_IRUGO, show_alarm, NULL, 13);
-static SENSOR_DEVICE_ATTR(temp1_crit_alarm, S_IRUGO, show_alarm, NULL, 14);
+static SENSOR_DEVICE_ATTR_RO(fan1_alarm, alarm, 0);
+static SENSOR_DEVICE_ATTR_RO(fan1_fault, alarm, 1);
+static SENSOR_DEVICE_ATTR_RO(temp2_max_alarm, alarm, 2);
+static SENSOR_DEVICE_ATTR_RO(temp2_min_alarm, alarm, 3);
+static SENSOR_DEVICE_ATTR_RO(temp2_crit_alarm, alarm, 4);
+static SENSOR_DEVICE_ATTR_RO(temp2_fault, alarm, 5);
+static SENSOR_DEVICE_ATTR_RO(temp1_max_alarm, alarm, 6);
+static SENSOR_DEVICE_ATTR_RO(temp1_min_alarm, alarm, 7);
+static SENSOR_DEVICE_ATTR_RO(fan2_alarm, alarm, 8);
+static SENSOR_DEVICE_ATTR_RO(fan2_fault, alarm, 9);
+static SENSOR_DEVICE_ATTR_RO(temp3_max_alarm, alarm, 10);
+static SENSOR_DEVICE_ATTR_RO(temp3_min_alarm, alarm, 11);
+static SENSOR_DEVICE_ATTR_RO(temp3_crit_alarm, alarm, 12);
+static SENSOR_DEVICE_ATTR_RO(temp3_fault, alarm, 13);
+static SENSOR_DEVICE_ATTR_RO(temp1_crit_alarm, alarm, 14);
 
 /* Update Interval */
 static const unsigned int update_intervals[] = {
diff --git a/drivers/hwmon/adm9240.c b/drivers/hwmon/adm9240.c
index 255413fdbde9..000b20f1db71 100644
--- a/drivers/hwmon/adm9240.c
+++ b/drivers/hwmon/adm9240.c
@@ -269,16 +269,16 @@ static ssize_t temp1_input_show(struct device *dev,
 	return sprintf(buf, "%d\n", data->temp / 128 * 500); /* 9-bit value */
 }
 
-static ssize_t show_max(struct device *dev, struct device_attribute *devattr,
-		char *buf)
+static ssize_t max_show(struct device *dev, struct device_attribute *devattr,
+			char *buf)
 {
 	struct sensor_device_attribute *attr = to_sensor_dev_attr(devattr);
 	struct adm9240_data *data = adm9240_update_device(dev);
 	return sprintf(buf, "%d\n", data->temp_max[attr->index] * 1000);
 }
 
-static ssize_t set_max(struct device *dev, struct device_attribute *devattr,
-		const char *buf, size_t count)
+static ssize_t max_store(struct device *dev, struct device_attribute *devattr,
+			 const char *buf, size_t count)
 {
 	struct sensor_device_attribute *attr = to_sensor_dev_attr(devattr);
 	struct adm9240_data *data = dev_get_drvdata(dev);
@@ -299,14 +299,12 @@ static ssize_t set_max(struct device *dev, struct device_attribute *devattr,
 }
 
 static DEVICE_ATTR_RO(temp1_input);
-static SENSOR_DEVICE_ATTR(temp1_max, S_IWUSR | S_IRUGO,
-		show_max, set_max, 0);
-static SENSOR_DEVICE_ATTR(temp1_max_hyst, S_IWUSR | S_IRUGO,
-		show_max, set_max, 1);
+static SENSOR_DEVICE_ATTR_RW(temp1_max, max, 0);
+static SENSOR_DEVICE_ATTR_RW(temp1_max_hyst, max, 1);
 
 /* voltage */
-static ssize_t show_in(struct device *dev, struct device_attribute *devattr,
-		char *buf)
+static ssize_t in_show(struct device *dev, struct device_attribute *devattr,
+		       char *buf)
 {
 	struct sensor_device_attribute *attr = to_sensor_dev_attr(devattr);
 	struct adm9240_data *data = adm9240_update_device(dev);
@@ -314,8 +312,8 @@ static ssize_t show_in(struct device *dev, struct device_attribute *devattr,
 				attr->index));
 }
 
-static ssize_t show_in_min(struct device *dev,
-		struct device_attribute *devattr, char *buf)
+static ssize_t in_min_show(struct device *dev,
+			   struct device_attribute *devattr, char *buf)
 {
 	struct sensor_device_attribute *attr = to_sensor_dev_attr(devattr);
 	struct adm9240_data *data = adm9240_update_device(dev);
@@ -323,8 +321,8 @@ static ssize_t show_in_min(struct device *dev,
 				attr->index));
 }
 
-static ssize_t show_in_max(struct device *dev,
-		struct device_attribute *devattr, char *buf)
+static ssize_t in_max_show(struct device *dev,
+			   struct device_attribute *devattr, char *buf)
 {
 	struct sensor_device_attribute *attr = to_sensor_dev_attr(devattr);
 	struct adm9240_data *data = adm9240_update_device(dev);
@@ -332,9 +330,9 @@ static ssize_t show_in_max(struct device *dev,
 				attr->index));
 }
 
-static ssize_t set_in_min(struct device *dev,
-		struct device_attribute *devattr,
-		const char *buf, size_t count)
+static ssize_t in_min_store(struct device *dev,
+			    struct device_attribute *devattr, const char *buf,
+			    size_t count)
 {
 	struct sensor_device_attribute *attr = to_sensor_dev_attr(devattr);
 	struct adm9240_data *data = dev_get_drvdata(dev);
@@ -354,9 +352,9 @@ static ssize_t set_in_min(struct device *dev,
 	return count;
 }
 
-static ssize_t set_in_max(struct device *dev,
-		struct device_attribute *devattr,
-		const char *buf, size_t count)
+static ssize_t in_max_store(struct device *dev,
+			    struct device_attribute *devattr, const char *buf,
+			    size_t count)
 {
 	struct sensor_device_attribute *attr = to_sensor_dev_attr(devattr);
 	struct adm9240_data *data = dev_get_drvdata(dev);
@@ -376,24 +374,28 @@ static ssize_t set_in_max(struct device *dev,
 	return count;
 }
 
-#define vin(nr)							\
-static SENSOR_DEVICE_ATTR(in##nr##_input, S_IRUGO,		\
-		show_in, NULL, nr);				\
-static SENSOR_DEVICE_ATTR(in##nr##_min, S_IRUGO | S_IWUSR,	\
-		show_in_min, set_in_min, nr);			\
-static SENSOR_DEVICE_ATTR(in##nr##_max, S_IRUGO | S_IWUSR,	\
-		show_in_max, set_in_max, nr);
-
-vin(0);
-vin(1);
-vin(2);
-vin(3);
-vin(4);
-vin(5);
+static SENSOR_DEVICE_ATTR_RO(in0_input, in, 0);
+static SENSOR_DEVICE_ATTR_RW(in0_min, in_min, 0);
+static SENSOR_DEVICE_ATTR_RW(in0_max, in_max, 0);
+static SENSOR_DEVICE_ATTR_RO(in1_input, in, 1);
+static SENSOR_DEVICE_ATTR_RW(in1_min, in_min, 1);
+static SENSOR_DEVICE_ATTR_RW(in1_max, in_max, 1);
+static SENSOR_DEVICE_ATTR_RO(in2_input, in, 2);
+static SENSOR_DEVICE_ATTR_RW(in2_min, in_min, 2);
+static SENSOR_DEVICE_ATTR_RW(in2_max, in_max, 2);
+static SENSOR_DEVICE_ATTR_RO(in3_input, in, 3);
+static SENSOR_DEVICE_ATTR_RW(in3_min, in_min, 3);
+static SENSOR_DEVICE_ATTR_RW(in3_max, in_max, 3);
+static SENSOR_DEVICE_ATTR_RO(in4_input, in, 4);
+static SENSOR_DEVICE_ATTR_RW(in4_min, in_min, 4);
+static SENSOR_DEVICE_ATTR_RW(in4_max, in_max, 4);
+static SENSOR_DEVICE_ATTR_RO(in5_input, in, 5);
+static SENSOR_DEVICE_ATTR_RW(in5_min, in_min, 5);
+static SENSOR_DEVICE_ATTR_RW(in5_max, in_max, 5);
 
 /* fans */
-static ssize_t show_fan(struct device *dev,
-		struct device_attribute *devattr, char *buf)
+static ssize_t fan_show(struct device *dev, struct device_attribute *devattr,
+			char *buf)
 {
 	struct sensor_device_attribute *attr = to_sensor_dev_attr(devattr);
 	struct adm9240_data *data = adm9240_update_device(dev);
@@ -401,8 +403,8 @@ static ssize_t show_fan(struct device *dev,
 				1 << data->fan_div[attr->index]));
 }
 
-static ssize_t show_fan_min(struct device *dev,
-		struct device_attribute *devattr, char *buf)
+static ssize_t fan_min_show(struct device *dev,
+			    struct device_attribute *devattr, char *buf)
 {
 	struct sensor_device_attribute *attr = to_sensor_dev_attr(devattr);
 	struct adm9240_data *data = adm9240_update_device(dev);
@@ -410,8 +412,8 @@ static ssize_t show_fan_min(struct device *dev,
 				1 << data->fan_div[attr->index]));
 }
 
-static ssize_t show_fan_div(struct device *dev,
-		struct device_attribute *devattr, char *buf)
+static ssize_t fan_div_show(struct device *dev,
+			    struct device_attribute *devattr, char *buf)
 {
 	struct sensor_device_attribute *attr = to_sensor_dev_attr(devattr);
 	struct adm9240_data *data = adm9240_update_device(dev);
@@ -429,9 +431,9 @@ static ssize_t show_fan_div(struct device *dev,
  * - otherwise: select fan clock divider to suit fan speed low limit,
  *   measurement code may adjust registers to ensure fan speed reading
  */
-static ssize_t set_fan_min(struct device *dev,
-		struct device_attribute *devattr,
-		const char *buf, size_t count)
+static ssize_t fan_min_store(struct device *dev,
+			     struct device_attribute *devattr,
+			     const char *buf, size_t count)
 {
 	struct sensor_device_attribute *attr = to_sensor_dev_attr(devattr);
 	struct adm9240_data *data = dev_get_drvdata(dev);
@@ -489,16 +491,12 @@ static ssize_t set_fan_min(struct device *dev,
 	return count;
 }
 
-#define fan(nr)							\
-static SENSOR_DEVICE_ATTR(fan##nr##_input, S_IRUGO,		\
-		show_fan, NULL, nr - 1);			\
-static SENSOR_DEVICE_ATTR(fan##nr##_div, S_IRUGO,		\
-		show_fan_div, NULL, nr - 1);			\
-static SENSOR_DEVICE_ATTR(fan##nr##_min, S_IRUGO | S_IWUSR,	\
-		show_fan_min, set_fan_min, nr - 1);
-
-fan(1);
-fan(2);
+static SENSOR_DEVICE_ATTR_RO(fan1_input, fan, 0);
+static SENSOR_DEVICE_ATTR_RW(fan1_min, fan_min, 0);
+static SENSOR_DEVICE_ATTR_RO(fan1_div, fan_div, 0);
+static SENSOR_DEVICE_ATTR_RO(fan2_input, fan, 1);
+static SENSOR_DEVICE_ATTR_RW(fan2_min, fan_min, 1);
+static SENSOR_DEVICE_ATTR_RO(fan2_div, fan_div, 1);
 
 /* alarms */
 static ssize_t alarms_show(struct device *dev,
@@ -509,22 +507,22 @@ static ssize_t alarms_show(struct device *dev,
 }
 static DEVICE_ATTR_RO(alarms);
 
-static ssize_t show_alarm(struct device *dev,
-		struct device_attribute *attr, char *buf)
+static ssize_t alarm_show(struct device *dev, struct device_attribute *attr,
+			  char *buf)
 {
 	int bitnr = to_sensor_dev_attr(attr)->index;
 	struct adm9240_data *data = adm9240_update_device(dev);
 	return sprintf(buf, "%u\n", (data->alarms >> bitnr) & 1);
 }
-static SENSOR_DEVICE_ATTR(in0_alarm, S_IRUGO, show_alarm, NULL, 0);
-static SENSOR_DEVICE_ATTR(in1_alarm, S_IRUGO, show_alarm, NULL, 1);
-static SENSOR_DEVICE_ATTR(in2_alarm, S_IRUGO, show_alarm, NULL, 2);
-static SENSOR_DEVICE_ATTR(in3_alarm, S_IRUGO, show_alarm, NULL, 3);
-static SENSOR_DEVICE_ATTR(in4_alarm, S_IRUGO, show_alarm, NULL, 8);
-static SENSOR_DEVICE_ATTR(in5_alarm, S_IRUGO, show_alarm, NULL, 9);
-static SENSOR_DEVICE_ATTR(temp1_alarm, S_IRUGO, show_alarm, NULL, 4);
-static SENSOR_DEVICE_ATTR(fan1_alarm, S_IRUGO, show_alarm, NULL, 6);
-static SENSOR_DEVICE_ATTR(fan2_alarm, S_IRUGO, show_alarm, NULL, 7);
+static SENSOR_DEVICE_ATTR_RO(in0_alarm, alarm, 0);
+static SENSOR_DEVICE_ATTR_RO(in1_alarm, alarm, 1);
+static SENSOR_DEVICE_ATTR_RO(in2_alarm, alarm, 2);
+static SENSOR_DEVICE_ATTR_RO(in3_alarm, alarm, 3);
+static SENSOR_DEVICE_ATTR_RO(in4_alarm, alarm, 8);
+static SENSOR_DEVICE_ATTR_RO(in5_alarm, alarm, 9);
+static SENSOR_DEVICE_ATTR_RO(temp1_alarm, alarm, 4);
+static SENSOR_DEVICE_ATTR_RO(fan1_alarm, alarm, 6);
+static SENSOR_DEVICE_ATTR_RO(fan2_alarm, alarm, 7);
 
 /* vid */
 static ssize_t cpu0_vid_show(struct device *dev,
@@ -564,9 +562,8 @@ static ssize_t aout_output_store(struct device *dev,
 }
 static DEVICE_ATTR_RW(aout_output);
 
-static ssize_t chassis_clear(struct device *dev,
-		struct device_attribute *attr,
-		const char *buf, size_t count)
+static ssize_t alarm_store(struct device *dev, struct device_attribute *attr,
+			   const char *buf, size_t count)
 {
 	struct adm9240_data *data = dev_get_drvdata(dev);
 	struct i2c_client *client = data->client;
@@ -583,8 +580,7 @@ static ssize_t chassis_clear(struct device *dev,
 
 	return count;
 }
-static SENSOR_DEVICE_ATTR(intrusion0_alarm, S_IRUGO | S_IWUSR, show_alarm,
-		chassis_clear, 12);
+static SENSOR_DEVICE_ATTR_RW(intrusion0_alarm, alarm, 12);
 
 static struct attribute *adm9240_attrs[] = {
 	&sensor_dev_attr_in0_input.dev_attr.attr,
@@ -632,7 +628,6 @@ static struct attribute *adm9240_attrs[] = {
 
 ATTRIBUTE_GROUPS(adm9240);
 
-
 /*** sensor chip detect and driver install ***/
 
 /* Return 0 if detection is successful, -ENODEV otherwise */
diff --git a/drivers/hwmon/ads1015.c b/drivers/hwmon/ads1015.c
index c21b0529adb2..412ab7015d75 100644
--- a/drivers/hwmon/ads1015.c
+++ b/drivers/hwmon/ads1015.c
@@ -307,7 +307,7 @@ static const struct i2c_device_id ads1015_id[] = {
 };
 MODULE_DEVICE_TABLE(i2c, ads1015_id);
 
-static const struct of_device_id ads1015_of_match[] = {
+static const struct of_device_id __maybe_unused ads1015_of_match[] = {
 	{
 		.compatible = "ti,ads1015",
 		.data = (void *)ads1015
diff --git a/drivers/hwmon/ads7828.c b/drivers/hwmon/ads7828.c
index 12c56d3783ed..03d6e782777a 100644
--- a/drivers/hwmon/ads7828.c
+++ b/drivers/hwmon/ads7828.c
@@ -8,7 +8,7 @@
  *
  * ADS7830 support, by Guillaume Roguez <guillaume.roguez@savoirfairelinux.com>
  *
- * For further information, see the Documentation/hwmon/ads7828 file.
+ * For further information, see the Documentation/hwmon/ads7828.rst file.
  *
  * This program is free software; you can redistribute it and/or modify
  * it under the terms of the GNU General Public License as published by
@@ -200,7 +200,7 @@ static const struct i2c_device_id ads7828_device_ids[] = {
 };
 MODULE_DEVICE_TABLE(i2c, ads7828_device_ids);
 
-static const struct of_device_id ads7828_of_match[] = {
+static const struct of_device_id __maybe_unused ads7828_of_match[] = {
 	{
 		.compatible = "ti,ads7828",
 		.data = (void *)ads7828
diff --git a/drivers/hwmon/adt7411.c b/drivers/hwmon/adt7411.c
index b939f8a115ba..44a827b031cb 100644
--- a/drivers/hwmon/adt7411.c
+++ b/drivers/hwmon/adt7411.c
@@ -639,40 +639,22 @@ static int adt7411_init_device(struct adt7411_data *data)
 	return i2c_smbus_write_byte_data(data->client, ADT7411_REG_CFG1, val);
 }
 
-static const u32 adt7411_in_config[] = {
-	HWMON_I_INPUT | HWMON_I_MIN | HWMON_I_MAX | HWMON_I_ALARM,
-	HWMON_I_INPUT | HWMON_I_MIN | HWMON_I_MAX | HWMON_I_ALARM,
-	HWMON_I_INPUT | HWMON_I_MIN | HWMON_I_MAX | HWMON_I_ALARM,
-	HWMON_I_INPUT | HWMON_I_MIN | HWMON_I_MAX | HWMON_I_ALARM,
-	HWMON_I_INPUT | HWMON_I_MIN | HWMON_I_MAX | HWMON_I_ALARM,
-	HWMON_I_INPUT | HWMON_I_MIN | HWMON_I_MAX | HWMON_I_ALARM,
-	HWMON_I_INPUT | HWMON_I_MIN | HWMON_I_MAX | HWMON_I_ALARM,
-	HWMON_I_INPUT | HWMON_I_MIN | HWMON_I_MAX | HWMON_I_ALARM,
-	HWMON_I_INPUT | HWMON_I_MIN | HWMON_I_MAX | HWMON_I_ALARM,
-	0
-};
-
-static const struct hwmon_channel_info adt7411_in = {
-	.type = hwmon_in,
-	.config = adt7411_in_config,
-};
-
-static const u32 adt7411_temp_config[] = {
-	HWMON_T_INPUT | HWMON_T_MIN | HWMON_T_MIN_ALARM |
-		HWMON_T_MAX | HWMON_T_MAX_ALARM,
-	HWMON_T_INPUT | HWMON_T_MIN | HWMON_T_MIN_ALARM |
-		HWMON_T_MAX | HWMON_T_MAX_ALARM | HWMON_T_FAULT,
-	0
-};
-
-static const struct hwmon_channel_info adt7411_temp = {
-	.type = hwmon_temp,
-	.config = adt7411_temp_config,
-};
-
 static const struct hwmon_channel_info *adt7411_info[] = {
-	&adt7411_in,
-	&adt7411_temp,
+	HWMON_CHANNEL_INFO(in,
+			   HWMON_I_INPUT | HWMON_I_MIN | HWMON_I_MAX | HWMON_I_ALARM,
+			   HWMON_I_INPUT | HWMON_I_MIN | HWMON_I_MAX | HWMON_I_ALARM,
+			   HWMON_I_INPUT | HWMON_I_MIN | HWMON_I_MAX | HWMON_I_ALARM,
+			   HWMON_I_INPUT | HWMON_I_MIN | HWMON_I_MAX | HWMON_I_ALARM,
+			   HWMON_I_INPUT | HWMON_I_MIN | HWMON_I_MAX | HWMON_I_ALARM,
+			   HWMON_I_INPUT | HWMON_I_MIN | HWMON_I_MAX | HWMON_I_ALARM,
+			   HWMON_I_INPUT | HWMON_I_MIN | HWMON_I_MAX | HWMON_I_ALARM,
+			   HWMON_I_INPUT | HWMON_I_MIN | HWMON_I_MAX | HWMON_I_ALARM,
+			   HWMON_I_INPUT | HWMON_I_MIN | HWMON_I_MAX | HWMON_I_ALARM),
+	HWMON_CHANNEL_INFO(temp,
+			   HWMON_T_INPUT | HWMON_T_MIN | HWMON_T_MIN_ALARM |
+			   HWMON_T_MAX | HWMON_T_MAX_ALARM,
+			   HWMON_T_INPUT | HWMON_T_MIN | HWMON_T_MIN_ALARM |
+			   HWMON_T_MAX | HWMON_T_MAX_ALARM | HWMON_T_FAULT),
 	NULL
 };
 
diff --git a/drivers/hwmon/adt7475.c b/drivers/hwmon/adt7475.c
index 0dbb8df74e44..7caec127df86 100644
--- a/drivers/hwmon/adt7475.c
+++ b/drivers/hwmon/adt7475.c
@@ -168,7 +168,7 @@ static const struct i2c_device_id adt7475_id[] = {
 };
 MODULE_DEVICE_TABLE(i2c, adt7475_id);
 
-static const struct of_device_id adt7475_of_match[] = {
+static const struct of_device_id __maybe_unused adt7475_of_match[] = {
 	{
 		.compatible = "adi,adt7473",
 		.data = (void *)adt7473
diff --git a/drivers/hwmon/f71805f.c b/drivers/hwmon/f71805f.c
index 73c681162653..623736d2a7c1 100644
--- a/drivers/hwmon/f71805f.c
+++ b/drivers/hwmon/f71805f.c
@@ -96,17 +96,23 @@ superio_select(int base, int ld)
 	outb(ld, base + 1);
 }
 
-static inline void
+static inline int
 superio_enter(int base)
 {
+	if (!request_muxed_region(base, 2, DRVNAME))
+		return -EBUSY;
+
 	outb(0x87, base);
 	outb(0x87, base);
+
+	return 0;
 }
 
 static inline void
 superio_exit(int base)
 {
 	outb(0xaa, base);
+	release_region(base, 2);
 }
 
 /*
@@ -1561,7 +1567,7 @@ exit:
 static int __init f71805f_find(int sioaddr, unsigned short *address,
 			       struct f71805f_sio_data *sio_data)
 {
-	int err = -ENODEV;
+	int err;
 	u16 devid;
 
 	static const char * const names[] = {
@@ -1569,8 +1575,11 @@ static int __init f71805f_find(int sioaddr, unsigned short *address,
 		"F71872F/FG or F71806F/FG",
 	};
 
-	superio_enter(sioaddr);
+	err = superio_enter(sioaddr);
+	if (err)
+		return err;
 
+	err = -ENODEV;
 	devid = superio_inw(sioaddr, SIO_REG_MANID);
 	if (devid != SIO_FINTEK_ID)
 		goto exit;
diff --git a/drivers/hwmon/hih6130.c b/drivers/hwmon/hih6130.c
index d167fcfec765..2bf9599b34a1 100644
--- a/drivers/hwmon/hih6130.c
+++ b/drivers/hwmon/hih6130.c
@@ -252,7 +252,7 @@ static const struct i2c_device_id hih6130_id[] = {
 };
 MODULE_DEVICE_TABLE(i2c, hih6130_id);
 
-static const struct of_device_id hih6130_of_match[] = {
+static const struct of_device_id __maybe_unused hih6130_of_match[] = {
 	{ .compatible = "honeywell,hih6130", },
 	{ }
 };
diff --git a/drivers/hwmon/hwmon.c b/drivers/hwmon/hwmon.c
index c22dc1e07911..cd91510a5387 100644
--- a/drivers/hwmon/hwmon.c
+++ b/drivers/hwmon/hwmon.c
@@ -324,6 +324,11 @@ static const char * const hwmon_chip_attrs[] = {
 	[hwmon_chip_power_reset_history] = "power_reset_history",
 	[hwmon_chip_update_interval] = "update_interval",
 	[hwmon_chip_alarms] = "alarms",
+	[hwmon_chip_samples] = "samples",
+	[hwmon_chip_curr_samples] = "curr_samples",
+	[hwmon_chip_in_samples] = "in_samples",
+	[hwmon_chip_power_samples] = "power_samples",
+	[hwmon_chip_temp_samples] = "temp_samples",
 };
 
 static const char * const hwmon_temp_attr_templates[] = {
diff --git a/drivers/hwmon/iio_hwmon.c b/drivers/hwmon/iio_hwmon.c
index 5c3c08449de7..1770423f7a80 100644
--- a/drivers/hwmon/iio_hwmon.c
+++ b/drivers/hwmon/iio_hwmon.c
@@ -92,6 +92,9 @@ static int iio_hwmon_probe(struct platform_device *pdev)
 		return -ENOMEM;
 
 	for (i = 0; i < st->num_channels; i++) {
+		const char *prefix;
+		int n;
+
 		a = devm_kzalloc(dev, sizeof(*a), GFP_KERNEL);
 		if (a == NULL)
 			return -ENOMEM;
@@ -103,28 +106,28 @@ static int iio_hwmon_probe(struct platform_device *pdev)
 
 		switch (type) {
 		case IIO_VOLTAGE:
-			a->dev_attr.attr.name = devm_kasprintf(dev, GFP_KERNEL,
-							       "in%d_input",
-							       in_i++);
+			n = in_i++;
+			prefix = "in";
 			break;
 		case IIO_TEMP:
-			a->dev_attr.attr.name = devm_kasprintf(dev, GFP_KERNEL,
-							       "temp%d_input",
-							       temp_i++);
+			n = temp_i++;
+			prefix = "temp";
 			break;
 		case IIO_CURRENT:
-			a->dev_attr.attr.name = devm_kasprintf(dev, GFP_KERNEL,
-							       "curr%d_input",
-							       curr_i++);
+			n = curr_i++;
+			prefix = "curr";
 			break;
 		case IIO_HUMIDITYRELATIVE:
-			a->dev_attr.attr.name = devm_kasprintf(dev, GFP_KERNEL,
-							       "humidity%d_input",
-							       humidity_i++);
+			n = humidity_i++;
+			prefix = "humidity";
 			break;
 		default:
 			return -EINVAL;
 		}
+
+		a->dev_attr.attr.name = devm_kasprintf(dev, GFP_KERNEL,
+						       "%s%d_input",
+						       prefix, n);
 		if (a->dev_attr.attr.name == NULL)
 			return -ENOMEM;
 
diff --git a/drivers/hwmon/ina209.c b/drivers/hwmon/ina209.c
index e3854463db84..6a4ec2f2ddb2 100644
--- a/drivers/hwmon/ina209.c
+++ b/drivers/hwmon/ina209.c
@@ -587,7 +587,7 @@ static const struct i2c_device_id ina209_id[] = {
 };
 MODULE_DEVICE_TABLE(i2c, ina209_id);
 
-static const struct of_device_id ina209_of_match[] = {
+static const struct of_device_id __maybe_unused ina209_of_match[] = {
 	{ .compatible = "ti,ina209" },
 	{ },
 };
diff --git a/drivers/hwmon/ina2xx.c b/drivers/hwmon/ina2xx.c
index 290379c49be9..42df51f8cdf2 100644
--- a/drivers/hwmon/ina2xx.c
+++ b/drivers/hwmon/ina2xx.c
@@ -507,7 +507,7 @@ static const struct i2c_device_id ina2xx_id[] = {
 };
 MODULE_DEVICE_TABLE(i2c, ina2xx_id);
 
-static const struct of_device_id ina2xx_of_match[] = {
+static const struct of_device_id __maybe_unused ina2xx_of_match[] = {
 	{
 		.compatible = "ti,ina219",
 		.data = (void *)ina219
diff --git a/drivers/hwmon/ina3221.c b/drivers/hwmon/ina3221.c
index 3626b87a5fd2..e0637fed9585 100644
--- a/drivers/hwmon/ina3221.c
+++ b/drivers/hwmon/ina3221.c
@@ -22,6 +22,7 @@
 #include <linux/of.h>
 #include <linux/pm_runtime.h>
 #include <linux/regmap.h>
+#include <linux/util_macros.h>
 
 #define INA3221_DRIVER_NAME		"ina3221"
 
@@ -51,6 +52,9 @@
 #define INA3221_CONFIG_VBUS_CT_SHIFT	6
 #define INA3221_CONFIG_VBUS_CT_MASK	GENMASK(8, 6)
 #define INA3221_CONFIG_VBUS_CT(x)	(((x) & GENMASK(8, 6)) >> 6)
+#define INA3221_CONFIG_AVG_SHIFT	9
+#define INA3221_CONFIG_AVG_MASK		GENMASK(11, 9)
+#define INA3221_CONFIG_AVG(x)		(((x) & GENMASK(11, 9)) >> 9)
 #define INA3221_CONFIG_CHs_EN_MASK	GENMASK(14, 12)
 #define INA3221_CONFIG_CHx_EN(x)	BIT(14 - (x))
 
@@ -135,17 +139,42 @@ static const u16 ina3221_conv_time[] = {
 	140, 204, 332, 588, 1100, 2116, 4156, 8244,
 };
 
-static inline int ina3221_wait_for_data(struct ina3221_data *ina)
+/* Lookup table for number of samples using in averaging mode */
+static const int ina3221_avg_samples[] = {
+	1, 4, 16, 64, 128, 256, 512, 1024,
+};
+
+/* Converting update_interval in msec to conversion time in usec */
+static inline u32 ina3221_interval_ms_to_conv_time(u16 config, int interval)
+{
+	u32 channels = hweight16(config & INA3221_CONFIG_CHs_EN_MASK);
+	u32 samples_idx = INA3221_CONFIG_AVG(config);
+	u32 samples = ina3221_avg_samples[samples_idx];
+
+	/* Bisect the result to Bus and Shunt conversion times */
+	return DIV_ROUND_CLOSEST(interval * 1000 / 2, channels * samples);
+}
+
+/* Converting CONFIG register value to update_interval in usec */
+static inline u32 ina3221_reg_to_interval_us(u16 config)
 {
-	u32 channels = hweight16(ina->reg_config & INA3221_CONFIG_CHs_EN_MASK);
-	u32 vbus_ct_idx = INA3221_CONFIG_VBUS_CT(ina->reg_config);
-	u32 vsh_ct_idx = INA3221_CONFIG_VSH_CT(ina->reg_config);
+	u32 channels = hweight16(config & INA3221_CONFIG_CHs_EN_MASK);
+	u32 vbus_ct_idx = INA3221_CONFIG_VBUS_CT(config);
+	u32 vsh_ct_idx = INA3221_CONFIG_VSH_CT(config);
+	u32 samples_idx = INA3221_CONFIG_AVG(config);
+	u32 samples = ina3221_avg_samples[samples_idx];
 	u32 vbus_ct = ina3221_conv_time[vbus_ct_idx];
 	u32 vsh_ct = ina3221_conv_time[vsh_ct_idx];
-	u32 wait, cvrf;
 
 	/* Calculate total conversion time */
-	wait = channels * (vbus_ct + vsh_ct);
+	return channels * (vbus_ct + vsh_ct) * samples;
+}
+
+static inline int ina3221_wait_for_data(struct ina3221_data *ina)
+{
+	u32 wait, cvrf;
+
+	wait = ina3221_reg_to_interval_us(ina->reg_config);
 
 	/* Polling the CVRF bit to make sure read data is ready */
 	return regmap_field_read_poll_timeout(ina->fields[F_CVRF],
@@ -176,6 +205,26 @@ static const u8 ina3221_in_reg[] = {
 	INA3221_SHUNT3,
 };
 
+static int ina3221_read_chip(struct device *dev, u32 attr, long *val)
+{
+	struct ina3221_data *ina = dev_get_drvdata(dev);
+	int regval;
+
+	switch (attr) {
+	case hwmon_chip_samples:
+		regval = INA3221_CONFIG_AVG(ina->reg_config);
+		*val = ina3221_avg_samples[regval];
+		return 0;
+	case hwmon_chip_update_interval:
+		/* Return in msec */
+		*val = ina3221_reg_to_interval_us(ina->reg_config);
+		*val = DIV_ROUND_CLOSEST(*val, 1000);
+		return 0;
+	default:
+		return -EOPNOTSUPP;
+	}
+}
+
 static int ina3221_read_in(struct device *dev, u32 attr, int channel, long *val)
 {
 	const bool is_shunt = channel > INA3221_CHANNEL3;
@@ -279,6 +328,48 @@ static int ina3221_read_curr(struct device *dev, u32 attr,
 	}
 }
 
+static int ina3221_write_chip(struct device *dev, u32 attr, long val)
+{
+	struct ina3221_data *ina = dev_get_drvdata(dev);
+	int ret, idx;
+	u32 tmp;
+
+	switch (attr) {
+	case hwmon_chip_samples:
+		idx = find_closest(val, ina3221_avg_samples,
+				   ARRAY_SIZE(ina3221_avg_samples));
+
+		tmp = (ina->reg_config & ~INA3221_CONFIG_AVG_MASK) |
+		      (idx << INA3221_CONFIG_AVG_SHIFT);
+		ret = regmap_write(ina->regmap, INA3221_CONFIG, tmp);
+		if (ret)
+			return ret;
+
+		/* Update reg_config accordingly */
+		ina->reg_config = tmp;
+		return 0;
+	case hwmon_chip_update_interval:
+		tmp = ina3221_interval_ms_to_conv_time(ina->reg_config, val);
+		idx = find_closest(tmp, ina3221_conv_time,
+				   ARRAY_SIZE(ina3221_conv_time));
+
+		/* Update Bus and Shunt voltage conversion times */
+		tmp = INA3221_CONFIG_VBUS_CT_MASK | INA3221_CONFIG_VSH_CT_MASK;
+		tmp = (ina->reg_config & ~tmp) |
+		      (idx << INA3221_CONFIG_VBUS_CT_SHIFT) |
+		      (idx << INA3221_CONFIG_VSH_CT_SHIFT);
+		ret = regmap_write(ina->regmap, INA3221_CONFIG, tmp);
+		if (ret)
+			return ret;
+
+		/* Update reg_config accordingly */
+		ina->reg_config = tmp;
+		return 0;
+	default:
+		return -EOPNOTSUPP;
+	}
+}
+
 static int ina3221_write_curr(struct device *dev, u32 attr,
 			      int channel, long val)
 {
@@ -309,6 +400,7 @@ static int ina3221_write_enable(struct device *dev, int channel, bool enable)
 	struct ina3221_data *ina = dev_get_drvdata(dev);
 	u16 config, mask = INA3221_CONFIG_CHx_EN(channel);
 	u16 config_old = ina->reg_config & mask;
+	u32 tmp;
 	int ret;
 
 	config = enable ? mask : 0;
@@ -327,14 +419,13 @@ static int ina3221_write_enable(struct device *dev, int channel, bool enable)
 	}
 
 	/* Enable or disable the channel */
-	ret = regmap_update_bits(ina->regmap, INA3221_CONFIG, mask, config);
+	tmp = (ina->reg_config & ~mask) | (config & mask);
+	ret = regmap_write(ina->regmap, INA3221_CONFIG, tmp);
 	if (ret)
 		goto fail;
 
 	/* Cache the latest config register value */
-	ret = regmap_read(ina->regmap, INA3221_CONFIG, &ina->reg_config);
-	if (ret)
-		goto fail;
+	ina->reg_config = tmp;
 
 	/* For disabling routine, decrease refcount or suspend() at last */
 	if (!enable)
@@ -361,6 +452,9 @@ static int ina3221_read(struct device *dev, enum hwmon_sensor_types type,
 	mutex_lock(&ina->lock);
 
 	switch (type) {
+	case hwmon_chip:
+		ret = ina3221_read_chip(dev, attr, val);
+		break;
 	case hwmon_in:
 		/* 0-align channel ID */
 		ret = ina3221_read_in(dev, attr, channel - 1, val);
@@ -387,6 +481,9 @@ static int ina3221_write(struct device *dev, enum hwmon_sensor_types type,
 	mutex_lock(&ina->lock);
 
 	switch (type) {
+	case hwmon_chip:
+		ret = ina3221_write_chip(dev, attr, val);
+		break;
 	case hwmon_in:
 		/* 0-align channel ID */
 		ret = ina3221_write_enable(dev, channel - 1, val);
@@ -423,6 +520,14 @@ static umode_t ina3221_is_visible(const void *drvdata,
 	const struct ina3221_input *input = NULL;
 
 	switch (type) {
+	case hwmon_chip:
+		switch (attr) {
+		case hwmon_chip_samples:
+		case hwmon_chip_update_interval:
+			return 0644;
+		default:
+			return 0;
+		}
 	case hwmon_in:
 		/* Ignore in0_ */
 		if (channel == 0)
@@ -458,44 +563,29 @@ static umode_t ina3221_is_visible(const void *drvdata,
 	}
 }
 
-static const u32 ina3221_in_config[] = {
-	/* 0: dummy, skipped in is_visible */
-	HWMON_I_INPUT,
-	/* 1-3: input voltage Channels */
-	HWMON_I_INPUT | HWMON_I_ENABLE | HWMON_I_LABEL,
-	HWMON_I_INPUT | HWMON_I_ENABLE | HWMON_I_LABEL,
-	HWMON_I_INPUT | HWMON_I_ENABLE | HWMON_I_LABEL,
-	/* 4-6: shunt voltage Channels */
-	HWMON_I_INPUT,
-	HWMON_I_INPUT,
-	HWMON_I_INPUT,
-	0
-};
-
-static const struct hwmon_channel_info ina3221_in = {
-	.type = hwmon_in,
-	.config = ina3221_in_config,
-};
-
 #define INA3221_HWMON_CURR_CONFIG (HWMON_C_INPUT | \
 				   HWMON_C_CRIT | HWMON_C_CRIT_ALARM | \
 				   HWMON_C_MAX | HWMON_C_MAX_ALARM)
 
-static const u32 ina3221_curr_config[] = {
-	INA3221_HWMON_CURR_CONFIG,
-	INA3221_HWMON_CURR_CONFIG,
-	INA3221_HWMON_CURR_CONFIG,
-	0
-};
-
-static const struct hwmon_channel_info ina3221_curr = {
-	.type = hwmon_curr,
-	.config = ina3221_curr_config,
-};
-
 static const struct hwmon_channel_info *ina3221_info[] = {
-	&ina3221_in,
-	&ina3221_curr,
+	HWMON_CHANNEL_INFO(chip,
+			   HWMON_C_SAMPLES,
+			   HWMON_C_UPDATE_INTERVAL),
+	HWMON_CHANNEL_INFO(in,
+			   /* 0: dummy, skipped in is_visible */
+			   HWMON_I_INPUT,
+			   /* 1-3: input voltage Channels */
+			   HWMON_I_INPUT | HWMON_I_ENABLE | HWMON_I_LABEL,
+			   HWMON_I_INPUT | HWMON_I_ENABLE | HWMON_I_LABEL,
+			   HWMON_I_INPUT | HWMON_I_ENABLE | HWMON_I_LABEL,
+			   /* 4-6: shunt voltage Channels */
+			   HWMON_I_INPUT,
+			   HWMON_I_INPUT,
+			   HWMON_I_INPUT),
+	HWMON_CHANNEL_INFO(curr,
+			   INA3221_HWMON_CURR_CONFIG,
+			   INA3221_HWMON_CURR_CONFIG,
+			   INA3221_HWMON_CURR_CONFIG),
 	NULL
 };
 
diff --git a/drivers/hwmon/jc42.c b/drivers/hwmon/jc42.c
index 4fa482ae0eb5..6b57a6d4e626 100644
--- a/drivers/hwmon/jc42.c
+++ b/drivers/hwmon/jc42.c
@@ -451,20 +451,12 @@ static int jc42_detect(struct i2c_client *client, struct i2c_board_info *info)
 	return -ENODEV;
 }
 
-static const u32 jc42_temp_config[] = {
-	HWMON_T_INPUT | HWMON_T_MIN | HWMON_T_MAX | HWMON_T_CRIT |
-	HWMON_T_MAX_HYST | HWMON_T_CRIT_HYST |
-	HWMON_T_MIN_ALARM | HWMON_T_MAX_ALARM | HWMON_T_CRIT_ALARM,
-	0
-};
-
-static const struct hwmon_channel_info jc42_temp = {
-	.type = hwmon_temp,
-	.config = jc42_temp_config,
-};
-
 static const struct hwmon_channel_info *jc42_info[] = {
-	&jc42_temp,
+	HWMON_CHANNEL_INFO(temp,
+			   HWMON_T_INPUT | HWMON_T_MIN | HWMON_T_MAX |
+			   HWMON_T_CRIT | HWMON_T_MAX_HYST |
+			   HWMON_T_CRIT_HYST | HWMON_T_MIN_ALARM |
+			   HWMON_T_MAX_ALARM | HWMON_T_CRIT_ALARM),
 	NULL
 };
 
diff --git a/drivers/hwmon/jz4740-hwmon.c b/drivers/hwmon/jz4740-hwmon.c
index 2d40a2e771d7..7d5947595b45 100644
--- a/drivers/hwmon/jz4740-hwmon.c
+++ b/drivers/hwmon/jz4740-hwmon.c
@@ -94,7 +94,6 @@ static int jz4740_hwmon_probe(struct platform_device *pdev)
 	struct device *dev = &pdev->dev;
 	struct jz4740_hwmon *hwmon;
 	struct device *hwmon_dev;
-	struct resource *mem;
 
 	hwmon = devm_kzalloc(dev, sizeof(*hwmon), GFP_KERNEL);
 	if (!hwmon)
@@ -109,8 +108,7 @@ static int jz4740_hwmon_probe(struct platform_device *pdev)
 		return hwmon->irq;
 	}
 
-	mem = platform_get_resource(pdev, IORESOURCE_MEM, 0);
-	hwmon->base = devm_ioremap_resource(&pdev->dev, mem);
+	hwmon->base = devm_platform_ioremap_resource(pdev, 0);
 	if (IS_ERR(hwmon->base))
 		return PTR_ERR(hwmon->base);
 
diff --git a/drivers/hwmon/lm63.c b/drivers/hwmon/lm63.c
index eac54b9cdeec..8848fbe5fd16 100644
--- a/drivers/hwmon/lm63.c
+++ b/drivers/hwmon/lm63.c
@@ -1153,7 +1153,7 @@ static const struct i2c_device_id lm63_id[] = {
 };
 MODULE_DEVICE_TABLE(i2c, lm63_id);
 
-static const struct of_device_id lm63_of_match[] = {
+static const struct of_device_id __maybe_unused lm63_of_match[] = {
 	{
 		.compatible = "national,lm63",
 		.data = (void *)lm63
diff --git a/drivers/hwmon/lm75.c b/drivers/hwmon/lm75.c
index 447af07450f1..423a382420b9 100644
--- a/drivers/hwmon/lm75.c
+++ b/drivers/hwmon/lm75.c
@@ -59,6 +59,7 @@ enum lm75_type {		/* keep sorted in alphabetical order */
 	tmp175,
 	tmp275,
 	tmp75,
+	tmp75b,
 	tmp75c,
 };
 
@@ -194,35 +195,11 @@ static umode_t lm75_is_visible(const void *data, enum hwmon_sensor_types type,
 	return 0;
 }
 
-/*-----------------------------------------------------------------------*/
-
-/* device probe and removal */
-
-/* chip configuration */
-
-static const u32 lm75_chip_config[] = {
-	HWMON_C_REGISTER_TZ | HWMON_C_UPDATE_INTERVAL,
-	0
-};
-
-static const struct hwmon_channel_info lm75_chip = {
-	.type = hwmon_chip,
-	.config = lm75_chip_config,
-};
-
-static const u32 lm75_temp_config[] = {
-	HWMON_T_INPUT | HWMON_T_MAX | HWMON_T_MAX_HYST,
-	0
-};
-
-static const struct hwmon_channel_info lm75_temp = {
-	.type = hwmon_temp,
-	.config = lm75_temp_config,
-};
-
 static const struct hwmon_channel_info *lm75_info[] = {
-	&lm75_chip,
-	&lm75_temp,
+	HWMON_CHANNEL_INFO(chip,
+			   HWMON_C_REGISTER_TZ | HWMON_C_UPDATE_INTERVAL),
+	HWMON_CHANNEL_INFO(temp,
+			   HWMON_T_INPUT | HWMON_T_MAX | HWMON_T_MAX_HYST),
 	NULL
 };
 
@@ -378,6 +355,11 @@ lm75_probe(struct i2c_client *client, const struct i2c_device_id *id)
 		data->resolution = 12;
 		data->sample_time = MSEC_PER_SEC / 2;
 		break;
+	case tmp75b:  /* not one-shot mode, Conversion rate 37Hz */
+		clr_mask |= 1 << 15 | 0x3 << 13;
+		data->resolution = 12;
+		data->sample_time = MSEC_PER_SEC / 37;
+		break;
 	case tmp75c:
 		clr_mask |= 1 << 5;		/* not one-shot mode */
 		data->resolution = 12;
@@ -438,12 +420,13 @@ static const struct i2c_device_id lm75_ids[] = {
 	{ "tmp175", tmp175, },
 	{ "tmp275", tmp275, },
 	{ "tmp75", tmp75, },
+	{ "tmp75b", tmp75b, },
 	{ "tmp75c", tmp75c, },
 	{ /* LIST END */ }
 };
 MODULE_DEVICE_TABLE(i2c, lm75_ids);
 
-static const struct of_device_id lm75_of_match[] = {
+static const struct of_device_id __maybe_unused lm75_of_match[] = {
 	{
 		.compatible = "adi,adt75",
 		.data = (void *)adt75
@@ -537,6 +520,10 @@ static const struct of_device_id lm75_of_match[] = {
 		.data = (void *)tmp75
 	},
 	{
+		.compatible = "ti,tmp75b",
+		.data = (void *)tmp75b
+	},
+	{
 		.compatible = "ti,tmp75c",
 		.data = (void *)tmp75c
 	},
diff --git a/drivers/hwmon/lm78.c b/drivers/hwmon/lm78.c
index 0cb7ff613b80..eb95947673de 100644
--- a/drivers/hwmon/lm78.c
+++ b/drivers/hwmon/lm78.c
@@ -73,7 +73,6 @@ enum chips { lm78, lm79 };
 #define LM78_REG_CHIPID 0x49
 #define LM78_REG_I2C_ADDR 0x48
 
-
 /*
  * Conversions. Rounding and limit checking is only done on the TO_REG
  * variants.
@@ -147,15 +146,13 @@ struct lm78_data {
 	u16 alarms;		/* Register encoding, combined */
 };
 
-
 static int lm78_read_value(struct lm78_data *data, u8 reg);
 static int lm78_write_value(struct lm78_data *data, u8 reg, u8 value);
 static struct lm78_data *lm78_update_device(struct device *dev);
 static void lm78_init_device(struct lm78_data *data);
 
-
 /* 7 Voltages */
-static ssize_t show_in(struct device *dev, struct device_attribute *da,
+static ssize_t in_show(struct device *dev, struct device_attribute *da,
 		       char *buf)
 {
 	struct sensor_device_attribute *attr = to_sensor_dev_attr(da);
@@ -163,7 +160,7 @@ static ssize_t show_in(struct device *dev, struct device_attribute *da,
 	return sprintf(buf, "%d\n", IN_FROM_REG(data->in[attr->index]));
 }
 
-static ssize_t show_in_min(struct device *dev, struct device_attribute *da,
+static ssize_t in_min_show(struct device *dev, struct device_attribute *da,
 			   char *buf)
 {
 	struct sensor_device_attribute *attr = to_sensor_dev_attr(da);
@@ -171,7 +168,7 @@ static ssize_t show_in_min(struct device *dev, struct device_attribute *da,
 	return sprintf(buf, "%d\n", IN_FROM_REG(data->in_min[attr->index]));
 }
 
-static ssize_t show_in_max(struct device *dev, struct device_attribute *da,
+static ssize_t in_max_show(struct device *dev, struct device_attribute *da,
 			   char *buf)
 {
 	struct sensor_device_attribute *attr = to_sensor_dev_attr(da);
@@ -179,8 +176,8 @@ static ssize_t show_in_max(struct device *dev, struct device_attribute *da,
 	return sprintf(buf, "%d\n", IN_FROM_REG(data->in_max[attr->index]));
 }
 
-static ssize_t set_in_min(struct device *dev, struct device_attribute *da,
-			  const char *buf, size_t count)
+static ssize_t in_min_store(struct device *dev, struct device_attribute *da,
+			    const char *buf, size_t count)
 {
 	struct sensor_device_attribute *attr = to_sensor_dev_attr(da);
 	struct lm78_data *data = dev_get_drvdata(dev);
@@ -199,8 +196,8 @@ static ssize_t set_in_min(struct device *dev, struct device_attribute *da,
 	return count;
 }
 
-static ssize_t set_in_max(struct device *dev, struct device_attribute *da,
-			  const char *buf, size_t count)
+static ssize_t in_max_store(struct device *dev, struct device_attribute *da,
+			    const char *buf, size_t count)
 {
 	struct sensor_device_attribute *attr = to_sensor_dev_attr(da);
 	struct lm78_data *data = dev_get_drvdata(dev);
@@ -219,21 +216,27 @@ static ssize_t set_in_max(struct device *dev, struct device_attribute *da,
 	return count;
 }
 
-#define show_in_offset(offset)					\
-static SENSOR_DEVICE_ATTR(in##offset##_input, S_IRUGO,		\
-		show_in, NULL, offset);				\
-static SENSOR_DEVICE_ATTR(in##offset##_min, S_IRUGO | S_IWUSR,	\
-		show_in_min, set_in_min, offset);		\
-static SENSOR_DEVICE_ATTR(in##offset##_max, S_IRUGO | S_IWUSR,	\
-		show_in_max, set_in_max, offset);
-
-show_in_offset(0);
-show_in_offset(1);
-show_in_offset(2);
-show_in_offset(3);
-show_in_offset(4);
-show_in_offset(5);
-show_in_offset(6);
+static SENSOR_DEVICE_ATTR_RO(in0_input, in, 0);
+static SENSOR_DEVICE_ATTR_RW(in0_min, in_min, 0);
+static SENSOR_DEVICE_ATTR_RW(in0_max, in_max, 0);
+static SENSOR_DEVICE_ATTR_RO(in1_input, in, 1);
+static SENSOR_DEVICE_ATTR_RW(in1_min, in_min, 1);
+static SENSOR_DEVICE_ATTR_RW(in1_max, in_max, 1);
+static SENSOR_DEVICE_ATTR_RO(in2_input, in, 2);
+static SENSOR_DEVICE_ATTR_RW(in2_min, in_min, 2);
+static SENSOR_DEVICE_ATTR_RW(in2_max, in_max, 2);
+static SENSOR_DEVICE_ATTR_RO(in3_input, in, 3);
+static SENSOR_DEVICE_ATTR_RW(in3_min, in_min, 3);
+static SENSOR_DEVICE_ATTR_RW(in3_max, in_max, 3);
+static SENSOR_DEVICE_ATTR_RO(in4_input, in, 4);
+static SENSOR_DEVICE_ATTR_RW(in4_min, in_min, 4);
+static SENSOR_DEVICE_ATTR_RW(in4_max, in_max, 4);
+static SENSOR_DEVICE_ATTR_RO(in5_input, in, 5);
+static SENSOR_DEVICE_ATTR_RW(in5_min, in_min, 5);
+static SENSOR_DEVICE_ATTR_RW(in5_max, in_max, 5);
+static SENSOR_DEVICE_ATTR_RO(in6_input, in, 6);
+static SENSOR_DEVICE_ATTR_RW(in6_min, in_min, 6);
+static SENSOR_DEVICE_ATTR_RW(in6_max, in_max, 6);
 
 /* Temperature */
 static ssize_t temp1_input_show(struct device *dev,
@@ -300,7 +303,7 @@ static DEVICE_ATTR_RW(temp1_max);
 static DEVICE_ATTR_RW(temp1_max_hyst);
 
 /* 3 Fans */
-static ssize_t show_fan(struct device *dev, struct device_attribute *da,
+static ssize_t fan_show(struct device *dev, struct device_attribute *da,
 			char *buf)
 {
 	struct sensor_device_attribute *attr = to_sensor_dev_attr(da);
@@ -310,7 +313,7 @@ static ssize_t show_fan(struct device *dev, struct device_attribute *da,
 		DIV_FROM_REG(data->fan_div[nr])));
 }
 
-static ssize_t show_fan_min(struct device *dev, struct device_attribute *da,
+static ssize_t fan_min_show(struct device *dev, struct device_attribute *da,
 			    char *buf)
 {
 	struct sensor_device_attribute *attr = to_sensor_dev_attr(da);
@@ -320,8 +323,8 @@ static ssize_t show_fan_min(struct device *dev, struct device_attribute *da,
 		DIV_FROM_REG(data->fan_div[nr])));
 }
 
-static ssize_t set_fan_min(struct device *dev, struct device_attribute *da,
-			   const char *buf, size_t count)
+static ssize_t fan_min_store(struct device *dev, struct device_attribute *da,
+			     const char *buf, size_t count)
 {
 	struct sensor_device_attribute *attr = to_sensor_dev_attr(da);
 	struct lm78_data *data = dev_get_drvdata(dev);
@@ -340,7 +343,7 @@ static ssize_t set_fan_min(struct device *dev, struct device_attribute *da,
 	return count;
 }
 
-static ssize_t show_fan_div(struct device *dev, struct device_attribute *da,
+static ssize_t fan_div_show(struct device *dev, struct device_attribute *da,
 			    char *buf)
 {
 	struct sensor_device_attribute *attr = to_sensor_dev_attr(da);
@@ -354,8 +357,8 @@ static ssize_t show_fan_div(struct device *dev, struct device_attribute *da,
  * least surprise; the user doesn't expect the fan minimum to change just
  * because the divisor changed.
  */
-static ssize_t set_fan_div(struct device *dev, struct device_attribute *da,
-			   const char *buf, size_t count)
+static ssize_t fan_div_store(struct device *dev, struct device_attribute *da,
+			     const char *buf, size_t count)
 {
 	struct sensor_device_attribute *attr = to_sensor_dev_attr(da);
 	struct lm78_data *data = dev_get_drvdata(dev);
@@ -413,22 +416,17 @@ static ssize_t set_fan_div(struct device *dev, struct device_attribute *da,
 	return count;
 }
 
-#define show_fan_offset(offset)				\
-static SENSOR_DEVICE_ATTR(fan##offset##_input, S_IRUGO,		\
-		show_fan, NULL, offset - 1);			\
-static SENSOR_DEVICE_ATTR(fan##offset##_min, S_IRUGO | S_IWUSR,	\
-		show_fan_min, set_fan_min, offset - 1);
-
-show_fan_offset(1);
-show_fan_offset(2);
-show_fan_offset(3);
+static SENSOR_DEVICE_ATTR_RO(fan1_input, fan, 0);
+static SENSOR_DEVICE_ATTR_RW(fan1_min, fan_min, 0);
+static SENSOR_DEVICE_ATTR_RO(fan2_input, fan, 1);
+static SENSOR_DEVICE_ATTR_RW(fan2_min, fan_min, 1);
+static SENSOR_DEVICE_ATTR_RO(fan3_input, fan, 2);
+static SENSOR_DEVICE_ATTR_RW(fan3_min, fan_min, 2);
 
 /* Fan 3 divisor is locked in H/W */
-static SENSOR_DEVICE_ATTR(fan1_div, S_IRUGO | S_IWUSR,
-		show_fan_div, set_fan_div, 0);
-static SENSOR_DEVICE_ATTR(fan2_div, S_IRUGO | S_IWUSR,
-		show_fan_div, set_fan_div, 1);
-static SENSOR_DEVICE_ATTR(fan3_div, S_IRUGO, show_fan_div, NULL, 2);
+static SENSOR_DEVICE_ATTR_RW(fan1_div, fan_div, 0);
+static SENSOR_DEVICE_ATTR_RW(fan2_div, fan_div, 1);
+static SENSOR_DEVICE_ATTR_RO(fan3_div, fan_div, 2);
 
 /* VID */
 static ssize_t cpu0_vid_show(struct device *dev, struct device_attribute *da,
@@ -448,24 +446,24 @@ static ssize_t alarms_show(struct device *dev, struct device_attribute *da,
 }
 static DEVICE_ATTR_RO(alarms);
 
-static ssize_t show_alarm(struct device *dev, struct device_attribute *da,
+static ssize_t alarm_show(struct device *dev, struct device_attribute *da,
 			  char *buf)
 {
 	struct lm78_data *data = lm78_update_device(dev);
 	int nr = to_sensor_dev_attr(da)->index;
 	return sprintf(buf, "%u\n", (data->alarms >> nr) & 1);
 }
-static SENSOR_DEVICE_ATTR(in0_alarm, S_IRUGO, show_alarm, NULL, 0);
-static SENSOR_DEVICE_ATTR(in1_alarm, S_IRUGO, show_alarm, NULL, 1);
-static SENSOR_DEVICE_ATTR(in2_alarm, S_IRUGO, show_alarm, NULL, 2);
-static SENSOR_DEVICE_ATTR(in3_alarm, S_IRUGO, show_alarm, NULL, 3);
-static SENSOR_DEVICE_ATTR(in4_alarm, S_IRUGO, show_alarm, NULL, 8);
-static SENSOR_DEVICE_ATTR(in5_alarm, S_IRUGO, show_alarm, NULL, 9);
-static SENSOR_DEVICE_ATTR(in6_alarm, S_IRUGO, show_alarm, NULL, 10);
-static SENSOR_DEVICE_ATTR(fan1_alarm, S_IRUGO, show_alarm, NULL, 6);
-static SENSOR_DEVICE_ATTR(fan2_alarm, S_IRUGO, show_alarm, NULL, 7);
-static SENSOR_DEVICE_ATTR(fan3_alarm, S_IRUGO, show_alarm, NULL, 11);
-static SENSOR_DEVICE_ATTR(temp1_alarm, S_IRUGO, show_alarm, NULL, 4);
+static SENSOR_DEVICE_ATTR_RO(in0_alarm, alarm, 0);
+static SENSOR_DEVICE_ATTR_RO(in1_alarm, alarm, 1);
+static SENSOR_DEVICE_ATTR_RO(in2_alarm, alarm, 2);
+static SENSOR_DEVICE_ATTR_RO(in3_alarm, alarm, 3);
+static SENSOR_DEVICE_ATTR_RO(in4_alarm, alarm, 8);
+static SENSOR_DEVICE_ATTR_RO(in5_alarm, alarm, 9);
+static SENSOR_DEVICE_ATTR_RO(in6_alarm, alarm, 10);
+static SENSOR_DEVICE_ATTR_RO(fan1_alarm, alarm, 6);
+static SENSOR_DEVICE_ATTR_RO(fan2_alarm, alarm, 7);
+static SENSOR_DEVICE_ATTR_RO(fan3_alarm, alarm, 11);
+static SENSOR_DEVICE_ATTR_RO(temp1_alarm, alarm, 4);
 
 static struct attribute *lm78_attrs[] = {
 	&sensor_dev_attr_in0_input.dev_attr.attr,
diff --git a/drivers/hwmon/lm85.c b/drivers/hwmon/lm85.c
index a95d48316f06..80db367b4c54 100644
--- a/drivers/hwmon/lm85.c
+++ b/drivers/hwmon/lm85.c
@@ -165,7 +165,6 @@ static inline u16 FAN_TO_REG(unsigned long val)
 #define PWM_TO_REG(val)			clamp_val(val, 0, 255)
 #define PWM_FROM_REG(val)		(val)
 
-
 /*
  * ZONEs have the following parameters:
  *    Limit (low) temp,           1. degC
@@ -563,24 +562,25 @@ static struct lm85_data *lm85_update_device(struct device *dev)
 }
 
 /* 4 Fans */
-static ssize_t show_fan(struct device *dev, struct device_attribute *attr,
-		char *buf)
+static ssize_t fan_show(struct device *dev, struct device_attribute *attr,
+			char *buf)
 {
 	int nr = to_sensor_dev_attr(attr)->index;
 	struct lm85_data *data = lm85_update_device(dev);
 	return sprintf(buf, "%d\n", FAN_FROM_REG(data->fan[nr]));
 }
 
-static ssize_t show_fan_min(struct device *dev, struct device_attribute *attr,
-		char *buf)
+static ssize_t fan_min_show(struct device *dev, struct device_attribute *attr,
+			    char *buf)
 {
 	int nr = to_sensor_dev_attr(attr)->index;
 	struct lm85_data *data = lm85_update_device(dev);
 	return sprintf(buf, "%d\n", FAN_FROM_REG(data->fan_min[nr]));
 }
 
-static ssize_t set_fan_min(struct device *dev, struct device_attribute *attr,
-		const char *buf, size_t count)
+static ssize_t fan_min_store(struct device *dev,
+			     struct device_attribute *attr, const char *buf,
+			     size_t count)
 {
 	int nr = to_sensor_dev_attr(attr)->index;
 	struct lm85_data *data = dev_get_drvdata(dev);
@@ -599,16 +599,14 @@ static ssize_t set_fan_min(struct device *dev, struct device_attribute *attr,
 	return count;
 }
 
-#define show_fan_offset(offset)						\
-static SENSOR_DEVICE_ATTR(fan##offset##_input, S_IRUGO,			\
-		show_fan, NULL, offset - 1);				\
-static SENSOR_DEVICE_ATTR(fan##offset##_min, S_IRUGO | S_IWUSR,		\
-		show_fan_min, set_fan_min, offset - 1)
-
-show_fan_offset(1);
-show_fan_offset(2);
-show_fan_offset(3);
-show_fan_offset(4);
+static SENSOR_DEVICE_ATTR_RO(fan1_input, fan, 0);
+static SENSOR_DEVICE_ATTR_RW(fan1_min, fan_min, 0);
+static SENSOR_DEVICE_ATTR_RO(fan2_input, fan, 1);
+static SENSOR_DEVICE_ATTR_RW(fan2_min, fan_min, 1);
+static SENSOR_DEVICE_ATTR_RO(fan3_input, fan, 2);
+static SENSOR_DEVICE_ATTR_RW(fan3_min, fan_min, 2);
+static SENSOR_DEVICE_ATTR_RO(fan4_input, fan, 3);
+static SENSOR_DEVICE_ATTR_RW(fan4_min, fan_min, 3);
 
 /* vid, vrm, alarms */
 
@@ -667,44 +665,44 @@ static ssize_t alarms_show(struct device *dev, struct device_attribute *attr,
 
 static DEVICE_ATTR_RO(alarms);
 
-static ssize_t show_alarm(struct device *dev, struct device_attribute *attr,
-		char *buf)
+static ssize_t alarm_show(struct device *dev, struct device_attribute *attr,
+			  char *buf)
 {
 	int nr = to_sensor_dev_attr(attr)->index;
 	struct lm85_data *data = lm85_update_device(dev);
 	return sprintf(buf, "%u\n", (data->alarms >> nr) & 1);
 }
 
-static SENSOR_DEVICE_ATTR(in0_alarm, S_IRUGO, show_alarm, NULL, 0);
-static SENSOR_DEVICE_ATTR(in1_alarm, S_IRUGO, show_alarm, NULL, 1);
-static SENSOR_DEVICE_ATTR(in2_alarm, S_IRUGO, show_alarm, NULL, 2);
-static SENSOR_DEVICE_ATTR(in3_alarm, S_IRUGO, show_alarm, NULL, 3);
-static SENSOR_DEVICE_ATTR(in4_alarm, S_IRUGO, show_alarm, NULL, 8);
-static SENSOR_DEVICE_ATTR(in5_alarm, S_IRUGO, show_alarm, NULL, 18);
-static SENSOR_DEVICE_ATTR(in6_alarm, S_IRUGO, show_alarm, NULL, 16);
-static SENSOR_DEVICE_ATTR(in7_alarm, S_IRUGO, show_alarm, NULL, 17);
-static SENSOR_DEVICE_ATTR(temp1_alarm, S_IRUGO, show_alarm, NULL, 4);
-static SENSOR_DEVICE_ATTR(temp1_fault, S_IRUGO, show_alarm, NULL, 14);
-static SENSOR_DEVICE_ATTR(temp2_alarm, S_IRUGO, show_alarm, NULL, 5);
-static SENSOR_DEVICE_ATTR(temp3_alarm, S_IRUGO, show_alarm, NULL, 6);
-static SENSOR_DEVICE_ATTR(temp3_fault, S_IRUGO, show_alarm, NULL, 15);
-static SENSOR_DEVICE_ATTR(fan1_alarm, S_IRUGO, show_alarm, NULL, 10);
-static SENSOR_DEVICE_ATTR(fan2_alarm, S_IRUGO, show_alarm, NULL, 11);
-static SENSOR_DEVICE_ATTR(fan3_alarm, S_IRUGO, show_alarm, NULL, 12);
-static SENSOR_DEVICE_ATTR(fan4_alarm, S_IRUGO, show_alarm, NULL, 13);
+static SENSOR_DEVICE_ATTR_RO(in0_alarm, alarm, 0);
+static SENSOR_DEVICE_ATTR_RO(in1_alarm, alarm, 1);
+static SENSOR_DEVICE_ATTR_RO(in2_alarm, alarm, 2);
+static SENSOR_DEVICE_ATTR_RO(in3_alarm, alarm, 3);
+static SENSOR_DEVICE_ATTR_RO(in4_alarm, alarm, 8);
+static SENSOR_DEVICE_ATTR_RO(in5_alarm, alarm, 18);
+static SENSOR_DEVICE_ATTR_RO(in6_alarm, alarm, 16);
+static SENSOR_DEVICE_ATTR_RO(in7_alarm, alarm, 17);
+static SENSOR_DEVICE_ATTR_RO(temp1_alarm, alarm, 4);
+static SENSOR_DEVICE_ATTR_RO(temp1_fault, alarm, 14);
+static SENSOR_DEVICE_ATTR_RO(temp2_alarm, alarm, 5);
+static SENSOR_DEVICE_ATTR_RO(temp3_alarm, alarm, 6);
+static SENSOR_DEVICE_ATTR_RO(temp3_fault, alarm, 15);
+static SENSOR_DEVICE_ATTR_RO(fan1_alarm, alarm, 10);
+static SENSOR_DEVICE_ATTR_RO(fan2_alarm, alarm, 11);
+static SENSOR_DEVICE_ATTR_RO(fan3_alarm, alarm, 12);
+static SENSOR_DEVICE_ATTR_RO(fan4_alarm, alarm, 13);
 
 /* pwm */
 
-static ssize_t show_pwm(struct device *dev, struct device_attribute *attr,
-		char *buf)
+static ssize_t pwm_show(struct device *dev, struct device_attribute *attr,
+			char *buf)
 {
 	int nr = to_sensor_dev_attr(attr)->index;
 	struct lm85_data *data = lm85_update_device(dev);
 	return sprintf(buf, "%d\n", PWM_FROM_REG(data->pwm[nr]));
 }
 
-static ssize_t set_pwm(struct device *dev, struct device_attribute *attr,
-		const char *buf, size_t count)
+static ssize_t pwm_store(struct device *dev, struct device_attribute *attr,
+			 const char *buf, size_t count)
 {
 	int nr = to_sensor_dev_attr(attr)->index;
 	struct lm85_data *data = dev_get_drvdata(dev);
@@ -723,8 +721,8 @@ static ssize_t set_pwm(struct device *dev, struct device_attribute *attr,
 	return count;
 }
 
-static ssize_t show_pwm_enable(struct device *dev, struct device_attribute
-		*attr, char *buf)
+static ssize_t pwm_enable_show(struct device *dev,
+			       struct device_attribute *attr, char *buf)
 {
 	int nr = to_sensor_dev_attr(attr)->index;
 	struct lm85_data *data = lm85_update_device(dev);
@@ -745,8 +743,9 @@ static ssize_t show_pwm_enable(struct device *dev, struct device_attribute
 	return sprintf(buf, "%d\n", enable);
 }
 
-static ssize_t set_pwm_enable(struct device *dev, struct device_attribute
-		*attr, const char *buf, size_t count)
+static ssize_t pwm_enable_store(struct device *dev,
+				struct device_attribute *attr,
+				const char *buf, size_t count)
 {
 	int nr = to_sensor_dev_attr(attr)->index;
 	struct lm85_data *data = dev_get_drvdata(dev);
@@ -788,8 +787,8 @@ static ssize_t set_pwm_enable(struct device *dev, struct device_attribute
 	return count;
 }
 
-static ssize_t show_pwm_freq(struct device *dev,
-		struct device_attribute *attr, char *buf)
+static ssize_t pwm_freq_show(struct device *dev,
+			     struct device_attribute *attr, char *buf)
 {
 	int nr = to_sensor_dev_attr(attr)->index;
 	struct lm85_data *data = lm85_update_device(dev);
@@ -804,8 +803,9 @@ static ssize_t show_pwm_freq(struct device *dev,
 	return sprintf(buf, "%d\n", freq);
 }
 
-static ssize_t set_pwm_freq(struct device *dev,
-		struct device_attribute *attr, const char *buf, size_t count)
+static ssize_t pwm_freq_store(struct device *dev,
+			      struct device_attribute *attr, const char *buf,
+			      size_t count)
 {
 	int nr = to_sensor_dev_attr(attr)->index;
 	struct lm85_data *data = dev_get_drvdata(dev);
@@ -841,22 +841,20 @@ static ssize_t set_pwm_freq(struct device *dev,
 	return count;
 }
 
-#define show_pwm_reg(offset)						\
-static SENSOR_DEVICE_ATTR(pwm##offset, S_IRUGO | S_IWUSR,		\
-		show_pwm, set_pwm, offset - 1);				\
-static SENSOR_DEVICE_ATTR(pwm##offset##_enable, S_IRUGO | S_IWUSR,	\
-		show_pwm_enable, set_pwm_enable, offset - 1);		\
-static SENSOR_DEVICE_ATTR(pwm##offset##_freq, S_IRUGO | S_IWUSR,	\
-		show_pwm_freq, set_pwm_freq, offset - 1)
-
-show_pwm_reg(1);
-show_pwm_reg(2);
-show_pwm_reg(3);
+static SENSOR_DEVICE_ATTR_RW(pwm1, pwm, 0);
+static SENSOR_DEVICE_ATTR_RW(pwm1_enable, pwm_enable, 0);
+static SENSOR_DEVICE_ATTR_RW(pwm1_freq, pwm_freq, 0);
+static SENSOR_DEVICE_ATTR_RW(pwm2, pwm, 1);
+static SENSOR_DEVICE_ATTR_RW(pwm2_enable, pwm_enable, 1);
+static SENSOR_DEVICE_ATTR_RW(pwm2_freq, pwm_freq, 1);
+static SENSOR_DEVICE_ATTR_RW(pwm3, pwm, 2);
+static SENSOR_DEVICE_ATTR_RW(pwm3_enable, pwm_enable, 2);
+static SENSOR_DEVICE_ATTR_RW(pwm3_freq, pwm_freq, 2);
 
 /* Voltages */
 
-static ssize_t show_in(struct device *dev, struct device_attribute *attr,
-		char *buf)
+static ssize_t in_show(struct device *dev, struct device_attribute *attr,
+		       char *buf)
 {
 	int nr = to_sensor_dev_attr(attr)->index;
 	struct lm85_data *data = lm85_update_device(dev);
@@ -864,16 +862,16 @@ static ssize_t show_in(struct device *dev, struct device_attribute *attr,
 						    data->in_ext[nr]));
 }
 
-static ssize_t show_in_min(struct device *dev, struct device_attribute *attr,
-		char *buf)
+static ssize_t in_min_show(struct device *dev, struct device_attribute *attr,
+			   char *buf)
 {
 	int nr = to_sensor_dev_attr(attr)->index;
 	struct lm85_data *data = lm85_update_device(dev);
 	return sprintf(buf, "%d\n", INS_FROM_REG(nr, data->in_min[nr]));
 }
 
-static ssize_t set_in_min(struct device *dev, struct device_attribute *attr,
-		const char *buf, size_t count)
+static ssize_t in_min_store(struct device *dev, struct device_attribute *attr,
+			    const char *buf, size_t count)
 {
 	int nr = to_sensor_dev_attr(attr)->index;
 	struct lm85_data *data = dev_get_drvdata(dev);
@@ -892,16 +890,16 @@ static ssize_t set_in_min(struct device *dev, struct device_attribute *attr,
 	return count;
 }
 
-static ssize_t show_in_max(struct device *dev, struct device_attribute *attr,
-		char *buf)
+static ssize_t in_max_show(struct device *dev, struct device_attribute *attr,
+			   char *buf)
 {
 	int nr = to_sensor_dev_attr(attr)->index;
 	struct lm85_data *data = lm85_update_device(dev);
 	return sprintf(buf, "%d\n", INS_FROM_REG(nr, data->in_max[nr]));
 }
 
-static ssize_t set_in_max(struct device *dev, struct device_attribute *attr,
-		const char *buf, size_t count)
+static ssize_t in_max_store(struct device *dev, struct device_attribute *attr,
+			    const char *buf, size_t count)
 {
 	int nr = to_sensor_dev_attr(attr)->index;
 	struct lm85_data *data = dev_get_drvdata(dev);
@@ -920,27 +918,35 @@ static ssize_t set_in_max(struct device *dev, struct device_attribute *attr,
 	return count;
 }
 
-#define show_in_reg(offset)						\
-static SENSOR_DEVICE_ATTR(in##offset##_input, S_IRUGO,			\
-		show_in, NULL, offset);					\
-static SENSOR_DEVICE_ATTR(in##offset##_min, S_IRUGO | S_IWUSR,		\
-		show_in_min, set_in_min, offset);			\
-static SENSOR_DEVICE_ATTR(in##offset##_max, S_IRUGO | S_IWUSR,		\
-		show_in_max, set_in_max, offset)
-
-show_in_reg(0);
-show_in_reg(1);
-show_in_reg(2);
-show_in_reg(3);
-show_in_reg(4);
-show_in_reg(5);
-show_in_reg(6);
-show_in_reg(7);
+static SENSOR_DEVICE_ATTR_RO(in0_input, in, 0);
+static SENSOR_DEVICE_ATTR_RW(in0_min, in_min, 0);
+static SENSOR_DEVICE_ATTR_RW(in0_max, in_max, 0);
+static SENSOR_DEVICE_ATTR_RO(in1_input, in, 1);
+static SENSOR_DEVICE_ATTR_RW(in1_min, in_min, 1);
+static SENSOR_DEVICE_ATTR_RW(in1_max, in_max, 1);
+static SENSOR_DEVICE_ATTR_RO(in2_input, in, 2);
+static SENSOR_DEVICE_ATTR_RW(in2_min, in_min, 2);
+static SENSOR_DEVICE_ATTR_RW(in2_max, in_max, 2);
+static SENSOR_DEVICE_ATTR_RO(in3_input, in, 3);
+static SENSOR_DEVICE_ATTR_RW(in3_min, in_min, 3);
+static SENSOR_DEVICE_ATTR_RW(in3_max, in_max, 3);
+static SENSOR_DEVICE_ATTR_RO(in4_input, in, 4);
+static SENSOR_DEVICE_ATTR_RW(in4_min, in_min, 4);
+static SENSOR_DEVICE_ATTR_RW(in4_max, in_max, 4);
+static SENSOR_DEVICE_ATTR_RO(in5_input, in, 5);
+static SENSOR_DEVICE_ATTR_RW(in5_min, in_min, 5);
+static SENSOR_DEVICE_ATTR_RW(in5_max, in_max, 5);
+static SENSOR_DEVICE_ATTR_RO(in6_input, in, 6);
+static SENSOR_DEVICE_ATTR_RW(in6_min, in_min, 6);
+static SENSOR_DEVICE_ATTR_RW(in6_max, in_max, 6);
+static SENSOR_DEVICE_ATTR_RO(in7_input, in, 7);
+static SENSOR_DEVICE_ATTR_RW(in7_min, in_min, 7);
+static SENSOR_DEVICE_ATTR_RW(in7_max, in_max, 7);
 
 /* Temps */
 
-static ssize_t show_temp(struct device *dev, struct device_attribute *attr,
-		char *buf)
+static ssize_t temp_show(struct device *dev, struct device_attribute *attr,
+			 char *buf)
 {
 	int nr = to_sensor_dev_attr(attr)->index;
 	struct lm85_data *data = lm85_update_device(dev);
@@ -948,16 +954,17 @@ static ssize_t show_temp(struct device *dev, struct device_attribute *attr,
 						     data->temp_ext[nr]));
 }
 
-static ssize_t show_temp_min(struct device *dev, struct device_attribute *attr,
-		char *buf)
+static ssize_t temp_min_show(struct device *dev,
+			     struct device_attribute *attr, char *buf)
 {
 	int nr = to_sensor_dev_attr(attr)->index;
 	struct lm85_data *data = lm85_update_device(dev);
 	return sprintf(buf, "%d\n", TEMP_FROM_REG(data->temp_min[nr]));
 }
 
-static ssize_t set_temp_min(struct device *dev, struct device_attribute *attr,
-		const char *buf, size_t count)
+static ssize_t temp_min_store(struct device *dev,
+			      struct device_attribute *attr, const char *buf,
+			      size_t count)
 {
 	int nr = to_sensor_dev_attr(attr)->index;
 	struct lm85_data *data = dev_get_drvdata(dev);
@@ -979,16 +986,17 @@ static ssize_t set_temp_min(struct device *dev, struct device_attribute *attr,
 	return count;
 }
 
-static ssize_t show_temp_max(struct device *dev, struct device_attribute *attr,
-		char *buf)
+static ssize_t temp_max_show(struct device *dev,
+			     struct device_attribute *attr, char *buf)
 {
 	int nr = to_sensor_dev_attr(attr)->index;
 	struct lm85_data *data = lm85_update_device(dev);
 	return sprintf(buf, "%d\n", TEMP_FROM_REG(data->temp_max[nr]));
 }
 
-static ssize_t set_temp_max(struct device *dev, struct device_attribute *attr,
-		const char *buf, size_t count)
+static ssize_t temp_max_store(struct device *dev,
+			      struct device_attribute *attr, const char *buf,
+			      size_t count)
 {
 	int nr = to_sensor_dev_attr(attr)->index;
 	struct lm85_data *data = dev_get_drvdata(dev);
@@ -1010,31 +1018,30 @@ static ssize_t set_temp_max(struct device *dev, struct device_attribute *attr,
 	return count;
 }
 
-#define show_temp_reg(offset)						\
-static SENSOR_DEVICE_ATTR(temp##offset##_input, S_IRUGO,		\
-		show_temp, NULL, offset - 1);				\
-static SENSOR_DEVICE_ATTR(temp##offset##_min, S_IRUGO | S_IWUSR,	\
-		show_temp_min, set_temp_min, offset - 1);		\
-static SENSOR_DEVICE_ATTR(temp##offset##_max, S_IRUGO | S_IWUSR,	\
-		show_temp_max, set_temp_max, offset - 1);
-
-show_temp_reg(1);
-show_temp_reg(2);
-show_temp_reg(3);
-
+static SENSOR_DEVICE_ATTR_RO(temp1_input, temp, 0);
+static SENSOR_DEVICE_ATTR_RW(temp1_min, temp_min, 0);
+static SENSOR_DEVICE_ATTR_RW(temp1_max, temp_max, 0);
+static SENSOR_DEVICE_ATTR_RO(temp2_input, temp, 1);
+static SENSOR_DEVICE_ATTR_RW(temp2_min, temp_min, 1);
+static SENSOR_DEVICE_ATTR_RW(temp2_max, temp_max, 1);
+static SENSOR_DEVICE_ATTR_RO(temp3_input, temp, 2);
+static SENSOR_DEVICE_ATTR_RW(temp3_min, temp_min, 2);
+static SENSOR_DEVICE_ATTR_RW(temp3_max, temp_max, 2);
 
 /* Automatic PWM control */
 
-static ssize_t show_pwm_auto_channels(struct device *dev,
-		struct device_attribute *attr, char *buf)
+static ssize_t pwm_auto_channels_show(struct device *dev,
+				      struct device_attribute *attr,
+				      char *buf)
 {
 	int nr = to_sensor_dev_attr(attr)->index;
 	struct lm85_data *data = lm85_update_device(dev);
 	return sprintf(buf, "%d\n", ZONE_FROM_REG(data->autofan[nr].config));
 }
 
-static ssize_t set_pwm_auto_channels(struct device *dev,
-		struct device_attribute *attr, const char *buf, size_t count)
+static ssize_t pwm_auto_channels_store(struct device *dev,
+				       struct device_attribute *attr,
+				       const char *buf, size_t count)
 {
 	int nr = to_sensor_dev_attr(attr)->index;
 	struct lm85_data *data = dev_get_drvdata(dev);
@@ -1055,16 +1062,17 @@ static ssize_t set_pwm_auto_channels(struct device *dev,
 	return count;
 }
 
-static ssize_t show_pwm_auto_pwm_min(struct device *dev,
-		struct device_attribute *attr, char *buf)
+static ssize_t pwm_auto_pwm_min_show(struct device *dev,
+				     struct device_attribute *attr, char *buf)
 {
 	int nr = to_sensor_dev_attr(attr)->index;
 	struct lm85_data *data = lm85_update_device(dev);
 	return sprintf(buf, "%d\n", PWM_FROM_REG(data->autofan[nr].min_pwm));
 }
 
-static ssize_t set_pwm_auto_pwm_min(struct device *dev,
-		struct device_attribute *attr, const char *buf, size_t count)
+static ssize_t pwm_auto_pwm_min_store(struct device *dev,
+				      struct device_attribute *attr,
+				      const char *buf, size_t count)
 {
 	int nr = to_sensor_dev_attr(attr)->index;
 	struct lm85_data *data = dev_get_drvdata(dev);
@@ -1084,16 +1092,18 @@ static ssize_t set_pwm_auto_pwm_min(struct device *dev,
 	return count;
 }
 
-static ssize_t show_pwm_auto_pwm_minctl(struct device *dev,
-		struct device_attribute *attr, char *buf)
+static ssize_t pwm_auto_pwm_minctl_show(struct device *dev,
+					struct device_attribute *attr,
+					char *buf)
 {
 	int nr = to_sensor_dev_attr(attr)->index;
 	struct lm85_data *data = lm85_update_device(dev);
 	return sprintf(buf, "%d\n", data->autofan[nr].min_off);
 }
 
-static ssize_t set_pwm_auto_pwm_minctl(struct device *dev,
-		struct device_attribute *attr, const char *buf, size_t count)
+static ssize_t pwm_auto_pwm_minctl_store(struct device *dev,
+					 struct device_attribute *attr,
+					 const char *buf, size_t count)
 {
 	int nr = to_sensor_dev_attr(attr)->index;
 	struct lm85_data *data = dev_get_drvdata(dev);
@@ -1117,25 +1127,21 @@ static ssize_t set_pwm_auto_pwm_minctl(struct device *dev,
 	return count;
 }
 
-#define pwm_auto(offset)						\
-static SENSOR_DEVICE_ATTR(pwm##offset##_auto_channels,			\
-		S_IRUGO | S_IWUSR, show_pwm_auto_channels,		\
-		set_pwm_auto_channels, offset - 1);			\
-static SENSOR_DEVICE_ATTR(pwm##offset##_auto_pwm_min,			\
-		S_IRUGO | S_IWUSR, show_pwm_auto_pwm_min,		\
-		set_pwm_auto_pwm_min, offset - 1);			\
-static SENSOR_DEVICE_ATTR(pwm##offset##_auto_pwm_minctl,		\
-		S_IRUGO | S_IWUSR, show_pwm_auto_pwm_minctl,		\
-		set_pwm_auto_pwm_minctl, offset - 1)
-
-pwm_auto(1);
-pwm_auto(2);
-pwm_auto(3);
+static SENSOR_DEVICE_ATTR_RW(pwm1_auto_channels, pwm_auto_channels, 0);
+static SENSOR_DEVICE_ATTR_RW(pwm1_auto_pwm_min, pwm_auto_pwm_min, 0);
+static SENSOR_DEVICE_ATTR_RW(pwm1_auto_pwm_minctl, pwm_auto_pwm_minctl, 0);
+static SENSOR_DEVICE_ATTR_RW(pwm2_auto_channels, pwm_auto_channels, 1);
+static SENSOR_DEVICE_ATTR_RW(pwm2_auto_pwm_min, pwm_auto_pwm_min, 1);
+static SENSOR_DEVICE_ATTR_RW(pwm2_auto_pwm_minctl, pwm_auto_pwm_minctl, 1);
+static SENSOR_DEVICE_ATTR_RW(pwm3_auto_channels, pwm_auto_channels, 2);
+static SENSOR_DEVICE_ATTR_RW(pwm3_auto_pwm_min, pwm_auto_pwm_min, 2);
+static SENSOR_DEVICE_ATTR_RW(pwm3_auto_pwm_minctl, pwm_auto_pwm_minctl, 2);
 
 /* Temperature settings for automatic PWM control */
 
-static ssize_t show_temp_auto_temp_off(struct device *dev,
-		struct device_attribute *attr, char *buf)
+static ssize_t temp_auto_temp_off_show(struct device *dev,
+				       struct device_attribute *attr,
+				       char *buf)
 {
 	int nr = to_sensor_dev_attr(attr)->index;
 	struct lm85_data *data = lm85_update_device(dev);
@@ -1143,8 +1149,9 @@ static ssize_t show_temp_auto_temp_off(struct device *dev,
 		HYST_FROM_REG(data->zone[nr].hyst));
 }
 
-static ssize_t set_temp_auto_temp_off(struct device *dev,
-		struct device_attribute *attr, const char *buf, size_t count)
+static ssize_t temp_auto_temp_off_store(struct device *dev,
+					struct device_attribute *attr,
+					const char *buf, size_t count)
 {
 	int nr = to_sensor_dev_attr(attr)->index;
 	struct lm85_data *data = dev_get_drvdata(dev);
@@ -1172,16 +1179,18 @@ static ssize_t set_temp_auto_temp_off(struct device *dev,
 	return count;
 }
 
-static ssize_t show_temp_auto_temp_min(struct device *dev,
-		struct device_attribute *attr, char *buf)
+static ssize_t temp_auto_temp_min_show(struct device *dev,
+				       struct device_attribute *attr,
+				       char *buf)
 {
 	int nr = to_sensor_dev_attr(attr)->index;
 	struct lm85_data *data = lm85_update_device(dev);
 	return sprintf(buf, "%d\n", TEMP_FROM_REG(data->zone[nr].limit));
 }
 
-static ssize_t set_temp_auto_temp_min(struct device *dev,
-		struct device_attribute *attr, const char *buf, size_t count)
+static ssize_t temp_auto_temp_min_store(struct device *dev,
+					struct device_attribute *attr,
+					const char *buf, size_t count)
 {
 	int nr = to_sensor_dev_attr(attr)->index;
 	struct lm85_data *data = dev_get_drvdata(dev);
@@ -1210,8 +1219,9 @@ static ssize_t set_temp_auto_temp_min(struct device *dev,
 	return count;
 }
 
-static ssize_t show_temp_auto_temp_max(struct device *dev,
-		struct device_attribute *attr, char *buf)
+static ssize_t temp_auto_temp_max_show(struct device *dev,
+				       struct device_attribute *attr,
+				       char *buf)
 {
 	int nr = to_sensor_dev_attr(attr)->index;
 	struct lm85_data *data = lm85_update_device(dev);
@@ -1219,8 +1229,9 @@ static ssize_t show_temp_auto_temp_max(struct device *dev,
 		RANGE_FROM_REG(data->zone[nr].range));
 }
 
-static ssize_t set_temp_auto_temp_max(struct device *dev,
-		struct device_attribute *attr, const char *buf, size_t count)
+static ssize_t temp_auto_temp_max_store(struct device *dev,
+					struct device_attribute *attr,
+					const char *buf, size_t count)
 {
 	int nr = to_sensor_dev_attr(attr)->index;
 	struct lm85_data *data = dev_get_drvdata(dev);
@@ -1245,16 +1256,18 @@ static ssize_t set_temp_auto_temp_max(struct device *dev,
 	return count;
 }
 
-static ssize_t show_temp_auto_temp_crit(struct device *dev,
-		struct device_attribute *attr, char *buf)
+static ssize_t temp_auto_temp_crit_show(struct device *dev,
+					struct device_attribute *attr,
+					char *buf)
 {
 	int nr = to_sensor_dev_attr(attr)->index;
 	struct lm85_data *data = lm85_update_device(dev);
 	return sprintf(buf, "%d\n", TEMP_FROM_REG(data->zone[nr].critical));
 }
 
-static ssize_t set_temp_auto_temp_crit(struct device *dev,
-		struct device_attribute *attr, const char *buf, size_t count)
+static ssize_t temp_auto_temp_crit_store(struct device *dev,
+					 struct device_attribute *attr,
+					 const char *buf, size_t count)
 {
 	int nr = to_sensor_dev_attr(attr)->index;
 	struct lm85_data *data = dev_get_drvdata(dev);
@@ -1274,23 +1287,18 @@ static ssize_t set_temp_auto_temp_crit(struct device *dev,
 	return count;
 }
 
-#define temp_auto(offset)						\
-static SENSOR_DEVICE_ATTR(temp##offset##_auto_temp_off,			\
-		S_IRUGO | S_IWUSR, show_temp_auto_temp_off,		\
-		set_temp_auto_temp_off, offset - 1);			\
-static SENSOR_DEVICE_ATTR(temp##offset##_auto_temp_min,			\
-		S_IRUGO | S_IWUSR, show_temp_auto_temp_min,		\
-		set_temp_auto_temp_min, offset - 1);			\
-static SENSOR_DEVICE_ATTR(temp##offset##_auto_temp_max,			\
-		S_IRUGO | S_IWUSR, show_temp_auto_temp_max,		\
-		set_temp_auto_temp_max, offset - 1);			\
-static SENSOR_DEVICE_ATTR(temp##offset##_auto_temp_crit,		\
-		S_IRUGO | S_IWUSR, show_temp_auto_temp_crit,		\
-		set_temp_auto_temp_crit, offset - 1);
-
-temp_auto(1);
-temp_auto(2);
-temp_auto(3);
+static SENSOR_DEVICE_ATTR_RW(temp1_auto_temp_off, temp_auto_temp_off, 0);
+static SENSOR_DEVICE_ATTR_RW(temp1_auto_temp_min, temp_auto_temp_min, 0);
+static SENSOR_DEVICE_ATTR_RW(temp1_auto_temp_max, temp_auto_temp_max, 0);
+static SENSOR_DEVICE_ATTR_RW(temp1_auto_temp_crit, temp_auto_temp_crit, 0);
+static SENSOR_DEVICE_ATTR_RW(temp2_auto_temp_off, temp_auto_temp_off, 1);
+static SENSOR_DEVICE_ATTR_RW(temp2_auto_temp_min, temp_auto_temp_min, 1);
+static SENSOR_DEVICE_ATTR_RW(temp2_auto_temp_max, temp_auto_temp_max, 1);
+static SENSOR_DEVICE_ATTR_RW(temp2_auto_temp_crit, temp_auto_temp_crit, 1);
+static SENSOR_DEVICE_ATTR_RW(temp3_auto_temp_off, temp_auto_temp_off, 2);
+static SENSOR_DEVICE_ATTR_RW(temp3_auto_temp_min, temp_auto_temp_min, 2);
+static SENSOR_DEVICE_ATTR_RW(temp3_auto_temp_max, temp_auto_temp_max, 2);
+static SENSOR_DEVICE_ATTR_RW(temp3_auto_temp_crit, temp_auto_temp_crit, 2);
 
 static struct attribute *lm85_attributes[] = {
 	&sensor_dev_attr_fan1_input.dev_attr.attr,
@@ -1642,7 +1650,7 @@ static const struct i2c_device_id lm85_id[] = {
 };
 MODULE_DEVICE_TABLE(i2c, lm85_id);
 
-static const struct of_device_id lm85_of_match[] = {
+static const struct of_device_id __maybe_unused lm85_of_match[] = {
 	{
 		.compatible = "adi,adm1027",
 		.data = (void *)adm1027
diff --git a/drivers/hwmon/lm87.c b/drivers/hwmon/lm87.c
index b48d30760388..644e61eae574 100644
--- a/drivers/hwmon/lm87.c
+++ b/drivers/hwmon/lm87.c
@@ -276,8 +276,8 @@ static struct lm87_data *lm87_update_device(struct device *dev)
  * Sysfs stuff
  */
 
-static ssize_t show_in_input(struct device *dev, struct device_attribute *attr,
-			     char *buf)
+static ssize_t in_input_show(struct device *dev,
+			     struct device_attribute *attr, char *buf)
 {
 	struct lm87_data *data = lm87_update_device(dev);
 	int nr = to_sensor_dev_attr(attr)->index;
@@ -286,8 +286,8 @@ static ssize_t show_in_input(struct device *dev, struct device_attribute *attr,
 		       data->in_scale[nr]));
 }
 
-static ssize_t show_in_min(struct device *dev,
-				     struct device_attribute *attr, char *buf)
+static ssize_t in_min_show(struct device *dev, struct device_attribute *attr,
+			   char *buf)
 {
 	struct lm87_data *data = lm87_update_device(dev);
 	int nr = to_sensor_dev_attr(attr)->index;
@@ -296,8 +296,8 @@ static ssize_t show_in_min(struct device *dev,
 		       data->in_scale[nr]));
 }
 
-static ssize_t show_in_max(struct device *dev,
-				     struct device_attribute *attr, char *buf)
+static ssize_t in_max_show(struct device *dev, struct device_attribute *attr,
+			   char *buf)
 {
 	struct lm87_data *data = lm87_update_device(dev);
 	int nr = to_sensor_dev_attr(attr)->index;
@@ -306,8 +306,8 @@ static ssize_t show_in_max(struct device *dev,
 		       data->in_scale[nr]));
 }
 
-static ssize_t set_in_min(struct device *dev, struct device_attribute *attr,
-			  const char *buf, size_t count)
+static ssize_t in_min_store(struct device *dev, struct device_attribute *attr,
+			    const char *buf, size_t count)
 {
 	struct i2c_client *client = dev_get_drvdata(dev);
 	struct lm87_data *data = i2c_get_clientdata(client);
@@ -327,8 +327,8 @@ static ssize_t set_in_min(struct device *dev, struct device_attribute *attr,
 	return count;
 }
 
-static ssize_t set_in_max(struct device *dev,  struct device_attribute *attr,
-			  const char *buf, size_t count)
+static ssize_t in_max_store(struct device *dev, struct device_attribute *attr,
+			    const char *buf, size_t count)
 {
 	struct i2c_client *client = dev_get_drvdata(dev);
 	struct lm87_data *data = i2c_get_clientdata(client);
@@ -348,23 +348,32 @@ static ssize_t set_in_max(struct device *dev,  struct device_attribute *attr,
 	return count;
 }
 
-#define set_in(offset) \
-static SENSOR_DEVICE_ATTR(in##offset##_input, S_IRUGO, \
-		show_in_input, NULL, offset); \
-static SENSOR_DEVICE_ATTR(in##offset##_min, S_IRUGO | S_IWUSR, \
-		show_in_min, set_in_min, offset); \
-static SENSOR_DEVICE_ATTR(in##offset##_max, S_IRUGO | S_IWUSR, \
-		show_in_max, set_in_max, offset)
-set_in(0);
-set_in(1);
-set_in(2);
-set_in(3);
-set_in(4);
-set_in(5);
-set_in(6);
-set_in(7);
-
-static ssize_t show_temp_input(struct device *dev,
+static SENSOR_DEVICE_ATTR_RO(in0_input, in_input, 0);
+static SENSOR_DEVICE_ATTR_RW(in0_min, in_min, 0);
+static SENSOR_DEVICE_ATTR_RW(in0_max, in_max, 0);
+static SENSOR_DEVICE_ATTR_RO(in1_input, in_input, 1);
+static SENSOR_DEVICE_ATTR_RW(in1_min, in_min, 1);
+static SENSOR_DEVICE_ATTR_RW(in1_max, in_max, 1);
+static SENSOR_DEVICE_ATTR_RO(in2_input, in_input, 2);
+static SENSOR_DEVICE_ATTR_RW(in2_min, in_min, 2);
+static SENSOR_DEVICE_ATTR_RW(in2_max, in_max, 2);
+static SENSOR_DEVICE_ATTR_RO(in3_input, in_input, 3);
+static SENSOR_DEVICE_ATTR_RW(in3_min, in_min, 3);
+static SENSOR_DEVICE_ATTR_RW(in3_max, in_max, 3);
+static SENSOR_DEVICE_ATTR_RO(in4_input, in_input, 4);
+static SENSOR_DEVICE_ATTR_RW(in4_min, in_min, 4);
+static SENSOR_DEVICE_ATTR_RW(in4_max, in_max, 4);
+static SENSOR_DEVICE_ATTR_RO(in5_input, in_input, 5);
+static SENSOR_DEVICE_ATTR_RW(in5_min, in_min, 5);
+static SENSOR_DEVICE_ATTR_RW(in5_max, in_max, 5);
+static SENSOR_DEVICE_ATTR_RO(in6_input, in_input, 6);
+static SENSOR_DEVICE_ATTR_RW(in6_min, in_min, 6);
+static SENSOR_DEVICE_ATTR_RW(in6_max, in_max, 6);
+static SENSOR_DEVICE_ATTR_RO(in7_input, in_input, 7);
+static SENSOR_DEVICE_ATTR_RW(in7_min, in_min, 7);
+static SENSOR_DEVICE_ATTR_RW(in7_max, in_max, 7);
+
+static ssize_t temp_input_show(struct device *dev,
 			       struct device_attribute *attr, char *buf)
 {
 	struct lm87_data *data = lm87_update_device(dev);
@@ -373,7 +382,7 @@ static ssize_t show_temp_input(struct device *dev,
 	return sprintf(buf, "%d\n", TEMP_FROM_REG(data->temp[nr]));
 }
 
-static ssize_t show_temp_low(struct device *dev,
+static ssize_t temp_low_show(struct device *dev,
 			     struct device_attribute *attr, char *buf)
 {
 	struct lm87_data *data = lm87_update_device(dev);
@@ -383,7 +392,7 @@ static ssize_t show_temp_low(struct device *dev,
 		       TEMP_FROM_REG(data->temp_low[nr]));
 }
 
-static ssize_t show_temp_high(struct device *dev,
+static ssize_t temp_high_show(struct device *dev,
 			      struct device_attribute *attr, char *buf)
 {
 	struct lm87_data *data = lm87_update_device(dev);
@@ -393,8 +402,9 @@ static ssize_t show_temp_high(struct device *dev,
 		       TEMP_FROM_REG(data->temp_high[nr]));
 }
 
-static ssize_t set_temp_low(struct device *dev, struct device_attribute *attr,
-			    const char *buf, size_t count)
+static ssize_t temp_low_store(struct device *dev,
+			      struct device_attribute *attr, const char *buf,
+			      size_t count)
 {
 	struct i2c_client *client = dev_get_drvdata(dev);
 	struct lm87_data *data = i2c_get_clientdata(client);
@@ -413,8 +423,9 @@ static ssize_t set_temp_low(struct device *dev, struct device_attribute *attr,
 	return count;
 }
 
-static ssize_t set_temp_high(struct device *dev, struct device_attribute *attr,
-			     const char *buf, size_t count)
+static ssize_t temp_high_store(struct device *dev,
+			       struct device_attribute *attr, const char *buf,
+			       size_t count)
 {
 	struct i2c_client *client = dev_get_drvdata(dev);
 	struct lm87_data *data = i2c_get_clientdata(client);
@@ -433,16 +444,15 @@ static ssize_t set_temp_high(struct device *dev, struct device_attribute *attr,
 	return count;
 }
 
-#define set_temp(offset) \
-static SENSOR_DEVICE_ATTR(temp##offset##_input, S_IRUGO, \
-		show_temp_input, NULL, offset - 1); \
-static SENSOR_DEVICE_ATTR(temp##offset##_max, S_IRUGO | S_IWUSR, \
-		show_temp_high, set_temp_high, offset - 1); \
-static SENSOR_DEVICE_ATTR(temp##offset##_min, S_IRUGO | S_IWUSR, \
-		show_temp_low, set_temp_low, offset - 1)
-set_temp(1);
-set_temp(2);
-set_temp(3);
+static SENSOR_DEVICE_ATTR_RO(temp1_input, temp_input, 0);
+static SENSOR_DEVICE_ATTR_RW(temp1_min, temp_low, 0);
+static SENSOR_DEVICE_ATTR_RW(temp1_max, temp_high, 0);
+static SENSOR_DEVICE_ATTR_RO(temp2_input, temp_input, 1);
+static SENSOR_DEVICE_ATTR_RW(temp2_min, temp_low, 1);
+static SENSOR_DEVICE_ATTR_RW(temp2_max, temp_high, 1);
+static SENSOR_DEVICE_ATTR_RO(temp3_input, temp_input, 2);
+static SENSOR_DEVICE_ATTR_RW(temp3_min, temp_low, 2);
+static SENSOR_DEVICE_ATTR_RW(temp3_max, temp_high, 2);
 
 static ssize_t temp1_crit_show(struct device *dev,
 			       struct device_attribute *attr, char *buf)
@@ -460,9 +470,9 @@ static ssize_t temp2_crit_show(struct device *dev,
 
 static DEVICE_ATTR_RO(temp1_crit);
 static DEVICE_ATTR_RO(temp2_crit);
-static DEVICE_ATTR(temp3_crit, S_IRUGO, temp2_crit_show, NULL);
+static DEVICE_ATTR(temp3_crit, 0444, temp2_crit_show, NULL);
 
-static ssize_t show_fan_input(struct device *dev,
+static ssize_t fan_input_show(struct device *dev,
 			      struct device_attribute *attr, char *buf)
 {
 	struct lm87_data *data = lm87_update_device(dev);
@@ -472,8 +482,8 @@ static ssize_t show_fan_input(struct device *dev,
 		       FAN_DIV_FROM_REG(data->fan_div[nr])));
 }
 
-static ssize_t show_fan_min(struct device *dev,
-			    struct device_attribute *attr, char *buf)
+static ssize_t fan_min_show(struct device *dev, struct device_attribute *attr,
+			    char *buf)
 {
 	struct lm87_data *data = lm87_update_device(dev);
 	int nr = to_sensor_dev_attr(attr)->index;
@@ -482,8 +492,8 @@ static ssize_t show_fan_min(struct device *dev,
 		       FAN_DIV_FROM_REG(data->fan_div[nr])));
 }
 
-static ssize_t show_fan_div(struct device *dev,
-			    struct device_attribute *attr, char *buf)
+static ssize_t fan_div_show(struct device *dev, struct device_attribute *attr,
+			    char *buf)
 {
 	struct lm87_data *data = lm87_update_device(dev);
 	int nr = to_sensor_dev_attr(attr)->index;
@@ -492,8 +502,9 @@ static ssize_t show_fan_div(struct device *dev,
 		       FAN_DIV_FROM_REG(data->fan_div[nr]));
 }
 
-static ssize_t set_fan_min(struct device *dev, struct device_attribute *attr,
-			   const char *buf, size_t count)
+static ssize_t fan_min_store(struct device *dev,
+			     struct device_attribute *attr, const char *buf,
+			     size_t count)
 {
 	struct i2c_client *client = dev_get_drvdata(dev);
 	struct lm87_data *data = i2c_get_clientdata(client);
@@ -519,8 +530,9 @@ static ssize_t set_fan_min(struct device *dev, struct device_attribute *attr,
  * of least surprise; the user doesn't expect the fan minimum to change just
  * because the divider changed.
  */
-static ssize_t set_fan_div(struct device *dev, struct device_attribute *attr,
-			   const char *buf, size_t count)
+static ssize_t fan_div_store(struct device *dev,
+			     struct device_attribute *attr, const char *buf,
+			     size_t count)
 {
 	struct i2c_client *client = dev_get_drvdata(dev);
 	struct lm87_data *data = i2c_get_clientdata(client);
@@ -575,15 +587,12 @@ static ssize_t set_fan_div(struct device *dev, struct device_attribute *attr,
 	return count;
 }
 
-#define set_fan(offset) \
-static SENSOR_DEVICE_ATTR(fan##offset##_input, S_IRUGO, \
-		show_fan_input, NULL, offset - 1); \
-static SENSOR_DEVICE_ATTR(fan##offset##_min, S_IRUGO | S_IWUSR, \
-		show_fan_min, set_fan_min, offset - 1); \
-static SENSOR_DEVICE_ATTR(fan##offset##_div, S_IRUGO | S_IWUSR, \
-		show_fan_div, set_fan_div, offset - 1)
-set_fan(1);
-set_fan(2);
+static SENSOR_DEVICE_ATTR_RO(fan1_input, fan_input, 0);
+static SENSOR_DEVICE_ATTR_RW(fan1_min, fan_min, 0);
+static SENSOR_DEVICE_ATTR_RW(fan1_div, fan_div, 0);
+static SENSOR_DEVICE_ATTR_RO(fan2_input, fan_input, 1);
+static SENSOR_DEVICE_ATTR_RW(fan2_min, fan_min, 1);
+static SENSOR_DEVICE_ATTR_RW(fan2_div, fan_div, 1);
 
 static ssize_t alarms_show(struct device *dev, struct device_attribute *attr,
 			   char *buf)
@@ -653,28 +662,28 @@ static ssize_t aout_output_store(struct device *dev,
 }
 static DEVICE_ATTR_RW(aout_output);
 
-static ssize_t show_alarm(struct device *dev, struct device_attribute *attr,
+static ssize_t alarm_show(struct device *dev, struct device_attribute *attr,
 			  char *buf)
 {
 	struct lm87_data *data = lm87_update_device(dev);
 	int bitnr = to_sensor_dev_attr(attr)->index;
 	return sprintf(buf, "%u\n", (data->alarms >> bitnr) & 1);
 }
-static SENSOR_DEVICE_ATTR(in0_alarm, S_IRUGO, show_alarm, NULL, 0);
-static SENSOR_DEVICE_ATTR(in1_alarm, S_IRUGO, show_alarm, NULL, 1);
-static SENSOR_DEVICE_ATTR(in2_alarm, S_IRUGO, show_alarm, NULL, 2);
-static SENSOR_DEVICE_ATTR(in3_alarm, S_IRUGO, show_alarm, NULL, 3);
-static SENSOR_DEVICE_ATTR(in4_alarm, S_IRUGO, show_alarm, NULL, 8);
-static SENSOR_DEVICE_ATTR(in5_alarm, S_IRUGO, show_alarm, NULL, 9);
-static SENSOR_DEVICE_ATTR(in6_alarm, S_IRUGO, show_alarm, NULL, 6);
-static SENSOR_DEVICE_ATTR(in7_alarm, S_IRUGO, show_alarm, NULL, 7);
-static SENSOR_DEVICE_ATTR(temp1_alarm, S_IRUGO, show_alarm, NULL, 4);
-static SENSOR_DEVICE_ATTR(temp2_alarm, S_IRUGO, show_alarm, NULL, 5);
-static SENSOR_DEVICE_ATTR(temp3_alarm, S_IRUGO, show_alarm, NULL, 5);
-static SENSOR_DEVICE_ATTR(fan1_alarm, S_IRUGO, show_alarm, NULL, 6);
-static SENSOR_DEVICE_ATTR(fan2_alarm, S_IRUGO, show_alarm, NULL, 7);
-static SENSOR_DEVICE_ATTR(temp2_fault, S_IRUGO, show_alarm, NULL, 14);
-static SENSOR_DEVICE_ATTR(temp3_fault, S_IRUGO, show_alarm, NULL, 15);
+static SENSOR_DEVICE_ATTR_RO(in0_alarm, alarm, 0);
+static SENSOR_DEVICE_ATTR_RO(in1_alarm, alarm, 1);
+static SENSOR_DEVICE_ATTR_RO(in2_alarm, alarm, 2);
+static SENSOR_DEVICE_ATTR_RO(in3_alarm, alarm, 3);
+static SENSOR_DEVICE_ATTR_RO(in4_alarm, alarm, 8);
+static SENSOR_DEVICE_ATTR_RO(in5_alarm, alarm, 9);
+static SENSOR_DEVICE_ATTR_RO(in6_alarm, alarm, 6);
+static SENSOR_DEVICE_ATTR_RO(in7_alarm, alarm, 7);
+static SENSOR_DEVICE_ATTR_RO(temp1_alarm, alarm, 4);
+static SENSOR_DEVICE_ATTR_RO(temp2_alarm, alarm, 5);
+static SENSOR_DEVICE_ATTR_RO(temp3_alarm, alarm, 5);
+static SENSOR_DEVICE_ATTR_RO(fan1_alarm, alarm, 6);
+static SENSOR_DEVICE_ATTR_RO(fan2_alarm, alarm, 7);
+static SENSOR_DEVICE_ATTR_RO(temp2_fault, alarm, 14);
+static SENSOR_DEVICE_ATTR_RO(temp3_fault, alarm, 15);
 
 /*
  * Real code
diff --git a/drivers/hwmon/lm90.c b/drivers/hwmon/lm90.c
index 480d70a51778..b99eda01696e 100644
--- a/drivers/hwmon/lm90.c
+++ b/drivers/hwmon/lm90.c
@@ -236,7 +236,7 @@ static const struct i2c_device_id lm90_id[] = {
 };
 MODULE_DEVICE_TABLE(i2c, lm90_id);
 
-static const struct of_device_id lm90_of_match[] = {
+static const struct of_device_id __maybe_unused lm90_of_match[] = {
 	{
 		.compatible = "adi,adm1032",
 		.data = (void *)adm1032
@@ -1720,16 +1720,6 @@ static void lm90_regulator_disable(void *regulator)
 	regulator_disable(regulator);
 }
 
-static const u32 lm90_chip_config[] = {
-	HWMON_C_REGISTER_TZ | HWMON_C_UPDATE_INTERVAL | HWMON_C_ALARMS,
-	0
-};
-
-static const struct hwmon_channel_info lm90_chip_info = {
-	.type = hwmon_chip,
-	.config = lm90_chip_config,
-};
-
 
 static const struct hwmon_ops lm90_ops = {
 	.is_visible = lm90_is_visible,
@@ -1792,7 +1782,8 @@ static int lm90_probe(struct i2c_client *client,
 	data->chip.ops = &lm90_ops;
 	data->chip.info = data->info;
 
-	data->info[0] = &lm90_chip_info;
+	data->info[0] = HWMON_CHANNEL_INFO(chip,
+		HWMON_C_REGISTER_TZ | HWMON_C_UPDATE_INTERVAL | HWMON_C_ALARMS);
 	data->info[1] = &data->temp_info;
 
 	info = &data->temp_info;
diff --git a/drivers/hwmon/lm95241.c b/drivers/hwmon/lm95241.c
index 3ff188937158..6c5215e6d448 100644
--- a/drivers/hwmon/lm95241.c
+++ b/drivers/hwmon/lm95241.c
@@ -418,33 +418,15 @@ static void lm95241_init_client(struct i2c_client *client,
 				  data->model);
 }
 
-static const u32 lm95241_chip_config[] = {
-	HWMON_C_UPDATE_INTERVAL,
-	0
-};
-
-static const struct hwmon_channel_info lm95241_chip = {
-	.type = hwmon_chip,
-	.config = lm95241_chip_config,
-};
-
-static const u32 lm95241_temp_config[] = {
-	HWMON_T_INPUT,
-	HWMON_T_INPUT | HWMON_T_MAX | HWMON_T_MIN | HWMON_T_TYPE |
-		HWMON_T_FAULT,
-	HWMON_T_INPUT | HWMON_T_MAX | HWMON_T_MIN | HWMON_T_TYPE |
-		HWMON_T_FAULT,
-	0
-};
-
-static const struct hwmon_channel_info lm95241_temp = {
-	.type = hwmon_temp,
-	.config = lm95241_temp_config,
-};
-
 static const struct hwmon_channel_info *lm95241_info[] = {
-	&lm95241_chip,
-	&lm95241_temp,
+	HWMON_CHANNEL_INFO(chip,
+			   HWMON_C_UPDATE_INTERVAL),
+	HWMON_CHANNEL_INFO(temp,
+			   HWMON_T_INPUT,
+			   HWMON_T_INPUT | HWMON_T_MAX | HWMON_T_MIN |
+			   HWMON_T_TYPE | HWMON_T_FAULT,
+			   HWMON_T_INPUT | HWMON_T_MAX | HWMON_T_MIN |
+			   HWMON_T_TYPE | HWMON_T_FAULT),
 	NULL
 };
 
diff --git a/drivers/hwmon/lm95245.c b/drivers/hwmon/lm95245.c
index e4cac3a04536..8d08ca8bbdf8 100644
--- a/drivers/hwmon/lm95245.c
+++ b/drivers/hwmon/lm95245.c
@@ -92,19 +92,6 @@ static const unsigned short normal_i2c[] = {
 #define LM95235_REVISION	0xB1
 #define LM95245_REVISION	0xB3
 
-static const u8 lm95245_reg_address[] = {
-	LM95245_REG_R_LOCAL_TEMPH_S,
-	LM95245_REG_R_LOCAL_TEMPL_S,
-	LM95245_REG_R_REMOTE_TEMPH_S,
-	LM95245_REG_R_REMOTE_TEMPL_S,
-	LM95245_REG_R_REMOTE_TEMPH_U,
-	LM95245_REG_R_REMOTE_TEMPL_U,
-	LM95245_REG_RW_LOCAL_OS_TCRIT_LIMIT,
-	LM95245_REG_RW_REMOTE_TCRIT_LIMIT,
-	LM95245_REG_RW_COMMON_HYSTERESIS,
-	LM95245_REG_R_STATUS1,
-};
-
 /* Client data (each client gets its own) */
 struct lm95245_data {
 	struct regmap *regmap;
@@ -545,32 +532,16 @@ static const struct regmap_config lm95245_regmap_config = {
 	.use_single_write = true,
 };
 
-static const u32 lm95245_chip_config[] = {
-	HWMON_C_UPDATE_INTERVAL,
-	0
-};
-
-static const struct hwmon_channel_info lm95245_chip = {
-	.type = hwmon_chip,
-	.config = lm95245_chip_config,
-};
-
-static const u32 lm95245_temp_config[] = {
-	HWMON_T_INPUT | HWMON_T_CRIT | HWMON_T_CRIT_HYST | HWMON_T_CRIT_ALARM,
-	HWMON_T_INPUT | HWMON_T_MAX | HWMON_T_MAX_HYST | HWMON_T_CRIT |
-		HWMON_T_CRIT_HYST | HWMON_T_FAULT | HWMON_T_MAX_ALARM |
-		HWMON_T_CRIT_ALARM | HWMON_T_TYPE | HWMON_T_OFFSET,
-	0
-};
-
-static const struct hwmon_channel_info lm95245_temp = {
-	.type = hwmon_temp,
-	.config = lm95245_temp_config,
-};
-
 static const struct hwmon_channel_info *lm95245_info[] = {
-	&lm95245_chip,
-	&lm95245_temp,
+	HWMON_CHANNEL_INFO(chip,
+			   HWMON_C_UPDATE_INTERVAL),
+	HWMON_CHANNEL_INFO(temp,
+			   HWMON_T_INPUT | HWMON_T_CRIT | HWMON_T_CRIT_HYST |
+			   HWMON_T_CRIT_ALARM,
+			   HWMON_T_INPUT | HWMON_T_MAX | HWMON_T_MAX_HYST |
+			   HWMON_T_CRIT | HWMON_T_CRIT_HYST | HWMON_T_FAULT |
+			   HWMON_T_MAX_ALARM | HWMON_T_CRIT_ALARM |
+			   HWMON_T_TYPE | HWMON_T_OFFSET),
 	NULL
 };
 
@@ -623,7 +594,7 @@ static const struct i2c_device_id lm95245_id[] = {
 };
 MODULE_DEVICE_TABLE(i2c, lm95245_id);
 
-static const struct of_device_id lm95245_of_match[] = {
+static const struct of_device_id __maybe_unused lm95245_of_match[] = {
 	{ .compatible = "national,lm95235" },
 	{ .compatible = "national,lm95245" },
 	{ },
diff --git a/drivers/hwmon/lochnagar-hwmon.c b/drivers/hwmon/lochnagar-hwmon.c
new file mode 100644
index 000000000000..8b19adf2eeb0
--- /dev/null
+++ b/drivers/hwmon/lochnagar-hwmon.c
@@ -0,0 +1,412 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Lochnagar hardware monitoring features
+ *
+ * Copyright (c) 2016-2019 Cirrus Logic, Inc. and
+ *                         Cirrus Logic International Semiconductor Ltd.
+ *
+ * Author: Lucas Tanure <tanureal@opensource.cirrus.com>
+ */
+
+#include <linux/delay.h>
+#include <linux/hwmon.h>
+#include <linux/hwmon-sysfs.h>
+#include <linux/i2c.h>
+#include <linux/math64.h>
+#include <linux/mfd/lochnagar.h>
+#include <linux/mfd/lochnagar2_regs.h>
+#include <linux/module.h>
+#include <linux/of.h>
+#include <linux/of_device.h>
+#include <linux/platform_device.h>
+#include <linux/regmap.h>
+
+#define LN2_MAX_NSAMPLE 1023
+#define LN2_SAMPLE_US   1670
+
+#define LN2_CURR_UNITS  1000
+#define LN2_VOLT_UNITS  1000
+#define LN2_TEMP_UNITS  1000
+#define LN2_PWR_UNITS   1000000
+
+static const char * const lochnagar_chan_names[] = {
+	"DBVDD1",
+	"1V8 DSP",
+	"1V8 CDC",
+	"VDDCORE DSP",
+	"AVDD 1V8",
+	"SYSVDD",
+	"VDDCORE CDC",
+	"MICVDD",
+};
+
+struct lochnagar_hwmon {
+	struct regmap *regmap;
+
+	long power_nsamples[ARRAY_SIZE(lochnagar_chan_names)];
+
+	/* Lock to ensure only a single sensor is read at a time */
+	struct mutex sensor_lock;
+};
+
+enum lochnagar_measure_mode {
+	LN2_CURR = 0,
+	LN2_VOLT,
+	LN2_TEMP,
+};
+
+/**
+ * float_to_long - Convert ieee754 reading from hardware to an integer
+ *
+ * @data: Value read from the hardware
+ * @precision: Units to multiply up to eg. 1000 = milli, 1000000 = micro
+ *
+ * Return: Converted integer reading
+ *
+ * Depending on the measurement type the hardware returns an ieee754
+ * floating point value in either volts, amps or celsius. This function
+ * will convert that into an integer in a smaller unit such as micro-amps
+ * or milli-celsius. The hardware does not return NaN, so consideration of
+ * that is not required.
+ */
+static long float_to_long(u32 data, u32 precision)
+{
+	u64 man = data & 0x007FFFFF;
+	int exp = ((data & 0x7F800000) >> 23) - 127 - 23;
+	bool negative = data & 0x80000000;
+	long result;
+
+	man = (man + (1 << 23)) * precision;
+
+	if (fls64(man) + exp > (int)sizeof(long) * 8 - 1)
+		result = LONG_MAX;
+	else if (exp < 0)
+		result = (man + (1ull << (-exp - 1))) >> -exp;
+	else
+		result = man << exp;
+
+	return negative ? -result : result;
+}
+
+static int do_measurement(struct regmap *regmap, int chan,
+			  enum lochnagar_measure_mode mode, int nsamples)
+{
+	unsigned int val;
+	int ret;
+
+	chan = 1 << (chan + LOCHNAGAR2_IMON_MEASURED_CHANNELS_SHIFT);
+
+	ret = regmap_write(regmap, LOCHNAGAR2_IMON_CTRL1,
+			   LOCHNAGAR2_IMON_ENA_MASK | chan | mode);
+	if (ret < 0)
+		return ret;
+
+	ret = regmap_write(regmap, LOCHNAGAR2_IMON_CTRL2, nsamples);
+	if (ret < 0)
+		return ret;
+
+	ret = regmap_write(regmap, LOCHNAGAR2_IMON_CTRL3,
+			   LOCHNAGAR2_IMON_CONFIGURE_MASK);
+	if (ret < 0)
+		return ret;
+
+	ret =  regmap_read_poll_timeout(regmap, LOCHNAGAR2_IMON_CTRL3, val,
+					val & LOCHNAGAR2_IMON_DONE_MASK,
+					1000, 10000);
+	if (ret < 0)
+		return ret;
+
+	ret = regmap_write(regmap, LOCHNAGAR2_IMON_CTRL3,
+			   LOCHNAGAR2_IMON_MEASURE_MASK);
+	if (ret < 0)
+		return ret;
+
+	/*
+	 * Actual measurement time is ~1.67mS per sample, approximate this
+	 * with a 1.5mS per sample msleep and then poll for success up to
+	 * ~0.17mS * 1023 (LN2_MAX_NSAMPLES). Normally for smaller values
+	 * of nsamples the poll will complete on the first loop due to
+	 * other latency in the system.
+	 */
+	msleep((nsamples * 3) / 2);
+
+	ret =  regmap_read_poll_timeout(regmap, LOCHNAGAR2_IMON_CTRL3, val,
+					val & LOCHNAGAR2_IMON_DONE_MASK,
+					5000, 200000);
+	if (ret < 0)
+		return ret;
+
+	return regmap_write(regmap, LOCHNAGAR2_IMON_CTRL3, 0);
+}
+
+static int request_data(struct regmap *regmap, int chan, u32 *data)
+{
+	unsigned int val;
+	int ret;
+
+	ret = regmap_write(regmap, LOCHNAGAR2_IMON_CTRL4,
+			   LOCHNAGAR2_IMON_DATA_REQ_MASK |
+			   chan << LOCHNAGAR2_IMON_CH_SEL_SHIFT);
+	if (ret < 0)
+		return ret;
+
+	ret =  regmap_read_poll_timeout(regmap, LOCHNAGAR2_IMON_CTRL4, val,
+					val & LOCHNAGAR2_IMON_DATA_RDY_MASK,
+					1000, 10000);
+	if (ret < 0)
+		return ret;
+
+	ret = regmap_read(regmap, LOCHNAGAR2_IMON_DATA1, &val);
+	if (ret < 0)
+		return ret;
+
+	*data = val << 16;
+
+	ret = regmap_read(regmap, LOCHNAGAR2_IMON_DATA2, &val);
+	if (ret < 0)
+		return ret;
+
+	*data |= val;
+
+	return regmap_write(regmap, LOCHNAGAR2_IMON_CTRL4, 0);
+}
+
+static int read_sensor(struct device *dev, int chan,
+		       enum lochnagar_measure_mode mode, int nsamples,
+		       unsigned int precision, long *val)
+{
+	struct lochnagar_hwmon *priv = dev_get_drvdata(dev);
+	struct regmap *regmap = priv->regmap;
+	u32 data;
+	int ret;
+
+	mutex_lock(&priv->sensor_lock);
+
+	ret = do_measurement(regmap, chan, mode, nsamples);
+	if (ret < 0) {
+		dev_err(dev, "Failed to perform measurement: %d\n", ret);
+		goto error;
+	}
+
+	ret = request_data(regmap, chan, &data);
+	if (ret < 0) {
+		dev_err(dev, "Failed to read measurement: %d\n", ret);
+		goto error;
+	}
+
+	*val = float_to_long(data, precision);
+
+error:
+	mutex_unlock(&priv->sensor_lock);
+
+	return ret;
+}
+
+static int read_power(struct device *dev, int chan, long *val)
+{
+	struct lochnagar_hwmon *priv = dev_get_drvdata(dev);
+	int nsamples = priv->power_nsamples[chan];
+	u64 power;
+	int ret;
+
+	if (!strcmp("SYSVDD", lochnagar_chan_names[chan])) {
+		power = 5 * LN2_PWR_UNITS;
+	} else {
+		ret = read_sensor(dev, chan, LN2_VOLT, 1, LN2_PWR_UNITS, val);
+		if (ret < 0)
+			return ret;
+
+		power = abs(*val);
+	}
+
+	ret = read_sensor(dev, chan, LN2_CURR, nsamples, LN2_PWR_UNITS, val);
+	if (ret < 0)
+		return ret;
+
+	power *= abs(*val);
+	power = DIV_ROUND_CLOSEST_ULL(power, LN2_PWR_UNITS);
+
+	if (power > LONG_MAX)
+		*val = LONG_MAX;
+	else
+		*val = power;
+
+	return 0;
+}
+
+static umode_t lochnagar_is_visible(const void *drvdata,
+				    enum hwmon_sensor_types type,
+				    u32 attr, int chan)
+{
+	switch (type) {
+	case hwmon_in:
+		if (!strcmp("SYSVDD", lochnagar_chan_names[chan]))
+			return 0;
+		break;
+	case hwmon_power:
+		if (attr == hwmon_power_average_interval)
+			return 0644;
+		break;
+	default:
+		break;
+	}
+
+	return 0444;
+}
+
+static int lochnagar_read(struct device *dev, enum hwmon_sensor_types type,
+			  u32 attr, int chan, long *val)
+{
+	struct lochnagar_hwmon *priv = dev_get_drvdata(dev);
+	int interval;
+
+	switch (type) {
+	case hwmon_in:
+		return read_sensor(dev, chan, LN2_VOLT, 1, LN2_VOLT_UNITS, val);
+	case hwmon_curr:
+		return read_sensor(dev, chan, LN2_CURR, 1, LN2_CURR_UNITS, val);
+	case hwmon_temp:
+		return read_sensor(dev, chan, LN2_TEMP, 1, LN2_TEMP_UNITS, val);
+	case hwmon_power:
+		switch (attr) {
+		case hwmon_power_average:
+			return read_power(dev, chan, val);
+		case hwmon_power_average_interval:
+			interval = priv->power_nsamples[chan] * LN2_SAMPLE_US;
+			*val = DIV_ROUND_CLOSEST(interval, 1000);
+			return 0;
+		default:
+			return -EOPNOTSUPP;
+		}
+	default:
+		return -EOPNOTSUPP;
+	}
+}
+
+static int lochnagar_read_string(struct device *dev,
+				 enum hwmon_sensor_types type, u32 attr,
+				 int chan, const char **str)
+{
+	switch (type) {
+	case hwmon_in:
+	case hwmon_curr:
+	case hwmon_power:
+		*str = lochnagar_chan_names[chan];
+		return 0;
+	default:
+		return -EOPNOTSUPP;
+	}
+}
+
+static int lochnagar_write(struct device *dev, enum hwmon_sensor_types type,
+			   u32 attr, int chan, long val)
+{
+	struct lochnagar_hwmon *priv = dev_get_drvdata(dev);
+
+	if (type != hwmon_power || attr != hwmon_power_average_interval)
+		return -EOPNOTSUPP;
+
+	val = clamp_t(long, val, 1, (LN2_MAX_NSAMPLE * LN2_SAMPLE_US) / 1000);
+	val = DIV_ROUND_CLOSEST(val * 1000, LN2_SAMPLE_US);
+
+	priv->power_nsamples[chan] = val;
+
+	return 0;
+}
+
+static const struct hwmon_ops lochnagar_ops = {
+	.is_visible = lochnagar_is_visible,
+	.read = lochnagar_read,
+	.read_string = lochnagar_read_string,
+	.write = lochnagar_write,
+};
+
+static const struct hwmon_channel_info *lochnagar_info[] = {
+	HWMON_CHANNEL_INFO(temp,  HWMON_T_INPUT),
+	HWMON_CHANNEL_INFO(in,    HWMON_I_INPUT | HWMON_I_LABEL,
+				  HWMON_I_INPUT | HWMON_I_LABEL,
+				  HWMON_I_INPUT | HWMON_I_LABEL,
+				  HWMON_I_INPUT | HWMON_I_LABEL,
+				  HWMON_I_INPUT | HWMON_I_LABEL,
+				  HWMON_I_INPUT | HWMON_I_LABEL,
+				  HWMON_I_INPUT | HWMON_I_LABEL,
+				  HWMON_I_INPUT | HWMON_I_LABEL),
+	HWMON_CHANNEL_INFO(curr,  HWMON_C_INPUT | HWMON_C_LABEL,
+				  HWMON_C_INPUT | HWMON_C_LABEL,
+				  HWMON_C_INPUT | HWMON_C_LABEL,
+				  HWMON_C_INPUT | HWMON_C_LABEL,
+				  HWMON_C_INPUT | HWMON_C_LABEL,
+				  HWMON_C_INPUT | HWMON_C_LABEL,
+				  HWMON_C_INPUT | HWMON_C_LABEL,
+				  HWMON_C_INPUT | HWMON_C_LABEL),
+	HWMON_CHANNEL_INFO(power, HWMON_P_AVERAGE | HWMON_P_AVERAGE_INTERVAL |
+				  HWMON_P_LABEL,
+				  HWMON_P_AVERAGE | HWMON_P_AVERAGE_INTERVAL |
+				  HWMON_P_LABEL,
+				  HWMON_P_AVERAGE | HWMON_P_AVERAGE_INTERVAL |
+				  HWMON_P_LABEL,
+				  HWMON_P_AVERAGE | HWMON_P_AVERAGE_INTERVAL |
+				  HWMON_P_LABEL,
+				  HWMON_P_AVERAGE | HWMON_P_AVERAGE_INTERVAL |
+				  HWMON_P_LABEL,
+				  HWMON_P_AVERAGE | HWMON_P_AVERAGE_INTERVAL |
+				  HWMON_P_LABEL,
+				  HWMON_P_AVERAGE | HWMON_P_AVERAGE_INTERVAL |
+				  HWMON_P_LABEL,
+				  HWMON_P_AVERAGE | HWMON_P_AVERAGE_INTERVAL |
+				  HWMON_P_LABEL),
+	NULL
+};
+
+static const struct hwmon_chip_info lochnagar_chip_info = {
+	.ops = &lochnagar_ops,
+	.info = lochnagar_info,
+};
+
+static const struct of_device_id lochnagar_of_match[] = {
+	{ .compatible = "cirrus,lochnagar2-hwmon" },
+	{}
+};
+MODULE_DEVICE_TABLE(of, lochnagar_of_match);
+
+static int lochnagar_hwmon_probe(struct platform_device *pdev)
+{
+	struct device *dev = &pdev->dev;
+	struct device *hwmon_dev;
+	struct lochnagar_hwmon *priv;
+	int i;
+
+	priv = devm_kzalloc(dev, sizeof(*priv), GFP_KERNEL);
+	if (!priv)
+		return -ENOMEM;
+
+	mutex_init(&priv->sensor_lock);
+
+	priv->regmap = dev_get_regmap(dev->parent, NULL);
+	if (!priv->regmap) {
+		dev_err(dev, "No register map found\n");
+		return -EINVAL;
+	}
+
+	for (i = 0; i < ARRAY_SIZE(priv->power_nsamples); i++)
+		priv->power_nsamples[i] = 96;
+
+	hwmon_dev = devm_hwmon_device_register_with_info(dev, "Lochnagar", priv,
+							 &lochnagar_chip_info,
+							 NULL);
+
+	return PTR_ERR_OR_ZERO(hwmon_dev);
+}
+
+static struct platform_driver lochnagar_hwmon_driver = {
+	.driver = {
+		.name = "lochnagar-hwmon",
+		.of_match_table = lochnagar_of_match,
+	},
+	.probe = lochnagar_hwmon_probe,
+};
+module_platform_driver(lochnagar_hwmon_driver);
+
+MODULE_AUTHOR("Lucas Tanure <tanureal@opensource.cirrus.com>");
+MODULE_DESCRIPTION("Lochnagar hardware monitoring features");
+MODULE_LICENSE("GPL");
diff --git a/drivers/hwmon/ltc4151.c b/drivers/hwmon/ltc4151.c
index 76c6fda76d95..2b5cd37e6dc3 100644
--- a/drivers/hwmon/ltc4151.c
+++ b/drivers/hwmon/ltc4151.c
@@ -208,7 +208,7 @@ static const struct i2c_device_id ltc4151_id[] = {
 };
 MODULE_DEVICE_TABLE(i2c, ltc4151_id);
 
-static const struct of_device_id ltc4151_match[] = {
+static const struct of_device_id __maybe_unused ltc4151_match[] = {
 	{ .compatible = "lltc,ltc4151" },
 	{},
 };
diff --git a/drivers/hwmon/ltc4245.c b/drivers/hwmon/ltc4245.c
index 34d0653ca607..26542635de9b 100644
--- a/drivers/hwmon/ltc4245.c
+++ b/drivers/hwmon/ltc4245.c
@@ -390,57 +390,30 @@ static umode_t ltc4245_is_visible(const void *_data,
 	}
 }
 
-static const u32 ltc4245_in_config[] = {
-	HWMON_I_INPUT,			/* dummy, skipped in is_visible */
-	HWMON_I_INPUT | HWMON_I_MIN_ALARM,
-	HWMON_I_INPUT | HWMON_I_MIN_ALARM,
-	HWMON_I_INPUT | HWMON_I_MIN_ALARM,
-	HWMON_I_INPUT | HWMON_I_MIN_ALARM,
-	HWMON_I_INPUT | HWMON_I_MIN_ALARM,
-	HWMON_I_INPUT | HWMON_I_MIN_ALARM,
-	HWMON_I_INPUT | HWMON_I_MIN_ALARM,
-	HWMON_I_INPUT | HWMON_I_MIN_ALARM,
-	HWMON_I_INPUT,
-	HWMON_I_INPUT,
-	HWMON_I_INPUT,
-	0
-};
-
-static const struct hwmon_channel_info ltc4245_in = {
-	.type = hwmon_in,
-	.config = ltc4245_in_config,
-};
-
-static const u32 ltc4245_curr_config[] = {
-	HWMON_C_INPUT | HWMON_C_MAX_ALARM,
-	HWMON_C_INPUT | HWMON_C_MAX_ALARM,
-	HWMON_C_INPUT | HWMON_C_MAX_ALARM,
-	HWMON_C_INPUT | HWMON_C_MAX_ALARM,
-	0
-};
-
-static const struct hwmon_channel_info ltc4245_curr = {
-	.type = hwmon_curr,
-	.config = ltc4245_curr_config,
-};
-
-static const u32 ltc4245_power_config[] = {
-	HWMON_P_INPUT,
-	HWMON_P_INPUT,
-	HWMON_P_INPUT,
-	HWMON_P_INPUT,
-	0
-};
-
-static const struct hwmon_channel_info ltc4245_power = {
-	.type = hwmon_power,
-	.config = ltc4245_power_config,
-};
-
 static const struct hwmon_channel_info *ltc4245_info[] = {
-	&ltc4245_in,
-	&ltc4245_curr,
-	&ltc4245_power,
+	HWMON_CHANNEL_INFO(in,
+			   HWMON_I_INPUT,
+			   HWMON_I_INPUT | HWMON_I_MIN_ALARM,
+			   HWMON_I_INPUT | HWMON_I_MIN_ALARM,
+			   HWMON_I_INPUT | HWMON_I_MIN_ALARM,
+			   HWMON_I_INPUT | HWMON_I_MIN_ALARM,
+			   HWMON_I_INPUT | HWMON_I_MIN_ALARM,
+			   HWMON_I_INPUT | HWMON_I_MIN_ALARM,
+			   HWMON_I_INPUT | HWMON_I_MIN_ALARM,
+			   HWMON_I_INPUT | HWMON_I_MIN_ALARM,
+			   HWMON_I_INPUT,
+			   HWMON_I_INPUT,
+			   HWMON_I_INPUT),
+	HWMON_CHANNEL_INFO(curr,
+			   HWMON_C_INPUT | HWMON_C_MAX_ALARM,
+			   HWMON_C_INPUT | HWMON_C_MAX_ALARM,
+			   HWMON_C_INPUT | HWMON_C_MAX_ALARM,
+			   HWMON_C_INPUT | HWMON_C_MAX_ALARM),
+	HWMON_CHANNEL_INFO(power,
+			   HWMON_P_INPUT,
+			   HWMON_P_INPUT,
+			   HWMON_P_INPUT,
+			   HWMON_P_INPUT),
 	NULL
 };
 
diff --git a/drivers/hwmon/ltq-cputemp.c b/drivers/hwmon/ltq-cputemp.c
index 1d33f94594c1..570791f0e024 100644
--- a/drivers/hwmon/ltq-cputemp.c
+++ b/drivers/hwmon/ltq-cputemp.c
@@ -77,29 +77,11 @@ static umode_t ltq_is_visible(const void *_data, enum hwmon_sensor_types type,
 	}
 }
 
-static const u32 ltq_chip_config[] = {
-	HWMON_C_REGISTER_TZ,
-	0
-};
-
-static const struct hwmon_channel_info ltq_chip = {
-	.type = hwmon_chip,
-	.config = ltq_chip_config,
-};
-
-static const u32 ltq_temp_config[] = {
-	HWMON_T_INPUT,
-	0
-};
-
-static const struct hwmon_channel_info ltq_temp = {
-	.type = hwmon_temp,
-	.config = ltq_temp_config,
-};
-
 static const struct hwmon_channel_info *ltq_info[] = {
-	&ltq_chip,
-	&ltq_temp,
+	HWMON_CHANNEL_INFO(chip,
+			   HWMON_C_REGISTER_TZ),
+	HWMON_CHANNEL_INFO(temp,
+			   HWMON_T_INPUT),
 	NULL
 };
 
diff --git a/drivers/hwmon/max197.c b/drivers/hwmon/max197.c
index 3d9e210beedf..dd6a35219a18 100644
--- a/drivers/hwmon/max197.c
+++ b/drivers/hwmon/max197.c
@@ -8,7 +8,7 @@
  * it under the terms of the GNU General Public License version 2 as
  * published by the Free Software Foundation.
  *
- * For further information, see the Documentation/hwmon/max197 file.
+ * For further information, see the Documentation/hwmon/max197.rst file.
  */
 
 #include <linux/kernel.h>
diff --git a/drivers/hwmon/max31790.c b/drivers/hwmon/max31790.c
index 722bcbb9865a..0b0b04d36931 100644
--- a/drivers/hwmon/max31790.c
+++ b/drivers/hwmon/max31790.c
@@ -400,45 +400,27 @@ static umode_t max31790_is_visible(const void *data,
 	}
 }
 
-static const u32 max31790_fan_config[] = {
-	HWMON_F_INPUT | HWMON_F_TARGET | HWMON_F_FAULT,
-	HWMON_F_INPUT | HWMON_F_TARGET | HWMON_F_FAULT,
-	HWMON_F_INPUT | HWMON_F_TARGET | HWMON_F_FAULT,
-	HWMON_F_INPUT | HWMON_F_TARGET | HWMON_F_FAULT,
-	HWMON_F_INPUT | HWMON_F_TARGET | HWMON_F_FAULT,
-	HWMON_F_INPUT | HWMON_F_TARGET | HWMON_F_FAULT,
-	HWMON_F_INPUT | HWMON_F_FAULT,
-	HWMON_F_INPUT | HWMON_F_FAULT,
-	HWMON_F_INPUT | HWMON_F_FAULT,
-	HWMON_F_INPUT | HWMON_F_FAULT,
-	HWMON_F_INPUT | HWMON_F_FAULT,
-	HWMON_F_INPUT | HWMON_F_FAULT,
-	0
-};
-
-static const struct hwmon_channel_info max31790_fan = {
-	.type = hwmon_fan,
-	.config = max31790_fan_config,
-};
-
-static const u32 max31790_pwm_config[] = {
-	HWMON_PWM_INPUT | HWMON_PWM_ENABLE,
-	HWMON_PWM_INPUT | HWMON_PWM_ENABLE,
-	HWMON_PWM_INPUT | HWMON_PWM_ENABLE,
-	HWMON_PWM_INPUT | HWMON_PWM_ENABLE,
-	HWMON_PWM_INPUT | HWMON_PWM_ENABLE,
-	HWMON_PWM_INPUT | HWMON_PWM_ENABLE,
-	0
-};
-
-static const struct hwmon_channel_info max31790_pwm = {
-	.type = hwmon_pwm,
-	.config = max31790_pwm_config,
-};
-
 static const struct hwmon_channel_info *max31790_info[] = {
-	&max31790_fan,
-	&max31790_pwm,
+	HWMON_CHANNEL_INFO(fan,
+			   HWMON_F_INPUT | HWMON_F_TARGET | HWMON_F_FAULT,
+			   HWMON_F_INPUT | HWMON_F_TARGET | HWMON_F_FAULT,
+			   HWMON_F_INPUT | HWMON_F_TARGET | HWMON_F_FAULT,
+			   HWMON_F_INPUT | HWMON_F_TARGET | HWMON_F_FAULT,
+			   HWMON_F_INPUT | HWMON_F_TARGET | HWMON_F_FAULT,
+			   HWMON_F_INPUT | HWMON_F_TARGET | HWMON_F_FAULT,
+			   HWMON_F_INPUT | HWMON_F_FAULT,
+			   HWMON_F_INPUT | HWMON_F_FAULT,
+			   HWMON_F_INPUT | HWMON_F_FAULT,
+			   HWMON_F_INPUT | HWMON_F_FAULT,
+			   HWMON_F_INPUT | HWMON_F_FAULT,
+			   HWMON_F_INPUT | HWMON_F_FAULT),
+	HWMON_CHANNEL_INFO(pwm,
+			   HWMON_PWM_INPUT | HWMON_PWM_ENABLE,
+			   HWMON_PWM_INPUT | HWMON_PWM_ENABLE,
+			   HWMON_PWM_INPUT | HWMON_PWM_ENABLE,
+			   HWMON_PWM_INPUT | HWMON_PWM_ENABLE,
+			   HWMON_PWM_INPUT | HWMON_PWM_ENABLE,
+			   HWMON_PWM_INPUT | HWMON_PWM_ENABLE),
 	NULL
 };
 
diff --git a/drivers/hwmon/max6621.c b/drivers/hwmon/max6621.c
index 35555f0eefb9..1810a753f1a3 100644
--- a/drivers/hwmon/max6621.c
+++ b/drivers/hwmon/max6621.c
@@ -458,37 +458,19 @@ static const struct regmap_config max6621_regmap_config = {
 	.num_reg_defaults = ARRAY_SIZE(max6621_regmap_default),
 };
 
-static u32 max6621_chip_config[] = {
-	HWMON_C_REGISTER_TZ,
-	0
-};
-
-static const struct hwmon_channel_info max6621_chip = {
-	.type = hwmon_chip,
-	.config = max6621_chip_config,
-};
-
-static const u32 max6621_temp_config[] = {
-	HWMON_T_INPUT | HWMON_T_LABEL | HWMON_T_OFFSET,
-	HWMON_T_INPUT | HWMON_T_CRIT | HWMON_T_CRIT_ALARM | HWMON_T_LABEL,
-	HWMON_T_INPUT | HWMON_T_CRIT | HWMON_T_CRIT_ALARM | HWMON_T_LABEL,
-	HWMON_T_INPUT | HWMON_T_CRIT | HWMON_T_CRIT_ALARM | HWMON_T_LABEL,
-	HWMON_T_INPUT | HWMON_T_CRIT | HWMON_T_CRIT_ALARM | HWMON_T_LABEL,
-	HWMON_T_INPUT | HWMON_T_LABEL,
-	HWMON_T_INPUT | HWMON_T_LABEL,
-	HWMON_T_INPUT | HWMON_T_LABEL,
-	HWMON_T_INPUT | HWMON_T_LABEL,
-	0
-};
-
-static const struct hwmon_channel_info max6621_temp = {
-	.type = hwmon_temp,
-	.config = max6621_temp_config,
-};
-
 static const struct hwmon_channel_info *max6621_info[] = {
-	&max6621_chip,
-	&max6621_temp,
+	HWMON_CHANNEL_INFO(chip,
+			   HWMON_C_REGISTER_TZ),
+	HWMON_CHANNEL_INFO(temp,
+			   HWMON_T_INPUT | HWMON_T_LABEL | HWMON_T_OFFSET,
+			   HWMON_T_INPUT | HWMON_T_CRIT | HWMON_T_CRIT_ALARM | HWMON_T_LABEL,
+			   HWMON_T_INPUT | HWMON_T_CRIT | HWMON_T_CRIT_ALARM | HWMON_T_LABEL,
+			   HWMON_T_INPUT | HWMON_T_CRIT | HWMON_T_CRIT_ALARM | HWMON_T_LABEL,
+			   HWMON_T_INPUT | HWMON_T_CRIT | HWMON_T_CRIT_ALARM | HWMON_T_LABEL,
+			   HWMON_T_INPUT | HWMON_T_LABEL,
+			   HWMON_T_INPUT | HWMON_T_LABEL,
+			   HWMON_T_INPUT | HWMON_T_LABEL,
+			   HWMON_T_INPUT | HWMON_T_LABEL),
 	NULL
 };
 
@@ -570,7 +552,7 @@ static const struct i2c_device_id max6621_id[] = {
 };
 MODULE_DEVICE_TABLE(i2c, max6621_id);
 
-static const struct of_device_id max6621_of_match[] = {
+static const struct of_device_id __maybe_unused max6621_of_match[] = {
 	{ .compatible = "maxim,max6621" },
 	{ }
 };
diff --git a/drivers/hwmon/max6650.c b/drivers/hwmon/max6650.c
index 61135a2d0cff..939953240827 100644
--- a/drivers/hwmon/max6650.c
+++ b/drivers/hwmon/max6650.c
@@ -40,6 +40,7 @@
 #include <linux/hwmon-sysfs.h>
 #include <linux/err.h>
 #include <linux/of_device.h>
+#include <linux/thermal.h>
 
 /*
  * Insmod parameters
@@ -113,6 +114,7 @@ module_param(clock, int, 0444);
 struct max6650_data {
 	struct i2c_client *client;
 	const struct attribute_group *groups[3];
+	struct thermal_cooling_device *cooling_dev;
 	struct mutex update_lock;
 	int nr_fans;
 	char valid; /* zero until following fields are valid */
@@ -125,6 +127,7 @@ struct max6650_data {
 	u8 count;
 	u8 dac;
 	u8 alarm;
+	unsigned long cooling_dev_state;
 };
 
 static const u8 tach_reg[] = {
@@ -134,7 +137,7 @@ static const u8 tach_reg[] = {
 	MAX6650_REG_TACH3,
 };
 
-static const struct of_device_id max6650_dt_match[] = {
+static const struct of_device_id __maybe_unused max6650_dt_match[] = {
 	{
 		.compatible = "maxim,max6650",
 		.data = (void *)1
@@ -694,6 +697,63 @@ static int max6650_init_client(struct max6650_data *data,
 	return 0;
 }
 
+#if IS_ENABLED(CONFIG_THERMAL)
+
+static int max6650_get_max_state(struct thermal_cooling_device *cdev,
+				 unsigned long *state)
+{
+	*state = 255;
+
+	return 0;
+}
+
+static int max6650_get_cur_state(struct thermal_cooling_device *cdev,
+				 unsigned long *state)
+{
+	struct max6650_data *data = cdev->devdata;
+
+	*state = data->cooling_dev_state;
+
+	return 0;
+}
+
+static int max6650_set_cur_state(struct thermal_cooling_device *cdev,
+				 unsigned long state)
+{
+	struct max6650_data *data = cdev->devdata;
+	struct i2c_client *client = data->client;
+	int err;
+
+	state = clamp_val(state, 0, 255);
+
+	mutex_lock(&data->update_lock);
+
+	if (data->config & MAX6650_CFG_V12)
+		data->dac = 180 - (180 * state)/255;
+	else
+		data->dac = 76 - (76 * state)/255;
+
+	err = i2c_smbus_write_byte_data(client, MAX6650_REG_DAC, data->dac);
+
+	if (!err) {
+		max6650_set_operating_mode(data, state ?
+						   MAX6650_CFG_MODE_OPEN_LOOP :
+						   MAX6650_CFG_MODE_OFF);
+		data->cooling_dev_state = state;
+	}
+
+	mutex_unlock(&data->update_lock);
+
+	return err < 0 ? err : 0;
+}
+
+static const struct thermal_cooling_device_ops max6650_cooling_ops = {
+	.get_max_state = max6650_get_max_state,
+	.get_cur_state = max6650_get_cur_state,
+	.set_cur_state = max6650_set_cur_state,
+};
+#endif
+
 static int max6650_probe(struct i2c_client *client,
 			 const struct i2c_device_id *id)
 {
@@ -709,6 +769,7 @@ static int max6650_probe(struct i2c_client *client,
 		return -ENOMEM;
 
 	data->client = client;
+	i2c_set_clientdata(client, data);
 	mutex_init(&data->update_lock);
 	data->nr_fans = of_id ? (int)(uintptr_t)of_id->data : id->driver_data;
 
@@ -727,7 +788,31 @@ static int max6650_probe(struct i2c_client *client,
 	hwmon_dev = devm_hwmon_device_register_with_groups(dev,
 							   client->name, data,
 							   data->groups);
-	return PTR_ERR_OR_ZERO(hwmon_dev);
+	err = PTR_ERR_OR_ZERO(hwmon_dev);
+	if (err)
+		return err;
+
+#if IS_ENABLED(CONFIG_THERMAL)
+	data->cooling_dev =
+		thermal_of_cooling_device_register(client->dev.of_node,
+						   client->name, data,
+						   &max6650_cooling_ops);
+	if (IS_ERR(data->cooling_dev))
+		dev_warn(&client->dev,
+			 "thermal cooling device register failed: %ld\n",
+			 PTR_ERR(data->cooling_dev));
+#endif
+	return 0;
+}
+
+static int max6650_remove(struct i2c_client *client)
+{
+	struct max6650_data *data = i2c_get_clientdata(client);
+
+	if (!IS_ERR(data->cooling_dev))
+		thermal_cooling_device_unregister(data->cooling_dev);
+
+	return 0;
 }
 
 static const struct i2c_device_id max6650_id[] = {
@@ -743,6 +828,7 @@ static struct i2c_driver max6650_driver = {
 		.of_match_table = of_match_ptr(max6650_dt_match),
 	},
 	.probe		= max6650_probe,
+	.remove		= max6650_remove,
 	.id_table	= max6650_id,
 };
 
diff --git a/drivers/hwmon/max6697.c b/drivers/hwmon/max6697.c
index da43f7ae3de1..328793eaee3c 100644
--- a/drivers/hwmon/max6697.c
+++ b/drivers/hwmon/max6697.c
@@ -650,7 +650,7 @@ static const struct i2c_device_id max6697_id[] = {
 };
 MODULE_DEVICE_TABLE(i2c, max6697_id);
 
-static const struct of_device_id max6697_of_match[] = {
+static const struct of_device_id __maybe_unused max6697_of_match[] = {
 	{
 		.compatible = "maxim,max6581",
 		.data = (void *)max6581
diff --git a/drivers/hwmon/menf21bmc_hwmon.c b/drivers/hwmon/menf21bmc_hwmon.c
index c29a4c3c6b9e..f540f938fcd9 100644
--- a/drivers/hwmon/menf21bmc_hwmon.c
+++ b/drivers/hwmon/menf21bmc_hwmon.c
@@ -101,7 +101,7 @@ static int menf21bmc_hwmon_get_volt_limits(struct menf21bmc_hwmon *drv_data)
 }
 
 static ssize_t
-show_label(struct device *dev, struct device_attribute *devattr, char *buf)
+label_show(struct device *dev, struct device_attribute *devattr, char *buf)
 {
 	struct sensor_device_attribute *attr = to_sensor_dev_attr(devattr);
 
@@ -109,7 +109,7 @@ show_label(struct device *dev, struct device_attribute *devattr, char *buf)
 }
 
 static ssize_t
-show_in(struct device *dev, struct device_attribute *devattr, char *buf)
+in_show(struct device *dev, struct device_attribute *devattr, char *buf)
 {
 	struct sensor_device_attribute *attr = to_sensor_dev_attr(devattr);
 	struct menf21bmc_hwmon *drv_data = menf21bmc_hwmon_update(dev);
@@ -121,7 +121,7 @@ show_in(struct device *dev, struct device_attribute *devattr, char *buf)
 }
 
 static ssize_t
-show_min(struct device *dev, struct device_attribute *devattr, char *buf)
+min_show(struct device *dev, struct device_attribute *devattr, char *buf)
 {
 	struct sensor_device_attribute *attr = to_sensor_dev_attr(devattr);
 	struct menf21bmc_hwmon *drv_data = dev_get_drvdata(dev);
@@ -130,7 +130,7 @@ show_min(struct device *dev, struct device_attribute *devattr, char *buf)
 }
 
 static ssize_t
-show_max(struct device *dev, struct device_attribute *devattr, char *buf)
+max_show(struct device *dev, struct device_attribute *devattr, char *buf)
 {
 	struct sensor_device_attribute *attr = to_sensor_dev_attr(devattr);
 	struct menf21bmc_hwmon *drv_data = dev_get_drvdata(dev);
@@ -138,21 +138,26 @@ show_max(struct device *dev, struct device_attribute *devattr, char *buf)
 	return sprintf(buf, "%d\n", drv_data->in_max[attr->index]);
 }
 
-#define create_voltage_sysfs(idx)			\
-static SENSOR_DEVICE_ATTR(in##idx##_input, S_IRUGO,	\
-			show_in, NULL, idx);		\
-static SENSOR_DEVICE_ATTR(in##idx##_min, S_IRUGO,	\
-			show_min, NULL, idx);		\
-static SENSOR_DEVICE_ATTR(in##idx##_max, S_IRUGO,	\
-			show_max, NULL, idx);		\
-static SENSOR_DEVICE_ATTR(in##idx##_label, S_IRUGO,	\
-			show_label, NULL, idx);
-
-create_voltage_sysfs(0);
-create_voltage_sysfs(1);
-create_voltage_sysfs(2);
-create_voltage_sysfs(3);
-create_voltage_sysfs(4);
+static SENSOR_DEVICE_ATTR_RO(in0_input, in, 0);
+static SENSOR_DEVICE_ATTR_RO(in0_min, min, 0);
+static SENSOR_DEVICE_ATTR_RO(in0_max, max, 0);
+static SENSOR_DEVICE_ATTR_RO(in0_label, label, 0);
+static SENSOR_DEVICE_ATTR_RO(in1_input, in, 1);
+static SENSOR_DEVICE_ATTR_RO(in1_min, min, 1);
+static SENSOR_DEVICE_ATTR_RO(in1_max, max, 1);
+static SENSOR_DEVICE_ATTR_RO(in1_label, label, 1);
+static SENSOR_DEVICE_ATTR_RO(in2_input, in, 2);
+static SENSOR_DEVICE_ATTR_RO(in2_min, min, 2);
+static SENSOR_DEVICE_ATTR_RO(in2_max, max, 2);
+static SENSOR_DEVICE_ATTR_RO(in2_label, label, 2);
+static SENSOR_DEVICE_ATTR_RO(in3_input, in, 3);
+static SENSOR_DEVICE_ATTR_RO(in3_min, min, 3);
+static SENSOR_DEVICE_ATTR_RO(in3_max, max, 3);
+static SENSOR_DEVICE_ATTR_RO(in3_label, label, 3);
+static SENSOR_DEVICE_ATTR_RO(in4_input, in, 4);
+static SENSOR_DEVICE_ATTR_RO(in4_min, min, 4);
+static SENSOR_DEVICE_ATTR_RO(in4_max, max, 4);
+static SENSOR_DEVICE_ATTR_RO(in4_label, label, 4);
 
 static struct attribute *menf21bmc_hwmon_attrs[] = {
 	&sensor_dev_attr_in0_input.dev_attr.attr,
diff --git a/drivers/hwmon/mlxreg-fan.c b/drivers/hwmon/mlxreg-fan.c
index db8c6de0b6a0..f816d2ae1e58 100644
--- a/drivers/hwmon/mlxreg-fan.c
+++ b/drivers/hwmon/mlxreg-fan.c
@@ -27,7 +27,9 @@
 #define MLXREG_FAN_SPEED_MAX			(MLXREG_FAN_MAX_STATE * 2)
 #define MLXREG_FAN_SPEED_MIN_LEVEL		2	/* 20 percent */
 #define MLXREG_FAN_TACHO_SAMPLES_PER_PULSE_DEF	44
-#define MLXREG_FAN_TACHO_DIVIDER_DEF		1132
+#define MLXREG_FAN_TACHO_DIV_MIN		283
+#define MLXREG_FAN_TACHO_DIV_DEF		(MLXREG_FAN_TACHO_DIV_MIN * 4)
+#define MLXREG_FAN_TACHO_DIV_SCALE_MAX	64
 /*
  * FAN datasheet defines the formula for RPM calculations as RPM = 15/t-high.
  * The logic in a programmable device measures the time t-high by sampling the
@@ -227,40 +229,22 @@ mlxreg_fan_is_visible(const void *data, enum hwmon_sensor_types type, u32 attr,
 	return 0;
 }
 
-static const u32 mlxreg_fan_hwmon_fan_config[] = {
-	HWMON_F_INPUT | HWMON_F_FAULT,
-	HWMON_F_INPUT | HWMON_F_FAULT,
-	HWMON_F_INPUT | HWMON_F_FAULT,
-	HWMON_F_INPUT | HWMON_F_FAULT,
-	HWMON_F_INPUT | HWMON_F_FAULT,
-	HWMON_F_INPUT | HWMON_F_FAULT,
-	HWMON_F_INPUT | HWMON_F_FAULT,
-	HWMON_F_INPUT | HWMON_F_FAULT,
-	HWMON_F_INPUT | HWMON_F_FAULT,
-	HWMON_F_INPUT | HWMON_F_FAULT,
-	HWMON_F_INPUT | HWMON_F_FAULT,
-	HWMON_F_INPUT | HWMON_F_FAULT,
-	0
-};
-
-static const struct hwmon_channel_info mlxreg_fan_hwmon_fan = {
-	.type = hwmon_fan,
-	.config = mlxreg_fan_hwmon_fan_config,
-};
-
-static const u32 mlxreg_fan_hwmon_pwm_config[] = {
-	HWMON_PWM_INPUT,
-	0
-};
-
-static const struct hwmon_channel_info mlxreg_fan_hwmon_pwm = {
-	.type = hwmon_pwm,
-	.config = mlxreg_fan_hwmon_pwm_config,
-};
-
 static const struct hwmon_channel_info *mlxreg_fan_hwmon_info[] = {
-	&mlxreg_fan_hwmon_fan,
-	&mlxreg_fan_hwmon_pwm,
+	HWMON_CHANNEL_INFO(fan,
+			   HWMON_F_INPUT | HWMON_F_FAULT,
+			   HWMON_F_INPUT | HWMON_F_FAULT,
+			   HWMON_F_INPUT | HWMON_F_FAULT,
+			   HWMON_F_INPUT | HWMON_F_FAULT,
+			   HWMON_F_INPUT | HWMON_F_FAULT,
+			   HWMON_F_INPUT | HWMON_F_FAULT,
+			   HWMON_F_INPUT | HWMON_F_FAULT,
+			   HWMON_F_INPUT | HWMON_F_FAULT,
+			   HWMON_F_INPUT | HWMON_F_FAULT,
+			   HWMON_F_INPUT | HWMON_F_FAULT,
+			   HWMON_F_INPUT | HWMON_F_FAULT,
+			   HWMON_F_INPUT | HWMON_F_FAULT),
+	HWMON_CHANNEL_INFO(pwm,
+			   HWMON_PWM_INPUT),
 	NULL
 };
 
@@ -360,15 +344,57 @@ static const struct thermal_cooling_device_ops mlxreg_fan_cooling_ops = {
 	.set_cur_state	= mlxreg_fan_set_cur_state,
 };
 
+static int mlxreg_fan_connect_verify(struct mlxreg_fan *fan,
+				     struct mlxreg_core_data *data)
+{
+	u32 regval;
+	int err;
+
+	err = regmap_read(fan->regmap, data->capability, &regval);
+	if (err) {
+		dev_err(fan->dev, "Failed to query capability register 0x%08x\n",
+			data->capability);
+		return err;
+	}
+
+	return !!(regval & data->bit);
+}
+
+static int mlxreg_fan_speed_divider_get(struct mlxreg_fan *fan,
+					struct mlxreg_core_data *data)
+{
+	u32 regval;
+	int err;
+
+	err = regmap_read(fan->regmap, data->capability, &regval);
+	if (err) {
+		dev_err(fan->dev, "Failed to query capability register 0x%08x\n",
+			data->capability);
+		return err;
+	}
+
+	/*
+	 * Set divider value according to the capability register, in case it
+	 * contains valid value. Otherwise use default value. The purpose of
+	 * this validation is to protect against the old hardware, in which
+	 * this register can return zero.
+	 */
+	if (regval > 0 && regval <= MLXREG_FAN_TACHO_DIV_SCALE_MAX)
+		fan->divider = regval * MLXREG_FAN_TACHO_DIV_MIN;
+
+	return 0;
+}
+
 static int mlxreg_fan_config(struct mlxreg_fan *fan,
 			     struct mlxreg_core_platform_data *pdata)
 {
 	struct mlxreg_core_data *data = pdata->data;
 	bool configured = false;
 	int tacho_num = 0, i;
+	int err;
 
 	fan->samples = MLXREG_FAN_TACHO_SAMPLES_PER_PULSE_DEF;
-	fan->divider = MLXREG_FAN_TACHO_DIVIDER_DEF;
+	fan->divider = MLXREG_FAN_TACHO_DIV_DEF;
 	for (i = 0; i < pdata->counter; i++, data++) {
 		if (strnstr(data->label, "tacho", sizeof(data->label))) {
 			if (tacho_num == MLXREG_FAN_MAX_TACHO) {
@@ -376,6 +402,17 @@ static int mlxreg_fan_config(struct mlxreg_fan *fan,
 					data->label);
 				return -EINVAL;
 			}
+
+			if (data->capability) {
+				err = mlxreg_fan_connect_verify(fan, data);
+				if (err < 0)
+					return err;
+				else if (!err) {
+					tacho_num++;
+					continue;
+				}
+			}
+
 			fan->tacho[tacho_num].reg = data->reg;
 			fan->tacho[tacho_num].mask = data->mask;
 			fan->tacho[tacho_num++].connected = true;
@@ -394,13 +431,21 @@ static int mlxreg_fan_config(struct mlxreg_fan *fan,
 				return -EINVAL;
 			}
 			/* Validate that conf parameters are not zeros. */
-			if (!data->mask || !data->bit) {
+			if (!data->mask && !data->bit && !data->capability) {
 				dev_err(fan->dev, "invalid conf entry params: %s\n",
 					data->label);
 				return -EINVAL;
 			}
-			fan->samples = data->mask;
-			fan->divider = data->bit;
+			if (data->capability) {
+				err = mlxreg_fan_speed_divider_get(fan, data);
+				if (err)
+					return err;
+			} else {
+				if (data->mask)
+					fan->samples = data->mask;
+				if (data->bit)
+					fan->divider = data->bit;
+			}
 			configured = true;
 		} else {
 			dev_err(fan->dev, "invalid label: %s\n", data->label);
diff --git a/drivers/hwmon/nct7904.c b/drivers/hwmon/nct7904.c
index 82c7de7b4639..04516789b070 100644
--- a/drivers/hwmon/nct7904.c
+++ b/drivers/hwmon/nct7904.c
@@ -400,89 +400,53 @@ static int nct7904_detect(struct i2c_client *client,
 	return 0;
 }
 
-static const u32 nct7904_in_config[] = {
-	HWMON_I_INPUT,                  /* dummy, skipped in is_visible */
-	HWMON_I_INPUT,
-	HWMON_I_INPUT,
-	HWMON_I_INPUT,
-	HWMON_I_INPUT,
-	HWMON_I_INPUT,
-	HWMON_I_INPUT,
-	HWMON_I_INPUT,
-	HWMON_I_INPUT,
-	HWMON_I_INPUT,
-	HWMON_I_INPUT,
-	HWMON_I_INPUT,
-	HWMON_I_INPUT,
-	HWMON_I_INPUT,
-	HWMON_I_INPUT,
-	HWMON_I_INPUT,
-	HWMON_I_INPUT,
-	HWMON_I_INPUT,
-	HWMON_I_INPUT,
-	HWMON_I_INPUT,
-	HWMON_I_INPUT,
-	0
-};
-
-static const struct hwmon_channel_info nct7904_in = {
-	.type = hwmon_in,
-	.config = nct7904_in_config,
-};
-
-static const u32 nct7904_fan_config[] = {
-	HWMON_F_INPUT,
-	HWMON_F_INPUT,
-	HWMON_F_INPUT,
-	HWMON_F_INPUT,
-	HWMON_F_INPUT,
-	HWMON_F_INPUT,
-	HWMON_F_INPUT,
-	HWMON_F_INPUT,
-	0
-};
-
-static const struct hwmon_channel_info nct7904_fan = {
-	.type = hwmon_fan,
-	.config = nct7904_fan_config,
-};
-
-static const u32 nct7904_pwm_config[] = {
-	HWMON_PWM_INPUT | HWMON_PWM_ENABLE,
-	HWMON_PWM_INPUT | HWMON_PWM_ENABLE,
-	HWMON_PWM_INPUT | HWMON_PWM_ENABLE,
-	HWMON_PWM_INPUT | HWMON_PWM_ENABLE,
-	0
-};
-
-static const struct hwmon_channel_info nct7904_pwm = {
-	.type = hwmon_pwm,
-	.config = nct7904_pwm_config,
-};
-
-static const u32 nct7904_temp_config[] = {
-	HWMON_T_INPUT,
-	HWMON_T_INPUT,
-	HWMON_T_INPUT,
-	HWMON_T_INPUT,
-	HWMON_T_INPUT,
-	HWMON_T_INPUT,
-	HWMON_T_INPUT,
-	HWMON_T_INPUT,
-	HWMON_T_INPUT,
-	0
-};
-
-static const struct hwmon_channel_info nct7904_temp = {
-	.type = hwmon_temp,
-	.config = nct7904_temp_config,
-};
-
 static const struct hwmon_channel_info *nct7904_info[] = {
-	&nct7904_in,
-	&nct7904_fan,
-	&nct7904_pwm,
-	&nct7904_temp,
+	HWMON_CHANNEL_INFO(in,
+			   HWMON_I_INPUT, /* dummy, skipped in is_visible */
+			   HWMON_I_INPUT,
+			   HWMON_I_INPUT,
+			   HWMON_I_INPUT,
+			   HWMON_I_INPUT,
+			   HWMON_I_INPUT,
+			   HWMON_I_INPUT,
+			   HWMON_I_INPUT,
+			   HWMON_I_INPUT,
+			   HWMON_I_INPUT,
+			   HWMON_I_INPUT,
+			   HWMON_I_INPUT,
+			   HWMON_I_INPUT,
+			   HWMON_I_INPUT,
+			   HWMON_I_INPUT,
+			   HWMON_I_INPUT,
+			   HWMON_I_INPUT,
+			   HWMON_I_INPUT,
+			   HWMON_I_INPUT,
+			   HWMON_I_INPUT,
+			   HWMON_I_INPUT),
+	HWMON_CHANNEL_INFO(fan,
+			   HWMON_F_INPUT,
+			   HWMON_F_INPUT,
+			   HWMON_F_INPUT,
+			   HWMON_F_INPUT,
+			   HWMON_F_INPUT,
+			   HWMON_F_INPUT,
+			   HWMON_F_INPUT,
+			   HWMON_F_INPUT),
+	HWMON_CHANNEL_INFO(pwm,
+			   HWMON_PWM_INPUT | HWMON_PWM_ENABLE,
+			   HWMON_PWM_INPUT | HWMON_PWM_ENABLE,
+			   HWMON_PWM_INPUT | HWMON_PWM_ENABLE,
+			   HWMON_PWM_INPUT | HWMON_PWM_ENABLE),
+	HWMON_CHANNEL_INFO(temp,
+			   HWMON_T_INPUT,
+			   HWMON_T_INPUT,
+			   HWMON_T_INPUT,
+			   HWMON_T_INPUT,
+			   HWMON_T_INPUT,
+			   HWMON_T_INPUT,
+			   HWMON_T_INPUT,
+			   HWMON_T_INPUT,
+			   HWMON_T_INPUT),
 	NULL
 };
 
diff --git a/drivers/hwmon/npcm750-pwm-fan.c b/drivers/hwmon/npcm750-pwm-fan.c
index b3b907bdfb63..1dc0cd452498 100644
--- a/drivers/hwmon/npcm750-pwm-fan.c
+++ b/drivers/hwmon/npcm750-pwm-fan.c
@@ -629,51 +629,33 @@ static umode_t npcm7xx_is_visible(const void *data,
 	}
 }
 
-static const u32 npcm7xx_pwm_config[] = {
-	HWMON_PWM_INPUT,
-	HWMON_PWM_INPUT,
-	HWMON_PWM_INPUT,
-	HWMON_PWM_INPUT,
-	HWMON_PWM_INPUT,
-	HWMON_PWM_INPUT,
-	HWMON_PWM_INPUT,
-	HWMON_PWM_INPUT,
-	0
-};
-
-static const struct hwmon_channel_info npcm7xx_pwm = {
-	.type = hwmon_pwm,
-	.config = npcm7xx_pwm_config,
-};
-
-static const u32 npcm7xx_fan_config[] = {
-	HWMON_F_INPUT,
-	HWMON_F_INPUT,
-	HWMON_F_INPUT,
-	HWMON_F_INPUT,
-	HWMON_F_INPUT,
-	HWMON_F_INPUT,
-	HWMON_F_INPUT,
-	HWMON_F_INPUT,
-	HWMON_F_INPUT,
-	HWMON_F_INPUT,
-	HWMON_F_INPUT,
-	HWMON_F_INPUT,
-	HWMON_F_INPUT,
-	HWMON_F_INPUT,
-	HWMON_F_INPUT,
-	HWMON_F_INPUT,
-	0
-};
-
-static const struct hwmon_channel_info npcm7xx_fan = {
-	.type = hwmon_fan,
-	.config = npcm7xx_fan_config,
-};
-
 static const struct hwmon_channel_info *npcm7xx_info[] = {
-	&npcm7xx_pwm,
-	&npcm7xx_fan,
+	HWMON_CHANNEL_INFO(pwm,
+			   HWMON_PWM_INPUT,
+			   HWMON_PWM_INPUT,
+			   HWMON_PWM_INPUT,
+			   HWMON_PWM_INPUT,
+			   HWMON_PWM_INPUT,
+			   HWMON_PWM_INPUT,
+			   HWMON_PWM_INPUT,
+			   HWMON_PWM_INPUT),
+	HWMON_CHANNEL_INFO(fan,
+			   HWMON_F_INPUT,
+			   HWMON_F_INPUT,
+			   HWMON_F_INPUT,
+			   HWMON_F_INPUT,
+			   HWMON_F_INPUT,
+			   HWMON_F_INPUT,
+			   HWMON_F_INPUT,
+			   HWMON_F_INPUT,
+			   HWMON_F_INPUT,
+			   HWMON_F_INPUT,
+			   HWMON_F_INPUT,
+			   HWMON_F_INPUT,
+			   HWMON_F_INPUT,
+			   HWMON_F_INPUT,
+			   HWMON_F_INPUT,
+			   HWMON_F_INPUT),
 	NULL
 };
 
diff --git a/drivers/hwmon/ntc_thermistor.c b/drivers/hwmon/ntc_thermistor.c
index e4f9f7ce92fa..fd47c36a52bc 100644
--- a/drivers/hwmon/ntc_thermistor.c
+++ b/drivers/hwmon/ntc_thermistor.c
@@ -629,29 +629,9 @@ static umode_t ntc_is_visible(const void *data, enum hwmon_sensor_types type,
 	return 0;
 }
 
-static const u32 ntc_chip_config[] = {
-	HWMON_C_REGISTER_TZ,
-	0
-};
-
-static const struct hwmon_channel_info ntc_chip = {
-	.type = hwmon_chip,
-	.config = ntc_chip_config,
-};
-
-static const u32 ntc_temp_config[] = {
-	HWMON_T_INPUT, HWMON_T_TYPE,
-	0
-};
-
-static const struct hwmon_channel_info ntc_temp = {
-	.type = hwmon_temp,
-	.config = ntc_temp_config,
-};
-
 static const struct hwmon_channel_info *ntc_info[] = {
-	&ntc_chip,
-	&ntc_temp,
+	HWMON_CHANNEL_INFO(chip, HWMON_C_REGISTER_TZ),
+	HWMON_CHANNEL_INFO(temp, HWMON_T_INPUT | HWMON_T_TYPE),
 	NULL
 };
 
diff --git a/drivers/hwmon/occ/Kconfig b/drivers/hwmon/occ/Kconfig
index 66686628fb53..1658634a053e 100644
--- a/drivers/hwmon/occ/Kconfig
+++ b/drivers/hwmon/occ/Kconfig
@@ -5,11 +5,14 @@
 config SENSORS_OCC_P8_I2C
 	tristate "POWER8 OCC through I2C"
 	depends on I2C
+	depends on ARM || ARM64 || COMPILE_TEST
 	select SENSORS_OCC
 	help
 	 This option enables support for monitoring sensors provided by the
-	 On-Chip Controller (OCC) on a POWER8 processor. Communications with
-	 the OCC are established through I2C bus.
+	 On-Chip Controller (OCC) on a POWER8 processor. However, this driver
+	 can only run on a baseboard management controller (BMC) connected to
+	 the P8, not the POWER processor itself. Communications with the OCC are
+	 established through I2C bus.
 
 	 This driver can also be built as a module. If so, the module will be
 	 called occ-p8-hwmon.
@@ -17,15 +20,17 @@ config SENSORS_OCC_P8_I2C
 config SENSORS_OCC_P9_SBE
 	tristate "POWER9 OCC through SBE"
 	depends on FSI_OCC
+	depends on ARM || ARM64 || COMPILE_TEST
 	select SENSORS_OCC
 	help
 	 This option enables support for monitoring sensors provided by the
-	 On-Chip Controller (OCC) on a POWER9 processor. Communications with
-	 the OCC are established through SBE fifo on an FSI bus.
+	 On-Chip Controller (OCC) on a POWER9 processor. However, this driver
+	 can only run on a baseboard management controller (BMC) connected to
+	 the P9, not the POWER processor itself. Communications with the OCC are
+	 established through SBE fifo on an FSI bus.
 
 	 This driver can also be built as a module. If so, the module will be
 	 called occ-p9-hwmon.
 
 config SENSORS_OCC
-	bool "POWER On-Chip Controller"
-	depends on SENSORS_OCC_P8_I2C || SENSORS_OCC_P9_SBE
+	tristate
diff --git a/drivers/hwmon/occ/Makefile b/drivers/hwmon/occ/Makefile
index 3fec12ddc7e7..493588d5a9d3 100644
--- a/drivers/hwmon/occ/Makefile
+++ b/drivers/hwmon/occ/Makefile
@@ -1,5 +1,7 @@
-occ-p8-hwmon-objs := common.o sysfs.o p8_i2c.o
-occ-p9-hwmon-objs := common.o sysfs.o p9_sbe.o
+occ-hwmon-common-objs := common.o sysfs.o
+occ-p8-hwmon-objs := p8_i2c.o
+occ-p9-hwmon-objs := p9_sbe.o
 
+obj-$(CONFIG_SENSORS_OCC) += occ-hwmon-common.o
 obj-$(CONFIG_SENSORS_OCC_P8_I2C) += occ-p8-hwmon.o
 obj-$(CONFIG_SENSORS_OCC_P9_SBE) += occ-p9-hwmon.o
diff --git a/drivers/hwmon/occ/common.c b/drivers/hwmon/occ/common.c
index b91a80abf724..13a6290c8d25 100644
--- a/drivers/hwmon/occ/common.c
+++ b/drivers/hwmon/occ/common.c
@@ -2,11 +2,13 @@
 // Copyright IBM Corp 2019
 
 #include <linux/device.h>
+#include <linux/export.h>
 #include <linux/hwmon.h>
 #include <linux/hwmon-sysfs.h>
 #include <linux/jiffies.h>
 #include <linux/kernel.h>
 #include <linux/math64.h>
+#include <linux/module.h>
 #include <linux/mutex.h>
 #include <linux/sysfs.h>
 #include <asm/unaligned.h>
@@ -139,6 +141,7 @@ static int occ_poll(struct occ *occ)
 	/* mutex should already be locked if necessary */
 	rc = occ->send_cmd(occ, cmd);
 	if (rc) {
+		occ->last_error = rc;
 		if (occ->error_count++ > OCC_ERROR_COUNT_THRESHOLD)
 			occ->error = rc;
 
@@ -147,6 +150,7 @@ static int occ_poll(struct occ *occ)
 
 	/* clear error since communication was successful */
 	occ->error_count = 0;
+	occ->last_error = 0;
 	occ->error = 0;
 
 	/* check for safe state */
@@ -208,6 +212,8 @@ int occ_update_response(struct occ *occ)
 	if (time_after(jiffies, occ->last_update + OCC_UPDATE_FREQUENCY)) {
 		rc = occ_poll(occ);
 		occ->last_update = jiffies;
+	} else {
+		rc = occ->last_error;
 	}
 
 	mutex_unlock(&occ->lock);
@@ -890,6 +896,8 @@ static int occ_setup_sensor_attrs(struct occ *occ)
 				s++;
 			}
 		}
+
+		s = (sensors->power.num_sensors * 4) + 1;
 	} else {
 		for (i = 0; i < sensors->power.num_sensors; ++i) {
 			s = i + 1;
@@ -918,11 +926,11 @@ static int occ_setup_sensor_attrs(struct occ *occ)
 						     show_power, NULL, 3, i);
 			attr++;
 		}
-	}
 
-	if (sensors->caps.num_sensors >= 1) {
 		s = sensors->power.num_sensors + 1;
+	}
 
+	if (sensors->caps.num_sensors >= 1) {
 		snprintf(attr->name, sizeof(attr->name), "power%d_label", s);
 		attr->sensor = OCC_INIT_ATTR(attr->name, 0444, show_caps, NULL,
 					     0, 0);
@@ -1097,3 +1105,8 @@ int occ_setup(struct occ *occ, const char *name)
 
 	return rc;
 }
+EXPORT_SYMBOL_GPL(occ_setup);
+
+MODULE_AUTHOR("Eddie James <eajames@linux.ibm.com>");
+MODULE_DESCRIPTION("Common OCC hwmon code");
+MODULE_LICENSE("GPL");
diff --git a/drivers/hwmon/occ/common.h b/drivers/hwmon/occ/common.h
index ed2cf4245295..fc13f3c73c47 100644
--- a/drivers/hwmon/occ/common.h
+++ b/drivers/hwmon/occ/common.h
@@ -106,7 +106,8 @@ struct occ {
 	struct attribute_group group;
 	const struct attribute_group *groups[2];
 
-	int error;                      /* latest transfer error */
+	int error;                      /* final transfer error after retry */
+	int last_error;			/* latest transfer error */
 	unsigned int error_count;       /* number of xfr errors observed */
 	unsigned long last_safe;        /* time OCC entered "safe" state */
 
diff --git a/drivers/hwmon/occ/sysfs.c b/drivers/hwmon/occ/sysfs.c
index fe3d15e416e7..c73be0747e66 100644
--- a/drivers/hwmon/occ/sysfs.c
+++ b/drivers/hwmon/occ/sysfs.c
@@ -3,6 +3,7 @@
 
 #include <linux/bitops.h>
 #include <linux/device.h>
+#include <linux/export.h>
 #include <linux/hwmon-sysfs.h>
 #include <linux/kernel.h>
 #include <linux/sysfs.h>
@@ -42,16 +43,16 @@ static ssize_t occ_sysfs_show(struct device *dev,
 		val = !!(header->status & OCC_STAT_ACTIVE);
 		break;
 	case 2:
-		val = !!(header->status & OCC_EXT_STAT_DVFS_OT);
+		val = !!(header->ext_status & OCC_EXT_STAT_DVFS_OT);
 		break;
 	case 3:
-		val = !!(header->status & OCC_EXT_STAT_DVFS_POWER);
+		val = !!(header->ext_status & OCC_EXT_STAT_DVFS_POWER);
 		break;
 	case 4:
-		val = !!(header->status & OCC_EXT_STAT_MEM_THROTTLE);
+		val = !!(header->ext_status & OCC_EXT_STAT_MEM_THROTTLE);
 		break;
 	case 5:
-		val = !!(header->status & OCC_EXT_STAT_QUICK_DROP);
+		val = !!(header->ext_status & OCC_EXT_STAT_QUICK_DROP);
 		break;
 	case 6:
 		val = header->occ_state;
@@ -62,9 +63,6 @@ static ssize_t occ_sysfs_show(struct device *dev,
 		else
 			val = 1;
 		break;
-	case 8:
-		val = occ->error;
-		break;
 	default:
 		return -EINVAL;
 	}
@@ -72,6 +70,16 @@ static ssize_t occ_sysfs_show(struct device *dev,
 	return snprintf(buf, PAGE_SIZE - 1, "%d\n", val);
 }
 
+static ssize_t occ_error_show(struct device *dev,
+			      struct device_attribute *attr, char *buf)
+{
+	struct occ *occ = dev_get_drvdata(dev);
+
+	occ_update_response(occ);
+
+	return snprintf(buf, PAGE_SIZE - 1, "%d\n", occ->error);
+}
+
 static SENSOR_DEVICE_ATTR(occ_master, 0444, occ_sysfs_show, NULL, 0);
 static SENSOR_DEVICE_ATTR(occ_active, 0444, occ_sysfs_show, NULL, 1);
 static SENSOR_DEVICE_ATTR(occ_dvfs_overtemp, 0444, occ_sysfs_show, NULL, 2);
@@ -80,7 +88,7 @@ static SENSOR_DEVICE_ATTR(occ_mem_throttle, 0444, occ_sysfs_show, NULL, 4);
 static SENSOR_DEVICE_ATTR(occ_quick_pwr_drop, 0444, occ_sysfs_show, NULL, 5);
 static SENSOR_DEVICE_ATTR(occ_state, 0444, occ_sysfs_show, NULL, 6);
 static SENSOR_DEVICE_ATTR(occs_present, 0444, occ_sysfs_show, NULL, 7);
-static SENSOR_DEVICE_ATTR(occ_error, 0444, occ_sysfs_show, NULL, 8);
+static DEVICE_ATTR_RO(occ_error);
 
 static struct attribute *occ_attributes[] = {
 	&sensor_dev_attr_occ_master.dev_attr.attr,
@@ -91,7 +99,7 @@ static struct attribute *occ_attributes[] = {
 	&sensor_dev_attr_occ_quick_pwr_drop.dev_attr.attr,
 	&sensor_dev_attr_occ_state.dev_attr.attr,
 	&sensor_dev_attr_occs_present.dev_attr.attr,
-	&sensor_dev_attr_occ_error.dev_attr.attr,
+	&dev_attr_occ_error.attr,
 	NULL
 };
 
@@ -155,7 +163,7 @@ void occ_sysfs_poll_done(struct occ *occ)
 	}
 
 	if (occ->error && occ->error != occ->prev_error) {
-		name = sensor_dev_attr_occ_error.dev_attr.attr.name;
+		name = dev_attr_occ_error.attr.name;
 		sysfs_notify(&occ->bus_dev->kobj, NULL, name);
 	}
 
@@ -177,3 +185,4 @@ void occ_shutdown(struct occ *occ)
 {
 	sysfs_remove_group(&occ->bus_dev->kobj, &occ_sysfs);
 }
+EXPORT_SYMBOL_GPL(occ_shutdown);
diff --git a/drivers/hwmon/pc87427.c b/drivers/hwmon/pc87427.c
index d1a3f2040c00..58eee8fa3e6d 100644
--- a/drivers/hwmon/pc87427.c
+++ b/drivers/hwmon/pc87427.c
@@ -106,6 +106,13 @@ static const char *logdev_str[2] = { DRVNAME " FMC", DRVNAME " HMC" };
 #define LD_IN		1
 #define LD_TEMP		1
 
+static inline int superio_enter(int sioaddr)
+{
+	if (!request_muxed_region(sioaddr, 2, DRVNAME))
+		return -EBUSY;
+	return 0;
+}
+
 static inline void superio_outb(int sioaddr, int reg, int val)
 {
 	outb(reg, sioaddr);
@@ -122,6 +129,7 @@ static inline void superio_exit(int sioaddr)
 {
 	outb(0x02, sioaddr);
 	outb(0x02, sioaddr + 1);
+	release_region(sioaddr, 2);
 }
 
 /*
@@ -1195,7 +1203,11 @@ static int __init pc87427_find(int sioaddr, struct pc87427_sio_data *sio_data)
 {
 	u16 val;
 	u8 cfg, cfg_b;
-	int i, err = 0;
+	int i, err;
+
+	err = superio_enter(sioaddr);
+	if (err)
+		return err;
 
 	/* Identify device */
 	val = force_id ? force_id : superio_inb(sioaddr, SIOREG_DEVID);
diff --git a/drivers/hwmon/pmbus/Kconfig b/drivers/hwmon/pmbus/Kconfig
index 629cb45f8557..7edab7e30eaf 100644
--- a/drivers/hwmon/pmbus/Kconfig
+++ b/drivers/hwmon/pmbus/Kconfig
@@ -54,6 +54,24 @@ config SENSORS_IR35221
 	  This driver can also be built as a module. If so, the module will
 	  be called ir35521.
 
+config SENSORS_IR38064
+	tristate "Infineon IR38064"
+	help
+	  If you say yes here you get hardware monitoring support for Infineon
+	  IR38064.
+
+	  This driver can also be built as a module. If so, the module will
+	  be called ir38064.
+
+config SENSORS_ISL68137
+	tristate "Intersil ISL68137"
+	help
+	  If you say yes here you get hardware monitoring support for Intersil
+	  ISL68137.
+
+	  This driver can also be built as a module. If so, the module will
+	  be called isl68137.
+
 config SENSORS_LM25066
 	tristate "National Semiconductor LM25066 and compatibles"
 	help
diff --git a/drivers/hwmon/pmbus/Makefile b/drivers/hwmon/pmbus/Makefile
index ea0e39518c21..2219b9300316 100644
--- a/drivers/hwmon/pmbus/Makefile
+++ b/drivers/hwmon/pmbus/Makefile
@@ -8,6 +8,8 @@ obj-$(CONFIG_SENSORS_PMBUS)	+= pmbus.o
 obj-$(CONFIG_SENSORS_ADM1275)	+= adm1275.o
 obj-$(CONFIG_SENSORS_IBM_CFFPS)	+= ibm-cffps.o
 obj-$(CONFIG_SENSORS_IR35221)	+= ir35221.o
+obj-$(CONFIG_SENSORS_IR38064)	+= ir38064.o
+obj-$(CONFIG_SENSORS_ISL68137)	+= isl68137.o
 obj-$(CONFIG_SENSORS_LM25066)	+= lm25066.o
 obj-$(CONFIG_SENSORS_LTC2978)	+= ltc2978.o
 obj-$(CONFIG_SENSORS_LTC3815)	+= ltc3815.o
diff --git a/drivers/hwmon/pmbus/ir38064.c b/drivers/hwmon/pmbus/ir38064.c
new file mode 100644
index 000000000000..1820f5077f66
--- /dev/null
+++ b/drivers/hwmon/pmbus/ir38064.c
@@ -0,0 +1,65 @@
+// SPDX-License-Identifier: GPL-2.0+
+/*
+ * Hardware monitoring driver for Infineon IR38064
+ *
+ * Copyright (c) 2017 Google Inc
+ *
+ * VOUT_MODE is not supported by the device. The driver fakes VOUT linear16
+ * mode with exponent value -8 as direct mode with m=256/b=0/R=0.
+ *          
+ * The device supports VOUT_PEAK, IOUT_PEAK, and TEMPERATURE_PEAK, however
+ * this driver does not currently support them.
+ */
+
+#include <linux/err.h>
+#include <linux/i2c.h>
+#include <linux/init.h>
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include "pmbus.h"
+
+static struct pmbus_driver_info ir38064_info = {
+	.pages = 1,
+	.format[PSC_VOLTAGE_IN] = linear,
+	.format[PSC_VOLTAGE_OUT] = direct,
+	.format[PSC_CURRENT_OUT] = linear,
+	.format[PSC_POWER] = linear,
+	.format[PSC_TEMPERATURE] = linear,
+	.m[PSC_VOLTAGE_OUT] = 256,
+	.b[PSC_VOLTAGE_OUT] = 0,
+	.R[PSC_VOLTAGE_OUT] = 0,
+	.func[0] = PMBUS_HAVE_VIN | PMBUS_HAVE_STATUS_INPUT
+	    | PMBUS_HAVE_TEMP | PMBUS_HAVE_STATUS_TEMP
+	    | PMBUS_HAVE_VOUT | PMBUS_HAVE_STATUS_VOUT
+	    | PMBUS_HAVE_IOUT | PMBUS_HAVE_STATUS_IOUT
+	    | PMBUS_HAVE_POUT,
+};
+
+static int ir38064_probe(struct i2c_client *client,
+			 const struct i2c_device_id *id)
+{
+	return pmbus_do_probe(client, id, &ir38064_info);
+}
+
+static const struct i2c_device_id ir38064_id[] = {
+	{"ir38064", 0},
+	{}
+};
+
+MODULE_DEVICE_TABLE(i2c, ir38064_id);
+
+/* This is the driver that will be inserted */
+static struct i2c_driver ir38064_driver = {
+	.driver = {
+		   .name = "ir38064",
+		   },
+	.probe = ir38064_probe,
+	.remove = pmbus_do_remove,
+	.id_table = ir38064_id,
+};
+
+module_i2c_driver(ir38064_driver);
+
+MODULE_AUTHOR("Maxim Sloyko <maxims@google.com>");
+MODULE_DESCRIPTION("PMBus driver for Infineon IR38064");
+MODULE_LICENSE("GPL");
diff --git a/drivers/hwmon/pmbus/isl68137.c b/drivers/hwmon/pmbus/isl68137.c
new file mode 100644
index 000000000000..515596c92fe1
--- /dev/null
+++ b/drivers/hwmon/pmbus/isl68137.c
@@ -0,0 +1,169 @@
+// SPDX-License-Identifier: GPL-2.0+
+/*
+ * Hardware monitoring driver for Intersil ISL68137
+ *
+ * Copyright (c) 2017 Google Inc
+ *
+ */
+
+#include <linux/err.h>
+#include <linux/hwmon-sysfs.h>
+#include <linux/i2c.h>
+#include <linux/init.h>
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/string.h>
+#include <linux/sysfs.h>
+#include "pmbus.h"
+
+#define ISL68137_VOUT_AVS	0x30
+
+static ssize_t isl68137_avs_enable_show_page(struct i2c_client *client,
+					     int page,
+					     char *buf)
+{
+	int val = pmbus_read_byte_data(client, page, PMBUS_OPERATION);
+
+	return sprintf(buf, "%d\n",
+		       (val & ISL68137_VOUT_AVS) == ISL68137_VOUT_AVS ? 1 : 0);
+}
+
+static ssize_t isl68137_avs_enable_store_page(struct i2c_client *client,
+					      int page,
+					      const char *buf, size_t count)
+{
+	int rc, op_val;
+	bool result;
+
+	rc = kstrtobool(buf, &result);
+	if (rc)
+		return rc;
+
+	op_val = result ? ISL68137_VOUT_AVS : 0;
+
+	/*
+	 * Writes to VOUT setpoint over AVSBus will persist after the VRM is
+	 * switched to PMBus control. Switching back to AVSBus control
+	 * restores this persisted setpoint rather than re-initializing to
+	 * PMBus VOUT_COMMAND. Writing VOUT_COMMAND first over PMBus before
+	 * enabling AVS control is the workaround.
+	 */
+	if (op_val == ISL68137_VOUT_AVS) {
+		rc = pmbus_read_word_data(client, page, PMBUS_VOUT_COMMAND);
+		if (rc < 0)
+			return rc;
+
+		rc = pmbus_write_word_data(client, page, PMBUS_VOUT_COMMAND,
+					   rc);
+		if (rc < 0)
+			return rc;
+	}
+
+	rc = pmbus_update_byte_data(client, page, PMBUS_OPERATION,
+				    ISL68137_VOUT_AVS, op_val);
+
+	return (rc < 0) ? rc : count;
+}
+
+static ssize_t isl68137_avs_enable_show(struct device *dev,
+					struct device_attribute *devattr,
+					char *buf)
+{
+	struct i2c_client *client = to_i2c_client(dev->parent);
+	struct sensor_device_attribute *attr = to_sensor_dev_attr(devattr);
+
+	return isl68137_avs_enable_show_page(client, attr->index, buf);
+}
+
+static ssize_t isl68137_avs_enable_store(struct device *dev,
+				struct device_attribute *devattr,
+				const char *buf, size_t count)
+{
+	struct i2c_client *client = to_i2c_client(dev->parent);
+	struct sensor_device_attribute *attr = to_sensor_dev_attr(devattr);
+
+	return isl68137_avs_enable_store_page(client, attr->index, buf, count);
+}
+
+static SENSOR_DEVICE_ATTR_RW(avs0_enable, isl68137_avs_enable, 0);
+static SENSOR_DEVICE_ATTR_RW(avs1_enable, isl68137_avs_enable, 1);
+
+static struct attribute *enable_attrs[] = {
+	&sensor_dev_attr_avs0_enable.dev_attr.attr,
+	&sensor_dev_attr_avs1_enable.dev_attr.attr,
+	NULL,
+};
+
+static const struct attribute_group enable_group = {
+	.attrs = enable_attrs,
+};
+
+static const struct attribute_group *attribute_groups[] = {
+	&enable_group,
+	NULL,
+};
+
+static struct pmbus_driver_info isl68137_info = {
+	.pages = 2,
+	.format[PSC_VOLTAGE_IN] = direct,
+	.format[PSC_VOLTAGE_OUT] = direct,
+	.format[PSC_CURRENT_IN] = direct,
+	.format[PSC_CURRENT_OUT] = direct,
+	.format[PSC_POWER] = direct,
+	.format[PSC_TEMPERATURE] = direct,
+	.m[PSC_VOLTAGE_IN] = 1,
+	.b[PSC_VOLTAGE_IN] = 0,
+	.R[PSC_VOLTAGE_IN] = 3,
+	.m[PSC_VOLTAGE_OUT] = 1,
+	.b[PSC_VOLTAGE_OUT] = 0,
+	.R[PSC_VOLTAGE_OUT] = 3,
+	.m[PSC_CURRENT_IN] = 1,
+	.b[PSC_CURRENT_IN] = 0,
+	.R[PSC_CURRENT_IN] = 2,
+	.m[PSC_CURRENT_OUT] = 1,
+	.b[PSC_CURRENT_OUT] = 0,
+	.R[PSC_CURRENT_OUT] = 1,
+	.m[PSC_POWER] = 1,
+	.b[PSC_POWER] = 0,
+	.R[PSC_POWER] = 0,
+	.m[PSC_TEMPERATURE] = 1,
+	.b[PSC_TEMPERATURE] = 0,
+	.R[PSC_TEMPERATURE] = 0,
+	.func[0] = PMBUS_HAVE_VIN | PMBUS_HAVE_IIN | PMBUS_HAVE_PIN
+	    | PMBUS_HAVE_STATUS_INPUT | PMBUS_HAVE_TEMP | PMBUS_HAVE_TEMP2
+	    | PMBUS_HAVE_TEMP3 | PMBUS_HAVE_STATUS_TEMP
+	    | PMBUS_HAVE_VOUT | PMBUS_HAVE_STATUS_VOUT
+	    | PMBUS_HAVE_IOUT | PMBUS_HAVE_STATUS_IOUT | PMBUS_HAVE_POUT,
+	.func[1] = PMBUS_HAVE_VOUT | PMBUS_HAVE_STATUS_VOUT
+	    | PMBUS_HAVE_IOUT | PMBUS_HAVE_STATUS_IOUT | PMBUS_HAVE_POUT,
+	.groups = attribute_groups,
+};
+
+static int isl68137_probe(struct i2c_client *client,
+			  const struct i2c_device_id *id)
+{
+	return pmbus_do_probe(client, id, &isl68137_info);
+}
+
+static const struct i2c_device_id isl68137_id[] = {
+	{"isl68137", 0},
+	{}
+};
+
+MODULE_DEVICE_TABLE(i2c, isl68137_id);
+
+/* This is the driver that will be inserted */
+static struct i2c_driver isl68137_driver = {
+	.driver = {
+		   .name = "isl68137",
+		   },
+	.probe = isl68137_probe,
+	.remove = pmbus_do_remove,
+	.id_table = isl68137_id,
+};
+
+module_i2c_driver(isl68137_driver);
+
+MODULE_AUTHOR("Maxim Sloyko <maxims@google.com>");
+MODULE_DESCRIPTION("PMBus driver for Intersil ISL68137");
+MODULE_LICENSE("GPL");
diff --git a/drivers/hwmon/pmbus/lm25066.c b/drivers/hwmon/pmbus/lm25066.c
index 53db78753a0d..715d4ab57516 100644
--- a/drivers/hwmon/pmbus/lm25066.c
+++ b/drivers/hwmon/pmbus/lm25066.c
@@ -26,6 +26,7 @@
 #include <linux/err.h>
 #include <linux/slab.h>
 #include <linux/i2c.h>
+#include <linux/log2.h>
 #include "pmbus.h"
 
 enum chips { lm25056, lm25066, lm5064, lm5066, lm5066i };
@@ -39,12 +40,15 @@ enum chips { lm25056, lm25066, lm5064, lm5066, lm5066i };
 #define LM25066_CLEAR_PIN_PEAK		0xd6
 #define LM25066_DEVICE_SETUP		0xd9
 #define LM25066_READ_AVG_VIN		0xdc
+#define LM25066_SAMPLES_FOR_AVG		0xdb
 #define LM25066_READ_AVG_VOUT		0xdd
 #define LM25066_READ_AVG_IIN		0xde
 #define LM25066_READ_AVG_PIN		0xdf
 
 #define LM25066_DEV_SETUP_CL		BIT(4)	/* Current limit */
 
+#define LM25066_SAMPLES_FOR_AVG_MAX	4096
+
 /* LM25056 only */
 
 #define LM25056_VAUX_OV_WARN_LIMIT	0xe3
@@ -284,6 +288,12 @@ static int lm25066_read_word_data(struct i2c_client *client, int page, int reg)
 	case PMBUS_VIRT_RESET_PIN_HISTORY:
 		ret = 0;
 		break;
+	case PMBUS_VIRT_SAMPLES:
+		ret = pmbus_read_byte_data(client, 0, LM25066_SAMPLES_FOR_AVG);
+		if (ret < 0)
+			break;
+		ret = 1 << ret;
+		break;
 	default:
 		ret = -ENODATA;
 		break;
@@ -398,6 +408,11 @@ static int lm25066_write_word_data(struct i2c_client *client, int page, int reg,
 	case PMBUS_VIRT_RESET_PIN_HISTORY:
 		ret = pmbus_write_byte(client, 0, LM25066_CLEAR_PIN_PEAK);
 		break;
+	case PMBUS_VIRT_SAMPLES:
+		word = clamp_val(word, 1, LM25066_SAMPLES_FOR_AVG_MAX);
+		ret = pmbus_write_byte_data(client, 0, LM25066_SAMPLES_FOR_AVG,
+					    ilog2(word));
+		break;
 	default:
 		ret = -ENODATA;
 		break;
@@ -438,7 +453,7 @@ static int lm25066_probe(struct i2c_client *client,
 
 	info->func[0] = PMBUS_HAVE_VIN | PMBUS_HAVE_VMON
 	  | PMBUS_HAVE_PIN | PMBUS_HAVE_IIN | PMBUS_HAVE_STATUS_INPUT
-	  | PMBUS_HAVE_TEMP | PMBUS_HAVE_STATUS_TEMP;
+	  | PMBUS_HAVE_TEMP | PMBUS_HAVE_STATUS_TEMP | PMBUS_HAVE_SAMPLES;
 
 	if (data->id == lm25056) {
 		info->func[0] |= PMBUS_HAVE_STATUS_VMON;
diff --git a/drivers/hwmon/pmbus/pmbus.h b/drivers/hwmon/pmbus/pmbus.h
index 1d24397d36ec..59f85658313c 100644
--- a/drivers/hwmon/pmbus/pmbus.h
+++ b/drivers/hwmon/pmbus/pmbus.h
@@ -217,6 +217,20 @@ enum pmbus_regs {
 	PMBUS_VIRT_PWM_ENABLE_2,
 	PMBUS_VIRT_PWM_ENABLE_3,
 	PMBUS_VIRT_PWM_ENABLE_4,
+
+	/* Samples for average
+	 *
+	 * Drivers wanting to expose functionality for changing the number of
+	 * samples used for average values should implement support in
+	 * {read,write}_word_data callback for either PMBUS_VIRT_SAMPLES if it
+	 * applies to all types of measurements, or any number of specific
+	 * PMBUS_VIRT_*_SAMPLES registers to allow for individual control.
+	 */
+	PMBUS_VIRT_SAMPLES,
+	PMBUS_VIRT_IN_SAMPLES,
+	PMBUS_VIRT_CURR_SAMPLES,
+	PMBUS_VIRT_POWER_SAMPLES,
+	PMBUS_VIRT_TEMP_SAMPLES,
 };
 
 /*
@@ -371,6 +385,7 @@ enum pmbus_sensor_classes {
 #define PMBUS_HAVE_STATUS_VMON	BIT(19)
 #define PMBUS_HAVE_PWM12	BIT(20)
 #define PMBUS_HAVE_PWM34	BIT(21)
+#define PMBUS_HAVE_SAMPLES	BIT(22)
 
 #define PMBUS_PAGE_VIRTUAL	BIT(31)
 
@@ -417,6 +432,9 @@ struct pmbus_driver_info {
 	/* Regulator functionality, if supported by this chip driver. */
 	int num_regulators;
 	const struct regulator_desc *reg_desc;
+
+	/* custom attributes */
+	const struct attribute_group **groups;
 };
 
 /* Regulator ops */
diff --git a/drivers/hwmon/pmbus/pmbus_core.c b/drivers/hwmon/pmbus/pmbus_core.c
index 2e2b5851139c..32a74b8be6bd 100644
--- a/drivers/hwmon/pmbus/pmbus_core.c
+++ b/drivers/hwmon/pmbus/pmbus_core.c
@@ -103,7 +103,7 @@ struct pmbus_data {
 	int max_attributes;
 	int num_attributes;
 	struct attribute_group group;
-	const struct attribute_group *groups[2];
+	const struct attribute_group **groups;
 	struct dentry *debugfs;		/* debugfs device directory */
 
 	struct pmbus_sensor *sensors;
@@ -1073,7 +1073,7 @@ static int pmbus_add_boolean(struct pmbus_data *data,
 		 name, seq, type);
 	boolean->s1 = s1;
 	boolean->s2 = s2;
-	pmbus_attr_init(a, boolean->name, S_IRUGO, pmbus_show_boolean, NULL,
+	pmbus_attr_init(a, boolean->name, 0444, pmbus_show_boolean, NULL,
 			(reg << 16) | mask);
 
 	return pmbus_add_attribute(data, &a->dev_attr.attr);
@@ -1107,7 +1107,7 @@ static struct pmbus_sensor *pmbus_add_sensor(struct pmbus_data *data,
 	sensor->update = update;
 	sensor->convert = convert;
 	pmbus_dev_attr_init(a, sensor->name,
-			    readonly ? S_IRUGO : S_IRUGO | S_IWUSR,
+			    readonly ? 0444 : 0644,
 			    pmbus_show_sensor, pmbus_set_sensor);
 
 	if (pmbus_add_attribute(data, &a->attr))
@@ -1139,7 +1139,7 @@ static int pmbus_add_label(struct pmbus_data *data,
 		snprintf(label->label, sizeof(label->label), "%s%d", lstring,
 			 index);
 
-	pmbus_dev_attr_init(a, label->name, S_IRUGO, pmbus_show_label, NULL);
+	pmbus_dev_attr_init(a, label->name, 0444, pmbus_show_label, NULL);
 	return pmbus_add_attribute(data, &a->attr);
 }
 
@@ -1901,6 +1901,112 @@ static int pmbus_add_fan_attributes(struct i2c_client *client,
 	return 0;
 }
 
+struct pmbus_samples_attr {
+	int reg;
+	char *name;
+};
+
+struct pmbus_samples_reg {
+	int page;
+	struct pmbus_samples_attr *attr;
+	struct device_attribute dev_attr;
+};
+
+static struct pmbus_samples_attr pmbus_samples_registers[] = {
+	{
+		.reg = PMBUS_VIRT_SAMPLES,
+		.name = "samples",
+	}, {
+		.reg = PMBUS_VIRT_IN_SAMPLES,
+		.name = "in_samples",
+	}, {
+		.reg = PMBUS_VIRT_CURR_SAMPLES,
+		.name = "curr_samples",
+	}, {
+		.reg = PMBUS_VIRT_POWER_SAMPLES,
+		.name = "power_samples",
+	}, {
+		.reg = PMBUS_VIRT_TEMP_SAMPLES,
+		.name = "temp_samples",
+	}
+};
+
+#define to_samples_reg(x) container_of(x, struct pmbus_samples_reg, dev_attr)
+
+static ssize_t pmbus_show_samples(struct device *dev,
+				  struct device_attribute *devattr, char *buf)
+{
+	int val;
+	struct i2c_client *client = to_i2c_client(dev->parent);
+	struct pmbus_samples_reg *reg = to_samples_reg(devattr);
+
+	val = _pmbus_read_word_data(client, reg->page, reg->attr->reg);
+	if (val < 0)
+		return val;
+
+	return snprintf(buf, PAGE_SIZE, "%d\n", val);
+}
+
+static ssize_t pmbus_set_samples(struct device *dev,
+				 struct device_attribute *devattr,
+				 const char *buf, size_t count)
+{
+	int ret;
+	long val;
+	struct i2c_client *client = to_i2c_client(dev->parent);
+	struct pmbus_samples_reg *reg = to_samples_reg(devattr);
+
+	if (kstrtol(buf, 0, &val) < 0)
+		return -EINVAL;
+
+	ret = _pmbus_write_word_data(client, reg->page, reg->attr->reg, val);
+
+	return ret ? : count;
+}
+
+static int pmbus_add_samples_attr(struct pmbus_data *data, int page,
+				  struct pmbus_samples_attr *attr)
+{
+	struct pmbus_samples_reg *reg;
+
+	reg = devm_kzalloc(data->dev, sizeof(*reg), GFP_KERNEL);
+	if (!reg)
+		return -ENOMEM;
+
+	reg->attr = attr;
+	reg->page = page;
+
+	pmbus_dev_attr_init(&reg->dev_attr, attr->name, 0644,
+			    pmbus_show_samples, pmbus_set_samples);
+
+	return pmbus_add_attribute(data, &reg->dev_attr.attr);
+}
+
+static int pmbus_add_samples_attributes(struct i2c_client *client,
+					struct pmbus_data *data)
+{
+	const struct pmbus_driver_info *info = data->info;
+	int s;
+
+	if (!(info->func[0] & PMBUS_HAVE_SAMPLES))
+		return 0;
+
+	for (s = 0; s < ARRAY_SIZE(pmbus_samples_registers); s++) {
+		struct pmbus_samples_attr *attr;
+		int ret;
+
+		attr = &pmbus_samples_registers[s];
+		if (!pmbus_check_word_register(client, 0, attr->reg))
+			continue;
+
+		ret = pmbus_add_samples_attr(data, 0, attr);
+		if (ret)
+			return ret;
+	}
+
+	return 0;
+}
+
 static int pmbus_find_attributes(struct i2c_client *client,
 				 struct pmbus_data *data)
 {
@@ -1932,6 +2038,10 @@ static int pmbus_find_attributes(struct i2c_client *client,
 
 	/* Fans */
 	ret = pmbus_add_fan_attributes(client, data);
+	if (ret)
+		return ret;
+
+	ret = pmbus_add_samples_attributes(client, data);
 	return ret;
 }
 
@@ -2305,6 +2415,7 @@ int pmbus_do_probe(struct i2c_client *client, const struct i2c_device_id *id,
 	struct device *dev = &client->dev;
 	const struct pmbus_platform_data *pdata = dev_get_platdata(dev);
 	struct pmbus_data *data;
+	size_t groups_num = 0;
 	int ret;
 
 	if (!info)
@@ -2319,6 +2430,15 @@ int pmbus_do_probe(struct i2c_client *client, const struct i2c_device_id *id,
 	if (!data)
 		return -ENOMEM;
 
+	if (info->groups)
+		while (info->groups[groups_num])
+			groups_num++;
+
+	data->groups = devm_kcalloc(dev, groups_num + 2, sizeof(void *),
+				    GFP_KERNEL);
+	if (!data->groups)
+		return -ENOMEM;
+
 	i2c_set_clientdata(client, data);
 	mutex_init(&data->update_lock);
 	data->dev = dev;
@@ -2346,6 +2466,7 @@ int pmbus_do_probe(struct i2c_client *client, const struct i2c_device_id *id,
 	}
 
 	data->groups[0] = &data->group;
+	memcpy(data->groups + 1, info->groups, sizeof(void *) * groups_num);
 	data->hwmon_dev = hwmon_device_register_with_groups(dev, client->name,
 							    data, data->groups);
 	if (IS_ERR(data->hwmon_dev)) {
diff --git a/drivers/hwmon/pmbus/tps53679.c b/drivers/hwmon/pmbus/tps53679.c
index 2bc352c5357f..3fd5105ee9ae 100644
--- a/drivers/hwmon/pmbus/tps53679.c
+++ b/drivers/hwmon/pmbus/tps53679.c
@@ -97,7 +97,7 @@ static const struct i2c_device_id tps53679_id[] = {
 
 MODULE_DEVICE_TABLE(i2c, tps53679_id);
 
-static const struct of_device_id tps53679_of_match[] = {
+static const struct of_device_id __maybe_unused tps53679_of_match[] = {
 	{.compatible = "ti,tps53679"},
 	{}
 };
diff --git a/drivers/hwmon/pmbus/ucd9000.c b/drivers/hwmon/pmbus/ucd9000.c
index ae93885fccd8..40a3e3d0e661 100644
--- a/drivers/hwmon/pmbus/ucd9000.c
+++ b/drivers/hwmon/pmbus/ucd9000.c
@@ -151,7 +151,7 @@ static const struct i2c_device_id ucd9000_id[] = {
 };
 MODULE_DEVICE_TABLE(i2c, ucd9000_id);
 
-static const struct of_device_id ucd9000_of_match[] = {
+static const struct of_device_id __maybe_unused ucd9000_of_match[] = {
 	{
 		.compatible = "ti,ucd9000",
 		.data = (void *)ucd9000
diff --git a/drivers/hwmon/pmbus/ucd9200.c b/drivers/hwmon/pmbus/ucd9200.c
index 3ed94585837a..fec7656700db 100644
--- a/drivers/hwmon/pmbus/ucd9200.c
+++ b/drivers/hwmon/pmbus/ucd9200.c
@@ -47,7 +47,7 @@ static const struct i2c_device_id ucd9200_id[] = {
 };
 MODULE_DEVICE_TABLE(i2c, ucd9200_id);
 
-static const struct of_device_id ucd9200_of_match[] = {
+static const struct of_device_id __maybe_unused ucd9200_of_match[] = {
 	{
 		.compatible = "ti,cd9200",
 		.data = (void *)ucd9200
diff --git a/drivers/hwmon/pwm-fan.c b/drivers/hwmon/pwm-fan.c
index 167221c7628a..eead8afe6447 100644
--- a/drivers/hwmon/pwm-fan.c
+++ b/drivers/hwmon/pwm-fan.c
@@ -18,6 +18,7 @@
 
 #include <linux/hwmon.h>
 #include <linux/hwmon-sysfs.h>
+#include <linux/interrupt.h>
 #include <linux/module.h>
 #include <linux/mutex.h>
 #include <linux/of.h>
@@ -26,6 +27,7 @@
 #include <linux/regulator/consumer.h>
 #include <linux/sysfs.h>
 #include <linux/thermal.h>
+#include <linux/timer.h>
 
 #define MAX_PWM 255
 
@@ -33,6 +35,14 @@ struct pwm_fan_ctx {
 	struct mutex lock;
 	struct pwm_device *pwm;
 	struct regulator *reg_en;
+
+	int irq;
+	atomic_t pulses;
+	unsigned int rpm;
+	u8 pulses_per_revolution;
+	ktime_t sample_start;
+	struct timer_list rpm_timer;
+
 	unsigned int pwm_value;
 	unsigned int pwm_fan_state;
 	unsigned int pwm_fan_max_state;
@@ -40,6 +50,32 @@ struct pwm_fan_ctx {
 	struct thermal_cooling_device *cdev;
 };
 
+/* This handler assumes self resetting edge triggered interrupt. */
+static irqreturn_t pulse_handler(int irq, void *dev_id)
+{
+	struct pwm_fan_ctx *ctx = dev_id;
+
+	atomic_inc(&ctx->pulses);
+
+	return IRQ_HANDLED;
+}
+
+static void sample_timer(struct timer_list *t)
+{
+	struct pwm_fan_ctx *ctx = from_timer(ctx, t, rpm_timer);
+	int pulses;
+	u64 tmp;
+
+	pulses = atomic_read(&ctx->pulses);
+	atomic_sub(pulses, &ctx->pulses);
+	tmp = (u64)pulses * ktime_ms_delta(ktime_get(), ctx->sample_start) * 60;
+	do_div(tmp, ctx->pulses_per_revolution * 1000);
+	ctx->rpm = tmp;
+
+	ctx->sample_start = ktime_get();
+	mod_timer(&ctx->rpm_timer, jiffies + HZ);
+}
+
 static int  __set_pwm(struct pwm_fan_ctx *ctx, unsigned long pwm)
 {
 	unsigned long period;
@@ -100,15 +136,45 @@ static ssize_t pwm_show(struct device *dev, struct device_attribute *attr,
 	return sprintf(buf, "%u\n", ctx->pwm_value);
 }
 
+static ssize_t rpm_show(struct device *dev,
+			struct device_attribute *attr, char *buf)
+{
+	struct pwm_fan_ctx *ctx = dev_get_drvdata(dev);
+
+	return sprintf(buf, "%u\n", ctx->rpm);
+}
 
 static SENSOR_DEVICE_ATTR_RW(pwm1, pwm, 0);
+static SENSOR_DEVICE_ATTR_RO(fan1_input, rpm, 0);
 
 static struct attribute *pwm_fan_attrs[] = {
 	&sensor_dev_attr_pwm1.dev_attr.attr,
+	&sensor_dev_attr_fan1_input.dev_attr.attr,
 	NULL,
 };
 
-ATTRIBUTE_GROUPS(pwm_fan);
+static umode_t pwm_fan_attrs_visible(struct kobject *kobj, struct attribute *a,
+				     int n)
+{
+	struct device *dev = container_of(kobj, struct device, kobj);
+	struct pwm_fan_ctx *ctx = dev_get_drvdata(dev);
+
+	/* Hide fan_input in case no interrupt is available  */
+	if (n == 1 && ctx->irq <= 0)
+		return 0;
+
+	return a->mode;
+}
+
+static const struct attribute_group pwm_fan_group = {
+	.attrs = pwm_fan_attrs,
+	.is_visible = pwm_fan_attrs_visible,
+};
+
+static const struct attribute_group *pwm_fan_groups[] = {
+	&pwm_fan_group,
+	NULL,
+};
 
 /* thermal cooling device callbacks */
 static int pwm_fan_get_max_state(struct thermal_cooling_device *cdev,
@@ -214,6 +280,7 @@ static int pwm_fan_probe(struct platform_device *pdev)
 	struct device *hwmon;
 	int ret;
 	struct pwm_state state = { };
+	u32 ppr = 2;
 
 	ctx = devm_kzalloc(&pdev->dev, sizeof(*ctx), GFP_KERNEL);
 	if (!ctx)
@@ -233,6 +300,10 @@ static int pwm_fan_probe(struct platform_device *pdev)
 
 	platform_set_drvdata(pdev, ctx);
 
+	ctx->irq = platform_get_irq(pdev, 0);
+	if (ctx->irq == -EPROBE_DEFER)
+		return ctx->irq;
+
 	ctx->reg_en = devm_regulator_get_optional(&pdev->dev, "fan");
 	if (IS_ERR(ctx->reg_en)) {
 		if (PTR_ERR(ctx->reg_en) != -ENODEV)
@@ -257,21 +328,44 @@ static int pwm_fan_probe(struct platform_device *pdev)
 
 	ret = pwm_apply_state(ctx->pwm, &state);
 	if (ret) {
-		dev_err(&pdev->dev, "Failed to configure PWM\n");
+		dev_err(&pdev->dev, "Failed to configure PWM: %d\n", ret);
 		goto err_reg_disable;
 	}
 
+	timer_setup(&ctx->rpm_timer, sample_timer, 0);
+
+	of_property_read_u32(pdev->dev.of_node, "pulses-per-revolution", &ppr);
+	ctx->pulses_per_revolution = ppr;
+	if (!ctx->pulses_per_revolution) {
+		dev_err(&pdev->dev, "pulses-per-revolution can't be zero.\n");
+		ret = -EINVAL;
+		goto err_pwm_disable;
+	}
+
+	if (ctx->irq > 0) {
+		ret = devm_request_irq(&pdev->dev, ctx->irq, pulse_handler, 0,
+				       pdev->name, ctx);
+		if (ret) {
+			dev_err(&pdev->dev,
+				"Failed to request interrupt: %d\n", ret);
+			goto err_pwm_disable;
+		}
+		ctx->sample_start = ktime_get();
+		mod_timer(&ctx->rpm_timer, jiffies + HZ);
+	}
+
 	hwmon = devm_hwmon_device_register_with_groups(&pdev->dev, "pwmfan",
 						       ctx, pwm_fan_groups);
 	if (IS_ERR(hwmon)) {
-		dev_err(&pdev->dev, "Failed to register hwmon device\n");
 		ret = PTR_ERR(hwmon);
-		goto err_pwm_disable;
+		dev_err(&pdev->dev,
+			"Failed to register hwmon device: %d\n", ret);
+		goto err_del_timer;
 	}
 
 	ret = pwm_fan_of_get_cooling_data(&pdev->dev, ctx);
 	if (ret)
-		return ret;
+		goto err_del_timer;
 
 	ctx->pwm_fan_state = ctx->pwm_fan_max_state;
 	if (IS_ENABLED(CONFIG_THERMAL)) {
@@ -279,10 +373,11 @@ static int pwm_fan_probe(struct platform_device *pdev)
 							  "pwm-fan", ctx,
 							  &pwm_fan_cooling_ops);
 		if (IS_ERR(cdev)) {
-			dev_err(&pdev->dev,
-				"Failed to register pwm-fan as cooling device");
 			ret = PTR_ERR(cdev);
-			goto err_pwm_disable;
+			dev_err(&pdev->dev,
+				"Failed to register pwm-fan as cooling device: %d\n",
+				ret);
+			goto err_del_timer;
 		}
 		ctx->cdev = cdev;
 		thermal_cdev_update(cdev);
@@ -290,6 +385,9 @@ static int pwm_fan_probe(struct platform_device *pdev)
 
 	return 0;
 
+err_del_timer:
+	del_timer_sync(&ctx->rpm_timer);
+
 err_pwm_disable:
 	state.enabled = false;
 	pwm_apply_state(ctx->pwm, &state);
@@ -306,6 +404,8 @@ static int pwm_fan_remove(struct platform_device *pdev)
 	struct pwm_fan_ctx *ctx = platform_get_drvdata(pdev);
 
 	thermal_cooling_device_unregister(ctx->cdev);
+	del_timer_sync(&ctx->rpm_timer);
+
 	if (ctx->pwm_value)
 		pwm_disable(ctx->pwm);
 
diff --git a/drivers/hwmon/raspberrypi-hwmon.c b/drivers/hwmon/raspberrypi-hwmon.c
index 0d0457245e7d..efe4bb1ff221 100644
--- a/drivers/hwmon/raspberrypi-hwmon.c
+++ b/drivers/hwmon/raspberrypi-hwmon.c
@@ -86,18 +86,9 @@ static umode_t rpi_is_visible(const void *_data, enum hwmon_sensor_types type,
 	return 0444;
 }
 
-static const u32 rpi_in_config[] = {
-	HWMON_I_LCRIT_ALARM,
-	0
-};
-
-static const struct hwmon_channel_info rpi_in = {
-	.type = hwmon_in,
-	.config = rpi_in_config,
-};
-
 static const struct hwmon_channel_info *rpi_info[] = {
-	&rpi_in,
+	HWMON_CHANNEL_INFO(in,
+			   HWMON_I_LCRIT_ALARM),
 	NULL
 };
 
diff --git a/drivers/hwmon/s3c-hwmon.c b/drivers/hwmon/s3c-hwmon.c
index 0c4710d35d16..0d65aa5985e2 100644
--- a/drivers/hwmon/s3c-hwmon.c
+++ b/drivers/hwmon/s3c-hwmon.c
@@ -98,7 +98,7 @@ static int s3c_hwmon_read_ch(struct device *dev,
 static ssize_t s3c_hwmon_show_raw(struct device *dev,
 				  struct device_attribute *attr, char *buf)
 {
-	struct s3c_hwmon *adc = platform_get_drvdata(to_platform_device(dev));
+	struct s3c_hwmon *adc = dev_get_drvdata(dev);
 	struct sensor_device_attribute *sa = to_sensor_dev_attr(attr);
 	int ret;
 
@@ -164,7 +164,7 @@ static ssize_t s3c_hwmon_ch_show(struct device *dev,
 				 char *buf)
 {
 	struct sensor_device_attribute *sen_attr = to_sensor_dev_attr(attr);
-	struct s3c_hwmon *hwmon = platform_get_drvdata(to_platform_device(dev));
+	struct s3c_hwmon *hwmon = dev_get_drvdata(dev);
 	struct s3c_hwmon_pdata *pdata = dev_get_platdata(dev);
 	struct s3c_hwmon_chcfg *cfg;
 	int ret;
diff --git a/drivers/hwmon/sht15.c b/drivers/hwmon/sht15.c
index 39b41e35c2bf..7f4a63959730 100644
--- a/drivers/hwmon/sht15.c
+++ b/drivers/hwmon/sht15.c
@@ -10,7 +10,7 @@
  *
  * Copyright (c) 2007 Wouter Horre
  *
- * For further information, see the Documentation/hwmon/sht15 file.
+ * For further information, see the Documentation/hwmon/sht15.rst file.
  */
 
 #include <linux/interrupt.h>
diff --git a/drivers/hwmon/sis5595.c b/drivers/hwmon/sis5595.c
index 6d789aab54c9..44451b913292 100644
--- a/drivers/hwmon/sis5595.c
+++ b/drivers/hwmon/sis5595.c
@@ -67,7 +67,6 @@
 #include <linux/acpi.h>
 #include <linux/io.h>
 
-
 /*
  * If force_addr is set to anything different from 0, we forcibly enable
  * the device at the given address.
@@ -222,7 +221,7 @@ static struct platform_driver sis5595_driver = {
 };
 
 /* 4 Voltages */
-static ssize_t show_in(struct device *dev, struct device_attribute *da,
+static ssize_t in_show(struct device *dev, struct device_attribute *da,
 		       char *buf)
 {
 	struct sis5595_data *data = sis5595_update_device(dev);
@@ -231,7 +230,7 @@ static ssize_t show_in(struct device *dev, struct device_attribute *da,
 	return sprintf(buf, "%d\n", IN_FROM_REG(data->in[nr]));
 }
 
-static ssize_t show_in_min(struct device *dev, struct device_attribute *da,
+static ssize_t in_min_show(struct device *dev, struct device_attribute *da,
 			   char *buf)
 {
 	struct sis5595_data *data = sis5595_update_device(dev);
@@ -240,7 +239,7 @@ static ssize_t show_in_min(struct device *dev, struct device_attribute *da,
 	return sprintf(buf, "%d\n", IN_FROM_REG(data->in_min[nr]));
 }
 
-static ssize_t show_in_max(struct device *dev, struct device_attribute *da,
+static ssize_t in_max_show(struct device *dev, struct device_attribute *da,
 			   char *buf)
 {
 	struct sis5595_data *data = sis5595_update_device(dev);
@@ -249,8 +248,8 @@ static ssize_t show_in_max(struct device *dev, struct device_attribute *da,
 	return sprintf(buf, "%d\n", IN_FROM_REG(data->in_max[nr]));
 }
 
-static ssize_t set_in_min(struct device *dev, struct device_attribute *da,
-			  const char *buf, size_t count)
+static ssize_t in_min_store(struct device *dev, struct device_attribute *da,
+			    const char *buf, size_t count)
 {
 	struct sis5595_data *data = dev_get_drvdata(dev);
 	struct sensor_device_attribute *attr = to_sensor_dev_attr(da);
@@ -269,8 +268,8 @@ static ssize_t set_in_min(struct device *dev, struct device_attribute *da,
 	return count;
 }
 
-static ssize_t set_in_max(struct device *dev, struct device_attribute *da,
-			  const char *buf, size_t count)
+static ssize_t in_max_store(struct device *dev, struct device_attribute *da,
+			    const char *buf, size_t count)
 {
 	struct sis5595_data *data = dev_get_drvdata(dev);
 	struct sensor_device_attribute *attr = to_sensor_dev_attr(da);
@@ -289,19 +288,21 @@ static ssize_t set_in_max(struct device *dev, struct device_attribute *da,
 	return count;
 }
 
-#define show_in_offset(offset)					\
-static SENSOR_DEVICE_ATTR(in##offset##_input, S_IRUGO,		\
-		show_in, NULL, offset);				\
-static SENSOR_DEVICE_ATTR(in##offset##_min, S_IRUGO | S_IWUSR,	\
-		show_in_min, set_in_min, offset);		\
-static SENSOR_DEVICE_ATTR(in##offset##_max, S_IRUGO | S_IWUSR,	\
-		show_in_max, set_in_max, offset);
-
-show_in_offset(0);
-show_in_offset(1);
-show_in_offset(2);
-show_in_offset(3);
-show_in_offset(4);
+static SENSOR_DEVICE_ATTR_RO(in0_input, in, 0);
+static SENSOR_DEVICE_ATTR_RW(in0_min, in_min, 0);
+static SENSOR_DEVICE_ATTR_RW(in0_max, in_max, 0);
+static SENSOR_DEVICE_ATTR_RO(in1_input, in, 1);
+static SENSOR_DEVICE_ATTR_RW(in1_min, in_min, 1);
+static SENSOR_DEVICE_ATTR_RW(in1_max, in_max, 1);
+static SENSOR_DEVICE_ATTR_RO(in2_input, in, 2);
+static SENSOR_DEVICE_ATTR_RW(in2_min, in_min, 2);
+static SENSOR_DEVICE_ATTR_RW(in2_max, in_max, 2);
+static SENSOR_DEVICE_ATTR_RO(in3_input, in, 3);
+static SENSOR_DEVICE_ATTR_RW(in3_min, in_min, 3);
+static SENSOR_DEVICE_ATTR_RW(in3_max, in_max, 3);
+static SENSOR_DEVICE_ATTR_RO(in4_input, in, 4);
+static SENSOR_DEVICE_ATTR_RW(in4_min, in_min, 4);
+static SENSOR_DEVICE_ATTR_RW(in4_max, in_max, 4);
 
 /* Temperature */
 static ssize_t temp1_input_show(struct device *dev,
@@ -368,7 +369,7 @@ static DEVICE_ATTR_RW(temp1_max);
 static DEVICE_ATTR_RW(temp1_max_hyst);
 
 /* 2 Fans */
-static ssize_t show_fan(struct device *dev, struct device_attribute *da,
+static ssize_t fan_show(struct device *dev, struct device_attribute *da,
 			char *buf)
 {
 	struct sis5595_data *data = sis5595_update_device(dev);
@@ -378,7 +379,7 @@ static ssize_t show_fan(struct device *dev, struct device_attribute *da,
 		DIV_FROM_REG(data->fan_div[nr])));
 }
 
-static ssize_t show_fan_min(struct device *dev, struct device_attribute *da,
+static ssize_t fan_min_show(struct device *dev, struct device_attribute *da,
 			    char *buf)
 {
 	struct sis5595_data *data = sis5595_update_device(dev);
@@ -388,8 +389,8 @@ static ssize_t show_fan_min(struct device *dev, struct device_attribute *da,
 		DIV_FROM_REG(data->fan_div[nr])));
 }
 
-static ssize_t set_fan_min(struct device *dev, struct device_attribute *da,
-			   const char *buf, size_t count)
+static ssize_t fan_min_store(struct device *dev, struct device_attribute *da,
+			     const char *buf, size_t count)
 {
 	struct sis5595_data *data = dev_get_drvdata(dev);
 	struct sensor_device_attribute *attr = to_sensor_dev_attr(da);
@@ -408,7 +409,7 @@ static ssize_t set_fan_min(struct device *dev, struct device_attribute *da,
 	return count;
 }
 
-static ssize_t show_fan_div(struct device *dev, struct device_attribute *da,
+static ssize_t fan_div_show(struct device *dev, struct device_attribute *da,
 			    char *buf)
 {
 	struct sis5595_data *data = sis5595_update_device(dev);
@@ -423,8 +424,8 @@ static ssize_t show_fan_div(struct device *dev, struct device_attribute *da,
  * least surprise; the user doesn't expect the fan minimum to change just
  * because the divisor changed.
  */
-static ssize_t set_fan_div(struct device *dev, struct device_attribute *da,
-			   const char *buf, size_t count)
+static ssize_t fan_div_store(struct device *dev, struct device_attribute *da,
+			     const char *buf, size_t count)
 {
 	struct sis5595_data *data = dev_get_drvdata(dev);
 	struct sensor_device_attribute *attr = to_sensor_dev_attr(da);
@@ -480,16 +481,12 @@ static ssize_t set_fan_div(struct device *dev, struct device_attribute *da,
 	return count;
 }
 
-#define show_fan_offset(offset)						\
-static SENSOR_DEVICE_ATTR(fan##offset##_input, S_IRUGO,			\
-		show_fan, NULL, offset - 1);				\
-static SENSOR_DEVICE_ATTR(fan##offset##_min, S_IRUGO | S_IWUSR,		\
-		show_fan_min, set_fan_min, offset - 1);			\
-static SENSOR_DEVICE_ATTR(fan##offset##_div, S_IRUGO | S_IWUSR,		\
-		show_fan_div, set_fan_div, offset - 1);
-
-show_fan_offset(1);
-show_fan_offset(2);
+static SENSOR_DEVICE_ATTR_RO(fan1_input, fan, 0);
+static SENSOR_DEVICE_ATTR_RW(fan1_min, fan_min, 0);
+static SENSOR_DEVICE_ATTR_RW(fan1_div, fan_div, 0);
+static SENSOR_DEVICE_ATTR_RO(fan2_input, fan, 1);
+static SENSOR_DEVICE_ATTR_RW(fan2_min, fan_min, 1);
+static SENSOR_DEVICE_ATTR_RW(fan2_div, fan_div, 1);
 
 /* Alarms */
 static ssize_t alarms_show(struct device *dev, struct device_attribute *attr,
@@ -500,21 +497,21 @@ static ssize_t alarms_show(struct device *dev, struct device_attribute *attr,
 }
 static DEVICE_ATTR_RO(alarms);
 
-static ssize_t show_alarm(struct device *dev, struct device_attribute *da,
+static ssize_t alarm_show(struct device *dev, struct device_attribute *da,
 			  char *buf)
 {
 	struct sis5595_data *data = sis5595_update_device(dev);
 	int nr = to_sensor_dev_attr(da)->index;
 	return sprintf(buf, "%u\n", (data->alarms >> nr) & 1);
 }
-static SENSOR_DEVICE_ATTR(in0_alarm, S_IRUGO, show_alarm, NULL, 0);
-static SENSOR_DEVICE_ATTR(in1_alarm, S_IRUGO, show_alarm, NULL, 1);
-static SENSOR_DEVICE_ATTR(in2_alarm, S_IRUGO, show_alarm, NULL, 2);
-static SENSOR_DEVICE_ATTR(in3_alarm, S_IRUGO, show_alarm, NULL, 3);
-static SENSOR_DEVICE_ATTR(in4_alarm, S_IRUGO, show_alarm, NULL, 15);
-static SENSOR_DEVICE_ATTR(fan1_alarm, S_IRUGO, show_alarm, NULL, 6);
-static SENSOR_DEVICE_ATTR(fan2_alarm, S_IRUGO, show_alarm, NULL, 7);
-static SENSOR_DEVICE_ATTR(temp1_alarm, S_IRUGO, show_alarm, NULL, 15);
+static SENSOR_DEVICE_ATTR_RO(in0_alarm, alarm, 0);
+static SENSOR_DEVICE_ATTR_RO(in1_alarm, alarm, 1);
+static SENSOR_DEVICE_ATTR_RO(in2_alarm, alarm, 2);
+static SENSOR_DEVICE_ATTR_RO(in3_alarm, alarm, 3);
+static SENSOR_DEVICE_ATTR_RO(in4_alarm, alarm, 15);
+static SENSOR_DEVICE_ATTR_RO(fan1_alarm, alarm, 6);
+static SENSOR_DEVICE_ATTR_RO(fan2_alarm, alarm, 7);
+static SENSOR_DEVICE_ATTR_RO(temp1_alarm, alarm, 15);
 
 static ssize_t name_show(struct device *dev, struct device_attribute *attr,
 			 char *buf)
@@ -673,7 +670,6 @@ static int sis5595_remove(struct platform_device *pdev)
 	return 0;
 }
 
-
 /* ISA access must be locked explicitly. */
 static int sis5595_read_value(struct sis5595_data *data, u8 reg)
 {
diff --git a/drivers/hwmon/smsc47b397.c b/drivers/hwmon/smsc47b397.c
index c0775084dde0..60e193f2e970 100644
--- a/drivers/hwmon/smsc47b397.c
+++ b/drivers/hwmon/smsc47b397.c
@@ -72,14 +72,19 @@ static inline void superio_select(int ld)
 	superio_outb(0x07, ld);
 }
 
-static inline void superio_enter(void)
+static inline int superio_enter(void)
 {
+	if (!request_muxed_region(REG, 2, DRVNAME))
+		return -EBUSY;
+
 	outb(0x55, REG);
+	return 0;
 }
 
 static inline void superio_exit(void)
 {
 	outb(0xAA, REG);
+	release_region(REG, 2);
 }
 
 #define SUPERIO_REG_DEVID	0x20
@@ -300,8 +305,12 @@ static int __init smsc47b397_find(void)
 	u8 id, rev;
 	char *name;
 	unsigned short addr;
+	int err;
+
+	err = superio_enter();
+	if (err)
+		return err;
 
-	superio_enter();
 	id = force_id ? force_id : superio_inb(SUPERIO_REG_DEVID);
 
 	switch (id) {
diff --git a/drivers/hwmon/smsc47m1.c b/drivers/hwmon/smsc47m1.c
index c7b6a425e2c0..5f92eab24c62 100644
--- a/drivers/hwmon/smsc47m1.c
+++ b/drivers/hwmon/smsc47m1.c
@@ -73,16 +73,21 @@ superio_inb(int reg)
 /* logical device for fans is 0x0A */
 #define superio_select() superio_outb(0x07, 0x0A)
 
-static inline void
+static inline int
 superio_enter(void)
 {
+	if (!request_muxed_region(REG, 2, DRVNAME))
+		return -EBUSY;
+
 	outb(0x55, REG);
+	return 0;
 }
 
 static inline void
 superio_exit(void)
 {
 	outb(0xAA, REG);
+	release_region(REG, 2);
 }
 
 #define SUPERIO_REG_ACT		0x30
@@ -202,8 +207,8 @@ static struct smsc47m1_data *smsc47m1_update_device(struct device *dev,
 	return data;
 }
 
-static ssize_t get_fan(struct device *dev, struct device_attribute
-		       *devattr, char *buf)
+static ssize_t fan_show(struct device *dev, struct device_attribute *devattr,
+			char *buf)
 {
 	struct sensor_device_attribute *attr = to_sensor_dev_attr(devattr);
 	struct smsc47m1_data *data = smsc47m1_update_device(dev, 0);
@@ -221,8 +226,8 @@ static ssize_t get_fan(struct device *dev, struct device_attribute
 	return sprintf(buf, "%d\n", rpm);
 }
 
-static ssize_t get_fan_min(struct device *dev, struct device_attribute
-			   *devattr, char *buf)
+static ssize_t fan_min_show(struct device *dev,
+			    struct device_attribute *devattr, char *buf)
 {
 	struct sensor_device_attribute *attr = to_sensor_dev_attr(devattr);
 	struct smsc47m1_data *data = smsc47m1_update_device(dev, 0);
@@ -232,32 +237,32 @@ static ssize_t get_fan_min(struct device *dev, struct device_attribute
 	return sprintf(buf, "%d\n", rpm);
 }
 
-static ssize_t get_fan_div(struct device *dev, struct device_attribute
-			   *devattr, char *buf)
+static ssize_t fan_div_show(struct device *dev,
+			    struct device_attribute *devattr, char *buf)
 {
 	struct sensor_device_attribute *attr = to_sensor_dev_attr(devattr);
 	struct smsc47m1_data *data = smsc47m1_update_device(dev, 0);
 	return sprintf(buf, "%d\n", DIV_FROM_REG(data->fan_div[attr->index]));
 }
 
-static ssize_t get_fan_alarm(struct device *dev, struct device_attribute
-			     *devattr, char *buf)
+static ssize_t fan_alarm_show(struct device *dev,
+			      struct device_attribute *devattr, char *buf)
 {
 	int bitnr = to_sensor_dev_attr(devattr)->index;
 	struct smsc47m1_data *data = smsc47m1_update_device(dev, 0);
 	return sprintf(buf, "%u\n", (data->alarms >> bitnr) & 1);
 }
 
-static ssize_t get_pwm(struct device *dev, struct device_attribute
-		       *devattr, char *buf)
+static ssize_t pwm_show(struct device *dev, struct device_attribute *devattr,
+			char *buf)
 {
 	struct sensor_device_attribute *attr = to_sensor_dev_attr(devattr);
 	struct smsc47m1_data *data = smsc47m1_update_device(dev, 0);
 	return sprintf(buf, "%d\n", PWM_FROM_REG(data->pwm[attr->index]));
 }
 
-static ssize_t get_pwm_en(struct device *dev, struct device_attribute
-			  *devattr, char *buf)
+static ssize_t pwm_en_show(struct device *dev,
+			   struct device_attribute *devattr, char *buf)
 {
 	struct sensor_device_attribute *attr = to_sensor_dev_attr(devattr);
 	struct smsc47m1_data *data = smsc47m1_update_device(dev, 0);
@@ -271,8 +276,9 @@ static ssize_t alarms_show(struct device *dev,
 	return sprintf(buf, "%d\n", data->alarms);
 }
 
-static ssize_t set_fan_min(struct device *dev, struct device_attribute
-			   *devattr, const char *buf, size_t count)
+static ssize_t fan_min_store(struct device *dev,
+			     struct device_attribute *devattr,
+			     const char *buf, size_t count)
 {
 	struct sensor_device_attribute *attr = to_sensor_dev_attr(devattr);
 	struct smsc47m1_data *data = dev_get_drvdata(dev);
@@ -307,8 +313,9 @@ static ssize_t set_fan_min(struct device *dev, struct device_attribute
  * of least surprise; the user doesn't expect the fan minimum to change just
  * because the divider changed.
  */
-static ssize_t set_fan_div(struct device *dev, struct device_attribute
-			   *devattr, const char *buf, size_t count)
+static ssize_t fan_div_store(struct device *dev,
+			     struct device_attribute *devattr,
+			     const char *buf, size_t count)
 {
 	struct sensor_device_attribute *attr = to_sensor_dev_attr(devattr);
 	struct smsc47m1_data *data = dev_get_drvdata(dev);
@@ -370,8 +377,8 @@ static ssize_t set_fan_div(struct device *dev, struct device_attribute
 	return count;
 }
 
-static ssize_t set_pwm(struct device *dev, struct device_attribute
-		       *devattr, const char *buf, size_t count)
+static ssize_t pwm_store(struct device *dev, struct device_attribute *devattr,
+			 const char *buf, size_t count)
 {
 	struct sensor_device_attribute *attr = to_sensor_dev_attr(devattr);
 	struct smsc47m1_data *data = dev_get_drvdata(dev);
@@ -396,8 +403,9 @@ static ssize_t set_pwm(struct device *dev, struct device_attribute
 	return count;
 }
 
-static ssize_t set_pwm_en(struct device *dev, struct device_attribute
-			  *devattr, const char *buf, size_t count)
+static ssize_t pwm_en_store(struct device *dev,
+			    struct device_attribute *devattr, const char *buf,
+			    size_t count)
 {
 	struct sensor_device_attribute *attr = to_sensor_dev_attr(devattr);
 	struct smsc47m1_data *data = dev_get_drvdata(dev);
@@ -422,23 +430,24 @@ static ssize_t set_pwm_en(struct device *dev, struct device_attribute
 	return count;
 }
 
-#define fan_present(offset)						\
-static SENSOR_DEVICE_ATTR(fan##offset##_input, S_IRUGO, get_fan,	\
-		NULL, offset - 1);					\
-static SENSOR_DEVICE_ATTR(fan##offset##_min, S_IRUGO | S_IWUSR,		\
-		get_fan_min, set_fan_min, offset - 1);			\
-static SENSOR_DEVICE_ATTR(fan##offset##_div, S_IRUGO | S_IWUSR,		\
-		get_fan_div, set_fan_div, offset - 1);			\
-static SENSOR_DEVICE_ATTR(fan##offset##_alarm, S_IRUGO, get_fan_alarm,	\
-		NULL, offset - 1);					\
-static SENSOR_DEVICE_ATTR(pwm##offset, S_IRUGO | S_IWUSR,		\
-		get_pwm, set_pwm, offset - 1);				\
-static SENSOR_DEVICE_ATTR(pwm##offset##_enable, S_IRUGO | S_IWUSR,	\
-		get_pwm_en, set_pwm_en, offset - 1)
-
-fan_present(1);
-fan_present(2);
-fan_present(3);
+static SENSOR_DEVICE_ATTR_RO(fan1_input, fan, 0);
+static SENSOR_DEVICE_ATTR_RW(fan1_min, fan_min, 0);
+static SENSOR_DEVICE_ATTR_RW(fan1_div, fan_div, 0);
+static SENSOR_DEVICE_ATTR_RO(fan1_alarm, fan_alarm, 0);
+static SENSOR_DEVICE_ATTR_RW(pwm1, pwm, 0);
+static SENSOR_DEVICE_ATTR_RW(pwm1_enable, pwm_en, 0);
+static SENSOR_DEVICE_ATTR_RO(fan2_input, fan, 1);
+static SENSOR_DEVICE_ATTR_RW(fan2_min, fan_min, 1);
+static SENSOR_DEVICE_ATTR_RW(fan2_div, fan_div, 1);
+static SENSOR_DEVICE_ATTR_RO(fan2_alarm, fan_alarm, 1);
+static SENSOR_DEVICE_ATTR_RW(pwm2, pwm, 1);
+static SENSOR_DEVICE_ATTR_RW(pwm2_enable, pwm_en, 1);
+static SENSOR_DEVICE_ATTR_RO(fan3_input, fan, 2);
+static SENSOR_DEVICE_ATTR_RW(fan3_min, fan_min, 2);
+static SENSOR_DEVICE_ATTR_RW(fan3_div, fan_div, 2);
+static SENSOR_DEVICE_ATTR_RO(fan3_alarm, fan_alarm, 2);
+static SENSOR_DEVICE_ATTR_RW(pwm3, pwm, 2);
+static SENSOR_DEVICE_ATTR_RW(pwm3_enable, pwm_en, 2);
 
 static DEVICE_ATTR_RO(alarms);
 
@@ -531,8 +540,12 @@ static int __init smsc47m1_find(struct smsc47m1_sio_data *sio_data)
 {
 	u8 val;
 	unsigned short addr;
+	int err;
+
+	err = superio_enter();
+	if (err)
+		return err;
 
-	superio_enter();
 	val = force_id ? force_id : superio_inb(SUPERIO_REG_DEVID);
 
 	/*
@@ -608,13 +621,14 @@ static int __init smsc47m1_find(struct smsc47m1_sio_data *sio_data)
 static void smsc47m1_restore(const struct smsc47m1_sio_data *sio_data)
 {
 	if ((sio_data->activate & 0x01) == 0) {
-		superio_enter();
-		superio_select();
-
-		pr_info("Disabling device\n");
-		superio_outb(SUPERIO_REG_ACT, sio_data->activate);
-
-		superio_exit();
+		if (!superio_enter()) {
+			superio_select();
+			pr_info("Disabling device\n");
+			superio_outb(SUPERIO_REG_ACT, sio_data->activate);
+			superio_exit();
+		} else {
+			pr_warn("Failed to disable device\n");
+		}
 	}
 }
 
diff --git a/drivers/hwmon/smsc47m192.c b/drivers/hwmon/smsc47m192.c
index 6989408033ec..e5d9222b22f1 100644
--- a/drivers/hwmon/smsc47m192.c
+++ b/drivers/hwmon/smsc47m192.c
@@ -179,8 +179,8 @@ static struct smsc47m192_data *smsc47m192_update_device(struct device *dev)
 }
 
 /* Voltages */
-static ssize_t show_in(struct device *dev, struct device_attribute *attr,
-		char *buf)
+static ssize_t in_show(struct device *dev, struct device_attribute *attr,
+		       char *buf)
 {
 	struct sensor_device_attribute *sensor_attr = to_sensor_dev_attr(attr);
 	int nr = sensor_attr->index;
@@ -188,8 +188,8 @@ static ssize_t show_in(struct device *dev, struct device_attribute *attr,
 	return sprintf(buf, "%d\n", IN_FROM_REG(data->in[nr], nr));
 }
 
-static ssize_t show_in_min(struct device *dev, struct device_attribute *attr,
-		char *buf)
+static ssize_t in_min_show(struct device *dev, struct device_attribute *attr,
+			   char *buf)
 {
 	struct sensor_device_attribute *sensor_attr = to_sensor_dev_attr(attr);
 	int nr = sensor_attr->index;
@@ -197,8 +197,8 @@ static ssize_t show_in_min(struct device *dev, struct device_attribute *attr,
 	return sprintf(buf, "%d\n", IN_FROM_REG(data->in_min[nr], nr));
 }
 
-static ssize_t show_in_max(struct device *dev, struct device_attribute *attr,
-		char *buf)
+static ssize_t in_max_show(struct device *dev, struct device_attribute *attr,
+			   char *buf)
 {
 	struct sensor_device_attribute *sensor_attr = to_sensor_dev_attr(attr);
 	int nr = sensor_attr->index;
@@ -206,8 +206,8 @@ static ssize_t show_in_max(struct device *dev, struct device_attribute *attr,
 	return sprintf(buf, "%d\n", IN_FROM_REG(data->in_max[nr], nr));
 }
 
-static ssize_t set_in_min(struct device *dev, struct device_attribute *attr,
-		const char *buf, size_t count)
+static ssize_t in_min_store(struct device *dev, struct device_attribute *attr,
+			    const char *buf, size_t count)
 {
 	struct sensor_device_attribute *sensor_attr = to_sensor_dev_attr(attr);
 	int nr = sensor_attr->index;
@@ -228,8 +228,8 @@ static ssize_t set_in_min(struct device *dev, struct device_attribute *attr,
 	return count;
 }
 
-static ssize_t set_in_max(struct device *dev, struct device_attribute *attr,
-		const char *buf, size_t count)
+static ssize_t in_max_store(struct device *dev, struct device_attribute *attr,
+			    const char *buf, size_t count)
 {
 	struct sensor_device_attribute *sensor_attr = to_sensor_dev_attr(attr);
 	int nr = sensor_attr->index;
@@ -250,26 +250,34 @@ static ssize_t set_in_max(struct device *dev, struct device_attribute *attr,
 	return count;
 }
 
-#define show_in_offset(offset)					\
-static SENSOR_DEVICE_ATTR(in##offset##_input, S_IRUGO,		\
-		show_in, NULL, offset);				\
-static SENSOR_DEVICE_ATTR(in##offset##_min, S_IRUGO | S_IWUSR,	\
-		show_in_min, set_in_min, offset);		\
-static SENSOR_DEVICE_ATTR(in##offset##_max, S_IRUGO | S_IWUSR,	\
-		show_in_max, set_in_max, offset);
-
-show_in_offset(0)
-show_in_offset(1)
-show_in_offset(2)
-show_in_offset(3)
-show_in_offset(4)
-show_in_offset(5)
-show_in_offset(6)
-show_in_offset(7)
+static SENSOR_DEVICE_ATTR_RO(in0_input, in, 0);
+static SENSOR_DEVICE_ATTR_RW(in0_min, in_min, 0);
+static SENSOR_DEVICE_ATTR_RW(in0_max, in_max, 0);
+static SENSOR_DEVICE_ATTR_RO(in1_input, in, 1);
+static SENSOR_DEVICE_ATTR_RW(in1_min, in_min, 1);
+static SENSOR_DEVICE_ATTR_RW(in1_max, in_max, 1);
+static SENSOR_DEVICE_ATTR_RO(in2_input, in, 2);
+static SENSOR_DEVICE_ATTR_RW(in2_min, in_min, 2);
+static SENSOR_DEVICE_ATTR_RW(in2_max, in_max, 2);
+static SENSOR_DEVICE_ATTR_RO(in3_input, in, 3);
+static SENSOR_DEVICE_ATTR_RW(in3_min, in_min, 3);
+static SENSOR_DEVICE_ATTR_RW(in3_max, in_max, 3);
+static SENSOR_DEVICE_ATTR_RO(in4_input, in, 4);
+static SENSOR_DEVICE_ATTR_RW(in4_min, in_min, 4);
+static SENSOR_DEVICE_ATTR_RW(in4_max, in_max, 4);
+static SENSOR_DEVICE_ATTR_RO(in5_input, in, 5);
+static SENSOR_DEVICE_ATTR_RW(in5_min, in_min, 5);
+static SENSOR_DEVICE_ATTR_RW(in5_max, in_max, 5);
+static SENSOR_DEVICE_ATTR_RO(in6_input, in, 6);
+static SENSOR_DEVICE_ATTR_RW(in6_min, in_min, 6);
+static SENSOR_DEVICE_ATTR_RW(in6_max, in_max, 6);
+static SENSOR_DEVICE_ATTR_RO(in7_input, in, 7);
+static SENSOR_DEVICE_ATTR_RW(in7_min, in_min, 7);
+static SENSOR_DEVICE_ATTR_RW(in7_max, in_max, 7);
 
 /* Temperatures */
-static ssize_t show_temp(struct device *dev, struct device_attribute *attr,
-		char *buf)
+static ssize_t temp_show(struct device *dev, struct device_attribute *attr,
+			 char *buf)
 {
 	struct sensor_device_attribute *sensor_attr = to_sensor_dev_attr(attr);
 	int nr = sensor_attr->index;
@@ -277,8 +285,8 @@ static ssize_t show_temp(struct device *dev, struct device_attribute *attr,
 	return sprintf(buf, "%d\n", TEMP_FROM_REG(data->temp[nr]));
 }
 
-static ssize_t show_temp_min(struct device *dev, struct device_attribute *attr,
-		char *buf)
+static ssize_t temp_min_show(struct device *dev,
+			     struct device_attribute *attr, char *buf)
 {
 	struct sensor_device_attribute *sensor_attr = to_sensor_dev_attr(attr);
 	int nr = sensor_attr->index;
@@ -286,8 +294,8 @@ static ssize_t show_temp_min(struct device *dev, struct device_attribute *attr,
 	return sprintf(buf, "%d\n", TEMP_FROM_REG(data->temp_min[nr]));
 }
 
-static ssize_t show_temp_max(struct device *dev, struct device_attribute *attr,
-		char *buf)
+static ssize_t temp_max_show(struct device *dev,
+			     struct device_attribute *attr, char *buf)
 {
 	struct sensor_device_attribute *sensor_attr = to_sensor_dev_attr(attr);
 	int nr = sensor_attr->index;
@@ -295,8 +303,9 @@ static ssize_t show_temp_max(struct device *dev, struct device_attribute *attr,
 	return sprintf(buf, "%d\n", TEMP_FROM_REG(data->temp_max[nr]));
 }
 
-static ssize_t set_temp_min(struct device *dev, struct device_attribute *attr,
-		const char *buf, size_t count)
+static ssize_t temp_min_store(struct device *dev,
+			      struct device_attribute *attr, const char *buf,
+			      size_t count)
 {
 	struct sensor_device_attribute *sensor_attr = to_sensor_dev_attr(attr);
 	int nr = sensor_attr->index;
@@ -317,8 +326,9 @@ static ssize_t set_temp_min(struct device *dev, struct device_attribute *attr,
 	return count;
 }
 
-static ssize_t set_temp_max(struct device *dev, struct device_attribute *attr,
-		const char *buf, size_t count)
+static ssize_t temp_max_store(struct device *dev,
+			      struct device_attribute *attr, const char *buf,
+			      size_t count)
 {
 	struct sensor_device_attribute *sensor_attr = to_sensor_dev_attr(attr);
 	int nr = sensor_attr->index;
@@ -339,8 +349,8 @@ static ssize_t set_temp_max(struct device *dev, struct device_attribute *attr,
 	return count;
 }
 
-static ssize_t show_temp_offset(struct device *dev, struct device_attribute
-		*attr, char *buf)
+static ssize_t temp_offset_show(struct device *dev,
+				struct device_attribute *attr, char *buf)
 {
 	struct sensor_device_attribute *sensor_attr = to_sensor_dev_attr(attr);
 	int nr = sensor_attr->index;
@@ -348,8 +358,9 @@ static ssize_t show_temp_offset(struct device *dev, struct device_attribute
 	return sprintf(buf, "%d\n", TEMP_FROM_REG(data->temp_offset[nr]));
 }
 
-static ssize_t set_temp_offset(struct device *dev, struct device_attribute
-		*attr, const char *buf, size_t count)
+static ssize_t temp_offset_store(struct device *dev,
+				 struct device_attribute *attr,
+				 const char *buf, size_t count)
 {
 	struct sensor_device_attribute *sensor_attr = to_sensor_dev_attr(attr);
 	int nr = sensor_attr->index;
@@ -385,19 +396,18 @@ static ssize_t set_temp_offset(struct device *dev, struct device_attribute
 	return count;
 }
 
-#define show_temp_index(index)						\
-static SENSOR_DEVICE_ATTR(temp##index##_input, S_IRUGO,			\
-		show_temp, NULL, index-1);				\
-static SENSOR_DEVICE_ATTR(temp##index##_min, S_IRUGO | S_IWUSR,		\
-		show_temp_min, set_temp_min, index-1);			\
-static SENSOR_DEVICE_ATTR(temp##index##_max, S_IRUGO | S_IWUSR,		\
-		show_temp_max, set_temp_max, index-1);			\
-static SENSOR_DEVICE_ATTR(temp##index##_offset, S_IRUGO | S_IWUSR,	\
-		show_temp_offset, set_temp_offset, index-1);
-
-show_temp_index(1)
-show_temp_index(2)
-show_temp_index(3)
+static SENSOR_DEVICE_ATTR_RO(temp1_input, temp, 0);
+static SENSOR_DEVICE_ATTR_RW(temp1_min, temp_min, 0);
+static SENSOR_DEVICE_ATTR_RW(temp1_max, temp_max, 0);
+static SENSOR_DEVICE_ATTR_RW(temp1_offset, temp_offset, 0);
+static SENSOR_DEVICE_ATTR_RO(temp2_input, temp, 1);
+static SENSOR_DEVICE_ATTR_RW(temp2_min, temp_min, 1);
+static SENSOR_DEVICE_ATTR_RW(temp2_max, temp_max, 1);
+static SENSOR_DEVICE_ATTR_RW(temp2_offset, temp_offset, 1);
+static SENSOR_DEVICE_ATTR_RO(temp3_input, temp, 2);
+static SENSOR_DEVICE_ATTR_RW(temp3_min, temp_min, 2);
+static SENSOR_DEVICE_ATTR_RW(temp3_max, temp_max, 2);
+static SENSOR_DEVICE_ATTR_RW(temp3_offset, temp_offset, 2);
 
 /* VID */
 static ssize_t cpu0_vid_show(struct device *dev,
@@ -434,8 +444,8 @@ static ssize_t vrm_store(struct device *dev, struct device_attribute *attr,
 static DEVICE_ATTR_RW(vrm);
 
 /* Alarms */
-static ssize_t show_alarm(struct device *dev, struct device_attribute *attr,
-		char *buf)
+static ssize_t alarm_show(struct device *dev, struct device_attribute *attr,
+			  char *buf)
 {
 	struct sensor_device_attribute *sensor_attr = to_sensor_dev_attr(attr);
 	int nr = sensor_attr->index;
@@ -443,19 +453,19 @@ static ssize_t show_alarm(struct device *dev, struct device_attribute *attr,
 	return sprintf(buf, "%u\n", (data->alarms & nr) ? 1 : 0);
 }
 
-static SENSOR_DEVICE_ATTR(temp1_alarm, S_IRUGO, show_alarm, NULL, 0x0010);
-static SENSOR_DEVICE_ATTR(temp2_alarm, S_IRUGO, show_alarm, NULL, 0x0020);
-static SENSOR_DEVICE_ATTR(temp3_alarm, S_IRUGO, show_alarm, NULL, 0x0040);
-static SENSOR_DEVICE_ATTR(temp2_fault, S_IRUGO, show_alarm, NULL, 0x4000);
-static SENSOR_DEVICE_ATTR(temp3_fault, S_IRUGO, show_alarm, NULL, 0x8000);
-static SENSOR_DEVICE_ATTR(in0_alarm, S_IRUGO, show_alarm, NULL, 0x0001);
-static SENSOR_DEVICE_ATTR(in1_alarm, S_IRUGO, show_alarm, NULL, 0x0002);
-static SENSOR_DEVICE_ATTR(in2_alarm, S_IRUGO, show_alarm, NULL, 0x0004);
-static SENSOR_DEVICE_ATTR(in3_alarm, S_IRUGO, show_alarm, NULL, 0x0008);
-static SENSOR_DEVICE_ATTR(in4_alarm, S_IRUGO, show_alarm, NULL, 0x0100);
-static SENSOR_DEVICE_ATTR(in5_alarm, S_IRUGO, show_alarm, NULL, 0x0200);
-static SENSOR_DEVICE_ATTR(in6_alarm, S_IRUGO, show_alarm, NULL, 0x0400);
-static SENSOR_DEVICE_ATTR(in7_alarm, S_IRUGO, show_alarm, NULL, 0x0800);
+static SENSOR_DEVICE_ATTR_RO(temp1_alarm, alarm, 0x0010);
+static SENSOR_DEVICE_ATTR_RO(temp2_alarm, alarm, 0x0020);
+static SENSOR_DEVICE_ATTR_RO(temp3_alarm, alarm, 0x0040);
+static SENSOR_DEVICE_ATTR_RO(temp2_fault, alarm, 0x4000);
+static SENSOR_DEVICE_ATTR_RO(temp3_fault, alarm, 0x8000);
+static SENSOR_DEVICE_ATTR_RO(in0_alarm, alarm, 0x0001);
+static SENSOR_DEVICE_ATTR_RO(in1_alarm, alarm, 0x0002);
+static SENSOR_DEVICE_ATTR_RO(in2_alarm, alarm, 0x0004);
+static SENSOR_DEVICE_ATTR_RO(in3_alarm, alarm, 0x0008);
+static SENSOR_DEVICE_ATTR_RO(in4_alarm, alarm, 0x0100);
+static SENSOR_DEVICE_ATTR_RO(in5_alarm, alarm, 0x0200);
+static SENSOR_DEVICE_ATTR_RO(in6_alarm, alarm, 0x0400);
+static SENSOR_DEVICE_ATTR_RO(in7_alarm, alarm, 0x0800);
 
 static struct attribute *smsc47m192_attributes[] = {
 	&sensor_dev_attr_in0_input.dev_attr.attr,
diff --git a/drivers/hwmon/stts751.c b/drivers/hwmon/stts751.c
index 90b60297f2f7..f670796b609a 100644
--- a/drivers/hwmon/stts751.c
+++ b/drivers/hwmon/stts751.c
@@ -85,7 +85,7 @@ static const struct i2c_device_id stts751_id[] = {
 	{ }
 };
 
-static const struct of_device_id stts751_of_match[] = {
+static const struct of_device_id __maybe_unused stts751_of_match[] = {
 	{ .compatible = "stts751" },
 	{ },
 };
diff --git a/drivers/hwmon/thmc50.c b/drivers/hwmon/thmc50.c
index 6a0ee903127e..ae9942331cae 100644
--- a/drivers/hwmon/thmc50.c
+++ b/drivers/hwmon/thmc50.c
@@ -128,16 +128,16 @@ static struct thmc50_data *thmc50_update_device(struct device *dev)
 	return data;
 }
 
-static ssize_t show_analog_out(struct device *dev,
+static ssize_t analog_out_show(struct device *dev,
 			       struct device_attribute *attr, char *buf)
 {
 	struct thmc50_data *data = thmc50_update_device(dev);
 	return sprintf(buf, "%d\n", data->analog_out);
 }
 
-static ssize_t set_analog_out(struct device *dev,
-			      struct device_attribute *attr,
-			      const char *buf, size_t count)
+static ssize_t analog_out_store(struct device *dev,
+				struct device_attribute *attr,
+				const char *buf, size_t count)
 {
 	struct thmc50_data *data = dev_get_drvdata(dev);
 	struct i2c_client *client = data->client;
@@ -166,14 +166,14 @@ static ssize_t set_analog_out(struct device *dev,
 }
 
 /* There is only one PWM mode = DC */
-static ssize_t show_pwm_mode(struct device *dev, struct device_attribute *attr,
-			     char *buf)
+static ssize_t pwm_mode_show(struct device *dev,
+			     struct device_attribute *attr, char *buf)
 {
 	return sprintf(buf, "0\n");
 }
 
 /* Temperatures */
-static ssize_t show_temp(struct device *dev, struct device_attribute *attr,
+static ssize_t temp_show(struct device *dev, struct device_attribute *attr,
 			 char *buf)
 {
 	int nr = to_sensor_dev_attr(attr)->index;
@@ -181,16 +181,17 @@ static ssize_t show_temp(struct device *dev, struct device_attribute *attr,
 	return sprintf(buf, "%d\n", data->temp_input[nr] * 1000);
 }
 
-static ssize_t show_temp_min(struct device *dev, struct device_attribute *attr,
-			     char *buf)
+static ssize_t temp_min_show(struct device *dev,
+			     struct device_attribute *attr, char *buf)
 {
 	int nr = to_sensor_dev_attr(attr)->index;
 	struct thmc50_data *data = thmc50_update_device(dev);
 	return sprintf(buf, "%d\n", data->temp_min[nr] * 1000);
 }
 
-static ssize_t set_temp_min(struct device *dev, struct device_attribute *attr,
-			    const char *buf, size_t count)
+static ssize_t temp_min_store(struct device *dev,
+			      struct device_attribute *attr, const char *buf,
+			      size_t count)
 {
 	int nr = to_sensor_dev_attr(attr)->index;
 	struct thmc50_data *data = dev_get_drvdata(dev);
@@ -210,16 +211,17 @@ static ssize_t set_temp_min(struct device *dev, struct device_attribute *attr,
 	return count;
 }
 
-static ssize_t show_temp_max(struct device *dev, struct device_attribute *attr,
-			     char *buf)
+static ssize_t temp_max_show(struct device *dev,
+			     struct device_attribute *attr, char *buf)
 {
 	int nr = to_sensor_dev_attr(attr)->index;
 	struct thmc50_data *data = thmc50_update_device(dev);
 	return sprintf(buf, "%d\n", data->temp_max[nr] * 1000);
 }
 
-static ssize_t set_temp_max(struct device *dev, struct device_attribute *attr,
-			    const char *buf, size_t count)
+static ssize_t temp_max_store(struct device *dev,
+			      struct device_attribute *attr, const char *buf,
+			      size_t count)
 {
 	int nr = to_sensor_dev_attr(attr)->index;
 	struct thmc50_data *data = dev_get_drvdata(dev);
@@ -239,16 +241,15 @@ static ssize_t set_temp_max(struct device *dev, struct device_attribute *attr,
 	return count;
 }
 
-static ssize_t show_temp_critical(struct device *dev,
-				  struct device_attribute *attr,
-				  char *buf)
+static ssize_t temp_critical_show(struct device *dev,
+				  struct device_attribute *attr, char *buf)
 {
 	int nr = to_sensor_dev_attr(attr)->index;
 	struct thmc50_data *data = thmc50_update_device(dev);
 	return sprintf(buf, "%d\n", data->temp_critical[nr] * 1000);
 }
 
-static ssize_t show_alarm(struct device *dev, struct device_attribute *attr,
+static ssize_t alarm_show(struct device *dev, struct device_attribute *attr,
 			  char *buf)
 {
 	int index = to_sensor_dev_attr(attr)->index;
@@ -257,29 +258,27 @@ static ssize_t show_alarm(struct device *dev, struct device_attribute *attr,
 	return sprintf(buf, "%u\n", (data->alarms >> index) & 1);
 }
 
-#define temp_reg(offset)						\
-static SENSOR_DEVICE_ATTR(temp##offset##_input, S_IRUGO, show_temp,	\
-			NULL, offset - 1);				\
-static SENSOR_DEVICE_ATTR(temp##offset##_min, S_IRUGO | S_IWUSR,	\
-			show_temp_min, set_temp_min, offset - 1);	\
-static SENSOR_DEVICE_ATTR(temp##offset##_max, S_IRUGO | S_IWUSR,	\
-			show_temp_max, set_temp_max, offset - 1);	\
-static SENSOR_DEVICE_ATTR(temp##offset##_crit, S_IRUGO,			\
-			show_temp_critical, NULL, offset - 1);
-
-temp_reg(1);
-temp_reg(2);
-temp_reg(3);
-
-static SENSOR_DEVICE_ATTR(temp1_alarm, S_IRUGO, show_alarm, NULL, 0);
-static SENSOR_DEVICE_ATTR(temp2_alarm, S_IRUGO, show_alarm, NULL, 5);
-static SENSOR_DEVICE_ATTR(temp3_alarm, S_IRUGO, show_alarm, NULL, 1);
-static SENSOR_DEVICE_ATTR(temp2_fault, S_IRUGO, show_alarm, NULL, 7);
-static SENSOR_DEVICE_ATTR(temp3_fault, S_IRUGO, show_alarm, NULL, 2);
-
-static SENSOR_DEVICE_ATTR(pwm1, S_IRUGO | S_IWUSR, show_analog_out,
-			  set_analog_out, 0);
-static SENSOR_DEVICE_ATTR(pwm1_mode, S_IRUGO, show_pwm_mode, NULL, 0);
+static SENSOR_DEVICE_ATTR_RO(temp1_input, temp, 0);
+static SENSOR_DEVICE_ATTR_RW(temp1_min, temp_min, 0);
+static SENSOR_DEVICE_ATTR_RW(temp1_max, temp_max, 0);
+static SENSOR_DEVICE_ATTR_RO(temp1_crit, temp_critical, 0);
+static SENSOR_DEVICE_ATTR_RO(temp2_input, temp, 1);
+static SENSOR_DEVICE_ATTR_RW(temp2_min, temp_min, 1);
+static SENSOR_DEVICE_ATTR_RW(temp2_max, temp_max, 1);
+static SENSOR_DEVICE_ATTR_RO(temp2_crit, temp_critical, 1);
+static SENSOR_DEVICE_ATTR_RO(temp3_input, temp, 2);
+static SENSOR_DEVICE_ATTR_RW(temp3_min, temp_min, 2);
+static SENSOR_DEVICE_ATTR_RW(temp3_max, temp_max, 2);
+static SENSOR_DEVICE_ATTR_RO(temp3_crit, temp_critical, 2);
+
+static SENSOR_DEVICE_ATTR_RO(temp1_alarm, alarm, 0);
+static SENSOR_DEVICE_ATTR_RO(temp2_alarm, alarm, 5);
+static SENSOR_DEVICE_ATTR_RO(temp3_alarm, alarm, 1);
+static SENSOR_DEVICE_ATTR_RO(temp2_fault, alarm, 7);
+static SENSOR_DEVICE_ATTR_RO(temp3_fault, alarm, 2);
+
+static SENSOR_DEVICE_ATTR_RW(pwm1, analog_out, 0);
+static SENSOR_DEVICE_ATTR_RO(pwm1_mode, pwm_mode, 0);
 
 static struct attribute *thmc50_attributes[] = {
 	&sensor_dev_attr_temp1_max.dev_attr.attr,
diff --git a/drivers/hwmon/tmp102.c b/drivers/hwmon/tmp102.c
index 35523d315f25..f4ee55615dea 100644
--- a/drivers/hwmon/tmp102.c
+++ b/drivers/hwmon/tmp102.c
@@ -150,29 +150,11 @@ static umode_t tmp102_is_visible(const void *data, enum hwmon_sensor_types type,
 	}
 }
 
-static u32 tmp102_chip_config[] = {
-	HWMON_C_REGISTER_TZ,
-	0
-};
-
-static const struct hwmon_channel_info tmp102_chip = {
-	.type = hwmon_chip,
-	.config = tmp102_chip_config,
-};
-
-static u32 tmp102_temp_config[] = {
-	HWMON_T_INPUT | HWMON_T_MAX | HWMON_T_MAX_HYST,
-	0
-};
-
-static const struct hwmon_channel_info tmp102_temp = {
-	.type = hwmon_temp,
-	.config = tmp102_temp_config,
-};
-
 static const struct hwmon_channel_info *tmp102_info[] = {
-	&tmp102_chip,
-	&tmp102_temp,
+	HWMON_CHANNEL_INFO(chip,
+			   HWMON_C_REGISTER_TZ),
+	HWMON_CHANNEL_INFO(temp,
+			   HWMON_T_INPUT | HWMON_T_MAX | HWMON_T_MAX_HYST),
 	NULL
 };
 
@@ -321,7 +303,7 @@ static const struct i2c_device_id tmp102_id[] = {
 };
 MODULE_DEVICE_TABLE(i2c, tmp102_id);
 
-static const struct of_device_id tmp102_of_match[] = {
+static const struct of_device_id __maybe_unused tmp102_of_match[] = {
 	{ .compatible = "ti,tmp102" },
 	{ },
 };
diff --git a/drivers/hwmon/tmp103.c b/drivers/hwmon/tmp103.c
index bda0fdc1eb53..a91726d33da8 100644
--- a/drivers/hwmon/tmp103.c
+++ b/drivers/hwmon/tmp103.c
@@ -170,7 +170,7 @@ static const struct i2c_device_id tmp103_id[] = {
 };
 MODULE_DEVICE_TABLE(i2c, tmp103_id);
 
-static const struct of_device_id tmp103_of_match[] = {
+static const struct of_device_id __maybe_unused tmp103_of_match[] = {
 	{ .compatible = "ti,tmp103" },
 	{ },
 };
diff --git a/drivers/hwmon/tmp108.c b/drivers/hwmon/tmp108.c
index 429bfeae4ca8..2447af704424 100644
--- a/drivers/hwmon/tmp108.c
+++ b/drivers/hwmon/tmp108.c
@@ -281,30 +281,13 @@ static umode_t tmp108_is_visible(const void *data, enum hwmon_sensor_types type,
 	}
 }
 
-static u32 tmp108_chip_config[] = {
-	HWMON_C_REGISTER_TZ | HWMON_C_UPDATE_INTERVAL,
-	0
-};
-
-static const struct hwmon_channel_info tmp108_chip = {
-	.type = hwmon_chip,
-	.config = tmp108_chip_config,
-};
-
-static u32 tmp108_temp_config[] = {
-	HWMON_T_INPUT | HWMON_T_MAX | HWMON_T_MIN | HWMON_T_MIN_HYST
-		| HWMON_T_MAX_HYST | HWMON_T_MIN_ALARM | HWMON_T_MAX_ALARM,
-	0
-};
-
-static const struct hwmon_channel_info tmp108_temp = {
-	.type = hwmon_temp,
-	.config = tmp108_temp_config,
-};
-
 static const struct hwmon_channel_info *tmp108_info[] = {
-	&tmp108_chip,
-	&tmp108_temp,
+	HWMON_CHANNEL_INFO(chip,
+			   HWMON_C_REGISTER_TZ | HWMON_C_UPDATE_INTERVAL),
+	HWMON_CHANNEL_INFO(temp,
+			   HWMON_T_INPUT | HWMON_T_MAX | HWMON_T_MIN |
+			   HWMON_T_MIN_HYST | HWMON_T_MAX_HYST |
+			   HWMON_T_MIN_ALARM | HWMON_T_MAX_ALARM),
 	NULL
 };
 
diff --git a/drivers/hwmon/tmp421.c b/drivers/hwmon/tmp421.c
index 2732a71f3b39..5e63010dd3a0 100644
--- a/drivers/hwmon/tmp421.c
+++ b/drivers/hwmon/tmp421.c
@@ -70,7 +70,7 @@ static const struct i2c_device_id tmp421_id[] = {
 };
 MODULE_DEVICE_TABLE(i2c, tmp421_id);
 
-static const struct of_device_id tmp421_of_match[] = {
+static const struct of_device_id __maybe_unused tmp421_of_match[] = {
 	{
 		.compatible = "ti,tmp421",
 		.data = (void *)2
diff --git a/drivers/hwmon/via686a.c b/drivers/hwmon/via686a.c
index 81f35e3a06b8..259725dec37e 100644
--- a/drivers/hwmon/via686a.c
+++ b/drivers/hwmon/via686a.c
@@ -47,7 +47,6 @@
 #include <linux/acpi.h>
 #include <linux/io.h>
 
-
 /*
  * If force_addr is set to anything different from 0, we forcibly enable
  * the device at the given address.
@@ -355,32 +354,32 @@ static void via686a_init_device(struct via686a_data *data);
 /* following are the sysfs callback functions */
 
 /* 7 voltage sensors */
-static ssize_t show_in(struct device *dev, struct device_attribute *da,
-		char *buf) {
+static ssize_t in_show(struct device *dev, struct device_attribute *da,
+		       char *buf) {
 	struct via686a_data *data = via686a_update_device(dev);
 	struct sensor_device_attribute *attr = to_sensor_dev_attr(da);
 	int nr = attr->index;
 	return sprintf(buf, "%ld\n", IN_FROM_REG(data->in[nr], nr));
 }
 
-static ssize_t show_in_min(struct device *dev, struct device_attribute *da,
-		char *buf) {
+static ssize_t in_min_show(struct device *dev, struct device_attribute *da,
+			   char *buf) {
 	struct via686a_data *data = via686a_update_device(dev);
 	struct sensor_device_attribute *attr = to_sensor_dev_attr(da);
 	int nr = attr->index;
 	return sprintf(buf, "%ld\n", IN_FROM_REG(data->in_min[nr], nr));
 }
 
-static ssize_t show_in_max(struct device *dev, struct device_attribute *da,
-		char *buf) {
+static ssize_t in_max_show(struct device *dev, struct device_attribute *da,
+			   char *buf) {
 	struct via686a_data *data = via686a_update_device(dev);
 	struct sensor_device_attribute *attr = to_sensor_dev_attr(da);
 	int nr = attr->index;
 	return sprintf(buf, "%ld\n", IN_FROM_REG(data->in_max[nr], nr));
 }
 
-static ssize_t set_in_min(struct device *dev, struct device_attribute *da,
-		const char *buf, size_t count) {
+static ssize_t in_min_store(struct device *dev, struct device_attribute *da,
+			    const char *buf, size_t count) {
 	struct via686a_data *data = dev_get_drvdata(dev);
 	struct sensor_device_attribute *attr = to_sensor_dev_attr(da);
 	int nr = attr->index;
@@ -398,8 +397,8 @@ static ssize_t set_in_min(struct device *dev, struct device_attribute *da,
 	mutex_unlock(&data->update_lock);
 	return count;
 }
-static ssize_t set_in_max(struct device *dev, struct device_attribute *da,
-		const char *buf, size_t count) {
+static ssize_t in_max_store(struct device *dev, struct device_attribute *da,
+			    const char *buf, size_t count) {
 	struct via686a_data *data = dev_get_drvdata(dev);
 	struct sensor_device_attribute *attr = to_sensor_dev_attr(da);
 	int nr = attr->index;
@@ -417,44 +416,48 @@ static ssize_t set_in_max(struct device *dev, struct device_attribute *da,
 	mutex_unlock(&data->update_lock);
 	return count;
 }
-#define show_in_offset(offset)					\
-static SENSOR_DEVICE_ATTR(in##offset##_input, S_IRUGO,		\
-		show_in, NULL, offset);				\
-static SENSOR_DEVICE_ATTR(in##offset##_min, S_IRUGO | S_IWUSR,	\
-		show_in_min, set_in_min, offset);		\
-static SENSOR_DEVICE_ATTR(in##offset##_max, S_IRUGO | S_IWUSR,	\
-		show_in_max, set_in_max, offset);
 
-show_in_offset(0);
-show_in_offset(1);
-show_in_offset(2);
-show_in_offset(3);
-show_in_offset(4);
+static SENSOR_DEVICE_ATTR_RO(in0_input, in, 0);
+static SENSOR_DEVICE_ATTR_RW(in0_min, in_min, 0);
+static SENSOR_DEVICE_ATTR_RW(in0_max, in_max, 0);
+static SENSOR_DEVICE_ATTR_RO(in1_input, in, 1);
+static SENSOR_DEVICE_ATTR_RW(in1_min, in_min, 1);
+static SENSOR_DEVICE_ATTR_RW(in1_max, in_max, 1);
+static SENSOR_DEVICE_ATTR_RO(in2_input, in, 2);
+static SENSOR_DEVICE_ATTR_RW(in2_min, in_min, 2);
+static SENSOR_DEVICE_ATTR_RW(in2_max, in_max, 2);
+static SENSOR_DEVICE_ATTR_RO(in3_input, in, 3);
+static SENSOR_DEVICE_ATTR_RW(in3_min, in_min, 3);
+static SENSOR_DEVICE_ATTR_RW(in3_max, in_max, 3);
+static SENSOR_DEVICE_ATTR_RO(in4_input, in, 4);
+static SENSOR_DEVICE_ATTR_RW(in4_min, in_min, 4);
+static SENSOR_DEVICE_ATTR_RW(in4_max, in_max, 4);
 
 /* 3 temperatures */
-static ssize_t show_temp(struct device *dev, struct device_attribute *da,
-		char *buf) {
+static ssize_t temp_show(struct device *dev, struct device_attribute *da,
+			 char *buf) {
 	struct via686a_data *data = via686a_update_device(dev);
 	struct sensor_device_attribute *attr = to_sensor_dev_attr(da);
 	int nr = attr->index;
 	return sprintf(buf, "%ld\n", TEMP_FROM_REG10(data->temp[nr]));
 }
-static ssize_t show_temp_over(struct device *dev, struct device_attribute *da,
-		char *buf) {
+static ssize_t temp_over_show(struct device *dev, struct device_attribute *da,
+			      char *buf) {
 	struct via686a_data *data = via686a_update_device(dev);
 	struct sensor_device_attribute *attr = to_sensor_dev_attr(da);
 	int nr = attr->index;
 	return sprintf(buf, "%ld\n", TEMP_FROM_REG(data->temp_over[nr]));
 }
-static ssize_t show_temp_hyst(struct device *dev, struct device_attribute *da,
-		char *buf) {
+static ssize_t temp_hyst_show(struct device *dev, struct device_attribute *da,
+			      char *buf) {
 	struct via686a_data *data = via686a_update_device(dev);
 	struct sensor_device_attribute *attr = to_sensor_dev_attr(da);
 	int nr = attr->index;
 	return sprintf(buf, "%ld\n", TEMP_FROM_REG(data->temp_hyst[nr]));
 }
-static ssize_t set_temp_over(struct device *dev, struct device_attribute *da,
-		const char *buf, size_t count) {
+static ssize_t temp_over_store(struct device *dev,
+			       struct device_attribute *da, const char *buf,
+			       size_t count) {
 	struct via686a_data *data = dev_get_drvdata(dev);
 	struct sensor_device_attribute *attr = to_sensor_dev_attr(da);
 	int nr = attr->index;
@@ -472,8 +475,9 @@ static ssize_t set_temp_over(struct device *dev, struct device_attribute *da,
 	mutex_unlock(&data->update_lock);
 	return count;
 }
-static ssize_t set_temp_hyst(struct device *dev, struct device_attribute *da,
-		const char *buf, size_t count) {
+static ssize_t temp_hyst_store(struct device *dev,
+			       struct device_attribute *da, const char *buf,
+			       size_t count) {
 	struct via686a_data *data = dev_get_drvdata(dev);
 	struct sensor_device_attribute *attr = to_sensor_dev_attr(da);
 	int nr = attr->index;
@@ -491,29 +495,28 @@ static ssize_t set_temp_hyst(struct device *dev, struct device_attribute *da,
 	mutex_unlock(&data->update_lock);
 	return count;
 }
-#define show_temp_offset(offset)					\
-static SENSOR_DEVICE_ATTR(temp##offset##_input, S_IRUGO,		\
-		show_temp, NULL, offset - 1);				\
-static SENSOR_DEVICE_ATTR(temp##offset##_max, S_IRUGO | S_IWUSR,	\
-		show_temp_over, set_temp_over, offset - 1);		\
-static SENSOR_DEVICE_ATTR(temp##offset##_max_hyst, S_IRUGO | S_IWUSR,	\
-		show_temp_hyst, set_temp_hyst, offset - 1);
 
-show_temp_offset(1);
-show_temp_offset(2);
-show_temp_offset(3);
+static SENSOR_DEVICE_ATTR_RO(temp1_input, temp, 0);
+static SENSOR_DEVICE_ATTR_RW(temp1_max, temp_over, 0);
+static SENSOR_DEVICE_ATTR_RW(temp1_max_hyst, temp_hyst, 0);
+static SENSOR_DEVICE_ATTR_RO(temp2_input, temp, 1);
+static SENSOR_DEVICE_ATTR_RW(temp2_max, temp_over, 1);
+static SENSOR_DEVICE_ATTR_RW(temp2_max_hyst, temp_hyst, 1);
+static SENSOR_DEVICE_ATTR_RO(temp3_input, temp, 2);
+static SENSOR_DEVICE_ATTR_RW(temp3_max, temp_over, 2);
+static SENSOR_DEVICE_ATTR_RW(temp3_max_hyst, temp_hyst, 2);
 
 /* 2 Fans */
-static ssize_t show_fan(struct device *dev, struct device_attribute *da,
-		char *buf) {
+static ssize_t fan_show(struct device *dev, struct device_attribute *da,
+			char *buf) {
 	struct via686a_data *data = via686a_update_device(dev);
 	struct sensor_device_attribute *attr = to_sensor_dev_attr(da);
 	int nr = attr->index;
 	return sprintf(buf, "%d\n", FAN_FROM_REG(data->fan[nr],
 				DIV_FROM_REG(data->fan_div[nr])));
 }
-static ssize_t show_fan_min(struct device *dev, struct device_attribute *da,
-		char *buf) {
+static ssize_t fan_min_show(struct device *dev, struct device_attribute *da,
+			    char *buf) {
 	struct via686a_data *data = via686a_update_device(dev);
 	struct sensor_device_attribute *attr = to_sensor_dev_attr(da);
 	int nr = attr->index;
@@ -521,15 +524,15 @@ static ssize_t show_fan_min(struct device *dev, struct device_attribute *da,
 		FAN_FROM_REG(data->fan_min[nr],
 			     DIV_FROM_REG(data->fan_div[nr])));
 }
-static ssize_t show_fan_div(struct device *dev, struct device_attribute *da,
-		char *buf) {
+static ssize_t fan_div_show(struct device *dev, struct device_attribute *da,
+			    char *buf) {
 	struct via686a_data *data = via686a_update_device(dev);
 	struct sensor_device_attribute *attr = to_sensor_dev_attr(da);
 	int nr = attr->index;
 	return sprintf(buf, "%d\n", DIV_FROM_REG(data->fan_div[nr]));
 }
-static ssize_t set_fan_min(struct device *dev, struct device_attribute *da,
-		const char *buf, size_t count) {
+static ssize_t fan_min_store(struct device *dev, struct device_attribute *da,
+			     const char *buf, size_t count) {
 	struct via686a_data *data = dev_get_drvdata(dev);
 	struct sensor_device_attribute *attr = to_sensor_dev_attr(da);
 	int nr = attr->index;
@@ -546,8 +549,8 @@ static ssize_t set_fan_min(struct device *dev, struct device_attribute *da,
 	mutex_unlock(&data->update_lock);
 	return count;
 }
-static ssize_t set_fan_div(struct device *dev, struct device_attribute *da,
-		const char *buf, size_t count) {
+static ssize_t fan_div_store(struct device *dev, struct device_attribute *da,
+			     const char *buf, size_t count) {
 	struct via686a_data *data = dev_get_drvdata(dev);
 	struct sensor_device_attribute *attr = to_sensor_dev_attr(da);
 	int nr = attr->index;
@@ -568,16 +571,12 @@ static ssize_t set_fan_div(struct device *dev, struct device_attribute *da,
 	return count;
 }
 
-#define show_fan_offset(offset)						\
-static SENSOR_DEVICE_ATTR(fan##offset##_input, S_IRUGO,			\
-		show_fan, NULL, offset - 1);				\
-static SENSOR_DEVICE_ATTR(fan##offset##_min, S_IRUGO | S_IWUSR,		\
-		show_fan_min, set_fan_min, offset - 1);			\
-static SENSOR_DEVICE_ATTR(fan##offset##_div, S_IRUGO | S_IWUSR,		\
-		show_fan_div, set_fan_div, offset - 1);
-
-show_fan_offset(1);
-show_fan_offset(2);
+static SENSOR_DEVICE_ATTR_RO(fan1_input, fan, 0);
+static SENSOR_DEVICE_ATTR_RW(fan1_min, fan_min, 0);
+static SENSOR_DEVICE_ATTR_RW(fan1_div, fan_div, 0);
+static SENSOR_DEVICE_ATTR_RO(fan2_input, fan, 1);
+static SENSOR_DEVICE_ATTR_RW(fan2_min, fan_min, 1);
+static SENSOR_DEVICE_ATTR_RW(fan2_div, fan_div, 1);
 
 /* Alarms */
 static ssize_t alarms_show(struct device *dev, struct device_attribute *attr,
@@ -589,23 +588,23 @@ static ssize_t alarms_show(struct device *dev, struct device_attribute *attr,
 
 static DEVICE_ATTR_RO(alarms);
 
-static ssize_t show_alarm(struct device *dev, struct device_attribute *attr,
+static ssize_t alarm_show(struct device *dev, struct device_attribute *attr,
 			  char *buf)
 {
 	int bitnr = to_sensor_dev_attr(attr)->index;
 	struct via686a_data *data = via686a_update_device(dev);
 	return sprintf(buf, "%u\n", (data->alarms >> bitnr) & 1);
 }
-static SENSOR_DEVICE_ATTR(in0_alarm, S_IRUGO, show_alarm, NULL, 0);
-static SENSOR_DEVICE_ATTR(in1_alarm, S_IRUGO, show_alarm, NULL, 1);
-static SENSOR_DEVICE_ATTR(in2_alarm, S_IRUGO, show_alarm, NULL, 2);
-static SENSOR_DEVICE_ATTR(in3_alarm, S_IRUGO, show_alarm, NULL, 3);
-static SENSOR_DEVICE_ATTR(in4_alarm, S_IRUGO, show_alarm, NULL, 8);
-static SENSOR_DEVICE_ATTR(temp1_alarm, S_IRUGO, show_alarm, NULL, 4);
-static SENSOR_DEVICE_ATTR(temp2_alarm, S_IRUGO, show_alarm, NULL, 11);
-static SENSOR_DEVICE_ATTR(temp3_alarm, S_IRUGO, show_alarm, NULL, 15);
-static SENSOR_DEVICE_ATTR(fan1_alarm, S_IRUGO, show_alarm, NULL, 6);
-static SENSOR_DEVICE_ATTR(fan2_alarm, S_IRUGO, show_alarm, NULL, 7);
+static SENSOR_DEVICE_ATTR_RO(in0_alarm, alarm, 0);
+static SENSOR_DEVICE_ATTR_RO(in1_alarm, alarm, 1);
+static SENSOR_DEVICE_ATTR_RO(in2_alarm, alarm, 2);
+static SENSOR_DEVICE_ATTR_RO(in3_alarm, alarm, 3);
+static SENSOR_DEVICE_ATTR_RO(in4_alarm, alarm, 8);
+static SENSOR_DEVICE_ATTR_RO(temp1_alarm, alarm, 4);
+static SENSOR_DEVICE_ATTR_RO(temp2_alarm, alarm, 11);
+static SENSOR_DEVICE_ATTR_RO(temp3_alarm, alarm, 15);
+static SENSOR_DEVICE_ATTR_RO(fan1_alarm, alarm, 6);
+static SENSOR_DEVICE_ATTR_RO(fan2_alarm, alarm, 7);
 
 static ssize_t name_show(struct device *dev, struct device_attribute
 			 *devattr, char *buf)
@@ -676,7 +675,6 @@ static struct platform_driver via686a_driver = {
 	.remove		= via686a_remove,
 };
 
-
 /* This is called when the module is loaded */
 static int via686a_probe(struct platform_device *pdev)
 {
diff --git a/drivers/hwmon/vt1211.c b/drivers/hwmon/vt1211.c
index 3a6bfa51cb94..95d5e8ec8b7f 100644
--- a/drivers/hwmon/vt1211.c
+++ b/drivers/hwmon/vt1211.c
@@ -226,15 +226,21 @@ static inline void superio_select(int sio_cip, int ldn)
 	outb(ldn, sio_cip + 1);
 }
 
-static inline void superio_enter(int sio_cip)
+static inline int superio_enter(int sio_cip)
 {
+	if (!request_muxed_region(sio_cip, 2, DRVNAME))
+		return -EBUSY;
+
 	outb(0x87, sio_cip);
 	outb(0x87, sio_cip);
+
+	return 0;
 }
 
 static inline void superio_exit(int sio_cip)
 {
 	outb(0xaa, sio_cip);
+	release_region(sio_cip, 2);
 }
 
 /* ---------------------------------------------------------------------
@@ -1282,11 +1288,14 @@ EXIT:
 
 static int __init vt1211_find(int sio_cip, unsigned short *address)
 {
-	int err = -ENODEV;
+	int err;
 	int devid;
 
-	superio_enter(sio_cip);
+	err = superio_enter(sio_cip);
+	if (err)
+		return err;
 
+	err = -ENODEV;
 	devid = force_id ? force_id : superio_inb(sio_cip, SIO_VT1211_DEVID);
 	if (devid != SIO_VT1211_ID)
 		goto EXIT;
diff --git a/drivers/hwmon/vt8231.c b/drivers/hwmon/vt8231.c
index 367b5eb53fb6..e2f1a80367e2 100644
--- a/drivers/hwmon/vt8231.c
+++ b/drivers/hwmon/vt8231.c
@@ -192,8 +192,8 @@ static inline void vt8231_write_value(struct vt8231_data *data, u8 reg,
 }
 
 /* following are the sysfs callback functions */
-static ssize_t show_in(struct device *dev, struct device_attribute *attr,
-		char *buf)
+static ssize_t in_show(struct device *dev, struct device_attribute *attr,
+		       char *buf)
 {
 	struct sensor_device_attribute *sensor_attr = to_sensor_dev_attr(attr);
 	int nr = sensor_attr->index;
@@ -202,8 +202,8 @@ static ssize_t show_in(struct device *dev, struct device_attribute *attr,
 	return sprintf(buf, "%d\n", ((data->in[nr] - 3) * 10000) / 958);
 }
 
-static ssize_t show_in_min(struct device *dev, struct device_attribute *attr,
-		char *buf)
+static ssize_t in_min_show(struct device *dev, struct device_attribute *attr,
+			   char *buf)
 {
 	struct sensor_device_attribute *sensor_attr = to_sensor_dev_attr(attr);
 	int nr = sensor_attr->index;
@@ -212,8 +212,8 @@ static ssize_t show_in_min(struct device *dev, struct device_attribute *attr,
 	return sprintf(buf, "%d\n", ((data->in_min[nr] - 3) * 10000) / 958);
 }
 
-static ssize_t show_in_max(struct device *dev, struct device_attribute *attr,
-		char *buf)
+static ssize_t in_max_show(struct device *dev, struct device_attribute *attr,
+			   char *buf)
 {
 	struct sensor_device_attribute *sensor_attr = to_sensor_dev_attr(attr);
 	int nr = sensor_attr->index;
@@ -222,8 +222,8 @@ static ssize_t show_in_max(struct device *dev, struct device_attribute *attr,
 	return sprintf(buf, "%d\n", (((data->in_max[nr] - 3) * 10000) / 958));
 }
 
-static ssize_t set_in_min(struct device *dev, struct device_attribute *attr,
-		const char *buf, size_t count)
+static ssize_t in_min_store(struct device *dev, struct device_attribute *attr,
+			    const char *buf, size_t count)
 {
 	struct sensor_device_attribute *sensor_attr = to_sensor_dev_attr(attr);
 	int nr = sensor_attr->index;
@@ -242,8 +242,8 @@ static ssize_t set_in_min(struct device *dev, struct device_attribute *attr,
 	return count;
 }
 
-static ssize_t set_in_max(struct device *dev, struct device_attribute *attr,
-		const char *buf, size_t count)
+static ssize_t in_max_store(struct device *dev, struct device_attribute *attr,
+			    const char *buf, size_t count)
 {
 	struct sensor_device_attribute *sensor_attr = to_sensor_dev_attr(attr);
 	int nr = sensor_attr->index;
@@ -330,19 +330,21 @@ static ssize_t in5_max_store(struct device *dev,
 	return count;
 }
 
-#define define_voltage_sysfs(offset)				\
-static SENSOR_DEVICE_ATTR(in##offset##_input, S_IRUGO,		\
-		show_in, NULL, offset);				\
-static SENSOR_DEVICE_ATTR(in##offset##_min, S_IRUGO | S_IWUSR,	\
-		show_in_min, set_in_min, offset);		\
-static SENSOR_DEVICE_ATTR(in##offset##_max, S_IRUGO | S_IWUSR,	\
-		show_in_max, set_in_max, offset)
-
-define_voltage_sysfs(0);
-define_voltage_sysfs(1);
-define_voltage_sysfs(2);
-define_voltage_sysfs(3);
-define_voltage_sysfs(4);
+static SENSOR_DEVICE_ATTR_RO(in0_input, in, 0);
+static SENSOR_DEVICE_ATTR_RW(in0_min, in_min, 0);
+static SENSOR_DEVICE_ATTR_RW(in0_max, in_max, 0);
+static SENSOR_DEVICE_ATTR_RO(in1_input, in, 1);
+static SENSOR_DEVICE_ATTR_RW(in1_min, in_min, 1);
+static SENSOR_DEVICE_ATTR_RW(in1_max, in_max, 1);
+static SENSOR_DEVICE_ATTR_RO(in2_input, in, 2);
+static SENSOR_DEVICE_ATTR_RW(in2_min, in_min, 2);
+static SENSOR_DEVICE_ATTR_RW(in2_max, in_max, 2);
+static SENSOR_DEVICE_ATTR_RO(in3_input, in, 3);
+static SENSOR_DEVICE_ATTR_RW(in3_min, in_min, 3);
+static SENSOR_DEVICE_ATTR_RW(in3_max, in_max, 3);
+static SENSOR_DEVICE_ATTR_RO(in4_input, in, 4);
+static SENSOR_DEVICE_ATTR_RW(in4_min, in_min, 4);
+static SENSOR_DEVICE_ATTR_RW(in4_max, in_max, 4);
 
 static DEVICE_ATTR_RO(in5_input);
 static DEVICE_ATTR_RW(in5_min);
@@ -407,8 +409,8 @@ static ssize_t temp1_max_hyst_store(struct device *dev,
 	return count;
 }
 
-static ssize_t show_temp(struct device *dev, struct device_attribute *attr,
-		char *buf)
+static ssize_t temp_show(struct device *dev, struct device_attribute *attr,
+			 char *buf)
 {
 	struct sensor_device_attribute *sensor_attr = to_sensor_dev_attr(attr);
 	int nr = sensor_attr->index;
@@ -416,8 +418,8 @@ static ssize_t show_temp(struct device *dev, struct device_attribute *attr,
 	return sprintf(buf, "%d\n", TEMP_FROM_REG(data->temp[nr]));
 }
 
-static ssize_t show_temp_max(struct device *dev, struct device_attribute *attr,
-		char *buf)
+static ssize_t temp_max_show(struct device *dev,
+			     struct device_attribute *attr, char *buf)
 {
 	struct sensor_device_attribute *sensor_attr = to_sensor_dev_attr(attr);
 	int nr = sensor_attr->index;
@@ -425,8 +427,8 @@ static ssize_t show_temp_max(struct device *dev, struct device_attribute *attr,
 	return sprintf(buf, "%d\n", TEMP_MAXMIN_FROM_REG(data->temp_max[nr]));
 }
 
-static ssize_t show_temp_min(struct device *dev, struct device_attribute *attr,
-		char *buf)
+static ssize_t temp_min_show(struct device *dev,
+			     struct device_attribute *attr, char *buf)
 {
 	struct sensor_device_attribute *sensor_attr = to_sensor_dev_attr(attr);
 	int nr = sensor_attr->index;
@@ -434,8 +436,9 @@ static ssize_t show_temp_min(struct device *dev, struct device_attribute *attr,
 	return sprintf(buf, "%d\n", TEMP_MAXMIN_FROM_REG(data->temp_min[nr]));
 }
 
-static ssize_t set_temp_max(struct device *dev, struct device_attribute *attr,
-		const char *buf, size_t count)
+static ssize_t temp_max_store(struct device *dev,
+			      struct device_attribute *attr, const char *buf,
+			      size_t count)
 {
 	struct sensor_device_attribute *sensor_attr = to_sensor_dev_attr(attr);
 	int nr = sensor_attr->index;
@@ -453,8 +456,9 @@ static ssize_t set_temp_max(struct device *dev, struct device_attribute *attr,
 	mutex_unlock(&data->update_lock);
 	return count;
 }
-static ssize_t set_temp_min(struct device *dev, struct device_attribute *attr,
-		const char *buf, size_t count)
+static ssize_t temp_min_store(struct device *dev,
+			      struct device_attribute *attr, const char *buf,
+			      size_t count)
 {
 	struct sensor_device_attribute *sensor_attr = to_sensor_dev_attr(attr);
 	int nr = sensor_attr->index;
@@ -477,27 +481,30 @@ static ssize_t set_temp_min(struct device *dev, struct device_attribute *attr,
  * Note that these map the Linux temperature sensor numbering (1-6) to the VIA
  * temperature sensor numbering (0-5)
  */
-#define define_temperature_sysfs(offset)				\
-static SENSOR_DEVICE_ATTR(temp##offset##_input, S_IRUGO,		\
-		show_temp, NULL, offset - 1);				\
-static SENSOR_DEVICE_ATTR(temp##offset##_max, S_IRUGO | S_IWUSR,	\
-		show_temp_max, set_temp_max, offset - 1);		\
-static SENSOR_DEVICE_ATTR(temp##offset##_max_hyst, S_IRUGO | S_IWUSR,	\
-		show_temp_min, set_temp_min, offset - 1)
 
 static DEVICE_ATTR_RO(temp1_input);
 static DEVICE_ATTR_RW(temp1_max);
 static DEVICE_ATTR_RW(temp1_max_hyst);
 
-define_temperature_sysfs(2);
-define_temperature_sysfs(3);
-define_temperature_sysfs(4);
-define_temperature_sysfs(5);
-define_temperature_sysfs(6);
+static SENSOR_DEVICE_ATTR_RO(temp2_input, temp, 1);
+static SENSOR_DEVICE_ATTR_RW(temp2_max, temp_max, 1);
+static SENSOR_DEVICE_ATTR_RW(temp2_max_hyst, temp_min, 1);
+static SENSOR_DEVICE_ATTR_RO(temp3_input, temp, 2);
+static SENSOR_DEVICE_ATTR_RW(temp3_max, temp_max, 2);
+static SENSOR_DEVICE_ATTR_RW(temp3_max_hyst, temp_min, 2);
+static SENSOR_DEVICE_ATTR_RO(temp4_input, temp, 3);
+static SENSOR_DEVICE_ATTR_RW(temp4_max, temp_max, 3);
+static SENSOR_DEVICE_ATTR_RW(temp4_max_hyst, temp_min, 3);
+static SENSOR_DEVICE_ATTR_RO(temp5_input, temp, 4);
+static SENSOR_DEVICE_ATTR_RW(temp5_max, temp_max, 4);
+static SENSOR_DEVICE_ATTR_RW(temp5_max_hyst, temp_min, 4);
+static SENSOR_DEVICE_ATTR_RO(temp6_input, temp, 5);
+static SENSOR_DEVICE_ATTR_RW(temp6_max, temp_max, 5);
+static SENSOR_DEVICE_ATTR_RW(temp6_max_hyst, temp_min, 5);
 
 /* Fans */
-static ssize_t show_fan(struct device *dev, struct device_attribute *attr,
-		char *buf)
+static ssize_t fan_show(struct device *dev, struct device_attribute *attr,
+			char *buf)
 {
 	struct sensor_device_attribute *sensor_attr = to_sensor_dev_attr(attr);
 	int nr = sensor_attr->index;
@@ -506,8 +513,8 @@ static ssize_t show_fan(struct device *dev, struct device_attribute *attr,
 				DIV_FROM_REG(data->fan_div[nr])));
 }
 
-static ssize_t show_fan_min(struct device *dev, struct device_attribute *attr,
-		char *buf)
+static ssize_t fan_min_show(struct device *dev, struct device_attribute *attr,
+			    char *buf)
 {
 	struct sensor_device_attribute *sensor_attr = to_sensor_dev_attr(attr);
 	int nr = sensor_attr->index;
@@ -516,8 +523,8 @@ static ssize_t show_fan_min(struct device *dev, struct device_attribute *attr,
 			DIV_FROM_REG(data->fan_div[nr])));
 }
 
-static ssize_t show_fan_div(struct device *dev, struct device_attribute *attr,
-		char *buf)
+static ssize_t fan_div_show(struct device *dev, struct device_attribute *attr,
+			    char *buf)
 {
 	struct sensor_device_attribute *sensor_attr = to_sensor_dev_attr(attr);
 	int nr = sensor_attr->index;
@@ -525,8 +532,9 @@ static ssize_t show_fan_div(struct device *dev, struct device_attribute *attr,
 	return sprintf(buf, "%d\n", DIV_FROM_REG(data->fan_div[nr]));
 }
 
-static ssize_t set_fan_min(struct device *dev, struct device_attribute *attr,
-		const char *buf, size_t count)
+static ssize_t fan_min_store(struct device *dev,
+			     struct device_attribute *attr, const char *buf,
+			     size_t count)
 {
 	struct sensor_device_attribute *sensor_attr = to_sensor_dev_attr(attr);
 	int nr = sensor_attr->index;
@@ -545,8 +553,9 @@ static ssize_t set_fan_min(struct device *dev, struct device_attribute *attr,
 	return count;
 }
 
-static ssize_t set_fan_div(struct device *dev, struct device_attribute *attr,
-		const char *buf, size_t count)
+static ssize_t fan_div_store(struct device *dev,
+			     struct device_attribute *attr, const char *buf,
+			     size_t count)
 {
 	struct vt8231_data *data = dev_get_drvdata(dev);
 	struct sensor_device_attribute *sensor_attr = to_sensor_dev_attr(attr);
@@ -593,17 +602,12 @@ static ssize_t set_fan_div(struct device *dev, struct device_attribute *attr,
 	return count;
 }
 
-
-#define define_fan_sysfs(offset)					\
-static SENSOR_DEVICE_ATTR(fan##offset##_input, S_IRUGO,			\
-		show_fan, NULL, offset - 1);				\
-static SENSOR_DEVICE_ATTR(fan##offset##_div, S_IRUGO | S_IWUSR,		\
-		show_fan_div, set_fan_div, offset - 1);			\
-static SENSOR_DEVICE_ATTR(fan##offset##_min, S_IRUGO | S_IWUSR,		\
-		show_fan_min, set_fan_min, offset - 1)
-
-define_fan_sysfs(1);
-define_fan_sysfs(2);
+static SENSOR_DEVICE_ATTR_RO(fan1_input, fan, 0);
+static SENSOR_DEVICE_ATTR_RW(fan1_min, fan_min, 0);
+static SENSOR_DEVICE_ATTR_RW(fan1_div, fan_div, 0);
+static SENSOR_DEVICE_ATTR_RO(fan2_input, fan, 1);
+static SENSOR_DEVICE_ATTR_RW(fan2_min, fan_min, 1);
+static SENSOR_DEVICE_ATTR_RW(fan2_div, fan_div, 1);
 
 /* Alarms */
 static ssize_t alarms_show(struct device *dev, struct device_attribute *attr,
@@ -614,27 +618,27 @@ static ssize_t alarms_show(struct device *dev, struct device_attribute *attr,
 }
 static DEVICE_ATTR_RO(alarms);
 
-static ssize_t show_alarm(struct device *dev, struct device_attribute *attr,
+static ssize_t alarm_show(struct device *dev, struct device_attribute *attr,
 			  char *buf)
 {
 	int bitnr = to_sensor_dev_attr(attr)->index;
 	struct vt8231_data *data = vt8231_update_device(dev);
 	return sprintf(buf, "%u\n", (data->alarms >> bitnr) & 1);
 }
-static SENSOR_DEVICE_ATTR(temp1_alarm, S_IRUGO, show_alarm, NULL, 4);
-static SENSOR_DEVICE_ATTR(temp2_alarm, S_IRUGO, show_alarm, NULL, 11);
-static SENSOR_DEVICE_ATTR(temp3_alarm, S_IRUGO, show_alarm, NULL, 0);
-static SENSOR_DEVICE_ATTR(temp4_alarm, S_IRUGO, show_alarm, NULL, 1);
-static SENSOR_DEVICE_ATTR(temp5_alarm, S_IRUGO, show_alarm, NULL, 3);
-static SENSOR_DEVICE_ATTR(temp6_alarm, S_IRUGO, show_alarm, NULL, 8);
-static SENSOR_DEVICE_ATTR(in0_alarm, S_IRUGO, show_alarm, NULL, 11);
-static SENSOR_DEVICE_ATTR(in1_alarm, S_IRUGO, show_alarm, NULL, 0);
-static SENSOR_DEVICE_ATTR(in2_alarm, S_IRUGO, show_alarm, NULL, 1);
-static SENSOR_DEVICE_ATTR(in3_alarm, S_IRUGO, show_alarm, NULL, 3);
-static SENSOR_DEVICE_ATTR(in4_alarm, S_IRUGO, show_alarm, NULL, 8);
-static SENSOR_DEVICE_ATTR(in5_alarm, S_IRUGO, show_alarm, NULL, 2);
-static SENSOR_DEVICE_ATTR(fan1_alarm, S_IRUGO, show_alarm, NULL, 6);
-static SENSOR_DEVICE_ATTR(fan2_alarm, S_IRUGO, show_alarm, NULL, 7);
+static SENSOR_DEVICE_ATTR_RO(temp1_alarm, alarm, 4);
+static SENSOR_DEVICE_ATTR_RO(temp2_alarm, alarm, 11);
+static SENSOR_DEVICE_ATTR_RO(temp3_alarm, alarm, 0);
+static SENSOR_DEVICE_ATTR_RO(temp4_alarm, alarm, 1);
+static SENSOR_DEVICE_ATTR_RO(temp5_alarm, alarm, 3);
+static SENSOR_DEVICE_ATTR_RO(temp6_alarm, alarm, 8);
+static SENSOR_DEVICE_ATTR_RO(in0_alarm, alarm, 11);
+static SENSOR_DEVICE_ATTR_RO(in1_alarm, alarm, 0);
+static SENSOR_DEVICE_ATTR_RO(in2_alarm, alarm, 1);
+static SENSOR_DEVICE_ATTR_RO(in3_alarm, alarm, 3);
+static SENSOR_DEVICE_ATTR_RO(in4_alarm, alarm, 8);
+static SENSOR_DEVICE_ATTR_RO(in5_alarm, alarm, 2);
+static SENSOR_DEVICE_ATTR_RO(fan1_alarm, alarm, 6);
+static SENSOR_DEVICE_ATTR_RO(fan2_alarm, alarm, 7);
 
 static ssize_t name_show(struct device *dev, struct device_attribute
 			 *devattr, char *buf)
diff --git a/drivers/hwmon/w83627hf.c b/drivers/hwmon/w83627hf.c
index 8ac89d0781cc..7ca53a28c305 100644
--- a/drivers/hwmon/w83627hf.c
+++ b/drivers/hwmon/w83627hf.c
@@ -130,17 +130,23 @@ superio_select(struct w83627hf_sio_data *sio, int ld)
 	outb(ld,  sio->sioaddr + 1);
 }
 
-static inline void
+static inline int
 superio_enter(struct w83627hf_sio_data *sio)
 {
+	if (!request_muxed_region(sio->sioaddr, 2, DRVNAME))
+		return -EBUSY;
+
 	outb(0x87, sio->sioaddr);
 	outb(0x87, sio->sioaddr);
+
+	return 0;
 }
 
 static inline void
 superio_exit(struct w83627hf_sio_data *sio)
 {
 	outb(0xAA, sio->sioaddr);
+	release_region(sio->sioaddr, 2);
 }
 
 #define W627_DEVID 0x52
@@ -396,7 +402,6 @@ struct w83627hf_data {
 #endif
 };
 
-
 static int w83627hf_probe(struct platform_device *pdev);
 static int w83627hf_remove(struct platform_device *pdev);
 
@@ -482,28 +487,28 @@ static struct platform_driver w83627hf_driver = {
 };
 
 static ssize_t
-show_in_input(struct device *dev, struct device_attribute *devattr, char *buf)
+in_input_show(struct device *dev, struct device_attribute *devattr, char *buf)
 {
 	int nr = to_sensor_dev_attr(devattr)->index;
 	struct w83627hf_data *data = w83627hf_update_device(dev);
 	return sprintf(buf, "%ld\n", (long)IN_FROM_REG(data->in[nr]));
 }
 static ssize_t
-show_in_min(struct device *dev, struct device_attribute *devattr, char *buf)
+in_min_show(struct device *dev, struct device_attribute *devattr, char *buf)
 {
 	int nr = to_sensor_dev_attr(devattr)->index;
 	struct w83627hf_data *data = w83627hf_update_device(dev);
 	return sprintf(buf, "%ld\n", (long)IN_FROM_REG(data->in_min[nr]));
 }
 static ssize_t
-show_in_max(struct device *dev, struct device_attribute *devattr, char *buf)
+in_max_show(struct device *dev, struct device_attribute *devattr, char *buf)
 {
 	int nr = to_sensor_dev_attr(devattr)->index;
 	struct w83627hf_data *data = w83627hf_update_device(dev);
 	return sprintf(buf, "%ld\n", (long)IN_FROM_REG(data->in_max[nr]));
 }
 static ssize_t
-store_in_min(struct device *dev, struct device_attribute *devattr,
+in_min_store(struct device *dev, struct device_attribute *devattr,
 	     const char *buf, size_t count)
 {
 	int nr = to_sensor_dev_attr(devattr)->index;
@@ -522,7 +527,7 @@ store_in_min(struct device *dev, struct device_attribute *devattr,
 	return count;
 }
 static ssize_t
-store_in_max(struct device *dev, struct device_attribute *devattr,
+in_max_store(struct device *dev, struct device_attribute *devattr,
 	     const char *buf, size_t count)
 {
 	int nr = to_sensor_dev_attr(devattr)->index;
@@ -540,22 +545,31 @@ store_in_max(struct device *dev, struct device_attribute *devattr,
 	mutex_unlock(&data->update_lock);
 	return count;
 }
-#define sysfs_vin_decl(offset) \
-static SENSOR_DEVICE_ATTR(in##offset##_input, S_IRUGO,		\
-			  show_in_input, NULL, offset);		\
-static SENSOR_DEVICE_ATTR(in##offset##_min, S_IRUGO|S_IWUSR,	\
-			  show_in_min, store_in_min, offset);	\
-static SENSOR_DEVICE_ATTR(in##offset##_max, S_IRUGO|S_IWUSR,	\
-			  show_in_max, store_in_max, offset);
-
-sysfs_vin_decl(1);
-sysfs_vin_decl(2);
-sysfs_vin_decl(3);
-sysfs_vin_decl(4);
-sysfs_vin_decl(5);
-sysfs_vin_decl(6);
-sysfs_vin_decl(7);
-sysfs_vin_decl(8);
+
+static SENSOR_DEVICE_ATTR_RO(in1_input, in_input, 1);
+static SENSOR_DEVICE_ATTR_RW(in1_min, in_min, 1);
+static SENSOR_DEVICE_ATTR_RW(in1_max, in_max, 1);
+static SENSOR_DEVICE_ATTR_RO(in2_input, in_input, 2);
+static SENSOR_DEVICE_ATTR_RW(in2_min, in_min, 2);
+static SENSOR_DEVICE_ATTR_RW(in2_max, in_max, 2);
+static SENSOR_DEVICE_ATTR_RO(in3_input, in_input, 3);
+static SENSOR_DEVICE_ATTR_RW(in3_min, in_min, 3);
+static SENSOR_DEVICE_ATTR_RW(in3_max, in_max, 3);
+static SENSOR_DEVICE_ATTR_RO(in4_input, in_input, 4);
+static SENSOR_DEVICE_ATTR_RW(in4_min, in_min, 4);
+static SENSOR_DEVICE_ATTR_RW(in4_max, in_max, 4);
+static SENSOR_DEVICE_ATTR_RO(in5_input, in_input, 5);
+static SENSOR_DEVICE_ATTR_RW(in5_min, in_min, 5);
+static SENSOR_DEVICE_ATTR_RW(in5_max, in_max, 5);
+static SENSOR_DEVICE_ATTR_RO(in6_input, in_input, 6);
+static SENSOR_DEVICE_ATTR_RW(in6_min, in_min, 6);
+static SENSOR_DEVICE_ATTR_RW(in6_max, in_max, 6);
+static SENSOR_DEVICE_ATTR_RO(in7_input, in_input, 7);
+static SENSOR_DEVICE_ATTR_RW(in7_min, in_min, 7);
+static SENSOR_DEVICE_ATTR_RW(in7_max, in_max, 7);
+static SENSOR_DEVICE_ATTR_RO(in8_input, in_input, 8);
+static SENSOR_DEVICE_ATTR_RW(in8_min, in_min, 8);
+static SENSOR_DEVICE_ATTR_RW(in8_max, in_max, 8);
 
 /* use a different set of functions for in0 */
 static ssize_t show_in_0(struct w83627hf_data *data, char *buf, u8 reg)
@@ -661,7 +675,8 @@ static DEVICE_ATTR_RW(in0_min);
 static DEVICE_ATTR_RW(in0_max);
 
 static ssize_t
-show_fan_input(struct device *dev, struct device_attribute *devattr, char *buf)
+fan_input_show(struct device *dev, struct device_attribute *devattr,
+	       char *buf)
 {
 	int nr = to_sensor_dev_attr(devattr)->index;
 	struct w83627hf_data *data = w83627hf_update_device(dev);
@@ -669,7 +684,7 @@ show_fan_input(struct device *dev, struct device_attribute *devattr, char *buf)
 				(long)DIV_FROM_REG(data->fan_div[nr])));
 }
 static ssize_t
-show_fan_min(struct device *dev, struct device_attribute *devattr, char *buf)
+fan_min_show(struct device *dev, struct device_attribute *devattr, char *buf)
 {
 	int nr = to_sensor_dev_attr(devattr)->index;
 	struct w83627hf_data *data = w83627hf_update_device(dev);
@@ -677,7 +692,7 @@ show_fan_min(struct device *dev, struct device_attribute *devattr, char *buf)
 				(long)DIV_FROM_REG(data->fan_div[nr])));
 }
 static ssize_t
-store_fan_min(struct device *dev, struct device_attribute *devattr,
+fan_min_store(struct device *dev, struct device_attribute *devattr,
 	      const char *buf, size_t count)
 {
 	int nr = to_sensor_dev_attr(devattr)->index;
@@ -697,18 +712,16 @@ store_fan_min(struct device *dev, struct device_attribute *devattr,
 	mutex_unlock(&data->update_lock);
 	return count;
 }
-#define sysfs_fan_decl(offset)	\
-static SENSOR_DEVICE_ATTR(fan##offset##_input, S_IRUGO,			\
-			  show_fan_input, NULL, offset - 1);		\
-static SENSOR_DEVICE_ATTR(fan##offset##_min, S_IRUGO | S_IWUSR,		\
-			  show_fan_min, store_fan_min, offset - 1);
 
-sysfs_fan_decl(1);
-sysfs_fan_decl(2);
-sysfs_fan_decl(3);
+static SENSOR_DEVICE_ATTR_RO(fan1_input, fan_input, 0);
+static SENSOR_DEVICE_ATTR_RW(fan1_min, fan_min, 0);
+static SENSOR_DEVICE_ATTR_RO(fan2_input, fan_input, 1);
+static SENSOR_DEVICE_ATTR_RW(fan2_min, fan_min, 1);
+static SENSOR_DEVICE_ATTR_RO(fan3_input, fan_input, 2);
+static SENSOR_DEVICE_ATTR_RW(fan3_min, fan_min, 2);
 
 static ssize_t
-show_temp(struct device *dev, struct device_attribute *devattr, char *buf)
+temp_show(struct device *dev, struct device_attribute *devattr, char *buf)
 {
 	int nr = to_sensor_dev_attr(devattr)->index;
 	struct w83627hf_data *data = w83627hf_update_device(dev);
@@ -719,8 +732,7 @@ show_temp(struct device *dev, struct device_attribute *devattr, char *buf)
 }
 
 static ssize_t
-show_temp_max(struct device *dev, struct device_attribute *devattr,
-	      char *buf)
+temp_max_show(struct device *dev, struct device_attribute *devattr, char *buf)
 {
 	int nr = to_sensor_dev_attr(devattr)->index;
 	struct w83627hf_data *data = w83627hf_update_device(dev);
@@ -731,7 +743,7 @@ show_temp_max(struct device *dev, struct device_attribute *devattr,
 }
 
 static ssize_t
-show_temp_max_hyst(struct device *dev, struct device_attribute *devattr,
+temp_max_hyst_show(struct device *dev, struct device_attribute *devattr,
 		   char *buf)
 {
 	int nr = to_sensor_dev_attr(devattr)->index;
@@ -743,7 +755,7 @@ show_temp_max_hyst(struct device *dev, struct device_attribute *devattr,
 }
 
 static ssize_t
-store_temp_max(struct device *dev, struct device_attribute *devattr,
+temp_max_store(struct device *dev, struct device_attribute *devattr,
 	       const char *buf, size_t count)
 {
 	int nr = to_sensor_dev_attr(devattr)->index;
@@ -765,7 +777,7 @@ store_temp_max(struct device *dev, struct device_attribute *devattr,
 }
 
 static ssize_t
-store_temp_max_hyst(struct device *dev, struct device_attribute *devattr,
+temp_max_hyst_store(struct device *dev, struct device_attribute *devattr,
 		    const char *buf, size_t count)
 {
 	int nr = to_sensor_dev_attr(devattr)->index;
@@ -786,17 +798,15 @@ store_temp_max_hyst(struct device *dev, struct device_attribute *devattr,
 	return count;
 }
 
-#define sysfs_temp_decl(offset) \
-static SENSOR_DEVICE_ATTR(temp##offset##_input, S_IRUGO,		\
-			  show_temp, NULL, offset - 1);			\
-static SENSOR_DEVICE_ATTR(temp##offset##_max, S_IRUGO|S_IWUSR,	 	\
-			  show_temp_max, store_temp_max, offset - 1);	\
-static SENSOR_DEVICE_ATTR(temp##offset##_max_hyst, S_IRUGO|S_IWUSR,	\
-			  show_temp_max_hyst, store_temp_max_hyst, offset - 1);
-
-sysfs_temp_decl(1);
-sysfs_temp_decl(2);
-sysfs_temp_decl(3);
+static SENSOR_DEVICE_ATTR_RO(temp1_input, temp, 0);
+static SENSOR_DEVICE_ATTR_RW(temp1_max, temp_max, 0);
+static SENSOR_DEVICE_ATTR_RW(temp1_max_hyst, temp_max_hyst, 0);
+static SENSOR_DEVICE_ATTR_RO(temp2_input, temp, 1);
+static SENSOR_DEVICE_ATTR_RW(temp2_max, temp_max, 1);
+static SENSOR_DEVICE_ATTR_RW(temp2_max_hyst, temp_max_hyst, 1);
+static SENSOR_DEVICE_ATTR_RO(temp3_input, temp, 2);
+static SENSOR_DEVICE_ATTR_RW(temp3_max, temp_max, 2);
+static SENSOR_DEVICE_ATTR_RW(temp3_max_hyst, temp_max_hyst, 2);
 
 static ssize_t
 cpu0_vid_show(struct device *dev, struct device_attribute *attr, char *buf)
@@ -841,27 +851,27 @@ alarms_show(struct device *dev, struct device_attribute *attr, char *buf)
 static DEVICE_ATTR_RO(alarms);
 
 static ssize_t
-show_alarm(struct device *dev, struct device_attribute *attr, char *buf)
+alarm_show(struct device *dev, struct device_attribute *attr, char *buf)
 {
 	struct w83627hf_data *data = w83627hf_update_device(dev);
 	int bitnr = to_sensor_dev_attr(attr)->index;
 	return sprintf(buf, "%u\n", (data->alarms >> bitnr) & 1);
 }
-static SENSOR_DEVICE_ATTR(in0_alarm, S_IRUGO, show_alarm, NULL, 0);
-static SENSOR_DEVICE_ATTR(in1_alarm, S_IRUGO, show_alarm, NULL, 1);
-static SENSOR_DEVICE_ATTR(in2_alarm, S_IRUGO, show_alarm, NULL, 2);
-static SENSOR_DEVICE_ATTR(in3_alarm, S_IRUGO, show_alarm, NULL, 3);
-static SENSOR_DEVICE_ATTR(in4_alarm, S_IRUGO, show_alarm, NULL, 8);
-static SENSOR_DEVICE_ATTR(in5_alarm, S_IRUGO, show_alarm, NULL, 9);
-static SENSOR_DEVICE_ATTR(in6_alarm, S_IRUGO, show_alarm, NULL, 10);
-static SENSOR_DEVICE_ATTR(in7_alarm, S_IRUGO, show_alarm, NULL, 16);
-static SENSOR_DEVICE_ATTR(in8_alarm, S_IRUGO, show_alarm, NULL, 17);
-static SENSOR_DEVICE_ATTR(fan1_alarm, S_IRUGO, show_alarm, NULL, 6);
-static SENSOR_DEVICE_ATTR(fan2_alarm, S_IRUGO, show_alarm, NULL, 7);
-static SENSOR_DEVICE_ATTR(fan3_alarm, S_IRUGO, show_alarm, NULL, 11);
-static SENSOR_DEVICE_ATTR(temp1_alarm, S_IRUGO, show_alarm, NULL, 4);
-static SENSOR_DEVICE_ATTR(temp2_alarm, S_IRUGO, show_alarm, NULL, 5);
-static SENSOR_DEVICE_ATTR(temp3_alarm, S_IRUGO, show_alarm, NULL, 13);
+static SENSOR_DEVICE_ATTR_RO(in0_alarm, alarm, 0);
+static SENSOR_DEVICE_ATTR_RO(in1_alarm, alarm, 1);
+static SENSOR_DEVICE_ATTR_RO(in2_alarm, alarm, 2);
+static SENSOR_DEVICE_ATTR_RO(in3_alarm, alarm, 3);
+static SENSOR_DEVICE_ATTR_RO(in4_alarm, alarm, 8);
+static SENSOR_DEVICE_ATTR_RO(in5_alarm, alarm, 9);
+static SENSOR_DEVICE_ATTR_RO(in6_alarm, alarm, 10);
+static SENSOR_DEVICE_ATTR_RO(in7_alarm, alarm, 16);
+static SENSOR_DEVICE_ATTR_RO(in8_alarm, alarm, 17);
+static SENSOR_DEVICE_ATTR_RO(fan1_alarm, alarm, 6);
+static SENSOR_DEVICE_ATTR_RO(fan2_alarm, alarm, 7);
+static SENSOR_DEVICE_ATTR_RO(fan3_alarm, alarm, 11);
+static SENSOR_DEVICE_ATTR_RO(temp1_alarm, alarm, 4);
+static SENSOR_DEVICE_ATTR_RO(temp2_alarm, alarm, 5);
+static SENSOR_DEVICE_ATTR_RO(temp3_alarm, alarm, 13);
 
 static ssize_t
 beep_mask_show(struct device *dev, struct device_attribute *attr, char *buf)
@@ -902,7 +912,7 @@ beep_mask_store(struct device *dev, struct device_attribute *attr,
 static DEVICE_ATTR_RW(beep_mask);
 
 static ssize_t
-show_beep(struct device *dev, struct device_attribute *attr, char *buf)
+beep_show(struct device *dev, struct device_attribute *attr, char *buf)
 {
 	struct w83627hf_data *data = w83627hf_update_device(dev);
 	int bitnr = to_sensor_dev_attr(attr)->index;
@@ -910,8 +920,8 @@ show_beep(struct device *dev, struct device_attribute *attr, char *buf)
 }
 
 static ssize_t
-store_beep(struct device *dev, struct device_attribute *attr,
-		const char *buf, size_t count)
+beep_store(struct device *dev, struct device_attribute *attr, const char *buf,
+	   size_t count)
 {
 	struct w83627hf_data *data = dev_get_drvdata(dev);
 	int bitnr = to_sensor_dev_attr(attr)->index;
@@ -959,41 +969,25 @@ store_beep(struct device *dev, struct device_attribute *attr,
 	return count;
 }
 
-static SENSOR_DEVICE_ATTR(in0_beep, S_IRUGO | S_IWUSR,
-			show_beep, store_beep, 0);
-static SENSOR_DEVICE_ATTR(in1_beep, S_IRUGO | S_IWUSR,
-			show_beep, store_beep, 1);
-static SENSOR_DEVICE_ATTR(in2_beep, S_IRUGO | S_IWUSR,
-			show_beep, store_beep, 2);
-static SENSOR_DEVICE_ATTR(in3_beep, S_IRUGO | S_IWUSR,
-			show_beep, store_beep, 3);
-static SENSOR_DEVICE_ATTR(in4_beep, S_IRUGO | S_IWUSR,
-			show_beep, store_beep, 8);
-static SENSOR_DEVICE_ATTR(in5_beep, S_IRUGO | S_IWUSR,
-			show_beep, store_beep, 9);
-static SENSOR_DEVICE_ATTR(in6_beep, S_IRUGO | S_IWUSR,
-			show_beep, store_beep, 10);
-static SENSOR_DEVICE_ATTR(in7_beep, S_IRUGO | S_IWUSR,
-			show_beep, store_beep, 16);
-static SENSOR_DEVICE_ATTR(in8_beep, S_IRUGO | S_IWUSR,
-			show_beep, store_beep, 17);
-static SENSOR_DEVICE_ATTR(fan1_beep, S_IRUGO | S_IWUSR,
-			show_beep, store_beep, 6);
-static SENSOR_DEVICE_ATTR(fan2_beep, S_IRUGO | S_IWUSR,
-			show_beep, store_beep, 7);
-static SENSOR_DEVICE_ATTR(fan3_beep, S_IRUGO | S_IWUSR,
-			show_beep, store_beep, 11);
-static SENSOR_DEVICE_ATTR(temp1_beep, S_IRUGO | S_IWUSR,
-			show_beep, store_beep, 4);
-static SENSOR_DEVICE_ATTR(temp2_beep, S_IRUGO | S_IWUSR,
-			show_beep, store_beep, 5);
-static SENSOR_DEVICE_ATTR(temp3_beep, S_IRUGO | S_IWUSR,
-			show_beep, store_beep, 13);
-static SENSOR_DEVICE_ATTR(beep_enable, S_IRUGO | S_IWUSR,
-			show_beep, store_beep, 15);
+static SENSOR_DEVICE_ATTR_RW(in0_beep, beep, 0);
+static SENSOR_DEVICE_ATTR_RW(in1_beep, beep, 1);
+static SENSOR_DEVICE_ATTR_RW(in2_beep, beep, 2);
+static SENSOR_DEVICE_ATTR_RW(in3_beep, beep, 3);
+static SENSOR_DEVICE_ATTR_RW(in4_beep, beep, 8);
+static SENSOR_DEVICE_ATTR_RW(in5_beep, beep, 9);
+static SENSOR_DEVICE_ATTR_RW(in6_beep, beep, 10);
+static SENSOR_DEVICE_ATTR_RW(in7_beep, beep, 16);
+static SENSOR_DEVICE_ATTR_RW(in8_beep, beep, 17);
+static SENSOR_DEVICE_ATTR_RW(fan1_beep, beep, 6);
+static SENSOR_DEVICE_ATTR_RW(fan2_beep, beep, 7);
+static SENSOR_DEVICE_ATTR_RW(fan3_beep, beep, 11);
+static SENSOR_DEVICE_ATTR_RW(temp1_beep, beep, 4);
+static SENSOR_DEVICE_ATTR_RW(temp2_beep, beep, 5);
+static SENSOR_DEVICE_ATTR_RW(temp3_beep, beep, 13);
+static SENSOR_DEVICE_ATTR_RW(beep_enable, beep, 15);
 
 static ssize_t
-show_fan_div(struct device *dev, struct device_attribute *devattr, char *buf)
+fan_div_show(struct device *dev, struct device_attribute *devattr, char *buf)
 {
 	int nr = to_sensor_dev_attr(devattr)->index;
 	struct w83627hf_data *data = w83627hf_update_device(dev);
@@ -1007,7 +1001,7 @@ show_fan_div(struct device *dev, struct device_attribute *devattr, char *buf)
  * because the divisor changed.
  */
 static ssize_t
-store_fan_div(struct device *dev, struct device_attribute *devattr,
+fan_div_store(struct device *dev, struct device_attribute *devattr,
 	      const char *buf, size_t count)
 {
 	int nr = to_sensor_dev_attr(devattr)->index;
@@ -1047,15 +1041,12 @@ store_fan_div(struct device *dev, struct device_attribute *devattr,
 	return count;
 }
 
-static SENSOR_DEVICE_ATTR(fan1_div, S_IRUGO|S_IWUSR,
-			  show_fan_div, store_fan_div, 0);
-static SENSOR_DEVICE_ATTR(fan2_div, S_IRUGO|S_IWUSR,
-			  show_fan_div, store_fan_div, 1);
-static SENSOR_DEVICE_ATTR(fan3_div, S_IRUGO|S_IWUSR,
-			  show_fan_div, store_fan_div, 2);
+static SENSOR_DEVICE_ATTR_RW(fan1_div, fan_div, 0);
+static SENSOR_DEVICE_ATTR_RW(fan2_div, fan_div, 1);
+static SENSOR_DEVICE_ATTR_RW(fan3_div, fan_div, 2);
 
 static ssize_t
-show_pwm(struct device *dev, struct device_attribute *devattr, char *buf)
+pwm_show(struct device *dev, struct device_attribute *devattr, char *buf)
 {
 	int nr = to_sensor_dev_attr(devattr)->index;
 	struct w83627hf_data *data = w83627hf_update_device(dev);
@@ -1063,7 +1054,7 @@ show_pwm(struct device *dev, struct device_attribute *devattr, char *buf)
 }
 
 static ssize_t
-store_pwm(struct device *dev, struct device_attribute *devattr,
+pwm_store(struct device *dev, struct device_attribute *devattr,
 	  const char *buf, size_t count)
 {
 	int nr = to_sensor_dev_attr(devattr)->index;
@@ -1096,12 +1087,13 @@ store_pwm(struct device *dev, struct device_attribute *devattr,
 	return count;
 }
 
-static SENSOR_DEVICE_ATTR(pwm1, S_IRUGO|S_IWUSR, show_pwm, store_pwm, 0);
-static SENSOR_DEVICE_ATTR(pwm2, S_IRUGO|S_IWUSR, show_pwm, store_pwm, 1);
-static SENSOR_DEVICE_ATTR(pwm3, S_IRUGO|S_IWUSR, show_pwm, store_pwm, 2);
+static SENSOR_DEVICE_ATTR_RW(pwm1, pwm, 0);
+static SENSOR_DEVICE_ATTR_RW(pwm2, pwm, 1);
+static SENSOR_DEVICE_ATTR_RW(pwm3, pwm, 2);
 
 static ssize_t
-show_pwm_enable(struct device *dev, struct device_attribute *devattr, char *buf)
+pwm_enable_show(struct device *dev, struct device_attribute *devattr,
+		char *buf)
 {
 	int nr = to_sensor_dev_attr(devattr)->index;
 	struct w83627hf_data *data = w83627hf_update_device(dev);
@@ -1109,8 +1101,8 @@ show_pwm_enable(struct device *dev, struct device_attribute *devattr, char *buf)
 }
 
 static ssize_t
-store_pwm_enable(struct device *dev, struct device_attribute *devattr,
-	  const char *buf, size_t count)
+pwm_enable_store(struct device *dev, struct device_attribute *devattr,
+		 const char *buf, size_t count)
 {
 	int nr = to_sensor_dev_attr(devattr)->index;
 	struct w83627hf_data *data = dev_get_drvdata(dev);
@@ -1134,15 +1126,12 @@ store_pwm_enable(struct device *dev, struct device_attribute *devattr,
 	return count;
 }
 
-static SENSOR_DEVICE_ATTR(pwm1_enable, S_IRUGO|S_IWUSR, show_pwm_enable,
-						  store_pwm_enable, 0);
-static SENSOR_DEVICE_ATTR(pwm2_enable, S_IRUGO|S_IWUSR, show_pwm_enable,
-						  store_pwm_enable, 1);
-static SENSOR_DEVICE_ATTR(pwm3_enable, S_IRUGO|S_IWUSR, show_pwm_enable,
-						  store_pwm_enable, 2);
+static SENSOR_DEVICE_ATTR_RW(pwm1_enable, pwm_enable, 0);
+static SENSOR_DEVICE_ATTR_RW(pwm2_enable, pwm_enable, 1);
+static SENSOR_DEVICE_ATTR_RW(pwm3_enable, pwm_enable, 2);
 
 static ssize_t
-show_pwm_freq(struct device *dev, struct device_attribute *devattr, char *buf)
+pwm_freq_show(struct device *dev, struct device_attribute *devattr, char *buf)
 {
 	int nr = to_sensor_dev_attr(devattr)->index;
 	struct w83627hf_data *data = w83627hf_update_device(dev);
@@ -1155,7 +1144,7 @@ show_pwm_freq(struct device *dev, struct device_attribute *devattr, char *buf)
 }
 
 static ssize_t
-store_pwm_freq(struct device *dev, struct device_attribute *devattr,
+pwm_freq_store(struct device *dev, struct device_attribute *devattr,
 	       const char *buf, size_t count)
 {
 	int nr = to_sensor_dev_attr(devattr)->index;
@@ -1186,15 +1175,12 @@ store_pwm_freq(struct device *dev, struct device_attribute *devattr,
 	return count;
 }
 
-static SENSOR_DEVICE_ATTR(pwm1_freq, S_IRUGO|S_IWUSR,
-			  show_pwm_freq, store_pwm_freq, 0);
-static SENSOR_DEVICE_ATTR(pwm2_freq, S_IRUGO|S_IWUSR,
-			  show_pwm_freq, store_pwm_freq, 1);
-static SENSOR_DEVICE_ATTR(pwm3_freq, S_IRUGO|S_IWUSR,
-			  show_pwm_freq, store_pwm_freq, 2);
+static SENSOR_DEVICE_ATTR_RW(pwm1_freq, pwm_freq, 0);
+static SENSOR_DEVICE_ATTR_RW(pwm2_freq, pwm_freq, 1);
+static SENSOR_DEVICE_ATTR_RW(pwm3_freq, pwm_freq, 2);
 
 static ssize_t
-show_temp_type(struct device *dev, struct device_attribute *devattr,
+temp_type_show(struct device *dev, struct device_attribute *devattr,
 	       char *buf)
 {
 	int nr = to_sensor_dev_attr(devattr)->index;
@@ -1203,7 +1189,7 @@ show_temp_type(struct device *dev, struct device_attribute *devattr,
 }
 
 static ssize_t
-store_temp_type(struct device *dev, struct device_attribute *devattr,
+temp_type_store(struct device *dev, struct device_attribute *devattr,
 		const char *buf, size_t count)
 {
 	int nr = to_sensor_dev_attr(devattr)->index;
@@ -1258,13 +1244,9 @@ store_temp_type(struct device *dev, struct device_attribute *devattr,
 	return count;
 }
 
-#define sysfs_temp_type(offset) \
-static SENSOR_DEVICE_ATTR(temp##offset##_type, S_IRUGO | S_IWUSR, \
-			  show_temp_type, store_temp_type, offset - 1);
-
-sysfs_temp_type(1);
-sysfs_temp_type(2);
-sysfs_temp_type(3);
+static SENSOR_DEVICE_ATTR_RW(temp1_type, temp_type, 0);
+static SENSOR_DEVICE_ATTR_RW(temp2_type, temp_type, 1);
+static SENSOR_DEVICE_ATTR_RW(temp3_type, temp_type, 2);
 
 static ssize_t
 name_show(struct device *dev, struct device_attribute *devattr, char *buf)
@@ -1278,7 +1260,7 @@ static DEVICE_ATTR_RO(name);
 static int __init w83627hf_find(int sioaddr, unsigned short *addr,
 				struct w83627hf_sio_data *sio_data)
 {
-	int err = -ENODEV;
+	int err;
 	u16 val;
 
 	static __initconst char *const names[] = {
@@ -1290,7 +1272,11 @@ static int __init w83627hf_find(int sioaddr, unsigned short *addr,
 	};
 
 	sio_data->sioaddr = sioaddr;
-	superio_enter(sio_data);
+	err = superio_enter(sio_data);
+	if (err)
+		return err;
+
+	err = -ENODEV;
 	val = force_id ? force_id : superio_inb(sio_data, DEVID);
 	switch (val) {
 	case W627_DEVID:
@@ -1595,7 +1581,6 @@ static int w83627hf_remove(struct platform_device *pdev)
 	return 0;
 }
 
-
 /* Registers 0x50-0x5f are banked */
 static inline void w83627hf_set_bank(struct w83627hf_data *data, u16 reg)
 {
@@ -1644,9 +1629,21 @@ static int w83627thf_read_gpio5(struct platform_device *pdev)
 	struct w83627hf_sio_data *sio_data = dev_get_platdata(&pdev->dev);
 	int res = 0xff, sel;
 
-	superio_enter(sio_data);
+	if (superio_enter(sio_data)) {
+		/*
+		 * Some other driver reserved the address space for itself.
+		 * We don't want to fail driver instantiation because of that,
+		 * so display a warning and keep going.
+		 */
+		dev_warn(&pdev->dev,
+			 "Can not read VID data: Failed to enable SuperIO access\n");
+		return res;
+	}
+
 	superio_select(sio_data, W83627HF_LD_GPIO5);
 
+	res = 0xff;
+
 	/* Make sure these GPIO pins are enabled */
 	if (!(superio_inb(sio_data, W83627THF_GPIO5_EN) & (1<<3))) {
 		dev_dbg(&pdev->dev, "GPIO5 disabled, no VID function\n");
@@ -1677,7 +1674,17 @@ static int w83687thf_read_vid(struct platform_device *pdev)
 	struct w83627hf_sio_data *sio_data = dev_get_platdata(&pdev->dev);
 	int res = 0xff;
 
-	superio_enter(sio_data);
+	if (superio_enter(sio_data)) {
+		/*
+		 * Some other driver reserved the address space for itself.
+		 * We don't want to fail driver instantiation because of that,
+		 * so display a warning and keep going.
+		 */
+		dev_warn(&pdev->dev,
+			 "Can not read VID data: Failed to enable SuperIO access\n");
+		return res;
+	}
+
 	superio_select(sio_data, W83627HF_LD_HWM);
 
 	/* Make sure these GPIO pins are enabled */
diff --git a/drivers/hwmon/w83773g.c b/drivers/hwmon/w83773g.c
index e858093ac806..d4105321e462 100644
--- a/drivers/hwmon/w83773g.c
+++ b/drivers/hwmon/w83773g.c
@@ -44,7 +44,7 @@ static const struct i2c_device_id w83773_id[] = {
 
 MODULE_DEVICE_TABLE(i2c, w83773_id);
 
-static const struct of_device_id w83773_of_match[] = {
+static const struct of_device_id __maybe_unused w83773_of_match[] = {
 	{
 		.compatible = "nuvoton,w83773g"
 	},
@@ -237,31 +237,13 @@ static umode_t w83773_is_visible(const void *data, enum hwmon_sensor_types type,
 	return 0;
 }
 
-static const u32 w83773_chip_config[] = {
-	HWMON_C_REGISTER_TZ | HWMON_C_UPDATE_INTERVAL,
-	0
-};
-
-static const struct hwmon_channel_info w83773_chip = {
-	.type = hwmon_chip,
-	.config = w83773_chip_config,
-};
-
-static const u32 w83773_temp_config[] = {
-	HWMON_T_INPUT,
-	HWMON_T_INPUT | HWMON_T_FAULT | HWMON_T_OFFSET,
-	HWMON_T_INPUT | HWMON_T_FAULT | HWMON_T_OFFSET,
-	0
-};
-
-static const struct hwmon_channel_info w83773_temp = {
-	.type = hwmon_temp,
-	.config = w83773_temp_config,
-};
-
 static const struct hwmon_channel_info *w83773_info[] = {
-	&w83773_chip,
-	&w83773_temp,
+	HWMON_CHANNEL_INFO(chip,
+			   HWMON_C_REGISTER_TZ | HWMON_C_UPDATE_INTERVAL),
+	HWMON_CHANNEL_INFO(temp,
+			   HWMON_T_INPUT,
+			   HWMON_T_INPUT | HWMON_T_FAULT | HWMON_T_OFFSET,
+			   HWMON_T_INPUT | HWMON_T_FAULT | HWMON_T_OFFSET),
 	NULL
 };
 
diff --git a/drivers/i2c/busses/Kconfig b/drivers/i2c/busses/Kconfig
index f2c681971201..f8979abb9a19 100644
--- a/drivers/i2c/busses/Kconfig
+++ b/drivers/i2c/busses/Kconfig
@@ -131,6 +131,7 @@ config I2C_I801
 	    Cannon Lake (PCH)
 	    Cedar Fork (PCH)
 	    Ice Lake (PCH)
+	    Comet Lake (PCH)
 
 	  This driver can also be built as a module.  If so, the module
 	  will be called i2c-i801.
diff --git a/drivers/i2c/busses/i2c-designware-master.c b/drivers/i2c/busses/i2c-designware-master.c
index bb8e3f149979..d464799e40a3 100644
--- a/drivers/i2c/busses/i2c-designware-master.c
+++ b/drivers/i2c/busses/i2c-designware-master.c
@@ -426,8 +426,7 @@ i2c_dw_xfer(struct i2c_adapter *adap, struct i2c_msg msgs[], int num)
 
 	pm_runtime_get_sync(dev->dev);
 
-	if (dev->suspended) {
-		dev_err(dev->dev, "Error %s call while suspended\n", __func__);
+	if (dev_WARN_ONCE(dev->dev, dev->suspended, "Transfer while suspended\n")) {
 		ret = -ESHUTDOWN;
 		goto done_nolock;
 	}
diff --git a/drivers/i2c/busses/i2c-i801.c b/drivers/i2c/busses/i2c-i801.c
index c91e145ef5a5..679c6c41f64b 100644
--- a/drivers/i2c/busses/i2c-i801.c
+++ b/drivers/i2c/busses/i2c-i801.c
@@ -71,6 +71,7 @@
  * Cannon Lake-LP (PCH)		0x9da3	32	hard	yes	yes	yes
  * Cedar Fork (PCH)		0x18df	32	hard	yes	yes	yes
  * Ice Lake-LP (PCH)		0x34a3	32	hard	yes	yes	yes
+ * Comet Lake (PCH)		0x02a3	32	hard	yes	yes	yes
  *
  * Features supported by this driver:
  * Software PEC				no
@@ -240,6 +241,7 @@
 #define PCI_DEVICE_ID_INTEL_LEWISBURG_SSKU_SMBUS	0xa223
 #define PCI_DEVICE_ID_INTEL_KABYLAKE_PCH_H_SMBUS	0xa2a3
 #define PCI_DEVICE_ID_INTEL_CANNONLAKE_H_SMBUS		0xa323
+#define PCI_DEVICE_ID_INTEL_COMETLAKE_SMBUS		0x02a3
 
 struct i801_mux_config {
 	char *gpio_chip;
@@ -1038,6 +1040,7 @@ static const struct pci_device_id i801_ids[] = {
 	{ PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_CANNONLAKE_H_SMBUS) },
 	{ PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_CANNONLAKE_LP_SMBUS) },
 	{ PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_ICELAKE_LP_SMBUS) },
+	{ PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_COMETLAKE_SMBUS) },
 	{ 0, }
 };
 
@@ -1534,6 +1537,7 @@ static int i801_probe(struct pci_dev *dev, const struct pci_device_id *id)
 	case PCI_DEVICE_ID_INTEL_DNV_SMBUS:
 	case PCI_DEVICE_ID_INTEL_KABYLAKE_PCH_H_SMBUS:
 	case PCI_DEVICE_ID_INTEL_ICELAKE_LP_SMBUS:
+	case PCI_DEVICE_ID_INTEL_COMETLAKE_SMBUS:
 		priv->features |= FEATURE_I2C_BLOCK_READ;
 		priv->features |= FEATURE_IRQ;
 		priv->features |= FEATURE_SMBUS_PEC;
diff --git a/drivers/i2c/busses/i2c-imx.c b/drivers/i2c/busses/i2c-imx.c
index 42fed40198a0..fd70b110e8f4 100644
--- a/drivers/i2c/busses/i2c-imx.c
+++ b/drivers/i2c/busses/i2c-imx.c
@@ -515,9 +515,9 @@ static int i2c_imx_clk_notifier_call(struct notifier_block *nb,
 				     unsigned long action, void *data)
 {
 	struct clk_notifier_data *ndata = data;
-	struct imx_i2c_struct *i2c_imx = container_of(&ndata->clk,
+	struct imx_i2c_struct *i2c_imx = container_of(nb,
 						      struct imx_i2c_struct,
-						      clk);
+						      clk_change_nb);
 
 	if (action & POST_RATE_CHANGE)
 		i2c_imx_set_clk(i2c_imx, ndata->new_rate);
@@ -1169,11 +1169,13 @@ static int i2c_imx_probe(struct platform_device *pdev)
 	/* Init DMA config if supported */
 	ret = i2c_imx_dma_request(i2c_imx, phy_addr);
 	if (ret < 0)
-		goto clk_notifier_unregister;
+		goto del_adapter;
 
 	dev_info(&i2c_imx->adapter.dev, "IMX I2C adapter registered\n");
 	return 0;   /* Return OK */
 
+del_adapter:
+	i2c_del_adapter(&i2c_imx->adapter);
 clk_notifier_unregister:
 	clk_notifier_unregister(i2c_imx->clk, &i2c_imx->clk_change_nb);
 rpm_disable:
diff --git a/drivers/i2c/busses/i2c-synquacer.c b/drivers/i2c/busses/i2c-synquacer.c
index d18b0941b71a..f14d4b3fab44 100644
--- a/drivers/i2c/busses/i2c-synquacer.c
+++ b/drivers/i2c/busses/i2c-synquacer.c
@@ -597,6 +597,8 @@ static int synquacer_i2c_probe(struct platform_device *pdev)
 	i2c->adapter = synquacer_i2c_ops;
 	i2c_set_adapdata(&i2c->adapter, i2c);
 	i2c->adapter.dev.parent = &pdev->dev;
+	i2c->adapter.dev.of_node = pdev->dev.of_node;
+	ACPI_COMPANION_SET(&i2c->adapter.dev, ACPI_COMPANION(&pdev->dev));
 	i2c->adapter.nr = pdev->id;
 	init_completion(&i2c->completion);
 
diff --git a/drivers/i2c/i2c-core-base.c b/drivers/i2c/i2c-core-base.c
index 38af18645133..688aa3b5f3ac 100644
--- a/drivers/i2c/i2c-core-base.c
+++ b/drivers/i2c/i2c-core-base.c
@@ -185,7 +185,7 @@ static int i2c_generic_bus_free(struct i2c_adapter *adap)
 int i2c_generic_scl_recovery(struct i2c_adapter *adap)
 {
 	struct i2c_bus_recovery_info *bri = adap->bus_recovery_info;
-	int i = 0, scl = 1, ret;
+	int i = 0, scl = 1, ret = 0;
 
 	if (bri->prepare_recovery)
 		bri->prepare_recovery(adap);
@@ -327,6 +327,8 @@ static int i2c_device_probe(struct device *dev)
 
 		if (client->flags & I2C_CLIENT_HOST_NOTIFY) {
 			dev_dbg(dev, "Using Host Notify IRQ\n");
+			/* Keep adapter active when Host Notify is required */
+			pm_runtime_get_sync(&client->adapter->dev);
 			irq = i2c_smbus_host_notify_to_irq(client);
 		} else if (dev->of_node) {
 			irq = of_irq_get_byname(dev->of_node, "irq");
@@ -431,6 +433,8 @@ static int i2c_device_remove(struct device *dev)
 	device_init_wakeup(&client->dev, false);
 
 	client->irq = client->init_irq;
+	if (client->flags & I2C_CLIENT_HOST_NOTIFY)
+		pm_runtime_put(&client->adapter->dev);
 
 	return status;
 }
diff --git a/drivers/i3c/master.c b/drivers/i3c/master.c
index 2dc628d4f1ae..1412abcff010 100644
--- a/drivers/i3c/master.c
+++ b/drivers/i3c/master.c
@@ -1980,7 +1980,6 @@ of_i3c_master_add_i3c_boardinfo(struct i3c_master_controller *master,
 {
 	struct i3c_dev_boardinfo *boardinfo;
 	struct device *dev = &master->dev;
-	struct i3c_device_info info = { };
 	enum i3c_addr_slot_status addrstatus;
 	u32 init_dyn_addr = 0;
 
@@ -2012,8 +2011,8 @@ of_i3c_master_add_i3c_boardinfo(struct i3c_master_controller *master,
 
 	boardinfo->pid = ((u64)reg[1] << 32) | reg[2];
 
-	if ((info.pid & GENMASK_ULL(63, 48)) ||
-	    I3C_PID_RND_LOWER_32BITS(info.pid))
+	if ((boardinfo->pid & GENMASK_ULL(63, 48)) ||
+	    I3C_PID_RND_LOWER_32BITS(boardinfo->pid))
 		return -EINVAL;
 
 	boardinfo->init_dyn_addr = init_dyn_addr;
diff --git a/drivers/i3c/master/dw-i3c-master.c b/drivers/i3c/master/dw-i3c-master.c
index 59279224e07f..10c26ffaa8ef 100644
--- a/drivers/i3c/master/dw-i3c-master.c
+++ b/drivers/i3c/master/dw-i3c-master.c
@@ -300,7 +300,7 @@ to_dw_i3c_master(struct i3c_master_controller *master)
 
 static void dw_i3c_master_disable(struct dw_i3c_master *master)
 {
-	writel(readl(master->regs + DEVICE_CTRL) & DEV_CTRL_ENABLE,
+	writel(readl(master->regs + DEVICE_CTRL) & ~DEV_CTRL_ENABLE,
 	       master->regs + DEVICE_CTRL);
 }
 
diff --git a/drivers/ide/tx4939ide.c b/drivers/ide/tx4939ide.c
index 67d4a7d4acc8..88d132edc4e3 100644
--- a/drivers/ide/tx4939ide.c
+++ b/drivers/ide/tx4939ide.c
@@ -156,7 +156,6 @@ static u16 tx4939ide_check_error_ints(ide_hwif_t *hwif)
 		u16 sysctl = tx4939ide_readw(base, TX4939IDE_Sys_Ctl);
 
 		tx4939ide_writew(sysctl | 0x4000, base, TX4939IDE_Sys_Ctl);
-		mmiowb();
 		/* wait 12GBUSCLK (typ. 60ns @ GBUS200MHz, max 270ns) */
 		ndelay(270);
 		tx4939ide_writew(sysctl, base, TX4939IDE_Sys_Ctl);
@@ -396,7 +395,6 @@ static void tx4939ide_init_hwif(ide_hwif_t *hwif)
 
 	/* Soft Reset */
 	tx4939ide_writew(0x8000, base, TX4939IDE_Sys_Ctl);
-	mmiowb();
 	/* at least 20 GBUSCLK (typ. 100ns @ GBUS200MHz, max 450ns) */
 	ndelay(450);
 	tx4939ide_writew(0x0000, base, TX4939IDE_Sys_Ctl);
diff --git a/drivers/iio/accel/kxcjk-1013.c b/drivers/iio/accel/kxcjk-1013.c
index 7096e577b23f..50f3ff386bea 100644
--- a/drivers/iio/accel/kxcjk-1013.c
+++ b/drivers/iio/accel/kxcjk-1013.c
@@ -1437,6 +1437,8 @@ static int kxcjk1013_resume(struct device *dev)
 
 	mutex_lock(&data->mutex);
 	ret = kxcjk1013_set_mode(data, OPERATION);
+	if (ret == 0)
+		ret = kxcjk1013_set_range(data, data->range);
 	mutex_unlock(&data->mutex);
 
 	return ret;
diff --git a/drivers/iio/adc/ad_sigma_delta.c b/drivers/iio/adc/ad_sigma_delta.c
index ff5f2da2e1b1..54d9978b2740 100644
--- a/drivers/iio/adc/ad_sigma_delta.c
+++ b/drivers/iio/adc/ad_sigma_delta.c
@@ -121,6 +121,7 @@ static int ad_sd_read_reg_raw(struct ad_sigma_delta *sigma_delta,
 	if (sigma_delta->info->has_registers) {
 		data[0] = reg << sigma_delta->info->addr_shift;
 		data[0] |= sigma_delta->info->read_mask;
+		data[0] |= sigma_delta->comm;
 		spi_message_add_tail(&t[0], &m);
 	}
 	spi_message_add_tail(&t[1], &m);
diff --git a/drivers/iio/adc/at91_adc.c b/drivers/iio/adc/at91_adc.c
index 75d2f73582a3..596841a3c4db 100644
--- a/drivers/iio/adc/at91_adc.c
+++ b/drivers/iio/adc/at91_adc.c
@@ -704,23 +704,29 @@ static int at91_adc_read_raw(struct iio_dev *idev,
 		ret = wait_event_interruptible_timeout(st->wq_data_avail,
 						       st->done,
 						       msecs_to_jiffies(1000));
-		if (ret == 0)
-			ret = -ETIMEDOUT;
-		if (ret < 0) {
-			mutex_unlock(&st->lock);
-			return ret;
-		}
-
-		*val = st->last_value;
 
+		/* Disable interrupts, regardless if adc conversion was
+		 * successful or not
+		 */
 		at91_adc_writel(st, AT91_ADC_CHDR,
 				AT91_ADC_CH(chan->channel));
 		at91_adc_writel(st, AT91_ADC_IDR, BIT(chan->channel));
 
-		st->last_value = 0;
-		st->done = false;
+		if (ret > 0) {
+			/* a valid conversion took place */
+			*val = st->last_value;
+			st->last_value = 0;
+			st->done = false;
+			ret = IIO_VAL_INT;
+		} else if (ret == 0) {
+			/* conversion timeout */
+			dev_err(&idev->dev, "ADC Channel %d timeout.\n",
+				chan->channel);
+			ret = -ETIMEDOUT;
+		}
+
 		mutex_unlock(&st->lock);
-		return IIO_VAL_INT;
+		return ret;
 
 	case IIO_CHAN_INFO_SCALE:
 		*val = st->vref_mv;
diff --git a/drivers/iio/adc/xilinx-xadc-core.c b/drivers/iio/adc/xilinx-xadc-core.c
index b13c61539d46..6401ca7a9a20 100644
--- a/drivers/iio/adc/xilinx-xadc-core.c
+++ b/drivers/iio/adc/xilinx-xadc-core.c
@@ -1292,6 +1292,7 @@ static int xadc_probe(struct platform_device *pdev)
 
 err_free_irq:
 	free_irq(xadc->irq, indio_dev);
+	cancel_delayed_work_sync(&xadc->zynq_unmask_work);
 err_clk_disable_unprepare:
 	clk_disable_unprepare(xadc->clk);
 err_free_samplerate_trigger:
@@ -1321,8 +1322,8 @@ static int xadc_remove(struct platform_device *pdev)
 		iio_triggered_buffer_cleanup(indio_dev);
 	}
 	free_irq(xadc->irq, indio_dev);
+	cancel_delayed_work_sync(&xadc->zynq_unmask_work);
 	clk_disable_unprepare(xadc->clk);
-	cancel_delayed_work(&xadc->zynq_unmask_work);
 	kfree(xadc->data);
 	kfree(indio_dev->channels);
 
diff --git a/drivers/iio/chemical/Kconfig b/drivers/iio/chemical/Kconfig
index d5d146e9e372..92c684d2b67e 100644
--- a/drivers/iio/chemical/Kconfig
+++ b/drivers/iio/chemical/Kconfig
@@ -64,6 +64,7 @@ config IAQCORE
 config PMS7003
 	tristate "Plantower PMS7003 particulate matter sensor"
 	depends on SERIAL_DEV_BUS
+	select IIO_TRIGGERED_BUFFER
 	help
 	  Say Y here to build support for the Plantower PMS7003 particulate
 	  matter sensor.
@@ -71,6 +72,19 @@ config PMS7003
 	  To compile this driver as a module, choose M here: the module will
 	  be called pms7003.
 
+config SENSIRION_SGP30
+	tristate "Sensirion SGPxx gas sensors"
+	depends on I2C
+	select CRC8
+	help
+	  Say Y here to build I2C interface support for the following
+	  Sensirion SGP gas sensors:
+	    * SGP30 gas sensor
+	    * SGPC3 low power gas sensor
+
+	  To compile this driver as module, choose M here: the
+	  module will be called sgp30.
+
 config SPS30
 	tristate "SPS30 particulate matter sensor"
 	depends on I2C
diff --git a/drivers/iio/chemical/bme680.h b/drivers/iio/chemical/bme680.h
index 0ae89b87e2d6..4edc5d21cb9f 100644
--- a/drivers/iio/chemical/bme680.h
+++ b/drivers/iio/chemical/bme680.h
@@ -2,11 +2,9 @@
 #ifndef BME680_H_
 #define BME680_H_
 
-#define BME680_REG_CHIP_I2C_ID			0xD0
-#define BME680_REG_CHIP_SPI_ID			0x50
+#define BME680_REG_CHIP_ID			0xD0
 #define   BME680_CHIP_ID_VAL			0x61
-#define BME680_REG_SOFT_RESET_I2C		0xE0
-#define BME680_REG_SOFT_RESET_SPI		0x60
+#define BME680_REG_SOFT_RESET			0xE0
 #define   BME680_CMD_SOFTRESET			0xB6
 #define BME680_REG_STATUS			0x73
 #define   BME680_SPI_MEM_PAGE_BIT		BIT(4)
diff --git a/drivers/iio/chemical/bme680_core.c b/drivers/iio/chemical/bme680_core.c
index 70c1fe4366f4..ccde4c65ff93 100644
--- a/drivers/iio/chemical/bme680_core.c
+++ b/drivers/iio/chemical/bme680_core.c
@@ -63,9 +63,23 @@ struct bme680_data {
 	s32 t_fine;
 };
 
+static const struct regmap_range bme680_volatile_ranges[] = {
+	regmap_reg_range(BME680_REG_MEAS_STAT_0, BME680_REG_GAS_R_LSB),
+	regmap_reg_range(BME680_REG_STATUS, BME680_REG_STATUS),
+	regmap_reg_range(BME680_T2_LSB_REG, BME680_GH3_REG),
+};
+
+static const struct regmap_access_table bme680_volatile_table = {
+	.yes_ranges	= bme680_volatile_ranges,
+	.n_yes_ranges	= ARRAY_SIZE(bme680_volatile_ranges),
+};
+
 const struct regmap_config bme680_regmap_config = {
 	.reg_bits = 8,
 	.val_bits = 8,
+	.max_register = 0xef,
+	.volatile_table = &bme680_volatile_table,
+	.cache_type = REGCACHE_RBTREE,
 };
 EXPORT_SYMBOL(bme680_regmap_config);
 
@@ -316,6 +330,10 @@ static s16 bme680_compensate_temp(struct bme680_data *data,
 	s64 var1, var2, var3;
 	s16 calc_temp;
 
+	/* If the calibration is invalid, attempt to reload it */
+	if (!calib->par_t2)
+		bme680_read_calib(data, calib);
+
 	var1 = (adc_temp >> 3) - (calib->par_t1 << 1);
 	var2 = (var1 * calib->par_t2) >> 11;
 	var3 = ((var1 >> 1) * (var1 >> 1)) >> 12;
@@ -583,8 +601,7 @@ static int bme680_gas_config(struct bme680_data *data)
 	return ret;
 }
 
-static int bme680_read_temp(struct bme680_data *data,
-			    int *val, int *val2)
+static int bme680_read_temp(struct bme680_data *data, int *val)
 {
 	struct device *dev = regmap_get_device(data->regmap);
 	int ret;
@@ -617,10 +634,9 @@ static int bme680_read_temp(struct bme680_data *data,
 	 * compensate_press/compensate_humid to get compensated
 	 * pressure/humidity readings.
 	 */
-	if (val && val2) {
-		*val = comp_temp;
-		*val2 = 100;
-		return IIO_VAL_FRACTIONAL;
+	if (val) {
+		*val = comp_temp * 10; /* Centidegrees to millidegrees */
+		return IIO_VAL_INT;
 	}
 
 	return ret;
@@ -635,7 +651,7 @@ static int bme680_read_press(struct bme680_data *data,
 	s32 adc_press;
 
 	/* Read and compensate temperature to get a reading of t_fine */
-	ret = bme680_read_temp(data, NULL, NULL);
+	ret = bme680_read_temp(data, NULL);
 	if (ret < 0)
 		return ret;
 
@@ -668,7 +684,7 @@ static int bme680_read_humid(struct bme680_data *data,
 	u32 comp_humidity;
 
 	/* Read and compensate temperature to get a reading of t_fine */
-	ret = bme680_read_temp(data, NULL, NULL);
+	ret = bme680_read_temp(data, NULL);
 	if (ret < 0)
 		return ret;
 
@@ -761,7 +777,7 @@ static int bme680_read_raw(struct iio_dev *indio_dev,
 	case IIO_CHAN_INFO_PROCESSED:
 		switch (chan->type) {
 		case IIO_TEMP:
-			return bme680_read_temp(data, val, val2);
+			return bme680_read_temp(data, val);
 		case IIO_PRESSURE:
 			return bme680_read_press(data, val, val2);
 		case IIO_HUMIDITYRELATIVE:
@@ -867,8 +883,28 @@ int bme680_core_probe(struct device *dev, struct regmap *regmap,
 {
 	struct iio_dev *indio_dev;
 	struct bme680_data *data;
+	unsigned int val;
 	int ret;
 
+	ret = regmap_write(regmap, BME680_REG_SOFT_RESET,
+			   BME680_CMD_SOFTRESET);
+	if (ret < 0) {
+		dev_err(dev, "Failed to reset chip\n");
+		return ret;
+	}
+
+	ret = regmap_read(regmap, BME680_REG_CHIP_ID, &val);
+	if (ret < 0) {
+		dev_err(dev, "Error reading chip ID\n");
+		return ret;
+	}
+
+	if (val != BME680_CHIP_ID_VAL) {
+		dev_err(dev, "Wrong chip ID, got %x expected %x\n",
+				val, BME680_CHIP_ID_VAL);
+		return -ENODEV;
+	}
+
 	indio_dev = devm_iio_device_alloc(dev, sizeof(*data));
 	if (!indio_dev)
 		return -ENOMEM;
diff --git a/drivers/iio/chemical/bme680_i2c.c b/drivers/iio/chemical/bme680_i2c.c
index b2f805b6b36a..de9c9e3d23ea 100644
--- a/drivers/iio/chemical/bme680_i2c.c
+++ b/drivers/iio/chemical/bme680_i2c.c
@@ -23,8 +23,6 @@ static int bme680_i2c_probe(struct i2c_client *client,
 {
 	struct regmap *regmap;
 	const char *name = NULL;
-	unsigned int val;
-	int ret;
 
 	regmap = devm_regmap_init_i2c(client, &bme680_regmap_config);
 	if (IS_ERR(regmap)) {
@@ -33,25 +31,6 @@ static int bme680_i2c_probe(struct i2c_client *client,
 		return PTR_ERR(regmap);
 	}
 
-	ret = regmap_write(regmap, BME680_REG_SOFT_RESET_I2C,
-			   BME680_CMD_SOFTRESET);
-	if (ret < 0) {
-		dev_err(&client->dev, "Failed to reset chip\n");
-		return ret;
-	}
-
-	ret = regmap_read(regmap, BME680_REG_CHIP_I2C_ID, &val);
-	if (ret < 0) {
-		dev_err(&client->dev, "Error reading I2C chip ID\n");
-		return ret;
-	}
-
-	if (val != BME680_CHIP_ID_VAL) {
-		dev_err(&client->dev, "Wrong chip ID, got %x expected %x\n",
-				val, BME680_CHIP_ID_VAL);
-		return -ENODEV;
-	}
-
 	if (id)
 		name = id->name;
 
diff --git a/drivers/iio/chemical/bme680_spi.c b/drivers/iio/chemical/bme680_spi.c
index d0b7bdd3f066..3b838068a7e4 100644
--- a/drivers/iio/chemical/bme680_spi.c
+++ b/drivers/iio/chemical/bme680_spi.c
@@ -12,28 +12,93 @@
 
 #include "bme680.h"
 
+struct bme680_spi_bus_context {
+	struct spi_device *spi;
+	u8 current_page;
+};
+
+/*
+ * In SPI mode there are only 7 address bits, a "page" register determines
+ * which part of the 8-bit range is active. This function looks at the address
+ * and writes the page selection bit if needed
+ */
+static int bme680_regmap_spi_select_page(
+	struct bme680_spi_bus_context *ctx, u8 reg)
+{
+	struct spi_device *spi = ctx->spi;
+	int ret;
+	u8 buf[2];
+	u8 page = (reg & 0x80) ? 0 : 1; /* Page "1" is low range */
+
+	if (page == ctx->current_page)
+		return 0;
+
+	/*
+	 * Data sheet claims we're only allowed to change bit 4, so we must do
+	 * a read-modify-write on each and every page select
+	 */
+	buf[0] = BME680_REG_STATUS;
+	ret = spi_write_then_read(spi, buf, 1, buf + 1, 1);
+	if (ret < 0) {
+		dev_err(&spi->dev, "failed to set page %u\n", page);
+		return ret;
+	}
+
+	buf[0] = BME680_REG_STATUS;
+	if (page)
+		buf[1] |= BME680_SPI_MEM_PAGE_BIT;
+	else
+		buf[1] &= ~BME680_SPI_MEM_PAGE_BIT;
+
+	ret = spi_write(spi, buf, 2);
+	if (ret < 0) {
+		dev_err(&spi->dev, "failed to set page %u\n", page);
+		return ret;
+	}
+
+	ctx->current_page = page;
+
+	return 0;
+}
+
 static int bme680_regmap_spi_write(void *context, const void *data,
 				   size_t count)
 {
-	struct spi_device *spi = context;
+	struct bme680_spi_bus_context *ctx = context;
+	struct spi_device *spi = ctx->spi;
+	int ret;
 	u8 buf[2];
 
 	memcpy(buf, data, 2);
+
+	ret = bme680_regmap_spi_select_page(ctx, buf[0]);
+	if (ret)
+		return ret;
+
 	/*
 	 * The SPI register address (= full register address without bit 7)
 	 * and the write command (bit7 = RW = '0')
 	 */
 	buf[0] &= ~0x80;
 
-	return spi_write_then_read(spi, buf, 2, NULL, 0);
+	return spi_write(spi, buf, 2);
 }
 
 static int bme680_regmap_spi_read(void *context, const void *reg,
 				  size_t reg_size, void *val, size_t val_size)
 {
-	struct spi_device *spi = context;
+	struct bme680_spi_bus_context *ctx = context;
+	struct spi_device *spi = ctx->spi;
+	int ret;
+	u8 addr = *(const u8 *)reg;
+
+	ret = bme680_regmap_spi_select_page(ctx, addr);
+	if (ret)
+		return ret;
 
-	return spi_write_then_read(spi, reg, reg_size, val, val_size);
+	addr |= 0x80; /* bit7 = RW = '1' */
+
+	return spi_write_then_read(spi, &addr, 1, val, val_size);
 }
 
 static struct regmap_bus bme680_regmap_bus = {
@@ -46,8 +111,8 @@ static struct regmap_bus bme680_regmap_bus = {
 static int bme680_spi_probe(struct spi_device *spi)
 {
 	const struct spi_device_id *id = spi_get_device_id(spi);
+	struct bme680_spi_bus_context *bus_context;
 	struct regmap *regmap;
-	unsigned int val;
 	int ret;
 
 	spi->bits_per_word = 8;
@@ -57,45 +122,21 @@ static int bme680_spi_probe(struct spi_device *spi)
 		return ret;
 	}
 
+	bus_context = devm_kzalloc(&spi->dev, sizeof(*bus_context), GFP_KERNEL);
+	if (!bus_context)
+		return -ENOMEM;
+
+	bus_context->spi = spi;
+	bus_context->current_page = 0xff; /* Undefined on warm boot */
+
 	regmap = devm_regmap_init(&spi->dev, &bme680_regmap_bus,
-				  &spi->dev, &bme680_regmap_config);
+				  bus_context, &bme680_regmap_config);
 	if (IS_ERR(regmap)) {
 		dev_err(&spi->dev, "Failed to register spi regmap %d\n",
 				(int)PTR_ERR(regmap));
 		return PTR_ERR(regmap);
 	}
 
-	ret = regmap_write(regmap, BME680_REG_SOFT_RESET_SPI,
-			   BME680_CMD_SOFTRESET);
-	if (ret < 0) {
-		dev_err(&spi->dev, "Failed to reset chip\n");
-		return ret;
-	}
-
-	/* after power-on reset, Page 0(0x80-0xFF) of spi_mem_page is active */
-	ret = regmap_read(regmap, BME680_REG_CHIP_SPI_ID, &val);
-	if (ret < 0) {
-		dev_err(&spi->dev, "Error reading SPI chip ID\n");
-		return ret;
-	}
-
-	if (val != BME680_CHIP_ID_VAL) {
-		dev_err(&spi->dev, "Wrong chip ID, got %x expected %x\n",
-				val, BME680_CHIP_ID_VAL);
-		return -ENODEV;
-	}
-	/*
-	 * select Page 1 of spi_mem_page to enable access to
-	 * to registers from address 0x00 to 0x7F.
-	 */
-	ret = regmap_write_bits(regmap, BME680_REG_STATUS,
-				BME680_SPI_MEM_PAGE_BIT,
-				BME680_SPI_MEM_PAGE_1_VAL);
-	if (ret < 0) {
-		dev_err(&spi->dev, "failed to set page 1 of spi_mem_page\n");
-		return ret;
-	}
-
 	return bme680_core_probe(&spi->dev, regmap, id->name);
 }
 
diff --git a/drivers/iio/common/cros_ec_sensors/cros_ec_sensors.c b/drivers/iio/common/cros_ec_sensors/cros_ec_sensors.c
index 89cb0066a6e0..8d76afb87d87 100644
--- a/drivers/iio/common/cros_ec_sensors/cros_ec_sensors.c
+++ b/drivers/iio/common/cros_ec_sensors/cros_ec_sensors.c
@@ -103,9 +103,10 @@ static int cros_ec_sensors_read(struct iio_dev *indio_dev,
 			 * Do not use IIO_DEGREE_TO_RAD to avoid precision
 			 * loss. Round to the nearest integer.
 			 */
-			*val = div_s64(val64 * 314159 + 9000000ULL, 1000);
-			*val2 = 18000 << (CROS_EC_SENSOR_BITS - 1);
-			ret = IIO_VAL_FRACTIONAL;
+			*val = 0;
+			*val2 = div_s64(val64 * 3141592653ULL,
+					180 << (CROS_EC_SENSOR_BITS - 1));
+			ret = IIO_VAL_INT_PLUS_NANO;
 			break;
 		case MOTIONSENSE_TYPE_MAG:
 			/*
diff --git a/drivers/iio/dac/mcp4725.c b/drivers/iio/dac/mcp4725.c
index 6d71fd905e29..c701a45469f6 100644
--- a/drivers/iio/dac/mcp4725.c
+++ b/drivers/iio/dac/mcp4725.c
@@ -92,6 +92,7 @@ static ssize_t mcp4725_store_eeprom(struct device *dev,
 
 	inoutbuf[0] = 0x60; /* write EEPROM */
 	inoutbuf[0] |= data->ref_mode << 3;
+	inoutbuf[0] |= data->powerdown ? ((data->powerdown_mode + 1) << 1) : 0;
 	inoutbuf[1] = data->dac_value >> 4;
 	inoutbuf[2] = (data->dac_value & 0xf) << 4;
 
diff --git a/drivers/iio/gyro/bmg160_core.c b/drivers/iio/gyro/bmg160_core.c
index 63ca31628a93..92c07ab826eb 100644
--- a/drivers/iio/gyro/bmg160_core.c
+++ b/drivers/iio/gyro/bmg160_core.c
@@ -582,11 +582,10 @@ static int bmg160_read_raw(struct iio_dev *indio_dev,
 	case IIO_CHAN_INFO_LOW_PASS_FILTER_3DB_FREQUENCY:
 		return bmg160_get_filter(data, val);
 	case IIO_CHAN_INFO_SCALE:
-		*val = 0;
 		switch (chan->type) {
 		case IIO_TEMP:
-			*val2 = 500000;
-			return IIO_VAL_INT_PLUS_MICRO;
+			*val = 500;
+			return IIO_VAL_INT;
 		case IIO_ANGL_VEL:
 		{
 			int i;
@@ -594,6 +593,7 @@ static int bmg160_read_raw(struct iio_dev *indio_dev,
 			for (i = 0; i < ARRAY_SIZE(bmg160_scale_table); ++i) {
 				if (bmg160_scale_table[i].dps_range ==
 							data->dps_range) {
+					*val = 0;
 					*val2 = bmg160_scale_table[i].scale;
 					return IIO_VAL_INT_PLUS_MICRO;
 				}
diff --git a/drivers/iio/gyro/mpu3050-core.c b/drivers/iio/gyro/mpu3050-core.c
index 77fac81a3adc..5ddebede31a6 100644
--- a/drivers/iio/gyro/mpu3050-core.c
+++ b/drivers/iio/gyro/mpu3050-core.c
@@ -29,7 +29,8 @@
 
 #include "mpu3050.h"
 
-#define MPU3050_CHIP_ID		0x69
+#define MPU3050_CHIP_ID		0x68
+#define MPU3050_CHIP_ID_MASK	0x7E
 
 /*
  * Register map: anything suffixed *_H is a big-endian high byte and always
@@ -1176,8 +1177,9 @@ int mpu3050_common_probe(struct device *dev,
 		goto err_power_down;
 	}
 
-	if (val != MPU3050_CHIP_ID) {
-		dev_err(dev, "unsupported chip id %02x\n", (u8)val);
+	if ((val & MPU3050_CHIP_ID_MASK) != MPU3050_CHIP_ID) {
+		dev_err(dev, "unsupported chip id %02x\n",
+				(u8)(val & MPU3050_CHIP_ID_MASK));
 		ret = -ENODEV;
 		goto err_power_down;
 	}
diff --git a/drivers/iio/industrialio-buffer.c b/drivers/iio/industrialio-buffer.c
index cd5bfe39591b..dadd921a4a30 100644
--- a/drivers/iio/industrialio-buffer.c
+++ b/drivers/iio/industrialio-buffer.c
@@ -320,9 +320,8 @@ static int iio_scan_mask_set(struct iio_dev *indio_dev,
 	const unsigned long *mask;
 	unsigned long *trialmask;
 
-	trialmask = kmalloc_array(BITS_TO_LONGS(indio_dev->masklength),
-				  sizeof(*trialmask),
-				  GFP_KERNEL);
+	trialmask = kcalloc(BITS_TO_LONGS(indio_dev->masklength),
+			    sizeof(*trialmask), GFP_KERNEL);
 	if (trialmask == NULL)
 		return -ENOMEM;
 	if (!indio_dev->masklength) {
diff --git a/drivers/iio/industrialio-core.c b/drivers/iio/industrialio-core.c
index 4700fd5d8c90..9c4d92115504 100644
--- a/drivers/iio/industrialio-core.c
+++ b/drivers/iio/industrialio-core.c
@@ -1743,10 +1743,10 @@ EXPORT_SYMBOL(__iio_device_register);
  **/
 void iio_device_unregister(struct iio_dev *indio_dev)
 {
-	mutex_lock(&indio_dev->info_exist_lock);
-
 	cdev_device_del(&indio_dev->chrdev, &indio_dev->dev);
 
+	mutex_lock(&indio_dev->info_exist_lock);
+
 	iio_device_unregister_debugfs(indio_dev);
 
 	iio_disable_all_buffers(indio_dev);
diff --git a/drivers/infiniband/core/uverbs.h b/drivers/infiniband/core/uverbs.h
index ea0bc6885517..32cc8fe7902f 100644
--- a/drivers/infiniband/core/uverbs.h
+++ b/drivers/infiniband/core/uverbs.h
@@ -160,6 +160,7 @@ struct ib_uverbs_file {
 
 	struct mutex umap_lock;
 	struct list_head umaps;
+	struct page *disassociate_page;
 
 	struct idr		idr;
 	/* spinlock protects write access to idr */
diff --git a/drivers/infiniband/core/uverbs_main.c b/drivers/infiniband/core/uverbs_main.c
index 70b7d80431a9..c489f545baae 100644
--- a/drivers/infiniband/core/uverbs_main.c
+++ b/drivers/infiniband/core/uverbs_main.c
@@ -208,6 +208,9 @@ void ib_uverbs_release_file(struct kref *ref)
 		kref_put(&file->async_file->ref,
 			 ib_uverbs_release_async_event_file);
 	put_device(&file->device->dev);
+
+	if (file->disassociate_page)
+		__free_pages(file->disassociate_page, 0);
 	kfree(file);
 }
 
@@ -877,9 +880,50 @@ static void rdma_umap_close(struct vm_area_struct *vma)
 	kfree(priv);
 }
 
+/*
+ * Once the zap_vma_ptes has been called touches to the VMA will come here and
+ * we return a dummy writable zero page for all the pfns.
+ */
+static vm_fault_t rdma_umap_fault(struct vm_fault *vmf)
+{
+	struct ib_uverbs_file *ufile = vmf->vma->vm_file->private_data;
+	struct rdma_umap_priv *priv = vmf->vma->vm_private_data;
+	vm_fault_t ret = 0;
+
+	if (!priv)
+		return VM_FAULT_SIGBUS;
+
+	/* Read only pages can just use the system zero page. */
+	if (!(vmf->vma->vm_flags & (VM_WRITE | VM_MAYWRITE))) {
+		vmf->page = ZERO_PAGE(vmf->address);
+		get_page(vmf->page);
+		return 0;
+	}
+
+	mutex_lock(&ufile->umap_lock);
+	if (!ufile->disassociate_page)
+		ufile->disassociate_page =
+			alloc_pages(vmf->gfp_mask | __GFP_ZERO, 0);
+
+	if (ufile->disassociate_page) {
+		/*
+		 * This VMA is forced to always be shared so this doesn't have
+		 * to worry about COW.
+		 */
+		vmf->page = ufile->disassociate_page;
+		get_page(vmf->page);
+	} else {
+		ret = VM_FAULT_SIGBUS;
+	}
+	mutex_unlock(&ufile->umap_lock);
+
+	return ret;
+}
+
 static const struct vm_operations_struct rdma_umap_ops = {
 	.open = rdma_umap_open,
 	.close = rdma_umap_close,
+	.fault = rdma_umap_fault,
 };
 
 static struct rdma_umap_priv *rdma_user_mmap_pre(struct ib_ucontext *ucontext,
@@ -889,6 +933,9 @@ static struct rdma_umap_priv *rdma_user_mmap_pre(struct ib_ucontext *ucontext,
 	struct ib_uverbs_file *ufile = ucontext->ufile;
 	struct rdma_umap_priv *priv;
 
+	if (!(vma->vm_flags & VM_SHARED))
+		return ERR_PTR(-EINVAL);
+
 	if (vma->vm_end - vma->vm_start != size)
 		return ERR_PTR(-EINVAL);
 
@@ -992,7 +1039,9 @@ void uverbs_user_mmap_disassociate(struct ib_uverbs_file *ufile)
 		 * at a time to get the lock ordering right. Typically there
 		 * will only be one mm, so no big deal.
 		 */
-		down_write(&mm->mmap_sem);
+		down_read(&mm->mmap_sem);
+		if (!mmget_still_valid(mm))
+			goto skip_mm;
 		mutex_lock(&ufile->umap_lock);
 		list_for_each_entry_safe (priv, next_priv, &ufile->umaps,
 					  list) {
@@ -1004,10 +1053,10 @@ void uverbs_user_mmap_disassociate(struct ib_uverbs_file *ufile)
 
 			zap_vma_ptes(vma, vma->vm_start,
 				     vma->vm_end - vma->vm_start);
-			vma->vm_flags &= ~(VM_SHARED | VM_MAYSHARE);
 		}
 		mutex_unlock(&ufile->umap_lock);
-		up_write(&mm->mmap_sem);
+	skip_mm:
+		up_read(&mm->mmap_sem);
 		mmput(mm);
 	}
 }
diff --git a/drivers/infiniband/hw/hfi1/chip.c b/drivers/infiniband/hw/hfi1/chip.c
index 612f04190ed8..addefae16c9c 100644
--- a/drivers/infiniband/hw/hfi1/chip.c
+++ b/drivers/infiniband/hw/hfi1/chip.c
@@ -8365,7 +8365,6 @@ static inline void clear_recv_intr(struct hfi1_ctxtdata *rcd)
 	struct hfi1_devdata *dd = rcd->dd;
 	u32 addr = CCE_INT_CLEAR + (8 * rcd->ireg);
 
-	mmiowb();	/* make sure everything before is written */
 	write_csr(dd, addr, rcd->imask);
 	/* force the above write on the chip and get a value back */
 	(void)read_csr(dd, addr);
@@ -11803,12 +11802,10 @@ void update_usrhead(struct hfi1_ctxtdata *rcd, u32 hd, u32 updegr, u32 egrhd,
 			<< RCV_EGR_INDEX_HEAD_HEAD_SHIFT;
 		write_uctxt_csr(dd, ctxt, RCV_EGR_INDEX_HEAD, reg);
 	}
-	mmiowb();
 	reg = ((u64)rcv_intr_count << RCV_HDR_HEAD_COUNTER_SHIFT) |
 		(((u64)hd & RCV_HDR_HEAD_HEAD_MASK)
 			<< RCV_HDR_HEAD_HEAD_SHIFT);
 	write_uctxt_csr(dd, ctxt, RCV_HDR_HEAD, reg);
-	mmiowb();
 }
 
 u32 hdrqempty(struct hfi1_ctxtdata *rcd)
@@ -13232,7 +13229,7 @@ static int set_up_context_variables(struct hfi1_devdata *dd)
 	int total_contexts;
 	int ret;
 	unsigned ngroups;
-	int qos_rmt_count;
+	int rmt_count;
 	int user_rmt_reduced;
 	u32 n_usr_ctxts;
 	u32 send_contexts = chip_send_contexts(dd);
@@ -13294,10 +13291,20 @@ static int set_up_context_variables(struct hfi1_devdata *dd)
 		n_usr_ctxts = rcv_contexts - total_contexts;
 	}
 
-	/* each user context requires an entry in the RMT */
-	qos_rmt_count = qos_rmt_entries(dd, NULL, NULL);
-	if (qos_rmt_count + n_usr_ctxts > NUM_MAP_ENTRIES) {
-		user_rmt_reduced = NUM_MAP_ENTRIES - qos_rmt_count;
+	/*
+	 * The RMT entries are currently allocated as shown below:
+	 * 1. QOS (0 to 128 entries);
+	 * 2. FECN for PSM (num_user_contexts + num_vnic_contexts);
+	 * 3. VNIC (num_vnic_contexts).
+	 * It should be noted that PSM FECN oversubscribe num_vnic_contexts
+	 * entries of RMT because both VNIC and PSM could allocate any receive
+	 * context between dd->first_dyn_alloc_text and dd->num_rcv_contexts,
+	 * and PSM FECN must reserve an RMT entry for each possible PSM receive
+	 * context.
+	 */
+	rmt_count = qos_rmt_entries(dd, NULL, NULL) + (num_vnic_contexts * 2);
+	if (rmt_count + n_usr_ctxts > NUM_MAP_ENTRIES) {
+		user_rmt_reduced = NUM_MAP_ENTRIES - rmt_count;
 		dd_dev_err(dd,
 			   "RMT size is reducing the number of user receive contexts from %u to %d\n",
 			   n_usr_ctxts,
@@ -14285,9 +14292,11 @@ static void init_user_fecn_handling(struct hfi1_devdata *dd,
 	u64 reg;
 	int i, idx, regoff, regidx;
 	u8 offset;
+	u32 total_cnt;
 
 	/* there needs to be enough room in the map table */
-	if (rmt->used + dd->num_user_contexts >= NUM_MAP_ENTRIES) {
+	total_cnt = dd->num_rcv_contexts - dd->first_dyn_alloc_ctxt;
+	if (rmt->used + total_cnt >= NUM_MAP_ENTRIES) {
 		dd_dev_err(dd, "User FECN handling disabled - too many user contexts allocated\n");
 		return;
 	}
@@ -14341,7 +14350,7 @@ static void init_user_fecn_handling(struct hfi1_devdata *dd,
 	/* add rule 1 */
 	add_rsm_rule(dd, RSM_INS_FECN, &rrd);
 
-	rmt->used += dd->num_user_contexts;
+	rmt->used += total_cnt;
 }
 
 /* Initialize RSM for VNIC */
diff --git a/drivers/infiniband/hw/hfi1/pio.c b/drivers/infiniband/hw/hfi1/pio.c
index a1de566fe95e..16ba9d52e1b9 100644
--- a/drivers/infiniband/hw/hfi1/pio.c
+++ b/drivers/infiniband/hw/hfi1/pio.c
@@ -1578,7 +1578,6 @@ void hfi1_sc_wantpiobuf_intr(struct send_context *sc, u32 needint)
 		sc_del_credit_return_intr(sc);
 	trace_hfi1_wantpiointr(sc, needint, sc->credit_ctrl);
 	if (needint) {
-		mmiowb();
 		sc_return_credits(sc);
 	}
 }
diff --git a/drivers/infiniband/hw/hfi1/qp.c b/drivers/infiniband/hw/hfi1/qp.c
index 9b643c2409cf..eba300330a02 100644
--- a/drivers/infiniband/hw/hfi1/qp.c
+++ b/drivers/infiniband/hw/hfi1/qp.c
@@ -898,7 +898,9 @@ void notify_error_qp(struct rvt_qp *qp)
 		if (!list_empty(&priv->s_iowait.list) &&
 		    !(qp->s_flags & RVT_S_BUSY) &&
 		    !(priv->s_flags & RVT_S_BUSY)) {
-			qp->s_flags &= ~RVT_S_ANY_WAIT_IO;
+			qp->s_flags &= ~HFI1_S_ANY_WAIT_IO;
+			iowait_clear_flag(&priv->s_iowait, IOWAIT_PENDING_IB);
+			iowait_clear_flag(&priv->s_iowait, IOWAIT_PENDING_TID);
 			list_del_init(&priv->s_iowait.list);
 			priv->s_iowait.lock = NULL;
 			rvt_put_qp(qp);
diff --git a/drivers/infiniband/hw/hfi1/rc.c b/drivers/infiniband/hw/hfi1/rc.c
index e6726c1ab866..5991211d72bd 100644
--- a/drivers/infiniband/hw/hfi1/rc.c
+++ b/drivers/infiniband/hw/hfi1/rc.c
@@ -3088,7 +3088,7 @@ send_last:
 			update_ack_queue(qp, next);
 		}
 		e = &qp->s_ack_queue[qp->r_head_ack_queue];
-		if (e->opcode == OP(RDMA_READ_REQUEST) && e->rdma_sge.mr) {
+		if (e->rdma_sge.mr) {
 			rvt_put_mr(e->rdma_sge.mr);
 			e->rdma_sge.mr = NULL;
 		}
@@ -3166,7 +3166,7 @@ send_last:
 			update_ack_queue(qp, next);
 		}
 		e = &qp->s_ack_queue[qp->r_head_ack_queue];
-		if (e->opcode == OP(RDMA_READ_REQUEST) && e->rdma_sge.mr) {
+		if (e->rdma_sge.mr) {
 			rvt_put_mr(e->rdma_sge.mr);
 			e->rdma_sge.mr = NULL;
 		}
diff --git a/drivers/infiniband/hw/hfi1/tid_rdma.c b/drivers/infiniband/hw/hfi1/tid_rdma.c
index fdda33aca77f..43cbce7a19ea 100644
--- a/drivers/infiniband/hw/hfi1/tid_rdma.c
+++ b/drivers/infiniband/hw/hfi1/tid_rdma.c
@@ -5017,24 +5017,14 @@ int hfi1_make_tid_rdma_pkt(struct rvt_qp *qp, struct hfi1_pkt_state *ps)
 	    make_tid_rdma_ack(qp, ohdr, ps))
 		return 1;
 
-	if (!(ib_rvt_state_ops[qp->state] & RVT_PROCESS_SEND_OK)) {
-		if (!(ib_rvt_state_ops[qp->state] & RVT_FLUSH_SEND))
-			goto bail;
-		/* We are in the error state, flush the work request. */
-		if (qp->s_last == READ_ONCE(qp->s_head))
-			goto bail;
-		/* If DMAs are in progress, we can't flush immediately. */
-		if (iowait_sdma_pending(&priv->s_iowait)) {
-			qp->s_flags |= RVT_S_WAIT_DMA;
-			goto bail;
-		}
-		clear_ahg(qp);
-		wqe = rvt_get_swqe_ptr(qp, qp->s_last);
-		hfi1_trdma_send_complete(qp, wqe, qp->s_last != qp->s_acked ?
-					 IB_WC_SUCCESS : IB_WC_WR_FLUSH_ERR);
-		/* will get called again */
-		goto done_free_tx;
-	}
+	/*
+	 * Bail out if we can't send data.
+	 * Be reminded that this check must been done after the call to
+	 * make_tid_rdma_ack() because the responding QP could be in
+	 * RTR state where it can send TID RDMA ACK, not TID RDMA WRITE DATA.
+	 */
+	if (!(ib_rvt_state_ops[qp->state] & RVT_PROCESS_SEND_OK))
+		goto bail;
 
 	if (priv->s_flags & RVT_S_WAIT_ACK)
 		goto bail;
@@ -5144,11 +5134,6 @@ int hfi1_make_tid_rdma_pkt(struct rvt_qp *qp, struct hfi1_pkt_state *ps)
 	hfi1_make_ruc_header(qp, ohdr, (opcode << 24), bth1, bth2,
 			     middle, ps);
 	return 1;
-done_free_tx:
-	hfi1_put_txreq(ps->s_txreq);
-	ps->s_txreq = NULL;
-	return 1;
-
 bail:
 	hfi1_put_txreq(ps->s_txreq);
 bail_no_tx:
diff --git a/drivers/infiniband/hw/hns/hns_roce_hem.c b/drivers/infiniband/hw/hns/hns_roce_hem.c
index f1fec56f3ff4..8e29dbb5b5fb 100644
--- a/drivers/infiniband/hw/hns/hns_roce_hem.c
+++ b/drivers/infiniband/hw/hns/hns_roce_hem.c
@@ -792,6 +792,8 @@ void *hns_roce_table_find(struct hns_roce_dev *hr_dev,
 		idx_offset = (obj & (table->num_obj - 1)) % obj_per_chunk;
 		dma_offset = offset = idx_offset * table->obj_size;
 	} else {
+		u32 seg_size = 64; /* 8 bytes per BA and 8 BA per segment */
+
 		hns_roce_calc_hem_mhop(hr_dev, table, &mhop_obj, &mhop);
 		/* mtt mhop */
 		i = mhop.l0_idx;
@@ -803,8 +805,8 @@ void *hns_roce_table_find(struct hns_roce_dev *hr_dev,
 			hem_idx = i;
 
 		hem = table->hem[hem_idx];
-		dma_offset = offset = (obj & (table->num_obj - 1)) *
-				       table->obj_size % mhop.bt_chunk_size;
+		dma_offset = offset = (obj & (table->num_obj - 1)) * seg_size %
+				       mhop.bt_chunk_size;
 		if (mhop.hop_num == 2)
 			dma_offset = offset = 0;
 	}
diff --git a/drivers/infiniband/hw/hns/hns_roce_hw_v1.c b/drivers/infiniband/hw/hns/hns_roce_hw_v1.c
index 97515c340134..c8555f7704d8 100644
--- a/drivers/infiniband/hw/hns/hns_roce_hw_v1.c
+++ b/drivers/infiniband/hw/hns/hns_roce_hw_v1.c
@@ -1750,8 +1750,6 @@ static int hns_roce_v1_post_mbox(struct hns_roce_dev *hr_dev, u64 in_param,
 
 	writel(val, hcr + 5);
 
-	mmiowb();
-
 	return 0;
 }
 
diff --git a/drivers/infiniband/hw/hns/hns_roce_mr.c b/drivers/infiniband/hw/hns/hns_roce_mr.c
index b09f1cde2ff5..08be0e4eabcd 100644
--- a/drivers/infiniband/hw/hns/hns_roce_mr.c
+++ b/drivers/infiniband/hw/hns/hns_roce_mr.c
@@ -746,7 +746,6 @@ static int hns_roce_write_mtt_chunk(struct hns_roce_dev *hr_dev,
 	struct hns_roce_hem_table *table;
 	dma_addr_t dma_handle;
 	__le64 *mtts;
-	u32 s = start_index * sizeof(u64);
 	u32 bt_page_size;
 	u32 i;
 
@@ -780,7 +779,8 @@ static int hns_roce_write_mtt_chunk(struct hns_roce_dev *hr_dev,
 		return -EINVAL;
 
 	mtts = hns_roce_table_find(hr_dev, table,
-				mtt->first_seg + s / hr_dev->caps.mtt_entry_sz,
+				mtt->first_seg +
+				start_index / HNS_ROCE_MTT_ENTRY_PER_SEG,
 				&dma_handle);
 	if (!mtts)
 		return -ENOMEM;
diff --git a/drivers/infiniband/hw/hns/hns_roce_qp.c b/drivers/infiniband/hw/hns/hns_roce_qp.c
index 57c76eafef2f..60cf9f03e941 100644
--- a/drivers/infiniband/hw/hns/hns_roce_qp.c
+++ b/drivers/infiniband/hw/hns/hns_roce_qp.c
@@ -274,9 +274,6 @@ void hns_roce_qp_free(struct hns_roce_dev *hr_dev, struct hns_roce_qp *hr_qp)
 	wait_for_completion(&hr_qp->free);
 
 	if ((hr_qp->ibqp.qp_type) != IB_QPT_GSI) {
-		if (hr_dev->caps.sccc_entry_sz)
-			hns_roce_table_put(hr_dev, &qp_table->sccc_table,
-					   hr_qp->qpn);
 		if (hr_dev->caps.trrl_entry_sz)
 			hns_roce_table_put(hr_dev, &qp_table->trrl_table,
 					   hr_qp->qpn);
@@ -536,7 +533,7 @@ static int hns_roce_set_kernel_sq_size(struct hns_roce_dev *hr_dev,
 
 static int hns_roce_qp_has_sq(struct ib_qp_init_attr *attr)
 {
-	if (attr->qp_type == IB_QPT_XRC_TGT)
+	if (attr->qp_type == IB_QPT_XRC_TGT || !attr->cap.max_send_wr)
 		return 0;
 
 	return 1;
diff --git a/drivers/infiniband/hw/i40iw/i40iw_osdep.h b/drivers/infiniband/hw/i40iw/i40iw_osdep.h
index f27be3e7830b..d474aad62a81 100644
--- a/drivers/infiniband/hw/i40iw/i40iw_osdep.h
+++ b/drivers/infiniband/hw/i40iw/i40iw_osdep.h
@@ -211,7 +211,7 @@ enum i40iw_status_code i40iw_hw_manage_vf_pble_bp(struct i40iw_device *iwdev,
 struct i40iw_sc_vsi;
 void i40iw_hw_stats_start_timer(struct i40iw_sc_vsi *vsi);
 void i40iw_hw_stats_stop_timer(struct i40iw_sc_vsi *vsi);
-#define i40iw_mmiowb() mmiowb()
+#define i40iw_mmiowb() do { } while (0)
 void i40iw_wr32(struct i40iw_hw *hw, u32 reg, u32 value);
 u32  i40iw_rd32(struct i40iw_hw *hw, u32 reg);
 #endif				/* _I40IW_OSDEP_H_ */
diff --git a/drivers/infiniband/hw/mlx4/qp.c b/drivers/infiniband/hw/mlx4/qp.c
index 429a59c5801c..9426936460f8 100644
--- a/drivers/infiniband/hw/mlx4/qp.c
+++ b/drivers/infiniband/hw/mlx4/qp.c
@@ -3744,12 +3744,6 @@ out:
 		writel_relaxed(qp->doorbell_qpn,
 			to_mdev(ibqp->device)->uar_map + MLX4_SEND_DOORBELL);
 
-		/*
-		 * Make sure doorbells don't leak out of SQ spinlock
-		 * and reach the HCA out of order.
-		 */
-		mmiowb();
-
 		stamp_send_wqe(qp, ind + qp->sq_spare_wqes - 1);
 
 		qp->sq_next_wqe = ind;
diff --git a/drivers/infiniband/hw/mlx5/main.c b/drivers/infiniband/hw/mlx5/main.c
index 531ff20b32ad..d3dd290ae1b1 100644
--- a/drivers/infiniband/hw/mlx5/main.c
+++ b/drivers/infiniband/hw/mlx5/main.c
@@ -1119,6 +1119,8 @@ static int mlx5_ib_query_device(struct ib_device *ibdev,
 		if (MLX5_CAP_GEN(mdev, qp_packet_based))
 			resp.flags |=
 				MLX5_IB_QUERY_DEV_RESP_PACKET_BASED_CREDIT_MODE;
+
+		resp.flags |= MLX5_IB_QUERY_DEV_RESP_FLAGS_SCAT2CQE_DCT;
 	}
 
 	if (field_avail(typeof(resp), sw_parsing_caps,
@@ -2066,6 +2068,7 @@ static int mlx5_ib_mmap_clock_info_page(struct mlx5_ib_dev *dev,
 
 	if (vma->vm_flags & VM_WRITE)
 		return -EPERM;
+	vma->vm_flags &= ~VM_MAYWRITE;
 
 	if (!dev->mdev->clock_info_page)
 		return -EOPNOTSUPP;
@@ -2231,19 +2234,18 @@ static int mlx5_ib_mmap(struct ib_ucontext *ibcontext, struct vm_area_struct *vm
 
 		if (vma->vm_flags & VM_WRITE)
 			return -EPERM;
+		vma->vm_flags &= ~VM_MAYWRITE;
 
 		/* Don't expose to user-space information it shouldn't have */
 		if (PAGE_SIZE > 4096)
 			return -EOPNOTSUPP;
 
-		vma->vm_page_prot = pgprot_noncached(vma->vm_page_prot);
 		pfn = (dev->mdev->iseg_base +
 		       offsetof(struct mlx5_init_seg, internal_timer_h)) >>
 			PAGE_SHIFT;
-		if (io_remap_pfn_range(vma, vma->vm_start, pfn,
-				       PAGE_SIZE, vma->vm_page_prot))
-			return -EAGAIN;
-		break;
+		return rdma_user_mmap_io(&context->ibucontext, vma, pfn,
+					 PAGE_SIZE,
+					 pgprot_noncached(vma->vm_page_prot));
 	case MLX5_IB_MMAP_CLOCK_INFO:
 		return mlx5_ib_mmap_clock_info_page(dev, vma, context);
 
diff --git a/drivers/infiniband/hw/mlx5/odp.c b/drivers/infiniband/hw/mlx5/odp.c
index c20bfc41ecf1..0aa10ebda5d9 100644
--- a/drivers/infiniband/hw/mlx5/odp.c
+++ b/drivers/infiniband/hw/mlx5/odp.c
@@ -585,7 +585,7 @@ static int pagefault_mr(struct mlx5_ib_dev *dev, struct mlx5_ib_mr *mr,
 	struct ib_umem_odp *odp_mr = to_ib_umem_odp(mr->umem);
 	bool downgrade = flags & MLX5_PF_FLAGS_DOWNGRADE;
 	bool prefetch = flags & MLX5_PF_FLAGS_PREFETCH;
-	u64 access_mask = ODP_READ_ALLOWED_BIT;
+	u64 access_mask;
 	u64 start_idx, page_mask;
 	struct ib_umem_odp *odp;
 	size_t size;
@@ -607,6 +607,7 @@ next_mr:
 	page_shift = mr->umem->page_shift;
 	page_mask = ~(BIT(page_shift) - 1);
 	start_idx = (io_virt - (mr->mmkey.iova & page_mask)) >> page_shift;
+	access_mask = ODP_READ_ALLOWED_BIT;
 
 	if (prefetch && !downgrade && !mr->umem->writable) {
 		/* prefetch with write-access must
diff --git a/drivers/infiniband/hw/mlx5/qp.c b/drivers/infiniband/hw/mlx5/qp.c
index 7cd006da1dae..8aafb2208899 100644
--- a/drivers/infiniband/hw/mlx5/qp.c
+++ b/drivers/infiniband/hw/mlx5/qp.c
@@ -1818,13 +1818,16 @@ static void configure_responder_scat_cqe(struct ib_qp_init_attr *init_attr,
 
 	rcqe_sz = mlx5_ib_get_cqe_size(init_attr->recv_cq);
 
-	if (rcqe_sz == 128) {
-		MLX5_SET(qpc, qpc, cs_res, MLX5_RES_SCAT_DATA64_CQE);
+	if (init_attr->qp_type == MLX5_IB_QPT_DCT) {
+		if (rcqe_sz == 128)
+			MLX5_SET(dctc, qpc, cs_res, MLX5_RES_SCAT_DATA64_CQE);
+
 		return;
 	}
 
-	if (init_attr->qp_type != MLX5_IB_QPT_DCT)
-		MLX5_SET(qpc, qpc, cs_res, MLX5_RES_SCAT_DATA32_CQE);
+	MLX5_SET(qpc, qpc, cs_res,
+		 rcqe_sz == 128 ? MLX5_RES_SCAT_DATA64_CQE :
+				  MLX5_RES_SCAT_DATA32_CQE);
 }
 
 static void configure_requester_scat_cqe(struct mlx5_ib_dev *dev,
@@ -5123,7 +5126,6 @@ out:
 		/* Make sure doorbells don't leak out of SQ spinlock
 		 * and reach the HCA out of order.
 		 */
-		mmiowb();
 		bf->offset ^= bf->buf_size;
 	}
 
diff --git a/drivers/infiniband/hw/mthca/mthca_cmd.c b/drivers/infiniband/hw/mthca/mthca_cmd.c
index 83aa47eb81a9..bdf5ed38de22 100644
--- a/drivers/infiniband/hw/mthca/mthca_cmd.c
+++ b/drivers/infiniband/hw/mthca/mthca_cmd.c
@@ -292,12 +292,6 @@ static int mthca_cmd_post(struct mthca_dev *dev,
 		err = mthca_cmd_post_hcr(dev, in_param, out_param, in_modifier,
 					 op_modifier, op, token, event);
 
-	/*
-	 * Make sure that our HCR writes don't get mixed in with
-	 * writes from another CPU starting a FW command.
-	 */
-	mmiowb();
-
 	mutex_unlock(&dev->cmd.hcr_mutex);
 	return err;
 }
diff --git a/drivers/infiniband/hw/mthca/mthca_cq.c b/drivers/infiniband/hw/mthca/mthca_cq.c
index a6531ffe29a6..877a6daffa98 100644
--- a/drivers/infiniband/hw/mthca/mthca_cq.c
+++ b/drivers/infiniband/hw/mthca/mthca_cq.c
@@ -211,11 +211,6 @@ static inline void update_cons_index(struct mthca_dev *dev, struct mthca_cq *cq,
 		mthca_write64(MTHCA_TAVOR_CQ_DB_INC_CI | cq->cqn, incr - 1,
 			      dev->kar + MTHCA_CQ_DOORBELL,
 			      MTHCA_GET_DOORBELL_LOCK(&dev->doorbell_lock));
-		/*
-		 * Make sure doorbells don't leak out of CQ spinlock
-		 * and reach the HCA out of order:
-		 */
-		mmiowb();
 	}
 }
 
diff --git a/drivers/infiniband/hw/mthca/mthca_qp.c b/drivers/infiniband/hw/mthca/mthca_qp.c
index 7a5b25d13faa..d65b189f20ea 100644
--- a/drivers/infiniband/hw/mthca/mthca_qp.c
+++ b/drivers/infiniband/hw/mthca/mthca_qp.c
@@ -1809,11 +1809,6 @@ out:
 			      (qp->qpn << 8) | size0,
 			      dev->kar + MTHCA_SEND_DOORBELL,
 			      MTHCA_GET_DOORBELL_LOCK(&dev->doorbell_lock));
-		/*
-		 * Make sure doorbells don't leak out of SQ spinlock
-		 * and reach the HCA out of order:
-		 */
-		mmiowb();
 	}
 
 	qp->sq.next_ind = ind;
@@ -1924,12 +1919,6 @@ out:
 	qp->rq.next_ind = ind;
 	qp->rq.head    += nreq;
 
-	/*
-	 * Make sure doorbells don't leak out of RQ spinlock and reach
-	 * the HCA out of order:
-	 */
-	mmiowb();
-
 	spin_unlock_irqrestore(&qp->rq.lock, flags);
 	return err;
 }
@@ -2164,12 +2153,6 @@ out:
 			      MTHCA_GET_DOORBELL_LOCK(&dev->doorbell_lock));
 	}
 
-	/*
-	 * Make sure doorbells don't leak out of SQ spinlock and reach
-	 * the HCA out of order:
-	 */
-	mmiowb();
-
 	spin_unlock_irqrestore(&qp->sq.lock, flags);
 	return err;
 }
diff --git a/drivers/infiniband/hw/mthca/mthca_srq.c b/drivers/infiniband/hw/mthca/mthca_srq.c
index 06b920385512..a85935ccce88 100644
--- a/drivers/infiniband/hw/mthca/mthca_srq.c
+++ b/drivers/infiniband/hw/mthca/mthca_srq.c
@@ -570,12 +570,6 @@ int mthca_tavor_post_srq_recv(struct ib_srq *ibsrq, const struct ib_recv_wr *wr,
 			      MTHCA_GET_DOORBELL_LOCK(&dev->doorbell_lock));
 	}
 
-	/*
-	 * Make sure doorbells don't leak out of SRQ spinlock and
-	 * reach the HCA out of order:
-	 */
-	mmiowb();
-
 	spin_unlock_irqrestore(&srq->lock, flags);
 	return err;
 }
diff --git a/drivers/infiniband/hw/qedr/verbs.c b/drivers/infiniband/hw/qedr/verbs.c
index 59ad4202422c..8686a98e113d 100644
--- a/drivers/infiniband/hw/qedr/verbs.c
+++ b/drivers/infiniband/hw/qedr/verbs.c
@@ -773,9 +773,6 @@ static void doorbell_cq(struct qedr_cq *cq, u32 cons, u8 flags)
 	cq->db.data.agg_flags = flags;
 	cq->db.data.value = cpu_to_le32(cons);
 	writeq(cq->db.raw, cq->db_addr);
-
-	/* Make sure write would stick */
-	mmiowb();
 }
 
 int qedr_arm_cq(struct ib_cq *ibcq, enum ib_cq_notify_flags flags)
@@ -2084,8 +2081,6 @@ static int qedr_update_qp_state(struct qedr_dev *dev,
 
 			if (rdma_protocol_roce(&dev->ibdev, 1)) {
 				writel(qp->rq.db_data.raw, qp->rq.db);
-				/* Make sure write takes effect */
-				mmiowb();
 			}
 			break;
 		case QED_ROCE_QP_STATE_ERR:
@@ -3502,9 +3497,6 @@ int qedr_post_send(struct ib_qp *ibqp, const struct ib_send_wr *wr,
 	smp_wmb();
 	writel(qp->sq.db_data.raw, qp->sq.db);
 
-	/* Make sure write sticks */
-	mmiowb();
-
 	spin_unlock_irqrestore(&qp->q_lock, flags);
 
 	return rc;
@@ -3695,12 +3687,8 @@ int qedr_post_recv(struct ib_qp *ibqp, const struct ib_recv_wr *wr,
 
 		writel(qp->rq.db_data.raw, qp->rq.db);
 
-		/* Make sure write sticks */
-		mmiowb();
-
 		if (rdma_protocol_iwarp(&dev->ibdev, 1)) {
 			writel(qp->rq.iwarp_db2_data.raw, qp->rq.iwarp_db2);
-			mmiowb();	/* for second doorbell */
 		}
 
 		wr = wr->next;
diff --git a/drivers/infiniband/hw/qib/qib_iba6120.c b/drivers/infiniband/hw/qib/qib_iba6120.c
index cdbf707fa267..531d8a1db2c3 100644
--- a/drivers/infiniband/hw/qib/qib_iba6120.c
+++ b/drivers/infiniband/hw/qib/qib_iba6120.c
@@ -1884,7 +1884,6 @@ static void qib_6120_put_tid(struct qib_devdata *dd, u64 __iomem *tidptr,
 	qib_write_kreg(dd, kr_scratch, 0xfeeddeaf);
 	writel(pa, tidp32);
 	qib_write_kreg(dd, kr_scratch, 0xdeadbeef);
-	mmiowb();
 	spin_unlock_irqrestore(tidlockp, flags);
 }
 
@@ -1928,7 +1927,6 @@ static void qib_6120_put_tid_2(struct qib_devdata *dd, u64 __iomem *tidptr,
 			pa |= 2 << 29;
 	}
 	writel(pa, tidp32);
-	mmiowb();
 }
 
 
@@ -2053,9 +2051,7 @@ static void qib_update_6120_usrhead(struct qib_ctxtdata *rcd, u64 hd,
 {
 	if (updegr)
 		qib_write_ureg(rcd->dd, ur_rcvegrindexhead, egrhd, rcd->ctxt);
-	mmiowb();
 	qib_write_ureg(rcd->dd, ur_rcvhdrhead, hd, rcd->ctxt);
-	mmiowb();
 }
 
 static u32 qib_6120_hdrqempty(struct qib_ctxtdata *rcd)
diff --git a/drivers/infiniband/hw/qib/qib_iba7220.c b/drivers/infiniband/hw/qib/qib_iba7220.c
index 9fde45538f6e..ea3ddb05cbad 100644
--- a/drivers/infiniband/hw/qib/qib_iba7220.c
+++ b/drivers/infiniband/hw/qib/qib_iba7220.c
@@ -2175,7 +2175,6 @@ static void qib_7220_put_tid(struct qib_devdata *dd, u64 __iomem *tidptr,
 		pa = chippa;
 	}
 	writeq(pa, tidptr);
-	mmiowb();
 }
 
 /**
@@ -2704,9 +2703,7 @@ static void qib_update_7220_usrhead(struct qib_ctxtdata *rcd, u64 hd,
 {
 	if (updegr)
 		qib_write_ureg(rcd->dd, ur_rcvegrindexhead, egrhd, rcd->ctxt);
-	mmiowb();
 	qib_write_ureg(rcd->dd, ur_rcvhdrhead, hd, rcd->ctxt);
-	mmiowb();
 }
 
 static u32 qib_7220_hdrqempty(struct qib_ctxtdata *rcd)
diff --git a/drivers/infiniband/hw/qib/qib_iba7322.c b/drivers/infiniband/hw/qib/qib_iba7322.c
index 17d6b24b3473..ac6a84f11ad0 100644
--- a/drivers/infiniband/hw/qib/qib_iba7322.c
+++ b/drivers/infiniband/hw/qib/qib_iba7322.c
@@ -3793,7 +3793,6 @@ static void qib_7322_put_tid(struct qib_devdata *dd, u64 __iomem *tidptr,
 		pa = chippa;
 	}
 	writeq(pa, tidptr);
-	mmiowb();
 }
 
 /**
@@ -4440,10 +4439,8 @@ static void qib_update_7322_usrhead(struct qib_ctxtdata *rcd, u64 hd,
 		adjust_rcv_timeout(rcd, npkts);
 	if (updegr)
 		qib_write_ureg(rcd->dd, ur_rcvegrindexhead, egrhd, rcd->ctxt);
-	mmiowb();
 	qib_write_ureg(rcd->dd, ur_rcvhdrhead, hd, rcd->ctxt);
 	qib_write_ureg(rcd->dd, ur_rcvhdrhead, hd, rcd->ctxt);
-	mmiowb();
 }
 
 static u32 qib_7322_hdrqempty(struct qib_ctxtdata *rcd)
diff --git a/drivers/infiniband/hw/qib/qib_sd7220.c b/drivers/infiniband/hw/qib/qib_sd7220.c
index 12caf3db8c34..4f4a09c2dbcd 100644
--- a/drivers/infiniband/hw/qib/qib_sd7220.c
+++ b/drivers/infiniband/hw/qib/qib_sd7220.c
@@ -1068,7 +1068,6 @@ static int qib_sd_setvals(struct qib_devdata *dd)
 	for (idx = 0; idx < NUM_DDS_REGS; ++idx) {
 		data = ((dds_reg_map & 0xF) << 4) | TX_FAST_ELT;
 		writeq(data, iaddr + idx);
-		mmiowb();
 		qib_read_kreg32(dd, kr_scratch);
 		dds_reg_map >>= 4;
 		for (midx = 0; midx < DDS_ROWS; ++midx) {
@@ -1076,7 +1075,6 @@ static int qib_sd_setvals(struct qib_devdata *dd)
 
 			data = dds_init_vals[midx].reg_vals[idx];
 			writeq(data, daddr);
-			mmiowb();
 			qib_read_kreg32(dd, kr_scratch);
 		} /* End inner for (vals for this reg, each row) */
 	} /* end outer for (regs to be stored) */
@@ -1098,13 +1096,11 @@ static int qib_sd_setvals(struct qib_devdata *dd)
 		didx = idx + min_idx;
 		/* Store the next RXEQ register address */
 		writeq(rxeq_init_vals[idx].rdesc, iaddr + didx);
-		mmiowb();
 		qib_read_kreg32(dd, kr_scratch);
 		/* Iterate through RXEQ values */
 		for (vidx = 0; vidx < 4; vidx++) {
 			data = rxeq_init_vals[idx].rdata[vidx];
 			writeq(data, taddr + (vidx << 6) + idx);
-			mmiowb();
 			qib_read_kreg32(dd, kr_scratch);
 		}
 	} /* end outer for (Reg-writes for RXEQ) */
diff --git a/drivers/infiniband/hw/vmw_pvrdma/pvrdma_main.c b/drivers/infiniband/hw/vmw_pvrdma/pvrdma_main.c
index 6d8b3e0de57a..ec41400fec0c 100644
--- a/drivers/infiniband/hw/vmw_pvrdma/pvrdma_main.c
+++ b/drivers/infiniband/hw/vmw_pvrdma/pvrdma_main.c
@@ -1131,6 +1131,8 @@ static void pvrdma_pci_remove(struct pci_dev *pdev)
 	pvrdma_page_dir_cleanup(dev, &dev->cq_pdir);
 	pvrdma_page_dir_cleanup(dev, &dev->async_pdir);
 	pvrdma_free_slots(dev);
+	dma_free_coherent(&pdev->dev, sizeof(*dev->dsr), dev->dsr,
+			  dev->dsrbase);
 
 	iounmap(dev->regs);
 	kfree(dev->sgid_tbl);
diff --git a/drivers/infiniband/sw/rdmavt/mr.c b/drivers/infiniband/sw/rdmavt/mr.c
index 728795043496..0bb6e39dd03a 100644
--- a/drivers/infiniband/sw/rdmavt/mr.c
+++ b/drivers/infiniband/sw/rdmavt/mr.c
@@ -608,11 +608,6 @@ static int rvt_set_page(struct ib_mr *ibmr, u64 addr)
 	if (unlikely(mapped_segs == mr->mr.max_segs))
 		return -ENOMEM;
 
-	if (mr->mr.length == 0) {
-		mr->mr.user_base = addr;
-		mr->mr.iova = addr;
-	}
-
 	m = mapped_segs / RVT_SEGSZ;
 	n = mapped_segs % RVT_SEGSZ;
 	mr->mr.map[m]->segs[n].vaddr = (void *)addr;
@@ -630,17 +625,24 @@ static int rvt_set_page(struct ib_mr *ibmr, u64 addr)
  * @sg_nents: number of entries in sg
  * @sg_offset: offset in bytes into sg
  *
+ * Overwrite rvt_mr length with mr length calculated by ib_sg_to_pages.
+ *
  * Return: number of sg elements mapped to the memory region
  */
 int rvt_map_mr_sg(struct ib_mr *ibmr, struct scatterlist *sg,
 		  int sg_nents, unsigned int *sg_offset)
 {
 	struct rvt_mr *mr = to_imr(ibmr);
+	int ret;
 
 	mr->mr.length = 0;
 	mr->mr.page_shift = PAGE_SHIFT;
-	return ib_sg_to_pages(ibmr, sg, sg_nents, sg_offset,
-			      rvt_set_page);
+	ret = ib_sg_to_pages(ibmr, sg, sg_nents, sg_offset, rvt_set_page);
+	mr->mr.user_base = ibmr->iova;
+	mr->mr.iova = ibmr->iova;
+	mr->mr.offset = ibmr->iova - (u64)mr->mr.map[0]->segs[0].vaddr;
+	mr->mr.length = (size_t)ibmr->length;
+	return ret;
 }
 
 /**
@@ -671,6 +673,7 @@ int rvt_fast_reg_mr(struct rvt_qp *qp, struct ib_mr *ibmr, u32 key,
 	ibmr->rkey = key;
 	mr->mr.lkey = key;
 	mr->mr.access_flags = access;
+	mr->mr.iova = ibmr->iova;
 	atomic_set(&mr->mr.lkey_invalid, 0);
 
 	return 0;
diff --git a/drivers/infiniband/sw/rxe/rxe.h b/drivers/infiniband/sw/rxe/rxe.h
index 2e2dff478833..ecf6e659c0da 100644
--- a/drivers/infiniband/sw/rxe/rxe.h
+++ b/drivers/infiniband/sw/rxe/rxe.h
@@ -80,7 +80,6 @@ static inline u32 rxe_crc32(struct rxe_dev *rxe,
 	SHASH_DESC_ON_STACK(shash, rxe->tfm);
 
 	shash->tfm = rxe->tfm;
-	shash->flags = 0;
 	*(u32 *)shash_desc_ctx(shash) = crc;
 	err = crypto_shash_update(shash, next, len);
 	if (unlikely(err)) {
diff --git a/drivers/input/keyboard/Kconfig b/drivers/input/keyboard/Kconfig
index a878351f1643..52d7f55fca32 100644
--- a/drivers/input/keyboard/Kconfig
+++ b/drivers/input/keyboard/Kconfig
@@ -420,7 +420,7 @@ config KEYBOARD_MPR121
 
 config KEYBOARD_SNVS_PWRKEY
 	tristate "IMX SNVS Power Key Driver"
-	depends on SOC_IMX6SX || SOC_IMX7D
+	depends on ARCH_MXC || COMPILE_TEST
 	depends on OF
 	help
 	  This is the snvs powerkey driver for the Freescale i.MX application
diff --git a/drivers/input/keyboard/snvs_pwrkey.c b/drivers/input/keyboard/snvs_pwrkey.c
index effb63205d3d..4c67cf30a5d9 100644
--- a/drivers/input/keyboard/snvs_pwrkey.c
+++ b/drivers/input/keyboard/snvs_pwrkey.c
@@ -148,6 +148,9 @@ static int imx_snvs_pwrkey_probe(struct platform_device *pdev)
 		return error;
 	}
 
+	pdata->input = input;
+	platform_set_drvdata(pdev, pdata);
+
 	error = devm_request_irq(&pdev->dev, pdata->irq,
 			       imx_snvs_pwrkey_interrupt,
 			       0, pdev->name, pdev);
@@ -163,9 +166,6 @@ static int imx_snvs_pwrkey_probe(struct platform_device *pdev)
 		return error;
 	}
 
-	pdata->input = input;
-	platform_set_drvdata(pdev, pdata);
-
 	device_init_wakeup(&pdev->dev, pdata->wakeup);
 
 	return 0;
diff --git a/drivers/input/mouse/elan_i2c_core.c b/drivers/input/mouse/elan_i2c_core.c
index 628ef617bb2f..f9525d6f0bfe 100644
--- a/drivers/input/mouse/elan_i2c_core.c
+++ b/drivers/input/mouse/elan_i2c_core.c
@@ -1339,21 +1339,46 @@ static const struct acpi_device_id elan_acpi_id[] = {
 	{ "ELAN0600", 0 },
 	{ "ELAN0601", 0 },
 	{ "ELAN0602", 0 },
+	{ "ELAN0603", 0 },
+	{ "ELAN0604", 0 },
 	{ "ELAN0605", 0 },
+	{ "ELAN0606", 0 },
+	{ "ELAN0607", 0 },
 	{ "ELAN0608", 0 },
 	{ "ELAN0609", 0 },
 	{ "ELAN060B", 0 },
 	{ "ELAN060C", 0 },
+	{ "ELAN060F", 0 },
+	{ "ELAN0610", 0 },
 	{ "ELAN0611", 0 },
 	{ "ELAN0612", 0 },
+	{ "ELAN0615", 0 },
+	{ "ELAN0616", 0 },
 	{ "ELAN0617", 0 },
 	{ "ELAN0618", 0 },
+	{ "ELAN0619", 0 },
+	{ "ELAN061A", 0 },
+	{ "ELAN061B", 0 },
 	{ "ELAN061C", 0 },
 	{ "ELAN061D", 0 },
 	{ "ELAN061E", 0 },
+	{ "ELAN061F", 0 },
 	{ "ELAN0620", 0 },
 	{ "ELAN0621", 0 },
 	{ "ELAN0622", 0 },
+	{ "ELAN0623", 0 },
+	{ "ELAN0624", 0 },
+	{ "ELAN0625", 0 },
+	{ "ELAN0626", 0 },
+	{ "ELAN0627", 0 },
+	{ "ELAN0628", 0 },
+	{ "ELAN0629", 0 },
+	{ "ELAN062A", 0 },
+	{ "ELAN062B", 0 },
+	{ "ELAN062C", 0 },
+	{ "ELAN062D", 0 },
+	{ "ELAN0631", 0 },
+	{ "ELAN0632", 0 },
 	{ "ELAN1000", 0 },
 	{ }
 };
diff --git a/drivers/input/rmi4/rmi_driver.c b/drivers/input/rmi4/rmi_driver.c
index fc3ab93b7aea..7fb358f96195 100644
--- a/drivers/input/rmi4/rmi_driver.c
+++ b/drivers/input/rmi4/rmi_driver.c
@@ -860,7 +860,7 @@ static int rmi_create_function(struct rmi_device *rmi_dev,
 
 	error = rmi_register_function(fn);
 	if (error)
-		goto err_put_fn;
+		return error;
 
 	if (pdt->function_number == 0x01)
 		data->f01_container = fn;
@@ -870,10 +870,6 @@ static int rmi_create_function(struct rmi_device *rmi_dev,
 	list_add_tail(&fn->node, &data->function_list);
 
 	return RMI_SCAN_CONTINUE;
-
-err_put_fn:
-	put_device(&fn->dev);
-	return error;
 }
 
 void rmi_enable_irq(struct rmi_device *rmi_dev, bool clear_wake)
diff --git a/drivers/input/rmi4/rmi_f11.c b/drivers/input/rmi4/rmi_f11.c
index df64d6aed4f7..93901ebd122a 100644
--- a/drivers/input/rmi4/rmi_f11.c
+++ b/drivers/input/rmi4/rmi_f11.c
@@ -1230,7 +1230,7 @@ static int rmi_f11_initialize(struct rmi_function *fn)
 	}
 
 	rc = f11_write_control_regs(fn, &f11->sens_query,
-			   &f11->dev_controls, fn->fd.query_base_addr);
+			   &f11->dev_controls, fn->fd.control_base_addr);
 	if (rc)
 		dev_warn(&fn->dev, "Failed to write control registers\n");
 
diff --git a/drivers/iommu/amd_iommu.c b/drivers/iommu/amd_iommu.c
index 21cb088d6687..f7cdd2ab7f11 100644
--- a/drivers/iommu/amd_iommu.c
+++ b/drivers/iommu/amd_iommu.c
@@ -3169,21 +3169,24 @@ static void amd_iommu_get_resv_regions(struct device *dev,
 		return;
 
 	list_for_each_entry(entry, &amd_iommu_unity_map, list) {
+		int type, prot = 0;
 		size_t length;
-		int prot = 0;
 
 		if (devid < entry->devid_start || devid > entry->devid_end)
 			continue;
 
+		type   = IOMMU_RESV_DIRECT;
 		length = entry->address_end - entry->address_start;
 		if (entry->prot & IOMMU_PROT_IR)
 			prot |= IOMMU_READ;
 		if (entry->prot & IOMMU_PROT_IW)
 			prot |= IOMMU_WRITE;
+		if (entry->prot & IOMMU_UNITY_MAP_FLAG_EXCL_RANGE)
+			/* Exclusion range */
+			type = IOMMU_RESV_RESERVED;
 
 		region = iommu_alloc_resv_region(entry->address_start,
-						 length, prot,
-						 IOMMU_RESV_DIRECT);
+						 length, prot, type);
 		if (!region) {
 			dev_err(dev, "Out of memory allocating dm-regions\n");
 			return;
diff --git a/drivers/iommu/amd_iommu_init.c b/drivers/iommu/amd_iommu_init.c
index f773792d77fd..ff40ba758cf3 100644
--- a/drivers/iommu/amd_iommu_init.c
+++ b/drivers/iommu/amd_iommu_init.c
@@ -359,7 +359,7 @@ static void iommu_write_l2(struct amd_iommu *iommu, u8 address, u32 val)
 static void iommu_set_exclusion_range(struct amd_iommu *iommu)
 {
 	u64 start = iommu->exclusion_start & PAGE_MASK;
-	u64 limit = (start + iommu->exclusion_length) & PAGE_MASK;
+	u64 limit = (start + iommu->exclusion_length - 1) & PAGE_MASK;
 	u64 entry;
 
 	if (!iommu->exclusion_start)
@@ -2013,6 +2013,9 @@ static int __init init_unity_map_range(struct ivmd_header *m)
 	if (e == NULL)
 		return -ENOMEM;
 
+	if (m->flags & IVMD_FLAG_EXCL_RANGE)
+		init_exclusion_range(m);
+
 	switch (m->type) {
 	default:
 		kfree(e);
@@ -2059,9 +2062,7 @@ static int __init init_memory_definitions(struct acpi_table_header *table)
 
 	while (p < end) {
 		m = (struct ivmd_header *)p;
-		if (m->flags & IVMD_FLAG_EXCL_RANGE)
-			init_exclusion_range(m);
-		else if (m->flags & IVMD_FLAG_UNITY_MAP)
+		if (m->flags & (IVMD_FLAG_UNITY_MAP | IVMD_FLAG_EXCL_RANGE))
 			init_unity_map_range(m);
 
 		p += m->length;
diff --git a/drivers/iommu/amd_iommu_types.h b/drivers/iommu/amd_iommu_types.h
index eae0741f72dc..87965e4d9647 100644
--- a/drivers/iommu/amd_iommu_types.h
+++ b/drivers/iommu/amd_iommu_types.h
@@ -374,6 +374,8 @@
 #define IOMMU_PROT_IR 0x01
 #define IOMMU_PROT_IW 0x02
 
+#define IOMMU_UNITY_MAP_FLAG_EXCL_RANGE	(1 << 2)
+
 /* IOMMU capabilities */
 #define IOMMU_CAP_IOTLB   24
 #define IOMMU_CAP_NPCACHE 26
diff --git a/drivers/iommu/io-pgtable-arm-v7s.c b/drivers/iommu/io-pgtable-arm-v7s.c
index f101afc315ab..9a8a8870e267 100644
--- a/drivers/iommu/io-pgtable-arm-v7s.c
+++ b/drivers/iommu/io-pgtable-arm-v7s.c
@@ -160,6 +160,14 @@
 
 #define ARM_V7S_TCR_PD1			BIT(5)
 
+#ifdef CONFIG_ZONE_DMA32
+#define ARM_V7S_TABLE_GFP_DMA GFP_DMA32
+#define ARM_V7S_TABLE_SLAB_FLAGS SLAB_CACHE_DMA32
+#else
+#define ARM_V7S_TABLE_GFP_DMA GFP_DMA
+#define ARM_V7S_TABLE_SLAB_FLAGS SLAB_CACHE_DMA
+#endif
+
 typedef u32 arm_v7s_iopte;
 
 static bool selftest_running;
@@ -197,13 +205,16 @@ static void *__arm_v7s_alloc_table(int lvl, gfp_t gfp,
 	void *table = NULL;
 
 	if (lvl == 1)
-		table = (void *)__get_dma_pages(__GFP_ZERO, get_order(size));
+		table = (void *)__get_free_pages(
+			__GFP_ZERO | ARM_V7S_TABLE_GFP_DMA, get_order(size));
 	else if (lvl == 2)
-		table = kmem_cache_zalloc(data->l2_tables, gfp | GFP_DMA);
+		table = kmem_cache_zalloc(data->l2_tables, gfp);
 	phys = virt_to_phys(table);
-	if (phys != (arm_v7s_iopte)phys)
+	if (phys != (arm_v7s_iopte)phys) {
 		/* Doesn't fit in PTE */
+		dev_err(dev, "Page table does not fit in PTE: %pa", &phys);
 		goto out_free;
+	}
 	if (table && !(cfg->quirks & IO_PGTABLE_QUIRK_NO_DMA)) {
 		dma = dma_map_single(dev, table, size, DMA_TO_DEVICE);
 		if (dma_mapping_error(dev, dma))
@@ -733,7 +744,7 @@ static struct io_pgtable *arm_v7s_alloc_pgtable(struct io_pgtable_cfg *cfg,
 	data->l2_tables = kmem_cache_create("io-pgtable_armv7s_l2",
 					    ARM_V7S_TABLE_SIZE(2),
 					    ARM_V7S_TABLE_SIZE(2),
-					    SLAB_CACHE_DMA, NULL);
+					    ARM_V7S_TABLE_SLAB_FLAGS, NULL);
 	if (!data->l2_tables)
 		goto out_free_data;
 
diff --git a/drivers/iommu/iommu.c b/drivers/iommu/iommu.c
index 33a982e33716..109de67d5d72 100644
--- a/drivers/iommu/iommu.c
+++ b/drivers/iommu/iommu.c
@@ -1105,10 +1105,12 @@ struct iommu_group *iommu_group_get_for_dev(struct device *dev)
 
 		dom = __iommu_domain_alloc(dev->bus, iommu_def_domain_type);
 		if (!dom && iommu_def_domain_type != IOMMU_DOMAIN_DMA) {
-			dev_warn(dev,
-				 "failed to allocate default IOMMU domain of type %u; falling back to IOMMU_DOMAIN_DMA",
-				 iommu_def_domain_type);
 			dom = __iommu_domain_alloc(dev->bus, IOMMU_DOMAIN_DMA);
+			if (dom) {
+				dev_warn(dev,
+					 "failed to allocate default IOMMU domain of type %u; falling back to IOMMU_DOMAIN_DMA",
+					 iommu_def_domain_type);
+			}
 		}
 
 		group->default_domain = dom;
diff --git a/drivers/irqchip/irq-ath79-misc.c b/drivers/irqchip/irq-ath79-misc.c
index aa7290784636..0390603170b4 100644
--- a/drivers/irqchip/irq-ath79-misc.c
+++ b/drivers/irqchip/irq-ath79-misc.c
@@ -22,6 +22,15 @@
 #define AR71XX_RESET_REG_MISC_INT_ENABLE	4
 
 #define ATH79_MISC_IRQ_COUNT			32
+#define ATH79_MISC_PERF_IRQ			5
+
+static int ath79_perfcount_irq;
+
+int get_c0_perfcount_int(void)
+{
+	return ath79_perfcount_irq;
+}
+EXPORT_SYMBOL_GPL(get_c0_perfcount_int);
 
 static void ath79_misc_irq_handler(struct irq_desc *desc)
 {
@@ -113,6 +122,8 @@ static void __init ath79_misc_intc_domain_init(
 {
 	void __iomem *base = domain->host_data;
 
+	ath79_perfcount_irq = irq_create_mapping(domain, ATH79_MISC_PERF_IRQ);
+
 	/* Disable and clear all interrupts */
 	__raw_writel(0, base + AR71XX_RESET_REG_MISC_INT_ENABLE);
 	__raw_writel(0, base + AR71XX_RESET_REG_MISC_INT_STATUS);
diff --git a/drivers/irqchip/irq-ls1x.c b/drivers/irqchip/irq-ls1x.c
index 86b72fbd3b45..353111a10413 100644
--- a/drivers/irqchip/irq-ls1x.c
+++ b/drivers/irqchip/irq-ls1x.c
@@ -130,6 +130,7 @@ static int __init ls1x_intc_of_init(struct device_node *node,
 					     NULL);
 	if (!priv->domain) {
 		pr_err("ls1x-irq: cannot add IRQ domain\n");
+		err = -ENOMEM;
 		goto out_iounmap;
 	}
 
diff --git a/drivers/isdn/hardware/mISDN/hfcmulti.c b/drivers/isdn/hardware/mISDN/hfcmulti.c
index 4d85645c87f7..0928fd1f0e0c 100644
--- a/drivers/isdn/hardware/mISDN/hfcmulti.c
+++ b/drivers/isdn/hardware/mISDN/hfcmulti.c
@@ -4365,7 +4365,8 @@ setup_pci(struct hfc_multi *hc, struct pci_dev *pdev,
 	if (m->clock2)
 		test_and_set_bit(HFC_CHIP_CLOCK2, &hc->chip);
 
-	if (ent->device == 0xB410) {
+	if (ent->vendor == PCI_VENDOR_ID_DIGIUM &&
+	    ent->device == PCI_DEVICE_ID_DIGIUM_HFC4S) {
 		test_and_set_bit(HFC_CHIP_B410P, &hc->chip);
 		test_and_set_bit(HFC_CHIP_PCM_MASTER, &hc->chip);
 		test_and_clear_bit(HFC_CHIP_PCM_SLAVE, &hc->chip);
diff --git a/drivers/isdn/mISDN/socket.c b/drivers/isdn/mISDN/socket.c
index 4ab8b1b6608f..a14e35d40538 100644
--- a/drivers/isdn/mISDN/socket.c
+++ b/drivers/isdn/mISDN/socket.c
@@ -710,10 +710,10 @@ base_sock_bind(struct socket *sock, struct sockaddr *addr, int addr_len)
 	struct sock *sk = sock->sk;
 	int err = 0;
 
-	if (!maddr || maddr->family != AF_ISDN)
+	if (addr_len < sizeof(struct sockaddr_mISDN))
 		return -EINVAL;
 
-	if (addr_len < sizeof(struct sockaddr_mISDN))
+	if (!maddr || maddr->family != AF_ISDN)
 		return -EINVAL;
 
 	lock_sock(sk);
diff --git a/drivers/leds/leds-pca9532.c b/drivers/leds/leds-pca9532.c
index 7fea18b0c15d..7cb4d685a1f1 100644
--- a/drivers/leds/leds-pca9532.c
+++ b/drivers/leds/leds-pca9532.c
@@ -513,6 +513,7 @@ static int pca9532_probe(struct i2c_client *client,
 	const struct i2c_device_id *id)
 {
 	int devid;
+	const struct of_device_id *of_id;
 	struct pca9532_data *data = i2c_get_clientdata(client);
 	struct pca9532_platform_data *pca9532_pdata =
 			dev_get_platdata(&client->dev);
@@ -528,8 +529,11 @@ static int pca9532_probe(struct i2c_client *client,
 			dev_err(&client->dev, "no platform data\n");
 			return -EINVAL;
 		}
-		devid = (int)(uintptr_t)of_match_device(
-			of_pca9532_leds_match, &client->dev)->data;
+		of_id = of_match_device(of_pca9532_leds_match,
+				&client->dev);
+		if (unlikely(!of_id))
+			return -EINVAL;
+		devid = (int)(uintptr_t) of_id->data;
 	} else {
 		devid = id->driver_data;
 	}
diff --git a/drivers/leds/trigger/ledtrig-netdev.c b/drivers/leds/trigger/ledtrig-netdev.c
index 3dd3ed46d473..136f86a1627d 100644
--- a/drivers/leds/trigger/ledtrig-netdev.c
+++ b/drivers/leds/trigger/ledtrig-netdev.c
@@ -122,7 +122,8 @@ static ssize_t device_name_store(struct device *dev,
 		trigger_data->net_dev = NULL;
 	}
 
-	strncpy(trigger_data->device_name, buf, size);
+	memcpy(trigger_data->device_name, buf, size);
+	trigger_data->device_name[size] = 0;
 	if (size > 0 && trigger_data->device_name[size - 1] == '\n')
 		trigger_data->device_name[size - 1] = 0;
 
@@ -301,11 +302,11 @@ static int netdev_trig_notify(struct notifier_block *nb,
 		container_of(nb, struct led_netdev_data, notifier);
 
 	if (evt != NETDEV_UP && evt != NETDEV_DOWN && evt != NETDEV_CHANGE
-	    && evt != NETDEV_REGISTER && evt != NETDEV_UNREGISTER
-	    && evt != NETDEV_CHANGENAME)
+	    && evt != NETDEV_REGISTER && evt != NETDEV_UNREGISTER)
 		return NOTIFY_DONE;
 
-	if (strcmp(dev->name, trigger_data->device_name))
+	if (!(dev == trigger_data->net_dev ||
+	      (evt == NETDEV_REGISTER && !strcmp(dev->name, trigger_data->device_name))))
 		return NOTIFY_DONE;
 
 	cancel_delayed_work_sync(&trigger_data->work);
@@ -320,12 +321,9 @@ static int netdev_trig_notify(struct notifier_block *nb,
 		dev_hold(dev);
 		trigger_data->net_dev = dev;
 		break;
-	case NETDEV_CHANGENAME:
 	case NETDEV_UNREGISTER:
-		if (trigger_data->net_dev) {
-			dev_put(trigger_data->net_dev);
-			trigger_data->net_dev = NULL;
-		}
+		dev_put(trigger_data->net_dev);
+		trigger_data->net_dev = NULL;
 		break;
 	case NETDEV_UP:
 	case NETDEV_CHANGE:
diff --git a/drivers/lightnvm/pblk-read.c b/drivers/lightnvm/pblk-read.c
index 3789185144da..0b7d5fb4548d 100644
--- a/drivers/lightnvm/pblk-read.c
+++ b/drivers/lightnvm/pblk-read.c
@@ -231,14 +231,14 @@ static void pblk_end_partial_read(struct nvm_rq *rqd)
 	struct pblk_sec_meta *meta;
 	struct bio *new_bio = rqd->bio;
 	struct bio *bio = pr_ctx->orig_bio;
-	struct bio_vec src_bv, dst_bv;
 	void *meta_list = rqd->meta_list;
-	int bio_init_idx = pr_ctx->bio_init_idx;
 	unsigned long *read_bitmap = pr_ctx->bitmap;
+	struct bvec_iter orig_iter = BVEC_ITER_ALL_INIT;
+	struct bvec_iter new_iter = BVEC_ITER_ALL_INIT;
 	int nr_secs = pr_ctx->orig_nr_secs;
 	int nr_holes = nr_secs - bitmap_weight(read_bitmap, nr_secs);
 	void *src_p, *dst_p;
-	int hole, i;
+	int bit, i;
 
 	if (unlikely(nr_holes == 1)) {
 		struct ppa_addr ppa;
@@ -257,33 +257,39 @@ static void pblk_end_partial_read(struct nvm_rq *rqd)
 
 	/* Fill the holes in the original bio */
 	i = 0;
-	hole = find_first_zero_bit(read_bitmap, nr_secs);
-	do {
-		struct pblk_line *line;
+	for (bit = 0; bit < nr_secs; bit++) {
+		if (!test_bit(bit, read_bitmap)) {
+			struct bio_vec dst_bv, src_bv;
+			struct pblk_line *line;
 
-		line = pblk_ppa_to_line(pblk, rqd->ppa_list[i]);
-		kref_put(&line->ref, pblk_line_put);
+			line = pblk_ppa_to_line(pblk, rqd->ppa_list[i]);
+			kref_put(&line->ref, pblk_line_put);
 
-		meta = pblk_get_meta(pblk, meta_list, hole);
-		meta->lba = cpu_to_le64(pr_ctx->lba_list_media[i]);
+			meta = pblk_get_meta(pblk, meta_list, bit);
+			meta->lba = cpu_to_le64(pr_ctx->lba_list_media[i]);
 
-		src_bv = new_bio->bi_io_vec[i++];
-		dst_bv = bio->bi_io_vec[bio_init_idx + hole];
+			dst_bv = bio_iter_iovec(bio, orig_iter);
+			src_bv = bio_iter_iovec(new_bio, new_iter);
 
-		src_p = kmap_atomic(src_bv.bv_page);
-		dst_p = kmap_atomic(dst_bv.bv_page);
+			src_p = kmap_atomic(src_bv.bv_page);
+			dst_p = kmap_atomic(dst_bv.bv_page);
 
-		memcpy(dst_p + dst_bv.bv_offset,
-			src_p + src_bv.bv_offset,
-			PBLK_EXPOSED_PAGE_SIZE);
+			memcpy(dst_p + dst_bv.bv_offset,
+				src_p + src_bv.bv_offset,
+				PBLK_EXPOSED_PAGE_SIZE);
 
-		kunmap_atomic(src_p);
-		kunmap_atomic(dst_p);
+			kunmap_atomic(src_p);
+			kunmap_atomic(dst_p);
 
-		mempool_free(src_bv.bv_page, &pblk->page_bio_pool);
+			flush_dcache_page(dst_bv.bv_page);
+			mempool_free(src_bv.bv_page, &pblk->page_bio_pool);
 
-		hole = find_next_zero_bit(read_bitmap, nr_secs, hole + 1);
-	} while (hole < nr_secs);
+			bio_advance_iter(new_bio, &new_iter,
+					PBLK_EXPOSED_PAGE_SIZE);
+			i++;
+		}
+		bio_advance_iter(bio, &orig_iter, PBLK_EXPOSED_PAGE_SIZE);
+	}
 
 	bio_put(new_bio);
 	kfree(pr_ctx);
diff --git a/drivers/md/dm-bufio.c b/drivers/md/dm-bufio.c
index 1ecef76225a1..2a48ea3f1b30 100644
--- a/drivers/md/dm-bufio.c
+++ b/drivers/md/dm-bufio.c
@@ -150,7 +150,7 @@ struct dm_buffer {
 	void (*end_io)(struct dm_buffer *, blk_status_t);
 #ifdef CONFIG_DM_DEBUG_BLOCK_STACK_TRACING
 #define MAX_STACK 10
-	struct stack_trace stack_trace;
+	unsigned int stack_len;
 	unsigned long stack_entries[MAX_STACK];
 #endif
 };
@@ -232,11 +232,7 @@ static DEFINE_MUTEX(dm_bufio_clients_lock);
 #ifdef CONFIG_DM_DEBUG_BLOCK_STACK_TRACING
 static void buffer_record_stack(struct dm_buffer *b)
 {
-	b->stack_trace.nr_entries = 0;
-	b->stack_trace.max_entries = MAX_STACK;
-	b->stack_trace.entries = b->stack_entries;
-	b->stack_trace.skip = 2;
-	save_stack_trace(&b->stack_trace);
+	b->stack_len = stack_trace_save(b->stack_entries, MAX_STACK, 2);
 }
 #endif
 
@@ -438,7 +434,7 @@ static struct dm_buffer *alloc_buffer(struct dm_bufio_client *c, gfp_t gfp_mask)
 	adjust_total_allocated(b->data_mode, (long)c->block_size);
 
 #ifdef CONFIG_DM_DEBUG_BLOCK_STACK_TRACING
-	memset(&b->stack_trace, 0, sizeof(b->stack_trace));
+	b->stack_len = 0;
 #endif
 	return b;
 }
@@ -1520,8 +1516,9 @@ static void drop_buffers(struct dm_bufio_client *c)
 			DMERR("leaked buffer %llx, hold count %u, list %d",
 			      (unsigned long long)b->block, b->hold_count, i);
 #ifdef CONFIG_DM_DEBUG_BLOCK_STACK_TRACING
-			print_stack_trace(&b->stack_trace, 1);
-			b->hold_count = 0; /* mark unclaimed to avoid BUG_ON below */
+			stack_trace_print(b->stack_entries, b->stack_len, 1);
+			/* mark unclaimed to avoid BUG_ON below */
+			b->hold_count = 0;
 #endif
 		}
 
diff --git a/drivers/md/dm-core.h b/drivers/md/dm-core.h
index 95c6d86ab5e8..c4ef1fceead6 100644
--- a/drivers/md/dm-core.h
+++ b/drivers/md/dm-core.h
@@ -115,6 +115,7 @@ struct mapped_device {
 	struct srcu_struct io_barrier;
 };
 
+void disable_discard(struct mapped_device *md);
 void disable_write_same(struct mapped_device *md);
 void disable_write_zeroes(struct mapped_device *md);
 
diff --git a/drivers/md/dm-crypt.c b/drivers/md/dm-crypt.c
index dd6565798778..9faed1c92b52 100644
--- a/drivers/md/dm-crypt.c
+++ b/drivers/md/dm-crypt.c
@@ -332,7 +332,6 @@ static int crypt_iv_essiv_init(struct crypt_config *cc)
 	int err;
 
 	desc->tfm = essiv->hash_tfm;
-	desc->flags = 0;
 
 	err = crypto_shash_digest(desc, cc->key, cc->key_size, essiv->salt);
 	shash_desc_zero(desc);
@@ -606,7 +605,6 @@ static int crypt_iv_lmk_one(struct crypt_config *cc, u8 *iv,
 	int i, r;
 
 	desc->tfm = lmk->hash_tfm;
-	desc->flags = 0;
 
 	r = crypto_shash_init(desc);
 	if (r)
@@ -768,7 +766,6 @@ static int crypt_iv_tcw_whitening(struct crypt_config *cc,
 
 	/* calculate crc32 for every 32bit part and xor it */
 	desc->tfm = tcw->crc32_tfm;
-	desc->flags = 0;
 	for (i = 0; i < 4; i++) {
 		r = crypto_shash_init(desc);
 		if (r)
diff --git a/drivers/md/dm-init.c b/drivers/md/dm-init.c
index b53f30f16b4d..4b76f84424c3 100644
--- a/drivers/md/dm-init.c
+++ b/drivers/md/dm-init.c
@@ -36,7 +36,7 @@ struct dm_device {
 	struct list_head list;
 };
 
-const char *dm_allowed_targets[] __initconst = {
+const char * const dm_allowed_targets[] __initconst = {
 	"crypt",
 	"delay",
 	"linear",
diff --git a/drivers/md/dm-integrity.c b/drivers/md/dm-integrity.c
index d57d997a52c8..95ae4bf34203 100644
--- a/drivers/md/dm-integrity.c
+++ b/drivers/md/dm-integrity.c
@@ -532,7 +532,6 @@ static void section_mac(struct dm_integrity_c *ic, unsigned section, __u8 result
 	unsigned j, size;
 
 	desc->tfm = ic->journal_mac;
-	desc->flags = 0;
 
 	r = crypto_shash_init(desc);
 	if (unlikely(r)) {
@@ -913,7 +912,7 @@ static void copy_from_journal(struct dm_integrity_c *ic, unsigned section, unsig
 static bool ranges_overlap(struct dm_integrity_range *range1, struct dm_integrity_range *range2)
 {
 	return range1->logical_sector < range2->logical_sector + range2->n_sectors &&
-	       range2->logical_sector + range2->n_sectors > range2->logical_sector;
+	       range1->logical_sector + range1->n_sectors > range2->logical_sector;
 }
 
 static bool add_new_range(struct dm_integrity_c *ic, struct dm_integrity_range *new_range, bool check_waiting)
@@ -959,8 +958,6 @@ static void remove_range_unlocked(struct dm_integrity_c *ic, struct dm_integrity
 		struct dm_integrity_range *last_range =
 			list_first_entry(&ic->wait_list, struct dm_integrity_range, wait_entry);
 		struct task_struct *last_range_task;
-		if (!ranges_overlap(range, last_range))
-			break;
 		last_range_task = last_range->task;
 		list_del(&last_range->wait_entry);
 		if (!add_new_range(ic, last_range, false)) {
@@ -1278,7 +1275,6 @@ static void integrity_sector_checksum(struct dm_integrity_c *ic, sector_t sector
 	unsigned digest_size;
 
 	req->tfm = ic->internal_hash;
-	req->flags = 0;
 
 	r = crypto_shash_init(req);
 	if (unlikely(r < 0)) {
@@ -3185,7 +3181,7 @@ static int dm_integrity_ctr(struct dm_target *ti, unsigned argc, char **argv)
 			journal_watermark = val;
 		else if (sscanf(opt_string, "commit_time:%u%c", &val, &dummy) == 1)
 			sync_msec = val;
-		else if (!memcmp(opt_string, "meta_device:", strlen("meta_device:"))) {
+		else if (!strncmp(opt_string, "meta_device:", strlen("meta_device:"))) {
 			if (ic->meta_dev) {
 				dm_put_device(ti, ic->meta_dev);
 				ic->meta_dev = NULL;
@@ -3204,17 +3200,17 @@ static int dm_integrity_ctr(struct dm_target *ti, unsigned argc, char **argv)
 				goto bad;
 			}
 			ic->sectors_per_block = val >> SECTOR_SHIFT;
-		} else if (!memcmp(opt_string, "internal_hash:", strlen("internal_hash:"))) {
+		} else if (!strncmp(opt_string, "internal_hash:", strlen("internal_hash:"))) {
 			r = get_alg_and_key(opt_string, &ic->internal_hash_alg, &ti->error,
 					    "Invalid internal_hash argument");
 			if (r)
 				goto bad;
-		} else if (!memcmp(opt_string, "journal_crypt:", strlen("journal_crypt:"))) {
+		} else if (!strncmp(opt_string, "journal_crypt:", strlen("journal_crypt:"))) {
 			r = get_alg_and_key(opt_string, &ic->journal_crypt_alg, &ti->error,
 					    "Invalid journal_crypt argument");
 			if (r)
 				goto bad;
-		} else if (!memcmp(opt_string, "journal_mac:", strlen("journal_mac:"))) {
+		} else if (!strncmp(opt_string, "journal_mac:", strlen("journal_mac:"))) {
 			r = get_alg_and_key(opt_string, &ic->journal_mac_alg,  &ti->error,
 					    "Invalid journal_mac argument");
 			if (r)
@@ -3616,7 +3612,7 @@ static struct target_type integrity_target = {
 	.io_hints		= dm_integrity_io_hints,
 };
 
-int __init dm_integrity_init(void)
+static int __init dm_integrity_init(void)
 {
 	int r;
 
@@ -3635,7 +3631,7 @@ int __init dm_integrity_init(void)
 	return r;
 }
 
-void dm_integrity_exit(void)
+static void __exit dm_integrity_exit(void)
 {
 	dm_unregister_target(&integrity_target);
 	kmem_cache_destroy(journal_io_cache);
diff --git a/drivers/md/dm-rq.c b/drivers/md/dm-rq.c
index 09773636602d..b66745bd08bb 100644
--- a/drivers/md/dm-rq.c
+++ b/drivers/md/dm-rq.c
@@ -222,11 +222,14 @@ static void dm_done(struct request *clone, blk_status_t error, bool mapped)
 	}
 
 	if (unlikely(error == BLK_STS_TARGET)) {
-		if (req_op(clone) == REQ_OP_WRITE_SAME &&
-		    !clone->q->limits.max_write_same_sectors)
+		if (req_op(clone) == REQ_OP_DISCARD &&
+		    !clone->q->limits.max_discard_sectors)
+			disable_discard(tio->md);
+		else if (req_op(clone) == REQ_OP_WRITE_SAME &&
+			 !clone->q->limits.max_write_same_sectors)
 			disable_write_same(tio->md);
-		if (req_op(clone) == REQ_OP_WRITE_ZEROES &&
-		    !clone->q->limits.max_write_zeroes_sectors)
+		else if (req_op(clone) == REQ_OP_WRITE_ZEROES &&
+			 !clone->q->limits.max_write_zeroes_sectors)
 			disable_write_zeroes(tio->md);
 	}
 
diff --git a/drivers/md/dm-table.c b/drivers/md/dm-table.c
index ba9481f1bf3c..cde3b49b2a91 100644
--- a/drivers/md/dm-table.c
+++ b/drivers/md/dm-table.c
@@ -1844,6 +1844,36 @@ static bool dm_table_supports_secure_erase(struct dm_table *t)
 	return true;
 }
 
+static int device_requires_stable_pages(struct dm_target *ti,
+					struct dm_dev *dev, sector_t start,
+					sector_t len, void *data)
+{
+	struct request_queue *q = bdev_get_queue(dev->bdev);
+
+	return q && bdi_cap_stable_pages_required(q->backing_dev_info);
+}
+
+/*
+ * If any underlying device requires stable pages, a table must require
+ * them as well.  Only targets that support iterate_devices are considered:
+ * don't want error, zero, etc to require stable pages.
+ */
+static bool dm_table_requires_stable_pages(struct dm_table *t)
+{
+	struct dm_target *ti;
+	unsigned i;
+
+	for (i = 0; i < dm_table_get_num_targets(t); i++) {
+		ti = dm_table_get_target(t, i);
+
+		if (ti->type->iterate_devices &&
+		    ti->type->iterate_devices(ti, device_requires_stable_pages, NULL))
+			return true;
+	}
+
+	return false;
+}
+
 void dm_table_set_restrictions(struct dm_table *t, struct request_queue *q,
 			       struct queue_limits *limits)
 {
@@ -1897,6 +1927,15 @@ void dm_table_set_restrictions(struct dm_table *t, struct request_queue *q,
 	dm_table_verify_integrity(t);
 
 	/*
+	 * Some devices don't use blk_integrity but still want stable pages
+	 * because they do their own checksumming.
+	 */
+	if (dm_table_requires_stable_pages(t))
+		q->backing_dev_info->capabilities |= BDI_CAP_STABLE_WRITES;
+	else
+		q->backing_dev_info->capabilities &= ~BDI_CAP_STABLE_WRITES;
+
+	/*
 	 * Determine whether or not this queue's I/O timings contribute
 	 * to the entropy pool, Only request-based targets use this.
 	 * Clear QUEUE_FLAG_ADD_RANDOM if any underlying device does not
diff --git a/drivers/md/dm.c b/drivers/md/dm.c
index 68d24056d0b1..043f0761e4a0 100644
--- a/drivers/md/dm.c
+++ b/drivers/md/dm.c
@@ -945,6 +945,15 @@ static void dec_pending(struct dm_io *io, blk_status_t error)
 	}
 }
 
+void disable_discard(struct mapped_device *md)
+{
+	struct queue_limits *limits = dm_get_queue_limits(md);
+
+	/* device doesn't really support DISCARD, disable it */
+	limits->max_discard_sectors = 0;
+	blk_queue_flag_clear(QUEUE_FLAG_DISCARD, md->queue);
+}
+
 void disable_write_same(struct mapped_device *md)
 {
 	struct queue_limits *limits = dm_get_queue_limits(md);
@@ -970,11 +979,14 @@ static void clone_endio(struct bio *bio)
 	dm_endio_fn endio = tio->ti->type->end_io;
 
 	if (unlikely(error == BLK_STS_TARGET) && md->type != DM_TYPE_NVME_BIO_BASED) {
-		if (bio_op(bio) == REQ_OP_WRITE_SAME &&
-		    !bio->bi_disk->queue->limits.max_write_same_sectors)
+		if (bio_op(bio) == REQ_OP_DISCARD &&
+		    !bio->bi_disk->queue->limits.max_discard_sectors)
+			disable_discard(md);
+		else if (bio_op(bio) == REQ_OP_WRITE_SAME &&
+			 !bio->bi_disk->queue->limits.max_write_same_sectors)
 			disable_write_same(md);
-		if (bio_op(bio) == REQ_OP_WRITE_ZEROES &&
-		    !bio->bi_disk->queue->limits.max_write_zeroes_sectors)
+		else if (bio_op(bio) == REQ_OP_WRITE_ZEROES &&
+			 !bio->bi_disk->queue->limits.max_write_zeroes_sectors)
 			disable_write_zeroes(md);
 	}
 
@@ -1042,15 +1054,7 @@ int dm_set_target_max_io_len(struct dm_target *ti, sector_t len)
 		return -EINVAL;
 	}
 
-	/*
-	 * BIO based queue uses its own splitting. When multipage bvecs
-	 * is switched on, size of the incoming bio may be too big to
-	 * be handled in some targets, such as crypt.
-	 *
-	 * When these targets are ready for the big bio, we can remove
-	 * the limit.
-	 */
-	ti->max_io_len = min_t(uint32_t, len, BIO_MAX_PAGES * PAGE_SIZE);
+	ti->max_io_len = (uint32_t) len;
 
 	return 0;
 }
diff --git a/drivers/md/persistent-data/dm-block-manager.c b/drivers/md/persistent-data/dm-block-manager.c
index 3972232b8037..749ec268d957 100644
--- a/drivers/md/persistent-data/dm-block-manager.c
+++ b/drivers/md/persistent-data/dm-block-manager.c
@@ -35,7 +35,10 @@
 #define MAX_HOLDERS 4
 #define MAX_STACK 10
 
-typedef unsigned long stack_entries[MAX_STACK];
+struct stack_store {
+	unsigned int	nr_entries;
+	unsigned long	entries[MAX_STACK];
+};
 
 struct block_lock {
 	spinlock_t lock;
@@ -44,8 +47,7 @@ struct block_lock {
 	struct task_struct *holders[MAX_HOLDERS];
 
 #ifdef CONFIG_DM_DEBUG_BLOCK_STACK_TRACING
-	struct stack_trace traces[MAX_HOLDERS];
-	stack_entries entries[MAX_HOLDERS];
+	struct stack_store traces[MAX_HOLDERS];
 #endif
 };
 
@@ -73,7 +75,7 @@ static void __add_holder(struct block_lock *lock, struct task_struct *task)
 {
 	unsigned h = __find_holder(lock, NULL);
 #ifdef CONFIG_DM_DEBUG_BLOCK_STACK_TRACING
-	struct stack_trace *t;
+	struct stack_store *t;
 #endif
 
 	get_task_struct(task);
@@ -81,11 +83,7 @@ static void __add_holder(struct block_lock *lock, struct task_struct *task)
 
 #ifdef CONFIG_DM_DEBUG_BLOCK_STACK_TRACING
 	t = lock->traces + h;
-	t->nr_entries = 0;
-	t->max_entries = MAX_STACK;
-	t->entries = lock->entries[h];
-	t->skip = 2;
-	save_stack_trace(t);
+	t->nr_entries = stack_trace_save(t->entries, MAX_STACK, 2);
 #endif
 }
 
@@ -106,7 +104,8 @@ static int __check_holder(struct block_lock *lock)
 			DMERR("recursive lock detected in metadata");
 #ifdef CONFIG_DM_DEBUG_BLOCK_STACK_TRACING
 			DMERR("previously held here:");
-			print_stack_trace(lock->traces + i, 4);
+			stack_trace_print(lock->traces[i].entries,
+					  lock->traces[i].nr_entries, 4);
 
 			DMERR("subsequent acquisition attempted here:");
 			dump_stack();
diff --git a/drivers/media/pci/dt3155/dt3155.c b/drivers/media/pci/dt3155/dt3155.c
index 17d69bd5d7f1..49677ee889e3 100644
--- a/drivers/media/pci/dt3155/dt3155.c
+++ b/drivers/media/pci/dt3155/dt3155.c
@@ -46,7 +46,6 @@ static int read_i2c_reg(void __iomem *addr, u8 index, u8 *data)
 	u32 tmp = index;
 
 	iowrite32((tmp << 17) | IIC_READ, addr + IIC_CSR2);
-	mmiowb();
 	udelay(45); /* wait at least 43 usec for NEW_CYCLE to clear */
 	if (ioread32(addr + IIC_CSR2) & NEW_CYCLE)
 		return -EIO; /* error: NEW_CYCLE not cleared */
@@ -77,7 +76,6 @@ static int write_i2c_reg(void __iomem *addr, u8 index, u8 data)
 	u32 tmp = index;
 
 	iowrite32((tmp << 17) | IIC_WRITE | data, addr + IIC_CSR2);
-	mmiowb();
 	udelay(65); /* wait at least 63 usec for NEW_CYCLE to clear */
 	if (ioread32(addr + IIC_CSR2) & NEW_CYCLE)
 		return -EIO; /* error: NEW_CYCLE not cleared */
@@ -104,7 +102,6 @@ static void write_i2c_reg_nowait(void __iomem *addr, u8 index, u8 data)
 	u32 tmp = index;
 
 	iowrite32((tmp << 17) | IIC_WRITE | data, addr + IIC_CSR2);
-	mmiowb();
 }
 
 /**
@@ -264,7 +261,6 @@ static irqreturn_t dt3155_irq_handler_even(int irq, void *dev_id)
 						FLD_DN_ODD | FLD_DN_EVEN |
 						CAP_CONT_EVEN | CAP_CONT_ODD,
 							ipd->regs + CSR1);
-		mmiowb();
 	}
 
 	spin_lock(&ipd->lock);
@@ -282,7 +278,6 @@ static irqreturn_t dt3155_irq_handler_even(int irq, void *dev_id)
 		iowrite32(dma_addr + ipd->width, ipd->regs + ODD_DMA_START);
 		iowrite32(ipd->width, ipd->regs + EVEN_DMA_STRIDE);
 		iowrite32(ipd->width, ipd->regs + ODD_DMA_STRIDE);
-		mmiowb();
 	}
 
 	/* enable interrupts, clear all irq flags */
@@ -437,12 +432,10 @@ static int dt3155_init_board(struct dt3155_priv *pd)
 	/*  resetting the adapter  */
 	iowrite32(ADDR_ERR_ODD | ADDR_ERR_EVEN | FLD_CRPT_ODD | FLD_CRPT_EVEN |
 			FLD_DN_ODD | FLD_DN_EVEN, pd->regs + CSR1);
-	mmiowb();
 	msleep(20);
 
 	/*  initializing adapter registers  */
 	iowrite32(FIFO_EN | SRST, pd->regs + CSR1);
-	mmiowb();
 	iowrite32(0xEEEEEE01, pd->regs + EVEN_PIXEL_FMT);
 	iowrite32(0xEEEEEE01, pd->regs + ODD_PIXEL_FMT);
 	iowrite32(0x00000020, pd->regs + FIFO_TRIGER);
@@ -454,7 +447,6 @@ static int dt3155_init_board(struct dt3155_priv *pd)
 	iowrite32(0, pd->regs + MASK_LENGTH);
 	iowrite32(0x0005007C, pd->regs + FIFO_FLAG_CNT);
 	iowrite32(0x01010101, pd->regs + IIC_CLK_DUR);
-	mmiowb();
 
 	/* verifying that we have a DT3155 board (not just a SAA7116 chip) */
 	read_i2c_reg(pd->regs, DT_ID, &tmp);
diff --git a/drivers/memstick/host/jmb38x_ms.c b/drivers/memstick/host/jmb38x_ms.c
index bcdca9fbef51..e3a5af65dbce 100644
--- a/drivers/memstick/host/jmb38x_ms.c
+++ b/drivers/memstick/host/jmb38x_ms.c
@@ -644,7 +644,6 @@ static int jmb38x_ms_reset(struct jmb38x_ms_host *host)
 	writel(HOST_CONTROL_RESET_REQ | HOST_CONTROL_CLOCK_EN
 	       | readl(host->addr + HOST_CONTROL),
 	       host->addr + HOST_CONTROL);
-	mmiowb();
 
 	for (cnt = 0; cnt < 20; ++cnt) {
 		if (!(HOST_CONTROL_RESET_REQ
@@ -659,7 +658,6 @@ reset_next:
 	writel(HOST_CONTROL_RESET | HOST_CONTROL_CLOCK_EN
 	       | readl(host->addr + HOST_CONTROL),
 	       host->addr + HOST_CONTROL);
-	mmiowb();
 
 	for (cnt = 0; cnt < 20; ++cnt) {
 		if (!(HOST_CONTROL_RESET
@@ -672,7 +670,6 @@ reset_next:
 	return -EIO;
 
 reset_ok:
-	mmiowb();
 	writel(INT_STATUS_ALL, host->addr + INT_SIGNAL_ENABLE);
 	writel(INT_STATUS_ALL, host->addr + INT_STATUS_ENABLE);
 	return 0;
@@ -1009,7 +1006,6 @@ static void jmb38x_ms_remove(struct pci_dev *dev)
 		tasklet_kill(&host->notify);
 		writel(0, host->addr + INT_SIGNAL_ENABLE);
 		writel(0, host->addr + INT_STATUS_ENABLE);
-		mmiowb();
 		dev_dbg(&jm->pdev->dev, "interrupts off\n");
 		spin_lock_irqsave(&host->lock, flags);
 		if (host->req) {
diff --git a/drivers/mfd/Kconfig b/drivers/mfd/Kconfig
index 0ce2d8dfc5f1..26ad6468d13a 100644
--- a/drivers/mfd/Kconfig
+++ b/drivers/mfd/Kconfig
@@ -1246,7 +1246,7 @@ config MFD_STA2X11
 
 config MFD_SUN6I_PRCM
 	bool "Allwinner A31 PRCM controller"
-	depends on ARCH_SUNXI
+	depends on ARCH_SUNXI || COMPILE_TEST
 	select MFD_CORE
 	help
 	  Support for the PRCM (Power/Reset/Clock Management) unit available
diff --git a/drivers/mfd/sprd-sc27xx-spi.c b/drivers/mfd/sprd-sc27xx-spi.c
index 69df27769c21..43ac71691fe4 100644
--- a/drivers/mfd/sprd-sc27xx-spi.c
+++ b/drivers/mfd/sprd-sc27xx-spi.c
@@ -53,67 +53,67 @@ static const struct sprd_pmic_data sc2731_data = {
 static const struct mfd_cell sprd_pmic_devs[] = {
 	{
 		.name = "sc27xx-wdt",
-		.of_compatible = "sprd,sc27xx-wdt",
+		.of_compatible = "sprd,sc2731-wdt",
 	}, {
 		.name = "sc27xx-rtc",
-		.of_compatible = "sprd,sc27xx-rtc",
+		.of_compatible = "sprd,sc2731-rtc",
 	}, {
 		.name = "sc27xx-charger",
-		.of_compatible = "sprd,sc27xx-charger",
+		.of_compatible = "sprd,sc2731-charger",
 	}, {
 		.name = "sc27xx-chg-timer",
-		.of_compatible = "sprd,sc27xx-chg-timer",
+		.of_compatible = "sprd,sc2731-chg-timer",
 	}, {
 		.name = "sc27xx-fast-chg",
-		.of_compatible = "sprd,sc27xx-fast-chg",
+		.of_compatible = "sprd,sc2731-fast-chg",
 	}, {
 		.name = "sc27xx-chg-wdt",
-		.of_compatible = "sprd,sc27xx-chg-wdt",
+		.of_compatible = "sprd,sc2731-chg-wdt",
 	}, {
 		.name = "sc27xx-typec",
-		.of_compatible = "sprd,sc27xx-typec",
+		.of_compatible = "sprd,sc2731-typec",
 	}, {
 		.name = "sc27xx-flash",
-		.of_compatible = "sprd,sc27xx-flash",
+		.of_compatible = "sprd,sc2731-flash",
 	}, {
 		.name = "sc27xx-eic",
-		.of_compatible = "sprd,sc27xx-eic",
+		.of_compatible = "sprd,sc2731-eic",
 	}, {
 		.name = "sc27xx-efuse",
-		.of_compatible = "sprd,sc27xx-efuse",
+		.of_compatible = "sprd,sc2731-efuse",
 	}, {
 		.name = "sc27xx-thermal",
-		.of_compatible = "sprd,sc27xx-thermal",
+		.of_compatible = "sprd,sc2731-thermal",
 	}, {
 		.name = "sc27xx-adc",
-		.of_compatible = "sprd,sc27xx-adc",
+		.of_compatible = "sprd,sc2731-adc",
 	}, {
 		.name = "sc27xx-audio-codec",
-		.of_compatible = "sprd,sc27xx-audio-codec",
+		.of_compatible = "sprd,sc2731-audio-codec",
 	}, {
 		.name = "sc27xx-regulator",
-		.of_compatible = "sprd,sc27xx-regulator",
+		.of_compatible = "sprd,sc2731-regulator",
 	}, {
 		.name = "sc27xx-vibrator",
-		.of_compatible = "sprd,sc27xx-vibrator",
+		.of_compatible = "sprd,sc2731-vibrator",
 	}, {
 		.name = "sc27xx-keypad-led",
-		.of_compatible = "sprd,sc27xx-keypad-led",
+		.of_compatible = "sprd,sc2731-keypad-led",
 	}, {
 		.name = "sc27xx-bltc",
-		.of_compatible = "sprd,sc27xx-bltc",
+		.of_compatible = "sprd,sc2731-bltc",
 	}, {
 		.name = "sc27xx-fgu",
-		.of_compatible = "sprd,sc27xx-fgu",
+		.of_compatible = "sprd,sc2731-fgu",
 	}, {
 		.name = "sc27xx-7sreset",
-		.of_compatible = "sprd,sc27xx-7sreset",
+		.of_compatible = "sprd,sc2731-7sreset",
 	}, {
 		.name = "sc27xx-poweroff",
-		.of_compatible = "sprd,sc27xx-poweroff",
+		.of_compatible = "sprd,sc2731-poweroff",
 	}, {
 		.name = "sc27xx-syscon",
-		.of_compatible = "sprd,sc27xx-syscon",
+		.of_compatible = "sprd,sc2731-syscon",
 	},
 };
 
diff --git a/drivers/mfd/twl-core.c b/drivers/mfd/twl-core.c
index 299016bc46d9..104477b512a2 100644
--- a/drivers/mfd/twl-core.c
+++ b/drivers/mfd/twl-core.c
@@ -1245,6 +1245,28 @@ free:
 	return status;
 }
 
+static int __maybe_unused twl_suspend(struct device *dev)
+{
+	struct i2c_client *client = to_i2c_client(dev);
+
+	if (client->irq)
+		disable_irq(client->irq);
+
+	return 0;
+}
+
+static int __maybe_unused twl_resume(struct device *dev)
+{
+	struct i2c_client *client = to_i2c_client(dev);
+
+	if (client->irq)
+		enable_irq(client->irq);
+
+	return 0;
+}
+
+static SIMPLE_DEV_PM_OPS(twl_dev_pm_ops, twl_suspend, twl_resume);
+
 static const struct i2c_device_id twl_ids[] = {
 	{ "twl4030", TWL4030_VAUX2 },	/* "Triton 2" */
 	{ "twl5030", 0 },		/* T2 updated */
@@ -1262,6 +1284,7 @@ static const struct i2c_device_id twl_ids[] = {
 /* One Client Driver , 4 Clients */
 static struct i2c_driver twl_driver = {
 	.driver.name	= DRIVER_NAME,
+	.driver.pm	= &twl_dev_pm_ops,
 	.id_table	= twl_ids,
 	.probe		= twl_probe,
 	.remove		= twl_remove,
diff --git a/drivers/mfd/wm831x-core.c b/drivers/mfd/wm831x-core.c
index 25fbbaf39cb9..21bae64e0451 100644
--- a/drivers/mfd/wm831x-core.c
+++ b/drivers/mfd/wm831x-core.c
@@ -34,7 +34,7 @@
 /* Current settings - values are 2*2^(reg_val/4) microamps.  These are
  * exported since they are used by multiple drivers.
  */
-int wm831x_isinkv_values[WM831X_ISINK_MAX_ISEL + 1] = {
+const unsigned int wm831x_isinkv_values[WM831X_ISINK_MAX_ISEL + 1] = {
 	2,
 	2,
 	3,
diff --git a/drivers/mfd/wm8400-core.c b/drivers/mfd/wm8400-core.c
index 79756c83f5f0..cf067424a156 100644
--- a/drivers/mfd/wm8400-core.c
+++ b/drivers/mfd/wm8400-core.c
@@ -35,12 +35,6 @@ static bool wm8400_volatile(struct device *dev, unsigned int reg)
 	}
 }
 
-int wm8400_block_read(struct wm8400 *wm8400, u8 reg, int count, u16 *data)
-{
-	return regmap_bulk_read(wm8400->regmap, reg, data, count);
-}
-EXPORT_SYMBOL_GPL(wm8400_block_read);
-
 static int wm8400_register_codec(struct wm8400 *wm8400)
 {
 	const struct mfd_cell cell = {
diff --git a/drivers/misc/fastrpc.c b/drivers/misc/fastrpc.c
index 39f832d27288..36d0d5c9cfba 100644
--- a/drivers/misc/fastrpc.c
+++ b/drivers/misc/fastrpc.c
@@ -1184,6 +1184,7 @@ static int fastrpc_cb_probe(struct platform_device *pdev)
 	struct fastrpc_session_ctx *sess;
 	struct device *dev = &pdev->dev;
 	int i, sessions = 0;
+	int rc;
 
 	cctx = dev_get_drvdata(dev->parent);
 	if (!cctx)
@@ -1213,7 +1214,11 @@ static int fastrpc_cb_probe(struct platform_device *pdev)
 	}
 	cctx->sesscount++;
 	spin_unlock(&cctx->lock);
-	dma_set_mask(dev, DMA_BIT_MASK(32));
+	rc = dma_set_mask(dev, DMA_BIT_MASK(32));
+	if (rc) {
+		dev_err(dev, "32-bit DMA enable failed\n");
+		return rc;
+	}
 
 	return 0;
 }
diff --git a/drivers/misc/habanalabs/command_submission.c b/drivers/misc/habanalabs/command_submission.c
index 3525236ed8d9..19c84214a7ea 100644
--- a/drivers/misc/habanalabs/command_submission.c
+++ b/drivers/misc/habanalabs/command_submission.c
@@ -179,6 +179,12 @@ static void cs_do_release(struct kref *ref)
 
 	/* We also need to update CI for internal queues */
 	if (cs->submitted) {
+		int cs_cnt = atomic_dec_return(&hdev->cs_active_cnt);
+
+		WARN_ONCE((cs_cnt < 0),
+			"hl%d: error in CS active cnt %d\n",
+			hdev->id, cs_cnt);
+
 		hl_int_hw_queue_update_ci(cs);
 
 		spin_lock(&hdev->hw_queues_mirror_lock);
diff --git a/drivers/misc/habanalabs/debugfs.c b/drivers/misc/habanalabs/debugfs.c
index a53c12aff6ad..974a87789bd8 100644
--- a/drivers/misc/habanalabs/debugfs.c
+++ b/drivers/misc/habanalabs/debugfs.c
@@ -232,6 +232,7 @@ static int vm_show(struct seq_file *s, void *data)
 	struct hl_vm_phys_pg_pack *phys_pg_pack = NULL;
 	enum vm_type_t *vm_type;
 	bool once = true;
+	u64 j;
 	int i;
 
 	if (!dev_entry->hdev->mmu_enable)
@@ -260,7 +261,7 @@ static int vm_show(struct seq_file *s, void *data)
 			} else {
 				phys_pg_pack = hnode->ptr;
 				seq_printf(s,
-					"    0x%-14llx      %-10u       %-4u\n",
+					"    0x%-14llx      %-10llu       %-4u\n",
 					hnode->vaddr, phys_pg_pack->total_size,
 					phys_pg_pack->handle);
 			}
@@ -282,9 +283,9 @@ static int vm_show(struct seq_file *s, void *data)
 						phys_pg_pack->page_size);
 			seq_puts(s, "   physical address\n");
 			seq_puts(s, "---------------------\n");
-			for (i = 0 ; i < phys_pg_pack->npages ; i++) {
+			for (j = 0 ; j < phys_pg_pack->npages ; j++) {
 				seq_printf(s, "    0x%-14llx\n",
-						phys_pg_pack->pages[i]);
+						phys_pg_pack->pages[j]);
 			}
 		}
 		spin_unlock(&vm->idr_lock);
diff --git a/drivers/misc/habanalabs/device.c b/drivers/misc/habanalabs/device.c
index de46aa6ed154..77d51be66c7e 100644
--- a/drivers/misc/habanalabs/device.c
+++ b/drivers/misc/habanalabs/device.c
@@ -11,6 +11,8 @@
 #include <linux/sched/signal.h>
 #include <linux/hwmon.h>
 
+#define HL_PLDM_PENDING_RESET_PER_SEC	(HL_PENDING_RESET_PER_SEC * 10)
+
 bool hl_device_disabled_or_in_reset(struct hl_device *hdev)
 {
 	if ((hdev->disabled) || (atomic_read(&hdev->in_reset)))
@@ -216,6 +218,7 @@ static int device_early_init(struct hl_device *hdev)
 	spin_lock_init(&hdev->hw_queues_mirror_lock);
 	atomic_set(&hdev->in_reset, 0);
 	atomic_set(&hdev->fd_open_cnt, 0);
+	atomic_set(&hdev->cs_active_cnt, 0);
 
 	return 0;
 
@@ -413,6 +416,27 @@ int hl_device_suspend(struct hl_device *hdev)
 
 	pci_save_state(hdev->pdev);
 
+	/* Block future CS/VM/JOB completion operations */
+	rc = atomic_cmpxchg(&hdev->in_reset, 0, 1);
+	if (rc) {
+		dev_err(hdev->dev, "Can't suspend while in reset\n");
+		return -EIO;
+	}
+
+	/* This blocks all other stuff that is not blocked by in_reset */
+	hdev->disabled = true;
+
+	/*
+	 * Flush anyone that is inside the critical section of enqueue
+	 * jobs to the H/W
+	 */
+	hdev->asic_funcs->hw_queues_lock(hdev);
+	hdev->asic_funcs->hw_queues_unlock(hdev);
+
+	/* Flush processes that are sending message to CPU */
+	mutex_lock(&hdev->send_cpu_message_lock);
+	mutex_unlock(&hdev->send_cpu_message_lock);
+
 	rc = hdev->asic_funcs->suspend(hdev);
 	if (rc)
 		dev_err(hdev->dev,
@@ -440,21 +464,38 @@ int hl_device_resume(struct hl_device *hdev)
 
 	pci_set_power_state(hdev->pdev, PCI_D0);
 	pci_restore_state(hdev->pdev);
-	rc = pci_enable_device(hdev->pdev);
+	rc = pci_enable_device_mem(hdev->pdev);
 	if (rc) {
 		dev_err(hdev->dev,
 			"Failed to enable PCI device in resume\n");
 		return rc;
 	}
 
+	pci_set_master(hdev->pdev);
+
 	rc = hdev->asic_funcs->resume(hdev);
 	if (rc) {
-		dev_err(hdev->dev,
-			"Failed to enable PCI access from device CPU\n");
-		return rc;
+		dev_err(hdev->dev, "Failed to resume device after suspend\n");
+		goto disable_device;
+	}
+
+
+	hdev->disabled = false;
+	atomic_set(&hdev->in_reset, 0);
+
+	rc = hl_device_reset(hdev, true, false);
+	if (rc) {
+		dev_err(hdev->dev, "Failed to reset device during resume\n");
+		goto disable_device;
 	}
 
 	return 0;
+
+disable_device:
+	pci_clear_master(hdev->pdev);
+	pci_disable_device(hdev->pdev);
+
+	return rc;
 }
 
 static void hl_device_hard_reset_pending(struct work_struct *work)
@@ -462,9 +503,16 @@ static void hl_device_hard_reset_pending(struct work_struct *work)
 	struct hl_device_reset_work *device_reset_work =
 		container_of(work, struct hl_device_reset_work, reset_work);
 	struct hl_device *hdev = device_reset_work->hdev;
-	u16 pending_cnt = HL_PENDING_RESET_PER_SEC;
+	u16 pending_total, pending_cnt;
 	struct task_struct *task = NULL;
 
+	if (hdev->pldm)
+		pending_total = HL_PLDM_PENDING_RESET_PER_SEC;
+	else
+		pending_total = HL_PENDING_RESET_PER_SEC;
+
+	pending_cnt = pending_total;
+
 	/* Flush all processes that are inside hl_open */
 	mutex_lock(&hdev->fd_open_cnt_lock);
 
@@ -489,6 +537,19 @@ static void hl_device_hard_reset_pending(struct work_struct *work)
 		}
 	}
 
+	pending_cnt = pending_total;
+
+	while ((atomic_read(&hdev->fd_open_cnt)) && (pending_cnt)) {
+
+		pending_cnt--;
+
+		ssleep(1);
+	}
+
+	if (atomic_read(&hdev->fd_open_cnt))
+		dev_crit(hdev->dev,
+			"Going to hard reset with open user contexts\n");
+
 	mutex_unlock(&hdev->fd_open_cnt_lock);
 
 	hl_device_reset(hdev, true, true);
diff --git a/drivers/misc/habanalabs/goya/goya.c b/drivers/misc/habanalabs/goya/goya.c
index 238dd57c541b..3c509e19d69d 100644
--- a/drivers/misc/habanalabs/goya/goya.c
+++ b/drivers/misc/habanalabs/goya/goya.c
@@ -1201,15 +1201,6 @@ static int goya_stop_external_queues(struct hl_device *hdev)
 	return retval;
 }
 
-static void goya_resume_external_queues(struct hl_device *hdev)
-{
-	WREG32(mmDMA_QM_0_GLBL_CFG1, 0);
-	WREG32(mmDMA_QM_1_GLBL_CFG1, 0);
-	WREG32(mmDMA_QM_2_GLBL_CFG1, 0);
-	WREG32(mmDMA_QM_3_GLBL_CFG1, 0);
-	WREG32(mmDMA_QM_4_GLBL_CFG1, 0);
-}
-
 /*
  * goya_init_cpu_queues - Initialize PQ/CQ/EQ of CPU
  *
@@ -1697,12 +1688,11 @@ static void goya_init_golden_registers(struct hl_device *hdev)
 
 	/*
 	 * Workaround for H2 #HW-23 bug
-	 * Set DMA max outstanding read requests to 240 on DMA CH 1. Set it
-	 * to 16 on KMD DMA
-	 * We need to limit only these DMAs because the user can only read
+	 * Set DMA max outstanding read requests to 240 on DMA CH 1.
+	 * This limitation is still large enough to not affect Gen4 bandwidth.
+	 * We need to only limit that DMA channel because the user can only read
 	 * from Host using DMA CH 1
 	 */
-	WREG32(mmDMA_CH_0_CFG0, 0x0fff0010);
 	WREG32(mmDMA_CH_1_CFG0, 0x0fff00F0);
 
 	goya->hw_cap_initialized |= HW_CAP_GOLDEN;
@@ -2178,36 +2168,6 @@ static int goya_stop_internal_queues(struct hl_device *hdev)
 	return retval;
 }
 
-static void goya_resume_internal_queues(struct hl_device *hdev)
-{
-	WREG32(mmMME_QM_GLBL_CFG1, 0);
-	WREG32(mmMME_CMDQ_GLBL_CFG1, 0);
-
-	WREG32(mmTPC0_QM_GLBL_CFG1, 0);
-	WREG32(mmTPC0_CMDQ_GLBL_CFG1, 0);
-
-	WREG32(mmTPC1_QM_GLBL_CFG1, 0);
-	WREG32(mmTPC1_CMDQ_GLBL_CFG1, 0);
-
-	WREG32(mmTPC2_QM_GLBL_CFG1, 0);
-	WREG32(mmTPC2_CMDQ_GLBL_CFG1, 0);
-
-	WREG32(mmTPC3_QM_GLBL_CFG1, 0);
-	WREG32(mmTPC3_CMDQ_GLBL_CFG1, 0);
-
-	WREG32(mmTPC4_QM_GLBL_CFG1, 0);
-	WREG32(mmTPC4_CMDQ_GLBL_CFG1, 0);
-
-	WREG32(mmTPC5_QM_GLBL_CFG1, 0);
-	WREG32(mmTPC5_CMDQ_GLBL_CFG1, 0);
-
-	WREG32(mmTPC6_QM_GLBL_CFG1, 0);
-	WREG32(mmTPC6_CMDQ_GLBL_CFG1, 0);
-
-	WREG32(mmTPC7_QM_GLBL_CFG1, 0);
-	WREG32(mmTPC7_CMDQ_GLBL_CFG1, 0);
-}
-
 static void goya_dma_stall(struct hl_device *hdev)
 {
 	WREG32(mmDMA_QM_0_GLBL_CFG1, 1 << DMA_QM_0_GLBL_CFG1_DMA_STOP_SHIFT);
@@ -2905,20 +2865,6 @@ int goya_suspend(struct hl_device *hdev)
 {
 	int rc;
 
-	rc = goya_stop_internal_queues(hdev);
-
-	if (rc) {
-		dev_err(hdev->dev, "failed to stop internal queues\n");
-		return rc;
-	}
-
-	rc = goya_stop_external_queues(hdev);
-
-	if (rc) {
-		dev_err(hdev->dev, "failed to stop external queues\n");
-		return rc;
-	}
-
 	rc = goya_send_pci_access_msg(hdev, ARMCP_PACKET_DISABLE_PCI_ACCESS);
 	if (rc)
 		dev_err(hdev->dev, "Failed to disable PCI access from CPU\n");
@@ -2928,15 +2874,7 @@ int goya_suspend(struct hl_device *hdev)
 
 int goya_resume(struct hl_device *hdev)
 {
-	int rc;
-
-	goya_resume_external_queues(hdev);
-	goya_resume_internal_queues(hdev);
-
-	rc = goya_send_pci_access_msg(hdev, ARMCP_PACKET_ENABLE_PCI_ACCESS);
-	if (rc)
-		dev_err(hdev->dev, "Failed to enable PCI access from CPU\n");
-	return rc;
+	return goya_init_iatu(hdev);
 }
 
 static int goya_cb_mmap(struct hl_device *hdev, struct vm_area_struct *vma,
@@ -3070,7 +3008,7 @@ void *goya_get_int_queue_base(struct hl_device *hdev, u32 queue_id,
 
 	*dma_handle = hdev->asic_prop.sram_base_address;
 
-	base = hdev->pcie_bar[SRAM_CFG_BAR_ID];
+	base = (void *) hdev->pcie_bar[SRAM_CFG_BAR_ID];
 
 	switch (queue_id) {
 	case GOYA_QUEUE_ID_MME:
@@ -3754,7 +3692,7 @@ static int goya_validate_dma_pkt_mmu(struct hl_device *hdev,
 	 * WA for HW-23.
 	 * We can't allow user to read from Host using QMANs other than 1.
 	 */
-	if (parser->hw_queue_id > GOYA_QUEUE_ID_DMA_1 &&
+	if (parser->hw_queue_id != GOYA_QUEUE_ID_DMA_1 &&
 		hl_mem_area_inside_range(le64_to_cpu(user_dma_pkt->src_addr),
 				le32_to_cpu(user_dma_pkt->tsize),
 				hdev->asic_prop.va_space_host_start_address,
diff --git a/drivers/misc/habanalabs/habanalabs.h b/drivers/misc/habanalabs/habanalabs.h
index a7c95e9f9b9a..a8ee52c880cd 100644
--- a/drivers/misc/habanalabs/habanalabs.h
+++ b/drivers/misc/habanalabs/habanalabs.h
@@ -793,11 +793,11 @@ struct hl_vm_hash_node {
  * struct hl_vm_phys_pg_pack - physical page pack.
  * @vm_type: describes the type of the virtual area descriptor.
  * @pages: the physical page array.
+ * @npages: num physical pages in the pack.
+ * @total_size: total size of all the pages in this list.
  * @mapping_cnt: number of shared mappings.
  * @asid: the context related to this list.
- * @npages: num physical pages in the pack.
  * @page_size: size of each page in the pack.
- * @total_size: total size of all the pages in this list.
  * @flags: HL_MEM_* flags related to this list.
  * @handle: the provided handle related to this list.
  * @offset: offset from the first page.
@@ -807,11 +807,11 @@ struct hl_vm_hash_node {
 struct hl_vm_phys_pg_pack {
 	enum vm_type_t		vm_type; /* must be first */
 	u64			*pages;
+	u64			npages;
+	u64			total_size;
 	atomic_t		mapping_cnt;
 	u32			asid;
-	u32			npages;
 	u32			page_size;
-	u32			total_size;
 	u32			flags;
 	u32			handle;
 	u32			offset;
@@ -1056,13 +1056,15 @@ struct hl_device_reset_work {
  * @cb_pool_lock: protects the CB pool.
  * @user_ctx: current user context executing.
  * @dram_used_mem: current DRAM memory consumption.
- * @in_reset: is device in reset flow.
- * @curr_pll_profile: current PLL profile.
- * @fd_open_cnt: number of open user processes.
  * @timeout_jiffies: device CS timeout value.
  * @max_power: the max power of the device, as configured by the sysadmin. This
  *             value is saved so in case of hard-reset, KMD will restore this
  *             value and update the F/W after the re-initialization
+ * @in_reset: is device in reset flow.
+ * @curr_pll_profile: current PLL profile.
+ * @fd_open_cnt: number of open user processes.
+ * @cs_active_cnt: number of active command submissions on this device (active
+ *                 means already in H/W queues)
  * @major: habanalabs KMD major.
  * @high_pll: high PLL profile frequency.
  * @soft_reset_cnt: number of soft reset since KMD loading.
@@ -1128,11 +1130,12 @@ struct hl_device {
 	struct hl_ctx			*user_ctx;
 
 	atomic64_t			dram_used_mem;
+	u64				timeout_jiffies;
+	u64				max_power;
 	atomic_t			in_reset;
 	atomic_t			curr_pll_profile;
 	atomic_t			fd_open_cnt;
-	u64				timeout_jiffies;
-	u64				max_power;
+	atomic_t			cs_active_cnt;
 	u32				major;
 	u32				high_pll;
 	u32				soft_reset_cnt;
diff --git a/drivers/misc/habanalabs/hw_queue.c b/drivers/misc/habanalabs/hw_queue.c
index 67bece26417c..ef3bb6951360 100644
--- a/drivers/misc/habanalabs/hw_queue.c
+++ b/drivers/misc/habanalabs/hw_queue.c
@@ -370,12 +370,13 @@ int hl_hw_queue_schedule_cs(struct hl_cs *cs)
 		spin_unlock(&hdev->hw_queues_mirror_lock);
 	}
 
-	list_for_each_entry_safe(job, tmp, &cs->job_list, cs_node) {
+	atomic_inc(&hdev->cs_active_cnt);
+
+	list_for_each_entry_safe(job, tmp, &cs->job_list, cs_node)
 		if (job->ext_queue)
 			ext_hw_queue_schedule_job(job);
 		else
 			int_hw_queue_schedule_job(job);
-	}
 
 	cs->submitted = true;
 
diff --git a/drivers/misc/habanalabs/memory.c b/drivers/misc/habanalabs/memory.c
index 3a12fd1a5274..ce1fda40a8b8 100644
--- a/drivers/misc/habanalabs/memory.c
+++ b/drivers/misc/habanalabs/memory.c
@@ -56,9 +56,9 @@ static int alloc_device_memory(struct hl_ctx *ctx, struct hl_mem_in *args,
 	struct hl_device *hdev = ctx->hdev;
 	struct hl_vm *vm = &hdev->vm;
 	struct hl_vm_phys_pg_pack *phys_pg_pack;
-	u64 paddr = 0;
-	u32 total_size, num_pgs, num_curr_pgs, page_size, page_shift;
-	int handle, rc, i;
+	u64 paddr = 0, total_size, num_pgs, i;
+	u32 num_curr_pgs, page_size, page_shift;
+	int handle, rc;
 	bool contiguous;
 
 	num_curr_pgs = 0;
@@ -73,7 +73,7 @@ static int alloc_device_memory(struct hl_ctx *ctx, struct hl_mem_in *args,
 		paddr = (u64) gen_pool_alloc(vm->dram_pg_pool, total_size);
 		if (!paddr) {
 			dev_err(hdev->dev,
-				"failed to allocate %u huge contiguous pages\n",
+				"failed to allocate %llu huge contiguous pages\n",
 				num_pgs);
 			return -ENOMEM;
 		}
@@ -93,7 +93,7 @@ static int alloc_device_memory(struct hl_ctx *ctx, struct hl_mem_in *args,
 	phys_pg_pack->flags = args->flags;
 	phys_pg_pack->contiguous = contiguous;
 
-	phys_pg_pack->pages = kcalloc(num_pgs, sizeof(u64), GFP_KERNEL);
+	phys_pg_pack->pages = kvmalloc_array(num_pgs, sizeof(u64), GFP_KERNEL);
 	if (!phys_pg_pack->pages) {
 		rc = -ENOMEM;
 		goto pages_arr_err;
@@ -148,7 +148,7 @@ page_err:
 			gen_pool_free(vm->dram_pg_pool, phys_pg_pack->pages[i],
 					page_size);
 
-	kfree(phys_pg_pack->pages);
+	kvfree(phys_pg_pack->pages);
 pages_arr_err:
 	kfree(phys_pg_pack);
 pages_pack_err:
@@ -267,7 +267,7 @@ static void free_phys_pg_pack(struct hl_device *hdev,
 		struct hl_vm_phys_pg_pack *phys_pg_pack)
 {
 	struct hl_vm *vm = &hdev->vm;
-	int i;
+	u64 i;
 
 	if (!phys_pg_pack->created_from_userptr) {
 		if (phys_pg_pack->contiguous) {
@@ -288,7 +288,7 @@ static void free_phys_pg_pack(struct hl_device *hdev,
 		}
 	}
 
-	kfree(phys_pg_pack->pages);
+	kvfree(phys_pg_pack->pages);
 	kfree(phys_pg_pack);
 }
 
@@ -519,7 +519,7 @@ static inline int add_va_block(struct hl_device *hdev,
  * - Return the start address of the virtual block
  */
 static u64 get_va_block(struct hl_device *hdev,
-		struct hl_va_range *va_range, u32 size, u64 hint_addr,
+		struct hl_va_range *va_range, u64 size, u64 hint_addr,
 		bool is_userptr)
 {
 	struct hl_vm_va_block *va_block, *new_va_block = NULL;
@@ -577,7 +577,8 @@ static u64 get_va_block(struct hl_device *hdev,
 	}
 
 	if (!new_va_block) {
-		dev_err(hdev->dev, "no available va block for size %u\n", size);
+		dev_err(hdev->dev, "no available va block for size %llu\n",
+				size);
 		goto out;
 	}
 
@@ -648,8 +649,8 @@ static int init_phys_pg_pack_from_userptr(struct hl_ctx *ctx,
 	struct hl_vm_phys_pg_pack *phys_pg_pack;
 	struct scatterlist *sg;
 	dma_addr_t dma_addr;
-	u64 page_mask;
-	u32 npages, total_npages, page_size = PAGE_SIZE;
+	u64 page_mask, total_npages;
+	u32 npages, page_size = PAGE_SIZE;
 	bool first = true, is_huge_page_opt = true;
 	int rc, i, j;
 
@@ -691,7 +692,8 @@ static int init_phys_pg_pack_from_userptr(struct hl_ctx *ctx,
 
 	page_mask = ~(((u64) page_size) - 1);
 
-	phys_pg_pack->pages = kcalloc(total_npages, sizeof(u64), GFP_KERNEL);
+	phys_pg_pack->pages = kvmalloc_array(total_npages, sizeof(u64),
+						GFP_KERNEL);
 	if (!phys_pg_pack->pages) {
 		rc = -ENOMEM;
 		goto page_pack_arr_mem_err;
@@ -750,9 +752,9 @@ static int map_phys_page_pack(struct hl_ctx *ctx, u64 vaddr,
 		struct hl_vm_phys_pg_pack *phys_pg_pack)
 {
 	struct hl_device *hdev = ctx->hdev;
-	u64 next_vaddr = vaddr, paddr;
+	u64 next_vaddr = vaddr, paddr, mapped_pg_cnt = 0, i;
 	u32 page_size = phys_pg_pack->page_size;
-	int i, rc = 0, mapped_pg_cnt = 0;
+	int rc = 0;
 
 	for (i = 0 ; i < phys_pg_pack->npages ; i++) {
 		paddr = phys_pg_pack->pages[i];
@@ -764,7 +766,7 @@ static int map_phys_page_pack(struct hl_ctx *ctx, u64 vaddr,
 		rc = hl_mmu_map(ctx, next_vaddr, paddr, page_size);
 		if (rc) {
 			dev_err(hdev->dev,
-				"map failed for handle %u, npages: %d, mapped: %d",
+				"map failed for handle %u, npages: %llu, mapped: %llu",
 				phys_pg_pack->handle, phys_pg_pack->npages,
 				mapped_pg_cnt);
 			goto err;
@@ -985,10 +987,10 @@ static int unmap_device_va(struct hl_ctx *ctx, u64 vaddr)
 	struct hl_vm_hash_node *hnode = NULL;
 	struct hl_userptr *userptr = NULL;
 	enum vm_type_t *vm_type;
-	u64 next_vaddr;
+	u64 next_vaddr, i;
 	u32 page_size;
 	bool is_userptr;
-	int i, rc;
+	int rc;
 
 	/* protect from double entrance */
 	mutex_lock(&ctx->mem_hash_lock);
diff --git a/drivers/misc/habanalabs/mmu.c b/drivers/misc/habanalabs/mmu.c
index 2f2e99cb2743..3a5a2cec8305 100644
--- a/drivers/misc/habanalabs/mmu.c
+++ b/drivers/misc/habanalabs/mmu.c
@@ -832,7 +832,7 @@ err:
 int hl_mmu_map(struct hl_ctx *ctx, u64 virt_addr, u64 phys_addr, u32 page_size)
 {
 	struct hl_device *hdev = ctx->hdev;
-	u64 real_virt_addr;
+	u64 real_virt_addr, real_phys_addr;
 	u32 real_page_size, npages;
 	int i, rc, mapped_cnt = 0;
 
@@ -857,14 +857,16 @@ int hl_mmu_map(struct hl_ctx *ctx, u64 virt_addr, u64 phys_addr, u32 page_size)
 
 	npages = page_size / real_page_size;
 	real_virt_addr = virt_addr;
+	real_phys_addr = phys_addr;
 
 	for (i = 0 ; i < npages ; i++) {
-		rc = _hl_mmu_map(ctx, real_virt_addr, phys_addr,
+		rc = _hl_mmu_map(ctx, real_virt_addr, real_phys_addr,
 				real_page_size);
 		if (rc)
 			goto err;
 
 		real_virt_addr += real_page_size;
+		real_phys_addr += real_page_size;
 		mapped_cnt++;
 	}
 
diff --git a/drivers/misc/ioc4.c b/drivers/misc/ioc4.c
index ec0832278170..9d0445a567db 100644
--- a/drivers/misc/ioc4.c
+++ b/drivers/misc/ioc4.c
@@ -156,7 +156,6 @@ ioc4_clock_calibrate(struct ioc4_driver_data *idd)
 
 	/* Reset to power-on state */
 	writel(0, &idd->idd_misc_regs->int_out.raw);
-	mmiowb();
 
 	/* Set up square wave */
 	int_out.raw = 0;
@@ -164,7 +163,6 @@ ioc4_clock_calibrate(struct ioc4_driver_data *idd)
 	int_out.fields.mode = IOC4_INT_OUT_MODE_TOGGLE;
 	int_out.fields.diag = 0;
 	writel(int_out.raw, &idd->idd_misc_regs->int_out.raw);
-	mmiowb();
 
 	/* Check square wave period averaged over some number of cycles */
 	start = ktime_get_ns();
diff --git a/drivers/misc/mei/hw-me.c b/drivers/misc/mei/hw-me.c
index 3fbbadfa2ae1..8a47a6fc3fc7 100644
--- a/drivers/misc/mei/hw-me.c
+++ b/drivers/misc/mei/hw-me.c
@@ -350,9 +350,6 @@ static void mei_me_hw_reset_release(struct mei_device *dev)
 	hcsr |= H_IG;
 	hcsr &= ~H_RST;
 	mei_hcsr_set(dev, hcsr);
-
-	/* complete this write before we set host ready on another CPU */
-	mmiowb();
 }
 
 /**
diff --git a/drivers/misc/mic/Kconfig b/drivers/misc/mic/Kconfig
index 242dcee14689..6736f72cc14a 100644
--- a/drivers/misc/mic/Kconfig
+++ b/drivers/misc/mic/Kconfig
@@ -4,7 +4,7 @@ comment "Intel MIC Bus Driver"
 
 config INTEL_MIC_BUS
 	tristate "Intel MIC Bus Driver"
-	depends on 64BIT && PCI && X86 && X86_DEV_DMA_OPS
+	depends on 64BIT && PCI && X86
 	help
 	  This option is selected by any driver which registers a
 	  device or driver on the MIC Bus, such as CONFIG_INTEL_MIC_HOST,
@@ -21,7 +21,7 @@ comment "SCIF Bus Driver"
 
 config SCIF_BUS
 	tristate "SCIF Bus Driver"
-	depends on 64BIT && PCI && X86 && X86_DEV_DMA_OPS
+	depends on 64BIT && PCI && X86
 	help
 	  This option is selected by any driver which registers a
 	  device or driver on the SCIF Bus, such as CONFIG_INTEL_MIC_HOST
diff --git a/drivers/misc/tifm_7xx1.c b/drivers/misc/tifm_7xx1.c
index 9ac95b48ef92..cc729f7ab32e 100644
--- a/drivers/misc/tifm_7xx1.c
+++ b/drivers/misc/tifm_7xx1.c
@@ -403,7 +403,6 @@ static void tifm_7xx1_remove(struct pci_dev *dev)
 	fm->eject = tifm_7xx1_dummy_eject;
 	fm->has_ms_pif = tifm_7xx1_dummy_has_ms_pif;
 	writel(TIFM_IRQ_SETALL, fm->addr + FM_CLEAR_INTERRUPT_ENABLE);
-	mmiowb();
 	free_irq(dev->irq, fm);
 
 	tifm_remove_adapter(fm);
diff --git a/drivers/mmc/host/alcor.c b/drivers/mmc/host/alcor.c
index 82a97866e0cf..6e6b7ade4b60 100644
--- a/drivers/mmc/host/alcor.c
+++ b/drivers/mmc/host/alcor.c
@@ -48,7 +48,6 @@ struct alcor_sdmmc_host {
 	struct mmc_command *cmd;
 	struct mmc_data *data;
 	unsigned int dma_on:1;
-	unsigned int early_data:1;
 
 	struct mutex cmd_mutex;
 
@@ -144,8 +143,7 @@ static void alcor_data_set_dma(struct alcor_sdmmc_host *host)
 	host->sg_count--;
 }
 
-static void alcor_trigger_data_transfer(struct alcor_sdmmc_host *host,
-					bool early)
+static void alcor_trigger_data_transfer(struct alcor_sdmmc_host *host)
 {
 	struct alcor_pci_priv *priv = host->alcor_pci;
 	struct mmc_data *data = host->data;
@@ -155,13 +153,6 @@ static void alcor_trigger_data_transfer(struct alcor_sdmmc_host *host,
 		ctrl |= AU6601_DATA_WRITE;
 
 	if (data->host_cookie == COOKIE_MAPPED) {
-		if (host->early_data) {
-			host->early_data = false;
-			return;
-		}
-
-		host->early_data = early;
-
 		alcor_data_set_dma(host);
 		ctrl |= AU6601_DATA_DMA_MODE;
 		host->dma_on = 1;
@@ -231,6 +222,7 @@ static void alcor_prepare_sg_miter(struct alcor_sdmmc_host *host)
 static void alcor_prepare_data(struct alcor_sdmmc_host *host,
 			       struct mmc_command *cmd)
 {
+	struct alcor_pci_priv *priv = host->alcor_pci;
 	struct mmc_data *data = cmd->data;
 
 	if (!data)
@@ -248,7 +240,7 @@ static void alcor_prepare_data(struct alcor_sdmmc_host *host,
 	if (data->host_cookie != COOKIE_MAPPED)
 		alcor_prepare_sg_miter(host);
 
-	alcor_trigger_data_transfer(host, true);
+	alcor_write8(priv, 0, AU6601_DATA_XFER_CTRL);
 }
 
 static void alcor_send_cmd(struct alcor_sdmmc_host *host,
@@ -435,7 +427,7 @@ static int alcor_cmd_irq_done(struct alcor_sdmmc_host *host, u32 intmask)
 	if (!host->data)
 		return false;
 
-	alcor_trigger_data_transfer(host, false);
+	alcor_trigger_data_transfer(host);
 	host->cmd = NULL;
 	return true;
 }
@@ -456,7 +448,7 @@ static void alcor_cmd_irq_thread(struct alcor_sdmmc_host *host, u32 intmask)
 	if (!host->data)
 		alcor_request_complete(host, 1);
 	else
-		alcor_trigger_data_transfer(host, false);
+		alcor_trigger_data_transfer(host);
 	host->cmd = NULL;
 }
 
@@ -487,15 +479,9 @@ static int alcor_data_irq_done(struct alcor_sdmmc_host *host, u32 intmask)
 		break;
 	case AU6601_INT_READ_BUF_RDY:
 		alcor_trf_block_pio(host, true);
-		if (!host->blocks)
-			break;
-		alcor_trigger_data_transfer(host, false);
 		return 1;
 	case AU6601_INT_WRITE_BUF_RDY:
 		alcor_trf_block_pio(host, false);
-		if (!host->blocks)
-			break;
-		alcor_trigger_data_transfer(host, false);
 		return 1;
 	case AU6601_INT_DMA_END:
 		if (!host->sg_count)
@@ -508,8 +494,14 @@ static int alcor_data_irq_done(struct alcor_sdmmc_host *host, u32 intmask)
 		break;
 	}
 
-	if (intmask & AU6601_INT_DATA_END)
-		return 0;
+	if (intmask & AU6601_INT_DATA_END) {
+		if (!host->dma_on && host->blocks) {
+			alcor_trigger_data_transfer(host);
+			return 1;
+		} else {
+			return 0;
+		}
+	}
 
 	return 1;
 }
@@ -967,7 +959,6 @@ static void alcor_timeout_timer(struct work_struct *work)
 		alcor_request_complete(host, 0);
 	}
 
-	mmiowb();
 	mutex_unlock(&host->cmd_mutex);
 }
 
diff --git a/drivers/mmc/host/sdhci-omap.c b/drivers/mmc/host/sdhci-omap.c
index 5bbed477c9b1..9f20fff9781b 100644
--- a/drivers/mmc/host/sdhci-omap.c
+++ b/drivers/mmc/host/sdhci-omap.c
@@ -797,6 +797,43 @@ void sdhci_omap_reset(struct sdhci_host *host, u8 mask)
 	sdhci_reset(host, mask);
 }
 
+#define CMD_ERR_MASK (SDHCI_INT_CRC | SDHCI_INT_END_BIT | SDHCI_INT_INDEX |\
+		      SDHCI_INT_TIMEOUT)
+#define CMD_MASK (CMD_ERR_MASK | SDHCI_INT_RESPONSE)
+
+static u32 sdhci_omap_irq(struct sdhci_host *host, u32 intmask)
+{
+	struct sdhci_pltfm_host *pltfm_host = sdhci_priv(host);
+	struct sdhci_omap_host *omap_host = sdhci_pltfm_priv(pltfm_host);
+
+	if (omap_host->is_tuning && host->cmd && !host->data_early &&
+	    (intmask & CMD_ERR_MASK)) {
+
+		/*
+		 * Since we are not resetting data lines during tuning
+		 * operation, data error or data complete interrupts
+		 * might still arrive. Mark this request as a failure
+		 * but still wait for the data interrupt
+		 */
+		if (intmask & SDHCI_INT_TIMEOUT)
+			host->cmd->error = -ETIMEDOUT;
+		else
+			host->cmd->error = -EILSEQ;
+
+		host->cmd = NULL;
+
+		/*
+		 * Sometimes command error interrupts and command complete
+		 * interrupt will arrive together. Clear all command related
+		 * interrupts here.
+		 */
+		sdhci_writel(host, intmask & CMD_MASK, SDHCI_INT_STATUS);
+		intmask &= ~CMD_MASK;
+	}
+
+	return intmask;
+}
+
 static struct sdhci_ops sdhci_omap_ops = {
 	.set_clock = sdhci_omap_set_clock,
 	.set_power = sdhci_omap_set_power,
@@ -807,6 +844,7 @@ static struct sdhci_ops sdhci_omap_ops = {
 	.platform_send_init_74_clocks = sdhci_omap_init_74_clocks,
 	.reset = sdhci_omap_reset,
 	.set_uhs_signaling = sdhci_omap_set_uhs_signaling,
+	.irq = sdhci_omap_irq,
 };
 
 static int sdhci_omap_set_capabilities(struct sdhci_omap_host *omap_host)
diff --git a/drivers/mmc/host/sdhci.c b/drivers/mmc/host/sdhci.c
index a8141ff9be03..42e1bad024f4 100644
--- a/drivers/mmc/host/sdhci.c
+++ b/drivers/mmc/host/sdhci.c
@@ -1807,7 +1807,6 @@ void sdhci_request(struct mmc_host *mmc, struct mmc_request *mrq)
 			sdhci_send_command(host, mrq->cmd);
 	}
 
-	mmiowb();
 	spin_unlock_irqrestore(&host->lock, flags);
 }
 EXPORT_SYMBOL_GPL(sdhci_request);
@@ -2010,8 +2009,6 @@ void sdhci_set_ios(struct mmc_host *mmc, struct mmc_ios *ios)
 	 */
 	if (host->quirks & SDHCI_QUIRK_RESET_CMD_DATA_ON_IOS)
 		sdhci_do_reset(host, SDHCI_RESET_CMD | SDHCI_RESET_DATA);
-
-	mmiowb();
 }
 EXPORT_SYMBOL_GPL(sdhci_set_ios);
 
@@ -2105,7 +2102,6 @@ static void sdhci_enable_sdio_irq_nolock(struct sdhci_host *host, int enable)
 
 		sdhci_writel(host, host->ier, SDHCI_INT_ENABLE);
 		sdhci_writel(host, host->ier, SDHCI_SIGNAL_ENABLE);
-		mmiowb();
 	}
 }
 
@@ -2353,7 +2349,6 @@ void sdhci_send_tuning(struct sdhci_host *host, u32 opcode)
 
 	host->tuning_done = 0;
 
-	mmiowb();
 	spin_unlock_irqrestore(&host->lock, flags);
 
 	/* Wait for Buffer Read Ready interrupt */
@@ -2705,7 +2700,6 @@ static bool sdhci_request_done(struct sdhci_host *host)
 
 	host->mrqs_done[i] = NULL;
 
-	mmiowb();
 	spin_unlock_irqrestore(&host->lock, flags);
 
 	mmc_request_done(host->mmc, mrq);
@@ -2739,7 +2733,6 @@ static void sdhci_timeout_timer(struct timer_list *t)
 		sdhci_finish_mrq(host, host->cmd->mrq);
 	}
 
-	mmiowb();
 	spin_unlock_irqrestore(&host->lock, flags);
 }
 
@@ -2770,7 +2763,6 @@ static void sdhci_timeout_data_timer(struct timer_list *t)
 		}
 	}
 
-	mmiowb();
 	spin_unlock_irqrestore(&host->lock, flags);
 }
 
@@ -3251,7 +3243,6 @@ int sdhci_resume_host(struct sdhci_host *host)
 		mmc->ops->set_ios(mmc, &mmc->ios);
 	} else {
 		sdhci_init(host, (host->mmc->pm_flags & MMC_PM_KEEP_POWER));
-		mmiowb();
 	}
 
 	if (host->irq_wake_enabled) {
@@ -3391,7 +3382,6 @@ void sdhci_cqe_enable(struct mmc_host *mmc)
 		 mmc_hostname(mmc), host->ier,
 		 sdhci_readl(host, SDHCI_INT_STATUS));
 
-	mmiowb();
 	spin_unlock_irqrestore(&host->lock, flags);
 }
 EXPORT_SYMBOL_GPL(sdhci_cqe_enable);
@@ -3416,7 +3406,6 @@ void sdhci_cqe_disable(struct mmc_host *mmc, bool recovery)
 		 mmc_hostname(mmc), host->ier,
 		 sdhci_readl(host, SDHCI_INT_STATUS));
 
-	mmiowb();
 	spin_unlock_irqrestore(&host->lock, flags);
 }
 EXPORT_SYMBOL_GPL(sdhci_cqe_disable);
@@ -4255,8 +4244,6 @@ int __sdhci_add_host(struct sdhci_host *host)
 		goto unirq;
 	}
 
-	mmiowb();
-
 	ret = mmc_add_host(mmc);
 	if (ret)
 		goto unled;
diff --git a/drivers/mmc/host/tifm_sd.c b/drivers/mmc/host/tifm_sd.c
index b6644ce296b2..35dd34b82a4d 100644
--- a/drivers/mmc/host/tifm_sd.c
+++ b/drivers/mmc/host/tifm_sd.c
@@ -889,7 +889,6 @@ static int tifm_sd_initialize_host(struct tifm_sd *host)
 	struct tifm_dev *sock = host->dev;
 
 	writel(0, sock->addr + SOCK_MMCSD_INT_ENABLE);
-	mmiowb();
 	host->clk_div = 61;
 	host->clk_freq = 20000000;
 	writel(TIFM_MMCSD_RESET, sock->addr + SOCK_MMCSD_SYSTEM_CONTROL);
@@ -940,7 +939,6 @@ static int tifm_sd_initialize_host(struct tifm_sd *host)
 	writel(TIFM_MMCSD_CERR | TIFM_MMCSD_BRS | TIFM_MMCSD_EOC
 	       | TIFM_MMCSD_ERRMASK,
 	       sock->addr + SOCK_MMCSD_INT_ENABLE);
-	mmiowb();
 
 	return 0;
 }
@@ -1005,7 +1003,6 @@ static void tifm_sd_remove(struct tifm_dev *sock)
 	spin_lock_irqsave(&sock->lock, flags);
 	host->eject = 1;
 	writel(0, sock->addr + SOCK_MMCSD_INT_ENABLE);
-	mmiowb();
 	spin_unlock_irqrestore(&sock->lock, flags);
 
 	tasklet_kill(&host->finish_tasklet);
diff --git a/drivers/mmc/host/via-sdmmc.c b/drivers/mmc/host/via-sdmmc.c
index 32c4211506fc..412395ac2935 100644
--- a/drivers/mmc/host/via-sdmmc.c
+++ b/drivers/mmc/host/via-sdmmc.c
@@ -686,7 +686,6 @@ static void via_sdc_request(struct mmc_host *mmc, struct mmc_request *mrq)
 		via_sdc_send_command(host, mrq->cmd);
 	}
 
-	mmiowb();
 	spin_unlock_irqrestore(&host->lock, flags);
 }
 
@@ -711,7 +710,6 @@ static void via_sdc_set_power(struct via_crdr_mmc_host *host,
 		gatt &= ~VIA_CRDR_PCICLKGATT_PAD_PWRON;
 	writeb(gatt, host->pcictrl_mmiobase + VIA_CRDR_PCICLKGATT);
 
-	mmiowb();
 	spin_unlock_irqrestore(&host->lock, flags);
 
 	via_pwron_sleep(host);
@@ -770,7 +768,6 @@ static void via_sdc_set_ios(struct mmc_host *mmc, struct mmc_ios *ios)
 	if (readb(addrbase + VIA_CRDR_PCISDCCLK) != clock)
 		writeb(clock, addrbase + VIA_CRDR_PCISDCCLK);
 
-	mmiowb();
 	spin_unlock_irqrestore(&host->lock, flags);
 
 	if (ios->power_mode != MMC_POWER_OFF)
@@ -830,7 +827,6 @@ static void via_reset_pcictrl(struct via_crdr_mmc_host *host)
 	via_restore_pcictrlreg(host);
 	via_restore_sdcreg(host);
 
-	mmiowb();
 	spin_unlock_irqrestore(&host->lock, flags);
 }
 
@@ -925,7 +921,6 @@ static irqreturn_t via_sdc_isr(int irq, void *dev_id)
 
 	result = IRQ_HANDLED;
 
-	mmiowb();
 out:
 	spin_unlock(&sdhost->lock);
 
@@ -960,7 +955,6 @@ static void via_sdc_timeout(struct timer_list *t)
 		}
 	}
 
-	mmiowb();
 	spin_unlock_irqrestore(&sdhost->lock, flags);
 }
 
@@ -1012,7 +1006,6 @@ static void via_sdc_card_detect(struct work_struct *work)
 			tasklet_schedule(&host->finish_tasklet);
 		}
 
-		mmiowb();
 		spin_unlock_irqrestore(&host->lock, flags);
 
 		via_reset_pcictrl(host);
@@ -1020,7 +1013,6 @@ static void via_sdc_card_detect(struct work_struct *work)
 		spin_lock_irqsave(&host->lock, flags);
 	}
 
-	mmiowb();
 	spin_unlock_irqrestore(&host->lock, flags);
 
 	via_print_pcictrl(host);
@@ -1188,7 +1180,6 @@ static void via_sd_remove(struct pci_dev *pcidev)
 
 	/* Disable generating further interrupts */
 	writeb(0x0, sdhost->pcictrl_mmiobase + VIA_CRDR_PCIINTCTRL);
-	mmiowb();
 
 	if (sdhost->mrq) {
 		pr_err("%s: Controller removed during "
@@ -1197,7 +1188,6 @@ static void via_sd_remove(struct pci_dev *pcidev)
 		/* make sure all DMA is stopped */
 		writel(VIA_CRDR_DMACTRL_SFTRST,
 			sdhost->ddma_mmiobase + VIA_CRDR_DMACTRL);
-		mmiowb();
 		sdhost->mrq->cmd->error = -ENOMEDIUM;
 		if (sdhost->mrq->stop)
 			sdhost->mrq->stop->error = -ENOMEDIUM;
diff --git a/drivers/mtd/chips/cfi_cmdset_0002.c b/drivers/mtd/chips/cfi_cmdset_0002.c
index 72428b6bfc47..7b7286b4d81e 100644
--- a/drivers/mtd/chips/cfi_cmdset_0002.c
+++ b/drivers/mtd/chips/cfi_cmdset_0002.c
@@ -1876,7 +1876,11 @@ static int __xipram do_write_buffer(struct map_info *map, struct flchip *chip,
 			continue;
 		}
 
-		if (time_after(jiffies, timeo) && !chip_ready(map, adr))
+		/*
+		 * We check "time_after" and "!chip_good" before checking "chip_good" to avoid
+		 * the failure due to scheduling.
+		 */
+		if (time_after(jiffies, timeo) && !chip_good(map, adr, datum))
 			break;
 
 		if (chip_good(map, adr, datum)) {
diff --git a/drivers/mtd/nand/raw/marvell_nand.c b/drivers/mtd/nand/raw/marvell_nand.c
index f38e5c1b87e4..d984538980e2 100644
--- a/drivers/mtd/nand/raw/marvell_nand.c
+++ b/drivers/mtd/nand/raw/marvell_nand.c
@@ -722,12 +722,6 @@ static void marvell_nfc_select_target(struct nand_chip *chip,
 	struct marvell_nfc *nfc = to_marvell_nfc(chip->controller);
 	u32 ndcr_generic;
 
-	if (chip == nfc->selected_chip && die_nr == marvell_nand->selected_die)
-		return;
-
-	writel_relaxed(marvell_nand->ndtr0, nfc->regs + NDTR0);
-	writel_relaxed(marvell_nand->ndtr1, nfc->regs + NDTR1);
-
 	/*
 	 * Reset the NDCR register to a clean state for this particular chip,
 	 * also clear ND_RUN bit.
@@ -739,6 +733,12 @@ static void marvell_nfc_select_target(struct nand_chip *chip,
 	/* Also reset the interrupt status register */
 	marvell_nfc_clear_int(nfc, NDCR_ALL_INT);
 
+	if (chip == nfc->selected_chip && die_nr == marvell_nand->selected_die)
+		return;
+
+	writel_relaxed(marvell_nand->ndtr0, nfc->regs + NDTR0);
+	writel_relaxed(marvell_nand->ndtr1, nfc->regs + NDTR1);
+
 	nfc->selected_chip = chip;
 	marvell_nand->selected_die = die_nr;
 }
diff --git a/drivers/mtd/nand/raw/r852.c b/drivers/mtd/nand/raw/r852.c
index 86456216fb93..7b99831aa046 100644
--- a/drivers/mtd/nand/raw/r852.c
+++ b/drivers/mtd/nand/raw/r852.c
@@ -45,7 +45,6 @@ static inline void r852_write_reg(struct r852_device *dev,
 						int address, uint8_t value)
 {
 	writeb(value, dev->mmio + address);
-	mmiowb();
 }
 
 
@@ -61,7 +60,6 @@ static inline void r852_write_reg_dword(struct r852_device *dev,
 							int address, uint32_t value)
 {
 	writel(cpu_to_le32(value), dev->mmio + address);
-	mmiowb();
 }
 
 /* returns pointer to our private structure */
diff --git a/drivers/mtd/nand/raw/txx9ndfmc.c b/drivers/mtd/nand/raw/txx9ndfmc.c
index ddf0420c0997..97978227aa55 100644
--- a/drivers/mtd/nand/raw/txx9ndfmc.c
+++ b/drivers/mtd/nand/raw/txx9ndfmc.c
@@ -159,7 +159,6 @@ static void txx9ndfmc_cmd_ctrl(struct nand_chip *chip, int cmd,
 		if ((ctrl & NAND_CTRL_CHANGE) && cmd == NAND_CMD_NONE)
 			txx9ndfmc_write(dev, 0, TXX9_NDFDTR);
 	}
-	mmiowb();
 }
 
 static int txx9ndfmc_dev_ready(struct nand_chip *chip)
diff --git a/drivers/net/Kconfig b/drivers/net/Kconfig
index 5e4ca082cfcd..7a96d168efc4 100644
--- a/drivers/net/Kconfig
+++ b/drivers/net/Kconfig
@@ -216,8 +216,8 @@ config GENEVE
 
 config GTP
 	tristate "GPRS Tunneling Protocol datapath (GTP-U)"
-	depends on INET && NET_UDP_TUNNEL
-	select NET_IP_TUNNEL
+	depends on INET
+	select NET_UDP_TUNNEL
 	---help---
 	  This allows one to create gtp virtual interfaces that provide
 	  the GPRS Tunneling Protocol datapath (GTP-U). This tunneling protocol
diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c
index b59708c35faf..ee610721098e 100644
--- a/drivers/net/bonding/bond_main.c
+++ b/drivers/net/bonding/bond_main.c
@@ -3213,8 +3213,12 @@ static int bond_netdev_event(struct notifier_block *this,
 		return NOTIFY_DONE;
 
 	if (event_dev->flags & IFF_MASTER) {
+		int ret;
+
 		netdev_dbg(event_dev, "IFF_MASTER\n");
-		return bond_master_netdev_event(event, event_dev);
+		ret = bond_master_netdev_event(event, event_dev);
+		if (ret != NOTIFY_DONE)
+			return ret;
 	}
 
 	if (event_dev->flags & IFF_SLAVE) {
diff --git a/drivers/net/bonding/bond_sysfs_slave.c b/drivers/net/bonding/bond_sysfs_slave.c
index 2f120b2ffef0..4985268e2273 100644
--- a/drivers/net/bonding/bond_sysfs_slave.c
+++ b/drivers/net/bonding/bond_sysfs_slave.c
@@ -55,7 +55,9 @@ static SLAVE_ATTR_RO(link_failure_count);
 
 static ssize_t perm_hwaddr_show(struct slave *slave, char *buf)
 {
-	return sprintf(buf, "%pM\n", slave->perm_hwaddr);
+	return sprintf(buf, "%*phC\n",
+		       slave->dev->addr_len,
+		       slave->perm_hwaddr);
 }
 static SLAVE_ATTR_RO(perm_hwaddr);
 
diff --git a/drivers/net/dsa/bcm_sf2_cfp.c b/drivers/net/dsa/bcm_sf2_cfp.c
index e6234d209787..4212bc4a5f31 100644
--- a/drivers/net/dsa/bcm_sf2_cfp.c
+++ b/drivers/net/dsa/bcm_sf2_cfp.c
@@ -886,6 +886,9 @@ static int bcm_sf2_cfp_rule_set(struct dsa_switch *ds, int port,
 	     fs->m_ext.data[1]))
 		return -EINVAL;
 
+	if (fs->location != RX_CLS_LOC_ANY && fs->location >= CFP_NUM_RULES)
+		return -EINVAL;
+
 	if (fs->location != RX_CLS_LOC_ANY &&
 	    test_bit(fs->location, priv->cfp.used))
 		return -EBUSY;
@@ -974,6 +977,9 @@ static int bcm_sf2_cfp_rule_del(struct bcm_sf2_priv *priv, int port, u32 loc)
 	struct cfp_rule *rule;
 	int ret;
 
+	if (loc >= CFP_NUM_RULES)
+		return -EINVAL;
+
 	/* Refuse deleting unused rules, and those that are not unique since
 	 * that could leave IPv6 rules with one of the chained rule in the
 	 * table.
diff --git a/drivers/net/dsa/mv88e6xxx/port.c b/drivers/net/dsa/mv88e6xxx/port.c
index dce84a2a65c7..c44b2822e4dd 100644
--- a/drivers/net/dsa/mv88e6xxx/port.c
+++ b/drivers/net/dsa/mv88e6xxx/port.c
@@ -427,18 +427,22 @@ int mv88e6390x_port_set_cmode(struct mv88e6xxx_chip *chip, int port,
 		return 0;
 
 	lane = mv88e6390x_serdes_get_lane(chip, port);
-	if (lane < 0)
+	if (lane < 0 && lane != -ENODEV)
 		return lane;
 
-	if (chip->ports[port].serdes_irq) {
-		err = mv88e6390_serdes_irq_disable(chip, port, lane);
+	if (lane >= 0) {
+		if (chip->ports[port].serdes_irq) {
+			err = mv88e6390_serdes_irq_disable(chip, port, lane);
+			if (err)
+				return err;
+		}
+
+		err = mv88e6390x_serdes_power(chip, port, false);
 		if (err)
 			return err;
 	}
 
-	err = mv88e6390x_serdes_power(chip, port, false);
-	if (err)
-		return err;
+	chip->ports[port].cmode = 0;
 
 	if (cmode) {
 		err = mv88e6xxx_port_read(chip, port, MV88E6XXX_PORT_STS, &reg);
@@ -452,6 +456,12 @@ int mv88e6390x_port_set_cmode(struct mv88e6xxx_chip *chip, int port,
 		if (err)
 			return err;
 
+		chip->ports[port].cmode = cmode;
+
+		lane = mv88e6390x_serdes_get_lane(chip, port);
+		if (lane < 0)
+			return lane;
+
 		err = mv88e6390x_serdes_power(chip, port, true);
 		if (err)
 			return err;
@@ -463,8 +473,6 @@ int mv88e6390x_port_set_cmode(struct mv88e6xxx_chip *chip, int port,
 		}
 	}
 
-	chip->ports[port].cmode = cmode;
-
 	return 0;
 }
 
diff --git a/drivers/net/dsa/qca8k.c b/drivers/net/dsa/qca8k.c
index 576b37d12a63..c4fa400efdcc 100644
--- a/drivers/net/dsa/qca8k.c
+++ b/drivers/net/dsa/qca8k.c
@@ -481,6 +481,155 @@ qca8k_port_set_status(struct qca8k_priv *priv, int port, int enable)
 		qca8k_reg_clear(priv, QCA8K_REG_PORT_STATUS(port), mask);
 }
 
+static u32
+qca8k_port_to_phy(int port)
+{
+	/* From Andrew Lunn:
+	 * Port 0 has no internal phy.
+	 * Port 1 has an internal PHY at MDIO address 0.
+	 * Port 2 has an internal PHY at MDIO address 1.
+	 * ...
+	 * Port 5 has an internal PHY at MDIO address 4.
+	 * Port 6 has no internal PHY.
+	 */
+
+	return port - 1;
+}
+
+static int
+qca8k_mdio_write(struct qca8k_priv *priv, int port, u32 regnum, u16 data)
+{
+	u32 phy, val;
+
+	if (regnum >= QCA8K_MDIO_MASTER_MAX_REG)
+		return -EINVAL;
+
+	/* callee is responsible for not passing bad ports,
+	 * but we still would like to make spills impossible.
+	 */
+	phy = qca8k_port_to_phy(port) % PHY_MAX_ADDR;
+	val = QCA8K_MDIO_MASTER_BUSY | QCA8K_MDIO_MASTER_EN |
+	      QCA8K_MDIO_MASTER_WRITE | QCA8K_MDIO_MASTER_PHY_ADDR(phy) |
+	      QCA8K_MDIO_MASTER_REG_ADDR(regnum) |
+	      QCA8K_MDIO_MASTER_DATA(data);
+
+	qca8k_write(priv, QCA8K_MDIO_MASTER_CTRL, val);
+
+	return qca8k_busy_wait(priv, QCA8K_MDIO_MASTER_CTRL,
+		QCA8K_MDIO_MASTER_BUSY);
+}
+
+static int
+qca8k_mdio_read(struct qca8k_priv *priv, int port, u32 regnum)
+{
+	u32 phy, val;
+
+	if (regnum >= QCA8K_MDIO_MASTER_MAX_REG)
+		return -EINVAL;
+
+	/* callee is responsible for not passing bad ports,
+	 * but we still would like to make spills impossible.
+	 */
+	phy = qca8k_port_to_phy(port) % PHY_MAX_ADDR;
+	val = QCA8K_MDIO_MASTER_BUSY | QCA8K_MDIO_MASTER_EN |
+	      QCA8K_MDIO_MASTER_READ | QCA8K_MDIO_MASTER_PHY_ADDR(phy) |
+	      QCA8K_MDIO_MASTER_REG_ADDR(regnum);
+
+	qca8k_write(priv, QCA8K_MDIO_MASTER_CTRL, val);
+
+	if (qca8k_busy_wait(priv, QCA8K_MDIO_MASTER_CTRL,
+			    QCA8K_MDIO_MASTER_BUSY))
+		return -ETIMEDOUT;
+
+	val = (qca8k_read(priv, QCA8K_MDIO_MASTER_CTRL) &
+		QCA8K_MDIO_MASTER_DATA_MASK);
+
+	return val;
+}
+
+static int
+qca8k_phy_write(struct dsa_switch *ds, int port, int regnum, u16 data)
+{
+	struct qca8k_priv *priv = ds->priv;
+
+	return qca8k_mdio_write(priv, port, regnum, data);
+}
+
+static int
+qca8k_phy_read(struct dsa_switch *ds, int port, int regnum)
+{
+	struct qca8k_priv *priv = ds->priv;
+	int ret;
+
+	ret = qca8k_mdio_read(priv, port, regnum);
+
+	if (ret < 0)
+		return 0xffff;
+
+	return ret;
+}
+
+static int
+qca8k_setup_mdio_bus(struct qca8k_priv *priv)
+{
+	u32 internal_mdio_mask = 0, external_mdio_mask = 0, reg;
+	struct device_node *ports, *port;
+	int err;
+
+	ports = of_get_child_by_name(priv->dev->of_node, "ports");
+	if (!ports)
+		return -EINVAL;
+
+	for_each_available_child_of_node(ports, port) {
+		err = of_property_read_u32(port, "reg", &reg);
+		if (err)
+			return err;
+
+		if (!dsa_is_user_port(priv->ds, reg))
+			continue;
+
+		if (of_property_read_bool(port, "phy-handle"))
+			external_mdio_mask |= BIT(reg);
+		else
+			internal_mdio_mask |= BIT(reg);
+	}
+
+	if (!external_mdio_mask && !internal_mdio_mask) {
+		dev_err(priv->dev, "no PHYs are defined.\n");
+		return -EINVAL;
+	}
+
+	/* The QCA8K_MDIO_MASTER_EN Bit, which grants access to PHYs through
+	 * the MDIO_MASTER register also _disconnects_ the external MDC
+	 * passthrough to the internal PHYs. It's not possible to use both
+	 * configurations at the same time!
+	 *
+	 * Because this came up during the review process:
+	 * If the external mdio-bus driver is capable magically disabling
+	 * the QCA8K_MDIO_MASTER_EN and mutex/spin-locking out the qca8k's
+	 * accessors for the time being, it would be possible to pull this
+	 * off.
+	 */
+	if (!!external_mdio_mask && !!internal_mdio_mask) {
+		dev_err(priv->dev, "either internal or external mdio bus configuration is supported.\n");
+		return -EINVAL;
+	}
+
+	if (external_mdio_mask) {
+		/* Make sure to disable the internal mdio bus in cases
+		 * a dt-overlay and driver reload changed the configuration
+		 */
+
+		qca8k_reg_clear(priv, QCA8K_MDIO_MASTER_CTRL,
+				QCA8K_MDIO_MASTER_EN);
+		return 0;
+	}
+
+	priv->ops.phy_read = qca8k_phy_read;
+	priv->ops.phy_write = qca8k_phy_write;
+	return 0;
+}
+
 static int
 qca8k_setup(struct dsa_switch *ds)
 {
@@ -502,6 +651,10 @@ qca8k_setup(struct dsa_switch *ds)
 	if (IS_ERR(priv->regmap))
 		pr_warn("regmap initialization failed");
 
+	ret = qca8k_setup_mdio_bus(priv);
+	if (ret)
+		return ret;
+
 	/* Initialize CPU port pad mode (xMII type, delays...) */
 	phy_mode = of_get_phy_mode(ds->ports[QCA8K_CPU_PORT].dn);
 	if (phy_mode < 0) {
@@ -624,22 +777,6 @@ qca8k_adjust_link(struct dsa_switch *ds, int port, struct phy_device *phy)
 	qca8k_port_set_status(priv, port, 1);
 }
 
-static int
-qca8k_phy_read(struct dsa_switch *ds, int phy, int regnum)
-{
-	struct qca8k_priv *priv = (struct qca8k_priv *)ds->priv;
-
-	return mdiobus_read(priv->bus, phy, regnum);
-}
-
-static int
-qca8k_phy_write(struct dsa_switch *ds, int phy, int regnum, u16 val)
-{
-	struct qca8k_priv *priv = (struct qca8k_priv *)ds->priv;
-
-	return mdiobus_write(priv->bus, phy, regnum, val);
-}
-
 static void
 qca8k_get_strings(struct dsa_switch *ds, int port, u32 stringset, uint8_t *data)
 {
@@ -879,8 +1016,6 @@ static const struct dsa_switch_ops qca8k_switch_ops = {
 	.setup			= qca8k_setup,
 	.adjust_link            = qca8k_adjust_link,
 	.get_strings		= qca8k_get_strings,
-	.phy_read		= qca8k_phy_read,
-	.phy_write		= qca8k_phy_write,
 	.get_ethtool_stats	= qca8k_get_ethtool_stats,
 	.get_sset_count		= qca8k_get_sset_count,
 	.get_mac_eee		= qca8k_get_mac_eee,
@@ -923,7 +1058,8 @@ qca8k_sw_probe(struct mdio_device *mdiodev)
 		return -ENOMEM;
 
 	priv->ds->priv = priv;
-	priv->ds->ops = &qca8k_switch_ops;
+	priv->ops = qca8k_switch_ops;
+	priv->ds->ops = &priv->ops;
 	mutex_init(&priv->reg_mutex);
 	dev_set_drvdata(&mdiodev->dev, priv);
 
diff --git a/drivers/net/dsa/qca8k.h b/drivers/net/dsa/qca8k.h
index d146e54c8a6c..249fd62268e5 100644
--- a/drivers/net/dsa/qca8k.h
+++ b/drivers/net/dsa/qca8k.h
@@ -49,6 +49,18 @@
 #define   QCA8K_MIB_FLUSH				BIT(24)
 #define   QCA8K_MIB_CPU_KEEP				BIT(20)
 #define   QCA8K_MIB_BUSY				BIT(17)
+#define QCA8K_MDIO_MASTER_CTRL				0x3c
+#define   QCA8K_MDIO_MASTER_BUSY			BIT(31)
+#define   QCA8K_MDIO_MASTER_EN				BIT(30)
+#define   QCA8K_MDIO_MASTER_READ			BIT(27)
+#define   QCA8K_MDIO_MASTER_WRITE			0
+#define   QCA8K_MDIO_MASTER_SUP_PRE			BIT(26)
+#define   QCA8K_MDIO_MASTER_PHY_ADDR(x)			((x) << 21)
+#define   QCA8K_MDIO_MASTER_REG_ADDR(x)			((x) << 16)
+#define   QCA8K_MDIO_MASTER_DATA(x)			(x)
+#define   QCA8K_MDIO_MASTER_DATA_MASK			GENMASK(15, 0)
+#define   QCA8K_MDIO_MASTER_MAX_PORTS			5
+#define   QCA8K_MDIO_MASTER_MAX_REG			32
 #define QCA8K_GOL_MAC_ADDR0				0x60
 #define QCA8K_GOL_MAC_ADDR1				0x64
 #define QCA8K_REG_PORT_STATUS(_i)			(0x07c + (_i) * 4)
@@ -169,6 +181,7 @@ struct qca8k_priv {
 	struct dsa_switch *ds;
 	struct mutex reg_mutex;
 	struct device *dev;
+	struct dsa_switch_ops ops;
 };
 
 struct qca8k_mib_desc {
diff --git a/drivers/net/ethernet/3com/3c515.c b/drivers/net/ethernet/3com/3c515.c
index 808abb6b3671..b15752267c8d 100644
--- a/drivers/net/ethernet/3com/3c515.c
+++ b/drivers/net/ethernet/3com/3c515.c
@@ -1521,7 +1521,7 @@ static void update_stats(int ioaddr, struct net_device *dev)
 static void set_rx_mode(struct net_device *dev)
 {
 	int ioaddr = dev->base_addr;
-	short new_mode;
+	unsigned short new_mode;
 
 	if (dev->flags & IFF_PROMISC) {
 		if (corkscrew_debug > 3)
diff --git a/drivers/net/ethernet/8390/mac8390.c b/drivers/net/ethernet/8390/mac8390.c
index 342ae08ec3c2..d60a86aa8aa8 100644
--- a/drivers/net/ethernet/8390/mac8390.c
+++ b/drivers/net/ethernet/8390/mac8390.c
@@ -153,8 +153,6 @@ static void dayna_block_input(struct net_device *dev, int count,
 static void dayna_block_output(struct net_device *dev, int count,
 			       const unsigned char *buf, int start_page);
 
-#define memcmp_withio(a, b, c)	memcmp((a), (void *)(b), (c))
-
 /* Slow Sane (16-bit chunk memory read/write) Cabletron uses this */
 static void slow_sane_get_8390_hdr(struct net_device *dev,
 				   struct e8390_pkt_hdr *hdr, int ring_page);
@@ -233,19 +231,26 @@ static enum mac8390_type mac8390_ident(struct nubus_rsrc *fres)
 
 static enum mac8390_access mac8390_testio(unsigned long membase)
 {
-	unsigned long outdata = 0xA5A0B5B0;
-	unsigned long indata =  0x00000000;
+	u32 outdata = 0xA5A0B5B0;
+	u32 indata = 0;
+
 	/* Try writing 32 bits */
-	memcpy_toio((void __iomem *)membase, &outdata, 4);
-	/* Now compare them */
-	if (memcmp_withio(&outdata, membase, 4) == 0)
+	nubus_writel(outdata, membase);
+	/* Now read it back */
+	indata = nubus_readl(membase);
+	if (outdata == indata)
 		return ACCESS_32;
+
+	outdata = 0xC5C0D5D0;
+	indata = 0;
+
 	/* Write 16 bit output */
 	word_memcpy_tocard(membase, &outdata, 4);
 	/* Now read it back */
 	word_memcpy_fromcard(&indata, membase, 4);
 	if (outdata == indata)
 		return ACCESS_16;
+
 	return ACCESS_UNKNOWN;
 }
 
diff --git a/drivers/net/ethernet/aeroflex/greth.c b/drivers/net/ethernet/aeroflex/greth.c
index 47e5984f16fb..3155f7fa83eb 100644
--- a/drivers/net/ethernet/aeroflex/greth.c
+++ b/drivers/net/ethernet/aeroflex/greth.c
@@ -613,7 +613,6 @@ static irqreturn_t greth_interrupt(int irq, void *dev_id)
 		napi_schedule(&greth->napi);
 	}
 
-	mmiowb();
 	spin_unlock(&greth->devlock);
 
 	return retval;
diff --git a/drivers/net/ethernet/alacritech/slicoss.c b/drivers/net/ethernet/alacritech/slicoss.c
index 16477aa6d61f..4f7e792e50e9 100644
--- a/drivers/net/ethernet/alacritech/slicoss.c
+++ b/drivers/net/ethernet/alacritech/slicoss.c
@@ -345,8 +345,6 @@ static void slic_set_rx_mode(struct net_device *dev)
 	if (sdev->promisc != set_promisc) {
 		sdev->promisc = set_promisc;
 		slic_configure_rcv(sdev);
-		/* make sure writes to receiver cant leak out of the lock */
-		mmiowb();
 	}
 	spin_unlock_bh(&sdev->link_lock);
 }
@@ -1461,8 +1459,6 @@ static netdev_tx_t slic_xmit(struct sk_buff *skb, struct net_device *dev)
 
 	if (slic_get_free_tx_descs(txq) < SLIC_MAX_REQ_TX_DESCS)
 		netif_stop_queue(dev);
-	/* make sure writes to io-memory cant leak out of tx queue lock */
-	mmiowb();
 
 	return NETDEV_TX_OK;
 drop_skb:
diff --git a/drivers/net/ethernet/amazon/ena/ena_com.c b/drivers/net/ethernet/amazon/ena/ena_com.c
index b17d435de09f..05798aa5bb73 100644
--- a/drivers/net/ethernet/amazon/ena/ena_com.c
+++ b/drivers/net/ethernet/amazon/ena/ena_com.c
@@ -2016,7 +2016,6 @@ void ena_com_aenq_intr_handler(struct ena_com_dev *dev, void *data)
 	mb();
 	writel_relaxed((u32)aenq->head,
 		       dev->reg_bar + ENA_REGS_AENQ_HEAD_DB_OFF);
-	mmiowb();
 }
 
 int ena_com_dev_reset(struct ena_com_dev *ena_dev,
diff --git a/drivers/net/ethernet/aquantia/atlantic/aq_ring.c b/drivers/net/ethernet/aquantia/atlantic/aq_ring.c
index 74550ccc7a20..e2ffb159cbe2 100644
--- a/drivers/net/ethernet/aquantia/atlantic/aq_ring.c
+++ b/drivers/net/ethernet/aquantia/atlantic/aq_ring.c
@@ -186,11 +186,12 @@ static void aq_rx_checksum(struct aq_ring_s *self,
 	}
 	if (buff->is_ip_cso) {
 		__skb_incr_checksum_unnecessary(skb);
-		if (buff->is_udp_cso || buff->is_tcp_cso)
-			__skb_incr_checksum_unnecessary(skb);
 	} else {
 		skb->ip_summed = CHECKSUM_NONE;
 	}
+
+	if (buff->is_udp_cso || buff->is_tcp_cso)
+		__skb_incr_checksum_unnecessary(skb);
 }
 
 #define AQ_SKB_ALIGN SKB_DATA_ALIGN(sizeof(struct skb_shared_info))
diff --git a/drivers/net/ethernet/atheros/atlx/atl1.c b/drivers/net/ethernet/atheros/atlx/atl1.c
index 9e07b469066a..f35c9a75be50 100644
--- a/drivers/net/ethernet/atheros/atlx/atl1.c
+++ b/drivers/net/ethernet/atheros/atlx/atl1.c
@@ -1721,7 +1721,7 @@ static void atl1_inc_smb(struct atl1_adapter *adapter)
 	adapter->soft_stats.scc += smb->tx_1_col;
 	adapter->soft_stats.mcc += smb->tx_2_col;
 	adapter->soft_stats.latecol += smb->tx_late_col;
-	adapter->soft_stats.tx_underun += smb->tx_underrun;
+	adapter->soft_stats.tx_underrun += smb->tx_underrun;
 	adapter->soft_stats.tx_trunc += smb->tx_trunc;
 	adapter->soft_stats.tx_pause += smb->tx_pause;
 
@@ -2439,7 +2439,6 @@ static netdev_tx_t atl1_xmit_frame(struct sk_buff *skb,
 	atl1_tx_map(adapter, skb, ptpd);
 	atl1_tx_queue(adapter, count, ptpd);
 	atl1_update_mailbox(adapter);
-	mmiowb();
 	return NETDEV_TX_OK;
 }
 
@@ -3179,7 +3178,7 @@ static struct atl1_stats atl1_gstrings_stats[] = {
 	{"tx_deferred_ok", ATL1_STAT(soft_stats.deffer)},
 	{"tx_single_coll_ok", ATL1_STAT(soft_stats.scc)},
 	{"tx_multi_coll_ok", ATL1_STAT(soft_stats.mcc)},
-	{"tx_underun", ATL1_STAT(soft_stats.tx_underun)},
+	{"tx_underrun", ATL1_STAT(soft_stats.tx_underrun)},
 	{"tx_trunc", ATL1_STAT(soft_stats.tx_trunc)},
 	{"tx_pause", ATL1_STAT(soft_stats.tx_pause)},
 	{"rx_pause", ATL1_STAT(soft_stats.rx_pause)},
diff --git a/drivers/net/ethernet/atheros/atlx/atl1.h b/drivers/net/ethernet/atheros/atlx/atl1.h
index 34a58cd846a0..eacff19ea05b 100644
--- a/drivers/net/ethernet/atheros/atlx/atl1.h
+++ b/drivers/net/ethernet/atheros/atlx/atl1.h
@@ -681,7 +681,7 @@ struct atl1_sft_stats {
 	u64 scc;		/* packets TX after a single collision */
 	u64 mcc;		/* packets TX after multiple collisions */
 	u64 latecol;		/* TX packets w/ late collisions */
-	u64 tx_underun;		/* TX packets aborted due to TX FIFO underrun
+	u64 tx_underrun;	/* TX packets aborted due to TX FIFO underrun
 				 * or TRD FIFO underrun */
 	u64 tx_trunc;		/* TX packets truncated due to size > MTU */
 	u64 rx_pause;		/* num Pause packets received. */
diff --git a/drivers/net/ethernet/atheros/atlx/atl2.c b/drivers/net/ethernet/atheros/atlx/atl2.c
index d99317b3d891..dd81c5863111 100644
--- a/drivers/net/ethernet/atheros/atlx/atl2.c
+++ b/drivers/net/ethernet/atheros/atlx/atl2.c
@@ -553,7 +553,7 @@ static void atl2_intr_tx(struct atl2_adapter *adapter)
 			netdev->stats.tx_aborted_errors++;
 		if (txs->late_col)
 			netdev->stats.tx_window_errors++;
-		if (txs->underun)
+		if (txs->underrun)
 			netdev->stats.tx_fifo_errors++;
 	} while (1);
 
@@ -908,7 +908,6 @@ static netdev_tx_t atl2_xmit_frame(struct sk_buff *skb,
 	ATL2_WRITE_REGW(&adapter->hw, REG_MB_TXD_WR_IDX,
 		(adapter->txd_write_ptr >> 2));
 
-	mmiowb();
 	dev_consume_skb_any(skb);
 	return NETDEV_TX_OK;
 }
diff --git a/drivers/net/ethernet/atheros/atlx/atl2.h b/drivers/net/ethernet/atheros/atlx/atl2.h
index c64a6bdfa7ae..25ec84cb4853 100644
--- a/drivers/net/ethernet/atheros/atlx/atl2.h
+++ b/drivers/net/ethernet/atheros/atlx/atl2.h
@@ -260,7 +260,7 @@ struct tx_pkt_status {
 	unsigned multi_col:1;
 	unsigned late_col:1;
 	unsigned abort_col:1;
-	unsigned underun:1;	/* current packet is aborted
+	unsigned underrun:1;	/* current packet is aborted
 				 * due to txram underrun */
 	unsigned:3;		/* reserved */
 	unsigned update:1;	/* always 1'b1 in tx_status_buf */
diff --git a/drivers/net/ethernet/broadcom/bnx2.c b/drivers/net/ethernet/broadcom/bnx2.c
index d63371d70bce..dfdd14eadd57 100644
--- a/drivers/net/ethernet/broadcom/bnx2.c
+++ b/drivers/net/ethernet/broadcom/bnx2.c
@@ -3305,8 +3305,6 @@ next_rx:
 
 	BNX2_WR(bp, rxr->rx_bseq_addr, rxr->rx_prod_bseq);
 
-	mmiowb();
-
 	return rx_pkt;
 
 }
@@ -6723,8 +6721,6 @@ bnx2_start_xmit(struct sk_buff *skb, struct net_device *dev)
 	BNX2_WR16(bp, txr->tx_bidx_addr, prod);
 	BNX2_WR(bp, txr->tx_bseq_addr, txr->tx_prod_bseq);
 
-	mmiowb();
-
 	txr->tx_prod = prod;
 
 	if (unlikely(bnx2_tx_avail(bp, txr) <= MAX_SKB_FRAGS)) {
diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c
index ecb1bd7eb508..0c8f5b546c6f 100644
--- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c
+++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c
@@ -4166,8 +4166,6 @@ netdev_tx_t bnx2x_start_xmit(struct sk_buff *skb, struct net_device *dev)
 
 	DOORBELL_RELAXED(bp, txdata->cid, txdata->tx_db.raw);
 
-	mmiowb();
-
 	txdata->tx_bd_prod += nbd;
 
 	if (unlikely(bnx2x_tx_avail(bp, txdata) < MAX_DESC_PER_TX_PKT)) {
diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.h b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.h
index 2462e7aa0c5d..2d57af9c061c 100644
--- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.h
+++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.h
@@ -527,8 +527,6 @@ static inline void bnx2x_update_rx_prod(struct bnx2x *bp,
 		REG_WR_RELAXED(bp, fp->ustorm_rx_prods_offset + i * 4,
 			       ((u32 *)&rx_prods)[i]);
 
-	mmiowb(); /* keep prod updates ordered */
-
 	DP(NETIF_MSG_RX_STATUS,
 	   "queue[%d]:  wrote  bd_prod %u  cqe_prod %u  sge_prod %u\n",
 	   fp->index, bd_prod, rx_comp_prod, rx_sge_prod);
@@ -653,7 +651,6 @@ static inline void bnx2x_igu_ack_sb_gen(struct bnx2x *bp, u8 igu_sb_id,
 	REG_WR(bp, igu_addr, cmd_data.sb_id_and_flags);
 
 	/* Make sure that ACK is written */
-	mmiowb();
 	barrier();
 }
 
@@ -674,7 +671,6 @@ static inline void bnx2x_hc_ack_sb(struct bnx2x *bp, u8 sb_id,
 	REG_WR(bp, hc_addr, (*(u32 *)&igu_ack));
 
 	/* Make sure that ACK is written */
-	mmiowb();
 	barrier();
 }
 
diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_ethtool.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_ethtool.c
index 749d0ef44371..0745cccd416d 100644
--- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_ethtool.c
+++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_ethtool.c
@@ -2623,7 +2623,6 @@ static int bnx2x_run_loopback(struct bnx2x *bp, int loopback_mode)
 	wmb();
 	DOORBELL_RELAXED(bp, txdata->cid, txdata->tx_db.raw);
 
-	mmiowb();
 	barrier();
 
 	num_pkts++;
diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c
index 626b491f7674..3716c828ff5d 100644
--- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c
+++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c
@@ -869,9 +869,6 @@ static void bnx2x_hc_int_disable(struct bnx2x *bp)
 	   "write %x to HC %d (addr 0x%x)\n",
 	   val, port, addr);
 
-	/* flush all outstanding writes */
-	mmiowb();
-
 	REG_WR(bp, addr, val);
 	if (REG_RD(bp, addr) != val)
 		BNX2X_ERR("BUG! Proper val not read from IGU!\n");
@@ -887,9 +884,6 @@ static void bnx2x_igu_int_disable(struct bnx2x *bp)
 
 	DP(NETIF_MSG_IFDOWN, "write %x to IGU\n", val);
 
-	/* flush all outstanding writes */
-	mmiowb();
-
 	REG_WR(bp, IGU_REG_PF_CONFIGURATION, val);
 	if (REG_RD(bp, IGU_REG_PF_CONFIGURATION) != val)
 		BNX2X_ERR("BUG! Proper val not read from IGU!\n");
@@ -1595,7 +1589,6 @@ static void bnx2x_hc_int_enable(struct bnx2x *bp)
 	/*
 	 * Ensure that HC_CONFIG is written before leading/trailing edge config
 	 */
-	mmiowb();
 	barrier();
 
 	if (!CHIP_IS_E1(bp)) {
@@ -1611,9 +1604,6 @@ static void bnx2x_hc_int_enable(struct bnx2x *bp)
 		REG_WR(bp, HC_REG_TRAILING_EDGE_0 + port*8, val);
 		REG_WR(bp, HC_REG_LEADING_EDGE_0 + port*8, val);
 	}
-
-	/* Make sure that interrupts are indeed enabled from here on */
-	mmiowb();
 }
 
 static void bnx2x_igu_int_enable(struct bnx2x *bp)
@@ -1674,9 +1664,6 @@ static void bnx2x_igu_int_enable(struct bnx2x *bp)
 
 	REG_WR(bp, IGU_REG_TRAILING_EDGE_LATCH, val);
 	REG_WR(bp, IGU_REG_LEADING_EDGE_LATCH, val);
-
-	/* Make sure that interrupts are indeed enabled from here on */
-	mmiowb();
 }
 
 void bnx2x_int_enable(struct bnx2x *bp)
@@ -3833,7 +3820,6 @@ static void bnx2x_sp_prod_update(struct bnx2x *bp)
 
 	REG_WR16_RELAXED(bp, BAR_XSTRORM_INTMEM + XSTORM_SPQ_PROD_OFFSET(func),
 			 bp->spq_prod_idx);
-	mmiowb();
 }
 
 /**
@@ -5244,7 +5230,6 @@ static void bnx2x_update_eq_prod(struct bnx2x *bp, u16 prod)
 {
 	/* No memory barriers */
 	storm_memset_eq_prod(bp, prod, BP_FUNC(bp));
-	mmiowb(); /* keep prod updates ordered */
 }
 
 static int  bnx2x_cnic_handle_cfc_del(struct bnx2x *bp, u32 cid,
@@ -6513,7 +6498,6 @@ void bnx2x_nic_init_cnic(struct bnx2x *bp)
 
 	/* flush all */
 	mb();
-	mmiowb();
 }
 
 void bnx2x_pre_irq_nic_init(struct bnx2x *bp)
@@ -6553,7 +6537,6 @@ void bnx2x_post_irq_nic_init(struct bnx2x *bp, u32 load_code)
 
 	/* flush all before enabling interrupts */
 	mb();
-	mmiowb();
 
 	bnx2x_int_enable(bp);
 
@@ -7775,12 +7758,10 @@ void bnx2x_igu_clear_sb_gen(struct bnx2x *bp, u8 func, u8 idu_sb_id, bool is_pf)
 	DP(NETIF_MSG_HW, "write 0x%08x to IGU(via GRC) addr 0x%x\n",
 			 data, igu_addr_data);
 	REG_WR(bp, igu_addr_data, data);
-	mmiowb();
 	barrier();
 	DP(NETIF_MSG_HW, "write 0x%08x to IGU(via GRC) addr 0x%x\n",
 			  ctl, igu_addr_ctl);
 	REG_WR(bp, igu_addr_ctl, ctl);
-	mmiowb();
 	barrier();
 
 	/* wait for clean up to finish */
@@ -9550,7 +9531,6 @@ static void bnx2x_set_234_gates(struct bnx2x *bp, bool close)
 
 	DP(NETIF_MSG_HW | NETIF_MSG_IFUP, "%s gates #2, #3 and #4\n",
 		close ? "closing" : "opening");
-	mmiowb();
 }
 
 #define SHARED_MF_CLP_MAGIC  0x80000000 /* `magic' bit */
@@ -9674,7 +9654,6 @@ static void bnx2x_pxp_prep(struct bnx2x *bp)
 	if (!CHIP_IS_E1(bp)) {
 		REG_WR(bp, PXP2_REG_RD_START_INIT, 0);
 		REG_WR(bp, PXP2_REG_RQ_RBC_DONE, 0);
-		mmiowb();
 	}
 }
 
@@ -9774,16 +9753,13 @@ static void bnx2x_process_kill_chip_reset(struct bnx2x *bp, bool global)
 	       reset_mask1 & (~not_reset_mask1));
 
 	barrier();
-	mmiowb();
 
 	REG_WR(bp, GRCBASE_MISC + MISC_REGISTERS_RESET_REG_2_SET,
 	       reset_mask2 & (~stay_reset2));
 
 	barrier();
-	mmiowb();
 
 	REG_WR(bp, GRCBASE_MISC + MISC_REGISTERS_RESET_REG_1_SET, reset_mask1);
-	mmiowb();
 }
 
 /**
@@ -9867,9 +9843,6 @@ static int bnx2x_process_kill(struct bnx2x *bp, bool global)
 	REG_WR(bp, MISC_REG_UNPREPARED, 0);
 	barrier();
 
-	/* Make sure all is written to the chip before the reset */
-	mmiowb();
-
 	/* Wait for 1ms to empty GLUE and PCI-E core queues,
 	 * PSWHST, GRC and PSWRD Tetris buffer.
 	 */
@@ -14828,7 +14801,6 @@ static int bnx2x_drv_ctl(struct net_device *dev, struct drv_ctl_info *ctl)
 		if (rc)
 			break;
 
-		mmiowb();
 		barrier();
 
 		/* Start accepting on iSCSI L2 ring */
@@ -14863,7 +14835,6 @@ static int bnx2x_drv_ctl(struct net_device *dev, struct drv_ctl_info *ctl)
 		if (!bnx2x_wait_sp_comp(bp, sp_bits))
 			BNX2X_ERR("rx_mode completion timed out!\n");
 
-		mmiowb();
 		barrier();
 
 		/* Unset iSCSI L2 MAC */
diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sp.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sp.c
index 7b22a6d8514c..80d250a6d048 100644
--- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sp.c
+++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sp.c
@@ -5039,7 +5039,6 @@ static inline int bnx2x_q_init(struct bnx2x *bp,
 	/* As no ramrod is sent, complete the command immediately  */
 	o->complete_cmd(bp, o, BNX2X_Q_CMD_INIT);
 
-	mmiowb();
 	smp_mb();
 
 	return 0;
diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sriov.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sriov.c
index c97b642e6537..0edbb0a76847 100644
--- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sriov.c
+++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sriov.c
@@ -100,13 +100,11 @@ static void bnx2x_vf_igu_ack_sb(struct bnx2x *bp, struct bnx2x_virtf *vf,
 	DP(NETIF_MSG_HW, "write 0x%08x to IGU(via GRC) addr 0x%x\n",
 	   cmd_data.sb_id_and_flags, igu_addr_data);
 	REG_WR(bp, igu_addr_data, cmd_data.sb_id_and_flags);
-	mmiowb();
 	barrier();
 
 	DP(NETIF_MSG_HW, "write 0x%08x to IGU(via GRC) addr 0x%x\n",
 	   ctl, igu_addr_ctl);
 	REG_WR(bp, igu_addr_ctl, ctl);
-	mmiowb();
 	barrier();
 }
 
diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_vfpf.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_vfpf.c
index a9bdc21873d3..0752b7fa4d9c 100644
--- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_vfpf.c
+++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_vfpf.c
@@ -172,8 +172,6 @@ static int bnx2x_send_msg2pf(struct bnx2x *bp, u8 *done, dma_addr_t msg_mapping)
 	/* Trigger the PF FW */
 	writeb_relaxed(1, &zone_data->trigger.vf_pf_channel.addr_valid);
 
-	mmiowb();
-
 	/* Wait for PF to complete */
 	while ((tout >= 0) && (!*done)) {
 		msleep(interval);
@@ -957,7 +955,7 @@ int bnx2x_vfpf_update_vlan(struct bnx2x *bp, u16 vid, u8 vf_qid, bool add)
 	bnx2x_sample_bulletin(bp);
 
 	if (bp->shadow_bulletin.content.valid_bitmap & 1 << VLAN_VALID) {
-		BNX2X_ERR("Hypervisor will dicline the request, avoiding\n");
+		BNX2X_ERR("Hypervisor will decline the request, avoiding\n");
 		rc = -EINVAL;
 		goto out;
 	}
@@ -1179,7 +1177,6 @@ static void bnx2x_vf_mbx_resp_send_msg(struct bnx2x *bp,
 
 	/* ack the FW */
 	storm_memset_vf_mbx_ack(bp, vf->abs_vfid);
-	mmiowb();
 
 	/* copy the response header including status-done field,
 	 * must be last dmae, must be after FW is acked
@@ -2174,7 +2171,6 @@ static void bnx2x_vf_mbx_request(struct bnx2x *bp, struct bnx2x_virtf *vf,
 		 */
 		storm_memset_vf_mbx_ack(bp, vf->abs_vfid);
 		/* Firmware ack should be written before unlocking channel */
-		mmiowb();
 		bnx2x_unlock_vf_pf_channel(bp, vf, mbx->first_tlv.tl.type);
 	}
 }
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
index 0bb9d7b3a2b6..2a4341708c0f 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
@@ -556,8 +556,6 @@ normal_tx:
 
 tx_done:
 
-	mmiowb();
-
 	if (unlikely(bnxt_tx_avail(bp, txr) <= MAX_SKB_FRAGS + 1)) {
 		if (skb->xmit_more && !tx_buf->is_push)
 			bnxt_db_write(bp, &txr->tx_db, prod);
@@ -1133,6 +1131,8 @@ static void bnxt_tpa_start(struct bnxt *bp, struct bnxt_rx_ring_info *rxr,
 	tpa_info = &rxr->rx_tpa[agg_id];
 
 	if (unlikely(cons != rxr->rx_next_cons)) {
+		netdev_warn(bp->dev, "TPA cons %x != expected cons %x\n",
+			    cons, rxr->rx_next_cons);
 		bnxt_sched_reset(bp, rxr);
 		return;
 	}
@@ -1585,15 +1585,17 @@ static int bnxt_rx_pkt(struct bnxt *bp, struct bnxt_cp_ring_info *cpr,
 	}
 
 	cons = rxcmp->rx_cmp_opaque;
-	rx_buf = &rxr->rx_buf_ring[cons];
-	data = rx_buf->data;
-	data_ptr = rx_buf->data_ptr;
 	if (unlikely(cons != rxr->rx_next_cons)) {
 		int rc1 = bnxt_discard_rx(bp, cpr, raw_cons, rxcmp);
 
+		netdev_warn(bp->dev, "RX cons %x != expected cons %x\n",
+			    cons, rxr->rx_next_cons);
 		bnxt_sched_reset(bp, rxr);
 		return rc1;
 	}
+	rx_buf = &rxr->rx_buf_ring[cons];
+	data = rx_buf->data;
+	data_ptr = rx_buf->data_ptr;
 	prefetch(data_ptr);
 
 	misc = le32_to_cpu(rxcmp->rx_cmp_misc_v1);
@@ -1610,12 +1612,18 @@ static int bnxt_rx_pkt(struct bnxt *bp, struct bnxt_cp_ring_info *cpr,
 
 	rx_buf->data = NULL;
 	if (rxcmp1->rx_cmp_cfa_code_errors_v2 & RX_CMP_L2_ERRORS) {
+		u32 rx_err = le32_to_cpu(rxcmp1->rx_cmp_cfa_code_errors_v2);
+
 		bnxt_reuse_rx_data(rxr, cons, data);
 		if (agg_bufs)
 			bnxt_reuse_rx_agg_bufs(cpr, cp_cons, agg_bufs);
 
 		rc = -EIO;
-		goto next_rx;
+		if (rx_err & RX_CMPL_ERRORS_BUFFER_ERROR_MASK) {
+			netdev_warn(bp->dev, "RX buffer error %x\n", rx_err);
+			bnxt_sched_reset(bp, rxr);
+		}
+		goto next_rx_no_len;
 	}
 
 	len = le32_to_cpu(rxcmp->rx_cmp_len_flags_type) >> RX_CMP_LEN_SHIFT;
@@ -1696,12 +1704,13 @@ static int bnxt_rx_pkt(struct bnxt *bp, struct bnxt_cp_ring_info *cpr,
 	rc = 1;
 
 next_rx:
-	rxr->rx_prod = NEXT_RX(prod);
-	rxr->rx_next_cons = NEXT_RX(cons);
-
 	cpr->rx_packets += 1;
 	cpr->rx_bytes += len;
 
+next_rx_no_len:
+	rxr->rx_prod = NEXT_RX(prod);
+	rxr->rx_next_cons = NEXT_RX(cons);
+
 next_rx_no_prod_no_len:
 	*raw_cons = tmp_raw_cons;
 
@@ -2123,7 +2132,6 @@ static int bnxt_poll(struct napi_struct *napi, int budget)
 			       &dim_sample);
 		net_dim(&cpr->dim, dim_sample);
 	}
-	mmiowb();
 	return work_done;
 }
 
@@ -5125,10 +5133,10 @@ static void bnxt_hwrm_ring_free(struct bnxt *bp, bool close_path)
 	for (i = 0; i < bp->tx_nr_rings; i++) {
 		struct bnxt_tx_ring_info *txr = &bp->tx_ring[i];
 		struct bnxt_ring_struct *ring = &txr->tx_ring_struct;
-		u32 cmpl_ring_id;
 
-		cmpl_ring_id = bnxt_cp_ring_for_tx(bp, txr);
 		if (ring->fw_ring_id != INVALID_HW_RING_ID) {
+			u32 cmpl_ring_id = bnxt_cp_ring_for_tx(bp, txr);
+
 			hwrm_ring_free_send_msg(bp, ring,
 						RING_FREE_REQ_RING_TYPE_TX,
 						close_path ? cmpl_ring_id :
@@ -5141,10 +5149,10 @@ static void bnxt_hwrm_ring_free(struct bnxt *bp, bool close_path)
 		struct bnxt_rx_ring_info *rxr = &bp->rx_ring[i];
 		struct bnxt_ring_struct *ring = &rxr->rx_ring_struct;
 		u32 grp_idx = rxr->bnapi->index;
-		u32 cmpl_ring_id;
 
-		cmpl_ring_id = bnxt_cp_ring_for_rx(bp, rxr);
 		if (ring->fw_ring_id != INVALID_HW_RING_ID) {
+			u32 cmpl_ring_id = bnxt_cp_ring_for_rx(bp, rxr);
+
 			hwrm_ring_free_send_msg(bp, ring,
 						RING_FREE_REQ_RING_TYPE_RX,
 						close_path ? cmpl_ring_id :
@@ -5163,10 +5171,10 @@ static void bnxt_hwrm_ring_free(struct bnxt *bp, bool close_path)
 		struct bnxt_rx_ring_info *rxr = &bp->rx_ring[i];
 		struct bnxt_ring_struct *ring = &rxr->rx_agg_ring_struct;
 		u32 grp_idx = rxr->bnapi->index;
-		u32 cmpl_ring_id;
 
-		cmpl_ring_id = bnxt_cp_ring_for_rx(bp, rxr);
 		if (ring->fw_ring_id != INVALID_HW_RING_ID) {
+			u32 cmpl_ring_id = bnxt_cp_ring_for_rx(bp, rxr);
+
 			hwrm_ring_free_send_msg(bp, ring, type,
 						close_path ? cmpl_ring_id :
 						INVALID_HW_RING_ID);
@@ -5305,17 +5313,16 @@ __bnxt_hwrm_reserve_pf_rings(struct bnxt *bp, struct hwrm_func_cfg_input *req,
 	req->num_tx_rings = cpu_to_le16(tx_rings);
 	if (BNXT_NEW_RM(bp)) {
 		enables |= rx_rings ? FUNC_CFG_REQ_ENABLES_NUM_RX_RINGS : 0;
+		enables |= stats ? FUNC_CFG_REQ_ENABLES_NUM_STAT_CTXS : 0;
 		if (bp->flags & BNXT_FLAG_CHIP_P5) {
 			enables |= cp_rings ? FUNC_CFG_REQ_ENABLES_NUM_MSIX : 0;
 			enables |= tx_rings + ring_grps ?
-				   FUNC_CFG_REQ_ENABLES_NUM_CMPL_RINGS |
-				   FUNC_CFG_REQ_ENABLES_NUM_STAT_CTXS : 0;
+				   FUNC_CFG_REQ_ENABLES_NUM_CMPL_RINGS : 0;
 			enables |= rx_rings ?
 				FUNC_CFG_REQ_ENABLES_NUM_RSSCOS_CTXS : 0;
 		} else {
 			enables |= cp_rings ?
-				   FUNC_CFG_REQ_ENABLES_NUM_CMPL_RINGS |
-				   FUNC_CFG_REQ_ENABLES_NUM_STAT_CTXS : 0;
+				   FUNC_CFG_REQ_ENABLES_NUM_CMPL_RINGS : 0;
 			enables |= ring_grps ?
 				   FUNC_CFG_REQ_ENABLES_NUM_HW_RING_GRPS |
 				   FUNC_CFG_REQ_ENABLES_NUM_RSSCOS_CTXS : 0;
@@ -5355,14 +5362,13 @@ __bnxt_hwrm_reserve_vf_rings(struct bnxt *bp,
 	enables |= tx_rings ? FUNC_VF_CFG_REQ_ENABLES_NUM_TX_RINGS : 0;
 	enables |= rx_rings ? FUNC_VF_CFG_REQ_ENABLES_NUM_RX_RINGS |
 			      FUNC_VF_CFG_REQ_ENABLES_NUM_RSSCOS_CTXS : 0;
+	enables |= stats ? FUNC_VF_CFG_REQ_ENABLES_NUM_STAT_CTXS : 0;
 	if (bp->flags & BNXT_FLAG_CHIP_P5) {
 		enables |= tx_rings + ring_grps ?
-			   FUNC_VF_CFG_REQ_ENABLES_NUM_CMPL_RINGS |
-			   FUNC_VF_CFG_REQ_ENABLES_NUM_STAT_CTXS : 0;
+			   FUNC_VF_CFG_REQ_ENABLES_NUM_CMPL_RINGS : 0;
 	} else {
 		enables |= cp_rings ?
-			   FUNC_VF_CFG_REQ_ENABLES_NUM_CMPL_RINGS |
-			   FUNC_VF_CFG_REQ_ENABLES_NUM_STAT_CTXS : 0;
+			   FUNC_VF_CFG_REQ_ENABLES_NUM_CMPL_RINGS : 0;
 		enables |= ring_grps ?
 			   FUNC_VF_CFG_REQ_ENABLES_NUM_HW_RING_GRPS : 0;
 	}
@@ -6743,6 +6749,7 @@ static int bnxt_hwrm_port_qstats_ext(struct bnxt *bp)
 	struct hwrm_queue_pri2cos_qcfg_input req2 = {0};
 	struct hwrm_port_qstats_ext_input req = {0};
 	struct bnxt_pf_info *pf = &bp->pf;
+	u32 tx_stat_size;
 	int rc;
 
 	if (!(bp->flags & BNXT_FLAG_PORT_STATS_EXT))
@@ -6752,13 +6759,16 @@ static int bnxt_hwrm_port_qstats_ext(struct bnxt *bp)
 	req.port_id = cpu_to_le16(pf->port_id);
 	req.rx_stat_size = cpu_to_le16(sizeof(struct rx_port_stats_ext));
 	req.rx_stat_host_addr = cpu_to_le64(bp->hw_rx_port_stats_ext_map);
-	req.tx_stat_size = cpu_to_le16(sizeof(struct tx_port_stats_ext));
+	tx_stat_size = bp->hw_tx_port_stats_ext ?
+		       sizeof(*bp->hw_tx_port_stats_ext) : 0;
+	req.tx_stat_size = cpu_to_le16(tx_stat_size);
 	req.tx_stat_host_addr = cpu_to_le64(bp->hw_tx_port_stats_ext_map);
 	mutex_lock(&bp->hwrm_cmd_lock);
 	rc = _hwrm_send_message(bp, &req, sizeof(req), HWRM_CMD_TIMEOUT);
 	if (!rc) {
 		bp->fw_rx_stats_ext_size = le16_to_cpu(resp->rx_stat_size) / 8;
-		bp->fw_tx_stats_ext_size = le16_to_cpu(resp->tx_stat_size) / 8;
+		bp->fw_tx_stats_ext_size = tx_stat_size ?
+			le16_to_cpu(resp->tx_stat_size) / 8 : 0;
 	} else {
 		bp->fw_rx_stats_ext_size = 0;
 		bp->fw_tx_stats_ext_size = 0;
@@ -8951,8 +8961,15 @@ static int bnxt_cfg_rx_mode(struct bnxt *bp)
 
 skip_uc:
 	rc = bnxt_hwrm_cfa_l2_set_rx_mask(bp, 0);
+	if (rc && vnic->mc_list_count) {
+		netdev_info(bp->dev, "Failed setting MC filters rc: %d, turning on ALL_MCAST mode\n",
+			    rc);
+		vnic->rx_mask |= CFA_L2_SET_RX_MASK_REQ_MASK_ALL_MCAST;
+		vnic->mc_list_count = 0;
+		rc = bnxt_hwrm_cfa_l2_set_rx_mask(bp, 0);
+	}
 	if (rc)
-		netdev_err(bp->dev, "HWRM cfa l2 rx mask failure rc: %x\n",
+		netdev_err(bp->dev, "HWRM cfa l2 rx mask failure rc: %d\n",
 			   rc);
 
 	return rc;
@@ -10675,6 +10692,7 @@ init_err_cleanup_tc:
 	bnxt_clear_int_mode(bp);
 
 init_err_pci_clean:
+	bnxt_free_hwrm_short_cmd_req(bp);
 	bnxt_free_hwrm_resources(bp);
 	bnxt_free_ctx_mem(bp);
 	kfree(bp->ctx);
diff --git a/drivers/net/ethernet/broadcom/tg3.c b/drivers/net/ethernet/broadcom/tg3.c
index 328373e0578f..2aebd4bbb67d 100644
--- a/drivers/net/ethernet/broadcom/tg3.c
+++ b/drivers/net/ethernet/broadcom/tg3.c
@@ -1073,7 +1073,6 @@ static void tg3_int_reenable(struct tg3_napi *tnapi)
 	struct tg3 *tp = tnapi->tp;
 
 	tw32_mailbox(tnapi->int_mbox, tnapi->last_tag << 24);
-	mmiowb();
 
 	/* When doing tagged status, this work check is unnecessary.
 	 * The last_tag we write above tells the chip which piece of
@@ -4283,7 +4282,7 @@ static void tg3_power_down(struct tg3 *tp)
 	pci_set_power_state(tp->pdev, PCI_D3hot);
 }
 
-static void tg3_aux_stat_to_speed_duplex(struct tg3 *tp, u32 val, u16 *speed, u8 *duplex)
+static void tg3_aux_stat_to_speed_duplex(struct tg3 *tp, u32 val, u32 *speed, u8 *duplex)
 {
 	switch (val & MII_TG3_AUX_STAT_SPDMASK) {
 	case MII_TG3_AUX_STAT_10HALF:
@@ -4787,7 +4786,7 @@ static int tg3_setup_copper_phy(struct tg3 *tp, bool force_reset)
 	bool current_link_up;
 	u32 bmsr, val;
 	u32 lcl_adv, rmt_adv;
-	u16 current_speed;
+	u32 current_speed;
 	u8 current_duplex;
 	int i, err;
 
@@ -5719,7 +5718,7 @@ out:
 static int tg3_setup_fiber_phy(struct tg3 *tp, bool force_reset)
 {
 	u32 orig_pause_cfg;
-	u16 orig_active_speed;
+	u32 orig_active_speed;
 	u8 orig_active_duplex;
 	u32 mac_status;
 	bool current_link_up;
@@ -5823,7 +5822,7 @@ static int tg3_setup_fiber_mii_phy(struct tg3 *tp, bool force_reset)
 {
 	int err = 0;
 	u32 bmsr, bmcr;
-	u16 current_speed = SPEED_UNKNOWN;
+	u32 current_speed = SPEED_UNKNOWN;
 	u8 current_duplex = DUPLEX_UNKNOWN;
 	bool current_link_up = false;
 	u32 local_adv, remote_adv, sgsr;
@@ -6999,7 +6998,6 @@ next_pkt_nopost:
 			tw32_rx_mbox(TG3_RX_JMB_PROD_IDX_REG,
 				     tpr->rx_jmb_prod_idx);
 		}
-		mmiowb();
 	} else if (work_mask) {
 		/* rx_std_buffers[] and rx_jmb_buffers[] entries must be
 		 * updated before the producer indices can be updated.
@@ -7210,8 +7208,6 @@ static int tg3_poll_work(struct tg3_napi *tnapi, int work_done, int budget)
 			tw32_rx_mbox(TG3_RX_JMB_PROD_IDX_REG,
 				     dpr->rx_jmb_prod_idx);
 
-		mmiowb();
-
 		if (err)
 			tw32_f(HOSTCC_MODE, tp->coal_now);
 	}
@@ -7278,7 +7274,6 @@ static int tg3_poll_msix(struct napi_struct *napi, int budget)
 						  HOSTCC_MODE_ENABLE |
 						  tnapi->coal_now);
 			}
-			mmiowb();
 			break;
 		}
 	}
@@ -8159,7 +8154,6 @@ static netdev_tx_t tg3_start_xmit(struct sk_buff *skb, struct net_device *dev)
 	if (!skb->xmit_more || netif_xmit_stopped(txq)) {
 		/* Packets are ready, update Tx producer idx on card. */
 		tw32_tx_mbox(tnapi->prodmbox, entry);
-		mmiowb();
 	}
 
 	return NETDEV_TX_OK;
diff --git a/drivers/net/ethernet/broadcom/tg3.h b/drivers/net/ethernet/broadcom/tg3.h
index a772a33b685c..6953d0546acb 100644
--- a/drivers/net/ethernet/broadcom/tg3.h
+++ b/drivers/net/ethernet/broadcom/tg3.h
@@ -2873,7 +2873,7 @@ struct tg3_tx_ring_info {
 struct tg3_link_config {
 	/* Describes what we're trying to get. */
 	u32				advertising;
-	u16				speed;
+	u32				speed;
 	u8				duplex;
 	u8				autoneg;
 	u8				flowctrl;
@@ -2882,7 +2882,7 @@ struct tg3_link_config {
 	u8				active_flowctrl;
 
 	u8				active_duplex;
-	u16				active_speed;
+	u32				active_speed;
 	u32				rmt_adv;
 };
 
diff --git a/drivers/net/ethernet/cadence/macb_main.c b/drivers/net/ethernet/cadence/macb_main.c
index ad099fd01b45..3da2795e2486 100644
--- a/drivers/net/ethernet/cadence/macb_main.c
+++ b/drivers/net/ethernet/cadence/macb_main.c
@@ -898,7 +898,9 @@ static void macb_tx_interrupt(struct macb_queue *queue)
 
 			/* First, update TX stats if needed */
 			if (skb) {
-				if (gem_ptp_do_txstamp(queue, skb, desc) == 0) {
+				if (unlikely(skb_shinfo(skb)->tx_flags &
+					     SKBTX_HW_TSTAMP) &&
+				    gem_ptp_do_txstamp(queue, skb, desc) == 0) {
 					/* skb now belongs to timestamp buffer
 					 * and will be removed later
 					 */
@@ -3370,14 +3372,20 @@ static int macb_clk_init(struct platform_device *pdev, struct clk **pclk,
 		*hclk = devm_clk_get(&pdev->dev, "hclk");
 	}
 
-	if (IS_ERR(*pclk)) {
+	if (IS_ERR_OR_NULL(*pclk)) {
 		err = PTR_ERR(*pclk);
+		if (!err)
+			err = -ENODEV;
+
 		dev_err(&pdev->dev, "failed to get macb_clk (%u)\n", err);
 		return err;
 	}
 
-	if (IS_ERR(*hclk)) {
+	if (IS_ERR_OR_NULL(*hclk)) {
 		err = PTR_ERR(*hclk);
+		if (!err)
+			err = -ENODEV;
+
 		dev_err(&pdev->dev, "failed to get hclk (%u)\n", err);
 		return err;
 	}
diff --git a/drivers/net/ethernet/cavium/liquidio/cn66xx_device.c b/drivers/net/ethernet/cavium/liquidio/cn66xx_device.c
index 2df7440f58df..39643be8c30a 100644
--- a/drivers/net/ethernet/cavium/liquidio/cn66xx_device.c
+++ b/drivers/net/ethernet/cavium/liquidio/cn66xx_device.c
@@ -38,9 +38,6 @@ int lio_cn6xxx_soft_reset(struct octeon_device *oct)
 	lio_pci_readq(oct, CN6XXX_CIU_SOFT_RST);
 	lio_pci_writeq(oct, 1, CN6XXX_CIU_SOFT_RST);
 
-	/* make sure that the reset is written before starting timer */
-	mmiowb();
-
 	/* Wait for 10ms as Octeon resets. */
 	mdelay(100);
 
@@ -487,9 +484,6 @@ void lio_cn6xxx_disable_interrupt(struct octeon_device *oct,
 
 	/* Disable Interrupts */
 	writeq(0, cn6xxx->intr_enb_reg64);
-
-	/* make sure interrupts are really disabled */
-	mmiowb();
 }
 
 static void lio_cn6xxx_get_pcie_qlmport(struct octeon_device *oct)
@@ -555,10 +549,6 @@ static int lio_cn6xxx_process_droq_intr_regs(struct octeon_device *oct)
 				value &= ~(1 << oq_no);
 				octeon_write_csr(oct, reg, value);
 
-				/* Ensure that the enable register is written.
-				 */
-				mmiowb();
-
 				spin_unlock(&cn6xxx->lock_for_droq_int_enb_reg);
 			}
 		}
diff --git a/drivers/net/ethernet/cavium/liquidio/octeon_device.c b/drivers/net/ethernet/cavium/liquidio/octeon_device.c
index ce8c3f818666..934115d18488 100644
--- a/drivers/net/ethernet/cavium/liquidio/octeon_device.c
+++ b/drivers/net/ethernet/cavium/liquidio/octeon_device.c
@@ -1449,7 +1449,6 @@ void lio_enable_irq(struct octeon_droq *droq, struct octeon_instr_queue *iq)
 		iq->pkt_in_done -= iq->pkts_processed;
 		iq->pkts_processed = 0;
 		/* this write needs to be flushed before we release the lock */
-		mmiowb();
 		spin_unlock_bh(&iq->lock);
 		oct = iq->oct_dev;
 	}
diff --git a/drivers/net/ethernet/cavium/liquidio/octeon_droq.c b/drivers/net/ethernet/cavium/liquidio/octeon_droq.c
index a0c099f71524..017169023cca 100644
--- a/drivers/net/ethernet/cavium/liquidio/octeon_droq.c
+++ b/drivers/net/ethernet/cavium/liquidio/octeon_droq.c
@@ -513,8 +513,6 @@ int octeon_retry_droq_refill(struct octeon_droq *droq)
 		 */
 		wmb();
 		writel(desc_refilled, droq->pkts_credit_reg);
-		/* make sure mmio write completes */
-		mmiowb();
 
 		if (pkts_credit + desc_refilled >= CN23XX_SLI_DEF_BP)
 			reschedule = 0;
@@ -712,8 +710,6 @@ octeon_droq_fast_process_packets(struct octeon_device *oct,
 				 */
 				wmb();
 				writel(desc_refilled, droq->pkts_credit_reg);
-				/* make sure mmio write completes */
-				mmiowb();
 			}
 		}
 	}                       /* for (each packet)... */
diff --git a/drivers/net/ethernet/cavium/liquidio/request_manager.c b/drivers/net/ethernet/cavium/liquidio/request_manager.c
index c6f4cbda040f..fcf20a8f92d9 100644
--- a/drivers/net/ethernet/cavium/liquidio/request_manager.c
+++ b/drivers/net/ethernet/cavium/liquidio/request_manager.c
@@ -278,7 +278,6 @@ ring_doorbell(struct octeon_device *oct, struct octeon_instr_queue *iq)
 	if (atomic_read(&oct->status) == OCT_DEV_RUNNING) {
 		writel(iq->fill_cnt, iq->doorbell_reg);
 		/* make sure doorbell write goes through */
-		mmiowb();
 		iq->fill_cnt = 0;
 		iq->last_db_time = jiffies;
 		return;
diff --git a/drivers/net/ethernet/cavium/thunder/nicvf_main.c b/drivers/net/ethernet/cavium/thunder/nicvf_main.c
index aa2be4807191..c032bef1b776 100644
--- a/drivers/net/ethernet/cavium/thunder/nicvf_main.c
+++ b/drivers/net/ethernet/cavium/thunder/nicvf_main.c
@@ -32,6 +32,13 @@
 #define DRV_NAME	"nicvf"
 #define DRV_VERSION	"1.0"
 
+/* NOTE: Packets bigger than 1530 are split across multiple pages and XDP needs
+ * the buffer to be contiguous. Allow XDP to be set up only if we don't exceed
+ * this value, keeping headroom for the 14 byte Ethernet header and two
+ * VLAN tags (for QinQ)
+ */
+#define MAX_XDP_MTU	(1530 - ETH_HLEN - VLAN_HLEN * 2)
+
 /* Supported devices */
 static const struct pci_device_id nicvf_id_table[] = {
 	{ PCI_DEVICE_SUB(PCI_VENDOR_ID_CAVIUM,
@@ -1328,10 +1335,11 @@ int nicvf_stop(struct net_device *netdev)
 	struct nicvf_cq_poll *cq_poll = NULL;
 	union nic_mbx mbx = {};
 
-	cancel_delayed_work_sync(&nic->link_change_work);
-
 	/* wait till all queued set_rx_mode tasks completes */
-	drain_workqueue(nic->nicvf_rx_mode_wq);
+	if (nic->nicvf_rx_mode_wq) {
+		cancel_delayed_work_sync(&nic->link_change_work);
+		drain_workqueue(nic->nicvf_rx_mode_wq);
+	}
 
 	mbx.msg.msg = NIC_MBOX_MSG_SHUTDOWN;
 	nicvf_send_msg_to_pf(nic, &mbx);
@@ -1452,7 +1460,8 @@ int nicvf_open(struct net_device *netdev)
 	struct nicvf_cq_poll *cq_poll = NULL;
 
 	/* wait till all queued set_rx_mode tasks completes if any */
-	drain_workqueue(nic->nicvf_rx_mode_wq);
+	if (nic->nicvf_rx_mode_wq)
+		drain_workqueue(nic->nicvf_rx_mode_wq);
 
 	netif_carrier_off(netdev);
 
@@ -1550,10 +1559,12 @@ int nicvf_open(struct net_device *netdev)
 	/* Send VF config done msg to PF */
 	nicvf_send_cfg_done(nic);
 
-	INIT_DELAYED_WORK(&nic->link_change_work,
-			  nicvf_link_status_check_task);
-	queue_delayed_work(nic->nicvf_rx_mode_wq,
-			   &nic->link_change_work, 0);
+	if (nic->nicvf_rx_mode_wq) {
+		INIT_DELAYED_WORK(&nic->link_change_work,
+				  nicvf_link_status_check_task);
+		queue_delayed_work(nic->nicvf_rx_mode_wq,
+				   &nic->link_change_work, 0);
+	}
 
 	return 0;
 cleanup:
@@ -1578,6 +1589,15 @@ static int nicvf_change_mtu(struct net_device *netdev, int new_mtu)
 	struct nicvf *nic = netdev_priv(netdev);
 	int orig_mtu = netdev->mtu;
 
+	/* For now just support only the usual MTU sized frames,
+	 * plus some headroom for VLAN, QinQ.
+	 */
+	if (nic->xdp_prog && new_mtu > MAX_XDP_MTU) {
+		netdev_warn(netdev, "Jumbo frames not yet supported with XDP, current MTU %d.\n",
+			    netdev->mtu);
+		return -EINVAL;
+	}
+
 	netdev->mtu = new_mtu;
 
 	if (!netif_running(netdev))
@@ -1826,8 +1846,10 @@ static int nicvf_xdp_setup(struct nicvf *nic, struct bpf_prog *prog)
 	bool bpf_attached = false;
 	int ret = 0;
 
-	/* For now just support only the usual MTU sized frames */
-	if (prog && (dev->mtu > 1500)) {
+	/* For now just support only the usual MTU sized frames,
+	 * plus some headroom for VLAN, QinQ.
+	 */
+	if (prog && dev->mtu > MAX_XDP_MTU) {
 		netdev_warn(dev, "Jumbo frames not yet supported with XDP, current MTU %d.\n",
 			    dev->mtu);
 		return -EOPNOTSUPP;
diff --git a/drivers/net/ethernet/cavium/thunder/nicvf_queues.c b/drivers/net/ethernet/cavium/thunder/nicvf_queues.c
index 5b4d3badcb73..e246f9733bb8 100644
--- a/drivers/net/ethernet/cavium/thunder/nicvf_queues.c
+++ b/drivers/net/ethernet/cavium/thunder/nicvf_queues.c
@@ -105,20 +105,19 @@ static inline struct pgcache *nicvf_alloc_page(struct nicvf *nic,
 	/* Check if page can be recycled */
 	if (page) {
 		ref_count = page_ref_count(page);
-		/* Check if this page has been used once i.e 'put_page'
-		 * called after packet transmission i.e internal ref_count
-		 * and page's ref_count are equal i.e page can be recycled.
+		/* This page can be recycled if internal ref_count and page's
+		 * ref_count are equal, indicating that the page has been used
+		 * once for packet transmission. For non-XDP mode, internal
+		 * ref_count is always '1'.
 		 */
-		if (rbdr->is_xdp && (ref_count == pgcache->ref_count))
-			pgcache->ref_count--;
-		else
-			page = NULL;
-
-		/* In non-XDP mode, page's ref_count needs to be '1' for it
-		 * to be recycled.
-		 */
-		if (!rbdr->is_xdp && (ref_count != 1))
+		if (rbdr->is_xdp) {
+			if (ref_count == pgcache->ref_count)
+				pgcache->ref_count--;
+			else
+				page = NULL;
+		} else if (ref_count != 1) {
 			page = NULL;
+		}
 	}
 
 	if (!page) {
@@ -365,11 +364,10 @@ static void nicvf_free_rbdr(struct nicvf *nic, struct rbdr *rbdr)
 	while (head < rbdr->pgcnt) {
 		pgcache = &rbdr->pgcache[head];
 		if (pgcache->page && page_ref_count(pgcache->page) != 0) {
-			if (!rbdr->is_xdp) {
-				put_page(pgcache->page);
-				continue;
+			if (rbdr->is_xdp) {
+				page_ref_sub(pgcache->page,
+					     pgcache->ref_count - 1);
 			}
-			page_ref_sub(pgcache->page, pgcache->ref_count - 1);
 			put_page(pgcache->page);
 		}
 		head++;
diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_debugfs.c b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_debugfs.c
index 3130b43bba52..02959035ed3f 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_debugfs.c
+++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_debugfs.c
@@ -2620,7 +2620,7 @@ static inline struct port_info *ethqset2pinfo(struct adapter *adap, int qset)
 	}
 
 	/* should never happen! */
-	BUG_ON(1);
+	BUG();
 	return NULL;
 }
 
diff --git a/drivers/net/ethernet/chelsio/cxgb4/sge.c b/drivers/net/ethernet/chelsio/cxgb4/sge.c
index 88773ca58e6b..b3da81e90132 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/sge.c
+++ b/drivers/net/ethernet/chelsio/cxgb4/sge.c
@@ -476,7 +476,7 @@ static inline int get_buf_size(struct adapter *adapter,
 		break;
 
 	default:
-		BUG_ON(1);
+		BUG();
 	}
 
 	return buf_size;
diff --git a/drivers/net/ethernet/chelsio/libcxgb/libcxgb_ppm.c b/drivers/net/ethernet/chelsio/libcxgb/libcxgb_ppm.c
index 74849be5f004..e2919005ead3 100644
--- a/drivers/net/ethernet/chelsio/libcxgb/libcxgb_ppm.c
+++ b/drivers/net/ethernet/chelsio/libcxgb/libcxgb_ppm.c
@@ -354,7 +354,10 @@ static struct cxgbi_ppm_pool *ppm_alloc_cpu_pool(unsigned int *total,
 		ppmax = max;
 
 	/* pool size must be multiple of unsigned long */
-	bmap = BITS_TO_LONGS(ppmax);
+	bmap = ppmax / BITS_PER_TYPE(unsigned long);
+	if (!bmap)
+		return NULL;
+
 	ppmax = (bmap * sizeof(unsigned long)) << 3;
 
 	alloc_sz = sizeof(*pools) + sizeof(unsigned long) * bmap;
@@ -402,6 +405,10 @@ int cxgbi_ppm_init(void **ppm_pp, struct net_device *ndev,
 	if (reserve_factor) {
 		ppmax_pool = ppmax / reserve_factor;
 		pool = ppm_alloc_cpu_pool(&ppmax_pool, &pool_index_max);
+		if (!pool) {
+			ppmax_pool = 0;
+			reserve_factor = 0;
+		}
 
 		pr_debug("%s: ppmax %u, cpu total %u, per cpu %u.\n",
 			 ndev->name, ppmax, ppmax_pool, pool_index_max);
diff --git a/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.c b/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.c
index 2ba49e959c3f..dc339dc1adb2 100644
--- a/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.c
+++ b/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.c
@@ -815,6 +815,14 @@ static netdev_tx_t dpaa2_eth_tx(struct sk_buff *skb, struct net_device *net_dev)
 	 */
 	queue_mapping = skb_get_queue_mapping(skb);
 	fq = &priv->fq[queue_mapping];
+
+	fd_len = dpaa2_fd_get_len(&fd);
+	nq = netdev_get_tx_queue(net_dev, queue_mapping);
+	netdev_tx_sent_queue(nq, fd_len);
+
+	/* Everything that happens after this enqueues might race with
+	 * the Tx confirmation callback for this frame
+	 */
 	for (i = 0; i < DPAA2_ETH_ENQUEUE_RETRIES; i++) {
 		err = priv->enqueue(priv, fq, &fd, 0);
 		if (err != -EBUSY)
@@ -825,13 +833,10 @@ static netdev_tx_t dpaa2_eth_tx(struct sk_buff *skb, struct net_device *net_dev)
 		percpu_stats->tx_errors++;
 		/* Clean up everything, including freeing the skb */
 		free_tx_fd(priv, fq, &fd, false);
+		netdev_tx_completed_queue(nq, 1, fd_len);
 	} else {
-		fd_len = dpaa2_fd_get_len(&fd);
 		percpu_stats->tx_packets++;
 		percpu_stats->tx_bytes += fd_len;
-
-		nq = netdev_get_tx_queue(net_dev, queue_mapping);
-		netdev_tx_sent_queue(nq, fd_len);
 	}
 
 	return NETDEV_TX_OK;
@@ -1817,7 +1822,7 @@ static int dpaa2_eth_xdp_xmit_frame(struct net_device *net_dev,
 	dpaa2_fd_set_format(&fd, dpaa2_fd_single);
 	dpaa2_fd_set_ctrl(&fd, FD_CTRL_PTA);
 
-	fq = &priv->fq[smp_processor_id()];
+	fq = &priv->fq[smp_processor_id() % dpaa2_eth_queue_count(priv)];
 	for (i = 0; i < DPAA2_ETH_ENQUEUE_RETRIES; i++) {
 		err = priv->enqueue(priv, fq, &fd, 0);
 		if (err != -EBUSY)
diff --git a/drivers/net/ethernet/freescale/fec_main.c b/drivers/net/ethernet/freescale/fec_main.c
index 697c2427f2b7..a96ad20ee484 100644
--- a/drivers/net/ethernet/freescale/fec_main.c
+++ b/drivers/net/ethernet/freescale/fec_main.c
@@ -1840,13 +1840,9 @@ static int fec_enet_clk_enable(struct net_device *ndev, bool enable)
 	int ret;
 
 	if (enable) {
-		ret = clk_prepare_enable(fep->clk_ahb);
-		if (ret)
-			return ret;
-
 		ret = clk_prepare_enable(fep->clk_enet_out);
 		if (ret)
-			goto failed_clk_enet_out;
+			return ret;
 
 		if (fep->clk_ptp) {
 			mutex_lock(&fep->ptp_clk_mutex);
@@ -1866,7 +1862,6 @@ static int fec_enet_clk_enable(struct net_device *ndev, bool enable)
 
 		phy_reset_after_clk_enable(ndev->phydev);
 	} else {
-		clk_disable_unprepare(fep->clk_ahb);
 		clk_disable_unprepare(fep->clk_enet_out);
 		if (fep->clk_ptp) {
 			mutex_lock(&fep->ptp_clk_mutex);
@@ -1885,8 +1880,6 @@ failed_clk_ref:
 failed_clk_ptp:
 	if (fep->clk_enet_out)
 		clk_disable_unprepare(fep->clk_enet_out);
-failed_clk_enet_out:
-		clk_disable_unprepare(fep->clk_ahb);
 
 	return ret;
 }
@@ -3470,6 +3463,9 @@ fec_probe(struct platform_device *pdev)
 	ret = clk_prepare_enable(fep->clk_ipg);
 	if (ret)
 		goto failed_clk_ipg;
+	ret = clk_prepare_enable(fep->clk_ahb);
+	if (ret)
+		goto failed_clk_ahb;
 
 	fep->reg_phy = devm_regulator_get_optional(&pdev->dev, "phy");
 	if (!IS_ERR(fep->reg_phy)) {
@@ -3563,6 +3559,9 @@ failed_reset:
 	pm_runtime_put(&pdev->dev);
 	pm_runtime_disable(&pdev->dev);
 failed_regulator:
+	clk_disable_unprepare(fep->clk_ahb);
+failed_clk_ahb:
+	clk_disable_unprepare(fep->clk_ipg);
 failed_clk_ipg:
 	fec_enet_clk_enable(ndev, false);
 failed_clk:
@@ -3686,6 +3685,7 @@ static int __maybe_unused fec_runtime_suspend(struct device *dev)
 	struct net_device *ndev = dev_get_drvdata(dev);
 	struct fec_enet_private *fep = netdev_priv(ndev);
 
+	clk_disable_unprepare(fep->clk_ahb);
 	clk_disable_unprepare(fep->clk_ipg);
 
 	return 0;
@@ -3695,8 +3695,20 @@ static int __maybe_unused fec_runtime_resume(struct device *dev)
 {
 	struct net_device *ndev = dev_get_drvdata(dev);
 	struct fec_enet_private *fep = netdev_priv(ndev);
+	int ret;
 
-	return clk_prepare_enable(fep->clk_ipg);
+	ret = clk_prepare_enable(fep->clk_ahb);
+	if (ret)
+		return ret;
+	ret = clk_prepare_enable(fep->clk_ipg);
+	if (ret)
+		goto failed_clk_ipg;
+
+	return 0;
+
+failed_clk_ipg:
+	clk_disable_unprepare(fep->clk_ahb);
+	return ret;
 }
 
 static const struct dev_pm_ops fec_pm_ops = {
diff --git a/drivers/net/ethernet/hisilicon/hns/hnae.c b/drivers/net/ethernet/hisilicon/hns/hnae.c
index 79d03f8ee7b1..c7fa97a7e1f4 100644
--- a/drivers/net/ethernet/hisilicon/hns/hnae.c
+++ b/drivers/net/ethernet/hisilicon/hns/hnae.c
@@ -150,7 +150,6 @@ out_buffer_fail:
 /* free desc along with its attached buffer */
 static void hnae_free_desc(struct hnae_ring *ring)
 {
-	hnae_free_buffers(ring);
 	dma_unmap_single(ring_to_dev(ring), ring->desc_dma_addr,
 			 ring->desc_num * sizeof(ring->desc[0]),
 			 ring_to_dma_dir(ring));
@@ -183,6 +182,9 @@ static int hnae_alloc_desc(struct hnae_ring *ring)
 /* fini ring, also free the buffer for the ring */
 static void hnae_fini_ring(struct hnae_ring *ring)
 {
+	if (is_rx_ring(ring))
+		hnae_free_buffers(ring);
+
 	hnae_free_desc(ring);
 	kfree(ring->desc_cb);
 	ring->desc_cb = NULL;
diff --git a/drivers/net/ethernet/hisilicon/hns/hnae.h b/drivers/net/ethernet/hisilicon/hns/hnae.h
index 08a750fb60c4..d6fb83437230 100644
--- a/drivers/net/ethernet/hisilicon/hns/hnae.h
+++ b/drivers/net/ethernet/hisilicon/hns/hnae.h
@@ -357,7 +357,7 @@ struct hnae_buf_ops {
 };
 
 struct hnae_queue {
-	void __iomem *io_base;
+	u8 __iomem *io_base;
 	phys_addr_t phy_base;
 	struct hnae_ae_dev *dev;	/* the device who use this queue */
 	struct hnae_ring rx_ring ____cacheline_internodealigned_in_smp;
diff --git a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_mac.c b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_mac.c
index a97228c93831..6c0507921623 100644
--- a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_mac.c
+++ b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_mac.c
@@ -370,7 +370,7 @@ int hns_mac_clr_multicast(struct hns_mac_cb *mac_cb, int vfn)
 static void hns_mac_param_get(struct mac_params *param,
 			      struct hns_mac_cb *mac_cb)
 {
-	param->vaddr = (void *)mac_cb->vaddr;
+	param->vaddr = mac_cb->vaddr;
 	param->mac_mode = hns_get_enet_interface(mac_cb);
 	ether_addr_copy(param->addr, mac_cb->addr_entry_idx[0].addr);
 	param->mac_id = mac_cb->mac_id;
diff --git a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_mac.h b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_mac.h
index fbc75341bef7..22589799f1a5 100644
--- a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_mac.h
+++ b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_mac.h
@@ -187,7 +187,7 @@ struct mac_statistics {
 /*mac para struct ,mac get param from nic or dsaf when initialize*/
 struct mac_params {
 	char addr[ETH_ALEN];
-	void *vaddr; /*virtual address*/
+	u8 __iomem *vaddr; /*virtual address*/
 	struct device *dev;
 	u8 mac_id;
 	/**< Ethernet operation mode (MAC-PHY interface and speed) */
@@ -402,7 +402,7 @@ struct mac_driver {
 	enum mac_mode mac_mode;
 	u8 mac_id;
 	struct hns_mac_cb *mac_cb;
-	void __iomem *io_base;
+	u8 __iomem *io_base;
 	unsigned int mac_en_flg;/*you'd better don't enable mac twice*/
 	unsigned int virt_dev_num;
 	struct device *dev;
diff --git a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_main.c b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_main.c
index ac55db065f16..61eea6ac846f 100644
--- a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_main.c
+++ b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_main.c
@@ -1602,8 +1602,6 @@ static void hns_dsaf_set_mac_key(
 		       DSAF_TBL_TCAM_KEY_VLAN_S, vlan_id);
 	dsaf_set_field(mac_key->low.bits.port_vlan, DSAF_TBL_TCAM_KEY_PORT_M,
 		       DSAF_TBL_TCAM_KEY_PORT_S, port);
-
-	mac_key->low.bits.port_vlan = le16_to_cpu(mac_key->low.bits.port_vlan);
 }
 
 /**
@@ -1663,8 +1661,8 @@ int hns_dsaf_set_mac_uc_entry(
 	/* default config dvc to 0 */
 	mac_data.tbl_ucast_dvc = 0;
 	mac_data.tbl_ucast_out_port = mac_entry->port_num;
-	tcam_data.tbl_tcam_data_high = cpu_to_le32(mac_key.high.val);
-	tcam_data.tbl_tcam_data_low = cpu_to_le32(mac_key.low.val);
+	tcam_data.tbl_tcam_data_high = mac_key.high.val;
+	tcam_data.tbl_tcam_data_low = mac_key.low.val;
 
 	hns_dsaf_tcam_uc_cfg(dsaf_dev, entry_index, &tcam_data, &mac_data);
 
@@ -1786,9 +1784,6 @@ int hns_dsaf_add_mac_mc_port(struct dsaf_device *dsaf_dev,
 				     0xff,
 				     mc_mask);
 
-		mask_key.high.val = le32_to_cpu(mask_key.high.val);
-		mask_key.low.val = le32_to_cpu(mask_key.low.val);
-
 		pmask_key = (struct dsaf_tbl_tcam_data *)(&mask_key);
 	}
 
@@ -1840,8 +1835,8 @@ int hns_dsaf_add_mac_mc_port(struct dsaf_device *dsaf_dev,
 		dsaf_dev->ae_dev.name, mac_key.high.val,
 		mac_key.low.val, entry_index);
 
-	tcam_data.tbl_tcam_data_high = cpu_to_le32(mac_key.high.val);
-	tcam_data.tbl_tcam_data_low = cpu_to_le32(mac_key.low.val);
+	tcam_data.tbl_tcam_data_high = mac_key.high.val;
+	tcam_data.tbl_tcam_data_low = mac_key.low.val;
 
 	/* config mc entry with mask */
 	hns_dsaf_tcam_mc_cfg(dsaf_dev, entry_index, &tcam_data,
@@ -1956,9 +1951,6 @@ int hns_dsaf_del_mac_mc_port(struct dsaf_device *dsaf_dev,
 		/* config key mask */
 		hns_dsaf_set_mac_key(dsaf_dev, &mask_key, 0x00, 0xff, mc_mask);
 
-		mask_key.high.val = le32_to_cpu(mask_key.high.val);
-		mask_key.low.val = le32_to_cpu(mask_key.low.val);
-
 		pmask_key = (struct dsaf_tbl_tcam_data *)(&mask_key);
 	}
 
@@ -2012,8 +2004,8 @@ int hns_dsaf_del_mac_mc_port(struct dsaf_device *dsaf_dev,
 		soft_mac_entry += entry_index;
 		soft_mac_entry->index = DSAF_INVALID_ENTRY_IDX;
 	} else { /* not zero, just del port, update */
-		tcam_data.tbl_tcam_data_high = cpu_to_le32(mac_key.high.val);
-		tcam_data.tbl_tcam_data_low = cpu_to_le32(mac_key.low.val);
+		tcam_data.tbl_tcam_data_high = mac_key.high.val;
+		tcam_data.tbl_tcam_data_low = mac_key.low.val;
 
 		hns_dsaf_tcam_mc_cfg(dsaf_dev, entry_index,
 				     &tcam_data,
@@ -2750,6 +2742,17 @@ int hns_dsaf_get_regs_count(void)
 	return DSAF_DUMP_REGS_NUM;
 }
 
+static int hns_dsaf_get_port_id(u8 port)
+{
+	if (port < DSAF_SERVICE_NW_NUM)
+		return port;
+
+	if (port >= DSAF_BASE_INNER_PORT_NUM)
+		return port - DSAF_BASE_INNER_PORT_NUM + DSAF_SERVICE_NW_NUM;
+
+	return -EINVAL;
+}
+
 static void set_promisc_tcam_enable(struct dsaf_device *dsaf_dev, u32 port)
 {
 	struct dsaf_tbl_tcam_ucast_cfg tbl_tcam_ucast = {0, 1, 0, 0, 0x80};
@@ -2815,23 +2818,33 @@ static void set_promisc_tcam_enable(struct dsaf_device *dsaf_dev, u32 port)
 	memset(&temp_key, 0x0, sizeof(temp_key));
 	mask_entry.addr[0] = 0x01;
 	hns_dsaf_set_mac_key(dsaf_dev, &mask_key, mask_entry.in_vlan_id,
-			     port, mask_entry.addr);
+			     0xf, mask_entry.addr);
 	tbl_tcam_mcast.tbl_mcast_item_vld = 1;
 	tbl_tcam_mcast.tbl_mcast_old_en = 0;
 
-	if (port < DSAF_SERVICE_NW_NUM) {
-		mskid = port;
-	} else if (port >= DSAF_BASE_INNER_PORT_NUM) {
-		mskid = port - DSAF_BASE_INNER_PORT_NUM + DSAF_SERVICE_NW_NUM;
-	} else {
+	/* set MAC port to handle multicast */
+	mskid = hns_dsaf_get_port_id(port);
+	if (mskid == -EINVAL) {
 		dev_err(dsaf_dev->dev, "%s,pnum(%d)error,key(%#x:%#x)\n",
 			dsaf_dev->ae_dev.name, port,
 			mask_key.high.val, mask_key.low.val);
 		return;
 	}
+	dsaf_set_bit(tbl_tcam_mcast.tbl_mcast_port_msk[mskid / 32],
+		     mskid % 32, 1);
 
+	/* set pool bit map to handle multicast */
+	mskid = hns_dsaf_get_port_id(port_num);
+	if (mskid == -EINVAL) {
+		dev_err(dsaf_dev->dev,
+			"%s, pool bit map pnum(%d)error,key(%#x:%#x)\n",
+			dsaf_dev->ae_dev.name, port_num,
+			mask_key.high.val, mask_key.low.val);
+		return;
+	}
 	dsaf_set_bit(tbl_tcam_mcast.tbl_mcast_port_msk[mskid / 32],
 		     mskid % 32, 1);
+
 	memcpy(&temp_key, &mask_key, sizeof(mask_key));
 	hns_dsaf_tcam_mc_cfg_vague(dsaf_dev, entry_index, &tbl_tcam_data_mc,
 				   (struct dsaf_tbl_tcam_data *)(&mask_key),
diff --git a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_main.h b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_main.h
index 0e1cd99831a6..76cc8887e1a8 100644
--- a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_main.h
+++ b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_main.h
@@ -467,4 +467,6 @@ int hns_dsaf_clr_mac_mc_port(struct dsaf_device *dsaf_dev,
 			     u8 mac_id, u8 port_num);
 int hns_dsaf_wait_pkt_clean(struct dsaf_device *dsaf_dev, int port);
 
+int hns_dsaf_roce_reset(struct fwnode_handle *dsaf_fwnode, bool dereset);
+
 #endif /* __HNS_DSAF_MAIN_H__ */
diff --git a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_misc.c b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_misc.c
index 16294cd3c954..19b94879691f 100644
--- a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_misc.c
+++ b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_misc.c
@@ -670,7 +670,7 @@ static int hns_mac_config_sds_loopback(struct hns_mac_cb *mac_cb, bool en)
 		dsaf_set_field(origin, 1ull << 10, 10, en);
 		dsaf_write_syscon(mac_cb->serdes_ctrl, reg_offset, origin);
 	} else {
-		u8 *base_addr = (u8 *)mac_cb->serdes_vaddr +
+		u8 __iomem *base_addr = mac_cb->serdes_vaddr +
 				(mac_cb->mac_id <= 3 ? 0x00280000 : 0x00200000);
 		dsaf_set_reg_field(base_addr, reg_offset, 1ull << 10, 10, en);
 	}
diff --git a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_ppe.c b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_ppe.c
index 3d07c8a7639d..17c019106e6e 100644
--- a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_ppe.c
+++ b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_ppe.c
@@ -61,7 +61,7 @@ void hns_ppe_set_indir_table(struct hns_ppe_cb *ppe_cb,
 	}
 }
 
-static void __iomem *
+static u8 __iomem *
 hns_ppe_common_get_ioaddr(struct ppe_common_cb *ppe_common)
 {
 	return ppe_common->dsaf_dev->ppe_base + PPE_COMMON_REG_OFFSET;
@@ -111,8 +111,8 @@ hns_ppe_common_free_cfg(struct dsaf_device *dsaf_dev, u32 comm_index)
 	dsaf_dev->ppe_common[comm_index] = NULL;
 }
 
-static void __iomem *hns_ppe_get_iobase(struct ppe_common_cb *ppe_common,
-					int ppe_idx)
+static u8 __iomem *hns_ppe_get_iobase(struct ppe_common_cb *ppe_common,
+				      int ppe_idx)
 {
 	return ppe_common->dsaf_dev->ppe_base + ppe_idx * PPE_REG_OFFSET;
 }
diff --git a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_ppe.h b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_ppe.h
index f670e63a5a01..110c6e8222c7 100644
--- a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_ppe.h
+++ b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_ppe.h
@@ -80,7 +80,7 @@ struct hns_ppe_cb {
 	struct hns_ppe_hw_stats hw_stats;
 
 	u8 index;	/* index in a ppe common device */
-	void __iomem *io_base;
+	u8 __iomem *io_base;
 	int virq;
 	u32 rss_indir_table[HNS_PPEV2_RSS_IND_TBL_SIZE]; /*shadow indir tab */
 	u32 rss_key[HNS_PPEV2_RSS_KEY_NUM]; /* rss hash key */
@@ -89,7 +89,7 @@ struct hns_ppe_cb {
 struct ppe_common_cb {
 	struct device *dev;
 	struct dsaf_device *dsaf_dev;
-	void __iomem *io_base;
+	u8 __iomem *io_base;
 
 	enum ppe_common_mode ppe_mode;
 
diff --git a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_rcb.c b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_rcb.c
index 6bf346c11b25..ac3518ca4d7b 100644
--- a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_rcb.c
+++ b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_rcb.c
@@ -458,7 +458,7 @@ static void hns_rcb_ring_get_cfg(struct hnae_queue *q, int ring_type)
 		mdnum_ppkt = HNS_RCB_RING_MAX_BD_PER_PKT;
 	} else {
 		ring = &q->tx_ring;
-		ring->io_base = (u8 __iomem *)ring_pair_cb->q.io_base +
+		ring->io_base = ring_pair_cb->q.io_base +
 			HNS_RCB_TX_REG_OFFSET;
 		irq_idx = HNS_RCB_IRQ_IDX_TX;
 		mdnum_ppkt = is_ver1 ? HNS_RCB_RING_MAX_TXBD_PER_PKT :
@@ -764,7 +764,7 @@ static int hns_rcb_get_ring_num(struct dsaf_device *dsaf_dev)
 	}
 }
 
-static void __iomem *hns_rcb_common_get_vaddr(struct rcb_common_cb *rcb_common)
+static u8 __iomem *hns_rcb_common_get_vaddr(struct rcb_common_cb *rcb_common)
 {
 	struct dsaf_device *dsaf_dev = rcb_common->dsaf_dev;
 
diff --git a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_reg.h b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_reg.h
index b9733b0b8482..b9e7f11f0896 100644
--- a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_reg.h
+++ b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_reg.h
@@ -1018,7 +1018,7 @@
 #define XGMAC_PAUSE_CTL_RSP_MODE_B	2
 #define XGMAC_PAUSE_CTL_TX_XOFF_B	3
 
-static inline void dsaf_write_reg(void __iomem *base, u32 reg, u32 value)
+static inline void dsaf_write_reg(u8 __iomem *base, u32 reg, u32 value)
 {
 	writel(value, base + reg);
 }
@@ -1053,7 +1053,7 @@ static inline int dsaf_read_syscon(struct regmap *base, u32 reg, u32 *val)
 #define dsaf_set_bit(origin, shift, val) \
 	dsaf_set_field((origin), (1ull << (shift)), (shift), (val))
 
-static inline void dsaf_set_reg_field(void __iomem *base, u32 reg, u32 mask,
+static inline void dsaf_set_reg_field(u8 __iomem *base, u32 reg, u32 mask,
 				      u32 shift, u32 val)
 {
 	u32 origin = dsaf_read_reg(base, reg);
@@ -1073,7 +1073,7 @@ static inline void dsaf_set_reg_field(void __iomem *base, u32 reg, u32 mask,
 #define dsaf_get_bit(origin, shift) \
 	dsaf_get_field((origin), (1ull << (shift)), (shift))
 
-static inline u32 dsaf_get_reg_field(void __iomem *base, u32 reg, u32 mask,
+static inline u32 dsaf_get_reg_field(u8 __iomem *base, u32 reg, u32 mask,
 				     u32 shift)
 {
 	u32 origin;
@@ -1089,11 +1089,11 @@ static inline u32 dsaf_get_reg_field(void __iomem *base, u32 reg, u32 mask,
 	dsaf_get_reg_field((dev)->io_base, (reg), (1ull << (bit)), (bit))
 
 #define dsaf_write_b(addr, data)\
-	writeb((data), (__iomem unsigned char *)(addr))
+	writeb((data), (__iomem u8 *)(addr))
 #define dsaf_read_b(addr)\
-	readb((__iomem unsigned char *)(addr))
+	readb((__iomem u8 *)(addr))
 
 #define hns_mac_reg_read64(drv, offset) \
-	readq((__iomem void *)(((u8 *)(drv)->io_base + 0xc00 + (offset))))
+	readq((__iomem void *)(((drv)->io_base + 0xc00 + (offset))))
 
 #endif	/* _DSAF_REG_H */
diff --git a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_xgmac.c b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_xgmac.c
index ba4316910dea..a60f207768fc 100644
--- a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_xgmac.c
+++ b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_xgmac.c
@@ -129,7 +129,7 @@ static void hns_xgmac_lf_rf_control_init(struct mac_driver *mac_drv)
 	dsaf_set_bit(val, XGMAC_UNIDIR_EN_B, 0);
 	dsaf_set_bit(val, XGMAC_RF_TX_EN_B, 1);
 	dsaf_set_field(val, XGMAC_LF_RF_INSERT_M, XGMAC_LF_RF_INSERT_S, 0);
-	dsaf_write_reg(mac_drv, XGMAC_MAC_TX_LF_RF_CONTROL_REG, val);
+	dsaf_write_dev(mac_drv, XGMAC_MAC_TX_LF_RF_CONTROL_REG, val);
 }
 
 /**
diff --git a/drivers/net/ethernet/hisilicon/hns/hns_enet.c b/drivers/net/ethernet/hisilicon/hns/hns_enet.c
index 60e7d7ae3787..4cd86ba1f050 100644
--- a/drivers/net/ethernet/hisilicon/hns/hns_enet.c
+++ b/drivers/net/ethernet/hisilicon/hns/hns_enet.c
@@ -29,9 +29,6 @@
 
 #define SERVICE_TIMER_HZ (1 * HZ)
 
-#define NIC_TX_CLEAN_MAX_NUM 256
-#define NIC_RX_CLEAN_MAX_NUM 64
-
 #define RCB_IRQ_NOT_INITED 0
 #define RCB_IRQ_INITED 1
 #define HNS_BUFFER_SIZE_2048 2048
@@ -376,8 +373,6 @@ netdev_tx_t hns_nic_net_xmit_hw(struct net_device *ndev,
 	wmb(); /* commit all data before submit */
 	assert(skb->queue_mapping < priv->ae_handle->q_num);
 	hnae_queue_xmit(priv->ae_handle->qs[skb->queue_mapping], buf_num);
-	ring->stats.tx_pkts++;
-	ring->stats.tx_bytes += skb->len;
 
 	return NETDEV_TX_OK;
 
@@ -999,6 +994,9 @@ static int hns_nic_tx_poll_one(struct hns_nic_ring_data *ring_data,
 		/* issue prefetch for next Tx descriptor */
 		prefetch(&ring->desc_cb[ring->next_to_clean]);
 	}
+	/* update tx ring statistics. */
+	ring->stats.tx_pkts += pkts;
+	ring->stats.tx_bytes += bytes;
 
 	NETIF_TX_UNLOCK(ring);
 
@@ -2152,7 +2150,7 @@ static int hns_nic_init_ring_data(struct hns_nic_priv *priv)
 			hns_nic_tx_fini_pro_v2;
 
 		netif_napi_add(priv->netdev, &rd->napi,
-			       hns_nic_common_poll, NIC_TX_CLEAN_MAX_NUM);
+			       hns_nic_common_poll, NAPI_POLL_WEIGHT);
 		rd->ring->irq_init_flag = RCB_IRQ_NOT_INITED;
 	}
 	for (i = h->q_num; i < h->q_num * 2; i++) {
@@ -2165,7 +2163,7 @@ static int hns_nic_init_ring_data(struct hns_nic_priv *priv)
 			hns_nic_rx_fini_pro_v2;
 
 		netif_napi_add(priv->netdev, &rd->napi,
-			       hns_nic_common_poll, NIC_RX_CLEAN_MAX_NUM);
+			       hns_nic_common_poll, NAPI_POLL_WEIGHT);
 		rd->ring->irq_init_flag = RCB_IRQ_NOT_INITED;
 	}
 
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c
index 1c1f17ec6be2..162cb9afa0e7 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c
@@ -22,6 +22,7 @@
 #include "hns3_enet.h"
 
 #define hns3_set_field(origin, shift, val)	((origin) |= ((val) << (shift)))
+#define hns3_tx_bd_count(S)	DIV_ROUND_UP(S, HNS3_MAX_BD_SIZE)
 
 static void hns3_clear_all_ring(struct hnae3_handle *h);
 static void hns3_force_clear_all_rx_ring(struct hnae3_handle *h);
@@ -1079,7 +1080,7 @@ static int hns3_fill_desc(struct hns3_enet_ring *ring, void *priv,
 
 	desc_cb->length = size;
 
-	frag_buf_num = (size + HNS3_MAX_BD_SIZE - 1) >> HNS3_MAX_BD_SIZE_OFFSET;
+	frag_buf_num = hns3_tx_bd_count(size);
 	sizeoflast = size & HNS3_TX_LAST_SIZE_M;
 	sizeoflast = sizeoflast ? sizeoflast : HNS3_MAX_BD_SIZE;
 
@@ -1124,14 +1125,13 @@ static int hns3_nic_maybe_stop_tso(struct sk_buff **out_skb, int *bnum,
 	int i;
 
 	size = skb_headlen(skb);
-	buf_num = (size + HNS3_MAX_BD_SIZE - 1) >> HNS3_MAX_BD_SIZE_OFFSET;
+	buf_num = hns3_tx_bd_count(size);
 
 	frag_num = skb_shinfo(skb)->nr_frags;
 	for (i = 0; i < frag_num; i++) {
 		frag = &skb_shinfo(skb)->frags[i];
 		size = skb_frag_size(frag);
-		bdnum_for_frag = (size + HNS3_MAX_BD_SIZE - 1) >>
-				 HNS3_MAX_BD_SIZE_OFFSET;
+		bdnum_for_frag = hns3_tx_bd_count(size);
 		if (unlikely(bdnum_for_frag > HNS3_MAX_BD_PER_FRAG))
 			return -ENOMEM;
 
@@ -1139,8 +1139,7 @@ static int hns3_nic_maybe_stop_tso(struct sk_buff **out_skb, int *bnum,
 	}
 
 	if (unlikely(buf_num > HNS3_MAX_BD_PER_FRAG)) {
-		buf_num = (skb->len + HNS3_MAX_BD_SIZE - 1) >>
-			  HNS3_MAX_BD_SIZE_OFFSET;
+		buf_num = hns3_tx_bd_count(skb->len);
 		if (ring_space(ring) < buf_num)
 			return -EBUSY;
 		/* manual split the send packet */
@@ -1169,7 +1168,7 @@ static int hns3_nic_maybe_stop_tx(struct sk_buff **out_skb, int *bnum,
 	buf_num = skb_shinfo(skb)->nr_frags + 1;
 
 	if (unlikely(buf_num > HNS3_MAX_BD_PER_FRAG)) {
-		buf_num = (skb->len + HNS3_MAX_BD_SIZE - 1) / HNS3_MAX_BD_SIZE;
+		buf_num = hns3_tx_bd_count(skb->len);
 		if (ring_space(ring) < buf_num)
 			return -EBUSY;
 		/* manual split the send packet */
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.h b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.h
index 1db0bd41d209..75669cd0c311 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.h
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.h
@@ -193,7 +193,6 @@ enum hns3_nic_state {
 #define HNS3_VECTOR_INITED			1
 
 #define HNS3_MAX_BD_SIZE			65535
-#define HNS3_MAX_BD_SIZE_OFFSET		16
 #define HNS3_MAX_BD_PER_FRAG			8
 #define HNS3_MAX_BD_PER_PKT			MAX_SKB_FRAGS
 
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/Makefile b/drivers/net/ethernet/hisilicon/hns3/hns3pf/Makefile
index fffe8c1c45d3..0fb61d440d3b 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/Makefile
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/Makefile
@@ -3,7 +3,7 @@
 # Makefile for the HISILICON network device drivers.
 #
 
-ccflags-y := -Idrivers/net/ethernet/hisilicon/hns3
+ccflags-y := -I $(srctree)/drivers/net/ethernet/hisilicon/hns3
 
 obj-$(CONFIG_HNS3_HCLGE) += hclge.o
 hclge-objs = hclge_main.o hclge_cmd.o hclge_mdio.o hclge_tm.o hclge_mbx.o hclge_err.o  hclge_debugfs.o
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3vf/Makefile b/drivers/net/ethernet/hisilicon/hns3/hns3vf/Makefile
index fb93bbd35845..6193f8fa7cf3 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3vf/Makefile
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3vf/Makefile
@@ -3,7 +3,7 @@
 # Makefile for the HISILICON network device drivers.
 #
 
-ccflags-y := -Idrivers/net/ethernet/hisilicon/hns3
+ccflags-y := -I $(srctree)/drivers/net/ethernet/hisilicon/hns3
 
 obj-$(CONFIG_HNS3_HCLGEVF) += hclgevf.o
 hclgevf-objs = hclgevf_main.o hclgevf_cmd.o hclgevf_mbx.o
\ No newline at end of file
diff --git a/drivers/net/ethernet/hisilicon/hns_mdio.c b/drivers/net/ethernet/hisilicon/hns_mdio.c
index baf5cc251f32..8b8a7d00e8e0 100644
--- a/drivers/net/ethernet/hisilicon/hns_mdio.c
+++ b/drivers/net/ethernet/hisilicon/hns_mdio.c
@@ -39,7 +39,7 @@ struct hns_mdio_sc_reg {
 };
 
 struct hns_mdio_device {
-	void *vbase;		/* mdio reg base address */
+	u8 __iomem *vbase;		/* mdio reg base address */
 	struct regmap *subctrl_vbase;
 	struct hns_mdio_sc_reg sc_reg;
 };
@@ -96,21 +96,17 @@ enum mdio_c45_op_seq {
 #define MDIO_SC_CLK_ST		0x531C
 #define MDIO_SC_RESET_ST	0x5A1C
 
-static void mdio_write_reg(void *base, u32 reg, u32 value)
+static void mdio_write_reg(u8 __iomem *base, u32 reg, u32 value)
 {
-	u8 __iomem *reg_addr = (u8 __iomem *)base;
-
-	writel_relaxed(value, reg_addr + reg);
+	writel_relaxed(value, base + reg);
 }
 
 #define MDIO_WRITE_REG(a, reg, value) \
 	mdio_write_reg((a)->vbase, (reg), (value))
 
-static u32 mdio_read_reg(void *base, u32 reg)
+static u32 mdio_read_reg(u8 __iomem *base, u32 reg)
 {
-	u8 __iomem *reg_addr = (u8 __iomem *)base;
-
-	return readl_relaxed(reg_addr + reg);
+	return readl_relaxed(base + reg);
 }
 
 #define mdio_set_field(origin, mask, shift, val) \
@@ -121,7 +117,7 @@ static u32 mdio_read_reg(void *base, u32 reg)
 
 #define mdio_get_field(origin, mask, shift) (((origin) >> (shift)) & (mask))
 
-static void mdio_set_reg_field(void *base, u32 reg, u32 mask, u32 shift,
+static void mdio_set_reg_field(u8 __iomem *base, u32 reg, u32 mask, u32 shift,
 			       u32 val)
 {
 	u32 origin = mdio_read_reg(base, reg);
@@ -133,7 +129,7 @@ static void mdio_set_reg_field(void *base, u32 reg, u32 mask, u32 shift,
 #define MDIO_SET_REG_FIELD(dev, reg, mask, shift, val) \
 	mdio_set_reg_field((dev)->vbase, (reg), (mask), (shift), (val))
 
-static u32 mdio_get_reg_field(void *base, u32 reg, u32 mask, u32 shift)
+static u32 mdio_get_reg_field(u8 __iomem *base, u32 reg, u32 mask, u32 shift)
 {
 	u32 origin;
 
diff --git a/drivers/net/ethernet/ibm/ehea/ehea_main.c b/drivers/net/ethernet/ibm/ehea/ehea_main.c
index 3baabdc89726..90b62c1412c8 100644
--- a/drivers/net/ethernet/ibm/ehea/ehea_main.c
+++ b/drivers/net/ethernet/ibm/ehea/ehea_main.c
@@ -3160,6 +3160,7 @@ static ssize_t ehea_probe_port(struct device *dev,
 
 	if (ehea_add_adapter_mr(adapter)) {
 		pr_err("creating MR failed\n");
+		of_node_put(eth_dn);
 		return -EIO;
 	}
 
diff --git a/drivers/net/ethernet/ibm/ibmvnic.c b/drivers/net/ethernet/ibm/ibmvnic.c
index 5ecbb1adcf3b..3dfb2d131eb7 100644
--- a/drivers/net/ethernet/ibm/ibmvnic.c
+++ b/drivers/net/ethernet/ibm/ibmvnic.c
@@ -1885,6 +1885,7 @@ static int do_hard_reset(struct ibmvnic_adapter *adapter,
 	 */
 	adapter->state = VNIC_PROBED;
 
+	reinit_completion(&adapter->init_done);
 	rc = init_crq_queue(adapter);
 	if (rc) {
 		netdev_err(adapter->netdev,
@@ -3761,6 +3762,7 @@ static void handle_query_ip_offload_rsp(struct ibmvnic_adapter *adapter)
 {
 	struct device *dev = &adapter->vdev->dev;
 	struct ibmvnic_query_ip_offload_buffer *buf = &adapter->ip_offload_buf;
+	netdev_features_t old_hw_features = 0;
 	union ibmvnic_crq crq;
 	int i;
 
@@ -3836,24 +3838,41 @@ static void handle_query_ip_offload_rsp(struct ibmvnic_adapter *adapter)
 	adapter->ip_offload_ctrl.large_rx_ipv4 = 0;
 	adapter->ip_offload_ctrl.large_rx_ipv6 = 0;
 
-	adapter->netdev->features = NETIF_F_SG | NETIF_F_GSO;
+	if (adapter->state != VNIC_PROBING) {
+		old_hw_features = adapter->netdev->hw_features;
+		adapter->netdev->hw_features = 0;
+	}
+
+	adapter->netdev->hw_features = NETIF_F_SG | NETIF_F_GSO | NETIF_F_GRO;
 
 	if (buf->tcp_ipv4_chksum || buf->udp_ipv4_chksum)
-		adapter->netdev->features |= NETIF_F_IP_CSUM;
+		adapter->netdev->hw_features |= NETIF_F_IP_CSUM;
 
 	if (buf->tcp_ipv6_chksum || buf->udp_ipv6_chksum)
-		adapter->netdev->features |= NETIF_F_IPV6_CSUM;
+		adapter->netdev->hw_features |= NETIF_F_IPV6_CSUM;
 
 	if ((adapter->netdev->features &
 	    (NETIF_F_IP_CSUM | NETIF_F_IPV6_CSUM)))
-		adapter->netdev->features |= NETIF_F_RXCSUM;
+		adapter->netdev->hw_features |= NETIF_F_RXCSUM;
 
 	if (buf->large_tx_ipv4)
-		adapter->netdev->features |= NETIF_F_TSO;
+		adapter->netdev->hw_features |= NETIF_F_TSO;
 	if (buf->large_tx_ipv6)
-		adapter->netdev->features |= NETIF_F_TSO6;
+		adapter->netdev->hw_features |= NETIF_F_TSO6;
+
+	if (adapter->state == VNIC_PROBING) {
+		adapter->netdev->features |= adapter->netdev->hw_features;
+	} else if (old_hw_features != adapter->netdev->hw_features) {
+		netdev_features_t tmp = 0;
 
-	adapter->netdev->hw_features |= adapter->netdev->features;
+		/* disable features no longer supported */
+		adapter->netdev->features &= adapter->netdev->hw_features;
+		/* turn on features now supported if previously enabled */
+		tmp = (old_hw_features ^ adapter->netdev->hw_features) &
+			adapter->netdev->hw_features;
+		adapter->netdev->features |=
+				tmp & adapter->netdev->wanted_features;
+	}
 
 	memset(&crq, 0, sizeof(crq));
 	crq.control_ip_offload.first = IBMVNIC_CRQ_CMD;
@@ -4625,7 +4644,7 @@ static int ibmvnic_reset_init(struct ibmvnic_adapter *adapter)
 	old_num_rx_queues = adapter->req_rx_queues;
 	old_num_tx_queues = adapter->req_tx_queues;
 
-	init_completion(&adapter->init_done);
+	reinit_completion(&adapter->init_done);
 	adapter->init_done_rc = 0;
 	ibmvnic_send_crq_init(adapter);
 	if (!wait_for_completion_timeout(&adapter->init_done, timeout)) {
@@ -4680,7 +4699,6 @@ static int ibmvnic_init(struct ibmvnic_adapter *adapter)
 
 	adapter->from_passive_init = false;
 
-	init_completion(&adapter->init_done);
 	adapter->init_done_rc = 0;
 	ibmvnic_send_crq_init(adapter);
 	if (!wait_for_completion_timeout(&adapter->init_done, timeout)) {
@@ -4759,6 +4777,7 @@ static int ibmvnic_probe(struct vio_dev *dev, const struct vio_device_id *id)
 	INIT_WORK(&adapter->ibmvnic_reset, __ibmvnic_reset);
 	INIT_LIST_HEAD(&adapter->rwi_list);
 	spin_lock_init(&adapter->rwi_lock);
+	init_completion(&adapter->init_done);
 	adapter->resetting = false;
 
 	adapter->mac_change_pending = false;
diff --git a/drivers/net/ethernet/intel/e1000/e1000_main.c b/drivers/net/ethernet/intel/e1000/e1000_main.c
index 8fe9af0e2ab7..466bf1ea186d 100644
--- a/drivers/net/ethernet/intel/e1000/e1000_main.c
+++ b/drivers/net/ethernet/intel/e1000/e1000_main.c
@@ -3270,11 +3270,6 @@ static netdev_tx_t e1000_xmit_frame(struct sk_buff *skb,
 		if (!skb->xmit_more ||
 		    netif_xmit_stopped(netdev_get_tx_queue(netdev, 0))) {
 			writel(tx_ring->next_to_use, hw->hw_addr + tx_ring->tdt);
-			/* we need this if more than one processor can write to
-			 * our tail at a time, it synchronizes IO on IA64/Altix
-			 * systems
-			 */
-			mmiowb();
 		}
 	} else {
 		dev_kfree_skb_any(skb);
diff --git a/drivers/net/ethernet/intel/e1000e/netdev.c b/drivers/net/ethernet/intel/e1000e/netdev.c
index 7acc61e4f645..022c3ac0e40f 100644
--- a/drivers/net/ethernet/intel/e1000e/netdev.c
+++ b/drivers/net/ethernet/intel/e1000e/netdev.c
@@ -3816,7 +3816,6 @@ static void e1000_flush_tx_ring(struct e1000_adapter *adapter)
 	if (tx_ring->next_to_use == tx_ring->count)
 		tx_ring->next_to_use = 0;
 	ew32(TDT(0), tx_ring->next_to_use);
-	mmiowb();
 	usleep_range(200, 250);
 }
 
@@ -5904,12 +5903,6 @@ static netdev_tx_t e1000_xmit_frame(struct sk_buff *skb,
 						     tx_ring->next_to_use);
 			else
 				writel(tx_ring->next_to_use, tx_ring->tail);
-
-			/* we need this if more than one processor can write
-			 * to our tail at a time, it synchronizes IO on
-			 *IA64/Altix systems
-			 */
-			mmiowb();
 		}
 	} else {
 		dev_kfree_skb_any(skb);
diff --git a/drivers/net/ethernet/intel/fm10k/fm10k_iov.c b/drivers/net/ethernet/intel/fm10k/fm10k_iov.c
index 5d4f1761dc0c..8de77155f2e7 100644
--- a/drivers/net/ethernet/intel/fm10k/fm10k_iov.c
+++ b/drivers/net/ethernet/intel/fm10k/fm10k_iov.c
@@ -321,8 +321,6 @@ static void fm10k_mask_aer_comp_abort(struct pci_dev *pdev)
 	pci_read_config_dword(pdev, pos + PCI_ERR_UNCOR_MASK, &err_mask);
 	err_mask |= PCI_ERR_UNC_COMP_ABORT;
 	pci_write_config_dword(pdev, pos + PCI_ERR_UNCOR_MASK, err_mask);
-
-	mmiowb();
 }
 
 int fm10k_iov_resume(struct pci_dev *pdev)
diff --git a/drivers/net/ethernet/intel/fm10k/fm10k_main.c b/drivers/net/ethernet/intel/fm10k/fm10k_main.c
index 5a0419421511..cbf76a96e94e 100644
--- a/drivers/net/ethernet/intel/fm10k/fm10k_main.c
+++ b/drivers/net/ethernet/intel/fm10k/fm10k_main.c
@@ -41,6 +41,8 @@ static int __init fm10k_init_module(void)
 	/* create driver workqueue */
 	fm10k_workqueue = alloc_workqueue("%s", WQ_MEM_RECLAIM, 0,
 					  fm10k_driver_name);
+	if (!fm10k_workqueue)
+		return -ENOMEM;
 
 	fm10k_dbg_init();
 
@@ -1037,11 +1039,6 @@ static void fm10k_tx_map(struct fm10k_ring *tx_ring,
 	/* notify HW of packet */
 	if (netif_xmit_stopped(txring_txq(tx_ring)) || !skb->xmit_more) {
 		writel(i, tx_ring->tail);
-
-		/* we need this if more than one processor can write to our tail
-		 * at a time, it synchronizes IO on IA64/Altix systems
-		 */
-		mmiowb();
 	}
 
 	return;
diff --git a/drivers/net/ethernet/intel/i40e/i40e.h b/drivers/net/ethernet/intel/i40e/i40e.h
index d684998ba2b0..d3cc3427caad 100644
--- a/drivers/net/ethernet/intel/i40e/i40e.h
+++ b/drivers/net/ethernet/intel/i40e/i40e.h
@@ -790,6 +790,8 @@ struct i40e_vsi {
 
 	/* VSI specific handlers */
 	irqreturn_t (*irq_handler)(int irq, void *data);
+
+	unsigned long *af_xdp_zc_qps; /* tracks AF_XDP ZC enabled qps */
 } ____cacheline_internodealigned_in_smp;
 
 struct i40e_netdev_priv {
@@ -1096,20 +1098,6 @@ static inline bool i40e_enabled_xdp_vsi(struct i40e_vsi *vsi)
 	return !!vsi->xdp_prog;
 }
 
-static inline struct xdp_umem *i40e_xsk_umem(struct i40e_ring *ring)
-{
-	bool xdp_on = i40e_enabled_xdp_vsi(ring->vsi);
-	int qid = ring->queue_index;
-
-	if (ring_is_xdp(ring))
-		qid -= ring->vsi->alloc_queue_pairs;
-
-	if (!xdp_on)
-		return NULL;
-
-	return xdp_get_umem_from_qid(ring->vsi->netdev, qid);
-}
-
 int i40e_create_queue_channel(struct i40e_vsi *vsi, struct i40e_channel *ch);
 int i40e_set_bw_limit(struct i40e_vsi *vsi, u16 seid, u64 max_tx_rate);
 int i40e_add_del_cloud_filter(struct i40e_vsi *vsi,
diff --git a/drivers/net/ethernet/intel/i40e/i40e_ethtool.c b/drivers/net/ethernet/intel/i40e/i40e_ethtool.c
index 4c885801fa26..7874d0ec7fb0 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_ethtool.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_ethtool.c
@@ -2573,8 +2573,7 @@ static int i40e_set_wol(struct net_device *netdev, struct ethtool_wolinfo *wol)
 		return -EOPNOTSUPP;
 
 	/* only magic packet is supported */
-	if (wol->wolopts && (wol->wolopts != WAKE_MAGIC)
-			  | (wol->wolopts != WAKE_FILTER))
+	if (wol->wolopts & ~WAKE_MAGIC)
 		return -EOPNOTSUPP;
 
 	/* is this a new value? */
diff --git a/drivers/net/ethernet/intel/i40e/i40e_main.c b/drivers/net/ethernet/intel/i40e/i40e_main.c
index da62218eb70a..b1c265012c8a 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_main.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_main.c
@@ -3064,6 +3064,26 @@ static void i40e_config_xps_tx_ring(struct i40e_ring *ring)
 }
 
 /**
+ * i40e_xsk_umem - Retrieve the AF_XDP ZC if XDP and ZC is enabled
+ * @ring: The Tx or Rx ring
+ *
+ * Returns the UMEM or NULL.
+ **/
+static struct xdp_umem *i40e_xsk_umem(struct i40e_ring *ring)
+{
+	bool xdp_on = i40e_enabled_xdp_vsi(ring->vsi);
+	int qid = ring->queue_index;
+
+	if (ring_is_xdp(ring))
+		qid -= ring->vsi->alloc_queue_pairs;
+
+	if (!xdp_on || !test_bit(qid, ring->vsi->af_xdp_zc_qps))
+		return NULL;
+
+	return xdp_get_umem_from_qid(ring->vsi->netdev, qid);
+}
+
+/**
  * i40e_configure_tx_ring - Configure a transmit ring context and rest
  * @ring: The Tx ring to configure
  *
@@ -10064,6 +10084,12 @@ static int i40e_vsi_mem_alloc(struct i40e_pf *pf, enum i40e_vsi_type type)
 	hash_init(vsi->mac_filter_hash);
 	vsi->irqs_ready = false;
 
+	if (type == I40E_VSI_MAIN) {
+		vsi->af_xdp_zc_qps = bitmap_zalloc(pf->num_lan_qps, GFP_KERNEL);
+		if (!vsi->af_xdp_zc_qps)
+			goto err_rings;
+	}
+
 	ret = i40e_set_num_rings_in_vsi(vsi);
 	if (ret)
 		goto err_rings;
@@ -10082,6 +10108,7 @@ static int i40e_vsi_mem_alloc(struct i40e_pf *pf, enum i40e_vsi_type type)
 	goto unlock_pf;
 
 err_rings:
+	bitmap_free(vsi->af_xdp_zc_qps);
 	pf->next_vsi = i - 1;
 	kfree(vsi);
 unlock_pf:
@@ -10162,6 +10189,7 @@ static int i40e_vsi_clear(struct i40e_vsi *vsi)
 	i40e_put_lump(pf->qp_pile, vsi->base_queue, vsi->idx);
 	i40e_put_lump(pf->irq_pile, vsi->base_vector, vsi->idx);
 
+	bitmap_free(vsi->af_xdp_zc_qps);
 	i40e_vsi_free_arrays(vsi, true);
 	i40e_clear_rss_config_user(vsi);
 
diff --git a/drivers/net/ethernet/intel/i40e/i40e_ptp.c b/drivers/net/ethernet/intel/i40e/i40e_ptp.c
index 5fb4353c742b..31575c0bb884 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_ptp.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_ptp.c
@@ -146,12 +146,13 @@ static int i40e_ptp_adjfreq(struct ptp_clock_info *ptp, s32 ppb)
 static int i40e_ptp_adjtime(struct ptp_clock_info *ptp, s64 delta)
 {
 	struct i40e_pf *pf = container_of(ptp, struct i40e_pf, ptp_caps);
-	struct timespec64 now;
+	struct timespec64 now, then;
 
+	then = ns_to_timespec64(delta);
 	mutex_lock(&pf->tmreg_lock);
 
 	i40e_ptp_read(pf, &now, NULL);
-	timespec64_add_ns(&now, delta);
+	now = timespec64_add(now, then);
 	i40e_ptp_write(pf, (const struct timespec64 *)&now);
 
 	mutex_unlock(&pf->tmreg_lock);
diff --git a/drivers/net/ethernet/intel/i40e/i40e_txrx.c b/drivers/net/ethernet/intel/i40e/i40e_txrx.c
index 6c97667d20ef..ffb611bbedfa 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_txrx.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_txrx.c
@@ -3471,11 +3471,6 @@ static inline int i40e_tx_map(struct i40e_ring *tx_ring, struct sk_buff *skb,
 	/* notify HW of packet */
 	if (netif_xmit_stopped(txring_txq(tx_ring)) || !skb->xmit_more) {
 		writel(i, tx_ring->tail);
-
-		/* we need this if more than one processor can write to our tail
-		 * at a time, it synchronizes IO on IA64/Altix systems
-		 */
-		mmiowb();
 	}
 
 	return 0;
diff --git a/drivers/net/ethernet/intel/i40e/i40e_xsk.c b/drivers/net/ethernet/intel/i40e/i40e_xsk.c
index b5c182e688e3..1b17486543ac 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_xsk.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_xsk.c
@@ -102,6 +102,8 @@ static int i40e_xsk_umem_enable(struct i40e_vsi *vsi, struct xdp_umem *umem,
 	if (err)
 		return err;
 
+	set_bit(qid, vsi->af_xdp_zc_qps);
+
 	if_running = netif_running(vsi->netdev) && i40e_enabled_xdp_vsi(vsi);
 
 	if (if_running) {
@@ -148,6 +150,7 @@ static int i40e_xsk_umem_disable(struct i40e_vsi *vsi, u16 qid)
 			return err;
 	}
 
+	clear_bit(qid, vsi->af_xdp_zc_qps);
 	i40e_xsk_umem_dma_unmap(vsi, umem);
 
 	if (if_running) {
diff --git a/drivers/net/ethernet/intel/iavf/iavf_txrx.c b/drivers/net/ethernet/intel/iavf/iavf_txrx.c
index 9b4d7cec2e18..6bfef82e7607 100644
--- a/drivers/net/ethernet/intel/iavf/iavf_txrx.c
+++ b/drivers/net/ethernet/intel/iavf/iavf_txrx.c
@@ -2360,11 +2360,6 @@ static inline void iavf_tx_map(struct iavf_ring *tx_ring, struct sk_buff *skb,
 	/* notify HW of packet */
 	if (netif_xmit_stopped(txring_txq(tx_ring)) || !skb->xmit_more) {
 		writel(i, tx_ring->tail);
-
-		/* we need this if more than one processor can write to our tail
-		 * at a time, it synchronizes IO on IA64/Altix systems
-		 */
-		mmiowb();
 	}
 
 	return;
diff --git a/drivers/net/ethernet/intel/ice/ice_txrx.c b/drivers/net/ethernet/intel/ice/ice_txrx.c
index c289d97f477d..1af21bbe180e 100644
--- a/drivers/net/ethernet/intel/ice/ice_txrx.c
+++ b/drivers/net/ethernet/intel/ice/ice_txrx.c
@@ -1356,11 +1356,6 @@ ice_tx_map(struct ice_ring *tx_ring, struct ice_tx_buf *first,
 	/* notify HW of packet */
 	if (netif_xmit_stopped(txring_txq(tx_ring)) || !skb->xmit_more) {
 		writel(i, tx_ring->tail);
-
-		/* we need this if more than one processor can write to our tail
-		 * at a time, it synchronizes IO on IA64/Altix systems
-		 */
-		mmiowb();
 	}
 
 	return;
diff --git a/drivers/net/ethernet/intel/igb/e1000_defines.h b/drivers/net/ethernet/intel/igb/e1000_defines.h
index 01fcfc6f3415..d2e2c50ce257 100644
--- a/drivers/net/ethernet/intel/igb/e1000_defines.h
+++ b/drivers/net/ethernet/intel/igb/e1000_defines.h
@@ -194,6 +194,8 @@
 /* enable link status from external LINK_0 and LINK_1 pins */
 #define E1000_CTRL_SWDPIN0  0x00040000  /* SWDPIN 0 value */
 #define E1000_CTRL_SWDPIN1  0x00080000  /* SWDPIN 1 value */
+#define E1000_CTRL_ADVD3WUC 0x00100000  /* D3 WUC */
+#define E1000_CTRL_EN_PHY_PWR_MGMT 0x00200000 /* PHY PM enable */
 #define E1000_CTRL_SDP0_DIR 0x00400000  /* SDP0 Data direction */
 #define E1000_CTRL_SDP1_DIR 0x00800000  /* SDP1 Data direction */
 #define E1000_CTRL_RST      0x04000000  /* Global reset */
diff --git a/drivers/net/ethernet/intel/igb/igb_main.c b/drivers/net/ethernet/intel/igb/igb_main.c
index 69b230c53fed..1d71ec360b1c 100644
--- a/drivers/net/ethernet/intel/igb/igb_main.c
+++ b/drivers/net/ethernet/intel/igb/igb_main.c
@@ -6028,11 +6028,6 @@ static int igb_tx_map(struct igb_ring *tx_ring,
 
 	if (netif_xmit_stopped(txring_txq(tx_ring)) || !skb->xmit_more) {
 		writel(i, tx_ring->tail);
-
-		/* we need this if more than one processor can write to our tail
-		 * at a time, it synchronizes IO on IA64/Altix systems
-		 */
-		mmiowb();
 	}
 	return 0;
 
@@ -8740,9 +8735,7 @@ static int __igb_shutdown(struct pci_dev *pdev, bool *enable_wake,
 	struct e1000_hw *hw = &adapter->hw;
 	u32 ctrl, rctl, status;
 	u32 wufc = runtime ? E1000_WUFC_LNKC : adapter->wol;
-#ifdef CONFIG_PM
-	int retval = 0;
-#endif
+	bool wake;
 
 	rtnl_lock();
 	netif_device_detach(netdev);
@@ -8755,14 +8748,6 @@ static int __igb_shutdown(struct pci_dev *pdev, bool *enable_wake,
 	igb_clear_interrupt_scheme(adapter);
 	rtnl_unlock();
 
-#ifdef CONFIG_PM
-	if (!runtime) {
-		retval = pci_save_state(pdev);
-		if (retval)
-			return retval;
-	}
-#endif
-
 	status = rd32(E1000_STATUS);
 	if (status & E1000_STATUS_LU)
 		wufc &= ~E1000_WUFC_LNKC;
@@ -8779,10 +8764,6 @@ static int __igb_shutdown(struct pci_dev *pdev, bool *enable_wake,
 		}
 
 		ctrl = rd32(E1000_CTRL);
-		/* advertise wake from D3Cold */
-		#define E1000_CTRL_ADVD3WUC 0x00100000
-		/* phy power management enable */
-		#define E1000_CTRL_EN_PHY_PWR_MGMT 0x00200000
 		ctrl |= E1000_CTRL_ADVD3WUC;
 		wr32(E1000_CTRL, ctrl);
 
@@ -8796,12 +8777,15 @@ static int __igb_shutdown(struct pci_dev *pdev, bool *enable_wake,
 		wr32(E1000_WUFC, 0);
 	}
 
-	*enable_wake = wufc || adapter->en_mng_pt;
-	if (!*enable_wake)
+	wake = wufc || adapter->en_mng_pt;
+	if (!wake)
 		igb_power_down_link(adapter);
 	else
 		igb_power_up_link(adapter);
 
+	if (enable_wake)
+		*enable_wake = wake;
+
 	/* Release control of h/w to f/w.  If f/w is AMT enabled, this
 	 * would have already happened in close and is redundant.
 	 */
@@ -8844,22 +8828,7 @@ static void igb_deliver_wake_packet(struct net_device *netdev)
 
 static int __maybe_unused igb_suspend(struct device *dev)
 {
-	int retval;
-	bool wake;
-	struct pci_dev *pdev = to_pci_dev(dev);
-
-	retval = __igb_shutdown(pdev, &wake, 0);
-	if (retval)
-		return retval;
-
-	if (wake) {
-		pci_prepare_to_sleep(pdev);
-	} else {
-		pci_wake_from_d3(pdev, false);
-		pci_set_power_state(pdev, PCI_D3hot);
-	}
-
-	return 0;
+	return __igb_shutdown(to_pci_dev(dev), NULL, 0);
 }
 
 static int __maybe_unused igb_resume(struct device *dev)
@@ -8930,22 +8899,7 @@ static int __maybe_unused igb_runtime_idle(struct device *dev)
 
 static int __maybe_unused igb_runtime_suspend(struct device *dev)
 {
-	struct pci_dev *pdev = to_pci_dev(dev);
-	int retval;
-	bool wake;
-
-	retval = __igb_shutdown(pdev, &wake, 1);
-	if (retval)
-		return retval;
-
-	if (wake) {
-		pci_prepare_to_sleep(pdev);
-	} else {
-		pci_wake_from_d3(pdev, false);
-		pci_set_power_state(pdev, PCI_D3hot);
-	}
-
-	return 0;
+	return __igb_shutdown(to_pci_dev(dev), NULL, 1);
 }
 
 static int __maybe_unused igb_runtime_resume(struct device *dev)
diff --git a/drivers/net/ethernet/intel/igbvf/netdev.c b/drivers/net/ethernet/intel/igbvf/netdev.c
index 4eab83faec62..34cd30d7162f 100644
--- a/drivers/net/ethernet/intel/igbvf/netdev.c
+++ b/drivers/net/ethernet/intel/igbvf/netdev.c
@@ -2279,10 +2279,6 @@ static inline void igbvf_tx_queue_adv(struct igbvf_adapter *adapter,
 	tx_ring->buffer_info[first].next_to_watch = tx_desc;
 	tx_ring->next_to_use = i;
 	writel(i, adapter->hw.hw_addr + tx_ring->tail);
-	/* we need this if more than one processor can write to our tail
-	 * at a time, it synchronizes IO on IA64/Altix systems
-	 */
-	mmiowb();
 }
 
 static netdev_tx_t igbvf_xmit_frame_ring_adv(struct sk_buff *skb,
diff --git a/drivers/net/ethernet/intel/igc/igc_main.c b/drivers/net/ethernet/intel/igc/igc_main.c
index 87a11879bf2d..f8d692f6aa4f 100644
--- a/drivers/net/ethernet/intel/igc/igc_main.c
+++ b/drivers/net/ethernet/intel/igc/igc_main.c
@@ -892,11 +892,6 @@ static int igc_tx_map(struct igc_ring *tx_ring,
 
 	if (netif_xmit_stopped(txring_txq(tx_ring)) || !skb->xmit_more) {
 		writel(i, tx_ring->tail);
-
-		/* we need this if more than one processor can write to our tail
-		 * at a time, it synchronizes IO on IA64/Altix systems
-		 */
-		mmiowb();
 	}
 
 	return 0;
diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
index e100054a3765..99e23cf6a73a 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
@@ -8299,11 +8299,6 @@ static int ixgbe_tx_map(struct ixgbe_ring *tx_ring,
 
 	if (netif_xmit_stopped(txring_txq(tx_ring)) || !skb->xmit_more) {
 		writel(i, tx_ring->tail);
-
-		/* we need this if more than one processor can write to our tail
-		 * at a time, it synchronizes IO on IA64/Altix systems
-		 */
-		mmiowb();
 	}
 
 	return 0;
diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_phy.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_phy.c
index cc4907f9ff02..2fb97967961c 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe_phy.c
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_phy.c
@@ -905,13 +905,12 @@ s32 ixgbe_mii_bus_init(struct ixgbe_hw *hw)
 	struct pci_dev *pdev = adapter->pdev;
 	struct device *dev = &adapter->netdev->dev;
 	struct mii_bus *bus;
+	int err = -ENODEV;
 
-	adapter->mii_bus = devm_mdiobus_alloc(dev);
-	if (!adapter->mii_bus)
+	bus = devm_mdiobus_alloc(dev);
+	if (!bus)
 		return -ENOMEM;
 
-	bus = adapter->mii_bus;
-
 	switch (hw->device_id) {
 	/* C3000 SoCs */
 	case IXGBE_DEV_ID_X550EM_A_KR:
@@ -949,12 +948,15 @@ s32 ixgbe_mii_bus_init(struct ixgbe_hw *hw)
 	 */
 	hw->phy.mdio.mode_support = MDIO_SUPPORTS_C45 | MDIO_SUPPORTS_C22;
 
-	return mdiobus_register(bus);
+	err = mdiobus_register(bus);
+	if (!err) {
+		adapter->mii_bus = bus;
+		return 0;
+	}
 
 ixgbe_no_mii_bus:
 	devm_mdiobus_free(dev, bus);
-	adapter->mii_bus = NULL;
-	return -ENODEV;
+	return err;
 }
 
 /**
diff --git a/drivers/net/ethernet/marvell/sky2.c b/drivers/net/ethernet/marvell/sky2.c
index 8b3495ee2b6e..49486c10ef81 100644
--- a/drivers/net/ethernet/marvell/sky2.c
+++ b/drivers/net/ethernet/marvell/sky2.c
@@ -1139,9 +1139,6 @@ static inline void sky2_put_idx(struct sky2_hw *hw, unsigned q, u16 idx)
 	/* Make sure write' to descriptors are complete before we tell hardware */
 	wmb();
 	sky2_write16(hw, Y2_QADDR(q, PREF_UNIT_PUT_IDX), idx);
-
-	/* Synchronize I/O on since next processor may write to tail */
-	mmiowb();
 }
 
 
@@ -1354,7 +1351,6 @@ stopped:
 
 	/* reset the Rx prefetch unit */
 	sky2_write32(hw, Y2_QADDR(rxq, PREF_UNIT_CTRL), PREF_UNIT_RST_SET);
-	mmiowb();
 }
 
 /* Clean out receive buffer area, assumes receiver hardware stopped */
diff --git a/drivers/net/ethernet/mellanox/mlx4/catas.c b/drivers/net/ethernet/mellanox/mlx4/catas.c
index c81d15bf259c..87e90b5d4d7d 100644
--- a/drivers/net/ethernet/mellanox/mlx4/catas.c
+++ b/drivers/net/ethernet/mellanox/mlx4/catas.c
@@ -129,10 +129,6 @@ static int mlx4_reset_slave(struct mlx4_dev *dev)
 	comm_flags = rst_req << COM_CHAN_RST_REQ_OFFSET;
 	__raw_writel((__force u32)cpu_to_be32(comm_flags),
 		     (__iomem char *)priv->mfunc.comm + MLX4_COMM_CHAN_FLAGS);
-	/* Make sure that our comm channel write doesn't
-	 * get mixed in with writes from another CPU.
-	 */
-	mmiowb();
 
 	end = msecs_to_jiffies(MLX4_COMM_TIME) + jiffies;
 	while (time_before(jiffies, end)) {
diff --git a/drivers/net/ethernet/mellanox/mlx4/cmd.c b/drivers/net/ethernet/mellanox/mlx4/cmd.c
index a5d5d6fc1da0..c678344d22a2 100644
--- a/drivers/net/ethernet/mellanox/mlx4/cmd.c
+++ b/drivers/net/ethernet/mellanox/mlx4/cmd.c
@@ -281,7 +281,6 @@ static int mlx4_comm_cmd_post(struct mlx4_dev *dev, u8 cmd, u16 param)
 	val = param | (cmd << 16) | (priv->cmd.comm_toggle << 31);
 	__raw_writel((__force u32) cpu_to_be32(val),
 		     &priv->mfunc.comm->slave_write);
-	mmiowb();
 	mutex_unlock(&dev->persist->device_state_mutex);
 	return 0;
 }
@@ -496,12 +495,6 @@ static int mlx4_cmd_post(struct mlx4_dev *dev, u64 in_param, u64 out_param,
 					       (op_modifier << HCR_OPMOD_SHIFT) |
 					       op), hcr + 6);
 
-	/*
-	 * Make sure that our HCR writes don't get mixed in with
-	 * writes from another CPU starting a FW command.
-	 */
-	mmiowb();
-
 	cmd->toggle = cmd->toggle ^ 1;
 
 	ret = 0;
@@ -2206,7 +2199,6 @@ static void mlx4_master_do_cmd(struct mlx4_dev *dev, int slave, u8 cmd,
 	}
 	__raw_writel((__force u32) cpu_to_be32(reply),
 		     &priv->mfunc.comm[slave].slave_read);
-	mmiowb();
 
 	return;
 
@@ -2410,7 +2402,6 @@ int mlx4_multi_func_init(struct mlx4_dev *dev)
 				     &priv->mfunc.comm[i].slave_write);
 			__raw_writel((__force u32) 0,
 				     &priv->mfunc.comm[i].slave_read);
-			mmiowb();
 			for (port = 1; port <= MLX4_MAX_PORTS; port++) {
 				struct mlx4_vport_state *admin_vport;
 				struct mlx4_vport_state *oper_vport;
@@ -2576,10 +2567,6 @@ void mlx4_report_internal_err_comm_event(struct mlx4_dev *dev)
 		slave_read |= (u32)COMM_CHAN_EVENT_INTERNAL_ERR;
 		__raw_writel((__force u32)cpu_to_be32(slave_read),
 			     &priv->mfunc.comm[slave].slave_read);
-		/* Make sure that our comm channel write doesn't
-		 * get mixed in with writes from another CPU.
-		 */
-		mmiowb();
 	}
 }
 
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/cmd.c b/drivers/net/ethernet/mellanox/mlx5/core/cmd.c
index be48c6440251..c087d1014b09 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/cmd.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/cmd.c
@@ -917,7 +917,6 @@ static void cmd_work_handler(struct work_struct *work)
 	mlx5_core_dbg(dev, "writing 0x%x to command doorbell\n", 1 << ent->idx);
 	wmb();
 	iowrite32be(1 << ent->idx, &dev->iseg->cmd_dbell);
-	mmiowb();
 	/* if not in polling don't use ent after this point */
 	if (cmd_mode == CMD_MODE_POLLING || poll_cmd) {
 		poll_timeout(ent);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en.h b/drivers/net/ethernet/mellanox/mlx5/core/en.h
index 71c65cc17904..d3eaf2ceaa39 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en.h
@@ -858,6 +858,7 @@ void mlx5e_close_channels(struct mlx5e_channels *chs);
  * switching channels
  */
 typedef int (*mlx5e_fp_hw_modify)(struct mlx5e_priv *priv);
+int mlx5e_safe_reopen_channels(struct mlx5e_priv *priv);
 int mlx5e_safe_switch_channels(struct mlx5e_priv *priv,
 			       struct mlx5e_channels *new_chs,
 			       mlx5e_fp_hw_modify hw_modify);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/port.c b/drivers/net/ethernet/mellanox/mlx5/core/en/port.c
index 122927f3a600..d5e5afbdca6d 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/port.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/port.c
@@ -96,9 +96,6 @@ int mlx5_port_query_eth_proto(struct mlx5_core_dev *dev, u8 port, bool ext,
 	if (!eproto)
 		return -EINVAL;
 
-	if (ext !=  MLX5_CAP_PCAM_FEATURE(dev, ptys_extended_ethernet))
-		return -EOPNOTSUPP;
-
 	err = mlx5_query_port_ptys(dev, out, sizeof(out), MLX5_PTYS_EN, port);
 	if (err)
 		return err;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/port_buffer.c b/drivers/net/ethernet/mellanox/mlx5/core/en/port_buffer.c
index eac245a93f91..4ab0d030b544 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/port_buffer.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/port_buffer.c
@@ -122,7 +122,9 @@ out:
 	return err;
 }
 
-/* xoff = ((301+2.16 * len [m]) * speed [Gbps] + 2.72 MTU [B]) */
+/* xoff = ((301+2.16 * len [m]) * speed [Gbps] + 2.72 MTU [B])
+ * minimum speed value is 40Gbps
+ */
 static u32 calculate_xoff(struct mlx5e_priv *priv, unsigned int mtu)
 {
 	u32 speed;
@@ -130,10 +132,9 @@ static u32 calculate_xoff(struct mlx5e_priv *priv, unsigned int mtu)
 	int err;
 
 	err = mlx5e_port_linkspeed(priv->mdev, &speed);
-	if (err) {
-		mlx5_core_warn(priv->mdev, "cannot get port speed\n");
-		return 0;
-	}
+	if (err)
+		speed = SPEED_40000;
+	speed = max_t(u32, speed, SPEED_40000);
 
 	xoff = (301 + 216 * priv->dcbx.cable_len / 100) * speed / 1000 + 272 * mtu / 100;
 
@@ -142,7 +143,7 @@ static u32 calculate_xoff(struct mlx5e_priv *priv, unsigned int mtu)
 }
 
 static int update_xoff_threshold(struct mlx5e_port_buffer *port_buffer,
-				 u32 xoff, unsigned int mtu)
+				 u32 xoff, unsigned int max_mtu)
 {
 	int i;
 
@@ -154,11 +155,12 @@ static int update_xoff_threshold(struct mlx5e_port_buffer *port_buffer,
 		}
 
 		if (port_buffer->buffer[i].size <
-		    (xoff + mtu + (1 << MLX5E_BUFFER_CELL_SHIFT)))
+		    (xoff + max_mtu + (1 << MLX5E_BUFFER_CELL_SHIFT)))
 			return -ENOMEM;
 
 		port_buffer->buffer[i].xoff = port_buffer->buffer[i].size - xoff;
-		port_buffer->buffer[i].xon  = port_buffer->buffer[i].xoff - mtu;
+		port_buffer->buffer[i].xon  =
+			port_buffer->buffer[i].xoff - max_mtu;
 	}
 
 	return 0;
@@ -166,7 +168,7 @@ static int update_xoff_threshold(struct mlx5e_port_buffer *port_buffer,
 
 /**
  * update_buffer_lossy()
- *   mtu: device's MTU
+ *   max_mtu: netdev's max_mtu
  *   pfc_en: <input> current pfc configuration
  *   buffer: <input> current prio to buffer mapping
  *   xoff:   <input> xoff value
@@ -183,7 +185,7 @@ static int update_xoff_threshold(struct mlx5e_port_buffer *port_buffer,
  *     Return 0 if no error.
  *     Set change to true if buffer configuration is modified.
  */
-static int update_buffer_lossy(unsigned int mtu,
+static int update_buffer_lossy(unsigned int max_mtu,
 			       u8 pfc_en, u8 *buffer, u32 xoff,
 			       struct mlx5e_port_buffer *port_buffer,
 			       bool *change)
@@ -220,7 +222,7 @@ static int update_buffer_lossy(unsigned int mtu,
 	}
 
 	if (changed) {
-		err = update_xoff_threshold(port_buffer, xoff, mtu);
+		err = update_xoff_threshold(port_buffer, xoff, max_mtu);
 		if (err)
 			return err;
 
@@ -230,6 +232,7 @@ static int update_buffer_lossy(unsigned int mtu,
 	return 0;
 }
 
+#define MINIMUM_MAX_MTU 9216
 int mlx5e_port_manual_buffer_config(struct mlx5e_priv *priv,
 				    u32 change, unsigned int mtu,
 				    struct ieee_pfc *pfc,
@@ -241,12 +244,14 @@ int mlx5e_port_manual_buffer_config(struct mlx5e_priv *priv,
 	bool update_prio2buffer = false;
 	u8 buffer[MLX5E_MAX_PRIORITY];
 	bool update_buffer = false;
+	unsigned int max_mtu;
 	u32 total_used = 0;
 	u8 curr_pfc_en;
 	int err;
 	int i;
 
 	mlx5e_dbg(HW, priv, "%s: change=%x\n", __func__, change);
+	max_mtu = max_t(unsigned int, priv->netdev->max_mtu, MINIMUM_MAX_MTU);
 
 	err = mlx5e_port_query_buffer(priv, &port_buffer);
 	if (err)
@@ -254,7 +259,7 @@ int mlx5e_port_manual_buffer_config(struct mlx5e_priv *priv,
 
 	if (change & MLX5E_PORT_BUFFER_CABLE_LEN) {
 		update_buffer = true;
-		err = update_xoff_threshold(&port_buffer, xoff, mtu);
+		err = update_xoff_threshold(&port_buffer, xoff, max_mtu);
 		if (err)
 			return err;
 	}
@@ -264,7 +269,7 @@ int mlx5e_port_manual_buffer_config(struct mlx5e_priv *priv,
 		if (err)
 			return err;
 
-		err = update_buffer_lossy(mtu, pfc->pfc_en, buffer, xoff,
+		err = update_buffer_lossy(max_mtu, pfc->pfc_en, buffer, xoff,
 					  &port_buffer, &update_buffer);
 		if (err)
 			return err;
@@ -276,8 +281,8 @@ int mlx5e_port_manual_buffer_config(struct mlx5e_priv *priv,
 		if (err)
 			return err;
 
-		err = update_buffer_lossy(mtu, curr_pfc_en, prio2buffer, xoff,
-					  &port_buffer, &update_buffer);
+		err = update_buffer_lossy(max_mtu, curr_pfc_en, prio2buffer,
+					  xoff, &port_buffer, &update_buffer);
 		if (err)
 			return err;
 	}
@@ -301,7 +306,7 @@ int mlx5e_port_manual_buffer_config(struct mlx5e_priv *priv,
 			return -EINVAL;
 
 		update_buffer = true;
-		err = update_xoff_threshold(&port_buffer, xoff, mtu);
+		err = update_xoff_threshold(&port_buffer, xoff, max_mtu);
 		if (err)
 			return err;
 	}
@@ -309,7 +314,7 @@ int mlx5e_port_manual_buffer_config(struct mlx5e_priv *priv,
 	/* Need to update buffer configuration if xoff value is changed */
 	if (!update_buffer && xoff != priv->dcbx.xoff) {
 		update_buffer = true;
-		err = update_xoff_threshold(&port_buffer, xoff, mtu);
+		err = update_xoff_threshold(&port_buffer, xoff, max_mtu);
 		if (err)
 			return err;
 	}
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/reporter_tx.c b/drivers/net/ethernet/mellanox/mlx5/core/en/reporter_tx.c
index 9d38e62cdf24..476dd97f7f2f 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/reporter_tx.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/reporter_tx.c
@@ -186,12 +186,17 @@ static int mlx5e_tx_reporter_recover_from_ctx(struct mlx5e_tx_err_ctx *err_ctx)
 
 static int mlx5e_tx_reporter_recover_all(struct mlx5e_priv *priv)
 {
-	int err;
+	int err = 0;
 
 	rtnl_lock();
 	mutex_lock(&priv->state_lock);
-	mlx5e_close_locked(priv->netdev);
-	err = mlx5e_open_locked(priv->netdev);
+
+	if (!test_bit(MLX5E_STATE_OPENED, &priv->state))
+		goto out;
+
+	err = mlx5e_safe_reopen_channels(priv);
+
+out:
 	mutex_unlock(&priv->state_lock);
 	rtnl_unlock();
 
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun.c b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun.c
index fa2a3c444cdc..eec07b34b4ad 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun.c
@@ -39,6 +39,10 @@ static int get_route_and_out_devs(struct mlx5e_priv *priv,
 			return -EOPNOTSUPP;
 	}
 
+	if (!(mlx5e_eswitch_rep(*out_dev) &&
+	      mlx5e_is_uplink_rep(netdev_priv(*out_dev))))
+		return -EOPNOTSUPP;
+
 	return 0;
 }
 
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.c b/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.c
index 03b2a9f9c589..cad34d6f5f45 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.c
@@ -33,6 +33,26 @@
 #include <linux/bpf_trace.h>
 #include "en/xdp.h"
 
+int mlx5e_xdp_max_mtu(struct mlx5e_params *params)
+{
+	int hr = NET_IP_ALIGN + XDP_PACKET_HEADROOM;
+
+	/* Let S := SKB_DATA_ALIGN(sizeof(struct skb_shared_info)).
+	 * The condition checked in mlx5e_rx_is_linear_skb is:
+	 *   SKB_DATA_ALIGN(sw_mtu + hard_mtu + hr) + S <= PAGE_SIZE         (1)
+	 *   (Note that hw_mtu == sw_mtu + hard_mtu.)
+	 * What is returned from this function is:
+	 *   max_mtu = PAGE_SIZE - S - hr - hard_mtu                         (2)
+	 * After assigning sw_mtu := max_mtu, the left side of (1) turns to
+	 * SKB_DATA_ALIGN(PAGE_SIZE - S) + S, which is equal to PAGE_SIZE,
+	 * because both PAGE_SIZE and S are already aligned. Any number greater
+	 * than max_mtu would make the left side of (1) greater than PAGE_SIZE,
+	 * so max_mtu is the maximum MTU allowed.
+	 */
+
+	return MLX5E_HW2SW_MTU(params, SKB_MAX_HEAD(hr));
+}
+
 static inline bool
 mlx5e_xmit_xdp_buff(struct mlx5e_xdpsq *sq, struct mlx5e_dma_info *di,
 		    struct xdp_buff *xdp)
@@ -304,9 +324,9 @@ bool mlx5e_poll_xdpsq_cq(struct mlx5e_cq *cq, struct mlx5e_rq *rq)
 					mlx5e_xdpi_fifo_pop(xdpi_fifo);
 
 				if (is_redirect) {
-					xdp_return_frame(xdpi.xdpf);
 					dma_unmap_single(sq->pdev, xdpi.dma_addr,
 							 xdpi.xdpf->len, DMA_TO_DEVICE);
+					xdp_return_frame(xdpi.xdpf);
 				} else {
 					/* Recycle RX page */
 					mlx5e_page_release(rq, &xdpi.di, true);
@@ -345,9 +365,9 @@ void mlx5e_free_xdpsq_descs(struct mlx5e_xdpsq *sq, struct mlx5e_rq *rq)
 				mlx5e_xdpi_fifo_pop(xdpi_fifo);
 
 			if (is_redirect) {
-				xdp_return_frame(xdpi.xdpf);
 				dma_unmap_single(sq->pdev, xdpi.dma_addr,
 						 xdpi.xdpf->len, DMA_TO_DEVICE);
+				xdp_return_frame(xdpi.xdpf);
 			} else {
 				/* Recycle RX page */
 				mlx5e_page_release(rq, &xdpi.di, false);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.h b/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.h
index ee27a7c8cd87..553956cadc8a 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.h
@@ -34,13 +34,12 @@
 
 #include "en.h"
 
-#define MLX5E_XDP_MAX_MTU ((int)(PAGE_SIZE - \
-				 MLX5_SKB_FRAG_SZ(XDP_PACKET_HEADROOM)))
 #define MLX5E_XDP_MIN_INLINE (ETH_HLEN + VLAN_HLEN)
 #define MLX5E_XDP_TX_EMPTY_DS_COUNT \
 	(sizeof(struct mlx5e_tx_wqe) / MLX5_SEND_WQE_DS)
 #define MLX5E_XDP_TX_DS_COUNT (MLX5E_XDP_TX_EMPTY_DS_COUNT + 1 /* SG DS */)
 
+int mlx5e_xdp_max_mtu(struct mlx5e_params *params);
 bool mlx5e_xdp_handle(struct mlx5e_rq *rq, struct mlx5e_dma_info *di,
 		      void *va, u16 *rx_headroom, u32 *len);
 bool mlx5e_poll_xdpsq_cq(struct mlx5e_cq *cq, struct mlx5e_rq *rq);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_common.c b/drivers/net/ethernet/mellanox/mlx5/core/en_common.c
index 3078491cc0d0..1539cf3de5dc 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_common.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_common.c
@@ -45,7 +45,9 @@ int mlx5e_create_tir(struct mlx5_core_dev *mdev,
 	if (err)
 		return err;
 
+	mutex_lock(&mdev->mlx5e_res.td.list_lock);
 	list_add(&tir->list, &mdev->mlx5e_res.td.tirs_list);
+	mutex_unlock(&mdev->mlx5e_res.td.list_lock);
 
 	return 0;
 }
@@ -53,8 +55,10 @@ int mlx5e_create_tir(struct mlx5_core_dev *mdev,
 void mlx5e_destroy_tir(struct mlx5_core_dev *mdev,
 		       struct mlx5e_tir *tir)
 {
+	mutex_lock(&mdev->mlx5e_res.td.list_lock);
 	mlx5_core_destroy_tir(mdev, tir->tirn);
 	list_del(&tir->list);
+	mutex_unlock(&mdev->mlx5e_res.td.list_lock);
 }
 
 static int mlx5e_create_mkey(struct mlx5_core_dev *mdev, u32 pdn,
@@ -114,6 +118,7 @@ int mlx5e_create_mdev_resources(struct mlx5_core_dev *mdev)
 	}
 
 	INIT_LIST_HEAD(&mdev->mlx5e_res.td.tirs_list);
+	mutex_init(&mdev->mlx5e_res.td.list_lock);
 
 	return 0;
 
@@ -141,15 +146,17 @@ int mlx5e_refresh_tirs(struct mlx5e_priv *priv, bool enable_uc_lb)
 {
 	struct mlx5_core_dev *mdev = priv->mdev;
 	struct mlx5e_tir *tir;
-	int err  = -ENOMEM;
+	int err  = 0;
 	u32 tirn = 0;
 	int inlen;
 	void *in;
 
 	inlen = MLX5_ST_SZ_BYTES(modify_tir_in);
 	in = kvzalloc(inlen, GFP_KERNEL);
-	if (!in)
+	if (!in) {
+		err = -ENOMEM;
 		goto out;
+	}
 
 	if (enable_uc_lb)
 		MLX5_SET(modify_tir_in, in, ctx.self_lb_block,
@@ -157,6 +164,7 @@ int mlx5e_refresh_tirs(struct mlx5e_priv *priv, bool enable_uc_lb)
 
 	MLX5_SET(modify_tir_in, in, bitmask.self_lb_en, 1);
 
+	mutex_lock(&mdev->mlx5e_res.td.list_lock);
 	list_for_each_entry(tir, &mdev->mlx5e_res.td.tirs_list, list) {
 		tirn = tir->tirn;
 		err = mlx5_core_modify_tir(mdev, tirn, in, inlen);
@@ -168,6 +176,7 @@ out:
 	kvfree(in);
 	if (err)
 		netdev_err(priv->netdev, "refresh tir(0x%x) failed, %d\n", tirn, err);
+	mutex_unlock(&mdev->mlx5e_res.td.list_lock);
 
 	return err;
 }
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c b/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c
index a0987cc5fe4a..78dc8fe2a83c 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c
@@ -603,16 +603,18 @@ static void ptys2ethtool_supported_link(struct mlx5_core_dev *mdev,
 			  __ETHTOOL_LINK_MODE_MASK_NBITS);
 }
 
-static void ptys2ethtool_adver_link(struct mlx5_core_dev *mdev,
-				    unsigned long *advertising_modes,
-				    u32 eth_proto_cap)
+static void ptys2ethtool_adver_link(unsigned long *advertising_modes,
+				    u32 eth_proto_cap, bool ext)
 {
 	unsigned long proto_cap = eth_proto_cap;
 	struct ptys2ethtool_config *table;
 	u32 max_size;
 	int proto;
 
-	mlx5e_ethtool_get_speed_arr(mdev, &table, &max_size);
+	table = ext ? ptys2ext_ethtool_table : ptys2legacy_ethtool_table;
+	max_size = ext ? ARRAY_SIZE(ptys2ext_ethtool_table) :
+			 ARRAY_SIZE(ptys2legacy_ethtool_table);
+
 	for_each_set_bit(proto, &proto_cap, max_size)
 		bitmap_or(advertising_modes, advertising_modes,
 			  table[proto].advertised,
@@ -794,12 +796,12 @@ static void get_supported(struct mlx5_core_dev *mdev, u32 eth_proto_cap,
 	ethtool_link_ksettings_add_link_mode(link_ksettings, supported, Pause);
 }
 
-static void get_advertising(struct mlx5_core_dev *mdev, u32 eth_proto_cap,
-			    u8 tx_pause, u8 rx_pause,
-			    struct ethtool_link_ksettings *link_ksettings)
+static void get_advertising(u32 eth_proto_cap, u8 tx_pause, u8 rx_pause,
+			    struct ethtool_link_ksettings *link_ksettings,
+			    bool ext)
 {
 	unsigned long *advertising = link_ksettings->link_modes.advertising;
-	ptys2ethtool_adver_link(mdev, advertising, eth_proto_cap);
+	ptys2ethtool_adver_link(advertising, eth_proto_cap, ext);
 
 	if (rx_pause)
 		ethtool_link_ksettings_add_link_mode(link_ksettings, advertising, Pause);
@@ -854,8 +856,9 @@ static void get_lp_advertising(struct mlx5_core_dev *mdev, u32 eth_proto_lp,
 			       struct ethtool_link_ksettings *link_ksettings)
 {
 	unsigned long *lp_advertising = link_ksettings->link_modes.lp_advertising;
+	bool ext = MLX5_CAP_PCAM_FEATURE(mdev, ptys_extended_ethernet);
 
-	ptys2ethtool_adver_link(mdev, lp_advertising, eth_proto_lp);
+	ptys2ethtool_adver_link(lp_advertising, eth_proto_lp, ext);
 }
 
 int mlx5e_ethtool_get_link_ksettings(struct mlx5e_priv *priv,
@@ -872,6 +875,7 @@ int mlx5e_ethtool_get_link_ksettings(struct mlx5e_priv *priv,
 	u8 an_disable_admin;
 	u8 an_status;
 	u8 connector_type;
+	bool admin_ext;
 	bool ext;
 	int err;
 
@@ -886,6 +890,19 @@ int mlx5e_ethtool_get_link_ksettings(struct mlx5e_priv *priv,
 					      eth_proto_capability);
 	eth_proto_admin  = MLX5_GET_ETH_PROTO(ptys_reg, out, ext,
 					      eth_proto_admin);
+	/* Fields: eth_proto_admin and ext_eth_proto_admin  are
+	 * mutually exclusive. Hence try reading legacy advertising
+	 * when extended advertising is zero.
+	 * admin_ext indicates how eth_proto_admin should be
+	 * interpreted
+	 */
+	admin_ext = ext;
+	if (ext && !eth_proto_admin) {
+		eth_proto_admin  = MLX5_GET_ETH_PROTO(ptys_reg, out, false,
+						      eth_proto_admin);
+		admin_ext = false;
+	}
+
 	eth_proto_oper   = MLX5_GET_ETH_PROTO(ptys_reg, out, ext,
 					      eth_proto_oper);
 	eth_proto_lp	    = MLX5_GET(ptys_reg, out, eth_proto_lp_advertise);
@@ -899,7 +916,8 @@ int mlx5e_ethtool_get_link_ksettings(struct mlx5e_priv *priv,
 	ethtool_link_ksettings_zero_link_mode(link_ksettings, advertising);
 
 	get_supported(mdev, eth_proto_cap, link_ksettings);
-	get_advertising(mdev, eth_proto_admin, tx_pause, rx_pause, link_ksettings);
+	get_advertising(eth_proto_admin, tx_pause, rx_pause, link_ksettings,
+			admin_ext);
 	get_speed_duplex(priv->netdev, eth_proto_oper, link_ksettings);
 
 	eth_proto_oper = eth_proto_oper ? eth_proto_oper : eth_proto_cap;
@@ -997,19 +1015,17 @@ int mlx5e_ethtool_set_link_ksettings(struct mlx5e_priv *priv,
 
 #define MLX5E_PTYS_EXT ((1ULL << ETHTOOL_LINK_MODE_50000baseKR_Full_BIT) - 1)
 
-	ext_requested = (link_ksettings->link_modes.advertising[0] >
-			MLX5E_PTYS_EXT);
+	ext_requested = !!(link_ksettings->link_modes.advertising[0] >
+			MLX5E_PTYS_EXT ||
+			link_ksettings->link_modes.advertising[1]);
 	ext_supported = MLX5_CAP_PCAM_FEATURE(mdev, ptys_extended_ethernet);
-
-	/*when ptys_extended_ethernet is set legacy link modes are deprecated */
-	if (ext_requested != ext_supported)
-		return -EPROTONOSUPPORT;
+	ext_requested &= ext_supported;
 
 	speed = link_ksettings->base.speed;
 	ethtool2ptys_adver_func = ext_requested ?
 				  mlx5e_ethtool2ptys_ext_adver_link :
 				  mlx5e_ethtool2ptys_adver_link;
-	err = mlx5_port_query_eth_proto(mdev, 1, ext_supported, &eproto);
+	err = mlx5_port_query_eth_proto(mdev, 1, ext_requested, &eproto);
 	if (err) {
 		netdev_err(priv->netdev, "%s: query port eth proto failed: %d\n",
 			   __func__, err);
@@ -1037,7 +1053,7 @@ int mlx5e_ethtool_set_link_ksettings(struct mlx5e_priv *priv,
 	if (!an_changes && link_modes == eproto.admin)
 		goto out;
 
-	mlx5_port_set_eth_ptys(mdev, an_disable, link_modes, ext_supported);
+	mlx5_port_set_eth_ptys(mdev, an_disable, link_modes, ext_requested);
 	mlx5_toggle_port_link(mdev);
 
 out:
@@ -1570,7 +1586,7 @@ static int mlx5e_get_module_info(struct net_device *netdev,
 		break;
 	case MLX5_MODULE_ID_SFP:
 		modinfo->type       = ETH_MODULE_SFF_8472;
-		modinfo->eeprom_len = ETH_MODULE_SFF_8472_LEN;
+		modinfo->eeprom_len = MLX5_EEPROM_PAGE_LENGTH;
 		break;
 	default:
 		netdev_err(priv->netdev, "%s: cable type not recognized:0x%x\n",
@@ -1752,7 +1768,8 @@ static int set_pflag_rx_no_csum_complete(struct net_device *netdev, bool enable)
 	struct mlx5e_channel *c;
 	int i;
 
-	if (!test_bit(MLX5E_STATE_OPENED, &priv->state))
+	if (!test_bit(MLX5E_STATE_OPENED, &priv->state) ||
+	    priv->channels.params.xdp_prog)
 		return 0;
 
 	for (i = 0; i < channels->num; i++) {
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
index b5fdbd3190d9..46157e2a1e5a 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
@@ -951,7 +951,11 @@ static int mlx5e_open_rq(struct mlx5e_channel *c,
 	if (params->rx_dim_enabled)
 		__set_bit(MLX5E_RQ_STATE_AM, &c->rq.state);
 
-	if (MLX5E_GET_PFLAG(params, MLX5E_PFLAG_RX_NO_CSUM_COMPLETE))
+	/* We disable csum_complete when XDP is enabled since
+	 * XDP programs might manipulate packets which will render
+	 * skb->checksum incorrect.
+	 */
+	if (MLX5E_GET_PFLAG(params, MLX5E_PFLAG_RX_NO_CSUM_COMPLETE) || c->xdp)
 		__set_bit(MLX5E_RQ_STATE_NO_CSUM_COMPLETE, &c->rq.state);
 
 	return 0;
@@ -2937,6 +2941,14 @@ int mlx5e_safe_switch_channels(struct mlx5e_priv *priv,
 	return 0;
 }
 
+int mlx5e_safe_reopen_channels(struct mlx5e_priv *priv)
+{
+	struct mlx5e_channels new_channels = {};
+
+	new_channels.params = priv->channels.params;
+	return mlx5e_safe_switch_channels(priv, &new_channels, NULL);
+}
+
 void mlx5e_timestamp_init(struct mlx5e_priv *priv)
 {
 	priv->tstamp.tx_type   = HWTSTAMP_TX_OFF;
@@ -3765,7 +3777,7 @@ int mlx5e_change_mtu(struct net_device *netdev, int new_mtu,
 	if (params->xdp_prog &&
 	    !mlx5e_rx_is_linear_skb(priv->mdev, &new_channels.params)) {
 		netdev_err(netdev, "MTU(%d) > %d is not allowed while XDP enabled\n",
-			   new_mtu, MLX5E_XDP_MAX_MTU);
+			   new_mtu, mlx5e_xdp_max_mtu(params));
 		err = -EINVAL;
 		goto out;
 	}
@@ -4161,11 +4173,10 @@ static void mlx5e_tx_timeout_work(struct work_struct *work)
 	if (!report_failed)
 		goto unlock;
 
-	mlx5e_close_locked(priv->netdev);
-	err = mlx5e_open_locked(priv->netdev);
+	err = mlx5e_safe_reopen_channels(priv);
 	if (err)
 		netdev_err(priv->netdev,
-			   "mlx5e_open_locked failed recovering from a tx_timeout, err(%d).\n",
+			   "mlx5e_safe_reopen_channels failed recovering from a tx_timeout, err(%d).\n",
 			   err);
 
 unlock:
@@ -4201,7 +4212,8 @@ static int mlx5e_xdp_allowed(struct mlx5e_priv *priv, struct bpf_prog *prog)
 
 	if (!mlx5e_rx_is_linear_skb(priv->mdev, &new_channels.params)) {
 		netdev_warn(netdev, "XDP is not allowed with MTU(%d) > %d\n",
-			    new_channels.params.sw_mtu, MLX5E_XDP_MAX_MTU);
+			    new_channels.params.sw_mtu,
+			    mlx5e_xdp_max_mtu(&new_channels.params));
 		return -EINVAL;
 	}
 
@@ -4553,7 +4565,7 @@ void mlx5e_build_rss_params(struct mlx5e_rss_params *rss_params,
 {
 	enum mlx5e_traffic_types tt;
 
-	rss_params->hfunc = ETH_RSS_HASH_XOR;
+	rss_params->hfunc = ETH_RSS_HASH_TOP;
 	netdev_rss_key_fill(rss_params->toeplitz_hash_key,
 			    sizeof(rss_params->toeplitz_hash_key));
 	mlx5e_build_default_indir_rqt(rss_params->indirection_rqt,
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c
index 3dde5c7e0739..c3b3002ff62f 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c
@@ -692,7 +692,14 @@ static inline bool is_last_ethertype_ip(struct sk_buff *skb, int *network_depth,
 {
 	*proto = ((struct ethhdr *)skb->data)->h_proto;
 	*proto = __vlan_get_protocol(skb, *proto, network_depth);
-	return (*proto == htons(ETH_P_IP) || *proto == htons(ETH_P_IPV6));
+
+	if (*proto == htons(ETH_P_IP))
+		return pskb_may_pull(skb, *network_depth + sizeof(struct iphdr));
+
+	if (*proto == htons(ETH_P_IPV6))
+		return pskb_may_pull(skb, *network_depth + sizeof(struct ipv6hdr));
+
+	return false;
 }
 
 static inline void mlx5e_enable_ecn(struct mlx5e_rq *rq, struct sk_buff *skb)
@@ -712,17 +719,6 @@ static inline void mlx5e_enable_ecn(struct mlx5e_rq *rq, struct sk_buff *skb)
 	rq->stats->ecn_mark += !!rc;
 }
 
-static u32 mlx5e_get_fcs(const struct sk_buff *skb)
-{
-	const void *fcs_bytes;
-	u32 _fcs_bytes;
-
-	fcs_bytes = skb_header_pointer(skb, skb->len - ETH_FCS_LEN,
-				       ETH_FCS_LEN, &_fcs_bytes);
-
-	return __get_unaligned_cpu32(fcs_bytes);
-}
-
 static u8 get_ip_proto(struct sk_buff *skb, int network_depth, __be16 proto)
 {
 	void *ip_p = skb->data + network_depth;
@@ -733,6 +729,68 @@ static u8 get_ip_proto(struct sk_buff *skb, int network_depth, __be16 proto)
 
 #define short_frame(size) ((size) <= ETH_ZLEN + ETH_FCS_LEN)
 
+#define MAX_PADDING 8
+
+static void
+tail_padding_csum_slow(struct sk_buff *skb, int offset, int len,
+		       struct mlx5e_rq_stats *stats)
+{
+	stats->csum_complete_tail_slow++;
+	skb->csum = csum_block_add(skb->csum,
+				   skb_checksum(skb, offset, len, 0),
+				   offset);
+}
+
+static void
+tail_padding_csum(struct sk_buff *skb, int offset,
+		  struct mlx5e_rq_stats *stats)
+{
+	u8 tail_padding[MAX_PADDING];
+	int len = skb->len - offset;
+	void *tail;
+
+	if (unlikely(len > MAX_PADDING)) {
+		tail_padding_csum_slow(skb, offset, len, stats);
+		return;
+	}
+
+	tail = skb_header_pointer(skb, offset, len, tail_padding);
+	if (unlikely(!tail)) {
+		tail_padding_csum_slow(skb, offset, len, stats);
+		return;
+	}
+
+	stats->csum_complete_tail++;
+	skb->csum = csum_block_add(skb->csum, csum_partial(tail, len, 0), offset);
+}
+
+static void
+mlx5e_skb_padding_csum(struct sk_buff *skb, int network_depth, __be16 proto,
+		       struct mlx5e_rq_stats *stats)
+{
+	struct ipv6hdr *ip6;
+	struct iphdr   *ip4;
+	int pkt_len;
+
+	switch (proto) {
+	case htons(ETH_P_IP):
+		ip4 = (struct iphdr *)(skb->data + network_depth);
+		pkt_len = network_depth + ntohs(ip4->tot_len);
+		break;
+	case htons(ETH_P_IPV6):
+		ip6 = (struct ipv6hdr *)(skb->data + network_depth);
+		pkt_len = network_depth + sizeof(*ip6) + ntohs(ip6->payload_len);
+		break;
+	default:
+		return;
+	}
+
+	if (likely(pkt_len >= skb->len))
+		return;
+
+	tail_padding_csum(skb, pkt_len, stats);
+}
+
 static inline void mlx5e_handle_csum(struct net_device *netdev,
 				     struct mlx5_cqe64 *cqe,
 				     struct mlx5e_rq *rq,
@@ -752,7 +810,8 @@ static inline void mlx5e_handle_csum(struct net_device *netdev,
 		return;
 	}
 
-	if (unlikely(test_bit(MLX5E_RQ_STATE_NO_CSUM_COMPLETE, &rq->state)))
+	/* True when explicitly set via priv flag, or XDP prog is loaded */
+	if (test_bit(MLX5E_RQ_STATE_NO_CSUM_COMPLETE, &rq->state))
 		goto csum_unnecessary;
 
 	/* CQE csum doesn't cover padding octets in short ethernet
@@ -780,18 +839,15 @@ static inline void mlx5e_handle_csum(struct net_device *netdev,
 			skb->csum = csum_partial(skb->data + ETH_HLEN,
 						 network_depth - ETH_HLEN,
 						 skb->csum);
-		if (unlikely(netdev->features & NETIF_F_RXFCS))
-			skb->csum = csum_block_add(skb->csum,
-						   (__force __wsum)mlx5e_get_fcs(skb),
-						   skb->len - ETH_FCS_LEN);
+
+		mlx5e_skb_padding_csum(skb, network_depth, proto, stats);
 		stats->csum_complete++;
 		return;
 	}
 
 csum_unnecessary:
 	if (likely((cqe->hds_ip_ext & CQE_L3_OK) &&
-		   ((cqe->hds_ip_ext & CQE_L4_OK) ||
-		    (get_cqe_l4_hdr_type(cqe) == CQE_L4_HDR_TYPE_NONE)))) {
+		   (cqe->hds_ip_ext & CQE_L4_OK))) {
 		skb->ip_summed = CHECKSUM_UNNECESSARY;
 		if (cqe_is_tunneled(cqe)) {
 			skb->csum_level = 1;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_stats.c b/drivers/net/ethernet/mellanox/mlx5/core/en_stats.c
index 1a78e05cbba8..b75aa8b8bf04 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_stats.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_stats.c
@@ -59,6 +59,8 @@ static const struct counter_desc sw_stats_desc[] = {
 	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_csum_unnecessary) },
 	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_csum_none) },
 	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_csum_complete) },
+	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_csum_complete_tail) },
+	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_csum_complete_tail_slow) },
 	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_csum_unnecessary_inner) },
 	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_xdp_drop) },
 	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_xdp_redirect) },
@@ -151,6 +153,8 @@ static void mlx5e_grp_sw_update_stats(struct mlx5e_priv *priv)
 		s->rx_removed_vlan_packets += rq_stats->removed_vlan_packets;
 		s->rx_csum_none	+= rq_stats->csum_none;
 		s->rx_csum_complete += rq_stats->csum_complete;
+		s->rx_csum_complete_tail += rq_stats->csum_complete_tail;
+		s->rx_csum_complete_tail_slow += rq_stats->csum_complete_tail_slow;
 		s->rx_csum_unnecessary += rq_stats->csum_unnecessary;
 		s->rx_csum_unnecessary_inner += rq_stats->csum_unnecessary_inner;
 		s->rx_xdp_drop     += rq_stats->xdp_drop;
@@ -1190,6 +1194,8 @@ static const struct counter_desc rq_stats_desc[] = {
 	{ MLX5E_DECLARE_RX_STAT(struct mlx5e_rq_stats, packets) },
 	{ MLX5E_DECLARE_RX_STAT(struct mlx5e_rq_stats, bytes) },
 	{ MLX5E_DECLARE_RX_STAT(struct mlx5e_rq_stats, csum_complete) },
+	{ MLX5E_DECLARE_RX_STAT(struct mlx5e_rq_stats, csum_complete_tail) },
+	{ MLX5E_DECLARE_RX_STAT(struct mlx5e_rq_stats, csum_complete_tail_slow) },
 	{ MLX5E_DECLARE_RX_STAT(struct mlx5e_rq_stats, csum_unnecessary) },
 	{ MLX5E_DECLARE_RX_STAT(struct mlx5e_rq_stats, csum_unnecessary_inner) },
 	{ MLX5E_DECLARE_RX_STAT(struct mlx5e_rq_stats, csum_none) },
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_stats.h b/drivers/net/ethernet/mellanox/mlx5/core/en_stats.h
index 4640d4f986f8..16c3b785f282 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_stats.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_stats.h
@@ -71,6 +71,8 @@ struct mlx5e_sw_stats {
 	u64 rx_csum_unnecessary;
 	u64 rx_csum_none;
 	u64 rx_csum_complete;
+	u64 rx_csum_complete_tail;
+	u64 rx_csum_complete_tail_slow;
 	u64 rx_csum_unnecessary_inner;
 	u64 rx_xdp_drop;
 	u64 rx_xdp_redirect;
@@ -181,6 +183,8 @@ struct mlx5e_rq_stats {
 	u64 packets;
 	u64 bytes;
 	u64 csum_complete;
+	u64 csum_complete_tail;
+	u64 csum_complete_tail_slow;
 	u64 csum_unnecessary;
 	u64 csum_unnecessary_inner;
 	u64 csum_none;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
index b4967a0ff8c7..d75dc44eb2ff 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
@@ -2158,6 +2158,52 @@ static bool csum_offload_supported(struct mlx5e_priv *priv,
 	return true;
 }
 
+struct ip_ttl_word {
+	__u8	ttl;
+	__u8	protocol;
+	__sum16	check;
+};
+
+struct ipv6_hoplimit_word {
+	__be16	payload_len;
+	__u8	nexthdr;
+	__u8	hop_limit;
+};
+
+static bool is_action_keys_supported(const struct flow_action_entry *act)
+{
+	u32 mask, offset;
+	u8 htype;
+
+	htype = act->mangle.htype;
+	offset = act->mangle.offset;
+	mask = ~act->mangle.mask;
+	/* For IPv4 & IPv6 header check 4 byte word,
+	 * to determine that modified fields
+	 * are NOT ttl & hop_limit only.
+	 */
+	if (htype == FLOW_ACT_MANGLE_HDR_TYPE_IP4) {
+		struct ip_ttl_word *ttl_word =
+			(struct ip_ttl_word *)&mask;
+
+		if (offset != offsetof(struct iphdr, ttl) ||
+		    ttl_word->protocol ||
+		    ttl_word->check) {
+			return true;
+		}
+	} else if (htype == FLOW_ACT_MANGLE_HDR_TYPE_IP6) {
+		struct ipv6_hoplimit_word *hoplimit_word =
+			(struct ipv6_hoplimit_word *)&mask;
+
+		if (offset != offsetof(struct ipv6hdr, payload_len) ||
+		    hoplimit_word->payload_len ||
+		    hoplimit_word->nexthdr) {
+			return true;
+		}
+	}
+	return false;
+}
+
 static bool modify_header_match_supported(struct mlx5_flow_spec *spec,
 					  struct flow_action *flow_action,
 					  u32 actions,
@@ -2165,9 +2211,9 @@ static bool modify_header_match_supported(struct mlx5_flow_spec *spec,
 {
 	const struct flow_action_entry *act;
 	bool modify_ip_header;
-	u8 htype, ip_proto;
 	void *headers_v;
 	u16 ethertype;
+	u8 ip_proto;
 	int i;
 
 	if (actions & MLX5_FLOW_CONTEXT_ACTION_DECAP)
@@ -2187,9 +2233,7 @@ static bool modify_header_match_supported(struct mlx5_flow_spec *spec,
 		    act->id != FLOW_ACTION_ADD)
 			continue;
 
-		htype = act->mangle.htype;
-		if (htype == FLOW_ACT_MANGLE_HDR_TYPE_IP4 ||
-		    htype == FLOW_ACT_MANGLE_HDR_TYPE_IP6) {
+		if (is_action_keys_supported(act)) {
 			modify_ip_header = true;
 			break;
 		}
@@ -2340,15 +2384,22 @@ static int parse_tc_nic_actions(struct mlx5e_priv *priv,
 	return 0;
 }
 
-static inline int cmp_encap_info(struct ip_tunnel_key *a,
-				 struct ip_tunnel_key *b)
+struct encap_key {
+	struct ip_tunnel_key *ip_tun_key;
+	int tunnel_type;
+};
+
+static inline int cmp_encap_info(struct encap_key *a,
+				 struct encap_key *b)
 {
-	return memcmp(a, b, sizeof(*a));
+	return memcmp(a->ip_tun_key, b->ip_tun_key, sizeof(*a->ip_tun_key)) ||
+	       a->tunnel_type != b->tunnel_type;
 }
 
-static inline int hash_encap_info(struct ip_tunnel_key *key)
+static inline int hash_encap_info(struct encap_key *key)
 {
-	return jhash(key, sizeof(*key), 0);
+	return jhash(key->ip_tun_key, sizeof(*key->ip_tun_key),
+		     key->tunnel_type);
 }
 
 
@@ -2379,7 +2430,7 @@ static int mlx5e_attach_encap(struct mlx5e_priv *priv,
 	struct mlx5_esw_flow_attr *attr = flow->esw_attr;
 	struct mlx5e_tc_flow_parse_attr *parse_attr;
 	struct ip_tunnel_info *tun_info;
-	struct ip_tunnel_key *key;
+	struct encap_key key, e_key;
 	struct mlx5e_encap_entry *e;
 	unsigned short family;
 	uintptr_t hash_key;
@@ -2389,13 +2440,16 @@ static int mlx5e_attach_encap(struct mlx5e_priv *priv,
 	parse_attr = attr->parse_attr;
 	tun_info = &parse_attr->tun_info[out_index];
 	family = ip_tunnel_info_af(tun_info);
-	key = &tun_info->key;
+	key.ip_tun_key = &tun_info->key;
+	key.tunnel_type = mlx5e_tc_tun_get_type(mirred_dev);
 
-	hash_key = hash_encap_info(key);
+	hash_key = hash_encap_info(&key);
 
 	hash_for_each_possible_rcu(esw->offloads.encap_tbl, e,
 				   encap_hlist, hash_key) {
-		if (!cmp_encap_info(&e->tun_info.key, key)) {
+		e_key.ip_tun_key = &e->tun_info.key;
+		e_key.tunnel_type = e->tunnel_type;
+		if (!cmp_encap_info(&e_key, &key)) {
 			found = true;
 			break;
 		}
@@ -2657,7 +2711,7 @@ static int parse_tc_fdb_actions(struct mlx5e_priv *priv,
 
 	if (hdrs[TCA_PEDIT_KEY_EX_CMD_SET].pedits ||
 	    hdrs[TCA_PEDIT_KEY_EX_CMD_ADD].pedits) {
-		err = alloc_tc_pedit_action(priv, MLX5_FLOW_NAMESPACE_KERNEL,
+		err = alloc_tc_pedit_action(priv, MLX5_FLOW_NAMESPACE_FDB,
 					    parse_attr, hdrs, extack);
 		if (err)
 			return err;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c
index ecd2c747f726..8a67fd197b79 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c
@@ -105,8 +105,7 @@ static int arm_vport_context_events_cmd(struct mlx5_core_dev *dev, u16 vport,
 		 opcode, MLX5_CMD_OP_MODIFY_NIC_VPORT_CONTEXT);
 	MLX5_SET(modify_nic_vport_context_in, in, field_select.change_event, 1);
 	MLX5_SET(modify_nic_vport_context_in, in, vport_number, vport);
-	if (vport)
-		MLX5_SET(modify_nic_vport_context_in, in, other_vport, 1);
+	MLX5_SET(modify_nic_vport_context_in, in, other_vport, 1);
 	nic_vport_ctx = MLX5_ADDR_OF(modify_nic_vport_context_in,
 				     in, nic_vport_context);
 
@@ -134,8 +133,7 @@ static int modify_esw_vport_context_cmd(struct mlx5_core_dev *dev, u16 vport,
 	MLX5_SET(modify_esw_vport_context_in, in, opcode,
 		 MLX5_CMD_OP_MODIFY_ESW_VPORT_CONTEXT);
 	MLX5_SET(modify_esw_vport_context_in, in, vport_number, vport);
-	if (vport)
-		MLX5_SET(modify_esw_vport_context_in, in, other_vport, 1);
+	MLX5_SET(modify_esw_vport_context_in, in, other_vport, 1);
 	return mlx5_cmd_exec(dev, in, inlen, out, sizeof(out));
 }
 
@@ -431,6 +429,8 @@ static int esw_create_legacy_table(struct mlx5_eswitch *esw)
 {
 	int err;
 
+	memset(&esw->fdb_table.legacy, 0, sizeof(struct legacy_fdb));
+
 	err = esw_create_legacy_vepa_table(esw);
 	if (err)
 		return err;
@@ -2157,6 +2157,7 @@ static int _mlx5_eswitch_set_vepa_locked(struct mlx5_eswitch *esw,
 
 	/* Star rule to forward all traffic to uplink vport */
 	memset(spec, 0, sizeof(*spec));
+	memset(&dest, 0, sizeof(dest));
 	dest.type = MLX5_FLOW_DESTINATION_TYPE_VPORT;
 	dest.vport.num = MLX5_VPORT_UPLINK;
 	flow_act.action = MLX5_FLOW_CONTEXT_ACTION_FWD_DEST;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c
index f2260391be5b..9b2d78ee22b8 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c
@@ -1611,6 +1611,7 @@ static int esw_offloads_steering_init(struct mlx5_eswitch *esw, int nvports)
 {
 	int err;
 
+	memset(&esw->fdb_table.offloads, 0, sizeof(struct offloads_fdb));
 	mutex_init(&esw->fdb_table.offloads.fdb_prio_lock);
 
 	err = esw_create_offloads_fdb_tables(esw, nvports);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fpga/tls.c b/drivers/net/ethernet/mellanox/mlx5/core/fpga/tls.c
index 5cf5f2a9d51f..22a2ef111514 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/fpga/tls.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/fpga/tls.c
@@ -148,14 +148,16 @@ static int mlx5_fpga_tls_alloc_swid(struct idr *idr, spinlock_t *idr_spinlock,
 	return ret;
 }
 
-static void mlx5_fpga_tls_release_swid(struct idr *idr,
-				       spinlock_t *idr_spinlock, u32 swid)
+static void *mlx5_fpga_tls_release_swid(struct idr *idr,
+					spinlock_t *idr_spinlock, u32 swid)
 {
 	unsigned long flags;
+	void *ptr;
 
 	spin_lock_irqsave(idr_spinlock, flags);
-	idr_remove(idr, swid);
+	ptr = idr_remove(idr, swid);
 	spin_unlock_irqrestore(idr_spinlock, flags);
+	return ptr;
 }
 
 static void mlx_tls_kfree_complete(struct mlx5_fpga_conn *conn,
@@ -165,20 +167,12 @@ static void mlx_tls_kfree_complete(struct mlx5_fpga_conn *conn,
 	kfree(buf);
 }
 
-struct mlx5_teardown_stream_context {
-	struct mlx5_fpga_tls_command_context cmd;
-	u32 swid;
-};
-
 static void
 mlx5_fpga_tls_teardown_completion(struct mlx5_fpga_conn *conn,
 				  struct mlx5_fpga_device *fdev,
 				  struct mlx5_fpga_tls_command_context *cmd,
 				  struct mlx5_fpga_dma_buf *resp)
 {
-	struct mlx5_teardown_stream_context *ctx =
-		    container_of(cmd, struct mlx5_teardown_stream_context, cmd);
-
 	if (resp) {
 		u32 syndrome = MLX5_GET(tls_resp, resp->sg[0].data, syndrome);
 
@@ -186,14 +180,6 @@ mlx5_fpga_tls_teardown_completion(struct mlx5_fpga_conn *conn,
 			mlx5_fpga_err(fdev,
 				      "Teardown stream failed with syndrome = %d",
 				      syndrome);
-		else if (MLX5_GET(tls_cmd, cmd->buf.sg[0].data, direction_sx))
-			mlx5_fpga_tls_release_swid(&fdev->tls->tx_idr,
-						   &fdev->tls->tx_idr_spinlock,
-						   ctx->swid);
-		else
-			mlx5_fpga_tls_release_swid(&fdev->tls->rx_idr,
-						   &fdev->tls->rx_idr_spinlock,
-						   ctx->swid);
 	}
 	mlx5_fpga_tls_put_command_ctx(cmd);
 }
@@ -225,8 +211,14 @@ int mlx5_fpga_tls_resync_rx(struct mlx5_core_dev *mdev, u32 handle, u32 seq,
 
 	rcu_read_lock();
 	flow = idr_find(&mdev->fpga->tls->rx_idr, ntohl(handle));
-	rcu_read_unlock();
+	if (unlikely(!flow)) {
+		rcu_read_unlock();
+		WARN_ONCE(1, "Received NULL pointer for handle\n");
+		kfree(buf);
+		return -EINVAL;
+	}
 	mlx5_fpga_tls_flow_to_cmd(flow, cmd);
+	rcu_read_unlock();
 
 	MLX5_SET(tls_cmd, cmd, swid, ntohl(handle));
 	MLX5_SET64(tls_cmd, cmd, tls_rcd_sn, be64_to_cpu(rcd_sn));
@@ -238,6 +230,8 @@ int mlx5_fpga_tls_resync_rx(struct mlx5_core_dev *mdev, u32 handle, u32 seq,
 	buf->complete = mlx_tls_kfree_complete;
 
 	ret = mlx5_fpga_sbu_conn_sendmsg(mdev->fpga->tls->conn, buf);
+	if (ret < 0)
+		kfree(buf);
 
 	return ret;
 }
@@ -245,7 +239,7 @@ int mlx5_fpga_tls_resync_rx(struct mlx5_core_dev *mdev, u32 handle, u32 seq,
 static void mlx5_fpga_tls_send_teardown_cmd(struct mlx5_core_dev *mdev,
 					    void *flow, u32 swid, gfp_t flags)
 {
-	struct mlx5_teardown_stream_context *ctx;
+	struct mlx5_fpga_tls_command_context *ctx;
 	struct mlx5_fpga_dma_buf *buf;
 	void *cmd;
 
@@ -253,7 +247,7 @@ static void mlx5_fpga_tls_send_teardown_cmd(struct mlx5_core_dev *mdev,
 	if (!ctx)
 		return;
 
-	buf = &ctx->cmd.buf;
+	buf = &ctx->buf;
 	cmd = (ctx + 1);
 	MLX5_SET(tls_cmd, cmd, command_type, CMD_TEARDOWN_STREAM);
 	MLX5_SET(tls_cmd, cmd, swid, swid);
@@ -264,8 +258,7 @@ static void mlx5_fpga_tls_send_teardown_cmd(struct mlx5_core_dev *mdev,
 	buf->sg[0].data = cmd;
 	buf->sg[0].size = MLX5_TLS_COMMAND_SIZE;
 
-	ctx->swid = swid;
-	mlx5_fpga_tls_cmd_send(mdev->fpga, &ctx->cmd,
+	mlx5_fpga_tls_cmd_send(mdev->fpga, ctx,
 			       mlx5_fpga_tls_teardown_completion);
 }
 
@@ -275,13 +268,14 @@ void mlx5_fpga_tls_del_flow(struct mlx5_core_dev *mdev, u32 swid,
 	struct mlx5_fpga_tls *tls = mdev->fpga->tls;
 	void *flow;
 
-	rcu_read_lock();
 	if (direction_sx)
-		flow = idr_find(&tls->tx_idr, swid);
+		flow = mlx5_fpga_tls_release_swid(&tls->tx_idr,
+						  &tls->tx_idr_spinlock,
+						  swid);
 	else
-		flow = idr_find(&tls->rx_idr, swid);
-
-	rcu_read_unlock();
+		flow = mlx5_fpga_tls_release_swid(&tls->rx_idr,
+						  &tls->rx_idr_spinlock,
+						  swid);
 
 	if (!flow) {
 		mlx5_fpga_err(mdev->fpga, "No flow information for swid %u\n",
@@ -289,6 +283,7 @@ void mlx5_fpga_tls_del_flow(struct mlx5_core_dev *mdev, u32 swid,
 		return;
 	}
 
+	synchronize_rcu(); /* before kfree(flow) */
 	mlx5_fpga_tls_send_teardown_cmd(mdev, flow, swid, flags);
 }
 
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/main.c b/drivers/net/ethernet/mellanox/mlx5/core/main.c
index 70cc906a102b..76716419370d 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/main.c
@@ -164,26 +164,6 @@ static struct mlx5_profile profile[] = {
 			.size	= 8,
 			.limit	= 4
 		},
-		.mr_cache[16]	= {
-			.size	= 8,
-			.limit	= 4
-		},
-		.mr_cache[17]	= {
-			.size	= 8,
-			.limit	= 4
-		},
-		.mr_cache[18]	= {
-			.size	= 8,
-			.limit	= 4
-		},
-		.mr_cache[19]	= {
-			.size	= 4,
-			.limit	= 2
-		},
-		.mr_cache[20]	= {
-			.size	= 4,
-			.limit	= 2
-		},
 	},
 };
 
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/port.c b/drivers/net/ethernet/mellanox/mlx5/core/port.c
index 21b7f05b16a5..361468e0435d 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/port.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/port.c
@@ -317,10 +317,6 @@ int mlx5_query_module_eeprom(struct mlx5_core_dev *dev,
 		size -= offset + size - MLX5_EEPROM_PAGE_LENGTH;
 
 	i2c_addr = MLX5_I2C_ADDR_LOW;
-	if (offset >= MLX5_EEPROM_PAGE_LENGTH) {
-		i2c_addr = MLX5_I2C_ADDR_HIGH;
-		offset -= MLX5_EEPROM_PAGE_LENGTH;
-	}
 
 	MLX5_SET(mcia_reg, in, l, 0);
 	MLX5_SET(mcia_reg, in, module, module_num);
diff --git a/drivers/net/ethernet/mellanox/mlxsw/core.c b/drivers/net/ethernet/mellanox/mlxsw/core.c
index d23d53c0e284..f26a4ca29363 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/core.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/core.c
@@ -568,7 +568,7 @@ static int mlxsw_emad_init(struct mlxsw_core *mlxsw_core)
 	if (!(mlxsw_core->bus->features & MLXSW_BUS_F_TXRX))
 		return 0;
 
-	emad_wq = alloc_workqueue("mlxsw_core_emad", WQ_MEM_RECLAIM, 0);
+	emad_wq = alloc_workqueue("mlxsw_core_emad", 0, 0);
 	if (!emad_wq)
 		return -ENOMEM;
 	mlxsw_core->emad_wq = emad_wq;
@@ -1958,10 +1958,10 @@ static int __init mlxsw_core_module_init(void)
 {
 	int err;
 
-	mlxsw_wq = alloc_workqueue(mlxsw_core_driver_name, WQ_MEM_RECLAIM, 0);
+	mlxsw_wq = alloc_workqueue(mlxsw_core_driver_name, 0, 0);
 	if (!mlxsw_wq)
 		return -ENOMEM;
-	mlxsw_owq = alloc_ordered_workqueue("%s_ordered", WQ_MEM_RECLAIM,
+	mlxsw_owq = alloc_ordered_workqueue("%s_ordered", 0,
 					    mlxsw_core_driver_name);
 	if (!mlxsw_owq) {
 		err = -ENOMEM;
diff --git a/drivers/net/ethernet/mellanox/mlxsw/core_env.c b/drivers/net/ethernet/mellanox/mlxsw/core_env.c
index 7a15e932ed2f..c1c1965d7acc 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/core_env.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/core_env.c
@@ -113,7 +113,7 @@ int mlxsw_env_module_temp_thresholds_get(struct mlxsw_core *core, int module,
 		return 0;
 	default:
 		/* Do not consider thresholds for zero temperature. */
-		if (!MLXSW_REG_MTMP_TEMP_TO_MC(module_temp)) {
+		if (MLXSW_REG_MTMP_TEMP_TO_MC(module_temp) == 0) {
 			*temp = 0;
 			return 0;
 		}
diff --git a/drivers/net/ethernet/mellanox/mlxsw/pci_hw.h b/drivers/net/ethernet/mellanox/mlxsw/pci_hw.h
index ffee38e36ce8..8648ca171254 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/pci_hw.h
+++ b/drivers/net/ethernet/mellanox/mlxsw/pci_hw.h
@@ -27,7 +27,7 @@
 
 #define MLXSW_PCI_SW_RESET			0xF0010
 #define MLXSW_PCI_SW_RESET_RST_BIT		BIT(0)
-#define MLXSW_PCI_SW_RESET_TIMEOUT_MSECS	13000
+#define MLXSW_PCI_SW_RESET_TIMEOUT_MSECS	20000
 #define MLXSW_PCI_SW_RESET_WAIT_MSECS		100
 #define MLXSW_PCI_FW_READY			0xA1844
 #define MLXSW_PCI_FW_READY_MASK			0xFFFF
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c
index 9eb63300c1d3..6b8aa3761899 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c
@@ -3126,11 +3126,11 @@ mlxsw_sp_port_set_link_ksettings(struct net_device *dev,
 	if (err)
 		return err;
 
+	mlxsw_sp_port->link.autoneg = autoneg;
+
 	if (!netif_running(dev))
 		return 0;
 
-	mlxsw_sp_port->link.autoneg = autoneg;
-
 	mlxsw_sp_port_admin_status_set(mlxsw_sp_port, false);
 	mlxsw_sp_port_admin_status_set(mlxsw_sp_port, true);
 
@@ -3316,7 +3316,7 @@ static int mlxsw_sp_port_ets_init(struct mlxsw_sp_port *mlxsw_sp_port)
 		err = mlxsw_sp_port_ets_set(mlxsw_sp_port,
 					    MLXSW_REG_QEEC_HIERARCY_TC,
 					    i + 8, i,
-					    false, 0);
+					    true, 100);
 		if (err)
 			return err;
 	}
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_buffers.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_buffers.c
index 9a79b5e11597..d633bef5f105 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_buffers.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_buffers.c
@@ -70,6 +70,7 @@ static const struct mlxsw_sp_sb_pool_des mlxsw_sp2_sb_pool_dess[] = {
 	{MLXSW_REG_SBXX_DIR_EGRESS, 1},
 	{MLXSW_REG_SBXX_DIR_EGRESS, 2},
 	{MLXSW_REG_SBXX_DIR_EGRESS, 3},
+	{MLXSW_REG_SBXX_DIR_EGRESS, 15},
 };
 
 #define MLXSW_SP_SB_ING_TC_COUNT 8
@@ -428,6 +429,7 @@ static const struct mlxsw_sp_sb_pr mlxsw_sp2_sb_prs[] = {
 	MLXSW_SP_SB_PR(MLXSW_REG_SBPR_MODE_STATIC, 0),
 	MLXSW_SP_SB_PR(MLXSW_REG_SBPR_MODE_STATIC, 0),
 	MLXSW_SP_SB_PR(MLXSW_REG_SBPR_MODE_STATIC, 0),
+	MLXSW_SP_SB_PR(MLXSW_REG_SBPR_MODE_STATIC, MLXSW_SP_SB_INFI),
 };
 
 static int mlxsw_sp_sb_prs_init(struct mlxsw_sp *mlxsw_sp,
@@ -517,14 +519,14 @@ static const struct mlxsw_sp_sb_cm mlxsw_sp2_sb_cms_egress[] = {
 	MLXSW_SP_SB_CM(0, 7, 4),
 	MLXSW_SP_SB_CM(0, 7, 4),
 	MLXSW_SP_SB_CM(0, 7, 4),
-	MLXSW_SP_SB_CM(0, 7, 4),
-	MLXSW_SP_SB_CM(0, 7, 4),
-	MLXSW_SP_SB_CM(0, 7, 4),
-	MLXSW_SP_SB_CM(0, 7, 4),
-	MLXSW_SP_SB_CM(0, 7, 4),
-	MLXSW_SP_SB_CM(0, 7, 4),
-	MLXSW_SP_SB_CM(0, 7, 4),
-	MLXSW_SP_SB_CM(0, 7, 4),
+	MLXSW_SP_SB_CM(0, MLXSW_SP_SB_INFI, 8),
+	MLXSW_SP_SB_CM(0, MLXSW_SP_SB_INFI, 8),
+	MLXSW_SP_SB_CM(0, MLXSW_SP_SB_INFI, 8),
+	MLXSW_SP_SB_CM(0, MLXSW_SP_SB_INFI, 8),
+	MLXSW_SP_SB_CM(0, MLXSW_SP_SB_INFI, 8),
+	MLXSW_SP_SB_CM(0, MLXSW_SP_SB_INFI, 8),
+	MLXSW_SP_SB_CM(0, MLXSW_SP_SB_INFI, 8),
+	MLXSW_SP_SB_CM(0, MLXSW_SP_SB_INFI, 8),
 	MLXSW_SP_SB_CM(1, 0xff, 4),
 };
 
@@ -671,6 +673,7 @@ static const struct mlxsw_sp_sb_pm mlxsw_sp2_sb_pms[] = {
 	MLXSW_SP_SB_PM(0, 0),
 	MLXSW_SP_SB_PM(0, 0),
 	MLXSW_SP_SB_PM(0, 0),
+	MLXSW_SP_SB_PM(10000, 90000),
 };
 
 static int mlxsw_sp_port_sb_pms_init(struct mlxsw_sp_port *mlxsw_sp_port)
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c
index 52fed8c7bf1e..902e766a8ed3 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c
@@ -6781,7 +6781,7 @@ static int mlxsw_sp_router_port_check_rif_addr(struct mlxsw_sp *mlxsw_sp,
 	/* A RIF is not created for macvlan netdevs. Their MAC is used to
 	 * populate the FDB
 	 */
-	if (netif_is_macvlan(dev))
+	if (netif_is_macvlan(dev) || netif_is_l3_master(dev))
 		return 0;
 
 	for (i = 0; i < MLXSW_CORE_RES_GET(mlxsw_sp->core, MAX_RIFS); i++) {
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.c
index f6ce386c3036..50111f228d77 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.c
@@ -1630,7 +1630,7 @@ static int mlxsw_sp_port_mdb_add(struct mlxsw_sp_port *mlxsw_sp_port,
 	u16 fid_index;
 	int err = 0;
 
-	if (switchdev_trans_ph_prepare(trans))
+	if (switchdev_trans_ph_commit(trans))
 		return 0;
 
 	bridge_port = mlxsw_sp_bridge_port_find(mlxsw_sp->bridge, orig_dev);
diff --git a/drivers/net/ethernet/micrel/ks8851.c b/drivers/net/ethernet/micrel/ks8851.c
index bd6e9014bc74..7849119d407a 100644
--- a/drivers/net/ethernet/micrel/ks8851.c
+++ b/drivers/net/ethernet/micrel/ks8851.c
@@ -142,6 +142,12 @@ struct ks8851_net {
 
 static int msg_enable;
 
+/* SPI frame opcodes */
+#define KS_SPIOP_RD	(0x00)
+#define KS_SPIOP_WR	(0x40)
+#define KS_SPIOP_RXFIFO	(0x80)
+#define KS_SPIOP_TXFIFO	(0xC0)
+
 /* shift for byte-enable data */
 #define BYTE_EN(_x)	((_x) << 2)
 
@@ -535,9 +541,8 @@ static void ks8851_rx_pkts(struct ks8851_net *ks)
 		/* set dma read address */
 		ks8851_wrreg16(ks, KS_RXFDPR, RXFDPR_RXFPAI | 0x00);
 
-		/* start the packet dma process, and set auto-dequeue rx */
-		ks8851_wrreg16(ks, KS_RXQCR,
-			       ks->rc_rxqcr | RXQCR_SDA | RXQCR_ADRFE);
+		/* start DMA access */
+		ks8851_wrreg16(ks, KS_RXQCR, ks->rc_rxqcr | RXQCR_SDA);
 
 		if (rxlen > 4) {
 			unsigned int rxalign;
@@ -568,7 +573,8 @@ static void ks8851_rx_pkts(struct ks8851_net *ks)
 			}
 		}
 
-		ks8851_wrreg16(ks, KS_RXQCR, ks->rc_rxqcr);
+		/* end DMA access and dequeue packet */
+		ks8851_wrreg16(ks, KS_RXQCR, ks->rc_rxqcr | RXQCR_RRXEF);
 	}
 }
 
@@ -785,6 +791,15 @@ static void ks8851_tx_work(struct work_struct *work)
 static int ks8851_net_open(struct net_device *dev)
 {
 	struct ks8851_net *ks = netdev_priv(dev);
+	int ret;
+
+	ret = request_threaded_irq(dev->irq, NULL, ks8851_irq,
+				   IRQF_TRIGGER_LOW | IRQF_ONESHOT,
+				   dev->name, ks);
+	if (ret < 0) {
+		netdev_err(dev, "failed to get irq\n");
+		return ret;
+	}
 
 	/* lock the card, even if we may not actually be doing anything
 	 * else at the moment */
@@ -849,6 +864,7 @@ static int ks8851_net_open(struct net_device *dev)
 	netif_dbg(ks, ifup, ks->netdev, "network device up\n");
 
 	mutex_unlock(&ks->lock);
+	mii_check_link(&ks->mii);
 	return 0;
 }
 
@@ -899,6 +915,8 @@ static int ks8851_net_stop(struct net_device *dev)
 		dev_kfree_skb(txb);
 	}
 
+	free_irq(dev->irq, ks);
+
 	return 0;
 }
 
@@ -1508,6 +1526,7 @@ static int ks8851_probe(struct spi_device *spi)
 
 	spi_set_drvdata(spi, ks);
 
+	netif_carrier_off(ks->netdev);
 	ndev->if_port = IF_PORT_100BASET;
 	ndev->netdev_ops = &ks8851_netdev_ops;
 	ndev->irq = spi->irq;
@@ -1529,14 +1548,6 @@ static int ks8851_probe(struct spi_device *spi)
 	ks8851_read_selftest(ks);
 	ks8851_init_mac(ks);
 
-	ret = request_threaded_irq(spi->irq, NULL, ks8851_irq,
-				   IRQF_TRIGGER_LOW | IRQF_ONESHOT,
-				   ndev->name, ks);
-	if (ret < 0) {
-		dev_err(&spi->dev, "failed to get irq\n");
-		goto err_irq;
-	}
-
 	ret = register_netdev(ndev);
 	if (ret) {
 		dev_err(&spi->dev, "failed to register network device\n");
@@ -1549,14 +1560,10 @@ static int ks8851_probe(struct spi_device *spi)
 
 	return 0;
 
-
 err_netdev:
-	free_irq(ndev->irq, ks);
-
-err_irq:
+err_id:
 	if (gpio_is_valid(gpio))
 		gpio_set_value(gpio, 0);
-err_id:
 	regulator_disable(ks->vdd_reg);
 err_reg:
 	regulator_disable(ks->vdd_io);
@@ -1574,7 +1581,6 @@ static int ks8851_remove(struct spi_device *spi)
 		dev_info(&spi->dev, "remove\n");
 
 	unregister_netdev(priv->netdev);
-	free_irq(spi->irq, priv);
 	if (gpio_is_valid(priv->gpio))
 		gpio_set_value(priv->gpio, 0);
 	regulator_disable(priv->vdd_reg);
diff --git a/drivers/net/ethernet/micrel/ks8851.h b/drivers/net/ethernet/micrel/ks8851.h
index 852256ef1f22..23da1e3ee429 100644
--- a/drivers/net/ethernet/micrel/ks8851.h
+++ b/drivers/net/ethernet/micrel/ks8851.h
@@ -11,9 +11,15 @@
 */
 
 #define KS_CCR					0x08
+#define CCR_LE					(1 << 10)   /* KSZ8851-16MLL */
 #define CCR_EEPROM				(1 << 9)
-#define CCR_SPI					(1 << 8)
-#define CCR_32PIN				(1 << 0)
+#define CCR_SPI					(1 << 8)    /* KSZ8851SNL    */
+#define CCR_8BIT				(1 << 7)    /* KSZ8851-16MLL */
+#define CCR_16BIT				(1 << 6)    /* KSZ8851-16MLL */
+#define CCR_32BIT				(1 << 5)    /* KSZ8851-16MLL */
+#define CCR_SHARED				(1 << 4)    /* KSZ8851-16MLL */
+#define CCR_48PIN				(1 << 1)    /* KSZ8851-16MLL */
+#define CCR_32PIN				(1 << 0)    /* KSZ8851SNL    */
 
 /* MAC address registers */
 #define KS_MAR(_m)				(0x15 - (_m))
@@ -112,13 +118,13 @@
 #define RXCR1_RXE				(1 << 0)
 
 #define KS_RXCR2				0x76
-#define RXCR2_SRDBL_MASK			(0x7 << 5)
-#define RXCR2_SRDBL_SHIFT			(5)
-#define RXCR2_SRDBL_4B				(0x0 << 5)
-#define RXCR2_SRDBL_8B				(0x1 << 5)
-#define RXCR2_SRDBL_16B				(0x2 << 5)
-#define RXCR2_SRDBL_32B				(0x3 << 5)
-#define RXCR2_SRDBL_FRAME			(0x4 << 5)
+#define RXCR2_SRDBL_MASK			(0x7 << 5)  /* KSZ8851SNL    */
+#define RXCR2_SRDBL_SHIFT			(5)	    /* KSZ8851SNL    */
+#define RXCR2_SRDBL_4B				(0x0 << 5)  /* KSZ8851SNL    */
+#define RXCR2_SRDBL_8B				(0x1 << 5)  /* KSZ8851SNL    */
+#define RXCR2_SRDBL_16B				(0x2 << 5)  /* KSZ8851SNL    */
+#define RXCR2_SRDBL_32B				(0x3 << 5)  /* KSZ8851SNL    */
+#define RXCR2_SRDBL_FRAME			(0x4 << 5)  /* KSZ8851SNL    */
 #define RXCR2_IUFFP				(1 << 4)
 #define RXCR2_RXIUFCEZ				(1 << 3)
 #define RXCR2_UDPLFE				(1 << 2)
@@ -143,8 +149,10 @@
 #define RXFSHR_RXCE				(1 << 0)
 
 #define KS_RXFHBCR				0x7E
+#define RXFHBCR_CNT_MASK			(0xfff << 0)
+
 #define KS_TXQCR				0x80
-#define TXQCR_AETFE				(1 << 2)
+#define TXQCR_AETFE				(1 << 2)    /* KSZ8851SNL    */
 #define TXQCR_TXQMAM				(1 << 1)
 #define TXQCR_METFE				(1 << 0)
 
@@ -167,6 +175,10 @@
 
 #define KS_RXFDPR				0x86
 #define RXFDPR_RXFPAI				(1 << 14)
+#define RXFDPR_WST				(1 << 12)   /* KSZ8851-16MLL */
+#define RXFDPR_EMS				(1 << 11)   /* KSZ8851-16MLL */
+#define RXFDPR_RXFP_MASK			(0x7ff << 0)
+#define RXFDPR_RXFP_SHIFT			(0)
 
 #define KS_RXDTTR				0x8C
 #define KS_RXDBCTR				0x8E
@@ -184,7 +196,7 @@
 #define IRQ_RXMPDI				(1 << 4)
 #define IRQ_LDI					(1 << 3)
 #define IRQ_EDI					(1 << 2)
-#define IRQ_SPIBEI				(1 << 1)
+#define IRQ_SPIBEI				(1 << 1)    /* KSZ8851SNL    */
 #define IRQ_DEDI				(1 << 0)
 
 #define KS_RXFCTR				0x9C
@@ -257,42 +269,37 @@
 #define KS_P1ANLPR				0xEE
 
 #define KS_P1SCLMD				0xF4
-#define P1SCLMD_LEDOFF				(1 << 15)
-#define P1SCLMD_TXIDS				(1 << 14)
-#define P1SCLMD_RESTARTAN			(1 << 13)
-#define P1SCLMD_DISAUTOMDIX			(1 << 10)
-#define P1SCLMD_FORCEMDIX			(1 << 9)
-#define P1SCLMD_AUTONEGEN			(1 << 7)
-#define P1SCLMD_FORCE100			(1 << 6)
-#define P1SCLMD_FORCEFDX			(1 << 5)
-#define P1SCLMD_ADV_FLOW			(1 << 4)
-#define P1SCLMD_ADV_100BT_FDX			(1 << 3)
-#define P1SCLMD_ADV_100BT_HDX			(1 << 2)
-#define P1SCLMD_ADV_10BT_FDX			(1 << 1)
-#define P1SCLMD_ADV_10BT_HDX			(1 << 0)
 
 #define KS_P1CR					0xF6
-#define P1CR_HP_MDIX				(1 << 15)
-#define P1CR_REV_POL				(1 << 13)
-#define P1CR_OP_100M				(1 << 10)
-#define P1CR_OP_FDX				(1 << 9)
-#define P1CR_OP_MDI				(1 << 7)
-#define P1CR_AN_DONE				(1 << 6)
-#define P1CR_LINK_GOOD				(1 << 5)
-#define P1CR_PNTR_FLOW				(1 << 4)
-#define P1CR_PNTR_100BT_FDX			(1 << 3)
-#define P1CR_PNTR_100BT_HDX			(1 << 2)
-#define P1CR_PNTR_10BT_FDX			(1 << 1)
-#define P1CR_PNTR_10BT_HDX			(1 << 0)
+#define P1CR_LEDOFF				(1 << 15)
+#define P1CR_TXIDS				(1 << 14)
+#define P1CR_RESTARTAN				(1 << 13)
+#define P1CR_DISAUTOMDIX			(1 << 10)
+#define P1CR_FORCEMDIX				(1 << 9)
+#define P1CR_AUTONEGEN				(1 << 7)
+#define P1CR_FORCE100				(1 << 6)
+#define P1CR_FORCEFDX				(1 << 5)
+#define P1CR_ADV_FLOW				(1 << 4)
+#define P1CR_ADV_100BT_FDX			(1 << 3)
+#define P1CR_ADV_100BT_HDX			(1 << 2)
+#define P1CR_ADV_10BT_FDX			(1 << 1)
+#define P1CR_ADV_10BT_HDX			(1 << 0)
+
+#define KS_P1SR					0xF8
+#define P1SR_HP_MDIX				(1 << 15)
+#define P1SR_REV_POL				(1 << 13)
+#define P1SR_OP_100M				(1 << 10)
+#define P1SR_OP_FDX				(1 << 9)
+#define P1SR_OP_MDI				(1 << 7)
+#define P1SR_AN_DONE				(1 << 6)
+#define P1SR_LINK_GOOD				(1 << 5)
+#define P1SR_PNTR_FLOW				(1 << 4)
+#define P1SR_PNTR_100BT_FDX			(1 << 3)
+#define P1SR_PNTR_100BT_HDX			(1 << 2)
+#define P1SR_PNTR_10BT_FDX			(1 << 1)
+#define P1SR_PNTR_10BT_HDX			(1 << 0)
 
 /* TX Frame control */
-
 #define TXFR_TXIC				(1 << 15)
 #define TXFR_TXFID_MASK				(0x3f << 0)
 #define TXFR_TXFID_SHIFT			(0)
-
-/* SPI frame opcodes */
-#define KS_SPIOP_RD				(0x00)
-#define KS_SPIOP_WR				(0x40)
-#define KS_SPIOP_RXFIFO				(0x80)
-#define KS_SPIOP_TXFIFO				(0xC0)
diff --git a/drivers/net/ethernet/micrel/ks8851_mll.c b/drivers/net/ethernet/micrel/ks8851_mll.c
index 35f8c9ef204d..c946841c0a06 100644
--- a/drivers/net/ethernet/micrel/ks8851_mll.c
+++ b/drivers/net/ethernet/micrel/ks8851_mll.c
@@ -40,6 +40,8 @@
 #include <linux/of_device.h>
 #include <linux/of_net.h>
 
+#include "ks8851.h"
+
 #define	DRV_NAME	"ks8851_mll"
 
 static u8 KS_DEFAULT_MAC_ADDRESS[] = { 0x00, 0x10, 0xA1, 0x86, 0x95, 0x11 };
@@ -48,319 +50,10 @@ static u8 KS_DEFAULT_MAC_ADDRESS[] = { 0x00, 0x10, 0xA1, 0x86, 0x95, 0x11 };
 #define TX_BUF_SIZE			2000
 #define RX_BUF_SIZE			2000
 
-#define KS_CCR				0x08
-#define CCR_EEPROM			(1 << 9)
-#define CCR_SPI				(1 << 8)
-#define CCR_8BIT			(1 << 7)
-#define CCR_16BIT			(1 << 6)
-#define CCR_32BIT			(1 << 5)
-#define CCR_SHARED			(1 << 4)
-#define CCR_32PIN			(1 << 0)
-
-/* MAC address registers */
-#define KS_MARL				0x10
-#define KS_MARM				0x12
-#define KS_MARH				0x14
-
-#define KS_OBCR				0x20
-#define OBCR_ODS_16MA			(1 << 6)
-
-#define KS_EEPCR			0x22
-#define EEPCR_EESA			(1 << 4)
-#define EEPCR_EESB			(1 << 3)
-#define EEPCR_EEDO			(1 << 2)
-#define EEPCR_EESCK			(1 << 1)
-#define EEPCR_EECS			(1 << 0)
-
-#define KS_MBIR				0x24
-#define MBIR_TXMBF			(1 << 12)
-#define MBIR_TXMBFA			(1 << 11)
-#define MBIR_RXMBF			(1 << 4)
-#define MBIR_RXMBFA			(1 << 3)
-
-#define KS_GRR				0x26
-#define GRR_QMU				(1 << 1)
-#define GRR_GSR				(1 << 0)
-
-#define KS_WFCR				0x2A
-#define WFCR_MPRXE			(1 << 7)
-#define WFCR_WF3E			(1 << 3)
-#define WFCR_WF2E			(1 << 2)
-#define WFCR_WF1E			(1 << 1)
-#define WFCR_WF0E			(1 << 0)
-
-#define KS_WF0CRC0			0x30
-#define KS_WF0CRC1			0x32
-#define KS_WF0BM0			0x34
-#define KS_WF0BM1			0x36
-#define KS_WF0BM2			0x38
-#define KS_WF0BM3			0x3A
-
-#define KS_WF1CRC0			0x40
-#define KS_WF1CRC1			0x42
-#define KS_WF1BM0			0x44
-#define KS_WF1BM1			0x46
-#define KS_WF1BM2			0x48
-#define KS_WF1BM3			0x4A
-
-#define KS_WF2CRC0			0x50
-#define KS_WF2CRC1			0x52
-#define KS_WF2BM0			0x54
-#define KS_WF2BM1			0x56
-#define KS_WF2BM2			0x58
-#define KS_WF2BM3			0x5A
-
-#define KS_WF3CRC0			0x60
-#define KS_WF3CRC1			0x62
-#define KS_WF3BM0			0x64
-#define KS_WF3BM1			0x66
-#define KS_WF3BM2			0x68
-#define KS_WF3BM3			0x6A
-
-#define KS_TXCR				0x70
-#define TXCR_TCGICMP			(1 << 8)
-#define TXCR_TCGUDP			(1 << 7)
-#define TXCR_TCGTCP			(1 << 6)
-#define TXCR_TCGIP			(1 << 5)
-#define TXCR_FTXQ			(1 << 4)
-#define TXCR_TXFCE			(1 << 3)
-#define TXCR_TXPE			(1 << 2)
-#define TXCR_TXCRC			(1 << 1)
-#define TXCR_TXE			(1 << 0)
-
-#define KS_TXSR				0x72
-#define TXSR_TXLC			(1 << 13)
-#define TXSR_TXMC			(1 << 12)
-#define TXSR_TXFID_MASK			(0x3f << 0)
-#define TXSR_TXFID_SHIFT		(0)
-#define TXSR_TXFID_GET(_v)		(((_v) >> 0) & 0x3f)
-
-
-#define KS_RXCR1			0x74
-#define RXCR1_FRXQ			(1 << 15)
-#define RXCR1_RXUDPFCC			(1 << 14)
-#define RXCR1_RXTCPFCC			(1 << 13)
-#define RXCR1_RXIPFCC			(1 << 12)
-#define RXCR1_RXPAFMA			(1 << 11)
-#define RXCR1_RXFCE			(1 << 10)
-#define RXCR1_RXEFE			(1 << 9)
-#define RXCR1_RXMAFMA			(1 << 8)
-#define RXCR1_RXBE			(1 << 7)
-#define RXCR1_RXME			(1 << 6)
-#define RXCR1_RXUE			(1 << 5)
-#define RXCR1_RXAE			(1 << 4)
-#define RXCR1_RXINVF			(1 << 1)
-#define RXCR1_RXE			(1 << 0)
 #define RXCR1_FILTER_MASK    		(RXCR1_RXINVF | RXCR1_RXAE | \
 					 RXCR1_RXMAFMA | RXCR1_RXPAFMA)
-
-#define KS_RXCR2			0x76
-#define RXCR2_SRDBL_MASK		(0x7 << 5)
-#define RXCR2_SRDBL_SHIFT		(5)
-#define RXCR2_SRDBL_4B			(0x0 << 5)
-#define RXCR2_SRDBL_8B			(0x1 << 5)
-#define RXCR2_SRDBL_16B			(0x2 << 5)
-#define RXCR2_SRDBL_32B			(0x3 << 5)
-/* #define RXCR2_SRDBL_FRAME		(0x4 << 5) */
-#define RXCR2_IUFFP			(1 << 4)
-#define RXCR2_RXIUFCEZ			(1 << 3)
-#define RXCR2_UDPLFE			(1 << 2)
-#define RXCR2_RXICMPFCC			(1 << 1)
-#define RXCR2_RXSAF			(1 << 0)
-
-#define KS_TXMIR			0x78
-
-#define KS_RXFHSR			0x7C
-#define RXFSHR_RXFV			(1 << 15)
-#define RXFSHR_RXICMPFCS		(1 << 13)
-#define RXFSHR_RXIPFCS			(1 << 12)
-#define RXFSHR_RXTCPFCS			(1 << 11)
-#define RXFSHR_RXUDPFCS			(1 << 10)
-#define RXFSHR_RXBF			(1 << 7)
-#define RXFSHR_RXMF			(1 << 6)
-#define RXFSHR_RXUF			(1 << 5)
-#define RXFSHR_RXMR			(1 << 4)
-#define RXFSHR_RXFT			(1 << 3)
-#define RXFSHR_RXFTL			(1 << 2)
-#define RXFSHR_RXRF			(1 << 1)
-#define RXFSHR_RXCE			(1 << 0)
-#define	RXFSHR_ERR			(RXFSHR_RXCE | RXFSHR_RXRF |\
-					RXFSHR_RXFTL | RXFSHR_RXMR |\
-					RXFSHR_RXICMPFCS | RXFSHR_RXIPFCS |\
-					RXFSHR_RXTCPFCS)
-#define KS_RXFHBCR			0x7E
-#define RXFHBCR_CNT_MASK		0x0FFF
-
-#define KS_TXQCR			0x80
-#define TXQCR_AETFE			(1 << 2)
-#define TXQCR_TXQMAM			(1 << 1)
-#define TXQCR_METFE			(1 << 0)
-
-#define KS_RXQCR			0x82
-#define RXQCR_RXDTTS			(1 << 12)
-#define RXQCR_RXDBCTS			(1 << 11)
-#define RXQCR_RXFCTS			(1 << 10)
-#define RXQCR_RXIPHTOE			(1 << 9)
-#define RXQCR_RXDTTE			(1 << 7)
-#define RXQCR_RXDBCTE			(1 << 6)
-#define RXQCR_RXFCTE			(1 << 5)
-#define RXQCR_ADRFE			(1 << 4)
-#define RXQCR_SDA			(1 << 3)
-#define RXQCR_RRXEF			(1 << 0)
 #define RXQCR_CMD_CNTL                	(RXQCR_RXFCTE|RXQCR_ADRFE)
 
-#define KS_TXFDPR			0x84
-#define TXFDPR_TXFPAI			(1 << 14)
-#define TXFDPR_TXFP_MASK		(0x7ff << 0)
-#define TXFDPR_TXFP_SHIFT		(0)
-
-#define KS_RXFDPR			0x86
-#define RXFDPR_RXFPAI			(1 << 14)
-
-#define KS_RXDTTR			0x8C
-#define KS_RXDBCTR			0x8E
-
-#define KS_IER				0x90
-#define KS_ISR				0x92
-#define IRQ_LCI				(1 << 15)
-#define IRQ_TXI				(1 << 14)
-#define IRQ_RXI				(1 << 13)
-#define IRQ_RXOI			(1 << 11)
-#define IRQ_TXPSI			(1 << 9)
-#define IRQ_RXPSI			(1 << 8)
-#define IRQ_TXSAI			(1 << 6)
-#define IRQ_RXWFDI			(1 << 5)
-#define IRQ_RXMPDI			(1 << 4)
-#define IRQ_LDI				(1 << 3)
-#define IRQ_EDI				(1 << 2)
-#define IRQ_SPIBEI			(1 << 1)
-#define IRQ_DEDI			(1 << 0)
-
-#define KS_RXFCTR			0x9C
-#define RXFCTR_THRESHOLD_MASK     	0x00FF
-
-#define KS_RXFC				0x9D
-#define RXFCTR_RXFC_MASK		(0xff << 8)
-#define RXFCTR_RXFC_SHIFT		(8)
-#define RXFCTR_RXFC_GET(_v)		(((_v) >> 8) & 0xff)
-#define RXFCTR_RXFCT_MASK		(0xff << 0)
-#define RXFCTR_RXFCT_SHIFT		(0)
-
-#define KS_TXNTFSR			0x9E
-
-#define KS_MAHTR0			0xA0
-#define KS_MAHTR1			0xA2
-#define KS_MAHTR2			0xA4
-#define KS_MAHTR3			0xA6
-
-#define KS_FCLWR			0xB0
-#define KS_FCHWR			0xB2
-#define KS_FCOWR			0xB4
-
-#define KS_CIDER			0xC0
-#define CIDER_ID			0x8870
-#define CIDER_REV_MASK			(0x7 << 1)
-#define CIDER_REV_SHIFT			(1)
-#define CIDER_REV_GET(_v)		(((_v) >> 1) & 0x7)
-
-#define KS_CGCR				0xC6
-#define KS_IACR				0xC8
-#define IACR_RDEN			(1 << 12)
-#define IACR_TSEL_MASK			(0x3 << 10)
-#define IACR_TSEL_SHIFT			(10)
-#define IACR_TSEL_MIB			(0x3 << 10)
-#define IACR_ADDR_MASK			(0x1f << 0)
-#define IACR_ADDR_SHIFT			(0)
-
-#define KS_IADLR			0xD0
-#define KS_IAHDR			0xD2
-
-#define KS_PMECR			0xD4
-#define PMECR_PME_DELAY			(1 << 14)
-#define PMECR_PME_POL			(1 << 12)
-#define PMECR_WOL_WAKEUP		(1 << 11)
-#define PMECR_WOL_MAGICPKT		(1 << 10)
-#define PMECR_WOL_LINKUP		(1 << 9)
-#define PMECR_WOL_ENERGY		(1 << 8)
-#define PMECR_AUTO_WAKE_EN		(1 << 7)
-#define PMECR_WAKEUP_NORMAL		(1 << 6)
-#define PMECR_WKEVT_MASK		(0xf << 2)
-#define PMECR_WKEVT_SHIFT		(2)
-#define PMECR_WKEVT_GET(_v)		(((_v) >> 2) & 0xf)
-#define PMECR_WKEVT_ENERGY		(0x1 << 2)
-#define PMECR_WKEVT_LINK		(0x2 << 2)
-#define PMECR_WKEVT_MAGICPKT		(0x4 << 2)
-#define PMECR_WKEVT_FRAME		(0x8 << 2)
-#define PMECR_PM_MASK			(0x3 << 0)
-#define PMECR_PM_SHIFT			(0)
-#define PMECR_PM_NORMAL			(0x0 << 0)
-#define PMECR_PM_ENERGY			(0x1 << 0)
-#define PMECR_PM_SOFTDOWN		(0x2 << 0)
-#define PMECR_PM_POWERSAVE		(0x3 << 0)
-
-/* Standard MII PHY data */
-#define KS_P1MBCR			0xE4
-#define P1MBCR_FORCE_FDX		(1 << 8)
-
-#define KS_P1MBSR			0xE6
-#define P1MBSR_AN_COMPLETE		(1 << 5)
-#define P1MBSR_AN_CAPABLE		(1 << 3)
-#define P1MBSR_LINK_UP			(1 << 2)
-
-#define KS_PHY1ILR			0xE8
-#define KS_PHY1IHR			0xEA
-#define KS_P1ANAR			0xEC
-#define KS_P1ANLPR			0xEE
-
-#define KS_P1SCLMD			0xF4
-#define P1SCLMD_LEDOFF			(1 << 15)
-#define P1SCLMD_TXIDS			(1 << 14)
-#define P1SCLMD_RESTARTAN		(1 << 13)
-#define P1SCLMD_DISAUTOMDIX		(1 << 10)
-#define P1SCLMD_FORCEMDIX		(1 << 9)
-#define P1SCLMD_AUTONEGEN		(1 << 7)
-#define P1SCLMD_FORCE100		(1 << 6)
-#define P1SCLMD_FORCEFDX		(1 << 5)
-#define P1SCLMD_ADV_FLOW		(1 << 4)
-#define P1SCLMD_ADV_100BT_FDX		(1 << 3)
-#define P1SCLMD_ADV_100BT_HDX		(1 << 2)
-#define P1SCLMD_ADV_10BT_FDX		(1 << 1)
-#define P1SCLMD_ADV_10BT_HDX		(1 << 0)
-
-#define KS_P1CR				0xF6
-#define P1CR_HP_MDIX			(1 << 15)
-#define P1CR_REV_POL			(1 << 13)
-#define P1CR_OP_100M			(1 << 10)
-#define P1CR_OP_FDX			(1 << 9)
-#define P1CR_OP_MDI			(1 << 7)
-#define P1CR_AN_DONE			(1 << 6)
-#define P1CR_LINK_GOOD			(1 << 5)
-#define P1CR_PNTR_FLOW			(1 << 4)
-#define P1CR_PNTR_100BT_FDX		(1 << 3)
-#define P1CR_PNTR_100BT_HDX		(1 << 2)
-#define P1CR_PNTR_10BT_FDX		(1 << 1)
-#define P1CR_PNTR_10BT_HDX		(1 << 0)
-
-/* TX Frame control */
-
-#define TXFR_TXIC			(1 << 15)
-#define TXFR_TXFID_MASK			(0x3f << 0)
-#define TXFR_TXFID_SHIFT		(0)
-
-#define KS_P1SR				0xF8
-#define P1SR_HP_MDIX			(1 << 15)
-#define P1SR_REV_POL			(1 << 13)
-#define P1SR_OP_100M			(1 << 10)
-#define P1SR_OP_FDX			(1 << 9)
-#define P1SR_OP_MDI			(1 << 7)
-#define P1SR_AN_DONE			(1 << 6)
-#define P1SR_LINK_GOOD			(1 << 5)
-#define P1SR_PNTR_FLOW			(1 << 4)
-#define P1SR_PNTR_100BT_FDX		(1 << 3)
-#define P1SR_PNTR_100BT_HDX		(1 << 2)
-#define P1SR_PNTR_10BT_FDX		(1 << 1)
-#define P1SR_PNTR_10BT_HDX		(1 << 0)
-
 #define	ENUM_BUS_NONE			0
 #define	ENUM_BUS_8BIT			1
 #define	ENUM_BUS_16BIT			2
@@ -1475,7 +1168,7 @@ static void ks_setup(struct ks_net *ks)
 	ks_wrreg16(ks, KS_RXFDPR, RXFDPR_RXFPAI);
 
 	/* Setup Receive Frame Threshold - 1 frame (RXFCTFC) */
-	ks_wrreg16(ks, KS_RXFCTR, 1 & RXFCTR_THRESHOLD_MASK);
+	ks_wrreg16(ks, KS_RXFCTR, 1 & RXFCTR_RXFCT_MASK);
 
 	/* Setup RxQ Command Control (RXQCR) */
 	ks->rc_rxqcr = RXQCR_CMD_CNTL;
@@ -1488,7 +1181,7 @@ static void ks_setup(struct ks_net *ks)
 	 */
 
 	w = ks_rdreg16(ks, KS_P1MBCR);
-	w &= ~P1MBCR_FORCE_FDX;
+	w &= ~BMCR_FULLDPLX;
 	ks_wrreg16(ks, KS_P1MBCR, w);
 
 	w = TXCR_TXFCE | TXCR_TXPE | TXCR_TXCRC | TXCR_TCGIP;
@@ -1629,7 +1322,7 @@ static int ks8851_probe(struct platform_device *pdev)
 	ks_setup_int(ks);
 
 	data = ks_rdreg16(ks, KS_OBCR);
-	ks_wrreg16(ks, KS_OBCR, data | OBCR_ODS_16MA);
+	ks_wrreg16(ks, KS_OBCR, data | OBCR_ODS_16mA);
 
 	/* overwriting the default MAC address */
 	if (pdev->dev.of_node) {
diff --git a/drivers/net/ethernet/mscc/ocelot.c b/drivers/net/ethernet/mscc/ocelot.c
index a1d0d6e42533..d715ef4fc92f 100644
--- a/drivers/net/ethernet/mscc/ocelot.c
+++ b/drivers/net/ethernet/mscc/ocelot.c
@@ -613,7 +613,7 @@ static int ocelot_mact_mc_add(struct ocelot_port *port,
 			      struct netdev_hw_addr *hw_addr)
 {
 	struct ocelot *ocelot = port->ocelot;
-	struct netdev_hw_addr *ha = kzalloc(sizeof(*ha), GFP_KERNEL);
+	struct netdev_hw_addr *ha = kzalloc(sizeof(*ha), GFP_ATOMIC);
 
 	if (!ha)
 		return -ENOMEM;
@@ -959,10 +959,8 @@ static void ocelot_get_strings(struct net_device *netdev, u32 sset, u8 *data)
 		       ETH_GSTRING_LEN);
 }
 
-static void ocelot_check_stats(struct work_struct *work)
+static void ocelot_update_stats(struct ocelot *ocelot)
 {
-	struct delayed_work *del_work = to_delayed_work(work);
-	struct ocelot *ocelot = container_of(del_work, struct ocelot, stats_work);
 	int i, j;
 
 	mutex_lock(&ocelot->stats_lock);
@@ -986,11 +984,19 @@ static void ocelot_check_stats(struct work_struct *work)
 		}
 	}
 
-	cancel_delayed_work(&ocelot->stats_work);
+	mutex_unlock(&ocelot->stats_lock);
+}
+
+static void ocelot_check_stats_work(struct work_struct *work)
+{
+	struct delayed_work *del_work = to_delayed_work(work);
+	struct ocelot *ocelot = container_of(del_work, struct ocelot,
+					     stats_work);
+
+	ocelot_update_stats(ocelot);
+
 	queue_delayed_work(ocelot->stats_queue, &ocelot->stats_work,
 			   OCELOT_STATS_CHECK_DELAY);
-
-	mutex_unlock(&ocelot->stats_lock);
 }
 
 static void ocelot_get_ethtool_stats(struct net_device *dev,
@@ -1001,7 +1007,7 @@ static void ocelot_get_ethtool_stats(struct net_device *dev,
 	int i;
 
 	/* check and update now */
-	ocelot_check_stats(&ocelot->stats_work.work);
+	ocelot_update_stats(ocelot);
 
 	/* Copy all counters */
 	for (i = 0; i < ocelot->num_stats; i++)
@@ -1809,7 +1815,7 @@ int ocelot_init(struct ocelot *ocelot)
 				 ANA_CPUQ_8021_CFG_CPUQ_BPDU_VAL(6),
 				 ANA_CPUQ_8021_CFG, i);
 
-	INIT_DELAYED_WORK(&ocelot->stats_work, ocelot_check_stats);
+	INIT_DELAYED_WORK(&ocelot->stats_work, ocelot_check_stats_work);
 	queue_delayed_work(ocelot->stats_queue, &ocelot->stats_work,
 			   OCELOT_STATS_CHECK_DELAY);
 	return 0;
diff --git a/drivers/net/ethernet/myricom/myri10ge/myri10ge.c b/drivers/net/ethernet/myricom/myri10ge/myri10ge.c
index e0340f778d8f..d8b7fba96d58 100644
--- a/drivers/net/ethernet/myricom/myri10ge/myri10ge.c
+++ b/drivers/net/ethernet/myricom/myri10ge/myri10ge.c
@@ -1439,7 +1439,6 @@ myri10ge_tx_done(struct myri10ge_slice_state *ss, int mcp_index)
 			tx->queue_active = 0;
 			put_be32(htonl(1), tx->send_stop);
 			mb();
-			mmiowb();
 		}
 		__netif_tx_unlock(dev_queue);
 	}
@@ -2861,7 +2860,6 @@ again:
 		tx->queue_active = 1;
 		put_be32(htonl(1), tx->send_go);
 		mb();
-		mmiowb();
 	}
 	tx->pkt_start++;
 	if ((avail - count) < MXGEFW_MAX_SEND_DESC) {
diff --git a/drivers/net/ethernet/neterion/s2io.c b/drivers/net/ethernet/neterion/s2io.c
index feda9644289d..3b2ae1a21678 100644
--- a/drivers/net/ethernet/neterion/s2io.c
+++ b/drivers/net/ethernet/neterion/s2io.c
@@ -4153,8 +4153,6 @@ static netdev_tx_t s2io_xmit(struct sk_buff *skb, struct net_device *dev)
 
 	writeq(val64, &tx_fifo->List_Control);
 
-	mmiowb();
-
 	put_off++;
 	if (put_off == fifo->tx_curr_put_info.fifo_len + 1)
 		put_off = 0;
diff --git a/drivers/net/ethernet/neterion/vxge/vxge-config.c b/drivers/net/ethernet/neterion/vxge/vxge-config.c
index 7cde387e5ec6..51cd57ab3d95 100644
--- a/drivers/net/ethernet/neterion/vxge/vxge-config.c
+++ b/drivers/net/ethernet/neterion/vxge/vxge-config.c
@@ -2366,6 +2366,7 @@ static void *__vxge_hw_blockpool_malloc(struct __vxge_hw_device *devh, u32 size,
 				dma_object->addr))) {
 			vxge_os_dma_free(devh->pdev, memblock,
 				&dma_object->acc_handle);
+			memblock = NULL;
 			goto exit;
 		}
 
diff --git a/drivers/net/ethernet/neterion/vxge/vxge-main.c b/drivers/net/ethernet/neterion/vxge/vxge-main.c
index b877acec5cde..1d334f2e0a56 100644
--- a/drivers/net/ethernet/neterion/vxge/vxge-main.c
+++ b/drivers/net/ethernet/neterion/vxge/vxge-main.c
@@ -1826,7 +1826,6 @@ static int vxge_poll_msix(struct napi_struct *napi, int budget)
 		vxge_hw_channel_msix_unmask(
 				(struct __vxge_hw_channel *)ring->handle,
 				ring->rx_vector_no);
-		mmiowb();
 	}
 
 	/* We are copying and returning the local variable, in case if after
@@ -2234,8 +2233,6 @@ static irqreturn_t vxge_tx_msix_handle(int irq, void *dev_id)
 	vxge_hw_channel_msix_unmask((struct __vxge_hw_channel *)fifo->handle,
 				    fifo->tx_vector_no);
 
-	mmiowb();
-
 	return IRQ_HANDLED;
 }
 
@@ -2272,14 +2269,12 @@ vxge_alarm_msix_handle(int irq, void *dev_id)
 		 */
 		vxge_hw_vpath_msix_mask(vdev->vpaths[i].handle, msix_id);
 		vxge_hw_vpath_msix_clear(vdev->vpaths[i].handle, msix_id);
-		mmiowb();
 
 		status = vxge_hw_vpath_alarm_process(vdev->vpaths[i].handle,
 			vdev->exec_mode);
 		if (status == VXGE_HW_OK) {
 			vxge_hw_vpath_msix_unmask(vdev->vpaths[i].handle,
 						  msix_id);
-			mmiowb();
 			continue;
 		}
 		vxge_debug_intr(VXGE_ERR,
diff --git a/drivers/net/ethernet/neterion/vxge/vxge-traffic.c b/drivers/net/ethernet/neterion/vxge/vxge-traffic.c
index 59e77e3086bb..709d20d9938f 100644
--- a/drivers/net/ethernet/neterion/vxge/vxge-traffic.c
+++ b/drivers/net/ethernet/neterion/vxge/vxge-traffic.c
@@ -1399,11 +1399,7 @@ static void __vxge_hw_non_offload_db_post(struct __vxge_hw_fifo *fifo,
 		VXGE_HW_NODBW_GET_NO_SNOOP(no_snoop),
 		&fifo->nofl_db->control_0);
 
-	mmiowb();
-
 	writeq(txdl_ptr, &fifo->nofl_db->txdl_ptr);
-
-	mmiowb();
 }
 
 /**
diff --git a/drivers/net/ethernet/netronome/nfp/abm/cls.c b/drivers/net/ethernet/netronome/nfp/abm/cls.c
index 9852080cf454..ff3913085665 100644
--- a/drivers/net/ethernet/netronome/nfp/abm/cls.c
+++ b/drivers/net/ethernet/netronome/nfp/abm/cls.c
@@ -39,7 +39,7 @@ nfp_abm_u32_check_knode(struct nfp_abm *abm, struct tc_cls_u32_knode *knode,
 	}
 	if (knode->sel->off || knode->sel->offshift || knode->sel->offmask ||
 	    knode->sel->offoff || knode->fshift) {
-		NL_SET_ERR_MSG_MOD(extack, "variable offseting not supported");
+		NL_SET_ERR_MSG_MOD(extack, "variable offsetting not supported");
 		return false;
 	}
 	if (knode->sel->hoff || knode->sel->hmask) {
@@ -78,7 +78,7 @@ nfp_abm_u32_check_knode(struct nfp_abm *abm, struct tc_cls_u32_knode *knode,
 
 	k = &knode->sel->keys[0];
 	if (k->offmask) {
-		NL_SET_ERR_MSG_MOD(extack, "offset mask - variable offseting not supported");
+		NL_SET_ERR_MSG_MOD(extack, "offset mask - variable offsetting not supported");
 		return false;
 	}
 	if (k->off) {
diff --git a/drivers/net/ethernet/netronome/nfp/flower/action.c b/drivers/net/ethernet/netronome/nfp/flower/action.c
index eeda4ed98333..e336f6ee94f5 100644
--- a/drivers/net/ethernet/netronome/nfp/flower/action.c
+++ b/drivers/net/ethernet/netronome/nfp/flower/action.c
@@ -48,8 +48,7 @@ nfp_fl_push_vlan(struct nfp_fl_push_vlan *push_vlan,
 
 	tmp_push_vlan_tci =
 		FIELD_PREP(NFP_FL_PUSH_VLAN_PRIO, act->vlan.prio) |
-		FIELD_PREP(NFP_FL_PUSH_VLAN_VID, act->vlan.vid) |
-		NFP_FL_PUSH_VLAN_CFI;
+		FIELD_PREP(NFP_FL_PUSH_VLAN_VID, act->vlan.vid);
 	push_vlan->vlan_tci = cpu_to_be16(tmp_push_vlan_tci);
 }
 
diff --git a/drivers/net/ethernet/netronome/nfp/flower/cmsg.h b/drivers/net/ethernet/netronome/nfp/flower/cmsg.h
index 4fcaf11ed56e..0ed51e79db00 100644
--- a/drivers/net/ethernet/netronome/nfp/flower/cmsg.h
+++ b/drivers/net/ethernet/netronome/nfp/flower/cmsg.h
@@ -26,7 +26,7 @@
 #define NFP_FLOWER_LAYER2_GENEVE_OP	BIT(6)
 
 #define NFP_FLOWER_MASK_VLAN_PRIO	GENMASK(15, 13)
-#define NFP_FLOWER_MASK_VLAN_CFI	BIT(12)
+#define NFP_FLOWER_MASK_VLAN_PRESENT	BIT(12)
 #define NFP_FLOWER_MASK_VLAN_VID	GENMASK(11, 0)
 
 #define NFP_FLOWER_MASK_MPLS_LB		GENMASK(31, 12)
@@ -82,7 +82,6 @@
 #define NFP_FL_OUT_FLAGS_TYPE_IDX	GENMASK(2, 0)
 
 #define NFP_FL_PUSH_VLAN_PRIO		GENMASK(15, 13)
-#define NFP_FL_PUSH_VLAN_CFI		BIT(12)
 #define NFP_FL_PUSH_VLAN_VID		GENMASK(11, 0)
 
 #define IPV6_FLOW_LABEL_MASK		cpu_to_be32(0x000fffff)
diff --git a/drivers/net/ethernet/netronome/nfp/flower/match.c b/drivers/net/ethernet/netronome/nfp/flower/match.c
index e03c8ef2c28c..9b8b843d0340 100644
--- a/drivers/net/ethernet/netronome/nfp/flower/match.c
+++ b/drivers/net/ethernet/netronome/nfp/flower/match.c
@@ -30,20 +30,19 @@ nfp_flower_compile_meta_tci(struct nfp_flower_meta_tci *ext,
 
 		flow_rule_match_vlan(rule, &match);
 		/* Populate the tci field. */
-		if (match.key->vlan_id || match.key->vlan_priority) {
-			tmp_tci = FIELD_PREP(NFP_FLOWER_MASK_VLAN_PRIO,
-					     match.key->vlan_priority) |
-				  FIELD_PREP(NFP_FLOWER_MASK_VLAN_VID,
-					     match.key->vlan_id) |
-				  NFP_FLOWER_MASK_VLAN_CFI;
-			ext->tci = cpu_to_be16(tmp_tci);
-			tmp_tci = FIELD_PREP(NFP_FLOWER_MASK_VLAN_PRIO,
-					     match.mask->vlan_priority) |
-				  FIELD_PREP(NFP_FLOWER_MASK_VLAN_VID,
-					     match.mask->vlan_id) |
-				  NFP_FLOWER_MASK_VLAN_CFI;
-			msk->tci = cpu_to_be16(tmp_tci);
-		}
+		tmp_tci = NFP_FLOWER_MASK_VLAN_PRESENT;
+		tmp_tci |= FIELD_PREP(NFP_FLOWER_MASK_VLAN_PRIO,
+				      match.key->vlan_priority) |
+			   FIELD_PREP(NFP_FLOWER_MASK_VLAN_VID,
+				      match.key->vlan_id);
+		ext->tci = cpu_to_be16(tmp_tci);
+
+		tmp_tci = NFP_FLOWER_MASK_VLAN_PRESENT;
+		tmp_tci |= FIELD_PREP(NFP_FLOWER_MASK_VLAN_PRIO,
+				      match.mask->vlan_priority) |
+			   FIELD_PREP(NFP_FLOWER_MASK_VLAN_VID,
+				      match.mask->vlan_id);
+		msk->tci = cpu_to_be16(tmp_tci);
 	}
 }
 
diff --git a/drivers/net/ethernet/netronome/nfp/nfp_net_repr.c b/drivers/net/ethernet/netronome/nfp/nfp_net_repr.c
index d2c803bb4e56..94d228c04496 100644
--- a/drivers/net/ethernet/netronome/nfp/nfp_net_repr.c
+++ b/drivers/net/ethernet/netronome/nfp/nfp_net_repr.c
@@ -195,7 +195,7 @@ static netdev_tx_t nfp_repr_xmit(struct sk_buff *skb, struct net_device *netdev)
 	ret = dev_queue_xmit(skb);
 	nfp_repr_inc_tx_stats(netdev, len, ret);
 
-	return ret;
+	return NETDEV_TX_OK;
 }
 
 static int nfp_repr_stop(struct net_device *netdev)
@@ -383,7 +383,7 @@ int nfp_repr_init(struct nfp_app *app, struct net_device *netdev,
 	netdev->features &= ~(NETIF_F_TSO | NETIF_F_TSO6);
 	netdev->gso_max_segs = NFP_NET_LSO_MAX_SEGS;
 
-	netdev->priv_flags |= IFF_NO_QUEUE;
+	netdev->priv_flags |= IFF_NO_QUEUE | IFF_DISABLE_NETPOLL;
 	netdev->features |= NETIF_F_LLTX;
 
 	if (nfp_app_has_tc(app)) {
diff --git a/drivers/net/ethernet/qlogic/qed/qed.h b/drivers/net/ethernet/qlogic/qed/qed.h
index 43a57ec296fd..127c89b22ef0 100644
--- a/drivers/net/ethernet/qlogic/qed/qed.h
+++ b/drivers/net/ethernet/qlogic/qed/qed.h
@@ -431,12 +431,16 @@ struct qed_qm_info {
 	u8 num_pf_rls;
 };
 
+#define QED_OVERFLOW_BIT	1
+
 struct qed_db_recovery_info {
 	struct list_head list;
 
 	/* Lock to protect the doorbell recovery mechanism list */
 	spinlock_t lock;
+	bool dorq_attn;
 	u32 db_recovery_counter;
+	unsigned long overflow;
 };
 
 struct storm_stats {
@@ -920,8 +924,7 @@ u16 qed_get_cm_pq_idx_llt_mtc(struct qed_hwfn *p_hwfn, u8 tc);
 
 /* doorbell recovery mechanism */
 void qed_db_recovery_dp(struct qed_hwfn *p_hwfn);
-void qed_db_recovery_execute(struct qed_hwfn *p_hwfn,
-			     enum qed_db_rec_exec db_exec);
+void qed_db_recovery_execute(struct qed_hwfn *p_hwfn);
 bool qed_edpm_enabled(struct qed_hwfn *p_hwfn);
 
 /* Other Linux specific common definitions */
diff --git a/drivers/net/ethernet/qlogic/qed/qed_dev.c b/drivers/net/ethernet/qlogic/qed/qed_dev.c
index 9df8c4b3b54e..866cdc86a3f2 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_dev.c
+++ b/drivers/net/ethernet/qlogic/qed/qed_dev.c
@@ -102,11 +102,15 @@ static void qed_db_recovery_dp_entry(struct qed_hwfn *p_hwfn,
 
 /* Doorbell address sanity (address within doorbell bar range) */
 static bool qed_db_rec_sanity(struct qed_dev *cdev,
-			      void __iomem *db_addr, void *db_data)
+			      void __iomem *db_addr,
+			      enum qed_db_rec_width db_width,
+			      void *db_data)
 {
+	u32 width = (db_width == DB_REC_WIDTH_32B) ? 32 : 64;
+
 	/* Make sure doorbell address is within the doorbell bar */
 	if (db_addr < cdev->doorbells ||
-	    (u8 __iomem *)db_addr >
+	    (u8 __iomem *)db_addr + width >
 	    (u8 __iomem *)cdev->doorbells + cdev->db_size) {
 		WARN(true,
 		     "Illegal doorbell address: %p. Legal range for doorbell addresses is [%p..%p]\n",
@@ -159,7 +163,7 @@ int qed_db_recovery_add(struct qed_dev *cdev,
 	}
 
 	/* Sanitize doorbell address */
-	if (!qed_db_rec_sanity(cdev, db_addr, db_data))
+	if (!qed_db_rec_sanity(cdev, db_addr, db_width, db_data))
 		return -EINVAL;
 
 	/* Obtain hwfn from doorbell address */
@@ -205,10 +209,6 @@ int qed_db_recovery_del(struct qed_dev *cdev,
 		return 0;
 	}
 
-	/* Sanitize doorbell address */
-	if (!qed_db_rec_sanity(cdev, db_addr, db_data))
-		return -EINVAL;
-
 	/* Obtain hwfn from doorbell address */
 	p_hwfn = qed_db_rec_find_hwfn(cdev, db_addr);
 
@@ -300,31 +300,24 @@ void qed_db_recovery_dp(struct qed_hwfn *p_hwfn)
 
 /* Ring the doorbell of a single doorbell recovery entry */
 static void qed_db_recovery_ring(struct qed_hwfn *p_hwfn,
-				 struct qed_db_recovery_entry *db_entry,
-				 enum qed_db_rec_exec db_exec)
-{
-	if (db_exec != DB_REC_ONCE) {
-		/* Print according to width */
-		if (db_entry->db_width == DB_REC_WIDTH_32B) {
-			DP_VERBOSE(p_hwfn, QED_MSG_SPQ,
-				   "%s doorbell address %p data %x\n",
-				   db_exec == DB_REC_DRY_RUN ?
-				   "would have rung" : "ringing",
-				   db_entry->db_addr,
-				   *(u32 *)db_entry->db_data);
-		} else {
-			DP_VERBOSE(p_hwfn, QED_MSG_SPQ,
-				   "%s doorbell address %p data %llx\n",
-				   db_exec == DB_REC_DRY_RUN ?
-				   "would have rung" : "ringing",
-				   db_entry->db_addr,
-				   *(u64 *)(db_entry->db_data));
-		}
+				 struct qed_db_recovery_entry *db_entry)
+{
+	/* Print according to width */
+	if (db_entry->db_width == DB_REC_WIDTH_32B) {
+		DP_VERBOSE(p_hwfn, QED_MSG_SPQ,
+			   "ringing doorbell address %p data %x\n",
+			   db_entry->db_addr,
+			   *(u32 *)db_entry->db_data);
+	} else {
+		DP_VERBOSE(p_hwfn, QED_MSG_SPQ,
+			   "ringing doorbell address %p data %llx\n",
+			   db_entry->db_addr,
+			   *(u64 *)(db_entry->db_data));
 	}
 
 	/* Sanity */
 	if (!qed_db_rec_sanity(p_hwfn->cdev, db_entry->db_addr,
-			       db_entry->db_data))
+			       db_entry->db_width, db_entry->db_data))
 		return;
 
 	/* Flush the write combined buffer. Since there are multiple doorbelling
@@ -334,14 +327,12 @@ static void qed_db_recovery_ring(struct qed_hwfn *p_hwfn,
 	wmb();
 
 	/* Ring the doorbell */
-	if (db_exec == DB_REC_REAL_DEAL || db_exec == DB_REC_ONCE) {
-		if (db_entry->db_width == DB_REC_WIDTH_32B)
-			DIRECT_REG_WR(db_entry->db_addr,
-				      *(u32 *)(db_entry->db_data));
-		else
-			DIRECT_REG_WR64(db_entry->db_addr,
-					*(u64 *)(db_entry->db_data));
-	}
+	if (db_entry->db_width == DB_REC_WIDTH_32B)
+		DIRECT_REG_WR(db_entry->db_addr,
+			      *(u32 *)(db_entry->db_data));
+	else
+		DIRECT_REG_WR64(db_entry->db_addr,
+				*(u64 *)(db_entry->db_data));
 
 	/* Flush the write combined buffer. Next doorbell may come from a
 	 * different entity to the same address...
@@ -350,29 +341,21 @@ static void qed_db_recovery_ring(struct qed_hwfn *p_hwfn,
 }
 
 /* Traverse the doorbell recovery entry list and ring all the doorbells */
-void qed_db_recovery_execute(struct qed_hwfn *p_hwfn,
-			     enum qed_db_rec_exec db_exec)
+void qed_db_recovery_execute(struct qed_hwfn *p_hwfn)
 {
 	struct qed_db_recovery_entry *db_entry = NULL;
 
-	if (db_exec != DB_REC_ONCE) {
-		DP_NOTICE(p_hwfn,
-			  "Executing doorbell recovery. Counter was %d\n",
-			  p_hwfn->db_recovery_info.db_recovery_counter);
+	DP_NOTICE(p_hwfn, "Executing doorbell recovery. Counter was %d\n",
+		  p_hwfn->db_recovery_info.db_recovery_counter);
 
-		/* Track amount of times recovery was executed */
-		p_hwfn->db_recovery_info.db_recovery_counter++;
-	}
+	/* Track amount of times recovery was executed */
+	p_hwfn->db_recovery_info.db_recovery_counter++;
 
 	/* Protect the list */
 	spin_lock_bh(&p_hwfn->db_recovery_info.lock);
 	list_for_each_entry(db_entry,
-			    &p_hwfn->db_recovery_info.list, list_entry) {
-		qed_db_recovery_ring(p_hwfn, db_entry, db_exec);
-		if (db_exec == DB_REC_ONCE)
-			break;
-	}
-
+			    &p_hwfn->db_recovery_info.list, list_entry)
+		qed_db_recovery_ring(p_hwfn, db_entry);
 	spin_unlock_bh(&p_hwfn->db_recovery_info.lock);
 }
 
diff --git a/drivers/net/ethernet/qlogic/qed/qed_int.c b/drivers/net/ethernet/qlogic/qed/qed_int.c
index e23980e301b6..fdfedbc8e431 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_int.c
+++ b/drivers/net/ethernet/qlogic/qed/qed_int.c
@@ -378,6 +378,9 @@ static int qed_db_rec_flush_queue(struct qed_hwfn *p_hwfn,
 	u32 count = QED_DB_REC_COUNT;
 	u32 usage = 1;
 
+	/* Flush any pending (e)dpms as they may never arrive */
+	qed_wr(p_hwfn, p_ptt, DORQ_REG_DPM_FORCE_ABORT, 0x1);
+
 	/* wait for usage to zero or count to run out. This is necessary since
 	 * EDPM doorbell transactions can take multiple 64b cycles, and as such
 	 * can "split" over the pci. Possibly, the doorbell drop can happen with
@@ -406,51 +409,74 @@ static int qed_db_rec_flush_queue(struct qed_hwfn *p_hwfn,
 
 int qed_db_rec_handler(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt)
 {
-	u32 overflow;
+	u32 attn_ovfl, cur_ovfl;
 	int rc;
 
-	overflow = qed_rd(p_hwfn, p_ptt, DORQ_REG_PF_OVFL_STICKY);
-	DP_NOTICE(p_hwfn, "PF Overflow sticky 0x%x\n", overflow);
-	if (!overflow) {
-		qed_db_recovery_execute(p_hwfn, DB_REC_ONCE);
+	attn_ovfl = test_and_clear_bit(QED_OVERFLOW_BIT,
+				       &p_hwfn->db_recovery_info.overflow);
+	cur_ovfl = qed_rd(p_hwfn, p_ptt, DORQ_REG_PF_OVFL_STICKY);
+	if (!cur_ovfl && !attn_ovfl)
 		return 0;
-	}
 
-	if (qed_edpm_enabled(p_hwfn)) {
+	DP_NOTICE(p_hwfn, "PF Overflow sticky: attn %u current %u\n",
+		  attn_ovfl, cur_ovfl);
+
+	if (cur_ovfl && !p_hwfn->db_bar_no_edpm) {
 		rc = qed_db_rec_flush_queue(p_hwfn, p_ptt);
 		if (rc)
 			return rc;
 	}
 
-	/* Flush any pending (e)dpm as they may never arrive */
-	qed_wr(p_hwfn, p_ptt, DORQ_REG_DPM_FORCE_ABORT, 0x1);
-
 	/* Release overflow sticky indication (stop silently dropping everything) */
 	qed_wr(p_hwfn, p_ptt, DORQ_REG_PF_OVFL_STICKY, 0x0);
 
 	/* Repeat all last doorbells (doorbell drop recovery) */
-	qed_db_recovery_execute(p_hwfn, DB_REC_REAL_DEAL);
+	qed_db_recovery_execute(p_hwfn);
 
 	return 0;
 }
 
-static int qed_dorq_attn_cb(struct qed_hwfn *p_hwfn)
+static void qed_dorq_attn_overflow(struct qed_hwfn *p_hwfn)
 {
-	u32 int_sts, first_drop_reason, details, address, all_drops_reason;
 	struct qed_ptt *p_ptt = p_hwfn->p_dpc_ptt;
+	u32 overflow;
 	int rc;
 
-	int_sts = qed_rd(p_hwfn, p_ptt, DORQ_REG_INT_STS);
-	DP_NOTICE(p_hwfn->cdev, "DORQ attention. int_sts was %x\n", int_sts);
+	overflow = qed_rd(p_hwfn, p_ptt, DORQ_REG_PF_OVFL_STICKY);
+	if (!overflow)
+		goto out;
+
+	/* Run PF doorbell recovery in next periodic handler */
+	set_bit(QED_OVERFLOW_BIT, &p_hwfn->db_recovery_info.overflow);
+
+	if (!p_hwfn->db_bar_no_edpm) {
+		rc = qed_db_rec_flush_queue(p_hwfn, p_ptt);
+		if (rc)
+			goto out;
+	}
+
+	qed_wr(p_hwfn, p_ptt, DORQ_REG_PF_OVFL_STICKY, 0x0);
+out:
+	/* Schedule the handler even if overflow was not detected */
+	qed_periodic_db_rec_start(p_hwfn);
+}
+
+static int qed_dorq_attn_int_sts(struct qed_hwfn *p_hwfn)
+{
+	u32 int_sts, first_drop_reason, details, address, all_drops_reason;
+	struct qed_ptt *p_ptt = p_hwfn->p_dpc_ptt;
 
 	/* int_sts may be zero since all PFs were interrupted for doorbell
 	 * overflow but another one already handled it. Can abort here. If
 	 * This PF also requires overflow recovery we will be interrupted again.
 	 * The masked almost full indication may also be set. Ignoring.
 	 */
+	int_sts = qed_rd(p_hwfn, p_ptt, DORQ_REG_INT_STS);
 	if (!(int_sts & ~DORQ_REG_INT_STS_DORQ_FIFO_AFULL))
 		return 0;
 
+	DP_NOTICE(p_hwfn->cdev, "DORQ attention. int_sts was %x\n", int_sts);
+
 	/* check if db_drop or overflow happened */
 	if (int_sts & (DORQ_REG_INT_STS_DB_DROP |
 		       DORQ_REG_INT_STS_DORQ_FIFO_OVFL_ERR)) {
@@ -477,11 +503,6 @@ static int qed_dorq_attn_cb(struct qed_hwfn *p_hwfn)
 			  GET_FIELD(details, QED_DORQ_ATTENTION_SIZE) * 4,
 			  first_drop_reason, all_drops_reason);
 
-		rc = qed_db_rec_handler(p_hwfn, p_ptt);
-		qed_periodic_db_rec_start(p_hwfn);
-		if (rc)
-			return rc;
-
 		/* Clear the doorbell drop details and prepare for next drop */
 		qed_wr(p_hwfn, p_ptt, DORQ_REG_DB_DROP_DETAILS_REL, 0);
 
@@ -507,6 +528,25 @@ static int qed_dorq_attn_cb(struct qed_hwfn *p_hwfn)
 	return -EINVAL;
 }
 
+static int qed_dorq_attn_cb(struct qed_hwfn *p_hwfn)
+{
+	p_hwfn->db_recovery_info.dorq_attn = true;
+	qed_dorq_attn_overflow(p_hwfn);
+
+	return qed_dorq_attn_int_sts(p_hwfn);
+}
+
+static void qed_dorq_attn_handler(struct qed_hwfn *p_hwfn)
+{
+	if (p_hwfn->db_recovery_info.dorq_attn)
+		goto out;
+
+	/* Call DORQ callback if the attention was missed */
+	qed_dorq_attn_cb(p_hwfn);
+out:
+	p_hwfn->db_recovery_info.dorq_attn = false;
+}
+
 /* Instead of major changes to the data-structure, we have a some 'special'
  * identifiers for sources that changed meaning between adapters.
  */
@@ -774,18 +814,12 @@ static inline u16 qed_attn_update_idx(struct qed_hwfn *p_hwfn,
 {
 	u16 rc = 0, index;
 
-	/* Make certain HW write took affect */
-	mmiowb();
-
 	index = le16_to_cpu(p_sb_desc->sb_attn->sb_index);
 	if (p_sb_desc->index != index) {
 		p_sb_desc->index	= index;
 		rc		      = QED_SB_ATT_IDX;
 	}
 
-	/* Make certain we got a consistent view with HW */
-	mmiowb();
-
 	return rc;
 }
 
@@ -1080,6 +1114,9 @@ static int qed_int_deassertion(struct qed_hwfn  *p_hwfn,
 		}
 	}
 
+	/* Handle missed DORQ attention */
+	qed_dorq_attn_handler(p_hwfn);
+
 	/* Clear IGU indication for the deasserted bits */
 	DIRECT_REG_WR((u8 __iomem *)p_hwfn->regview +
 				    GTT_BAR0_MAP_REG_IGU_CMD +
@@ -1170,7 +1207,6 @@ static void qed_sb_ack_attn(struct qed_hwfn *p_hwfn,
 	/* Both segments (interrupts & acks) are written to same place address;
 	 * Need to guarantee all commands will be received (in-order) by HW.
 	 */
-	mmiowb();
 	barrier();
 }
 
@@ -1805,9 +1841,6 @@ static void qed_int_igu_enable_attn(struct qed_hwfn *p_hwfn,
 	qed_wr(p_hwfn, p_ptt, IGU_REG_TRAILING_EDGE_LATCH, 0xfff);
 	qed_wr(p_hwfn, p_ptt, IGU_REG_ATTENTION_ENABLE, 0xfff);
 
-	/* Flush the writes to IGU */
-	mmiowb();
-
 	/* Unmask AEU signals toward IGU */
 	qed_wr(p_hwfn, p_ptt, MISC_REG_AEU_MASK_ATTN_IGU, 0xff);
 }
@@ -1871,9 +1904,6 @@ static void qed_int_igu_cleanup_sb(struct qed_hwfn *p_hwfn,
 
 	qed_wr(p_hwfn, p_ptt, IGU_REG_COMMAND_REG_CTRL, cmd_ctrl);
 
-	/* Flush the write to IGU */
-	mmiowb();
-
 	/* calculate where to read the status bit from */
 	sb_bit = 1 << (igu_sb_id % 32);
 	sb_bit_addr = igu_sb_id / 32 * sizeof(u32);
diff --git a/drivers/net/ethernet/qlogic/qed/qed_int.h b/drivers/net/ethernet/qlogic/qed/qed_int.h
index 1f356ed4f761..d473b522afc5 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_int.h
+++ b/drivers/net/ethernet/qlogic/qed/qed_int.h
@@ -192,8 +192,8 @@ void qed_int_disable_post_isr_release(struct qed_dev *cdev);
 
 /**
  * @brief - Doorbell Recovery handler.
- *          Run DB_REAL_DEAL doorbell recovery in case of PF overflow
- *          (and flush DORQ if needed), otherwise run DB_REC_ONCE.
+ *          Run doorbell recovery in case of PF overflow (and flush DORQ if
+ *          needed).
  *
  * @param p_hwfn
  * @param p_ptt
diff --git a/drivers/net/ethernet/qlogic/qed/qed_main.c b/drivers/net/ethernet/qlogic/qed/qed_main.c
index f164d4acebcb..6de23b56b294 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_main.c
+++ b/drivers/net/ethernet/qlogic/qed/qed_main.c
@@ -970,7 +970,7 @@ static void qed_update_pf_params(struct qed_dev *cdev,
 	}
 }
 
-#define QED_PERIODIC_DB_REC_COUNT		100
+#define QED_PERIODIC_DB_REC_COUNT		10
 #define QED_PERIODIC_DB_REC_INTERVAL_MS		100
 #define QED_PERIODIC_DB_REC_INTERVAL \
 	msecs_to_jiffies(QED_PERIODIC_DB_REC_INTERVAL_MS)
diff --git a/drivers/net/ethernet/qlogic/qed/qed_spq.c b/drivers/net/ethernet/qlogic/qed/qed_spq.c
index 79b311b86f66..f5f3c03b9dd2 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_spq.c
+++ b/drivers/net/ethernet/qlogic/qed/qed_spq.c
@@ -341,9 +341,6 @@ void qed_eq_prod_update(struct qed_hwfn *p_hwfn, u16 prod)
 		   USTORM_EQE_CONS_OFFSET(p_hwfn->rel_pf_id);
 
 	REG_WR16(p_hwfn, addr, prod);
-
-	/* keep prod updates ordered */
-	mmiowb();
 }
 
 int qed_eq_completion(struct qed_hwfn *p_hwfn, void *cookie)
diff --git a/drivers/net/ethernet/qlogic/qed/qed_sriov.c b/drivers/net/ethernet/qlogic/qed/qed_sriov.c
index 9faaa6df78ed..2f318aaf2b05 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_sriov.c
+++ b/drivers/net/ethernet/qlogic/qed/qed_sriov.c
@@ -1591,7 +1591,7 @@ static void qed_iov_vf_mbx_acquire(struct qed_hwfn *p_hwfn,
 			p_vfdev->eth_fp_hsi_minor = ETH_HSI_VER_NO_PKT_LEN_TUNN;
 		} else {
 			DP_INFO(p_hwfn,
-				"VF[%d] needs fastpath HSI %02x.%02x, which is incompatible with loaded FW's faspath HSI %02x.%02x\n",
+				"VF[%d] needs fastpath HSI %02x.%02x, which is incompatible with loaded FW's fastpath HSI %02x.%02x\n",
 				vf->abs_vf_id,
 				req->vfdev_info.eth_fp_hsi_major,
 				req->vfdev_info.eth_fp_hsi_minor,
diff --git a/drivers/net/ethernet/qlogic/qede/qede_ethtool.c b/drivers/net/ethernet/qlogic/qede/qede_ethtool.c
index b4c8949933f1..4555c0b161ef 100644
--- a/drivers/net/ethernet/qlogic/qede/qede_ethtool.c
+++ b/drivers/net/ethernet/qlogic/qede/qede_ethtool.c
@@ -1526,14 +1526,6 @@ static int qede_selftest_transmit_traffic(struct qede_dev *edev,
 	barrier();
 	writel(txq->tx_db.raw, txq->doorbell_addr);
 
-	/* mmiowb is needed to synchronize doorbell writes from more than one
-	 * processor. It guarantees that the write arrives to the device before
-	 * the queue lock is released and another start_xmit is called (possibly
-	 * on another CPU). Without this barrier, the next doorbell can bypass
-	 * this doorbell. This is applicable to IA64/Altix systems.
-	 */
-	mmiowb();
-
 	for (i = 0; i < QEDE_SELFTEST_POLL_COUNT; i++) {
 		if (qede_txq_has_work(txq))
 			break;
diff --git a/drivers/net/ethernet/qlogic/qede/qede_fp.c b/drivers/net/ethernet/qlogic/qede/qede_fp.c
index 31b046e24565..6f7e3622c6b4 100644
--- a/drivers/net/ethernet/qlogic/qede/qede_fp.c
+++ b/drivers/net/ethernet/qlogic/qede/qede_fp.c
@@ -580,14 +580,6 @@ void qede_update_rx_prod(struct qede_dev *edev, struct qede_rx_queue *rxq)
 
 	internal_ram_wr(rxq->hw_rxq_prod_addr, sizeof(rx_prods),
 			(u32 *)&rx_prods);
-
-	/* mmiowb is needed to synchronize doorbell writes from more than one
-	 * processor. It guarantees that the write arrives to the device before
-	 * the napi lock is released and another qede_poll is called (possibly
-	 * on another CPU). Without this barrier, the next doorbell can bypass
-	 * this doorbell. This is applicable to IA64/Altix systems.
-	 */
-	mmiowb();
 }
 
 static void qede_get_rxhash(struct sk_buff *skb, u8 bitfields, __le32 rss_hash)
diff --git a/drivers/net/ethernet/qlogic/qede/qede_ptp.c b/drivers/net/ethernet/qlogic/qede/qede_ptp.c
index 5f3f42a25361..bddb2b5982dc 100644
--- a/drivers/net/ethernet/qlogic/qede/qede_ptp.c
+++ b/drivers/net/ethernet/qlogic/qede/qede_ptp.c
@@ -490,18 +490,17 @@ int qede_ptp_enable(struct qede_dev *edev, bool init_tc)
 
 	ptp->clock = ptp_clock_register(&ptp->clock_info, &edev->pdev->dev);
 	if (IS_ERR(ptp->clock)) {
-		rc = -EINVAL;
 		DP_ERR(edev, "PTP clock registration failed\n");
+		qede_ptp_disable(edev);
+		rc = -EINVAL;
 		goto err2;
 	}
 
 	return 0;
 
-err2:
-	qede_ptp_disable(edev);
-	ptp->clock = NULL;
 err1:
 	kfree(ptp);
+err2:
 	edev->ptp = NULL;
 
 	return rc;
diff --git a/drivers/net/ethernet/qlogic/qla3xxx.c b/drivers/net/ethernet/qlogic/qla3xxx.c
index b61b88cbc0c7..457444894d80 100644
--- a/drivers/net/ethernet/qlogic/qla3xxx.c
+++ b/drivers/net/ethernet/qlogic/qla3xxx.c
@@ -1858,7 +1858,6 @@ static void ql_update_small_bufq_prod_index(struct ql3_adapter *qdev)
 		wmb();
 		writel_relaxed(qdev->small_buf_q_producer_index,
 			       &port_regs->CommonRegs.rxSmallQProducerIndex);
-		mmiowb();
 	}
 }
 
diff --git a/drivers/net/ethernet/qlogic/qlcnic/qlcnic.h b/drivers/net/ethernet/qlogic/qlcnic/qlcnic.h
index 0c443ea98479..374a4d4371f9 100644
--- a/drivers/net/ethernet/qlogic/qlcnic/qlcnic.h
+++ b/drivers/net/ethernet/qlogic/qlcnic/qlcnic.h
@@ -497,7 +497,7 @@ struct qlcnic_hardware_context {
 	u16 board_type;
 	u16 supported_type;
 
-	u16 link_speed;
+	u32 link_speed;
 	u16 link_duplex;
 	u16 link_autoneg;
 	u16 module_type;
diff --git a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_ethtool.c b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_ethtool.c
index 3b0adda7cc9c..a4cd6f2cfb86 100644
--- a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_ethtool.c
+++ b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_ethtool.c
@@ -1048,6 +1048,8 @@ int qlcnic_do_lb_test(struct qlcnic_adapter *adapter, u8 mode)
 
 	for (i = 0; i < QLCNIC_NUM_ILB_PKT; i++) {
 		skb = netdev_alloc_skb(adapter->netdev, QLCNIC_ILB_PKT_SIZE);
+		if (!skb)
+			break;
 		qlcnic_create_loopback_buff(skb->data, adapter->mac_addr);
 		skb_put(skb, QLCNIC_ILB_PKT_SIZE);
 		adapter->ahw->diag_cnt = 0;
diff --git a/drivers/net/ethernet/qlogic/qlge/qlge.h b/drivers/net/ethernet/qlogic/qlge/qlge.h
index 3e71b65a9546..ad7c5eb8a3b6 100644
--- a/drivers/net/ethernet/qlogic/qlge/qlge.h
+++ b/drivers/net/ethernet/qlogic/qlge/qlge.h
@@ -2181,7 +2181,6 @@ static inline void ql_write32(const struct ql_adapter *qdev, int reg, u32 val)
 static inline void ql_write_db_reg(u32 val, void __iomem *addr)
 {
 	writel(val, addr);
-	mmiowb();
 }
 
 /*
diff --git a/drivers/net/ethernet/qlogic/qlge/qlge_main.c b/drivers/net/ethernet/qlogic/qlge/qlge_main.c
index 07e1c623048e..6cae33072496 100644
--- a/drivers/net/ethernet/qlogic/qlge/qlge_main.c
+++ b/drivers/net/ethernet/qlogic/qlge/qlge_main.c
@@ -2695,7 +2695,6 @@ static netdev_tx_t qlge_send(struct sk_buff *skb, struct net_device *ndev)
 	wmb();
 
 	ql_write_db_reg_relaxed(tx_ring->prod_idx, tx_ring->prod_idx_db_reg);
-	mmiowb();
 	netif_printk(qdev, tx_queued, KERN_DEBUG, qdev->ndev,
 		     "tx queued, slot %d, len %d\n",
 		     tx_ring->prod_idx, skb->len);
diff --git a/drivers/net/ethernet/realtek/atp.c b/drivers/net/ethernet/realtek/atp.c
index cfb67b746595..58e0ca9093d3 100644
--- a/drivers/net/ethernet/realtek/atp.c
+++ b/drivers/net/ethernet/realtek/atp.c
@@ -482,7 +482,7 @@ static void hardware_init(struct net_device *dev)
 	write_reg_high(ioaddr, IMR, ISRh_RxErr);
 
 	lp->tx_unit_busy = 0;
-    lp->pac_cnt_in_tx_buf = 0;
+	lp->pac_cnt_in_tx_buf = 0;
 	lp->saved_tx_size = 0;
 }
 
diff --git a/drivers/net/ethernet/realtek/r8169.c b/drivers/net/ethernet/realtek/r8169.c
index c29dde064078..ed651dde6ef9 100644
--- a/drivers/net/ethernet/realtek/r8169.c
+++ b/drivers/net/ethernet/realtek/r8169.c
@@ -28,6 +28,7 @@
 #include <linux/pm_runtime.h>
 #include <linux/firmware.h>
 #include <linux/prefetch.h>
+#include <linux/pci-aspm.h>
 #include <linux/ipv6.h>
 #include <net/ip6_checksum.h>
 
@@ -678,6 +679,7 @@ struct rtl8169_private {
 		struct work_struct work;
 	} wk;
 
+	unsigned irq_enabled:1;
 	unsigned supports_gmii:1;
 	dma_addr_t counters_phys_addr;
 	struct rtl8169_counters *counters;
@@ -1293,6 +1295,7 @@ static void rtl_ack_events(struct rtl8169_private *tp, u16 bits)
 static void rtl_irq_disable(struct rtl8169_private *tp)
 {
 	RTL_W16(tp, IntrMask, 0);
+	tp->irq_enabled = 0;
 }
 
 #define RTL_EVENT_NAPI_RX	(RxOK | RxErr)
@@ -1301,6 +1304,7 @@ static void rtl_irq_disable(struct rtl8169_private *tp)
 
 static void rtl_irq_enable(struct rtl8169_private *tp)
 {
+	tp->irq_enabled = 1;
 	RTL_W16(tp, IntrMask, tp->irq_mask);
 }
 
@@ -5457,7 +5461,7 @@ static void rtl_hw_start_8168(struct rtl8169_private *tp)
 	tp->cp_cmd |= PktCntrDisable | INTT_1;
 	RTL_W16(tp, CPlusCmd, tp->cp_cmd);
 
-	RTL_W16(tp, IntrMitigate, 0x5151);
+	RTL_W16(tp, IntrMitigate, 0x5100);
 
 	/* Work around for RxFIFO overflow. */
 	if (tp->mac_version == RTL_GIGA_MAC_VER_11) {
@@ -6520,9 +6524,8 @@ static irqreturn_t rtl8169_interrupt(int irq, void *dev_instance)
 {
 	struct rtl8169_private *tp = dev_instance;
 	u16 status = RTL_R16(tp, IntrStatus);
-	u16 irq_mask = RTL_R16(tp, IntrMask);
 
-	if (status == 0xffff || !(status & irq_mask))
+	if (!tp->irq_enabled || status == 0xffff || !(status & tp->irq_mask))
 		return IRQ_NONE;
 
 	if (unlikely(status & SYSErr)) {
@@ -6540,7 +6543,7 @@ static irqreturn_t rtl8169_interrupt(int irq, void *dev_instance)
 		set_bit(RTL_FLAG_TASK_RESET_PENDING, tp->wk.flags);
 	}
 
-	if (status & RTL_EVENT_NAPI) {
+	if (status & (RTL_EVENT_NAPI | LinkChg)) {
 		rtl_irq_disable(tp);
 		napi_schedule_irqoff(&tp->napi);
 	}
@@ -7350,6 +7353,11 @@ static int rtl_init_one(struct pci_dev *pdev, const struct pci_device_id *ent)
 	if (rc)
 		return rc;
 
+	/* Disable ASPM completely as that cause random device stop working
+	 * problems as well as full system hangs for some PCIe devices users.
+	 */
+	pci_disable_link_state(pdev, PCIE_LINK_STATE_L0S | PCIE_LINK_STATE_L1);
+
 	/* enable device (incl. PCI PM wakeup and hotplug setup) */
 	rc = pcim_enable_device(pdev);
 	if (rc < 0) {
diff --git a/drivers/net/ethernet/renesas/ravb_main.c b/drivers/net/ethernet/renesas/ravb_main.c
index 8154b38c08f7..316b47741d3f 100644
--- a/drivers/net/ethernet/renesas/ravb_main.c
+++ b/drivers/net/ethernet/renesas/ravb_main.c
@@ -728,7 +728,6 @@ static irqreturn_t ravb_emac_interrupt(int irq, void *dev_id)
 
 	spin_lock(&priv->lock);
 	ravb_emac_interrupt_unlocked(ndev);
-	mmiowb();
 	spin_unlock(&priv->lock);
 	return IRQ_HANDLED;
 }
@@ -848,7 +847,6 @@ static irqreturn_t ravb_interrupt(int irq, void *dev_id)
 		result = IRQ_HANDLED;
 	}
 
-	mmiowb();
 	spin_unlock(&priv->lock);
 	return result;
 }
@@ -881,7 +879,6 @@ static irqreturn_t ravb_multi_interrupt(int irq, void *dev_id)
 		result = IRQ_HANDLED;
 	}
 
-	mmiowb();
 	spin_unlock(&priv->lock);
 	return result;
 }
@@ -898,7 +895,6 @@ static irqreturn_t ravb_dma_interrupt(int irq, void *dev_id, int q)
 	if (ravb_queue_interrupt(ndev, q))
 		result = IRQ_HANDLED;
 
-	mmiowb();
 	spin_unlock(&priv->lock);
 	return result;
 }
@@ -943,7 +939,6 @@ static int ravb_poll(struct napi_struct *napi, int budget)
 			ravb_write(ndev, ~(mask | TIS_RESERVED), TIS);
 			ravb_tx_free(ndev, q, true);
 			netif_wake_subqueue(ndev, q);
-			mmiowb();
 			spin_unlock_irqrestore(&priv->lock, flags);
 		}
 	}
@@ -959,7 +954,6 @@ static int ravb_poll(struct napi_struct *napi, int budget)
 		ravb_write(ndev, mask, RIE0);
 		ravb_write(ndev, mask, TIE);
 	}
-	mmiowb();
 	spin_unlock_irqrestore(&priv->lock, flags);
 
 	/* Receive error message handling */
@@ -1008,7 +1002,6 @@ static void ravb_adjust_link(struct net_device *ndev)
 	if (priv->no_avb_link && phydev->link)
 		ravb_rcv_snd_enable(ndev);
 
-	mmiowb();
 	spin_unlock_irqrestore(&priv->lock, flags);
 
 	if (new_state && netif_msg_link(priv))
@@ -1601,7 +1594,6 @@ static netdev_tx_t ravb_start_xmit(struct sk_buff *skb, struct net_device *ndev)
 		netif_stop_subqueue(ndev, q);
 
 exit:
-	mmiowb();
 	spin_unlock_irqrestore(&priv->lock, flags);
 	return NETDEV_TX_OK;
 
@@ -1673,7 +1665,6 @@ static void ravb_set_rx_mode(struct net_device *ndev)
 	spin_lock_irqsave(&priv->lock, flags);
 	ravb_modify(ndev, ECMR, ECMR_PRM,
 		    ndev->flags & IFF_PROMISC ? ECMR_PRM : 0);
-	mmiowb();
 	spin_unlock_irqrestore(&priv->lock, flags);
 }
 
diff --git a/drivers/net/ethernet/renesas/ravb_ptp.c b/drivers/net/ethernet/renesas/ravb_ptp.c
index dce2a40a31e3..9a42580693cb 100644
--- a/drivers/net/ethernet/renesas/ravb_ptp.c
+++ b/drivers/net/ethernet/renesas/ravb_ptp.c
@@ -196,7 +196,6 @@ static int ravb_ptp_extts(struct ptp_clock_info *ptp,
 		ravb_write(ndev, GIE_PTCS, GIE);
 	else
 		ravb_write(ndev, GID_PTCD, GID);
-	mmiowb();
 	spin_unlock_irqrestore(&priv->lock, flags);
 
 	return 0;
@@ -259,7 +258,6 @@ static int ravb_ptp_perout(struct ptp_clock_info *ptp,
 		else
 			ravb_write(ndev, GID_PTMD0, GID);
 	}
-	mmiowb();
 	spin_unlock_irqrestore(&priv->lock, flags);
 
 	return error;
@@ -331,7 +329,6 @@ void ravb_ptp_init(struct net_device *ndev, struct platform_device *pdev)
 	spin_lock_irqsave(&priv->lock, flags);
 	ravb_wait(ndev, GCCR, GCCR_TCR, GCCR_TCR_NOREQ);
 	ravb_modify(ndev, GCCR, GCCR_TCSS, GCCR_TCSS_ADJGPTP);
-	mmiowb();
 	spin_unlock_irqrestore(&priv->lock, flags);
 
 	priv->ptp.clock = ptp_clock_register(&priv->ptp.info, &pdev->dev);
diff --git a/drivers/net/ethernet/renesas/sh_eth.c b/drivers/net/ethernet/renesas/sh_eth.c
index e33af371b169..ed30aebdb941 100644
--- a/drivers/net/ethernet/renesas/sh_eth.c
+++ b/drivers/net/ethernet/renesas/sh_eth.c
@@ -2010,7 +2010,6 @@ static void sh_eth_adjust_link(struct net_device *ndev)
 	if ((mdp->cd->no_psr || mdp->no_ether_link) && phydev->link)
 		sh_eth_rcv_snd_enable(ndev);
 
-	mmiowb();
 	spin_unlock_irqrestore(&mdp->lock, flags);
 
 	if (new_state && netif_msg_link(mdp))
diff --git a/drivers/net/ethernet/sfc/falcon/io.h b/drivers/net/ethernet/sfc/falcon/io.h
index 7085ee1d5e2b..c3577643fbda 100644
--- a/drivers/net/ethernet/sfc/falcon/io.h
+++ b/drivers/net/ethernet/sfc/falcon/io.h
@@ -108,7 +108,6 @@ static inline void ef4_writeo(struct ef4_nic *efx, const ef4_oword_t *value,
 	_ef4_writed(efx, value->u32[2], reg + 8);
 	_ef4_writed(efx, value->u32[3], reg + 12);
 #endif
-	mmiowb();
 	spin_unlock_irqrestore(&efx->biu_lock, flags);
 }
 
@@ -130,7 +129,6 @@ static inline void ef4_sram_writeq(struct ef4_nic *efx, void __iomem *membase,
 	__raw_writel((__force u32)value->u32[0], membase + addr);
 	__raw_writel((__force u32)value->u32[1], membase + addr + 4);
 #endif
-	mmiowb();
 	spin_unlock_irqrestore(&efx->biu_lock, flags);
 }
 
diff --git a/drivers/net/ethernet/sfc/io.h b/drivers/net/ethernet/sfc/io.h
index 89563170af52..2774a10f44e9 100644
--- a/drivers/net/ethernet/sfc/io.h
+++ b/drivers/net/ethernet/sfc/io.h
@@ -120,7 +120,6 @@ static inline void efx_writeo(struct efx_nic *efx, const efx_oword_t *value,
 	_efx_writed(efx, value->u32[2], reg + 8);
 	_efx_writed(efx, value->u32[3], reg + 12);
 #endif
-	mmiowb();
 	spin_unlock_irqrestore(&efx->biu_lock, flags);
 }
 
@@ -142,7 +141,6 @@ static inline void efx_sram_writeq(struct efx_nic *efx, void __iomem *membase,
 	__raw_writel((__force u32)value->u32[0], membase + addr);
 	__raw_writel((__force u32)value->u32[1], membase + addr + 4);
 #endif
-	mmiowb();
 	spin_unlock_irqrestore(&efx->biu_lock, flags);
 }
 
diff --git a/drivers/net/ethernet/silan/sc92031.c b/drivers/net/ethernet/silan/sc92031.c
index c07fd594fe71..02b3962b0e63 100644
--- a/drivers/net/ethernet/silan/sc92031.c
+++ b/drivers/net/ethernet/silan/sc92031.c
@@ -251,7 +251,6 @@ enum PMConfigBits {
  * use of mdelay() at _sc92031_reset.
  * Functions prefixed with _sc92031_ must be called with the lock held;
  * functions prefixed with sc92031_ must be called without the lock held.
- * Use mmiowb() before unlocking if the hardware was written to.
  */
 
 /* Locking rules for the interrupt:
@@ -361,7 +360,6 @@ static void sc92031_disable_interrupts(struct net_device *dev)
 	/* stop interrupts */
 	iowrite32(0, port_base + IntrMask);
 	_sc92031_dummy_read(port_base);
-	mmiowb();
 
 	/* wait for any concurrent interrupt/tasklet to finish */
 	synchronize_irq(priv->pdev->irq);
@@ -379,7 +377,6 @@ static void sc92031_enable_interrupts(struct net_device *dev)
 	wmb();
 
 	iowrite32(IntrBits, port_base + IntrMask);
-	mmiowb();
 }
 
 static void _sc92031_disable_tx_rx(struct net_device *dev)
@@ -867,7 +864,6 @@ out:
 	rmb();
 
 	iowrite32(intr_mask, port_base + IntrMask);
-	mmiowb();
 
 	spin_unlock(&priv->lock);
 }
@@ -901,7 +897,6 @@ out_none:
 	rmb();
 
 	iowrite32(intr_mask, port_base + IntrMask);
-	mmiowb();
 
 	return IRQ_NONE;
 }
@@ -978,7 +973,6 @@ static netdev_tx_t sc92031_start_xmit(struct sk_buff *skb,
 	iowrite32(priv->tx_bufs_dma_addr + entry * TX_BUF_SIZE,
 			port_base + TxAddr0 + entry * 4);
 	iowrite32(tx_status, port_base + TxStatus0 + entry * 4);
-	mmiowb();
 
 	if (priv->tx_head - priv->tx_tail >= NUM_TX_DESC)
 		netif_stop_queue(dev);
@@ -1024,7 +1018,6 @@ static int sc92031_open(struct net_device *dev)
 	spin_lock_bh(&priv->lock);
 
 	_sc92031_reset(dev);
-	mmiowb();
 
 	spin_unlock_bh(&priv->lock);
 	sc92031_enable_interrupts(dev);
@@ -1060,7 +1053,6 @@ static int sc92031_stop(struct net_device *dev)
 
 	_sc92031_disable_tx_rx(dev);
 	_sc92031_tx_clear(dev);
-	mmiowb();
 
 	spin_unlock_bh(&priv->lock);
 
@@ -1081,7 +1073,6 @@ static void sc92031_set_multicast_list(struct net_device *dev)
 
 	_sc92031_set_mar(dev);
 	_sc92031_set_rx_config(dev);
-	mmiowb();
 
 	spin_unlock_bh(&priv->lock);
 }
@@ -1098,7 +1089,6 @@ static void sc92031_tx_timeout(struct net_device *dev)
 	priv->tx_timeouts++;
 
 	_sc92031_reset(dev);
-	mmiowb();
 
 	spin_unlock(&priv->lock);
 
@@ -1140,7 +1130,6 @@ sc92031_ethtool_get_link_ksettings(struct net_device *dev,
 
 	output_status = _sc92031_mii_read(port_base, MII_OutputStatus);
 	_sc92031_mii_scan(port_base);
-	mmiowb();
 
 	spin_unlock_bh(&priv->lock);
 
@@ -1311,7 +1300,6 @@ static int sc92031_ethtool_set_wol(struct net_device *dev,
 
 	priv->pm_config = pm_config;
 	iowrite32(pm_config, port_base + PMConfig);
-	mmiowb();
 
 	spin_unlock_bh(&priv->lock);
 
@@ -1337,7 +1325,6 @@ static int sc92031_ethtool_nway_reset(struct net_device *dev)
 
 out:
 	_sc92031_mii_scan(port_base);
-	mmiowb();
 
 	spin_unlock_bh(&priv->lock);
 
@@ -1530,7 +1517,6 @@ static int sc92031_suspend(struct pci_dev *pdev, pm_message_t state)
 
 	_sc92031_disable_tx_rx(dev);
 	_sc92031_tx_clear(dev);
-	mmiowb();
 
 	spin_unlock_bh(&priv->lock);
 
@@ -1555,7 +1541,6 @@ static int sc92031_resume(struct pci_dev *pdev)
 	spin_lock_bh(&priv->lock);
 
 	_sc92031_reset(dev);
-	mmiowb();
 
 	spin_unlock_bh(&priv->lock);
 	sc92031_enable_interrupts(dev);
diff --git a/drivers/net/ethernet/sis/sis900.c b/drivers/net/ethernet/sis/sis900.c
index 6073387511f8..67f9bb6e941b 100644
--- a/drivers/net/ethernet/sis/sis900.c
+++ b/drivers/net/ethernet/sis/sis900.c
@@ -730,10 +730,10 @@ static u16 sis900_default_phy(struct net_device * net_dev)
 		status = mdio_read(net_dev, phy->phy_addr, MII_STATUS);
 
 		/* Link ON & Not select default PHY & not ghost PHY */
-		 if ((status & MII_STAT_LINK) && !default_phy &&
-					(phy->phy_types != UNKNOWN))
-		 	default_phy = phy;
-		 else {
+		if ((status & MII_STAT_LINK) && !default_phy &&
+		    (phy->phy_types != UNKNOWN)) {
+			default_phy = phy;
+		} else {
 			status = mdio_read(net_dev, phy->phy_addr, MII_CONTROL);
 			mdio_write(net_dev, phy->phy_addr, MII_CONTROL,
 				status | MII_CNTL_AUTO | MII_CNTL_ISOLATE);
@@ -741,7 +741,7 @@ static u16 sis900_default_phy(struct net_device * net_dev)
 				phy_home = phy;
 			else if(phy->phy_types == LAN)
 				phy_lan = phy;
-		 }
+		}
 	}
 
 	if (!default_phy && phy_home)
diff --git a/drivers/net/ethernet/socionext/netsec.c b/drivers/net/ethernet/socionext/netsec.c
index a18149720aa2..cba5881b2746 100644
--- a/drivers/net/ethernet/socionext/netsec.c
+++ b/drivers/net/ethernet/socionext/netsec.c
@@ -673,7 +673,8 @@ static void netsec_process_tx(struct netsec_priv *priv)
 }
 
 static void *netsec_alloc_rx_data(struct netsec_priv *priv,
-				  dma_addr_t *dma_handle, u16 *desc_len)
+				  dma_addr_t *dma_handle, u16 *desc_len,
+				  bool napi)
 {
 	size_t total_len = SKB_DATA_ALIGN(sizeof(struct skb_shared_info));
 	size_t payload_len = NETSEC_RX_BUF_SZ;
@@ -682,7 +683,7 @@ static void *netsec_alloc_rx_data(struct netsec_priv *priv,
 
 	total_len += SKB_DATA_ALIGN(payload_len + NETSEC_SKB_PAD);
 
-	buf = napi_alloc_frag(total_len);
+	buf = napi ? napi_alloc_frag(total_len) : netdev_alloc_frag(total_len);
 	if (!buf)
 		return NULL;
 
@@ -765,7 +766,8 @@ static int netsec_process_rx(struct netsec_priv *priv, int budget)
 		/* allocate a fresh buffer and map it to the hardware.
 		 * This will eventually replace the old buffer in the hardware
 		 */
-		buf_addr = netsec_alloc_rx_data(priv, &dma_handle, &desc_len);
+		buf_addr = netsec_alloc_rx_data(priv, &dma_handle, &desc_len,
+						true);
 		if (unlikely(!buf_addr))
 			break;
 
@@ -1069,7 +1071,8 @@ static int netsec_setup_rx_dring(struct netsec_priv *priv)
 		void *buf;
 		u16 len;
 
-		buf = netsec_alloc_rx_data(priv, &dma_handle, &len);
+		buf = netsec_alloc_rx_data(priv, &dma_handle, &len,
+					   false);
 		if (!buf) {
 			netsec_uninit_pkt_dring(priv, NETSEC_RING_RX);
 			goto err_out;
diff --git a/drivers/net/ethernet/stmicro/stmmac/descs_com.h b/drivers/net/ethernet/stmicro/stmmac/descs_com.h
index 40d6356a7e73..3dfb07a78952 100644
--- a/drivers/net/ethernet/stmicro/stmmac/descs_com.h
+++ b/drivers/net/ethernet/stmicro/stmmac/descs_com.h
@@ -29,11 +29,13 @@
 /* Specific functions used for Ring mode */
 
 /* Enhanced descriptors */
-static inline void ehn_desc_rx_set_on_ring(struct dma_desc *p, int end)
+static inline void ehn_desc_rx_set_on_ring(struct dma_desc *p, int end,
+					   int bfsize)
 {
-	p->des1 |= cpu_to_le32((BUF_SIZE_8KiB
-			<< ERDES1_BUFFER2_SIZE_SHIFT)
-		   & ERDES1_BUFFER2_SIZE_MASK);
+	if (bfsize == BUF_SIZE_16KiB)
+		p->des1 |= cpu_to_le32((BUF_SIZE_8KiB
+				<< ERDES1_BUFFER2_SIZE_SHIFT)
+			   & ERDES1_BUFFER2_SIZE_MASK);
 
 	if (end)
 		p->des1 |= cpu_to_le32(ERDES1_END_RING);
@@ -59,11 +61,15 @@ static inline void enh_set_tx_desc_len_on_ring(struct dma_desc *p, int len)
 }
 
 /* Normal descriptors */
-static inline void ndesc_rx_set_on_ring(struct dma_desc *p, int end)
+static inline void ndesc_rx_set_on_ring(struct dma_desc *p, int end, int bfsize)
 {
-	p->des1 |= cpu_to_le32(((BUF_SIZE_2KiB - 1)
-				<< RDES1_BUFFER2_SIZE_SHIFT)
-		    & RDES1_BUFFER2_SIZE_MASK);
+	if (bfsize >= BUF_SIZE_2KiB) {
+		int bfsize2;
+
+		bfsize2 = min(bfsize - BUF_SIZE_2KiB + 1, BUF_SIZE_2KiB - 1);
+		p->des1 |= cpu_to_le32((bfsize2 << RDES1_BUFFER2_SIZE_SHIFT)
+			    & RDES1_BUFFER2_SIZE_MASK);
+	}
 
 	if (end)
 		p->des1 |= cpu_to_le32(RDES1_END_RING);
diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-stm32.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-stm32.c
index 062a600fa5a7..21428537e231 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac-stm32.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-stm32.c
@@ -333,6 +333,9 @@ static int stm32mp1_parse_data(struct stm32_dwmac *dwmac,
 	 */
 	dwmac->irq_pwr_wakeup = platform_get_irq_byname(pdev,
 							"stm32_pwr_wakeup");
+	if (dwmac->irq_pwr_wakeup == -EPROBE_DEFER)
+		return -EPROBE_DEFER;
+
 	if (!dwmac->clk_eth_ck && dwmac->irq_pwr_wakeup >= 0) {
 		err = device_init_wakeup(&pdev->dev, true);
 		if (err) {
diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac4_descs.c b/drivers/net/ethernet/stmicro/stmmac/dwmac4_descs.c
index 7fbb6a4dbf51..e061e9f5fad7 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac4_descs.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac4_descs.c
@@ -296,7 +296,7 @@ exit:
 }
 
 static void dwmac4_rd_init_rx_desc(struct dma_desc *p, int disable_rx_ic,
-				   int mode, int end)
+				   int mode, int end, int bfsize)
 {
 	dwmac4_set_rx_owner(p, disable_rx_ic);
 }
diff --git a/drivers/net/ethernet/stmicro/stmmac/dwxgmac2_descs.c b/drivers/net/ethernet/stmicro/stmmac/dwxgmac2_descs.c
index 1d858fdec997..98fa471da7c0 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwxgmac2_descs.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwxgmac2_descs.c
@@ -123,7 +123,7 @@ static int dwxgmac2_get_rx_timestamp_status(void *desc, void *next_desc,
 }
 
 static void dwxgmac2_init_rx_desc(struct dma_desc *p, int disable_rx_ic,
-				  int mode, int end)
+				  int mode, int end, int bfsize)
 {
 	dwxgmac2_set_rx_owner(p, disable_rx_ic);
 }
diff --git a/drivers/net/ethernet/stmicro/stmmac/enh_desc.c b/drivers/net/ethernet/stmicro/stmmac/enh_desc.c
index 5ef91a790f9d..5202d6ad7919 100644
--- a/drivers/net/ethernet/stmicro/stmmac/enh_desc.c
+++ b/drivers/net/ethernet/stmicro/stmmac/enh_desc.c
@@ -201,6 +201,11 @@ static int enh_desc_get_rx_status(void *data, struct stmmac_extra_stats *x,
 	if (unlikely(rdes0 & RDES0_OWN))
 		return dma_own;
 
+	if (unlikely(!(rdes0 & RDES0_LAST_DESCRIPTOR))) {
+		stats->rx_length_errors++;
+		return discard_frame;
+	}
+
 	if (unlikely(rdes0 & RDES0_ERROR_SUMMARY)) {
 		if (unlikely(rdes0 & RDES0_DESCRIPTOR_ERROR)) {
 			x->rx_desc++;
@@ -231,9 +236,10 @@ static int enh_desc_get_rx_status(void *data, struct stmmac_extra_stats *x,
 	 * It doesn't match with the information reported into the databook.
 	 * At any rate, we need to understand if the CSUM hw computation is ok
 	 * and report this info to the upper layers. */
-	ret = enh_desc_coe_rdes0(!!(rdes0 & RDES0_IPC_CSUM_ERROR),
-				 !!(rdes0 & RDES0_FRAME_TYPE),
-				 !!(rdes0 & ERDES0_RX_MAC_ADDR));
+	if (likely(ret == good_frame))
+		ret = enh_desc_coe_rdes0(!!(rdes0 & RDES0_IPC_CSUM_ERROR),
+					 !!(rdes0 & RDES0_FRAME_TYPE),
+					 !!(rdes0 & ERDES0_RX_MAC_ADDR));
 
 	if (unlikely(rdes0 & RDES0_DRIBBLING))
 		x->dribbling_bit++;
@@ -259,15 +265,19 @@ static int enh_desc_get_rx_status(void *data, struct stmmac_extra_stats *x,
 }
 
 static void enh_desc_init_rx_desc(struct dma_desc *p, int disable_rx_ic,
-				  int mode, int end)
+				  int mode, int end, int bfsize)
 {
+	int bfsize1;
+
 	p->des0 |= cpu_to_le32(RDES0_OWN);
-	p->des1 |= cpu_to_le32(BUF_SIZE_8KiB & ERDES1_BUFFER1_SIZE_MASK);
+
+	bfsize1 = min(bfsize, BUF_SIZE_8KiB);
+	p->des1 |= cpu_to_le32(bfsize1 & ERDES1_BUFFER1_SIZE_MASK);
 
 	if (mode == STMMAC_CHAIN_MODE)
 		ehn_desc_rx_set_on_chain(p);
 	else
-		ehn_desc_rx_set_on_ring(p, end);
+		ehn_desc_rx_set_on_ring(p, end, bfsize);
 
 	if (disable_rx_ic)
 		p->des1 |= cpu_to_le32(ERDES1_DISABLE_IC);
diff --git a/drivers/net/ethernet/stmicro/stmmac/hwif.h b/drivers/net/ethernet/stmicro/stmmac/hwif.h
index 92b8944f26e3..5bb00234d961 100644
--- a/drivers/net/ethernet/stmicro/stmmac/hwif.h
+++ b/drivers/net/ethernet/stmicro/stmmac/hwif.h
@@ -33,7 +33,7 @@ struct dma_extended_desc;
 struct stmmac_desc_ops {
 	/* DMA RX descriptor ring initialization */
 	void (*init_rx_desc)(struct dma_desc *p, int disable_rx_ic, int mode,
-			int end);
+			int end, int bfsize);
 	/* DMA TX descriptor ring initialization */
 	void (*init_tx_desc)(struct dma_desc *p, int mode, int end);
 	/* Invoked by the xmit function to prepare the tx descriptor */
diff --git a/drivers/net/ethernet/stmicro/stmmac/norm_desc.c b/drivers/net/ethernet/stmicro/stmmac/norm_desc.c
index de65bb29feba..6d690678c20e 100644
--- a/drivers/net/ethernet/stmicro/stmmac/norm_desc.c
+++ b/drivers/net/ethernet/stmicro/stmmac/norm_desc.c
@@ -91,8 +91,6 @@ static int ndesc_get_rx_status(void *data, struct stmmac_extra_stats *x,
 		return dma_own;
 
 	if (unlikely(!(rdes0 & RDES0_LAST_DESCRIPTOR))) {
-		pr_warn("%s: Oversized frame spanned multiple buffers\n",
-			__func__);
 		stats->rx_length_errors++;
 		return discard_frame;
 	}
@@ -135,15 +133,19 @@ static int ndesc_get_rx_status(void *data, struct stmmac_extra_stats *x,
 }
 
 static void ndesc_init_rx_desc(struct dma_desc *p, int disable_rx_ic, int mode,
-			       int end)
+			       int end, int bfsize)
 {
+	int bfsize1;
+
 	p->des0 |= cpu_to_le32(RDES0_OWN);
-	p->des1 |= cpu_to_le32((BUF_SIZE_2KiB - 1) & RDES1_BUFFER1_SIZE_MASK);
+
+	bfsize1 = min(bfsize, BUF_SIZE_2KiB - 1);
+	p->des1 |= cpu_to_le32(bfsize1 & RDES1_BUFFER1_SIZE_MASK);
 
 	if (mode == STMMAC_CHAIN_MODE)
 		ndesc_rx_set_on_chain(p, end);
 	else
-		ndesc_rx_set_on_ring(p, end);
+		ndesc_rx_set_on_ring(p, end, bfsize);
 
 	if (disable_rx_ic)
 		p->des1 |= cpu_to_le32(RDES1_DISABLE_IC);
diff --git a/drivers/net/ethernet/stmicro/stmmac/ring_mode.c b/drivers/net/ethernet/stmicro/stmmac/ring_mode.c
index d8c5bc412219..4d9bcb4d0378 100644
--- a/drivers/net/ethernet/stmicro/stmmac/ring_mode.c
+++ b/drivers/net/ethernet/stmicro/stmmac/ring_mode.c
@@ -59,7 +59,7 @@ static int jumbo_frm(void *p, struct sk_buff *skb, int csum)
 
 		desc->des3 = cpu_to_le32(des2 + BUF_SIZE_4KiB);
 		stmmac_prepare_tx_desc(priv, desc, 1, bmax, csum,
-				STMMAC_RING_MODE, 1, false, skb->len);
+				STMMAC_RING_MODE, 0, false, skb->len);
 		tx_q->tx_skbuff[entry] = NULL;
 		entry = STMMAC_GET_ENTRY(entry, DMA_TX_SIZE);
 
@@ -79,7 +79,8 @@ static int jumbo_frm(void *p, struct sk_buff *skb, int csum)
 
 		desc->des3 = cpu_to_le32(des2 + BUF_SIZE_4KiB);
 		stmmac_prepare_tx_desc(priv, desc, 0, len, csum,
-				STMMAC_RING_MODE, 1, true, skb->len);
+				STMMAC_RING_MODE, 1, !skb_is_nonlinear(skb),
+				skb->len);
 	} else {
 		des2 = dma_map_single(priv->device, skb->data,
 				      nopaged_len, DMA_TO_DEVICE);
@@ -91,7 +92,8 @@ static int jumbo_frm(void *p, struct sk_buff *skb, int csum)
 		tx_q->tx_skbuff_dma[entry].is_jumbo = true;
 		desc->des3 = cpu_to_le32(des2 + BUF_SIZE_4KiB);
 		stmmac_prepare_tx_desc(priv, desc, 1, nopaged_len, csum,
-				STMMAC_RING_MODE, 1, true, skb->len);
+				STMMAC_RING_MODE, 0, !skb_is_nonlinear(skb),
+				skb->len);
 	}
 
 	tx_q->cur_tx = entry;
@@ -111,10 +113,11 @@ static unsigned int is_jumbo_frm(int len, int enh_desc)
 
 static void refill_desc3(void *priv_ptr, struct dma_desc *p)
 {
-	struct stmmac_priv *priv = (struct stmmac_priv *)priv_ptr;
+	struct stmmac_rx_queue *rx_q = priv_ptr;
+	struct stmmac_priv *priv = rx_q->priv_data;
 
 	/* Fill DES3 in case of RING mode */
-	if (priv->dma_buf_sz >= BUF_SIZE_8KiB)
+	if (priv->dma_buf_sz == BUF_SIZE_16KiB)
 		p->des3 = cpu_to_le32(le32_to_cpu(p->des2) + BUF_SIZE_8KiB);
 }
 
diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
index 97c5e1aad88f..48712437d0da 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
@@ -1136,11 +1136,13 @@ static void stmmac_clear_rx_descriptors(struct stmmac_priv *priv, u32 queue)
 		if (priv->extend_desc)
 			stmmac_init_rx_desc(priv, &rx_q->dma_erx[i].basic,
 					priv->use_riwt, priv->mode,
-					(i == DMA_RX_SIZE - 1));
+					(i == DMA_RX_SIZE - 1),
+					priv->dma_buf_sz);
 		else
 			stmmac_init_rx_desc(priv, &rx_q->dma_rx[i],
 					priv->use_riwt, priv->mode,
-					(i == DMA_RX_SIZE - 1));
+					(i == DMA_RX_SIZE - 1),
+					priv->dma_buf_sz);
 }
 
 /**
@@ -2614,8 +2616,6 @@ static int stmmac_open(struct net_device *dev)
 	u32 chan;
 	int ret;
 
-	stmmac_check_ether_addr(priv);
-
 	if (priv->hw->pcs != STMMAC_PCS_RGMII &&
 	    priv->hw->pcs != STMMAC_PCS_TBI &&
 	    priv->hw->pcs != STMMAC_PCS_RTBI) {
@@ -3216,14 +3216,16 @@ static netdev_tx_t stmmac_xmit(struct sk_buff *skb, struct net_device *dev)
 		stmmac_prepare_tx_desc(priv, first, 1, nopaged_len,
 				csum_insertion, priv->mode, 1, last_segment,
 				skb->len);
-
-		/* The own bit must be the latest setting done when prepare the
-		 * descriptor and then barrier is needed to make sure that
-		 * all is coherent before granting the DMA engine.
-		 */
-		wmb();
+	} else {
+		stmmac_set_tx_owner(priv, first);
 	}
 
+	/* The own bit must be the latest setting done when prepare the
+	 * descriptor and then barrier is needed to make sure that
+	 * all is coherent before granting the DMA engine.
+	 */
+	wmb();
+
 	netdev_tx_sent_queue(netdev_get_tx_queue(dev, queue), skb->len);
 
 	stmmac_enable_dma_transmission(priv, priv->ioaddr);
@@ -3350,9 +3352,8 @@ static int stmmac_rx(struct stmmac_priv *priv, int limit, u32 queue)
 {
 	struct stmmac_rx_queue *rx_q = &priv->rx_queue[queue];
 	struct stmmac_channel *ch = &priv->channel[queue];
-	unsigned int entry = rx_q->cur_rx;
+	unsigned int next_entry = rx_q->cur_rx;
 	int coe = priv->hw->rx_csum;
-	unsigned int next_entry;
 	unsigned int count = 0;
 	bool xmac;
 
@@ -3370,10 +3371,12 @@ static int stmmac_rx(struct stmmac_priv *priv, int limit, u32 queue)
 		stmmac_display_ring(priv, rx_head, DMA_RX_SIZE, true);
 	}
 	while (count < limit) {
-		int status;
+		int entry, status;
 		struct dma_desc *p;
 		struct dma_desc *np;
 
+		entry = next_entry;
+
 		if (priv->extend_desc)
 			p = (struct dma_desc *)(rx_q->dma_erx + entry);
 		else
@@ -3429,11 +3432,12 @@ static int stmmac_rx(struct stmmac_priv *priv, int limit, u32 queue)
 			 *  ignored
 			 */
 			if (frame_len > priv->dma_buf_sz) {
-				netdev_err(priv->dev,
-					   "len %d larger than size (%d)\n",
-					   frame_len, priv->dma_buf_sz);
+				if (net_ratelimit())
+					netdev_err(priv->dev,
+						   "len %d larger than size (%d)\n",
+						   frame_len, priv->dma_buf_sz);
 				priv->dev->stats.rx_length_errors++;
-				break;
+				continue;
 			}
 
 			/* ACS is set; GMAC core strips PAD/FCS for IEEE 802.3
@@ -3468,7 +3472,7 @@ static int stmmac_rx(struct stmmac_priv *priv, int limit, u32 queue)
 						dev_warn(priv->device,
 							 "packet dropped\n");
 					priv->dev->stats.rx_dropped++;
-					break;
+					continue;
 				}
 
 				dma_sync_single_for_cpu(priv->device,
@@ -3488,11 +3492,12 @@ static int stmmac_rx(struct stmmac_priv *priv, int limit, u32 queue)
 			} else {
 				skb = rx_q->rx_skbuff[entry];
 				if (unlikely(!skb)) {
-					netdev_err(priv->dev,
-						   "%s: Inconsistent Rx chain\n",
-						   priv->dev->name);
+					if (net_ratelimit())
+						netdev_err(priv->dev,
+							   "%s: Inconsistent Rx chain\n",
+							   priv->dev->name);
 					priv->dev->stats.rx_dropped++;
-					break;
+					continue;
 				}
 				prefetch(skb->data - NET_IP_ALIGN);
 				rx_q->rx_skbuff[entry] = NULL;
@@ -3527,7 +3532,6 @@ static int stmmac_rx(struct stmmac_priv *priv, int limit, u32 queue)
 			priv->dev->stats.rx_packets++;
 			priv->dev->stats.rx_bytes += frame_len;
 		}
-		entry = next_entry;
 	}
 
 	stmmac_rx_refill(priv, queue);
@@ -4297,6 +4301,8 @@ int stmmac_dvr_probe(struct device *device,
 	if (ret)
 		goto error_hw_init;
 
+	stmmac_check_ether_addr(priv);
+
 	/* Configure real RX and TX queues */
 	netif_set_real_num_rx_queues(ndev, priv->plat->rx_queues_to_use);
 	netif_set_real_num_tx_queues(ndev, priv->plat->tx_queues_to_use);
diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_pci.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_pci.c
index d819e8eaba12..26db6aa002d1 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_pci.c
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_pci.c
@@ -159,6 +159,12 @@ static const struct dmi_system_id quark_pci_dmi[] = {
 		},
 		.driver_data = (void *)&galileo_stmmac_dmi_data,
 	},
+	/*
+	 * There are 2 types of SIMATIC IOT2000: IOT2020 and IOT2040.
+	 * The asset tag "6ES7647-0AA00-0YA2" is only for IOT2020 which
+	 * has only one pci network device while other asset tags are
+	 * for IOT2040 which has two.
+	 */
 	{
 		.matches = {
 			DMI_EXACT_MATCH(DMI_BOARD_NAME, "SIMATIC IOT2000"),
@@ -170,8 +176,6 @@ static const struct dmi_system_id quark_pci_dmi[] = {
 	{
 		.matches = {
 			DMI_EXACT_MATCH(DMI_BOARD_NAME, "SIMATIC IOT2000"),
-			DMI_EXACT_MATCH(DMI_BOARD_ASSET_TAG,
-					"6ES7647-0AA00-1YA2"),
 		},
 		.driver_data = (void *)&iot2040_stmmac_dmi_data,
 	},
diff --git a/drivers/net/ethernet/ti/netcp_ethss.c b/drivers/net/ethernet/ti/netcp_ethss.c
index 5174d318901e..0a920c5936b2 100644
--- a/drivers/net/ethernet/ti/netcp_ethss.c
+++ b/drivers/net/ethernet/ti/netcp_ethss.c
@@ -3657,12 +3657,16 @@ static int gbe_probe(struct netcp_device *netcp_device, struct device *dev,
 
 	ret = netcp_txpipe_init(&gbe_dev->tx_pipe, netcp_device,
 				gbe_dev->dma_chan_name, gbe_dev->tx_queue_id);
-	if (ret)
+	if (ret) {
+		of_node_put(interfaces);
 		return ret;
+	}
 
 	ret = netcp_txpipe_open(&gbe_dev->tx_pipe);
-	if (ret)
+	if (ret) {
+		of_node_put(interfaces);
 		return ret;
+	}
 
 	/* Create network interfaces */
 	INIT_LIST_HEAD(&gbe_dev->gbe_intf_head);
diff --git a/drivers/net/ethernet/via/via-rhine.c b/drivers/net/ethernet/via/via-rhine.c
index 33949248c829..ab55416a10fa 100644
--- a/drivers/net/ethernet/via/via-rhine.c
+++ b/drivers/net/ethernet/via/via-rhine.c
@@ -571,7 +571,6 @@ static void rhine_ack_events(struct rhine_private *rp, u32 mask)
 	if (rp->quirks & rqStatusWBRace)
 		iowrite8(mask >> 16, ioaddr + IntrStatus2);
 	iowrite16(mask, ioaddr + IntrStatus);
-	mmiowb();
 }
 
 /*
@@ -863,7 +862,6 @@ static int rhine_napipoll(struct napi_struct *napi, int budget)
 	if (work_done < budget) {
 		napi_complete_done(napi, work_done);
 		iowrite16(enable_mask, ioaddr + IntrEnable);
-		mmiowb();
 	}
 	return work_done;
 }
@@ -1893,7 +1891,6 @@ static netdev_tx_t rhine_start_tx(struct sk_buff *skb,
 static void rhine_irq_disable(struct rhine_private *rp)
 {
 	iowrite16(0x0000, rp->base + IntrEnable);
-	mmiowb();
 }
 
 /* The interrupt handler does all of the Rx thread work and cleans up
diff --git a/drivers/net/ethernet/wiznet/w5100.c b/drivers/net/ethernet/wiznet/w5100.c
index d8ba512f166a..1713c2d2dccf 100644
--- a/drivers/net/ethernet/wiznet/w5100.c
+++ b/drivers/net/ethernet/wiznet/w5100.c
@@ -219,7 +219,6 @@ static inline int __w5100_write_direct(struct net_device *ndev, u32 addr,
 static inline int w5100_write_direct(struct net_device *ndev, u32 addr, u8 data)
 {
 	__w5100_write_direct(ndev, addr, data);
-	mmiowb();
 
 	return 0;
 }
@@ -236,7 +235,6 @@ static int w5100_write16_direct(struct net_device *ndev, u32 addr, u16 data)
 {
 	__w5100_write_direct(ndev, addr, data >> 8);
 	__w5100_write_direct(ndev, addr + 1, data);
-	mmiowb();
 
 	return 0;
 }
@@ -260,8 +258,6 @@ static int w5100_writebulk_direct(struct net_device *ndev, u32 addr,
 	for (i = 0; i < len; i++, addr++)
 		__w5100_write_direct(ndev, addr, *buf++);
 
-	mmiowb();
-
 	return 0;
 }
 
@@ -375,7 +371,6 @@ static int w5100_readbulk_indirect(struct net_device *ndev, u32 addr, u8 *buf,
 	for (i = 0; i < len; i++)
 		*buf++ = w5100_read_direct(ndev, W5100_IDM_DR);
 
-	mmiowb();
 	spin_unlock_irqrestore(&mmio_priv->reg_lock, flags);
 
 	return 0;
@@ -394,7 +389,6 @@ static int w5100_writebulk_indirect(struct net_device *ndev, u32 addr,
 	for (i = 0; i < len; i++)
 		__w5100_write_direct(ndev, W5100_IDM_DR, *buf++);
 
-	mmiowb();
 	spin_unlock_irqrestore(&mmio_priv->reg_lock, flags);
 
 	return 0;
diff --git a/drivers/net/ethernet/wiznet/w5300.c b/drivers/net/ethernet/wiznet/w5300.c
index f9da5d6172e3..3f03eecc0479 100644
--- a/drivers/net/ethernet/wiznet/w5300.c
+++ b/drivers/net/ethernet/wiznet/w5300.c
@@ -141,7 +141,6 @@ static u16 w5300_read_indirect(struct w5300_priv *priv, u16 addr)
 
 	spin_lock_irqsave(&priv->reg_lock, flags);
 	w5300_write_direct(priv, W5300_IDM_AR, addr);
-	mmiowb();
 	data = w5300_read_direct(priv, W5300_IDM_DR);
 	spin_unlock_irqrestore(&priv->reg_lock, flags);
 
@@ -154,9 +153,7 @@ static void w5300_write_indirect(struct w5300_priv *priv, u16 addr, u16 data)
 
 	spin_lock_irqsave(&priv->reg_lock, flags);
 	w5300_write_direct(priv, W5300_IDM_AR, addr);
-	mmiowb();
 	w5300_write_direct(priv, W5300_IDM_DR, data);
-	mmiowb();
 	spin_unlock_irqrestore(&priv->reg_lock, flags);
 }
 
@@ -192,7 +189,6 @@ static int w5300_command(struct w5300_priv *priv, u16 cmd)
 	unsigned long timeout = jiffies + msecs_to_jiffies(100);
 
 	w5300_write(priv, W5300_S0_CR, cmd);
-	mmiowb();
 
 	while (w5300_read(priv, W5300_S0_CR) != 0) {
 		if (time_after(jiffies, timeout))
@@ -241,18 +237,15 @@ static void w5300_write_macaddr(struct w5300_priv *priv)
 	w5300_write(priv, W5300_SHARH,
 		      ndev->dev_addr[4] << 8 |
 		      ndev->dev_addr[5]);
-	mmiowb();
 }
 
 static void w5300_hw_reset(struct w5300_priv *priv)
 {
 	w5300_write_direct(priv, W5300_MR, MR_RST);
-	mmiowb();
 	mdelay(5);
 	w5300_write_direct(priv, W5300_MR, priv->indirect ?
 				 MR_WDF(7) | MR_PB | MR_IND :
 				 MR_WDF(7) | MR_PB);
-	mmiowb();
 	w5300_write(priv, W5300_IMR, 0);
 	w5300_write_macaddr(priv);
 
@@ -264,24 +257,20 @@ static void w5300_hw_reset(struct w5300_priv *priv)
 	w5300_write32(priv, W5300_TMSRL, 64 << 24);
 	w5300_write32(priv, W5300_TMSRH, 0);
 	w5300_write(priv, W5300_MTYPE, 0x00ff);
-	mmiowb();
 }
 
 static void w5300_hw_start(struct w5300_priv *priv)
 {
 	w5300_write(priv, W5300_S0_MR, priv->promisc ?
 			  S0_MR_MACRAW : S0_MR_MACRAW_MF);
-	mmiowb();
 	w5300_command(priv, S0_CR_OPEN);
 	w5300_write(priv, W5300_S0_IMR, S0_IR_RECV | S0_IR_SENDOK);
 	w5300_write(priv, W5300_IMR, IR_S0);
-	mmiowb();
 }
 
 static void w5300_hw_close(struct w5300_priv *priv)
 {
 	w5300_write(priv, W5300_IMR, 0);
-	mmiowb();
 	w5300_command(priv, S0_CR_CLOSE);
 }
 
@@ -372,7 +361,6 @@ static netdev_tx_t w5300_start_tx(struct sk_buff *skb, struct net_device *ndev)
 	netif_stop_queue(ndev);
 
 	w5300_write_frame(priv, skb->data, skb->len);
-	mmiowb();
 	ndev->stats.tx_packets++;
 	ndev->stats.tx_bytes += skb->len;
 	dev_kfree_skb(skb);
@@ -419,7 +407,6 @@ static int w5300_napi_poll(struct napi_struct *napi, int budget)
 	if (rx_count < budget) {
 		napi_complete_done(napi, rx_count);
 		w5300_write(priv, W5300_IMR, IR_S0);
-		mmiowb();
 	}
 
 	return rx_count;
@@ -434,7 +421,6 @@ static irqreturn_t w5300_interrupt(int irq, void *ndev_instance)
 	if (!ir)
 		return IRQ_NONE;
 	w5300_write(priv, W5300_S0_IR, ir);
-	mmiowb();
 
 	if (ir & S0_IR_SENDOK) {
 		netif_dbg(priv, tx_done, ndev, "tx done\n");
@@ -444,7 +430,6 @@ static irqreturn_t w5300_interrupt(int irq, void *ndev_instance)
 	if (ir & S0_IR_RECV) {
 		if (napi_schedule_prep(&priv->napi)) {
 			w5300_write(priv, W5300_IMR, 0);
-			mmiowb();
 			__napi_schedule(&priv->napi);
 		}
 	}
diff --git a/drivers/net/ethernet/xilinx/xilinx_axienet_main.c b/drivers/net/ethernet/xilinx/xilinx_axienet_main.c
index ec7e7ec24ff9..4041c75997ba 100644
--- a/drivers/net/ethernet/xilinx/xilinx_axienet_main.c
+++ b/drivers/net/ethernet/xilinx/xilinx_axienet_main.c
@@ -1575,12 +1575,14 @@ static int axienet_probe(struct platform_device *pdev)
 	ret = of_address_to_resource(np, 0, &dmares);
 	if (ret) {
 		dev_err(&pdev->dev, "unable to get DMA resource\n");
+		of_node_put(np);
 		goto free_netdev;
 	}
 	lp->dma_regs = devm_ioremap_resource(&pdev->dev, &dmares);
 	if (IS_ERR(lp->dma_regs)) {
 		dev_err(&pdev->dev, "could not map DMA regs\n");
 		ret = PTR_ERR(lp->dma_regs);
+		of_node_put(np);
 		goto free_netdev;
 	}
 	lp->rx_irq = irq_of_parse_and_map(np, 1);
diff --git a/drivers/net/hyperv/hyperv_net.h b/drivers/net/hyperv/hyperv_net.h
index e859ae2e42d5..49f41b64077b 100644
--- a/drivers/net/hyperv/hyperv_net.h
+++ b/drivers/net/hyperv/hyperv_net.h
@@ -987,6 +987,7 @@ struct netvsc_device {
 
 	wait_queue_head_t wait_drain;
 	bool destroy;
+	bool tx_disable; /* if true, do not wake up queue again */
 
 	/* Receive buffer allocated by us but manages by NetVSP */
 	void *recv_buf;
diff --git a/drivers/net/hyperv/netvsc.c b/drivers/net/hyperv/netvsc.c
index 813d195bbd57..e0dce373cdd9 100644
--- a/drivers/net/hyperv/netvsc.c
+++ b/drivers/net/hyperv/netvsc.c
@@ -110,6 +110,7 @@ static struct netvsc_device *alloc_net_device(void)
 
 	init_waitqueue_head(&net_device->wait_drain);
 	net_device->destroy = false;
+	net_device->tx_disable = false;
 
 	net_device->max_pkt = RNDIS_MAX_PKT_DEFAULT;
 	net_device->pkt_align = RNDIS_PKT_ALIGN_DEFAULT;
@@ -719,7 +720,7 @@ static void netvsc_send_tx_complete(struct net_device *ndev,
 	} else {
 		struct netdev_queue *txq = netdev_get_tx_queue(ndev, q_idx);
 
-		if (netif_tx_queue_stopped(txq) &&
+		if (netif_tx_queue_stopped(txq) && !net_device->tx_disable &&
 		    (hv_get_avail_to_write_percent(&channel->outbound) >
 		     RING_AVAIL_PERCENT_HIWATER || queue_sends < 1)) {
 			netif_tx_wake_queue(txq);
@@ -874,7 +875,8 @@ static inline int netvsc_send_pkt(
 	} else if (ret == -EAGAIN) {
 		netif_tx_stop_queue(txq);
 		ndev_ctx->eth_stats.stop_queue++;
-		if (atomic_read(&nvchan->queue_sends) < 1) {
+		if (atomic_read(&nvchan->queue_sends) < 1 &&
+		    !net_device->tx_disable) {
 			netif_tx_wake_queue(txq);
 			ndev_ctx->eth_stats.wake_queue++;
 			ret = -ENOSPC;
diff --git a/drivers/net/hyperv/netvsc_drv.c b/drivers/net/hyperv/netvsc_drv.c
index cf4897043e83..b20fb0fb595b 100644
--- a/drivers/net/hyperv/netvsc_drv.c
+++ b/drivers/net/hyperv/netvsc_drv.c
@@ -109,6 +109,15 @@ static void netvsc_set_rx_mode(struct net_device *net)
 	rcu_read_unlock();
 }
 
+static void netvsc_tx_enable(struct netvsc_device *nvscdev,
+			     struct net_device *ndev)
+{
+	nvscdev->tx_disable = false;
+	virt_wmb(); /* ensure queue wake up mechanism is on */
+
+	netif_tx_wake_all_queues(ndev);
+}
+
 static int netvsc_open(struct net_device *net)
 {
 	struct net_device_context *ndev_ctx = netdev_priv(net);
@@ -129,7 +138,7 @@ static int netvsc_open(struct net_device *net)
 	rdev = nvdev->extension;
 	if (!rdev->link_state) {
 		netif_carrier_on(net);
-		netif_tx_wake_all_queues(net);
+		netvsc_tx_enable(nvdev, net);
 	}
 
 	if (vf_netdev) {
@@ -184,6 +193,17 @@ static int netvsc_wait_until_empty(struct netvsc_device *nvdev)
 	}
 }
 
+static void netvsc_tx_disable(struct netvsc_device *nvscdev,
+			      struct net_device *ndev)
+{
+	if (nvscdev) {
+		nvscdev->tx_disable = true;
+		virt_wmb(); /* ensure txq will not wake up after stop */
+	}
+
+	netif_tx_disable(ndev);
+}
+
 static int netvsc_close(struct net_device *net)
 {
 	struct net_device_context *net_device_ctx = netdev_priv(net);
@@ -192,7 +212,7 @@ static int netvsc_close(struct net_device *net)
 	struct netvsc_device *nvdev = rtnl_dereference(net_device_ctx->nvdev);
 	int ret;
 
-	netif_tx_disable(net);
+	netvsc_tx_disable(nvdev, net);
 
 	/* No need to close rndis filter if it is removed already */
 	if (!nvdev)
@@ -920,7 +940,7 @@ static int netvsc_detach(struct net_device *ndev,
 
 	/* If device was up (receiving) then shutdown */
 	if (netif_running(ndev)) {
-		netif_tx_disable(ndev);
+		netvsc_tx_disable(nvdev, ndev);
 
 		ret = rndis_filter_close(nvdev);
 		if (ret) {
@@ -1908,7 +1928,7 @@ static void netvsc_link_change(struct work_struct *w)
 		if (rdev->link_state) {
 			rdev->link_state = false;
 			netif_carrier_on(net);
-			netif_tx_wake_all_queues(net);
+			netvsc_tx_enable(net_device, net);
 		} else {
 			notify = true;
 		}
@@ -1918,7 +1938,7 @@ static void netvsc_link_change(struct work_struct *w)
 		if (!rdev->link_state) {
 			rdev->link_state = true;
 			netif_carrier_off(net);
-			netif_tx_stop_all_queues(net);
+			netvsc_tx_disable(net_device, net);
 		}
 		kfree(event);
 		break;
@@ -1927,7 +1947,7 @@ static void netvsc_link_change(struct work_struct *w)
 		if (!rdev->link_state) {
 			rdev->link_state = true;
 			netif_carrier_off(net);
-			netif_tx_stop_all_queues(net);
+			netvsc_tx_disable(net_device, net);
 			event->event = RNDIS_STATUS_MEDIA_CONNECT;
 			spin_lock_irqsave(&ndev_ctx->lock, flags);
 			list_add(&event->list, &ndev_ctx->reconfig_events);
diff --git a/drivers/net/ieee802154/adf7242.c b/drivers/net/ieee802154/adf7242.c
index cd1d8faccca5..cd6b95e673a5 100644
--- a/drivers/net/ieee802154/adf7242.c
+++ b/drivers/net/ieee802154/adf7242.c
@@ -1268,6 +1268,10 @@ static int adf7242_probe(struct spi_device *spi)
 	INIT_DELAYED_WORK(&lp->work, adf7242_rx_cal_work);
 	lp->wqueue = alloc_ordered_workqueue(dev_name(&spi->dev),
 					     WQ_MEM_RECLAIM);
+	if (unlikely(!lp->wqueue)) {
+		ret = -ENOMEM;
+		goto err_hw_init;
+	}
 
 	ret = adf7242_hw_init(lp);
 	if (ret)
diff --git a/drivers/net/ieee802154/mac802154_hwsim.c b/drivers/net/ieee802154/mac802154_hwsim.c
index b6743f03dce0..3b88846de31b 100644
--- a/drivers/net/ieee802154/mac802154_hwsim.c
+++ b/drivers/net/ieee802154/mac802154_hwsim.c
@@ -324,7 +324,7 @@ static int hwsim_get_radio_nl(struct sk_buff *msg, struct genl_info *info)
 			goto out_err;
 		}
 
-		genlmsg_reply(skb, info);
+		res = genlmsg_reply(skb, info);
 		break;
 	}
 
diff --git a/drivers/net/ieee802154/mcr20a.c b/drivers/net/ieee802154/mcr20a.c
index c589f5ae75bb..8bb53ec8d9cf 100644
--- a/drivers/net/ieee802154/mcr20a.c
+++ b/drivers/net/ieee802154/mcr20a.c
@@ -533,6 +533,8 @@ mcr20a_start(struct ieee802154_hw *hw)
 	dev_dbg(printdev(lp), "no slotted operation\n");
 	ret = regmap_update_bits(lp->regmap_dar, DAR_PHY_CTRL1,
 				 DAR_PHY_CTRL1_SLOTTED, 0x0);
+	if (ret < 0)
+		return ret;
 
 	/* enable irq */
 	enable_irq(lp->spi->irq);
@@ -540,11 +542,15 @@ mcr20a_start(struct ieee802154_hw *hw)
 	/* Unmask SEQ interrupt */
 	ret = regmap_update_bits(lp->regmap_dar, DAR_PHY_CTRL2,
 				 DAR_PHY_CTRL2_SEQMSK, 0x0);
+	if (ret < 0)
+		return ret;
 
 	/* Start the RX sequence */
 	dev_dbg(printdev(lp), "start the RX sequence\n");
 	ret = regmap_update_bits(lp->regmap_dar, DAR_PHY_CTRL1,
 				 DAR_PHY_CTRL1_XCVSEQ_MASK, MCR20A_XCVSEQ_RX);
+	if (ret < 0)
+		return ret;
 
 	return 0;
 }
diff --git a/drivers/net/phy/Kconfig b/drivers/net/phy/Kconfig
index 071869db44cf..520657945b82 100644
--- a/drivers/net/phy/Kconfig
+++ b/drivers/net/phy/Kconfig
@@ -7,6 +7,8 @@ menuconfig MDIO_DEVICE
 	help
 	  MDIO devices and driver infrastructure code.
 
+if MDIO_DEVICE
+
 config MDIO_BUS
 	tristate
 	default m if PHYLIB=m
@@ -179,6 +181,7 @@ config MDIO_XGENE
 	  APM X-Gene SoC's.
 
 endif
+endif
 
 config PHYLINK
 	tristate
diff --git a/drivers/net/phy/broadcom.c b/drivers/net/phy/broadcom.c
index 9605d4fe540b..cb86a3e90c7d 100644
--- a/drivers/net/phy/broadcom.c
+++ b/drivers/net/phy/broadcom.c
@@ -323,6 +323,19 @@ static int bcm54xx_config_init(struct phy_device *phydev)
 
 	bcm54xx_phydsp_config(phydev);
 
+	/* Encode link speed into LED1 and LED3 pair (green/amber).
+	 * Also flash these two LEDs on activity. This means configuring
+	 * them for MULTICOLOR and encoding link/activity into them.
+	 */
+	val = BCM5482_SHD_LEDS1_LED1(BCM_LED_SRC_MULTICOLOR1) |
+		BCM5482_SHD_LEDS1_LED3(BCM_LED_SRC_MULTICOLOR1);
+	bcm_phy_write_shadow(phydev, BCM5482_SHD_LEDS1, val);
+
+	val = BCM_LED_MULTICOLOR_IN_PHASE |
+		BCM5482_SHD_LEDS1_LED1(BCM_LED_MULTICOLOR_LINK_ACT) |
+		BCM5482_SHD_LEDS1_LED3(BCM_LED_MULTICOLOR_LINK_ACT);
+	bcm_phy_write_exp(phydev, BCM_EXP_MULTICOLOR, val);
+
 	return 0;
 }
 
diff --git a/drivers/net/phy/dp83822.c b/drivers/net/phy/dp83822.c
index bbd8c22067f3..97d45bd5b38e 100644
--- a/drivers/net/phy/dp83822.c
+++ b/drivers/net/phy/dp83822.c
@@ -15,6 +15,8 @@
 #include <linux/netdevice.h>
 
 #define DP83822_PHY_ID	        0x2000a240
+#define DP83825I_PHY_ID		0x2000a150
+
 #define DP83822_DEVADDR		0x1f
 
 #define MII_DP83822_PHYSCR	0x11
@@ -304,26 +306,30 @@ static int dp83822_resume(struct phy_device *phydev)
 	return 0;
 }
 
+#define DP83822_PHY_DRIVER(_id, _name)				\
+	{							\
+		PHY_ID_MATCH_MODEL(_id),			\
+		.name		= (_name),			\
+		.features	= PHY_BASIC_FEATURES,		\
+		.soft_reset	= dp83822_phy_reset,		\
+		.config_init	= dp83822_config_init,		\
+		.get_wol = dp83822_get_wol,			\
+		.set_wol = dp83822_set_wol,			\
+		.ack_interrupt = dp83822_ack_interrupt,		\
+		.config_intr = dp83822_config_intr,		\
+		.suspend = dp83822_suspend,			\
+		.resume = dp83822_resume,			\
+	}
+
 static struct phy_driver dp83822_driver[] = {
-	{
-		.phy_id = DP83822_PHY_ID,
-		.phy_id_mask = 0xfffffff0,
-		.name = "TI DP83822",
-		.features = PHY_BASIC_FEATURES,
-		.config_init = dp83822_config_init,
-		.soft_reset = dp83822_phy_reset,
-		.get_wol = dp83822_get_wol,
-		.set_wol = dp83822_set_wol,
-		.ack_interrupt = dp83822_ack_interrupt,
-		.config_intr = dp83822_config_intr,
-		.suspend = dp83822_suspend,
-		.resume = dp83822_resume,
-	 },
+	DP83822_PHY_DRIVER(DP83822_PHY_ID, "TI DP83822"),
+	DP83822_PHY_DRIVER(DP83825I_PHY_ID, "TI DP83825I"),
 };
 module_phy_driver(dp83822_driver);
 
 static struct mdio_device_id __maybe_unused dp83822_tbl[] = {
 	{ DP83822_PHY_ID, 0xfffffff0 },
+	{ DP83825I_PHY_ID, 0xfffffff0 },
 	{ },
 };
 MODULE_DEVICE_TABLE(mdio, dp83822_tbl);
diff --git a/drivers/net/phy/marvell.c b/drivers/net/phy/marvell.c
index 3ccba37bd6dd..f76c4048b978 100644
--- a/drivers/net/phy/marvell.c
+++ b/drivers/net/phy/marvell.c
@@ -1489,9 +1489,10 @@ static int marvell_get_sset_count(struct phy_device *phydev)
 
 static void marvell_get_strings(struct phy_device *phydev, u8 *data)
 {
+	int count = marvell_get_sset_count(phydev);
 	int i;
 
-	for (i = 0; i < ARRAY_SIZE(marvell_hw_stats); i++) {
+	for (i = 0; i < count; i++) {
 		strlcpy(data + i * ETH_GSTRING_LEN,
 			marvell_hw_stats[i].string, ETH_GSTRING_LEN);
 	}
@@ -1519,9 +1520,10 @@ static u64 marvell_get_stat(struct phy_device *phydev, int i)
 static void marvell_get_stats(struct phy_device *phydev,
 			      struct ethtool_stats *stats, u64 *data)
 {
+	int count = marvell_get_sset_count(phydev);
 	int i;
 
-	for (i = 0; i < ARRAY_SIZE(marvell_hw_stats); i++)
+	for (i = 0; i < count; i++)
 		data[i] = marvell_get_stat(phydev, i);
 }
 
diff --git a/drivers/net/phy/meson-gxl.c b/drivers/net/phy/meson-gxl.c
index a238388eb1a5..0eec2913c289 100644
--- a/drivers/net/phy/meson-gxl.c
+++ b/drivers/net/phy/meson-gxl.c
@@ -201,6 +201,7 @@ static int meson_gxl_ack_interrupt(struct phy_device *phydev)
 static int meson_gxl_config_intr(struct phy_device *phydev)
 {
 	u16 val;
+	int ret;
 
 	if (phydev->interrupts == PHY_INTERRUPT_ENABLED) {
 		val = INTSRC_ANEG_PR
@@ -213,6 +214,11 @@ static int meson_gxl_config_intr(struct phy_device *phydev)
 		val = 0;
 	}
 
+	/* Ack any pending IRQ */
+	ret = meson_gxl_ack_interrupt(phydev);
+	if (ret)
+		return ret;
+
 	return phy_write(phydev, INTSRC_MASK, val);
 }
 
diff --git a/drivers/net/phy/phy_device.c b/drivers/net/phy/phy_device.c
index 49fdd1ee798e..77068c545de0 100644
--- a/drivers/net/phy/phy_device.c
+++ b/drivers/net/phy/phy_device.c
@@ -1831,7 +1831,7 @@ int genphy_soft_reset(struct phy_device *phydev)
 {
 	int ret;
 
-	ret = phy_write(phydev, MII_BMCR, BMCR_RESET);
+	ret = phy_set_bits(phydev, MII_BMCR, BMCR_RESET);
 	if (ret < 0)
 		return ret;
 
diff --git a/drivers/net/phy/spi_ks8995.c b/drivers/net/phy/spi_ks8995.c
index 92b64e254b44..7475cef17cf7 100644
--- a/drivers/net/phy/spi_ks8995.c
+++ b/drivers/net/phy/spi_ks8995.c
@@ -159,6 +159,14 @@ static const struct spi_device_id ks8995_id[] = {
 };
 MODULE_DEVICE_TABLE(spi, ks8995_id);
 
+static const struct of_device_id ks8895_spi_of_match[] = {
+        { .compatible = "micrel,ks8995" },
+        { .compatible = "micrel,ksz8864" },
+        { .compatible = "micrel,ksz8795" },
+        { },
+ };
+MODULE_DEVICE_TABLE(of, ks8895_spi_of_match);
+
 static inline u8 get_chip_id(u8 val)
 {
 	return (val >> ID1_CHIPID_S) & ID1_CHIPID_M;
@@ -526,6 +534,7 @@ static int ks8995_remove(struct spi_device *spi)
 static struct spi_driver ks8995_driver = {
 	.driver = {
 		.name	    = "spi-ks8995",
+		.of_match_table = of_match_ptr(ks8895_spi_of_match),
 	},
 	.probe	  = ks8995_probe,
 	.remove	  = ks8995_remove,
diff --git a/drivers/net/ppp/ppp_mppe.c b/drivers/net/ppp/ppp_mppe.c
index 7ccdc62c6052..ff61dd8748de 100644
--- a/drivers/net/ppp/ppp_mppe.c
+++ b/drivers/net/ppp/ppp_mppe.c
@@ -222,7 +222,6 @@ static void *mppe_alloc(unsigned char *options, int optlen)
 		goto out_free;
 	}
 	state->sha1->tfm = shash;
-	state->sha1->flags = 0;
 
 	digestsize = crypto_shash_digestsize(shash);
 	if (digestsize < MPPE_MAX_KEY_LEN)
diff --git a/drivers/net/slip/slhc.c b/drivers/net/slip/slhc.c
index f4e93f5fc204..ea90db3c7705 100644
--- a/drivers/net/slip/slhc.c
+++ b/drivers/net/slip/slhc.c
@@ -153,7 +153,7 @@ out_fail:
 void
 slhc_free(struct slcompress *comp)
 {
-	if ( comp == NULLSLCOMPR )
+	if ( IS_ERR_OR_NULL(comp) )
 		return;
 
 	if ( comp->tstate != NULLSLSTATE )
diff --git a/drivers/net/team/team.c b/drivers/net/team/team.c
index 6ed96fdfd96d..16963f7a88f7 100644
--- a/drivers/net/team/team.c
+++ b/drivers/net/team/team.c
@@ -1156,6 +1156,13 @@ static int team_port_add(struct team *team, struct net_device *port_dev,
 		return -EINVAL;
 	}
 
+	if (netdev_has_upper_dev(dev, port_dev)) {
+		NL_SET_ERR_MSG(extack, "Device is already an upper device of the team interface");
+		netdev_err(dev, "Device %s is already an upper device of the team interface\n",
+			   portname);
+		return -EBUSY;
+	}
+
 	if (port_dev->features & NETIF_F_VLAN_CHALLENGED &&
 	    vlan_uses_dev(dev)) {
 		NL_SET_ERR_MSG(extack, "Device is VLAN challenged and team device has VLAN set up");
@@ -1246,6 +1253,23 @@ static int team_port_add(struct team *team, struct net_device *port_dev,
 		goto err_option_port_add;
 	}
 
+	/* set promiscuity level to new slave */
+	if (dev->flags & IFF_PROMISC) {
+		err = dev_set_promiscuity(port_dev, 1);
+		if (err)
+			goto err_set_slave_promisc;
+	}
+
+	/* set allmulti level to new slave */
+	if (dev->flags & IFF_ALLMULTI) {
+		err = dev_set_allmulti(port_dev, 1);
+		if (err) {
+			if (dev->flags & IFF_PROMISC)
+				dev_set_promiscuity(port_dev, -1);
+			goto err_set_slave_promisc;
+		}
+	}
+
 	netif_addr_lock_bh(dev);
 	dev_uc_sync_multiple(port_dev, dev);
 	dev_mc_sync_multiple(port_dev, dev);
@@ -1262,6 +1286,9 @@ static int team_port_add(struct team *team, struct net_device *port_dev,
 
 	return 0;
 
+err_set_slave_promisc:
+	__team_option_inst_del_port(team, port);
+
 err_option_port_add:
 	team_upper_dev_unlink(team, port);
 
@@ -1307,6 +1334,12 @@ static int team_port_del(struct team *team, struct net_device *port_dev)
 
 	team_port_disable(team, port);
 	list_del_rcu(&port->list);
+
+	if (dev->flags & IFF_PROMISC)
+		dev_set_promiscuity(port_dev, -1);
+	if (dev->flags & IFF_ALLMULTI)
+		dev_set_allmulti(port_dev, -1);
+
 	team_upper_dev_unlink(team, port);
 	netdev_rx_handler_unregister(port_dev);
 	team_port_disable_netpoll(port);
diff --git a/drivers/net/tun.c b/drivers/net/tun.c
index 1d68921723dc..e9ca1c088d0b 100644
--- a/drivers/net/tun.c
+++ b/drivers/net/tun.c
@@ -1763,9 +1763,6 @@ static ssize_t tun_get_user(struct tun_struct *tun, struct tun_file *tfile,
 	int skb_xdp = 1;
 	bool frags = tun_napi_frags_enabled(tfile);
 
-	if (!(tun->dev->flags & IFF_UP))
-		return -EIO;
-
 	if (!(tun->flags & IFF_NO_PI)) {
 		if (len < sizeof(pi))
 			return -EINVAL;
@@ -1867,6 +1864,8 @@ static ssize_t tun_get_user(struct tun_struct *tun, struct tun_file *tfile,
 			err = skb_copy_datagram_from_iter(skb, 0, from, len);
 
 		if (err) {
+			err = -EFAULT;
+drop:
 			this_cpu_inc(tun->pcpu_stats->rx_dropped);
 			kfree_skb(skb);
 			if (frags) {
@@ -1874,7 +1873,7 @@ static ssize_t tun_get_user(struct tun_struct *tun, struct tun_file *tfile,
 				mutex_unlock(&tfile->napi_mutex);
 			}
 
-			return -EFAULT;
+			return err;
 		}
 	}
 
@@ -1958,6 +1957,13 @@ static ssize_t tun_get_user(struct tun_struct *tun, struct tun_file *tfile,
 	    !tfile->detached)
 		rxhash = __skb_get_hash_symmetric(skb);
 
+	rcu_read_lock();
+	if (unlikely(!(tun->dev->flags & IFF_UP))) {
+		err = -EIO;
+		rcu_read_unlock();
+		goto drop;
+	}
+
 	if (frags) {
 		/* Exercise flow dissector code path. */
 		u32 headlen = eth_get_headlen(skb->data, skb_headlen(skb));
@@ -1965,6 +1971,7 @@ static ssize_t tun_get_user(struct tun_struct *tun, struct tun_file *tfile,
 		if (unlikely(headlen > skb_headlen(skb))) {
 			this_cpu_inc(tun->pcpu_stats->rx_dropped);
 			napi_free_frags(&tfile->napi);
+			rcu_read_unlock();
 			mutex_unlock(&tfile->napi_mutex);
 			WARN_ON(1);
 			return -ENOMEM;
@@ -1992,6 +1999,7 @@ static ssize_t tun_get_user(struct tun_struct *tun, struct tun_file *tfile,
 	} else {
 		netif_rx_ni(skb);
 	}
+	rcu_read_unlock();
 
 	stats = get_cpu_ptr(tun->pcpu_stats);
 	u64_stats_update_begin(&stats->syncp);
diff --git a/drivers/net/usb/aqc111.c b/drivers/net/usb/aqc111.c
index 820a2fe7d027..aff995be2a31 100644
--- a/drivers/net/usb/aqc111.c
+++ b/drivers/net/usb/aqc111.c
@@ -1301,6 +1301,20 @@ static const struct driver_info trendnet_info = {
 	.tx_fixup	= aqc111_tx_fixup,
 };
 
+static const struct driver_info qnap_info = {
+	.description	= "QNAP QNA-UC5G1T USB to 5GbE Adapter",
+	.bind		= aqc111_bind,
+	.unbind		= aqc111_unbind,
+	.status		= aqc111_status,
+	.link_reset	= aqc111_link_reset,
+	.reset		= aqc111_reset,
+	.stop		= aqc111_stop,
+	.flags		= FLAG_ETHER | FLAG_FRAMING_AX |
+			  FLAG_AVOID_UNLINK_URBS | FLAG_MULTI_PACKET,
+	.rx_fixup	= aqc111_rx_fixup,
+	.tx_fixup	= aqc111_tx_fixup,
+};
+
 static int aqc111_suspend(struct usb_interface *intf, pm_message_t message)
 {
 	struct usbnet *dev = usb_get_intfdata(intf);
@@ -1455,6 +1469,7 @@ static const struct usb_device_id products[] = {
 	{AQC111_USB_ETH_DEV(0x0b95, 0x2790, asix111_info)},
 	{AQC111_USB_ETH_DEV(0x0b95, 0x2791, asix112_info)},
 	{AQC111_USB_ETH_DEV(0x20f4, 0xe05a, trendnet_info)},
+	{AQC111_USB_ETH_DEV(0x1c04, 0x0015, qnap_info)},
 	{ },/* END */
 };
 MODULE_DEVICE_TABLE(usb, products);
diff --git a/drivers/net/usb/cdc_ether.c b/drivers/net/usb/cdc_ether.c
index 5512a1038721..3e9b2c319e45 100644
--- a/drivers/net/usb/cdc_ether.c
+++ b/drivers/net/usb/cdc_ether.c
@@ -851,6 +851,14 @@ static const struct usb_device_id	products[] = {
 	.driver_info = 0,
 },
 
+/* QNAP QNA-UC5G1T USB to 5GbE Adapter (based on AQC111U) */
+{
+	USB_DEVICE_AND_INTERFACE_INFO(0x1c04, 0x0015, USB_CLASS_COMM,
+				      USB_CDC_SUBCLASS_ETHERNET,
+				      USB_CDC_PROTO_NONE),
+	.driver_info = 0,
+},
+
 /* WHITELIST!!!
  *
  * CDC Ether uses two interfaces, not necessarily consecutive.
diff --git a/drivers/net/usb/qmi_wwan.c b/drivers/net/usb/qmi_wwan.c
index 74bebbdb4b15..679e404a5224 100644
--- a/drivers/net/usb/qmi_wwan.c
+++ b/drivers/net/usb/qmi_wwan.c
@@ -1122,9 +1122,16 @@ static const struct usb_device_id products[] = {
 	{QMI_FIXED_INTF(0x0846, 0x68d3, 8)},	/* Netgear Aircard 779S */
 	{QMI_FIXED_INTF(0x12d1, 0x140c, 1)},	/* Huawei E173 */
 	{QMI_FIXED_INTF(0x12d1, 0x14ac, 1)},	/* Huawei E1820 */
+	{QMI_FIXED_INTF(0x1435, 0x0918, 3)},	/* Wistron NeWeb D16Q1 */
+	{QMI_FIXED_INTF(0x1435, 0x0918, 4)},	/* Wistron NeWeb D16Q1 */
+	{QMI_FIXED_INTF(0x1435, 0x0918, 5)},	/* Wistron NeWeb D16Q1 */
+	{QMI_FIXED_INTF(0x1435, 0x3185, 4)},	/* Wistron NeWeb M18Q5 */
+	{QMI_FIXED_INTF(0x1435, 0xd111, 4)},	/* M9615A DM11-1 D51QC */
 	{QMI_FIXED_INTF(0x1435, 0xd181, 3)},	/* Wistron NeWeb D18Q1 */
 	{QMI_FIXED_INTF(0x1435, 0xd181, 4)},	/* Wistron NeWeb D18Q1 */
 	{QMI_FIXED_INTF(0x1435, 0xd181, 5)},	/* Wistron NeWeb D18Q1 */
+	{QMI_FIXED_INTF(0x1435, 0xd182, 4)},	/* Wistron NeWeb D18 */
+	{QMI_FIXED_INTF(0x1435, 0xd182, 5)},	/* Wistron NeWeb D18 */
 	{QMI_FIXED_INTF(0x1435, 0xd191, 4)},	/* Wistron NeWeb D19Q1 */
 	{QMI_QUIRK_SET_DTR(0x1508, 0x1001, 4)},	/* Fibocom NL668 series */
 	{QMI_FIXED_INTF(0x16d8, 0x6003, 0)},	/* CMOTech 6003 */
@@ -1180,6 +1187,7 @@ static const struct usb_device_id products[] = {
 	{QMI_FIXED_INTF(0x19d2, 0x0265, 4)},	/* ONDA MT8205 4G LTE */
 	{QMI_FIXED_INTF(0x19d2, 0x0284, 4)},	/* ZTE MF880 */
 	{QMI_FIXED_INTF(0x19d2, 0x0326, 4)},	/* ZTE MF821D */
+	{QMI_FIXED_INTF(0x19d2, 0x0396, 3)},	/* ZTE ZM8620 */
 	{QMI_FIXED_INTF(0x19d2, 0x0412, 4)},	/* Telewell TW-LTE 4G */
 	{QMI_FIXED_INTF(0x19d2, 0x1008, 4)},	/* ZTE (Vodafone) K3570-Z */
 	{QMI_FIXED_INTF(0x19d2, 0x1010, 4)},	/* ZTE (Vodafone) K3571-Z */
@@ -1200,9 +1208,12 @@ static const struct usb_device_id products[] = {
 	{QMI_FIXED_INTF(0x19d2, 0x1425, 2)},
 	{QMI_FIXED_INTF(0x19d2, 0x1426, 2)},	/* ZTE MF91 */
 	{QMI_FIXED_INTF(0x19d2, 0x1428, 2)},	/* Telewell TW-LTE 4G v2 */
+	{QMI_FIXED_INTF(0x19d2, 0x1432, 3)},	/* ZTE ME3620 */
 	{QMI_FIXED_INTF(0x19d2, 0x2002, 4)},	/* ZTE (Vodafone) K3765-Z */
+	{QMI_FIXED_INTF(0x2001, 0x7e16, 3)},	/* D-Link DWM-221 */
 	{QMI_FIXED_INTF(0x2001, 0x7e19, 4)},	/* D-Link DWM-221 B1 */
 	{QMI_FIXED_INTF(0x2001, 0x7e35, 4)},	/* D-Link DWM-222 */
+	{QMI_FIXED_INTF(0x2020, 0x2031, 4)},	/* Olicard 600 */
 	{QMI_FIXED_INTF(0x2020, 0x2033, 4)},	/* BroadMobi BM806U */
 	{QMI_FIXED_INTF(0x0f3d, 0x68a2, 8)},    /* Sierra Wireless MC7700 */
 	{QMI_FIXED_INTF(0x114f, 0x68a2, 8)},    /* Sierra Wireless MC7750 */
diff --git a/drivers/net/vrf.c b/drivers/net/vrf.c
index 7c1430ed0244..9ee4d7402ca2 100644
--- a/drivers/net/vrf.c
+++ b/drivers/net/vrf.c
@@ -875,6 +875,7 @@ static const struct net_device_ops vrf_netdev_ops = {
 	.ndo_init		= vrf_dev_init,
 	.ndo_uninit		= vrf_dev_uninit,
 	.ndo_start_xmit		= vrf_xmit,
+	.ndo_set_mac_address	= eth_mac_addr,
 	.ndo_get_stats64	= vrf_get_stats64,
 	.ndo_add_slave		= vrf_add_slave,
 	.ndo_del_slave		= vrf_del_slave,
@@ -1273,9 +1274,15 @@ static void vrf_setup(struct net_device *dev)
 
 	/* default to no qdisc; user can add if desired */
 	dev->priv_flags |= IFF_NO_QUEUE;
+	dev->priv_flags |= IFF_NO_RX_HANDLER;
+	dev->priv_flags |= IFF_LIVE_ADDR_CHANGE;
 
-	dev->min_mtu = 0;
-	dev->max_mtu = 0;
+	/* VRF devices do not care about MTU, but if the MTU is set
+	 * too low then the ipv4 and ipv6 protocols are disabled
+	 * which breaks networking.
+	 */
+	dev->min_mtu = IPV6_MIN_MTU;
+	dev->max_mtu = ETH_MAX_MTU;
 }
 
 static int vrf_validate(struct nlattr *tb[], struct nlattr *data[],
diff --git a/drivers/net/vxlan.c b/drivers/net/vxlan.c
index 077f1b9f2761..d76dfed8d9bb 100644
--- a/drivers/net/vxlan.c
+++ b/drivers/net/vxlan.c
@@ -4335,10 +4335,8 @@ static void vxlan_destroy_tunnels(struct net *net, struct list_head *head)
 		/* If vxlan->dev is in the same netns, it has already been added
 		 * to the list by the previous loop.
 		 */
-		if (!net_eq(dev_net(vxlan->dev), net)) {
-			gro_cells_destroy(&vxlan->gro_cells);
+		if (!net_eq(dev_net(vxlan->dev), net))
 			unregister_netdevice_queue(vxlan->dev, head);
-		}
 	}
 
 	for (h = 0; h < PORT_HASH_SIZE; ++h)
diff --git a/drivers/net/wireless/ath/ath10k/ce.c b/drivers/net/wireless/ath/ath10k/ce.c
index 24b983edb357..eca87f7c5b6c 100644
--- a/drivers/net/wireless/ath/ath10k/ce.c
+++ b/drivers/net/wireless/ath/ath10k/ce.c
@@ -1855,7 +1855,7 @@ void ath10k_ce_dump_registers(struct ath10k *ar,
 	struct ath10k_ce_crash_data ce_data;
 	u32 addr, id;
 
-	lockdep_assert_held(&ar->data_lock);
+	lockdep_assert_held(&ar->dump_mutex);
 
 	ath10k_err(ar, "Copy Engine register dump:\n");
 
diff --git a/drivers/net/wireless/ath/ath10k/core.c b/drivers/net/wireless/ath/ath10k/core.c
index 835b8de92d55..aff585658fc0 100644
--- a/drivers/net/wireless/ath/ath10k/core.c
+++ b/drivers/net/wireless/ath/ath10k/core.c
@@ -3119,6 +3119,7 @@ struct ath10k *ath10k_core_create(size_t priv_size, struct device *dev,
 		goto err_free_wq;
 
 	mutex_init(&ar->conf_mutex);
+	mutex_init(&ar->dump_mutex);
 	spin_lock_init(&ar->data_lock);
 
 	INIT_LIST_HEAD(&ar->peers);
diff --git a/drivers/net/wireless/ath/ath10k/core.h b/drivers/net/wireless/ath/ath10k/core.h
index e08a17b01e03..e35aae5146f1 100644
--- a/drivers/net/wireless/ath/ath10k/core.h
+++ b/drivers/net/wireless/ath/ath10k/core.h
@@ -1063,6 +1063,9 @@ struct ath10k {
 	/* prevents concurrent FW reconfiguration */
 	struct mutex conf_mutex;
 
+	/* protects coredump data */
+	struct mutex dump_mutex;
+
 	/* protects shared structure data */
 	spinlock_t data_lock;
 
diff --git a/drivers/net/wireless/ath/ath10k/coredump.c b/drivers/net/wireless/ath/ath10k/coredump.c
index 33838d9c1cb6..45a355fb62b9 100644
--- a/drivers/net/wireless/ath/ath10k/coredump.c
+++ b/drivers/net/wireless/ath/ath10k/coredump.c
@@ -1102,7 +1102,7 @@ struct ath10k_fw_crash_data *ath10k_coredump_new(struct ath10k *ar)
 {
 	struct ath10k_fw_crash_data *crash_data = ar->coredump.fw_crash_data;
 
-	lockdep_assert_held(&ar->data_lock);
+	lockdep_assert_held(&ar->dump_mutex);
 
 	if (ath10k_coredump_mask == 0)
 		/* coredump disabled */
@@ -1146,7 +1146,7 @@ static struct ath10k_dump_file_data *ath10k_coredump_build(struct ath10k *ar)
 	if (!buf)
 		return NULL;
 
-	spin_lock_bh(&ar->data_lock);
+	mutex_lock(&ar->dump_mutex);
 
 	dump_data = (struct ath10k_dump_file_data *)(buf);
 	strlcpy(dump_data->df_magic, "ATH10K-FW-DUMP",
@@ -1213,7 +1213,7 @@ static struct ath10k_dump_file_data *ath10k_coredump_build(struct ath10k *ar)
 		sofar += sizeof(*dump_tlv) + crash_data->ramdump_buf_len;
 	}
 
-	spin_unlock_bh(&ar->data_lock);
+	mutex_unlock(&ar->dump_mutex);
 
 	return dump_data;
 }
diff --git a/drivers/net/wireless/ath/ath10k/htt_rx.c b/drivers/net/wireless/ath/ath10k/htt_rx.c
index a20ea270d519..1acc622d2183 100644
--- a/drivers/net/wireless/ath/ath10k/htt_rx.c
+++ b/drivers/net/wireless/ath/ath10k/htt_rx.c
@@ -2728,7 +2728,7 @@ static void ath10k_htt_rx_tx_fetch_ind(struct ath10k *ar, struct sk_buff *skb)
 			num_msdus++;
 			num_bytes += ret;
 		}
-		ieee80211_return_txq(hw, txq);
+		ieee80211_return_txq(hw, txq, false);
 		ieee80211_txq_schedule_end(hw, txq->ac);
 
 		record->num_msdus = cpu_to_le16(num_msdus);
diff --git a/drivers/net/wireless/ath/ath10k/mac.c b/drivers/net/wireless/ath/ath10k/mac.c
index b73c23d4ce86..9c703d287333 100644
--- a/drivers/net/wireless/ath/ath10k/mac.c
+++ b/drivers/net/wireless/ath/ath10k/mac.c
@@ -4089,7 +4089,7 @@ static int ath10k_mac_schedule_txq(struct ieee80211_hw *hw, u32 ac)
 			if (ret < 0)
 				break;
 		}
-		ieee80211_return_txq(hw, txq);
+		ieee80211_return_txq(hw, txq, false);
 		ath10k_htt_tx_txq_update(hw, txq);
 		if (ret == -EBUSY)
 			break;
@@ -4374,7 +4374,7 @@ static void ath10k_mac_op_wake_tx_queue(struct ieee80211_hw *hw,
 		if (ret < 0)
 			break;
 	}
-	ieee80211_return_txq(hw, txq);
+	ieee80211_return_txq(hw, txq, false);
 	ath10k_htt_tx_txq_update(hw, txq);
 out:
 	ieee80211_txq_schedule_end(hw, ac);
@@ -5774,7 +5774,7 @@ static void ath10k_bss_info_changed(struct ieee80211_hw *hw,
 	}
 
 	if (changed & BSS_CHANGED_MCAST_RATE &&
-	    !WARN_ON(ath10k_mac_vif_chan(arvif->vif, &def))) {
+	    !ath10k_mac_vif_chan(arvif->vif, &def)) {
 		band = def.chan->band;
 		rateidx = vif->bss_conf.mcast_rate[band] - 1;
 
@@ -5812,7 +5812,7 @@ static void ath10k_bss_info_changed(struct ieee80211_hw *hw,
 	}
 
 	if (changed & BSS_CHANGED_BASIC_RATES) {
-		if (WARN_ON(ath10k_mac_vif_chan(vif, &def))) {
+		if (ath10k_mac_vif_chan(vif, &def)) {
 			mutex_unlock(&ar->conf_mutex);
 			return;
 		}
diff --git a/drivers/net/wireless/ath/ath10k/pci.c b/drivers/net/wireless/ath/ath10k/pci.c
index 271f92c24d44..2c27f407a851 100644
--- a/drivers/net/wireless/ath/ath10k/pci.c
+++ b/drivers/net/wireless/ath/ath10k/pci.c
@@ -1441,7 +1441,7 @@ static void ath10k_pci_dump_registers(struct ath10k *ar,
 	__le32 reg_dump_values[REG_DUMP_COUNT_QCA988X] = {};
 	int i, ret;
 
-	lockdep_assert_held(&ar->data_lock);
+	lockdep_assert_held(&ar->dump_mutex);
 
 	ret = ath10k_pci_diag_read_hi(ar, &reg_dump_values[0],
 				      hi_failure_state,
@@ -1656,7 +1656,7 @@ static void ath10k_pci_dump_memory(struct ath10k *ar,
 	int ret, i;
 	u8 *buf;
 
-	lockdep_assert_held(&ar->data_lock);
+	lockdep_assert_held(&ar->dump_mutex);
 
 	if (!crash_data)
 		return;
@@ -1734,14 +1734,19 @@ static void ath10k_pci_dump_memory(struct ath10k *ar,
 	}
 }
 
-static void ath10k_pci_fw_crashed_dump(struct ath10k *ar)
+static void ath10k_pci_fw_dump_work(struct work_struct *work)
 {
+	struct ath10k_pci *ar_pci = container_of(work, struct ath10k_pci,
+						 dump_work);
 	struct ath10k_fw_crash_data *crash_data;
+	struct ath10k *ar = ar_pci->ar;
 	char guid[UUID_STRING_LEN + 1];
 
-	spin_lock_bh(&ar->data_lock);
+	mutex_lock(&ar->dump_mutex);
 
+	spin_lock_bh(&ar->data_lock);
 	ar->stats.fw_crash_counter++;
+	spin_unlock_bh(&ar->data_lock);
 
 	crash_data = ath10k_coredump_new(ar);
 
@@ -1756,11 +1761,18 @@ static void ath10k_pci_fw_crashed_dump(struct ath10k *ar)
 	ath10k_ce_dump_registers(ar, crash_data);
 	ath10k_pci_dump_memory(ar, crash_data);
 
-	spin_unlock_bh(&ar->data_lock);
+	mutex_unlock(&ar->dump_mutex);
 
 	queue_work(ar->workqueue, &ar->restart_work);
 }
 
+static void ath10k_pci_fw_crashed_dump(struct ath10k *ar)
+{
+	struct ath10k_pci *ar_pci = ath10k_pci_priv(ar);
+
+	queue_work(ar->workqueue, &ar_pci->dump_work);
+}
+
 void ath10k_pci_hif_send_complete_check(struct ath10k *ar, u8 pipe,
 					int force)
 {
@@ -3442,6 +3454,8 @@ int ath10k_pci_setup_resource(struct ath10k *ar)
 	spin_lock_init(&ar_pci->ps_lock);
 	mutex_init(&ar_pci->ce_diag_mutex);
 
+	INIT_WORK(&ar_pci->dump_work, ath10k_pci_fw_dump_work);
+
 	timer_setup(&ar_pci->rx_post_retry, ath10k_pci_rx_replenish_retry, 0);
 
 	if (QCA_REV_6174(ar) || QCA_REV_9377(ar))
diff --git a/drivers/net/wireless/ath/ath10k/pci.h b/drivers/net/wireless/ath/ath10k/pci.h
index 3773c79f322f..4455ed6c5275 100644
--- a/drivers/net/wireless/ath/ath10k/pci.h
+++ b/drivers/net/wireless/ath/ath10k/pci.h
@@ -121,6 +121,8 @@ struct ath10k_pci {
 	/* For protecting ce_diag */
 	struct mutex ce_diag_mutex;
 
+	struct work_struct dump_work;
+
 	struct ath10k_ce ce;
 	struct timer_list rx_post_retry;
 
diff --git a/drivers/net/wireless/ath/ath5k/base.c b/drivers/net/wireless/ath/ath5k/base.c
index a2351ef45ae0..65a4c142640d 100644
--- a/drivers/net/wireless/ath/ath5k/base.c
+++ b/drivers/net/wireless/ath/ath5k/base.c
@@ -837,7 +837,6 @@ ath5k_txbuf_setup(struct ath5k_hw *ah, struct ath5k_buf *bf,
 
 	txq->link = &ds->ds_link;
 	ath5k_hw_start_tx_dma(ah, txq->qnum);
-	mmiowb();
 	spin_unlock_bh(&txq->lock);
 
 	return 0;
@@ -2174,7 +2173,6 @@ ath5k_beacon_config(struct ath5k_hw *ah)
 	}
 
 	ath5k_hw_set_imr(ah, ah->imask);
-	mmiowb();
 	spin_unlock_bh(&ah->block);
 }
 
@@ -2779,7 +2777,6 @@ int ath5k_start(struct ieee80211_hw *hw)
 
 	ret = 0;
 done:
-	mmiowb();
 	mutex_unlock(&ah->lock);
 
 	set_bit(ATH_STAT_STARTED, ah->status);
@@ -2839,7 +2836,6 @@ void ath5k_stop(struct ieee80211_hw *hw)
 				"putting device to sleep\n");
 	}
 
-	mmiowb();
 	mutex_unlock(&ah->lock);
 
 	ath5k_stop_tasklets(ah);
diff --git a/drivers/net/wireless/ath/ath5k/mac80211-ops.c b/drivers/net/wireless/ath/ath5k/mac80211-ops.c
index 16e052d02c94..5e866a193ed0 100644
--- a/drivers/net/wireless/ath/ath5k/mac80211-ops.c
+++ b/drivers/net/wireless/ath/ath5k/mac80211-ops.c
@@ -263,7 +263,6 @@ ath5k_bss_info_changed(struct ieee80211_hw *hw, struct ieee80211_vif *vif,
 		memcpy(common->curbssid, bss_conf->bssid, ETH_ALEN);
 		common->curaid = 0;
 		ath5k_hw_set_bssid(ah);
-		mmiowb();
 	}
 
 	if (changes & BSS_CHANGED_BEACON_INT)
@@ -528,7 +527,6 @@ ath5k_set_key(struct ieee80211_hw *hw, enum set_key_cmd cmd,
 		ret = -EINVAL;
 	}
 
-	mmiowb();
 	mutex_unlock(&ah->lock);
 	return ret;
 }
diff --git a/drivers/net/wireless/ath/ath9k/xmit.c b/drivers/net/wireless/ath/ath9k/xmit.c
index 773d428ff1b0..b17e1ca40995 100644
--- a/drivers/net/wireless/ath/ath9k/xmit.c
+++ b/drivers/net/wireless/ath/ath9k/xmit.c
@@ -1938,12 +1938,15 @@ void ath_txq_schedule(struct ath_softc *sc, struct ath_txq *txq)
 		goto out;
 
 	while ((queue = ieee80211_next_txq(hw, txq->mac80211_qnum))) {
+		bool force;
+
 		tid = (struct ath_atx_tid *)queue->drv_priv;
 
 		ret = ath_tx_sched_aggr(sc, txq, tid);
 		ath_dbg(common, QUEUE, "ath_tx_sched_aggr returned %d\n", ret);
 
-		ieee80211_return_txq(hw, queue);
+		force = !skb_queue_empty(&tid->retry_q);
+		ieee80211_return_txq(hw, queue, force);
 	}
 
 out:
diff --git a/drivers/net/wireless/broadcom/b43/main.c b/drivers/net/wireless/broadcom/b43/main.c
index 74be3c809225..4c7980f84591 100644
--- a/drivers/net/wireless/broadcom/b43/main.c
+++ b/drivers/net/wireless/broadcom/b43/main.c
@@ -485,7 +485,6 @@ static void b43_ram_write(struct b43_wldev *dev, u16 offset, u32 val)
 		val = swab32(val);
 
 	b43_write32(dev, B43_MMIO_RAM_CONTROL, offset);
-	mmiowb();
 	b43_write32(dev, B43_MMIO_RAM_DATA, val);
 }
 
@@ -656,9 +655,7 @@ static void b43_tsf_write_locked(struct b43_wldev *dev, u64 tsf)
 	/* The hardware guarantees us an atomic write, if we
 	 * write the low register first. */
 	b43_write32(dev, B43_MMIO_REV3PLUS_TSF_LOW, low);
-	mmiowb();
 	b43_write32(dev, B43_MMIO_REV3PLUS_TSF_HIGH, high);
-	mmiowb();
 }
 
 void b43_tsf_write(struct b43_wldev *dev, u64 tsf)
@@ -1822,11 +1819,9 @@ static void b43_beacon_update_trigger_work(struct work_struct *work)
 		if (b43_bus_host_is_sdio(dev->dev)) {
 			/* wl->mutex is enough. */
 			b43_do_beacon_update_trigger_work(dev);
-			mmiowb();
 		} else {
 			spin_lock_irq(&wl->hardirq_lock);
 			b43_do_beacon_update_trigger_work(dev);
-			mmiowb();
 			spin_unlock_irq(&wl->hardirq_lock);
 		}
 	}
@@ -2078,7 +2073,6 @@ static irqreturn_t b43_interrupt_thread_handler(int irq, void *dev_id)
 
 	mutex_lock(&dev->wl->mutex);
 	b43_do_interrupt_thread(dev);
-	mmiowb();
 	mutex_unlock(&dev->wl->mutex);
 
 	return IRQ_HANDLED;
@@ -2143,7 +2137,6 @@ static irqreturn_t b43_interrupt_handler(int irq, void *dev_id)
 
 	spin_lock(&dev->wl->hardirq_lock);
 	ret = b43_do_interrupt(dev);
-	mmiowb();
 	spin_unlock(&dev->wl->hardirq_lock);
 
 	return ret;
diff --git a/drivers/net/wireless/broadcom/b43/sysfs.c b/drivers/net/wireless/broadcom/b43/sysfs.c
index 3190493bd07f..93d03b673670 100644
--- a/drivers/net/wireless/broadcom/b43/sysfs.c
+++ b/drivers/net/wireless/broadcom/b43/sysfs.c
@@ -129,7 +129,6 @@ static ssize_t b43_attr_interfmode_store(struct device *dev,
 	} else
 		err = -ENOSYS;
 
-	mmiowb();
 	mutex_unlock(&wldev->wl->mutex);
 
 	return err ? err : count;
diff --git a/drivers/net/wireless/broadcom/b43legacy/ilt.c b/drivers/net/wireless/broadcom/b43legacy/ilt.c
index ee5682e54204..6d15fb4d30c6 100644
--- a/drivers/net/wireless/broadcom/b43legacy/ilt.c
+++ b/drivers/net/wireless/broadcom/b43legacy/ilt.c
@@ -315,14 +315,12 @@ const u16 b43legacy_ilt_sigmasqr2[B43legacy_ILT_SIGMASQR_SIZE] = {
 void b43legacy_ilt_write(struct b43legacy_wldev *dev, u16 offset, u16 val)
 {
 	b43legacy_phy_write(dev, B43legacy_PHY_ILT_G_CTRL, offset);
-	mmiowb();
 	b43legacy_phy_write(dev, B43legacy_PHY_ILT_G_DATA1, val);
 }
 
 void b43legacy_ilt_write32(struct b43legacy_wldev *dev, u16 offset, u32 val)
 {
 	b43legacy_phy_write(dev, B43legacy_PHY_ILT_G_CTRL, offset);
-	mmiowb();
 	b43legacy_phy_write(dev, B43legacy_PHY_ILT_G_DATA2,
 			    (val & 0xFFFF0000) >> 16);
 	b43legacy_phy_write(dev, B43legacy_PHY_ILT_G_DATA1,
diff --git a/drivers/net/wireless/broadcom/b43legacy/main.c b/drivers/net/wireless/broadcom/b43legacy/main.c
index 55f411925960..c777efc6dc13 100644
--- a/drivers/net/wireless/broadcom/b43legacy/main.c
+++ b/drivers/net/wireless/broadcom/b43legacy/main.c
@@ -264,7 +264,6 @@ static void b43legacy_ram_write(struct b43legacy_wldev *dev, u16 offset,
 		val = swab32(val);
 
 	b43legacy_write32(dev, B43legacy_MMIO_RAM_CONTROL, offset);
-	mmiowb();
 	b43legacy_write32(dev, B43legacy_MMIO_RAM_DATA, val);
 }
 
@@ -341,14 +340,11 @@ void b43legacy_shm_write32(struct b43legacy_wldev *dev,
 		if (offset & 0x0003) {
 			/* Unaligned access */
 			b43legacy_shm_control_word(dev, routing, offset >> 2);
-			mmiowb();
 			b43legacy_write16(dev,
 					  B43legacy_MMIO_SHM_DATA_UNALIGNED,
 					  (value >> 16) & 0xffff);
-			mmiowb();
 			b43legacy_shm_control_word(dev, routing,
 						   (offset >> 2) + 1);
-			mmiowb();
 			b43legacy_write16(dev, B43legacy_MMIO_SHM_DATA,
 					  value & 0xffff);
 			return;
@@ -356,7 +352,6 @@ void b43legacy_shm_write32(struct b43legacy_wldev *dev,
 		offset >>= 2;
 	}
 	b43legacy_shm_control_word(dev, routing, offset);
-	mmiowb();
 	b43legacy_write32(dev, B43legacy_MMIO_SHM_DATA, value);
 }
 
@@ -368,7 +363,6 @@ void b43legacy_shm_write16(struct b43legacy_wldev *dev, u16 routing, u16 offset,
 		if (offset & 0x0003) {
 			/* Unaligned access */
 			b43legacy_shm_control_word(dev, routing, offset >> 2);
-			mmiowb();
 			b43legacy_write16(dev,
 					  B43legacy_MMIO_SHM_DATA_UNALIGNED,
 					  value);
@@ -377,7 +371,6 @@ void b43legacy_shm_write16(struct b43legacy_wldev *dev, u16 routing, u16 offset,
 		offset >>= 2;
 	}
 	b43legacy_shm_control_word(dev, routing, offset);
-	mmiowb();
 	b43legacy_write16(dev, B43legacy_MMIO_SHM_DATA, value);
 }
 
@@ -471,7 +464,6 @@ static void b43legacy_time_lock(struct b43legacy_wldev *dev)
 	status = b43legacy_read32(dev, B43legacy_MMIO_MACCTL);
 	status |= B43legacy_MACCTL_TBTTHOLD;
 	b43legacy_write32(dev, B43legacy_MMIO_MACCTL, status);
-	mmiowb();
 }
 
 static void b43legacy_time_unlock(struct b43legacy_wldev *dev)
@@ -494,10 +486,8 @@ static void b43legacy_tsf_write_locked(struct b43legacy_wldev *dev, u64 tsf)
 		u32 hi = (tsf & 0xFFFFFFFF00000000ULL) >> 32;
 
 		b43legacy_write32(dev, B43legacy_MMIO_REV3PLUS_TSF_LOW, 0);
-		mmiowb();
 		b43legacy_write32(dev, B43legacy_MMIO_REV3PLUS_TSF_HIGH,
 				    hi);
-		mmiowb();
 		b43legacy_write32(dev, B43legacy_MMIO_REV3PLUS_TSF_LOW,
 				    lo);
 	} else {
@@ -507,13 +497,9 @@ static void b43legacy_tsf_write_locked(struct b43legacy_wldev *dev, u64 tsf)
 		u16 v3 = (tsf & 0xFFFF000000000000ULL) >> 48;
 
 		b43legacy_write16(dev, B43legacy_MMIO_TSF_0, 0);
-		mmiowb();
 		b43legacy_write16(dev, B43legacy_MMIO_TSF_3, v3);
-		mmiowb();
 		b43legacy_write16(dev, B43legacy_MMIO_TSF_2, v2);
-		mmiowb();
 		b43legacy_write16(dev, B43legacy_MMIO_TSF_1, v1);
-		mmiowb();
 		b43legacy_write16(dev, B43legacy_MMIO_TSF_0, v0);
 	}
 }
@@ -1250,7 +1236,6 @@ static void b43legacy_beacon_update_trigger_work(struct work_struct *work)
 		/* The handler might have updated the IRQ mask. */
 		b43legacy_write32(dev, B43legacy_MMIO_GEN_IRQ_MASK,
 				  dev->irq_mask);
-		mmiowb();
 		spin_unlock_irq(&wl->irq_lock);
 	}
 	mutex_unlock(&wl->mutex);
@@ -1346,7 +1331,6 @@ static void b43legacy_interrupt_tasklet(struct b43legacy_wldev *dev)
 			       dma_reason[2], dma_reason[3],
 			       dma_reason[4], dma_reason[5]);
 			b43legacy_controller_restart(dev, "DMA error");
-			mmiowb();
 			spin_unlock_irqrestore(&dev->wl->irq_lock, flags);
 			return;
 		}
@@ -1396,7 +1380,6 @@ static void b43legacy_interrupt_tasklet(struct b43legacy_wldev *dev)
 		handle_irq_transmit_status(dev);
 
 	b43legacy_write32(dev, B43legacy_MMIO_GEN_IRQ_MASK, dev->irq_mask);
-	mmiowb();
 	spin_unlock_irqrestore(&dev->wl->irq_lock, flags);
 }
 
@@ -1488,7 +1471,6 @@ static irqreturn_t b43legacy_interrupt_handler(int irq, void *dev_id)
 	dev->irq_reason = reason;
 	tasklet_schedule(&dev->isr_tasklet);
 out:
-	mmiowb();
 	spin_unlock(&dev->wl->irq_lock);
 
 	return ret;
@@ -2781,7 +2763,6 @@ static int b43legacy_op_dev_config(struct ieee80211_hw *hw,
 
 	spin_lock_irqsave(&wl->irq_lock, flags);
 	b43legacy_write32(dev, B43legacy_MMIO_GEN_IRQ_MASK, dev->irq_mask);
-	mmiowb();
 	spin_unlock_irqrestore(&wl->irq_lock, flags);
 out_unlock_mutex:
 	mutex_unlock(&wl->mutex);
@@ -2900,7 +2881,6 @@ static void b43legacy_op_bss_info_changed(struct ieee80211_hw *hw,
 	spin_lock_irqsave(&wl->irq_lock, flags);
 	b43legacy_write32(dev, B43legacy_MMIO_GEN_IRQ_MASK, dev->irq_mask);
 	/* XXX: why? */
-	mmiowb();
 	spin_unlock_irqrestore(&wl->irq_lock, flags);
  out_unlock_mutex:
 	mutex_unlock(&wl->mutex);
diff --git a/drivers/net/wireless/broadcom/b43legacy/phy.c b/drivers/net/wireless/broadcom/b43legacy/phy.c
index 995c7d0c212a..f949766d27ca 100644
--- a/drivers/net/wireless/broadcom/b43legacy/phy.c
+++ b/drivers/net/wireless/broadcom/b43legacy/phy.c
@@ -134,7 +134,6 @@ u16 b43legacy_phy_read(struct b43legacy_wldev *dev, u16 offset)
 void b43legacy_phy_write(struct b43legacy_wldev *dev, u16 offset, u16 val)
 {
 	b43legacy_write16(dev, B43legacy_MMIO_PHY_CONTROL, offset);
-	mmiowb();
 	b43legacy_write16(dev, B43legacy_MMIO_PHY_DATA, val);
 }
 
diff --git a/drivers/net/wireless/broadcom/b43legacy/pio.h b/drivers/net/wireless/broadcom/b43legacy/pio.h
index 1cd1b9ca5e9c..08cd02282beb 100644
--- a/drivers/net/wireless/broadcom/b43legacy/pio.h
+++ b/drivers/net/wireless/broadcom/b43legacy/pio.h
@@ -92,7 +92,6 @@ void b43legacy_pio_write(struct b43legacy_pioqueue *queue,
 		       u16 offset, u16 value)
 {
 	b43legacy_write16(queue->dev, queue->mmio_base + offset, value);
-	mmiowb();
 }
 
 
diff --git a/drivers/net/wireless/broadcom/b43legacy/radio.c b/drivers/net/wireless/broadcom/b43legacy/radio.c
index eab1c9387846..c6db444ea07e 100644
--- a/drivers/net/wireless/broadcom/b43legacy/radio.c
+++ b/drivers/net/wireless/broadcom/b43legacy/radio.c
@@ -95,7 +95,6 @@ void b43legacy_radio_lock(struct b43legacy_wldev *dev)
 	B43legacy_WARN_ON(status & B43legacy_MACCTL_RADIOLOCK);
 	status |= B43legacy_MACCTL_RADIOLOCK;
 	b43legacy_write32(dev, B43legacy_MMIO_MACCTL, status);
-	mmiowb();
 	udelay(10);
 }
 
@@ -108,7 +107,6 @@ void b43legacy_radio_unlock(struct b43legacy_wldev *dev)
 	B43legacy_WARN_ON(!(status & B43legacy_MACCTL_RADIOLOCK));
 	status &= ~B43legacy_MACCTL_RADIOLOCK;
 	b43legacy_write32(dev, B43legacy_MMIO_MACCTL, status);
-	mmiowb();
 }
 
 u16 b43legacy_radio_read16(struct b43legacy_wldev *dev, u16 offset)
@@ -141,7 +139,6 @@ u16 b43legacy_radio_read16(struct b43legacy_wldev *dev, u16 offset)
 void b43legacy_radio_write16(struct b43legacy_wldev *dev, u16 offset, u16 val)
 {
 	b43legacy_write16(dev, B43legacy_MMIO_RADIO_CONTROL, offset);
-	mmiowb();
 	b43legacy_write16(dev, B43legacy_MMIO_RADIO_DATA_LOW, val);
 }
 
@@ -333,7 +330,6 @@ u8 b43legacy_radio_aci_scan(struct b43legacy_wldev *dev)
 void b43legacy_nrssi_hw_write(struct b43legacy_wldev *dev, u16 offset, s16 val)
 {
 	b43legacy_phy_write(dev, B43legacy_PHY_NRSSILT_CTRL, offset);
-	mmiowb();
 	b43legacy_phy_write(dev, B43legacy_PHY_NRSSILT_DATA, (u16)val);
 }
 
diff --git a/drivers/net/wireless/broadcom/b43legacy/sysfs.c b/drivers/net/wireless/broadcom/b43legacy/sysfs.c
index 2a1da15c913b..2db83eec7a11 100644
--- a/drivers/net/wireless/broadcom/b43legacy/sysfs.c
+++ b/drivers/net/wireless/broadcom/b43legacy/sysfs.c
@@ -143,7 +143,6 @@ static ssize_t b43legacy_attr_interfmode_store(struct device *dev,
 	if (err)
 		b43legacyerr(wldev->wl, "Interference Mitigation not "
 		       "supported by device\n");
-	mmiowb();
 	spin_unlock_irqrestore(&wldev->wl->irq_lock, flags);
 	mutex_unlock(&wldev->wl->mutex);
 
diff --git a/drivers/net/wireless/intel/iwlegacy/common.h b/drivers/net/wireless/intel/iwlegacy/common.h
index b079c64ca014..986646af8dfd 100644
--- a/drivers/net/wireless/intel/iwlegacy/common.h
+++ b/drivers/net/wireless/intel/iwlegacy/common.h
@@ -2030,13 +2030,6 @@ static inline void
 _il_release_nic_access(struct il_priv *il)
 {
 	_il_clear_bit(il, CSR_GP_CNTRL, CSR_GP_CNTRL_REG_FLAG_MAC_ACCESS_REQ);
-	/*
-	 * In above we are reading CSR_GP_CNTRL register, what will flush any
-	 * previous writes, but still want write, which clear MAC_ACCESS_REQ
-	 * bit, be performed on PCI bus before any other writes scheduled on
-	 * different CPUs (after we drop reg_lock).
-	 */
-	mmiowb();
 }
 
 static inline u32
diff --git a/drivers/net/wireless/intel/iwlwifi/cfg/22000.c b/drivers/net/wireless/intel/iwlwifi/cfg/22000.c
index fdc56f821b5a..0a87d87fbb4f 100644
--- a/drivers/net/wireless/intel/iwlwifi/cfg/22000.c
+++ b/drivers/net/wireless/intel/iwlwifi/cfg/22000.c
@@ -82,6 +82,7 @@
 #define IWL_22000_HR_A0_FW_PRE		"iwlwifi-QuQnj-a0-hr-a0-"
 #define IWL_22000_SU_Z0_FW_PRE		"iwlwifi-su-z0-"
 #define IWL_QU_B_JF_B_FW_PRE		"iwlwifi-Qu-b0-jf-b0-"
+#define IWL_QUZ_A_HR_B_FW_PRE		"iwlwifi-QuZ-a0-hr-b0-"
 #define IWL_QNJ_B_JF_B_FW_PRE		"iwlwifi-QuQnj-b0-jf-b0-"
 #define IWL_CC_A_FW_PRE			"iwlwifi-cc-a0-"
 #define IWL_22000_SO_A_JF_B_FW_PRE	"iwlwifi-so-a0-jf-b0-"
@@ -105,8 +106,8 @@
 	IWL_22000_HR_A0_FW_PRE __stringify(api) ".ucode"
 #define IWL_22000_SU_Z0_MODULE_FIRMWARE(api) \
 	IWL_22000_SU_Z0_FW_PRE __stringify(api) ".ucode"
-#define IWL_QU_B_JF_B_MODULE_FIRMWARE(api) \
-	IWL_QU_B_JF_B_FW_PRE __stringify(api) ".ucode"
+#define IWL_QUZ_A_HR_B_MODULE_FIRMWARE(api) \
+	IWL_QUZ_A_HR_B_FW_PRE __stringify(api) ".ucode"
 #define IWL_QU_B_JF_B_MODULE_FIRMWARE(api) \
 	IWL_QU_B_JF_B_FW_PRE __stringify(api) ".ucode"
 #define IWL_QNJ_B_JF_B_MODULE_FIRMWARE(api)		\
@@ -200,7 +201,7 @@ static const struct iwl_ht_params iwl_22000_ht_params = {
 #define IWL_DEVICE_AX210						\
 	IWL_DEVICE_AX200_COMMON,					\
 	.device_family = IWL_DEVICE_FAMILY_AX210,			\
-	.base_params = &iwl_22000_base_params,				\
+	.base_params = &iwl_22560_base_params,				\
 	.csr = &iwl_csr_v1,						\
 	.min_txq_size = 128
 
@@ -235,8 +236,20 @@ const struct iwl_cfg iwl_ax101_cfg_qu_hr = {
 	.max_tx_agg_size = IEEE80211_MAX_AMPDU_BUF_HT,
 };
 
-const struct iwl_cfg iwl22260_2ax_cfg = {
-	.name = "Intel(R) Wireless-AX 22260",
+const struct iwl_cfg iwl_ax101_cfg_quz_hr = {
+	.name = "Intel(R) Wi-Fi 6 AX101",
+	.fw_name_pre = IWL_QUZ_A_HR_B_FW_PRE,
+	IWL_DEVICE_22500,
+	/*
+	 * This device doesn't support receiving BlockAck with a large bitmap
+	 * so we need to restrict the size of transmitted aggregation to the
+	 * HT size; mac80211 would otherwise pick the HE max (256) by default.
+	 */
+	.max_tx_agg_size = IEEE80211_MAX_AMPDU_BUF_HT,
+};
+
+const struct iwl_cfg iwl_ax200_cfg_cc = {
+	.name = "Intel(R) Wi-Fi 6 AX200 160MHz",
 	.fw_name_pre = IWL_CC_A_FW_PRE,
 	IWL_DEVICE_22500,
 	/*
@@ -249,7 +262,7 @@ const struct iwl_cfg iwl22260_2ax_cfg = {
 };
 
 const struct iwl_cfg killer1650x_2ax_cfg = {
-	.name = "Killer(R) Wireless-AX 1650x Wireless Network Adapter (200NGW)",
+	.name = "Killer(R) Wi-Fi 6 AX1650x 160MHz Wireless Network Adapter (200NGW)",
 	.fw_name_pre = IWL_CC_A_FW_PRE,
 	IWL_DEVICE_22500,
 	/*
@@ -262,7 +275,7 @@ const struct iwl_cfg killer1650x_2ax_cfg = {
 };
 
 const struct iwl_cfg killer1650w_2ax_cfg = {
-	.name = "Killer(R) Wireless-AX 1650w Wireless Network Adapter (200D2W)",
+	.name = "Killer(R) Wi-Fi 6 AX1650w 160MHz Wireless Network Adapter (200D2W)",
 	.fw_name_pre = IWL_CC_A_FW_PRE,
 	IWL_DEVICE_22500,
 	/*
@@ -328,7 +341,7 @@ const struct iwl_cfg killer1550s_2ac_cfg_qu_b0_jf_b0 = {
 };
 
 const struct iwl_cfg killer1650s_2ax_cfg_qu_b0_hr_b0 = {
-	.name = "Killer(R) Wireless-AX 1650i Wireless Network Adapter (22560NGW)",
+	.name = "Killer(R) Wi-Fi 6 AX1650i 160MHz Wireless Network Adapter (201NGW)",
 	.fw_name_pre = IWL_22000_QU_B_HR_B_FW_PRE,
 	IWL_DEVICE_22500,
 	/*
@@ -340,7 +353,7 @@ const struct iwl_cfg killer1650s_2ax_cfg_qu_b0_hr_b0 = {
 };
 
 const struct iwl_cfg killer1650i_2ax_cfg_qu_b0_hr_b0 = {
-	.name = "Killer(R) Wireless-AX 1650s Wireless Network Adapter (22560D2W)",
+	.name = "Killer(R) Wi-Fi 6 AX1650s 160MHz Wireless Network Adapter (201D2W)",
 	.fw_name_pre = IWL_22000_QU_B_HR_B_FW_PRE,
 	IWL_DEVICE_22500,
 	/*
@@ -444,6 +457,7 @@ MODULE_FIRMWARE(IWL_22000_HR_B_QNJ_MODULE_FIRMWARE(IWL_22000_UCODE_API_MAX));
 MODULE_FIRMWARE(IWL_22000_HR_A0_QNJ_MODULE_FIRMWARE(IWL_22000_UCODE_API_MAX));
 MODULE_FIRMWARE(IWL_22000_SU_Z0_MODULE_FIRMWARE(IWL_22000_UCODE_API_MAX));
 MODULE_FIRMWARE(IWL_QU_B_JF_B_MODULE_FIRMWARE(IWL_22000_UCODE_API_MAX));
+MODULE_FIRMWARE(IWL_QUZ_A_HR_B_MODULE_FIRMWARE(IWL_22000_UCODE_API_MAX));
 MODULE_FIRMWARE(IWL_QNJ_B_JF_B_MODULE_FIRMWARE(IWL_22000_UCODE_API_MAX));
 MODULE_FIRMWARE(IWL_CC_A_MODULE_FIRMWARE(IWL_22000_UCODE_API_MAX));
 MODULE_FIRMWARE(IWL_22000_SO_A_JF_B_MODULE_FIRMWARE(IWL_22000_UCODE_API_MAX));
diff --git a/drivers/net/wireless/intel/iwlwifi/cfg/5000.c b/drivers/net/wireless/intel/iwlwifi/cfg/5000.c
index 575a7022d045..3846064d51a5 100644
--- a/drivers/net/wireless/intel/iwlwifi/cfg/5000.c
+++ b/drivers/net/wireless/intel/iwlwifi/cfg/5000.c
@@ -1,7 +1,7 @@
 /******************************************************************************
  *
  * Copyright(c) 2007 - 2014 Intel Corporation. All rights reserved.
- * Copyright(c) 2018 Intel Corporation
+ * Copyright(c) 2018 - 2019 Intel Corporation
  *
  * This program is free software; you can redistribute it and/or modify it
  * under the terms of version 2 of the GNU General Public License as
@@ -136,6 +136,7 @@ const struct iwl_cfg iwl5350_agn_cfg = {
 	.ht_params = &iwl5000_ht_params,
 	.led_mode = IWL_LED_BLINK,
 	.internal_wimax_coex = true,
+	.csr = &iwl_csr_v1,
 };
 
 #define IWL_DEVICE_5150						\
diff --git a/drivers/net/wireless/intel/iwlwifi/fw/dbg.c b/drivers/net/wireless/intel/iwlwifi/fw/dbg.c
index f119c49cd39c..d7380016f1c0 100644
--- a/drivers/net/wireless/intel/iwlwifi/fw/dbg.c
+++ b/drivers/net/wireless/intel/iwlwifi/fw/dbg.c
@@ -1614,6 +1614,7 @@ iwl_dump_ini_mem(struct iwl_fw_runtime *fwrt,
 	if (!range) {
 		IWL_ERR(fwrt, "Failed to fill region header: id=%d, type=%d\n",
 			le32_to_cpu(reg->region_id), type);
+		memset(*data, 0, le32_to_cpu((*data)->len));
 		return;
 	}
 
@@ -1623,6 +1624,7 @@ iwl_dump_ini_mem(struct iwl_fw_runtime *fwrt,
 		if (range_size < 0) {
 			IWL_ERR(fwrt, "Failed to dump region: id=%d, type=%d\n",
 				le32_to_cpu(reg->region_id), type);
+			memset(*data, 0, le32_to_cpu((*data)->len));
 			return;
 		}
 		range = range + range_size;
@@ -1807,12 +1809,12 @@ _iwl_fw_error_ini_dump(struct iwl_fw_runtime *fwrt,
 
 	trigger = fwrt->dump.active_trigs[id].trig;
 
-	size = sizeof(*dump_file);
-	size += iwl_fw_ini_get_trigger_len(fwrt, trigger);
-
+	size = iwl_fw_ini_get_trigger_len(fwrt, trigger);
 	if (!size)
 		return NULL;
 
+	size += sizeof(*dump_file);
+
 	dump_file = vzalloc(size);
 	if (!dump_file)
 		return NULL;
@@ -1942,14 +1944,10 @@ int iwl_fw_dbg_error_collect(struct iwl_fw_runtime *fwrt,
 	iwl_dump_error_desc->len = 0;
 
 	ret = iwl_fw_dbg_collect_desc(fwrt, iwl_dump_error_desc, false, 0);
-	if (ret) {
+	if (ret)
 		kfree(iwl_dump_error_desc);
-	} else {
-		set_bit(STATUS_FW_WAIT_DUMP, &fwrt->trans->status);
-
-		/* trigger nmi to halt the fw */
-		iwl_force_nmi(fwrt->trans);
-	}
+	else
+		iwl_trans_sync_nmi(fwrt->trans);
 
 	return ret;
 }
@@ -2489,22 +2487,6 @@ IWL_EXPORT_SYMBOL(iwl_fw_dbg_apply_point);
 
 void iwl_fwrt_stop_device(struct iwl_fw_runtime *fwrt)
 {
-	/* if the wait event timeout elapses instead of wake up then
-	 * the driver did not receive NMI interrupt and can not assume the FW
-	 * is halted
-	 */
-	int ret = wait_event_timeout(fwrt->trans->fw_halt_waitq,
-				     !test_bit(STATUS_FW_WAIT_DUMP,
-					       &fwrt->trans->status),
-				     msecs_to_jiffies(2000));
-	if (!ret) {
-		/* failed to receive NMI interrupt, assuming the FW is stuck */
-		set_bit(STATUS_FW_ERROR, &fwrt->trans->status);
-
-		clear_bit(STATUS_FW_WAIT_DUMP, &fwrt->trans->status);
-	}
-
-	/* Assuming the op mode mutex is held at this point */
 	iwl_fw_dbg_collect_sync(fwrt);
 
 	iwl_trans_stop_device(fwrt->trans);
diff --git a/drivers/net/wireless/intel/iwlwifi/fw/file.h b/drivers/net/wireless/intel/iwlwifi/fw/file.h
index 641c95d03b15..e06407dc088b 100644
--- a/drivers/net/wireless/intel/iwlwifi/fw/file.h
+++ b/drivers/net/wireless/intel/iwlwifi/fw/file.h
@@ -93,7 +93,7 @@ struct iwl_ucode_header {
 	} u;
 };
 
-#define IWL_UCODE_INI_TLV_GROUP	BIT(24)
+#define IWL_UCODE_INI_TLV_GROUP	0x1000000
 
 /*
  * new TLV uCode file layout
@@ -148,11 +148,14 @@ enum iwl_ucode_tlv_type {
 	IWL_UCODE_TLV_UMAC_DEBUG_ADDRS	= 54,
 	IWL_UCODE_TLV_LMAC_DEBUG_ADDRS	= 55,
 	IWL_UCODE_TLV_FW_RECOVERY_INFO	= 57,
-	IWL_UCODE_TLV_TYPE_BUFFER_ALLOCATION	= IWL_UCODE_INI_TLV_GROUP | 0x1,
-	IWL_UCODE_TLV_TYPE_HCMD			= IWL_UCODE_INI_TLV_GROUP | 0x2,
-	IWL_UCODE_TLV_TYPE_REGIONS		= IWL_UCODE_INI_TLV_GROUP | 0x3,
-	IWL_UCODE_TLV_TYPE_TRIGGERS		= IWL_UCODE_INI_TLV_GROUP | 0x4,
-	IWL_UCODE_TLV_TYPE_DEBUG_FLOW		= IWL_UCODE_INI_TLV_GROUP | 0x5,
+
+	IWL_UCODE_TLV_TYPE_BUFFER_ALLOCATION	= IWL_UCODE_INI_TLV_GROUP + 0x1,
+	IWL_UCODE_TLV_DEBUG_BASE = IWL_UCODE_TLV_TYPE_BUFFER_ALLOCATION,
+	IWL_UCODE_TLV_TYPE_HCMD			= IWL_UCODE_INI_TLV_GROUP + 0x2,
+	IWL_UCODE_TLV_TYPE_REGIONS		= IWL_UCODE_INI_TLV_GROUP + 0x3,
+	IWL_UCODE_TLV_TYPE_TRIGGERS		= IWL_UCODE_INI_TLV_GROUP + 0x4,
+	IWL_UCODE_TLV_TYPE_DEBUG_FLOW		= IWL_UCODE_INI_TLV_GROUP + 0x5,
+	IWL_UCODE_TLV_DEBUG_MAX = IWL_UCODE_TLV_TYPE_DEBUG_FLOW,
 
 	/* TLVs 0x1000-0x2000 are for internal driver usage */
 	IWL_UCODE_TLV_FW_DBG_DUMP_LST	= 0x1000,
diff --git a/drivers/net/wireless/intel/iwlwifi/fw/init.c b/drivers/net/wireless/intel/iwlwifi/fw/init.c
index 7adf4e4e841a..12310e3d2fc5 100644
--- a/drivers/net/wireless/intel/iwlwifi/fw/init.c
+++ b/drivers/net/wireless/intel/iwlwifi/fw/init.c
@@ -76,7 +76,6 @@ void iwl_fw_runtime_init(struct iwl_fw_runtime *fwrt, struct iwl_trans *trans,
 	fwrt->ops_ctx = ops_ctx;
 	INIT_DELAYED_WORK(&fwrt->dump.wk, iwl_fw_error_dump_wk);
 	iwl_fwrt_dbgfs_register(fwrt, dbgfs_dir);
-	init_waitqueue_head(&fwrt->trans->fw_halt_waitq);
 }
 IWL_EXPORT_SYMBOL(iwl_fw_runtime_init);
 
diff --git a/drivers/net/wireless/intel/iwlwifi/iwl-config.h b/drivers/net/wireless/intel/iwlwifi/iwl-config.h
index f5f87773667b..93070848280a 100644
--- a/drivers/net/wireless/intel/iwlwifi/iwl-config.h
+++ b/drivers/net/wireless/intel/iwlwifi/iwl-config.h
@@ -549,8 +549,9 @@ extern const struct iwl_cfg iwl22000_2ac_cfg_hr;
 extern const struct iwl_cfg iwl22000_2ac_cfg_hr_cdb;
 extern const struct iwl_cfg iwl22000_2ac_cfg_jf;
 extern const struct iwl_cfg iwl_ax101_cfg_qu_hr;
+extern const struct iwl_cfg iwl_ax101_cfg_quz_hr;
 extern const struct iwl_cfg iwl22000_2ax_cfg_hr;
-extern const struct iwl_cfg iwl22260_2ax_cfg;
+extern const struct iwl_cfg iwl_ax200_cfg_cc;
 extern const struct iwl_cfg killer1650s_2ax_cfg_qu_b0_hr_b0;
 extern const struct iwl_cfg killer1650i_2ax_cfg_qu_b0_hr_b0;
 extern const struct iwl_cfg killer1650x_2ax_cfg;
diff --git a/drivers/net/wireless/intel/iwlwifi/iwl-csr.h b/drivers/net/wireless/intel/iwlwifi/iwl-csr.h
index aea6d03e545a..e539bc94eff7 100644
--- a/drivers/net/wireless/intel/iwlwifi/iwl-csr.h
+++ b/drivers/net/wireless/intel/iwlwifi/iwl-csr.h
@@ -327,6 +327,7 @@ enum {
 #define CSR_HW_REV_TYPE_NONE		(0x00001F0)
 #define CSR_HW_REV_TYPE_QNJ		(0x0000360)
 #define CSR_HW_REV_TYPE_QNJ_B0		(0x0000364)
+#define CSR_HW_REV_TYPE_QUZ		(0x0000354)
 #define CSR_HW_REV_TYPE_HR_CDB		(0x0000340)
 #define CSR_HW_REV_TYPE_SO		(0x0000370)
 #define CSR_HW_REV_TYPE_TY		(0x0000420)
diff --git a/drivers/net/wireless/intel/iwlwifi/iwl-dbg-tlv.c b/drivers/net/wireless/intel/iwlwifi/iwl-dbg-tlv.c
index 5798f434f68f..c7070760a10a 100644
--- a/drivers/net/wireless/intel/iwlwifi/iwl-dbg-tlv.c
+++ b/drivers/net/wireless/intel/iwlwifi/iwl-dbg-tlv.c
@@ -126,7 +126,8 @@ void iwl_alloc_dbg_tlv(struct iwl_trans *trans, size_t len, const u8 *data,
 		len -= ALIGN(tlv_len, 4);
 		data += sizeof(*tlv) + ALIGN(tlv_len, 4);
 
-		if (!(tlv_type & IWL_UCODE_INI_TLV_GROUP))
+		if (tlv_type < IWL_UCODE_TLV_DEBUG_BASE ||
+		    tlv_type > IWL_UCODE_TLV_DEBUG_MAX)
 			continue;
 
 		hdr = (void *)&tlv->data[0];
diff --git a/drivers/net/wireless/intel/iwlwifi/iwl-trans.h b/drivers/net/wireless/intel/iwlwifi/iwl-trans.h
index bbebbf3efd57..d8690acee40c 100644
--- a/drivers/net/wireless/intel/iwlwifi/iwl-trans.h
+++ b/drivers/net/wireless/intel/iwlwifi/iwl-trans.h
@@ -338,7 +338,6 @@ enum iwl_d3_status {
  *	are sent
  * @STATUS_TRANS_IDLE: the trans is idle - general commands are not to be sent
  * @STATUS_TRANS_DEAD: trans is dead - avoid any read/write operation
- * @STATUS_FW_WAIT_DUMP: if set, wait until cleared before collecting dump
  */
 enum iwl_trans_status {
 	STATUS_SYNC_HCMD_ACTIVE,
@@ -351,7 +350,6 @@ enum iwl_trans_status {
 	STATUS_TRANS_GOING_IDLE,
 	STATUS_TRANS_IDLE,
 	STATUS_TRANS_DEAD,
-	STATUS_FW_WAIT_DUMP,
 };
 
 static inline int
@@ -618,6 +616,7 @@ struct iwl_trans_ops {
 	struct iwl_trans_dump_data *(*dump_data)(struct iwl_trans *trans,
 						 u32 dump_mask);
 	void (*debugfs_cleanup)(struct iwl_trans *trans);
+	void (*sync_nmi)(struct iwl_trans *trans);
 };
 
 /**
@@ -831,7 +830,6 @@ struct iwl_trans {
 	u32 lmac_error_event_table[2];
 	u32 umac_error_event_table;
 	unsigned int error_event_table_tlv_status;
-	wait_queue_head_t fw_halt_waitq;
 
 	/* pointer to trans specific struct */
 	/*Ensure that this pointer will always be aligned to sizeof pointer */
@@ -1239,10 +1237,12 @@ static inline void iwl_trans_fw_error(struct iwl_trans *trans)
 	/* prevent double restarts due to the same erroneous FW */
 	if (!test_and_set_bit(STATUS_FW_ERROR, &trans->status))
 		iwl_op_mode_nic_error(trans->op_mode);
+}
 
-	if (test_and_clear_bit(STATUS_FW_WAIT_DUMP, &trans->status))
-		wake_up(&trans->fw_halt_waitq);
-
+static inline void iwl_trans_sync_nmi(struct iwl_trans *trans)
+{
+	if (trans->ops->sync_nmi)
+		trans->ops->sync_nmi(trans);
 }
 
 /*****************************************************
diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/debugfs-vif.c b/drivers/net/wireless/intel/iwlwifi/mvm/debugfs-vif.c
index 2453ceabf00d..6925527d8457 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/debugfs-vif.c
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/debugfs-vif.c
@@ -774,8 +774,7 @@ void iwl_mvm_vif_dbgfs_register(struct iwl_mvm *mvm, struct ieee80211_vif *vif)
 		return;
 
 	mvmvif->dbgfs_dir = debugfs_create_dir("iwlmvm", dbgfs_dir);
-
-	if (!mvmvif->dbgfs_dir) {
+	if (IS_ERR_OR_NULL(mvmvif->dbgfs_dir)) {
 		IWL_ERR(mvm, "Failed to create debugfs directory under %pd\n",
 			dbgfs_dir);
 		return;
diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/ftm-initiator.c b/drivers/net/wireless/intel/iwlwifi/mvm/ftm-initiator.c
index e9822a3ec373..94132cfd1f56 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/ftm-initiator.c
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/ftm-initiator.c
@@ -460,9 +460,7 @@ static int iwl_mvm_ftm_range_resp_valid(struct iwl_mvm *mvm, u8 request_id,
 static void iwl_mvm_debug_range_resp(struct iwl_mvm *mvm, u8 index,
 				     struct cfg80211_pmsr_result *res)
 {
-	s64 rtt_avg = res->ftm.rtt_avg * 100;
-
-	do_div(rtt_avg, 6666);
+	s64 rtt_avg = div_s64(res->ftm.rtt_avg * 100, 6666);
 
 	IWL_DEBUG_INFO(mvm, "entry %d\n", index);
 	IWL_DEBUG_INFO(mvm, "\tstatus: %d\n", res->status);
diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/fw.c b/drivers/net/wireless/intel/iwlwifi/mvm/fw.c
index 00a47f6f1d81..ab68b5d53ec9 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/fw.c
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/fw.c
@@ -1121,7 +1121,9 @@ int iwl_mvm_up(struct iwl_mvm *mvm)
 	ret = iwl_mvm_load_rt_fw(mvm);
 	if (ret) {
 		IWL_ERR(mvm, "Failed to start RT ucode: %d\n", ret);
-		iwl_fw_dbg_error_collect(&mvm->fwrt, FW_DBG_TRIGGER_DRIVER);
+		if (ret != -ERFKILL)
+			iwl_fw_dbg_error_collect(&mvm->fwrt,
+						 FW_DBG_TRIGGER_DRIVER);
 		goto error;
 	}
 
diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/mac80211.c b/drivers/net/wireless/intel/iwlwifi/mvm/mac80211.c
index 3a92c09d4692..6a3b11dd2edf 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/mac80211.c
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/mac80211.c
@@ -2714,9 +2714,6 @@ static void iwl_mvm_stop_ap_ibss(struct ieee80211_hw *hw,
 
 	iwl_mvm_mac_ctxt_remove(mvm, vif);
 
-	kfree(mvmvif->ap_wep_key);
-	mvmvif->ap_wep_key = NULL;
-
 	mutex_unlock(&mvm->mutex);
 }
 
@@ -3183,24 +3180,7 @@ static int iwl_mvm_mac_sta_state(struct ieee80211_hw *hw,
 		ret = iwl_mvm_update_sta(mvm, vif, sta);
 	} else if (old_state == IEEE80211_STA_ASSOC &&
 		   new_state == IEEE80211_STA_AUTHORIZED) {
-		/* if wep is used, need to set the key for the station now */
-		if (vif->type == NL80211_IFTYPE_AP && mvmvif->ap_wep_key) {
-			mvm_sta->wep_key =
-				kmemdup(mvmvif->ap_wep_key,
-					sizeof(*mvmvif->ap_wep_key) +
-					mvmvif->ap_wep_key->keylen,
-					GFP_KERNEL);
-			if (!mvm_sta->wep_key) {
-				ret = -ENOMEM;
-				goto out_unlock;
-			}
-
-			ret = iwl_mvm_set_sta_key(mvm, vif, sta,
-						  mvm_sta->wep_key,
-						  STA_KEY_IDX_INVALID);
-		} else {
-			ret = 0;
-		}
+		ret = 0;
 
 		/* we don't support TDLS during DCM */
 		if (iwl_mvm_phy_ctx_count(mvm) > 1)
@@ -3242,17 +3222,6 @@ static int iwl_mvm_mac_sta_state(struct ieee80211_hw *hw,
 						   NL80211_TDLS_DISABLE_LINK);
 		}
 
-		/* Remove STA key if this is an AP using WEP */
-		if (vif->type == NL80211_IFTYPE_AP && mvmvif->ap_wep_key) {
-			int rm_ret = iwl_mvm_remove_sta_key(mvm, vif, sta,
-							    mvm_sta->wep_key);
-
-			if (!ret)
-				ret = rm_ret;
-			kfree(mvm_sta->wep_key);
-			mvm_sta->wep_key = NULL;
-		}
-
 		if (unlikely(ret &&
 			     test_bit(IWL_MVM_STATUS_HW_RESTART_REQUESTED,
 				      &mvm->status)))
@@ -3289,6 +3258,13 @@ static void iwl_mvm_sta_rc_update(struct ieee80211_hw *hw,
 				  struct ieee80211_sta *sta, u32 changed)
 {
 	struct iwl_mvm *mvm = IWL_MAC80211_GET_MVM(hw);
+	struct iwl_mvm_vif *mvmvif = iwl_mvm_vif_from_mac80211(vif);
+
+	if (changed & (IEEE80211_RC_BW_CHANGED |
+		       IEEE80211_RC_SUPP_RATES_CHANGED |
+		       IEEE80211_RC_NSS_CHANGED))
+		iwl_mvm_rs_rate_init(mvm, sta, mvmvif->phy_ctxt->channel->band,
+				     true);
 
 	if (vif->type == NL80211_IFTYPE_STATION &&
 	    changed & IEEE80211_RC_NSS_CHANGED)
@@ -3439,20 +3415,12 @@ static int iwl_mvm_mac_set_key(struct ieee80211_hw *hw,
 		break;
 	case WLAN_CIPHER_SUITE_WEP40:
 	case WLAN_CIPHER_SUITE_WEP104:
-		if (vif->type == NL80211_IFTYPE_AP) {
-			struct iwl_mvm_vif *mvmvif =
-				iwl_mvm_vif_from_mac80211(vif);
-
-			mvmvif->ap_wep_key = kmemdup(key,
-						     sizeof(*key) + key->keylen,
-						     GFP_KERNEL);
-			if (!mvmvif->ap_wep_key)
-				return -ENOMEM;
-		}
-
-		if (vif->type != NL80211_IFTYPE_STATION)
-			return 0;
-		break;
+		if (vif->type == NL80211_IFTYPE_STATION)
+			break;
+		if (iwl_mvm_has_new_tx_api(mvm))
+			return -EOPNOTSUPP;
+		/* support HW crypto on TX */
+		return 0;
 	default:
 		/* currently FW supports only one optional cipher scheme */
 		if (hw->n_cipher_schemes &&
@@ -3540,12 +3508,17 @@ static int iwl_mvm_mac_set_key(struct ieee80211_hw *hw,
 		ret = iwl_mvm_set_sta_key(mvm, vif, sta, key, key_offset);
 		if (ret) {
 			IWL_WARN(mvm, "set key failed\n");
+			key->hw_key_idx = STA_KEY_IDX_INVALID;
 			/*
 			 * can't add key for RX, but we don't need it
-			 * in the device for TX so still return 0
+			 * in the device for TX so still return 0,
+			 * unless we have new TX API where we cannot
+			 * put key material into the TX_CMD
 			 */
-			key->hw_key_idx = STA_KEY_IDX_INVALID;
-			ret = 0;
+			if (iwl_mvm_has_new_tx_api(mvm))
+				ret = -EOPNOTSUPP;
+			else
+				ret = 0;
 		}
 
 		break;
diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/mvm.h b/drivers/net/wireless/intel/iwlwifi/mvm/mvm.h
index bca6f6b536d9..a50dc53df086 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/mvm.h
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/mvm.h
@@ -498,7 +498,6 @@ struct iwl_mvm_vif {
 	netdev_features_t features;
 
 	struct iwl_probe_resp_data __rcu *probe_resp_data;
-	struct ieee80211_key_conf *ap_wep_key;
 };
 
 static inline struct iwl_mvm_vif *
diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/ops.c b/drivers/net/wireless/intel/iwlwifi/mvm/ops.c
index ba27dce4c2bb..13681b03c10e 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/ops.c
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/ops.c
@@ -834,7 +834,7 @@ iwl_op_mode_mvm_start(struct iwl_trans *trans, const struct iwl_cfg *cfg,
 	mutex_lock(&mvm->mutex);
 	iwl_mvm_ref(mvm, IWL_MVM_REF_INIT_UCODE);
 	err = iwl_run_init_mvm_ucode(mvm, true);
-	if (err)
+	if (err && err != -ERFKILL)
 		iwl_fw_dbg_error_collect(&mvm->fwrt, FW_DBG_TRIGGER_DRIVER);
 	if (!iwlmvm_mod_params.init_dbg || !err)
 		iwl_mvm_stop_device(mvm);
diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/rxmq.c b/drivers/net/wireless/intel/iwlwifi/mvm/rxmq.c
index 1e03acf30762..b516fd1867ec 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/rxmq.c
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/rxmq.c
@@ -169,9 +169,9 @@ static inline int iwl_mvm_check_pn(struct iwl_mvm *mvm, struct sk_buff *skb,
 }
 
 /* iwl_mvm_create_skb Adds the rxb to a new skb */
-static void iwl_mvm_create_skb(struct sk_buff *skb, struct ieee80211_hdr *hdr,
-			       u16 len, u8 crypt_len,
-			       struct iwl_rx_cmd_buffer *rxb)
+static int iwl_mvm_create_skb(struct iwl_mvm *mvm, struct sk_buff *skb,
+			      struct ieee80211_hdr *hdr, u16 len, u8 crypt_len,
+			      struct iwl_rx_cmd_buffer *rxb)
 {
 	struct iwl_rx_packet *pkt = rxb_addr(rxb);
 	struct iwl_rx_mpdu_desc *desc = (void *)pkt->data;
@@ -204,6 +204,20 @@ static void iwl_mvm_create_skb(struct sk_buff *skb, struct ieee80211_hdr *hdr,
 	 * present before copying packet data.
 	 */
 	hdrlen += crypt_len;
+
+	if (WARN_ONCE(headlen < hdrlen,
+		      "invalid packet lengths (hdrlen=%d, len=%d, crypt_len=%d)\n",
+		      hdrlen, len, crypt_len)) {
+		/*
+		 * We warn and trace because we want to be able to see
+		 * it in trace-cmd as well.
+		 */
+		IWL_DEBUG_RX(mvm,
+			     "invalid packet lengths (hdrlen=%d, len=%d, crypt_len=%d)\n",
+			     hdrlen, len, crypt_len);
+		return -EINVAL;
+	}
+
 	skb_put_data(skb, hdr, hdrlen);
 	skb_put_data(skb, (u8 *)hdr + hdrlen + pad_len, headlen - hdrlen);
 
@@ -216,6 +230,8 @@ static void iwl_mvm_create_skb(struct sk_buff *skb, struct ieee80211_hdr *hdr,
 		skb_add_rx_frag(skb, 0, rxb_steal_page(rxb), offset,
 				fraglen, rxb->truesize);
 	}
+
+	return 0;
 }
 
 static void iwl_mvm_add_rtap_sniffer_config(struct iwl_mvm *mvm,
@@ -1671,7 +1687,11 @@ void iwl_mvm_rx_mpdu_mq(struct iwl_mvm *mvm, struct napi_struct *napi,
 			rx_status->boottime_ns = ktime_get_boot_ns();
 	}
 
-	iwl_mvm_create_skb(skb, hdr, len, crypt_len, rxb);
+	if (iwl_mvm_create_skb(mvm, skb, hdr, len, crypt_len, rxb)) {
+		kfree_skb(skb);
+		goto out;
+	}
+
 	if (!iwl_mvm_reorder(mvm, napi, queue, sta, skb, desc))
 		iwl_mvm_pass_packet_to_mac80211(mvm, napi, skb, queue,
 						sta, csi);
diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/sta.c b/drivers/net/wireless/intel/iwlwifi/mvm/sta.c
index 498c315291cf..98d123dd7177 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/sta.c
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/sta.c
@@ -8,7 +8,7 @@
  * Copyright(c) 2012 - 2015 Intel Corporation. All rights reserved.
  * Copyright(c) 2013 - 2015 Intel Mobile Communications GmbH
  * Copyright(c) 2016 - 2017 Intel Deutschland GmbH
- * Copyright(c) 2018 Intel Corporation
+ * Copyright(c) 2018 - 2019 Intel Corporation
  *
  * This program is free software; you can redistribute it and/or modify
  * it under the terms of version 2 of the GNU General Public License as
@@ -31,7 +31,7 @@
  * Copyright(c) 2012 - 2015 Intel Corporation. All rights reserved.
  * Copyright(c) 2013 - 2015 Intel Mobile Communications GmbH
  * Copyright(c) 2016 - 2017 Intel Deutschland GmbH
- * Copyright(c) 2018 Intel Corporation
+ * Copyright(c) 2018 - 2019 Intel Corporation
  * All rights reserved.
  *
  * Redistribution and use in source and binary forms, with or without
@@ -1399,7 +1399,9 @@ void iwl_mvm_add_new_dqa_stream_wk(struct work_struct *wk)
 
 		iwl_mvm_sta_alloc_queue(mvm, txq->sta, txq->ac, tid);
 		list_del_init(&mvmtxq->list);
+		local_bh_disable();
 		iwl_mvm_mac_itxq_xmit(mvm->hw, txq);
+		local_bh_enable();
 	}
 
 	mutex_unlock(&mvm->mutex);
@@ -2333,21 +2335,6 @@ int iwl_mvm_add_mcast_sta(struct iwl_mvm *mvm, struct ieee80211_vif *vif)
 		iwl_mvm_enable_txq(mvm, NULL, mvmvif->cab_queue, 0, &cfg,
 				   timeout);
 
-	if (mvmvif->ap_wep_key) {
-		u8 key_offset = iwl_mvm_set_fw_key_idx(mvm);
-
-		__set_bit(key_offset, mvm->fw_key_table);
-
-		if (key_offset == STA_KEY_IDX_INVALID)
-			return -ENOSPC;
-
-		ret = iwl_mvm_send_sta_key(mvm, mvmvif->mcast_sta.sta_id,
-					   mvmvif->ap_wep_key, true, 0, NULL, 0,
-					   key_offset, 0);
-		if (ret)
-			return ret;
-	}
-
 	return 0;
 }
 
@@ -2419,28 +2406,6 @@ int iwl_mvm_rm_mcast_sta(struct iwl_mvm *mvm, struct ieee80211_vif *vif)
 
 	iwl_mvm_disable_txq(mvm, NULL, mvmvif->cab_queue, 0, 0);
 
-	if (mvmvif->ap_wep_key) {
-		int i;
-
-		if (!__test_and_clear_bit(mvmvif->ap_wep_key->hw_key_idx,
-					  mvm->fw_key_table)) {
-			IWL_ERR(mvm, "offset %d not used in fw key table.\n",
-				mvmvif->ap_wep_key->hw_key_idx);
-			return -ENOENT;
-		}
-
-		/* track which key was deleted last */
-		for (i = 0; i < STA_KEY_MAX_NUM; i++) {
-			if (mvm->fw_key_deleted[i] < U8_MAX)
-				mvm->fw_key_deleted[i]++;
-		}
-		mvm->fw_key_deleted[mvmvif->ap_wep_key->hw_key_idx] = 0;
-		ret = __iwl_mvm_remove_sta_key(mvm, mvmvif->mcast_sta.sta_id,
-					       mvmvif->ap_wep_key, true);
-		if (ret)
-			return ret;
-	}
-
 	ret = iwl_mvm_rm_sta_common(mvm, mvmvif->mcast_sta.sta_id);
 	if (ret)
 		IWL_WARN(mvm, "Failed sending remove station\n");
diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/sta.h b/drivers/net/wireless/intel/iwlwifi/mvm/sta.h
index 79700c7310a1..b4d4071b865d 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/sta.h
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/sta.h
@@ -8,7 +8,7 @@
  * Copyright(c) 2012 - 2014 Intel Corporation. All rights reserved.
  * Copyright(c) 2013 - 2014 Intel Mobile Communications GmbH
  * Copyright(c) 2015 - 2016 Intel Deutschland GmbH
- * Copyright(c) 2018 Intel Corporation
+ * Copyright(c) 2018 - 2019 Intel Corporation
  *
  * This program is free software; you can redistribute it and/or modify
  * it under the terms of version 2 of the GNU General Public License as
@@ -31,7 +31,7 @@
  * Copyright(c) 2012 - 2014 Intel Corporation. All rights reserved.
  * Copyright(c) 2013 - 2014 Intel Mobile Communications GmbH
  * Copyright(c) 2015 - 2016 Intel Deutschland GmbH
- * Copyright(c) 2018 Intel Corporation
+ * Copyright(c) 2018 - 2019 Intel Corporation
  * All rights reserved.
  *
  * Redistribution and use in source and binary forms, with or without
@@ -394,7 +394,6 @@ struct iwl_mvm_rxq_dup_data {
  *	the BA window. To be used for UAPSD only.
  * @ptk_pn: per-queue PTK PN data structures
  * @dup_data: per queue duplicate packet detection data
- * @wep_key: used in AP mode. Is a duplicate of the WEP key.
  * @deferred_traffic_tid_map: indication bitmap of deferred traffic per-TID
  * @tx_ant: the index of the antenna to use for data tx to this station. Only
  *	used during connection establishment (e.g. for the 4 way handshake
@@ -426,8 +425,6 @@ struct iwl_mvm_sta {
 	struct iwl_mvm_key_pn __rcu *ptk_pn[4];
 	struct iwl_mvm_rxq_dup_data *dup_data;
 
-	struct ieee80211_key_conf *wep_key;
-
 	u8 reserved_queue;
 
 	/* Temporary, until the new TLC will control the Tx protection */
diff --git a/drivers/net/wireless/intel/iwlwifi/pcie/drv.c b/drivers/net/wireless/intel/iwlwifi/pcie/drv.c
index 2b94e4cef56c..9f1af8da9dc1 100644
--- a/drivers/net/wireless/intel/iwlwifi/pcie/drv.c
+++ b/drivers/net/wireless/intel/iwlwifi/pcie/drv.c
@@ -953,14 +953,15 @@ static const struct pci_device_id iwl_hw_card_ids[] = {
 	{IWL_PCI_DEVICE(0xA0F0, 0x1652, killer1650i_2ax_cfg_qu_b0_hr_b0)},
 	{IWL_PCI_DEVICE(0xA0F0, 0x4070, iwl_ax101_cfg_qu_hr)},
 
-	{IWL_PCI_DEVICE(0x2723, 0x0080, iwl22260_2ax_cfg)},
-	{IWL_PCI_DEVICE(0x2723, 0x0084, iwl22260_2ax_cfg)},
-	{IWL_PCI_DEVICE(0x2723, 0x0088, iwl22260_2ax_cfg)},
-	{IWL_PCI_DEVICE(0x2723, 0x008C, iwl22260_2ax_cfg)},
+	{IWL_PCI_DEVICE(0x2723, 0x0080, iwl_ax200_cfg_cc)},
+	{IWL_PCI_DEVICE(0x2723, 0x0084, iwl_ax200_cfg_cc)},
+	{IWL_PCI_DEVICE(0x2723, 0x0088, iwl_ax200_cfg_cc)},
+	{IWL_PCI_DEVICE(0x2723, 0x008C, iwl_ax200_cfg_cc)},
 	{IWL_PCI_DEVICE(0x2723, 0x1653, killer1650w_2ax_cfg)},
 	{IWL_PCI_DEVICE(0x2723, 0x1654, killer1650x_2ax_cfg)},
-	{IWL_PCI_DEVICE(0x2723, 0x4080, iwl22260_2ax_cfg)},
-	{IWL_PCI_DEVICE(0x2723, 0x4088, iwl22260_2ax_cfg)},
+	{IWL_PCI_DEVICE(0x2723, 0x2080, iwl_ax200_cfg_cc)},
+	{IWL_PCI_DEVICE(0x2723, 0x4080, iwl_ax200_cfg_cc)},
+	{IWL_PCI_DEVICE(0x2723, 0x4088, iwl_ax200_cfg_cc)},
 
 	{IWL_PCI_DEVICE(0x1a56, 0x1653, killer1650w_2ax_cfg)},
 	{IWL_PCI_DEVICE(0x1a56, 0x1654, killer1650x_2ax_cfg)},
diff --git a/drivers/net/wireless/intel/iwlwifi/pcie/internal.h b/drivers/net/wireless/intel/iwlwifi/pcie/internal.h
index bf8b61a476c5..59213164f35e 100644
--- a/drivers/net/wireless/intel/iwlwifi/pcie/internal.h
+++ b/drivers/net/wireless/intel/iwlwifi/pcie/internal.h
@@ -1043,7 +1043,7 @@ static inline bool iwl_pcie_dbg_on(struct iwl_trans *trans)
 
 void iwl_trans_pcie_rf_kill(struct iwl_trans *trans, bool state);
 void iwl_trans_pcie_dump_regs(struct iwl_trans *trans);
-void iwl_trans_sync_nmi(struct iwl_trans *trans);
+void iwl_trans_pcie_sync_nmi(struct iwl_trans *trans);
 
 #ifdef CONFIG_IWLWIFI_DEBUGFS
 int iwl_trans_pcie_dbgfs_register(struct iwl_trans *trans);
diff --git a/drivers/net/wireless/intel/iwlwifi/pcie/trans.c b/drivers/net/wireless/intel/iwlwifi/pcie/trans.c
index fe8269d023de..4f5eec7e44bd 100644
--- a/drivers/net/wireless/intel/iwlwifi/pcie/trans.c
+++ b/drivers/net/wireless/intel/iwlwifi/pcie/trans.c
@@ -2067,7 +2067,6 @@ static void iwl_trans_pcie_release_nic_access(struct iwl_trans *trans,
 	 * MAC_ACCESS_REQ bit to be performed before any other writes
 	 * scheduled on different CPUs (after we drop reg_lock).
 	 */
-	mmiowb();
 out:
 	spin_unlock_irqrestore(&trans_pcie->reg_lock, *flags);
 }
@@ -3318,7 +3317,8 @@ static void iwl_trans_pcie_resume(struct iwl_trans *trans)
 	.unref = iwl_trans_pcie_unref,					\
 	.dump_data = iwl_trans_pcie_dump_data,				\
 	.d3_suspend = iwl_trans_pcie_d3_suspend,			\
-	.d3_resume = iwl_trans_pcie_d3_resume
+	.d3_resume = iwl_trans_pcie_d3_resume,				\
+	.sync_nmi = iwl_trans_pcie_sync_nmi
 
 #ifdef CONFIG_PM_SLEEP
 #define IWL_TRANS_PM_OPS						\
@@ -3542,6 +3542,10 @@ struct iwl_trans *iwl_trans_pcie_alloc(struct pci_dev *pdev,
 		}
 	} else if (cfg == &iwl_ax101_cfg_qu_hr) {
 		if (CSR_HW_RF_ID_TYPE_CHIP_ID(trans->hw_rf_id) ==
+		    CSR_HW_RF_ID_TYPE_CHIP_ID(CSR_HW_RF_ID_TYPE_HR) &&
+		    trans->hw_rev == CSR_HW_REV_TYPE_QNJ_B0) {
+			trans->cfg = &iwl22000_2ax_cfg_qnj_hr_b0;
+		} else if (CSR_HW_RF_ID_TYPE_CHIP_ID(trans->hw_rf_id) ==
 		    CSR_HW_RF_ID_TYPE_CHIP_ID(CSR_HW_RF_ID_TYPE_HR)) {
 			trans->cfg = &iwl_ax101_cfg_qu_hr;
 		} else if (CSR_HW_RF_ID_TYPE_CHIP_ID(trans->hw_rf_id) ==
@@ -3560,7 +3564,7 @@ struct iwl_trans *iwl_trans_pcie_alloc(struct pci_dev *pdev,
 		}
 	} else if (CSR_HW_RF_ID_TYPE_CHIP_ID(trans->hw_rf_id) ==
 		   CSR_HW_RF_ID_TYPE_CHIP_ID(CSR_HW_RF_ID_TYPE_HR) &&
-		   (trans->cfg != &iwl22260_2ax_cfg ||
+		   (trans->cfg != &iwl_ax200_cfg_cc ||
 		    trans->hw_rev == CSR_HW_REV_TYPE_QNJ_B0)) {
 		u32 hw_status;
 
@@ -3637,22 +3641,29 @@ out_no_pci:
 	return ERR_PTR(ret);
 }
 
-void iwl_trans_sync_nmi(struct iwl_trans *trans)
+void iwl_trans_pcie_sync_nmi(struct iwl_trans *trans)
 {
+	struct iwl_trans_pcie *trans_pcie = IWL_TRANS_GET_PCIE_TRANS(trans);
 	unsigned long timeout = jiffies + IWL_TRANS_NMI_TIMEOUT;
+	u32 inta_addr, sw_err_bit;
+
+	if (trans_pcie->msix_enabled) {
+		inta_addr = CSR_MSIX_HW_INT_CAUSES_AD;
+		sw_err_bit = MSIX_HW_INT_CAUSES_REG_SW_ERR;
+	} else {
+		inta_addr = CSR_INT;
+		sw_err_bit = CSR_INT_BIT_SW_ERR;
+	}
 
 	iwl_disable_interrupts(trans);
 	iwl_force_nmi(trans);
 	while (time_after(timeout, jiffies)) {
-		u32 inta_hw = iwl_read32(trans,
-					 CSR_MSIX_HW_INT_CAUSES_AD);
+		u32 inta_hw = iwl_read32(trans, inta_addr);
 
 		/* Error detected by uCode */
-		if (inta_hw & MSIX_HW_INT_CAUSES_REG_SW_ERR) {
+		if (inta_hw & sw_err_bit) {
 			/* Clear causes register */
-			iwl_write32(trans, CSR_MSIX_HW_INT_CAUSES_AD,
-				    inta_hw &
-				    MSIX_HW_INT_CAUSES_REG_SW_ERR);
+			iwl_write32(trans, inta_addr, inta_hw & sw_err_bit);
 			break;
 		}
 
diff --git a/drivers/net/wireless/intel/iwlwifi/pcie/tx-gen2.c b/drivers/net/wireless/intel/iwlwifi/pcie/tx-gen2.c
index 88530d9f4a54..38d110338987 100644
--- a/drivers/net/wireless/intel/iwlwifi/pcie/tx-gen2.c
+++ b/drivers/net/wireless/intel/iwlwifi/pcie/tx-gen2.c
@@ -965,7 +965,7 @@ static int iwl_pcie_gen2_send_hcmd_sync(struct iwl_trans *trans,
 			       cmd_str);
 		ret = -ETIMEDOUT;
 
-		iwl_trans_sync_nmi(trans);
+		iwl_trans_pcie_sync_nmi(trans);
 		goto cancel;
 	}
 
diff --git a/drivers/net/wireless/intel/iwlwifi/pcie/tx.c b/drivers/net/wireless/intel/iwlwifi/pcie/tx.c
index 9fbd37d23e85..7be73e2c4681 100644
--- a/drivers/net/wireless/intel/iwlwifi/pcie/tx.c
+++ b/drivers/net/wireless/intel/iwlwifi/pcie/tx.c
@@ -1960,7 +1960,7 @@ static int iwl_pcie_send_hcmd_sync(struct iwl_trans *trans,
 			       iwl_get_cmd_string(trans, cmd->id));
 		ret = -ETIMEDOUT;
 
-		iwl_trans_sync_nmi(trans);
+		iwl_trans_pcie_sync_nmi(trans);
 		goto cancel;
 	}
 
diff --git a/drivers/net/wireless/intersil/orinoco/mic.c b/drivers/net/wireless/intersil/orinoco/mic.c
index 67b0c05afbdb..a324bc4b7938 100644
--- a/drivers/net/wireless/intersil/orinoco/mic.c
+++ b/drivers/net/wireless/intersil/orinoco/mic.c
@@ -65,7 +65,6 @@ int orinoco_mic(struct crypto_shash *tfm_michael, u8 *key,
 	hdr[ETH_ALEN * 2 + 3] = 0;
 
 	desc->tfm = tfm_michael;
-	desc->flags = 0;
 
 	err = crypto_shash_setkey(tfm_michael, key, MIC_KEYLEN);
 	if (err)
diff --git a/drivers/net/wireless/mac80211_hwsim.c b/drivers/net/wireless/mac80211_hwsim.c
index 0838af04d681..c71adb1f1f41 100644
--- a/drivers/net/wireless/mac80211_hwsim.c
+++ b/drivers/net/wireless/mac80211_hwsim.c
@@ -521,7 +521,7 @@ struct mac80211_hwsim_data {
 	unsigned int rx_filter;
 	bool started, idle, scanning;
 	struct mutex mutex;
-	struct tasklet_hrtimer beacon_timer;
+	struct hrtimer beacon_timer;
 	enum ps_mode {
 		PS_DISABLED, PS_ENABLED, PS_AUTO_POLL, PS_MANUAL_POLL
 	} ps;
@@ -1460,7 +1460,7 @@ static void mac80211_hwsim_stop(struct ieee80211_hw *hw)
 {
 	struct mac80211_hwsim_data *data = hw->priv;
 	data->started = false;
-	tasklet_hrtimer_cancel(&data->beacon_timer);
+	hrtimer_cancel(&data->beacon_timer);
 	wiphy_dbg(hw->wiphy, "%s\n", __func__);
 }
 
@@ -1583,14 +1583,12 @@ static enum hrtimer_restart
 mac80211_hwsim_beacon(struct hrtimer *timer)
 {
 	struct mac80211_hwsim_data *data =
-		container_of(timer, struct mac80211_hwsim_data,
-			     beacon_timer.timer);
+		container_of(timer, struct mac80211_hwsim_data, beacon_timer);
 	struct ieee80211_hw *hw = data->hw;
 	u64 bcn_int = data->beacon_int;
-	ktime_t next_bcn;
 
 	if (!data->started)
-		goto out;
+		return HRTIMER_NORESTART;
 
 	ieee80211_iterate_active_interfaces_atomic(
 		hw, IEEE80211_IFACE_ITER_NORMAL,
@@ -1601,12 +1599,9 @@ mac80211_hwsim_beacon(struct hrtimer *timer)
 		bcn_int -= data->bcn_delta;
 		data->bcn_delta = 0;
 	}
-
-	next_bcn = ktime_add(hrtimer_get_expires(timer),
-			     ns_to_ktime(bcn_int * 1000));
-	tasklet_hrtimer_start(&data->beacon_timer, next_bcn, HRTIMER_MODE_ABS);
-out:
-	return HRTIMER_NORESTART;
+	hrtimer_forward(&data->beacon_timer, hrtimer_get_expires(timer),
+			ns_to_ktime(bcn_int * NSEC_PER_USEC));
+	return HRTIMER_RESTART;
 }
 
 static const char * const hwsim_chanwidths[] = {
@@ -1680,15 +1675,15 @@ static int mac80211_hwsim_config(struct ieee80211_hw *hw, u32 changed)
 	mutex_unlock(&data->mutex);
 
 	if (!data->started || !data->beacon_int)
-		tasklet_hrtimer_cancel(&data->beacon_timer);
-	else if (!hrtimer_is_queued(&data->beacon_timer.timer)) {
+		hrtimer_cancel(&data->beacon_timer);
+	else if (!hrtimer_is_queued(&data->beacon_timer)) {
 		u64 tsf = mac80211_hwsim_get_tsf(hw, NULL);
 		u32 bcn_int = data->beacon_int;
 		u64 until_tbtt = bcn_int - do_div(tsf, bcn_int);
 
-		tasklet_hrtimer_start(&data->beacon_timer,
-				      ns_to_ktime(until_tbtt * 1000),
-				      HRTIMER_MODE_REL);
+		hrtimer_start(&data->beacon_timer,
+			      ns_to_ktime(until_tbtt * NSEC_PER_USEC),
+			      HRTIMER_MODE_REL_SOFT);
 	}
 
 	return 0;
@@ -1751,7 +1746,7 @@ static void mac80211_hwsim_bss_info_changed(struct ieee80211_hw *hw,
 			  info->enable_beacon, info->beacon_int);
 		vp->bcn_en = info->enable_beacon;
 		if (data->started &&
-		    !hrtimer_is_queued(&data->beacon_timer.timer) &&
+		    !hrtimer_is_queued(&data->beacon_timer) &&
 		    info->enable_beacon) {
 			u64 tsf, until_tbtt;
 			u32 bcn_int;
@@ -1759,9 +1754,10 @@ static void mac80211_hwsim_bss_info_changed(struct ieee80211_hw *hw,
 			tsf = mac80211_hwsim_get_tsf(hw, vif);
 			bcn_int = data->beacon_int;
 			until_tbtt = bcn_int - do_div(tsf, bcn_int);
-			tasklet_hrtimer_start(&data->beacon_timer,
-					      ns_to_ktime(until_tbtt * 1000),
-					      HRTIMER_MODE_REL);
+
+			hrtimer_start(&data->beacon_timer,
+				      ns_to_ktime(until_tbtt * NSEC_PER_USEC),
+				      HRTIMER_MODE_REL_SOFT);
 		} else if (!info->enable_beacon) {
 			unsigned int count = 0;
 			ieee80211_iterate_active_interfaces_atomic(
@@ -1770,7 +1766,7 @@ static void mac80211_hwsim_bss_info_changed(struct ieee80211_hw *hw,
 			wiphy_dbg(hw->wiphy, "  beaconing vifs remaining: %u",
 				  count);
 			if (count == 0) {
-				tasklet_hrtimer_cancel(&data->beacon_timer);
+				hrtimer_cancel(&data->beacon_timer);
 				data->beacon_int = 0;
 			}
 		}
@@ -2644,7 +2640,7 @@ static int mac80211_hwsim_new_radio(struct genl_info *info,
 	enum nl80211_band band;
 	const struct ieee80211_ops *ops = &mac80211_hwsim_ops;
 	struct net *net;
-	int idx;
+	int idx, i;
 	int n_limits = 0;
 
 	if (WARN_ON(param->channels > 1 && !param->use_chanctx))
@@ -2768,12 +2764,23 @@ static int mac80211_hwsim_new_radio(struct genl_info *info,
 		goto failed_hw;
 	}
 
+	data->if_combination.max_interfaces = 0;
+	for (i = 0; i < n_limits; i++)
+		data->if_combination.max_interfaces +=
+			data->if_limits[i].max;
+
 	data->if_combination.n_limits = n_limits;
-	data->if_combination.max_interfaces = 2048;
 	data->if_combination.limits = data->if_limits;
 
-	hw->wiphy->iface_combinations = &data->if_combination;
-	hw->wiphy->n_iface_combinations = 1;
+	/*
+	 * If we actually were asked to support combinations,
+	 * advertise them - if there's only a single thing like
+	 * only IBSS then don't advertise it as combinations.
+	 */
+	if (data->if_combination.max_interfaces > 1) {
+		hw->wiphy->iface_combinations = &data->if_combination;
+		hw->wiphy->n_iface_combinations = 1;
+	}
 
 	if (param->ciphers) {
 		memcpy(data->ciphers, param->ciphers,
@@ -2922,9 +2929,9 @@ static int mac80211_hwsim_new_radio(struct genl_info *info,
 
 	wiphy_ext_feature_set(hw->wiphy, NL80211_EXT_FEATURE_CQM_RSSI_LIST);
 
-	tasklet_hrtimer_init(&data->beacon_timer,
-			     mac80211_hwsim_beacon,
-			     CLOCK_MONOTONIC, HRTIMER_MODE_ABS);
+	hrtimer_init(&data->beacon_timer, CLOCK_MONOTONIC,
+		     HRTIMER_MODE_ABS_SOFT);
+	data->beacon_timer.function = mac80211_hwsim_beacon;
 
 	err = ieee80211_register_hw(hw);
 	if (err < 0) {
diff --git a/drivers/net/wireless/marvell/mwifiex/sdio.c b/drivers/net/wireless/marvell/mwifiex/sdio.c
index a85648342d15..d5a70340a945 100644
--- a/drivers/net/wireless/marvell/mwifiex/sdio.c
+++ b/drivers/net/wireless/marvell/mwifiex/sdio.c
@@ -181,7 +181,7 @@ static int mwifiex_sdio_resume(struct device *dev)
 
 	adapter = card->adapter;
 
-	if (test_bit(MWIFIEX_IS_SUSPENDED, &adapter->work_flags)) {
+	if (!test_bit(MWIFIEX_IS_SUSPENDED, &adapter->work_flags)) {
 		mwifiex_dbg(adapter, WARN,
 			    "device already resumed\n");
 		return 0;
diff --git a/drivers/net/wireless/mediatek/mt76/dma.c b/drivers/net/wireless/mediatek/mt76/dma.c
index 6eedc0ec7661..76629b98c78d 100644
--- a/drivers/net/wireless/mediatek/mt76/dma.c
+++ b/drivers/net/wireless/mediatek/mt76/dma.c
@@ -130,6 +130,8 @@ mt76_dma_tx_cleanup_idx(struct mt76_dev *dev, struct mt76_queue *q, int idx,
 static void
 mt76_dma_sync_idx(struct mt76_dev *dev, struct mt76_queue *q)
 {
+	iowrite32(q->desc_dma, &q->regs->desc_base);
+	iowrite32(q->ndesc, &q->regs->ring_size);
 	q->head = ioread32(&q->regs->dma_idx);
 	q->tail = q->head;
 	iowrite32(q->head, &q->regs->cpu_idx);
@@ -180,7 +182,10 @@ mt76_dma_tx_cleanup(struct mt76_dev *dev, enum mt76_txq_id qid, bool flush)
 	else
 		mt76_dma_sync_idx(dev, q);
 
-	wake = wake && qid < IEEE80211_NUM_ACS && q->queued < q->ndesc - 8;
+	wake = wake && q->stopped &&
+	       qid < IEEE80211_NUM_ACS && q->queued < q->ndesc - 8;
+	if (wake)
+		q->stopped = false;
 
 	if (!q->queued)
 		wake_up(&dev->tx_wait);
diff --git a/drivers/net/wireless/mediatek/mt76/mac80211.c b/drivers/net/wireless/mediatek/mt76/mac80211.c
index a033745adb2f..316167404729 100644
--- a/drivers/net/wireless/mediatek/mt76/mac80211.c
+++ b/drivers/net/wireless/mediatek/mt76/mac80211.c
@@ -679,19 +679,15 @@ out:
 	return ret;
 }
 
-static void
-mt76_sta_remove(struct mt76_dev *dev, struct ieee80211_vif *vif,
-	        struct ieee80211_sta *sta)
+void __mt76_sta_remove(struct mt76_dev *dev, struct ieee80211_vif *vif,
+		       struct ieee80211_sta *sta)
 {
 	struct mt76_wcid *wcid = (struct mt76_wcid *)sta->drv_priv;
-	int idx = wcid->idx;
-	int i;
+	int i, idx = wcid->idx;
 
 	rcu_assign_pointer(dev->wcid[idx], NULL);
 	synchronize_rcu();
 
-	mutex_lock(&dev->mutex);
-
 	if (dev->drv->sta_remove)
 		dev->drv->sta_remove(dev, vif, sta);
 
@@ -699,7 +695,15 @@ mt76_sta_remove(struct mt76_dev *dev, struct ieee80211_vif *vif,
 	for (i = 0; i < ARRAY_SIZE(sta->txq); i++)
 		mt76_txq_remove(dev, sta->txq[i]);
 	mt76_wcid_free(dev->wcid_mask, idx);
+}
+EXPORT_SYMBOL_GPL(__mt76_sta_remove);
 
+static void
+mt76_sta_remove(struct mt76_dev *dev, struct ieee80211_vif *vif,
+		struct ieee80211_sta *sta)
+{
+	mutex_lock(&dev->mutex);
+	__mt76_sta_remove(dev, vif, sta);
 	mutex_unlock(&dev->mutex);
 }
 
diff --git a/drivers/net/wireless/mediatek/mt76/mt76.h b/drivers/net/wireless/mediatek/mt76/mt76.h
index 5dfb0601f101..bcbfd3c4a44b 100644
--- a/drivers/net/wireless/mediatek/mt76/mt76.h
+++ b/drivers/net/wireless/mediatek/mt76/mt76.h
@@ -126,6 +126,7 @@ struct mt76_queue {
 	int ndesc;
 	int queued;
 	int buf_size;
+	bool stopped;
 
 	u8 buf_offset;
 	u8 hw_idx;
@@ -143,6 +144,7 @@ struct mt76_mcu_ops {
 			 const struct mt76_reg_pair *rp, int len);
 	int (*mcu_rd_rp)(struct mt76_dev *dev, u32 base,
 			 struct mt76_reg_pair *rp, int len);
+	int (*mcu_restart)(struct mt76_dev *dev);
 };
 
 struct mt76_queue_ops {
@@ -693,6 +695,8 @@ int mt76_sta_state(struct ieee80211_hw *hw, struct ieee80211_vif *vif,
 		   struct ieee80211_sta *sta,
 		   enum ieee80211_sta_state old_state,
 		   enum ieee80211_sta_state new_state);
+void __mt76_sta_remove(struct mt76_dev *dev, struct ieee80211_vif *vif,
+		       struct ieee80211_sta *sta);
 
 struct ieee80211_sta *mt76_rx_convert(struct sk_buff *skb);
 
diff --git a/drivers/net/wireless/mediatek/mt76/mt7603/beacon.c b/drivers/net/wireless/mediatek/mt76/mt7603/beacon.c
index afcd86f735b4..4dcb465095d1 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7603/beacon.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7603/beacon.c
@@ -135,8 +135,7 @@ void mt7603_pre_tbtt_tasklet(unsigned long arg)
 
 out:
 	mt76_queue_tx_cleanup(dev, MT_TXQ_BEACON, false);
-	if (dev->mt76.q_tx[MT_TXQ_BEACON].queued >
-	    __sw_hweight8(dev->beacon_mask))
+	if (dev->mt76.q_tx[MT_TXQ_BEACON].queued > hweight8(dev->beacon_mask))
 		dev->beacon_check++;
 }
 
diff --git a/drivers/net/wireless/mediatek/mt76/mt7603/dma.c b/drivers/net/wireless/mediatek/mt76/mt7603/dma.c
index d69e82c66ab2..b3ae0aaea62a 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7603/dma.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7603/dma.c
@@ -27,12 +27,16 @@ static void
 mt7603_rx_loopback_skb(struct mt7603_dev *dev, struct sk_buff *skb)
 {
 	__le32 *txd = (__le32 *)skb->data;
+	struct ieee80211_hdr *hdr;
+	struct ieee80211_sta *sta;
 	struct mt7603_sta *msta;
 	struct mt76_wcid *wcid;
+	void *priv;
 	int idx;
 	u32 val;
+	u8 tid;
 
-	if (skb->len < sizeof(MT_TXD_SIZE) + sizeof(struct ieee80211_hdr))
+	if (skb->len < MT_TXD_SIZE + sizeof(struct ieee80211_hdr))
 		goto free;
 
 	val = le32_to_cpu(txd[1]);
@@ -46,10 +50,19 @@ mt7603_rx_loopback_skb(struct mt7603_dev *dev, struct sk_buff *skb)
 	if (!wcid)
 		goto free;
 
-	msta = container_of(wcid, struct mt7603_sta, wcid);
+	priv = msta = container_of(wcid, struct mt7603_sta, wcid);
 	val = le32_to_cpu(txd[0]);
 	skb_set_queue_mapping(skb, FIELD_GET(MT_TXD0_Q_IDX, val));
 
+	val &= ~(MT_TXD0_P_IDX | MT_TXD0_Q_IDX);
+	val |= FIELD_PREP(MT_TXD0_Q_IDX, MT_TX_HW_QUEUE_MGMT);
+	txd[0] = cpu_to_le32(val);
+
+	sta = container_of(priv, struct ieee80211_sta, drv_priv);
+	hdr = (struct ieee80211_hdr *) &skb->data[MT_TXD_SIZE];
+	tid = *ieee80211_get_qos_ctl(hdr) & IEEE80211_QOS_CTL_TID_MASK;
+	ieee80211_sta_set_buffered(sta, tid, true);
+
 	spin_lock_bh(&dev->ps_lock);
 	__skb_queue_tail(&msta->psq, skb);
 	if (skb_queue_len(&msta->psq) >= 64) {
diff --git a/drivers/net/wireless/mediatek/mt76/mt7603/init.c b/drivers/net/wireless/mediatek/mt76/mt7603/init.c
index 15cc8f33b34d..3af45949e868 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7603/init.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7603/init.c
@@ -112,7 +112,7 @@ static void
 mt7603_phy_init(struct mt7603_dev *dev)
 {
 	int rx_chains = dev->mt76.antenna_mask;
-	int tx_chains = __sw_hweight8(rx_chains) - 1;
+	int tx_chains = hweight8(rx_chains) - 1;
 
 	mt76_rmw(dev, MT_WF_RMAC_RMCR,
 		 (MT_WF_RMAC_RMCR_SMPS_MODE |
@@ -510,6 +510,8 @@ int mt7603_register_device(struct mt7603_dev *dev)
 	bus_ops->rmw = mt7603_rmw;
 	dev->mt76.bus = bus_ops;
 
+	spin_lock_init(&dev->ps_lock);
+
 	INIT_DELAYED_WORK(&dev->mac_work, mt7603_mac_work);
 	tasklet_init(&dev->pre_tbtt_tasklet, mt7603_pre_tbtt_tasklet,
 		     (unsigned long)dev);
diff --git a/drivers/net/wireless/mediatek/mt76/mt7603/mac.c b/drivers/net/wireless/mediatek/mt76/mt7603/mac.c
index 0a0115861b51..5abc02b57818 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7603/mac.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7603/mac.c
@@ -343,7 +343,7 @@ void mt7603_mac_rx_ba_reset(struct mt7603_dev *dev, void *addr, u8 tid)
 		 MT_BA_CONTROL_1_RESET));
 }
 
-void mt7603_mac_tx_ba_reset(struct mt7603_dev *dev, int wcid, int tid, int ssn,
+void mt7603_mac_tx_ba_reset(struct mt7603_dev *dev, int wcid, int tid,
 			    int ba_size)
 {
 	u32 addr = mt7603_wtbl2_addr(wcid);
@@ -358,43 +358,6 @@ void mt7603_mac_tx_ba_reset(struct mt7603_dev *dev, int wcid, int tid, int ssn,
 		mt76_clear(dev, addr + (15 * 4), tid_mask);
 		return;
 	}
-	mt76_poll(dev, MT_WTBL_UPDATE, MT_WTBL_UPDATE_BUSY, 0, 5000);
-
-	mt7603_mac_stop(dev);
-	switch (tid) {
-	case 0:
-		mt76_rmw_field(dev, addr + (2 * 4), MT_WTBL2_W2_TID0_SN, ssn);
-		break;
-	case 1:
-		mt76_rmw_field(dev, addr + (2 * 4), MT_WTBL2_W2_TID1_SN, ssn);
-		break;
-	case 2:
-		mt76_rmw_field(dev, addr + (2 * 4), MT_WTBL2_W2_TID2_SN_LO,
-			       ssn);
-		mt76_rmw_field(dev, addr + (3 * 4), MT_WTBL2_W3_TID2_SN_HI,
-			       ssn >> 8);
-		break;
-	case 3:
-		mt76_rmw_field(dev, addr + (3 * 4), MT_WTBL2_W3_TID3_SN, ssn);
-		break;
-	case 4:
-		mt76_rmw_field(dev, addr + (3 * 4), MT_WTBL2_W3_TID4_SN, ssn);
-		break;
-	case 5:
-		mt76_rmw_field(dev, addr + (3 * 4), MT_WTBL2_W3_TID5_SN_LO,
-			       ssn);
-		mt76_rmw_field(dev, addr + (4 * 4), MT_WTBL2_W4_TID5_SN_HI,
-			       ssn >> 4);
-		break;
-	case 6:
-		mt76_rmw_field(dev, addr + (4 * 4), MT_WTBL2_W4_TID6_SN, ssn);
-		break;
-	case 7:
-		mt76_rmw_field(dev, addr + (4 * 4), MT_WTBL2_W4_TID7_SN, ssn);
-		break;
-	}
-	mt7603_wtbl_update(dev, wcid, MT_WTBL_UPDATE_WTBL2);
-	mt7603_mac_start(dev);
 
 	for (i = 7; i > 0; i--) {
 		if (ba_size >= MT_AGG_SIZE_LIMIT(i))
@@ -827,6 +790,7 @@ mt7603_mac_write_txwi(struct mt7603_dev *dev, __le32 *txwi,
 	struct ieee80211_tx_info *info = IEEE80211_SKB_CB(skb);
 	struct ieee80211_tx_rate *rate = &info->control.rates[0];
 	struct ieee80211_hdr *hdr = (struct ieee80211_hdr *)skb->data;
+	struct ieee80211_bar *bar = (struct ieee80211_bar *)skb->data;
 	struct ieee80211_vif *vif = info->control.vif;
 	struct mt7603_vif *mvif;
 	int wlan_idx;
@@ -834,6 +798,7 @@ mt7603_mac_write_txwi(struct mt7603_dev *dev, __le32 *txwi,
 	int tx_count = 8;
 	u8 frame_type, frame_subtype;
 	u16 fc = le16_to_cpu(hdr->frame_control);
+	u16 seqno = 0;
 	u8 vif_idx = 0;
 	u32 val;
 	u8 bw;
@@ -919,7 +884,17 @@ mt7603_mac_write_txwi(struct mt7603_dev *dev, __le32 *txwi,
 		tx_count = 0x1f;
 
 	val = FIELD_PREP(MT_TXD3_REM_TX_COUNT, tx_count) |
-	      FIELD_PREP(MT_TXD3_SEQ, le16_to_cpu(hdr->seq_ctrl));
+		  MT_TXD3_SN_VALID;
+
+	if (ieee80211_is_data_qos(hdr->frame_control))
+		seqno = le16_to_cpu(hdr->seq_ctrl);
+	else if (ieee80211_is_back_req(hdr->frame_control))
+		seqno = le16_to_cpu(bar->start_seq_num);
+	else
+		val &= ~MT_TXD3_SN_VALID;
+
+	val |= FIELD_PREP(MT_TXD3_SEQ, seqno >> 4);
+
 	txwi[3] = cpu_to_le32(val);
 
 	if (key) {
@@ -1072,7 +1047,7 @@ out:
 	case MT_PHY_TYPE_HT:
 		final_rate_flags |= IEEE80211_TX_RC_MCS;
 		final_rate &= GENMASK(5, 0);
-		if (i > 15)
+		if (final_rate > 15)
 			return false;
 		break;
 	default:
diff --git a/drivers/net/wireless/mediatek/mt76/mt7603/main.c b/drivers/net/wireless/mediatek/mt76/mt7603/main.c
index b10775ed92e6..a3c4ef198bfe 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7603/main.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7603/main.c
@@ -5,6 +5,7 @@
 #include <linux/pci.h>
 #include <linux/module.h>
 #include "mt7603.h"
+#include "mac.h"
 #include "eeprom.h"
 
 static int
@@ -371,7 +372,7 @@ mt7603_sta_ps(struct mt76_dev *mdev, struct ieee80211_sta *sta, bool ps)
 	struct mt7603_sta *msta = (struct mt7603_sta *)sta->drv_priv;
 	struct sk_buff_head list;
 
-	mt76_stop_tx_queues(&dev->mt76, sta, false);
+	mt76_stop_tx_queues(&dev->mt76, sta, true);
 	mt7603_wtbl_set_ps(dev, msta, ps);
 	if (ps)
 		return;
@@ -386,6 +387,15 @@ mt7603_sta_ps(struct mt76_dev *mdev, struct ieee80211_sta *sta, bool ps)
 }
 
 static void
+mt7603_ps_set_more_data(struct sk_buff *skb)
+{
+	struct ieee80211_hdr *hdr;
+
+	hdr = (struct ieee80211_hdr *) &skb->data[MT_TXD_SIZE];
+	hdr->frame_control |= cpu_to_le16(IEEE80211_FCTL_MOREDATA);
+}
+
+static void
 mt7603_release_buffered_frames(struct ieee80211_hw *hw,
 			       struct ieee80211_sta *sta,
 			       u16 tids, int nframes,
@@ -399,6 +409,8 @@ mt7603_release_buffered_frames(struct ieee80211_hw *hw,
 
 	__skb_queue_head_init(&list);
 
+	mt7603_wtbl_set_ps(dev, msta, false);
+
 	spin_lock_bh(&dev->ps_lock);
 	skb_queue_walk_safe(&msta->psq, skb, tmp) {
 		if (!nframes)
@@ -409,11 +421,15 @@ mt7603_release_buffered_frames(struct ieee80211_hw *hw,
 
 		skb_set_queue_mapping(skb, MT_TXQ_PSD);
 		__skb_unlink(skb, &msta->psq);
+		mt7603_ps_set_more_data(skb);
 		__skb_queue_tail(&list, skb);
 		nframes--;
 	}
 	spin_unlock_bh(&dev->ps_lock);
 
+	if (!skb_queue_empty(&list))
+		ieee80211_sta_eosp(sta);
+
 	mt7603_ps_tx_list(dev, &list);
 
 	if (nframes)
@@ -568,13 +584,13 @@ mt7603_ampdu_action(struct ieee80211_hw *hw, struct ieee80211_vif *vif,
 	case IEEE80211_AMPDU_TX_OPERATIONAL:
 		mtxq->aggr = true;
 		mtxq->send_bar = false;
-		mt7603_mac_tx_ba_reset(dev, msta->wcid.idx, tid, *ssn, ba_size);
+		mt7603_mac_tx_ba_reset(dev, msta->wcid.idx, tid, ba_size);
 		break;
 	case IEEE80211_AMPDU_TX_STOP_FLUSH:
 	case IEEE80211_AMPDU_TX_STOP_FLUSH_CONT:
 		mtxq->aggr = false;
 		ieee80211_send_bar(vif, sta->addr, tid, mtxq->agg_ssn);
-		mt7603_mac_tx_ba_reset(dev, msta->wcid.idx, tid, *ssn, -1);
+		mt7603_mac_tx_ba_reset(dev, msta->wcid.idx, tid, -1);
 		break;
 	case IEEE80211_AMPDU_TX_START:
 		mtxq->agg_ssn = *ssn << 4;
@@ -582,7 +598,7 @@ mt7603_ampdu_action(struct ieee80211_hw *hw, struct ieee80211_vif *vif,
 		break;
 	case IEEE80211_AMPDU_TX_STOP_CONT:
 		mtxq->aggr = false;
-		mt7603_mac_tx_ba_reset(dev, msta->wcid.idx, tid, *ssn, -1);
+		mt7603_mac_tx_ba_reset(dev, msta->wcid.idx, tid, -1);
 		ieee80211_stop_tx_ba_cb_irqsafe(vif, sta->addr, tid);
 		break;
 	}
diff --git a/drivers/net/wireless/mediatek/mt76/mt7603/mcu.c b/drivers/net/wireless/mediatek/mt76/mt7603/mcu.c
index 4b0713f1fd5e..d06905ea8cc6 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7603/mcu.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7603/mcu.c
@@ -433,7 +433,7 @@ int mt7603_mcu_set_channel(struct mt7603_dev *dev)
 {
 	struct cfg80211_chan_def *chandef = &dev->mt76.chandef;
 	struct ieee80211_hw *hw = mt76_hw(dev);
-	int n_chains = __sw_hweight8(dev->mt76.antenna_mask);
+	int n_chains = hweight8(dev->mt76.antenna_mask);
 	struct {
 		u8 control_chan;
 		u8 center_chan;
diff --git a/drivers/net/wireless/mediatek/mt76/mt7603/mt7603.h b/drivers/net/wireless/mediatek/mt76/mt7603/mt7603.h
index 79f332429432..6049f3b7c8fe 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7603/mt7603.h
+++ b/drivers/net/wireless/mediatek/mt76/mt7603/mt7603.h
@@ -200,7 +200,7 @@ void mt7603_beacon_set_timer(struct mt7603_dev *dev, int idx, int intval);
 int mt7603_mac_fill_rx(struct mt7603_dev *dev, struct sk_buff *skb);
 void mt7603_mac_add_txs(struct mt7603_dev *dev, void *data);
 void mt7603_mac_rx_ba_reset(struct mt7603_dev *dev, void *addr, u8 tid);
-void mt7603_mac_tx_ba_reset(struct mt7603_dev *dev, int wcid, int tid, int ssn,
+void mt7603_mac_tx_ba_reset(struct mt7603_dev *dev, int wcid, int tid,
 			    int ba_size);
 
 void mt7603_pse_client_reset(struct mt7603_dev *dev);
diff --git a/drivers/net/wireless/mediatek/mt76/mt7603/soc.c b/drivers/net/wireless/mediatek/mt76/mt7603/soc.c
index e13fea80d970..b920be1f5718 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7603/soc.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7603/soc.c
@@ -23,9 +23,9 @@ mt76_wmac_probe(struct platform_device *pdev)
 	}
 
 	mem_base = devm_ioremap_resource(&pdev->dev, res);
-	if (!mem_base) {
+	if (IS_ERR(mem_base)) {
 		dev_err(&pdev->dev, "Failed to get memory resource\n");
-		return -EINVAL;
+		return PTR_ERR(mem_base);
 	}
 
 	mdev = mt76_alloc_device(&pdev->dev, sizeof(*dev), &mt7603_ops,
diff --git a/drivers/net/wireless/mediatek/mt76/mt76x0/initvals.h b/drivers/net/wireless/mediatek/mt76/mt76x0/initvals.h
index 0290ba5869a5..736f81752b5b 100644
--- a/drivers/net/wireless/mediatek/mt76/mt76x0/initvals.h
+++ b/drivers/net/wireless/mediatek/mt76/mt76x0/initvals.h
@@ -46,7 +46,7 @@ static const struct mt76_reg_pair common_mac_reg_table[] = {
 	{ MT_MM20_PROT_CFG,		0x01742004 },
 	{ MT_MM40_PROT_CFG,		0x03f42084 },
 	{ MT_TXOP_CTRL_CFG,		0x0000583f },
-	{ MT_TX_RTS_CFG,		0x00092b20 },
+	{ MT_TX_RTS_CFG,		0x00ffff20 },
 	{ MT_EXP_ACK_TIME,		0x002400ca },
 	{ MT_TXOP_HLDR_ET,		0x00000002 },
 	{ MT_XIFS_TIME_CFG,		0x33a41010 },
diff --git a/drivers/net/wireless/mediatek/mt76/mt76x0/usb.c b/drivers/net/wireless/mediatek/mt76/mt76x0/usb.c
index 91718647da02..e5a06f74a6f7 100644
--- a/drivers/net/wireless/mediatek/mt76/mt76x0/usb.c
+++ b/drivers/net/wireless/mediatek/mt76/mt76x0/usb.c
@@ -229,7 +229,7 @@ static int mt76x0u_probe(struct usb_interface *usb_intf,
 	struct usb_device *usb_dev = interface_to_usbdev(usb_intf);
 	struct mt76x02_dev *dev;
 	struct mt76_dev *mdev;
-	u32 asic_rev, mac_rev;
+	u32 mac_rev;
 	int ret;
 
 	mdev = mt76_alloc_device(&usb_intf->dev, sizeof(*dev), &mt76x0u_ops,
@@ -262,10 +262,14 @@ static int mt76x0u_probe(struct usb_interface *usb_intf,
 		goto err;
 	}
 
-	asic_rev = mt76_rr(dev, MT_ASIC_VERSION);
+	mdev->rev = mt76_rr(dev, MT_ASIC_VERSION);
 	mac_rev = mt76_rr(dev, MT_MAC_CSR0);
 	dev_info(mdev->dev, "ASIC revision: %08x MAC revision: %08x\n",
-		 asic_rev, mac_rev);
+		 mdev->rev, mac_rev);
+	if (!is_mt76x0(dev)) {
+		ret = -ENODEV;
+		goto err;
+	}
 
 	/* Note: vendor driver skips this check for MT76X0U */
 	if (!(mt76_rr(dev, MT_EFUSE_CTRL) & MT_EFUSE_CTRL_SEL))
diff --git a/drivers/net/wireless/mediatek/mt76/mt76x02.h b/drivers/net/wireless/mediatek/mt76/mt76x02.h
index 6915cce5def9..07061eb4d1e1 100644
--- a/drivers/net/wireless/mediatek/mt76/mt76x02.h
+++ b/drivers/net/wireless/mediatek/mt76/mt76x02.h
@@ -51,6 +51,7 @@ struct mt76x02_calibration {
 	u16 false_cca;
 	s8 avg_rssi_all;
 	s8 agc_gain_adjust;
+	s8 agc_lowest_gain;
 	s8 low_gain;
 
 	s8 temp_vco;
@@ -114,8 +115,11 @@ struct mt76x02_dev {
 	struct mt76x02_dfs_pattern_detector dfs_pd;
 
 	/* edcca monitor */
+	unsigned long ed_trigger_timeout;
 	bool ed_tx_blocked;
 	bool ed_monitor;
+	u8 ed_monitor_enabled;
+	u8 ed_monitor_learning;
 	u8 ed_trigger;
 	u8 ed_silent;
 	ktime_t ed_time;
@@ -188,6 +192,13 @@ void mt76x02_mac_start(struct mt76x02_dev *dev);
 
 void mt76x02_init_debugfs(struct mt76x02_dev *dev);
 
+static inline bool is_mt76x0(struct mt76x02_dev *dev)
+{
+	return mt76_chip(&dev->mt76) == 0x7610 ||
+	       mt76_chip(&dev->mt76) == 0x7630 ||
+	       mt76_chip(&dev->mt76) == 0x7650;
+}
+
 static inline bool is_mt76x2(struct mt76x02_dev *dev)
 {
 	return mt76_chip(&dev->mt76) == 0x7612 ||
diff --git a/drivers/net/wireless/mediatek/mt76/mt76x02_debugfs.c b/drivers/net/wireless/mediatek/mt76/mt76x02_debugfs.c
index 7580c5c986ff..b1d6fd4861e3 100644
--- a/drivers/net/wireless/mediatek/mt76/mt76x02_debugfs.c
+++ b/drivers/net/wireless/mediatek/mt76/mt76x02_debugfs.c
@@ -116,6 +116,32 @@ static int read_agc(struct seq_file *file, void *data)
 	return 0;
 }
 
+static int
+mt76_edcca_set(void *data, u64 val)
+{
+	struct mt76x02_dev *dev = data;
+	enum nl80211_dfs_regions region = dev->dfs_pd.region;
+
+	dev->ed_monitor_enabled = !!val;
+	dev->ed_monitor = dev->ed_monitor_enabled &&
+			  region == NL80211_DFS_ETSI;
+	mt76x02_edcca_init(dev, true);
+
+	return 0;
+}
+
+static int
+mt76_edcca_get(void *data, u64 *val)
+{
+	struct mt76x02_dev *dev = data;
+
+	*val = dev->ed_monitor_enabled;
+	return 0;
+}
+
+DEFINE_DEBUGFS_ATTRIBUTE(fops_edcca, mt76_edcca_get, mt76_edcca_set,
+			 "%lld\n");
+
 void mt76x02_init_debugfs(struct mt76x02_dev *dev)
 {
 	struct dentry *dir;
@@ -127,6 +153,7 @@ void mt76x02_init_debugfs(struct mt76x02_dev *dev)
 	debugfs_create_u8("temperature", 0400, dir, &dev->cal.temp);
 	debugfs_create_bool("tpc", 0600, dir, &dev->enable_tpc);
 
+	debugfs_create_file("edcca", 0400, dir, dev, &fops_edcca);
 	debugfs_create_file("ampdu_stat", 0400, dir, dev, &fops_ampdu_stat);
 	debugfs_create_file("dfs_stats", 0400, dir, dev, &fops_dfs_stat);
 	debugfs_create_devm_seqfile(dev->mt76.dev, "txpower", dir,
diff --git a/drivers/net/wireless/mediatek/mt76/mt76x02_dfs.c b/drivers/net/wireless/mediatek/mt76/mt76x02_dfs.c
index e4649103efd4..17d12d212d1b 100644
--- a/drivers/net/wireless/mediatek/mt76/mt76x02_dfs.c
+++ b/drivers/net/wireless/mediatek/mt76/mt76x02_dfs.c
@@ -885,7 +885,8 @@ mt76x02_dfs_set_domain(struct mt76x02_dev *dev,
 	if (dfs_pd->region != region) {
 		tasklet_disable(&dfs_pd->dfs_tasklet);
 
-		dev->ed_monitor = region == NL80211_DFS_ETSI;
+		dev->ed_monitor = dev->ed_monitor_enabled &&
+				  region == NL80211_DFS_ETSI;
 		mt76x02_edcca_init(dev, true);
 
 		dfs_pd->region = region;
diff --git a/drivers/net/wireless/mediatek/mt76/mt76x02_mac.c b/drivers/net/wireless/mediatek/mt76/mt76x02_mac.c
index 91ff6598eccf..4fe5a83ca5a4 100644
--- a/drivers/net/wireless/mediatek/mt76/mt76x02_mac.c
+++ b/drivers/net/wireless/mediatek/mt76/mt76x02_mac.c
@@ -67,12 +67,39 @@ int mt76x02_mac_shared_key_setup(struct mt76x02_dev *dev, u8 vif_idx,
 }
 EXPORT_SYMBOL_GPL(mt76x02_mac_shared_key_setup);
 
+void mt76x02_mac_wcid_sync_pn(struct mt76x02_dev *dev, u8 idx,
+			      struct ieee80211_key_conf *key)
+{
+	enum mt76x02_cipher_type cipher;
+	u8 key_data[32];
+	u32 iv, eiv;
+	u64 pn;
+
+	cipher = mt76x02_mac_get_key_info(key, key_data);
+	iv = mt76_rr(dev, MT_WCID_IV(idx));
+	eiv = mt76_rr(dev, MT_WCID_IV(idx) + 4);
+
+	pn = (u64)eiv << 16;
+	if (cipher == MT_CIPHER_TKIP) {
+		pn |= (iv >> 16) & 0xff;
+		pn |= (iv & 0xff) << 8;
+	} else if (cipher >= MT_CIPHER_AES_CCMP) {
+		pn |= iv & 0xffff;
+	} else {
+		return;
+	}
+
+	atomic64_set(&key->tx_pn, pn);
+}
+
+
 int mt76x02_mac_wcid_set_key(struct mt76x02_dev *dev, u8 idx,
 			     struct ieee80211_key_conf *key)
 {
 	enum mt76x02_cipher_type cipher;
 	u8 key_data[32];
 	u8 iv_data[8];
+	u64 pn;
 
 	cipher = mt76x02_mac_get_key_info(key, key_data);
 	if (cipher == MT_CIPHER_NONE && key)
@@ -85,9 +112,22 @@ int mt76x02_mac_wcid_set_key(struct mt76x02_dev *dev, u8 idx,
 	if (key) {
 		mt76_rmw_field(dev, MT_WCID_ATTR(idx), MT_WCID_ATTR_PAIRWISE,
 			       !!(key->flags & IEEE80211_KEY_FLAG_PAIRWISE));
+
+		pn = atomic64_read(&key->tx_pn);
+
 		iv_data[3] = key->keyidx << 6;
-		if (cipher >= MT_CIPHER_TKIP)
+		if (cipher >= MT_CIPHER_TKIP) {
 			iv_data[3] |= 0x20;
+			put_unaligned_le32(pn >> 16, &iv_data[4]);
+		}
+
+		if (cipher == MT_CIPHER_TKIP) {
+			iv_data[0] = (pn >> 8) & 0xff;
+			iv_data[1] = (iv_data[0] | 0x20) & 0x7f;
+			iv_data[2] = pn & 0xff;
+		} else if (cipher >= MT_CIPHER_AES_CCMP) {
+			put_unaligned_le16((pn & 0xffff), &iv_data[0]);
+		}
 	}
 
 	mt76_wr_copy(dev, MT_WCID_IV(idx), iv_data, sizeof(iv_data));
@@ -426,7 +466,6 @@ void mt76x02_send_tx_status(struct mt76x02_dev *dev,
 		return;
 
 	rcu_read_lock();
-	mt76_tx_status_lock(mdev, &list);
 
 	if (stat->wcid < ARRAY_SIZE(dev->mt76.wcid))
 		wcid = rcu_dereference(dev->mt76.wcid[stat->wcid]);
@@ -439,6 +478,8 @@ void mt76x02_send_tx_status(struct mt76x02_dev *dev,
 					  drv_priv);
 	}
 
+	mt76_tx_status_lock(mdev, &list);
+
 	if (wcid) {
 		if (stat->pktid >= MT_PACKET_ID_FIRST)
 			status.skb = mt76_tx_status_skb_get(mdev, wcid,
@@ -458,7 +499,9 @@ void mt76x02_send_tx_status(struct mt76x02_dev *dev,
 		if (*update == 0 && stat_val == stat_cache &&
 		    stat->wcid == msta->status.wcid && msta->n_frames < 32) {
 			msta->n_frames++;
-			goto out;
+			mt76_tx_status_unlock(mdev, &list);
+			rcu_read_unlock();
+			return;
 		}
 
 		mt76x02_mac_fill_tx_status(dev, status.info, &msta->status,
@@ -474,11 +517,10 @@ void mt76x02_send_tx_status(struct mt76x02_dev *dev,
 
 	if (status.skb)
 		mt76_tx_status_skb_done(mdev, status.skb, &list);
-	else
-		ieee80211_tx_status_ext(mt76_hw(dev), &status);
-
-out:
 	mt76_tx_status_unlock(mdev, &list);
+
+	if (!status.skb)
+		ieee80211_tx_status_ext(mt76_hw(dev), &status);
 	rcu_read_unlock();
 }
 
@@ -920,6 +962,7 @@ void mt76x02_edcca_init(struct mt76x02_dev *dev, bool enable)
 		}
 	}
 	mt76x02_edcca_tx_enable(dev, true);
+	dev->ed_monitor_learning = true;
 
 	/* clear previous CCA timer value */
 	mt76_rr(dev, MT_ED_CCA_TIMER);
@@ -929,6 +972,10 @@ EXPORT_SYMBOL_GPL(mt76x02_edcca_init);
 
 #define MT_EDCCA_TH		92
 #define MT_EDCCA_BLOCK_TH	2
+#define MT_EDCCA_LEARN_TH	50
+#define MT_EDCCA_LEARN_CCA	180
+#define MT_EDCCA_LEARN_TIMEOUT	(20 * HZ)
+
 static void mt76x02_edcca_check(struct mt76x02_dev *dev)
 {
 	ktime_t cur_time;
@@ -951,11 +998,23 @@ static void mt76x02_edcca_check(struct mt76x02_dev *dev)
 		dev->ed_trigger = 0;
 	}
 
-	if (dev->ed_trigger > MT_EDCCA_BLOCK_TH &&
-	    !dev->ed_tx_blocked)
+	if (dev->cal.agc_lowest_gain &&
+	    dev->cal.false_cca > MT_EDCCA_LEARN_CCA &&
+	    dev->ed_trigger > MT_EDCCA_LEARN_TH) {
+		dev->ed_monitor_learning = false;
+		dev->ed_trigger_timeout = jiffies + 20 * HZ;
+	} else if (!dev->ed_monitor_learning &&
+		   time_is_after_jiffies(dev->ed_trigger_timeout)) {
+		dev->ed_monitor_learning = true;
+		mt76x02_edcca_tx_enable(dev, true);
+	}
+
+	if (dev->ed_monitor_learning)
+		return;
+
+	if (dev->ed_trigger > MT_EDCCA_BLOCK_TH && !dev->ed_tx_blocked)
 		mt76x02_edcca_tx_enable(dev, false);
-	else if (dev->ed_silent > MT_EDCCA_BLOCK_TH &&
-		 dev->ed_tx_blocked)
+	else if (dev->ed_silent > MT_EDCCA_BLOCK_TH && dev->ed_tx_blocked)
 		mt76x02_edcca_tx_enable(dev, true);
 }
 
diff --git a/drivers/net/wireless/mediatek/mt76/mt76x02_mac.h b/drivers/net/wireless/mediatek/mt76/mt76x02_mac.h
index 6b1f25d2f64c..caeeef96c42f 100644
--- a/drivers/net/wireless/mediatek/mt76/mt76x02_mac.h
+++ b/drivers/net/wireless/mediatek/mt76/mt76x02_mac.h
@@ -177,6 +177,8 @@ int mt76x02_mac_shared_key_setup(struct mt76x02_dev *dev, u8 vif_idx,
 				 u8 key_idx, struct ieee80211_key_conf *key);
 int mt76x02_mac_wcid_set_key(struct mt76x02_dev *dev, u8 idx,
 			     struct ieee80211_key_conf *key);
+void mt76x02_mac_wcid_sync_pn(struct mt76x02_dev *dev, u8 idx,
+			      struct ieee80211_key_conf *key);
 void mt76x02_mac_wcid_setup(struct mt76x02_dev *dev, u8 idx, u8 vif_idx,
 			    u8 *mac);
 void mt76x02_mac_wcid_set_drop(struct mt76x02_dev *dev, u8 idx, bool drop);
diff --git a/drivers/net/wireless/mediatek/mt76/mt76x02_mmio.c b/drivers/net/wireless/mediatek/mt76/mt76x02_mmio.c
index 1229f19f2b02..daaed1220147 100644
--- a/drivers/net/wireless/mediatek/mt76/mt76x02_mmio.c
+++ b/drivers/net/wireless/mediatek/mt76/mt76x02_mmio.c
@@ -19,6 +19,7 @@
 #include <linux/irq.h>
 
 #include "mt76x02.h"
+#include "mt76x02_mcu.h"
 #include "mt76x02_trace.h"
 
 struct beacon_bc_data {
@@ -418,9 +419,66 @@ static bool mt76x02_tx_hang(struct mt76x02_dev *dev)
 	return i < 4;
 }
 
+static void mt76x02_key_sync(struct ieee80211_hw *hw, struct ieee80211_vif *vif,
+			     struct ieee80211_sta *sta,
+			     struct ieee80211_key_conf *key, void *data)
+{
+	struct mt76x02_dev *dev = hw->priv;
+	struct mt76_wcid *wcid;
+
+	if (!sta)
+	    return;
+
+	wcid = (struct mt76_wcid *) sta->drv_priv;
+
+	if (wcid->hw_key_idx != key->keyidx || wcid->sw_iv)
+	    return;
+
+	mt76x02_mac_wcid_sync_pn(dev, wcid->idx, key);
+}
+
+static void mt76x02_reset_state(struct mt76x02_dev *dev)
+{
+	int i;
+
+	lockdep_assert_held(&dev->mt76.mutex);
+
+	clear_bit(MT76_STATE_RUNNING, &dev->mt76.state);
+
+	rcu_read_lock();
+	ieee80211_iter_keys_rcu(dev->mt76.hw, NULL, mt76x02_key_sync, NULL);
+	rcu_read_unlock();
+
+	for (i = 0; i < ARRAY_SIZE(dev->mt76.wcid); i++) {
+		struct ieee80211_sta *sta;
+		struct ieee80211_vif *vif;
+		struct mt76x02_sta *msta;
+		struct mt76_wcid *wcid;
+		void *priv;
+
+		wcid = rcu_dereference_protected(dev->mt76.wcid[i],
+					lockdep_is_held(&dev->mt76.mutex));
+		if (!wcid)
+			continue;
+
+		priv = msta = container_of(wcid, struct mt76x02_sta, wcid);
+		sta = container_of(priv, struct ieee80211_sta, drv_priv);
+
+		priv = msta->vif;
+		vif = container_of(priv, struct ieee80211_vif, drv_priv);
+
+		__mt76_sta_remove(&dev->mt76, vif, sta);
+		memset(msta, 0, sizeof(*msta));
+	}
+
+	dev->vif_mask = 0;
+	dev->beacon_mask = 0;
+}
+
 static void mt76x02_watchdog_reset(struct mt76x02_dev *dev)
 {
 	u32 mask = dev->mt76.mmio.irqmask;
+	bool restart = dev->mt76.mcu_ops->mcu_restart;
 	int i;
 
 	ieee80211_stop_queues(dev->mt76.hw);
@@ -434,6 +492,9 @@ static void mt76x02_watchdog_reset(struct mt76x02_dev *dev)
 
 	mutex_lock(&dev->mt76.mutex);
 
+	if (restart)
+		mt76x02_reset_state(dev);
+
 	if (dev->beacon_mask)
 		mt76_clear(dev, MT_BEACON_TIME_CFG,
 			   MT_BEACON_TIME_CFG_BEACON_TX |
@@ -452,20 +513,21 @@ static void mt76x02_watchdog_reset(struct mt76x02_dev *dev)
 	/* let fw reset DMA */
 	mt76_set(dev, 0x734, 0x3);
 
+	if (restart)
+		dev->mt76.mcu_ops->mcu_restart(&dev->mt76);
+
 	for (i = 0; i < ARRAY_SIZE(dev->mt76.q_tx); i++)
 		mt76_queue_tx_cleanup(dev, i, true);
 
 	for (i = 0; i < ARRAY_SIZE(dev->mt76.q_rx); i++)
 		mt76_queue_rx_reset(dev, i);
 
-	mt76_wr(dev, MT_MAC_SYS_CTRL,
-		MT_MAC_SYS_CTRL_ENABLE_TX | MT_MAC_SYS_CTRL_ENABLE_RX);
-	mt76_set(dev, MT_WPDMA_GLO_CFG,
-		 MT_WPDMA_GLO_CFG_TX_DMA_EN | MT_WPDMA_GLO_CFG_RX_DMA_EN);
+	mt76x02_mac_start(dev);
+
 	if (dev->ed_monitor)
 		mt76_set(dev, MT_TXOP_CTRL_CFG, MT_TXOP_ED_CCA_EN);
 
-	if (dev->beacon_mask)
+	if (dev->beacon_mask && !restart)
 		mt76_set(dev, MT_BEACON_TIME_CFG,
 			 MT_BEACON_TIME_CFG_BEACON_TX |
 			 MT_BEACON_TIME_CFG_TBTT_EN);
@@ -486,9 +548,13 @@ static void mt76x02_watchdog_reset(struct mt76x02_dev *dev)
 		napi_schedule(&dev->mt76.napi[i]);
 	}
 
-	ieee80211_wake_queues(dev->mt76.hw);
-
-	mt76_txq_schedule_all(&dev->mt76);
+	if (restart) {
+		mt76x02_mcu_function_select(dev, Q_SELECT, 1);
+		ieee80211_restart_hw(dev->mt76.hw);
+	} else {
+		ieee80211_wake_queues(dev->mt76.hw);
+		mt76_txq_schedule_all(&dev->mt76);
+	}
 }
 
 static void mt76x02_check_tx_hang(struct mt76x02_dev *dev)
diff --git a/drivers/net/wireless/mediatek/mt76/mt76x02_phy.c b/drivers/net/wireless/mediatek/mt76/mt76x02_phy.c
index a020c757ba5c..a54b63a96eae 100644
--- a/drivers/net/wireless/mediatek/mt76/mt76x02_phy.c
+++ b/drivers/net/wireless/mediatek/mt76/mt76x02_phy.c
@@ -194,6 +194,8 @@ bool mt76x02_phy_adjust_vga_gain(struct mt76x02_dev *dev)
 		ret = true;
 	}
 
+	dev->cal.agc_lowest_gain = dev->cal.agc_gain_adjust >= limit;
+
 	return ret;
 }
 EXPORT_SYMBOL_GPL(mt76x02_phy_adjust_vga_gain);
diff --git a/drivers/net/wireless/mediatek/mt76/mt76x02_usb_core.c b/drivers/net/wireless/mediatek/mt76/mt76x02_usb_core.c
index 43f07461c8d3..6fb52b596d42 100644
--- a/drivers/net/wireless/mediatek/mt76/mt76x02_usb_core.c
+++ b/drivers/net/wireless/mediatek/mt76/mt76x02_usb_core.c
@@ -85,8 +85,9 @@ int mt76x02u_tx_prepare_skb(struct mt76_dev *mdev, void *data,
 
 	mt76x02_insert_hdr_pad(skb);
 
-	txwi = skb_push(skb, sizeof(struct mt76x02_txwi));
+	txwi = (struct mt76x02_txwi *)(skb->data - sizeof(struct mt76x02_txwi));
 	mt76x02_mac_write_txwi(dev, txwi, skb, wcid, sta, len);
+	skb_push(skb, sizeof(struct mt76x02_txwi));
 
 	pid = mt76_tx_status_skb_add(mdev, wcid, skb);
 	txwi->pktid = pid;
diff --git a/drivers/net/wireless/mediatek/mt76/mt76x02_util.c b/drivers/net/wireless/mediatek/mt76/mt76x02_util.c
index a48c261b0c63..cd072ac614f7 100644
--- a/drivers/net/wireless/mediatek/mt76/mt76x02_util.c
+++ b/drivers/net/wireless/mediatek/mt76/mt76x02_util.c
@@ -237,6 +237,8 @@ int mt76x02_sta_add(struct mt76_dev *mdev, struct ieee80211_vif *vif,
 	struct mt76x02_vif *mvif = (struct mt76x02_vif *)vif->drv_priv;
 	int idx = 0;
 
+	memset(msta, 0, sizeof(*msta));
+
 	idx = mt76_wcid_alloc(dev->mt76.wcid_mask, ARRAY_SIZE(dev->mt76.wcid));
 	if (idx < 0)
 		return -ENOSPC;
@@ -274,6 +276,8 @@ mt76x02_vif_init(struct mt76x02_dev *dev, struct ieee80211_vif *vif,
 	struct mt76x02_vif *mvif = (struct mt76x02_vif *)vif->drv_priv;
 	struct mt76_txq *mtxq;
 
+	memset(mvif, 0, sizeof(*mvif));
+
 	mvif->idx = idx;
 	mvif->group_wcid.idx = MT_VIF_WCID(idx);
 	mvif->group_wcid.hw_key_idx = -1;
@@ -289,6 +293,12 @@ mt76x02_add_interface(struct ieee80211_hw *hw, struct ieee80211_vif *vif)
 	struct mt76x02_dev *dev = hw->priv;
 	unsigned int idx = 0;
 
+	/* Allow to change address in HW if we create first interface. */
+	if (!dev->vif_mask &&
+	    (((vif->addr[0] ^ dev->mt76.macaddr[0]) & ~GENMASK(4, 1)) ||
+	     memcmp(vif->addr + 1, dev->mt76.macaddr + 1, ETH_ALEN - 1)))
+		mt76x02_mac_setaddr(dev, vif->addr);
+
 	if (vif->addr[0] & BIT(1))
 		idx = 1 + (((dev->mt76.macaddr[0] ^ vif->addr[0]) >> 2) & 7);
 
@@ -311,10 +321,6 @@ mt76x02_add_interface(struct ieee80211_hw *hw, struct ieee80211_vif *vif)
 	if (dev->vif_mask & BIT(idx))
 		return -EBUSY;
 
-	/* Allow to change address in HW if we create first interface. */
-	if (!dev->vif_mask && !ether_addr_equal(dev->mt76.macaddr, vif->addr))
-                mt76x02_mac_setaddr(dev, vif->addr);
-
 	dev->vif_mask |= BIT(idx);
 
 	mt76x02_vif_init(dev, vif, idx);
diff --git a/drivers/net/wireless/mediatek/mt76/mt76x2/init.c b/drivers/net/wireless/mediatek/mt76/mt76x2/init.c
index f8534362e2c8..a30ef2c5a9db 100644
--- a/drivers/net/wireless/mediatek/mt76/mt76x2/init.c
+++ b/drivers/net/wireless/mediatek/mt76/mt76x2/init.c
@@ -106,7 +106,7 @@ void mt76_write_mac_initvals(struct mt76x02_dev *dev)
 		{ MT_TX_SW_CFG1,		0x00010000 },
 		{ MT_TX_SW_CFG2,		0x00000000 },
 		{ MT_TXOP_CTRL_CFG,		0x0400583f },
-		{ MT_TX_RTS_CFG,		0x00100020 },
+		{ MT_TX_RTS_CFG,		0x00ffff20 },
 		{ MT_TX_TIMEOUT_CFG,		0x000a2290 },
 		{ MT_TX_RETRY_CFG,		0x47f01f0f },
 		{ MT_EXP_ACK_TIME,		0x002c00dc },
diff --git a/drivers/net/wireless/mediatek/mt76/mt76x2/mt76x2.h b/drivers/net/wireless/mediatek/mt76/mt76x2/mt76x2.h
index 6c619f1c65c9..d7abe3d73bad 100644
--- a/drivers/net/wireless/mediatek/mt76/mt76x2/mt76x2.h
+++ b/drivers/net/wireless/mediatek/mt76/mt76x2/mt76x2.h
@@ -71,6 +71,7 @@ int mt76x2_mcu_load_cr(struct mt76x02_dev *dev, u8 type, u8 temp_level,
 
 void mt76x2_cleanup(struct mt76x02_dev *dev);
 
+int mt76x2_mac_reset(struct mt76x02_dev *dev, bool hard);
 void mt76x2_reset_wlan(struct mt76x02_dev *dev, bool enable);
 void mt76x2_init_txpower(struct mt76x02_dev *dev,
 			 struct ieee80211_supported_band *sband);
diff --git a/drivers/net/wireless/mediatek/mt76/mt76x2/pci_init.c b/drivers/net/wireless/mediatek/mt76/mt76x2/pci_init.c
index 984d9c4c2e1a..d3927a13e92e 100644
--- a/drivers/net/wireless/mediatek/mt76/mt76x2/pci_init.c
+++ b/drivers/net/wireless/mediatek/mt76/mt76x2/pci_init.c
@@ -77,7 +77,7 @@ mt76x2_fixup_xtal(struct mt76x02_dev *dev)
 	}
 }
 
-static int mt76x2_mac_reset(struct mt76x02_dev *dev, bool hard)
+int mt76x2_mac_reset(struct mt76x02_dev *dev, bool hard)
 {
 	const u8 *macaddr = dev->mt76.macaddr;
 	u32 val;
diff --git a/drivers/net/wireless/mediatek/mt76/mt76x2/pci_mcu.c b/drivers/net/wireless/mediatek/mt76/mt76x2/pci_mcu.c
index 03e24ae7f66c..605dc66ae83b 100644
--- a/drivers/net/wireless/mediatek/mt76/mt76x2/pci_mcu.c
+++ b/drivers/net/wireless/mediatek/mt76/mt76x2/pci_mcu.c
@@ -165,9 +165,30 @@ error:
 	return -ENOENT;
 }
 
+static int
+mt76pci_mcu_restart(struct mt76_dev *mdev)
+{
+	struct mt76x02_dev *dev;
+	int ret;
+
+	dev = container_of(mdev, struct mt76x02_dev, mt76);
+
+	mt76x02_mcu_cleanup(dev);
+	mt76x2_mac_reset(dev, true);
+
+	ret = mt76pci_load_firmware(dev);
+	if (ret)
+		return ret;
+
+	mt76_wr(dev, MT_WPDMA_RST_IDX, ~0);
+
+	return 0;
+}
+
 int mt76x2_mcu_init(struct mt76x02_dev *dev)
 {
 	static const struct mt76_mcu_ops mt76x2_mcu_ops = {
+		.mcu_restart = mt76pci_mcu_restart,
 		.mcu_send_msg = mt76x02_mcu_msg_send,
 	};
 	int ret;
diff --git a/drivers/net/wireless/mediatek/mt76/mt76x2/phy.c b/drivers/net/wireless/mediatek/mt76/mt76x2/phy.c
index 1848e8ab2e21..769a9b972044 100644
--- a/drivers/net/wireless/mediatek/mt76/mt76x2/phy.c
+++ b/drivers/net/wireless/mediatek/mt76/mt76x2/phy.c
@@ -260,10 +260,15 @@ mt76x2_phy_set_gain_val(struct mt76x02_dev *dev)
 	gain_val[0] = dev->cal.agc_gain_cur[0] - dev->cal.agc_gain_adjust;
 	gain_val[1] = dev->cal.agc_gain_cur[1] - dev->cal.agc_gain_adjust;
 
-	if (dev->mt76.chandef.width >= NL80211_CHAN_WIDTH_40)
+	val = 0x1836 << 16;
+	if (!mt76x2_has_ext_lna(dev) &&
+	    dev->mt76.chandef.width >= NL80211_CHAN_WIDTH_40)
 		val = 0x1e42 << 16;
-	else
-		val = 0x1836 << 16;
+
+	if (mt76x2_has_ext_lna(dev) &&
+	    dev->mt76.chandef.chan->band == NL80211_BAND_2GHZ &&
+	    dev->mt76.chandef.width < NL80211_CHAN_WIDTH_40)
+		val = 0x0f36 << 16;
 
 	val |= 0xf8;
 
@@ -280,6 +285,7 @@ void mt76x2_phy_update_channel_gain(struct mt76x02_dev *dev)
 {
 	u8 *gain = dev->cal.agc_gain_init;
 	u8 low_gain_delta, gain_delta;
+	u32 agc_35, agc_37;
 	bool gain_change;
 	int low_gain;
 	u32 val;
@@ -318,6 +324,16 @@ void mt76x2_phy_update_channel_gain(struct mt76x02_dev *dev)
 	else
 		low_gain_delta = 14;
 
+	agc_37 = 0x2121262c;
+	if (dev->mt76.chandef.chan->band == NL80211_BAND_2GHZ)
+		agc_35 = 0x11111516;
+	else if (low_gain == 2)
+		agc_35 = agc_37 = 0x08080808;
+	else if (dev->mt76.chandef.width == NL80211_CHAN_WIDTH_80)
+		agc_35 = 0x10101014;
+	else
+		agc_35 = 0x11111116;
+
 	if (low_gain == 2) {
 		mt76_wr(dev, MT_BBP(RXO, 18), 0xf000a990);
 		mt76_wr(dev, MT_BBP(AGC, 35), 0x08080808);
@@ -326,15 +342,13 @@ void mt76x2_phy_update_channel_gain(struct mt76x02_dev *dev)
 		dev->cal.agc_gain_adjust = 0;
 	} else {
 		mt76_wr(dev, MT_BBP(RXO, 18), 0xf000a991);
-		if (dev->mt76.chandef.width == NL80211_CHAN_WIDTH_80)
-			mt76_wr(dev, MT_BBP(AGC, 35), 0x10101014);
-		else
-			mt76_wr(dev, MT_BBP(AGC, 35), 0x11111116);
-		mt76_wr(dev, MT_BBP(AGC, 37), 0x2121262C);
 		gain_delta = 0;
 		dev->cal.agc_gain_adjust = low_gain_delta;
 	}
 
+	mt76_wr(dev, MT_BBP(AGC, 35), agc_35);
+	mt76_wr(dev, MT_BBP(AGC, 37), agc_37);
+
 	dev->cal.agc_gain_cur[0] = gain[0] - gain_delta;
 	dev->cal.agc_gain_cur[1] = gain[1] - gain_delta;
 	mt76x2_phy_set_gain_val(dev);
diff --git a/drivers/net/wireless/mediatek/mt76/mt76x2/usb.c b/drivers/net/wireless/mediatek/mt76/mt76x2/usb.c
index ddb6b2c48e01..ac0f13d46299 100644
--- a/drivers/net/wireless/mediatek/mt76/mt76x2/usb.c
+++ b/drivers/net/wireless/mediatek/mt76/mt76x2/usb.c
@@ -21,11 +21,10 @@
 #include "mt76x2u.h"
 
 static const struct usb_device_id mt76x2u_device_table[] = {
-	{ USB_DEVICE(0x0e8d, 0x7612) }, /* Alfa AWUS036ACM */
 	{ USB_DEVICE(0x0b05, 0x1833) },	/* Asus USB-AC54 */
 	{ USB_DEVICE(0x0b05, 0x17eb) },	/* Asus USB-AC55 */
 	{ USB_DEVICE(0x0b05, 0x180b) },	/* Asus USB-N53 B1 */
-	{ USB_DEVICE(0x0e8d, 0x7612) },	/* Aukey USB-AC1200 */
+	{ USB_DEVICE(0x0e8d, 0x7612) },	/* Aukey USBAC1200 - Alfa AWUS036ACM */
 	{ USB_DEVICE(0x057c, 0x8503) },	/* Avm FRITZ!WLAN AC860 */
 	{ USB_DEVICE(0x7392, 0xb711) },	/* Edimax EW 7722 UAC */
 	{ USB_DEVICE(0x0846, 0x9053) },	/* Netgear A6210 */
@@ -66,6 +65,10 @@ static int mt76x2u_probe(struct usb_interface *intf,
 
 	mdev->rev = mt76_rr(dev, MT_ASIC_VERSION);
 	dev_info(mdev->dev, "ASIC revision: %08x\n", mdev->rev);
+	if (!is_mt76x2(dev)) {
+		err = -ENODEV;
+		goto err;
+	}
 
 	err = mt76x2u_register_device(dev);
 	if (err < 0)
diff --git a/drivers/net/wireless/mediatek/mt76/mt76x2/usb_mac.c b/drivers/net/wireless/mediatek/mt76/mt76x2/usb_mac.c
index 5e84b4535cb1..3b82345756ea 100644
--- a/drivers/net/wireless/mediatek/mt76/mt76x2/usb_mac.c
+++ b/drivers/net/wireless/mediatek/mt76/mt76x2/usb_mac.c
@@ -93,7 +93,6 @@ int mt76x2u_mac_reset(struct mt76x02_dev *dev)
 	mt76_wr(dev, MT_TX_LINK_CFG, 0x1020);
 	mt76_wr(dev, MT_AUTO_RSP_CFG, 0x13);
 	mt76_wr(dev, MT_MAX_LEN_CFG, 0x2f00);
-	mt76_wr(dev, MT_TX_RTS_CFG, 0x92b20);
 
 	mt76_wr(dev, MT_WMM_AIFSN, 0x2273);
 	mt76_wr(dev, MT_WMM_CWMIN, 0x2344);
diff --git a/drivers/net/wireless/mediatek/mt76/tx.c b/drivers/net/wireless/mediatek/mt76/tx.c
index 5a349fe3e576..2585df512335 100644
--- a/drivers/net/wireless/mediatek/mt76/tx.c
+++ b/drivers/net/wireless/mediatek/mt76/tx.c
@@ -289,8 +289,11 @@ mt76_tx(struct mt76_dev *dev, struct ieee80211_sta *sta,
 	dev->queue_ops->tx_queue_skb(dev, q, skb, wcid, sta);
 	dev->queue_ops->kick(dev, q);
 
-	if (q->queued > q->ndesc - 8)
+	if (q->queued > q->ndesc - 8 && !q->stopped) {
 		ieee80211_stop_queue(dev->hw, skb_get_queue_mapping(skb));
+		q->stopped = true;
+	}
+
 	spin_unlock_bh(&q->lock);
 }
 EXPORT_SYMBOL_GPL(mt76_tx);
@@ -374,7 +377,10 @@ mt76_release_buffered_frames(struct ieee80211_hw *hw, struct ieee80211_sta *sta,
 	if (last_skb) {
 		mt76_queue_ps_skb(dev, sta, last_skb, true);
 		dev->queue_ops->kick(dev, hwq);
+	} else {
+		ieee80211_sta_eosp(sta);
 	}
+
 	spin_unlock_bh(&hwq->lock);
 }
 EXPORT_SYMBOL_GPL(mt76_release_buffered_frames);
@@ -577,6 +583,9 @@ void mt76_wake_tx_queue(struct ieee80211_hw *hw, struct ieee80211_txq *txq)
 	struct mt76_txq *mtxq = (struct mt76_txq *) txq->drv_priv;
 	struct mt76_queue *hwq = mtxq->hwq;
 
+	if (!test_bit(MT76_STATE_RUNNING, &dev->state))
+		return;
+
 	spin_lock_bh(&hwq->lock);
 	if (list_empty(&mtxq->list))
 		list_add_tail(&mtxq->list, &hwq->swq);
diff --git a/drivers/net/wireless/mediatek/mt76/usb.c b/drivers/net/wireless/mediatek/mt76/usb.c
index ae6ada370597..4c1abd492405 100644
--- a/drivers/net/wireless/mediatek/mt76/usb.c
+++ b/drivers/net/wireless/mediatek/mt76/usb.c
@@ -655,7 +655,11 @@ static void mt76u_tx_tasklet(unsigned long data)
 			spin_lock_bh(&q->lock);
 		}
 		mt76_txq_schedule(dev, q);
-		wake = i < IEEE80211_NUM_ACS && q->queued < q->ndesc - 8;
+
+		wake = q->stopped && q->queued < q->ndesc - 8;
+		if (wake)
+			q->stopped = false;
+
 		if (!q->queued)
 			wake_up(&dev->tx_wait);
 
diff --git a/drivers/net/wireless/mediatek/mt7601u/usb.c b/drivers/net/wireless/mediatek/mt7601u/usb.c
index d8b7863f7926..6ae7f14dc9bf 100644
--- a/drivers/net/wireless/mediatek/mt7601u/usb.c
+++ b/drivers/net/wireless/mediatek/mt7601u/usb.c
@@ -303,6 +303,10 @@ static int mt7601u_probe(struct usb_interface *usb_intf,
 	mac_rev = mt7601u_rr(dev, MT_MAC_CSR0);
 	dev_info(dev->dev, "ASIC revision: %08x MAC revision: %08x\n",
 		 asic_rev, mac_rev);
+	if ((asic_rev >> 16) != 0x7601) {
+		ret = -ENODEV;
+		goto err;
+	}
 
 	/* Note: vendor driver skips this check for MT7601U */
 	if (!(mt7601u_rr(dev, MT_EFUSE_CTRL) & MT_EFUSE_CTRL_SEL))
diff --git a/drivers/net/wireless/ralink/rt2x00/rt2x00.h b/drivers/net/wireless/ralink/rt2x00/rt2x00.h
index 4b1744e9fb78..50b92ca92bd7 100644
--- a/drivers/net/wireless/ralink/rt2x00/rt2x00.h
+++ b/drivers/net/wireless/ralink/rt2x00/rt2x00.h
@@ -673,7 +673,6 @@ enum rt2x00_state_flags {
 	CONFIG_CHANNEL_HT40,
 	CONFIG_POWERSAVING,
 	CONFIG_HT_DISABLED,
-	CONFIG_QOS_DISABLED,
 	CONFIG_MONITORING,
 
 	/*
diff --git a/drivers/net/wireless/ralink/rt2x00/rt2x00mac.c b/drivers/net/wireless/ralink/rt2x00/rt2x00mac.c
index 2825560e2424..e8462f25d252 100644
--- a/drivers/net/wireless/ralink/rt2x00/rt2x00mac.c
+++ b/drivers/net/wireless/ralink/rt2x00/rt2x00mac.c
@@ -642,19 +642,9 @@ void rt2x00mac_bss_info_changed(struct ieee80211_hw *hw,
 			rt2x00dev->intf_associated--;
 
 		rt2x00leds_led_assoc(rt2x00dev, !!rt2x00dev->intf_associated);
-
-		clear_bit(CONFIG_QOS_DISABLED, &rt2x00dev->flags);
 	}
 
 	/*
-	 * Check for access point which do not support 802.11e . We have to
-	 * generate data frames sequence number in S/W for such AP, because
-	 * of H/W bug.
-	 */
-	if (changes & BSS_CHANGED_QOS && !bss_conf->qos)
-		set_bit(CONFIG_QOS_DISABLED, &rt2x00dev->flags);
-
-	/*
 	 * When the erp information has changed, we should perform
 	 * additional configuration steps. For all other changes we are done.
 	 */
diff --git a/drivers/net/wireless/ralink/rt2x00/rt2x00queue.c b/drivers/net/wireless/ralink/rt2x00/rt2x00queue.c
index 92ddc19e7bf7..4834b4eb0206 100644
--- a/drivers/net/wireless/ralink/rt2x00/rt2x00queue.c
+++ b/drivers/net/wireless/ralink/rt2x00/rt2x00queue.c
@@ -201,15 +201,18 @@ static void rt2x00queue_create_tx_descriptor_seq(struct rt2x00_dev *rt2x00dev,
 	if (!rt2x00_has_cap_flag(rt2x00dev, REQUIRE_SW_SEQNO)) {
 		/*
 		 * rt2800 has a H/W (or F/W) bug, device incorrectly increase
-		 * seqno on retransmited data (non-QOS) frames. To workaround
-		 * the problem let's generate seqno in software if QOS is
-		 * disabled.
+		 * seqno on retransmitted data (non-QOS) and management frames.
+		 * To workaround the problem let's generate seqno in software.
+		 * Except for beacons which are transmitted periodically by H/W
+		 * hence hardware has to assign seqno for them.
 		 */
-		if (test_bit(CONFIG_QOS_DISABLED, &rt2x00dev->flags))
-			__clear_bit(ENTRY_TXD_GENERATE_SEQ, &txdesc->flags);
-		else
+	    	if (ieee80211_is_beacon(hdr->frame_control)) {
+			__set_bit(ENTRY_TXD_GENERATE_SEQ, &txdesc->flags);
 			/* H/W will generate sequence number */
 			return;
+		}
+
+		__clear_bit(ENTRY_TXD_GENERATE_SEQ, &txdesc->flags);
 	}
 
 	/*
diff --git a/drivers/nfc/s3fwrn5/firmware.c b/drivers/nfc/s3fwrn5/firmware.c
index b7828fb252f2..b681073ae8ba 100644
--- a/drivers/nfc/s3fwrn5/firmware.c
+++ b/drivers/nfc/s3fwrn5/firmware.c
@@ -449,7 +449,6 @@ int s3fwrn5_fw_download(struct s3fwrn5_fw_info *fw_info)
 		SHASH_DESC_ON_STACK(desc, tfm);
 
 		desc->tfm = tfm;
-		desc->flags = CRYPTO_TFM_REQ_MAY_SLEEP;
 
 		ret = crypto_shash_digest(desc, fw->image, image_size,
 					  hash_data);
diff --git a/drivers/nfc/st95hf/core.c b/drivers/nfc/st95hf/core.c
index 2b26f762fbc3..01acb6e53365 100644
--- a/drivers/nfc/st95hf/core.c
+++ b/drivers/nfc/st95hf/core.c
@@ -1074,6 +1074,12 @@ static const struct spi_device_id st95hf_id[] = {
 };
 MODULE_DEVICE_TABLE(spi, st95hf_id);
 
+static const struct of_device_id st95hf_spi_of_match[] = {
+        { .compatible = "st,st95hf" },
+        { },
+};
+MODULE_DEVICE_TABLE(of, st95hf_spi_of_match);
+
 static int st95hf_probe(struct spi_device *nfc_spi_dev)
 {
 	int ret;
@@ -1260,6 +1266,7 @@ static struct spi_driver st95hf_driver = {
 	.driver = {
 		.name = "st95hf",
 		.owner = THIS_MODULE,
+		.of_match_table = of_match_ptr(st95hf_spi_of_match),
 	},
 	.id_table = st95hf_id,
 	.probe = st95hf_probe,
diff --git a/drivers/ntb/hw/idt/ntb_hw_idt.c b/drivers/ntb/hw/idt/ntb_hw_idt.c
index 1dede87dd54f..dcf234680535 100644
--- a/drivers/ntb/hw/idt/ntb_hw_idt.c
+++ b/drivers/ntb/hw/idt/ntb_hw_idt.c
@@ -358,8 +358,6 @@ static void idt_sw_write(struct idt_ntb_dev *ndev,
 	iowrite32((u32)reg, ndev->cfgspc + (ptrdiff_t)IDT_NT_GASAADDR);
 	/* Put the new value of the register */
 	iowrite32(data, ndev->cfgspc + (ptrdiff_t)IDT_NT_GASADATA);
-	/* Make sure the PCIe transactions are executed */
-	mmiowb();
 	/* Unlock GASA registers operations */
 	spin_unlock_irqrestore(&ndev->gasa_lock, irqflags);
 }
@@ -750,7 +748,6 @@ static void idt_ntb_local_link_enable(struct idt_ntb_dev *ndev)
 	spin_lock_irqsave(&ndev->mtbl_lock, irqflags);
 	idt_nt_write(ndev, IDT_NT_NTMTBLADDR, ndev->part);
 	idt_nt_write(ndev, IDT_NT_NTMTBLDATA, mtbldata);
-	mmiowb();
 	spin_unlock_irqrestore(&ndev->mtbl_lock, irqflags);
 
 	/* Notify the peers by setting and clearing the global signal bit */
@@ -778,7 +775,6 @@ static void idt_ntb_local_link_disable(struct idt_ntb_dev *ndev)
 	spin_lock_irqsave(&ndev->mtbl_lock, irqflags);
 	idt_nt_write(ndev, IDT_NT_NTMTBLADDR, ndev->part);
 	idt_nt_write(ndev, IDT_NT_NTMTBLDATA, 0);
-	mmiowb();
 	spin_unlock_irqrestore(&ndev->mtbl_lock, irqflags);
 
 	/* Notify the peers by setting and clearing the global signal bit */
@@ -1339,7 +1335,6 @@ static int idt_ntb_peer_mw_set_trans(struct ntb_dev *ntb, int pidx, int widx,
 		idt_nt_write(ndev, IDT_NT_LUTLDATA, (u32)addr);
 		idt_nt_write(ndev, IDT_NT_LUTMDATA, (u32)(addr >> 32));
 		idt_nt_write(ndev, IDT_NT_LUTUDATA, data);
-		mmiowb();
 		spin_unlock_irqrestore(&ndev->lut_lock, irqflags);
 		/* Limit address isn't specified since size is fixed for LUT */
 	}
@@ -1393,7 +1388,6 @@ static int idt_ntb_peer_mw_clear_trans(struct ntb_dev *ntb, int pidx,
 		idt_nt_write(ndev, IDT_NT_LUTLDATA, 0);
 		idt_nt_write(ndev, IDT_NT_LUTMDATA, 0);
 		idt_nt_write(ndev, IDT_NT_LUTUDATA, 0);
-		mmiowb();
 		spin_unlock_irqrestore(&ndev->lut_lock, irqflags);
 	}
 
@@ -1812,7 +1806,6 @@ static int idt_ntb_peer_msg_write(struct ntb_dev *ntb, int pidx, int midx,
 	/* Set the route and send the data */
 	idt_sw_write(ndev, partdata_tbl[ndev->part].msgctl[midx], swpmsgctl);
 	idt_nt_write(ndev, ntdata_tbl.msgs[midx].out, msg);
-	mmiowb();
 	/* Unlock the messages routing table */
 	spin_unlock_irqrestore(&ndev->msg_locks[midx], irqflags);
 
diff --git a/drivers/ntb/test/ntb_perf.c b/drivers/ntb/test/ntb_perf.c
index 2a9d6b0d1f19..11a6cd374004 100644
--- a/drivers/ntb/test/ntb_perf.c
+++ b/drivers/ntb/test/ntb_perf.c
@@ -284,11 +284,9 @@ static int perf_spad_cmd_send(struct perf_peer *peer, enum perf_cmd cmd,
 		ntb_peer_spad_write(perf->ntb, peer->pidx,
 				    PERF_SPAD_HDATA(perf->gidx),
 				    upper_32_bits(data));
-		mmiowb();
 		ntb_peer_spad_write(perf->ntb, peer->pidx,
 				    PERF_SPAD_CMD(perf->gidx),
 				    cmd);
-		mmiowb();
 		ntb_peer_db_set(perf->ntb, PERF_SPAD_NOTIFY(peer->gidx));
 
 		dev_dbg(&perf->ntb->dev, "DB ring peer %#llx\n",
@@ -379,7 +377,6 @@ static int perf_msg_cmd_send(struct perf_peer *peer, enum perf_cmd cmd,
 
 		ntb_peer_msg_write(perf->ntb, peer->pidx, PERF_MSG_HDATA,
 				   upper_32_bits(data));
-		mmiowb();
 
 		/* This call shall trigger peer message event */
 		ntb_peer_msg_write(perf->ntb, peer->pidx, PERF_MSG_CMD, cmd);
diff --git a/drivers/nvdimm/btt_devs.c b/drivers/nvdimm/btt_devs.c
index b72a303176c7..9486acc08402 100644
--- a/drivers/nvdimm/btt_devs.c
+++ b/drivers/nvdimm/btt_devs.c
@@ -198,14 +198,15 @@ static struct device *__nd_btt_create(struct nd_region *nd_region,
 		return NULL;
 
 	nd_btt->id = ida_simple_get(&nd_region->btt_ida, 0, 0, GFP_KERNEL);
-	if (nd_btt->id < 0) {
-		kfree(nd_btt);
-		return NULL;
-	}
+	if (nd_btt->id < 0)
+		goto out_nd_btt;
 
 	nd_btt->lbasize = lbasize;
-	if (uuid)
+	if (uuid) {
 		uuid = kmemdup(uuid, 16, GFP_KERNEL);
+		if (!uuid)
+			goto out_put_id;
+	}
 	nd_btt->uuid = uuid;
 	dev = &nd_btt->dev;
 	dev_set_name(dev, "btt%d.%d", nd_region->id, nd_btt->id);
@@ -220,6 +221,13 @@ static struct device *__nd_btt_create(struct nd_region *nd_region,
 		return NULL;
 	}
 	return dev;
+
+out_put_id:
+	ida_simple_remove(&nd_region->btt_ida, nd_btt->id);
+
+out_nd_btt:
+	kfree(nd_btt);
+	return NULL;
 }
 
 struct device *nd_btt_create(struct nd_region *nd_region)
diff --git a/drivers/nvdimm/namespace_devs.c b/drivers/nvdimm/namespace_devs.c
index 7849bf1812c4..f293556cbbf6 100644
--- a/drivers/nvdimm/namespace_devs.c
+++ b/drivers/nvdimm/namespace_devs.c
@@ -2249,9 +2249,12 @@ static struct device *create_namespace_blk(struct nd_region *nd_region,
 	if (!nsblk->uuid)
 		goto blk_err;
 	memcpy(name, nd_label->name, NSLABEL_NAME_LEN);
-	if (name[0])
+	if (name[0]) {
 		nsblk->alt_name = kmemdup(name, NSLABEL_NAME_LEN,
 				GFP_KERNEL);
+		if (!nsblk->alt_name)
+			goto blk_err;
+	}
 	res = nsblk_add_resource(nd_region, ndd, nsblk,
 			__le64_to_cpu(nd_label->dpa));
 	if (!res)
diff --git a/drivers/nvdimm/pmem.c b/drivers/nvdimm/pmem.c
index bc2f700feef8..0279eb1da3ef 100644
--- a/drivers/nvdimm/pmem.c
+++ b/drivers/nvdimm/pmem.c
@@ -113,13 +113,13 @@ static void write_pmem(void *pmem_addr, struct page *page,
 
 	while (len) {
 		mem = kmap_atomic(page);
-		chunk = min_t(unsigned int, len, PAGE_SIZE);
+		chunk = min_t(unsigned int, len, PAGE_SIZE - off);
 		memcpy_flushcache(pmem_addr, mem + off, chunk);
 		kunmap_atomic(mem);
 		len -= chunk;
 		off = 0;
 		page++;
-		pmem_addr += PAGE_SIZE;
+		pmem_addr += chunk;
 	}
 }
 
@@ -132,7 +132,7 @@ static blk_status_t read_pmem(struct page *page, unsigned int off,
 
 	while (len) {
 		mem = kmap_atomic(page);
-		chunk = min_t(unsigned int, len, PAGE_SIZE);
+		chunk = min_t(unsigned int, len, PAGE_SIZE - off);
 		rem = memcpy_mcsafe(mem + off, pmem_addr, chunk);
 		kunmap_atomic(mem);
 		if (rem)
@@ -140,7 +140,7 @@ static blk_status_t read_pmem(struct page *page, unsigned int off,
 		len -= chunk;
 		off = 0;
 		page++;
-		pmem_addr += PAGE_SIZE;
+		pmem_addr += chunk;
 	}
 	return BLK_STS_OK;
 }
diff --git a/drivers/nvdimm/security.c b/drivers/nvdimm/security.c
index f8bb746a549f..a570f2263a42 100644
--- a/drivers/nvdimm/security.c
+++ b/drivers/nvdimm/security.c
@@ -22,6 +22,8 @@ static bool key_revalidate = true;
 module_param(key_revalidate, bool, 0444);
 MODULE_PARM_DESC(key_revalidate, "Require key validation at init.");
 
+static const char zero_key[NVDIMM_PASSPHRASE_LEN];
+
 static void *key_data(struct key *key)
 {
 	struct encrypted_key_payload *epayload = dereference_key_locked(key);
@@ -75,6 +77,16 @@ static struct key *nvdimm_request_key(struct nvdimm *nvdimm)
 	return key;
 }
 
+static const void *nvdimm_get_key_payload(struct nvdimm *nvdimm,
+		struct key **key)
+{
+	*key = nvdimm_request_key(nvdimm);
+	if (!*key)
+		return zero_key;
+
+	return key_data(*key);
+}
+
 static struct key *nvdimm_lookup_user_key(struct nvdimm *nvdimm,
 		key_serial_t id, int subclass)
 {
@@ -105,36 +117,57 @@ static struct key *nvdimm_lookup_user_key(struct nvdimm *nvdimm,
 	return key;
 }
 
-static struct key *nvdimm_key_revalidate(struct nvdimm *nvdimm)
+static const void *nvdimm_get_user_key_payload(struct nvdimm *nvdimm,
+		key_serial_t id, int subclass, struct key **key)
+{
+	*key = NULL;
+	if (id == 0) {
+		if (subclass == NVDIMM_BASE_KEY)
+			return zero_key;
+		else
+			return NULL;
+	}
+
+	*key = nvdimm_lookup_user_key(nvdimm, id, subclass);
+	if (!*key)
+		return NULL;
+
+	return key_data(*key);
+}
+
+
+static int nvdimm_key_revalidate(struct nvdimm *nvdimm)
 {
 	struct key *key;
 	int rc;
+	const void *data;
 
 	if (!nvdimm->sec.ops->change_key)
-		return NULL;
+		return -EOPNOTSUPP;
 
-	key = nvdimm_request_key(nvdimm);
-	if (!key)
-		return NULL;
+	data = nvdimm_get_key_payload(nvdimm, &key);
 
 	/*
 	 * Send the same key to the hardware as new and old key to
 	 * verify that the key is good.
 	 */
-	rc = nvdimm->sec.ops->change_key(nvdimm, key_data(key),
-			key_data(key), NVDIMM_USER);
+	rc = nvdimm->sec.ops->change_key(nvdimm, data, data, NVDIMM_USER);
 	if (rc < 0) {
 		nvdimm_put_key(key);
-		key = NULL;
+		return rc;
 	}
-	return key;
+
+	nvdimm_put_key(key);
+	nvdimm->sec.state = nvdimm_security_state(nvdimm, NVDIMM_USER);
+	return 0;
 }
 
 static int __nvdimm_security_unlock(struct nvdimm *nvdimm)
 {
 	struct device *dev = &nvdimm->dev;
 	struct nvdimm_bus *nvdimm_bus = walk_to_nvdimm_bus(dev);
-	struct key *key = NULL;
+	struct key *key;
+	const void *data;
 	int rc;
 
 	/* The bus lock should be held at the top level of the call stack */
@@ -160,16 +193,11 @@ static int __nvdimm_security_unlock(struct nvdimm *nvdimm)
 		if (!key_revalidate)
 			return 0;
 
-		key = nvdimm_key_revalidate(nvdimm);
-		if (!key)
-			return nvdimm_security_freeze(nvdimm);
+		return nvdimm_key_revalidate(nvdimm);
 	} else
-		key = nvdimm_request_key(nvdimm);
+		data = nvdimm_get_key_payload(nvdimm, &key);
 
-	if (!key)
-		return -ENOKEY;
-
-	rc = nvdimm->sec.ops->unlock(nvdimm, key_data(key));
+	rc = nvdimm->sec.ops->unlock(nvdimm, data);
 	dev_dbg(dev, "key: %d unlock: %s\n", key_serial(key),
 			rc == 0 ? "success" : "fail");
 
@@ -195,6 +223,7 @@ int nvdimm_security_disable(struct nvdimm *nvdimm, unsigned int keyid)
 	struct nvdimm_bus *nvdimm_bus = walk_to_nvdimm_bus(dev);
 	struct key *key;
 	int rc;
+	const void *data;
 
 	/* The bus lock should be held at the top level of the call stack */
 	lockdep_assert_held(&nvdimm_bus->reconfig_mutex);
@@ -214,11 +243,12 @@ int nvdimm_security_disable(struct nvdimm *nvdimm, unsigned int keyid)
 		return -EBUSY;
 	}
 
-	key = nvdimm_lookup_user_key(nvdimm, keyid, NVDIMM_BASE_KEY);
-	if (!key)
+	data = nvdimm_get_user_key_payload(nvdimm, keyid,
+			NVDIMM_BASE_KEY, &key);
+	if (!data)
 		return -ENOKEY;
 
-	rc = nvdimm->sec.ops->disable(nvdimm, key_data(key));
+	rc = nvdimm->sec.ops->disable(nvdimm, data);
 	dev_dbg(dev, "key: %d disable: %s\n", key_serial(key),
 			rc == 0 ? "success" : "fail");
 
@@ -235,6 +265,7 @@ int nvdimm_security_update(struct nvdimm *nvdimm, unsigned int keyid,
 	struct nvdimm_bus *nvdimm_bus = walk_to_nvdimm_bus(dev);
 	struct key *key, *newkey;
 	int rc;
+	const void *data, *newdata;
 
 	/* The bus lock should be held at the top level of the call stack */
 	lockdep_assert_held(&nvdimm_bus->reconfig_mutex);
@@ -249,22 +280,19 @@ int nvdimm_security_update(struct nvdimm *nvdimm, unsigned int keyid,
 		return -EIO;
 	}
 
-	if (keyid == 0)
-		key = NULL;
-	else {
-		key = nvdimm_lookup_user_key(nvdimm, keyid, NVDIMM_BASE_KEY);
-		if (!key)
-			return -ENOKEY;
-	}
+	data = nvdimm_get_user_key_payload(nvdimm, keyid,
+			NVDIMM_BASE_KEY, &key);
+	if (!data)
+		return -ENOKEY;
 
-	newkey = nvdimm_lookup_user_key(nvdimm, new_keyid, NVDIMM_NEW_KEY);
-	if (!newkey) {
+	newdata = nvdimm_get_user_key_payload(nvdimm, new_keyid,
+			NVDIMM_NEW_KEY, &newkey);
+	if (!newdata) {
 		nvdimm_put_key(key);
 		return -ENOKEY;
 	}
 
-	rc = nvdimm->sec.ops->change_key(nvdimm, key ? key_data(key) : NULL,
-			key_data(newkey), pass_type);
+	rc = nvdimm->sec.ops->change_key(nvdimm, data, newdata, pass_type);
 	dev_dbg(dev, "key: %d %d update%s: %s\n",
 			key_serial(key), key_serial(newkey),
 			pass_type == NVDIMM_MASTER ? "(master)" : "(user)",
@@ -286,8 +314,9 @@ int nvdimm_security_erase(struct nvdimm *nvdimm, unsigned int keyid,
 {
 	struct device *dev = &nvdimm->dev;
 	struct nvdimm_bus *nvdimm_bus = walk_to_nvdimm_bus(dev);
-	struct key *key;
+	struct key *key = NULL;
 	int rc;
+	const void *data;
 
 	/* The bus lock should be held at the top level of the call stack */
 	lockdep_assert_held(&nvdimm_bus->reconfig_mutex);
@@ -319,11 +348,12 @@ int nvdimm_security_erase(struct nvdimm *nvdimm, unsigned int keyid,
 		return -EOPNOTSUPP;
 	}
 
-	key = nvdimm_lookup_user_key(nvdimm, keyid, NVDIMM_BASE_KEY);
-	if (!key)
+	data = nvdimm_get_user_key_payload(nvdimm, keyid,
+			NVDIMM_BASE_KEY, &key);
+	if (!data)
 		return -ENOKEY;
 
-	rc = nvdimm->sec.ops->erase(nvdimm, key_data(key), pass_type);
+	rc = nvdimm->sec.ops->erase(nvdimm, data, pass_type);
 	dev_dbg(dev, "key: %d erase%s: %s\n", key_serial(key),
 			pass_type == NVDIMM_MASTER ? "(master)" : "(user)",
 			rc == 0 ? "success" : "fail");
@@ -337,8 +367,9 @@ int nvdimm_security_overwrite(struct nvdimm *nvdimm, unsigned int keyid)
 {
 	struct device *dev = &nvdimm->dev;
 	struct nvdimm_bus *nvdimm_bus = walk_to_nvdimm_bus(dev);
-	struct key *key;
+	struct key *key = NULL;
 	int rc;
+	const void *data;
 
 	/* The bus lock should be held at the top level of the call stack */
 	lockdep_assert_held(&nvdimm_bus->reconfig_mutex);
@@ -368,15 +399,12 @@ int nvdimm_security_overwrite(struct nvdimm *nvdimm, unsigned int keyid)
 		return -EBUSY;
 	}
 
-	if (keyid == 0)
-		key = NULL;
-	else {
-		key = nvdimm_lookup_user_key(nvdimm, keyid, NVDIMM_BASE_KEY);
-		if (!key)
-			return -ENOKEY;
-	}
+	data = nvdimm_get_user_key_payload(nvdimm, keyid,
+			NVDIMM_BASE_KEY, &key);
+	if (!data)
+		return -ENOKEY;
 
-	rc = nvdimm->sec.ops->overwrite(nvdimm, key ? key_data(key) : NULL);
+	rc = nvdimm->sec.ops->overwrite(nvdimm, data);
 	dev_dbg(dev, "key: %d overwrite submission: %s\n", key_serial(key),
 			rc == 0 ? "success" : "fail");
 
diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c
index 470601980794..6265d9225ec8 100644
--- a/drivers/nvme/host/core.c
+++ b/drivers/nvme/host/core.c
@@ -288,7 +288,7 @@ bool nvme_cancel_request(struct request *req, void *data, bool reserved)
 				"Cancelling I/O %d", req->tag);
 
 	nvme_req(req)->status = NVME_SC_ABORT_REQ;
-	blk_mq_complete_request(req);
+	blk_mq_complete_request_sync(req);
 	return true;
 }
 EXPORT_SYMBOL_GPL(nvme_cancel_request);
@@ -388,7 +388,7 @@ static void nvme_free_ns_head(struct kref *ref)
 	nvme_mpath_remove_disk(head);
 	ida_simple_remove(&head->subsys->ns_ida, head->instance);
 	list_del_init(&head->entry);
-	cleanup_srcu_struct_quiesced(&head->srcu);
+	cleanup_srcu_struct(&head->srcu);
 	nvme_put_subsystem(head->subsys);
 	kfree(head);
 }
diff --git a/drivers/nvme/host/fc.c b/drivers/nvme/host/fc.c
index f3b9d91ba0df..6d8451356eac 100644
--- a/drivers/nvme/host/fc.c
+++ b/drivers/nvme/host/fc.c
@@ -1845,7 +1845,7 @@ nvme_fc_init_queue(struct nvme_fc_ctrl *ctrl, int idx)
 	memset(queue, 0, sizeof(*queue));
 	queue->ctrl = ctrl;
 	queue->qnum = idx;
-	atomic_set(&queue->csn, 1);
+	atomic_set(&queue->csn, 0);
 	queue->dev = ctrl->dev;
 
 	if (idx > 0)
@@ -1887,7 +1887,7 @@ nvme_fc_free_queue(struct nvme_fc_queue *queue)
 	 */
 
 	queue->connection_id = 0;
-	atomic_set(&queue->csn, 1);
+	atomic_set(&queue->csn, 0);
 }
 
 static void
@@ -2183,7 +2183,6 @@ nvme_fc_start_fcp_op(struct nvme_fc_ctrl *ctrl, struct nvme_fc_queue *queue,
 {
 	struct nvme_fc_cmd_iu *cmdiu = &op->cmd_iu;
 	struct nvme_command *sqe = &cmdiu->sqe;
-	u32 csn;
 	int ret, opstate;
 
 	/*
@@ -2198,8 +2197,6 @@ nvme_fc_start_fcp_op(struct nvme_fc_ctrl *ctrl, struct nvme_fc_queue *queue,
 
 	/* format the FC-NVME CMD IU and fcp_req */
 	cmdiu->connection_id = cpu_to_be64(queue->connection_id);
-	csn = atomic_inc_return(&queue->csn);
-	cmdiu->csn = cpu_to_be32(csn);
 	cmdiu->data_len = cpu_to_be32(data_len);
 	switch (io_dir) {
 	case NVMEFC_FCP_WRITE:
@@ -2257,11 +2254,24 @@ nvme_fc_start_fcp_op(struct nvme_fc_ctrl *ctrl, struct nvme_fc_queue *queue,
 	if (!(op->flags & FCOP_FLAGS_AEN))
 		blk_mq_start_request(op->rq);
 
+	cmdiu->csn = cpu_to_be32(atomic_inc_return(&queue->csn));
 	ret = ctrl->lport->ops->fcp_io(&ctrl->lport->localport,
 					&ctrl->rport->remoteport,
 					queue->lldd_handle, &op->fcp_req);
 
 	if (ret) {
+		/*
+		 * If the lld fails to send the command is there an issue with
+		 * the csn value?  If the command that fails is the Connect,
+		 * no - as the connection won't be live.  If it is a command
+		 * post-connect, it's possible a gap in csn may be created.
+		 * Does this matter?  As Linux initiators don't send fused
+		 * commands, no.  The gap would exist, but as there's nothing
+		 * that depends on csn order to be delivered on the target
+		 * side, it shouldn't hurt.  It would be difficult for a
+		 * target to even detect the csn gap as it has no idea when the
+		 * cmd with the csn was supposed to arrive.
+		 */
 		opstate = atomic_xchg(&op->state, FCPOP_STATE_COMPLETE);
 		__nvme_fc_fcpop_chk_teardowns(ctrl, op, opstate);
 
diff --git a/drivers/nvme/host/multipath.c b/drivers/nvme/host/multipath.c
index 2839bb70badf..f0716f6ce41f 100644
--- a/drivers/nvme/host/multipath.c
+++ b/drivers/nvme/host/multipath.c
@@ -404,15 +404,12 @@ static inline bool nvme_state_is_live(enum nvme_ana_state state)
 static void nvme_update_ns_ana_state(struct nvme_ana_group_desc *desc,
 		struct nvme_ns *ns)
 {
-	enum nvme_ana_state old;
-
 	mutex_lock(&ns->head->lock);
-	old = ns->ana_state;
 	ns->ana_grpid = le32_to_cpu(desc->grpid);
 	ns->ana_state = desc->state;
 	clear_bit(NVME_NS_ANA_PENDING, &ns->flags);
 
-	if (nvme_state_is_live(ns->ana_state) && !nvme_state_is_live(old))
+	if (nvme_state_is_live(ns->ana_state))
 		nvme_mpath_set_live(ns);
 	mutex_unlock(&ns->head->lock);
 }
diff --git a/drivers/nvme/host/tcp.c b/drivers/nvme/host/tcp.c
index e7e08889865e..68c49dd67210 100644
--- a/drivers/nvme/host/tcp.c
+++ b/drivers/nvme/host/tcp.c
@@ -627,7 +627,7 @@ static int nvme_tcp_recv_pdu(struct nvme_tcp_queue *queue, struct sk_buff *skb,
 	return ret;
 }
 
-static inline void nvme_tcp_end_request(struct request *rq, __le16 status)
+static inline void nvme_tcp_end_request(struct request *rq, u16 status)
 {
 	union nvme_result res = {};
 
diff --git a/drivers/nvme/target/admin-cmd.c b/drivers/nvme/target/admin-cmd.c
index 76250181fee0..9f72d515fc4b 100644
--- a/drivers/nvme/target/admin-cmd.c
+++ b/drivers/nvme/target/admin-cmd.c
@@ -24,6 +24,11 @@ u32 nvmet_get_log_page_len(struct nvme_command *cmd)
 	return len;
 }
 
+u64 nvmet_get_log_page_offset(struct nvme_command *cmd)
+{
+	return le64_to_cpu(cmd->get_log_page.lpo);
+}
+
 static void nvmet_execute_get_log_page_noop(struct nvmet_req *req)
 {
 	nvmet_req_complete(req, nvmet_zero_sgl(req, 0, req->data_len));
diff --git a/drivers/nvme/target/core.c b/drivers/nvme/target/core.c
index 2d73b66e3686..b3e765a95af8 100644
--- a/drivers/nvme/target/core.c
+++ b/drivers/nvme/target/core.c
@@ -509,7 +509,7 @@ int nvmet_ns_enable(struct nvmet_ns *ns)
 
 	ret = nvmet_p2pmem_ns_enable(ns);
 	if (ret)
-		goto out_unlock;
+		goto out_dev_disable;
 
 	list_for_each_entry(ctrl, &subsys->ctrls, subsys_entry)
 		nvmet_p2pmem_ns_add_p2p(ctrl, ns);
@@ -550,7 +550,7 @@ out_unlock:
 out_dev_put:
 	list_for_each_entry(ctrl, &subsys->ctrls, subsys_entry)
 		pci_dev_put(radix_tree_delete(&ctrl->p2p_ns_map, ns->nsid));
-
+out_dev_disable:
 	nvmet_ns_dev_disable(ns);
 	goto out_unlock;
 }
diff --git a/drivers/nvme/target/discovery.c b/drivers/nvme/target/discovery.c
index c872b47a88f3..33ed95e72d6b 100644
--- a/drivers/nvme/target/discovery.c
+++ b/drivers/nvme/target/discovery.c
@@ -131,54 +131,76 @@ static void nvmet_set_disc_traddr(struct nvmet_req *req, struct nvmet_port *port
 		memcpy(traddr, port->disc_addr.traddr, NVMF_TRADDR_SIZE);
 }
 
+static size_t discovery_log_entries(struct nvmet_req *req)
+{
+	struct nvmet_ctrl *ctrl = req->sq->ctrl;
+	struct nvmet_subsys_link *p;
+	struct nvmet_port *r;
+	size_t entries = 0;
+
+	list_for_each_entry(p, &req->port->subsystems, entry) {
+		if (!nvmet_host_allowed(p->subsys, ctrl->hostnqn))
+			continue;
+		entries++;
+	}
+	list_for_each_entry(r, &req->port->referrals, entry)
+		entries++;
+	return entries;
+}
+
 static void nvmet_execute_get_disc_log_page(struct nvmet_req *req)
 {
 	const int entry_size = sizeof(struct nvmf_disc_rsp_page_entry);
 	struct nvmet_ctrl *ctrl = req->sq->ctrl;
 	struct nvmf_disc_rsp_page_hdr *hdr;
+	u64 offset = nvmet_get_log_page_offset(req->cmd);
 	size_t data_len = nvmet_get_log_page_len(req->cmd);
-	size_t alloc_len = max(data_len, sizeof(*hdr));
-	int residual_len = data_len - sizeof(*hdr);
+	size_t alloc_len;
 	struct nvmet_subsys_link *p;
 	struct nvmet_port *r;
 	u32 numrec = 0;
 	u16 status = 0;
+	void *buffer;
+
+	/* Spec requires dword aligned offsets */
+	if (offset & 0x3) {
+		status = NVME_SC_INVALID_FIELD | NVME_SC_DNR;
+		goto out;
+	}
 
 	/*
 	 * Make sure we're passing at least a buffer of response header size.
 	 * If host provided data len is less than the header size, only the
 	 * number of bytes requested by host will be sent to host.
 	 */
-	hdr = kzalloc(alloc_len, GFP_KERNEL);
-	if (!hdr) {
+	down_read(&nvmet_config_sem);
+	alloc_len = sizeof(*hdr) + entry_size * discovery_log_entries(req);
+	buffer = kzalloc(alloc_len, GFP_KERNEL);
+	if (!buffer) {
+		up_read(&nvmet_config_sem);
 		status = NVME_SC_INTERNAL;
 		goto out;
 	}
 
-	down_read(&nvmet_config_sem);
+	hdr = buffer;
 	list_for_each_entry(p, &req->port->subsystems, entry) {
+		char traddr[NVMF_TRADDR_SIZE];
+
 		if (!nvmet_host_allowed(p->subsys, ctrl->hostnqn))
 			continue;
-		if (residual_len >= entry_size) {
-			char traddr[NVMF_TRADDR_SIZE];
-
-			nvmet_set_disc_traddr(req, req->port, traddr);
-			nvmet_format_discovery_entry(hdr, req->port,
-					p->subsys->subsysnqn, traddr,
-					NVME_NQN_NVME, numrec);
-			residual_len -= entry_size;
-		}
+
+		nvmet_set_disc_traddr(req, req->port, traddr);
+		nvmet_format_discovery_entry(hdr, req->port,
+				p->subsys->subsysnqn, traddr,
+				NVME_NQN_NVME, numrec);
 		numrec++;
 	}
 
 	list_for_each_entry(r, &req->port->referrals, entry) {
-		if (residual_len >= entry_size) {
-			nvmet_format_discovery_entry(hdr, r,
-					NVME_DISC_SUBSYS_NAME,
-					r->disc_addr.traddr,
-					NVME_NQN_DISC, numrec);
-			residual_len -= entry_size;
-		}
+		nvmet_format_discovery_entry(hdr, r,
+				NVME_DISC_SUBSYS_NAME,
+				r->disc_addr.traddr,
+				NVME_NQN_DISC, numrec);
 		numrec++;
 	}
 
@@ -190,8 +212,8 @@ static void nvmet_execute_get_disc_log_page(struct nvmet_req *req)
 
 	up_read(&nvmet_config_sem);
 
-	status = nvmet_copy_to_sgl(req, 0, hdr, data_len);
-	kfree(hdr);
+	status = nvmet_copy_to_sgl(req, 0, buffer + offset, data_len);
+	kfree(buffer);
 out:
 	nvmet_req_complete(req, status);
 }
diff --git a/drivers/nvme/target/io-cmd-file.c b/drivers/nvme/target/io-cmd-file.c
index 3e43212d3c1c..bc6ebb51b0bf 100644
--- a/drivers/nvme/target/io-cmd-file.c
+++ b/drivers/nvme/target/io-cmd-file.c
@@ -75,11 +75,11 @@ err:
 	return ret;
 }
 
-static void nvmet_file_init_bvec(struct bio_vec *bv, struct sg_page_iter *iter)
+static void nvmet_file_init_bvec(struct bio_vec *bv, struct scatterlist *sg)
 {
-	bv->bv_page = sg_page_iter_page(iter);
-	bv->bv_offset = iter->sg->offset;
-	bv->bv_len = PAGE_SIZE - iter->sg->offset;
+	bv->bv_page = sg_page(sg);
+	bv->bv_offset = sg->offset;
+	bv->bv_len = sg->length;
 }
 
 static ssize_t nvmet_file_submit_bvec(struct nvmet_req *req, loff_t pos,
@@ -128,14 +128,14 @@ static void nvmet_file_io_done(struct kiocb *iocb, long ret, long ret2)
 
 static bool nvmet_file_execute_io(struct nvmet_req *req, int ki_flags)
 {
-	ssize_t nr_bvec = DIV_ROUND_UP(req->data_len, PAGE_SIZE);
-	struct sg_page_iter sg_pg_iter;
+	ssize_t nr_bvec = req->sg_cnt;
 	unsigned long bv_cnt = 0;
 	bool is_sync = false;
 	size_t len = 0, total_len = 0;
 	ssize_t ret = 0;
 	loff_t pos;
-
+	int i;
+	struct scatterlist *sg;
 
 	if (req->f.mpool_alloc && nr_bvec > NVMET_MAX_MPOOL_BVEC)
 		is_sync = true;
@@ -147,8 +147,8 @@ static bool nvmet_file_execute_io(struct nvmet_req *req, int ki_flags)
 	}
 
 	memset(&req->f.iocb, 0, sizeof(struct kiocb));
-	for_each_sg_page(req->sg, &sg_pg_iter, req->sg_cnt, 0) {
-		nvmet_file_init_bvec(&req->f.bvec[bv_cnt], &sg_pg_iter);
+	for_each_sg(req->sg, sg, req->sg_cnt, i) {
+		nvmet_file_init_bvec(&req->f.bvec[bv_cnt], sg);
 		len += req->f.bvec[bv_cnt].bv_len;
 		total_len += req->f.bvec[bv_cnt].bv_len;
 		bv_cnt++;
@@ -225,7 +225,7 @@ static void nvmet_file_submit_buffered_io(struct nvmet_req *req)
 
 static void nvmet_file_execute_rw(struct nvmet_req *req)
 {
-	ssize_t nr_bvec = DIV_ROUND_UP(req->data_len, PAGE_SIZE);
+	ssize_t nr_bvec = req->sg_cnt;
 
 	if (!req->sg_cnt || !nr_bvec) {
 		nvmet_req_complete(req, 0);
diff --git a/drivers/nvme/target/nvmet.h b/drivers/nvme/target/nvmet.h
index 51e49efd7849..1653d19b187f 100644
--- a/drivers/nvme/target/nvmet.h
+++ b/drivers/nvme/target/nvmet.h
@@ -428,6 +428,7 @@ u16 nvmet_copy_from_sgl(struct nvmet_req *req, off_t off, void *buf,
 u16 nvmet_zero_sgl(struct nvmet_req *req, off_t off, size_t len);
 
 u32 nvmet_get_log_page_len(struct nvme_command *cmd);
+u64 nvmet_get_log_page_offset(struct nvme_command *cmd);
 
 extern struct list_head *nvmet_ports;
 void nvmet_port_disc_changed(struct nvmet_port *port,
diff --git a/drivers/of/of_net.c b/drivers/of/of_net.c
index 810ab0fbcccb..d820f3edd431 100644
--- a/drivers/of/of_net.c
+++ b/drivers/of/of_net.c
@@ -7,7 +7,6 @@
  */
 #include <linux/etherdevice.h>
 #include <linux/kernel.h>
-#include <linux/nvmem-consumer.h>
 #include <linux/of_net.h>
 #include <linux/phy.h>
 #include <linux/export.h>
diff --git a/drivers/opp/core.c b/drivers/opp/core.c
index 0420f7e8ad5b..0e7703fe733f 100644
--- a/drivers/opp/core.c
+++ b/drivers/opp/core.c
@@ -526,6 +526,60 @@ struct dev_pm_opp *dev_pm_opp_find_freq_floor(struct device *dev,
 }
 EXPORT_SYMBOL_GPL(dev_pm_opp_find_freq_floor);
 
+/**
+ * dev_pm_opp_find_freq_ceil_by_volt() - Find OPP with highest frequency for
+ *					 target voltage.
+ * @dev:	Device for which we do this operation.
+ * @u_volt:	Target voltage.
+ *
+ * Search for OPP with highest (ceil) frequency and has voltage <= u_volt.
+ *
+ * Return: matching *opp, else returns ERR_PTR in case of error which should be
+ * handled using IS_ERR.
+ *
+ * Error return values can be:
+ * EINVAL:	bad parameters
+ *
+ * The callers are required to call dev_pm_opp_put() for the returned OPP after
+ * use.
+ */
+struct dev_pm_opp *dev_pm_opp_find_freq_ceil_by_volt(struct device *dev,
+						     unsigned long u_volt)
+{
+	struct opp_table *opp_table;
+	struct dev_pm_opp *temp_opp, *opp = ERR_PTR(-ERANGE);
+
+	if (!dev || !u_volt) {
+		dev_err(dev, "%s: Invalid argument volt=%lu\n", __func__,
+			u_volt);
+		return ERR_PTR(-EINVAL);
+	}
+
+	opp_table = _find_opp_table(dev);
+	if (IS_ERR(opp_table))
+		return ERR_CAST(opp_table);
+
+	mutex_lock(&opp_table->lock);
+
+	list_for_each_entry(temp_opp, &opp_table->opp_list, node) {
+		if (temp_opp->available) {
+			if (temp_opp->supplies[0].u_volt > u_volt)
+				break;
+			opp = temp_opp;
+		}
+	}
+
+	/* Increment the reference count of OPP */
+	if (!IS_ERR(opp))
+		dev_pm_opp_get(opp);
+
+	mutex_unlock(&opp_table->lock);
+	dev_pm_opp_put_opp_table(opp_table);
+
+	return opp;
+}
+EXPORT_SYMBOL_GPL(dev_pm_opp_find_freq_ceil_by_volt);
+
 static int _set_opp_voltage(struct device *dev, struct regulator *reg,
 			    struct dev_pm_opp_supply *supply)
 {
diff --git a/drivers/parisc/iosapic.c b/drivers/parisc/iosapic.c
index 1be571c20062..6bad04cbb1d3 100644
--- a/drivers/parisc/iosapic.c
+++ b/drivers/parisc/iosapic.c
@@ -157,8 +157,12 @@
 #define DBG_IRT(x...)
 #endif
 
+#ifdef CONFIG_64BIT
+#define COMPARE_IRTE_ADDR(irte, hpa)	((irte)->dest_iosapic_addr == (hpa))
+#else
 #define COMPARE_IRTE_ADDR(irte, hpa)	\
-		((irte)->dest_iosapic_addr == F_EXTEND(hpa))
+		((irte)->dest_iosapic_addr == ((hpa) | 0xffffffff00000000ULL))
+#endif
 
 #define IOSAPIC_REG_SELECT              0x00
 #define IOSAPIC_REG_WINDOW              0x10
diff --git a/drivers/parport/daisy.c b/drivers/parport/daisy.c
index 56dd83a45e55..5484a46dafda 100644
--- a/drivers/parport/daisy.c
+++ b/drivers/parport/daisy.c
@@ -213,12 +213,10 @@ void parport_daisy_fini(struct parport *port)
 struct pardevice *parport_open(int devnum, const char *name)
 {
 	struct daisydev *p = topology;
-	struct pardev_cb par_cb;
 	struct parport *port;
 	struct pardevice *dev;
 	int daisy;
 
-	memset(&par_cb, 0, sizeof(par_cb));
 	spin_lock(&topology_lock);
 	while (p && p->devnum != devnum)
 		p = p->next;
@@ -232,7 +230,7 @@ struct pardevice *parport_open(int devnum, const char *name)
 	port = parport_get_port(p->port);
 	spin_unlock(&topology_lock);
 
-	dev = parport_register_dev_model(port, name, &par_cb, devnum);
+	dev = parport_register_device(port, name, NULL, NULL, NULL, 0, NULL);
 	parport_put_port(port);
 	if (!dev)
 		return NULL;
@@ -482,31 +480,3 @@ static int assign_addrs(struct parport *port)
 	kfree(deviceid);
 	return detected;
 }
-
-static int daisy_drv_probe(struct pardevice *par_dev)
-{
-	struct device_driver *drv = par_dev->dev.driver;
-
-	if (strcmp(drv->name, "daisy_drv"))
-		return -ENODEV;
-	if (strcmp(par_dev->name, daisy_dev_name))
-		return -ENODEV;
-
-	return 0;
-}
-
-static struct parport_driver daisy_driver = {
-	.name = "daisy_drv",
-	.probe = daisy_drv_probe,
-	.devmodel = true,
-};
-
-int daisy_drv_init(void)
-{
-	return parport_register_driver(&daisy_driver);
-}
-
-void daisy_drv_exit(void)
-{
-	parport_unregister_driver(&daisy_driver);
-}
diff --git a/drivers/parport/probe.c b/drivers/parport/probe.c
index e5e6a463a941..e035174ba205 100644
--- a/drivers/parport/probe.c
+++ b/drivers/parport/probe.c
@@ -257,7 +257,7 @@ static ssize_t parport_read_device_id (struct parport *port, char *buffer,
 ssize_t parport_device_id (int devnum, char *buffer, size_t count)
 {
 	ssize_t retval = -ENXIO;
-	struct pardevice *dev = parport_open(devnum, daisy_dev_name);
+	struct pardevice *dev = parport_open (devnum, "Device ID probe");
 	if (!dev)
 		return -ENXIO;
 
diff --git a/drivers/parport/share.c b/drivers/parport/share.c
index 0171b8dbcdcd..5dc53d420ca8 100644
--- a/drivers/parport/share.c
+++ b/drivers/parport/share.c
@@ -137,19 +137,11 @@ static struct bus_type parport_bus_type = {
 
 int parport_bus_init(void)
 {
-	int retval;
-
-	retval = bus_register(&parport_bus_type);
-	if (retval)
-		return retval;
-	daisy_drv_init();
-
-	return 0;
+	return bus_register(&parport_bus_type);
 }
 
 void parport_bus_exit(void)
 {
-	daisy_drv_exit();
 	bus_unregister(&parport_bus_type);
 }
 
diff --git a/drivers/pci/controller/Kconfig b/drivers/pci/controller/Kconfig
index 6012f3059acd..011c57cae4b0 100644
--- a/drivers/pci/controller/Kconfig
+++ b/drivers/pci/controller/Kconfig
@@ -267,6 +267,7 @@ config PCIE_TANGO_SMP8759
 
 config VMD
 	depends on PCI_MSI && X86_64 && SRCU
+	select X86_DEV_DMA_OPS
 	tristate "Intel Volume Management Device Driver"
 	---help---
 	  Adds support for the Intel Volume Management Device (VMD). VMD is a
diff --git a/drivers/pci/controller/vmd.c b/drivers/pci/controller/vmd.c
index cf6816b55b5e..999a5509e57e 100644
--- a/drivers/pci/controller/vmd.c
+++ b/drivers/pci/controller/vmd.c
@@ -95,10 +95,8 @@ struct vmd_dev {
 	struct irq_domain	*irq_domain;
 	struct pci_bus		*bus;
 
-#ifdef CONFIG_X86_DEV_DMA_OPS
 	struct dma_map_ops	dma_ops;
 	struct dma_domain	dma_domain;
-#endif
 };
 
 static inline struct vmd_dev *vmd_from_bus(struct pci_bus *bus)
@@ -293,7 +291,6 @@ static struct msi_domain_info vmd_msi_domain_info = {
 	.chip		= &vmd_msi_controller,
 };
 
-#ifdef CONFIG_X86_DEV_DMA_OPS
 /*
  * VMD replaces the requester ID with its own.  DMA mappings for devices in a
  * VMD domain need to be mapped for the VMD, not the device requiring
@@ -438,10 +435,6 @@ static void vmd_setup_dma_ops(struct vmd_dev *vmd)
 	add_dma_domain(domain);
 }
 #undef ASSIGN_VMD_DMA_OPS
-#else
-static void vmd_teardown_dma_ops(struct vmd_dev *vmd) {}
-static void vmd_setup_dma_ops(struct vmd_dev *vmd) {}
-#endif
 
 static char __iomem *vmd_cfg_addr(struct vmd_dev *vmd, struct pci_bus *bus,
 				  unsigned int devfn, int reg, int len)
diff --git a/drivers/pci/hotplug/pciehp_ctrl.c b/drivers/pci/hotplug/pciehp_ctrl.c
index 3f3df4c29f6e..905282a8ddaa 100644
--- a/drivers/pci/hotplug/pciehp_ctrl.c
+++ b/drivers/pci/hotplug/pciehp_ctrl.c
@@ -115,6 +115,10 @@ static void remove_board(struct controller *ctrl, bool safe_removal)
 		 * removed from the slot/adapter.
 		 */
 		msleep(1000);
+
+		/* Ignore link or presence changes caused by power off */
+		atomic_and(~(PCI_EXP_SLTSTA_DLLSC | PCI_EXP_SLTSTA_PDC),
+			   &ctrl->pending_events);
 	}
 
 	/* turn off Green LED */
diff --git a/drivers/pci/pci.c b/drivers/pci/pci.c
index 7c1b362f599a..766f5779db92 100644
--- a/drivers/pci/pci.c
+++ b/drivers/pci/pci.c
@@ -6262,8 +6262,7 @@ static int __init pci_setup(char *str)
 			} else if (!strncmp(str, "pcie_scan_all", 13)) {
 				pci_add_flags(PCI_SCAN_ALL_PCIE_DEVS);
 			} else if (!strncmp(str, "disable_acs_redir=", 18)) {
-				disable_acs_redir_param =
-					kstrdup(str + 18, GFP_KERNEL);
+				disable_acs_redir_param = str + 18;
 			} else {
 				printk(KERN_ERR "PCI: Unknown option `%s'\n",
 						str);
@@ -6274,3 +6273,19 @@ static int __init pci_setup(char *str)
 	return 0;
 }
 early_param("pci", pci_setup);
+
+/*
+ * 'disable_acs_redir_param' is initialized in pci_setup(), above, to point
+ * to data in the __initdata section which will be freed after the init
+ * sequence is complete. We can't allocate memory in pci_setup() because some
+ * architectures do not have any memory allocation service available during
+ * an early_param() call. So we allocate memory and copy the variable here
+ * before the init section is freed.
+ */
+static int __init pci_realloc_setup_params(void)
+{
+	disable_acs_redir_param = kstrdup(disable_acs_redir_param, GFP_KERNEL);
+
+	return 0;
+}
+pure_initcall(pci_realloc_setup_params);
diff --git a/drivers/pci/pci.h b/drivers/pci/pci.h
index 224d88634115..d994839a3e24 100644
--- a/drivers/pci/pci.h
+++ b/drivers/pci/pci.h
@@ -273,6 +273,7 @@ enum pcie_link_width pcie_get_width_cap(struct pci_dev *dev);
 u32 pcie_bandwidth_capable(struct pci_dev *dev, enum pci_bus_speed *speed,
 			   enum pcie_link_width *width);
 void __pcie_print_link_status(struct pci_dev *dev, bool verbose);
+void pcie_report_downtraining(struct pci_dev *dev);
 
 /* Single Root I/O Virtualization */
 struct pci_sriov {
diff --git a/drivers/pci/pcie/Kconfig b/drivers/pci/pcie/Kconfig
index 5cbdbca904ac..362eb8cfa53b 100644
--- a/drivers/pci/pcie/Kconfig
+++ b/drivers/pci/pcie/Kconfig
@@ -142,3 +142,11 @@ config PCIE_PTM
 
 	  This is only useful if you have devices that support PTM, but it
 	  is safe to enable even if you don't.
+
+config PCIE_BW
+	bool "PCI Express Bandwidth Change Notification"
+	depends on PCIEPORTBUS
+	help
+	  This enables PCI Express Bandwidth Change Notification.  If
+	  you know link width or rate changes occur only to correct
+	  unreliable links, you may answer Y.
diff --git a/drivers/pci/pcie/Makefile b/drivers/pci/pcie/Makefile
index f1d7bc1e5efa..efb9d2e71e9e 100644
--- a/drivers/pci/pcie/Makefile
+++ b/drivers/pci/pcie/Makefile
@@ -3,7 +3,6 @@
 # Makefile for PCI Express features and port driver
 
 pcieportdrv-y			:= portdrv_core.o portdrv_pci.o err.o
-pcieportdrv-y			+= bw_notification.o
 
 obj-$(CONFIG_PCIEPORTBUS)	+= pcieportdrv.o
 
@@ -13,3 +12,4 @@ obj-$(CONFIG_PCIEAER_INJECT)	+= aer_inject.o
 obj-$(CONFIG_PCIE_PME)		+= pme.o
 obj-$(CONFIG_PCIE_DPC)		+= dpc.o
 obj-$(CONFIG_PCIE_PTM)		+= ptm.o
+obj-$(CONFIG_PCIE_BW)		+= bw_notification.o
diff --git a/drivers/pci/pcie/bw_notification.c b/drivers/pci/pcie/bw_notification.c
index d2eae3b7cc0f..4fa9e3523ee1 100644
--- a/drivers/pci/pcie/bw_notification.c
+++ b/drivers/pci/pcie/bw_notification.c
@@ -30,6 +30,8 @@ static void pcie_enable_link_bandwidth_notification(struct pci_dev *dev)
 {
 	u16 lnk_ctl;
 
+	pcie_capability_write_word(dev, PCI_EXP_LNKSTA, PCI_EXP_LNKSTA_LBMS);
+
 	pcie_capability_read_word(dev, PCI_EXP_LNKCTL, &lnk_ctl);
 	lnk_ctl |= PCI_EXP_LNKCTL_LBMIE;
 	pcie_capability_write_word(dev, PCI_EXP_LNKCTL, lnk_ctl);
@@ -44,11 +46,10 @@ static void pcie_disable_link_bandwidth_notification(struct pci_dev *dev)
 	pcie_capability_write_word(dev, PCI_EXP_LNKCTL, lnk_ctl);
 }
 
-static irqreturn_t pcie_bw_notification_handler(int irq, void *context)
+static irqreturn_t pcie_bw_notification_irq(int irq, void *context)
 {
 	struct pcie_device *srv = context;
 	struct pci_dev *port = srv->port;
-	struct pci_dev *dev;
 	u16 link_status, events;
 	int ret;
 
@@ -58,17 +59,26 @@ static irqreturn_t pcie_bw_notification_handler(int irq, void *context)
 	if (ret != PCIBIOS_SUCCESSFUL || !events)
 		return IRQ_NONE;
 
+	pcie_capability_write_word(port, PCI_EXP_LNKSTA, events);
+	pcie_update_link_speed(port->subordinate, link_status);
+	return IRQ_WAKE_THREAD;
+}
+
+static irqreturn_t pcie_bw_notification_handler(int irq, void *context)
+{
+	struct pcie_device *srv = context;
+	struct pci_dev *port = srv->port;
+	struct pci_dev *dev;
+
 	/*
 	 * Print status from downstream devices, not this root port or
 	 * downstream switch port.
 	 */
 	down_read(&pci_bus_sem);
 	list_for_each_entry(dev, &port->subordinate->devices, bus_list)
-		__pcie_print_link_status(dev, false);
+		pcie_report_downtraining(dev);
 	up_read(&pci_bus_sem);
 
-	pcie_update_link_speed(port->subordinate, link_status);
-	pcie_capability_write_word(port, PCI_EXP_LNKSTA, events);
 	return IRQ_HANDLED;
 }
 
@@ -80,7 +90,8 @@ static int pcie_bandwidth_notification_probe(struct pcie_device *srv)
 	if (!pcie_link_bandwidth_notification_supported(srv->port))
 		return -ENODEV;
 
-	ret = request_threaded_irq(srv->irq, NULL, pcie_bw_notification_handler,
+	ret = request_threaded_irq(srv->irq, pcie_bw_notification_irq,
+				   pcie_bw_notification_handler,
 				   IRQF_SHARED, "PCIe BW notif", srv);
 	if (ret)
 		return ret;
diff --git a/drivers/pci/pcie/portdrv.h b/drivers/pci/pcie/portdrv.h
index 1d50dc58ac40..944827a8c7d3 100644
--- a/drivers/pci/pcie/portdrv.h
+++ b/drivers/pci/pcie/portdrv.h
@@ -49,7 +49,11 @@ int pcie_dpc_init(void);
 static inline int pcie_dpc_init(void) { return 0; }
 #endif
 
+#ifdef CONFIG_PCIE_BW
 int pcie_bandwidth_notification_init(void);
+#else
+static inline int pcie_bandwidth_notification_init(void) { return 0; }
+#endif
 
 /* Port Type */
 #define PCIE_ANY_PORT			(~0)
diff --git a/drivers/pci/pcie/portdrv_core.c b/drivers/pci/pcie/portdrv_core.c
index 7d04f9d087a6..1b330129089f 100644
--- a/drivers/pci/pcie/portdrv_core.c
+++ b/drivers/pci/pcie/portdrv_core.c
@@ -55,7 +55,8 @@ static int pcie_message_numbers(struct pci_dev *dev, int mask,
 	 * 7.8.2, 7.10.10, 7.31.2.
 	 */
 
-	if (mask & (PCIE_PORT_SERVICE_PME | PCIE_PORT_SERVICE_HP)) {
+	if (mask & (PCIE_PORT_SERVICE_PME | PCIE_PORT_SERVICE_HP |
+		    PCIE_PORT_SERVICE_BWNOTIF)) {
 		pcie_capability_read_word(dev, PCI_EXP_FLAGS, &reg16);
 		*pme = (reg16 & PCI_EXP_FLAGS_IRQ) >> 9;
 		nvec = *pme + 1;
diff --git a/drivers/pci/probe.c b/drivers/pci/probe.c
index 2ec0df04e0dc..7e12d0163863 100644
--- a/drivers/pci/probe.c
+++ b/drivers/pci/probe.c
@@ -2388,7 +2388,7 @@ static struct pci_dev *pci_scan_device(struct pci_bus *bus, int devfn)
 	return dev;
 }
 
-static void pcie_report_downtraining(struct pci_dev *dev)
+void pcie_report_downtraining(struct pci_dev *dev)
 {
 	if (!pci_is_pcie(dev))
 		return;
diff --git a/drivers/pci/quirks.c b/drivers/pci/quirks.c
index a59ad09ce911..a077f67fe1da 100644
--- a/drivers/pci/quirks.c
+++ b/drivers/pci/quirks.c
@@ -3877,6 +3877,8 @@ DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_MARVELL_EXT, 0x9128,
 /* https://bugzilla.kernel.org/show_bug.cgi?id=42679#c14 */
 DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_MARVELL_EXT, 0x9130,
 			 quirk_dma_func1_alias);
+DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_MARVELL_EXT, 0x9170,
+			 quirk_dma_func1_alias);
 /* https://bugzilla.kernel.org/show_bug.cgi?id=42679#c47 + c57 */
 DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_MARVELL_EXT, 0x9172,
 			 quirk_dma_func1_alias);
diff --git a/drivers/perf/Kconfig b/drivers/perf/Kconfig
index af9bc178495d..a94e586a58b2 100644
--- a/drivers/perf/Kconfig
+++ b/drivers/perf/Kconfig
@@ -52,6 +52,15 @@ config ARM_PMU_ACPI
 	depends on ARM_PMU && ACPI
 	def_bool y
 
+config ARM_SMMU_V3_PMU
+	 tristate "ARM SMMUv3 Performance Monitors Extension"
+	 depends on ARM64 && ACPI && ARM_SMMU_V3
+	   help
+	   Provides support for the ARM SMMUv3 Performance Monitor Counter
+	   Groups (PMCG), which provide monitoring of transactions passing
+	   through the SMMU and allow the resulting information to be filtered
+	   based on the Stream ID of the corresponding master.
+
 config ARM_DSU_PMU
 	tristate "ARM DynamIQ Shared Unit (DSU) PMU"
 	depends on ARM64
diff --git a/drivers/perf/Makefile b/drivers/perf/Makefile
index 909f27fd9db3..30489941f3d6 100644
--- a/drivers/perf/Makefile
+++ b/drivers/perf/Makefile
@@ -4,6 +4,7 @@ obj-$(CONFIG_ARM_CCN) += arm-ccn.o
 obj-$(CONFIG_ARM_DSU_PMU) += arm_dsu_pmu.o
 obj-$(CONFIG_ARM_PMU) += arm_pmu.o arm_pmu_platform.o
 obj-$(CONFIG_ARM_PMU_ACPI) += arm_pmu_acpi.o
+obj-$(CONFIG_ARM_SMMU_V3_PMU) += arm_smmuv3_pmu.o
 obj-$(CONFIG_HISI_PMU) += hisilicon/
 obj-$(CONFIG_QCOM_L2_PMU)	+= qcom_l2_pmu.o
 obj-$(CONFIG_QCOM_L3_PMU) += qcom_l3_pmu.o
diff --git a/drivers/perf/arm-cci.c b/drivers/perf/arm-cci.c
index bfd03e023308..8f8606b9bc9e 100644
--- a/drivers/perf/arm-cci.c
+++ b/drivers/perf/arm-cci.c
@@ -1684,21 +1684,24 @@ static int cci_pmu_probe(struct platform_device *pdev)
 	raw_spin_lock_init(&cci_pmu->hw_events.pmu_lock);
 	mutex_init(&cci_pmu->reserve_mutex);
 	atomic_set(&cci_pmu->active_events, 0);
-	cci_pmu->cpu = get_cpu();
-
-	ret = cci_pmu_init(cci_pmu, pdev);
-	if (ret) {
-		put_cpu();
-		return ret;
-	}
 
+	cci_pmu->cpu = raw_smp_processor_id();
+	g_cci_pmu = cci_pmu;
 	cpuhp_setup_state_nocalls(CPUHP_AP_PERF_ARM_CCI_ONLINE,
 				  "perf/arm/cci:online", NULL,
 				  cci_pmu_offline_cpu);
-	put_cpu();
-	g_cci_pmu = cci_pmu;
+
+	ret = cci_pmu_init(cci_pmu, pdev);
+	if (ret)
+		goto error_pmu_init;
+
 	pr_info("ARM %s PMU driver probed", cci_pmu->model->name);
 	return 0;
+
+error_pmu_init:
+	cpuhp_remove_state(CPUHP_AP_PERF_ARM_CCI_ONLINE);
+	g_cci_pmu = NULL;
+	return ret;
 }
 
 static int cci_pmu_remove(struct platform_device *pdev)
diff --git a/drivers/perf/arm-ccn.c b/drivers/perf/arm-ccn.c
index 2ae76026e947..0bb52d9bdcf7 100644
--- a/drivers/perf/arm-ccn.c
+++ b/drivers/perf/arm-ccn.c
@@ -167,7 +167,7 @@ struct arm_ccn_dt {
 
 	struct hrtimer hrtimer;
 
-	cpumask_t cpu;
+	unsigned int cpu;
 	struct hlist_node node;
 
 	struct pmu pmu;
@@ -559,7 +559,7 @@ static ssize_t arm_ccn_pmu_cpumask_show(struct device *dev,
 {
 	struct arm_ccn *ccn = pmu_to_arm_ccn(dev_get_drvdata(dev));
 
-	return cpumap_print_to_pagebuf(true, buf, &ccn->dt.cpu);
+	return cpumap_print_to_pagebuf(true, buf, cpumask_of(ccn->dt.cpu));
 }
 
 static struct device_attribute arm_ccn_pmu_cpumask_attr =
@@ -759,7 +759,7 @@ static int arm_ccn_pmu_event_init(struct perf_event *event)
 	 * mitigate this, we enforce CPU assignment to one, selected
 	 * processor (the one described in the "cpumask" attribute).
 	 */
-	event->cpu = cpumask_first(&ccn->dt.cpu);
+	event->cpu = ccn->dt.cpu;
 
 	node_xp = CCN_CONFIG_NODE(event->attr.config);
 	type = CCN_CONFIG_TYPE(event->attr.config);
@@ -1215,15 +1215,15 @@ static int arm_ccn_pmu_offline_cpu(unsigned int cpu, struct hlist_node *node)
 	struct arm_ccn *ccn = container_of(dt, struct arm_ccn, dt);
 	unsigned int target;
 
-	if (!cpumask_test_and_clear_cpu(cpu, &dt->cpu))
+	if (cpu != dt->cpu)
 		return 0;
 	target = cpumask_any_but(cpu_online_mask, cpu);
 	if (target >= nr_cpu_ids)
 		return 0;
 	perf_pmu_migrate_context(&dt->pmu, cpu, target);
-	cpumask_set_cpu(target, &dt->cpu);
+	dt->cpu = target;
 	if (ccn->irq)
-		WARN_ON(irq_set_affinity_hint(ccn->irq, &dt->cpu) != 0);
+		WARN_ON(irq_set_affinity_hint(ccn->irq, cpumask_of(dt->cpu)));
 	return 0;
 }
 
@@ -1299,29 +1299,30 @@ static int arm_ccn_pmu_init(struct arm_ccn *ccn)
 	}
 
 	/* Pick one CPU which we will use to collect data from CCN... */
-	cpumask_set_cpu(get_cpu(), &ccn->dt.cpu);
+	ccn->dt.cpu = raw_smp_processor_id();
 
 	/* Also make sure that the overflow interrupt is handled by this CPU */
 	if (ccn->irq) {
-		err = irq_set_affinity_hint(ccn->irq, &ccn->dt.cpu);
+		err = irq_set_affinity_hint(ccn->irq, cpumask_of(ccn->dt.cpu));
 		if (err) {
 			dev_err(ccn->dev, "Failed to set interrupt affinity!\n");
 			goto error_set_affinity;
 		}
 	}
 
+	cpuhp_state_add_instance_nocalls(CPUHP_AP_PERF_ARM_CCN_ONLINE,
+					 &ccn->dt.node);
+
 	err = perf_pmu_register(&ccn->dt.pmu, name, -1);
 	if (err)
 		goto error_pmu_register;
 
-	cpuhp_state_add_instance_nocalls(CPUHP_AP_PERF_ARM_CCN_ONLINE,
-					 &ccn->dt.node);
-	put_cpu();
 	return 0;
 
 error_pmu_register:
+	cpuhp_state_remove_instance_nocalls(CPUHP_AP_PERF_ARM_CCN_ONLINE,
+					    &ccn->dt.node);
 error_set_affinity:
-	put_cpu();
 error_choose_name:
 	ida_simple_remove(&arm_ccn_pmu_ida, ccn->dt.id);
 	for (i = 0; i < ccn->num_xps; i++)
diff --git a/drivers/perf/arm_smmuv3_pmu.c b/drivers/perf/arm_smmuv3_pmu.c
new file mode 100644
index 000000000000..da71c741cb46
--- /dev/null
+++ b/drivers/perf/arm_smmuv3_pmu.c
@@ -0,0 +1,865 @@
+// SPDX-License-Identifier: GPL-2.0
+
+/*
+ * This driver adds support for perf events to use the Performance
+ * Monitor Counter Groups (PMCG) associated with an SMMUv3 node
+ * to monitor that node.
+ *
+ * SMMUv3 PMCG devices are named as smmuv3_pmcg_<phys_addr_page> where
+ * <phys_addr_page> is the physical page address of the SMMU PMCG wrapped
+ * to 4K boundary. For example, the PMCG at 0xff88840000 is named
+ * smmuv3_pmcg_ff88840
+ *
+ * Filtering by stream id is done by specifying filtering parameters
+ * with the event. options are:
+ *   filter_enable    - 0 = no filtering, 1 = filtering enabled
+ *   filter_span      - 0 = exact match, 1 = pattern match
+ *   filter_stream_id - pattern to filter against
+ *
+ * To match a partial StreamID where the X most-significant bits must match
+ * but the Y least-significant bits might differ, STREAMID is programmed
+ * with a value that contains:
+ *  STREAMID[Y - 1] == 0.
+ *  STREAMID[Y - 2:0] == 1 (where Y > 1).
+ * The remainder of implemented bits of STREAMID (X bits, from bit Y upwards)
+ * contain a value to match from the corresponding bits of event StreamID.
+ *
+ * Example: perf stat -e smmuv3_pmcg_ff88840/transaction,filter_enable=1,
+ *                    filter_span=1,filter_stream_id=0x42/ -a netperf
+ * Applies filter pattern 0x42 to transaction events, which means events
+ * matching stream ids 0x42 and 0x43 are counted. Further filtering
+ * information is available in the SMMU documentation.
+ *
+ * SMMU events are not attributable to a CPU, so task mode and sampling
+ * are not supported.
+ */
+
+#include <linux/acpi.h>
+#include <linux/acpi_iort.h>
+#include <linux/bitfield.h>
+#include <linux/bitops.h>
+#include <linux/cpuhotplug.h>
+#include <linux/cpumask.h>
+#include <linux/device.h>
+#include <linux/errno.h>
+#include <linux/interrupt.h>
+#include <linux/irq.h>
+#include <linux/kernel.h>
+#include <linux/list.h>
+#include <linux/msi.h>
+#include <linux/perf_event.h>
+#include <linux/platform_device.h>
+#include <linux/smp.h>
+#include <linux/sysfs.h>
+#include <linux/types.h>
+
+#define SMMU_PMCG_EVCNTR0               0x0
+#define SMMU_PMCG_EVCNTR(n, stride)     (SMMU_PMCG_EVCNTR0 + (n) * (stride))
+#define SMMU_PMCG_EVTYPER0              0x400
+#define SMMU_PMCG_EVTYPER(n)            (SMMU_PMCG_EVTYPER0 + (n) * 4)
+#define SMMU_PMCG_SID_SPAN_SHIFT        29
+#define SMMU_PMCG_SMR0                  0xA00
+#define SMMU_PMCG_SMR(n)                (SMMU_PMCG_SMR0 + (n) * 4)
+#define SMMU_PMCG_CNTENSET0             0xC00
+#define SMMU_PMCG_CNTENCLR0             0xC20
+#define SMMU_PMCG_INTENSET0             0xC40
+#define SMMU_PMCG_INTENCLR0             0xC60
+#define SMMU_PMCG_OVSCLR0               0xC80
+#define SMMU_PMCG_OVSSET0               0xCC0
+#define SMMU_PMCG_CFGR                  0xE00
+#define SMMU_PMCG_CFGR_SID_FILTER_TYPE  BIT(23)
+#define SMMU_PMCG_CFGR_MSI              BIT(21)
+#define SMMU_PMCG_CFGR_RELOC_CTRS       BIT(20)
+#define SMMU_PMCG_CFGR_SIZE             GENMASK(13, 8)
+#define SMMU_PMCG_CFGR_NCTR             GENMASK(5, 0)
+#define SMMU_PMCG_CR                    0xE04
+#define SMMU_PMCG_CR_ENABLE             BIT(0)
+#define SMMU_PMCG_CEID0                 0xE20
+#define SMMU_PMCG_CEID1                 0xE28
+#define SMMU_PMCG_IRQ_CTRL              0xE50
+#define SMMU_PMCG_IRQ_CTRL_IRQEN        BIT(0)
+#define SMMU_PMCG_IRQ_CFG0              0xE58
+#define SMMU_PMCG_IRQ_CFG1              0xE60
+#define SMMU_PMCG_IRQ_CFG2              0xE64
+
+/* MSI config fields */
+#define MSI_CFG0_ADDR_MASK              GENMASK_ULL(51, 2)
+#define MSI_CFG2_MEMATTR_DEVICE_nGnRE   0x1
+
+#define SMMU_PMCG_DEFAULT_FILTER_SPAN   1
+#define SMMU_PMCG_DEFAULT_FILTER_SID    GENMASK(31, 0)
+
+#define SMMU_PMCG_MAX_COUNTERS          64
+#define SMMU_PMCG_ARCH_MAX_EVENTS       128
+
+#define SMMU_PMCG_PA_SHIFT              12
+
+#define SMMU_PMCG_EVCNTR_RDONLY         BIT(0)
+
+static int cpuhp_state_num;
+
+struct smmu_pmu {
+	struct hlist_node node;
+	struct perf_event *events[SMMU_PMCG_MAX_COUNTERS];
+	DECLARE_BITMAP(used_counters, SMMU_PMCG_MAX_COUNTERS);
+	DECLARE_BITMAP(supported_events, SMMU_PMCG_ARCH_MAX_EVENTS);
+	unsigned int irq;
+	unsigned int on_cpu;
+	struct pmu pmu;
+	unsigned int num_counters;
+	struct device *dev;
+	void __iomem *reg_base;
+	void __iomem *reloc_base;
+	u64 counter_mask;
+	u32 options;
+	bool global_filter;
+	u32 global_filter_span;
+	u32 global_filter_sid;
+};
+
+#define to_smmu_pmu(p) (container_of(p, struct smmu_pmu, pmu))
+
+#define SMMU_PMU_EVENT_ATTR_EXTRACTOR(_name, _config, _start, _end)        \
+	static inline u32 get_##_name(struct perf_event *event)            \
+	{                                                                  \
+		return FIELD_GET(GENMASK_ULL(_end, _start),                \
+				 event->attr._config);                     \
+	}                                                                  \
+
+SMMU_PMU_EVENT_ATTR_EXTRACTOR(event, config, 0, 15);
+SMMU_PMU_EVENT_ATTR_EXTRACTOR(filter_stream_id, config1, 0, 31);
+SMMU_PMU_EVENT_ATTR_EXTRACTOR(filter_span, config1, 32, 32);
+SMMU_PMU_EVENT_ATTR_EXTRACTOR(filter_enable, config1, 33, 33);
+
+static inline void smmu_pmu_enable(struct pmu *pmu)
+{
+	struct smmu_pmu *smmu_pmu = to_smmu_pmu(pmu);
+
+	writel(SMMU_PMCG_IRQ_CTRL_IRQEN,
+	       smmu_pmu->reg_base + SMMU_PMCG_IRQ_CTRL);
+	writel(SMMU_PMCG_CR_ENABLE, smmu_pmu->reg_base + SMMU_PMCG_CR);
+}
+
+static inline void smmu_pmu_disable(struct pmu *pmu)
+{
+	struct smmu_pmu *smmu_pmu = to_smmu_pmu(pmu);
+
+	writel(0, smmu_pmu->reg_base + SMMU_PMCG_CR);
+	writel(0, smmu_pmu->reg_base + SMMU_PMCG_IRQ_CTRL);
+}
+
+static inline void smmu_pmu_counter_set_value(struct smmu_pmu *smmu_pmu,
+					      u32 idx, u64 value)
+{
+	if (smmu_pmu->counter_mask & BIT(32))
+		writeq(value, smmu_pmu->reloc_base + SMMU_PMCG_EVCNTR(idx, 8));
+	else
+		writel(value, smmu_pmu->reloc_base + SMMU_PMCG_EVCNTR(idx, 4));
+}
+
+static inline u64 smmu_pmu_counter_get_value(struct smmu_pmu *smmu_pmu, u32 idx)
+{
+	u64 value;
+
+	if (smmu_pmu->counter_mask & BIT(32))
+		value = readq(smmu_pmu->reloc_base + SMMU_PMCG_EVCNTR(idx, 8));
+	else
+		value = readl(smmu_pmu->reloc_base + SMMU_PMCG_EVCNTR(idx, 4));
+
+	return value;
+}
+
+static inline void smmu_pmu_counter_enable(struct smmu_pmu *smmu_pmu, u32 idx)
+{
+	writeq(BIT(idx), smmu_pmu->reg_base + SMMU_PMCG_CNTENSET0);
+}
+
+static inline void smmu_pmu_counter_disable(struct smmu_pmu *smmu_pmu, u32 idx)
+{
+	writeq(BIT(idx), smmu_pmu->reg_base + SMMU_PMCG_CNTENCLR0);
+}
+
+static inline void smmu_pmu_interrupt_enable(struct smmu_pmu *smmu_pmu, u32 idx)
+{
+	writeq(BIT(idx), smmu_pmu->reg_base + SMMU_PMCG_INTENSET0);
+}
+
+static inline void smmu_pmu_interrupt_disable(struct smmu_pmu *smmu_pmu,
+					      u32 idx)
+{
+	writeq(BIT(idx), smmu_pmu->reg_base + SMMU_PMCG_INTENCLR0);
+}
+
+static inline void smmu_pmu_set_evtyper(struct smmu_pmu *smmu_pmu, u32 idx,
+					u32 val)
+{
+	writel(val, smmu_pmu->reg_base + SMMU_PMCG_EVTYPER(idx));
+}
+
+static inline void smmu_pmu_set_smr(struct smmu_pmu *smmu_pmu, u32 idx, u32 val)
+{
+	writel(val, smmu_pmu->reg_base + SMMU_PMCG_SMR(idx));
+}
+
+static void smmu_pmu_event_update(struct perf_event *event)
+{
+	struct hw_perf_event *hwc = &event->hw;
+	struct smmu_pmu *smmu_pmu = to_smmu_pmu(event->pmu);
+	u64 delta, prev, now;
+	u32 idx = hwc->idx;
+
+	do {
+		prev = local64_read(&hwc->prev_count);
+		now = smmu_pmu_counter_get_value(smmu_pmu, idx);
+	} while (local64_cmpxchg(&hwc->prev_count, prev, now) != prev);
+
+	/* handle overflow. */
+	delta = now - prev;
+	delta &= smmu_pmu->counter_mask;
+
+	local64_add(delta, &event->count);
+}
+
+static void smmu_pmu_set_period(struct smmu_pmu *smmu_pmu,
+				struct hw_perf_event *hwc)
+{
+	u32 idx = hwc->idx;
+	u64 new;
+
+	if (smmu_pmu->options & SMMU_PMCG_EVCNTR_RDONLY) {
+		/*
+		 * On platforms that require this quirk, if the counter starts
+		 * at < half_counter value and wraps, the current logic of
+		 * handling the overflow may not work. It is expected that,
+		 * those platforms will have full 64 counter bits implemented
+		 * so that such a possibility is remote(eg: HiSilicon HIP08).
+		 */
+		new = smmu_pmu_counter_get_value(smmu_pmu, idx);
+	} else {
+		/*
+		 * We limit the max period to half the max counter value
+		 * of the counter size, so that even in the case of extreme
+		 * interrupt latency the counter will (hopefully) not wrap
+		 * past its initial value.
+		 */
+		new = smmu_pmu->counter_mask >> 1;
+		smmu_pmu_counter_set_value(smmu_pmu, idx, new);
+	}
+
+	local64_set(&hwc->prev_count, new);
+}
+
+static void smmu_pmu_set_event_filter(struct perf_event *event,
+				      int idx, u32 span, u32 sid)
+{
+	struct smmu_pmu *smmu_pmu = to_smmu_pmu(event->pmu);
+	u32 evtyper;
+
+	evtyper = get_event(event) | span << SMMU_PMCG_SID_SPAN_SHIFT;
+	smmu_pmu_set_evtyper(smmu_pmu, idx, evtyper);
+	smmu_pmu_set_smr(smmu_pmu, idx, sid);
+}
+
+static int smmu_pmu_apply_event_filter(struct smmu_pmu *smmu_pmu,
+				       struct perf_event *event, int idx)
+{
+	u32 span, sid;
+	unsigned int num_ctrs = smmu_pmu->num_counters;
+	bool filter_en = !!get_filter_enable(event);
+
+	span = filter_en ? get_filter_span(event) :
+			   SMMU_PMCG_DEFAULT_FILTER_SPAN;
+	sid = filter_en ? get_filter_stream_id(event) :
+			   SMMU_PMCG_DEFAULT_FILTER_SID;
+
+	/* Support individual filter settings */
+	if (!smmu_pmu->global_filter) {
+		smmu_pmu_set_event_filter(event, idx, span, sid);
+		return 0;
+	}
+
+	/* Requested settings same as current global settings*/
+	if (span == smmu_pmu->global_filter_span &&
+	    sid == smmu_pmu->global_filter_sid)
+		return 0;
+
+	if (!bitmap_empty(smmu_pmu->used_counters, num_ctrs))
+		return -EAGAIN;
+
+	smmu_pmu_set_event_filter(event, 0, span, sid);
+	smmu_pmu->global_filter_span = span;
+	smmu_pmu->global_filter_sid = sid;
+	return 0;
+}
+
+static int smmu_pmu_get_event_idx(struct smmu_pmu *smmu_pmu,
+				  struct perf_event *event)
+{
+	int idx, err;
+	unsigned int num_ctrs = smmu_pmu->num_counters;
+
+	idx = find_first_zero_bit(smmu_pmu->used_counters, num_ctrs);
+	if (idx == num_ctrs)
+		/* The counters are all in use. */
+		return -EAGAIN;
+
+	err = smmu_pmu_apply_event_filter(smmu_pmu, event, idx);
+	if (err)
+		return err;
+
+	set_bit(idx, smmu_pmu->used_counters);
+
+	return idx;
+}
+
+/*
+ * Implementation of abstract pmu functionality required by
+ * the core perf events code.
+ */
+
+static int smmu_pmu_event_init(struct perf_event *event)
+{
+	struct hw_perf_event *hwc = &event->hw;
+	struct smmu_pmu *smmu_pmu = to_smmu_pmu(event->pmu);
+	struct device *dev = smmu_pmu->dev;
+	struct perf_event *sibling;
+	u16 event_id;
+
+	if (event->attr.type != event->pmu->type)
+		return -ENOENT;
+
+	if (hwc->sample_period) {
+		dev_dbg(dev, "Sampling not supported\n");
+		return -EOPNOTSUPP;
+	}
+
+	if (event->cpu < 0) {
+		dev_dbg(dev, "Per-task mode not supported\n");
+		return -EOPNOTSUPP;
+	}
+
+	/* Verify specified event is supported on this PMU */
+	event_id = get_event(event);
+	if (event_id < SMMU_PMCG_ARCH_MAX_EVENTS &&
+	    (!test_bit(event_id, smmu_pmu->supported_events))) {
+		dev_dbg(dev, "Invalid event %d for this PMU\n", event_id);
+		return -EINVAL;
+	}
+
+	/* Don't allow groups with mixed PMUs, except for s/w events */
+	if (event->group_leader->pmu != event->pmu &&
+	    !is_software_event(event->group_leader)) {
+		dev_dbg(dev, "Can't create mixed PMU group\n");
+		return -EINVAL;
+	}
+
+	for_each_sibling_event(sibling, event->group_leader) {
+		if (sibling->pmu != event->pmu &&
+		    !is_software_event(sibling)) {
+			dev_dbg(dev, "Can't create mixed PMU group\n");
+			return -EINVAL;
+		}
+	}
+
+	hwc->idx = -1;
+
+	/*
+	 * Ensure all events are on the same cpu so all events are in the
+	 * same cpu context, to avoid races on pmu_enable etc.
+	 */
+	event->cpu = smmu_pmu->on_cpu;
+
+	return 0;
+}
+
+static void smmu_pmu_event_start(struct perf_event *event, int flags)
+{
+	struct smmu_pmu *smmu_pmu = to_smmu_pmu(event->pmu);
+	struct hw_perf_event *hwc = &event->hw;
+	int idx = hwc->idx;
+
+	hwc->state = 0;
+
+	smmu_pmu_set_period(smmu_pmu, hwc);
+
+	smmu_pmu_counter_enable(smmu_pmu, idx);
+}
+
+static void smmu_pmu_event_stop(struct perf_event *event, int flags)
+{
+	struct smmu_pmu *smmu_pmu = to_smmu_pmu(event->pmu);
+	struct hw_perf_event *hwc = &event->hw;
+	int idx = hwc->idx;
+
+	if (hwc->state & PERF_HES_STOPPED)
+		return;
+
+	smmu_pmu_counter_disable(smmu_pmu, idx);
+	/* As the counter gets updated on _start, ignore PERF_EF_UPDATE */
+	smmu_pmu_event_update(event);
+	hwc->state |= PERF_HES_STOPPED | PERF_HES_UPTODATE;
+}
+
+static int smmu_pmu_event_add(struct perf_event *event, int flags)
+{
+	struct hw_perf_event *hwc = &event->hw;
+	int idx;
+	struct smmu_pmu *smmu_pmu = to_smmu_pmu(event->pmu);
+
+	idx = smmu_pmu_get_event_idx(smmu_pmu, event);
+	if (idx < 0)
+		return idx;
+
+	hwc->idx = idx;
+	hwc->state = PERF_HES_STOPPED | PERF_HES_UPTODATE;
+	smmu_pmu->events[idx] = event;
+	local64_set(&hwc->prev_count, 0);
+
+	smmu_pmu_interrupt_enable(smmu_pmu, idx);
+
+	if (flags & PERF_EF_START)
+		smmu_pmu_event_start(event, flags);
+
+	/* Propagate changes to the userspace mapping. */
+	perf_event_update_userpage(event);
+
+	return 0;
+}
+
+static void smmu_pmu_event_del(struct perf_event *event, int flags)
+{
+	struct hw_perf_event *hwc = &event->hw;
+	struct smmu_pmu *smmu_pmu = to_smmu_pmu(event->pmu);
+	int idx = hwc->idx;
+
+	smmu_pmu_event_stop(event, flags | PERF_EF_UPDATE);
+	smmu_pmu_interrupt_disable(smmu_pmu, idx);
+	smmu_pmu->events[idx] = NULL;
+	clear_bit(idx, smmu_pmu->used_counters);
+
+	perf_event_update_userpage(event);
+}
+
+static void smmu_pmu_event_read(struct perf_event *event)
+{
+	smmu_pmu_event_update(event);
+}
+
+/* cpumask */
+
+static ssize_t smmu_pmu_cpumask_show(struct device *dev,
+				     struct device_attribute *attr,
+				     char *buf)
+{
+	struct smmu_pmu *smmu_pmu = to_smmu_pmu(dev_get_drvdata(dev));
+
+	return cpumap_print_to_pagebuf(true, buf, cpumask_of(smmu_pmu->on_cpu));
+}
+
+static struct device_attribute smmu_pmu_cpumask_attr =
+		__ATTR(cpumask, 0444, smmu_pmu_cpumask_show, NULL);
+
+static struct attribute *smmu_pmu_cpumask_attrs[] = {
+	&smmu_pmu_cpumask_attr.attr,
+	NULL
+};
+
+static struct attribute_group smmu_pmu_cpumask_group = {
+	.attrs = smmu_pmu_cpumask_attrs,
+};
+
+/* Events */
+
+static ssize_t smmu_pmu_event_show(struct device *dev,
+				   struct device_attribute *attr, char *page)
+{
+	struct perf_pmu_events_attr *pmu_attr;
+
+	pmu_attr = container_of(attr, struct perf_pmu_events_attr, attr);
+
+	return sprintf(page, "event=0x%02llx\n", pmu_attr->id);
+}
+
+#define SMMU_EVENT_ATTR(name, config) \
+	PMU_EVENT_ATTR(name, smmu_event_attr_##name, \
+		       config, smmu_pmu_event_show)
+SMMU_EVENT_ATTR(cycles, 0);
+SMMU_EVENT_ATTR(transaction, 1);
+SMMU_EVENT_ATTR(tlb_miss, 2);
+SMMU_EVENT_ATTR(config_cache_miss, 3);
+SMMU_EVENT_ATTR(trans_table_walk_access, 4);
+SMMU_EVENT_ATTR(config_struct_access, 5);
+SMMU_EVENT_ATTR(pcie_ats_trans_rq, 6);
+SMMU_EVENT_ATTR(pcie_ats_trans_passed, 7);
+
+static struct attribute *smmu_pmu_events[] = {
+	&smmu_event_attr_cycles.attr.attr,
+	&smmu_event_attr_transaction.attr.attr,
+	&smmu_event_attr_tlb_miss.attr.attr,
+	&smmu_event_attr_config_cache_miss.attr.attr,
+	&smmu_event_attr_trans_table_walk_access.attr.attr,
+	&smmu_event_attr_config_struct_access.attr.attr,
+	&smmu_event_attr_pcie_ats_trans_rq.attr.attr,
+	&smmu_event_attr_pcie_ats_trans_passed.attr.attr,
+	NULL
+};
+
+static umode_t smmu_pmu_event_is_visible(struct kobject *kobj,
+					 struct attribute *attr, int unused)
+{
+	struct device *dev = kobj_to_dev(kobj);
+	struct smmu_pmu *smmu_pmu = to_smmu_pmu(dev_get_drvdata(dev));
+	struct perf_pmu_events_attr *pmu_attr;
+
+	pmu_attr = container_of(attr, struct perf_pmu_events_attr, attr.attr);
+
+	if (test_bit(pmu_attr->id, smmu_pmu->supported_events))
+		return attr->mode;
+
+	return 0;
+}
+
+static struct attribute_group smmu_pmu_events_group = {
+	.name = "events",
+	.attrs = smmu_pmu_events,
+	.is_visible = smmu_pmu_event_is_visible,
+};
+
+/* Formats */
+PMU_FORMAT_ATTR(event,		   "config:0-15");
+PMU_FORMAT_ATTR(filter_stream_id,  "config1:0-31");
+PMU_FORMAT_ATTR(filter_span,	   "config1:32");
+PMU_FORMAT_ATTR(filter_enable,	   "config1:33");
+
+static struct attribute *smmu_pmu_formats[] = {
+	&format_attr_event.attr,
+	&format_attr_filter_stream_id.attr,
+	&format_attr_filter_span.attr,
+	&format_attr_filter_enable.attr,
+	NULL
+};
+
+static struct attribute_group smmu_pmu_format_group = {
+	.name = "format",
+	.attrs = smmu_pmu_formats,
+};
+
+static const struct attribute_group *smmu_pmu_attr_grps[] = {
+	&smmu_pmu_cpumask_group,
+	&smmu_pmu_events_group,
+	&smmu_pmu_format_group,
+	NULL
+};
+
+/*
+ * Generic device handlers
+ */
+
+static int smmu_pmu_offline_cpu(unsigned int cpu, struct hlist_node *node)
+{
+	struct smmu_pmu *smmu_pmu;
+	unsigned int target;
+
+	smmu_pmu = hlist_entry_safe(node, struct smmu_pmu, node);
+	if (cpu != smmu_pmu->on_cpu)
+		return 0;
+
+	target = cpumask_any_but(cpu_online_mask, cpu);
+	if (target >= nr_cpu_ids)
+		return 0;
+
+	perf_pmu_migrate_context(&smmu_pmu->pmu, cpu, target);
+	smmu_pmu->on_cpu = target;
+	WARN_ON(irq_set_affinity_hint(smmu_pmu->irq, cpumask_of(target)));
+
+	return 0;
+}
+
+static irqreturn_t smmu_pmu_handle_irq(int irq_num, void *data)
+{
+	struct smmu_pmu *smmu_pmu = data;
+	u64 ovsr;
+	unsigned int idx;
+
+	ovsr = readq(smmu_pmu->reloc_base + SMMU_PMCG_OVSSET0);
+	if (!ovsr)
+		return IRQ_NONE;
+
+	writeq(ovsr, smmu_pmu->reloc_base + SMMU_PMCG_OVSCLR0);
+
+	for_each_set_bit(idx, (unsigned long *)&ovsr, smmu_pmu->num_counters) {
+		struct perf_event *event = smmu_pmu->events[idx];
+		struct hw_perf_event *hwc;
+
+		if (WARN_ON_ONCE(!event))
+			continue;
+
+		smmu_pmu_event_update(event);
+		hwc = &event->hw;
+
+		smmu_pmu_set_period(smmu_pmu, hwc);
+	}
+
+	return IRQ_HANDLED;
+}
+
+static void smmu_pmu_free_msis(void *data)
+{
+	struct device *dev = data;
+
+	platform_msi_domain_free_irqs(dev);
+}
+
+static void smmu_pmu_write_msi_msg(struct msi_desc *desc, struct msi_msg *msg)
+{
+	phys_addr_t doorbell;
+	struct device *dev = msi_desc_to_dev(desc);
+	struct smmu_pmu *pmu = dev_get_drvdata(dev);
+
+	doorbell = (((u64)msg->address_hi) << 32) | msg->address_lo;
+	doorbell &= MSI_CFG0_ADDR_MASK;
+
+	writeq_relaxed(doorbell, pmu->reg_base + SMMU_PMCG_IRQ_CFG0);
+	writel_relaxed(msg->data, pmu->reg_base + SMMU_PMCG_IRQ_CFG1);
+	writel_relaxed(MSI_CFG2_MEMATTR_DEVICE_nGnRE,
+		       pmu->reg_base + SMMU_PMCG_IRQ_CFG2);
+}
+
+static void smmu_pmu_setup_msi(struct smmu_pmu *pmu)
+{
+	struct msi_desc *desc;
+	struct device *dev = pmu->dev;
+	int ret;
+
+	/* Clear MSI address reg */
+	writeq_relaxed(0, pmu->reg_base + SMMU_PMCG_IRQ_CFG0);
+
+	/* MSI supported or not */
+	if (!(readl(pmu->reg_base + SMMU_PMCG_CFGR) & SMMU_PMCG_CFGR_MSI))
+		return;
+
+	ret = platform_msi_domain_alloc_irqs(dev, 1, smmu_pmu_write_msi_msg);
+	if (ret) {
+		dev_warn(dev, "failed to allocate MSIs\n");
+		return;
+	}
+
+	desc = first_msi_entry(dev);
+	if (desc)
+		pmu->irq = desc->irq;
+
+	/* Add callback to free MSIs on teardown */
+	devm_add_action(dev, smmu_pmu_free_msis, dev);
+}
+
+static int smmu_pmu_setup_irq(struct smmu_pmu *pmu)
+{
+	unsigned long flags = IRQF_NOBALANCING | IRQF_SHARED | IRQF_NO_THREAD;
+	int irq, ret = -ENXIO;
+
+	smmu_pmu_setup_msi(pmu);
+
+	irq = pmu->irq;
+	if (irq)
+		ret = devm_request_irq(pmu->dev, irq, smmu_pmu_handle_irq,
+				       flags, "smmuv3-pmu", pmu);
+	return ret;
+}
+
+static void smmu_pmu_reset(struct smmu_pmu *smmu_pmu)
+{
+	u64 counter_present_mask = GENMASK_ULL(smmu_pmu->num_counters - 1, 0);
+
+	smmu_pmu_disable(&smmu_pmu->pmu);
+
+	/* Disable counter and interrupt */
+	writeq_relaxed(counter_present_mask,
+		       smmu_pmu->reg_base + SMMU_PMCG_CNTENCLR0);
+	writeq_relaxed(counter_present_mask,
+		       smmu_pmu->reg_base + SMMU_PMCG_INTENCLR0);
+	writeq_relaxed(counter_present_mask,
+		       smmu_pmu->reloc_base + SMMU_PMCG_OVSCLR0);
+}
+
+static void smmu_pmu_get_acpi_options(struct smmu_pmu *smmu_pmu)
+{
+	u32 model;
+
+	model = *(u32 *)dev_get_platdata(smmu_pmu->dev);
+
+	switch (model) {
+	case IORT_SMMU_V3_PMCG_HISI_HIP08:
+		/* HiSilicon Erratum 162001800 */
+		smmu_pmu->options |= SMMU_PMCG_EVCNTR_RDONLY;
+		break;
+	}
+
+	dev_notice(smmu_pmu->dev, "option mask 0x%x\n", smmu_pmu->options);
+}
+
+static int smmu_pmu_probe(struct platform_device *pdev)
+{
+	struct smmu_pmu *smmu_pmu;
+	struct resource *res_0, *res_1;
+	u32 cfgr, reg_size;
+	u64 ceid_64[2];
+	int irq, err;
+	char *name;
+	struct device *dev = &pdev->dev;
+
+	smmu_pmu = devm_kzalloc(dev, sizeof(*smmu_pmu), GFP_KERNEL);
+	if (!smmu_pmu)
+		return -ENOMEM;
+
+	smmu_pmu->dev = dev;
+	platform_set_drvdata(pdev, smmu_pmu);
+
+	smmu_pmu->pmu = (struct pmu) {
+		.task_ctx_nr    = perf_invalid_context,
+		.pmu_enable	= smmu_pmu_enable,
+		.pmu_disable	= smmu_pmu_disable,
+		.event_init	= smmu_pmu_event_init,
+		.add		= smmu_pmu_event_add,
+		.del		= smmu_pmu_event_del,
+		.start		= smmu_pmu_event_start,
+		.stop		= smmu_pmu_event_stop,
+		.read		= smmu_pmu_event_read,
+		.attr_groups	= smmu_pmu_attr_grps,
+		.capabilities	= PERF_PMU_CAP_NO_EXCLUDE,
+	};
+
+	res_0 = platform_get_resource(pdev, IORESOURCE_MEM, 0);
+	smmu_pmu->reg_base = devm_ioremap_resource(dev, res_0);
+	if (IS_ERR(smmu_pmu->reg_base))
+		return PTR_ERR(smmu_pmu->reg_base);
+
+	cfgr = readl_relaxed(smmu_pmu->reg_base + SMMU_PMCG_CFGR);
+
+	/* Determine if page 1 is present */
+	if (cfgr & SMMU_PMCG_CFGR_RELOC_CTRS) {
+		res_1 = platform_get_resource(pdev, IORESOURCE_MEM, 1);
+		smmu_pmu->reloc_base = devm_ioremap_resource(dev, res_1);
+		if (IS_ERR(smmu_pmu->reloc_base))
+			return PTR_ERR(smmu_pmu->reloc_base);
+	} else {
+		smmu_pmu->reloc_base = smmu_pmu->reg_base;
+	}
+
+	irq = platform_get_irq(pdev, 0);
+	if (irq > 0)
+		smmu_pmu->irq = irq;
+
+	ceid_64[0] = readq_relaxed(smmu_pmu->reg_base + SMMU_PMCG_CEID0);
+	ceid_64[1] = readq_relaxed(smmu_pmu->reg_base + SMMU_PMCG_CEID1);
+	bitmap_from_arr32(smmu_pmu->supported_events, (u32 *)ceid_64,
+			  SMMU_PMCG_ARCH_MAX_EVENTS);
+
+	smmu_pmu->num_counters = FIELD_GET(SMMU_PMCG_CFGR_NCTR, cfgr) + 1;
+
+	smmu_pmu->global_filter = !!(cfgr & SMMU_PMCG_CFGR_SID_FILTER_TYPE);
+
+	reg_size = FIELD_GET(SMMU_PMCG_CFGR_SIZE, cfgr);
+	smmu_pmu->counter_mask = GENMASK_ULL(reg_size, 0);
+
+	smmu_pmu_reset(smmu_pmu);
+
+	err = smmu_pmu_setup_irq(smmu_pmu);
+	if (err) {
+		dev_err(dev, "Setup irq failed, PMU @%pa\n", &res_0->start);
+		return err;
+	}
+
+	name = devm_kasprintf(&pdev->dev, GFP_KERNEL, "smmuv3_pmcg_%llx",
+			      (res_0->start) >> SMMU_PMCG_PA_SHIFT);
+	if (!name) {
+		dev_err(dev, "Create name failed, PMU @%pa\n", &res_0->start);
+		return -EINVAL;
+	}
+
+	smmu_pmu_get_acpi_options(smmu_pmu);
+
+	/* Pick one CPU to be the preferred one to use */
+	smmu_pmu->on_cpu = raw_smp_processor_id();
+	WARN_ON(irq_set_affinity_hint(smmu_pmu->irq,
+				      cpumask_of(smmu_pmu->on_cpu)));
+
+	err = cpuhp_state_add_instance_nocalls(cpuhp_state_num,
+					       &smmu_pmu->node);
+	if (err) {
+		dev_err(dev, "Error %d registering hotplug, PMU @%pa\n",
+			err, &res_0->start);
+		goto out_cpuhp_err;
+	}
+
+	err = perf_pmu_register(&smmu_pmu->pmu, name, -1);
+	if (err) {
+		dev_err(dev, "Error %d registering PMU @%pa\n",
+			err, &res_0->start);
+		goto out_unregister;
+	}
+
+	dev_info(dev, "Registered PMU @ %pa using %d counters with %s filter settings\n",
+		 &res_0->start, smmu_pmu->num_counters,
+		 smmu_pmu->global_filter ? "Global(Counter0)" :
+		 "Individual");
+
+	return 0;
+
+out_unregister:
+	cpuhp_state_remove_instance_nocalls(cpuhp_state_num, &smmu_pmu->node);
+out_cpuhp_err:
+	put_cpu();
+	return err;
+}
+
+static int smmu_pmu_remove(struct platform_device *pdev)
+{
+	struct smmu_pmu *smmu_pmu = platform_get_drvdata(pdev);
+
+	perf_pmu_unregister(&smmu_pmu->pmu);
+	cpuhp_state_remove_instance_nocalls(cpuhp_state_num, &smmu_pmu->node);
+
+	return 0;
+}
+
+static void smmu_pmu_shutdown(struct platform_device *pdev)
+{
+	struct smmu_pmu *smmu_pmu = platform_get_drvdata(pdev);
+
+	smmu_pmu_disable(&smmu_pmu->pmu);
+}
+
+static struct platform_driver smmu_pmu_driver = {
+	.driver = {
+		.name = "arm-smmu-v3-pmcg",
+	},
+	.probe = smmu_pmu_probe,
+	.remove = smmu_pmu_remove,
+	.shutdown = smmu_pmu_shutdown,
+};
+
+static int __init arm_smmu_pmu_init(void)
+{
+	cpuhp_state_num = cpuhp_setup_state_multi(CPUHP_AP_ONLINE_DYN,
+						  "perf/arm/pmcg:online",
+						  NULL,
+						  smmu_pmu_offline_cpu);
+	if (cpuhp_state_num < 0)
+		return cpuhp_state_num;
+
+	return platform_driver_register(&smmu_pmu_driver);
+}
+module_init(arm_smmu_pmu_init);
+
+static void __exit arm_smmu_pmu_exit(void)
+{
+	platform_driver_unregister(&smmu_pmu_driver);
+	cpuhp_remove_multi_state(cpuhp_state_num);
+}
+
+module_exit(arm_smmu_pmu_exit);
+
+MODULE_DESCRIPTION("PMU driver for ARM SMMUv3 Performance Monitors Extension");
+MODULE_AUTHOR("Neil Leeder <nleeder@codeaurora.org>");
+MODULE_AUTHOR("Shameer Kolothum <shameerali.kolothum.thodi@huawei.com>");
+MODULE_LICENSE("GPL v2");
diff --git a/drivers/phy/allwinner/phy-sun4i-usb.c b/drivers/phy/allwinner/phy-sun4i-usb.c
index 5163097b43df..4bbd9ede38c8 100644
--- a/drivers/phy/allwinner/phy-sun4i-usb.c
+++ b/drivers/phy/allwinner/phy-sun4i-usb.c
@@ -485,8 +485,11 @@ static int sun4i_usb_phy_set_mode(struct phy *_phy,
 	struct sun4i_usb_phy_data *data = to_sun4i_usb_phy_data(phy);
 	int new_mode;
 
-	if (phy->index != 0)
+	if (phy->index != 0) {
+		if (mode == PHY_MODE_USB_HOST)
+			return 0;
 		return -EINVAL;
+	}
 
 	switch (mode) {
 	case PHY_MODE_USB_HOST:
diff --git a/drivers/platform/x86/pmc_atom.c b/drivers/platform/x86/pmc_atom.c
index 8f018b3f3cd4..c7039f52ad51 100644
--- a/drivers/platform/x86/pmc_atom.c
+++ b/drivers/platform/x86/pmc_atom.c
@@ -17,6 +17,7 @@
 
 #include <linux/debugfs.h>
 #include <linux/device.h>
+#include <linux/dmi.h>
 #include <linux/init.h>
 #include <linux/io.h>
 #include <linux/platform_data/x86/clk-pmc-atom.h>
@@ -391,11 +392,27 @@ static int pmc_dbgfs_register(struct pmc_dev *pmc)
 }
 #endif /* CONFIG_DEBUG_FS */
 
+/*
+ * Some systems need one or more of their pmc_plt_clks to be
+ * marked as critical.
+ */
+static const struct dmi_system_id critclk_systems[] = {
+	{
+		.ident = "MPL CEC1x",
+		.matches = {
+			DMI_MATCH(DMI_SYS_VENDOR, "MPL AG"),
+			DMI_MATCH(DMI_PRODUCT_NAME, "CEC10 Family"),
+		},
+	},
+	{ /*sentinel*/ }
+};
+
 static int pmc_setup_clks(struct pci_dev *pdev, void __iomem *pmc_regmap,
 			  const struct pmc_data *pmc_data)
 {
 	struct platform_device *clkdev;
 	struct pmc_clk_data *clk_data;
+	const struct dmi_system_id *d = dmi_first_match(critclk_systems);
 
 	clk_data = kzalloc(sizeof(*clk_data), GFP_KERNEL);
 	if (!clk_data)
@@ -403,6 +420,10 @@ static int pmc_setup_clks(struct pci_dev *pdev, void __iomem *pmc_regmap,
 
 	clk_data->base = pmc_regmap; /* offset is added by client */
 	clk_data->clks = pmc_data->clks;
+	if (d) {
+		clk_data->critical = true;
+		pr_info("%s critclks quirk enabled\n", d->ident);
+	}
 
 	clkdev = platform_device_register_data(&pdev->dev, "clk-pmc-atom",
 					       PLATFORM_DEVID_NONE,
diff --git a/drivers/power/supply/cpcap-battery.c b/drivers/power/supply/cpcap-battery.c
index 08d5037fd052..6887870ba32c 100644
--- a/drivers/power/supply/cpcap-battery.c
+++ b/drivers/power/supply/cpcap-battery.c
@@ -221,6 +221,9 @@ static int cpcap_battery_cc_raw_div(struct cpcap_battery_ddata *ddata,
 	int avg_current;
 	u32 cc_lsb;
 
+	if (!divider)
+		return 0;
+
 	sample &= 0xffffff;		/* 24-bits, unsigned */
 	offset &= 0x7ff;		/* 10-bits, signed */
 
diff --git a/drivers/power/supply/goldfish_battery.c b/drivers/power/supply/goldfish_battery.c
index ad969d9fc981..c2644a9fe80f 100644
--- a/drivers/power/supply/goldfish_battery.c
+++ b/drivers/power/supply/goldfish_battery.c
@@ -1,4 +1,4 @@
-// SPDX-License-Identifier: GPL
+// SPDX-License-Identifier: GPL-2.0
 /*
  * Power supply driver for the goldfish emulator
  *
diff --git a/drivers/power/supply/power_supply_sysfs.c b/drivers/power/supply/power_supply_sysfs.c
index dce24f596160..5358a80d854f 100644
--- a/drivers/power/supply/power_supply_sysfs.c
+++ b/drivers/power/supply/power_supply_sysfs.c
@@ -383,15 +383,11 @@ int power_supply_uevent(struct device *dev, struct kobj_uevent_env *env)
 	char *prop_buf;
 	char *attrname;
 
-	dev_dbg(dev, "uevent\n");
-
 	if (!psy || !psy->desc) {
 		dev_dbg(dev, "No power supply yet\n");
 		return ret;
 	}
 
-	dev_dbg(dev, "POWER_SUPPLY_NAME=%s\n", psy->desc->name);
-
 	ret = add_uevent_var(env, "POWER_SUPPLY_NAME=%s", psy->desc->name);
 	if (ret)
 		return ret;
@@ -427,8 +423,6 @@ int power_supply_uevent(struct device *dev, struct kobj_uevent_env *env)
 			goto out;
 		}
 
-		dev_dbg(dev, "prop %s=%s\n", attrname, prop_buf);
-
 		ret = add_uevent_var(env, "POWER_SUPPLY_%s=%s", attrname, prop_buf);
 		kfree(attrname);
 		if (ret)
diff --git a/drivers/ras/cec.c b/drivers/ras/cec.c
index 2d9ec378a8bc..88e4f3ff0cb8 100644
--- a/drivers/ras/cec.c
+++ b/drivers/ras/cec.c
@@ -286,10 +286,10 @@ int cec_add_elem(u64 pfn)
 	if (!ce_arr.array || ce_arr.disabled)
 		return -ENODEV;
 
-	ca->ces_entered++;
-
 	mutex_lock(&ce_mutex);
 
+	ca->ces_entered++;
+
 	if (ca->n == MAX_ELEMS)
 		WARN_ON(!del_lru_elem_unlocked(ca));
 
diff --git a/drivers/regulator/88pm800.c b/drivers/regulator/88pm800.c
index 89bbd6e8bad1..9fd379732d18 100644
--- a/drivers/regulator/88pm800.c
+++ b/drivers/regulator/88pm800.c
@@ -77,11 +77,6 @@ struct pm800_regulator_info {
 	int max_ua;
 };
 
-struct pm800_regulators {
-	struct pm80x_chip *chip;
-	struct regmap *map;
-};
-
 /*
  * vreg - the buck regs string.
  * ereg - the string for the enable register.
@@ -235,7 +230,6 @@ static int pm800_regulator_probe(struct platform_device *pdev)
 {
 	struct pm80x_chip *chip = dev_get_drvdata(pdev->dev.parent);
 	struct pm80x_platform_data *pdata = dev_get_platdata(pdev->dev.parent);
-	struct pm800_regulators *pm800_data;
 	struct regulator_config config = { };
 	struct regulator_init_data *init_data;
 	int i, ret;
@@ -252,18 +246,8 @@ static int pm800_regulator_probe(struct platform_device *pdev)
 			return -EINVAL;
 	}
 
-	pm800_data = devm_kzalloc(&pdev->dev, sizeof(*pm800_data),
-					GFP_KERNEL);
-	if (!pm800_data)
-		return -ENOMEM;
-
-	pm800_data->map = chip->subchip->regmap_power;
-	pm800_data->chip = chip;
-
-	platform_set_drvdata(pdev, pm800_data);
-
 	config.dev = chip->dev;
-	config.regmap = pm800_data->map;
+	config.regmap = chip->subchip->regmap_power;
 	for (i = 0; i < PM800_ID_RG_MAX; i++) {
 		struct regulator_dev *regulator;
 
diff --git a/drivers/regulator/88pm8607.c b/drivers/regulator/88pm8607.c
index 753a6a1b30c3..35d767aeeb57 100644
--- a/drivers/regulator/88pm8607.c
+++ b/drivers/regulator/88pm8607.c
@@ -235,6 +235,8 @@ static const struct regulator_ops pm8606_preg_ops = {
 {									\
 	.desc	= {							\
 		.name	= "PREG",					\
+		.of_match = of_match_ptr("PREG"),			\
+		.regulators_node = of_match_ptr("regulators"),		\
 		.ops	= &pm8606_preg_ops,				\
 		.type	= REGULATOR_CURRENT,				\
 		.id	= PM8606_ID_PREG,				\
@@ -249,6 +251,8 @@ static const struct regulator_ops pm8606_preg_ops = {
 {									\
 	.desc	= {							\
 		.name	= #vreg,					\
+		.of_match = of_match_ptr(#vreg),			\
+		.regulators_node = of_match_ptr("regulators"),		\
 		.ops	= &pm8607_regulator_ops,			\
 		.type	= REGULATOR_VOLTAGE,				\
 		.id	= PM8607_ID_##vreg,				\
@@ -270,6 +274,8 @@ static const struct regulator_ops pm8606_preg_ops = {
 {									\
 	.desc	= {							\
 		.name	= "LDO" #_id,					\
+		.of_match = of_match_ptr("LDO" #_id),			\
+		.regulators_node = of_match_ptr("regulators"),		\
 		.ops	= &pm8607_regulator_ops,			\
 		.type	= REGULATOR_VOLTAGE,				\
 		.id	= PM8607_ID_LDO##_id,				\
@@ -309,36 +315,6 @@ static struct pm8607_regulator_info pm8606_regulator_info[] = {
 	PM8606_PREG(PREREGULATORB, 5),
 };
 
-#ifdef CONFIG_OF
-static int pm8607_regulator_dt_init(struct platform_device *pdev,
-				    struct pm8607_regulator_info *info,
-				    struct regulator_config *config)
-{
-	struct device_node *nproot, *np;
-	nproot = pdev->dev.parent->of_node;
-	if (!nproot)
-		return -ENODEV;
-	nproot = of_get_child_by_name(nproot, "regulators");
-	if (!nproot) {
-		dev_err(&pdev->dev, "failed to find regulators node\n");
-		return -ENODEV;
-	}
-	for_each_child_of_node(nproot, np) {
-		if (of_node_name_eq(np, info->desc.name)) {
-			config->init_data =
-				of_get_regulator_init_data(&pdev->dev, np,
-							   &info->desc);
-			config->of_node = np;
-			break;
-		}
-	}
-	of_node_put(nproot);
-	return 0;
-}
-#else
-#define pm8607_regulator_dt_init(x, y, z)	(-1)
-#endif
-
 static int pm8607_regulator_probe(struct platform_device *pdev)
 {
 	struct pm860x_chip *chip = dev_get_drvdata(pdev->dev.parent);
@@ -373,12 +349,11 @@ static int pm8607_regulator_probe(struct platform_device *pdev)
 	if ((i == PM8607_ID_BUCK3) && chip->buck3_double)
 		info->slope_double = 1;
 
-	config.dev = &pdev->dev;
+	config.dev = chip->dev;
 	config.driver_data = info;
 
-	if (pm8607_regulator_dt_init(pdev, info, &config))
-		if (pdata)
-			config.init_data = pdata;
+	if (pdata)
+		config.init_data = pdata;
 
 	if (chip->id == CHIP_PM8607)
 		config.regmap = chip->regmap;
diff --git a/drivers/regulator/Kconfig b/drivers/regulator/Kconfig
index b7f249ee5e68..6c37f0df9323 100644
--- a/drivers/regulator/Kconfig
+++ b/drivers/regulator/Kconfig
@@ -223,6 +223,7 @@ config REGULATOR_CPCAP
 config REGULATOR_DA903X
 	tristate "Dialog Semiconductor DA9030/DA9034 regulators"
 	depends on PMIC_DA903X
+	depends on !CC_IS_CLANG # https://bugs.llvm.org/show_bug.cgi?id=38789
 	help
 	  Say y here to support the BUCKs and LDOs regulators found on
 	  Dialog Semiconductor DA9030/DA9034 PMIC.
@@ -839,6 +840,13 @@ config REGULATOR_STM32_VREFBUF
 	  This driver can also be built as a module. If so, the module
 	  will be called stm32-vrefbuf.
 
+config REGULATOR_STM32_PWR
+	bool "STMicroelectronics STM32 PWR"
+	depends on ARCH_STM32 || COMPILE_TEST
+	help
+	  This driver supports internal regulators (1V1, 1V8, 3V3) in the
+	  STMicroelectronics STM32 chips.
+
 config REGULATOR_STPMIC1
 	tristate "STMicroelectronics STPMIC1 PMIC Regulators"
 	depends on MFD_STPMIC1
@@ -1010,7 +1018,8 @@ config REGULATOR_TWL4030
 config REGULATOR_UNIPHIER
 	tristate "UniPhier regulator driver"
 	depends on ARCH_UNIPHIER || COMPILE_TEST
-	depends on OF && MFD_SYSCON
+	depends on OF
+	select REGMAP_MMIO
 	default ARCH_UNIPHIER
 	help
 	  Support for regulators implemented on Socionext UniPhier SoCs.
diff --git a/drivers/regulator/Makefile b/drivers/regulator/Makefile
index 1169f8a27d91..93f53840e8f1 100644
--- a/drivers/regulator/Makefile
+++ b/drivers/regulator/Makefile
@@ -105,6 +105,7 @@ obj-$(CONFIG_REGULATOR_S5M8767) += s5m8767.o
 obj-$(CONFIG_REGULATOR_SC2731) += sc2731-regulator.o
 obj-$(CONFIG_REGULATOR_SKY81452) += sky81452-regulator.o
 obj-$(CONFIG_REGULATOR_STM32_VREFBUF) += stm32-vrefbuf.o
+obj-$(CONFIG_REGULATOR_STM32_PWR) += stm32-pwr.o
 obj-$(CONFIG_REGULATOR_STPMIC1) += stpmic1_regulator.o
 obj-$(CONFIG_REGULATOR_STW481X_VMMC) += stw481x-vmmc.o
 obj-$(CONFIG_REGULATOR_SY8106A) += sy8106a-regulator.o
diff --git a/drivers/regulator/ab3100.c b/drivers/regulator/ab3100.c
index de2644490f0d..438509f55f05 100644
--- a/drivers/regulator/ab3100.c
+++ b/drivers/regulator/ab3100.c
@@ -48,7 +48,6 @@
  * @regreg: regulator register number in the AB3100
  */
 struct ab3100_regulator {
-	struct regulator_dev *rdev;
 	struct device *dev;
 	struct ab3100_platform_data *plfdata;
 	u8 regreg;
@@ -354,14 +353,13 @@ static int ab3100_get_voltage_regulator_external(struct regulator_dev *reg)
 		return 0;
 }
 
-static struct regulator_ops regulator_ops_fixed = {
-	.list_voltage = regulator_list_voltage_linear,
+static const struct regulator_ops regulator_ops_fixed = {
 	.enable      = ab3100_enable_regulator,
 	.disable     = ab3100_disable_regulator,
 	.is_enabled  = ab3100_is_enabled_regulator,
 };
 
-static struct regulator_ops regulator_ops_variable = {
+static const struct regulator_ops regulator_ops_variable = {
 	.enable      = ab3100_enable_regulator,
 	.disable     = ab3100_disable_regulator,
 	.is_enabled  = ab3100_is_enabled_regulator,
@@ -370,7 +368,7 @@ static struct regulator_ops regulator_ops_variable = {
 	.list_voltage = regulator_list_voltage_table,
 };
 
-static struct regulator_ops regulator_ops_variable_sleepable = {
+static const struct regulator_ops regulator_ops_variable_sleepable = {
 	.enable      = ab3100_enable_regulator,
 	.disable     = ab3100_disable_regulator,
 	.is_enabled  = ab3100_is_enabled_regulator,
@@ -386,14 +384,14 @@ static struct regulator_ops regulator_ops_variable_sleepable = {
  * is an on/off switch plain an simple. The external
  * voltage is defined in the board set-up if any.
  */
-static struct regulator_ops regulator_ops_external = {
+static const struct regulator_ops regulator_ops_external = {
 	.enable      = ab3100_enable_regulator,
 	.disable     = ab3100_disable_regulator,
 	.is_enabled  = ab3100_is_enabled_regulator,
 	.get_voltage = ab3100_get_voltage_regulator_external,
 };
 
-static struct regulator_desc
+static const struct regulator_desc
 ab3100_regulator_desc[AB3100_NUM_REGULATORS] = {
 	{
 		.name = "LDO_A",
@@ -402,7 +400,7 @@ ab3100_regulator_desc[AB3100_NUM_REGULATORS] = {
 		.n_voltages = 1,
 		.type = REGULATOR_VOLTAGE,
 		.owner = THIS_MODULE,
-		.min_uV = LDO_A_VOLTAGE,
+		.fixed_uV = LDO_A_VOLTAGE,
 		.enable_time = 200,
 	},
 	{
@@ -412,7 +410,7 @@ ab3100_regulator_desc[AB3100_NUM_REGULATORS] = {
 		.n_voltages = 1,
 		.type = REGULATOR_VOLTAGE,
 		.owner = THIS_MODULE,
-		.min_uV = LDO_C_VOLTAGE,
+		.fixed_uV = LDO_C_VOLTAGE,
 		.enable_time = 200,
 	},
 	{
@@ -422,7 +420,7 @@ ab3100_regulator_desc[AB3100_NUM_REGULATORS] = {
 		.n_voltages = 1,
 		.type = REGULATOR_VOLTAGE,
 		.owner = THIS_MODULE,
-		.min_uV = LDO_D_VOLTAGE,
+		.fixed_uV = LDO_D_VOLTAGE,
 		.enable_time = 200,
 	},
 	{
@@ -500,7 +498,7 @@ static int ab3100_regulator_register(struct platform_device *pdev,
 				     struct device_node *np,
 				     unsigned long id)
 {
-	struct regulator_desc *desc;
+	const struct regulator_desc *desc;
 	struct ab3100_regulator *reg;
 	struct regulator_dev *rdev;
 	struct regulator_config config = { };
@@ -545,8 +543,6 @@ static int ab3100_regulator_register(struct platform_device *pdev,
 		return err;
 	}
 
-	/* Then set a pointer back to the registered regulator */
-	reg->rdev = rdev;
 	return 0;
 }
 
@@ -609,18 +605,6 @@ static const u8 ab3100_reg_initvals[] = {
 	LDO_D_SETTING,
 };
 
-static int ab3100_regulators_remove(struct platform_device *pdev)
-{
-	int i;
-
-	for (i = 0; i < AB3100_NUM_REGULATORS; i++) {
-		struct ab3100_regulator *reg = &ab3100_regulators[i];
-
-		reg->rdev = NULL;
-	}
-	return 0;
-}
-
 static int
 ab3100_regulator_of_probe(struct platform_device *pdev, struct device_node *np)
 {
@@ -647,10 +631,8 @@ ab3100_regulator_of_probe(struct platform_device *pdev, struct device_node *np)
 			pdev, NULL, ab3100_regulator_matches[i].init_data,
 			ab3100_regulator_matches[i].of_node,
 			(unsigned long)ab3100_regulator_matches[i].driver_data);
-		if (err) {
-			ab3100_regulators_remove(pdev);
+		if (err)
 			return err;
-		}
 	}
 
 	return 0;
@@ -705,14 +687,12 @@ static int ab3100_regulators_probe(struct platform_device *pdev)
 
 	/* Register the regulators */
 	for (i = 0; i < AB3100_NUM_REGULATORS; i++) {
-		struct regulator_desc *desc = &ab3100_regulator_desc[i];
+		const struct regulator_desc *desc = &ab3100_regulator_desc[i];
 
 		err = ab3100_regulator_register(pdev, plfdata, NULL, NULL,
 						desc->id);
-		if (err) {
-			ab3100_regulators_remove(pdev);
+		if (err)
 			return err;
-		}
 	}
 
 	return 0;
@@ -723,7 +703,6 @@ static struct platform_driver ab3100_regulators_driver = {
 		.name  = "ab3100-regulators",
 	},
 	.probe = ab3100_regulators_probe,
-	.remove = ab3100_regulators_remove,
 };
 
 static __init int ab3100_regulators_init(void)
diff --git a/drivers/regulator/ab8500-ext.c b/drivers/regulator/ab8500-ext.c
index 2ca00045eb99..95704446d89e 100644
--- a/drivers/regulator/ab8500-ext.c
+++ b/drivers/regulator/ab8500-ext.c
@@ -479,7 +479,6 @@ static struct ab8500_regulator_platform_data ab8500_regulator_plat_data = {
  * struct ab8500_ext_regulator_info - ab8500 regulator information
  * @dev: device pointer
  * @desc: regulator description
- * @rdev: regulator device
  * @cfg: regulator configuration (extension of regulator FW configuration)
  * @update_bank: bank to control on/off
  * @update_reg: register to control on/off
@@ -495,7 +494,6 @@ static struct ab8500_regulator_platform_data ab8500_regulator_plat_data = {
 struct ab8500_ext_regulator_info {
 	struct device *dev;
 	struct regulator_desc desc;
-	struct regulator_dev *rdev;
 	struct ab8500_ext_regulator_cfg *cfg;
 	u8 update_bank;
 	u8 update_reg;
@@ -530,7 +528,7 @@ static int ab8500_ext_regulator_enable(struct regulator_dev *rdev)
 		info->update_bank, info->update_reg,
 		info->update_mask, regval);
 	if (ret < 0) {
-		dev_err(rdev_get_dev(info->rdev),
+		dev_err(rdev_get_dev(rdev),
 			"couldn't set enable bits for regulator\n");
 		return ret;
 	}
@@ -566,7 +564,7 @@ static int ab8500_ext_regulator_disable(struct regulator_dev *rdev)
 		info->update_bank, info->update_reg,
 		info->update_mask, regval);
 	if (ret < 0) {
-		dev_err(rdev_get_dev(info->rdev),
+		dev_err(rdev_get_dev(rdev),
 			"couldn't set disable bits for regulator\n");
 		return ret;
 	}
@@ -720,7 +718,7 @@ static int ab8500_ext_list_voltage(struct regulator_dev *rdev,
 	return -EINVAL;
 }
 
-static struct regulator_ops ab8500_ext_regulator_ops = {
+static const struct regulator_ops ab8500_ext_regulator_ops = {
 	.enable			= ab8500_ext_regulator_enable,
 	.disable		= ab8500_ext_regulator_disable,
 	.is_enabled		= ab8500_ext_regulator_is_enabled,
@@ -735,6 +733,7 @@ static struct ab8500_ext_regulator_info
 	[AB8500_EXT_SUPPLY1] = {
 		.desc = {
 			.name		= "VEXTSUPPLY1",
+			.of_match	= of_match_ptr("ab8500_ext1"),
 			.ops		= &ab8500_ext_regulator_ops,
 			.type		= REGULATOR_VOLTAGE,
 			.id		= AB8500_EXT_SUPPLY1,
@@ -752,6 +751,7 @@ static struct ab8500_ext_regulator_info
 	[AB8500_EXT_SUPPLY2] = {
 		.desc = {
 			.name		= "VEXTSUPPLY2",
+			.of_match	= of_match_ptr("ab8500_ext2"),
 			.ops		= &ab8500_ext_regulator_ops,
 			.type		= REGULATOR_VOLTAGE,
 			.id		= AB8500_EXT_SUPPLY2,
@@ -769,6 +769,7 @@ static struct ab8500_ext_regulator_info
 	[AB8500_EXT_SUPPLY3] = {
 		.desc = {
 			.name		= "VEXTSUPPLY3",
+			.of_match	= of_match_ptr("ab8500_ext3"),
 			.ops		= &ab8500_ext_regulator_ops,
 			.type		= REGULATOR_VOLTAGE,
 			.id		= AB8500_EXT_SUPPLY3,
@@ -785,30 +786,13 @@ static struct ab8500_ext_regulator_info
 	},
 };
 
-static struct of_regulator_match ab8500_ext_regulator_match[] = {
-	{ .name = "ab8500_ext1", .driver_data = (void *) AB8500_EXT_SUPPLY1, },
-	{ .name = "ab8500_ext2", .driver_data = (void *) AB8500_EXT_SUPPLY2, },
-	{ .name = "ab8500_ext3", .driver_data = (void *) AB8500_EXT_SUPPLY3, },
-};
-
 static int ab8500_ext_regulator_probe(struct platform_device *pdev)
 {
 	struct ab8500 *ab8500 = dev_get_drvdata(pdev->dev.parent);
 	struct ab8500_regulator_platform_data *pdata = &ab8500_regulator_plat_data;
-	struct device_node *np = pdev->dev.of_node;
 	struct regulator_config config = { };
-	int i, err;
-
-	if (np) {
-		err = of_regulator_match(&pdev->dev, np,
-					 ab8500_ext_regulator_match,
-					 ARRAY_SIZE(ab8500_ext_regulator_match));
-		if (err < 0) {
-			dev_err(&pdev->dev,
-				"Error parsing regulator init data: %d\n", err);
-			return err;
-		}
-	}
+	struct regulator_dev *rdev;
+	int i;
 
 	if (!ab8500) {
 		dev_err(&pdev->dev, "null mfd parent\n");
@@ -844,23 +828,18 @@ static int ab8500_ext_regulator_probe(struct platform_device *pdev)
 
 		config.dev = &pdev->dev;
 		config.driver_data = info;
-		config.of_node = ab8500_ext_regulator_match[i].of_node;
-		config.init_data = (np) ?
-			ab8500_ext_regulator_match[i].init_data :
-			&pdata->ext_regulator[i];
+		config.init_data = &pdata->ext_regulator[i];
 
 		/* register regulator with framework */
-		info->rdev = devm_regulator_register(&pdev->dev, &info->desc,
-						     &config);
-		if (IS_ERR(info->rdev)) {
-			err = PTR_ERR(info->rdev);
+		rdev = devm_regulator_register(&pdev->dev, &info->desc,
+					       &config);
+		if (IS_ERR(rdev)) {
 			dev_err(&pdev->dev, "failed to register regulator %s\n",
 					info->desc.name);
-			return err;
+			return PTR_ERR(rdev);
 		}
 
-		dev_dbg(rdev_get_dev(info->rdev),
-			"%s-probed\n", info->desc.name);
+		dev_dbg(&pdev->dev, "%s-probed\n", info->desc.name);
 	}
 
 	return 0;
diff --git a/drivers/regulator/ab8500.c b/drivers/regulator/ab8500.c
index 83dba3fbfe0c..3fcb4cbaab02 100644
--- a/drivers/regulator/ab8500.c
+++ b/drivers/regulator/ab8500.c
@@ -44,7 +44,6 @@ struct ab8500_shared_mode {
  * struct ab8500_regulator_info - ab8500 regulator information
  * @dev: device pointer
  * @desc: regulator description
- * @regulator_dev: regulator device
  * @shared_mode: used when mode is shared between two regulators
  * @load_lp_uA: maximum load in idle (low power) mode
  * @update_bank: bank to control on/off
@@ -65,7 +64,6 @@ struct ab8500_shared_mode {
 struct ab8500_regulator_info {
 	struct device		*dev;
 	struct regulator_desc	desc;
-	struct regulator_dev	*regulator;
 	struct ab8500_shared_mode *shared_mode;
 	int load_lp_uA;
 	u8 update_bank;
@@ -510,7 +508,7 @@ static int ab8500_regulator_set_voltage_sel(struct regulator_dev *rdev,
 	return ret;
 }
 
-static struct regulator_ops ab8500_regulator_volt_mode_ops = {
+static const struct regulator_ops ab8500_regulator_volt_mode_ops = {
 	.enable			= ab8500_regulator_enable,
 	.disable		= ab8500_regulator_disable,
 	.is_enabled		= ab8500_regulator_is_enabled,
@@ -522,7 +520,7 @@ static struct regulator_ops ab8500_regulator_volt_mode_ops = {
 	.list_voltage		= regulator_list_voltage_table,
 };
 
-static struct regulator_ops ab8500_regulator_volt_ops = {
+static const struct regulator_ops ab8500_regulator_volt_ops = {
 	.enable		= ab8500_regulator_enable,
 	.disable	= ab8500_regulator_disable,
 	.is_enabled	= ab8500_regulator_is_enabled,
@@ -531,7 +529,7 @@ static struct regulator_ops ab8500_regulator_volt_ops = {
 	.list_voltage	= regulator_list_voltage_table,
 };
 
-static struct regulator_ops ab8500_regulator_mode_ops = {
+static const struct regulator_ops ab8500_regulator_mode_ops = {
 	.enable			= ab8500_regulator_enable,
 	.disable		= ab8500_regulator_disable,
 	.is_enabled		= ab8500_regulator_is_enabled,
@@ -541,14 +539,14 @@ static struct regulator_ops ab8500_regulator_mode_ops = {
 	.list_voltage		= regulator_list_voltage_table,
 };
 
-static struct regulator_ops ab8500_regulator_ops = {
+static const struct regulator_ops ab8500_regulator_ops = {
 	.enable			= ab8500_regulator_enable,
 	.disable		= ab8500_regulator_disable,
 	.is_enabled		= ab8500_regulator_is_enabled,
 	.list_voltage		= regulator_list_voltage_table,
 };
 
-static struct regulator_ops ab8500_regulator_anamic_mode_ops = {
+static const struct regulator_ops ab8500_regulator_anamic_mode_ops = {
 	.enable		= ab8500_regulator_enable,
 	.disable	= ab8500_regulator_disable,
 	.is_enabled	= ab8500_regulator_is_enabled,
@@ -1600,6 +1598,7 @@ static int ab8500_regulator_register(struct platform_device *pdev,
 	struct ab8500 *ab8500 = dev_get_drvdata(pdev->dev.parent);
 	struct ab8500_regulator_info *info = NULL;
 	struct regulator_config config = { };
+	struct regulator_dev *rdev;
 
 	/* assign per-regulator data */
 	info = &abx500_regulator.info[id];
@@ -1621,12 +1620,11 @@ static int ab8500_regulator_register(struct platform_device *pdev,
 	}
 
 	/* register regulator with framework */
-	info->regulator = devm_regulator_register(&pdev->dev, &info->desc,
-						&config);
-	if (IS_ERR(info->regulator)) {
+	rdev = devm_regulator_register(&pdev->dev, &info->desc, &config);
+	if (IS_ERR(rdev)) {
 		dev_err(&pdev->dev, "failed to register regulator %s\n",
 			info->desc.name);
-		return PTR_ERR(info->regulator);
+		return PTR_ERR(rdev);
 	}
 
 	return 0;
diff --git a/drivers/regulator/act8865-regulator.c b/drivers/regulator/act8865-regulator.c
index e0239cf3f56d..19d9ee2dac1f 100644
--- a/drivers/regulator/act8865-regulator.c
+++ b/drivers/regulator/act8865-regulator.c
@@ -226,7 +226,7 @@ static const struct regulator_linear_range act8600_sudcdc_voltage_ranges[] = {
 	REGULATOR_LINEAR_RANGE(41400000, 248, 255, 0),
 };
 
-static struct regulator_ops act8865_ops = {
+static const struct regulator_ops act8865_ops = {
 	.list_voltage		= regulator_list_voltage_linear_range,
 	.map_voltage		= regulator_map_voltage_linear_range,
 	.get_voltage_sel	= regulator_get_voltage_sel_regmap,
@@ -236,7 +236,7 @@ static struct regulator_ops act8865_ops = {
 	.is_enabled		= regulator_is_enabled_regmap,
 };
 
-static struct regulator_ops act8865_ldo_ops = {
+static const struct regulator_ops act8865_ldo_ops = {
 	.enable			= regulator_enable_regmap,
 	.disable		= regulator_disable_regmap,
 	.is_enabled		= regulator_is_enabled_regmap,
@@ -245,6 +245,8 @@ static struct regulator_ops act8865_ldo_ops = {
 #define ACT88xx_REG(_name, _family, _id, _vsel_reg, _supply)		\
 	[_family##_ID_##_id] = {					\
 		.name			= _name,			\
+		.of_match		= of_match_ptr(_name),		\
+		.regulators_node	= of_match_ptr("regulators"),	\
 		.supply_name		= _supply,			\
 		.id			= _family##_ID_##_id,		\
 		.type			= REGULATOR_VOLTAGE,		\
@@ -265,6 +267,8 @@ static const struct regulator_desc act8600_regulators[] = {
 	ACT88xx_REG("DCDC3", ACT8600, DCDC3, VSET, "vp3"),
 	{
 		.name = "SUDCDC_REG4",
+		.of_match = of_match_ptr("SUDCDC_REG4"),
+		.regulators_node = of_match_ptr("regulators"),
 		.id = ACT8600_ID_SUDCDC4,
 		.ops = &act8865_ops,
 		.type = REGULATOR_VOLTAGE,
@@ -283,6 +287,8 @@ static const struct regulator_desc act8600_regulators[] = {
 	ACT88xx_REG("LDO8", ACT8600, LDO8, VSET, "inl"),
 	{
 		.name = "LDO_REG9",
+		.of_match = of_match_ptr("LDO_REG9"),
+		.regulators_node = of_match_ptr("regulators"),
 		.id = ACT8600_ID_LDO9,
 		.ops = &act8865_ldo_ops,
 		.type = REGULATOR_VOLTAGE,
@@ -294,6 +300,8 @@ static const struct regulator_desc act8600_regulators[] = {
 	},
 	{
 		.name = "LDO_REG10",
+		.of_match = of_match_ptr("LDO_REG10"),
+		.regulators_node = of_match_ptr("regulators"),
 		.id = ACT8600_ID_LDO10,
 		.ops = &act8865_ldo_ops,
 		.type = REGULATOR_VOLTAGE,
@@ -348,110 +356,6 @@ static const struct of_device_id act8865_dt_ids[] = {
 	{ }
 };
 MODULE_DEVICE_TABLE(of, act8865_dt_ids);
-
-static struct of_regulator_match act8846_matches[] = {
-	[ACT8846_ID_REG1]	= { .name = "REG1" },
-	[ACT8846_ID_REG2]	= { .name = "REG2" },
-	[ACT8846_ID_REG3]	= { .name = "REG3" },
-	[ACT8846_ID_REG4]	= { .name = "REG4" },
-	[ACT8846_ID_REG5]	= { .name = "REG5" },
-	[ACT8846_ID_REG6]	= { .name = "REG6" },
-	[ACT8846_ID_REG7]	= { .name = "REG7" },
-	[ACT8846_ID_REG8]	= { .name = "REG8" },
-	[ACT8846_ID_REG9]	= { .name = "REG9" },
-	[ACT8846_ID_REG10]	= { .name = "REG10" },
-	[ACT8846_ID_REG11]	= { .name = "REG11" },
-	[ACT8846_ID_REG12]	= { .name = "REG12" },
-};
-
-static struct of_regulator_match act8865_matches[] = {
-	[ACT8865_ID_DCDC1]	= { .name = "DCDC_REG1"},
-	[ACT8865_ID_DCDC2]	= { .name = "DCDC_REG2"},
-	[ACT8865_ID_DCDC3]	= { .name = "DCDC_REG3"},
-	[ACT8865_ID_LDO1]	= { .name = "LDO_REG1"},
-	[ACT8865_ID_LDO2]	= { .name = "LDO_REG2"},
-	[ACT8865_ID_LDO3]	= { .name = "LDO_REG3"},
-	[ACT8865_ID_LDO4]	= { .name = "LDO_REG4"},
-};
-
-static struct of_regulator_match act8600_matches[] = {
-	[ACT8600_ID_DCDC1]	= { .name = "DCDC_REG1"},
-	[ACT8600_ID_DCDC2]	= { .name = "DCDC_REG2"},
-	[ACT8600_ID_DCDC3]	= { .name = "DCDC_REG3"},
-	[ACT8600_ID_SUDCDC4]	= { .name = "SUDCDC_REG4"},
-	[ACT8600_ID_LDO5]	= { .name = "LDO_REG5"},
-	[ACT8600_ID_LDO6]	= { .name = "LDO_REG6"},
-	[ACT8600_ID_LDO7]	= { .name = "LDO_REG7"},
-	[ACT8600_ID_LDO8]	= { .name = "LDO_REG8"},
-	[ACT8600_ID_LDO9]	= { .name = "LDO_REG9"},
-	[ACT8600_ID_LDO10]	= { .name = "LDO_REG10"},
-};
-
-static int act8865_pdata_from_dt(struct device *dev,
-				 struct act8865_platform_data *pdata,
-				 unsigned long type)
-{
-	int matched, i, num_matches;
-	struct device_node *np;
-	struct act8865_regulator_data *regulator;
-	struct of_regulator_match *matches;
-
-	switch (type) {
-	case ACT8600:
-		matches = act8600_matches;
-		num_matches = ARRAY_SIZE(act8600_matches);
-		break;
-	case ACT8846:
-		matches = act8846_matches;
-		num_matches = ARRAY_SIZE(act8846_matches);
-		break;
-	case ACT8865:
-		matches = act8865_matches;
-		num_matches = ARRAY_SIZE(act8865_matches);
-		break;
-	default:
-		dev_err(dev, "invalid device id %lu\n", type);
-		return -EINVAL;
-	}
-
-	np = of_get_child_by_name(dev->of_node, "regulators");
-	if (!np) {
-		dev_err(dev, "missing 'regulators' subnode in DT\n");
-		return -EINVAL;
-	}
-
-	matched = of_regulator_match(dev, np, matches, num_matches);
-	of_node_put(np);
-	if (matched <= 0)
-		return matched;
-
-	pdata->regulators = devm_kcalloc(dev,
-					 num_matches,
-					 sizeof(struct act8865_regulator_data),
-					 GFP_KERNEL);
-	if (!pdata->regulators)
-		return -ENOMEM;
-
-	pdata->num_regulators = num_matches;
-	regulator = pdata->regulators;
-
-	for (i = 0; i < num_matches; i++) {
-		regulator->id = i;
-		regulator->name = matches[i].name;
-		regulator->init_data = matches[i].init_data;
-		regulator->of_node = matches[i].of_node;
-		regulator++;
-	}
-
-	return 0;
-}
-#else
-static inline int act8865_pdata_from_dt(struct device *dev,
-					struct act8865_platform_data *pdata,
-					unsigned long type)
-{
-	return 0;
-}
 #endif
 
 static struct act8865_regulator_data *act8865_get_regulator_data(
@@ -459,9 +363,6 @@ static struct act8865_regulator_data *act8865_get_regulator_data(
 {
 	int i;
 
-	if (!pdata)
-		return NULL;
-
 	for (i = 0; i < pdata->num_regulators; i++) {
 		if (pdata->regulators[i].id == id)
 			return &pdata->regulators[i];
@@ -484,7 +385,7 @@ static int act8865_pmic_probe(struct i2c_client *client,
 			      const struct i2c_device_id *i2c_id)
 {
 	const struct regulator_desc *regulators;
-	struct act8865_platform_data pdata_of, *pdata;
+	struct act8865_platform_data *pdata = NULL;
 	struct device *dev = &client->dev;
 	int i, ret, num_regulators;
 	struct act8865 *act8865;
@@ -493,9 +394,7 @@ static int act8865_pmic_probe(struct i2c_client *client,
 	int off_reg, off_mask;
 	int voltage_select = 0;
 
-	pdata = dev_get_platdata(dev);
-
-	if (dev->of_node && !pdata) {
+	if (dev->of_node) {
 		const struct of_device_id *id;
 
 		id = of_match_device(of_match_ptr(act8865_dt_ids), dev);
@@ -509,6 +408,7 @@ static int act8865_pmic_probe(struct i2c_client *client,
 						   NULL);
 	} else {
 		type = i2c_id->driver_data;
+		pdata = dev_get_platdata(dev);
 	}
 
 	switch (type) {
@@ -543,14 +443,6 @@ static int act8865_pmic_probe(struct i2c_client *client,
 		return -EINVAL;
 	}
 
-	if (dev->of_node && !pdata) {
-		ret = act8865_pdata_from_dt(dev, &pdata_of, type);
-		if (ret < 0)
-			return ret;
-
-		pdata = &pdata_of;
-	}
-
 	act8865 = devm_kzalloc(dev, sizeof(struct act8865), GFP_KERNEL);
 	if (!act8865)
 		return -ENOMEM;
@@ -577,17 +469,20 @@ static int act8865_pmic_probe(struct i2c_client *client,
 	for (i = 0; i < num_regulators; i++) {
 		const struct regulator_desc *desc = &regulators[i];
 		struct regulator_config config = { };
-		struct act8865_regulator_data *rdata;
 		struct regulator_dev *rdev;
 
 		config.dev = dev;
 		config.driver_data = act8865;
 		config.regmap = act8865->regmap;
 
-		rdata = act8865_get_regulator_data(desc->id, pdata);
-		if (rdata) {
-			config.init_data = rdata->init_data;
-			config.of_node = rdata->of_node;
+		if (pdata) {
+			struct act8865_regulator_data *rdata;
+
+			rdata = act8865_get_regulator_data(desc->id, pdata);
+			if (rdata) {
+				config.init_data = rdata->init_data;
+				config.of_node = rdata->of_node;
+			}
 		}
 
 		rdev = devm_regulator_register(dev, desc, &config);
diff --git a/drivers/regulator/anatop-regulator.c b/drivers/regulator/anatop-regulator.c
index d9d8155ed8cb..754739d004e5 100644
--- a/drivers/regulator/anatop-regulator.c
+++ b/drivers/regulator/anatop-regulator.c
@@ -23,18 +23,10 @@
 #define LDO_FET_FULL_ON			0x1f
 
 struct anatop_regulator {
-	u32 control_reg;
-	struct regmap *anatop;
-	int vol_bit_shift;
-	int vol_bit_width;
 	u32 delay_reg;
 	int delay_bit_shift;
 	int delay_bit_width;
-	int min_bit_val;
-	int min_voltage;
-	int max_voltage;
 	struct regulator_desc rdesc;
-	struct regulator_init_data *initdata;
 	bool bypass;
 	int sel;
 };
@@ -55,7 +47,7 @@ static int anatop_regmap_set_voltage_time_sel(struct regulator_dev *reg,
 		 * to calculate how many steps LDO need to
 		 * ramp up, and how much delay needed. (us)
 		 */
-		regmap_read(anatop_reg->anatop, anatop_reg->delay_reg, &val);
+		regmap_read(reg->regmap, anatop_reg->delay_reg, &val);
 		val = (val >> anatop_reg->delay_bit_shift) &
 			((1 << anatop_reg->delay_bit_width) - 1);
 		ret = (new_sel - old_sel) * (LDO_RAMP_UP_UNIT_IN_CYCLES <<
@@ -170,6 +162,13 @@ static int anatop_regulator_probe(struct platform_device *pdev)
 	struct anatop_regulator *sreg;
 	struct regulator_init_data *initdata;
 	struct regulator_config config = { };
+	struct regmap *regmap;
+	u32 control_reg;
+	u32 vol_bit_shift;
+	u32 vol_bit_width;
+	u32 min_bit_val;
+	u32 min_voltage;
+	u32 max_voltage;
 	int ret = 0;
 	u32 val;
 
@@ -192,48 +191,41 @@ static int anatop_regulator_probe(struct platform_device *pdev)
 		return -ENOMEM;
 
 	initdata->supply_regulator = "vin";
-	sreg->initdata = initdata;
 
 	anatop_np = of_get_parent(np);
 	if (!anatop_np)
 		return -ENODEV;
-	sreg->anatop = syscon_node_to_regmap(anatop_np);
+	regmap = syscon_node_to_regmap(anatop_np);
 	of_node_put(anatop_np);
-	if (IS_ERR(sreg->anatop))
-		return PTR_ERR(sreg->anatop);
+	if (IS_ERR(regmap))
+		return PTR_ERR(regmap);
 
-	ret = of_property_read_u32(np, "anatop-reg-offset",
-				   &sreg->control_reg);
+	ret = of_property_read_u32(np, "anatop-reg-offset", &control_reg);
 	if (ret) {
 		dev_err(dev, "no anatop-reg-offset property set\n");
 		return ret;
 	}
-	ret = of_property_read_u32(np, "anatop-vol-bit-width",
-				   &sreg->vol_bit_width);
+	ret = of_property_read_u32(np, "anatop-vol-bit-width", &vol_bit_width);
 	if (ret) {
 		dev_err(dev, "no anatop-vol-bit-width property set\n");
 		return ret;
 	}
-	ret = of_property_read_u32(np, "anatop-vol-bit-shift",
-				   &sreg->vol_bit_shift);
+	ret = of_property_read_u32(np, "anatop-vol-bit-shift", &vol_bit_shift);
 	if (ret) {
 		dev_err(dev, "no anatop-vol-bit-shift property set\n");
 		return ret;
 	}
-	ret = of_property_read_u32(np, "anatop-min-bit-val",
-				   &sreg->min_bit_val);
+	ret = of_property_read_u32(np, "anatop-min-bit-val", &min_bit_val);
 	if (ret) {
 		dev_err(dev, "no anatop-min-bit-val property set\n");
 		return ret;
 	}
-	ret = of_property_read_u32(np, "anatop-min-voltage",
-				   &sreg->min_voltage);
+	ret = of_property_read_u32(np, "anatop-min-voltage", &min_voltage);
 	if (ret) {
 		dev_err(dev, "no anatop-min-voltage property set\n");
 		return ret;
 	}
-	ret = of_property_read_u32(np, "anatop-max-voltage",
-				   &sreg->max_voltage);
+	ret = of_property_read_u32(np, "anatop-max-voltage", &max_voltage);
 	if (ret) {
 		dev_err(dev, "no anatop-max-voltage property set\n");
 		return ret;
@@ -247,24 +239,23 @@ static int anatop_regulator_probe(struct platform_device *pdev)
 	of_property_read_u32(np, "anatop-delay-bit-shift",
 			     &sreg->delay_bit_shift);
 
-	rdesc->n_voltages = (sreg->max_voltage - sreg->min_voltage) / 25000 + 1
-			    + sreg->min_bit_val;
-	rdesc->min_uV = sreg->min_voltage;
+	rdesc->n_voltages = (max_voltage - min_voltage) / 25000 + 1
+			    + min_bit_val;
+	rdesc->min_uV = min_voltage;
 	rdesc->uV_step = 25000;
-	rdesc->linear_min_sel = sreg->min_bit_val;
-	rdesc->vsel_reg = sreg->control_reg;
-	rdesc->vsel_mask = ((1 << sreg->vol_bit_width) - 1) <<
-			   sreg->vol_bit_shift;
+	rdesc->linear_min_sel = min_bit_val;
+	rdesc->vsel_reg = control_reg;
+	rdesc->vsel_mask = ((1 << vol_bit_width) - 1) << vol_bit_shift;
 	rdesc->min_dropout_uV = 125000;
 
 	config.dev = &pdev->dev;
 	config.init_data = initdata;
 	config.driver_data = sreg;
 	config.of_node = pdev->dev.of_node;
-	config.regmap = sreg->anatop;
+	config.regmap = regmap;
 
 	/* Only core regulators have the ramp up delay configuration. */
-	if (sreg->control_reg && sreg->delay_bit_width) {
+	if (control_reg && sreg->delay_bit_width) {
 		rdesc->ops = &anatop_core_rops;
 
 		ret = regmap_read(config.regmap, rdesc->vsel_reg, &val);
@@ -273,7 +264,7 @@ static int anatop_regulator_probe(struct platform_device *pdev)
 			return ret;
 		}
 
-		sreg->sel = (val & rdesc->vsel_mask) >> sreg->vol_bit_shift;
+		sreg->sel = (val & rdesc->vsel_mask) >> vol_bit_shift;
 		if (sreg->sel == LDO_FET_FULL_ON) {
 			sreg->sel = 0;
 			sreg->bypass = true;
@@ -306,7 +297,7 @@ static int anatop_regulator_probe(struct platform_device *pdev)
 			anatop_rops.disable = regulator_disable_regmap;
 			anatop_rops.is_enabled = regulator_is_enabled_regmap;
 
-			rdesc->enable_reg = sreg->control_reg;
+			rdesc->enable_reg = control_reg;
 			rdesc->enable_mask = BIT(enable_bit);
 		}
 	}
diff --git a/drivers/regulator/arizona-ldo1.c b/drivers/regulator/arizona-ldo1.c
index bf3ab405eed1..e4bc7b1e5ccd 100644
--- a/drivers/regulator/arizona-ldo1.c
+++ b/drivers/regulator/arizona-ldo1.c
@@ -1,15 +1,10 @@
-/*
- * arizona-ldo1.c  --  LDO1 supply for Arizona devices
- *
- * Copyright 2012 Wolfson Microelectronics PLC.
- *
- * Author: Mark Brown <broonie@opensource.wolfsonmicro.com>
- *
- *  This program is free software; you can redistribute  it and/or modify it
- *  under  the terms of  the GNU General  Public License as published by the
- *  Free Software Foundation;  either version 2 of the  License, or (at your
- *  option) any later version.
- */
+// SPDX-License-Identifier: GPL-2.0+
+//
+// arizona-ldo1.c  --  LDO1 supply for Arizona devices
+//
+// Copyright 2012 Wolfson Microelectronics PLC.
+//
+// Author: Mark Brown <broonie@opensource.wolfsonmicro.com>
 
 #include <linux/module.h>
 #include <linux/moduleparam.h>
diff --git a/drivers/regulator/arizona-micsupp.c b/drivers/regulator/arizona-micsupp.c
index 120de94caf02..be0d46da51a1 100644
--- a/drivers/regulator/arizona-micsupp.c
+++ b/drivers/regulator/arizona-micsupp.c
@@ -1,15 +1,10 @@
-/*
- * arizona-micsupp.c  --  Microphone supply for Arizona devices
- *
- * Copyright 2012 Wolfson Microelectronics PLC.
- *
- * Author: Mark Brown <broonie@opensource.wolfsonmicro.com>
- *
- *  This program is free software; you can redistribute  it and/or modify it
- *  under  the terms of  the GNU General  Public License as published by the
- *  Free Software Foundation;  either version 2 of the  License, or (at your
- *  option) any later version.
- */
+// SPDX-License-Identifier: GPL-2.0+
+//
+// arizona-micsupp.c  --  Microphone supply for Arizona devices
+//
+// Copyright 2012 Wolfson Microelectronics PLC.
+//
+// Author: Mark Brown <broonie@opensource.wolfsonmicro.com>
 
 #include <linux/module.h>
 #include <linux/moduleparam.h>
diff --git a/drivers/regulator/as3711-regulator.c b/drivers/regulator/as3711-regulator.c
index f7fe218bb3e4..ece88103f2fd 100644
--- a/drivers/regulator/as3711-regulator.c
+++ b/drivers/regulator/as3711-regulator.c
@@ -17,14 +17,6 @@
 #include <linux/regulator/of_regulator.h>
 #include <linux/slab.h>
 
-struct as3711_regulator_info {
-	struct regulator_desc	desc;
-};
-
-struct as3711_regulator {
-	struct as3711_regulator_info *reg_info;
-};
-
 /*
  * The regulator API supports 4 modes of operataion: FAST, NORMAL, IDLE and
  * STANDBY. We map them in the following way to AS3711 SD1-4 DCDC modes:
@@ -129,7 +121,6 @@ static const struct regulator_linear_range as3711_dldo_ranges[] = {
 
 #define AS3711_REG(_id, _en_reg, _en_bit, _vmask, _sfx)			   \
 	[AS3711_REGULATOR_ ## _id] = {					   \
-	.desc = {							   \
 		.name = "as3711-regulator-" # _id,			   \
 		.id = AS3711_REGULATOR_ ## _id,				   \
 		.n_voltages = (_vmask + 1),				   \
@@ -142,10 +133,9 @@ static const struct regulator_linear_range as3711_dldo_ranges[] = {
 		.enable_mask = BIT(_en_bit),				   \
 		.linear_ranges = as3711_ ## _sfx ## _ranges,		   \
 		.n_linear_ranges = ARRAY_SIZE(as3711_ ## _sfx ## _ranges), \
-	},								   \
 }
 
-static struct as3711_regulator_info as3711_reg_info[] = {
+static const struct regulator_desc as3711_reg_desc[] = {
 	AS3711_REG(SD_1, SD_CONTROL, 0, 0x7f, sd),
 	AS3711_REG(SD_2, SD_CONTROL, 1, 0x7f, sd),
 	AS3711_REG(SD_3, SD_CONTROL, 2, 0x7f, sd),
@@ -161,7 +151,7 @@ static struct as3711_regulator_info as3711_reg_info[] = {
 	/* StepUp output voltage depends on supplying regulator */
 };
 
-#define AS3711_REGULATOR_NUM ARRAY_SIZE(as3711_reg_info)
+#define AS3711_REGULATOR_NUM ARRAY_SIZE(as3711_reg_desc)
 
 static struct of_regulator_match
 as3711_regulator_matches[AS3711_REGULATOR_NUM] = {
@@ -215,11 +205,8 @@ static int as3711_regulator_probe(struct platform_device *pdev)
 	struct as3711_regulator_pdata *pdata = dev_get_platdata(&pdev->dev);
 	struct as3711 *as3711 = dev_get_drvdata(pdev->dev.parent);
 	struct regulator_config config = {.dev = &pdev->dev,};
-	struct as3711_regulator *reg = NULL;
-	struct as3711_regulator *regs;
 	struct device_node *of_node[AS3711_REGULATOR_NUM] = {};
 	struct regulator_dev *rdev;
-	struct as3711_regulator_info *ri;
 	int ret;
 	int id;
 
@@ -236,30 +223,20 @@ static int as3711_regulator_probe(struct platform_device *pdev)
 		}
 	}
 
-	regs = devm_kcalloc(&pdev->dev,
-			    AS3711_REGULATOR_NUM,
-			    sizeof(struct as3711_regulator),
-			    GFP_KERNEL);
-	if (!regs)
-		return -ENOMEM;
-
-	for (id = 0, ri = as3711_reg_info; id < AS3711_REGULATOR_NUM; ++id, ri++) {
-		reg = &regs[id];
-		reg->reg_info = ri;
-
+	for (id = 0; id < AS3711_REGULATOR_NUM; id++) {
 		config.init_data = pdata->init_data[id];
-		config.driver_data = reg;
 		config.regmap = as3711->regmap;
 		config.of_node = of_node[id];
 
-		rdev = devm_regulator_register(&pdev->dev, &ri->desc, &config);
+		rdev = devm_regulator_register(&pdev->dev, &as3711_reg_desc[id],
+					       &config);
 		if (IS_ERR(rdev)) {
 			dev_err(&pdev->dev, "Failed to register regulator %s\n",
-				ri->desc.name);
+				as3711_reg_desc[id].name);
 			return PTR_ERR(rdev);
 		}
 	}
-	platform_set_drvdata(pdev, regs);
+
 	return 0;
 }
 
diff --git a/drivers/regulator/as3722-regulator.c b/drivers/regulator/as3722-regulator.c
index e5fed289b52d..dc75c33bd950 100644
--- a/drivers/regulator/as3722-regulator.c
+++ b/drivers/regulator/as3722-regulator.c
@@ -81,7 +81,6 @@ struct as3722_regulator_config_data {
 struct as3722_regulators {
 	struct device *dev;
 	struct as3722 *as3722;
-	struct regulator_dev *rdevs[AS3722_REGULATOR_ID_MAX];
 	struct regulator_desc desc[AS3722_REGULATOR_ID_MAX];
 	struct as3722_regulator_config_data
 			reg_config_data[AS3722_REGULATOR_ID_MAX];
@@ -314,63 +313,10 @@ static const struct as3722_register_mapping as3722_reg_lookup[] = {
 	},
 };
 
-
-static const int as3722_ldo_current[] = { 150000, 300000 };
-static const int as3722_sd016_current[] = { 2500000, 3000000, 3500000 };
-
-static int as3722_current_to_index(int min_uA, int max_uA,
-		const int *curr_table, int n_currents)
-{
-	int i;
-
-	for (i = n_currents - 1; i >= 0; i--) {
-		if ((min_uA <= curr_table[i]) && (curr_table[i] <= max_uA))
-			return i;
-	}
-	return -EINVAL;
-}
-
-static int as3722_ldo_get_current_limit(struct regulator_dev *rdev)
-{
-	struct as3722_regulators *as3722_regs = rdev_get_drvdata(rdev);
-	struct as3722 *as3722 = as3722_regs->as3722;
-	int id = rdev_get_id(rdev);
-	u32 val;
-	int ret;
-
-	ret = as3722_read(as3722, as3722_reg_lookup[id].vsel_reg, &val);
-	if (ret < 0) {
-		dev_err(as3722_regs->dev, "Reg 0x%02x read failed: %d\n",
-			as3722_reg_lookup[id].vsel_reg, ret);
-		return ret;
-	}
-	if (val & AS3722_LDO_ILIMIT_MASK)
-		return 300000;
-	return 150000;
-}
-
-static int as3722_ldo_set_current_limit(struct regulator_dev *rdev,
-		int min_uA, int max_uA)
-{
-	struct as3722_regulators *as3722_regs = rdev_get_drvdata(rdev);
-	struct as3722 *as3722 = as3722_regs->as3722;
-	int id = rdev_get_id(rdev);
-	int ret;
-	u32 reg = 0;
-
-	ret = as3722_current_to_index(min_uA, max_uA, as3722_ldo_current,
-				ARRAY_SIZE(as3722_ldo_current));
-	if (ret < 0) {
-		dev_err(as3722_regs->dev,
-			"Current range min:max = %d:%d does not support\n",
-			min_uA, max_uA);
-		return ret;
-	}
-	if (ret)
-		reg = AS3722_LDO_ILIMIT_BIT;
-	return as3722_update_bits(as3722, as3722_reg_lookup[id].vsel_reg,
-			AS3722_LDO_ILIMIT_MASK, reg);
-}
+static const unsigned int as3722_ldo_current[] = { 150000, 300000 };
+static const unsigned int as3722_sd016_current[] = {
+	2500000, 3000000, 3500000
+};
 
 static const struct regulator_ops as3722_ldo0_ops = {
 	.is_enabled = regulator_is_enabled_regmap,
@@ -379,16 +325,16 @@ static const struct regulator_ops as3722_ldo0_ops = {
 	.list_voltage = regulator_list_voltage_linear,
 	.get_voltage_sel = regulator_get_voltage_sel_regmap,
 	.set_voltage_sel = regulator_set_voltage_sel_regmap,
-	.get_current_limit = as3722_ldo_get_current_limit,
-	.set_current_limit = as3722_ldo_set_current_limit,
+	.get_current_limit = regulator_get_current_limit_regmap,
+	.set_current_limit = regulator_set_current_limit_regmap,
 };
 
 static const struct regulator_ops as3722_ldo0_extcntrl_ops = {
 	.list_voltage = regulator_list_voltage_linear,
 	.get_voltage_sel = regulator_get_voltage_sel_regmap,
 	.set_voltage_sel = regulator_set_voltage_sel_regmap,
-	.get_current_limit = as3722_ldo_get_current_limit,
-	.set_current_limit = as3722_ldo_set_current_limit,
+	.get_current_limit = regulator_get_current_limit_regmap,
+	.set_current_limit = regulator_set_current_limit_regmap,
 };
 
 static int as3722_ldo3_set_tracking_mode(struct as3722_regulators *as3722_reg,
@@ -440,8 +386,8 @@ static const struct regulator_ops as3722_ldo6_ops = {
 	.set_voltage_sel = regulator_set_voltage_sel_regmap,
 	.get_voltage_sel = regulator_get_voltage_sel_regmap,
 	.list_voltage = regulator_list_voltage_linear_range,
-	.get_current_limit = as3722_ldo_get_current_limit,
-	.set_current_limit = as3722_ldo_set_current_limit,
+	.get_current_limit = regulator_get_current_limit_regmap,
+	.set_current_limit = regulator_set_current_limit_regmap,
 	.get_bypass = regulator_get_bypass_regmap,
 	.set_bypass = regulator_set_bypass_regmap,
 };
@@ -451,8 +397,8 @@ static const struct regulator_ops as3722_ldo6_extcntrl_ops = {
 	.set_voltage_sel = regulator_set_voltage_sel_regmap,
 	.get_voltage_sel = regulator_get_voltage_sel_regmap,
 	.list_voltage = regulator_list_voltage_linear_range,
-	.get_current_limit = as3722_ldo_get_current_limit,
-	.set_current_limit = as3722_ldo_set_current_limit,
+	.get_current_limit = regulator_get_current_limit_regmap,
+	.set_current_limit = regulator_set_current_limit_regmap,
 	.get_bypass = regulator_get_bypass_regmap,
 	.set_bypass = regulator_set_bypass_regmap,
 };
@@ -471,8 +417,8 @@ static const struct regulator_ops as3722_ldo_ops = {
 	.set_voltage_sel = regulator_set_voltage_sel_regmap,
 	.get_voltage_sel = regulator_get_voltage_sel_regmap,
 	.list_voltage = regulator_list_voltage_linear_range,
-	.get_current_limit = as3722_ldo_get_current_limit,
-	.set_current_limit = as3722_ldo_set_current_limit,
+	.get_current_limit = regulator_get_current_limit_regmap,
+	.set_current_limit = regulator_set_current_limit_regmap,
 };
 
 static const struct regulator_ops as3722_ldo_extcntrl_ops = {
@@ -480,8 +426,8 @@ static const struct regulator_ops as3722_ldo_extcntrl_ops = {
 	.set_voltage_sel = regulator_set_voltage_sel_regmap,
 	.get_voltage_sel = regulator_get_voltage_sel_regmap,
 	.list_voltage = regulator_list_voltage_linear_range,
-	.get_current_limit = as3722_ldo_get_current_limit,
-	.set_current_limit = as3722_ldo_set_current_limit,
+	.get_current_limit = regulator_get_current_limit_regmap,
+	.set_current_limit = regulator_set_current_limit_regmap,
 };
 
 static unsigned int as3722_sd_get_mode(struct regulator_dev *rdev)
@@ -539,85 +485,6 @@ static int as3722_sd_set_mode(struct regulator_dev *rdev,
 	return ret;
 }
 
-static int as3722_sd016_get_current_limit(struct regulator_dev *rdev)
-{
-	struct as3722_regulators *as3722_regs = rdev_get_drvdata(rdev);
-	struct as3722 *as3722 = as3722_regs->as3722;
-	int id = rdev_get_id(rdev);
-	u32 val, reg;
-	int mask;
-	int ret;
-
-	switch (id) {
-	case AS3722_REGULATOR_ID_SD0:
-		reg = AS3722_OVCURRENT_REG;
-		mask = AS3722_OVCURRENT_SD0_TRIP_MASK;
-		break;
-	case AS3722_REGULATOR_ID_SD1:
-		reg = AS3722_OVCURRENT_REG;
-		mask = AS3722_OVCURRENT_SD1_TRIP_MASK;
-		break;
-	case AS3722_REGULATOR_ID_SD6:
-		reg = AS3722_OVCURRENT_DEB_REG;
-		mask = AS3722_OVCURRENT_SD6_TRIP_MASK;
-		break;
-	default:
-		return -EINVAL;
-	}
-	ret = as3722_read(as3722, reg, &val);
-	if (ret < 0) {
-		dev_err(as3722_regs->dev, "Reg 0x%02x read failed: %d\n",
-			reg, ret);
-		return ret;
-	}
-	val &= mask;
-	val >>= ffs(mask) - 1;
-	if (val == 3)
-		return -EINVAL;
-	return as3722_sd016_current[val];
-}
-
-static int as3722_sd016_set_current_limit(struct regulator_dev *rdev,
-		int min_uA, int max_uA)
-{
-	struct as3722_regulators *as3722_regs = rdev_get_drvdata(rdev);
-	struct as3722 *as3722 = as3722_regs->as3722;
-	int id = rdev_get_id(rdev);
-	int ret;
-	int val;
-	int mask;
-	u32 reg;
-
-	ret = as3722_current_to_index(min_uA, max_uA, as3722_sd016_current,
-				ARRAY_SIZE(as3722_sd016_current));
-	if (ret < 0) {
-		dev_err(as3722_regs->dev,
-			"Current range min:max = %d:%d does not support\n",
-			min_uA, max_uA);
-		return ret;
-	}
-
-	switch (id) {
-	case AS3722_REGULATOR_ID_SD0:
-		reg = AS3722_OVCURRENT_REG;
-		mask = AS3722_OVCURRENT_SD0_TRIP_MASK;
-		break;
-	case AS3722_REGULATOR_ID_SD1:
-		reg = AS3722_OVCURRENT_REG;
-		mask = AS3722_OVCURRENT_SD1_TRIP_MASK;
-		break;
-	case AS3722_REGULATOR_ID_SD6:
-		reg = AS3722_OVCURRENT_DEB_REG;
-		mask = AS3722_OVCURRENT_SD6_TRIP_MASK;
-		break;
-	default:
-		return -EINVAL;
-	}
-	ret <<= ffs(mask) - 1;
-	val = ret & mask;
-	return as3722_update_bits(as3722, reg, mask, val);
-}
-
 static bool as3722_sd0_is_low_voltage(struct as3722_regulators *as3722_regs)
 {
 	int err;
@@ -649,8 +516,8 @@ static const struct regulator_ops as3722_sd016_ops = {
 	.map_voltage = regulator_map_voltage_linear,
 	.get_voltage_sel = regulator_get_voltage_sel_regmap,
 	.set_voltage_sel = regulator_set_voltage_sel_regmap,
-	.get_current_limit = as3722_sd016_get_current_limit,
-	.set_current_limit = as3722_sd016_set_current_limit,
+	.get_current_limit = regulator_get_current_limit_regmap,
+	.set_current_limit = regulator_set_current_limit_regmap,
 	.get_mode = as3722_sd_get_mode,
 	.set_mode = as3722_sd_set_mode,
 };
@@ -660,8 +527,8 @@ static const struct regulator_ops as3722_sd016_extcntrl_ops = {
 	.map_voltage = regulator_map_voltage_linear,
 	.get_voltage_sel = regulator_get_voltage_sel_regmap,
 	.set_voltage_sel = regulator_set_voltage_sel_regmap,
-	.get_current_limit = as3722_sd016_get_current_limit,
-	.set_current_limit = as3722_sd016_set_current_limit,
+	.get_current_limit = regulator_get_current_limit_regmap,
+	.set_current_limit = regulator_set_current_limit_regmap,
 	.get_mode = as3722_sd_get_mode,
 	.set_mode = as3722_sd_set_mode,
 };
@@ -807,42 +674,45 @@ static int as3722_regulator_probe(struct platform_device *pdev)
 	config.regmap = as3722->regmap;
 
 	for (id = 0; id < AS3722_REGULATOR_ID_MAX; id++) {
+		struct regulator_desc *desc;
+
+		desc = &as3722_regs->desc[id];
 		reg_config = &as3722_regs->reg_config_data[id];
 
-		as3722_regs->desc[id].name = as3722_reg_lookup[id].name;
-		as3722_regs->desc[id].supply_name = as3722_reg_lookup[id].sname;
-		as3722_regs->desc[id].id = as3722_reg_lookup[id].regulator_id;
-		as3722_regs->desc[id].n_voltages =
-					as3722_reg_lookup[id].n_voltages;
-		as3722_regs->desc[id].type = REGULATOR_VOLTAGE;
-		as3722_regs->desc[id].owner = THIS_MODULE;
-		as3722_regs->desc[id].enable_reg =
-					as3722_reg_lookup[id].enable_reg;
-		as3722_regs->desc[id].enable_mask =
-					as3722_reg_lookup[id].enable_mask;
-		as3722_regs->desc[id].vsel_reg = as3722_reg_lookup[id].vsel_reg;
-		as3722_regs->desc[id].vsel_mask =
-					as3722_reg_lookup[id].vsel_mask;
+		desc->name = as3722_reg_lookup[id].name;
+		desc->supply_name = as3722_reg_lookup[id].sname;
+		desc->id = as3722_reg_lookup[id].regulator_id;
+		desc->n_voltages = as3722_reg_lookup[id].n_voltages;
+		desc->type = REGULATOR_VOLTAGE;
+		desc->owner = THIS_MODULE;
+		desc->enable_reg = as3722_reg_lookup[id].enable_reg;
+		desc->enable_mask = as3722_reg_lookup[id].enable_mask;
+		desc->vsel_reg = as3722_reg_lookup[id].vsel_reg;
+		desc->vsel_mask = as3722_reg_lookup[id].vsel_mask;
 		switch (id) {
 		case AS3722_REGULATOR_ID_LDO0:
 			if (reg_config->ext_control)
 				ops = &as3722_ldo0_extcntrl_ops;
 			else
 				ops = &as3722_ldo0_ops;
-			as3722_regs->desc[id].min_uV = 825000;
-			as3722_regs->desc[id].uV_step = 25000;
-			as3722_regs->desc[id].linear_min_sel = 1;
-			as3722_regs->desc[id].enable_time = 500;
+			desc->min_uV = 825000;
+			desc->uV_step = 25000;
+			desc->linear_min_sel = 1;
+			desc->enable_time = 500;
+			desc->curr_table = as3722_ldo_current;
+			desc->n_current_limits = ARRAY_SIZE(as3722_ldo_current);
+			desc->csel_reg = as3722_reg_lookup[id].vsel_reg;
+			desc->csel_mask = AS3722_LDO_ILIMIT_MASK;
 			break;
 		case AS3722_REGULATOR_ID_LDO3:
 			if (reg_config->ext_control)
 				ops = &as3722_ldo3_extcntrl_ops;
 			else
 				ops = &as3722_ldo3_ops;
-			as3722_regs->desc[id].min_uV = 620000;
-			as3722_regs->desc[id].uV_step = 20000;
-			as3722_regs->desc[id].linear_min_sel = 1;
-			as3722_regs->desc[id].enable_time = 500;
+			desc->min_uV = 620000;
+			desc->uV_step = 20000;
+			desc->linear_min_sel = 1;
+			desc->enable_time = 500;
 			if (reg_config->enable_tracking) {
 				ret = as3722_ldo3_set_tracking_mode(as3722_regs,
 					id, AS3722_LDO3_MODE_PMOS_TRACKING);
@@ -859,18 +729,17 @@ static int as3722_regulator_probe(struct platform_device *pdev)
 				ops = &as3722_ldo6_extcntrl_ops;
 			else
 				ops = &as3722_ldo6_ops;
-			as3722_regs->desc[id].enable_time = 500;
-			as3722_regs->desc[id].bypass_reg =
-						AS3722_LDO6_VOLTAGE_REG;
-			as3722_regs->desc[id].bypass_mask =
-						AS3722_LDO_VSEL_MASK;
-			as3722_regs->desc[id].bypass_val_on =
-						AS3722_LDO6_VSEL_BYPASS;
-			as3722_regs->desc[id].bypass_val_off =
-						AS3722_LDO6_VSEL_BYPASS;
-			as3722_regs->desc[id].linear_ranges = as3722_ldo_ranges;
-			as3722_regs->desc[id].n_linear_ranges =
-						ARRAY_SIZE(as3722_ldo_ranges);
+			desc->enable_time = 500;
+			desc->bypass_reg = AS3722_LDO6_VOLTAGE_REG;
+			desc->bypass_mask = AS3722_LDO_VSEL_MASK;
+			desc->bypass_val_on = AS3722_LDO6_VSEL_BYPASS;
+			desc->bypass_val_off = AS3722_LDO6_VSEL_BYPASS;
+			desc->linear_ranges = as3722_ldo_ranges;
+			desc->n_linear_ranges = ARRAY_SIZE(as3722_ldo_ranges);
+			desc->curr_table = as3722_ldo_current;
+			desc->n_current_limits = ARRAY_SIZE(as3722_ldo_current);
+			desc->csel_reg = as3722_reg_lookup[id].vsel_reg;
+			desc->csel_mask = AS3722_LDO_ILIMIT_MASK;
 			break;
 		case AS3722_REGULATOR_ID_SD0:
 		case AS3722_REGULATOR_ID_SD1:
@@ -889,9 +758,25 @@ static int as3722_regulator_probe(struct platform_device *pdev)
 					AS3722_SD0_VSEL_MAX + 1;
 				as3722_regs->desc[id].min_uV = 610000;
 			}
-			as3722_regs->desc[id].uV_step = 10000;
-			as3722_regs->desc[id].linear_min_sel = 1;
-			as3722_regs->desc[id].enable_time = 600;
+			desc->uV_step = 10000;
+			desc->linear_min_sel = 1;
+			desc->enable_time = 600;
+			desc->curr_table = as3722_sd016_current;
+			desc->n_current_limits =
+				ARRAY_SIZE(as3722_sd016_current);
+			if (id == AS3722_REGULATOR_ID_SD0) {
+				desc->csel_reg = AS3722_OVCURRENT_REG;
+				desc->csel_mask =
+					AS3722_OVCURRENT_SD0_TRIP_MASK;
+			} else if (id == AS3722_REGULATOR_ID_SD1) {
+				desc->csel_reg = AS3722_OVCURRENT_REG;
+				desc->csel_mask =
+					AS3722_OVCURRENT_SD1_TRIP_MASK;
+			} else if (id == AS3722_REGULATOR_ID_SD6) {
+				desc->csel_reg = AS3722_OVCURRENT_DEB_REG;
+				desc->csel_mask =
+					AS3722_OVCURRENT_SD6_TRIP_MASK;
+			}
 			break;
 		case AS3722_REGULATOR_ID_SD2:
 		case AS3722_REGULATOR_ID_SD3:
@@ -901,9 +786,8 @@ static int as3722_regulator_probe(struct platform_device *pdev)
 				ops = &as3722_sd2345_extcntrl_ops;
 			else
 				ops = &as3722_sd2345_ops;
-			as3722_regs->desc[id].linear_ranges =
-						as3722_sd2345_ranges;
-			as3722_regs->desc[id].n_linear_ranges =
+			desc->linear_ranges = as3722_sd2345_ranges;
+			desc->n_linear_ranges =
 					ARRAY_SIZE(as3722_sd2345_ranges);
 			break;
 		default:
@@ -911,17 +795,19 @@ static int as3722_regulator_probe(struct platform_device *pdev)
 				ops = &as3722_ldo_extcntrl_ops;
 			else
 				ops = &as3722_ldo_ops;
-			as3722_regs->desc[id].enable_time = 500;
-			as3722_regs->desc[id].linear_ranges = as3722_ldo_ranges;
-			as3722_regs->desc[id].n_linear_ranges =
-						ARRAY_SIZE(as3722_ldo_ranges);
+			desc->enable_time = 500;
+			desc->linear_ranges = as3722_ldo_ranges;
+			desc->n_linear_ranges = ARRAY_SIZE(as3722_ldo_ranges);
+			desc->curr_table = as3722_ldo_current;
+			desc->n_current_limits = ARRAY_SIZE(as3722_ldo_current);
+			desc->csel_reg = as3722_reg_lookup[id].vsel_reg;
+			desc->csel_mask = AS3722_LDO_ILIMIT_MASK;
 			break;
 		}
-		as3722_regs->desc[id].ops = ops;
+		desc->ops = ops;
 		config.init_data = reg_config->reg_init;
 		config.of_node = as3722_regulator_matches[id].of_node;
-		rdev = devm_regulator_register(&pdev->dev,
-					&as3722_regs->desc[id], &config);
+		rdev = devm_regulator_register(&pdev->dev, desc, &config);
 		if (IS_ERR(rdev)) {
 			ret = PTR_ERR(rdev);
 			dev_err(&pdev->dev, "regulator %d register failed %d\n",
@@ -929,7 +815,6 @@ static int as3722_regulator_probe(struct platform_device *pdev)
 			return ret;
 		}
 
-		as3722_regs->rdevs[id] = rdev;
 		if (reg_config->ext_control) {
 			ret = regulator_enable_regmap(rdev);
 			if (ret < 0) {
diff --git a/drivers/regulator/axp20x-regulator.c b/drivers/regulator/axp20x-regulator.c
index fba8f58ab769..152053361862 100644
--- a/drivers/regulator/axp20x-regulator.c
+++ b/drivers/regulator/axp20x-regulator.c
@@ -367,16 +367,14 @@ static const int axp209_dcdc2_ldo3_slew_rates[] = {
 static int axp20x_set_ramp_delay(struct regulator_dev *rdev, int ramp)
 {
 	struct axp20x_dev *axp20x = rdev_get_drvdata(rdev);
-	const struct regulator_desc *desc;
+	int id = rdev_get_id(rdev);
 	u8 reg, mask, enable, cfg = 0xff;
 	const int *slew_rates;
 	int rate_count = 0;
 
-	desc = rdev->desc;
-
 	switch (axp20x->variant) {
 	case AXP209_ID:
-		if (desc->id == AXP20X_DCDC2) {
+		if (id == AXP20X_DCDC2) {
 			slew_rates = axp209_dcdc2_ldo3_slew_rates;
 			rate_count = ARRAY_SIZE(axp209_dcdc2_ldo3_slew_rates);
 			reg = AXP20X_DCDC2_LDO3_V_RAMP;
@@ -388,7 +386,7 @@ static int axp20x_set_ramp_delay(struct regulator_dev *rdev, int ramp)
 			break;
 		}
 
-		if (desc->id == AXP20X_LDO3) {
+		if (id == AXP20X_LDO3) {
 			slew_rates = axp209_dcdc2_ldo3_slew_rates;
 			rate_count = ARRAY_SIZE(axp209_dcdc2_ldo3_slew_rates);
 			reg = AXP20X_DCDC2_LDO3_V_RAMP;
@@ -435,16 +433,11 @@ static int axp20x_set_ramp_delay(struct regulator_dev *rdev, int ramp)
 static int axp20x_regulator_enable_regmap(struct regulator_dev *rdev)
 {
 	struct axp20x_dev *axp20x = rdev_get_drvdata(rdev);
-	const struct regulator_desc *desc;
-
-	if (!rdev)
-		return -EINVAL;
-
-	desc = rdev->desc;
+	int id = rdev_get_id(rdev);
 
 	switch (axp20x->variant) {
 	case AXP209_ID:
-		if ((desc->id == AXP20X_LDO3) &&
+		if ((id == AXP20X_LDO3) &&
 		    rdev->constraints && rdev->constraints->soft_start) {
 			int v_out;
 			int ret;
@@ -1028,7 +1021,7 @@ static int axp20x_set_dcdc_freq(struct platform_device *pdev, u32 dcdcfreq)
 		 * (See include/linux/mfd/axp20x.h)
 		 */
 		reg = AXP803_DCDC_FREQ_CTRL;
-		/* Fall through to the check below.*/
+		/* Fall through - to the check below.*/
 	case AXP806_ID:
 		/*
 		 * AXP806 also have DCDC work frequency setting register at a
@@ -1119,12 +1112,12 @@ static int axp20x_set_dcdc_workmode(struct regulator_dev *rdev, int id, u32 work
 		break;
 
 	case AXP806_ID:
-		reg = AXP806_DCDC_MODE_CTRL2;
 		/*
 		 * AXP806 DCDC regulator IDs have the same range as AXP22X.
-		 * Fall through to the check below.
 		 * (See include/linux/mfd/axp20x.h)
 		 */
+		reg = AXP806_DCDC_MODE_CTRL2;
+		 /* Fall through - to the check below. */
 	case AXP221_ID:
 	case AXP223_ID:
 	case AXP809_ID:
diff --git a/drivers/regulator/bcm590xx-regulator.c b/drivers/regulator/bcm590xx-regulator.c
index e49c0a7d5dd5..85ccc93b2bb6 100644
--- a/drivers/regulator/bcm590xx-regulator.c
+++ b/drivers/regulator/bcm590xx-regulator.c
@@ -103,10 +103,6 @@
 	((n > BCM590XX_REG_VSR) && (n < BCM590XX_REG_VBUS))
 #define BCM590XX_REG_IS_VBUS(n)	(n == BCM590XX_REG_VBUS)
 
-struct bcm590xx_board {
-	struct regulator_init_data *bcm590xx_pmu_init_data[BCM590XX_NUM_REGS];
-};
-
 /* LDO group A: supported voltages in microvolts */
 static const unsigned int ldo_a_table[] = {
 	1200000, 1800000, 2500000, 2700000, 2800000,
@@ -280,105 +276,15 @@ static const struct regulator_ops bcm590xx_ops_vbus = {
 	.disable		= regulator_disable_regmap,
 };
 
-#define BCM590XX_MATCH(_name, _id) \
-	{ \
-		.name = #_name, \
-		.driver_data = (void *)&bcm590xx_regs[BCM590XX_REG_##_id], \
-	}
-
-static struct of_regulator_match bcm590xx_matches[] = {
-	BCM590XX_MATCH(rfldo, RFLDO),
-	BCM590XX_MATCH(camldo1, CAMLDO1),
-	BCM590XX_MATCH(camldo2, CAMLDO2),
-	BCM590XX_MATCH(simldo1, SIMLDO1),
-	BCM590XX_MATCH(simldo2, SIMLDO2),
-	BCM590XX_MATCH(sdldo, SDLDO),
-	BCM590XX_MATCH(sdxldo, SDXLDO),
-	BCM590XX_MATCH(mmcldo1, MMCLDO1),
-	BCM590XX_MATCH(mmcldo2, MMCLDO2),
-	BCM590XX_MATCH(audldo, AUDLDO),
-	BCM590XX_MATCH(micldo, MICLDO),
-	BCM590XX_MATCH(usbldo, USBLDO),
-	BCM590XX_MATCH(vibldo, VIBLDO),
-	BCM590XX_MATCH(csr, CSR),
-	BCM590XX_MATCH(iosr1, IOSR1),
-	BCM590XX_MATCH(iosr2, IOSR2),
-	BCM590XX_MATCH(msr, MSR),
-	BCM590XX_MATCH(sdsr1, SDSR1),
-	BCM590XX_MATCH(sdsr2, SDSR2),
-	BCM590XX_MATCH(vsr, VSR),
-	BCM590XX_MATCH(gpldo1, GPLDO1),
-	BCM590XX_MATCH(gpldo2, GPLDO2),
-	BCM590XX_MATCH(gpldo3, GPLDO3),
-	BCM590XX_MATCH(gpldo4, GPLDO4),
-	BCM590XX_MATCH(gpldo5, GPLDO5),
-	BCM590XX_MATCH(gpldo6, GPLDO6),
-	BCM590XX_MATCH(vbus, VBUS),
-};
-
-static struct bcm590xx_board *bcm590xx_parse_dt_reg_data(
-		struct platform_device *pdev,
-		struct of_regulator_match **bcm590xx_reg_matches)
-{
-	struct bcm590xx_board *data;
-	struct device_node *np = pdev->dev.parent->of_node;
-	struct device_node *regulators;
-	struct of_regulator_match *matches = bcm590xx_matches;
-	int count = ARRAY_SIZE(bcm590xx_matches);
-	int idx = 0;
-	int ret;
-
-	if (!np) {
-		dev_err(&pdev->dev, "of node not found\n");
-		return NULL;
-	}
-
-	data = devm_kzalloc(&pdev->dev, sizeof(*data), GFP_KERNEL);
-	if (!data)
-		return NULL;
-
-	np = of_node_get(np);
-	regulators = of_get_child_by_name(np, "regulators");
-	if (!regulators) {
-		dev_warn(&pdev->dev, "regulator node not found\n");
-		return NULL;
-	}
-
-	ret = of_regulator_match(&pdev->dev, regulators, matches, count);
-	of_node_put(regulators);
-	if (ret < 0) {
-		dev_err(&pdev->dev, "Error parsing regulator init data: %d\n",
-			ret);
-		return NULL;
-	}
-
-	*bcm590xx_reg_matches = matches;
-
-	for (idx = 0; idx < count; idx++) {
-		if (!matches[idx].init_data || !matches[idx].of_node)
-			continue;
-
-		data->bcm590xx_pmu_init_data[idx] = matches[idx].init_data;
-	}
-
-	return data;
-}
-
 static int bcm590xx_probe(struct platform_device *pdev)
 {
 	struct bcm590xx *bcm590xx = dev_get_drvdata(pdev->dev.parent);
-	struct bcm590xx_board *pmu_data = NULL;
 	struct bcm590xx_reg *pmu;
 	struct regulator_config config = { };
 	struct bcm590xx_info *info;
-	struct regulator_init_data *reg_data;
 	struct regulator_dev *rdev;
-	struct of_regulator_match *bcm590xx_reg_matches = NULL;
 	int i;
 
-	pmu_data = bcm590xx_parse_dt_reg_data(pdev,
-					      &bcm590xx_reg_matches);
-
 	pmu = devm_kzalloc(&pdev->dev, sizeof(*pmu), GFP_KERNEL);
 	if (!pmu)
 		return -ENOMEM;
@@ -397,13 +303,10 @@ static int bcm590xx_probe(struct platform_device *pdev)
 	info = bcm590xx_regs;
 
 	for (i = 0; i < BCM590XX_NUM_REGS; i++, info++) {
-		if (pmu_data)
-			reg_data = pmu_data->bcm590xx_pmu_init_data[i];
-		else
-			reg_data = NULL;
-
 		/* Register the regulators */
 		pmu->desc[i].name = info->name;
+		pmu->desc[i].of_match = of_match_ptr(info->name);
+		pmu->desc[i].regulators_node = of_match_ptr("regulators");
 		pmu->desc[i].supply_name = info->vin_name;
 		pmu->desc[i].id = i;
 		pmu->desc[i].volt_table = info->volt_table;
@@ -433,16 +336,12 @@ static int bcm590xx_probe(struct platform_device *pdev)
 		pmu->desc[i].owner = THIS_MODULE;
 
 		config.dev = bcm590xx->dev;
-		config.init_data = reg_data;
 		config.driver_data = pmu;
 		if (BCM590XX_REG_IS_GPLDO(i) || BCM590XX_REG_IS_VBUS(i))
 			config.regmap = bcm590xx->regmap_sec;
 		else
 			config.regmap = bcm590xx->regmap_pri;
 
-		if (bcm590xx_reg_matches)
-			config.of_node = bcm590xx_reg_matches[i].of_node;
-
 		rdev = devm_regulator_register(&pdev->dev, &pmu->desc[i],
 					       &config);
 		if (IS_ERR(rdev)) {
diff --git a/drivers/regulator/bd718x7-regulator.c b/drivers/regulator/bd718x7-regulator.c
index b2191be49670..fde4264da6ff 100644
--- a/drivers/regulator/bd718x7-regulator.c
+++ b/drivers/regulator/bd718x7-regulator.c
@@ -27,8 +27,8 @@
 static int bd718xx_buck1234_set_ramp_delay(struct regulator_dev *rdev,
 					   int ramp_delay)
 {
-	int id = rdev->desc->id;
-	unsigned int ramp_value = BUCK_RAMPRATE_10P00MV;
+	int id = rdev_get_id(rdev);
+	unsigned int ramp_value;
 
 	dev_dbg(&rdev->dev, "Buck[%d] Set Ramp = %d\n", id + 1,
 		ramp_delay);
diff --git a/drivers/regulator/core.c b/drivers/regulator/core.c
index 68473d0cc57e..955a0a15b9cb 100644
--- a/drivers/regulator/core.c
+++ b/drivers/regulator/core.c
@@ -1339,9 +1339,7 @@ static int set_machine_constraints(struct regulator_dev *rdev,
 		 * We'll only apply the initial system load if an
 		 * initial mode wasn't specified.
 		 */
-		regulator_lock(rdev);
 		drms_uA_update(rdev);
-		regulator_unlock(rdev);
 	}
 
 	if ((rdev->constraints->ramp_delay || rdev->constraints->ramp_disable)
@@ -2256,6 +2254,7 @@ static void regulator_ena_gpio_free(struct regulator_dev *rdev)
 		if (pin->gpiod == rdev->ena_pin->gpiod) {
 			if (pin->request_count <= 1) {
 				pin->request_count = 0;
+				gpiod_put(pin->gpiod);
 				list_del(&pin->list);
 				kfree(pin);
 				rdev->ena_pin = NULL;
@@ -3004,7 +3003,7 @@ EXPORT_SYMBOL_GPL(regulator_get_linear_step);
  * @min_uV: Minimum required voltage in uV.
  * @max_uV: Maximum required voltage in uV.
  *
- * Returns a boolean or a negative error code.
+ * Returns a boolean.
  */
 int regulator_is_supported_voltage(struct regulator *regulator,
 				   int min_uV, int max_uV)
@@ -3028,7 +3027,7 @@ int regulator_is_supported_voltage(struct regulator *regulator,
 
 	ret = regulator_count_voltages(regulator);
 	if (ret < 0)
-		return ret;
+		return 0;
 	voltages = ret;
 
 	for (i = 0; i < voltages; i++) {
@@ -3322,15 +3321,12 @@ static int regulator_set_voltage_unlocked(struct regulator *regulator,
 
 	/* for not coupled regulators this will just set the voltage */
 	ret = regulator_balance_voltage(rdev, state);
-	if (ret < 0)
-		goto out2;
+	if (ret < 0) {
+		voltage->min_uV = old_min_uV;
+		voltage->max_uV = old_max_uV;
+	}
 
 out:
-	return 0;
-out2:
-	voltage->min_uV = old_min_uV;
-	voltage->max_uV = old_max_uV;
-
 	return ret;
 }
 
@@ -4347,8 +4343,6 @@ int regulator_bulk_get(struct device *dev, int num_consumers,
 						      consumers[i].supply);
 		if (IS_ERR(consumers[i].consumer)) {
 			ret = PTR_ERR(consumers[i].consumer);
-			dev_err(dev, "Failed to get supply '%s': %d\n",
-				consumers[i].supply, ret);
 			consumers[i].consumer = NULL;
 			goto err;
 		}
@@ -4357,6 +4351,13 @@ int regulator_bulk_get(struct device *dev, int num_consumers,
 	return 0;
 
 err:
+	if (ret != -EPROBE_DEFER)
+		dev_err(dev, "Failed to get supply '%s': %d\n",
+			consumers[i].supply, ret);
+	else
+		dev_dbg(dev, "Failed to get supply '%s', deferring\n",
+			consumers[i].supply);
+
 	while (--i >= 0)
 		regulator_put(consumers[i].consumer);
 
@@ -5064,10 +5065,11 @@ void regulator_unregister(struct regulator_dev *rdev)
 		regulator_put(rdev->supply);
 	}
 
+	flush_work(&rdev->disable_work.work);
+
 	mutex_lock(&regulator_list_mutex);
 
 	debugfs_remove_recursive(rdev->debugfs);
-	flush_work(&rdev->disable_work.work);
 	WARN_ON(rdev->open_count);
 	regulator_remove_coupling(rdev);
 	unset_regulator_supplies(rdev);
diff --git a/drivers/regulator/cpcap-regulator.c b/drivers/regulator/cpcap-regulator.c
index e7dab5c4d1d1..d3284361e594 100644
--- a/drivers/regulator/cpcap-regulator.c
+++ b/drivers/regulator/cpcap-regulator.c
@@ -505,17 +505,12 @@ MODULE_DEVICE_TABLE(of, cpcap_regulator_id_table);
 static int cpcap_regulator_probe(struct platform_device *pdev)
 {
 	struct cpcap_ddata *ddata;
-	const struct of_device_id *match;
+	const struct cpcap_regulator *match_data;
 	struct regulator_config config;
-	struct regulator_init_data init_data;
 	int i;
 
-	match = of_match_device(of_match_ptr(cpcap_regulator_id_table),
-				&pdev->dev);
-	if (!match)
-		return -EINVAL;
-
-	if (!match->data) {
+	match_data = of_device_get_match_data(&pdev->dev);
+	if (!match_data) {
 		dev_err(&pdev->dev, "no configuration data found\n");
 
 		return -ENODEV;
@@ -530,14 +525,12 @@ static int cpcap_regulator_probe(struct platform_device *pdev)
 		return -ENODEV;
 
 	ddata->dev = &pdev->dev;
-	ddata->soc = match->data;
+	ddata->soc = match_data;
 	platform_set_drvdata(pdev, ddata);
 
 	memset(&config, 0, sizeof(config));
-	memset(&init_data, 0, sizeof(init_data));
 	config.dev = &pdev->dev;
 	config.regmap = ddata->reg;
-	config.init_data = &init_data;
 
 	for (i = 0; i < CPCAP_NR_REGULATORS; i++) {
 		const struct cpcap_regulator *regulator = &ddata->soc[i];
diff --git a/drivers/regulator/da903x.c b/drivers/regulator/da903x.c
index 33e8f3b8d2bd..5493c3a86426 100644
--- a/drivers/regulator/da903x.c
+++ b/drivers/regulator/da903x.c
@@ -1,13 +1,9 @@
-/*
- * Regulators driver for Dialog Semiconductor DA903x
- *
- * Copyright (C) 2006-2008 Marvell International Ltd.
- * Copyright (C) 2008 Compulab Ltd.
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- */
+// SPDX-License-Identifier: GPL-2.0
+//
+// Regulators driver for Dialog Semiconductor DA903x
+//
+// Copyright (C) 2006-2008 Marvell International Ltd.
+// Copyright (C) 2008 Compulab Ltd.
 
 #include <linux/kernel.h>
 #include <linux/init.h>
diff --git a/drivers/regulator/da9052-regulator.c b/drivers/regulator/da9052-regulator.c
index cefa3558236d..e18d291c7f21 100644
--- a/drivers/regulator/da9052-regulator.c
+++ b/drivers/regulator/da9052-regulator.c
@@ -1,16 +1,10 @@
-/*
-* da9052-regulator.c: Regulator driver for DA9052
-*
-* Copyright(c) 2011 Dialog Semiconductor Ltd.
-*
-* Author: David Dajun Chen <dchen@diasemi.com>
-*
-* This program is free software; you can redistribute it and/or modify
-* it under the terms of the GNU General Public License as published by
-* the Free Software Foundation; either version 2 of the License, or
-* (at your option) any later version.
-*
-*/
+// SPDX-License-Identifier: GPL-2.0+
+//
+// da9052-regulator.c: Regulator driver for DA9052
+//
+// Copyright(c) 2011 Dialog Semiconductor Ltd.
+//
+// Author: David Dajun Chen <dchen@diasemi.com>
 
 #include <linux/module.h>
 #include <linux/moduleparam.h>
@@ -19,10 +13,8 @@
 #include <linux/platform_device.h>
 #include <linux/regulator/driver.h>
 #include <linux/regulator/machine.h>
-#ifdef CONFIG_OF
 #include <linux/of.h>
 #include <linux/regulator/of_regulator.h>
-#endif
 
 #include <linux/mfd/da9052/da9052.h>
 #include <linux/mfd/da9052/reg.h>
@@ -294,6 +286,8 @@ static const struct regulator_ops da9052_ldo_ops = {
 {\
 	.reg_desc = {\
 		.name = #_name,\
+		.of_match = of_match_ptr(#_name),\
+		.regulators_node = of_match_ptr("regulators"),\
 		.ops = &da9052_ldo_ops,\
 		.type = REGULATOR_VOLTAGE,\
 		.id = DA9052_ID_##_id,\
@@ -314,6 +308,8 @@ static const struct regulator_ops da9052_ldo_ops = {
 {\
 	.reg_desc = {\
 		.name = #_name,\
+		.of_match = of_match_ptr(#_name),\
+		.regulators_node = of_match_ptr("regulators"),\
 		.ops = &da9052_dcdc_ops,\
 		.type = REGULATOR_VOLTAGE,\
 		.id = DA9052_ID_##_id,\
@@ -417,36 +413,11 @@ static int da9052_regulator_probe(struct platform_device *pdev)
 		return -EINVAL;
 	}
 
-	config.dev = &pdev->dev;
+	config.dev = da9052->dev;
 	config.driver_data = regulator;
 	config.regmap = da9052->regmap;
-	if (pdata) {
+	if (pdata)
 		config.init_data = pdata->regulators[cell->id];
-	} else {
-#ifdef CONFIG_OF
-		struct device_node *nproot = da9052->dev->of_node;
-		struct device_node *np;
-
-		if (!nproot)
-			return -ENODEV;
-
-		nproot = of_get_child_by_name(nproot, "regulators");
-		if (!nproot)
-			return -ENODEV;
-
-		for_each_child_of_node(nproot, np) {
-			if (of_node_name_eq(np,
-					 regulator->info->reg_desc.name)) {
-				config.init_data = of_get_regulator_init_data(
-					&pdev->dev, np,
-					&regulator->info->reg_desc);
-				config.of_node = np;
-				break;
-			}
-		}
-		of_node_put(nproot);
-#endif
-	}
 
 	regulator->rdev = devm_regulator_register(&pdev->dev,
 						  &regulator->info->reg_desc,
diff --git a/drivers/regulator/da9055-regulator.c b/drivers/regulator/da9055-regulator.c
index 3c6fac793658..c025ccb1a30a 100644
--- a/drivers/regulator/da9055-regulator.c
+++ b/drivers/regulator/da9055-regulator.c
@@ -1,16 +1,10 @@
-/*
-* Regulator driver for DA9055 PMIC
-*
-* Copyright(c) 2012 Dialog Semiconductor Ltd.
-*
-* Author: David Dajun Chen <dchen@diasemi.com>
-*
-* This program is free software; you can redistribute it and/or modify
-* it under the terms of the GNU General Public License as published by
-* the Free Software Foundation; either version 2 of the License, or
-* (at your option) any later version.
-*
-*/
+// SPDX-License-Identifier: GPL-2.0+
+//
+// Regulator driver for DA9055 PMIC
+//
+// Copyright(c) 2012 Dialog Semiconductor Ltd.
+//
+// Author: David Dajun Chen <dchen@diasemi.com>
 
 #include <linux/module.h>
 #include <linux/init.h>
@@ -338,6 +332,8 @@ static const struct regulator_ops da9055_ldo_ops = {
 {\
 	.reg_desc = {\
 		.name = #_id,\
+		.of_match = of_match_ptr(#_id),\
+		.regulators_node = of_match_ptr("regulators"),\
 		.ops = &da9055_ldo_ops,\
 		.type = REGULATOR_VOLTAGE,\
 		.id = DA9055_ID_##_id,\
@@ -366,6 +362,8 @@ static const struct regulator_ops da9055_ldo_ops = {
 {\
 	.reg_desc = {\
 		.name = #_id,\
+		.of_match = of_match_ptr(#_id),\
+		.regulators_node = of_match_ptr("regulators"),\
 		.ops = &da9055_buck_ops,\
 		.type = REGULATOR_VOLTAGE,\
 		.id = DA9055_ID_##_id,\
@@ -487,8 +485,10 @@ static irqreturn_t da9055_ldo5_6_oc_irq(int irq, void *data)
 {
 	struct da9055_regulator *regulator = data;
 
+	regulator_lock(regulator->rdev);
 	regulator_notifier_call_chain(regulator->rdev,
 				      REGULATOR_EVENT_OVER_CURRENT, NULL);
+	regulator_unlock(regulator->rdev);
 
 	return IRQ_HANDLED;
 }
@@ -507,59 +507,6 @@ static inline struct da9055_regulator_info *find_regulator_info(int id)
 	return NULL;
 }
 
-#ifdef CONFIG_OF
-static struct of_regulator_match da9055_reg_matches[] = {
-	{ .name = "BUCK1", },
-	{ .name = "BUCK2", },
-	{ .name = "LDO1", },
-	{ .name = "LDO2", },
-	{ .name = "LDO3", },
-	{ .name = "LDO4", },
-	{ .name = "LDO5", },
-	{ .name = "LDO6", },
-};
-
-static int da9055_regulator_dt_init(struct platform_device *pdev,
-				    struct da9055_regulator *regulator,
-				    struct regulator_config *config,
-				    int regid)
-{
-	struct device_node *nproot, *np;
-	int ret;
-
-	nproot = of_node_get(pdev->dev.parent->of_node);
-	if (!nproot)
-		return -ENODEV;
-
-	np = of_get_child_by_name(nproot, "regulators");
-	if (!np)
-		return -ENODEV;
-
-	ret = of_regulator_match(&pdev->dev, np, &da9055_reg_matches[regid], 1);
-	of_node_put(nproot);
-	if (ret < 0) {
-		dev_err(&pdev->dev, "Error matching regulator: %d\n", ret);
-		return ret;
-	}
-
-	config->init_data = da9055_reg_matches[regid].init_data;
-	config->of_node = da9055_reg_matches[regid].of_node;
-
-	if (!config->of_node)
-		return -ENODEV;
-
-	return 0;
-}
-#else
-static inline int da9055_regulator_dt_init(struct platform_device *pdev,
-				       struct da9055_regulator *regulator,
-				       struct regulator_config *config,
-				       int regid)
-{
-	return -ENODEV;
-}
-#endif /* CONFIG_OF */
-
 static int da9055_regulator_probe(struct platform_device *pdev)
 {
 	struct regulator_config config = { };
@@ -580,18 +527,12 @@ static int da9055_regulator_probe(struct platform_device *pdev)
 	}
 
 	regulator->da9055 = da9055;
-	config.dev = &pdev->dev;
+	config.dev = da9055->dev;
 	config.driver_data = regulator;
 	config.regmap = da9055->regmap;
 
-	if (pdata) {
+	if (pdata)
 		config.init_data = pdata->regulators[pdev->id];
-	} else {
-		ret = da9055_regulator_dt_init(pdev, regulator, &config,
-					       pdev->id);
-		if (ret < 0)
-			return ret;
-	}
 
 	ret = da9055_gpio_init(regulator, &config, pdata, pdev->id);
 	if (ret < 0)
diff --git a/drivers/regulator/da9062-regulator.c b/drivers/regulator/da9062-regulator.c
index b064d8a19d4c..a02e0488410f 100644
--- a/drivers/regulator/da9062-regulator.c
+++ b/drivers/regulator/da9062-regulator.c
@@ -1,17 +1,8 @@
-/*
- * Regulator device driver for DA9061 and DA9062.
- * Copyright (C) 2015-2017  Dialog Semiconductor
- *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of the GNU General Public License
- * as published by the Free Software Foundation; either version 2
- * of the License, or (at your option) any later version.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- */
+// SPDX-License-Identifier: GPL-2.0+
+//
+// Regulator device driver for DA9061 and DA9062.
+// Copyright (C) 2015-2017  Dialog Semiconductor
+
 #include <linux/kernel.h>
 #include <linux/module.h>
 #include <linux/init.h>
@@ -53,16 +44,12 @@ enum {
 /* Regulator capabilities and registers description */
 struct da9062_regulator_info {
 	struct regulator_desc desc;
-	/* Current limiting */
-	unsigned int n_current_limits;
-	const int *current_limits;
 	/* Main register fields */
 	struct reg_field mode;
 	struct reg_field suspend;
 	struct reg_field sleep;
 	struct reg_field suspend_sleep;
 	unsigned int suspend_vsel_reg;
-	struct reg_field ilimit;
 	/* Event detection bit */
 	struct reg_field oc_event;
 };
@@ -78,7 +65,6 @@ struct da9062_regulator {
 	struct regmap_field			*suspend;
 	struct regmap_field			*sleep;
 	struct regmap_field			*suspend_sleep;
-	struct regmap_field			*ilimit;
 };
 
 /* Encapsulates all information for the regulators driver */
@@ -104,7 +90,7 @@ enum {
  * - DA9062_ID_[BUCK1|BUCK2|BUCK4]
  * Entry indexes corresponds to register values.
  */
-static const int da9062_buck_a_limits[] = {
+static const unsigned int da9062_buck_a_limits[] = {
 	 500000,  600000,  700000,  800000,  900000, 1000000, 1100000, 1200000,
 	1300000, 1400000, 1500000, 1600000, 1700000, 1800000, 1900000, 2000000
 };
@@ -114,44 +100,11 @@ static const int da9062_buck_a_limits[] = {
  * - DA9062_ID_BUCK3
  * Entry indexes corresponds to register values.
  */
-static const int da9062_buck_b_limits[] = {
+static const unsigned int da9062_buck_b_limits[] = {
 	1500000, 1600000, 1700000, 1800000, 1900000, 2000000, 2100000, 2200000,
 	2300000, 2400000, 2500000, 2600000, 2700000, 2800000, 2900000, 3000000
 };
 
-static int da9062_set_current_limit(struct regulator_dev *rdev,
-				    int min_ua, int max_ua)
-{
-	struct da9062_regulator *regl = rdev_get_drvdata(rdev);
-	const struct da9062_regulator_info *rinfo = regl->info;
-	int n, tval;
-
-	for (n = rinfo->n_current_limits - 1; n >= 0; n--) {
-		tval = rinfo->current_limits[n];
-		if (tval >= min_ua && tval <= max_ua)
-			return regmap_field_write(regl->ilimit, n);
-	}
-
-	return -EINVAL;
-}
-
-static int da9062_get_current_limit(struct regulator_dev *rdev)
-{
-	struct da9062_regulator *regl = rdev_get_drvdata(rdev);
-	const struct da9062_regulator_info *rinfo = regl->info;
-	unsigned int sel;
-	int ret;
-
-	ret = regmap_field_read(regl->ilimit, &sel);
-	if (ret < 0)
-		return ret;
-
-	if (sel >= rinfo->n_current_limits)
-		sel = rinfo->n_current_limits - 1;
-
-	return rinfo->current_limits[sel];
-}
-
 static int da9062_buck_set_mode(struct regulator_dev *rdev, unsigned mode)
 {
 	struct da9062_regulator *regl = rdev_get_drvdata(rdev);
@@ -395,8 +348,8 @@ static const struct regulator_ops da9062_buck_ops = {
 	.get_voltage_sel	= regulator_get_voltage_sel_regmap,
 	.set_voltage_sel	= regulator_set_voltage_sel_regmap,
 	.list_voltage		= regulator_list_voltage_linear,
-	.set_current_limit	= da9062_set_current_limit,
-	.get_current_limit	= da9062_get_current_limit,
+	.set_current_limit	= regulator_set_current_limit_regmap,
+	.get_current_limit	= regulator_get_current_limit_regmap,
 	.set_mode		= da9062_buck_set_mode,
 	.get_mode		= da9062_buck_get_mode,
 	.get_status		= da9062_buck_get_status,
@@ -433,8 +386,10 @@ static const struct da9062_regulator_info local_da9061_regulator_info[] = {
 		.desc.min_uV = (300) * 1000,
 		.desc.uV_step = (10) * 1000,
 		.desc.n_voltages = ((1570) - (300))/(10) + 1,
-		.current_limits = da9062_buck_a_limits,
-		.n_current_limits = ARRAY_SIZE(da9062_buck_a_limits),
+		.desc.curr_table = da9062_buck_a_limits,
+		.desc.n_current_limits = ARRAY_SIZE(da9062_buck_a_limits),
+		.desc.csel_reg = DA9062AA_BUCK_ILIM_C,
+		.desc.csel_mask = DA9062AA_BUCK1_ILIM_MASK,
 		.desc.enable_reg = DA9062AA_BUCK1_CONT,
 		.desc.enable_mask = DA9062AA_BUCK1_EN_MASK,
 		.desc.vsel_reg = DA9062AA_VBUCK1_A,
@@ -457,10 +412,6 @@ static const struct da9062_regulator_info local_da9061_regulator_info[] = {
 			__builtin_ffs((int)DA9062AA_VBUCK1_SEL_MASK) - 1,
 			sizeof(unsigned int) * 8 -
 			__builtin_clz((DA9062AA_VBUCK1_SEL_MASK)) - 1),
-		.ilimit = REG_FIELD(DA9062AA_BUCK_ILIM_C,
-			__builtin_ffs((int)DA9062AA_BUCK1_ILIM_MASK) - 1,
-			sizeof(unsigned int) * 8 -
-			__builtin_clz((DA9062AA_BUCK1_ILIM_MASK)) - 1),
 	},
 	{
 		.desc.id = DA9061_ID_BUCK2,
@@ -471,8 +422,10 @@ static const struct da9062_regulator_info local_da9061_regulator_info[] = {
 		.desc.min_uV = (800) * 1000,
 		.desc.uV_step = (20) * 1000,
 		.desc.n_voltages = ((3340) - (800))/(20) + 1,
-		.current_limits = da9062_buck_b_limits,
-		.n_current_limits = ARRAY_SIZE(da9062_buck_b_limits),
+		.desc.curr_table = da9062_buck_b_limits,
+		.desc.n_current_limits = ARRAY_SIZE(da9062_buck_b_limits),
+		.desc.csel_reg = DA9062AA_BUCK_ILIM_A,
+		.desc.csel_mask = DA9062AA_BUCK3_ILIM_MASK,
 		.desc.enable_reg = DA9062AA_BUCK3_CONT,
 		.desc.enable_mask = DA9062AA_BUCK3_EN_MASK,
 		.desc.vsel_reg = DA9062AA_VBUCK3_A,
@@ -495,10 +448,6 @@ static const struct da9062_regulator_info local_da9061_regulator_info[] = {
 			__builtin_ffs((int)DA9062AA_VBUCK3_SEL_MASK) - 1,
 			sizeof(unsigned int) * 8 -
 			__builtin_clz((DA9062AA_VBUCK3_SEL_MASK)) - 1),
-		.ilimit = REG_FIELD(DA9062AA_BUCK_ILIM_A,
-			__builtin_ffs((int)DA9062AA_BUCK3_ILIM_MASK) - 1,
-			sizeof(unsigned int) * 8 -
-			__builtin_clz((DA9062AA_BUCK3_ILIM_MASK)) - 1),
 	},
 	{
 		.desc.id = DA9061_ID_BUCK3,
@@ -509,8 +458,10 @@ static const struct da9062_regulator_info local_da9061_regulator_info[] = {
 		.desc.min_uV = (530) * 1000,
 		.desc.uV_step = (10) * 1000,
 		.desc.n_voltages = ((1800) - (530))/(10) + 1,
-		.current_limits = da9062_buck_a_limits,
-		.n_current_limits = ARRAY_SIZE(da9062_buck_a_limits),
+		.desc.curr_table = da9062_buck_a_limits,
+		.desc.n_current_limits = ARRAY_SIZE(da9062_buck_a_limits),
+		.desc.csel_reg = DA9062AA_BUCK_ILIM_B,
+		.desc.csel_mask = DA9062AA_BUCK4_ILIM_MASK,
 		.desc.enable_reg = DA9062AA_BUCK4_CONT,
 		.desc.enable_mask = DA9062AA_BUCK4_EN_MASK,
 		.desc.vsel_reg = DA9062AA_VBUCK4_A,
@@ -533,10 +484,6 @@ static const struct da9062_regulator_info local_da9061_regulator_info[] = {
 			__builtin_ffs((int)DA9062AA_VBUCK4_SEL_MASK) - 1,
 			sizeof(unsigned int) * 8 -
 			__builtin_clz((DA9062AA_VBUCK4_SEL_MASK)) - 1),
-		.ilimit = REG_FIELD(DA9062AA_BUCK_ILIM_B,
-			__builtin_ffs((int)DA9062AA_BUCK4_ILIM_MASK) - 1,
-			sizeof(unsigned int) * 8 -
-			__builtin_clz((DA9062AA_BUCK4_ILIM_MASK)) - 1),
 	},
 	{
 		.desc.id = DA9061_ID_LDO1,
@@ -679,8 +626,10 @@ static const struct da9062_regulator_info local_da9062_regulator_info[] = {
 		.desc.min_uV = (300) * 1000,
 		.desc.uV_step = (10) * 1000,
 		.desc.n_voltages = ((1570) - (300))/(10) + 1,
-		.current_limits = da9062_buck_a_limits,
-		.n_current_limits = ARRAY_SIZE(da9062_buck_a_limits),
+		.desc.curr_table = da9062_buck_a_limits,
+		.desc.n_current_limits = ARRAY_SIZE(da9062_buck_a_limits),
+		.desc.csel_reg = DA9062AA_BUCK_ILIM_C,
+		.desc.csel_mask = DA9062AA_BUCK1_ILIM_MASK,
 		.desc.enable_reg = DA9062AA_BUCK1_CONT,
 		.desc.enable_mask = DA9062AA_BUCK1_EN_MASK,
 		.desc.vsel_reg = DA9062AA_VBUCK1_A,
@@ -703,10 +652,6 @@ static const struct da9062_regulator_info local_da9062_regulator_info[] = {
 			__builtin_ffs((int)DA9062AA_VBUCK1_SEL_MASK) - 1,
 			sizeof(unsigned int) * 8 -
 			__builtin_clz((DA9062AA_VBUCK1_SEL_MASK)) - 1),
-		.ilimit = REG_FIELD(DA9062AA_BUCK_ILIM_C,
-			__builtin_ffs((int)DA9062AA_BUCK1_ILIM_MASK) - 1,
-			sizeof(unsigned int) * 8 -
-			__builtin_clz((DA9062AA_BUCK1_ILIM_MASK)) - 1),
 	},
 	{
 		.desc.id = DA9062_ID_BUCK2,
@@ -717,8 +662,10 @@ static const struct da9062_regulator_info local_da9062_regulator_info[] = {
 		.desc.min_uV = (300) * 1000,
 		.desc.uV_step = (10) * 1000,
 		.desc.n_voltages = ((1570) - (300))/(10) + 1,
-		.current_limits = da9062_buck_a_limits,
-		.n_current_limits = ARRAY_SIZE(da9062_buck_a_limits),
+		.desc.curr_table = da9062_buck_a_limits,
+		.desc.n_current_limits = ARRAY_SIZE(da9062_buck_a_limits),
+		.desc.csel_reg = DA9062AA_BUCK_ILIM_C,
+		.desc.csel_mask = DA9062AA_BUCK2_ILIM_MASK,
 		.desc.enable_reg = DA9062AA_BUCK2_CONT,
 		.desc.enable_mask = DA9062AA_BUCK2_EN_MASK,
 		.desc.vsel_reg = DA9062AA_VBUCK2_A,
@@ -741,10 +688,6 @@ static const struct da9062_regulator_info local_da9062_regulator_info[] = {
 			__builtin_ffs((int)DA9062AA_VBUCK2_SEL_MASK) - 1,
 			sizeof(unsigned int) * 8 -
 			__builtin_clz((DA9062AA_VBUCK2_SEL_MASK)) - 1),
-		.ilimit = REG_FIELD(DA9062AA_BUCK_ILIM_C,
-			__builtin_ffs((int)DA9062AA_BUCK2_ILIM_MASK) - 1,
-			sizeof(unsigned int) * 8 -
-			__builtin_clz((DA9062AA_BUCK2_ILIM_MASK)) - 1),
 	},
 	{
 		.desc.id = DA9062_ID_BUCK3,
@@ -755,8 +698,10 @@ static const struct da9062_regulator_info local_da9062_regulator_info[] = {
 		.desc.min_uV = (800) * 1000,
 		.desc.uV_step = (20) * 1000,
 		.desc.n_voltages = ((3340) - (800))/(20) + 1,
-		.current_limits = da9062_buck_b_limits,
-		.n_current_limits = ARRAY_SIZE(da9062_buck_b_limits),
+		.desc.curr_table = da9062_buck_b_limits,
+		.desc.n_current_limits = ARRAY_SIZE(da9062_buck_b_limits),
+		.desc.csel_reg = DA9062AA_BUCK_ILIM_A,
+		.desc.csel_mask = DA9062AA_BUCK3_ILIM_MASK,
 		.desc.enable_reg = DA9062AA_BUCK3_CONT,
 		.desc.enable_mask = DA9062AA_BUCK3_EN_MASK,
 		.desc.vsel_reg = DA9062AA_VBUCK3_A,
@@ -779,10 +724,6 @@ static const struct da9062_regulator_info local_da9062_regulator_info[] = {
 			__builtin_ffs((int)DA9062AA_VBUCK3_SEL_MASK) - 1,
 			sizeof(unsigned int) * 8 -
 			__builtin_clz((DA9062AA_VBUCK3_SEL_MASK)) - 1),
-		.ilimit = REG_FIELD(DA9062AA_BUCK_ILIM_A,
-			__builtin_ffs((int)DA9062AA_BUCK3_ILIM_MASK) - 1,
-			sizeof(unsigned int) * 8 -
-			__builtin_clz((DA9062AA_BUCK3_ILIM_MASK)) - 1),
 	},
 	{
 		.desc.id = DA9062_ID_BUCK4,
@@ -793,8 +734,10 @@ static const struct da9062_regulator_info local_da9062_regulator_info[] = {
 		.desc.min_uV = (530) * 1000,
 		.desc.uV_step = (10) * 1000,
 		.desc.n_voltages = ((1800) - (530))/(10) + 1,
-		.current_limits = da9062_buck_a_limits,
-		.n_current_limits = ARRAY_SIZE(da9062_buck_a_limits),
+		.desc.curr_table = da9062_buck_a_limits,
+		.desc.n_current_limits = ARRAY_SIZE(da9062_buck_a_limits),
+		.desc.csel_reg = DA9062AA_BUCK_ILIM_B,
+		.desc.csel_mask = DA9062AA_BUCK4_ILIM_MASK,
 		.desc.enable_reg = DA9062AA_BUCK4_CONT,
 		.desc.enable_mask = DA9062AA_BUCK4_EN_MASK,
 		.desc.vsel_reg = DA9062AA_VBUCK4_A,
@@ -817,10 +760,6 @@ static const struct da9062_regulator_info local_da9062_regulator_info[] = {
 			__builtin_ffs((int)DA9062AA_VBUCK4_SEL_MASK) - 1,
 			sizeof(unsigned int) * 8 -
 			__builtin_clz((DA9062AA_VBUCK4_SEL_MASK)) - 1),
-		.ilimit = REG_FIELD(DA9062AA_BUCK_ILIM_B,
-			__builtin_ffs((int)DA9062AA_BUCK4_ILIM_MASK) - 1,
-			sizeof(unsigned int) * 8 -
-			__builtin_clz((DA9062AA_BUCK4_ILIM_MASK)) - 1),
 	},
 	{
 		.desc.id = DA9062_ID_LDO1,
@@ -974,8 +913,10 @@ static irqreturn_t da9062_ldo_lim_event(int irq, void *data)
 			continue;
 
 		if (BIT(regl->info->oc_event.lsb) & bits) {
+			regulator_lock(regl->rdev);
 			regulator_notifier_call_chain(regl->rdev,
 					REGULATOR_EVENT_OVER_CURRENT, NULL);
+			regulator_unlock(regl->rdev);
 			handled = IRQ_HANDLED;
 		}
 	}
@@ -1063,15 +1004,6 @@ static int da9062_regulator_probe(struct platform_device *pdev)
 				return PTR_ERR(regl->suspend_sleep);
 		}
 
-		if (regl->info->ilimit.reg) {
-			regl->ilimit = devm_regmap_field_alloc(
-					&pdev->dev,
-					chip->regmap,
-					regl->info->ilimit);
-			if (IS_ERR(regl->ilimit))
-				return PTR_ERR(regl->ilimit);
-		}
-
 		/* Register regulator */
 		memset(&config, 0, sizeof(config));
 		config.dev = chip->dev;
diff --git a/drivers/regulator/da9063-regulator.c b/drivers/regulator/da9063-regulator.c
index 2b0c7a85306a..6f9ce1a6e44d 100644
--- a/drivers/regulator/da9063-regulator.c
+++ b/drivers/regulator/da9063-regulator.c
@@ -1,18 +1,12 @@
+// SPDX-License-Identifier: GPL-2.0+
+//
+// Regulator driver for DA9063 PMIC series
+//
+// Copyright 2012 Dialog Semiconductors Ltd.
+// Copyright 2013 Philipp Zabel, Pengutronix
+//
+// Author: Krystian Garbaciak <krystian.garbaciak@diasemi.com>
 
-/*
- * Regulator driver for DA9063 PMIC series
- *
- * Copyright 2012 Dialog Semiconductors Ltd.
- * Copyright 2013 Philipp Zabel, Pengutronix
- *
- * Author: Krystian Garbaciak <krystian.garbaciak@diasemi.com>
- *
- *  This program is free software; you can redistribute  it and/or modify it
- *  under  the terms of  the GNU General  Public License as published by the
- *  Free Software Foundation;  either version 2 of the  License, or (at your
- *  option) any later version.
- *
- */
 #include <linux/kernel.h>
 #include <linux/module.h>
 #include <linux/init.h>
@@ -38,17 +32,12 @@
 struct da9063_regulator_info {
 	struct regulator_desc desc;
 
-	/* Current limiting */
-	unsigned	n_current_limits;
-	const int	*current_limits;
-
 	/* DA9063 main register fields */
 	struct reg_field mode;		/* buck mode of operation */
 	struct reg_field suspend;
 	struct reg_field sleep;
 	struct reg_field suspend_sleep;
 	unsigned int suspend_vsel_reg;
-	struct reg_field ilimit;
 
 	/* DA9063 event detection bit */
 	struct reg_field oc_event;
@@ -73,15 +62,18 @@ struct da9063_regulator_info {
 	.suspend_vsel_reg = DA9063_REG_V##regl_name##_B
 
 /* Macros for voltage DC/DC converters (BUCKs) */
-#define DA9063_BUCK(chip, regl_name, min_mV, step_mV, max_mV, limits_array) \
+#define DA9063_BUCK(chip, regl_name, min_mV, step_mV, max_mV, limits_array, \
+		    creg, cmask) \
 	.desc.id = chip##_ID_##regl_name, \
 	.desc.name = __stringify(chip##_##regl_name), \
 	.desc.ops = &da9063_buck_ops, \
 	.desc.min_uV = (min_mV) * 1000, \
 	.desc.uV_step = (step_mV) * 1000, \
 	.desc.n_voltages = ((max_mV) - (min_mV))/(step_mV) + 1, \
-	.current_limits = limits_array, \
-	.n_current_limits = ARRAY_SIZE(limits_array)
+	.desc.csel_reg = (creg), \
+	.desc.csel_mask = (cmask), \
+	.desc.curr_table = limits_array, \
+	.desc.n_current_limits = ARRAY_SIZE(limits_array)
 
 #define DA9063_BUCK_COMMON_FIELDS(regl_name) \
 	.desc.enable_reg = DA9063_REG_##regl_name##_CONT, \
@@ -112,7 +104,6 @@ struct da9063_regulator {
 	struct regmap_field			*suspend;
 	struct regmap_field			*sleep;
 	struct regmap_field			*suspend_sleep;
-	struct regmap_field			*ilimit;
 };
 
 /* Encapsulates all information for the regulators driver */
@@ -134,65 +125,32 @@ enum {
 
 /* Current limits array (in uA) for BCORE1, BCORE2, BPRO.
    Entry indexes corresponds to register values. */
-static const int da9063_buck_a_limits[] = {
+static const unsigned int da9063_buck_a_limits[] = {
 	 500000,  600000,  700000,  800000,  900000, 1000000, 1100000, 1200000,
 	1300000, 1400000, 1500000, 1600000, 1700000, 1800000, 1900000, 2000000
 };
 
 /* Current limits array (in uA) for BMEM, BIO, BPERI.
    Entry indexes corresponds to register values. */
-static const int da9063_buck_b_limits[] = {
+static const unsigned int da9063_buck_b_limits[] = {
 	1500000, 1600000, 1700000, 1800000, 1900000, 2000000, 2100000, 2200000,
 	2300000, 2400000, 2500000, 2600000, 2700000, 2800000, 2900000, 3000000
 };
 
 /* Current limits array (in uA) for merged BCORE1 and BCORE2.
    Entry indexes corresponds to register values. */
-static const int da9063_bcores_merged_limits[] = {
+static const unsigned int da9063_bcores_merged_limits[] = {
 	1000000, 1200000, 1400000, 1600000, 1800000, 2000000, 2200000, 2400000,
 	2600000, 2800000, 3000000, 3200000, 3400000, 3600000, 3800000, 4000000
 };
 
 /* Current limits array (in uA) for merged BMEM and BIO.
    Entry indexes corresponds to register values. */
-static const int da9063_bmem_bio_merged_limits[] = {
+static const unsigned int da9063_bmem_bio_merged_limits[] = {
 	3000000, 3200000, 3400000, 3600000, 3800000, 4000000, 4200000, 4400000,
 	4600000, 4800000, 5000000, 5200000, 5400000, 5600000, 5800000, 6000000
 };
 
-static int da9063_set_current_limit(struct regulator_dev *rdev,
-							int min_uA, int max_uA)
-{
-	struct da9063_regulator *regl = rdev_get_drvdata(rdev);
-	const struct da9063_regulator_info *rinfo = regl->info;
-	int n, tval;
-
-	for (n = rinfo->n_current_limits - 1; n >= 0; n--) {
-		tval = rinfo->current_limits[n];
-		if (tval >= min_uA && tval <= max_uA)
-			return regmap_field_write(regl->ilimit, n);
-	}
-
-	return -EINVAL;
-}
-
-static int da9063_get_current_limit(struct regulator_dev *rdev)
-{
-	struct da9063_regulator *regl = rdev_get_drvdata(rdev);
-	const struct da9063_regulator_info *rinfo = regl->info;
-	unsigned int sel;
-	int ret;
-
-	ret = regmap_field_read(regl->ilimit, &sel);
-	if (ret < 0)
-		return ret;
-
-	if (sel >= rinfo->n_current_limits)
-		sel = rinfo->n_current_limits - 1;
-
-	return rinfo->current_limits[sel];
-}
-
 static int da9063_buck_set_mode(struct regulator_dev *rdev, unsigned mode)
 {
 	struct da9063_regulator *regl = rdev_get_drvdata(rdev);
@@ -434,8 +392,8 @@ static const struct regulator_ops da9063_buck_ops = {
 	.get_voltage_sel	= regulator_get_voltage_sel_regmap,
 	.set_voltage_sel	= regulator_set_voltage_sel_regmap,
 	.list_voltage		= regulator_list_voltage_linear,
-	.set_current_limit	= da9063_set_current_limit,
-	.get_current_limit	= da9063_get_current_limit,
+	.set_current_limit	= regulator_set_current_limit_regmap,
+	.get_current_limit	= regulator_get_current_limit_regmap,
 	.set_mode		= da9063_buck_set_mode,
 	.get_mode		= da9063_buck_get_mode,
 	.get_status		= da9063_buck_get_status,
@@ -465,69 +423,61 @@ static const struct regulator_ops da9063_ldo_ops = {
 static const struct da9063_regulator_info da9063_regulator_info[] = {
 	{
 		DA9063_BUCK(DA9063, BCORE1, 300, 10, 1570,
-			    da9063_buck_a_limits),
+			    da9063_buck_a_limits,
+			    DA9063_REG_BUCK_ILIM_C, DA9063_BCORE1_ILIM_MASK),
 		DA9063_BUCK_COMMON_FIELDS(BCORE1),
 		.suspend = BFIELD(DA9063_REG_DVC_1, DA9063_VBCORE1_SEL),
-		.ilimit = BFIELD(DA9063_REG_BUCK_ILIM_C,
-				 DA9063_BCORE1_ILIM_MASK),
 	},
 	{
 		DA9063_BUCK(DA9063, BCORE2, 300, 10, 1570,
-			    da9063_buck_a_limits),
+			    da9063_buck_a_limits,
+			    DA9063_REG_BUCK_ILIM_C, DA9063_BCORE2_ILIM_MASK),
 		DA9063_BUCK_COMMON_FIELDS(BCORE2),
 		.suspend = BFIELD(DA9063_REG_DVC_1, DA9063_VBCORE2_SEL),
-		.ilimit = BFIELD(DA9063_REG_BUCK_ILIM_C,
-				 DA9063_BCORE2_ILIM_MASK),
 	},
 	{
 		DA9063_BUCK(DA9063, BPRO, 530, 10, 1800,
-			    da9063_buck_a_limits),
+			    da9063_buck_a_limits,
+			    DA9063_REG_BUCK_ILIM_B, DA9063_BPRO_ILIM_MASK),
 		DA9063_BUCK_COMMON_FIELDS(BPRO),
 		.suspend = BFIELD(DA9063_REG_DVC_1, DA9063_VBPRO_SEL),
-		.ilimit = BFIELD(DA9063_REG_BUCK_ILIM_B,
-				 DA9063_BPRO_ILIM_MASK),
 	},
 	{
 		DA9063_BUCK(DA9063, BMEM, 800, 20, 3340,
-			    da9063_buck_b_limits),
+			    da9063_buck_b_limits,
+			    DA9063_REG_BUCK_ILIM_A, DA9063_BMEM_ILIM_MASK),
 		DA9063_BUCK_COMMON_FIELDS(BMEM),
 		.suspend = BFIELD(DA9063_REG_DVC_1, DA9063_VBMEM_SEL),
-		.ilimit = BFIELD(DA9063_REG_BUCK_ILIM_A,
-				 DA9063_BMEM_ILIM_MASK),
 	},
 	{
 		DA9063_BUCK(DA9063, BIO, 800, 20, 3340,
-			    da9063_buck_b_limits),
+			    da9063_buck_b_limits,
+			    DA9063_REG_BUCK_ILIM_A, DA9063_BIO_ILIM_MASK),
 		DA9063_BUCK_COMMON_FIELDS(BIO),
 		.suspend = BFIELD(DA9063_REG_DVC_2, DA9063_VBIO_SEL),
-		.ilimit = BFIELD(DA9063_REG_BUCK_ILIM_A,
-				 DA9063_BIO_ILIM_MASK),
 	},
 	{
 		DA9063_BUCK(DA9063, BPERI, 800, 20, 3340,
-			    da9063_buck_b_limits),
+			    da9063_buck_b_limits,
+			    DA9063_REG_BUCK_ILIM_B, DA9063_BPERI_ILIM_MASK),
 		DA9063_BUCK_COMMON_FIELDS(BPERI),
 		.suspend = BFIELD(DA9063_REG_DVC_1, DA9063_VBPERI_SEL),
-		.ilimit = BFIELD(DA9063_REG_BUCK_ILIM_B,
-				 DA9063_BPERI_ILIM_MASK),
 	},
 	{
 		DA9063_BUCK(DA9063, BCORES_MERGED, 300, 10, 1570,
-			    da9063_bcores_merged_limits),
+			    da9063_bcores_merged_limits,
+			    DA9063_REG_BUCK_ILIM_C, DA9063_BCORE1_ILIM_MASK),
 		/* BCORES_MERGED uses the same register fields as BCORE1 */
 		DA9063_BUCK_COMMON_FIELDS(BCORE1),
 		.suspend = BFIELD(DA9063_REG_DVC_1, DA9063_VBCORE1_SEL),
-		.ilimit = BFIELD(DA9063_REG_BUCK_ILIM_C,
-				 DA9063_BCORE1_ILIM_MASK),
 	},
 	{
 		DA9063_BUCK(DA9063, BMEM_BIO_MERGED, 800, 20, 3340,
-			    da9063_bmem_bio_merged_limits),
+			    da9063_bmem_bio_merged_limits,
+			    DA9063_REG_BUCK_ILIM_A, DA9063_BMEM_ILIM_MASK),
 		/* BMEM_BIO_MERGED uses the same register fields as BMEM */
 		DA9063_BUCK_COMMON_FIELDS(BMEM),
 		.suspend = BFIELD(DA9063_REG_DVC_1, DA9063_VBMEM_SEL),
-		.ilimit = BFIELD(DA9063_REG_BUCK_ILIM_A,
-				 DA9063_BMEM_ILIM_MASK),
 	},
 	{
 		DA9063_LDO(DA9063, LDO3, 900, 20, 3440),
@@ -615,9 +565,12 @@ static irqreturn_t da9063_ldo_lim_event(int irq, void *data)
 		if (regl->info->oc_event.reg != DA9063_REG_STATUS_D)
 			continue;
 
-		if (BIT(regl->info->oc_event.lsb) & bits)
+		if (BIT(regl->info->oc_event.lsb) & bits) {
+		        regulator_lock(regl->rdev);
 			regulator_notifier_call_chain(regl->rdev,
 					REGULATOR_EVENT_OVER_CURRENT, NULL);
+		        regulator_unlock(regl->rdev);
+		}
 	}
 
 	return IRQ_HANDLED;
@@ -861,13 +814,6 @@ static int da9063_regulator_probe(struct platform_device *pdev)
 				return PTR_ERR(regl->suspend_sleep);
 		}
 
-		if (regl->info->ilimit.reg) {
-			regl->ilimit = devm_regmap_field_alloc(&pdev->dev,
-					da9063->regmap, regl->info->ilimit);
-			if (IS_ERR(regl->ilimit))
-				return PTR_ERR(regl->ilimit);
-		}
-
 		/* Register regulator */
 		memset(&config, 0, sizeof(config));
 		config.dev = &pdev->dev;
diff --git a/drivers/regulator/da9210-regulator.c b/drivers/regulator/da9210-regulator.c
index 528303771723..f9448ed50e05 100644
--- a/drivers/regulator/da9210-regulator.c
+++ b/drivers/regulator/da9210-regulator.c
@@ -1,22 +1,7 @@
-/*
- * da9210-regulator.c - Regulator device driver for DA9210
- * Copyright (C) 2013  Dialog Semiconductor Ltd.
- *
- * This library is free software; you can redistribute it and/or
- * modify it under the terms of the GNU Library General Public
- * License as published by the Free Software Foundation; either
- * version 2 of the License, or (at your option) any later version.
- *
- * This library is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
- * Library General Public License for more details.
- *
- * You should have received a copy of the GNU Library General Public
- * License along with this library; if not, write to the
- * Free Software Foundation, Inc., 51 Franklin St, Fifth Floor,
- * Boston, MA  02110-1301, USA.
- */
+// SPDX-License-Identifier: GPL-2.0+
+//
+// da9210-regulator.c - Regulator device driver for DA9210
+// Copyright (C) 2013  Dialog Semiconductor Ltd.
 
 #include <linux/err.h>
 #include <linux/i2c.h>
diff --git a/drivers/regulator/da9210-regulator.h b/drivers/regulator/da9210-regulator.h
index 749c550808b6..b1f1a607c208 100644
--- a/drivers/regulator/da9210-regulator.h
+++ b/drivers/regulator/da9210-regulator.h
@@ -1,22 +1,7 @@
-
+/* SPDX-License-Identifier: GPL-2.0+ */
 /*
  * da9210-regulator.h - Regulator definitions for DA9210
  * Copyright (C) 2013  Dialog Semiconductor Ltd.
- *
- * This library is free software; you can redistribute it and/or
- * modify it under the terms of the GNU Library General Public
- * License as published by the Free Software Foundation; either
- * version 2 of the License, or (at your option) any later version.
- *
- * This library is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
- * Library General Public License for more details.
- *
- * You should have received a copy of the GNU Library General Public
- * License along with this library; if not, write to the
- * Free Software Foundation, Inc., 51 Franklin St, Fifth Floor,
- * Boston, MA  02110-1301, USA.
  */
 
 #ifndef __DA9210_REGISTERS_H__
diff --git a/drivers/regulator/da9211-regulator.c b/drivers/regulator/da9211-regulator.c
index 109ee12d4362..da37b4ccd834 100644
--- a/drivers/regulator/da9211-regulator.c
+++ b/drivers/regulator/da9211-regulator.c
@@ -1,18 +1,8 @@
-/*
- * da9211-regulator.c - Regulator device driver for DA9211/DA9212
- * /DA9213/DA9223/DA9214/DA9224/DA9215/DA9225
- * Copyright (C) 2015  Dialog Semiconductor Ltd.
- *
- * This library is free software; you can redistribute it and/or
- * modify it under the terms of the GNU Library General Public
- * License as published by the Free Software Foundation; either
- * version 2 of the License, or (at your option) any later version.
- *
- * This library is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
- * Library General Public License for more details.
- */
+// SPDX-License-Identifier: GPL-2.0+
+//
+// da9211-regulator.c - Regulator device driver for DA9211/DA9212
+// /DA9213/DA9223/DA9214/DA9224/DA9215/DA9225
+// Copyright (C) 2015  Dialog Semiconductor Ltd.
 
 #include <linux/err.h>
 #include <linux/i2c.h>
@@ -322,8 +312,10 @@ static irqreturn_t da9211_irq_handler(int irq, void *data)
 		goto error_i2c;
 
 	if (reg_val & DA9211_E_OV_CURR_A) {
+	        regulator_lock(chip->rdev[0]);
 		regulator_notifier_call_chain(chip->rdev[0],
 			REGULATOR_EVENT_OVER_CURRENT, NULL);
+	        regulator_unlock(chip->rdev[0]);
 
 		err = regmap_write(chip->regmap, DA9211_REG_EVENT_B,
 			DA9211_E_OV_CURR_A);
@@ -334,8 +326,10 @@ static irqreturn_t da9211_irq_handler(int irq, void *data)
 	}
 
 	if (reg_val & DA9211_E_OV_CURR_B) {
+	        regulator_lock(chip->rdev[1]);
 		regulator_notifier_call_chain(chip->rdev[1],
 			REGULATOR_EVENT_OVER_CURRENT, NULL);
+	        regulator_unlock(chip->rdev[1]);
 
 		err = regmap_write(chip->regmap, DA9211_REG_EVENT_B,
 			DA9211_E_OV_CURR_B);
diff --git a/drivers/regulator/da9211-regulator.h b/drivers/regulator/da9211-regulator.h
index 2cb32aab4f82..1201e7cc056c 100644
--- a/drivers/regulator/da9211-regulator.h
+++ b/drivers/regulator/da9211-regulator.h
@@ -1,17 +1,8 @@
+/* SPDX-License-Identifier: GPL-2.0+ */
 /*
  * da9211-regulator.h - Regulator definitions for DA9211/DA9212
  * /DA9213/DA9223/DA9214/DA9224/DA9215/DA9225
  * Copyright (C) 2015  Dialog Semiconductor Ltd.
- *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of the GNU General Public License
- * as published by the Free Software Foundation; either version 2
- * of the License, or (at your option) any later version.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
  */
 
 #ifndef __DA9211_REGISTERS_H__
diff --git a/drivers/regulator/db8500-prcmu.c b/drivers/regulator/db8500-prcmu.c
index 7cec535cf0bc..eb317663f875 100644
--- a/drivers/regulator/db8500-prcmu.c
+++ b/drivers/regulator/db8500-prcmu.c
@@ -75,7 +75,7 @@ static int db8500_regulator_is_enabled(struct regulator_dev *rdev)
 }
 
 /* db8500 regulator operations */
-static struct regulator_ops db8500_regulator_ops = {
+static const struct regulator_ops db8500_regulator_ops = {
 	.enable			= db8500_regulator_enable,
 	.disable		= db8500_regulator_disable,
 	.is_enabled		= db8500_regulator_is_enabled,
@@ -200,7 +200,7 @@ static int db8500_regulator_switch_is_enabled(struct regulator_dev *rdev)
 	return info->is_enabled;
 }
 
-static struct regulator_ops db8500_regulator_switch_ops = {
+static const struct regulator_ops db8500_regulator_switch_ops = {
 	.enable			= db8500_regulator_switch_enable,
 	.disable		= db8500_regulator_switch_disable,
 	.is_enabled		= db8500_regulator_switch_is_enabled,
@@ -214,6 +214,7 @@ dbx500_regulator_info[DB8500_NUM_REGULATORS] = {
 	[DB8500_REGULATOR_VAPE] = {
 		.desc = {
 			.name	= "db8500-vape",
+			.of_match = of_match_ptr("db8500_vape"),
 			.id	= DB8500_REGULATOR_VAPE,
 			.ops	= &db8500_regulator_ops,
 			.type	= REGULATOR_VOLTAGE,
@@ -223,6 +224,7 @@ dbx500_regulator_info[DB8500_NUM_REGULATORS] = {
 	[DB8500_REGULATOR_VARM] = {
 		.desc = {
 			.name	= "db8500-varm",
+			.of_match = of_match_ptr("db8500_varm"),
 			.id	= DB8500_REGULATOR_VARM,
 			.ops	= &db8500_regulator_ops,
 			.type	= REGULATOR_VOLTAGE,
@@ -232,6 +234,7 @@ dbx500_regulator_info[DB8500_NUM_REGULATORS] = {
 	[DB8500_REGULATOR_VMODEM] = {
 		.desc = {
 			.name	= "db8500-vmodem",
+			.of_match = of_match_ptr("db8500_vmodem"),
 			.id	= DB8500_REGULATOR_VMODEM,
 			.ops	= &db8500_regulator_ops,
 			.type	= REGULATOR_VOLTAGE,
@@ -241,6 +244,7 @@ dbx500_regulator_info[DB8500_NUM_REGULATORS] = {
 	[DB8500_REGULATOR_VPLL] = {
 		.desc = {
 			.name	= "db8500-vpll",
+			.of_match = of_match_ptr("db8500_vpll"),
 			.id	= DB8500_REGULATOR_VPLL,
 			.ops	= &db8500_regulator_ops,
 			.type	= REGULATOR_VOLTAGE,
@@ -250,6 +254,7 @@ dbx500_regulator_info[DB8500_NUM_REGULATORS] = {
 	[DB8500_REGULATOR_VSMPS1] = {
 		.desc = {
 			.name	= "db8500-vsmps1",
+			.of_match = of_match_ptr("db8500_vsmps1"),
 			.id	= DB8500_REGULATOR_VSMPS1,
 			.ops	= &db8500_regulator_ops,
 			.type	= REGULATOR_VOLTAGE,
@@ -259,6 +264,7 @@ dbx500_regulator_info[DB8500_NUM_REGULATORS] = {
 	[DB8500_REGULATOR_VSMPS2] = {
 		.desc = {
 			.name	= "db8500-vsmps2",
+			.of_match = of_match_ptr("db8500_vsmps2"),
 			.id	= DB8500_REGULATOR_VSMPS2,
 			.ops	= &db8500_regulator_ops,
 			.type	= REGULATOR_VOLTAGE,
@@ -271,6 +277,7 @@ dbx500_regulator_info[DB8500_NUM_REGULATORS] = {
 	[DB8500_REGULATOR_VSMPS3] = {
 		.desc = {
 			.name	= "db8500-vsmps3",
+			.of_match = of_match_ptr("db8500_vsmps3"),
 			.id	= DB8500_REGULATOR_VSMPS3,
 			.ops	= &db8500_regulator_ops,
 			.type	= REGULATOR_VOLTAGE,
@@ -280,6 +287,7 @@ dbx500_regulator_info[DB8500_NUM_REGULATORS] = {
 	[DB8500_REGULATOR_VRF1] = {
 		.desc = {
 			.name	= "db8500-vrf1",
+			.of_match = of_match_ptr("db8500_vrf1"),
 			.id	= DB8500_REGULATOR_VRF1,
 			.ops	= &db8500_regulator_ops,
 			.type	= REGULATOR_VOLTAGE,
@@ -289,6 +297,7 @@ dbx500_regulator_info[DB8500_NUM_REGULATORS] = {
 	[DB8500_REGULATOR_SWITCH_SVAMMDSP] = {
 		.desc = {
 			.name	= "db8500-sva-mmdsp",
+			.of_match = of_match_ptr("db8500_sva_mmdsp"),
 			.id	= DB8500_REGULATOR_SWITCH_SVAMMDSP,
 			.ops	= &db8500_regulator_switch_ops,
 			.type	= REGULATOR_VOLTAGE,
@@ -299,6 +308,7 @@ dbx500_regulator_info[DB8500_NUM_REGULATORS] = {
 	[DB8500_REGULATOR_SWITCH_SVAMMDSPRET] = {
 		.desc = {
 			.name	= "db8500-sva-mmdsp-ret",
+			.of_match = of_match_ptr("db8500_sva_mmdsp_ret"),
 			.id	= DB8500_REGULATOR_SWITCH_SVAMMDSPRET,
 			.ops	= &db8500_regulator_switch_ops,
 			.type	= REGULATOR_VOLTAGE,
@@ -310,6 +320,7 @@ dbx500_regulator_info[DB8500_NUM_REGULATORS] = {
 	[DB8500_REGULATOR_SWITCH_SVAPIPE] = {
 		.desc = {
 			.name	= "db8500-sva-pipe",
+			.of_match = of_match_ptr("db8500_sva_pipe"),
 			.id	= DB8500_REGULATOR_SWITCH_SVAPIPE,
 			.ops	= &db8500_regulator_switch_ops,
 			.type	= REGULATOR_VOLTAGE,
@@ -320,6 +331,7 @@ dbx500_regulator_info[DB8500_NUM_REGULATORS] = {
 	[DB8500_REGULATOR_SWITCH_SIAMMDSP] = {
 		.desc = {
 			.name	= "db8500-sia-mmdsp",
+			.of_match = of_match_ptr("db8500_sia_mmdsp"),
 			.id	= DB8500_REGULATOR_SWITCH_SIAMMDSP,
 			.ops	= &db8500_regulator_switch_ops,
 			.type	= REGULATOR_VOLTAGE,
@@ -330,6 +342,7 @@ dbx500_regulator_info[DB8500_NUM_REGULATORS] = {
 	[DB8500_REGULATOR_SWITCH_SIAMMDSPRET] = {
 		.desc = {
 			.name	= "db8500-sia-mmdsp-ret",
+			.of_match = of_match_ptr("db8500_sia_mmdsp_ret"),
 			.id	= DB8500_REGULATOR_SWITCH_SIAMMDSPRET,
 			.ops	= &db8500_regulator_switch_ops,
 			.type	= REGULATOR_VOLTAGE,
@@ -341,6 +354,7 @@ dbx500_regulator_info[DB8500_NUM_REGULATORS] = {
 	[DB8500_REGULATOR_SWITCH_SIAPIPE] = {
 		.desc = {
 			.name	= "db8500-sia-pipe",
+			.of_match = of_match_ptr("db8500_sia_pipe"),
 			.id	= DB8500_REGULATOR_SWITCH_SIAPIPE,
 			.ops	= &db8500_regulator_switch_ops,
 			.type	= REGULATOR_VOLTAGE,
@@ -351,6 +365,7 @@ dbx500_regulator_info[DB8500_NUM_REGULATORS] = {
 	[DB8500_REGULATOR_SWITCH_SGA] = {
 		.desc = {
 			.name	= "db8500-sga",
+			.of_match = of_match_ptr("db8500_sga"),
 			.id	= DB8500_REGULATOR_SWITCH_SGA,
 			.ops	= &db8500_regulator_switch_ops,
 			.type	= REGULATOR_VOLTAGE,
@@ -361,6 +376,7 @@ dbx500_regulator_info[DB8500_NUM_REGULATORS] = {
 	[DB8500_REGULATOR_SWITCH_B2R2_MCDE] = {
 		.desc = {
 			.name	= "db8500-b2r2-mcde",
+			.of_match = of_match_ptr("db8500_b2r2_mcde"),
 			.id	= DB8500_REGULATOR_SWITCH_B2R2_MCDE,
 			.ops	= &db8500_regulator_switch_ops,
 			.type	= REGULATOR_VOLTAGE,
@@ -371,6 +387,7 @@ dbx500_regulator_info[DB8500_NUM_REGULATORS] = {
 	[DB8500_REGULATOR_SWITCH_ESRAM12] = {
 		.desc = {
 			.name	= "db8500-esram12",
+			.of_match = of_match_ptr("db8500_esram12"),
 			.id	= DB8500_REGULATOR_SWITCH_ESRAM12,
 			.ops	= &db8500_regulator_switch_ops,
 			.type	= REGULATOR_VOLTAGE,
@@ -382,6 +399,7 @@ dbx500_regulator_info[DB8500_NUM_REGULATORS] = {
 	[DB8500_REGULATOR_SWITCH_ESRAM12RET] = {
 		.desc = {
 			.name	= "db8500-esram12-ret",
+			.of_match = of_match_ptr("db8500_esram12_ret"),
 			.id	= DB8500_REGULATOR_SWITCH_ESRAM12RET,
 			.ops	= &db8500_regulator_switch_ops,
 			.type	= REGULATOR_VOLTAGE,
@@ -393,6 +411,7 @@ dbx500_regulator_info[DB8500_NUM_REGULATORS] = {
 	[DB8500_REGULATOR_SWITCH_ESRAM34] = {
 		.desc = {
 			.name	= "db8500-esram34",
+			.of_match = of_match_ptr("db8500_esram34"),
 			.id	= DB8500_REGULATOR_SWITCH_ESRAM34,
 			.ops	= &db8500_regulator_switch_ops,
 			.type	= REGULATOR_VOLTAGE,
@@ -404,6 +423,7 @@ dbx500_regulator_info[DB8500_NUM_REGULATORS] = {
 	[DB8500_REGULATOR_SWITCH_ESRAM34RET] = {
 		.desc = {
 			.name	= "db8500-esram34-ret",
+			.of_match = of_match_ptr("db8500_esram34_ret"),
 			.id	= DB8500_REGULATOR_SWITCH_ESRAM34RET,
 			.ops	= &db8500_regulator_switch_ops,
 			.type	= REGULATOR_VOLTAGE,
@@ -414,113 +434,38 @@ dbx500_regulator_info[DB8500_NUM_REGULATORS] = {
 	},
 };
 
-static int db8500_regulator_register(struct platform_device *pdev,
-					struct regulator_init_data *init_data,
-					int id,
-					struct device_node *np)
+static int db8500_regulator_probe(struct platform_device *pdev)
 {
+	struct regulator_init_data *db8500_init_data;
 	struct dbx500_regulator_info *info;
 	struct regulator_config config = { };
-	int err;
-
-	/* assign per-regulator data */
-	info = &dbx500_regulator_info[id];
-	info->dev = &pdev->dev;
-
-	config.dev = &pdev->dev;
-	config.init_data = init_data;
-	config.driver_data = info;
-	config.of_node = np;
-
-	/* register with the regulator framework */
-	info->rdev = devm_regulator_register(&pdev->dev, &info->desc, &config);
-	if (IS_ERR(info->rdev)) {
-		err = PTR_ERR(info->rdev);
-		dev_err(&pdev->dev, "failed to register %s: err %i\n",
-			info->desc.name, err);
-		return err;
-	}
-
-	dev_dbg(rdev_get_dev(info->rdev),
-		"regulator-%s-probed\n", info->desc.name);
+	struct regulator_dev *rdev;
+	int err, i;
 
-	return 0;
-}
-
-static struct of_regulator_match db8500_regulator_matches[] = {
-	{ .name	= "db8500_vape",          .driver_data = (void *) DB8500_REGULATOR_VAPE, },
-	{ .name	= "db8500_varm",          .driver_data = (void *) DB8500_REGULATOR_VARM, },
-	{ .name	= "db8500_vmodem",        .driver_data = (void *) DB8500_REGULATOR_VMODEM, },
-	{ .name	= "db8500_vpll",          .driver_data = (void *) DB8500_REGULATOR_VPLL, },
-	{ .name	= "db8500_vsmps1",        .driver_data = (void *) DB8500_REGULATOR_VSMPS1, },
-	{ .name	= "db8500_vsmps2",        .driver_data = (void *) DB8500_REGULATOR_VSMPS2, },
-	{ .name	= "db8500_vsmps3",        .driver_data = (void *) DB8500_REGULATOR_VSMPS3, },
-	{ .name	= "db8500_vrf1",          .driver_data = (void *) DB8500_REGULATOR_VRF1, },
-	{ .name	= "db8500_sva_mmdsp",     .driver_data = (void *) DB8500_REGULATOR_SWITCH_SVAMMDSP, },
-	{ .name	= "db8500_sva_mmdsp_ret", .driver_data = (void *) DB8500_REGULATOR_SWITCH_SVAMMDSPRET, },
-	{ .name	= "db8500_sva_pipe",      .driver_data = (void *) DB8500_REGULATOR_SWITCH_SVAPIPE, },
-	{ .name	= "db8500_sia_mmdsp",     .driver_data = (void *) DB8500_REGULATOR_SWITCH_SIAMMDSP, },
-	{ .name	= "db8500_sia_mmdsp_ret", .driver_data = (void *) DB8500_REGULATOR_SWITCH_SIAMMDSPRET, },
-	{ .name	= "db8500_sia_pipe",      .driver_data = (void *) DB8500_REGULATOR_SWITCH_SIAPIPE, },
-	{ .name	= "db8500_sga",           .driver_data = (void *) DB8500_REGULATOR_SWITCH_SGA, },
-	{ .name	= "db8500_b2r2_mcde",     .driver_data = (void *) DB8500_REGULATOR_SWITCH_B2R2_MCDE, },
-	{ .name	= "db8500_esram12",       .driver_data = (void *) DB8500_REGULATOR_SWITCH_ESRAM12, },
-	{ .name	= "db8500_esram12_ret",   .driver_data = (void *) DB8500_REGULATOR_SWITCH_ESRAM12RET, },
-	{ .name	= "db8500_esram34",       .driver_data = (void *) DB8500_REGULATOR_SWITCH_ESRAM34, },
-	{ .name	= "db8500_esram34_ret",   .driver_data = (void *) DB8500_REGULATOR_SWITCH_ESRAM34RET, },
-};
-
-static int
-db8500_regulator_of_probe(struct platform_device *pdev,
-			struct device_node *np)
-{
-	int i, err;
+	db8500_init_data = dev_get_platdata(&pdev->dev);
 
 	for (i = 0; i < ARRAY_SIZE(dbx500_regulator_info); i++) {
-		err = db8500_regulator_register(
-			pdev, db8500_regulator_matches[i].init_data,
-			i, db8500_regulator_matches[i].of_node);
-		if (err)
+		/* assign per-regulator data */
+		info = &dbx500_regulator_info[i];
+
+		config.driver_data = info;
+		config.dev = &pdev->dev;
+		if (db8500_init_data)
+			config.init_data = &db8500_init_data[i];
+
+		rdev = devm_regulator_register(&pdev->dev, &info->desc,
+					       &config);
+		if (IS_ERR(rdev)) {
+			err = PTR_ERR(rdev);
+			dev_err(&pdev->dev, "failed to register %s: err %i\n",
+				info->desc.name, err);
 			return err;
-	}
-
-	return 0;
-}
-
-static int db8500_regulator_probe(struct platform_device *pdev)
-{
-	struct regulator_init_data *db8500_init_data =
-					dev_get_platdata(&pdev->dev);
-	struct device_node *np = pdev->dev.of_node;
-	int i, err;
-
-	/* register all regulators */
-	if (np) {
-		err = of_regulator_match(&pdev->dev, np,
-					db8500_regulator_matches,
-					ARRAY_SIZE(db8500_regulator_matches));
-		if (err < 0) {
-			dev_err(&pdev->dev,
-				"Error parsing regulator init data: %d\n", err);
-			return err;
-		}
-
-		err = db8500_regulator_of_probe(pdev, np);
-		if (err)
-			return err;
-	} else {
-		for (i = 0; i < ARRAY_SIZE(dbx500_regulator_info); i++) {
-			err = db8500_regulator_register(pdev,
-							&db8500_init_data[i],
-							i, NULL);
-			if (err)
-				return err;
 		}
+		dev_dbg(&pdev->dev, "regulator-%s-probed\n", info->desc.name);
 	}
 
-	err = ux500_regulator_debug_init(pdev,
-					 dbx500_regulator_info,
-					 ARRAY_SIZE(dbx500_regulator_info));
+	ux500_regulator_debug_init(pdev, dbx500_regulator_info,
+				   ARRAY_SIZE(dbx500_regulator_info));
 	return 0;
 }
 
diff --git a/drivers/regulator/dbx500-prcmu.h b/drivers/regulator/dbx500-prcmu.h
index c8e51ace9f06..6e20dab611ac 100644
--- a/drivers/regulator/dbx500-prcmu.h
+++ b/drivers/regulator/dbx500-prcmu.h
@@ -15,18 +15,14 @@
 
 /**
  * struct dbx500_regulator_info - dbx500 regulator information
- * @dev: device pointer
  * @desc: regulator description
- * @rdev: regulator device pointer
  * @is_enabled: status of the regulator
  * @epod_id: id for EPOD (power domain)
  * @is_ramret: RAM retention switch for EPOD (power domain)
  *
  */
 struct dbx500_regulator_info {
-	struct device *dev;
 	struct regulator_desc desc;
-	struct regulator_dev *rdev;
 	bool is_enabled;
 	u16 epod_id;
 	bool is_ramret;
diff --git a/drivers/regulator/fan53555.c b/drivers/regulator/fan53555.c
index 771a06d1900d..dbe477da4e55 100644
--- a/drivers/regulator/fan53555.c
+++ b/drivers/regulator/fan53555.c
@@ -1,17 +1,13 @@
-/*
- * FAN53555 Fairchild Digitally Programmable TinyBuck Regulator Driver.
- *
- * Supported Part Numbers:
- * FAN53555UC00X/01X/03X/04X/05X
- *
- * Copyright (c) 2012 Marvell Technology Ltd.
- * Yunfan Zhang <yfzhang@marvell.com>
- *
- * This package is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- *
- */
+// SPDX-License-Identifier: GPL-2.0
+//
+// FAN53555 Fairchild Digitally Programmable TinyBuck Regulator Driver.
+//
+// Supported Part Numbers:
+// FAN53555UC00X/01X/03X/04X/05X
+//
+// Copyright (c) 2012 Marvell Technology Ltd.
+// Yunfan Zhang <yfzhang@marvell.com>
+
 #include <linux/module.h>
 #include <linux/param.h>
 #include <linux/err.h>
@@ -91,10 +87,8 @@ enum {
 
 struct fan53555_device_info {
 	enum fan53555_vendor vendor;
-	struct regmap *regmap;
 	struct device *dev;
 	struct regulator_desc desc;
-	struct regulator_dev *rdev;
 	struct regulator_init_data *regulator;
 	/* IC Type and Rev */
 	int chip_id;
@@ -106,8 +100,6 @@ struct fan53555_device_info {
 	unsigned int vsel_min;
 	unsigned int vsel_step;
 	unsigned int vsel_count;
-	/* Voltage slew rate limiting */
-	unsigned int slew_rate;
 	/* Mode */
 	unsigned int mode_reg;
 	unsigned int mode_mask;
@@ -125,7 +117,7 @@ static int fan53555_set_suspend_voltage(struct regulator_dev *rdev, int uV)
 	ret = regulator_map_voltage_linear(rdev, uV, uV);
 	if (ret < 0)
 		return ret;
-	ret = regmap_update_bits(di->regmap, di->sleep_reg,
+	ret = regmap_update_bits(rdev->regmap, di->sleep_reg,
 				 di->desc.vsel_mask, ret);
 	if (ret < 0)
 		return ret;
@@ -140,7 +132,7 @@ static int fan53555_set_suspend_enable(struct regulator_dev *rdev)
 {
 	struct fan53555_device_info *di = rdev_get_drvdata(rdev);
 
-	return regmap_update_bits(di->regmap, di->sleep_reg,
+	return regmap_update_bits(rdev->regmap, di->sleep_reg,
 				  VSEL_BUCK_EN, VSEL_BUCK_EN);
 }
 
@@ -148,7 +140,7 @@ static int fan53555_set_suspend_disable(struct regulator_dev *rdev)
 {
 	struct fan53555_device_info *di = rdev_get_drvdata(rdev);
 
-	return regmap_update_bits(di->regmap, di->sleep_reg,
+	return regmap_update_bits(rdev->regmap, di->sleep_reg,
 				  VSEL_BUCK_EN, 0);
 }
 
@@ -158,11 +150,11 @@ static int fan53555_set_mode(struct regulator_dev *rdev, unsigned int mode)
 
 	switch (mode) {
 	case REGULATOR_MODE_FAST:
-		regmap_update_bits(di->regmap, di->mode_reg,
+		regmap_update_bits(rdev->regmap, di->mode_reg,
 				   di->mode_mask, di->mode_mask);
 		break;
 	case REGULATOR_MODE_NORMAL:
-		regmap_update_bits(di->regmap, di->vol_reg, di->mode_mask, 0);
+		regmap_update_bits(rdev->regmap, di->vol_reg, di->mode_mask, 0);
 		break;
 	default:
 		return -EINVAL;
@@ -176,7 +168,7 @@ static unsigned int fan53555_get_mode(struct regulator_dev *rdev)
 	unsigned int val;
 	int ret = 0;
 
-	ret = regmap_read(di->regmap, di->mode_reg, &val);
+	ret = regmap_read(rdev->regmap, di->mode_reg, &val);
 	if (ret < 0)
 		return ret;
 	if (val & di->mode_mask)
@@ -213,7 +205,7 @@ static int fan53555_set_ramp(struct regulator_dev *rdev, int ramp)
 		return -EINVAL;
 	}
 
-	return regmap_update_bits(di->regmap, FAN53555_CONTROL,
+	return regmap_update_bits(rdev->regmap, FAN53555_CONTROL,
 				  CTL_SLEW_MASK, regval << CTL_SLEW_SHIFT);
 }
 
@@ -396,6 +388,7 @@ static int fan53555_regulator_register(struct fan53555_device_info *di,
 			struct regulator_config *config)
 {
 	struct regulator_desc *rdesc = &di->desc;
+	struct regulator_dev *rdev;
 
 	rdesc->name = "fan53555-reg";
 	rdesc->supply_name = "vin";
@@ -410,8 +403,8 @@ static int fan53555_regulator_register(struct fan53555_device_info *di,
 	rdesc->vsel_mask = di->vsel_count - 1;
 	rdesc->owner = THIS_MODULE;
 
-	di->rdev = devm_regulator_register(di->dev, &di->desc, config);
-	return PTR_ERR_OR_ZERO(di->rdev);
+	rdev = devm_regulator_register(di->dev, &di->desc, config);
+	return PTR_ERR_OR_ZERO(rdev);
 }
 
 static const struct regmap_config fan53555_regmap_config = {
@@ -466,6 +459,7 @@ static int fan53555_regulator_probe(struct i2c_client *client,
 	struct fan53555_device_info *di;
 	struct fan53555_platform_data *pdata;
 	struct regulator_config config = { };
+	struct regmap *regmap;
 	unsigned int val;
 	int ret;
 
@@ -502,22 +496,22 @@ static int fan53555_regulator_probe(struct i2c_client *client,
 		di->vendor = id->driver_data;
 	}
 
-	di->regmap = devm_regmap_init_i2c(client, &fan53555_regmap_config);
-	if (IS_ERR(di->regmap)) {
+	regmap = devm_regmap_init_i2c(client, &fan53555_regmap_config);
+	if (IS_ERR(regmap)) {
 		dev_err(&client->dev, "Failed to allocate regmap!\n");
-		return PTR_ERR(di->regmap);
+		return PTR_ERR(regmap);
 	}
 	di->dev = &client->dev;
 	i2c_set_clientdata(client, di);
 	/* Get chip ID */
-	ret = regmap_read(di->regmap, FAN53555_ID1, &val);
+	ret = regmap_read(regmap, FAN53555_ID1, &val);
 	if (ret < 0) {
 		dev_err(&client->dev, "Failed to get chip ID!\n");
 		return ret;
 	}
 	di->chip_id = val & DIE_ID;
 	/* Get chip revision */
-	ret = regmap_read(di->regmap, FAN53555_ID2, &val);
+	ret = regmap_read(regmap, FAN53555_ID2, &val);
 	if (ret < 0) {
 		dev_err(&client->dev, "Failed to get chip Rev!\n");
 		return ret;
@@ -534,7 +528,7 @@ static int fan53555_regulator_probe(struct i2c_client *client,
 	/* Register regulator */
 	config.dev = di->dev;
 	config.init_data = di->regulator;
-	config.regmap = di->regmap;
+	config.regmap = regmap;
 	config.driver_data = di;
 	config.of_node = np;
 
diff --git a/drivers/regulator/gpio-regulator.c b/drivers/regulator/gpio-regulator.c
index 6157001df0a4..f50d86a66138 100644
--- a/drivers/regulator/gpio-regulator.c
+++ b/drivers/regulator/gpio-regulator.c
@@ -36,7 +36,6 @@
 
 struct gpio_regulator_data {
 	struct regulator_desc desc;
-	struct regulator_dev *dev;
 
 	struct gpio_desc **gpiods;
 	int nr_gpios;
@@ -125,7 +124,7 @@ static int gpio_regulator_set_current_limit(struct regulator_dev *dev,
 	return 0;
 }
 
-static struct regulator_ops gpio_regulator_voltage_ops = {
+static const struct regulator_ops gpio_regulator_voltage_ops = {
 	.get_voltage = gpio_regulator_get_value,
 	.set_voltage = gpio_regulator_set_voltage,
 	.list_voltage = gpio_regulator_list_voltage,
@@ -221,7 +220,7 @@ of_get_gpio_regulator_config(struct device *dev, struct device_node *np,
 	return config;
 }
 
-static struct regulator_ops gpio_regulator_current_ops = {
+static const struct regulator_ops gpio_regulator_current_ops = {
 	.get_current_limit = gpio_regulator_get_value,
 	.set_current_limit = gpio_regulator_set_current_limit,
 };
@@ -233,6 +232,7 @@ static int gpio_regulator_probe(struct platform_device *pdev)
 	struct device_node *np = dev->of_node;
 	struct gpio_regulator_data *drvdata;
 	struct regulator_config cfg = { };
+	struct regulator_dev *rdev;
 	enum gpiod_flags gflags;
 	int ptr, ret, state, i;
 
@@ -326,9 +326,9 @@ static int gpio_regulator_probe(struct platform_device *pdev)
 	if (IS_ERR(cfg.ena_gpiod))
 		return PTR_ERR(cfg.ena_gpiod);
 
-	drvdata->dev = regulator_register(&drvdata->desc, &cfg);
-	if (IS_ERR(drvdata->dev)) {
-		ret = PTR_ERR(drvdata->dev);
+	rdev = devm_regulator_register(dev, &drvdata->desc, &cfg);
+	if (IS_ERR(rdev)) {
+		ret = PTR_ERR(rdev);
 		dev_err(dev, "Failed to register regulator: %d\n", ret);
 		return ret;
 	}
@@ -338,15 +338,6 @@ static int gpio_regulator_probe(struct platform_device *pdev)
 	return 0;
 }
 
-static int gpio_regulator_remove(struct platform_device *pdev)
-{
-	struct gpio_regulator_data *drvdata = platform_get_drvdata(pdev);
-
-	regulator_unregister(drvdata->dev);
-
-	return 0;
-}
-
 #if defined(CONFIG_OF)
 static const struct of_device_id regulator_gpio_of_match[] = {
 	{ .compatible = "regulator-gpio", },
@@ -357,7 +348,6 @@ MODULE_DEVICE_TABLE(of, regulator_gpio_of_match);
 
 static struct platform_driver gpio_regulator_driver = {
 	.probe		= gpio_regulator_probe,
-	.remove		= gpio_regulator_remove,
 	.driver		= {
 		.name		= "gpio-regulator",
 		.of_match_table = of_match_ptr(regulator_gpio_of_match),
diff --git a/drivers/regulator/hi6421-regulator.c b/drivers/regulator/hi6421-regulator.c
index 259c3a865ac6..5ac3d7c29725 100644
--- a/drivers/regulator/hi6421-regulator.c
+++ b/drivers/regulator/hi6421-regulator.c
@@ -1,17 +1,13 @@
-/*
- * Device driver for regulators in Hi6421 IC
- *
- * Copyright (c) <2011-2014> HiSilicon Technologies Co., Ltd.
- *              http://www.hisilicon.com
- * Copyright (c) <2013-2014> Linaro Ltd.
- *              http://www.linaro.org
- *
- * Author: Guodong Xu <guodong.xu@linaro.org>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- */
+// SPDX-License-Identifier: GPL-2.0
+//
+// Device driver for regulators in Hi6421 IC
+//
+// Copyright (c) <2011-2014> HiSilicon Technologies Co., Ltd.
+//              http://www.hisilicon.com
+// Copyright (c) <2013-2014> Linaro Ltd.
+//              http://www.linaro.org
+//
+// Author: Guodong Xu <guodong.xu@linaro.org>
 
 #include <linux/slab.h>
 #include <linux/device.h>
@@ -78,43 +74,6 @@ enum hi6421_regulator_id {
 	HI6421_NUM_REGULATORS,
 };
 
-#define HI6421_REGULATOR_OF_MATCH(_name, id)				\
-{									\
-	.name = #_name,							\
-	.driver_data = (void *) HI6421_##id,				\
-}
-
-static struct of_regulator_match hi6421_regulator_match[] = {
-	HI6421_REGULATOR_OF_MATCH(hi6421_vout0, LDO0),
-	HI6421_REGULATOR_OF_MATCH(hi6421_vout1, LDO1),
-	HI6421_REGULATOR_OF_MATCH(hi6421_vout2, LDO2),
-	HI6421_REGULATOR_OF_MATCH(hi6421_vout3, LDO3),
-	HI6421_REGULATOR_OF_MATCH(hi6421_vout4, LDO4),
-	HI6421_REGULATOR_OF_MATCH(hi6421_vout5, LDO5),
-	HI6421_REGULATOR_OF_MATCH(hi6421_vout6, LDO6),
-	HI6421_REGULATOR_OF_MATCH(hi6421_vout7, LDO7),
-	HI6421_REGULATOR_OF_MATCH(hi6421_vout8, LDO8),
-	HI6421_REGULATOR_OF_MATCH(hi6421_vout9, LDO9),
-	HI6421_REGULATOR_OF_MATCH(hi6421_vout10, LDO10),
-	HI6421_REGULATOR_OF_MATCH(hi6421_vout11, LDO11),
-	HI6421_REGULATOR_OF_MATCH(hi6421_vout12, LDO12),
-	HI6421_REGULATOR_OF_MATCH(hi6421_vout13, LDO13),
-	HI6421_REGULATOR_OF_MATCH(hi6421_vout14, LDO14),
-	HI6421_REGULATOR_OF_MATCH(hi6421_vout15, LDO15),
-	HI6421_REGULATOR_OF_MATCH(hi6421_vout16, LDO16),
-	HI6421_REGULATOR_OF_MATCH(hi6421_vout17, LDO17),
-	HI6421_REGULATOR_OF_MATCH(hi6421_vout18, LDO18),
-	HI6421_REGULATOR_OF_MATCH(hi6421_vout19, LDO19),
-	HI6421_REGULATOR_OF_MATCH(hi6421_vout20, LDO20),
-	HI6421_REGULATOR_OF_MATCH(hi6421_vout_audio, LDOAUDIO),
-	HI6421_REGULATOR_OF_MATCH(hi6421_buck0, BUCK0),
-	HI6421_REGULATOR_OF_MATCH(hi6421_buck1, BUCK1),
-	HI6421_REGULATOR_OF_MATCH(hi6421_buck2, BUCK2),
-	HI6421_REGULATOR_OF_MATCH(hi6421_buck3, BUCK3),
-	HI6421_REGULATOR_OF_MATCH(hi6421_buck4, BUCK4),
-	HI6421_REGULATOR_OF_MATCH(hi6421_buck5, BUCK5),
-};
-
 /* LDO 0, 4~7, 9~14, 16~20 have same voltage table. */
 static const unsigned int ldo_0_voltages[] = {
 	1500000, 1800000, 2400000, 2500000,
@@ -157,6 +116,7 @@ static const struct regulator_ops hi6421_buck345_ops;
 #define HI6421_LDO_ENABLE_TIME (350)
 /*
  * _id - LDO id name string
+ * _match - of match name string
  * v_table - voltage table
  * vreg - voltage select register
  * vmask - voltage select mask
@@ -166,11 +126,13 @@ static const struct regulator_ops hi6421_buck345_ops;
  * ecomask - eco mode mask
  * ecoamp - eco mode load uppler limit in uA
  */
-#define HI6421_LDO(_id, v_table, vreg, vmask, ereg, emask,		\
+#define HI6421_LDO(_id, _match, v_table, vreg, vmask, ereg, emask,	\
 		   odelay, ecomask, ecoamp)				\
 	[HI6421_##_id] = {						\
 		.desc = {						\
 			.name		= #_id,				\
+			.of_match        = of_match_ptr(#_match),	\
+			.regulators_node = of_match_ptr("regulators"),	\
 			.ops		= &hi6421_ldo_ops,		\
 			.type		= REGULATOR_VOLTAGE,		\
 			.id		= HI6421_##_id,			\
@@ -191,6 +153,7 @@ static const struct regulator_ops hi6421_buck345_ops;
 /* HI6421 LDO1~3 are linear voltage regulators at fixed uV_step
  *
  * _id - LDO id name string
+ * _match - of match name string
  * _min_uV - minimum voltage supported in uV
  * n_volt - number of votages available
  * vstep - voltage increase in each linear step in uV
@@ -202,11 +165,13 @@ static const struct regulator_ops hi6421_buck345_ops;
  * ecomask - eco mode mask
  * ecoamp - eco mode load uppler limit in uA
  */
-#define HI6421_LDO_LINEAR(_id, _min_uV, n_volt, vstep, vreg, vmask,	\
+#define HI6421_LDO_LINEAR(_id, _match, _min_uV, n_volt, vstep, vreg, vmask,\
 			  ereg, emask, odelay, ecomask, ecoamp)		\
 	[HI6421_##_id] = {						\
 		.desc = {						\
 			.name		= #_id,				\
+			.of_match        = of_match_ptr(#_match),	\
+			.regulators_node = of_match_ptr("regulators"),	\
 			.ops		= &hi6421_ldo_linear_ops,	\
 			.type		= REGULATOR_VOLTAGE,		\
 			.id		= HI6421_##_id,			\
@@ -228,6 +193,7 @@ static const struct regulator_ops hi6421_buck345_ops;
 /* HI6421 LDOAUDIO is a linear voltage regulator with two 4-step ranges
  *
  * _id - LDO id name string
+ * _match - of match name string
  * n_volt - number of votages available
  * volt_ranges - array of regulator_linear_range
  * vstep - voltage increase in each linear step in uV
@@ -239,11 +205,13 @@ static const struct regulator_ops hi6421_buck345_ops;
  * ecomask - eco mode mask
  * ecoamp - eco mode load uppler limit in uA
  */
-#define HI6421_LDO_LINEAR_RANGE(_id, n_volt, volt_ranges, vreg, vmask,	\
+#define HI6421_LDO_LINEAR_RANGE(_id, _match, n_volt, volt_ranges, vreg, vmask,\
 				ereg, emask, odelay, ecomask, ecoamp)	\
 	[HI6421_##_id] = {						\
 		.desc = {						\
 			.name		= #_id,				\
+			.of_match        = of_match_ptr(#_match),	\
+			.regulators_node = of_match_ptr("regulators"),	\
 			.ops		= &hi6421_ldo_linear_range_ops,	\
 			.type		= REGULATOR_VOLTAGE,		\
 			.id		= HI6421_##_id,			\
@@ -265,6 +233,7 @@ static const struct regulator_ops hi6421_buck345_ops;
 /* HI6421 BUCK0/1/2 are linear voltage regulators at fixed uV_step
  *
  * _id - BUCK0/1/2 id name string
+ * _match - of match name string
  * vreg - voltage select register
  * vmask - voltage select mask
  * ereg - enable register
@@ -273,11 +242,13 @@ static const struct regulator_ops hi6421_buck345_ops;
  * etime - enable time
  * odelay - off/on delay time in uS
  */
-#define HI6421_BUCK012(_id, vreg, vmask, ereg, emask, sleepmask,	\
+#define HI6421_BUCK012(_id, _match, vreg, vmask, ereg, emask, sleepmask,\
 			etime, odelay)					\
 	[HI6421_##_id] = {						\
 		.desc = {						\
 			.name		= #_id,				\
+			.of_match        = of_match_ptr(#_match),	\
+			.regulators_node = of_match_ptr("regulators"),	\
 			.ops		= &hi6421_buck012_ops,		\
 			.type		= REGULATOR_VOLTAGE,		\
 			.id		= HI6421_##_id,			\
@@ -299,6 +270,7 @@ static const struct regulator_ops hi6421_buck345_ops;
  *  that it supports SLEEP mode, so has different .ops.
  *
  * _id - LDO id name string
+ * _match - of match name string
  * v_table - voltage table
  * vreg - voltage select register
  * vmask - voltage select mask
@@ -307,11 +279,13 @@ static const struct regulator_ops hi6421_buck345_ops;
  * odelay - off/on delay time in uS
  * sleepmask - mask of sleep mode
  */
-#define HI6421_BUCK345(_id, v_table, vreg, vmask, ereg, emask,		\
+#define HI6421_BUCK345(_id, _match, v_table, vreg, vmask, ereg, emask,	\
 			odelay, sleepmask)				\
 	[HI6421_##_id] = {						\
 		.desc = {						\
 			.name		= #_id,				\
+			.of_match        = of_match_ptr(#_match),	\
+			.regulators_node = of_match_ptr("regulators"),	\
 			.ops		= &hi6421_buck345_ops,		\
 			.type		= REGULATOR_VOLTAGE,		\
 			.id		= HI6421_##_id,			\
@@ -331,59 +305,63 @@ static const struct regulator_ops hi6421_buck345_ops;
 /* HI6421 regulator information */
 static struct hi6421_regulator_info
 		hi6421_regulator_info[HI6421_NUM_REGULATORS] = {
-	HI6421_LDO(LDO0, ldo_0_voltages, 0x20, 0x07, 0x20, 0x10,
+	HI6421_LDO(LDO0, hi6421_vout0, ldo_0_voltages, 0x20, 0x07, 0x20, 0x10,
 		   10000, 0x20, 8000),
-	HI6421_LDO_LINEAR(LDO1, 1700000, 4, 100000, 0x21, 0x03, 0x21, 0x10,
-			  10000, 0x20, 5000),
-	HI6421_LDO_LINEAR(LDO2, 1050000, 8, 50000, 0x22, 0x07, 0x22, 0x10,
-			  20000, 0x20, 8000),
-	HI6421_LDO_LINEAR(LDO3, 1050000, 8, 50000, 0x23, 0x07, 0x23, 0x10,
-			  20000, 0x20, 8000),
-	HI6421_LDO(LDO4, ldo_0_voltages, 0x24, 0x07, 0x24, 0x10,
+	HI6421_LDO_LINEAR(LDO1, hi6421_vout1, 1700000, 4, 100000, 0x21, 0x03,
+			  0x21, 0x10, 10000, 0x20, 5000),
+	HI6421_LDO_LINEAR(LDO2, hi6421_vout2, 1050000, 8, 50000, 0x22, 0x07,
+			  0x22, 0x10, 20000, 0x20, 8000),
+	HI6421_LDO_LINEAR(LDO3, hi6421_vout3, 1050000, 8, 50000, 0x23, 0x07,
+			  0x23, 0x10, 20000, 0x20, 8000),
+	HI6421_LDO(LDO4, hi6421_vout4, ldo_0_voltages, 0x24, 0x07, 0x24, 0x10,
 		   20000, 0x20, 8000),
-	HI6421_LDO(LDO5, ldo_0_voltages, 0x25, 0x07, 0x25, 0x10,
+	HI6421_LDO(LDO5, hi6421_vout5, ldo_0_voltages, 0x25, 0x07, 0x25, 0x10,
 		   20000, 0x20, 8000),
-	HI6421_LDO(LDO6, ldo_0_voltages, 0x26, 0x07, 0x26, 0x10,
+	HI6421_LDO(LDO6, hi6421_vout6, ldo_0_voltages, 0x26, 0x07, 0x26, 0x10,
 		   20000, 0x20, 8000),
-	HI6421_LDO(LDO7, ldo_0_voltages, 0x27, 0x07, 0x27, 0x10,
+	HI6421_LDO(LDO7, hi6421_vout7, ldo_0_voltages, 0x27, 0x07, 0x27, 0x10,
 		   20000, 0x20, 5000),
-	HI6421_LDO(LDO8, ldo_8_voltages, 0x28, 0x07, 0x28, 0x10,
+	HI6421_LDO(LDO8, hi6421_vout8, ldo_8_voltages, 0x28, 0x07, 0x28, 0x10,
 		   20000, 0x20, 8000),
-	HI6421_LDO(LDO9, ldo_0_voltages, 0x29, 0x07, 0x29, 0x10,
+	HI6421_LDO(LDO9, hi6421_vout9, ldo_0_voltages, 0x29, 0x07, 0x29, 0x10,
 		   40000, 0x20, 8000),
-	HI6421_LDO(LDO10, ldo_0_voltages, 0x2a, 0x07, 0x2a, 0x10,
+	HI6421_LDO(LDO10, hi6421_vout10, ldo_0_voltages, 0x2a, 0x07, 0x2a, 0x10,
 		   40000, 0x20, 8000),
-	HI6421_LDO(LDO11, ldo_0_voltages, 0x2b, 0x07, 0x2b, 0x10,
+	HI6421_LDO(LDO11, hi6421_vout11, ldo_0_voltages, 0x2b, 0x07, 0x2b, 0x10,
 		   40000, 0x20, 8000),
-	HI6421_LDO(LDO12, ldo_0_voltages, 0x2c, 0x07, 0x2c, 0x10,
+	HI6421_LDO(LDO12, hi6421_vout12, ldo_0_voltages, 0x2c, 0x07, 0x2c, 0x10,
 		   40000, 0x20, 8000),
-	HI6421_LDO(LDO13, ldo_0_voltages, 0x2d, 0x07, 0x2d, 0x10,
+	HI6421_LDO(LDO13, hi6421_vout13, ldo_0_voltages, 0x2d, 0x07, 0x2d, 0x10,
 		   40000, 0x20, 8000),
-	HI6421_LDO(LDO14, ldo_0_voltages, 0x2e, 0x07, 0x2e, 0x10,
+	HI6421_LDO(LDO14, hi6421_vout14, ldo_0_voltages, 0x2e, 0x07, 0x2e, 0x10,
 		   40000, 0x20, 8000),
-	HI6421_LDO(LDO15, ldo_8_voltages, 0x2f, 0x07, 0x2f, 0x10,
+	HI6421_LDO(LDO15, hi6421_vout15, ldo_8_voltages, 0x2f, 0x07, 0x2f, 0x10,
 		   40000, 0x20, 8000),
-	HI6421_LDO(LDO16, ldo_0_voltages, 0x30, 0x07, 0x30, 0x10,
+	HI6421_LDO(LDO16, hi6421_vout16, ldo_0_voltages, 0x30, 0x07, 0x30, 0x10,
 		   40000, 0x20, 8000),
-	HI6421_LDO(LDO17, ldo_0_voltages, 0x31, 0x07, 0x31, 0x10,
+	HI6421_LDO(LDO17, hi6421_vout17, ldo_0_voltages, 0x31, 0x07, 0x31, 0x10,
 		   40000, 0x20, 8000),
-	HI6421_LDO(LDO18, ldo_0_voltages, 0x32, 0x07, 0x32, 0x10,
+	HI6421_LDO(LDO18, hi6421_vout18, ldo_0_voltages, 0x32, 0x07, 0x32, 0x10,
 		   40000, 0x20, 8000),
-	HI6421_LDO(LDO19, ldo_0_voltages, 0x33, 0x07, 0x33, 0x10,
+	HI6421_LDO(LDO19, hi6421_vout19, ldo_0_voltages, 0x33, 0x07, 0x33, 0x10,
 		   40000, 0x20, 8000),
-	HI6421_LDO(LDO20, ldo_0_voltages, 0x34, 0x07, 0x34, 0x10,
+	HI6421_LDO(LDO20, hi6421_vout20, ldo_0_voltages, 0x34, 0x07, 0x34, 0x10,
 		   40000, 0x20, 8000),
-	HI6421_LDO_LINEAR_RANGE(LDOAUDIO, 8, ldo_audio_volt_range, 0x36,
-				0x70, 0x36, 0x01, 40000, 0x02, 5000),
-	HI6421_BUCK012(BUCK0, 0x0d, 0x7f, 0x0c, 0x01, 0x10, 400, 20000),
-	HI6421_BUCK012(BUCK1, 0x0f, 0x7f, 0x0e, 0x01, 0x10, 400, 20000),
-	HI6421_BUCK012(BUCK2, 0x11, 0x7f, 0x10, 0x01, 0x10, 350, 100),
-	HI6421_BUCK345(BUCK3, buck_3_voltages, 0x13, 0x07, 0x12, 0x01,
-		       20000, 0x10),
-	HI6421_BUCK345(BUCK4, buck_4_voltages, 0x15, 0x07, 0x14, 0x01,
-		       20000, 0x10),
-	HI6421_BUCK345(BUCK5, buck_5_voltages, 0x17, 0x07, 0x16, 0x01,
-		       20000, 0x10),
+	HI6421_LDO_LINEAR_RANGE(LDOAUDIO, hi6421_vout_audio, 8,
+				ldo_audio_volt_range, 0x36, 0x70, 0x36, 0x01,
+				40000, 0x02, 5000),
+	HI6421_BUCK012(BUCK0, hi6421_buck0, 0x0d, 0x7f, 0x0c, 0x01, 0x10, 400,
+		       20000),
+	HI6421_BUCK012(BUCK1, hi6421_buck1, 0x0f, 0x7f, 0x0e, 0x01, 0x10, 400,
+		       20000),
+	HI6421_BUCK012(BUCK2, hi6421_buck2, 0x11, 0x7f, 0x10, 0x01, 0x10, 350,
+		       100),
+	HI6421_BUCK345(BUCK3, hi6421_buck3, buck_3_voltages, 0x13, 0x07, 0x12,
+		       0x01, 20000, 0x10),
+	HI6421_BUCK345(BUCK4, hi6421_buck4, buck_4_voltages, 0x15, 0x07, 0x14,
+		       0x01, 20000, 0x10),
+	HI6421_BUCK345(BUCK5, hi6421_buck5, buck_5_voltages, 0x17, 0x07, 0x16,
+		       0x01, 20000, 0x10),
 };
 
 static int hi6421_regulator_enable(struct regulator_dev *rdev)
@@ -552,42 +530,14 @@ static const struct regulator_ops hi6421_buck345_ops = {
 	.set_mode = hi6421_regulator_buck_set_mode,
 };
 
-static int hi6421_regulator_register(struct platform_device *pdev,
-				     struct regmap *rmap,
-				     struct regulator_init_data *init_data,
-				     int id, struct device_node *np)
-{
-	struct hi6421_regulator_info *info = NULL;
-	struct regulator_config config = { };
-	struct regulator_dev *rdev;
-
-	/* assign per-regulator data */
-	info = &hi6421_regulator_info[id];
-
-	config.dev = &pdev->dev;
-	config.init_data = init_data;
-	config.driver_data = info;
-	config.regmap = rmap;
-	config.of_node = np;
-
-	/* register regulator with framework */
-	rdev = devm_regulator_register(&pdev->dev, &info->desc, &config);
-	if (IS_ERR(rdev)) {
-		dev_err(&pdev->dev, "failed to register regulator %s\n",
-			info->desc.name);
-		return PTR_ERR(rdev);
-	}
-
-	return 0;
-}
-
 static int hi6421_regulator_probe(struct platform_device *pdev)
 {
-	struct device *dev = &pdev->dev;
-	struct device_node *np;
-	struct hi6421_pmic *pmic;
+	struct hi6421_pmic *pmic = dev_get_drvdata(pdev->dev.parent);
 	struct hi6421_regulator_pdata *pdata;
-	int i, ret = 0;
+	struct hi6421_regulator_info *info;
+	struct regulator_config config = { };
+	struct regulator_dev *rdev;
+	int i;
 
 	pdata = devm_kzalloc(&pdev->dev, sizeof(*pdata), GFP_KERNEL);
 	if (!pdata)
@@ -595,27 +545,21 @@ static int hi6421_regulator_probe(struct platform_device *pdev)
 	mutex_init(&pdata->lock);
 	platform_set_drvdata(pdev, pdata);
 
-	np = of_get_child_by_name(dev->parent->of_node, "regulators");
-	if (!np)
-		return -ENODEV;
-
-	ret = of_regulator_match(dev, np,
-				 hi6421_regulator_match,
-				 ARRAY_SIZE(hi6421_regulator_match));
-	of_node_put(np);
-	if (ret < 0) {
-		dev_err(dev, "Error parsing regulator init data: %d\n", ret);
-		return ret;
-	}
-
-	pmic = dev_get_drvdata(dev->parent);
-
 	for (i = 0; i < ARRAY_SIZE(hi6421_regulator_info); i++) {
-		ret = hi6421_regulator_register(pdev, pmic->regmap,
-			hi6421_regulator_match[i].init_data, i,
-			hi6421_regulator_match[i].of_node);
-		if (ret)
-			return ret;
+		/* assign per-regulator data */
+		info = &hi6421_regulator_info[i];
+
+		config.dev = pdev->dev.parent;
+		config.driver_data = info;
+		config.regmap = pmic->regmap;
+
+		rdev = devm_regulator_register(&pdev->dev, &info->desc,
+					       &config);
+		if (IS_ERR(rdev)) {
+			dev_err(&pdev->dev, "failed to register regulator %s\n",
+				info->desc.name);
+			return PTR_ERR(rdev);
+		}
 	}
 
 	return 0;
diff --git a/drivers/regulator/hi6421v530-regulator.c b/drivers/regulator/hi6421v530-regulator.c
index c09bc71538a5..06ae65199afd 100644
--- a/drivers/regulator/hi6421v530-regulator.c
+++ b/drivers/regulator/hi6421v530-regulator.c
@@ -1,18 +1,14 @@
-/*
- * Device driver for regulators in Hi6421V530 IC
- *
- * Copyright (c) <2017> HiSilicon Technologies Co., Ltd.
- *              http://www.hisilicon.com
- * Copyright (c) <2017> Linaro Ltd.
- *              http://www.linaro.org
- *
- * Author: Wang Xiaoyin <hw.wangxiaoyin@hisilicon.com>
- *         Guodong Xu <guodong.xu@linaro.org>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- */
+// SPDX-License-Identifier: GPL-2.0
+//
+// Device driver for regulators in Hi6421V530 IC
+//
+// Copyright (c) <2017> HiSilicon Technologies Co., Ltd.
+//              http://www.hisilicon.com
+// Copyright (c) <2017> Linaro Ltd.
+//              http://www.linaro.org
+//
+// Author: Wang Xiaoyin <hw.wangxiaoyin@hisilicon.com>
+//         Guodong Xu <guodong.xu@linaro.org>
 
 #include <linux/mfd/hi6421-pmic.h>
 #include <linux/module.h>
diff --git a/drivers/regulator/hi655x-regulator.c b/drivers/regulator/hi655x-regulator.c
index bba24a6fdb1e..ac2ee2030211 100644
--- a/drivers/regulator/hi655x-regulator.c
+++ b/drivers/regulator/hi655x-regulator.c
@@ -1,16 +1,12 @@
-/*
- * Device driver for regulators in Hi655x IC
- *
- * Copyright (c) 2016 Hisilicon.
- *
- * Authors:
- * Chen Feng <puck.chen@hisilicon.com>
- * Fei  Wang <w.f@huawei.com>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- */
+// SPDX-License-Identifier: GPL-2.0
+//
+// Device driver for regulators in Hi655x IC
+//
+// Copyright (c) 2016 Hisilicon.
+//
+// Authors:
+// Chen Feng <puck.chen@hisilicon.com>
+// Fei  Wang <w.f@huawei.com>
 
 #include <linux/bitops.h>
 #include <linux/device.h>
@@ -28,7 +24,6 @@
 struct hi655x_regulator {
 	unsigned int disable_reg;
 	unsigned int status_reg;
-	unsigned int ctrl_mask;
 	struct regulator_desc rdesc;
 };
 
@@ -77,22 +72,18 @@ enum hi655x_regulator_id {
 static int hi655x_is_enabled(struct regulator_dev *rdev)
 {
 	unsigned int value = 0;
-
 	struct hi655x_regulator *regulator = rdev_get_drvdata(rdev);
 
 	regmap_read(rdev->regmap, regulator->status_reg, &value);
-	return (value & BIT(regulator->ctrl_mask));
+	return (value & rdev->desc->enable_mask);
 }
 
 static int hi655x_disable(struct regulator_dev *rdev)
 {
-	int ret = 0;
-
 	struct hi655x_regulator *regulator = rdev_get_drvdata(rdev);
 
-	ret = regmap_write(rdev->regmap, regulator->disable_reg,
-			   BIT(regulator->ctrl_mask));
-	return ret;
+	return regmap_write(rdev->regmap, regulator->disable_reg,
+			    rdev->desc->enable_mask);
 }
 
 static const struct regulator_ops hi655x_regulator_ops = {
@@ -132,7 +123,6 @@ static const struct regulator_ops hi655x_ldo_linear_ops = {
 	},                                                       \
 	.disable_reg = HI655X_BUS_ADDR(dreg),                    \
 	.status_reg = HI655X_BUS_ADDR(sreg),                     \
-	.ctrl_mask = cmask,                                      \
 }
 
 #define HI655X_LDO_LINEAR(_ID, vreg, vmask, ereg, dreg,          \
@@ -155,10 +145,9 @@ static const struct regulator_ops hi655x_ldo_linear_ops = {
 	},                                                       \
 	.disable_reg = HI655X_BUS_ADDR(dreg),                    \
 	.status_reg = HI655X_BUS_ADDR(sreg),                     \
-	.ctrl_mask = cmask,                                      \
 }
 
-static struct hi655x_regulator regulators[] = {
+static const struct hi655x_regulator regulators[] = {
 	HI655X_LDO_LINEAR(LDO2, 0x72, 0x07, 0x29, 0x2a, 0x2b, 0x01,
 			  2500000, 8, 100000),
 	HI655X_LDO(LDO7, 0x78, 0x07, 0x29, 0x2a, 0x2b, 0x06, ldo7_voltages),
diff --git a/drivers/regulator/lm363x-regulator.c b/drivers/regulator/lm363x-regulator.c
index c876e161052a..e02fdd1dd092 100644
--- a/drivers/regulator/lm363x-regulator.c
+++ b/drivers/regulator/lm363x-regulator.c
@@ -48,7 +48,7 @@ static const int ldo_cont_enable_time[] = {
 static int lm363x_regulator_enable_time(struct regulator_dev *rdev)
 {
 	enum lm363x_regulator_id id = rdev_get_id(rdev);
-	u8 val, addr, mask;
+	unsigned int val, addr, mask;
 
 	switch (id) {
 	case LM3631_LDO_CONT:
@@ -71,7 +71,7 @@ static int lm363x_regulator_enable_time(struct regulator_dev *rdev)
 		return 0;
 	}
 
-	if (regmap_read(rdev->regmap, addr, (unsigned int *)&val))
+	if (regmap_read(rdev->regmap, addr, &val))
 		return -EINVAL;
 
 	val = (val & mask) >> LM3631_ENTIME_SHIFT;
@@ -82,13 +82,13 @@ static int lm363x_regulator_enable_time(struct regulator_dev *rdev)
 		return ENABLE_TIME_USEC * val;
 }
 
-static struct regulator_ops lm363x_boost_voltage_table_ops = {
+static const struct regulator_ops lm363x_boost_voltage_table_ops = {
 	.list_voltage     = regulator_list_voltage_linear,
 	.set_voltage_sel  = regulator_set_voltage_sel_regmap,
 	.get_voltage_sel  = regulator_get_voltage_sel_regmap,
 };
 
-static struct regulator_ops lm363x_regulator_voltage_table_ops = {
+static const struct regulator_ops lm363x_regulator_voltage_table_ops = {
 	.list_voltage     = regulator_list_voltage_linear,
 	.set_voltage_sel  = regulator_set_voltage_sel_regmap,
 	.get_voltage_sel  = regulator_get_voltage_sel_regmap,
diff --git a/drivers/regulator/lp8755.c b/drivers/regulator/lp8755.c
index 14fd38807134..2e16a6ab491d 100644
--- a/drivers/regulator/lp8755.c
+++ b/drivers/regulator/lp8755.c
@@ -372,10 +372,13 @@ static irqreturn_t lp8755_irq_handler(int irq, void *data)
 	for (icnt = 0; icnt < LP8755_BUCK_MAX; icnt++)
 		if ((flag0 & (0x4 << icnt))
 		    && (pchip->irqmask & (0x04 << icnt))
-		    && (pchip->rdev[icnt] != NULL))
+		    && (pchip->rdev[icnt] != NULL)) {
+			regulator_lock(pchip->rdev[icnt]);
 			regulator_notifier_call_chain(pchip->rdev[icnt],
 						      LP8755_EVENT_PWR_FAULT,
 						      NULL);
+			regulator_unlock(pchip->rdev[icnt]);
+		}
 
 	/* read flag1 register */
 	ret = lp8755_read(pchip, 0x0E, &flag1);
@@ -389,18 +392,24 @@ static irqreturn_t lp8755_irq_handler(int irq, void *data)
 	/* send OCP event to all regulator devices */
 	if ((flag1 & 0x01) && (pchip->irqmask & 0x01))
 		for (icnt = 0; icnt < LP8755_BUCK_MAX; icnt++)
-			if (pchip->rdev[icnt] != NULL)
+			if (pchip->rdev[icnt] != NULL) {
+				regulator_lock(pchip->rdev[icnt]);
 				regulator_notifier_call_chain(pchip->rdev[icnt],
 							      LP8755_EVENT_OCP,
 							      NULL);
+				regulator_unlock(pchip->rdev[icnt]);
+			}
 
 	/* send OVP event to all regulator devices */
 	if ((flag1 & 0x02) && (pchip->irqmask & 0x02))
 		for (icnt = 0; icnt < LP8755_BUCK_MAX; icnt++)
-			if (pchip->rdev[icnt] != NULL)
+			if (pchip->rdev[icnt] != NULL) {
+				regulator_lock(pchip->rdev[icnt]);
 				regulator_notifier_call_chain(pchip->rdev[icnt],
 							      LP8755_EVENT_OVP,
 							      NULL);
+				regulator_unlock(pchip->rdev[icnt]);
+			}
 	return IRQ_HANDLED;
 
 err_i2c:
diff --git a/drivers/regulator/lp87565-regulator.c b/drivers/regulator/lp87565-regulator.c
index 4ed41731a5b1..81eb4b890c0c 100644
--- a/drivers/regulator/lp87565-regulator.c
+++ b/drivers/regulator/lp87565-regulator.c
@@ -34,6 +34,10 @@
 			.ramp_delay		= _delay,		\
 			.linear_ranges		= _lr,			\
 			.n_linear_ranges	= ARRAY_SIZE(_lr),	\
+			.curr_table = lp87565_buck_uA,			\
+			.n_current_limits = ARRAY_SIZE(lp87565_buck_uA),\
+			.csel_reg = (_cr),				\
+			.csel_mask = LP87565_BUCK_CTRL_2_ILIM,		\
 		},							\
 		.ctrl2_reg = _cr,					\
 	}
@@ -102,44 +106,7 @@ static int lp87565_buck_set_ramp_delay(struct regulator_dev *rdev,
 	return 0;
 }
 
-static int lp87565_buck_set_current_limit(struct regulator_dev *rdev,
-					  int min_uA, int max_uA)
-{
-	int id = rdev_get_id(rdev);
-	struct lp87565 *lp87565 = rdev_get_drvdata(rdev);
-	int i;
-
-	for (i = ARRAY_SIZE(lp87565_buck_uA) - 1; i >= 0; i--) {
-		if (lp87565_buck_uA[i] >= min_uA &&
-		    lp87565_buck_uA[i] <= max_uA)
-			return regmap_update_bits(lp87565->regmap,
-						  regulators[id].ctrl2_reg,
-						  LP87565_BUCK_CTRL_2_ILIM,
-						  i << __ffs(LP87565_BUCK_CTRL_2_ILIM));
-	}
-
-	return -EINVAL;
-}
-
-static int lp87565_buck_get_current_limit(struct regulator_dev *rdev)
-{
-	int id = rdev_get_id(rdev);
-	struct lp87565 *lp87565 = rdev_get_drvdata(rdev);
-	int ret;
-	unsigned int val;
-
-	ret = regmap_read(lp87565->regmap, regulators[id].ctrl2_reg, &val);
-	if (ret)
-		return ret;
-
-	val = (val & LP87565_BUCK_CTRL_2_ILIM) >>
-	       __ffs(LP87565_BUCK_CTRL_2_ILIM);
-
-	return (val < ARRAY_SIZE(lp87565_buck_uA)) ?
-			lp87565_buck_uA[val] : -EINVAL;
-}
-
-/* Operations permitted on BUCK0, BUCK1 */
+/* Operations permitted on BUCKs */
 static const struct regulator_ops lp87565_buck_ops = {
 	.is_enabled		= regulator_is_enabled_regmap,
 	.enable			= regulator_enable_regmap,
@@ -150,8 +117,8 @@ static const struct regulator_ops lp87565_buck_ops = {
 	.map_voltage		= regulator_map_voltage_linear_range,
 	.set_voltage_time_sel	= regulator_set_voltage_time_sel,
 	.set_ramp_delay		= lp87565_buck_set_ramp_delay,
-	.set_current_limit	= lp87565_buck_set_current_limit,
-	.get_current_limit	= lp87565_buck_get_current_limit,
+	.set_current_limit	= regulator_set_current_limit_regmap,
+	.get_current_limit	= regulator_get_current_limit_regmap,
 };
 
 static const struct lp87565_regulator regulators[] = {
@@ -193,7 +160,7 @@ static int lp87565_regulator_probe(struct platform_device *pdev)
 	struct lp87565 *lp87565 = dev_get_drvdata(pdev->dev.parent);
 	struct regulator_config config = { };
 	struct regulator_dev *rdev;
-	int i, min_idx = LP87565_BUCK_1, max_idx = LP87565_BUCK_3;
+	int i, min_idx = LP87565_BUCK_0, max_idx = LP87565_BUCK_3;
 
 	platform_set_drvdata(pdev, lp87565);
 
diff --git a/drivers/regulator/ltc3589.c b/drivers/regulator/ltc3589.c
index 63f724f260ef..9a037fdc5fc5 100644
--- a/drivers/regulator/ltc3589.c
+++ b/drivers/regulator/ltc3589.c
@@ -1,21 +1,9 @@
-/*
- * Linear Technology LTC3589,LTC3589-1 regulator support
- *
- * Copyright (c) 2014 Philipp Zabel <p.zabel@pengutronix.de>, Pengutronix
- *
- * See file CREDITS for list of people who contributed to this
- * project.
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2
- * as published by the Free Software Foundation.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- *
- */
+// SPDX-License-Identifier: GPL-2.0
+//
+// Linear Technology LTC3589,LTC3589-1 regulator support
+//
+// Copyright (c) 2014 Philipp Zabel <p.zabel@pengutronix.de>, Pengutronix
+
 #include <linux/i2c.h>
 #include <linux/init.h>
 #include <linux/interrupt.h>
@@ -84,19 +72,11 @@ enum ltc3589_reg {
 	LTC3589_NUM_REGULATORS,
 };
 
-struct ltc3589_regulator {
-	struct regulator_desc desc;
-
-	/* External feedback voltage divider */
-	unsigned int r1;
-	unsigned int r2;
-};
-
 struct ltc3589 {
 	struct regmap *regmap;
 	struct device *dev;
 	enum ltc3589_variant variant;
-	struct ltc3589_regulator regulator_descs[LTC3589_NUM_REGULATORS];
+	struct regulator_desc regulator_descs[LTC3589_NUM_REGULATORS];
 	struct regulator_dev *regulators[LTC3589_NUM_REGULATORS];
 };
 
@@ -196,131 +176,90 @@ static const struct regulator_ops ltc3589_table_regulator_ops = {
 	.get_voltage_sel = regulator_get_voltage_sel_regmap,
 };
 
+static inline unsigned int ltc3589_scale(unsigned int uV, u32 r1, u32 r2)
+{
+	uint64_t tmp;
 
-#define LTC3589_REG(_name, _ops, en_bit, dtv1_reg, dtv_mask, go_bit)	\
-	[LTC3589_ ## _name] = {						\
-		.desc = {						\
-			.name = #_name,					\
-			.n_voltages = (dtv_mask) + 1,			\
-			.min_uV = (go_bit) ? 362500 : 0,		\
-			.uV_step = (go_bit) ? 12500 : 0,		\
-			.ramp_delay = (go_bit) ? 1750 : 0,		\
-			.fixed_uV = (dtv_mask) ? 0 : 800000,		\
-			.ops = &ltc3589_ ## _ops ## _regulator_ops,	\
-			.type = REGULATOR_VOLTAGE,			\
-			.id = LTC3589_ ## _name,			\
-			.owner = THIS_MODULE,				\
-			.vsel_reg = (dtv1_reg),			\
-			.vsel_mask = (dtv_mask),			\
-			.apply_reg = (go_bit) ? LTC3589_VCCR : 0,	\
-			.apply_bit = (go_bit),				\
-			.enable_reg = (en_bit) ? LTC3589_OVEN : 0,	\
-			.enable_mask = (en_bit),			\
-		},							\
-	}
-
-#define LTC3589_LINEAR_REG(_name, _dtv1)				\
-	LTC3589_REG(_name, linear, LTC3589_OVEN_ ## _name,		\
-		    LTC3589_ ## _dtv1, 0x1f,				\
-		    LTC3589_VCCR_ ## _name ## _GO)
-
-#define LTC3589_FIXED_REG(_name) \
-	LTC3589_REG(_name, fixed, LTC3589_OVEN_ ## _name, 0, 0, 0)
-
-static struct ltc3589_regulator ltc3589_regulators[LTC3589_NUM_REGULATORS] = {
-	LTC3589_LINEAR_REG(SW1, B1DTV1),
-	LTC3589_LINEAR_REG(SW2, B2DTV1),
-	LTC3589_LINEAR_REG(SW3, B3DTV1),
-	LTC3589_FIXED_REG(BB_OUT),
-	LTC3589_REG(LDO1, fixed_standby, 0, 0, 0, 0),
-	LTC3589_LINEAR_REG(LDO2, L2DTV1),
-	LTC3589_FIXED_REG(LDO3),
-	LTC3589_REG(LDO4, table, LTC3589_OVEN_LDO4, LTC3589_L2DTV2, 0x60, 0),
-};
+	if (uV == 0)
+		return 0;
 
-#ifdef CONFIG_OF
-static struct of_regulator_match ltc3589_matches[LTC3589_NUM_REGULATORS] = {
-	{ .name = "sw1",    },
-	{ .name = "sw2",    },
-	{ .name = "sw3",    },
-	{ .name = "bb-out", },
-	{ .name = "ldo1",   }, /* standby */
-	{ .name = "ldo2",   },
-	{ .name = "ldo3",   },
-	{ .name = "ldo4",   },
-};
+	tmp = (uint64_t)uV * r1;
+	do_div(tmp, r2);
+	return uV + (unsigned int)tmp;
+}
 
-static int ltc3589_parse_regulators_dt(struct ltc3589 *ltc3589)
+static int ltc3589_of_parse_cb(struct device_node *np,
+			       const struct regulator_desc *desc,
+			       struct regulator_config *config)
 {
-	struct device *dev = ltc3589->dev;
-	struct device_node *node;
-	int i, ret;
+	struct ltc3589 *ltc3589 = config->driver_data;
+	struct regulator_desc *rdesc = &ltc3589->regulator_descs[desc->id];
+	u32 r[2];
+	int ret;
 
-	node = of_get_child_by_name(dev->of_node, "regulators");
-	if (!node) {
-		dev_err(dev, "regulators node not found\n");
-		return -EINVAL;
-	}
+	/* Parse feedback voltage dividers. LDO3 and LDO4 don't have them */
+	if (desc->id >= LTC3589_LDO3)
+		return 0;
 
-	ret = of_regulator_match(dev, node, ltc3589_matches,
-				 ARRAY_SIZE(ltc3589_matches));
-	of_node_put(node);
-	if (ret < 0) {
-		dev_err(dev, "Error parsing regulator init data: %d\n", ret);
-		return ret;
-	}
-	if (ret != LTC3589_NUM_REGULATORS) {
-		dev_err(dev, "Only %d regulators described in device tree\n",
+	ret = of_property_read_u32_array(np, "lltc,fb-voltage-divider", r, 2);
+	if (ret) {
+		dev_err(ltc3589->dev, "Failed to parse voltage divider: %d\n",
 			ret);
-		return -EINVAL;
+		return ret;
 	}
 
-	/* Parse feedback voltage dividers. LDO3 and LDO4 don't have them */
-	for (i = 0; i < LTC3589_LDO3; i++) {
-		struct ltc3589_regulator *desc = &ltc3589->regulator_descs[i];
-		struct device_node *np = ltc3589_matches[i].of_node;
-		u32 vdiv[2];
-
-		ret = of_property_read_u32_array(np, "lltc,fb-voltage-divider",
-						 vdiv, 2);
-		if (ret) {
-			dev_err(dev, "Failed to parse voltage divider: %d\n",
-				ret);
-			return ret;
-		}
+	if (!r[0] || !r[1])
+		return 0;
 
-		desc->r1 = vdiv[0];
-		desc->r2 = vdiv[1];
-	}
+	rdesc->min_uV = ltc3589_scale(desc->min_uV, r[0], r[1]);
+	rdesc->uV_step = ltc3589_scale(desc->uV_step, r[0], r[1]);
+	rdesc->fixed_uV = ltc3589_scale(desc->fixed_uV, r[0], r[1]);
 
 	return 0;
 }
 
-static inline struct regulator_init_data *match_init_data(int index)
-{
-	return ltc3589_matches[index].init_data;
-}
-
-static inline struct device_node *match_of_node(int index)
-{
-	return ltc3589_matches[index].of_node;
-}
-#else
-static inline int ltc3589_parse_regulators_dt(struct ltc3589 *ltc3589)
-{
-	return 0;
-}
+#define LTC3589_REG(_name, _of_name, _ops, en_bit, dtv1_reg, dtv_mask, go_bit)\
+	[LTC3589_ ## _name] = {						\
+		.name = #_name,						\
+		.of_match = of_match_ptr(#_of_name),			\
+		.regulators_node = of_match_ptr("regulators"),		\
+		.of_parse_cb = ltc3589_of_parse_cb,			\
+		.n_voltages = (dtv_mask) + 1,				\
+		.min_uV = (go_bit) ? 362500 : 0,			\
+		.uV_step = (go_bit) ? 12500 : 0,			\
+		.ramp_delay = (go_bit) ? 1750 : 0,			\
+		.fixed_uV = (dtv_mask) ? 0 : 800000,			\
+		.ops = &ltc3589_ ## _ops ## _regulator_ops,		\
+		.type = REGULATOR_VOLTAGE,				\
+		.id = LTC3589_ ## _name,				\
+		.owner = THIS_MODULE,					\
+		.vsel_reg = (dtv1_reg),					\
+		.vsel_mask = (dtv_mask),				\
+		.apply_reg = (go_bit) ? LTC3589_VCCR : 0,		\
+		.apply_bit = (go_bit),					\
+		.enable_reg = (en_bit) ? LTC3589_OVEN : 0,		\
+		.enable_mask = (en_bit),				\
+	}
 
-static inline struct regulator_init_data *match_init_data(int index)
-{
-	return NULL;
-}
+#define LTC3589_LINEAR_REG(_name, _of_name, _dtv1)			\
+	LTC3589_REG(_name, _of_name, linear, LTC3589_OVEN_ ## _name,	\
+		    LTC3589_ ## _dtv1, 0x1f,				\
+		    LTC3589_VCCR_ ## _name ## _GO)
 
-static inline struct device_node *match_of_node(int index)
-{
-	return NULL;
-}
-#endif
+#define LTC3589_FIXED_REG(_name, _of_name)				\
+	LTC3589_REG(_name, _of_name, fixed, LTC3589_OVEN_ ## _name, 0, 0, 0)
+
+static const struct regulator_desc ltc3589_regulators[] = {
+	LTC3589_LINEAR_REG(SW1, sw1, B1DTV1),
+	LTC3589_LINEAR_REG(SW2, sw2, B2DTV1),
+	LTC3589_LINEAR_REG(SW3, sw3, B3DTV1),
+	LTC3589_FIXED_REG(BB_OUT, bb-out),
+	LTC3589_REG(LDO1, ldo1, fixed_standby, 0, 0, 0, 0),
+	LTC3589_LINEAR_REG(LDO2, ldo2, L2DTV1),
+	LTC3589_FIXED_REG(LDO3, ldo3),
+	LTC3589_REG(LDO4, ldo4, table, LTC3589_OVEN_LDO4, LTC3589_L2DTV2,
+		    0x60, 0),
+};
 
 static bool ltc3589_writeable_reg(struct device *dev, unsigned int reg)
 {
@@ -409,7 +348,6 @@ static const struct regmap_config ltc3589_regmap_config = {
 	.cache_type = REGCACHE_RBTREE,
 };
 
-
 static irqreturn_t ltc3589_isr(int irq, void *dev_id)
 {
 	struct ltc3589 *ltc3589 = dev_id;
@@ -419,16 +357,22 @@ static irqreturn_t ltc3589_isr(int irq, void *dev_id)
 
 	if (irqstat & LTC3589_IRQSTAT_THERMAL_WARN) {
 		event = REGULATOR_EVENT_OVER_TEMP;
-		for (i = 0; i < LTC3589_NUM_REGULATORS; i++)
+		for (i = 0; i < LTC3589_NUM_REGULATORS; i++) {
+		        regulator_lock(ltc3589->regulators[i]);
 			regulator_notifier_call_chain(ltc3589->regulators[i],
 						      event, NULL);
+		        regulator_unlock(ltc3589->regulators[i]);
+		}
 	}
 
 	if (irqstat & LTC3589_IRQSTAT_UNDERVOLT_WARN) {
 		event = REGULATOR_EVENT_UNDER_VOLTAGE;
-		for (i = 0; i < LTC3589_NUM_REGULATORS; i++)
+		for (i = 0; i < LTC3589_NUM_REGULATORS; i++) {
+		        regulator_lock(ltc3589->regulators[i]);
 			regulator_notifier_call_chain(ltc3589->regulators[i],
 						      event, NULL);
+		        regulator_unlock(ltc3589->regulators[i]);
+		}
 	}
 
 	/* Clear warning condition */
@@ -437,33 +381,11 @@ static irqreturn_t ltc3589_isr(int irq, void *dev_id)
 	return IRQ_HANDLED;
 }
 
-static inline unsigned int ltc3589_scale(unsigned int uV, u32 r1, u32 r2)
-{
-	uint64_t tmp;
-	if (uV == 0)
-		return 0;
-	tmp = (uint64_t)uV * r1;
-	do_div(tmp, r2);
-	return uV + (unsigned int)tmp;
-}
-
-static void ltc3589_apply_fb_voltage_divider(struct ltc3589_regulator *rdesc)
-{
-	struct regulator_desc *desc = &rdesc->desc;
-
-	if (!rdesc->r1 || !rdesc->r2)
-		return;
-
-	desc->min_uV = ltc3589_scale(desc->min_uV, rdesc->r1, rdesc->r2);
-	desc->uV_step = ltc3589_scale(desc->uV_step, rdesc->r1, rdesc->r2);
-	desc->fixed_uV = ltc3589_scale(desc->fixed_uV, rdesc->r1, rdesc->r2);
-}
-
 static int ltc3589_probe(struct i2c_client *client,
 			 const struct i2c_device_id *id)
 {
 	struct device *dev = &client->dev;
-	struct ltc3589_regulator *descs;
+	struct regulator_desc *descs;
 	struct ltc3589 *ltc3589;
 	int i, ret;
 
@@ -482,11 +404,11 @@ static int ltc3589_probe(struct i2c_client *client,
 	descs = ltc3589->regulator_descs;
 	memcpy(descs, ltc3589_regulators, sizeof(ltc3589_regulators));
 	if (ltc3589->variant == LTC3589) {
-		descs[LTC3589_LDO3].desc.fixed_uV = 1800000;
-		descs[LTC3589_LDO4].desc.volt_table = ltc3589_ldo4;
+		descs[LTC3589_LDO3].fixed_uV = 1800000;
+		descs[LTC3589_LDO4].volt_table = ltc3589_ldo4;
 	} else {
-		descs[LTC3589_LDO3].desc.fixed_uV = 2800000;
-		descs[LTC3589_LDO4].desc.volt_table = ltc3589_12_ldo4;
+		descs[LTC3589_LDO3].fixed_uV = 2800000;
+		descs[LTC3589_LDO4].volt_table = ltc3589_12_ldo4;
 	}
 
 	ltc3589->regmap = devm_regmap_init_i2c(client, &ltc3589_regmap_config);
@@ -496,25 +418,12 @@ static int ltc3589_probe(struct i2c_client *client,
 		return ret;
 	}
 
-	ret = ltc3589_parse_regulators_dt(ltc3589);
-	if (ret)
-		return ret;
-
 	for (i = 0; i < LTC3589_NUM_REGULATORS; i++) {
-		struct ltc3589_regulator *rdesc = &ltc3589->regulator_descs[i];
-		struct regulator_desc *desc = &rdesc->desc;
-		struct regulator_init_data *init_data;
+		struct regulator_desc *desc = &ltc3589->regulator_descs[i];
 		struct regulator_config config = { };
 
-		init_data = match_init_data(i);
-
-		if (i < LTC3589_LDO3)
-			ltc3589_apply_fb_voltage_divider(rdesc);
-
 		config.dev = dev;
-		config.init_data = init_data;
 		config.driver_data = ltc3589;
-		config.of_node = match_of_node(i);
 
 		ltc3589->regulators[i] = devm_regulator_register(dev, desc,
 								 &config);
diff --git a/drivers/regulator/ltc3676.c b/drivers/regulator/ltc3676.c
index e6d66e492b85..4be90c78c720 100644
--- a/drivers/regulator/ltc3676.c
+++ b/drivers/regulator/ltc3676.c
@@ -285,17 +285,23 @@ static irqreturn_t ltc3676_isr(int irq, void *dev_id)
 	if (irqstat & LTC3676_IRQSTAT_THERMAL_WARN) {
 		dev_warn(dev, "Over-temperature Warning\n");
 		event = REGULATOR_EVENT_OVER_TEMP;
-		for (i = 0; i < LTC3676_NUM_REGULATORS; i++)
+		for (i = 0; i < LTC3676_NUM_REGULATORS; i++) {
+			regulator_lock(ltc3676->regulators[i]);
 			regulator_notifier_call_chain(ltc3676->regulators[i],
 						      event, NULL);
+			regulator_unlock(ltc3676->regulators[i]);
+		}
 	}
 
 	if (irqstat & LTC3676_IRQSTAT_UNDERVOLT_WARN) {
 		dev_info(dev, "Undervoltage Warning\n");
 		event = REGULATOR_EVENT_UNDER_VOLTAGE;
-		for (i = 0; i < LTC3676_NUM_REGULATORS; i++)
+		for (i = 0; i < LTC3676_NUM_REGULATORS; i++) {
+			regulator_lock(ltc3676->regulators[i]);
 			regulator_notifier_call_chain(ltc3676->regulators[i],
 						      event, NULL);
+			regulator_unlock(ltc3676->regulators[i]);
+		}
 	}
 
 	/* Clear warning condition */
diff --git a/drivers/regulator/max14577-regulator.c b/drivers/regulator/max14577-regulator.c
index 85a88a9e4d42..07a150c9bbf2 100644
--- a/drivers/regulator/max14577-regulator.c
+++ b/drivers/regulator/max14577-regulator.c
@@ -155,58 +155,6 @@ static const struct regulator_desc max77836_supported_regulators[] = {
 	[MAX77836_LDO2] = MAX77836_LDO_REG(2),
 };
 
-#ifdef CONFIG_OF
-static struct of_regulator_match max14577_regulator_matches[] = {
-	{ .name	= "SAFEOUT", },
-	{ .name = "CHARGER", },
-};
-
-static struct of_regulator_match max77836_regulator_matches[] = {
-	{ .name	= "SAFEOUT", },
-	{ .name = "CHARGER", },
-	{ .name = "LDO1", },
-	{ .name = "LDO2", },
-};
-
-static inline struct regulator_init_data *match_init_data(int index,
-		enum maxim_device_type dev_type)
-{
-	switch (dev_type) {
-	case MAXIM_DEVICE_TYPE_MAX77836:
-		return max77836_regulator_matches[index].init_data;
-
-	case MAXIM_DEVICE_TYPE_MAX14577:
-	default:
-		return max14577_regulator_matches[index].init_data;
-	}
-}
-
-static inline struct device_node *match_of_node(int index,
-		enum maxim_device_type dev_type)
-{
-	switch (dev_type) {
-	case MAXIM_DEVICE_TYPE_MAX77836:
-		return max77836_regulator_matches[index].of_node;
-
-	case MAXIM_DEVICE_TYPE_MAX14577:
-	default:
-		return max14577_regulator_matches[index].of_node;
-	}
-}
-#else /* CONFIG_OF */
-static inline struct regulator_init_data *match_init_data(int index,
-		enum maxim_device_type dev_type)
-{
-	return NULL;
-}
-
-static inline struct device_node *match_of_node(int index,
-		enum maxim_device_type dev_type)
-{
-	return NULL;
-}
-#endif /* CONFIG_OF */
-
 /**
  * Registers for regulators of max77836 use different I2C slave addresses so
  * different regmaps must be used for them.
@@ -265,9 +213,6 @@ static int max14577_regulator_probe(struct platform_device *pdev)
 		if (pdata && pdata->regulators) {
 			config.init_data = pdata->regulators[i].initdata;
 			config.of_node = pdata->regulators[i].of_node;
-		} else {
-			config.init_data = match_init_data(i, dev_type);
-			config.of_node = match_of_node(i, dev_type);
 		}
 		config.regmap = max14577_get_regmap(max14577,
 				supported_regulators[i].id);
diff --git a/drivers/regulator/max77620-regulator.c b/drivers/regulator/max77620-regulator.c
index 1607ac673e44..0ad91a7f9cb9 100644
--- a/drivers/regulator/max77620-regulator.c
+++ b/drivers/regulator/max77620-regulator.c
@@ -803,7 +803,7 @@ static int max77620_regulator_probe(struct platform_device *pdev)
 			continue;
 
 		rdesc = &rinfo[id].desc;
-		pmic->rinfo[id] = &max77620_regs_info[id];
+		pmic->rinfo[id] = &rinfo[id];
 		pmic->enable_power_mode[id] = MAX77620_POWER_MODE_NORMAL;
 		pmic->reg_pdata[id].active_fps_src = -1;
 		pmic->reg_pdata[id].active_fps_pd_slot = -1;
diff --git a/drivers/regulator/max77650-regulator.c b/drivers/regulator/max77650-regulator.c
index 31ebf34b01ec..5c4f86c98510 100644
--- a/drivers/regulator/max77650-regulator.c
+++ b/drivers/regulator/max77650-regulator.c
@@ -41,7 +41,7 @@ struct max77650_regulator_desc {
 	unsigned int regB;
 };
 
-static const u32 max77651_sbb1_regulator_volt_table[] = {
+static const unsigned int max77651_sbb1_regulator_volt_table[] = {
 	2400000, 3200000, 4000000, 4800000,
 	2450000, 3250000, 4050000, 4850000,
 	2500000, 3300000, 4100000, 4900000,
diff --git a/drivers/regulator/max8925-regulator.c b/drivers/regulator/max8925-regulator.c
index 39b63ddefeb2..aed6727982cd 100644
--- a/drivers/regulator/max8925-regulator.c
+++ b/drivers/regulator/max8925-regulator.c
@@ -159,6 +159,8 @@ static const struct regulator_ops max8925_regulator_ldo_ops = {
 {								\
 	.desc	= {						\
 		.name	= "SDV" #_id,				\
+		.of_match = of_match_ptr("SDV" #_id),		\
+		.regulators_node = of_match_ptr("regulators"),	\
 		.ops	= &max8925_regulator_sdv_ops,		\
 		.type	= REGULATOR_VOLTAGE,			\
 		.id	= MAX8925_ID_SD##_id,			\
@@ -175,6 +177,8 @@ static const struct regulator_ops max8925_regulator_ldo_ops = {
 {								\
 	.desc	= {						\
 		.name	= "LDO" #_id,				\
+		.of_match = of_match_ptr("LDO" #_id),		\
+		.regulators_node = of_match_ptr("regulators"),	\
 		.ops	= &max8925_regulator_ldo_ops,		\
 		.type	= REGULATOR_VOLTAGE,			\
 		.id	= MAX8925_ID_LDO##_id,			\
@@ -187,34 +191,6 @@ static const struct regulator_ops max8925_regulator_ldo_ops = {
 	.enable_reg	= MAX8925_LDOCTL##_id,			\
 }
 
-#ifdef CONFIG_OF
-static struct of_regulator_match max8925_regulator_matches[] = {
-	{ .name	= "SDV1",},
-	{ .name = "SDV2",},
-	{ .name = "SDV3",},
-	{ .name = "LDO1",},
-	{ .name = "LDO2",},
-	{ .name = "LDO3",},
-	{ .name = "LDO4",},
-	{ .name = "LDO5",},
-	{ .name = "LDO6",},
-	{ .name = "LDO7",},
-	{ .name = "LDO8",},
-	{ .name = "LDO9",},
-	{ .name = "LDO10",},
-	{ .name = "LDO11",},
-	{ .name = "LDO12",},
-	{ .name = "LDO13",},
-	{ .name = "LDO14",},
-	{ .name = "LDO15",},
-	{ .name = "LDO16",},
-	{ .name = "LDO17",},
-	{ .name = "LDO18",},
-	{ .name = "LDO19",},
-	{ .name = "LDO20",},
-};
-#endif
-
 static struct max8925_regulator_info max8925_regulator_info[] = {
 	MAX8925_SDV(1, 637.5, 1425, 12.5),
 	MAX8925_SDV(2,   650, 2225,   25),
@@ -242,37 +218,6 @@ static struct max8925_regulator_info max8925_regulator_info[] = {
 	MAX8925_LDO(20, 750, 3900, 50),
 };
 
-#ifdef CONFIG_OF
-static int max8925_regulator_dt_init(struct platform_device *pdev,
-				    struct regulator_config *config,
-				    int ridx)
-{
-	struct device_node *nproot, *np;
-	int rcount;
-
-	nproot = pdev->dev.parent->of_node;
-	if (!nproot)
-		return -ENODEV;
-	np = of_get_child_by_name(nproot, "regulators");
-	if (!np) {
-		dev_err(&pdev->dev, "failed to find regulators node\n");
-		return -ENODEV;
-	}
-
-	rcount = of_regulator_match(&pdev->dev, np,
-				&max8925_regulator_matches[ridx], 1);
-	of_node_put(np);
-	if (rcount < 0)
-		return rcount;
-	config->init_data =	max8925_regulator_matches[ridx].init_data;
-	config->of_node = max8925_regulator_matches[ridx].of_node;
-
-	return 0;
-}
-#else
-#define max8925_regulator_dt_init(x, y, z)	(-1)
-#endif
-
 static int max8925_regulator_probe(struct platform_device *pdev)
 {
 	struct max8925_chip *chip = dev_get_drvdata(pdev->dev.parent);
@@ -281,7 +226,7 @@ static int max8925_regulator_probe(struct platform_device *pdev)
 	struct max8925_regulator_info *ri;
 	struct resource *res;
 	struct regulator_dev *rdev;
-	int i, regulator_idx;
+	int i;
 
 	res = platform_get_resource(pdev, IORESOURCE_REG, 0);
 	if (!res) {
@@ -290,10 +235,8 @@ static int max8925_regulator_probe(struct platform_device *pdev)
 	}
 	for (i = 0; i < ARRAY_SIZE(max8925_regulator_info); i++) {
 		ri = &max8925_regulator_info[i];
-		if (ri->vol_reg == res->start) {
-			regulator_idx = i;
+		if (ri->vol_reg == res->start)
 			break;
-		}
 	}
 
 	if (i == ARRAY_SIZE(max8925_regulator_info)) {
@@ -303,12 +246,11 @@ static int max8925_regulator_probe(struct platform_device *pdev)
 	}
 	ri->i2c = chip->i2c;
 
-	config.dev = &pdev->dev;
+	config.dev = chip->dev;
 	config.driver_data = ri;
 
-	if (max8925_regulator_dt_init(pdev, &config, regulator_idx))
-		if (pdata)
-			config.init_data = pdata;
+	if (pdata)
+		config.init_data = pdata;
 
 	rdev = devm_regulator_register(&pdev->dev, &ri->desc, &config);
 	if (IS_ERR(rdev)) {
diff --git a/drivers/regulator/max8998.c b/drivers/regulator/max8998.c
index 271bb736f3f5..60599c3bb845 100644
--- a/drivers/regulator/max8998.c
+++ b/drivers/regulator/max8998.c
@@ -33,72 +33,6 @@ struct max8998_data {
 	unsigned int		buck2_idx;
 };
 
-struct voltage_map_desc {
-	int min;
-	int max;
-	int step;
-};
-
-/* Voltage maps in uV*/
-static const struct voltage_map_desc ldo23_voltage_map_desc = {
-	.min = 800000,	.step = 50000,	.max = 1300000,
-};
-static const struct voltage_map_desc ldo456711_voltage_map_desc = {
-	.min = 1600000,	.step = 100000,	.max = 3600000,
-};
-static const struct voltage_map_desc ldo8_voltage_map_desc = {
-	.min = 3000000,	.step = 100000,	.max = 3600000,
-};
-static const struct voltage_map_desc ldo9_voltage_map_desc = {
-	.min = 2800000,	.step = 100000,	.max = 3100000,
-};
-static const struct voltage_map_desc ldo10_voltage_map_desc = {
-	.min = 950000,	.step = 50000,	.max = 1300000,
-};
-static const struct voltage_map_desc ldo1213_voltage_map_desc = {
-	.min = 800000,	.step = 100000,	.max = 3300000,
-};
-static const struct voltage_map_desc ldo1415_voltage_map_desc = {
-	.min = 1200000,	.step = 100000,	.max = 3300000,
-};
-static const struct voltage_map_desc ldo1617_voltage_map_desc = {
-	.min = 1600000,	.step = 100000,	.max = 3600000,
-};
-static const struct voltage_map_desc buck12_voltage_map_desc = {
-	.min = 750000,	.step = 25000,	.max = 1525000,
-};
-static const struct voltage_map_desc buck3_voltage_map_desc = {
-	.min = 1600000,	.step = 100000,	.max = 3600000,
-};
-static const struct voltage_map_desc buck4_voltage_map_desc = {
-	.min = 800000,	.step = 100000,	.max = 2300000,
-};
-
-static const struct voltage_map_desc *ldo_voltage_map[] = {
-	NULL,
-	NULL,
-	&ldo23_voltage_map_desc,	/* LDO2 */
-	&ldo23_voltage_map_desc,	/* LDO3 */
-	&ldo456711_voltage_map_desc,	/* LDO4 */
-	&ldo456711_voltage_map_desc,	/* LDO5 */
-	&ldo456711_voltage_map_desc,	/* LDO6 */
-	&ldo456711_voltage_map_desc,	/* LDO7 */
-	&ldo8_voltage_map_desc,		/* LDO8 */
-	&ldo9_voltage_map_desc,		/* LDO9 */
-	&ldo10_voltage_map_desc,	/* LDO10 */
-	&ldo456711_voltage_map_desc,	/* LDO11 */
-	&ldo1213_voltage_map_desc,	/* LDO12 */
-	&ldo1213_voltage_map_desc,	/* LDO13 */
-	&ldo1415_voltage_map_desc,	/* LDO14 */
-	&ldo1415_voltage_map_desc,	/* LDO15 */
-	&ldo1617_voltage_map_desc,	/* LDO16 */
-	&ldo1617_voltage_map_desc,	/* LDO17 */
-	&buck12_voltage_map_desc,	/* BUCK1 */
-	&buck12_voltage_map_desc,	/* BUCK2 */
-	&buck3_voltage_map_desc,	/* BUCK3 */
-	&buck4_voltage_map_desc,	/* BUCK4 */
-};
-
 static int max8998_get_enable_register(struct regulator_dev *rdev,
 					int *reg, int *shift)
 {
@@ -400,7 +334,6 @@ static int max8998_set_voltage_buck_time_sel(struct regulator_dev *rdev,
 {
 	struct max8998_data *max8998 = rdev_get_drvdata(rdev);
 	struct i2c_client *i2c = max8998->iodev->i2c;
-	const struct voltage_map_desc *desc;
 	int buck = rdev_get_id(rdev);
 	u8 val = 0;
 	int difference, ret;
@@ -408,8 +341,6 @@ static int max8998_set_voltage_buck_time_sel(struct regulator_dev *rdev,
 	if (buck < MAX8998_BUCK1 || buck > MAX8998_BUCK4)
 		return -EINVAL;
 
-	desc = ldo_voltage_map[buck];
-
 	/* Voltage stabilization */
 	ret = max8998_read_reg(i2c, MAX8998_REG_ONOFF4, &val);
 	if (ret)
@@ -420,14 +351,14 @@ static int max8998_set_voltage_buck_time_sel(struct regulator_dev *rdev,
 	if (max8998->iodev->type == TYPE_MAX8998 && !(val & MAX8998_ENRAMP))
 		return 0;
 
-	difference = (new_selector - old_selector) * desc->step / 1000;
+	difference = (new_selector - old_selector) * rdev->desc->uV_step / 1000;
 	if (difference > 0)
 		return DIV_ROUND_UP(difference, (val & 0x0f) + 1);
 
 	return 0;
 }
 
-static struct regulator_ops max8998_ldo_ops = {
+static const struct regulator_ops max8998_ldo_ops = {
 	.list_voltage		= regulator_list_voltage_linear,
 	.map_voltage		= regulator_map_voltage_linear,
 	.is_enabled		= max8998_ldo_is_enabled,
@@ -437,7 +368,7 @@ static struct regulator_ops max8998_ldo_ops = {
 	.set_voltage_sel	= max8998_set_voltage_ldo_sel,
 };
 
-static struct regulator_ops max8998_buck_ops = {
+static const struct regulator_ops max8998_buck_ops = {
 	.list_voltage		= regulator_list_voltage_linear,
 	.map_voltage		= regulator_map_voltage_linear,
 	.is_enabled		= max8998_ldo_is_enabled,
@@ -448,164 +379,59 @@ static struct regulator_ops max8998_buck_ops = {
 	.set_voltage_time_sel	= max8998_set_voltage_buck_time_sel,
 };
 
-static struct regulator_ops max8998_others_ops = {
+static const struct regulator_ops max8998_others_ops = {
 	.is_enabled		= max8998_ldo_is_enabled,
 	.enable			= max8998_ldo_enable,
 	.disable		= max8998_ldo_disable,
 };
 
-static struct regulator_desc regulators[] = {
-	{
-		.name		= "LDO2",
-		.id		= MAX8998_LDO2,
-		.ops		= &max8998_ldo_ops,
-		.type		= REGULATOR_VOLTAGE,
-		.owner		= THIS_MODULE,
-	}, {
-		.name		= "LDO3",
-		.id		= MAX8998_LDO3,
-		.ops		= &max8998_ldo_ops,
-		.type		= REGULATOR_VOLTAGE,
-		.owner		= THIS_MODULE,
-	}, {
-		.name		= "LDO4",
-		.id		= MAX8998_LDO4,
-		.ops		= &max8998_ldo_ops,
-		.type		= REGULATOR_VOLTAGE,
-		.owner		= THIS_MODULE,
-	}, {
-		.name		= "LDO5",
-		.id		= MAX8998_LDO5,
-		.ops		= &max8998_ldo_ops,
-		.type		= REGULATOR_VOLTAGE,
-		.owner		= THIS_MODULE,
-	}, {
-		.name		= "LDO6",
-		.id		= MAX8998_LDO6,
-		.ops		= &max8998_ldo_ops,
-		.type		= REGULATOR_VOLTAGE,
-		.owner		= THIS_MODULE,
-	}, {
-		.name		= "LDO7",
-		.id		= MAX8998_LDO7,
-		.ops		= &max8998_ldo_ops,
-		.type		= REGULATOR_VOLTAGE,
-		.owner		= THIS_MODULE,
-	}, {
-		.name		= "LDO8",
-		.id		= MAX8998_LDO8,
-		.ops		= &max8998_ldo_ops,
-		.type		= REGULATOR_VOLTAGE,
-		.owner		= THIS_MODULE,
-	}, {
-		.name		= "LDO9",
-		.id		= MAX8998_LDO9,
-		.ops		= &max8998_ldo_ops,
-		.type		= REGULATOR_VOLTAGE,
-		.owner		= THIS_MODULE,
-	}, {
-		.name		= "LDO10",
-		.id		= MAX8998_LDO10,
-		.ops		= &max8998_ldo_ops,
-		.type		= REGULATOR_VOLTAGE,
-		.owner		= THIS_MODULE,
-	}, {
-		.name		= "LDO11",
-		.id		= MAX8998_LDO11,
-		.ops		= &max8998_ldo_ops,
-		.type		= REGULATOR_VOLTAGE,
-		.owner		= THIS_MODULE,
-	}, {
-		.name		= "LDO12",
-		.id		= MAX8998_LDO12,
-		.ops		= &max8998_ldo_ops,
-		.type		= REGULATOR_VOLTAGE,
-		.owner		= THIS_MODULE,
-	}, {
-		.name		= "LDO13",
-		.id		= MAX8998_LDO13,
-		.ops		= &max8998_ldo_ops,
-		.type		= REGULATOR_VOLTAGE,
-		.owner		= THIS_MODULE,
-	}, {
-		.name		= "LDO14",
-		.id		= MAX8998_LDO14,
-		.ops		= &max8998_ldo_ops,
-		.type		= REGULATOR_VOLTAGE,
-		.owner		= THIS_MODULE,
-	}, {
-		.name		= "LDO15",
-		.id		= MAX8998_LDO15,
-		.ops		= &max8998_ldo_ops,
-		.type		= REGULATOR_VOLTAGE,
-		.owner		= THIS_MODULE,
-	}, {
-		.name		= "LDO16",
-		.id		= MAX8998_LDO16,
-		.ops		= &max8998_ldo_ops,
-		.type		= REGULATOR_VOLTAGE,
-		.owner		= THIS_MODULE,
-	}, {
-		.name		= "LDO17",
-		.id		= MAX8998_LDO17,
-		.ops		= &max8998_ldo_ops,
-		.type		= REGULATOR_VOLTAGE,
-		.owner		= THIS_MODULE,
-	}, {
-		.name		= "BUCK1",
-		.id		= MAX8998_BUCK1,
-		.ops		= &max8998_buck_ops,
-		.type		= REGULATOR_VOLTAGE,
-		.owner		= THIS_MODULE,
-	}, {
-		.name		= "BUCK2",
-		.id		= MAX8998_BUCK2,
-		.ops		= &max8998_buck_ops,
-		.type		= REGULATOR_VOLTAGE,
-		.owner		= THIS_MODULE,
-	}, {
-		.name		= "BUCK3",
-		.id		= MAX8998_BUCK3,
-		.ops		= &max8998_buck_ops,
-		.type		= REGULATOR_VOLTAGE,
-		.owner		= THIS_MODULE,
-	}, {
-		.name		= "BUCK4",
-		.id		= MAX8998_BUCK4,
-		.ops		= &max8998_buck_ops,
-		.type		= REGULATOR_VOLTAGE,
-		.owner		= THIS_MODULE,
-	}, {
-		.name		= "EN32KHz-AP",
-		.id		= MAX8998_EN32KHZ_AP,
-		.ops		= &max8998_others_ops,
-		.type		= REGULATOR_VOLTAGE,
-		.owner		= THIS_MODULE,
-	}, {
-		.name		= "EN32KHz-CP",
-		.id		= MAX8998_EN32KHZ_CP,
-		.ops		= &max8998_others_ops,
-		.type		= REGULATOR_VOLTAGE,
-		.owner		= THIS_MODULE,
-	}, {
-		.name		= "ENVICHG",
-		.id		= MAX8998_ENVICHG,
-		.ops		= &max8998_others_ops,
-		.type		= REGULATOR_VOLTAGE,
-		.owner		= THIS_MODULE,
-	}, {
-		.name		= "ESAFEOUT1",
-		.id		= MAX8998_ESAFEOUT1,
-		.ops		= &max8998_others_ops,
-		.type		= REGULATOR_VOLTAGE,
-		.owner		= THIS_MODULE,
-	}, {
-		.name		= "ESAFEOUT2",
-		.id		= MAX8998_ESAFEOUT2,
-		.ops		= &max8998_others_ops,
-		.type		= REGULATOR_VOLTAGE,
-		.owner		= THIS_MODULE,
+#define MAX8998_LINEAR_REG(_name, _ops, _min, _step, _max) \
+	{ \
+		.name = #_name, \
+		.id = MAX8998_##_name, \
+		.ops = _ops, \
+		.min_uV = (_min), \
+		.uV_step = (_step), \
+		.n_voltages = ((_max) - (_min)) / (_step) + 1, \
+		.type = REGULATOR_VOLTAGE, \
+		.owner = THIS_MODULE, \
 	}
+
+#define MAX8998_OTHERS_REG(_name, _id) \
+	{ \
+		.name = #_name, \
+		.id = _id, \
+		.ops = &max8998_others_ops, \
+		.type = REGULATOR_VOLTAGE, \
+		.owner = THIS_MODULE, \
+	}
+
+static const struct regulator_desc regulators[] = {
+	MAX8998_LINEAR_REG(LDO2, &max8998_ldo_ops, 800000, 50000, 1300000),
+	MAX8998_LINEAR_REG(LDO3, &max8998_ldo_ops, 800000, 50000, 1300000),
+	MAX8998_LINEAR_REG(LDO4, &max8998_ldo_ops, 1600000, 100000, 3600000),
+	MAX8998_LINEAR_REG(LDO5, &max8998_ldo_ops, 1600000, 100000, 3600000),
+	MAX8998_LINEAR_REG(LDO6, &max8998_ldo_ops, 1600000, 100000, 3600000),
+	MAX8998_LINEAR_REG(LDO7, &max8998_ldo_ops, 1600000, 100000, 3600000),
+	MAX8998_LINEAR_REG(LDO8, &max8998_ldo_ops, 3000000, 100000, 3600000),
+	MAX8998_LINEAR_REG(LDO9, &max8998_ldo_ops, 2800000, 100000, 3100000),
+	MAX8998_LINEAR_REG(LDO10, &max8998_ldo_ops, 950000, 50000, 1300000),
+	MAX8998_LINEAR_REG(LDO11, &max8998_ldo_ops, 1600000, 100000, 3600000),
+	MAX8998_LINEAR_REG(LDO12, &max8998_ldo_ops, 800000, 100000, 3300000),
+	MAX8998_LINEAR_REG(LDO13, &max8998_ldo_ops, 800000, 100000, 3300000),
+	MAX8998_LINEAR_REG(LDO14, &max8998_ldo_ops, 1200000, 100000, 3300000),
+	MAX8998_LINEAR_REG(LDO15, &max8998_ldo_ops, 1200000, 100000, 3300000),
+	MAX8998_LINEAR_REG(LDO16, &max8998_ldo_ops, 1600000, 100000, 3600000),
+	MAX8998_LINEAR_REG(LDO17, &max8998_ldo_ops, 1600000, 100000, 3600000),
+	MAX8998_LINEAR_REG(BUCK1, &max8998_buck_ops, 750000, 25000, 1525000),
+	MAX8998_LINEAR_REG(BUCK2, &max8998_buck_ops, 750000, 25000, 1525000),
+	MAX8998_LINEAR_REG(BUCK3, &max8998_buck_ops, 1600000, 100000, 3600000),
+	MAX8998_LINEAR_REG(BUCK4, &max8998_buck_ops, 800000, 100000, 2300000),
+	MAX8998_OTHERS_REG(EN32KHz-AP, MAX8998_EN32KHZ_AP),
+	MAX8998_OTHERS_REG(EN32KHz-CP, MAX8998_EN32KHZ_CP),
+	MAX8998_OTHERS_REG(ENVICHG, MAX8998_ENVICHG),
+	MAX8998_OTHERS_REG(ESAFEOUT1, MAX8998_ESAFEOUT1),
+	MAX8998_OTHERS_REG(ESAFEOUT2, MAX8998_ESAFEOUT2),
 };
 
 static int max8998_pmic_dt_parse_dvs_gpio(struct max8998_dev *iodev,
@@ -796,9 +622,11 @@ static int max8998_pmic_probe(struct platform_device *pdev)
 
 		/* Set predefined values for BUCK1 registers */
 		for (v = 0; v < ARRAY_SIZE(pdata->buck1_voltage); ++v) {
+			int index = MAX8998_BUCK1 - MAX8998_LDO2;
+
 			i = 0;
-			while (buck12_voltage_map_desc.min +
-			       buck12_voltage_map_desc.step*i
+			while (regulators[index].min_uV +
+			       regulators[index].uV_step * i
 			       < pdata->buck1_voltage[v])
 				i++;
 
@@ -824,9 +652,11 @@ static int max8998_pmic_probe(struct platform_device *pdev)
 
 		/* Set predefined values for BUCK2 registers */
 		for (v = 0; v < ARRAY_SIZE(pdata->buck2_voltage); ++v) {
+			int index = MAX8998_BUCK2 - MAX8998_LDO2;
+
 			i = 0;
-			while (buck12_voltage_map_desc.min +
-			       buck12_voltage_map_desc.step*i
+			while (regulators[index].min_uV +
+			       regulators[index].uV_step * i
 			       < pdata->buck2_voltage[v])
 				i++;
 
@@ -839,18 +669,7 @@ static int max8998_pmic_probe(struct platform_device *pdev)
 	}
 
 	for (i = 0; i < pdata->num_regulators; i++) {
-		const struct voltage_map_desc *desc;
-		int id = pdata->regulators[i].id;
-		int index = id - MAX8998_LDO2;
-
-		desc = ldo_voltage_map[id];
-		if (desc && regulators[index].ops != &max8998_others_ops) {
-			int count = (desc->max - desc->min) / desc->step + 1;
-
-			regulators[index].n_voltages = count;
-			regulators[index].min_uV = desc->min;
-			regulators[index].uV_step = desc->step;
-		}
+		int index = pdata->regulators[i].id - MAX8998_LDO2;
 
 		config.dev = max8998->dev;
 		config.of_node = pdata->regulators[i].reg_node;
@@ -867,7 +686,6 @@ static int max8998_pmic_probe(struct platform_device *pdev)
 		}
 	}
 
-
 	return 0;
 }
 
diff --git a/drivers/regulator/mcp16502.c b/drivers/regulator/mcp16502.c
index 3a8004abe044..e5a02711cb46 100644
--- a/drivers/regulator/mcp16502.c
+++ b/drivers/regulator/mcp16502.c
@@ -119,8 +119,6 @@ enum {
  * @lpm: LPM GPIO descriptor
  */
 struct mcp16502 {
-	struct regulator_dev *rdev[NUM_REGULATORS];
-	struct regmap *rmap;
 	struct gpio_desc *lpm;
 };
 
@@ -179,13 +177,12 @@ static unsigned int mcp16502_get_mode(struct regulator_dev *rdev)
 {
 	unsigned int val;
 	int ret, reg;
-	struct mcp16502 *mcp = rdev_get_drvdata(rdev);
 
 	reg = mcp16502_get_reg(rdev, MCP16502_OPMODE_ACTIVE);
 	if (reg < 0)
 		return reg;
 
-	ret = regmap_read(mcp->rmap, reg, &val);
+	ret = regmap_read(rdev->regmap, reg, &val);
 	if (ret)
 		return ret;
 
@@ -211,7 +208,6 @@ static int _mcp16502_set_mode(struct regulator_dev *rdev, unsigned int mode,
 {
 	int val;
 	int reg;
-	struct mcp16502 *mcp = rdev_get_drvdata(rdev);
 
 	reg = mcp16502_get_reg(rdev, op_mode);
 	if (reg < 0)
@@ -228,7 +224,7 @@ static int _mcp16502_set_mode(struct regulator_dev *rdev, unsigned int mode,
 		return -EINVAL;
 	}
 
-	reg = regmap_update_bits(mcp->rmap, reg, MCP16502_MODE, val);
+	reg = regmap_update_bits(rdev->regmap, reg, MCP16502_MODE, val);
 	return reg;
 }
 
@@ -247,9 +243,8 @@ static int mcp16502_get_status(struct regulator_dev *rdev)
 {
 	int ret;
 	unsigned int val;
-	struct mcp16502 *mcp = rdev_get_drvdata(rdev);
 
-	ret = regmap_read(mcp->rmap, MCP16502_STAT_BASE(rdev_get_id(rdev)),
+	ret = regmap_read(rdev->regmap, MCP16502_STAT_BASE(rdev_get_id(rdev)),
 			  &val);
 	if (ret)
 		return ret;
@@ -290,7 +285,6 @@ static int mcp16502_suspend_get_target_reg(struct regulator_dev *rdev)
  */
 static int mcp16502_set_suspend_voltage(struct regulator_dev *rdev, int uV)
 {
-	struct mcp16502 *mcp = rdev_get_drvdata(rdev);
 	int sel = regulator_map_voltage_linear_range(rdev, uV, uV);
 	int reg = mcp16502_suspend_get_target_reg(rdev);
 
@@ -300,7 +294,7 @@ static int mcp16502_set_suspend_voltage(struct regulator_dev *rdev, int uV)
 	if (reg < 0)
 		return reg;
 
-	return regmap_update_bits(mcp->rmap, reg, MCP16502_VSEL, sel);
+	return regmap_update_bits(rdev->regmap, reg, MCP16502_VSEL, sel);
 }
 
 /*
@@ -328,13 +322,12 @@ static int mcp16502_set_suspend_mode(struct regulator_dev *rdev,
  */
 static int mcp16502_set_suspend_enable(struct regulator_dev *rdev)
 {
-	struct mcp16502 *mcp = rdev_get_drvdata(rdev);
 	int reg = mcp16502_suspend_get_target_reg(rdev);
 
 	if (reg < 0)
 		return reg;
 
-	return regmap_update_bits(mcp->rmap, reg, MCP16502_EN, MCP16502_EN);
+	return regmap_update_bits(rdev->regmap, reg, MCP16502_EN, MCP16502_EN);
 }
 
 /*
@@ -342,13 +335,12 @@ static int mcp16502_set_suspend_enable(struct regulator_dev *rdev)
  */
 static int mcp16502_set_suspend_disable(struct regulator_dev *rdev)
 {
-	struct mcp16502 *mcp = rdev_get_drvdata(rdev);
 	int reg = mcp16502_suspend_get_target_reg(rdev);
 
 	if (reg < 0)
 		return reg;
 
-	return regmap_update_bits(mcp->rmap, reg, MCP16502_EN, 0);
+	return regmap_update_bits(rdev->regmap, reg, MCP16502_EN, 0);
 }
 #endif /* CONFIG_SUSPEND */
 
@@ -435,36 +427,15 @@ static const struct regmap_config mcp16502_regmap_config = {
 	.wr_table	= &mcp16502_yes_reg_table,
 };
 
-/*
- * set_up_regulators() - initialize all regulators
- */
-static int setup_regulators(struct mcp16502 *mcp, struct device *dev,
-			    struct regulator_config config)
-{
-	int i;
-
-	for (i = 0; i < NUM_REGULATORS; i++) {
-		mcp->rdev[i] = devm_regulator_register(dev,
-						       &mcp16502_desc[i],
-						       &config);
-		if (IS_ERR(mcp->rdev[i])) {
-			dev_err(dev,
-				"failed to register %s regulator %ld\n",
-				mcp16502_desc[i].name, PTR_ERR(mcp->rdev[i]));
-			return PTR_ERR(mcp->rdev[i]);
-		}
-	}
-
-	return 0;
-}
-
 static int mcp16502_probe(struct i2c_client *client,
 			  const struct i2c_device_id *id)
 {
 	struct regulator_config config = { };
+	struct regulator_dev *rdev;
 	struct device *dev;
 	struct mcp16502 *mcp;
-	int ret = 0;
+	struct regmap *rmap;
+	int i, ret;
 
 	dev = &client->dev;
 	config.dev = dev;
@@ -473,15 +444,15 @@ static int mcp16502_probe(struct i2c_client *client,
 	if (!mcp)
 		return -ENOMEM;
 
-	mcp->rmap = devm_regmap_init_i2c(client, &mcp16502_regmap_config);
-	if (IS_ERR(mcp->rmap)) {
-		ret = PTR_ERR(mcp->rmap);
+	rmap = devm_regmap_init_i2c(client, &mcp16502_regmap_config);
+	if (IS_ERR(rmap)) {
+		ret = PTR_ERR(rmap);
 		dev_err(dev, "regmap init failed: %d\n", ret);
 		return ret;
 	}
 
 	i2c_set_clientdata(client, mcp);
-	config.regmap = mcp->rmap;
+	config.regmap = rmap;
 	config.driver_data = mcp;
 
 	mcp->lpm = devm_gpiod_get(dev, "lpm", GPIOD_OUT_LOW);
@@ -490,9 +461,15 @@ static int mcp16502_probe(struct i2c_client *client,
 		return PTR_ERR(mcp->lpm);
 	}
 
-	ret = setup_regulators(mcp, dev, config);
-	if (ret != 0)
-		return ret;
+	for (i = 0; i < NUM_REGULATORS; i++) {
+		rdev = devm_regulator_register(dev, &mcp16502_desc[i], &config);
+		if (IS_ERR(rdev)) {
+			dev_err(dev,
+				"failed to register %s regulator %ld\n",
+				mcp16502_desc[i].name, PTR_ERR(rdev));
+			return PTR_ERR(rdev);
+		}
+	}
 
 	mcp16502_gpio_set_mode(mcp, MCP16502_OPMODE_ACTIVE);
 
diff --git a/drivers/regulator/mt6311-regulator.c b/drivers/regulator/mt6311-regulator.c
index 01d69f43d2b0..af95449d3590 100644
--- a/drivers/regulator/mt6311-regulator.c
+++ b/drivers/regulator/mt6311-regulator.c
@@ -1,16 +1,7 @@
-/*
- * Copyright (c) 2015 MediaTek Inc.
- * Author: Henry Chen <henryc.chen@mediatek.com>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- */
+// SPDX-License-Identifier: GPL-2.0
+//
+// Copyright (c) 2015 MediaTek Inc.
+// Author: Henry Chen <henryc.chen@mediatek.com>
 
 #include <linux/err.h>
 #include <linux/gpio.h>
diff --git a/drivers/regulator/mt6311-regulator.h b/drivers/regulator/mt6311-regulator.h
index 5218db46a798..4904d6751714 100644
--- a/drivers/regulator/mt6311-regulator.h
+++ b/drivers/regulator/mt6311-regulator.h
@@ -1,15 +1,7 @@
+/* SPDX-License-Identifier: GPL-2.0 */
 /*
  * Copyright (c) 2015 MediaTek Inc.
  * Author: Henry Chen <henryc.chen@mediatek.com>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
  */
 
 #ifndef __MT6311_REGULATOR_H__
diff --git a/drivers/regulator/mt6323-regulator.c b/drivers/regulator/mt6323-regulator.c
index b7b9670f0979..893ea190788a 100644
--- a/drivers/regulator/mt6323-regulator.c
+++ b/drivers/regulator/mt6323-regulator.c
@@ -1,11 +1,7 @@
-/*
- * Copyright (c) 2016 MediaTek Inc.
- * Author: Chen Zhong <chen.zhong@mediatek.com>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- */
+// SPDX-License-Identifier: GPL-2.0
+//
+// Copyright (c) 2016 MediaTek Inc.
+// Author: Chen Zhong <chen.zhong@mediatek.com>
 
 #include <linux/module.h>
 #include <linux/of.h>
@@ -118,43 +114,43 @@ static const struct regulator_linear_range buck_volt_range3[] = {
 	REGULATOR_LINEAR_RANGE(500000, 0, 0x3f, 50000),
 };
 
-static const u32 ldo_volt_table1[] = {
+static const unsigned int ldo_volt_table1[] = {
 	3300000, 3400000, 3500000, 3600000,
 };
 
-static const u32 ldo_volt_table2[] = {
+static const unsigned int ldo_volt_table2[] = {
 	1500000, 1800000, 2500000, 2800000,
 };
 
-static const u32 ldo_volt_table3[] = {
+static const unsigned int ldo_volt_table3[] = {
 	1800000, 3300000,
 };
 
-static const u32 ldo_volt_table4[] = {
+static const unsigned int ldo_volt_table4[] = {
 	3000000, 3300000,
 };
 
-static const u32 ldo_volt_table5[] = {
+static const unsigned int ldo_volt_table5[] = {
 	1200000, 1300000, 1500000, 1800000, 2000000, 2800000, 3000000, 3300000,
 };
 
-static const u32 ldo_volt_table6[] = {
+static const unsigned int ldo_volt_table6[] = {
 	1200000, 1300000, 1500000, 1800000, 2500000, 2800000, 3000000, 2000000,
 };
 
-static const u32 ldo_volt_table7[] = {
+static const unsigned int ldo_volt_table7[] = {
 	1200000, 1300000, 1500000, 1800000,
 };
 
-static const u32 ldo_volt_table8[] = {
+static const unsigned int ldo_volt_table8[] = {
 	1800000, 3000000,
 };
 
-static const u32 ldo_volt_table9[] = {
+static const unsigned int ldo_volt_table9[] = {
 	1200000, 1350000, 1500000, 1800000,
 };
 
-static const u32 ldo_volt_table10[] = {
+static const unsigned int ldo_volt_table10[] = {
 	1200000, 1300000, 1500000, 1800000,
 };
 
diff --git a/drivers/regulator/mt6380-regulator.c b/drivers/regulator/mt6380-regulator.c
index 127dd720cbcc..b6aed090b5e0 100644
--- a/drivers/regulator/mt6380-regulator.c
+++ b/drivers/regulator/mt6380-regulator.c
@@ -1,16 +1,7 @@
-/*
- * Copyright (c) 2017 MediaTek Inc.
- * Author: Chenglin Xu <chenglin.xu@mediatek.com>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- */
+// SPDX-License-Identifier: GPL-2.0
+//
+// Copyright (c) 2017 MediaTek Inc.
+// Author: Chenglin Xu <chenglin.xu@mediatek.com>
 
 #include <linux/module.h>
 #include <linux/of.h>
@@ -173,19 +164,19 @@ static const struct regulator_linear_range buck_volt_range3[] = {
 	REGULATOR_LINEAR_RANGE(1200000, 0, 0x3c, 25000),
 };
 
-static const u32 ldo_volt_table1[] = {
+static const unsigned int ldo_volt_table1[] = {
 	1400000, 1350000, 1300000, 1250000, 1200000, 1150000, 1100000, 1050000,
 };
 
-static const u32 ldo_volt_table2[] = {
+static const unsigned int ldo_volt_table2[] = {
 	2200000, 3300000,
 };
 
-static const u32 ldo_volt_table3[] = {
+static const unsigned int ldo_volt_table3[] = {
 	1240000, 1390000, 1540000, 1840000,
 };
 
-static const u32 ldo_volt_table4[] = {
+static const unsigned int ldo_volt_table4[] = {
 	2200000, 3300000,
 };
 
diff --git a/drivers/regulator/mt6397-regulator.c b/drivers/regulator/mt6397-regulator.c
index c6c6aa85e4e8..fd9ed864a0c1 100644
--- a/drivers/regulator/mt6397-regulator.c
+++ b/drivers/regulator/mt6397-regulator.c
@@ -1,16 +1,7 @@
-/*
- * Copyright (c) 2014 MediaTek Inc.
- * Author: Flora Fu <flora.fu@mediatek.com>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- */
+// SPDX-License-Identifier: GPL-2.0
+//
+// Copyright (c) 2014 MediaTek Inc.
+// Author: Flora Fu <flora.fu@mediatek.com>
 
 #include <linux/module.h>
 #include <linux/of.h>
@@ -123,35 +114,35 @@ static const struct regulator_linear_range buck_volt_range3[] = {
 	REGULATOR_LINEAR_RANGE(1500000, 0, 0x1f, 20000),
 };
 
-static const u32 ldo_volt_table1[] = {
+static const unsigned int ldo_volt_table1[] = {
 	1500000, 1800000, 2500000, 2800000,
 };
 
-static const u32 ldo_volt_table2[] = {
+static const unsigned int ldo_volt_table2[] = {
 	1800000, 3300000,
 };
 
-static const u32 ldo_volt_table3[] = {
+static const unsigned int ldo_volt_table3[] = {
 	3000000, 3300000,
 };
 
-static const u32 ldo_volt_table4[] = {
+static const unsigned int ldo_volt_table4[] = {
 	1220000, 1300000, 1500000, 1800000, 2500000, 2800000, 3000000, 3300000,
 };
 
-static const u32 ldo_volt_table5[] = {
+static const unsigned int ldo_volt_table5[] = {
 	1200000, 1300000, 1500000, 1800000, 2500000, 2800000, 3000000, 3300000,
 };
 
-static const u32 ldo_volt_table5_v2[] = {
+static const unsigned int ldo_volt_table5_v2[] = {
 	1200000, 1000000, 1500000, 1800000, 2500000, 2800000, 3000000, 3300000,
 };
 
-static const u32 ldo_volt_table6[] = {
+static const unsigned int ldo_volt_table6[] = {
 	1200000, 1300000, 1500000, 1800000, 2500000, 2800000, 3000000, 2000000,
 };
 
-static const u32 ldo_volt_table7[] = {
+static const unsigned int ldo_volt_table7[] = {
 	1300000, 1500000, 1800000, 2000000, 2500000, 2800000, 3000000, 3300000,
 };
 
diff --git a/drivers/regulator/of_regulator.c b/drivers/regulator/of_regulator.c
index 7b6bf3536271..6dca0ba044d8 100644
--- a/drivers/regulator/of_regulator.c
+++ b/drivers/regulator/of_regulator.c
@@ -371,8 +371,9 @@ int of_regulator_match(struct device *dev, struct device_node *node,
 }
 EXPORT_SYMBOL_GPL(of_regulator_match);
 
-struct device_node *regulator_of_get_init_node(struct device *dev,
-					       const struct regulator_desc *desc)
+static struct
+device_node *regulator_of_get_init_node(struct device *dev,
+					const struct regulator_desc *desc)
 {
 	struct device_node *search, *child;
 	const char *name;
diff --git a/drivers/regulator/palmas-regulator.c b/drivers/regulator/palmas-regulator.c
index 7fb9e8dd834e..f13c7c8b1061 100644
--- a/drivers/regulator/palmas-regulator.c
+++ b/drivers/regulator/palmas-regulator.c
@@ -991,9 +991,6 @@ static int palmas_ldo_registration(struct palmas_pmic *pmic,
 			return PTR_ERR(rdev);
 		}
 
-		/* Save regulator for cleanup */
-		pmic->rdev[id] = rdev;
-
 		/* Initialise sleep/init values from platform data */
 		if (pdata) {
 			reg_init = pdata->reg_init[id];
@@ -1101,9 +1098,6 @@ static int tps65917_ldo_registration(struct palmas_pmic *pmic,
 			return PTR_ERR(rdev);
 		}
 
-		/* Save regulator for cleanup */
-		pmic->rdev[id] = rdev;
-
 		/* Initialise sleep/init values from platform data */
 		if (pdata) {
 			reg_init = pdata->reg_init[id];
@@ -1288,9 +1282,6 @@ static int palmas_smps_registration(struct palmas_pmic *pmic,
 				pdev_name);
 			return PTR_ERR(rdev);
 		}
-
-		/* Save regulator for cleanup */
-		pmic->rdev[id] = rdev;
 	}
 
 	return 0;
@@ -1395,9 +1386,6 @@ static int tps65917_smps_registration(struct palmas_pmic *pmic,
 				pdev_name);
 			return PTR_ERR(rdev);
 		}
-
-		/* Save regulator for cleanup */
-		pmic->rdev[id] = rdev;
 	}
 
 	return 0;
diff --git a/drivers/regulator/pv88060-regulator.c b/drivers/regulator/pv88060-regulator.c
index 1600f9821891..3d3415839ba2 100644
--- a/drivers/regulator/pv88060-regulator.c
+++ b/drivers/regulator/pv88060-regulator.c
@@ -1,17 +1,7 @@
-/*
- * pv88060-regulator.c - Regulator device driver for PV88060
- * Copyright (C) 2015  Powerventure Semiconductor Ltd.
- *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of the GNU General Public License
- * as published by the Free Software Foundation; either version 2
- * of the License, or (at your option) any later version.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- */
+// SPDX-License-Identifier: GPL-2.0+
+//
+// pv88060-regulator.c - Regulator device driver for PV88060
+// Copyright (C) 2015  Powerventure Semiconductor Ltd.
 
 #include <linux/err.h>
 #include <linux/i2c.h>
@@ -244,9 +234,11 @@ static irqreturn_t pv88060_irq_handler(int irq, void *data)
 	if (reg_val & PV88060_E_VDD_FLT) {
 		for (i = 0; i < PV88060_MAX_REGULATORS; i++) {
 			if (chip->rdev[i] != NULL) {
+				regulator_lock(chip->rdev[i]);
 				regulator_notifier_call_chain(chip->rdev[i],
 					REGULATOR_EVENT_UNDER_VOLTAGE,
 					NULL);
+				regulator_unlock(chip->rdev[i]);
 			}
 		}
 
@@ -261,9 +253,11 @@ static irqreturn_t pv88060_irq_handler(int irq, void *data)
 	if (reg_val & PV88060_E_OVER_TEMP) {
 		for (i = 0; i < PV88060_MAX_REGULATORS; i++) {
 			if (chip->rdev[i] != NULL) {
+				regulator_lock(chip->rdev[i]);
 				regulator_notifier_call_chain(chip->rdev[i],
 					REGULATOR_EVENT_OVER_TEMP,
 					NULL);
+				regulator_unlock(chip->rdev[i]);
 			}
 		}
 
diff --git a/drivers/regulator/pv88060-regulator.h b/drivers/regulator/pv88060-regulator.h
index 02ca9203a172..d333dbf3be94 100644
--- a/drivers/regulator/pv88060-regulator.h
+++ b/drivers/regulator/pv88060-regulator.h
@@ -1,16 +1,7 @@
+/* SPDX-License-Identifier: GPL-2.0+ */
 /*
  * pv88060-regulator.h - Regulator definitions for PV88060
  * Copyright (C) 2015 Powerventure Semiconductor Ltd.
- *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of the GNU General Public License
- * as published by the Free Software Foundation; either version 2
- * of the License, or (at your option) any later version.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
  */
 
 #ifndef __PV88060_REGISTERS_H__
diff --git a/drivers/regulator/pv88080-regulator.c b/drivers/regulator/pv88080-regulator.c
index bdddacdbeb99..a444f68af1a8 100644
--- a/drivers/regulator/pv88080-regulator.c
+++ b/drivers/regulator/pv88080-regulator.c
@@ -1,17 +1,7 @@
-/*
- * pv88080-regulator.c - Regulator device driver for PV88080
- * Copyright (C) 2016  Powerventure Semiconductor Ltd.
- *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of the GNU General Public License
- * as published by the Free Software Foundation; either version 2
- * of the License, or (at your option) any later version.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- */
+// SPDX-License-Identifier: GPL-2.0+
+//
+// pv88080-regulator.c - Regulator device driver for PV88080
+// Copyright (C) 2016  Powerventure Semiconductor Ltd.
 
 #include <linux/err.h>
 #include <linux/i2c.h>
@@ -345,9 +335,11 @@ static irqreturn_t pv88080_irq_handler(int irq, void *data)
 	if (reg_val & PV88080_E_VDD_FLT) {
 		for (i = 0; i < PV88080_MAX_REGULATORS; i++) {
 			if (chip->rdev[i] != NULL) {
+			        regulator_lock(chip->rdev[i]);
 				regulator_notifier_call_chain(chip->rdev[i],
 					REGULATOR_EVENT_UNDER_VOLTAGE,
 					NULL);
+			        regulator_unlock(chip->rdev[i]);
 			}
 		}
 
@@ -362,9 +354,11 @@ static irqreturn_t pv88080_irq_handler(int irq, void *data)
 	if (reg_val & PV88080_E_OVER_TEMP) {
 		for (i = 0; i < PV88080_MAX_REGULATORS; i++) {
 			if (chip->rdev[i] != NULL) {
+			        regulator_lock(chip->rdev[i]);
 				regulator_notifier_call_chain(chip->rdev[i],
 					REGULATOR_EVENT_OVER_TEMP,
 					NULL);
+			        regulator_unlock(chip->rdev[i]);
 			}
 		}
 
diff --git a/drivers/regulator/pv88080-regulator.h b/drivers/regulator/pv88080-regulator.h
index ae25ff360e3d..7d7f8f11a75a 100644
--- a/drivers/regulator/pv88080-regulator.h
+++ b/drivers/regulator/pv88080-regulator.h
@@ -1,16 +1,7 @@
+/* SPDX-License-Identifier: GPL-2.0+ */
 /*
  * pv88080-regulator.h - Regulator definitions for PV88080
  * Copyright (C) 2016 Powerventure Semiconductor Ltd.
- *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of the GNU General Public License
- * as published by the Free Software Foundation; either version 2
- * of the License, or (at your option) any later version.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
  */
 
 #ifndef __PV88080_REGISTERS_H__
diff --git a/drivers/regulator/pv88090-regulator.c b/drivers/regulator/pv88090-regulator.c
index 6e97cc6df2ee..b1d0d97ae935 100644
--- a/drivers/regulator/pv88090-regulator.c
+++ b/drivers/regulator/pv88090-regulator.c
@@ -1,17 +1,7 @@
-/*
- * pv88090-regulator.c - Regulator device driver for PV88090
- * Copyright (C) 2015  Powerventure Semiconductor Ltd.
- *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of the GNU General Public License
- * as published by the Free Software Foundation; either version 2
- * of the License, or (at your option) any later version.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- */
+// SPDX-License-Identifier: GPL-2.0+
+//
+// pv88090-regulator.c - Regulator device driver for PV88090
+// Copyright (C) 2015  Powerventure Semiconductor Ltd.
 
 #include <linux/err.h>
 #include <linux/i2c.h>
@@ -237,9 +227,11 @@ static irqreturn_t pv88090_irq_handler(int irq, void *data)
 	if (reg_val & PV88090_E_VDD_FLT) {
 		for (i = 0; i < PV88090_MAX_REGULATORS; i++) {
 			if (chip->rdev[i] != NULL) {
+			        regulator_lock(chip->rdev[i]);
 				regulator_notifier_call_chain(chip->rdev[i],
 					REGULATOR_EVENT_UNDER_VOLTAGE,
 					NULL);
+			        regulator_unlock(chip->rdev[i]);
 			}
 		}
 
@@ -254,9 +246,11 @@ static irqreturn_t pv88090_irq_handler(int irq, void *data)
 	if (reg_val & PV88090_E_OVER_TEMP) {
 		for (i = 0; i < PV88090_MAX_REGULATORS; i++) {
 			if (chip->rdev[i] != NULL) {
+			        regulator_lock(chip->rdev[i]);
 				regulator_notifier_call_chain(chip->rdev[i],
 					REGULATOR_EVENT_OVER_TEMP,
 					NULL);
+			        regulator_unlock(chip->rdev[i]);
 			}
 		}
 
diff --git a/drivers/regulator/pv88090-regulator.h b/drivers/regulator/pv88090-regulator.h
index 62d9029277f4..f814ee52cff3 100644
--- a/drivers/regulator/pv88090-regulator.h
+++ b/drivers/regulator/pv88090-regulator.h
@@ -1,16 +1,7 @@
+/* SPDX-License-Identifier: GPL-2.0+ */
 /*
  * pv88090-regulator.h - Regulator definitions for PV88090
  * Copyright (C) 2015 Powerventure Semiconductor Ltd.
- *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of the GNU General Public License
- * as published by the Free Software Foundation; either version 2
- * of the License, or (at your option) any later version.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
  */
 
 #ifndef __PV88090_REGISTERS_H__
diff --git a/drivers/regulator/rc5t583-regulator.c b/drivers/regulator/rc5t583-regulator.c
index 2ec51af43673..9446653e7a89 100644
--- a/drivers/regulator/rc5t583-regulator.c
+++ b/drivers/regulator/rc5t583-regulator.c
@@ -47,18 +47,13 @@ struct rc5t583_regulator_info {
 	struct regulator_desc	desc;
 };
 
-struct rc5t583_regulator {
-	struct rc5t583_regulator_info *reg_info;
-	struct regulator_dev	*rdev;
-};
-
 static int rc5t583_regulator_enable_time(struct regulator_dev *rdev)
 {
-	struct rc5t583_regulator *reg = rdev_get_drvdata(rdev);
+	struct rc5t583_regulator_info *reg_info = rdev_get_drvdata(rdev);
 	int vsel = regulator_get_voltage_sel_regmap(rdev);
 	int curr_uV = regulator_list_voltage_linear(rdev, vsel);
 
-	return DIV_ROUND_UP(curr_uV, reg->reg_info->enable_uv_per_us);
+	return DIV_ROUND_UP(curr_uV, reg_info->enable_uv_per_us);
 }
 
 static const struct regulator_ops rc5t583_ops = {
@@ -120,8 +115,6 @@ static int rc5t583_regulator_probe(struct platform_device *pdev)
 	struct rc5t583 *rc5t583 = dev_get_drvdata(pdev->dev.parent);
 	struct rc5t583_platform_data *pdata = dev_get_platdata(rc5t583->dev);
 	struct regulator_config config = { };
-	struct rc5t583_regulator *reg = NULL;
-	struct rc5t583_regulator *regs;
 	struct regulator_dev *rdev;
 	struct rc5t583_regulator_info *ri;
 	int ret;
@@ -132,18 +125,8 @@ static int rc5t583_regulator_probe(struct platform_device *pdev)
 		return -ENODEV;
 	}
 
-	regs = devm_kcalloc(&pdev->dev,
-			    RC5T583_REGULATOR_MAX,
-			    sizeof(struct rc5t583_regulator),
-			    GFP_KERNEL);
-	if (!regs)
-		return -ENOMEM;
-
-
 	for (id = 0; id < RC5T583_REGULATOR_MAX; ++id) {
-		reg = &regs[id];
 		ri = &rc5t583_reg_info[id];
-		reg->reg_info = ri;
 
 		if (ri->deepsleep_id == RC5T583_DS_NONE)
 			goto skip_ext_pwr_config;
@@ -163,7 +146,7 @@ static int rc5t583_regulator_probe(struct platform_device *pdev)
 skip_ext_pwr_config:
 		config.dev = &pdev->dev;
 		config.init_data = pdata->reg_init_data[id];
-		config.driver_data = reg;
+		config.driver_data = ri;
 		config.regmap = rc5t583->regmap;
 
 		rdev = devm_regulator_register(&pdev->dev, &ri->desc, &config);
@@ -172,9 +155,7 @@ skip_ext_pwr_config:
 						ri->desc.name);
 			return PTR_ERR(rdev);
 		}
-		reg->rdev = rdev;
 	}
-	platform_set_drvdata(pdev, regs);
 	return 0;
 }
 
diff --git a/drivers/regulator/rn5t618-regulator.c b/drivers/regulator/rn5t618-regulator.c
index 790a4a73ea2c..a79c0c43b9f8 100644
--- a/drivers/regulator/rn5t618-regulator.c
+++ b/drivers/regulator/rn5t618-regulator.c
@@ -46,7 +46,7 @@ static const struct regulator_ops rn5t618_reg_ops = {
 		.vsel_mask	= (vmask),				\
 	}
 
-static struct regulator_desc rn5t567_regulators[] = {
+static const struct regulator_desc rn5t567_regulators[] = {
 	/* DCDC */
 	REG(DCDC1, DC1CTL, BIT(0), DC1DAC, 0xff, 600000, 3500000, 12500),
 	REG(DCDC2, DC2CTL, BIT(0), DC2DAC, 0xff, 600000, 3500000, 12500),
@@ -63,7 +63,7 @@ static struct regulator_desc rn5t567_regulators[] = {
 	REG(LDORTC2, LDOEN2, BIT(5), LDORTC2DAC, 0x7f, 900000, 3500000, 25000),
 };
 
-static struct regulator_desc rn5t618_regulators[] = {
+static const struct regulator_desc rn5t618_regulators[] = {
 	/* DCDC */
 	REG(DCDC1, DC1CTL, BIT(0), DC1DAC, 0xff, 600000, 3500000, 12500),
 	REG(DCDC2, DC2CTL, BIT(0), DC2DAC, 0xff, 600000, 3500000, 12500),
@@ -79,7 +79,7 @@ static struct regulator_desc rn5t618_regulators[] = {
 	REG(LDORTC2, LDOEN2, BIT(5), LDORTC2DAC, 0x7f, 900000, 3500000, 25000),
 };
 
-static struct regulator_desc rc5t619_regulators[] = {
+static const struct regulator_desc rc5t619_regulators[] = {
 	/* DCDC */
 	REG(DCDC1, DC1CTL, BIT(0), DC1DAC, 0xff, 600000, 3500000, 12500),
 	REG(DCDC2, DC2CTL, BIT(0), DC2DAC, 0xff, 600000, 3500000, 12500),
@@ -107,7 +107,7 @@ static int rn5t618_regulator_probe(struct platform_device *pdev)
 	struct rn5t618 *rn5t618 = dev_get_drvdata(pdev->dev.parent);
 	struct regulator_config config = { };
 	struct regulator_dev *rdev;
-	struct regulator_desc *regulators;
+	const struct regulator_desc *regulators;
 	int i;
 	int num_regulators = 0;
 
diff --git a/drivers/regulator/s2mpa01.c b/drivers/regulator/s2mpa01.c
index 58a1fe583a6c..51f7e8b74d8c 100644
--- a/drivers/regulator/s2mpa01.c
+++ b/drivers/regulator/s2mpa01.c
@@ -17,10 +17,7 @@
 #include <linux/mfd/samsung/core.h>
 #include <linux/mfd/samsung/s2mpa01.h>
 
-#define S2MPA01_REGULATOR_CNT ARRAY_SIZE(regulators)
-
 struct s2mpa01_info {
-	struct of_regulator_match rdata[S2MPA01_REGULATOR_MAX];
 	int ramp_delay24;
 	int ramp_delay3;
 	int ramp_delay5;
@@ -232,6 +229,8 @@ static const struct regulator_ops s2mpa01_buck_ops = {
 
 #define regulator_desc_ldo(num, step) {			\
 	.name		= "LDO"#num,			\
+	.of_match	= of_match_ptr("LDO"#num),	\
+	.regulators_node = of_match_ptr("regulators"),	\
 	.id		= S2MPA01_LDO##num,		\
 	.ops		= &s2mpa01_ldo_ops,		\
 	.type		= REGULATOR_VOLTAGE,		\
@@ -247,6 +246,8 @@ static const struct regulator_ops s2mpa01_buck_ops = {
 
 #define regulator_desc_buck1_4(num)	{			\
 	.name		= "BUCK"#num,				\
+	.of_match	= of_match_ptr("BUCK"#num),		\
+	.regulators_node = of_match_ptr("regulators"),		\
 	.id		= S2MPA01_BUCK##num,			\
 	.ops		= &s2mpa01_buck_ops,			\
 	.type		= REGULATOR_VOLTAGE,			\
@@ -263,6 +264,8 @@ static const struct regulator_ops s2mpa01_buck_ops = {
 
 #define regulator_desc_buck5	{				\
 	.name		= "BUCK5",				\
+	.of_match	= of_match_ptr("BUCK5"),		\
+	.regulators_node = of_match_ptr("regulators"),		\
 	.id		= S2MPA01_BUCK5,			\
 	.ops		= &s2mpa01_buck_ops,			\
 	.type		= REGULATOR_VOLTAGE,			\
@@ -279,6 +282,8 @@ static const struct regulator_ops s2mpa01_buck_ops = {
 
 #define regulator_desc_buck6_10(num, min, step) {			\
 	.name		= "BUCK"#num,				\
+	.of_match	= of_match_ptr("BUCK"#num),		\
+	.regulators_node = of_match_ptr("regulators"),		\
 	.id		= S2MPA01_BUCK##num,			\
 	.ops		= &s2mpa01_buck_ops,			\
 	.type		= REGULATOR_VOLTAGE,			\
@@ -336,9 +341,7 @@ static int s2mpa01_pmic_probe(struct platform_device *pdev)
 {
 	struct sec_pmic_dev *iodev = dev_get_drvdata(pdev->dev.parent);
 	struct sec_platform_data *pdata = dev_get_platdata(iodev->dev);
-	struct device_node *reg_np = NULL;
 	struct regulator_config config = { };
-	struct of_regulator_match *rdata;
 	struct s2mpa01_info *s2mpa01;
 	int i;
 
@@ -346,39 +349,15 @@ static int s2mpa01_pmic_probe(struct platform_device *pdev)
 	if (!s2mpa01)
 		return -ENOMEM;
 
-	rdata = s2mpa01->rdata;
-	for (i = 0; i < S2MPA01_REGULATOR_CNT; i++)
-		rdata[i].name = regulators[i].name;
-
-	if (iodev->dev->of_node) {
-		reg_np = of_get_child_by_name(iodev->dev->of_node,
-							"regulators");
-		if (!reg_np) {
-			dev_err(&pdev->dev,
-				"could not find regulators sub-node\n");
-			return -EINVAL;
-		}
-
-		of_regulator_match(&pdev->dev, reg_np, rdata,
-						S2MPA01_REGULATOR_MAX);
-		of_node_put(reg_np);
-	}
-
-	platform_set_drvdata(pdev, s2mpa01);
-
-	config.dev = &pdev->dev;
+	config.dev = iodev->dev;
 	config.regmap = iodev->regmap_pmic;
 	config.driver_data = s2mpa01;
 
 	for (i = 0; i < S2MPA01_REGULATOR_MAX; i++) {
 		struct regulator_dev *rdev;
+
 		if (pdata)
 			config.init_data = pdata->regulators[i].initdata;
-		else
-			config.init_data = rdata[i].init_data;
-
-		if (reg_np)
-			config.of_node = rdata[i].of_node;
 
 		rdev = devm_regulator_register(&pdev->dev,
 						&regulators[i], &config);
diff --git a/drivers/regulator/sc2731-regulator.c b/drivers/regulator/sc2731-regulator.c
index eb2bdf060b7b..0f21f95c8981 100644
--- a/drivers/regulator/sc2731-regulator.c
+++ b/drivers/regulator/sc2731-regulator.c
@@ -146,7 +146,7 @@ static const struct regulator_ops sc2731_regu_linear_ops = {
 	.vsel_mask		= vmask,			\
 }
 
-static struct regulator_desc regulators[] = {
+static const struct regulator_desc regulators[] = {
 	SC2731_REGU_LINEAR(BUCK_CPU0, SC2731_POWER_PD_SW,
 			   SC2731_DCDC_CPU0_PD_MASK, SC2731_DCDC_CPU0_VOL,
 			   SC2731_DCDC_CPU0_VOL_MASK, 3125, 400000, 1996875),
diff --git a/drivers/regulator/sky81452-regulator.c b/drivers/regulator/sky81452-regulator.c
index 647860611916..177dede82a61 100644
--- a/drivers/regulator/sky81452-regulator.c
+++ b/drivers/regulator/sky81452-regulator.c
@@ -1,21 +1,9 @@
-/*
- * sky81452-regulator.c	SKY81452 regulator driver
- *
- * Copyright 2014 Skyworks Solutions Inc.
- * Author : Gyungoh Yoo <jack.yoo@skyworksinc.com>
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms of the GNU General Public License version 2
- * as published by the Free Software Foundation.
- *
- * This program is distributed in the hope that it will be useful, but
- * WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
- * General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License along
- * with this program; if not, see <http://www.gnu.org/licenses/>.
- */
+// SPDX-License-Identifier: GPL-2.0
+//
+// sky81452-regulator.c	SKY81452 regulator driver
+//
+// Copyright 2014 Skyworks Solutions Inc.
+// Author : Gyungoh Yoo <jack.yoo@skyworksinc.com>
 
 #include <linux/module.h>
 #include <linux/kernel.h>
@@ -34,7 +22,7 @@
 #define SKY81452_LEN	0x40
 #define SKY81452_LOUT	0x1F
 
-static struct regulator_ops sky81452_reg_ops = {
+static const struct regulator_ops sky81452_reg_ops = {
 	.list_voltage = regulator_list_voltage_linear_range,
 	.map_voltage = regulator_map_voltage_linear_range,
 	.get_voltage_sel = regulator_get_voltage_sel_regmap,
diff --git a/drivers/regulator/stm32-pwr.c b/drivers/regulator/stm32-pwr.c
new file mode 100644
index 000000000000..e0e627b0106e
--- /dev/null
+++ b/drivers/regulator/stm32-pwr.c
@@ -0,0 +1,186 @@
+// SPDX-License-Identifier: GPL-2.0
+// Copyright (C) STMicroelectronics 2019
+// Authors: Gabriel Fernandez <gabriel.fernandez@st.com>
+//          Pascal Paillet <p.paillet@st.com>.
+
+#include <linux/io.h>
+#include <linux/iopoll.h>
+#include <linux/module.h>
+#include <linux/of_address.h>
+#include <linux/of_device.h>
+#include <linux/platform_device.h>
+#include <linux/regulator/driver.h>
+#include <linux/regulator/of_regulator.h>
+
+/*
+ * Registers description
+ */
+#define REG_PWR_CR3 0x0C
+
+#define USB_3_3_EN BIT(24)
+#define USB_3_3_RDY BIT(26)
+#define REG_1_8_EN BIT(28)
+#define REG_1_8_RDY BIT(29)
+#define REG_1_1_EN BIT(30)
+#define REG_1_1_RDY BIT(31)
+
+/* list of supported regulators */
+enum {
+	PWR_REG11,
+	PWR_REG18,
+	PWR_USB33,
+	STM32PWR_REG_NUM_REGS
+};
+
+static u32 ready_mask_table[STM32PWR_REG_NUM_REGS] = {
+	[PWR_REG11] = REG_1_1_RDY,
+	[PWR_REG18] = REG_1_8_RDY,
+	[PWR_USB33] = USB_3_3_RDY,
+};
+
+struct stm32_pwr_reg {
+	void __iomem *base;
+	u32 ready_mask;
+};
+
+static int stm32_pwr_reg_is_ready(struct regulator_dev *rdev)
+{
+	struct stm32_pwr_reg *priv = rdev_get_drvdata(rdev);
+	u32 val;
+
+	val = readl_relaxed(priv->base + REG_PWR_CR3);
+
+	return (val & priv->ready_mask);
+}
+
+static int stm32_pwr_reg_is_enabled(struct regulator_dev *rdev)
+{
+	struct stm32_pwr_reg *priv = rdev_get_drvdata(rdev);
+	u32 val;
+
+	val = readl_relaxed(priv->base + REG_PWR_CR3);
+
+	return (val & rdev->desc->enable_mask);
+}
+
+static int stm32_pwr_reg_enable(struct regulator_dev *rdev)
+{
+	struct stm32_pwr_reg *priv = rdev_get_drvdata(rdev);
+	int ret;
+	u32 val;
+
+	val = readl_relaxed(priv->base + REG_PWR_CR3);
+	val |= rdev->desc->enable_mask;
+	writel_relaxed(val, priv->base + REG_PWR_CR3);
+
+	/* use an arbitrary timeout of 20ms */
+	ret = readx_poll_timeout(stm32_pwr_reg_is_ready, rdev, val, val,
+				 100, 20 * 1000);
+	if (ret)
+		dev_err(&rdev->dev, "regulator enable timed out!\n");
+
+	return ret;
+}
+
+static int stm32_pwr_reg_disable(struct regulator_dev *rdev)
+{
+	struct stm32_pwr_reg *priv = rdev_get_drvdata(rdev);
+	int ret;
+	u32 val;
+
+	val = readl_relaxed(priv->base + REG_PWR_CR3);
+	val &= ~rdev->desc->enable_mask;
+	writel_relaxed(val, priv->base + REG_PWR_CR3);
+
+	/* use an arbitrary timeout of 20ms */
+	ret = readx_poll_timeout(stm32_pwr_reg_is_ready, rdev, val, !val,
+				 100, 20 * 1000);
+	if (ret)
+		dev_err(&rdev->dev, "regulator disable timed out!\n");
+
+	return ret;
+}
+
+static const struct regulator_ops stm32_pwr_reg_ops = {
+	.enable		= stm32_pwr_reg_enable,
+	.disable	= stm32_pwr_reg_disable,
+	.is_enabled	= stm32_pwr_reg_is_enabled,
+};
+
+#define PWR_REG(_id, _name, _volt, _en, _supply) \
+	[_id] = { \
+		.id = _id, \
+		.name = _name, \
+		.of_match = of_match_ptr(_name), \
+		.n_voltages = 1, \
+		.type = REGULATOR_VOLTAGE, \
+		.fixed_uV = _volt, \
+		.ops = &stm32_pwr_reg_ops, \
+		.enable_mask = _en, \
+		.owner = THIS_MODULE, \
+		.supply_name = _supply, \
+	} \
+
+static const struct regulator_desc stm32_pwr_desc[] = {
+	PWR_REG(PWR_REG11, "reg11", 1100000, REG_1_1_EN, "vdd"),
+	PWR_REG(PWR_REG18, "reg18", 1800000, REG_1_8_EN, "vdd"),
+	PWR_REG(PWR_USB33, "usb33", 3300000, USB_3_3_EN, "vdd_3v3_usbfs"),
+};
+
+static int stm32_pwr_regulator_probe(struct platform_device *pdev)
+{
+	struct device_node *np = pdev->dev.of_node;
+	struct stm32_pwr_reg *priv;
+	void __iomem *base;
+	struct regulator_dev *rdev;
+	struct regulator_config config = { };
+	int i, ret = 0;
+
+	base = of_iomap(np, 0);
+	if (!base) {
+		dev_err(&pdev->dev, "Unable to map IO memory\n");
+		return -ENOMEM;
+	}
+
+	config.dev = &pdev->dev;
+
+	for (i = 0; i < STM32PWR_REG_NUM_REGS; i++) {
+		priv = devm_kzalloc(&pdev->dev, sizeof(struct stm32_pwr_reg),
+				    GFP_KERNEL);
+		if (!priv)
+			return -ENOMEM;
+		priv->base = base;
+		priv->ready_mask = ready_mask_table[i];
+		config.driver_data = priv;
+
+		rdev = devm_regulator_register(&pdev->dev,
+					       &stm32_pwr_desc[i],
+					       &config);
+		if (IS_ERR(rdev)) {
+			ret = PTR_ERR(rdev);
+			dev_err(&pdev->dev,
+				"Failed to register regulator: %d\n", ret);
+			break;
+		}
+	}
+	return ret;
+}
+
+static const struct of_device_id stm32_pwr_of_match[] = {
+	{ .compatible = "st,stm32mp1,pwr-reg", },
+	{},
+};
+MODULE_DEVICE_TABLE(of, stm32_pwr_of_match);
+
+static struct platform_driver stm32_pwr_driver = {
+	.probe = stm32_pwr_regulator_probe,
+	.driver = {
+		.name  = "stm32-pwr-regulator",
+		.of_match_table = of_match_ptr(stm32_pwr_of_match),
+	},
+};
+module_platform_driver(stm32_pwr_driver);
+
+MODULE_DESCRIPTION("STM32MP1 PWR voltage regulator driver");
+MODULE_AUTHOR("Pascal Paillet <p.paillet@st.com>");
+MODULE_LICENSE("GPL v2");
diff --git a/drivers/regulator/sy8106a-regulator.c b/drivers/regulator/sy8106a-regulator.c
index 65fbd1f0b612..42e03b2c10a0 100644
--- a/drivers/regulator/sy8106a-regulator.c
+++ b/drivers/regulator/sy8106a-regulator.c
@@ -22,12 +22,6 @@
  */
 #define SY8106A_GO_BIT			BIT(7)
 
-struct sy8106a {
-	struct regulator_dev *rdev;
-	struct regmap *regmap;
-	u32 fixed_voltage;
-};
-
 static const struct regmap_config sy8106a_regmap_config = {
 	.reg_bits = 8,
 	.val_bits = 8,
@@ -70,36 +64,32 @@ static const struct regulator_desc sy8106a_reg = {
 static int sy8106a_i2c_probe(struct i2c_client *i2c,
 			    const struct i2c_device_id *id)
 {
-	struct sy8106a *chip;
 	struct device *dev = &i2c->dev;
-	struct regulator_dev *rdev = NULL;
+	struct regulator_dev *rdev;
 	struct regulator_config config = { };
+	struct regmap *regmap;
 	unsigned int reg, vsel;
+	u32 fixed_voltage;
 	int error;
 
-	chip = devm_kzalloc(&i2c->dev, sizeof(struct sy8106a), GFP_KERNEL);
-	if (!chip)
-		return -ENOMEM;
-
 	error = of_property_read_u32(dev->of_node, "silergy,fixed-microvolt",
-				     &chip->fixed_voltage);
+				     &fixed_voltage);
 	if (error)
 		return error;
 
-	if (chip->fixed_voltage < SY8106A_MIN_MV * 1000 ||
-	    chip->fixed_voltage > SY8106A_MAX_MV * 1000)
+	if (fixed_voltage < SY8106A_MIN_MV * 1000 ||
+	    fixed_voltage > SY8106A_MAX_MV * 1000)
 		return -EINVAL;
 
-	chip->regmap = devm_regmap_init_i2c(i2c, &sy8106a_regmap_config);
-	if (IS_ERR(chip->regmap)) {
-		error = PTR_ERR(chip->regmap);
+	regmap = devm_regmap_init_i2c(i2c, &sy8106a_regmap_config);
+	if (IS_ERR(regmap)) {
+		error = PTR_ERR(regmap);
 		dev_err(dev, "Failed to allocate register map: %d\n", error);
 		return error;
 	}
 
 	config.dev = &i2c->dev;
-	config.regmap = chip->regmap;
-	config.driver_data = chip;
+	config.regmap = regmap;
 
 	config.of_node = dev->of_node;
 	config.init_data = of_get_regulator_init_data(dev, dev->of_node,
@@ -109,15 +99,15 @@ static int sy8106a_i2c_probe(struct i2c_client *i2c,
 		return -ENOMEM;
 
 	/* Ensure GO_BIT is enabled when probing */
-	error = regmap_read(chip->regmap, SY8106A_REG_VOUT1_SEL, &reg);
+	error = regmap_read(regmap, SY8106A_REG_VOUT1_SEL, &reg);
 	if (error)
 		return error;
 
 	if (!(reg & SY8106A_GO_BIT)) {
-		vsel = (chip->fixed_voltage / 1000 - SY8106A_MIN_MV) /
+		vsel = (fixed_voltage / 1000 - SY8106A_MIN_MV) /
 		       SY8106A_STEP_MV;
 
-		error = regmap_write(chip->regmap, SY8106A_REG_VOUT1_SEL,
+		error = regmap_write(regmap, SY8106A_REG_VOUT1_SEL,
 				     vsel | SY8106A_GO_BIT);
 		if (error)
 			return error;
@@ -131,10 +121,6 @@ static int sy8106a_i2c_probe(struct i2c_client *i2c,
 		return error;
 	}
 
-	chip->rdev = rdev;
-
-	i2c_set_clientdata(i2c, chip);
-
 	return 0;
 }
 
diff --git a/drivers/regulator/tps6507x-regulator.c b/drivers/regulator/tps6507x-regulator.c
index c179a3a221af..a1b7fab91dd4 100644
--- a/drivers/regulator/tps6507x-regulator.c
+++ b/drivers/regulator/tps6507x-regulator.c
@@ -115,7 +115,6 @@ static struct tps_info tps6507x_pmic_regs[] = {
 struct tps6507x_pmic {
 	struct regulator_desc desc[TPS6507X_NUM_REGULATOR];
 	struct tps6507x_dev *mfd;
-	struct regulator_dev *rdev[TPS6507X_NUM_REGULATOR];
 	struct tps_info *info[TPS6507X_NUM_REGULATOR];
 	struct mutex io_lock;
 };
@@ -349,7 +348,7 @@ static int tps6507x_pmic_set_voltage_sel(struct regulator_dev *dev,
 	return tps6507x_pmic_reg_write(tps, reg, data);
 }
 
-static struct regulator_ops tps6507x_pmic_ops = {
+static const struct regulator_ops tps6507x_pmic_ops = {
 	.is_enabled = tps6507x_pmic_is_enabled,
 	.enable = tps6507x_pmic_enable,
 	.disable = tps6507x_pmic_disable,
@@ -359,66 +358,20 @@ static struct regulator_ops tps6507x_pmic_ops = {
 	.map_voltage = regulator_map_voltage_ascend,
 };
 
-static struct of_regulator_match tps6507x_matches[] = {
-	{ .name = "VDCDC1"},
-	{ .name = "VDCDC2"},
-	{ .name = "VDCDC3"},
-	{ .name = "LDO1"},
-	{ .name = "LDO2"},
-};
-
-static struct tps6507x_board *tps6507x_parse_dt_reg_data(
-		struct platform_device *pdev,
-		struct of_regulator_match **tps6507x_reg_matches)
+static int tps6507x_pmic_of_parse_cb(struct device_node *np,
+				     const struct regulator_desc *desc,
+				     struct regulator_config *config)
 {
-	struct tps6507x_board *tps_board;
-	struct device_node *np = pdev->dev.parent->of_node;
-	struct device_node *regulators;
-	struct of_regulator_match *matches;
-	struct regulator_init_data *reg_data;
-	int idx = 0, count, ret;
-
-	tps_board = devm_kzalloc(&pdev->dev, sizeof(*tps_board),
-					GFP_KERNEL);
-	if (!tps_board)
-		return NULL;
-
-	regulators = of_get_child_by_name(np, "regulators");
-	if (!regulators) {
-		dev_err(&pdev->dev, "regulator node not found\n");
-		return NULL;
-	}
-
-	count = ARRAY_SIZE(tps6507x_matches);
-	matches = tps6507x_matches;
-
-	ret = of_regulator_match(&pdev->dev, regulators, matches, count);
-	of_node_put(regulators);
-	if (ret < 0) {
-		dev_err(&pdev->dev, "Error parsing regulator init data: %d\n",
-			ret);
-		return NULL;
-	}
+	struct tps6507x_pmic *tps = config->driver_data;
+	struct tps_info *info = tps->info[desc->id];
+	u32 prop;
+	int ret;
 
-	*tps6507x_reg_matches = matches;
-
-	reg_data = devm_kzalloc(&pdev->dev, (sizeof(struct regulator_init_data)
-					* TPS6507X_NUM_REGULATOR), GFP_KERNEL);
-	if (!reg_data)
-		return NULL;
-
-	tps_board->tps6507x_pmic_init_data = reg_data;
-
-	for (idx = 0; idx < count; idx++) {
-		if (!matches[idx].init_data || !matches[idx].of_node)
-			continue;
-
-		memcpy(&reg_data[idx], matches[idx].init_data,
-				sizeof(struct regulator_init_data));
-
-	}
+	ret = of_property_read_u32(np, "ti,defdcdc_default", &prop);
+	if (!ret)
+		info->defdcdc_default = prop;
 
-	return tps_board;
+	return 0;
 }
 
 static int tps6507x_pmic_probe(struct platform_device *pdev)
@@ -426,14 +379,11 @@ static int tps6507x_pmic_probe(struct platform_device *pdev)
 	struct tps6507x_dev *tps6507x_dev = dev_get_drvdata(pdev->dev.parent);
 	struct tps_info *info = &tps6507x_pmic_regs[0];
 	struct regulator_config config = { };
-	struct regulator_init_data *init_data;
+	struct regulator_init_data *init_data = NULL;
 	struct regulator_dev *rdev;
 	struct tps6507x_pmic *tps;
 	struct tps6507x_board *tps_board;
-	struct of_regulator_match *tps6507x_reg_matches = NULL;
 	int i;
-	int error;
-	unsigned int prop;
 
 	/**
 	 * tps_board points to pmic related constants
@@ -441,20 +391,8 @@ static int tps6507x_pmic_probe(struct platform_device *pdev)
 	 */
 
 	tps_board = dev_get_platdata(tps6507x_dev->dev);
-	if (IS_ENABLED(CONFIG_OF) && !tps_board &&
-		tps6507x_dev->dev->of_node)
-		tps_board = tps6507x_parse_dt_reg_data(pdev,
-				&tps6507x_reg_matches);
-	if (!tps_board)
-		return -EINVAL;
-
-	/**
-	 * init_data points to array of regulator_init structures
-	 * coming from the board-evm file.
-	 */
-	init_data = tps_board->tps6507x_pmic_init_data;
-	if (!init_data)
-		return -EINVAL;
+	if (tps_board)
+		init_data = tps_board->tps6507x_pmic_init_data;
 
 	tps = devm_kzalloc(&pdev->dev, sizeof(*tps), GFP_KERNEL);
 	if (!tps)
@@ -468,13 +406,16 @@ static int tps6507x_pmic_probe(struct platform_device *pdev)
 	for (i = 0; i < TPS6507X_NUM_REGULATOR; i++, info++, init_data++) {
 		/* Register the regulators */
 		tps->info[i] = info;
-		if (init_data->driver_data) {
+		if (init_data && init_data->driver_data) {
 			struct tps6507x_reg_platform_data *data =
 					init_data->driver_data;
-			tps->info[i]->defdcdc_default = data->defdcdc_default;
+			info->defdcdc_default = data->defdcdc_default;
 		}
 
 		tps->desc[i].name = info->name;
+		tps->desc[i].of_match = of_match_ptr(info->name);
+		tps->desc[i].regulators_node = of_match_ptr("regulators");
+		tps->desc[i].of_parse_cb = tps6507x_pmic_of_parse_cb;
 		tps->desc[i].id = i;
 		tps->desc[i].n_voltages = info->table_len;
 		tps->desc[i].volt_table = info->table;
@@ -486,17 +427,6 @@ static int tps6507x_pmic_probe(struct platform_device *pdev)
 		config.init_data = init_data;
 		config.driver_data = tps;
 
-		if (tps6507x_reg_matches) {
-			error = of_property_read_u32(
-				tps6507x_reg_matches[i].of_node,
-					"ti,defdcdc_default", &prop);
-
-			if (!error)
-				tps->info[i]->defdcdc_default = prop;
-
-			config.of_node = tps6507x_reg_matches[i].of_node;
-		}
-
 		rdev = devm_regulator_register(&pdev->dev, &tps->desc[i],
 					       &config);
 		if (IS_ERR(rdev)) {
@@ -505,9 +435,6 @@ static int tps6507x_pmic_probe(struct platform_device *pdev)
 				pdev->name);
 			return PTR_ERR(rdev);
 		}
-
-		/* Save regulator for cleanup */
-		tps->rdev[i] = rdev;
 	}
 
 	tps6507x_dev->pmic = tps;
diff --git a/drivers/regulator/tps65086-regulator.c b/drivers/regulator/tps65086-regulator.c
index 45e96e154690..5a5e9b5bf4be 100644
--- a/drivers/regulator/tps65086-regulator.c
+++ b/drivers/regulator/tps65086-regulator.c
@@ -90,8 +90,8 @@ static const struct regulator_linear_range tps65086_buck345_25mv_ranges[] = {
 static const struct regulator_linear_range tps65086_ldoa1_ranges[] = {
 	REGULATOR_LINEAR_RANGE(1350000, 0x0, 0x0, 0),
 	REGULATOR_LINEAR_RANGE(1500000, 0x1, 0x7, 100000),
-	REGULATOR_LINEAR_RANGE(2300000, 0x8, 0xA, 100000),
-	REGULATOR_LINEAR_RANGE(2700000, 0xB, 0xD, 150000),
+	REGULATOR_LINEAR_RANGE(2300000, 0x8, 0xB, 100000),
+	REGULATOR_LINEAR_RANGE(2850000, 0xC, 0xD, 150000),
 	REGULATOR_LINEAR_RANGE(3300000, 0xE, 0xE, 0),
 };
 
diff --git a/drivers/regulator/tps65132-regulator.c b/drivers/regulator/tps65132-regulator.c
index 73978dd440f7..6e22f5ebba2e 100644
--- a/drivers/regulator/tps65132-regulator.c
+++ b/drivers/regulator/tps65132-regulator.c
@@ -55,10 +55,7 @@ struct tps65132_reg_pdata {
 
 struct tps65132_regulator {
 	struct device *dev;
-	struct regmap *rmap;
-	struct regulator_desc *rdesc[TPS65132_MAX_REGULATORS];
 	struct tps65132_reg_pdata reg_pdata[TPS65132_MAX_REGULATORS];
-	struct regulator_dev *rdev[TPS65132_MAX_REGULATORS];
 };
 
 static int tps65132_regulator_enable(struct regulator_dev *rdev)
@@ -120,7 +117,7 @@ static int tps65132_regulator_is_enabled(struct regulator_dev *rdev)
 	return 1;
 }
 
-static struct regulator_ops tps65132_regulator_ops = {
+static const struct regulator_ops tps65132_regulator_ops = {
 	.enable = tps65132_regulator_enable,
 	.disable = tps65132_regulator_disable,
 	.is_enabled = tps65132_regulator_is_enabled,
@@ -196,7 +193,7 @@ static int tps65132_of_parse_cb(struct device_node *np,
 		.owner = THIS_MODULE,			\
 	}
 
-static struct regulator_desc tps_regs_desc[TPS65132_MAX_REGULATORS] = {
+static const struct regulator_desc tps_regs_desc[TPS65132_MAX_REGULATORS] = {
 	TPS65132_REGULATOR_DESC(VPOS, outp),
 	TPS65132_REGULATOR_DESC(VNEG, outn),
 };
@@ -225,6 +222,8 @@ static int tps65132_probe(struct i2c_client *client,
 {
 	struct device *dev = &client->dev;
 	struct tps65132_regulator *tps;
+	struct regulator_dev *rdev;
+	struct regmap *rmap;
 	struct regulator_config config = { };
 	int id;
 	int ret;
@@ -233,9 +232,9 @@ static int tps65132_probe(struct i2c_client *client,
 	if (!tps)
 		return -ENOMEM;
 
-	tps->rmap = devm_regmap_init_i2c(client, &tps65132_regmap_config);
-	if (IS_ERR(tps->rmap)) {
-		ret = PTR_ERR(tps->rmap);
+	rmap = devm_regmap_init_i2c(client, &tps65132_regmap_config);
+	if (IS_ERR(rmap)) {
+		ret = PTR_ERR(rmap);
 		dev_err(dev, "regmap init failed: %d\n", ret);
 		return ret;
 	}
@@ -244,18 +243,16 @@ static int tps65132_probe(struct i2c_client *client,
 	tps->dev = dev;
 
 	for (id = 0; id < TPS65132_MAX_REGULATORS; ++id) {
-		tps->rdesc[id] = &tps_regs_desc[id];
-
-		config.regmap = tps->rmap;
+		config.regmap = rmap;
 		config.dev = dev;
 		config.driver_data = tps;
 
-		tps->rdev[id] = devm_regulator_register(dev,
-					tps->rdesc[id], &config);
-		if (IS_ERR(tps->rdev[id])) {
-			ret = PTR_ERR(tps->rdev[id]);
+		rdev = devm_regulator_register(dev, &tps_regs_desc[id],
+					       &config);
+		if (IS_ERR(rdev)) {
+			ret = PTR_ERR(rdev);
 			dev_err(dev, "regulator %s register failed: %d\n",
-				tps->rdesc[id]->name, ret);
+				tps_regs_desc[id].name, ret);
 			return ret;
 		}
 	}
diff --git a/drivers/regulator/tps65217-regulator.c b/drivers/regulator/tps65217-regulator.c
index d84fab616abf..67ba78da77ec 100644
--- a/drivers/regulator/tps65217-regulator.c
+++ b/drivers/regulator/tps65217-regulator.c
@@ -58,10 +58,9 @@ static const unsigned int LDO1_VSEL_table[] = {
 
 static const struct regulator_linear_range tps65217_uv1_ranges[] = {
 	REGULATOR_LINEAR_RANGE(900000, 0, 24, 25000),
-	REGULATOR_LINEAR_RANGE(1550000, 25, 30, 50000),
-	REGULATOR_LINEAR_RANGE(1850000, 31, 52, 50000),
+	REGULATOR_LINEAR_RANGE(1550000, 25, 52, 50000),
 	REGULATOR_LINEAR_RANGE(3000000, 53, 55, 100000),
-	REGULATOR_LINEAR_RANGE(3300000, 56, 62, 0),
+	REGULATOR_LINEAR_RANGE(3300000, 56, 63, 0),
 };
 
 static const struct regulator_linear_range tps65217_uv2_ranges[] = {
@@ -150,7 +149,7 @@ static int tps65217_pmic_set_suspend_disable(struct regulator_dev *dev)
 }
 
 /* Operations permitted on DCDCx, LDO2, LDO3 and LDO4 */
-static struct regulator_ops tps65217_pmic_ops = {
+static const struct regulator_ops tps65217_pmic_ops = {
 	.is_enabled		= regulator_is_enabled_regmap,
 	.enable			= tps65217_pmic_enable,
 	.disable		= tps65217_pmic_disable,
@@ -163,7 +162,7 @@ static struct regulator_ops tps65217_pmic_ops = {
 };
 
 /* Operations permitted on LDO1 */
-static struct regulator_ops tps65217_pmic_ldo1_ops = {
+static const struct regulator_ops tps65217_pmic_ldo1_ops = {
 	.is_enabled		= regulator_is_enabled_regmap,
 	.enable			= tps65217_pmic_enable,
 	.disable		= tps65217_pmic_disable,
diff --git a/drivers/regulator/tps65218-regulator.c b/drivers/regulator/tps65218-regulator.c
index 95708d34876b..b72035610013 100644
--- a/drivers/regulator/tps65218-regulator.c
+++ b/drivers/regulator/tps65218-regulator.c
@@ -29,7 +29,8 @@
 #include <linux/mfd/tps65218.h>
 
 #define TPS65218_REGULATOR(_name, _of, _id, _type, _ops, _n, _vr, _vm, _er, \
-			   _em, _cr, _cm, _lr, _nlr, _delay, _fuv, _sr, _sm) \
+			   _em, _cr, _cm, _lr, _nlr, _delay, _fuv, _sr, _sm, \
+			   _ct, _ncl) \
 	{							\
 		.name			= _name,		\
 		.of_match		= _of,			\
@@ -42,6 +43,8 @@
 		.vsel_mask		= _vm,			\
 		.csel_reg		= _cr,			\
 		.csel_mask		= _cm,			\
+		.curr_table		= _ct,			\
+		.n_current_limits	= _ncl,			\
 		.enable_reg		= _er,			\
 		.enable_mask		= _em,			\
 		.volt_table		= NULL,			\
@@ -162,7 +165,7 @@ static int tps65218_pmic_set_suspend_disable(struct regulator_dev *dev)
 }
 
 /* Operations permitted on DCDC1, DCDC2 */
-static struct regulator_ops tps65218_dcdc12_ops = {
+static const struct regulator_ops tps65218_dcdc12_ops = {
 	.is_enabled		= regulator_is_enabled_regmap,
 	.enable			= tps65218_pmic_enable,
 	.disable		= tps65218_pmic_disable,
@@ -176,7 +179,7 @@ static struct regulator_ops tps65218_dcdc12_ops = {
 };
 
 /* Operations permitted on DCDC3, DCDC4 and LDO1 */
-static struct regulator_ops tps65218_ldo1_dcdc34_ops = {
+static const struct regulator_ops tps65218_ldo1_dcdc34_ops = {
 	.is_enabled		= regulator_is_enabled_regmap,
 	.enable			= tps65218_pmic_enable,
 	.disable		= tps65218_pmic_disable,
@@ -188,8 +191,7 @@ static struct regulator_ops tps65218_ldo1_dcdc34_ops = {
 	.set_suspend_disable	= tps65218_pmic_set_suspend_disable,
 };
 
-static const int ls3_currents[] = { 100000, 200000, 500000, 1000000 };
-
+static const unsigned int ls3_currents[] = { 100000, 200000, 500000, 1000000 };
 
 static int tps65218_pmic_set_input_current_lim(struct regulator_dev *dev,
 					       int lim_uA)
@@ -229,33 +231,17 @@ static int tps65218_pmic_set_current_limit(struct regulator_dev *dev,
 				 TPS65218_PROTECT_L1);
 }
 
-static int tps65218_pmic_get_current_limit(struct regulator_dev *dev)
-{
-	int retval;
-	unsigned int index;
-	struct tps65218 *tps = rdev_get_drvdata(dev);
-
-	retval = regmap_read(tps->regmap, dev->desc->csel_reg, &index);
-	if (retval < 0)
-		return retval;
-
-	index = (index & dev->desc->csel_mask) >>
-					 __builtin_ctz(dev->desc->csel_mask);
-
-	return ls3_currents[index];
-}
-
-static struct regulator_ops tps65218_ls23_ops = {
+static const struct regulator_ops tps65218_ls23_ops = {
 	.is_enabled		= regulator_is_enabled_regmap,
 	.enable			= tps65218_pmic_enable,
 	.disable		= tps65218_pmic_disable,
 	.set_input_current_limit = tps65218_pmic_set_input_current_lim,
 	.set_current_limit	= tps65218_pmic_set_current_limit,
-	.get_current_limit	= tps65218_pmic_get_current_limit,
+	.get_current_limit	= regulator_get_current_limit_regmap,
 };
 
 /* Operations permitted on DCDC5, DCDC6 */
-static struct regulator_ops tps65218_dcdc56_pmic_ops = {
+static const struct regulator_ops tps65218_dcdc56_pmic_ops = {
 	.is_enabled		= regulator_is_enabled_regmap,
 	.enable			= tps65218_pmic_enable,
 	.disable		= tps65218_pmic_disable,
@@ -270,53 +256,57 @@ static const struct regulator_desc regulators[] = {
 			   TPS65218_CONTROL_DCDC1_MASK, TPS65218_REG_ENABLE1,
 			   TPS65218_ENABLE1_DC1_EN, 0, 0, dcdc1_dcdc2_ranges,
 			   2, 4000, 0, TPS65218_REG_SEQ3,
-			   TPS65218_SEQ3_DC1_SEQ_MASK),
+			   TPS65218_SEQ3_DC1_SEQ_MASK, NULL, 0),
 	TPS65218_REGULATOR("DCDC2", "regulator-dcdc2", TPS65218_DCDC_2,
 			   REGULATOR_VOLTAGE, tps65218_dcdc12_ops, 64,
 			   TPS65218_REG_CONTROL_DCDC2,
 			   TPS65218_CONTROL_DCDC2_MASK, TPS65218_REG_ENABLE1,
 			   TPS65218_ENABLE1_DC2_EN, 0, 0, dcdc1_dcdc2_ranges,
 			   2, 4000, 0, TPS65218_REG_SEQ3,
-			   TPS65218_SEQ3_DC2_SEQ_MASK),
+			   TPS65218_SEQ3_DC2_SEQ_MASK, NULL, 0),
 	TPS65218_REGULATOR("DCDC3", "regulator-dcdc3", TPS65218_DCDC_3,
 			   REGULATOR_VOLTAGE, tps65218_ldo1_dcdc34_ops, 64,
 			   TPS65218_REG_CONTROL_DCDC3,
 			   TPS65218_CONTROL_DCDC3_MASK, TPS65218_REG_ENABLE1,
 			   TPS65218_ENABLE1_DC3_EN, 0, 0, ldo1_dcdc3_ranges, 2,
-			   0, 0, TPS65218_REG_SEQ4, TPS65218_SEQ4_DC3_SEQ_MASK),
+			   0, 0, TPS65218_REG_SEQ4, TPS65218_SEQ4_DC3_SEQ_MASK,
+			   NULL, 0),
 	TPS65218_REGULATOR("DCDC4", "regulator-dcdc4", TPS65218_DCDC_4,
 			   REGULATOR_VOLTAGE, tps65218_ldo1_dcdc34_ops, 53,
 			   TPS65218_REG_CONTROL_DCDC4,
 			   TPS65218_CONTROL_DCDC4_MASK, TPS65218_REG_ENABLE1,
 			   TPS65218_ENABLE1_DC4_EN, 0, 0, dcdc4_ranges, 2,
-			   0, 0, TPS65218_REG_SEQ4, TPS65218_SEQ4_DC4_SEQ_MASK),
+			   0, 0, TPS65218_REG_SEQ4, TPS65218_SEQ4_DC4_SEQ_MASK,
+			   NULL, 0),
 	TPS65218_REGULATOR("DCDC5", "regulator-dcdc5", TPS65218_DCDC_5,
 			   REGULATOR_VOLTAGE, tps65218_dcdc56_pmic_ops, 1, -1,
 			   -1, TPS65218_REG_ENABLE1, TPS65218_ENABLE1_DC5_EN, 0,
 			   0, NULL, 0, 0, 1000000, TPS65218_REG_SEQ5,
-			   TPS65218_SEQ5_DC5_SEQ_MASK),
+			   TPS65218_SEQ5_DC5_SEQ_MASK, NULL, 0),
 	TPS65218_REGULATOR("DCDC6", "regulator-dcdc6", TPS65218_DCDC_6,
 			   REGULATOR_VOLTAGE, tps65218_dcdc56_pmic_ops, 1, -1,
 			   -1, TPS65218_REG_ENABLE1, TPS65218_ENABLE1_DC6_EN, 0,
 			   0, NULL, 0, 0, 1800000, TPS65218_REG_SEQ5,
-			   TPS65218_SEQ5_DC6_SEQ_MASK),
+			   TPS65218_SEQ5_DC6_SEQ_MASK, NULL, 0),
 	TPS65218_REGULATOR("LDO1", "regulator-ldo1", TPS65218_LDO_1,
 			   REGULATOR_VOLTAGE, tps65218_ldo1_dcdc34_ops, 64,
 			   TPS65218_REG_CONTROL_LDO1,
 			   TPS65218_CONTROL_LDO1_MASK, TPS65218_REG_ENABLE2,
 			   TPS65218_ENABLE2_LDO1_EN, 0, 0, ldo1_dcdc3_ranges,
 			   2, 0, 0, TPS65218_REG_SEQ6,
-			   TPS65218_SEQ6_LDO1_SEQ_MASK),
+			   TPS65218_SEQ6_LDO1_SEQ_MASK, NULL, 0),
 	TPS65218_REGULATOR("LS2", "regulator-ls2", TPS65218_LS_2,
 			   REGULATOR_CURRENT, tps65218_ls23_ops, 0, 0, 0,
 			   TPS65218_REG_ENABLE2, TPS65218_ENABLE2_LS2_EN,
 			   TPS65218_REG_CONFIG2, TPS65218_CONFIG2_LS2ILIM_MASK,
-			   NULL, 0, 0, 0, 0, 0),
+			   NULL, 0, 0, 0, 0, 0, ls3_currents,
+			   ARRAY_SIZE(ls3_currents)),
 	TPS65218_REGULATOR("LS3", "regulator-ls3", TPS65218_LS_3,
 			   REGULATOR_CURRENT, tps65218_ls23_ops, 0, 0, 0,
 			   TPS65218_REG_ENABLE2, TPS65218_ENABLE2_LS3_EN,
 			   TPS65218_REG_CONFIG2, TPS65218_CONFIG2_LS3ILIM_MASK,
-			   NULL, 0, 0, 0, 0, 0),
+			   NULL, 0, 0, 0, 0, 0, ls3_currents,
+			   ARRAY_SIZE(ls3_currents)),
 };
 
 static int tps65218_regulator_probe(struct platform_device *pdev)
diff --git a/drivers/regulator/tps6524x-regulator.c b/drivers/regulator/tps6524x-regulator.c
index 67cac2682f50..740aeccdfb1f 100644
--- a/drivers/regulator/tps6524x-regulator.c
+++ b/drivers/regulator/tps6524x-regulator.c
@@ -137,7 +137,6 @@ struct tps6524x {
 	struct spi_device	*spi;
 	struct mutex		lock;
 	struct regulator_desc	desc[N_REGULATORS];
-	struct regulator_dev	*rdev[N_REGULATORS];
 };
 
 static int __read_reg(struct tps6524x *hw, int reg)
@@ -565,7 +564,7 @@ static int is_supply_enabled(struct regulator_dev *rdev)
 	return read_field(hw, &info->enable);
 }
 
-static struct regulator_ops regulator_ops = {
+static const struct regulator_ops regulator_ops = {
 	.is_enabled		= is_supply_enabled,
 	.enable			= enable_supply,
 	.disable		= disable_supply,
@@ -584,6 +583,7 @@ static int pmic_probe(struct spi_device *spi)
 	const struct supply_info *info = supply_info;
 	struct regulator_init_data *init_data;
 	struct regulator_config config = { };
+	struct regulator_dev *rdev;
 	int i;
 
 	init_data = dev_get_platdata(dev);
@@ -616,10 +616,9 @@ static int pmic_probe(struct spi_device *spi)
 		config.init_data = init_data;
 		config.driver_data = hw;
 
-		hw->rdev[i] = devm_regulator_register(dev, &hw->desc[i],
-						      &config);
-		if (IS_ERR(hw->rdev[i]))
-			return PTR_ERR(hw->rdev[i]);
+		rdev = devm_regulator_register(dev, &hw->desc[i], &config);
+		if (IS_ERR(rdev))
+			return PTR_ERR(rdev);
 	}
 
 	return 0;
diff --git a/drivers/regulator/tps80031-regulator.c b/drivers/regulator/tps80031-regulator.c
index 1001147404c3..85a6a8ca8c1b 100644
--- a/drivers/regulator/tps80031-regulator.c
+++ b/drivers/regulator/tps80031-regulator.c
@@ -1,27 +1,13 @@
-/*
- * tps80031-regulator.c -- TI TPS80031 regulator driver.
- *
- * Regulator driver for TI TPS80031/TPS80032 Fully Integrated Power
- * Management with Power Path and Battery Charger.
- *
- * Copyright (c) 2012, NVIDIA Corporation.
- *
- * Author: Laxman Dewangan <ldewangan@nvidia.com>
- *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of the GNU General Public License as
- * published by the Free Software Foundation version 2.
- *
- * This program is distributed "as is" WITHOUT ANY WARRANTY of any kind,
- * whether express or implied; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
- * General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA
- * 02111-1307, USA
- */
+// SPDX-License-Identifier: GPL-2.0
+//
+// tps80031-regulator.c -- TI TPS80031 regulator driver.
+//
+// Regulator driver for TI TPS80031/TPS80032 Fully Integrated Power
+// Management with Power Path and Battery Charger.
+//
+// Copyright (c) 2012, NVIDIA Corporation.
+//
+// Author: Laxman Dewangan <ldewangan@nvidia.com>
 
 #include <linux/delay.h>
 #include <linux/err.h>
@@ -85,7 +71,6 @@ struct tps80031_regulator_info {
 
 struct tps80031_regulator {
 	struct device			*dev;
-	struct regulator_dev		*rdev;
 	struct tps80031_regulator_info	*rinfo;
 
 	u8				device_flags;
@@ -155,7 +140,7 @@ static int tps80031_reg_disable(struct regulator_dev *rdev)
 }
 
 /* DCDC voltages for the selector of 58 to 63 */
-static int tps80031_dcdc_voltages[4][5] = {
+static const int tps80031_dcdc_voltages[4][5] = {
 	{ 1350, 1500, 1800, 1900, 2100},
 	{ 1350, 1500, 1800, 1900, 2100},
 	{ 2084, 2315, 2778, 2932, 3241},
@@ -378,7 +363,7 @@ static int tps80031_vbus_disable(struct regulator_dev *rdev)
 	return ret;
 }
 
-static struct regulator_ops tps80031_dcdc_ops = {
+static const struct regulator_ops tps80031_dcdc_ops = {
 	.list_voltage		= tps80031_dcdc_list_voltage,
 	.set_voltage_sel	= tps80031_dcdc_set_voltage_sel,
 	.get_voltage_sel	= tps80031_dcdc_get_voltage_sel,
@@ -387,7 +372,7 @@ static struct regulator_ops tps80031_dcdc_ops = {
 	.is_enabled	= tps80031_reg_is_enabled,
 };
 
-static struct regulator_ops tps80031_ldo_ops = {
+static const struct regulator_ops tps80031_ldo_ops = {
 	.list_voltage		= tps80031_ldo_list_voltage,
 	.map_voltage		= tps80031_ldo_map_voltage,
 	.set_voltage_sel	= regulator_set_voltage_sel_regmap,
@@ -397,18 +382,18 @@ static struct regulator_ops tps80031_ldo_ops = {
 	.is_enabled		= tps80031_reg_is_enabled,
 };
 
-static struct regulator_ops tps80031_vbus_sw_ops = {
+static const struct regulator_ops tps80031_vbus_sw_ops = {
 	.list_voltage	= regulator_list_voltage_linear,
 	.enable		= tps80031_vbus_enable,
 	.disable	= tps80031_vbus_disable,
 	.is_enabled	= tps80031_vbus_is_enabled,
 };
 
-static struct regulator_ops tps80031_vbus_hw_ops = {
+static const struct regulator_ops tps80031_vbus_hw_ops = {
 	.list_voltage	= regulator_list_voltage_linear,
 };
 
-static struct regulator_ops tps80031_ext_reg_ops = {
+static const struct regulator_ops tps80031_ext_reg_ops = {
 	.list_voltage	= regulator_list_voltage_linear,
 	.enable		= tps80031_reg_enable,
 	.disable	= tps80031_reg_disable,
@@ -736,7 +721,6 @@ static int tps80031_regulator_probe(struct platform_device *pdev)
 					ri->rinfo->desc.name);
 			return PTR_ERR(rdev);
 		}
-		ri->rdev = rdev;
 	}
 
 	platform_set_drvdata(pdev, pmic);
diff --git a/drivers/regulator/twl-regulator.c b/drivers/regulator/twl-regulator.c
index 402ea43c77d1..cdd81e1985ff 100644
--- a/drivers/regulator/twl-regulator.c
+++ b/drivers/regulator/twl-regulator.c
@@ -392,7 +392,7 @@ static int twl4030ldo_get_voltage_sel(struct regulator_dev *rdev)
 	return vsel;
 }
 
-static struct regulator_ops twl4030ldo_ops = {
+static const struct regulator_ops twl4030ldo_ops = {
 	.list_voltage	= twl4030ldo_list_voltage,
 
 	.set_voltage_sel = twl4030ldo_set_voltage_sel,
@@ -430,14 +430,14 @@ static int twl4030smps_get_voltage(struct regulator_dev *rdev)
 	return vsel * 12500 + 600000;
 }
 
-static struct regulator_ops twl4030smps_ops = {
+static const struct regulator_ops twl4030smps_ops = {
 	.set_voltage	= twl4030smps_set_voltage,
 	.get_voltage	= twl4030smps_get_voltage,
 };
 
 /*----------------------------------------------------------------------*/
 
-static struct regulator_ops twl4030fixed_ops = {
+static const struct regulator_ops twl4030fixed_ops = {
 	.list_voltage	= regulator_list_voltage_linear,
 
 	.enable		= twl4030reg_enable,
diff --git a/drivers/regulator/vctrl-regulator.c b/drivers/regulator/vctrl-regulator.c
index 78de002037c7..259864520a06 100644
--- a/drivers/regulator/vctrl-regulator.c
+++ b/drivers/regulator/vctrl-regulator.c
@@ -334,10 +334,8 @@ static int vctrl_init_vtable(struct platform_device *pdev)
 		ctrl_uV = regulator_list_voltage(ctrl_reg, i);
 
 		if (ctrl_uV < vrange_ctrl->min_uV ||
-		    ctrl_uV > vrange_ctrl->max_uV) {
+		    ctrl_uV > vrange_ctrl->max_uV)
 			rdesc->n_voltages--;
-			continue;
-		}
 	}
 
 	if (rdesc->n_voltages == 0) {
diff --git a/drivers/regulator/vexpress-regulator.c b/drivers/regulator/vexpress-regulator.c
index c810cbbd463f..1235f46e633e 100644
--- a/drivers/regulator/vexpress-regulator.c
+++ b/drivers/regulator/vexpress-regulator.c
@@ -1,15 +1,6 @@
-/*
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- *
- * Copyright (C) 2012 ARM Limited
- */
+// SPDX-License-Identifier: GPL-2.0
+//
+// Copyright (C) 2012 ARM Limited
 
 #define DRVNAME "vexpress-regulator"
 #define pr_fmt(fmt) DRVNAME ": " fmt
@@ -23,17 +14,10 @@
 #include <linux/regulator/of_regulator.h>
 #include <linux/vexpress.h>
 
-struct vexpress_regulator {
-	struct regulator_desc desc;
-	struct regulator_dev *regdev;
-	struct regmap *regmap;
-};
-
 static int vexpress_regulator_get_voltage(struct regulator_dev *regdev)
 {
-	struct vexpress_regulator *reg = rdev_get_drvdata(regdev);
-	u32 uV;
-	int err = regmap_read(reg->regmap, 0, &uV);
+	unsigned int uV;
+	int err = regmap_read(regdev->regmap, 0, &uV);
 
 	return err ? err : uV;
 }
@@ -41,60 +25,58 @@ static int vexpress_regulator_get_voltage(struct regulator_dev *regdev)
 static int vexpress_regulator_set_voltage(struct regulator_dev *regdev,
 		int min_uV, int max_uV, unsigned *selector)
 {
-	struct vexpress_regulator *reg = rdev_get_drvdata(regdev);
-
-	return regmap_write(reg->regmap, 0, min_uV);
+	return regmap_write(regdev->regmap, 0, min_uV);
 }
 
-static struct regulator_ops vexpress_regulator_ops_ro = {
+static const struct regulator_ops vexpress_regulator_ops_ro = {
 	.get_voltage = vexpress_regulator_get_voltage,
 };
 
-static struct regulator_ops vexpress_regulator_ops = {
+static const struct regulator_ops vexpress_regulator_ops = {
 	.get_voltage = vexpress_regulator_get_voltage,
 	.set_voltage = vexpress_regulator_set_voltage,
 };
 
 static int vexpress_regulator_probe(struct platform_device *pdev)
 {
-	struct vexpress_regulator *reg;
+	struct regulator_desc *desc;
 	struct regulator_init_data *init_data;
 	struct regulator_config config = { };
+	struct regulator_dev *rdev;
+	struct regmap *regmap;
 
-	reg = devm_kzalloc(&pdev->dev, sizeof(*reg), GFP_KERNEL);
-	if (!reg)
+	desc = devm_kzalloc(&pdev->dev, sizeof(*desc), GFP_KERNEL);
+	if (!desc)
 		return -ENOMEM;
 
-	reg->regmap = devm_regmap_init_vexpress_config(&pdev->dev);
-	if (IS_ERR(reg->regmap))
-		return PTR_ERR(reg->regmap);
+	regmap = devm_regmap_init_vexpress_config(&pdev->dev);
+	if (IS_ERR(regmap))
+		return PTR_ERR(regmap);
 
-	reg->desc.name = dev_name(&pdev->dev);
-	reg->desc.type = REGULATOR_VOLTAGE;
-	reg->desc.owner = THIS_MODULE;
-	reg->desc.continuous_voltage_range = true;
+	desc->name = dev_name(&pdev->dev);
+	desc->type = REGULATOR_VOLTAGE;
+	desc->owner = THIS_MODULE;
+	desc->continuous_voltage_range = true;
 
 	init_data = of_get_regulator_init_data(&pdev->dev, pdev->dev.of_node,
-					       &reg->desc);
+					       desc);
 	if (!init_data)
 		return -EINVAL;
 
 	init_data->constraints.apply_uV = 0;
 	if (init_data->constraints.min_uV && init_data->constraints.max_uV)
-		reg->desc.ops = &vexpress_regulator_ops;
+		desc->ops = &vexpress_regulator_ops;
 	else
-		reg->desc.ops = &vexpress_regulator_ops_ro;
+		desc->ops = &vexpress_regulator_ops_ro;
 
+	config.regmap = regmap;
 	config.dev = &pdev->dev;
 	config.init_data = init_data;
-	config.driver_data = reg;
 	config.of_node = pdev->dev.of_node;
 
-	reg->regdev = devm_regulator_register(&pdev->dev, &reg->desc, &config);
-	if (IS_ERR(reg->regdev))
-		return PTR_ERR(reg->regdev);
-
-	platform_set_drvdata(pdev, reg);
+	rdev = devm_regulator_register(&pdev->dev, desc, &config);
+	if (IS_ERR(rdev))
+		return PTR_ERR(rdev);
 
 	return 0;
 }
diff --git a/drivers/regulator/wm831x-dcdc.c b/drivers/regulator/wm831x-dcdc.c
index 12b422373580..b422eef97b77 100644
--- a/drivers/regulator/wm831x-dcdc.c
+++ b/drivers/regulator/wm831x-dcdc.c
@@ -1,15 +1,10 @@
-/*
- * wm831x-dcdc.c  --  DC-DC buck convertor driver for the WM831x series
- *
- * Copyright 2009 Wolfson Microelectronics PLC.
- *
- * Author: Mark Brown <broonie@opensource.wolfsonmicro.com>
- *
- *  This program is free software; you can redistribute  it and/or modify it
- *  under  the terms of  the GNU General  Public License as published by the
- *  Free Software Foundation;  either version 2 of the  License, or (at your
- *  option) any later version.
- */
+// SPDX-License-Identifier: GPL-2.0+
+//
+// wm831x-dcdc.c  --  DC-DC buck converter driver for the WM831x series
+//
+// Copyright 2009 Wolfson Microelectronics PLC.
+//
+// Author: Mark Brown <broonie@opensource.wolfsonmicro.com>
 
 #include <linux/module.h>
 #include <linux/moduleparam.h>
@@ -183,9 +178,11 @@ static irqreturn_t wm831x_dcdc_uv_irq(int irq, void *data)
 {
 	struct wm831x_dcdc *dcdc = data;
 
+	regulator_lock(dcdc->regulator);
 	regulator_notifier_call_chain(dcdc->regulator,
 				      REGULATOR_EVENT_UNDER_VOLTAGE,
 				      NULL);
+	regulator_unlock(dcdc->regulator);
 
 	return IRQ_HANDLED;
 }
@@ -194,9 +191,11 @@ static irqreturn_t wm831x_dcdc_oc_irq(int irq, void *data)
 {
 	struct wm831x_dcdc *dcdc = data;
 
+	regulator_lock(dcdc->regulator);
 	regulator_notifier_call_chain(dcdc->regulator,
 				      REGULATOR_EVENT_OVER_CURRENT,
 				      NULL);
+	regulator_unlock(dcdc->regulator);
 
 	return IRQ_HANDLED;
 }
diff --git a/drivers/regulator/wm831x-isink.c b/drivers/regulator/wm831x-isink.c
index 6dd891d7eee3..ff3d2bf50410 100644
--- a/drivers/regulator/wm831x-isink.c
+++ b/drivers/regulator/wm831x-isink.c
@@ -1,15 +1,10 @@
-/*
- * wm831x-isink.c  --  Current sink driver for the WM831x series
- *
- * Copyright 2009 Wolfson Microelectronics PLC.
- *
- * Author: Mark Brown <broonie@opensource.wolfsonmicro.com>
- *
- *  This program is free software; you can redistribute  it and/or modify it
- *  under  the terms of  the GNU General  Public License as published by the
- *  Free Software Foundation;  either version 2 of the  License, or (at your
- *  option) any later version.
- */
+// SPDX-License-Identifier: GPL-2.0+
+//
+// wm831x-isink.c  --  Current sink driver for the WM831x series
+//
+// Copyright 2009 Wolfson Microelectronics PLC.
+//
+// Author: Mark Brown <broonie@opensource.wolfsonmicro.com>
 
 #include <linux/module.h>
 #include <linux/moduleparam.h>
@@ -92,57 +87,23 @@ static int wm831x_isink_is_enabled(struct regulator_dev *rdev)
 		return 0;
 }
 
-static int wm831x_isink_set_current(struct regulator_dev *rdev,
-				    int min_uA, int max_uA)
-{
-	struct wm831x_isink *isink = rdev_get_drvdata(rdev);
-	struct wm831x *wm831x = isink->wm831x;
-	int ret, i;
-
-	for (i = 0; i < ARRAY_SIZE(wm831x_isinkv_values); i++) {
-		int val = wm831x_isinkv_values[i];
-		if (min_uA <= val && val <= max_uA) {
-			ret = wm831x_set_bits(wm831x, isink->reg,
-					      WM831X_CS1_ISEL_MASK, i);
-			return ret;
-		}
-	}
-
-	return -EINVAL;
-}
-
-static int wm831x_isink_get_current(struct regulator_dev *rdev)
-{
-	struct wm831x_isink *isink = rdev_get_drvdata(rdev);
-	struct wm831x *wm831x = isink->wm831x;
-	int ret;
-
-	ret = wm831x_reg_read(wm831x, isink->reg);
-	if (ret < 0)
-		return ret;
-
-	ret &= WM831X_CS1_ISEL_MASK;
-	if (ret > WM831X_ISINK_MAX_ISEL)
-		ret = WM831X_ISINK_MAX_ISEL;
-
-	return wm831x_isinkv_values[ret];
-}
-
 static const struct regulator_ops wm831x_isink_ops = {
 	.is_enabled = wm831x_isink_is_enabled,
 	.enable = wm831x_isink_enable,
 	.disable = wm831x_isink_disable,
-	.set_current_limit = wm831x_isink_set_current,
-	.get_current_limit = wm831x_isink_get_current,
+	.set_current_limit = regulator_set_current_limit_regmap,
+	.get_current_limit = regulator_get_current_limit_regmap,
 };
 
 static irqreturn_t wm831x_isink_irq(int irq, void *data)
 {
 	struct wm831x_isink *isink = data;
 
+	regulator_lock(isink->regulator);
 	regulator_notifier_call_chain(isink->regulator,
 				      REGULATOR_EVENT_OVER_CURRENT,
 				      NULL);
+	regulator_unlock(isink->regulator);
 
 	return IRQ_HANDLED;
 }
@@ -187,10 +148,15 @@ static int wm831x_isink_probe(struct platform_device *pdev)
 	isink->desc.ops = &wm831x_isink_ops;
 	isink->desc.type = REGULATOR_CURRENT;
 	isink->desc.owner = THIS_MODULE;
+	isink->desc.curr_table = wm831x_isinkv_values,
+	isink->desc.n_current_limits = ARRAY_SIZE(wm831x_isinkv_values),
+	isink->desc.csel_reg = isink->reg,
+	isink->desc.csel_mask = WM831X_CS1_ISEL_MASK,
 
 	config.dev = pdev->dev.parent;
 	config.init_data = pdata->isink[id];
 	config.driver_data = isink;
+	config.regmap = wm831x->regmap;
 
 	isink->regulator = devm_regulator_register(&pdev->dev, &isink->desc,
 						   &config);
diff --git a/drivers/regulator/wm831x-ldo.c b/drivers/regulator/wm831x-ldo.c
index e4a6f888484e..56754686c982 100644
--- a/drivers/regulator/wm831x-ldo.c
+++ b/drivers/regulator/wm831x-ldo.c
@@ -1,15 +1,10 @@
-/*
- * wm831x-ldo.c  --  LDO driver for the WM831x series
- *
- * Copyright 2009 Wolfson Microelectronics PLC.
- *
- * Author: Mark Brown <broonie@opensource.wolfsonmicro.com>
- *
- *  This program is free software; you can redistribute  it and/or modify it
- *  under  the terms of  the GNU General  Public License as published by the
- *  Free Software Foundation;  either version 2 of the  License, or (at your
- *  option) any later version.
- */
+// SPDX-License-Identifier: GPL-2.0+
+//
+// wm831x-ldo.c  --  LDO driver for the WM831x series
+//
+// Copyright 2009 Wolfson Microelectronics PLC.
+//
+// Author: Mark Brown <broonie@opensource.wolfsonmicro.com>
 
 #include <linux/module.h>
 #include <linux/moduleparam.h>
@@ -51,9 +46,11 @@ static irqreturn_t wm831x_ldo_uv_irq(int irq, void *data)
 {
 	struct wm831x_ldo *ldo = data;
 
+	regulator_lock(ldo->regulator);
 	regulator_notifier_call_chain(ldo->regulator,
 				      REGULATOR_EVENT_UNDER_VOLTAGE,
 				      NULL);
+	regulator_unlock(ldo->regulator);
 
 	return IRQ_HANDLED;
 }
diff --git a/drivers/regulator/wm8350-regulator.c b/drivers/regulator/wm8350-regulator.c
index a1c7dfee5c37..56d6168a888d 100644
--- a/drivers/regulator/wm8350-regulator.c
+++ b/drivers/regulator/wm8350-regulator.c
@@ -1,16 +1,11 @@
-/*
- * wm8350.c  --  Voltage and current regulation for the Wolfson WM8350 PMIC
- *
- * Copyright 2007, 2008 Wolfson Microelectronics PLC.
- *
- * Author: Liam Girdwood
- *         linux@wolfsonmicro.com
- *
- *  This program is free software; you can redistribute  it and/or modify it
- *  under  the terms of  the GNU General  Public License as published by the
- *  Free Software Foundation;  either version 2 of the  License, or (at your
- *  option) any later version.
- */
+// SPDX-License-Identifier: GPL-2.0+
+//
+// wm8350.c  --  Voltage and current regulation for the Wolfson WM8350 PMIC
+//
+// Copyright 2007, 2008 Wolfson Microelectronics PLC.
+//
+// Author: Liam Girdwood
+//         linux@wolfsonmicro.com
 
 #include <linux/module.h>
 #include <linux/moduleparam.h>
@@ -28,7 +23,7 @@
 #define WM8350_DCDC_MAX_VSEL 0x66
 
 /* Microamps */
-static const int isink_cur[] = {
+static const unsigned int isink_cur[] = {
 	4,
 	5,
 	6,
@@ -95,73 +90,6 @@ static const int isink_cur[] = {
 	223191
 };
 
-static int get_isink_val(int min_uA, int max_uA, u16 *setting)
-{
-	int i;
-
-	for (i = 0; i < ARRAY_SIZE(isink_cur); i++) {
-		if (min_uA <= isink_cur[i] && max_uA >= isink_cur[i]) {
-			*setting = i;
-			return 0;
-		}
-	}
-	return -EINVAL;
-}
-
-static int wm8350_isink_set_current(struct regulator_dev *rdev, int min_uA,
-	int max_uA)
-{
-	struct wm8350 *wm8350 = rdev_get_drvdata(rdev);
-	int isink = rdev_get_id(rdev);
-	u16 val, setting;
-	int ret;
-
-	ret = get_isink_val(min_uA, max_uA, &setting);
-	if (ret != 0)
-		return ret;
-
-	switch (isink) {
-	case WM8350_ISINK_A:
-		val = wm8350_reg_read(wm8350, WM8350_CURRENT_SINK_DRIVER_A) &
-		    ~WM8350_CS1_ISEL_MASK;
-		wm8350_reg_write(wm8350, WM8350_CURRENT_SINK_DRIVER_A,
-				 val | setting);
-		break;
-	case WM8350_ISINK_B:
-		val = wm8350_reg_read(wm8350, WM8350_CURRENT_SINK_DRIVER_B) &
-		    ~WM8350_CS1_ISEL_MASK;
-		wm8350_reg_write(wm8350, WM8350_CURRENT_SINK_DRIVER_B,
-				 val | setting);
-		break;
-	default:
-		return -EINVAL;
-	}
-
-	return 0;
-}
-
-static int wm8350_isink_get_current(struct regulator_dev *rdev)
-{
-	struct wm8350 *wm8350 = rdev_get_drvdata(rdev);
-	int isink = rdev_get_id(rdev);
-	u16 val;
-
-	switch (isink) {
-	case WM8350_ISINK_A:
-		val = wm8350_reg_read(wm8350, WM8350_CURRENT_SINK_DRIVER_A) &
-		    WM8350_CS1_ISEL_MASK;
-		break;
-	case WM8350_ISINK_B:
-		val = wm8350_reg_read(wm8350, WM8350_CURRENT_SINK_DRIVER_B) &
-		    WM8350_CS1_ISEL_MASK;
-		break;
-	default:
-		return 0;
-	}
-
-	return isink_cur[val];
-}
-
 /* turn on ISINK followed by DCDC */
 static int wm8350_isink_enable(struct regulator_dev *rdev)
 {
@@ -982,8 +910,8 @@ static const struct regulator_ops wm8350_ldo_ops = {
 };
 
 static const struct regulator_ops wm8350_isink_ops = {
-	.set_current_limit = wm8350_isink_set_current,
-	.get_current_limit = wm8350_isink_get_current,
+	.set_current_limit = regulator_set_current_limit_regmap,
+	.get_current_limit = regulator_get_current_limit_regmap,
 	.enable = wm8350_isink_enable,
 	.disable = wm8350_isink_disable,
 	.is_enabled = wm8350_isink_is_enabled,
@@ -1138,6 +1066,10 @@ static const struct regulator_desc wm8350_reg[NUM_WM8350_REGULATORS] = {
 		.irq = WM8350_IRQ_CS1,
 		.type = REGULATOR_CURRENT,
 		.owner = THIS_MODULE,
+		.curr_table = isink_cur,
+		.n_current_limits = ARRAY_SIZE(isink_cur),
+		.csel_reg = WM8350_CURRENT_SINK_DRIVER_A,
+		.csel_mask = WM8350_CS1_ISEL_MASK,
 	 },
 	{
 		.name = "ISINKB",
@@ -1146,6 +1078,10 @@ static const struct regulator_desc wm8350_reg[NUM_WM8350_REGULATORS] = {
 		.irq = WM8350_IRQ_CS2,
 		.type = REGULATOR_CURRENT,
 		.owner = THIS_MODULE,
+		.curr_table = isink_cur,
+		.n_current_limits = ARRAY_SIZE(isink_cur),
+		.csel_reg = WM8350_CURRENT_SINK_DRIVER_B,
+		.csel_mask = WM8350_CS2_ISEL_MASK,
 	 },
 };
 
diff --git a/drivers/regulator/wm8400-regulator.c b/drivers/regulator/wm8400-regulator.c
index fb1837657b64..6f331b51e479 100644
--- a/drivers/regulator/wm8400-regulator.c
+++ b/drivers/regulator/wm8400-regulator.c
@@ -1,16 +1,10 @@
-/*
- * Regulator support for WM8400
- *
- * Copyright 2008 Wolfson Microelectronics PLC.
- *
- * Author: Mark Brown <broonie@opensource.wolfsonmicro.com>
- *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of the GNU General Public License as
- * published by the Free Software Foundation; either version 2 of the
- * License, or (at your option) any later version.
- *
- */
+// SPDX-License-Identifier: GPL-2.0+
+//
+// Regulator support for WM8400
+//
+// Copyright 2008 Wolfson Microelectronics PLC.
+//
+// Author: Mark Brown <broonie@opensource.wolfsonmicro.com>
 
 #include <linux/bug.h>
 #include <linux/err.h>
@@ -36,13 +30,12 @@ static const struct regulator_ops wm8400_ldo_ops = {
 
 static unsigned int wm8400_dcdc_get_mode(struct regulator_dev *dev)
 {
-	struct wm8400 *wm8400 = rdev_get_drvdata(dev);
+	struct regmap *rmap = rdev_get_regmap(dev);
 	int offset = (rdev_get_id(dev) - WM8400_DCDC1) * 2;
 	u16 data[2];
 	int ret;
 
-	ret = wm8400_block_read(wm8400, WM8400_DCDC1_CONTROL_1 + offset, 2,
-				data);
+	ret = regmap_bulk_read(rmap, WM8400_DCDC1_CONTROL_1 + offset, data, 2);
 	if (ret != 0)
 		return 0;
 
@@ -63,36 +56,36 @@ static unsigned int wm8400_dcdc_get_mode(struct regulator_dev *dev)
 
 static int wm8400_dcdc_set_mode(struct regulator_dev *dev, unsigned int mode)
 {
-	struct wm8400 *wm8400 = rdev_get_drvdata(dev);
+	struct regmap *rmap = rdev_get_regmap(dev);
 	int offset = (rdev_get_id(dev) - WM8400_DCDC1) * 2;
 	int ret;
 
 	switch (mode) {
 	case REGULATOR_MODE_FAST:
 		/* Datasheet: active with force PWM */
-		ret = wm8400_set_bits(wm8400, WM8400_DCDC1_CONTROL_2 + offset,
+		ret = regmap_update_bits(rmap, WM8400_DCDC1_CONTROL_2 + offset,
 				      WM8400_DC1_FRC_PWM, WM8400_DC1_FRC_PWM);
 		if (ret != 0)
 			return ret;
 
-		return wm8400_set_bits(wm8400, WM8400_DCDC1_CONTROL_1 + offset,
+		return regmap_update_bits(rmap, WM8400_DCDC1_CONTROL_1 + offset,
 				       WM8400_DC1_ACTIVE | WM8400_DC1_SLEEP,
 				       WM8400_DC1_ACTIVE);
 
 	case REGULATOR_MODE_NORMAL:
 		/* Datasheet: active */
-		ret = wm8400_set_bits(wm8400, WM8400_DCDC1_CONTROL_2 + offset,
+		ret = regmap_update_bits(rmap, WM8400_DCDC1_CONTROL_2 + offset,
 				      WM8400_DC1_FRC_PWM, 0);
 		if (ret != 0)
 			return ret;
 
-		return wm8400_set_bits(wm8400, WM8400_DCDC1_CONTROL_1 + offset,
+		return regmap_update_bits(rmap, WM8400_DCDC1_CONTROL_1 + offset,
 				       WM8400_DC1_ACTIVE | WM8400_DC1_SLEEP,
 				       WM8400_DC1_ACTIVE);
 
 	case REGULATOR_MODE_IDLE:
 		/* Datasheet: standby */
-		return wm8400_set_bits(wm8400, WM8400_DCDC1_CONTROL_1 + offset,
+		return regmap_update_bits(rmap, WM8400_DCDC1_CONTROL_1 + offset,
 				       WM8400_DC1_ACTIVE | WM8400_DC1_SLEEP, 0);
 	default:
 		return -EINVAL;
@@ -195,7 +188,7 @@ static struct regulator_desc regulators[] = {
 		.id = WM8400_DCDC2,
 		.ops = &wm8400_dcdc_ops,
 		.enable_reg = WM8400_DCDC2_CONTROL_1,
-		.enable_mask = WM8400_DC1_ENA_MASK,
+		.enable_mask = WM8400_DC2_ENA_MASK,
 		.n_voltages = WM8400_DC2_VSEL_MASK + 1,
 		.vsel_reg = WM8400_DCDC2_CONTROL_1,
 		.vsel_mask = WM8400_DC2_VSEL_MASK,
diff --git a/drivers/regulator/wm8994-regulator.c b/drivers/regulator/wm8994-regulator.c
index 38928cdcb6e6..cadea0344486 100644
--- a/drivers/regulator/wm8994-regulator.c
+++ b/drivers/regulator/wm8994-regulator.c
@@ -1,15 +1,10 @@
-/*
- * wm8994-regulator.c  --  Regulator driver for the WM8994
- *
- * Copyright 2009 Wolfson Microelectronics PLC.
- *
- * Author: Mark Brown <broonie@opensource.wolfsonmicro.com>
- *
- *  This program is free software; you can redistribute  it and/or modify it
- *  under  the terms of  the GNU General  Public License as published by the
- *  Free Software Foundation;  either version 2 of the  License, or (at your
- *  option) any later version.
- */
+// SPDX-License-Identifier: GPL-2.0+
+//
+// wm8994-regulator.c  --  Regulator driver for the WM8994
+//
+// Copyright 2009 Wolfson Microelectronics PLC.
+//
+// Author: Mark Brown <broonie@opensource.wolfsonmicro.com>
 
 #include <linux/module.h>
 #include <linux/moduleparam.h>
diff --git a/drivers/reset/reset-meson-audio-arb.c b/drivers/reset/reset-meson-audio-arb.c
index 91751617b37a..c53a2185a039 100644
--- a/drivers/reset/reset-meson-audio-arb.c
+++ b/drivers/reset/reset-meson-audio-arb.c
@@ -130,6 +130,7 @@ static int meson_audio_arb_probe(struct platform_device *pdev)
 	arb->rstc.nr_resets = ARRAY_SIZE(axg_audio_arb_reset_bits);
 	arb->rstc.ops = &meson_audio_arb_rstc_ops;
 	arb->rstc.of_node = dev->of_node;
+	arb->rstc.owner = THIS_MODULE;
 
 	/*
 	 * Enable general :
diff --git a/drivers/rtc/Kconfig b/drivers/rtc/Kconfig
index a71734c41693..f933c06bff4f 100644
--- a/drivers/rtc/Kconfig
+++ b/drivers/rtc/Kconfig
@@ -667,9 +667,9 @@ config RTC_DRV_S5M
 	  will be called rtc-s5m.
 
 config RTC_DRV_SD3078
-    tristate "ZXW Crystal SD3078"
+    tristate "ZXW Shenzhen whwave SD3078"
     help
-      If you say yes here you get support for the ZXW Crystal
+      If you say yes here you get support for the ZXW Shenzhen whwave
       SD3078 RTC chips.
 
       This driver can also be built as a module. If so, the module
diff --git a/drivers/rtc/rtc-cros-ec.c b/drivers/rtc/rtc-cros-ec.c
index e5444296075e..4d6bf9304ceb 100644
--- a/drivers/rtc/rtc-cros-ec.c
+++ b/drivers/rtc/rtc-cros-ec.c
@@ -298,7 +298,7 @@ static int cros_ec_rtc_suspend(struct device *dev)
 	struct cros_ec_rtc *cros_ec_rtc = dev_get_drvdata(&pdev->dev);
 
 	if (device_may_wakeup(dev))
-		enable_irq_wake(cros_ec_rtc->cros_ec->irq);
+		return enable_irq_wake(cros_ec_rtc->cros_ec->irq);
 
 	return 0;
 }
@@ -309,7 +309,7 @@ static int cros_ec_rtc_resume(struct device *dev)
 	struct cros_ec_rtc *cros_ec_rtc = dev_get_drvdata(&pdev->dev);
 
 	if (device_may_wakeup(dev))
-		disable_irq_wake(cros_ec_rtc->cros_ec->irq);
+		return disable_irq_wake(cros_ec_rtc->cros_ec->irq);
 
 	return 0;
 }
diff --git a/drivers/rtc/rtc-da9063.c b/drivers/rtc/rtc-da9063.c
index b4e054c64bad..69b54e5556c0 100644
--- a/drivers/rtc/rtc-da9063.c
+++ b/drivers/rtc/rtc-da9063.c
@@ -480,6 +480,13 @@ static int da9063_rtc_probe(struct platform_device *pdev)
 	da9063_data_to_tm(data, &rtc->alarm_time, rtc);
 	rtc->rtc_sync = false;
 
+	/*
+	 * TODO: some models have alarms on a minute boundary but still support
+	 * real hardware interrupts. Add this once the core supports it.
+	 */
+	if (config->rtc_data_start != RTC_SEC)
+		rtc->rtc_dev->uie_unsupported = 1;
+
 	irq_alarm = platform_get_irq_byname(pdev, "ALARM");
 	ret = devm_request_threaded_irq(&pdev->dev, irq_alarm, NULL,
 					da9063_alarm_event,
diff --git a/drivers/rtc/rtc-sh.c b/drivers/rtc/rtc-sh.c
index d417b203cbc5..1d3de2a3d1a4 100644
--- a/drivers/rtc/rtc-sh.c
+++ b/drivers/rtc/rtc-sh.c
@@ -374,7 +374,7 @@ static int sh_rtc_set_time(struct device *dev, struct rtc_time *tm)
 static inline int sh_rtc_read_alarm_value(struct sh_rtc *rtc, int reg_off)
 {
 	unsigned int byte;
-	int value = 0xff;	/* return 0xff for ignored values */
+	int value = -1;			/* return -1 for ignored values */
 
 	byte = readb(rtc->regbase + reg_off);
 	if (byte & AR_ENB) {
diff --git a/drivers/s390/block/dasd_eckd.c b/drivers/s390/block/dasd_eckd.c
index 6e294b4d3635..f89f9d02e788 100644
--- a/drivers/s390/block/dasd_eckd.c
+++ b/drivers/s390/block/dasd_eckd.c
@@ -2004,14 +2004,14 @@ static int dasd_eckd_end_analysis(struct dasd_block *block)
 	blk_per_trk = recs_per_track(&private->rdc_data, 0, block->bp_block);
 
 raw:
-	block->blocks = (private->real_cyl *
+	block->blocks = ((unsigned long) private->real_cyl *
 			  private->rdc_data.trk_per_cyl *
 			  blk_per_trk);
 
 	dev_info(&device->cdev->dev,
-		 "DASD with %d KB/block, %d KB total size, %d KB/track, "
+		 "DASD with %u KB/block, %lu KB total size, %u KB/track, "
 		 "%s\n", (block->bp_block >> 10),
-		 ((private->real_cyl *
+		 (((unsigned long) private->real_cyl *
 		   private->rdc_data.trk_per_cyl *
 		   blk_per_trk * (block->bp_block >> 9)) >> 1),
 		 ((blk_per_trk * block->bp_block) >> 10),
diff --git a/drivers/s390/char/con3270.c b/drivers/s390/char/con3270.c
index fd2146bcc0ad..e17364e13d2f 100644
--- a/drivers/s390/char/con3270.c
+++ b/drivers/s390/char/con3270.c
@@ -629,7 +629,7 @@ con3270_init(void)
 		     (void (*)(unsigned long)) con3270_read_tasklet,
 		     (unsigned long) condev->read);
 
-	raw3270_add_view(&condev->view, &con3270_fn, 1);
+	raw3270_add_view(&condev->view, &con3270_fn, 1, RAW3270_VIEW_LOCK_IRQ);
 
 	INIT_LIST_HEAD(&condev->freemem);
 	for (i = 0; i < CON3270_STRING_PAGES; i++) {
diff --git a/drivers/s390/char/fs3270.c b/drivers/s390/char/fs3270.c
index 8f3a2eeb28dc..8b48ba9c598e 100644
--- a/drivers/s390/char/fs3270.c
+++ b/drivers/s390/char/fs3270.c
@@ -463,7 +463,8 @@ fs3270_open(struct inode *inode, struct file *filp)
 
 	init_waitqueue_head(&fp->wait);
 	fp->fs_pid = get_pid(task_pid(current));
-	rc = raw3270_add_view(&fp->view, &fs3270_fn, minor);
+	rc = raw3270_add_view(&fp->view, &fs3270_fn, minor,
+			      RAW3270_VIEW_LOCK_BH);
 	if (rc) {
 		fs3270_free_view(&fp->view);
 		goto out;
diff --git a/drivers/s390/char/raw3270.c b/drivers/s390/char/raw3270.c
index f8cd2935fbfd..63a41b168761 100644
--- a/drivers/s390/char/raw3270.c
+++ b/drivers/s390/char/raw3270.c
@@ -920,7 +920,7 @@ raw3270_deactivate_view(struct raw3270_view *view)
  * Add view to device with minor "minor".
  */
 int
-raw3270_add_view(struct raw3270_view *view, struct raw3270_fn *fn, int minor)
+raw3270_add_view(struct raw3270_view *view, struct raw3270_fn *fn, int minor, int subclass)
 {
 	unsigned long flags;
 	struct raw3270 *rp;
@@ -942,6 +942,7 @@ raw3270_add_view(struct raw3270_view *view, struct raw3270_fn *fn, int minor)
 		view->cols = rp->cols;
 		view->ascebc = rp->ascebc;
 		spin_lock_init(&view->lock);
+		lockdep_set_subclass(&view->lock, subclass);
 		list_add(&view->list, &rp->view_list);
 		rc = 0;
 		spin_unlock_irqrestore(get_ccwdev_lock(rp->cdev), flags);
diff --git a/drivers/s390/char/raw3270.h b/drivers/s390/char/raw3270.h
index 114ca7cbf889..3afaa35f7351 100644
--- a/drivers/s390/char/raw3270.h
+++ b/drivers/s390/char/raw3270.h
@@ -150,6 +150,8 @@ struct raw3270_fn {
 struct raw3270_view {
 	struct list_head list;
 	spinlock_t lock;
+#define RAW3270_VIEW_LOCK_IRQ	0
+#define RAW3270_VIEW_LOCK_BH	1
 	atomic_t ref_count;
 	struct raw3270 *dev;
 	struct raw3270_fn *fn;
@@ -158,7 +160,7 @@ struct raw3270_view {
 	unsigned char *ascebc;		/* ascii -> ebcdic table */
 };
 
-int raw3270_add_view(struct raw3270_view *, struct raw3270_fn *, int);
+int raw3270_add_view(struct raw3270_view *, struct raw3270_fn *, int, int);
 int raw3270_activate_view(struct raw3270_view *);
 void raw3270_del_view(struct raw3270_view *);
 void raw3270_deactivate_view(struct raw3270_view *);
diff --git a/drivers/s390/char/sclp.c b/drivers/s390/char/sclp.c
index e9aa71cdfc44..d2ab3f07c008 100644
--- a/drivers/s390/char/sclp.c
+++ b/drivers/s390/char/sclp.c
@@ -45,8 +45,8 @@ static struct list_head sclp_req_queue;
 /* Data for read and and init requests. */
 static struct sclp_req sclp_read_req;
 static struct sclp_req sclp_init_req;
-static char sclp_read_sccb[PAGE_SIZE] __attribute__((__aligned__(PAGE_SIZE)));
-static char sclp_init_sccb[PAGE_SIZE] __attribute__((__aligned__(PAGE_SIZE)));
+static void *sclp_read_sccb;
+static struct init_sccb *sclp_init_sccb;
 
 /* Suspend request */
 static DECLARE_COMPLETION(sclp_request_queue_flushed);
@@ -753,9 +753,8 @@ EXPORT_SYMBOL(sclp_remove_processed);
 static inline void
 __sclp_make_init_req(sccb_mask_t receive_mask, sccb_mask_t send_mask)
 {
-	struct init_sccb *sccb;
+	struct init_sccb *sccb = sclp_init_sccb;
 
-	sccb = (struct init_sccb *) sclp_init_sccb;
 	clear_page(sccb);
 	memset(&sclp_init_req, 0, sizeof(struct sclp_req));
 	sclp_init_req.command = SCLP_CMDW_WRITE_EVENT_MASK;
@@ -782,7 +781,7 @@ static int
 sclp_init_mask(int calculate)
 {
 	unsigned long flags;
-	struct init_sccb *sccb = (struct init_sccb *) sclp_init_sccb;
+	struct init_sccb *sccb = sclp_init_sccb;
 	sccb_mask_t receive_mask;
 	sccb_mask_t send_mask;
 	int retry;
@@ -1175,6 +1174,9 @@ sclp_init(void)
 	if (sclp_init_state != sclp_init_state_uninitialized)
 		goto fail_unlock;
 	sclp_init_state = sclp_init_state_initializing;
+	sclp_read_sccb = (void *) __get_free_page(GFP_ATOMIC | GFP_DMA);
+	sclp_init_sccb = (void *) __get_free_page(GFP_ATOMIC | GFP_DMA);
+	BUG_ON(!sclp_read_sccb || !sclp_init_sccb);
 	/* Set up variables */
 	INIT_LIST_HEAD(&sclp_req_queue);
 	INIT_LIST_HEAD(&sclp_reg_list);
@@ -1207,6 +1209,8 @@ fail_unregister_reboot_notifier:
 	unregister_reboot_notifier(&sclp_reboot_notifier);
 fail_init_state_uninitialized:
 	sclp_init_state = sclp_init_state_uninitialized;
+	free_page((unsigned long) sclp_read_sccb);
+	free_page((unsigned long) sclp_init_sccb);
 fail_unlock:
 	spin_unlock_irqrestore(&sclp_lock, flags);
 	return rc;
diff --git a/drivers/s390/char/sclp.h b/drivers/s390/char/sclp.h
index 367e9d384d85..196333013e54 100644
--- a/drivers/s390/char/sclp.h
+++ b/drivers/s390/char/sclp.h
@@ -197,7 +197,9 @@ struct read_info_sccb {
 	u32	hmfai;			/* 124-127 */
 	u8	_pad_128[134 - 128];	/* 128-133 */
 	u8	byte_134;			/* 134 */
-	u8	_pad_135[4096 - 135];	/* 135-4095 */
+	u8	cpudirq;		/* 135 */
+	u16	cbl;			/* 136-137 */
+	u8	_pad_138[4096 - 138];	/* 138-4095 */
 } __packed __aligned(PAGE_SIZE);
 
 struct read_storage_sccb {
@@ -319,7 +321,7 @@ extern int sclp_console_drop;
 extern unsigned long sclp_console_full;
 extern bool sclp_mask_compat_mode;
 
-extern char sclp_early_sccb[PAGE_SIZE];
+extern char *sclp_early_sccb;
 
 void sclp_early_wait_irq(void);
 int sclp_early_cmd(sclp_cmdw_t cmd, void *sccb);
@@ -365,14 +367,14 @@ sclp_ascebc(unsigned char ch)
 
 /* translate string from EBCDIC to ASCII */
 static inline void
-sclp_ebcasc_str(unsigned char *str, int nr)
+sclp_ebcasc_str(char *str, int nr)
 {
 	(MACHINE_IS_VM) ? EBCASC(str, nr) : EBCASC_500(str, nr);
 }
 
 /* translate string from ASCII to EBCDIC */
 static inline void
-sclp_ascebc_str(unsigned char *str, int nr)
+sclp_ascebc_str(char *str, int nr)
 {
 	(MACHINE_IS_VM) ? ASCEBC(str, nr) : ASCEBC_500(str, nr);
 }
diff --git a/drivers/s390/char/sclp_early.c b/drivers/s390/char/sclp_early.c
index 8332788681c4..6c90aa725f23 100644
--- a/drivers/s390/char/sclp_early.c
+++ b/drivers/s390/char/sclp_early.c
@@ -40,6 +40,8 @@ static void __init sclp_early_facilities_detect(struct read_info_sccb *sccb)
 	sclp.has_gisaf = !!(sccb->fac118 & 0x08);
 	sclp.has_hvs = !!(sccb->fac119 & 0x80);
 	sclp.has_kss = !!(sccb->fac98 & 0x01);
+	sclp.has_sipl = !!(sccb->cbl & 0x02);
+	sclp.has_sipl_g2 = !!(sccb->cbl & 0x04);
 	if (sccb->fac85 & 0x02)
 		S390_lowcore.machine_flags |= MACHINE_FLAG_ESOP;
 	if (sccb->fac91 & 0x40)
@@ -93,6 +95,7 @@ static void __init sclp_early_facilities_detect(struct read_info_sccb *sccb)
 	sclp.mtid_prev = (sccb->fac42 & 0x80) ? (sccb->fac66 & 31) : 0;
 
 	sclp.hmfai = sccb->hmfai;
+	sclp.has_dirq = !!(sccb->cpudirq & 0x80);
 }
 
 /*
@@ -144,7 +147,7 @@ static void __init sclp_early_console_detect(struct init_sccb *sccb)
 
 void __init sclp_early_detect(void)
 {
-	void *sccb = &sclp_early_sccb;
+	void *sccb = sclp_early_sccb;
 
 	sclp_early_facilities_detect(sccb);
 	sclp_early_init_core_info(sccb);
diff --git a/drivers/s390/char/sclp_early_core.c b/drivers/s390/char/sclp_early_core.c
index 387c114ded3f..7737470f8498 100644
--- a/drivers/s390/char/sclp_early_core.c
+++ b/drivers/s390/char/sclp_early_core.c
@@ -16,7 +16,7 @@
 
 static struct read_info_sccb __bootdata(sclp_info_sccb);
 static int __bootdata(sclp_info_sccb_valid);
-char sclp_early_sccb[PAGE_SIZE] __aligned(PAGE_SIZE) __section(.data);
+char *sclp_early_sccb = (char *) EARLY_SCCB_OFFSET;
 int sclp_init_state __section(.data) = sclp_init_state_uninitialized;
 /*
  * Used to keep track of the size of the event masks. Qemu until version 2.11
@@ -91,8 +91,8 @@ static void sclp_early_print_lm(const char *str, unsigned int len)
 	struct mto *mto;
 	struct go *go;
 
-	sccb = (struct write_sccb *) &sclp_early_sccb;
-	end = (unsigned char *) sccb + sizeof(sclp_early_sccb) - 1;
+	sccb = (struct write_sccb *) sclp_early_sccb;
+	end = (unsigned char *) sccb + EARLY_SCCB_SIZE - 1;
 	memset(sccb, 0, sizeof(*sccb));
 	ptr = (unsigned char *) &sccb->msg.mdb.mto;
 	offset = 0;
@@ -139,9 +139,9 @@ static void sclp_early_print_vt220(const char *str, unsigned int len)
 {
 	struct vt220_sccb *sccb;
 
-	sccb = (struct vt220_sccb *) &sclp_early_sccb;
-	if (sizeof(*sccb) + len >= sizeof(sclp_early_sccb))
-		len = sizeof(sclp_early_sccb) - sizeof(*sccb);
+	sccb = (struct vt220_sccb *) sclp_early_sccb;
+	if (sizeof(*sccb) + len >= EARLY_SCCB_SIZE)
+		len = EARLY_SCCB_SIZE - sizeof(*sccb);
 	memset(sccb, 0, sizeof(*sccb));
 	memcpy(&sccb->msg.data, str, len);
 	sccb->header.length = sizeof(*sccb) + len;
@@ -199,7 +199,7 @@ static int sclp_early_setup(int disable, int *have_linemode, int *have_vt220)
 	BUILD_BUG_ON(sizeof(struct init_sccb) > PAGE_SIZE);
 
 	*have_linemode = *have_vt220 = 0;
-	sccb = (struct init_sccb *) &sclp_early_sccb;
+	sccb = (struct init_sccb *) sclp_early_sccb;
 	receive_mask = disable ? 0 : EVTYP_OPCMD_MASK;
 	send_mask = disable ? 0 : EVTYP_VT220MSG_MASK | EVTYP_MSG_MASK;
 	rc = sclp_early_set_event_mask(sccb, receive_mask, send_mask);
@@ -304,7 +304,7 @@ int __init sclp_early_get_hsa_size(unsigned long *hsa_size)
 void __weak __init add_mem_detect_block(u64 start, u64 end) {}
 int __init sclp_early_read_storage_info(void)
 {
-	struct read_storage_sccb *sccb = (struct read_storage_sccb *)&sclp_early_sccb;
+	struct read_storage_sccb *sccb = (struct read_storage_sccb *)sclp_early_sccb;
 	int rc, id, max_id = 0;
 	unsigned long rn, rzm;
 	sclp_cmdw_t command;
@@ -320,8 +320,8 @@ int __init sclp_early_read_storage_info(void)
 	rzm <<= 20;
 
 	for (id = 0; id <= max_id; id++) {
-		memset(sclp_early_sccb, 0, sizeof(sclp_early_sccb));
-		sccb->header.length = sizeof(sclp_early_sccb);
+		memset(sclp_early_sccb, 0, EARLY_SCCB_SIZE);
+		sccb->header.length = EARLY_SCCB_SIZE;
 		command = SCLP_CMDW_READ_STORAGE_INFO | (id << 8);
 		rc = sclp_early_cmd(command, sccb);
 		if (rc)
diff --git a/drivers/s390/char/sclp_sdias.c b/drivers/s390/char/sclp_sdias.c
index 8e0b69a2f11a..13f97fd73aca 100644
--- a/drivers/s390/char/sclp_sdias.c
+++ b/drivers/s390/char/sclp_sdias.c
@@ -29,7 +29,7 @@ static struct sclp_register sclp_sdias_register = {
 	.send_mask = EVTYP_SDIAS_MASK,
 };
 
-static struct sdias_sccb sccb __attribute__((aligned(4096)));
+static struct sdias_sccb *sclp_sdias_sccb;
 static struct sdias_evbuf sdias_evbuf;
 
 static DECLARE_COMPLETION(evbuf_accepted);
@@ -58,6 +58,7 @@ static void sdias_callback(struct sclp_req *request, void *data)
 
 static int sdias_sclp_send(struct sclp_req *req)
 {
+	struct sdias_sccb *sccb = sclp_sdias_sccb;
 	int retries;
 	int rc;
 
@@ -78,16 +79,16 @@ static int sdias_sclp_send(struct sclp_req *req)
 			continue;
 		}
 		/* if not accepted, retry */
-		if (!(sccb.evbuf.hdr.flags & 0x80)) {
+		if (!(sccb->evbuf.hdr.flags & 0x80)) {
 			TRACE("sclp request failed: flags=%x\n",
-			      sccb.evbuf.hdr.flags);
+			      sccb->evbuf.hdr.flags);
 			continue;
 		}
 		/*
 		 * for the sync interface the response is in the initial sccb
 		 */
 		if (!sclp_sdias_register.receiver_fn) {
-			memcpy(&sdias_evbuf, &sccb.evbuf, sizeof(sdias_evbuf));
+			memcpy(&sdias_evbuf, &sccb->evbuf, sizeof(sdias_evbuf));
 			TRACE("sync request done\n");
 			return 0;
 		}
@@ -104,23 +105,24 @@ static int sdias_sclp_send(struct sclp_req *req)
  */
 int sclp_sdias_blk_count(void)
 {
+	struct sdias_sccb *sccb = sclp_sdias_sccb;
 	struct sclp_req request;
 	int rc;
 
 	mutex_lock(&sdias_mutex);
 
-	memset(&sccb, 0, sizeof(sccb));
+	memset(sccb, 0, sizeof(*sccb));
 	memset(&request, 0, sizeof(request));
 
-	sccb.hdr.length = sizeof(sccb);
-	sccb.evbuf.hdr.length = sizeof(struct sdias_evbuf);
-	sccb.evbuf.hdr.type = EVTYP_SDIAS;
-	sccb.evbuf.event_qual = SDIAS_EQ_SIZE;
-	sccb.evbuf.data_id = SDIAS_DI_FCP_DUMP;
-	sccb.evbuf.event_id = 4712;
-	sccb.evbuf.dbs = 1;
+	sccb->hdr.length = sizeof(*sccb);
+	sccb->evbuf.hdr.length = sizeof(struct sdias_evbuf);
+	sccb->evbuf.hdr.type = EVTYP_SDIAS;
+	sccb->evbuf.event_qual = SDIAS_EQ_SIZE;
+	sccb->evbuf.data_id = SDIAS_DI_FCP_DUMP;
+	sccb->evbuf.event_id = 4712;
+	sccb->evbuf.dbs = 1;
 
-	request.sccb = &sccb;
+	request.sccb = sccb;
 	request.command = SCLP_CMDW_WRITE_EVENT_DATA;
 	request.status = SCLP_REQ_FILLED;
 	request.callback = sdias_callback;
@@ -130,8 +132,8 @@ int sclp_sdias_blk_count(void)
 		pr_err("sclp_send failed for get_nr_blocks\n");
 		goto out;
 	}
-	if (sccb.hdr.response_code != 0x0020) {
-		TRACE("send failed: %x\n", sccb.hdr.response_code);
+	if (sccb->hdr.response_code != 0x0020) {
+		TRACE("send failed: %x\n", sccb->hdr.response_code);
 		rc = -EIO;
 		goto out;
 	}
@@ -163,30 +165,31 @@ out:
  */
 int sclp_sdias_copy(void *dest, int start_blk, int nr_blks)
 {
+	struct sdias_sccb *sccb = sclp_sdias_sccb;
 	struct sclp_req request;
 	int rc;
 
 	mutex_lock(&sdias_mutex);
 
-	memset(&sccb, 0, sizeof(sccb));
+	memset(sccb, 0, sizeof(*sccb));
 	memset(&request, 0, sizeof(request));
 
-	sccb.hdr.length = sizeof(sccb);
-	sccb.evbuf.hdr.length = sizeof(struct sdias_evbuf);
-	sccb.evbuf.hdr.type = EVTYP_SDIAS;
-	sccb.evbuf.hdr.flags = 0;
-	sccb.evbuf.event_qual = SDIAS_EQ_STORE_DATA;
-	sccb.evbuf.data_id = SDIAS_DI_FCP_DUMP;
-	sccb.evbuf.event_id = 4712;
-	sccb.evbuf.asa_size = SDIAS_ASA_SIZE_64;
-	sccb.evbuf.event_status = 0;
-	sccb.evbuf.blk_cnt = nr_blks;
-	sccb.evbuf.asa = (unsigned long)dest;
-	sccb.evbuf.fbn = start_blk;
-	sccb.evbuf.lbn = 0;
-	sccb.evbuf.dbs = 1;
-
-	request.sccb	 = &sccb;
+	sccb->hdr.length = sizeof(*sccb);
+	sccb->evbuf.hdr.length = sizeof(struct sdias_evbuf);
+	sccb->evbuf.hdr.type = EVTYP_SDIAS;
+	sccb->evbuf.hdr.flags = 0;
+	sccb->evbuf.event_qual = SDIAS_EQ_STORE_DATA;
+	sccb->evbuf.data_id = SDIAS_DI_FCP_DUMP;
+	sccb->evbuf.event_id = 4712;
+	sccb->evbuf.asa_size = SDIAS_ASA_SIZE_64;
+	sccb->evbuf.event_status = 0;
+	sccb->evbuf.blk_cnt = nr_blks;
+	sccb->evbuf.asa = (unsigned long)dest;
+	sccb->evbuf.fbn = start_blk;
+	sccb->evbuf.lbn = 0;
+	sccb->evbuf.dbs = 1;
+
+	request.sccb	 = sccb;
 	request.command  = SCLP_CMDW_WRITE_EVENT_DATA;
 	request.status	 = SCLP_REQ_FILLED;
 	request.callback = sdias_callback;
@@ -196,8 +199,8 @@ int sclp_sdias_copy(void *dest, int start_blk, int nr_blks)
 		pr_err("sclp_send failed: %x\n", rc);
 		goto out;
 	}
-	if (sccb.hdr.response_code != 0x0020) {
-		TRACE("copy failed: %x\n", sccb.hdr.response_code);
+	if (sccb->hdr.response_code != 0x0020) {
+		TRACE("copy failed: %x\n", sccb->hdr.response_code);
 		rc = -EIO;
 		goto out;
 	}
@@ -256,6 +259,8 @@ int __init sclp_sdias_init(void)
 {
 	if (ipl_info.type != IPL_TYPE_FCP_DUMP)
 		return 0;
+	sclp_sdias_sccb = (void *) __get_free_page(GFP_KERNEL | GFP_DMA);
+	BUG_ON(!sclp_sdias_sccb);
 	sdias_dbf = debug_register("dump_sdias", 4, 1, 4 * sizeof(long));
 	debug_register_view(sdias_dbf, &debug_sprintf_view);
 	debug_set_level(sdias_dbf, 6);
@@ -264,6 +269,7 @@ int __init sclp_sdias_init(void)
 	if (sclp_sdias_init_async() == 0)
 		goto out;
 	TRACE("init failed\n");
+	free_page((unsigned long) sclp_sdias_sccb);
 	return -ENODEV;
 out:
 	TRACE("init done\n");
diff --git a/drivers/s390/char/tty3270.c b/drivers/s390/char/tty3270.c
index 2b0c36c2c568..98d7fc152e32 100644
--- a/drivers/s390/char/tty3270.c
+++ b/drivers/s390/char/tty3270.c
@@ -980,7 +980,8 @@ static int tty3270_install(struct tty_driver *driver, struct tty_struct *tty)
 		return PTR_ERR(tp);
 
 	rc = raw3270_add_view(&tp->view, &tty3270_fn,
-			      tty->index + RAW3270_FIRSTMINOR);
+			      tty->index + RAW3270_FIRSTMINOR,
+			      RAW3270_VIEW_LOCK_BH);
 	if (rc) {
 		tty3270_free_view(tp);
 		return rc;
diff --git a/drivers/s390/char/zcore.c b/drivers/s390/char/zcore.c
index 76d3c50bf078..f75d3bfb5af3 100644
--- a/drivers/s390/char/zcore.c
+++ b/drivers/s390/char/zcore.c
@@ -51,7 +51,7 @@ static struct dentry *zcore_dir;
 static struct dentry *zcore_memmap_file;
 static struct dentry *zcore_reipl_file;
 static struct dentry *zcore_hsa_file;
-static struct ipl_parameter_block *ipl_block;
+static struct ipl_parameter_block *zcore_ipl_block;
 
 static char hsa_buf[PAGE_SIZE] __aligned(PAGE_SIZE);
 
@@ -182,8 +182,8 @@ static const struct file_operations zcore_memmap_fops = {
 static ssize_t zcore_reipl_write(struct file *filp, const char __user *buf,
 				 size_t count, loff_t *ppos)
 {
-	if (ipl_block) {
-		diag308(DIAG308_SET, ipl_block);
+	if (zcore_ipl_block) {
+		diag308(DIAG308_SET, zcore_ipl_block);
 		diag308(DIAG308_LOAD_CLEAR, NULL);
 	}
 	return count;
@@ -265,18 +265,20 @@ static int __init zcore_reipl_init(void)
 		return rc;
 	if (ipib_info.ipib == 0)
 		return 0;
-	ipl_block = (void *) __get_free_page(GFP_KERNEL);
-	if (!ipl_block)
+	zcore_ipl_block = (void *) __get_free_page(GFP_KERNEL);
+	if (!zcore_ipl_block)
 		return -ENOMEM;
 	if (ipib_info.ipib < sclp.hsa_size)
-		rc = memcpy_hsa_kernel(ipl_block, ipib_info.ipib, PAGE_SIZE);
+		rc = memcpy_hsa_kernel(zcore_ipl_block, ipib_info.ipib,
+				       PAGE_SIZE);
 	else
-		rc = memcpy_real(ipl_block, (void *) ipib_info.ipib, PAGE_SIZE);
-	if (rc || (__force u32)csum_partial(ipl_block, ipl_block->hdr.len, 0) !=
+		rc = memcpy_real(zcore_ipl_block, (void *) ipib_info.ipib,
+				 PAGE_SIZE);
+	if (rc || (__force u32)csum_partial(zcore_ipl_block, zcore_ipl_block->hdr.len, 0) !=
 	    ipib_info.checksum) {
 		TRACE("Checksum does not match\n");
-		free_page((unsigned long) ipl_block);
-		ipl_block = NULL;
+		free_page((unsigned long) zcore_ipl_block);
+		zcore_ipl_block = NULL;
 	}
 	return 0;
 }
diff --git a/drivers/s390/cio/Makefile b/drivers/s390/cio/Makefile
index f230516abb96..f6a8db04177c 100644
--- a/drivers/s390/cio/Makefile
+++ b/drivers/s390/cio/Makefile
@@ -20,5 +20,6 @@ obj-$(CONFIG_CCWGROUP) += ccwgroup.o
 qdio-objs := qdio_main.o qdio_thinint.o qdio_debug.o qdio_setup.o
 obj-$(CONFIG_QDIO) += qdio.o
 
-vfio_ccw-objs += vfio_ccw_drv.o vfio_ccw_cp.o vfio_ccw_ops.o vfio_ccw_fsm.o
+vfio_ccw-objs += vfio_ccw_drv.o vfio_ccw_cp.o vfio_ccw_ops.o vfio_ccw_fsm.o \
+	vfio_ccw_async.o
 obj-$(CONFIG_VFIO_CCW) += vfio_ccw.o
diff --git a/drivers/s390/cio/airq.c b/drivers/s390/cio/airq.c
index a45011e4529e..4534afc63591 100644
--- a/drivers/s390/cio/airq.c
+++ b/drivers/s390/cio/airq.c
@@ -27,6 +27,8 @@
 static DEFINE_SPINLOCK(airq_lists_lock);
 static struct hlist_head airq_lists[MAX_ISC+1];
 
+static struct kmem_cache *airq_iv_cache;
+
 /**
  * register_adapter_interrupt() - register adapter interrupt handler
  * @airq: pointer to adapter interrupt descriptor
@@ -95,7 +97,7 @@ static irqreturn_t do_airq_interrupt(int irq, void *dummy)
 	rcu_read_lock();
 	hlist_for_each_entry_rcu(airq, head, list)
 		if ((*airq->lsi_ptr & airq->lsi_mask) != 0)
-			airq->handler(airq);
+			airq->handler(airq, !tpi_info->directed_irq);
 	rcu_read_unlock();
 
 	return IRQ_HANDLED;
@@ -129,10 +131,21 @@ struct airq_iv *airq_iv_create(unsigned long bits, unsigned long flags)
 	if (!iv)
 		goto out;
 	iv->bits = bits;
+	iv->flags = flags;
 	size = BITS_TO_LONGS(bits) * sizeof(unsigned long);
-	iv->vector = kzalloc(size, GFP_KERNEL);
-	if (!iv->vector)
-		goto out_free;
+
+	if (flags & AIRQ_IV_CACHELINE) {
+		if ((cache_line_size() * BITS_PER_BYTE) < bits)
+			goto out_free;
+
+		iv->vector = kmem_cache_zalloc(airq_iv_cache, GFP_KERNEL);
+		if (!iv->vector)
+			goto out_free;
+	} else {
+		iv->vector = kzalloc(size, GFP_KERNEL);
+		if (!iv->vector)
+			goto out_free;
+	}
 	if (flags & AIRQ_IV_ALLOC) {
 		iv->avail = kmalloc(size, GFP_KERNEL);
 		if (!iv->avail)
@@ -165,7 +178,10 @@ out_free:
 	kfree(iv->ptr);
 	kfree(iv->bitlock);
 	kfree(iv->avail);
-	kfree(iv->vector);
+	if (iv->flags & AIRQ_IV_CACHELINE)
+		kmem_cache_free(airq_iv_cache, iv->vector);
+	else
+		kfree(iv->vector);
 	kfree(iv);
 out:
 	return NULL;
@@ -181,7 +197,10 @@ void airq_iv_release(struct airq_iv *iv)
 	kfree(iv->data);
 	kfree(iv->ptr);
 	kfree(iv->bitlock);
-	kfree(iv->vector);
+	if (iv->flags & AIRQ_IV_CACHELINE)
+		kmem_cache_free(airq_iv_cache, iv->vector);
+	else
+		kfree(iv->vector);
 	kfree(iv->avail);
 	kfree(iv);
 }
@@ -275,3 +294,13 @@ unsigned long airq_iv_scan(struct airq_iv *iv, unsigned long start,
 	return bit;
 }
 EXPORT_SYMBOL(airq_iv_scan);
+
+static int __init airq_init(void)
+{
+	airq_iv_cache = kmem_cache_create("airq_iv_cache", cache_line_size(),
+					  cache_line_size(), 0, NULL);
+	if (!airq_iv_cache)
+		return -ENOMEM;
+	return 0;
+}
+subsys_initcall(airq_init);
diff --git a/drivers/s390/cio/chsc.c b/drivers/s390/cio/chsc.c
index 4159c63a5fd2..a835b31aad99 100644
--- a/drivers/s390/cio/chsc.c
+++ b/drivers/s390/cio/chsc.c
@@ -24,6 +24,7 @@
 #include <asm/crw.h>
 #include <asm/isc.h>
 #include <asm/ebcdic.h>
+#include <asm/ap.h>
 
 #include "css.h"
 #include "cio.h"
@@ -586,6 +587,15 @@ static void chsc_process_sei_scm_avail(struct chsc_sei_nt0_area *sei_area)
 			      " failed (rc=%d).\n", ret);
 }
 
+static void chsc_process_sei_ap_cfg_chg(struct chsc_sei_nt0_area *sei_area)
+{
+	CIO_CRW_EVENT(3, "chsc: ap config changed\n");
+	if (sei_area->rs != 5)
+		return;
+
+	ap_bus_cfg_chg();
+}
+
 static void chsc_process_sei_nt2(struct chsc_sei_nt2_area *sei_area)
 {
 	switch (sei_area->cc) {
@@ -612,6 +622,9 @@ static void chsc_process_sei_nt0(struct chsc_sei_nt0_area *sei_area)
 	case 2: /* i/o resource accessibility */
 		chsc_process_sei_res_acc(sei_area);
 		break;
+	case 3: /* ap config changed */
+		chsc_process_sei_ap_cfg_chg(sei_area);
+		break;
 	case 7: /* channel-path-availability information */
 		chsc_process_sei_chp_avail(sei_area);
 		break;
diff --git a/drivers/s390/cio/cio.c b/drivers/s390/cio/cio.c
index de744ca158fd..18f5458f90e8 100644
--- a/drivers/s390/cio/cio.c
+++ b/drivers/s390/cio/cio.c
@@ -564,7 +564,7 @@ static irqreturn_t do_cio_interrupt(int irq, void *dummy)
 }
 
 static struct irqaction io_interrupt = {
-	.name	 = "IO",
+	.name	 = "I/O",
 	.handler = do_cio_interrupt,
 };
 
diff --git a/drivers/s390/cio/cio.h b/drivers/s390/cio/cio.h
index 9811fd8a0c73..06a91743335a 100644
--- a/drivers/s390/cio/cio.h
+++ b/drivers/s390/cio/cio.h
@@ -51,7 +51,7 @@ struct tpi_info {
 	struct subchannel_id schid;
 	u32 intparm;
 	u32 adapter_IO:1;
-	u32 :1;
+	u32 directed_irq:1;
 	u32 isc:3;
 	u32 :27;
 	u32 type:3;
@@ -115,7 +115,7 @@ struct subchannel {
 	struct schib_config config;
 } __attribute__ ((aligned(8)));
 
-DECLARE_PER_CPU(struct irb, cio_irb);
+DECLARE_PER_CPU_ALIGNED(struct irb, cio_irb);
 
 #define to_subchannel(n) container_of(n, struct subchannel, dev)
 
diff --git a/drivers/s390/cio/ioasm.c b/drivers/s390/cio/ioasm.c
index 14d328338ce2..08eb10283b18 100644
--- a/drivers/s390/cio/ioasm.c
+++ b/drivers/s390/cio/ioasm.c
@@ -233,6 +233,7 @@ int hsch(struct subchannel_id schid)
 
 	return ccode;
 }
+EXPORT_SYMBOL(hsch);
 
 static inline int __xsch(struct subchannel_id schid)
 {
diff --git a/drivers/s390/cio/qdio.h b/drivers/s390/cio/qdio.h
index a6f7c2986b94..a06944399865 100644
--- a/drivers/s390/cio/qdio.h
+++ b/drivers/s390/cio/qdio.h
@@ -228,9 +228,6 @@ struct qdio_q {
 	 */
 	int first_to_check;
 
-	/* first_to_check of the last time */
-	int last_move;
-
 	/* beginning position for calling the program */
 	int first_to_kick;
 
@@ -341,8 +338,7 @@ static inline int multicast_outbound(struct qdio_q *q)
 	       (q->nr == q->irq_ptr->nr_output_qs - 1);
 }
 
-#define pci_out_supported(q) \
-	(q->irq_ptr->qib.ac & QIB_AC_OUTBOUND_PCI_SUPPORTED)
+#define pci_out_supported(irq) ((irq)->qib.ac & QIB_AC_OUTBOUND_PCI_SUPPORTED)
 #define is_qebsm(q)			(q->irq_ptr->sch_token != 0)
 
 #define need_siga_in(q)			(q->irq_ptr->siga_flag.input)
diff --git a/drivers/s390/cio/qdio_debug.c b/drivers/s390/cio/qdio_debug.c
index d2f98e5829d4..35410e6eda2e 100644
--- a/drivers/s390/cio/qdio_debug.c
+++ b/drivers/s390/cio/qdio_debug.c
@@ -121,15 +121,14 @@ static int qstat_show(struct seq_file *m, void *v)
 
 	seq_printf(m, "Timestamp: %Lx  Last AI: %Lx\n",
 		   q->timestamp, last_ai_time);
-	seq_printf(m, "nr_used: %d  ftc: %d  last_move: %d\n",
-		   atomic_read(&q->nr_buf_used),
-		   q->first_to_check, q->last_move);
+	seq_printf(m, "nr_used: %d  ftc: %d\n",
+		   atomic_read(&q->nr_buf_used), q->first_to_check);
 	if (q->is_input_q) {
 		seq_printf(m, "polling: %d  ack start: %d  ack count: %d\n",
 			   q->u.in.polling, q->u.in.ack_start,
 			   q->u.in.ack_count);
-		seq_printf(m, "DSCI: %d   IRQs disabled: %u\n",
-			   *(u32 *)q->irq_ptr->dsci,
+		seq_printf(m, "DSCI: %x   IRQs disabled: %u\n",
+			   *(u8 *)q->irq_ptr->dsci,
 			   test_bit(QDIO_QUEUE_IRQS_DISABLED,
 			   &q->u.in.queue_irq_state));
 	}
diff --git a/drivers/s390/cio/qdio_main.c b/drivers/s390/cio/qdio_main.c
index 9537e656e927..cfce255521ac 100644
--- a/drivers/s390/cio/qdio_main.c
+++ b/drivers/s390/cio/qdio_main.c
@@ -371,7 +371,7 @@ static inline int qdio_siga_input(struct qdio_q *q)
 static inline void qdio_sync_queues(struct qdio_q *q)
 {
 	/* PCI capable outbound queues will also be scanned so sync them too */
-	if (pci_out_supported(q))
+	if (pci_out_supported(q->irq_ptr))
 		qdio_siga_sync_all(q);
 	else
 		qdio_siga_sync_q(q);
@@ -415,7 +415,8 @@ static inline void account_sbals(struct qdio_q *q, unsigned int count)
 	q->q_stats.nr_sbals[pos]++;
 }
 
-static void process_buffer_error(struct qdio_q *q, int count)
+static void process_buffer_error(struct qdio_q *q, unsigned int start,
+				 int count)
 {
 	unsigned char state = (q->is_input_q) ? SLSB_P_INPUT_NOT_INIT :
 					SLSB_P_OUTPUT_NOT_INIT;
@@ -424,29 +425,29 @@ static void process_buffer_error(struct qdio_q *q, int count)
 
 	/* special handling for no target buffer empty */
 	if (queue_type(q) == QDIO_IQDIO_QFMT && !q->is_input_q &&
-	    q->sbal[q->first_to_check]->element[15].sflags == 0x10) {
+	    q->sbal[start]->element[15].sflags == 0x10) {
 		qperf_inc(q, target_full);
-		DBF_DEV_EVENT(DBF_INFO, q->irq_ptr, "OUTFULL FTC:%02x",
-			      q->first_to_check);
+		DBF_DEV_EVENT(DBF_INFO, q->irq_ptr, "OUTFULL FTC:%02x", start);
 		goto set;
 	}
 
 	DBF_ERROR("%4x BUF ERROR", SCH_NO(q));
 	DBF_ERROR((q->is_input_q) ? "IN:%2d" : "OUT:%2d", q->nr);
-	DBF_ERROR("FTC:%3d C:%3d", q->first_to_check, count);
+	DBF_ERROR("FTC:%3d C:%3d", start, count);
 	DBF_ERROR("F14:%2x F15:%2x",
-		  q->sbal[q->first_to_check]->element[14].sflags,
-		  q->sbal[q->first_to_check]->element[15].sflags);
+		  q->sbal[start]->element[14].sflags,
+		  q->sbal[start]->element[15].sflags);
 
 set:
 	/*
 	 * Interrupts may be avoided as long as the error is present
 	 * so change the buffer state immediately to avoid starvation.
 	 */
-	set_buf_states(q, q->first_to_check, state, count);
+	set_buf_states(q, start, state, count);
 }
 
-static inline void inbound_primed(struct qdio_q *q, int count)
+static inline void inbound_primed(struct qdio_q *q, unsigned int start,
+				  int count)
 {
 	int new;
 
@@ -457,7 +458,7 @@ static inline void inbound_primed(struct qdio_q *q, int count)
 		if (!q->u.in.polling) {
 			q->u.in.polling = 1;
 			q->u.in.ack_count = count;
-			q->u.in.ack_start = q->first_to_check;
+			q->u.in.ack_start = start;
 			return;
 		}
 
@@ -465,7 +466,7 @@ static inline void inbound_primed(struct qdio_q *q, int count)
 		set_buf_states(q, q->u.in.ack_start, SLSB_P_INPUT_NOT_INIT,
 			       q->u.in.ack_count);
 		q->u.in.ack_count = count;
-		q->u.in.ack_start = q->first_to_check;
+		q->u.in.ack_start = start;
 		return;
 	}
 
@@ -473,7 +474,7 @@ static inline void inbound_primed(struct qdio_q *q, int count)
 	 * ACK the newest buffer. The ACK will be removed in qdio_stop_polling
 	 * or by the next inbound run.
 	 */
-	new = add_buf(q->first_to_check, count - 1);
+	new = add_buf(start, count - 1);
 	if (q->u.in.polling) {
 		/* reset the previous ACK but first set the new one */
 		set_buf_state(q, new, SLSB_P_INPUT_ACK);
@@ -488,10 +489,10 @@ static inline void inbound_primed(struct qdio_q *q, int count)
 	if (!count)
 		return;
 	/* need to change ALL buffers to get more interrupts */
-	set_buf_states(q, q->first_to_check, SLSB_P_INPUT_NOT_INIT, count);
+	set_buf_states(q, start, SLSB_P_INPUT_NOT_INIT, count);
 }
 
-static int get_inbound_buffer_frontier(struct qdio_q *q)
+static int get_inbound_buffer_frontier(struct qdio_q *q, unsigned int start)
 {
 	unsigned char state = 0;
 	int count;
@@ -504,64 +505,58 @@ static int get_inbound_buffer_frontier(struct qdio_q *q)
 	 */
 	count = min(atomic_read(&q->nr_buf_used), QDIO_MAX_BUFFERS_MASK);
 	if (!count)
-		goto out;
+		return 0;
 
 	/*
 	 * No siga sync here, as a PCI or we after a thin interrupt
 	 * already sync'ed the queues.
 	 */
-	count = get_buf_states(q, q->first_to_check, &state, count, 1, 0);
+	count = get_buf_states(q, start, &state, count, 1, 0);
 	if (!count)
-		goto out;
+		return 0;
 
 	switch (state) {
 	case SLSB_P_INPUT_PRIMED:
-		inbound_primed(q, count);
-		q->first_to_check = add_buf(q->first_to_check, count);
+		inbound_primed(q, start, count);
 		if (atomic_sub_return(count, &q->nr_buf_used) == 0)
 			qperf_inc(q, inbound_queue_full);
 		if (q->irq_ptr->perf_stat_enabled)
 			account_sbals(q, count);
-		break;
+		return count;
 	case SLSB_P_INPUT_ERROR:
-		process_buffer_error(q, count);
-		q->first_to_check = add_buf(q->first_to_check, count);
+		process_buffer_error(q, start, count);
 		if (atomic_sub_return(count, &q->nr_buf_used) == 0)
 			qperf_inc(q, inbound_queue_full);
 		if (q->irq_ptr->perf_stat_enabled)
 			account_sbals_error(q, count);
-		break;
+		return count;
 	case SLSB_CU_INPUT_EMPTY:
 	case SLSB_P_INPUT_NOT_INIT:
 	case SLSB_P_INPUT_ACK:
 		if (q->irq_ptr->perf_stat_enabled)
 			q->q_stats.nr_sbal_nop++;
 		DBF_DEV_EVENT(DBF_INFO, q->irq_ptr, "in nop:%1d %#02x",
-			q->nr, q->first_to_check);
-		break;
+			      q->nr, start);
+		return 0;
 	default:
 		WARN_ON_ONCE(1);
+		return 0;
 	}
-out:
-	return q->first_to_check;
 }
 
-static int qdio_inbound_q_moved(struct qdio_q *q)
+static int qdio_inbound_q_moved(struct qdio_q *q, unsigned int start)
 {
-	int bufnr;
+	int count;
 
-	bufnr = get_inbound_buffer_frontier(q);
+	count = get_inbound_buffer_frontier(q, start);
 
-	if (bufnr != q->last_move) {
-		q->last_move = bufnr;
-		if (!is_thinint_irq(q->irq_ptr) && MACHINE_IS_LPAR)
-			q->u.in.timestamp = get_tod_clock();
-		return 1;
-	} else
-		return 0;
+	if (count && !is_thinint_irq(q->irq_ptr) && MACHINE_IS_LPAR)
+		q->u.in.timestamp = get_tod_clock();
+
+	return count;
 }
 
-static inline int qdio_inbound_q_done(struct qdio_q *q)
+static inline int qdio_inbound_q_done(struct qdio_q *q, unsigned int start)
 {
 	unsigned char state = 0;
 
@@ -570,7 +565,7 @@ static inline int qdio_inbound_q_done(struct qdio_q *q)
 
 	if (need_siga_sync(q))
 		qdio_siga_sync_q(q);
-	get_buf_state(q, q->first_to_check, &state, 0);
+	get_buf_state(q, start, &state, 0);
 
 	if (state == SLSB_P_INPUT_PRIMED || state == SLSB_P_INPUT_ERROR)
 		/* more work coming */
@@ -588,8 +583,7 @@ static inline int qdio_inbound_q_done(struct qdio_q *q)
 	 * has (probably) not moved (see qdio_inbound_processing).
 	 */
 	if (get_tod_clock_fast() > q->u.in.timestamp + QDIO_INPUT_THRESHOLD) {
-		DBF_DEV_EVENT(DBF_INFO, q->irq_ptr, "in done:%02x",
-			      q->first_to_check);
+		DBF_DEV_EVENT(DBF_INFO, q->irq_ptr, "in done:%02x", start);
 		return 1;
 	} else
 		return 0;
@@ -637,17 +631,13 @@ static inline unsigned long qdio_aob_for_buffer(struct qdio_output_q *q,
 	return phys_aob;
 }
 
-static void qdio_kick_handler(struct qdio_q *q)
+static void qdio_kick_handler(struct qdio_q *q, unsigned int count)
 {
 	int start = q->first_to_kick;
-	int end = q->first_to_check;
-	int count;
 
 	if (unlikely(q->irq_ptr->state != QDIO_IRQ_STATE_ACTIVE))
 		return;
 
-	count = sub_buf(end, start);
-
 	if (q->is_input_q) {
 		qperf_inc(q, inbound_handler);
 		DBF_DEV_EVENT(DBF_INFO, q->irq_ptr, "kih s:%02x c:%02x", start, count);
@@ -663,7 +653,7 @@ static void qdio_kick_handler(struct qdio_q *q)
 		   q->irq_ptr->int_parm);
 
 	/* for the next time */
-	q->first_to_kick = end;
+	q->first_to_kick = add_buf(start, count);
 	q->qdio_error = 0;
 }
 
@@ -678,14 +668,20 @@ static inline int qdio_tasklet_schedule(struct qdio_q *q)
 
 static void __qdio_inbound_processing(struct qdio_q *q)
 {
+	unsigned int start = q->first_to_check;
+	int count;
+
 	qperf_inc(q, tasklet_inbound);
 
-	if (!qdio_inbound_q_moved(q))
+	count = qdio_inbound_q_moved(q, start);
+	if (count == 0)
 		return;
 
-	qdio_kick_handler(q);
+	start = add_buf(start, count);
+	q->first_to_check = start;
+	qdio_kick_handler(q, count);
 
-	if (!qdio_inbound_q_done(q)) {
+	if (!qdio_inbound_q_done(q, start)) {
 		/* means poll time is not yet over */
 		qperf_inc(q, tasklet_inbound_resched);
 		if (!qdio_tasklet_schedule(q))
@@ -697,7 +693,7 @@ static void __qdio_inbound_processing(struct qdio_q *q)
 	 * We need to check again to not lose initiative after
 	 * resetting the ACK state.
 	 */
-	if (!qdio_inbound_q_done(q)) {
+	if (!qdio_inbound_q_done(q, start)) {
 		qperf_inc(q, tasklet_inbound_resched2);
 		qdio_tasklet_schedule(q);
 	}
@@ -709,7 +705,7 @@ void qdio_inbound_processing(unsigned long data)
 	__qdio_inbound_processing(q);
 }
 
-static int get_outbound_buffer_frontier(struct qdio_q *q)
+static int get_outbound_buffer_frontier(struct qdio_q *q, unsigned int start)
 {
 	unsigned char state = 0;
 	int count;
@@ -718,7 +714,7 @@ static int get_outbound_buffer_frontier(struct qdio_q *q)
 
 	if (need_siga_sync(q))
 		if (((queue_type(q) != QDIO_IQDIO_QFMT) &&
-		    !pci_out_supported(q)) ||
+		    !pci_out_supported(q->irq_ptr)) ||
 		    (queue_type(q) == QDIO_IQDIO_QFMT &&
 		    multicast_outbound(q)))
 			qdio_siga_sync_q(q);
@@ -729,12 +725,11 @@ static int get_outbound_buffer_frontier(struct qdio_q *q)
 	 */
 	count = min(atomic_read(&q->nr_buf_used), QDIO_MAX_BUFFERS_MASK);
 	if (!count)
-		goto out;
+		return 0;
 
-	count = get_buf_states(q, q->first_to_check, &state, count, 0,
-			       q->u.out.use_cq);
+	count = get_buf_states(q, start, &state, count, 0, q->u.out.use_cq);
 	if (!count)
-		goto out;
+		return 0;
 
 	switch (state) {
 	case SLSB_P_OUTPUT_EMPTY:
@@ -743,34 +738,29 @@ static int get_outbound_buffer_frontier(struct qdio_q *q)
 			"out empty:%1d %02x", q->nr, count);
 
 		atomic_sub(count, &q->nr_buf_used);
-		q->first_to_check = add_buf(q->first_to_check, count);
 		if (q->irq_ptr->perf_stat_enabled)
 			account_sbals(q, count);
-
-		break;
+		return count;
 	case SLSB_P_OUTPUT_ERROR:
-		process_buffer_error(q, count);
-		q->first_to_check = add_buf(q->first_to_check, count);
+		process_buffer_error(q, start, count);
 		atomic_sub(count, &q->nr_buf_used);
 		if (q->irq_ptr->perf_stat_enabled)
 			account_sbals_error(q, count);
-		break;
+		return count;
 	case SLSB_CU_OUTPUT_PRIMED:
 		/* the adapter has not fetched the output yet */
 		if (q->irq_ptr->perf_stat_enabled)
 			q->q_stats.nr_sbal_nop++;
 		DBF_DEV_EVENT(DBF_INFO, q->irq_ptr, "out primed:%1d",
 			      q->nr);
-		break;
+		return 0;
 	case SLSB_P_OUTPUT_NOT_INIT:
 	case SLSB_P_OUTPUT_HALTED:
-		break;
+		return 0;
 	default:
 		WARN_ON_ONCE(1);
+		return 0;
 	}
-
-out:
-	return q->first_to_check;
 }
 
 /* all buffers processed? */
@@ -779,18 +769,16 @@ static inline int qdio_outbound_q_done(struct qdio_q *q)
 	return atomic_read(&q->nr_buf_used) == 0;
 }
 
-static inline int qdio_outbound_q_moved(struct qdio_q *q)
+static inline int qdio_outbound_q_moved(struct qdio_q *q, unsigned int start)
 {
-	int bufnr;
+	int count;
 
-	bufnr = get_outbound_buffer_frontier(q);
+	count = get_outbound_buffer_frontier(q, start);
 
-	if (bufnr != q->last_move) {
-		q->last_move = bufnr;
+	if (count)
 		DBF_DEV_EVENT(DBF_INFO, q->irq_ptr, "out moved:%1d", q->nr);
-		return 1;
-	} else
-		return 0;
+
+	return count;
 }
 
 static int qdio_kick_outbound_q(struct qdio_q *q, unsigned long aob)
@@ -837,15 +825,21 @@ retry:
 
 static void __qdio_outbound_processing(struct qdio_q *q)
 {
+	unsigned int start = q->first_to_check;
+	int count;
+
 	qperf_inc(q, tasklet_outbound);
 	WARN_ON_ONCE(atomic_read(&q->nr_buf_used) < 0);
 
-	if (qdio_outbound_q_moved(q))
-		qdio_kick_handler(q);
+	count = qdio_outbound_q_moved(q, start);
+	if (count) {
+		q->first_to_check = add_buf(start, count);
+		qdio_kick_handler(q, count);
+	}
 
-	if (queue_type(q) == QDIO_ZFCP_QFMT)
-		if (!pci_out_supported(q) && !qdio_outbound_q_done(q))
-			goto sched;
+	if (queue_type(q) == QDIO_ZFCP_QFMT && !pci_out_supported(q->irq_ptr) &&
+	    !qdio_outbound_q_done(q))
+		goto sched;
 
 	if (q->u.out.pci_out_enabled)
 		return;
@@ -881,37 +875,40 @@ void qdio_outbound_timer(struct timer_list *t)
 	qdio_tasklet_schedule(q);
 }
 
-static inline void qdio_check_outbound_after_thinint(struct qdio_q *q)
+static inline void qdio_check_outbound_pci_queues(struct qdio_irq *irq)
 {
 	struct qdio_q *out;
 	int i;
 
-	if (!pci_out_supported(q))
+	if (!pci_out_supported(irq))
 		return;
 
-	for_each_output_queue(q->irq_ptr, out, i)
+	for_each_output_queue(irq, out, i)
 		if (!qdio_outbound_q_done(out))
 			qdio_tasklet_schedule(out);
 }
 
 static void __tiqdio_inbound_processing(struct qdio_q *q)
 {
+	unsigned int start = q->first_to_check;
+	int count;
+
 	qperf_inc(q, tasklet_inbound);
 	if (need_siga_sync(q) && need_siga_sync_after_ai(q))
 		qdio_sync_queues(q);
 
-	/*
-	 * The interrupt could be caused by a PCI request. Check the
-	 * PCI capable outbound queues.
-	 */
-	qdio_check_outbound_after_thinint(q);
+	/* The interrupt could be caused by a PCI request: */
+	qdio_check_outbound_pci_queues(q->irq_ptr);
 
-	if (!qdio_inbound_q_moved(q))
+	count = qdio_inbound_q_moved(q, start);
+	if (count == 0)
 		return;
 
-	qdio_kick_handler(q);
+	start = add_buf(start, count);
+	q->first_to_check = start;
+	qdio_kick_handler(q, count);
 
-	if (!qdio_inbound_q_done(q)) {
+	if (!qdio_inbound_q_done(q, start)) {
 		qperf_inc(q, tasklet_inbound_resched);
 		if (!qdio_tasklet_schedule(q))
 			return;
@@ -922,7 +919,7 @@ static void __tiqdio_inbound_processing(struct qdio_q *q)
 	 * We need to check again to not lose initiative after
 	 * resetting the ACK state.
 	 */
-	if (!qdio_inbound_q_done(q)) {
+	if (!qdio_inbound_q_done(q, start)) {
 		qperf_inc(q, tasklet_inbound_resched2);
 		qdio_tasklet_schedule(q);
 	}
@@ -976,7 +973,7 @@ static void qdio_int_handler_pci(struct qdio_irq *irq_ptr)
 		}
 	}
 
-	if (!(irq_ptr->qib.ac & QIB_AC_OUTBOUND_PCI_SUPPORTED))
+	if (!pci_out_supported(irq_ptr))
 		return;
 
 	for_each_output_queue(irq_ptr, q, i) {
@@ -1642,7 +1639,7 @@ int qdio_start_irq(struct ccw_device *cdev, int nr)
 	 */
 	if (test_nonshared_ind(irq_ptr))
 		goto rescan;
-	if (!qdio_inbound_q_done(q))
+	if (!qdio_inbound_q_done(q, q->first_to_check))
 		goto rescan;
 	return 0;
 
@@ -1672,12 +1669,14 @@ int qdio_get_next_buffers(struct ccw_device *cdev, int nr, int *bufnr,
 			  int *error)
 {
 	struct qdio_q *q;
-	int start, end;
 	struct qdio_irq *irq_ptr = cdev->private->qdio_data;
+	unsigned int start;
+	int count;
 
 	if (!irq_ptr)
 		return -ENODEV;
 	q = irq_ptr->input_qs[nr];
+	start = q->first_to_check;
 
 	/*
 	 * Cannot rely on automatic sync after interrupt since queues may
@@ -1686,25 +1685,27 @@ int qdio_get_next_buffers(struct ccw_device *cdev, int nr, int *bufnr,
 	if (need_siga_sync(q))
 		qdio_sync_queues(q);
 
-	/* check the PCI capable outbound queues. */
-	qdio_check_outbound_after_thinint(q);
+	qdio_check_outbound_pci_queues(irq_ptr);
 
-	if (!qdio_inbound_q_moved(q))
+	count = qdio_inbound_q_moved(q, start);
+	if (count == 0)
 		return 0;
 
+	start = add_buf(start, count);
+	q->first_to_check = start;
+
 	/* Note: upper-layer MUST stop processing immediately here ... */
 	if (unlikely(q->irq_ptr->state != QDIO_IRQ_STATE_ACTIVE))
 		return -EIO;
 
-	start = q->first_to_kick;
-	end = q->first_to_check;
-	*bufnr = start;
+	*bufnr = q->first_to_kick;
 	*error = q->qdio_error;
 
 	/* for the next time */
-	q->first_to_kick = end;
+	q->first_to_kick = add_buf(q->first_to_kick, count);
 	q->qdio_error = 0;
-	return sub_buf(end, start);
+
+	return count;
 }
 EXPORT_SYMBOL(qdio_get_next_buffers);
 
diff --git a/drivers/s390/cio/qdio_setup.c b/drivers/s390/cio/qdio_setup.c
index a59887fad13e..99d7d2566a3a 100644
--- a/drivers/s390/cio/qdio_setup.c
+++ b/drivers/s390/cio/qdio_setup.c
@@ -523,7 +523,7 @@ void qdio_print_subchannel_info(struct qdio_irq *irq_ptr,
 		 irq_ptr->schid.sch_no,
 		 is_thinint_irq(irq_ptr),
 		 (irq_ptr->sch_token) ? 1 : 0,
-		 (irq_ptr->qib.ac & QIB_AC_OUTBOUND_PCI_SUPPORTED) ? 1 : 0,
+		 pci_out_supported(irq_ptr) ? 1 : 0,
 		 css_general_characteristics.aif_tdd,
 		 (irq_ptr->siga_flag.input) ? "R" : " ",
 		 (irq_ptr->siga_flag.output) ? "W" : " ",
diff --git a/drivers/s390/cio/qdio_thinint.c b/drivers/s390/cio/qdio_thinint.c
index 07dea602205b..28d59ac2204c 100644
--- a/drivers/s390/cio/qdio_thinint.c
+++ b/drivers/s390/cio/qdio_thinint.c
@@ -40,7 +40,7 @@ static LIST_HEAD(tiq_list);
 static DEFINE_MUTEX(tiq_list_lock);
 
 /* Adapter interrupt definitions */
-static void tiqdio_thinint_handler(struct airq_struct *airq);
+static void tiqdio_thinint_handler(struct airq_struct *airq, bool floating);
 
 static struct airq_struct tiqdio_airq = {
 	.handler = tiqdio_thinint_handler,
@@ -179,7 +179,7 @@ static inline void tiqdio_call_inq_handlers(struct qdio_irq *irq)
  * tiqdio_thinint_handler - thin interrupt handler for qdio
  * @airq: pointer to adapter interrupt descriptor
  */
-static void tiqdio_thinint_handler(struct airq_struct *airq)
+static void tiqdio_thinint_handler(struct airq_struct *airq, bool floating)
 {
 	u32 si_used = clear_shared_ind();
 	struct qdio_q *q;
diff --git a/drivers/s390/cio/vfio_ccw_async.c b/drivers/s390/cio/vfio_ccw_async.c
new file mode 100644
index 000000000000..8c1d2357ef5b
--- /dev/null
+++ b/drivers/s390/cio/vfio_ccw_async.c
@@ -0,0 +1,88 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Async I/O region for vfio_ccw
+ *
+ * Copyright Red Hat, Inc. 2019
+ *
+ * Author(s): Cornelia Huck <cohuck@redhat.com>
+ */
+
+#include <linux/vfio.h>
+#include <linux/mdev.h>
+
+#include "vfio_ccw_private.h"
+
+static ssize_t vfio_ccw_async_region_read(struct vfio_ccw_private *private,
+					  char __user *buf, size_t count,
+					  loff_t *ppos)
+{
+	unsigned int i = VFIO_CCW_OFFSET_TO_INDEX(*ppos) - VFIO_CCW_NUM_REGIONS;
+	loff_t pos = *ppos & VFIO_CCW_OFFSET_MASK;
+	struct ccw_cmd_region *region;
+	int ret;
+
+	if (pos + count > sizeof(*region))
+		return -EINVAL;
+
+	mutex_lock(&private->io_mutex);
+	region = private->region[i].data;
+	if (copy_to_user(buf, (void *)region + pos, count))
+		ret = -EFAULT;
+	else
+		ret = count;
+	mutex_unlock(&private->io_mutex);
+	return ret;
+}
+
+static ssize_t vfio_ccw_async_region_write(struct vfio_ccw_private *private,
+					   const char __user *buf, size_t count,
+					   loff_t *ppos)
+{
+	unsigned int i = VFIO_CCW_OFFSET_TO_INDEX(*ppos) - VFIO_CCW_NUM_REGIONS;
+	loff_t pos = *ppos & VFIO_CCW_OFFSET_MASK;
+	struct ccw_cmd_region *region;
+	int ret;
+
+	if (pos + count > sizeof(*region))
+		return -EINVAL;
+
+	if (!mutex_trylock(&private->io_mutex))
+		return -EAGAIN;
+
+	region = private->region[i].data;
+	if (copy_from_user((void *)region + pos, buf, count)) {
+		ret = -EFAULT;
+		goto out_unlock;
+	}
+
+	vfio_ccw_fsm_event(private, VFIO_CCW_EVENT_ASYNC_REQ);
+
+	ret = region->ret_code ? region->ret_code : count;
+
+out_unlock:
+	mutex_unlock(&private->io_mutex);
+	return ret;
+}
+
+static void vfio_ccw_async_region_release(struct vfio_ccw_private *private,
+					  struct vfio_ccw_region *region)
+{
+
+}
+
+const struct vfio_ccw_regops vfio_ccw_async_region_ops = {
+	.read = vfio_ccw_async_region_read,
+	.write = vfio_ccw_async_region_write,
+	.release = vfio_ccw_async_region_release,
+};
+
+int vfio_ccw_register_async_dev_regions(struct vfio_ccw_private *private)
+{
+	return vfio_ccw_register_dev_region(private,
+					    VFIO_REGION_SUBTYPE_CCW_ASYNC_CMD,
+					    &vfio_ccw_async_region_ops,
+					    sizeof(struct ccw_cmd_region),
+					    VFIO_REGION_INFO_FLAG_READ |
+					    VFIO_REGION_INFO_FLAG_WRITE,
+					    private->cmd_region);
+}
diff --git a/drivers/s390/cio/vfio_ccw_cp.c b/drivers/s390/cio/vfio_ccw_cp.c
index 384b3987eeb4..0e79799e9a71 100644
--- a/drivers/s390/cio/vfio_ccw_cp.c
+++ b/drivers/s390/cio/vfio_ccw_cp.c
@@ -362,6 +362,7 @@ static void cp_unpin_free(struct channel_program *cp)
 	struct ccwchain *chain, *temp;
 	int i;
 
+	cp->initialized = false;
 	list_for_each_entry_safe(chain, temp, &cp->ccwchain_list, next) {
 		for (i = 0; i < chain->ch_len; i++) {
 			pfn_array_table_unpin_free(chain->ch_pat + i,
@@ -732,6 +733,9 @@ int cp_init(struct channel_program *cp, struct device *mdev, union orb *orb)
 	 */
 	cp->orb.cmd.c64 = 1;
 
+	if (!ret)
+		cp->initialized = true;
+
 	return ret;
 }
 
@@ -746,7 +750,8 @@ int cp_init(struct channel_program *cp, struct device *mdev, union orb *orb)
  */
 void cp_free(struct channel_program *cp)
 {
-	cp_unpin_free(cp);
+	if (cp->initialized)
+		cp_unpin_free(cp);
 }
 
 /**
@@ -791,6 +796,10 @@ int cp_prefetch(struct channel_program *cp)
 	struct ccwchain *chain;
 	int len, idx, ret;
 
+	/* this is an error in the caller */
+	if (!cp->initialized)
+		return -EINVAL;
+
 	list_for_each_entry(chain, &cp->ccwchain_list, next) {
 		len = chain->ch_len;
 		for (idx = 0; idx < len; idx++) {
@@ -826,6 +835,10 @@ union orb *cp_get_orb(struct channel_program *cp, u32 intparm, u8 lpm)
 	struct ccwchain *chain;
 	struct ccw1 *cpa;
 
+	/* this is an error in the caller */
+	if (!cp->initialized)
+		return NULL;
+
 	orb = &cp->orb;
 
 	orb->cmd.intparm = intparm;
@@ -862,6 +875,9 @@ void cp_update_scsw(struct channel_program *cp, union scsw *scsw)
 	u32 cpa = scsw->cmd.cpa;
 	u32 ccw_head;
 
+	if (!cp->initialized)
+		return;
+
 	/*
 	 * LATER:
 	 * For now, only update the cmd.cpa part. We may need to deal with
@@ -898,6 +914,9 @@ bool cp_iova_pinned(struct channel_program *cp, u64 iova)
 	struct ccwchain *chain;
 	int i;
 
+	if (!cp->initialized)
+		return false;
+
 	list_for_each_entry(chain, &cp->ccwchain_list, next) {
 		for (i = 0; i < chain->ch_len; i++)
 			if (pfn_array_table_iova_pinned(chain->ch_pat + i,
diff --git a/drivers/s390/cio/vfio_ccw_cp.h b/drivers/s390/cio/vfio_ccw_cp.h
index a4b74fb1aa57..3c20cd208da5 100644
--- a/drivers/s390/cio/vfio_ccw_cp.h
+++ b/drivers/s390/cio/vfio_ccw_cp.h
@@ -21,6 +21,7 @@
  * @ccwchain_list: list head of ccwchains
  * @orb: orb for the currently processed ssch request
  * @mdev: the mediated device to perform page pinning/unpinning
+ * @initialized: whether this instance is actually initialized
  *
  * @ccwchain_list is the head of a ccwchain list, that contents the
  * translated result of the guest channel program that pointed out by
@@ -30,6 +31,7 @@ struct channel_program {
 	struct list_head ccwchain_list;
 	union orb orb;
 	struct device *mdev;
+	bool initialized;
 };
 
 extern int cp_init(struct channel_program *cp, struct device *mdev,
diff --git a/drivers/s390/cio/vfio_ccw_drv.c b/drivers/s390/cio/vfio_ccw_drv.c
index a10cec0e86eb..ee8767f5845a 100644
--- a/drivers/s390/cio/vfio_ccw_drv.c
+++ b/drivers/s390/cio/vfio_ccw_drv.c
@@ -3,9 +3,11 @@
  * VFIO based Physical Subchannel device driver
  *
  * Copyright IBM Corp. 2017
+ * Copyright Red Hat, Inc. 2019
  *
  * Author(s): Dong Jia Shi <bjsdjshi@linux.vnet.ibm.com>
  *            Xiao Feng Ren <renxiaof@linux.vnet.ibm.com>
+ *            Cornelia Huck <cohuck@redhat.com>
  */
 
 #include <linux/module.h>
@@ -23,6 +25,7 @@
 
 struct workqueue_struct *vfio_ccw_work_q;
 static struct kmem_cache *vfio_ccw_io_region;
+static struct kmem_cache *vfio_ccw_cmd_region;
 
 /*
  * Helpers
@@ -40,26 +43,30 @@ int vfio_ccw_sch_quiesce(struct subchannel *sch)
 	if (ret != -EBUSY)
 		goto out_unlock;
 
+	iretry = 255;
 	do {
-		iretry = 255;
 
 		ret = cio_cancel_halt_clear(sch, &iretry);
-		while (ret == -EBUSY) {
-			/*
-			 * Flush all I/O and wait for
-			 * cancel/halt/clear completion.
-			 */
-			private->completion = &completion;
-			spin_unlock_irq(sch->lock);
 
-			wait_for_completion_timeout(&completion, 3*HZ);
+		if (ret == -EIO) {
+			pr_err("vfio_ccw: could not quiesce subchannel 0.%x.%04x!\n",
+			       sch->schid.ssid, sch->schid.sch_no);
+			break;
+		}
+
+		/*
+		 * Flush all I/O and wait for
+		 * cancel/halt/clear completion.
+		 */
+		private->completion = &completion;
+		spin_unlock_irq(sch->lock);
 
-			spin_lock_irq(sch->lock);
-			private->completion = NULL;
-			flush_workqueue(vfio_ccw_work_q);
-			ret = cio_cancel_halt_clear(sch, &iretry);
-		};
+		if (ret == -EBUSY)
+			wait_for_completion_timeout(&completion, 3*HZ);
 
+		private->completion = NULL;
+		flush_workqueue(vfio_ccw_work_q);
+		spin_lock_irq(sch->lock);
 		ret = cio_disable_subchannel(sch);
 	} while (ret == -EBUSY);
 out_unlock:
@@ -72,20 +79,26 @@ static void vfio_ccw_sch_io_todo(struct work_struct *work)
 {
 	struct vfio_ccw_private *private;
 	struct irb *irb;
+	bool is_final;
 
 	private = container_of(work, struct vfio_ccw_private, io_work);
 	irb = &private->irb;
 
+	is_final = !(scsw_actl(&irb->scsw) &
+		     (SCSW_ACTL_DEVACT | SCSW_ACTL_SCHACT));
 	if (scsw_is_solicited(&irb->scsw)) {
 		cp_update_scsw(&private->cp, &irb->scsw);
-		cp_free(&private->cp);
+		if (is_final)
+			cp_free(&private->cp);
 	}
+	mutex_lock(&private->io_mutex);
 	memcpy(private->io_region->irb_area, irb, sizeof(*irb));
+	mutex_unlock(&private->io_mutex);
 
 	if (private->io_trigger)
 		eventfd_signal(private->io_trigger, 1);
 
-	if (private->mdev)
+	if (private->mdev && is_final)
 		private->state = VFIO_CCW_STATE_IDLE;
 }
 
@@ -104,7 +117,7 @@ static int vfio_ccw_sch_probe(struct subchannel *sch)
 {
 	struct pmcw *pmcw = &sch->schib.pmcw;
 	struct vfio_ccw_private *private;
-	int ret;
+	int ret = -ENOMEM;
 
 	if (pmcw->qf) {
 		dev_warn(&sch->dev, "vfio: ccw: does not support QDIO: %s\n",
@@ -118,13 +131,17 @@ static int vfio_ccw_sch_probe(struct subchannel *sch)
 
 	private->io_region = kmem_cache_zalloc(vfio_ccw_io_region,
 					       GFP_KERNEL | GFP_DMA);
-	if (!private->io_region) {
-		kfree(private);
-		return -ENOMEM;
-	}
+	if (!private->io_region)
+		goto out_free;
+
+	private->cmd_region = kmem_cache_zalloc(vfio_ccw_cmd_region,
+						GFP_KERNEL | GFP_DMA);
+	if (!private->cmd_region)
+		goto out_free;
 
 	private->sch = sch;
 	dev_set_drvdata(&sch->dev, private);
+	mutex_init(&private->io_mutex);
 
 	spin_lock_irq(sch->lock);
 	private->state = VFIO_CCW_STATE_NOT_OPER;
@@ -148,7 +165,10 @@ out_disable:
 	cio_disable_subchannel(sch);
 out_free:
 	dev_set_drvdata(&sch->dev, NULL);
-	kmem_cache_free(vfio_ccw_io_region, private->io_region);
+	if (private->cmd_region)
+		kmem_cache_free(vfio_ccw_cmd_region, private->cmd_region);
+	if (private->io_region)
+		kmem_cache_free(vfio_ccw_io_region, private->io_region);
 	kfree(private);
 	return ret;
 }
@@ -163,6 +183,7 @@ static int vfio_ccw_sch_remove(struct subchannel *sch)
 
 	dev_set_drvdata(&sch->dev, NULL);
 
+	kmem_cache_free(vfio_ccw_cmd_region, private->cmd_region);
 	kmem_cache_free(vfio_ccw_io_region, private->io_region);
 	kfree(private);
 
@@ -237,7 +258,7 @@ static struct css_driver vfio_ccw_sch_driver = {
 
 static int __init vfio_ccw_sch_init(void)
 {
-	int ret;
+	int ret = -ENOMEM;
 
 	vfio_ccw_work_q = create_singlethread_workqueue("vfio-ccw");
 	if (!vfio_ccw_work_q)
@@ -247,20 +268,30 @@ static int __init vfio_ccw_sch_init(void)
 					sizeof(struct ccw_io_region), 0,
 					SLAB_ACCOUNT, 0,
 					sizeof(struct ccw_io_region), NULL);
-	if (!vfio_ccw_io_region) {
-		destroy_workqueue(vfio_ccw_work_q);
-		return -ENOMEM;
-	}
+	if (!vfio_ccw_io_region)
+		goto out_err;
+
+	vfio_ccw_cmd_region = kmem_cache_create_usercopy("vfio_ccw_cmd_region",
+					sizeof(struct ccw_cmd_region), 0,
+					SLAB_ACCOUNT, 0,
+					sizeof(struct ccw_cmd_region), NULL);
+	if (!vfio_ccw_cmd_region)
+		goto out_err;
 
 	isc_register(VFIO_CCW_ISC);
 	ret = css_driver_register(&vfio_ccw_sch_driver);
 	if (ret) {
 		isc_unregister(VFIO_CCW_ISC);
-		kmem_cache_destroy(vfio_ccw_io_region);
-		destroy_workqueue(vfio_ccw_work_q);
+		goto out_err;
 	}
 
 	return ret;
+
+out_err:
+	kmem_cache_destroy(vfio_ccw_cmd_region);
+	kmem_cache_destroy(vfio_ccw_io_region);
+	destroy_workqueue(vfio_ccw_work_q);
+	return ret;
 }
 
 static void __exit vfio_ccw_sch_exit(void)
diff --git a/drivers/s390/cio/vfio_ccw_fsm.c b/drivers/s390/cio/vfio_ccw_fsm.c
index cab17865aafe..49d9d3da0282 100644
--- a/drivers/s390/cio/vfio_ccw_fsm.c
+++ b/drivers/s390/cio/vfio_ccw_fsm.c
@@ -3,8 +3,10 @@
  * Finite state machine for vfio-ccw device handling
  *
  * Copyright IBM Corp. 2017
+ * Copyright Red Hat, Inc. 2019
  *
  * Author(s): Dong Jia Shi <bjsdjshi@linux.vnet.ibm.com>
+ *            Cornelia Huck <cohuck@redhat.com>
  */
 
 #include <linux/vfio.h>
@@ -28,9 +30,12 @@ static int fsm_io_helper(struct vfio_ccw_private *private)
 	sch = private->sch;
 
 	spin_lock_irqsave(sch->lock, flags);
-	private->state = VFIO_CCW_STATE_BUSY;
 
 	orb = cp_get_orb(&private->cp, (u32)(addr_t)sch, sch->lpm);
+	if (!orb) {
+		ret = -EIO;
+		goto out;
+	}
 
 	/* Issue "Start Subchannel" */
 	ccode = ssch(sch->schid, orb);
@@ -42,6 +47,7 @@ static int fsm_io_helper(struct vfio_ccw_private *private)
 		 */
 		sch->schib.scsw.cmd.actl |= SCSW_ACTL_START_PEND;
 		ret = 0;
+		private->state = VFIO_CCW_STATE_CP_PENDING;
 		break;
 	case 1:		/* Status pending */
 	case 2:		/* Busy */
@@ -64,6 +70,76 @@ static int fsm_io_helper(struct vfio_ccw_private *private)
 	default:
 		ret = ccode;
 	}
+out:
+	spin_unlock_irqrestore(sch->lock, flags);
+	return ret;
+}
+
+static int fsm_do_halt(struct vfio_ccw_private *private)
+{
+	struct subchannel *sch;
+	unsigned long flags;
+	int ccode;
+	int ret;
+
+	sch = private->sch;
+
+	spin_lock_irqsave(sch->lock, flags);
+
+	/* Issue "Halt Subchannel" */
+	ccode = hsch(sch->schid);
+
+	switch (ccode) {
+	case 0:
+		/*
+		 * Initialize device status information
+		 */
+		sch->schib.scsw.cmd.actl |= SCSW_ACTL_HALT_PEND;
+		ret = 0;
+		break;
+	case 1:		/* Status pending */
+	case 2:		/* Busy */
+		ret = -EBUSY;
+		break;
+	case 3:		/* Device not operational */
+		ret = -ENODEV;
+		break;
+	default:
+		ret = ccode;
+	}
+	spin_unlock_irqrestore(sch->lock, flags);
+	return ret;
+}
+
+static int fsm_do_clear(struct vfio_ccw_private *private)
+{
+	struct subchannel *sch;
+	unsigned long flags;
+	int ccode;
+	int ret;
+
+	sch = private->sch;
+
+	spin_lock_irqsave(sch->lock, flags);
+
+	/* Issue "Clear Subchannel" */
+	ccode = csch(sch->schid);
+
+	switch (ccode) {
+	case 0:
+		/*
+		 * Initialize device status information
+		 */
+		sch->schib.scsw.cmd.actl = SCSW_ACTL_CLEAR_PEND;
+		/* TODO: check what else we might need to clear */
+		ret = 0;
+		break;
+	case 3:		/* Device not operational */
+		ret = -ENODEV;
+		break;
+	default:
+		ret = ccode;
+	}
 	spin_unlock_irqrestore(sch->lock, flags);
 	return ret;
 }
@@ -102,6 +178,30 @@ static void fsm_io_busy(struct vfio_ccw_private *private,
 	private->io_region->ret_code = -EBUSY;
 }
 
+static void fsm_io_retry(struct vfio_ccw_private *private,
+			 enum vfio_ccw_event event)
+{
+	private->io_region->ret_code = -EAGAIN;
+}
+
+static void fsm_async_error(struct vfio_ccw_private *private,
+			    enum vfio_ccw_event event)
+{
+	struct ccw_cmd_region *cmd_region = private->cmd_region;
+
+	pr_err("vfio-ccw: FSM: %s request from state:%d\n",
+	       cmd_region->command == VFIO_CCW_ASYNC_CMD_HSCH ? "halt" :
+	       cmd_region->command == VFIO_CCW_ASYNC_CMD_CSCH ? "clear" :
+	       "<unknown>", private->state);
+	cmd_region->ret_code = -EIO;
+}
+
+static void fsm_async_retry(struct vfio_ccw_private *private,
+			    enum vfio_ccw_event event)
+{
+	private->cmd_region->ret_code = -EAGAIN;
+}
+
 static void fsm_disabled_irq(struct vfio_ccw_private *private,
 			     enum vfio_ccw_event event)
 {
@@ -130,8 +230,7 @@ static void fsm_io_request(struct vfio_ccw_private *private,
 	struct mdev_device *mdev = private->mdev;
 	char *errstr = "request";
 
-	private->state = VFIO_CCW_STATE_BUSY;
-
+	private->state = VFIO_CCW_STATE_CP_PROCESSING;
 	memcpy(scsw, io_region->scsw_area, sizeof(*scsw));
 
 	if (scsw->cmd.fctl & SCSW_FCTL_START_FUNC) {
@@ -166,22 +265,42 @@ static void fsm_io_request(struct vfio_ccw_private *private,
 		}
 		return;
 	} else if (scsw->cmd.fctl & SCSW_FCTL_HALT_FUNC) {
-		/* XXX: Handle halt. */
+		/* halt is handled via the async cmd region */
 		io_region->ret_code = -EOPNOTSUPP;
 		goto err_out;
 	} else if (scsw->cmd.fctl & SCSW_FCTL_CLEAR_FUNC) {
-		/* XXX: Handle clear. */
+		/* clear is handled via the async cmd region */
 		io_region->ret_code = -EOPNOTSUPP;
 		goto err_out;
 	}
 
 err_out:
-	private->state = VFIO_CCW_STATE_IDLE;
 	trace_vfio_ccw_io_fctl(scsw->cmd.fctl, get_schid(private),
 			       io_region->ret_code, errstr);
 }
 
 /*
+ * Deal with an async request from userspace.
+ */
+static void fsm_async_request(struct vfio_ccw_private *private,
+			      enum vfio_ccw_event event)
+{
+	struct ccw_cmd_region *cmd_region = private->cmd_region;
+
+	switch (cmd_region->command) {
+	case VFIO_CCW_ASYNC_CMD_HSCH:
+		cmd_region->ret_code = fsm_do_halt(private);
+		break;
+	case VFIO_CCW_ASYNC_CMD_CSCH:
+		cmd_region->ret_code = fsm_do_clear(private);
+		break;
+	default:
+		/* should not happen? */
+		cmd_region->ret_code = -EINVAL;
+	}
+}
+
+/*
  * Got an interrupt for a normal io (state busy).
  */
 static void fsm_irq(struct vfio_ccw_private *private,
@@ -204,21 +323,31 @@ fsm_func_t *vfio_ccw_jumptable[NR_VFIO_CCW_STATES][NR_VFIO_CCW_EVENTS] = {
 	[VFIO_CCW_STATE_NOT_OPER] = {
 		[VFIO_CCW_EVENT_NOT_OPER]	= fsm_nop,
 		[VFIO_CCW_EVENT_IO_REQ]		= fsm_io_error,
+		[VFIO_CCW_EVENT_ASYNC_REQ]	= fsm_async_error,
 		[VFIO_CCW_EVENT_INTERRUPT]	= fsm_disabled_irq,
 	},
 	[VFIO_CCW_STATE_STANDBY] = {
 		[VFIO_CCW_EVENT_NOT_OPER]	= fsm_notoper,
 		[VFIO_CCW_EVENT_IO_REQ]		= fsm_io_error,
+		[VFIO_CCW_EVENT_ASYNC_REQ]	= fsm_async_error,
 		[VFIO_CCW_EVENT_INTERRUPT]	= fsm_irq,
 	},
 	[VFIO_CCW_STATE_IDLE] = {
 		[VFIO_CCW_EVENT_NOT_OPER]	= fsm_notoper,
 		[VFIO_CCW_EVENT_IO_REQ]		= fsm_io_request,
+		[VFIO_CCW_EVENT_ASYNC_REQ]	= fsm_async_request,
+		[VFIO_CCW_EVENT_INTERRUPT]	= fsm_irq,
+	},
+	[VFIO_CCW_STATE_CP_PROCESSING] = {
+		[VFIO_CCW_EVENT_NOT_OPER]	= fsm_notoper,
+		[VFIO_CCW_EVENT_IO_REQ]		= fsm_io_retry,
+		[VFIO_CCW_EVENT_ASYNC_REQ]	= fsm_async_retry,
 		[VFIO_CCW_EVENT_INTERRUPT]	= fsm_irq,
 	},
-	[VFIO_CCW_STATE_BUSY] = {
+	[VFIO_CCW_STATE_CP_PENDING] = {
 		[VFIO_CCW_EVENT_NOT_OPER]	= fsm_notoper,
 		[VFIO_CCW_EVENT_IO_REQ]		= fsm_io_busy,
+		[VFIO_CCW_EVENT_ASYNC_REQ]	= fsm_async_request,
 		[VFIO_CCW_EVENT_INTERRUPT]	= fsm_irq,
 	},
 };
diff --git a/drivers/s390/cio/vfio_ccw_ops.c b/drivers/s390/cio/vfio_ccw_ops.c
index f673e106c041..5eb61116ca6f 100644
--- a/drivers/s390/cio/vfio_ccw_ops.c
+++ b/drivers/s390/cio/vfio_ccw_ops.c
@@ -3,13 +3,17 @@
  * Physical device callbacks for vfio_ccw
  *
  * Copyright IBM Corp. 2017
+ * Copyright Red Hat, Inc. 2019
  *
  * Author(s): Dong Jia Shi <bjsdjshi@linux.vnet.ibm.com>
  *            Xiao Feng Ren <renxiaof@linux.vnet.ibm.com>
+ *            Cornelia Huck <cohuck@redhat.com>
  */
 
 #include <linux/vfio.h>
 #include <linux/mdev.h>
+#include <linux/nospec.h>
+#include <linux/slab.h>
 
 #include "vfio_ccw_private.h"
 
@@ -130,11 +134,12 @@ static int vfio_ccw_mdev_remove(struct mdev_device *mdev)
 
 	if ((private->state != VFIO_CCW_STATE_NOT_OPER) &&
 	    (private->state != VFIO_CCW_STATE_STANDBY)) {
-		if (!vfio_ccw_mdev_reset(mdev))
+		if (!vfio_ccw_sch_quiesce(private->sch))
 			private->state = VFIO_CCW_STATE_STANDBY;
 		/* The state will be NOT_OPER on error. */
 	}
 
+	cp_free(&private->cp);
 	private->mdev = NULL;
 	atomic_inc(&private->avail);
 
@@ -146,20 +151,66 @@ static int vfio_ccw_mdev_open(struct mdev_device *mdev)
 	struct vfio_ccw_private *private =
 		dev_get_drvdata(mdev_parent_dev(mdev));
 	unsigned long events = VFIO_IOMMU_NOTIFY_DMA_UNMAP;
+	int ret;
 
 	private->nb.notifier_call = vfio_ccw_mdev_notifier;
 
-	return vfio_register_notifier(mdev_dev(mdev), VFIO_IOMMU_NOTIFY,
-				      &events, &private->nb);
+	ret = vfio_register_notifier(mdev_dev(mdev), VFIO_IOMMU_NOTIFY,
+				     &events, &private->nb);
+	if (ret)
+		return ret;
+
+	ret = vfio_ccw_register_async_dev_regions(private);
+	if (ret)
+		vfio_unregister_notifier(mdev_dev(mdev), VFIO_IOMMU_NOTIFY,
+					 &private->nb);
+	return ret;
 }
 
 static void vfio_ccw_mdev_release(struct mdev_device *mdev)
 {
 	struct vfio_ccw_private *private =
 		dev_get_drvdata(mdev_parent_dev(mdev));
+	int i;
 
+	if ((private->state != VFIO_CCW_STATE_NOT_OPER) &&
+	    (private->state != VFIO_CCW_STATE_STANDBY)) {
+		if (!vfio_ccw_mdev_reset(mdev))
+			private->state = VFIO_CCW_STATE_STANDBY;
+		/* The state will be NOT_OPER on error. */
+	}
+
+	cp_free(&private->cp);
 	vfio_unregister_notifier(mdev_dev(mdev), VFIO_IOMMU_NOTIFY,
 				 &private->nb);
+
+	for (i = 0; i < private->num_regions; i++)
+		private->region[i].ops->release(private, &private->region[i]);
+
+	private->num_regions = 0;
+	kfree(private->region);
+	private->region = NULL;
+}
+
+static ssize_t vfio_ccw_mdev_read_io_region(struct vfio_ccw_private *private,
+					    char __user *buf, size_t count,
+					    loff_t *ppos)
+{
+	loff_t pos = *ppos & VFIO_CCW_OFFSET_MASK;
+	struct ccw_io_region *region;
+	int ret;
+
+	if (pos + count > sizeof(*region))
+		return -EINVAL;
+
+	mutex_lock(&private->io_mutex);
+	region = private->io_region;
+	if (copy_to_user(buf, (void *)region + pos, count))
+		ret = -EFAULT;
+	else
+		ret = count;
+	mutex_unlock(&private->io_mutex);
+	return ret;
 }
 
 static ssize_t vfio_ccw_mdev_read(struct mdev_device *mdev,
@@ -167,18 +218,54 @@ static ssize_t vfio_ccw_mdev_read(struct mdev_device *mdev,
 				  size_t count,
 				  loff_t *ppos)
 {
+	unsigned int index = VFIO_CCW_OFFSET_TO_INDEX(*ppos);
 	struct vfio_ccw_private *private;
+
+	private = dev_get_drvdata(mdev_parent_dev(mdev));
+
+	if (index >= VFIO_CCW_NUM_REGIONS + private->num_regions)
+		return -EINVAL;
+
+	switch (index) {
+	case VFIO_CCW_CONFIG_REGION_INDEX:
+		return vfio_ccw_mdev_read_io_region(private, buf, count, ppos);
+	default:
+		index -= VFIO_CCW_NUM_REGIONS;
+		return private->region[index].ops->read(private, buf, count,
+							ppos);
+	}
+
+	return -EINVAL;
+}
+
+static ssize_t vfio_ccw_mdev_write_io_region(struct vfio_ccw_private *private,
+					     const char __user *buf,
+					     size_t count, loff_t *ppos)
+{
+	loff_t pos = *ppos & VFIO_CCW_OFFSET_MASK;
 	struct ccw_io_region *region;
+	int ret;
 
-	if (*ppos + count > sizeof(*region))
+	if (pos + count > sizeof(*region))
 		return -EINVAL;
 
-	private = dev_get_drvdata(mdev_parent_dev(mdev));
+	if (!mutex_trylock(&private->io_mutex))
+		return -EAGAIN;
+
 	region = private->io_region;
-	if (copy_to_user(buf, (void *)region + *ppos, count))
-		return -EFAULT;
+	if (copy_from_user((void *)region + pos, buf, count)) {
+		ret = -EFAULT;
+		goto out_unlock;
+	}
 
-	return count;
+	vfio_ccw_fsm_event(private, VFIO_CCW_EVENT_IO_REQ);
+	if (region->ret_code != 0)
+		private->state = VFIO_CCW_STATE_IDLE;
+	ret = (region->ret_code != 0) ? region->ret_code : count;
+
+out_unlock:
+	mutex_unlock(&private->io_mutex);
+	return ret;
 }
 
 static ssize_t vfio_ccw_mdev_write(struct mdev_device *mdev,
@@ -186,42 +273,47 @@ static ssize_t vfio_ccw_mdev_write(struct mdev_device *mdev,
 				   size_t count,
 				   loff_t *ppos)
 {
+	unsigned int index = VFIO_CCW_OFFSET_TO_INDEX(*ppos);
 	struct vfio_ccw_private *private;
-	struct ccw_io_region *region;
-
-	if (*ppos + count > sizeof(*region))
-		return -EINVAL;
 
 	private = dev_get_drvdata(mdev_parent_dev(mdev));
-	if (private->state != VFIO_CCW_STATE_IDLE)
-		return -EACCES;
 
-	region = private->io_region;
-	if (copy_from_user((void *)region + *ppos, buf, count))
-		return -EFAULT;
+	if (index >= VFIO_CCW_NUM_REGIONS + private->num_regions)
+		return -EINVAL;
 
-	vfio_ccw_fsm_event(private, VFIO_CCW_EVENT_IO_REQ);
-	if (region->ret_code != 0) {
-		private->state = VFIO_CCW_STATE_IDLE;
-		return region->ret_code;
+	switch (index) {
+	case VFIO_CCW_CONFIG_REGION_INDEX:
+		return vfio_ccw_mdev_write_io_region(private, buf, count, ppos);
+	default:
+		index -= VFIO_CCW_NUM_REGIONS;
+		return private->region[index].ops->write(private, buf, count,
+							 ppos);
 	}
 
-	return count;
+	return -EINVAL;
 }
 
-static int vfio_ccw_mdev_get_device_info(struct vfio_device_info *info)
+static int vfio_ccw_mdev_get_device_info(struct vfio_device_info *info,
+					 struct mdev_device *mdev)
 {
+	struct vfio_ccw_private *private;
+
+	private = dev_get_drvdata(mdev_parent_dev(mdev));
 	info->flags = VFIO_DEVICE_FLAGS_CCW | VFIO_DEVICE_FLAGS_RESET;
-	info->num_regions = VFIO_CCW_NUM_REGIONS;
+	info->num_regions = VFIO_CCW_NUM_REGIONS + private->num_regions;
 	info->num_irqs = VFIO_CCW_NUM_IRQS;
 
 	return 0;
 }
 
 static int vfio_ccw_mdev_get_region_info(struct vfio_region_info *info,
-					 u16 *cap_type_id,
-					 void **cap_type)
+					 struct mdev_device *mdev,
+					 unsigned long arg)
 {
+	struct vfio_ccw_private *private;
+	int i;
+
+	private = dev_get_drvdata(mdev_parent_dev(mdev));
 	switch (info->index) {
 	case VFIO_CCW_CONFIG_REGION_INDEX:
 		info->offset = 0;
@@ -229,9 +321,55 @@ static int vfio_ccw_mdev_get_region_info(struct vfio_region_info *info,
 		info->flags = VFIO_REGION_INFO_FLAG_READ
 			      | VFIO_REGION_INFO_FLAG_WRITE;
 		return 0;
-	default:
-		return -EINVAL;
+	default: /* all other regions are handled via capability chain */
+	{
+		struct vfio_info_cap caps = { .buf = NULL, .size = 0 };
+		struct vfio_region_info_cap_type cap_type = {
+			.header.id = VFIO_REGION_INFO_CAP_TYPE,
+			.header.version = 1 };
+		int ret;
+
+		if (info->index >=
+		    VFIO_CCW_NUM_REGIONS + private->num_regions)
+			return -EINVAL;
+
+		info->index = array_index_nospec(info->index,
+						 VFIO_CCW_NUM_REGIONS +
+						 private->num_regions);
+
+		i = info->index - VFIO_CCW_NUM_REGIONS;
+
+		info->offset = VFIO_CCW_INDEX_TO_OFFSET(info->index);
+		info->size = private->region[i].size;
+		info->flags = private->region[i].flags;
+
+		cap_type.type = private->region[i].type;
+		cap_type.subtype = private->region[i].subtype;
+
+		ret = vfio_info_add_capability(&caps, &cap_type.header,
+					       sizeof(cap_type));
+		if (ret)
+			return ret;
+
+		info->flags |= VFIO_REGION_INFO_FLAG_CAPS;
+		if (info->argsz < sizeof(*info) + caps.size) {
+			info->argsz = sizeof(*info) + caps.size;
+			info->cap_offset = 0;
+		} else {
+			vfio_info_cap_shift(&caps, sizeof(*info));
+			if (copy_to_user((void __user *)arg + sizeof(*info),
+					 caps.buf, caps.size)) {
+				kfree(caps.buf);
+				return -EFAULT;
+			}
+			info->cap_offset = sizeof(*info);
+		}
+
+		kfree(caps.buf);
+
 	}
+	}
+	return 0;
 }
 
 static int vfio_ccw_mdev_get_irq_info(struct vfio_irq_info *info)
@@ -308,6 +446,32 @@ static int vfio_ccw_mdev_set_irqs(struct mdev_device *mdev,
 	}
 }
 
+int vfio_ccw_register_dev_region(struct vfio_ccw_private *private,
+				 unsigned int subtype,
+				 const struct vfio_ccw_regops *ops,
+				 size_t size, u32 flags, void *data)
+{
+	struct vfio_ccw_region *region;
+
+	region = krealloc(private->region,
+			  (private->num_regions + 1) * sizeof(*region),
+			  GFP_KERNEL);
+	if (!region)
+		return -ENOMEM;
+
+	private->region = region;
+	private->region[private->num_regions].type = VFIO_REGION_TYPE_CCW;
+	private->region[private->num_regions].subtype = subtype;
+	private->region[private->num_regions].ops = ops;
+	private->region[private->num_regions].size = size;
+	private->region[private->num_regions].flags = flags;
+	private->region[private->num_regions].data = data;
+
+	private->num_regions++;
+
+	return 0;
+}
+
 static ssize_t vfio_ccw_mdev_ioctl(struct mdev_device *mdev,
 				   unsigned int cmd,
 				   unsigned long arg)
@@ -328,7 +492,7 @@ static ssize_t vfio_ccw_mdev_ioctl(struct mdev_device *mdev,
 		if (info.argsz < minsz)
 			return -EINVAL;
 
-		ret = vfio_ccw_mdev_get_device_info(&info);
+		ret = vfio_ccw_mdev_get_device_info(&info, mdev);
 		if (ret)
 			return ret;
 
@@ -337,8 +501,6 @@ static ssize_t vfio_ccw_mdev_ioctl(struct mdev_device *mdev,
 	case VFIO_DEVICE_GET_REGION_INFO:
 	{
 		struct vfio_region_info info;
-		u16 cap_type_id = 0;
-		void *cap_type = NULL;
 
 		minsz = offsetofend(struct vfio_region_info, offset);
 
@@ -348,8 +510,7 @@ static ssize_t vfio_ccw_mdev_ioctl(struct mdev_device *mdev,
 		if (info.argsz < minsz)
 			return -EINVAL;
 
-		ret = vfio_ccw_mdev_get_region_info(&info, &cap_type_id,
-						    &cap_type);
+		ret = vfio_ccw_mdev_get_region_info(&info, mdev, arg);
 		if (ret)
 			return ret;
 
diff --git a/drivers/s390/cio/vfio_ccw_private.h b/drivers/s390/cio/vfio_ccw_private.h
index 08e9a7dc9176..f1092c3dc1b1 100644
--- a/drivers/s390/cio/vfio_ccw_private.h
+++ b/drivers/s390/cio/vfio_ccw_private.h
@@ -3,9 +3,11 @@
  * Private stuff for vfio_ccw driver
  *
  * Copyright IBM Corp. 2017
+ * Copyright Red Hat, Inc. 2019
  *
  * Author(s): Dong Jia Shi <bjsdjshi@linux.vnet.ibm.com>
  *            Xiao Feng Ren <renxiaof@linux.vnet.ibm.com>
+ *            Cornelia Huck <cohuck@redhat.com>
  */
 
 #ifndef _VFIO_CCW_PRIVATE_H_
@@ -19,6 +21,40 @@
 #include "css.h"
 #include "vfio_ccw_cp.h"
 
+#define VFIO_CCW_OFFSET_SHIFT   10
+#define VFIO_CCW_OFFSET_TO_INDEX(off)	(off >> VFIO_CCW_OFFSET_SHIFT)
+#define VFIO_CCW_INDEX_TO_OFFSET(index)	((u64)(index) << VFIO_CCW_OFFSET_SHIFT)
+#define VFIO_CCW_OFFSET_MASK	(((u64)(1) << VFIO_CCW_OFFSET_SHIFT) - 1)
+
+/* capability chain handling similar to vfio-pci */
+struct vfio_ccw_private;
+struct vfio_ccw_region;
+
+struct vfio_ccw_regops {
+	ssize_t	(*read)(struct vfio_ccw_private *private, char __user *buf,
+			size_t count, loff_t *ppos);
+	ssize_t	(*write)(struct vfio_ccw_private *private,
+			 const char __user *buf, size_t count, loff_t *ppos);
+	void	(*release)(struct vfio_ccw_private *private,
+			   struct vfio_ccw_region *region);
+};
+
+struct vfio_ccw_region {
+	u32				type;
+	u32				subtype;
+	const struct vfio_ccw_regops	*ops;
+	void				*data;
+	size_t				size;
+	u32				flags;
+};
+
+int vfio_ccw_register_dev_region(struct vfio_ccw_private *private,
+				 unsigned int subtype,
+				 const struct vfio_ccw_regops *ops,
+				 size_t size, u32 flags, void *data);
+
+int vfio_ccw_register_async_dev_regions(struct vfio_ccw_private *private);
+
 /**
  * struct vfio_ccw_private
  * @sch: pointer to the subchannel
@@ -28,6 +64,10 @@
  * @mdev: pointer to the mediated device
  * @nb: notifier for vfio events
  * @io_region: MMIO region to input/output I/O arguments/results
+ * @io_mutex: protect against concurrent update of I/O regions
+ * @region: additional regions for other subchannel operations
+ * @cmd_region: MMIO region for asynchronous I/O commands other than START
+ * @num_regions: number of additional regions
  * @cp: channel program for the current I/O operation
  * @irb: irb info received from interrupt
  * @scsw: scsw info
@@ -42,6 +82,10 @@ struct vfio_ccw_private {
 	struct mdev_device	*mdev;
 	struct notifier_block	nb;
 	struct ccw_io_region	*io_region;
+	struct mutex		io_mutex;
+	struct vfio_ccw_region *region;
+	struct ccw_cmd_region	*cmd_region;
+	int num_regions;
 
 	struct channel_program	cp;
 	struct irb		irb;
@@ -63,7 +107,8 @@ enum vfio_ccw_state {
 	VFIO_CCW_STATE_NOT_OPER,
 	VFIO_CCW_STATE_STANDBY,
 	VFIO_CCW_STATE_IDLE,
-	VFIO_CCW_STATE_BUSY,
+	VFIO_CCW_STATE_CP_PROCESSING,
+	VFIO_CCW_STATE_CP_PENDING,
 	/* last element! */
 	NR_VFIO_CCW_STATES
 };
@@ -75,6 +120,7 @@ enum vfio_ccw_event {
 	VFIO_CCW_EVENT_NOT_OPER,
 	VFIO_CCW_EVENT_IO_REQ,
 	VFIO_CCW_EVENT_INTERRUPT,
+	VFIO_CCW_EVENT_ASYNC_REQ,
 	/* last element! */
 	NR_VFIO_CCW_EVENTS
 };
diff --git a/drivers/s390/crypto/ap_bus.c b/drivers/s390/crypto/ap_bus.c
index e15816ff1265..cc30e4f07fff 100644
--- a/drivers/s390/crypto/ap_bus.c
+++ b/drivers/s390/crypto/ap_bus.c
@@ -116,7 +116,7 @@ static int user_set_domain;
 static struct bus_type ap_bus_type;
 
 /* Adapter interrupt definitions */
-static void ap_interrupt_handler(struct airq_struct *airq);
+static void ap_interrupt_handler(struct airq_struct *airq, bool floating);
 
 static int ap_airq_flag;
 
@@ -393,7 +393,7 @@ static enum hrtimer_restart ap_poll_timeout(struct hrtimer *unused)
  * ap_interrupt_handler() - Schedule ap_tasklet on interrupt
  * @airq: pointer to adapter interrupt descriptor
  */
-static void ap_interrupt_handler(struct airq_struct *airq)
+static void ap_interrupt_handler(struct airq_struct *airq, bool floating)
 {
 	inc_irq_stat(IRQIO_APB);
 	if (!ap_suspend_flag)
@@ -810,11 +810,18 @@ static int ap_device_remove(struct device *dev)
 	struct ap_device *ap_dev = to_ap_dev(dev);
 	struct ap_driver *ap_drv = ap_dev->drv;
 
+	/* prepare ap queue device removal */
 	if (is_queue_dev(dev))
-		ap_queue_remove(to_ap_queue(dev));
+		ap_queue_prepare_remove(to_ap_queue(dev));
+
+	/* driver's chance to clean up gracefully */
 	if (ap_drv->remove)
 		ap_drv->remove(ap_dev);
 
+	/* now do the ap queue device remove */
+	if (is_queue_dev(dev))
+		ap_queue_remove(to_ap_queue(dev));
+
 	/* Remove queue/card from list of active queues/cards */
 	spin_lock_bh(&ap_list_lock);
 	if (is_card_dev(dev))
@@ -861,6 +868,16 @@ void ap_bus_force_rescan(void)
 EXPORT_SYMBOL(ap_bus_force_rescan);
 
 /*
+* A config change has happened, force an ap bus rescan.
+*/
+void ap_bus_cfg_chg(void)
+{
+	AP_DBF(DBF_INFO, "%s config change, forcing bus rescan\n", __func__);
+
+	ap_bus_force_rescan();
+}
+
+/*
  * hex2bitmap() - parse hex mask string and set bitmap.
  * Valid strings are "0x012345678" with at least one valid hex number.
  * Rest of the bitmap to the right is padded with 0. No spaces allowed
diff --git a/drivers/s390/crypto/ap_bus.h b/drivers/s390/crypto/ap_bus.h
index d0059eae5d94..15a98a673c5c 100644
--- a/drivers/s390/crypto/ap_bus.h
+++ b/drivers/s390/crypto/ap_bus.h
@@ -91,6 +91,7 @@ enum ap_state {
 	AP_STATE_WORKING,
 	AP_STATE_QUEUE_FULL,
 	AP_STATE_SUSPEND_WAIT,
+	AP_STATE_REMOVE,	/* about to be removed from driver */
 	AP_STATE_UNBOUND,	/* momentary not bound to a driver */
 	AP_STATE_BORKED,	/* broken */
 	NR_AP_STATES
@@ -252,6 +253,7 @@ void ap_bus_force_rescan(void);
 
 void ap_queue_init_reply(struct ap_queue *aq, struct ap_message *ap_msg);
 struct ap_queue *ap_queue_create(ap_qid_t qid, int device_type);
+void ap_queue_prepare_remove(struct ap_queue *aq);
 void ap_queue_remove(struct ap_queue *aq);
 void ap_queue_suspend(struct ap_device *ap_dev);
 void ap_queue_resume(struct ap_device *ap_dev);
diff --git a/drivers/s390/crypto/ap_queue.c b/drivers/s390/crypto/ap_queue.c
index ba261210c6da..5ea83dc4f1d7 100644
--- a/drivers/s390/crypto/ap_queue.c
+++ b/drivers/s390/crypto/ap_queue.c
@@ -420,6 +420,10 @@ static ap_func_t *ap_jumptable[NR_AP_STATES][NR_AP_EVENTS] = {
 		[AP_EVENT_POLL] = ap_sm_suspend_read,
 		[AP_EVENT_TIMEOUT] = ap_sm_nop,
 	},
+	[AP_STATE_REMOVE] = {
+		[AP_EVENT_POLL] = ap_sm_nop,
+		[AP_EVENT_TIMEOUT] = ap_sm_nop,
+	},
 	[AP_STATE_UNBOUND] = {
 		[AP_EVENT_POLL] = ap_sm_nop,
 		[AP_EVENT_TIMEOUT] = ap_sm_nop,
@@ -740,18 +744,31 @@ void ap_flush_queue(struct ap_queue *aq)
 }
 EXPORT_SYMBOL(ap_flush_queue);
 
-void ap_queue_remove(struct ap_queue *aq)
+void ap_queue_prepare_remove(struct ap_queue *aq)
 {
-	ap_flush_queue(aq);
+	spin_lock_bh(&aq->lock);
+	/* flush queue */
+	__ap_flush_queue(aq);
+	/* set REMOVE state to prevent new messages are queued in */
+	aq->state = AP_STATE_REMOVE;
+	spin_unlock_bh(&aq->lock);
 	del_timer_sync(&aq->timeout);
+}
 
-	/* reset with zero, also clears irq registration */
+void ap_queue_remove(struct ap_queue *aq)
+{
+	/*
+	 * all messages have been flushed and the state is
+	 * AP_STATE_REMOVE. Now reset with zero which also
+	 * clears the irq registration and move the state
+	 * to AP_STATE_UNBOUND to signal that this queue
+	 * is not used by any driver currently.
+	 */
 	spin_lock_bh(&aq->lock);
 	ap_zapq(aq->qid);
 	aq->state = AP_STATE_UNBOUND;
 	spin_unlock_bh(&aq->lock);
 }
-EXPORT_SYMBOL(ap_queue_remove);
 
 void ap_queue_reinit_state(struct ap_queue *aq)
 {
@@ -760,4 +777,3 @@ void ap_queue_reinit_state(struct ap_queue *aq)
 	ap_wait(ap_sm_event(aq, AP_EVENT_POLL));
 	spin_unlock_bh(&aq->lock);
 }
-EXPORT_SYMBOL(ap_queue_reinit_state);
diff --git a/drivers/s390/crypto/pkey_api.c b/drivers/s390/crypto/pkey_api.c
index 3e85d665c572..45eb0c14b880 100644
--- a/drivers/s390/crypto/pkey_api.c
+++ b/drivers/s390/crypto/pkey_api.c
@@ -51,7 +51,8 @@ static debug_info_t *debug_info;
 
 static void __init pkey_debug_init(void)
 {
-	debug_info = debug_register("pkey", 1, 1, 4 * sizeof(long));
+	/* 5 arguments per dbf entry (including the format string ptr) */
+	debug_info = debug_register("pkey", 1, 1, 5 * sizeof(long));
 	debug_register_view(debug_info, &debug_sprintf_view);
 	debug_set_level(debug_info, 3);
 }
diff --git a/drivers/s390/crypto/zcrypt_api.c b/drivers/s390/crypto/zcrypt_api.c
index eb93c2d27d0a..c31b2d31cd83 100644
--- a/drivers/s390/crypto/zcrypt_api.c
+++ b/drivers/s390/crypto/zcrypt_api.c
@@ -586,6 +586,7 @@ static inline bool zcrypt_check_queue(struct ap_perms *perms, int queue)
 
 static inline struct zcrypt_queue *zcrypt_pick_queue(struct zcrypt_card *zc,
 						     struct zcrypt_queue *zq,
+						     struct module **pmod,
 						     unsigned int weight)
 {
 	if (!zq || !try_module_get(zq->queue->ap_dev.drv->driver.owner))
@@ -595,15 +596,15 @@ static inline struct zcrypt_queue *zcrypt_pick_queue(struct zcrypt_card *zc,
 	atomic_add(weight, &zc->load);
 	atomic_add(weight, &zq->load);
 	zq->request_count++;
+	*pmod = zq->queue->ap_dev.drv->driver.owner;
 	return zq;
 }
 
 static inline void zcrypt_drop_queue(struct zcrypt_card *zc,
 				     struct zcrypt_queue *zq,
+				     struct module *mod,
 				     unsigned int weight)
 {
-	struct module *mod = zq->queue->ap_dev.drv->driver.owner;
-
 	zq->request_count--;
 	atomic_sub(weight, &zc->load);
 	atomic_sub(weight, &zq->load);
@@ -653,10 +654,12 @@ static long zcrypt_rsa_modexpo(struct ap_perms *perms,
 	unsigned int weight, pref_weight;
 	unsigned int func_code;
 	int qid = 0, rc = -ENODEV;
+	struct module *mod;
 
 	trace_s390_zcrypt_req(mex, TP_ICARSAMODEXPO);
 
 	if (mex->outputdatalength < mex->inputdatalength) {
+		func_code = 0;
 		rc = -EINVAL;
 		goto out;
 	}
@@ -706,7 +709,7 @@ static long zcrypt_rsa_modexpo(struct ap_perms *perms,
 			pref_weight = weight;
 		}
 	}
-	pref_zq = zcrypt_pick_queue(pref_zc, pref_zq, weight);
+	pref_zq = zcrypt_pick_queue(pref_zc, pref_zq, &mod, weight);
 	spin_unlock(&zcrypt_list_lock);
 
 	if (!pref_zq) {
@@ -718,7 +721,7 @@ static long zcrypt_rsa_modexpo(struct ap_perms *perms,
 	rc = pref_zq->ops->rsa_modexpo(pref_zq, mex);
 
 	spin_lock(&zcrypt_list_lock);
-	zcrypt_drop_queue(pref_zc, pref_zq, weight);
+	zcrypt_drop_queue(pref_zc, pref_zq, mod, weight);
 	spin_unlock(&zcrypt_list_lock);
 
 out:
@@ -735,10 +738,12 @@ static long zcrypt_rsa_crt(struct ap_perms *perms,
 	unsigned int weight, pref_weight;
 	unsigned int func_code;
 	int qid = 0, rc = -ENODEV;
+	struct module *mod;
 
 	trace_s390_zcrypt_req(crt, TP_ICARSACRT);
 
 	if (crt->outputdatalength < crt->inputdatalength) {
+		func_code = 0;
 		rc = -EINVAL;
 		goto out;
 	}
@@ -788,7 +793,7 @@ static long zcrypt_rsa_crt(struct ap_perms *perms,
 			pref_weight = weight;
 		}
 	}
-	pref_zq = zcrypt_pick_queue(pref_zc, pref_zq, weight);
+	pref_zq = zcrypt_pick_queue(pref_zc, pref_zq, &mod, weight);
 	spin_unlock(&zcrypt_list_lock);
 
 	if (!pref_zq) {
@@ -800,7 +805,7 @@ static long zcrypt_rsa_crt(struct ap_perms *perms,
 	rc = pref_zq->ops->rsa_modexpo_crt(pref_zq, crt);
 
 	spin_lock(&zcrypt_list_lock);
-	zcrypt_drop_queue(pref_zc, pref_zq, weight);
+	zcrypt_drop_queue(pref_zc, pref_zq, mod, weight);
 	spin_unlock(&zcrypt_list_lock);
 
 out:
@@ -819,6 +824,7 @@ static long _zcrypt_send_cprb(struct ap_perms *perms,
 	unsigned int func_code;
 	unsigned short *domain;
 	int qid = 0, rc = -ENODEV;
+	struct module *mod;
 
 	trace_s390_zcrypt_req(xcRB, TB_ZSECSENDCPRB);
 
@@ -865,7 +871,7 @@ static long _zcrypt_send_cprb(struct ap_perms *perms,
 			pref_weight = weight;
 		}
 	}
-	pref_zq = zcrypt_pick_queue(pref_zc, pref_zq, weight);
+	pref_zq = zcrypt_pick_queue(pref_zc, pref_zq, &mod, weight);
 	spin_unlock(&zcrypt_list_lock);
 
 	if (!pref_zq) {
@@ -881,7 +887,7 @@ static long _zcrypt_send_cprb(struct ap_perms *perms,
 	rc = pref_zq->ops->send_cprb(pref_zq, xcRB, &ap_msg);
 
 	spin_lock(&zcrypt_list_lock);
-	zcrypt_drop_queue(pref_zc, pref_zq, weight);
+	zcrypt_drop_queue(pref_zc, pref_zq, mod, weight);
 	spin_unlock(&zcrypt_list_lock);
 
 out:
@@ -932,6 +938,7 @@ static long zcrypt_send_ep11_cprb(struct ap_perms *perms,
 	unsigned int func_code;
 	struct ap_message ap_msg;
 	int qid = 0, rc = -ENODEV;
+	struct module *mod;
 
 	trace_s390_zcrypt_req(xcrb, TP_ZSENDEP11CPRB);
 
@@ -946,6 +953,7 @@ static long zcrypt_send_ep11_cprb(struct ap_perms *perms,
 
 		targets = kcalloc(target_num, sizeof(*targets), GFP_KERNEL);
 		if (!targets) {
+			func_code = 0;
 			rc = -ENOMEM;
 			goto out;
 		}
@@ -953,6 +961,7 @@ static long zcrypt_send_ep11_cprb(struct ap_perms *perms,
 		uptr = (struct ep11_target_dev __force __user *) xcrb->targets;
 		if (copy_from_user(targets, uptr,
 				   target_num * sizeof(*targets))) {
+			func_code = 0;
 			rc = -EFAULT;
 			goto out_free;
 		}
@@ -1000,7 +1009,7 @@ static long zcrypt_send_ep11_cprb(struct ap_perms *perms,
 			pref_weight = weight;
 		}
 	}
-	pref_zq = zcrypt_pick_queue(pref_zc, pref_zq, weight);
+	pref_zq = zcrypt_pick_queue(pref_zc, pref_zq, &mod, weight);
 	spin_unlock(&zcrypt_list_lock);
 
 	if (!pref_zq) {
@@ -1012,7 +1021,7 @@ static long zcrypt_send_ep11_cprb(struct ap_perms *perms,
 	rc = pref_zq->ops->send_ep11_cprb(pref_zq, xcrb, &ap_msg);
 
 	spin_lock(&zcrypt_list_lock);
-	zcrypt_drop_queue(pref_zc, pref_zq, weight);
+	zcrypt_drop_queue(pref_zc, pref_zq, mod, weight);
 	spin_unlock(&zcrypt_list_lock);
 
 out_free:
@@ -1033,6 +1042,7 @@ static long zcrypt_rng(char *buffer)
 	struct ap_message ap_msg;
 	unsigned int domain;
 	int qid = 0, rc = -ENODEV;
+	struct module *mod;
 
 	trace_s390_zcrypt_req(buffer, TP_HWRNGCPRB);
 
@@ -1064,7 +1074,7 @@ static long zcrypt_rng(char *buffer)
 			pref_weight = weight;
 		}
 	}
-	pref_zq = zcrypt_pick_queue(pref_zc, pref_zq, weight);
+	pref_zq = zcrypt_pick_queue(pref_zc, pref_zq, &mod, weight);
 	spin_unlock(&zcrypt_list_lock);
 
 	if (!pref_zq) {
@@ -1076,7 +1086,7 @@ static long zcrypt_rng(char *buffer)
 	rc = pref_zq->ops->rng(pref_zq, buffer, &ap_msg);
 
 	spin_lock(&zcrypt_list_lock);
-	zcrypt_drop_queue(pref_zc, pref_zq, weight);
+	zcrypt_drop_queue(pref_zc, pref_zq, mod, weight);
 	spin_unlock(&zcrypt_list_lock);
 
 out:
diff --git a/drivers/s390/net/ctcm_main.c b/drivers/s390/net/ctcm_main.c
index 7617d21cb296..f63c5c871d3d 100644
--- a/drivers/s390/net/ctcm_main.c
+++ b/drivers/s390/net/ctcm_main.c
@@ -1595,6 +1595,7 @@ static int ctcm_new_device(struct ccwgroup_device *cgdev)
 		if (priv->channel[direction] == NULL) {
 			if (direction == CTCM_WRITE)
 				channel_free(priv->channel[CTCM_READ]);
+			result = -ENODEV;
 			goto out_dev;
 		}
 		priv->channel[direction]->netdev = dev;
diff --git a/drivers/s390/net/ism.h b/drivers/s390/net/ism.h
index 0aab90817326..66eac2b9704d 100644
--- a/drivers/s390/net/ism.h
+++ b/drivers/s390/net/ism.h
@@ -6,6 +6,7 @@
 #include <linux/types.h>
 #include <linux/pci.h>
 #include <net/smc.h>
+#include <asm/pci_insn.h>
 
 #define UTIL_STR_LEN	16
 
@@ -194,8 +195,6 @@ struct ism_dev {
 	struct pci_dev *pdev;
 	struct smcd_dev *smcd;
 
-	void __iomem *ctl;
-
 	struct ism_sba *sba;
 	dma_addr_t sba_dma_addr;
 	DECLARE_BITMAP(sba_bitmap, ISM_NR_DMBS);
@@ -209,13 +208,37 @@ struct ism_dev {
 #define ISM_CREATE_REQ(dmb, idx, sf, offset)		\
 	((dmb) | (idx) << 24 | (sf) << 23 | (offset))
 
+static inline void __ism_read_cmd(struct ism_dev *ism, void *data,
+				  unsigned long offset, unsigned long len)
+{
+	struct zpci_dev *zdev = to_zpci(ism->pdev);
+	u64 req = ZPCI_CREATE_REQ(zdev->fh, 2, 8);
+
+	while (len > 0) {
+		__zpci_load(data, req, offset);
+		offset += 8;
+		data += 8;
+		len -= 8;
+	}
+}
+
+static inline void __ism_write_cmd(struct ism_dev *ism, void *data,
+				   unsigned long offset, unsigned long len)
+{
+	struct zpci_dev *zdev = to_zpci(ism->pdev);
+	u64 req = ZPCI_CREATE_REQ(zdev->fh, 2, len);
+
+	if (len)
+		__zpci_store_block(data, req, offset);
+}
+
 static inline int __ism_move(struct ism_dev *ism, u64 dmb_req, void *data,
 			     unsigned int size)
 {
 	struct zpci_dev *zdev = to_zpci(ism->pdev);
 	u64 req = ZPCI_CREATE_REQ(zdev->fh, 0, size);
 
-	return zpci_write_block(req, data, dmb_req);
+	return __zpci_store_block(data, req, dmb_req);
 }
 
 #endif /* S390_ISM_H */
diff --git a/drivers/s390/net/ism_drv.c b/drivers/s390/net/ism_drv.c
index 3e132592c1fe..4fc2056bd227 100644
--- a/drivers/s390/net/ism_drv.c
+++ b/drivers/s390/net/ism_drv.c
@@ -38,19 +38,18 @@ static int ism_cmd(struct ism_dev *ism, void *cmd)
 	struct ism_req_hdr *req = cmd;
 	struct ism_resp_hdr *resp = cmd;
 
-	memcpy_toio(ism->ctl + sizeof(*req), req + 1, req->len - sizeof(*req));
-	memcpy_toio(ism->ctl, req, sizeof(*req));
+	__ism_write_cmd(ism, req + 1, sizeof(*req), req->len - sizeof(*req));
+	__ism_write_cmd(ism, req, 0, sizeof(*req));
 
 	WRITE_ONCE(resp->ret, ISM_ERROR);
 
-	memcpy_fromio(resp, ism->ctl, sizeof(*resp));
+	__ism_read_cmd(ism, resp, 0, sizeof(*resp));
 	if (resp->ret) {
 		debug_text_event(ism_debug_info, 0, "cmd failure");
 		debug_event(ism_debug_info, 0, resp, sizeof(*resp));
 		goto out;
 	}
-	memcpy_fromio(resp + 1, ism->ctl + sizeof(*resp),
-		      resp->len - sizeof(*resp));
+	__ism_read_cmd(ism, resp + 1, sizeof(*resp), resp->len - sizeof(*resp));
 out:
 	return resp->ret;
 }
@@ -512,13 +511,9 @@ static int ism_probe(struct pci_dev *pdev, const struct pci_device_id *id)
 	if (ret)
 		goto err_disable;
 
-	ism->ctl = pci_iomap(pdev, 2, 0);
-	if (!ism->ctl)
-		goto err_resource;
-
 	ret = pci_set_dma_mask(pdev, DMA_BIT_MASK(64));
 	if (ret)
-		goto err_unmap;
+		goto err_resource;
 
 	dma_set_seg_boundary(&pdev->dev, SZ_1M - 1);
 	dma_set_max_seg_size(&pdev->dev, SZ_1M);
@@ -527,7 +522,7 @@ static int ism_probe(struct pci_dev *pdev, const struct pci_device_id *id)
 	ism->smcd = smcd_alloc_dev(&pdev->dev, dev_name(&pdev->dev), &ism_ops,
 				   ISM_NR_DMBS);
 	if (!ism->smcd)
-		goto err_unmap;
+		goto err_resource;
 
 	ism->smcd->priv = ism;
 	ret = ism_dev_init(ism);
@@ -538,8 +533,6 @@ static int ism_probe(struct pci_dev *pdev, const struct pci_device_id *id)
 
 err_free:
 	smcd_free_dev(ism->smcd);
-err_unmap:
-	pci_iounmap(pdev, ism->ctl);
 err_resource:
 	pci_release_mem_regions(pdev);
 err_disable:
@@ -568,7 +561,6 @@ static void ism_remove(struct pci_dev *pdev)
 	ism_dev_exit(ism);
 
 	smcd_free_dev(ism->smcd);
-	pci_iounmap(pdev, ism->ctl);
 	pci_release_mem_regions(pdev);
 	pci_disable_device(pdev);
 	dev_set_drvdata(&pdev->dev, NULL);
diff --git a/drivers/s390/net/qeth_core_main.c b/drivers/s390/net/qeth_core_main.c
index 197b0f5b63e7..44bd6f04c145 100644
--- a/drivers/s390/net/qeth_core_main.c
+++ b/drivers/s390/net/qeth_core_main.c
@@ -1150,13 +1150,16 @@ static void qeth_notify_skbs(struct qeth_qdio_out_q *q,
 
 static void qeth_release_skbs(struct qeth_qdio_out_buffer *buf)
 {
+	struct sk_buff *skb;
+
 	/* release may never happen from within CQ tasklet scope */
 	WARN_ON_ONCE(atomic_read(&buf->state) == QETH_QDIO_BUF_IN_CQ);
 
 	if (atomic_read(&buf->state) == QETH_QDIO_BUF_PENDING)
 		qeth_notify_skbs(buf->q, buf, TX_NOTIFY_GENERALERROR);
 
-	__skb_queue_purge(&buf->skb_list);
+	while ((skb = __skb_dequeue(&buf->skb_list)) != NULL)
+		consume_skb(skb);
 }
 
 static void qeth_clear_output_buffer(struct qeth_qdio_out_q *queue,
diff --git a/drivers/s390/net/qeth_l2_main.c b/drivers/s390/net/qeth_l2_main.c
index 8efb2e8ff8f4..c3067fd3bd9e 100644
--- a/drivers/s390/net/qeth_l2_main.c
+++ b/drivers/s390/net/qeth_l2_main.c
@@ -629,8 +629,7 @@ static netdev_tx_t qeth_l2_hard_start_xmit(struct sk_buff *skb,
 	} /* else fall through */
 
 	QETH_TXQ_STAT_INC(queue, tx_dropped);
-	QETH_TXQ_STAT_INC(queue, tx_errors);
-	dev_kfree_skb_any(skb);
+	kfree_skb(skb);
 	netif_wake_queue(dev);
 	return NETDEV_TX_OK;
 }
@@ -645,6 +644,8 @@ static int qeth_l2_probe_device(struct ccwgroup_device *gdev)
 	struct qeth_card *card = dev_get_drvdata(&gdev->dev);
 	int rc;
 
+	qeth_l2_vnicc_set_defaults(card);
+
 	if (gdev->dev.type == &qeth_generic_devtype) {
 		rc = qeth_l2_create_device_attributes(&gdev->dev);
 		if (rc)
@@ -652,8 +653,6 @@ static int qeth_l2_probe_device(struct ccwgroup_device *gdev)
 	}
 
 	hash_init(card->mac_htable);
-	card->info.hwtrap = 0;
-	qeth_l2_vnicc_set_defaults(card);
 	return 0;
 }
 
diff --git a/drivers/s390/net/qeth_l3_main.c b/drivers/s390/net/qeth_l3_main.c
index 7e68d9d16859..53712cf26406 100644
--- a/drivers/s390/net/qeth_l3_main.c
+++ b/drivers/s390/net/qeth_l3_main.c
@@ -2096,8 +2096,7 @@ static netdev_tx_t qeth_l3_hard_start_xmit(struct sk_buff *skb,
 
 tx_drop:
 	QETH_TXQ_STAT_INC(queue, tx_dropped);
-	QETH_TXQ_STAT_INC(queue, tx_errors);
-	dev_kfree_skb_any(skb);
+	kfree_skb(skb);
 	netif_wake_queue(dev);
 	return NETDEV_TX_OK;
 }
@@ -2253,14 +2252,15 @@ static int qeth_l3_probe_device(struct ccwgroup_device *gdev)
 	struct qeth_card *card = dev_get_drvdata(&gdev->dev);
 	int rc;
 
+	hash_init(card->ip_htable);
+
 	if (gdev->dev.type == &qeth_generic_devtype) {
 		rc = qeth_l3_create_device_attributes(&gdev->dev);
 		if (rc)
 			return rc;
 	}
-	hash_init(card->ip_htable);
+
 	hash_init(card->ip_mc_htable);
-	card->info.hwtrap = 0;
 	return 0;
 }
 
diff --git a/drivers/s390/scsi/zfcp_erp.c b/drivers/s390/scsi/zfcp_erp.c
index 744a64680d5b..e8fc28dba8df 100644
--- a/drivers/s390/scsi/zfcp_erp.c
+++ b/drivers/s390/scsi/zfcp_erp.c
@@ -624,6 +624,20 @@ static void zfcp_erp_strategy_memwait(struct zfcp_erp_action *erp_action)
 	add_timer(&erp_action->timer);
 }
 
+void zfcp_erp_port_forced_reopen_all(struct zfcp_adapter *adapter,
+				     int clear, char *dbftag)
+{
+	unsigned long flags;
+	struct zfcp_port *port;
+
+	write_lock_irqsave(&adapter->erp_lock, flags);
+	read_lock(&adapter->port_list_lock);
+	list_for_each_entry(port, &adapter->port_list, list)
+		_zfcp_erp_port_forced_reopen(port, clear, dbftag);
+	read_unlock(&adapter->port_list_lock);
+	write_unlock_irqrestore(&adapter->erp_lock, flags);
+}
+
 static void _zfcp_erp_port_reopen_all(struct zfcp_adapter *adapter,
 				      int clear, char *dbftag)
 {
@@ -1341,6 +1355,9 @@ static void zfcp_erp_try_rport_unblock(struct zfcp_port *port)
 		struct zfcp_scsi_dev *zsdev = sdev_to_zfcp(sdev);
 		int lun_status;
 
+		if (sdev->sdev_state == SDEV_DEL ||
+		    sdev->sdev_state == SDEV_CANCEL)
+			continue;
 		if (zsdev->port != port)
 			continue;
 		/* LUN under port of interest */
diff --git a/drivers/s390/scsi/zfcp_ext.h b/drivers/s390/scsi/zfcp_ext.h
index 3fce47b0b21b..c6acca521ffe 100644
--- a/drivers/s390/scsi/zfcp_ext.h
+++ b/drivers/s390/scsi/zfcp_ext.h
@@ -70,6 +70,8 @@ extern void zfcp_erp_port_reopen(struct zfcp_port *port, int clear,
 				 char *dbftag);
 extern void zfcp_erp_port_shutdown(struct zfcp_port *, int, char *);
 extern void zfcp_erp_port_forced_reopen(struct zfcp_port *, int, char *);
+extern void zfcp_erp_port_forced_reopen_all(struct zfcp_adapter *adapter,
+					    int clear, char *dbftag);
 extern void zfcp_erp_set_lun_status(struct scsi_device *, u32);
 extern void zfcp_erp_clear_lun_status(struct scsi_device *, u32);
 extern void zfcp_erp_lun_reopen(struct scsi_device *, int, char *);
diff --git a/drivers/s390/scsi/zfcp_fc.c b/drivers/s390/scsi/zfcp_fc.c
index db00b5e3abbe..33eddb02ee30 100644
--- a/drivers/s390/scsi/zfcp_fc.c
+++ b/drivers/s390/scsi/zfcp_fc.c
@@ -239,10 +239,6 @@ static void _zfcp_fc_incoming_rscn(struct zfcp_fsf_req *fsf_req, u32 range,
 	list_for_each_entry(port, &adapter->port_list, list) {
 		if ((port->d_id & range) == (ntoh24(page->rscn_fid) & range))
 			zfcp_fc_test_link(port);
-		if (!port->d_id)
-			zfcp_erp_port_reopen(port,
-					     ZFCP_STATUS_COMMON_ERP_FAILED,
-					     "fcrscn1");
 	}
 	read_unlock_irqrestore(&adapter->port_list_lock, flags);
 }
@@ -250,6 +246,7 @@ static void _zfcp_fc_incoming_rscn(struct zfcp_fsf_req *fsf_req, u32 range,
 static void zfcp_fc_incoming_rscn(struct zfcp_fsf_req *fsf_req)
 {
 	struct fsf_status_read_buffer *status_buffer = (void *)fsf_req->data;
+	struct zfcp_adapter *adapter = fsf_req->adapter;
 	struct fc_els_rscn *head;
 	struct fc_els_rscn_page *page;
 	u16 i;
@@ -263,6 +260,22 @@ static void zfcp_fc_incoming_rscn(struct zfcp_fsf_req *fsf_req)
 	no_entries = be16_to_cpu(head->rscn_plen) /
 		sizeof(struct fc_els_rscn_page);
 
+	if (no_entries > 1) {
+		/* handle failed ports */
+		unsigned long flags;
+		struct zfcp_port *port;
+
+		read_lock_irqsave(&adapter->port_list_lock, flags);
+		list_for_each_entry(port, &adapter->port_list, list) {
+			if (port->d_id)
+				continue;
+			zfcp_erp_port_reopen(port,
+					     ZFCP_STATUS_COMMON_ERP_FAILED,
+					     "fcrscn1");
+		}
+		read_unlock_irqrestore(&adapter->port_list_lock, flags);
+	}
+
 	for (i = 1; i < no_entries; i++) {
 		/* skip head and start with 1st element */
 		page++;
diff --git a/drivers/s390/scsi/zfcp_scsi.c b/drivers/s390/scsi/zfcp_scsi.c
index f4f6a07c5222..221d0dfb8493 100644
--- a/drivers/s390/scsi/zfcp_scsi.c
+++ b/drivers/s390/scsi/zfcp_scsi.c
@@ -368,6 +368,10 @@ static int zfcp_scsi_eh_host_reset_handler(struct scsi_cmnd *scpnt)
 	struct zfcp_adapter *adapter = zfcp_sdev->port->adapter;
 	int ret = SUCCESS, fc_ret;
 
+	if (!(adapter->connection_features & FSF_FEATURE_NPIV_MODE)) {
+		zfcp_erp_port_forced_reopen_all(adapter, 0, "schrh_p");
+		zfcp_erp_wait(adapter);
+	}
 	zfcp_erp_adapter_reopen(adapter, 0, "schrh_1");
 	zfcp_erp_wait(adapter);
 	fc_ret = fc_block_scsi_eh(scpnt);
diff --git a/drivers/s390/virtio/virtio_ccw.c b/drivers/s390/virtio/virtio_ccw.c
index 74c328321889..991420caa4f2 100644
--- a/drivers/s390/virtio/virtio_ccw.c
+++ b/drivers/s390/virtio/virtio_ccw.c
@@ -182,7 +182,7 @@ static void drop_airq_indicator(struct virtqueue *vq, struct airq_info *info)
 	write_unlock_irqrestore(&info->lock, flags);
 }
 
-static void virtio_airq_handler(struct airq_struct *airq)
+static void virtio_airq_handler(struct airq_struct *airq, bool floating)
 {
 	struct airq_info *info = container_of(airq, struct airq_info, airq);
 	unsigned long ai;
diff --git a/drivers/scsi/aacraid/aacraid.h b/drivers/scsi/aacraid/aacraid.h
index 1df5171594b8..11fb68d7e60d 100644
--- a/drivers/scsi/aacraid/aacraid.h
+++ b/drivers/scsi/aacraid/aacraid.h
@@ -2640,9 +2640,14 @@ static inline unsigned int cap_to_cyls(sector_t capacity, unsigned divisor)
 	return capacity;
 }
 
+static inline int aac_pci_offline(struct aac_dev *dev)
+{
+	return pci_channel_offline(dev->pdev) || dev->handle_pci_error;
+}
+
 static inline int aac_adapter_check_health(struct aac_dev *dev)
 {
-	if (unlikely(pci_channel_offline(dev->pdev)))
+	if (unlikely(aac_pci_offline(dev)))
 		return -1;
 
 	return (dev)->a_ops.adapter_check_health(dev);
diff --git a/drivers/scsi/aacraid/commsup.c b/drivers/scsi/aacraid/commsup.c
index e67e032936ef..78430a7b294c 100644
--- a/drivers/scsi/aacraid/commsup.c
+++ b/drivers/scsi/aacraid/commsup.c
@@ -672,7 +672,7 @@ int aac_fib_send(u16 command, struct fib *fibptr, unsigned long size,
 					return -ETIMEDOUT;
 				}
 
-				if (unlikely(pci_channel_offline(dev->pdev)))
+				if (unlikely(aac_pci_offline(dev)))
 					return -EFAULT;
 
 				if ((blink = aac_adapter_check_health(dev)) > 0) {
@@ -772,7 +772,7 @@ int aac_hba_send(u8 command, struct fib *fibptr, fib_callback callback,
 
 		spin_unlock_irqrestore(&fibptr->event_lock, flags);
 
-		if (unlikely(pci_channel_offline(dev->pdev)))
+		if (unlikely(aac_pci_offline(dev)))
 			return -EFAULT;
 
 		fibptr->flags |= FIB_CONTEXT_FLAG_WAIT;
diff --git a/drivers/scsi/aic7xxx/aic7770_osm.c b/drivers/scsi/aic7xxx/aic7770_osm.c
index 3d401d02c019..bdd177e3d762 100644
--- a/drivers/scsi/aic7xxx/aic7770_osm.c
+++ b/drivers/scsi/aic7xxx/aic7770_osm.c
@@ -91,6 +91,7 @@ aic7770_probe(struct device *dev)
 	ahc = ahc_alloc(&aic7xxx_driver_template, name);
 	if (ahc == NULL)
 		return (ENOMEM);
+	ahc->dev = dev;
 	error = aic7770_config(ahc, aic7770_ident_table + edev->id.driver_data,
 			       eisaBase);
 	if (error != 0) {
diff --git a/drivers/scsi/aic7xxx/aic7xxx.h b/drivers/scsi/aic7xxx/aic7xxx.h
index 5614921b4041..88b90f9806c9 100644
--- a/drivers/scsi/aic7xxx/aic7xxx.h
+++ b/drivers/scsi/aic7xxx/aic7xxx.h
@@ -943,6 +943,7 @@ struct ahc_softc {
 	 * Platform specific device information.
 	 */
 	ahc_dev_softc_t		  dev_softc;
+	struct device		  *dev;
 
 	/*
 	 * Bus specific device information.
diff --git a/drivers/scsi/aic7xxx/aic7xxx_osm.c b/drivers/scsi/aic7xxx/aic7xxx_osm.c
index 3c9c17450bb3..d5c4a0d23706 100644
--- a/drivers/scsi/aic7xxx/aic7xxx_osm.c
+++ b/drivers/scsi/aic7xxx/aic7xxx_osm.c
@@ -860,8 +860,8 @@ int
 ahc_dmamem_alloc(struct ahc_softc *ahc, bus_dma_tag_t dmat, void** vaddr,
 		 int flags, bus_dmamap_t *mapp)
 {
-	*vaddr = pci_alloc_consistent(ahc->dev_softc,
-				      dmat->maxsize, mapp);
+	/* XXX: check if we really need the GFP_ATOMIC and unwind this mess! */
+	*vaddr = dma_alloc_coherent(ahc->dev, dmat->maxsize, mapp, GFP_ATOMIC);
 	if (*vaddr == NULL)
 		return ENOMEM;
 	return 0;
@@ -871,8 +871,7 @@ void
 ahc_dmamem_free(struct ahc_softc *ahc, bus_dma_tag_t dmat,
 		void* vaddr, bus_dmamap_t map)
 {
-	pci_free_consistent(ahc->dev_softc, dmat->maxsize,
-			    vaddr, map);
+	dma_free_coherent(ahc->dev, dmat->maxsize, vaddr, map);
 }
 
 int
@@ -1123,8 +1122,7 @@ ahc_linux_register_host(struct ahc_softc *ahc, struct scsi_host_template *templa
 
 	host->transportt = ahc_linux_transport_template;
 
-	retval = scsi_add_host(host,
-			(ahc->dev_softc ? &ahc->dev_softc->dev : NULL));
+	retval = scsi_add_host(host, ahc->dev);
 	if (retval) {
 		printk(KERN_WARNING "aic7xxx: scsi_add_host failed\n");
 		scsi_host_put(host);
diff --git a/drivers/scsi/aic7xxx/aic7xxx_osm_pci.c b/drivers/scsi/aic7xxx/aic7xxx_osm_pci.c
index 0fc14dac7070..717d8d1082ce 100644
--- a/drivers/scsi/aic7xxx/aic7xxx_osm_pci.c
+++ b/drivers/scsi/aic7xxx/aic7xxx_osm_pci.c
@@ -250,6 +250,7 @@ ahc_linux_pci_dev_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 		}
 	}
 	ahc->dev_softc = pci;
+	ahc->dev = &pci->dev;
 	error = ahc_pci_config(ahc, entry);
 	if (error != 0) {
 		ahc_free(ahc);
diff --git a/drivers/scsi/bfa/bfa.h b/drivers/scsi/bfa/bfa.h
index 0e119d838e1b..762cb77253b9 100644
--- a/drivers/scsi/bfa/bfa.h
+++ b/drivers/scsi/bfa/bfa.h
@@ -62,8 +62,7 @@ void bfa_isr_unhandled(struct bfa_s *bfa, struct bfi_msg_s *m);
 			((__bfa)->iocfc.cfg.drvcfg.num_reqq_elems - 1); \
 		writel((__bfa)->iocfc.req_cq_pi[__reqq],		\
 			(__bfa)->iocfc.bfa_regs.cpe_q_pi[__reqq]);	\
-		mmiowb();      \
-	} while (0)
+		} while (0)
 
 #define bfa_rspq_pi(__bfa, __rspq)					\
 	(*(u32 *)((__bfa)->iocfc.rsp_cq_shadow_pi[__rspq].kva))
diff --git a/drivers/scsi/bfa/bfa_hw_cb.c b/drivers/scsi/bfa/bfa_hw_cb.c
index c4a0c0eb88a5..4a0d881b2602 100644
--- a/drivers/scsi/bfa/bfa_hw_cb.c
+++ b/drivers/scsi/bfa/bfa_hw_cb.c
@@ -61,7 +61,6 @@ bfa_hwcb_rspq_ack_msix(struct bfa_s *bfa, int rspq, u32 ci)
 
 	bfa_rspq_ci(bfa, rspq) = ci;
 	writel(ci, bfa->iocfc.bfa_regs.rme_q_ci[rspq]);
-	mmiowb();
 }
 
 void
@@ -72,7 +71,6 @@ bfa_hwcb_rspq_ack(struct bfa_s *bfa, int rspq, u32 ci)
 
 	bfa_rspq_ci(bfa, rspq) = ci;
 	writel(ci, bfa->iocfc.bfa_regs.rme_q_ci[rspq]);
-	mmiowb();
 }
 
 void
diff --git a/drivers/scsi/bfa/bfa_hw_ct.c b/drivers/scsi/bfa/bfa_hw_ct.c
index b0ff378dece2..b7be5f4f02a5 100644
--- a/drivers/scsi/bfa/bfa_hw_ct.c
+++ b/drivers/scsi/bfa/bfa_hw_ct.c
@@ -81,7 +81,6 @@ bfa_hwct_rspq_ack(struct bfa_s *bfa, int rspq, u32 ci)
 
 	bfa_rspq_ci(bfa, rspq) = ci;
 	writel(ci, bfa->iocfc.bfa_regs.rme_q_ci[rspq]);
-	mmiowb();
 }
 
 /*
@@ -94,7 +93,6 @@ bfa_hwct2_rspq_ack(struct bfa_s *bfa, int rspq, u32 ci)
 {
 	bfa_rspq_ci(bfa, rspq) = ci;
 	writel(ci, bfa->iocfc.bfa_regs.rme_q_ci[rspq]);
-	mmiowb();
 }
 
 void
diff --git a/drivers/scsi/bnx2fc/bnx2fc_hwi.c b/drivers/scsi/bnx2fc/bnx2fc_hwi.c
index 039328d9ef13..19734ec7f42e 100644
--- a/drivers/scsi/bnx2fc/bnx2fc_hwi.c
+++ b/drivers/scsi/bnx2fc/bnx2fc_hwi.c
@@ -991,7 +991,6 @@ void bnx2fc_arm_cq(struct bnx2fc_rport *tgt)
 			FCOE_CQE_TOGGLE_BIT_SHIFT);
 	msg = *((u32 *)rx_db);
 	writel(cpu_to_le32(msg), tgt->ctx_base);
-	mmiowb();
 
 }
 
@@ -1409,7 +1408,6 @@ void bnx2fc_ring_doorbell(struct bnx2fc_rport *tgt)
 				(tgt->sq_curr_toggle_bit << 15);
 	msg = *((u32 *)sq_db);
 	writel(cpu_to_le32(msg), tgt->ctx_base);
-	mmiowb();
 
 }
 
diff --git a/drivers/scsi/bnx2i/bnx2i_hwi.c b/drivers/scsi/bnx2i/bnx2i_hwi.c
index fae6f71e677d..12666313b937 100644
--- a/drivers/scsi/bnx2i/bnx2i_hwi.c
+++ b/drivers/scsi/bnx2i/bnx2i_hwi.c
@@ -253,7 +253,6 @@ void bnx2i_put_rq_buf(struct bnx2i_conn *bnx2i_conn, int count)
 		writew(ep->qp.rq_prod_idx,
 		       ep->qp.ctx_base + CNIC_RECV_DOORBELL);
 	}
-	mmiowb();
 }
 
 
@@ -279,8 +278,6 @@ static void bnx2i_ring_sq_dbell(struct bnx2i_conn *bnx2i_conn, int count)
 		bnx2i_ring_577xx_doorbell(bnx2i_conn);
 	} else
 		writew(count, ep->qp.ctx_base + CNIC_SEND_DOORBELL);
-
-	mmiowb(); /* flush posted PCI writes */
 }
 
 
diff --git a/drivers/scsi/csiostor/csio_scsi.c b/drivers/scsi/csiostor/csio_scsi.c
index 462560b2855e..469d0bc9f5fe 100644
--- a/drivers/scsi/csiostor/csio_scsi.c
+++ b/drivers/scsi/csiostor/csio_scsi.c
@@ -1713,8 +1713,11 @@ csio_scsi_err_handler(struct csio_hw *hw, struct csio_ioreq *req)
 	}
 
 out:
-	if (req->nsge > 0)
+	if (req->nsge > 0) {
 		scsi_dma_unmap(cmnd);
+		if (req->dcopy && (host_status == DID_OK))
+			host_status = csio_scsi_copy_to_sgl(hw, req);
+	}
 
 	cmnd->result = (((host_status) << 16) | scsi_status);
 	cmnd->scsi_done(cmnd);
diff --git a/drivers/scsi/ibmvscsi/ibmvfc.c b/drivers/scsi/ibmvscsi/ibmvfc.c
index dbaa4f131433..3ad997ac3510 100644
--- a/drivers/scsi/ibmvscsi/ibmvfc.c
+++ b/drivers/scsi/ibmvscsi/ibmvfc.c
@@ -139,6 +139,7 @@ static const struct {
 	{ IBMVFC_FC_FAILURE, IBMVFC_VENDOR_SPECIFIC, DID_ERROR, 1, 1, "vendor specific" },
 
 	{ IBMVFC_FC_SCSI_ERROR, 0, DID_OK, 1, 0, "SCSI error" },
+	{ IBMVFC_FC_SCSI_ERROR, IBMVFC_COMMAND_FAILED, DID_ERROR, 0, 1, "PRLI to device failed." },
 };
 
 static void ibmvfc_npiv_login(struct ibmvfc_host *);
@@ -1494,9 +1495,9 @@ static void ibmvfc_log_error(struct ibmvfc_event *evt)
 	if (rsp->flags & FCP_RSP_LEN_VALID)
 		rsp_code = rsp->data.info.rsp_code;
 
-	scmd_printk(KERN_ERR, cmnd, "Command (%02X) failed: %s (%x:%x) "
+	scmd_printk(KERN_ERR, cmnd, "Command (%02X) : %s (%x:%x) "
 		    "flags: %x fcp_rsp: %x, resid=%d, scsi_status: %x\n",
-		    cmnd->cmnd[0], err, vfc_cmd->status, vfc_cmd->error,
+		    cmnd->cmnd[0], err, be16_to_cpu(vfc_cmd->status), be16_to_cpu(vfc_cmd->error),
 		    rsp->flags, rsp_code, scsi_get_resid(cmnd), rsp->scsi_status);
 }
 
@@ -2022,7 +2023,7 @@ static int ibmvfc_reset_device(struct scsi_device *sdev, int type, char *desc)
 		sdev_printk(KERN_ERR, sdev, "%s reset failed: %s (%x:%x) "
 			    "flags: %x fcp_rsp: %x, scsi_status: %x\n", desc,
 			    ibmvfc_get_cmd_error(be16_to_cpu(rsp_iu.cmd.status), be16_to_cpu(rsp_iu.cmd.error)),
-			    rsp_iu.cmd.status, rsp_iu.cmd.error, fc_rsp->flags, rsp_code,
+			    be16_to_cpu(rsp_iu.cmd.status), be16_to_cpu(rsp_iu.cmd.error), fc_rsp->flags, rsp_code,
 			    fc_rsp->scsi_status);
 		rsp_rc = -EIO;
 	} else
@@ -2381,7 +2382,7 @@ static int ibmvfc_abort_task_set(struct scsi_device *sdev)
 		sdev_printk(KERN_ERR, sdev, "Abort failed: %s (%x:%x) "
 			    "flags: %x fcp_rsp: %x, scsi_status: %x\n",
 			    ibmvfc_get_cmd_error(be16_to_cpu(rsp_iu.cmd.status), be16_to_cpu(rsp_iu.cmd.error)),
-			    rsp_iu.cmd.status, rsp_iu.cmd.error, fc_rsp->flags, rsp_code,
+			    be16_to_cpu(rsp_iu.cmd.status), be16_to_cpu(rsp_iu.cmd.error), fc_rsp->flags, rsp_code,
 			    fc_rsp->scsi_status);
 		rsp_rc = -EIO;
 	} else
@@ -2755,16 +2756,18 @@ static void ibmvfc_handle_crq(struct ibmvfc_crq *crq, struct ibmvfc_host *vhost)
 		ibmvfc_set_host_action(vhost, IBMVFC_HOST_ACTION_NONE);
 		if (crq->format == IBMVFC_PARTITION_MIGRATED) {
 			/* We need to re-setup the interpartition connection */
-			dev_info(vhost->dev, "Re-enabling adapter\n");
+			dev_info(vhost->dev, "Partition migrated, Re-enabling adapter\n");
 			vhost->client_migrated = 1;
 			ibmvfc_purge_requests(vhost, DID_REQUEUE);
 			ibmvfc_link_down(vhost, IBMVFC_LINK_DOWN);
 			ibmvfc_set_host_action(vhost, IBMVFC_HOST_ACTION_REENABLE);
-		} else {
-			dev_err(vhost->dev, "Virtual adapter failed (rc=%d)\n", crq->format);
+		} else if (crq->format == IBMVFC_PARTNER_FAILED || crq->format == IBMVFC_PARTNER_DEREGISTER) {
+			dev_err(vhost->dev, "Host partner adapter deregistered or failed (rc=%d)\n", crq->format);
 			ibmvfc_purge_requests(vhost, DID_ERROR);
 			ibmvfc_link_down(vhost, IBMVFC_LINK_DOWN);
 			ibmvfc_set_host_action(vhost, IBMVFC_HOST_ACTION_RESET);
+		} else {
+			dev_err(vhost->dev, "Received unknown transport event from partner (rc=%d)\n", crq->format);
 		}
 		return;
 	case IBMVFC_CRQ_CMD_RSP:
@@ -3348,7 +3351,7 @@ static void ibmvfc_tgt_prli_done(struct ibmvfc_event *evt)
 
 		tgt_log(tgt, level, "Process Login failed: %s (%x:%x) rc=0x%02X\n",
 			ibmvfc_get_cmd_error(be16_to_cpu(rsp->status), be16_to_cpu(rsp->error)),
-			rsp->status, rsp->error, status);
+			be16_to_cpu(rsp->status), be16_to_cpu(rsp->error), status);
 		break;
 	}
 
@@ -3446,9 +3449,10 @@ static void ibmvfc_tgt_plogi_done(struct ibmvfc_event *evt)
 			ibmvfc_set_tgt_action(tgt, IBMVFC_TGT_ACTION_DEL_RPORT);
 
 		tgt_log(tgt, level, "Port Login failed: %s (%x:%x) %s (%x) %s (%x) rc=0x%02X\n",
-			ibmvfc_get_cmd_error(be16_to_cpu(rsp->status), be16_to_cpu(rsp->error)), rsp->status, rsp->error,
-			ibmvfc_get_fc_type(be16_to_cpu(rsp->fc_type)), rsp->fc_type,
-			ibmvfc_get_ls_explain(be16_to_cpu(rsp->fc_explain)), rsp->fc_explain, status);
+			ibmvfc_get_cmd_error(be16_to_cpu(rsp->status), be16_to_cpu(rsp->error)),
+					     be16_to_cpu(rsp->status), be16_to_cpu(rsp->error),
+			ibmvfc_get_fc_type(be16_to_cpu(rsp->fc_type)), be16_to_cpu(rsp->fc_type),
+			ibmvfc_get_ls_explain(be16_to_cpu(rsp->fc_explain)), be16_to_cpu(rsp->fc_explain), status);
 		break;
 	}
 
@@ -3619,7 +3623,7 @@ static void ibmvfc_tgt_adisc_done(struct ibmvfc_event *evt)
 		fc_explain = (be32_to_cpu(mad->fc_iu.response[1]) & 0x0000ff00) >> 8;
 		tgt_info(tgt, "ADISC failed: %s (%x:%x) %s (%x) %s (%x) rc=0x%02X\n",
 			 ibmvfc_get_cmd_error(be16_to_cpu(mad->iu.status), be16_to_cpu(mad->iu.error)),
-			 mad->iu.status, mad->iu.error,
+			 be16_to_cpu(mad->iu.status), be16_to_cpu(mad->iu.error),
 			 ibmvfc_get_fc_type(fc_reason), fc_reason,
 			 ibmvfc_get_ls_explain(fc_explain), fc_explain, status);
 		break;
@@ -3831,9 +3835,10 @@ static void ibmvfc_tgt_query_target_done(struct ibmvfc_event *evt)
 
 		tgt_log(tgt, level, "Query Target failed: %s (%x:%x) %s (%x) %s (%x) rc=0x%02X\n",
 			ibmvfc_get_cmd_error(be16_to_cpu(rsp->status), be16_to_cpu(rsp->error)),
-			rsp->status, rsp->error, ibmvfc_get_fc_type(be16_to_cpu(rsp->fc_type)),
-			rsp->fc_type, ibmvfc_get_gs_explain(be16_to_cpu(rsp->fc_explain)),
-			rsp->fc_explain, status);
+			be16_to_cpu(rsp->status), be16_to_cpu(rsp->error),
+			ibmvfc_get_fc_type(be16_to_cpu(rsp->fc_type)), be16_to_cpu(rsp->fc_type),
+			ibmvfc_get_gs_explain(be16_to_cpu(rsp->fc_explain)), be16_to_cpu(rsp->fc_explain),
+			status);
 		break;
 	}
 
@@ -3959,7 +3964,7 @@ static void ibmvfc_discover_targets_done(struct ibmvfc_event *evt)
 		level += ibmvfc_retry_host_init(vhost);
 		ibmvfc_log(vhost, level, "Discover Targets failed: %s (%x:%x)\n",
 			   ibmvfc_get_cmd_error(be16_to_cpu(rsp->status), be16_to_cpu(rsp->error)),
-			   rsp->status, rsp->error);
+			   be16_to_cpu(rsp->status), be16_to_cpu(rsp->error));
 		break;
 	case IBMVFC_MAD_DRIVER_FAILED:
 		break;
@@ -4024,7 +4029,7 @@ static void ibmvfc_npiv_login_done(struct ibmvfc_event *evt)
 			ibmvfc_link_down(vhost, IBMVFC_LINK_DEAD);
 		ibmvfc_log(vhost, level, "NPIV Login failed: %s (%x:%x)\n",
 			   ibmvfc_get_cmd_error(be16_to_cpu(rsp->status), be16_to_cpu(rsp->error)),
-						rsp->status, rsp->error);
+						be16_to_cpu(rsp->status), be16_to_cpu(rsp->error));
 		ibmvfc_free_event(evt);
 		return;
 	case IBMVFC_MAD_CRQ_ERROR:
diff --git a/drivers/scsi/ibmvscsi/ibmvfc.h b/drivers/scsi/ibmvscsi/ibmvfc.h
index b81a53c4a9a8..459cc288ba1d 100644
--- a/drivers/scsi/ibmvscsi/ibmvfc.h
+++ b/drivers/scsi/ibmvscsi/ibmvfc.h
@@ -78,9 +78,14 @@ enum ibmvfc_crq_valid {
 	IBMVFC_CRQ_XPORT_EVENT		= 0xFF,
 };
 
-enum ibmvfc_crq_format {
+enum ibmvfc_crq_init_msg {
 	IBMVFC_CRQ_INIT			= 0x01,
 	IBMVFC_CRQ_INIT_COMPLETE	= 0x02,
+};
+
+enum ibmvfc_crq_xport_evts {
+	IBMVFC_PARTNER_FAILED		= 0x01,
+	IBMVFC_PARTNER_DEREGISTER	= 0x02,
 	IBMVFC_PARTITION_MIGRATED	= 0x06,
 };
 
diff --git a/drivers/scsi/libfc/fc_rport.c b/drivers/scsi/libfc/fc_rport.c
index dfba4921b265..5bf61431434b 100644
--- a/drivers/scsi/libfc/fc_rport.c
+++ b/drivers/scsi/libfc/fc_rport.c
@@ -2162,7 +2162,6 @@ static void fc_rport_recv_logo_req(struct fc_lport *lport, struct fc_frame *fp)
 		FC_RPORT_DBG(rdata, "Received LOGO request while in state %s\n",
 			     fc_rport_state(rdata));
 
-		rdata->flags &= ~FC_RP_STARTED;
 		fc_rport_enter_delete(rdata, RPORT_EV_STOP);
 		mutex_unlock(&rdata->rp_mutex);
 		kref_put(&rdata->kref, fc_rport_destroy);
diff --git a/drivers/scsi/lpfc/lpfc_scsi.c b/drivers/scsi/lpfc/lpfc_scsi.c
index c98f264f1d83..a497b2c0cb79 100644
--- a/drivers/scsi/lpfc/lpfc_scsi.c
+++ b/drivers/scsi/lpfc/lpfc_scsi.c
@@ -3878,10 +3878,9 @@ lpfc_scsi_cmd_iocb_cmpl(struct lpfc_hba *phba, struct lpfc_iocbq *pIocbIn,
 	 * wake up the thread.
 	 */
 	spin_lock(&lpfc_cmd->buf_lock);
-	if (unlikely(lpfc_cmd->cur_iocbq.iocb_flag & LPFC_DRIVER_ABORTED)) {
-		lpfc_cmd->cur_iocbq.iocb_flag &= ~LPFC_DRIVER_ABORTED;
-		if (lpfc_cmd->waitq)
-			wake_up(lpfc_cmd->waitq);
+	lpfc_cmd->cur_iocbq.iocb_flag &= ~LPFC_DRIVER_ABORTED;
+	if (lpfc_cmd->waitq) {
+		wake_up(lpfc_cmd->waitq);
 		lpfc_cmd->waitq = NULL;
 	}
 	spin_unlock(&lpfc_cmd->buf_lock);
diff --git a/drivers/scsi/megaraid/megaraid_sas_base.c b/drivers/scsi/megaraid/megaraid_sas_base.c
index 293f5cf524d7..59a6546fd602 100644
--- a/drivers/scsi/megaraid/megaraid_sas_base.c
+++ b/drivers/scsi/megaraid/megaraid_sas_base.c
@@ -815,7 +815,6 @@ megasas_fire_cmd_skinny(struct megasas_instance *instance,
 	       &(regs)->inbound_high_queue_port);
 	writel((lower_32_bits(frame_phys_addr) | (frame_count<<1))|1,
 	       &(regs)->inbound_low_queue_port);
-	mmiowb();
 	spin_unlock_irqrestore(&instance->hba_lock, flags);
 }
 
diff --git a/drivers/scsi/megaraid/megaraid_sas_fusion.c b/drivers/scsi/megaraid/megaraid_sas_fusion.c
index 1d17128030cd..e35c2b64c145 100644
--- a/drivers/scsi/megaraid/megaraid_sas_fusion.c
+++ b/drivers/scsi/megaraid/megaraid_sas_fusion.c
@@ -242,7 +242,6 @@ megasas_fire_cmd_fusion(struct megasas_instance *instance,
 		&instance->reg_set->inbound_low_queue_port);
 	writel(le32_to_cpu(req_desc->u.high),
 		&instance->reg_set->inbound_high_queue_port);
-	mmiowb();
 	spin_unlock_irqrestore(&instance->hba_lock, flags);
 #endif
 }
diff --git a/drivers/scsi/mpt3sas/mpt3sas_base.c b/drivers/scsi/mpt3sas/mpt3sas_base.c
index e57774472e75..f60b9e0a6ca6 100644
--- a/drivers/scsi/mpt3sas/mpt3sas_base.c
+++ b/drivers/scsi/mpt3sas/mpt3sas_base.c
@@ -3281,12 +3281,18 @@ mpt3sas_base_free_smid(struct MPT3SAS_ADAPTER *ioc, u16 smid)
 
 	if (smid < ioc->hi_priority_smid) {
 		struct scsiio_tracker *st;
+		void *request;
 
 		st = _get_st_from_smid(ioc, smid);
 		if (!st) {
 			_base_recovery_check(ioc);
 			return;
 		}
+
+		/* Clear MPI request frame */
+		request = mpt3sas_base_get_msg_frame(ioc, smid);
+		memset(request, 0, ioc->request_sz);
+
 		mpt3sas_base_clear_st(ioc, st);
 		_base_recovery_check(ioc);
 		return;
@@ -3327,7 +3333,6 @@ _base_mpi_ep_writeq(__u64 b, volatile void __iomem *addr,
 	spin_lock_irqsave(writeq_lock, flags);
 	__raw_writel((u32)(b), addr);
 	__raw_writel((u32)(b >> 32), (addr + 4));
-	mmiowb();
 	spin_unlock_irqrestore(writeq_lock, flags);
 }
 
diff --git a/drivers/scsi/mpt3sas/mpt3sas_scsih.c b/drivers/scsi/mpt3sas/mpt3sas_scsih.c
index 8bb5b8f9f4d2..1ccfbc7eebe0 100644
--- a/drivers/scsi/mpt3sas/mpt3sas_scsih.c
+++ b/drivers/scsi/mpt3sas/mpt3sas_scsih.c
@@ -1462,11 +1462,23 @@ mpt3sas_scsih_scsi_lookup_get(struct MPT3SAS_ADAPTER *ioc, u16 smid)
 {
 	struct scsi_cmnd *scmd = NULL;
 	struct scsiio_tracker *st;
+	Mpi25SCSIIORequest_t *mpi_request;
 
 	if (smid > 0  &&
 	    smid <= ioc->scsiio_depth - INTERNAL_SCSIIO_CMDS_COUNT) {
 		u32 unique_tag = smid - 1;
 
+		mpi_request = mpt3sas_base_get_msg_frame(ioc, smid);
+
+		/*
+		 * If SCSI IO request is outstanding at driver level then
+		 * DevHandle filed must be non-zero. If DevHandle is zero
+		 * then it means that this smid is free at driver level,
+		 * so return NULL.
+		 */
+		if (!mpi_request->DevHandle)
+			return scmd;
+
 		scmd = scsi_host_find_tag(ioc->shost, unique_tag);
 		if (scmd) {
 			st = scsi_cmd_priv(scmd);
diff --git a/drivers/scsi/qedf/qedf_io.c b/drivers/scsi/qedf/qedf_io.c
index 6ca583bdde23..53e8221f6816 100644
--- a/drivers/scsi/qedf/qedf_io.c
+++ b/drivers/scsi/qedf/qedf_io.c
@@ -807,7 +807,6 @@ void qedf_ring_doorbell(struct qedf_rport *fcport)
 	writel(*(u32 *)&dbell, fcport->p_doorbell);
 	/* Make sure SQ index is updated so f/w prcesses requests in order */
 	wmb();
-	mmiowb();
 }
 
 static void qedf_trace_io(struct qedf_rport *fcport, struct qedf_ioreq *io_req,
diff --git a/drivers/scsi/qedi/qedi_fw.c b/drivers/scsi/qedi/qedi_fw.c
index e2a995a6e8e7..f8f86774f77f 100644
--- a/drivers/scsi/qedi/qedi_fw.c
+++ b/drivers/scsi/qedi/qedi_fw.c
@@ -985,7 +985,6 @@ static void qedi_ring_doorbell(struct qedi_conn *qedi_conn)
 	 * others they are two different assembly operations.
 	 */
 	wmb();
-	mmiowb();
 	QEDI_INFO(&qedi_conn->qedi->dbg_ctx, QEDI_LOG_MP_REQ,
 		  "prod_idx=0x%x, fw_prod_idx=0x%x, cid=0x%x\n",
 		  qedi_conn->ep->sq_prod_idx, qedi_conn->ep->fw_sq_prod_idx,
diff --git a/drivers/scsi/qedi/qedi_main.c b/drivers/scsi/qedi/qedi_main.c
index e74a62448ba4..e5db9a9954dc 100644
--- a/drivers/scsi/qedi/qedi_main.c
+++ b/drivers/scsi/qedi/qedi_main.c
@@ -1392,10 +1392,8 @@ static void qedi_free_nvm_iscsi_cfg(struct qedi_ctx *qedi)
 
 static int qedi_alloc_nvm_iscsi_cfg(struct qedi_ctx *qedi)
 {
-	struct qedi_nvm_iscsi_image nvm_image;
-
 	qedi->iscsi_image = dma_alloc_coherent(&qedi->pdev->dev,
-					       sizeof(nvm_image),
+					       sizeof(struct qedi_nvm_iscsi_image),
 					       &qedi->nvm_buf_dma, GFP_KERNEL);
 	if (!qedi->iscsi_image) {
 		QEDI_ERR(&qedi->dbg_ctx, "Could not allocate NVM BUF.\n");
@@ -2236,14 +2234,13 @@ static void qedi_boot_release(void *data)
 static int qedi_get_boot_info(struct qedi_ctx *qedi)
 {
 	int ret = 1;
-	struct qedi_nvm_iscsi_image nvm_image;
 
 	QEDI_INFO(&qedi->dbg_ctx, QEDI_LOG_INFO,
 		  "Get NVM iSCSI CFG image\n");
 	ret = qedi_ops->common->nvm_get_image(qedi->cdev,
 					      QED_NVM_IMAGE_ISCSI_CFG,
 					      (char *)qedi->iscsi_image,
-					      sizeof(nvm_image));
+					      sizeof(struct qedi_nvm_iscsi_image));
 	if (ret)
 		QEDI_ERR(&qedi->dbg_ctx,
 			 "Could not get NVM image. ret = %d\n", ret);
diff --git a/drivers/scsi/qla1280.c b/drivers/scsi/qla1280.c
index 6856dfdfa473..327eff67a1ee 100644
--- a/drivers/scsi/qla1280.c
+++ b/drivers/scsi/qla1280.c
@@ -3004,8 +3004,6 @@ qla1280_64bit_start_scsi(struct scsi_qla_host *ha, struct srb * sp)
 	sp->flags |= SRB_SENT;
 	ha->actthreads++;
 	WRT_REG_WORD(&reg->mailbox4, ha->req_ring_index);
-	/* Enforce mmio write ordering; see comment in qla1280_isp_cmd(). */
-	mmiowb();
 
  out:
 	if (status)
@@ -3254,8 +3252,6 @@ qla1280_32bit_start_scsi(struct scsi_qla_host *ha, struct srb * sp)
 	sp->flags |= SRB_SENT;
 	ha->actthreads++;
 	WRT_REG_WORD(&reg->mailbox4, ha->req_ring_index);
-	/* Enforce mmio write ordering; see comment in qla1280_isp_cmd(). */
-	mmiowb();
 
 out:
 	if (status)
@@ -3367,19 +3363,8 @@ qla1280_isp_cmd(struct scsi_qla_host *ha)
 
 	/*
 	 * Update request index to mailbox4 (Request Queue In).
-	 * The mmiowb() ensures that this write is ordered with writes by other
-	 * CPUs.  Without the mmiowb(), it is possible for the following:
-	 *    CPUA posts write of index 5 to mailbox4
-	 *    CPUA releases host lock
-	 *    CPUB acquires host lock
-	 *    CPUB posts write of index 6 to mailbox4
-	 *    On PCI bus, order reverses and write of 6 posts, then index 5,
-	 *       causing chip to issue full queue of stale commands
-	 * The mmiowb() prevents future writes from crossing the barrier.
-	 * See Documentation/driver-api/device-io.rst for more information.
 	 */
 	WRT_REG_WORD(&reg->mailbox4, ha->req_ring_index);
-	mmiowb();
 
 	LEAVE("qla1280_isp_cmd");
 }
diff --git a/drivers/scsi/qla4xxx/ql4_os.c b/drivers/scsi/qla4xxx/ql4_os.c
index 16a18d5d856f..6e4f4931ae17 100644
--- a/drivers/scsi/qla4xxx/ql4_os.c
+++ b/drivers/scsi/qla4xxx/ql4_os.c
@@ -3203,6 +3203,8 @@ static int qla4xxx_conn_bind(struct iscsi_cls_session *cls_session,
 	if (iscsi_conn_bind(cls_session, cls_conn, is_leading))
 		return -EINVAL;
 	ep = iscsi_lookup_endpoint(transport_fd);
+	if (!ep)
+		return -EINVAL;
 	conn = cls_conn->dd_data;
 	qla_conn = conn->dd_data;
 	qla_conn->qla_ep = ep->dd_data;
diff --git a/drivers/scsi/scsi_devinfo.c b/drivers/scsi/scsi_devinfo.c
index c4cbfd07b916..a08ff3bd6310 100644
--- a/drivers/scsi/scsi_devinfo.c
+++ b/drivers/scsi/scsi_devinfo.c
@@ -238,6 +238,7 @@ static struct {
 	{"NETAPP", "Universal Xport", "*", BLIST_NO_ULD_ATTACH},
 	{"LSI", "Universal Xport", "*", BLIST_NO_ULD_ATTACH},
 	{"ENGENIO", "Universal Xport", "*", BLIST_NO_ULD_ATTACH},
+	{"LENOVO", "Universal Xport", "*", BLIST_NO_ULD_ATTACH},
 	{"SMSC", "USB 2 HS-CF", NULL, BLIST_SPARSELUN | BLIST_INQUIRY_36},
 	{"SONY", "CD-ROM CDU-8001", NULL, BLIST_BORKEN},
 	{"SONY", "TSL", NULL, BLIST_FORCELUN},		/* DDS3 & DDS4 autoloaders */
diff --git a/drivers/scsi/scsi_dh.c b/drivers/scsi/scsi_dh.c
index 5a58cbf3a75d..c14006ac98f9 100644
--- a/drivers/scsi/scsi_dh.c
+++ b/drivers/scsi/scsi_dh.c
@@ -75,6 +75,7 @@ static const struct scsi_dh_blist scsi_dh_blist[] = {
 	{"NETAPP", "INF-01-00",		"rdac", },
 	{"LSI", "INF-01-00",		"rdac", },
 	{"ENGENIO", "INF-01-00",	"rdac", },
+	{"LENOVO", "DE_Series",		"rdac", },
 	{NULL, NULL,			NULL },
 };
 
diff --git a/drivers/scsi/scsi_lib.c b/drivers/scsi/scsi_lib.c
index 601b9f1de267..07dfc17d4824 100644
--- a/drivers/scsi/scsi_lib.c
+++ b/drivers/scsi/scsi_lib.c
@@ -1706,8 +1706,12 @@ out_put_budget:
 			ret = BLK_STS_DEV_RESOURCE;
 		break;
 	default:
+		if (unlikely(!scsi_device_online(sdev)))
+			scsi_req(req)->result = DID_NO_CONNECT << 16;
+		else
+			scsi_req(req)->result = DID_ERROR << 16;
 		/*
-		 * Make sure to release all allocated ressources when
+		 * Make sure to release all allocated resources when
 		 * we hit an error, as we will never see this command
 		 * again.
 		 */
diff --git a/drivers/scsi/scsi_sysfs.c b/drivers/scsi/scsi_sysfs.c
index 6a9040faed00..3b119ca0cc0c 100644
--- a/drivers/scsi/scsi_sysfs.c
+++ b/drivers/scsi/scsi_sysfs.c
@@ -771,6 +771,12 @@ store_state_field(struct device *dev, struct device_attribute *attr,
 
 	mutex_lock(&sdev->state_mutex);
 	ret = scsi_device_set_state(sdev, state);
+	/*
+	 * If the device state changes to SDEV_RUNNING, we need to run
+	 * the queue to avoid I/O hang.
+	 */
+	if (ret == 0 && state == SDEV_RUNNING)
+		blk_mq_run_hw_queues(sdev->request_queue, true);
 	mutex_unlock(&sdev->state_mutex);
 
 	return ret == 0 ? count : -EINVAL;
diff --git a/drivers/scsi/sd.c b/drivers/scsi/sd.c
index 251db30d0882..2b2bc4b49d78 100644
--- a/drivers/scsi/sd.c
+++ b/drivers/scsi/sd.c
@@ -1415,11 +1415,6 @@ static void sd_release(struct gendisk *disk, fmode_t mode)
 			scsi_set_medium_removal(sdev, SCSI_REMOVAL_ALLOW);
 	}
 
-	/*
-	 * XXX and what if there are packets in flight and this close()
-	 * XXX is followed by a "rmmod sd_mod"?
-	 */
-
 	scsi_disk_put(sdkp);
 }
 
@@ -3076,6 +3071,9 @@ static bool sd_validate_opt_xfer_size(struct scsi_disk *sdkp,
 	unsigned int opt_xfer_bytes =
 		logical_to_bytes(sdp, sdkp->opt_xfer_blocks);
 
+	if (sdkp->opt_xfer_blocks == 0)
+		return false;
+
 	if (sdkp->opt_xfer_blocks > dev_max) {
 		sd_first_printk(KERN_WARNING, sdkp,
 				"Optimal transfer size %u logical blocks " \
@@ -3505,9 +3503,21 @@ static void scsi_disk_release(struct device *dev)
 {
 	struct scsi_disk *sdkp = to_scsi_disk(dev);
 	struct gendisk *disk = sdkp->disk;
-	
+	struct request_queue *q = disk->queue;
+
 	ida_free(&sd_index_ida, sdkp->index);
 
+	/*
+	 * Wait until all requests that are in progress have completed.
+	 * This is necessary to avoid that e.g. scsi_end_request() crashes
+	 * due to clearing the disk->private_data pointer. Wait from inside
+	 * scsi_disk_release() instead of from sd_release() to avoid that
+	 * freezing and unfreezing the request queue affects user space I/O
+	 * in case multiple processes open a /dev/sd... node concurrently.
+	 */
+	blk_mq_freeze_queue(q);
+	blk_mq_unfreeze_queue(q);
+
 	disk->private_data = NULL;
 	put_disk(disk);
 	put_device(&sdkp->device->sdev_gendev);
diff --git a/drivers/scsi/storvsc_drv.c b/drivers/scsi/storvsc_drv.c
index 84380bae20f1..8472de1007ff 100644
--- a/drivers/scsi/storvsc_drv.c
+++ b/drivers/scsi/storvsc_drv.c
@@ -385,7 +385,7 @@ enum storvsc_request_type {
  * This is the end of Protocol specific defines.
  */
 
-static int storvsc_ringbuffer_size = (256 * PAGE_SIZE);
+static int storvsc_ringbuffer_size = (128 * 1024);
 static u32 max_outstanding_req_per_channel;
 
 static int storvsc_vcpus_per_sub_channel = 4;
@@ -668,13 +668,22 @@ static void  handle_multichannel_storage(struct hv_device *device, int max_chns)
 {
 	struct device *dev = &device->device;
 	struct storvsc_device *stor_device;
-	int num_cpus = num_online_cpus();
 	int num_sc;
 	struct storvsc_cmd_request *request;
 	struct vstor_packet *vstor_packet;
 	int ret, t;
 
-	num_sc = ((max_chns > num_cpus) ? num_cpus : max_chns);
+	/*
+	 * If the number of CPUs is artificially restricted, such as
+	 * with maxcpus=1 on the kernel boot line, Hyper-V could offer
+	 * sub-channels >= the number of CPUs. These sub-channels
+	 * should not be created. The primary channel is already created
+	 * and assigned to one CPU, so check against # CPUs - 1.
+	 */
+	num_sc = min((int)(num_online_cpus() - 1), max_chns);
+	if (!num_sc)
+		return;
+
 	stor_device = get_out_stor_device(device);
 	if (!stor_device)
 		return;
diff --git a/drivers/scsi/virtio_scsi.c b/drivers/scsi/virtio_scsi.c
index 8af01777d09c..f8cb7c23305b 100644
--- a/drivers/scsi/virtio_scsi.c
+++ b/drivers/scsi/virtio_scsi.c
@@ -793,6 +793,7 @@ static int virtscsi_probe(struct virtio_device *vdev)
 
 	/* We need to know how many queues before we allocate. */
 	num_queues = virtscsi_config_get(vdev, num_queues) ? : 1;
+	num_queues = min_t(unsigned int, nr_cpu_ids, num_queues);
 
 	num_targets = virtscsi_config_get(vdev, max_target) + 1;
 
diff --git a/drivers/soc/bcm/bcm2835-power.c b/drivers/soc/bcm/bcm2835-power.c
index 9351349cf0a9..1e0041ec8132 100644
--- a/drivers/soc/bcm/bcm2835-power.c
+++ b/drivers/soc/bcm/bcm2835-power.c
@@ -150,7 +150,12 @@ struct bcm2835_power {
 
 static int bcm2835_asb_enable(struct bcm2835_power *power, u32 reg)
 {
-	u64 start = ktime_get_ns();
+	u64 start;
+
+	if (!reg)
+		return 0;
+
+	start = ktime_get_ns();
 
 	/* Enable the module's async AXI bridges. */
 	ASB_WRITE(reg, ASB_READ(reg) & ~ASB_REQ_STOP);
@@ -165,7 +170,12 @@ static int bcm2835_asb_enable(struct bcm2835_power *power, u32 reg)
 
 static int bcm2835_asb_disable(struct bcm2835_power *power, u32 reg)
 {
-	u64 start = ktime_get_ns();
+	u64 start;
+
+	if (!reg)
+		return 0;
+
+	start = ktime_get_ns();
 
 	/* Enable the module's async AXI bridges. */
 	ASB_WRITE(reg, ASB_READ(reg) | ASB_REQ_STOP);
@@ -475,7 +485,7 @@ static int bcm2835_power_pd_power_off(struct generic_pm_domain *domain)
 	}
 }
 
-static void
+static int
 bcm2835_init_power_domain(struct bcm2835_power *power,
 			  int pd_xlate_index, const char *name)
 {
@@ -483,6 +493,17 @@ bcm2835_init_power_domain(struct bcm2835_power *power,
 	struct bcm2835_power_domain *dom = &power->domains[pd_xlate_index];
 
 	dom->clk = devm_clk_get(dev->parent, name);
+	if (IS_ERR(dom->clk)) {
+		int ret = PTR_ERR(dom->clk);
+
+		if (ret == -EPROBE_DEFER)
+			return ret;
+
+		/* Some domains don't have a clk, so make sure that we
+		 * don't deref an error pointer later.
+		 */
+		dom->clk = NULL;
+	}
 
 	dom->base.name = name;
 	dom->base.power_on = bcm2835_power_pd_power_on;
@@ -495,6 +516,8 @@ bcm2835_init_power_domain(struct bcm2835_power *power,
 	pm_genpd_init(&dom->base, NULL, true);
 
 	power->pd_xlate.domains[pd_xlate_index] = &dom->base;
+
+	return 0;
 }
 
 /** bcm2835_reset_reset - Resets a block that has a reset line in the
@@ -592,7 +615,7 @@ static int bcm2835_power_probe(struct platform_device *pdev)
 		{ BCM2835_POWER_DOMAIN_IMAGE_PERI, BCM2835_POWER_DOMAIN_CAM0 },
 		{ BCM2835_POWER_DOMAIN_IMAGE_PERI, BCM2835_POWER_DOMAIN_CAM1 },
 	};
-	int ret, i;
+	int ret = 0, i;
 	u32 id;
 
 	power = devm_kzalloc(dev, sizeof(*power), GFP_KERNEL);
@@ -619,8 +642,11 @@ static int bcm2835_power_probe(struct platform_device *pdev)
 
 	power->pd_xlate.num_domains = ARRAY_SIZE(power_domain_names);
 
-	for (i = 0; i < ARRAY_SIZE(power_domain_names); i++)
-		bcm2835_init_power_domain(power, i, power_domain_names[i]);
+	for (i = 0; i < ARRAY_SIZE(power_domain_names); i++) {
+		ret = bcm2835_init_power_domain(power, i, power_domain_names[i]);
+		if (ret)
+			goto fail;
+	}
 
 	for (i = 0; i < ARRAY_SIZE(domain_deps); i++) {
 		pm_genpd_add_subdomain(&power->domains[domain_deps[i].parent].base,
@@ -634,12 +660,21 @@ static int bcm2835_power_probe(struct platform_device *pdev)
 
 	ret = devm_reset_controller_register(dev, &power->reset);
 	if (ret)
-		return ret;
+		goto fail;
 
 	of_genpd_add_provider_onecell(dev->parent->of_node, &power->pd_xlate);
 
 	dev_info(dev, "Broadcom BCM2835 power domains driver");
 	return 0;
+
+fail:
+	for (i = 0; i < ARRAY_SIZE(power_domain_names); i++) {
+		struct generic_pm_domain *dom = &power->domains[i].base;
+
+		if (dom->name)
+			pm_genpd_remove(dom);
+	}
+	return ret;
 }
 
 static int bcm2835_power_remove(struct platform_device *pdev)
diff --git a/drivers/spi/Kconfig b/drivers/spi/Kconfig
index f761655e2a36..0fba8f400c59 100644
--- a/drivers/spi/Kconfig
+++ b/drivers/spi/Kconfig
@@ -426,6 +426,12 @@ config SPI_MT65XX
 	  say Y or M here.If you are not sure, say N.
 	  SPI drivers for Mediatek MT65XX and MT81XX series ARM SoCs.
 
+config SPI_MT7621
+	tristate "MediaTek MT7621 SPI Controller"
+	depends on RALINK || COMPILE_TEST
+	help
+	  This selects a driver for the MediaTek MT7621 SPI Controller.
+
 config SPI_NPCM_PSPI
 	tristate "Nuvoton NPCM PSPI Controller"
 	depends on ARCH_NPCM || COMPILE_TEST
@@ -842,9 +848,17 @@ config SPI_XTENSA_XTFPGA
 	  16 bit words in SPI mode 0, automatically asserting CS on transfer
 	  start and deasserting on end.
 
+config SPI_ZYNQ_QSPI
+	tristate "Xilinx Zynq QSPI controller"
+	depends on ARCH_ZYNQ || COMPILE_TEST
+	help
+	  This enables support for the Zynq Quad SPI controller
+	  in master mode.
+	  This controller only supports SPI memory interface.
+
 config SPI_ZYNQMP_GQSPI
 	tristate "Xilinx ZynqMP GQSPI controller"
-	depends on SPI_MASTER && HAS_DMA
+	depends on (SPI_MASTER && HAS_DMA) || COMPILE_TEST
 	help
 	  Enables Xilinx GQSPI controller driver for Zynq UltraScale+ MPSoC.
 
diff --git a/drivers/spi/Makefile b/drivers/spi/Makefile
index d8fc03c9faa2..f2f78d03dc28 100644
--- a/drivers/spi/Makefile
+++ b/drivers/spi/Makefile
@@ -60,6 +60,7 @@ obj-$(CONFIG_SPI_MPC512x_PSC)		+= spi-mpc512x-psc.o
 obj-$(CONFIG_SPI_MPC52xx_PSC)		+= spi-mpc52xx-psc.o
 obj-$(CONFIG_SPI_MPC52xx)		+= spi-mpc52xx.o
 obj-$(CONFIG_SPI_MT65XX)                += spi-mt65xx.o
+obj-$(CONFIG_SPI_MT7621)		+= spi-mt7621.o
 obj-$(CONFIG_SPI_MXIC)			+= spi-mxic.o
 obj-$(CONFIG_SPI_MXS)			+= spi-mxs.o
 obj-$(CONFIG_SPI_NPCM_PSPI)		+= spi-npcm-pspi.o
@@ -118,6 +119,7 @@ obj-$(CONFIG_SPI_XCOMM)		+= spi-xcomm.o
 obj-$(CONFIG_SPI_XILINX)		+= spi-xilinx.o
 obj-$(CONFIG_SPI_XLP)			+= spi-xlp.o
 obj-$(CONFIG_SPI_XTENSA_XTFPGA)		+= spi-xtensa-xtfpga.o
+obj-$(CONFIG_SPI_ZYNQ_QSPI)		+= spi-zynq-qspi.o
 obj-$(CONFIG_SPI_ZYNQMP_GQSPI)		+= spi-zynqmp-gqspi.o
 
 # SPI slave protocol handlers
diff --git a/drivers/spi/atmel-quadspi.c b/drivers/spi/atmel-quadspi.c
index fffc21cd5f79..9f24d5f0b431 100644
--- a/drivers/spi/atmel-quadspi.c
+++ b/drivers/spi/atmel-quadspi.c
@@ -366,7 +366,7 @@ static int atmel_qspi_exec_op(struct spi_mem *mem, const struct spi_mem_op *op)
 	return err;
 }
 
-const char *atmel_qspi_get_name(struct spi_mem *spimem)
+static const char *atmel_qspi_get_name(struct spi_mem *spimem)
 {
 	return dev_name(spimem->spi->dev.parent);
 }
@@ -570,7 +570,8 @@ static int atmel_qspi_remove(struct platform_device *pdev)
 
 static int __maybe_unused atmel_qspi_suspend(struct device *dev)
 {
-	struct atmel_qspi *aq = dev_get_drvdata(dev);
+	struct spi_controller *ctrl = dev_get_drvdata(dev);
+	struct atmel_qspi *aq = spi_controller_get_devdata(ctrl);
 
 	clk_disable_unprepare(aq->qspick);
 	clk_disable_unprepare(aq->pclk);
@@ -580,7 +581,8 @@ static int __maybe_unused atmel_qspi_suspend(struct device *dev)
 
 static int __maybe_unused atmel_qspi_resume(struct device *dev)
 {
-	struct atmel_qspi *aq = dev_get_drvdata(dev);
+	struct spi_controller *ctrl = dev_get_drvdata(dev);
+	struct atmel_qspi *aq = spi_controller_get_devdata(ctrl);
 
 	clk_prepare_enable(aq->pclk);
 	clk_prepare_enable(aq->qspick);
diff --git a/drivers/spi/spi-at91-usart.c b/drivers/spi/spi-at91-usart.c
index a694d702e574..f763e14bdf12 100644
--- a/drivers/spi/spi-at91-usart.c
+++ b/drivers/spi/spi-at91-usart.c
@@ -178,12 +178,6 @@ static int at91_usart_spi_setup(struct spi_device *spi)
 	struct at91_usart_spi *aus = spi_master_get_devdata(spi->controller);
 	u32 *ausd = spi->controller_state;
 	unsigned int mr = at91_usart_spi_readl(aus, MR);
-	u8 bits = spi->bits_per_word;
-
-	if (bits != 8) {
-		dev_dbg(&spi->dev, "Only 8 bits per word are supported\n");
-		return -EINVAL;
-	}
 
 	if (spi->mode & SPI_CPOL)
 		mr |= US_MR_CPOL;
@@ -212,7 +206,7 @@ static int at91_usart_spi_setup(struct spi_device *spi)
 
 	dev_dbg(&spi->dev,
 		"setup: bpw %u mode 0x%x -> mr %d %08x\n",
-		bits, spi->mode, spi->chip_select, mr);
+		spi->bits_per_word, spi->mode, spi->chip_select, mr);
 
 	return 0;
 }
diff --git a/drivers/spi/spi-bcm2835.c b/drivers/spi/spi-bcm2835.c
index 35aebdfd3b4e..8aa22713c483 100644
--- a/drivers/spi/spi-bcm2835.c
+++ b/drivers/spi/spi-bcm2835.c
@@ -335,20 +335,6 @@ static int bcm2835_spi_transfer_one_irq(struct spi_master *master,
 	return 1;
 }
 
-/*
- * DMA support
- *
- * this implementation has currently a few issues in so far as it does
- * not work arrount limitations of the HW.
- *
- * the main one being that DMA transfers are limited to 16 bit
- * (so 0 to 65535 bytes) by the SPI HW due to BCM2835_SPI_DLEN
- *
- * there may be a few more border-cases we may need to address as well
- * but unfortunately this would mean splitting up the scatter-gather
- * list making it slightly unpractical...
- */
-
 /**
  * bcm2835_spi_transfer_prologue() - transfer first few bytes without DMA
  * @master: SPI master
@@ -630,19 +616,6 @@ static bool bcm2835_spi_can_dma(struct spi_master *master,
 	if (tfr->len < BCM2835_SPI_DMA_MIN_LENGTH)
 		return false;
 
-	/* BCM2835_SPI_DLEN has defined a max transfer size as
-	 * 16 bit, so max is 65535
-	 * we can revisit this by using an alternative transfer
-	 * method - ideally this would get done without any more
-	 * interaction...
-	 */
-	if (tfr->len > 65535) {
-		dev_warn_once(&spi->dev,
-			      "transfer size of %d too big for dma-transfer\n",
-			      tfr->len);
-		return false;
-	}
-
 	/* return OK */
 	return true;
 }
@@ -707,7 +680,6 @@ static void bcm2835_dma_init(struct spi_master *master, struct device *dev)
 
 	/* all went well, so set can_dma */
 	master->can_dma = bcm2835_spi_can_dma;
-	master->max_dma_len = 65535; /* limitation by BCM2835_SPI_DLEN */
 	/* need to do TX AND RX DMA, so we need dummy buffers */
 	master->flags = SPI_MASTER_MUST_RX | SPI_MASTER_MUST_TX;
 
@@ -844,6 +816,17 @@ static int bcm2835_spi_prepare_message(struct spi_master *master,
 	struct spi_device *spi = msg->spi;
 	struct bcm2835_spi *bs = spi_master_get_devdata(master);
 	u32 cs = bcm2835_rd(bs, BCM2835_SPI_CS);
+	int ret;
+
+	/*
+	 * DMA transfers are limited to 16 bit (0 to 65535 bytes) by the SPI HW
+	 * due to DLEN. Split up transfers (32-bit FIFO aligned) if the limit is
+	 * exceeded.
+	 */
+	ret = spi_split_transfers_maxsize(master, msg, 65532,
+					  GFP_KERNEL | GFP_DMA);
+	if (ret)
+		return ret;
 
 	cs &= ~(BCM2835_SPI_CS_CPOL | BCM2835_SPI_CS_CPHA);
 
diff --git a/drivers/spi/spi-bcm2835aux.c b/drivers/spi/spi-bcm2835aux.c
index f7e054848ca5..bbf87adb3ff8 100644
--- a/drivers/spi/spi-bcm2835aux.c
+++ b/drivers/spi/spi-bcm2835aux.c
@@ -21,6 +21,7 @@
 
 #include <linux/clk.h>
 #include <linux/completion.h>
+#include <linux/debugfs.h>
 #include <linux/delay.h>
 #include <linux/err.h>
 #include <linux/interrupt.h>
@@ -36,6 +37,12 @@
 #include <linux/spi/spi.h>
 #include <linux/spinlock.h>
 
+/* define polling limits */
+static unsigned int polling_limit_us = 30;
+module_param(polling_limit_us, uint, 0664);
+MODULE_PARM_DESC(polling_limit_us,
+		 "time in us to run a transfer in polling mode - if zero no polling is used\n");
+
 /*
  * spi register defines
  *
@@ -88,10 +95,6 @@
 #define BCM2835_AUX_SPI_STAT_BUSY	0x00000040
 #define BCM2835_AUX_SPI_STAT_BITCOUNT	0x0000003F
 
-/* timeout values */
-#define BCM2835_AUX_SPI_POLLING_LIMIT_US	30
-#define BCM2835_AUX_SPI_POLLING_JIFFIES		2
-
 struct bcm2835aux_spi {
 	void __iomem *regs;
 	struct clk *clk;
@@ -102,8 +105,53 @@ struct bcm2835aux_spi {
 	int tx_len;
 	int rx_len;
 	int pending;
+
+	u64 count_transfer_polling;
+	u64 count_transfer_irq;
+	u64 count_transfer_irq_after_poll;
+
+	struct dentry *debugfs_dir;
 };
 
+#if defined(CONFIG_DEBUG_FS)
+static void bcm2835aux_debugfs_create(struct bcm2835aux_spi *bs,
+				      const char *dname)
+{
+	char name[64];
+	struct dentry *dir;
+
+	/* get full name */
+	snprintf(name, sizeof(name), "spi-bcm2835aux-%s", dname);
+
+	/* the base directory */
+	dir = debugfs_create_dir(name, NULL);
+	bs->debugfs_dir = dir;
+
+	/* the counters */
+	debugfs_create_u64("count_transfer_polling", 0444, dir,
+			   &bs->count_transfer_polling);
+	debugfs_create_u64("count_transfer_irq", 0444, dir,
+			   &bs->count_transfer_irq);
+	debugfs_create_u64("count_transfer_irq_after_poll", 0444, dir,
+			   &bs->count_transfer_irq_after_poll);
+}
+
+static void bcm2835aux_debugfs_remove(struct bcm2835aux_spi *bs)
+{
+	debugfs_remove_recursive(bs->debugfs_dir);
+	bs->debugfs_dir = NULL;
+}
+#else
+static void bcm2835aux_debugfs_create(struct bcm2835aux_spi *bs,
+				      const char *dname)
+{
+}
+
+static void bcm2835aux_debugfs_remove(struct bcm2835aux_spi *bs)
+{
+}
+#endif /* CONFIG_DEBUG_FS */
+
 static inline u32 bcm2835aux_rd(struct bcm2835aux_spi *bs, unsigned reg)
 {
 	return readl(bs->regs + reg);
@@ -123,9 +171,6 @@ static inline void bcm2835aux_rd_fifo(struct bcm2835aux_spi *bs)
 	data = bcm2835aux_rd(bs, BCM2835_AUX_SPI_IO);
 	if (bs->rx_buf) {
 		switch (count) {
-		case 4:
-			*bs->rx_buf++ = (data >> 24) & 0xff;
-			/* fallthrough */
 		case 3:
 			*bs->rx_buf++ = (data >> 16) & 0xff;
 			/* fallthrough */
@@ -178,24 +223,14 @@ static void bcm2835aux_spi_reset_hw(struct bcm2835aux_spi *bs)
 		      BCM2835_AUX_SPI_CNTL0_CLEARFIFO);
 }
 
-static irqreturn_t bcm2835aux_spi_interrupt(int irq, void *dev_id)
+static void bcm2835aux_spi_transfer_helper(struct bcm2835aux_spi *bs)
 {
-	struct spi_master *master = dev_id;
-	struct bcm2835aux_spi *bs = spi_master_get_devdata(master);
-	irqreturn_t ret = IRQ_NONE;
-
-	/* IRQ may be shared, so return if our interrupts are disabled */
-	if (!(bcm2835aux_rd(bs, BCM2835_AUX_SPI_CNTL1) &
-	      (BCM2835_AUX_SPI_CNTL1_TXEMPTY | BCM2835_AUX_SPI_CNTL1_IDLE)))
-		return ret;
+	u32 stat = bcm2835aux_rd(bs, BCM2835_AUX_SPI_STAT);
 
 	/* check if we have data to read */
-	while (bs->rx_len &&
-	       (!(bcm2835aux_rd(bs, BCM2835_AUX_SPI_STAT) &
-		  BCM2835_AUX_SPI_STAT_RX_EMPTY))) {
+	for (; bs->rx_len && (stat & BCM2835_AUX_SPI_STAT_RX_LVL);
+	     stat = bcm2835aux_rd(bs, BCM2835_AUX_SPI_STAT))
 		bcm2835aux_rd_fifo(bs);
-		ret = IRQ_HANDLED;
-	}
 
 	/* check if we have data to write */
 	while (bs->tx_len &&
@@ -203,16 +238,21 @@ static irqreturn_t bcm2835aux_spi_interrupt(int irq, void *dev_id)
 	       (!(bcm2835aux_rd(bs, BCM2835_AUX_SPI_STAT) &
 		  BCM2835_AUX_SPI_STAT_TX_FULL))) {
 		bcm2835aux_wr_fifo(bs);
-		ret = IRQ_HANDLED;
 	}
+}
 
-	/* and check if we have reached "done" */
-	while (bs->rx_len &&
-	       (!(bcm2835aux_rd(bs, BCM2835_AUX_SPI_STAT) &
-		  BCM2835_AUX_SPI_STAT_BUSY))) {
-		bcm2835aux_rd_fifo(bs);
-		ret = IRQ_HANDLED;
-	}
+static irqreturn_t bcm2835aux_spi_interrupt(int irq, void *dev_id)
+{
+	struct spi_master *master = dev_id;
+	struct bcm2835aux_spi *bs = spi_master_get_devdata(master);
+
+	/* IRQ may be shared, so return if our interrupts are disabled */
+	if (!(bcm2835aux_rd(bs, BCM2835_AUX_SPI_CNTL1) &
+	      (BCM2835_AUX_SPI_CNTL1_TXEMPTY | BCM2835_AUX_SPI_CNTL1_IDLE)))
+		return IRQ_NONE;
+
+	/* do common fifo handling */
+	bcm2835aux_spi_transfer_helper(bs);
 
 	if (!bs->tx_len) {
 		/* disable tx fifo empty interrupt */
@@ -226,8 +266,7 @@ static irqreturn_t bcm2835aux_spi_interrupt(int irq, void *dev_id)
 		complete(&master->xfer_completion);
 	}
 
-	/* and return */
-	return ret;
+	return IRQ_HANDLED;
 }
 
 static int __bcm2835aux_spi_transfer_one_irq(struct spi_master *master,
@@ -251,6 +290,9 @@ static int bcm2835aux_spi_transfer_one_irq(struct spi_master *master,
 {
 	struct bcm2835aux_spi *bs = spi_master_get_devdata(master);
 
+	/* update statistics */
+	bs->count_transfer_irq++;
+
 	/* fill in registers and fifos before enabling interrupts */
 	bcm2835aux_wr(bs, BCM2835_AUX_SPI_CNTL1, bs->cntl[1]);
 	bcm2835aux_wr(bs, BCM2835_AUX_SPI_CNTL0, bs->cntl[0]);
@@ -273,35 +315,22 @@ static int bcm2835aux_spi_transfer_one_poll(struct spi_master *master,
 {
 	struct bcm2835aux_spi *bs = spi_master_get_devdata(master);
 	unsigned long timeout;
-	u32 stat;
+
+	/* update statistics */
+	bs->count_transfer_polling++;
 
 	/* configure spi */
 	bcm2835aux_wr(bs, BCM2835_AUX_SPI_CNTL1, bs->cntl[1]);
 	bcm2835aux_wr(bs, BCM2835_AUX_SPI_CNTL0, bs->cntl[0]);
 
-	/* set the timeout */
-	timeout = jiffies + BCM2835_AUX_SPI_POLLING_JIFFIES;
+	/* set the timeout to at least 2 jiffies */
+	timeout = jiffies + 2 + HZ * polling_limit_us / 1000000;
 
 	/* loop until finished the transfer */
 	while (bs->rx_len) {
-		/* read status */
-		stat = bcm2835aux_rd(bs, BCM2835_AUX_SPI_STAT);
 
-		/* fill in tx fifo with remaining data */
-		if ((bs->tx_len) && (!(stat & BCM2835_AUX_SPI_STAT_TX_FULL))) {
-			bcm2835aux_wr_fifo(bs);
-			continue;
-		}
-
-		/* read data from fifo for both cases */
-		if (!(stat & BCM2835_AUX_SPI_STAT_RX_EMPTY)) {
-			bcm2835aux_rd_fifo(bs);
-			continue;
-		}
-		if (!(stat & BCM2835_AUX_SPI_STAT_BUSY)) {
-			bcm2835aux_rd_fifo(bs);
-			continue;
-		}
+		/* do common fifo handling */
+		bcm2835aux_spi_transfer_helper(bs);
 
 		/* there is still data pending to read check the timeout */
 		if (bs->rx_len && time_after(jiffies, timeout)) {
@@ -310,6 +339,7 @@ static int bcm2835aux_spi_transfer_one_poll(struct spi_master *master,
 					    jiffies - timeout,
 					    bs->tx_len, bs->rx_len);
 			/* forward to interrupt handler */
+			bs->count_transfer_irq_after_poll++;
 			return __bcm2835aux_spi_transfer_one_irq(master,
 							       spi, tfr);
 		}
@@ -324,8 +354,8 @@ static int bcm2835aux_spi_transfer_one(struct spi_master *master,
 				       struct spi_transfer *tfr)
 {
 	struct bcm2835aux_spi *bs = spi_master_get_devdata(master);
-	unsigned long spi_hz, clk_hz, speed;
-	unsigned long spi_used_hz;
+	unsigned long spi_hz, clk_hz, speed, spi_used_hz;
+	unsigned long hz_per_byte, byte_limit;
 
 	/* calculate the registers to handle
 	 *
@@ -369,14 +399,15 @@ static int bcm2835aux_spi_transfer_one(struct spi_master *master,
 	 * of Hz per byte per polling limit.  E.g., we can transfer 1 byte in
 	 * 30 µs per 300,000 Hz of bus clock.
 	 */
-#define HZ_PER_BYTE ((9 * 1000000) / BCM2835_AUX_SPI_POLLING_LIMIT_US)
+	hz_per_byte = polling_limit_us ? (9 * 1000000) / polling_limit_us : 0;
+	byte_limit = hz_per_byte ? spi_used_hz / hz_per_byte : 1;
+
 	/* run in polling mode for short transfers */
-	if (tfr->len < spi_used_hz / HZ_PER_BYTE)
+	if (tfr->len < byte_limit)
 		return bcm2835aux_spi_transfer_one_poll(master, spi, tfr);
 
 	/* run in interrupt mode for all others */
 	return bcm2835aux_spi_transfer_one_irq(master, spi, tfr);
-#undef HZ_PER_BYTE
 }
 
 static int bcm2835aux_spi_prepare_message(struct spi_master *master,
@@ -421,6 +452,50 @@ static void bcm2835aux_spi_handle_err(struct spi_master *master,
 	bcm2835aux_spi_reset_hw(bs);
 }
 
+static int bcm2835aux_spi_setup(struct spi_device *spi)
+{
+	int ret;
+
+	/* sanity check for native cs */
+	if (spi->mode & SPI_NO_CS)
+		return 0;
+	if (gpio_is_valid(spi->cs_gpio)) {
+		/* with gpio-cs set the GPIO to the correct level
+		 * and as output (in case the dt has the gpio not configured
+		 * as output but native cs)
+		 */
+		ret = gpio_direction_output(spi->cs_gpio,
+					    (spi->mode & SPI_CS_HIGH) ? 0 : 1);
+		if (ret)
+			dev_err(&spi->dev,
+				"could not set gpio %i as output: %i\n",
+				spi->cs_gpio, ret);
+
+		return ret;
+	}
+
+	/* for dt-backwards compatibility: only support native on CS0
+	 * known things not supported with broken native CS:
+	 * * multiple chip-selects: cs0-cs2 are all
+	 *     simultaniously asserted whenever there is a transfer
+	 *     this even includes SPI_NO_CS
+	 * * SPI_CS_HIGH: cs are always asserted low
+	 * * cs_change: cs is deasserted after each spi_transfer
+	 * * cs_delay_usec: cs is always deasserted one SCK cycle
+	 *     after the last transfer
+	 * probably more...
+	 */
+	dev_warn(&spi->dev,
+		 "Native CS is not supported - please configure cs-gpio in device-tree\n");
+
+	if (spi->chip_select == 0)
+		return 0;
+
+	dev_warn(&spi->dev, "Native CS is not working for cs > 0\n");
+
+	return -EINVAL;
+}
+
 static int bcm2835aux_spi_probe(struct platform_device *pdev)
 {
 	struct spi_master *master;
@@ -438,7 +513,19 @@ static int bcm2835aux_spi_probe(struct platform_device *pdev)
 	platform_set_drvdata(pdev, master);
 	master->mode_bits = (SPI_CPOL | SPI_CS_HIGH | SPI_NO_CS);
 	master->bits_per_word_mask = SPI_BPW_MASK(8);
-	master->num_chipselect = -1;
+	/* even though the driver never officially supported native CS
+	 * allow a single native CS for legacy DT support purposes when
+	 * no cs-gpio is configured.
+	 * Known limitations for native cs are:
+	 * * multiple chip-selects: cs0-cs2 are all simultaniously asserted
+	 *     whenever there is a transfer -  this even includes SPI_NO_CS
+	 * * SPI_CS_HIGH: is ignores - cs are always asserted low
+	 * * cs_change: cs is deasserted after each spi_transfer
+	 * * cs_delay_usec: cs is always deasserted one SCK cycle after
+	 *     a spi_transfer
+	 */
+	master->num_chipselect = 1;
+	master->setup = bcm2835aux_spi_setup;
 	master->transfer_one = bcm2835aux_spi_transfer_one;
 	master->handle_err = bcm2835aux_spi_handle_err;
 	master->prepare_message = bcm2835aux_spi_prepare_message;
@@ -502,6 +589,8 @@ static int bcm2835aux_spi_probe(struct platform_device *pdev)
 		goto out_clk_disable;
 	}
 
+	bcm2835aux_debugfs_create(bs, dev_name(&pdev->dev));
+
 	return 0;
 
 out_clk_disable:
@@ -516,6 +605,8 @@ static int bcm2835aux_spi_remove(struct platform_device *pdev)
 	struct spi_master *master = platform_get_drvdata(pdev);
 	struct bcm2835aux_spi *bs = spi_master_get_devdata(master);
 
+	bcm2835aux_debugfs_remove(bs);
+
 	bcm2835aux_spi_reset_hw(bs);
 
 	/* disable the HW block by releasing the clock */
diff --git a/drivers/spi/spi-bitbang.c b/drivers/spi/spi-bitbang.c
index dd9a8c54a693..4243e53f9f7b 100644
--- a/drivers/spi/spi-bitbang.c
+++ b/drivers/spi/spi-bitbang.c
@@ -335,6 +335,42 @@ static void spi_bitbang_set_cs(struct spi_device *spi, bool enable)
 
 /*----------------------------------------------------------------------*/
 
+int spi_bitbang_init(struct spi_bitbang *bitbang)
+{
+	struct spi_master *master = bitbang->master;
+
+	if (!master || !bitbang->chipselect)
+		return -EINVAL;
+
+	mutex_init(&bitbang->lock);
+
+	if (!master->mode_bits)
+		master->mode_bits = SPI_CPOL | SPI_CPHA | bitbang->flags;
+
+	if (master->transfer || master->transfer_one_message)
+		return -EINVAL;
+
+	master->prepare_transfer_hardware = spi_bitbang_prepare_hardware;
+	master->unprepare_transfer_hardware = spi_bitbang_unprepare_hardware;
+	master->transfer_one = spi_bitbang_transfer_one;
+	master->set_cs = spi_bitbang_set_cs;
+
+	if (!bitbang->txrx_bufs) {
+		bitbang->use_dma = 0;
+		bitbang->txrx_bufs = spi_bitbang_bufs;
+		if (!master->setup) {
+			if (!bitbang->setup_transfer)
+				bitbang->setup_transfer =
+					 spi_bitbang_setup_transfer;
+			master->setup = spi_bitbang_setup;
+			master->cleanup = spi_bitbang_cleanup;
+		}
+	}
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(spi_bitbang_init);
+
 /**
  * spi_bitbang_start - start up a polled/bitbanging SPI master driver
  * @bitbang: driver handle
@@ -368,33 +404,9 @@ int spi_bitbang_start(struct spi_bitbang *bitbang)
 	struct spi_master *master = bitbang->master;
 	int ret;
 
-	if (!master || !bitbang->chipselect)
-		return -EINVAL;
-
-	mutex_init(&bitbang->lock);
-
-	if (!master->mode_bits)
-		master->mode_bits = SPI_CPOL | SPI_CPHA | bitbang->flags;
-
-	if (master->transfer || master->transfer_one_message)
-		return -EINVAL;
-
-	master->prepare_transfer_hardware = spi_bitbang_prepare_hardware;
-	master->unprepare_transfer_hardware = spi_bitbang_unprepare_hardware;
-	master->transfer_one = spi_bitbang_transfer_one;
-	master->set_cs = spi_bitbang_set_cs;
-
-	if (!bitbang->txrx_bufs) {
-		bitbang->use_dma = 0;
-		bitbang->txrx_bufs = spi_bitbang_bufs;
-		if (!master->setup) {
-			if (!bitbang->setup_transfer)
-				bitbang->setup_transfer =
-					 spi_bitbang_setup_transfer;
-			master->setup = spi_bitbang_setup;
-			master->cleanup = spi_bitbang_cleanup;
-		}
-	}
+	ret = spi_bitbang_init(bitbang);
+	if (ret)
+		return ret;
 
 	/* driver may get busy before register() returns, especially
 	 * if someone registered boardinfo for devices
diff --git a/drivers/spi/spi-dw-mmio.c b/drivers/spi/spi-dw-mmio.c
index 4bd59a93d988..de952b17bc10 100644
--- a/drivers/spi/spi-dw-mmio.c
+++ b/drivers/spi/spi-dw-mmio.c
@@ -30,6 +30,7 @@
 struct dw_spi_mmio {
 	struct dw_spi  dws;
 	struct clk     *clk;
+	struct clk     *pclk;
 	void           *priv;
 };
 
@@ -172,6 +173,14 @@ static int dw_spi_mmio_probe(struct platform_device *pdev)
 	if (ret)
 		return ret;
 
+	/* Optional clock needed to access the registers */
+	dwsmmio->pclk = devm_clk_get_optional(&pdev->dev, "pclk");
+	if (IS_ERR(dwsmmio->pclk))
+		return PTR_ERR(dwsmmio->pclk);
+	ret = clk_prepare_enable(dwsmmio->pclk);
+	if (ret)
+		goto out_clk;
+
 	dws->bus_num = pdev->id;
 
 	dws->max_freq = clk_get_rate(dwsmmio->clk);
@@ -199,6 +208,8 @@ static int dw_spi_mmio_probe(struct platform_device *pdev)
 	return 0;
 
 out:
+	clk_disable_unprepare(dwsmmio->pclk);
+out_clk:
 	clk_disable_unprepare(dwsmmio->clk);
 	return ret;
 }
@@ -208,6 +219,7 @@ static int dw_spi_mmio_remove(struct platform_device *pdev)
 	struct dw_spi_mmio *dwsmmio = platform_get_drvdata(pdev);
 
 	dw_spi_remove_host(&dwsmmio->dws);
+	clk_disable_unprepare(dwsmmio->pclk);
 	clk_disable_unprepare(dwsmmio->clk);
 
 	return 0;
diff --git a/drivers/spi/spi-ep93xx.c b/drivers/spi/spi-ep93xx.c
index 79fc3940245a..81889389280b 100644
--- a/drivers/spi/spi-ep93xx.c
+++ b/drivers/spi/spi-ep93xx.c
@@ -28,7 +28,6 @@
 #include <linux/platform_device.h>
 #include <linux/sched.h>
 #include <linux/scatterlist.h>
-#include <linux/gpio.h>
 #include <linux/spi/spi.h>
 
 #include <linux/platform_data/dma-ep93xx.h>
@@ -652,7 +651,6 @@ static int ep93xx_spi_probe(struct platform_device *pdev)
 	struct resource *res;
 	int irq;
 	int error;
-	int i;
 
 	info = dev_get_platdata(&pdev->dev);
 	if (!info) {
@@ -676,6 +674,7 @@ static int ep93xx_spi_probe(struct platform_device *pdev)
 	if (!master)
 		return -ENOMEM;
 
+	master->use_gpio_descriptors = true;
 	master->prepare_transfer_hardware = ep93xx_spi_prepare_hardware;
 	master->unprepare_transfer_hardware = ep93xx_spi_unprepare_hardware;
 	master->prepare_message = ep93xx_spi_prepare_message;
@@ -683,31 +682,11 @@ static int ep93xx_spi_probe(struct platform_device *pdev)
 	master->bus_num = pdev->id;
 	master->mode_bits = SPI_CPOL | SPI_CPHA | SPI_CS_HIGH;
 	master->bits_per_word_mask = SPI_BPW_RANGE_MASK(4, 16);
-
-	master->num_chipselect = info->num_chipselect;
-	master->cs_gpios = devm_kcalloc(&master->dev,
-					master->num_chipselect, sizeof(int),
-					GFP_KERNEL);
-	if (!master->cs_gpios) {
-		error = -ENOMEM;
-		goto fail_release_master;
-	}
-
-	for (i = 0; i < master->num_chipselect; i++) {
-		master->cs_gpios[i] = info->chipselect[i];
-
-		if (!gpio_is_valid(master->cs_gpios[i]))
-			continue;
-
-		error = devm_gpio_request_one(&pdev->dev, master->cs_gpios[i],
-					      GPIOF_OUT_INIT_HIGH,
-					      "ep93xx-spi");
-		if (error) {
-			dev_err(&pdev->dev, "could not request cs gpio %d\n",
-				master->cs_gpios[i]);
-			goto fail_release_master;
-		}
-	}
+	/*
+	 * The SPI core will count the number of GPIO descriptors to figure
+	 * out the number of chip selects available on the platform.
+	 */
+	master->num_chipselect = 0;
 
 	platform_set_drvdata(pdev, master);
 
diff --git a/drivers/spi/spi-fsl-lib.h b/drivers/spi/spi-fsl-lib.h
index f303f306b38e..483734bc1b1e 100644
--- a/drivers/spi/spi-fsl-lib.h
+++ b/drivers/spi/spi-fsl-lib.h
@@ -95,8 +95,10 @@ static inline u32 mpc8xxx_spi_read_reg(__be32 __iomem *reg)
 
 struct mpc8xxx_spi_probe_info {
 	struct fsl_spi_platform_data pdata;
+	int ngpios;
 	int *gpios;
 	bool *alow_flags;
+	__be32 __iomem *immr_spi_cs;
 };
 
 extern u32 mpc8xxx_spi_tx_buf_u8(struct mpc8xxx_spi *mpc8xxx_spi);
diff --git a/drivers/spi/spi-fsl-lpspi.c b/drivers/spi/spi-fsl-lpspi.c
index 391863914043..d08e9324140e 100644
--- a/drivers/spi/spi-fsl-lpspi.c
+++ b/drivers/spi/spi-fsl-lpspi.c
@@ -8,7 +8,10 @@
 #include <linux/clk.h>
 #include <linux/completion.h>
 #include <linux/delay.h>
+#include <linux/dmaengine.h>
+#include <linux/dma-mapping.h>
 #include <linux/err.h>
+#include <linux/gpio.h>
 #include <linux/interrupt.h>
 #include <linux/io.h>
 #include <linux/irq.h>
@@ -16,7 +19,12 @@
 #include <linux/module.h>
 #include <linux/of.h>
 #include <linux/of_device.h>
+#include <linux/of_gpio.h>
+#include <linux/pinctrl/consumer.h>
 #include <linux/platform_device.h>
+#include <linux/platform_data/dma-imx.h>
+#include <linux/platform_data/spi-imx.h>
+#include <linux/pm_runtime.h>
 #include <linux/slab.h>
 #include <linux/spi/spi.h>
 #include <linux/spi/spi_bitbang.h>
@@ -24,6 +32,11 @@
 
 #define DRIVER_NAME "fsl_lpspi"
 
+#define FSL_LPSPI_RPM_TIMEOUT 50 /* 50ms */
+
+/* The maximum bytes that edma can transfer once.*/
+#define FSL_LPSPI_MAX_EDMA_BYTES  ((1 << 15) - 1)
+
 /* i.MX7ULP LPSPI registers */
 #define IMX7ULP_VERID	0x0
 #define IMX7ULP_PARAM	0x4
@@ -57,12 +70,14 @@
 #define IER_FCIE	BIT(9)
 #define IER_RDIE	BIT(1)
 #define IER_TDIE	BIT(0)
+#define DER_RDDE	BIT(1)
+#define DER_TDDE	BIT(0)
 #define CFGR1_PCSCFG	BIT(27)
 #define CFGR1_PINCFG	(BIT(24)|BIT(25))
 #define CFGR1_PCSPOL	BIT(8)
 #define CFGR1_NOSTALL	BIT(3)
 #define CFGR1_MASTER	BIT(0)
-#define FSR_RXCOUNT	(BIT(16)|BIT(17)|BIT(18))
+#define FSR_TXCOUNT	(0xFF)
 #define RSR_RXEMPTY	BIT(1)
 #define TCR_CPOL	BIT(31)
 #define TCR_CPHA	BIT(30)
@@ -84,8 +99,11 @@ struct lpspi_config {
 struct fsl_lpspi_data {
 	struct device *dev;
 	void __iomem *base;
-	struct clk *clk;
+	unsigned long base_phys;
+	struct clk *clk_ipg;
+	struct clk *clk_per;
 	bool is_slave;
+	bool is_first_byte;
 
 	void *rx_buf;
 	const void *tx_buf;
@@ -101,6 +119,13 @@ struct fsl_lpspi_data {
 	struct completion xfer_done;
 
 	bool slave_aborted;
+
+	/* DMA */
+	bool usedma;
+	struct completion dma_rx_completion;
+	struct completion dma_tx_completion;
+
+	int chipselect[0];
 };
 
 static const struct of_device_id fsl_lpspi_dt_ids[] = {
@@ -147,12 +172,48 @@ static void fsl_lpspi_intctrl(struct fsl_lpspi_data *fsl_lpspi,
 	writel(enable, fsl_lpspi->base + IMX7ULP_IER);
 }
 
+static int fsl_lpspi_bytes_per_word(const int bpw)
+{
+	return DIV_ROUND_UP(bpw, BITS_PER_BYTE);
+}
+
+static bool fsl_lpspi_can_dma(struct spi_controller *controller,
+			      struct spi_device *spi,
+			      struct spi_transfer *transfer)
+{
+	unsigned int bytes_per_word;
+
+	if (!controller->dma_rx)
+		return false;
+
+	bytes_per_word = fsl_lpspi_bytes_per_word(transfer->bits_per_word);
+
+	switch (bytes_per_word)
+	{
+		case 1:
+		case 2:
+		case 4:
+			break;
+		default:
+			return false;
+	}
+
+	return true;
+}
+
 static int lpspi_prepare_xfer_hardware(struct spi_controller *controller)
 {
 	struct fsl_lpspi_data *fsl_lpspi =
 				spi_controller_get_devdata(controller);
+	int ret;
+
+	ret = pm_runtime_get_sync(fsl_lpspi->dev);
+	if (ret < 0) {
+		dev_err(fsl_lpspi->dev, "failed to enable clock\n");
+		return ret;
+	}
 
-	return clk_prepare_enable(fsl_lpspi->clk);
+	return 0;
 }
 
 static int lpspi_unprepare_xfer_hardware(struct spi_controller *controller)
@@ -160,7 +221,22 @@ static int lpspi_unprepare_xfer_hardware(struct spi_controller *controller)
 	struct fsl_lpspi_data *fsl_lpspi =
 				spi_controller_get_devdata(controller);
 
-	clk_disable_unprepare(fsl_lpspi->clk);
+	pm_runtime_mark_last_busy(fsl_lpspi->dev);
+	pm_runtime_put_autosuspend(fsl_lpspi->dev);
+
+	return 0;
+}
+
+static int fsl_lpspi_prepare_message(struct spi_controller *controller,
+				     struct spi_message *msg)
+{
+	struct fsl_lpspi_data *fsl_lpspi =
+					spi_controller_get_devdata(controller);
+	struct spi_device *spi = msg->spi;
+	int gpio = fsl_lpspi->chipselect[spi->chip_select];
+
+	if (gpio_is_valid(gpio))
+		gpio_direction_output(gpio, spi->mode & SPI_CS_HIGH ? 0 : 1);
 
 	return 0;
 }
@@ -197,8 +273,7 @@ static void fsl_lpspi_read_rx_fifo(struct fsl_lpspi_data *fsl_lpspi)
 		fsl_lpspi->rx(fsl_lpspi);
 }
 
-static void fsl_lpspi_set_cmd(struct fsl_lpspi_data *fsl_lpspi,
-			      bool is_first_xfer)
+static void fsl_lpspi_set_cmd(struct fsl_lpspi_data *fsl_lpspi)
 {
 	u32 temp = 0;
 
@@ -213,11 +288,13 @@ static void fsl_lpspi_set_cmd(struct fsl_lpspi_data *fsl_lpspi,
 		 * For the first transfer, clear TCR_CONTC to assert SS.
 		 * For subsequent transfer, set TCR_CONTC to keep SS asserted.
 		 */
-		temp |= TCR_CONT;
-		if (is_first_xfer)
-			temp &= ~TCR_CONTC;
-		else
-			temp |= TCR_CONTC;
+		if (!fsl_lpspi->usedma) {
+			temp |= TCR_CONT;
+			if (fsl_lpspi->is_first_byte)
+				temp &= ~TCR_CONTC;
+			else
+				temp |= TCR_CONTC;
+		}
 	}
 	writel(temp, fsl_lpspi->base + IMX7ULP_TCR);
 
@@ -228,7 +305,11 @@ static void fsl_lpspi_set_watermark(struct fsl_lpspi_data *fsl_lpspi)
 {
 	u32 temp;
 
-	temp = fsl_lpspi->watermark >> 1 | (fsl_lpspi->watermark >> 1) << 16;
+	if (!fsl_lpspi->usedma)
+		temp = fsl_lpspi->watermark >> 1 |
+		       (fsl_lpspi->watermark >> 1) << 16;
+	else
+		temp = fsl_lpspi->watermark >> 1;
 
 	writel(temp, fsl_lpspi->base + IMX7ULP_FCR);
 
@@ -241,7 +322,14 @@ static int fsl_lpspi_set_bitrate(struct fsl_lpspi_data *fsl_lpspi)
 	unsigned int perclk_rate, scldiv;
 	u8 prescale;
 
-	perclk_rate = clk_get_rate(fsl_lpspi->clk);
+	perclk_rate = clk_get_rate(fsl_lpspi->clk_per);
+
+	if (config.speed_hz > perclk_rate / 2) {
+		dev_err(fsl_lpspi->dev,
+		      "per-clk should be at least two times of transfer speed");
+		return -EINVAL;
+	}
+
 	for (prescale = 0; prescale < 8; prescale++) {
 		scldiv = perclk_rate /
 			 (clkdivs[prescale] * config.speed_hz) - 2;
@@ -257,12 +345,59 @@ static int fsl_lpspi_set_bitrate(struct fsl_lpspi_data *fsl_lpspi)
 	writel(scldiv | (scldiv << 8) | ((scldiv >> 1) << 16),
 					fsl_lpspi->base + IMX7ULP_CCR);
 
-	dev_dbg(fsl_lpspi->dev, "perclk=%d, speed=%d, prescale =%d, scldiv=%d\n",
+	dev_dbg(fsl_lpspi->dev, "perclk=%d, speed=%d, prescale=%d, scldiv=%d\n",
 		perclk_rate, config.speed_hz, prescale, scldiv);
 
 	return 0;
 }
 
+static int fsl_lpspi_dma_configure(struct spi_controller *controller)
+{
+	int ret;
+	enum dma_slave_buswidth buswidth;
+	struct dma_slave_config rx = {}, tx = {};
+	struct fsl_lpspi_data *fsl_lpspi =
+				spi_controller_get_devdata(controller);
+
+	switch (fsl_lpspi_bytes_per_word(fsl_lpspi->config.bpw)) {
+	case 4:
+		buswidth = DMA_SLAVE_BUSWIDTH_4_BYTES;
+		break;
+	case 2:
+		buswidth = DMA_SLAVE_BUSWIDTH_2_BYTES;
+		break;
+	case 1:
+		buswidth = DMA_SLAVE_BUSWIDTH_1_BYTE;
+		break;
+	default:
+		return -EINVAL;
+	}
+
+	tx.direction = DMA_MEM_TO_DEV;
+	tx.dst_addr = fsl_lpspi->base_phys + IMX7ULP_TDR;
+	tx.dst_addr_width = buswidth;
+	tx.dst_maxburst = 1;
+	ret = dmaengine_slave_config(controller->dma_tx, &tx);
+	if (ret) {
+		dev_err(fsl_lpspi->dev, "TX dma configuration failed with %d\n",
+			ret);
+		return ret;
+	}
+
+	rx.direction = DMA_DEV_TO_MEM;
+	rx.src_addr = fsl_lpspi->base_phys + IMX7ULP_RDR;
+	rx.src_addr_width = buswidth;
+	rx.src_maxburst = 1;
+	ret = dmaengine_slave_config(controller->dma_rx, &rx);
+	if (ret) {
+		dev_err(fsl_lpspi->dev, "RX dma configuration failed with %d\n",
+			ret);
+		return ret;
+	}
+
+	return 0;
+}
+
 static int fsl_lpspi_config(struct fsl_lpspi_data *fsl_lpspi)
 {
 	u32 temp;
@@ -288,18 +423,27 @@ static int fsl_lpspi_config(struct fsl_lpspi_data *fsl_lpspi)
 	temp |= CR_RRF | CR_RTF | CR_MEN;
 	writel(temp, fsl_lpspi->base + IMX7ULP_CR);
 
+	temp = 0;
+	if (fsl_lpspi->usedma)
+		temp = DER_TDDE | DER_RDDE;
+	writel(temp, fsl_lpspi->base + IMX7ULP_DER);
+
 	return 0;
 }
 
-static void fsl_lpspi_setup_transfer(struct spi_device *spi,
+static int fsl_lpspi_setup_transfer(struct spi_controller *controller,
+				     struct spi_device *spi,
 				     struct spi_transfer *t)
 {
 	struct fsl_lpspi_data *fsl_lpspi =
 				spi_controller_get_devdata(spi->controller);
 
+	if (t == NULL)
+		return -EINVAL;
+
 	fsl_lpspi->config.mode = spi->mode;
-	fsl_lpspi->config.bpw = t ? t->bits_per_word : spi->bits_per_word;
-	fsl_lpspi->config.speed_hz = t ? t->speed_hz : spi->max_speed_hz;
+	fsl_lpspi->config.bpw = t->bits_per_word;
+	fsl_lpspi->config.speed_hz = t->speed_hz;
 	fsl_lpspi->config.chip_select = spi->chip_select;
 
 	if (!fsl_lpspi->config.speed_hz)
@@ -324,7 +468,12 @@ static void fsl_lpspi_setup_transfer(struct spi_device *spi,
 	else
 		fsl_lpspi->watermark = fsl_lpspi->txfifosize;
 
-	fsl_lpspi_config(fsl_lpspi);
+	if (fsl_lpspi_can_dma(controller, spi, t))
+		fsl_lpspi->usedma = 1;
+	else
+		fsl_lpspi->usedma = 0;
+
+	return fsl_lpspi_config(fsl_lpspi);
 }
 
 static int fsl_lpspi_slave_abort(struct spi_controller *controller)
@@ -333,7 +482,13 @@ static int fsl_lpspi_slave_abort(struct spi_controller *controller)
 				spi_controller_get_devdata(controller);
 
 	fsl_lpspi->slave_aborted = true;
-	complete(&fsl_lpspi->xfer_done);
+	if (!fsl_lpspi->usedma)
+		complete(&fsl_lpspi->xfer_done);
+	else {
+		complete(&fsl_lpspi->dma_tx_completion);
+		complete(&fsl_lpspi->dma_rx_completion);
+	}
+
 	return 0;
 }
 
@@ -362,8 +517,10 @@ static int fsl_lpspi_reset(struct fsl_lpspi_data *fsl_lpspi)
 {
 	u32 temp;
 
-	/* Disable all interrupt */
-	fsl_lpspi_intctrl(fsl_lpspi, 0);
+	if (!fsl_lpspi->usedma) {
+		/* Disable all interrupt */
+		fsl_lpspi_intctrl(fsl_lpspi, 0);
+	}
 
 	/* W1C for all flags in SR */
 	temp = 0x3F << 8;
@@ -376,8 +533,177 @@ static int fsl_lpspi_reset(struct fsl_lpspi_data *fsl_lpspi)
 	return 0;
 }
 
-static int fsl_lpspi_transfer_one(struct spi_controller *controller,
-				  struct spi_device *spi,
+static void fsl_lpspi_dma_rx_callback(void *cookie)
+{
+	struct fsl_lpspi_data *fsl_lpspi = (struct fsl_lpspi_data *)cookie;
+
+	complete(&fsl_lpspi->dma_rx_completion);
+}
+
+static void fsl_lpspi_dma_tx_callback(void *cookie)
+{
+	struct fsl_lpspi_data *fsl_lpspi = (struct fsl_lpspi_data *)cookie;
+
+	complete(&fsl_lpspi->dma_tx_completion);
+}
+
+static int fsl_lpspi_calculate_timeout(struct fsl_lpspi_data *fsl_lpspi,
+				       int size)
+{
+	unsigned long timeout = 0;
+
+	/* Time with actual data transfer and CS change delay related to HW */
+	timeout = (8 + 4) * size / fsl_lpspi->config.speed_hz;
+
+	/* Add extra second for scheduler related activities */
+	timeout += 1;
+
+	/* Double calculated timeout */
+	return msecs_to_jiffies(2 * timeout * MSEC_PER_SEC);
+}
+
+static int fsl_lpspi_dma_transfer(struct spi_controller *controller,
+				struct fsl_lpspi_data *fsl_lpspi,
+				struct spi_transfer *transfer)
+{
+	struct dma_async_tx_descriptor *desc_tx, *desc_rx;
+	unsigned long transfer_timeout;
+	unsigned long timeout;
+	struct sg_table *tx = &transfer->tx_sg, *rx = &transfer->rx_sg;
+	int ret;
+
+	ret = fsl_lpspi_dma_configure(controller);
+	if (ret)
+		return ret;
+
+	desc_rx = dmaengine_prep_slave_sg(controller->dma_rx,
+				rx->sgl, rx->nents, DMA_DEV_TO_MEM,
+				DMA_PREP_INTERRUPT | DMA_CTRL_ACK);
+	if (!desc_rx)
+		return -EINVAL;
+
+	desc_rx->callback = fsl_lpspi_dma_rx_callback;
+	desc_rx->callback_param = (void *)fsl_lpspi;
+	dmaengine_submit(desc_rx);
+	reinit_completion(&fsl_lpspi->dma_rx_completion);
+	dma_async_issue_pending(controller->dma_rx);
+
+	desc_tx = dmaengine_prep_slave_sg(controller->dma_tx,
+				tx->sgl, tx->nents, DMA_MEM_TO_DEV,
+				DMA_PREP_INTERRUPT | DMA_CTRL_ACK);
+	if (!desc_tx) {
+		dmaengine_terminate_all(controller->dma_tx);
+		return -EINVAL;
+	}
+
+	desc_tx->callback = fsl_lpspi_dma_tx_callback;
+	desc_tx->callback_param = (void *)fsl_lpspi;
+	dmaengine_submit(desc_tx);
+	reinit_completion(&fsl_lpspi->dma_tx_completion);
+	dma_async_issue_pending(controller->dma_tx);
+
+	fsl_lpspi->slave_aborted = false;
+
+	if (!fsl_lpspi->is_slave) {
+		transfer_timeout = fsl_lpspi_calculate_timeout(fsl_lpspi,
+							       transfer->len);
+
+		/* Wait eDMA to finish the data transfer.*/
+		timeout = wait_for_completion_timeout(&fsl_lpspi->dma_tx_completion,
+						      transfer_timeout);
+		if (!timeout) {
+			dev_err(fsl_lpspi->dev, "I/O Error in DMA TX\n");
+			dmaengine_terminate_all(controller->dma_tx);
+			dmaengine_terminate_all(controller->dma_rx);
+			fsl_lpspi_reset(fsl_lpspi);
+			return -ETIMEDOUT;
+		}
+
+		timeout = wait_for_completion_timeout(&fsl_lpspi->dma_rx_completion,
+						      transfer_timeout);
+		if (!timeout) {
+			dev_err(fsl_lpspi->dev, "I/O Error in DMA RX\n");
+			dmaengine_terminate_all(controller->dma_tx);
+			dmaengine_terminate_all(controller->dma_rx);
+			fsl_lpspi_reset(fsl_lpspi);
+			return -ETIMEDOUT;
+		}
+	} else {
+		if (wait_for_completion_interruptible(&fsl_lpspi->dma_tx_completion) ||
+			fsl_lpspi->slave_aborted) {
+			dev_dbg(fsl_lpspi->dev,
+				"I/O Error in DMA TX interrupted\n");
+			dmaengine_terminate_all(controller->dma_tx);
+			dmaengine_terminate_all(controller->dma_rx);
+			fsl_lpspi_reset(fsl_lpspi);
+			return -EINTR;
+		}
+
+		if (wait_for_completion_interruptible(&fsl_lpspi->dma_rx_completion) ||
+			fsl_lpspi->slave_aborted) {
+			dev_dbg(fsl_lpspi->dev,
+				"I/O Error in DMA RX interrupted\n");
+			dmaengine_terminate_all(controller->dma_tx);
+			dmaengine_terminate_all(controller->dma_rx);
+			fsl_lpspi_reset(fsl_lpspi);
+			return -EINTR;
+		}
+	}
+
+	fsl_lpspi_reset(fsl_lpspi);
+
+	return 0;
+}
+
+static void fsl_lpspi_dma_exit(struct spi_controller *controller)
+{
+	if (controller->dma_rx) {
+		dma_release_channel(controller->dma_rx);
+		controller->dma_rx = NULL;
+	}
+
+	if (controller->dma_tx) {
+		dma_release_channel(controller->dma_tx);
+		controller->dma_tx = NULL;
+	}
+}
+
+static int fsl_lpspi_dma_init(struct device *dev,
+			      struct fsl_lpspi_data *fsl_lpspi,
+			      struct spi_controller *controller)
+{
+	int ret;
+
+	/* Prepare for TX DMA: */
+	controller->dma_tx = dma_request_slave_channel_reason(dev, "tx");
+	if (IS_ERR(controller->dma_tx)) {
+		ret = PTR_ERR(controller->dma_tx);
+		dev_dbg(dev, "can't get the TX DMA channel, error %d!\n", ret);
+		controller->dma_tx = NULL;
+		goto err;
+	}
+
+	/* Prepare for RX DMA: */
+	controller->dma_rx = dma_request_slave_channel_reason(dev, "rx");
+	if (IS_ERR(controller->dma_rx)) {
+		ret = PTR_ERR(controller->dma_rx);
+		dev_dbg(dev, "can't get the RX DMA channel, error %d\n", ret);
+		controller->dma_rx = NULL;
+		goto err;
+	}
+
+	init_completion(&fsl_lpspi->dma_rx_completion);
+	init_completion(&fsl_lpspi->dma_tx_completion);
+	controller->can_dma = fsl_lpspi_can_dma;
+	controller->max_dma_len = FSL_LPSPI_MAX_EDMA_BYTES;
+
+	return 0;
+err:
+	fsl_lpspi_dma_exit(controller);
+	return ret;
+}
+
+static int fsl_lpspi_pio_transfer(struct spi_controller *controller,
 				  struct spi_transfer *t)
 {
 	struct fsl_lpspi_data *fsl_lpspi =
@@ -402,37 +728,30 @@ static int fsl_lpspi_transfer_one(struct spi_controller *controller,
 	return 0;
 }
 
-static int fsl_lpspi_transfer_one_msg(struct spi_controller *controller,
-				      struct spi_message *msg)
+static int fsl_lpspi_transfer_one(struct spi_controller *controller,
+				  struct spi_device *spi,
+				  struct spi_transfer *t)
 {
 	struct fsl_lpspi_data *fsl_lpspi =
-				spi_controller_get_devdata(controller);
-	struct spi_device *spi = msg->spi;
-	struct spi_transfer *xfer;
-	bool is_first_xfer = true;
-	int ret = 0;
-
-	msg->status = 0;
-	msg->actual_length = 0;
-
-	list_for_each_entry(xfer, &msg->transfers, transfer_list) {
-		fsl_lpspi_setup_transfer(spi, xfer);
-		fsl_lpspi_set_cmd(fsl_lpspi, is_first_xfer);
-
-		is_first_xfer = false;
+					spi_controller_get_devdata(controller);
+	int ret;
 
-		ret = fsl_lpspi_transfer_one(controller, spi, xfer);
-		if (ret < 0)
-			goto complete;
+	fsl_lpspi->is_first_byte = true;
+	ret = fsl_lpspi_setup_transfer(controller, spi, t);
+	if (ret < 0)
+		return ret;
 
-		msg->actual_length += xfer->len;
-	}
+	fsl_lpspi_set_cmd(fsl_lpspi);
+	fsl_lpspi->is_first_byte = false;
 
-complete:
-	msg->status = ret;
-	spi_finalize_current_message(controller);
+	if (fsl_lpspi->usedma)
+		ret = fsl_lpspi_dma_transfer(controller, fsl_lpspi, t);
+	else
+		ret = fsl_lpspi_pio_transfer(controller, t);
+	if (ret < 0)
+		return ret;
 
-	return ret;
+	return 0;
 }
 
 static irqreturn_t fsl_lpspi_isr(int irq, void *dev_id)
@@ -452,7 +771,7 @@ static irqreturn_t fsl_lpspi_isr(int irq, void *dev_id)
 	}
 
 	if (temp_SR & SR_MBF ||
-	    readl(fsl_lpspi->base + IMX7ULP_FSR) & FSR_RXCOUNT) {
+	    readl(fsl_lpspi->base + IMX7ULP_FSR) & FSR_TXCOUNT) {
 		writel(SR_FCF, fsl_lpspi->base + IMX7ULP_SR);
 		fsl_lpspi_intctrl(fsl_lpspi, IER_FCIE);
 		return IRQ_HANDLED;
@@ -467,15 +786,67 @@ static irqreturn_t fsl_lpspi_isr(int irq, void *dev_id)
 	return IRQ_NONE;
 }
 
+#ifdef CONFIG_PM
+static int fsl_lpspi_runtime_resume(struct device *dev)
+{
+	struct spi_controller *controller = dev_get_drvdata(dev);
+	struct fsl_lpspi_data *fsl_lpspi;
+	int ret;
+
+	fsl_lpspi = spi_controller_get_devdata(controller);
+
+	ret = clk_prepare_enable(fsl_lpspi->clk_per);
+	if (ret)
+		return ret;
+
+	ret = clk_prepare_enable(fsl_lpspi->clk_ipg);
+	if (ret) {
+		clk_disable_unprepare(fsl_lpspi->clk_per);
+		return ret;
+	}
+
+	return 0;
+}
+
+static int fsl_lpspi_runtime_suspend(struct device *dev)
+{
+	struct spi_controller *controller = dev_get_drvdata(dev);
+	struct fsl_lpspi_data *fsl_lpspi;
+
+	fsl_lpspi = spi_controller_get_devdata(controller);
+
+	clk_disable_unprepare(fsl_lpspi->clk_per);
+	clk_disable_unprepare(fsl_lpspi->clk_ipg);
+
+	return 0;
+}
+#endif
+
+static int fsl_lpspi_init_rpm(struct fsl_lpspi_data *fsl_lpspi)
+{
+	struct device *dev = fsl_lpspi->dev;
+
+	pm_runtime_enable(dev);
+	pm_runtime_set_autosuspend_delay(dev, FSL_LPSPI_RPM_TIMEOUT);
+	pm_runtime_use_autosuspend(dev);
+
+	return 0;
+}
+
 static int fsl_lpspi_probe(struct platform_device *pdev)
 {
+	struct device_node *np = pdev->dev.of_node;
 	struct fsl_lpspi_data *fsl_lpspi;
 	struct spi_controller *controller;
+	struct spi_imx_master *lpspi_platform_info =
+		dev_get_platdata(&pdev->dev);
 	struct resource *res;
-	int ret, irq;
+	int i, ret, irq;
 	u32 temp;
+	bool is_slave;
 
-	if (of_property_read_bool((&pdev->dev)->of_node, "spi-slave"))
+	is_slave = of_property_read_bool((&pdev->dev)->of_node, "spi-slave");
+	if (is_slave)
 		controller = spi_alloc_slave(&pdev->dev,
 					sizeof(struct fsl_lpspi_data));
 	else
@@ -487,15 +858,35 @@ static int fsl_lpspi_probe(struct platform_device *pdev)
 
 	platform_set_drvdata(pdev, controller);
 
-	controller->bits_per_word_mask = SPI_BPW_RANGE_MASK(8, 32);
-	controller->bus_num = pdev->id;
-
 	fsl_lpspi = spi_controller_get_devdata(controller);
 	fsl_lpspi->dev = &pdev->dev;
-	fsl_lpspi->is_slave = of_property_read_bool((&pdev->dev)->of_node,
-						    "spi-slave");
+	fsl_lpspi->is_slave = is_slave;
 
-	controller->transfer_one_message = fsl_lpspi_transfer_one_msg;
+	if (!fsl_lpspi->is_slave) {
+		for (i = 0; i < controller->num_chipselect; i++) {
+			int cs_gpio = of_get_named_gpio(np, "cs-gpios", i);
+
+			if (!gpio_is_valid(cs_gpio) && lpspi_platform_info)
+				cs_gpio = lpspi_platform_info->chipselect[i];
+
+			fsl_lpspi->chipselect[i] = cs_gpio;
+			if (!gpio_is_valid(cs_gpio))
+				continue;
+
+			ret = devm_gpio_request(&pdev->dev,
+						fsl_lpspi->chipselect[i],
+						DRIVER_NAME);
+			if (ret) {
+				dev_err(&pdev->dev, "can't get cs gpios\n");
+				goto out_controller_put;
+			}
+		}
+		controller->cs_gpios = fsl_lpspi->chipselect;
+		controller->prepare_message = fsl_lpspi_prepare_message;
+	}
+
+	controller->bits_per_word_mask = SPI_BPW_RANGE_MASK(8, 32);
+	controller->transfer_one = fsl_lpspi_transfer_one;
 	controller->prepare_transfer_hardware = lpspi_prepare_xfer_hardware;
 	controller->unprepare_transfer_hardware = lpspi_unprepare_xfer_hardware;
 	controller->mode_bits = SPI_CPOL | SPI_CPHA | SPI_CS_HIGH;
@@ -512,6 +903,7 @@ static int fsl_lpspi_probe(struct platform_device *pdev)
 		ret = PTR_ERR(fsl_lpspi->base);
 		goto out_controller_put;
 	}
+	fsl_lpspi->base_phys = res->start;
 
 	irq = platform_get_irq(pdev, 0);
 	if (irq < 0) {
@@ -526,23 +918,39 @@ static int fsl_lpspi_probe(struct platform_device *pdev)
 		goto out_controller_put;
 	}
 
-	fsl_lpspi->clk = devm_clk_get(&pdev->dev, "ipg");
-	if (IS_ERR(fsl_lpspi->clk)) {
-		ret = PTR_ERR(fsl_lpspi->clk);
+	fsl_lpspi->clk_per = devm_clk_get(&pdev->dev, "per");
+	if (IS_ERR(fsl_lpspi->clk_per)) {
+		ret = PTR_ERR(fsl_lpspi->clk_per);
 		goto out_controller_put;
 	}
 
-	ret = clk_prepare_enable(fsl_lpspi->clk);
-	if (ret) {
-		dev_err(&pdev->dev, "can't enable lpspi clock, ret=%d\n", ret);
+	fsl_lpspi->clk_ipg = devm_clk_get(&pdev->dev, "ipg");
+	if (IS_ERR(fsl_lpspi->clk_ipg)) {
+		ret = PTR_ERR(fsl_lpspi->clk_ipg);
+		goto out_controller_put;
+	}
+
+	/* enable the clock */
+	ret = fsl_lpspi_init_rpm(fsl_lpspi);
+	if (ret)
 		goto out_controller_put;
+
+	ret = pm_runtime_get_sync(fsl_lpspi->dev);
+	if (ret < 0) {
+		dev_err(fsl_lpspi->dev, "failed to enable clock\n");
+		return ret;
 	}
 
 	temp = readl(fsl_lpspi->base + IMX7ULP_PARAM);
 	fsl_lpspi->txfifosize = 1 << (temp & 0x0f);
 	fsl_lpspi->rxfifosize = 1 << ((temp >> 8) & 0x0f);
 
-	clk_disable_unprepare(fsl_lpspi->clk);
+	ret = fsl_lpspi_dma_init(&pdev->dev, fsl_lpspi, controller);
+	if (ret == -EPROBE_DEFER)
+		goto out_controller_put;
+
+	if (ret < 0)
+		dev_err(&pdev->dev, "dma setup error %d, use pio\n", ret);
 
 	ret = devm_spi_register_controller(&pdev->dev, controller);
 	if (ret < 0) {
@@ -564,15 +972,50 @@ static int fsl_lpspi_remove(struct platform_device *pdev)
 	struct fsl_lpspi_data *fsl_lpspi =
 				spi_controller_get_devdata(controller);
 
-	clk_disable_unprepare(fsl_lpspi->clk);
+	pm_runtime_disable(fsl_lpspi->dev);
+
+	spi_master_put(controller);
 
 	return 0;
 }
 
+#ifdef CONFIG_PM_SLEEP
+static int fsl_lpspi_suspend(struct device *dev)
+{
+	int ret;
+
+	pinctrl_pm_select_sleep_state(dev);
+	ret = pm_runtime_force_suspend(dev);
+	return ret;
+}
+
+static int fsl_lpspi_resume(struct device *dev)
+{
+	int ret;
+
+	ret = pm_runtime_force_resume(dev);
+	if (ret) {
+		dev_err(dev, "Error in resume: %d\n", ret);
+		return ret;
+	}
+
+	pinctrl_pm_select_default_state(dev);
+
+	return 0;
+}
+#endif /* CONFIG_PM_SLEEP */
+
+static const struct dev_pm_ops fsl_lpspi_pm_ops = {
+	SET_RUNTIME_PM_OPS(fsl_lpspi_runtime_suspend,
+				fsl_lpspi_runtime_resume, NULL)
+	SET_SYSTEM_SLEEP_PM_OPS(fsl_lpspi_suspend, fsl_lpspi_resume)
+};
+
 static struct platform_driver fsl_lpspi_driver = {
 	.driver = {
 		.name = DRIVER_NAME,
 		.of_match_table = fsl_lpspi_dt_ids,
+		.pm = &fsl_lpspi_pm_ops,
 	},
 	.probe = fsl_lpspi_probe,
 	.remove = fsl_lpspi_remove,
diff --git a/drivers/spi/spi-fsl-qspi.c b/drivers/spi/spi-fsl-qspi.c
index 6a713f78a62e..41a49b93ca60 100644
--- a/drivers/spi/spi-fsl-qspi.c
+++ b/drivers/spi/spi-fsl-qspi.c
@@ -882,7 +882,7 @@ static int fsl_qspi_probe(struct platform_device *pdev)
 
 	ctlr->dev.of_node = np;
 
-	ret = spi_register_controller(ctlr);
+	ret = devm_spi_register_controller(dev, ctlr);
 	if (ret)
 		goto err_destroy_mutex;
 
diff --git a/drivers/spi/spi-fsl-spi.c b/drivers/spi/spi-fsl-spi.c
index 8f2e97857e8b..b36ac6aa3b1f 100644
--- a/drivers/spi/spi-fsl-spi.c
+++ b/drivers/spi/spi-fsl-spi.c
@@ -39,6 +39,14 @@
 #include <linux/spi/spi_bitbang.h>
 #include <linux/types.h>
 
+#ifdef CONFIG_FSL_SOC
+#include <sysdev/fsl_soc.h>
+#endif
+
+/* Specific to the MPC8306/MPC8309 */
+#define IMMR_SPI_CS_OFFSET 0x14c
+#define SPI_BOOT_SEL_BIT   0x80000000
+
 #include "spi-fsl-lib.h"
 #include "spi-fsl-cpm.h"
 #include "spi-fsl-spi.h"
@@ -355,33 +363,50 @@ static int fsl_spi_bufs(struct spi_device *spi, struct spi_transfer *t,
 static int fsl_spi_do_one_msg(struct spi_master *master,
 			      struct spi_message *m)
 {
+	struct mpc8xxx_spi *mpc8xxx_spi = spi_master_get_devdata(master);
 	struct spi_device *spi = m->spi;
 	struct spi_transfer *t, *first;
 	unsigned int cs_change;
 	const int nsecs = 50;
-	int status;
+	int status, last_bpw;
+
+	/*
+	 * In CPU mode, optimize large byte transfers to use larger
+	 * bits_per_word values to reduce number of interrupts taken.
+	 */
+	if (!(mpc8xxx_spi->flags & SPI_CPM_MODE)) {
+		list_for_each_entry(t, &m->transfers, transfer_list) {
+			if (t->len < 256 || t->bits_per_word != 8)
+				continue;
+			if ((t->len & 3) == 0)
+				t->bits_per_word = 32;
+			else if ((t->len & 1) == 0)
+				t->bits_per_word = 16;
+		}
+	}
 
 	/* Don't allow changes if CS is active */
-	first = list_first_entry(&m->transfers, struct spi_transfer,
-			transfer_list);
+	cs_change = 1;
 	list_for_each_entry(t, &m->transfers, transfer_list) {
-		if ((first->bits_per_word != t->bits_per_word) ||
-			(first->speed_hz != t->speed_hz)) {
+		if (cs_change)
+			first = t;
+		cs_change = t->cs_change;
+		if (first->speed_hz != t->speed_hz) {
 			dev_err(&spi->dev,
-				"bits_per_word/speed_hz should be same for the same SPI transfer\n");
+				"speed_hz cannot change while CS is active\n");
 			return -EINVAL;
 		}
 	}
 
+	last_bpw = -1;
 	cs_change = 1;
 	status = -EINVAL;
 	list_for_each_entry(t, &m->transfers, transfer_list) {
-		if (t->bits_per_word || t->speed_hz) {
-			if (cs_change)
-				status = fsl_spi_setup_transfer(spi, t);
-			if (status < 0)
-				break;
-		}
+		if (cs_change || last_bpw != t->bits_per_word)
+			status = fsl_spi_setup_transfer(spi, t);
+		if (status < 0)
+			break;
+		last_bpw = t->bits_per_word;
 
 		if (cs_change) {
 			fsl_spi_chipselect(spi, BITBANG_CS_ACTIVE);
@@ -701,10 +726,17 @@ static void fsl_spi_cs_control(struct spi_device *spi, bool on)
 	struct fsl_spi_platform_data *pdata = dev_get_platdata(dev);
 	struct mpc8xxx_spi_probe_info *pinfo = to_of_pinfo(pdata);
 	u16 cs = spi->chip_select;
-	int gpio = pinfo->gpios[cs];
-	bool alow = pinfo->alow_flags[cs];
 
-	gpio_set_value(gpio, on ^ alow);
+	if (cs < pinfo->ngpios) {
+		int gpio = pinfo->gpios[cs];
+		bool alow = pinfo->alow_flags[cs];
+
+		gpio_set_value(gpio, on ^ alow);
+	} else {
+		if (WARN_ON_ONCE(cs > pinfo->ngpios || !pinfo->immr_spi_cs))
+			return;
+		iowrite32be(on ? SPI_BOOT_SEL_BIT : 0, pinfo->immr_spi_cs);
+	}
 }
 
 static int of_fsl_spi_get_chipselects(struct device *dev)
@@ -712,12 +744,15 @@ static int of_fsl_spi_get_chipselects(struct device *dev)
 	struct device_node *np = dev->of_node;
 	struct fsl_spi_platform_data *pdata = dev_get_platdata(dev);
 	struct mpc8xxx_spi_probe_info *pinfo = to_of_pinfo(pdata);
+	bool spisel_boot = IS_ENABLED(CONFIG_FSL_SOC) &&
+		of_property_read_bool(np, "fsl,spisel_boot");
 	int ngpios;
 	int i = 0;
 	int ret;
 
 	ngpios = of_gpio_count(np);
-	if (ngpios <= 0) {
+	ngpios = max(ngpios, 0);
+	if (ngpios == 0 && !spisel_boot) {
 		/*
 		 * SPI w/o chip-select line. One SPI device is still permitted
 		 * though.
@@ -726,6 +761,7 @@ static int of_fsl_spi_get_chipselects(struct device *dev)
 		return 0;
 	}
 
+	pinfo->ngpios = ngpios;
 	pinfo->gpios = kmalloc_array(ngpios, sizeof(*pinfo->gpios),
 				     GFP_KERNEL);
 	if (!pinfo->gpios)
@@ -769,7 +805,18 @@ static int of_fsl_spi_get_chipselects(struct device *dev)
 		}
 	}
 
-	pdata->max_chipselect = ngpios;
+#if IS_ENABLED(CONFIG_FSL_SOC)
+	if (spisel_boot) {
+		pinfo->immr_spi_cs = ioremap(get_immrbase() + IMMR_SPI_CS_OFFSET, 4);
+		if (!pinfo->immr_spi_cs) {
+			ret = -ENOMEM;
+			i = ngpios - 1;
+			goto err_loop;
+		}
+	}
+#endif
+
+	pdata->max_chipselect = ngpios + spisel_boot;
 	pdata->cs_control = fsl_spi_cs_control;
 
 	return 0;
diff --git a/drivers/spi/spi-gpio.c b/drivers/spi/spi-gpio.c
index 53b35c56a557..487ee55d26f7 100644
--- a/drivers/spi/spi-gpio.c
+++ b/drivers/spi/spi-gpio.c
@@ -35,20 +35,16 @@
  * platform_device->driver_data ... points to spi_gpio
  *
  * spi->controller_state ... reserved for bitbang framework code
- * spi->controller_data ... holds chipselect GPIO
  *
  * spi->master->dev.driver_data ... points to spi_gpio->bitbang
  */
 
 struct spi_gpio {
 	struct spi_bitbang		bitbang;
-	struct spi_gpio_platform_data	pdata;
-	struct platform_device		*pdev;
 	struct gpio_desc		*sck;
 	struct gpio_desc		*miso;
 	struct gpio_desc		*mosi;
 	struct gpio_desc		**cs_gpios;
-	bool				has_cs;
 };
 
 /*----------------------------------------------------------------------*/
@@ -96,12 +92,6 @@ spi_to_spi_gpio(const struct spi_device *spi)
 	return spi_gpio;
 }
 
-static inline struct spi_gpio_platform_data *__pure
-spi_to_pdata(const struct spi_device *spi)
-{
-	return &spi_to_spi_gpio(spi)->pdata;
-}
-
 /* These helpers are in turn called by the bitbang inlines */
 static inline void setsck(const struct spi_device *spi, int is_on)
 {
@@ -224,7 +214,7 @@ static void spi_gpio_chipselect(struct spi_device *spi, int is_active)
 		gpiod_set_value_cansleep(spi_gpio->sck, spi->mode & SPI_CPOL);
 
 	/* Drive chip select line, if we have one */
-	if (spi_gpio->has_cs) {
+	if (spi_gpio->cs_gpios) {
 		struct gpio_desc *cs = spi_gpio->cs_gpios[spi->chip_select];
 
 		/* SPI chip selects are normally active-low */
@@ -242,10 +232,12 @@ static int spi_gpio_setup(struct spi_device *spi)
 	 * The CS GPIOs have already been
 	 * initialized from the descriptor lookup.
 	 */
-	cs = spi_gpio->cs_gpios[spi->chip_select];
-	if (!spi->controller_state && cs)
-		status = gpiod_direction_output(cs,
-						!(spi->mode & SPI_CS_HIGH));
+	if (spi_gpio->cs_gpios) {
+		cs = spi_gpio->cs_gpios[spi->chip_select];
+		if (!spi->controller_state && cs)
+			status = gpiod_direction_output(cs,
+						  !(spi->mode & SPI_CS_HIGH));
+	}
 
 	if (!status)
 		status = spi_bitbang_setup(spi);
@@ -296,40 +288,20 @@ static void spi_gpio_cleanup(struct spi_device *spi)
  * floating signals.  (A weak pulldown would save power too, but many
  * drivers expect to see all-ones data as the no slave "response".)
  */
-static int spi_gpio_request(struct device *dev,
-			    struct spi_gpio *spi_gpio,
-			    unsigned int num_chipselects,
-			    u16 *mflags)
+static int spi_gpio_request(struct device *dev, struct spi_gpio *spi_gpio)
 {
-	int i;
-
 	spi_gpio->mosi = devm_gpiod_get_optional(dev, "mosi", GPIOD_OUT_LOW);
 	if (IS_ERR(spi_gpio->mosi))
 		return PTR_ERR(spi_gpio->mosi);
-	if (!spi_gpio->mosi)
-		/* HW configuration without MOSI pin */
-		*mflags |= SPI_MASTER_NO_TX;
 
 	spi_gpio->miso = devm_gpiod_get_optional(dev, "miso", GPIOD_IN);
 	if (IS_ERR(spi_gpio->miso))
 		return PTR_ERR(spi_gpio->miso);
-	/*
-	 * No setting SPI_MASTER_NO_RX here - if there is only a MOSI
-	 * pin connected the host can still do RX by changing the
-	 * direction of the line.
-	 */
 
 	spi_gpio->sck = devm_gpiod_get(dev, "sck", GPIOD_OUT_LOW);
 	if (IS_ERR(spi_gpio->sck))
 		return PTR_ERR(spi_gpio->sck);
 
-	for (i = 0; i < num_chipselects; i++) {
-		spi_gpio->cs_gpios[i] = devm_gpiod_get_index(dev, "cs",
-							     i, GPIOD_OUT_HIGH);
-		if (IS_ERR(spi_gpio->cs_gpios[i]))
-			return PTR_ERR(spi_gpio->cs_gpios[i]);
-	}
-
 	return 0;
 }
 
@@ -340,142 +312,134 @@ static const struct of_device_id spi_gpio_dt_ids[] = {
 };
 MODULE_DEVICE_TABLE(of, spi_gpio_dt_ids);
 
-static int spi_gpio_probe_dt(struct platform_device *pdev)
+static int spi_gpio_probe_dt(struct platform_device *pdev,
+			     struct spi_master *master)
 {
-	int ret;
-	u32 tmp;
-	struct spi_gpio_platform_data	*pdata;
-	struct device_node *np = pdev->dev.of_node;
-	const struct of_device_id *of_id =
-			of_match_device(spi_gpio_dt_ids, &pdev->dev);
-
-	if (!of_id)
-		return 0;
+	master->dev.of_node = pdev->dev.of_node;
+	master->use_gpio_descriptors = true;
 
-	pdata = devm_kzalloc(&pdev->dev, sizeof(*pdata), GFP_KERNEL);
-	if (!pdata)
-		return -ENOMEM;
+	return 0;
+}
+#else
+static inline int spi_gpio_probe_dt(struct platform_device *pdev,
+				    struct spi_master *master)
+{
+	return 0;
+}
+#endif
 
+static int spi_gpio_probe_pdata(struct platform_device *pdev,
+				struct spi_master *master)
+{
+	struct device *dev = &pdev->dev;
+	struct spi_gpio_platform_data *pdata = dev_get_platdata(dev);
+	struct spi_gpio *spi_gpio = spi_master_get_devdata(master);
+	int i;
 
-	ret = of_property_read_u32(np, "num-chipselects", &tmp);
-	if (ret < 0) {
-		dev_err(&pdev->dev, "num-chipselects property not found\n");
-		goto error_free;
-	}
+#ifdef GENERIC_BITBANG
+	if (!pdata || !pdata->num_chipselect)
+		return -ENODEV;
+#endif
+	/*
+	 * The master needs to think there is a chipselect even if not
+	 * connected
+	 */
+	master->num_chipselect = pdata->num_chipselect ?: 1;
 
-	pdata->num_chipselect = tmp;
-	pdev->dev.platform_data = pdata;
+	spi_gpio->cs_gpios = devm_kcalloc(dev, master->num_chipselect,
+					  sizeof(*spi_gpio->cs_gpios),
+					  GFP_KERNEL);
+	if (!spi_gpio->cs_gpios)
+		return -ENOMEM;
 
-	return 1;
+	for (i = 0; i < master->num_chipselect; i++) {
+		spi_gpio->cs_gpios[i] = devm_gpiod_get_index(dev, "cs", i,
+							     GPIOD_OUT_HIGH);
+		if (IS_ERR(spi_gpio->cs_gpios[i]))
+			return PTR_ERR(spi_gpio->cs_gpios[i]);
+	}
 
-error_free:
-	devm_kfree(&pdev->dev, pdata);
-	return ret;
+	return 0;
 }
-#else
-static inline int spi_gpio_probe_dt(struct platform_device *pdev)
+
+static void spi_gpio_put(void *data)
 {
-	return 0;
+	spi_master_put(data);
 }
-#endif
 
 static int spi_gpio_probe(struct platform_device *pdev)
 {
 	int				status;
 	struct spi_master		*master;
 	struct spi_gpio			*spi_gpio;
-	struct spi_gpio_platform_data	*pdata;
-	u16 master_flags = 0;
-	bool use_of = 0;
+	struct device			*dev = &pdev->dev;
+	struct spi_bitbang		*bb;
+	const struct of_device_id	*of_id;
 
-	status = spi_gpio_probe_dt(pdev);
-	if (status < 0)
-		return status;
-	if (status > 0)
-		use_of = 1;
-
-	pdata = dev_get_platdata(&pdev->dev);
-#ifdef GENERIC_BITBANG
-	if (!pdata || (!use_of && !pdata->num_chipselect))
-		return -ENODEV;
-#endif
+	of_id = of_match_device(spi_gpio_dt_ids, &pdev->dev);
 
-	master = spi_alloc_master(&pdev->dev, sizeof(*spi_gpio));
+	master = spi_alloc_master(dev, sizeof(*spi_gpio));
 	if (!master)
 		return -ENOMEM;
 
-	spi_gpio = spi_master_get_devdata(master);
-
-	spi_gpio->cs_gpios = devm_kcalloc(&pdev->dev,
-				pdata->num_chipselect,
-				sizeof(*spi_gpio->cs_gpios),
-				GFP_KERNEL);
-	if (!spi_gpio->cs_gpios)
-		return -ENOMEM;
+	status = devm_add_action_or_reset(&pdev->dev, spi_gpio_put, master);
+	if (status)
+		return status;
 
-	platform_set_drvdata(pdev, spi_gpio);
+	if (of_id)
+		status = spi_gpio_probe_dt(pdev, master);
+	else
+		status = spi_gpio_probe_pdata(pdev, master);
 
-	/* Determine if we have chip selects connected */
-	spi_gpio->has_cs = !!pdata->num_chipselect;
+	if (status)
+		return status;
 
-	spi_gpio->pdev = pdev;
-	if (pdata)
-		spi_gpio->pdata = *pdata;
+	spi_gpio = spi_master_get_devdata(master);
 
-	status = spi_gpio_request(&pdev->dev, spi_gpio,
-				  pdata->num_chipselect, &master_flags);
+	status = spi_gpio_request(dev, spi_gpio);
 	if (status)
 		return status;
 
 	master->bits_per_word_mask = SPI_BPW_RANGE_MASK(1, 32);
 	master->mode_bits = SPI_3WIRE | SPI_3WIRE_HIZ | SPI_CPHA | SPI_CPOL |
 			    SPI_CS_HIGH;
-	master->flags = master_flags;
+	if (!spi_gpio->mosi) {
+		/* HW configuration without MOSI pin
+		 *
+		 * No setting SPI_MASTER_NO_RX here - if there is only
+		 * a MOSI pin connected the host can still do RX by
+		 * changing the direction of the line.
+		 */
+		master->flags = SPI_MASTER_NO_TX;
+	}
+
 	master->bus_num = pdev->id;
-	/* The master needs to think there is a chipselect even if not connected */
-	master->num_chipselect = spi_gpio->has_cs ? pdata->num_chipselect : 1;
 	master->setup = spi_gpio_setup;
 	master->cleanup = spi_gpio_cleanup;
-#ifdef CONFIG_OF
-	master->dev.of_node = pdev->dev.of_node;
-#endif
 
-	spi_gpio->bitbang.master = master;
-	spi_gpio->bitbang.chipselect = spi_gpio_chipselect;
-	spi_gpio->bitbang.set_line_direction = spi_gpio_set_direction;
+	bb = &spi_gpio->bitbang;
+	bb->master = master;
+	bb->chipselect = spi_gpio_chipselect;
+	bb->set_line_direction = spi_gpio_set_direction;
 
-	if ((master_flags & SPI_MASTER_NO_TX) == 0) {
-		spi_gpio->bitbang.txrx_word[SPI_MODE_0] = spi_gpio_txrx_word_mode0;
-		spi_gpio->bitbang.txrx_word[SPI_MODE_1] = spi_gpio_txrx_word_mode1;
-		spi_gpio->bitbang.txrx_word[SPI_MODE_2] = spi_gpio_txrx_word_mode2;
-		spi_gpio->bitbang.txrx_word[SPI_MODE_3] = spi_gpio_txrx_word_mode3;
+	if (master->flags & SPI_MASTER_NO_TX) {
+		bb->txrx_word[SPI_MODE_0] = spi_gpio_spec_txrx_word_mode0;
+		bb->txrx_word[SPI_MODE_1] = spi_gpio_spec_txrx_word_mode1;
+		bb->txrx_word[SPI_MODE_2] = spi_gpio_spec_txrx_word_mode2;
+		bb->txrx_word[SPI_MODE_3] = spi_gpio_spec_txrx_word_mode3;
 	} else {
-		spi_gpio->bitbang.txrx_word[SPI_MODE_0] = spi_gpio_spec_txrx_word_mode0;
-		spi_gpio->bitbang.txrx_word[SPI_MODE_1] = spi_gpio_spec_txrx_word_mode1;
-		spi_gpio->bitbang.txrx_word[SPI_MODE_2] = spi_gpio_spec_txrx_word_mode2;
-		spi_gpio->bitbang.txrx_word[SPI_MODE_3] = spi_gpio_spec_txrx_word_mode3;
+		bb->txrx_word[SPI_MODE_0] = spi_gpio_txrx_word_mode0;
+		bb->txrx_word[SPI_MODE_1] = spi_gpio_txrx_word_mode1;
+		bb->txrx_word[SPI_MODE_2] = spi_gpio_txrx_word_mode2;
+		bb->txrx_word[SPI_MODE_3] = spi_gpio_txrx_word_mode3;
 	}
-	spi_gpio->bitbang.setup_transfer = spi_bitbang_setup_transfer;
+	bb->setup_transfer = spi_bitbang_setup_transfer;
 
-	status = spi_bitbang_start(&spi_gpio->bitbang);
+	status = spi_bitbang_init(&spi_gpio->bitbang);
 	if (status)
-		spi_master_put(master);
-
-	return status;
-}
-
-static int spi_gpio_remove(struct platform_device *pdev)
-{
-	struct spi_gpio			*spi_gpio;
-
-	spi_gpio = platform_get_drvdata(pdev);
-
-	/* stop() unregisters child devices too */
-	spi_bitbang_stop(&spi_gpio->bitbang);
-
-	spi_master_put(spi_gpio->bitbang.master);
+		return status;
 
-	return 0;
+	return devm_spi_register_master(&pdev->dev, spi_master_get(master));
 }
 
 MODULE_ALIAS("platform:" DRIVER_NAME);
@@ -486,7 +450,6 @@ static struct platform_driver spi_gpio_driver = {
 		.of_match_table = of_match_ptr(spi_gpio_dt_ids),
 	},
 	.probe		= spi_gpio_probe,
-	.remove		= spi_gpio_remove,
 };
 module_platform_driver(spi_gpio_driver);
 
diff --git a/drivers/spi/spi-imx.c b/drivers/spi/spi-imx.c
index 6ec647bbba77..09c9a1edb2c6 100644
--- a/drivers/spi/spi-imx.c
+++ b/drivers/spi/spi-imx.c
@@ -28,6 +28,10 @@
 
 #define DRIVER_NAME "spi_imx"
 
+static bool use_dma = true;
+module_param(use_dma, bool, 0644);
+MODULE_PARM_DESC(use_dma, "Enable usage of DMA when available (default)");
+
 #define MXC_CSPIRXDATA		0x00
 #define MXC_CSPITXDATA		0x04
 #define MXC_CSPICTRL		0x08
@@ -219,6 +223,9 @@ static bool spi_imx_can_dma(struct spi_master *master, struct spi_device *spi,
 {
 	struct spi_imx_data *spi_imx = spi_master_get_devdata(master);
 
+	if (!use_dma)
+		return false;
+
 	if (!master->dma_rx)
 		return false;
 
@@ -1494,7 +1501,7 @@ static int spi_imx_transfer(struct spi_device *spi,
 
 	/* flush rxfifo before transfer */
 	while (spi_imx->devtype_data->rx_available(spi_imx))
-		spi_imx->rx(spi_imx);
+		readl(spi_imx->base + MXC_CSPIRXDATA);
 
 	if (spi_imx->slave_mode)
 		return spi_imx_pio_transfer_slave(spi, transfer);
diff --git a/drivers/spi/spi-mem.c b/drivers/spi/spi-mem.c
index a4d8d19ecff9..9f0fa9f3116d 100644
--- a/drivers/spi/spi-mem.c
+++ b/drivers/spi/spi-mem.c
@@ -135,8 +135,8 @@ static int spi_check_buswidth_req(struct spi_mem *mem, u8 buswidth, bool tx)
 	return -ENOTSUPP;
 }
 
-static bool spi_mem_default_supports_op(struct spi_mem *mem,
-					const struct spi_mem_op *op)
+bool spi_mem_default_supports_op(struct spi_mem *mem,
+				 const struct spi_mem_op *op)
 {
 	if (spi_check_buswidth_req(mem, op->cmd.buswidth, true))
 		return false;
@@ -622,7 +622,7 @@ void devm_spi_mem_dirmap_destroy(struct device *dev,
 EXPORT_SYMBOL_GPL(devm_spi_mem_dirmap_destroy);
 
 /**
- * spi_mem_dirmap_dirmap_read() - Read data through a direct mapping
+ * spi_mem_dirmap_read() - Read data through a direct mapping
  * @desc: direct mapping descriptor
  * @offs: offset to start reading from. Note that this is not an absolute
  *	  offset, but the offset within the direct mapping which already has
@@ -668,7 +668,7 @@ ssize_t spi_mem_dirmap_read(struct spi_mem_dirmap_desc *desc,
 EXPORT_SYMBOL_GPL(spi_mem_dirmap_read);
 
 /**
- * spi_mem_dirmap_dirmap_write() - Write data through a direct mapping
+ * spi_mem_dirmap_write() - Write data through a direct mapping
  * @desc: direct mapping descriptor
  * @offs: offset to start writing from. Note that this is not an absolute
  *	  offset, but the offset within the direct mapping which already has
diff --git a/drivers/staging/mt7621-spi/spi-mt7621.c b/drivers/spi/spi-mt7621.c
index b509f9fe3346..ae836114ee3d 100644
--- a/drivers/staging/mt7621-spi/spi-mt7621.c
+++ b/drivers/spi/spi-mt7621.c
@@ -1,15 +1,14 @@
 // SPDX-License-Identifier: GPL-2.0
-/*
- * spi-mt7621.c -- MediaTek MT7621 SPI controller driver
- *
- * Copyright (C) 2011 Sergiy <piratfm@gmail.com>
- * Copyright (C) 2011-2013 Gabor Juhos <juhosg@openwrt.org>
- * Copyright (C) 2014-2015 Felix Fietkau <nbd@nbd.name>
- *
- * Some parts are based on spi-orion.c:
- *   Author: Shadi Ammouri <shadi@marvell.com>
- *   Copyright (C) 2007-2008 Marvell Ltd.
- */
+//
+// spi-mt7621.c -- MediaTek MT7621 SPI controller driver
+//
+// Copyright (C) 2011 Sergiy <piratfm@gmail.com>
+// Copyright (C) 2011-2013 Gabor Juhos <juhosg@openwrt.org>
+// Copyright (C) 2014-2015 Felix Fietkau <nbd@nbd.name>
+//
+// Some parts are based on spi-orion.c:
+//   Author: Shadi Ammouri <shadi@marvell.com>
+//   Copyright (C) 2007-2008 Marvell Ltd.
 
 #include <linux/clk.h>
 #include <linux/delay.h>
@@ -52,7 +51,7 @@
 #define MT7621_LSB_FIRST	BIT(3)
 
 struct mt7621_spi {
-	struct spi_master	*master;
+	struct spi_controller	*master;
 	void __iomem		*base;
 	unsigned int		sys_freq;
 	unsigned int		speed;
@@ -64,7 +63,7 @@ struct mt7621_spi {
 
 static inline struct mt7621_spi *spidev_to_mt7621_spi(struct spi_device *spi)
 {
-	return spi_master_get_devdata(spi->master);
+	return spi_controller_get_devdata(spi->master);
 }
 
 static inline u32 mt7621_spi_read(struct mt7621_spi *rs, u32 reg)
@@ -77,29 +76,25 @@ static inline void mt7621_spi_write(struct mt7621_spi *rs, u32 reg, u32 val)
 	iowrite32(val, rs->base + reg);
 }
 
-static void mt7621_spi_reset(struct mt7621_spi *rs)
+static void mt7621_spi_set_cs(struct spi_device *spi, int enable)
 {
-	u32 master = mt7621_spi_read(rs, MT7621_SPI_MASTER);
+	struct mt7621_spi *rs = spidev_to_mt7621_spi(spi);
+	int cs = spi->chip_select;
+	u32 polar = 0;
+	u32 master;
 
 	/*
 	 * Select SPI device 7, enable "more buffer mode" and disable
 	 * full-duplex (only half-duplex really works on this chip
 	 * reliably)
 	 */
+	master = mt7621_spi_read(rs, MT7621_SPI_MASTER);
 	master |= MASTER_RS_SLAVE_SEL | MASTER_MORE_BUFMODE;
 	master &= ~MASTER_FULL_DUPLEX;
-
 	mt7621_spi_write(rs, MT7621_SPI_MASTER, master);
-	rs->pending_write = 0;
-}
 
-static void mt7621_spi_set_cs(struct spi_device *spi, int enable)
-{
-	struct mt7621_spi *rs = spidev_to_mt7621_spi(spi);
-	int cs = spi->chip_select;
-	u32 polar = 0;
+	rs->pending_write = 0;
 
-	mt7621_spi_reset(rs);
 	if (enable)
 		polar = BIT(cs);
 	mt7621_spi_write(rs, MT7621_SPI_POLAR, polar);
@@ -163,13 +158,14 @@ static inline int mt7621_spi_wait_till_ready(struct mt7621_spi *rs)
 static void mt7621_spi_read_half_duplex(struct mt7621_spi *rs,
 					int rx_len, u8 *buf)
 {
+	int tx_len;
+
 	/*
 	 * Combine with any pending write, and perform one or more half-duplex
 	 * transactions reading 'len' bytes. Data to be written is already in
 	 * MT7621_SPI_DATA.
 	 */
-	int tx_len = rs->pending_write;
-
+	tx_len = rs->pending_write;
 	rs->pending_write = 0;
 
 	while (rx_len || tx_len) {
@@ -209,8 +205,8 @@ static inline void mt7621_spi_flush(struct mt7621_spi *rs)
 static void mt7621_spi_write_half_duplex(struct mt7621_spi *rs,
 					 int tx_len, const u8 *buf)
 {
-	int val = 0;
 	int len = rs->pending_write;
+	int val = 0;
 
 	if (len & 3) {
 		val = mt7621_spi_read(rs, MT7621_SPI_OPCODE + (len & ~3));
@@ -238,6 +234,7 @@ static void mt7621_spi_write_half_duplex(struct mt7621_spi *rs,
 		}
 		tx_len -= 1;
 	}
+
 	if (len & 3) {
 		if (len < 4) {
 			val = swab32(val);
@@ -245,13 +242,14 @@ static void mt7621_spi_write_half_duplex(struct mt7621_spi *rs,
 		}
 		mt7621_spi_write(rs, MT7621_SPI_OPCODE + (len & ~3), val);
 	}
+
 	rs->pending_write = len;
 }
 
-static int mt7621_spi_transfer_one_message(struct spi_master *master,
+static int mt7621_spi_transfer_one_message(struct spi_controller *master,
 					   struct spi_message *m)
 {
-	struct mt7621_spi *rs = spi_master_get_devdata(master);
+	struct mt7621_spi *rs = spi_controller_get_devdata(master);
 	struct spi_device *spi = m->spi;
 	unsigned int speed = spi->max_speed_hz;
 	struct spi_transfer *t = NULL;
@@ -268,11 +266,14 @@ static int mt7621_spi_transfer_one_message(struct spi_master *master,
 		goto msg_done;
 	}
 
+	/* Assert CS */
 	mt7621_spi_set_cs(spi, 1);
+
 	m->actual_length = 0;
 	list_for_each_entry(t, &m->transfers, transfer_list) {
 		if ((t->rx_buf) && (t->tx_buf)) {
-			/* This controller will shift some extra data out
+			/*
+			 * This controller will shift some extra data out
 			 * of spi_opcode if (mosi_bit_cnt > 0) &&
 			 * (cmd_bit_cnt == 0). So the claimed full-duplex
 			 * support is broken since we have no way to read
@@ -287,8 +288,9 @@ static int mt7621_spi_transfer_one_message(struct spi_master *master,
 		}
 		m->actual_length += t->len;
 	}
-	mt7621_spi_flush(rs);
 
+	/* Flush data and deassert CS */
+	mt7621_spi_flush(rs);
 	mt7621_spi_set_cs(spi, 0);
 
 msg_done:
@@ -303,7 +305,7 @@ static int mt7621_spi_setup(struct spi_device *spi)
 	struct mt7621_spi *rs = spidev_to_mt7621_spi(spi);
 
 	if ((spi->max_speed_hz == 0) ||
-		(spi->max_speed_hz > (rs->sys_freq / 2)))
+	    (spi->max_speed_hz > (rs->sys_freq / 2)))
 		spi->max_speed_hz = (rs->sys_freq / 2);
 
 	if (spi->max_speed_hz < (rs->sys_freq / 4097)) {
@@ -324,7 +326,7 @@ MODULE_DEVICE_TABLE(of, mt7621_spi_match);
 static int mt7621_spi_probe(struct platform_device *pdev)
 {
 	const struct of_device_id *match;
-	struct spi_master *master;
+	struct spi_controller *master;
 	struct mt7621_spi *rs;
 	void __iomem *base;
 	struct resource *r;
@@ -361,7 +363,7 @@ static int mt7621_spi_probe(struct platform_device *pdev)
 	}
 
 	master->mode_bits = SPI_LSB_FIRST;
-
+	master->flags = SPI_CONTROLLER_HALF_DUPLEX;
 	master->setup = mt7621_spi_setup;
 	master->transfer_one_message = mt7621_spi_transfer_one_message;
 	master->bits_per_word_mask = SPI_BPW_MASK(8);
@@ -370,7 +372,7 @@ static int mt7621_spi_probe(struct platform_device *pdev)
 
 	dev_set_drvdata(&pdev->dev, master);
 
-	rs = spi_master_get_devdata(master);
+	rs = spi_controller_get_devdata(master);
 	rs->base = base;
 	rs->clk = clk;
 	rs->master = master;
@@ -385,21 +387,18 @@ static int mt7621_spi_probe(struct platform_device *pdev)
 		return ret;
 	}
 
-	mt7621_spi_reset(rs);
-
-	return spi_register_master(master);
+	return devm_spi_register_controller(&pdev->dev, master);
 }
 
 static int mt7621_spi_remove(struct platform_device *pdev)
 {
-	struct spi_master *master;
+	struct spi_controller *master;
 	struct mt7621_spi *rs;
 
 	master = dev_get_drvdata(&pdev->dev);
-	rs = spi_master_get_devdata(master);
+	rs = spi_controller_get_devdata(master);
 
-	clk_disable(rs->clk);
-	spi_unregister_master(master);
+	clk_disable_unprepare(rs->clk);
 
 	return 0;
 }
diff --git a/drivers/spi/spi-mxic.c b/drivers/spi/spi-mxic.c
index e41ae6ef0f8a..f48563c09b97 100644
--- a/drivers/spi/spi-mxic.c
+++ b/drivers/spi/spi-mxic.c
@@ -492,8 +492,7 @@ static int mxic_spi_transfer_one(struct spi_master *master,
 
 static int __maybe_unused mxic_spi_runtime_suspend(struct device *dev)
 {
-	struct platform_device *pdev = to_platform_device(dev);
-	struct spi_master *master = platform_get_drvdata(pdev);
+	struct spi_master *master = dev_get_drvdata(dev);
 	struct mxic_spi *mxic = spi_master_get_devdata(master);
 
 	mxic_spi_clk_disable(mxic);
@@ -504,8 +503,7 @@ static int __maybe_unused mxic_spi_runtime_suspend(struct device *dev)
 
 static int __maybe_unused mxic_spi_runtime_resume(struct device *dev)
 {
-	struct platform_device *pdev = to_platform_device(dev);
-	struct spi_master *master = platform_get_drvdata(pdev);
+	struct spi_master *master = dev_get_drvdata(dev);
 	struct mxic_spi *mxic = spi_master_get_devdata(master);
 	int ret;
 
diff --git a/drivers/spi/spi-orion.c b/drivers/spi/spi-orion.c
index 7f280567093e..25ea4a9e0dbc 100644
--- a/drivers/spi/spi-orion.c
+++ b/drivers/spi/spi-orion.c
@@ -470,6 +470,8 @@ orion_spi_write_read(struct spi_device *spi, struct spi_transfer *xfer)
 			if (orion_spi_write_read_8bit(spi, &tx, &rx) < 0)
 				goto out;
 			count--;
+			if (xfer->word_delay_usecs)
+				udelay(xfer->word_delay_usecs);
 		} while (count);
 	} else if (word_len == 16) {
 		const u16 *tx = xfer->tx_buf;
@@ -479,6 +481,8 @@ orion_spi_write_read(struct spi_device *spi, struct spi_transfer *xfer)
 			if (orion_spi_write_read_16bit(spi, &tx, &rx) < 0)
 				goto out;
 			count -= 2;
+			if (xfer->word_delay_usecs)
+				udelay(xfer->word_delay_usecs);
 		} while (count);
 	}
 
diff --git a/drivers/spi/spi-pic32.c b/drivers/spi/spi-pic32.c
index 131849adc570..d9f374c8b709 100644
--- a/drivers/spi/spi-pic32.c
+++ b/drivers/spi/spi-pic32.c
@@ -559,7 +559,7 @@ static int pic32_spi_one_transfer(struct spi_master *master,
 		dev_err(&spi->dev, "wait error/timedout\n");
 		if (dma_issued) {
 			dmaengine_terminate_all(master->dma_rx);
-			dmaengine_terminate_all(master->dma_rx);
+			dmaengine_terminate_all(master->dma_tx);
 		}
 		ret = -ETIMEDOUT;
 	} else {
diff --git a/drivers/spi/spi-pxa2xx-dma.c b/drivers/spi/spi-pxa2xx-dma.c
index 15592598273e..e5c26c1779ab 100644
--- a/drivers/spi/spi-pxa2xx-dma.c
+++ b/drivers/spi/spi-pxa2xx-dma.c
@@ -239,13 +239,15 @@ int pxa2xx_spi_set_dma_burst_and_threshold(struct chip_data *chip,
 					   u32 *threshold)
 {
 	struct pxa2xx_spi_chip *chip_info = spi->controller_data;
+	struct driver_data *drv_data = spi_controller_get_devdata(spi->controller);
+	u32 dma_burst_size = drv_data->controller_info->dma_burst_size;
 
 	/*
 	 * If the DMA burst size is given in chip_info we use that,
 	 * otherwise we use the default. Also we use the default FIFO
 	 * thresholds for now.
 	 */
-	*burst_code = chip_info ? chip_info->dma_burst_size : 1;
+	*burst_code = chip_info ? chip_info->dma_burst_size : dma_burst_size;
 	*threshold = SSCR1_RxTresh(RX_THRESH_DFLT)
 		   | SSCR1_TxTresh(TX_THRESH_DFLT);
 
diff --git a/drivers/spi/spi-pxa2xx-pci.c b/drivers/spi/spi-pxa2xx-pci.c
index 1727fdfbac28..d456c5251b5d 100644
--- a/drivers/spi/spi-pxa2xx-pci.c
+++ b/drivers/spi/spi-pxa2xx-pci.c
@@ -5,7 +5,6 @@
  */
 #include <linux/clk-provider.h>
 #include <linux/module.h>
-#include <linux/of_device.h>
 #include <linux/pci.h>
 #include <linux/platform_device.h>
 #include <linux/spi/pxa2xx_spi.h>
@@ -35,6 +34,8 @@ struct pxa_spi_info {
 	void *tx_param;
 	void *rx_param;
 
+	int dma_burst_size;
+
 	int (*setup)(struct pci_dev *pdev, struct pxa_spi_info *c);
 };
 
@@ -133,6 +134,7 @@ static int mrfld_spi_setup(struct pci_dev *dev, struct pxa_spi_info *c)
 	rx->dma_dev = &dma_dev->dev;
 
 	c->dma_filter = lpss_dma_filter;
+	c->dma_burst_size = 8;
 	return 0;
 }
 
@@ -223,6 +225,7 @@ static int pxa2xx_spi_pci_probe(struct pci_dev *dev,
 	spi_pdata.tx_param = c->tx_param;
 	spi_pdata.rx_param = c->rx_param;
 	spi_pdata.enable_dma = c->rx_param && c->tx_param;
+	spi_pdata.dma_burst_size = c->dma_burst_size ? c->dma_burst_size : 1;
 
 	ssp = &spi_pdata.ssp;
 	ssp->phys_base = pci_resource_start(dev, 0);
diff --git a/drivers/spi/spi-pxa2xx.c b/drivers/spi/spi-pxa2xx.c
index b6ddba833d02..e59c8b27b155 100644
--- a/drivers/spi/spi-pxa2xx.c
+++ b/drivers/spi/spi-pxa2xx.c
@@ -884,10 +884,14 @@ static unsigned int ssp_get_clk_div(struct driver_data *drv_data, int rate)
 
 	rate = min_t(int, ssp_clk, rate);
 
+	/*
+	 * Calculate the divisor for the SCR (Serial Clock Rate), avoiding
+	 * that the SSP transmission rate can be greater than the device rate
+	 */
 	if (ssp->type == PXA25x_SSP || ssp->type == CE4100_SSP)
-		return (ssp_clk / (2 * rate) - 1) & 0xff;
+		return (DIV_ROUND_UP(ssp_clk, 2 * rate) - 1) & 0xff;
 	else
-		return (ssp_clk / rate - 1) & 0xfff;
+		return (DIV_ROUND_UP(ssp_clk, rate) - 1)  & 0xfff;
 }
 
 static unsigned int pxa2xx_ssp_get_clk_div(struct driver_data *drv_data,
@@ -925,7 +929,7 @@ static int pxa2xx_spi_transfer_one(struct spi_controller *controller,
 {
 	struct driver_data *drv_data = spi_controller_get_devdata(controller);
 	struct spi_message *message = controller->cur_msg;
-	struct chip_data *chip = spi_get_ctldata(message->spi);
+	struct chip_data *chip = spi_get_ctldata(spi);
 	u32 dma_thresh = chip->dma_threshold;
 	u32 dma_burst = chip->dma_burst_size;
 	u32 change_mask = pxa2xx_spi_get_ssrc1_change_mask(drv_data);
@@ -943,21 +947,21 @@ static int pxa2xx_spi_transfer_one(struct spi_controller *controller,
 		/* reject already-mapped transfers; PIO won't always work */
 		if (message->is_dma_mapped
 				|| transfer->rx_dma || transfer->tx_dma) {
-			dev_err(&drv_data->pdev->dev,
+			dev_err(&spi->dev,
 				"Mapped transfer length of %u is greater than %d\n",
 				transfer->len, MAX_DMA_LEN);
 			return -EINVAL;
 		}
 
 		/* warn ... we force this to PIO mode */
-		dev_warn_ratelimited(&message->spi->dev,
+		dev_warn_ratelimited(&spi->dev,
 				     "DMA disabled for transfer length %ld greater than %d\n",
 				     (long)transfer->len, MAX_DMA_LEN);
 	}
 
 	/* Setup the transfer state based on the type of transfer */
 	if (pxa2xx_spi_flush(drv_data) == 0) {
-		dev_err(&drv_data->pdev->dev, "Flush failed\n");
+		dev_err(&spi->dev, "Flush failed\n");
 		return -EIO;
 	}
 	drv_data->n_bytes = chip->n_bytes;
@@ -999,15 +1003,15 @@ static int pxa2xx_spi_transfer_one(struct spi_controller *controller,
 	 */
 	if (chip->enable_dma) {
 		if (pxa2xx_spi_set_dma_burst_and_threshold(chip,
-						message->spi,
+						spi,
 						bits, &dma_burst,
 						&dma_thresh))
-			dev_warn_ratelimited(&message->spi->dev,
+			dev_warn_ratelimited(&spi->dev,
 					     "DMA burst size reduced to match bits_per_word\n");
 	}
 
 	dma_mapped = controller->can_dma &&
-		     controller->can_dma(controller, message->spi, transfer) &&
+		     controller->can_dma(controller, spi, transfer) &&
 		     controller->cur_msg_mapped;
 	if (dma_mapped) {
 
@@ -1035,12 +1039,12 @@ static int pxa2xx_spi_transfer_one(struct spi_controller *controller,
 	/* NOTE:  PXA25x_SSP _could_ use external clocking ... */
 	cr0 = pxa2xx_configure_sscr0(drv_data, clk_div, bits);
 	if (!pxa25x_ssp_comp(drv_data))
-		dev_dbg(&message->spi->dev, "%u Hz actual, %s\n",
+		dev_dbg(&spi->dev, "%u Hz actual, %s\n",
 			controller->max_speed_hz
 				/ (1 + ((cr0 & SSCR0_SCR(0xfff)) >> 8)),
 			dma_mapped ? "DMA" : "PIO");
 	else
-		dev_dbg(&message->spi->dev, "%u Hz actual, %s\n",
+		dev_dbg(&spi->dev, "%u Hz actual, %s\n",
 			controller->max_speed_hz / 2
 				/ (1 + ((cr0 & SSCR0_SCR(0x0ff)) >> 8)),
 			dma_mapped ? "DMA" : "PIO");
@@ -1333,6 +1337,9 @@ static int setup(struct spi_device *spi)
 			dev_warn(&spi->dev,
 				 "in setup: DMA burst size reduced to match bits_per_word\n");
 		}
+		dev_dbg(&spi->dev,
+			"in setup: DMA burst size set to %u\n",
+			chip->dma_burst_size);
 	}
 
 	switch (drv_data->ssp_type) {
@@ -1451,6 +1458,10 @@ static const struct pci_device_id pxa2xx_spi_pci_compound_match[] = {
 	{ PCI_VDEVICE(INTEL, 0xa32a), LPSS_CNL_SSP },
 	{ PCI_VDEVICE(INTEL, 0xa32b), LPSS_CNL_SSP },
 	{ PCI_VDEVICE(INTEL, 0xa37b), LPSS_CNL_SSP },
+	/* CML-LP */
+	{ PCI_VDEVICE(INTEL, 0x02aa), LPSS_CNL_SSP },
+	{ PCI_VDEVICE(INTEL, 0x02ab), LPSS_CNL_SSP },
+	{ PCI_VDEVICE(INTEL, 0x02fb), LPSS_CNL_SSP },
 	{ },
 };
 
@@ -1564,6 +1575,7 @@ pxa2xx_spi_init_pdata(struct platform_device *pdev)
 	pdata->is_slave = of_property_read_bool(pdev->dev.of_node, "spi-slave");
 	pdata->num_chipselect = 1;
 	pdata->enable_dma = true;
+	pdata->dma_burst_size = 1;
 
 	return pdata;
 }
@@ -1692,7 +1704,7 @@ static int pxa2xx_spi_probe(struct platform_device *pdev)
 	if (platform_info->enable_dma) {
 		status = pxa2xx_spi_dma_setup(drv_data);
 		if (status) {
-			dev_dbg(dev, "no DMA channels available, using PIO\n");
+			dev_warn(dev, "no DMA channels available, using PIO\n");
 			platform_info->enable_dma = false;
 		} else {
 			controller->can_dma = pxa2xx_spi_can_dma;
@@ -1953,3 +1965,5 @@ static void __exit pxa2xx_spi_exit(void)
 	platform_driver_unregister(&driver);
 }
 module_exit(pxa2xx_spi_exit);
+
+MODULE_SOFTDEP("pre: dw_dmac");
diff --git a/drivers/spi/spi-rspi.c b/drivers/spi/spi-rspi.c
index 556870dcdf79..15f5723d9f95 100644
--- a/drivers/spi/spi-rspi.c
+++ b/drivers/spi/spi-rspi.c
@@ -271,7 +271,8 @@ static int rspi_set_config_register(struct rspi_data *rspi, int access_size)
 	/* Sets parity, interrupt mask */
 	rspi_write8(rspi, 0x00, RSPI_SPCR2);
 
-	/* Sets SPCMD */
+	/* Resets sequencer */
+	rspi_write8(rspi, 0, RSPI_SPSCR);
 	rspi->spcmd |= SPCMD_SPB_8_TO_16(access_size);
 	rspi_write16(rspi, rspi->spcmd, RSPI_SPCMD0);
 
@@ -315,7 +316,8 @@ static int rspi_rz_set_config_register(struct rspi_data *rspi, int access_size)
 	rspi_write8(rspi, 0x00, RSPI_SSLND);
 	rspi_write8(rspi, 0x00, RSPI_SPND);
 
-	/* Sets SPCMD */
+	/* Resets sequencer */
+	rspi_write8(rspi, 0, RSPI_SPSCR);
 	rspi->spcmd |= SPCMD_SPB_8_TO_16(access_size);
 	rspi_write16(rspi, rspi->spcmd, RSPI_SPCMD0);
 
@@ -366,7 +368,8 @@ static int qspi_set_config_register(struct rspi_data *rspi, int access_size)
 	/* Sets buffer to allow normal operation */
 	rspi_write8(rspi, 0x00, QSPI_SPBFCR);
 
-	/* Sets SPCMD */
+	/* Resets sequencer */
+	rspi_write8(rspi, 0, RSPI_SPSCR);
 	rspi_write16(rspi, rspi->spcmd, RSPI_SPCMD0);
 
 	/* Sets RSPI mode */
@@ -736,27 +739,22 @@ static int qspi_trigger_transfer_out_in(struct rspi_data *rspi, const u8 *tx,
 	while (len > 0) {
 		n = qspi_set_send_trigger(rspi, len);
 		qspi_set_receive_trigger(rspi, len);
-		if (n == QSPI_BUFFER_SIZE) {
-			ret = rspi_wait_for_tx_empty(rspi);
-			if (ret < 0) {
-				dev_err(&rspi->ctlr->dev, "transmit timeout\n");
-				return ret;
-			}
-			for (i = 0; i < n; i++)
-				rspi_write_data(rspi, *tx++);
+		ret = rspi_wait_for_tx_empty(rspi);
+		if (ret < 0) {
+			dev_err(&rspi->ctlr->dev, "transmit timeout\n");
+			return ret;
+		}
+		for (i = 0; i < n; i++)
+			rspi_write_data(rspi, *tx++);
 
-			ret = rspi_wait_for_rx_full(rspi);
-			if (ret < 0) {
-				dev_err(&rspi->ctlr->dev, "receive timeout\n");
-				return ret;
-			}
-			for (i = 0; i < n; i++)
-				*rx++ = rspi_read_data(rspi);
-		} else {
-			ret = rspi_pio_transfer(rspi, tx, rx, n);
-			if (ret < 0)
-				return ret;
+		ret = rspi_wait_for_rx_full(rspi);
+		if (ret < 0) {
+			dev_err(&rspi->ctlr->dev, "receive timeout\n");
+			return ret;
 		}
+		for (i = 0; i < n; i++)
+			*rx++ = rspi_read_data(rspi);
+
 		len -= n;
 	}
 
@@ -793,19 +791,14 @@ static int qspi_transfer_out(struct rspi_data *rspi, struct spi_transfer *xfer)
 
 	while (n > 0) {
 		len = qspi_set_send_trigger(rspi, n);
-		if (len == QSPI_BUFFER_SIZE) {
-			ret = rspi_wait_for_tx_empty(rspi);
-			if (ret < 0) {
-				dev_err(&rspi->ctlr->dev, "transmit timeout\n");
-				return ret;
-			}
-			for (i = 0; i < len; i++)
-				rspi_write_data(rspi, *tx++);
-		} else {
-			ret = rspi_pio_transfer(rspi, tx, NULL, len);
-			if (ret < 0)
-				return ret;
+		ret = rspi_wait_for_tx_empty(rspi);
+		if (ret < 0) {
+			dev_err(&rspi->ctlr->dev, "transmit timeout\n");
+			return ret;
 		}
+		for (i = 0; i < len; i++)
+			rspi_write_data(rspi, *tx++);
+
 		n -= len;
 	}
 
@@ -830,19 +823,14 @@ static int qspi_transfer_in(struct rspi_data *rspi, struct spi_transfer *xfer)
 
 	while (n > 0) {
 		len = qspi_set_receive_trigger(rspi, n);
-		if (len == QSPI_BUFFER_SIZE) {
-			ret = rspi_wait_for_rx_full(rspi);
-			if (ret < 0) {
-				dev_err(&rspi->ctlr->dev, "receive timeout\n");
-				return ret;
-			}
-			for (i = 0; i < len; i++)
-				*rx++ = rspi_read_data(rspi);
-		} else {
-			ret = rspi_pio_transfer(rspi, NULL, rx, len);
-			if (ret < 0)
-				return ret;
+		ret = rspi_wait_for_rx_full(rspi);
+		if (ret < 0) {
+			dev_err(&rspi->ctlr->dev, "receive timeout\n");
+			return ret;
 		}
+		for (i = 0; i < len; i++)
+			*rx++ = rspi_read_data(rspi);
+
 		n -= len;
 	}
 
@@ -868,28 +856,6 @@ static int qspi_transfer_one(struct spi_controller *ctlr,
 	}
 }
 
-static int rspi_setup(struct spi_device *spi)
-{
-	struct rspi_data *rspi = spi_controller_get_devdata(spi->controller);
-
-	rspi->max_speed_hz = spi->max_speed_hz;
-
-	rspi->spcmd = SPCMD_SSLKP;
-	if (spi->mode & SPI_CPOL)
-		rspi->spcmd |= SPCMD_CPOL;
-	if (spi->mode & SPI_CPHA)
-		rspi->spcmd |= SPCMD_CPHA;
-
-	/* CMOS output mode and MOSI signal from previous transfer */
-	rspi->sppcr = 0;
-	if (spi->mode & SPI_LOOP)
-		rspi->sppcr |= SPPCR_SPLP;
-
-	set_config_register(rspi, 8);
-
-	return 0;
-}
-
 static u16 qspi_transfer_mode(const struct spi_transfer *xfer)
 {
 	if (xfer->tx_buf)
@@ -959,8 +925,24 @@ static int rspi_prepare_message(struct spi_controller *ctlr,
 				struct spi_message *msg)
 {
 	struct rspi_data *rspi = spi_controller_get_devdata(ctlr);
+	struct spi_device *spi = msg->spi;
 	int ret;
 
+	rspi->max_speed_hz = spi->max_speed_hz;
+
+	rspi->spcmd = SPCMD_SSLKP;
+	if (spi->mode & SPI_CPOL)
+		rspi->spcmd |= SPCMD_CPOL;
+	if (spi->mode & SPI_CPHA)
+		rspi->spcmd |= SPCMD_CPHA;
+
+	/* CMOS output mode and MOSI signal from previous transfer */
+	rspi->sppcr = 0;
+	if (spi->mode & SPI_LOOP)
+		rspi->sppcr |= SPPCR_SPLP;
+
+	set_config_register(rspi, 8);
+
 	if (msg->spi->mode &
 	    (SPI_TX_DUAL | SPI_TX_QUAD | SPI_RX_DUAL | SPI_RX_QUAD)) {
 		/* Setup sequencer for messages with multiple transfer modes */
@@ -1267,7 +1249,6 @@ static int rspi_probe(struct platform_device *pdev)
 	init_waitqueue_head(&rspi->wait);
 
 	ctlr->bus_num = pdev->id;
-	ctlr->setup = rspi_setup;
 	ctlr->auto_runtime_pm = true;
 	ctlr->transfer_one = ops->transfer_one;
 	ctlr->prepare_message = rspi_prepare_message;
diff --git a/drivers/spi/spi-sh-msiof.c b/drivers/spi/spi-sh-msiof.c
index e2eb466db10a..6aab7b2136db 100644
--- a/drivers/spi/spi-sh-msiof.c
+++ b/drivers/spi/spi-sh-msiof.c
@@ -18,6 +18,7 @@
 #include <linux/gpio/consumer.h>
 #include <linux/interrupt.h>
 #include <linux/io.h>
+#include <linux/iopoll.h>
 #include <linux/kernel.h>
 #include <linux/module.h>
 #include <linux/of.h>
@@ -82,111 +83,113 @@ struct sh_msiof_spi_priv {
 #define RFDR	0x60	/* Receive FIFO Data Register */
 
 /* TMDR1 and RMDR1 */
-#define MDR1_TRMD	 0x80000000 /* Transfer Mode (1 = Master mode) */
-#define MDR1_SYNCMD_MASK 0x30000000 /* SYNC Mode */
-#define MDR1_SYNCMD_SPI	 0x20000000 /*   Level mode/SPI */
-#define MDR1_SYNCMD_LR	 0x30000000 /*   L/R mode */
-#define MDR1_SYNCAC_SHIFT	 25 /* Sync Polarity (1 = Active-low) */
-#define MDR1_BITLSB_SHIFT	 24 /* MSB/LSB First (1 = LSB first) */
-#define MDR1_DTDL_SHIFT		 20 /* Data Pin Bit Delay for MSIOF_SYNC */
-#define MDR1_SYNCDL_SHIFT	 16 /* Frame Sync Signal Timing Delay */
-#define MDR1_FLD_MASK	 0x0000000c /* Frame Sync Signal Interval (0-3) */
-#define MDR1_FLD_SHIFT		  2
-#define MDR1_XXSTP	 0x00000001 /* Transmission/Reception Stop on FIFO */
+#define MDR1_TRMD	   BIT(31)  /* Transfer Mode (1 = Master mode) */
+#define MDR1_SYNCMD_MASK   GENMASK(29, 28) /* SYNC Mode */
+#define MDR1_SYNCMD_SPI	   (2 << 28)/*   Level mode/SPI */
+#define MDR1_SYNCMD_LR	   (3 << 28)/*   L/R mode */
+#define MDR1_SYNCAC_SHIFT  25       /* Sync Polarity (1 = Active-low) */
+#define MDR1_BITLSB_SHIFT  24       /* MSB/LSB First (1 = LSB first) */
+#define MDR1_DTDL_SHIFT	   20       /* Data Pin Bit Delay for MSIOF_SYNC */
+#define MDR1_SYNCDL_SHIFT  16       /* Frame Sync Signal Timing Delay */
+#define MDR1_FLD_MASK	   GENMASK(3, 2) /* Frame Sync Signal Interval (0-3) */
+#define MDR1_FLD_SHIFT	   2
+#define MDR1_XXSTP	   BIT(0)   /* Transmission/Reception Stop on FIFO */
 /* TMDR1 */
-#define TMDR1_PCON	 0x40000000 /* Transfer Signal Connection */
-#define TMDR1_SYNCCH_MASK 0xc000000 /* Synchronization Signal Channel Select */
-#define TMDR1_SYNCCH_SHIFT	 26 /* 0=MSIOF_SYNC, 1=MSIOF_SS1, 2=MSIOF_SS2 */
+#define TMDR1_PCON	   BIT(30)  /* Transfer Signal Connection */
+#define TMDR1_SYNCCH_MASK  GENMASK(27, 26) /* Sync Signal Channel Select */
+#define TMDR1_SYNCCH_SHIFT 26       /* 0=MSIOF_SYNC, 1=MSIOF_SS1, 2=MSIOF_SS2 */
 
 /* TMDR2 and RMDR2 */
 #define MDR2_BITLEN1(i)	(((i) - 1) << 24) /* Data Size (8-32 bits) */
 #define MDR2_WDLEN1(i)	(((i) - 1) << 16) /* Word Count (1-64/256 (SH, A1))) */
-#define MDR2_GRPMASK1	0x00000001 /* Group Output Mask 1 (SH, A1) */
+#define MDR2_GRPMASK1	BIT(0)      /* Group Output Mask 1 (SH, A1) */
 
 /* TSCR and RSCR */
-#define SCR_BRPS_MASK	    0x1f00 /* Prescaler Setting (1-32) */
+#define SCR_BRPS_MASK	GENMASK(12, 8) /* Prescaler Setting (1-32) */
 #define SCR_BRPS(i)	(((i) - 1) << 8)
-#define SCR_BRDV_MASK	    0x0007 /* Baud Rate Generator's Division Ratio */
-#define SCR_BRDV_DIV_2	    0x0000
-#define SCR_BRDV_DIV_4	    0x0001
-#define SCR_BRDV_DIV_8	    0x0002
-#define SCR_BRDV_DIV_16	    0x0003
-#define SCR_BRDV_DIV_32	    0x0004
-#define SCR_BRDV_DIV_1	    0x0007
+#define SCR_BRDV_MASK	GENMASK(2, 0) /* Baud Rate Generator's Division Ratio */
+#define SCR_BRDV_DIV_2	0
+#define SCR_BRDV_DIV_4	1
+#define SCR_BRDV_DIV_8	2
+#define SCR_BRDV_DIV_16	3
+#define SCR_BRDV_DIV_32	4
+#define SCR_BRDV_DIV_1	7
 
 /* CTR */
-#define CTR_TSCKIZ_MASK	0xc0000000 /* Transmit Clock I/O Polarity Select */
-#define CTR_TSCKIZ_SCK	0x80000000 /*   Disable SCK when TX disabled */
-#define CTR_TSCKIZ_POL_SHIFT	30 /*   Transmit Clock Polarity */
-#define CTR_RSCKIZ_MASK	0x30000000 /* Receive Clock Polarity Select */
-#define CTR_RSCKIZ_SCK	0x20000000 /*   Must match CTR_TSCKIZ_SCK */
-#define CTR_RSCKIZ_POL_SHIFT	28 /*   Receive Clock Polarity */
-#define CTR_TEDG_SHIFT		27 /* Transmit Timing (1 = falling edge) */
-#define CTR_REDG_SHIFT		26 /* Receive Timing (1 = falling edge) */
-#define CTR_TXDIZ_MASK	0x00c00000 /* Pin Output When TX is Disabled */
-#define CTR_TXDIZ_LOW	0x00000000 /*   0 */
-#define CTR_TXDIZ_HIGH	0x00400000 /*   1 */
-#define CTR_TXDIZ_HIZ	0x00800000 /*   High-impedance */
-#define CTR_TSCKE	0x00008000 /* Transmit Serial Clock Output Enable */
-#define CTR_TFSE	0x00004000 /* Transmit Frame Sync Signal Output Enable */
-#define CTR_TXE		0x00000200 /* Transmit Enable */
-#define CTR_RXE		0x00000100 /* Receive Enable */
+#define CTR_TSCKIZ_MASK	GENMASK(31, 30) /* Transmit Clock I/O Polarity Select */
+#define CTR_TSCKIZ_SCK	BIT(31)   /*   Disable SCK when TX disabled */
+#define CTR_TSCKIZ_POL_SHIFT 30   /*   Transmit Clock Polarity */
+#define CTR_RSCKIZ_MASK	GENMASK(29, 28) /* Receive Clock Polarity Select */
+#define CTR_RSCKIZ_SCK	BIT(29)   /*   Must match CTR_TSCKIZ_SCK */
+#define CTR_RSCKIZ_POL_SHIFT 28   /*   Receive Clock Polarity */
+#define CTR_TEDG_SHIFT	     27   /* Transmit Timing (1 = falling edge) */
+#define CTR_REDG_SHIFT	     26   /* Receive Timing (1 = falling edge) */
+#define CTR_TXDIZ_MASK	GENMASK(23, 22) /* Pin Output When TX is Disabled */
+#define CTR_TXDIZ_LOW	(0 << 22) /*   0 */
+#define CTR_TXDIZ_HIGH	(1 << 22) /*   1 */
+#define CTR_TXDIZ_HIZ	(2 << 22) /*   High-impedance */
+#define CTR_TSCKE	BIT(15)   /* Transmit Serial Clock Output Enable */
+#define CTR_TFSE	BIT(14)   /* Transmit Frame Sync Signal Output Enable */
+#define CTR_TXE		BIT(9)    /* Transmit Enable */
+#define CTR_RXE		BIT(8)    /* Receive Enable */
+#define CTR_TXRST	BIT(1)    /* Transmit Reset */
+#define CTR_RXRST	BIT(0)    /* Receive Reset */
 
 /* FCTR */
-#define FCTR_TFWM_MASK	0xe0000000 /* Transmit FIFO Watermark */
-#define FCTR_TFWM_64	0x00000000 /*  Transfer Request when 64 empty stages */
-#define FCTR_TFWM_32	0x20000000 /*  Transfer Request when 32 empty stages */
-#define FCTR_TFWM_24	0x40000000 /*  Transfer Request when 24 empty stages */
-#define FCTR_TFWM_16	0x60000000 /*  Transfer Request when 16 empty stages */
-#define FCTR_TFWM_12	0x80000000 /*  Transfer Request when 12 empty stages */
-#define FCTR_TFWM_8	0xa0000000 /*  Transfer Request when 8 empty stages */
-#define FCTR_TFWM_4	0xc0000000 /*  Transfer Request when 4 empty stages */
-#define FCTR_TFWM_1	0xe0000000 /*  Transfer Request when 1 empty stage */
-#define FCTR_TFUA_MASK	0x07f00000 /* Transmit FIFO Usable Area */
-#define FCTR_TFUA_SHIFT		20
+#define FCTR_TFWM_MASK	GENMASK(31, 29) /* Transmit FIFO Watermark */
+#define FCTR_TFWM_64	(0 << 29) /*  Transfer Request when 64 empty stages */
+#define FCTR_TFWM_32	(1 << 29) /*  Transfer Request when 32 empty stages */
+#define FCTR_TFWM_24	(2 << 29) /*  Transfer Request when 24 empty stages */
+#define FCTR_TFWM_16	(3 << 29) /*  Transfer Request when 16 empty stages */
+#define FCTR_TFWM_12	(4 << 29) /*  Transfer Request when 12 empty stages */
+#define FCTR_TFWM_8	(5 << 29) /*  Transfer Request when 8 empty stages */
+#define FCTR_TFWM_4	(6 << 29) /*  Transfer Request when 4 empty stages */
+#define FCTR_TFWM_1	(7 << 29) /*  Transfer Request when 1 empty stage */
+#define FCTR_TFUA_MASK	GENMASK(26, 20) /* Transmit FIFO Usable Area */
+#define FCTR_TFUA_SHIFT	20
 #define FCTR_TFUA(i)	((i) << FCTR_TFUA_SHIFT)
-#define FCTR_RFWM_MASK	0x0000e000 /* Receive FIFO Watermark */
-#define FCTR_RFWM_1	0x00000000 /*  Transfer Request when 1 valid stages */
-#define FCTR_RFWM_4	0x00002000 /*  Transfer Request when 4 valid stages */
-#define FCTR_RFWM_8	0x00004000 /*  Transfer Request when 8 valid stages */
-#define FCTR_RFWM_16	0x00006000 /*  Transfer Request when 16 valid stages */
-#define FCTR_RFWM_32	0x00008000 /*  Transfer Request when 32 valid stages */
-#define FCTR_RFWM_64	0x0000a000 /*  Transfer Request when 64 valid stages */
-#define FCTR_RFWM_128	0x0000c000 /*  Transfer Request when 128 valid stages */
-#define FCTR_RFWM_256	0x0000e000 /*  Transfer Request when 256 valid stages */
-#define FCTR_RFUA_MASK	0x00001ff0 /* Receive FIFO Usable Area (0x40 = full) */
-#define FCTR_RFUA_SHIFT		 4
+#define FCTR_RFWM_MASK	GENMASK(15, 13) /* Receive FIFO Watermark */
+#define FCTR_RFWM_1	(0 << 13) /*  Transfer Request when 1 valid stages */
+#define FCTR_RFWM_4	(1 << 13) /*  Transfer Request when 4 valid stages */
+#define FCTR_RFWM_8	(2 << 13) /*  Transfer Request when 8 valid stages */
+#define FCTR_RFWM_16	(3 << 13) /*  Transfer Request when 16 valid stages */
+#define FCTR_RFWM_32	(4 << 13) /*  Transfer Request when 32 valid stages */
+#define FCTR_RFWM_64	(5 << 13) /*  Transfer Request when 64 valid stages */
+#define FCTR_RFWM_128	(6 << 13) /*  Transfer Request when 128 valid stages */
+#define FCTR_RFWM_256	(7 << 13) /*  Transfer Request when 256 valid stages */
+#define FCTR_RFUA_MASK	GENMASK(12, 4) /* Receive FIFO Usable Area (0x40 = full) */
+#define FCTR_RFUA_SHIFT	4
 #define FCTR_RFUA(i)	((i) << FCTR_RFUA_SHIFT)
 
 /* STR */
-#define STR_TFEMP	0x20000000 /* Transmit FIFO Empty */
-#define STR_TDREQ	0x10000000 /* Transmit Data Transfer Request */
-#define STR_TEOF	0x00800000 /* Frame Transmission End */
-#define STR_TFSERR	0x00200000 /* Transmit Frame Synchronization Error */
-#define STR_TFOVF	0x00100000 /* Transmit FIFO Overflow */
-#define STR_TFUDF	0x00080000 /* Transmit FIFO Underflow */
-#define STR_RFFUL	0x00002000 /* Receive FIFO Full */
-#define STR_RDREQ	0x00001000 /* Receive Data Transfer Request */
-#define STR_REOF	0x00000080 /* Frame Reception End */
-#define STR_RFSERR	0x00000020 /* Receive Frame Synchronization Error */
-#define STR_RFUDF	0x00000010 /* Receive FIFO Underflow */
-#define STR_RFOVF	0x00000008 /* Receive FIFO Overflow */
+#define STR_TFEMP	BIT(29) /* Transmit FIFO Empty */
+#define STR_TDREQ	BIT(28) /* Transmit Data Transfer Request */
+#define STR_TEOF	BIT(23) /* Frame Transmission End */
+#define STR_TFSERR	BIT(21) /* Transmit Frame Synchronization Error */
+#define STR_TFOVF	BIT(20) /* Transmit FIFO Overflow */
+#define STR_TFUDF	BIT(19) /* Transmit FIFO Underflow */
+#define STR_RFFUL	BIT(13) /* Receive FIFO Full */
+#define STR_RDREQ	BIT(12) /* Receive Data Transfer Request */
+#define STR_REOF	BIT(7)  /* Frame Reception End */
+#define STR_RFSERR	BIT(5)  /* Receive Frame Synchronization Error */
+#define STR_RFUDF	BIT(4)  /* Receive FIFO Underflow */
+#define STR_RFOVF	BIT(3)  /* Receive FIFO Overflow */
 
 /* IER */
-#define IER_TDMAE	0x80000000 /* Transmit Data DMA Transfer Req. Enable */
-#define IER_TFEMPE	0x20000000 /* Transmit FIFO Empty Enable */
-#define IER_TDREQE	0x10000000 /* Transmit Data Transfer Request Enable */
-#define IER_TEOFE	0x00800000 /* Frame Transmission End Enable */
-#define IER_TFSERRE	0x00200000 /* Transmit Frame Sync Error Enable */
-#define IER_TFOVFE	0x00100000 /* Transmit FIFO Overflow Enable */
-#define IER_TFUDFE	0x00080000 /* Transmit FIFO Underflow Enable */
-#define IER_RDMAE	0x00008000 /* Receive Data DMA Transfer Req. Enable */
-#define IER_RFFULE	0x00002000 /* Receive FIFO Full Enable */
-#define IER_RDREQE	0x00001000 /* Receive Data Transfer Request Enable */
-#define IER_REOFE	0x00000080 /* Frame Reception End Enable */
-#define IER_RFSERRE	0x00000020 /* Receive Frame Sync Error Enable */
-#define IER_RFUDFE	0x00000010 /* Receive FIFO Underflow Enable */
-#define IER_RFOVFE	0x00000008 /* Receive FIFO Overflow Enable */
+#define IER_TDMAE	BIT(31) /* Transmit Data DMA Transfer Req. Enable */
+#define IER_TFEMPE	BIT(29) /* Transmit FIFO Empty Enable */
+#define IER_TDREQE	BIT(28) /* Transmit Data Transfer Request Enable */
+#define IER_TEOFE	BIT(23) /* Frame Transmission End Enable */
+#define IER_TFSERRE	BIT(21) /* Transmit Frame Sync Error Enable */
+#define IER_TFOVFE	BIT(20) /* Transmit FIFO Overflow Enable */
+#define IER_TFUDFE	BIT(19) /* Transmit FIFO Underflow Enable */
+#define IER_RDMAE	BIT(15) /* Receive Data DMA Transfer Req. Enable */
+#define IER_RFFULE	BIT(13) /* Receive FIFO Full Enable */
+#define IER_RDREQE	BIT(12) /* Receive Data Transfer Request Enable */
+#define IER_REOFE	BIT(7)  /* Frame Reception End Enable */
+#define IER_RFSERRE	BIT(5)  /* Receive Frame Sync Error Enable */
+#define IER_RFUDFE	BIT(4)  /* Receive FIFO Underflow Enable */
+#define IER_RFOVFE	BIT(3)  /* Receive FIFO Overflow Enable */
 
 
 static u32 sh_msiof_read(struct sh_msiof_spi_priv *p, int reg_offs)
@@ -219,21 +222,14 @@ static int sh_msiof_modify_ctr_wait(struct sh_msiof_spi_priv *p,
 {
 	u32 mask = clr | set;
 	u32 data;
-	int k;
 
 	data = sh_msiof_read(p, CTR);
 	data &= ~clr;
 	data |= set;
 	sh_msiof_write(p, CTR, data);
 
-	for (k = 100; k > 0; k--) {
-		if ((sh_msiof_read(p, CTR) & mask) == set)
-			break;
-
-		udelay(10);
-	}
-
-	return k > 0 ? 0 : -ETIMEDOUT;
+	return readl_poll_timeout_atomic(p->mapbase + CTR, data,
+					 (data & mask) == set, 10, 1000);
 }
 
 static irqreturn_t sh_msiof_spi_irq(int irq, void *data)
@@ -247,6 +243,19 @@ static irqreturn_t sh_msiof_spi_irq(int irq, void *data)
 	return IRQ_HANDLED;
 }
 
+static void sh_msiof_spi_reset_regs(struct sh_msiof_spi_priv *p)
+{
+	u32 mask = CTR_TXRST | CTR_RXRST;
+	u32 data;
+
+	data = sh_msiof_read(p, CTR);
+	data |= mask;
+	sh_msiof_write(p, CTR, data);
+
+	readl_poll_timeout_atomic(p->mapbase + CTR, data, !(data & mask), 1,
+				  100);
+}
+
 static const u32 sh_msiof_spi_div_array[] = {
 	SCR_BRDV_DIV_1, SCR_BRDV_DIV_2,	 SCR_BRDV_DIV_4,
 	SCR_BRDV_DIV_8,	SCR_BRDV_DIV_16, SCR_BRDV_DIV_32,
@@ -540,25 +549,11 @@ static void sh_msiof_spi_read_fifo_s32u(struct sh_msiof_spi_priv *p,
 
 static int sh_msiof_spi_setup(struct spi_device *spi)
 {
-	struct device_node *np = spi->controller->dev.of_node;
 	struct sh_msiof_spi_priv *p =
 		spi_controller_get_devdata(spi->controller);
 	u32 clr, set, tmp;
 
-	if (!np) {
-		/*
-		 * Use spi->controller_data for CS (same strategy as spi_gpio),
-		 * if any. otherwise let HW control CS
-		 */
-		spi->cs_gpio = (uintptr_t)spi->controller_data;
-	}
-
-	if (gpio_is_valid(spi->cs_gpio)) {
-		gpio_direction_output(spi->cs_gpio, !(spi->mode & SPI_CS_HIGH));
-		return 0;
-	}
-
-	if (spi_controller_is_slave(p->ctlr))
+	if (spi->cs_gpiod || spi_controller_is_slave(p->ctlr))
 		return 0;
 
 	if (p->native_cs_inited &&
@@ -591,7 +586,7 @@ static int sh_msiof_prepare_message(struct spi_controller *ctlr,
 	u32 ss, cs_high;
 
 	/* Configure pins before asserting CS */
-	if (gpio_is_valid(spi->cs_gpio)) {
+	if (spi->cs_gpiod) {
 		ss = p->unused_ss;
 		cs_high = p->native_cs_high;
 	} else {
@@ -926,6 +921,9 @@ static int sh_msiof_transfer_one(struct spi_controller *ctlr,
 	bool swab;
 	int ret;
 
+	/* reset registers */
+	sh_msiof_spi_reset_regs(p);
+
 	/* setup clocks (clock already enabled in chipselect()) */
 	if (!spi_controller_is_slave(p->ctlr))
 		sh_msiof_spi_set_clk_regs(p, clk_get_rate(p->clk), t->speed_hz);
@@ -1144,6 +1142,7 @@ static int sh_msiof_get_cs_gpios(struct sh_msiof_spi_priv *p)
 
 		gpiod = devm_gpiod_get_index(dev, "cs", i, GPIOD_ASIS);
 		if (!IS_ERR(gpiod)) {
+			devm_gpiod_put(dev, gpiod);
 			cs_gpios++;
 			continue;
 		}
@@ -1395,6 +1394,7 @@ static int sh_msiof_spi_probe(struct platform_device *pdev)
 	ctlr->bits_per_word_mask = chipdata->bits_per_word_mask;
 	ctlr->auto_runtime_pm = true;
 	ctlr->transfer_one = sh_msiof_transfer_one;
+	ctlr->use_gpio_descriptors = true;
 
 	ret = sh_msiof_request_dma(p);
 	if (ret < 0)
diff --git a/drivers/spi/spi-stm32-qspi.c b/drivers/spi/spi-stm32-qspi.c
index 3b2a9a6b990d..42f8e3c6aa1f 100644
--- a/drivers/spi/spi-stm32-qspi.c
+++ b/drivers/spi/spi-stm32-qspi.c
@@ -5,6 +5,8 @@
  */
 #include <linux/bitfield.h>
 #include <linux/clk.h>
+#include <linux/dmaengine.h>
+#include <linux/dma-mapping.h>
 #include <linux/errno.h>
 #include <linux/io.h>
 #include <linux/iopoll.h>
@@ -13,6 +15,7 @@
 #include <linux/mutex.h>
 #include <linux/of.h>
 #include <linux/of_device.h>
+#include <linux/pinctrl/consumer.h>
 #include <linux/platform_device.h>
 #include <linux/reset.h>
 #include <linux/sizes.h>
@@ -76,7 +79,6 @@
 #define QSPI_PSMAR		0x28
 #define QSPI_PIR		0x2c
 #define QSPI_LPTR		0x30
-#define LPTR_DFT_TIMEOUT	0x10
 
 #define STM32_QSPI_MAX_MMAP_SZ	SZ_256M
 #define STM32_QSPI_MAX_NORCHIP	2
@@ -84,6 +86,7 @@
 #define STM32_FIFO_TIMEOUT_US 30000
 #define STM32_BUSY_TIMEOUT_US 100000
 #define STM32_ABT_TIMEOUT_US 100000
+#define STM32_COMP_TIMEOUT_MS 1000
 
 struct stm32_qspi_flash {
 	struct stm32_qspi *qspi;
@@ -93,6 +96,8 @@ struct stm32_qspi_flash {
 
 struct stm32_qspi {
 	struct device *dev;
+	struct spi_controller *ctrl;
+	phys_addr_t phys_base;
 	void __iomem *io_base;
 	void __iomem *mm_base;
 	resource_size_t mm_size;
@@ -102,6 +107,13 @@ struct stm32_qspi {
 	struct completion data_completion;
 	u32 fmode;
 
+	struct dma_chan *dma_chtx;
+	struct dma_chan *dma_chrx;
+	struct completion dma_completion;
+
+	u32 cr_reg;
+	u32 dcr_reg;
+
 	/*
 	 * to protect device configuration, could be different between
 	 * 2 flash access (bk1, bk2)
@@ -177,6 +189,81 @@ static int stm32_qspi_tx_mm(struct stm32_qspi *qspi,
 	return 0;
 }
 
+static void stm32_qspi_dma_callback(void *arg)
+{
+	struct completion *dma_completion = arg;
+
+	complete(dma_completion);
+}
+
+static int stm32_qspi_tx_dma(struct stm32_qspi *qspi,
+			     const struct spi_mem_op *op)
+{
+	struct dma_async_tx_descriptor *desc;
+	enum dma_transfer_direction dma_dir;
+	struct dma_chan *dma_ch;
+	struct sg_table sgt;
+	dma_cookie_t cookie;
+	u32 cr, t_out;
+	int err;
+
+	if (op->data.dir == SPI_MEM_DATA_IN) {
+		dma_dir = DMA_DEV_TO_MEM;
+		dma_ch = qspi->dma_chrx;
+	} else {
+		dma_dir = DMA_MEM_TO_DEV;
+		dma_ch = qspi->dma_chtx;
+	}
+
+	/*
+	 * spi_map_buf return -EINVAL if the buffer is not DMA-able
+	 * (DMA-able: in vmalloc | kmap | virt_addr_valid)
+	 */
+	err = spi_controller_dma_map_mem_op_data(qspi->ctrl, op, &sgt);
+	if (err)
+		return err;
+
+	desc = dmaengine_prep_slave_sg(dma_ch, sgt.sgl, sgt.nents,
+				       dma_dir, DMA_PREP_INTERRUPT);
+	if (!desc) {
+		err = -ENOMEM;
+		goto out_unmap;
+	}
+
+	cr = readl_relaxed(qspi->io_base + QSPI_CR);
+
+	reinit_completion(&qspi->dma_completion);
+	desc->callback = stm32_qspi_dma_callback;
+	desc->callback_param = &qspi->dma_completion;
+	cookie = dmaengine_submit(desc);
+	err = dma_submit_error(cookie);
+	if (err)
+		goto out;
+
+	dma_async_issue_pending(dma_ch);
+
+	writel_relaxed(cr | CR_DMAEN, qspi->io_base + QSPI_CR);
+
+	t_out = sgt.nents * STM32_COMP_TIMEOUT_MS;
+	if (!wait_for_completion_interruptible_timeout(&qspi->dma_completion,
+						       msecs_to_jiffies(t_out)))
+		err = -ETIMEDOUT;
+
+	if (dma_async_is_tx_complete(dma_ch, cookie,
+				     NULL, NULL) != DMA_COMPLETE)
+		err = -ETIMEDOUT;
+
+	if (err)
+		dmaengine_terminate_all(dma_ch);
+
+out:
+	writel_relaxed(cr & ~CR_DMAEN, qspi->io_base + QSPI_CR);
+out_unmap:
+	spi_controller_dma_unmap_mem_op_data(qspi->ctrl, op, &sgt);
+
+	return err;
+}
+
 static int stm32_qspi_tx(struct stm32_qspi *qspi, const struct spi_mem_op *op)
 {
 	if (!op->data.nbytes)
@@ -184,6 +271,10 @@ static int stm32_qspi_tx(struct stm32_qspi *qspi, const struct spi_mem_op *op)
 
 	if (qspi->fmode == CCR_FMODE_MM)
 		return stm32_qspi_tx_mm(qspi, op);
+	else if ((op->data.dir == SPI_MEM_DATA_IN && qspi->dma_chrx) ||
+		 (op->data.dir == SPI_MEM_DATA_OUT && qspi->dma_chtx))
+		if (!stm32_qspi_tx_dma(qspi, op))
+			return 0;
 
 	return stm32_qspi_tx_poll(qspi, op);
 }
@@ -214,7 +305,7 @@ static int stm32_qspi_wait_cmd(struct stm32_qspi *qspi,
 	writel_relaxed(cr | CR_TCIE | CR_TEIE, qspi->io_base + QSPI_CR);
 
 	if (!wait_for_completion_interruptible_timeout(&qspi->data_completion,
-						msecs_to_jiffies(1000))) {
+				msecs_to_jiffies(STM32_COMP_TIMEOUT_MS))) {
 		err = -ETIMEDOUT;
 	} else {
 		sr = readl_relaxed(qspi->io_base + QSPI_SR);
@@ -356,7 +447,7 @@ static int stm32_qspi_setup(struct spi_device *spi)
 	struct spi_controller *ctrl = spi->master;
 	struct stm32_qspi *qspi = spi_controller_get_devdata(ctrl);
 	struct stm32_qspi_flash *flash;
-	u32 cr, presc;
+	u32 presc;
 
 	if (ctrl->busy)
 		return -EBUSY;
@@ -372,17 +463,60 @@ static int stm32_qspi_setup(struct spi_device *spi)
 	flash->presc = presc;
 
 	mutex_lock(&qspi->lock);
-	writel_relaxed(LPTR_DFT_TIMEOUT, qspi->io_base + QSPI_LPTR);
-	cr = FIELD_PREP(CR_FTHRES_MASK, 3) | CR_TCEN | CR_SSHIFT | CR_EN;
-	writel_relaxed(cr, qspi->io_base + QSPI_CR);
+	qspi->cr_reg = FIELD_PREP(CR_FTHRES_MASK, 3) | CR_SSHIFT | CR_EN;
+	writel_relaxed(qspi->cr_reg, qspi->io_base + QSPI_CR);
 
 	/* set dcr fsize to max address */
-	writel_relaxed(DCR_FSIZE_MASK, qspi->io_base + QSPI_DCR);
+	qspi->dcr_reg = DCR_FSIZE_MASK;
+	writel_relaxed(qspi->dcr_reg, qspi->io_base + QSPI_DCR);
 	mutex_unlock(&qspi->lock);
 
 	return 0;
 }
 
+static void stm32_qspi_dma_setup(struct stm32_qspi *qspi)
+{
+	struct dma_slave_config dma_cfg;
+	struct device *dev = qspi->dev;
+
+	memset(&dma_cfg, 0, sizeof(dma_cfg));
+
+	dma_cfg.src_addr_width = DMA_SLAVE_BUSWIDTH_1_BYTE;
+	dma_cfg.dst_addr_width = DMA_SLAVE_BUSWIDTH_1_BYTE;
+	dma_cfg.src_addr = qspi->phys_base + QSPI_DR;
+	dma_cfg.dst_addr = qspi->phys_base + QSPI_DR;
+	dma_cfg.src_maxburst = 4;
+	dma_cfg.dst_maxburst = 4;
+
+	qspi->dma_chrx = dma_request_slave_channel(dev, "rx");
+	if (qspi->dma_chrx) {
+		if (dmaengine_slave_config(qspi->dma_chrx, &dma_cfg)) {
+			dev_err(dev, "dma rx config failed\n");
+			dma_release_channel(qspi->dma_chrx);
+			qspi->dma_chrx = NULL;
+		}
+	}
+
+	qspi->dma_chtx = dma_request_slave_channel(dev, "tx");
+	if (qspi->dma_chtx) {
+		if (dmaengine_slave_config(qspi->dma_chtx, &dma_cfg)) {
+			dev_err(dev, "dma tx config failed\n");
+			dma_release_channel(qspi->dma_chtx);
+			qspi->dma_chtx = NULL;
+		}
+	}
+
+	init_completion(&qspi->dma_completion);
+}
+
+static void stm32_qspi_dma_free(struct stm32_qspi *qspi)
+{
+	if (qspi->dma_chtx)
+		dma_release_channel(qspi->dma_chtx);
+	if (qspi->dma_chrx)
+		dma_release_channel(qspi->dma_chrx);
+}
+
 /*
  * no special host constraint, so use default spi_mem_default_supports_op
  * to check supported mode.
@@ -395,8 +529,10 @@ static void stm32_qspi_release(struct stm32_qspi *qspi)
 {
 	/* disable qspi */
 	writel_relaxed(0, qspi->io_base + QSPI_CR);
+	stm32_qspi_dma_free(qspi);
 	mutex_destroy(&qspi->lock);
 	clk_disable_unprepare(qspi->clk);
+	spi_master_put(qspi->ctrl);
 }
 
 static int stm32_qspi_probe(struct platform_device *pdev)
@@ -413,43 +549,62 @@ static int stm32_qspi_probe(struct platform_device *pdev)
 		return -ENOMEM;
 
 	qspi = spi_controller_get_devdata(ctrl);
+	qspi->ctrl = ctrl;
 
 	res = platform_get_resource_byname(pdev, IORESOURCE_MEM, "qspi");
 	qspi->io_base = devm_ioremap_resource(dev, res);
-	if (IS_ERR(qspi->io_base))
-		return PTR_ERR(qspi->io_base);
+	if (IS_ERR(qspi->io_base)) {
+		ret = PTR_ERR(qspi->io_base);
+		goto err;
+	}
+
+	qspi->phys_base = res->start;
 
 	res = platform_get_resource_byname(pdev, IORESOURCE_MEM, "qspi_mm");
 	qspi->mm_base = devm_ioremap_resource(dev, res);
-	if (IS_ERR(qspi->mm_base))
-		return PTR_ERR(qspi->mm_base);
+	if (IS_ERR(qspi->mm_base)) {
+		ret = PTR_ERR(qspi->mm_base);
+		goto err;
+	}
 
 	qspi->mm_size = resource_size(res);
-	if (qspi->mm_size > STM32_QSPI_MAX_MMAP_SZ)
-		return -EINVAL;
+	if (qspi->mm_size > STM32_QSPI_MAX_MMAP_SZ) {
+		ret = -EINVAL;
+		goto err;
+	}
 
 	irq = platform_get_irq(pdev, 0);
+	if (irq < 0) {
+		if (irq != -EPROBE_DEFER)
+			dev_err(dev, "IRQ error missing or invalid\n");
+		return irq;
+	}
+
 	ret = devm_request_irq(dev, irq, stm32_qspi_irq, 0,
 			       dev_name(dev), qspi);
 	if (ret) {
 		dev_err(dev, "failed to request irq\n");
-		return ret;
+		goto err;
 	}
 
 	init_completion(&qspi->data_completion);
 
 	qspi->clk = devm_clk_get(dev, NULL);
-	if (IS_ERR(qspi->clk))
-		return PTR_ERR(qspi->clk);
+	if (IS_ERR(qspi->clk)) {
+		ret = PTR_ERR(qspi->clk);
+		goto err;
+	}
 
 	qspi->clk_rate = clk_get_rate(qspi->clk);
-	if (!qspi->clk_rate)
-		return -EINVAL;
+	if (!qspi->clk_rate) {
+		ret = -EINVAL;
+		goto err;
+	}
 
 	ret = clk_prepare_enable(qspi->clk);
 	if (ret) {
 		dev_err(dev, "can not enable the clock\n");
-		return ret;
+		goto err;
 	}
 
 	rstc = devm_reset_control_get_exclusive(dev, NULL);
@@ -461,6 +616,7 @@ static int stm32_qspi_probe(struct platform_device *pdev)
 
 	qspi->dev = dev;
 	platform_set_drvdata(pdev, qspi);
+	stm32_qspi_dma_setup(qspi);
 	mutex_init(&qspi->lock);
 
 	ctrl->mode_bits = SPI_RX_DUAL | SPI_RX_QUAD
@@ -472,14 +628,11 @@ static int stm32_qspi_probe(struct platform_device *pdev)
 	ctrl->dev.of_node = dev->of_node;
 
 	ret = devm_spi_register_master(dev, ctrl);
-	if (ret)
-		goto err_spi_register;
-
-	return 0;
+	if (!ret)
+		return 0;
 
-err_spi_register:
+err:
 	stm32_qspi_release(qspi);
-
 	return ret;
 }
 
@@ -491,6 +644,31 @@ static int stm32_qspi_remove(struct platform_device *pdev)
 	return 0;
 }
 
+static int __maybe_unused stm32_qspi_suspend(struct device *dev)
+{
+	struct stm32_qspi *qspi = dev_get_drvdata(dev);
+
+	clk_disable_unprepare(qspi->clk);
+	pinctrl_pm_select_sleep_state(dev);
+
+	return 0;
+}
+
+static int __maybe_unused stm32_qspi_resume(struct device *dev)
+{
+	struct stm32_qspi *qspi = dev_get_drvdata(dev);
+
+	pinctrl_pm_select_default_state(dev);
+	clk_prepare_enable(qspi->clk);
+
+	writel_relaxed(qspi->cr_reg, qspi->io_base + QSPI_CR);
+	writel_relaxed(qspi->dcr_reg, qspi->io_base + QSPI_DCR);
+
+	return 0;
+}
+
+static SIMPLE_DEV_PM_OPS(stm32_qspi_pm_ops, stm32_qspi_suspend, stm32_qspi_resume);
+
 static const struct of_device_id stm32_qspi_match[] = {
 	{.compatible = "st,stm32f469-qspi"},
 	{}
@@ -503,6 +681,7 @@ static struct platform_driver stm32_qspi_driver = {
 	.driver	= {
 		.name = "stm32-qspi",
 		.of_match_table = stm32_qspi_match,
+		.pm = &stm32_qspi_pm_ops,
 	},
 };
 module_platform_driver(stm32_qspi_driver);
diff --git a/drivers/spi/spi-stm32.c b/drivers/spi/spi-stm32.c
index 4186ed20d796..b222ce8d083e 100644
--- a/drivers/spi/spi-stm32.c
+++ b/drivers/spi/spi-stm32.c
@@ -1839,8 +1839,9 @@ static int stm32_spi_probe(struct platform_device *pdev)
 
 	spi->irq = platform_get_irq(pdev, 0);
 	if (spi->irq <= 0) {
-		dev_err(&pdev->dev, "no irq: %d\n", spi->irq);
-		ret = -ENOENT;
+		ret = spi->irq;
+		if (ret != -EPROBE_DEFER)
+			dev_err(&pdev->dev, "failed to get irq: %d\n", ret);
 		goto err_master_put;
 	}
 	ret = devm_request_threaded_irq(&pdev->dev, spi->irq,
diff --git a/drivers/spi/spi-tegra114.c b/drivers/spi/spi-tegra114.c
index a76acedd7e2f..b1f31bb16659 100644
--- a/drivers/spi/spi-tegra114.c
+++ b/drivers/spi/spi-tegra114.c
@@ -149,6 +149,8 @@
 
 #define SPI_TX_FIFO				0x108
 #define SPI_RX_FIFO				0x188
+#define SPI_INTR_MASK				0x18c
+#define SPI_INTR_ALL_MASK			(0x1fUL << 25)
 #define MAX_CHIP_SELECT				4
 #define SPI_FIFO_DEPTH				64
 #define DATA_DIR_TX				(1 << 0)
@@ -161,6 +163,10 @@
 #define MAX_HOLD_CYCLES				16
 #define SPI_DEFAULT_SPEED			25000000
 
+struct tegra_spi_soc_data {
+	bool has_intr_mask_reg;
+};
+
 struct tegra_spi_data {
 	struct device				*dev;
 	struct spi_master			*master;
@@ -211,6 +217,7 @@ struct tegra_spi_data {
 	u32					*tx_dma_buf;
 	dma_addr_t				tx_dma_phys;
 	struct dma_async_tx_descriptor		*tx_dma_desc;
+	const struct tegra_spi_soc_data		*soc_data;
 };
 
 static int tegra_spi_runtime_suspend(struct device *dev);
@@ -259,7 +266,8 @@ static unsigned tegra_spi_calculate_curr_xfer_param(
 
 	tspi->bytes_per_word = DIV_ROUND_UP(bits_per_word, 8);
 
-	if (bits_per_word == 8 || bits_per_word == 16) {
+	if ((bits_per_word == 8 || bits_per_word == 16 ||
+	     bits_per_word == 32) && t->len > 3) {
 		tspi->is_packed = 1;
 		tspi->words_per_32bit = 32/bits_per_word;
 	} else {
@@ -307,10 +315,16 @@ static unsigned tegra_spi_fill_tx_fifo_from_client_txbuf(
 				x |= (u32)(*tx_buf++) << (i * 8);
 			tegra_spi_writel(tspi, x, SPI_TX_FIFO);
 		}
+
+		tspi->cur_tx_pos += written_words * tspi->bytes_per_word;
 	} else {
+		unsigned int write_bytes;
 		max_n_32bit = min(tspi->curr_dma_words,  tx_empty_count);
 		written_words = max_n_32bit;
 		nbytes = written_words * tspi->bytes_per_word;
+		if (nbytes > t->len - tspi->cur_pos)
+			nbytes = t->len - tspi->cur_pos;
+		write_bytes = nbytes;
 		for (count = 0; count < max_n_32bit; count++) {
 			u32 x = 0;
 
@@ -319,8 +333,10 @@ static unsigned tegra_spi_fill_tx_fifo_from_client_txbuf(
 				x |= (u32)(*tx_buf++) << (i * 8);
 			tegra_spi_writel(tspi, x, SPI_TX_FIFO);
 		}
+
+		tspi->cur_tx_pos += write_bytes;
 	}
-	tspi->cur_tx_pos += written_words * tspi->bytes_per_word;
+
 	return written_words;
 }
 
@@ -344,20 +360,27 @@ static unsigned int tegra_spi_read_rx_fifo_to_client_rxbuf(
 			for (i = 0; len && (i < 4); i++, len--)
 				*rx_buf++ = (x >> i*8) & 0xFF;
 		}
-		tspi->cur_rx_pos += tspi->curr_dma_words * tspi->bytes_per_word;
 		read_words += tspi->curr_dma_words;
+		tspi->cur_rx_pos += tspi->curr_dma_words * tspi->bytes_per_word;
 	} else {
 		u32 rx_mask = ((u32)1 << t->bits_per_word) - 1;
+		u8 bytes_per_word = tspi->bytes_per_word;
+		unsigned int read_bytes;
 
+		len = rx_full_count * bytes_per_word;
+		if (len > t->len - tspi->cur_pos)
+			len = t->len - tspi->cur_pos;
+		read_bytes = len;
 		for (count = 0; count < rx_full_count; count++) {
 			u32 x = tegra_spi_readl(tspi, SPI_RX_FIFO) & rx_mask;
 
-			for (i = 0; (i < tspi->bytes_per_word); i++)
+			for (i = 0; len && (i < bytes_per_word); i++, len--)
 				*rx_buf++ = (x >> (i*8)) & 0xFF;
 		}
-		tspi->cur_rx_pos += rx_full_count * tspi->bytes_per_word;
 		read_words += rx_full_count;
+		tspi->cur_rx_pos += read_bytes;
 	}
+
 	return read_words;
 }
 
@@ -372,12 +395,17 @@ static void tegra_spi_copy_client_txbuf_to_spi_txbuf(
 		unsigned len = tspi->curr_dma_words * tspi->bytes_per_word;
 
 		memcpy(tspi->tx_dma_buf, t->tx_buf + tspi->cur_pos, len);
+		tspi->cur_tx_pos += tspi->curr_dma_words * tspi->bytes_per_word;
 	} else {
 		unsigned int i;
 		unsigned int count;
 		u8 *tx_buf = (u8 *)t->tx_buf + tspi->cur_tx_pos;
 		unsigned consume = tspi->curr_dma_words * tspi->bytes_per_word;
+		unsigned int write_bytes;
 
+		if (consume > t->len - tspi->cur_pos)
+			consume = t->len - tspi->cur_pos;
+		write_bytes = consume;
 		for (count = 0; count < tspi->curr_dma_words; count++) {
 			u32 x = 0;
 
@@ -386,8 +414,9 @@ static void tegra_spi_copy_client_txbuf_to_spi_txbuf(
 				x |= (u32)(*tx_buf++) << (i * 8);
 			tspi->tx_dma_buf[count] = x;
 		}
+
+		tspi->cur_tx_pos += write_bytes;
 	}
-	tspi->cur_tx_pos += tspi->curr_dma_words * tspi->bytes_per_word;
 
 	/* Make the dma buffer to read by dma */
 	dma_sync_single_for_device(tspi->dev, tspi->tx_dma_phys,
@@ -405,20 +434,28 @@ static void tegra_spi_copy_spi_rxbuf_to_client_rxbuf(
 		unsigned len = tspi->curr_dma_words * tspi->bytes_per_word;
 
 		memcpy(t->rx_buf + tspi->cur_rx_pos, tspi->rx_dma_buf, len);
+		tspi->cur_rx_pos += tspi->curr_dma_words * tspi->bytes_per_word;
 	} else {
 		unsigned int i;
 		unsigned int count;
 		unsigned char *rx_buf = t->rx_buf + tspi->cur_rx_pos;
 		u32 rx_mask = ((u32)1 << t->bits_per_word) - 1;
+		unsigned consume = tspi->curr_dma_words * tspi->bytes_per_word;
+		unsigned int read_bytes;
 
+		if (consume > t->len - tspi->cur_pos)
+			consume = t->len - tspi->cur_pos;
+		read_bytes = consume;
 		for (count = 0; count < tspi->curr_dma_words; count++) {
 			u32 x = tspi->rx_dma_buf[count] & rx_mask;
 
-			for (i = 0; (i < tspi->bytes_per_word); i++)
+			for (i = 0; consume && (i < tspi->bytes_per_word);
+							i++, consume--)
 				*rx_buf++ = (x >> (i*8)) & 0xFF;
 		}
+
+		tspi->cur_rx_pos += read_bytes;
 	}
-	tspi->cur_rx_pos += tspi->curr_dma_words * tspi->bytes_per_word;
 
 	/* Make the dma buffer to read by dma */
 	dma_sync_single_for_device(tspi->dev, tspi->rx_dma_phys,
@@ -470,22 +507,39 @@ static int tegra_spi_start_rx_dma(struct tegra_spi_data *tspi, int len)
 	return 0;
 }
 
-static int tegra_spi_start_dma_based_transfer(
-		struct tegra_spi_data *tspi, struct spi_transfer *t)
+static int tegra_spi_flush_fifos(struct tegra_spi_data *tspi)
 {
-	u32 val;
-	unsigned int len;
-	int ret = 0;
+	unsigned long timeout = jiffies + HZ;
 	u32 status;
 
-	/* Make sure that Rx and Tx fifo are empty */
 	status = tegra_spi_readl(tspi, SPI_FIFO_STATUS);
 	if ((status & SPI_FIFO_EMPTY) != SPI_FIFO_EMPTY) {
-		dev_err(tspi->dev, "Rx/Tx fifo are not empty status 0x%08x\n",
-			(unsigned)status);
-		return -EIO;
+		status |= SPI_RX_FIFO_FLUSH | SPI_TX_FIFO_FLUSH;
+		tegra_spi_writel(tspi, status, SPI_FIFO_STATUS);
+		while ((status & SPI_FIFO_EMPTY) != SPI_FIFO_EMPTY) {
+			status = tegra_spi_readl(tspi, SPI_FIFO_STATUS);
+			if (time_after(jiffies, timeout)) {
+				dev_err(tspi->dev,
+					"timeout waiting for fifo flush\n");
+				return -EIO;
+			}
+
+			udelay(1);
+		}
 	}
 
+	return 0;
+}
+
+static int tegra_spi_start_dma_based_transfer(
+		struct tegra_spi_data *tspi, struct spi_transfer *t)
+{
+	u32 val;
+	unsigned int len;
+	int ret = 0;
+	u8 dma_burst;
+	struct dma_slave_config dma_sconfig = {0};
+
 	val = SPI_DMA_BLK_SET(tspi->curr_dma_words - 1);
 	tegra_spi_writel(tspi, val, SPI_DMA_BLK);
 
@@ -496,23 +550,40 @@ static int tegra_spi_start_dma_based_transfer(
 		len = tspi->curr_dma_words * 4;
 
 	/* Set attention level based on length of transfer */
-	if (len & 0xF)
+	if (len & 0xF) {
 		val |= SPI_TX_TRIG_1 | SPI_RX_TRIG_1;
-	else if (((len) >> 4) & 0x1)
+		dma_burst = 1;
+	} else if (((len) >> 4) & 0x1) {
 		val |= SPI_TX_TRIG_4 | SPI_RX_TRIG_4;
-	else
+		dma_burst = 4;
+	} else {
 		val |= SPI_TX_TRIG_8 | SPI_RX_TRIG_8;
+		dma_burst = 8;
+	}
 
-	if (tspi->cur_direction & DATA_DIR_TX)
-		val |= SPI_IE_TX;
+	if (!tspi->soc_data->has_intr_mask_reg) {
+		if (tspi->cur_direction & DATA_DIR_TX)
+			val |= SPI_IE_TX;
 
-	if (tspi->cur_direction & DATA_DIR_RX)
-		val |= SPI_IE_RX;
+		if (tspi->cur_direction & DATA_DIR_RX)
+			val |= SPI_IE_RX;
+	}
 
 	tegra_spi_writel(tspi, val, SPI_DMA_CTL);
 	tspi->dma_control_reg = val;
 
+	dma_sconfig.device_fc = true;
 	if (tspi->cur_direction & DATA_DIR_TX) {
+		dma_sconfig.dst_addr = tspi->phys + SPI_TX_FIFO;
+		dma_sconfig.dst_addr_width = DMA_SLAVE_BUSWIDTH_4_BYTES;
+		dma_sconfig.dst_maxburst = dma_burst;
+		ret = dmaengine_slave_config(tspi->tx_dma_chan, &dma_sconfig);
+		if (ret < 0) {
+			dev_err(tspi->dev,
+				"DMA slave config failed: %d\n", ret);
+			return ret;
+		}
+
 		tegra_spi_copy_client_txbuf_to_spi_txbuf(tspi, t);
 		ret = tegra_spi_start_tx_dma(tspi, len);
 		if (ret < 0) {
@@ -523,6 +594,16 @@ static int tegra_spi_start_dma_based_transfer(
 	}
 
 	if (tspi->cur_direction & DATA_DIR_RX) {
+		dma_sconfig.src_addr = tspi->phys + SPI_RX_FIFO;
+		dma_sconfig.src_addr_width = DMA_SLAVE_BUSWIDTH_4_BYTES;
+		dma_sconfig.src_maxburst = dma_burst;
+		ret = dmaengine_slave_config(tspi->rx_dma_chan, &dma_sconfig);
+		if (ret < 0) {
+			dev_err(tspi->dev,
+				"DMA slave config failed: %d\n", ret);
+			return ret;
+		}
+
 		/* Make the dma buffer to read by dma */
 		dma_sync_single_for_device(tspi->dev, tspi->rx_dma_phys,
 				tspi->dma_buf_size, DMA_FROM_DEVICE);
@@ -570,8 +651,9 @@ static int tegra_spi_start_cpu_based_transfer(
 
 	tspi->is_curr_dma_xfer = false;
 
-	val |= SPI_DMA_EN;
-	tegra_spi_writel(tspi, val, SPI_DMA_CTL);
+	val = tspi->command1_reg;
+	val |= SPI_PIO;
+	tegra_spi_writel(tspi, val, SPI_COMMAND1);
 	return 0;
 }
 
@@ -582,7 +664,6 @@ static int tegra_spi_init_dma_param(struct tegra_spi_data *tspi,
 	u32 *dma_buf;
 	dma_addr_t dma_phys;
 	int ret;
-	struct dma_slave_config dma_sconfig;
 
 	dma_chan = dma_request_slave_channel_reason(tspi->dev,
 					dma_to_memory ? "rx" : "tx");
@@ -603,19 +684,6 @@ static int tegra_spi_init_dma_param(struct tegra_spi_data *tspi,
 	}
 
 	if (dma_to_memory) {
-		dma_sconfig.src_addr = tspi->phys + SPI_RX_FIFO;
-		dma_sconfig.src_addr_width = DMA_SLAVE_BUSWIDTH_4_BYTES;
-		dma_sconfig.src_maxburst = 0;
-	} else {
-		dma_sconfig.dst_addr = tspi->phys + SPI_TX_FIFO;
-		dma_sconfig.dst_addr_width = DMA_SLAVE_BUSWIDTH_4_BYTES;
-		dma_sconfig.dst_maxburst = 0;
-	}
-
-	ret = dmaengine_slave_config(dma_chan, &dma_sconfig);
-	if (ret)
-		goto scrub;
-	if (dma_to_memory) {
 		tspi->rx_dma_chan = dma_chan;
 		tspi->rx_dma_buf = dma_buf;
 		tspi->rx_dma_phys = dma_phys;
@@ -625,11 +693,6 @@ static int tegra_spi_init_dma_param(struct tegra_spi_data *tspi,
 		tspi->tx_dma_phys = dma_phys;
 	}
 	return 0;
-
-scrub:
-	dma_free_coherent(tspi->dev, tspi->dma_buf_size, dma_buf, dma_phys);
-	dma_release_channel(dma_chan);
-	return ret;
 }
 
 static void tegra_spi_deinit_dma_param(struct tegra_spi_data *tspi,
@@ -696,6 +759,16 @@ static u32 tegra_spi_setup_transfer_one(struct spi_device *spi,
 		else if (req_mode == SPI_MODE_3)
 			command1 |= SPI_CONTROL_MODE_3;
 
+		if (spi->mode & SPI_LSB_FIRST)
+			command1 |= SPI_LSBIT_FE;
+		else
+			command1 &= ~SPI_LSBIT_FE;
+
+		if (spi->mode & SPI_3WIRE)
+			command1 |= SPI_BIDIROE;
+		else
+			command1 &= ~SPI_BIDIROE;
+
 		if (tspi->cs_control) {
 			if (tspi->cs_control != spi)
 				tegra_spi_writel(tspi, command1, SPI_COMMAND1);
@@ -728,8 +801,15 @@ static int tegra_spi_start_transfer_one(struct spi_device *spi,
 
 	total_fifo_words = tegra_spi_calculate_curr_xfer_param(spi, tspi, t);
 
+	if (t->rx_nbits == SPI_NBITS_DUAL || t->tx_nbits == SPI_NBITS_DUAL)
+		command1 |= SPI_BOTH_EN_BIT;
+	else
+		command1 &= ~SPI_BOTH_EN_BIT;
+
 	if (tspi->is_packed)
 		command1 |= SPI_PACKED;
+	else
+		command1 &= ~SPI_PACKED;
 
 	command1 &= ~(SPI_CS_SEL_MASK | SPI_TX_EN | SPI_RX_EN);
 	tspi->cur_direction = 0;
@@ -748,6 +828,9 @@ static int tegra_spi_start_transfer_one(struct spi_device *spi,
 	dev_dbg(tspi->dev, "The def 0x%x and written 0x%x\n",
 		tspi->def_command1_reg, (unsigned)command1);
 
+	ret = tegra_spi_flush_fifos(tspi);
+	if (ret < 0)
+		return ret;
 	if (total_fifo_words > SPI_FIFO_DEPTH)
 		ret = tegra_spi_start_dma_based_transfer(tspi, t);
 	else
@@ -774,6 +857,12 @@ static int tegra_spi_setup(struct spi_device *spi)
 		return ret;
 	}
 
+	if (tspi->soc_data->has_intr_mask_reg) {
+		val = tegra_spi_readl(tspi, SPI_INTR_MASK);
+		val &= ~SPI_INTR_ALL_MASK;
+		tegra_spi_writel(tspi, val, SPI_INTR_MASK);
+	}
+
 	spin_lock_irqsave(&tspi->lock, flags);
 	val = tspi->def_command1_reg;
 	if (spi->mode & SPI_CS_HIGH)
@@ -799,6 +888,33 @@ static void tegra_spi_transfer_delay(int delay)
 	udelay(delay % 1000);
 }
 
+static void tegra_spi_transfer_end(struct spi_device *spi)
+{
+	struct tegra_spi_data *tspi = spi_master_get_devdata(spi->master);
+	int cs_val = (spi->mode & SPI_CS_HIGH) ? 0 : 1;
+
+	if (cs_val)
+		tspi->command1_reg |= SPI_CS_SW_VAL;
+	else
+		tspi->command1_reg &= ~SPI_CS_SW_VAL;
+	tegra_spi_writel(tspi, tspi->command1_reg, SPI_COMMAND1);
+	tegra_spi_writel(tspi, tspi->def_command1_reg, SPI_COMMAND1);
+}
+
+static void tegra_spi_dump_regs(struct tegra_spi_data *tspi)
+{
+	dev_dbg(tspi->dev, "============ SPI REGISTER DUMP ============\n");
+	dev_dbg(tspi->dev, "Command1:    0x%08x | Command2:    0x%08x\n",
+		tegra_spi_readl(tspi, SPI_COMMAND1),
+		tegra_spi_readl(tspi, SPI_COMMAND2));
+	dev_dbg(tspi->dev, "DMA_CTL:     0x%08x | DMA_BLK:     0x%08x\n",
+		tegra_spi_readl(tspi, SPI_DMA_CTL),
+		tegra_spi_readl(tspi, SPI_DMA_BLK));
+	dev_dbg(tspi->dev, "TRANS_STAT:  0x%08x | FIFO_STATUS: 0x%08x\n",
+		tegra_spi_readl(tspi, SPI_TRANS_STATUS),
+		tegra_spi_readl(tspi, SPI_FIFO_STATUS));
+}
+
 static int tegra_spi_transfer_one_message(struct spi_master *master,
 			struct spi_message *msg)
 {
@@ -838,21 +954,32 @@ static int tegra_spi_transfer_one_message(struct spi_master *master,
 		if (WARN_ON(ret == 0)) {
 			dev_err(tspi->dev,
 				"spi transfer timeout, err %d\n", ret);
+			if (tspi->is_curr_dma_xfer &&
+			    (tspi->cur_direction & DATA_DIR_TX))
+				dmaengine_terminate_all(tspi->tx_dma_chan);
+			if (tspi->is_curr_dma_xfer &&
+			    (tspi->cur_direction & DATA_DIR_RX))
+				dmaengine_terminate_all(tspi->rx_dma_chan);
 			ret = -EIO;
+			tegra_spi_dump_regs(tspi);
+			tegra_spi_flush_fifos(tspi);
+			reset_control_assert(tspi->rst);
+			udelay(2);
+			reset_control_deassert(tspi->rst);
 			goto complete_xfer;
 		}
 
 		if (tspi->tx_status ||  tspi->rx_status) {
 			dev_err(tspi->dev, "Error in Transfer\n");
 			ret = -EIO;
+			tegra_spi_dump_regs(tspi);
 			goto complete_xfer;
 		}
 		msg->actual_length += xfer->len;
 
 complete_xfer:
 		if (ret < 0 || skip) {
-			tegra_spi_writel(tspi, tspi->def_command1_reg,
-					SPI_COMMAND1);
+			tegra_spi_transfer_end(spi);
 			tegra_spi_transfer_delay(xfer->delay_usecs);
 			goto exit;
 		} else if (list_is_last(&xfer->transfer_list,
@@ -860,13 +987,11 @@ complete_xfer:
 			if (xfer->cs_change)
 				tspi->cs_control = spi;
 			else {
-				tegra_spi_writel(tspi, tspi->def_command1_reg,
-						SPI_COMMAND1);
+				tegra_spi_transfer_end(spi);
 				tegra_spi_transfer_delay(xfer->delay_usecs);
 			}
 		} else if (xfer->cs_change) {
-			tegra_spi_writel(tspi, tspi->def_command1_reg,
-					SPI_COMMAND1);
+			tegra_spi_transfer_end(spi);
 			tegra_spi_transfer_delay(xfer->delay_usecs);
 		}
 
@@ -889,11 +1014,14 @@ static irqreturn_t handle_cpu_based_xfer(struct tegra_spi_data *tspi)
 			tspi->status_reg);
 		dev_err(tspi->dev, "CpuXfer 0x%08x:0x%08x\n",
 			tspi->command1_reg, tspi->dma_control_reg);
+		tegra_spi_dump_regs(tspi);
+		tegra_spi_flush_fifos(tspi);
+		complete(&tspi->xfer_completion);
+		spin_unlock_irqrestore(&tspi->lock, flags);
 		reset_control_assert(tspi->rst);
 		udelay(2);
 		reset_control_deassert(tspi->rst);
-		complete(&tspi->xfer_completion);
-		goto exit;
+		return IRQ_HANDLED;
 	}
 
 	if (tspi->cur_direction & DATA_DIR_RX)
@@ -961,11 +1089,13 @@ static irqreturn_t handle_dma_based_xfer(struct tegra_spi_data *tspi)
 			tspi->status_reg);
 		dev_err(tspi->dev, "DmaXfer 0x%08x:0x%08x\n",
 			tspi->command1_reg, tspi->dma_control_reg);
+		tegra_spi_dump_regs(tspi);
+		tegra_spi_flush_fifos(tspi);
+		complete(&tspi->xfer_completion);
+		spin_unlock_irqrestore(&tspi->lock, flags);
 		reset_control_assert(tspi->rst);
 		udelay(2);
 		reset_control_deassert(tspi->rst);
-		complete(&tspi->xfer_completion);
-		spin_unlock_irqrestore(&tspi->lock, flags);
 		return IRQ_HANDLED;
 	}
 
@@ -1021,8 +1151,29 @@ static irqreturn_t tegra_spi_isr(int irq, void *context_data)
 	return IRQ_WAKE_THREAD;
 }
 
+static struct tegra_spi_soc_data tegra114_spi_soc_data = {
+	.has_intr_mask_reg = false,
+};
+
+static struct tegra_spi_soc_data tegra124_spi_soc_data = {
+	.has_intr_mask_reg = false,
+};
+
+static struct tegra_spi_soc_data tegra210_spi_soc_data = {
+	.has_intr_mask_reg = true,
+};
+
 static const struct of_device_id tegra_spi_of_match[] = {
-	{ .compatible = "nvidia,tegra114-spi", },
+	{
+		.compatible = "nvidia,tegra114-spi",
+		.data	    = &tegra114_spi_soc_data,
+	}, {
+		.compatible = "nvidia,tegra124-spi",
+		.data	    = &tegra124_spi_soc_data,
+	}, {
+		.compatible = "nvidia,tegra210-spi",
+		.data	    = &tegra210_spi_soc_data,
+	},
 	{}
 };
 MODULE_DEVICE_TABLE(of, tegra_spi_of_match);
@@ -1033,6 +1184,7 @@ static int tegra_spi_probe(struct platform_device *pdev)
 	struct tegra_spi_data	*tspi;
 	struct resource		*r;
 	int ret, spi_irq;
+	int bus_num;
 
 	master = spi_alloc_master(&pdev->dev, sizeof(*tspi));
 	if (!master) {
@@ -1047,16 +1199,28 @@ static int tegra_spi_probe(struct platform_device *pdev)
 		master->max_speed_hz = 25000000; /* 25MHz */
 
 	/* the spi->mode bits understood by this driver: */
-	master->mode_bits = SPI_CPOL | SPI_CPHA | SPI_CS_HIGH;
+	master->mode_bits = SPI_CPOL | SPI_CPHA | SPI_CS_HIGH | SPI_LSB_FIRST |
+			    SPI_TX_DUAL | SPI_RX_DUAL | SPI_3WIRE;
+	master->bits_per_word_mask = SPI_BPW_RANGE_MASK(4, 32);
 	master->setup = tegra_spi_setup;
 	master->transfer_one_message = tegra_spi_transfer_one_message;
 	master->num_chipselect = MAX_CHIP_SELECT;
 	master->auto_runtime_pm = true;
+	bus_num = of_alias_get_id(pdev->dev.of_node, "spi");
+	if (bus_num >= 0)
+		master->bus_num = bus_num;
 
 	tspi->master = master;
 	tspi->dev = &pdev->dev;
 	spin_lock_init(&tspi->lock);
 
+	tspi->soc_data = of_device_get_match_data(&pdev->dev);
+	if (!tspi->soc_data) {
+		dev_err(&pdev->dev, "unsupported tegra\n");
+		ret = -ENODEV;
+		goto exit_free_master;
+	}
+
 	r = platform_get_resource(pdev, IORESOURCE_MEM, 0);
 	tspi->base = devm_ioremap_resource(&pdev->dev, r);
 	if (IS_ERR(tspi->base)) {
@@ -1067,27 +1231,19 @@ static int tegra_spi_probe(struct platform_device *pdev)
 
 	spi_irq = platform_get_irq(pdev, 0);
 	tspi->irq = spi_irq;
-	ret = request_threaded_irq(tspi->irq, tegra_spi_isr,
-			tegra_spi_isr_thread, IRQF_ONESHOT,
-			dev_name(&pdev->dev), tspi);
-	if (ret < 0) {
-		dev_err(&pdev->dev, "Failed to register ISR for IRQ %d\n",
-					tspi->irq);
-		goto exit_free_master;
-	}
 
 	tspi->clk = devm_clk_get(&pdev->dev, "spi");
 	if (IS_ERR(tspi->clk)) {
 		dev_err(&pdev->dev, "can not get clock\n");
 		ret = PTR_ERR(tspi->clk);
-		goto exit_free_irq;
+		goto exit_free_master;
 	}
 
 	tspi->rst = devm_reset_control_get_exclusive(&pdev->dev, "spi");
 	if (IS_ERR(tspi->rst)) {
 		dev_err(&pdev->dev, "can not get reset\n");
 		ret = PTR_ERR(tspi->rst);
-		goto exit_free_irq;
+		goto exit_free_master;
 	}
 
 	tspi->max_buf_size = SPI_FIFO_DEPTH << 2;
@@ -1095,7 +1251,7 @@ static int tegra_spi_probe(struct platform_device *pdev)
 
 	ret = tegra_spi_init_dma_param(tspi, true);
 	if (ret < 0)
-		goto exit_free_irq;
+		goto exit_free_master;
 	ret = tegra_spi_init_dma_param(tspi, false);
 	if (ret < 0)
 		goto exit_rx_dma_free;
@@ -1117,18 +1273,32 @@ static int tegra_spi_probe(struct platform_device *pdev)
 		dev_err(&pdev->dev, "pm runtime get failed, e = %d\n", ret);
 		goto exit_pm_disable;
 	}
+
+	reset_control_assert(tspi->rst);
+	udelay(2);
+	reset_control_deassert(tspi->rst);
 	tspi->def_command1_reg  = SPI_M_S;
 	tegra_spi_writel(tspi, tspi->def_command1_reg, SPI_COMMAND1);
 	pm_runtime_put(&pdev->dev);
+	ret = request_threaded_irq(tspi->irq, tegra_spi_isr,
+				   tegra_spi_isr_thread, IRQF_ONESHOT,
+				   dev_name(&pdev->dev), tspi);
+	if (ret < 0) {
+		dev_err(&pdev->dev, "Failed to register ISR for IRQ %d\n",
+			tspi->irq);
+		goto exit_pm_disable;
+	}
 
 	master->dev.of_node = pdev->dev.of_node;
 	ret = devm_spi_register_master(&pdev->dev, master);
 	if (ret < 0) {
 		dev_err(&pdev->dev, "can not register to master err %d\n", ret);
-		goto exit_pm_disable;
+		goto exit_free_irq;
 	}
 	return ret;
 
+exit_free_irq:
+	free_irq(spi_irq, tspi);
 exit_pm_disable:
 	pm_runtime_disable(&pdev->dev);
 	if (!pm_runtime_status_suspended(&pdev->dev))
@@ -1136,8 +1306,6 @@ exit_pm_disable:
 	tegra_spi_deinit_dma_param(tspi, false);
 exit_rx_dma_free:
 	tegra_spi_deinit_dma_param(tspi, true);
-exit_free_irq:
-	free_irq(spi_irq, tspi);
 exit_free_master:
 	spi_master_put(master);
 	return ret;
diff --git a/drivers/spi/spi-tegra20-slink.c b/drivers/spi/spi-tegra20-slink.c
index 1427f343b39a..6d4679126213 100644
--- a/drivers/spi/spi-tegra20-slink.c
+++ b/drivers/spi/spi-tegra20-slink.c
@@ -717,9 +717,6 @@ static int tegra_slink_start_transfer_one(struct spi_device *spi,
 	command2 = tspi->command2_reg;
 	command2 &= ~(SLINK_RXEN | SLINK_TXEN);
 
-	tegra_slink_writel(tspi, command, SLINK_COMMAND);
-	tspi->command_reg = command;
-
 	tspi->cur_direction = 0;
 	if (t->rx_buf) {
 		command2 |= SLINK_RXEN;
@@ -729,9 +726,18 @@ static int tegra_slink_start_transfer_one(struct spi_device *spi,
 		command2 |= SLINK_TXEN;
 		tspi->cur_direction |= DATA_DIR_TX;
 	}
+
+	/*
+	 * Writing to the command2 register bevore the command register prevents
+	 * a spike in chip_select line 0. This selects the chip_select line
+	 * before changing the chip_select value.
+	 */
 	tegra_slink_writel(tspi, command2, SLINK_COMMAND2);
 	tspi->command2_reg = command2;
 
+	tegra_slink_writel(tspi, command, SLINK_COMMAND);
+	tspi->command_reg = command;
+
 	if (total_fifo_words > SLINK_FIFO_DEPTH)
 		ret = tegra_slink_start_dma_based_transfer(tspi, t);
 	else
diff --git a/drivers/spi/spi-topcliff-pch.c b/drivers/spi/spi-topcliff-pch.c
index fba3f180f233..8a5966963834 100644
--- a/drivers/spi/spi-topcliff-pch.c
+++ b/drivers/spi/spi-topcliff-pch.c
@@ -1299,18 +1299,27 @@ static void pch_free_dma_buf(struct pch_spi_board_data *board_dat,
 				  dma->rx_buf_virt, dma->rx_buf_dma);
 }
 
-static void pch_alloc_dma_buf(struct pch_spi_board_data *board_dat,
+static int pch_alloc_dma_buf(struct pch_spi_board_data *board_dat,
 			      struct pch_spi_data *data)
 {
 	struct pch_spi_dma_ctrl *dma;
+	int ret;
 
 	dma = &data->dma;
+	ret = 0;
 	/* Get Consistent memory for Tx DMA */
 	dma->tx_buf_virt = dma_alloc_coherent(&board_dat->pdev->dev,
 				PCH_BUF_SIZE, &dma->tx_buf_dma, GFP_KERNEL);
+	if (!dma->tx_buf_virt)
+		ret = -ENOMEM;
+
 	/* Get Consistent memory for Rx DMA */
 	dma->rx_buf_virt = dma_alloc_coherent(&board_dat->pdev->dev,
 				PCH_BUF_SIZE, &dma->rx_buf_dma, GFP_KERNEL);
+	if (!dma->rx_buf_virt)
+		ret = -ENOMEM;
+
+	return ret;
 }
 
 static int pch_spi_pd_probe(struct platform_device *plat_dev)
@@ -1387,7 +1396,9 @@ static int pch_spi_pd_probe(struct platform_device *plat_dev)
 
 	if (use_dma) {
 		dev_info(&plat_dev->dev, "Use DMA for data transfers\n");
-		pch_alloc_dma_buf(board_dat, data);
+		ret = pch_alloc_dma_buf(board_dat, data);
+		if (ret)
+			goto err_spi_register_master;
 	}
 
 	ret = spi_register_master(master);
diff --git a/drivers/spi/spi-zynq-qspi.c b/drivers/spi/spi-zynq-qspi.c
new file mode 100644
index 000000000000..c6bee67decb5
--- /dev/null
+++ b/drivers/spi/spi-zynq-qspi.c
@@ -0,0 +1,761 @@
+// SPDX-License-Identifier: GPL-2.0+
+/*
+ * Copyright (C) 2019 Xilinx, Inc.
+ *
+ * Author: Naga Sureshkumar Relli <nagasure@xilinx.com>
+ */
+
+#include <linux/clk.h>
+#include <linux/delay.h>
+#include <linux/gpio.h>
+#include <linux/interrupt.h>
+#include <linux/io.h>
+#include <linux/module.h>
+#include <linux/of_irq.h>
+#include <linux/of_address.h>
+#include <linux/platform_device.h>
+#include <linux/spi/spi.h>
+#include <linux/workqueue.h>
+#include <linux/spi/spi-mem.h>
+
+/* Register offset definitions */
+#define ZYNQ_QSPI_CONFIG_OFFSET		0x00 /* Configuration  Register, RW */
+#define ZYNQ_QSPI_STATUS_OFFSET		0x04 /* Interrupt Status Register, RO */
+#define ZYNQ_QSPI_IEN_OFFSET		0x08 /* Interrupt Enable Register, WO */
+#define ZYNQ_QSPI_IDIS_OFFSET		0x0C /* Interrupt Disable Reg, WO */
+#define ZYNQ_QSPI_IMASK_OFFSET		0x10 /* Interrupt Enabled Mask Reg,RO */
+#define ZYNQ_QSPI_ENABLE_OFFSET		0x14 /* Enable/Disable Register, RW */
+#define ZYNQ_QSPI_DELAY_OFFSET		0x18 /* Delay Register, RW */
+#define ZYNQ_QSPI_TXD_00_00_OFFSET	0x1C /* Transmit 4-byte inst, WO */
+#define ZYNQ_QSPI_TXD_00_01_OFFSET	0x80 /* Transmit 1-byte inst, WO */
+#define ZYNQ_QSPI_TXD_00_10_OFFSET	0x84 /* Transmit 2-byte inst, WO */
+#define ZYNQ_QSPI_TXD_00_11_OFFSET	0x88 /* Transmit 3-byte inst, WO */
+#define ZYNQ_QSPI_RXD_OFFSET		0x20 /* Data Receive Register, RO */
+#define ZYNQ_QSPI_SIC_OFFSET		0x24 /* Slave Idle Count Register, RW */
+#define ZYNQ_QSPI_TX_THRESH_OFFSET	0x28 /* TX FIFO Watermark Reg, RW */
+#define ZYNQ_QSPI_RX_THRESH_OFFSET	0x2C /* RX FIFO Watermark Reg, RW */
+#define ZYNQ_QSPI_GPIO_OFFSET		0x30 /* GPIO Register, RW */
+#define ZYNQ_QSPI_LINEAR_CFG_OFFSET	0xA0 /* Linear Adapter Config Ref, RW */
+#define ZYNQ_QSPI_MOD_ID_OFFSET		0xFC /* Module ID Register, RO */
+
+/*
+ * QSPI Configuration Register bit Masks
+ *
+ * This register contains various control bits that effect the operation
+ * of the QSPI controller
+ */
+#define ZYNQ_QSPI_CONFIG_IFMODE_MASK	BIT(31) /* Flash Memory Interface */
+#define ZYNQ_QSPI_CONFIG_MANSRT_MASK	BIT(16) /* Manual TX Start */
+#define ZYNQ_QSPI_CONFIG_MANSRTEN_MASK	BIT(15) /* Enable Manual TX Mode */
+#define ZYNQ_QSPI_CONFIG_SSFORCE_MASK	BIT(14) /* Manual Chip Select */
+#define ZYNQ_QSPI_CONFIG_BDRATE_MASK	GENMASK(5, 3) /* Baud Rate Mask */
+#define ZYNQ_QSPI_CONFIG_CPHA_MASK	BIT(2) /* Clock Phase Control */
+#define ZYNQ_QSPI_CONFIG_CPOL_MASK	BIT(1) /* Clock Polarity Control */
+#define ZYNQ_QSPI_CONFIG_SSCTRL_MASK	BIT(10) /* Slave Select Mask */
+#define ZYNQ_QSPI_CONFIG_FWIDTH_MASK	GENMASK(7, 6) /* FIFO width */
+#define ZYNQ_QSPI_CONFIG_MSTREN_MASK	BIT(0) /* Master Mode */
+
+/*
+ * QSPI Configuration Register - Baud rate and slave select
+ *
+ * These are the values used in the calculation of baud rate divisor and
+ * setting the slave select.
+ */
+#define ZYNQ_QSPI_BAUD_DIV_MAX		GENMASK(2, 0) /* Baud rate maximum */
+#define ZYNQ_QSPI_BAUD_DIV_SHIFT	3 /* Baud rate divisor shift in CR */
+#define ZYNQ_QSPI_SS_SHIFT		10 /* Slave Select field shift in CR */
+
+/*
+ * QSPI Interrupt Registers bit Masks
+ *
+ * All the four interrupt registers (Status/Mask/Enable/Disable) have the same
+ * bit definitions.
+ */
+#define ZYNQ_QSPI_IXR_RX_OVERFLOW_MASK	BIT(0) /* QSPI RX FIFO Overflow */
+#define ZYNQ_QSPI_IXR_TXNFULL_MASK	BIT(2) /* QSPI TX FIFO Overflow */
+#define ZYNQ_QSPI_IXR_TXFULL_MASK	BIT(3) /* QSPI TX FIFO is full */
+#define ZYNQ_QSPI_IXR_RXNEMTY_MASK	BIT(4) /* QSPI RX FIFO Not Empty */
+#define ZYNQ_QSPI_IXR_RXF_FULL_MASK	BIT(5) /* QSPI RX FIFO is full */
+#define ZYNQ_QSPI_IXR_TXF_UNDRFLOW_MASK	BIT(6) /* QSPI TX FIFO Underflow */
+#define ZYNQ_QSPI_IXR_ALL_MASK		(ZYNQ_QSPI_IXR_RX_OVERFLOW_MASK | \
+					ZYNQ_QSPI_IXR_TXNFULL_MASK | \
+					ZYNQ_QSPI_IXR_TXFULL_MASK | \
+					ZYNQ_QSPI_IXR_RXNEMTY_MASK | \
+					ZYNQ_QSPI_IXR_RXF_FULL_MASK | \
+					ZYNQ_QSPI_IXR_TXF_UNDRFLOW_MASK)
+#define ZYNQ_QSPI_IXR_RXTX_MASK		(ZYNQ_QSPI_IXR_TXNFULL_MASK | \
+					ZYNQ_QSPI_IXR_RXNEMTY_MASK)
+
+/*
+ * QSPI Enable Register bit Masks
+ *
+ * This register is used to enable or disable the QSPI controller
+ */
+#define ZYNQ_QSPI_ENABLE_ENABLE_MASK	BIT(0) /* QSPI Enable Bit Mask */
+
+/*
+ * QSPI Linear Configuration Register
+ *
+ * It is named Linear Configuration but it controls other modes when not in
+ * linear mode also.
+ */
+#define ZYNQ_QSPI_LCFG_TWO_MEM_MASK	BIT(30) /* LQSPI Two memories Mask */
+#define ZYNQ_QSPI_LCFG_SEP_BUS_MASK	BIT(29) /* LQSPI Separate bus Mask */
+#define ZYNQ_QSPI_LCFG_U_PAGE_MASK	BIT(28) /* LQSPI Upper Page Mask */
+
+#define ZYNQ_QSPI_LCFG_DUMMY_SHIFT	8
+
+#define ZYNQ_QSPI_FAST_READ_QOUT_CODE	0x6B /* read instruction code */
+#define ZYNQ_QSPI_FIFO_DEPTH		63 /* FIFO depth in words */
+#define ZYNQ_QSPI_RX_THRESHOLD		32 /* Rx FIFO threshold level */
+#define ZYNQ_QSPI_TX_THRESHOLD		1 /* Tx FIFO threshold level */
+
+/*
+ * The modebits configurable by the driver to make the SPI support different
+ * data formats
+ */
+#define ZYNQ_QSPI_MODEBITS			(SPI_CPOL | SPI_CPHA)
+
+/* Default number of chip selects */
+#define ZYNQ_QSPI_DEFAULT_NUM_CS	1
+
+/**
+ * struct zynq_qspi - Defines qspi driver instance
+ * @regs:		Virtual address of the QSPI controller registers
+ * @refclk:		Pointer to the peripheral clock
+ * @pclk:		Pointer to the APB clock
+ * @irq:		IRQ number
+ * @txbuf:		Pointer to the TX buffer
+ * @rxbuf:		Pointer to the RX buffer
+ * @tx_bytes:		Number of bytes left to transfer
+ * @rx_bytes:		Number of bytes left to receive
+ * @data_completion:	completion structure
+ */
+struct zynq_qspi {
+	struct device *dev;
+	void __iomem *regs;
+	struct clk *refclk;
+	struct clk *pclk;
+	int irq;
+	u8 *txbuf;
+	u8 *rxbuf;
+	int tx_bytes;
+	int rx_bytes;
+	struct completion data_completion;
+};
+
+/*
+ * Inline functions for the QSPI controller read/write
+ */
+static inline u32 zynq_qspi_read(struct zynq_qspi *xqspi, u32 offset)
+{
+	return readl_relaxed(xqspi->regs + offset);
+}
+
+static inline void zynq_qspi_write(struct zynq_qspi *xqspi, u32 offset,
+				   u32 val)
+{
+	writel_relaxed(val, xqspi->regs + offset);
+}
+
+/**
+ * zynq_qspi_init_hw - Initialize the hardware
+ * @xqspi:	Pointer to the zynq_qspi structure
+ *
+ * The default settings of the QSPI controller's configurable parameters on
+ * reset are
+ *	- Master mode
+ *	- Baud rate divisor is set to 2
+ *	- Tx threshold set to 1l Rx threshold set to 32
+ *	- Flash memory interface mode enabled
+ *	- Size of the word to be transferred as 8 bit
+ * This function performs the following actions
+ *	- Disable and clear all the interrupts
+ *	- Enable manual slave select
+ *	- Enable manual start
+ *	- Deselect all the chip select lines
+ *	- Set the size of the word to be transferred as 32 bit
+ *	- Set the little endian mode of TX FIFO and
+ *	- Enable the QSPI controller
+ */
+static void zynq_qspi_init_hw(struct zynq_qspi *xqspi)
+{
+	u32 config_reg;
+
+	zynq_qspi_write(xqspi, ZYNQ_QSPI_ENABLE_OFFSET, 0);
+	zynq_qspi_write(xqspi, ZYNQ_QSPI_IDIS_OFFSET, ZYNQ_QSPI_IXR_ALL_MASK);
+
+	/* Disable linear mode as the boot loader may have used it */
+	zynq_qspi_write(xqspi, ZYNQ_QSPI_LINEAR_CFG_OFFSET, 0);
+
+	/* Clear the RX FIFO */
+	while (zynq_qspi_read(xqspi, ZYNQ_QSPI_STATUS_OFFSET) &
+			      ZYNQ_QSPI_IXR_RXNEMTY_MASK)
+		zynq_qspi_read(xqspi, ZYNQ_QSPI_RXD_OFFSET);
+
+	zynq_qspi_write(xqspi, ZYNQ_QSPI_STATUS_OFFSET, ZYNQ_QSPI_IXR_ALL_MASK);
+	config_reg = zynq_qspi_read(xqspi, ZYNQ_QSPI_CONFIG_OFFSET);
+	config_reg &= ~(ZYNQ_QSPI_CONFIG_MSTREN_MASK |
+			ZYNQ_QSPI_CONFIG_CPOL_MASK |
+			ZYNQ_QSPI_CONFIG_CPHA_MASK |
+			ZYNQ_QSPI_CONFIG_BDRATE_MASK |
+			ZYNQ_QSPI_CONFIG_SSFORCE_MASK |
+			ZYNQ_QSPI_CONFIG_MANSRTEN_MASK |
+			ZYNQ_QSPI_CONFIG_MANSRT_MASK);
+	config_reg |= (ZYNQ_QSPI_CONFIG_MSTREN_MASK |
+		       ZYNQ_QSPI_CONFIG_SSFORCE_MASK |
+		       ZYNQ_QSPI_CONFIG_FWIDTH_MASK |
+		       ZYNQ_QSPI_CONFIG_IFMODE_MASK);
+	zynq_qspi_write(xqspi, ZYNQ_QSPI_CONFIG_OFFSET, config_reg);
+
+	zynq_qspi_write(xqspi, ZYNQ_QSPI_RX_THRESH_OFFSET,
+			ZYNQ_QSPI_RX_THRESHOLD);
+	zynq_qspi_write(xqspi, ZYNQ_QSPI_TX_THRESH_OFFSET,
+			ZYNQ_QSPI_TX_THRESHOLD);
+
+	zynq_qspi_write(xqspi, ZYNQ_QSPI_ENABLE_OFFSET,
+			ZYNQ_QSPI_ENABLE_ENABLE_MASK);
+}
+
+static bool zynq_qspi_supports_op(struct spi_mem *mem,
+				  const struct spi_mem_op *op)
+{
+	if (!spi_mem_default_supports_op(mem, op))
+		return false;
+
+	/*
+	 * The number of address bytes should be equal to or less than 3 bytes.
+	 */
+	if (op->addr.nbytes > 3)
+		return false;
+
+	return true;
+}
+
+/**
+ * zynq_qspi_rxfifo_op - Read 1..4 bytes from RxFIFO to RX buffer
+ * @xqspi:	Pointer to the zynq_qspi structure
+ * @size:	Number of bytes to be read (1..4)
+ */
+static void zynq_qspi_rxfifo_op(struct zynq_qspi *xqspi, unsigned int size)
+{
+	u32 data;
+
+	data = zynq_qspi_read(xqspi, ZYNQ_QSPI_RXD_OFFSET);
+
+	if (xqspi->rxbuf) {
+		memcpy(xqspi->rxbuf, ((u8 *)&data) + 4 - size, size);
+		xqspi->rxbuf += size;
+	}
+
+	xqspi->rx_bytes -= size;
+	if (xqspi->rx_bytes < 0)
+		xqspi->rx_bytes = 0;
+}
+
+/**
+ * zynq_qspi_txfifo_op - Write 1..4 bytes from TX buffer to TxFIFO
+ * @xqspi:	Pointer to the zynq_qspi structure
+ * @size:	Number of bytes to be written (1..4)
+ */
+static void zynq_qspi_txfifo_op(struct zynq_qspi *xqspi, unsigned int size)
+{
+	static const unsigned int offset[4] = {
+		ZYNQ_QSPI_TXD_00_01_OFFSET, ZYNQ_QSPI_TXD_00_10_OFFSET,
+		ZYNQ_QSPI_TXD_00_11_OFFSET, ZYNQ_QSPI_TXD_00_00_OFFSET };
+	u32 data;
+
+	if (xqspi->txbuf) {
+		data = 0xffffffff;
+		memcpy(&data, xqspi->txbuf, size);
+		xqspi->txbuf += size;
+	} else {
+		data = 0;
+	}
+
+	xqspi->tx_bytes -= size;
+	zynq_qspi_write(xqspi, offset[size - 1], data);
+}
+
+/**
+ * zynq_qspi_chipselect - Select or deselect the chip select line
+ * @spi:	Pointer to the spi_device structure
+ * @assert:	1 for select or 0 for deselect the chip select line
+ */
+static void zynq_qspi_chipselect(struct spi_device *spi, bool assert)
+{
+	struct spi_controller *ctrl = spi->master;
+	struct zynq_qspi *xqspi = spi_controller_get_devdata(ctrl);
+	u32 config_reg;
+
+	config_reg = zynq_qspi_read(xqspi, ZYNQ_QSPI_CONFIG_OFFSET);
+	if (assert) {
+		/* Select the slave */
+		config_reg &= ~ZYNQ_QSPI_CONFIG_SSCTRL_MASK;
+		config_reg |= (((~(BIT(spi->chip_select))) <<
+				ZYNQ_QSPI_SS_SHIFT) &
+				ZYNQ_QSPI_CONFIG_SSCTRL_MASK);
+	} else {
+		config_reg |= ZYNQ_QSPI_CONFIG_SSCTRL_MASK;
+	}
+
+	zynq_qspi_write(xqspi, ZYNQ_QSPI_CONFIG_OFFSET, config_reg);
+}
+
+/**
+ * zynq_qspi_config_op - Configure QSPI controller for specified transfer
+ * @xqspi:	Pointer to the zynq_qspi structure
+ * @qspi:	Pointer to the spi_device structure
+ *
+ * Sets the operational mode of QSPI controller for the next QSPI transfer and
+ * sets the requested clock frequency.
+ *
+ * Return:	0 on success and -EINVAL on invalid input parameter
+ *
+ * Note: If the requested frequency is not an exact match with what can be
+ * obtained using the prescalar value, the driver sets the clock frequency which
+ * is lower than the requested frequency (maximum lower) for the transfer. If
+ * the requested frequency is higher or lower than that is supported by the QSPI
+ * controller the driver will set the highest or lowest frequency supported by
+ * controller.
+ */
+static int zynq_qspi_config_op(struct zynq_qspi *xqspi, struct spi_device *spi)
+{
+	u32 config_reg, baud_rate_val = 0;
+
+	/*
+	 * Set the clock frequency
+	 * The baud rate divisor is not a direct mapping to the value written
+	 * into the configuration register (config_reg[5:3])
+	 * i.e. 000 - divide by 2
+	 *      001 - divide by 4
+	 *      ----------------
+	 *      111 - divide by 256
+	 */
+	while ((baud_rate_val < ZYNQ_QSPI_BAUD_DIV_MAX)  &&
+	       (clk_get_rate(xqspi->refclk) / (2 << baud_rate_val)) >
+		spi->max_speed_hz)
+		baud_rate_val++;
+
+	config_reg = zynq_qspi_read(xqspi, ZYNQ_QSPI_CONFIG_OFFSET);
+
+	/* Set the QSPI clock phase and clock polarity */
+	config_reg &= (~ZYNQ_QSPI_CONFIG_CPHA_MASK) &
+		      (~ZYNQ_QSPI_CONFIG_CPOL_MASK);
+	if (spi->mode & SPI_CPHA)
+		config_reg |= ZYNQ_QSPI_CONFIG_CPHA_MASK;
+	if (spi->mode & SPI_CPOL)
+		config_reg |= ZYNQ_QSPI_CONFIG_CPOL_MASK;
+
+	config_reg &= ~ZYNQ_QSPI_CONFIG_BDRATE_MASK;
+	config_reg |= (baud_rate_val << ZYNQ_QSPI_BAUD_DIV_SHIFT);
+	zynq_qspi_write(xqspi, ZYNQ_QSPI_CONFIG_OFFSET, config_reg);
+
+	return 0;
+}
+
+/**
+ * zynq_qspi_setup - Configure the QSPI controller
+ * @spi:	Pointer to the spi_device structure
+ *
+ * Sets the operational mode of QSPI controller for the next QSPI transfer, baud
+ * rate and divisor value to setup the requested qspi clock.
+ *
+ * Return:	0 on success and error value on failure
+ */
+static int zynq_qspi_setup_op(struct spi_device *spi)
+{
+	struct spi_controller *ctrl = spi->master;
+	struct zynq_qspi *qspi = spi_controller_get_devdata(ctrl);
+
+	if (ctrl->busy)
+		return -EBUSY;
+
+	clk_enable(qspi->refclk);
+	clk_enable(qspi->pclk);
+	zynq_qspi_write(qspi, ZYNQ_QSPI_ENABLE_OFFSET,
+			ZYNQ_QSPI_ENABLE_ENABLE_MASK);
+
+	return 0;
+}
+
+/**
+ * zynq_qspi_write_op - Fills the TX FIFO with as many bytes as possible
+ * @xqspi:	Pointer to the zynq_qspi structure
+ * @txcount:	Maximum number of words to write
+ * @txempty:	Indicates that TxFIFO is empty
+ */
+static void zynq_qspi_write_op(struct zynq_qspi *xqspi, int txcount,
+			       bool txempty)
+{
+	int count, len, k;
+
+	len = xqspi->tx_bytes;
+	if (len && len < 4) {
+		/*
+		 * We must empty the TxFIFO between accesses to TXD0,
+		 * TXD1, TXD2, TXD3.
+		 */
+		if (txempty)
+			zynq_qspi_txfifo_op(xqspi, len);
+
+		return;
+	}
+
+	count = len / 4;
+	if (count > txcount)
+		count = txcount;
+
+	if (xqspi->txbuf) {
+		iowrite32_rep(xqspi->regs + ZYNQ_QSPI_TXD_00_00_OFFSET,
+			      xqspi->txbuf, count);
+		xqspi->txbuf += count * 4;
+	} else {
+		for (k = 0; k < count; k++)
+			writel_relaxed(0, xqspi->regs +
+					  ZYNQ_QSPI_TXD_00_00_OFFSET);
+	}
+
+	xqspi->tx_bytes -= count * 4;
+}
+
+/**
+ * zynq_qspi_read_op - Drains the RX FIFO by as many bytes as possible
+ * @xqspi:	Pointer to the zynq_qspi structure
+ * @rxcount:	Maximum number of words to read
+ */
+static void zynq_qspi_read_op(struct zynq_qspi *xqspi, int rxcount)
+{
+	int count, len, k;
+
+	len = xqspi->rx_bytes - xqspi->tx_bytes;
+	count = len / 4;
+	if (count > rxcount)
+		count = rxcount;
+	if (xqspi->rxbuf) {
+		ioread32_rep(xqspi->regs + ZYNQ_QSPI_RXD_OFFSET,
+			     xqspi->rxbuf, count);
+		xqspi->rxbuf += count * 4;
+	} else {
+		for (k = 0; k < count; k++)
+			readl_relaxed(xqspi->regs + ZYNQ_QSPI_RXD_OFFSET);
+	}
+	xqspi->rx_bytes -= count * 4;
+	len -= count * 4;
+
+	if (len && len < 4 && count < rxcount)
+		zynq_qspi_rxfifo_op(xqspi, len);
+}
+
+/**
+ * zynq_qspi_irq - Interrupt service routine of the QSPI controller
+ * @irq:	IRQ number
+ * @dev_id:	Pointer to the xqspi structure
+ *
+ * This function handles TX empty only.
+ * On TX empty interrupt this function reads the received data from RX FIFO and
+ * fills the TX FIFO if there is any data remaining to be transferred.
+ *
+ * Return:	IRQ_HANDLED when interrupt is handled; IRQ_NONE otherwise.
+ */
+static irqreturn_t zynq_qspi_irq(int irq, void *dev_id)
+{
+	u32 intr_status;
+	bool txempty;
+	struct zynq_qspi *xqspi = (struct zynq_qspi *)dev_id;
+
+	intr_status = zynq_qspi_read(xqspi, ZYNQ_QSPI_STATUS_OFFSET);
+	zynq_qspi_write(xqspi, ZYNQ_QSPI_STATUS_OFFSET, intr_status);
+
+	if ((intr_status & ZYNQ_QSPI_IXR_TXNFULL_MASK) ||
+	    (intr_status & ZYNQ_QSPI_IXR_RXNEMTY_MASK)) {
+		/*
+		 * This bit is set when Tx FIFO has < THRESHOLD entries.
+		 * We have the THRESHOLD value set to 1,
+		 * so this bit indicates Tx FIFO is empty.
+		 */
+		txempty = !!(intr_status & ZYNQ_QSPI_IXR_TXNFULL_MASK);
+		/* Read out the data from the RX FIFO */
+		zynq_qspi_read_op(xqspi, ZYNQ_QSPI_RX_THRESHOLD);
+		if (xqspi->tx_bytes) {
+			/* There is more data to send */
+			zynq_qspi_write_op(xqspi, ZYNQ_QSPI_RX_THRESHOLD,
+					   txempty);
+		} else {
+			/*
+			 * If transfer and receive is completed then only send
+			 * complete signal.
+			 */
+			if (!xqspi->rx_bytes) {
+				zynq_qspi_write(xqspi,
+						ZYNQ_QSPI_IDIS_OFFSET,
+						ZYNQ_QSPI_IXR_RXTX_MASK);
+				complete(&xqspi->data_completion);
+			}
+		}
+		return IRQ_HANDLED;
+	}
+
+	return IRQ_NONE;
+}
+
+/**
+ * zynq_qspi_exec_mem_op() - Initiates the QSPI transfer
+ * @mem: the SPI memory
+ * @op: the memory operation to execute
+ *
+ * Executes a memory operation.
+ *
+ * This function first selects the chip and starts the memory operation.
+ *
+ * Return: 0 in case of success, a negative error code otherwise.
+ */
+static int zynq_qspi_exec_mem_op(struct spi_mem *mem,
+				 const struct spi_mem_op *op)
+{
+	struct zynq_qspi *xqspi = spi_controller_get_devdata(mem->spi->master);
+	int err = 0, i;
+	u8 *tmpbuf;
+
+	dev_dbg(xqspi->dev, "cmd:%#x mode:%d.%d.%d.%d\n",
+		op->cmd.opcode, op->cmd.buswidth, op->addr.buswidth,
+		op->dummy.buswidth, op->data.buswidth);
+
+	zynq_qspi_chipselect(mem->spi, true);
+	zynq_qspi_config_op(xqspi, mem->spi);
+
+	if (op->cmd.opcode) {
+		reinit_completion(&xqspi->data_completion);
+		xqspi->txbuf = (u8 *)&op->cmd.opcode;
+		xqspi->rxbuf = NULL;
+		xqspi->tx_bytes = sizeof(op->cmd.opcode);
+		xqspi->rx_bytes = sizeof(op->cmd.opcode);
+		zynq_qspi_write_op(xqspi, ZYNQ_QSPI_FIFO_DEPTH, true);
+		zynq_qspi_write(xqspi, ZYNQ_QSPI_IEN_OFFSET,
+				ZYNQ_QSPI_IXR_RXTX_MASK);
+		if (!wait_for_completion_interruptible_timeout(&xqspi->data_completion,
+							       msecs_to_jiffies(1000)))
+			err = -ETIMEDOUT;
+	}
+
+	if (op->addr.nbytes) {
+		for (i = 0; i < op->addr.nbytes; i++) {
+			xqspi->txbuf[i] = op->addr.val >>
+					(8 * (op->addr.nbytes - i - 1));
+		}
+
+		reinit_completion(&xqspi->data_completion);
+		xqspi->rxbuf = NULL;
+		xqspi->tx_bytes = op->addr.nbytes;
+		xqspi->rx_bytes = op->addr.nbytes;
+		zynq_qspi_write_op(xqspi, ZYNQ_QSPI_FIFO_DEPTH, true);
+		zynq_qspi_write(xqspi, ZYNQ_QSPI_IEN_OFFSET,
+				ZYNQ_QSPI_IXR_RXTX_MASK);
+		if (!wait_for_completion_interruptible_timeout(&xqspi->data_completion,
+							       msecs_to_jiffies(1000)))
+			err = -ETIMEDOUT;
+	}
+
+	if (op->dummy.nbytes) {
+		tmpbuf = kzalloc(op->dummy.nbytes, GFP_KERNEL);
+		memset(tmpbuf, 0xff, op->dummy.nbytes);
+		reinit_completion(&xqspi->data_completion);
+		xqspi->txbuf = tmpbuf;
+		xqspi->rxbuf = NULL;
+		xqspi->tx_bytes = op->dummy.nbytes;
+		xqspi->rx_bytes = op->dummy.nbytes;
+		zynq_qspi_write_op(xqspi, ZYNQ_QSPI_FIFO_DEPTH, true);
+		zynq_qspi_write(xqspi, ZYNQ_QSPI_IEN_OFFSET,
+				ZYNQ_QSPI_IXR_RXTX_MASK);
+		if (!wait_for_completion_interruptible_timeout(&xqspi->data_completion,
+							       msecs_to_jiffies(1000)))
+			err = -ETIMEDOUT;
+
+		kfree(tmpbuf);
+	}
+
+	if (op->data.nbytes) {
+		reinit_completion(&xqspi->data_completion);
+		if (op->data.dir == SPI_MEM_DATA_OUT) {
+			xqspi->txbuf = (u8 *)op->data.buf.out;
+			xqspi->tx_bytes = op->data.nbytes;
+			xqspi->rxbuf = NULL;
+			xqspi->rx_bytes = op->data.nbytes;
+		} else {
+			xqspi->txbuf = NULL;
+			xqspi->rxbuf = (u8 *)op->data.buf.in;
+			xqspi->rx_bytes = op->data.nbytes;
+			xqspi->tx_bytes = op->data.nbytes;
+		}
+
+		zynq_qspi_write_op(xqspi, ZYNQ_QSPI_FIFO_DEPTH, true);
+		zynq_qspi_write(xqspi, ZYNQ_QSPI_IEN_OFFSET,
+				ZYNQ_QSPI_IXR_RXTX_MASK);
+		if (!wait_for_completion_interruptible_timeout(&xqspi->data_completion,
+							       msecs_to_jiffies(1000)))
+			err = -ETIMEDOUT;
+	}
+	zynq_qspi_chipselect(mem->spi, false);
+
+	return err;
+}
+
+static const struct spi_controller_mem_ops zynq_qspi_mem_ops = {
+	.supports_op = zynq_qspi_supports_op,
+	.exec_op = zynq_qspi_exec_mem_op,
+};
+
+/**
+ * zynq_qspi_probe - Probe method for the QSPI driver
+ * @pdev:	Pointer to the platform_device structure
+ *
+ * This function initializes the driver data structures and the hardware.
+ *
+ * Return:	0 on success and error value on failure
+ */
+static int zynq_qspi_probe(struct platform_device *pdev)
+{
+	int ret = 0;
+	struct spi_controller *ctlr;
+	struct device *dev = &pdev->dev;
+	struct device_node *np = dev->of_node;
+	struct zynq_qspi *xqspi;
+	struct resource *res;
+	u32 num_cs;
+
+	ctlr = spi_alloc_master(&pdev->dev, sizeof(*xqspi));
+	if (!ctlr)
+		return -ENOMEM;
+
+	xqspi = spi_controller_get_devdata(ctlr);
+	xqspi->dev = dev;
+	platform_set_drvdata(pdev, xqspi);
+	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
+	xqspi->regs = devm_ioremap_resource(&pdev->dev, res);
+	if (IS_ERR(xqspi->regs)) {
+		ret = PTR_ERR(xqspi->regs);
+		goto remove_master;
+	}
+
+	xqspi->pclk = devm_clk_get(&pdev->dev, "pclk");
+	if (IS_ERR(xqspi->pclk)) {
+		dev_err(&pdev->dev, "pclk clock not found.\n");
+		ret = PTR_ERR(xqspi->pclk);
+		goto remove_master;
+	}
+
+	init_completion(&xqspi->data_completion);
+
+	xqspi->refclk = devm_clk_get(&pdev->dev, "ref_clk");
+	if (IS_ERR(xqspi->refclk)) {
+		dev_err(&pdev->dev, "ref_clk clock not found.\n");
+		ret = PTR_ERR(xqspi->refclk);
+		goto remove_master;
+	}
+
+	ret = clk_prepare_enable(xqspi->pclk);
+	if (ret) {
+		dev_err(&pdev->dev, "Unable to enable APB clock.\n");
+		goto remove_master;
+	}
+
+	ret = clk_prepare_enable(xqspi->refclk);
+	if (ret) {
+		dev_err(&pdev->dev, "Unable to enable device clock.\n");
+		goto clk_dis_pclk;
+	}
+
+	/* QSPI controller initializations */
+	zynq_qspi_init_hw(xqspi);
+
+	xqspi->irq = platform_get_irq(pdev, 0);
+	if (xqspi->irq <= 0) {
+		ret = -ENXIO;
+		dev_err(&pdev->dev, "irq resource not found\n");
+		goto remove_master;
+	}
+	ret = devm_request_irq(&pdev->dev, xqspi->irq, zynq_qspi_irq,
+			       0, pdev->name, xqspi);
+	if (ret != 0) {
+		ret = -ENXIO;
+		dev_err(&pdev->dev, "request_irq failed\n");
+		goto remove_master;
+	}
+
+	ret = of_property_read_u32(np, "num-cs",
+				   &num_cs);
+	if (ret < 0)
+		ctlr->num_chipselect = ZYNQ_QSPI_DEFAULT_NUM_CS;
+	else
+		ctlr->num_chipselect = num_cs;
+
+	ctlr->mode_bits =  SPI_RX_DUAL | SPI_RX_QUAD |
+			    SPI_TX_DUAL | SPI_TX_QUAD;
+	ctlr->mem_ops = &zynq_qspi_mem_ops;
+	ctlr->setup = zynq_qspi_setup_op;
+	ctlr->max_speed_hz = clk_get_rate(xqspi->refclk) / 2;
+	ctlr->dev.of_node = np;
+	ret = spi_register_controller(ctlr);
+	if (ret) {
+		dev_err(&pdev->dev, "spi_register_master failed\n");
+		goto clk_dis_all;
+	}
+
+	return ret;
+
+clk_dis_all:
+	clk_disable_unprepare(xqspi->refclk);
+clk_dis_pclk:
+	clk_disable_unprepare(xqspi->pclk);
+remove_master:
+	spi_controller_put(ctlr);
+
+	return ret;
+}
+
+/**
+ * zynq_qspi_remove - Remove method for the QSPI driver
+ * @pdev:	Pointer to the platform_device structure
+ *
+ * This function is called if a device is physically removed from the system or
+ * if the driver module is being unloaded. It frees all resources allocated to
+ * the device.
+ *
+ * Return:	0 on success and error value on failure
+ */
+static int zynq_qspi_remove(struct platform_device *pdev)
+{
+	struct zynq_qspi *xqspi = platform_get_drvdata(pdev);
+
+	zynq_qspi_write(xqspi, ZYNQ_QSPI_ENABLE_OFFSET, 0);
+
+	clk_disable_unprepare(xqspi->refclk);
+	clk_disable_unprepare(xqspi->pclk);
+
+	return 0;
+}
+
+static const struct of_device_id zynq_qspi_of_match[] = {
+	{ .compatible = "xlnx,zynq-qspi-1.0", },
+	{ /* end of table */ }
+};
+
+MODULE_DEVICE_TABLE(of, zynq_qspi_of_match);
+
+/*
+ * zynq_qspi_driver - This structure defines the QSPI platform driver
+ */
+static struct platform_driver zynq_qspi_driver = {
+	.probe = zynq_qspi_probe,
+	.remove = zynq_qspi_remove,
+	.driver = {
+		.name = "zynq-qspi",
+		.of_match_table = zynq_qspi_of_match,
+	},
+};
+
+module_platform_driver(zynq_qspi_driver);
+
+MODULE_AUTHOR("Xilinx, Inc.");
+MODULE_DESCRIPTION("Xilinx Zynq QSPI driver");
+MODULE_LICENSE("GPL");
diff --git a/drivers/spi/spi.c b/drivers/spi/spi.c
index 93986f879b09..5e75944ad5d1 100644
--- a/drivers/spi/spi.c
+++ b/drivers/spi/spi.c
@@ -36,6 +36,8 @@
 
 #define CREATE_TRACE_POINTS
 #include <trace/events/spi.h>
+EXPORT_TRACEPOINT_SYMBOL(spi_transfer_start);
+EXPORT_TRACEPOINT_SYMBOL(spi_transfer_stop);
 
 #include "internals.h"
 
@@ -1039,6 +1041,8 @@ static int spi_map_msg(struct spi_controller *ctlr, struct spi_message *msg)
 		if (max_tx || max_rx) {
 			list_for_each_entry(xfer, &msg->transfers,
 					    transfer_list) {
+				if (!xfer->len)
+					continue;
 				if (!xfer->tx_buf)
 					xfer->tx_buf = ctlr->dummy_tx;
 				if (!xfer->rx_buf)
@@ -1177,10 +1181,10 @@ out:
 	if (msg->status && ctlr->handle_err)
 		ctlr->handle_err(ctlr, msg);
 
-	spi_res_release(ctlr, msg);
-
 	spi_finalize_current_message(ctlr);
 
+	spi_res_release(ctlr, msg);
+
 	return ret;
 }
 
@@ -2195,6 +2199,8 @@ static int spi_get_gpio_descs(struct spi_controller *ctlr)
 		 */
 		cs[i] = devm_gpiod_get_index_optional(dev, "cs", i,
 						      GPIOD_OUT_LOW);
+		if (IS_ERR(cs[i]))
+			return PTR_ERR(cs[i]);
 
 		if (cs[i]) {
 			/*
@@ -2261,7 +2267,7 @@ int spi_register_controller(struct spi_controller *ctlr)
 {
 	struct device		*dev = ctlr->dev.parent;
 	struct boardinfo	*bi;
-	int			status = -ENODEV;
+	int			status;
 	int			id, first_dynamic;
 
 	if (!dev)
@@ -2275,24 +2281,6 @@ int spi_register_controller(struct spi_controller *ctlr)
 	if (status)
 		return status;
 
-	if (!spi_controller_is_slave(ctlr)) {
-		if (ctlr->use_gpio_descriptors) {
-			status = spi_get_gpio_descs(ctlr);
-			if (status)
-				return status;
-			/*
-			 * A controller using GPIO descriptors always
-			 * supports SPI_CS_HIGH if need be.
-			 */
-			ctlr->mode_bits |= SPI_CS_HIGH;
-		} else {
-			/* Legacy code path for GPIOs from DT */
-			status = of_spi_register_master(ctlr);
-			if (status)
-				return status;
-		}
-	}
-
 	/* even if it's just one always-selected device, there must
 	 * be at least one chipselect
 	 */
@@ -2349,6 +2337,25 @@ int spi_register_controller(struct spi_controller *ctlr)
 	 * registration fails if the bus ID is in use.
 	 */
 	dev_set_name(&ctlr->dev, "spi%u", ctlr->bus_num);
+
+	if (!spi_controller_is_slave(ctlr)) {
+		if (ctlr->use_gpio_descriptors) {
+			status = spi_get_gpio_descs(ctlr);
+			if (status)
+				return status;
+			/*
+			 * A controller using GPIO descriptors always
+			 * supports SPI_CS_HIGH if need be.
+			 */
+			ctlr->mode_bits |= SPI_CS_HIGH;
+		} else {
+			/* Legacy code path for GPIOs from DT */
+			status = of_spi_register_master(ctlr);
+			if (status)
+				return status;
+		}
+	}
+
 	status = device_add(&ctlr->dev);
 	if (status < 0) {
 		/* free bus id */
@@ -2781,11 +2788,6 @@ static int __spi_split_transfer_maxsize(struct spi_controller *ctlr,
 	size_t offset;
 	size_t count, i;
 
-	/* warn once about this fact that we are splitting a transfer */
-	dev_warn_once(&msg->spi->dev,
-		      "spi_transfer of length %i exceed max length of %zu - needed to split transfers\n",
-		      xfer->len, maxsize);
-
 	/* calculate how many we have to replace */
 	count = DIV_ROUND_UP(xfer->len, maxsize);
 
@@ -2943,6 +2945,11 @@ int spi_setup(struct spi_device *spi)
 	 * so it is ignored here.
 	 */
 	bad_bits = spi->mode & ~(spi->controller->mode_bits | SPI_CS_WORD);
+	/* nothing prevents from working with active-high CS in case if it
+	 * is driven by GPIO.
+	 */
+	if (gpio_is_valid(spi->cs_gpio))
+		bad_bits &= ~SPI_CS_HIGH;
 	ugly_bits = bad_bits &
 		    (SPI_TX_DUAL | SPI_TX_QUAD | SPI_TX_OCTAL |
 		     SPI_RX_DUAL | SPI_RX_QUAD | SPI_RX_OCTAL);
@@ -2988,6 +2995,21 @@ int spi_setup(struct spi_device *spi)
 }
 EXPORT_SYMBOL_GPL(spi_setup);
 
+/**
+ * spi_set_cs_timing - configure CS setup, hold, and inactive delays
+ * @spi: the device that requires specific CS timing configuration
+ * @setup: CS setup time in terms of clock count
+ * @hold: CS hold time in terms of clock count
+ * @inactive_dly: CS inactive delay between transfers in terms of clock count
+ */
+void spi_set_cs_timing(struct spi_device *spi, u8 setup, u8 hold,
+		       u8 inactive_dly)
+{
+	if (spi->controller->set_cs_timing)
+		spi->controller->set_cs_timing(spi, setup, hold, inactive_dly);
+}
+EXPORT_SYMBOL_GPL(spi_set_cs_timing);
+
 static int __spi_validate(struct spi_device *spi, struct spi_message *message)
 {
 	struct spi_controller *ctlr = spi->controller;
@@ -3062,8 +3084,6 @@ static int __spi_validate(struct spi_device *spi, struct spi_message *message)
 
 		if (!xfer->speed_hz)
 			xfer->speed_hz = spi->max_speed_hz;
-		if (!xfer->speed_hz)
-			xfer->speed_hz = ctlr->max_speed_hz;
 
 		if (ctlr->max_speed_hz && xfer->speed_hz > ctlr->max_speed_hz)
 			xfer->speed_hz = ctlr->max_speed_hz;
diff --git a/drivers/spi/spidev.c b/drivers/spi/spidev.c
index b0c76e2626ce..70966e10be7e 100644
--- a/drivers/spi/spidev.c
+++ b/drivers/spi/spidev.c
@@ -276,17 +276,19 @@ static int spidev_message(struct spidev_data *spidev,
 		k_tmp->bits_per_word = u_tmp->bits_per_word;
 		k_tmp->delay_usecs = u_tmp->delay_usecs;
 		k_tmp->speed_hz = u_tmp->speed_hz;
+		k_tmp->word_delay_usecs = u_tmp->word_delay_usecs;
 		if (!k_tmp->speed_hz)
 			k_tmp->speed_hz = spidev->speed_hz;
 #ifdef VERBOSE
 		dev_dbg(&spidev->spi->dev,
-			"  xfer len %u %s%s%s%dbits %u usec %uHz\n",
+			"  xfer len %u %s%s%s%dbits %u usec %u usec %uHz\n",
 			u_tmp->len,
 			u_tmp->rx_buf ? "rx " : "",
 			u_tmp->tx_buf ? "tx " : "",
 			u_tmp->cs_change ? "cs " : "",
 			u_tmp->bits_per_word ? : spidev->spi->bits_per_word,
 			u_tmp->delay_usecs,
+			u_tmp->word_delay_usecs,
 			u_tmp->speed_hz ? : spidev->spi->max_speed_hz);
 #endif
 		spi_message_add_tail(k_tmp, &msg);
diff --git a/drivers/ssb/pci.c b/drivers/ssb/pci.c
index 84807a9b4b13..da2d2ab8104d 100644
--- a/drivers/ssb/pci.c
+++ b/drivers/ssb/pci.c
@@ -305,7 +305,6 @@ static int sprom_do_write(struct ssb_bus *bus, const u16 *sprom)
 		else if (i % 2)
 			pr_cont(".");
 		writew(sprom[i], bus->mmio + bus->sprom_offset + (i * 2));
-		mmiowb();
 		msleep(20);
 	}
 	err = pci_read_config_dword(pdev, SSB_SPROMCTL, &spromctl);
diff --git a/drivers/ssb/pcmcia.c b/drivers/ssb/pcmcia.c
index 567013f8a8be..d7d730c245c5 100644
--- a/drivers/ssb/pcmcia.c
+++ b/drivers/ssb/pcmcia.c
@@ -338,7 +338,6 @@ static void ssb_pcmcia_write8(struct ssb_device *dev, u16 offset, u8 value)
 	err = select_core_and_segment(dev, &offset);
 	if (likely(!err))
 		writeb(value, bus->mmio + offset);
-	mmiowb();
 	spin_unlock_irqrestore(&bus->bar_lock, flags);
 }
 
@@ -352,7 +351,6 @@ static void ssb_pcmcia_write16(struct ssb_device *dev, u16 offset, u16 value)
 	err = select_core_and_segment(dev, &offset);
 	if (likely(!err))
 		writew(value, bus->mmio + offset);
-	mmiowb();
 	spin_unlock_irqrestore(&bus->bar_lock, flags);
 }
 
@@ -368,7 +366,6 @@ static void ssb_pcmcia_write32(struct ssb_device *dev, u16 offset, u32 value)
 		writew((value & 0x0000FFFF), bus->mmio + offset);
 		writew(((value & 0xFFFF0000) >> 16), bus->mmio + offset + 2);
 	}
-	mmiowb();
 	spin_unlock_irqrestore(&bus->bar_lock, flags);
 }
 
@@ -424,7 +421,6 @@ static void ssb_pcmcia_block_write(struct ssb_device *dev, const void *buffer,
 		WARN_ON(1);
 	}
 unlock:
-	mmiowb();
 	spin_unlock_irqrestore(&bus->bar_lock, flags);
 }
 #endif /* CONFIG_SSB_BLOCKIO */
diff --git a/drivers/staging/Kconfig b/drivers/staging/Kconfig
index c0901b96cfe4..c7d7dc89deba 100644
--- a/drivers/staging/Kconfig
+++ b/drivers/staging/Kconfig
@@ -106,16 +106,12 @@ source "drivers/staging/mt7621-pci-phy/Kconfig"
 
 source "drivers/staging/mt7621-pinctrl/Kconfig"
 
-source "drivers/staging/mt7621-spi/Kconfig"
-
 source "drivers/staging/mt7621-dma/Kconfig"
 
 source "drivers/staging/ralink-gdma/Kconfig"
 
 source "drivers/staging/mt7621-mmc/Kconfig"
 
-source "drivers/staging/mt7621-eth/Kconfig"
-
 source "drivers/staging/mt7621-dts/Kconfig"
 
 source "drivers/staging/gasket/Kconfig"
diff --git a/drivers/staging/Makefile b/drivers/staging/Makefile
index 57c6bce13ff4..19c0a25ff98b 100644
--- a/drivers/staging/Makefile
+++ b/drivers/staging/Makefile
@@ -43,11 +43,9 @@ obj-$(CONFIG_PI433)		+= pi433/
 obj-$(CONFIG_PCI_MT7621)	+= mt7621-pci/
 obj-$(CONFIG_PCI_MT7621_PHY)	+= mt7621-pci-phy/
 obj-$(CONFIG_PINCTRL_RT2880)	+= mt7621-pinctrl/
-obj-$(CONFIG_SPI_MT7621)	+= mt7621-spi/
 obj-$(CONFIG_SOC_MT7621)	+= mt7621-dma/
 obj-$(CONFIG_DMA_RALINK)	+= ralink-gdma/
 obj-$(CONFIG_MTK_MMC)		+= mt7621-mmc/
-obj-$(CONFIG_NET_MEDIATEK_SOC_STAGING)	+= mt7621-eth/
 obj-$(CONFIG_SOC_MT7621)	+= mt7621-dts/
 obj-$(CONFIG_STAGING_GASKET_FRAMEWORK)	+= gasket/
 obj-$(CONFIG_XIL_AXIS_FIFO)	+= axis-fifo/
diff --git a/drivers/staging/axis-fifo/Kconfig b/drivers/staging/axis-fifo/Kconfig
index 687537203d9c..d9725888af6f 100644
--- a/drivers/staging/axis-fifo/Kconfig
+++ b/drivers/staging/axis-fifo/Kconfig
@@ -3,6 +3,7 @@
 #
 config XIL_AXIS_FIFO
 	tristate "Xilinx AXI-Stream FIFO IP core driver"
+	depends on OF
 	default n
 	help
 	  This adds support for the Xilinx AXI-Stream
diff --git a/drivers/staging/comedi/comedidev.h b/drivers/staging/comedi/comedidev.h
index a7d569cfca5d..0dff1ac057cd 100644
--- a/drivers/staging/comedi/comedidev.h
+++ b/drivers/staging/comedi/comedidev.h
@@ -1001,6 +1001,8 @@ int comedi_dio_insn_config(struct comedi_device *dev,
 			   unsigned int mask);
 unsigned int comedi_dio_update_state(struct comedi_subdevice *s,
 				     unsigned int *data);
+unsigned int comedi_bytes_per_scan_cmd(struct comedi_subdevice *s,
+				       struct comedi_cmd *cmd);
 unsigned int comedi_bytes_per_scan(struct comedi_subdevice *s);
 unsigned int comedi_nscans_left(struct comedi_subdevice *s,
 				unsigned int nscans);
diff --git a/drivers/staging/comedi/drivers.c b/drivers/staging/comedi/drivers.c
index eefa62f42c0f..5a32b8fc000e 100644
--- a/drivers/staging/comedi/drivers.c
+++ b/drivers/staging/comedi/drivers.c
@@ -394,11 +394,13 @@ unsigned int comedi_dio_update_state(struct comedi_subdevice *s,
 EXPORT_SYMBOL_GPL(comedi_dio_update_state);
 
 /**
- * comedi_bytes_per_scan() - Get length of asynchronous command "scan" in bytes
+ * comedi_bytes_per_scan_cmd() - Get length of asynchronous command "scan" in
+ * bytes
  * @s: COMEDI subdevice.
+ * @cmd: COMEDI command.
  *
  * Determines the overall scan length according to the subdevice type and the
- * number of channels in the scan.
+ * number of channels in the scan for the specified command.
  *
  * For digital input, output or input/output subdevices, samples for
  * multiple channels are assumed to be packed into one or more unsigned
@@ -408,9 +410,9 @@ EXPORT_SYMBOL_GPL(comedi_dio_update_state);
  *
  * Returns the overall scan length in bytes.
  */
-unsigned int comedi_bytes_per_scan(struct comedi_subdevice *s)
+unsigned int comedi_bytes_per_scan_cmd(struct comedi_subdevice *s,
+				       struct comedi_cmd *cmd)
 {
-	struct comedi_cmd *cmd = &s->async->cmd;
 	unsigned int num_samples;
 	unsigned int bits_per_sample;
 
@@ -427,6 +429,29 @@ unsigned int comedi_bytes_per_scan(struct comedi_subdevice *s)
 	}
 	return comedi_samples_to_bytes(s, num_samples);
 }
+EXPORT_SYMBOL_GPL(comedi_bytes_per_scan_cmd);
+
+/**
+ * comedi_bytes_per_scan() - Get length of asynchronous command "scan" in bytes
+ * @s: COMEDI subdevice.
+ *
+ * Determines the overall scan length according to the subdevice type and the
+ * number of channels in the scan for the current command.
+ *
+ * For digital input, output or input/output subdevices, samples for
+ * multiple channels are assumed to be packed into one or more unsigned
+ * short or unsigned int values according to the subdevice's %SDF_LSAMPL
+ * flag.  For other types of subdevice, samples are assumed to occupy a
+ * whole unsigned short or unsigned int according to the %SDF_LSAMPL flag.
+ *
+ * Returns the overall scan length in bytes.
+ */
+unsigned int comedi_bytes_per_scan(struct comedi_subdevice *s)
+{
+	struct comedi_cmd *cmd = &s->async->cmd;
+
+	return comedi_bytes_per_scan_cmd(s, cmd);
+}
 EXPORT_SYMBOL_GPL(comedi_bytes_per_scan);
 
 static unsigned int __comedi_nscans_left(struct comedi_subdevice *s,
diff --git a/drivers/staging/comedi/drivers/mite.c b/drivers/staging/comedi/drivers/mite.c
index 61e03ad84123..639ec1586976 100644
--- a/drivers/staging/comedi/drivers/mite.c
+++ b/drivers/staging/comedi/drivers/mite.c
@@ -371,7 +371,6 @@ static unsigned int mite_get_status(struct mite_channel *mite_chan)
 		writel(CHOR_CLRDONE,
 		       mite->mmio + MITE_CHOR(mite_chan->channel));
 	}
-	mmiowb();
 	spin_unlock_irqrestore(&mite->lock, flags);
 	return status;
 }
@@ -451,7 +450,6 @@ void mite_dma_arm(struct mite_channel *mite_chan)
 	mite_chan->done = 0;
 	/* arm */
 	writel(CHOR_START, mite->mmio + MITE_CHOR(mite_chan->channel));
-	mmiowb();
 	spin_unlock_irqrestore(&mite->lock, flags);
 }
 EXPORT_SYMBOL_GPL(mite_dma_arm);
@@ -638,7 +636,6 @@ void mite_release_channel(struct mite_channel *mite_chan)
 		       CHCR_CLR_LC_IE | CHCR_CLR_CONT_RB_IE,
 		       mite->mmio + MITE_CHCR(mite_chan->channel));
 		mite_chan->ring = NULL;
-		mmiowb();
 	}
 	spin_unlock_irqrestore(&mite->lock, flags);
 }
diff --git a/drivers/staging/comedi/drivers/ni_660x.c b/drivers/staging/comedi/drivers/ni_660x.c
index 405573e927cf..4ee9b260eab0 100644
--- a/drivers/staging/comedi/drivers/ni_660x.c
+++ b/drivers/staging/comedi/drivers/ni_660x.c
@@ -320,7 +320,6 @@ static inline void ni_660x_set_dma_channel(struct comedi_device *dev,
 	ni_660x_write(dev, chip, devpriv->dma_cfg[chip] |
 		      NI660X_DMA_CFG_RESET(mite_channel),
 		      NI660X_DMA_CFG);
-	mmiowb();
 }
 
 static inline void ni_660x_unset_dma_channel(struct comedi_device *dev,
@@ -333,7 +332,6 @@ static inline void ni_660x_unset_dma_channel(struct comedi_device *dev,
 	devpriv->dma_cfg[chip] &= ~NI660X_DMA_CFG_SEL_MASK(mite_channel);
 	devpriv->dma_cfg[chip] |= NI660X_DMA_CFG_SEL_NONE(mite_channel);
 	ni_660x_write(dev, chip, devpriv->dma_cfg[chip], NI660X_DMA_CFG);
-	mmiowb();
 }
 
 static int ni_660x_request_mite_channel(struct comedi_device *dev,
diff --git a/drivers/staging/comedi/drivers/ni_mio_common.c b/drivers/staging/comedi/drivers/ni_mio_common.c
index 5edf59ac6706..668f2aa16baa 100644
--- a/drivers/staging/comedi/drivers/ni_mio_common.c
+++ b/drivers/staging/comedi/drivers/ni_mio_common.c
@@ -547,7 +547,6 @@ static inline void ni_set_bitfield(struct comedi_device *dev, int reg,
 			reg);
 		break;
 	}
-	mmiowb();
 	spin_unlock_irqrestore(&devpriv->soft_reg_copy_lock, flags);
 }
 
@@ -3545,6 +3544,7 @@ static int ni_cdio_cmdtest(struct comedi_device *dev,
 			   struct comedi_subdevice *s, struct comedi_cmd *cmd)
 {
 	struct ni_private *devpriv = dev->private;
+	unsigned int bytes_per_scan;
 	int err = 0;
 
 	/* Step 1 : check if triggers are trivially valid */
@@ -3579,9 +3579,12 @@ static int ni_cdio_cmdtest(struct comedi_device *dev,
 	err |= comedi_check_trigger_arg_is(&cmd->convert_arg, 0);
 	err |= comedi_check_trigger_arg_is(&cmd->scan_end_arg,
 					   cmd->chanlist_len);
-	err |= comedi_check_trigger_arg_max(&cmd->stop_arg,
-					    s->async->prealloc_bufsz /
-					    comedi_bytes_per_scan(s));
+	bytes_per_scan = comedi_bytes_per_scan_cmd(s, cmd);
+	if (bytes_per_scan) {
+		err |= comedi_check_trigger_arg_max(&cmd->stop_arg,
+						    s->async->prealloc_bufsz /
+						    bytes_per_scan);
+	}
 
 	if (err)
 		return 3;
diff --git a/drivers/staging/comedi/drivers/ni_pcidio.c b/drivers/staging/comedi/drivers/ni_pcidio.c
index 4bdef87d5dd7..8f3864799c19 100644
--- a/drivers/staging/comedi/drivers/ni_pcidio.c
+++ b/drivers/staging/comedi/drivers/ni_pcidio.c
@@ -310,7 +310,6 @@ static int ni_pcidio_request_di_mite_channel(struct comedi_device *dev)
 	writeb(primary_DMAChannel_bits(devpriv->di_mite_chan->channel) |
 	       secondary_DMAChannel_bits(devpriv->di_mite_chan->channel),
 	       dev->mmio + DMA_LINE_CONTROL_GROUP1);
-	mmiowb();
 	spin_unlock_irqrestore(&devpriv->mite_channel_lock, flags);
 	return 0;
 }
@@ -327,7 +326,6 @@ static void ni_pcidio_release_di_mite_channel(struct comedi_device *dev)
 		writeb(primary_DMAChannel_bits(0) |
 		       secondary_DMAChannel_bits(0),
 		       dev->mmio + DMA_LINE_CONTROL_GROUP1);
-		mmiowb();
 	}
 	spin_unlock_irqrestore(&devpriv->mite_channel_lock, flags);
 }
diff --git a/drivers/staging/comedi/drivers/ni_tio.c b/drivers/staging/comedi/drivers/ni_tio.c
index 048cb35723ad..c1131a1622c0 100644
--- a/drivers/staging/comedi/drivers/ni_tio.c
+++ b/drivers/staging/comedi/drivers/ni_tio.c
@@ -234,7 +234,6 @@ static void ni_tio_set_bits_transient(struct ni_gpct *counter,
 		regs[reg] &= ~mask;
 		regs[reg] |= (value & mask);
 		ni_tio_write(counter, regs[reg] | transient, reg);
-		mmiowb();
 		spin_unlock_irqrestore(&counter_dev->regs_lock, flags);
 	}
 }
diff --git a/drivers/staging/comedi/drivers/ni_usb6501.c b/drivers/staging/comedi/drivers/ni_usb6501.c
index 808ed92ed66f..1bb1cb651349 100644
--- a/drivers/staging/comedi/drivers/ni_usb6501.c
+++ b/drivers/staging/comedi/drivers/ni_usb6501.c
@@ -463,10 +463,8 @@ static int ni6501_alloc_usb_buffers(struct comedi_device *dev)
 
 	size = usb_endpoint_maxp(devpriv->ep_tx);
 	devpriv->usb_tx_buf = kzalloc(size, GFP_KERNEL);
-	if (!devpriv->usb_tx_buf) {
-		kfree(devpriv->usb_rx_buf);
+	if (!devpriv->usb_tx_buf)
 		return -ENOMEM;
-	}
 
 	return 0;
 }
@@ -518,6 +516,9 @@ static int ni6501_auto_attach(struct comedi_device *dev,
 	if (!devpriv)
 		return -ENOMEM;
 
+	mutex_init(&devpriv->mut);
+	usb_set_intfdata(intf, devpriv);
+
 	ret = ni6501_find_endpoints(dev);
 	if (ret)
 		return ret;
@@ -526,9 +527,6 @@ static int ni6501_auto_attach(struct comedi_device *dev,
 	if (ret)
 		return ret;
 
-	mutex_init(&devpriv->mut);
-	usb_set_intfdata(intf, devpriv);
-
 	ret = comedi_alloc_subdevices(dev, 2);
 	if (ret)
 		return ret;
diff --git a/drivers/staging/comedi/drivers/s626.c b/drivers/staging/comedi/drivers/s626.c
index f5af6f4069dc..39049d3c56d7 100644
--- a/drivers/staging/comedi/drivers/s626.c
+++ b/drivers/staging/comedi/drivers/s626.c
@@ -108,7 +108,6 @@ static void s626_mc_enable(struct comedi_device *dev,
 {
 	unsigned int val = (cmd << 16) | cmd;
 
-	mmiowb();
 	writel(val, dev->mmio + reg);
 }
 
@@ -116,7 +115,6 @@ static void s626_mc_disable(struct comedi_device *dev,
 			    unsigned int cmd, unsigned int reg)
 {
 	writel(cmd << 16, dev->mmio + reg);
-	mmiowb();
 }
 
 static bool s626_mc_test(struct comedi_device *dev,
diff --git a/drivers/staging/comedi/drivers/vmk80xx.c b/drivers/staging/comedi/drivers/vmk80xx.c
index 6234b649d887..65dc6c51037e 100644
--- a/drivers/staging/comedi/drivers/vmk80xx.c
+++ b/drivers/staging/comedi/drivers/vmk80xx.c
@@ -682,10 +682,8 @@ static int vmk80xx_alloc_usb_buffers(struct comedi_device *dev)
 
 	size = usb_endpoint_maxp(devpriv->ep_tx);
 	devpriv->usb_tx_buf = kzalloc(size, GFP_KERNEL);
-	if (!devpriv->usb_tx_buf) {
-		kfree(devpriv->usb_rx_buf);
+	if (!devpriv->usb_tx_buf)
 		return -ENOMEM;
-	}
 
 	return 0;
 }
@@ -800,6 +798,8 @@ static int vmk80xx_auto_attach(struct comedi_device *dev,
 
 	devpriv->model = board->model;
 
+	sema_init(&devpriv->limit_sem, 8);
+
 	ret = vmk80xx_find_usb_endpoints(dev);
 	if (ret)
 		return ret;
@@ -808,8 +808,6 @@ static int vmk80xx_auto_attach(struct comedi_device *dev,
 	if (ret)
 		return ret;
 
-	sema_init(&devpriv->limit_sem, 8);
-
 	usb_set_intfdata(intf, devpriv);
 
 	if (devpriv->model == VMK8055_MODEL)
diff --git a/drivers/staging/erofs/data.c b/drivers/staging/erofs/data.c
index 526e0dbea5b5..81af768e7248 100644
--- a/drivers/staging/erofs/data.c
+++ b/drivers/staging/erofs/data.c
@@ -298,7 +298,7 @@ submit_bio_retry:
 	*last_block = current_block;
 
 	/* shift in advance in case of it followed by too many gaps */
-	if (unlikely(bio->bi_vcnt >= bio->bi_max_vecs)) {
+	if (bio->bi_iter.bi_size >= bio->bi_max_vecs * PAGE_SIZE) {
 		/* err should reassign to 0 after submitting */
 		err = 0;
 		goto submit_bio_out;
diff --git a/drivers/staging/erofs/dir.c b/drivers/staging/erofs/dir.c
index 829f7b12e0dc..9bbc68729c11 100644
--- a/drivers/staging/erofs/dir.c
+++ b/drivers/staging/erofs/dir.c
@@ -23,6 +23,21 @@ static const unsigned char erofs_filetype_table[EROFS_FT_MAX] = {
 	[EROFS_FT_SYMLINK]	= DT_LNK,
 };
 
+static void debug_one_dentry(unsigned char d_type, const char *de_name,
+			     unsigned int de_namelen)
+{
+#ifdef CONFIG_EROFS_FS_DEBUG
+	/* since the on-disk name could not have the trailing '\0' */
+	unsigned char dbg_namebuf[EROFS_NAME_LEN + 1];
+
+	memcpy(dbg_namebuf, de_name, de_namelen);
+	dbg_namebuf[de_namelen] = '\0';
+
+	debugln("found dirent %s de_len %u d_type %d", dbg_namebuf,
+		de_namelen, d_type);
+#endif
+}
+
 static int erofs_fill_dentries(struct dir_context *ctx,
 			       void *dentry_blk, unsigned int *ofs,
 			       unsigned int nameoff, unsigned int maxsize)
@@ -33,14 +48,10 @@ static int erofs_fill_dentries(struct dir_context *ctx,
 	de = dentry_blk + *ofs;
 	while (de < end) {
 		const char *de_name;
-		int de_namelen;
+		unsigned int de_namelen;
 		unsigned char d_type;
-#ifdef CONFIG_EROFS_FS_DEBUG
-		unsigned int dbg_namelen;
-		unsigned char dbg_namebuf[EROFS_NAME_LEN];
-#endif
 
-		if (unlikely(de->file_type < EROFS_FT_MAX))
+		if (de->file_type < EROFS_FT_MAX)
 			d_type = erofs_filetype_table[de->file_type];
 		else
 			d_type = DT_UNKNOWN;
@@ -48,26 +59,20 @@ static int erofs_fill_dentries(struct dir_context *ctx,
 		nameoff = le16_to_cpu(de->nameoff);
 		de_name = (char *)dentry_blk + nameoff;
 
-		de_namelen = unlikely(de + 1 >= end) ?
-			/* last directory entry */
-			strnlen(de_name, maxsize - nameoff) :
-			le16_to_cpu(de[1].nameoff) - nameoff;
+		/* the last dirent in the block? */
+		if (de + 1 >= end)
+			de_namelen = strnlen(de_name, maxsize - nameoff);
+		else
+			de_namelen = le16_to_cpu(de[1].nameoff) - nameoff;
 
 		/* a corrupted entry is found */
-		if (unlikely(de_namelen < 0)) {
+		if (unlikely(nameoff + de_namelen > maxsize ||
+			     de_namelen > EROFS_NAME_LEN)) {
 			DBG_BUGON(1);
 			return -EIO;
 		}
 
-#ifdef CONFIG_EROFS_FS_DEBUG
-		dbg_namelen = min(EROFS_NAME_LEN - 1, de_namelen);
-		memcpy(dbg_namebuf, de_name, dbg_namelen);
-		dbg_namebuf[dbg_namelen] = '\0';
-
-		debugln("%s, found de_name %s de_len %d d_type %d", __func__,
-			dbg_namebuf, de_namelen, d_type);
-#endif
-
+		debug_one_dentry(d_type, de_name, de_namelen);
 		if (!dir_emit(ctx, de_name, de_namelen,
 			      le64_to_cpu(de->nid), d_type))
 			/* stopped by some reason */
diff --git a/drivers/staging/erofs/unzip_vle.c b/drivers/staging/erofs/unzip_vle.c
index 8715bc50e09c..31eef8395774 100644
--- a/drivers/staging/erofs/unzip_vle.c
+++ b/drivers/staging/erofs/unzip_vle.c
@@ -972,6 +972,7 @@ repeat:
 	overlapped = false;
 	compressed_pages = grp->compressed_pages;
 
+	err = 0;
 	for (i = 0; i < clusterpages; ++i) {
 		unsigned int pagenr;
 
@@ -981,26 +982,39 @@ repeat:
 		DBG_BUGON(!page);
 		DBG_BUGON(!page->mapping);
 
-		if (z_erofs_is_stagingpage(page))
-			continue;
+		if (!z_erofs_is_stagingpage(page)) {
 #ifdef EROFS_FS_HAS_MANAGED_CACHE
-		if (page->mapping == MNGD_MAPPING(sbi)) {
-			DBG_BUGON(!PageUptodate(page));
-			continue;
-		}
+			if (page->mapping == MNGD_MAPPING(sbi)) {
+				if (unlikely(!PageUptodate(page)))
+					err = -EIO;
+				continue;
+			}
 #endif
 
-		/* only non-head page could be reused as a compressed page */
-		pagenr = z_erofs_onlinepage_index(page);
+			/*
+			 * only if non-head page can be selected
+			 * for inplace decompression
+			 */
+			pagenr = z_erofs_onlinepage_index(page);
 
-		DBG_BUGON(pagenr >= nr_pages);
-		DBG_BUGON(pages[pagenr]);
-		++sparsemem_pages;
-		pages[pagenr] = page;
+			DBG_BUGON(pagenr >= nr_pages);
+			DBG_BUGON(pages[pagenr]);
+			++sparsemem_pages;
+			pages[pagenr] = page;
 
-		overlapped = true;
+			overlapped = true;
+		}
+
+		/* PG_error needs checking for inplaced and staging pages */
+		if (unlikely(PageError(page))) {
+			DBG_BUGON(PageUptodate(page));
+			err = -EIO;
+		}
 	}
 
+	if (unlikely(err))
+		goto out;
+
 	llen = (nr_pages << PAGE_SHIFT) - work->pageofs;
 
 	if (z_erofs_vle_workgrp_fmt(grp) == Z_EROFS_VLE_WORKGRP_FMT_PLAIN) {
@@ -1029,6 +1043,10 @@ repeat:
 
 skip_allocpage:
 	vout = erofs_vmap(pages, nr_pages);
+	if (!vout) {
+		err = -ENOMEM;
+		goto out;
+	}
 
 	err = z_erofs_vle_unzip_vmap(compressed_pages,
 		clusterpages, vout, llen, work->pageofs, overlapped);
@@ -1194,6 +1212,7 @@ repeat:
 	if (page->mapping == mc) {
 		WRITE_ONCE(grp->compressed_pages[nr], page);
 
+		ClearPageError(page);
 		if (!PagePrivate(page)) {
 			/*
 			 * impossible to be !PagePrivate(page) for
diff --git a/drivers/staging/erofs/unzip_vle_lz4.c b/drivers/staging/erofs/unzip_vle_lz4.c
index 48b263a2731a..0daac9b984a8 100644
--- a/drivers/staging/erofs/unzip_vle_lz4.c
+++ b/drivers/staging/erofs/unzip_vle_lz4.c
@@ -136,10 +136,13 @@ int z_erofs_vle_unzip_fast_percpu(struct page **compressed_pages,
 
 	nr_pages = DIV_ROUND_UP(outlen + pageofs, PAGE_SIZE);
 
-	if (clusterpages == 1)
+	if (clusterpages == 1) {
 		vin = kmap_atomic(compressed_pages[0]);
-	else
+	} else {
 		vin = erofs_vmap(compressed_pages, clusterpages);
+		if (!vin)
+			return -ENOMEM;
+	}
 
 	preempt_disable();
 	vout = erofs_pcpubuf[smp_processor_id()].data;
diff --git a/drivers/staging/iio/adc/ad7192.c b/drivers/staging/iio/adc/ad7192.c
index acdbc07fd259..2fc8bc22b57b 100644
--- a/drivers/staging/iio/adc/ad7192.c
+++ b/drivers/staging/iio/adc/ad7192.c
@@ -109,10 +109,10 @@
 #define AD7192_CH_AIN3		BIT(6) /* AIN3 - AINCOM */
 #define AD7192_CH_AIN4		BIT(7) /* AIN4 - AINCOM */
 
-#define AD7193_CH_AIN1P_AIN2M	0x000  /* AIN1(+) - AIN2(-) */
-#define AD7193_CH_AIN3P_AIN4M	0x001  /* AIN3(+) - AIN4(-) */
-#define AD7193_CH_AIN5P_AIN6M	0x002  /* AIN5(+) - AIN6(-) */
-#define AD7193_CH_AIN7P_AIN8M	0x004  /* AIN7(+) - AIN8(-) */
+#define AD7193_CH_AIN1P_AIN2M	0x001  /* AIN1(+) - AIN2(-) */
+#define AD7193_CH_AIN3P_AIN4M	0x002  /* AIN3(+) - AIN4(-) */
+#define AD7193_CH_AIN5P_AIN6M	0x004  /* AIN5(+) - AIN6(-) */
+#define AD7193_CH_AIN7P_AIN8M	0x008  /* AIN7(+) - AIN8(-) */
 #define AD7193_CH_TEMP		0x100 /* Temp senseor */
 #define AD7193_CH_AIN2P_AIN2M	0x200 /* AIN2(+) - AIN2(-) */
 #define AD7193_CH_AIN1		0x401 /* AIN1 - AINCOM */
diff --git a/drivers/staging/iio/meter/ade7854.c b/drivers/staging/iio/meter/ade7854.c
index 029c3bf42d4d..07774c000c5a 100644
--- a/drivers/staging/iio/meter/ade7854.c
+++ b/drivers/staging/iio/meter/ade7854.c
@@ -269,7 +269,7 @@ static IIO_DEV_ATTR_VPEAK(0644,
 static IIO_DEV_ATTR_IPEAK(0644,
 		ade7854_read_32bit,
 		ade7854_write_32bit,
-		ADE7854_VPEAK);
+		ADE7854_IPEAK);
 static IIO_DEV_ATTR_APHCAL(0644,
 		ade7854_read_16bit,
 		ade7854_write_16bit,
diff --git a/drivers/staging/ks7010/ks_hostif.c b/drivers/staging/ks7010/ks_hostif.c
index 06ebea0be118..122d4c0af363 100644
--- a/drivers/staging/ks7010/ks_hostif.c
+++ b/drivers/staging/ks7010/ks_hostif.c
@@ -219,7 +219,6 @@ michael_mic(u8 *key, u8 *data, unsigned int len, u8 priority, u8 *result)
 	}
 
 	desc->tfm = tfm;
-	desc->flags = 0;
 
 	ret = crypto_shash_init(desc);
 	if (ret < 0)
diff --git a/drivers/staging/most/core.c b/drivers/staging/most/core.c
index 18936cdb1083..956daf8c3bd2 100644
--- a/drivers/staging/most/core.c
+++ b/drivers/staging/most/core.c
@@ -1431,7 +1431,7 @@ int most_register_interface(struct most_interface *iface)
 
 	INIT_LIST_HEAD(&iface->p->channel_list);
 	iface->p->dev_id = id;
-	snprintf(iface->p->name, STRING_SIZE, "mdev%d", id);
+	strcpy(iface->p->name, iface->description);
 	iface->dev.init_name = iface->p->name;
 	iface->dev.bus = &mc.bus;
 	iface->dev.parent = &mc.dev;
diff --git a/drivers/staging/mt7621-dts/gbpc1.dts b/drivers/staging/mt7621-dts/gbpc1.dts
index b73385540216..250c15ace2a7 100644
--- a/drivers/staging/mt7621-dts/gbpc1.dts
+++ b/drivers/staging/mt7621-dts/gbpc1.dts
@@ -117,22 +117,6 @@
 	status = "okay";
 };
 
-&ethernet {
-	//mtd-mac-address = <&factory 0xe000>;
-	gmac1: mac@0 {
-		compatible = "mediatek,eth-mac";
-		reg = <0>;
-		phy-handle = <&phy1>;
-	};
-
-	mdio-bus {
-		phy1: ethernet-phy@1 {
-			reg = <1>;
-			phy-mode = "rgmii";
-		};
-	};
-};
-
 &pinctrl {
 	state_default: pinctrl0 {
 		gpio {
@@ -141,3 +125,16 @@
 		};
 	};
 };
+
+&switch0 {
+	ports {
+		port@0 {
+			label = "ethblack";
+			status = "ok";
+		};
+		port@4 {
+			label = "ethblue";
+			status = "ok";
+		};
+	};
+};
diff --git a/drivers/staging/mt7621-dts/mt7621.dtsi b/drivers/staging/mt7621-dts/mt7621.dtsi
index 6aff3680ce4b..17020e24abd2 100644
--- a/drivers/staging/mt7621-dts/mt7621.dtsi
+++ b/drivers/staging/mt7621-dts/mt7621.dtsi
@@ -372,16 +372,83 @@
 
 		mediatek,ethsys = <&ethsys>;
 
-		mediatek,switch = <&gsw>;
 
+		gmac0: mac@0 {
+			compatible = "mediatek,eth-mac";
+			reg = <0>;
+			phy-mode = "rgmii";
+			fixed-link {
+				speed = <1000>;
+				full-duplex;
+				pause;
+			};
+		};
+		gmac1: mac@1 {
+			compatible = "mediatek,eth-mac";
+			reg = <1>;
+			status = "off";
+			phy-mode = "rgmii";
+			phy-handle = <&phy5>;
+		};
 		mdio-bus {
 			#address-cells = <1>;
 			#size-cells = <0>;
 
-			phy1f: ethernet-phy@1f {
-				reg = <0x1f>;
+			phy5: ethernet-phy@5 {
+				reg = <5>;
 				phy-mode = "rgmii";
 			};
+
+			switch0: switch0@0 {
+				compatible = "mediatek,mt7621";
+				#address-cells = <1>;
+				#size-cells = <0>;
+				reg = <0>;
+				mediatek,mcm;
+				resets = <&rstctrl 2>;
+				reset-names = "mcm";
+
+				ports {
+					#address-cells = <1>;
+					#size-cells = <0>;
+					reg = <0>;
+					port@0 {
+						status = "off";
+						reg = <0>;
+						label = "lan0";
+					};
+					port@1 {
+						status = "off";
+						reg = <1>;
+						label = "lan1";
+					};
+					port@2 {
+						status = "off";
+						reg = <2>;
+						label = "lan2";
+					};
+					port@3 {
+						status = "off";
+						reg = <3>;
+						label = "lan3";
+					};
+					port@4 {
+						status = "off";
+						reg = <4>;
+						label = "lan4";
+					};
+					port@6 {
+						reg = <6>;
+						label = "cpu";
+						ethernet = <&gmac0>;
+						phy-mode = "trgmii";
+						fixed-link {
+							speed = <1000>;
+							full-duplex;
+						};
+					};
+				};
+			};
 		};
 	};
 
diff --git a/drivers/staging/mt7621-eth/Documentation/devicetree/bindings/net/mediatek-net-gsw.txt b/drivers/staging/mt7621-eth/Documentation/devicetree/bindings/net/mediatek-net-gsw.txt
deleted file mode 100644
index 596b38552697..000000000000
--- a/drivers/staging/mt7621-eth/Documentation/devicetree/bindings/net/mediatek-net-gsw.txt
+++ /dev/null
@@ -1,48 +0,0 @@
-Mediatek Gigabit Switch
-=======================
-
-The mediatek gigabit switch can be found on Mediatek SoCs.
-
-Required properties:
-- compatible: Should be "mediatek,mt7620-gsw", "mediatek,mt7621-gsw",
-  "mediatek,mt7623-gsw"
-- reg: Address and length of the register set for the device
-- interrupts: Should contain the gigabit switches interrupt
-
-
-Additional required properties for ARM based SoCs:
-- mediatek,reset-pin: phandle describing the reset GPIO
-- clocks: the clocks used by the switch
-- clock-names: the names of the clocks listed in the clocks property
-  these should be "trgpll", "esw", "gp2", "gp1"
-- mt7530-supply: the phandle of the regulator used to power the switch
-- mediatek,pctl-regmap: phandle to the port control regmap. this is used to
-  setup the drive current
-
-
-Optional properties:
-- interrupt-parent: Should be the phandle for the interrupt controller
-  that services interrupts for this device
-
-Example:
-
-gsw: switch@1b100000 {
-	compatible = "mediatek,mt7623-gsw";
-	reg = <0 0x1b110000 0 0x300000>;
-
-	interrupt-parent = <&pio>;
-	interrupts = <168 IRQ_TYPE_EDGE_RISING>;
-
-	clocks = <&apmixedsys CLK_APMIXED_TRGPLL>,
-		 <&ethsys CLK_ETHSYS_ESW>,
-		 <&ethsys CLK_ETHSYS_GP2>,
-		 <&ethsys CLK_ETHSYS_GP1>;
-	clock-names = "trgpll", "esw", "gp2", "gp1";
-
-	mt7530-supply = <&mt6323_vpa_reg>;
-
-	mediatek,pctl-regmap = <&syscfg_pctl_a>;
-	mediatek,reset-pin = <&pio 15 0>;
-
-	status = "okay";
-};
diff --git a/drivers/staging/mt7621-eth/Kconfig b/drivers/staging/mt7621-eth/Kconfig
deleted file mode 100644
index 44ea86c7a96c..000000000000
--- a/drivers/staging/mt7621-eth/Kconfig
+++ /dev/null
@@ -1,39 +0,0 @@
-config NET_VENDOR_MEDIATEK_STAGING
-	bool "MediaTek ethernet driver - staging version"
-	depends on RALINK
-	---help---
-	  If you have an MT7621 Mediatek SoC with ethernet, say Y.
-
-if NET_VENDOR_MEDIATEK_STAGING
-choice
-	prompt "MAC type"
-
-config NET_MEDIATEK_MT7621
-	bool "MT7621"
-	depends on MIPS && SOC_MT7621
-
-endchoice
-
-config NET_MEDIATEK_SOC_STAGING
-	tristate "MediaTek SoC Gigabit Ethernet support"
-	depends on NET_VENDOR_MEDIATEK_STAGING
-	select PHYLIB
-	---help---
-	  This driver supports the gigabit ethernet MACs in the
-	  MediaTek SoC family.
-
-config NET_MEDIATEK_MDIO
-	def_bool NET_MEDIATEK_SOC_STAGING
-	depends on NET_MEDIATEK_MT7621
-	select PHYLIB
-
-config NET_MEDIATEK_MDIO_MT7620
-	def_bool NET_MEDIATEK_SOC_STAGING
-	depends on NET_MEDIATEK_MT7621
-	select NET_MEDIATEK_MDIO
-
-config NET_MEDIATEK_GSW_MT7621
-	def_tristate NET_MEDIATEK_SOC_STAGING
-	depends on NET_MEDIATEK_MT7621
-
-endif #NET_VENDOR_MEDIATEK_STAGING
diff --git a/drivers/staging/mt7621-eth/Makefile b/drivers/staging/mt7621-eth/Makefile
deleted file mode 100644
index 018bcc3596b3..000000000000
--- a/drivers/staging/mt7621-eth/Makefile
+++ /dev/null
@@ -1,14 +0,0 @@
-#
-# Makefile for the Ralink SoCs built-in ethernet macs
-#
-
-mtk-eth-soc-y					+= mtk_eth_soc.o ethtool.o
-
-mtk-eth-soc-$(CONFIG_NET_MEDIATEK_MDIO)		+= mdio.o
-mtk-eth-soc-$(CONFIG_NET_MEDIATEK_MDIO_MT7620)	+= mdio_mt7620.o
-
-mtk-eth-soc-$(CONFIG_NET_MEDIATEK_MT7621)	+= soc_mt7621.o
-
-obj-$(CONFIG_NET_MEDIATEK_GSW_MT7621)		+= gsw_mt7621.o
-
-obj-$(CONFIG_NET_MEDIATEK_SOC_STAGING)		+= mtk-eth-soc.o
diff --git a/drivers/staging/mt7621-eth/TODO b/drivers/staging/mt7621-eth/TODO
deleted file mode 100644
index f9e47d4b4cd4..000000000000
--- a/drivers/staging/mt7621-eth/TODO
+++ /dev/null
@@ -1,13 +0,0 @@
-
-- verify devicetree documentation is consistent with code
-- fix ethtool - currently doesn't return valid data.
-- general code review and clean up
-- add support for second MAC on mt7621
-- convert gsw code to use switchdev interfaces
-- md7620_mmi_write etc should probably be wrapped
-  in a regmap abstraction.
-- Get soc_mt7621 to work with QDMA TX if possible.
-- Ensure phys are correctly configured when a cable
-  is plugged in.
-
-Cc: NeilBrown <neil@brown.name>
diff --git a/drivers/staging/mt7621-eth/ethtool.c b/drivers/staging/mt7621-eth/ethtool.c
deleted file mode 100644
index 8c4228e2c987..000000000000
--- a/drivers/staging/mt7621-eth/ethtool.c
+++ /dev/null
@@ -1,250 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0
-/*   This program is free software; you can redistribute it and/or modify
- *   it under the terms of the GNU General Public License as published by
- *   the Free Software Foundation; version 2 of the License
- *
- *   This program is distributed in the hope that it will be useful,
- *   but WITHOUT ANY WARRANTY; without even the implied warranty of
- *   MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- *   GNU General Public License for more details.
- *
- *   Copyright (C) 2009-2016 John Crispin <blogic@openwrt.org>
- *   Copyright (C) 2009-2016 Felix Fietkau <nbd@openwrt.org>
- *   Copyright (C) 2013-2016 Michael Lee <igvtee@gmail.com>
- */
-
-#include "mtk_eth_soc.h"
-#include "ethtool.h"
-
-struct mtk_stat {
-	char name[ETH_GSTRING_LEN];
-	unsigned int idx;
-};
-
-#define MTK_HW_STAT(stat) { \
-	.name = #stat, \
-	.idx = offsetof(struct mtk_hw_stats, stat) / sizeof(u64) \
-}
-
-static const struct mtk_stat mtk_ethtool_hw_stats[] = {
-	MTK_HW_STAT(tx_bytes),
-	MTK_HW_STAT(tx_packets),
-	MTK_HW_STAT(tx_skip),
-	MTK_HW_STAT(tx_collisions),
-	MTK_HW_STAT(rx_bytes),
-	MTK_HW_STAT(rx_packets),
-	MTK_HW_STAT(rx_overflow),
-	MTK_HW_STAT(rx_fcs_errors),
-	MTK_HW_STAT(rx_short_errors),
-	MTK_HW_STAT(rx_long_errors),
-	MTK_HW_STAT(rx_checksum_errors),
-	MTK_HW_STAT(rx_flow_control_packets),
-};
-
-#define MTK_HW_STATS_LEN	ARRAY_SIZE(mtk_ethtool_hw_stats)
-
-static int mtk_get_link_ksettings(struct net_device *dev,
-				  struct ethtool_link_ksettings *cmd)
-{
-	struct mtk_mac *mac = netdev_priv(dev);
-	int err;
-
-	if (!mac->phy_dev)
-		return -ENODEV;
-
-	if (mac->phy_flags == MTK_PHY_FLAG_ATTACH) {
-		err = phy_read_status(mac->phy_dev);
-		if (err)
-			return -ENODEV;
-	}
-
-	phy_ethtool_ksettings_get(mac->phy_dev, cmd);
-	return 0;
-}
-
-static int mtk_set_link_ksettings(struct net_device *dev,
-				  const struct ethtool_link_ksettings *cmd)
-{
-	struct mtk_mac *mac = netdev_priv(dev);
-
-	if (!mac->phy_dev)
-		return -ENODEV;
-
-	if (cmd->base.phy_address != mac->phy_dev->mdio.addr) {
-		if (mac->hw->phy->phy_node[cmd->base.phy_address]) {
-			mac->phy_dev = mac->hw->phy->phy[cmd->base.phy_address];
-			mac->phy_flags = MTK_PHY_FLAG_PORT;
-		} else if (mac->hw->mii_bus) {
-			mac->phy_dev = mdiobus_get_phy(mac->hw->mii_bus,
-						       cmd->base.phy_address);
-			if (!mac->phy_dev)
-				return -ENODEV;
-			mac->phy_flags = MTK_PHY_FLAG_ATTACH;
-		} else {
-			return -ENODEV;
-		}
-	}
-
-	return phy_ethtool_ksettings_set(mac->phy_dev, cmd);
-}
-
-static void mtk_get_drvinfo(struct net_device *dev,
-			    struct ethtool_drvinfo *info)
-{
-	struct mtk_mac *mac = netdev_priv(dev);
-	struct mtk_soc_data *soc = mac->hw->soc;
-
-	strlcpy(info->driver, mac->hw->dev->driver->name, sizeof(info->driver));
-	strlcpy(info->bus_info, dev_name(mac->hw->dev), sizeof(info->bus_info));
-
-	if (soc->reg_table[MTK_REG_MTK_COUNTER_BASE])
-		info->n_stats = MTK_HW_STATS_LEN;
-}
-
-static u32 mtk_get_msglevel(struct net_device *dev)
-{
-	struct mtk_mac *mac = netdev_priv(dev);
-
-	return mac->hw->msg_enable;
-}
-
-static void mtk_set_msglevel(struct net_device *dev, u32 value)
-{
-	struct mtk_mac *mac = netdev_priv(dev);
-
-	mac->hw->msg_enable = value;
-}
-
-static int mtk_nway_reset(struct net_device *dev)
-{
-	struct mtk_mac *mac = netdev_priv(dev);
-
-	if (!mac->phy_dev)
-		return -EOPNOTSUPP;
-
-	return genphy_restart_aneg(mac->phy_dev);
-}
-
-static u32 mtk_get_link(struct net_device *dev)
-{
-	struct mtk_mac *mac = netdev_priv(dev);
-	int err;
-
-	if (!mac->phy_dev)
-		goto out_get_link;
-
-	if (mac->phy_flags == MTK_PHY_FLAG_ATTACH) {
-		err = genphy_update_link(mac->phy_dev);
-		if (err)
-			goto out_get_link;
-	}
-
-	return mac->phy_dev->link;
-
-out_get_link:
-	return ethtool_op_get_link(dev);
-}
-
-static int mtk_set_ringparam(struct net_device *dev,
-			     struct ethtool_ringparam *ring)
-{
-	struct mtk_mac *mac = netdev_priv(dev);
-
-	if ((ring->tx_pending < 2) ||
-	    (ring->rx_pending < 2) ||
-	    (ring->rx_pending > mac->hw->soc->dma_ring_size) ||
-	    (ring->tx_pending > mac->hw->soc->dma_ring_size))
-		return -EINVAL;
-
-	dev->netdev_ops->ndo_stop(dev);
-
-	mac->hw->tx_ring.tx_ring_size = BIT(fls(ring->tx_pending) - 1);
-	mac->hw->rx_ring[0].rx_ring_size = BIT(fls(ring->rx_pending) - 1);
-
-	return dev->netdev_ops->ndo_open(dev);
-}
-
-static void mtk_get_ringparam(struct net_device *dev,
-			      struct ethtool_ringparam *ring)
-{
-	struct mtk_mac *mac = netdev_priv(dev);
-
-	ring->rx_max_pending = mac->hw->soc->dma_ring_size;
-	ring->tx_max_pending = mac->hw->soc->dma_ring_size;
-	ring->rx_pending = mac->hw->rx_ring[0].rx_ring_size;
-	ring->tx_pending = mac->hw->tx_ring.tx_ring_size;
-}
-
-static void mtk_get_strings(struct net_device *dev, u32 stringset, u8 *data)
-{
-	int i;
-
-	switch (stringset) {
-	case ETH_SS_STATS:
-		for (i = 0; i < MTK_HW_STATS_LEN; i++) {
-			memcpy(data, mtk_ethtool_hw_stats[i].name,
-			       ETH_GSTRING_LEN);
-			data += ETH_GSTRING_LEN;
-		}
-		break;
-	}
-}
-
-static int mtk_get_sset_count(struct net_device *dev, int sset)
-{
-	switch (sset) {
-	case ETH_SS_STATS:
-		return MTK_HW_STATS_LEN;
-	default:
-		return -EOPNOTSUPP;
-	}
-}
-
-static void mtk_get_ethtool_stats(struct net_device *dev,
-				  struct ethtool_stats *stats, u64 *data)
-{
-	struct mtk_mac *mac = netdev_priv(dev);
-	struct mtk_hw_stats *hwstats = mac->hw_stats;
-	unsigned int start;
-	int i;
-
-	if (netif_running(dev) && netif_device_present(dev)) {
-		if (spin_trylock(&hwstats->stats_lock)) {
-			mtk_stats_update_mac(mac);
-			spin_unlock(&hwstats->stats_lock);
-		}
-	}
-
-	do {
-		start = u64_stats_fetch_begin_irq(&hwstats->syncp);
-		for (i = 0; i < MTK_HW_STATS_LEN; i++)
-			data[i] = ((u64 *)hwstats)[mtk_ethtool_hw_stats[i].idx];
-
-	} while (u64_stats_fetch_retry_irq(&hwstats->syncp, start));
-}
-
-static struct ethtool_ops mtk_ethtool_ops = {
-	.get_link_ksettings     = mtk_get_link_ksettings,
-	.set_link_ksettings     = mtk_set_link_ksettings,
-	.get_drvinfo		= mtk_get_drvinfo,
-	.get_msglevel		= mtk_get_msglevel,
-	.set_msglevel		= mtk_set_msglevel,
-	.nway_reset		= mtk_nway_reset,
-	.get_link		= mtk_get_link,
-	.set_ringparam		= mtk_set_ringparam,
-	.get_ringparam		= mtk_get_ringparam,
-};
-
-void mtk_set_ethtool_ops(struct net_device *netdev)
-{
-	struct mtk_mac *mac = netdev_priv(netdev);
-	struct mtk_soc_data *soc = mac->hw->soc;
-
-	if (soc->reg_table[MTK_REG_MTK_COUNTER_BASE]) {
-		mtk_ethtool_ops.get_strings = mtk_get_strings;
-		mtk_ethtool_ops.get_sset_count = mtk_get_sset_count;
-		mtk_ethtool_ops.get_ethtool_stats = mtk_get_ethtool_stats;
-	}
-
-	netdev->ethtool_ops = &mtk_ethtool_ops;
-}
diff --git a/drivers/staging/mt7621-eth/ethtool.h b/drivers/staging/mt7621-eth/ethtool.h
deleted file mode 100644
index 0071469aea6c..000000000000
--- a/drivers/staging/mt7621-eth/ethtool.h
+++ /dev/null
@@ -1,15 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 */
-/*
- *   Copyright (C) 2009-2016 John Crispin <blogic@openwrt.org>
- *   Copyright (C) 2009-2016 Felix Fietkau <nbd@openwrt.org>
- *   Copyright (C) 2013-2016 Michael Lee <igvtee@gmail.com>
- */
-
-#ifndef MTK_ETHTOOL_H
-#define MTK_ETHTOOL_H
-
-#include <linux/ethtool.h>
-
-void mtk_set_ethtool_ops(struct net_device *netdev);
-
-#endif /* MTK_ETHTOOL_H */
diff --git a/drivers/staging/mt7621-eth/gsw_mt7620.h b/drivers/staging/mt7621-eth/gsw_mt7620.h
deleted file mode 100644
index 70f7e5481952..000000000000
--- a/drivers/staging/mt7621-eth/gsw_mt7620.h
+++ /dev/null
@@ -1,277 +0,0 @@
-/*   This program is free software; you can redistribute it and/or modify
- *   it under the terms of the GNU General Public License as published by
- *   the Free Software Foundation; version 2 of the License
- *
- *   This program is distributed in the hope that it will be useful,
- *   but WITHOUT ANY WARRANTY; without even the implied warranty of
- *   MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- *   GNU General Public License for more details.
- *
- *   Copyright (C) 2009-2016 John Crispin <blogic@openwrt.org>
- *   Copyright (C) 2009-2016 Felix Fietkau <nbd@openwrt.org>
- *   Copyright (C) 2013-2016 Michael Lee <igvtee@gmail.com>
- */
-
-#ifndef _RALINK_GSW_MT7620_H__
-#define _RALINK_GSW_MT7620_H__
-
-#define GSW_REG_PHY_TIMEOUT	(5 * HZ)
-
-#define MT7620_GSW_REG_PIAC	0x0004
-
-#define GSW_NUM_VLANS		16
-#define GSW_NUM_VIDS		4096
-#define GSW_NUM_PORTS		7
-#define GSW_PORT6		6
-
-#define GSW_MDIO_ACCESS		BIT(31)
-#define GSW_MDIO_READ		BIT(19)
-#define GSW_MDIO_WRITE		BIT(18)
-#define GSW_MDIO_START		BIT(16)
-#define GSW_MDIO_ADDR_SHIFT	20
-#define GSW_MDIO_REG_SHIFT	25
-
-#define GSW_REG_PORT_PMCR(x)	(0x3000 + (x * 0x100))
-#define GSW_REG_PORT_STATUS(x)	(0x3008 + (x * 0x100))
-#define GSW_REG_SMACCR0		0x3fE4
-#define GSW_REG_SMACCR1		0x3fE8
-#define GSW_REG_CKGCR		0x3ff0
-
-#define GSW_REG_IMR		0x7008
-#define GSW_REG_ISR		0x700c
-#define GSW_REG_GPC1		0x7014
-
-#define SYSC_REG_CHIP_REV_ID	0x0c
-#define SYSC_REG_CFG		0x10
-#define SYSC_REG_CFG1		0x14
-#define RST_CTRL_MCM		BIT(2)
-#define SYSC_PAD_RGMII2_MDIO	0x58
-#define SYSC_GPIO_MODE		0x60
-
-#define PORT_IRQ_ST_CHG		0x7f
-
-#define MT7621_ESW_PHY_POLLING	0x0000
-#define MT7620_ESW_PHY_POLLING	0x7000
-
-#define	PMCR_IPG		BIT(18)
-#define	PMCR_MAC_MODE		BIT(16)
-#define	PMCR_FORCE		BIT(15)
-#define	PMCR_TX_EN		BIT(14)
-#define	PMCR_RX_EN		BIT(13)
-#define	PMCR_BACKOFF		BIT(9)
-#define	PMCR_BACKPRES		BIT(8)
-#define	PMCR_RX_FC		BIT(5)
-#define	PMCR_TX_FC		BIT(4)
-#define	PMCR_SPEED(_x)		(_x << 2)
-#define	PMCR_DUPLEX		BIT(1)
-#define	PMCR_LINK		BIT(0)
-
-#define PHY_AN_EN		BIT(31)
-#define PHY_PRE_EN		BIT(30)
-#define PMY_MDC_CONF(_x)	((_x & 0x3f) << 24)
-
-/* ethernet subsystem config register */
-#define ETHSYS_SYSCFG0		0x14
-/* ethernet subsystem clock register */
-#define ETHSYS_CLKCFG0		0x2c
-#define ETHSYS_TRGMII_CLK_SEL362_5	BIT(11)
-
-/* p5 RGMII wrapper TX clock control register */
-#define MT7530_P5RGMIITXCR	0x7b04
-/* p5 RGMII wrapper RX clock control register */
-#define MT7530_P5RGMIIRXCR	0x7b00
-/* TRGMII TDX ODT registers */
-#define MT7530_TRGMII_TD0_ODT	0x7a54
-#define MT7530_TRGMII_TD1_ODT	0x7a5c
-#define MT7530_TRGMII_TD2_ODT	0x7a64
-#define MT7530_TRGMII_TD3_ODT	0x7a6c
-#define MT7530_TRGMII_TD4_ODT	0x7a74
-#define MT7530_TRGMII_TD5_ODT	0x7a7c
-/* TRGMII TCK ctrl register */
-#define MT7530_TRGMII_TCK_CTRL	0x7a78
-/* TRGMII Tx ctrl register */
-#define MT7530_TRGMII_TXCTRL	0x7a40
-/* port 6 extended control register */
-#define MT7530_P6ECR            0x7830
-/* IO driver control register */
-#define MT7530_IO_DRV_CR	0x7810
-/* top signal control register */
-#define MT7530_TOP_SIG_CTRL	0x7808
-/* modified hwtrap register */
-#define MT7530_MHWTRAP		0x7804
-/* hwtrap status register */
-#define MT7530_HWTRAP		0x7800
-/* status interrupt register */
-#define MT7530_SYS_INT_STS	0x700c
-/* system nterrupt register */
-#define MT7530_SYS_INT_EN	0x7008
-/* system control register */
-#define MT7530_SYS_CTRL		0x7000
-/* port MAC status register */
-#define MT7530_PMSR_P(x)	(0x3008 + (x * 0x100))
-/* port MAC control register */
-#define MT7530_PMCR_P(x)	(0x3000 + (x * 0x100))
-
-#define MT7621_XTAL_SHIFT	6
-#define MT7621_XTAL_MASK	0x7
-#define MT7621_XTAL_25		6
-#define MT7621_XTAL_40		3
-#define MT7621_MDIO_DRV_MASK	(3 << 4)
-#define MT7621_GE1_MODE_MASK	(3 << 12)
-
-#define TRGMII_TXCTRL_TXC_INV	BIT(30)
-#define P6ECR_INTF_MODE_RGMII	BIT(1)
-#define P5RGMIIRXCR_C_ALIGN	BIT(8)
-#define P5RGMIIRXCR_DELAY_2	BIT(1)
-#define P5RGMIITXCR_DELAY_2	(BIT(8) | BIT(2))
-
-/* TOP_SIG_CTRL bits */
-#define TOP_SIG_CTRL_NORMAL	(BIT(17) | BIT(16))
-
-/* MHWTRAP bits */
-#define MHWTRAP_MANUAL		BIT(16)
-#define MHWTRAP_P5_MAC_SEL	BIT(13)
-#define MHWTRAP_P6_DIS		BIT(8)
-#define MHWTRAP_P5_RGMII_MODE	BIT(7)
-#define MHWTRAP_P5_DIS		BIT(6)
-#define MHWTRAP_PHY_ACCESS	BIT(5)
-
-/* HWTRAP bits */
-#define HWTRAP_XTAL_SHIFT	9
-#define HWTRAP_XTAL_MASK	0x3
-
-/* SYS_CTRL bits */
-#define SYS_CTRL_SW_RST		BIT(1)
-#define SYS_CTRL_REG_RST	BIT(0)
-
-/* PMCR bits */
-#define PMCR_IFG_XMIT_96	BIT(18)
-#define PMCR_MAC_MODE		BIT(16)
-#define PMCR_FORCE_MODE		BIT(15)
-#define PMCR_TX_EN		BIT(14)
-#define PMCR_RX_EN		BIT(13)
-#define PMCR_BACK_PRES_EN	BIT(9)
-#define PMCR_BACKOFF_EN		BIT(8)
-#define PMCR_TX_FC_EN		BIT(5)
-#define PMCR_RX_FC_EN		BIT(4)
-#define PMCR_FORCE_SPEED_1000	BIT(3)
-#define PMCR_FORCE_FDX		BIT(1)
-#define PMCR_FORCE_LNK		BIT(0)
-#define PMCR_FIXED_LINK		(PMCR_IFG_XMIT_96 | PMCR_MAC_MODE | \
-				 PMCR_FORCE_MODE | PMCR_TX_EN | PMCR_RX_EN | \
-				 PMCR_BACK_PRES_EN | PMCR_BACKOFF_EN | \
-				 PMCR_FORCE_SPEED_1000 | PMCR_FORCE_FDX | \
-				 PMCR_FORCE_LNK)
-
-#define PMCR_FIXED_LINK_FC	(PMCR_FIXED_LINK | \
-				 PMCR_TX_FC_EN | PMCR_RX_FC_EN)
-
-/* TRGMII control registers */
-#define GSW_INTF_MODE		0x390
-#define GSW_TRGMII_TD0_ODT	0x354
-#define GSW_TRGMII_TD1_ODT	0x35c
-#define GSW_TRGMII_TD2_ODT	0x364
-#define GSW_TRGMII_TD3_ODT	0x36c
-#define GSW_TRGMII_TXCTL_ODT	0x374
-#define GSW_TRGMII_TCK_ODT	0x37c
-#define GSW_TRGMII_RCK_CTRL	0x300
-
-#define INTF_MODE_TRGMII	BIT(1)
-#define TRGMII_RCK_CTRL_RX_RST	BIT(31)
-
-/* Mac control registers */
-#define MTK_MAC_P2_MCR		0x200
-#define MTK_MAC_P1_MCR		0x100
-
-#define MAC_MCR_MAX_RX_2K	BIT(29)
-#define MAC_MCR_IPG_CFG		(BIT(18) | BIT(16))
-#define MAC_MCR_FORCE_MODE	BIT(15)
-#define MAC_MCR_TX_EN		BIT(14)
-#define MAC_MCR_RX_EN		BIT(13)
-#define MAC_MCR_BACKOFF_EN	BIT(9)
-#define MAC_MCR_BACKPR_EN	BIT(8)
-#define MAC_MCR_FORCE_RX_FC	BIT(5)
-#define MAC_MCR_FORCE_TX_FC	BIT(4)
-#define MAC_MCR_SPEED_1000	BIT(3)
-#define MAC_MCR_FORCE_DPX	BIT(1)
-#define MAC_MCR_FORCE_LINK	BIT(0)
-#define MAC_MCR_FIXED_LINK	(MAC_MCR_MAX_RX_2K | MAC_MCR_IPG_CFG | \
-				 MAC_MCR_FORCE_MODE | MAC_MCR_TX_EN | \
-				 MAC_MCR_RX_EN | MAC_MCR_BACKOFF_EN | \
-				 MAC_MCR_BACKPR_EN | MAC_MCR_FORCE_RX_FC | \
-				 MAC_MCR_FORCE_TX_FC | MAC_MCR_SPEED_1000 | \
-				 MAC_MCR_FORCE_DPX | MAC_MCR_FORCE_LINK)
-#define MAC_MCR_FIXED_LINK_FC	(MAC_MCR_MAX_RX_2K | MAC_MCR_IPG_CFG | \
-				 MAC_MCR_FIXED_LINK)
-
-/* possible XTAL speed */
-#define	MT7623_XTAL_40		0
-#define MT7623_XTAL_20		1
-#define MT7623_XTAL_25		3
-
-/* GPIO port control registers */
-#define	GPIO_OD33_CTRL8		0x4c0
-#define	GPIO_BIAS_CTRL		0xed0
-#define GPIO_DRV_SEL10		0xf00
-
-/* on MT7620 the functio of port 4 can be software configured */
-enum {
-	PORT4_EPHY = 0,
-	PORT4_EXT,
-};
-
-/* struct mt7620_gsw -	the structure that holds the SoC specific data
- * @dev:		The Device struct
- * @base:		The base address
- * @piac_offset:	The PIAC base may change depending on SoC
- * @irq:		The IRQ we are using
- * @port4:		The port4 mode on MT7620
- * @autopoll:		Is MDIO autopolling enabled
- * @ethsys:		The ethsys register map
- * @pctl:		The pin control register map
- * @clk_gsw:		The switch clock
- * @clk_gp1:		The gmac1 clock
- * @clk_gp2:		The gmac2 clock
- * @clk_trgpll:		The trgmii pll clock
- */
-struct mt7620_gsw {
-	struct device		*dev;
-	void __iomem		*base;
-	u32			piac_offset;
-	int			irq;
-	int			port4;
-	unsigned long int	autopoll;
-
-	struct regmap		*ethsys;
-	struct regmap		*pctl;
-
-	struct clk		*clk_gsw;
-	struct clk		*clk_gp1;
-	struct clk		*clk_gp2;
-	struct clk		*clk_trgpll;
-};
-
-/* switch register I/O wrappers */
-void mtk_switch_w32(struct mt7620_gsw *gsw, u32 val, unsigned int reg);
-u32 mtk_switch_r32(struct mt7620_gsw *gsw, unsigned int reg);
-
-/* the callback used by the driver core to bringup the switch */
-int mtk_gsw_init(struct mtk_eth *eth);
-
-/* MDIO access wrappers */
-int mt7620_mdio_write(struct mii_bus *bus, int phy_addr, int phy_reg, u16 val);
-int mt7620_mdio_read(struct mii_bus *bus, int phy_addr, int phy_reg);
-void mt7620_mdio_link_adjust(struct mtk_eth *eth, int port);
-int mt7620_has_carrier(struct mtk_eth *eth);
-void mt7620_print_link_state(struct mtk_eth *eth, int port, int link,
-			     int speed, int duplex);
-void mt7530_mdio_w32(struct mt7620_gsw *gsw, u32 reg, u32 val);
-u32 mt7530_mdio_r32(struct mt7620_gsw *gsw, u32 reg);
-void mt7530_mdio_m32(struct mt7620_gsw *gsw, u32 mask, u32 set, u32 reg);
-
-u32 _mt7620_mii_write(struct mt7620_gsw *gsw, u32 phy_addr,
-		      u32 phy_register, u32 write_data);
-u32 _mt7620_mii_read(struct mt7620_gsw *gsw, int phy_addr, int phy_reg);
-void mt7620_handle_carrier(struct mtk_eth *eth);
-
-#endif
diff --git a/drivers/staging/mt7621-eth/gsw_mt7621.c b/drivers/staging/mt7621-eth/gsw_mt7621.c
deleted file mode 100644
index 53767b17bad9..000000000000
--- a/drivers/staging/mt7621-eth/gsw_mt7621.c
+++ /dev/null
@@ -1,297 +0,0 @@
-/*   This program is free software; you can redistribute it and/or modify
- *   it under the terms of the GNU General Public License as published by
- *   the Free Software Foundation; version 2 of the License
- *
- *   This program is distributed in the hope that it will be useful,
- *   but WITHOUT ANY WARRANTY; without even the implied warranty of
- *   MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- *   GNU General Public License for more details.
- *
- *   Copyright (C) 2009-2016 John Crispin <blogic@openwrt.org>
- *   Copyright (C) 2009-2016 Felix Fietkau <nbd@openwrt.org>
- *   Copyright (C) 2013-2016 Michael Lee <igvtee@gmail.com>
- */
-
-#include <linux/module.h>
-#include <linux/kernel.h>
-#include <linux/types.h>
-#include <linux/platform_device.h>
-#include <linux/of_device.h>
-#include <linux/of_irq.h>
-
-#include <ralink_regs.h>
-
-#include "mtk_eth_soc.h"
-#include "gsw_mt7620.h"
-
-void mtk_switch_w32(struct mt7620_gsw *gsw, u32 val, unsigned int reg)
-{
-	iowrite32(val, gsw->base + reg);
-}
-EXPORT_SYMBOL_GPL(mtk_switch_w32);
-
-u32 mtk_switch_r32(struct mt7620_gsw *gsw, unsigned int reg)
-{
-	return ioread32(gsw->base + reg);
-}
-EXPORT_SYMBOL_GPL(mtk_switch_r32);
-
-static irqreturn_t gsw_interrupt_mt7621(int irq, void *_eth)
-{
-	struct mtk_eth *eth = (struct mtk_eth *)_eth;
-	struct mt7620_gsw *gsw = (struct mt7620_gsw *)eth->sw_priv;
-	u32 reg, i;
-
-	reg = mt7530_mdio_r32(gsw, MT7530_SYS_INT_STS);
-
-	for (i = 0; i < 5; i++) {
-		unsigned int link;
-
-		if ((reg & BIT(i)) == 0)
-			continue;
-
-		link = mt7530_mdio_r32(gsw, MT7530_PMSR_P(i)) & 0x1;
-
-		if (link == eth->link[i])
-			continue;
-
-		eth->link[i] = link;
-		if (link)
-			netdev_info(*eth->netdev,
-				    "port %d link up\n", i);
-		else
-			netdev_info(*eth->netdev,
-				    "port %d link down\n", i);
-	}
-
-	mt7530_mdio_w32(gsw, MT7530_SYS_INT_STS, 0x1f);
-
-	return IRQ_HANDLED;
-}
-
-static void mt7621_hw_init(struct mtk_eth *eth, struct mt7620_gsw *gsw,
-			   struct device_node *np)
-{
-	u32 i;
-	u32 val;
-
-	/* hardware reset the switch */
-	mtk_reset(eth, RST_CTRL_MCM);
-	mdelay(10);
-
-	/* reduce RGMII2 PAD driving strength */
-	rt_sysc_m32(MT7621_MDIO_DRV_MASK, 0, SYSC_PAD_RGMII2_MDIO);
-
-	/* gpio mux - RGMII1=Normal mode */
-	rt_sysc_m32(BIT(14), 0, SYSC_GPIO_MODE);
-
-	/* set GMAC1 RGMII mode */
-	rt_sysc_m32(MT7621_GE1_MODE_MASK, 0, SYSC_REG_CFG1);
-
-	/* enable MDIO to control MT7530 */
-	rt_sysc_m32(3 << 12, 0, SYSC_GPIO_MODE);
-
-	/* turn off all PHYs */
-	for (i = 0; i <= 4; i++) {
-		val = _mt7620_mii_read(gsw, i, 0x0);
-		val |= BIT(11);
-		_mt7620_mii_write(gsw, i, 0x0, val);
-	}
-
-	/* reset the switch */
-	mt7530_mdio_w32(gsw, MT7530_SYS_CTRL,
-			SYS_CTRL_SW_RST | SYS_CTRL_REG_RST);
-	usleep_range(10, 20);
-
-	if ((rt_sysc_r32(SYSC_REG_CHIP_REV_ID) & 0xFFFF) == 0x0101) {
-		/* GE1, Force 1000M/FD, FC ON, MAX_RX_LENGTH 1536 */
-		mtk_switch_w32(gsw, MAC_MCR_FIXED_LINK, MTK_MAC_P2_MCR);
-		mt7530_mdio_w32(gsw, MT7530_PMCR_P(6), PMCR_FIXED_LINK);
-	} else {
-		/* GE1, Force 1000M/FD, FC ON, MAX_RX_LENGTH 1536 */
-		mtk_switch_w32(gsw, MAC_MCR_FIXED_LINK_FC, MTK_MAC_P1_MCR);
-		mt7530_mdio_w32(gsw, MT7530_PMCR_P(6), PMCR_FIXED_LINK_FC);
-	}
-
-	/* GE2, Link down */
-	mtk_switch_w32(gsw, MAC_MCR_FORCE_MODE, MTK_MAC_P2_MCR);
-
-	/* Enable Port 6, P5 as GMAC5, P5 disable */
-	val = mt7530_mdio_r32(gsw, MT7530_MHWTRAP);
-	/* Enable Port 6 */
-	val &= ~MHWTRAP_P6_DIS;
-	/* Disable Port 5 */
-	val |= MHWTRAP_P5_DIS;
-	/* manual override of HW-Trap */
-	val |= MHWTRAP_MANUAL;
-	mt7530_mdio_w32(gsw, MT7530_MHWTRAP, val);
-
-	val = rt_sysc_r32(SYSC_REG_CFG);
-	val = (val >> MT7621_XTAL_SHIFT) & MT7621_XTAL_MASK;
-	if (val < MT7621_XTAL_25 && val >= MT7621_XTAL_40) {
-		/* 40Mhz */
-
-		/* disable MT7530 core clock */
-		_mt7620_mii_write(gsw, 0, 13, 0x1f);
-		_mt7620_mii_write(gsw, 0, 14, 0x410);
-		_mt7620_mii_write(gsw, 0, 13, 0x401f);
-		_mt7620_mii_write(gsw, 0, 14, 0x0);
-
-		/* disable MT7530 PLL */
-		_mt7620_mii_write(gsw, 0, 13, 0x1f);
-		_mt7620_mii_write(gsw, 0, 14, 0x40d);
-		_mt7620_mii_write(gsw, 0, 13, 0x401f);
-		_mt7620_mii_write(gsw, 0, 14, 0x2020);
-
-		/* for MT7530 core clock = 500Mhz */
-		_mt7620_mii_write(gsw, 0, 13, 0x1f);
-		_mt7620_mii_write(gsw, 0, 14, 0x40e);
-		_mt7620_mii_write(gsw, 0, 13, 0x401f);
-		_mt7620_mii_write(gsw, 0, 14, 0x119);
-
-		/* enable MT7530 PLL */
-		_mt7620_mii_write(gsw, 0, 13, 0x1f);
-		_mt7620_mii_write(gsw, 0, 14, 0x40d);
-		_mt7620_mii_write(gsw, 0, 13, 0x401f);
-		_mt7620_mii_write(gsw, 0, 14, 0x2820);
-
-		usleep_range(20, 40);
-
-		/* enable MT7530 core clock */
-		_mt7620_mii_write(gsw, 0, 13, 0x1f);
-		_mt7620_mii_write(gsw, 0, 14, 0x410);
-		_mt7620_mii_write(gsw, 0, 13, 0x401f);
-	}
-
-	/* RGMII */
-	_mt7620_mii_write(gsw, 0, 14, 0x1);
-
-	/* set MT7530 central align */
-	mt7530_mdio_m32(gsw, BIT(0), P6ECR_INTF_MODE_RGMII, MT7530_P6ECR);
-	mt7530_mdio_m32(gsw, TRGMII_TXCTRL_TXC_INV, 0,
-			MT7530_TRGMII_TXCTRL);
-	mt7530_mdio_w32(gsw, MT7530_TRGMII_TCK_CTRL, 0x855);
-
-	/* delay setting for 10/1000M */
-	mt7530_mdio_w32(gsw, MT7530_P5RGMIIRXCR,
-			P5RGMIIRXCR_C_ALIGN | P5RGMIIRXCR_DELAY_2);
-	mt7530_mdio_w32(gsw, MT7530_P5RGMIITXCR, 0x14);
-
-	/* lower Tx Driving*/
-	mt7530_mdio_w32(gsw, MT7530_TRGMII_TD0_ODT, 0x44);
-	mt7530_mdio_w32(gsw, MT7530_TRGMII_TD1_ODT, 0x44);
-	mt7530_mdio_w32(gsw, MT7530_TRGMII_TD2_ODT, 0x44);
-	mt7530_mdio_w32(gsw, MT7530_TRGMII_TD3_ODT, 0x44);
-	mt7530_mdio_w32(gsw, MT7530_TRGMII_TD4_ODT, 0x44);
-	mt7530_mdio_w32(gsw, MT7530_TRGMII_TD5_ODT, 0x44);
-
-	/* turn on all PHYs */
-	for (i = 0; i <= 4; i++) {
-		val = _mt7620_mii_read(gsw, i, 0);
-		val &= ~BIT(11);
-		_mt7620_mii_write(gsw, i, 0, val);
-	}
-
-#define MT7530_NUM_PORTS 8
-#define REG_ESW_PORT_PCR(x)    (0x2004 | ((x) << 8))
-#define REG_ESW_PORT_PVC(x)    (0x2010 | ((x) << 8))
-#define REG_ESW_PORT_PPBV1(x)  (0x2014 | ((x) << 8))
-#define MT7530_CPU_PORT                6
-
-	/* This is copied from mt7530_apply_config in libreCMC driver */
-	{
-		int i;
-
-		for (i = 0; i < MT7530_NUM_PORTS; i++)
-			mt7530_mdio_w32(gsw, REG_ESW_PORT_PCR(i), 0x00400000);
-
-		mt7530_mdio_w32(gsw, REG_ESW_PORT_PCR(MT7530_CPU_PORT),
-				0x00ff0000);
-
-		for (i = 0; i < MT7530_NUM_PORTS; i++)
-			mt7530_mdio_w32(gsw, REG_ESW_PORT_PVC(i), 0x810000c0);
-	}
-
-	/* enable irq */
-	mt7530_mdio_m32(gsw, 0, 3 << 16, MT7530_TOP_SIG_CTRL);
-	mt7530_mdio_w32(gsw, MT7530_SYS_INT_EN, 0x1f);
-}
-
-static const struct of_device_id mediatek_gsw_match[] = {
-	{ .compatible = "mediatek,mt7621-gsw" },
-	{},
-};
-MODULE_DEVICE_TABLE(of, mediatek_gsw_match);
-
-int mtk_gsw_init(struct mtk_eth *eth)
-{
-	struct device_node *np = eth->switch_np;
-	struct platform_device *pdev = of_find_device_by_node(np);
-	struct mt7620_gsw *gsw;
-
-	if (!pdev)
-		return -ENODEV;
-
-	if (!of_device_is_compatible(np, mediatek_gsw_match->compatible))
-		return -EINVAL;
-
-	gsw = platform_get_drvdata(pdev);
-	eth->sw_priv = gsw;
-
-	if (!gsw->irq)
-		return -EINVAL;
-
-	request_irq(gsw->irq, gsw_interrupt_mt7621, 0,
-		    "gsw", eth);
-	disable_irq(gsw->irq);
-
-	mt7621_hw_init(eth, gsw, np);
-
-	enable_irq(gsw->irq);
-
-	return 0;
-}
-EXPORT_SYMBOL_GPL(mtk_gsw_init);
-
-static int mt7621_gsw_probe(struct platform_device *pdev)
-{
-	struct resource *res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
-	struct mt7620_gsw *gsw;
-
-	gsw = devm_kzalloc(&pdev->dev, sizeof(struct mt7620_gsw), GFP_KERNEL);
-	if (!gsw)
-		return -ENOMEM;
-
-	gsw->base = devm_ioremap_resource(&pdev->dev, res);
-	if (IS_ERR(gsw->base))
-		return PTR_ERR(gsw->base);
-
-	gsw->dev = &pdev->dev;
-	gsw->irq = irq_of_parse_and_map(pdev->dev.of_node, 0);
-
-	platform_set_drvdata(pdev, gsw);
-
-	return 0;
-}
-
-static int mt7621_gsw_remove(struct platform_device *pdev)
-{
-	platform_set_drvdata(pdev, NULL);
-
-	return 0;
-}
-
-static struct platform_driver gsw_driver = {
-	.probe = mt7621_gsw_probe,
-	.remove = mt7621_gsw_remove,
-	.driver = {
-		.name = "mt7621-gsw",
-		.of_match_table = mediatek_gsw_match,
-	},
-};
-
-module_platform_driver(gsw_driver);
-
-MODULE_LICENSE("GPL");
-MODULE_AUTHOR("John Crispin <blogic@openwrt.org>");
-MODULE_DESCRIPTION("GBit switch driver for Mediatek MT7621 SoC");
diff --git a/drivers/staging/mt7621-eth/mdio.c b/drivers/staging/mt7621-eth/mdio.c
deleted file mode 100644
index 5fea6a447eed..000000000000
--- a/drivers/staging/mt7621-eth/mdio.c
+++ /dev/null
@@ -1,275 +0,0 @@
-/*   This program is free software; you can redistribute it and/or modify
- *   it under the terms of the GNU General Public License as published by
- *   the Free Software Foundation; version 2 of the License
- *
- *   Copyright (C) 2009-2016 John Crispin <blogic@openwrt.org>
- *   Copyright (C) 2009-2016 Felix Fietkau <nbd@openwrt.org>
- *   Copyright (C) 2013-2016 Michael Lee <igvtee@gmail.com>
- */
-
-#include <linux/module.h>
-#include <linux/kernel.h>
-#include <linux/phy.h>
-#include <linux/of_net.h>
-#include <linux/of_mdio.h>
-
-#include "mtk_eth_soc.h"
-#include "mdio.h"
-
-static int mtk_mdio_reset(struct mii_bus *bus)
-{
-	/* TODO */
-	return 0;
-}
-
-static void mtk_phy_link_adjust(struct net_device *dev)
-{
-	struct mtk_eth *eth = netdev_priv(dev);
-	unsigned long flags;
-	int i;
-
-	spin_lock_irqsave(&eth->phy->lock, flags);
-	for (i = 0; i < 8; i++) {
-		if (eth->phy->phy_node[i]) {
-			struct phy_device *phydev = eth->phy->phy[i];
-			int status_change = 0;
-
-			if (phydev->link)
-				if (eth->phy->duplex[i] != phydev->duplex ||
-				    eth->phy->speed[i] != phydev->speed)
-					status_change = 1;
-
-			if (phydev->link != eth->link[i])
-				status_change = 1;
-
-			switch (phydev->speed) {
-			case SPEED_1000:
-			case SPEED_100:
-			case SPEED_10:
-				eth->link[i] = phydev->link;
-				eth->phy->duplex[i] = phydev->duplex;
-				eth->phy->speed[i] = phydev->speed;
-
-				if (status_change &&
-				    eth->soc->mdio_adjust_link)
-					eth->soc->mdio_adjust_link(eth, i);
-				break;
-			}
-		}
-	}
-	spin_unlock_irqrestore(&eth->phy->lock, flags);
-}
-
-int mtk_connect_phy_node(struct mtk_eth *eth, struct mtk_mac *mac,
-			 struct device_node *phy_node)
-{
-	const __be32 *_port = NULL;
-	struct phy_device *phydev;
-	int phy_mode, port;
-
-	_port = of_get_property(phy_node, "reg", NULL);
-
-	if (!_port || (be32_to_cpu(*_port) >= 0x20)) {
-		pr_err("%pOFn: invalid port id\n", phy_node);
-		return -EINVAL;
-	}
-	port = be32_to_cpu(*_port);
-	phy_mode = of_get_phy_mode(phy_node);
-	if (phy_mode < 0) {
-		dev_err(eth->dev, "incorrect phy-mode %d\n", phy_mode);
-		eth->phy->phy_node[port] = NULL;
-		return -EINVAL;
-	}
-
-	phydev = of_phy_connect(eth->netdev[mac->id], phy_node,
-				mtk_phy_link_adjust, 0, phy_mode);
-	if (!phydev) {
-		dev_err(eth->dev, "could not connect to PHY\n");
-		eth->phy->phy_node[port] = NULL;
-		return -ENODEV;
-	}
-
-	phydev->supported &= PHY_1000BT_FEATURES;
-	phydev->advertising = phydev->supported;
-
-	dev_info(eth->dev,
-		 "connected port %d to PHY at %s [uid=%08x, driver=%s]\n",
-		 port, phydev_name(phydev), phydev->phy_id,
-		 phydev->drv->name);
-
-	eth->phy->phy[port] = phydev;
-	eth->link[port] = 0;
-
-	return 0;
-}
-
-static void phy_init(struct mtk_eth *eth, struct mtk_mac *mac,
-		     struct phy_device *phy)
-{
-	phy_attach(eth->netdev[mac->id], phydev_name(phy),
-		   PHY_INTERFACE_MODE_MII);
-
-	phy->autoneg = AUTONEG_ENABLE;
-	phy->speed = 0;
-	phy->duplex = 0;
-	phy_set_max_speed(phy, SPEED_100);
-	phy->advertising = phy->supported | ADVERTISED_Autoneg;
-
-	phy_start_aneg(phy);
-}
-
-static int mtk_phy_connect(struct mtk_mac *mac)
-{
-	struct mtk_eth *eth = mac->hw;
-	int i;
-
-	for (i = 0; i < 8; i++) {
-		if (eth->phy->phy_node[i]) {
-			if (!mac->phy_dev) {
-				mac->phy_dev = eth->phy->phy[i];
-				mac->phy_flags = MTK_PHY_FLAG_PORT;
-			}
-		} else if (eth->mii_bus) {
-			struct phy_device *phy;
-
-			phy = mdiobus_get_phy(eth->mii_bus, i);
-			if (phy) {
-				phy_init(eth, mac, phy);
-				if (!mac->phy_dev) {
-					mac->phy_dev = phy;
-					mac->phy_flags = MTK_PHY_FLAG_ATTACH;
-				}
-			}
-		}
-	}
-
-	return 0;
-}
-
-static void mtk_phy_disconnect(struct mtk_mac *mac)
-{
-	struct mtk_eth *eth = mac->hw;
-	unsigned long flags;
-	int i;
-
-	for (i = 0; i < 8; i++)
-		if (eth->phy->phy_fixed[i]) {
-			spin_lock_irqsave(&eth->phy->lock, flags);
-			eth->link[i] = 0;
-			if (eth->soc->mdio_adjust_link)
-				eth->soc->mdio_adjust_link(eth, i);
-			spin_unlock_irqrestore(&eth->phy->lock, flags);
-		} else if (eth->phy->phy[i]) {
-			phy_disconnect(eth->phy->phy[i]);
-		} else if (eth->mii_bus) {
-			struct phy_device *phy =
-				mdiobus_get_phy(eth->mii_bus, i);
-
-			if (phy)
-				phy_detach(phy);
-		}
-}
-
-static void mtk_phy_start(struct mtk_mac *mac)
-{
-	struct mtk_eth *eth = mac->hw;
-	unsigned long flags;
-	int i;
-
-	for (i = 0; i < 8; i++) {
-		if (eth->phy->phy_fixed[i]) {
-			spin_lock_irqsave(&eth->phy->lock, flags);
-			eth->link[i] = 1;
-			if (eth->soc->mdio_adjust_link)
-				eth->soc->mdio_adjust_link(eth, i);
-			spin_unlock_irqrestore(&eth->phy->lock, flags);
-		} else if (eth->phy->phy[i]) {
-			phy_start(eth->phy->phy[i]);
-		}
-	}
-}
-
-static void mtk_phy_stop(struct mtk_mac *mac)
-{
-	struct mtk_eth *eth = mac->hw;
-	unsigned long flags;
-	int i;
-
-	for (i = 0; i < 8; i++)
-		if (eth->phy->phy_fixed[i]) {
-			spin_lock_irqsave(&eth->phy->lock, flags);
-			eth->link[i] = 0;
-			if (eth->soc->mdio_adjust_link)
-				eth->soc->mdio_adjust_link(eth, i);
-			spin_unlock_irqrestore(&eth->phy->lock, flags);
-		} else if (eth->phy->phy[i]) {
-			phy_stop(eth->phy->phy[i]);
-		}
-}
-
-static struct mtk_phy phy_ralink = {
-	.connect = mtk_phy_connect,
-	.disconnect = mtk_phy_disconnect,
-	.start = mtk_phy_start,
-	.stop = mtk_phy_stop,
-};
-
-int mtk_mdio_init(struct mtk_eth *eth)
-{
-	struct device_node *mii_np;
-	int err;
-
-	if (!eth->soc->mdio_read || !eth->soc->mdio_write)
-		return 0;
-
-	spin_lock_init(&phy_ralink.lock);
-	eth->phy = &phy_ralink;
-
-	mii_np = of_get_child_by_name(eth->dev->of_node, "mdio-bus");
-	if (!mii_np) {
-		dev_err(eth->dev, "no %s child node found", "mdio-bus");
-		return -ENODEV;
-	}
-
-	if (!of_device_is_available(mii_np)) {
-		err = 0;
-		goto err_put_node;
-	}
-
-	eth->mii_bus = mdiobus_alloc();
-	if (!eth->mii_bus) {
-		err = -ENOMEM;
-		goto err_put_node;
-	}
-
-	eth->mii_bus->name = "mdio";
-	eth->mii_bus->read = eth->soc->mdio_read;
-	eth->mii_bus->write = eth->soc->mdio_write;
-	eth->mii_bus->reset = mtk_mdio_reset;
-	eth->mii_bus->priv = eth;
-	eth->mii_bus->parent = eth->dev;
-
-	snprintf(eth->mii_bus->id, MII_BUS_ID_SIZE, "%pOFn", mii_np);
-	err = of_mdiobus_register(eth->mii_bus, mii_np);
-	if (err)
-		goto err_free_bus;
-
-	return 0;
-
-err_free_bus:
-	kfree(eth->mii_bus);
-err_put_node:
-	of_node_put(mii_np);
-	eth->mii_bus = NULL;
-	return err;
-}
-
-void mtk_mdio_cleanup(struct mtk_eth *eth)
-{
-	if (!eth->mii_bus)
-		return;
-
-	mdiobus_unregister(eth->mii_bus);
-	of_node_put(eth->mii_bus->dev.of_node);
-	kfree(eth->mii_bus);
-}
diff --git a/drivers/staging/mt7621-eth/mdio.h b/drivers/staging/mt7621-eth/mdio.h
deleted file mode 100644
index b14e23842a01..000000000000
--- a/drivers/staging/mt7621-eth/mdio.h
+++ /dev/null
@@ -1,27 +0,0 @@
-/*   This program is free software; you can redistribute it and/or modify
- *   it under the terms of the GNU General Public License as published by
- *   the Free Software Foundation; version 2 of the License
- *
- *   This program is distributed in the hope that it will be useful,
- *   but WITHOUT ANY WARRANTY; without even the implied warranty of
- *   MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- *   GNU General Public License for more details.
- *
- *   Copyright (C) 2009-2016 John Crispin <blogic@openwrt.org>
- *   Copyright (C) 2009-2016 Felix Fietkau <nbd@openwrt.org>
- *   Copyright (C) 2013-2016 Michael Lee <igvtee@gmail.com>
- */
-
-#ifndef _RALINK_MDIO_H__
-#define _RALINK_MDIO_H__
-
-#ifdef CONFIG_NET_MEDIATEK_MDIO
-int mtk_mdio_init(struct mtk_eth *eth);
-void mtk_mdio_cleanup(struct mtk_eth *eth);
-int mtk_connect_phy_node(struct mtk_eth *eth, struct mtk_mac *mac,
-			 struct device_node *phy_node);
-#else
-static inline int mtk_mdio_init(struct mtk_eth *eth) { return 0; }
-static inline void mtk_mdio_cleanup(struct mtk_eth *eth) {}
-#endif
-#endif
diff --git a/drivers/staging/mt7621-eth/mdio_mt7620.c b/drivers/staging/mt7621-eth/mdio_mt7620.c
deleted file mode 100644
index ced605c2914e..000000000000
--- a/drivers/staging/mt7621-eth/mdio_mt7620.c
+++ /dev/null
@@ -1,173 +0,0 @@
-/*   This program is free software; you can redistribute it and/or modify
- *   it under the terms of the GNU General Public License as published by
- *   the Free Software Foundation; version 2 of the License
- *
- *   This program is distributed in the hope that it will be useful,
- *   but WITHOUT ANY WARRANTY; without even the implied warranty of
- *   MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- *   GNU General Public License for more details.
- *
- *   Copyright (C) 2009-2016 John Crispin <blogic@openwrt.org>
- *   Copyright (C) 2009-2016 Felix Fietkau <nbd@openwrt.org>
- *   Copyright (C) 2013-2016 Michael Lee <igvtee@gmail.com>
- */
-
-#include <linux/module.h>
-#include <linux/kernel.h>
-#include <linux/types.h>
-
-#include "mtk_eth_soc.h"
-#include "gsw_mt7620.h"
-#include "mdio.h"
-
-static int mt7620_mii_busy_wait(struct mt7620_gsw *gsw)
-{
-	unsigned long t_start = jiffies;
-
-	while (1) {
-		if (!(mtk_switch_r32(gsw,
-				     gsw->piac_offset + MT7620_GSW_REG_PIAC) &
-				     GSW_MDIO_ACCESS))
-			return 0;
-		if (time_after(jiffies, t_start + GSW_REG_PHY_TIMEOUT))
-			break;
-	}
-
-	dev_err(gsw->dev, "mdio: MDIO timeout\n");
-	return -1;
-}
-
-u32 _mt7620_mii_write(struct mt7620_gsw *gsw, u32 phy_addr,
-		      u32 phy_register, u32 write_data)
-{
-	if (mt7620_mii_busy_wait(gsw))
-		return -1;
-
-	write_data &= 0xffff;
-
-	mtk_switch_w32(gsw, GSW_MDIO_ACCESS | GSW_MDIO_START | GSW_MDIO_WRITE |
-		(phy_register << GSW_MDIO_REG_SHIFT) |
-		(phy_addr << GSW_MDIO_ADDR_SHIFT) | write_data,
-		MT7620_GSW_REG_PIAC);
-
-	if (mt7620_mii_busy_wait(gsw))
-		return -1;
-
-	return 0;
-}
-EXPORT_SYMBOL_GPL(_mt7620_mii_write);
-
-u32 _mt7620_mii_read(struct mt7620_gsw *gsw, int phy_addr, int phy_reg)
-{
-	u32 d;
-
-	if (mt7620_mii_busy_wait(gsw))
-		return 0xffff;
-
-	mtk_switch_w32(gsw, GSW_MDIO_ACCESS | GSW_MDIO_START | GSW_MDIO_READ |
-		(phy_reg << GSW_MDIO_REG_SHIFT) |
-		(phy_addr << GSW_MDIO_ADDR_SHIFT),
-		MT7620_GSW_REG_PIAC);
-
-	if (mt7620_mii_busy_wait(gsw))
-		return 0xffff;
-
-	d = mtk_switch_r32(gsw, MT7620_GSW_REG_PIAC) & 0xffff;
-
-	return d;
-}
-EXPORT_SYMBOL_GPL(_mt7620_mii_read);
-
-int mt7620_mdio_write(struct mii_bus *bus, int phy_addr, int phy_reg, u16 val)
-{
-	struct mtk_eth *eth = bus->priv;
-	struct mt7620_gsw *gsw = (struct mt7620_gsw *)eth->sw_priv;
-
-	return _mt7620_mii_write(gsw, phy_addr, phy_reg, val);
-}
-
-int mt7620_mdio_read(struct mii_bus *bus, int phy_addr, int phy_reg)
-{
-	struct mtk_eth *eth = bus->priv;
-	struct mt7620_gsw *gsw = (struct mt7620_gsw *)eth->sw_priv;
-
-	return _mt7620_mii_read(gsw, phy_addr, phy_reg);
-}
-
-void mt7530_mdio_w32(struct mt7620_gsw *gsw, u32 reg, u32 val)
-{
-	_mt7620_mii_write(gsw, 0x1f, 0x1f, (reg >> 6) & 0x3ff);
-	_mt7620_mii_write(gsw, 0x1f, (reg >> 2) & 0xf,  val & 0xffff);
-	_mt7620_mii_write(gsw, 0x1f, 0x10, val >> 16);
-}
-EXPORT_SYMBOL_GPL(mt7530_mdio_w32);
-
-u32 mt7530_mdio_r32(struct mt7620_gsw *gsw, u32 reg)
-{
-	u16 high, low;
-
-	_mt7620_mii_write(gsw, 0x1f, 0x1f, (reg >> 6) & 0x3ff);
-	low = _mt7620_mii_read(gsw, 0x1f, (reg >> 2) & 0xf);
-	high = _mt7620_mii_read(gsw, 0x1f, 0x10);
-
-	return (high << 16) | (low & 0xffff);
-}
-EXPORT_SYMBOL_GPL(mt7530_mdio_r32);
-
-void mt7530_mdio_m32(struct mt7620_gsw *gsw, u32 mask, u32 set, u32 reg)
-{
-	u32 val = mt7530_mdio_r32(gsw, reg);
-
-	val &= ~mask;
-	val |= set;
-	mt7530_mdio_w32(gsw, reg, val);
-}
-EXPORT_SYMBOL_GPL(mt7530_mdio_m32);
-
-static unsigned char *mtk_speed_str(int speed)
-{
-	switch (speed) {
-	case 2:
-	case SPEED_1000:
-		return "1000";
-	case 1:
-	case SPEED_100:
-		return "100";
-	case 0:
-	case SPEED_10:
-		return "10";
-	}
-
-	return "? ";
-}
-
-int mt7620_has_carrier(struct mtk_eth *eth)
-{
-	struct mt7620_gsw *gsw = (struct mt7620_gsw *)eth->sw_priv;
-	int i;
-
-	for (i = 0; i < GSW_PORT6; i++)
-		if (mt7530_mdio_r32(gsw, GSW_REG_PORT_STATUS(i)) & 0x1)
-			return 1;
-	return 0;
-}
-
-void mt7620_print_link_state(struct mtk_eth *eth, int port, int link,
-			     int speed, int duplex)
-{
-	struct mt7620_gsw *gsw = eth->sw_priv;
-
-	if (link)
-		dev_info(gsw->dev, "port %d link up (%sMbps/%s duplex)\n",
-			 port, mtk_speed_str(speed),
-			 (duplex) ? "Full" : "Half");
-	else
-		dev_info(gsw->dev, "port %d link down\n", port);
-}
-
-void mt7620_mdio_link_adjust(struct mtk_eth *eth, int port)
-{
-	mt7620_print_link_state(eth, port, eth->link[port],
-				eth->phy->speed[port],
-				(eth->phy->duplex[port] == DUPLEX_FULL));
-}
diff --git a/drivers/staging/mt7621-eth/mtk_eth_soc.c b/drivers/staging/mt7621-eth/mtk_eth_soc.c
deleted file mode 100644
index 6027b19f7bc2..000000000000
--- a/drivers/staging/mt7621-eth/mtk_eth_soc.c
+++ /dev/null
@@ -1,2176 +0,0 @@
-/*   This program is free software; you can redistribute it and/or modify
- *   it under the terms of the GNU General Public License as published by
- *   the Free Software Foundation; version 2 of the License
- *
- *   This program is distributed in the hope that it will be useful,
- *   but WITHOUT ANY WARRANTY; without even the implied warranty of
- *   MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- *   GNU General Public License for more details.
- *
- *   Copyright (C) 2009-2016 John Crispin <blogic@openwrt.org>
- *   Copyright (C) 2009-2016 Felix Fietkau <nbd@openwrt.org>
- *   Copyright (C) 2013-2016 Michael Lee <igvtee@gmail.com>
- */
-
-#include <linux/module.h>
-#include <linux/kernel.h>
-#include <linux/types.h>
-#include <linux/dma-mapping.h>
-#include <linux/init.h>
-#include <linux/skbuff.h>
-#include <linux/etherdevice.h>
-#include <linux/ethtool.h>
-#include <linux/platform_device.h>
-#include <linux/of_device.h>
-#include <linux/mfd/syscon.h>
-#include <linux/clk.h>
-#include <linux/of_net.h>
-#include <linux/of_mdio.h>
-#include <linux/if_vlan.h>
-#include <linux/reset.h>
-#include <linux/tcp.h>
-#include <linux/io.h>
-#include <linux/bug.h>
-#include <linux/regmap.h>
-
-#include "mtk_eth_soc.h"
-#include "mdio.h"
-#include "ethtool.h"
-
-#define	MAX_RX_LENGTH		1536
-#define MTK_RX_ETH_HLEN		(VLAN_ETH_HLEN + VLAN_HLEN + ETH_FCS_LEN)
-#define MTK_RX_HLEN		(NET_SKB_PAD + MTK_RX_ETH_HLEN + NET_IP_ALIGN)
-#define DMA_DUMMY_DESC		0xffffffff
-#define MTK_DEFAULT_MSG_ENABLE \
-		(NETIF_MSG_DRV | \
-		NETIF_MSG_PROBE | \
-		NETIF_MSG_LINK | \
-		NETIF_MSG_TIMER | \
-		NETIF_MSG_IFDOWN | \
-		NETIF_MSG_IFUP | \
-		NETIF_MSG_RX_ERR | \
-		NETIF_MSG_TX_ERR)
-
-#define TX_DMA_DESP2_DEF	(TX_DMA_LS0 | TX_DMA_DONE)
-#define NEXT_TX_DESP_IDX(X)	(((X) + 1) & (ring->tx_ring_size - 1))
-#define NEXT_RX_DESP_IDX(X)	(((X) + 1) & (ring->rx_ring_size - 1))
-
-#define SYSC_REG_RSTCTRL	0x34
-
-static int mtk_msg_level = -1;
-module_param_named(msg_level, mtk_msg_level, int, 0);
-MODULE_PARM_DESC(msg_level, "Message level (-1=defaults,0=none,...,16=all)");
-
-static const u16 mtk_reg_table_default[MTK_REG_COUNT] = {
-	[MTK_REG_PDMA_GLO_CFG] = MTK_PDMA_GLO_CFG,
-	[MTK_REG_PDMA_RST_CFG] = MTK_PDMA_RST_CFG,
-	[MTK_REG_DLY_INT_CFG] = MTK_DLY_INT_CFG,
-	[MTK_REG_TX_BASE_PTR0] = MTK_TX_BASE_PTR0,
-	[MTK_REG_TX_MAX_CNT0] = MTK_TX_MAX_CNT0,
-	[MTK_REG_TX_CTX_IDX0] = MTK_TX_CTX_IDX0,
-	[MTK_REG_TX_DTX_IDX0] = MTK_TX_DTX_IDX0,
-	[MTK_REG_RX_BASE_PTR0] = MTK_RX_BASE_PTR0,
-	[MTK_REG_RX_MAX_CNT0] = MTK_RX_MAX_CNT0,
-	[MTK_REG_RX_CALC_IDX0] = MTK_RX_CALC_IDX0,
-	[MTK_REG_RX_DRX_IDX0] = MTK_RX_DRX_IDX0,
-	[MTK_REG_MTK_INT_ENABLE] = MTK_INT_ENABLE,
-	[MTK_REG_MTK_INT_STATUS] = MTK_INT_STATUS,
-	[MTK_REG_MTK_DMA_VID_BASE] = MTK_DMA_VID0,
-	[MTK_REG_MTK_COUNTER_BASE] = MTK_GDMA1_TX_GBCNT,
-	[MTK_REG_MTK_RST_GL] = MTK_RST_GL,
-};
-
-static const u16 *mtk_reg_table = mtk_reg_table_default;
-
-void mtk_w32(struct mtk_eth *eth, u32 val, unsigned int reg)
-{
-	__raw_writel(val, eth->base + reg);
-}
-
-u32 mtk_r32(struct mtk_eth *eth, unsigned int reg)
-{
-	return __raw_readl(eth->base + reg);
-}
-
-static void mtk_reg_w32(struct mtk_eth *eth, u32 val, enum mtk_reg reg)
-{
-	mtk_w32(eth, val, mtk_reg_table[reg]);
-}
-
-static u32 mtk_reg_r32(struct mtk_eth *eth, enum mtk_reg reg)
-{
-	return mtk_r32(eth, mtk_reg_table[reg]);
-}
-
-/* these bits are also exposed via the reset-controller API. however the switch
- * and FE need to be brought out of reset in the exakt same moemtn and the
- * reset-controller api does not provide this feature yet. Do the reset manually
- * until we fixed the reset-controller api to be able to do this
- */
-void mtk_reset(struct mtk_eth *eth, u32 reset_bits)
-{
-	u32 val;
-
-	regmap_read(eth->ethsys, SYSC_REG_RSTCTRL, &val);
-	val |= reset_bits;
-	regmap_write(eth->ethsys, SYSC_REG_RSTCTRL, val);
-	usleep_range(10, 20);
-	val &= ~reset_bits;
-	regmap_write(eth->ethsys, SYSC_REG_RSTCTRL, val);
-	usleep_range(10, 20);
-}
-EXPORT_SYMBOL(mtk_reset);
-
-static inline void mtk_irq_ack(struct mtk_eth *eth, u32 mask)
-{
-	if (eth->soc->dma_type & MTK_PDMA)
-		mtk_reg_w32(eth, mask, MTK_REG_MTK_INT_STATUS);
-	if (eth->soc->dma_type & MTK_QDMA)
-		mtk_w32(eth, mask, MTK_QMTK_INT_STATUS);
-}
-
-static inline u32 mtk_irq_pending(struct mtk_eth *eth)
-{
-	u32 status = 0;
-
-	if (eth->soc->dma_type & MTK_PDMA)
-		status |= mtk_reg_r32(eth, MTK_REG_MTK_INT_STATUS);
-	if (eth->soc->dma_type & MTK_QDMA)
-		status |= mtk_r32(eth, MTK_QMTK_INT_STATUS);
-
-	return status;
-}
-
-static void mtk_irq_ack_status(struct mtk_eth *eth, u32 mask)
-{
-	u32 status_reg = MTK_REG_MTK_INT_STATUS;
-
-	if (mtk_reg_table[MTK_REG_MTK_INT_STATUS2])
-		status_reg = MTK_REG_MTK_INT_STATUS2;
-
-	mtk_reg_w32(eth, mask, status_reg);
-}
-
-static u32 mtk_irq_pending_status(struct mtk_eth *eth)
-{
-	u32 status_reg = MTK_REG_MTK_INT_STATUS;
-
-	if (mtk_reg_table[MTK_REG_MTK_INT_STATUS2])
-		status_reg = MTK_REG_MTK_INT_STATUS2;
-
-	return mtk_reg_r32(eth, status_reg);
-}
-
-static inline void mtk_irq_disable(struct mtk_eth *eth, u32 mask)
-{
-	u32 val;
-
-	if (eth->soc->dma_type & MTK_PDMA) {
-		val = mtk_reg_r32(eth, MTK_REG_MTK_INT_ENABLE);
-		mtk_reg_w32(eth, val & ~mask, MTK_REG_MTK_INT_ENABLE);
-		/* flush write */
-		mtk_reg_r32(eth, MTK_REG_MTK_INT_ENABLE);
-	}
-	if (eth->soc->dma_type & MTK_QDMA) {
-		val = mtk_r32(eth, MTK_QMTK_INT_ENABLE);
-		mtk_w32(eth, val & ~mask, MTK_QMTK_INT_ENABLE);
-		/* flush write */
-		mtk_r32(eth, MTK_QMTK_INT_ENABLE);
-	}
-}
-
-static inline void mtk_irq_enable(struct mtk_eth *eth, u32 mask)
-{
-	u32 val;
-
-	if (eth->soc->dma_type & MTK_PDMA) {
-		val = mtk_reg_r32(eth, MTK_REG_MTK_INT_ENABLE);
-		mtk_reg_w32(eth, val | mask, MTK_REG_MTK_INT_ENABLE);
-		/* flush write */
-		mtk_reg_r32(eth, MTK_REG_MTK_INT_ENABLE);
-	}
-	if (eth->soc->dma_type & MTK_QDMA) {
-		val = mtk_r32(eth, MTK_QMTK_INT_ENABLE);
-		mtk_w32(eth, val | mask, MTK_QMTK_INT_ENABLE);
-		/* flush write */
-		mtk_r32(eth, MTK_QMTK_INT_ENABLE);
-	}
-}
-
-static inline u32 mtk_irq_enabled(struct mtk_eth *eth)
-{
-	u32 enabled = 0;
-
-	if (eth->soc->dma_type & MTK_PDMA)
-		enabled |= mtk_reg_r32(eth, MTK_REG_MTK_INT_ENABLE);
-	if (eth->soc->dma_type & MTK_QDMA)
-		enabled |= mtk_r32(eth, MTK_QMTK_INT_ENABLE);
-
-	return enabled;
-}
-
-static inline void mtk_hw_set_macaddr(struct mtk_mac *mac,
-				      unsigned char *macaddr)
-{
-	unsigned long flags;
-
-	spin_lock_irqsave(&mac->hw->page_lock, flags);
-	mtk_w32(mac->hw, (macaddr[0] << 8) | macaddr[1], MTK_GDMA1_MAC_ADRH);
-	mtk_w32(mac->hw, (macaddr[2] << 24) | (macaddr[3] << 16) |
-		(macaddr[4] << 8) | macaddr[5],
-		MTK_GDMA1_MAC_ADRL);
-	spin_unlock_irqrestore(&mac->hw->page_lock, flags);
-}
-
-static int mtk_set_mac_address(struct net_device *dev, void *p)
-{
-	int ret = eth_mac_addr(dev, p);
-	struct mtk_mac *mac = netdev_priv(dev);
-	struct mtk_eth *eth = mac->hw;
-
-	if (ret)
-		return ret;
-
-	if (eth->soc->set_mac)
-		eth->soc->set_mac(mac, dev->dev_addr);
-	else
-		mtk_hw_set_macaddr(mac, p);
-
-	return 0;
-}
-
-static inline int mtk_max_frag_size(int mtu)
-{
-	/* make sure buf_size will be at least MAX_RX_LENGTH */
-	if (mtu + MTK_RX_ETH_HLEN < MAX_RX_LENGTH)
-		mtu = MAX_RX_LENGTH - MTK_RX_ETH_HLEN;
-
-	return SKB_DATA_ALIGN(MTK_RX_HLEN + mtu) +
-		SKB_DATA_ALIGN(sizeof(struct skb_shared_info));
-}
-
-static inline int mtk_max_buf_size(int frag_size)
-{
-	int buf_size = frag_size - NET_SKB_PAD - NET_IP_ALIGN -
-		       SKB_DATA_ALIGN(sizeof(struct skb_shared_info));
-
-	WARN_ON(buf_size < MAX_RX_LENGTH);
-
-	return buf_size;
-}
-
-static inline void mtk_get_rxd(struct mtk_rx_dma *rxd,
-			       struct mtk_rx_dma *dma_rxd)
-{
-	rxd->rxd1 = READ_ONCE(dma_rxd->rxd1);
-	rxd->rxd2 = READ_ONCE(dma_rxd->rxd2);
-	rxd->rxd3 = READ_ONCE(dma_rxd->rxd3);
-	rxd->rxd4 = READ_ONCE(dma_rxd->rxd4);
-}
-
-static inline void mtk_set_txd_pdma(struct mtk_tx_dma *txd,
-				    struct mtk_tx_dma *dma_txd)
-{
-	WRITE_ONCE(dma_txd->txd1, txd->txd1);
-	WRITE_ONCE(dma_txd->txd3, txd->txd3);
-	WRITE_ONCE(dma_txd->txd4, txd->txd4);
-	/* clean dma done flag last */
-	WRITE_ONCE(dma_txd->txd2, txd->txd2);
-}
-
-static void mtk_clean_rx(struct mtk_eth *eth, struct mtk_rx_ring *ring)
-{
-	int i;
-
-	if (ring->rx_data && ring->rx_dma) {
-		for (i = 0; i < ring->rx_ring_size; i++) {
-			if (!ring->rx_data[i])
-				continue;
-			if (!ring->rx_dma[i].rxd1)
-				continue;
-			dma_unmap_single(eth->dev,
-					 ring->rx_dma[i].rxd1,
-					 ring->rx_buf_size,
-					 DMA_FROM_DEVICE);
-			skb_free_frag(ring->rx_data[i]);
-		}
-		kfree(ring->rx_data);
-		ring->rx_data = NULL;
-	}
-
-	if (ring->rx_dma) {
-		dma_free_coherent(eth->dev,
-				  ring->rx_ring_size * sizeof(*ring->rx_dma),
-				  ring->rx_dma,
-				  ring->rx_phys);
-		ring->rx_dma = NULL;
-	}
-}
-
-static int mtk_dma_rx_alloc(struct mtk_eth *eth, struct mtk_rx_ring *ring)
-{
-	int i, pad = 0;
-
-	ring->frag_size = mtk_max_frag_size(ETH_DATA_LEN);
-	ring->rx_buf_size = mtk_max_buf_size(ring->frag_size);
-	ring->rx_ring_size = eth->soc->dma_ring_size;
-	ring->rx_data = kcalloc(ring->rx_ring_size, sizeof(*ring->rx_data),
-				GFP_KERNEL);
-	if (!ring->rx_data)
-		goto no_rx_mem;
-
-	for (i = 0; i < ring->rx_ring_size; i++) {
-		ring->rx_data[i] = netdev_alloc_frag(ring->frag_size);
-		if (!ring->rx_data[i])
-			goto no_rx_mem;
-	}
-
-	ring->rx_dma =
-		dma_alloc_coherent(eth->dev,
-				   ring->rx_ring_size * sizeof(*ring->rx_dma),
-				   &ring->rx_phys, GFP_ATOMIC | __GFP_ZERO);
-	if (!ring->rx_dma)
-		goto no_rx_mem;
-
-	if (!eth->soc->rx_2b_offset)
-		pad = NET_IP_ALIGN;
-
-	for (i = 0; i < ring->rx_ring_size; i++) {
-		dma_addr_t dma_addr = dma_map_single(eth->dev,
-				ring->rx_data[i] + NET_SKB_PAD + pad,
-				ring->rx_buf_size,
-				DMA_FROM_DEVICE);
-		if (unlikely(dma_mapping_error(eth->dev, dma_addr)))
-			goto no_rx_mem;
-		ring->rx_dma[i].rxd1 = (unsigned int)dma_addr;
-
-		if (eth->soc->rx_sg_dma)
-			ring->rx_dma[i].rxd2 = RX_DMA_PLEN0(ring->rx_buf_size);
-		else
-			ring->rx_dma[i].rxd2 = RX_DMA_LSO;
-	}
-	ring->rx_calc_idx = ring->rx_ring_size - 1;
-	/* make sure that all changes to the dma ring are flushed before we
-	 * continue
-	 */
-	wmb();
-
-	return 0;
-
-no_rx_mem:
-	return -ENOMEM;
-}
-
-static void mtk_txd_unmap(struct device *dev, struct mtk_tx_buf *tx_buf)
-{
-	if (tx_buf->flags & MTK_TX_FLAGS_SINGLE0) {
-		dma_unmap_single(dev,
-				 dma_unmap_addr(tx_buf, dma_addr0),
-				 dma_unmap_len(tx_buf, dma_len0),
-				 DMA_TO_DEVICE);
-	} else if (tx_buf->flags & MTK_TX_FLAGS_PAGE0) {
-		dma_unmap_page(dev,
-			       dma_unmap_addr(tx_buf, dma_addr0),
-			       dma_unmap_len(tx_buf, dma_len0),
-			       DMA_TO_DEVICE);
-	}
-	if (tx_buf->flags & MTK_TX_FLAGS_PAGE1)
-		dma_unmap_page(dev,
-			       dma_unmap_addr(tx_buf, dma_addr1),
-			       dma_unmap_len(tx_buf, dma_len1),
-			       DMA_TO_DEVICE);
-
-	tx_buf->flags = 0;
-	if (tx_buf->skb && (tx_buf->skb != (struct sk_buff *)DMA_DUMMY_DESC))
-		dev_kfree_skb_any(tx_buf->skb);
-	tx_buf->skb = NULL;
-}
-
-static void mtk_pdma_tx_clean(struct mtk_eth *eth)
-{
-	struct mtk_tx_ring *ring = &eth->tx_ring;
-	int i;
-
-	if (ring->tx_buf) {
-		for (i = 0; i < ring->tx_ring_size; i++)
-			mtk_txd_unmap(eth->dev, &ring->tx_buf[i]);
-		kfree(ring->tx_buf);
-		ring->tx_buf = NULL;
-	}
-
-	if (ring->tx_dma) {
-		dma_free_coherent(eth->dev,
-				  ring->tx_ring_size * sizeof(*ring->tx_dma),
-				  ring->tx_dma,
-				  ring->tx_phys);
-		ring->tx_dma = NULL;
-	}
-}
-
-static void mtk_qdma_tx_clean(struct mtk_eth *eth)
-{
-	struct mtk_tx_ring *ring = &eth->tx_ring;
-	int i;
-
-	if (ring->tx_buf) {
-		for (i = 0; i < ring->tx_ring_size; i++)
-			mtk_txd_unmap(eth->dev, &ring->tx_buf[i]);
-		kfree(ring->tx_buf);
-		ring->tx_buf = NULL;
-	}
-
-	if (ring->tx_dma) {
-		dma_free_coherent(eth->dev,
-				  ring->tx_ring_size * sizeof(*ring->tx_dma),
-				  ring->tx_dma,
-				  ring->tx_phys);
-		ring->tx_dma = NULL;
-	}
-}
-
-void mtk_stats_update_mac(struct mtk_mac *mac)
-{
-	struct mtk_hw_stats *hw_stats = mac->hw_stats;
-	unsigned int base = mtk_reg_table[MTK_REG_MTK_COUNTER_BASE];
-	u64 stats;
-
-	base += hw_stats->reg_offset;
-
-	u64_stats_update_begin(&hw_stats->syncp);
-
-	if (mac->hw->soc->new_stats) {
-		hw_stats->rx_bytes += mtk_r32(mac->hw, base);
-		stats =  mtk_r32(mac->hw, base + 0x04);
-		if (stats)
-			hw_stats->rx_bytes += (stats << 32);
-		hw_stats->rx_packets += mtk_r32(mac->hw, base + 0x08);
-		hw_stats->rx_overflow += mtk_r32(mac->hw, base + 0x10);
-		hw_stats->rx_fcs_errors += mtk_r32(mac->hw, base + 0x14);
-		hw_stats->rx_short_errors += mtk_r32(mac->hw, base + 0x18);
-		hw_stats->rx_long_errors += mtk_r32(mac->hw, base + 0x1c);
-		hw_stats->rx_checksum_errors += mtk_r32(mac->hw, base + 0x20);
-		hw_stats->rx_flow_control_packets +=
-						mtk_r32(mac->hw, base + 0x24);
-		hw_stats->tx_skip += mtk_r32(mac->hw, base + 0x28);
-		hw_stats->tx_collisions += mtk_r32(mac->hw, base + 0x2c);
-		hw_stats->tx_bytes += mtk_r32(mac->hw, base + 0x30);
-		stats =  mtk_r32(mac->hw, base + 0x34);
-		if (stats)
-			hw_stats->tx_bytes += (stats << 32);
-		hw_stats->tx_packets += mtk_r32(mac->hw, base + 0x38);
-	} else {
-		hw_stats->tx_bytes += mtk_r32(mac->hw, base);
-		hw_stats->tx_packets += mtk_r32(mac->hw, base + 0x04);
-		hw_stats->tx_skip += mtk_r32(mac->hw, base + 0x08);
-		hw_stats->tx_collisions += mtk_r32(mac->hw, base + 0x0c);
-		hw_stats->rx_bytes += mtk_r32(mac->hw, base + 0x20);
-		hw_stats->rx_packets += mtk_r32(mac->hw, base + 0x24);
-		hw_stats->rx_overflow += mtk_r32(mac->hw, base + 0x28);
-		hw_stats->rx_fcs_errors += mtk_r32(mac->hw, base + 0x2c);
-		hw_stats->rx_short_errors += mtk_r32(mac->hw, base + 0x30);
-		hw_stats->rx_long_errors += mtk_r32(mac->hw, base + 0x34);
-		hw_stats->rx_checksum_errors += mtk_r32(mac->hw, base + 0x38);
-		hw_stats->rx_flow_control_packets +=
-						mtk_r32(mac->hw, base + 0x3c);
-	}
-
-	u64_stats_update_end(&hw_stats->syncp);
-}
-
-static void mtk_get_stats64(struct net_device *dev,
-			    struct rtnl_link_stats64 *storage)
-{
-	struct mtk_mac *mac = netdev_priv(dev);
-	struct mtk_hw_stats *hw_stats = mac->hw_stats;
-	unsigned int base = mtk_reg_table[MTK_REG_MTK_COUNTER_BASE];
-	unsigned int start;
-
-	if (!base) {
-		netdev_stats_to_stats64(storage, &dev->stats);
-		return;
-	}
-
-	if (netif_running(dev) && netif_device_present(dev)) {
-		if (spin_trylock(&hw_stats->stats_lock)) {
-			mtk_stats_update_mac(mac);
-			spin_unlock(&hw_stats->stats_lock);
-		}
-	}
-
-	do {
-		start = u64_stats_fetch_begin_irq(&hw_stats->syncp);
-		storage->rx_packets = hw_stats->rx_packets;
-		storage->tx_packets = hw_stats->tx_packets;
-		storage->rx_bytes = hw_stats->rx_bytes;
-		storage->tx_bytes = hw_stats->tx_bytes;
-		storage->collisions = hw_stats->tx_collisions;
-		storage->rx_length_errors = hw_stats->rx_short_errors +
-			hw_stats->rx_long_errors;
-		storage->rx_over_errors = hw_stats->rx_overflow;
-		storage->rx_crc_errors = hw_stats->rx_fcs_errors;
-		storage->rx_errors = hw_stats->rx_checksum_errors;
-		storage->tx_aborted_errors = hw_stats->tx_skip;
-	} while (u64_stats_fetch_retry_irq(&hw_stats->syncp, start));
-
-	storage->tx_errors = dev->stats.tx_errors;
-	storage->rx_dropped = dev->stats.rx_dropped;
-	storage->tx_dropped = dev->stats.tx_dropped;
-}
-
-static int mtk_vlan_rx_add_vid(struct net_device *dev,
-			       __be16 proto, u16 vid)
-{
-	struct mtk_mac *mac = netdev_priv(dev);
-	struct mtk_eth *eth = mac->hw;
-	u32 idx = (vid & 0xf);
-	u32 vlan_cfg;
-
-	if (!((mtk_reg_table[MTK_REG_MTK_DMA_VID_BASE]) &&
-	      (dev->features & NETIF_F_HW_VLAN_CTAG_TX)))
-		return 0;
-
-	if (test_bit(idx, &eth->vlan_map)) {
-		netdev_warn(dev, "disable tx vlan offload\n");
-		dev->wanted_features &= ~NETIF_F_HW_VLAN_CTAG_TX;
-		netdev_update_features(dev);
-	} else {
-		vlan_cfg = mtk_r32(eth,
-				   mtk_reg_table[MTK_REG_MTK_DMA_VID_BASE] +
-				   ((idx >> 1) << 2));
-		if (idx & 0x1) {
-			vlan_cfg &= 0xffff;
-			vlan_cfg |= (vid << 16);
-		} else {
-			vlan_cfg &= 0xffff0000;
-			vlan_cfg |= vid;
-		}
-		mtk_w32(eth,
-			vlan_cfg, mtk_reg_table[MTK_REG_MTK_DMA_VID_BASE] +
-			((idx >> 1) << 2));
-		set_bit(idx, &eth->vlan_map);
-	}
-
-	return 0;
-}
-
-static int mtk_vlan_rx_kill_vid(struct net_device *dev,
-				__be16 proto, u16 vid)
-{
-	struct mtk_mac *mac = netdev_priv(dev);
-	struct mtk_eth *eth = mac->hw;
-	u32 idx = (vid & 0xf);
-
-	if (!((mtk_reg_table[MTK_REG_MTK_DMA_VID_BASE]) &&
-	      (dev->features & NETIF_F_HW_VLAN_CTAG_TX)))
-		return 0;
-
-	clear_bit(idx, &eth->vlan_map);
-
-	return 0;
-}
-
-static inline u32 mtk_pdma_empty_txd(struct mtk_tx_ring *ring)
-{
-	barrier();
-	return (u32)(ring->tx_ring_size -
-		     ((ring->tx_next_idx - ring->tx_free_idx) &
-		      (ring->tx_ring_size - 1)));
-}
-
-static int mtk_skb_padto(struct sk_buff *skb, struct mtk_eth *eth)
-{
-	unsigned int len;
-	int ret;
-
-	if (unlikely(skb->len >= VLAN_ETH_ZLEN))
-		return 0;
-
-	if (eth->soc->padding_64b && !eth->soc->padding_bug)
-		return 0;
-
-	if (skb_vlan_tag_present(skb))
-		len = ETH_ZLEN;
-	else if (skb->protocol == cpu_to_be16(ETH_P_8021Q))
-		len = VLAN_ETH_ZLEN;
-	else if (!eth->soc->padding_64b)
-		len = ETH_ZLEN;
-	else
-		return 0;
-
-	if (skb->len >= len)
-		return 0;
-
-	ret = skb_pad(skb, len - skb->len);
-	if (ret < 0)
-		return ret;
-	skb->len = len;
-	skb_set_tail_pointer(skb, len);
-
-	return ret;
-}
-
-static int mtk_pdma_tx_map(struct sk_buff *skb, struct net_device *dev,
-			   int tx_num, struct mtk_tx_ring *ring, bool gso)
-{
-	struct mtk_mac *mac = netdev_priv(dev);
-	struct mtk_eth *eth = mac->hw;
-	struct skb_frag_struct *frag;
-	struct mtk_tx_dma txd, *ptxd;
-	struct mtk_tx_buf *tx_buf;
-	int i, j, k, frag_size, frag_map_size, offset;
-	dma_addr_t mapped_addr;
-	unsigned int nr_frags;
-	u32 def_txd4;
-
-	if (mtk_skb_padto(skb, eth)) {
-		netif_warn(eth, tx_err, dev, "tx padding failed!\n");
-		return -1;
-	}
-
-	tx_buf = &ring->tx_buf[ring->tx_next_idx];
-	memset(tx_buf, 0, sizeof(*tx_buf));
-	memset(&txd, 0, sizeof(txd));
-	nr_frags = skb_shinfo(skb)->nr_frags;
-
-	/* init tx descriptor */
-	def_txd4 = eth->soc->txd4;
-	txd.txd4 = def_txd4;
-
-	if (eth->soc->mac_count > 1)
-		txd.txd4 |= (mac->id + 1) << TX_DMA_FPORT_SHIFT;
-
-	if (gso)
-		txd.txd4 |= TX_DMA_TSO;
-
-	/* TX Checksum offload */
-	if (skb->ip_summed == CHECKSUM_PARTIAL)
-		txd.txd4 |= TX_DMA_CHKSUM;
-
-	/* VLAN header offload */
-	if (skb_vlan_tag_present(skb)) {
-		u16 tag = skb_vlan_tag_get(skb);
-
-		txd.txd4 |= TX_DMA_INS_VLAN |
-			((tag >> VLAN_PRIO_SHIFT) << 4) |
-			(tag & 0xF);
-	}
-
-	mapped_addr = dma_map_single(&dev->dev, skb->data,
-				     skb_headlen(skb), DMA_TO_DEVICE);
-	if (unlikely(dma_mapping_error(&dev->dev, mapped_addr)))
-		return -1;
-
-	txd.txd1 = mapped_addr;
-	txd.txd2 = TX_DMA_PLEN0(skb_headlen(skb));
-
-	tx_buf->flags |= MTK_TX_FLAGS_SINGLE0;
-	dma_unmap_addr_set(tx_buf, dma_addr0, mapped_addr);
-	dma_unmap_len_set(tx_buf, dma_len0, skb_headlen(skb));
-
-	/* TX SG offload */
-	j = ring->tx_next_idx;
-	k = 0;
-	for (i = 0; i < nr_frags; i++) {
-		offset = 0;
-		frag = &skb_shinfo(skb)->frags[i];
-		frag_size = skb_frag_size(frag);
-
-		while (frag_size > 0) {
-			frag_map_size = min(frag_size, TX_DMA_BUF_LEN);
-			mapped_addr = skb_frag_dma_map(&dev->dev, frag, offset,
-						       frag_map_size,
-						       DMA_TO_DEVICE);
-			if (unlikely(dma_mapping_error(&dev->dev, mapped_addr)))
-				goto err_dma;
-
-			if (k & 0x1) {
-				j = NEXT_TX_DESP_IDX(j);
-				txd.txd1 = mapped_addr;
-				txd.txd2 = TX_DMA_PLEN0(frag_map_size);
-				txd.txd4 = def_txd4;
-
-				tx_buf = &ring->tx_buf[j];
-				memset(tx_buf, 0, sizeof(*tx_buf));
-
-				tx_buf->flags |= MTK_TX_FLAGS_PAGE0;
-				dma_unmap_addr_set(tx_buf, dma_addr0,
-						   mapped_addr);
-				dma_unmap_len_set(tx_buf, dma_len0,
-						  frag_map_size);
-			} else {
-				txd.txd3 = mapped_addr;
-				txd.txd2 |= TX_DMA_PLEN1(frag_map_size);
-
-				tx_buf->skb = (struct sk_buff *)DMA_DUMMY_DESC;
-				tx_buf->flags |= MTK_TX_FLAGS_PAGE1;
-				dma_unmap_addr_set(tx_buf, dma_addr1,
-						   mapped_addr);
-				dma_unmap_len_set(tx_buf, dma_len1,
-						  frag_map_size);
-
-				if (!((i == (nr_frags - 1)) &&
-				      (frag_map_size == frag_size))) {
-					mtk_set_txd_pdma(&txd,
-							 &ring->tx_dma[j]);
-					memset(&txd, 0, sizeof(txd));
-				}
-			}
-			frag_size -= frag_map_size;
-			offset += frag_map_size;
-			k++;
-		}
-	}
-
-	/* set last segment */
-	if (k & 0x1)
-		txd.txd2 |= TX_DMA_LS1;
-	else
-		txd.txd2 |= TX_DMA_LS0;
-	mtk_set_txd_pdma(&txd, &ring->tx_dma[j]);
-
-	/* store skb to cleanup */
-	tx_buf->skb = skb;
-
-	netdev_sent_queue(dev, skb->len);
-	skb_tx_timestamp(skb);
-
-	ring->tx_next_idx = NEXT_TX_DESP_IDX(j);
-	/* make sure that all changes to the dma ring are flushed before we
-	 * continue
-	 */
-	wmb();
-	atomic_set(&ring->tx_free_count, mtk_pdma_empty_txd(ring));
-
-	if (netif_xmit_stopped(netdev_get_tx_queue(dev, 0)) || !skb->xmit_more)
-		mtk_reg_w32(eth, ring->tx_next_idx, MTK_REG_TX_CTX_IDX0);
-
-	return 0;
-
-err_dma:
-	j = ring->tx_next_idx;
-	for (i = 0; i < tx_num; i++) {
-		ptxd = &ring->tx_dma[j];
-		tx_buf = &ring->tx_buf[j];
-
-		/* unmap dma */
-		mtk_txd_unmap(&dev->dev, tx_buf);
-
-		ptxd->txd2 = TX_DMA_DESP2_DEF;
-		j = NEXT_TX_DESP_IDX(j);
-	}
-	/* make sure that all changes to the dma ring are flushed before we
-	 * continue
-	 */
-	wmb();
-	return -1;
-}
-
-/* the qdma core needs scratch memory to be setup */
-static int mtk_init_fq_dma(struct mtk_eth *eth)
-{
-	dma_addr_t dma_addr, phy_ring_head, phy_ring_tail;
-	int cnt = eth->soc->dma_ring_size;
-	int i;
-
-	eth->scratch_ring = dma_alloc_coherent(eth->dev,
-					       cnt * sizeof(struct mtk_tx_dma),
-					       &phy_ring_head,
-					       GFP_ATOMIC | __GFP_ZERO);
-	if (unlikely(!eth->scratch_ring))
-		return -ENOMEM;
-
-	eth->scratch_head = kcalloc(cnt, QDMA_PAGE_SIZE,
-				    GFP_KERNEL);
-	dma_addr = dma_map_single(eth->dev,
-				  eth->scratch_head, cnt * QDMA_PAGE_SIZE,
-				  DMA_FROM_DEVICE);
-	if (unlikely(dma_mapping_error(eth->dev, dma_addr)))
-		return -ENOMEM;
-
-	memset(eth->scratch_ring, 0x0, sizeof(struct mtk_tx_dma) * cnt);
-	phy_ring_tail = phy_ring_head + (sizeof(struct mtk_tx_dma) * (cnt - 1));
-
-	for (i = 0; i < cnt; i++) {
-		eth->scratch_ring[i].txd1 = (dma_addr + (i * QDMA_PAGE_SIZE));
-		if (i < cnt - 1)
-			eth->scratch_ring[i].txd2 = (phy_ring_head +
-				((i + 1) * sizeof(struct mtk_tx_dma)));
-		eth->scratch_ring[i].txd3 = TX_QDMA_SDL(QDMA_PAGE_SIZE);
-	}
-
-	mtk_w32(eth, phy_ring_head, MTK_QDMA_FQ_HEAD);
-	mtk_w32(eth, phy_ring_tail, MTK_QDMA_FQ_TAIL);
-	mtk_w32(eth, (cnt << 16) | cnt, MTK_QDMA_FQ_CNT);
-	mtk_w32(eth, QDMA_PAGE_SIZE << 16, MTK_QDMA_FQ_BLEN);
-
-	return 0;
-}
-
-static void *mtk_qdma_phys_to_virt(struct mtk_tx_ring *ring, u32 desc)
-{
-	void *ret = ring->tx_dma;
-
-	return ret + (desc - ring->tx_phys);
-}
-
-static struct mtk_tx_dma *mtk_tx_next_qdma(struct mtk_tx_ring *ring,
-					   struct mtk_tx_dma *txd)
-{
-	return mtk_qdma_phys_to_virt(ring, txd->txd2);
-}
-
-static struct mtk_tx_buf *mtk_desc_to_tx_buf(struct mtk_tx_ring *ring,
-					     struct mtk_tx_dma *txd)
-{
-	int idx = txd - ring->tx_dma;
-
-	return &ring->tx_buf[idx];
-}
-
-static int mtk_qdma_tx_map(struct sk_buff *skb, struct net_device *dev,
-			   int tx_num, struct mtk_tx_ring *ring, bool gso)
-{
-	struct mtk_mac *mac = netdev_priv(dev);
-	struct mtk_eth *eth = mac->hw;
-	struct mtk_tx_dma *itxd, *txd;
-	struct mtk_tx_buf *tx_buf;
-	dma_addr_t mapped_addr;
-	unsigned int nr_frags;
-	int i, n_desc = 1;
-	u32 txd4 = eth->soc->txd4;
-
-	itxd = ring->tx_next_free;
-	if (itxd == ring->tx_last_free)
-		return -ENOMEM;
-
-	if (eth->soc->mac_count > 1)
-		txd4 |= (mac->id + 1) << TX_DMA_FPORT_SHIFT;
-
-	tx_buf = mtk_desc_to_tx_buf(ring, itxd);
-	memset(tx_buf, 0, sizeof(*tx_buf));
-
-	if (gso)
-		txd4 |= TX_DMA_TSO;
-
-	/* TX Checksum offload */
-	if (skb->ip_summed == CHECKSUM_PARTIAL)
-		txd4 |= TX_DMA_CHKSUM;
-
-	/* VLAN header offload */
-	if (skb_vlan_tag_present(skb))
-		txd4 |= TX_DMA_INS_VLAN_MT7621 | skb_vlan_tag_get(skb);
-
-	mapped_addr = dma_map_single(&dev->dev, skb->data,
-				     skb_headlen(skb), DMA_TO_DEVICE);
-	if (unlikely(dma_mapping_error(&dev->dev, mapped_addr)))
-		return -ENOMEM;
-
-	WRITE_ONCE(itxd->txd1, mapped_addr);
-	tx_buf->flags |= MTK_TX_FLAGS_SINGLE0;
-	dma_unmap_addr_set(tx_buf, dma_addr0, mapped_addr);
-	dma_unmap_len_set(tx_buf, dma_len0, skb_headlen(skb));
-
-	/* TX SG offload */
-	txd = itxd;
-	nr_frags = skb_shinfo(skb)->nr_frags;
-	for (i = 0; i < nr_frags; i++) {
-		struct skb_frag_struct *frag = &skb_shinfo(skb)->frags[i];
-		unsigned int offset = 0;
-		int frag_size = skb_frag_size(frag);
-
-		while (frag_size) {
-			bool last_frag = false;
-			unsigned int frag_map_size;
-
-			txd = mtk_tx_next_qdma(ring, txd);
-			if (txd == ring->tx_last_free)
-				goto err_dma;
-
-			n_desc++;
-			frag_map_size = min(frag_size, TX_DMA_BUF_LEN);
-			mapped_addr = skb_frag_dma_map(&dev->dev, frag, offset,
-						       frag_map_size,
-						       DMA_TO_DEVICE);
-			if (unlikely(dma_mapping_error(&dev->dev, mapped_addr)))
-				goto err_dma;
-
-			if (i == nr_frags - 1 &&
-			    (frag_size - frag_map_size) == 0)
-				last_frag = true;
-
-			WRITE_ONCE(txd->txd1, mapped_addr);
-			WRITE_ONCE(txd->txd3, (QDMA_TX_SWC |
-					       TX_DMA_PLEN0(frag_map_size) |
-					       last_frag * TX_DMA_LS0) |
-					       mac->id);
-			WRITE_ONCE(txd->txd4, 0);
-
-			tx_buf->skb = (struct sk_buff *)DMA_DUMMY_DESC;
-			tx_buf = mtk_desc_to_tx_buf(ring, txd);
-			memset(tx_buf, 0, sizeof(*tx_buf));
-
-			tx_buf->flags |= MTK_TX_FLAGS_PAGE0;
-			dma_unmap_addr_set(tx_buf, dma_addr0, mapped_addr);
-			dma_unmap_len_set(tx_buf, dma_len0, frag_map_size);
-			frag_size -= frag_map_size;
-			offset += frag_map_size;
-		}
-	}
-
-	/* store skb to cleanup */
-	tx_buf->skb = skb;
-
-	WRITE_ONCE(itxd->txd4, txd4);
-	WRITE_ONCE(itxd->txd3, (QDMA_TX_SWC | TX_DMA_PLEN0(skb_headlen(skb)) |
-				(!nr_frags * TX_DMA_LS0)));
-
-	netdev_sent_queue(dev, skb->len);
-	skb_tx_timestamp(skb);
-
-	ring->tx_next_free = mtk_tx_next_qdma(ring, txd);
-	atomic_sub(n_desc, &ring->tx_free_count);
-
-	/* make sure that all changes to the dma ring are flushed before we
-	 * continue
-	 */
-	wmb();
-
-	if (netif_xmit_stopped(netdev_get_tx_queue(dev, 0)) || !skb->xmit_more)
-		mtk_w32(eth, txd->txd2, MTK_QTX_CTX_PTR);
-
-	return 0;
-
-err_dma:
-	do {
-		tx_buf = mtk_desc_to_tx_buf(ring, txd);
-
-		/* unmap dma */
-		mtk_txd_unmap(&dev->dev, tx_buf);
-
-		itxd->txd3 = TX_DMA_DESP2_DEF;
-		itxd = mtk_tx_next_qdma(ring, itxd);
-	} while (itxd != txd);
-
-	return -ENOMEM;
-}
-
-static inline int mtk_cal_txd_req(struct sk_buff *skb)
-{
-	int i, nfrags;
-	struct skb_frag_struct *frag;
-
-	nfrags = 1;
-	if (skb_is_gso(skb)) {
-		for (i = 0; i < skb_shinfo(skb)->nr_frags; i++) {
-			frag = &skb_shinfo(skb)->frags[i];
-			nfrags += DIV_ROUND_UP(frag->size, TX_DMA_BUF_LEN);
-		}
-	} else {
-		nfrags += skb_shinfo(skb)->nr_frags;
-	}
-
-	return DIV_ROUND_UP(nfrags, 2);
-}
-
-static int mtk_start_xmit(struct sk_buff *skb, struct net_device *dev)
-{
-	struct mtk_mac *mac = netdev_priv(dev);
-	struct mtk_eth *eth = mac->hw;
-	struct mtk_tx_ring *ring = &eth->tx_ring;
-	struct net_device_stats *stats = &dev->stats;
-	int tx_num;
-	int len = skb->len;
-	bool gso = false;
-
-	tx_num = mtk_cal_txd_req(skb);
-	if (unlikely(atomic_read(&ring->tx_free_count) <= tx_num)) {
-		netif_stop_queue(dev);
-		netif_err(eth, tx_queued, dev,
-			  "Tx Ring full when queue awake!\n");
-		return NETDEV_TX_BUSY;
-	}
-
-	/* TSO: fill MSS info in tcp checksum field */
-	if (skb_is_gso(skb)) {
-		if (skb_cow_head(skb, 0)) {
-			netif_warn(eth, tx_err, dev,
-				   "GSO expand head fail.\n");
-			goto drop;
-		}
-
-		if (skb_shinfo(skb)->gso_type &
-				(SKB_GSO_TCPV4 | SKB_GSO_TCPV6)) {
-			gso = true;
-			tcp_hdr(skb)->check = htons(skb_shinfo(skb)->gso_size);
-		}
-	}
-
-	if (ring->tx_map(skb, dev, tx_num, ring, gso) < 0)
-		goto drop;
-
-	stats->tx_packets++;
-	stats->tx_bytes += len;
-
-	if (unlikely(atomic_read(&ring->tx_free_count) <= ring->tx_thresh)) {
-		netif_stop_queue(dev);
-		smp_mb();
-		if (unlikely(atomic_read(&ring->tx_free_count) >
-			     ring->tx_thresh))
-			netif_wake_queue(dev);
-	}
-
-	return NETDEV_TX_OK;
-
-drop:
-	stats->tx_dropped++;
-	dev_kfree_skb(skb);
-	return NETDEV_TX_OK;
-}
-
-static int mtk_poll_rx(struct napi_struct *napi, int budget,
-		       struct mtk_eth *eth, u32 rx_intr)
-{
-	struct mtk_soc_data *soc = eth->soc;
-	struct mtk_rx_ring *ring = &eth->rx_ring[0];
-	int idx = ring->rx_calc_idx;
-	u32 checksum_bit;
-	struct sk_buff *skb;
-	u8 *data, *new_data;
-	struct mtk_rx_dma *rxd, trxd;
-	int done = 0, pad;
-
-	if (eth->soc->hw_features & NETIF_F_RXCSUM)
-		checksum_bit = soc->checksum_bit;
-	else
-		checksum_bit = 0;
-
-	if (eth->soc->rx_2b_offset)
-		pad = 0;
-	else
-		pad = NET_IP_ALIGN;
-
-	while (done < budget) {
-		struct net_device *netdev;
-		unsigned int pktlen;
-		dma_addr_t dma_addr;
-		int mac = 0;
-
-		idx = NEXT_RX_DESP_IDX(idx);
-		rxd = &ring->rx_dma[idx];
-		data = ring->rx_data[idx];
-
-		mtk_get_rxd(&trxd, rxd);
-		if (!(trxd.rxd2 & RX_DMA_DONE))
-			break;
-
-		/* find out which mac the packet come from. values start at 1 */
-		if (eth->soc->mac_count > 1) {
-			mac = (trxd.rxd4 >> RX_DMA_FPORT_SHIFT) &
-			      RX_DMA_FPORT_MASK;
-			mac--;
-			if (mac < 0 || mac >= eth->soc->mac_count)
-				goto release_desc;
-		}
-
-		netdev = eth->netdev[mac];
-
-		/* alloc new buffer */
-		new_data = napi_alloc_frag(ring->frag_size);
-		if (unlikely(!new_data || !netdev)) {
-			netdev->stats.rx_dropped++;
-			goto release_desc;
-		}
-		dma_addr = dma_map_single(&netdev->dev,
-					  new_data + NET_SKB_PAD + pad,
-					  ring->rx_buf_size,
-					  DMA_FROM_DEVICE);
-		if (unlikely(dma_mapping_error(&netdev->dev, dma_addr))) {
-			skb_free_frag(new_data);
-			goto release_desc;
-		}
-
-		/* receive data */
-		skb = build_skb(data, ring->frag_size);
-		if (unlikely(!skb)) {
-			put_page(virt_to_head_page(new_data));
-			goto release_desc;
-		}
-		skb_reserve(skb, NET_SKB_PAD + NET_IP_ALIGN);
-
-		dma_unmap_single(&netdev->dev, trxd.rxd1,
-				 ring->rx_buf_size, DMA_FROM_DEVICE);
-		pktlen = RX_DMA_GET_PLEN0(trxd.rxd2);
-		skb->dev = netdev;
-		skb_put(skb, pktlen);
-		if (trxd.rxd4 & checksum_bit)
-			skb->ip_summed = CHECKSUM_UNNECESSARY;
-		else
-			skb_checksum_none_assert(skb);
-		skb->protocol = eth_type_trans(skb, netdev);
-
-		netdev->stats.rx_packets++;
-		netdev->stats.rx_bytes += pktlen;
-
-		if (netdev->features & NETIF_F_HW_VLAN_CTAG_RX &&
-		    RX_DMA_VID(trxd.rxd3))
-			__vlan_hwaccel_put_tag(skb, htons(ETH_P_8021Q),
-					       RX_DMA_VID(trxd.rxd3));
-		napi_gro_receive(napi, skb);
-
-		ring->rx_data[idx] = new_data;
-		rxd->rxd1 = (unsigned int)dma_addr;
-
-release_desc:
-		if (eth->soc->rx_sg_dma)
-			rxd->rxd2 = RX_DMA_PLEN0(ring->rx_buf_size);
-		else
-			rxd->rxd2 = RX_DMA_LSO;
-
-		ring->rx_calc_idx = idx;
-		/* make sure that all changes to the dma ring are flushed before
-		 * we continue
-		 */
-		wmb();
-		if (eth->soc->dma_type == MTK_QDMA)
-			mtk_w32(eth, ring->rx_calc_idx, MTK_QRX_CRX_IDX0);
-		else
-			mtk_reg_w32(eth, ring->rx_calc_idx,
-				    MTK_REG_RX_CALC_IDX0);
-		done++;
-	}
-
-	if (done < budget)
-		mtk_irq_ack(eth, rx_intr);
-
-	return done;
-}
-
-static int mtk_pdma_tx_poll(struct mtk_eth *eth, int budget, bool *tx_again)
-{
-	struct sk_buff *skb;
-	struct mtk_tx_buf *tx_buf;
-	int done = 0;
-	u32 idx, hwidx;
-	struct mtk_tx_ring *ring = &eth->tx_ring;
-	unsigned int bytes = 0;
-
-	idx = ring->tx_free_idx;
-	hwidx = mtk_reg_r32(eth, MTK_REG_TX_DTX_IDX0);
-
-	while ((idx != hwidx) && budget) {
-		tx_buf = &ring->tx_buf[idx];
-		skb = tx_buf->skb;
-
-		if (!skb)
-			break;
-
-		if (skb != (struct sk_buff *)DMA_DUMMY_DESC) {
-			bytes += skb->len;
-			done++;
-			budget--;
-		}
-		mtk_txd_unmap(eth->dev, tx_buf);
-		idx = NEXT_TX_DESP_IDX(idx);
-	}
-	ring->tx_free_idx = idx;
-	atomic_set(&ring->tx_free_count, mtk_pdma_empty_txd(ring));
-
-	/* read hw index again make sure no new tx packet */
-	if (idx != hwidx || idx != mtk_reg_r32(eth, MTK_REG_TX_DTX_IDX0))
-		*tx_again = 1;
-
-	if (done)
-		netdev_completed_queue(*eth->netdev, done, bytes);
-
-	return done;
-}
-
-static int mtk_qdma_tx_poll(struct mtk_eth *eth, int budget, bool *tx_again)
-{
-	struct mtk_tx_ring *ring = &eth->tx_ring;
-	struct mtk_tx_dma *desc;
-	struct sk_buff *skb;
-	struct mtk_tx_buf *tx_buf;
-	int total = 0, done[MTK_MAX_DEVS];
-	unsigned int bytes[MTK_MAX_DEVS];
-	u32 cpu, dma;
-	int i;
-
-	memset(done, 0, sizeof(done));
-	memset(bytes, 0, sizeof(bytes));
-
-	cpu = mtk_r32(eth, MTK_QTX_CRX_PTR);
-	dma = mtk_r32(eth, MTK_QTX_DRX_PTR);
-
-	desc = mtk_qdma_phys_to_virt(ring, cpu);
-
-	while ((cpu != dma) && budget) {
-		u32 next_cpu = desc->txd2;
-		int mac;
-
-		desc = mtk_tx_next_qdma(ring, desc);
-		if ((desc->txd3 & QDMA_TX_OWNER_CPU) == 0)
-			break;
-
-		mac = (desc->txd4 >> TX_DMA_FPORT_SHIFT) &
-		       TX_DMA_FPORT_MASK;
-		mac--;
-
-		tx_buf = mtk_desc_to_tx_buf(ring, desc);
-		skb = tx_buf->skb;
-		if (!skb)
-			break;
-
-		if (skb != (struct sk_buff *)DMA_DUMMY_DESC) {
-			bytes[mac] += skb->len;
-			done[mac]++;
-			budget--;
-		}
-		mtk_txd_unmap(eth->dev, tx_buf);
-
-		ring->tx_last_free->txd2 = next_cpu;
-		ring->tx_last_free = desc;
-		atomic_inc(&ring->tx_free_count);
-
-		cpu = next_cpu;
-	}
-
-	mtk_w32(eth, cpu, MTK_QTX_CRX_PTR);
-
-	/* read hw index again make sure no new tx packet */
-	if (cpu != dma || cpu != mtk_r32(eth, MTK_QTX_DRX_PTR))
-		*tx_again = true;
-
-	for (i = 0; i < eth->soc->mac_count; i++) {
-		if (!done[i])
-			continue;
-		netdev_completed_queue(eth->netdev[i], done[i], bytes[i]);
-		total += done[i];
-	}
-
-	return total;
-}
-
-static int mtk_poll_tx(struct mtk_eth *eth, int budget, u32 tx_intr,
-		       bool *tx_again)
-{
-	struct mtk_tx_ring *ring = &eth->tx_ring;
-	struct net_device *netdev = eth->netdev[0];
-	int done;
-
-	done = eth->tx_ring.tx_poll(eth, budget, tx_again);
-	if (!*tx_again)
-		mtk_irq_ack(eth, tx_intr);
-
-	if (!done)
-		return 0;
-
-	smp_mb();
-	if (unlikely(!netif_queue_stopped(netdev)))
-		return done;
-
-	if (atomic_read(&ring->tx_free_count) > ring->tx_thresh)
-		netif_wake_queue(netdev);
-
-	return done;
-}
-
-static void mtk_stats_update(struct mtk_eth *eth)
-{
-	int i;
-
-	for (i = 0; i < eth->soc->mac_count; i++) {
-		if (!eth->mac[i] || !eth->mac[i]->hw_stats)
-			continue;
-		if (spin_trylock(&eth->mac[i]->hw_stats->stats_lock)) {
-			mtk_stats_update_mac(eth->mac[i]);
-			spin_unlock(&eth->mac[i]->hw_stats->stats_lock);
-		}
-	}
-}
-
-static int mtk_poll(struct napi_struct *napi, int budget)
-{
-	struct mtk_eth *eth = container_of(napi, struct mtk_eth, rx_napi);
-	u32 status, mtk_status, mask, tx_intr, rx_intr, status_intr;
-	int tx_done, rx_done;
-	bool tx_again = false;
-
-	status = mtk_irq_pending(eth);
-	mtk_status = mtk_irq_pending_status(eth);
-	tx_intr = eth->soc->tx_int;
-	rx_intr = eth->soc->rx_int;
-	status_intr = eth->soc->status_int;
-	tx_done = 0;
-	rx_done = 0;
-	tx_again = 0;
-
-	if (status & tx_intr)
-		tx_done = mtk_poll_tx(eth, budget, tx_intr, &tx_again);
-
-	if (status & rx_intr)
-		rx_done = mtk_poll_rx(napi, budget, eth, rx_intr);
-
-	if (unlikely(mtk_status & status_intr)) {
-		mtk_stats_update(eth);
-		mtk_irq_ack_status(eth, status_intr);
-	}
-
-	if (unlikely(netif_msg_intr(eth))) {
-		mask = mtk_irq_enabled(eth);
-		netdev_info(eth->netdev[0],
-			    "done tx %d, rx %d, intr 0x%08x/0x%x\n",
-			    tx_done, rx_done, status, mask);
-	}
-
-	if (tx_again || rx_done == budget)
-		return budget;
-
-	status = mtk_irq_pending(eth);
-	if (status & (tx_intr | rx_intr))
-		return budget;
-
-	napi_complete(napi);
-	mtk_irq_enable(eth, tx_intr | rx_intr);
-
-	return rx_done;
-}
-
-static int mtk_pdma_tx_alloc(struct mtk_eth *eth)
-{
-	int i;
-	struct mtk_tx_ring *ring = &eth->tx_ring;
-
-	ring->tx_ring_size = eth->soc->dma_ring_size;
-	ring->tx_free_idx = 0;
-	ring->tx_next_idx = 0;
-	ring->tx_thresh = max((unsigned long)ring->tx_ring_size >> 2,
-			      MAX_SKB_FRAGS);
-
-	ring->tx_buf = kcalloc(ring->tx_ring_size, sizeof(*ring->tx_buf),
-			       GFP_KERNEL);
-	if (!ring->tx_buf)
-		goto no_tx_mem;
-
-	ring->tx_dma =
-		dma_alloc_coherent(eth->dev,
-				   ring->tx_ring_size * sizeof(*ring->tx_dma),
-				   &ring->tx_phys, GFP_ATOMIC | __GFP_ZERO);
-	if (!ring->tx_dma)
-		goto no_tx_mem;
-
-	for (i = 0; i < ring->tx_ring_size; i++) {
-		ring->tx_dma[i].txd2 = TX_DMA_DESP2_DEF;
-		ring->tx_dma[i].txd4 = eth->soc->txd4;
-	}
-
-	atomic_set(&ring->tx_free_count, mtk_pdma_empty_txd(ring));
-	ring->tx_map = mtk_pdma_tx_map;
-	ring->tx_poll = mtk_pdma_tx_poll;
-	ring->tx_clean = mtk_pdma_tx_clean;
-
-	/* make sure that all changes to the dma ring are flushed before we
-	 * continue
-	 */
-	wmb();
-
-	mtk_reg_w32(eth, ring->tx_phys, MTK_REG_TX_BASE_PTR0);
-	mtk_reg_w32(eth, ring->tx_ring_size, MTK_REG_TX_MAX_CNT0);
-	mtk_reg_w32(eth, 0, MTK_REG_TX_CTX_IDX0);
-	mtk_reg_w32(eth, MTK_PST_DTX_IDX0, MTK_REG_PDMA_RST_CFG);
-
-	return 0;
-
-no_tx_mem:
-	return -ENOMEM;
-}
-
-static int mtk_qdma_tx_alloc_tx(struct mtk_eth *eth)
-{
-	struct mtk_tx_ring *ring = &eth->tx_ring;
-	int i, sz = sizeof(*ring->tx_dma);
-
-	ring->tx_ring_size = eth->soc->dma_ring_size;
-	ring->tx_buf = kcalloc(ring->tx_ring_size, sizeof(*ring->tx_buf),
-			       GFP_KERNEL);
-	if (!ring->tx_buf)
-		goto no_tx_mem;
-
-	ring->tx_dma = dma_alloc_coherent(eth->dev, ring->tx_ring_size * sz,
-					  &ring->tx_phys,
-					  GFP_ATOMIC | __GFP_ZERO);
-	if (!ring->tx_dma)
-		goto no_tx_mem;
-
-	for (i = 0; i < ring->tx_ring_size; i++) {
-		int next = (i + 1) % ring->tx_ring_size;
-		u32 next_ptr = ring->tx_phys + next * sz;
-
-		ring->tx_dma[i].txd2 = next_ptr;
-		ring->tx_dma[i].txd3 = TX_DMA_DESP2_DEF;
-	}
-
-	atomic_set(&ring->tx_free_count, ring->tx_ring_size - 2);
-	ring->tx_next_free = &ring->tx_dma[0];
-	ring->tx_last_free = &ring->tx_dma[ring->tx_ring_size - 2];
-	ring->tx_thresh = max((unsigned long)ring->tx_ring_size >> 2,
-			      MAX_SKB_FRAGS);
-
-	ring->tx_map = mtk_qdma_tx_map;
-	ring->tx_poll = mtk_qdma_tx_poll;
-	ring->tx_clean = mtk_qdma_tx_clean;
-
-	/* make sure that all changes to the dma ring are flushed before we
-	 * continue
-	 */
-	wmb();
-
-	mtk_w32(eth, ring->tx_phys, MTK_QTX_CTX_PTR);
-	mtk_w32(eth, ring->tx_phys, MTK_QTX_DTX_PTR);
-	mtk_w32(eth,
-		ring->tx_phys + ((ring->tx_ring_size - 1) * sz),
-		MTK_QTX_CRX_PTR);
-	mtk_w32(eth,
-		ring->tx_phys + ((ring->tx_ring_size - 1) * sz),
-		MTK_QTX_DRX_PTR);
-
-	return 0;
-
-no_tx_mem:
-	return -ENOMEM;
-}
-
-static int mtk_qdma_init(struct mtk_eth *eth, int ring)
-{
-	int err;
-
-	err = mtk_init_fq_dma(eth);
-	if (err)
-		return err;
-
-	err = mtk_qdma_tx_alloc_tx(eth);
-	if (err)
-		return err;
-
-	err = mtk_dma_rx_alloc(eth, &eth->rx_ring[ring]);
-	if (err)
-		return err;
-
-	mtk_w32(eth, eth->rx_ring[ring].rx_phys, MTK_QRX_BASE_PTR0);
-	mtk_w32(eth, eth->rx_ring[ring].rx_ring_size, MTK_QRX_MAX_CNT0);
-	mtk_w32(eth, eth->rx_ring[ring].rx_calc_idx, MTK_QRX_CRX_IDX0);
-	mtk_w32(eth, MTK_PST_DRX_IDX0, MTK_QDMA_RST_IDX);
-	mtk_w32(eth, (QDMA_RES_THRES << 8) | QDMA_RES_THRES, MTK_QTX_CFG(0));
-
-	/* Enable random early drop and set drop threshold automatically */
-	mtk_w32(eth, 0x174444, MTK_QDMA_FC_THRES);
-	mtk_w32(eth, 0x0, MTK_QDMA_HRED2);
-
-	return 0;
-}
-
-static int mtk_pdma_qdma_init(struct mtk_eth *eth)
-{
-	int err = mtk_qdma_init(eth, 1);
-
-	if (err)
-		return err;
-
-	err = mtk_dma_rx_alloc(eth, &eth->rx_ring[0]);
-	if (err)
-		return err;
-
-	mtk_reg_w32(eth, eth->rx_ring[0].rx_phys, MTK_REG_RX_BASE_PTR0);
-	mtk_reg_w32(eth, eth->rx_ring[0].rx_ring_size, MTK_REG_RX_MAX_CNT0);
-	mtk_reg_w32(eth, eth->rx_ring[0].rx_calc_idx, MTK_REG_RX_CALC_IDX0);
-	mtk_reg_w32(eth, MTK_PST_DRX_IDX0, MTK_REG_PDMA_RST_CFG);
-
-	return 0;
-}
-
-static int mtk_pdma_init(struct mtk_eth *eth)
-{
-	struct mtk_rx_ring *ring = &eth->rx_ring[0];
-	int err;
-
-	err = mtk_pdma_tx_alloc(eth);
-	if (err)
-		return err;
-
-	err = mtk_dma_rx_alloc(eth, ring);
-	if (err)
-		return err;
-
-	mtk_reg_w32(eth, ring->rx_phys, MTK_REG_RX_BASE_PTR0);
-	mtk_reg_w32(eth, ring->rx_ring_size, MTK_REG_RX_MAX_CNT0);
-	mtk_reg_w32(eth, ring->rx_calc_idx, MTK_REG_RX_CALC_IDX0);
-	mtk_reg_w32(eth, MTK_PST_DRX_IDX0, MTK_REG_PDMA_RST_CFG);
-
-	return 0;
-}
-
-static void mtk_dma_free(struct mtk_eth *eth)
-{
-	int i;
-
-	for (i = 0; i < eth->soc->mac_count; i++)
-		if (eth->netdev[i])
-			netdev_reset_queue(eth->netdev[i]);
-	eth->tx_ring.tx_clean(eth);
-	mtk_clean_rx(eth, &eth->rx_ring[0]);
-	mtk_clean_rx(eth, &eth->rx_ring[1]);
-	kfree(eth->scratch_head);
-}
-
-static void mtk_tx_timeout(struct net_device *dev)
-{
-	struct mtk_mac *mac = netdev_priv(dev);
-	struct mtk_eth *eth = mac->hw;
-	struct mtk_tx_ring *ring = &eth->tx_ring;
-
-	eth->netdev[mac->id]->stats.tx_errors++;
-	netif_err(eth, tx_err, dev,
-		  "transmit timed out\n");
-	if (eth->soc->dma_type & MTK_PDMA) {
-		netif_info(eth, drv, dev, "pdma_cfg:%08x\n",
-			   mtk_reg_r32(eth, MTK_REG_PDMA_GLO_CFG));
-		netif_info(eth, drv, dev,
-			   "tx_ring=%d, base=%08x, max=%u, ctx=%u, dtx=%u, fdx=%hu, next=%hu\n",
-			   0, mtk_reg_r32(eth, MTK_REG_TX_BASE_PTR0),
-			   mtk_reg_r32(eth, MTK_REG_TX_MAX_CNT0),
-			   mtk_reg_r32(eth, MTK_REG_TX_CTX_IDX0),
-			   mtk_reg_r32(eth, MTK_REG_TX_DTX_IDX0),
-			   ring->tx_free_idx,
-			   ring->tx_next_idx);
-	}
-	if (eth->soc->dma_type & MTK_QDMA) {
-		netif_info(eth, drv, dev, "qdma_cfg:%08x\n",
-			   mtk_r32(eth, MTK_QDMA_GLO_CFG));
-		netif_info(eth, drv, dev,
-			   "tx_ring=%d, ctx=%08x, dtx=%08x, crx=%08x, drx=%08x, free=%hu\n",
-			   0, mtk_r32(eth, MTK_QTX_CTX_PTR),
-			   mtk_r32(eth, MTK_QTX_DTX_PTR),
-			   mtk_r32(eth, MTK_QTX_CRX_PTR),
-			   mtk_r32(eth, MTK_QTX_DRX_PTR),
-			   atomic_read(&ring->tx_free_count));
-	}
-	netif_info(eth, drv, dev,
-		   "rx_ring=%d, base=%08x, max=%u, calc=%u, drx=%u\n",
-		   0, mtk_reg_r32(eth, MTK_REG_RX_BASE_PTR0),
-		   mtk_reg_r32(eth, MTK_REG_RX_MAX_CNT0),
-		   mtk_reg_r32(eth, MTK_REG_RX_CALC_IDX0),
-		   mtk_reg_r32(eth, MTK_REG_RX_DRX_IDX0));
-
-	schedule_work(&mac->pending_work);
-}
-
-static irqreturn_t mtk_handle_irq(int irq, void *_eth)
-{
-	struct mtk_eth *eth = _eth;
-	u32 status, int_mask;
-
-	status = mtk_irq_pending(eth);
-	if (unlikely(!status))
-		return IRQ_NONE;
-
-	int_mask = (eth->soc->rx_int | eth->soc->tx_int);
-	if (likely(status & int_mask)) {
-		if (likely(napi_schedule_prep(&eth->rx_napi)))
-			__napi_schedule(&eth->rx_napi);
-	} else {
-		mtk_irq_ack(eth, status);
-	}
-	mtk_irq_disable(eth, int_mask);
-
-	return IRQ_HANDLED;
-}
-
-#ifdef CONFIG_NET_POLL_CONTROLLER
-static void mtk_poll_controller(struct net_device *dev)
-{
-	struct mtk_mac *mac = netdev_priv(dev);
-	struct mtk_eth *eth = mac->hw;
-	u32 int_mask = eth->soc->tx_int | eth->soc->rx_int;
-
-	mtk_irq_disable(eth, int_mask);
-	mtk_handle_irq(dev->irq, dev);
-	mtk_irq_enable(eth, int_mask);
-}
-#endif
-
-int mtk_set_clock_cycle(struct mtk_eth *eth)
-{
-	unsigned long sysclk = eth->sysclk;
-
-	sysclk /= MTK_US_CYC_CNT_DIVISOR;
-	sysclk <<= MTK_US_CYC_CNT_SHIFT;
-
-	mtk_w32(eth, (mtk_r32(eth, MTK_GLO_CFG) &
-			~(MTK_US_CYC_CNT_MASK << MTK_US_CYC_CNT_SHIFT)) |
-			sysclk,
-			MTK_GLO_CFG);
-	return 0;
-}
-
-void mtk_fwd_config(struct mtk_eth *eth)
-{
-	u32 fwd_cfg;
-
-	fwd_cfg = mtk_r32(eth, MTK_GDMA1_FWD_CFG);
-
-	/* disable jumbo frame */
-	if (eth->soc->jumbo_frame)
-		fwd_cfg &= ~MTK_GDM1_JMB_EN;
-
-	/* set unicast/multicast/broadcast frame to cpu */
-	fwd_cfg &= ~0xffff;
-
-	mtk_w32(eth, fwd_cfg, MTK_GDMA1_FWD_CFG);
-}
-
-void mtk_csum_config(struct mtk_eth *eth)
-{
-	if (eth->soc->hw_features & NETIF_F_RXCSUM)
-		mtk_w32(eth, mtk_r32(eth, MTK_GDMA1_FWD_CFG) |
-			(MTK_GDM1_ICS_EN | MTK_GDM1_TCS_EN | MTK_GDM1_UCS_EN),
-			MTK_GDMA1_FWD_CFG);
-	else
-		mtk_w32(eth, mtk_r32(eth, MTK_GDMA1_FWD_CFG) &
-			~(MTK_GDM1_ICS_EN | MTK_GDM1_TCS_EN | MTK_GDM1_UCS_EN),
-			MTK_GDMA1_FWD_CFG);
-	if (eth->soc->hw_features & NETIF_F_IP_CSUM)
-		mtk_w32(eth, mtk_r32(eth, MTK_CDMA_CSG_CFG) |
-			(MTK_ICS_GEN_EN | MTK_TCS_GEN_EN | MTK_UCS_GEN_EN),
-			MTK_CDMA_CSG_CFG);
-	else
-		mtk_w32(eth, mtk_r32(eth, MTK_CDMA_CSG_CFG) &
-			~(MTK_ICS_GEN_EN | MTK_TCS_GEN_EN | MTK_UCS_GEN_EN),
-			MTK_CDMA_CSG_CFG);
-}
-
-static int mtk_start_dma(struct mtk_eth *eth)
-{
-	unsigned long flags;
-	u32 val;
-	int err;
-
-	if (eth->soc->dma_type == MTK_PDMA)
-		err = mtk_pdma_init(eth);
-	else if (eth->soc->dma_type == MTK_QDMA)
-		err = mtk_qdma_init(eth, 0);
-	else
-		err = mtk_pdma_qdma_init(eth);
-	if (err) {
-		mtk_dma_free(eth);
-		return err;
-	}
-
-	spin_lock_irqsave(&eth->page_lock, flags);
-
-	val = MTK_TX_WB_DDONE | MTK_RX_DMA_EN | MTK_TX_DMA_EN;
-	if (eth->soc->rx_2b_offset)
-		val |= MTK_RX_2B_OFFSET;
-	val |= eth->soc->pdma_glo_cfg;
-
-	if (eth->soc->dma_type & MTK_PDMA)
-		mtk_reg_w32(eth, val, MTK_REG_PDMA_GLO_CFG);
-
-	if (eth->soc->dma_type & MTK_QDMA)
-		mtk_w32(eth, val, MTK_QDMA_GLO_CFG);
-
-	spin_unlock_irqrestore(&eth->page_lock, flags);
-
-	return 0;
-}
-
-static int mtk_open(struct net_device *dev)
-{
-	struct mtk_mac *mac = netdev_priv(dev);
-	struct mtk_eth *eth = mac->hw;
-
-	dma_coerce_mask_and_coherent(&dev->dev, DMA_BIT_MASK(32));
-
-	if (!atomic_read(&eth->dma_refcnt)) {
-		int err = mtk_start_dma(eth);
-
-		if (err)
-			return err;
-
-		napi_enable(&eth->rx_napi);
-		mtk_irq_enable(eth, eth->soc->tx_int | eth->soc->rx_int);
-	}
-	atomic_inc(&eth->dma_refcnt);
-
-	if (eth->phy)
-		eth->phy->start(mac);
-
-	if (eth->soc->has_carrier && eth->soc->has_carrier(eth))
-		netif_carrier_on(dev);
-
-	netif_start_queue(dev);
-	eth->soc->fwd_config(eth);
-
-	return 0;
-}
-
-static void mtk_stop_dma(struct mtk_eth *eth, u32 glo_cfg)
-{
-	unsigned long flags;
-	u32 val;
-	int i;
-
-	/* stop the dma enfine */
-	spin_lock_irqsave(&eth->page_lock, flags);
-	val = mtk_r32(eth, glo_cfg);
-	mtk_w32(eth, val & ~(MTK_TX_WB_DDONE | MTK_RX_DMA_EN | MTK_TX_DMA_EN),
-		glo_cfg);
-	spin_unlock_irqrestore(&eth->page_lock, flags);
-
-	/* wait for dma stop */
-	for (i = 0; i < 10; i++) {
-		val = mtk_r32(eth, glo_cfg);
-		if (val & (MTK_TX_DMA_BUSY | MTK_RX_DMA_BUSY)) {
-			msleep(20);
-			continue;
-		}
-		break;
-	}
-}
-
-static int mtk_stop(struct net_device *dev)
-{
-	struct mtk_mac *mac = netdev_priv(dev);
-	struct mtk_eth *eth = mac->hw;
-
-	netif_tx_disable(dev);
-	if (eth->phy)
-		eth->phy->stop(mac);
-
-	if (!atomic_dec_and_test(&eth->dma_refcnt))
-		return 0;
-
-	mtk_irq_disable(eth, eth->soc->tx_int | eth->soc->rx_int);
-	napi_disable(&eth->rx_napi);
-
-	if (eth->soc->dma_type & MTK_PDMA)
-		mtk_stop_dma(eth, mtk_reg_table[MTK_REG_PDMA_GLO_CFG]);
-
-	if (eth->soc->dma_type & MTK_QDMA)
-		mtk_stop_dma(eth, MTK_QDMA_GLO_CFG);
-
-	mtk_dma_free(eth);
-
-	return 0;
-}
-
-static int __init mtk_init_hw(struct mtk_eth *eth)
-{
-	int i, err;
-
-	eth->soc->reset_fe(eth);
-
-	if (eth->soc->switch_init)
-		if (eth->soc->switch_init(eth)) {
-			dev_err(eth->dev, "failed to initialize switch core\n");
-			return -ENODEV;
-		}
-
-	err = devm_request_irq(eth->dev, eth->irq, mtk_handle_irq, 0,
-			       dev_name(eth->dev), eth);
-	if (err)
-		return err;
-
-	err = mtk_mdio_init(eth);
-	if (err)
-		return err;
-
-	/* disable delay and normal interrupt */
-	mtk_reg_w32(eth, 0, MTK_REG_DLY_INT_CFG);
-	if (eth->soc->dma_type & MTK_QDMA)
-		mtk_w32(eth, 0, MTK_QDMA_DELAY_INT);
-	mtk_irq_disable(eth, eth->soc->tx_int | eth->soc->rx_int);
-
-	/* frame engine will push VLAN tag regarding to VIDX field in Tx desc */
-	if (mtk_reg_table[MTK_REG_MTK_DMA_VID_BASE])
-		for (i = 0; i < 16; i += 2)
-			mtk_w32(eth, ((i + 1) << 16) + i,
-				mtk_reg_table[MTK_REG_MTK_DMA_VID_BASE] +
-				(i * 2));
-
-	if (eth->soc->fwd_config(eth))
-		dev_err(eth->dev, "unable to get clock\n");
-
-	if (mtk_reg_table[MTK_REG_MTK_RST_GL]) {
-		mtk_reg_w32(eth, 1, MTK_REG_MTK_RST_GL);
-		mtk_reg_w32(eth, 0, MTK_REG_MTK_RST_GL);
-	}
-
-	return 0;
-}
-
-static int __init mtk_init(struct net_device *dev)
-{
-	struct mtk_mac *mac = netdev_priv(dev);
-	struct mtk_eth *eth = mac->hw;
-	struct device_node *port;
-	const char *mac_addr;
-	int err;
-
-	mac_addr = of_get_mac_address(mac->of_node);
-	if (mac_addr)
-		ether_addr_copy(dev->dev_addr, mac_addr);
-
-	/* If the mac address is invalid, use random mac address  */
-	if (!is_valid_ether_addr(dev->dev_addr)) {
-		eth_hw_addr_random(dev);
-		dev_err(eth->dev, "generated random MAC address %pM\n",
-			dev->dev_addr);
-	}
-	mac->hw->soc->set_mac(mac, dev->dev_addr);
-
-	if (eth->soc->port_init)
-		for_each_child_of_node(mac->of_node, port)
-			if (of_device_is_compatible(port,
-						    "mediatek,eth-port") &&
-			    of_device_is_available(port))
-				eth->soc->port_init(eth, mac, port);
-
-	if (eth->phy) {
-		err = eth->phy->connect(mac);
-		if (err)
-			return err;
-	}
-
-	return 0;
-}
-
-static void mtk_uninit(struct net_device *dev)
-{
-	struct mtk_mac *mac = netdev_priv(dev);
-	struct mtk_eth *eth = mac->hw;
-
-	if (eth->phy)
-		eth->phy->disconnect(mac);
-	mtk_mdio_cleanup(eth);
-
-	mtk_irq_disable(eth, ~0);
-	free_irq(dev->irq, dev);
-}
-
-static int mtk_do_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd)
-{
-	struct mtk_mac *mac = netdev_priv(dev);
-
-	if (!mac->phy_dev)
-		return -ENODEV;
-
-	switch (cmd) {
-	case SIOCGMIIPHY:
-	case SIOCGMIIREG:
-	case SIOCSMIIREG:
-		return phy_mii_ioctl(mac->phy_dev, ifr, cmd);
-	default:
-		break;
-	}
-
-	return -EOPNOTSUPP;
-}
-
-static int mtk_change_mtu(struct net_device *dev, int new_mtu)
-{
-	struct mtk_mac *mac = netdev_priv(dev);
-	struct mtk_eth *eth = mac->hw;
-	int frag_size, old_mtu;
-	u32 fwd_cfg;
-
-	if (!eth->soc->jumbo_frame)
-		return eth_change_mtu(dev, new_mtu);
-
-	frag_size = mtk_max_frag_size(new_mtu);
-	if (new_mtu < 68 || frag_size > PAGE_SIZE)
-		return -EINVAL;
-
-	old_mtu = dev->mtu;
-	dev->mtu = new_mtu;
-
-	/* return early if the buffer sizes will not change */
-	if (old_mtu <= ETH_DATA_LEN && new_mtu <= ETH_DATA_LEN)
-		return 0;
-	if (old_mtu > ETH_DATA_LEN && new_mtu > ETH_DATA_LEN)
-		return 0;
-
-	if (new_mtu <= ETH_DATA_LEN)
-		eth->rx_ring[0].frag_size = mtk_max_frag_size(ETH_DATA_LEN);
-	else
-		eth->rx_ring[0].frag_size = PAGE_SIZE;
-	eth->rx_ring[0].rx_buf_size =
-				mtk_max_buf_size(eth->rx_ring[0].frag_size);
-
-	if (!netif_running(dev))
-		return 0;
-
-	mtk_stop(dev);
-	fwd_cfg = mtk_r32(eth, MTK_GDMA1_FWD_CFG);
-	if (new_mtu <= ETH_DATA_LEN) {
-		fwd_cfg &= ~MTK_GDM1_JMB_EN;
-	} else {
-		fwd_cfg &= ~(MTK_GDM1_JMB_LEN_MASK << MTK_GDM1_JMB_LEN_SHIFT);
-		fwd_cfg |= (DIV_ROUND_UP(frag_size, 1024) <<
-				MTK_GDM1_JMB_LEN_SHIFT) | MTK_GDM1_JMB_EN;
-	}
-	mtk_w32(eth, fwd_cfg, MTK_GDMA1_FWD_CFG);
-
-	return mtk_open(dev);
-}
-
-static void mtk_pending_work(struct work_struct *work)
-{
-	struct mtk_mac *mac = container_of(work, struct mtk_mac, pending_work);
-	struct mtk_eth *eth = mac->hw;
-	struct net_device *dev = eth->netdev[mac->id];
-	int err;
-
-	rtnl_lock();
-	mtk_stop(dev);
-
-	err = mtk_open(dev);
-	if (err) {
-		netif_alert(eth, ifup, dev,
-			    "Driver up/down cycle failed, closing device.\n");
-		dev_close(dev);
-	}
-	rtnl_unlock();
-}
-
-static int mtk_cleanup(struct mtk_eth *eth)
-{
-	int i;
-
-	for (i = 0; i < eth->soc->mac_count; i++) {
-		struct mtk_mac *mac = netdev_priv(eth->netdev[i]);
-
-		if (!eth->netdev[i])
-			continue;
-
-		unregister_netdev(eth->netdev[i]);
-		free_netdev(eth->netdev[i]);
-		cancel_work_sync(&mac->pending_work);
-	}
-
-	return 0;
-}
-
-static const struct net_device_ops mtk_netdev_ops = {
-	.ndo_init		= mtk_init,
-	.ndo_uninit		= mtk_uninit,
-	.ndo_open		= mtk_open,
-	.ndo_stop		= mtk_stop,
-	.ndo_start_xmit		= mtk_start_xmit,
-	.ndo_set_mac_address	= mtk_set_mac_address,
-	.ndo_validate_addr	= eth_validate_addr,
-	.ndo_do_ioctl		= mtk_do_ioctl,
-	.ndo_change_mtu		= mtk_change_mtu,
-	.ndo_tx_timeout		= mtk_tx_timeout,
-	.ndo_get_stats64        = mtk_get_stats64,
-	.ndo_vlan_rx_add_vid	= mtk_vlan_rx_add_vid,
-	.ndo_vlan_rx_kill_vid	= mtk_vlan_rx_kill_vid,
-#ifdef CONFIG_NET_POLL_CONTROLLER
-	.ndo_poll_controller	= mtk_poll_controller,
-#endif
-};
-
-static int mtk_add_mac(struct mtk_eth *eth, struct device_node *np)
-{
-	struct mtk_mac *mac;
-	const __be32 *_id = of_get_property(np, "reg", NULL);
-	int id, err;
-
-	if (!_id) {
-		dev_err(eth->dev, "missing mac id\n");
-		return -EINVAL;
-	}
-	id = be32_to_cpup(_id);
-	if (id >= eth->soc->mac_count || eth->netdev[id]) {
-		dev_err(eth->dev, "%d is not a valid mac id\n", id);
-		return -EINVAL;
-	}
-
-	eth->netdev[id] = alloc_etherdev(sizeof(*mac));
-	if (!eth->netdev[id]) {
-		dev_err(eth->dev, "alloc_etherdev failed\n");
-		return -ENOMEM;
-	}
-	mac = netdev_priv(eth->netdev[id]);
-	eth->mac[id] = mac;
-	mac->id = id;
-	mac->hw = eth;
-	mac->of_node = np;
-	INIT_WORK(&mac->pending_work, mtk_pending_work);
-
-	if (mtk_reg_table[MTK_REG_MTK_COUNTER_BASE]) {
-		mac->hw_stats = devm_kzalloc(eth->dev,
-					     sizeof(*mac->hw_stats),
-					     GFP_KERNEL);
-		if (!mac->hw_stats) {
-			err = -ENOMEM;
-			goto free_netdev;
-		}
-		spin_lock_init(&mac->hw_stats->stats_lock);
-		mac->hw_stats->reg_offset = id * MTK_STAT_OFFSET;
-	}
-
-	SET_NETDEV_DEV(eth->netdev[id], eth->dev);
-	eth->netdev[id]->netdev_ops = &mtk_netdev_ops;
-	eth->netdev[id]->base_addr = (unsigned long)eth->base;
-
-	if (eth->soc->init_data)
-		eth->soc->init_data(eth->soc, eth->netdev[id]);
-
-	eth->netdev[id]->vlan_features = eth->soc->hw_features &
-		~(NETIF_F_HW_VLAN_CTAG_TX | NETIF_F_HW_VLAN_CTAG_RX);
-	eth->netdev[id]->features |= eth->soc->hw_features;
-
-	if (mtk_reg_table[MTK_REG_MTK_DMA_VID_BASE])
-		eth->netdev[id]->features |= NETIF_F_HW_VLAN_CTAG_FILTER;
-
-	mtk_set_ethtool_ops(eth->netdev[id]);
-
-	err = register_netdev(eth->netdev[id]);
-	if (err) {
-		dev_err(eth->dev, "error bringing up device\n");
-		err = -ENOMEM;
-		goto free_netdev;
-	}
-	eth->netdev[id]->irq = eth->irq;
-	netif_info(eth, probe, eth->netdev[id],
-		   "mediatek frame engine at 0x%08lx, irq %d\n",
-		   eth->netdev[id]->base_addr, eth->netdev[id]->irq);
-
-	return 0;
-
-free_netdev:
-	free_netdev(eth->netdev[id]);
-	return err;
-}
-
-static int mtk_probe(struct platform_device *pdev)
-{
-	struct resource *res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
-	const struct of_device_id *match;
-	struct device_node *mac_np;
-	struct mtk_soc_data *soc;
-	struct mtk_eth *eth;
-	struct clk *sysclk;
-	int err;
-
-	device_reset(&pdev->dev);
-
-	match = of_match_device(of_mtk_match, &pdev->dev);
-	soc = (struct mtk_soc_data *)match->data;
-
-	if (soc->reg_table)
-		mtk_reg_table = soc->reg_table;
-
-	eth = devm_kzalloc(&pdev->dev, sizeof(*eth), GFP_KERNEL);
-	if (!eth)
-		return -ENOMEM;
-
-	eth->base = devm_ioremap_resource(&pdev->dev, res);
-	if (IS_ERR(eth->base))
-		return PTR_ERR(eth->base);
-
-	spin_lock_init(&eth->page_lock);
-
-	eth->ethsys = syscon_regmap_lookup_by_phandle(pdev->dev.of_node,
-						      "mediatek,ethsys");
-	if (IS_ERR(eth->ethsys))
-		return PTR_ERR(eth->ethsys);
-
-	eth->irq = platform_get_irq(pdev, 0);
-	if (eth->irq < 0) {
-		dev_err(&pdev->dev, "no IRQ resource found\n");
-		return -ENXIO;
-	}
-
-	sysclk = devm_clk_get(&pdev->dev, NULL);
-	if (IS_ERR(sysclk)) {
-		dev_err(&pdev->dev,
-			"the clock is not defined in the devicetree\n");
-		return -ENXIO;
-	}
-	eth->sysclk = clk_get_rate(sysclk);
-
-	eth->switch_np = of_parse_phandle(pdev->dev.of_node,
-					  "mediatek,switch", 0);
-	if (soc->has_switch && !eth->switch_np) {
-		dev_err(&pdev->dev, "failed to read switch phandle\n");
-		return -ENODEV;
-	}
-
-	eth->dev = &pdev->dev;
-	eth->soc = soc;
-	eth->msg_enable = netif_msg_init(mtk_msg_level, MTK_DEFAULT_MSG_ENABLE);
-
-	err = mtk_init_hw(eth);
-	if (err)
-		return err;
-
-	if (eth->soc->mac_count > 1) {
-		for_each_child_of_node(pdev->dev.of_node, mac_np) {
-			if (!of_device_is_compatible(mac_np,
-						     "mediatek,eth-mac"))
-				continue;
-
-			if (!of_device_is_available(mac_np))
-				continue;
-
-			err = mtk_add_mac(eth, mac_np);
-			if (err)
-				goto err_free_dev;
-		}
-
-		init_dummy_netdev(&eth->dummy_dev);
-		netif_napi_add(&eth->dummy_dev, &eth->rx_napi, mtk_poll,
-			       soc->napi_weight);
-	} else {
-		err = mtk_add_mac(eth, pdev->dev.of_node);
-		if (err)
-			goto err_free_dev;
-		netif_napi_add(eth->netdev[0], &eth->rx_napi, mtk_poll,
-			       soc->napi_weight);
-	}
-
-	platform_set_drvdata(pdev, eth);
-
-	return 0;
-
-err_free_dev:
-	mtk_cleanup(eth);
-	return err;
-}
-
-static int mtk_remove(struct platform_device *pdev)
-{
-	struct mtk_eth *eth = platform_get_drvdata(pdev);
-
-	netif_napi_del(&eth->rx_napi);
-	mtk_cleanup(eth);
-	platform_set_drvdata(pdev, NULL);
-
-	return 0;
-}
-
-static struct platform_driver mtk_driver = {
-	.probe = mtk_probe,
-	.remove = mtk_remove,
-	.driver = {
-		.name = "mtk_soc_eth",
-		.of_match_table = of_mtk_match,
-	},
-};
-
-module_platform_driver(mtk_driver);
-
-MODULE_LICENSE("GPL");
-MODULE_AUTHOR("John Crispin <blogic@openwrt.org>");
-MODULE_DESCRIPTION("Ethernet driver for MediaTek SoC");
diff --git a/drivers/staging/mt7621-eth/mtk_eth_soc.h b/drivers/staging/mt7621-eth/mtk_eth_soc.h
deleted file mode 100644
index e6ed80433f49..000000000000
--- a/drivers/staging/mt7621-eth/mtk_eth_soc.h
+++ /dev/null
@@ -1,716 +0,0 @@
-/*   This program is free software; you can redistribute it and/or modify
- *   it under the terms of the GNU General Public License as published by
- *   the Free Software Foundation; version 2 of the License
- *
- *   This program is distributed in the hope that it will be useful,
- *   but WITHOUT ANY WARRANTY; without even the implied warranty of
- *   MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- *   GNU General Public License for more details.
- *
- *   Copyright (C) 2009-2016 John Crispin <blogic@openwrt.org>
- *   Copyright (C) 2009-2016 Felix Fietkau <nbd@openwrt.org>
- *   Copyright (C) 2013-2016 Michael Lee <igvtee@gmail.com>
- */
-
-#ifndef MTK_ETH_H
-#define MTK_ETH_H
-
-#include <linux/mii.h>
-#include <linux/interrupt.h>
-#include <linux/netdevice.h>
-#include <linux/dma-mapping.h>
-#include <linux/phy.h>
-#include <linux/ethtool.h>
-#include <linux/version.h>
-#include <linux/atomic.h>
-
-/* these registers have different offsets depending on the SoC. we use a lookup
- * table for these
- */
-enum mtk_reg {
-	MTK_REG_PDMA_GLO_CFG = 0,
-	MTK_REG_PDMA_RST_CFG,
-	MTK_REG_DLY_INT_CFG,
-	MTK_REG_TX_BASE_PTR0,
-	MTK_REG_TX_MAX_CNT0,
-	MTK_REG_TX_CTX_IDX0,
-	MTK_REG_TX_DTX_IDX0,
-	MTK_REG_RX_BASE_PTR0,
-	MTK_REG_RX_MAX_CNT0,
-	MTK_REG_RX_CALC_IDX0,
-	MTK_REG_RX_DRX_IDX0,
-	MTK_REG_MTK_INT_ENABLE,
-	MTK_REG_MTK_INT_STATUS,
-	MTK_REG_MTK_DMA_VID_BASE,
-	MTK_REG_MTK_COUNTER_BASE,
-	MTK_REG_MTK_RST_GL,
-	MTK_REG_MTK_INT_STATUS2,
-	MTK_REG_COUNT
-};
-
-/* delayed interrupt bits */
-#define MTK_DELAY_EN_INT	0x80
-#define MTK_DELAY_MAX_INT	0x04
-#define MTK_DELAY_MAX_TOUT	0x04
-#define MTK_DELAY_TIME		20
-#define MTK_DELAY_CHAN		(((MTK_DELAY_EN_INT | MTK_DELAY_MAX_INT) << 8) \
-				 | MTK_DELAY_MAX_TOUT)
-#define MTK_DELAY_INIT		((MTK_DELAY_CHAN << 16) | MTK_DELAY_CHAN)
-#define MTK_PSE_FQFC_CFG_INIT	0x80504000
-#define MTK_PSE_FQFC_CFG_256Q	0xff908000
-
-/* interrupt bits */
-#define MTK_CNT_PPE_AF		BIT(31)
-#define MTK_CNT_GDM_AF		BIT(29)
-#define MTK_PSE_P2_FC		BIT(26)
-#define MTK_PSE_BUF_DROP	BIT(24)
-#define MTK_GDM_OTHER_DROP	BIT(23)
-#define MTK_PSE_P1_FC		BIT(22)
-#define MTK_PSE_P0_FC		BIT(21)
-#define MTK_PSE_FQ_EMPTY	BIT(20)
-#define MTK_GE1_STA_CHG		BIT(18)
-#define MTK_TX_COHERENT		BIT(17)
-#define MTK_RX_COHERENT		BIT(16)
-#define MTK_TX_DONE_INT3	BIT(11)
-#define MTK_TX_DONE_INT2	BIT(10)
-#define MTK_TX_DONE_INT1	BIT(9)
-#define MTK_TX_DONE_INT0	BIT(8)
-#define MTK_RX_DONE_INT0	BIT(2)
-#define MTK_TX_DLY_INT		BIT(1)
-#define MTK_RX_DLY_INT		BIT(0)
-
-#define MTK_RX_DONE_INT		MTK_RX_DONE_INT0
-#define MTK_TX_DONE_INT		(MTK_TX_DONE_INT0 | MTK_TX_DONE_INT1 | \
-				 MTK_TX_DONE_INT2 | MTK_TX_DONE_INT3)
-
-#define RT5350_RX_DLY_INT	BIT(30)
-#define RT5350_TX_DLY_INT	BIT(28)
-#define RT5350_RX_DONE_INT1	BIT(17)
-#define RT5350_RX_DONE_INT0	BIT(16)
-#define RT5350_TX_DONE_INT3	BIT(3)
-#define RT5350_TX_DONE_INT2	BIT(2)
-#define RT5350_TX_DONE_INT1	BIT(1)
-#define RT5350_TX_DONE_INT0	BIT(0)
-
-#define RT5350_RX_DONE_INT	(RT5350_RX_DONE_INT0 | RT5350_RX_DONE_INT1)
-#define RT5350_TX_DONE_INT	(RT5350_TX_DONE_INT0 | RT5350_TX_DONE_INT1 | \
-				 RT5350_TX_DONE_INT2 | RT5350_TX_DONE_INT3)
-
-/* registers */
-#define MTK_GDMA_OFFSET		0x0020
-#define MTK_PSE_OFFSET		0x0040
-#define MTK_GDMA2_OFFSET	0x0060
-#define MTK_CDMA_OFFSET		0x0080
-#define MTK_DMA_VID0		0x00a8
-#define MTK_PDMA_OFFSET		0x0100
-#define MTK_PPE_OFFSET		0x0200
-#define MTK_CMTABLE_OFFSET	0x0400
-#define MTK_POLICYTABLE_OFFSET	0x1000
-
-#define MT7621_GDMA_OFFSET	0x0500
-#define MT7620_GDMA_OFFSET	0x0600
-
-#define RT5350_PDMA_OFFSET	0x0800
-#define RT5350_SDM_OFFSET	0x0c00
-
-#define MTK_MDIO_ACCESS		0x00
-#define MTK_MDIO_CFG		0x04
-#define MTK_GLO_CFG		0x08
-#define MTK_RST_GL		0x0C
-#define MTK_INT_STATUS		0x10
-#define MTK_INT_ENABLE		0x14
-#define MTK_MDIO_CFG2		0x18
-#define MTK_FOC_TS_T		0x1C
-
-#define	MTK_GDMA1_FWD_CFG	(MTK_GDMA_OFFSET + 0x00)
-#define MTK_GDMA1_SCH_CFG	(MTK_GDMA_OFFSET + 0x04)
-#define MTK_GDMA1_SHPR_CFG	(MTK_GDMA_OFFSET + 0x08)
-#define MTK_GDMA1_MAC_ADRL	(MTK_GDMA_OFFSET + 0x0C)
-#define MTK_GDMA1_MAC_ADRH	(MTK_GDMA_OFFSET + 0x10)
-
-#define	MTK_GDMA2_FWD_CFG	(MTK_GDMA2_OFFSET + 0x00)
-#define MTK_GDMA2_SCH_CFG	(MTK_GDMA2_OFFSET + 0x04)
-#define MTK_GDMA2_SHPR_CFG	(MTK_GDMA2_OFFSET + 0x08)
-#define MTK_GDMA2_MAC_ADRL	(MTK_GDMA2_OFFSET + 0x0C)
-#define MTK_GDMA2_MAC_ADRH	(MTK_GDMA2_OFFSET + 0x10)
-
-#define MTK_PSE_FQ_CFG		(MTK_PSE_OFFSET + 0x00)
-#define MTK_CDMA_FC_CFG		(MTK_PSE_OFFSET + 0x04)
-#define MTK_GDMA1_FC_CFG	(MTK_PSE_OFFSET + 0x08)
-#define MTK_GDMA2_FC_CFG	(MTK_PSE_OFFSET + 0x0C)
-
-#define MTK_CDMA_CSG_CFG	(MTK_CDMA_OFFSET + 0x00)
-#define MTK_CDMA_SCH_CFG	(MTK_CDMA_OFFSET + 0x04)
-
-#define	MT7621_GDMA_FWD_CFG(x)	(MT7621_GDMA_OFFSET + (x * 0x1000))
-
-/* FIXME this might be different for different SOCs */
-#define	MT7620_GDMA1_FWD_CFG	(MT7621_GDMA_OFFSET + 0x00)
-
-#define RT5350_TX_BASE_PTR0	(RT5350_PDMA_OFFSET + 0x00)
-#define RT5350_TX_MAX_CNT0	(RT5350_PDMA_OFFSET + 0x04)
-#define RT5350_TX_CTX_IDX0	(RT5350_PDMA_OFFSET + 0x08)
-#define RT5350_TX_DTX_IDX0	(RT5350_PDMA_OFFSET + 0x0C)
-#define RT5350_TX_BASE_PTR1	(RT5350_PDMA_OFFSET + 0x10)
-#define RT5350_TX_MAX_CNT1	(RT5350_PDMA_OFFSET + 0x14)
-#define RT5350_TX_CTX_IDX1	(RT5350_PDMA_OFFSET + 0x18)
-#define RT5350_TX_DTX_IDX1	(RT5350_PDMA_OFFSET + 0x1C)
-#define RT5350_TX_BASE_PTR2	(RT5350_PDMA_OFFSET + 0x20)
-#define RT5350_TX_MAX_CNT2	(RT5350_PDMA_OFFSET + 0x24)
-#define RT5350_TX_CTX_IDX2	(RT5350_PDMA_OFFSET + 0x28)
-#define RT5350_TX_DTX_IDX2	(RT5350_PDMA_OFFSET + 0x2C)
-#define RT5350_TX_BASE_PTR3	(RT5350_PDMA_OFFSET + 0x30)
-#define RT5350_TX_MAX_CNT3	(RT5350_PDMA_OFFSET + 0x34)
-#define RT5350_TX_CTX_IDX3	(RT5350_PDMA_OFFSET + 0x38)
-#define RT5350_TX_DTX_IDX3	(RT5350_PDMA_OFFSET + 0x3C)
-#define RT5350_RX_BASE_PTR0	(RT5350_PDMA_OFFSET + 0x100)
-#define RT5350_RX_MAX_CNT0	(RT5350_PDMA_OFFSET + 0x104)
-#define RT5350_RX_CALC_IDX0	(RT5350_PDMA_OFFSET + 0x108)
-#define RT5350_RX_DRX_IDX0	(RT5350_PDMA_OFFSET + 0x10C)
-#define RT5350_RX_BASE_PTR1	(RT5350_PDMA_OFFSET + 0x110)
-#define RT5350_RX_MAX_CNT1	(RT5350_PDMA_OFFSET + 0x114)
-#define RT5350_RX_CALC_IDX1	(RT5350_PDMA_OFFSET + 0x118)
-#define RT5350_RX_DRX_IDX1	(RT5350_PDMA_OFFSET + 0x11C)
-#define RT5350_PDMA_GLO_CFG	(RT5350_PDMA_OFFSET + 0x204)
-#define RT5350_PDMA_RST_CFG	(RT5350_PDMA_OFFSET + 0x208)
-#define RT5350_DLY_INT_CFG	(RT5350_PDMA_OFFSET + 0x20c)
-#define RT5350_MTK_INT_STATUS	(RT5350_PDMA_OFFSET + 0x220)
-#define RT5350_MTK_INT_ENABLE	(RT5350_PDMA_OFFSET + 0x228)
-#define RT5350_PDMA_SCH_CFG	(RT5350_PDMA_OFFSET + 0x280)
-
-#define MTK_PDMA_GLO_CFG	(MTK_PDMA_OFFSET + 0x00)
-#define MTK_PDMA_RST_CFG	(MTK_PDMA_OFFSET + 0x04)
-#define MTK_PDMA_SCH_CFG	(MTK_PDMA_OFFSET + 0x08)
-#define MTK_DLY_INT_CFG		(MTK_PDMA_OFFSET + 0x0C)
-#define MTK_TX_BASE_PTR0	(MTK_PDMA_OFFSET + 0x10)
-#define MTK_TX_MAX_CNT0		(MTK_PDMA_OFFSET + 0x14)
-#define MTK_TX_CTX_IDX0		(MTK_PDMA_OFFSET + 0x18)
-#define MTK_TX_DTX_IDX0		(MTK_PDMA_OFFSET + 0x1C)
-#define MTK_TX_BASE_PTR1	(MTK_PDMA_OFFSET + 0x20)
-#define MTK_TX_MAX_CNT1		(MTK_PDMA_OFFSET + 0x24)
-#define MTK_TX_CTX_IDX1		(MTK_PDMA_OFFSET + 0x28)
-#define MTK_TX_DTX_IDX1		(MTK_PDMA_OFFSET + 0x2C)
-#define MTK_RX_BASE_PTR0	(MTK_PDMA_OFFSET + 0x30)
-#define MTK_RX_MAX_CNT0		(MTK_PDMA_OFFSET + 0x34)
-#define MTK_RX_CALC_IDX0	(MTK_PDMA_OFFSET + 0x38)
-#define MTK_RX_DRX_IDX0		(MTK_PDMA_OFFSET + 0x3C)
-#define MTK_TX_BASE_PTR2	(MTK_PDMA_OFFSET + 0x40)
-#define MTK_TX_MAX_CNT2		(MTK_PDMA_OFFSET + 0x44)
-#define MTK_TX_CTX_IDX2		(MTK_PDMA_OFFSET + 0x48)
-#define MTK_TX_DTX_IDX2		(MTK_PDMA_OFFSET + 0x4C)
-#define MTK_TX_BASE_PTR3	(MTK_PDMA_OFFSET + 0x50)
-#define MTK_TX_MAX_CNT3		(MTK_PDMA_OFFSET + 0x54)
-#define MTK_TX_CTX_IDX3		(MTK_PDMA_OFFSET + 0x58)
-#define MTK_TX_DTX_IDX3		(MTK_PDMA_OFFSET + 0x5C)
-#define MTK_RX_BASE_PTR1	(MTK_PDMA_OFFSET + 0x60)
-#define MTK_RX_MAX_CNT1		(MTK_PDMA_OFFSET + 0x64)
-#define MTK_RX_CALC_IDX1	(MTK_PDMA_OFFSET + 0x68)
-#define MTK_RX_DRX_IDX1		(MTK_PDMA_OFFSET + 0x6C)
-
-/* Switch DMA configuration */
-#define RT5350_SDM_CFG		(RT5350_SDM_OFFSET + 0x00)
-#define RT5350_SDM_RRING	(RT5350_SDM_OFFSET + 0x04)
-#define RT5350_SDM_TRING	(RT5350_SDM_OFFSET + 0x08)
-#define RT5350_SDM_MAC_ADRL	(RT5350_SDM_OFFSET + 0x0C)
-#define RT5350_SDM_MAC_ADRH	(RT5350_SDM_OFFSET + 0x10)
-#define RT5350_SDM_TPCNT	(RT5350_SDM_OFFSET + 0x100)
-#define RT5350_SDM_TBCNT	(RT5350_SDM_OFFSET + 0x104)
-#define RT5350_SDM_RPCNT	(RT5350_SDM_OFFSET + 0x108)
-#define RT5350_SDM_RBCNT	(RT5350_SDM_OFFSET + 0x10C)
-#define RT5350_SDM_CS_ERR	(RT5350_SDM_OFFSET + 0x110)
-
-#define RT5350_SDM_ICS_EN	BIT(16)
-#define RT5350_SDM_TCS_EN	BIT(17)
-#define RT5350_SDM_UCS_EN	BIT(18)
-
-/* QDMA registers */
-#define MTK_QTX_CFG(x)		(0x1800 + (x * 0x10))
-#define MTK_QTX_SCH(x)		(0x1804 + (x * 0x10))
-#define MTK_QRX_BASE_PTR0	0x1900
-#define MTK_QRX_MAX_CNT0	0x1904
-#define MTK_QRX_CRX_IDX0	0x1908
-#define MTK_QRX_DRX_IDX0	0x190C
-#define MTK_QDMA_GLO_CFG	0x1A04
-#define MTK_QDMA_RST_IDX	0x1A08
-#define MTK_QDMA_DELAY_INT	0x1A0C
-#define MTK_QDMA_FC_THRES	0x1A10
-#define MTK_QMTK_INT_STATUS	0x1A18
-#define MTK_QMTK_INT_ENABLE	0x1A1C
-#define MTK_QDMA_HRED2		0x1A44
-
-#define MTK_QTX_CTX_PTR		0x1B00
-#define MTK_QTX_DTX_PTR		0x1B04
-
-#define MTK_QTX_CRX_PTR		0x1B10
-#define MTK_QTX_DRX_PTR		0x1B14
-
-#define MTK_QDMA_FQ_HEAD	0x1B20
-#define MTK_QDMA_FQ_TAIL	0x1B24
-#define MTK_QDMA_FQ_CNT		0x1B28
-#define MTK_QDMA_FQ_BLEN	0x1B2C
-
-#define QDMA_PAGE_SIZE		2048
-#define QDMA_TX_OWNER_CPU	BIT(31)
-#define QDMA_TX_SWC		BIT(14)
-#define TX_QDMA_SDL(_x)		(((_x) & 0x3fff) << 16)
-#define QDMA_RES_THRES		4
-
-/* MDIO_CFG register bits */
-#define MTK_MDIO_CFG_AUTO_POLL_EN	BIT(29)
-#define MTK_MDIO_CFG_GP1_BP_EN		BIT(16)
-#define MTK_MDIO_CFG_GP1_FRC_EN		BIT(15)
-#define MTK_MDIO_CFG_GP1_SPEED_10	(0 << 13)
-#define MTK_MDIO_CFG_GP1_SPEED_100	(1 << 13)
-#define MTK_MDIO_CFG_GP1_SPEED_1000	(2 << 13)
-#define MTK_MDIO_CFG_GP1_DUPLEX		BIT(12)
-#define MTK_MDIO_CFG_GP1_FC_TX		BIT(11)
-#define MTK_MDIO_CFG_GP1_FC_RX		BIT(10)
-#define MTK_MDIO_CFG_GP1_LNK_DWN	BIT(9)
-#define MTK_MDIO_CFG_GP1_AN_FAIL	BIT(8)
-#define MTK_MDIO_CFG_MDC_CLK_DIV_1	(0 << 6)
-#define MTK_MDIO_CFG_MDC_CLK_DIV_2	(1 << 6)
-#define MTK_MDIO_CFG_MDC_CLK_DIV_4	(2 << 6)
-#define MTK_MDIO_CFG_MDC_CLK_DIV_8	(3 << 6)
-#define MTK_MDIO_CFG_TURBO_MII_FREQ	BIT(5)
-#define MTK_MDIO_CFG_TURBO_MII_MODE	BIT(4)
-#define MTK_MDIO_CFG_RX_CLK_SKEW_0	(0 << 2)
-#define MTK_MDIO_CFG_RX_CLK_SKEW_200	(1 << 2)
-#define MTK_MDIO_CFG_RX_CLK_SKEW_400	(2 << 2)
-#define MTK_MDIO_CFG_RX_CLK_SKEW_INV	(3 << 2)
-#define MTK_MDIO_CFG_TX_CLK_SKEW_0	0
-#define MTK_MDIO_CFG_TX_CLK_SKEW_200	1
-#define MTK_MDIO_CFG_TX_CLK_SKEW_400	2
-#define MTK_MDIO_CFG_TX_CLK_SKEW_INV	3
-
-/* uni-cast port */
-#define MTK_GDM1_JMB_LEN_MASK	0xf
-#define MTK_GDM1_JMB_LEN_SHIFT	28
-#define MTK_GDM1_ICS_EN		BIT(22)
-#define MTK_GDM1_TCS_EN		BIT(21)
-#define MTK_GDM1_UCS_EN		BIT(20)
-#define MTK_GDM1_JMB_EN		BIT(19)
-#define MTK_GDM1_STRPCRC	BIT(16)
-#define MTK_GDM1_UFRC_P_CPU	(0 << 12)
-#define MTK_GDM1_UFRC_P_GDMA1	(1 << 12)
-#define MTK_GDM1_UFRC_P_PPE	(6 << 12)
-
-/* checksums */
-#define MTK_ICS_GEN_EN		BIT(2)
-#define MTK_UCS_GEN_EN		BIT(1)
-#define MTK_TCS_GEN_EN		BIT(0)
-
-/* dma mode */
-#define MTK_PDMA		BIT(0)
-#define MTK_QDMA		BIT(1)
-#define MTK_PDMA_RX_QDMA_TX	(MTK_PDMA | MTK_QDMA)
-
-/* dma ring */
-#define MTK_PST_DRX_IDX0	BIT(16)
-#define MTK_PST_DTX_IDX3	BIT(3)
-#define MTK_PST_DTX_IDX2	BIT(2)
-#define MTK_PST_DTX_IDX1	BIT(1)
-#define MTK_PST_DTX_IDX0	BIT(0)
-
-#define MTK_RX_2B_OFFSET	BIT(31)
-#define MTK_TX_WB_DDONE		BIT(6)
-#define MTK_RX_DMA_BUSY		BIT(3)
-#define MTK_TX_DMA_BUSY		BIT(1)
-#define MTK_RX_DMA_EN		BIT(2)
-#define MTK_TX_DMA_EN		BIT(0)
-
-#define MTK_PDMA_SIZE_4DWORDS	(0 << 4)
-#define MTK_PDMA_SIZE_8DWORDS	(1 << 4)
-#define MTK_PDMA_SIZE_16DWORDS	(2 << 4)
-
-#define MTK_US_CYC_CNT_MASK	0xff
-#define MTK_US_CYC_CNT_SHIFT	0x8
-#define MTK_US_CYC_CNT_DIVISOR	1000000
-
-/* PDMA descriptor rxd2 */
-#define RX_DMA_DONE		BIT(31)
-#define RX_DMA_LSO		BIT(30)
-#define RX_DMA_PLEN0(_x)	(((_x) & 0x3fff) << 16)
-#define RX_DMA_GET_PLEN0(_x)	(((_x) >> 16) & 0x3fff)
-#define RX_DMA_TAG		BIT(15)
-
-/* PDMA descriptor rxd3 */
-#define RX_DMA_TPID(_x)		(((_x) >> 16) & 0xffff)
-#define RX_DMA_VID(_x)		((_x) & 0xfff)
-
-/* PDMA descriptor rxd4 */
-#define RX_DMA_L4VALID		BIT(30)
-#define RX_DMA_FPORT_SHIFT	19
-#define RX_DMA_FPORT_MASK	0x7
-
-struct mtk_rx_dma {
-	unsigned int rxd1;
-	unsigned int rxd2;
-	unsigned int rxd3;
-	unsigned int rxd4;
-} __packed __aligned(4);
-
-/* PDMA tx descriptor bits */
-#define TX_DMA_BUF_LEN		0x3fff
-#define TX_DMA_PLEN0_MASK	(TX_DMA_BUF_LEN << 16)
-#define TX_DMA_PLEN0(_x)	(((_x) & TX_DMA_BUF_LEN) << 16)
-#define TX_DMA_PLEN1(_x)	((_x) & TX_DMA_BUF_LEN)
-#define TX_DMA_GET_PLEN0(_x)    (((_x) >> 16) & TX_DMA_BUF_LEN)
-#define TX_DMA_GET_PLEN1(_x)    ((_x) & TX_DMA_BUF_LEN)
-#define TX_DMA_LS1		BIT(14)
-#define TX_DMA_LS0		BIT(30)
-#define TX_DMA_DONE		BIT(31)
-#define TX_DMA_FPORT_SHIFT	25
-#define TX_DMA_FPORT_MASK	0x7
-#define TX_DMA_INS_VLAN_MT7621	BIT(16)
-#define TX_DMA_INS_VLAN		BIT(7)
-#define TX_DMA_INS_PPPOE	BIT(12)
-#define TX_DMA_TAG		BIT(15)
-#define TX_DMA_TAG_MASK		BIT(15)
-#define TX_DMA_QN(_x)		((_x) << 16)
-#define TX_DMA_PN(_x)		((_x) << 24)
-#define TX_DMA_QN_MASK		TX_DMA_QN(0x7)
-#define TX_DMA_PN_MASK		TX_DMA_PN(0x7)
-#define TX_DMA_UDF		BIT(20)
-#define TX_DMA_CHKSUM		(0x7 << 29)
-#define TX_DMA_TSO		BIT(28)
-#define TX_DMA_DESP4_DEF	(TX_DMA_QN(3) | TX_DMA_PN(1))
-
-/* frame engine counters */
-#define MTK_PPE_AC_BCNT0	(MTK_CMTABLE_OFFSET + 0x00)
-#define MTK_GDMA1_TX_GBCNT	(MTK_CMTABLE_OFFSET + 0x300)
-#define MTK_GDMA2_TX_GBCNT	(MTK_GDMA1_TX_GBCNT + 0x40)
-
-/* phy device flags */
-#define MTK_PHY_FLAG_PORT	BIT(0)
-#define MTK_PHY_FLAG_ATTACH	BIT(1)
-
-struct mtk_tx_dma {
-	unsigned int txd1;
-	unsigned int txd2;
-	unsigned int txd3;
-	unsigned int txd4;
-} __packed __aligned(4);
-
-struct mtk_eth;
-struct mtk_mac;
-
-/* manage the attached phys */
-struct mtk_phy {
-	spinlock_t		lock;
-
-	struct phy_device	*phy[8];
-	struct device_node	*phy_node[8];
-	const __be32		*phy_fixed[8];
-	int			duplex[8];
-	int			speed[8];
-	int			tx_fc[8];
-	int			rx_fc[8];
-	int (*connect)(struct mtk_mac *mac);
-	void (*disconnect)(struct mtk_mac *mac);
-	void (*start)(struct mtk_mac *mac);
-	void (*stop)(struct mtk_mac *mac);
-};
-
-/* struct mtk_soc_data - the structure that holds the SoC specific data
- * @reg_table:		Some of the legacy registers changed their location
- *			over time. Their offsets are stored in this table
- *
- * @init_data:		Some features depend on the silicon revision. This
- *			callback allows runtime modification of the content of
- *			this struct
- * @reset_fe:		This callback is used to trigger the reset of the frame
- *			engine
- * @set_mac:		This callback is used to set the unicast mac address
- *			filter
- * @fwd_config:		This callback is used to setup the forward config
- *			register of the MAC
- * @switch_init:	This callback is used to bring up the switch core
- * @port_init:		Some SoCs have ports that can be router to a switch port
- *			or an external PHY. This callback is used to setup these
- *			ports.
- * @has_carrier:	This callback allows driver to check if there is a cable
- *			attached.
- * @mdio_init:		This callbck is used to setup the MDIO bus if one is
- *			present
- * @mdio_cleanup:	This callback is used to cleanup the MDIO state.
- * @mdio_write:		This callback is used to write data to the MDIO bus.
- * @mdio_read:		This callback is used to write data to the MDIO bus.
- * @mdio_adjust_link:	This callback is used to apply the PHY settings.
- * @piac_offset:	the PIAC register has a different different base offset
- * @hw_features:	feature set depends on the SoC type
- * @dma_ring_size:	allow GBit SoCs to set bigger rings than FE SoCs
- * @napi_weight:	allow GBit SoCs to set bigger napi weight than FE SoCs
- * @dma_type:		SoCs is PDMA, QDMA or a mix of the 2
- * @pdma_glo_cfg:	the default DMA configuration
- * @rx_int:		the TX interrupt bits used by the SoC
- * @tx_int:		the TX interrupt bits used by the SoC
- * @status_int:		the Status interrupt bits used by the SoC
- * @checksum_bit:	the bits used to turn on HW checksumming
- * @txd4:		default value of the TXD4 descriptor
- * @mac_count:		the number of MACs that the SoC has
- * @new_stats:		there is a old and new way to read hardware stats
- *			registers
- * @jumbo_frame:	does the SoC support jumbo frames ?
- * @rx_2b_offset:	tell the rx dma to offset the data by 2 bytes
- * @rx_sg_dma:		scatter gather support
- * @padding_64b		enable 64 bit padding
- * @padding_bug:	rt2880 has a padding bug
- * @has_switch:		does the SoC have a built-in switch
- *
- * Although all of the supported SoCs share the same basic functionality, there
- * are several SoC specific functions and features that we need to support. This
- * struct holds the SoC specific data so that the common core can figure out
- * how to setup and use these differences.
- */
-struct mtk_soc_data {
-	const u16 *reg_table;
-
-	void (*init_data)(struct mtk_soc_data *data, struct net_device *netdev);
-	void (*reset_fe)(struct mtk_eth *eth);
-	void (*set_mac)(struct mtk_mac *mac, unsigned char *macaddr);
-	int (*fwd_config)(struct mtk_eth *eth);
-	int (*switch_init)(struct mtk_eth *eth);
-	void (*port_init)(struct mtk_eth *eth, struct mtk_mac *mac,
-			  struct device_node *port);
-	int (*has_carrier)(struct mtk_eth *eth);
-	int (*mdio_init)(struct mtk_eth *eth);
-	void (*mdio_cleanup)(struct mtk_eth *eth);
-	int (*mdio_write)(struct mii_bus *bus, int phy_addr, int phy_reg,
-			  u16 val);
-	int (*mdio_read)(struct mii_bus *bus, int phy_addr, int phy_reg);
-	void (*mdio_adjust_link)(struct mtk_eth *eth, int port);
-	u32 piac_offset;
-	netdev_features_t hw_features;
-	u32 dma_ring_size;
-	u32 napi_weight;
-	u32 dma_type;
-	u32 pdma_glo_cfg;
-	u32 rx_int;
-	u32 tx_int;
-	u32 status_int;
-	u32 checksum_bit;
-	u32 txd4;
-	u32 mac_count;
-
-	u32 new_stats:1;
-	u32 jumbo_frame:1;
-	u32 rx_2b_offset:1;
-	u32 rx_sg_dma:1;
-	u32 padding_64b:1;
-	u32 padding_bug:1;
-	u32 has_switch:1;
-};
-
-#define MTK_STAT_OFFSET			0x40
-
-/* struct mtk_hw_stats - the structure that holds the traffic statistics.
- * @stats_lock:		make sure that stats operations are atomic
- * @reg_offset:		the status register offset of the SoC
- * @syncp:		the refcount
- *
- * All of the supported SoCs have hardware counters for traffic statstics.
- * Whenever the status IRQ triggers we can read the latest stats from these
- * counters and store them in this struct.
- */
-struct mtk_hw_stats {
-	spinlock_t stats_lock;
-	u32 reg_offset;
-	struct u64_stats_sync syncp;
-
-	u64 tx_bytes;
-	u64 tx_packets;
-	u64 tx_skip;
-	u64 tx_collisions;
-	u64 rx_bytes;
-	u64 rx_packets;
-	u64 rx_overflow;
-	u64 rx_fcs_errors;
-	u64 rx_short_errors;
-	u64 rx_long_errors;
-	u64 rx_checksum_errors;
-	u64 rx_flow_control_packets;
-};
-
-/* PDMA descriptor can point at 1-2 segments. This enum allows us to track how
- * memory was allocated so that it can be freed properly
- */
-enum mtk_tx_flags {
-	MTK_TX_FLAGS_SINGLE0	= 0x01,
-	MTK_TX_FLAGS_PAGE0	= 0x02,
-	MTK_TX_FLAGS_PAGE1	= 0x04,
-};
-
-/* struct mtk_tx_buf -	This struct holds the pointers to the memory pointed at
- *			by the TX descriptor	s
- * @skb:		The SKB pointer of the packet being sent
- * @dma_addr0:		The base addr of the first segment
- * @dma_len0:		The length of the first segment
- * @dma_addr1:		The base addr of the second segment
- * @dma_len1:		The length of the second segment
- */
-struct mtk_tx_buf {
-	struct sk_buff *skb;
-	u32 flags;
-	DEFINE_DMA_UNMAP_ADDR(dma_addr0);
-	DEFINE_DMA_UNMAP_LEN(dma_len0);
-	DEFINE_DMA_UNMAP_ADDR(dma_addr1);
-	DEFINE_DMA_UNMAP_LEN(dma_len1);
-};
-
-/* struct mtk_tx_ring -	This struct holds info describing a TX ring
- * @tx_dma:		The descriptor ring
- * @tx_buf:		The memory pointed at by the ring
- * @tx_phys:		The physical addr of tx_buf
- * @tx_next_free:	Pointer to the next free descriptor
- * @tx_last_free:	Pointer to the last free descriptor
- * @tx_thresh:		The threshold of minimum amount of free descriptors
- * @tx_map:		Callback to map a new packet into the ring
- * @tx_poll:		Callback for the housekeeping function
- * @tx_clean:		Callback for the cleanup function
- * @tx_ring_size:	How many descriptors are in the ring
- * @tx_free_idx:	The index of th next free descriptor
- * @tx_next_idx:	QDMA uses a linked list. This element points to the next
- *			free descriptor in the list
- * @tx_free_count:	QDMA uses a linked list. Track how many free descriptors
- *			are present
- */
-struct mtk_tx_ring {
-	struct mtk_tx_dma *tx_dma;
-	struct mtk_tx_buf *tx_buf;
-	dma_addr_t tx_phys;
-	struct mtk_tx_dma *tx_next_free;
-	struct mtk_tx_dma *tx_last_free;
-	u16 tx_thresh;
-	int (*tx_map)(struct sk_buff *skb, struct net_device *dev, int tx_num,
-		      struct mtk_tx_ring *ring, bool gso);
-	int (*tx_poll)(struct mtk_eth *eth, int budget, bool *tx_again);
-	void (*tx_clean)(struct mtk_eth *eth);
-
-	/* PDMA only */
-	u16 tx_ring_size;
-	u16 tx_free_idx;
-
-	/* QDMA only */
-	u16 tx_next_idx;
-	atomic_t tx_free_count;
-};
-
-/* struct mtk_rx_ring -	This struct holds info describing a RX ring
- * @rx_dma:		The descriptor ring
- * @rx_data:		The memory pointed at by the ring
- * @trx_phys:		The physical addr of rx_buf
- * @rx_ring_size:	How many descriptors are in the ring
- * @rx_buf_size:	The size of each packet buffer
- * @rx_calc_idx:	The current head of ring
- */
-struct mtk_rx_ring {
-	struct mtk_rx_dma *rx_dma;
-	u8 **rx_data;
-	dma_addr_t rx_phys;
-	u16 rx_ring_size;
-	u16 frag_size;
-	u16 rx_buf_size;
-	u16 rx_calc_idx;
-};
-
-/* currently no SoC has more than 2 macs */
-#define MTK_MAX_DEVS			2
-
-/* struct mtk_eth -	This is the main datasructure for holding the state
- *			of the driver
- * @dev:		The device pointer
- * @base:		The mapped register i/o base
- * @page_lock:		Make sure that register operations are atomic
- * @soc:		pointer to our SoC specific data
- * @dummy_dev:		we run 2 netdevs on 1 physical DMA ring and need a
- *			dummy for NAPI to work
- * @netdev:		The netdev instances
- * @mac:		Each netdev is linked to a physical MAC
- * @switch_np:		The phandle for the switch
- * @irq:		The IRQ that we are using
- * @msg_enable:		Ethtool msg level
- * @ysclk:		The sysclk rate - neeed for calibration
- * @ethsys:		The register map pointing at the range used to setup
- *			MII modes
- * @dma_refcnt:		track how many netdevs are using the DMA engine
- * @tx_ring:		Pointer to the memore holding info about the TX ring
- * @rx_ring:		Pointer to the memore holding info about the RX ring
- * @rx_napi:		The NAPI struct
- * @scratch_ring:	Newer SoCs need memory for a second HW managed TX ring
- * @scratch_head:	The scratch memory that scratch_ring points to.
- * @phy:		Info about the attached PHYs
- * @mii_bus:		If there is a bus we need to create an instance for it
- * @link:		Track if the ports have a physical link
- * @sw_priv:		Pointer to the switches private data
- * @vlan_map:		RX VID tracking
- */
-
-struct mtk_eth {
-	struct device			*dev;
-	void __iomem			*base;
-	spinlock_t			page_lock;
-	struct mtk_soc_data		*soc;
-	struct net_device		dummy_dev;
-	struct net_device		*netdev[MTK_MAX_DEVS];
-	struct mtk_mac			*mac[MTK_MAX_DEVS];
-	struct device_node		*switch_np;
-	int				irq;
-	u32				msg_enable;
-	unsigned long			sysclk;
-	struct regmap			*ethsys;
-	atomic_t			dma_refcnt;
-	struct mtk_tx_ring		tx_ring;
-	struct mtk_rx_ring		rx_ring[2];
-	struct napi_struct		rx_napi;
-	struct mtk_tx_dma		*scratch_ring;
-	void				*scratch_head;
-	struct mtk_phy			*phy;
-	struct mii_bus			*mii_bus;
-	int				link[8];
-	void				*sw_priv;
-	unsigned long			vlan_map;
-};
-
-/* struct mtk_mac -	the structure that holds the info about the MACs of the
- *			SoC
- * @id:			The number of the MAC
- * @of_node:		Our devicetree node
- * @hw:			Backpointer to our main datastruture
- * @hw_stats:		Packet statistics counter
- * @phy_dev:		The attached PHY if available
- * @phy_flags:		The PHYs flags
- * @pending_work:	The workqueue used to reset the dma ring
- */
-struct mtk_mac {
-	int				id;
-	struct device_node		*of_node;
-	struct mtk_eth			*hw;
-	struct mtk_hw_stats		*hw_stats;
-	struct phy_device		*phy_dev;
-	u32				phy_flags;
-	struct work_struct		pending_work;
-};
-
-/* the struct describing the SoC. these are declared in the soc_xyz.c files */
-extern const struct of_device_id of_mtk_match[];
-
-/* read the hardware status register */
-void mtk_stats_update_mac(struct mtk_mac *mac);
-
-/* default checksum setup handler */
-void mtk_reset(struct mtk_eth *eth, u32 reset_bits);
-
-/* register i/o wrappers */
-void mtk_w32(struct mtk_eth *eth, u32 val, unsigned int reg);
-u32 mtk_r32(struct mtk_eth *eth, unsigned int reg);
-
-/* default clock calibration handler */
-int mtk_set_clock_cycle(struct mtk_eth *eth);
-
-/* default checksum setup handler */
-void mtk_csum_config(struct mtk_eth *eth);
-
-/* default forward config handler */
-void mtk_fwd_config(struct mtk_eth *eth);
-
-#endif /* MTK_ETH_H */
diff --git a/drivers/staging/mt7621-eth/soc_mt7621.c b/drivers/staging/mt7621-eth/soc_mt7621.c
deleted file mode 100644
index 5d63b5d96f6b..000000000000
--- a/drivers/staging/mt7621-eth/soc_mt7621.c
+++ /dev/null
@@ -1,161 +0,0 @@
-/*   This program is free software; you can redistribute it and/or modify
- *   it under the terms of the GNU General Public License as published by
- *   the Free Software Foundation; version 2 of the License
- *
- *   This program is distributed in the hope that it will be useful,
- *   but WITHOUT ANY WARRANTY; without even the implied warranty of
- *   MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- *   GNU General Public License for more details.
- *
- *   Copyright (C) 2009-2016 John Crispin <blogic@openwrt.org>
- *   Copyright (C) 2009-2016 Felix Fietkau <nbd@openwrt.org>
- *   Copyright (C) 2013-2016 Michael Lee <igvtee@gmail.com>
- */
-
-#include <linux/module.h>
-#include <linux/platform_device.h>
-#include <linux/if_vlan.h>
-#include <linux/of_net.h>
-
-#include <asm/mach-ralink/ralink_regs.h>
-
-#include "mtk_eth_soc.h"
-#include "gsw_mt7620.h"
-#include "mdio.h"
-
-#define MT7620_CDMA_CSG_CFG	0x400
-#define MT7621_CDMP_IG_CTRL	(MT7620_CDMA_CSG_CFG + 0x00)
-#define MT7621_CDMP_EG_CTRL	(MT7620_CDMA_CSG_CFG + 0x04)
-#define MT7621_RESET_FE		BIT(6)
-#define MT7621_L4_VALID		BIT(24)
-
-#define MT7621_TX_DMA_UDF	BIT(19)
-
-#define CDMA_ICS_EN		BIT(2)
-#define CDMA_UCS_EN		BIT(1)
-#define CDMA_TCS_EN		BIT(0)
-
-#define GDMA_ICS_EN		BIT(22)
-#define GDMA_TCS_EN		BIT(21)
-#define GDMA_UCS_EN		BIT(20)
-
-/* frame engine counters */
-#define MT7621_REG_MIB_OFFSET	0x2000
-#define MT7621_PPE_AC_BCNT0	(MT7621_REG_MIB_OFFSET + 0x00)
-#define MT7621_GDM1_TX_GBCNT	(MT7621_REG_MIB_OFFSET + 0x400)
-#define MT7621_GDM2_TX_GBCNT	(MT7621_GDM1_TX_GBCNT + 0x40)
-
-#define GSW_REG_GDMA1_MAC_ADRL	0x508
-#define GSW_REG_GDMA1_MAC_ADRH	0x50C
-#define GSW_REG_GDMA2_MAC_ADRL	0x1508
-#define GSW_REG_GDMA2_MAC_ADRH	0x150C
-
-#define MT7621_MTK_RST_GL	0x04
-#define MT7620_MTK_INT_STATUS2	0x08
-
-/* MTK_INT_STATUS reg on mt7620 define CNT_GDM1_AF at BIT(29)
- * but after test it should be BIT(13).
- */
-#define MT7621_MTK_GDM1_AF	BIT(28)
-#define MT7621_MTK_GDM2_AF	BIT(29)
-
-static const u16 mt7621_reg_table[MTK_REG_COUNT] = {
-	[MTK_REG_PDMA_GLO_CFG] = RT5350_PDMA_GLO_CFG,
-	[MTK_REG_PDMA_RST_CFG] = RT5350_PDMA_RST_CFG,
-	[MTK_REG_DLY_INT_CFG] = RT5350_DLY_INT_CFG,
-	[MTK_REG_TX_BASE_PTR0] = RT5350_TX_BASE_PTR0,
-	[MTK_REG_TX_MAX_CNT0] = RT5350_TX_MAX_CNT0,
-	[MTK_REG_TX_CTX_IDX0] = RT5350_TX_CTX_IDX0,
-	[MTK_REG_TX_DTX_IDX0] = RT5350_TX_DTX_IDX0,
-	[MTK_REG_RX_BASE_PTR0] = RT5350_RX_BASE_PTR0,
-	[MTK_REG_RX_MAX_CNT0] = RT5350_RX_MAX_CNT0,
-	[MTK_REG_RX_CALC_IDX0] = RT5350_RX_CALC_IDX0,
-	[MTK_REG_RX_DRX_IDX0] = RT5350_RX_DRX_IDX0,
-	[MTK_REG_MTK_INT_ENABLE] = RT5350_MTK_INT_ENABLE,
-	[MTK_REG_MTK_INT_STATUS] = RT5350_MTK_INT_STATUS,
-	[MTK_REG_MTK_DMA_VID_BASE] = 0,
-	[MTK_REG_MTK_COUNTER_BASE] = MT7621_GDM1_TX_GBCNT,
-	[MTK_REG_MTK_RST_GL] = MT7621_MTK_RST_GL,
-	[MTK_REG_MTK_INT_STATUS2] = MT7620_MTK_INT_STATUS2,
-};
-
-static void mt7621_mtk_reset(struct mtk_eth *eth)
-{
-	mtk_reset(eth, MT7621_RESET_FE);
-}
-
-static int mt7621_fwd_config(struct mtk_eth *eth)
-{
-	/* Setup GMAC1 only, there is no support for GMAC2 yet */
-	mtk_w32(eth, mtk_r32(eth, MT7620_GDMA1_FWD_CFG) & ~0xffff,
-		MT7620_GDMA1_FWD_CFG);
-
-	/* Enable RX checksum */
-	mtk_w32(eth, mtk_r32(eth, MT7620_GDMA1_FWD_CFG) | (GDMA_ICS_EN |
-		       GDMA_TCS_EN | GDMA_UCS_EN),
-		       MT7620_GDMA1_FWD_CFG);
-
-	/* Enable RX VLan Offloading */
-	mtk_w32(eth, 0, MT7621_CDMP_EG_CTRL);
-
-	return 0;
-}
-
-static void mt7621_set_mac(struct mtk_mac *mac, unsigned char *hwaddr)
-{
-	unsigned long flags;
-
-	spin_lock_irqsave(&mac->hw->page_lock, flags);
-	if (mac->id == 0) {
-		mtk_w32(mac->hw, (hwaddr[0] << 8) | hwaddr[1],
-			GSW_REG_GDMA1_MAC_ADRH);
-		mtk_w32(mac->hw, (hwaddr[2] << 24) | (hwaddr[3] << 16) |
-			(hwaddr[4] << 8) | hwaddr[5],
-			GSW_REG_GDMA1_MAC_ADRL);
-	}
-	if (mac->id == 1) {
-		mtk_w32(mac->hw, (hwaddr[0] << 8) | hwaddr[1],
-			GSW_REG_GDMA2_MAC_ADRH);
-		mtk_w32(mac->hw, (hwaddr[2] << 24) | (hwaddr[3] << 16) |
-			(hwaddr[4] << 8) | hwaddr[5],
-			GSW_REG_GDMA2_MAC_ADRL);
-	}
-	spin_unlock_irqrestore(&mac->hw->page_lock, flags);
-}
-
-static struct mtk_soc_data mt7621_data = {
-	.hw_features = NETIF_F_IP_CSUM | NETIF_F_RXCSUM |
-		       NETIF_F_HW_VLAN_CTAG_TX | NETIF_F_HW_VLAN_CTAG_RX |
-		       NETIF_F_SG | NETIF_F_TSO | NETIF_F_TSO6 |
-		       NETIF_F_IPV6_CSUM,
-	.dma_type = MTK_PDMA,
-	.dma_ring_size = 256,
-	.napi_weight = 64,
-	.new_stats = 1,
-	.padding_64b = 1,
-	.rx_2b_offset = 1,
-	.rx_sg_dma = 1,
-	.has_switch = 1,
-	.mac_count = 2,
-	.reset_fe = mt7621_mtk_reset,
-	.set_mac = mt7621_set_mac,
-	.fwd_config = mt7621_fwd_config,
-	.switch_init = mtk_gsw_init,
-	.reg_table = mt7621_reg_table,
-	.pdma_glo_cfg = MTK_PDMA_SIZE_16DWORDS,
-	.rx_int = RT5350_RX_DONE_INT,
-	.tx_int = RT5350_TX_DONE_INT,
-	.status_int = MT7621_MTK_GDM1_AF | MT7621_MTK_GDM2_AF,
-	.checksum_bit = MT7621_L4_VALID,
-	.has_carrier = mt7620_has_carrier,
-	.mdio_read = mt7620_mdio_read,
-	.mdio_write = mt7620_mdio_write,
-	.mdio_adjust_link = mt7620_mdio_link_adjust,
-};
-
-const struct of_device_id of_mtk_match[] = {
-	{ .compatible = "mediatek,mt7621-eth", .data = &mt7621_data },
-	{},
-};
-
-MODULE_DEVICE_TABLE(of, of_mtk_match);
diff --git a/drivers/staging/mt7621-pci/Kconfig b/drivers/staging/mt7621-pci/Kconfig
index d33533872a16..c8fa17cfa807 100644
--- a/drivers/staging/mt7621-pci/Kconfig
+++ b/drivers/staging/mt7621-pci/Kconfig
@@ -1,6 +1,7 @@
 config PCI_MT7621
 	tristate "MediaTek MT7621 PCI Controller"
 	depends on RALINK
+	depends on PCI
 	select PCI_DRIVERS_GENERIC
 	help
 	  This selects a driver for the MediaTek MT7621 PCI Controller.
diff --git a/drivers/staging/mt7621-spi/Kconfig b/drivers/staging/mt7621-spi/Kconfig
deleted file mode 100644
index 0b90f4cfa426..000000000000
--- a/drivers/staging/mt7621-spi/Kconfig
+++ /dev/null
@@ -1,6 +0,0 @@
-config SPI_MT7621
-	tristate "MediaTek MT7621 SPI Controller"
-	depends on RALINK
-	help
-	  This selects a driver for the MediaTek MT7621 SPI Controller.
-
diff --git a/drivers/staging/mt7621-spi/Makefile b/drivers/staging/mt7621-spi/Makefile
deleted file mode 100644
index 3be508f63bac..000000000000
--- a/drivers/staging/mt7621-spi/Makefile
+++ /dev/null
@@ -1 +0,0 @@
-obj-$(CONFIG_SPI_MT7621)		+= spi-mt7621.o
diff --git a/drivers/staging/mt7621-spi/TODO b/drivers/staging/mt7621-spi/TODO
deleted file mode 100644
index fdbc5002c32a..000000000000
--- a/drivers/staging/mt7621-spi/TODO
+++ /dev/null
@@ -1,5 +0,0 @@
-
-- general code review and clean up
-- ensure device-tree requirements are documented
-
-Cc: NeilBrown <neil@brown.name>
diff --git a/drivers/staging/octeon/ethernet-mdio.c b/drivers/staging/octeon/ethernet-mdio.c
index d6248eecf123..2aee64fdaec5 100644
--- a/drivers/staging/octeon/ethernet-mdio.c
+++ b/drivers/staging/octeon/ethernet-mdio.c
@@ -163,7 +163,7 @@ int cvm_oct_phy_setup_device(struct net_device *dev)
 		goto no_phy;
 
 	phydev = of_phy_connect(dev, phy_node, cvm_oct_adjust_link, 0,
-				PHY_INTERFACE_MODE_GMII);
+				priv->phy_mode);
 	of_node_put(phy_node);
 
 	if (!phydev)
diff --git a/drivers/staging/octeon/ethernet.c b/drivers/staging/octeon/ethernet.c
index ce61c5670ef6..986db76705cc 100644
--- a/drivers/staging/octeon/ethernet.c
+++ b/drivers/staging/octeon/ethernet.c
@@ -653,14 +653,37 @@ static struct device_node *cvm_oct_node_for_port(struct device_node *pip,
 	return np;
 }
 
-static void cvm_set_rgmii_delay(struct device_node *np, int iface, int port)
+static void cvm_set_rgmii_delay(struct octeon_ethernet *priv, int iface,
+				int port)
 {
+	struct device_node *np = priv->of_node;
 	u32 delay_value;
+	bool rx_delay;
+	bool tx_delay;
 
-	if (!of_property_read_u32(np, "rx-delay", &delay_value))
+	/* By default, both RX/TX delay is enabled in
+	 * __cvmx_helper_rgmii_enable().
+	 */
+	rx_delay = true;
+	tx_delay = true;
+
+	if (!of_property_read_u32(np, "rx-delay", &delay_value)) {
 		cvmx_write_csr(CVMX_ASXX_RX_CLK_SETX(port, iface), delay_value);
-	if (!of_property_read_u32(np, "tx-delay", &delay_value))
+		rx_delay = delay_value > 0;
+	}
+	if (!of_property_read_u32(np, "tx-delay", &delay_value)) {
 		cvmx_write_csr(CVMX_ASXX_TX_CLK_SETX(port, iface), delay_value);
+		tx_delay = delay_value > 0;
+	}
+
+	if (!rx_delay && !tx_delay)
+		priv->phy_mode = PHY_INTERFACE_MODE_RGMII_ID;
+	else if (!rx_delay)
+		priv->phy_mode = PHY_INTERFACE_MODE_RGMII_RXID;
+	else if (!tx_delay)
+		priv->phy_mode = PHY_INTERFACE_MODE_RGMII_TXID;
+	else
+		priv->phy_mode = PHY_INTERFACE_MODE_RGMII;
 }
 
 static int cvm_oct_probe(struct platform_device *pdev)
@@ -825,6 +848,7 @@ static int cvm_oct_probe(struct platform_device *pdev)
 			priv->port = port;
 			priv->queue = cvmx_pko_get_base_queue(priv->port);
 			priv->fau = fau - cvmx_pko_get_num_queues(port) * 4;
+			priv->phy_mode = PHY_INTERFACE_MODE_NA;
 			for (qos = 0; qos < 16; qos++)
 				skb_queue_head_init(&priv->tx_free_list[qos]);
 			for (qos = 0; qos < cvmx_pko_get_num_queues(port);
@@ -856,6 +880,7 @@ static int cvm_oct_probe(struct platform_device *pdev)
 				break;
 
 			case CVMX_HELPER_INTERFACE_MODE_SGMII:
+				priv->phy_mode = PHY_INTERFACE_MODE_SGMII;
 				dev->netdev_ops = &cvm_oct_sgmii_netdev_ops;
 				strcpy(dev->name, "eth%d");
 				break;
@@ -865,11 +890,16 @@ static int cvm_oct_probe(struct platform_device *pdev)
 				strcpy(dev->name, "spi%d");
 				break;
 
-			case CVMX_HELPER_INTERFACE_MODE_RGMII:
 			case CVMX_HELPER_INTERFACE_MODE_GMII:
+				priv->phy_mode = PHY_INTERFACE_MODE_GMII;
+				dev->netdev_ops = &cvm_oct_rgmii_netdev_ops;
+				strcpy(dev->name, "eth%d");
+				break;
+
+			case CVMX_HELPER_INTERFACE_MODE_RGMII:
 				dev->netdev_ops = &cvm_oct_rgmii_netdev_ops;
 				strcpy(dev->name, "eth%d");
-				cvm_set_rgmii_delay(priv->of_node, interface,
+				cvm_set_rgmii_delay(priv, interface,
 						    port_index);
 				break;
 			}
diff --git a/drivers/staging/octeon/octeon-ethernet.h b/drivers/staging/octeon/octeon-ethernet.h
index 4a07e7f43d12..be570d33685a 100644
--- a/drivers/staging/octeon/octeon-ethernet.h
+++ b/drivers/staging/octeon/octeon-ethernet.h
@@ -12,7 +12,7 @@
 #define OCTEON_ETHERNET_H
 
 #include <linux/of.h>
-
+#include <linux/phy.h>
 #include <asm/octeon/cvmx-helper-board.h>
 
 /**
@@ -33,6 +33,8 @@ struct octeon_ethernet {
 	 * cvmx_helper_interface_mode_t
 	 */
 	int imode;
+	/* PHY mode */
+	phy_interface_t phy_mode;
 	/* List of outstanding tx buffers per queue */
 	struct sk_buff_head tx_free_list[16];
 	unsigned int last_speed;
diff --git a/drivers/staging/olpc_dcon/olpc_dcon_xo_1.c b/drivers/staging/olpc_dcon/olpc_dcon_xo_1.c
index 80b8d4153414..a54286498a47 100644
--- a/drivers/staging/olpc_dcon/olpc_dcon_xo_1.c
+++ b/drivers/staging/olpc_dcon/olpc_dcon_xo_1.c
@@ -45,7 +45,7 @@ static int dcon_init_xo_1(struct dcon_priv *dcon)
 {
 	unsigned char lob;
 	int ret, i;
-	struct dcon_gpio *pin = &gpios_asis[0];
+	const struct dcon_gpio *pin = &gpios_asis[0];
 
 	for (i = 0; i < ARRAY_SIZE(gpios_asis); i++) {
 		gpios[i] = devm_gpiod_get(&dcon->client->dev, pin[i].name,
diff --git a/drivers/staging/rtl8188eu/core/rtw_xmit.c b/drivers/staging/rtl8188eu/core/rtw_xmit.c
index 1723a47a96b4..952f2ab51347 100644
--- a/drivers/staging/rtl8188eu/core/rtw_xmit.c
+++ b/drivers/staging/rtl8188eu/core/rtw_xmit.c
@@ -174,7 +174,9 @@ s32 _rtw_init_xmit_priv(struct xmit_priv *pxmitpriv, struct adapter *padapter)
 
 	pxmitpriv->free_xmit_extbuf_cnt = num_xmit_extbuf;
 
-	rtw_alloc_hwxmits(padapter);
+	res = rtw_alloc_hwxmits(padapter);
+	if (res == _FAIL)
+		goto exit;
 	rtw_init_hwxmits(pxmitpriv->hwxmits, pxmitpriv->hwxmit_entry);
 
 	for (i = 0; i < 4; i++)
@@ -1503,7 +1505,7 @@ exit:
 	return res;
 }
 
-void rtw_alloc_hwxmits(struct adapter *padapter)
+s32 rtw_alloc_hwxmits(struct adapter *padapter)
 {
 	struct hw_xmit *hwxmits;
 	struct xmit_priv *pxmitpriv = &padapter->xmitpriv;
@@ -1512,6 +1514,8 @@ void rtw_alloc_hwxmits(struct adapter *padapter)
 
 	pxmitpriv->hwxmits = kcalloc(pxmitpriv->hwxmit_entry,
 				     sizeof(struct hw_xmit), GFP_KERNEL);
+	if (!pxmitpriv->hwxmits)
+		return _FAIL;
 
 	hwxmits = pxmitpriv->hwxmits;
 
@@ -1519,6 +1523,7 @@ void rtw_alloc_hwxmits(struct adapter *padapter)
 	hwxmits[1] .sta_queue = &pxmitpriv->vi_pending;
 	hwxmits[2] .sta_queue = &pxmitpriv->be_pending;
 	hwxmits[3] .sta_queue = &pxmitpriv->bk_pending;
+	return _SUCCESS;
 }
 
 void rtw_free_hwxmits(struct adapter *padapter)
diff --git a/drivers/staging/rtl8188eu/include/rtw_xmit.h b/drivers/staging/rtl8188eu/include/rtw_xmit.h
index 788f59c74ea1..ba7e15fbde72 100644
--- a/drivers/staging/rtl8188eu/include/rtw_xmit.h
+++ b/drivers/staging/rtl8188eu/include/rtw_xmit.h
@@ -336,7 +336,7 @@ s32 rtw_txframes_sta_ac_pending(struct adapter *padapter,
 void rtw_init_hwxmits(struct hw_xmit *phwxmit, int entry);
 s32 _rtw_init_xmit_priv(struct xmit_priv *pxmitpriv, struct adapter *padapter);
 void _rtw_free_xmit_priv(struct xmit_priv *pxmitpriv);
-void rtw_alloc_hwxmits(struct adapter *padapter);
+s32 rtw_alloc_hwxmits(struct adapter *padapter);
 void rtw_free_hwxmits(struct adapter *padapter);
 s32 rtw_xmit(struct adapter *padapter, struct sk_buff **pkt);
 
diff --git a/drivers/staging/rtl8192e/rtllib_crypt_tkip.c b/drivers/staging/rtl8192e/rtllib_crypt_tkip.c
index 55da8c9dfe50..a084e1501f9d 100644
--- a/drivers/staging/rtl8192e/rtllib_crypt_tkip.c
+++ b/drivers/staging/rtl8192e/rtllib_crypt_tkip.c
@@ -507,7 +507,6 @@ static int michael_mic(struct crypto_shash *tfm_michael, u8 *key, u8 *hdr,
 	int err;
 
 	desc->tfm = tfm_michael;
-	desc->flags = 0;
 
 	if (crypto_shash_setkey(tfm_michael, key, 8))
 		return -1;
diff --git a/drivers/staging/rtl8192u/ieee80211/ieee80211_crypt_tkip.c b/drivers/staging/rtl8192u/ieee80211/ieee80211_crypt_tkip.c
index 829fa4bd253c..d67bb57994c4 100644
--- a/drivers/staging/rtl8192u/ieee80211/ieee80211_crypt_tkip.c
+++ b/drivers/staging/rtl8192u/ieee80211/ieee80211_crypt_tkip.c
@@ -503,7 +503,6 @@ static int michael_mic(struct crypto_shash *tfm_michael, u8 *key, u8 *hdr,
 	int err;
 
 	desc->tfm = tfm_michael;
-	desc->flags = 0;
 
 	if (crypto_shash_setkey(tfm_michael, key, 8))
 		return -1;
diff --git a/drivers/staging/rtl8712/rtl8712_cmd.c b/drivers/staging/rtl8712/rtl8712_cmd.c
index 1920d02f7c9f..8c36acedf507 100644
--- a/drivers/staging/rtl8712/rtl8712_cmd.c
+++ b/drivers/staging/rtl8712/rtl8712_cmd.c
@@ -147,17 +147,9 @@ static u8 write_macreg_hdl(struct _adapter *padapter, u8 *pbuf)
 
 static u8 read_bbreg_hdl(struct _adapter *padapter, u8 *pbuf)
 {
-	u32 val;
-	void (*pcmd_callback)(struct _adapter *dev, struct cmd_obj	*pcmd);
 	struct cmd_obj *pcmd  = (struct cmd_obj *)pbuf;
 
-	if (pcmd->rsp && pcmd->rspsz > 0)
-		memcpy(pcmd->rsp, (u8 *)&val, pcmd->rspsz);
-	pcmd_callback = cmd_callback[pcmd->cmdcode].callback;
-	if (!pcmd_callback)
-		r8712_free_cmd_obj(pcmd);
-	else
-		pcmd_callback(padapter, pcmd);
+	r8712_free_cmd_obj(pcmd);
 	return H2C_SUCCESS;
 }
 
diff --git a/drivers/staging/rtl8712/rtl8712_cmd.h b/drivers/staging/rtl8712/rtl8712_cmd.h
index 92fb77666d44..1ef86b8c592f 100644
--- a/drivers/staging/rtl8712/rtl8712_cmd.h
+++ b/drivers/staging/rtl8712/rtl8712_cmd.h
@@ -140,7 +140,7 @@ enum rtl8712_h2c_cmd {
 static struct _cmd_callback	cmd_callback[] = {
 	{GEN_CMD_CODE(_Read_MACREG), NULL}, /*0*/
 	{GEN_CMD_CODE(_Write_MACREG), NULL},
-	{GEN_CMD_CODE(_Read_BBREG), &r8712_getbbrfreg_cmdrsp_callback},
+	{GEN_CMD_CODE(_Read_BBREG), NULL},
 	{GEN_CMD_CODE(_Write_BBREG), NULL},
 	{GEN_CMD_CODE(_Read_RFREG), &r8712_getbbrfreg_cmdrsp_callback},
 	{GEN_CMD_CODE(_Write_RFREG), NULL}, /*5*/
diff --git a/drivers/staging/rtl8723bs/core/rtw_xmit.c b/drivers/staging/rtl8723bs/core/rtw_xmit.c
index 094d61bcb469..b87f13a0b563 100644
--- a/drivers/staging/rtl8723bs/core/rtw_xmit.c
+++ b/drivers/staging/rtl8723bs/core/rtw_xmit.c
@@ -260,7 +260,9 @@ s32 _rtw_init_xmit_priv(struct xmit_priv *pxmitpriv, struct adapter *padapter)
 		}
 	}
 
-	rtw_alloc_hwxmits(padapter);
+	res = rtw_alloc_hwxmits(padapter);
+	if (res == _FAIL)
+		goto exit;
 	rtw_init_hwxmits(pxmitpriv->hwxmits, pxmitpriv->hwxmit_entry);
 
 	for (i = 0; i < 4; i++) {
@@ -2144,7 +2146,7 @@ exit:
 	return res;
 }
 
-void rtw_alloc_hwxmits(struct adapter *padapter)
+s32 rtw_alloc_hwxmits(struct adapter *padapter)
 {
 	struct hw_xmit *hwxmits;
 	struct xmit_priv *pxmitpriv = &padapter->xmitpriv;
@@ -2155,10 +2157,8 @@ void rtw_alloc_hwxmits(struct adapter *padapter)
 
 	pxmitpriv->hwxmits = rtw_zmalloc(sizeof(struct hw_xmit) * pxmitpriv->hwxmit_entry);
 
-	if (pxmitpriv->hwxmits == NULL) {
-		DBG_871X("alloc hwxmits fail!...\n");
-		return;
-	}
+	if (!pxmitpriv->hwxmits)
+		return _FAIL;
 
 	hwxmits = pxmitpriv->hwxmits;
 
@@ -2204,7 +2204,7 @@ void rtw_alloc_hwxmits(struct adapter *padapter)
 
 	}
 
-
+	return _SUCCESS;
 }
 
 void rtw_free_hwxmits(struct adapter *padapter)
diff --git a/drivers/staging/rtl8723bs/include/rtw_xmit.h b/drivers/staging/rtl8723bs/include/rtw_xmit.h
index 1b38b9182b31..37f42b2f22f1 100644
--- a/drivers/staging/rtl8723bs/include/rtw_xmit.h
+++ b/drivers/staging/rtl8723bs/include/rtw_xmit.h
@@ -487,7 +487,7 @@ s32 _rtw_init_xmit_priv(struct xmit_priv *pxmitpriv, struct adapter *padapter);
 void _rtw_free_xmit_priv (struct xmit_priv *pxmitpriv);
 
 
-void rtw_alloc_hwxmits(struct adapter *padapter);
+s32 rtw_alloc_hwxmits(struct adapter *padapter);
 void rtw_free_hwxmits(struct adapter *padapter);
 
 
diff --git a/drivers/staging/rtlwifi/phydm/rtl_phydm.c b/drivers/staging/rtlwifi/phydm/rtl_phydm.c
index 9930ed954abb..4cc77b2016e1 100644
--- a/drivers/staging/rtlwifi/phydm/rtl_phydm.c
+++ b/drivers/staging/rtlwifi/phydm/rtl_phydm.c
@@ -180,6 +180,8 @@ static int rtl_phydm_init_priv(struct rtl_priv *rtlpriv,
 
 	rtlpriv->phydm.internal =
 		kzalloc(sizeof(struct phy_dm_struct), GFP_KERNEL);
+	if (!rtlpriv->phydm.internal)
+		return 0;
 
 	_rtl_phydm_init_com_info(rtlpriv, ic, params);
 
diff --git a/drivers/staging/rtlwifi/rtl8822be/fw.c b/drivers/staging/rtlwifi/rtl8822be/fw.c
index f061dd1382aa..cf6b7a80b753 100644
--- a/drivers/staging/rtlwifi/rtl8822be/fw.c
+++ b/drivers/staging/rtlwifi/rtl8822be/fw.c
@@ -743,6 +743,8 @@ void rtl8822be_set_fw_rsvdpagepkt(struct ieee80211_hw *hw, bool b_dl_finished)
 		      u1_rsvd_page_loc, 3);
 
 	skb = dev_alloc_skb(totalpacketlen);
+	if (!skb)
+		return;
 	memcpy((u8 *)skb_put(skb, totalpacketlen), &reserved_page_packet,
 	       totalpacketlen);
 
diff --git a/drivers/staging/speakup/speakup_soft.c b/drivers/staging/speakup/speakup_soft.c
index edff6ce85655..9d85a3a1af4c 100644
--- a/drivers/staging/speakup/speakup_soft.c
+++ b/drivers/staging/speakup/speakup_soft.c
@@ -210,12 +210,15 @@ static ssize_t softsynthx_read(struct file *fp, char __user *buf, size_t count,
 		return -EINVAL;
 
 	spin_lock_irqsave(&speakup_info.spinlock, flags);
+	synth_soft.alive = 1;
 	while (1) {
 		prepare_to_wait(&speakup_event, &wait, TASK_INTERRUPTIBLE);
-		if (!unicode)
-			synth_buffer_skip_nonlatin1();
-		if (!synth_buffer_empty() || speakup_info.flushing)
-			break;
+		if (synth_current() == &synth_soft) {
+			if (!unicode)
+				synth_buffer_skip_nonlatin1();
+			if (!synth_buffer_empty() || speakup_info.flushing)
+				break;
+		}
 		spin_unlock_irqrestore(&speakup_info.spinlock, flags);
 		if (fp->f_flags & O_NONBLOCK) {
 			finish_wait(&speakup_event, &wait);
@@ -235,6 +238,8 @@ static ssize_t softsynthx_read(struct file *fp, char __user *buf, size_t count,
 
 	/* Keep 3 bytes available for a 16bit UTF-8-encoded character */
 	while (chars_sent <= count - bytes_per_ch) {
+		if (synth_current() != &synth_soft)
+			break;
 		if (speakup_info.flushing) {
 			speakup_info.flushing = 0;
 			ch = '\x18';
@@ -331,7 +336,8 @@ static __poll_t softsynth_poll(struct file *fp, struct poll_table_struct *wait)
 	poll_wait(fp, &speakup_event, wait);
 
 	spin_lock_irqsave(&speakup_info.spinlock, flags);
-	if (!synth_buffer_empty() || speakup_info.flushing)
+	if (synth_current() == &synth_soft &&
+	    (!synth_buffer_empty() || speakup_info.flushing))
 		ret = EPOLLIN | EPOLLRDNORM;
 	spin_unlock_irqrestore(&speakup_info.spinlock, flags);
 	return ret;
diff --git a/drivers/staging/speakup/spk_priv.h b/drivers/staging/speakup/spk_priv.h
index c8e688878fc7..ac6a74883af4 100644
--- a/drivers/staging/speakup/spk_priv.h
+++ b/drivers/staging/speakup/spk_priv.h
@@ -74,6 +74,7 @@ int synth_request_region(unsigned long start, unsigned long n);
 int synth_release_region(unsigned long start, unsigned long n);
 int synth_add(struct spk_synth *in_synth);
 void synth_remove(struct spk_synth *in_synth);
+struct spk_synth *synth_current(void);
 
 extern struct speakup_info_t speakup_info;
 
diff --git a/drivers/staging/speakup/synth.c b/drivers/staging/speakup/synth.c
index 25f259ee4ffc..3568bfb89912 100644
--- a/drivers/staging/speakup/synth.c
+++ b/drivers/staging/speakup/synth.c
@@ -481,4 +481,10 @@ void synth_remove(struct spk_synth *in_synth)
 }
 EXPORT_SYMBOL_GPL(synth_remove);
 
+struct spk_synth *synth_current(void)
+{
+	return synth;
+}
+EXPORT_SYMBOL_GPL(synth_current);
+
 short spk_punc_masks[] = { 0, SOME, MOST, PUNC, PUNC | B_SYM };
diff --git a/drivers/staging/vc04_services/interface/vchiq_arm/vchiq_arm.c b/drivers/staging/vc04_services/interface/vchiq_arm/vchiq_arm.c
index 804daf83be35..064d0db4c51e 100644
--- a/drivers/staging/vc04_services/interface/vchiq_arm/vchiq_arm.c
+++ b/drivers/staging/vc04_services/interface/vchiq_arm/vchiq_arm.c
@@ -3513,6 +3513,7 @@ static int vchiq_probe(struct platform_device *pdev)
 	struct device_node *fw_node;
 	const struct of_device_id *of_id;
 	struct vchiq_drvdata *drvdata;
+	struct device *vchiq_dev;
 	int err;
 
 	of_id = of_match_node(vchiq_of_match, pdev->dev.of_node);
@@ -3547,9 +3548,12 @@ static int vchiq_probe(struct platform_device *pdev)
 		goto failed_platform_init;
 	}
 
-	if (IS_ERR(device_create(vchiq_class, &pdev->dev, vchiq_devid,
-				 NULL, "vchiq")))
+	vchiq_dev = device_create(vchiq_class, &pdev->dev, vchiq_devid, NULL,
+				  "vchiq");
+	if (IS_ERR(vchiq_dev)) {
+		err = PTR_ERR(vchiq_dev);
 		goto failed_device_create;
+	}
 
 	vchiq_debugfs_init();
 
diff --git a/drivers/staging/vt6655/device_main.c b/drivers/staging/vt6655/device_main.c
index b370985b58a1..c6bb4aaf9bd0 100644
--- a/drivers/staging/vt6655/device_main.c
+++ b/drivers/staging/vt6655/device_main.c
@@ -1033,8 +1033,6 @@ static void vnt_interrupt_process(struct vnt_private *priv)
 		return;
 	}
 
-	MACvIntDisable(priv->PortOffset);
-
 	spin_lock_irqsave(&priv->lock, flags);
 
 	/* Read low level stats */
@@ -1122,8 +1120,6 @@ static void vnt_interrupt_process(struct vnt_private *priv)
 	}
 
 	spin_unlock_irqrestore(&priv->lock, flags);
-
-	MACvIntEnable(priv->PortOffset, IMR_MASK_VALUE);
 }
 
 static void vnt_interrupt_work(struct work_struct *work)
@@ -1133,14 +1129,17 @@ static void vnt_interrupt_work(struct work_struct *work)
 
 	if (priv->vif)
 		vnt_interrupt_process(priv);
+
+	MACvIntEnable(priv->PortOffset, IMR_MASK_VALUE);
 }
 
 static irqreturn_t vnt_interrupt(int irq,  void *arg)
 {
 	struct vnt_private *priv = arg;
 
-	if (priv->vif)
-		schedule_work(&priv->interrupt_work);
+	schedule_work(&priv->interrupt_work);
+
+	MACvIntDisable(priv->PortOffset);
 
 	return IRQ_HANDLED;
 }
diff --git a/drivers/target/iscsi/iscsi_target_auth.c b/drivers/target/iscsi/iscsi_target_auth.c
index 4e680d753941..ca7d7e8aecc0 100644
--- a/drivers/target/iscsi/iscsi_target_auth.c
+++ b/drivers/target/iscsi/iscsi_target_auth.c
@@ -252,7 +252,6 @@ static int chap_server_compute_md5(
 	}
 
 	desc->tfm = tfm;
-	desc->flags = 0;
 
 	ret = crypto_shash_init(desc);
 	if (ret < 0) {
diff --git a/drivers/thermal/intel/int340x_thermal/acpi_thermal_rel.c b/drivers/thermal/intel/int340x_thermal/acpi_thermal_rel.c
index 45e7e5cbdffb..7c71ffb733a1 100644
--- a/drivers/thermal/intel/int340x_thermal/acpi_thermal_rel.c
+++ b/drivers/thermal/intel/int340x_thermal/acpi_thermal_rel.c
@@ -230,7 +230,7 @@ static void get_single_name(acpi_handle handle, char *name)
 	if (ACPI_FAILURE(acpi_get_name(handle, ACPI_SINGLE_NAME, &buffer)))
 		pr_warn("Failed to get device name from acpi handle\n");
 	else {
-		memcpy(name, buffer.pointer, ACPI_NAME_SIZE);
+		memcpy(name, buffer.pointer, ACPI_NAMESEG_SIZE);
 		kfree(buffer.pointer);
 	}
 }
diff --git a/drivers/thunderbolt/domain.c b/drivers/thunderbolt/domain.c
index 7416bdbd8576..b7980c856898 100644
--- a/drivers/thunderbolt/domain.c
+++ b/drivers/thunderbolt/domain.c
@@ -678,7 +678,6 @@ int tb_domain_challenge_switch_key(struct tb *tb, struct tb_switch *sw)
 	}
 
 	shash->tfm = tfm;
-	shash->flags = CRYPTO_TFM_REQ_MAY_SLEEP;
 
 	memset(hmac, 0, sizeof(hmac));
 	ret = crypto_shash_digest(shash, challenge, sizeof(hmac), hmac);
diff --git a/drivers/tty/rocket.c b/drivers/tty/rocket.c
index b121d8f8f3d7..27aeca30eeae 100644
--- a/drivers/tty/rocket.c
+++ b/drivers/tty/rocket.c
@@ -266,7 +266,7 @@ MODULE_PARM_DESC(pc104_3, "set interface types for ISA(PC104) board #3 (e.g. pc1
 module_param_array(pc104_4, ulong, NULL, 0);
 MODULE_PARM_DESC(pc104_4, "set interface types for ISA(PC104) board #4 (e.g. pc104_4=232,232,485,485,...");
 
-static int rp_init(void);
+static int __init rp_init(void);
 static void rp_cleanup_module(void);
 
 module_init(rp_init);
diff --git a/drivers/tty/serial/ar933x_uart.c b/drivers/tty/serial/ar933x_uart.c
index db5df3d54818..3bdd56a1021b 100644
--- a/drivers/tty/serial/ar933x_uart.c
+++ b/drivers/tty/serial/ar933x_uart.c
@@ -49,11 +49,6 @@ struct ar933x_uart_port {
 	struct clk		*clk;
 };
 
-static inline bool ar933x_uart_console_enabled(void)
-{
-	return IS_ENABLED(CONFIG_SERIAL_AR933X_CONSOLE);
-}
-
 static inline unsigned int ar933x_uart_read(struct ar933x_uart_port *up,
 					    int offset)
 {
@@ -508,6 +503,7 @@ static const struct uart_ops ar933x_uart_ops = {
 	.verify_port	= ar933x_uart_verify_port,
 };
 
+#ifdef CONFIG_SERIAL_AR933X_CONSOLE
 static struct ar933x_uart_port *
 ar933x_console_ports[CONFIG_SERIAL_AR933X_NR_UARTS];
 
@@ -604,14 +600,7 @@ static struct console ar933x_uart_console = {
 	.index		= -1,
 	.data		= &ar933x_uart_driver,
 };
-
-static void ar933x_uart_add_console_port(struct ar933x_uart_port *up)
-{
-	if (!ar933x_uart_console_enabled())
-		return;
-
-	ar933x_console_ports[up->port.line] = up;
-}
+#endif /* CONFIG_SERIAL_AR933X_CONSOLE */
 
 static struct uart_driver ar933x_uart_driver = {
 	.owner		= THIS_MODULE,
@@ -700,7 +689,9 @@ static int ar933x_uart_probe(struct platform_device *pdev)
 	baud = ar933x_uart_get_baud(port->uartclk, 0, AR933X_UART_MAX_STEP);
 	up->max_baud = min_t(unsigned int, baud, AR933X_UART_MAX_BAUD);
 
-	ar933x_uart_add_console_port(up);
+#ifdef CONFIG_SERIAL_AR933X_CONSOLE
+	ar933x_console_ports[up->port.line] = up;
+#endif
 
 	ret = uart_add_one_port(&ar933x_uart_driver, &up->port);
 	if (ret)
@@ -749,8 +740,9 @@ static int __init ar933x_uart_init(void)
 {
 	int ret;
 
-	if (ar933x_uart_console_enabled())
-		ar933x_uart_driver.cons = &ar933x_uart_console;
+#ifdef CONFIG_SERIAL_AR933X_CONSOLE
+	ar933x_uart_driver.cons = &ar933x_uart_console;
+#endif
 
 	ret = uart_register_driver(&ar933x_uart_driver);
 	if (ret)
diff --git a/drivers/tty/serial/atmel_serial.c b/drivers/tty/serial/atmel_serial.c
index 05147fe24343..0b4f36905321 100644
--- a/drivers/tty/serial/atmel_serial.c
+++ b/drivers/tty/serial/atmel_serial.c
@@ -166,6 +166,8 @@ struct atmel_uart_port {
 	unsigned int		pending_status;
 	spinlock_t		lock_suspended;
 
+	bool			hd_start_rx;	/* can start RX during half-duplex operation */
+
 	/* ISO7816 */
 	unsigned int		fidi_min;
 	unsigned int		fidi_max;
@@ -231,6 +233,13 @@ static inline void atmel_uart_write_char(struct uart_port *port, u8 value)
 	__raw_writeb(value, port->membase + ATMEL_US_THR);
 }
 
+static inline int atmel_uart_is_half_duplex(struct uart_port *port)
+{
+	return ((port->rs485.flags & SER_RS485_ENABLED) &&
+		!(port->rs485.flags & SER_RS485_RX_DURING_TX)) ||
+		(port->iso7816.flags & SER_ISO7816_ENABLED);
+}
+
 #ifdef CONFIG_SERIAL_ATMEL_PDC
 static bool atmel_use_pdc_rx(struct uart_port *port)
 {
@@ -608,10 +617,9 @@ static void atmel_stop_tx(struct uart_port *port)
 	/* Disable interrupts */
 	atmel_uart_writel(port, ATMEL_US_IDR, atmel_port->tx_done_mask);
 
-	if (((port->rs485.flags & SER_RS485_ENABLED) &&
-	     !(port->rs485.flags & SER_RS485_RX_DURING_TX)) ||
-	    port->iso7816.flags & SER_ISO7816_ENABLED)
+	if (atmel_uart_is_half_duplex(port))
 		atmel_start_rx(port);
+
 }
 
 /*
@@ -628,9 +636,7 @@ static void atmel_start_tx(struct uart_port *port)
 		return;
 
 	if (atmel_use_pdc_tx(port) || atmel_use_dma_tx(port))
-		if (((port->rs485.flags & SER_RS485_ENABLED) &&
-		     !(port->rs485.flags & SER_RS485_RX_DURING_TX)) ||
-		    port->iso7816.flags & SER_ISO7816_ENABLED)
+		if (atmel_uart_is_half_duplex(port))
 			atmel_stop_rx(port);
 
 	if (atmel_use_pdc_tx(port))
@@ -928,11 +934,14 @@ static void atmel_complete_tx_dma(void *arg)
 	 */
 	if (!uart_circ_empty(xmit))
 		atmel_tasklet_schedule(atmel_port, &atmel_port->tasklet_tx);
-	else if (((port->rs485.flags & SER_RS485_ENABLED) &&
-		  !(port->rs485.flags & SER_RS485_RX_DURING_TX)) ||
-		 port->iso7816.flags & SER_ISO7816_ENABLED) {
-		/* DMA done, stop TX, start RX for RS485 */
-		atmel_start_rx(port);
+	else if (atmel_uart_is_half_duplex(port)) {
+		/*
+		 * DMA done, re-enable TXEMPTY and signal that we can stop
+		 * TX and start RX for RS485
+		 */
+		atmel_port->hd_start_rx = true;
+		atmel_uart_writel(port, ATMEL_US_IER,
+				  atmel_port->tx_done_mask);
 	}
 
 	spin_unlock_irqrestore(&port->lock, flags);
@@ -1288,6 +1297,10 @@ static int atmel_prepare_rx_dma(struct uart_port *port)
 					 sg_dma_len(&atmel_port->sg_rx)/2,
 					 DMA_DEV_TO_MEM,
 					 DMA_PREP_INTERRUPT);
+	if (!desc) {
+		dev_err(port->dev, "Preparing DMA cyclic failed\n");
+		goto chan_err;
+	}
 	desc->callback = atmel_complete_rx_dma;
 	desc->callback_param = port;
 	atmel_port->desc_rx = desc;
@@ -1376,9 +1389,20 @@ atmel_handle_transmit(struct uart_port *port, unsigned int pending)
 	struct atmel_uart_port *atmel_port = to_atmel_uart_port(port);
 
 	if (pending & atmel_port->tx_done_mask) {
-		/* Either PDC or interrupt transmission */
 		atmel_uart_writel(port, ATMEL_US_IDR,
 				  atmel_port->tx_done_mask);
+
+		/* Start RX if flag was set and FIFO is empty */
+		if (atmel_port->hd_start_rx) {
+			if (!(atmel_uart_readl(port, ATMEL_US_CSR)
+					& ATMEL_US_TXEMPTY))
+				dev_warn(port->dev, "Should start RX, but TX fifo is not empty\n");
+
+			atmel_port->hd_start_rx = false;
+			atmel_start_rx(port);
+			return;
+		}
+
 		atmel_tasklet_schedule(atmel_port, &atmel_port->tasklet_tx);
 	}
 }
@@ -1508,9 +1532,7 @@ static void atmel_tx_pdc(struct uart_port *port)
 		atmel_uart_writel(port, ATMEL_US_IER,
 				  atmel_port->tx_done_mask);
 	} else {
-		if (((port->rs485.flags & SER_RS485_ENABLED) &&
-		     !(port->rs485.flags & SER_RS485_RX_DURING_TX)) ||
-		    port->iso7816.flags & SER_ISO7816_ENABLED) {
+		if (atmel_uart_is_half_duplex(port)) {
 			/* DMA done, stop TX, start RX for RS485 */
 			atmel_start_rx(port);
 		}
diff --git a/drivers/tty/serial/kgdboc.c b/drivers/tty/serial/kgdboc.c
index 6fb312e7af71..bfe5e9e034ec 100644
--- a/drivers/tty/serial/kgdboc.c
+++ b/drivers/tty/serial/kgdboc.c
@@ -148,8 +148,10 @@ static int configure_kgdboc(void)
 	char *cptr = config;
 	struct console *cons;
 
-	if (!strlen(config) || isspace(config[0]))
+	if (!strlen(config) || isspace(config[0])) {
+		err = 0;
 		goto noconfig;
+	}
 
 	kgdboc_io_ops.is_console = 0;
 	kgdb_tty_driver = NULL;
diff --git a/drivers/tty/serial/max310x.c b/drivers/tty/serial/max310x.c
index f5bdde405627..450ba6d7996c 100644
--- a/drivers/tty/serial/max310x.c
+++ b/drivers/tty/serial/max310x.c
@@ -1415,6 +1415,8 @@ static int max310x_spi_probe(struct spi_device *spi)
 	if (spi->dev.of_node) {
 		const struct of_device_id *of_id =
 			of_match_device(max310x_dt_ids, &spi->dev);
+		if (!of_id)
+			return -ENODEV;
 
 		devtype = (struct max310x_devtype *)of_id->data;
 	} else {
diff --git a/drivers/tty/serial/men_z135_uart.c b/drivers/tty/serial/men_z135_uart.c
index ef89534dd760..e5d3ebab6dae 100644
--- a/drivers/tty/serial/men_z135_uart.c
+++ b/drivers/tty/serial/men_z135_uart.c
@@ -353,7 +353,6 @@ static void men_z135_handle_tx(struct men_z135_port *uart)
 
 	memcpy_toio(port->membase + MEN_Z135_TX_RAM, &xmit->buf[xmit->tail], n);
 	xmit->tail = (xmit->tail + n) & (UART_XMIT_SIZE - 1);
-	mmiowb();
 
 	iowrite32(n & 0x3ff, port->membase + MEN_Z135_TX_CTRL);
 
diff --git a/drivers/tty/serial/mvebu-uart.c b/drivers/tty/serial/mvebu-uart.c
index 231f751d1ef4..7e7b1559fa36 100644
--- a/drivers/tty/serial/mvebu-uart.c
+++ b/drivers/tty/serial/mvebu-uart.c
@@ -810,6 +810,9 @@ static int mvebu_uart_probe(struct platform_device *pdev)
 		return -EINVAL;
 	}
 
+	if (!match)
+		return -ENODEV;
+
 	/* Assume that all UART ports have a DT alias or none has */
 	id = of_alias_get_id(pdev->dev.of_node, "serial");
 	if (!pdev->dev.of_node || id < 0)
diff --git a/drivers/tty/serial/mxs-auart.c b/drivers/tty/serial/mxs-auart.c
index 27235a526cce..4c188f4079b3 100644
--- a/drivers/tty/serial/mxs-auart.c
+++ b/drivers/tty/serial/mxs-auart.c
@@ -1686,6 +1686,10 @@ static int mxs_auart_probe(struct platform_device *pdev)
 
 	s->port.mapbase = r->start;
 	s->port.membase = ioremap(r->start, resource_size(r));
+	if (!s->port.membase) {
+		ret = -ENOMEM;
+		goto out_disable_clks;
+	}
 	s->port.ops = &mxs_auart_ops;
 	s->port.iotype = UPIO_MEM;
 	s->port.fifosize = MXS_AUART_FIFO_SIZE;
diff --git a/drivers/tty/serial/qcom_geni_serial.c b/drivers/tty/serial/qcom_geni_serial.c
index 3bcec1c20219..35e5f9c5d5be 100644
--- a/drivers/tty/serial/qcom_geni_serial.c
+++ b/drivers/tty/serial/qcom_geni_serial.c
@@ -1050,7 +1050,7 @@ static int __init qcom_geni_console_setup(struct console *co, char *options)
 {
 	struct uart_port *uport;
 	struct qcom_geni_serial_port *port;
-	int baud;
+	int baud = 9600;
 	int bits = 8;
 	int parity = 'n';
 	int flow = 'n';
diff --git a/drivers/tty/serial/sc16is7xx.c b/drivers/tty/serial/sc16is7xx.c
index 635178cf3eed..a31db15cd7c0 100644
--- a/drivers/tty/serial/sc16is7xx.c
+++ b/drivers/tty/serial/sc16is7xx.c
@@ -1507,7 +1507,7 @@ static int __init sc16is7xx_init(void)
 	ret = i2c_add_driver(&sc16is7xx_i2c_uart_driver);
 	if (ret < 0) {
 		pr_err("failed to init sc16is7xx i2c --> %d\n", ret);
-		return ret;
+		goto err_i2c;
 	}
 #endif
 
@@ -1515,10 +1515,20 @@ static int __init sc16is7xx_init(void)
 	ret = spi_register_driver(&sc16is7xx_spi_uart_driver);
 	if (ret < 0) {
 		pr_err("failed to init sc16is7xx spi --> %d\n", ret);
-		return ret;
+		goto err_spi;
 	}
 #endif
 	return ret;
+
+#ifdef CONFIG_SERIAL_SC16IS7XX_SPI
+err_spi:
+#endif
+#ifdef CONFIG_SERIAL_SC16IS7XX_I2C
+	i2c_del_driver(&sc16is7xx_i2c_uart_driver);
+err_i2c:
+#endif
+	uart_unregister_driver(&sc16is7xx_uart);
+	return ret;
 }
 module_init(sc16is7xx_init);
 
diff --git a/drivers/tty/serial/serial_txx9.c b/drivers/tty/serial/serial_txx9.c
index 1b4008d022bf..d22ccb32aa9b 100644
--- a/drivers/tty/serial/serial_txx9.c
+++ b/drivers/tty/serial/serial_txx9.c
@@ -248,7 +248,6 @@ static void serial_txx9_initialize(struct uart_port *port)
 	sio_out(up, TXX9_SIFCR, TXX9_SIFCR_SWRST);
 	/* TX4925 BUG WORKAROUND.  Accessing SIOC register
 	 * immediately after soft reset causes bus error. */
-	mmiowb();
 	udelay(1);
 	while ((sio_in(up, TXX9_SIFCR) & TXX9_SIFCR_SWRST) && --tmout)
 		udelay(1);
diff --git a/drivers/tty/serial/sh-sci.c b/drivers/tty/serial/sh-sci.c
index 060fcd42b6d5..3cd139752d3f 100644
--- a/drivers/tty/serial/sh-sci.c
+++ b/drivers/tty/serial/sh-sci.c
@@ -838,19 +838,9 @@ static void sci_transmit_chars(struct uart_port *port)
 
 	if (uart_circ_chars_pending(xmit) < WAKEUP_CHARS)
 		uart_write_wakeup(port);
-	if (uart_circ_empty(xmit)) {
+	if (uart_circ_empty(xmit))
 		sci_stop_tx(port);
-	} else {
-		ctrl = serial_port_in(port, SCSCR);
-
-		if (port->type != PORT_SCI) {
-			serial_port_in(port, SCxSR); /* Dummy read */
-			sci_clear_SCxSR(port, SCxSR_TDxE_CLEAR(port));
-		}
 
-		ctrl |= SCSCR_TIE;
-		serial_port_out(port, SCSCR, ctrl);
-	}
 }
 
 /* On SH3, SCIF may read end-of-break as a space->mark char */
@@ -2522,14 +2512,16 @@ done:
 			 * center of the last stop bit in sampling clocks.
 			 */
 			int last_stop = bits * 2 - 1;
-			int deviation = min_err * srr * last_stop / 2 / baud;
+			int deviation = DIV_ROUND_CLOSEST(min_err * last_stop *
+							  (int)(srr + 1),
+							  2 * (int)baud);
 
 			if (abs(deviation) >= 2) {
 				/* At least two sampling clocks off at the
 				 * last stop bit; we can increase the error
 				 * margin by shifting the sampling point.
 				 */
-				int shift = min(-8, max(7, deviation / 2));
+				int shift = clamp(deviation / 2, -8, 7);
 
 				hssrr |= (shift << HSCIF_SRHP_SHIFT) &
 					 HSCIF_SRHP_MASK;
diff --git a/drivers/tty/tty_port.c b/drivers/tty/tty_port.c
index 044c3cbdcfa4..a9e12b3bc31d 100644
--- a/drivers/tty/tty_port.c
+++ b/drivers/tty/tty_port.c
@@ -325,7 +325,7 @@ static void tty_port_shutdown(struct tty_port *port, struct tty_struct *tty)
 		if (tty && C_HUPCL(tty))
 			tty_port_lower_dtr_rts(port);
 
-		if (port->ops->shutdown)
+		if (port->ops && port->ops->shutdown)
 			port->ops->shutdown(port);
 	}
 out:
@@ -398,7 +398,7 @@ EXPORT_SYMBOL_GPL(tty_port_tty_wakeup);
  */
 int tty_port_carrier_raised(struct tty_port *port)
 {
-	if (port->ops->carrier_raised == NULL)
+	if (!port->ops || !port->ops->carrier_raised)
 		return 1;
 	return port->ops->carrier_raised(port);
 }
@@ -414,7 +414,7 @@ EXPORT_SYMBOL(tty_port_carrier_raised);
  */
 void tty_port_raise_dtr_rts(struct tty_port *port)
 {
-	if (port->ops->dtr_rts)
+	if (port->ops && port->ops->dtr_rts)
 		port->ops->dtr_rts(port, 1);
 }
 EXPORT_SYMBOL(tty_port_raise_dtr_rts);
@@ -429,7 +429,7 @@ EXPORT_SYMBOL(tty_port_raise_dtr_rts);
  */
 void tty_port_lower_dtr_rts(struct tty_port *port)
 {
-	if (port->ops->dtr_rts)
+	if (port->ops && port->ops->dtr_rts)
 		port->ops->dtr_rts(port, 0);
 }
 EXPORT_SYMBOL(tty_port_lower_dtr_rts);
@@ -684,7 +684,7 @@ int tty_port_open(struct tty_port *port, struct tty_struct *tty,
 
 	if (!tty_port_initialized(port)) {
 		clear_bit(TTY_IO_ERROR, &tty->flags);
-		if (port->ops->activate) {
+		if (port->ops && port->ops->activate) {
 			int retval = port->ops->activate(port, tty);
 			if (retval) {
 				mutex_unlock(&port->mutex);
diff --git a/drivers/tty/vt/vt.c b/drivers/tty/vt/vt.c
index d34984aa646d..650c66886c80 100644
--- a/drivers/tty/vt/vt.c
+++ b/drivers/tty/vt/vt.c
@@ -1520,7 +1520,8 @@ static void csi_J(struct vc_data *vc, int vpar)
 			return;
 	}
 	scr_memsetw(start, vc->vc_video_erase_char, 2 * count);
-	update_region(vc, (unsigned long) start, count);
+	if (con_should_update(vc))
+		do_update_region(vc, (unsigned long) start, count);
 	vc->vc_need_wrap = 0;
 }
 
diff --git a/drivers/usb/class/cdc-acm.c b/drivers/usb/class/cdc-acm.c
index 739f8960811a..ec666eb4b7b4 100644
--- a/drivers/usb/class/cdc-acm.c
+++ b/drivers/usb/class/cdc-acm.c
@@ -558,10 +558,8 @@ static void acm_softint(struct work_struct *work)
 		clear_bit(EVENT_RX_STALL, &acm->flags);
 	}
 
-	if (test_bit(EVENT_TTY_WAKEUP, &acm->flags)) {
+	if (test_and_clear_bit(EVENT_TTY_WAKEUP, &acm->flags))
 		tty_port_tty_wakeup(&acm->port);
-		clear_bit(EVENT_TTY_WAKEUP, &acm->flags);
-	}
 }
 
 /*
diff --git a/drivers/usb/common/common.c b/drivers/usb/common/common.c
index 48277bbc15e4..73c8e6591746 100644
--- a/drivers/usb/common/common.c
+++ b/drivers/usb/common/common.c
@@ -145,6 +145,8 @@ enum usb_dr_mode of_usb_get_dr_mode_by_phy(struct device_node *np, int arg0)
 
 	do {
 		controller = of_find_node_with_property(controller, "phys");
+		if (!of_device_is_available(controller))
+			continue;
 		index = 0;
 		do {
 			if (arg0 == -1) {
diff --git a/drivers/usb/core/driver.c b/drivers/usb/core/driver.c
index 8987cec9549d..ebcadaad89d1 100644
--- a/drivers/usb/core/driver.c
+++ b/drivers/usb/core/driver.c
@@ -473,11 +473,6 @@ static int usb_unbind_interface(struct device *dev)
 		pm_runtime_disable(dev);
 	pm_runtime_set_suspended(dev);
 
-	/* Undo any residual pm_autopm_get_interface_* calls */
-	for (r = atomic_read(&intf->pm_usage_cnt); r > 0; --r)
-		usb_autopm_put_interface_no_suspend(intf);
-	atomic_set(&intf->pm_usage_cnt, 0);
-
 	if (!error)
 		usb_autosuspend_device(udev);
 
@@ -1633,7 +1628,6 @@ void usb_autopm_put_interface(struct usb_interface *intf)
 	int			status;
 
 	usb_mark_last_busy(udev);
-	atomic_dec(&intf->pm_usage_cnt);
 	status = pm_runtime_put_sync(&intf->dev);
 	dev_vdbg(&intf->dev, "%s: cnt %d -> %d\n",
 			__func__, atomic_read(&intf->dev.power.usage_count),
@@ -1662,7 +1656,6 @@ void usb_autopm_put_interface_async(struct usb_interface *intf)
 	int			status;
 
 	usb_mark_last_busy(udev);
-	atomic_dec(&intf->pm_usage_cnt);
 	status = pm_runtime_put(&intf->dev);
 	dev_vdbg(&intf->dev, "%s: cnt %d -> %d\n",
 			__func__, atomic_read(&intf->dev.power.usage_count),
@@ -1684,7 +1677,6 @@ void usb_autopm_put_interface_no_suspend(struct usb_interface *intf)
 	struct usb_device	*udev = interface_to_usbdev(intf);
 
 	usb_mark_last_busy(udev);
-	atomic_dec(&intf->pm_usage_cnt);
 	pm_runtime_put_noidle(&intf->dev);
 }
 EXPORT_SYMBOL_GPL(usb_autopm_put_interface_no_suspend);
@@ -1715,8 +1707,6 @@ int usb_autopm_get_interface(struct usb_interface *intf)
 	status = pm_runtime_get_sync(&intf->dev);
 	if (status < 0)
 		pm_runtime_put_sync(&intf->dev);
-	else
-		atomic_inc(&intf->pm_usage_cnt);
 	dev_vdbg(&intf->dev, "%s: cnt %d -> %d\n",
 			__func__, atomic_read(&intf->dev.power.usage_count),
 			status);
@@ -1750,8 +1740,6 @@ int usb_autopm_get_interface_async(struct usb_interface *intf)
 	status = pm_runtime_get(&intf->dev);
 	if (status < 0 && status != -EINPROGRESS)
 		pm_runtime_put_noidle(&intf->dev);
-	else
-		atomic_inc(&intf->pm_usage_cnt);
 	dev_vdbg(&intf->dev, "%s: cnt %d -> %d\n",
 			__func__, atomic_read(&intf->dev.power.usage_count),
 			status);
@@ -1775,7 +1763,6 @@ void usb_autopm_get_interface_no_resume(struct usb_interface *intf)
 	struct usb_device	*udev = interface_to_usbdev(intf);
 
 	usb_mark_last_busy(udev);
-	atomic_inc(&intf->pm_usage_cnt);
 	pm_runtime_get_noresume(&intf->dev);
 }
 EXPORT_SYMBOL_GPL(usb_autopm_get_interface_no_resume);
diff --git a/drivers/usb/core/hcd.c b/drivers/usb/core/hcd.c
index 3189181bb628..975d7c1288e3 100644
--- a/drivers/usb/core/hcd.c
+++ b/drivers/usb/core/hcd.c
@@ -2742,6 +2742,9 @@ int usb_add_hcd(struct usb_hcd *hcd,
 		retval = usb_phy_roothub_set_mode(hcd->phy_roothub,
 						  PHY_MODE_USB_HOST_SS);
 		if (retval)
+			retval = usb_phy_roothub_set_mode(hcd->phy_roothub,
+							  PHY_MODE_USB_HOST);
+		if (retval)
 			goto err_usb_phy_roothub_power_on;
 
 		retval = usb_phy_roothub_power_on(hcd->phy_roothub);
diff --git a/drivers/usb/core/message.c b/drivers/usb/core/message.c
index 82239f27c4cc..e844bb7b5676 100644
--- a/drivers/usb/core/message.c
+++ b/drivers/usb/core/message.c
@@ -820,9 +820,11 @@ int usb_string(struct usb_device *dev, int index, char *buf, size_t size)
 
 	if (dev->state == USB_STATE_SUSPENDED)
 		return -EHOSTUNREACH;
-	if (size <= 0 || !buf || !index)
+	if (size <= 0 || !buf)
 		return -EINVAL;
 	buf[0] = 0;
+	if (index <= 0 || index >= 256)
+		return -EINVAL;
 	tbuf = kmalloc(256, GFP_NOIO);
 	if (!tbuf)
 		return -ENOMEM;
diff --git a/drivers/usb/dwc3/dwc3-pci.c b/drivers/usb/dwc3/dwc3-pci.c
index fdc6e4e403e8..8cced3609e24 100644
--- a/drivers/usb/dwc3/dwc3-pci.c
+++ b/drivers/usb/dwc3/dwc3-pci.c
@@ -29,6 +29,7 @@
 #define PCI_DEVICE_ID_INTEL_BXT_M		0x1aaa
 #define PCI_DEVICE_ID_INTEL_APL			0x5aaa
 #define PCI_DEVICE_ID_INTEL_KBP			0xa2b0
+#define PCI_DEVICE_ID_INTEL_CMLH		0x02ee
 #define PCI_DEVICE_ID_INTEL_GLK			0x31aa
 #define PCI_DEVICE_ID_INTEL_CNPLP		0x9dee
 #define PCI_DEVICE_ID_INTEL_CNPH		0xa36e
@@ -305,6 +306,9 @@ static const struct pci_device_id dwc3_pci_id_table[] = {
 	{ PCI_VDEVICE(INTEL, PCI_DEVICE_ID_INTEL_MRFLD),
 	  (kernel_ulong_t) &dwc3_pci_mrfld_properties, },
 
+	{ PCI_VDEVICE(INTEL, PCI_DEVICE_ID_INTEL_CMLH),
+	  (kernel_ulong_t) &dwc3_pci_intel_properties, },
+
 	{ PCI_VDEVICE(INTEL, PCI_DEVICE_ID_INTEL_SPTLP),
 	  (kernel_ulong_t) &dwc3_pci_intel_properties, },
 
diff --git a/drivers/usb/early/xhci-dbc.c b/drivers/usb/early/xhci-dbc.c
index c9cfb100ecdc..cac991173ac0 100644
--- a/drivers/usb/early/xhci-dbc.c
+++ b/drivers/usb/early/xhci-dbc.c
@@ -533,8 +533,6 @@ static int xdbc_handle_external_reset(void)
 
 	xdbc_mem_init();
 
-	mmiowb();
-
 	ret = xdbc_start();
 	if (ret < 0)
 		goto reset_out;
@@ -587,8 +585,6 @@ static int __init xdbc_early_setup(void)
 
 	xdbc_mem_init();
 
-	mmiowb();
-
 	ret = xdbc_start();
 	if (ret < 0) {
 		writel(0, &xdbc.xdbc_reg->control);
diff --git a/drivers/usb/gadget/function/f_hid.c b/drivers/usb/gadget/function/f_hid.c
index 75b113a5b25c..f3816a5c861e 100644
--- a/drivers/usb/gadget/function/f_hid.c
+++ b/drivers/usb/gadget/function/f_hid.c
@@ -391,20 +391,20 @@ try_again:
 	req->complete = f_hidg_req_complete;
 	req->context  = hidg;
 
+	spin_unlock_irqrestore(&hidg->write_spinlock, flags);
+
 	status = usb_ep_queue(hidg->in_ep, req, GFP_ATOMIC);
 	if (status < 0) {
 		ERROR(hidg->func.config->cdev,
 			"usb_ep_queue error on int endpoint %zd\n", status);
-		goto release_write_pending_unlocked;
+		goto release_write_pending;
 	} else {
 		status = count;
 	}
-	spin_unlock_irqrestore(&hidg->write_spinlock, flags);
 
 	return status;
 release_write_pending:
 	spin_lock_irqsave(&hidg->write_spinlock, flags);
-release_write_pending_unlocked:
 	hidg->write_pending = 0;
 	spin_unlock_irqrestore(&hidg->write_spinlock, flags);
 
diff --git a/drivers/usb/gadget/udc/dummy_hcd.c b/drivers/usb/gadget/udc/dummy_hcd.c
index baf72f95f0f1..213b52508621 100644
--- a/drivers/usb/gadget/udc/dummy_hcd.c
+++ b/drivers/usb/gadget/udc/dummy_hcd.c
@@ -979,8 +979,18 @@ static int dummy_udc_start(struct usb_gadget *g,
 	struct dummy_hcd	*dum_hcd = gadget_to_dummy_hcd(g);
 	struct dummy		*dum = dum_hcd->dum;
 
-	if (driver->max_speed == USB_SPEED_UNKNOWN)
+	switch (g->speed) {
+	/* All the speeds we support */
+	case USB_SPEED_LOW:
+	case USB_SPEED_FULL:
+	case USB_SPEED_HIGH:
+	case USB_SPEED_SUPER:
+		break;
+	default:
+		dev_err(dummy_dev(dum_hcd), "Unsupported driver max speed %d\n",
+				driver->max_speed);
 		return -EINVAL;
+	}
 
 	/*
 	 * SLAVE side init ... the layer above hardware, which
@@ -1784,9 +1794,10 @@ static void dummy_timer(struct timer_list *t)
 		/* Bus speed is 500000 bytes/ms, so use a little less */
 		total = 490000;
 		break;
-	default:
+	default:	/* Can't happen */
 		dev_err(dummy_dev(dum_hcd), "bogus device speed\n");
-		return;
+		total = 0;
+		break;
 	}
 
 	/* FIXME if HZ != 1000 this will probably misbehave ... */
@@ -1828,7 +1839,7 @@ restart:
 
 		/* Used up this frame's bandwidth? */
 		if (total <= 0)
-			break;
+			continue;
 
 		/* find the gadget's ep for this request (if configured) */
 		address = usb_pipeendpoint (urb->pipe);
diff --git a/drivers/usb/gadget/udc/net2272.c b/drivers/usb/gadget/udc/net2272.c
index b77f3126580e..c2011cd7df8c 100644
--- a/drivers/usb/gadget/udc/net2272.c
+++ b/drivers/usb/gadget/udc/net2272.c
@@ -945,6 +945,7 @@ net2272_dequeue(struct usb_ep *_ep, struct usb_request *_req)
 			break;
 	}
 	if (&req->req != _req) {
+		ep->stopped = stopped;
 		spin_unlock_irqrestore(&ep->dev->lock, flags);
 		return -EINVAL;
 	}
diff --git a/drivers/usb/gadget/udc/net2280.c b/drivers/usb/gadget/udc/net2280.c
index f63f82450bf4..898339e5df10 100644
--- a/drivers/usb/gadget/udc/net2280.c
+++ b/drivers/usb/gadget/udc/net2280.c
@@ -866,9 +866,6 @@ static void start_queue(struct net2280_ep *ep, u32 dmactl, u32 td_dma)
 	(void) readl(&ep->dev->pci->pcimstctl);
 
 	writel(BIT(DMA_START), &dma->dmastat);
-
-	if (!ep->is_in)
-		stop_out_naking(ep);
 }
 
 static void start_dma(struct net2280_ep *ep, struct net2280_request *req)
@@ -907,6 +904,7 @@ static void start_dma(struct net2280_ep *ep, struct net2280_request *req)
 			writel(BIT(DMA_START), &dma->dmastat);
 			return;
 		}
+		stop_out_naking(ep);
 	}
 
 	tmp = dmactl_default;
@@ -1275,9 +1273,9 @@ static int net2280_dequeue(struct usb_ep *_ep, struct usb_request *_req)
 			break;
 	}
 	if (&req->req != _req) {
+		ep->stopped = stopped;
 		spin_unlock_irqrestore(&ep->dev->lock, flags);
-		dev_err(&ep->dev->pdev->dev, "%s: Request mismatch\n",
-								__func__);
+		ep_dbg(ep->dev, "%s: Request mismatch\n", __func__);
 		return -EINVAL;
 	}
 
diff --git a/drivers/usb/host/u132-hcd.c b/drivers/usb/host/u132-hcd.c
index 934584f0a20a..6343fbacd244 100644
--- a/drivers/usb/host/u132-hcd.c
+++ b/drivers/usb/host/u132-hcd.c
@@ -3204,6 +3204,9 @@ static int __init u132_hcd_init(void)
 	printk(KERN_INFO "driver %s\n", hcd_name);
 	workqueue = create_singlethread_workqueue("u132");
 	retval = platform_driver_register(&u132_platform_driver);
+	if (retval)
+		destroy_workqueue(workqueue);
+
 	return retval;
 }
 
diff --git a/drivers/usb/host/xhci-dbgcap.c b/drivers/usb/host/xhci-dbgcap.c
index c78be578abb0..52e32644a4b2 100644
--- a/drivers/usb/host/xhci-dbgcap.c
+++ b/drivers/usb/host/xhci-dbgcap.c
@@ -421,8 +421,6 @@ static int xhci_dbc_mem_init(struct xhci_hcd *xhci, gfp_t flags)
 	string_length = xhci_dbc_populate_strings(dbc->string);
 	xhci_dbc_init_contexts(xhci, string_length);
 
-	mmiowb();
-
 	xhci_dbc_eps_init(xhci);
 	dbc->state = DS_INITIALIZED;
 
@@ -516,7 +514,6 @@ static int xhci_do_dbc_stop(struct xhci_hcd *xhci)
 		return -1;
 
 	writel(0, &dbc->regs->control);
-	xhci_dbc_mem_cleanup(xhci);
 	dbc->state = DS_DISABLED;
 
 	return 0;
@@ -562,8 +559,10 @@ static void xhci_dbc_stop(struct xhci_hcd *xhci)
 	ret = xhci_do_dbc_stop(xhci);
 	spin_unlock_irqrestore(&dbc->lock, flags);
 
-	if (!ret)
+	if (!ret) {
+		xhci_dbc_mem_cleanup(xhci);
 		pm_runtime_put_sync(xhci_to_hcd(xhci)->self.controller);
+	}
 }
 
 static void
diff --git a/drivers/usb/host/xhci-hub.c b/drivers/usb/host/xhci-hub.c
index e2eece693655..96a740543183 100644
--- a/drivers/usb/host/xhci-hub.c
+++ b/drivers/usb/host/xhci-hub.c
@@ -1545,20 +1545,25 @@ int xhci_bus_suspend(struct usb_hcd *hcd)
 	port_index = max_ports;
 	while (port_index--) {
 		u32 t1, t2;
-
+		int retries = 10;
+retry:
 		t1 = readl(ports[port_index]->addr);
 		t2 = xhci_port_state_to_neutral(t1);
 		portsc_buf[port_index] = 0;
 
-		/* Bail out if a USB3 port has a new device in link training */
-		if ((hcd->speed >= HCD_USB3) &&
+		/*
+		 * Give a USB3 port in link training time to finish, but don't
+		 * prevent suspend as port might be stuck
+		 */
+		if ((hcd->speed >= HCD_USB3) && retries-- &&
 		    (t1 & PORT_PLS_MASK) == XDEV_POLLING) {
-			bus_state->bus_suspended = 0;
 			spin_unlock_irqrestore(&xhci->lock, flags);
-			xhci_dbg(xhci, "Bus suspend bailout, port in polling\n");
-			return -EBUSY;
+			msleep(XHCI_PORT_POLLING_LFPS_TIME);
+			spin_lock_irqsave(&xhci->lock, flags);
+			xhci_dbg(xhci, "port %d polling in bus suspend, waiting\n",
+				 port_index);
+			goto retry;
 		}
-
 		/* suspend ports in U0, or bail out for new connect changes */
 		if ((t1 & PORT_PE) && (t1 & PORT_PLS_MASK) == XDEV_U0) {
 			if ((t1 & PORT_CSC) && wake_enabled) {
diff --git a/drivers/usb/host/xhci-rcar.c b/drivers/usb/host/xhci-rcar.c
index a6e463715779..671bce18782c 100644
--- a/drivers/usb/host/xhci-rcar.c
+++ b/drivers/usb/host/xhci-rcar.c
@@ -246,6 +246,7 @@ int xhci_rcar_init_quirk(struct usb_hcd *hcd)
 	if (!xhci_rcar_wait_for_pll_active(hcd))
 		return -ETIMEDOUT;
 
+	xhci->quirks |= XHCI_TRUST_TX_LENGTH;
 	return xhci_rcar_download_firmware(hcd);
 }
 
diff --git a/drivers/usb/host/xhci-ring.c b/drivers/usb/host/xhci-ring.c
index 40fa25c4d041..9215a28dad40 100644
--- a/drivers/usb/host/xhci-ring.c
+++ b/drivers/usb/host/xhci-ring.c
@@ -1647,10 +1647,13 @@ static void handle_port_status(struct xhci_hcd *xhci,
 		}
 	}
 
-	if ((portsc & PORT_PLC) && (portsc & PORT_PLS_MASK) == XDEV_U0 &&
-			DEV_SUPERSPEED_ANY(portsc)) {
+	if ((portsc & PORT_PLC) &&
+	    DEV_SUPERSPEED_ANY(portsc) &&
+	    ((portsc & PORT_PLS_MASK) == XDEV_U0 ||
+	     (portsc & PORT_PLS_MASK) == XDEV_U1 ||
+	     (portsc & PORT_PLS_MASK) == XDEV_U2)) {
 		xhci_dbg(xhci, "resume SS port %d finished\n", port_id);
-		/* We've just brought the device into U0 through either the
+		/* We've just brought the device into U0/1/2 through either the
 		 * Resume state after a device remote wakeup, or through the
 		 * U3Exit state after a host-initiated resume.  If it's a device
 		 * initiated remote wake, don't pass up the link state change,
diff --git a/drivers/usb/host/xhci.h b/drivers/usb/host/xhci.h
index 652dc36e3012..9334cdee382a 100644
--- a/drivers/usb/host/xhci.h
+++ b/drivers/usb/host/xhci.h
@@ -452,6 +452,14 @@ struct xhci_op_regs {
  */
 #define XHCI_DEFAULT_BESL	4
 
+/*
+ * USB3 specification define a 360ms tPollingLFPSTiemout for USB3 ports
+ * to complete link training. usually link trainig completes much faster
+ * so check status 10 times with 36ms sleep in places we need to wait for
+ * polling to complete.
+ */
+#define XHCI_PORT_POLLING_LFPS_TIME  36
+
 /**
  * struct xhci_intr_reg - Interrupt Register Set
  * @irq_pending:	IMAN - Interrupt Management Register.  Used to enable
diff --git a/drivers/usb/misc/usb251xb.c b/drivers/usb/misc/usb251xb.c
index 4d72b7d1d383..04684849d683 100644
--- a/drivers/usb/misc/usb251xb.c
+++ b/drivers/usb/misc/usb251xb.c
@@ -547,7 +547,7 @@ static int usb251xb_get_ofdata(struct usb251xb *hub,
 	 */
 	hub->port_swap = USB251XB_DEF_PORT_SWAP;
 	of_property_for_each_u32(np, "swap-dx-lanes", prop, p, port) {
-		if ((port >= 0) && (port <= data->port_cnt))
+		if (port <= data->port_cnt)
 			hub->port_swap |= BIT(port);
 	}
 
@@ -612,7 +612,7 @@ static int usb251xb_probe(struct usb251xb *hub)
 							   dev);
 	int err;
 
-	if (np) {
+	if (np && of_id) {
 		err = usb251xb_get_ofdata(hub,
 					  (struct usb251xb_data *)of_id->data);
 		if (err) {
diff --git a/drivers/usb/misc/yurex.c b/drivers/usb/misc/yurex.c
index 6d9fd5f64903..7b306aa22d25 100644
--- a/drivers/usb/misc/yurex.c
+++ b/drivers/usb/misc/yurex.c
@@ -314,6 +314,7 @@ static void yurex_disconnect(struct usb_interface *interface)
 	usb_deregister_dev(interface, &yurex_class);
 
 	/* prevent more I/O from starting */
+	usb_poison_urb(dev->urb);
 	mutex_lock(&dev->io_mutex);
 	dev->interface = NULL;
 	mutex_unlock(&dev->io_mutex);
diff --git a/drivers/usb/mtu3/Kconfig b/drivers/usb/mtu3/Kconfig
index bcc23486c4ed..928c2cd6fc00 100644
--- a/drivers/usb/mtu3/Kconfig
+++ b/drivers/usb/mtu3/Kconfig
@@ -6,6 +6,7 @@ config USB_MTU3
 	tristate "MediaTek USB3 Dual Role controller"
 	depends on USB || USB_GADGET
 	depends on ARCH_MEDIATEK || COMPILE_TEST
+	depends on EXTCON || !EXTCON
 	select USB_XHCI_MTK if USB_SUPPORT && USB_XHCI_HCD
 	help
 	  Say Y or M here if your system runs on MediaTek SoCs with
diff --git a/drivers/usb/serial/cp210x.c b/drivers/usb/serial/cp210x.c
index fffe23ab0189..979bef9bfb6b 100644
--- a/drivers/usb/serial/cp210x.c
+++ b/drivers/usb/serial/cp210x.c
@@ -80,6 +80,7 @@ static const struct usb_device_id id_table[] = {
 	{ USB_DEVICE(0x10C4, 0x804E) }, /* Software Bisque Paramount ME build-in converter */
 	{ USB_DEVICE(0x10C4, 0x8053) }, /* Enfora EDG1228 */
 	{ USB_DEVICE(0x10C4, 0x8054) }, /* Enfora GSM2228 */
+	{ USB_DEVICE(0x10C4, 0x8056) }, /* Lorenz Messtechnik devices */
 	{ USB_DEVICE(0x10C4, 0x8066) }, /* Argussoft In-System Programmer */
 	{ USB_DEVICE(0x10C4, 0x806F) }, /* IMS USB to RS422 Converter Cable */
 	{ USB_DEVICE(0x10C4, 0x807A) }, /* Crumb128 board */
diff --git a/drivers/usb/serial/ftdi_sio.c b/drivers/usb/serial/ftdi_sio.c
index 8f5b17471759..1d8461ae2c34 100644
--- a/drivers/usb/serial/ftdi_sio.c
+++ b/drivers/usb/serial/ftdi_sio.c
@@ -609,6 +609,8 @@ static const struct usb_device_id id_table_combined[] = {
 		.driver_info = (kernel_ulong_t)&ftdi_jtag_quirk },
 	{ USB_DEVICE(FTDI_VID, FTDI_NT_ORIONLXM_PID),
 		.driver_info = (kernel_ulong_t)&ftdi_jtag_quirk },
+	{ USB_DEVICE(FTDI_VID, FTDI_NT_ORIONLX_PLUS_PID) },
+	{ USB_DEVICE(FTDI_VID, FTDI_NT_ORION_IO_PID) },
 	{ USB_DEVICE(FTDI_VID, FTDI_SYNAPSE_SS200_PID) },
 	{ USB_DEVICE(FTDI_VID, FTDI_CUSTOMWARE_MINIPLEX_PID) },
 	{ USB_DEVICE(FTDI_VID, FTDI_CUSTOMWARE_MINIPLEX2_PID) },
diff --git a/drivers/usb/serial/ftdi_sio_ids.h b/drivers/usb/serial/ftdi_sio_ids.h
index b863bedb55a1..5755f0df0025 100644
--- a/drivers/usb/serial/ftdi_sio_ids.h
+++ b/drivers/usb/serial/ftdi_sio_ids.h
@@ -567,7 +567,9 @@
 /*
  * NovaTech product ids (FTDI_VID)
  */
-#define FTDI_NT_ORIONLXM_PID	0x7c90	/* OrionLXm Substation Automation Platform */
+#define FTDI_NT_ORIONLXM_PID		0x7c90	/* OrionLXm Substation Automation Platform */
+#define FTDI_NT_ORIONLX_PLUS_PID	0x7c91	/* OrionLX+ Substation Automation Platform */
+#define FTDI_NT_ORION_IO_PID		0x7c92	/* Orion I/O */
 
 /*
  * Synapse Wireless product ids (FTDI_VID)
diff --git a/drivers/usb/serial/mos7720.c b/drivers/usb/serial/mos7720.c
index fc52ac75fbf6..18110225d506 100644
--- a/drivers/usb/serial/mos7720.c
+++ b/drivers/usb/serial/mos7720.c
@@ -366,8 +366,6 @@ static int write_parport_reg_nonblock(struct mos7715_parport *mos_parport,
 	if (!urbtrack)
 		return -ENOMEM;
 
-	kref_get(&mos_parport->ref_count);
-	urbtrack->mos_parport = mos_parport;
 	urbtrack->urb = usb_alloc_urb(0, GFP_ATOMIC);
 	if (!urbtrack->urb) {
 		kfree(urbtrack);
@@ -388,6 +386,8 @@ static int write_parport_reg_nonblock(struct mos7715_parport *mos_parport,
 			     usb_sndctrlpipe(usbdev, 0),
 			     (unsigned char *)urbtrack->setup,
 			     NULL, 0, async_complete, urbtrack);
+	kref_get(&mos_parport->ref_count);
+	urbtrack->mos_parport = mos_parport;
 	kref_init(&urbtrack->ref_count);
 	INIT_LIST_HEAD(&urbtrack->urblist_entry);
 
diff --git a/drivers/usb/serial/option.c b/drivers/usb/serial/option.c
index 11b21d9410f3..83869065b802 100644
--- a/drivers/usb/serial/option.c
+++ b/drivers/usb/serial/option.c
@@ -246,6 +246,7 @@ static void option_instat_callback(struct urb *urb);
 #define QUECTEL_PRODUCT_EC25			0x0125
 #define QUECTEL_PRODUCT_BG96			0x0296
 #define QUECTEL_PRODUCT_EP06			0x0306
+#define QUECTEL_PRODUCT_EM12			0x0512
 
 #define CMOTECH_VENDOR_ID			0x16d8
 #define CMOTECH_PRODUCT_6001			0x6001
@@ -1066,7 +1067,8 @@ static const struct usb_device_id option_ids[] = {
 	  .driver_info = RSVD(3) },
 	{ USB_DEVICE(QUALCOMM_VENDOR_ID, 0x6613)}, /* Onda H600/ZTE MF330 */
 	{ USB_DEVICE(QUALCOMM_VENDOR_ID, 0x0023)}, /* ONYX 3G device */
-	{ USB_DEVICE(QUALCOMM_VENDOR_ID, 0x9000)}, /* SIMCom SIM5218 */
+	{ USB_DEVICE(QUALCOMM_VENDOR_ID, 0x9000), /* SIMCom SIM5218 */
+	  .driver_info = NCTRL(0) | NCTRL(1) | NCTRL(2) | NCTRL(3) | RSVD(4) },
 	/* Quectel products using Qualcomm vendor ID */
 	{ USB_DEVICE(QUALCOMM_VENDOR_ID, QUECTEL_PRODUCT_UC15)},
 	{ USB_DEVICE(QUALCOMM_VENDOR_ID, QUECTEL_PRODUCT_UC20),
@@ -1087,6 +1089,9 @@ static const struct usb_device_id option_ids[] = {
 	{ USB_DEVICE_AND_INTERFACE_INFO(QUECTEL_VENDOR_ID, QUECTEL_PRODUCT_EP06, 0xff, 0xff, 0xff),
 	  .driver_info = RSVD(1) | RSVD(2) | RSVD(3) | RSVD(4) | NUMEP2 },
 	{ USB_DEVICE_AND_INTERFACE_INFO(QUECTEL_VENDOR_ID, QUECTEL_PRODUCT_EP06, 0xff, 0, 0) },
+	{ USB_DEVICE_AND_INTERFACE_INFO(QUECTEL_VENDOR_ID, QUECTEL_PRODUCT_EM12, 0xff, 0xff, 0xff),
+	  .driver_info = RSVD(1) | RSVD(2) | RSVD(3) | RSVD(4) | NUMEP2 },
+	{ USB_DEVICE_AND_INTERFACE_INFO(QUECTEL_VENDOR_ID, QUECTEL_PRODUCT_EM12, 0xff, 0, 0) },
 	{ USB_DEVICE(CMOTECH_VENDOR_ID, CMOTECH_PRODUCT_6001) },
 	{ USB_DEVICE(CMOTECH_VENDOR_ID, CMOTECH_PRODUCT_CMU_300) },
 	{ USB_DEVICE(CMOTECH_VENDOR_ID, CMOTECH_PRODUCT_6003),
@@ -1940,10 +1945,12 @@ static const struct usb_device_id option_ids[] = {
 	  .driver_info = RSVD(4) },
 	{ USB_DEVICE_INTERFACE_CLASS(0x2001, 0x7e35, 0xff),			/* D-Link DWM-222 */
 	  .driver_info = RSVD(4) },
-	{ USB_DEVICE_AND_INTERFACE_INFO(0x07d1, 0x3e01, 0xff, 0xff, 0xff) }, /* D-Link DWM-152/C1 */
-	{ USB_DEVICE_AND_INTERFACE_INFO(0x07d1, 0x3e02, 0xff, 0xff, 0xff) }, /* D-Link DWM-156/C1 */
-	{ USB_DEVICE_AND_INTERFACE_INFO(0x07d1, 0x7e11, 0xff, 0xff, 0xff) }, /* D-Link DWM-156/A3 */
-	{ USB_DEVICE_INTERFACE_CLASS(0x2020, 0x4000, 0xff) },                /* OLICARD300 - MT6225 */
+	{ USB_DEVICE_AND_INTERFACE_INFO(0x07d1, 0x3e01, 0xff, 0xff, 0xff) },	/* D-Link DWM-152/C1 */
+	{ USB_DEVICE_AND_INTERFACE_INFO(0x07d1, 0x3e02, 0xff, 0xff, 0xff) },	/* D-Link DWM-156/C1 */
+	{ USB_DEVICE_AND_INTERFACE_INFO(0x07d1, 0x7e11, 0xff, 0xff, 0xff) },	/* D-Link DWM-156/A3 */
+	{ USB_DEVICE_INTERFACE_CLASS(0x2020, 0x2031, 0xff),			/* Olicard 600 */
+	  .driver_info = RSVD(4) },
+	{ USB_DEVICE_INTERFACE_CLASS(0x2020, 0x4000, 0xff) },			/* OLICARD300 - MT6225 */
 	{ USB_DEVICE(INOVIA_VENDOR_ID, INOVIA_SEW858) },
 	{ USB_DEVICE(VIATELECOM_VENDOR_ID, VIATELECOM_PRODUCT_CDS7) },
 	{ USB_DEVICE_AND_INTERFACE_INFO(WETELECOM_VENDOR_ID, WETELECOM_PRODUCT_WMD200, 0xff, 0xff, 0xff) },
diff --git a/drivers/usb/storage/realtek_cr.c b/drivers/usb/storage/realtek_cr.c
index 31b024441938..cc794e25a0b6 100644
--- a/drivers/usb/storage/realtek_cr.c
+++ b/drivers/usb/storage/realtek_cr.c
@@ -763,18 +763,16 @@ static void rts51x_suspend_timer_fn(struct timer_list *t)
 		break;
 	case RTS51X_STAT_IDLE:
 	case RTS51X_STAT_SS:
-		usb_stor_dbg(us, "RTS51X_STAT_SS, intf->pm_usage_cnt:%d, power.usage:%d\n",
-			     atomic_read(&us->pusb_intf->pm_usage_cnt),
+		usb_stor_dbg(us, "RTS51X_STAT_SS, power.usage:%d\n",
 			     atomic_read(&us->pusb_intf->dev.power.usage_count));
 
-		if (atomic_read(&us->pusb_intf->pm_usage_cnt) > 0) {
+		if (atomic_read(&us->pusb_intf->dev.power.usage_count) > 0) {
 			usb_stor_dbg(us, "Ready to enter SS state\n");
 			rts51x_set_stat(chip, RTS51X_STAT_SS);
 			/* ignore mass storage interface's children */
 			pm_suspend_ignore_children(&us->pusb_intf->dev, true);
 			usb_autopm_put_interface_async(us->pusb_intf);
-			usb_stor_dbg(us, "RTS51X_STAT_SS 01, intf->pm_usage_cnt:%d, power.usage:%d\n",
-				     atomic_read(&us->pusb_intf->pm_usage_cnt),
+			usb_stor_dbg(us, "RTS51X_STAT_SS 01, power.usage:%d\n",
 				     atomic_read(&us->pusb_intf->dev.power.usage_count));
 		}
 		break;
@@ -807,11 +805,10 @@ static void rts51x_invoke_transport(struct scsi_cmnd *srb, struct us_data *us)
 	int ret;
 
 	if (working_scsi(srb)) {
-		usb_stor_dbg(us, "working scsi, intf->pm_usage_cnt:%d, power.usage:%d\n",
-			     atomic_read(&us->pusb_intf->pm_usage_cnt),
+		usb_stor_dbg(us, "working scsi, power.usage:%d\n",
 			     atomic_read(&us->pusb_intf->dev.power.usage_count));
 
-		if (atomic_read(&us->pusb_intf->pm_usage_cnt) <= 0) {
+		if (atomic_read(&us->pusb_intf->dev.power.usage_count) <= 0) {
 			ret = usb_autopm_get_interface(us->pusb_intf);
 			usb_stor_dbg(us, "working scsi, ret=%d\n", ret);
 		}
diff --git a/drivers/usb/typec/tcpm/tcpm.c b/drivers/usb/typec/tcpm/tcpm.c
index 0f62db091d8d..a2233d72ae7c 100644
--- a/drivers/usb/typec/tcpm/tcpm.c
+++ b/drivers/usb/typec/tcpm/tcpm.c
@@ -37,6 +37,7 @@
 	S(SRC_ATTACHED),			\
 	S(SRC_STARTUP),				\
 	S(SRC_SEND_CAPABILITIES),		\
+	S(SRC_SEND_CAPABILITIES_TIMEOUT),	\
 	S(SRC_NEGOTIATE_CAPABILITIES),		\
 	S(SRC_TRANSITION_SUPPLY),		\
 	S(SRC_READY),				\
@@ -2966,10 +2967,34 @@ static void run_state_machine(struct tcpm_port *port)
 			/* port->hard_reset_count = 0; */
 			port->caps_count = 0;
 			port->pd_capable = true;
-			tcpm_set_state_cond(port, hard_reset_state(port),
+			tcpm_set_state_cond(port, SRC_SEND_CAPABILITIES_TIMEOUT,
 					    PD_T_SEND_SOURCE_CAP);
 		}
 		break;
+	case SRC_SEND_CAPABILITIES_TIMEOUT:
+		/*
+		 * Error recovery for a PD_DATA_SOURCE_CAP reply timeout.
+		 *
+		 * PD 2.0 sinks are supposed to accept src-capabilities with a
+		 * 3.0 header and simply ignore any src PDOs which the sink does
+		 * not understand such as PPS but some 2.0 sinks instead ignore
+		 * the entire PD_DATA_SOURCE_CAP message, causing contract
+		 * negotiation to fail.
+		 *
+		 * After PD_N_HARD_RESET_COUNT hard-reset attempts, we try
+		 * sending src-capabilities with a lower PD revision to
+		 * make these broken sinks work.
+		 */
+		if (port->hard_reset_count < PD_N_HARD_RESET_COUNT) {
+			tcpm_set_state(port, HARD_RESET_SEND, 0);
+		} else if (port->negotiated_rev > PD_REV20) {
+			port->negotiated_rev--;
+			port->hard_reset_count = 0;
+			tcpm_set_state(port, SRC_SEND_CAPABILITIES, 0);
+		} else {
+			tcpm_set_state(port, hard_reset_state(port), 0);
+		}
+		break;
 	case SRC_NEGOTIATE_CAPABILITIES:
 		ret = tcpm_pd_check_request(port);
 		if (ret < 0) {
diff --git a/drivers/usb/typec/tcpm/wcove.c b/drivers/usb/typec/tcpm/wcove.c
index 423208e19383..6770afd40765 100644
--- a/drivers/usb/typec/tcpm/wcove.c
+++ b/drivers/usb/typec/tcpm/wcove.c
@@ -615,8 +615,13 @@ static int wcove_typec_probe(struct platform_device *pdev)
 	wcove->dev = &pdev->dev;
 	wcove->regmap = pmic->regmap;
 
-	irq = regmap_irq_get_virq(pmic->irq_chip_data_chgr,
-				  platform_get_irq(pdev, 0));
+	irq = platform_get_irq(pdev, 0);
+	if (irq < 0) {
+		dev_err(&pdev->dev, "Failed to get IRQ: %d\n", irq);
+		return irq;
+	}
+
+	irq = regmap_irq_get_virq(pmic->irq_chip_data_chgr, irq);
 	if (irq < 0)
 		return irq;
 
diff --git a/drivers/usb/usbip/stub_rx.c b/drivers/usb/usbip/stub_rx.c
index 97b09a42a10c..dbfb2f24d71e 100644
--- a/drivers/usb/usbip/stub_rx.c
+++ b/drivers/usb/usbip/stub_rx.c
@@ -361,16 +361,10 @@ static int get_pipe(struct stub_device *sdev, struct usbip_header *pdu)
 	}
 
 	if (usb_endpoint_xfer_isoc(epd)) {
-		/* validate packet size and number of packets */
-		unsigned int maxp, packets, bytes;
-
-		maxp = usb_endpoint_maxp(epd);
-		maxp *= usb_endpoint_maxp_mult(epd);
-		bytes = pdu->u.cmd_submit.transfer_buffer_length;
-		packets = DIV_ROUND_UP(bytes, maxp);
-
+		/* validate number of packets */
 		if (pdu->u.cmd_submit.number_of_packets < 0 ||
-		    pdu->u.cmd_submit.number_of_packets > packets) {
+		    pdu->u.cmd_submit.number_of_packets >
+		    USBIP_MAX_ISO_PACKETS) {
 			dev_err(&sdev->udev->dev,
 				"CMD_SUBMIT: isoc invalid num packets %d\n",
 				pdu->u.cmd_submit.number_of_packets);
diff --git a/drivers/usb/usbip/usbip_common.h b/drivers/usb/usbip/usbip_common.h
index bf8afe9b5883..8be857a4fa13 100644
--- a/drivers/usb/usbip/usbip_common.h
+++ b/drivers/usb/usbip/usbip_common.h
@@ -121,6 +121,13 @@ extern struct device_attribute dev_attr_usbip_debug;
 #define USBIP_DIR_OUT	0x00
 #define USBIP_DIR_IN	0x01
 
+/*
+ * Arbitrary limit for the maximum number of isochronous packets in an URB,
+ * compare for example the uhci_submit_isochronous function in
+ * drivers/usb/host/uhci-q.c
+ */
+#define USBIP_MAX_ISO_PACKETS 1024
+
 /**
  * struct usbip_header_basic - data pertinent to every request
  * @command: the usbip request type
diff --git a/drivers/vfio/pci/vfio_pci.c b/drivers/vfio/pci/vfio_pci.c
index a25659b5a5d1..3fa20e95a6bb 100644
--- a/drivers/vfio/pci/vfio_pci.c
+++ b/drivers/vfio/pci/vfio_pci.c
@@ -1661,11 +1661,11 @@ static void __init vfio_pci_fill_ids(void)
 		rc = pci_add_dynid(&vfio_pci_driver, vendor, device,
 				   subvendor, subdevice, class, class_mask, 0);
 		if (rc)
-			pr_warn("failed to add dynamic id [%04hx:%04hx[%04hx:%04hx]] class %#08x/%08x (%d)\n",
+			pr_warn("failed to add dynamic id [%04x:%04x[%04x:%04x]] class %#08x/%08x (%d)\n",
 				vendor, device, subvendor, subdevice,
 				class, class_mask, rc);
 		else
-			pr_info("add [%04hx:%04hx[%04hx:%04hx]] class %#08x/%08x\n",
+			pr_info("add [%04x:%04x[%04x:%04x]] class %#08x/%08x\n",
 				vendor, device, subvendor, subdevice,
 				class, class_mask);
 	}
diff --git a/drivers/vfio/vfio_iommu_spapr_tce.c b/drivers/vfio/vfio_iommu_spapr_tce.c
index 8dbb270998f4..6b64e45a5269 100644
--- a/drivers/vfio/vfio_iommu_spapr_tce.c
+++ b/drivers/vfio/vfio_iommu_spapr_tce.c
@@ -1398,7 +1398,7 @@ unlock_exit:
 	mutex_unlock(&container->lock);
 }
 
-const struct vfio_iommu_driver_ops tce_iommu_driver_ops = {
+static const struct vfio_iommu_driver_ops tce_iommu_driver_ops = {
 	.name		= "iommu-vfio-powerpc",
 	.owner		= THIS_MODULE,
 	.open		= tce_iommu_open,
diff --git a/drivers/vfio/vfio_iommu_type1.c b/drivers/vfio/vfio_iommu_type1.c
index 73652e21efec..d0f731c9920a 100644
--- a/drivers/vfio/vfio_iommu_type1.c
+++ b/drivers/vfio/vfio_iommu_type1.c
@@ -58,12 +58,18 @@ module_param_named(disable_hugepages,
 MODULE_PARM_DESC(disable_hugepages,
 		 "Disable VFIO IOMMU support for IOMMU hugepages.");
 
+static unsigned int dma_entry_limit __read_mostly = U16_MAX;
+module_param_named(dma_entry_limit, dma_entry_limit, uint, 0644);
+MODULE_PARM_DESC(dma_entry_limit,
+		 "Maximum number of user DMA mappings per container (65535).");
+
 struct vfio_iommu {
 	struct list_head	domain_list;
 	struct vfio_domain	*external_domain; /* domain for external user */
 	struct mutex		lock;
 	struct rb_root		dma_list;
 	struct blocking_notifier_head notifier;
+	unsigned int		dma_avail;
 	bool			v2;
 	bool			nesting;
 };
@@ -836,6 +842,7 @@ static void vfio_remove_dma(struct vfio_iommu *iommu, struct vfio_dma *dma)
 	vfio_unlink_dma(iommu, dma);
 	put_task_struct(dma->task);
 	kfree(dma);
+	iommu->dma_avail++;
 }
 
 static unsigned long vfio_pgsize_bitmap(struct vfio_iommu *iommu)
@@ -1081,12 +1088,18 @@ static int vfio_dma_do_map(struct vfio_iommu *iommu,
 		goto out_unlock;
 	}
 
+	if (!iommu->dma_avail) {
+		ret = -ENOSPC;
+		goto out_unlock;
+	}
+
 	dma = kzalloc(sizeof(*dma), GFP_KERNEL);
 	if (!dma) {
 		ret = -ENOMEM;
 		goto out_unlock;
 	}
 
+	iommu->dma_avail--;
 	dma->iova = iova;
 	dma->vaddr = vaddr;
 	dma->prot = prot;
@@ -1583,6 +1596,7 @@ static void *vfio_iommu_type1_open(unsigned long arg)
 
 	INIT_LIST_HEAD(&iommu->domain_list);
 	iommu->dma_list = RB_ROOT;
+	iommu->dma_avail = dma_entry_limit;
 	mutex_init(&iommu->lock);
 	BLOCKING_INIT_NOTIFIER_HEAD(&iommu->notifier);
 
diff --git a/drivers/vhost/vhost.c b/drivers/vhost/vhost.c
index 5ace833de746..351af88231ad 100644
--- a/drivers/vhost/vhost.c
+++ b/drivers/vhost/vhost.c
@@ -911,8 +911,12 @@ static int vhost_new_umem_range(struct vhost_umem *umem,
 				u64 start, u64 size, u64 end,
 				u64 userspace_addr, int perm)
 {
-	struct vhost_umem_node *tmp, *node = kmalloc(sizeof(*node), GFP_ATOMIC);
+	struct vhost_umem_node *tmp, *node;
 
+	if (!size)
+		return -EFAULT;
+
+	node = kmalloc(sizeof(*node), GFP_ATOMIC);
 	if (!node)
 		return -ENOMEM;
 
diff --git a/drivers/video/fbdev/efifb.c b/drivers/video/fbdev/efifb.c
index ba906876cc45..9e529cc2b4ff 100644
--- a/drivers/video/fbdev/efifb.c
+++ b/drivers/video/fbdev/efifb.c
@@ -464,7 +464,8 @@ static int efifb_probe(struct platform_device *dev)
 	info->apertures->ranges[0].base = efifb_fix.smem_start;
 	info->apertures->ranges[0].size = size_remap;
 
-	if (!efi_mem_desc_lookup(efifb_fix.smem_start, &md)) {
+	if (efi_enabled(EFI_BOOT) &&
+	    !efi_mem_desc_lookup(efifb_fix.smem_start, &md)) {
 		if ((efifb_fix.smem_start + efifb_fix.smem_len) >
 		    (md.phys_addr + (md.num_pages << EFI_PAGE_SHIFT))) {
 			pr_err("efifb: video memory @ 0x%lx spans multiple EFI memory regions\n",
diff --git a/drivers/virt/vboxguest/vboxguest_core.c b/drivers/virt/vboxguest/vboxguest_core.c
index df7d09409efe..8ca333f21292 100644
--- a/drivers/virt/vboxguest/vboxguest_core.c
+++ b/drivers/virt/vboxguest/vboxguest_core.c
@@ -27,6 +27,10 @@
 
 #define GUEST_MAPPINGS_TRIES	5
 
+#define VBG_KERNEL_REQUEST \
+	(VMMDEV_REQUESTOR_KERNEL | VMMDEV_REQUESTOR_USR_DRV | \
+	 VMMDEV_REQUESTOR_CON_DONT_KNOW | VMMDEV_REQUESTOR_TRUST_NOT_GIVEN)
+
 /**
  * Reserves memory in which the VMM can relocate any guest mappings
  * that are floating around.
@@ -48,7 +52,8 @@ static void vbg_guest_mappings_init(struct vbg_dev *gdev)
 	int i, rc;
 
 	/* Query the required space. */
-	req = vbg_req_alloc(sizeof(*req), VMMDEVREQ_GET_HYPERVISOR_INFO);
+	req = vbg_req_alloc(sizeof(*req), VMMDEVREQ_GET_HYPERVISOR_INFO,
+			    VBG_KERNEL_REQUEST);
 	if (!req)
 		return;
 
@@ -135,7 +140,8 @@ static void vbg_guest_mappings_exit(struct vbg_dev *gdev)
 	 * Tell the host that we're going to free the memory we reserved for
 	 * it, the free it up. (Leak the memory if anything goes wrong here.)
 	 */
-	req = vbg_req_alloc(sizeof(*req), VMMDEVREQ_SET_HYPERVISOR_INFO);
+	req = vbg_req_alloc(sizeof(*req), VMMDEVREQ_SET_HYPERVISOR_INFO,
+			    VBG_KERNEL_REQUEST);
 	if (!req)
 		return;
 
@@ -172,8 +178,10 @@ static int vbg_report_guest_info(struct vbg_dev *gdev)
 	struct vmmdev_guest_info2 *req2 = NULL;
 	int rc, ret = -ENOMEM;
 
-	req1 = vbg_req_alloc(sizeof(*req1), VMMDEVREQ_REPORT_GUEST_INFO);
-	req2 = vbg_req_alloc(sizeof(*req2), VMMDEVREQ_REPORT_GUEST_INFO2);
+	req1 = vbg_req_alloc(sizeof(*req1), VMMDEVREQ_REPORT_GUEST_INFO,
+			     VBG_KERNEL_REQUEST);
+	req2 = vbg_req_alloc(sizeof(*req2), VMMDEVREQ_REPORT_GUEST_INFO2,
+			     VBG_KERNEL_REQUEST);
 	if (!req1 || !req2)
 		goto out_free;
 
@@ -187,8 +195,8 @@ static int vbg_report_guest_info(struct vbg_dev *gdev)
 	req2->additions_minor = VBG_VERSION_MINOR;
 	req2->additions_build = VBG_VERSION_BUILD;
 	req2->additions_revision = VBG_SVN_REV;
-	/* (no features defined yet) */
-	req2->additions_features = 0;
+	req2->additions_features =
+		VMMDEV_GUEST_INFO2_ADDITIONS_FEATURES_REQUESTOR_INFO;
 	strlcpy(req2->name, VBG_VERSION_STRING,
 		sizeof(req2->name));
 
@@ -230,7 +238,8 @@ static int vbg_report_driver_status(struct vbg_dev *gdev, bool active)
 	struct vmmdev_guest_status *req;
 	int rc;
 
-	req = vbg_req_alloc(sizeof(*req), VMMDEVREQ_REPORT_GUEST_STATUS);
+	req = vbg_req_alloc(sizeof(*req), VMMDEVREQ_REPORT_GUEST_STATUS,
+			    VBG_KERNEL_REQUEST);
 	if (!req)
 		return -ENOMEM;
 
@@ -423,7 +432,8 @@ static int vbg_heartbeat_host_config(struct vbg_dev *gdev, bool enabled)
 	struct vmmdev_heartbeat *req;
 	int rc;
 
-	req = vbg_req_alloc(sizeof(*req), VMMDEVREQ_HEARTBEAT_CONFIGURE);
+	req = vbg_req_alloc(sizeof(*req), VMMDEVREQ_HEARTBEAT_CONFIGURE,
+			    VBG_KERNEL_REQUEST);
 	if (!req)
 		return -ENOMEM;
 
@@ -457,7 +467,8 @@ static int vbg_heartbeat_init(struct vbg_dev *gdev)
 
 	gdev->guest_heartbeat_req = vbg_req_alloc(
 					sizeof(*gdev->guest_heartbeat_req),
-					VMMDEVREQ_GUEST_HEARTBEAT);
+					VMMDEVREQ_GUEST_HEARTBEAT,
+					VBG_KERNEL_REQUEST);
 	if (!gdev->guest_heartbeat_req)
 		return -ENOMEM;
 
@@ -528,7 +539,8 @@ static int vbg_reset_host_event_filter(struct vbg_dev *gdev,
 	struct vmmdev_mask *req;
 	int rc;
 
-	req = vbg_req_alloc(sizeof(*req), VMMDEVREQ_CTL_GUEST_FILTER_MASK);
+	req = vbg_req_alloc(sizeof(*req), VMMDEVREQ_CTL_GUEST_FILTER_MASK,
+			    VBG_KERNEL_REQUEST);
 	if (!req)
 		return -ENOMEM;
 
@@ -567,8 +579,14 @@ static int vbg_set_session_event_filter(struct vbg_dev *gdev,
 	u32 changed, previous;
 	int rc, ret = 0;
 
-	/* Allocate a request buffer before taking the spinlock */
-	req = vbg_req_alloc(sizeof(*req), VMMDEVREQ_CTL_GUEST_FILTER_MASK);
+	/*
+	 * Allocate a request buffer before taking the spinlock, when
+	 * the session is being terminated the requestor is the kernel,
+	 * as we're cleaning up.
+	 */
+	req = vbg_req_alloc(sizeof(*req), VMMDEVREQ_CTL_GUEST_FILTER_MASK,
+			    session_termination ? VBG_KERNEL_REQUEST :
+						  session->requestor);
 	if (!req) {
 		if (!session_termination)
 			return -ENOMEM;
@@ -627,7 +645,8 @@ static int vbg_reset_host_capabilities(struct vbg_dev *gdev)
 	struct vmmdev_mask *req;
 	int rc;
 
-	req = vbg_req_alloc(sizeof(*req), VMMDEVREQ_SET_GUEST_CAPABILITIES);
+	req = vbg_req_alloc(sizeof(*req), VMMDEVREQ_SET_GUEST_CAPABILITIES,
+			    VBG_KERNEL_REQUEST);
 	if (!req)
 		return -ENOMEM;
 
@@ -662,8 +681,14 @@ static int vbg_set_session_capabilities(struct vbg_dev *gdev,
 	u32 changed, previous;
 	int rc, ret = 0;
 
-	/* Allocate a request buffer before taking the spinlock */
-	req = vbg_req_alloc(sizeof(*req), VMMDEVREQ_SET_GUEST_CAPABILITIES);
+	/*
+	 * Allocate a request buffer before taking the spinlock, when
+	 * the session is being terminated the requestor is the kernel,
+	 * as we're cleaning up.
+	 */
+	req = vbg_req_alloc(sizeof(*req), VMMDEVREQ_SET_GUEST_CAPABILITIES,
+			    session_termination ? VBG_KERNEL_REQUEST :
+						  session->requestor);
 	if (!req) {
 		if (!session_termination)
 			return -ENOMEM;
@@ -722,7 +747,8 @@ static int vbg_query_host_version(struct vbg_dev *gdev)
 	struct vmmdev_host_version *req;
 	int rc, ret;
 
-	req = vbg_req_alloc(sizeof(*req), VMMDEVREQ_GET_HOST_VERSION);
+	req = vbg_req_alloc(sizeof(*req), VMMDEVREQ_GET_HOST_VERSION,
+			    VBG_KERNEL_REQUEST);
 	if (!req)
 		return -ENOMEM;
 
@@ -783,19 +809,24 @@ int vbg_core_init(struct vbg_dev *gdev, u32 fixed_events)
 
 	gdev->mem_balloon.get_req =
 		vbg_req_alloc(sizeof(*gdev->mem_balloon.get_req),
-			      VMMDEVREQ_GET_MEMBALLOON_CHANGE_REQ);
+			      VMMDEVREQ_GET_MEMBALLOON_CHANGE_REQ,
+			      VBG_KERNEL_REQUEST);
 	gdev->mem_balloon.change_req =
 		vbg_req_alloc(sizeof(*gdev->mem_balloon.change_req),
-			      VMMDEVREQ_CHANGE_MEMBALLOON);
+			      VMMDEVREQ_CHANGE_MEMBALLOON,
+			      VBG_KERNEL_REQUEST);
 	gdev->cancel_req =
 		vbg_req_alloc(sizeof(*(gdev->cancel_req)),
-			      VMMDEVREQ_HGCM_CANCEL2);
+			      VMMDEVREQ_HGCM_CANCEL2,
+			      VBG_KERNEL_REQUEST);
 	gdev->ack_events_req =
 		vbg_req_alloc(sizeof(*gdev->ack_events_req),
-			      VMMDEVREQ_ACKNOWLEDGE_EVENTS);
+			      VMMDEVREQ_ACKNOWLEDGE_EVENTS,
+			      VBG_KERNEL_REQUEST);
 	gdev->mouse_status_req =
 		vbg_req_alloc(sizeof(*gdev->mouse_status_req),
-			      VMMDEVREQ_GET_MOUSE_STATUS);
+			      VMMDEVREQ_GET_MOUSE_STATUS,
+			      VBG_KERNEL_REQUEST);
 
 	if (!gdev->mem_balloon.get_req || !gdev->mem_balloon.change_req ||
 	    !gdev->cancel_req || !gdev->ack_events_req ||
@@ -892,9 +923,9 @@ void vbg_core_exit(struct vbg_dev *gdev)
  * vboxguest_linux.c calls this when userspace opens the char-device.
  * Return: A pointer to the new session or an ERR_PTR on error.
  * @gdev:		The Guest extension device.
- * @user:		Set if this is a session for the vboxuser device.
+ * @requestor:		VMMDEV_REQUESTOR_* flags
  */
-struct vbg_session *vbg_core_open_session(struct vbg_dev *gdev, bool user)
+struct vbg_session *vbg_core_open_session(struct vbg_dev *gdev, u32 requestor)
 {
 	struct vbg_session *session;
 
@@ -903,7 +934,7 @@ struct vbg_session *vbg_core_open_session(struct vbg_dev *gdev, bool user)
 		return ERR_PTR(-ENOMEM);
 
 	session->gdev = gdev;
-	session->user_session = user;
+	session->requestor = requestor;
 
 	return session;
 }
@@ -924,7 +955,9 @@ void vbg_core_close_session(struct vbg_session *session)
 		if (!session->hgcm_client_ids[i])
 			continue;
 
-		vbg_hgcm_disconnect(gdev, session->hgcm_client_ids[i], &rc);
+		/* requestor is kernel here, as we're cleaning up. */
+		vbg_hgcm_disconnect(gdev, VBG_KERNEL_REQUEST,
+				    session->hgcm_client_ids[i], &rc);
 	}
 
 	kfree(session);
@@ -1152,7 +1185,8 @@ static int vbg_req_allowed(struct vbg_dev *gdev, struct vbg_session *session,
 		return -EPERM;
 	}
 
-	if (trusted_apps_only && session->user_session) {
+	if (trusted_apps_only &&
+	    (session->requestor & VMMDEV_REQUESTOR_USER_DEVICE)) {
 		vbg_err("Denying userspace vmm call type %#08x through vboxuser device node\n",
 			req->request_type);
 		return -EPERM;
@@ -1209,8 +1243,8 @@ static int vbg_ioctl_hgcm_connect(struct vbg_dev *gdev,
 	if (i >= ARRAY_SIZE(session->hgcm_client_ids))
 		return -EMFILE;
 
-	ret = vbg_hgcm_connect(gdev, &conn->u.in.loc, &client_id,
-			       &conn->hdr.rc);
+	ret = vbg_hgcm_connect(gdev, session->requestor, &conn->u.in.loc,
+			       &client_id, &conn->hdr.rc);
 
 	mutex_lock(&gdev->session_mutex);
 	if (ret == 0 && conn->hdr.rc >= 0) {
@@ -1251,7 +1285,8 @@ static int vbg_ioctl_hgcm_disconnect(struct vbg_dev *gdev,
 	if (i >= ARRAY_SIZE(session->hgcm_client_ids))
 		return -EINVAL;
 
-	ret = vbg_hgcm_disconnect(gdev, client_id, &disconn->hdr.rc);
+	ret = vbg_hgcm_disconnect(gdev, session->requestor, client_id,
+				  &disconn->hdr.rc);
 
 	mutex_lock(&gdev->session_mutex);
 	if (ret == 0 && disconn->hdr.rc >= 0)
@@ -1313,12 +1348,12 @@ static int vbg_ioctl_hgcm_call(struct vbg_dev *gdev,
 	}
 
 	if (IS_ENABLED(CONFIG_COMPAT) && f32bit)
-		ret = vbg_hgcm_call32(gdev, client_id,
+		ret = vbg_hgcm_call32(gdev, session->requestor, client_id,
 				      call->function, call->timeout_ms,
 				      VBG_IOCTL_HGCM_CALL_PARMS32(call),
 				      call->parm_count, &call->hdr.rc);
 	else
-		ret = vbg_hgcm_call(gdev, client_id,
+		ret = vbg_hgcm_call(gdev, session->requestor, client_id,
 				    call->function, call->timeout_ms,
 				    VBG_IOCTL_HGCM_CALL_PARMS(call),
 				    call->parm_count, &call->hdr.rc);
@@ -1408,6 +1443,7 @@ static int vbg_ioctl_check_balloon(struct vbg_dev *gdev,
 }
 
 static int vbg_ioctl_write_core_dump(struct vbg_dev *gdev,
+				     struct vbg_session *session,
 				     struct vbg_ioctl_write_coredump *dump)
 {
 	struct vmmdev_write_core_dump *req;
@@ -1415,7 +1451,8 @@ static int vbg_ioctl_write_core_dump(struct vbg_dev *gdev,
 	if (vbg_ioctl_chk(&dump->hdr, sizeof(dump->u.in), 0))
 		return -EINVAL;
 
-	req = vbg_req_alloc(sizeof(*req), VMMDEVREQ_WRITE_COREDUMP);
+	req = vbg_req_alloc(sizeof(*req), VMMDEVREQ_WRITE_COREDUMP,
+			    session->requestor);
 	if (!req)
 		return -ENOMEM;
 
@@ -1476,7 +1513,7 @@ int vbg_core_ioctl(struct vbg_session *session, unsigned int req, void *data)
 	case VBG_IOCTL_CHECK_BALLOON:
 		return vbg_ioctl_check_balloon(gdev, data);
 	case VBG_IOCTL_WRITE_CORE_DUMP:
-		return vbg_ioctl_write_core_dump(gdev, data);
+		return vbg_ioctl_write_core_dump(gdev, session, data);
 	}
 
 	/* Variable sized requests. */
@@ -1508,7 +1545,8 @@ int vbg_core_set_mouse_status(struct vbg_dev *gdev, u32 features)
 	struct vmmdev_mouse_status *req;
 	int rc;
 
-	req = vbg_req_alloc(sizeof(*req), VMMDEVREQ_SET_MOUSE_STATUS);
+	req = vbg_req_alloc(sizeof(*req), VMMDEVREQ_SET_MOUSE_STATUS,
+			    VBG_KERNEL_REQUEST);
 	if (!req)
 		return -ENOMEM;
 
diff --git a/drivers/virt/vboxguest/vboxguest_core.h b/drivers/virt/vboxguest/vboxguest_core.h
index 7ad9ec45bfa9..4188c12b839f 100644
--- a/drivers/virt/vboxguest/vboxguest_core.h
+++ b/drivers/virt/vboxguest/vboxguest_core.h
@@ -154,15 +154,15 @@ struct vbg_session {
 	 * host. Protected by vbg_gdev.session_mutex.
 	 */
 	u32 guest_caps;
-	/** Does this session belong to a root process or a user one? */
-	bool user_session;
+	/** VMMDEV_REQUESTOR_* flags */
+	u32 requestor;
 	/** Set on CANCEL_ALL_WAITEVENTS, protected by vbg_devevent_spinlock. */
 	bool cancel_waiters;
 };
 
 int  vbg_core_init(struct vbg_dev *gdev, u32 fixed_events);
 void vbg_core_exit(struct vbg_dev *gdev);
-struct vbg_session *vbg_core_open_session(struct vbg_dev *gdev, bool user);
+struct vbg_session *vbg_core_open_session(struct vbg_dev *gdev, u32 requestor);
 void vbg_core_close_session(struct vbg_session *session);
 int  vbg_core_ioctl(struct vbg_session *session, unsigned int req, void *data);
 int  vbg_core_set_mouse_status(struct vbg_dev *gdev, u32 features);
@@ -172,12 +172,13 @@ irqreturn_t vbg_core_isr(int irq, void *dev_id);
 void vbg_linux_mouse_event(struct vbg_dev *gdev);
 
 /* Private (non exported) functions form vboxguest_utils.c */
-void *vbg_req_alloc(size_t len, enum vmmdev_request_type req_type);
+void *vbg_req_alloc(size_t len, enum vmmdev_request_type req_type,
+		    u32 requestor);
 void vbg_req_free(void *req, size_t len);
 int vbg_req_perform(struct vbg_dev *gdev, void *req);
 int vbg_hgcm_call32(
-	struct vbg_dev *gdev, u32 client_id, u32 function, u32 timeout_ms,
-	struct vmmdev_hgcm_function_parameter32 *parm32, u32 parm_count,
-	int *vbox_status);
+	struct vbg_dev *gdev, u32 requestor, u32 client_id, u32 function,
+	u32 timeout_ms, struct vmmdev_hgcm_function_parameter32 *parm32,
+	u32 parm_count, int *vbox_status);
 
 #endif
diff --git a/drivers/virt/vboxguest/vboxguest_linux.c b/drivers/virt/vboxguest/vboxguest_linux.c
index 6e2a9619192d..6e8c0f1c1056 100644
--- a/drivers/virt/vboxguest/vboxguest_linux.c
+++ b/drivers/virt/vboxguest/vboxguest_linux.c
@@ -5,6 +5,7 @@
  * Copyright (C) 2006-2016 Oracle Corporation
  */
 
+#include <linux/cred.h>
 #include <linux/input.h>
 #include <linux/kernel.h>
 #include <linux/miscdevice.h>
@@ -28,6 +29,23 @@ static DEFINE_MUTEX(vbg_gdev_mutex);
 /** Global vbg_gdev pointer used by vbg_get/put_gdev. */
 static struct vbg_dev *vbg_gdev;
 
+static u32 vbg_misc_device_requestor(struct inode *inode)
+{
+	u32 requestor = VMMDEV_REQUESTOR_USERMODE |
+			VMMDEV_REQUESTOR_CON_DONT_KNOW |
+			VMMDEV_REQUESTOR_TRUST_NOT_GIVEN;
+
+	if (from_kuid(current_user_ns(), current->cred->uid) == 0)
+		requestor |= VMMDEV_REQUESTOR_USR_ROOT;
+	else
+		requestor |= VMMDEV_REQUESTOR_USR_USER;
+
+	if (in_egroup_p(inode->i_gid))
+		requestor |= VMMDEV_REQUESTOR_GRP_VBOX;
+
+	return requestor;
+}
+
 static int vbg_misc_device_open(struct inode *inode, struct file *filp)
 {
 	struct vbg_session *session;
@@ -36,7 +54,7 @@ static int vbg_misc_device_open(struct inode *inode, struct file *filp)
 	/* misc_open sets filp->private_data to our misc device */
 	gdev = container_of(filp->private_data, struct vbg_dev, misc_device);
 
-	session = vbg_core_open_session(gdev, false);
+	session = vbg_core_open_session(gdev, vbg_misc_device_requestor(inode));
 	if (IS_ERR(session))
 		return PTR_ERR(session);
 
@@ -53,7 +71,8 @@ static int vbg_misc_device_user_open(struct inode *inode, struct file *filp)
 	gdev = container_of(filp->private_data, struct vbg_dev,
 			    misc_device_user);
 
-	session = vbg_core_open_session(gdev, false);
+	session = vbg_core_open_session(gdev, vbg_misc_device_requestor(inode) |
+					      VMMDEV_REQUESTOR_USER_DEVICE);
 	if (IS_ERR(session))
 		return PTR_ERR(session);
 
@@ -115,7 +134,8 @@ static long vbg_misc_device_ioctl(struct file *filp, unsigned int req,
 			 req == VBG_IOCTL_VMMDEV_REQUEST_BIG;
 
 	if (is_vmmdev_req)
-		buf = vbg_req_alloc(size, VBG_IOCTL_HDR_TYPE_DEFAULT);
+		buf = vbg_req_alloc(size, VBG_IOCTL_HDR_TYPE_DEFAULT,
+				    session->requestor);
 	else
 		buf = kmalloc(size, GFP_KERNEL);
 	if (!buf)
diff --git a/drivers/virt/vboxguest/vboxguest_utils.c b/drivers/virt/vboxguest/vboxguest_utils.c
index bf4474214b4d..75fd140b02ff 100644
--- a/drivers/virt/vboxguest/vboxguest_utils.c
+++ b/drivers/virt/vboxguest/vboxguest_utils.c
@@ -62,7 +62,8 @@ VBG_LOG(vbg_err, pr_err);
 VBG_LOG(vbg_debug, pr_debug);
 #endif
 
-void *vbg_req_alloc(size_t len, enum vmmdev_request_type req_type)
+void *vbg_req_alloc(size_t len, enum vmmdev_request_type req_type,
+		    u32 requestor)
 {
 	struct vmmdev_request_header *req;
 	int order = get_order(PAGE_ALIGN(len));
@@ -78,7 +79,7 @@ void *vbg_req_alloc(size_t len, enum vmmdev_request_type req_type)
 	req->request_type = req_type;
 	req->rc = VERR_GENERAL_FAILURE;
 	req->reserved1 = 0;
-	req->reserved2 = 0;
+	req->requestor = requestor;
 
 	return req;
 }
@@ -119,7 +120,7 @@ static bool hgcm_req_done(struct vbg_dev *gdev,
 	return done;
 }
 
-int vbg_hgcm_connect(struct vbg_dev *gdev,
+int vbg_hgcm_connect(struct vbg_dev *gdev, u32 requestor,
 		     struct vmmdev_hgcm_service_location *loc,
 		     u32 *client_id, int *vbox_status)
 {
@@ -127,7 +128,7 @@ int vbg_hgcm_connect(struct vbg_dev *gdev,
 	int rc;
 
 	hgcm_connect = vbg_req_alloc(sizeof(*hgcm_connect),
-				     VMMDEVREQ_HGCM_CONNECT);
+				     VMMDEVREQ_HGCM_CONNECT, requestor);
 	if (!hgcm_connect)
 		return -ENOMEM;
 
@@ -153,13 +154,15 @@ int vbg_hgcm_connect(struct vbg_dev *gdev,
 }
 EXPORT_SYMBOL(vbg_hgcm_connect);
 
-int vbg_hgcm_disconnect(struct vbg_dev *gdev, u32 client_id, int *vbox_status)
+int vbg_hgcm_disconnect(struct vbg_dev *gdev, u32 requestor,
+			u32 client_id, int *vbox_status)
 {
 	struct vmmdev_hgcm_disconnect *hgcm_disconnect = NULL;
 	int rc;
 
 	hgcm_disconnect = vbg_req_alloc(sizeof(*hgcm_disconnect),
-					VMMDEVREQ_HGCM_DISCONNECT);
+					VMMDEVREQ_HGCM_DISCONNECT,
+					requestor);
 	if (!hgcm_disconnect)
 		return -ENOMEM;
 
@@ -593,9 +596,10 @@ static int hgcm_call_copy_back_result(
 	return 0;
 }
 
-int vbg_hgcm_call(struct vbg_dev *gdev, u32 client_id, u32 function,
-		  u32 timeout_ms, struct vmmdev_hgcm_function_parameter *parms,
-		  u32 parm_count, int *vbox_status)
+int vbg_hgcm_call(struct vbg_dev *gdev, u32 requestor, u32 client_id,
+		  u32 function, u32 timeout_ms,
+		  struct vmmdev_hgcm_function_parameter *parms, u32 parm_count,
+		  int *vbox_status)
 {
 	struct vmmdev_hgcm_call *call;
 	void **bounce_bufs = NULL;
@@ -615,7 +619,7 @@ int vbg_hgcm_call(struct vbg_dev *gdev, u32 client_id, u32 function,
 		goto free_bounce_bufs;
 	}
 
-	call = vbg_req_alloc(size, VMMDEVREQ_HGCM_CALL);
+	call = vbg_req_alloc(size, VMMDEVREQ_HGCM_CALL, requestor);
 	if (!call) {
 		ret = -ENOMEM;
 		goto free_bounce_bufs;
@@ -647,9 +651,9 @@ EXPORT_SYMBOL(vbg_hgcm_call);
 
 #ifdef CONFIG_COMPAT
 int vbg_hgcm_call32(
-	struct vbg_dev *gdev, u32 client_id, u32 function, u32 timeout_ms,
-	struct vmmdev_hgcm_function_parameter32 *parm32, u32 parm_count,
-	int *vbox_status)
+	struct vbg_dev *gdev, u32 requestor, u32 client_id, u32 function,
+	u32 timeout_ms, struct vmmdev_hgcm_function_parameter32 *parm32,
+	u32 parm_count, int *vbox_status)
 {
 	struct vmmdev_hgcm_function_parameter *parm64 = NULL;
 	u32 i, size;
@@ -689,7 +693,7 @@ int vbg_hgcm_call32(
 			goto out_free;
 	}
 
-	ret = vbg_hgcm_call(gdev, client_id, function, timeout_ms,
+	ret = vbg_hgcm_call(gdev, requestor, client_id, function, timeout_ms,
 			    parm64, parm_count, vbox_status);
 	if (ret < 0)
 		goto out_free;
diff --git a/drivers/virt/vboxguest/vboxguest_version.h b/drivers/virt/vboxguest/vboxguest_version.h
index 77f0c8f8a231..84834dad38d5 100644
--- a/drivers/virt/vboxguest/vboxguest_version.h
+++ b/drivers/virt/vboxguest/vboxguest_version.h
@@ -9,11 +9,10 @@
 #ifndef __VBOX_VERSION_H__
 #define __VBOX_VERSION_H__
 
-/* Last synced October 4th 2017 */
-#define VBG_VERSION_MAJOR 5
-#define VBG_VERSION_MINOR 2
+#define VBG_VERSION_MAJOR 6
+#define VBG_VERSION_MINOR 0
 #define VBG_VERSION_BUILD 0
-#define VBG_SVN_REV 68940
-#define VBG_VERSION_STRING "5.2.0"
+#define VBG_SVN_REV 127566
+#define VBG_VERSION_STRING "6.0.0"
 
 #endif
diff --git a/drivers/virt/vboxguest/vmmdev.h b/drivers/virt/vboxguest/vmmdev.h
index 5e2ae978935d..6337b8d75d96 100644
--- a/drivers/virt/vboxguest/vmmdev.h
+++ b/drivers/virt/vboxguest/vmmdev.h
@@ -98,8 +98,8 @@ struct vmmdev_request_header {
 	s32 rc;
 	/** Reserved field no.1. MBZ. */
 	u32 reserved1;
-	/** Reserved field no.2. MBZ. */
-	u32 reserved2;
+	/** IN: Requestor information (VMMDEV_REQUESTOR_*) */
+	u32 requestor;
 };
 VMMDEV_ASSERT_SIZE(vmmdev_request_header, 24);
 
@@ -247,6 +247,8 @@ struct vmmdev_guest_info {
 };
 VMMDEV_ASSERT_SIZE(vmmdev_guest_info, 24 + 8);
 
+#define VMMDEV_GUEST_INFO2_ADDITIONS_FEATURES_REQUESTOR_INFO	BIT(0)
+
 /** struct vmmdev_guestinfo2 - Guest information report, version 2. */
 struct vmmdev_guest_info2 {
 	/** Header. */
@@ -259,7 +261,7 @@ struct vmmdev_guest_info2 {
 	u32 additions_build;
 	/** SVN revision. */
 	u32 additions_revision;
-	/** Feature mask, currently unused. */
+	/** Feature mask. */
 	u32 additions_features;
 	/**
 	 * The intentional meaning of this field was:
diff --git a/drivers/virtio/virtio_pci_common.c b/drivers/virtio/virtio_pci_common.c
index d0584c040c60..7a0398bb84f7 100644
--- a/drivers/virtio/virtio_pci_common.c
+++ b/drivers/virtio/virtio_pci_common.c
@@ -255,9 +255,11 @@ void vp_del_vqs(struct virtio_device *vdev)
 	for (i = 0; i < vp_dev->msix_used_vectors; ++i)
 		free_irq(pci_irq_vector(vp_dev->pci_dev, i), vp_dev);
 
-	for (i = 0; i < vp_dev->msix_vectors; i++)
-		if (vp_dev->msix_affinity_masks[i])
-			free_cpumask_var(vp_dev->msix_affinity_masks[i]);
+	if (vp_dev->msix_affinity_masks) {
+		for (i = 0; i < vp_dev->msix_vectors; i++)
+			if (vp_dev->msix_affinity_masks[i])
+				free_cpumask_var(vp_dev->msix_affinity_masks[i]);
+	}
 
 	if (vp_dev->msix_enabled) {
 		/* Disable the vector used for configuration */
diff --git a/drivers/virtio/virtio_ring.c b/drivers/virtio/virtio_ring.c
index 18846afb39da..5df92c308286 100644
--- a/drivers/virtio/virtio_ring.c
+++ b/drivers/virtio/virtio_ring.c
@@ -882,6 +882,8 @@ static struct virtqueue *vring_create_virtqueue_split(
 					  GFP_KERNEL|__GFP_NOWARN|__GFP_ZERO);
 		if (queue)
 			break;
+		if (!may_reduce_num)
+			return NULL;
 	}
 
 	if (!num)
diff --git a/drivers/w1/masters/ds2490.c b/drivers/w1/masters/ds2490.c
index 0f4ecfcdb549..a9fb77585272 100644
--- a/drivers/w1/masters/ds2490.c
+++ b/drivers/w1/masters/ds2490.c
@@ -1016,15 +1016,15 @@ static int ds_probe(struct usb_interface *intf,
 	/* alternative 3, 1ms interrupt (greatly speeds search), 64 byte bulk */
 	alt = 3;
 	err = usb_set_interface(dev->udev,
-		intf->altsetting[alt].desc.bInterfaceNumber, alt);
+		intf->cur_altsetting->desc.bInterfaceNumber, alt);
 	if (err) {
 		dev_err(&dev->udev->dev, "Failed to set alternative setting %d "
 			"for %d interface: err=%d.\n", alt,
-			intf->altsetting[alt].desc.bInterfaceNumber, err);
+			intf->cur_altsetting->desc.bInterfaceNumber, err);
 		goto err_out_clear;
 	}
 
-	iface_desc = &intf->altsetting[alt];
+	iface_desc = intf->cur_altsetting;
 	if (iface_desc->desc.bNumEndpoints != NUM_EP-1) {
 		pr_info("Num endpoints=%d. It is not DS9490R.\n",
 			iface_desc->desc.bNumEndpoints);
diff --git a/drivers/watchdog/sbsa_gwdt.c b/drivers/watchdog/sbsa_gwdt.c
index e8bd9887c566..e221e47396ab 100644
--- a/drivers/watchdog/sbsa_gwdt.c
+++ b/drivers/watchdog/sbsa_gwdt.c
@@ -161,7 +161,7 @@ static unsigned int sbsa_gwdt_get_timeleft(struct watchdog_device *wdd)
 		timeleft += readl(gwdt->control_base + SBSA_GWDT_WOR);
 
 	timeleft += lo_hi_readq(gwdt->control_base + SBSA_GWDT_WCV) -
-		    arch_counter_get_cntvct();
+		    arch_timer_read_counter();
 
 	do_div(timeleft, gwdt->clk);
 
diff --git a/drivers/xen/events/events_base.c b/drivers/xen/events/events_base.c
index 117e76b2f939..084e45882c73 100644
--- a/drivers/xen/events/events_base.c
+++ b/drivers/xen/events/events_base.c
@@ -1687,7 +1687,6 @@ void __init xen_init_IRQ(void)
 
 #ifdef CONFIG_X86
 	if (xen_pv_domain()) {
-		irq_ctx_init(smp_processor_id());
 		if (xen_initial_domain())
 			pci_xen_initial_domain();
 	}
diff --git a/drivers/xen/privcmd-buf.c b/drivers/xen/privcmd-buf.c
index de01a6d0059d..a1c61e351d3f 100644
--- a/drivers/xen/privcmd-buf.c
+++ b/drivers/xen/privcmd-buf.c
@@ -140,8 +140,7 @@ static int privcmd_buf_mmap(struct file *file, struct vm_area_struct *vma)
 	if (!(vma->vm_flags & VM_SHARED))
 		return -EINVAL;
 
-	vma_priv = kzalloc(sizeof(*vma_priv) + count * sizeof(void *),
-			   GFP_KERNEL);
+	vma_priv = kzalloc(struct_size(vma_priv, pages, count), GFP_KERNEL);
 	if (!vma_priv)
 		return -ENOMEM;
 
diff --git a/drivers/xen/xenbus/xenbus_dev_frontend.c b/drivers/xen/xenbus/xenbus_dev_frontend.c
index c3e201025ef0..0782ff3c2273 100644
--- a/drivers/xen/xenbus/xenbus_dev_frontend.c
+++ b/drivers/xen/xenbus/xenbus_dev_frontend.c
@@ -622,9 +622,7 @@ static int xenbus_file_open(struct inode *inode, struct file *filp)
 	if (xen_store_evtchn == 0)
 		return -ENOENT;
 
-	nonseekable_open(inode, filp);
-
-	filp->f_mode &= ~FMODE_ATOMIC_POS; /* cdev-style semantics */
+	stream_open(inode, filp);
 
 	u = kzalloc(sizeof(*u), GFP_KERNEL);
 	if (u == NULL)
diff --git a/fs/afs/callback.c b/fs/afs/callback.c
index 1c7955f5cdaf..128f2dbe256a 100644
--- a/fs/afs/callback.c
+++ b/fs/afs/callback.c
@@ -203,8 +203,7 @@ void afs_put_cb_interest(struct afs_net *net, struct afs_cb_interest *cbi)
  */
 void afs_init_callback_state(struct afs_server *server)
 {
-	if (!test_and_clear_bit(AFS_SERVER_FL_NEW, &server->flags))
-		server->cb_s_break++;
+	server->cb_s_break++;
 }
 
 /*
diff --git a/fs/afs/cmservice.c b/fs/afs/cmservice.c
index 8ee5972893ed..2f8acb4c556d 100644
--- a/fs/afs/cmservice.c
+++ b/fs/afs/cmservice.c
@@ -34,7 +34,7 @@ static void SRXAFSCB_TellMeAboutYourself(struct work_struct *);
 static int afs_deliver_yfs_cb_callback(struct afs_call *);
 
 #define CM_NAME(name) \
-	const char afs_SRXCB##name##_name[] __tracepoint_string =	\
+	char afs_SRXCB##name##_name[] __tracepoint_string =	\
 		"CB." #name
 
 /*
diff --git a/fs/afs/fsclient.c b/fs/afs/fsclient.c
index ca08c83168f5..0b37867b5c20 100644
--- a/fs/afs/fsclient.c
+++ b/fs/afs/fsclient.c
@@ -1515,8 +1515,8 @@ static int afs_fs_setattr_size64(struct afs_fs_cursor *fc, struct iattr *attr)
 
 	xdr_encode_AFS_StoreStatus(&bp, attr);
 
-	*bp++ = 0;				/* position of start of write */
-	*bp++ = 0;
+	*bp++ = htonl(attr->ia_size >> 32);	/* position of start of write */
+	*bp++ = htonl((u32) attr->ia_size);
 	*bp++ = 0;				/* size of write */
 	*bp++ = 0;
 	*bp++ = htonl(attr->ia_size >> 32);	/* new file length */
@@ -1564,7 +1564,7 @@ static int afs_fs_setattr_size(struct afs_fs_cursor *fc, struct iattr *attr)
 
 	xdr_encode_AFS_StoreStatus(&bp, attr);
 
-	*bp++ = 0;				/* position of start of write */
+	*bp++ = htonl(attr->ia_size);		/* position of start of write */
 	*bp++ = 0;				/* size of write */
 	*bp++ = htonl(attr->ia_size);		/* new file length */
 
diff --git a/fs/afs/inode.c b/fs/afs/inode.c
index 1a4ce07fb406..9cedc3fc1b77 100644
--- a/fs/afs/inode.c
+++ b/fs/afs/inode.c
@@ -216,9 +216,7 @@ struct inode *afs_iget_pseudo_dir(struct super_block *sb, bool root)
 	set_nlink(inode, 2);
 	inode->i_uid		= GLOBAL_ROOT_UID;
 	inode->i_gid		= GLOBAL_ROOT_GID;
-	inode->i_ctime.tv_sec	= get_seconds();
-	inode->i_ctime.tv_nsec	= 0;
-	inode->i_atime		= inode->i_mtime = inode->i_ctime;
+	inode->i_ctime = inode->i_atime = inode->i_mtime = current_time(inode);
 	inode->i_blocks		= 0;
 	inode_set_iversion_raw(inode, 0);
 	inode->i_generation	= 0;
diff --git a/fs/afs/internal.h b/fs/afs/internal.h
index bb1f244b2b3a..3904ab0b9563 100644
--- a/fs/afs/internal.h
+++ b/fs/afs/internal.h
@@ -474,7 +474,6 @@ struct afs_server {
 	time64_t		put_time;	/* Time at which last put */
 	time64_t		update_at;	/* Time at which to next update the record */
 	unsigned long		flags;
-#define AFS_SERVER_FL_NEW	0		/* New server, don't inc cb_s_break */
 #define AFS_SERVER_FL_NOT_READY	1		/* The record is not ready for use */
 #define AFS_SERVER_FL_NOT_FOUND	2		/* VL server says no such server */
 #define AFS_SERVER_FL_VL_FAIL	3		/* Failed to access VL server */
@@ -827,7 +826,7 @@ static inline struct afs_cb_interest *afs_get_cb_interest(struct afs_cb_interest
 
 static inline unsigned int afs_calc_vnode_cb_break(struct afs_vnode *vnode)
 {
-	return vnode->cb_break + vnode->cb_s_break + vnode->cb_v_break;
+	return vnode->cb_break + vnode->cb_v_break;
 }
 
 static inline bool afs_cb_is_broken(unsigned int cb_break,
@@ -835,7 +834,6 @@ static inline bool afs_cb_is_broken(unsigned int cb_break,
 				    const struct afs_cb_interest *cbi)
 {
 	return !cbi || cb_break != (vnode->cb_break +
-				    cbi->server->cb_s_break +
 				    vnode->volume->cb_v_break);
 }
 
diff --git a/fs/afs/rxrpc.c b/fs/afs/rxrpc.c
index 2c588f9bbbda..15c7e82d80cb 100644
--- a/fs/afs/rxrpc.c
+++ b/fs/afs/rxrpc.c
@@ -572,13 +572,17 @@ static void afs_deliver_to_call(struct afs_call *call)
 		case -ENODATA:
 		case -EBADMSG:
 		case -EMSGSIZE:
-		default:
 			abort_code = RXGEN_CC_UNMARSHAL;
 			if (state != AFS_CALL_CL_AWAIT_REPLY)
 				abort_code = RXGEN_SS_UNMARSHAL;
 			rxrpc_kernel_abort_call(call->net->socket, call->rxcall,
 						abort_code, ret, "KUM");
 			goto local_abort;
+		default:
+			abort_code = RX_USER_ABORT;
+			rxrpc_kernel_abort_call(call->net->socket, call->rxcall,
+						abort_code, ret, "KER");
+			goto local_abort;
 		}
 	}
 
@@ -610,6 +614,7 @@ static long afs_wait_for_call_to_complete(struct afs_call *call,
 	bool stalled = false;
 	u64 rtt;
 	u32 life, last_life;
+	bool rxrpc_complete = false;
 
 	DECLARE_WAITQUEUE(myself, current);
 
@@ -621,7 +626,7 @@ static long afs_wait_for_call_to_complete(struct afs_call *call,
 		rtt2 = 2;
 
 	timeout = rtt2;
-	last_life = rxrpc_kernel_check_life(call->net->socket, call->rxcall);
+	rxrpc_kernel_check_life(call->net->socket, call->rxcall, &last_life);
 
 	add_wait_queue(&call->waitq, &myself);
 	for (;;) {
@@ -639,7 +644,12 @@ static long afs_wait_for_call_to_complete(struct afs_call *call,
 		if (afs_check_call_state(call, AFS_CALL_COMPLETE))
 			break;
 
-		life = rxrpc_kernel_check_life(call->net->socket, call->rxcall);
+		if (!rxrpc_kernel_check_life(call->net->socket, call->rxcall, &life)) {
+			/* rxrpc terminated the call. */
+			rxrpc_complete = true;
+			break;
+		}
+
 		if (timeout == 0 &&
 		    life == last_life && signal_pending(current)) {
 			if (stalled)
@@ -663,12 +673,16 @@ static long afs_wait_for_call_to_complete(struct afs_call *call,
 	remove_wait_queue(&call->waitq, &myself);
 	__set_current_state(TASK_RUNNING);
 
-	/* Kill off the call if it's still live. */
 	if (!afs_check_call_state(call, AFS_CALL_COMPLETE)) {
-		_debug("call interrupted");
-		if (rxrpc_kernel_abort_call(call->net->socket, call->rxcall,
-					    RX_USER_ABORT, -EINTR, "KWI"))
-			afs_set_call_complete(call, -EINTR, 0);
+		if (rxrpc_complete) {
+			afs_set_call_complete(call, call->error, call->abort_code);
+		} else {
+			/* Kill off the call if it's still live. */
+			_debug("call interrupted");
+			if (rxrpc_kernel_abort_call(call->net->socket, call->rxcall,
+						    RX_USER_ABORT, -EINTR, "KWI"))
+				afs_set_call_complete(call, -EINTR, 0);
+		}
 	}
 
 	spin_lock_bh(&call->state_lock);
diff --git a/fs/afs/server.c b/fs/afs/server.c
index 642afa2e9783..65b33b6da48b 100644
--- a/fs/afs/server.c
+++ b/fs/afs/server.c
@@ -226,7 +226,6 @@ static struct afs_server *afs_alloc_server(struct afs_net *net,
 	RCU_INIT_POINTER(server->addresses, alist);
 	server->addr_version = alist->version;
 	server->uuid = *uuid;
-	server->flags = (1UL << AFS_SERVER_FL_NEW);
 	server->update_at = ktime_get_real_seconds() + afs_server_update_delay;
 	rwlock_init(&server->fs_lock);
 	INIT_HLIST_HEAD(&server->cb_volumes);
diff --git a/fs/afs/write.c b/fs/afs/write.c
index 72efcfcf9f95..0122d7445fba 100644
--- a/fs/afs/write.c
+++ b/fs/afs/write.c
@@ -264,6 +264,7 @@ static void afs_kill_pages(struct address_space *mapping,
 				first = page->index + 1;
 			lock_page(page);
 			generic_error_remove_page(mapping, page);
+			unlock_page(page);
 		}
 
 		__pagevec_release(&pv);
diff --git a/fs/afs/yfsclient.c b/fs/afs/yfsclient.c
index 5aa57929e8c2..6e97a42d24d1 100644
--- a/fs/afs/yfsclient.c
+++ b/fs/afs/yfsclient.c
@@ -1514,7 +1514,7 @@ static int yfs_fs_setattr_size(struct afs_fs_cursor *fc, struct iattr *attr)
 	bp = xdr_encode_u32(bp, 0); /* RPC flags */
 	bp = xdr_encode_YFSFid(bp, &vnode->fid);
 	bp = xdr_encode_YFS_StoreStatus(bp, attr);
-	bp = xdr_encode_u64(bp, 0);		/* position of start of write */
+	bp = xdr_encode_u64(bp, attr->ia_size);	/* position of start of write */
 	bp = xdr_encode_u64(bp, 0);		/* size of write */
 	bp = xdr_encode_u64(bp, attr->ia_size);	/* new file length */
 	yfs_check_req(call, bp);
diff --git a/fs/aio.c b/fs/aio.c
index 38b741aef0bf..3490d1fa0e16 100644
--- a/fs/aio.c
+++ b/fs/aio.c
@@ -181,7 +181,7 @@ struct poll_iocb {
 	struct file		*file;
 	struct wait_queue_head	*head;
 	__poll_t		events;
-	bool			woken;
+	bool			done;
 	bool			cancelled;
 	struct wait_queue_entry	wait;
 	struct work_struct	work;
@@ -204,8 +204,7 @@ struct aio_kiocb {
 	struct kioctx		*ki_ctx;
 	kiocb_cancel_fn		*ki_cancel;
 
-	struct iocb __user	*ki_user_iocb;	/* user's aiocb */
-	__u64			ki_user_data;	/* user's data for completion */
+	struct io_event		ki_res;
 
 	struct list_head	ki_list;	/* the aio core uses this
 						 * for cancellation */
@@ -1022,6 +1021,9 @@ static bool get_reqs_available(struct kioctx *ctx)
 /* aio_get_req
  *	Allocate a slot for an aio request.
  * Returns NULL if no requests are free.
+ *
+ * The refcount is initialized to 2 - one for the async op completion,
+ * one for the synchronous code that does this.
  */
 static inline struct aio_kiocb *aio_get_req(struct kioctx *ctx)
 {
@@ -1031,10 +1033,15 @@ static inline struct aio_kiocb *aio_get_req(struct kioctx *ctx)
 	if (unlikely(!req))
 		return NULL;
 
+	if (unlikely(!get_reqs_available(ctx))) {
+		kmem_cache_free(kiocb_cachep, req);
+		return NULL;
+	}
+
 	percpu_ref_get(&ctx->reqs);
 	req->ki_ctx = ctx;
 	INIT_LIST_HEAD(&req->ki_list);
-	refcount_set(&req->ki_refcnt, 0);
+	refcount_set(&req->ki_refcnt, 2);
 	req->ki_eventfd = NULL;
 	return req;
 }
@@ -1067,30 +1074,20 @@ out:
 	return ret;
 }
 
-static inline void iocb_put(struct aio_kiocb *iocb)
-{
-	if (refcount_read(&iocb->ki_refcnt) == 0 ||
-	    refcount_dec_and_test(&iocb->ki_refcnt)) {
-		if (iocb->ki_filp)
-			fput(iocb->ki_filp);
-		percpu_ref_put(&iocb->ki_ctx->reqs);
-		kmem_cache_free(kiocb_cachep, iocb);
-	}
-}
-
-static void aio_fill_event(struct io_event *ev, struct aio_kiocb *iocb,
-			   long res, long res2)
+static inline void iocb_destroy(struct aio_kiocb *iocb)
 {
-	ev->obj = (u64)(unsigned long)iocb->ki_user_iocb;
-	ev->data = iocb->ki_user_data;
-	ev->res = res;
-	ev->res2 = res2;
+	if (iocb->ki_eventfd)
+		eventfd_ctx_put(iocb->ki_eventfd);
+	if (iocb->ki_filp)
+		fput(iocb->ki_filp);
+	percpu_ref_put(&iocb->ki_ctx->reqs);
+	kmem_cache_free(kiocb_cachep, iocb);
 }
 
 /* aio_complete
  *	Called when the io request on the given iocb is complete.
  */
-static void aio_complete(struct aio_kiocb *iocb, long res, long res2)
+static void aio_complete(struct aio_kiocb *iocb)
 {
 	struct kioctx	*ctx = iocb->ki_ctx;
 	struct aio_ring	*ring;
@@ -1114,14 +1111,14 @@ static void aio_complete(struct aio_kiocb *iocb, long res, long res2)
 	ev_page = kmap_atomic(ctx->ring_pages[pos / AIO_EVENTS_PER_PAGE]);
 	event = ev_page + pos % AIO_EVENTS_PER_PAGE;
 
-	aio_fill_event(event, iocb, res, res2);
+	*event = iocb->ki_res;
 
 	kunmap_atomic(ev_page);
 	flush_dcache_page(ctx->ring_pages[pos / AIO_EVENTS_PER_PAGE]);
 
-	pr_debug("%p[%u]: %p: %p %Lx %lx %lx\n",
-		 ctx, tail, iocb, iocb->ki_user_iocb, iocb->ki_user_data,
-		 res, res2);
+	pr_debug("%p[%u]: %p: %p %Lx %Lx %Lx\n", ctx, tail, iocb,
+		 (void __user *)(unsigned long)iocb->ki_res.obj,
+		 iocb->ki_res.data, iocb->ki_res.res, iocb->ki_res.res2);
 
 	/* after flagging the request as done, we
 	 * must never even look at it again
@@ -1148,10 +1145,8 @@ static void aio_complete(struct aio_kiocb *iocb, long res, long res2)
 	 * eventfd. The eventfd_signal() function is safe to be called
 	 * from IRQ context.
 	 */
-	if (iocb->ki_eventfd) {
+	if (iocb->ki_eventfd)
 		eventfd_signal(iocb->ki_eventfd, 1);
-		eventfd_ctx_put(iocb->ki_eventfd);
-	}
 
 	/*
 	 * We have to order our ring_info tail store above and test
@@ -1163,7 +1158,14 @@ static void aio_complete(struct aio_kiocb *iocb, long res, long res2)
 
 	if (waitqueue_active(&ctx->wait))
 		wake_up(&ctx->wait);
-	iocb_put(iocb);
+}
+
+static inline void iocb_put(struct aio_kiocb *iocb)
+{
+	if (refcount_dec_and_test(&iocb->ki_refcnt)) {
+		aio_complete(iocb);
+		iocb_destroy(iocb);
+	}
 }
 
 /* aio_read_events_ring
@@ -1437,7 +1439,9 @@ static void aio_complete_rw(struct kiocb *kiocb, long res, long res2)
 		file_end_write(kiocb->ki_filp);
 	}
 
-	aio_complete(iocb, res, res2);
+	iocb->ki_res.res = res;
+	iocb->ki_res.res2 = res2;
+	iocb_put(iocb);
 }
 
 static int aio_prep_rw(struct kiocb *req, const struct iocb *iocb)
@@ -1514,13 +1518,13 @@ static inline void aio_rw_done(struct kiocb *req, ssize_t ret)
 	}
 }
 
-static ssize_t aio_read(struct kiocb *req, const struct iocb *iocb,
+static int aio_read(struct kiocb *req, const struct iocb *iocb,
 			bool vectored, bool compat)
 {
 	struct iovec inline_vecs[UIO_FASTIOV], *iovec = inline_vecs;
 	struct iov_iter iter;
 	struct file *file;
-	ssize_t ret;
+	int ret;
 
 	ret = aio_prep_rw(req, iocb);
 	if (ret)
@@ -1542,13 +1546,13 @@ static ssize_t aio_read(struct kiocb *req, const struct iocb *iocb,
 	return ret;
 }
 
-static ssize_t aio_write(struct kiocb *req, const struct iocb *iocb,
+static int aio_write(struct kiocb *req, const struct iocb *iocb,
 			 bool vectored, bool compat)
 {
 	struct iovec inline_vecs[UIO_FASTIOV], *iovec = inline_vecs;
 	struct iov_iter iter;
 	struct file *file;
-	ssize_t ret;
+	int ret;
 
 	ret = aio_prep_rw(req, iocb);
 	if (ret)
@@ -1585,11 +1589,10 @@ static ssize_t aio_write(struct kiocb *req, const struct iocb *iocb,
 
 static void aio_fsync_work(struct work_struct *work)
 {
-	struct fsync_iocb *req = container_of(work, struct fsync_iocb, work);
-	int ret;
+	struct aio_kiocb *iocb = container_of(work, struct aio_kiocb, fsync.work);
 
-	ret = vfs_fsync(req->file, req->datasync);
-	aio_complete(container_of(req, struct aio_kiocb, fsync), ret, 0);
+	iocb->ki_res.res = vfs_fsync(iocb->fsync.file, iocb->fsync.datasync);
+	iocb_put(iocb);
 }
 
 static int aio_fsync(struct fsync_iocb *req, const struct iocb *iocb,
@@ -1608,11 +1611,6 @@ static int aio_fsync(struct fsync_iocb *req, const struct iocb *iocb,
 	return 0;
 }
 
-static inline void aio_poll_complete(struct aio_kiocb *iocb, __poll_t mask)
-{
-	aio_complete(iocb, mangle_poll(mask), 0);
-}
-
 static void aio_poll_complete_work(struct work_struct *work)
 {
 	struct poll_iocb *req = container_of(work, struct poll_iocb, work);
@@ -1638,9 +1636,11 @@ static void aio_poll_complete_work(struct work_struct *work)
 		return;
 	}
 	list_del_init(&iocb->ki_list);
+	iocb->ki_res.res = mangle_poll(mask);
+	req->done = true;
 	spin_unlock_irq(&ctx->ctx_lock);
 
-	aio_poll_complete(iocb, mask);
+	iocb_put(iocb);
 }
 
 /* assumes we are called with irqs disabled */
@@ -1668,31 +1668,27 @@ static int aio_poll_wake(struct wait_queue_entry *wait, unsigned mode, int sync,
 	__poll_t mask = key_to_poll(key);
 	unsigned long flags;
 
-	req->woken = true;
-
 	/* for instances that support it check for an event match first: */
-	if (mask) {
-		if (!(mask & req->events))
-			return 0;
+	if (mask && !(mask & req->events))
+		return 0;
+
+	list_del_init(&req->wait.entry);
 
+	if (mask && spin_trylock_irqsave(&iocb->ki_ctx->ctx_lock, flags)) {
 		/*
 		 * Try to complete the iocb inline if we can. Use
 		 * irqsave/irqrestore because not all filesystems (e.g. fuse)
 		 * call this function with IRQs disabled and because IRQs
 		 * have to be disabled before ctx_lock is obtained.
 		 */
-		if (spin_trylock_irqsave(&iocb->ki_ctx->ctx_lock, flags)) {
-			list_del(&iocb->ki_list);
-			spin_unlock_irqrestore(&iocb->ki_ctx->ctx_lock, flags);
-
-			list_del_init(&req->wait.entry);
-			aio_poll_complete(iocb, mask);
-			return 1;
-		}
+		list_del(&iocb->ki_list);
+		iocb->ki_res.res = mangle_poll(mask);
+		req->done = true;
+		spin_unlock_irqrestore(&iocb->ki_ctx->ctx_lock, flags);
+		iocb_put(iocb);
+	} else {
+		schedule_work(&req->work);
 	}
-
-	list_del_init(&req->wait.entry);
-	schedule_work(&req->work);
 	return 1;
 }
 
@@ -1719,11 +1715,12 @@ aio_poll_queue_proc(struct file *file, struct wait_queue_head *head,
 	add_wait_queue(head, &pt->iocb->poll.wait);
 }
 
-static ssize_t aio_poll(struct aio_kiocb *aiocb, const struct iocb *iocb)
+static int aio_poll(struct aio_kiocb *aiocb, const struct iocb *iocb)
 {
 	struct kioctx *ctx = aiocb->ki_ctx;
 	struct poll_iocb *req = &aiocb->poll;
 	struct aio_poll_table apt;
+	bool cancel = false;
 	__poll_t mask;
 
 	/* reject any unknown events outside the normal event mask. */
@@ -1737,7 +1734,7 @@ static ssize_t aio_poll(struct aio_kiocb *aiocb, const struct iocb *iocb)
 	req->events = demangle_poll(iocb->aio_buf) | EPOLLERR | EPOLLHUP;
 
 	req->head = NULL;
-	req->woken = false;
+	req->done = false;
 	req->cancelled = false;
 
 	apt.pt._qproc = aio_poll_queue_proc;
@@ -1749,156 +1746,135 @@ static ssize_t aio_poll(struct aio_kiocb *aiocb, const struct iocb *iocb)
 	INIT_LIST_HEAD(&req->wait.entry);
 	init_waitqueue_func_entry(&req->wait, aio_poll_wake);
 
-	/* one for removal from waitqueue, one for this function */
-	refcount_set(&aiocb->ki_refcnt, 2);
-
 	mask = vfs_poll(req->file, &apt.pt) & req->events;
-	if (unlikely(!req->head)) {
-		/* we did not manage to set up a waitqueue, done */
-		goto out;
-	}
-
 	spin_lock_irq(&ctx->ctx_lock);
-	spin_lock(&req->head->lock);
-	if (req->woken) {
-		/* wake_up context handles the rest */
-		mask = 0;
+	if (likely(req->head)) {
+		spin_lock(&req->head->lock);
+		if (unlikely(list_empty(&req->wait.entry))) {
+			if (apt.error)
+				cancel = true;
+			apt.error = 0;
+			mask = 0;
+		}
+		if (mask || apt.error) {
+			list_del_init(&req->wait.entry);
+		} else if (cancel) {
+			WRITE_ONCE(req->cancelled, true);
+		} else if (!req->done) { /* actually waiting for an event */
+			list_add_tail(&aiocb->ki_list, &ctx->active_reqs);
+			aiocb->ki_cancel = aio_poll_cancel;
+		}
+		spin_unlock(&req->head->lock);
+	}
+	if (mask) { /* no async, we'd stolen it */
+		aiocb->ki_res.res = mangle_poll(mask);
 		apt.error = 0;
-	} else if (mask || apt.error) {
-		/* if we get an error or a mask we are done */
-		WARN_ON_ONCE(list_empty(&req->wait.entry));
-		list_del_init(&req->wait.entry);
-	} else {
-		/* actually waiting for an event */
-		list_add_tail(&aiocb->ki_list, &ctx->active_reqs);
-		aiocb->ki_cancel = aio_poll_cancel;
 	}
-	spin_unlock(&req->head->lock);
 	spin_unlock_irq(&ctx->ctx_lock);
-
-out:
-	if (unlikely(apt.error))
-		return apt.error;
-
 	if (mask)
-		aio_poll_complete(aiocb, mask);
-	iocb_put(aiocb);
-	return 0;
+		iocb_put(aiocb);
+	return apt.error;
 }
 
 static int __io_submit_one(struct kioctx *ctx, const struct iocb *iocb,
-			   struct iocb __user *user_iocb, bool compat)
+			   struct iocb __user *user_iocb, struct aio_kiocb *req,
+			   bool compat)
 {
-	struct aio_kiocb *req;
-	ssize_t ret;
-
-	/* enforce forwards compatibility on users */
-	if (unlikely(iocb->aio_reserved2)) {
-		pr_debug("EINVAL: reserve field set\n");
-		return -EINVAL;
-	}
-
-	/* prevent overflows */
-	if (unlikely(
-	    (iocb->aio_buf != (unsigned long)iocb->aio_buf) ||
-	    (iocb->aio_nbytes != (size_t)iocb->aio_nbytes) ||
-	    ((ssize_t)iocb->aio_nbytes < 0)
-	   )) {
-		pr_debug("EINVAL: overflow check\n");
-		return -EINVAL;
-	}
-
-	if (!get_reqs_available(ctx))
-		return -EAGAIN;
-
-	ret = -EAGAIN;
-	req = aio_get_req(ctx);
-	if (unlikely(!req))
-		goto out_put_reqs_available;
-
 	req->ki_filp = fget(iocb->aio_fildes);
-	ret = -EBADF;
 	if (unlikely(!req->ki_filp))
-		goto out_put_req;
+		return -EBADF;
 
 	if (iocb->aio_flags & IOCB_FLAG_RESFD) {
+		struct eventfd_ctx *eventfd;
 		/*
 		 * If the IOCB_FLAG_RESFD flag of aio_flags is set, get an
 		 * instance of the file* now. The file descriptor must be
 		 * an eventfd() fd, and will be signaled for each completed
 		 * event using the eventfd_signal() function.
 		 */
-		req->ki_eventfd = eventfd_ctx_fdget((int) iocb->aio_resfd);
-		if (IS_ERR(req->ki_eventfd)) {
-			ret = PTR_ERR(req->ki_eventfd);
-			req->ki_eventfd = NULL;
-			goto out_put_req;
-		}
+		eventfd = eventfd_ctx_fdget(iocb->aio_resfd);
+		if (IS_ERR(eventfd))
+			return PTR_ERR(eventfd);
+
+		req->ki_eventfd = eventfd;
 	}
 
-	ret = put_user(KIOCB_KEY, &user_iocb->aio_key);
-	if (unlikely(ret)) {
+	if (unlikely(put_user(KIOCB_KEY, &user_iocb->aio_key))) {
 		pr_debug("EFAULT: aio_key\n");
-		goto out_put_req;
+		return -EFAULT;
 	}
 
-	req->ki_user_iocb = user_iocb;
-	req->ki_user_data = iocb->aio_data;
+	req->ki_res.obj = (u64)(unsigned long)user_iocb;
+	req->ki_res.data = iocb->aio_data;
+	req->ki_res.res = 0;
+	req->ki_res.res2 = 0;
 
 	switch (iocb->aio_lio_opcode) {
 	case IOCB_CMD_PREAD:
-		ret = aio_read(&req->rw, iocb, false, compat);
-		break;
+		return aio_read(&req->rw, iocb, false, compat);
 	case IOCB_CMD_PWRITE:
-		ret = aio_write(&req->rw, iocb, false, compat);
-		break;
+		return aio_write(&req->rw, iocb, false, compat);
 	case IOCB_CMD_PREADV:
-		ret = aio_read(&req->rw, iocb, true, compat);
-		break;
+		return aio_read(&req->rw, iocb, true, compat);
 	case IOCB_CMD_PWRITEV:
-		ret = aio_write(&req->rw, iocb, true, compat);
-		break;
+		return aio_write(&req->rw, iocb, true, compat);
 	case IOCB_CMD_FSYNC:
-		ret = aio_fsync(&req->fsync, iocb, false);
-		break;
+		return aio_fsync(&req->fsync, iocb, false);
 	case IOCB_CMD_FDSYNC:
-		ret = aio_fsync(&req->fsync, iocb, true);
-		break;
+		return aio_fsync(&req->fsync, iocb, true);
 	case IOCB_CMD_POLL:
-		ret = aio_poll(req, iocb);
-		break;
+		return aio_poll(req, iocb);
 	default:
 		pr_debug("invalid aio operation %d\n", iocb->aio_lio_opcode);
-		ret = -EINVAL;
-		break;
+		return -EINVAL;
 	}
-
-	/*
-	 * If ret is 0, we'd either done aio_complete() ourselves or have
-	 * arranged for that to be done asynchronously.  Anything non-zero
-	 * means that we need to destroy req ourselves.
-	 */
-	if (ret)
-		goto out_put_req;
-	return 0;
-out_put_req:
-	if (req->ki_eventfd)
-		eventfd_ctx_put(req->ki_eventfd);
-	iocb_put(req);
-out_put_reqs_available:
-	put_reqs_available(ctx, 1);
-	return ret;
 }
 
 static int io_submit_one(struct kioctx *ctx, struct iocb __user *user_iocb,
 			 bool compat)
 {
+	struct aio_kiocb *req;
 	struct iocb iocb;
+	int err;
 
 	if (unlikely(copy_from_user(&iocb, user_iocb, sizeof(iocb))))
 		return -EFAULT;
 
-	return __io_submit_one(ctx, &iocb, user_iocb, compat);
+	/* enforce forwards compatibility on users */
+	if (unlikely(iocb.aio_reserved2)) {
+		pr_debug("EINVAL: reserve field set\n");
+		return -EINVAL;
+	}
+
+	/* prevent overflows */
+	if (unlikely(
+	    (iocb.aio_buf != (unsigned long)iocb.aio_buf) ||
+	    (iocb.aio_nbytes != (size_t)iocb.aio_nbytes) ||
+	    ((ssize_t)iocb.aio_nbytes < 0)
+	   )) {
+		pr_debug("EINVAL: overflow check\n");
+		return -EINVAL;
+	}
+
+	req = aio_get_req(ctx);
+	if (unlikely(!req))
+		return -EAGAIN;
+
+	err = __io_submit_one(ctx, &iocb, user_iocb, req, compat);
+
+	/* Done with the synchronous reference */
+	iocb_put(req);
+
+	/*
+	 * If err is 0, we'd either done aio_complete() ourselves or have
+	 * arranged for that to be done asynchronously.  Anything non-zero
+	 * means that we need to destroy req ourselves.
+	 */
+	if (unlikely(err)) {
+		iocb_destroy(req);
+		put_reqs_available(ctx, 1);
+	}
+	return err;
 }
 
 /* sys_io_submit:
@@ -1997,24 +1973,6 @@ COMPAT_SYSCALL_DEFINE3(io_submit, compat_aio_context_t, ctx_id,
 }
 #endif
 
-/* lookup_kiocb
- *	Finds a given iocb for cancellation.
- */
-static struct aio_kiocb *
-lookup_kiocb(struct kioctx *ctx, struct iocb __user *iocb)
-{
-	struct aio_kiocb *kiocb;
-
-	assert_spin_locked(&ctx->ctx_lock);
-
-	/* TODO: use a hash or array, this sucks. */
-	list_for_each_entry(kiocb, &ctx->active_reqs, ki_list) {
-		if (kiocb->ki_user_iocb == iocb)
-			return kiocb;
-	}
-	return NULL;
-}
-
 /* sys_io_cancel:
  *	Attempts to cancel an iocb previously passed to io_submit.  If
  *	the operation is successfully cancelled, the resulting event is
@@ -2032,6 +1990,7 @@ SYSCALL_DEFINE3(io_cancel, aio_context_t, ctx_id, struct iocb __user *, iocb,
 	struct aio_kiocb *kiocb;
 	int ret = -EINVAL;
 	u32 key;
+	u64 obj = (u64)(unsigned long)iocb;
 
 	if (unlikely(get_user(key, &iocb->aio_key)))
 		return -EFAULT;
@@ -2043,10 +2002,13 @@ SYSCALL_DEFINE3(io_cancel, aio_context_t, ctx_id, struct iocb __user *, iocb,
 		return -EINVAL;
 
 	spin_lock_irq(&ctx->ctx_lock);
-	kiocb = lookup_kiocb(ctx, iocb);
-	if (kiocb) {
-		ret = kiocb->ki_cancel(&kiocb->rw);
-		list_del_init(&kiocb->ki_list);
+	/* TODO: use a hash or array, this sucks. */
+	list_for_each_entry(kiocb, &ctx->active_reqs, ki_list) {
+		if (kiocb->ki_res.obj == obj) {
+			ret = kiocb->ki_cancel(&kiocb->rw);
+			list_del_init(&kiocb->ki_list);
+			break;
+		}
 	}
 	spin_unlock_irq(&ctx->ctx_lock);
 
diff --git a/fs/block_dev.c b/fs/block_dev.c
index 78d3257435c0..bb28e2ead679 100644
--- a/fs/block_dev.c
+++ b/fs/block_dev.c
@@ -264,7 +264,8 @@ __blkdev_direct_IO_simple(struct kiocb *iocb, struct iov_iter *iter,
 	bio_for_each_segment_all(bvec, &bio, i, iter_all) {
 		if (should_dirty && !PageCompound(bvec->bv_page))
 			set_page_dirty_lock(bvec->bv_page);
-		put_page(bvec->bv_page);
+		if (!bio_flagged(&bio, BIO_NO_PAGE_REF))
+			put_page(bvec->bv_page);
 	}
 
 	if (unlikely(bio.bi_status))
@@ -307,10 +308,10 @@ static void blkdev_bio_end_io(struct bio *bio)
 	struct blkdev_dio *dio = bio->bi_private;
 	bool should_dirty = dio->should_dirty;
 
-	if (dio->multi_bio && !atomic_dec_and_test(&dio->ref)) {
-		if (bio->bi_status && !dio->bio.bi_status)
-			dio->bio.bi_status = bio->bi_status;
-	} else {
+	if (bio->bi_status && !dio->bio.bi_status)
+		dio->bio.bi_status = bio->bi_status;
+
+	if (!dio->multi_bio || atomic_dec_and_test(&dio->ref)) {
 		if (!dio->is_sync) {
 			struct kiocb *iocb = dio->iocb;
 			ssize_t ret;
diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c
index 1d49694e6ae3..c5880329ae37 100644
--- a/fs/btrfs/extent-tree.c
+++ b/fs/btrfs/extent-tree.c
@@ -6174,7 +6174,7 @@ static void btrfs_calculate_inode_block_rsv_size(struct btrfs_fs_info *fs_info,
 	 *
 	 * This is overestimating in most cases.
 	 */
-	qgroup_rsv_size = outstanding_extents * fs_info->nodesize;
+	qgroup_rsv_size = (u64)outstanding_extents * fs_info->nodesize;
 
 	spin_lock(&block_rsv->lock);
 	block_rsv->size = reserve_size;
diff --git a/fs/btrfs/file-item.c b/fs/btrfs/file-item.c
index 920bf3b4b0ef..cccc75d15970 100644
--- a/fs/btrfs/file-item.c
+++ b/fs/btrfs/file-item.c
@@ -7,6 +7,7 @@
 #include <linux/slab.h>
 #include <linux/pagemap.h>
 #include <linux/highmem.h>
+#include <linux/sched/mm.h>
 #include "ctree.h"
 #include "disk-io.h"
 #include "transaction.h"
@@ -427,9 +428,13 @@ blk_status_t btrfs_csum_one_bio(struct inode *inode, struct bio *bio,
 	unsigned long this_sum_bytes = 0;
 	int i;
 	u64 offset;
+	unsigned nofs_flag;
+
+	nofs_flag = memalloc_nofs_save();
+	sums = kvzalloc(btrfs_ordered_sum_size(fs_info, bio->bi_iter.bi_size),
+		       GFP_KERNEL);
+	memalloc_nofs_restore(nofs_flag);
 
-	sums = kzalloc(btrfs_ordered_sum_size(fs_info, bio->bi_iter.bi_size),
-		       GFP_NOFS);
 	if (!sums)
 		return BLK_STS_RESOURCE;
 
@@ -472,8 +477,10 @@ blk_status_t btrfs_csum_one_bio(struct inode *inode, struct bio *bio,
 
 				bytes_left = bio->bi_iter.bi_size - total_bytes;
 
-				sums = kzalloc(btrfs_ordered_sum_size(fs_info, bytes_left),
-					       GFP_NOFS);
+				nofs_flag = memalloc_nofs_save();
+				sums = kvzalloc(btrfs_ordered_sum_size(fs_info,
+						      bytes_left), GFP_KERNEL);
+				memalloc_nofs_restore(nofs_flag);
 				BUG_ON(!sums); /* -ENOMEM */
 				sums->len = bytes_left;
 				ordered = btrfs_lookup_ordered_extent(inode,
diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c
index 82fdda8ff5ab..2973608824ec 100644
--- a/fs/btrfs/inode.c
+++ b/fs/btrfs/inode.c
@@ -6783,7 +6783,7 @@ struct extent_map *btrfs_get_extent(struct btrfs_inode *inode,
 	u64 extent_start = 0;
 	u64 extent_end = 0;
 	u64 objectid = btrfs_ino(inode);
-	u8 extent_type;
+	int extent_type = -1;
 	struct btrfs_path *path = NULL;
 	struct btrfs_root *root = inode->root;
 	struct btrfs_file_extent_item *item;
diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c
index ec2d8919e7fb..cd4e693406a0 100644
--- a/fs/btrfs/ioctl.c
+++ b/fs/btrfs/ioctl.c
@@ -501,6 +501,16 @@ static noinline int btrfs_ioctl_fitrim(struct file *file, void __user *arg)
 	if (!capable(CAP_SYS_ADMIN))
 		return -EPERM;
 
+	/*
+	 * If the fs is mounted with nologreplay, which requires it to be
+	 * mounted in RO mode as well, we can not allow discard on free space
+	 * inside block groups, because log trees refer to extents that are not
+	 * pinned in a block group's free space cache (pinning the extents is
+	 * precisely the first phase of replaying a log tree).
+	 */
+	if (btrfs_test_opt(fs_info, NOLOGREPLAY))
+		return -EROFS;
+
 	rcu_read_lock();
 	list_for_each_entry_rcu(device, &fs_info->fs_devices->devices,
 				dev_list) {
diff --git a/fs/btrfs/ordered-data.c b/fs/btrfs/ordered-data.c
index 6fde2b2741ef..45e3cfd1198b 100644
--- a/fs/btrfs/ordered-data.c
+++ b/fs/btrfs/ordered-data.c
@@ -6,6 +6,7 @@
 #include <linux/slab.h>
 #include <linux/blkdev.h>
 #include <linux/writeback.h>
+#include <linux/sched/mm.h>
 #include "ctree.h"
 #include "transaction.h"
 #include "btrfs_inode.h"
@@ -442,7 +443,7 @@ void btrfs_put_ordered_extent(struct btrfs_ordered_extent *entry)
 			cur = entry->list.next;
 			sum = list_entry(cur, struct btrfs_ordered_sum, list);
 			list_del(&sum->list);
-			kfree(sum);
+			kvfree(sum);
 		}
 		kmem_cache_free(btrfs_ordered_extent_cache, entry);
 	}
diff --git a/fs/btrfs/props.c b/fs/btrfs/props.c
index dc6140013ae8..61d22a56c0ba 100644
--- a/fs/btrfs/props.c
+++ b/fs/btrfs/props.c
@@ -366,11 +366,11 @@ int btrfs_subvol_inherit_props(struct btrfs_trans_handle *trans,
 
 static int prop_compression_validate(const char *value, size_t len)
 {
-	if (!strncmp("lzo", value, len))
+	if (!strncmp("lzo", value, 3))
 		return 0;
-	else if (!strncmp("zlib", value, len))
+	else if (!strncmp("zlib", value, 4))
 		return 0;
-	else if (!strncmp("zstd", value, len))
+	else if (!strncmp("zstd", value, 4))
 		return 0;
 
 	return -EINVAL;
@@ -396,7 +396,7 @@ static int prop_compression_apply(struct inode *inode,
 		btrfs_set_fs_incompat(fs_info, COMPRESS_LZO);
 	} else if (!strncmp("zlib", value, 4)) {
 		type = BTRFS_COMPRESS_ZLIB;
-	} else if (!strncmp("zstd", value, len)) {
+	} else if (!strncmp("zstd", value, 4)) {
 		type = BTRFS_COMPRESS_ZSTD;
 		btrfs_set_fs_incompat(fs_info, COMPRESS_ZSTD);
 	} else {
diff --git a/fs/btrfs/qgroup.c b/fs/btrfs/qgroup.c
index eb680b715dd6..e659d9d61107 100644
--- a/fs/btrfs/qgroup.c
+++ b/fs/btrfs/qgroup.c
@@ -1922,8 +1922,8 @@ static int qgroup_trace_new_subtree_blocks(struct btrfs_trans_handle* trans,
 	int i;
 
 	/* Level sanity check */
-	if (cur_level < 0 || cur_level >= BTRFS_MAX_LEVEL ||
-	    root_level < 0 || root_level >= BTRFS_MAX_LEVEL ||
+	if (cur_level < 0 || cur_level >= BTRFS_MAX_LEVEL - 1 ||
+	    root_level < 0 || root_level >= BTRFS_MAX_LEVEL - 1 ||
 	    root_level < cur_level) {
 		btrfs_err_rl(fs_info,
 			"%s: bad levels, cur_level=%d root_level=%d",
diff --git a/fs/btrfs/raid56.c b/fs/btrfs/raid56.c
index 1869ba8e5981..67a6f7d47402 100644
--- a/fs/btrfs/raid56.c
+++ b/fs/btrfs/raid56.c
@@ -2430,8 +2430,9 @@ static noinline void finish_parity_scrub(struct btrfs_raid_bio *rbio,
 			bitmap_clear(rbio->dbitmap, pagenr, 1);
 		kunmap(p);
 
-		for (stripe = 0; stripe < rbio->real_stripes; stripe++)
+		for (stripe = 0; stripe < nr_data; stripe++)
 			kunmap(page_in_rbio(rbio, stripe, pagenr, 0));
+		kunmap(p_page);
 	}
 
 	__free_page(p_page);
diff --git a/fs/btrfs/ref-verify.c b/fs/btrfs/ref-verify.c
index d09b6cdb785a..b283d3a6e837 100644
--- a/fs/btrfs/ref-verify.c
+++ b/fs/btrfs/ref-verify.c
@@ -205,28 +205,17 @@ static struct root_entry *lookup_root_entry(struct rb_root *root, u64 objectid)
 #ifdef CONFIG_STACKTRACE
 static void __save_stack_trace(struct ref_action *ra)
 {
-	struct stack_trace stack_trace;
-
-	stack_trace.max_entries = MAX_TRACE;
-	stack_trace.nr_entries = 0;
-	stack_trace.entries = ra->trace;
-	stack_trace.skip = 2;
-	save_stack_trace(&stack_trace);
-	ra->trace_len = stack_trace.nr_entries;
+	ra->trace_len = stack_trace_save(ra->trace, MAX_TRACE, 2);
 }
 
 static void __print_stack_trace(struct btrfs_fs_info *fs_info,
 				struct ref_action *ra)
 {
-	struct stack_trace trace;
-
 	if (ra->trace_len == 0) {
 		btrfs_err(fs_info, "  ref-verify: no stacktrace");
 		return;
 	}
-	trace.nr_entries = ra->trace_len;
-	trace.entries = ra->trace;
-	print_stack_trace(&trace, 2);
+	stack_trace_print(ra->trace, ra->trace_len, 2);
 }
 #else
 static void inline __save_stack_trace(struct ref_action *ra)
diff --git a/fs/btrfs/transaction.c b/fs/btrfs/transaction.c
index acdad6d658f5..e4e665f422fc 100644
--- a/fs/btrfs/transaction.c
+++ b/fs/btrfs/transaction.c
@@ -1886,8 +1886,10 @@ static void btrfs_cleanup_pending_block_groups(struct btrfs_trans_handle *trans)
        }
 }
 
-static inline int btrfs_start_delalloc_flush(struct btrfs_fs_info *fs_info)
+static inline int btrfs_start_delalloc_flush(struct btrfs_trans_handle *trans)
 {
+	struct btrfs_fs_info *fs_info = trans->fs_info;
+
 	/*
 	 * We use writeback_inodes_sb here because if we used
 	 * btrfs_start_delalloc_roots we would deadlock with fs freeze.
@@ -1897,15 +1899,50 @@ static inline int btrfs_start_delalloc_flush(struct btrfs_fs_info *fs_info)
 	 * from already being in a transaction and our join_transaction doesn't
 	 * have to re-take the fs freeze lock.
 	 */
-	if (btrfs_test_opt(fs_info, FLUSHONCOMMIT))
+	if (btrfs_test_opt(fs_info, FLUSHONCOMMIT)) {
 		writeback_inodes_sb(fs_info->sb, WB_REASON_SYNC);
+	} else {
+		struct btrfs_pending_snapshot *pending;
+		struct list_head *head = &trans->transaction->pending_snapshots;
+
+		/*
+		 * Flush dellaloc for any root that is going to be snapshotted.
+		 * This is done to avoid a corrupted version of files, in the
+		 * snapshots, that had both buffered and direct IO writes (even
+		 * if they were done sequentially) due to an unordered update of
+		 * the inode's size on disk.
+		 */
+		list_for_each_entry(pending, head, list) {
+			int ret;
+
+			ret = btrfs_start_delalloc_snapshot(pending->root);
+			if (ret)
+				return ret;
+		}
+	}
 	return 0;
 }
 
-static inline void btrfs_wait_delalloc_flush(struct btrfs_fs_info *fs_info)
+static inline void btrfs_wait_delalloc_flush(struct btrfs_trans_handle *trans)
 {
-	if (btrfs_test_opt(fs_info, FLUSHONCOMMIT))
+	struct btrfs_fs_info *fs_info = trans->fs_info;
+
+	if (btrfs_test_opt(fs_info, FLUSHONCOMMIT)) {
 		btrfs_wait_ordered_roots(fs_info, U64_MAX, 0, (u64)-1);
+	} else {
+		struct btrfs_pending_snapshot *pending;
+		struct list_head *head = &trans->transaction->pending_snapshots;
+
+		/*
+		 * Wait for any dellaloc that we started previously for the roots
+		 * that are going to be snapshotted. This is to avoid a corrupted
+		 * version of files in the snapshots that had both buffered and
+		 * direct IO writes (even if they were done sequentially).
+		 */
+		list_for_each_entry(pending, head, list)
+			btrfs_wait_ordered_extents(pending->root,
+						   U64_MAX, 0, U64_MAX);
+	}
 }
 
 int btrfs_commit_transaction(struct btrfs_trans_handle *trans)
@@ -2023,7 +2060,7 @@ int btrfs_commit_transaction(struct btrfs_trans_handle *trans)
 
 	extwriter_counter_dec(cur_trans, trans->type);
 
-	ret = btrfs_start_delalloc_flush(fs_info);
+	ret = btrfs_start_delalloc_flush(trans);
 	if (ret)
 		goto cleanup_transaction;
 
@@ -2039,7 +2076,7 @@ int btrfs_commit_transaction(struct btrfs_trans_handle *trans)
 	if (ret)
 		goto cleanup_transaction;
 
-	btrfs_wait_delalloc_flush(fs_info);
+	btrfs_wait_delalloc_flush(trans);
 
 	btrfs_scrub_pause(fs_info);
 	/*
diff --git a/fs/btrfs/tree-log.c b/fs/btrfs/tree-log.c
index f06454a55e00..561884f60d35 100644
--- a/fs/btrfs/tree-log.c
+++ b/fs/btrfs/tree-log.c
@@ -3578,9 +3578,16 @@ static noinline int log_dir_items(struct btrfs_trans_handle *trans,
 	}
 	btrfs_release_path(path);
 
-	/* find the first key from this transaction again */
+	/*
+	 * Find the first key from this transaction again.  See the note for
+	 * log_new_dir_dentries, if we're logging a directory recursively we
+	 * won't be holding its i_mutex, which means we can modify the directory
+	 * while we're logging it.  If we remove an entry between our first
+	 * search and this search we'll not find the key again and can just
+	 * bail.
+	 */
 	ret = btrfs_search_slot(NULL, root, &min_key, path, 0, 0);
-	if (WARN_ON(ret != 0))
+	if (ret != 0)
 		goto done;
 
 	/*
@@ -4544,6 +4551,19 @@ static int logged_inode_size(struct btrfs_root *log, struct btrfs_inode *inode,
 		item = btrfs_item_ptr(path->nodes[0], path->slots[0],
 				      struct btrfs_inode_item);
 		*size_ret = btrfs_inode_size(path->nodes[0], item);
+		/*
+		 * If the in-memory inode's i_size is smaller then the inode
+		 * size stored in the btree, return the inode's i_size, so
+		 * that we get a correct inode size after replaying the log
+		 * when before a power failure we had a shrinking truncate
+		 * followed by addition of a new name (rename / new hard link).
+		 * Otherwise return the inode size from the btree, to avoid
+		 * data loss when replaying a log due to previously doing a
+		 * write that expands the inode's size and logging a new name
+		 * immediately after.
+		 */
+		if (*size_ret > inode->vfs_inode.i_size)
+			*size_ret = inode->vfs_inode.i_size;
 	}
 
 	btrfs_release_path(path);
@@ -4705,15 +4725,8 @@ static int btrfs_log_trailing_hole(struct btrfs_trans_handle *trans,
 					struct btrfs_file_extent_item);
 
 		if (btrfs_file_extent_type(leaf, extent) ==
-		    BTRFS_FILE_EXTENT_INLINE) {
-			len = btrfs_file_extent_ram_bytes(leaf, extent);
-			ASSERT(len == i_size ||
-			       (len == fs_info->sectorsize &&
-				btrfs_file_extent_compression(leaf, extent) !=
-				BTRFS_COMPRESS_NONE) ||
-			       (len < i_size && i_size < fs_info->sectorsize));
+		    BTRFS_FILE_EXTENT_INLINE)
 			return 0;
-		}
 
 		len = btrfs_file_extent_num_bytes(leaf, extent);
 		/* Last extent goes beyond i_size, no need to log a hole. */
diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c
index 9024eee889b9..db934ceae9c1 100644
--- a/fs/btrfs/volumes.c
+++ b/fs/btrfs/volumes.c
@@ -6407,7 +6407,7 @@ static void btrfs_end_bio(struct bio *bio)
 				if (bio_op(bio) == REQ_OP_WRITE)
 					btrfs_dev_stat_inc_and_print(dev,
 						BTRFS_DEV_STAT_WRITE_ERRS);
-				else
+				else if (!(bio->bi_opf & REQ_RAHEAD))
 					btrfs_dev_stat_inc_and_print(dev,
 						BTRFS_DEV_STAT_READ_ERRS);
 				if (bio->bi_opf & REQ_PREFLUSH)
diff --git a/fs/ceph/dir.c b/fs/ceph/dir.c
index a8f429882249..0637149fb9f9 100644
--- a/fs/ceph/dir.c
+++ b/fs/ceph/dir.c
@@ -1766,6 +1766,7 @@ static ssize_t ceph_read_dir(struct file *file, char __user *buf, size_t size,
 unsigned ceph_dentry_hash(struct inode *dir, struct dentry *dn)
 {
 	struct ceph_inode_info *dci = ceph_inode(dir);
+	unsigned hash;
 
 	switch (dci->i_dir_layout.dl_dir_hash) {
 	case 0:	/* for backward compat */
@@ -1773,8 +1774,11 @@ unsigned ceph_dentry_hash(struct inode *dir, struct dentry *dn)
 		return dn->d_name.hash;
 
 	default:
-		return ceph_str_hash(dci->i_dir_layout.dl_dir_hash,
+		spin_lock(&dn->d_lock);
+		hash = ceph_str_hash(dci->i_dir_layout.dl_dir_hash,
 				     dn->d_name.name, dn->d_name.len);
+		spin_unlock(&dn->d_lock);
+		return hash;
 	}
 }
 
diff --git a/fs/ceph/inode.c b/fs/ceph/inode.c
index e3346628efe2..c2feb310ac1e 100644
--- a/fs/ceph/inode.c
+++ b/fs/ceph/inode.c
@@ -524,6 +524,7 @@ static void ceph_i_callback(struct rcu_head *head)
 	struct inode *inode = container_of(head, struct inode, i_rcu);
 	struct ceph_inode_info *ci = ceph_inode(inode);
 
+	kfree(ci->i_symlink);
 	kmem_cache_free(ceph_inode_cachep, ci);
 }
 
@@ -566,7 +567,6 @@ void ceph_destroy_inode(struct inode *inode)
 		}
 	}
 
-	kfree(ci->i_symlink);
 	while ((n = rb_first(&ci->i_fragtree)) != NULL) {
 		frag = rb_entry(n, struct ceph_inode_frag, node);
 		rb_erase(n, &ci->i_fragtree);
@@ -1163,6 +1163,19 @@ static int splice_dentry(struct dentry **pdn, struct inode *in)
 	return 0;
 }
 
+static int d_name_cmp(struct dentry *dentry, const char *name, size_t len)
+{
+	int ret;
+
+	/* take d_lock to ensure dentry->d_name stability */
+	spin_lock(&dentry->d_lock);
+	ret = dentry->d_name.len - len;
+	if (!ret)
+		ret = memcmp(dentry->d_name.name, name, len);
+	spin_unlock(&dentry->d_lock);
+	return ret;
+}
+
 /*
  * Incorporate results into the local cache.  This is either just
  * one inode, or a directory, dentry, and possibly linked-to inode (e.g.,
@@ -1412,7 +1425,8 @@ retry_lookup:
 		err = splice_dentry(&req->r_dentry, in);
 		if (err < 0)
 			goto done;
-	} else if (rinfo->head->is_dentry) {
+	} else if (rinfo->head->is_dentry &&
+		   !d_name_cmp(req->r_dentry, rinfo->dname, rinfo->dname_len)) {
 		struct ceph_vino *ptvino = NULL;
 
 		if ((le32_to_cpu(rinfo->diri.in->cap.caps) & CEPH_CAP_FILE_SHARED) ||
diff --git a/fs/ceph/mds_client.c b/fs/ceph/mds_client.c
index 21c33ed048ed..9049c2a3e972 100644
--- a/fs/ceph/mds_client.c
+++ b/fs/ceph/mds_client.c
@@ -1414,6 +1414,15 @@ static int remove_session_caps_cb(struct inode *inode, struct ceph_cap *cap,
 			list_add(&ci->i_prealloc_cap_flush->i_list, &to_remove);
 			ci->i_prealloc_cap_flush = NULL;
 		}
+
+               if (drop &&
+                  ci->i_wrbuffer_ref_head == 0 &&
+                  ci->i_wr_ref == 0 &&
+                  ci->i_dirty_caps == 0 &&
+                  ci->i_flushing_caps == 0) {
+                      ceph_put_snap_context(ci->i_head_snapc);
+                      ci->i_head_snapc = NULL;
+               }
 	}
 	spin_unlock(&ci->i_ceph_lock);
 	while (!list_empty(&to_remove)) {
@@ -2161,10 +2170,39 @@ retry:
 	return path;
 }
 
+/* Duplicate the dentry->d_name.name safely */
+static int clone_dentry_name(struct dentry *dentry, const char **ppath,
+			     int *ppathlen)
+{
+	u32 len;
+	char *name;
+
+retry:
+	len = READ_ONCE(dentry->d_name.len);
+	name = kmalloc(len + 1, GFP_NOFS);
+	if (!name)
+		return -ENOMEM;
+
+	spin_lock(&dentry->d_lock);
+	if (dentry->d_name.len != len) {
+		spin_unlock(&dentry->d_lock);
+		kfree(name);
+		goto retry;
+	}
+	memcpy(name, dentry->d_name.name, len);
+	spin_unlock(&dentry->d_lock);
+
+	name[len] = '\0';
+	*ppath = name;
+	*ppathlen = len;
+	return 0;
+}
+
 static int build_dentry_path(struct dentry *dentry, struct inode *dir,
 			     const char **ppath, int *ppathlen, u64 *pino,
-			     int *pfreepath)
+			     bool *pfreepath, bool parent_locked)
 {
+	int ret;
 	char *path;
 
 	rcu_read_lock();
@@ -2173,8 +2211,15 @@ static int build_dentry_path(struct dentry *dentry, struct inode *dir,
 	if (dir && ceph_snap(dir) == CEPH_NOSNAP) {
 		*pino = ceph_ino(dir);
 		rcu_read_unlock();
-		*ppath = dentry->d_name.name;
-		*ppathlen = dentry->d_name.len;
+		if (parent_locked) {
+			*ppath = dentry->d_name.name;
+			*ppathlen = dentry->d_name.len;
+		} else {
+			ret = clone_dentry_name(dentry, ppath, ppathlen);
+			if (ret)
+				return ret;
+			*pfreepath = true;
+		}
 		return 0;
 	}
 	rcu_read_unlock();
@@ -2182,13 +2227,13 @@ static int build_dentry_path(struct dentry *dentry, struct inode *dir,
 	if (IS_ERR(path))
 		return PTR_ERR(path);
 	*ppath = path;
-	*pfreepath = 1;
+	*pfreepath = true;
 	return 0;
 }
 
 static int build_inode_path(struct inode *inode,
 			    const char **ppath, int *ppathlen, u64 *pino,
-			    int *pfreepath)
+			    bool *pfreepath)
 {
 	struct dentry *dentry;
 	char *path;
@@ -2204,7 +2249,7 @@ static int build_inode_path(struct inode *inode,
 	if (IS_ERR(path))
 		return PTR_ERR(path);
 	*ppath = path;
-	*pfreepath = 1;
+	*pfreepath = true;
 	return 0;
 }
 
@@ -2215,7 +2260,7 @@ static int build_inode_path(struct inode *inode,
 static int set_request_path_attr(struct inode *rinode, struct dentry *rdentry,
 				  struct inode *rdiri, const char *rpath,
 				  u64 rino, const char **ppath, int *pathlen,
-				  u64 *ino, int *freepath)
+				  u64 *ino, bool *freepath, bool parent_locked)
 {
 	int r = 0;
 
@@ -2225,7 +2270,7 @@ static int set_request_path_attr(struct inode *rinode, struct dentry *rdentry,
 		     ceph_snap(rinode));
 	} else if (rdentry) {
 		r = build_dentry_path(rdentry, rdiri, ppath, pathlen, ino,
-					freepath);
+					freepath, parent_locked);
 		dout(" dentry %p %llx/%.*s\n", rdentry, *ino, *pathlen,
 		     *ppath);
 	} else if (rpath || rino) {
@@ -2251,7 +2296,7 @@ static struct ceph_msg *create_request_message(struct ceph_mds_client *mdsc,
 	const char *path2 = NULL;
 	u64 ino1 = 0, ino2 = 0;
 	int pathlen1 = 0, pathlen2 = 0;
-	int freepath1 = 0, freepath2 = 0;
+	bool freepath1 = false, freepath2 = false;
 	int len;
 	u16 releases;
 	void *p, *end;
@@ -2259,16 +2304,19 @@ static struct ceph_msg *create_request_message(struct ceph_mds_client *mdsc,
 
 	ret = set_request_path_attr(req->r_inode, req->r_dentry,
 			      req->r_parent, req->r_path1, req->r_ino1.ino,
-			      &path1, &pathlen1, &ino1, &freepath1);
+			      &path1, &pathlen1, &ino1, &freepath1,
+			      test_bit(CEPH_MDS_R_PARENT_LOCKED,
+					&req->r_req_flags));
 	if (ret < 0) {
 		msg = ERR_PTR(ret);
 		goto out;
 	}
 
+	/* If r_old_dentry is set, then assume that its parent is locked */
 	ret = set_request_path_attr(NULL, req->r_old_dentry,
 			      req->r_old_dentry_dir,
 			      req->r_path2, req->r_ino2.ino,
-			      &path2, &pathlen2, &ino2, &freepath2);
+			      &path2, &pathlen2, &ino2, &freepath2, true);
 	if (ret < 0) {
 		msg = ERR_PTR(ret);
 		goto out_free1;
diff --git a/fs/ceph/snap.c b/fs/ceph/snap.c
index 89aa37fa0f84..b26e12cd8ec3 100644
--- a/fs/ceph/snap.c
+++ b/fs/ceph/snap.c
@@ -572,7 +572,12 @@ void ceph_queue_cap_snap(struct ceph_inode_info *ci)
 	old_snapc = NULL;
 
 update_snapc:
-	if (ci->i_head_snapc) {
+       if (ci->i_wrbuffer_ref_head == 0 &&
+           ci->i_wr_ref == 0 &&
+           ci->i_dirty_caps == 0 &&
+           ci->i_flushing_caps == 0) {
+               ci->i_head_snapc = NULL;
+       } else {
 		ci->i_head_snapc = ceph_get_snap_context(new_snapc);
 		dout(" new snapc is %p\n", new_snapc);
 	}
diff --git a/fs/cifs/cifsfs.c b/fs/cifs/cifsfs.c
index f9b71c12cc9f..a05bf1d6e1d0 100644
--- a/fs/cifs/cifsfs.c
+++ b/fs/cifs/cifsfs.c
@@ -559,6 +559,8 @@ cifs_show_options(struct seq_file *s, struct dentry *root)
 			tcon->ses->server->echo_interval / HZ);
 	if (tcon->snapshot_time)
 		seq_printf(s, ",snapshot=%llu", tcon->snapshot_time);
+	if (tcon->handle_timeout)
+		seq_printf(s, ",handletimeout=%u", tcon->handle_timeout);
 	/* convert actimeo and display it in seconds */
 	seq_printf(s, ",actimeo=%lu", cifs_sb->actimeo / HZ);
 
diff --git a/fs/cifs/cifsglob.h b/fs/cifs/cifsglob.h
index 38feae812b47..585ad3207cb1 100644
--- a/fs/cifs/cifsglob.h
+++ b/fs/cifs/cifsglob.h
@@ -60,6 +60,12 @@
 #define CIFS_MAX_ACTIMEO (1 << 30)
 
 /*
+ * Max persistent and resilient handle timeout (milliseconds).
+ * Windows durable max was 960000 (16 minutes)
+ */
+#define SMB3_MAX_HANDLE_TIMEOUT 960000
+
+/*
  * MAX_REQ is the maximum number of requests that WE will send
  * on one socket concurrently.
  */
@@ -586,6 +592,7 @@ struct smb_vol {
 	struct nls_table *local_nls;
 	unsigned int echo_interval; /* echo interval in secs */
 	__u64 snapshot_time; /* needed for timewarp tokens */
+	__u32 handle_timeout; /* persistent and durable handle timeout in ms */
 	unsigned int max_credits; /* smb3 max_credits 10 < credits < 60000 */
 };
 
@@ -1058,6 +1065,7 @@ struct cifs_tcon {
 	__u32 vol_serial_number;
 	__le64 vol_create_time;
 	__u64 snapshot_time; /* for timewarp tokens - timestamp of snapshot */
+	__u32 handle_timeout; /* persistent and durable handle timeout in ms */
 	__u32 ss_flags;		/* sector size flags */
 	__u32 perf_sector_size; /* best sector size for perf */
 	__u32 max_chunks;
@@ -1325,6 +1333,7 @@ cifsFileInfo_get_locked(struct cifsFileInfo *cifs_file)
 }
 
 struct cifsFileInfo *cifsFileInfo_get(struct cifsFileInfo *cifs_file);
+void _cifsFileInfo_put(struct cifsFileInfo *cifs_file, bool wait_oplock_hdlr);
 void cifsFileInfo_put(struct cifsFileInfo *cifs_file);
 
 #define CIFS_CACHE_READ_FLG	1
@@ -1847,6 +1856,7 @@ GLOBAL_EXTERN spinlock_t gidsidlock;
 #endif /* CONFIG_CIFS_ACL */
 
 void cifs_oplock_break(struct work_struct *work);
+void cifs_queue_oplock_break(struct cifsFileInfo *cfile);
 
 extern const struct slow_work_ops cifs_oplock_break_ops;
 extern struct workqueue_struct *cifsiod_wq;
diff --git a/fs/cifs/connect.c b/fs/cifs/connect.c
index a8e9738db691..4c0e44489f21 100644
--- a/fs/cifs/connect.c
+++ b/fs/cifs/connect.c
@@ -103,7 +103,7 @@ enum {
 	Opt_cruid, Opt_gid, Opt_file_mode,
 	Opt_dirmode, Opt_port,
 	Opt_blocksize, Opt_rsize, Opt_wsize, Opt_actimeo,
-	Opt_echo_interval, Opt_max_credits,
+	Opt_echo_interval, Opt_max_credits, Opt_handletimeout,
 	Opt_snapshot,
 
 	/* Mount options which take string value */
@@ -208,6 +208,7 @@ static const match_table_t cifs_mount_option_tokens = {
 	{ Opt_rsize, "rsize=%s" },
 	{ Opt_wsize, "wsize=%s" },
 	{ Opt_actimeo, "actimeo=%s" },
+	{ Opt_handletimeout, "handletimeout=%s" },
 	{ Opt_echo_interval, "echo_interval=%s" },
 	{ Opt_max_credits, "max_credits=%s" },
 	{ Opt_snapshot, "snapshot=%s" },
@@ -1619,6 +1620,9 @@ cifs_parse_mount_options(const char *mountdata, const char *devname,
 
 	vol->actimeo = CIFS_DEF_ACTIMEO;
 
+	/* Most clients set timeout to 0, allows server to use its default */
+	vol->handle_timeout = 0; /* See MS-SMB2 spec section 2.2.14.2.12 */
+
 	/* offer SMB2.1 and later (SMB3 etc). Secure and widely accepted */
 	vol->ops = &smb30_operations;
 	vol->vals = &smbdefault_values;
@@ -2017,6 +2021,18 @@ cifs_parse_mount_options(const char *mountdata, const char *devname,
 				goto cifs_parse_mount_err;
 			}
 			break;
+		case Opt_handletimeout:
+			if (get_option_ul(args, &option)) {
+				cifs_dbg(VFS, "%s: Invalid handletimeout value\n",
+					 __func__);
+				goto cifs_parse_mount_err;
+			}
+			vol->handle_timeout = option;
+			if (vol->handle_timeout > SMB3_MAX_HANDLE_TIMEOUT) {
+				cifs_dbg(VFS, "Invalid handle cache timeout, longer than 16 minutes\n");
+				goto cifs_parse_mount_err;
+			}
+			break;
 		case Opt_echo_interval:
 			if (get_option_ul(args, &option)) {
 				cifs_dbg(VFS, "%s: Invalid echo interval value\n",
@@ -3183,6 +3199,8 @@ static int match_tcon(struct cifs_tcon *tcon, struct smb_vol *volume_info)
 		return 0;
 	if (tcon->snapshot_time != volume_info->snapshot_time)
 		return 0;
+	if (tcon->handle_timeout != volume_info->handle_timeout)
+		return 0;
 	return 1;
 }
 
@@ -3297,6 +3315,16 @@ cifs_get_tcon(struct cifs_ses *ses, struct smb_vol *volume_info)
 			tcon->snapshot_time = volume_info->snapshot_time;
 	}
 
+	if (volume_info->handle_timeout) {
+		if (ses->server->vals->protocol_id == 0) {
+			cifs_dbg(VFS,
+			     "Use SMB2.1 or later for handle timeout option\n");
+			rc = -EOPNOTSUPP;
+			goto out_fail;
+		} else
+			tcon->handle_timeout = volume_info->handle_timeout;
+	}
+
 	tcon->ses = ses;
 	if (volume_info->password) {
 		tcon->password = kstrdup(volume_info->password, GFP_KERNEL);
diff --git a/fs/cifs/file.c b/fs/cifs/file.c
index 89006e044973..7037a137fa53 100644
--- a/fs/cifs/file.c
+++ b/fs/cifs/file.c
@@ -360,13 +360,31 @@ cifsFileInfo_get(struct cifsFileInfo *cifs_file)
 	return cifs_file;
 }
 
-/*
- * Release a reference on the file private data. This may involve closing
- * the filehandle out on the server. Must be called without holding
- * tcon->open_file_lock and cifs_file->file_info_lock.
+/**
+ * cifsFileInfo_put - release a reference of file priv data
+ *
+ * Always potentially wait for oplock handler. See _cifsFileInfo_put().
  */
 void cifsFileInfo_put(struct cifsFileInfo *cifs_file)
 {
+	_cifsFileInfo_put(cifs_file, true);
+}
+
+/**
+ * _cifsFileInfo_put - release a reference of file priv data
+ *
+ * This may involve closing the filehandle @cifs_file out on the
+ * server. Must be called without holding tcon->open_file_lock and
+ * cifs_file->file_info_lock.
+ *
+ * If @wait_for_oplock_handler is true and we are releasing the last
+ * reference, wait for any running oplock break handler of the file
+ * and cancel any pending one. If calling this function from the
+ * oplock break handler, you need to pass false.
+ *
+ */
+void _cifsFileInfo_put(struct cifsFileInfo *cifs_file, bool wait_oplock_handler)
+{
 	struct inode *inode = d_inode(cifs_file->dentry);
 	struct cifs_tcon *tcon = tlink_tcon(cifs_file->tlink);
 	struct TCP_Server_Info *server = tcon->ses->server;
@@ -414,7 +432,8 @@ void cifsFileInfo_put(struct cifsFileInfo *cifs_file)
 
 	spin_unlock(&tcon->open_file_lock);
 
-	oplock_break_cancelled = cancel_work_sync(&cifs_file->oplock_break);
+	oplock_break_cancelled = wait_oplock_handler ?
+		cancel_work_sync(&cifs_file->oplock_break) : false;
 
 	if (!tcon->need_reconnect && !cifs_file->invalidHandle) {
 		struct TCP_Server_Info *server = tcon->ses->server;
@@ -2858,7 +2877,6 @@ static void collect_uncached_write_data(struct cifs_aio_ctx *ctx)
 	struct cifs_tcon *tcon;
 	struct cifs_sb_info *cifs_sb;
 	struct dentry *dentry = ctx->cfile->dentry;
-	unsigned int i;
 	int rc;
 
 	tcon = tlink_tcon(ctx->cfile->tlink);
@@ -2922,10 +2940,6 @@ restart_loop:
 		kref_put(&wdata->refcount, cifs_uncached_writedata_release);
 	}
 
-	if (!ctx->direct_io)
-		for (i = 0; i < ctx->npages; i++)
-			put_page(ctx->bv[i].bv_page);
-
 	cifs_stats_bytes_written(tcon, ctx->total_len);
 	set_bit(CIFS_INO_INVALID_MAPPING, &CIFS_I(dentry->d_inode)->flags);
 
@@ -3563,7 +3577,6 @@ collect_uncached_read_data(struct cifs_aio_ctx *ctx)
 	struct iov_iter *to = &ctx->iter;
 	struct cifs_sb_info *cifs_sb;
 	struct cifs_tcon *tcon;
-	unsigned int i;
 	int rc;
 
 	tcon = tlink_tcon(ctx->cfile->tlink);
@@ -3647,15 +3660,8 @@ again:
 		kref_put(&rdata->refcount, cifs_uncached_readdata_release);
 	}
 
-	if (!ctx->direct_io) {
-		for (i = 0; i < ctx->npages; i++) {
-			if (ctx->should_dirty)
-				set_page_dirty(ctx->bv[i].bv_page);
-			put_page(ctx->bv[i].bv_page);
-		}
-
+	if (!ctx->direct_io)
 		ctx->total_len = ctx->len - iov_iter_count(to);
-	}
 
 	/* mask nodata case */
 	if (rc == -ENODATA)
@@ -4603,6 +4609,7 @@ void cifs_oplock_break(struct work_struct *work)
 							     cinode);
 		cifs_dbg(FYI, "Oplock release rc = %d\n", rc);
 	}
+	_cifsFileInfo_put(cfile, false /* do not wait for ourself */);
 	cifs_done_oplock_break(cinode);
 }
 
diff --git a/fs/cifs/inode.c b/fs/cifs/inode.c
index 53fdb5df0d2e..538fd7d807e4 100644
--- a/fs/cifs/inode.c
+++ b/fs/cifs/inode.c
@@ -1735,6 +1735,10 @@ cifs_do_rename(const unsigned int xid, struct dentry *from_dentry,
 	if (rc == 0 || rc != -EBUSY)
 		goto do_rename_exit;
 
+	/* Don't fall back to using SMB on SMB 2+ mount */
+	if (server->vals->protocol_id != 0)
+		goto do_rename_exit;
+
 	/* open-file renames don't work across directories */
 	if (to_dentry->d_parent != from_dentry->d_parent)
 		goto do_rename_exit;
diff --git a/fs/cifs/misc.c b/fs/cifs/misc.c
index bee203055b30..b1a696a73f7c 100644
--- a/fs/cifs/misc.c
+++ b/fs/cifs/misc.c
@@ -501,8 +501,7 @@ is_valid_oplock_break(char *buffer, struct TCP_Server_Info *srv)
 					   CIFS_INODE_DOWNGRADE_OPLOCK_TO_L2,
 					   &pCifsInode->flags);
 
-				queue_work(cifsoplockd_wq,
-					   &netfile->oplock_break);
+				cifs_queue_oplock_break(netfile);
 				netfile->oplock_break_cancelled = false;
 
 				spin_unlock(&tcon->open_file_lock);
@@ -607,6 +606,28 @@ void cifs_put_writer(struct cifsInodeInfo *cinode)
 	spin_unlock(&cinode->writers_lock);
 }
 
+/**
+ * cifs_queue_oplock_break - queue the oplock break handler for cfile
+ *
+ * This function is called from the demultiplex thread when it
+ * receives an oplock break for @cfile.
+ *
+ * Assumes the tcon->open_file_lock is held.
+ * Assumes cfile->file_info_lock is NOT held.
+ */
+void cifs_queue_oplock_break(struct cifsFileInfo *cfile)
+{
+	/*
+	 * Bump the handle refcount now while we hold the
+	 * open_file_lock to enforce the validity of it for the oplock
+	 * break handler. The matching put is done at the end of the
+	 * handler.
+	 */
+	cifsFileInfo_get(cfile);
+
+	queue_work(cifsoplockd_wq, &cfile->oplock_break);
+}
+
 void cifs_done_oplock_break(struct cifsInodeInfo *cinode)
 {
 	clear_bit(CIFS_INODE_PENDING_OPLOCK_BREAK, &cinode->flags);
@@ -768,6 +789,11 @@ cifs_aio_ctx_alloc(void)
 {
 	struct cifs_aio_ctx *ctx;
 
+	/*
+	 * Must use kzalloc to initialize ctx->bv to NULL and ctx->direct_io
+	 * to false so that we know when we have to unreference pages within
+	 * cifs_aio_ctx_release()
+	 */
 	ctx = kzalloc(sizeof(struct cifs_aio_ctx), GFP_KERNEL);
 	if (!ctx)
 		return NULL;
@@ -786,7 +812,23 @@ cifs_aio_ctx_release(struct kref *refcount)
 					struct cifs_aio_ctx, refcount);
 
 	cifsFileInfo_put(ctx->cfile);
-	kvfree(ctx->bv);
+
+	/*
+	 * ctx->bv is only set if setup_aio_ctx_iter() was call successfuly
+	 * which means that iov_iter_get_pages() was a success and thus that
+	 * we have taken reference on pages.
+	 */
+	if (ctx->bv) {
+		unsigned i;
+
+		for (i = 0; i < ctx->npages; i++) {
+			if (ctx->should_dirty)
+				set_page_dirty(ctx->bv[i].bv_page);
+			put_page(ctx->bv[i].bv_page);
+		}
+		kvfree(ctx->bv);
+	}
+
 	kfree(ctx);
 }
 
@@ -917,7 +959,6 @@ cifs_alloc_hash(const char *name,
 	}
 
 	(*sdesc)->shash.tfm = *shash;
-	(*sdesc)->shash.flags = 0x0;
 	return 0;
 }
 
diff --git a/fs/cifs/smb2file.c b/fs/cifs/smb2file.c
index b204e84b87fb..54bffb2a1786 100644
--- a/fs/cifs/smb2file.c
+++ b/fs/cifs/smb2file.c
@@ -68,13 +68,15 @@ smb2_open_file(const unsigned int xid, struct cifs_open_parms *oparms,
 
 
 	 if (oparms->tcon->use_resilient) {
-		nr_ioctl_req.Timeout = 0; /* use server default (120 seconds) */
+		/* default timeout is 0, servers pick default (120 seconds) */
+		nr_ioctl_req.Timeout =
+			cpu_to_le32(oparms->tcon->handle_timeout);
 		nr_ioctl_req.Reserved = 0;
 		rc = SMB2_ioctl(xid, oparms->tcon, fid->persistent_fid,
 			fid->volatile_fid, FSCTL_LMR_REQUEST_RESILIENCY,
 			true /* is_fsctl */,
 			(char *)&nr_ioctl_req, sizeof(nr_ioctl_req),
-			NULL, NULL /* no return info */);
+			CIFSMaxBufSize, NULL, NULL /* no return info */);
 		if (rc == -EOPNOTSUPP) {
 			cifs_dbg(VFS,
 			     "resiliency not supported by server, disabling\n");
diff --git a/fs/cifs/smb2misc.c b/fs/cifs/smb2misc.c
index 0e3570e40ff8..e311f58dc1c8 100644
--- a/fs/cifs/smb2misc.c
+++ b/fs/cifs/smb2misc.c
@@ -555,7 +555,7 @@ smb2_tcon_has_lease(struct cifs_tcon *tcon, struct smb2_lease_break *rsp,
 			clear_bit(CIFS_INODE_DOWNGRADE_OPLOCK_TO_L2,
 				  &cinode->flags);
 
-		queue_work(cifsoplockd_wq, &cfile->oplock_break);
+		cifs_queue_oplock_break(cfile);
 		kfree(lw);
 		return true;
 	}
@@ -712,8 +712,8 @@ smb2_is_valid_oplock_break(char *buffer, struct TCP_Server_Info *server)
 					   CIFS_INODE_DOWNGRADE_OPLOCK_TO_L2,
 					   &cinode->flags);
 				spin_unlock(&cfile->file_info_lock);
-				queue_work(cifsoplockd_wq,
-					   &cfile->oplock_break);
+
+				cifs_queue_oplock_break(cfile);
 
 				spin_unlock(&tcon->open_file_lock);
 				spin_unlock(&cifs_tcp_ses_lock);
diff --git a/fs/cifs/smb2ops.c b/fs/cifs/smb2ops.c
index 1022a3771e14..c36ff0d1fe2a 100644
--- a/fs/cifs/smb2ops.c
+++ b/fs/cifs/smb2ops.c
@@ -581,7 +581,7 @@ SMB3_request_interfaces(const unsigned int xid, struct cifs_tcon *tcon)
 	rc = SMB2_ioctl(xid, tcon, NO_FILE_ID, NO_FILE_ID,
 			FSCTL_QUERY_NETWORK_INTERFACE_INFO, true /* is_fsctl */,
 			NULL /* no data input */, 0 /* no data input */,
-			(char **)&out_buf, &ret_data_len);
+			CIFSMaxBufSize, (char **)&out_buf, &ret_data_len);
 	if (rc == -EOPNOTSUPP) {
 		cifs_dbg(FYI,
 			 "server does not support query network interfaces\n");
@@ -717,32 +717,28 @@ int open_shroot(unsigned int xid, struct cifs_tcon *tcon, struct cifs_fid *pfid)
 	oparms.fid->mid = le64_to_cpu(o_rsp->sync_hdr.MessageId);
 #endif /* CIFS_DEBUG2 */
 
-	if (o_rsp->OplockLevel == SMB2_OPLOCK_LEVEL_LEASE)
-		oplock = smb2_parse_lease_state(server, o_rsp,
-						&oparms.fid->epoch,
-						oparms.fid->lease_key);
-	else
-		goto oshr_exit;
-
-
 	memcpy(tcon->crfid.fid, pfid, sizeof(struct cifs_fid));
 	tcon->crfid.tcon = tcon;
 	tcon->crfid.is_valid = true;
 	kref_init(&tcon->crfid.refcount);
-	kref_get(&tcon->crfid.refcount);
 
+	if (o_rsp->OplockLevel == SMB2_OPLOCK_LEVEL_LEASE) {
+		kref_get(&tcon->crfid.refcount);
+		oplock = smb2_parse_lease_state(server, o_rsp,
+						&oparms.fid->epoch,
+						oparms.fid->lease_key);
+	} else
+		goto oshr_exit;
 
 	qi_rsp = (struct smb2_query_info_rsp *)rsp_iov[1].iov_base;
 	if (le32_to_cpu(qi_rsp->OutputBufferLength) < sizeof(struct smb2_file_all_info))
 		goto oshr_exit;
-	rc = smb2_validate_and_copy_iov(
+	if (!smb2_validate_and_copy_iov(
 				le16_to_cpu(qi_rsp->OutputBufferOffset),
 				sizeof(struct smb2_file_all_info),
 				&rsp_iov[1], sizeof(struct smb2_file_all_info),
-				(char *)&tcon->crfid.file_all_info);
-	if (rc)
-		goto oshr_exit;
-	tcon->crfid.file_all_info_is_valid = 1;
+				(char *)&tcon->crfid.file_all_info))
+		tcon->crfid.file_all_info_is_valid = 1;
 
  oshr_exit:
 	mutex_unlock(&tcon->crfid.fid_mutex);
@@ -1299,7 +1295,7 @@ SMB2_request_res_key(const unsigned int xid, struct cifs_tcon *tcon,
 
 	rc = SMB2_ioctl(xid, tcon, persistent_fid, volatile_fid,
 			FSCTL_SRV_REQUEST_RESUME_KEY, true /* is_fsctl */,
-			NULL, 0 /* no input */,
+			NULL, 0 /* no input */, CIFSMaxBufSize,
 			(char **)&res_key, &ret_data_len);
 
 	if (rc) {
@@ -1404,7 +1400,7 @@ smb2_ioctl_query_info(const unsigned int xid,
 			rc = SMB2_ioctl_init(tcon, &rqst[1],
 					     COMPOUND_FID, COMPOUND_FID,
 					     qi.info_type, true, NULL,
-					     0);
+					     0, CIFSMaxBufSize);
 		}
 	} else if (qi.flags == PASSTHRU_QUERY_INFO) {
 		memset(&qi_iov, 0, sizeof(qi_iov));
@@ -1532,8 +1528,8 @@ smb2_copychunk_range(const unsigned int xid,
 		rc = SMB2_ioctl(xid, tcon, trgtfile->fid.persistent_fid,
 			trgtfile->fid.volatile_fid, FSCTL_SRV_COPYCHUNK_WRITE,
 			true /* is_fsctl */, (char *)pcchunk,
-			sizeof(struct copychunk_ioctl),	(char **)&retbuf,
-			&ret_data_len);
+			sizeof(struct copychunk_ioctl),	CIFSMaxBufSize,
+			(char **)&retbuf, &ret_data_len);
 		if (rc == 0) {
 			if (ret_data_len !=
 					sizeof(struct copychunk_ioctl_rsp)) {
@@ -1693,7 +1689,7 @@ static bool smb2_set_sparse(const unsigned int xid, struct cifs_tcon *tcon,
 	rc = SMB2_ioctl(xid, tcon, cfile->fid.persistent_fid,
 			cfile->fid.volatile_fid, FSCTL_SET_SPARSE,
 			true /* is_fctl */,
-			&setsparse, 1, NULL, NULL);
+			&setsparse, 1, CIFSMaxBufSize, NULL, NULL);
 	if (rc) {
 		tcon->broken_sparse_sup = true;
 		cifs_dbg(FYI, "set sparse rc = %d\n", rc);
@@ -1766,7 +1762,7 @@ smb2_duplicate_extents(const unsigned int xid,
 			true /* is_fsctl */,
 			(char *)&dup_ext_buf,
 			sizeof(struct duplicate_extents_to_file),
-			NULL,
+			CIFSMaxBufSize, NULL,
 			&ret_data_len);
 
 	if (ret_data_len > 0)
@@ -1801,7 +1797,7 @@ smb3_set_integrity(const unsigned int xid, struct cifs_tcon *tcon,
 			true /* is_fsctl */,
 			(char *)&integr_info,
 			sizeof(struct fsctl_set_integrity_information_req),
-			NULL,
+			CIFSMaxBufSize, NULL,
 			&ret_data_len);
 
 }
@@ -1809,6 +1805,8 @@ smb3_set_integrity(const unsigned int xid, struct cifs_tcon *tcon,
 /* GMT Token is @GMT-YYYY.MM.DD-HH.MM.SS Unicode which is 48 bytes + null */
 #define GMT_TOKEN_SIZE 50
 
+#define MIN_SNAPSHOT_ARRAY_SIZE 16 /* See MS-SMB2 section 3.3.5.15.1 */
+
 /*
  * Input buffer contains (empty) struct smb_snapshot array with size filled in
  * For output see struct SRV_SNAPSHOT_ARRAY in MS-SMB2 section 2.2.32.2
@@ -1820,13 +1818,29 @@ smb3_enum_snapshots(const unsigned int xid, struct cifs_tcon *tcon,
 	char *retbuf = NULL;
 	unsigned int ret_data_len = 0;
 	int rc;
+	u32 max_response_size;
 	struct smb_snapshot_array snapshot_in;
 
+	if (get_user(ret_data_len, (unsigned int __user *)ioc_buf))
+		return -EFAULT;
+
+	/*
+	 * Note that for snapshot queries that servers like Azure expect that
+	 * the first query be minimal size (and just used to get the number/size
+	 * of previous versions) so response size must be specified as EXACTLY
+	 * sizeof(struct snapshot_array) which is 16 when rounded up to multiple
+	 * of eight bytes.
+	 */
+	if (ret_data_len == 0)
+		max_response_size = MIN_SNAPSHOT_ARRAY_SIZE;
+	else
+		max_response_size = CIFSMaxBufSize;
+
 	rc = SMB2_ioctl(xid, tcon, cfile->fid.persistent_fid,
 			cfile->fid.volatile_fid,
 			FSCTL_SRV_ENUMERATE_SNAPSHOTS,
 			true /* is_fsctl */,
-			NULL, 0 /* no input data */,
+			NULL, 0 /* no input data */, max_response_size,
 			(char **)&retbuf,
 			&ret_data_len);
 	cifs_dbg(FYI, "enum snaphots ioctl returned %d and ret buflen is %d\n",
@@ -2304,7 +2318,7 @@ smb2_get_dfs_refer(const unsigned int xid, struct cifs_ses *ses,
 		rc = SMB2_ioctl(xid, tcon, NO_FILE_ID, NO_FILE_ID,
 				FSCTL_DFS_GET_REFERRALS,
 				true /* is_fsctl */,
-				(char *)dfs_req, dfs_req_size,
+				(char *)dfs_req, dfs_req_size, CIFSMaxBufSize,
 				(char **)&dfs_rsp, &dfs_rsp_size);
 	} while (rc == -EAGAIN);
 
@@ -2375,6 +2389,8 @@ smb2_query_symlink(const unsigned int xid, struct cifs_tcon *tcon,
 
 	rc = SMB2_open(xid, &oparms, utf16_path, &oplock, NULL, &err_iov,
 		       &resp_buftype);
+	if (!rc)
+		SMB2_close(xid, tcon, fid.persistent_fid, fid.volatile_fid);
 	if (!rc || !err_iov.iov_base) {
 		rc = -ENOENT;
 		goto free_path;
@@ -2658,7 +2674,8 @@ static long smb3_zero_range(struct file *file, struct cifs_tcon *tcon,
 	rc = SMB2_ioctl_init(tcon, &rqst[num++], cfile->fid.persistent_fid,
 			     cfile->fid.volatile_fid, FSCTL_SET_ZERO_DATA,
 			     true /* is_fctl */, (char *)&fsctl_buf,
-			     sizeof(struct file_zero_data_information));
+			     sizeof(struct file_zero_data_information),
+			     CIFSMaxBufSize);
 	if (rc)
 		goto zero_range_exit;
 
@@ -2735,7 +2752,8 @@ static long smb3_punch_hole(struct file *file, struct cifs_tcon *tcon,
 	rc = SMB2_ioctl(xid, tcon, cfile->fid.persistent_fid,
 			cfile->fid.volatile_fid, FSCTL_SET_ZERO_DATA,
 			true /* is_fctl */, (char *)&fsctl_buf,
-			sizeof(struct file_zero_data_information), NULL, NULL);
+			sizeof(struct file_zero_data_information),
+			CIFSMaxBufSize, NULL, NULL);
 	free_xid(xid);
 	return rc;
 }
diff --git a/fs/cifs/smb2pdu.c b/fs/cifs/smb2pdu.c
index 21ac19ff19cb..a37774a55f3a 100644
--- a/fs/cifs/smb2pdu.c
+++ b/fs/cifs/smb2pdu.c
@@ -832,8 +832,11 @@ SMB2_negotiate(const unsigned int xid, struct cifs_ses *ses)
 		} else if (rsp->DialectRevision == cpu_to_le16(SMB21_PROT_ID)) {
 			/* ops set to 3.0 by default for default so update */
 			ses->server->ops = &smb21_operations;
-		} else if (rsp->DialectRevision == cpu_to_le16(SMB311_PROT_ID))
+			ses->server->vals = &smb21_values;
+		} else if (rsp->DialectRevision == cpu_to_le16(SMB311_PROT_ID)) {
 			ses->server->ops = &smb311_operations;
+			ses->server->vals = &smb311_values;
+		}
 	} else if (le16_to_cpu(rsp->DialectRevision) !=
 				ses->server->vals->protocol_id) {
 		/* if requested single dialect ensure returned dialect matched */
@@ -1002,7 +1005,8 @@ int smb3_validate_negotiate(const unsigned int xid, struct cifs_tcon *tcon)
 
 	rc = SMB2_ioctl(xid, tcon, NO_FILE_ID, NO_FILE_ID,
 		FSCTL_VALIDATE_NEGOTIATE_INFO, true /* is_fsctl */,
-		(char *)pneg_inbuf, inbuflen, (char **)&pneg_rsp, &rsplen);
+		(char *)pneg_inbuf, inbuflen, CIFSMaxBufSize,
+		(char **)&pneg_rsp, &rsplen);
 	if (rc == -EOPNOTSUPP) {
 		/*
 		 * Old Windows versions or Netapp SMB server can return
@@ -1858,8 +1862,9 @@ add_lease_context(struct TCP_Server_Info *server, struct kvec *iov,
 }
 
 static struct create_durable_v2 *
-create_durable_v2_buf(struct cifs_fid *pfid)
+create_durable_v2_buf(struct cifs_open_parms *oparms)
 {
+	struct cifs_fid *pfid = oparms->fid;
 	struct create_durable_v2 *buf;
 
 	buf = kzalloc(sizeof(struct create_durable_v2), GFP_KERNEL);
@@ -1873,7 +1878,14 @@ create_durable_v2_buf(struct cifs_fid *pfid)
 				(struct create_durable_v2, Name));
 	buf->ccontext.NameLength = cpu_to_le16(4);
 
-	buf->dcontext.Timeout = 0; /* Should this be configurable by workload */
+	/*
+	 * NB: Handle timeout defaults to 0, which allows server to choose
+	 * (most servers default to 120 seconds) and most clients default to 0.
+	 * This can be overridden at mount ("handletimeout=") if the user wants
+	 * a different persistent (or resilient) handle timeout for all opens
+	 * opens on a particular SMB3 mount.
+	 */
+	buf->dcontext.Timeout = cpu_to_le32(oparms->tcon->handle_timeout);
 	buf->dcontext.Flags = cpu_to_le32(SMB2_DHANDLE_FLAG_PERSISTENT);
 	generate_random_uuid(buf->dcontext.CreateGuid);
 	memcpy(pfid->create_guid, buf->dcontext.CreateGuid, 16);
@@ -1926,7 +1938,7 @@ add_durable_v2_context(struct kvec *iov, unsigned int *num_iovec,
 	struct smb2_create_req *req = iov[0].iov_base;
 	unsigned int num = *num_iovec;
 
-	iov[num].iov_base = create_durable_v2_buf(oparms->fid);
+	iov[num].iov_base = create_durable_v2_buf(oparms);
 	if (iov[num].iov_base == NULL)
 		return -ENOMEM;
 	iov[num].iov_len = sizeof(struct create_durable_v2);
@@ -2478,7 +2490,8 @@ creat_exit:
 int
 SMB2_ioctl_init(struct cifs_tcon *tcon, struct smb_rqst *rqst,
 		u64 persistent_fid, u64 volatile_fid, u32 opcode,
-		bool is_fsctl, char *in_data, u32 indatalen)
+		bool is_fsctl, char *in_data, u32 indatalen,
+		__u32 max_response_size)
 {
 	struct smb2_ioctl_req *req;
 	struct kvec *iov = rqst->rq_iov;
@@ -2520,16 +2533,21 @@ SMB2_ioctl_init(struct cifs_tcon *tcon, struct smb_rqst *rqst,
 	req->OutputCount = 0; /* MBZ */
 
 	/*
-	 * Could increase MaxOutputResponse, but that would require more
-	 * than one credit. Windows typically sets this smaller, but for some
+	 * In most cases max_response_size is set to 16K (CIFSMaxBufSize)
+	 * We Could increase default MaxOutputResponse, but that could require
+	 * more credits. Windows typically sets this smaller, but for some
 	 * ioctls it may be useful to allow server to send more. No point
 	 * limiting what the server can send as long as fits in one credit
-	 * Unfortunately - we can not handle more than CIFS_MAX_MSG_SIZE
-	 * (by default, note that it can be overridden to make max larger)
-	 * in responses (except for read responses which can be bigger.
-	 * We may want to bump this limit up
+	 * We can not handle more than CIFS_MAX_BUF_SIZE yet but may want
+	 * to increase this limit up in the future.
+	 * Note that for snapshot queries that servers like Azure expect that
+	 * the first query be minimal size (and just used to get the number/size
+	 * of previous versions) so response size must be specified as EXACTLY
+	 * sizeof(struct snapshot_array) which is 16 when rounded up to multiple
+	 * of eight bytes.  Currently that is the only case where we set max
+	 * response size smaller.
 	 */
-	req->MaxOutputResponse = cpu_to_le32(CIFSMaxBufSize);
+	req->MaxOutputResponse = cpu_to_le32(max_response_size);
 
 	if (is_fsctl)
 		req->Flags = cpu_to_le32(SMB2_0_IOCTL_IS_FSCTL);
@@ -2550,13 +2568,14 @@ SMB2_ioctl_free(struct smb_rqst *rqst)
 		cifs_small_buf_release(rqst->rq_iov[0].iov_base); /* request */
 }
 
+
 /*
  *	SMB2 IOCTL is used for both IOCTLs and FSCTLs
  */
 int
 SMB2_ioctl(const unsigned int xid, struct cifs_tcon *tcon, u64 persistent_fid,
 	   u64 volatile_fid, u32 opcode, bool is_fsctl,
-	   char *in_data, u32 indatalen,
+	   char *in_data, u32 indatalen, u32 max_out_data_len,
 	   char **out_data, u32 *plen /* returned data len */)
 {
 	struct smb_rqst rqst;
@@ -2593,8 +2612,8 @@ SMB2_ioctl(const unsigned int xid, struct cifs_tcon *tcon, u64 persistent_fid,
 	rqst.rq_iov = iov;
 	rqst.rq_nvec = SMB2_IOCTL_IOV_SIZE;
 
-	rc = SMB2_ioctl_init(tcon, &rqst, persistent_fid, volatile_fid,
-			     opcode, is_fsctl, in_data, indatalen);
+	rc = SMB2_ioctl_init(tcon, &rqst, persistent_fid, volatile_fid, opcode,
+			     is_fsctl, in_data, indatalen, max_out_data_len);
 	if (rc)
 		goto ioctl_exit;
 
@@ -2672,7 +2691,8 @@ SMB2_set_compression(const unsigned int xid, struct cifs_tcon *tcon,
 	rc = SMB2_ioctl(xid, tcon, persistent_fid, volatile_fid,
 			FSCTL_SET_COMPRESSION, true /* is_fsctl */,
 			(char *)&fsctl_input /* data input */,
-			2 /* in data len */, &ret_data /* out data */, NULL);
+			2 /* in data len */, CIFSMaxBufSize /* max out data */,
+			&ret_data /* out data */, NULL);
 
 	cifs_dbg(FYI, "set compression rc %d\n", rc);
 
@@ -3431,8 +3451,6 @@ SMB2_read(const unsigned int xid, struct cifs_io_parms *io_parms,
 	rqst.rq_nvec = 1;
 
 	rc = cifs_send_recv(xid, ses, &rqst, &resp_buftype, flags, &rsp_iov);
-	cifs_small_buf_release(req);
-
 	rsp = (struct smb2_read_rsp *)rsp_iov.iov_base;
 
 	if (rc) {
@@ -3448,12 +3466,15 @@ SMB2_read(const unsigned int xid, struct cifs_io_parms *io_parms,
 				    io_parms->tcon->tid, ses->Suid,
 				    io_parms->offset, 0);
 		free_rsp_buf(resp_buftype, rsp_iov.iov_base);
+		cifs_small_buf_release(req);
 		return rc == -ENODATA ? 0 : rc;
 	} else
 		trace_smb3_read_done(xid, req->PersistentFileId,
 				    io_parms->tcon->tid, ses->Suid,
 				    io_parms->offset, io_parms->length);
 
+	cifs_small_buf_release(req);
+
 	*nbytes = le32_to_cpu(rsp->DataLength);
 	if ((*nbytes > CIFS_MAX_MSGSIZE) ||
 	    (*nbytes > io_parms->length)) {
@@ -3752,7 +3773,6 @@ SMB2_write(const unsigned int xid, struct cifs_io_parms *io_parms,
 
 	rc = cifs_send_recv(xid, io_parms->tcon->ses, &rqst,
 			    &resp_buftype, flags, &rsp_iov);
-	cifs_small_buf_release(req);
 	rsp = (struct smb2_write_rsp *)rsp_iov.iov_base;
 
 	if (rc) {
@@ -3770,6 +3790,7 @@ SMB2_write(const unsigned int xid, struct cifs_io_parms *io_parms,
 				     io_parms->offset, *nbytes);
 	}
 
+	cifs_small_buf_release(req);
 	free_rsp_buf(resp_buftype, rsp);
 	return rc;
 }
diff --git a/fs/cifs/smb2proto.h b/fs/cifs/smb2proto.h
index 3c32d0cfea69..52df125e9189 100644
--- a/fs/cifs/smb2proto.h
+++ b/fs/cifs/smb2proto.h
@@ -142,11 +142,12 @@ extern int SMB2_open_init(struct cifs_tcon *tcon, struct smb_rqst *rqst,
 extern void SMB2_open_free(struct smb_rqst *rqst);
 extern int SMB2_ioctl(const unsigned int xid, struct cifs_tcon *tcon,
 		     u64 persistent_fid, u64 volatile_fid, u32 opcode,
-		     bool is_fsctl, char *in_data, u32 indatalen,
+		     bool is_fsctl, char *in_data, u32 indatalen, u32 maxoutlen,
 		     char **out_data, u32 *plen /* returned data len */);
 extern int SMB2_ioctl_init(struct cifs_tcon *tcon, struct smb_rqst *rqst,
 			   u64 persistent_fid, u64 volatile_fid, u32 opcode,
-			   bool is_fsctl, char *in_data, u32 indatalen);
+			   bool is_fsctl, char *in_data, u32 indatalen,
+			   __u32 max_response_size);
 extern void SMB2_ioctl_free(struct smb_rqst *rqst);
 extern int SMB2_close(const unsigned int xid, struct cifs_tcon *tcon,
 		      u64 persistent_file_id, u64 volatile_file_id);
diff --git a/fs/crypto/keyinfo.c b/fs/crypto/keyinfo.c
index 322ce9686bdb..2cb4956f8511 100644
--- a/fs/crypto/keyinfo.c
+++ b/fs/crypto/keyinfo.c
@@ -402,7 +402,6 @@ static int derive_essiv_salt(const u8 *key, int keysize, u8 *salt)
 	{
 		SHASH_DESC_ON_STACK(desc, tfm);
 		desc->tfm = tfm;
-		desc->flags = 0;
 
 		return crypto_shash_digest(desc, key, keysize, salt);
 	}
diff --git a/fs/dax.c b/fs/dax.c
index ca0671d55aa6..e5e54da1715f 100644
--- a/fs/dax.c
+++ b/fs/dax.c
@@ -33,6 +33,7 @@
 #include <linux/sizes.h>
 #include <linux/mmu_notifier.h>
 #include <linux/iomap.h>
+#include <asm/pgalloc.h>
 #include "internal.h"
 
 #define CREATE_TRACE_POINTS
@@ -1407,7 +1408,9 @@ static vm_fault_t dax_pmd_load_hole(struct xa_state *xas, struct vm_fault *vmf,
 {
 	struct address_space *mapping = vmf->vma->vm_file->f_mapping;
 	unsigned long pmd_addr = vmf->address & PMD_MASK;
+	struct vm_area_struct *vma = vmf->vma;
 	struct inode *inode = mapping->host;
+	pgtable_t pgtable = NULL;
 	struct page *zero_page;
 	spinlock_t *ptl;
 	pmd_t pmd_entry;
@@ -1422,12 +1425,22 @@ static vm_fault_t dax_pmd_load_hole(struct xa_state *xas, struct vm_fault *vmf,
 	*entry = dax_insert_entry(xas, mapping, vmf, *entry, pfn,
 			DAX_PMD | DAX_ZERO_PAGE, false);
 
+	if (arch_needs_pgtable_deposit()) {
+		pgtable = pte_alloc_one(vma->vm_mm);
+		if (!pgtable)
+			return VM_FAULT_OOM;
+	}
+
 	ptl = pmd_lock(vmf->vma->vm_mm, vmf->pmd);
 	if (!pmd_none(*(vmf->pmd))) {
 		spin_unlock(ptl);
 		goto fallback;
 	}
 
+	if (pgtable) {
+		pgtable_trans_huge_deposit(vma->vm_mm, vmf->pmd, pgtable);
+		mm_inc_nr_ptes(vma->vm_mm);
+	}
 	pmd_entry = mk_pmd(zero_page, vmf->vma->vm_page_prot);
 	pmd_entry = pmd_mkhuge(pmd_entry);
 	set_pmd_at(vmf->vma->vm_mm, pmd_addr, vmf->pmd, pmd_entry);
@@ -1436,6 +1449,8 @@ static vm_fault_t dax_pmd_load_hole(struct xa_state *xas, struct vm_fault *vmf,
 	return VM_FAULT_NOPAGE;
 
 fallback:
+	if (pgtable)
+		pte_free(vma->vm_mm, pgtable);
 	trace_dax_pmd_load_hole_fallback(inode, vmf, zero_page, *entry);
 	return VM_FAULT_FALLBACK;
 }
diff --git a/fs/debugfs/inode.c b/fs/debugfs/inode.c
index 95b5e78c22b1..f25daa207421 100644
--- a/fs/debugfs/inode.c
+++ b/fs/debugfs/inode.c
@@ -163,19 +163,24 @@ static int debugfs_show_options(struct seq_file *m, struct dentry *root)
 	return 0;
 }
 
-static void debugfs_evict_inode(struct inode *inode)
+static void debugfs_i_callback(struct rcu_head *head)
 {
-	truncate_inode_pages_final(&inode->i_data);
-	clear_inode(inode);
+	struct inode *inode = container_of(head, struct inode, i_rcu);
 	if (S_ISLNK(inode->i_mode))
 		kfree(inode->i_link);
+	free_inode_nonrcu(inode);
+}
+
+static void debugfs_destroy_inode(struct inode *inode)
+{
+	call_rcu(&inode->i_rcu, debugfs_i_callback);
 }
 
 static const struct super_operations debugfs_super_operations = {
 	.statfs		= simple_statfs,
 	.remount_fs	= debugfs_remount,
 	.show_options	= debugfs_show_options,
-	.evict_inode	= debugfs_evict_inode,
+	.destroy_inode	= debugfs_destroy_inode,
 };
 
 static void debugfs_release_dentry(struct dentry *dentry)
diff --git a/fs/ecryptfs/crypto.c b/fs/ecryptfs/crypto.c
index f664da55234e..491cf5baa8c2 100644
--- a/fs/ecryptfs/crypto.c
+++ b/fs/ecryptfs/crypto.c
@@ -68,7 +68,6 @@ static int ecryptfs_hash_digest(struct crypto_shash *tfm,
 	int err;
 
 	desc->tfm = tfm;
-	desc->flags = CRYPTO_TFM_REQ_MAY_SLEEP;
 	err = crypto_shash_digest(desc, src, len, dst);
 	shash_desc_zero(desc);
 	return err;
diff --git a/fs/ecryptfs/keystore.c b/fs/ecryptfs/keystore.c
index e74fe84d0886..90fbac5d485b 100644
--- a/fs/ecryptfs/keystore.c
+++ b/fs/ecryptfs/keystore.c
@@ -769,7 +769,6 @@ ecryptfs_write_tag_70_packet(char *dest, size_t *remaining_bytes,
 	}
 
 	s->hash_desc->tfm = s->hash_tfm;
-	s->hash_desc->flags = CRYPTO_TFM_REQ_MAY_SLEEP;
 
 	rc = crypto_shash_digest(s->hash_desc,
 				 (u8 *)s->auth_tok->token.password.session_key_encryption_key,
diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h
index 82ffdacdc7fa..0833b5fc0668 100644
--- a/fs/ext4/ext4.h
+++ b/fs/ext4/ext4.h
@@ -2024,7 +2024,6 @@ static inline u32 ext4_chksum(struct ext4_sb_info *sbi, u32 crc,
 	BUG_ON(crypto_shash_descsize(sbi->s_chksum_driver)!=sizeof(desc.ctx));
 
 	desc.shash.tfm = sbi->s_chksum_driver;
-	desc.shash.flags = 0;
 	*(u32 *)desc.ctx = crc;
 
 	BUG_ON(crypto_shash_update(&desc.shash, address, length));
diff --git a/fs/f2fs/f2fs.h b/fs/f2fs/f2fs.h
index 87f75ebd2fd6..21b0ab6bd15a 100644
--- a/fs/f2fs/f2fs.h
+++ b/fs/f2fs/f2fs.h
@@ -1422,7 +1422,6 @@ static inline u32 __f2fs_crc32(struct f2fs_sb_info *sbi, u32 crc,
 	BUG_ON(crypto_shash_descsize(sbi->s_chksum_driver) != sizeof(desc.ctx));
 
 	desc.shash.tfm = sbi->s_chksum_driver;
-	desc.shash.flags = 0;
 	*(u32 *)desc.ctx = crc;
 
 	err = crypto_shash_update(&desc.shash, address, length);
diff --git a/fs/fs_parser.c b/fs/fs_parser.c
index 842e8f749db6..570d71043acf 100644
--- a/fs/fs_parser.c
+++ b/fs/fs_parser.c
@@ -410,7 +410,7 @@ bool fs_validate_description(const struct fs_parameter_description *desc)
 			for (param = desc->specs; param->name; param++) {
 				if (param->opt == e->opt &&
 				    param->type != fs_param_is_enum) {
-					pr_err("VALIDATE %s: e[%lu] enum val for %s\n",
+					pr_err("VALIDATE %s: e[%tu] enum val for %s\n",
 					       name, e - desc->enums, param->name);
 					good = false;
 				}
diff --git a/fs/fuse/dev.c b/fs/fuse/dev.c
index 8a63e52785e9..9971a35cf1ef 100644
--- a/fs/fuse/dev.c
+++ b/fs/fuse/dev.c
@@ -2056,10 +2056,8 @@ static ssize_t fuse_dev_splice_write(struct pipe_inode_info *pipe,
 		rem += pipe->bufs[(pipe->curbuf + idx) & (pipe->buffers - 1)].len;
 
 	ret = -EINVAL;
-	if (rem < len) {
-		pipe_unlock(pipe);
-		goto out;
-	}
+	if (rem < len)
+		goto out_free;
 
 	rem = len;
 	while (rem) {
@@ -2077,7 +2075,9 @@ static ssize_t fuse_dev_splice_write(struct pipe_inode_info *pipe,
 			pipe->curbuf = (pipe->curbuf + 1) & (pipe->buffers - 1);
 			pipe->nrbufs--;
 		} else {
-			pipe_buf_get(pipe, ibuf);
+			if (!pipe_buf_get(pipe, ibuf))
+				goto out_free;
+
 			*obuf = *ibuf;
 			obuf->flags &= ~PIPE_BUF_FLAG_GIFT;
 			obuf->len = rem;
@@ -2100,11 +2100,11 @@ static ssize_t fuse_dev_splice_write(struct pipe_inode_info *pipe,
 	ret = fuse_dev_do_write(fud, &cs, len);
 
 	pipe_lock(pipe);
+out_free:
 	for (idx = 0; idx < nbuf; idx++)
 		pipe_buf_release(pipe, &bufs[idx]);
 	pipe_unlock(pipe);
 
-out:
 	kvfree(bufs);
 	return ret;
 }
diff --git a/fs/hugetlbfs/inode.c b/fs/hugetlbfs/inode.c
index ec32fece5e1e..9285dd4f4b1c 100644
--- a/fs/hugetlbfs/inode.c
+++ b/fs/hugetlbfs/inode.c
@@ -755,11 +755,17 @@ static struct inode *hugetlbfs_get_inode(struct super_block *sb,
 					umode_t mode, dev_t dev)
 {
 	struct inode *inode;
-	struct resv_map *resv_map;
+	struct resv_map *resv_map = NULL;
 
-	resv_map = resv_map_alloc();
-	if (!resv_map)
-		return NULL;
+	/*
+	 * Reserve maps are only needed for inodes that can have associated
+	 * page allocations.
+	 */
+	if (S_ISREG(mode) || S_ISLNK(mode)) {
+		resv_map = resv_map_alloc();
+		if (!resv_map)
+			return NULL;
+	}
 
 	inode = new_inode(sb);
 	if (inode) {
@@ -794,8 +800,10 @@ static struct inode *hugetlbfs_get_inode(struct super_block *sb,
 			break;
 		}
 		lockdep_annotate_inode_mutex_key(inode);
-	} else
-		kref_put(&resv_map->refs, resv_map_release);
+	} else {
+		if (resv_map)
+			kref_put(&resv_map->refs, resv_map_release);
+	}
 
 	return inode;
 }
diff --git a/fs/inode.c b/fs/inode.c
index e9d97add2b36..9a453f3637f8 100644
--- a/fs/inode.c
+++ b/fs/inode.c
@@ -1817,8 +1817,13 @@ int file_remove_privs(struct file *file)
 	int kill;
 	int error = 0;
 
-	/* Fast path for nothing security related */
-	if (IS_NOSEC(inode))
+	/*
+	 * Fast path for nothing security related.
+	 * As well for non-regular files, e.g. blkdev inodes.
+	 * For example, blkdev_write_iter() might get here
+	 * trying to remove privs which it is not allowed to.
+	 */
+	if (IS_NOSEC(inode) || !S_ISREG(inode->i_mode))
 		return 0;
 
 	kill = dentry_needs_remove_privs(dentry);
diff --git a/fs/io_uring.c b/fs/io_uring.c
index 6aaa30580a2b..84efb8956734 100644
--- a/fs/io_uring.c
+++ b/fs/io_uring.c
@@ -4,15 +4,28 @@
  * supporting fast/efficient IO.
  *
  * A note on the read/write ordering memory barriers that are matched between
- * the application and kernel side. When the application reads the CQ ring
- * tail, it must use an appropriate smp_rmb() to order with the smp_wmb()
- * the kernel uses after writing the tail. Failure to do so could cause a
- * delay in when the application notices that completion events available.
- * This isn't a fatal condition. Likewise, the application must use an
- * appropriate smp_wmb() both before writing the SQ tail, and after writing
- * the SQ tail. The first one orders the sqe writes with the tail write, and
- * the latter is paired with the smp_rmb() the kernel will issue before
- * reading the SQ tail on submission.
+ * the application and kernel side.
+ *
+ * After the application reads the CQ ring tail, it must use an
+ * appropriate smp_rmb() to pair with the smp_wmb() the kernel uses
+ * before writing the tail (using smp_load_acquire to read the tail will
+ * do). It also needs a smp_mb() before updating CQ head (ordering the
+ * entry load(s) with the head store), pairing with an implicit barrier
+ * through a control-dependency in io_get_cqring (smp_store_release to
+ * store head will do). Failure to do so could lead to reading invalid
+ * CQ entries.
+ *
+ * Likewise, the application must use an appropriate smp_wmb() before
+ * writing the SQ tail (ordering SQ entry stores with the tail store),
+ * which pairs with smp_load_acquire in io_get_sqring (smp_store_release
+ * to store the tail will do). And it needs a barrier ordering the SQ
+ * head load before writing new SQ entries (smp_load_acquire to read
+ * head will do).
+ *
+ * When using the SQ poll thread (IORING_SETUP_SQPOLL), the application
+ * needs to check the SQ flags for IORING_SQ_NEED_WAKEUP *after*
+ * updating the SQ tail; a full memory barrier smp_mb() is needed
+ * between.
  *
  * Also see the examples in the liburing library:
  *
@@ -70,20 +83,108 @@ struct io_uring {
 	u32 tail ____cacheline_aligned_in_smp;
 };
 
+/*
+ * This data is shared with the application through the mmap at offset
+ * IORING_OFF_SQ_RING.
+ *
+ * The offsets to the member fields are published through struct
+ * io_sqring_offsets when calling io_uring_setup.
+ */
 struct io_sq_ring {
+	/*
+	 * Head and tail offsets into the ring; the offsets need to be
+	 * masked to get valid indices.
+	 *
+	 * The kernel controls head and the application controls tail.
+	 */
 	struct io_uring		r;
+	/*
+	 * Bitmask to apply to head and tail offsets (constant, equals
+	 * ring_entries - 1)
+	 */
 	u32			ring_mask;
+	/* Ring size (constant, power of 2) */
 	u32			ring_entries;
+	/*
+	 * Number of invalid entries dropped by the kernel due to
+	 * invalid index stored in array
+	 *
+	 * Written by the kernel, shouldn't be modified by the
+	 * application (i.e. get number of "new events" by comparing to
+	 * cached value).
+	 *
+	 * After a new SQ head value was read by the application this
+	 * counter includes all submissions that were dropped reaching
+	 * the new SQ head (and possibly more).
+	 */
 	u32			dropped;
+	/*
+	 * Runtime flags
+	 *
+	 * Written by the kernel, shouldn't be modified by the
+	 * application.
+	 *
+	 * The application needs a full memory barrier before checking
+	 * for IORING_SQ_NEED_WAKEUP after updating the sq tail.
+	 */
 	u32			flags;
+	/*
+	 * Ring buffer of indices into array of io_uring_sqe, which is
+	 * mmapped by the application using the IORING_OFF_SQES offset.
+	 *
+	 * This indirection could e.g. be used to assign fixed
+	 * io_uring_sqe entries to operations and only submit them to
+	 * the queue when needed.
+	 *
+	 * The kernel modifies neither the indices array nor the entries
+	 * array.
+	 */
 	u32			array[];
 };
 
+/*
+ * This data is shared with the application through the mmap at offset
+ * IORING_OFF_CQ_RING.
+ *
+ * The offsets to the member fields are published through struct
+ * io_cqring_offsets when calling io_uring_setup.
+ */
 struct io_cq_ring {
+	/*
+	 * Head and tail offsets into the ring; the offsets need to be
+	 * masked to get valid indices.
+	 *
+	 * The application controls head and the kernel tail.
+	 */
 	struct io_uring		r;
+	/*
+	 * Bitmask to apply to head and tail offsets (constant, equals
+	 * ring_entries - 1)
+	 */
 	u32			ring_mask;
+	/* Ring size (constant, power of 2) */
 	u32			ring_entries;
+	/*
+	 * Number of completion events lost because the queue was full;
+	 * this should be avoided by the application by making sure
+	 * there are not more requests pending thatn there is space in
+	 * the completion queue.
+	 *
+	 * Written by the kernel, shouldn't be modified by the
+	 * application (i.e. get number of "new events" by comparing to
+	 * cached value).
+	 *
+	 * As completion events come in out of order this counter is not
+	 * ordered with any other data.
+	 */
 	u32			overflow;
+	/*
+	 * Ring buffer of completion events.
+	 *
+	 * The kernel writes completion events fresh every time they are
+	 * produced, so the application is allowed to modify pending
+	 * entries.
+	 */
 	struct io_uring_cqe	cqes[];
 };
 
@@ -221,7 +322,7 @@ struct io_kiocb {
 	struct list_head	list;
 	unsigned int		flags;
 	refcount_t		refs;
-#define REQ_F_FORCE_NONBLOCK	1	/* inline submission attempt */
+#define REQ_F_NOWAIT		1	/* must not punt to workers */
 #define REQ_F_IOPOLL_COMPLETED	2	/* polled IO has completed */
 #define REQ_F_FIXED_FILE	4	/* ctx owns file */
 #define REQ_F_SEQ_PREV		8	/* sequential with previous */
@@ -317,12 +418,6 @@ static void io_commit_cqring(struct io_ring_ctx *ctx)
 		/* order cqe stores with ring update */
 		smp_store_release(&ring->r.tail, ctx->cached_cq_tail);
 
-		/*
-		 * Write sider barrier of tail update, app has read side. See
-		 * comment at the top of this file.
-		 */
-		smp_wmb();
-
 		if (wq_has_sleeper(&ctx->cq_wait)) {
 			wake_up_interruptible(&ctx->cq_wait);
 			kill_fasync(&ctx->cq_fasync, SIGIO, POLL_IN);
@@ -336,9 +431,12 @@ static struct io_uring_cqe *io_get_cqring(struct io_ring_ctx *ctx)
 	unsigned tail;
 
 	tail = ctx->cached_cq_tail;
-	/* See comment at the top of the file */
-	smp_rmb();
-	if (tail + 1 == READ_ONCE(ring->r.head))
+	/*
+	 * writes to the cq entry need to come after reading head; the
+	 * control dependency is enough as we're using WRITE_ONCE to
+	 * fill the cq entry
+	 */
+	if (tail - READ_ONCE(ring->r.head) == ring->ring_entries)
 		return NULL;
 
 	ctx->cached_cq_tail++;
@@ -682,11 +780,9 @@ static void io_iopoll_req_issued(struct io_kiocb *req)
 		list_add_tail(&req->list, &ctx->poll_list);
 }
 
-static void io_file_put(struct io_submit_state *state, struct file *file)
+static void io_file_put(struct io_submit_state *state)
 {
-	if (!state) {
-		fput(file);
-	} else if (state->file) {
+	if (state->file) {
 		int diff = state->has_refs - state->used_refs;
 
 		if (diff)
@@ -711,7 +807,7 @@ static struct file *io_file_get(struct io_submit_state *state, int fd)
 			state->ios_left--;
 			return state->file;
 		}
-		io_file_put(state, NULL);
+		io_file_put(state);
 	}
 	state->file = fget_many(fd, state->ios_left);
 	if (!state->file)
@@ -742,7 +838,7 @@ static bool io_file_supports_async(struct file *file)
 }
 
 static int io_prep_rw(struct io_kiocb *req, const struct sqe_submit *s,
-		      bool force_nonblock, struct io_submit_state *state)
+		      bool force_nonblock)
 {
 	const struct io_uring_sqe *sqe = s->sqe;
 	struct io_ring_ctx *ctx = req->ctx;
@@ -776,10 +872,14 @@ static int io_prep_rw(struct io_kiocb *req, const struct sqe_submit *s,
 	ret = kiocb_set_rw_flags(kiocb, READ_ONCE(sqe->rw_flags));
 	if (unlikely(ret))
 		return ret;
-	if (force_nonblock) {
+
+	/* don't allow async punt if RWF_NOWAIT was requested */
+	if (kiocb->ki_flags & IOCB_NOWAIT)
+		req->flags |= REQ_F_NOWAIT;
+
+	if (force_nonblock)
 		kiocb->ki_flags |= IOCB_NOWAIT;
-		req->flags |= REQ_F_FORCE_NONBLOCK;
-	}
+
 	if (ctx->flags & IORING_SETUP_IOPOLL) {
 		if (!(kiocb->ki_flags & IOCB_DIRECT) ||
 		    !kiocb->ki_filp->f_op->iopoll)
@@ -940,7 +1040,7 @@ static void io_async_list_note(int rw, struct io_kiocb *req, size_t len)
 }
 
 static int io_read(struct io_kiocb *req, const struct sqe_submit *s,
-		   bool force_nonblock, struct io_submit_state *state)
+		   bool force_nonblock)
 {
 	struct iovec inline_vecs[UIO_FASTIOV], *iovec = inline_vecs;
 	struct kiocb *kiocb = &req->rw;
@@ -949,7 +1049,7 @@ static int io_read(struct io_kiocb *req, const struct sqe_submit *s,
 	size_t iov_count;
 	int ret;
 
-	ret = io_prep_rw(req, s, force_nonblock, state);
+	ret = io_prep_rw(req, s, force_nonblock);
 	if (ret)
 		return ret;
 	file = kiocb->ki_filp;
@@ -987,7 +1087,7 @@ static int io_read(struct io_kiocb *req, const struct sqe_submit *s,
 }
 
 static int io_write(struct io_kiocb *req, const struct sqe_submit *s,
-		    bool force_nonblock, struct io_submit_state *state)
+		    bool force_nonblock)
 {
 	struct iovec inline_vecs[UIO_FASTIOV], *iovec = inline_vecs;
 	struct kiocb *kiocb = &req->rw;
@@ -996,7 +1096,7 @@ static int io_write(struct io_kiocb *req, const struct sqe_submit *s,
 	size_t iov_count;
 	int ret;
 
-	ret = io_prep_rw(req, s, force_nonblock, state);
+	ret = io_prep_rw(req, s, force_nonblock);
 	if (ret)
 		return ret;
 
@@ -1022,6 +1122,8 @@ static int io_write(struct io_kiocb *req, const struct sqe_submit *s,
 
 	ret = rw_verify_area(WRITE, file, &kiocb->ki_pos, iov_count);
 	if (!ret) {
+		ssize_t ret2;
+
 		/*
 		 * Open-code file_start_write here to grab freeze protection,
 		 * which will be released by another thread in
@@ -1036,7 +1138,19 @@ static int io_write(struct io_kiocb *req, const struct sqe_submit *s,
 						SB_FREEZE_WRITE);
 		}
 		kiocb->ki_flags |= IOCB_WRITE;
-		io_rw_done(kiocb, call_write_iter(file, kiocb, &iter));
+
+		ret2 = call_write_iter(file, kiocb, &iter);
+		if (!force_nonblock || ret2 != -EAGAIN) {
+			io_rw_done(kiocb, ret2);
+		} else {
+			/*
+			 * If ->needs_lock is true, we're already in async
+			 * context.
+			 */
+			if (!s->needs_lock)
+				io_async_list_note(WRITE, req, iov_count);
+			ret = -EAGAIN;
+		}
 	}
 out_free:
 	kfree(iovec);
@@ -1324,8 +1438,7 @@ static int io_poll_add(struct io_kiocb *req, const struct io_uring_sqe *sqe)
 }
 
 static int __io_submit_sqe(struct io_ring_ctx *ctx, struct io_kiocb *req,
-			   const struct sqe_submit *s, bool force_nonblock,
-			   struct io_submit_state *state)
+			   const struct sqe_submit *s, bool force_nonblock)
 {
 	int ret, opcode;
 
@@ -1341,18 +1454,18 @@ static int __io_submit_sqe(struct io_ring_ctx *ctx, struct io_kiocb *req,
 	case IORING_OP_READV:
 		if (unlikely(s->sqe->buf_index))
 			return -EINVAL;
-		ret = io_read(req, s, force_nonblock, state);
+		ret = io_read(req, s, force_nonblock);
 		break;
 	case IORING_OP_WRITEV:
 		if (unlikely(s->sqe->buf_index))
 			return -EINVAL;
-		ret = io_write(req, s, force_nonblock, state);
+		ret = io_write(req, s, force_nonblock);
 		break;
 	case IORING_OP_READ_FIXED:
-		ret = io_read(req, s, force_nonblock, state);
+		ret = io_read(req, s, force_nonblock);
 		break;
 	case IORING_OP_WRITE_FIXED:
-		ret = io_write(req, s, force_nonblock, state);
+		ret = io_write(req, s, force_nonblock);
 		break;
 	case IORING_OP_FSYNC:
 		ret = io_fsync(req, s->sqe, force_nonblock);
@@ -1425,8 +1538,7 @@ restart:
 		struct sqe_submit *s = &req->submit;
 		const struct io_uring_sqe *sqe = s->sqe;
 
-		/* Ensure we clear previously set forced non-block flag */
-		req->flags &= ~REQ_F_FORCE_NONBLOCK;
+		/* Ensure we clear previously set non-block flag */
 		req->rw.ki_flags &= ~IOCB_NOWAIT;
 
 		ret = 0;
@@ -1445,7 +1557,7 @@ restart:
 			s->has_user = cur_mm != NULL;
 			s->needs_lock = true;
 			do {
-				ret = __io_submit_sqe(ctx, req, s, false, NULL);
+				ret = __io_submit_sqe(ctx, req, s, false);
 				/*
 				 * We can get EAGAIN for polled IO even though
 				 * we're forcing a sync submission from here,
@@ -1456,10 +1568,11 @@ restart:
 					break;
 				cond_resched();
 			} while (1);
-
-			/* drop submission reference */
-			io_put_req(req);
 		}
+
+		/* drop submission reference */
+		io_put_req(req);
+
 		if (ret) {
 			io_cqring_add_event(ctx, sqe->user_data, ret, 0);
 			io_put_req(req);
@@ -1611,8 +1724,8 @@ static int io_submit_sqe(struct io_ring_ctx *ctx, struct sqe_submit *s,
 	if (unlikely(ret))
 		goto out;
 
-	ret = __io_submit_sqe(ctx, req, s, true, state);
-	if (ret == -EAGAIN) {
+	ret = __io_submit_sqe(ctx, req, s, true);
+	if (ret == -EAGAIN && !(req->flags & REQ_F_NOWAIT)) {
 		struct io_uring_sqe *sqe_copy;
 
 		sqe_copy = kmalloc(sizeof(*sqe_copy), GFP_KERNEL);
@@ -1657,7 +1770,7 @@ out:
 static void io_submit_state_end(struct io_submit_state *state)
 {
 	blk_finish_plug(&state->plug);
-	io_file_put(state, NULL);
+	io_file_put(state);
 	if (state->free_reqs)
 		kmem_cache_free_bulk(req_cachep, state->free_reqs,
 					&state->reqs[state->cur_req]);
@@ -1686,24 +1799,10 @@ static void io_commit_sqring(struct io_ring_ctx *ctx)
 		 * write new data to them.
 		 */
 		smp_store_release(&ring->r.head, ctx->cached_sq_head);
-
-		/*
-		 * write side barrier of head update, app has read side. See
-		 * comment at the top of this file
-		 */
-		smp_wmb();
 	}
 }
 
 /*
- * Undo last io_get_sqring()
- */
-static void io_drop_sqring(struct io_ring_ctx *ctx)
-{
-	ctx->cached_sq_head--;
-}
-
-/*
  * Fetch an sqe, if one is available. Note that s->sqe will point to memory
  * that is mapped by userspace. This means that care needs to be taken to
  * ensure that reads are stable, as we cannot rely on userspace always
@@ -1725,9 +1824,8 @@ static bool io_get_sqring(struct io_ring_ctx *ctx, struct sqe_submit *s)
 	 *    though the application is the one updating it.
 	 */
 	head = ctx->cached_sq_head;
-	/* See comment at the top of this file */
-	smp_rmb();
-	if (head == READ_ONCE(ring->r.tail))
+	/* make sure SQ entry isn't read before tail */
+	if (head == smp_load_acquire(&ring->r.tail))
 		return false;
 
 	head = READ_ONCE(ring->array[head & ctx->sq_mask]);
@@ -1741,8 +1839,6 @@ static bool io_get_sqring(struct io_ring_ctx *ctx, struct sqe_submit *s)
 	/* drop invalid entries */
 	ctx->cached_sq_head++;
 	ring->dropped++;
-	/* See comment at the top of this file */
-	smp_wmb();
 	return false;
 }
 
@@ -1852,7 +1948,8 @@ static int io_sq_thread(void *data)
 
 			/* Tell userspace we may need a wakeup call */
 			ctx->sq_ring->flags |= IORING_SQ_NEED_WAKEUP;
-			smp_wmb();
+			/* make sure to read SQ tail after writing flags */
+			smp_mb();
 
 			if (!io_get_sqring(ctx, &sqes[0])) {
 				if (kthread_should_stop()) {
@@ -1865,13 +1962,11 @@ static int io_sq_thread(void *data)
 				finish_wait(&ctx->sqo_wait, &wait);
 
 				ctx->sq_ring->flags &= ~IORING_SQ_NEED_WAKEUP;
-				smp_wmb();
 				continue;
 			}
 			finish_wait(&ctx->sqo_wait, &wait);
 
 			ctx->sq_ring->flags &= ~IORING_SQ_NEED_WAKEUP;
-			smp_wmb();
 		}
 
 		i = 0;
@@ -1906,13 +2001,17 @@ static int io_sq_thread(void *data)
 		unuse_mm(cur_mm);
 		mmput(cur_mm);
 	}
+
+	if (kthread_should_park())
+		kthread_parkme();
+
 	return 0;
 }
 
 static int io_ring_submit(struct io_ring_ctx *ctx, unsigned int to_submit)
 {
 	struct io_submit_state state, *statep = NULL;
-	int i, ret = 0, submit = 0;
+	int i, submit = 0;
 
 	if (to_submit > IO_PLUG_THRESHOLD) {
 		io_submit_state_start(&state, ctx, to_submit);
@@ -1921,6 +2020,7 @@ static int io_ring_submit(struct io_ring_ctx *ctx, unsigned int to_submit)
 
 	for (i = 0; i < to_submit; i++) {
 		struct sqe_submit s;
+		int ret;
 
 		if (!io_get_sqring(ctx, &s))
 			break;
@@ -1928,21 +2028,18 @@ static int io_ring_submit(struct io_ring_ctx *ctx, unsigned int to_submit)
 		s.has_user = true;
 		s.needs_lock = false;
 		s.needs_fixed_file = false;
+		submit++;
 
 		ret = io_submit_sqe(ctx, &s, statep);
-		if (ret) {
-			io_drop_sqring(ctx);
-			break;
-		}
-
-		submit++;
+		if (ret)
+			io_cqring_add_event(ctx, s.sqe->user_data, ret, 0);
 	}
 	io_commit_sqring(ctx);
 
 	if (statep)
 		io_submit_state_end(statep);
 
-	return submit ? submit : ret;
+	return submit;
 }
 
 static unsigned io_cqring_events(struct io_cq_ring *ring)
@@ -1968,7 +2065,15 @@ static int io_cqring_wait(struct io_ring_ctx *ctx, int min_events,
 		return 0;
 
 	if (sig) {
-		ret = set_user_sigmask(sig, &ksigmask, &sigsaved, sigsz);
+#ifdef CONFIG_COMPAT
+		if (in_compat_syscall())
+			ret = set_compat_user_sigmask((const compat_sigset_t __user *)sig,
+						      &ksigmask, &sigsaved, sigsz);
+		else
+#endif
+			ret = set_user_sigmask(sig, &ksigmask,
+					       &sigsaved, sigsz);
+
 		if (ret)
 			return ret;
 	}
@@ -2032,6 +2137,7 @@ static void io_sq_thread_stop(struct io_ring_ctx *ctx)
 	if (ctx->sqo_thread) {
 		ctx->sqo_stop = 1;
 		mb();
+		kthread_park(ctx->sqo_thread);
 		kthread_stop(ctx->sqo_thread);
 		ctx->sqo_thread = NULL;
 	}
@@ -2193,6 +2299,7 @@ static int io_sqe_files_register(struct io_ring_ctx *ctx, void __user *arg,
 			fput(ctx->user_files[i]);
 
 		kfree(ctx->user_files);
+		ctx->user_files = NULL;
 		ctx->nr_user_files = 0;
 		return ret;
 	}
@@ -2213,19 +2320,23 @@ static int io_sq_offload_start(struct io_ring_ctx *ctx,
 	mmgrab(current->mm);
 	ctx->sqo_mm = current->mm;
 
-	ctx->sq_thread_idle = msecs_to_jiffies(p->sq_thread_idle);
-	if (!ctx->sq_thread_idle)
-		ctx->sq_thread_idle = HZ;
+	if (ctx->flags & IORING_SETUP_SQPOLL) {
+		ret = -EPERM;
+		if (!capable(CAP_SYS_ADMIN))
+			goto err;
 
-	ret = -EINVAL;
-	if (!cpu_possible(p->sq_thread_cpu))
-		goto err;
+		ctx->sq_thread_idle = msecs_to_jiffies(p->sq_thread_idle);
+		if (!ctx->sq_thread_idle)
+			ctx->sq_thread_idle = HZ;
 
-	if (ctx->flags & IORING_SETUP_SQPOLL) {
 		if (p->flags & IORING_SETUP_SQ_AFF) {
-			int cpu;
+			int cpu = array_index_nospec(p->sq_thread_cpu,
+							nr_cpu_ids);
+
+			ret = -EINVAL;
+			if (!cpu_possible(cpu))
+				goto err;
 
-			cpu = array_index_nospec(p->sq_thread_cpu, NR_CPUS);
 			ctx->sqo_thread = kthread_create_on_cpu(io_sq_thread,
 							ctx, cpu,
 							"io_uring-sq");
@@ -2286,8 +2397,12 @@ static int io_account_mem(struct user_struct *user, unsigned long nr_pages)
 
 static void io_mem_free(void *ptr)
 {
-	struct page *page = virt_to_head_page(ptr);
+	struct page *page;
+
+	if (!ptr)
+		return;
 
+	page = virt_to_head_page(ptr);
 	if (put_page_testzero(page))
 		free_compound_page(page);
 }
@@ -2328,7 +2443,7 @@ static int io_sqe_buffer_unregister(struct io_ring_ctx *ctx)
 
 		if (ctx->account_mem)
 			io_unaccount_mem(ctx->user, imu->nr_bvecs);
-		kfree(imu->bvec);
+		kvfree(imu->bvec);
 		imu->nr_bvecs = 0;
 	}
 
@@ -2420,9 +2535,9 @@ static int io_sqe_buffer_register(struct io_ring_ctx *ctx, void __user *arg,
 		if (!pages || nr_pages > got_pages) {
 			kfree(vmas);
 			kfree(pages);
-			pages = kmalloc_array(nr_pages, sizeof(struct page *),
+			pages = kvmalloc_array(nr_pages, sizeof(struct page *),
 						GFP_KERNEL);
-			vmas = kmalloc_array(nr_pages,
+			vmas = kvmalloc_array(nr_pages,
 					sizeof(struct vm_area_struct *),
 					GFP_KERNEL);
 			if (!pages || !vmas) {
@@ -2434,7 +2549,7 @@ static int io_sqe_buffer_register(struct io_ring_ctx *ctx, void __user *arg,
 			got_pages = nr_pages;
 		}
 
-		imu->bvec = kmalloc_array(nr_pages, sizeof(struct bio_vec),
+		imu->bvec = kvmalloc_array(nr_pages, sizeof(struct bio_vec),
 						GFP_KERNEL);
 		ret = -ENOMEM;
 		if (!imu->bvec) {
@@ -2473,6 +2588,7 @@ static int io_sqe_buffer_register(struct io_ring_ctx *ctx, void __user *arg,
 			}
 			if (ctx->account_mem)
 				io_unaccount_mem(ctx->user, nr_pages);
+			kvfree(imu->bvec);
 			goto err;
 		}
 
@@ -2495,12 +2611,12 @@ static int io_sqe_buffer_register(struct io_ring_ctx *ctx, void __user *arg,
 
 		ctx->nr_user_bufs++;
 	}
-	kfree(pages);
-	kfree(vmas);
+	kvfree(pages);
+	kvfree(vmas);
 	return 0;
 err:
-	kfree(pages);
-	kfree(vmas);
+	kvfree(pages);
+	kvfree(vmas);
 	io_sqe_buffer_unregister(ctx);
 	return ret;
 }
@@ -2538,9 +2654,13 @@ static __poll_t io_uring_poll(struct file *file, poll_table *wait)
 	__poll_t mask = 0;
 
 	poll_wait(file, &ctx->cq_wait, wait);
-	/* See comment at the top of this file */
+	/*
+	 * synchronizes with barrier from wq_has_sleeper call in
+	 * io_commit_cqring
+	 */
 	smp_rmb();
-	if (READ_ONCE(ctx->sq_ring->r.tail) + 1 != ctx->cached_sq_head)
+	if (READ_ONCE(ctx->sq_ring->r.tail) - ctx->cached_sq_head !=
+	    ctx->sq_ring->ring_entries)
 		mask |= EPOLLOUT | EPOLLWRNORM;
 	if (READ_ONCE(ctx->cq_ring->r.head) != ctx->cached_cq_tail)
 		mask |= EPOLLIN | EPOLLRDNORM;
@@ -2651,24 +2771,12 @@ SYSCALL_DEFINE6(io_uring_enter, unsigned int, fd, u32, to_submit,
 		mutex_lock(&ctx->uring_lock);
 		submitted = io_ring_submit(ctx, to_submit);
 		mutex_unlock(&ctx->uring_lock);
-
-		if (submitted < 0)
-			goto out_ctx;
 	}
 	if (flags & IORING_ENTER_GETEVENTS) {
 		unsigned nr_events = 0;
 
 		min_complete = min(min_complete, ctx->cq_entries);
 
-		/*
-		 * The application could have included the 'to_submit' count
-		 * in how many events it wanted to wait for. If we failed to
-		 * submit the desired count, we may need to adjust the number
-		 * of events to poll/wait for.
-		 */
-		if (submitted < to_submit)
-			min_complete = min_t(unsigned, submitted, min_complete);
-
 		if (ctx->flags & IORING_SETUP_IOPOLL) {
 			mutex_lock(&ctx->uring_lock);
 			ret = io_iopoll_check(ctx, &nr_events, min_complete);
@@ -2714,17 +2822,12 @@ static int io_allocate_scq_urings(struct io_ring_ctx *ctx,
 		return -EOVERFLOW;
 
 	ctx->sq_sqes = io_mem_alloc(size);
-	if (!ctx->sq_sqes) {
-		io_mem_free(ctx->sq_ring);
+	if (!ctx->sq_sqes)
 		return -ENOMEM;
-	}
 
 	cq_ring = io_mem_alloc(struct_size(cq_ring, cqes, p->cq_entries));
-	if (!cq_ring) {
-		io_mem_free(ctx->sq_ring);
-		io_mem_free(ctx->sq_sqes);
+	if (!cq_ring)
 		return -ENOMEM;
-	}
 
 	ctx->cq_ring = cq_ring;
 	cq_ring->ring_mask = p->cq_entries - 1;
@@ -2895,11 +2998,31 @@ SYSCALL_DEFINE2(io_uring_setup, u32, entries,
 
 static int __io_uring_register(struct io_ring_ctx *ctx, unsigned opcode,
 			       void __user *arg, unsigned nr_args)
+	__releases(ctx->uring_lock)
+	__acquires(ctx->uring_lock)
 {
 	int ret;
 
+	/*
+	 * We're inside the ring mutex, if the ref is already dying, then
+	 * someone else killed the ctx or is already going through
+	 * io_uring_register().
+	 */
+	if (percpu_ref_is_dying(&ctx->refs))
+		return -ENXIO;
+
 	percpu_ref_kill(&ctx->refs);
+
+	/*
+	 * Drop uring mutex before waiting for references to exit. If another
+	 * thread is currently inside io_uring_enter() it might need to grab
+	 * the uring_lock to make progress. If we hold it here across the drain
+	 * wait, then we can deadlock. It's safe to drop the mutex here, since
+	 * no new references will come in after we've killed the percpu ref.
+	 */
+	mutex_unlock(&ctx->uring_lock);
 	wait_for_completion(&ctx->ctx_done);
+	mutex_lock(&ctx->uring_lock);
 
 	switch (opcode) {
 	case IORING_REGISTER_BUFFERS:
diff --git a/fs/jffs2/readinode.c b/fs/jffs2/readinode.c
index 389ea53ea487..bccfc40b3a74 100644
--- a/fs/jffs2/readinode.c
+++ b/fs/jffs2/readinode.c
@@ -1414,11 +1414,6 @@ void jffs2_do_clear_inode(struct jffs2_sb_info *c, struct jffs2_inode_info *f)
 
 	jffs2_kill_fragtree(&f->fragtree, deleted?c:NULL);
 
-	if (f->target) {
-		kfree(f->target);
-		f->target = NULL;
-	}
-
 	fds = f->dents;
 	while(fds) {
 		fd = fds;
diff --git a/fs/jffs2/super.c b/fs/jffs2/super.c
index bb6ae387469f..05d892c79339 100644
--- a/fs/jffs2/super.c
+++ b/fs/jffs2/super.c
@@ -47,7 +47,10 @@ static struct inode *jffs2_alloc_inode(struct super_block *sb)
 static void jffs2_i_callback(struct rcu_head *head)
 {
 	struct inode *inode = container_of(head, struct inode, i_rcu);
-	kmem_cache_free(jffs2_inode_cachep, JFFS2_INODE_INFO(inode));
+	struct jffs2_inode_info *f = JFFS2_INODE_INFO(inode);
+
+	kfree(f->target);
+	kmem_cache_free(jffs2_inode_cachep, f);
 }
 
 static void jffs2_destroy_inode(struct inode *inode)
diff --git a/fs/lockd/host.c b/fs/lockd/host.c
index 93fb7cf0b92b..f0b5c987d6ae 100644
--- a/fs/lockd/host.c
+++ b/fs/lockd/host.c
@@ -290,12 +290,11 @@ void nlmclnt_release_host(struct nlm_host *host)
 
 	WARN_ON_ONCE(host->h_server);
 
-	if (refcount_dec_and_test(&host->h_count)) {
+	if (refcount_dec_and_mutex_lock(&host->h_count, &nlm_host_mutex)) {
 		WARN_ON_ONCE(!list_empty(&host->h_lockowners));
 		WARN_ON_ONCE(!list_empty(&host->h_granted));
 		WARN_ON_ONCE(!list_empty(&host->h_reclaim));
 
-		mutex_lock(&nlm_host_mutex);
 		nlm_destroy_host_locked(host);
 		mutex_unlock(&nlm_host_mutex);
 	}
diff --git a/fs/locks.c b/fs/locks.c
index eaa1cfaf73b0..71d0c6c2aac5 100644
--- a/fs/locks.c
+++ b/fs/locks.c
@@ -1160,6 +1160,11 @@ static int posix_lock_inode(struct inode *inode, struct file_lock *request,
 			 */
 			error = -EDEADLK;
 			spin_lock(&blocked_lock_lock);
+			/*
+			 * Ensure that we don't find any locks blocked on this
+			 * request during deadlock detection.
+			 */
+			__locks_wake_up_blocks(request);
 			if (likely(!posix_locks_deadlock(request, fl))) {
 				error = FILE_LOCK_DEFERRED;
 				__locks_insert_block(fl, request,
diff --git a/fs/nfs/client.c b/fs/nfs/client.c
index fb1cf1a4bda2..90d71fda65ce 100644
--- a/fs/nfs/client.c
+++ b/fs/nfs/client.c
@@ -453,7 +453,7 @@ void nfs_init_timeout_values(struct rpc_timeout *to, int proto,
 	case XPRT_TRANSPORT_RDMA:
 		if (retrans == NFS_UNSPEC_RETRANS)
 			to->to_retries = NFS_DEF_TCP_RETRANS;
-		if (timeo == NFS_UNSPEC_TIMEO || to->to_retries == 0)
+		if (timeo == NFS_UNSPEC_TIMEO || to->to_initval == 0)
 			to->to_initval = NFS_DEF_TCP_TIMEO * HZ / 10;
 		if (to->to_initval > NFS_MAX_TCP_TIMEOUT)
 			to->to_initval = NFS_MAX_TCP_TIMEOUT;
diff --git a/fs/nfs/flexfilelayout/flexfilelayout.c b/fs/nfs/flexfilelayout/flexfilelayout.c
index f9264e1922a2..6673d4ff5a2a 100644
--- a/fs/nfs/flexfilelayout/flexfilelayout.c
+++ b/fs/nfs/flexfilelayout/flexfilelayout.c
@@ -1289,6 +1289,7 @@ static void ff_layout_io_track_ds_error(struct pnfs_layout_segment *lseg,
 static int ff_layout_read_done_cb(struct rpc_task *task,
 				struct nfs_pgio_header *hdr)
 {
+	int new_idx = hdr->pgio_mirror_idx;
 	int err;
 
 	trace_nfs4_pnfs_read(hdr, task->tk_status);
@@ -1307,7 +1308,7 @@ static int ff_layout_read_done_cb(struct rpc_task *task,
 	case -NFS4ERR_RESET_TO_PNFS:
 		if (ff_layout_choose_best_ds_for_read(hdr->lseg,
 					hdr->pgio_mirror_idx + 1,
-					&hdr->pgio_mirror_idx))
+					&new_idx))
 			goto out_layouterror;
 		set_bit(NFS_IOHDR_RESEND_PNFS, &hdr->flags);
 		return task->tk_status;
@@ -1320,7 +1321,9 @@ static int ff_layout_read_done_cb(struct rpc_task *task,
 
 	return 0;
 out_layouterror:
+	ff_layout_read_record_layoutstats_done(task, hdr);
 	ff_layout_send_layouterror(hdr->lseg);
+	hdr->pgio_mirror_idx = new_idx;
 out_eagain:
 	rpc_restart_call_prepare(task);
 	return -EAGAIN;
diff --git a/fs/nfs/nfs42proc.c b/fs/nfs/nfs42proc.c
index ff6f85fb676b..5196bfa7894d 100644
--- a/fs/nfs/nfs42proc.c
+++ b/fs/nfs/nfs42proc.c
@@ -329,9 +329,6 @@ ssize_t nfs42_proc_copy(struct file *src, loff_t pos_src,
 	};
 	ssize_t err, err2;
 
-	if (!nfs_server_capable(file_inode(dst), NFS_CAP_COPY))
-		return -EOPNOTSUPP;
-
 	src_lock = nfs_get_lock_context(nfs_file_open_context(src));
 	if (IS_ERR(src_lock))
 		return PTR_ERR(src_lock);
diff --git a/fs/nfs/nfs4file.c b/fs/nfs/nfs4file.c
index 45b2322e092d..00d17198ee12 100644
--- a/fs/nfs/nfs4file.c
+++ b/fs/nfs/nfs4file.c
@@ -133,8 +133,10 @@ static ssize_t nfs4_copy_file_range(struct file *file_in, loff_t pos_in,
 				    struct file *file_out, loff_t pos_out,
 				    size_t count, unsigned int flags)
 {
+	if (!nfs_server_capable(file_inode(file_out), NFS_CAP_COPY))
+		return -EOPNOTSUPP;
 	if (file_inode(file_in) == file_inode(file_out))
-		return -EINVAL;
+		return -EOPNOTSUPP;
 	return nfs42_proc_copy(file_in, pos_in, file_out, pos_out, count);
 }
 
diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c
index 4dbb0ee23432..741ff8c9c6ed 100644
--- a/fs/nfs/nfs4proc.c
+++ b/fs/nfs/nfs4proc.c
@@ -2933,7 +2933,8 @@ static int _nfs4_open_and_get_state(struct nfs4_opendata *opendata,
 	}
 
 out:
-	nfs4_sequence_free_slot(&opendata->o_res.seq_res);
+	if (!opendata->cancelled)
+		nfs4_sequence_free_slot(&opendata->o_res.seq_res);
 	return ret;
 }
 
@@ -6301,7 +6302,6 @@ static struct nfs4_unlockdata *nfs4_alloc_unlockdata(struct file_lock *fl,
 	p->arg.seqid = seqid;
 	p->res.seqid = seqid;
 	p->lsp = lsp;
-	refcount_inc(&lsp->ls_count);
 	/* Ensure we don't close file until we're done freeing locks! */
 	p->ctx = get_nfs_open_context(ctx);
 	p->l_ctx = nfs_get_lock_context(ctx);
@@ -6526,7 +6526,6 @@ static struct nfs4_lockdata *nfs4_alloc_lockdata(struct file_lock *fl,
 	p->res.lock_seqid = p->arg.lock_seqid;
 	p->lsp = lsp;
 	p->server = server;
-	refcount_inc(&lsp->ls_count);
 	p->ctx = get_nfs_open_context(ctx);
 	locks_init_lock(&p->fl);
 	locks_copy_lock(&p->fl, fl);
diff --git a/fs/nfs/nfs4xdr.c b/fs/nfs/nfs4xdr.c
index cfcabc33e24d..602446158bfb 100644
--- a/fs/nfs/nfs4xdr.c
+++ b/fs/nfs/nfs4xdr.c
@@ -2589,7 +2589,7 @@ static void nfs4_xdr_enc_getacl(struct rpc_rqst *req, struct xdr_stream *xdr,
 			ARRAY_SIZE(nfs4_acl_bitmap), &hdr);
 
 	rpc_prepare_reply_pages(req, args->acl_pages, 0,
-				args->acl_len, replen);
+				args->acl_len, replen + 1);
 	encode_nops(&hdr);
 }
 
@@ -2811,7 +2811,7 @@ static void nfs4_xdr_enc_fs_locations(struct rpc_rqst *req,
 	}
 
 	rpc_prepare_reply_pages(req, (struct page **)&args->page, 0,
-				PAGE_SIZE, replen);
+				PAGE_SIZE, replen + 1);
 	encode_nops(&hdr);
 }
 
diff --git a/fs/nfs/super.c b/fs/nfs/super.c
index 23790c7b2289..c27ac96a95bd 100644
--- a/fs/nfs/super.c
+++ b/fs/nfs/super.c
@@ -2041,7 +2041,8 @@ static int nfs23_validate_mount_data(void *options,
 		memcpy(sap, &data->addr, sizeof(data->addr));
 		args->nfs_server.addrlen = sizeof(data->addr);
 		args->nfs_server.port = ntohs(data->addr.sin_port);
-		if (!nfs_verify_server_address(sap))
+		if (sap->sa_family != AF_INET ||
+		    !nfs_verify_server_address(sap))
 			goto out_no_address;
 
 		if (!(data->flags & NFS_MOUNT_TCP))
diff --git a/fs/nfsd/nfs3proc.c b/fs/nfsd/nfs3proc.c
index 8f933e84cec1..9bc32af4e2da 100644
--- a/fs/nfsd/nfs3proc.c
+++ b/fs/nfsd/nfs3proc.c
@@ -442,7 +442,9 @@ nfsd3_proc_readdir(struct svc_rqst *rqstp)
 	struct nfsd3_readdirargs *argp = rqstp->rq_argp;
 	struct nfsd3_readdirres  *resp = rqstp->rq_resp;
 	__be32		nfserr;
-	int		count;
+	int		count = 0;
+	struct page	**p;
+	caddr_t		page_addr = NULL;
 
 	dprintk("nfsd: READDIR(3)  %s %d bytes at %d\n",
 				SVCFH_fmt(&argp->fh),
@@ -462,7 +464,18 @@ nfsd3_proc_readdir(struct svc_rqst *rqstp)
 	nfserr = nfsd_readdir(rqstp, &resp->fh, (loff_t*) &argp->cookie, 
 					&resp->common, nfs3svc_encode_entry);
 	memcpy(resp->verf, argp->verf, 8);
-	resp->count = resp->buffer - argp->buffer;
+	count = 0;
+	for (p = rqstp->rq_respages + 1; p < rqstp->rq_next_page; p++) {
+		page_addr = page_address(*p);
+
+		if (((caddr_t)resp->buffer >= page_addr) &&
+		    ((caddr_t)resp->buffer < page_addr + PAGE_SIZE)) {
+			count += (caddr_t)resp->buffer - page_addr;
+			break;
+		}
+		count += PAGE_SIZE;
+	}
+	resp->count = count >> 2;
 	if (resp->offset) {
 		loff_t offset = argp->cookie;
 
diff --git a/fs/nfsd/nfs3xdr.c b/fs/nfsd/nfs3xdr.c
index 93fea246f676..8d789124ed3c 100644
--- a/fs/nfsd/nfs3xdr.c
+++ b/fs/nfsd/nfs3xdr.c
@@ -573,6 +573,7 @@ int
 nfs3svc_decode_readdirargs(struct svc_rqst *rqstp, __be32 *p)
 {
 	struct nfsd3_readdirargs *args = rqstp->rq_argp;
+	int len;
 	u32 max_blocksize = svc_max_payload(rqstp);
 
 	p = decode_fh(p, &args->fh);
@@ -582,8 +583,14 @@ nfs3svc_decode_readdirargs(struct svc_rqst *rqstp, __be32 *p)
 	args->verf   = p; p += 2;
 	args->dircount = ~0;
 	args->count  = ntohl(*p++);
-	args->count  = min_t(u32, args->count, max_blocksize);
-	args->buffer = page_address(*(rqstp->rq_next_page++));
+	len = args->count  = min_t(u32, args->count, max_blocksize);
+
+	while (len > 0) {
+		struct page *p = *(rqstp->rq_next_page++);
+		if (!args->buffer)
+			args->buffer = page_address(p);
+		len -= PAGE_SIZE;
+	}
 
 	return xdr_argsize_check(rqstp, p);
 }
diff --git a/fs/nfsd/nfs4callback.c b/fs/nfsd/nfs4callback.c
index d219159b98af..7caa3801ce72 100644
--- a/fs/nfsd/nfs4callback.c
+++ b/fs/nfsd/nfs4callback.c
@@ -1010,8 +1010,9 @@ static void nfsd4_cb_prepare(struct rpc_task *task, void *calldata)
 	cb->cb_seq_status = 1;
 	cb->cb_status = 0;
 	if (minorversion) {
-		if (!nfsd41_cb_get_slot(clp, task))
+		if (!cb->cb_holds_slot && !nfsd41_cb_get_slot(clp, task))
 			return;
+		cb->cb_holds_slot = true;
 	}
 	rpc_call_start(task);
 }
@@ -1038,6 +1039,9 @@ static bool nfsd4_cb_sequence_done(struct rpc_task *task, struct nfsd4_callback
 		return true;
 	}
 
+	if (!cb->cb_holds_slot)
+		goto need_restart;
+
 	switch (cb->cb_seq_status) {
 	case 0:
 		/*
@@ -1076,6 +1080,7 @@ static bool nfsd4_cb_sequence_done(struct rpc_task *task, struct nfsd4_callback
 			cb->cb_seq_status);
 	}
 
+	cb->cb_holds_slot = false;
 	clear_bit(0, &clp->cl_cb_slot_busy);
 	rpc_wake_up_next(&clp->cl_cb_waitq);
 	dprintk("%s: freed slot, new seqid=%d\n", __func__,
@@ -1283,6 +1288,7 @@ void nfsd4_init_cb(struct nfsd4_callback *cb, struct nfs4_client *clp,
 	cb->cb_seq_status = 1;
 	cb->cb_status = 0;
 	cb->cb_need_restart = false;
+	cb->cb_holds_slot = false;
 }
 
 void nfsd4_run_cb(struct nfsd4_callback *cb)
diff --git a/fs/nfsd/nfs4recover.c b/fs/nfsd/nfs4recover.c
index 5188f9f70c78..8c8563441208 100644
--- a/fs/nfsd/nfs4recover.c
+++ b/fs/nfsd/nfs4recover.c
@@ -126,7 +126,6 @@ nfs4_make_rec_clidname(char *dname, const struct xdr_netobj *clname)
 		SHASH_DESC_ON_STACK(desc, tfm);
 
 		desc->tfm = tfm;
-		desc->flags = CRYPTO_TFM_REQ_MAY_SLEEP;
 
 		status = crypto_shash_digest(desc, clname->data, clname->len,
 					     cksum.data);
diff --git a/fs/nfsd/nfs4state.c b/fs/nfsd/nfs4state.c
index 6a45fb00c5fc..f056b1d3fecd 100644
--- a/fs/nfsd/nfs4state.c
+++ b/fs/nfsd/nfs4state.c
@@ -265,6 +265,7 @@ find_or_allocate_block(struct nfs4_lockowner *lo, struct knfsd_fh *fh,
 static void
 free_blocked_lock(struct nfsd4_blocked_lock *nbl)
 {
+	locks_delete_block(&nbl->nbl_lock);
 	locks_release_private(&nbl->nbl_lock);
 	kfree(nbl);
 }
@@ -293,11 +294,18 @@ remove_blocked_locks(struct nfs4_lockowner *lo)
 		nbl = list_first_entry(&reaplist, struct nfsd4_blocked_lock,
 					nbl_lru);
 		list_del_init(&nbl->nbl_lru);
-		locks_delete_block(&nbl->nbl_lock);
 		free_blocked_lock(nbl);
 	}
 }
 
+static void
+nfsd4_cb_notify_lock_prepare(struct nfsd4_callback *cb)
+{
+	struct nfsd4_blocked_lock	*nbl = container_of(cb,
+						struct nfsd4_blocked_lock, nbl_cb);
+	locks_delete_block(&nbl->nbl_lock);
+}
+
 static int
 nfsd4_cb_notify_lock_done(struct nfsd4_callback *cb, struct rpc_task *task)
 {
@@ -325,6 +333,7 @@ nfsd4_cb_notify_lock_release(struct nfsd4_callback *cb)
 }
 
 static const struct nfsd4_callback_ops nfsd4_cb_notify_lock_ops = {
+	.prepare	= nfsd4_cb_notify_lock_prepare,
 	.done		= nfsd4_cb_notify_lock_done,
 	.release	= nfsd4_cb_notify_lock_release,
 };
@@ -4863,7 +4872,6 @@ nfs4_laundromat(struct nfsd_net *nn)
 		nbl = list_first_entry(&reaplist,
 					struct nfsd4_blocked_lock, nbl_lru);
 		list_del_init(&nbl->nbl_lru);
-		locks_delete_block(&nbl->nbl_lock);
 		free_blocked_lock(nbl);
 	}
 out:
diff --git a/fs/nfsd/state.h b/fs/nfsd/state.h
index 396c76755b03..9d6cb246c6c5 100644
--- a/fs/nfsd/state.h
+++ b/fs/nfsd/state.h
@@ -70,6 +70,7 @@ struct nfsd4_callback {
 	int cb_seq_status;
 	int cb_status;
 	bool cb_need_restart;
+	bool cb_holds_slot;
 };
 
 struct nfsd4_callback_ops {
diff --git a/fs/notify/fanotify/fanotify.c b/fs/notify/fanotify/fanotify.c
index 6b9c27548997..63c6bb1f8c4d 100644
--- a/fs/notify/fanotify/fanotify.c
+++ b/fs/notify/fanotify/fanotify.c
@@ -346,10 +346,16 @@ static __kernel_fsid_t fanotify_get_fsid(struct fsnotify_iter_info *iter_info)
 	__kernel_fsid_t fsid = {};
 
 	fsnotify_foreach_obj_type(type) {
+		struct fsnotify_mark_connector *conn;
+
 		if (!fsnotify_iter_should_report_type(iter_info, type))
 			continue;
 
-		fsid = iter_info->marks[type]->connector->fsid;
+		conn = READ_ONCE(iter_info->marks[type]->connector);
+		/* Mark is just getting destroyed or created? */
+		if (!conn)
+			continue;
+		fsid = conn->fsid;
 		if (WARN_ON_ONCE(!fsid.val[0] && !fsid.val[1]))
 			continue;
 		return fsid;
@@ -408,8 +414,12 @@ static int fanotify_handle_event(struct fsnotify_group *group,
 			return 0;
 	}
 
-	if (FAN_GROUP_FLAG(group, FAN_REPORT_FID))
+	if (FAN_GROUP_FLAG(group, FAN_REPORT_FID)) {
 		fsid = fanotify_get_fsid(iter_info);
+		/* Racing with mark destruction or creation? */
+		if (!fsid.val[0] && !fsid.val[1])
+			return 0;
+	}
 
 	event = fanotify_alloc_event(group, inode, mask, data, data_type,
 				     &fsid);
diff --git a/fs/notify/mark.c b/fs/notify/mark.c
index d593d4269561..22acb0a79b53 100644
--- a/fs/notify/mark.c
+++ b/fs/notify/mark.c
@@ -239,13 +239,13 @@ static void fsnotify_drop_object(unsigned int type, void *objp)
 
 void fsnotify_put_mark(struct fsnotify_mark *mark)
 {
-	struct fsnotify_mark_connector *conn;
+	struct fsnotify_mark_connector *conn = READ_ONCE(mark->connector);
 	void *objp = NULL;
 	unsigned int type = FSNOTIFY_OBJ_TYPE_DETACHED;
 	bool free_conn = false;
 
 	/* Catch marks that were actually never attached to object */
-	if (!mark->connector) {
+	if (!conn) {
 		if (refcount_dec_and_test(&mark->refcnt))
 			fsnotify_final_mark_destroy(mark);
 		return;
@@ -255,10 +255,9 @@ void fsnotify_put_mark(struct fsnotify_mark *mark)
 	 * We have to be careful so that traversals of obj_list under lock can
 	 * safely grab mark reference.
 	 */
-	if (!refcount_dec_and_lock(&mark->refcnt, &mark->connector->lock))
+	if (!refcount_dec_and_lock(&mark->refcnt, &conn->lock))
 		return;
 
-	conn = mark->connector;
 	hlist_del_init_rcu(&mark->obj_list);
 	if (hlist_empty(&conn->list)) {
 		objp = fsnotify_detach_connector_from_object(conn, &type);
@@ -266,7 +265,7 @@ void fsnotify_put_mark(struct fsnotify_mark *mark)
 	} else {
 		__fsnotify_recalc_mask(conn);
 	}
-	mark->connector = NULL;
+	WRITE_ONCE(mark->connector, NULL);
 	spin_unlock(&conn->lock);
 
 	fsnotify_drop_object(type, objp);
@@ -620,7 +619,7 @@ restart:
 	/* mark should be the last entry.  last is the current last entry */
 	hlist_add_behind_rcu(&mark->obj_list, &last->obj_list);
 added:
-	mark->connector = conn;
+	WRITE_ONCE(mark->connector, conn);
 out_err:
 	spin_unlock(&conn->lock);
 	spin_unlock(&mark->lock);
@@ -808,6 +807,7 @@ void fsnotify_init_mark(struct fsnotify_mark *mark,
 	refcount_set(&mark->refcnt, 1);
 	fsnotify_get_group(group);
 	mark->group = group;
+	WRITE_ONCE(mark->connector, NULL);
 }
 
 /*
diff --git a/fs/ocfs2/refcounttree.c b/fs/ocfs2/refcounttree.c
index a35259eebc56..1dc9a08e8bdc 100644
--- a/fs/ocfs2/refcounttree.c
+++ b/fs/ocfs2/refcounttree.c
@@ -4719,22 +4719,23 @@ out:
 
 /* Lock an inode and grab a bh pointing to the inode. */
 int ocfs2_reflink_inodes_lock(struct inode *s_inode,
-			      struct buffer_head **bh1,
+			      struct buffer_head **bh_s,
 			      struct inode *t_inode,
-			      struct buffer_head **bh2)
+			      struct buffer_head **bh_t)
 {
-	struct inode *inode1;
-	struct inode *inode2;
+	struct inode *inode1 = s_inode;
+	struct inode *inode2 = t_inode;
 	struct ocfs2_inode_info *oi1;
 	struct ocfs2_inode_info *oi2;
+	struct buffer_head *bh1 = NULL;
+	struct buffer_head *bh2 = NULL;
 	bool same_inode = (s_inode == t_inode);
+	bool need_swap = (inode1->i_ino > inode2->i_ino);
 	int status;
 
 	/* First grab the VFS and rw locks. */
 	lock_two_nondirectories(s_inode, t_inode);
-	inode1 = s_inode;
-	inode2 = t_inode;
-	if (inode1->i_ino > inode2->i_ino)
+	if (need_swap)
 		swap(inode1, inode2);
 
 	status = ocfs2_rw_lock(inode1, 1);
@@ -4757,17 +4758,13 @@ int ocfs2_reflink_inodes_lock(struct inode *s_inode,
 	trace_ocfs2_double_lock((unsigned long long)oi1->ip_blkno,
 				(unsigned long long)oi2->ip_blkno);
 
-	if (*bh1)
-		*bh1 = NULL;
-	if (*bh2)
-		*bh2 = NULL;
-
 	/* We always want to lock the one with the lower lockid first. */
 	if (oi1->ip_blkno > oi2->ip_blkno)
 		mlog_errno(-ENOLCK);
 
 	/* lock id1 */
-	status = ocfs2_inode_lock_nested(inode1, bh1, 1, OI_LS_REFLINK_TARGET);
+	status = ocfs2_inode_lock_nested(inode1, &bh1, 1,
+					 OI_LS_REFLINK_TARGET);
 	if (status < 0) {
 		if (status != -ENOENT)
 			mlog_errno(status);
@@ -4776,15 +4773,25 @@ int ocfs2_reflink_inodes_lock(struct inode *s_inode,
 
 	/* lock id2 */
 	if (!same_inode) {
-		status = ocfs2_inode_lock_nested(inode2, bh2, 1,
+		status = ocfs2_inode_lock_nested(inode2, &bh2, 1,
 						 OI_LS_REFLINK_TARGET);
 		if (status < 0) {
 			if (status != -ENOENT)
 				mlog_errno(status);
 			goto out_cl1;
 		}
-	} else
-		*bh2 = *bh1;
+	} else {
+		bh2 = bh1;
+	}
+
+	/*
+	 * If we swapped inode order above, we have to swap the buffer heads
+	 * before passing them back to the caller.
+	 */
+	if (need_swap)
+		swap(bh1, bh2);
+	*bh_s = bh1;
+	*bh_t = bh2;
 
 	trace_ocfs2_double_lock_end(
 			(unsigned long long)oi1->ip_blkno,
@@ -4794,8 +4801,7 @@ int ocfs2_reflink_inodes_lock(struct inode *s_inode,
 
 out_cl1:
 	ocfs2_inode_unlock(inode1, 1);
-	brelse(*bh1);
-	*bh1 = NULL;
+	brelse(bh1);
 out_rw2:
 	ocfs2_rw_unlock(inode2, 1);
 out_i2:
diff --git a/fs/open.c b/fs/open.c
index 0285ce7dbd51..a00350018a47 100644
--- a/fs/open.c
+++ b/fs/open.c
@@ -733,6 +733,12 @@ static int do_dentry_open(struct file *f,
 		return 0;
 	}
 
+	/* Any file opened for execve()/uselib() has to be a regular file. */
+	if (unlikely(f->f_flags & FMODE_EXEC && !S_ISREG(inode->i_mode))) {
+		error = -EACCES;
+		goto cleanup_file;
+	}
+
 	if (f->f_mode & FMODE_WRITE && !special_file(inode->i_mode)) {
 		error = get_write_access(inode);
 		if (unlikely(error))
@@ -1209,3 +1215,21 @@ int nonseekable_open(struct inode *inode, struct file *filp)
 }
 
 EXPORT_SYMBOL(nonseekable_open);
+
+/*
+ * stream_open is used by subsystems that want stream-like file descriptors.
+ * Such file descriptors are not seekable and don't have notion of position
+ * (file.f_pos is always 0). Contrary to file descriptors of other regular
+ * files, .read() and .write() can run simultaneously.
+ *
+ * stream_open never fails and is marked to return int so that it could be
+ * directly used as file_operations.open .
+ */
+int stream_open(struct inode *inode, struct file *filp)
+{
+	filp->f_mode &= ~(FMODE_LSEEK | FMODE_PREAD | FMODE_PWRITE | FMODE_ATOMIC_POS);
+	filp->f_mode |= FMODE_STREAM;
+	return 0;
+}
+
+EXPORT_SYMBOL(stream_open);
diff --git a/fs/pipe.c b/fs/pipe.c
index 070aad543382..41065901106b 100644
--- a/fs/pipe.c
+++ b/fs/pipe.c
@@ -188,9 +188,9 @@ EXPORT_SYMBOL(generic_pipe_buf_steal);
  *	in the tee() system call, when we duplicate the buffers in one
  *	pipe into another.
  */
-void generic_pipe_buf_get(struct pipe_inode_info *pipe, struct pipe_buffer *buf)
+bool generic_pipe_buf_get(struct pipe_inode_info *pipe, struct pipe_buffer *buf)
 {
-	get_page(buf->page);
+	return try_get_page(buf->page);
 }
 EXPORT_SYMBOL(generic_pipe_buf_get);
 
diff --git a/fs/proc/base.c b/fs/proc/base.c
index ddef482f1334..f179568b4c76 100644
--- a/fs/proc/base.c
+++ b/fs/proc/base.c
@@ -407,7 +407,6 @@ static void unlock_trace(struct task_struct *task)
 static int proc_pid_stack(struct seq_file *m, struct pid_namespace *ns,
 			  struct pid *pid, struct task_struct *task)
 {
-	struct stack_trace trace;
 	unsigned long *entries;
 	int err;
 
@@ -430,20 +429,17 @@ static int proc_pid_stack(struct seq_file *m, struct pid_namespace *ns,
 	if (!entries)
 		return -ENOMEM;
 
-	trace.nr_entries	= 0;
-	trace.max_entries	= MAX_STACK_TRACE_DEPTH;
-	trace.entries		= entries;
-	trace.skip		= 0;
-
 	err = lock_trace(task);
 	if (!err) {
-		unsigned int i;
+		unsigned int i, nr_entries;
 
-		save_stack_trace_tsk(task, &trace);
+		nr_entries = stack_trace_save_tsk(task, entries,
+						  MAX_STACK_TRACE_DEPTH, 0);
 
-		for (i = 0; i < trace.nr_entries; i++) {
+		for (i = 0; i < nr_entries; i++) {
 			seq_printf(m, "[<0>] %pB\n", (void *)entries[i]);
 		}
+
 		unlock_trace(task);
 	}
 	kfree(entries);
@@ -489,10 +485,9 @@ static int lstats_show_proc(struct seq_file *m, void *v)
 				   lr->count, lr->time, lr->max);
 			for (q = 0; q < LT_BACKTRACEDEPTH; q++) {
 				unsigned long bt = lr->backtrace[q];
+
 				if (!bt)
 					break;
-				if (bt == ULONG_MAX)
-					break;
 				seq_printf(m, " %ps", (void *)bt);
 			}
 			seq_putc(m, '\n');
@@ -616,24 +611,25 @@ static int proc_pid_limits(struct seq_file *m, struct pid_namespace *ns,
 static int proc_pid_syscall(struct seq_file *m, struct pid_namespace *ns,
 			    struct pid *pid, struct task_struct *task)
 {
-	long nr;
-	unsigned long args[6], sp, pc;
+	struct syscall_info info;
+	u64 *args = &info.data.args[0];
 	int res;
 
 	res = lock_trace(task);
 	if (res)
 		return res;
 
-	if (task_current_syscall(task, &nr, args, 6, &sp, &pc))
+	if (task_current_syscall(task, &info))
 		seq_puts(m, "running\n");
-	else if (nr < 0)
-		seq_printf(m, "%ld 0x%lx 0x%lx\n", nr, sp, pc);
+	else if (info.data.nr < 0)
+		seq_printf(m, "%d 0x%llx 0x%llx\n",
+			   info.data.nr, info.sp, info.data.instruction_pointer);
 	else
 		seq_printf(m,
-		       "%ld 0x%lx 0x%lx 0x%lx 0x%lx 0x%lx 0x%lx 0x%lx 0x%lx\n",
-		       nr,
+		       "%d 0x%llx 0x%llx 0x%llx 0x%llx 0x%llx 0x%llx 0x%llx 0x%llx\n",
+		       info.data.nr,
 		       args[0], args[1], args[2], args[3], args[4], args[5],
-		       sp, pc);
+		       info.sp, info.data.instruction_pointer);
 	unlock_trace(task);
 
 	return 0;
diff --git a/fs/proc/kcore.c b/fs/proc/kcore.c
index d29d869abec1..f5834488b67d 100644
--- a/fs/proc/kcore.c
+++ b/fs/proc/kcore.c
@@ -615,7 +615,7 @@ static void __init proc_kcore_text_init(void)
 /*
  * MODULES_VADDR has no intersection with VMALLOC_ADDR.
  */
-struct kcore_list kcore_modules;
+static struct kcore_list kcore_modules;
 static void __init add_modules_range(void)
 {
 	if (MODULES_VADDR != VMALLOC_START && MODULES_END != VMALLOC_END) {
diff --git a/fs/proc/proc_sysctl.c b/fs/proc/proc_sysctl.c
index 4d598a399bbf..7325baa8f9d4 100644
--- a/fs/proc/proc_sysctl.c
+++ b/fs/proc/proc_sysctl.c
@@ -1626,8 +1626,11 @@ static void drop_sysctl_table(struct ctl_table_header *header)
 	if (--header->nreg)
 		return;
 
-	put_links(header);
-	start_unregistering(header);
+	if (parent) {
+		put_links(header);
+		start_unregistering(header);
+	}
+
 	if (!--header->count)
 		kfree_rcu(header, rcu);
 
diff --git a/fs/proc/task_mmu.c b/fs/proc/task_mmu.c
index 92a91e7816d8..95ca1fe7283c 100644
--- a/fs/proc/task_mmu.c
+++ b/fs/proc/task_mmu.c
@@ -1143,6 +1143,24 @@ static ssize_t clear_refs_write(struct file *file, const char __user *buf,
 					count = -EINTR;
 					goto out_mm;
 				}
+				/*
+				 * Avoid to modify vma->vm_flags
+				 * without locked ops while the
+				 * coredump reads the vm_flags.
+				 */
+				if (!mmget_still_valid(mm)) {
+					/*
+					 * Silently return "count"
+					 * like if get_task_mm()
+					 * failed. FIXME: should this
+					 * function have returned
+					 * -ESRCH if get_task_mm()
+					 * failed like if
+					 * get_proc_task() fails?
+					 */
+					up_write(&mm->mmap_sem);
+					goto out_mm;
+				}
 				for (vma = mm->mmap; vma; vma = vma->vm_next) {
 					vma->vm_flags &= ~VM_SOFTDIRTY;
 					vma_set_page_prot(vma);
diff --git a/fs/read_write.c b/fs/read_write.c
index 177ccc3d405a..61b43ad7608e 100644
--- a/fs/read_write.c
+++ b/fs/read_write.c
@@ -560,12 +560,13 @@ ssize_t vfs_write(struct file *file, const char __user *buf, size_t count, loff_
 
 static inline loff_t file_pos_read(struct file *file)
 {
-	return file->f_pos;
+	return file->f_mode & FMODE_STREAM ? 0 : file->f_pos;
 }
 
 static inline void file_pos_write(struct file *file, loff_t pos)
 {
-	file->f_pos = pos;
+	if ((file->f_mode & FMODE_STREAM) == 0)
+		file->f_pos = pos;
 }
 
 ssize_t ksys_read(unsigned int fd, char __user *buf, size_t count)
diff --git a/fs/splice.c b/fs/splice.c
index 3ee7e82df48f..25212dcca2df 100644
--- a/fs/splice.c
+++ b/fs/splice.c
@@ -330,8 +330,8 @@ const struct pipe_buf_operations default_pipe_buf_ops = {
 	.get = generic_pipe_buf_get,
 };
 
-static int generic_pipe_buf_nosteal(struct pipe_inode_info *pipe,
-				    struct pipe_buffer *buf)
+int generic_pipe_buf_nosteal(struct pipe_inode_info *pipe,
+			     struct pipe_buffer *buf)
 {
 	return 1;
 }
@@ -1593,7 +1593,11 @@ retry:
 			 * Get a reference to this pipe buffer,
 			 * so we can copy the contents over.
 			 */
-			pipe_buf_get(ipipe, ibuf);
+			if (!pipe_buf_get(ipipe, ibuf)) {
+				if (ret == 0)
+					ret = -EFAULT;
+				break;
+			}
 			*obuf = *ibuf;
 
 			/*
@@ -1667,7 +1671,11 @@ static int link_pipe(struct pipe_inode_info *ipipe,
 		 * Get a reference to this pipe buffer,
 		 * so we can copy the contents over.
 		 */
-		pipe_buf_get(ipipe, ibuf);
+		if (!pipe_buf_get(ipipe, ibuf)) {
+			if (ret == 0)
+				ret = -EFAULT;
+			break;
+		}
 
 		obuf = opipe->bufs + nbuf;
 		*obuf = *ibuf;
diff --git a/fs/super.c b/fs/super.c
index 583a0124bc39..2739f57515f8 100644
--- a/fs/super.c
+++ b/fs/super.c
@@ -1467,11 +1467,6 @@ int vfs_get_tree(struct fs_context *fc)
 	struct super_block *sb;
 	int error;
 
-	if (fc->fs_type->fs_flags & FS_REQUIRES_DEV && !fc->source) {
-		errorf(fc, "Filesystem requires source device");
-		return -ENOENT;
-	}
-
 	if (fc->root)
 		return -EBUSY;
 
diff --git a/fs/ubifs/auth.c b/fs/ubifs/auth.c
index 5bf5fd08879e..b758004085c4 100644
--- a/fs/ubifs/auth.c
+++ b/fs/ubifs/auth.c
@@ -33,7 +33,6 @@ int __ubifs_node_calc_hash(const struct ubifs_info *c, const void *node,
 	int err;
 
 	shash->tfm = c->hash_tfm;
-	shash->flags = CRYPTO_TFM_REQ_MAY_SLEEP;
 
 	err = crypto_shash_digest(shash, node, le32_to_cpu(ch->len), hash);
 	if (err < 0)
@@ -56,7 +55,6 @@ static int ubifs_hash_calc_hmac(const struct ubifs_info *c, const u8 *hash,
 	int err;
 
 	shash->tfm = c->hmac_tfm;
-	shash->flags = CRYPTO_TFM_REQ_MAY_SLEEP;
 
 	err = crypto_shash_digest(shash, hash, c->hash_len, hmac);
 	if (err < 0)
@@ -88,7 +86,6 @@ int ubifs_prepare_auth_node(struct ubifs_info *c, void *node,
 		return -ENOMEM;
 
 	hash_desc->tfm = c->hash_tfm;
-	hash_desc->flags = CRYPTO_TFM_REQ_MAY_SLEEP;
 	ubifs_shash_copy_state(c, inhash, hash_desc);
 
 	err = crypto_shash_final(hash_desc, hash);
@@ -123,7 +120,6 @@ static struct shash_desc *ubifs_get_desc(const struct ubifs_info *c,
 		return ERR_PTR(-ENOMEM);
 
 	desc->tfm = tfm;
-	desc->flags = CRYPTO_TFM_REQ_MAY_SLEEP;
 
 	err = crypto_shash_init(desc);
 	if (err) {
@@ -364,7 +360,6 @@ static int ubifs_node_calc_hmac(const struct ubifs_info *c, const void *node,
 	ubifs_assert(c, ofs_hmac + hmac_len < len);
 
 	shash->tfm = c->hmac_tfm;
-	shash->flags = CRYPTO_TFM_REQ_MAY_SLEEP;
 
 	err = crypto_shash_init(shash);
 	if (err)
@@ -483,7 +478,6 @@ int ubifs_hmac_wkm(struct ubifs_info *c, u8 *hmac)
 		return 0;
 
 	shash->tfm = c->hmac_tfm;
-	shash->flags = CRYPTO_TFM_REQ_MAY_SLEEP;
 
 	err = crypto_shash_init(shash);
 	if (err)
diff --git a/fs/ubifs/replay.c b/fs/ubifs/replay.c
index 0a0e65c07c6d..5c8a81a019a4 100644
--- a/fs/ubifs/replay.c
+++ b/fs/ubifs/replay.c
@@ -576,7 +576,6 @@ static int authenticate_sleb_hash(struct ubifs_info *c, struct shash_desc *log_h
 	SHASH_DESC_ON_STACK(hash_desc, c->hash_tfm);
 
 	hash_desc->tfm = c->hash_tfm;
-	hash_desc->flags = CRYPTO_TFM_REQ_MAY_SLEEP;
 
 	ubifs_shash_copy_state(c, log_hash, hash_desc);
 	return crypto_shash_final(hash_desc, hash);
@@ -587,7 +586,6 @@ static int authenticate_sleb_hmac(struct ubifs_info *c, u8 *hash, u8 *hmac)
 	SHASH_DESC_ON_STACK(hmac_desc, c->hmac_tfm);
 
 	hmac_desc->tfm = c->hmac_tfm;
-	hmac_desc->flags = CRYPTO_TFM_REQ_MAY_SLEEP;
 
 	return crypto_shash_digest(hmac_desc, hash, c->hash_len, hmac);
 }
diff --git a/fs/ubifs/super.c b/fs/ubifs/super.c
index 8dc2818fdd84..12628184772c 100644
--- a/fs/ubifs/super.c
+++ b/fs/ubifs/super.c
@@ -276,14 +276,12 @@ static void ubifs_i_callback(struct rcu_head *head)
 {
 	struct inode *inode = container_of(head, struct inode, i_rcu);
 	struct ubifs_inode *ui = ubifs_inode(inode);
+	kfree(ui->data);
 	kmem_cache_free(ubifs_inode_slab, ui);
 }
 
 static void ubifs_destroy_inode(struct inode *inode)
 {
-	struct ubifs_inode *ui = ubifs_inode(inode);
-
-	kfree(ui->data);
 	call_rcu(&inode->i_rcu, ubifs_i_callback);
 }
 
diff --git a/fs/ufs/util.h b/fs/ufs/util.h
index 1fd3011ea623..7fd4802222b8 100644
--- a/fs/ufs/util.h
+++ b/fs/ufs/util.h
@@ -229,7 +229,7 @@ ufs_get_inode_gid(struct super_block *sb, struct ufs_inode *inode)
 	case UFS_UID_44BSD:
 		return fs32_to_cpu(sb, inode->ui_u3.ui_44.ui_gid);
 	case UFS_UID_EFT:
-		if (inode->ui_u1.oldids.ui_suid == 0xFFFF)
+		if (inode->ui_u1.oldids.ui_sgid == 0xFFFF)
 			return fs32_to_cpu(sb, inode->ui_u3.ui_sun.ui_gid);
 		/* Fall through */
 	default:
diff --git a/fs/userfaultfd.c b/fs/userfaultfd.c
index 89800fc7dc9d..f5de1e726356 100644
--- a/fs/userfaultfd.c
+++ b/fs/userfaultfd.c
@@ -629,6 +629,8 @@ static void userfaultfd_event_wait_completion(struct userfaultfd_ctx *ctx,
 
 		/* the various vma->vm_userfaultfd_ctx still points to it */
 		down_write(&mm->mmap_sem);
+		/* no task can run (and in turn coredump) yet */
+		VM_WARN_ON(!mmget_still_valid(mm));
 		for (vma = mm->mmap; vma; vma = vma->vm_next)
 			if (vma->vm_userfaultfd_ctx.ctx == release_new_ctx) {
 				vma->vm_userfaultfd_ctx = NULL_VM_UFFD_CTX;
@@ -883,6 +885,8 @@ static int userfaultfd_release(struct inode *inode, struct file *file)
 	 * taking the mmap_sem for writing.
 	 */
 	down_write(&mm->mmap_sem);
+	if (!mmget_still_valid(mm))
+		goto skip_mm;
 	prev = NULL;
 	for (vma = mm->mmap; vma; vma = vma->vm_next) {
 		cond_resched();
@@ -905,6 +909,7 @@ static int userfaultfd_release(struct inode *inode, struct file *file)
 		vma->vm_flags = new_flags;
 		vma->vm_userfaultfd_ctx = NULL_VM_UFFD_CTX;
 	}
+skip_mm:
 	up_write(&mm->mmap_sem);
 	mmput(mm);
 wakeup:
@@ -1333,6 +1338,8 @@ static int userfaultfd_register(struct userfaultfd_ctx *ctx,
 		goto out;
 
 	down_write(&mm->mmap_sem);
+	if (!mmget_still_valid(mm))
+		goto out_unlock;
 	vma = find_vma_prev(mm, start, &prev);
 	if (!vma)
 		goto out_unlock;
@@ -1520,6 +1527,8 @@ static int userfaultfd_unregister(struct userfaultfd_ctx *ctx,
 		goto out;
 
 	down_write(&mm->mmap_sem);
+	if (!mmget_still_valid(mm))
+		goto out_unlock;
 	vma = find_vma_prev(mm, start, &prev);
 	if (!vma)
 		goto out_unlock;
diff --git a/fs/xfs/libxfs/xfs_bmap.c b/fs/xfs/libxfs/xfs_bmap.c
index 48502cb9990f..4637ae1ae91c 100644
--- a/fs/xfs/libxfs/xfs_bmap.c
+++ b/fs/xfs/libxfs/xfs_bmap.c
@@ -1191,7 +1191,10 @@ xfs_iread_extents(
 	 * Root level must use BMAP_BROOT_PTR_ADDR macro to get ptr out.
 	 */
 	level = be16_to_cpu(block->bb_level);
-	ASSERT(level > 0);
+	if (unlikely(level == 0)) {
+		XFS_ERROR_REPORT(__func__, XFS_ERRLEVEL_LOW, mp);
+		return -EFSCORRUPTED;
+	}
 	pp = XFS_BMAP_BROOT_PTR_ADDR(mp, block, 1, ifp->if_broot_bytes);
 	bno = be64_to_cpu(*pp);
 
@@ -4249,9 +4252,13 @@ xfs_bmapi_write(
 	struct xfs_bmbt_irec	*mval,		/* output: map values */
 	int			*nmap)		/* i/o: mval size/count */
 {
+	struct xfs_bmalloca	bma = {
+		.tp		= tp,
+		.ip		= ip,
+		.total		= total,
+	};
 	struct xfs_mount	*mp = ip->i_mount;
 	struct xfs_ifork	*ifp;
-	struct xfs_bmalloca	bma = { NULL };	/* args for xfs_bmap_alloc */
 	xfs_fileoff_t		end;		/* end of mapped file region */
 	bool			eof = false;	/* after the end of extents */
 	int			error;		/* error return */
@@ -4319,10 +4326,6 @@ xfs_bmapi_write(
 		eof = true;
 	if (!xfs_iext_peek_prev_extent(ifp, &bma.icur, &bma.prev))
 		bma.prev.br_startoff = NULLFILEOFF;
-	bma.tp = tp;
-	bma.ip = ip;
-	bma.total = total;
-	bma.datatype = 0;
 	bma.minleft = xfs_bmapi_minleft(tp, ip, whichfork);
 
 	n = 0;
diff --git a/fs/xfs/scrub/btree.c b/fs/xfs/scrub/btree.c
index 6f94d1f7322d..117910db51b8 100644
--- a/fs/xfs/scrub/btree.c
+++ b/fs/xfs/scrub/btree.c
@@ -415,8 +415,17 @@ xchk_btree_check_owner(
 	struct xfs_btree_cur	*cur = bs->cur;
 	struct check_owner	*co;
 
-	if ((cur->bc_flags & XFS_BTREE_ROOT_IN_INODE) && bp == NULL)
+	/*
+	 * In theory, xfs_btree_get_block should only give us a null buffer
+	 * pointer for the root of a root-in-inode btree type, but we need
+	 * to check defensively here in case the cursor state is also screwed
+	 * up.
+	 */
+	if (bp == NULL) {
+		if (!(cur->bc_flags & XFS_BTREE_ROOT_IN_INODE))
+			xchk_btree_set_corrupt(bs->sc, bs->cur, level);
 		return 0;
+	}
 
 	/*
 	 * We want to cross-reference each btree block with the bnobt
diff --git a/fs/xfs/scrub/dabtree.c b/fs/xfs/scrub/dabtree.c
index f1260b4bfdee..90527b094878 100644
--- a/fs/xfs/scrub/dabtree.c
+++ b/fs/xfs/scrub/dabtree.c
@@ -574,6 +574,11 @@ xchk_da_btree(
 		/* Drill another level deeper. */
 		blkno = be32_to_cpu(key->before);
 		level++;
+		if (level >= XFS_DA_NODE_MAXDEPTH) {
+			/* Too deep! */
+			xchk_da_set_corrupt(&ds, level - 1);
+			break;
+		}
 		ds.tree_level--;
 		error = xchk_da_btree_block(&ds, level, blkno);
 		if (error)
diff --git a/fs/xfs/xfs_discard.c b/fs/xfs/xfs_discard.c
index 93f07edafd81..9ee2a7d02e70 100644
--- a/fs/xfs/xfs_discard.c
+++ b/fs/xfs/xfs_discard.c
@@ -161,6 +161,14 @@ xfs_ioc_trim(
 		return -EPERM;
 	if (!blk_queue_discard(q))
 		return -EOPNOTSUPP;
+
+	/*
+	 * We haven't recovered the log, so we cannot use our bnobt-guided
+	 * storage zapping commands.
+	 */
+	if (mp->m_flags & XFS_MOUNT_NORECOVERY)
+		return -EROFS;
+
 	if (copy_from_user(&range, urange, sizeof(range)))
 		return -EFAULT;
 
diff --git a/fs/xfs/xfs_file.c b/fs/xfs/xfs_file.c
index 1f2e2845eb76..a7ceae90110e 100644
--- a/fs/xfs/xfs_file.c
+++ b/fs/xfs/xfs_file.c
@@ -529,18 +529,17 @@ xfs_file_dio_aio_write(
 	count = iov_iter_count(from);
 
 	/*
-	 * If we are doing unaligned IO, wait for all other IO to drain,
-	 * otherwise demote the lock if we had to take the exclusive lock
-	 * for other reasons in xfs_file_aio_write_checks.
+	 * If we are doing unaligned IO, we can't allow any other overlapping IO
+	 * in-flight at the same time or we risk data corruption. Wait for all
+	 * other IO to drain before we submit. If the IO is aligned, demote the
+	 * iolock if we had to take the exclusive lock in
+	 * xfs_file_aio_write_checks() for other reasons.
 	 */
 	if (unaligned_io) {
-		/* If we are going to wait for other DIO to finish, bail */
-		if (iocb->ki_flags & IOCB_NOWAIT) {
-			if (atomic_read(&inode->i_dio_count))
-				return -EAGAIN;
-		} else {
-			inode_dio_wait(inode);
-		}
+		/* unaligned dio always waits, bail */
+		if (iocb->ki_flags & IOCB_NOWAIT)
+			return -EAGAIN;
+		inode_dio_wait(inode);
 	} else if (iolock == XFS_IOLOCK_EXCL) {
 		xfs_ilock_demote(ip, XFS_IOLOCK_EXCL);
 		iolock = XFS_IOLOCK_SHARED;
@@ -548,6 +547,14 @@ xfs_file_dio_aio_write(
 
 	trace_xfs_file_direct_write(ip, count, iocb->ki_pos);
 	ret = iomap_dio_rw(iocb, from, &xfs_iomap_ops, xfs_dio_write_end_io);
+
+	/*
+	 * If unaligned, this is the only IO in-flight. If it has not yet
+	 * completed, wait on it before we release the iolock to prevent
+	 * subsequent overlapping IO.
+	 */
+	if (ret == -EIOCBQUEUED && unaligned_io)
+		inode_dio_wait(inode);
 out:
 	xfs_iunlock(ip, iolock);
 
diff --git a/include/acpi/acoutput.h b/include/acpi/acoutput.h
index 30b1ae53689f..c50542dc71e0 100644
--- a/include/acpi/acoutput.h
+++ b/include/acpi/acoutput.h
@@ -150,7 +150,10 @@
 
 /* Defaults for debug_level, debug and normal */
 
+#ifndef ACPI_DEBUG_DEFAULT
 #define ACPI_DEBUG_DEFAULT          (ACPI_LV_INIT | ACPI_LV_DEBUG_OBJECT | ACPI_LV_EVALUATION | ACPI_LV_REPAIR)
+#endif
+
 #define ACPI_NORMAL_DEFAULT         (ACPI_LV_INIT | ACPI_LV_DEBUG_OBJECT | ACPI_LV_REPAIR)
 #define ACPI_DEBUG_ALL              (ACPI_LV_AML_DISASSEMBLE | ACPI_LV_ALL_EXCEPTIONS | ACPI_LV_ALL)
 
diff --git a/include/acpi/acpi_bus.h b/include/acpi/acpi_bus.h
index 0300374101cd..2a462cf4eaa9 100644
--- a/include/acpi/acpi_bus.h
+++ b/include/acpi/acpi_bus.h
@@ -91,8 +91,8 @@ acpi_evaluate_dsm_typed(acpi_handle handle, const guid_t *guid, u64 rev,
 bool acpi_dev_found(const char *hid);
 bool acpi_dev_present(const char *hid, const char *uid, s64 hrv);
 
-const char *
-acpi_dev_get_first_match_name(const char *hid, const char *uid, s64 hrv);
+struct acpi_device *
+acpi_dev_get_first_match_dev(const char *hid, const char *uid, s64 hrv);
 
 #ifdef CONFIG_ACPI
 
@@ -687,6 +687,10 @@ static inline bool acpi_device_can_poweroff(struct acpi_device *adev)
 		adev->power.states[ACPI_STATE_D3_HOT].flags.explicit_set);
 }
 
+static inline void acpi_dev_put(struct acpi_device *adev)
+{
+	put_device(&adev->dev);
+}
 #else	/* CONFIG_ACPI */
 
 static inline int register_acpi_bus_type(void *bus) { return 0; }
diff --git a/include/acpi/acpixf.h b/include/acpi/acpixf.h
index 24dbb4e742a6..3b1b1d0e4c33 100644
--- a/include/acpi/acpixf.h
+++ b/include/acpi/acpixf.h
@@ -12,7 +12,7 @@
 
 /* Current ACPICA subsystem version in YYYYMMDD format */
 
-#define ACPI_CA_VERSION                 0x20190215
+#define ACPI_CA_VERSION                 0x20190405
 
 #include <acpi/acconfig.h>
 #include <acpi/actypes.h>
diff --git a/include/acpi/actbl.h b/include/acpi/actbl.h
index 65cc9cbf1141..d568128025df 100644
--- a/include/acpi/actbl.h
+++ b/include/acpi/actbl.h
@@ -66,14 +66,14 @@
  ******************************************************************************/
 
 struct acpi_table_header {
-	char signature[ACPI_NAME_SIZE];	/* ASCII table signature */
+	char signature[ACPI_NAMESEG_SIZE];	/* ASCII table signature */
 	u32 length;		/* Length of table in bytes, including this header */
 	u8 revision;		/* ACPI Specification minor version number */
 	u8 checksum;		/* To make sum of entire table == 0 */
 	char oem_id[ACPI_OEM_ID_SIZE];	/* ASCII OEM identification */
 	char oem_table_id[ACPI_OEM_TABLE_ID_SIZE];	/* ASCII OEM table identification */
 	u32 oem_revision;	/* OEM revision number */
-	char asl_compiler_id[ACPI_NAME_SIZE];	/* ASCII ASL compiler vendor ID */
+	char asl_compiler_id[ACPI_NAMESEG_SIZE];	/* ASCII ASL compiler vendor ID */
 	u32 asl_compiler_revision;	/* ASL compiler version */
 };
 
diff --git a/include/acpi/actypes.h b/include/acpi/actypes.h
index f73382e82c26..ad6892a24015 100644
--- a/include/acpi/actypes.h
+++ b/include/acpi/actypes.h
@@ -375,7 +375,7 @@ typedef u64 acpi_physical_address;
 
 /* Names within the namespace are 4 bytes long */
 
-#define ACPI_NAME_SIZE                  4
+#define ACPI_NAMESEG_SIZE               4	/* Fixed by ACPI spec */
 #define ACPI_PATH_SEGMENT_LENGTH        5	/* 4 chars for name + 1 char for separator */
 #define ACPI_PATH_SEPARATOR             '.'
 
@@ -515,11 +515,11 @@ typedef u64 acpi_integer;
 /* Optimizations for 4-character (32-bit) acpi_name manipulation */
 
 #ifndef ACPI_MISALIGNMENT_NOT_SUPPORTED
-#define ACPI_COMPARE_NAME(a,b)          (*ACPI_CAST_PTR (u32, (a)) == *ACPI_CAST_PTR (u32, (b)))
-#define ACPI_MOVE_NAME(dest,src)        (*ACPI_CAST_PTR (u32, (dest)) = *ACPI_CAST_PTR (u32, (src)))
+#define ACPI_COMPARE_NAMESEG(a,b)       (*ACPI_CAST_PTR (u32, (a)) == *ACPI_CAST_PTR (u32, (b)))
+#define ACPI_COPY_NAMESEG(dest,src)     (*ACPI_CAST_PTR (u32, (dest)) = *ACPI_CAST_PTR (u32, (src)))
 #else
-#define ACPI_COMPARE_NAME(a,b)          (!strncmp (ACPI_CAST_PTR (char, (a)), ACPI_CAST_PTR (char, (b)), ACPI_NAME_SIZE))
-#define ACPI_MOVE_NAME(dest,src)        (strncpy (ACPI_CAST_PTR (char, (dest)), ACPI_CAST_PTR (char, (src)), ACPI_NAME_SIZE))
+#define ACPI_COMPARE_NAMESEG(a,b)       (!strncmp (ACPI_CAST_PTR (char, (a)), ACPI_CAST_PTR (char, (b)), ACPI_NAMESEG_SIZE))
+#define ACPI_COPY_NAMESEG(dest,src)     (strncpy (ACPI_CAST_PTR (char, (dest)), ACPI_CAST_PTR (char, (src)), ACPI_NAMESEG_SIZE))
 #endif
 
 /* Support for the special RSDP signature (8 characters) */
@@ -529,7 +529,7 @@ typedef u64 acpi_integer;
 
 /* Support for OEMx signature (x can be any character) */
 #define ACPI_IS_OEM_SIG(a)        (!strncmp (ACPI_CAST_PTR (char, (a)), ACPI_OEM_NAME, 3) &&\
-	 strnlen (a, ACPI_NAME_SIZE) == ACPI_NAME_SIZE)
+	 strnlen (a, ACPI_NAMESEG_SIZE) == ACPI_NAMESEG_SIZE)
 
 /*
  * Algorithm to obtain access bit width.
diff --git a/include/acpi/platform/aclinux.h b/include/acpi/platform/aclinux.h
index 9ff328fd946a..624b90b34085 100644
--- a/include/acpi/platform/aclinux.h
+++ b/include/acpi/platform/aclinux.h
@@ -82,6 +82,11 @@
 #define ACPI_NO_ERROR_MESSAGES
 #undef ACPI_DEBUG_OUTPUT
 
+/* Use a specific bugging default separate from ACPICA */
+
+#undef ACPI_DEBUG_DEFAULT
+#define ACPI_DEBUG_DEFAULT          (ACPI_LV_INFO | ACPI_LV_REPAIR)
+
 /* External interface for __KERNEL__, stub is needed */
 
 #define ACPI_EXTERNAL_RETURN_STATUS(prototype) \
diff --git a/include/asm-generic/futex.h b/include/asm-generic/futex.h
index fcb61b4659b3..8666fe7f35d7 100644
--- a/include/asm-generic/futex.h
+++ b/include/asm-generic/futex.h
@@ -23,7 +23,9 @@
  *
  * Return:
  * 0 - On success
- * <0 - On error
+ * -EFAULT - User access resulted in a page fault
+ * -EAGAIN - Atomic operation was unable to complete due to contention
+ * -ENOSYS - Operation not supported
  */
 static inline int
 arch_futex_atomic_op_inuser(int op, u32 oparg, int *oval, u32 __user *uaddr)
@@ -85,7 +87,9 @@ out_pagefault_enable:
  *
  * Return:
  * 0 - On success
- * <0 - On error
+ * -EFAULT - User access resulted in a page fault
+ * -EAGAIN - Atomic operation was unable to complete due to contention
+ * -ENOSYS - Function not implemented (only if !HAVE_FUTEX_CMPXCHG)
  */
 static inline int
 futex_atomic_cmpxchg_inatomic(u32 *uval, u32 __user *uaddr,
diff --git a/include/asm-generic/io.h b/include/asm-generic/io.h
index 303871651f8a..8f3bf95a36d1 100644
--- a/include/asm-generic/io.h
+++ b/include/asm-generic/io.h
@@ -19,12 +19,9 @@
 #include <asm-generic/iomap.h>
 #endif
 
+#include <asm/mmiowb.h>
 #include <asm-generic/pci_iomap.h>
 
-#ifndef mmiowb
-#define mmiowb() do {} while (0)
-#endif
-
 #ifndef __io_br
 #define __io_br()      barrier()
 #endif
@@ -49,7 +46,7 @@
 
 /* serialize device access against a spin_unlock, usually handled there. */
 #ifndef __io_aw
-#define __io_aw()      barrier()
+#define __io_aw()      mmiowb_set_pending()
 #endif
 
 #ifndef __io_pbw
diff --git a/include/asm-generic/mmiowb.h b/include/asm-generic/mmiowb.h
new file mode 100644
index 000000000000..9439ff037b2d
--- /dev/null
+++ b/include/asm-generic/mmiowb.h
@@ -0,0 +1,63 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef __ASM_GENERIC_MMIOWB_H
+#define __ASM_GENERIC_MMIOWB_H
+
+/*
+ * Generic implementation of mmiowb() tracking for spinlocks.
+ *
+ * If your architecture doesn't ensure that writes to an I/O peripheral
+ * within two spinlocked sections on two different CPUs are seen by the
+ * peripheral in the order corresponding to the lock handover, then you
+ * need to follow these FIVE easy steps:
+ *
+ * 	1. Implement mmiowb() (and arch_mmiowb_state() if you're fancy)
+ *	   in asm/mmiowb.h, then #include this file
+ *	2. Ensure your I/O write accessors call mmiowb_set_pending()
+ *	3. Select ARCH_HAS_MMIOWB
+ *	4. Untangle the resulting mess of header files
+ *	5. Complain to your architects
+ */
+#ifdef CONFIG_MMIOWB
+
+#include <linux/compiler.h>
+#include <asm-generic/mmiowb_types.h>
+
+#ifndef arch_mmiowb_state
+#include <asm/percpu.h>
+#include <asm/smp.h>
+
+DECLARE_PER_CPU(struct mmiowb_state, __mmiowb_state);
+#define __mmiowb_state()	this_cpu_ptr(&__mmiowb_state)
+#else
+#define __mmiowb_state()	arch_mmiowb_state()
+#endif	/* arch_mmiowb_state */
+
+static inline void mmiowb_set_pending(void)
+{
+	struct mmiowb_state *ms = __mmiowb_state();
+	ms->mmiowb_pending = ms->nesting_count;
+}
+
+static inline void mmiowb_spin_lock(void)
+{
+	struct mmiowb_state *ms = __mmiowb_state();
+	ms->nesting_count++;
+}
+
+static inline void mmiowb_spin_unlock(void)
+{
+	struct mmiowb_state *ms = __mmiowb_state();
+
+	if (unlikely(ms->mmiowb_pending)) {
+		ms->mmiowb_pending = 0;
+		mmiowb();
+	}
+
+	ms->nesting_count--;
+}
+#else
+#define mmiowb_set_pending()		do { } while (0)
+#define mmiowb_spin_lock()		do { } while (0)
+#define mmiowb_spin_unlock()		do { } while (0)
+#endif	/* CONFIG_MMIOWB */
+#endif	/* __ASM_GENERIC_MMIOWB_H */
diff --git a/include/asm-generic/mmiowb_types.h b/include/asm-generic/mmiowb_types.h
new file mode 100644
index 000000000000..8eb0095655e7
--- /dev/null
+++ b/include/asm-generic/mmiowb_types.h
@@ -0,0 +1,12 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef __ASM_GENERIC_MMIOWB_TYPES_H
+#define __ASM_GENERIC_MMIOWB_TYPES_H
+
+#include <linux/types.h>
+
+struct mmiowb_state {
+	u16	nesting_count;
+	u16	mmiowb_pending;
+};
+
+#endif	/* __ASM_GENERIC_MMIOWB_TYPES_H */
diff --git a/include/asm-generic/pgtable.h b/include/asm-generic/pgtable.h
index fa782fba51ee..75d9d68a6de7 100644
--- a/include/asm-generic/pgtable.h
+++ b/include/asm-generic/pgtable.h
@@ -1126,6 +1126,8 @@ int phys_mem_access_prot_allowed(struct file *file, unsigned long pfn,
 static inline void init_espfix_bsp(void) { }
 #endif
 
+extern void __init pgd_cache_init(void);
+
 #ifndef __HAVE_ARCH_PFN_MODIFY_ALLOWED
 static inline bool pfn_modify_allowed(unsigned long pfn, pgprot_t prot)
 {
diff --git a/include/asm-generic/rwsem.h b/include/asm-generic/rwsem.h
deleted file mode 100644
index 93e67a055a4d..000000000000
--- a/include/asm-generic/rwsem.h
+++ /dev/null
@@ -1,140 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 */
-#ifndef _ASM_GENERIC_RWSEM_H
-#define _ASM_GENERIC_RWSEM_H
-
-#ifndef _LINUX_RWSEM_H
-#error "Please don't include <asm/rwsem.h> directly, use <linux/rwsem.h> instead."
-#endif
-
-#ifdef __KERNEL__
-
-/*
- * R/W semaphores originally for PPC using the stuff in lib/rwsem.c.
- * Adapted largely from include/asm-i386/rwsem.h
- * by Paul Mackerras <paulus@samba.org>.
- */
-
-/*
- * the semaphore definition
- */
-#ifdef CONFIG_64BIT
-# define RWSEM_ACTIVE_MASK		0xffffffffL
-#else
-# define RWSEM_ACTIVE_MASK		0x0000ffffL
-#endif
-
-#define RWSEM_UNLOCKED_VALUE		0x00000000L
-#define RWSEM_ACTIVE_BIAS		0x00000001L
-#define RWSEM_WAITING_BIAS		(-RWSEM_ACTIVE_MASK-1)
-#define RWSEM_ACTIVE_READ_BIAS		RWSEM_ACTIVE_BIAS
-#define RWSEM_ACTIVE_WRITE_BIAS		(RWSEM_WAITING_BIAS + RWSEM_ACTIVE_BIAS)
-
-/*
- * lock for reading
- */
-static inline void __down_read(struct rw_semaphore *sem)
-{
-	if (unlikely(atomic_long_inc_return_acquire(&sem->count) <= 0))
-		rwsem_down_read_failed(sem);
-}
-
-static inline int __down_read_killable(struct rw_semaphore *sem)
-{
-	if (unlikely(atomic_long_inc_return_acquire(&sem->count) <= 0)) {
-		if (IS_ERR(rwsem_down_read_failed_killable(sem)))
-			return -EINTR;
-	}
-
-	return 0;
-}
-
-static inline int __down_read_trylock(struct rw_semaphore *sem)
-{
-	long tmp;
-
-	while ((tmp = atomic_long_read(&sem->count)) >= 0) {
-		if (tmp == atomic_long_cmpxchg_acquire(&sem->count, tmp,
-				   tmp + RWSEM_ACTIVE_READ_BIAS)) {
-			return 1;
-		}
-	}
-	return 0;
-}
-
-/*
- * lock for writing
- */
-static inline void __down_write(struct rw_semaphore *sem)
-{
-	long tmp;
-
-	tmp = atomic_long_add_return_acquire(RWSEM_ACTIVE_WRITE_BIAS,
-					     &sem->count);
-	if (unlikely(tmp != RWSEM_ACTIVE_WRITE_BIAS))
-		rwsem_down_write_failed(sem);
-}
-
-static inline int __down_write_killable(struct rw_semaphore *sem)
-{
-	long tmp;
-
-	tmp = atomic_long_add_return_acquire(RWSEM_ACTIVE_WRITE_BIAS,
-					     &sem->count);
-	if (unlikely(tmp != RWSEM_ACTIVE_WRITE_BIAS))
-		if (IS_ERR(rwsem_down_write_failed_killable(sem)))
-			return -EINTR;
-	return 0;
-}
-
-static inline int __down_write_trylock(struct rw_semaphore *sem)
-{
-	long tmp;
-
-	tmp = atomic_long_cmpxchg_acquire(&sem->count, RWSEM_UNLOCKED_VALUE,
-		      RWSEM_ACTIVE_WRITE_BIAS);
-	return tmp == RWSEM_UNLOCKED_VALUE;
-}
-
-/*
- * unlock after reading
- */
-static inline void __up_read(struct rw_semaphore *sem)
-{
-	long tmp;
-
-	tmp = atomic_long_dec_return_release(&sem->count);
-	if (unlikely(tmp < -1 && (tmp & RWSEM_ACTIVE_MASK) == 0))
-		rwsem_wake(sem);
-}
-
-/*
- * unlock after writing
- */
-static inline void __up_write(struct rw_semaphore *sem)
-{
-	if (unlikely(atomic_long_sub_return_release(RWSEM_ACTIVE_WRITE_BIAS,
-						    &sem->count) < 0))
-		rwsem_wake(sem);
-}
-
-/*
- * downgrade write lock to read lock
- */
-static inline void __downgrade_write(struct rw_semaphore *sem)
-{
-	long tmp;
-
-	/*
-	 * When downgrading from exclusive to shared ownership,
-	 * anything inside the write-locked region cannot leak
-	 * into the read side. In contrast, anything in the
-	 * read-locked region is ok to be re-ordered into the
-	 * write side. As such, rely on RELEASE semantics.
-	 */
-	tmp = atomic_long_add_return_release(-RWSEM_WAITING_BIAS, &sem->count);
-	if (tmp < 0)
-		rwsem_downgrade_wake(sem);
-}
-
-#endif	/* __KERNEL__ */
-#endif	/* _ASM_GENERIC_RWSEM_H */
diff --git a/include/asm-generic/sections.h b/include/asm-generic/sections.h
index d79abca81a52..d1779d442aa5 100644
--- a/include/asm-generic/sections.h
+++ b/include/asm-generic/sections.h
@@ -77,6 +77,20 @@ static inline int arch_is_kernel_data(unsigned long addr)
 }
 #endif
 
+/*
+ * Check if an address is part of freed initmem. This is needed on architectures
+ * with virt == phys kernel mapping, for code that wants to check if an address
+ * is part of a static object within [_stext, _end]. After initmem is freed,
+ * memory can be allocated from it, and such allocations would then have
+ * addresses within the range [_stext, _end].
+ */
+#ifndef arch_is_kernel_initmem_freed
+static inline int arch_is_kernel_initmem_freed(unsigned long addr)
+{
+	return 0;
+}
+#endif
+
 /**
  * memory_contains - checks if an object is contained within a memory region
  * @begin: virtual address of the beginning of the memory region
diff --git a/include/asm-generic/syscall.h b/include/asm-generic/syscall.h
index 0c938a4354f6..b88239e9efe4 100644
--- a/include/asm-generic/syscall.h
+++ b/include/asm-generic/syscall.h
@@ -105,41 +105,30 @@ void syscall_set_return_value(struct task_struct *task, struct pt_regs *regs,
  * syscall_get_arguments - extract system call parameter values
  * @task:	task of interest, must be blocked
  * @regs:	task_pt_regs() of @task
- * @i:		argument index [0,5]
- * @n:		number of arguments; n+i must be [1,6].
  * @args:	array filled with argument values
  *
- * Fetches @n arguments to the system call starting with the @i'th argument
- * (from 0 through 5).  Argument @i is stored in @args[0], and so on.
- * An arch inline version is probably optimal when @i and @n are constants.
+ * Fetches 6 arguments to the system call.  First argument is stored in
+*  @args[0], and so on.
  *
  * It's only valid to call this when @task is stopped for tracing on
  * entry to a system call, due to %TIF_SYSCALL_TRACE or %TIF_SYSCALL_AUDIT.
- * It's invalid to call this with @i + @n > 6; we only support system calls
- * taking up to 6 arguments.
  */
 void syscall_get_arguments(struct task_struct *task, struct pt_regs *regs,
-			   unsigned int i, unsigned int n, unsigned long *args);
+			   unsigned long *args);
 
 /**
  * syscall_set_arguments - change system call parameter value
  * @task:	task of interest, must be in system call entry tracing
  * @regs:	task_pt_regs() of @task
- * @i:		argument index [0,5]
- * @n:		number of arguments; n+i must be [1,6].
  * @args:	array of argument values to store
  *
- * Changes @n arguments to the system call starting with the @i'th argument.
- * Argument @i gets value @args[0], and so on.
- * An arch inline version is probably optimal when @i and @n are constants.
+ * Changes 6 arguments to the system call.
+ * The first argument gets value @args[0], and so on.
  *
  * It's only valid to call this when @task is stopped for tracing on
  * entry to a system call, due to %TIF_SYSCALL_TRACE or %TIF_SYSCALL_AUDIT.
- * It's invalid to call this with @i + @n > 6; we only support system calls
- * taking up to 6 arguments.
  */
 void syscall_set_arguments(struct task_struct *task, struct pt_regs *regs,
-			   unsigned int i, unsigned int n,
 			   const unsigned long *args);
 
 /**
diff --git a/include/asm-generic/tlb.h b/include/asm-generic/tlb.h
index 6be86c1c5c58..480e5b2a5748 100644
--- a/include/asm-generic/tlb.h
+++ b/include/asm-generic/tlb.h
@@ -19,9 +19,140 @@
 #include <linux/swap.h>
 #include <asm/pgalloc.h>
 #include <asm/tlbflush.h>
+#include <asm/cacheflush.h>
+
+/*
+ * Blindly accessing user memory from NMI context can be dangerous
+ * if we're in the middle of switching the current user task or switching
+ * the loaded mm.
+ */
+#ifndef nmi_uaccess_okay
+# define nmi_uaccess_okay() true
+#endif
 
 #ifdef CONFIG_MMU
 
+/*
+ * Generic MMU-gather implementation.
+ *
+ * The mmu_gather data structure is used by the mm code to implement the
+ * correct and efficient ordering of freeing pages and TLB invalidations.
+ *
+ * This correct ordering is:
+ *
+ *  1) unhook page
+ *  2) TLB invalidate page
+ *  3) free page
+ *
+ * That is, we must never free a page before we have ensured there are no live
+ * translations left to it. Otherwise it might be possible to observe (or
+ * worse, change) the page content after it has been reused.
+ *
+ * The mmu_gather API consists of:
+ *
+ *  - tlb_gather_mmu() / tlb_finish_mmu(); start and finish a mmu_gather
+ *
+ *    Finish in particular will issue a (final) TLB invalidate and free
+ *    all (remaining) queued pages.
+ *
+ *  - tlb_start_vma() / tlb_end_vma(); marks the start / end of a VMA
+ *
+ *    Defaults to flushing at tlb_end_vma() to reset the range; helps when
+ *    there's large holes between the VMAs.
+ *
+ *  - tlb_remove_page() / __tlb_remove_page()
+ *  - tlb_remove_page_size() / __tlb_remove_page_size()
+ *
+ *    __tlb_remove_page_size() is the basic primitive that queues a page for
+ *    freeing. __tlb_remove_page() assumes PAGE_SIZE. Both will return a
+ *    boolean indicating if the queue is (now) full and a call to
+ *    tlb_flush_mmu() is required.
+ *
+ *    tlb_remove_page() and tlb_remove_page_size() imply the call to
+ *    tlb_flush_mmu() when required and has no return value.
+ *
+ *  - tlb_change_page_size()
+ *
+ *    call before __tlb_remove_page*() to set the current page-size; implies a
+ *    possible tlb_flush_mmu() call.
+ *
+ *  - tlb_flush_mmu() / tlb_flush_mmu_tlbonly()
+ *
+ *    tlb_flush_mmu_tlbonly() - does the TLB invalidate (and resets
+ *                              related state, like the range)
+ *
+ *    tlb_flush_mmu() - in addition to the above TLB invalidate, also frees
+ *			whatever pages are still batched.
+ *
+ *  - mmu_gather::fullmm
+ *
+ *    A flag set by tlb_gather_mmu() to indicate we're going to free
+ *    the entire mm; this allows a number of optimizations.
+ *
+ *    - We can ignore tlb_{start,end}_vma(); because we don't
+ *      care about ranges. Everything will be shot down.
+ *
+ *    - (RISC) architectures that use ASIDs can cycle to a new ASID
+ *      and delay the invalidation until ASID space runs out.
+ *
+ *  - mmu_gather::need_flush_all
+ *
+ *    A flag that can be set by the arch code if it wants to force
+ *    flush the entire TLB irrespective of the range. For instance
+ *    x86-PAE needs this when changing top-level entries.
+ *
+ * And allows the architecture to provide and implement tlb_flush():
+ *
+ * tlb_flush() may, in addition to the above mentioned mmu_gather fields, make
+ * use of:
+ *
+ *  - mmu_gather::start / mmu_gather::end
+ *
+ *    which provides the range that needs to be flushed to cover the pages to
+ *    be freed.
+ *
+ *  - mmu_gather::freed_tables
+ *
+ *    set when we freed page table pages
+ *
+ *  - tlb_get_unmap_shift() / tlb_get_unmap_size()
+ *
+ *    returns the smallest TLB entry size unmapped in this range.
+ *
+ * If an architecture does not provide tlb_flush() a default implementation
+ * based on flush_tlb_range() will be used, unless MMU_GATHER_NO_RANGE is
+ * specified, in which case we'll default to flush_tlb_mm().
+ *
+ * Additionally there are a few opt-in features:
+ *
+ *  HAVE_MMU_GATHER_PAGE_SIZE
+ *
+ *  This ensures we call tlb_flush() every time tlb_change_page_size() actually
+ *  changes the size and provides mmu_gather::page_size to tlb_flush().
+ *
+ *  HAVE_RCU_TABLE_FREE
+ *
+ *  This provides tlb_remove_table(), to be used instead of tlb_remove_page()
+ *  for page directores (__p*_free_tlb()). This provides separate freeing of
+ *  the page-table pages themselves in a semi-RCU fashion (see comment below).
+ *  Useful if your architecture doesn't use IPIs for remote TLB invalidates
+ *  and therefore doesn't naturally serialize with software page-table walkers.
+ *
+ *  When used, an architecture is expected to provide __tlb_remove_table()
+ *  which does the actual freeing of these pages.
+ *
+ *  HAVE_RCU_TABLE_NO_INVALIDATE
+ *
+ *  This makes HAVE_RCU_TABLE_FREE avoid calling tlb_flush_mmu_tlbonly() before
+ *  freeing the page-table pages. This can be avoided if you use
+ *  HAVE_RCU_TABLE_FREE and your architecture does _NOT_ use the Linux
+ *  page-tables natively.
+ *
+ *  MMU_GATHER_NO_RANGE
+ *
+ *  Use this if your architecture lacks an efficient flush_tlb_range().
+ */
+
 #ifdef CONFIG_HAVE_RCU_TABLE_FREE
 /*
  * Semi RCU freeing of the page directories.
@@ -60,11 +191,11 @@ struct mmu_table_batch {
 #define MAX_TABLE_BATCH		\
 	((PAGE_SIZE - sizeof(struct mmu_table_batch)) / sizeof(void *))
 
-extern void tlb_table_flush(struct mmu_gather *tlb);
 extern void tlb_remove_table(struct mmu_gather *tlb, void *table);
 
 #endif
 
+#ifndef CONFIG_HAVE_MMU_GATHER_NO_GATHER
 /*
  * If we can't allocate a page to make a big batch of page pointers
  * to work on, then just handle a few from the on-stack structure.
@@ -89,14 +220,21 @@ struct mmu_gather_batch {
  */
 #define MAX_GATHER_BATCH_COUNT	(10000UL/MAX_GATHER_BATCH)
 
-/* struct mmu_gather is an opaque type used by the mm code for passing around
+extern bool __tlb_remove_page_size(struct mmu_gather *tlb, struct page *page,
+				   int page_size);
+#endif
+
+/*
+ * struct mmu_gather is an opaque type used by the mm code for passing around
  * any data needed by arch specific code for tlb_remove_page.
  */
 struct mmu_gather {
 	struct mm_struct	*mm;
+
 #ifdef CONFIG_HAVE_RCU_TABLE_FREE
 	struct mmu_table_batch	*batch;
 #endif
+
 	unsigned long		start;
 	unsigned long		end;
 	/*
@@ -124,23 +262,30 @@ struct mmu_gather {
 	unsigned int		cleared_puds : 1;
 	unsigned int		cleared_p4ds : 1;
 
+	/*
+	 * tracks VM_EXEC | VM_HUGETLB in tlb_start_vma
+	 */
+	unsigned int		vma_exec : 1;
+	unsigned int		vma_huge : 1;
+
+	unsigned int		batch_count;
+
+#ifndef CONFIG_HAVE_MMU_GATHER_NO_GATHER
 	struct mmu_gather_batch *active;
 	struct mmu_gather_batch	local;
 	struct page		*__pages[MMU_GATHER_BUNDLE];
-	unsigned int		batch_count;
-	int page_size;
-};
 
-#define HAVE_GENERIC_MMU_GATHER
+#ifdef CONFIG_HAVE_MMU_GATHER_PAGE_SIZE
+	unsigned int page_size;
+#endif
+#endif
+};
 
 void arch_tlb_gather_mmu(struct mmu_gather *tlb,
 	struct mm_struct *mm, unsigned long start, unsigned long end);
 void tlb_flush_mmu(struct mmu_gather *tlb);
 void arch_tlb_finish_mmu(struct mmu_gather *tlb,
 			 unsigned long start, unsigned long end, bool force);
-void tlb_flush_mmu_free(struct mmu_gather *tlb);
-extern bool __tlb_remove_page_size(struct mmu_gather *tlb, struct page *page,
-				   int page_size);
 
 static inline void __tlb_adjust_range(struct mmu_gather *tlb,
 				      unsigned long address,
@@ -163,8 +308,94 @@ static inline void __tlb_reset_range(struct mmu_gather *tlb)
 	tlb->cleared_pmds = 0;
 	tlb->cleared_puds = 0;
 	tlb->cleared_p4ds = 0;
+	/*
+	 * Do not reset mmu_gather::vma_* fields here, we do not
+	 * call into tlb_start_vma() again to set them if there is an
+	 * intermediate flush.
+	 */
+}
+
+#ifdef CONFIG_MMU_GATHER_NO_RANGE
+
+#if defined(tlb_flush) || defined(tlb_start_vma) || defined(tlb_end_vma)
+#error MMU_GATHER_NO_RANGE relies on default tlb_flush(), tlb_start_vma() and tlb_end_vma()
+#endif
+
+/*
+ * When an architecture does not have efficient means of range flushing TLBs
+ * there is no point in doing intermediate flushes on tlb_end_vma() to keep the
+ * range small. We equally don't have to worry about page granularity or other
+ * things.
+ *
+ * All we need to do is issue a full flush for any !0 range.
+ */
+static inline void tlb_flush(struct mmu_gather *tlb)
+{
+	if (tlb->end)
+		flush_tlb_mm(tlb->mm);
+}
+
+static inline void
+tlb_update_vma_flags(struct mmu_gather *tlb, struct vm_area_struct *vma) { }
+
+#define tlb_end_vma tlb_end_vma
+static inline void tlb_end_vma(struct mmu_gather *tlb, struct vm_area_struct *vma) { }
+
+#else /* CONFIG_MMU_GATHER_NO_RANGE */
+
+#ifndef tlb_flush
+
+#if defined(tlb_start_vma) || defined(tlb_end_vma)
+#error Default tlb_flush() relies on default tlb_start_vma() and tlb_end_vma()
+#endif
+
+/*
+ * When an architecture does not provide its own tlb_flush() implementation
+ * but does have a reasonably efficient flush_vma_range() implementation
+ * use that.
+ */
+static inline void tlb_flush(struct mmu_gather *tlb)
+{
+	if (tlb->fullmm || tlb->need_flush_all) {
+		flush_tlb_mm(tlb->mm);
+	} else if (tlb->end) {
+		struct vm_area_struct vma = {
+			.vm_mm = tlb->mm,
+			.vm_flags = (tlb->vma_exec ? VM_EXEC    : 0) |
+				    (tlb->vma_huge ? VM_HUGETLB : 0),
+		};
+
+		flush_tlb_range(&vma, tlb->start, tlb->end);
+	}
+}
+
+static inline void
+tlb_update_vma_flags(struct mmu_gather *tlb, struct vm_area_struct *vma)
+{
+	/*
+	 * flush_tlb_range() implementations that look at VM_HUGETLB (tile,
+	 * mips-4k) flush only large pages.
+	 *
+	 * flush_tlb_range() implementations that flush I-TLB also flush D-TLB
+	 * (tile, xtensa, arm), so it's ok to just add VM_EXEC to an existing
+	 * range.
+	 *
+	 * We rely on tlb_end_vma() to issue a flush, such that when we reset
+	 * these values the batch is empty.
+	 */
+	tlb->vma_huge = !!(vma->vm_flags & VM_HUGETLB);
+	tlb->vma_exec = !!(vma->vm_flags & VM_EXEC);
 }
 
+#else
+
+static inline void
+tlb_update_vma_flags(struct mmu_gather *tlb, struct vm_area_struct *vma) { }
+
+#endif
+
+#endif /* CONFIG_MMU_GATHER_NO_RANGE */
+
 static inline void tlb_flush_mmu_tlbonly(struct mmu_gather *tlb)
 {
 	if (!tlb->end)
@@ -196,21 +427,18 @@ static inline void tlb_remove_page(struct mmu_gather *tlb, struct page *page)
 	return tlb_remove_page_size(tlb, page, PAGE_SIZE);
 }
 
-#ifndef tlb_remove_check_page_size_change
-#define tlb_remove_check_page_size_change tlb_remove_check_page_size_change
-static inline void tlb_remove_check_page_size_change(struct mmu_gather *tlb,
+static inline void tlb_change_page_size(struct mmu_gather *tlb,
 						     unsigned int page_size)
 {
-	/*
-	 * We don't care about page size change, just update
-	 * mmu_gather page size here so that debug checks
-	 * doesn't throw false warning.
-	 */
-#ifdef CONFIG_DEBUG_VM
+#ifdef CONFIG_HAVE_MMU_GATHER_PAGE_SIZE
+	if (tlb->page_size && tlb->page_size != page_size) {
+		if (!tlb->fullmm)
+			tlb_flush_mmu(tlb);
+	}
+
 	tlb->page_size = page_size;
 #endif
 }
-#endif
 
 static inline unsigned long tlb_get_unmap_shift(struct mmu_gather *tlb)
 {
@@ -237,17 +465,30 @@ static inline unsigned long tlb_get_unmap_size(struct mmu_gather *tlb)
  * the vmas are adjusted to only cover the region to be torn down.
  */
 #ifndef tlb_start_vma
-#define tlb_start_vma(tlb, vma) do { } while (0)
-#endif
+static inline void tlb_start_vma(struct mmu_gather *tlb, struct vm_area_struct *vma)
+{
+	if (tlb->fullmm)
+		return;
 
-#define __tlb_end_vma(tlb, vma)					\
-	do {							\
-		if (!tlb->fullmm)				\
-			tlb_flush_mmu_tlbonly(tlb);		\
-	} while (0)
+	tlb_update_vma_flags(tlb, vma);
+	flush_cache_range(vma, vma->vm_start, vma->vm_end);
+}
+#endif
 
 #ifndef tlb_end_vma
-#define tlb_end_vma	__tlb_end_vma
+static inline void tlb_end_vma(struct mmu_gather *tlb, struct vm_area_struct *vma)
+{
+	if (tlb->fullmm)
+		return;
+
+	/*
+	 * Do a TLB flush and reset the range at VMA boundaries; this avoids
+	 * the ranges growing with the unused space between consecutive VMAs,
+	 * but also the mmu_gather::vma_* flags from tlb_start_vma() rely on
+	 * this.
+	 */
+	tlb_flush_mmu_tlbonly(tlb);
+}
 #endif
 
 #ifndef __tlb_remove_tlb_entry
@@ -372,6 +613,4 @@ static inline unsigned long tlb_get_unmap_size(struct mmu_gather *tlb)
 
 #endif /* CONFIG_MMU */
 
-#define tlb_migrate_finish(mm) do {} while (0)
-
 #endif /* _ASM_GENERIC__TLB_H */
diff --git a/include/crypto/aes.h b/include/crypto/aes.h
index 852eaa9cd4db..0fdb542c70cd 100644
--- a/include/crypto/aes.h
+++ b/include/crypto/aes.h
@@ -28,10 +28,10 @@ struct crypto_aes_ctx {
 	u32 key_length;
 };
 
-extern const u32 crypto_ft_tab[4][256];
-extern const u32 crypto_fl_tab[4][256];
-extern const u32 crypto_it_tab[4][256];
-extern const u32 crypto_il_tab[4][256];
+extern const u32 crypto_ft_tab[4][256] ____cacheline_aligned;
+extern const u32 crypto_fl_tab[4][256] ____cacheline_aligned;
+extern const u32 crypto_it_tab[4][256] ____cacheline_aligned;
+extern const u32 crypto_il_tab[4][256] ____cacheline_aligned;
 
 int crypto_aes_set_key(struct crypto_tfm *tfm, const u8 *in_key,
 		unsigned int key_len);
diff --git a/include/crypto/akcipher.h b/include/crypto/akcipher.h
index 2d690494568c..8884046659a0 100644
--- a/include/crypto/akcipher.h
+++ b/include/crypto/akcipher.h
@@ -19,14 +19,20 @@
  *
  * @base:	Common attributes for async crypto requests
  * @src:	Source data
- * @dst:	Destination data
+ *		For verify op this is signature + digest, in that case
+ *		total size of @src is @src_len + @dst_len.
+ * @dst:	Destination data (Should be NULL for verify op)
  * @src_len:	Size of the input buffer
- * @dst_len:	Size of the output buffer. It needs to be at least
- *		as big as the expected result depending	on the operation
+ *		For verify op it's size of signature part of @src, this part
+ *		is supposed to be operated by cipher.
+ * @dst_len:	Size of @dst buffer (for all ops except verify).
+ *		It needs to be at least	as big as the expected result
+ *		depending on the operation.
  *		After operation it will be updated with the actual size of the
  *		result.
  *		In case of error where the dst sgl size was insufficient,
  *		it will be updated to the size required for the operation.
+ *		For verify op this is size of digest part in @src.
  * @__ctx:	Start of private context data
  */
 struct akcipher_request {
@@ -55,10 +61,9 @@ struct crypto_akcipher {
  *		algorithm. In case of error, where the dst_len was insufficient,
  *		the req->dst_len will be updated to the size required for the
  *		operation
- * @verify:	Function performs a sign operation as defined by public key
- *		algorithm. In case of error, where the dst_len was insufficient,
- *		the req->dst_len will be updated to the size required for the
- *		operation
+ * @verify:	Function performs a complete verify operation as defined by
+ *		public key algorithm, returning verification status. Requires
+ *		digest value as input parameter.
  * @encrypt:	Function performs an encrypt operation as defined by public key
  *		algorithm. In case of error, where the dst_len was insufficient,
  *		the req->dst_len will be updated to the size required for the
@@ -69,10 +74,10 @@ struct crypto_akcipher {
  *		operation
  * @set_pub_key: Function invokes the algorithm specific set public key
  *		function, which knows how to decode and interpret
- *		the BER encoded public key
+ *		the BER encoded public key and parameters
  * @set_priv_key: Function invokes the algorithm specific set private key
  *		function, which knows how to decode and interpret
- *		the BER encoded private key
+ *		the BER encoded private key and parameters
  * @max_size:	Function returns dest buffer size required for a given key.
  * @init:	Initialize the cryptographic transformation object.
  *		This function is used to initialize the cryptographic
@@ -238,9 +243,10 @@ static inline void akcipher_request_set_callback(struct akcipher_request *req,
  *
  * @req:	public key request
  * @src:	ptr to input scatter list
- * @dst:	ptr to output scatter list
+ * @dst:	ptr to output scatter list or NULL for verify op
  * @src_len:	size of the src input scatter list to be processed
- * @dst_len:	size of the dst output scatter list
+ * @dst_len:	size of the dst output scatter list or size of signature
+ *		portion in @src for verify op
  */
 static inline void akcipher_request_set_crypt(struct akcipher_request *req,
 					      struct scatterlist *src,
@@ -343,14 +349,18 @@ static inline int crypto_akcipher_sign(struct akcipher_request *req)
 }
 
 /**
- * crypto_akcipher_verify() - Invoke public key verify operation
+ * crypto_akcipher_verify() - Invoke public key signature verification
  *
- * Function invokes the specific public key verify operation for a given
- * public key algorithm
+ * Function invokes the specific public key signature verification operation
+ * for a given public key algorithm.
  *
  * @req:	asymmetric key request
  *
- * Return: zero on success; error code in case of error
+ * Note: req->dst should be NULL, req->src should point to SG of size
+ * (req->src_size + req->dst_size), containing signature (of req->src_size
+ * length) with appended digest (of req->dst_size length).
+ *
+ * Return: zero on verification success; error code in case of error.
  */
 static inline int crypto_akcipher_verify(struct akcipher_request *req)
 {
@@ -369,11 +379,12 @@ static inline int crypto_akcipher_verify(struct akcipher_request *req)
  * crypto_akcipher_set_pub_key() - Invoke set public key operation
  *
  * Function invokes the algorithm specific set key function, which knows
- * how to decode and interpret the encoded key
+ * how to decode and interpret the encoded key and parameters
  *
  * @tfm:	tfm handle
- * @key:	BER encoded public key
- * @keylen:	length of the key
+ * @key:	BER encoded public key, algo OID, paramlen, BER encoded
+ *		parameters
+ * @keylen:	length of the key (not including other data)
  *
  * Return: zero on success; error code in case of error
  */
@@ -390,11 +401,12 @@ static inline int crypto_akcipher_set_pub_key(struct crypto_akcipher *tfm,
  * crypto_akcipher_set_priv_key() - Invoke set private key operation
  *
  * Function invokes the algorithm specific set key function, which knows
- * how to decode and interpret the encoded key
+ * how to decode and interpret the encoded key and parameters
  *
  * @tfm:	tfm handle
- * @key:	BER encoded private key
- * @keylen:	length of the key
+ * @key:	BER encoded private key, algo OID, paramlen, BER encoded
+ *		parameters
+ * @keylen:	length of the key (not including other data)
  *
  * Return: zero on success; error code in case of error
  */
diff --git a/include/crypto/cryptd.h b/include/crypto/cryptd.h
index 1e64f354c2b8..23169f4d87e6 100644
--- a/include/crypto/cryptd.h
+++ b/include/crypto/cryptd.h
@@ -18,27 +18,11 @@
 #include <crypto/hash.h>
 #include <crypto/skcipher.h>
 
-struct cryptd_ablkcipher {
-	struct crypto_ablkcipher base;
-};
-
-static inline struct cryptd_ablkcipher *__cryptd_ablkcipher_cast(
-	struct crypto_ablkcipher *tfm)
-{
-	return (struct cryptd_ablkcipher *)tfm;
-}
-
-/* alg_name should be algorithm to be cryptd-ed */
-struct cryptd_ablkcipher *cryptd_alloc_ablkcipher(const char *alg_name,
-						  u32 type, u32 mask);
-struct crypto_blkcipher *cryptd_ablkcipher_child(struct cryptd_ablkcipher *tfm);
-bool cryptd_ablkcipher_queued(struct cryptd_ablkcipher *tfm);
-void cryptd_free_ablkcipher(struct cryptd_ablkcipher *tfm);
-
 struct cryptd_skcipher {
 	struct crypto_skcipher base;
 };
 
+/* alg_name should be algorithm to be cryptd-ed */
 struct cryptd_skcipher *cryptd_alloc_skcipher(const char *alg_name,
 					      u32 type, u32 mask);
 struct crypto_skcipher *cryptd_skcipher_child(struct cryptd_skcipher *tfm);
diff --git a/include/crypto/des.h b/include/crypto/des.h
index d4094d58ac54..72c7c8e5a5a7 100644
--- a/include/crypto/des.h
+++ b/include/crypto/des.h
@@ -6,6 +6,11 @@
 #ifndef __CRYPTO_DES_H
 #define __CRYPTO_DES_H
 
+#include <crypto/skcipher.h>
+#include <linux/compiler.h>
+#include <linux/fips.h>
+#include <linux/string.h>
+
 #define DES_KEY_SIZE		8
 #define DES_EXPKEY_WORDS	32
 #define DES_BLOCK_SIZE		8
@@ -14,6 +19,44 @@
 #define DES3_EDE_EXPKEY_WORDS	(3 * DES_EXPKEY_WORDS)
 #define DES3_EDE_BLOCK_SIZE	DES_BLOCK_SIZE
 
+static inline int __des3_verify_key(u32 *flags, const u8 *key)
+{
+	int err = -EINVAL;
+	u32 K[6];
+
+	memcpy(K, key, DES3_EDE_KEY_SIZE);
+
+	if (unlikely(!((K[0] ^ K[2]) | (K[1] ^ K[3])) ||
+		     !((K[2] ^ K[4]) | (K[3] ^ K[5]))) &&
+		     (fips_enabled ||
+		      (*flags & CRYPTO_TFM_REQ_FORBID_WEAK_KEYS)))
+		goto bad;
+
+	if (unlikely(!((K[0] ^ K[4]) | (K[1] ^ K[5]))) && fips_enabled)
+		goto bad;
+
+	err = 0;
+
+out:
+	memzero_explicit(K, DES3_EDE_KEY_SIZE);
+
+	return err;
+
+bad:
+	*flags |= CRYPTO_TFM_RES_WEAK_KEY;
+	goto out;
+}
+
+static inline int des3_verify_key(struct crypto_skcipher *tfm, const u8 *key)
+{
+	u32 flags;
+	int err;
+
+	flags = crypto_skcipher_get_flags(tfm);
+	err = __des3_verify_key(&flags, key);
+	crypto_skcipher_set_flags(tfm, flags);
+	return err;
+}
 
 extern unsigned long des_ekey(u32 *pe, const u8 *k);
 
diff --git a/include/crypto/hash.h b/include/crypto/hash.h
index 3b31c1b349ae..d21bea2c4382 100644
--- a/include/crypto/hash.h
+++ b/include/crypto/hash.h
@@ -146,8 +146,6 @@ struct ahash_alg {
 
 struct shash_desc {
 	struct crypto_shash *tfm;
-	u32 flags;
-
 	void *__ctx[] CRYPTO_MINALIGN_ATTR;
 };
 
@@ -819,6 +817,7 @@ static inline void *shash_desc_ctx(struct shash_desc *desc)
  * cipher handle must point to a keyed message digest cipher in order for this
  * function to succeed.
  *
+ * Context: Any context.
  * Return: 0 if the setting of the key was successful; < 0 if an error occurred
  */
 int crypto_shash_setkey(struct crypto_shash *tfm, const u8 *key,
@@ -835,6 +834,7 @@ int crypto_shash_setkey(struct crypto_shash *tfm, const u8 *key,
  * crypto_shash_update and crypto_shash_final. The parameters have the same
  * meaning as discussed for those separate three functions.
  *
+ * Context: Any context.
  * Return: 0 if the message digest creation was successful; < 0 if an error
  *	   occurred
  */
@@ -850,6 +850,7 @@ int crypto_shash_digest(struct shash_desc *desc, const u8 *data,
  * caller-allocated output buffer out which must have sufficient size (e.g. by
  * calling crypto_shash_descsize).
  *
+ * Context: Any context.
  * Return: 0 if the export creation was successful; < 0 if an error occurred
  */
 static inline int crypto_shash_export(struct shash_desc *desc, void *out)
@@ -866,6 +867,7 @@ static inline int crypto_shash_export(struct shash_desc *desc, void *out)
  * the input buffer. That buffer should have been generated with the
  * crypto_ahash_export function.
  *
+ * Context: Any context.
  * Return: 0 if the import was successful; < 0 if an error occurred
  */
 static inline int crypto_shash_import(struct shash_desc *desc, const void *in)
@@ -886,6 +888,7 @@ static inline int crypto_shash_import(struct shash_desc *desc, const void *in)
  * operational state handle. Any potentially existing state created by
  * previous operations is discarded.
  *
+ * Context: Any context.
  * Return: 0 if the message digest initialization was successful; < 0 if an
  *	   error occurred
  */
@@ -907,6 +910,7 @@ static inline int crypto_shash_init(struct shash_desc *desc)
  *
  * Updates the message digest state of the operational state handle.
  *
+ * Context: Any context.
  * Return: 0 if the message digest update was successful; < 0 if an error
  *	   occurred
  */
@@ -923,6 +927,7 @@ int crypto_shash_update(struct shash_desc *desc, const u8 *data,
  * into the output buffer. The caller must ensure that the output buffer is
  * large enough by using crypto_shash_digestsize.
  *
+ * Context: Any context.
  * Return: 0 if the message digest creation was successful; < 0 if an error
  *	   occurred
  */
@@ -939,6 +944,7 @@ int crypto_shash_final(struct shash_desc *desc, u8 *out);
  * crypto_shash_update and crypto_shash_final. The parameters have the same
  * meaning as discussed for those separate functions.
  *
+ * Context: Any context.
  * Return: 0 if the message digest creation was successful; < 0 if an error
  *	   occurred
  */
diff --git a/include/crypto/internal/simd.h b/include/crypto/internal/simd.h
index f18344518e32..d2316242a988 100644
--- a/include/crypto/internal/simd.h
+++ b/include/crypto/internal/simd.h
@@ -6,6 +6,11 @@
 #ifndef _CRYPTO_INTERNAL_SIMD_H
 #define _CRYPTO_INTERNAL_SIMD_H
 
+#include <linux/percpu.h>
+#include <linux/types.h>
+
+/* skcipher support */
+
 struct simd_skcipher_alg;
 struct skcipher_alg;
 
@@ -22,4 +27,43 @@ int simd_register_skciphers_compat(struct skcipher_alg *algs, int count,
 void simd_unregister_skciphers(struct skcipher_alg *algs, int count,
 			       struct simd_skcipher_alg **simd_algs);
 
+/* AEAD support */
+
+struct simd_aead_alg;
+struct aead_alg;
+
+struct simd_aead_alg *simd_aead_create_compat(const char *algname,
+					      const char *drvname,
+					      const char *basename);
+struct simd_aead_alg *simd_aead_create(const char *algname,
+				       const char *basename);
+void simd_aead_free(struct simd_aead_alg *alg);
+
+int simd_register_aeads_compat(struct aead_alg *algs, int count,
+			       struct simd_aead_alg **simd_algs);
+
+void simd_unregister_aeads(struct aead_alg *algs, int count,
+			   struct simd_aead_alg **simd_algs);
+
+/*
+ * crypto_simd_usable() - is it allowed at this time to use SIMD instructions or
+ *			  access the SIMD register file?
+ *
+ * This delegates to may_use_simd(), except that this also returns false if SIMD
+ * in crypto code has been temporarily disabled on this CPU by the crypto
+ * self-tests, in order to test the no-SIMD fallback code.  This override is
+ * currently limited to configurations where the extra self-tests are enabled,
+ * because it might be a bit too invasive to be part of the regular self-tests.
+ *
+ * This is a macro so that <asm/simd.h>, which some architectures don't have,
+ * doesn't have to be included directly here.
+ */
+#ifdef CONFIG_CRYPTO_MANAGER_EXTRA_TESTS
+DECLARE_PER_CPU(bool, crypto_simd_disabled_for_test);
+#define crypto_simd_usable() \
+	(may_use_simd() && !this_cpu_read(crypto_simd_disabled_for_test))
+#else
+#define crypto_simd_usable() may_use_simd()
+#endif
+
 #endif /* _CRYPTO_INTERNAL_SIMD_H */
diff --git a/include/crypto/morus1280_glue.h b/include/crypto/morus1280_glue.h
index ad2aa743dd99..5cefddb1991f 100644
--- a/include/crypto/morus1280_glue.h
+++ b/include/crypto/morus1280_glue.h
@@ -47,16 +47,7 @@ int crypto_morus1280_glue_setauthsize(struct crypto_aead *tfm,
 int crypto_morus1280_glue_encrypt(struct aead_request *req);
 int crypto_morus1280_glue_decrypt(struct aead_request *req);
 
-int cryptd_morus1280_glue_setkey(struct crypto_aead *aead, const u8 *key,
-				 unsigned int keylen);
-int cryptd_morus1280_glue_setauthsize(struct crypto_aead *aead,
-				      unsigned int authsize);
-int cryptd_morus1280_glue_encrypt(struct aead_request *req);
-int cryptd_morus1280_glue_decrypt(struct aead_request *req);
-int cryptd_morus1280_glue_init_tfm(struct crypto_aead *aead);
-void cryptd_morus1280_glue_exit_tfm(struct crypto_aead *aead);
-
-#define MORUS1280_DECLARE_ALGS(id, driver_name, priority) \
+#define MORUS1280_DECLARE_ALG(id, driver_name, priority) \
 	static const struct morus1280_glue_ops crypto_morus1280_##id##_ops = {\
 		.init = crypto_morus1280_##id##_init, \
 		.ad = crypto_morus1280_##id##_ad, \
@@ -77,55 +68,29 @@ void cryptd_morus1280_glue_exit_tfm(struct crypto_aead *aead);
 	{ \
 	} \
 	\
-	static struct aead_alg crypto_morus1280_##id##_algs[] = {\
-		{ \
-			.setkey = crypto_morus1280_glue_setkey, \
-			.setauthsize = crypto_morus1280_glue_setauthsize, \
-			.encrypt = crypto_morus1280_glue_encrypt, \
-			.decrypt = crypto_morus1280_glue_decrypt, \
-			.init = crypto_morus1280_##id##_init_tfm, \
-			.exit = crypto_morus1280_##id##_exit_tfm, \
-			\
-			.ivsize = MORUS_NONCE_SIZE, \
-			.maxauthsize = MORUS_MAX_AUTH_SIZE, \
-			.chunksize = MORUS1280_BLOCK_SIZE, \
-			\
-			.base = { \
-				.cra_flags = CRYPTO_ALG_INTERNAL, \
-				.cra_blocksize = 1, \
-				.cra_ctxsize = sizeof(struct morus1280_ctx), \
-				.cra_alignmask = 0, \
-				\
-				.cra_name = "__morus1280", \
-				.cra_driver_name = "__"driver_name, \
-				\
-				.cra_module = THIS_MODULE, \
-			} \
-		}, { \
-			.setkey = cryptd_morus1280_glue_setkey, \
-			.setauthsize = cryptd_morus1280_glue_setauthsize, \
-			.encrypt = cryptd_morus1280_glue_encrypt, \
-			.decrypt = cryptd_morus1280_glue_decrypt, \
-			.init = cryptd_morus1280_glue_init_tfm, \
-			.exit = cryptd_morus1280_glue_exit_tfm, \
+	static struct aead_alg crypto_morus1280_##id##_alg = { \
+		.setkey = crypto_morus1280_glue_setkey, \
+		.setauthsize = crypto_morus1280_glue_setauthsize, \
+		.encrypt = crypto_morus1280_glue_encrypt, \
+		.decrypt = crypto_morus1280_glue_decrypt, \
+		.init = crypto_morus1280_##id##_init_tfm, \
+		.exit = crypto_morus1280_##id##_exit_tfm, \
+		\
+		.ivsize = MORUS_NONCE_SIZE, \
+		.maxauthsize = MORUS_MAX_AUTH_SIZE, \
+		.chunksize = MORUS1280_BLOCK_SIZE, \
+		\
+		.base = { \
+			.cra_flags = CRYPTO_ALG_INTERNAL, \
+			.cra_blocksize = 1, \
+			.cra_ctxsize = sizeof(struct morus1280_ctx), \
+			.cra_alignmask = 0, \
+			.cra_priority = priority, \
 			\
-			.ivsize = MORUS_NONCE_SIZE, \
-			.maxauthsize = MORUS_MAX_AUTH_SIZE, \
-			.chunksize = MORUS1280_BLOCK_SIZE, \
+			.cra_name = "__morus1280", \
+			.cra_driver_name = "__"driver_name, \
 			\
-			.base = { \
-				.cra_flags = CRYPTO_ALG_ASYNC, \
-				.cra_blocksize = 1, \
-				.cra_ctxsize = sizeof(struct crypto_aead *), \
-				.cra_alignmask = 0, \
-				\
-				.cra_priority = priority, \
-				\
-				.cra_name = "morus1280", \
-				.cra_driver_name = driver_name, \
-				\
-				.cra_module = THIS_MODULE, \
-			} \
+			.cra_module = THIS_MODULE, \
 		} \
 	}
 
diff --git a/include/crypto/morus640_glue.h b/include/crypto/morus640_glue.h
index df8e1103ff94..0ee6266cb26c 100644
--- a/include/crypto/morus640_glue.h
+++ b/include/crypto/morus640_glue.h
@@ -47,16 +47,7 @@ int crypto_morus640_glue_setauthsize(struct crypto_aead *tfm,
 int crypto_morus640_glue_encrypt(struct aead_request *req);
 int crypto_morus640_glue_decrypt(struct aead_request *req);
 
-int cryptd_morus640_glue_setkey(struct crypto_aead *aead, const u8 *key,
-				unsigned int keylen);
-int cryptd_morus640_glue_setauthsize(struct crypto_aead *aead,
-				     unsigned int authsize);
-int cryptd_morus640_glue_encrypt(struct aead_request *req);
-int cryptd_morus640_glue_decrypt(struct aead_request *req);
-int cryptd_morus640_glue_init_tfm(struct crypto_aead *aead);
-void cryptd_morus640_glue_exit_tfm(struct crypto_aead *aead);
-
-#define MORUS640_DECLARE_ALGS(id, driver_name, priority) \
+#define MORUS640_DECLARE_ALG(id, driver_name, priority) \
 	static const struct morus640_glue_ops crypto_morus640_##id##_ops = {\
 		.init = crypto_morus640_##id##_init, \
 		.ad = crypto_morus640_##id##_ad, \
@@ -77,55 +68,29 @@ void cryptd_morus640_glue_exit_tfm(struct crypto_aead *aead);
 	{ \
 	} \
 	\
-	static struct aead_alg crypto_morus640_##id##_algs[] = {\
-		{ \
-			.setkey = crypto_morus640_glue_setkey, \
-			.setauthsize = crypto_morus640_glue_setauthsize, \
-			.encrypt = crypto_morus640_glue_encrypt, \
-			.decrypt = crypto_morus640_glue_decrypt, \
-			.init = crypto_morus640_##id##_init_tfm, \
-			.exit = crypto_morus640_##id##_exit_tfm, \
-			\
-			.ivsize = MORUS_NONCE_SIZE, \
-			.maxauthsize = MORUS_MAX_AUTH_SIZE, \
-			.chunksize = MORUS640_BLOCK_SIZE, \
-			\
-			.base = { \
-				.cra_flags = CRYPTO_ALG_INTERNAL, \
-				.cra_blocksize = 1, \
-				.cra_ctxsize = sizeof(struct morus640_ctx), \
-				.cra_alignmask = 0, \
-				\
-				.cra_name = "__morus640", \
-				.cra_driver_name = "__"driver_name, \
-				\
-				.cra_module = THIS_MODULE, \
-			} \
-		}, { \
-			.setkey = cryptd_morus640_glue_setkey, \
-			.setauthsize = cryptd_morus640_glue_setauthsize, \
-			.encrypt = cryptd_morus640_glue_encrypt, \
-			.decrypt = cryptd_morus640_glue_decrypt, \
-			.init = cryptd_morus640_glue_init_tfm, \
-			.exit = cryptd_morus640_glue_exit_tfm, \
+	static struct aead_alg crypto_morus640_##id##_alg = {\
+		.setkey = crypto_morus640_glue_setkey, \
+		.setauthsize = crypto_morus640_glue_setauthsize, \
+		.encrypt = crypto_morus640_glue_encrypt, \
+		.decrypt = crypto_morus640_glue_decrypt, \
+		.init = crypto_morus640_##id##_init_tfm, \
+		.exit = crypto_morus640_##id##_exit_tfm, \
+		\
+		.ivsize = MORUS_NONCE_SIZE, \
+		.maxauthsize = MORUS_MAX_AUTH_SIZE, \
+		.chunksize = MORUS640_BLOCK_SIZE, \
+		\
+		.base = { \
+			.cra_flags = CRYPTO_ALG_INTERNAL, \
+			.cra_blocksize = 1, \
+			.cra_ctxsize = sizeof(struct morus640_ctx), \
+			.cra_alignmask = 0, \
+			.cra_priority = priority, \
 			\
-			.ivsize = MORUS_NONCE_SIZE, \
-			.maxauthsize = MORUS_MAX_AUTH_SIZE, \
-			.chunksize = MORUS640_BLOCK_SIZE, \
+			.cra_name = "__morus640", \
+			.cra_driver_name = "__"driver_name, \
 			\
-			.base = { \
-				.cra_flags = CRYPTO_ALG_ASYNC, \
-				.cra_blocksize = 1, \
-				.cra_ctxsize = sizeof(struct crypto_aead *), \
-				.cra_alignmask = 0, \
-				\
-				.cra_priority = priority, \
-				\
-				.cra_name = "morus640", \
-				.cra_driver_name = driver_name, \
-				\
-				.cra_module = THIS_MODULE, \
-			} \
+			.cra_module = THIS_MODULE, \
 		} \
 	}
 
diff --git a/include/crypto/public_key.h b/include/crypto/public_key.h
index be626eac9113..712fe1214b5f 100644
--- a/include/crypto/public_key.h
+++ b/include/crypto/public_key.h
@@ -15,6 +15,7 @@
 #define _LINUX_PUBLIC_KEY_H
 
 #include <linux/keyctl.h>
+#include <linux/oid_registry.h>
 
 /*
  * Cryptographic data for the public-key subtype of the asymmetric key type.
@@ -25,6 +26,9 @@
 struct public_key {
 	void *key;
 	u32 keylen;
+	enum OID algo;
+	void *params;
+	u32 paramlen;
 	bool key_is_private;
 	const char *id_type;
 	const char *pkey_algo;
diff --git a/include/crypto/streebog.h b/include/crypto/streebog.h
index 856e32af8657..cae1b4a01971 100644
--- a/include/crypto/streebog.h
+++ b/include/crypto/streebog.h
@@ -23,7 +23,10 @@ struct streebog_uint512 {
 };
 
 struct streebog_state {
-	u8 buffer[STREEBOG_BLOCK_SIZE];
+	union {
+		u8 buffer[STREEBOG_BLOCK_SIZE];
+		struct streebog_uint512 m;
+	};
 	struct streebog_uint512 hash;
 	struct streebog_uint512 h;
 	struct streebog_uint512 N;
diff --git a/include/drm/drm_modeset_helper_vtables.h b/include/drm/drm_modeset_helper_vtables.h
index cfb7be40bed7..ce4de6b1e444 100644
--- a/include/drm/drm_modeset_helper_vtables.h
+++ b/include/drm/drm_modeset_helper_vtables.h
@@ -418,6 +418,8 @@ struct drm_crtc_helper_funcs {
 	 * Drivers can use the @old_crtc_state input parameter if the operations
 	 * needed to enable the CRTC don't depend solely on the new state but
 	 * also on the transition between the old state and the new state.
+	 *
+	 * This function is optional.
 	 */
 	void (*atomic_enable)(struct drm_crtc *crtc,
 			      struct drm_crtc_state *old_crtc_state);
@@ -441,6 +443,8 @@ struct drm_crtc_helper_funcs {
 	 * parameter @old_crtc_state which could be used to access the old
 	 * state. Atomic drivers should consider to use this one instead
 	 * of @disable.
+	 *
+	 * This function is optional.
 	 */
 	void (*atomic_disable)(struct drm_crtc *crtc,
 			       struct drm_crtc_state *old_crtc_state);
diff --git a/include/drm/ttm/ttm_bo_driver.h b/include/drm/ttm/ttm_bo_driver.h
index cbf3180cb612..668ad971cd7b 100644
--- a/include/drm/ttm/ttm_bo_driver.h
+++ b/include/drm/ttm/ttm_bo_driver.h
@@ -420,7 +420,6 @@ extern struct ttm_bo_global {
 	/**
 	 * Protected by ttm_global_mutex.
 	 */
-	unsigned int use_count;
 	struct list_head device_list;
 
 	/**
diff --git a/include/dt-bindings/clock/sifive-fu540-prci.h b/include/dt-bindings/clock/sifive-fu540-prci.h
new file mode 100644
index 000000000000..6a0b70a37d78
--- /dev/null
+++ b/include/dt-bindings/clock/sifive-fu540-prci.h
@@ -0,0 +1,18 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Copyright (C) 2018-2019 SiFive, Inc.
+ * Wesley Terpstra
+ * Paul Walmsley
+ */
+
+#ifndef __DT_BINDINGS_CLOCK_SIFIVE_FU540_PRCI_H
+#define __DT_BINDINGS_CLOCK_SIFIVE_FU540_PRCI_H
+
+/* Clock indexes for use by Device Tree data and the PRCI driver */
+
+#define PRCI_CLK_COREPLL	       0
+#define PRCI_CLK_DDRPLL		       1
+#define PRCI_CLK_GEMGXLPLL	       2
+#define PRCI_CLK_TLCLK		       3
+
+#endif
diff --git a/include/dt-bindings/reset/amlogic,meson-g12a-reset.h b/include/dt-bindings/reset/amlogic,meson-g12a-reset.h
index 8063e8314eef..6d487c5eba2c 100644
--- a/include/dt-bindings/reset/amlogic,meson-g12a-reset.h
+++ b/include/dt-bindings/reset/amlogic,meson-g12a-reset.h
@@ -51,7 +51,10 @@
 #define RESET_SD_EMMC_A			44
 #define RESET_SD_EMMC_B			45
 #define RESET_SD_EMMC_C			46
-/*					47-60 */
+/*					47	*/
+#define RESET_USB_PHY20			48
+#define RESET_USB_PHY21			49
+/*					50-60	*/
 #define RESET_AUDIO_CODEC		61
 /*					62-63	*/
 /*	RESET2					*/
diff --git a/include/keys/trusted.h b/include/keys/trusted.h
index adbcb6817826..0071298b9b28 100644
--- a/include/keys/trusted.h
+++ b/include/keys/trusted.h
@@ -38,7 +38,7 @@ enum {
 
 int TSS_authhmac(unsigned char *digest, const unsigned char *key,
 			unsigned int keylen, unsigned char *h1,
-			unsigned char *h2, unsigned char h3, ...);
+			unsigned char *h2, unsigned int h3, ...);
 int TSS_checkhmac1(unsigned char *buffer,
 			  const uint32_t command,
 			  const unsigned char *ononce,
diff --git a/include/linux/acpi.h b/include/linux/acpi.h
index d5dcebd7aad3..ca55ae00f8c9 100644
--- a/include/linux/acpi.h
+++ b/include/linux/acpi.h
@@ -669,12 +669,14 @@ static inline bool acpi_dev_present(const char *hid, const char *uid, s64 hrv)
 	return false;
 }
 
-static inline const char *
-acpi_dev_get_first_match_name(const char *hid, const char *uid, s64 hrv)
+static inline struct acpi_device *
+acpi_dev_get_first_match_dev(const char *hid, const char *uid, s64 hrv)
 {
 	return NULL;
 }
 
+static inline void acpi_dev_put(struct acpi_device *adev) {}
+
 static inline bool is_acpi_node(struct fwnode_handle *fwnode)
 {
 	return false;
diff --git a/include/linux/acpi_iort.h b/include/linux/acpi_iort.h
index 38cd77b39a64..723e4dfa1c14 100644
--- a/include/linux/acpi_iort.h
+++ b/include/linux/acpi_iort.h
@@ -26,6 +26,14 @@
 #define IORT_IRQ_MASK(irq)		(irq & 0xffffffffULL)
 #define IORT_IRQ_TRIGGER_MASK(irq)	((irq >> 32) & 0xffffffffULL)
 
+/*
+ * PMCG model identifiers for use in smmu pmu driver. Please note
+ * that this is purely for the use of software and has nothing to
+ * do with hardware or with IORT specification.
+ */
+#define IORT_SMMU_V3_PMCG_GENERIC        0x00000000 /* Generic SMMUv3 PMCG */
+#define IORT_SMMU_V3_PMCG_HISI_HIP08     0x00000001 /* HiSilicon HIP08 PMCG */
+
 int iort_register_domain_token(int trans_id, phys_addr_t base,
 			       struct fwnode_handle *fw_node);
 void iort_deregister_domain_token(int trans_id);
diff --git a/include/linux/atalk.h b/include/linux/atalk.h
index d5cfc0b15b76..f6034ba774be 100644
--- a/include/linux/atalk.h
+++ b/include/linux/atalk.h
@@ -108,7 +108,7 @@ static __inline__ struct elapaarp *aarp_hdr(struct sk_buff *skb)
 #define AARP_RESOLVE_TIME	(10 * HZ)
 
 extern struct datalink_proto *ddp_dl, *aarp_dl;
-extern void aarp_proto_init(void);
+extern int aarp_proto_init(void);
 
 /* Inter module exports */
 
diff --git a/include/linux/bio.h b/include/linux/bio.h
index bb6090aa165d..e584673c1881 100644
--- a/include/linux/bio.h
+++ b/include/linux/bio.h
@@ -120,19 +120,23 @@ static inline bool bio_full(struct bio *bio)
 	return bio->bi_vcnt >= bio->bi_max_vecs;
 }
 
-#define mp_bvec_for_each_segment(bv, bvl, i, iter_all)			\
-	for (bv = bvec_init_iter_all(&iter_all);			\
-		(iter_all.done < (bvl)->bv_len) &&			\
-		(mp_bvec_next_segment((bvl), &iter_all), 1);		\
-		iter_all.done += bv->bv_len, i += 1)
+static inline bool bio_next_segment(const struct bio *bio,
+				    struct bvec_iter_all *iter)
+{
+	if (iter->idx >= bio->bi_vcnt)
+		return false;
+
+	bvec_advance(&bio->bi_io_vec[iter->idx], iter);
+	return true;
+}
 
 /*
  * drivers should _never_ use the all version - the bio may have been split
  * before it got to the driver and the driver won't own all of it
  */
-#define bio_for_each_segment_all(bvl, bio, i, iter_all)		\
-	for (i = 0, iter_all.idx = 0; iter_all.idx < (bio)->bi_vcnt; iter_all.idx++)	\
-		mp_bvec_for_each_segment(bvl, &((bio)->bi_io_vec[iter_all.idx]), i, iter_all)
+#define bio_for_each_segment_all(bvl, bio, i, iter)			\
+	for (i = 0, bvl = bvec_init_iter_all(&iter);			\
+	     bio_next_segment((bio), &iter); i++)
 
 static inline void bio_advance_iter(struct bio *bio, struct bvec_iter *iter,
 				    unsigned bytes)
diff --git a/include/linux/bitrev.h b/include/linux/bitrev.h
index 50fb0dee23e8..d35b8ec1c485 100644
--- a/include/linux/bitrev.h
+++ b/include/linux/bitrev.h
@@ -34,41 +34,41 @@ static inline u32 __bitrev32(u32 x)
 
 #define __constant_bitrev32(x)	\
 ({					\
-	u32 __x = x;			\
-	__x = (__x >> 16) | (__x << 16);	\
-	__x = ((__x & (u32)0xFF00FF00UL) >> 8) | ((__x & (u32)0x00FF00FFUL) << 8);	\
-	__x = ((__x & (u32)0xF0F0F0F0UL) >> 4) | ((__x & (u32)0x0F0F0F0FUL) << 4);	\
-	__x = ((__x & (u32)0xCCCCCCCCUL) >> 2) | ((__x & (u32)0x33333333UL) << 2);	\
-	__x = ((__x & (u32)0xAAAAAAAAUL) >> 1) | ((__x & (u32)0x55555555UL) << 1);	\
-	__x;								\
+	u32 ___x = x;			\
+	___x = (___x >> 16) | (___x << 16);	\
+	___x = ((___x & (u32)0xFF00FF00UL) >> 8) | ((___x & (u32)0x00FF00FFUL) << 8);	\
+	___x = ((___x & (u32)0xF0F0F0F0UL) >> 4) | ((___x & (u32)0x0F0F0F0FUL) << 4);	\
+	___x = ((___x & (u32)0xCCCCCCCCUL) >> 2) | ((___x & (u32)0x33333333UL) << 2);	\
+	___x = ((___x & (u32)0xAAAAAAAAUL) >> 1) | ((___x & (u32)0x55555555UL) << 1);	\
+	___x;								\
 })
 
 #define __constant_bitrev16(x)	\
 ({					\
-	u16 __x = x;			\
-	__x = (__x >> 8) | (__x << 8);	\
-	__x = ((__x & (u16)0xF0F0U) >> 4) | ((__x & (u16)0x0F0FU) << 4);	\
-	__x = ((__x & (u16)0xCCCCU) >> 2) | ((__x & (u16)0x3333U) << 2);	\
-	__x = ((__x & (u16)0xAAAAU) >> 1) | ((__x & (u16)0x5555U) << 1);	\
-	__x;								\
+	u16 ___x = x;			\
+	___x = (___x >> 8) | (___x << 8);	\
+	___x = ((___x & (u16)0xF0F0U) >> 4) | ((___x & (u16)0x0F0FU) << 4);	\
+	___x = ((___x & (u16)0xCCCCU) >> 2) | ((___x & (u16)0x3333U) << 2);	\
+	___x = ((___x & (u16)0xAAAAU) >> 1) | ((___x & (u16)0x5555U) << 1);	\
+	___x;								\
 })
 
 #define __constant_bitrev8x4(x) \
 ({			\
-	u32 __x = x;	\
-	__x = ((__x & (u32)0xF0F0F0F0UL) >> 4) | ((__x & (u32)0x0F0F0F0FUL) << 4);	\
-	__x = ((__x & (u32)0xCCCCCCCCUL) >> 2) | ((__x & (u32)0x33333333UL) << 2);	\
-	__x = ((__x & (u32)0xAAAAAAAAUL) >> 1) | ((__x & (u32)0x55555555UL) << 1);	\
-	__x;								\
+	u32 ___x = x;	\
+	___x = ((___x & (u32)0xF0F0F0F0UL) >> 4) | ((___x & (u32)0x0F0F0F0FUL) << 4);	\
+	___x = ((___x & (u32)0xCCCCCCCCUL) >> 2) | ((___x & (u32)0x33333333UL) << 2);	\
+	___x = ((___x & (u32)0xAAAAAAAAUL) >> 1) | ((___x & (u32)0x55555555UL) << 1);	\
+	___x;								\
 })
 
 #define __constant_bitrev8(x)	\
 ({					\
-	u8 __x = x;			\
-	__x = (__x >> 4) | (__x << 4);	\
-	__x = ((__x & (u8)0xCCU) >> 2) | ((__x & (u8)0x33U) << 2);	\
-	__x = ((__x & (u8)0xAAU) >> 1) | ((__x & (u8)0x55U) << 1);	\
-	__x;								\
+	u8 ___x = x;			\
+	___x = (___x >> 4) | (___x << 4);	\
+	___x = ((___x & (u8)0xCCU) >> 2) | ((___x & (u8)0x33U) << 2);	\
+	___x = ((___x & (u8)0xAAU) >> 1) | ((___x & (u8)0x55U) << 1);	\
+	___x;								\
 })
 
 #define bitrev32(x) \
diff --git a/include/linux/blk-mq.h b/include/linux/blk-mq.h
index cb2aa7ecafff..db29928de467 100644
--- a/include/linux/blk-mq.h
+++ b/include/linux/blk-mq.h
@@ -302,6 +302,7 @@ void blk_mq_requeue_request(struct request *rq, bool kick_requeue_list);
 void blk_mq_kick_requeue_list(struct request_queue *q);
 void blk_mq_delay_kick_requeue_list(struct request_queue *q, unsigned long msecs);
 bool blk_mq_complete_request(struct request *rq);
+void blk_mq_complete_request_sync(struct request *rq);
 bool blk_mq_bio_list_merge(struct request_queue *q, struct list_head *list,
 			   struct bio *bio);
 bool blk_mq_queue_stopped(struct request_queue *q);
diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h
index 5c58a3b2bf00..317ab30d2904 100644
--- a/include/linux/blkdev.h
+++ b/include/linux/blkdev.h
@@ -548,7 +548,6 @@ struct request_queue {
 	struct rcu_head		rcu_head;
 	wait_queue_head_t	mq_freeze_wq;
 	struct percpu_ref	q_usage_counter;
-	struct list_head	all_q_node;
 
 	struct blk_mq_tag_set	*tag_set;
 	struct list_head	tag_set_list;
diff --git a/include/linux/bpf.h b/include/linux/bpf.h
index a2132e09dc1c..944ccc310201 100644
--- a/include/linux/bpf.h
+++ b/include/linux/bpf.h
@@ -193,7 +193,6 @@ enum bpf_arg_type {
 
 	ARG_PTR_TO_CTX,		/* pointer to context */
 	ARG_ANYTHING,		/* any (initialized) argument is ok */
-	ARG_PTR_TO_SOCKET,	/* pointer to bpf_sock */
 	ARG_PTR_TO_SPIN_LOCK,	/* pointer to bpf_spin_lock */
 	ARG_PTR_TO_SOCK_COMMON,	/* pointer to sock_common */
 };
@@ -511,7 +510,7 @@ int bpf_prog_array_copy(struct bpf_prog_array __rcu *old_array,
 		}					\
 _out:							\
 		rcu_read_unlock();			\
-		preempt_enable_no_resched();		\
+		preempt_enable();			\
 		_ret;					\
 	 })
 
diff --git a/include/linux/bpf_verifier.h b/include/linux/bpf_verifier.h
index 69f7a3449eda..7d8228d1c898 100644
--- a/include/linux/bpf_verifier.h
+++ b/include/linux/bpf_verifier.h
@@ -66,6 +66,46 @@ struct bpf_reg_state {
 	 * same reference to the socket, to determine proper reference freeing.
 	 */
 	u32 id;
+	/* PTR_TO_SOCKET and PTR_TO_TCP_SOCK could be a ptr returned
+	 * from a pointer-cast helper, bpf_sk_fullsock() and
+	 * bpf_tcp_sock().
+	 *
+	 * Consider the following where "sk" is a reference counted
+	 * pointer returned from "sk = bpf_sk_lookup_tcp();":
+	 *
+	 * 1: sk = bpf_sk_lookup_tcp();
+	 * 2: if (!sk) { return 0; }
+	 * 3: fullsock = bpf_sk_fullsock(sk);
+	 * 4: if (!fullsock) { bpf_sk_release(sk); return 0; }
+	 * 5: tp = bpf_tcp_sock(fullsock);
+	 * 6: if (!tp) { bpf_sk_release(sk); return 0; }
+	 * 7: bpf_sk_release(sk);
+	 * 8: snd_cwnd = tp->snd_cwnd;  // verifier will complain
+	 *
+	 * After bpf_sk_release(sk) at line 7, both "fullsock" ptr and
+	 * "tp" ptr should be invalidated also.  In order to do that,
+	 * the reg holding "fullsock" and "sk" need to remember
+	 * the original refcounted ptr id (i.e. sk_reg->id) in ref_obj_id
+	 * such that the verifier can reset all regs which have
+	 * ref_obj_id matching the sk_reg->id.
+	 *
+	 * sk_reg->ref_obj_id is set to sk_reg->id at line 1.
+	 * sk_reg->id will stay as NULL-marking purpose only.
+	 * After NULL-marking is done, sk_reg->id can be reset to 0.
+	 *
+	 * After "fullsock = bpf_sk_fullsock(sk);" at line 3,
+	 * fullsock_reg->ref_obj_id is set to sk_reg->ref_obj_id.
+	 *
+	 * After "tp = bpf_tcp_sock(fullsock);" at line 5,
+	 * tp_reg->ref_obj_id is set to fullsock_reg->ref_obj_id
+	 * which is the same as sk_reg->ref_obj_id.
+	 *
+	 * From the verifier perspective, if sk, fullsock and tp
+	 * are not NULL, they are the same ptr with different
+	 * reg->type.  In particular, bpf_sk_release(tp) is also
+	 * allowed and has the same effect as bpf_sk_release(sk).
+	 */
+	u32 ref_obj_id;
 	/* For scalar types (SCALAR_VALUE), this represents our knowledge of
 	 * the actual value.
 	 * For pointer types, this represents the variable part of the offset
diff --git a/include/linux/brcmphy.h b/include/linux/brcmphy.h
index 9cd00a37b8d3..6db2d9a6e503 100644
--- a/include/linux/brcmphy.h
+++ b/include/linux/brcmphy.h
@@ -148,6 +148,22 @@
 #define BCM_LED_SRC_OFF		0xe	/* Tied high */
 #define BCM_LED_SRC_ON		0xf	/* Tied low */
 
+/*
+ * Broadcom Multicolor LED configurations (expansion register 4)
+ */
+#define BCM_EXP_MULTICOLOR		(MII_BCM54XX_EXP_SEL_ER + 0x04)
+#define BCM_LED_MULTICOLOR_IN_PHASE	BIT(8)
+#define BCM_LED_MULTICOLOR_LINK_ACT	0x0
+#define BCM_LED_MULTICOLOR_SPEED	0x1
+#define BCM_LED_MULTICOLOR_ACT_FLASH	0x2
+#define BCM_LED_MULTICOLOR_FDX		0x3
+#define BCM_LED_MULTICOLOR_OFF		0x4
+#define BCM_LED_MULTICOLOR_ON		0x5
+#define BCM_LED_MULTICOLOR_ALT		0x6
+#define BCM_LED_MULTICOLOR_FLASH	0x7
+#define BCM_LED_MULTICOLOR_LINK		0x8
+#define BCM_LED_MULTICOLOR_ACT		0x9
+#define BCM_LED_MULTICOLOR_PROGRAM	0xa
 
 /*
  * BCM5482: Shadow registers
diff --git a/include/linux/bvec.h b/include/linux/bvec.h
index f6275c4da13a..ff13cbc1887d 100644
--- a/include/linux/bvec.h
+++ b/include/linux/bvec.h
@@ -145,26 +145,33 @@ static inline bool bvec_iter_advance(const struct bio_vec *bv,
 
 static inline struct bio_vec *bvec_init_iter_all(struct bvec_iter_all *iter_all)
 {
-	iter_all->bv.bv_page = NULL;
 	iter_all->done = 0;
+	iter_all->idx = 0;
 
 	return &iter_all->bv;
 }
 
-static inline void mp_bvec_next_segment(const struct bio_vec *bvec,
-					struct bvec_iter_all *iter_all)
+static inline void bvec_advance(const struct bio_vec *bvec,
+				struct bvec_iter_all *iter_all)
 {
 	struct bio_vec *bv = &iter_all->bv;
 
-	if (bv->bv_page) {
+	if (iter_all->done) {
 		bv->bv_page = nth_page(bv->bv_page, 1);
 		bv->bv_offset = 0;
 	} else {
-		bv->bv_page = bvec->bv_page;
-		bv->bv_offset = bvec->bv_offset;
+		bv->bv_page = bvec_nth_page(bvec->bv_page, bvec->bv_offset /
+					    PAGE_SIZE);
+		bv->bv_offset = bvec->bv_offset & ~PAGE_MASK;
 	}
 	bv->bv_len = min_t(unsigned int, PAGE_SIZE - bv->bv_offset,
 			   bvec->bv_len - iter_all->done);
+	iter_all->done += bv->bv_len;
+
+	if (iter_all->done == bvec->bv_len) {
+		iter_all->idx++;
+		iter_all->done = 0;
+	}
 }
 
 /*
diff --git a/include/linux/clk.h b/include/linux/clk.h
index d8bc1a856b39..f689fc58d7be 100644
--- a/include/linux/clk.h
+++ b/include/linux/clk.h
@@ -811,6 +811,22 @@ static inline bool clk_has_parent(struct clk *clk, struct clk *parent)
 	return true;
 }
 
+static inline int clk_set_rate_range(struct clk *clk, unsigned long min,
+				     unsigned long max)
+{
+	return 0;
+}
+
+static inline int clk_set_min_rate(struct clk *clk, unsigned long rate)
+{
+	return 0;
+}
+
+static inline int clk_set_max_rate(struct clk *clk, unsigned long rate)
+{
+	return 0;
+}
+
 static inline int clk_set_parent(struct clk *clk, struct clk *parent)
 {
 	return 0;
diff --git a/include/linux/compiler.h b/include/linux/compiler.h
index 445348facea9..d58aa0db05f9 100644
--- a/include/linux/compiler.h
+++ b/include/linux/compiler.h
@@ -67,7 +67,7 @@ void ftrace_likely_update(struct ftrace_likely_data *f, int val,
 				.line = __LINE__,			\
 			};						\
 		______r = !!(cond);					\
-		______f.miss_hit[______r]++;					\
+		______r ? ______f.miss_hit[1]++ : ______f.miss_hit[0]++;\
 		______r;						\
 	}))
 #endif /* CONFIG_PROFILE_ALL_BRANCHES */
diff --git a/include/linux/cpu.h b/include/linux/cpu.h
index 5041357d0297..732745f865b7 100644
--- a/include/linux/cpu.h
+++ b/include/linux/cpu.h
@@ -137,9 +137,26 @@ static inline int disable_nonboot_cpus(void)
 	return freeze_secondary_cpus(0);
 }
 extern void enable_nonboot_cpus(void);
+
+static inline int suspend_disable_secondary_cpus(void)
+{
+	int cpu = 0;
+
+	if (IS_ENABLED(CONFIG_PM_SLEEP_SMP_NONZERO_CPU))
+		cpu = -1;
+
+	return freeze_secondary_cpus(cpu);
+}
+static inline void suspend_enable_secondary_cpus(void)
+{
+	return enable_nonboot_cpus();
+}
+
 #else /* !CONFIG_PM_SLEEP_SMP */
 static inline int disable_nonboot_cpus(void) { return 0; }
 static inline void enable_nonboot_cpus(void) {}
+static inline int suspend_disable_secondary_cpus(void) { return 0; }
+static inline void suspend_enable_secondary_cpus(void) { }
 #endif /* !CONFIG_PM_SLEEP_SMP */
 
 void cpu_startup_entry(enum cpuhp_state state);
@@ -175,6 +192,7 @@ enum cpuhp_smt_control {
 	CPU_SMT_DISABLED,
 	CPU_SMT_FORCE_DISABLED,
 	CPU_SMT_NOT_SUPPORTED,
+	CPU_SMT_NOT_IMPLEMENTED,
 };
 
 #if defined(CONFIG_SMP) && defined(CONFIG_HOTPLUG_SMT)
@@ -182,9 +200,33 @@ extern enum cpuhp_smt_control cpu_smt_control;
 extern void cpu_smt_disable(bool force);
 extern void cpu_smt_check_topology(void);
 #else
-# define cpu_smt_control		(CPU_SMT_ENABLED)
+# define cpu_smt_control		(CPU_SMT_NOT_IMPLEMENTED)
 static inline void cpu_smt_disable(bool force) { }
 static inline void cpu_smt_check_topology(void) { }
 #endif
 
+/*
+ * These are used for a global "mitigations=" cmdline option for toggling
+ * optional CPU mitigations.
+ */
+enum cpu_mitigations {
+	CPU_MITIGATIONS_OFF,
+	CPU_MITIGATIONS_AUTO,
+	CPU_MITIGATIONS_AUTO_NOSMT,
+};
+
+extern enum cpu_mitigations cpu_mitigations;
+
+/* mitigations=off */
+static inline bool cpu_mitigations_off(void)
+{
+	return cpu_mitigations == CPU_MITIGATIONS_OFF;
+}
+
+/* mitigations=auto,nosmt */
+static inline bool cpu_mitigations_auto_nosmt(void)
+{
+	return cpu_mitigations == CPU_MITIGATIONS_AUTO_NOSMT;
+}
+
 #endif /* _LINUX_CPU_H_ */
diff --git a/include/linux/cpufreq.h b/include/linux/cpufreq.h
index b160e98076e3..684caf067003 100644
--- a/include/linux/cpufreq.h
+++ b/include/linux/cpufreq.h
@@ -178,6 +178,11 @@ static inline struct cpufreq_policy *cpufreq_cpu_get(unsigned int cpu)
 static inline void cpufreq_cpu_put(struct cpufreq_policy *policy) { }
 #endif
 
+static inline bool policy_is_inactive(struct cpufreq_policy *policy)
+{
+	return cpumask_empty(policy->cpus);
+}
+
 static inline bool policy_is_shared(struct cpufreq_policy *policy)
 {
 	return cpumask_weight(policy->cpus) > 1;
@@ -193,8 +198,14 @@ unsigned int cpufreq_quick_get_max(unsigned int cpu);
 void disable_cpufreq(void);
 
 u64 get_cpu_idle_time(unsigned int cpu, u64 *wall, int io_busy);
+
+struct cpufreq_policy *cpufreq_cpu_acquire(unsigned int cpu);
+void cpufreq_cpu_release(struct cpufreq_policy *policy);
 int cpufreq_get_policy(struct cpufreq_policy *policy, unsigned int cpu);
+int cpufreq_set_policy(struct cpufreq_policy *policy,
+		       struct cpufreq_policy *new_policy);
 void cpufreq_update_policy(unsigned int cpu);
+void cpufreq_update_limits(unsigned int cpu);
 bool have_governor_per_policy(void);
 struct kobject *get_governor_parent_kobj(struct cpufreq_policy *policy);
 void cpufreq_enable_fast_switch(struct cpufreq_policy *policy);
@@ -322,6 +333,9 @@ struct cpufreq_driver {
 	/* should be defined, if possible */
 	unsigned int	(*get)(unsigned int cpu);
 
+	/* Called to update policy limits on firmware notifications. */
+	void		(*update_limits)(unsigned int cpu);
+
 	/* optional */
 	int		(*bios_limit)(int cpu, unsigned int *limit);
 
diff --git a/include/linux/cpuhotplug.h b/include/linux/cpuhotplug.h
index e78281d07b70..dbfdd0fadbef 100644
--- a/include/linux/cpuhotplug.h
+++ b/include/linux/cpuhotplug.h
@@ -147,6 +147,7 @@ enum cpuhp_state {
 	CPUHP_AP_X86_VDSO_VMA_ONLINE,
 	CPUHP_AP_IRQ_AFFINITY_ONLINE,
 	CPUHP_AP_ARM_MVEBU_SYNC_CLOCKS,
+	CPUHP_AP_X86_INTEL_EPB_ONLINE,
 	CPUHP_AP_PERF_ONLINE,
 	CPUHP_AP_PERF_X86_ONLINE,
 	CPUHP_AP_PERF_X86_UNCORE_ONLINE,
diff --git a/include/linux/cpuidle.h b/include/linux/cpuidle.h
index 3b39472324a3..bb9a0db89f1a 100644
--- a/include/linux/cpuidle.h
+++ b/include/linux/cpuidle.h
@@ -83,6 +83,7 @@ struct cpuidle_device {
 	unsigned int		use_deepest_state:1;
 	unsigned int		poll_time_limit:1;
 	unsigned int		cpu;
+	ktime_t			next_hrtimer;
 
 	int			last_residency;
 	struct cpuidle_state_usage	states_usage[CPUIDLE_STATE_MAX];
diff --git a/include/linux/device.h b/include/linux/device.h
index b425a7ee04ce..4e6987e11f68 100644
--- a/include/linux/device.h
+++ b/include/linux/device.h
@@ -49,8 +49,6 @@ struct bus_attribute {
 	ssize_t (*store)(struct bus_type *bus, const char *buf, size_t count);
 };
 
-#define BUS_ATTR(_name, _mode, _show, _store)	\
-	struct bus_attribute bus_attr_##_name = __ATTR(_name, _mode, _show, _store)
 #define BUS_ATTR_RW(_name) \
 	struct bus_attribute bus_attr_##_name = __ATTR_RW(_name)
 #define BUS_ATTR_RO(_name) \
diff --git a/include/linux/dmi.h b/include/linux/dmi.h
index c46fdb36700b..8de8c4f15163 100644
--- a/include/linux/dmi.h
+++ b/include/linux/dmi.h
@@ -102,9 +102,7 @@ const struct dmi_system_id *dmi_first_match(const struct dmi_system_id *list);
 extern const char * dmi_get_system_info(int field);
 extern const struct dmi_device * dmi_find_device(int type, const char *name,
 	const struct dmi_device *from);
-extern void dmi_scan_machine(void);
-extern void dmi_memdev_walk(void);
-extern void dmi_set_dump_stack_arch_desc(void);
+extern void dmi_setup(void);
 extern bool dmi_get_date(int field, int *yearp, int *monthp, int *dayp);
 extern int dmi_get_bios_year(void);
 extern int dmi_name_in_vendors(const char *str);
@@ -122,9 +120,7 @@ static inline int dmi_check_system(const struct dmi_system_id *list) { return 0;
 static inline const char * dmi_get_system_info(int field) { return NULL; }
 static inline const struct dmi_device * dmi_find_device(int type, const char *name,
 	const struct dmi_device *from) { return NULL; }
-static inline void dmi_scan_machine(void) { return; }
-static inline void dmi_memdev_walk(void) { }
-static inline void dmi_set_dump_stack_arch_desc(void) { }
+static inline void dmi_setup(void) { }
 static inline bool dmi_get_date(int field, int *yearp, int *monthp, int *dayp)
 {
 	if (yearp)
diff --git a/include/linux/efi.h b/include/linux/efi.h
index 54357a258b35..6ebc2098cfe1 100644
--- a/include/linux/efi.h
+++ b/include/linux/efi.h
@@ -1611,7 +1611,12 @@ efi_status_t efi_setup_gop(efi_system_table_t *sys_table_arg,
 			   struct screen_info *si, efi_guid_t *proto,
 			   unsigned long size);
 
-bool efi_runtime_disabled(void);
+#ifdef CONFIG_EFI
+extern bool efi_runtime_disabled(void);
+#else
+static inline bool efi_runtime_disabled(void) { return true; }
+#endif
+
 extern void efi_call_virt_check_flags(unsigned long flags, const char *call);
 extern unsigned long efi_call_virt_save_flags(void);
 
diff --git a/include/linux/elevator.h b/include/linux/elevator.h
index 2e9e2763bf47..6e8bc53740f0 100644
--- a/include/linux/elevator.h
+++ b/include/linux/elevator.h
@@ -31,6 +31,7 @@ struct elevator_mq_ops {
 	void (*exit_sched)(struct elevator_queue *);
 	int (*init_hctx)(struct blk_mq_hw_ctx *, unsigned int);
 	void (*exit_hctx)(struct blk_mq_hw_ctx *, unsigned int);
+	void (*depth_updated)(struct blk_mq_hw_ctx *);
 
 	bool (*allow_merge)(struct request_queue *, struct request *, struct bio *);
 	bool (*bio_merge)(struct blk_mq_hw_ctx *, struct bio *);
diff --git a/include/linux/etherdevice.h b/include/linux/etherdevice.h
index e2f3b21cd72a..aa8bfd6f738c 100644
--- a/include/linux/etherdevice.h
+++ b/include/linux/etherdevice.h
@@ -449,6 +449,18 @@ static inline void eth_addr_dec(u8 *addr)
 }
 
 /**
+ * eth_addr_inc() - Increment the given MAC address.
+ * @addr: Pointer to a six-byte array containing Ethernet address to increment.
+ */
+static inline void eth_addr_inc(u8 *addr)
+{
+	u64 u = ether_addr_to_u64(addr);
+
+	u++;
+	u64_to_ether_addr(u, addr);
+}
+
+/**
  * is_etherdev_addr - Tell if given Ethernet address belongs to the device.
  * @dev: Pointer to a device structure
  * @addr: Pointer to a six-byte array containing the Ethernet address
diff --git a/include/linux/filter.h b/include/linux/filter.h
index 6074aa064b54..7d3abde3f183 100644
--- a/include/linux/filter.h
+++ b/include/linux/filter.h
@@ -20,6 +20,7 @@
 #include <linux/set_memory.h>
 #include <linux/kallsyms.h>
 #include <linux/if_vlan.h>
+#include <linux/vmalloc.h>
 
 #include <net/sch_generic.h>
 
@@ -503,7 +504,6 @@ struct bpf_prog {
 	u16			pages;		/* Number of allocated pages */
 	u16			jited:1,	/* Is our filter JIT'ed? */
 				jit_requested:1,/* archs need to JIT the prog */
-				undo_set_mem:1,	/* Passed set_memory_ro() checkpoint */
 				gpl_compatible:1, /* Is filter GPL compatible? */
 				cb_access:1,	/* Is control block accessed? */
 				dst_needed:1,	/* Do we need dst entry? */
@@ -733,24 +733,15 @@ bpf_ctx_narrow_access_ok(u32 off, u32 size, u32 size_default)
 
 static inline void bpf_prog_lock_ro(struct bpf_prog *fp)
 {
-	fp->undo_set_mem = 1;
+	set_vm_flush_reset_perms(fp);
 	set_memory_ro((unsigned long)fp, fp->pages);
 }
 
-static inline void bpf_prog_unlock_ro(struct bpf_prog *fp)
-{
-	if (fp->undo_set_mem)
-		set_memory_rw((unsigned long)fp, fp->pages);
-}
-
 static inline void bpf_jit_binary_lock_ro(struct bpf_binary_header *hdr)
 {
+	set_vm_flush_reset_perms(hdr);
 	set_memory_ro((unsigned long)hdr, hdr->pages);
-}
-
-static inline void bpf_jit_binary_unlock_ro(struct bpf_binary_header *hdr)
-{
-	set_memory_rw((unsigned long)hdr, hdr->pages);
+	set_memory_x((unsigned long)hdr, hdr->pages);
 }
 
 static inline struct bpf_binary_header *
@@ -788,7 +779,6 @@ void __bpf_prog_free(struct bpf_prog *fp);
 
 static inline void bpf_prog_unlock_free(struct bpf_prog *fp)
 {
-	bpf_prog_unlock_ro(fp);
 	__bpf_prog_free(fp);
 }
 
diff --git a/include/linux/firmware/intel/stratix10-smc.h b/include/linux/firmware/intel/stratix10-smc.h
index 5be5dab50b13..01684d935580 100644
--- a/include/linux/firmware/intel/stratix10-smc.h
+++ b/include/linux/firmware/intel/stratix10-smc.h
@@ -309,4 +309,23 @@ INTEL_SIP_SMC_FAST_CALL_VAL(INTEL_SIP_SMC_FUNCID_FPGA_CONFIG_COMPLETED_WRITE)
 #define INTEL_SIP_SMC_FUNCID_RSU_UPDATE 12
 #define INTEL_SIP_SMC_RSU_UPDATE \
 	INTEL_SIP_SMC_FAST_CALL_VAL(INTEL_SIP_SMC_FUNCID_RSU_UPDATE)
+
+/*
+ * Request INTEL_SIP_SMC_ECC_DBE
+ *
+ * Sync call used by service driver at EL1 to alert EL3 that a Double
+ * Bit ECC error has occurred.
+ *
+ * Call register usage:
+ * a0 INTEL_SIP_SMC_ECC_DBE
+ * a1 SysManager Double Bit Error value
+ * a2-7 not used
+ *
+ * Return status
+ * a0 INTEL_SIP_SMC_STATUS_OK
+ */
+#define INTEL_SIP_SMC_FUNCID_ECC_DBE 13
+#define INTEL_SIP_SMC_ECC_DBE \
+	INTEL_SIP_SMC_FAST_CALL_VAL(INTEL_SIP_SMC_FUNCID_ECC_DBE)
+
 #endif
diff --git a/include/linux/fs.h b/include/linux/fs.h
index 8b42df09b04c..dd28e7679089 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -158,6 +158,9 @@ typedef int (dio_iodone_t)(struct kiocb *iocb, loff_t offset,
 #define FMODE_OPENED		((__force fmode_t)0x80000)
 #define FMODE_CREATED		((__force fmode_t)0x100000)
 
+/* File is stream-like */
+#define FMODE_STREAM		((__force fmode_t)0x200000)
+
 /* File was opened by fanotify and shouldn't generate fanotify events */
 #define FMODE_NONOTIFY		((__force fmode_t)0x4000000)
 
@@ -3074,6 +3077,7 @@ extern loff_t no_seek_end_llseek_size(struct file *, loff_t, int, loff_t);
 extern loff_t no_seek_end_llseek(struct file *, loff_t, int);
 extern int generic_file_open(struct inode * inode, struct file * filp);
 extern int nonseekable_open(struct inode * inode, struct file * filp);
+extern int stream_open(struct inode * inode, struct file * filp);
 
 #ifdef CONFIG_BLOCK
 typedef void (dio_submit_t)(struct bio *bio, struct inode *inode,
diff --git a/include/linux/ftrace.h b/include/linux/ftrace.h
index 730876187344..20899919ead8 100644
--- a/include/linux/ftrace.h
+++ b/include/linux/ftrace.h
@@ -241,21 +241,11 @@ static inline void ftrace_free_mem(struct module *mod, void *start, void *end) {
 
 #ifdef CONFIG_STACK_TRACER
 
-#define STACK_TRACE_ENTRIES 500
-
-struct stack_trace;
-
-extern unsigned stack_trace_index[];
-extern struct stack_trace stack_trace_max;
-extern unsigned long stack_trace_max_size;
-extern arch_spinlock_t stack_trace_max_lock;
-
 extern int stack_tracer_enabled;
-void stack_trace_print(void);
-int
-stack_trace_sysctl(struct ctl_table *table, int write,
-		   void __user *buffer, size_t *lenp,
-		   loff_t *ppos);
+
+int stack_trace_sysctl(struct ctl_table *table, int write,
+		       void __user *buffer, size_t *lenp,
+		       loff_t *ppos);
 
 /* DO NOT MODIFY THIS VARIABLE DIRECTLY! */
 DECLARE_PER_CPU(int, disable_stack_tracer);
diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h
index ea35263eb76b..11943b60f208 100644
--- a/include/linux/hugetlb.h
+++ b/include/linux/hugetlb.h
@@ -203,7 +203,6 @@ static inline void hugetlb_show_meminfo(void)
 #define pud_huge(x)	0
 #define is_hugepage_only_range(mm, addr, len)	0
 #define hugetlb_free_pgd_range(tlb, addr, end, floor, ceiling) ({BUG(); 0; })
-#define hugetlb_fault(mm, vma, addr, flags)	({ BUG(); 0; })
 #define hugetlb_mcopy_atomic_pte(dst_mm, dst_pte, dst_vma, dst_addr, \
 				src_addr, pagep)	({ BUG(); 0; })
 #define huge_pte_offset(mm, address, sz)	0
@@ -234,6 +233,13 @@ static inline void __unmap_hugepage_range(struct mmu_gather *tlb,
 {
 	BUG();
 }
+static inline vm_fault_t hugetlb_fault(struct mm_struct *mm,
+				struct vm_area_struct *vma, unsigned long address,
+				unsigned int flags)
+{
+	BUG();
+	return 0;
+}
 
 #endif /* !CONFIG_HUGETLB_PAGE */
 /*
diff --git a/include/linux/hwmon.h b/include/linux/hwmon.h
index 99e0c1b0b5fb..2b949fa501e1 100644
--- a/include/linux/hwmon.h
+++ b/include/linux/hwmon.h
@@ -40,6 +40,11 @@ enum hwmon_chip_attributes {
 	hwmon_chip_register_tz,
 	hwmon_chip_update_interval,
 	hwmon_chip_alarms,
+	hwmon_chip_samples,
+	hwmon_chip_curr_samples,
+	hwmon_chip_in_samples,
+	hwmon_chip_power_samples,
+	hwmon_chip_temp_samples,
 };
 
 #define HWMON_C_TEMP_RESET_HISTORY	BIT(hwmon_chip_temp_reset_history)
@@ -49,6 +54,11 @@ enum hwmon_chip_attributes {
 #define HWMON_C_REGISTER_TZ		BIT(hwmon_chip_register_tz)
 #define HWMON_C_UPDATE_INTERVAL		BIT(hwmon_chip_update_interval)
 #define HWMON_C_ALARMS			BIT(hwmon_chip_alarms)
+#define HWMON_C_SAMPLES			BIT(hwmon_chip_samples)
+#define HWMON_C_CURR_SAMPLES		BIT(hwmon_chip_curr_samples)
+#define HWMON_C_IN_SAMPLES		BIT(hwmon_chip_in_samples)
+#define HWMON_C_POWER_SAMPLES		BIT(hwmon_chip_power_samples)
+#define HWMON_C_TEMP_SAMPLES		BIT(hwmon_chip_temp_samples)
 
 enum hwmon_temp_attributes {
 	hwmon_temp_input = 0,
@@ -365,6 +375,14 @@ struct hwmon_channel_info {
 	const u32 *config;
 };
 
+#define HWMON_CHANNEL_INFO(stype, ...)	\
+	(&(struct hwmon_channel_info) {	\
+		.type = hwmon_##stype,	\
+		.config = (u32 []) {	\
+			__VA_ARGS__, 0	\
+		}			\
+	})
+
 /**
  * Chip configuration
  * @ops:	Pointer to hwmon operations.
diff --git a/include/linux/ima.h b/include/linux/ima.h
index dc12fbcf484c..fd9f7cf4cdf5 100644
--- a/include/linux/ima.h
+++ b/include/linux/ima.h
@@ -31,7 +31,7 @@ extern void ima_post_path_mknod(struct dentry *dentry);
 extern void ima_add_kexec_buffer(struct kimage *image);
 #endif
 
-#if defined(CONFIG_X86) && defined(CONFIG_EFI)
+#if (defined(CONFIG_X86) && defined(CONFIG_EFI)) || defined(CONFIG_S390)
 extern bool arch_ima_get_secureboot(void);
 extern const char * const *arch_get_ima_policy(void);
 #else
diff --git a/include/linux/interrupt.h b/include/linux/interrupt.h
index 690b238a44d5..c7eef32e7739 100644
--- a/include/linux/interrupt.h
+++ b/include/linux/interrupt.h
@@ -668,31 +668,6 @@ extern void tasklet_kill_immediate(struct tasklet_struct *t, unsigned int cpu);
 extern void tasklet_init(struct tasklet_struct *t,
 			 void (*func)(unsigned long), unsigned long data);
 
-struct tasklet_hrtimer {
-	struct hrtimer		timer;
-	struct tasklet_struct	tasklet;
-	enum hrtimer_restart	(*function)(struct hrtimer *);
-};
-
-extern void
-tasklet_hrtimer_init(struct tasklet_hrtimer *ttimer,
-		     enum hrtimer_restart (*function)(struct hrtimer *),
-		     clockid_t which_clock, enum hrtimer_mode mode);
-
-static inline
-void tasklet_hrtimer_start(struct tasklet_hrtimer *ttimer, ktime_t time,
-			   const enum hrtimer_mode mode)
-{
-	hrtimer_start(&ttimer->timer, time, mode);
-}
-
-static inline
-void tasklet_hrtimer_cancel(struct tasklet_hrtimer *ttimer)
-{
-	hrtimer_cancel(&ttimer->timer);
-	tasklet_kill(&ttimer->tasklet);
-}
-
 /*
  * Autoprobing for irqs:
  *
diff --git a/include/linux/jbd2.h b/include/linux/jbd2.h
index 0f919d5fe84f..c2ffff5f9ae2 100644
--- a/include/linux/jbd2.h
+++ b/include/linux/jbd2.h
@@ -1606,7 +1606,6 @@ static inline u32 jbd2_chksum(journal_t *journal, u32 crc,
 		JBD_MAX_CHECKSUM_SIZE);
 
 	desc.shash.tfm = journal->j_chksum_driver;
-	desc.shash.flags = 0;
 	*(u32 *)desc.ctx = crc;
 
 	err = crypto_shash_update(&desc.shash, address, length);
diff --git a/include/linux/jump_label_ratelimit.h b/include/linux/jump_label_ratelimit.h
index a49f2b45b3f0..42710d5949ba 100644
--- a/include/linux/jump_label_ratelimit.h
+++ b/include/linux/jump_label_ratelimit.h
@@ -12,21 +12,79 @@ struct static_key_deferred {
 	struct delayed_work work;
 };
 
-extern void static_key_slow_dec_deferred(struct static_key_deferred *key);
-extern void static_key_deferred_flush(struct static_key_deferred *key);
+struct static_key_true_deferred {
+	struct static_key_true key;
+	unsigned long timeout;
+	struct delayed_work work;
+};
+
+struct static_key_false_deferred {
+	struct static_key_false key;
+	unsigned long timeout;
+	struct delayed_work work;
+};
+
+#define static_key_slow_dec_deferred(x)					\
+	__static_key_slow_dec_deferred(&(x)->key, &(x)->work, (x)->timeout)
+#define static_branch_slow_dec_deferred(x)				\
+	__static_key_slow_dec_deferred(&(x)->key.key, &(x)->work, (x)->timeout)
+
+#define static_key_deferred_flush(x)					\
+	__static_key_deferred_flush((x), &(x)->work)
+
+extern void
+__static_key_slow_dec_deferred(struct static_key *key,
+			       struct delayed_work *work,
+			       unsigned long timeout);
+extern void __static_key_deferred_flush(void *key, struct delayed_work *work);
 extern void
 jump_label_rate_limit(struct static_key_deferred *key, unsigned long rl);
 
+extern void jump_label_update_timeout(struct work_struct *work);
+
+#define DEFINE_STATIC_KEY_DEFERRED_TRUE(name, rl)			\
+	struct static_key_true_deferred name = {			\
+		.key =		{ STATIC_KEY_INIT_TRUE },		\
+		.timeout =	(rl),					\
+		.work =	__DELAYED_WORK_INITIALIZER((name).work,		\
+						   jump_label_update_timeout, \
+						   0),			\
+	}
+
+#define DEFINE_STATIC_KEY_DEFERRED_FALSE(name, rl)			\
+	struct static_key_false_deferred name = {			\
+		.key =		{ STATIC_KEY_INIT_FALSE },		\
+		.timeout =	(rl),					\
+		.work =	__DELAYED_WORK_INITIALIZER((name).work,		\
+						   jump_label_update_timeout, \
+						   0),			\
+	}
+
+#define static_branch_deferred_inc(x)	static_branch_inc(&(x)->key)
+
 #else	/* !CONFIG_JUMP_LABEL */
 struct static_key_deferred {
 	struct static_key  key;
 };
+struct static_key_true_deferred {
+	struct static_key_true key;
+};
+struct static_key_false_deferred {
+	struct static_key_false key;
+};
+#define DEFINE_STATIC_KEY_DEFERRED_TRUE(name, rl)	\
+	struct static_key_true_deferred name = { STATIC_KEY_TRUE_INIT }
+#define DEFINE_STATIC_KEY_DEFERRED_FALSE(name, rl)	\
+	struct static_key_false_deferred name = { STATIC_KEY_FALSE_INIT }
+
+#define static_branch_slow_dec_deferred(x)	static_branch_dec(&(x)->key)
+
 static inline void static_key_slow_dec_deferred(struct static_key_deferred *key)
 {
 	STATIC_KEY_CHECK_USE(key);
 	static_key_slow_dec(&key->key);
 }
-static inline void static_key_deferred_flush(struct static_key_deferred *key)
+static inline void static_key_deferred_flush(void *key)
 {
 	STATIC_KEY_CHECK_USE(key);
 }
diff --git a/include/linux/kcore.h b/include/linux/kcore.h
index c843f4a9c512..da676cdbd727 100644
--- a/include/linux/kcore.h
+++ b/include/linux/kcore.h
@@ -38,12 +38,6 @@ struct vmcoredd_node {
 
 #ifdef CONFIG_PROC_KCORE
 void __init kclist_add(struct kcore_list *, void *, size_t, int type);
-static inline
-void kclist_add_remap(struct kcore_list *m, void *addr, void *vaddr, size_t sz)
-{
-	m->vaddr = (unsigned long)vaddr;
-	kclist_add(m, addr, sz, KCORE_REMAP);
-}
 
 extern int __init register_mem_pfn_is_ram(int (*fn)(unsigned long pfn));
 #else
@@ -51,11 +45,6 @@ static inline
 void kclist_add(struct kcore_list *new, void *addr, size_t size, int type)
 {
 }
-
-static inline
-void kclist_add_remap(struct kcore_list *m, void *addr, void *vaddr, size_t sz)
-{
-}
 #endif
 
 #endif /* _LINUX_KCORE_H */
diff --git a/include/linux/kernel.h b/include/linux/kernel.h
index 34a5036debd3..2d14e21c16c0 100644
--- a/include/linux/kernel.h
+++ b/include/linux/kernel.h
@@ -47,8 +47,8 @@
 
 #define u64_to_user_ptr(x) (		\
 {					\
-	typecheck(u64, x);		\
-	(void __user *)(uintptr_t)x;	\
+	typecheck(u64, (x));		\
+	(void __user *)(uintptr_t)(x);	\
 }					\
 )
 
diff --git a/include/linux/kprobes.h b/include/linux/kprobes.h
index 201f0f2683f2..9a897256e481 100644
--- a/include/linux/kprobes.h
+++ b/include/linux/kprobes.h
@@ -173,6 +173,7 @@ struct kretprobe_instance {
 	struct kretprobe *rp;
 	kprobe_opcode_t *ret_addr;
 	struct task_struct *task;
+	void *fp;
 	char data[0];
 };
 
diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h
index 9d55c63db09b..640a03642766 100644
--- a/include/linux/kvm_host.h
+++ b/include/linux/kvm_host.h
@@ -28,6 +28,7 @@
 #include <linux/irqbypass.h>
 #include <linux/swait.h>
 #include <linux/refcount.h>
+#include <linux/nospec.h>
 #include <asm/signal.h>
 
 #include <linux/kvm.h>
@@ -513,10 +514,10 @@ static inline struct kvm_io_bus *kvm_get_bus(struct kvm *kvm, enum kvm_bus idx)
 
 static inline struct kvm_vcpu *kvm_get_vcpu(struct kvm *kvm, int i)
 {
-	/* Pairs with smp_wmb() in kvm_vm_ioctl_create_vcpu, in case
-	 * the caller has read kvm->online_vcpus before (as is the case
-	 * for kvm_for_each_vcpu, for example).
-	 */
+	int num_vcpus = atomic_read(&kvm->online_vcpus);
+	i = array_index_nospec(i, num_vcpus);
+
+	/* Pairs with smp_wmb() in kvm_vm_ioctl_create_vcpu.  */
 	smp_rmb();
 	return kvm->vcpus[i];
 }
@@ -600,6 +601,7 @@ void kvm_put_kvm(struct kvm *kvm);
 
 static inline struct kvm_memslots *__kvm_memslots(struct kvm *kvm, int as_id)
 {
+	as_id = array_index_nospec(as_id, KVM_ADDRESS_SPACE_NUM);
 	return srcu_dereference_check(kvm->memslots[as_id], &kvm->srcu,
 			lockdep_is_held(&kvm->slots_lock) ||
 			!refcount_read(&kvm->users_count));
diff --git a/include/linux/list.h b/include/linux/list.h
index 79626b5ab36c..58aa3adf94e6 100644
--- a/include/linux/list.h
+++ b/include/linux/list.h
@@ -207,7 +207,7 @@ static inline void list_bulk_move_tail(struct list_head *head,
 }
 
 /**
- * list_is_first -- tests whether @ list is the first entry in list @head
+ * list_is_first -- tests whether @list is the first entry in list @head
  * @list: the entry to test
  * @head: the head of the list
  */
diff --git a/include/linux/lockdep.h b/include/linux/lockdep.h
index 79c3873d58ac..6e2377e6c1d6 100644
--- a/include/linux/lockdep.h
+++ b/include/linux/lockdep.h
@@ -66,6 +66,11 @@ struct lock_class_key {
 
 extern struct lock_class_key __lockdep_no_validate__;
 
+struct lock_trace {
+	unsigned int		nr_entries;
+	unsigned int		offset;
+};
+
 #define LOCKSTAT_POINTS		4
 
 /*
@@ -100,7 +105,7 @@ struct lock_class {
 	 * IRQ/softirq usage tracking bits:
 	 */
 	unsigned long			usage_mask;
-	struct stack_trace		usage_traces[XXX_LOCK_USAGE_STATES];
+	struct lock_trace		usage_traces[XXX_LOCK_USAGE_STATES];
 
 	/*
 	 * Generation counter, when doing certain classes of graph walking,
@@ -188,7 +193,7 @@ struct lock_list {
 	struct list_head		entry;
 	struct lock_class		*class;
 	struct lock_class		*links_to;
-	struct stack_trace		trace;
+	struct lock_trace		trace;
 	int				distance;
 
 	/*
@@ -471,7 +476,7 @@ struct pin_cookie { };
 
 #define NIL_COOKIE (struct pin_cookie){ }
 
-#define lockdep_pin_lock(l)			({ struct pin_cookie cookie; cookie; })
+#define lockdep_pin_lock(l)			({ struct pin_cookie cookie = { }; cookie; })
 #define lockdep_repin_lock(l, c)		do { (void)(l); (void)(c); } while (0)
 #define lockdep_unpin_lock(l, c)		do { (void)(l); (void)(c); } while (0)
 
diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h
index 1f3d880b7ca1..dbb6118370c1 100644
--- a/include/linux/memcontrol.h
+++ b/include/linux/memcontrol.h
@@ -566,7 +566,10 @@ struct mem_cgroup *lock_page_memcg(struct page *page);
 void __unlock_page_memcg(struct mem_cgroup *memcg);
 void unlock_page_memcg(struct page *page);
 
-/* idx can be of type enum memcg_stat_item or node_stat_item */
+/*
+ * idx can be of type enum memcg_stat_item or node_stat_item.
+ * Keep in sync with memcg_exact_page_state().
+ */
 static inline unsigned long memcg_page_state(struct mem_cgroup *memcg,
 					     int idx)
 {
diff --git a/include/linux/mfd/palmas.h b/include/linux/mfd/palmas.h
index 75e5c8ff85fc..c34d5f0d34d7 100644
--- a/include/linux/mfd/palmas.h
+++ b/include/linux/mfd/palmas.h
@@ -553,7 +553,6 @@ struct palmas_pmic {
 	struct palmas *palmas;
 	struct device *dev;
 	struct regulator_desc desc[PALMAS_NUM_REGS];
-	struct regulator_dev *rdev[PALMAS_NUM_REGS];
 	struct mutex mutex;
 
 	int smps123;
diff --git a/include/linux/mfd/wm831x/regulator.h b/include/linux/mfd/wm831x/regulator.h
index 955d30fc6a27..30c587a0624c 100644
--- a/include/linux/mfd/wm831x/regulator.h
+++ b/include/linux/mfd/wm831x/regulator.h
@@ -1213,6 +1213,6 @@
 #define WM831X_LDO1_OK_WIDTH                         1  /* LDO1_OK */
 
 #define WM831X_ISINK_MAX_ISEL 55
-extern int wm831x_isinkv_values[WM831X_ISINK_MAX_ISEL + 1];
+extern const unsigned int wm831x_isinkv_values[WM831X_ISINK_MAX_ISEL + 1];
 
 #endif
diff --git a/include/linux/mfd/wm8400-private.h b/include/linux/mfd/wm8400-private.h
index 4ee908f5b834..43d0d307e2e3 100644
--- a/include/linux/mfd/wm8400-private.h
+++ b/include/linux/mfd/wm8400-private.h
@@ -923,12 +923,4 @@ struct wm8400 {
 #define WM8400_LINE_CMP_VTHD_SHIFT                   0  /* LINE_CMP_VTHD - [3:0] */
 #define WM8400_LINE_CMP_VTHD_WIDTH                   4  /* LINE_CMP_VTHD - [3:0] */
 
-int wm8400_block_read(struct wm8400 *wm8400, u8 reg, int count, u16 *data);
-
-static inline int wm8400_set_bits(struct wm8400 *wm8400, u8 reg,
-				  u16 mask, u16 val)
-{
-	return regmap_update_bits(wm8400->regmap, reg, mask, val);
-}
-
 #endif
diff --git a/include/linux/mii.h b/include/linux/mii.h
index 6fee8b1a4400..5cd824c1c0ca 100644
--- a/include/linux/mii.h
+++ b/include/linux/mii.h
@@ -469,7 +469,7 @@ static inline u32 linkmode_adv_to_lcl_adv_t(unsigned long *advertising)
 	if (linkmode_test_bit(ETHTOOL_LINK_MODE_Pause_BIT,
 			      advertising))
 		lcl_adv |= ADVERTISE_PAUSE_CAP;
-	if (linkmode_test_bit(ETHTOOL_LINK_MODE_Pause_BIT,
+	if (linkmode_test_bit(ETHTOOL_LINK_MODE_Asym_Pause_BIT,
 			      advertising))
 		lcl_adv |= ADVERTISE_PAUSE_ASYM;
 
diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h
index 022541dc5dbf..0d0729648844 100644
--- a/include/linux/mlx5/driver.h
+++ b/include/linux/mlx5/driver.h
@@ -594,6 +594,8 @@ enum mlx5_pagefault_type_flags {
 };
 
 struct mlx5_td {
+	/* protects tirs list changes while tirs refresh */
+	struct mutex     list_lock;
 	struct list_head tirs_list;
 	u32              tdn;
 };
diff --git a/include/linux/mm.h b/include/linux/mm.h
index 76769749b5a5..083d7b4863ed 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -966,6 +966,10 @@ static inline bool is_pci_p2pdma_page(const struct page *page)
 }
 #endif /* CONFIG_DEV_PAGEMAP_OPS */
 
+/* 127: arbitrary random number, small enough to assemble well */
+#define page_ref_zero_or_close_to_overflow(page) \
+	((unsigned int) page_ref_count(page) + 127u <= 127u)
+
 static inline void get_page(struct page *page)
 {
 	page = compound_head(page);
@@ -973,10 +977,19 @@ static inline void get_page(struct page *page)
 	 * Getting a normal page or the head of a compound page
 	 * requires to already have an elevated page->_refcount.
 	 */
-	VM_BUG_ON_PAGE(page_ref_count(page) <= 0, page);
+	VM_BUG_ON_PAGE(page_ref_zero_or_close_to_overflow(page), page);
 	page_ref_inc(page);
 }
 
+static inline __must_check bool try_get_page(struct page *page)
+{
+	page = compound_head(page);
+	if (WARN_ON_ONCE(page_ref_count(page) <= 0))
+		return false;
+	page_ref_inc(page);
+	return true;
+}
+
 static inline void put_page(struct page *page)
 {
 	page = compound_head(page);
@@ -2597,37 +2610,31 @@ static inline void kernel_poison_pages(struct page *page, int numpages,
 					int enable) { }
 #endif
 
-#ifdef CONFIG_DEBUG_PAGEALLOC
 extern bool _debug_pagealloc_enabled;
-extern void __kernel_map_pages(struct page *page, int numpages, int enable);
 
 static inline bool debug_pagealloc_enabled(void)
 {
-	return _debug_pagealloc_enabled;
+	return IS_ENABLED(CONFIG_DEBUG_PAGEALLOC) && _debug_pagealloc_enabled;
 }
 
+#if defined(CONFIG_DEBUG_PAGEALLOC) || defined(CONFIG_ARCH_HAS_SET_DIRECT_MAP)
+extern void __kernel_map_pages(struct page *page, int numpages, int enable);
+
 static inline void
 kernel_map_pages(struct page *page, int numpages, int enable)
 {
-	if (!debug_pagealloc_enabled())
-		return;
-
 	__kernel_map_pages(page, numpages, enable);
 }
 #ifdef CONFIG_HIBERNATION
 extern bool kernel_page_present(struct page *page);
 #endif	/* CONFIG_HIBERNATION */
-#else	/* CONFIG_DEBUG_PAGEALLOC */
+#else	/* CONFIG_DEBUG_PAGEALLOC || CONFIG_ARCH_HAS_SET_DIRECT_MAP */
 static inline void
 kernel_map_pages(struct page *page, int numpages, int enable) {}
 #ifdef CONFIG_HIBERNATION
 static inline bool kernel_page_present(struct page *page) { return true; }
 #endif	/* CONFIG_HIBERNATION */
-static inline bool debug_pagealloc_enabled(void)
-{
-	return false;
-}
-#endif	/* CONFIG_DEBUG_PAGEALLOC */
+#endif	/* CONFIG_DEBUG_PAGEALLOC || CONFIG_ARCH_HAS_SET_DIRECT_MAP */
 
 #ifdef __HAVE_ARCH_GATE_AREA
 extern struct vm_area_struct *get_gate_vma(struct mm_struct *mm);
diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h
index 7eade9132f02..4ef4bbe78a1d 100644
--- a/include/linux/mm_types.h
+++ b/include/linux/mm_types.h
@@ -671,7 +671,7 @@ enum vm_fault_reason {
 
 /* Encode hstate index for a hwpoisoned large page */
 #define VM_FAULT_SET_HINDEX(x) ((__force vm_fault_t)((x) << 16))
-#define VM_FAULT_GET_HINDEX(x) (((x) >> 16) & 0xf)
+#define VM_FAULT_GET_HINDEX(x) (((__force unsigned int)(x) >> 16) & 0xf)
 
 #define VM_FAULT_ERROR (VM_FAULT_OOM | VM_FAULT_SIGBUS |	\
 			VM_FAULT_SIGSEGV | VM_FAULT_HWPOISON |	\
diff --git a/include/linux/net.h b/include/linux/net.h
index 651fca72286c..c606c72311d0 100644
--- a/include/linux/net.h
+++ b/include/linux/net.h
@@ -83,6 +83,12 @@ enum sock_type {
 
 #endif /* ARCH_HAS_SOCKET_TYPES */
 
+/**
+ * enum sock_shutdown_cmd - Shutdown types
+ * @SHUT_RD: shutdown receptions
+ * @SHUT_WR: shutdown transmissions
+ * @SHUT_RDWR: shutdown receptions/transmissions
+ */
 enum sock_shutdown_cmd {
 	SHUT_RD,
 	SHUT_WR,
diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index 26f69cf763f4..324e872c91d1 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -1500,6 +1500,7 @@ struct net_device_ops {
  * @IFF_FAILOVER: device is a failover master device
  * @IFF_FAILOVER_SLAVE: device is lower dev of a failover master device
  * @IFF_L3MDEV_RX_HANDLER: only invoke the rx handler of L3 master device
+ * @IFF_LIVE_RENAME_OK: rename is allowed while device is up and running
  */
 enum netdev_priv_flags {
 	IFF_802_1Q_VLAN			= 1<<0,
@@ -1532,6 +1533,7 @@ enum netdev_priv_flags {
 	IFF_FAILOVER			= 1<<27,
 	IFF_FAILOVER_SLAVE		= 1<<28,
 	IFF_L3MDEV_RX_HANDLER		= 1<<29,
+	IFF_LIVE_RENAME_OK		= 1<<30,
 };
 
 #define IFF_802_1Q_VLAN			IFF_802_1Q_VLAN
@@ -1563,6 +1565,7 @@ enum netdev_priv_flags {
 #define IFF_FAILOVER			IFF_FAILOVER
 #define IFF_FAILOVER_SLAVE		IFF_FAILOVER_SLAVE
 #define IFF_L3MDEV_RX_HANDLER		IFF_L3MDEV_RX_HANDLER
+#define IFF_LIVE_RENAME_OK		IFF_LIVE_RENAME_OK
 
 /**
  *	struct net_device - The DEVICE structure.
diff --git a/include/linux/nvme.h b/include/linux/nvme.h
index baa49e6a23cc..c40720cb59ac 100644
--- a/include/linux/nvme.h
+++ b/include/linux/nvme.h
@@ -967,8 +967,13 @@ struct nvme_get_log_page_command {
 	__le16			numdl;
 	__le16			numdu;
 	__u16			rsvd11;
-	__le32			lpol;
-	__le32			lpou;
+	union {
+		struct {
+			__le32 lpol;
+			__le32 lpou;
+		};
+		__le64 lpo;
+	};
 	__u32			rsvd14[2];
 };
 
diff --git a/include/linux/oid_registry.h b/include/linux/oid_registry.h
index d2fa9ca42e9a..7f30446348c4 100644
--- a/include/linux/oid_registry.h
+++ b/include/linux/oid_registry.h
@@ -93,6 +93,24 @@ enum OID {
 	OID_authorityKeyIdentifier,	/* 2.5.29.35 */
 	OID_extKeyUsage,		/* 2.5.29.37 */
 
+	/* EC-RDSA */
+	OID_gostCPSignA,		/* 1.2.643.2.2.35.1 */
+	OID_gostCPSignB,		/* 1.2.643.2.2.35.2 */
+	OID_gostCPSignC,		/* 1.2.643.2.2.35.3 */
+	OID_gost2012PKey256,		/* 1.2.643.7.1.1.1.1 */
+	OID_gost2012PKey512,		/* 1.2.643.7.1.1.1.2 */
+	OID_gost2012Digest256,		/* 1.2.643.7.1.1.2.2 */
+	OID_gost2012Digest512,		/* 1.2.643.7.1.1.2.3 */
+	OID_gost2012Signature256,	/* 1.2.643.7.1.1.3.2 */
+	OID_gost2012Signature512,	/* 1.2.643.7.1.1.3.3 */
+	OID_gostTC26Sign256A,		/* 1.2.643.7.1.2.1.1.1 */
+	OID_gostTC26Sign256B,		/* 1.2.643.7.1.2.1.1.2 */
+	OID_gostTC26Sign256C,		/* 1.2.643.7.1.2.1.1.3 */
+	OID_gostTC26Sign256D,		/* 1.2.643.7.1.2.1.1.4 */
+	OID_gostTC26Sign512A,		/* 1.2.643.7.1.2.1.2.1 */
+	OID_gostTC26Sign512B,		/* 1.2.643.7.1.2.1.2.2 */
+	OID_gostTC26Sign512C,		/* 1.2.643.7.1.2.1.2.3 */
+
 	OID__NR
 };
 
diff --git a/include/linux/page-isolation.h b/include/linux/page-isolation.h
index 4eb26d278046..280ae96dc4c3 100644
--- a/include/linux/page-isolation.h
+++ b/include/linux/page-isolation.h
@@ -41,16 +41,6 @@ int move_freepages_block(struct zone *zone, struct page *page,
 
 /*
  * Changes migrate type in [start_pfn, end_pfn) to be MIGRATE_ISOLATE.
- * If specified range includes migrate types other than MOVABLE or CMA,
- * this will fail with -EBUSY.
- *
- * For isolating all pages in the range finally, the caller have to
- * free all pages in the range. test_page_isolated() can be used for
- * test it.
- *
- * The following flags are allowed (they can be combined in a bit mask)
- * SKIP_HWPOISON - ignore hwpoison pages
- * REPORT_FAILURE - report details about the failure to isolate the range
  */
 int
 start_isolate_page_range(unsigned long start_pfn, unsigned long end_pfn,
diff --git a/include/linux/parport.h b/include/linux/parport.h
index f41f1d041e2c..397607a0c0eb 100644
--- a/include/linux/parport.h
+++ b/include/linux/parport.h
@@ -460,7 +460,6 @@ extern size_t parport_ieee1284_epp_read_addr (struct parport *,
 					      void *, size_t, int);
 
 /* IEEE1284.3 functions */
-#define daisy_dev_name "Device ID probe"
 extern int parport_daisy_init (struct parport *port);
 extern void parport_daisy_fini (struct parport *port);
 extern struct pardevice *parport_open (int devnum, const char *name);
@@ -469,18 +468,6 @@ extern ssize_t parport_device_id (int devnum, char *buffer, size_t len);
 extern void parport_daisy_deselect_all (struct parport *port);
 extern int parport_daisy_select (struct parport *port, int daisy, int mode);
 
-#ifdef CONFIG_PARPORT_1284
-extern int daisy_drv_init(void);
-extern void daisy_drv_exit(void);
-#else
-static inline int daisy_drv_init(void)
-{
-	return 0;
-}
-
-static inline void daisy_drv_exit(void) {}
-#endif
-
 /* Lowlevel drivers _can_ call this support function to handle irqs.  */
 static inline void parport_generic_irq(struct parport *port)
 {
diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h
index e47ef764f613..15a82ff0aefe 100644
--- a/include/linux/perf_event.h
+++ b/include/linux/perf_event.h
@@ -240,7 +240,6 @@ struct perf_event;
 #define PERF_PMU_CAP_NO_INTERRUPT		0x01
 #define PERF_PMU_CAP_NO_NMI			0x02
 #define PERF_PMU_CAP_AUX_NO_SG			0x04
-#define PERF_PMU_CAP_AUX_SW_DOUBLEBUF		0x08
 #define PERF_PMU_CAP_EXCLUSIVE			0x10
 #define PERF_PMU_CAP_ITRACE			0x20
 #define PERF_PMU_CAP_HETEROGENEOUS_CPUS		0x40
@@ -464,7 +463,7 @@ enum perf_addr_filter_action_t {
 /**
  * struct perf_addr_filter - address range filter definition
  * @entry:	event's filter list linkage
- * @inode:	object file's inode for file-based filters
+ * @path:	object file's path for file-based filters
  * @offset:	filter range offset
  * @size:	filter range size (size==0 means single address trigger)
  * @action:	filter/start/stop
@@ -888,6 +887,9 @@ extern void perf_sched_cb_dec(struct pmu *pmu);
 extern void perf_sched_cb_inc(struct pmu *pmu);
 extern int perf_event_task_disable(void);
 extern int perf_event_task_enable(void);
+
+extern void perf_pmu_resched(struct pmu *pmu);
+
 extern int perf_event_refresh(struct perf_event *event, int refresh);
 extern void perf_event_update_userpage(struct perf_event *event);
 extern int perf_event_release_kernel(struct perf_event *event);
@@ -1055,12 +1057,18 @@ static inline void perf_arch_fetch_caller_regs(struct pt_regs *regs, unsigned lo
 #endif
 
 /*
- * Take a snapshot of the regs. Skip ip and frame pointer to
- * the nth caller. We only need a few of the regs:
+ * When generating a perf sample in-line, instead of from an interrupt /
+ * exception, we lack a pt_regs. This is typically used from software events
+ * like: SW_CONTEXT_SWITCHES, SW_MIGRATIONS and the tie-in with tracepoints.
+ *
+ * We typically don't need a full set, but (for x86) do require:
  * - ip for PERF_SAMPLE_IP
  * - cs for user_mode() tests
- * - bp for callchains
- * - eflags, for future purposes, just in case
+ * - sp for PERF_SAMPLE_CALLCHAIN
+ * - eflags for MISC bits and CALLCHAIN (see: perf_hw_regs())
+ *
+ * NOTE: assumes @regs is otherwise already 0 filled; this is important for
+ * things like PERF_SAMPLE_REGS_INTR.
  */
 static inline void perf_fetch_caller_regs(struct pt_regs *regs)
 {
diff --git a/include/linux/pipe_fs_i.h b/include/linux/pipe_fs_i.h
index 787d224ff43e..5c626fdc10db 100644
--- a/include/linux/pipe_fs_i.h
+++ b/include/linux/pipe_fs_i.h
@@ -101,18 +101,20 @@ struct pipe_buf_operations {
 	/*
 	 * Get a reference to the pipe buffer.
 	 */
-	void (*get)(struct pipe_inode_info *, struct pipe_buffer *);
+	bool (*get)(struct pipe_inode_info *, struct pipe_buffer *);
 };
 
 /**
  * pipe_buf_get - get a reference to a pipe_buffer
  * @pipe:	the pipe that the buffer belongs to
  * @buf:	the buffer to get a reference to
+ *
+ * Return: %true if the reference was successfully obtained.
  */
-static inline void pipe_buf_get(struct pipe_inode_info *pipe,
+static inline __must_check bool pipe_buf_get(struct pipe_inode_info *pipe,
 				struct pipe_buffer *buf)
 {
-	buf->ops->get(pipe, buf);
+	return buf->ops->get(pipe, buf);
 }
 
 /**
@@ -171,9 +173,10 @@ struct pipe_inode_info *alloc_pipe_info(void);
 void free_pipe_info(struct pipe_inode_info *);
 
 /* Generic pipe buffer ops functions */
-void generic_pipe_buf_get(struct pipe_inode_info *, struct pipe_buffer *);
+bool generic_pipe_buf_get(struct pipe_inode_info *, struct pipe_buffer *);
 int generic_pipe_buf_confirm(struct pipe_inode_info *, struct pipe_buffer *);
 int generic_pipe_buf_steal(struct pipe_inode_info *, struct pipe_buffer *);
+int generic_pipe_buf_nosteal(struct pipe_inode_info *, struct pipe_buffer *);
 void generic_pipe_buf_release(struct pipe_inode_info *, struct pipe_buffer *);
 void pipe_buf_mark_unmergeable(struct pipe_buffer *buf);
 
diff --git a/include/linux/platform_data/ads7828.h b/include/linux/platform_data/ads7828.h
index 3245f45f9d77..a3370a007702 100644
--- a/include/linux/platform_data/ads7828.h
+++ b/include/linux/platform_data/ads7828.h
@@ -4,7 +4,7 @@
  * Copyright (c) 2012 Savoir-faire Linux Inc.
  *          Vivien Didelot <vivien.didelot@savoirfairelinux.com>
  *
- * For further information, see the Documentation/hwmon/ads7828 file.
+ * For further information, see the Documentation/hwmon/ads7828.rst file.
  *
  * This program is free software; you can redistribute it and/or modify
  * it under the terms of the GNU General Public License version 2 as
diff --git a/include/linux/platform_data/ds620.h b/include/linux/platform_data/ds620.h
index 6ef58bb77e46..f0ce22a78bb8 100644
--- a/include/linux/platform_data/ds620.h
+++ b/include/linux/platform_data/ds620.h
@@ -14,7 +14,7 @@ struct ds620_platform_data {
 	 *  1 = PO_LOW
 	 *  2 = PO_HIGH
 	 *
-	 * (see Documentation/hwmon/ds620)
+	 * (see Documentation/hwmon/ds620.rst)
 	 */
 	int pomode;
 };
diff --git a/include/linux/platform_data/gpio/gpio-amd-fch.h b/include/linux/platform_data/gpio/gpio-amd-fch.h
index a867637e172d..9e46678edb2a 100644
--- a/include/linux/platform_data/gpio/gpio-amd-fch.h
+++ b/include/linux/platform_data/gpio/gpio-amd-fch.h
@@ -1,4 +1,4 @@
-/* SPDX-License-Identifier: GPL+ */
+/* SPDX-License-Identifier: GPL-2.0+ */
 
 /*
  * AMD FCH gpio driver platform-data
diff --git a/include/linux/platform_data/ina2xx.h b/include/linux/platform_data/ina2xx.h
index 9f0aa1b48c78..dde59fd3590f 100644
--- a/include/linux/platform_data/ina2xx.h
+++ b/include/linux/platform_data/ina2xx.h
@@ -7,7 +7,7 @@
  * it under the terms of the GNU General Public License version 2 as
  * published by the Free Software Foundation.
  *
- * For further information, see the Documentation/hwmon/ina2xx file.
+ * For further information, see the Documentation/hwmon/ina2xx.rst file.
  */
 
 /**
diff --git a/include/linux/platform_data/max197.h b/include/linux/platform_data/max197.h
index 8da8f94ee15c..2bbd0919bc89 100644
--- a/include/linux/platform_data/max197.h
+++ b/include/linux/platform_data/max197.h
@@ -8,7 +8,7 @@
  * it under the terms of the GNU General Public License version 2 as
  * published by the Free Software Foundation.
  *
- * For further information, see the Documentation/hwmon/max197 file.
+ * For further information, see the Documentation/hwmon/max197.rst file.
  */
 
 #ifndef _PDATA_MAX197_H
diff --git a/include/linux/platform_data/ntc_thermistor.h b/include/linux/platform_data/ntc_thermistor.h
index ee03d429742b..5fa115d3ea4b 100644
--- a/include/linux/platform_data/ntc_thermistor.h
+++ b/include/linux/platform_data/ntc_thermistor.h
@@ -42,7 +42,7 @@ struct ntc_thermistor_platform_data {
 	 * read_uV()
 	 *
 	 * How to setup pullup_ohm, pulldown_ohm, and connect is
-	 * described at Documentation/hwmon/ntc_thermistor
+	 * described at Documentation/hwmon/ntc_thermistor.rst
 	 *
 	 * pullup/down_ohm: 0 for infinite / not-connected
 	 *
diff --git a/include/linux/platform_data/spi-ep93xx.h b/include/linux/platform_data/spi-ep93xx.h
index eb16c6739ac2..b439f2a896e0 100644
--- a/include/linux/platform_data/spi-ep93xx.h
+++ b/include/linux/platform_data/spi-ep93xx.h
@@ -6,13 +6,9 @@ struct spi_device;
 
 /**
  * struct ep93xx_spi_info - EP93xx specific SPI descriptor
- * @chipselect: array of gpio numbers to use as chip selects
- * @num_chipselect: ARRAY_SIZE(chipselect)
  * @use_dma: use DMA for the transfers
  */
 struct ep93xx_spi_info {
-	int	*chipselect;
-	int	num_chipselect;
 	bool	use_dma;
 };
 
diff --git a/include/linux/platform_data/x86/clk-pmc-atom.h b/include/linux/platform_data/x86/clk-pmc-atom.h
index 3ab892208343..7a37ac27d0fb 100644
--- a/include/linux/platform_data/x86/clk-pmc-atom.h
+++ b/include/linux/platform_data/x86/clk-pmc-atom.h
@@ -35,10 +35,13 @@ struct pmc_clk {
  *
  * @base:	PMC clock register base offset
  * @clks:	pointer to set of registered clocks, typically 0..5
+ * @critical:	flag to indicate if firmware enabled pmc_plt_clks
+ *		should be marked as critial or not
  */
 struct pmc_clk_data {
 	void __iomem *base;
 	const struct pmc_clk *clks;
+	bool critical;
 };
 
 #endif /* __PLATFORM_DATA_X86_CLK_PMC_ATOM_H */
diff --git a/include/linux/pm_domain.h b/include/linux/pm_domain.h
index 1ed5874bcee0..0e8e356bed6a 100644
--- a/include/linux/pm_domain.h
+++ b/include/linux/pm_domain.h
@@ -16,6 +16,7 @@
 #include <linux/of.h>
 #include <linux/notifier.h>
 #include <linux/spinlock.h>
+#include <linux/cpumask.h>
 
 /*
  * Flags to control the behaviour of a genpd.
@@ -42,11 +43,22 @@
  * GENPD_FLAG_ACTIVE_WAKEUP:	Instructs genpd to keep the PM domain powered
  *				on, in case any of its attached devices is used
  *				in the wakeup path to serve system wakeups.
+ *
+ * GENPD_FLAG_CPU_DOMAIN:	Instructs genpd that it should expect to get
+ *				devices attached, which may belong to CPUs or
+ *				possibly have subdomains with CPUs attached.
+ *				This flag enables the genpd backend driver to
+ *				deploy idle power management support for CPUs
+ *				and groups of CPUs. Note that, the backend
+ *				driver must then comply with the so called,
+ *				last-man-standing algorithm, for the CPUs in the
+ *				PM domain.
  */
 #define GENPD_FLAG_PM_CLK	 (1U << 0)
 #define GENPD_FLAG_IRQ_SAFE	 (1U << 1)
 #define GENPD_FLAG_ALWAYS_ON	 (1U << 2)
 #define GENPD_FLAG_ACTIVE_WAKEUP (1U << 3)
+#define GENPD_FLAG_CPU_DOMAIN	 (1U << 4)
 
 enum gpd_status {
 	GPD_STATE_ACTIVE = 0,	/* PM domain is active */
@@ -69,6 +81,7 @@ struct genpd_power_state {
 	s64 residency_ns;
 	struct fwnode_handle *fwnode;
 	ktime_t idle_time;
+	void *data;
 };
 
 struct genpd_lock_ops;
@@ -93,6 +106,7 @@ struct generic_pm_domain {
 	unsigned int suspended_count;	/* System suspend device counter */
 	unsigned int prepared_count;	/* Suspend counter of prepared devices */
 	unsigned int performance_state;	/* Aggregated max performance state */
+	cpumask_var_t cpus;		/* A cpumask of the attached CPUs */
 	int (*power_off)(struct generic_pm_domain *domain);
 	int (*power_on)(struct generic_pm_domain *domain);
 	struct opp_table *opp_table;	/* OPP table of the genpd */
@@ -104,15 +118,17 @@ struct generic_pm_domain {
 	s64 max_off_time_ns;	/* Maximum allowed "suspended" time. */
 	bool max_off_time_changed;
 	bool cached_power_down_ok;
+	bool cached_power_down_state_idx;
 	int (*attach_dev)(struct generic_pm_domain *domain,
 			  struct device *dev);
 	void (*detach_dev)(struct generic_pm_domain *domain,
 			   struct device *dev);
 	unsigned int flags;		/* Bit field of configs for genpd */
 	struct genpd_power_state *states;
+	void (*free_states)(struct genpd_power_state *states,
+			    unsigned int state_count);
 	unsigned int state_count; /* number of states */
 	unsigned int state_idx; /* state that genpd will go to when off */
-	void *free; /* Free the state that was allocated for default */
 	ktime_t on_time;
 	ktime_t accounting_time;
 	const struct genpd_lock_ops *lock_ops;
@@ -159,6 +175,7 @@ struct generic_pm_domain_data {
 	struct pm_domain_data base;
 	struct gpd_timing_data td;
 	struct notifier_block nb;
+	int cpu;
 	unsigned int performance_state;
 	void *data;
 };
@@ -187,6 +204,9 @@ int dev_pm_genpd_set_performance_state(struct device *dev, unsigned int state);
 
 extern struct dev_power_governor simple_qos_governor;
 extern struct dev_power_governor pm_domain_always_on_gov;
+#ifdef CONFIG_CPU_IDLE
+extern struct dev_power_governor pm_domain_cpu_gov;
+#endif
 #else
 
 static inline struct generic_pm_domain_data *dev_gpd_data(struct device *dev)
diff --git a/include/linux/pm_opp.h b/include/linux/pm_opp.h
index 24c757a32a7b..b150fe97ce5a 100644
--- a/include/linux/pm_opp.h
+++ b/include/linux/pm_opp.h
@@ -102,6 +102,8 @@ struct dev_pm_opp *dev_pm_opp_find_freq_exact(struct device *dev,
 
 struct dev_pm_opp *dev_pm_opp_find_freq_floor(struct device *dev,
 					      unsigned long *freq);
+struct dev_pm_opp *dev_pm_opp_find_freq_ceil_by_volt(struct device *dev,
+						     unsigned long u_volt);
 
 struct dev_pm_opp *dev_pm_opp_find_freq_ceil(struct device *dev,
 					     unsigned long *freq);
@@ -207,6 +209,12 @@ static inline struct dev_pm_opp *dev_pm_opp_find_freq_floor(struct device *dev,
 	return ERR_PTR(-ENOTSUPP);
 }
 
+static inline struct dev_pm_opp *dev_pm_opp_find_freq_ceil_by_volt(struct device *dev,
+					unsigned long u_volt)
+{
+	return ERR_PTR(-ENOTSUPP);
+}
+
 static inline struct dev_pm_opp *dev_pm_opp_find_freq_ceil(struct device *dev,
 					unsigned long *freq)
 {
diff --git a/include/linux/property.h b/include/linux/property.h
index 65d3420dd5d1..a29369c89e6e 100644
--- a/include/linux/property.h
+++ b/include/linux/property.h
@@ -13,6 +13,7 @@
 #ifndef _LINUX_PROPERTY_H_
 #define _LINUX_PROPERTY_H_
 
+#include <linux/bits.h>
 #include <linux/fwnode.h>
 #include <linux/types.h>
 
@@ -304,6 +305,23 @@ struct fwnode_handle *
 fwnode_graph_get_remote_node(const struct fwnode_handle *fwnode, u32 port,
 			     u32 endpoint);
 
+/*
+ * Fwnode lookup flags
+ *
+ * @FWNODE_GRAPH_ENDPOINT_NEXT: In the case of no exact match, look for the
+ *				closest endpoint ID greater than the specified
+ *				one.
+ * @FWNODE_GRAPH_DEVICE_DISABLED: That the device to which the remote
+ *				  endpoint of the given endpoint belongs to,
+ *				  may be disabled.
+ */
+#define FWNODE_GRAPH_ENDPOINT_NEXT	BIT(0)
+#define FWNODE_GRAPH_DEVICE_DISABLED	BIT(1)
+
+struct fwnode_handle *
+fwnode_graph_get_endpoint_by_id(const struct fwnode_handle *fwnode,
+				u32 port, u32 endpoint, unsigned long flags);
+
 #define fwnode_graph_for_each_endpoint(fwnode, child)			\
 	for (child = NULL;						\
 	     (child = fwnode_graph_get_next_endpoint(fwnode, child)); )
diff --git a/include/linux/psp-sev.h b/include/linux/psp-sev.h
index 827c601841c4..6f89fc8d4b8e 100644
--- a/include/linux/psp-sev.h
+++ b/include/linux/psp-sev.h
@@ -5,8 +5,7 @@
  *
  * Author: Brijesh Singh <brijesh.singh@amd.com>
  *
- * SEV spec 0.14 is available at:
- * http://support.amd.com/TechDocs/55766_SEV-KM API_Specification.pdf
+ * SEV API spec is available at https://developer.amd.com/sev
  *
  * This program is free software; you can redistribute it and/or modify
  * it under the terms of the GNU General Public License version 2 as
diff --git a/include/linux/ptrace.h b/include/linux/ptrace.h
index edb9b040c94c..d5084ebd9f03 100644
--- a/include/linux/ptrace.h
+++ b/include/linux/ptrace.h
@@ -9,6 +9,13 @@
 #include <linux/bug.h>			/* For BUG_ON.  */
 #include <linux/pid_namespace.h>	/* For task_active_pid_ns.  */
 #include <uapi/linux/ptrace.h>
+#include <linux/seccomp.h>
+
+/* Add sp to seccomp_data, as seccomp is user API, we don't want to modify it */
+struct syscall_info {
+	__u64			sp;
+	struct seccomp_data	data;
+};
 
 extern int ptrace_access_vm(struct task_struct *tsk, unsigned long addr,
 			    void *buf, int len, unsigned int gup_flags);
@@ -407,9 +414,7 @@ static inline void user_single_step_report(struct pt_regs *regs)
 #define current_user_stack_pointer() user_stack_pointer(current_pt_regs())
 #endif
 
-extern int task_current_syscall(struct task_struct *target, long *callno,
-				unsigned long args[6], unsigned int maxargs,
-				unsigned long *sp, unsigned long *pc);
+extern int task_current_syscall(struct task_struct *target, struct syscall_info *info);
 
 extern void sigaction_compat_abi(struct k_sigaction *act, struct k_sigaction *oact);
 #endif
diff --git a/include/linux/qed/qed_if.h b/include/linux/qed/qed_if.h
index f6165d304b4d..48841e5dab90 100644
--- a/include/linux/qed/qed_if.h
+++ b/include/linux/qed/qed_if.h
@@ -1338,7 +1338,6 @@ static inline u16 qed_sb_update_sb_idx(struct qed_sb_info *sb_info)
 	}
 
 	/* Let SB update */
-	mmiowb();
 	return rc;
 }
 
@@ -1374,7 +1373,6 @@ static inline void qed_sb_ack(struct qed_sb_info *sb_info,
 	/* Both segments (interrupts & acks) are written to same place address;
 	 * Need to guarantee all commands will be received (in-order) by HW.
 	 */
-	mmiowb();
 	barrier();
 }
 
diff --git a/include/linux/rcupdate.h b/include/linux/rcupdate.h
index 6cdb1db776cf..922bb6848813 100644
--- a/include/linux/rcupdate.h
+++ b/include/linux/rcupdate.h
@@ -878,9 +878,11 @@ static inline void rcu_head_init(struct rcu_head *rhp)
 static inline bool
 rcu_head_after_call_rcu(struct rcu_head *rhp, rcu_callback_t f)
 {
-	if (READ_ONCE(rhp->func) == f)
+	rcu_callback_t func = READ_ONCE(rhp->func);
+
+	if (func == f)
 		return true;
-	WARN_ON_ONCE(READ_ONCE(rhp->func) != (rcu_callback_t)~0L);
+	WARN_ON_ONCE(func != (rcu_callback_t)~0L);
 	return false;
 }
 
diff --git a/include/linux/rcuwait.h b/include/linux/rcuwait.h
index 90bfa3279a01..563290fc194f 100644
--- a/include/linux/rcuwait.h
+++ b/include/linux/rcuwait.h
@@ -18,7 +18,7 @@
  * awoken.
  */
 struct rcuwait {
-	struct task_struct *task;
+	struct task_struct __rcu *task;
 };
 
 #define __RCUWAIT_INITIALIZER(name)		\
diff --git a/include/linux/regulator/consumer.h b/include/linux/regulator/consumer.h
index f3f76051e8b0..aaf3cee70439 100644
--- a/include/linux/regulator/consumer.h
+++ b/include/linux/regulator/consumer.h
@@ -478,6 +478,11 @@ static inline int regulator_is_supported_voltage(struct regulator *regulator,
 	return 0;
 }
 
+static inline unsigned int regulator_get_linear_step(struct regulator *regulator)
+{
+	return 0;
+}
+
 static inline int regulator_set_current_limit(struct regulator *regulator,
 					     int min_uA, int max_uA)
 {
diff --git a/include/linux/rwsem-spinlock.h b/include/linux/rwsem-spinlock.h
deleted file mode 100644
index e47568363e5e..000000000000
--- a/include/linux/rwsem-spinlock.h
+++ /dev/null
@@ -1,47 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 */
-/* rwsem-spinlock.h: fallback C implementation
- *
- * Copyright (c) 2001   David Howells (dhowells@redhat.com).
- * - Derived partially from ideas by Andrea Arcangeli <andrea@suse.de>
- * - Derived also from comments by Linus
- */
-
-#ifndef _LINUX_RWSEM_SPINLOCK_H
-#define _LINUX_RWSEM_SPINLOCK_H
-
-#ifndef _LINUX_RWSEM_H
-#error "please don't include linux/rwsem-spinlock.h directly, use linux/rwsem.h instead"
-#endif
-
-#ifdef __KERNEL__
-/*
- * the rw-semaphore definition
- * - if count is 0 then there are no active readers or writers
- * - if count is +ve then that is the number of active readers
- * - if count is -1 then there is one active writer
- * - if wait_list is not empty, then there are processes waiting for the semaphore
- */
-struct rw_semaphore {
-	__s32			count;
-	raw_spinlock_t		wait_lock;
-	struct list_head	wait_list;
-#ifdef CONFIG_DEBUG_LOCK_ALLOC
-	struct lockdep_map dep_map;
-#endif
-};
-
-#define RWSEM_UNLOCKED_VALUE		0x00000000
-
-extern void __down_read(struct rw_semaphore *sem);
-extern int __must_check __down_read_killable(struct rw_semaphore *sem);
-extern int __down_read_trylock(struct rw_semaphore *sem);
-extern void __down_write(struct rw_semaphore *sem);
-extern int __must_check __down_write_killable(struct rw_semaphore *sem);
-extern int __down_write_trylock(struct rw_semaphore *sem);
-extern void __up_read(struct rw_semaphore *sem);
-extern void __up_write(struct rw_semaphore *sem);
-extern void __downgrade_write(struct rw_semaphore *sem);
-extern int rwsem_is_locked(struct rw_semaphore *sem);
-
-#endif /* __KERNEL__ */
-#endif /* _LINUX_RWSEM_SPINLOCK_H */
diff --git a/include/linux/rwsem.h b/include/linux/rwsem.h
index 67dbb57508b1..2ea18a3def04 100644
--- a/include/linux/rwsem.h
+++ b/include/linux/rwsem.h
@@ -20,25 +20,30 @@
 #include <linux/osq_lock.h>
 #endif
 
-struct rw_semaphore;
-
-#ifdef CONFIG_RWSEM_GENERIC_SPINLOCK
-#include <linux/rwsem-spinlock.h> /* use a generic implementation */
-#define __RWSEM_INIT_COUNT(name)	.count = RWSEM_UNLOCKED_VALUE
-#else
-/* All arch specific implementations share the same struct */
+/*
+ * For an uncontended rwsem, count and owner are the only fields a task
+ * needs to touch when acquiring the rwsem. So they are put next to each
+ * other to increase the chance that they will share the same cacheline.
+ *
+ * In a contended rwsem, the owner is likely the most frequently accessed
+ * field in the structure as the optimistic waiter that holds the osq lock
+ * will spin on owner. For an embedded rwsem, other hot fields in the
+ * containing structure should be moved further away from the rwsem to
+ * reduce the chance that they will share the same cacheline causing
+ * cacheline bouncing problem.
+ */
 struct rw_semaphore {
 	atomic_long_t count;
-	struct list_head wait_list;
-	raw_spinlock_t wait_lock;
 #ifdef CONFIG_RWSEM_SPIN_ON_OWNER
-	struct optimistic_spin_queue osq; /* spinner MCS lock */
 	/*
 	 * Write owner. Used as a speculative check to see
 	 * if the owner is running on the cpu.
 	 */
 	struct task_struct *owner;
+	struct optimistic_spin_queue osq; /* spinner MCS lock */
 #endif
+	raw_spinlock_t wait_lock;
+	struct list_head wait_list;
 #ifdef CONFIG_DEBUG_LOCK_ALLOC
 	struct lockdep_map	dep_map;
 #endif
@@ -50,24 +55,14 @@ struct rw_semaphore {
  */
 #define RWSEM_OWNER_UNKNOWN	((struct task_struct *)-2L)
 
-extern struct rw_semaphore *rwsem_down_read_failed(struct rw_semaphore *sem);
-extern struct rw_semaphore *rwsem_down_read_failed_killable(struct rw_semaphore *sem);
-extern struct rw_semaphore *rwsem_down_write_failed(struct rw_semaphore *sem);
-extern struct rw_semaphore *rwsem_down_write_failed_killable(struct rw_semaphore *sem);
-extern struct rw_semaphore *rwsem_wake(struct rw_semaphore *);
-extern struct rw_semaphore *rwsem_downgrade_wake(struct rw_semaphore *sem);
-
-/* Include the arch specific part */
-#include <asm/rwsem.h>
-
 /* In all implementations count != 0 means locked */
 static inline int rwsem_is_locked(struct rw_semaphore *sem)
 {
 	return atomic_long_read(&sem->count) != 0;
 }
 
+#define RWSEM_UNLOCKED_VALUE		0L
 #define __RWSEM_INIT_COUNT(name)	.count = ATOMIC_LONG_INIT(RWSEM_UNLOCKED_VALUE)
-#endif
 
 /* Common initializer macros and functions */
 
diff --git a/include/linux/sched.h b/include/linux/sched.h
index 1549584a1538..50606a6e73d6 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -1057,7 +1057,6 @@ struct task_struct {
 
 #ifdef CONFIG_RSEQ
 	struct rseq __user *rseq;
-	u32 rseq_len;
 	u32 rseq_sig;
 	/*
 	 * RmW on rseq_event_mask must be performed atomically
@@ -1855,12 +1854,10 @@ static inline void rseq_fork(struct task_struct *t, unsigned long clone_flags)
 {
 	if (clone_flags & CLONE_THREAD) {
 		t->rseq = NULL;
-		t->rseq_len = 0;
 		t->rseq_sig = 0;
 		t->rseq_event_mask = 0;
 	} else {
 		t->rseq = current->rseq;
-		t->rseq_len = current->rseq_len;
 		t->rseq_sig = current->rseq_sig;
 		t->rseq_event_mask = current->rseq_event_mask;
 	}
@@ -1869,7 +1866,6 @@ static inline void rseq_fork(struct task_struct *t, unsigned long clone_flags)
 static inline void rseq_execve(struct task_struct *t)
 {
 	t->rseq = NULL;
-	t->rseq_len = 0;
 	t->rseq_sig = 0;
 	t->rseq_event_mask = 0;
 }
diff --git a/include/linux/sched/mm.h b/include/linux/sched/mm.h
index 0cd9f10423fb..a3fda9f024c3 100644
--- a/include/linux/sched/mm.h
+++ b/include/linux/sched/mm.h
@@ -49,6 +49,27 @@ static inline void mmdrop(struct mm_struct *mm)
 		__mmdrop(mm);
 }
 
+/*
+ * This has to be called after a get_task_mm()/mmget_not_zero()
+ * followed by taking the mmap_sem for writing before modifying the
+ * vmas or anything the coredump pretends not to change from under it.
+ *
+ * NOTE: find_extend_vma() called from GUP context is the only place
+ * that can modify the "mm" (notably the vm_start/end) under mmap_sem
+ * for reading and outside the context of the process, so it is also
+ * the only case that holds the mmap_sem for reading that must call
+ * this function. Generally if the mmap_sem is hold for reading
+ * there's no need of this check after get_task_mm()/mmget_not_zero().
+ *
+ * This function can be obsoleted and the check can be removed, after
+ * the coredump code will hold the mmap_sem for writing before
+ * invoking the ->core_dump methods.
+ */
+static inline bool mmget_still_valid(struct mm_struct *mm)
+{
+	return likely(!mm->core_state);
+}
+
 /**
  * mmget() - Pin the address space associated with a &struct mm_struct.
  * @mm: The address space to pin.
diff --git a/include/linux/sched/signal.h b/include/linux/sched/signal.h
index ae5655197698..e412c092c1e8 100644
--- a/include/linux/sched/signal.h
+++ b/include/linux/sched/signal.h
@@ -418,10 +418,20 @@ static inline void set_restore_sigmask(void)
 	set_thread_flag(TIF_RESTORE_SIGMASK);
 	WARN_ON(!test_thread_flag(TIF_SIGPENDING));
 }
+
+static inline void clear_tsk_restore_sigmask(struct task_struct *tsk)
+{
+	clear_tsk_thread_flag(tsk, TIF_RESTORE_SIGMASK);
+}
+
 static inline void clear_restore_sigmask(void)
 {
 	clear_thread_flag(TIF_RESTORE_SIGMASK);
 }
+static inline bool test_tsk_restore_sigmask(struct task_struct *tsk)
+{
+	return test_tsk_thread_flag(tsk, TIF_RESTORE_SIGMASK);
+}
 static inline bool test_restore_sigmask(void)
 {
 	return test_thread_flag(TIF_RESTORE_SIGMASK);
@@ -439,6 +449,10 @@ static inline void set_restore_sigmask(void)
 	current->restore_sigmask = true;
 	WARN_ON(!test_thread_flag(TIF_SIGPENDING));
 }
+static inline void clear_tsk_restore_sigmask(struct task_struct *tsk)
+{
+	tsk->restore_sigmask = false;
+}
 static inline void clear_restore_sigmask(void)
 {
 	current->restore_sigmask = false;
@@ -447,6 +461,10 @@ static inline bool test_restore_sigmask(void)
 {
 	return current->restore_sigmask;
 }
+static inline bool test_tsk_restore_sigmask(struct task_struct *tsk)
+{
+	return tsk->restore_sigmask;
+}
 static inline bool test_and_clear_restore_sigmask(void)
 {
 	if (!current->restore_sigmask)
diff --git a/include/linux/sched/task.h b/include/linux/sched/task.h
index 2e97a2227045..f1227f2c38a4 100644
--- a/include/linux/sched/task.h
+++ b/include/linux/sched/task.h
@@ -76,6 +76,7 @@ extern void exit_itimers(struct signal_struct *);
 extern long _do_fork(unsigned long, unsigned long, unsigned long, int __user *, int __user *, unsigned long);
 extern long do_fork(unsigned long, unsigned long, unsigned long, int __user *, int __user *);
 struct task_struct *fork_idle(int);
+struct mm_struct *copy_init_mm(void);
 extern pid_t kernel_thread(int (*fn)(void *), void *arg, unsigned long flags);
 extern long kernel_wait4(pid_t, int __user *, int, struct rusage *);
 
diff --git a/include/linux/sched/topology.h b/include/linux/sched/topology.h
index 57c7ed3fe465..cfc0a89a7159 100644
--- a/include/linux/sched/topology.h
+++ b/include/linux/sched/topology.h
@@ -76,8 +76,8 @@ struct sched_domain_shared {
 
 struct sched_domain {
 	/* These fields must be setup */
-	struct sched_domain *parent;	/* top domain must be null terminated */
-	struct sched_domain *child;	/* bottom domain must be null terminated */
+	struct sched_domain __rcu *parent;	/* top domain must be null terminated */
+	struct sched_domain __rcu *child;	/* bottom domain must be null terminated */
 	struct sched_group *groups;	/* the balancing groups of the domain */
 	unsigned long min_interval;	/* Minimum balance interval ms */
 	unsigned long max_interval;	/* Maximum balance interval ms */
diff --git a/include/linux/set_memory.h b/include/linux/set_memory.h
index 2a986d282a97..b5071497b8cb 100644
--- a/include/linux/set_memory.h
+++ b/include/linux/set_memory.h
@@ -17,6 +17,17 @@ static inline int set_memory_x(unsigned long addr,  int numpages) { return 0; }
 static inline int set_memory_nx(unsigned long addr, int numpages) { return 0; }
 #endif
 
+#ifndef CONFIG_ARCH_HAS_SET_DIRECT_MAP
+static inline int set_direct_map_invalid_noflush(struct page *page)
+{
+	return 0;
+}
+static inline int set_direct_map_default_noflush(struct page *page)
+{
+	return 0;
+}
+#endif
+
 #ifndef set_mce_nospec
 static inline int set_mce_nospec(unsigned long pfn)
 {
diff --git a/include/linux/shmem_fs.h b/include/linux/shmem_fs.h
index f3fb1edb3526..20d815a33145 100644
--- a/include/linux/shmem_fs.h
+++ b/include/linux/shmem_fs.h
@@ -21,6 +21,7 @@ struct shmem_inode_info {
 	struct list_head	swaplist;	/* chain of maybes on swap */
 	struct shared_policy	policy;		/* NUMA memory alloc policy */
 	struct simple_xattrs	xattrs;		/* list of xattrs */
+	atomic_t		stop_eviction;	/* hold when working on inode */
 	struct inode		vfs_inode;
 };
 
diff --git a/include/linux/slab.h b/include/linux/slab.h
index 11b45f7ae405..9449b19c5f10 100644
--- a/include/linux/slab.h
+++ b/include/linux/slab.h
@@ -32,6 +32,8 @@
 #define SLAB_HWCACHE_ALIGN	((slab_flags_t __force)0x00002000U)
 /* Use GFP_DMA memory */
 #define SLAB_CACHE_DMA		((slab_flags_t __force)0x00004000U)
+/* Use GFP_DMA32 memory */
+#define SLAB_CACHE_DMA32	((slab_flags_t __force)0x00008000U)
 /* DEBUG: Store the last owner for bug hunting */
 #define SLAB_STORE_USER		((slab_flags_t __force)0x00010000U)
 /* Panic if kmem_cache_create() fails */
diff --git a/include/linux/smpboot.h b/include/linux/smpboot.h
index d0884b525001..9d1bc65d226c 100644
--- a/include/linux/smpboot.h
+++ b/include/linux/smpboot.h
@@ -29,7 +29,7 @@ struct smpboot_thread_data;
  * @thread_comm:	The base name of the thread
  */
 struct smp_hotplug_thread {
-	struct task_struct __percpu	**store;
+	struct task_struct		* __percpu *store;
 	struct list_head		list;
 	int				(*thread_should_run)(unsigned int cpu);
 	void				(*thread_fn)(unsigned int cpu);
diff --git a/include/linux/socket.h b/include/linux/socket.h
index 6016daeecee4..b57cd8bf96e2 100644
--- a/include/linux/socket.h
+++ b/include/linux/socket.h
@@ -26,7 +26,7 @@ typedef __kernel_sa_family_t	sa_family_t;
 /*
  *	1003.1g requires sa_family_t and that sa_data is char.
  */
- 
+
 struct sockaddr {
 	sa_family_t	sa_family;	/* address family, AF_xxx	*/
 	char		sa_data[14];	/* 14 bytes of protocol address	*/
@@ -44,7 +44,7 @@ struct linger {
  *	system, not 4.3. Thus msg_accrights(len) are now missing. They
  *	belong in an obscure libc emulation or the bin.
  */
- 
+
 struct msghdr {
 	void		*msg_name;	/* ptr to socket address structure */
 	int		msg_namelen;	/* size of socket address structure */
@@ -54,7 +54,7 @@ struct msghdr {
 	unsigned int	msg_flags;	/* flags on received message */
 	struct kiocb	*msg_iocb;	/* ptr to iocb for async requests */
 };
- 
+
 struct user_msghdr {
 	void		__user *msg_name;	/* ptr to socket address structure */
 	int		msg_namelen;		/* size of socket address structure */
@@ -122,7 +122,7 @@ struct cmsghdr {
  *	inside range, given by msg->msg_controllen before using
  *	ancillary object DATA.				--ANK (980731)
  */
- 
+
 static inline struct cmsghdr * __cmsg_nxthdr(void *__ctl, __kernel_size_t __size,
 					       struct cmsghdr *__cmsg)
 {
@@ -264,10 +264,10 @@ struct ucred {
 /* Maximum queue length specifiable by listen.  */
 #define SOMAXCONN	128
 
-/* Flags we can use with send/ and recv. 
+/* Flags we can use with send/ and recv.
    Added those for 1003.1g not all are supported yet
  */
- 
+
 #define MSG_OOB		1
 #define MSG_PEEK	2
 #define MSG_DONTROUTE	4
diff --git a/include/linux/spi/pxa2xx_spi.h b/include/linux/spi/pxa2xx_spi.h
index c1c59473cef9..6005f0126631 100644
--- a/include/linux/spi/pxa2xx_spi.h
+++ b/include/linux/spi/pxa2xx_spi.h
@@ -25,6 +25,7 @@ struct dma_chan;
 struct pxa2xx_spi_controller {
 	u16 num_chipselect;
 	u8 enable_dma;
+	u8 dma_burst_size;
 	bool is_slave;
 
 	/* DMA engine specific config */
diff --git a/include/linux/spi/spi-mem.h b/include/linux/spi/spi-mem.h
index 3703d0dcac2e..af9ff2f0f1b2 100644
--- a/include/linux/spi/spi-mem.h
+++ b/include/linux/spi/spi-mem.h
@@ -295,6 +295,10 @@ int spi_controller_dma_map_mem_op_data(struct spi_controller *ctlr,
 void spi_controller_dma_unmap_mem_op_data(struct spi_controller *ctlr,
 					  const struct spi_mem_op *op,
 					  struct sg_table *sg);
+
+bool spi_mem_default_supports_op(struct spi_mem *mem,
+				 const struct spi_mem_op *op);
+
 #else
 static inline int
 spi_controller_dma_map_mem_op_data(struct spi_controller *ctlr,
@@ -310,6 +314,14 @@ spi_controller_dma_unmap_mem_op_data(struct spi_controller *ctlr,
 				     struct sg_table *sg)
 {
 }
+
+static inline
+bool spi_mem_default_supports_op(struct spi_mem *mem,
+				 const struct spi_mem_op *op)
+{
+	return false;
+}
+
 #endif /* CONFIG_SPI_MEM */
 
 int spi_mem_adjust_op_size(struct spi_mem *mem, struct spi_mem_op *op);
diff --git a/include/linux/spi/spi.h b/include/linux/spi/spi.h
index 662b336aa2e4..053abd22ad31 100644
--- a/include/linux/spi/spi.h
+++ b/include/linux/spi/spi.h
@@ -143,7 +143,7 @@ struct spi_device {
 	u32			max_speed_hz;
 	u8			chip_select;
 	u8			bits_per_word;
-	u16			mode;
+	u32			mode;
 #define	SPI_CPHA	0x01			/* clock phase */
 #define	SPI_CPOL	0x02			/* clock polarity */
 #define	SPI_MODE_0	(0|0)			/* (original MicroWire) */
@@ -330,6 +330,9 @@ static inline void spi_unregister_driver(struct spi_driver *sdrv)
  *	must fail if an unrecognized or unsupported mode is requested.
  *	It's always safe to call this unless transfers are pending on
  *	the device whose settings are being modified.
+ * @set_cs_timing: optional hook for SPI devices to request SPI master
+ * controller for configuring specific CS setup time, hold time and inactive
+ * delay interms of clock counts
  * @transfer: adds a message to the controller's transfer queue.
  * @cleanup: frees controller-specific state
  * @can_dma: determine whether this controller supports DMA
@@ -363,6 +366,7 @@ static inline void spi_unregister_driver(struct spi_driver *sdrv)
  * @unprepare_transfer_hardware: there are currently no more messages on the
  *	queue so the subsystem notifies the driver that it may relax the
  *	hardware by issuing this call
+ *
  * @set_cs: set the logic level of the chip select line.  May be called
  *          from interrupt context.
  * @prepare_message: set up the controller to transfer a single message,
@@ -439,13 +443,12 @@ struct spi_controller {
 	u16			dma_alignment;
 
 	/* spi_device.mode flags understood by this controller driver */
-	u16			mode_bits;
+	u32			mode_bits;
 
 	/* bitmask of supported bits_per_word for transfers */
 	u32			bits_per_word_mask;
 #define SPI_BPW_MASK(bits) BIT((bits) - 1)
-#define SPI_BIT_MASK(bits) (((bits) == 32) ? ~0U : (BIT(bits) - 1))
-#define SPI_BPW_RANGE_MASK(min, max) (SPI_BIT_MASK(max) - SPI_BIT_MASK(min - 1))
+#define SPI_BPW_RANGE_MASK(min, max) GENMASK((max) - 1, (min) - 1)
 
 	/* limits on transfer speed */
 	u32			min_speed_hz;
@@ -489,6 +492,17 @@ struct spi_controller {
 	 */
 	int			(*setup)(struct spi_device *spi);
 
+	/*
+	 * set_cs_timing() method is for SPI controllers that supports
+	 * configuring CS timing.
+	 *
+	 * This hook allows SPI client drivers to request SPI controllers
+	 * to configure specific CS timing through spi_set_cs_timing() after
+	 * spi_setup().
+	 */
+	void (*set_cs_timing)(struct spi_device *spi, u8 setup_clk_cycles,
+			      u8 hold_clk_cycles, u8 inactive_clk_cycles);
+
 	/* bidirectional bulk transfers
 	 *
 	 * + The transfer() method may not sleep; its main role is
@@ -1277,7 +1291,7 @@ struct spi_board_info {
 	/* mode becomes spi_device.mode, and is essential for chips
 	 * where the default of SPI_CS_HIGH = 0 is wrong.
 	 */
-	u16		mode;
+	u32		mode;
 
 	/* ... may need additional spi_device chip config data here.
 	 * avoid stuff protocol drivers can set; but include stuff
diff --git a/include/linux/spi/spi_bitbang.h b/include/linux/spi/spi_bitbang.h
index b7e021b274dc..4444c2a992cb 100644
--- a/include/linux/spi/spi_bitbang.h
+++ b/include/linux/spi/spi_bitbang.h
@@ -44,6 +44,7 @@ extern int spi_bitbang_setup_transfer(struct spi_device *spi,
 
 /* start or stop queue processing */
 extern int spi_bitbang_start(struct spi_bitbang *spi);
+extern int spi_bitbang_init(struct spi_bitbang *spi);
 extern void spi_bitbang_stop(struct spi_bitbang *spi);
 
 #endif	/* __SPI_BITBANG_H */
diff --git a/include/linux/spinlock.h b/include/linux/spinlock.h
index e089157dcf97..ed7c4d6b8235 100644
--- a/include/linux/spinlock.h
+++ b/include/linux/spinlock.h
@@ -57,6 +57,7 @@
 #include <linux/stringify.h>
 #include <linux/bottom_half.h>
 #include <asm/barrier.h>
+#include <asm/mmiowb.h>
 
 
 /*
@@ -178,6 +179,7 @@ static inline void do_raw_spin_lock(raw_spinlock_t *lock) __acquires(lock)
 {
 	__acquire(lock);
 	arch_spin_lock(&lock->raw_lock);
+	mmiowb_spin_lock();
 }
 
 #ifndef arch_spin_lock_flags
@@ -189,15 +191,22 @@ do_raw_spin_lock_flags(raw_spinlock_t *lock, unsigned long *flags) __acquires(lo
 {
 	__acquire(lock);
 	arch_spin_lock_flags(&lock->raw_lock, *flags);
+	mmiowb_spin_lock();
 }
 
 static inline int do_raw_spin_trylock(raw_spinlock_t *lock)
 {
-	return arch_spin_trylock(&(lock)->raw_lock);
+	int ret = arch_spin_trylock(&(lock)->raw_lock);
+
+	if (ret)
+		mmiowb_spin_lock();
+
+	return ret;
 }
 
 static inline void do_raw_spin_unlock(raw_spinlock_t *lock) __releases(lock)
 {
+	mmiowb_spin_unlock();
 	arch_spin_unlock(&lock->raw_lock);
 	__release(lock);
 }
diff --git a/include/linux/srcu.h b/include/linux/srcu.h
index c495b2d51569..e432cc92c73d 100644
--- a/include/linux/srcu.h
+++ b/include/linux/srcu.h
@@ -56,45 +56,11 @@ struct srcu_struct { };
 
 void call_srcu(struct srcu_struct *ssp, struct rcu_head *head,
 		void (*func)(struct rcu_head *head));
-void _cleanup_srcu_struct(struct srcu_struct *ssp, bool quiesced);
+void cleanup_srcu_struct(struct srcu_struct *ssp);
 int __srcu_read_lock(struct srcu_struct *ssp) __acquires(ssp);
 void __srcu_read_unlock(struct srcu_struct *ssp, int idx) __releases(ssp);
 void synchronize_srcu(struct srcu_struct *ssp);
 
-/**
- * cleanup_srcu_struct - deconstruct a sleep-RCU structure
- * @ssp: structure to clean up.
- *
- * Must invoke this after you are finished using a given srcu_struct that
- * was initialized via init_srcu_struct(), else you leak memory.
- */
-static inline void cleanup_srcu_struct(struct srcu_struct *ssp)
-{
-	_cleanup_srcu_struct(ssp, false);
-}
-
-/**
- * cleanup_srcu_struct_quiesced - deconstruct a quiesced sleep-RCU structure
- * @ssp: structure to clean up.
- *
- * Must invoke this after you are finished using a given srcu_struct that
- * was initialized via init_srcu_struct(), else you leak memory.  Also,
- * all grace-period processing must have completed.
- *
- * "Completed" means that the last synchronize_srcu() and
- * synchronize_srcu_expedited() calls must have returned before the call
- * to cleanup_srcu_struct_quiesced().  It also means that the callback
- * from the last call_srcu() must have been invoked before the call to
- * cleanup_srcu_struct_quiesced(), but you can use srcu_barrier() to help
- * with this last.  Violating these rules will get you a WARN_ON() splat
- * (with high probability, anyway), and will also cause the srcu_struct
- * to be leaked.
- */
-static inline void cleanup_srcu_struct_quiesced(struct srcu_struct *ssp)
-{
-	_cleanup_srcu_struct(ssp, true);
-}
-
 #ifdef CONFIG_DEBUG_LOCK_ALLOC
 
 /**
diff --git a/include/linux/stackdepot.h b/include/linux/stackdepot.h
index 7978b3e2c1e1..0805dee1b6b8 100644
--- a/include/linux/stackdepot.h
+++ b/include/linux/stackdepot.h
@@ -23,10 +23,10 @@
 
 typedef u32 depot_stack_handle_t;
 
-struct stack_trace;
+depot_stack_handle_t stack_depot_save(unsigned long *entries,
+				      unsigned int nr_entries, gfp_t gfp_flags);
 
-depot_stack_handle_t depot_save_stack(struct stack_trace *trace, gfp_t flags);
-
-void depot_fetch_stack(depot_stack_handle_t handle, struct stack_trace *trace);
+unsigned int stack_depot_fetch(depot_stack_handle_t handle,
+			       unsigned long **entries);
 
 #endif
diff --git a/include/linux/stacktrace.h b/include/linux/stacktrace.h
index ba29a0613e66..f0cfd12cb45e 100644
--- a/include/linux/stacktrace.h
+++ b/include/linux/stacktrace.h
@@ -3,11 +3,64 @@
 #define __LINUX_STACKTRACE_H
 
 #include <linux/types.h>
+#include <asm/errno.h>
 
 struct task_struct;
 struct pt_regs;
 
 #ifdef CONFIG_STACKTRACE
+void stack_trace_print(unsigned long *trace, unsigned int nr_entries,
+		       int spaces);
+int stack_trace_snprint(char *buf, size_t size, unsigned long *entries,
+			unsigned int nr_entries, int spaces);
+unsigned int stack_trace_save(unsigned long *store, unsigned int size,
+			      unsigned int skipnr);
+unsigned int stack_trace_save_tsk(struct task_struct *task,
+				  unsigned long *store, unsigned int size,
+				  unsigned int skipnr);
+unsigned int stack_trace_save_regs(struct pt_regs *regs, unsigned long *store,
+				   unsigned int size, unsigned int skipnr);
+unsigned int stack_trace_save_user(unsigned long *store, unsigned int size);
+
+/* Internal interfaces. Do not use in generic code */
+#ifdef CONFIG_ARCH_STACKWALK
+
+/**
+ * stack_trace_consume_fn - Callback for arch_stack_walk()
+ * @cookie:	Caller supplied pointer handed back by arch_stack_walk()
+ * @addr:	The stack entry address to consume
+ * @reliable:	True when the stack entry is reliable. Required by
+ *		some printk based consumers.
+ *
+ * Return:	True, if the entry was consumed or skipped
+ *		False, if there is no space left to store
+ */
+typedef bool (*stack_trace_consume_fn)(void *cookie, unsigned long addr,
+				       bool reliable);
+/**
+ * arch_stack_walk - Architecture specific function to walk the stack
+ * @consume_entry:	Callback which is invoked by the architecture code for
+ *			each entry.
+ * @cookie:		Caller supplied pointer which is handed back to
+ *			@consume_entry
+ * @task:		Pointer to a task struct, can be NULL
+ * @regs:		Pointer to registers, can be NULL
+ *
+ * ============ ======= ============================================
+ * task	        regs
+ * ============ ======= ============================================
+ * task		NULL	Stack trace from task (can be current)
+ * current	regs	Stack trace starting on regs->stackpointer
+ * ============ ======= ============================================
+ */
+void arch_stack_walk(stack_trace_consume_fn consume_entry, void *cookie,
+		     struct task_struct *task, struct pt_regs *regs);
+int arch_stack_walk_reliable(stack_trace_consume_fn consume_entry, void *cookie,
+			     struct task_struct *task);
+void arch_stack_walk_user(stack_trace_consume_fn consume_entry, void *cookie,
+			  const struct pt_regs *regs);
+
+#else /* CONFIG_ARCH_STACKWALK */
 struct stack_trace {
 	unsigned int nr_entries, max_entries;
 	unsigned long *entries;
@@ -21,24 +74,20 @@ extern void save_stack_trace_tsk(struct task_struct *tsk,
 				struct stack_trace *trace);
 extern int save_stack_trace_tsk_reliable(struct task_struct *tsk,
 					 struct stack_trace *trace);
-
-extern void print_stack_trace(struct stack_trace *trace, int spaces);
-extern int snprint_stack_trace(char *buf, size_t size,
-			struct stack_trace *trace, int spaces);
-
-#ifdef CONFIG_USER_STACKTRACE_SUPPORT
 extern void save_stack_trace_user(struct stack_trace *trace);
+#endif /* !CONFIG_ARCH_STACKWALK */
+#endif /* CONFIG_STACKTRACE */
+
+#if defined(CONFIG_STACKTRACE) && defined(CONFIG_HAVE_RELIABLE_STACKTRACE)
+int stack_trace_save_tsk_reliable(struct task_struct *tsk, unsigned long *store,
+				  unsigned int size);
 #else
-# define save_stack_trace_user(trace)              do { } while (0)
+static inline int stack_trace_save_tsk_reliable(struct task_struct *tsk,
+						unsigned long *store,
+						unsigned int size)
+{
+	return -ENOSYS;
+}
 #endif
 
-#else /* !CONFIG_STACKTRACE */
-# define save_stack_trace(trace)			do { } while (0)
-# define save_stack_trace_tsk(tsk, trace)		do { } while (0)
-# define save_stack_trace_user(trace)			do { } while (0)
-# define print_stack_trace(trace, spaces)		do { } while (0)
-# define snprint_stack_trace(buf, size, trace, spaces)	do { } while (0)
-# define save_stack_trace_tsk_reliable(tsk, trace)	({ -ENOSYS; })
-#endif /* CONFIG_STACKTRACE */
-
 #endif /* __LINUX_STACKTRACE_H */
diff --git a/include/linux/string.h b/include/linux/string.h
index 7927b875f80c..4deb11f7976b 100644
--- a/include/linux/string.h
+++ b/include/linux/string.h
@@ -31,6 +31,10 @@ size_t strlcpy(char *, const char *, size_t);
 #ifndef __HAVE_ARCH_STRSCPY
 ssize_t strscpy(char *, const char *, size_t);
 #endif
+
+/* Wraps calls to strscpy()/memset(), no arch specific code required */
+ssize_t strscpy_pad(char *dest, const char *src, size_t count);
+
 #ifndef __HAVE_ARCH_STRCAT
 extern char * strcat(char *, const char *);
 #endif
@@ -150,6 +154,9 @@ extern void * memscan(void *,int,__kernel_size_t);
 #ifndef __HAVE_ARCH_MEMCMP
 extern int memcmp(const void *,const void *,__kernel_size_t);
 #endif
+#ifndef __HAVE_ARCH_BCMP
+extern int bcmp(const void *,const void *,__kernel_size_t);
+#endif
 #ifndef __HAVE_ARCH_MEMCHR
 extern void * memchr(const void *,int,__kernel_size_t);
 #endif
diff --git a/include/linux/sunrpc/sched.h b/include/linux/sunrpc/sched.h
index ec861cd0cfe8..52d41d0c1ae1 100644
--- a/include/linux/sunrpc/sched.h
+++ b/include/linux/sunrpc/sched.h
@@ -304,12 +304,4 @@ rpc_clnt_swap_deactivate(struct rpc_clnt *clnt)
 }
 #endif /* CONFIG_SUNRPC_SWAP */
 
-static inline bool
-rpc_task_need_resched(const struct rpc_task *task)
-{
-	if (RPC_IS_QUEUED(task) || task->tk_callback)
-		return true;
-	return false;
-}
-
 #endif /* _LINUX_SUNRPC_SCHED_H_ */
diff --git a/include/linux/suspend.h b/include/linux/suspend.h
index 3f529ad9a9d2..6b3ea9ea6a9e 100644
--- a/include/linux/suspend.h
+++ b/include/linux/suspend.h
@@ -425,6 +425,7 @@ void restore_processor_state(void);
 /* kernel/power/main.c */
 extern int register_pm_notifier(struct notifier_block *nb);
 extern int unregister_pm_notifier(struct notifier_block *nb);
+extern void ksys_sync_helper(void);
 
 #define pm_notifier(fn, pri) {				\
 	static struct notifier_block fn##_nb =			\
@@ -462,6 +463,8 @@ static inline int unregister_pm_notifier(struct notifier_block *nb)
 	return 0;
 }
 
+static inline void ksys_sync_helper(void) {}
+
 #define pm_notifier(fn, pri)	do { (void)(fn); } while (0)
 
 static inline bool pm_wakeup_pending(void) { return false; }
diff --git a/include/linux/tick.h b/include/linux/tick.h
index 55388ab45fd4..f92a10b5e112 100644
--- a/include/linux/tick.h
+++ b/include/linux/tick.h
@@ -68,6 +68,12 @@ extern void tick_broadcast_control(enum tick_broadcast_mode mode);
 static inline void tick_broadcast_control(enum tick_broadcast_mode mode) { }
 #endif /* BROADCAST */
 
+#if defined(CONFIG_GENERIC_CLOCKEVENTS_BROADCAST) && defined(CONFIG_HOTPLUG_CPU)
+extern void tick_offline_cpu(unsigned int cpu);
+#else
+static inline void tick_offline_cpu(unsigned int cpu) { }
+#endif
+
 #ifdef CONFIG_GENERIC_CLOCKEVENTS
 extern int tick_broadcast_oneshot_control(enum tick_broadcast_state state);
 #else
@@ -122,6 +128,7 @@ extern void tick_nohz_idle_enter(void);
 extern void tick_nohz_idle_exit(void);
 extern void tick_nohz_irq_exit(void);
 extern bool tick_nohz_idle_got_tick(void);
+extern ktime_t tick_nohz_get_next_hrtimer(void);
 extern ktime_t tick_nohz_get_sleep_length(ktime_t *delta_next);
 extern unsigned long tick_nohz_get_idle_calls(void);
 extern unsigned long tick_nohz_get_idle_calls_cpu(int cpu);
@@ -145,7 +152,11 @@ static inline void tick_nohz_idle_restart_tick(void) { }
 static inline void tick_nohz_idle_enter(void) { }
 static inline void tick_nohz_idle_exit(void) { }
 static inline bool tick_nohz_idle_got_tick(void) { return false; }
-
+static inline ktime_t tick_nohz_get_next_hrtimer(void)
+{
+	/* Next wake up is the tick period, assume it starts now */
+	return ktime_add(ktime_get(), TICK_NSEC);
+}
 static inline ktime_t tick_nohz_get_sleep_length(ktime_t *delta_next)
 {
 	*delta_next = TICK_NSEC;
diff --git a/include/linux/time64.h b/include/linux/time64.h
index f38d382ffec1..a620ee610b9f 100644
--- a/include/linux/time64.h
+++ b/include/linux/time64.h
@@ -33,6 +33,17 @@ struct itimerspec64 {
 #define KTIME_MAX			((s64)~((u64)1 << 63))
 #define KTIME_SEC_MAX			(KTIME_MAX / NSEC_PER_SEC)
 
+/*
+ * Limits for settimeofday():
+ *
+ * To prevent setting the time close to the wraparound point time setting
+ * is limited so a reasonable uptime can be accomodated. Uptime of 30 years
+ * should be really sufficient, which means the cutoff is 2232. At that
+ * point the cutoff is just a small part of the larger problem.
+ */
+#define TIME_UPTIME_SEC_MAX		(30LL * 365 * 24 *3600)
+#define TIME_SETTOD_SEC_MAX		(KTIME_SEC_MAX - TIME_UPTIME_SEC_MAX)
+
 static inline int timespec64_equal(const struct timespec64 *a,
 				   const struct timespec64 *b)
 {
@@ -100,6 +111,16 @@ static inline bool timespec64_valid_strict(const struct timespec64 *ts)
 	return true;
 }
 
+static inline bool timespec64_valid_settod(const struct timespec64 *ts)
+{
+	if (!timespec64_valid(ts))
+		return false;
+	/* Disallow values which cause overflow issues vs. CLOCK_REALTIME */
+	if ((unsigned long long)ts->tv_sec >= TIME_SETTOD_SEC_MAX)
+		return false;
+	return true;
+}
+
 /**
  * timespec64_to_ns - Convert timespec64 to nanoseconds
  * @ts:		pointer to the timespec64 variable to be converted
diff --git a/include/linux/uaccess.h b/include/linux/uaccess.h
index 37b226e8df13..2b70130af585 100644
--- a/include/linux/uaccess.h
+++ b/include/linux/uaccess.h
@@ -268,6 +268,8 @@ extern long strncpy_from_unsafe(char *dst, const void *unsafe_addr, long count);
 #define user_access_end() do { } while (0)
 #define unsafe_get_user(x, ptr, err) do { if (unlikely(__get_user(x, ptr))) goto err; } while (0)
 #define unsafe_put_user(x, ptr, err) do { if (unlikely(__put_user(x, ptr))) goto err; } while (0)
+static inline unsigned long user_access_save(void) { return 0UL; }
+static inline void user_access_restore(unsigned long flags) { }
 #endif
 
 #ifdef CONFIG_HARDENED_USERCOPY
diff --git a/include/linux/uio.h b/include/linux/uio.h
index f184af1999a8..2d0131ad4604 100644
--- a/include/linux/uio.h
+++ b/include/linux/uio.h
@@ -60,7 +60,7 @@ struct iov_iter {
 
 static inline enum iter_type iov_iter_type(const struct iov_iter *i)
 {
-	return i->type & ~(READ | WRITE);
+	return i->type & ~(READ | WRITE | ITER_BVEC_FLAG_NO_REF);
 }
 
 static inline bool iter_is_iovec(const struct iov_iter *i)
diff --git a/include/linux/uprobes.h b/include/linux/uprobes.h
index 103a48a48872..12bf0b68ed92 100644
--- a/include/linux/uprobes.h
+++ b/include/linux/uprobes.h
@@ -115,6 +115,7 @@ struct uprobes_state {
 	struct xol_area		*xol_area;
 };
 
+extern void __init uprobes_init(void);
 extern int set_swbp(struct arch_uprobe *aup, struct mm_struct *mm, unsigned long vaddr);
 extern int set_orig_insn(struct arch_uprobe *aup, struct mm_struct *mm, unsigned long vaddr);
 extern bool is_swbp_insn(uprobe_opcode_t *insn);
@@ -154,6 +155,10 @@ extern void arch_uprobe_copy_ixol(struct page *page, unsigned long vaddr,
 struct uprobes_state {
 };
 
+static inline void uprobes_init(void)
+{
+}
+
 #define uprobe_get_trap_addr(regs)	instruction_pointer(regs)
 
 static inline int
diff --git a/include/linux/usb.h b/include/linux/usb.h
index 5e49e82c4368..ff010d1fd1c7 100644
--- a/include/linux/usb.h
+++ b/include/linux/usb.h
@@ -200,7 +200,6 @@ usb_find_last_int_out_endpoint(struct usb_host_interface *alt,
  * @dev: driver model's view of this device
  * @usb_dev: if an interface is bound to the USB major, this will point
  *	to the sysfs representation for that device.
- * @pm_usage_cnt: PM usage counter for this interface
  * @reset_ws: Used for scheduling resets from atomic context.
  * @resetting_device: USB core reset the device, so use alt setting 0 as
  *	current; needs bandwidth alloc after reset.
@@ -257,7 +256,6 @@ struct usb_interface {
 
 	struct device dev;		/* interface specific device info */
 	struct device *usb_dev;
-	atomic_t pm_usage_cnt;		/* usage counter for autosuspend */
 	struct work_struct reset_ws;	/* for resets in atomic context */
 };
 #define	to_usb_interface(d) container_of(d, struct usb_interface, dev)
diff --git a/include/linux/vbox_utils.h b/include/linux/vbox_utils.h
index a240ed2a0372..ff56c443180c 100644
--- a/include/linux/vbox_utils.h
+++ b/include/linux/vbox_utils.h
@@ -24,15 +24,17 @@ __printf(1, 2) void vbg_debug(const char *fmt, ...);
 #define vbg_debug pr_debug
 #endif
 
-int vbg_hgcm_connect(struct vbg_dev *gdev,
+int vbg_hgcm_connect(struct vbg_dev *gdev, u32 requestor,
 		     struct vmmdev_hgcm_service_location *loc,
 		     u32 *client_id, int *vbox_status);
 
-int vbg_hgcm_disconnect(struct vbg_dev *gdev, u32 client_id, int *vbox_status);
+int vbg_hgcm_disconnect(struct vbg_dev *gdev, u32 requestor,
+			u32 client_id, int *vbox_status);
 
-int vbg_hgcm_call(struct vbg_dev *gdev, u32 client_id, u32 function,
-		  u32 timeout_ms, struct vmmdev_hgcm_function_parameter *parms,
-		  u32 parm_count, int *vbox_status);
+int vbg_hgcm_call(struct vbg_dev *gdev, u32 requestor, u32 client_id,
+		  u32 function, u32 timeout_ms,
+		  struct vmmdev_hgcm_function_parameter *parms, u32 parm_count,
+		  int *vbox_status);
 
 /**
  * Convert a VirtualBox status code to a standard Linux kernel return value.
diff --git a/include/linux/virtio_ring.h b/include/linux/virtio_ring.h
index fab02133a919..3dc70adfe5f5 100644
--- a/include/linux/virtio_ring.h
+++ b/include/linux/virtio_ring.h
@@ -63,7 +63,7 @@ struct virtqueue;
 /*
  * Creates a virtqueue and allocates the descriptor ring.  If
  * may_reduce_num is set, then this may allocate a smaller ring than
- * expected.  The caller should query virtqueue_get_ring_size to learn
+ * expected.  The caller should query virtqueue_get_vring_size to learn
  * the actual size of the ring.
  */
 struct virtqueue *vring_create_virtqueue(unsigned int index,
diff --git a/include/linux/vmalloc.h b/include/linux/vmalloc.h
index 398e9c95cd61..c6eebb839552 100644
--- a/include/linux/vmalloc.h
+++ b/include/linux/vmalloc.h
@@ -21,6 +21,11 @@ struct notifier_block;		/* in notifier.h */
 #define VM_UNINITIALIZED	0x00000020	/* vm_struct is not fully initialized */
 #define VM_NO_GUARD		0x00000040      /* don't add guard page */
 #define VM_KASAN		0x00000080      /* has allocated kasan shadow memory */
+/*
+ * Memory with VM_FLUSH_RESET_PERMS cannot be freed in an interrupt or with
+ * vfree_atomic().
+ */
+#define VM_FLUSH_RESET_PERMS	0x00000100      /* Reset direct map and flush TLB on unmap */
 /* bits [20..32] reserved for arch specific ioremap internals */
 
 /*
@@ -142,6 +147,13 @@ extern int map_kernel_range_noflush(unsigned long start, unsigned long size,
 				    pgprot_t prot, struct page **pages);
 extern void unmap_kernel_range_noflush(unsigned long addr, unsigned long size);
 extern void unmap_kernel_range(unsigned long addr, unsigned long size);
+static inline void set_vm_flush_reset_perms(void *addr)
+{
+	struct vm_struct *vm = find_vm_area(addr);
+
+	if (vm)
+		vm->flags |= VM_FLUSH_RESET_PERMS;
+}
 #else
 static inline int
 map_kernel_range_noflush(unsigned long start, unsigned long size,
@@ -157,6 +169,9 @@ static inline void
 unmap_kernel_range(unsigned long addr, unsigned long size)
 {
 }
+static inline void set_vm_flush_reset_perms(void *addr)
+{
+}
 #endif
 
 /* Allocate/destroy a 'vmalloc' VM area. */
diff --git a/include/net/act_api.h b/include/net/act_api.h
index c745e9ccfab2..c61a1bf4e3de 100644
--- a/include/net/act_api.h
+++ b/include/net/act_api.h
@@ -39,7 +39,7 @@ struct tc_action {
 	struct gnet_stats_basic_cpu __percpu *cpu_bstats_hw;
 	struct gnet_stats_queue __percpu *cpu_qstats;
 	struct tc_cookie	__rcu *act_cookie;
-	struct tcf_chain	*goto_chain;
+	struct tcf_chain	__rcu *goto_chain;
 };
 #define tcf_index	common.tcfa_index
 #define tcf_refcnt	common.tcfa_refcnt
@@ -90,7 +90,7 @@ struct tc_action_ops {
 	int     (*lookup)(struct net *net, struct tc_action **a, u32 index);
 	int     (*init)(struct net *net, struct nlattr *nla,
 			struct nlattr *est, struct tc_action **act, int ovr,
-			int bind, bool rtnl_held,
+			int bind, bool rtnl_held, struct tcf_proto *tp,
 			struct netlink_ext_ack *extack);
 	int     (*walk)(struct net *, struct sk_buff *,
 			struct netlink_callback *, int,
@@ -181,6 +181,11 @@ int tcf_action_dump_old(struct sk_buff *skb, struct tc_action *a, int, int);
 int tcf_action_dump_1(struct sk_buff *skb, struct tc_action *a, int, int);
 int tcf_action_copy_stats(struct sk_buff *, struct tc_action *, int);
 
+int tcf_action_check_ctrlact(int action, struct tcf_proto *tp,
+			     struct tcf_chain **handle,
+			     struct netlink_ext_ack *newchain);
+struct tcf_chain *tcf_action_set_ctrlact(struct tc_action *a, int action,
+					 struct tcf_chain *newchain);
 #endif /* CONFIG_NET_CLS_ACT */
 
 static inline void tcf_action_stats_update(struct tc_action *a, u64 bytes,
diff --git a/include/net/af_rxrpc.h b/include/net/af_rxrpc.h
index 2bfb87eb98ce..78c856cba4f5 100644
--- a/include/net/af_rxrpc.h
+++ b/include/net/af_rxrpc.h
@@ -61,10 +61,12 @@ int rxrpc_kernel_charge_accept(struct socket *, rxrpc_notify_rx_t,
 			       rxrpc_user_attach_call_t, unsigned long, gfp_t,
 			       unsigned int);
 void rxrpc_kernel_set_tx_length(struct socket *, struct rxrpc_call *, s64);
-u32 rxrpc_kernel_check_life(const struct socket *, const struct rxrpc_call *);
+bool rxrpc_kernel_check_life(const struct socket *, const struct rxrpc_call *,
+			     u32 *);
 void rxrpc_kernel_probe_life(struct socket *, struct rxrpc_call *);
 u32 rxrpc_kernel_get_epoch(struct socket *, struct rxrpc_call *);
 bool rxrpc_kernel_get_reply_time(struct socket *, struct rxrpc_call *,
 				 ktime_t *);
+bool rxrpc_kernel_call_is_complete(struct rxrpc_call *);
 
 #endif /* _NET_RXRPC_H */
diff --git a/include/net/cfg80211.h b/include/net/cfg80211.h
index bb307a11ee63..13bfeb712d36 100644
--- a/include/net/cfg80211.h
+++ b/include/net/cfg80211.h
@@ -7183,6 +7183,11 @@ void cfg80211_pmsr_complete(struct wireless_dev *wdev,
 #define wiphy_info(wiphy, format, args...)			\
 	dev_info(&(wiphy)->dev, format, ##args)
 
+#define wiphy_err_ratelimited(wiphy, format, args...)		\
+	dev_err_ratelimited(&(wiphy)->dev, format, ##args)
+#define wiphy_warn_ratelimited(wiphy, format, args...)		\
+	dev_warn_ratelimited(&(wiphy)->dev, format, ##args)
+
 #define wiphy_debug(wiphy, format, args...)			\
 	wiphy_printk(KERN_DEBUG, wiphy, format, ##args)
 
diff --git a/include/net/ip.h b/include/net/ip.h
index be3cad9c2e4c..583526aad1d0 100644
--- a/include/net/ip.h
+++ b/include/net/ip.h
@@ -677,7 +677,7 @@ int ip_options_get_from_user(struct net *net, struct ip_options_rcu **optp,
 			     unsigned char __user *data, int optlen);
 void ip_options_undo(struct ip_options *opt);
 void ip_forward_options(struct sk_buff *skb);
-int ip_options_rcv_srr(struct sk_buff *skb);
+int ip_options_rcv_srr(struct sk_buff *skb, struct net_device *dev);
 
 /*
  *	Functions provided by ip_sockglue.c
diff --git a/include/net/mac80211.h b/include/net/mac80211.h
index ac2ed8ec662b..112dc18c658f 100644
--- a/include/net/mac80211.h
+++ b/include/net/mac80211.h
@@ -6231,8 +6231,6 @@ struct sk_buff *ieee80211_tx_dequeue(struct ieee80211_hw *hw,
  * @hw: pointer as obtained from ieee80211_alloc_hw()
  * @ac: AC number to return packets from.
  *
- * Should only be called between calls to ieee80211_txq_schedule_start()
- * and ieee80211_txq_schedule_end().
  * Returns the next txq if successful, %NULL if no queue is eligible. If a txq
  * is returned, it should be returned with ieee80211_return_txq() after the
  * driver has finished scheduling it.
@@ -6240,51 +6238,58 @@ struct sk_buff *ieee80211_tx_dequeue(struct ieee80211_hw *hw,
 struct ieee80211_txq *ieee80211_next_txq(struct ieee80211_hw *hw, u8 ac);
 
 /**
- * ieee80211_return_txq - return a TXQ previously acquired by ieee80211_next_txq()
- *
- * @hw: pointer as obtained from ieee80211_alloc_hw()
- * @txq: pointer obtained from station or virtual interface
- *
- * Should only be called between calls to ieee80211_txq_schedule_start()
- * and ieee80211_txq_schedule_end().
- */
-void ieee80211_return_txq(struct ieee80211_hw *hw, struct ieee80211_txq *txq);
-
-/**
- * ieee80211_txq_schedule_start - acquire locks for safe scheduling of an AC
+ * ieee80211_txq_schedule_start - start new scheduling round for TXQs
  *
  * @hw: pointer as obtained from ieee80211_alloc_hw()
  * @ac: AC number to acquire locks for
  *
- * Acquire locks needed to schedule TXQs from the given AC. Should be called
- * before ieee80211_next_txq() or ieee80211_return_txq().
+ * Should be called before ieee80211_next_txq() or ieee80211_return_txq().
+ * The driver must not call multiple TXQ scheduling rounds concurrently.
  */
-void ieee80211_txq_schedule_start(struct ieee80211_hw *hw, u8 ac)
-	__acquires(txq_lock);
+void ieee80211_txq_schedule_start(struct ieee80211_hw *hw, u8 ac);
+
+/* (deprecated) */
+static inline void ieee80211_txq_schedule_end(struct ieee80211_hw *hw, u8 ac)
+{
+}
+
+void __ieee80211_schedule_txq(struct ieee80211_hw *hw,
+			      struct ieee80211_txq *txq, bool force);
 
 /**
- * ieee80211_txq_schedule_end - release locks for safe scheduling of an AC
+ * ieee80211_schedule_txq - schedule a TXQ for transmission
  *
  * @hw: pointer as obtained from ieee80211_alloc_hw()
- * @ac: AC number to acquire locks for
+ * @txq: pointer obtained from station or virtual interface
  *
- * Release locks previously acquired by ieee80211_txq_schedule_end().
+ * Schedules a TXQ for transmission if it is not already scheduled,
+ * even if mac80211 does not have any packets buffered.
+ *
+ * The driver may call this function if it has buffered packets for
+ * this TXQ internally.
  */
-void ieee80211_txq_schedule_end(struct ieee80211_hw *hw, u8 ac)
-	__releases(txq_lock);
+static inline void
+ieee80211_schedule_txq(struct ieee80211_hw *hw, struct ieee80211_txq *txq)
+{
+	__ieee80211_schedule_txq(hw, txq, true);
+}
 
 /**
- * ieee80211_schedule_txq - schedule a TXQ for transmission
+ * ieee80211_return_txq - return a TXQ previously acquired by ieee80211_next_txq()
  *
  * @hw: pointer as obtained from ieee80211_alloc_hw()
  * @txq: pointer obtained from station or virtual interface
+ * @force: schedule txq even if mac80211 does not have any buffered packets.
  *
- * Schedules a TXQ for transmission if it is not already scheduled. Takes a
- * lock, which means it must *not* be called between
- * ieee80211_txq_schedule_start() and ieee80211_txq_schedule_end()
+ * The driver may set force=true if it has buffered packets for this TXQ
+ * internally.
  */
-void ieee80211_schedule_txq(struct ieee80211_hw *hw, struct ieee80211_txq *txq)
-	__acquires(txq_lock) __releases(txq_lock);
+static inline void
+ieee80211_return_txq(struct ieee80211_hw *hw, struct ieee80211_txq *txq,
+		     bool force)
+{
+	__ieee80211_schedule_txq(hw, txq, force);
+}
 
 /**
  * ieee80211_txq_may_transmit - check whether TXQ is allowed to transmit
diff --git a/include/net/net_namespace.h b/include/net/net_namespace.h
index a68ced28d8f4..12689ddfc24c 100644
--- a/include/net/net_namespace.h
+++ b/include/net/net_namespace.h
@@ -59,6 +59,7 @@ struct net {
 						 */
 	spinlock_t		rules_mod_lock;
 
+	u32			hash_mix;
 	atomic64_t		cookie_gen;
 
 	struct list_head	list;		/* list of network namespaces */
diff --git a/include/net/netfilter/nf_conntrack.h b/include/net/netfilter/nf_conntrack.h
index 5ee7b30b4917..d2bc733a2ef1 100644
--- a/include/net/netfilter/nf_conntrack.h
+++ b/include/net/netfilter/nf_conntrack.h
@@ -316,6 +316,8 @@ struct nf_conn *nf_ct_tmpl_alloc(struct net *net,
 				 gfp_t flags);
 void nf_ct_tmpl_free(struct nf_conn *tmpl);
 
+u32 nf_ct_get_id(const struct nf_conn *ct);
+
 static inline void
 nf_ct_set(struct sk_buff *skb, struct nf_conn *ct, enum ip_conntrack_info info)
 {
diff --git a/include/net/netfilter/nf_conntrack_l4proto.h b/include/net/netfilter/nf_conntrack_l4proto.h
index 778087591983..a49edfdf47e8 100644
--- a/include/net/netfilter/nf_conntrack_l4proto.h
+++ b/include/net/netfilter/nf_conntrack_l4proto.h
@@ -75,6 +75,12 @@ bool nf_conntrack_invert_icmp_tuple(struct nf_conntrack_tuple *tuple,
 bool nf_conntrack_invert_icmpv6_tuple(struct nf_conntrack_tuple *tuple,
 				      const struct nf_conntrack_tuple *orig);
 
+int nf_conntrack_inet_error(struct nf_conn *tmpl, struct sk_buff *skb,
+			    unsigned int dataoff,
+			    const struct nf_hook_state *state,
+			    u8 l4proto,
+			    union nf_inet_addr *outer_daddr);
+
 int nf_conntrack_icmpv4_error(struct nf_conn *tmpl,
 			      struct sk_buff *skb,
 			      unsigned int dataoff,
diff --git a/include/net/netns/hash.h b/include/net/netns/hash.h
index 16a842456189..d9b665151f3d 100644
--- a/include/net/netns/hash.h
+++ b/include/net/netns/hash.h
@@ -2,16 +2,10 @@
 #ifndef __NET_NS_HASH_H__
 #define __NET_NS_HASH_H__
 
-#include <asm/cache.h>
-
-struct net;
+#include <net/net_namespace.h>
 
 static inline u32 net_hash_mix(const struct net *net)
 {
-#ifdef CONFIG_NET_NS
-	return (u32)(((unsigned long)net) >> ilog2(sizeof(*net)));
-#else
-	return 0;
-#endif
+	return net->hash_mix;
 }
 #endif
diff --git a/include/net/netrom.h b/include/net/netrom.h
index 5a0714ff500f..80f15b1c1a48 100644
--- a/include/net/netrom.h
+++ b/include/net/netrom.h
@@ -266,7 +266,7 @@ void nr_stop_idletimer(struct sock *);
 int nr_t1timer_running(struct sock *);
 
 /* sysctl_net_netrom.c */
-void nr_register_sysctl(void);
+int nr_register_sysctl(void);
 void nr_unregister_sysctl(void);
 
 #endif
diff --git a/include/net/nfc/nci_core.h b/include/net/nfc/nci_core.h
index 87499b6b35d6..df5c69db68af 100644
--- a/include/net/nfc/nci_core.h
+++ b/include/net/nfc/nci_core.h
@@ -166,7 +166,7 @@ struct nci_conn_info {
  * According to specification 102 622 chapter 4.4 Pipes,
  * the pipe identifier is 7 bits long.
  */
-#define NCI_HCI_MAX_PIPES          127
+#define NCI_HCI_MAX_PIPES          128
 
 struct nci_hci_gate {
 	u8 gate;
diff --git a/include/net/sch_generic.h b/include/net/sch_generic.h
index 31284c078d06..a2b38b3deeca 100644
--- a/include/net/sch_generic.h
+++ b/include/net/sch_generic.h
@@ -378,6 +378,7 @@ struct tcf_chain {
 	bool flushing;
 	const struct tcf_proto_ops *tmplt_ops;
 	void *tmplt_priv;
+	struct rcu_head rcu;
 };
 
 struct tcf_block {
@@ -922,6 +923,41 @@ static inline void qdisc_qstats_overlimit(struct Qdisc *sch)
 	sch->qstats.overlimits++;
 }
 
+static inline int qdisc_qstats_copy(struct gnet_dump *d, struct Qdisc *sch)
+{
+	__u32 qlen = qdisc_qlen_sum(sch);
+
+	return gnet_stats_copy_queue(d, sch->cpu_qstats, &sch->qstats, qlen);
+}
+
+static inline void qdisc_qstats_qlen_backlog(struct Qdisc *sch,  __u32 *qlen,
+					     __u32 *backlog)
+{
+	struct gnet_stats_queue qstats = { 0 };
+	__u32 len = qdisc_qlen_sum(sch);
+
+	__gnet_stats_copy_queue(&qstats, sch->cpu_qstats, &sch->qstats, len);
+	*qlen = qstats.qlen;
+	*backlog = qstats.backlog;
+}
+
+static inline void qdisc_tree_flush_backlog(struct Qdisc *sch)
+{
+	__u32 qlen, backlog;
+
+	qdisc_qstats_qlen_backlog(sch, &qlen, &backlog);
+	qdisc_tree_reduce_backlog(sch, qlen, backlog);
+}
+
+static inline void qdisc_purge_queue(struct Qdisc *sch)
+{
+	__u32 qlen, backlog;
+
+	qdisc_qstats_qlen_backlog(sch, &qlen, &backlog);
+	qdisc_reset(sch);
+	qdisc_tree_reduce_backlog(sch, qlen, backlog);
+}
+
 static inline void qdisc_skb_head_init(struct qdisc_skb_head *qh)
 {
 	qh->head = NULL;
@@ -1105,13 +1141,8 @@ static inline struct Qdisc *qdisc_replace(struct Qdisc *sch, struct Qdisc *new,
 	sch_tree_lock(sch);
 	old = *pold;
 	*pold = new;
-	if (old != NULL) {
-		unsigned int qlen = old->q.qlen;
-		unsigned int backlog = old->qstats.backlog;
-
-		qdisc_reset(old);
-		qdisc_tree_reduce_backlog(old, qlen, backlog);
-	}
+	if (old != NULL)
+		qdisc_tree_flush_backlog(old);
 	sch_tree_unlock(sch);
 
 	return old;
diff --git a/include/net/sctp/checksum.h b/include/net/sctp/checksum.h
index 32ee65a30aff..1c6e6c0766ca 100644
--- a/include/net/sctp/checksum.h
+++ b/include/net/sctp/checksum.h
@@ -61,7 +61,7 @@ static inline __wsum sctp_csum_combine(__wsum csum, __wsum csum2,
 static inline __le32 sctp_compute_cksum(const struct sk_buff *skb,
 					unsigned int offset)
 {
-	struct sctphdr *sh = sctp_hdr(skb);
+	struct sctphdr *sh = (struct sctphdr *)(skb->data + offset);
 	const struct skb_checksum_ops ops = {
 		.update  = sctp_csum_update,
 		.combine = sctp_csum_combine,
diff --git a/include/net/sctp/command.h b/include/net/sctp/command.h
index 6640f84fe536..6d5beac29bc1 100644
--- a/include/net/sctp/command.h
+++ b/include/net/sctp/command.h
@@ -105,7 +105,6 @@ enum sctp_verb {
 	SCTP_CMD_T1_RETRAN,	 /* Mark for retransmission after T1 timeout  */
 	SCTP_CMD_UPDATE_INITTAG, /* Update peer inittag */
 	SCTP_CMD_SEND_MSG,	 /* Send the whole use message */
-	SCTP_CMD_SEND_NEXT_ASCONF, /* Send the next ASCONF after ACK */
 	SCTP_CMD_PURGE_ASCONF_QUEUE, /* Purge all asconf queues.*/
 	SCTP_CMD_SET_ASOC,	 /* Restore association context */
 	SCTP_CMD_LAST
diff --git a/include/net/sock.h b/include/net/sock.h
index 328cb7cb7b0b..341f8bafa0cf 100644
--- a/include/net/sock.h
+++ b/include/net/sock.h
@@ -710,6 +710,12 @@ static inline void sk_add_node_rcu(struct sock *sk, struct hlist_head *list)
 		hlist_add_head_rcu(&sk->sk_node, list);
 }
 
+static inline void sk_add_node_tail_rcu(struct sock *sk, struct hlist_head *list)
+{
+	sock_hold(sk);
+	hlist_add_tail_rcu(&sk->sk_node, list);
+}
+
 static inline void __sk_nulls_add_node_rcu(struct sock *sk, struct hlist_nulls_head *list)
 {
 	hlist_nulls_add_head_rcu(&sk->sk_nulls_node, list);
@@ -2078,12 +2084,6 @@ static inline bool skwq_has_sleeper(struct socket_wq *wq)
  * @p:              poll_table
  *
  * See the comments in the wq_has_sleeper function.
- *
- * Do not derive sock from filp->private_data here. An SMC socket establishes
- * an internal TCP socket that is used in the fallback case. All socket
- * operations on the SMC socket are then forwarded to the TCP socket. In case of
- * poll, the filp->private_data pointer references the SMC socket because the
- * TCP socket has no file assigned.
  */
 static inline void sock_poll_wait(struct file *filp, struct socket *sock,
 				  poll_table *p)
diff --git a/include/net/tc_act/tc_gact.h b/include/net/tc_act/tc_gact.h
index ee8d005f56fc..eb8f01c819e6 100644
--- a/include/net/tc_act/tc_gact.h
+++ b/include/net/tc_act/tc_gact.h
@@ -56,7 +56,7 @@ static inline bool is_tcf_gact_goto_chain(const struct tc_action *a)
 
 static inline u32 tcf_gact_goto_chain_index(const struct tc_action *a)
 {
-	return a->goto_chain->index;
+	return READ_ONCE(a->tcfa_action) & TC_ACT_EXT_VAL_MASK;
 }
 
 #endif /* __NET_TC_GACT_H */
diff --git a/include/net/tls.h b/include/net/tls.h
index a5a938583295..5934246b2c6f 100644
--- a/include/net/tls.h
+++ b/include/net/tls.h
@@ -307,6 +307,7 @@ int tls_device_sendmsg(struct sock *sk, struct msghdr *msg, size_t size);
 int tls_device_sendpage(struct sock *sk, struct page *page,
 			int offset, size_t size, int flags);
 void tls_device_sk_destruct(struct sock *sk);
+void tls_device_free_resources_tx(struct sock *sk);
 void tls_device_init(void);
 void tls_device_cleanup(void);
 int tls_tx_records(struct sock *sk, int flags);
@@ -330,6 +331,7 @@ int tls_push_sg(struct sock *sk, struct tls_context *ctx,
 		int flags);
 int tls_push_partial_record(struct sock *sk, struct tls_context *ctx,
 			    int flags);
+bool tls_free_partial_record(struct sock *sk, struct tls_context *ctx);
 
 static inline struct tls_msg *tls_msg(struct sk_buff *skb)
 {
@@ -379,7 +381,7 @@ tls_validate_xmit_skb(struct sock *sk, struct net_device *dev,
 static inline bool tls_is_sk_tx_device_offloaded(struct sock *sk)
 {
 #ifdef CONFIG_SOCK_VALIDATE_XMIT
-	return sk_fullsock(sk) &
+	return sk_fullsock(sk) &&
 	       (smp_load_acquire(&sk->sk_validate_xmit_skb) ==
 	       &tls_validate_xmit_skb);
 #else
diff --git a/include/net/xdp_sock.h b/include/net/xdp_sock.h
index 61cf7dbb6782..d074b6d60f8a 100644
--- a/include/net/xdp_sock.h
+++ b/include/net/xdp_sock.h
@@ -36,7 +36,6 @@ struct xdp_umem {
 	u32 headroom;
 	u32 chunk_size_nohr;
 	struct user_struct *user;
-	struct pid *pid;
 	unsigned long address;
 	refcount_t users;
 	struct work_struct work;
diff --git a/include/net/xfrm.h b/include/net/xfrm.h
index 85386becbaea..99f722c4d804 100644
--- a/include/net/xfrm.h
+++ b/include/net/xfrm.h
@@ -219,7 +219,7 @@ struct xfrm_state {
 	struct xfrm_stats	stats;
 
 	struct xfrm_lifetime_cur curlft;
-	struct tasklet_hrtimer	mtimer;
+	struct hrtimer		mtimer;
 
 	struct xfrm_state_offload xso;
 
@@ -295,7 +295,8 @@ struct xfrm_replay {
 };
 
 struct xfrm_if_cb {
-	struct xfrm_if	*(*decode_session)(struct sk_buff *skb);
+	struct xfrm_if	*(*decode_session)(struct sk_buff *skb,
+					   unsigned short family);
 };
 
 void xfrm_if_register_cb(const struct xfrm_if_cb *ifcb);
@@ -1404,6 +1405,23 @@ static inline int xfrm_state_kern(const struct xfrm_state *x)
 	return atomic_read(&x->tunnel_users);
 }
 
+static inline bool xfrm_id_proto_valid(u8 proto)
+{
+	switch (proto) {
+	case IPPROTO_AH:
+	case IPPROTO_ESP:
+	case IPPROTO_COMP:
+#if IS_ENABLED(CONFIG_IPV6)
+	case IPPROTO_ROUTING:
+	case IPPROTO_DSTOPTS:
+#endif
+		return true;
+	default:
+		return false;
+	}
+}
+
+/* IPSEC_PROTO_ANY only matches 3 IPsec protocols, 0 could match all. */
 static inline int xfrm_id_proto_match(u8 proto, u8 userproto)
 {
 	return (!userproto || proto == userproto ||
diff --git a/include/soc/rockchip/rk3399_grf.h b/include/soc/rockchip/rk3399_grf.h
new file mode 100644
index 000000000000..3eebabcb2812
--- /dev/null
+++ b/include/soc/rockchip/rk3399_grf.h
@@ -0,0 +1,21 @@
+/* SPDX-License-Identifier: GPL-2.0+ */
+/*
+ * Rockchip General Register Files definitions
+ *
+ * Copyright (c) 2018, Collabora Ltd.
+ * Author: Enric Balletbo i Serra <enric.balletbo@collabora.com>
+ */
+
+#ifndef __SOC_RK3399_GRF_H
+#define __SOC_RK3399_GRF_H
+
+/* PMU GRF Registers */
+#define RK3399_PMUGRF_OS_REG2		0x308
+#define RK3399_PMUGRF_DDRTYPE_SHIFT	13
+#define RK3399_PMUGRF_DDRTYPE_MASK	7
+#define RK3399_PMUGRF_DDRTYPE_DDR3	3
+#define RK3399_PMUGRF_DDRTYPE_LPDDR2	5
+#define RK3399_PMUGRF_DDRTYPE_LPDDR3	6
+#define RK3399_PMUGRF_DDRTYPE_LPDDR4	7
+
+#endif
diff --git a/include/soc/rockchip/rockchip_sip.h b/include/soc/rockchip/rockchip_sip.h
index 7e28092c4d3d..ad9482c56797 100644
--- a/include/soc/rockchip/rockchip_sip.h
+++ b/include/soc/rockchip/rockchip_sip.h
@@ -23,5 +23,6 @@
 #define ROCKCHIP_SIP_CONFIG_DRAM_GET_RATE	0x05
 #define ROCKCHIP_SIP_CONFIG_DRAM_CLR_IRQ	0x06
 #define ROCKCHIP_SIP_CONFIG_DRAM_SET_PARAM	0x07
+#define ROCKCHIP_SIP_CONFIG_DRAM_SET_ODT_PD	0x08
 
 #endif
diff --git a/include/sound/soc.h b/include/sound/soc.h
index eb7db605955b..482b4ea87c3c 100644
--- a/include/sound/soc.h
+++ b/include/sound/soc.h
@@ -802,8 +802,13 @@ struct snd_soc_component_driver {
 	int probe_order;
 	int remove_order;
 
-	/* signal if the module handling the component cannot be removed */
-	unsigned int ignore_module_refcount:1;
+	/*
+	 * signal if the module handling the component should not be removed
+	 * if a pcm is open. Setting this would prevent the module
+	 * refcount being incremented in probe() but allow it be incremented
+	 * when a pcm is opened and decremented when it is closed.
+	 */
+	unsigned int module_get_upon_open:1;
 
 	/* bits */
 	unsigned int idle_bias_on:1;
@@ -1083,6 +1088,8 @@ struct snd_soc_card {
 	struct mutex mutex;
 	struct mutex dapm_mutex;
 
+	spinlock_t dpcm_lock;
+
 	bool instantiated;
 	bool topology_shortname_created;
 
diff --git a/include/trace/events/devfreq.h b/include/trace/events/devfreq.h
new file mode 100644
index 000000000000..cf5b8772175d
--- /dev/null
+++ b/include/trace/events/devfreq.h
@@ -0,0 +1,40 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#undef TRACE_SYSTEM
+#define TRACE_SYSTEM devfreq
+
+#if !defined(_TRACE_DEVFREQ_H) || defined(TRACE_HEADER_MULTI_READ)
+#define _TRACE_DEVFREQ_H
+
+#include <linux/devfreq.h>
+#include <linux/tracepoint.h>
+
+TRACE_EVENT(devfreq_monitor,
+	TP_PROTO(struct devfreq *devfreq),
+
+	TP_ARGS(devfreq),
+
+	TP_STRUCT__entry(
+		__field(unsigned long, freq)
+		__field(unsigned long, busy_time)
+		__field(unsigned long, total_time)
+		__field(unsigned int, polling_ms)
+		__string(dev_name, dev_name(&devfreq->dev))
+	),
+
+	TP_fast_assign(
+		__entry->freq = devfreq->previous_freq;
+		__entry->busy_time = devfreq->last_status.busy_time;
+		__entry->total_time = devfreq->last_status.total_time;
+		__entry->polling_ms = devfreq->profile->polling_ms;
+		__assign_str(dev_name, dev_name(&devfreq->dev));
+	),
+
+	TP_printk("dev_name=%s freq=%lu polling_ms=%u load=%lu",
+		__get_str(dev_name), __entry->freq, __entry->polling_ms,
+		__entry->total_time == 0 ? 0 :
+			(100 * __entry->busy_time) / __entry->total_time)
+);
+#endif /* _TRACE_DEVFREQ_H */
+
+/* This part must be outside protection */
+#include <trace/define_trace.h>
diff --git a/include/trace/events/spi.h b/include/trace/events/spi.h
index aef6869f563d..0dd9171d2ad8 100644
--- a/include/trace/events/spi.h
+++ b/include/trace/events/spi.h
@@ -131,9 +131,11 @@ DECLARE_EVENT_CLASS(spi_transfer,
 		__field(        struct spi_transfer *,   xfer   )
 		__field(        int,            len             )
 		__dynamic_array(u8, rx_buf,
-				spi_valid_rxbuf(msg, xfer) ? xfer->len : 0)
+				spi_valid_rxbuf(msg, xfer) ?
+					(xfer->len < 64 ? xfer->len : 64) : 0)
 		__dynamic_array(u8, tx_buf,
-				spi_valid_txbuf(msg, xfer) ? xfer->len : 0)
+				spi_valid_txbuf(msg, xfer) ?
+					(xfer->len < 64 ? xfer->len : 64) : 0)
 	),
 
 	TP_fast_assign(
@@ -144,11 +146,11 @@ DECLARE_EVENT_CLASS(spi_transfer,
 
 		if (spi_valid_txbuf(msg, xfer))
 			memcpy(__get_dynamic_array(tx_buf),
-			       xfer->tx_buf, xfer->len);
+			       xfer->tx_buf, __get_dynamic_array_len(tx_buf));
 
 		if (spi_valid_rxbuf(msg, xfer))
 			memcpy(__get_dynamic_array(rx_buf),
-			       xfer->rx_buf, xfer->len);
+			       xfer->rx_buf, __get_dynamic_array_len(rx_buf));
 	),
 
 	TP_printk("spi%d.%d %p len=%d tx=[%*phD] rx=[%*phD]",
diff --git a/include/trace/events/syscalls.h b/include/trace/events/syscalls.h
index 44a3259ed4a5..b6e0cbc2c71f 100644
--- a/include/trace/events/syscalls.h
+++ b/include/trace/events/syscalls.h
@@ -28,7 +28,7 @@ TRACE_EVENT_FN(sys_enter,
 
 	TP_fast_assign(
 		__entry->id	= id;
-		syscall_get_arguments(current, regs, 0, 6, __entry->args);
+		syscall_get_arguments(current, regs, __entry->args);
 	),
 
 	TP_printk("NR %ld (%lx, %lx, %lx, %lx, %lx, %lx)",
diff --git a/include/trace/events/timer.h b/include/trace/events/timer.h
index a57e4ee989d6..b7a904825e7d 100644
--- a/include/trace/events/timer.h
+++ b/include/trace/events/timer.h
@@ -73,7 +73,7 @@ TRACE_EVENT(timer_start,
 		__entry->flags		= flags;
 	),
 
-	TP_printk("timer=%p function=%pf expires=%lu [timeout=%ld] cpu=%u idx=%u flags=%s",
+	TP_printk("timer=%p function=%ps expires=%lu [timeout=%ld] cpu=%u idx=%u flags=%s",
 		  __entry->timer, __entry->function, __entry->expires,
 		  (long)__entry->expires - __entry->now,
 		  __entry->flags & TIMER_CPUMASK,
@@ -89,23 +89,27 @@ TRACE_EVENT(timer_start,
  */
 TRACE_EVENT(timer_expire_entry,
 
-	TP_PROTO(struct timer_list *timer),
+	TP_PROTO(struct timer_list *timer, unsigned long baseclk),
 
-	TP_ARGS(timer),
+	TP_ARGS(timer, baseclk),
 
 	TP_STRUCT__entry(
 		__field( void *,	timer	)
 		__field( unsigned long,	now	)
 		__field( void *,	function)
+		__field( unsigned long,	baseclk	)
 	),
 
 	TP_fast_assign(
 		__entry->timer		= timer;
 		__entry->now		= jiffies;
 		__entry->function	= timer->function;
+		__entry->baseclk	= baseclk;
 	),
 
-	TP_printk("timer=%p function=%pf now=%lu", __entry->timer, __entry->function,__entry->now)
+	TP_printk("timer=%p function=%ps now=%lu baseclk=%lu",
+		  __entry->timer, __entry->function, __entry->now,
+		  __entry->baseclk)
 );
 
 /**
@@ -210,7 +214,7 @@ TRACE_EVENT(hrtimer_start,
 		__entry->mode		= mode;
 	),
 
-	TP_printk("hrtimer=%p function=%pf expires=%llu softexpires=%llu "
+	TP_printk("hrtimer=%p function=%ps expires=%llu softexpires=%llu "
 		  "mode=%s", __entry->hrtimer, __entry->function,
 		  (unsigned long long) __entry->expires,
 		  (unsigned long long) __entry->softexpires,
@@ -243,7 +247,8 @@ TRACE_EVENT(hrtimer_expire_entry,
 		__entry->function	= hrtimer->function;
 	),
 
-	TP_printk("hrtimer=%p function=%pf now=%llu", __entry->hrtimer, __entry->function,
+	TP_printk("hrtimer=%p function=%ps now=%llu",
+		  __entry->hrtimer, __entry->function,
 		  (unsigned long long) __entry->now)
 );
 
diff --git a/include/uapi/linux/Kbuild b/include/uapi/linux/Kbuild
index 5f24b50c9e88..059dc2bedaf6 100644
--- a/include/uapi/linux/Kbuild
+++ b/include/uapi/linux/Kbuild
@@ -7,5 +7,7 @@ no-export-headers += kvm.h
 endif
 
 ifeq ($(wildcard $(srctree)/arch/$(SRCARCH)/include/uapi/asm/kvm_para.h),)
+ifeq ($(wildcard $(objtree)/arch/$(SRCARCH)/include/generated/uapi/asm/kvm_para.h),)
 no-export-headers += kvm_para.h
 endif
+endif
diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h
index 3c38ac9a92a7..929c8e537a14 100644
--- a/include/uapi/linux/bpf.h
+++ b/include/uapi/linux/bpf.h
@@ -502,16 +502,6 @@ union bpf_attr {
  * 	Return
  * 		0 on success, or a negative error in case of failure.
  *
- * int bpf_map_push_elem(struct bpf_map *map, const void *value, u64 flags)
- * 	Description
- * 		Push an element *value* in *map*. *flags* is one of:
- *
- * 		**BPF_EXIST**
- * 		If the queue/stack is full, the oldest element is removed to
- * 		make room for this.
- * 	Return
- * 		0 on success, or a negative error in case of failure.
- *
  * int bpf_probe_read(void *dst, u32 size, const void *src)
  * 	Description
  * 		For tracing programs, safely attempt to read *size* bytes from
@@ -1435,14 +1425,14 @@ union bpf_attr {
  * u64 bpf_get_socket_cookie(struct bpf_sock_addr *ctx)
  * 	Description
  * 		Equivalent to bpf_get_socket_cookie() helper that accepts
- * 		*skb*, but gets socket from **struct bpf_sock_addr** contex.
+ * 		*skb*, but gets socket from **struct bpf_sock_addr** context.
  * 	Return
  * 		A 8-byte long non-decreasing number.
  *
  * u64 bpf_get_socket_cookie(struct bpf_sock_ops *ctx)
  * 	Description
  * 		Equivalent to bpf_get_socket_cookie() helper that accepts
- * 		*skb*, but gets socket from **struct bpf_sock_ops** contex.
+ * 		*skb*, but gets socket from **struct bpf_sock_ops** context.
  * 	Return
  * 		A 8-byte long non-decreasing number.
  *
@@ -2098,52 +2088,52 @@ union bpf_attr {
  *	Return
  * 		0 on success, or a negative error in case of failure.
  *
- * int bpf_rc_keydown(void *ctx, u32 protocol, u64 scancode, u32 toggle)
+ * int bpf_rc_repeat(void *ctx)
  *	Description
  *		This helper is used in programs implementing IR decoding, to
- *		report a successfully decoded key press with *scancode*,
- *		*toggle* value in the given *protocol*. The scancode will be
- *		translated to a keycode using the rc keymap, and reported as
- *		an input key down event. After a period a key up event is
- *		generated. This period can be extended by calling either
- *		**bpf_rc_keydown**\ () again with the same values, or calling
- *		**bpf_rc_repeat**\ ().
+ *		report a successfully decoded repeat key message. This delays
+ *		the generation of a key up event for previously generated
+ *		key down event.
  *
- *		Some protocols include a toggle bit, in case the button	was
- *		released and pressed again between consecutive scancodes.
+ *		Some IR protocols like NEC have a special IR message for
+ *		repeating last button, for when a button is held down.
  *
  *		The *ctx* should point to the lirc sample as passed into
  *		the program.
  *
- *		The *protocol* is the decoded protocol number (see
- *		**enum rc_proto** for some predefined values).
- *
  *		This helper is only available is the kernel was compiled with
  *		the **CONFIG_BPF_LIRC_MODE2** configuration option set to
  *		"**y**".
  *	Return
  *		0
  *
- * int bpf_rc_repeat(void *ctx)
+ * int bpf_rc_keydown(void *ctx, u32 protocol, u64 scancode, u32 toggle)
  *	Description
  *		This helper is used in programs implementing IR decoding, to
- *		report a successfully decoded repeat key message. This delays
- *		the generation of a key up event for previously generated
- *		key down event.
+ *		report a successfully decoded key press with *scancode*,
+ *		*toggle* value in the given *protocol*. The scancode will be
+ *		translated to a keycode using the rc keymap, and reported as
+ *		an input key down event. After a period a key up event is
+ *		generated. This period can be extended by calling either
+ *		**bpf_rc_keydown**\ () again with the same values, or calling
+ *		**bpf_rc_repeat**\ ().
  *
- *		Some IR protocols like NEC have a special IR message for
- *		repeating last button, for when a button is held down.
+ *		Some protocols include a toggle bit, in case the button	was
+ *		released and pressed again between consecutive scancodes.
  *
  *		The *ctx* should point to the lirc sample as passed into
  *		the program.
  *
+ *		The *protocol* is the decoded protocol number (see
+ *		**enum rc_proto** for some predefined values).
+ *
  *		This helper is only available is the kernel was compiled with
  *		the **CONFIG_BPF_LIRC_MODE2** configuration option set to
  *		"**y**".
  *	Return
  *		0
  *
- * uint64_t bpf_skb_cgroup_id(struct sk_buff *skb)
+ * u64 bpf_skb_cgroup_id(struct sk_buff *skb)
  * 	Description
  * 		Return the cgroup v2 id of the socket associated with the *skb*.
  * 		This is roughly similar to the **bpf_get_cgroup_classid**\ ()
@@ -2159,30 +2149,12 @@ union bpf_attr {
  * 	Return
  * 		The id is returned or 0 in case the id could not be retrieved.
  *
- * u64 bpf_skb_ancestor_cgroup_id(struct sk_buff *skb, int ancestor_level)
- *	Description
- *		Return id of cgroup v2 that is ancestor of cgroup associated
- *		with the *skb* at the *ancestor_level*.  The root cgroup is at
- *		*ancestor_level* zero and each step down the hierarchy
- *		increments the level. If *ancestor_level* == level of cgroup
- *		associated with *skb*, then return value will be same as that
- *		of **bpf_skb_cgroup_id**\ ().
- *
- *		The helper is useful to implement policies based on cgroups
- *		that are upper in hierarchy than immediate cgroup associated
- *		with *skb*.
- *
- *		The format of returned id and helper limitations are same as in
- *		**bpf_skb_cgroup_id**\ ().
- *	Return
- *		The id is returned or 0 in case the id could not be retrieved.
- *
  * u64 bpf_get_current_cgroup_id(void)
  * 	Return
  * 		A 64-bit integer containing the current cgroup id based
  * 		on the cgroup within which the current task is running.
  *
- * void* get_local_storage(void *map, u64 flags)
+ * void *bpf_get_local_storage(void *map, u64 flags)
  *	Description
  *		Get the pointer to the local storage area.
  *		The type and the size of the local storage is defined
@@ -2209,6 +2181,24 @@ union bpf_attr {
  *	Return
  *		0 on success, or a negative error in case of failure.
  *
+ * u64 bpf_skb_ancestor_cgroup_id(struct sk_buff *skb, int ancestor_level)
+ *	Description
+ *		Return id of cgroup v2 that is ancestor of cgroup associated
+ *		with the *skb* at the *ancestor_level*.  The root cgroup is at
+ *		*ancestor_level* zero and each step down the hierarchy
+ *		increments the level. If *ancestor_level* == level of cgroup
+ *		associated with *skb*, then return value will be same as that
+ *		of **bpf_skb_cgroup_id**\ ().
+ *
+ *		The helper is useful to implement policies based on cgroups
+ *		that are upper in hierarchy than immediate cgroup associated
+ *		with *skb*.
+ *
+ *		The format of returned id and helper limitations are same as in
+ *		**bpf_skb_cgroup_id**\ ().
+ *	Return
+ *		The id is returned or 0 in case the id could not be retrieved.
+ *
  * struct bpf_sock *bpf_sk_lookup_tcp(void *ctx, struct bpf_sock_tuple *tuple, u32 tuple_size, u64 netns, u64 flags)
  *	Description
  *		Look for TCP socket matching *tuple*, optionally in a child
@@ -2289,6 +2279,16 @@ union bpf_attr {
  *	Return
  *		0 on success, or a negative error in case of failure.
  *
+ * int bpf_map_push_elem(struct bpf_map *map, const void *value, u64 flags)
+ * 	Description
+ * 		Push an element *value* in *map*. *flags* is one of:
+ *
+ * 		**BPF_EXIST**
+ * 			If the queue/stack is full, the oldest element is
+ * 			removed to make room for this.
+ * 	Return
+ * 		0 on success, or a negative error in case of failure.
+ *
  * int bpf_map_pop_elem(struct bpf_map *map, void *value)
  * 	Description
  * 		Pop an element from *map*.
@@ -2343,29 +2343,94 @@ union bpf_attr {
  *	Return
  *		0
  *
+ * int bpf_spin_lock(struct bpf_spin_lock *lock)
+ *	Description
+ *		Acquire a spinlock represented by the pointer *lock*, which is
+ *		stored as part of a value of a map. Taking the lock allows to
+ *		safely update the rest of the fields in that value. The
+ *		spinlock can (and must) later be released with a call to
+ *		**bpf_spin_unlock**\ (\ *lock*\ ).
+ *
+ *		Spinlocks in BPF programs come with a number of restrictions
+ *		and constraints:
+ *
+ *		* **bpf_spin_lock** objects are only allowed inside maps of
+ *		  types **BPF_MAP_TYPE_HASH** and **BPF_MAP_TYPE_ARRAY** (this
+ *		  list could be extended in the future).
+ *		* BTF description of the map is mandatory.
+ *		* The BPF program can take ONE lock at a time, since taking two
+ *		  or more could cause dead locks.
+ *		* Only one **struct bpf_spin_lock** is allowed per map element.
+ *		* When the lock is taken, calls (either BPF to BPF or helpers)
+ *		  are not allowed.
+ *		* The **BPF_LD_ABS** and **BPF_LD_IND** instructions are not
+ *		  allowed inside a spinlock-ed region.
+ *		* The BPF program MUST call **bpf_spin_unlock**\ () to release
+ *		  the lock, on all execution paths, before it returns.
+ *		* The BPF program can access **struct bpf_spin_lock** only via
+ *		  the **bpf_spin_lock**\ () and **bpf_spin_unlock**\ ()
+ *		  helpers. Loading or storing data into the **struct
+ *		  bpf_spin_lock** *lock*\ **;** field of a map is not allowed.
+ *		* To use the **bpf_spin_lock**\ () helper, the BTF description
+ *		  of the map value must be a struct and have **struct
+ *		  bpf_spin_lock** *anyname*\ **;** field at the top level.
+ *		  Nested lock inside another struct is not allowed.
+ *		* The **struct bpf_spin_lock** *lock* field in a map value must
+ *		  be aligned on a multiple of 4 bytes in that value.
+ *		* Syscall with command **BPF_MAP_LOOKUP_ELEM** does not copy
+ *		  the **bpf_spin_lock** field to user space.
+ *		* Syscall with command **BPF_MAP_UPDATE_ELEM**, or update from
+ *		  a BPF program, do not update the **bpf_spin_lock** field.
+ *		* **bpf_spin_lock** cannot be on the stack or inside a
+ *		  networking packet (it can only be inside of a map values).
+ *		* **bpf_spin_lock** is available to root only.
+ *		* Tracing programs and socket filter programs cannot use
+ *		  **bpf_spin_lock**\ () due to insufficient preemption checks
+ *		  (but this may change in the future).
+ *		* **bpf_spin_lock** is not allowed in inner maps of map-in-map.
+ *	Return
+ *		0
+ *
+ * int bpf_spin_unlock(struct bpf_spin_lock *lock)
+ *	Description
+ *		Release the *lock* previously locked by a call to
+ *		**bpf_spin_lock**\ (\ *lock*\ ).
+ *	Return
+ *		0
+ *
  * struct bpf_sock *bpf_sk_fullsock(struct bpf_sock *sk)
  *	Description
  *		This helper gets a **struct bpf_sock** pointer such
- *		that all the fields in bpf_sock can be accessed.
+ *		that all the fields in this **bpf_sock** can be accessed.
  *	Return
- *		A **struct bpf_sock** pointer on success, or NULL in
+ *		A **struct bpf_sock** pointer on success, or **NULL** in
  *		case of failure.
  *
  * struct bpf_tcp_sock *bpf_tcp_sock(struct bpf_sock *sk)
  *	Description
  *		This helper gets a **struct bpf_tcp_sock** pointer from a
  *		**struct bpf_sock** pointer.
- *
  *	Return
- *		A **struct bpf_tcp_sock** pointer on success, or NULL in
+ *		A **struct bpf_tcp_sock** pointer on success, or **NULL** in
  *		case of failure.
  *
  * int bpf_skb_ecn_set_ce(struct sk_buf *skb)
- *     Description
- *             Sets ECN of IP header to ce (congestion encountered) if
- *             current value is ect (ECN capable). Works with IPv6 and IPv4.
- *     Return
- *             1 if set, 0 if not set.
+ *	Description
+ *		Set ECN (Explicit Congestion Notification) field of IP header
+ *		to **CE** (Congestion Encountered) if current value is **ECT**
+ *		(ECN Capable Transport). Otherwise, do nothing. Works with IPv6
+ *		and IPv4.
+ *	Return
+ *		1 if the **CE** flag is set (either by the current helper call
+ *		or because it was already present), 0 if it is not set.
+ *
+ * struct bpf_sock *bpf_get_listener_sock(struct bpf_sock *sk)
+ *	Description
+ *		Return a **struct bpf_sock** pointer in **TCP_LISTEN** state.
+ *		**bpf_sk_release**\ () is unnecessary and not allowed.
+ *	Return
+ *		A **struct bpf_sock** pointer on success, or **NULL** in
+ *		case of failure.
  */
 #define __BPF_FUNC_MAPPER(FN)		\
 	FN(unspec),			\
@@ -2465,7 +2530,8 @@ union bpf_attr {
 	FN(spin_unlock),		\
 	FN(sk_fullsock),		\
 	FN(tcp_sock),			\
-	FN(skb_ecn_set_ce),
+	FN(skb_ecn_set_ce),		\
+	FN(get_listener_sock),
 
 /* integer value in 'imm' field of BPF_CALL instruction selects which helper
  * function eBPF program intends to call
diff --git a/include/uapi/linux/ethtool.h b/include/uapi/linux/ethtool.h
index 3652b239dad1..d473e5ed044c 100644
--- a/include/uapi/linux/ethtool.h
+++ b/include/uapi/linux/ethtool.h
@@ -1591,7 +1591,7 @@ enum ethtool_link_mode_bit_indices {
 
 static inline int ethtool_validate_speed(__u32 speed)
 {
-	return speed <= INT_MAX || speed == SPEED_UNKNOWN;
+	return speed <= INT_MAX || speed == (__u32)SPEED_UNKNOWN;
 }
 
 /* Duplex, half or full. */
diff --git a/include/uapi/linux/input-event-codes.h b/include/uapi/linux/input-event-codes.h
index 7f14d4a66c28..64cee116928e 100644
--- a/include/uapi/linux/input-event-codes.h
+++ b/include/uapi/linux/input-event-codes.h
@@ -439,10 +439,12 @@
 #define KEY_TITLE		0x171
 #define KEY_SUBTITLE		0x172
 #define KEY_ANGLE		0x173
-#define KEY_ZOOM		0x174
+#define KEY_FULL_SCREEN		0x174	/* AC View Toggle */
+#define KEY_ZOOM		KEY_FULL_SCREEN
 #define KEY_MODE		0x175
 #define KEY_KEYBOARD		0x176
-#define KEY_SCREEN		0x177
+#define KEY_ASPECT_RATIO	0x177	/* HUTRR37: Aspect */
+#define KEY_SCREEN		KEY_ASPECT_RATIO
 #define KEY_PC			0x178	/* Media Select Computer */
 #define KEY_TV			0x179	/* Media Select TV */
 #define KEY_TV2			0x17a	/* Media Select Cable */
diff --git a/include/uapi/linux/psci.h b/include/uapi/linux/psci.h
index b3bcabe380da..2fcad1dd0b0e 100644
--- a/include/uapi/linux/psci.h
+++ b/include/uapi/linux/psci.h
@@ -49,8 +49,11 @@
 
 #define PSCI_1_0_FN_PSCI_FEATURES		PSCI_0_2_FN(10)
 #define PSCI_1_0_FN_SYSTEM_SUSPEND		PSCI_0_2_FN(14)
+#define PSCI_1_0_FN_SET_SUSPEND_MODE		PSCI_0_2_FN(15)
+#define PSCI_1_1_FN_SYSTEM_RESET2		PSCI_0_2_FN(18)
 
 #define PSCI_1_0_FN64_SYSTEM_SUSPEND		PSCI_0_2_FN64(14)
+#define PSCI_1_1_FN64_SYSTEM_RESET2		PSCI_0_2_FN64(18)
 
 /* PSCI v0.2 power state encoding for CPU_SUSPEND function */
 #define PSCI_0_2_POWER_STATE_ID_MASK		0xffff
@@ -97,6 +100,10 @@
 #define PSCI_1_0_FEATURES_CPU_SUSPEND_PF_MASK	\
 			(0x1 << PSCI_1_0_FEATURES_CPU_SUSPEND_PF_SHIFT)
 
+#define PSCI_1_0_OS_INITIATED			BIT(0)
+#define PSCI_1_0_SUSPEND_MODE_PC		0
+#define PSCI_1_0_SUSPEND_MODE_OSI		1
+
 /* PSCI return values (inclusive of all PSCI versions) */
 #define PSCI_RET_SUCCESS			0
 #define PSCI_RET_NOT_SUPPORTED			-1
diff --git a/include/uapi/linux/psp-sev.h b/include/uapi/linux/psp-sev.h
index ac8c60bcc83b..43521d500c2b 100644
--- a/include/uapi/linux/psp-sev.h
+++ b/include/uapi/linux/psp-sev.h
@@ -6,8 +6,7 @@
  *
  * Author: Brijesh Singh <brijesh.singh@amd.com>
  *
- * SEV spec 0.14 is available at:
- * http://support.amd.com/TechDocs/55766_SEV-KM%20API_Specification.pdf
+ * SEV API specification is available at: https://developer.amd.com/sev/
  *
  * This program is free software; you can redistribute it and/or modify
  * it under the terms of the GNU General Public License version 2 as
@@ -30,7 +29,8 @@ enum {
 	SEV_PDH_GEN,
 	SEV_PDH_CERT_EXPORT,
 	SEV_PEK_CERT_IMPORT,
-	SEV_GET_ID,
+	SEV_GET_ID,	/* This command is deprecated, use SEV_GET_ID2 */
+	SEV_GET_ID2,
 
 	SEV_MAX,
 };
@@ -125,7 +125,7 @@ struct sev_user_data_pdh_cert_export {
 } __packed;
 
 /**
- * struct sev_user_data_get_id - GET_ID command parameters
+ * struct sev_user_data_get_id - GET_ID command parameters (deprecated)
  *
  * @socket1: Buffer to pass unique ID of first socket
  * @socket2: Buffer to pass unique ID of second socket
@@ -136,6 +136,16 @@ struct sev_user_data_get_id {
 } __packed;
 
 /**
+ * struct sev_user_data_get_id2 - GET_ID command parameters
+ * @address: Buffer to store unique ID
+ * @length: length of the unique ID
+ */
+struct sev_user_data_get_id2 {
+	__u64 address;				/* In */
+	__u32 length;				/* In/Out */
+} __packed;
+
+/**
  * struct sev_issue_cmd - SEV ioctl parameters
  *
  * @cmd: SEV commands to execute
diff --git a/include/uapi/linux/spi/spidev.h b/include/uapi/linux/spi/spidev.h
index c4253f0090d8..ee0f2460bff6 100644
--- a/include/uapi/linux/spi/spidev.h
+++ b/include/uapi/linux/spi/spidev.h
@@ -66,6 +66,9 @@
  * @delay_usecs: If nonzero, how long to delay after the last bit transfer
  *	before optionally deselecting the device before the next transfer.
  * @cs_change: True to deselect device before starting the next transfer.
+ * @word_delay_usecs: If nonzero, how long to wait between words within one
+ *	transfer. This property needs explicit support in the SPI controller,
+ *	otherwise it is silently ignored.
  *
  * This structure is mapped directly to the kernel spi_transfer structure;
  * the fields have the same meanings, except of course that the pointers
@@ -100,7 +103,8 @@ struct spi_ioc_transfer {
 	__u8		cs_change;
 	__u8		tx_nbits;
 	__u8		rx_nbits;
-	__u16		pad;
+	__u8		word_delay_usecs;
+	__u8		pad;
 
 	/* If the contents of 'struct spi_ioc_transfer' ever change
 	 * incompatibly, then the ioctl number (currently 0) must change;
diff --git a/include/uapi/linux/vbox_vmmdev_types.h b/include/uapi/linux/vbox_vmmdev_types.h
index 0e68024f36c7..26f39816af14 100644
--- a/include/uapi/linux/vbox_vmmdev_types.h
+++ b/include/uapi/linux/vbox_vmmdev_types.h
@@ -102,6 +102,66 @@ enum vmmdev_request_type {
 #define VMMDEVREQ_HGCM_CALL VMMDEVREQ_HGCM_CALL32
 #endif
 
+/* vmmdev_request_header.requestor defines */
+
+/* Requestor user not given. */
+#define VMMDEV_REQUESTOR_USR_NOT_GIVEN                      0x00000000
+/* The kernel driver (vboxguest) is the requestor. */
+#define VMMDEV_REQUESTOR_USR_DRV                            0x00000001
+/* Some other kernel driver is the requestor. */
+#define VMMDEV_REQUESTOR_USR_DRV_OTHER                      0x00000002
+/* The root or a admin user is the requestor. */
+#define VMMDEV_REQUESTOR_USR_ROOT                           0x00000003
+/* Regular joe user is making the request. */
+#define VMMDEV_REQUESTOR_USR_USER                           0x00000006
+/* User classification mask. */
+#define VMMDEV_REQUESTOR_USR_MASK                           0x00000007
+
+/* Kernel mode request. Note this is 0, check for !USERMODE instead. */
+#define VMMDEV_REQUESTOR_KERNEL                             0x00000000
+/* User mode request. */
+#define VMMDEV_REQUESTOR_USERMODE                           0x00000008
+/* User or kernel mode classification mask. */
+#define VMMDEV_REQUESTOR_MODE_MASK                          0x00000008
+
+/* Don't know the physical console association of the requestor. */
+#define VMMDEV_REQUESTOR_CON_DONT_KNOW                      0x00000000
+/*
+ * The request originates with a process that is NOT associated with the
+ * physical console.
+ */
+#define VMMDEV_REQUESTOR_CON_NO                             0x00000010
+/* Requestor process is associated with the physical console. */
+#define VMMDEV_REQUESTOR_CON_YES                            0x00000020
+/* Console classification mask. */
+#define VMMDEV_REQUESTOR_CON_MASK                           0x00000030
+
+/* Requestor is member of special VirtualBox user group. */
+#define VMMDEV_REQUESTOR_GRP_VBOX                           0x00000080
+
+/* Note: trust level is for windows guests only, linux always uses not-given */
+/* Requestor trust level: Unspecified */
+#define VMMDEV_REQUESTOR_TRUST_NOT_GIVEN                    0x00000000
+/* Requestor trust level: Untrusted (SID S-1-16-0) */
+#define VMMDEV_REQUESTOR_TRUST_UNTRUSTED                    0x00001000
+/* Requestor trust level: Untrusted (SID S-1-16-4096) */
+#define VMMDEV_REQUESTOR_TRUST_LOW                          0x00002000
+/* Requestor trust level: Medium (SID S-1-16-8192) */
+#define VMMDEV_REQUESTOR_TRUST_MEDIUM                       0x00003000
+/* Requestor trust level: Medium plus (SID S-1-16-8448) */
+#define VMMDEV_REQUESTOR_TRUST_MEDIUM_PLUS                  0x00004000
+/* Requestor trust level: High (SID S-1-16-12288) */
+#define VMMDEV_REQUESTOR_TRUST_HIGH                         0x00005000
+/* Requestor trust level: System (SID S-1-16-16384) */
+#define VMMDEV_REQUESTOR_TRUST_SYSTEM                       0x00006000
+/* Requestor trust level >= Protected (SID S-1-16-20480, S-1-16-28672) */
+#define VMMDEV_REQUESTOR_TRUST_PROTECTED                    0x00007000
+/* Requestor trust level mask */
+#define VMMDEV_REQUESTOR_TRUST_MASK                         0x00007000
+
+/* Requestor is using the less trusted user device node (/dev/vboxuser) */
+#define VMMDEV_REQUESTOR_USER_DEVICE                        0x00008000
+
 /** HGCM service location types. */
 enum vmmdev_hgcm_service_location_type {
 	VMMDEV_HGCM_LOC_INVALID    = 0,
diff --git a/include/uapi/linux/vfio.h b/include/uapi/linux/vfio.h
index 02bb7ad6e986..8f10748dac79 100644
--- a/include/uapi/linux/vfio.h
+++ b/include/uapi/linux/vfio.h
@@ -353,6 +353,10 @@ struct vfio_region_gfx_edid {
 #define VFIO_DEVICE_GFX_LINK_STATE_DOWN  2
 };
 
+#define VFIO_REGION_TYPE_CCW			(2)
+/* ccw sub-types */
+#define VFIO_REGION_SUBTYPE_CCW_ASYNC_CMD	(1)
+
 /*
  * 10de vendor sub-type
  *
diff --git a/include/uapi/linux/vfio_ccw.h b/include/uapi/linux/vfio_ccw.h
index 2ec5f367ff78..cbecbf0cd54f 100644
--- a/include/uapi/linux/vfio_ccw.h
+++ b/include/uapi/linux/vfio_ccw.h
@@ -12,6 +12,7 @@
 
 #include <linux/types.h>
 
+/* used for START SUBCHANNEL, always present */
 struct ccw_io_region {
 #define ORB_AREA_SIZE 12
 	__u8	orb_area[ORB_AREA_SIZE];
@@ -22,4 +23,15 @@ struct ccw_io_region {
 	__u32	ret_code;
 } __packed;
 
+/*
+ * used for processing commands that trigger asynchronous actions
+ * Note: this is controlled by a capability
+ */
+#define VFIO_CCW_ASYNC_CMD_HSCH (1 << 0)
+#define VFIO_CCW_ASYNC_CMD_CSCH (1 << 1)
+struct ccw_cmd_region {
+	__u32 command;
+	__u32 ret_code;
+} __packed;
+
 #endif
diff --git a/include/uapi/rdma/mlx5-abi.h b/include/uapi/rdma/mlx5-abi.h
index 87b3198f4b5d..f4d4010b7e3e 100644
--- a/include/uapi/rdma/mlx5-abi.h
+++ b/include/uapi/rdma/mlx5-abi.h
@@ -238,6 +238,7 @@ enum mlx5_ib_query_dev_resp_flags {
 	MLX5_IB_QUERY_DEV_RESP_FLAGS_CQE_128B_COMP = 1 << 0,
 	MLX5_IB_QUERY_DEV_RESP_FLAGS_CQE_128B_PAD  = 1 << 1,
 	MLX5_IB_QUERY_DEV_RESP_PACKET_BASED_CREDIT_MODE = 1 << 2,
+	MLX5_IB_QUERY_DEV_RESP_FLAGS_SCAT2CQE_DCT = 1 << 3,
 };
 
 enum mlx5_ib_tunnel_offloads {
diff --git a/include/uapi/sound/asound.h b/include/uapi/sound/asound.h
index 404d4b9ffe76..df1153cea0b7 100644
--- a/include/uapi/sound/asound.h
+++ b/include/uapi/sound/asound.h
@@ -32,6 +32,7 @@
 
 #ifndef __KERNEL__
 #include <stdlib.h>
+#include <time.h>
 #endif
 
 /*
diff --git a/init/main.c b/init/main.c
index 598e278b46f7..9dc2f3b4f753 100644
--- a/init/main.c
+++ b/init/main.c
@@ -504,6 +504,10 @@ void __init __weak thread_stack_cache_init(void)
 
 void __init __weak mem_encrypt_init(void) { }
 
+void __init __weak poking_init(void) { }
+
+void __init __weak pgd_cache_init(void) { }
+
 bool initcall_debug;
 core_param(initcall_debug, initcall_debug, bool, 0644);
 
@@ -535,6 +539,7 @@ static void __init mm_init(void)
 	init_espfix_bsp();
 	/* Should be run after espfix64 is set up. */
 	pti_init();
+	pgd_cache_init();
 }
 
 void __init __weak arch_call_rest_init(void)
@@ -582,6 +587,8 @@ asmlinkage __visible void __init start_kernel(void)
 	page_alloc_init();
 
 	pr_notice("Kernel command line: %s\n", boot_command_line);
+	/* parameters may set static keys */
+	jump_label_init();
 	parse_early_param();
 	after_dashes = parse_args("Booting kernel",
 				  static_command_line, __start___param,
@@ -591,8 +598,6 @@ asmlinkage __visible void __init start_kernel(void)
 		parse_args("Setting init args", after_dashes, NULL, 0, -1, -1,
 			   NULL, set_init_arg);
 
-	jump_label_init();
-
 	/*
 	 * These use large bootmem allocations and must precede
 	 * kmem_cache_init()
@@ -737,6 +742,7 @@ asmlinkage __visible void __init start_kernel(void)
 	taskstats_init_early();
 	delayacct_init();
 
+	poking_init();
 	check_bugs();
 
 	acpi_subsystem_init();
diff --git a/kernel/Kconfig.locks b/kernel/Kconfig.locks
index fbba478ae522..bf770d7556f7 100644
--- a/kernel/Kconfig.locks
+++ b/kernel/Kconfig.locks
@@ -229,7 +229,7 @@ config MUTEX_SPIN_ON_OWNER
 
 config RWSEM_SPIN_ON_OWNER
        def_bool y
-       depends on SMP && RWSEM_XCHGADD_ALGORITHM && ARCH_SUPPORTS_ATOMIC_RMW
+       depends on SMP && ARCH_SUPPORTS_ATOMIC_RMW
 
 config LOCK_SPIN_ON_OWNER
        def_bool y
@@ -251,3 +251,10 @@ config ARCH_USE_QUEUED_RWLOCKS
 config QUEUED_RWLOCKS
 	def_bool y if ARCH_USE_QUEUED_RWLOCKS
 	depends on SMP
+
+config ARCH_HAS_MMIOWB
+	bool
+
+config MMIOWB
+	def_bool y if ARCH_HAS_MMIOWB
+	depends on SMP
diff --git a/kernel/Makefile b/kernel/Makefile
index 6c57e78817da..62471e75a2b0 100644
--- a/kernel/Makefile
+++ b/kernel/Makefile
@@ -30,6 +30,7 @@ KCOV_INSTRUMENT_extable.o := n
 # Don't self-instrument.
 KCOV_INSTRUMENT_kcov.o := n
 KASAN_SANITIZE_kcov.o := n
+CFLAGS_kcov.o := $(call cc-option, -fno-conserve-stack -fno-stack-protector)
 
 # cond_syscall is currently not LTO compatible
 CFLAGS_sys_ni.o = $(DISABLE_LTO)
diff --git a/kernel/backtracetest.c b/kernel/backtracetest.c
index 1323360d90e3..a563c8fdad0d 100644
--- a/kernel/backtracetest.c
+++ b/kernel/backtracetest.c
@@ -48,19 +48,14 @@ static void backtrace_test_irq(void)
 #ifdef CONFIG_STACKTRACE
 static void backtrace_test_saved(void)
 {
-	struct stack_trace trace;
 	unsigned long entries[8];
+	unsigned int nr_entries;
 
 	pr_info("Testing a saved backtrace.\n");
 	pr_info("The following trace is a kernel self test and not a bug!\n");
 
-	trace.nr_entries = 0;
-	trace.max_entries = ARRAY_SIZE(entries);
-	trace.entries = entries;
-	trace.skip = 0;
-
-	save_stack_trace(&trace);
-	print_stack_trace(&trace, 0);
+	nr_entries = stack_trace_save(entries, ARRAY_SIZE(entries), 0);
+	stack_trace_print(entries, nr_entries, 0);
 }
 #else
 static void backtrace_test_saved(void)
diff --git a/kernel/bpf/core.c b/kernel/bpf/core.c
index ff09d32a8a1b..c605397c79f0 100644
--- a/kernel/bpf/core.c
+++ b/kernel/bpf/core.c
@@ -848,7 +848,6 @@ void __weak bpf_jit_free(struct bpf_prog *fp)
 	if (fp->jited) {
 		struct bpf_binary_header *hdr = bpf_jit_binary_hdr(fp);
 
-		bpf_jit_binary_unlock_ro(hdr);
 		bpf_jit_binary_free(hdr);
 
 		WARN_ON_ONCE(!bpf_prog_kallsyms_verify_off(fp));
diff --git a/kernel/bpf/cpumap.c b/kernel/bpf/cpumap.c
index 8974b3755670..3c18260403dd 100644
--- a/kernel/bpf/cpumap.c
+++ b/kernel/bpf/cpumap.c
@@ -162,10 +162,14 @@ static void cpu_map_kthread_stop(struct work_struct *work)
 static struct sk_buff *cpu_map_build_skb(struct bpf_cpu_map_entry *rcpu,
 					 struct xdp_frame *xdpf)
 {
+	unsigned int hard_start_headroom;
 	unsigned int frame_size;
 	void *pkt_data_start;
 	struct sk_buff *skb;
 
+	/* Part of headroom was reserved to xdpf */
+	hard_start_headroom = sizeof(struct xdp_frame) +  xdpf->headroom;
+
 	/* build_skb need to place skb_shared_info after SKB end, and
 	 * also want to know the memory "truesize".  Thus, need to
 	 * know the memory frame size backing xdp_buff.
@@ -183,15 +187,15 @@ static struct sk_buff *cpu_map_build_skb(struct bpf_cpu_map_entry *rcpu,
 	 * is not at a fixed memory location, with mixed length
 	 * packets, which is bad for cache-line hotness.
 	 */
-	frame_size = SKB_DATA_ALIGN(xdpf->len + xdpf->headroom) +
+	frame_size = SKB_DATA_ALIGN(xdpf->len + hard_start_headroom) +
 		SKB_DATA_ALIGN(sizeof(struct skb_shared_info));
 
-	pkt_data_start = xdpf->data - xdpf->headroom;
+	pkt_data_start = xdpf->data - hard_start_headroom;
 	skb = build_skb(pkt_data_start, frame_size);
 	if (!skb)
 		return NULL;
 
-	skb_reserve(skb, xdpf->headroom);
+	skb_reserve(skb, hard_start_headroom);
 	__skb_put(skb, xdpf->len);
 	if (xdpf->metasize)
 		skb_metadata_set(skb, xdpf->metasize);
@@ -205,6 +209,9 @@ static struct sk_buff *cpu_map_build_skb(struct bpf_cpu_map_entry *rcpu,
 	 * - RX ring dev queue index	(skb_record_rx_queue)
 	 */
 
+	/* Allow SKB to reuse area used by xdp_frame */
+	xdp_scrub_frame(xdpf);
+
 	return skb;
 }
 
diff --git a/kernel/bpf/inode.c b/kernel/bpf/inode.c
index 2ada5e21dfa6..4a8f390a2b82 100644
--- a/kernel/bpf/inode.c
+++ b/kernel/bpf/inode.c
@@ -554,19 +554,6 @@ struct bpf_prog *bpf_prog_get_type_path(const char *name, enum bpf_prog_type typ
 }
 EXPORT_SYMBOL(bpf_prog_get_type_path);
 
-static void bpf_evict_inode(struct inode *inode)
-{
-	enum bpf_type type;
-
-	truncate_inode_pages_final(&inode->i_data);
-	clear_inode(inode);
-
-	if (S_ISLNK(inode->i_mode))
-		kfree(inode->i_link);
-	if (!bpf_inode_type(inode, &type))
-		bpf_any_put(inode->i_private, type);
-}
-
 /*
  * Display the mount options in /proc/mounts.
  */
@@ -579,11 +566,28 @@ static int bpf_show_options(struct seq_file *m, struct dentry *root)
 	return 0;
 }
 
+static void bpf_destroy_inode_deferred(struct rcu_head *head)
+{
+	struct inode *inode = container_of(head, struct inode, i_rcu);
+	enum bpf_type type;
+
+	if (S_ISLNK(inode->i_mode))
+		kfree(inode->i_link);
+	if (!bpf_inode_type(inode, &type))
+		bpf_any_put(inode->i_private, type);
+	free_inode_nonrcu(inode);
+}
+
+static void bpf_destroy_inode(struct inode *inode)
+{
+	call_rcu(&inode->i_rcu, bpf_destroy_inode_deferred);
+}
+
 static const struct super_operations bpf_super_ops = {
 	.statfs		= simple_statfs,
 	.drop_inode	= generic_delete_inode,
 	.show_options	= bpf_show_options,
-	.evict_inode	= bpf_evict_inode,
+	.destroy_inode	= bpf_destroy_inode,
 };
 
 enum {
diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c
index 62f6bced3a3c..afca36f53c49 100644
--- a/kernel/bpf/syscall.c
+++ b/kernel/bpf/syscall.c
@@ -136,21 +136,29 @@ static struct bpf_map *find_and_alloc_map(union bpf_attr *attr)
 
 void *bpf_map_area_alloc(size_t size, int numa_node)
 {
-	/* We definitely need __GFP_NORETRY, so OOM killer doesn't
-	 * trigger under memory pressure as we really just want to
-	 * fail instead.
+	/* We really just want to fail instead of triggering OOM killer
+	 * under memory pressure, therefore we set __GFP_NORETRY to kmalloc,
+	 * which is used for lower order allocation requests.
+	 *
+	 * It has been observed that higher order allocation requests done by
+	 * vmalloc with __GFP_NORETRY being set might fail due to not trying
+	 * to reclaim memory from the page cache, thus we set
+	 * __GFP_RETRY_MAYFAIL to avoid such situations.
 	 */
-	const gfp_t flags = __GFP_NOWARN | __GFP_NORETRY | __GFP_ZERO;
+
+	const gfp_t flags = __GFP_NOWARN | __GFP_ZERO;
 	void *area;
 
 	if (size <= (PAGE_SIZE << PAGE_ALLOC_COSTLY_ORDER)) {
-		area = kmalloc_node(size, GFP_USER | flags, numa_node);
+		area = kmalloc_node(size, GFP_USER | __GFP_NORETRY | flags,
+				    numa_node);
 		if (area != NULL)
 			return area;
 	}
 
-	return __vmalloc_node_flags_caller(size, numa_node, GFP_KERNEL | flags,
-					   __builtin_return_address(0));
+	return __vmalloc_node_flags_caller(size, numa_node,
+					   GFP_KERNEL | __GFP_RETRY_MAYFAIL |
+					   flags, __builtin_return_address(0));
 }
 
 void bpf_map_area_free(void *area)
diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index ce166a002d16..09d5d972c9ff 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -212,7 +212,7 @@ struct bpf_call_arg_meta {
 	int access_size;
 	s64 msize_smax_value;
 	u64 msize_umax_value;
-	int ptr_id;
+	int ref_obj_id;
 	int func_id;
 };
 
@@ -346,35 +346,23 @@ static bool reg_type_may_be_null(enum bpf_reg_type type)
 	       type == PTR_TO_TCP_SOCK_OR_NULL;
 }
 
-static bool type_is_refcounted(enum bpf_reg_type type)
-{
-	return type == PTR_TO_SOCKET;
-}
-
-static bool type_is_refcounted_or_null(enum bpf_reg_type type)
-{
-	return type == PTR_TO_SOCKET || type == PTR_TO_SOCKET_OR_NULL;
-}
-
-static bool reg_is_refcounted(const struct bpf_reg_state *reg)
-{
-	return type_is_refcounted(reg->type);
-}
-
 static bool reg_may_point_to_spin_lock(const struct bpf_reg_state *reg)
 {
 	return reg->type == PTR_TO_MAP_VALUE &&
 		map_value_has_spin_lock(reg->map_ptr);
 }
 
-static bool reg_is_refcounted_or_null(const struct bpf_reg_state *reg)
+static bool reg_type_may_be_refcounted_or_null(enum bpf_reg_type type)
 {
-	return type_is_refcounted_or_null(reg->type);
+	return type == PTR_TO_SOCKET ||
+		type == PTR_TO_SOCKET_OR_NULL ||
+		type == PTR_TO_TCP_SOCK ||
+		type == PTR_TO_TCP_SOCK_OR_NULL;
 }
 
-static bool arg_type_is_refcounted(enum bpf_arg_type type)
+static bool arg_type_may_be_refcounted(enum bpf_arg_type type)
 {
-	return type == ARG_PTR_TO_SOCKET;
+	return type == ARG_PTR_TO_SOCK_COMMON;
 }
 
 /* Determine whether the function releases some resources allocated by another
@@ -392,6 +380,12 @@ static bool is_acquire_function(enum bpf_func_id func_id)
 		func_id == BPF_FUNC_sk_lookup_udp;
 }
 
+static bool is_ptr_cast_function(enum bpf_func_id func_id)
+{
+	return func_id == BPF_FUNC_tcp_sock ||
+		func_id == BPF_FUNC_sk_fullsock;
+}
+
 /* string representation of 'enum bpf_reg_type' */
 static const char * const reg_type_str[] = {
 	[NOT_INIT]		= "?",
@@ -466,6 +460,8 @@ static void print_verifier_state(struct bpf_verifier_env *env,
 				verbose(env, ",call_%d", func(env, reg)->callsite);
 		} else {
 			verbose(env, "(id=%d", reg->id);
+			if (reg_type_may_be_refcounted_or_null(t))
+				verbose(env, ",ref_obj_id=%d", reg->ref_obj_id);
 			if (t != SCALAR_VALUE)
 				verbose(env, ",off=%d", reg->off);
 			if (type_is_pkt_pointer(t))
@@ -1901,8 +1897,9 @@ continue_func:
 		}
 		frame++;
 		if (frame >= MAX_CALL_FRAMES) {
-			WARN_ONCE(1, "verifier bug. Call stack is too deep\n");
-			return -EFAULT;
+			verbose(env, "the call stack of %d frames is too deep !\n",
+				frame);
+			return -E2BIG;
 		}
 		goto process_func;
 	}
@@ -2414,16 +2411,15 @@ static int check_func_arg(struct bpf_verifier_env *env, u32 regno,
 		/* Any sk pointer can be ARG_PTR_TO_SOCK_COMMON */
 		if (!type_is_sk_pointer(type))
 			goto err_type;
-	} else if (arg_type == ARG_PTR_TO_SOCKET) {
-		expected_type = PTR_TO_SOCKET;
-		if (type != expected_type)
-			goto err_type;
-		if (meta->ptr_id || !reg->id) {
-			verbose(env, "verifier internal error: mismatched references meta=%d, reg=%d\n",
-				meta->ptr_id, reg->id);
-			return -EFAULT;
+		if (reg->ref_obj_id) {
+			if (meta->ref_obj_id) {
+				verbose(env, "verifier internal error: more than one arg with ref_obj_id R%d %u %u\n",
+					regno, reg->ref_obj_id,
+					meta->ref_obj_id);
+				return -EFAULT;
+			}
+			meta->ref_obj_id = reg->ref_obj_id;
 		}
-		meta->ptr_id = reg->id;
 	} else if (arg_type == ARG_PTR_TO_SPIN_LOCK) {
 		if (meta->func_id == BPF_FUNC_spin_lock) {
 			if (process_spin_lock(env, regno, true))
@@ -2740,32 +2736,38 @@ static bool check_arg_pair_ok(const struct bpf_func_proto *fn)
 	return true;
 }
 
-static bool check_refcount_ok(const struct bpf_func_proto *fn)
+static bool check_refcount_ok(const struct bpf_func_proto *fn, int func_id)
 {
 	int count = 0;
 
-	if (arg_type_is_refcounted(fn->arg1_type))
+	if (arg_type_may_be_refcounted(fn->arg1_type))
 		count++;
-	if (arg_type_is_refcounted(fn->arg2_type))
+	if (arg_type_may_be_refcounted(fn->arg2_type))
 		count++;
-	if (arg_type_is_refcounted(fn->arg3_type))
+	if (arg_type_may_be_refcounted(fn->arg3_type))
 		count++;
-	if (arg_type_is_refcounted(fn->arg4_type))
+	if (arg_type_may_be_refcounted(fn->arg4_type))
 		count++;
-	if (arg_type_is_refcounted(fn->arg5_type))
+	if (arg_type_may_be_refcounted(fn->arg5_type))
 		count++;
 
+	/* A reference acquiring function cannot acquire
+	 * another refcounted ptr.
+	 */
+	if (is_acquire_function(func_id) && count)
+		return false;
+
 	/* We only support one arg being unreferenced at the moment,
 	 * which is sufficient for the helper functions we have right now.
 	 */
 	return count <= 1;
 }
 
-static int check_func_proto(const struct bpf_func_proto *fn)
+static int check_func_proto(const struct bpf_func_proto *fn, int func_id)
 {
 	return check_raw_mode_ok(fn) &&
 	       check_arg_pair_ok(fn) &&
-	       check_refcount_ok(fn) ? 0 : -EINVAL;
+	       check_refcount_ok(fn, func_id) ? 0 : -EINVAL;
 }
 
 /* Packet data might have moved, any old PTR_TO_PACKET[_META,_END]
@@ -2799,19 +2801,20 @@ static void clear_all_pkt_pointers(struct bpf_verifier_env *env)
 }
 
 static void release_reg_references(struct bpf_verifier_env *env,
-				   struct bpf_func_state *state, int id)
+				   struct bpf_func_state *state,
+				   int ref_obj_id)
 {
 	struct bpf_reg_state *regs = state->regs, *reg;
 	int i;
 
 	for (i = 0; i < MAX_BPF_REG; i++)
-		if (regs[i].id == id)
+		if (regs[i].ref_obj_id == ref_obj_id)
 			mark_reg_unknown(env, regs, i);
 
 	bpf_for_each_spilled_reg(i, state, reg) {
 		if (!reg)
 			continue;
-		if (reg_is_refcounted(reg) && reg->id == id)
+		if (reg->ref_obj_id == ref_obj_id)
 			__mark_reg_unknown(reg);
 	}
 }
@@ -2820,15 +2823,20 @@ static void release_reg_references(struct bpf_verifier_env *env,
  * resources. Identify all copies of the same pointer and clear the reference.
  */
 static int release_reference(struct bpf_verifier_env *env,
-			     struct bpf_call_arg_meta *meta)
+			     int ref_obj_id)
 {
 	struct bpf_verifier_state *vstate = env->cur_state;
+	int err;
 	int i;
 
+	err = release_reference_state(cur_func(env), ref_obj_id);
+	if (err)
+		return err;
+
 	for (i = 0; i <= vstate->curframe; i++)
-		release_reg_references(env, vstate->frame[i], meta->ptr_id);
+		release_reg_references(env, vstate->frame[i], ref_obj_id);
 
-	return release_reference_state(cur_func(env), meta->ptr_id);
+	return 0;
 }
 
 static int check_func_call(struct bpf_verifier_env *env, struct bpf_insn *insn,
@@ -3047,7 +3055,7 @@ static int check_helper_call(struct bpf_verifier_env *env, int func_id, int insn
 	memset(&meta, 0, sizeof(meta));
 	meta.pkt_access = fn->pkt_access;
 
-	err = check_func_proto(fn);
+	err = check_func_proto(fn, func_id);
 	if (err) {
 		verbose(env, "kernel subsystem misconfigured func %s#%d\n",
 			func_id_name(func_id), func_id);
@@ -3093,7 +3101,7 @@ static int check_helper_call(struct bpf_verifier_env *env, int func_id, int insn
 			return err;
 		}
 	} else if (is_release_function(func_id)) {
-		err = release_reference(env, &meta);
+		err = release_reference(env, meta.ref_obj_id);
 		if (err) {
 			verbose(env, "func %s#%d reference has not been acquired before\n",
 				func_id_name(func_id), func_id);
@@ -3154,8 +3162,10 @@ static int check_helper_call(struct bpf_verifier_env *env, int func_id, int insn
 
 			if (id < 0)
 				return id;
-			/* For release_reference() */
+			/* For mark_ptr_or_null_reg() */
 			regs[BPF_REG_0].id = id;
+			/* For release_reference() */
+			regs[BPF_REG_0].ref_obj_id = id;
 		} else {
 			/* For mark_ptr_or_null_reg() */
 			regs[BPF_REG_0].id = ++env->id_gen;
@@ -3170,6 +3180,10 @@ static int check_helper_call(struct bpf_verifier_env *env, int func_id, int insn
 		return -EINVAL;
 	}
 
+	if (is_ptr_cast_function(func_id))
+		/* For release_reference() */
+		regs[BPF_REG_0].ref_obj_id = meta.ref_obj_id;
+
 	do_refine_retval_range(regs, fn->ret_type, func_id, &meta);
 
 	err = check_map_func_compatibility(env, meta.map_ptr, func_id);
@@ -3368,7 +3382,7 @@ do_sim:
 		*dst_reg = *ptr_reg;
 	}
 	ret = push_stack(env, env->insn_idx + 1, env->insn_idx, true);
-	if (!ptr_is_dst_reg)
+	if (!ptr_is_dst_reg && ret)
 		*dst_reg = tmp;
 	return !ret ? -EFAULT : 0;
 }
@@ -4124,15 +4138,35 @@ static int check_alu_op(struct bpf_verifier_env *env, struct bpf_insn *insn)
 	return 0;
 }
 
+static void __find_good_pkt_pointers(struct bpf_func_state *state,
+				     struct bpf_reg_state *dst_reg,
+				     enum bpf_reg_type type, u16 new_range)
+{
+	struct bpf_reg_state *reg;
+	int i;
+
+	for (i = 0; i < MAX_BPF_REG; i++) {
+		reg = &state->regs[i];
+		if (reg->type == type && reg->id == dst_reg->id)
+			/* keep the maximum range already checked */
+			reg->range = max(reg->range, new_range);
+	}
+
+	bpf_for_each_spilled_reg(i, state, reg) {
+		if (!reg)
+			continue;
+		if (reg->type == type && reg->id == dst_reg->id)
+			reg->range = max(reg->range, new_range);
+	}
+}
+
 static void find_good_pkt_pointers(struct bpf_verifier_state *vstate,
 				   struct bpf_reg_state *dst_reg,
 				   enum bpf_reg_type type,
 				   bool range_right_open)
 {
-	struct bpf_func_state *state = vstate->frame[vstate->curframe];
-	struct bpf_reg_state *regs = state->regs, *reg;
 	u16 new_range;
-	int i, j;
+	int i;
 
 	if (dst_reg->off < 0 ||
 	    (dst_reg->off == 0 && range_right_open))
@@ -4197,20 +4231,9 @@ static void find_good_pkt_pointers(struct bpf_verifier_state *vstate,
 	 * the range won't allow anything.
 	 * dst_reg->off is known < MAX_PACKET_OFF, therefore it fits in a u16.
 	 */
-	for (i = 0; i < MAX_BPF_REG; i++)
-		if (regs[i].type == type && regs[i].id == dst_reg->id)
-			/* keep the maximum range already checked */
-			regs[i].range = max(regs[i].range, new_range);
-
-	for (j = 0; j <= vstate->curframe; j++) {
-		state = vstate->frame[j];
-		bpf_for_each_spilled_reg(i, state, reg) {
-			if (!reg)
-				continue;
-			if (reg->type == type && reg->id == dst_reg->id)
-				reg->range = max(reg->range, new_range);
-		}
-	}
+	for (i = 0; i <= vstate->curframe; i++)
+		__find_good_pkt_pointers(vstate->frame[i], dst_reg, type,
+					 new_range);
 }
 
 /* compute branch direction of the expression "if (reg opcode val) goto target;"
@@ -4665,17 +4688,41 @@ static void mark_ptr_or_null_reg(struct bpf_func_state *state,
 		} else if (reg->type == PTR_TO_TCP_SOCK_OR_NULL) {
 			reg->type = PTR_TO_TCP_SOCK;
 		}
-		if (is_null || !(reg_is_refcounted(reg) ||
-				 reg_may_point_to_spin_lock(reg))) {
-			/* We don't need id from this point onwards anymore,
-			 * thus we should better reset it, so that state
-			 * pruning has chances to take effect.
+		if (is_null) {
+			/* We don't need id and ref_obj_id from this point
+			 * onwards anymore, thus we should better reset it,
+			 * so that state pruning has chances to take effect.
+			 */
+			reg->id = 0;
+			reg->ref_obj_id = 0;
+		} else if (!reg_may_point_to_spin_lock(reg)) {
+			/* For not-NULL ptr, reg->ref_obj_id will be reset
+			 * in release_reg_references().
+			 *
+			 * reg->id is still used by spin_lock ptr. Other
+			 * than spin_lock ptr type, reg->id can be reset.
 			 */
 			reg->id = 0;
 		}
 	}
 }
 
+static void __mark_ptr_or_null_regs(struct bpf_func_state *state, u32 id,
+				    bool is_null)
+{
+	struct bpf_reg_state *reg;
+	int i;
+
+	for (i = 0; i < MAX_BPF_REG; i++)
+		mark_ptr_or_null_reg(state, &state->regs[i], id, is_null);
+
+	bpf_for_each_spilled_reg(i, state, reg) {
+		if (!reg)
+			continue;
+		mark_ptr_or_null_reg(state, reg, id, is_null);
+	}
+}
+
 /* The logic is similar to find_good_pkt_pointers(), both could eventually
  * be folded together at some point.
  */
@@ -4683,24 +4730,20 @@ static void mark_ptr_or_null_regs(struct bpf_verifier_state *vstate, u32 regno,
 				  bool is_null)
 {
 	struct bpf_func_state *state = vstate->frame[vstate->curframe];
-	struct bpf_reg_state *reg, *regs = state->regs;
+	struct bpf_reg_state *regs = state->regs;
+	u32 ref_obj_id = regs[regno].ref_obj_id;
 	u32 id = regs[regno].id;
-	int i, j;
-
-	if (reg_is_refcounted_or_null(&regs[regno]) && is_null)
-		release_reference_state(state, id);
+	int i;
 
-	for (i = 0; i < MAX_BPF_REG; i++)
-		mark_ptr_or_null_reg(state, &regs[i], id, is_null);
+	if (ref_obj_id && ref_obj_id == id && is_null)
+		/* regs[regno] is in the " == NULL" branch.
+		 * No one could have freed the reference state before
+		 * doing the NULL check.
+		 */
+		WARN_ON_ONCE(release_reference_state(state, id));
 
-	for (j = 0; j <= vstate->curframe; j++) {
-		state = vstate->frame[j];
-		bpf_for_each_spilled_reg(i, state, reg) {
-			if (!reg)
-				continue;
-			mark_ptr_or_null_reg(state, reg, id, is_null);
-		}
-	}
+	for (i = 0; i <= vstate->curframe; i++)
+		__mark_ptr_or_null_regs(vstate->frame[i], id, is_null);
 }
 
 static bool try_match_pkt_pointers(const struct bpf_insn *insn,
@@ -6052,15 +6095,17 @@ static int propagate_liveness(struct bpf_verifier_env *env,
 	}
 	/* Propagate read liveness of registers... */
 	BUILD_BUG_ON(BPF_REG_FP + 1 != MAX_BPF_REG);
-	/* We don't need to worry about FP liveness because it's read-only */
-	for (i = 0; i < BPF_REG_FP; i++) {
-		if (vparent->frame[vparent->curframe]->regs[i].live & REG_LIVE_READ)
-			continue;
-		if (vstate->frame[vstate->curframe]->regs[i].live & REG_LIVE_READ) {
-			err = mark_reg_read(env, &vstate->frame[vstate->curframe]->regs[i],
-					    &vparent->frame[vstate->curframe]->regs[i]);
-			if (err)
-				return err;
+	for (frame = 0; frame <= vstate->curframe; frame++) {
+		/* We don't need to worry about FP liveness, it's read-only */
+		for (i = frame < vstate->curframe ? BPF_REG_6 : 0; i < BPF_REG_FP; i++) {
+			if (vparent->frame[frame]->regs[i].live & REG_LIVE_READ)
+				continue;
+			if (vstate->frame[frame]->regs[i].live & REG_LIVE_READ) {
+				err = mark_reg_read(env, &vstate->frame[frame]->regs[i],
+						    &vparent->frame[frame]->regs[i]);
+				if (err)
+					return err;
+			}
 		}
 	}
 
diff --git a/kernel/cgroup/cpuset.c b/kernel/cgroup/cpuset.c
index 4834c4214e9c..6a1942ed781c 100644
--- a/kernel/cgroup/cpuset.c
+++ b/kernel/cgroup/cpuset.c
@@ -740,11 +740,10 @@ static inline int nr_cpusets(void)
  * Must be called with cpuset_mutex held.
  *
  * The three key local variables below are:
- *    q  - a linked-list queue of cpuset pointers, used to implement a
- *	   top-down scan of all cpusets.  This scan loads a pointer
- *	   to each cpuset marked is_sched_load_balance into the
- *	   array 'csa'.  For our purposes, rebuilding the schedulers
- *	   sched domains, we can ignore !is_sched_load_balance cpusets.
+ *    cp - cpuset pointer, used (together with pos_css) to perform a
+ *	   top-down scan of all cpusets. For our purposes, rebuilding
+ *	   the schedulers sched domains, we can ignore !is_sched_load_
+ *	   balance cpusets.
  *  csa  - (for CpuSet Array) Array of pointers to all the cpusets
  *	   that need to be load balanced, for convenient iterative
  *	   access by the subsequent code that finds the best partition,
@@ -775,7 +774,7 @@ static inline int nr_cpusets(void)
 static int generate_sched_domains(cpumask_var_t **domains,
 			struct sched_domain_attr **attributes)
 {
-	struct cpuset *cp;	/* scans q */
+	struct cpuset *cp;	/* top-down scan of cpusets */
 	struct cpuset **csa;	/* array of all cpuset ptrs */
 	int csn;		/* how many cpuset ptrs in csa so far */
 	int i, j, k;		/* indices for partition finding loops */
diff --git a/kernel/cpu.c b/kernel/cpu.c
index 025f419d16f6..f2ef10460698 100644
--- a/kernel/cpu.c
+++ b/kernel/cpu.c
@@ -9,6 +9,7 @@
 #include <linux/notifier.h>
 #include <linux/sched/signal.h>
 #include <linux/sched/hotplug.h>
+#include <linux/sched/isolation.h>
 #include <linux/sched/task.h>
 #include <linux/sched/smt.h>
 #include <linux/unistd.h>
@@ -564,6 +565,20 @@ static void undo_cpu_up(unsigned int cpu, struct cpuhp_cpu_state *st)
 		cpuhp_invoke_callback(cpu, st->state, false, NULL, NULL);
 }
 
+static inline bool can_rollback_cpu(struct cpuhp_cpu_state *st)
+{
+	if (IS_ENABLED(CONFIG_HOTPLUG_CPU))
+		return true;
+	/*
+	 * When CPU hotplug is disabled, then taking the CPU down is not
+	 * possible because takedown_cpu() and the architecture and
+	 * subsystem specific mechanisms are not available. So the CPU
+	 * which would be completely unplugged again needs to stay around
+	 * in the current state.
+	 */
+	return st->state <= CPUHP_BRINGUP_CPU;
+}
+
 static int cpuhp_up_callbacks(unsigned int cpu, struct cpuhp_cpu_state *st,
 			      enum cpuhp_state target)
 {
@@ -574,8 +589,10 @@ static int cpuhp_up_callbacks(unsigned int cpu, struct cpuhp_cpu_state *st,
 		st->state++;
 		ret = cpuhp_invoke_callback(cpu, st->state, true, NULL, NULL);
 		if (ret) {
-			st->target = prev_state;
-			undo_cpu_up(cpu, st);
+			if (can_rollback_cpu(st)) {
+				st->target = prev_state;
+				undo_cpu_up(cpu, st);
+			}
 			break;
 		}
 	}
@@ -844,6 +861,8 @@ static int take_cpu_down(void *_param)
 
 	/* Give up timekeeping duties */
 	tick_handover_do_timer();
+	/* Remove CPU from timer broadcasting */
+	tick_offline_cpu(cpu);
 	/* Park the stopper thread */
 	stop_machine_park(cpu);
 	return 0;
@@ -1183,8 +1202,15 @@ int freeze_secondary_cpus(int primary)
 	int cpu, error = 0;
 
 	cpu_maps_update_begin();
-	if (!cpu_online(primary))
+	if (primary == -1) {
 		primary = cpumask_first(cpu_online_mask);
+		if (!housekeeping_cpu(primary, HK_FLAG_TIMER))
+			primary = housekeeping_any_cpu(HK_FLAG_TIMER);
+	} else {
+		if (!cpu_online(primary))
+			primary = cpumask_first(cpu_online_mask);
+	}
+
 	/*
 	 * We take down all of the non-boot CPUs in one shot to avoid races
 	 * with the userspace trying to use the CPU hotplug at the same time
@@ -2017,19 +2043,6 @@ static const struct attribute_group cpuhp_cpu_root_attr_group = {
 
 #ifdef CONFIG_HOTPLUG_SMT
 
-static const char *smt_states[] = {
-	[CPU_SMT_ENABLED]		= "on",
-	[CPU_SMT_DISABLED]		= "off",
-	[CPU_SMT_FORCE_DISABLED]	= "forceoff",
-	[CPU_SMT_NOT_SUPPORTED]		= "notsupported",
-};
-
-static ssize_t
-show_smt_control(struct device *dev, struct device_attribute *attr, char *buf)
-{
-	return snprintf(buf, PAGE_SIZE - 2, "%s\n", smt_states[cpu_smt_control]);
-}
-
 static void cpuhp_offline_cpu_device(unsigned int cpu)
 {
 	struct device *dev = get_cpu_device(cpu);
@@ -2100,9 +2113,10 @@ static int cpuhp_smt_enable(void)
 	return ret;
 }
 
+
 static ssize_t
-store_smt_control(struct device *dev, struct device_attribute *attr,
-		  const char *buf, size_t count)
+__store_smt_control(struct device *dev, struct device_attribute *attr,
+		    const char *buf, size_t count)
 {
 	int ctrlval, ret;
 
@@ -2140,14 +2154,44 @@ store_smt_control(struct device *dev, struct device_attribute *attr,
 	unlock_device_hotplug();
 	return ret ? ret : count;
 }
+
+#else /* !CONFIG_HOTPLUG_SMT */
+static ssize_t
+__store_smt_control(struct device *dev, struct device_attribute *attr,
+		    const char *buf, size_t count)
+{
+	return -ENODEV;
+}
+#endif /* CONFIG_HOTPLUG_SMT */
+
+static const char *smt_states[] = {
+	[CPU_SMT_ENABLED]		= "on",
+	[CPU_SMT_DISABLED]		= "off",
+	[CPU_SMT_FORCE_DISABLED]	= "forceoff",
+	[CPU_SMT_NOT_SUPPORTED]		= "notsupported",
+	[CPU_SMT_NOT_IMPLEMENTED]	= "notimplemented",
+};
+
+static ssize_t
+show_smt_control(struct device *dev, struct device_attribute *attr, char *buf)
+{
+	const char *state = smt_states[cpu_smt_control];
+
+	return snprintf(buf, PAGE_SIZE - 2, "%s\n", state);
+}
+
+static ssize_t
+store_smt_control(struct device *dev, struct device_attribute *attr,
+		  const char *buf, size_t count)
+{
+	return __store_smt_control(dev, attr, buf, count);
+}
 static DEVICE_ATTR(control, 0644, show_smt_control, store_smt_control);
 
 static ssize_t
 show_smt_active(struct device *dev, struct device_attribute *attr, char *buf)
 {
-	bool active = topology_max_smt_threads() > 1;
-
-	return snprintf(buf, PAGE_SIZE - 2, "%d\n", active);
+	return snprintf(buf, PAGE_SIZE - 2, "%d\n", sched_smt_active());
 }
 static DEVICE_ATTR(active, 0444, show_smt_active, NULL);
 
@@ -2163,21 +2207,17 @@ static const struct attribute_group cpuhp_smt_attr_group = {
 	NULL
 };
 
-static int __init cpu_smt_state_init(void)
+static int __init cpu_smt_sysfs_init(void)
 {
 	return sysfs_create_group(&cpu_subsys.dev_root->kobj,
 				  &cpuhp_smt_attr_group);
 }
 
-#else
-static inline int cpu_smt_state_init(void) { return 0; }
-#endif
-
 static int __init cpuhp_sysfs_init(void)
 {
 	int cpu, ret;
 
-	ret = cpu_smt_state_init();
+	ret = cpu_smt_sysfs_init();
 	if (ret)
 		return ret;
 
@@ -2198,7 +2238,7 @@ static int __init cpuhp_sysfs_init(void)
 	return 0;
 }
 device_initcall(cpuhp_sysfs_init);
-#endif
+#endif /* CONFIG_SYSFS && CONFIG_HOTPLUG_CPU */
 
 /*
  * cpu_bit_bitmap[] is a special, "compressed" data structure that
@@ -2288,3 +2328,18 @@ void __init boot_cpu_hotplug_init(void)
 #endif
 	this_cpu_write(cpuhp_state.state, CPUHP_ONLINE);
 }
+
+enum cpu_mitigations cpu_mitigations __ro_after_init = CPU_MITIGATIONS_AUTO;
+
+static int __init mitigations_parse_cmdline(char *arg)
+{
+	if (!strcmp(arg, "off"))
+		cpu_mitigations = CPU_MITIGATIONS_OFF;
+	else if (!strcmp(arg, "auto"))
+		cpu_mitigations = CPU_MITIGATIONS_AUTO;
+	else if (!strcmp(arg, "auto,nosmt"))
+		cpu_mitigations = CPU_MITIGATIONS_AUTO_NOSMT;
+
+	return 0;
+}
+early_param("mitigations", mitigations_parse_cmdline);
diff --git a/kernel/dma/debug.c b/kernel/dma/debug.c
index 45d51e8e26f6..badd77670d00 100644
--- a/kernel/dma/debug.c
+++ b/kernel/dma/debug.c
@@ -89,8 +89,8 @@ struct dma_debug_entry {
 	int		 sg_mapped_ents;
 	enum map_err_types  map_err_type;
 #ifdef CONFIG_STACKTRACE
-	struct		 stack_trace stacktrace;
-	unsigned long	 st_entries[DMA_DEBUG_STACKTRACE_ENTRIES];
+	unsigned int	stack_len;
+	unsigned long	stack_entries[DMA_DEBUG_STACKTRACE_ENTRIES];
 #endif
 };
 
@@ -174,7 +174,7 @@ static inline void dump_entry_trace(struct dma_debug_entry *entry)
 #ifdef CONFIG_STACKTRACE
 	if (entry) {
 		pr_warning("Mapped at:\n");
-		print_stack_trace(&entry->stacktrace, 0);
+		stack_trace_print(entry->stack_entries, entry->stack_len, 0);
 	}
 #endif
 }
@@ -704,12 +704,10 @@ static struct dma_debug_entry *dma_entry_alloc(void)
 	spin_unlock_irqrestore(&free_entries_lock, flags);
 
 #ifdef CONFIG_STACKTRACE
-	entry->stacktrace.max_entries = DMA_DEBUG_STACKTRACE_ENTRIES;
-	entry->stacktrace.entries = entry->st_entries;
-	entry->stacktrace.skip = 2;
-	save_stack_trace(&entry->stacktrace);
+	entry->stack_len = stack_trace_save(entry->stack_entries,
+					    ARRAY_SIZE(entry->stack_entries),
+					    1);
 #endif
-
 	return entry;
 }
 
diff --git a/kernel/events/core.c b/kernel/events/core.c
index 72d06e302e99..abbd4b3b96c2 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -2009,8 +2009,8 @@ event_sched_out(struct perf_event *event,
 	event->pmu->del(event, 0);
 	event->oncpu = -1;
 
-	if (event->pending_disable) {
-		event->pending_disable = 0;
+	if (READ_ONCE(event->pending_disable) >= 0) {
+		WRITE_ONCE(event->pending_disable, -1);
 		state = PERF_EVENT_STATE_OFF;
 	}
 	perf_event_set_state(event, state);
@@ -2198,7 +2198,8 @@ EXPORT_SYMBOL_GPL(perf_event_disable);
 
 void perf_event_disable_inatomic(struct perf_event *event)
 {
-	event->pending_disable = 1;
+	WRITE_ONCE(event->pending_disable, smp_processor_id());
+	/* can fail, see perf_pending_event_disable() */
 	irq_work_queue(&event->pending);
 }
 
@@ -2477,6 +2478,16 @@ static void ctx_resched(struct perf_cpu_context *cpuctx,
 	perf_pmu_enable(cpuctx->ctx.pmu);
 }
 
+void perf_pmu_resched(struct pmu *pmu)
+{
+	struct perf_cpu_context *cpuctx = this_cpu_ptr(pmu->pmu_cpu_context);
+	struct perf_event_context *task_ctx = cpuctx->task_ctx;
+
+	perf_ctx_lock(cpuctx, task_ctx);
+	ctx_resched(cpuctx, task_ctx, EVENT_ALL|EVENT_CPU);
+	perf_ctx_unlock(cpuctx, task_ctx);
+}
+
 /*
  * Cross CPU call to install and enable a performance event
  *
@@ -5810,10 +5821,45 @@ void perf_event_wakeup(struct perf_event *event)
 	}
 }
 
+static void perf_pending_event_disable(struct perf_event *event)
+{
+	int cpu = READ_ONCE(event->pending_disable);
+
+	if (cpu < 0)
+		return;
+
+	if (cpu == smp_processor_id()) {
+		WRITE_ONCE(event->pending_disable, -1);
+		perf_event_disable_local(event);
+		return;
+	}
+
+	/*
+	 *  CPU-A			CPU-B
+	 *
+	 *  perf_event_disable_inatomic()
+	 *    @pending_disable = CPU-A;
+	 *    irq_work_queue();
+	 *
+	 *  sched-out
+	 *    @pending_disable = -1;
+	 *
+	 *				sched-in
+	 *				perf_event_disable_inatomic()
+	 *				  @pending_disable = CPU-B;
+	 *				  irq_work_queue(); // FAILS
+	 *
+	 *  irq_work_run()
+	 *    perf_pending_event()
+	 *
+	 * But the event runs on CPU-B and wants disabling there.
+	 */
+	irq_work_queue_on(&event->pending, cpu);
+}
+
 static void perf_pending_event(struct irq_work *entry)
 {
-	struct perf_event *event = container_of(entry,
-			struct perf_event, pending);
+	struct perf_event *event = container_of(entry, struct perf_event, pending);
 	int rctx;
 
 	rctx = perf_swevent_get_recursion_context();
@@ -5822,10 +5868,7 @@ static void perf_pending_event(struct irq_work *entry)
 	 * and we won't recurse 'further'.
 	 */
 
-	if (event->pending_disable) {
-		event->pending_disable = 0;
-		perf_event_disable_local(event);
-	}
+	perf_pending_event_disable(event);
 
 	if (event->pending_wakeup) {
 		event->pending_wakeup = 0;
@@ -9044,26 +9087,29 @@ static void perf_event_addr_filters_apply(struct perf_event *event)
 	if (task == TASK_TOMBSTONE)
 		return;
 
-	if (!ifh->nr_file_filters)
-		return;
-
-	mm = get_task_mm(event->ctx->task);
-	if (!mm)
-		goto restart;
+	if (ifh->nr_file_filters) {
+		mm = get_task_mm(event->ctx->task);
+		if (!mm)
+			goto restart;
 
-	down_read(&mm->mmap_sem);
+		down_read(&mm->mmap_sem);
+	}
 
 	raw_spin_lock_irqsave(&ifh->lock, flags);
 	list_for_each_entry(filter, &ifh->list, entry) {
-		event->addr_filter_ranges[count].start = 0;
-		event->addr_filter_ranges[count].size = 0;
+		if (filter->path.dentry) {
+			/*
+			 * Adjust base offset if the filter is associated to a
+			 * binary that needs to be mapped:
+			 */
+			event->addr_filter_ranges[count].start = 0;
+			event->addr_filter_ranges[count].size = 0;
 
-		/*
-		 * Adjust base offset if the filter is associated to a binary
-		 * that needs to be mapped:
-		 */
-		if (filter->path.dentry)
 			perf_addr_filter_apply(filter, mm, &event->addr_filter_ranges[count]);
+		} else {
+			event->addr_filter_ranges[count].start = filter->offset;
+			event->addr_filter_ranges[count].size  = filter->size;
+		}
 
 		count++;
 	}
@@ -9071,9 +9117,11 @@ static void perf_event_addr_filters_apply(struct perf_event *event)
 	event->addr_filters_gen++;
 	raw_spin_unlock_irqrestore(&ifh->lock, flags);
 
-	up_read(&mm->mmap_sem);
+	if (ifh->nr_file_filters) {
+		up_read(&mm->mmap_sem);
 
-	mmput(mm);
+		mmput(mm);
+	}
 
 restart:
 	perf_event_stop(event, 1);
@@ -10236,6 +10284,7 @@ perf_event_alloc(struct perf_event_attr *attr, int cpu,
 
 
 	init_waitqueue_head(&event->waitq);
+	event->pending_disable = -1;
 	init_irq_work(&event->pending, perf_pending_event);
 
 	mutex_init(&event->mmap_mutex);
@@ -11878,7 +11927,7 @@ static void __init perf_event_init_all_cpus(void)
 	}
 }
 
-void perf_swevent_init_cpu(unsigned int cpu)
+static void perf_swevent_init_cpu(unsigned int cpu)
 {
 	struct swevent_htable *swhash = &per_cpu(swevent_htable, cpu);
 
diff --git a/kernel/events/ring_buffer.c b/kernel/events/ring_buffer.c
index a4047321d7d8..674b35383491 100644
--- a/kernel/events/ring_buffer.c
+++ b/kernel/events/ring_buffer.c
@@ -392,7 +392,7 @@ void *perf_aux_output_begin(struct perf_output_handle *handle,
 		 * store that will be enabled on successful return
 		 */
 		if (!handle->size) { /* A, matches D */
-			event->pending_disable = 1;
+			event->pending_disable = smp_processor_id();
 			perf_output_wakeup(handle);
 			local_set(&rb->aux_nest, 0);
 			goto err_put;
@@ -455,24 +455,21 @@ void perf_aux_output_end(struct perf_output_handle *handle, unsigned long size)
 		rb->aux_head += size;
 	}
 
-	if (size || handle->aux_flags) {
-		/*
-		 * Only send RECORD_AUX if we have something useful to communicate
-		 *
-		 * Note: the OVERWRITE records by themselves are not considered
-		 * useful, as they don't communicate any *new* information,
-		 * aside from the short-lived offset, that becomes history at
-		 * the next event sched-in and therefore isn't useful.
-		 * The userspace that needs to copy out AUX data in overwrite
-		 * mode should know to use user_page::aux_head for the actual
-		 * offset. So, from now on we don't output AUX records that
-		 * have *only* OVERWRITE flag set.
-		 */
-
-		if (handle->aux_flags & ~(u64)PERF_AUX_FLAG_OVERWRITE)
-			perf_event_aux_event(handle->event, aux_head, size,
-			                     handle->aux_flags);
-	}
+	/*
+	 * Only send RECORD_AUX if we have something useful to communicate
+	 *
+	 * Note: the OVERWRITE records by themselves are not considered
+	 * useful, as they don't communicate any *new* information,
+	 * aside from the short-lived offset, that becomes history at
+	 * the next event sched-in and therefore isn't useful.
+	 * The userspace that needs to copy out AUX data in overwrite
+	 * mode should know to use user_page::aux_head for the actual
+	 * offset. So, from now on we don't output AUX records that
+	 * have *only* OVERWRITE flag set.
+	 */
+	if (size || (handle->aux_flags & ~(u64)PERF_AUX_FLAG_OVERWRITE))
+		perf_event_aux_event(handle->event, aux_head, size,
+				     handle->aux_flags);
 
 	rb->user_page->aux_head = rb->aux_head;
 	if (rb_need_aux_wakeup(rb))
@@ -480,7 +477,7 @@ void perf_aux_output_end(struct perf_output_handle *handle, unsigned long size)
 
 	if (wakeup) {
 		if (handle->aux_flags & PERF_AUX_FLAG_TRUNCATED)
-			handle->event->pending_disable = 1;
+			handle->event->pending_disable = smp_processor_id();
 		perf_output_wakeup(handle);
 	}
 
@@ -613,8 +610,7 @@ int rb_alloc_aux(struct ring_buffer *rb, struct perf_event *event,
 	 * PMU requests more than one contiguous chunks of memory
 	 * for SW double buffering
 	 */
-	if ((event->pmu->capabilities & PERF_PMU_CAP_AUX_SW_DOUBLEBUF) &&
-	    !overwrite) {
+	if (!overwrite) {
 		if (!max_order)
 			return -EINVAL;
 
diff --git a/kernel/events/uprobes.c b/kernel/events/uprobes.c
index c5cde87329c7..e6a0d6be87e3 100644
--- a/kernel/events/uprobes.c
+++ b/kernel/events/uprobes.c
@@ -2294,16 +2294,14 @@ static struct notifier_block uprobe_exception_nb = {
 	.priority		= INT_MAX-1,	/* notified after kprobes, kgdb */
 };
 
-static int __init init_uprobes(void)
+void __init uprobes_init(void)
 {
 	int i;
 
 	for (i = 0; i < UPROBES_HASH_SZ; i++)
 		mutex_init(&uprobes_mmap_mutex[i]);
 
-	if (percpu_init_rwsem(&dup_mmap_sem))
-		return -ENOMEM;
+	BUG_ON(percpu_init_rwsem(&dup_mmap_sem));
 
-	return register_die_notifier(&uprobe_exception_nb);
+	BUG_ON(register_die_notifier(&uprobe_exception_nb));
 }
-__initcall(init_uprobes);
diff --git a/kernel/fork.c b/kernel/fork.c
index 9dcd18aa210b..fbe9dfcd8680 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -815,6 +815,7 @@ void __init fork_init(void)
 #endif
 
 	lockdep_init_task(&init_task);
+	uprobes_init();
 }
 
 int __weak arch_dup_task_struct(struct task_struct *dst,
@@ -1298,13 +1299,20 @@ void mm_release(struct task_struct *tsk, struct mm_struct *mm)
 		complete_vfork_done(tsk);
 }
 
-/*
- * Allocate a new mm structure and copy contents from the
- * mm structure of the passed in task structure.
+/**
+ * dup_mm() - duplicates an existing mm structure
+ * @tsk: the task_struct with which the new mm will be associated.
+ * @oldmm: the mm to duplicate.
+ *
+ * Allocates a new mm structure and duplicates the provided @oldmm structure
+ * content into it.
+ *
+ * Return: the duplicated mm or NULL on failure.
  */
-static struct mm_struct *dup_mm(struct task_struct *tsk)
+static struct mm_struct *dup_mm(struct task_struct *tsk,
+				struct mm_struct *oldmm)
 {
-	struct mm_struct *mm, *oldmm = current->mm;
+	struct mm_struct *mm;
 	int err;
 
 	mm = allocate_mm();
@@ -1371,7 +1379,7 @@ static int copy_mm(unsigned long clone_flags, struct task_struct *tsk)
 	}
 
 	retval = -ENOMEM;
-	mm = dup_mm(tsk);
+	mm = dup_mm(tsk, current->mm);
 	if (!mm)
 		goto fail_nomem;
 
@@ -2186,6 +2194,11 @@ struct task_struct *fork_idle(int cpu)
 	return task;
 }
 
+struct mm_struct *copy_init_mm(void)
+{
+	return dup_mm(NULL, &init_mm);
+}
+
 /*
  *  Ok, this is the main fork-routine.
  *
diff --git a/kernel/futex.c b/kernel/futex.c
index 9e40cf7be606..6262f1534ac9 100644
--- a/kernel/futex.c
+++ b/kernel/futex.c
@@ -1311,13 +1311,15 @@ static int lookup_pi_state(u32 __user *uaddr, u32 uval,
 
 static int lock_pi_update_atomic(u32 __user *uaddr, u32 uval, u32 newval)
 {
+	int err;
 	u32 uninitialized_var(curval);
 
 	if (unlikely(should_fail_futex(true)))
 		return -EFAULT;
 
-	if (unlikely(cmpxchg_futex_value_locked(&curval, uaddr, uval, newval)))
-		return -EFAULT;
+	err = cmpxchg_futex_value_locked(&curval, uaddr, uval, newval);
+	if (unlikely(err))
+		return err;
 
 	/* If user space value changed, let the caller retry */
 	return curval != uval ? -EAGAIN : 0;
@@ -1502,10 +1504,8 @@ static int wake_futex_pi(u32 __user *uaddr, u32 uval, struct futex_pi_state *pi_
 	if (unlikely(should_fail_futex(true)))
 		ret = -EFAULT;
 
-	if (cmpxchg_futex_value_locked(&curval, uaddr, uval, newval)) {
-		ret = -EFAULT;
-
-	} else if (curval != uval) {
+	ret = cmpxchg_futex_value_locked(&curval, uaddr, uval, newval);
+	if (!ret && (curval != uval)) {
 		/*
 		 * If a unconditional UNLOCK_PI operation (user space did not
 		 * try the TID->0 transition) raced with a waiter setting the
@@ -1700,32 +1700,32 @@ retry_private:
 	double_lock_hb(hb1, hb2);
 	op_ret = futex_atomic_op_inuser(op, uaddr2);
 	if (unlikely(op_ret < 0)) {
-
 		double_unlock_hb(hb1, hb2);
 
-#ifndef CONFIG_MMU
-		/*
-		 * we don't get EFAULT from MMU faults if we don't have an MMU,
-		 * but we might get them from range checking
-		 */
-		ret = op_ret;
-		goto out_put_keys;
-#endif
-
-		if (unlikely(op_ret != -EFAULT)) {
+		if (!IS_ENABLED(CONFIG_MMU) ||
+		    unlikely(op_ret != -EFAULT && op_ret != -EAGAIN)) {
+			/*
+			 * we don't get EFAULT from MMU faults if we don't have
+			 * an MMU, but we might get them from range checking
+			 */
 			ret = op_ret;
 			goto out_put_keys;
 		}
 
-		ret = fault_in_user_writeable(uaddr2);
-		if (ret)
-			goto out_put_keys;
+		if (op_ret == -EFAULT) {
+			ret = fault_in_user_writeable(uaddr2);
+			if (ret)
+				goto out_put_keys;
+		}
 
-		if (!(flags & FLAGS_SHARED))
+		if (!(flags & FLAGS_SHARED)) {
+			cond_resched();
 			goto retry_private;
+		}
 
 		put_futex_key(&key2);
 		put_futex_key(&key1);
+		cond_resched();
 		goto retry;
 	}
 
@@ -2350,7 +2350,7 @@ static int fixup_pi_state_owner(u32 __user *uaddr, struct futex_q *q,
 	u32 uval, uninitialized_var(curval), newval;
 	struct task_struct *oldowner, *newowner;
 	u32 newtid;
-	int ret;
+	int ret, err = 0;
 
 	lockdep_assert_held(q->lock_ptr);
 
@@ -2421,14 +2421,17 @@ retry:
 	if (!pi_state->owner)
 		newtid |= FUTEX_OWNER_DIED;
 
-	if (get_futex_value_locked(&uval, uaddr))
-		goto handle_fault;
+	err = get_futex_value_locked(&uval, uaddr);
+	if (err)
+		goto handle_err;
 
 	for (;;) {
 		newval = (uval & FUTEX_OWNER_DIED) | newtid;
 
-		if (cmpxchg_futex_value_locked(&curval, uaddr, uval, newval))
-			goto handle_fault;
+		err = cmpxchg_futex_value_locked(&curval, uaddr, uval, newval);
+		if (err)
+			goto handle_err;
+
 		if (curval == uval)
 			break;
 		uval = curval;
@@ -2456,23 +2459,37 @@ retry:
 	return 0;
 
 	/*
-	 * To handle the page fault we need to drop the locks here. That gives
-	 * the other task (either the highest priority waiter itself or the
-	 * task which stole the rtmutex) the chance to try the fixup of the
-	 * pi_state. So once we are back from handling the fault we need to
-	 * check the pi_state after reacquiring the locks and before trying to
-	 * do another fixup. When the fixup has been done already we simply
-	 * return.
+	 * In order to reschedule or handle a page fault, we need to drop the
+	 * locks here. In the case of a fault, this gives the other task
+	 * (either the highest priority waiter itself or the task which stole
+	 * the rtmutex) the chance to try the fixup of the pi_state. So once we
+	 * are back from handling the fault we need to check the pi_state after
+	 * reacquiring the locks and before trying to do another fixup. When
+	 * the fixup has been done already we simply return.
 	 *
 	 * Note: we hold both hb->lock and pi_mutex->wait_lock. We can safely
 	 * drop hb->lock since the caller owns the hb -> futex_q relation.
 	 * Dropping the pi_mutex->wait_lock requires the state revalidate.
 	 */
-handle_fault:
+handle_err:
 	raw_spin_unlock_irq(&pi_state->pi_mutex.wait_lock);
 	spin_unlock(q->lock_ptr);
 
-	ret = fault_in_user_writeable(uaddr);
+	switch (err) {
+	case -EFAULT:
+		ret = fault_in_user_writeable(uaddr);
+		break;
+
+	case -EAGAIN:
+		cond_resched();
+		ret = 0;
+		break;
+
+	default:
+		WARN_ON_ONCE(1);
+		ret = err;
+		break;
+	}
 
 	spin_lock(q->lock_ptr);
 	raw_spin_lock_irq(&pi_state->pi_mutex.wait_lock);
@@ -3041,10 +3058,8 @@ retry:
 		 * A unconditional UNLOCK_PI op raced against a waiter
 		 * setting the FUTEX_WAITERS bit. Try again.
 		 */
-		if (ret == -EAGAIN) {
-			put_futex_key(&key);
-			goto retry;
-		}
+		if (ret == -EAGAIN)
+			goto pi_retry;
 		/*
 		 * wake_futex_pi has detected invalid state. Tell user
 		 * space.
@@ -3059,9 +3074,19 @@ retry:
 	 * preserve the WAITERS bit not the OWNER_DIED one. We are the
 	 * owner.
 	 */
-	if (cmpxchg_futex_value_locked(&curval, uaddr, uval, 0)) {
+	if ((ret = cmpxchg_futex_value_locked(&curval, uaddr, uval, 0))) {
 		spin_unlock(&hb->lock);
-		goto pi_faulted;
+		switch (ret) {
+		case -EFAULT:
+			goto pi_faulted;
+
+		case -EAGAIN:
+			goto pi_retry;
+
+		default:
+			WARN_ON_ONCE(1);
+			goto out_putkey;
+		}
 	}
 
 	/*
@@ -3075,6 +3100,11 @@ out_putkey:
 	put_futex_key(&key);
 	return ret;
 
+pi_retry:
+	put_futex_key(&key);
+	cond_resched();
+	goto retry;
+
 pi_faulted:
 	put_futex_key(&key);
 
@@ -3435,6 +3465,7 @@ err_unlock:
 static int handle_futex_death(u32 __user *uaddr, struct task_struct *curr, int pi)
 {
 	u32 uval, uninitialized_var(nval), mval;
+	int err;
 
 	/* Futex address must be 32bit aligned */
 	if ((((unsigned long)uaddr) % sizeof(*uaddr)) != 0)
@@ -3444,42 +3475,57 @@ retry:
 	if (get_user(uval, uaddr))
 		return -1;
 
-	if ((uval & FUTEX_TID_MASK) == task_pid_vnr(curr)) {
-		/*
-		 * Ok, this dying thread is truly holding a futex
-		 * of interest. Set the OWNER_DIED bit atomically
-		 * via cmpxchg, and if the value had FUTEX_WAITERS
-		 * set, wake up a waiter (if any). (We have to do a
-		 * futex_wake() even if OWNER_DIED is already set -
-		 * to handle the rare but possible case of recursive
-		 * thread-death.) The rest of the cleanup is done in
-		 * userspace.
-		 */
-		mval = (uval & FUTEX_WAITERS) | FUTEX_OWNER_DIED;
-		/*
-		 * We are not holding a lock here, but we want to have
-		 * the pagefault_disable/enable() protection because
-		 * we want to handle the fault gracefully. If the
-		 * access fails we try to fault in the futex with R/W
-		 * verification via get_user_pages. get_user() above
-		 * does not guarantee R/W access. If that fails we
-		 * give up and leave the futex locked.
-		 */
-		if (cmpxchg_futex_value_locked(&nval, uaddr, uval, mval)) {
+	if ((uval & FUTEX_TID_MASK) != task_pid_vnr(curr))
+		return 0;
+
+	/*
+	 * Ok, this dying thread is truly holding a futex
+	 * of interest. Set the OWNER_DIED bit atomically
+	 * via cmpxchg, and if the value had FUTEX_WAITERS
+	 * set, wake up a waiter (if any). (We have to do a
+	 * futex_wake() even if OWNER_DIED is already set -
+	 * to handle the rare but possible case of recursive
+	 * thread-death.) The rest of the cleanup is done in
+	 * userspace.
+	 */
+	mval = (uval & FUTEX_WAITERS) | FUTEX_OWNER_DIED;
+
+	/*
+	 * We are not holding a lock here, but we want to have
+	 * the pagefault_disable/enable() protection because
+	 * we want to handle the fault gracefully. If the
+	 * access fails we try to fault in the futex with R/W
+	 * verification via get_user_pages. get_user() above
+	 * does not guarantee R/W access. If that fails we
+	 * give up and leave the futex locked.
+	 */
+	if ((err = cmpxchg_futex_value_locked(&nval, uaddr, uval, mval))) {
+		switch (err) {
+		case -EFAULT:
 			if (fault_in_user_writeable(uaddr))
 				return -1;
 			goto retry;
-		}
-		if (nval != uval)
+
+		case -EAGAIN:
+			cond_resched();
 			goto retry;
 
-		/*
-		 * Wake robust non-PI futexes here. The wakeup of
-		 * PI futexes happens in exit_pi_state():
-		 */
-		if (!pi && (uval & FUTEX_WAITERS))
-			futex_wake(uaddr, 1, 1, FUTEX_BITSET_MATCH_ANY);
+		default:
+			WARN_ON_ONCE(1);
+			return err;
+		}
 	}
+
+	if (nval != uval)
+		goto retry;
+
+	/*
+	 * Wake robust non-PI futexes here. The wakeup of
+	 * PI futexes happens in exit_pi_state():
+	 */
+	if (!pi && (uval & FUTEX_WAITERS))
+		futex_wake(uaddr, 1, 1, FUTEX_BITSET_MATCH_ANY);
+
 	return 0;
 }
 
diff --git a/kernel/iomem.c b/kernel/iomem.c
index f7525e14ebc6..93c264444510 100644
--- a/kernel/iomem.c
+++ b/kernel/iomem.c
@@ -55,7 +55,7 @@ static void *try_ram_remap(resource_size_t offset, size_t size,
  *
  * MEMREMAP_WB - matches the default mapping for System RAM on
  * the architecture.  This is usually a read-allocate write-back cache.
- * Morever, if MEMREMAP_WB is specified and the requested remap region is RAM
+ * Moreover, if MEMREMAP_WB is specified and the requested remap region is RAM
  * memremap() will bypass establishing a new mapping and instead return
  * a pointer into the direct map.
  *
@@ -86,7 +86,7 @@ void *memremap(resource_size_t offset, size_t size, unsigned long flags)
 	/* Try all mapping types requested until one returns non-NULL */
 	if (flags & MEMREMAP_WB) {
 		/*
-		 * MEMREMAP_WB is special in that it can be satisifed
+		 * MEMREMAP_WB is special in that it can be satisfied
 		 * from the direct map.  Some archs depend on the
 		 * capability of memremap() to autodetect cases where
 		 * the requested range is potentially in System RAM.
diff --git a/kernel/irq/chip.c b/kernel/irq/chip.c
index 3faef4a77f71..51128bea3846 100644
--- a/kernel/irq/chip.c
+++ b/kernel/irq/chip.c
@@ -1449,6 +1449,10 @@ int irq_chip_set_vcpu_affinity_parent(struct irq_data *data, void *vcpu_info)
 int irq_chip_set_wake_parent(struct irq_data *data, unsigned int on)
 {
 	data = data->parent_data;
+
+	if (data->chip->flags & IRQCHIP_SKIP_SET_WAKE)
+		return 0;
+
 	if (data->chip->irq_set_wake)
 		return data->chip->irq_set_wake(data, on);
 
diff --git a/kernel/irq/devres.c b/kernel/irq/devres.c
index f808c6a97dcc..f6e5515ee077 100644
--- a/kernel/irq/devres.c
+++ b/kernel/irq/devres.c
@@ -220,9 +220,8 @@ devm_irq_alloc_generic_chip(struct device *dev, const char *name, int num_ct,
 			    irq_flow_handler_t handler)
 {
 	struct irq_chip_generic *gc;
-	unsigned long sz = sizeof(*gc) + num_ct * sizeof(struct irq_chip_type);
 
-	gc = devm_kzalloc(dev, sz, GFP_KERNEL);
+	gc = devm_kzalloc(dev, struct_size(gc, chip_types, num_ct), GFP_KERNEL);
 	if (gc)
 		irq_init_generic_chip(gc, name, num_ct,
 				      irq_base, reg_base, handler);
diff --git a/kernel/irq/irqdesc.c b/kernel/irq/irqdesc.c
index 13539e12cd80..9f8a709337cf 100644
--- a/kernel/irq/irqdesc.c
+++ b/kernel/irq/irqdesc.c
@@ -558,6 +558,7 @@ int __init early_irq_init(void)
 		alloc_masks(&desc[i], node);
 		raw_spin_lock_init(&desc[i].lock);
 		lockdep_set_class(&desc[i].lock, &irq_desc_lock_class);
+		mutex_init(&desc[i].request_mutex);
 		desc_set_defaults(i, &desc[i], node, NULL, NULL);
 	}
 	return arch_early_irq_init();
diff --git a/kernel/irq/manage.c b/kernel/irq/manage.c
index 1401afa0d58a..53a081392115 100644
--- a/kernel/irq/manage.c
+++ b/kernel/irq/manage.c
@@ -357,8 +357,10 @@ irq_set_affinity_notifier(unsigned int irq, struct irq_affinity_notify *notify)
 	desc->affinity_notify = notify;
 	raw_spin_unlock_irqrestore(&desc->lock, flags);
 
-	if (old_notify)
+	if (old_notify) {
+		cancel_work_sync(&old_notify->work);
 		kref_put(&old_notify->kref, old_notify->release);
+	}
 
 	return 0;
 }
diff --git a/kernel/irq/timings.c b/kernel/irq/timings.c
index 1e4cb63a5c82..90c735da15d0 100644
--- a/kernel/irq/timings.c
+++ b/kernel/irq/timings.c
@@ -9,6 +9,7 @@
 #include <linux/idr.h>
 #include <linux/irq.h>
 #include <linux/math64.h>
+#include <linux/log2.h>
 
 #include <trace/events/irq.h>
 
@@ -18,16 +19,6 @@ DEFINE_STATIC_KEY_FALSE(irq_timing_enabled);
 
 DEFINE_PER_CPU(struct irq_timings, irq_timings);
 
-struct irqt_stat {
-	u64	next_evt;
-	u64	last_ts;
-	u64	variance;
-	u32	avg;
-	u32	nr_samples;
-	int	anomalies;
-	int	valid;
-};
-
 static DEFINE_IDR(irqt_stats);
 
 void irq_timings_enable(void)
@@ -40,75 +31,360 @@ void irq_timings_disable(void)
 	static_branch_disable(&irq_timing_enabled);
 }
 
-/**
- * irqs_update - update the irq timing statistics with a new timestamp
+/*
+ * The main goal of this algorithm is to predict the next interrupt
+ * occurrence on the current CPU.
+ *
+ * Currently, the interrupt timings are stored in a circular array
+ * buffer every time there is an interrupt, as a tuple: the interrupt
+ * number and the associated timestamp when the event occurred <irq,
+ * timestamp>.
+ *
+ * For every interrupt occurring in a short period of time, we can
+ * measure the elapsed time between the occurrences for the same
+ * interrupt and we end up with a suite of intervals. The experience
+ * showed the interrupts are often coming following a periodic
+ * pattern.
+ *
+ * The objective of the algorithm is to find out this periodic pattern
+ * in a fastest way and use its period to predict the next irq event.
+ *
+ * When the next interrupt event is requested, we are in the situation
+ * where the interrupts are disabled and the circular buffer
+ * containing the timings is filled with the events which happened
+ * after the previous next-interrupt-event request.
+ *
+ * At this point, we read the circular buffer and we fill the irq
+ * related statistics structure. After this step, the circular array
+ * containing the timings is empty because all the values are
+ * dispatched in their corresponding buffers.
+ *
+ * Now for each interrupt, we can predict the next event by using the
+ * suffix array, log interval and exponential moving average
+ *
+ * 1. Suffix array
+ *
+ * Suffix array is an array of all the suffixes of a string. It is
+ * widely used as a data structure for compression, text search, ...
+ * For instance for the word 'banana', the suffixes will be: 'banana'
+ * 'anana' 'nana' 'ana' 'na' 'a'
+ *
+ * Usually, the suffix array is sorted but for our purpose it is
+ * not necessary and won't provide any improvement in the context of
+ * the solved problem where we clearly define the boundaries of the
+ * search by a max period and min period.
+ *
+ * The suffix array will build a suite of intervals of different
+ * length and will look for the repetition of each suite. If the suite
+ * is repeating then we have the period because it is the length of
+ * the suite whatever its position in the buffer.
+ *
+ * 2. Log interval
+ *
+ * We saw the irq timings allow to compute the interval of the
+ * occurrences for a specific interrupt. We can reasonibly assume the
+ * longer is the interval, the higher is the error for the next event
+ * and we can consider storing those interval values into an array
+ * where each slot in the array correspond to an interval at the power
+ * of 2 of the index. For example, index 12 will contain values
+ * between 2^11 and 2^12.
+ *
+ * At the end we have an array of values where at each index defines a
+ * [2^index - 1, 2 ^ index] interval values allowing to store a large
+ * number of values inside a small array.
+ *
+ * For example, if we have the value 1123, then we store it at
+ * ilog2(1123) = 10 index value.
+ *
+ * Storing those value at the specific index is done by computing an
+ * exponential moving average for this specific slot. For instance,
+ * for values 1800, 1123, 1453, ... fall under the same slot (10) and
+ * the exponential moving average is computed every time a new value
+ * is stored at this slot.
+ *
+ * 3. Exponential Moving Average
+ *
+ * The EMA is largely used to track a signal for stocks or as a low
+ * pass filter. The magic of the formula, is it is very simple and the
+ * reactivity of the average can be tuned with the factors called
+ * alpha.
+ *
+ * The higher the alphas are, the faster the average respond to the
+ * signal change. In our case, if a slot in the array is a big
+ * interval, we can have numbers with a big difference between
+ * them. The impact of those differences in the average computation
+ * can be tuned by changing the alpha value.
+ *
+ *
+ *  -- The algorithm --
+ *
+ * We saw the different processing above, now let's see how they are
+ * used together.
+ *
+ * For each interrupt:
+ *	For each interval:
+ *		Compute the index = ilog2(interval)
+ *		Compute a new_ema(buffer[index], interval)
+ *		Store the index in a circular buffer
+ *
+ *	Compute the suffix array of the indexes
+ *
+ *	For each suffix:
+ *		If the suffix is reverse-found 3 times
+ *			Return suffix
+ *
+ *	Return Not found
+ *
+ * However we can not have endless suffix array to be build, it won't
+ * make sense and it will add an extra overhead, so we can restrict
+ * this to a maximum suffix length of 5 and a minimum suffix length of
+ * 2. The experience showed 5 is the majority of the maximum pattern
+ * period found for different devices.
+ *
+ * The result is a pattern finding less than 1us for an interrupt.
  *
- * @irqs: an irqt_stat struct pointer
- * @ts: the new timestamp
+ * Example based on real values:
  *
- * The statistics are computed online, in other words, the code is
- * designed to compute the statistics on a stream of values rather
- * than doing multiple passes on the values to compute the average,
- * then the variance. The integer division introduces a loss of
- * precision but with an acceptable error margin regarding the results
- * we would have with the double floating precision: we are dealing
- * with nanosec, so big numbers, consequently the mantisse is
- * negligeable, especially when converting the time in usec
- * afterwards.
+ * Example 1 : MMC write/read interrupt interval:
  *
- * The computation happens at idle time. When the CPU is not idle, the
- * interrupts' timestamps are stored in the circular buffer, when the
- * CPU goes idle and this routine is called, all the buffer's values
- * are injected in the statistical model continuying to extend the
- * statistics from the previous busy-idle cycle.
+ *	223947, 1240, 1384, 1386, 1386,
+ *	217416, 1236, 1384, 1386, 1387,
+ *	214719, 1241, 1386, 1387, 1384,
+ *	213696, 1234, 1384, 1386, 1388,
+ *	219904, 1240, 1385, 1389, 1385,
+ *	212240, 1240, 1386, 1386, 1386,
+ *	214415, 1236, 1384, 1386, 1387,
+ *	214276, 1234, 1384, 1388, ?
  *
- * The observations showed a device will trigger a burst of periodic
- * interrupts followed by one or two peaks of longer time, for
- * instance when a SD card device flushes its cache, then the periodic
- * intervals occur again. A one second inactivity period resets the
- * stats, that gives us the certitude the statistical values won't
- * exceed 1x10^9, thus the computation won't overflow.
+ * For each element, apply ilog2(value)
  *
- * Basically, the purpose of the algorithm is to watch the periodic
- * interrupts and eliminate the peaks.
+ *	15, 8, 8, 8, 8,
+ *	15, 8, 8, 8, 8,
+ *	15, 8, 8, 8, 8,
+ *	15, 8, 8, 8, 8,
+ *	15, 8, 8, 8, 8,
+ *	15, 8, 8, 8, 8,
+ *	15, 8, 8, 8, 8,
+ *	15, 8, 8, 8, ?
  *
- * An interrupt is considered periodically stable if the interval of
- * its occurences follow the normal distribution, thus the values
- * comply with:
+ * Max period of 5, we take the last (max_period * 3) 15 elements as
+ * we can be confident if the pattern repeats itself three times it is
+ * a repeating pattern.
  *
- *      avg - 3 x stddev < value < avg + 3 x stddev
+ *	             8,
+ *	15, 8, 8, 8, 8,
+ *	15, 8, 8, 8, 8,
+ *	15, 8, 8, 8, ?
  *
- * Which can be simplified to:
+ * Suffixes are:
  *
- *      -3 x stddev < value - avg < 3 x stddev
+ *  1) 8, 15, 8, 8, 8  <- max period
+ *  2) 8, 15, 8, 8
+ *  3) 8, 15, 8
+ *  4) 8, 15           <- min period
  *
- *      abs(value - avg) < 3 x stddev
+ * From there we search the repeating pattern for each suffix.
  *
- * In order to save a costly square root computation, we use the
- * variance. For the record, stddev = sqrt(variance). The equation
- * above becomes:
+ * buffer: 8, 15, 8, 8, 8, 8, 15, 8, 8, 8, 8, 15, 8, 8, 8
+ *         |   |  |  |  |  |   |  |  |  |  |   |  |  |  |
+ *         8, 15, 8, 8, 8  |   |  |  |  |  |   |  |  |  |
+ *                         8, 15, 8, 8, 8  |   |  |  |  |
+ *                                         8, 15, 8, 8, 8
  *
- *      abs(value - avg) < 3 x sqrt(variance)
+ * When moving the suffix, we found exactly 3 matches.
  *
- * And finally we square it:
+ * The first suffix with period 5 is repeating.
  *
- *      (value - avg) ^ 2 < (3 x sqrt(variance)) ^ 2
+ * The next event is (3 * max_period) % suffix_period
  *
- *      (value - avg) x (value - avg) < 9 x variance
+ * In this example, the result 0, so the next event is suffix[0] => 8
  *
- * Statistically speaking, any values out of this interval is
- * considered as an anomaly and is discarded. However, a normal
- * distribution appears when the number of samples is 30 (it is the
- * rule of thumb in statistics, cf. "30 samples" on Internet). When
- * there are three consecutive anomalies, the statistics are resetted.
+ * However, 8 is the index in the array of exponential moving average
+ * which was calculated on the fly when storing the values, so the
+ * interval is ema[8] = 1366
  *
+ *
+ * Example 2:
+ *
+ *	4, 3, 5, 100,
+ *	3, 3, 5, 117,
+ *	4, 4, 5, 112,
+ *	4, 3, 4, 110,
+ *	3, 5, 3, 117,
+ *	4, 4, 5, 112,
+ *	4, 3, 4, 110,
+ *	3, 4, 5, 112,
+ *	4, 3, 4, 110
+ *
+ * ilog2
+ *
+ *	0, 0, 0, 4,
+ *	0, 0, 0, 4,
+ *	0, 0, 0, 4,
+ *	0, 0, 0, 4,
+ *	0, 0, 0, 4,
+ *	0, 0, 0, 4,
+ *	0, 0, 0, 4,
+ *	0, 0, 0, 4,
+ *	0, 0, 0, 4
+ *
+ * Max period 5:
+ *	   0, 0, 4,
+ *	0, 0, 0, 4,
+ *	0, 0, 0, 4,
+ *	0, 0, 0, 4
+ *
+ * Suffixes:
+ *
+ *  1) 0, 0, 4, 0, 0
+ *  2) 0, 0, 4, 0
+ *  3) 0, 0, 4
+ *  4) 0, 0
+ *
+ * buffer: 0, 0, 4, 0, 0, 0, 4, 0, 0, 0, 4, 0, 0, 0, 4
+ *         |  |  |  |  |  |  X
+ *         0, 0, 4, 0, 0, |  X
+ *                        0, 0
+ *
+ * buffer: 0, 0, 4, 0, 0, 0, 4, 0, 0, 0, 4, 0, 0, 0, 4
+ *         |  |  |  |  |  |  |  |  |  |  |  |  |  |  |
+ *         0, 0, 4, 0, |  |  |  |  |  |  |  |  |  |  |
+ *                     0, 0, 4, 0, |  |  |  |  |  |  |
+ *                                 0, 0, 4, 0, |  |  |
+ *                                             0  0  4
+ *
+ * Pattern is found 3 times, the remaining is 1 which results from
+ * (max_period * 3) % suffix_period. This value is the index in the
+ * suffix arrays. The suffix array for a period 4 has the value 4
+ * at index 1.
+ */
+#define EMA_ALPHA_VAL		64
+#define EMA_ALPHA_SHIFT		7
+
+#define PREDICTION_PERIOD_MIN	2
+#define PREDICTION_PERIOD_MAX	5
+#define PREDICTION_FACTOR	4
+#define PREDICTION_MAX		10 /* 2 ^ PREDICTION_MAX useconds */
+#define PREDICTION_BUFFER_SIZE	16 /* slots for EMAs, hardly more than 16 */
+
+struct irqt_stat {
+	u64	last_ts;
+	u64	ema_time[PREDICTION_BUFFER_SIZE];
+	int	timings[IRQ_TIMINGS_SIZE];
+	int	circ_timings[IRQ_TIMINGS_SIZE];
+	int	count;
+};
+
+/*
+ * Exponential moving average computation
  */
-static void irqs_update(struct irqt_stat *irqs, u64 ts)
+static u64 irq_timings_ema_new(u64 value, u64 ema_old)
+{
+	s64 diff;
+
+	if (unlikely(!ema_old))
+		return value;
+
+	diff = (value - ema_old) * EMA_ALPHA_VAL;
+	/*
+	 * We can use a s64 type variable to be added with the u64
+	 * ema_old variable as this one will never have its topmost
+	 * bit set, it will be always smaller than 2^63 nanosec
+	 * interrupt interval (292 years).
+	 */
+	return ema_old + (diff >> EMA_ALPHA_SHIFT);
+}
+
+static int irq_timings_next_event_index(int *buffer, size_t len, int period_max)
+{
+	int i;
+
+	/*
+	 * The buffer contains the suite of intervals, in a ilog2
+	 * basis, we are looking for a repetition. We point the
+	 * beginning of the search three times the length of the
+	 * period beginning at the end of the buffer. We do that for
+	 * each suffix.
+	 */
+	for (i = period_max; i >= PREDICTION_PERIOD_MIN ; i--) {
+
+		int *begin = &buffer[len - (i * 3)];
+		int *ptr = begin;
+
+		/*
+		 * We look if the suite with period 'i' repeat
+		 * itself. If it is truncated at the end, as it
+		 * repeats we can use the period to find out the next
+		 * element.
+		 */
+		while (!memcmp(ptr, begin, i * sizeof(*ptr))) {
+			ptr += i;
+			if (ptr >= &buffer[len])
+				return begin[((i * 3) % i)];
+		}
+	}
+
+	return -1;
+}
+
+static u64 __irq_timings_next_event(struct irqt_stat *irqs, int irq, u64 now)
+{
+	int index, i, period_max, count, start, min = INT_MAX;
+
+	if ((now - irqs->last_ts) >= NSEC_PER_SEC) {
+		irqs->count = irqs->last_ts = 0;
+		return U64_MAX;
+	}
+
+	/*
+	 * As we want to find three times the repetition, we need a
+	 * number of intervals greater or equal to three times the
+	 * maximum period, otherwise we truncate the max period.
+	 */
+	period_max = irqs->count > (3 * PREDICTION_PERIOD_MAX) ?
+		PREDICTION_PERIOD_MAX : irqs->count / 3;
+
+	/*
+	 * If we don't have enough irq timings for this prediction,
+	 * just bail out.
+	 */
+	if (period_max <= PREDICTION_PERIOD_MIN)
+		return U64_MAX;
+
+	/*
+	 * 'count' will depends if the circular buffer wrapped or not
+	 */
+	count = irqs->count < IRQ_TIMINGS_SIZE ?
+		irqs->count : IRQ_TIMINGS_SIZE;
+
+	start = irqs->count < IRQ_TIMINGS_SIZE ?
+		0 : (irqs->count & IRQ_TIMINGS_MASK);
+
+	/*
+	 * Copy the content of the circular buffer into another buffer
+	 * in order to linearize the buffer instead of dealing with
+	 * wrapping indexes and shifted array which will be prone to
+	 * error and extremelly difficult to debug.
+	 */
+	for (i = 0; i < count; i++) {
+		int index = (start + i) & IRQ_TIMINGS_MASK;
+
+		irqs->timings[i] = irqs->circ_timings[index];
+		min = min_t(int, irqs->timings[i], min);
+	}
+
+	index = irq_timings_next_event_index(irqs->timings, count, period_max);
+	if (index < 0)
+		return irqs->last_ts + irqs->ema_time[min];
+
+	return irqs->last_ts + irqs->ema_time[index];
+}
+
+static inline void irq_timings_store(int irq, struct irqt_stat *irqs, u64 ts)
 {
 	u64 old_ts = irqs->last_ts;
-	u64 variance = 0;
 	u64 interval;
-	s64 diff;
+	int index;
 
 	/*
 	 * The timestamps are absolute time values, we need to compute
@@ -135,87 +411,28 @@ static void irqs_update(struct irqt_stat *irqs, u64 ts)
 	 * want as we need another timestamp to compute an interval.
 	 */
 	if (interval >= NSEC_PER_SEC) {
-		memset(irqs, 0, sizeof(*irqs));
-		irqs->last_ts = ts;
+		irqs->count = 0;
 		return;
 	}
 
 	/*
-	 * Pre-compute the delta with the average as the result is
-	 * used several times in this function.
-	 */
-	diff = interval - irqs->avg;
-
-	/*
-	 * Increment the number of samples.
-	 */
-	irqs->nr_samples++;
-
-	/*
-	 * Online variance divided by the number of elements if there
-	 * is more than one sample.  Normally the formula is division
-	 * by nr_samples - 1 but we assume the number of element will be
-	 * more than 32 and dividing by 32 instead of 31 is enough
-	 * precise.
-	 */
-	if (likely(irqs->nr_samples > 1))
-		variance = irqs->variance >> IRQ_TIMINGS_SHIFT;
-
-	/*
-	 * The rule of thumb in statistics for the normal distribution
-	 * is having at least 30 samples in order to have the model to
-	 * apply. Values outside the interval are considered as an
-	 * anomaly.
-	 */
-	if ((irqs->nr_samples >= 30) && ((diff * diff) > (9 * variance))) {
-		/*
-		 * After three consecutive anomalies, we reset the
-		 * stats as it is no longer stable enough.
-		 */
-		if (irqs->anomalies++ >= 3) {
-			memset(irqs, 0, sizeof(*irqs));
-			irqs->last_ts = ts;
-			return;
-		}
-	} else {
-		/*
-		 * The anomalies must be consecutives, so at this
-		 * point, we reset the anomalies counter.
-		 */
-		irqs->anomalies = 0;
-	}
-
-	/*
-	 * The interrupt is considered stable enough to try to predict
-	 * the next event on it.
+	 * Get the index in the ema table for this interrupt. The
+	 * PREDICTION_FACTOR increase the interval size for the array
+	 * of exponential average.
 	 */
-	irqs->valid = 1;
+	index = likely(interval) ?
+		ilog2((interval >> 10) / PREDICTION_FACTOR) : 0;
 
 	/*
-	 * Online average algorithm:
-	 *
-	 *  new_average = average + ((value - average) / count)
-	 *
-	 * The variance computation depends on the new average
-	 * to be computed here first.
-	 *
+	 * Store the index as an element of the pattern in another
+	 * circular array.
 	 */
-	irqs->avg = irqs->avg + (diff >> IRQ_TIMINGS_SHIFT);
+	irqs->circ_timings[irqs->count & IRQ_TIMINGS_MASK] = index;
 
-	/*
-	 * Online variance algorithm:
-	 *
-	 *  new_variance = variance + (value - average) x (value - new_average)
-	 *
-	 * Warning: irqs->avg is updated with the line above, hence
-	 * 'interval - irqs->avg' is no longer equal to 'diff'
-	 */
-	irqs->variance = irqs->variance + (diff * (interval - irqs->avg));
+	irqs->ema_time[index] = irq_timings_ema_new(interval,
+						    irqs->ema_time[index]);
 
-	/*
-	 * Update the next event
-	 */
-	irqs->next_evt = ts + irqs->avg;
+	irqs->count++;
 }
 
 /**
@@ -259,6 +476,9 @@ u64 irq_timings_next_event(u64 now)
 	 */
 	lockdep_assert_irqs_disabled();
 
+	if (!irqts->count)
+		return next_evt;
+
 	/*
 	 * Number of elements in the circular buffer: If it happens it
 	 * was flushed before, then the number of elements could be
@@ -269,21 +489,19 @@ u64 irq_timings_next_event(u64 now)
 	 * type but with the cost of extra computation in the
 	 * interrupt handler hot path. We choose efficiency.
 	 *
-	 * Inject measured irq/timestamp to the statistical model
-	 * while decrementing the counter because we consume the data
-	 * from our circular buffer.
+	 * Inject measured irq/timestamp to the pattern prediction
+	 * model while decrementing the counter because we consume the
+	 * data from our circular buffer.
 	 */
-	for (i = irqts->count & IRQ_TIMINGS_MASK,
-		     irqts->count = min(IRQ_TIMINGS_SIZE, irqts->count);
-	     irqts->count > 0; irqts->count--, i = (i + 1) & IRQ_TIMINGS_MASK) {
 
-		irq = irq_timing_decode(irqts->values[i], &ts);
+	i = (irqts->count & IRQ_TIMINGS_MASK) - 1;
+	irqts->count = min(IRQ_TIMINGS_SIZE, irqts->count);
 
+	for (; irqts->count > 0; irqts->count--, i = (i + 1) & IRQ_TIMINGS_MASK) {
+		irq = irq_timing_decode(irqts->values[i], &ts);
 		s = idr_find(&irqt_stats, irq);
-		if (s) {
-			irqs = this_cpu_ptr(s);
-			irqs_update(irqs, ts);
-		}
+		if (s)
+			irq_timings_store(irq, this_cpu_ptr(s), ts);
 	}
 
 	/*
@@ -294,26 +512,12 @@ u64 irq_timings_next_event(u64 now)
 
 		irqs = this_cpu_ptr(s);
 
-		if (!irqs->valid)
-			continue;
+		ts = __irq_timings_next_event(irqs, i, now);
+		if (ts <= now)
+			return now;
 
-		if (irqs->next_evt <= now) {
-			irq = i;
-			next_evt = now;
-
-			/*
-			 * This interrupt mustn't use in the future
-			 * until new events occur and update the
-			 * statistics.
-			 */
-			irqs->valid = 0;
-			break;
-		}
-
-		if (irqs->next_evt < next_evt) {
-			irq = i;
-			next_evt = irqs->next_evt;
-		}
+		if (ts < next_evt)
+			next_evt = ts;
 	}
 
 	return next_evt;
diff --git a/kernel/irq_work.c b/kernel/irq_work.c
index 6b7cdf17ccf8..73288914ed5e 100644
--- a/kernel/irq_work.c
+++ b/kernel/irq_work.c
@@ -56,61 +56,70 @@ void __weak arch_irq_work_raise(void)
 	 */
 }
 
-/*
- * Enqueue the irq_work @work on @cpu unless it's already pending
- * somewhere.
- *
- * Can be re-enqueued while the callback is still in progress.
- */
-bool irq_work_queue_on(struct irq_work *work, int cpu)
+/* Enqueue on current CPU, work must already be claimed and preempt disabled */
+static void __irq_work_queue_local(struct irq_work *work)
 {
-	/* All work should have been flushed before going offline */
-	WARN_ON_ONCE(cpu_is_offline(cpu));
-
-#ifdef CONFIG_SMP
-
-	/* Arch remote IPI send/receive backend aren't NMI safe */
-	WARN_ON_ONCE(in_nmi());
+	/* If the work is "lazy", handle it from next tick if any */
+	if (work->flags & IRQ_WORK_LAZY) {
+		if (llist_add(&work->llnode, this_cpu_ptr(&lazy_list)) &&
+		    tick_nohz_tick_stopped())
+			arch_irq_work_raise();
+	} else {
+		if (llist_add(&work->llnode, this_cpu_ptr(&raised_list)))
+			arch_irq_work_raise();
+	}
+}
 
+/* Enqueue the irq work @work on the current CPU */
+bool irq_work_queue(struct irq_work *work)
+{
 	/* Only queue if not already pending */
 	if (!irq_work_claim(work))
 		return false;
 
-	if (llist_add(&work->llnode, &per_cpu(raised_list, cpu)))
-		arch_send_call_function_single_ipi(cpu);
-
-#else /* #ifdef CONFIG_SMP */
-	irq_work_queue(work);
-#endif /* #else #ifdef CONFIG_SMP */
+	/* Queue the entry and raise the IPI if needed. */
+	preempt_disable();
+	__irq_work_queue_local(work);
+	preempt_enable();
 
 	return true;
 }
+EXPORT_SYMBOL_GPL(irq_work_queue);
 
-/* Enqueue the irq work @work on the current CPU */
-bool irq_work_queue(struct irq_work *work)
+/*
+ * Enqueue the irq_work @work on @cpu unless it's already pending
+ * somewhere.
+ *
+ * Can be re-enqueued while the callback is still in progress.
+ */
+bool irq_work_queue_on(struct irq_work *work, int cpu)
 {
+#ifndef CONFIG_SMP
+	return irq_work_queue(work);
+
+#else /* CONFIG_SMP: */
+	/* All work should have been flushed before going offline */
+	WARN_ON_ONCE(cpu_is_offline(cpu));
+
 	/* Only queue if not already pending */
 	if (!irq_work_claim(work))
 		return false;
 
-	/* Queue the entry and raise the IPI if needed. */
 	preempt_disable();
-
-	/* If the work is "lazy", handle it from next tick if any */
-	if (work->flags & IRQ_WORK_LAZY) {
-		if (llist_add(&work->llnode, this_cpu_ptr(&lazy_list)) &&
-		    tick_nohz_tick_stopped())
-			arch_irq_work_raise();
+	if (cpu != smp_processor_id()) {
+		/* Arch remote IPI send/receive backend aren't NMI safe */
+		WARN_ON_ONCE(in_nmi());
+		if (llist_add(&work->llnode, &per_cpu(raised_list, cpu)))
+			arch_send_call_function_single_ipi(cpu);
 	} else {
-		if (llist_add(&work->llnode, this_cpu_ptr(&raised_list)))
-			arch_irq_work_raise();
+		__irq_work_queue_local(work);
 	}
-
 	preempt_enable();
 
 	return true;
+#endif /* CONFIG_SMP */
 }
-EXPORT_SYMBOL_GPL(irq_work_queue);
+
 
 bool irq_work_needs_cpu(void)
 {
diff --git a/kernel/jump_label.c b/kernel/jump_label.c
index bad96b476eb6..de6efdecc70d 100644
--- a/kernel/jump_label.c
+++ b/kernel/jump_label.c
@@ -202,11 +202,13 @@ void static_key_disable(struct static_key *key)
 }
 EXPORT_SYMBOL_GPL(static_key_disable);
 
-static void __static_key_slow_dec_cpuslocked(struct static_key *key,
-					   unsigned long rate_limit,
-					   struct delayed_work *work)
+static bool static_key_slow_try_dec(struct static_key *key)
 {
-	lockdep_assert_cpus_held();
+	int val;
+
+	val = atomic_fetch_add_unless(&key->enabled, -1, 1);
+	if (val == 1)
+		return false;
 
 	/*
 	 * The negative count check is valid even when a negative
@@ -215,63 +217,70 @@ static void __static_key_slow_dec_cpuslocked(struct static_key *key,
 	 * returns is unbalanced, because all other static_key_slow_inc()
 	 * instances block while the update is in progress.
 	 */
-	if (!atomic_dec_and_mutex_lock(&key->enabled, &jump_label_mutex)) {
-		WARN(atomic_read(&key->enabled) < 0,
-		     "jump label: negative count!\n");
+	WARN(val < 0, "jump label: negative count!\n");
+	return true;
+}
+
+static void __static_key_slow_dec_cpuslocked(struct static_key *key)
+{
+	lockdep_assert_cpus_held();
+
+	if (static_key_slow_try_dec(key))
 		return;
-	}
 
-	if (rate_limit) {
-		atomic_inc(&key->enabled);
-		schedule_delayed_work(work, rate_limit);
-	} else {
+	jump_label_lock();
+	if (atomic_dec_and_test(&key->enabled))
 		jump_label_update(key);
-	}
 	jump_label_unlock();
 }
 
-static void __static_key_slow_dec(struct static_key *key,
-				  unsigned long rate_limit,
-				  struct delayed_work *work)
+static void __static_key_slow_dec(struct static_key *key)
 {
 	cpus_read_lock();
-	__static_key_slow_dec_cpuslocked(key, rate_limit, work);
+	__static_key_slow_dec_cpuslocked(key);
 	cpus_read_unlock();
 }
 
-static void jump_label_update_timeout(struct work_struct *work)
+void jump_label_update_timeout(struct work_struct *work)
 {
 	struct static_key_deferred *key =
 		container_of(work, struct static_key_deferred, work.work);
-	__static_key_slow_dec(&key->key, 0, NULL);
+	__static_key_slow_dec(&key->key);
 }
+EXPORT_SYMBOL_GPL(jump_label_update_timeout);
 
 void static_key_slow_dec(struct static_key *key)
 {
 	STATIC_KEY_CHECK_USE(key);
-	__static_key_slow_dec(key, 0, NULL);
+	__static_key_slow_dec(key);
 }
 EXPORT_SYMBOL_GPL(static_key_slow_dec);
 
 void static_key_slow_dec_cpuslocked(struct static_key *key)
 {
 	STATIC_KEY_CHECK_USE(key);
-	__static_key_slow_dec_cpuslocked(key, 0, NULL);
+	__static_key_slow_dec_cpuslocked(key);
 }
 
-void static_key_slow_dec_deferred(struct static_key_deferred *key)
+void __static_key_slow_dec_deferred(struct static_key *key,
+				    struct delayed_work *work,
+				    unsigned long timeout)
 {
 	STATIC_KEY_CHECK_USE(key);
-	__static_key_slow_dec(&key->key, key->timeout, &key->work);
+
+	if (static_key_slow_try_dec(key))
+		return;
+
+	schedule_delayed_work(work, timeout);
 }
-EXPORT_SYMBOL_GPL(static_key_slow_dec_deferred);
+EXPORT_SYMBOL_GPL(__static_key_slow_dec_deferred);
 
-void static_key_deferred_flush(struct static_key_deferred *key)
+void __static_key_deferred_flush(void *key, struct delayed_work *work)
 {
 	STATIC_KEY_CHECK_USE(key);
-	flush_delayed_work(&key->work);
+	flush_delayed_work(work);
 }
-EXPORT_SYMBOL_GPL(static_key_deferred_flush);
+EXPORT_SYMBOL_GPL(__static_key_deferred_flush);
 
 void jump_label_rate_limit(struct static_key_deferred *key,
 		unsigned long rl)
diff --git a/kernel/kexec_core.c b/kernel/kexec_core.c
index d7140447be75..fd5c95ff9251 100644
--- a/kernel/kexec_core.c
+++ b/kernel/kexec_core.c
@@ -1150,7 +1150,7 @@ int kernel_kexec(void)
 		error = dpm_suspend_end(PMSG_FREEZE);
 		if (error)
 			goto Resume_devices;
-		error = disable_nonboot_cpus();
+		error = suspend_disable_secondary_cpus();
 		if (error)
 			goto Enable_cpus;
 		local_irq_disable();
@@ -1183,7 +1183,7 @@ int kernel_kexec(void)
  Enable_irqs:
 		local_irq_enable();
  Enable_cpus:
-		enable_nonboot_cpus();
+		suspend_enable_secondary_cpus();
 		dpm_resume_start(PMSG_RESTORE);
  Resume_devices:
 		dpm_resume_end(PMSG_RESTORE);
diff --git a/kernel/kexec_file.c b/kernel/kexec_file.c
index f1d0e00a3971..f7fb8f6a688f 100644
--- a/kernel/kexec_file.c
+++ b/kernel/kexec_file.c
@@ -688,7 +688,6 @@ static int kexec_calculate_store_digests(struct kimage *image)
 		goto out_free_desc;
 
 	desc->tfm   = tfm;
-	desc->flags = 0;
 
 	ret = crypto_shash_init(desc);
 	if (ret < 0)
diff --git a/kernel/kprobes.c b/kernel/kprobes.c
index c83e54727131..b1ea30a5540e 100644
--- a/kernel/kprobes.c
+++ b/kernel/kprobes.c
@@ -709,7 +709,6 @@ static void unoptimize_kprobe(struct kprobe *p, bool force)
 static int reuse_unused_kprobe(struct kprobe *ap)
 {
 	struct optimized_kprobe *op;
-	int ret;
 
 	/*
 	 * Unused kprobe MUST be on the way of delayed unoptimizing (means
@@ -720,9 +719,8 @@ static int reuse_unused_kprobe(struct kprobe *ap)
 	/* Enable the probe again */
 	ap->flags &= ~KPROBE_FLAG_DISABLED;
 	/* Optimize it again (remove from op->list) */
-	ret = kprobe_optready(ap);
-	if (ret)
-		return ret;
+	if (!kprobe_optready(ap))
+		return -EINVAL;
 
 	optimize_kprobe(ap);
 	return 0;
diff --git a/kernel/latencytop.c b/kernel/latencytop.c
index 96b4179cee6a..99a5b5f46dc5 100644
--- a/kernel/latencytop.c
+++ b/kernel/latencytop.c
@@ -120,8 +120,8 @@ account_global_scheduler_latency(struct task_struct *tsk,
 				break;
 			}
 
-			/* 0 and ULONG_MAX entries mean end of backtrace: */
-			if (record == 0 || record == ULONG_MAX)
+			/* 0 entry marks end of backtrace: */
+			if (!record)
 				break;
 		}
 		if (same) {
@@ -141,20 +141,6 @@ account_global_scheduler_latency(struct task_struct *tsk,
 	memcpy(&latency_record[i], lat, sizeof(struct latency_record));
 }
 
-/*
- * Iterator to store a backtrace into a latency record entry
- */
-static inline void store_stacktrace(struct task_struct *tsk,
-					struct latency_record *lat)
-{
-	struct stack_trace trace;
-
-	memset(&trace, 0, sizeof(trace));
-	trace.max_entries = LT_BACKTRACEDEPTH;
-	trace.entries = &lat->backtrace[0];
-	save_stack_trace_tsk(tsk, &trace);
-}
-
 /**
  * __account_scheduler_latency - record an occurred latency
  * @tsk - the task struct of the task hitting the latency
@@ -191,7 +177,8 @@ __account_scheduler_latency(struct task_struct *tsk, int usecs, int inter)
 	lat.count = 1;
 	lat.time = usecs;
 	lat.max = usecs;
-	store_stacktrace(tsk, &lat);
+
+	stack_trace_save_tsk(tsk, lat.backtrace, LT_BACKTRACEDEPTH, 0);
 
 	raw_spin_lock_irqsave(&latency_lock, flags);
 
@@ -210,8 +197,8 @@ __account_scheduler_latency(struct task_struct *tsk, int usecs, int inter)
 				break;
 			}
 
-			/* 0 and ULONG_MAX entries mean end of backtrace: */
-			if (record == 0 || record == ULONG_MAX)
+			/* 0 entry is end of backtrace */
+			if (!record)
 				break;
 		}
 		if (same) {
@@ -252,10 +239,10 @@ static int lstats_show(struct seq_file *m, void *v)
 				   lr->count, lr->time, lr->max);
 			for (q = 0; q < LT_BACKTRACEDEPTH; q++) {
 				unsigned long bt = lr->backtrace[q];
+
 				if (!bt)
 					break;
-				if (bt == ULONG_MAX)
-					break;
+
 				seq_printf(m, " %ps", (void *)bt);
 			}
 			seq_puts(m, "\n");
diff --git a/kernel/livepatch/transition.c b/kernel/livepatch/transition.c
index 9c89ae8b337a..c53370d596be 100644
--- a/kernel/livepatch/transition.c
+++ b/kernel/livepatch/transition.c
@@ -202,15 +202,15 @@ void klp_update_patch_state(struct task_struct *task)
  * Determine whether the given stack trace includes any references to a
  * to-be-patched or to-be-unpatched function.
  */
-static int klp_check_stack_func(struct klp_func *func,
-				struct stack_trace *trace)
+static int klp_check_stack_func(struct klp_func *func, unsigned long *entries,
+				unsigned int nr_entries)
 {
 	unsigned long func_addr, func_size, address;
 	struct klp_ops *ops;
 	int i;
 
-	for (i = 0; i < trace->nr_entries; i++) {
-		address = trace->entries[i];
+	for (i = 0; i < nr_entries; i++) {
+		address = entries[i];
 
 		if (klp_target_state == KLP_UNPATCHED) {
 			 /*
@@ -254,29 +254,25 @@ static int klp_check_stack_func(struct klp_func *func,
 static int klp_check_stack(struct task_struct *task, char *err_buf)
 {
 	static unsigned long entries[MAX_STACK_ENTRIES];
-	struct stack_trace trace;
 	struct klp_object *obj;
 	struct klp_func *func;
-	int ret;
+	int ret, nr_entries;
 
-	trace.skip = 0;
-	trace.nr_entries = 0;
-	trace.max_entries = MAX_STACK_ENTRIES;
-	trace.entries = entries;
-	ret = save_stack_trace_tsk_reliable(task, &trace);
+	ret = stack_trace_save_tsk_reliable(task, entries, ARRAY_SIZE(entries));
 	WARN_ON_ONCE(ret == -ENOSYS);
-	if (ret) {
+	if (ret < 0) {
 		snprintf(err_buf, STACK_ERR_BUF_SIZE,
 			 "%s: %s:%d has an unreliable stack\n",
 			 __func__, task->comm, task->pid);
 		return ret;
 	}
+	nr_entries = ret;
 
 	klp_for_each_object(klp_transition_patch, obj) {
 		if (!obj->patched)
 			continue;
 		klp_for_each_func(obj, func) {
-			ret = klp_check_stack_func(func, &trace);
+			ret = klp_check_stack_func(func, entries, nr_entries);
 			if (ret) {
 				snprintf(err_buf, STACK_ERR_BUF_SIZE,
 					 "%s: %s:%d is sleeping on function %s\n",
diff --git a/kernel/locking/Makefile b/kernel/locking/Makefile
index 392c7f23af76..6fe2f333aecb 100644
--- a/kernel/locking/Makefile
+++ b/kernel/locking/Makefile
@@ -3,7 +3,7 @@
 # and is generally not a function of system call inputs.
 KCOV_INSTRUMENT		:= n
 
-obj-y += mutex.o semaphore.o rwsem.o percpu-rwsem.o
+obj-y += mutex.o semaphore.o rwsem.o percpu-rwsem.o rwsem-xadd.o
 
 ifdef CONFIG_FUNCTION_TRACER
 CFLAGS_REMOVE_lockdep.o = $(CC_FLAGS_FTRACE)
@@ -25,8 +25,7 @@ obj-$(CONFIG_RT_MUTEXES) += rtmutex.o
 obj-$(CONFIG_DEBUG_RT_MUTEXES) += rtmutex-debug.o
 obj-$(CONFIG_DEBUG_SPINLOCK) += spinlock.o
 obj-$(CONFIG_DEBUG_SPINLOCK) += spinlock_debug.o
-obj-$(CONFIG_RWSEM_GENERIC_SPINLOCK) += rwsem-spinlock.o
-obj-$(CONFIG_RWSEM_XCHGADD_ALGORITHM) += rwsem-xadd.o
 obj-$(CONFIG_QUEUED_RWLOCKS) += qrwlock.o
 obj-$(CONFIG_LOCK_TORTURE_TEST) += locktorture.o
 obj-$(CONFIG_WW_MUTEX_SELFTEST) += test-ww_mutex.o
+obj-$(CONFIG_LOCK_EVENT_COUNTS) += lock_events.o
diff --git a/kernel/locking/lock_events.c b/kernel/locking/lock_events.c
new file mode 100644
index 000000000000..fa2c2f951c6b
--- /dev/null
+++ b/kernel/locking/lock_events.c
@@ -0,0 +1,179 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * Authors: Waiman Long <waiman.long@hpe.com>
+ */
+
+/*
+ * Collect locking event counts
+ */
+#include <linux/debugfs.h>
+#include <linux/sched.h>
+#include <linux/sched/clock.h>
+#include <linux/fs.h>
+
+#include "lock_events.h"
+
+#undef  LOCK_EVENT
+#define LOCK_EVENT(name)	[LOCKEVENT_ ## name] = #name,
+
+#define LOCK_EVENTS_DIR		"lock_event_counts"
+
+/*
+ * When CONFIG_LOCK_EVENT_COUNTS is enabled, event counts of different
+ * types of locks will be reported under the <debugfs>/lock_event_counts/
+ * directory. See lock_events_list.h for the list of available locking
+ * events.
+ *
+ * Writing to the special ".reset_counts" file will reset all the above
+ * locking event counts. This is a very slow operation and so should not
+ * be done frequently.
+ *
+ * These event counts are implemented as per-cpu variables which are
+ * summed and computed whenever the corresponding debugfs files are read. This
+ * minimizes added overhead making the counts usable even in a production
+ * environment.
+ */
+static const char * const lockevent_names[lockevent_num + 1] = {
+
+#include "lock_events_list.h"
+
+	[LOCKEVENT_reset_cnts] = ".reset_counts",
+};
+
+/*
+ * Per-cpu counts
+ */
+DEFINE_PER_CPU(unsigned long, lockevents[lockevent_num]);
+
+/*
+ * The lockevent_read() function can be overridden.
+ */
+ssize_t __weak lockevent_read(struct file *file, char __user *user_buf,
+			      size_t count, loff_t *ppos)
+{
+	char buf[64];
+	int cpu, id, len;
+	u64 sum = 0;
+
+	/*
+	 * Get the counter ID stored in file->f_inode->i_private
+	 */
+	id = (long)file_inode(file)->i_private;
+
+	if (id >= lockevent_num)
+		return -EBADF;
+
+	for_each_possible_cpu(cpu)
+		sum += per_cpu(lockevents[id], cpu);
+	len = snprintf(buf, sizeof(buf) - 1, "%llu\n", sum);
+
+	return simple_read_from_buffer(user_buf, count, ppos, buf, len);
+}
+
+/*
+ * Function to handle write request
+ *
+ * When idx = reset_cnts, reset all the counts.
+ */
+static ssize_t lockevent_write(struct file *file, const char __user *user_buf,
+			   size_t count, loff_t *ppos)
+{
+	int cpu;
+
+	/*
+	 * Get the counter ID stored in file->f_inode->i_private
+	 */
+	if ((long)file_inode(file)->i_private != LOCKEVENT_reset_cnts)
+		return count;
+
+	for_each_possible_cpu(cpu) {
+		int i;
+		unsigned long *ptr = per_cpu_ptr(lockevents, cpu);
+
+		for (i = 0 ; i < lockevent_num; i++)
+			WRITE_ONCE(ptr[i], 0);
+	}
+	return count;
+}
+
+/*
+ * Debugfs data structures
+ */
+static const struct file_operations fops_lockevent = {
+	.read = lockevent_read,
+	.write = lockevent_write,
+	.llseek = default_llseek,
+};
+
+#ifdef CONFIG_PARAVIRT_SPINLOCKS
+#include <asm/paravirt.h>
+
+static bool __init skip_lockevent(const char *name)
+{
+	static int pv_on __initdata = -1;
+
+	if (pv_on < 0)
+		pv_on = !pv_is_native_spin_unlock();
+	/*
+	 * Skip PV qspinlock events on bare metal.
+	 */
+	if (!pv_on && !memcmp(name, "pv_", 3))
+		return true;
+	return false;
+}
+#else
+static inline bool skip_lockevent(const char *name)
+{
+	return false;
+}
+#endif
+
+/*
+ * Initialize debugfs for the locking event counts.
+ */
+static int __init init_lockevent_counts(void)
+{
+	struct dentry *d_counts = debugfs_create_dir(LOCK_EVENTS_DIR, NULL);
+	int i;
+
+	if (!d_counts)
+		goto out;
+
+	/*
+	 * Create the debugfs files
+	 *
+	 * As reading from and writing to the stat files can be slow, only
+	 * root is allowed to do the read/write to limit impact to system
+	 * performance.
+	 */
+	for (i = 0; i < lockevent_num; i++) {
+		if (skip_lockevent(lockevent_names[i]))
+			continue;
+		if (!debugfs_create_file(lockevent_names[i], 0400, d_counts,
+					 (void *)(long)i, &fops_lockevent))
+			goto fail_undo;
+	}
+
+	if (!debugfs_create_file(lockevent_names[LOCKEVENT_reset_cnts], 0200,
+				 d_counts, (void *)(long)LOCKEVENT_reset_cnts,
+				 &fops_lockevent))
+		goto fail_undo;
+
+	return 0;
+fail_undo:
+	debugfs_remove_recursive(d_counts);
+out:
+	pr_warn("Could not create '%s' debugfs entries\n", LOCK_EVENTS_DIR);
+	return -ENOMEM;
+}
+fs_initcall(init_lockevent_counts);
diff --git a/kernel/locking/lock_events.h b/kernel/locking/lock_events.h
new file mode 100644
index 000000000000..feb1acc54611
--- /dev/null
+++ b/kernel/locking/lock_events.h
@@ -0,0 +1,59 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * Authors: Waiman Long <longman@redhat.com>
+ */
+
+#ifndef __LOCKING_LOCK_EVENTS_H
+#define __LOCKING_LOCK_EVENTS_H
+
+enum lock_events {
+
+#include "lock_events_list.h"
+
+	lockevent_num,	/* Total number of lock event counts */
+	LOCKEVENT_reset_cnts = lockevent_num,
+};
+
+#ifdef CONFIG_LOCK_EVENT_COUNTS
+/*
+ * Per-cpu counters
+ */
+DECLARE_PER_CPU(unsigned long, lockevents[lockevent_num]);
+
+/*
+ * Increment the PV qspinlock statistical counters
+ */
+static inline void __lockevent_inc(enum lock_events event, bool cond)
+{
+	if (cond)
+		__this_cpu_inc(lockevents[event]);
+}
+
+#define lockevent_inc(ev)	  __lockevent_inc(LOCKEVENT_ ##ev, true)
+#define lockevent_cond_inc(ev, c) __lockevent_inc(LOCKEVENT_ ##ev, c)
+
+static inline void __lockevent_add(enum lock_events event, int inc)
+{
+	__this_cpu_add(lockevents[event], inc);
+}
+
+#define lockevent_add(ev, c)	__lockevent_add(LOCKEVENT_ ##ev, c)
+
+#else  /* CONFIG_LOCK_EVENT_COUNTS */
+
+#define lockevent_inc(ev)
+#define lockevent_add(ev, c)
+#define lockevent_cond_inc(ev, c)
+
+#endif /* CONFIG_LOCK_EVENT_COUNTS */
+#endif /* __LOCKING_LOCK_EVENTS_H */
diff --git a/kernel/locking/lock_events_list.h b/kernel/locking/lock_events_list.h
new file mode 100644
index 000000000000..ad7668cfc9da
--- /dev/null
+++ b/kernel/locking/lock_events_list.h
@@ -0,0 +1,67 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * Authors: Waiman Long <longman@redhat.com>
+ */
+
+#ifndef LOCK_EVENT
+#define LOCK_EVENT(name)	LOCKEVENT_ ## name,
+#endif
+
+#ifdef CONFIG_QUEUED_SPINLOCKS
+#ifdef CONFIG_PARAVIRT_SPINLOCKS
+/*
+ * Locking events for PV qspinlock.
+ */
+LOCK_EVENT(pv_hash_hops)	/* Average # of hops per hashing operation */
+LOCK_EVENT(pv_kick_unlock)	/* # of vCPU kicks issued at unlock time   */
+LOCK_EVENT(pv_kick_wake)	/* # of vCPU kicks for pv_latency_wake	   */
+LOCK_EVENT(pv_latency_kick)	/* Average latency (ns) of vCPU kick	   */
+LOCK_EVENT(pv_latency_wake)	/* Average latency (ns) of kick-to-wakeup  */
+LOCK_EVENT(pv_lock_stealing)	/* # of lock stealing operations	   */
+LOCK_EVENT(pv_spurious_wakeup)	/* # of spurious wakeups in non-head vCPUs */
+LOCK_EVENT(pv_wait_again)	/* # of wait's after queue head vCPU kick  */
+LOCK_EVENT(pv_wait_early)	/* # of early vCPU wait's		   */
+LOCK_EVENT(pv_wait_head)	/* # of vCPU wait's at the queue head	   */
+LOCK_EVENT(pv_wait_node)	/* # of vCPU wait's at non-head queue node */
+#endif /* CONFIG_PARAVIRT_SPINLOCKS */
+
+/*
+ * Locking events for qspinlock
+ *
+ * Subtracting lock_use_node[234] from lock_slowpath will give you
+ * lock_use_node1.
+ */
+LOCK_EVENT(lock_pending)	/* # of locking ops via pending code	     */
+LOCK_EVENT(lock_slowpath)	/* # of locking ops via MCS lock queue	     */
+LOCK_EVENT(lock_use_node2)	/* # of locking ops that use 2nd percpu node */
+LOCK_EVENT(lock_use_node3)	/* # of locking ops that use 3rd percpu node */
+LOCK_EVENT(lock_use_node4)	/* # of locking ops that use 4th percpu node */
+LOCK_EVENT(lock_no_node)	/* # of locking ops w/o using percpu node    */
+#endif /* CONFIG_QUEUED_SPINLOCKS */
+
+/*
+ * Locking events for rwsem
+ */
+LOCK_EVENT(rwsem_sleep_reader)	/* # of reader sleeps			*/
+LOCK_EVENT(rwsem_sleep_writer)	/* # of writer sleeps			*/
+LOCK_EVENT(rwsem_wake_reader)	/* # of reader wakeups			*/
+LOCK_EVENT(rwsem_wake_writer)	/* # of writer wakeups			*/
+LOCK_EVENT(rwsem_opt_wlock)	/* # of write locks opt-spin acquired	*/
+LOCK_EVENT(rwsem_opt_fail)	/* # of failed opt-spinnings		*/
+LOCK_EVENT(rwsem_rlock)		/* # of read locks acquired		*/
+LOCK_EVENT(rwsem_rlock_fast)	/* # of fast read locks acquired	*/
+LOCK_EVENT(rwsem_rlock_fail)	/* # of failed read lock acquisitions	*/
+LOCK_EVENT(rwsem_rtrylock)	/* # of read trylock calls		*/
+LOCK_EVENT(rwsem_wlock)		/* # of write locks acquired		*/
+LOCK_EVENT(rwsem_wlock_fail)	/* # of failed write lock acquisitions	*/
+LOCK_EVENT(rwsem_wtrylock)	/* # of write trylock calls		*/
diff --git a/kernel/locking/lockdep.c b/kernel/locking/lockdep.c
index 34cdcbedda49..d06190fa5082 100644
--- a/kernel/locking/lockdep.c
+++ b/kernel/locking/lockdep.c
@@ -434,29 +434,14 @@ static void print_lockdep_off(const char *bug_msg)
 #endif
 }
 
-static int save_trace(struct stack_trace *trace)
+static int save_trace(struct lock_trace *trace)
 {
-	trace->nr_entries = 0;
-	trace->max_entries = MAX_STACK_TRACE_ENTRIES - nr_stack_trace_entries;
-	trace->entries = stack_trace + nr_stack_trace_entries;
-
-	trace->skip = 3;
-
-	save_stack_trace(trace);
-
-	/*
-	 * Some daft arches put -1 at the end to indicate its a full trace.
-	 *
-	 * <rant> this is buggy anyway, since it takes a whole extra entry so a
-	 * complete trace that maxes out the entries provided will be reported
-	 * as incomplete, friggin useless </rant>
-	 */
-	if (trace->nr_entries != 0 &&
-	    trace->entries[trace->nr_entries-1] == ULONG_MAX)
-		trace->nr_entries--;
-
-	trace->max_entries = trace->nr_entries;
+	unsigned long *entries = stack_trace + nr_stack_trace_entries;
+	unsigned int max_entries;
 
+	trace->offset = nr_stack_trace_entries;
+	max_entries = MAX_STACK_TRACE_ENTRIES - nr_stack_trace_entries;
+	trace->nr_entries = stack_trace_save(entries, max_entries, 3);
 	nr_stack_trace_entries += trace->nr_entries;
 
 	if (nr_stack_trace_entries >= MAX_STACK_TRACE_ENTRIES-1) {
@@ -516,11 +501,11 @@ static char get_usage_char(struct lock_class *class, enum lock_usage_bit bit)
 {
 	char c = '.';
 
-	if (class->usage_mask & lock_flag(bit + 2))
+	if (class->usage_mask & lock_flag(bit + LOCK_USAGE_DIR_MASK))
 		c = '+';
 	if (class->usage_mask & lock_flag(bit)) {
 		c = '-';
-		if (class->usage_mask & lock_flag(bit + 2))
+		if (class->usage_mask & lock_flag(bit + LOCK_USAGE_DIR_MASK))
 			c = '?';
 	}
 
@@ -649,6 +634,9 @@ static int static_obj(const void *obj)
 		      end   = (unsigned long) &_end,
 		      addr  = (unsigned long) obj;
 
+	if (arch_is_kernel_initmem_freed(addr))
+		return 0;
+
 	/*
 	 * static variable?
 	 */
@@ -1207,7 +1195,7 @@ static struct lock_list *alloc_list_entry(void)
 static int add_lock_to_list(struct lock_class *this,
 			    struct lock_class *links_to, struct list_head *head,
 			    unsigned long ip, int distance,
-			    struct stack_trace *trace)
+			    struct lock_trace *trace)
 {
 	struct lock_list *entry;
 	/*
@@ -1426,6 +1414,13 @@ static inline int __bfs_backwards(struct lock_list *src_entry,
  * checking.
  */
 
+static void print_lock_trace(struct lock_trace *trace, unsigned int spaces)
+{
+	unsigned long *entries = stack_trace + trace->offset;
+
+	stack_trace_print(entries, trace->nr_entries, spaces);
+}
+
 /*
  * Print a dependency chain entry (this is only done when a deadlock
  * has been detected):
@@ -1438,8 +1433,7 @@ print_circular_bug_entry(struct lock_list *target, int depth)
 	printk("\n-> #%u", depth);
 	print_lock_name(target->class);
 	printk(KERN_CONT ":\n");
-	print_stack_trace(&target->trace, 6);
-
+	print_lock_trace(&target->trace, 6);
 	return 0;
 }
 
@@ -1533,10 +1527,9 @@ static inline int class_equal(struct lock_list *entry, void *data)
 }
 
 static noinline int print_circular_bug(struct lock_list *this,
-				struct lock_list *target,
-				struct held_lock *check_src,
-				struct held_lock *check_tgt,
-				struct stack_trace *trace)
+				       struct lock_list *target,
+				       struct held_lock *check_src,
+				       struct held_lock *check_tgt)
 {
 	struct task_struct *curr = current;
 	struct lock_list *parent;
@@ -1676,19 +1669,25 @@ check_redundant(struct lock_list *root, struct lock_class *target,
 }
 
 #if defined(CONFIG_TRACE_IRQFLAGS) && defined(CONFIG_PROVE_LOCKING)
+
+static inline int usage_accumulate(struct lock_list *entry, void *mask)
+{
+	*(unsigned long *)mask |= entry->class->usage_mask;
+
+	return 0;
+}
+
 /*
  * Forwards and backwards subgraph searching, for the purposes of
  * proving that two subgraphs can be connected by a new dependency
  * without creating any illegal irq-safe -> irq-unsafe lock dependency.
  */
 
-static inline int usage_match(struct lock_list *entry, void *bit)
+static inline int usage_match(struct lock_list *entry, void *mask)
 {
-	return entry->class->usage_mask & (1 << (enum lock_usage_bit)bit);
+	return entry->class->usage_mask & *(unsigned long *)mask;
 }
 
-
-
 /*
  * Find a node in the forwards-direction dependency sub-graph starting
  * at @root->class that matches @bit.
@@ -1700,14 +1699,14 @@ static inline int usage_match(struct lock_list *entry, void *bit)
  * Return <0 on error.
  */
 static int
-find_usage_forwards(struct lock_list *root, enum lock_usage_bit bit,
+find_usage_forwards(struct lock_list *root, unsigned long usage_mask,
 			struct lock_list **target_entry)
 {
 	int result;
 
 	debug_atomic_inc(nr_find_usage_forwards_checks);
 
-	result = __bfs_forwards(root, (void *)bit, usage_match, target_entry);
+	result = __bfs_forwards(root, &usage_mask, usage_match, target_entry);
 
 	return result;
 }
@@ -1723,14 +1722,14 @@ find_usage_forwards(struct lock_list *root, enum lock_usage_bit bit,
  * Return <0 on error.
  */
 static int
-find_usage_backwards(struct lock_list *root, enum lock_usage_bit bit,
+find_usage_backwards(struct lock_list *root, unsigned long usage_mask,
 			struct lock_list **target_entry)
 {
 	int result;
 
 	debug_atomic_inc(nr_find_usage_backwards_checks);
 
-	result = __bfs_backwards(root, (void *)bit, usage_match, target_entry);
+	result = __bfs_backwards(root, &usage_mask, usage_match, target_entry);
 
 	return result;
 }
@@ -1752,7 +1751,7 @@ static void print_lock_class_header(struct lock_class *class, int depth)
 
 			len += printk("%*s   %s", depth, "", usage_str[bit]);
 			len += printk(KERN_CONT " at:\n");
-			print_stack_trace(class->usage_traces + bit, len);
+			print_lock_trace(class->usage_traces + bit, len);
 		}
 	}
 	printk("%*s }\n", depth, "");
@@ -1777,7 +1776,7 @@ print_shortest_lock_dependencies(struct lock_list *leaf,
 	do {
 		print_lock_class_header(entry->class, depth);
 		printk("%*s ... acquired at:\n", depth, "");
-		print_stack_trace(&entry->trace, 2);
+		print_lock_trace(&entry->trace, 2);
 		printk("\n");
 
 		if (depth == 0 && (entry != root)) {
@@ -1890,14 +1889,14 @@ print_bad_irq_dependency(struct task_struct *curr,
 	print_lock_name(backwards_entry->class);
 	pr_warn("\n... which became %s-irq-safe at:\n", irqclass);
 
-	print_stack_trace(backwards_entry->class->usage_traces + bit1, 1);
+	print_lock_trace(backwards_entry->class->usage_traces + bit1, 1);
 
 	pr_warn("\nto a %s-irq-unsafe lock:\n", irqclass);
 	print_lock_name(forwards_entry->class);
 	pr_warn("\n... which became %s-irq-unsafe at:\n", irqclass);
 	pr_warn("...");
 
-	print_stack_trace(forwards_entry->class->usage_traces + bit2, 1);
+	print_lock_trace(forwards_entry->class->usage_traces + bit2, 1);
 
 	pr_warn("\nother info that might help us debug this:\n\n");
 	print_irq_lock_scenario(backwards_entry, forwards_entry,
@@ -1922,39 +1921,6 @@ print_bad_irq_dependency(struct task_struct *curr,
 	return 0;
 }
 
-static int
-check_usage(struct task_struct *curr, struct held_lock *prev,
-	    struct held_lock *next, enum lock_usage_bit bit_backwards,
-	    enum lock_usage_bit bit_forwards, const char *irqclass)
-{
-	int ret;
-	struct lock_list this, that;
-	struct lock_list *uninitialized_var(target_entry);
-	struct lock_list *uninitialized_var(target_entry1);
-
-	this.parent = NULL;
-
-	this.class = hlock_class(prev);
-	ret = find_usage_backwards(&this, bit_backwards, &target_entry);
-	if (ret < 0)
-		return print_bfs_bug(ret);
-	if (ret == 1)
-		return ret;
-
-	that.parent = NULL;
-	that.class = hlock_class(next);
-	ret = find_usage_forwards(&that, bit_forwards, &target_entry1);
-	if (ret < 0)
-		return print_bfs_bug(ret);
-	if (ret == 1)
-		return ret;
-
-	return print_bad_irq_dependency(curr, &this, &that,
-			target_entry, target_entry1,
-			prev, next,
-			bit_backwards, bit_forwards, irqclass);
-}
-
 static const char *state_names[] = {
 #define LOCKDEP_STATE(__STATE) \
 	__stringify(__STATE),
@@ -1971,9 +1937,19 @@ static const char *state_rnames[] = {
 
 static inline const char *state_name(enum lock_usage_bit bit)
 {
-	return (bit & LOCK_USAGE_READ_MASK) ? state_rnames[bit >> 2] : state_names[bit >> 2];
+	if (bit & LOCK_USAGE_READ_MASK)
+		return state_rnames[bit >> LOCK_USAGE_DIR_MASK];
+	else
+		return state_names[bit >> LOCK_USAGE_DIR_MASK];
 }
 
+/*
+ * The bit number is encoded like:
+ *
+ *  bit0: 0 exclusive, 1 read lock
+ *  bit1: 0 used in irq, 1 irq enabled
+ *  bit2-n: state
+ */
 static int exclusive_bit(int new_bit)
 {
 	int state = new_bit & LOCK_USAGE_STATE_MASK;
@@ -1985,45 +1961,160 @@ static int exclusive_bit(int new_bit)
 	return state | (dir ^ LOCK_USAGE_DIR_MASK);
 }
 
+/*
+ * Observe that when given a bitmask where each bitnr is encoded as above, a
+ * right shift of the mask transforms the individual bitnrs as -1 and
+ * conversely, a left shift transforms into +1 for the individual bitnrs.
+ *
+ * So for all bits whose number have LOCK_ENABLED_* set (bitnr1 == 1), we can
+ * create the mask with those bit numbers using LOCK_USED_IN_* (bitnr1 == 0)
+ * instead by subtracting the bit number by 2, or shifting the mask right by 2.
+ *
+ * Similarly, bitnr1 == 0 becomes bitnr1 == 1 by adding 2, or shifting left 2.
+ *
+ * So split the mask (note that LOCKF_ENABLED_IRQ_ALL|LOCKF_USED_IN_IRQ_ALL is
+ * all bits set) and recompose with bitnr1 flipped.
+ */
+static unsigned long invert_dir_mask(unsigned long mask)
+{
+	unsigned long excl = 0;
+
+	/* Invert dir */
+	excl |= (mask & LOCKF_ENABLED_IRQ_ALL) >> LOCK_USAGE_DIR_MASK;
+	excl |= (mask & LOCKF_USED_IN_IRQ_ALL) << LOCK_USAGE_DIR_MASK;
+
+	return excl;
+}
+
+/*
+ * As above, we clear bitnr0 (LOCK_*_READ off) with bitmask ops. First, for all
+ * bits with bitnr0 set (LOCK_*_READ), add those with bitnr0 cleared (LOCK_*).
+ * And then mask out all bitnr0.
+ */
+static unsigned long exclusive_mask(unsigned long mask)
+{
+	unsigned long excl = invert_dir_mask(mask);
+
+	/* Strip read */
+	excl |= (excl & LOCKF_IRQ_READ) >> LOCK_USAGE_READ_MASK;
+	excl &= ~LOCKF_IRQ_READ;
+
+	return excl;
+}
+
+/*
+ * Retrieve the _possible_ original mask to which @mask is
+ * exclusive. Ie: this is the opposite of exclusive_mask().
+ * Note that 2 possible original bits can match an exclusive
+ * bit: one has LOCK_USAGE_READ_MASK set, the other has it
+ * cleared. So both are returned for each exclusive bit.
+ */
+static unsigned long original_mask(unsigned long mask)
+{
+	unsigned long excl = invert_dir_mask(mask);
+
+	/* Include read in existing usages */
+	excl |= (excl & LOCKF_IRQ) << LOCK_USAGE_READ_MASK;
+
+	return excl;
+}
+
+/*
+ * Find the first pair of bit match between an original
+ * usage mask and an exclusive usage mask.
+ */
+static int find_exclusive_match(unsigned long mask,
+				unsigned long excl_mask,
+				enum lock_usage_bit *bitp,
+				enum lock_usage_bit *excl_bitp)
+{
+	int bit, excl;
+
+	for_each_set_bit(bit, &mask, LOCK_USED) {
+		excl = exclusive_bit(bit);
+		if (excl_mask & lock_flag(excl)) {
+			*bitp = bit;
+			*excl_bitp = excl;
+			return 0;
+		}
+	}
+	return -1;
+}
+
+/*
+ * Prove that the new dependency does not connect a hardirq-safe(-read)
+ * lock with a hardirq-unsafe lock - to achieve this we search
+ * the backwards-subgraph starting at <prev>, and the
+ * forwards-subgraph starting at <next>:
+ */
 static int check_irq_usage(struct task_struct *curr, struct held_lock *prev,
-			   struct held_lock *next, enum lock_usage_bit bit)
+			   struct held_lock *next)
 {
+	unsigned long usage_mask = 0, forward_mask, backward_mask;
+	enum lock_usage_bit forward_bit = 0, backward_bit = 0;
+	struct lock_list *uninitialized_var(target_entry1);
+	struct lock_list *uninitialized_var(target_entry);
+	struct lock_list this, that;
+	int ret;
+
 	/*
-	 * Prove that the new dependency does not connect a hardirq-safe
-	 * lock with a hardirq-unsafe lock - to achieve this we search
-	 * the backwards-subgraph starting at <prev>, and the
-	 * forwards-subgraph starting at <next>:
+	 * Step 1: gather all hard/soft IRQs usages backward in an
+	 * accumulated usage mask.
 	 */
-	if (!check_usage(curr, prev, next, bit,
-			   exclusive_bit(bit), state_name(bit)))
-		return 0;
+	this.parent = NULL;
+	this.class = hlock_class(prev);
+
+	ret = __bfs_backwards(&this, &usage_mask, usage_accumulate, NULL);
+	if (ret < 0)
+		return print_bfs_bug(ret);
 
-	bit++; /* _READ */
+	usage_mask &= LOCKF_USED_IN_IRQ_ALL;
+	if (!usage_mask)
+		return 1;
 
 	/*
-	 * Prove that the new dependency does not connect a hardirq-safe-read
-	 * lock with a hardirq-unsafe lock - to achieve this we search
-	 * the backwards-subgraph starting at <prev>, and the
-	 * forwards-subgraph starting at <next>:
+	 * Step 2: find exclusive uses forward that match the previous
+	 * backward accumulated mask.
 	 */
-	if (!check_usage(curr, prev, next, bit,
-			   exclusive_bit(bit), state_name(bit)))
-		return 0;
+	forward_mask = exclusive_mask(usage_mask);
 
-	return 1;
-}
+	that.parent = NULL;
+	that.class = hlock_class(next);
 
-static int
-check_prev_add_irq(struct task_struct *curr, struct held_lock *prev,
-		struct held_lock *next)
-{
-#define LOCKDEP_STATE(__STATE)						\
-	if (!check_irq_usage(curr, prev, next, LOCK_USED_IN_##__STATE))	\
-		return 0;
-#include "lockdep_states.h"
-#undef LOCKDEP_STATE
+	ret = find_usage_forwards(&that, forward_mask, &target_entry1);
+	if (ret < 0)
+		return print_bfs_bug(ret);
+	if (ret == 1)
+		return ret;
 
-	return 1;
+	/*
+	 * Step 3: we found a bad match! Now retrieve a lock from the backward
+	 * list whose usage mask matches the exclusive usage mask from the
+	 * lock found on the forward list.
+	 */
+	backward_mask = original_mask(target_entry1->class->usage_mask);
+
+	ret = find_usage_backwards(&this, backward_mask, &target_entry);
+	if (ret < 0)
+		return print_bfs_bug(ret);
+	if (DEBUG_LOCKS_WARN_ON(ret == 1))
+		return 1;
+
+	/*
+	 * Step 4: narrow down to a pair of incompatible usage bits
+	 * and report it.
+	 */
+	ret = find_exclusive_match(target_entry->class->usage_mask,
+				   target_entry1->class->usage_mask,
+				   &backward_bit, &forward_bit);
+	if (DEBUG_LOCKS_WARN_ON(ret == -1))
+		return 1;
+
+	return print_bad_irq_dependency(curr, &this, &that,
+			target_entry, target_entry1,
+			prev, next,
+			backward_bit, forward_bit,
+			state_name(backward_bit));
 }
 
 static void inc_chains(void)
@@ -2040,9 +2131,8 @@ static void inc_chains(void)
 
 #else
 
-static inline int
-check_prev_add_irq(struct task_struct *curr, struct held_lock *prev,
-		struct held_lock *next)
+static inline int check_irq_usage(struct task_struct *curr,
+				  struct held_lock *prev, struct held_lock *next)
 {
 	return 1;
 }
@@ -2170,8 +2260,7 @@ check_deadlock(struct task_struct *curr, struct held_lock *next,
  */
 static int
 check_prev_add(struct task_struct *curr, struct held_lock *prev,
-	       struct held_lock *next, int distance, struct stack_trace *trace,
-	       int (*save)(struct stack_trace *trace))
+	       struct held_lock *next, int distance, struct lock_trace *trace)
 {
 	struct lock_list *uninitialized_var(target_entry);
 	struct lock_list *entry;
@@ -2209,20 +2298,20 @@ check_prev_add(struct task_struct *curr, struct held_lock *prev,
 	this.parent = NULL;
 	ret = check_noncircular(&this, hlock_class(prev), &target_entry);
 	if (unlikely(!ret)) {
-		if (!trace->entries) {
+		if (!trace->nr_entries) {
 			/*
-			 * If @save fails here, the printing might trigger
-			 * a WARN but because of the !nr_entries it should
-			 * not do bad things.
+			 * If save_trace fails here, the printing might
+			 * trigger a WARN but because of the !nr_entries it
+			 * should not do bad things.
 			 */
-			save(trace);
+			save_trace(trace);
 		}
-		return print_circular_bug(&this, target_entry, next, prev, trace);
+		return print_circular_bug(&this, target_entry, next, prev);
 	}
 	else if (unlikely(ret < 0))
 		return print_bfs_bug(ret);
 
-	if (!check_prev_add_irq(curr, prev, next))
+	if (!check_irq_usage(curr, prev, next))
 		return 0;
 
 	/*
@@ -2265,7 +2354,7 @@ check_prev_add(struct task_struct *curr, struct held_lock *prev,
 		return print_bfs_bug(ret);
 
 
-	if (!trace->entries && !save(trace))
+	if (!trace->nr_entries && !save_trace(trace))
 		return 0;
 
 	/*
@@ -2297,14 +2386,9 @@ check_prev_add(struct task_struct *curr, struct held_lock *prev,
 static int
 check_prevs_add(struct task_struct *curr, struct held_lock *next)
 {
+	struct lock_trace trace = { .nr_entries = 0 };
 	int depth = curr->lockdep_depth;
 	struct held_lock *hlock;
-	struct stack_trace trace = {
-		.nr_entries = 0,
-		.max_entries = 0,
-		.entries = NULL,
-		.skip = 0,
-	};
 
 	/*
 	 * Debugging checks.
@@ -2330,7 +2414,8 @@ check_prevs_add(struct task_struct *curr, struct held_lock *next)
 		 * added:
 		 */
 		if (hlock->read != 2 && hlock->check) {
-			int ret = check_prev_add(curr, hlock, next, distance, &trace, save_trace);
+			int ret = check_prev_add(curr, hlock, next, distance,
+						 &trace);
 			if (!ret)
 				return 0;
 
@@ -2731,6 +2816,10 @@ static inline int validate_chain(struct task_struct *curr,
 {
 	return 1;
 }
+
+static void print_lock_trace(struct lock_trace *trace, unsigned int spaces)
+{
+}
 #endif
 
 /*
@@ -2784,6 +2873,12 @@ static void check_chain_key(struct task_struct *curr)
 #endif
 }
 
+static int mark_lock(struct task_struct *curr, struct held_lock *this,
+		     enum lock_usage_bit new_bit);
+
+#if defined(CONFIG_TRACE_IRQFLAGS) && defined(CONFIG_PROVE_LOCKING)
+
+
 static void
 print_usage_bug_scenario(struct held_lock *lock)
 {
@@ -2827,7 +2922,7 @@ print_usage_bug(struct task_struct *curr, struct held_lock *this,
 	print_lock(this);
 
 	pr_warn("{%s} state was registered at:\n", usage_str[prev_bit]);
-	print_stack_trace(hlock_class(this)->usage_traces + prev_bit, 1);
+	print_lock_trace(hlock_class(this)->usage_traces + prev_bit, 1);
 
 	print_irqtrace_events(curr);
 	pr_warn("\nother info that might help us debug this:\n");
@@ -2853,10 +2948,6 @@ valid_state(struct task_struct *curr, struct held_lock *this,
 	return 1;
 }
 
-static int mark_lock(struct task_struct *curr, struct held_lock *this,
-		     enum lock_usage_bit new_bit);
-
-#if defined(CONFIG_TRACE_IRQFLAGS) && defined(CONFIG_PROVE_LOCKING)
 
 /*
  * print irq inversion bug:
@@ -2936,7 +3027,7 @@ check_usage_forwards(struct task_struct *curr, struct held_lock *this,
 
 	root.parent = NULL;
 	root.class = hlock_class(this);
-	ret = find_usage_forwards(&root, bit, &target_entry);
+	ret = find_usage_forwards(&root, lock_flag(bit), &target_entry);
 	if (ret < 0)
 		return print_bfs_bug(ret);
 	if (ret == 1)
@@ -2960,7 +3051,7 @@ check_usage_backwards(struct task_struct *curr, struct held_lock *this,
 
 	root.parent = NULL;
 	root.class = hlock_class(this);
-	ret = find_usage_backwards(&root, bit, &target_entry);
+	ret = find_usage_backwards(&root, lock_flag(bit), &target_entry);
 	if (ret < 0)
 		return print_bfs_bug(ret);
 	if (ret == 1)
@@ -3015,7 +3106,7 @@ static int (*state_verbose_f[])(struct lock_class *class) = {
 static inline int state_verbose(enum lock_usage_bit bit,
 				struct lock_class *class)
 {
-	return state_verbose_f[bit >> 2](class);
+	return state_verbose_f[bit >> LOCK_USAGE_DIR_MASK](class);
 }
 
 typedef int (*check_usage_f)(struct task_struct *, struct held_lock *,
@@ -3157,7 +3248,7 @@ void lockdep_hardirqs_on(unsigned long ip)
 	/*
 	 * See the fine text that goes along with this variable definition.
 	 */
-	if (DEBUG_LOCKS_WARN_ON(unlikely(early_boot_irqs_disabled)))
+	if (DEBUG_LOCKS_WARN_ON(early_boot_irqs_disabled))
 		return;
 
 	/*
@@ -4689,8 +4780,8 @@ static void free_zapped_rcu(struct rcu_head *ch)
 		return;
 
 	raw_local_irq_save(flags);
-	if (!graph_lock())
-		goto out_irq;
+	arch_spin_lock(&lockdep_lock);
+	current->lockdep_recursion = 1;
 
 	/* closed head */
 	pf = delayed_free.pf + (delayed_free.index ^ 1);
@@ -4702,8 +4793,8 @@ static void free_zapped_rcu(struct rcu_head *ch)
 	 */
 	call_rcu_zapped(delayed_free.pf + delayed_free.index);
 
-	graph_unlock();
-out_irq:
+	current->lockdep_recursion = 0;
+	arch_spin_unlock(&lockdep_lock);
 	raw_local_irq_restore(flags);
 }
 
@@ -4744,21 +4835,17 @@ static void lockdep_free_key_range_reg(void *start, unsigned long size)
 {
 	struct pending_free *pf;
 	unsigned long flags;
-	int locked;
 
 	init_data_structures_once();
 
 	raw_local_irq_save(flags);
-	locked = graph_lock();
-	if (!locked)
-		goto out_irq;
-
+	arch_spin_lock(&lockdep_lock);
+	current->lockdep_recursion = 1;
 	pf = get_pending_free();
 	__lockdep_free_key_range(pf, start, size);
 	call_rcu_zapped(pf);
-
-	graph_unlock();
-out_irq:
+	current->lockdep_recursion = 0;
+	arch_spin_unlock(&lockdep_lock);
 	raw_local_irq_restore(flags);
 
 	/*
diff --git a/kernel/locking/lockdep_internals.h b/kernel/locking/lockdep_internals.h
index d4c197425f68..150ec3f0c5b5 100644
--- a/kernel/locking/lockdep_internals.h
+++ b/kernel/locking/lockdep_internals.h
@@ -42,13 +42,35 @@ enum {
 	__LOCKF(USED)
 };
 
-#define LOCKF_ENABLED_IRQ (LOCKF_ENABLED_HARDIRQ | LOCKF_ENABLED_SOFTIRQ)
-#define LOCKF_USED_IN_IRQ (LOCKF_USED_IN_HARDIRQ | LOCKF_USED_IN_SOFTIRQ)
+#define LOCKDEP_STATE(__STATE)	LOCKF_ENABLED_##__STATE |
+static const unsigned long LOCKF_ENABLED_IRQ =
+#include "lockdep_states.h"
+	0;
+#undef LOCKDEP_STATE
+
+#define LOCKDEP_STATE(__STATE)	LOCKF_USED_IN_##__STATE |
+static const unsigned long LOCKF_USED_IN_IRQ =
+#include "lockdep_states.h"
+	0;
+#undef LOCKDEP_STATE
+
+#define LOCKDEP_STATE(__STATE)	LOCKF_ENABLED_##__STATE##_READ |
+static const unsigned long LOCKF_ENABLED_IRQ_READ =
+#include "lockdep_states.h"
+	0;
+#undef LOCKDEP_STATE
+
+#define LOCKDEP_STATE(__STATE)	LOCKF_USED_IN_##__STATE##_READ |
+static const unsigned long LOCKF_USED_IN_IRQ_READ =
+#include "lockdep_states.h"
+	0;
+#undef LOCKDEP_STATE
+
+#define LOCKF_ENABLED_IRQ_ALL (LOCKF_ENABLED_IRQ | LOCKF_ENABLED_IRQ_READ)
+#define LOCKF_USED_IN_IRQ_ALL (LOCKF_USED_IN_IRQ | LOCKF_USED_IN_IRQ_READ)
 
-#define LOCKF_ENABLED_IRQ_READ \
-		(LOCKF_ENABLED_HARDIRQ_READ | LOCKF_ENABLED_SOFTIRQ_READ)
-#define LOCKF_USED_IN_IRQ_READ \
-		(LOCKF_USED_IN_HARDIRQ_READ | LOCKF_USED_IN_SOFTIRQ_READ)
+#define LOCKF_IRQ (LOCKF_ENABLED_IRQ | LOCKF_USED_IN_IRQ)
+#define LOCKF_IRQ_READ (LOCKF_ENABLED_IRQ_READ | LOCKF_USED_IN_IRQ_READ)
 
 /*
  * CONFIG_LOCKDEP_SMALL is defined for sparc. Sparc requires .text,
diff --git a/kernel/locking/locktorture.c b/kernel/locking/locktorture.c
index ad40a2617063..80a463d31a8d 100644
--- a/kernel/locking/locktorture.c
+++ b/kernel/locking/locktorture.c
@@ -829,7 +829,9 @@ static void lock_torture_cleanup(void)
 						"End of test: SUCCESS");
 
 	kfree(cxt.lwsa);
+	cxt.lwsa = NULL;
 	kfree(cxt.lrsa);
+	cxt.lrsa = NULL;
 
 end:
 	torture_cleanup_end();
diff --git a/kernel/locking/percpu-rwsem.c b/kernel/locking/percpu-rwsem.c
index 883cf1b92d90..f17dad99eec8 100644
--- a/kernel/locking/percpu-rwsem.c
+++ b/kernel/locking/percpu-rwsem.c
@@ -7,6 +7,8 @@
 #include <linux/sched.h>
 #include <linux/errno.h>
 
+#include "rwsem.h"
+
 int __percpu_init_rwsem(struct percpu_rw_semaphore *sem,
 			const char *name, struct lock_class_key *rwsem_key)
 {
diff --git a/kernel/locking/qspinlock.c b/kernel/locking/qspinlock.c
index 5e9247dc2515..e14b32c69639 100644
--- a/kernel/locking/qspinlock.c
+++ b/kernel/locking/qspinlock.c
@@ -395,7 +395,7 @@ void queued_spin_lock_slowpath(struct qspinlock *lock, u32 val)
 	 * 0,1,0 -> 0,0,1
 	 */
 	clear_pending_set_locked(lock);
-	qstat_inc(qstat_lock_pending, true);
+	lockevent_inc(lock_pending);
 	return;
 
 	/*
@@ -403,7 +403,7 @@ void queued_spin_lock_slowpath(struct qspinlock *lock, u32 val)
 	 * queuing.
 	 */
 queue:
-	qstat_inc(qstat_lock_slowpath, true);
+	lockevent_inc(lock_slowpath);
 pv_queue:
 	node = this_cpu_ptr(&qnodes[0].mcs);
 	idx = node->count++;
@@ -419,7 +419,7 @@ pv_queue:
 	 * simple enough.
 	 */
 	if (unlikely(idx >= MAX_NODES)) {
-		qstat_inc(qstat_lock_no_node, true);
+		lockevent_inc(lock_no_node);
 		while (!queued_spin_trylock(lock))
 			cpu_relax();
 		goto release;
@@ -430,7 +430,7 @@ pv_queue:
 	/*
 	 * Keep counts of non-zero index values:
 	 */
-	qstat_inc(qstat_lock_use_node2 + idx - 1, idx);
+	lockevent_cond_inc(lock_use_node2 + idx - 1, idx);
 
 	/*
 	 * Ensure that we increment the head node->count before initialising
diff --git a/kernel/locking/qspinlock_paravirt.h b/kernel/locking/qspinlock_paravirt.h
index 8f36c27c1794..89bab079e7a4 100644
--- a/kernel/locking/qspinlock_paravirt.h
+++ b/kernel/locking/qspinlock_paravirt.h
@@ -89,7 +89,7 @@ static inline bool pv_hybrid_queued_unfair_trylock(struct qspinlock *lock)
 
 		if (!(val & _Q_LOCKED_PENDING_MASK) &&
 		   (cmpxchg_acquire(&lock->locked, 0, _Q_LOCKED_VAL) == 0)) {
-			qstat_inc(qstat_pv_lock_stealing, true);
+			lockevent_inc(pv_lock_stealing);
 			return true;
 		}
 		if (!(val & _Q_TAIL_MASK) || (val & _Q_PENDING_MASK))
@@ -219,7 +219,7 @@ static struct qspinlock **pv_hash(struct qspinlock *lock, struct pv_node *node)
 		hopcnt++;
 		if (!cmpxchg(&he->lock, NULL, lock)) {
 			WRITE_ONCE(he->node, node);
-			qstat_hop(hopcnt);
+			lockevent_pv_hop(hopcnt);
 			return &he->lock;
 		}
 	}
@@ -320,8 +320,8 @@ static void pv_wait_node(struct mcs_spinlock *node, struct mcs_spinlock *prev)
 		smp_store_mb(pn->state, vcpu_halted);
 
 		if (!READ_ONCE(node->locked)) {
-			qstat_inc(qstat_pv_wait_node, true);
-			qstat_inc(qstat_pv_wait_early, wait_early);
+			lockevent_inc(pv_wait_node);
+			lockevent_cond_inc(pv_wait_early, wait_early);
 			pv_wait(&pn->state, vcpu_halted);
 		}
 
@@ -339,7 +339,8 @@ static void pv_wait_node(struct mcs_spinlock *node, struct mcs_spinlock *prev)
 		 * So it is better to spin for a while in the hope that the
 		 * MCS lock will be released soon.
 		 */
-		qstat_inc(qstat_pv_spurious_wakeup, !READ_ONCE(node->locked));
+		lockevent_cond_inc(pv_spurious_wakeup,
+				  !READ_ONCE(node->locked));
 	}
 
 	/*
@@ -416,7 +417,7 @@ pv_wait_head_or_lock(struct qspinlock *lock, struct mcs_spinlock *node)
 	/*
 	 * Tracking # of slowpath locking operations
 	 */
-	qstat_inc(qstat_lock_slowpath, true);
+	lockevent_inc(lock_slowpath);
 
 	for (;; waitcnt++) {
 		/*
@@ -464,8 +465,8 @@ pv_wait_head_or_lock(struct qspinlock *lock, struct mcs_spinlock *node)
 			}
 		}
 		WRITE_ONCE(pn->state, vcpu_hashed);
-		qstat_inc(qstat_pv_wait_head, true);
-		qstat_inc(qstat_pv_wait_again, waitcnt);
+		lockevent_inc(pv_wait_head);
+		lockevent_cond_inc(pv_wait_again, waitcnt);
 		pv_wait(&lock->locked, _Q_SLOW_VAL);
 
 		/*
@@ -528,7 +529,7 @@ __pv_queued_spin_unlock_slowpath(struct qspinlock *lock, u8 locked)
 	 * vCPU is harmless other than the additional latency in completing
 	 * the unlock.
 	 */
-	qstat_inc(qstat_pv_kick_unlock, true);
+	lockevent_inc(pv_kick_unlock);
 	pv_kick(node->cpu);
 }
 
diff --git a/kernel/locking/qspinlock_stat.h b/kernel/locking/qspinlock_stat.h
index d73f85388d5c..54152670ff24 100644
--- a/kernel/locking/qspinlock_stat.h
+++ b/kernel/locking/qspinlock_stat.h
@@ -9,262 +9,105 @@
  * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
  * GNU General Public License for more details.
  *
- * Authors: Waiman Long <waiman.long@hpe.com>
+ * Authors: Waiman Long <longman@redhat.com>
  */
 
-/*
- * When queued spinlock statistical counters are enabled, the following
- * debugfs files will be created for reporting the counter values:
- *
- * <debugfs>/qlockstat/
- *   pv_hash_hops	- average # of hops per hashing operation
- *   pv_kick_unlock	- # of vCPU kicks issued at unlock time
- *   pv_kick_wake	- # of vCPU kicks used for computing pv_latency_wake
- *   pv_latency_kick	- average latency (ns) of vCPU kick operation
- *   pv_latency_wake	- average latency (ns) from vCPU kick to wakeup
- *   pv_lock_stealing	- # of lock stealing operations
- *   pv_spurious_wakeup	- # of spurious wakeups in non-head vCPUs
- *   pv_wait_again	- # of wait's after a queue head vCPU kick
- *   pv_wait_early	- # of early vCPU wait's
- *   pv_wait_head	- # of vCPU wait's at the queue head
- *   pv_wait_node	- # of vCPU wait's at a non-head queue node
- *   lock_pending	- # of locking operations via pending code
- *   lock_slowpath	- # of locking operations via MCS lock queue
- *   lock_use_node2	- # of locking operations that use 2nd per-CPU node
- *   lock_use_node3	- # of locking operations that use 3rd per-CPU node
- *   lock_use_node4	- # of locking operations that use 4th per-CPU node
- *   lock_no_node	- # of locking operations without using per-CPU node
- *
- * Subtracting lock_use_node[234] from lock_slowpath will give you
- * lock_use_node1.
- *
- * Writing to the "reset_counters" file will reset all the above counter
- * values.
- *
- * These statistical counters are implemented as per-cpu variables which are
- * summed and computed whenever the corresponding debugfs files are read. This
- * minimizes added overhead making the counters usable even in a production
- * environment.
- *
- * There may be slight difference between pv_kick_wake and pv_kick_unlock.
- */
-enum qlock_stats {
-	qstat_pv_hash_hops,
-	qstat_pv_kick_unlock,
-	qstat_pv_kick_wake,
-	qstat_pv_latency_kick,
-	qstat_pv_latency_wake,
-	qstat_pv_lock_stealing,
-	qstat_pv_spurious_wakeup,
-	qstat_pv_wait_again,
-	qstat_pv_wait_early,
-	qstat_pv_wait_head,
-	qstat_pv_wait_node,
-	qstat_lock_pending,
-	qstat_lock_slowpath,
-	qstat_lock_use_node2,
-	qstat_lock_use_node3,
-	qstat_lock_use_node4,
-	qstat_lock_no_node,
-	qstat_num,	/* Total number of statistical counters */
-	qstat_reset_cnts = qstat_num,
-};
+#include "lock_events.h"
 
-#ifdef CONFIG_QUEUED_LOCK_STAT
+#ifdef CONFIG_LOCK_EVENT_COUNTS
+#ifdef CONFIG_PARAVIRT_SPINLOCKS
 /*
- * Collect pvqspinlock statistics
+ * Collect pvqspinlock locking event counts
  */
-#include <linux/debugfs.h>
 #include <linux/sched.h>
 #include <linux/sched/clock.h>
 #include <linux/fs.h>
 
-static const char * const qstat_names[qstat_num + 1] = {
-	[qstat_pv_hash_hops]	   = "pv_hash_hops",
-	[qstat_pv_kick_unlock]     = "pv_kick_unlock",
-	[qstat_pv_kick_wake]       = "pv_kick_wake",
-	[qstat_pv_spurious_wakeup] = "pv_spurious_wakeup",
-	[qstat_pv_latency_kick]	   = "pv_latency_kick",
-	[qstat_pv_latency_wake]    = "pv_latency_wake",
-	[qstat_pv_lock_stealing]   = "pv_lock_stealing",
-	[qstat_pv_wait_again]      = "pv_wait_again",
-	[qstat_pv_wait_early]      = "pv_wait_early",
-	[qstat_pv_wait_head]       = "pv_wait_head",
-	[qstat_pv_wait_node]       = "pv_wait_node",
-	[qstat_lock_pending]       = "lock_pending",
-	[qstat_lock_slowpath]      = "lock_slowpath",
-	[qstat_lock_use_node2]	   = "lock_use_node2",
-	[qstat_lock_use_node3]	   = "lock_use_node3",
-	[qstat_lock_use_node4]	   = "lock_use_node4",
-	[qstat_lock_no_node]	   = "lock_no_node",
-	[qstat_reset_cnts]         = "reset_counters",
-};
+#define EVENT_COUNT(ev)	lockevents[LOCKEVENT_ ## ev]
 
 /*
- * Per-cpu counters
+ * PV specific per-cpu counter
  */
-static DEFINE_PER_CPU(unsigned long, qstats[qstat_num]);
 static DEFINE_PER_CPU(u64, pv_kick_time);
 
 /*
- * Function to read and return the qlock statistical counter values
+ * Function to read and return the PV qspinlock counts.
  *
  * The following counters are handled specially:
- * 1. qstat_pv_latency_kick
+ * 1. pv_latency_kick
  *    Average kick latency (ns) = pv_latency_kick/pv_kick_unlock
- * 2. qstat_pv_latency_wake
+ * 2. pv_latency_wake
  *    Average wake latency (ns) = pv_latency_wake/pv_kick_wake
- * 3. qstat_pv_hash_hops
+ * 3. pv_hash_hops
  *    Average hops/hash = pv_hash_hops/pv_kick_unlock
  */
-static ssize_t qstat_read(struct file *file, char __user *user_buf,
-			  size_t count, loff_t *ppos)
+ssize_t lockevent_read(struct file *file, char __user *user_buf,
+		       size_t count, loff_t *ppos)
 {
 	char buf[64];
-	int cpu, counter, len;
-	u64 stat = 0, kicks = 0;
+	int cpu, id, len;
+	u64 sum = 0, kicks = 0;
 
 	/*
 	 * Get the counter ID stored in file->f_inode->i_private
 	 */
-	counter = (long)file_inode(file)->i_private;
+	id = (long)file_inode(file)->i_private;
 
-	if (counter >= qstat_num)
+	if (id >= lockevent_num)
 		return -EBADF;
 
 	for_each_possible_cpu(cpu) {
-		stat += per_cpu(qstats[counter], cpu);
+		sum += per_cpu(lockevents[id], cpu);
 		/*
-		 * Need to sum additional counter for some of them
+		 * Need to sum additional counters for some of them
 		 */
-		switch (counter) {
+		switch (id) {
 
-		case qstat_pv_latency_kick:
-		case qstat_pv_hash_hops:
-			kicks += per_cpu(qstats[qstat_pv_kick_unlock], cpu);
+		case LOCKEVENT_pv_latency_kick:
+		case LOCKEVENT_pv_hash_hops:
+			kicks += per_cpu(EVENT_COUNT(pv_kick_unlock), cpu);
 			break;
 
-		case qstat_pv_latency_wake:
-			kicks += per_cpu(qstats[qstat_pv_kick_wake], cpu);
+		case LOCKEVENT_pv_latency_wake:
+			kicks += per_cpu(EVENT_COUNT(pv_kick_wake), cpu);
 			break;
 		}
 	}
 
-	if (counter == qstat_pv_hash_hops) {
+	if (id == LOCKEVENT_pv_hash_hops) {
 		u64 frac = 0;
 
 		if (kicks) {
-			frac = 100ULL * do_div(stat, kicks);
+			frac = 100ULL * do_div(sum, kicks);
 			frac = DIV_ROUND_CLOSEST_ULL(frac, kicks);
 		}
 
 		/*
 		 * Return a X.XX decimal number
 		 */
-		len = snprintf(buf, sizeof(buf) - 1, "%llu.%02llu\n", stat, frac);
+		len = snprintf(buf, sizeof(buf) - 1, "%llu.%02llu\n",
+			       sum, frac);
 	} else {
 		/*
 		 * Round to the nearest ns
 		 */
-		if ((counter == qstat_pv_latency_kick) ||
-		    (counter == qstat_pv_latency_wake)) {
+		if ((id == LOCKEVENT_pv_latency_kick) ||
+		    (id == LOCKEVENT_pv_latency_wake)) {
 			if (kicks)
-				stat = DIV_ROUND_CLOSEST_ULL(stat, kicks);
+				sum = DIV_ROUND_CLOSEST_ULL(sum, kicks);
 		}
-		len = snprintf(buf, sizeof(buf) - 1, "%llu\n", stat);
+		len = snprintf(buf, sizeof(buf) - 1, "%llu\n", sum);
 	}
 
 	return simple_read_from_buffer(user_buf, count, ppos, buf, len);
 }
 
 /*
- * Function to handle write request
- *
- * When counter = reset_cnts, reset all the counter values.
- * Since the counter updates aren't atomic, the resetting is done twice
- * to make sure that the counters are very likely to be all cleared.
- */
-static ssize_t qstat_write(struct file *file, const char __user *user_buf,
-			   size_t count, loff_t *ppos)
-{
-	int cpu;
-
-	/*
-	 * Get the counter ID stored in file->f_inode->i_private
-	 */
-	if ((long)file_inode(file)->i_private != qstat_reset_cnts)
-		return count;
-
-	for_each_possible_cpu(cpu) {
-		int i;
-		unsigned long *ptr = per_cpu_ptr(qstats, cpu);
-
-		for (i = 0 ; i < qstat_num; i++)
-			WRITE_ONCE(ptr[i], 0);
-	}
-	return count;
-}
-
-/*
- * Debugfs data structures
- */
-static const struct file_operations fops_qstat = {
-	.read = qstat_read,
-	.write = qstat_write,
-	.llseek = default_llseek,
-};
-
-/*
- * Initialize debugfs for the qspinlock statistical counters
- */
-static int __init init_qspinlock_stat(void)
-{
-	struct dentry *d_qstat = debugfs_create_dir("qlockstat", NULL);
-	int i;
-
-	if (!d_qstat)
-		goto out;
-
-	/*
-	 * Create the debugfs files
-	 *
-	 * As reading from and writing to the stat files can be slow, only
-	 * root is allowed to do the read/write to limit impact to system
-	 * performance.
-	 */
-	for (i = 0; i < qstat_num; i++)
-		if (!debugfs_create_file(qstat_names[i], 0400, d_qstat,
-					 (void *)(long)i, &fops_qstat))
-			goto fail_undo;
-
-	if (!debugfs_create_file(qstat_names[qstat_reset_cnts], 0200, d_qstat,
-				 (void *)(long)qstat_reset_cnts, &fops_qstat))
-		goto fail_undo;
-
-	return 0;
-fail_undo:
-	debugfs_remove_recursive(d_qstat);
-out:
-	pr_warn("Could not create 'qlockstat' debugfs entries\n");
-	return -ENOMEM;
-}
-fs_initcall(init_qspinlock_stat);
-
-/*
- * Increment the PV qspinlock statistical counters
- */
-static inline void qstat_inc(enum qlock_stats stat, bool cond)
-{
-	if (cond)
-		this_cpu_inc(qstats[stat]);
-}
-
-/*
  * PV hash hop count
  */
-static inline void qstat_hop(int hopcnt)
+static inline void lockevent_pv_hop(int hopcnt)
 {
-	this_cpu_add(qstats[qstat_pv_hash_hops], hopcnt);
+	this_cpu_add(EVENT_COUNT(pv_hash_hops), hopcnt);
 }
 
 /*
@@ -276,7 +119,7 @@ static inline void __pv_kick(int cpu)
 
 	per_cpu(pv_kick_time, cpu) = start;
 	pv_kick(cpu);
-	this_cpu_add(qstats[qstat_pv_latency_kick], sched_clock() - start);
+	this_cpu_add(EVENT_COUNT(pv_latency_kick), sched_clock() - start);
 }
 
 /*
@@ -289,18 +132,19 @@ static inline void __pv_wait(u8 *ptr, u8 val)
 	*pkick_time = 0;
 	pv_wait(ptr, val);
 	if (*pkick_time) {
-		this_cpu_add(qstats[qstat_pv_latency_wake],
+		this_cpu_add(EVENT_COUNT(pv_latency_wake),
 			     sched_clock() - *pkick_time);
-		qstat_inc(qstat_pv_kick_wake, true);
+		lockevent_inc(pv_kick_wake);
 	}
 }
 
 #define pv_kick(c)	__pv_kick(c)
 #define pv_wait(p, v)	__pv_wait(p, v)
 
-#else /* CONFIG_QUEUED_LOCK_STAT */
+#endif /* CONFIG_PARAVIRT_SPINLOCKS */
+
+#else /* CONFIG_LOCK_EVENT_COUNTS */
 
-static inline void qstat_inc(enum qlock_stats stat, bool cond)	{ }
-static inline void qstat_hop(int hopcnt)			{ }
+static inline void lockevent_pv_hop(int hopcnt)	{ }
 
-#endif /* CONFIG_QUEUED_LOCK_STAT */
+#endif /* CONFIG_LOCK_EVENT_COUNTS */
diff --git a/kernel/locking/rwsem-spinlock.c b/kernel/locking/rwsem-spinlock.c
deleted file mode 100644
index a7ffb2a96ede..000000000000
--- a/kernel/locking/rwsem-spinlock.c
+++ /dev/null
@@ -1,339 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0
-/* rwsem-spinlock.c: R/W semaphores: contention handling functions for
- * generic spinlock implementation
- *
- * Copyright (c) 2001   David Howells (dhowells@redhat.com).
- * - Derived partially from idea by Andrea Arcangeli <andrea@suse.de>
- * - Derived also from comments by Linus
- */
-#include <linux/rwsem.h>
-#include <linux/sched/signal.h>
-#include <linux/sched/debug.h>
-#include <linux/export.h>
-
-enum rwsem_waiter_type {
-	RWSEM_WAITING_FOR_WRITE,
-	RWSEM_WAITING_FOR_READ
-};
-
-struct rwsem_waiter {
-	struct list_head list;
-	struct task_struct *task;
-	enum rwsem_waiter_type type;
-};
-
-int rwsem_is_locked(struct rw_semaphore *sem)
-{
-	int ret = 1;
-	unsigned long flags;
-
-	if (raw_spin_trylock_irqsave(&sem->wait_lock, flags)) {
-		ret = (sem->count != 0);
-		raw_spin_unlock_irqrestore(&sem->wait_lock, flags);
-	}
-	return ret;
-}
-EXPORT_SYMBOL(rwsem_is_locked);
-
-/*
- * initialise the semaphore
- */
-void __init_rwsem(struct rw_semaphore *sem, const char *name,
-		  struct lock_class_key *key)
-{
-#ifdef CONFIG_DEBUG_LOCK_ALLOC
-	/*
-	 * Make sure we are not reinitializing a held semaphore:
-	 */
-	debug_check_no_locks_freed((void *)sem, sizeof(*sem));
-	lockdep_init_map(&sem->dep_map, name, key, 0);
-#endif
-	sem->count = 0;
-	raw_spin_lock_init(&sem->wait_lock);
-	INIT_LIST_HEAD(&sem->wait_list);
-}
-EXPORT_SYMBOL(__init_rwsem);
-
-/*
- * handle the lock release when processes blocked on it that can now run
- * - if we come here, then:
- *   - the 'active count' _reached_ zero
- *   - the 'waiting count' is non-zero
- * - the spinlock must be held by the caller
- * - woken process blocks are discarded from the list after having task zeroed
- * - writers are only woken if wakewrite is non-zero
- */
-static inline struct rw_semaphore *
-__rwsem_do_wake(struct rw_semaphore *sem, int wakewrite)
-{
-	struct rwsem_waiter *waiter;
-	struct task_struct *tsk;
-	int woken;
-
-	waiter = list_entry(sem->wait_list.next, struct rwsem_waiter, list);
-
-	if (waiter->type == RWSEM_WAITING_FOR_WRITE) {
-		if (wakewrite)
-			/* Wake up a writer. Note that we do not grant it the
-			 * lock - it will have to acquire it when it runs. */
-			wake_up_process(waiter->task);
-		goto out;
-	}
-
-	/* grant an infinite number of read locks to the front of the queue */
-	woken = 0;
-	do {
-		struct list_head *next = waiter->list.next;
-
-		list_del(&waiter->list);
-		tsk = waiter->task;
-		/*
-		 * Make sure we do not wakeup the next reader before
-		 * setting the nil condition to grant the next reader;
-		 * otherwise we could miss the wakeup on the other
-		 * side and end up sleeping again. See the pairing
-		 * in rwsem_down_read_failed().
-		 */
-		smp_mb();
-		waiter->task = NULL;
-		wake_up_process(tsk);
-		put_task_struct(tsk);
-		woken++;
-		if (next == &sem->wait_list)
-			break;
-		waiter = list_entry(next, struct rwsem_waiter, list);
-	} while (waiter->type != RWSEM_WAITING_FOR_WRITE);
-
-	sem->count += woken;
-
- out:
-	return sem;
-}
-
-/*
- * wake a single writer
- */
-static inline struct rw_semaphore *
-__rwsem_wake_one_writer(struct rw_semaphore *sem)
-{
-	struct rwsem_waiter *waiter;
-
-	waiter = list_entry(sem->wait_list.next, struct rwsem_waiter, list);
-	wake_up_process(waiter->task);
-
-	return sem;
-}
-
-/*
- * get a read lock on the semaphore
- */
-int __sched __down_read_common(struct rw_semaphore *sem, int state)
-{
-	struct rwsem_waiter waiter;
-	unsigned long flags;
-
-	raw_spin_lock_irqsave(&sem->wait_lock, flags);
-
-	if (sem->count >= 0 && list_empty(&sem->wait_list)) {
-		/* granted */
-		sem->count++;
-		raw_spin_unlock_irqrestore(&sem->wait_lock, flags);
-		goto out;
-	}
-
-	/* set up my own style of waitqueue */
-	waiter.task = current;
-	waiter.type = RWSEM_WAITING_FOR_READ;
-	get_task_struct(current);
-
-	list_add_tail(&waiter.list, &sem->wait_list);
-
-	/* wait to be given the lock */
-	for (;;) {
-		if (!waiter.task)
-			break;
-		if (signal_pending_state(state, current))
-			goto out_nolock;
-		set_current_state(state);
-		raw_spin_unlock_irqrestore(&sem->wait_lock, flags);
-		schedule();
-		raw_spin_lock_irqsave(&sem->wait_lock, flags);
-	}
-
-	raw_spin_unlock_irqrestore(&sem->wait_lock, flags);
- out:
-	return 0;
-
-out_nolock:
-	/*
-	 * We didn't take the lock, so that there is a writer, which
-	 * is owner or the first waiter of the sem. If it's a waiter,
-	 * it will be woken by current owner. Not need to wake anybody.
-	 */
-	list_del(&waiter.list);
-	raw_spin_unlock_irqrestore(&sem->wait_lock, flags);
-	return -EINTR;
-}
-
-void __sched __down_read(struct rw_semaphore *sem)
-{
-	__down_read_common(sem, TASK_UNINTERRUPTIBLE);
-}
-
-int __sched __down_read_killable(struct rw_semaphore *sem)
-{
-	return __down_read_common(sem, TASK_KILLABLE);
-}
-
-/*
- * trylock for reading -- returns 1 if successful, 0 if contention
- */
-int __down_read_trylock(struct rw_semaphore *sem)
-{
-	unsigned long flags;
-	int ret = 0;
-
-
-	raw_spin_lock_irqsave(&sem->wait_lock, flags);
-
-	if (sem->count >= 0 && list_empty(&sem->wait_list)) {
-		/* granted */
-		sem->count++;
-		ret = 1;
-	}
-
-	raw_spin_unlock_irqrestore(&sem->wait_lock, flags);
-
-	return ret;
-}
-
-/*
- * get a write lock on the semaphore
- */
-int __sched __down_write_common(struct rw_semaphore *sem, int state)
-{
-	struct rwsem_waiter waiter;
-	unsigned long flags;
-	int ret = 0;
-
-	raw_spin_lock_irqsave(&sem->wait_lock, flags);
-
-	/* set up my own style of waitqueue */
-	waiter.task = current;
-	waiter.type = RWSEM_WAITING_FOR_WRITE;
-	list_add_tail(&waiter.list, &sem->wait_list);
-
-	/* wait for someone to release the lock */
-	for (;;) {
-		/*
-		 * That is the key to support write lock stealing: allows the
-		 * task already on CPU to get the lock soon rather than put
-		 * itself into sleep and waiting for system woke it or someone
-		 * else in the head of the wait list up.
-		 */
-		if (sem->count == 0)
-			break;
-		if (signal_pending_state(state, current))
-			goto out_nolock;
-
-		set_current_state(state);
-		raw_spin_unlock_irqrestore(&sem->wait_lock, flags);
-		schedule();
-		raw_spin_lock_irqsave(&sem->wait_lock, flags);
-	}
-	/* got the lock */
-	sem->count = -1;
-	list_del(&waiter.list);
-
-	raw_spin_unlock_irqrestore(&sem->wait_lock, flags);
-
-	return ret;
-
-out_nolock:
-	list_del(&waiter.list);
-	if (!list_empty(&sem->wait_list) && sem->count >= 0)
-		__rwsem_do_wake(sem, 0);
-	raw_spin_unlock_irqrestore(&sem->wait_lock, flags);
-
-	return -EINTR;
-}
-
-void __sched __down_write(struct rw_semaphore *sem)
-{
-	__down_write_common(sem, TASK_UNINTERRUPTIBLE);
-}
-
-int __sched __down_write_killable(struct rw_semaphore *sem)
-{
-	return __down_write_common(sem, TASK_KILLABLE);
-}
-
-/*
- * trylock for writing -- returns 1 if successful, 0 if contention
- */
-int __down_write_trylock(struct rw_semaphore *sem)
-{
-	unsigned long flags;
-	int ret = 0;
-
-	raw_spin_lock_irqsave(&sem->wait_lock, flags);
-
-	if (sem->count == 0) {
-		/* got the lock */
-		sem->count = -1;
-		ret = 1;
-	}
-
-	raw_spin_unlock_irqrestore(&sem->wait_lock, flags);
-
-	return ret;
-}
-
-/*
- * release a read lock on the semaphore
- */
-void __up_read(struct rw_semaphore *sem)
-{
-	unsigned long flags;
-
-	raw_spin_lock_irqsave(&sem->wait_lock, flags);
-
-	if (--sem->count == 0 && !list_empty(&sem->wait_list))
-		sem = __rwsem_wake_one_writer(sem);
-
-	raw_spin_unlock_irqrestore(&sem->wait_lock, flags);
-}
-
-/*
- * release a write lock on the semaphore
- */
-void __up_write(struct rw_semaphore *sem)
-{
-	unsigned long flags;
-
-	raw_spin_lock_irqsave(&sem->wait_lock, flags);
-
-	sem->count = 0;
-	if (!list_empty(&sem->wait_list))
-		sem = __rwsem_do_wake(sem, 1);
-
-	raw_spin_unlock_irqrestore(&sem->wait_lock, flags);
-}
-
-/*
- * downgrade a write lock into a read lock
- * - just wake up any readers at the front of the queue
- */
-void __downgrade_write(struct rw_semaphore *sem)
-{
-	unsigned long flags;
-
-	raw_spin_lock_irqsave(&sem->wait_lock, flags);
-
-	sem->count = 1;
-	if (!list_empty(&sem->wait_list))
-		sem = __rwsem_do_wake(sem, 0);
-
-	raw_spin_unlock_irqrestore(&sem->wait_lock, flags);
-}
-
diff --git a/kernel/locking/rwsem-xadd.c b/kernel/locking/rwsem-xadd.c
index fbe96341beee..6b3ee9948bf1 100644
--- a/kernel/locking/rwsem-xadd.c
+++ b/kernel/locking/rwsem-xadd.c
@@ -147,6 +147,7 @@ static void __rwsem_mark_wake(struct rw_semaphore *sem,
 			 * will notice the queued writer.
 			 */
 			wake_q_add(wake_q, waiter->task);
+			lockevent_inc(rwsem_wake_writer);
 		}
 
 		return;
@@ -176,9 +177,8 @@ static void __rwsem_mark_wake(struct rw_semaphore *sem,
 			goto try_reader_grant;
 		}
 		/*
-		 * It is not really necessary to set it to reader-owned here,
-		 * but it gives the spinners an early indication that the
-		 * readers now have the lock.
+		 * Set it to reader-owned to give spinners an early
+		 * indication that readers now have the lock.
 		 */
 		__rwsem_set_reader_owned(sem, waiter->task);
 	}
@@ -215,6 +215,7 @@ static void __rwsem_mark_wake(struct rw_semaphore *sem,
 	}
 
 	adjustment = woken * RWSEM_ACTIVE_READ_BIAS - adjustment;
+	lockevent_cond_inc(rwsem_wake_reader, woken);
 	if (list_empty(&sem->wait_list)) {
 		/* hit end of list above */
 		adjustment -= RWSEM_WAITING_BIAS;
@@ -225,92 +226,6 @@ static void __rwsem_mark_wake(struct rw_semaphore *sem,
 }
 
 /*
- * Wait for the read lock to be granted
- */
-static inline struct rw_semaphore __sched *
-__rwsem_down_read_failed_common(struct rw_semaphore *sem, int state)
-{
-	long count, adjustment = -RWSEM_ACTIVE_READ_BIAS;
-	struct rwsem_waiter waiter;
-	DEFINE_WAKE_Q(wake_q);
-
-	waiter.task = current;
-	waiter.type = RWSEM_WAITING_FOR_READ;
-
-	raw_spin_lock_irq(&sem->wait_lock);
-	if (list_empty(&sem->wait_list)) {
-		/*
-		 * In case the wait queue is empty and the lock isn't owned
-		 * by a writer, this reader can exit the slowpath and return
-		 * immediately as its RWSEM_ACTIVE_READ_BIAS has already
-		 * been set in the count.
-		 */
-		if (atomic_long_read(&sem->count) >= 0) {
-			raw_spin_unlock_irq(&sem->wait_lock);
-			return sem;
-		}
-		adjustment += RWSEM_WAITING_BIAS;
-	}
-	list_add_tail(&waiter.list, &sem->wait_list);
-
-	/* we're now waiting on the lock, but no longer actively locking */
-	count = atomic_long_add_return(adjustment, &sem->count);
-
-	/*
-	 * If there are no active locks, wake the front queued process(es).
-	 *
-	 * If there are no writers and we are first in the queue,
-	 * wake our own waiter to join the existing active readers !
-	 */
-	if (count == RWSEM_WAITING_BIAS ||
-	    (count > RWSEM_WAITING_BIAS &&
-	     adjustment != -RWSEM_ACTIVE_READ_BIAS))
-		__rwsem_mark_wake(sem, RWSEM_WAKE_ANY, &wake_q);
-
-	raw_spin_unlock_irq(&sem->wait_lock);
-	wake_up_q(&wake_q);
-
-	/* wait to be given the lock */
-	while (true) {
-		set_current_state(state);
-		if (!waiter.task)
-			break;
-		if (signal_pending_state(state, current)) {
-			raw_spin_lock_irq(&sem->wait_lock);
-			if (waiter.task)
-				goto out_nolock;
-			raw_spin_unlock_irq(&sem->wait_lock);
-			break;
-		}
-		schedule();
-	}
-
-	__set_current_state(TASK_RUNNING);
-	return sem;
-out_nolock:
-	list_del(&waiter.list);
-	if (list_empty(&sem->wait_list))
-		atomic_long_add(-RWSEM_WAITING_BIAS, &sem->count);
-	raw_spin_unlock_irq(&sem->wait_lock);
-	__set_current_state(TASK_RUNNING);
-	return ERR_PTR(-EINTR);
-}
-
-__visible struct rw_semaphore * __sched
-rwsem_down_read_failed(struct rw_semaphore *sem)
-{
-	return __rwsem_down_read_failed_common(sem, TASK_UNINTERRUPTIBLE);
-}
-EXPORT_SYMBOL(rwsem_down_read_failed);
-
-__visible struct rw_semaphore * __sched
-rwsem_down_read_failed_killable(struct rw_semaphore *sem)
-{
-	return __rwsem_down_read_failed_common(sem, TASK_KILLABLE);
-}
-EXPORT_SYMBOL(rwsem_down_read_failed_killable);
-
-/*
  * This function must be called with the sem->wait_lock held to prevent
  * race conditions between checking the rwsem wait list and setting the
  * sem->count accordingly.
@@ -346,21 +261,17 @@ static inline bool rwsem_try_write_lock(long count, struct rw_semaphore *sem)
  */
 static inline bool rwsem_try_write_lock_unqueued(struct rw_semaphore *sem)
 {
-	long old, count = atomic_long_read(&sem->count);
-
-	while (true) {
-		if (!(count == 0 || count == RWSEM_WAITING_BIAS))
-			return false;
+	long count = atomic_long_read(&sem->count);
 
-		old = atomic_long_cmpxchg_acquire(&sem->count, count,
-				      count + RWSEM_ACTIVE_WRITE_BIAS);
-		if (old == count) {
+	while (!count || count == RWSEM_WAITING_BIAS) {
+		if (atomic_long_try_cmpxchg_acquire(&sem->count, &count,
+					count + RWSEM_ACTIVE_WRITE_BIAS)) {
 			rwsem_set_owner(sem);
+			lockevent_inc(rwsem_opt_wlock);
 			return true;
 		}
-
-		count = old;
 	}
+	return false;
 }
 
 static inline bool owner_on_cpu(struct task_struct *owner)
@@ -481,6 +392,7 @@ static bool rwsem_optimistic_spin(struct rw_semaphore *sem)
 	osq_unlock(&sem->osq);
 done:
 	preempt_enable();
+	lockevent_cond_inc(rwsem_opt_fail, !taken);
 	return taken;
 }
 
@@ -505,6 +417,97 @@ static inline bool rwsem_has_spinner(struct rw_semaphore *sem)
 #endif
 
 /*
+ * Wait for the read lock to be granted
+ */
+static inline struct rw_semaphore __sched *
+__rwsem_down_read_failed_common(struct rw_semaphore *sem, int state)
+{
+	long count, adjustment = -RWSEM_ACTIVE_READ_BIAS;
+	struct rwsem_waiter waiter;
+	DEFINE_WAKE_Q(wake_q);
+
+	waiter.task = current;
+	waiter.type = RWSEM_WAITING_FOR_READ;
+
+	raw_spin_lock_irq(&sem->wait_lock);
+	if (list_empty(&sem->wait_list)) {
+		/*
+		 * In case the wait queue is empty and the lock isn't owned
+		 * by a writer, this reader can exit the slowpath and return
+		 * immediately as its RWSEM_ACTIVE_READ_BIAS has already
+		 * been set in the count.
+		 */
+		if (atomic_long_read(&sem->count) >= 0) {
+			raw_spin_unlock_irq(&sem->wait_lock);
+			rwsem_set_reader_owned(sem);
+			lockevent_inc(rwsem_rlock_fast);
+			return sem;
+		}
+		adjustment += RWSEM_WAITING_BIAS;
+	}
+	list_add_tail(&waiter.list, &sem->wait_list);
+
+	/* we're now waiting on the lock, but no longer actively locking */
+	count = atomic_long_add_return(adjustment, &sem->count);
+
+	/*
+	 * If there are no active locks, wake the front queued process(es).
+	 *
+	 * If there are no writers and we are first in the queue,
+	 * wake our own waiter to join the existing active readers !
+	 */
+	if (count == RWSEM_WAITING_BIAS ||
+	    (count > RWSEM_WAITING_BIAS &&
+	     adjustment != -RWSEM_ACTIVE_READ_BIAS))
+		__rwsem_mark_wake(sem, RWSEM_WAKE_ANY, &wake_q);
+
+	raw_spin_unlock_irq(&sem->wait_lock);
+	wake_up_q(&wake_q);
+
+	/* wait to be given the lock */
+	while (true) {
+		set_current_state(state);
+		if (!waiter.task)
+			break;
+		if (signal_pending_state(state, current)) {
+			raw_spin_lock_irq(&sem->wait_lock);
+			if (waiter.task)
+				goto out_nolock;
+			raw_spin_unlock_irq(&sem->wait_lock);
+			break;
+		}
+		schedule();
+		lockevent_inc(rwsem_sleep_reader);
+	}
+
+	__set_current_state(TASK_RUNNING);
+	lockevent_inc(rwsem_rlock);
+	return sem;
+out_nolock:
+	list_del(&waiter.list);
+	if (list_empty(&sem->wait_list))
+		atomic_long_add(-RWSEM_WAITING_BIAS, &sem->count);
+	raw_spin_unlock_irq(&sem->wait_lock);
+	__set_current_state(TASK_RUNNING);
+	lockevent_inc(rwsem_rlock_fail);
+	return ERR_PTR(-EINTR);
+}
+
+__visible struct rw_semaphore * __sched
+rwsem_down_read_failed(struct rw_semaphore *sem)
+{
+	return __rwsem_down_read_failed_common(sem, TASK_UNINTERRUPTIBLE);
+}
+EXPORT_SYMBOL(rwsem_down_read_failed);
+
+__visible struct rw_semaphore * __sched
+rwsem_down_read_failed_killable(struct rw_semaphore *sem)
+{
+	return __rwsem_down_read_failed_common(sem, TASK_KILLABLE);
+}
+EXPORT_SYMBOL(rwsem_down_read_failed_killable);
+
+/*
  * Wait until we successfully acquire the write lock
  */
 static inline struct rw_semaphore *
@@ -580,6 +583,7 @@ __rwsem_down_write_failed_common(struct rw_semaphore *sem, int state)
 				goto out_nolock;
 
 			schedule();
+			lockevent_inc(rwsem_sleep_writer);
 			set_current_state(state);
 		} while ((count = atomic_long_read(&sem->count)) & RWSEM_ACTIVE_MASK);
 
@@ -588,6 +592,7 @@ __rwsem_down_write_failed_common(struct rw_semaphore *sem, int state)
 	__set_current_state(TASK_RUNNING);
 	list_del(&waiter.list);
 	raw_spin_unlock_irq(&sem->wait_lock);
+	lockevent_inc(rwsem_wlock);
 
 	return ret;
 
@@ -601,6 +606,7 @@ out_nolock:
 		__rwsem_mark_wake(sem, RWSEM_WAKE_ANY, &wake_q);
 	raw_spin_unlock_irq(&sem->wait_lock);
 	wake_up_q(&wake_q);
+	lockevent_inc(rwsem_wlock_fail);
 
 	return ERR_PTR(-EINTR);
 }
diff --git a/kernel/locking/rwsem.c b/kernel/locking/rwsem.c
index e586f0d03ad3..ccbf18f560ff 100644
--- a/kernel/locking/rwsem.c
+++ b/kernel/locking/rwsem.c
@@ -24,7 +24,6 @@ void __sched down_read(struct rw_semaphore *sem)
 	rwsem_acquire_read(&sem->dep_map, 0, 0, _RET_IP_);
 
 	LOCK_CONTENDED(sem, __down_read_trylock, __down_read);
-	rwsem_set_reader_owned(sem);
 }
 
 EXPORT_SYMBOL(down_read);
@@ -39,7 +38,6 @@ int __sched down_read_killable(struct rw_semaphore *sem)
 		return -EINTR;
 	}
 
-	rwsem_set_reader_owned(sem);
 	return 0;
 }
 
@@ -52,10 +50,8 @@ int down_read_trylock(struct rw_semaphore *sem)
 {
 	int ret = __down_read_trylock(sem);
 
-	if (ret == 1) {
+	if (ret == 1)
 		rwsem_acquire_read(&sem->dep_map, 0, 1, _RET_IP_);
-		rwsem_set_reader_owned(sem);
-	}
 	return ret;
 }
 
@@ -70,7 +66,6 @@ void __sched down_write(struct rw_semaphore *sem)
 	rwsem_acquire(&sem->dep_map, 0, 0, _RET_IP_);
 
 	LOCK_CONTENDED(sem, __down_write_trylock, __down_write);
-	rwsem_set_owner(sem);
 }
 
 EXPORT_SYMBOL(down_write);
@@ -88,7 +83,6 @@ int __sched down_write_killable(struct rw_semaphore *sem)
 		return -EINTR;
 	}
 
-	rwsem_set_owner(sem);
 	return 0;
 }
 
@@ -101,10 +95,8 @@ int down_write_trylock(struct rw_semaphore *sem)
 {
 	int ret = __down_write_trylock(sem);
 
-	if (ret == 1) {
+	if (ret == 1)
 		rwsem_acquire(&sem->dep_map, 0, 1, _RET_IP_);
-		rwsem_set_owner(sem);
-	}
 
 	return ret;
 }
@@ -117,9 +109,7 @@ EXPORT_SYMBOL(down_write_trylock);
 void up_read(struct rw_semaphore *sem)
 {
 	rwsem_release(&sem->dep_map, 1, _RET_IP_);
-	DEBUG_RWSEMS_WARN_ON(!((unsigned long)sem->owner & RWSEM_READER_OWNED));
 
-	rwsem_clear_reader_owned(sem);
 	__up_read(sem);
 }
 
@@ -131,9 +121,7 @@ EXPORT_SYMBOL(up_read);
 void up_write(struct rw_semaphore *sem)
 {
 	rwsem_release(&sem->dep_map, 1, _RET_IP_);
-	DEBUG_RWSEMS_WARN_ON(sem->owner != current);
 
-	rwsem_clear_owner(sem);
 	__up_write(sem);
 }
 
@@ -145,9 +133,7 @@ EXPORT_SYMBOL(up_write);
 void downgrade_write(struct rw_semaphore *sem)
 {
 	lock_downgrade(&sem->dep_map, _RET_IP_);
-	DEBUG_RWSEMS_WARN_ON(sem->owner != current);
 
-	rwsem_set_reader_owned(sem);
 	__downgrade_write(sem);
 }
 
@@ -161,7 +147,6 @@ void down_read_nested(struct rw_semaphore *sem, int subclass)
 	rwsem_acquire_read(&sem->dep_map, subclass, 0, _RET_IP_);
 
 	LOCK_CONTENDED(sem, __down_read_trylock, __down_read);
-	rwsem_set_reader_owned(sem);
 }
 
 EXPORT_SYMBOL(down_read_nested);
@@ -172,7 +157,6 @@ void _down_write_nest_lock(struct rw_semaphore *sem, struct lockdep_map *nest)
 	rwsem_acquire_nest(&sem->dep_map, 0, 0, nest, _RET_IP_);
 
 	LOCK_CONTENDED(sem, __down_write_trylock, __down_write);
-	rwsem_set_owner(sem);
 }
 
 EXPORT_SYMBOL(_down_write_nest_lock);
@@ -193,7 +177,6 @@ void down_write_nested(struct rw_semaphore *sem, int subclass)
 	rwsem_acquire(&sem->dep_map, subclass, 0, _RET_IP_);
 
 	LOCK_CONTENDED(sem, __down_write_trylock, __down_write);
-	rwsem_set_owner(sem);
 }
 
 EXPORT_SYMBOL(down_write_nested);
@@ -208,7 +191,6 @@ int __sched down_write_killable_nested(struct rw_semaphore *sem, int subclass)
 		return -EINTR;
 	}
 
-	rwsem_set_owner(sem);
 	return 0;
 }
 
@@ -216,7 +198,8 @@ EXPORT_SYMBOL(down_write_killable_nested);
 
 void up_read_non_owner(struct rw_semaphore *sem)
 {
-	DEBUG_RWSEMS_WARN_ON(!((unsigned long)sem->owner & RWSEM_READER_OWNED));
+	DEBUG_RWSEMS_WARN_ON(!((unsigned long)sem->owner & RWSEM_READER_OWNED),
+				sem);
 	__up_read(sem);
 }
 
diff --git a/kernel/locking/rwsem.h b/kernel/locking/rwsem.h
index bad2bca0268b..64877f5294e3 100644
--- a/kernel/locking/rwsem.h
+++ b/kernel/locking/rwsem.h
@@ -23,15 +23,44 @@
  * is involved. Ideally we would like to track all the readers that own
  * a rwsem, but the overhead is simply too big.
  */
+#include "lock_events.h"
+
 #define RWSEM_READER_OWNED	(1UL << 0)
 #define RWSEM_ANONYMOUSLY_OWNED	(1UL << 1)
 
 #ifdef CONFIG_DEBUG_RWSEMS
-# define DEBUG_RWSEMS_WARN_ON(c)	DEBUG_LOCKS_WARN_ON(c)
+# define DEBUG_RWSEMS_WARN_ON(c, sem)	do {			\
+	if (!debug_locks_silent &&				\
+	    WARN_ONCE(c, "DEBUG_RWSEMS_WARN_ON(%s): count = 0x%lx, owner = 0x%lx, curr 0x%lx, list %sempty\n",\
+		#c, atomic_long_read(&(sem)->count),		\
+		(long)((sem)->owner), (long)current,		\
+		list_empty(&(sem)->wait_list) ? "" : "not "))	\
+			debug_locks_off();			\
+	} while (0)
+#else
+# define DEBUG_RWSEMS_WARN_ON(c, sem)
+#endif
+
+/*
+ * R/W semaphores originally for PPC using the stuff in lib/rwsem.c.
+ * Adapted largely from include/asm-i386/rwsem.h
+ * by Paul Mackerras <paulus@samba.org>.
+ */
+
+/*
+ * the semaphore definition
+ */
+#ifdef CONFIG_64BIT
+# define RWSEM_ACTIVE_MASK		0xffffffffL
 #else
-# define DEBUG_RWSEMS_WARN_ON(c)
+# define RWSEM_ACTIVE_MASK		0x0000ffffL
 #endif
 
+#define RWSEM_ACTIVE_BIAS		0x00000001L
+#define RWSEM_WAITING_BIAS		(-RWSEM_ACTIVE_MASK-1)
+#define RWSEM_ACTIVE_READ_BIAS		RWSEM_ACTIVE_BIAS
+#define RWSEM_ACTIVE_WRITE_BIAS		(RWSEM_WAITING_BIAS + RWSEM_ACTIVE_BIAS)
+
 #ifdef CONFIG_RWSEM_SPIN_ON_OWNER
 /*
  * All writes to owner are protected by WRITE_ONCE() to make sure that
@@ -132,3 +161,144 @@ static inline void rwsem_clear_reader_owned(struct rw_semaphore *sem)
 {
 }
 #endif
+
+extern struct rw_semaphore *rwsem_down_read_failed(struct rw_semaphore *sem);
+extern struct rw_semaphore *rwsem_down_read_failed_killable(struct rw_semaphore *sem);
+extern struct rw_semaphore *rwsem_down_write_failed(struct rw_semaphore *sem);
+extern struct rw_semaphore *rwsem_down_write_failed_killable(struct rw_semaphore *sem);
+extern struct rw_semaphore *rwsem_wake(struct rw_semaphore *sem);
+extern struct rw_semaphore *rwsem_downgrade_wake(struct rw_semaphore *sem);
+
+/*
+ * lock for reading
+ */
+static inline void __down_read(struct rw_semaphore *sem)
+{
+	if (unlikely(atomic_long_inc_return_acquire(&sem->count) <= 0)) {
+		rwsem_down_read_failed(sem);
+		DEBUG_RWSEMS_WARN_ON(!((unsigned long)sem->owner &
+					RWSEM_READER_OWNED), sem);
+	} else {
+		rwsem_set_reader_owned(sem);
+	}
+}
+
+static inline int __down_read_killable(struct rw_semaphore *sem)
+{
+	if (unlikely(atomic_long_inc_return_acquire(&sem->count) <= 0)) {
+		if (IS_ERR(rwsem_down_read_failed_killable(sem)))
+			return -EINTR;
+		DEBUG_RWSEMS_WARN_ON(!((unsigned long)sem->owner &
+					RWSEM_READER_OWNED), sem);
+	} else {
+		rwsem_set_reader_owned(sem);
+	}
+	return 0;
+}
+
+static inline int __down_read_trylock(struct rw_semaphore *sem)
+{
+	/*
+	 * Optimize for the case when the rwsem is not locked at all.
+	 */
+	long tmp = RWSEM_UNLOCKED_VALUE;
+
+	lockevent_inc(rwsem_rtrylock);
+	do {
+		if (atomic_long_try_cmpxchg_acquire(&sem->count, &tmp,
+					tmp + RWSEM_ACTIVE_READ_BIAS)) {
+			rwsem_set_reader_owned(sem);
+			return 1;
+		}
+	} while (tmp >= 0);
+	return 0;
+}
+
+/*
+ * lock for writing
+ */
+static inline void __down_write(struct rw_semaphore *sem)
+{
+	long tmp;
+
+	tmp = atomic_long_add_return_acquire(RWSEM_ACTIVE_WRITE_BIAS,
+					     &sem->count);
+	if (unlikely(tmp != RWSEM_ACTIVE_WRITE_BIAS))
+		rwsem_down_write_failed(sem);
+	rwsem_set_owner(sem);
+}
+
+static inline int __down_write_killable(struct rw_semaphore *sem)
+{
+	long tmp;
+
+	tmp = atomic_long_add_return_acquire(RWSEM_ACTIVE_WRITE_BIAS,
+					     &sem->count);
+	if (unlikely(tmp != RWSEM_ACTIVE_WRITE_BIAS))
+		if (IS_ERR(rwsem_down_write_failed_killable(sem)))
+			return -EINTR;
+	rwsem_set_owner(sem);
+	return 0;
+}
+
+static inline int __down_write_trylock(struct rw_semaphore *sem)
+{
+	long tmp;
+
+	lockevent_inc(rwsem_wtrylock);
+	tmp = atomic_long_cmpxchg_acquire(&sem->count, RWSEM_UNLOCKED_VALUE,
+		      RWSEM_ACTIVE_WRITE_BIAS);
+	if (tmp == RWSEM_UNLOCKED_VALUE) {
+		rwsem_set_owner(sem);
+		return true;
+	}
+	return false;
+}
+
+/*
+ * unlock after reading
+ */
+static inline void __up_read(struct rw_semaphore *sem)
+{
+	long tmp;
+
+	DEBUG_RWSEMS_WARN_ON(!((unsigned long)sem->owner & RWSEM_READER_OWNED),
+				sem);
+	rwsem_clear_reader_owned(sem);
+	tmp = atomic_long_dec_return_release(&sem->count);
+	if (unlikely(tmp < -1 && (tmp & RWSEM_ACTIVE_MASK) == 0))
+		rwsem_wake(sem);
+}
+
+/*
+ * unlock after writing
+ */
+static inline void __up_write(struct rw_semaphore *sem)
+{
+	DEBUG_RWSEMS_WARN_ON(sem->owner != current, sem);
+	rwsem_clear_owner(sem);
+	if (unlikely(atomic_long_sub_return_release(RWSEM_ACTIVE_WRITE_BIAS,
+						    &sem->count) < 0))
+		rwsem_wake(sem);
+}
+
+/*
+ * downgrade write lock to read lock
+ */
+static inline void __downgrade_write(struct rw_semaphore *sem)
+{
+	long tmp;
+
+	/*
+	 * When downgrading from exclusive to shared ownership,
+	 * anything inside the write-locked region cannot leak
+	 * into the read side. In contrast, anything in the
+	 * read-locked region is ok to be re-ordered into the
+	 * write side. As such, rely on RELEASE semantics.
+	 */
+	DEBUG_RWSEMS_WARN_ON(sem->owner != current, sem);
+	tmp = atomic_long_add_return_release(-RWSEM_WAITING_BIAS, &sem->count);
+	rwsem_set_reader_owned(sem);
+	if (tmp < 0)
+		rwsem_downgrade_wake(sem);
+}
diff --git a/kernel/locking/spinlock.c b/kernel/locking/spinlock.c
index 936f3d14dd6b..0ff08380f531 100644
--- a/kernel/locking/spinlock.c
+++ b/kernel/locking/spinlock.c
@@ -22,6 +22,13 @@
 #include <linux/debug_locks.h>
 #include <linux/export.h>
 
+#ifdef CONFIG_MMIOWB
+#ifndef arch_mmiowb_state
+DEFINE_PER_CPU(struct mmiowb_state, __mmiowb_state);
+EXPORT_PER_CPU_SYMBOL(__mmiowb_state);
+#endif
+#endif
+
 /*
  * If lockdep is enabled then we use the non-preemption spin-ops
  * even on CONFIG_PREEMPT, because lockdep assumes that interrupts are
diff --git a/kernel/locking/spinlock_debug.c b/kernel/locking/spinlock_debug.c
index 9aa0fccd5d43..399669f7eba8 100644
--- a/kernel/locking/spinlock_debug.c
+++ b/kernel/locking/spinlock_debug.c
@@ -111,6 +111,7 @@ void do_raw_spin_lock(raw_spinlock_t *lock)
 {
 	debug_spin_lock_before(lock);
 	arch_spin_lock(&lock->raw_lock);
+	mmiowb_spin_lock();
 	debug_spin_lock_after(lock);
 }
 
@@ -118,8 +119,10 @@ int do_raw_spin_trylock(raw_spinlock_t *lock)
 {
 	int ret = arch_spin_trylock(&lock->raw_lock);
 
-	if (ret)
+	if (ret) {
+		mmiowb_spin_lock();
 		debug_spin_lock_after(lock);
+	}
 #ifndef CONFIG_SMP
 	/*
 	 * Must not happen on UP:
@@ -131,6 +134,7 @@ int do_raw_spin_trylock(raw_spinlock_t *lock)
 
 void do_raw_spin_unlock(raw_spinlock_t *lock)
 {
+	mmiowb_spin_unlock();
 	debug_spin_unlock(lock);
 	arch_spin_unlock(&lock->raw_lock);
 }
diff --git a/kernel/module.c b/kernel/module.c
index 0b9aa8ab89f0..a9020bdd4cf6 100644
--- a/kernel/module.c
+++ b/kernel/module.c
@@ -98,6 +98,10 @@ DEFINE_MUTEX(module_mutex);
 EXPORT_SYMBOL_GPL(module_mutex);
 static LIST_HEAD(modules);
 
+/* Work queue for freeing init sections in success case */
+static struct work_struct init_free_wq;
+static struct llist_head init_free_list;
+
 #ifdef CONFIG_MODULES_TREE_LOOKUP
 
 /*
@@ -1949,9 +1953,16 @@ void module_enable_ro(const struct module *mod, bool after_init)
 	if (!rodata_enabled)
 		return;
 
+	set_vm_flush_reset_perms(mod->core_layout.base);
+	set_vm_flush_reset_perms(mod->init_layout.base);
 	frob_text(&mod->core_layout, set_memory_ro);
+	frob_text(&mod->core_layout, set_memory_x);
+
 	frob_rodata(&mod->core_layout, set_memory_ro);
+
 	frob_text(&mod->init_layout, set_memory_ro);
+	frob_text(&mod->init_layout, set_memory_x);
+
 	frob_rodata(&mod->init_layout, set_memory_ro);
 
 	if (after_init)
@@ -1967,15 +1978,6 @@ static void module_enable_nx(const struct module *mod)
 	frob_writable_data(&mod->init_layout, set_memory_nx);
 }
 
-static void module_disable_nx(const struct module *mod)
-{
-	frob_rodata(&mod->core_layout, set_memory_x);
-	frob_ro_after_init(&mod->core_layout, set_memory_x);
-	frob_writable_data(&mod->core_layout, set_memory_x);
-	frob_rodata(&mod->init_layout, set_memory_x);
-	frob_writable_data(&mod->init_layout, set_memory_x);
-}
-
 /* Iterate through all modules and set each module's text as RW */
 void set_all_modules_text_rw(void)
 {
@@ -2019,23 +2021,8 @@ void set_all_modules_text_ro(void)
 	}
 	mutex_unlock(&module_mutex);
 }
-
-static void disable_ro_nx(const struct module_layout *layout)
-{
-	if (rodata_enabled) {
-		frob_text(layout, set_memory_rw);
-		frob_rodata(layout, set_memory_rw);
-		frob_ro_after_init(layout, set_memory_rw);
-	}
-	frob_rodata(layout, set_memory_x);
-	frob_ro_after_init(layout, set_memory_x);
-	frob_writable_data(layout, set_memory_x);
-}
-
 #else
-static void disable_ro_nx(const struct module_layout *layout) { }
 static void module_enable_nx(const struct module *mod) { }
-static void module_disable_nx(const struct module *mod) { }
 #endif
 
 #ifdef CONFIG_LIVEPATCH
@@ -2115,6 +2102,11 @@ static void free_module_elf(struct module *mod)
 
 void __weak module_memfree(void *module_region)
 {
+	/*
+	 * This memory may be RO, and freeing RO memory in an interrupt is not
+	 * supported by vmalloc.
+	 */
+	WARN_ON(in_interrupt());
 	vfree(module_region);
 }
 
@@ -2166,7 +2158,6 @@ static void free_module(struct module *mod)
 	mutex_unlock(&module_mutex);
 
 	/* This may be empty, but that's OK */
-	disable_ro_nx(&mod->init_layout);
 	module_arch_freeing_init(mod);
 	module_memfree(mod->init_layout.base);
 	kfree(mod->args);
@@ -2176,7 +2167,6 @@ static void free_module(struct module *mod)
 	lockdep_free_key_range(mod->core_layout.base, mod->core_layout.size);
 
 	/* Finally, free the core (containing the module structure) */
-	disable_ro_nx(&mod->core_layout);
 	module_memfree(mod->core_layout.base);
 }
 
@@ -3415,17 +3405,34 @@ static void do_mod_ctors(struct module *mod)
 
 /* For freeing module_init on success, in case kallsyms traversing */
 struct mod_initfree {
-	struct rcu_head rcu;
+	struct llist_node node;
 	void *module_init;
 };
 
-static void do_free_init(struct rcu_head *head)
+static void do_free_init(struct work_struct *w)
 {
-	struct mod_initfree *m = container_of(head, struct mod_initfree, rcu);
-	module_memfree(m->module_init);
-	kfree(m);
+	struct llist_node *pos, *n, *list;
+	struct mod_initfree *initfree;
+
+	list = llist_del_all(&init_free_list);
+
+	synchronize_rcu();
+
+	llist_for_each_safe(pos, n, list) {
+		initfree = container_of(pos, struct mod_initfree, node);
+		module_memfree(initfree->module_init);
+		kfree(initfree);
+	}
 }
 
+static int __init modules_wq_init(void)
+{
+	INIT_WORK(&init_free_wq, do_free_init);
+	init_llist_head(&init_free_list);
+	return 0;
+}
+module_init(modules_wq_init);
+
 /*
  * This is where the real work happens.
  *
@@ -3502,7 +3509,6 @@ static noinline int do_init_module(struct module *mod)
 #endif
 	module_enable_ro(mod, true);
 	mod_tree_remove_init(mod);
-	disable_ro_nx(&mod->init_layout);
 	module_arch_freeing_init(mod);
 	mod->init_layout.base = NULL;
 	mod->init_layout.size = 0;
@@ -3513,14 +3519,18 @@ static noinline int do_init_module(struct module *mod)
 	 * We want to free module_init, but be aware that kallsyms may be
 	 * walking this with preempt disabled.  In all the failure paths, we
 	 * call synchronize_rcu(), but we don't want to slow down the success
-	 * path, so use actual RCU here.
+	 * path. module_memfree() cannot be called in an interrupt, so do the
+	 * work and call synchronize_rcu() in a work queue.
+	 *
 	 * Note that module_alloc() on most architectures creates W+X page
 	 * mappings which won't be cleaned up until do_free_init() runs.  Any
 	 * code such as mark_rodata_ro() which depends on those mappings to
 	 * be cleaned up needs to sync with the queued work - ie
 	 * rcu_barrier()
 	 */
-	call_rcu(&freeinit->rcu, do_free_init);
+	if (llist_add(&freeinit->node, &init_free_list))
+		schedule_work(&init_free_wq);
+
 	mutex_unlock(&module_mutex);
 	wake_up_all(&module_wq);
 
@@ -3817,10 +3827,6 @@ static int load_module(struct load_info *info, const char __user *uargs,
 	module_bug_cleanup(mod);
 	mutex_unlock(&module_mutex);
 
-	/* we can't deallocate the module until we clear memory protection */
-	module_disable_ro(mod);
-	module_disable_nx(mod);
-
  ddebug_cleanup:
 	ftrace_release_mod(mod);
 	dynamic_debug_remove(mod, info->debug);
diff --git a/kernel/panic.c b/kernel/panic.c
index 0ae0d7332f12..c1fcaad337b7 100644
--- a/kernel/panic.c
+++ b/kernel/panic.c
@@ -318,12 +318,7 @@ void panic(const char *fmt, ...)
 	}
 #endif
 #if defined(CONFIG_S390)
-	{
-		unsigned long caller;
-
-		caller = (unsigned long)__builtin_return_address(0);
-		disabled_wait(caller);
-	}
+	disabled_wait();
 #endif
 	pr_emerg("---[ end Kernel panic - not syncing: %s ]---\n", buf);
 	local_irq_enable();
diff --git a/kernel/power/Kconfig b/kernel/power/Kconfig
index f8fe57d1022e..9bbaaab14b36 100644
--- a/kernel/power/Kconfig
+++ b/kernel/power/Kconfig
@@ -114,6 +114,15 @@ config PM_SLEEP_SMP
 	depends on PM_SLEEP
 	select HOTPLUG_CPU
 
+config PM_SLEEP_SMP_NONZERO_CPU
+	def_bool y
+	depends on PM_SLEEP_SMP
+	depends on ARCH_SUSPEND_NONZERO_CPU
+	---help---
+	If an arch can suspend (for suspend, hibernate, kexec, etc) on a
+	non-zero numbered CPU, it may define ARCH_SUSPEND_NONZERO_CPU. This
+	will allow nohz_full mask to include CPU0.
+
 config PM_AUTOSLEEP
 	bool "Opportunistic sleep"
 	depends on PM_SLEEP
diff --git a/kernel/power/hibernate.c b/kernel/power/hibernate.c
index abef759de7c8..c8c272df7154 100644
--- a/kernel/power/hibernate.c
+++ b/kernel/power/hibernate.c
@@ -14,7 +14,6 @@
 
 #include <linux/export.h>
 #include <linux/suspend.h>
-#include <linux/syscalls.h>
 #include <linux/reboot.h>
 #include <linux/string.h>
 #include <linux/device.h>
@@ -281,7 +280,7 @@ static int create_image(int platform_mode)
 	if (error || hibernation_test(TEST_PLATFORM))
 		goto Platform_finish;
 
-	error = disable_nonboot_cpus();
+	error = suspend_disable_secondary_cpus();
 	if (error || hibernation_test(TEST_CPUS))
 		goto Enable_cpus;
 
@@ -323,7 +322,7 @@ static int create_image(int platform_mode)
 	local_irq_enable();
 
  Enable_cpus:
-	enable_nonboot_cpus();
+	suspend_enable_secondary_cpus();
 
  Platform_finish:
 	platform_finish(platform_mode);
@@ -417,7 +416,7 @@ int hibernation_snapshot(int platform_mode)
 
 int __weak hibernate_resume_nonboot_cpu_disable(void)
 {
-	return disable_nonboot_cpus();
+	return suspend_disable_secondary_cpus();
 }
 
 /**
@@ -486,7 +485,7 @@ static int resume_target_kernel(bool platform_mode)
 	local_irq_enable();
 
  Enable_cpus:
-	enable_nonboot_cpus();
+	suspend_enable_secondary_cpus();
 
  Cleanup:
 	platform_restore_cleanup(platform_mode);
@@ -564,7 +563,7 @@ int hibernation_platform_enter(void)
 	if (error)
 		goto Platform_finish;
 
-	error = disable_nonboot_cpus();
+	error = suspend_disable_secondary_cpus();
 	if (error)
 		goto Enable_cpus;
 
@@ -586,7 +585,7 @@ int hibernation_platform_enter(void)
 	local_irq_enable();
 
  Enable_cpus:
-	enable_nonboot_cpus();
+	suspend_enable_secondary_cpus();
 
  Platform_finish:
 	hibernation_ops->finish();
@@ -709,9 +708,7 @@ int hibernate(void)
 		goto Exit;
 	}
 
-	pr_info("Syncing filesystems ... \n");
-	ksys_sync();
-	pr_info("done.\n");
+	ksys_sync_helper();
 
 	error = freeze_processes();
 	if (error)
diff --git a/kernel/power/main.c b/kernel/power/main.c
index 98e76cad128b..4f43e724f6eb 100644
--- a/kernel/power/main.c
+++ b/kernel/power/main.c
@@ -16,6 +16,7 @@
 #include <linux/debugfs.h>
 #include <linux/seq_file.h>
 #include <linux/suspend.h>
+#include <linux/syscalls.h>
 
 #include "power.h"
 
@@ -51,6 +52,19 @@ void unlock_system_sleep(void)
 }
 EXPORT_SYMBOL_GPL(unlock_system_sleep);
 
+void ksys_sync_helper(void)
+{
+	ktime_t start;
+	long elapsed_msecs;
+
+	start = ktime_get();
+	ksys_sync();
+	elapsed_msecs = ktime_to_ms(ktime_sub(ktime_get(), start));
+	pr_info("Filesystems sync: %ld.%03ld seconds\n",
+		elapsed_msecs / MSEC_PER_SEC, elapsed_msecs % MSEC_PER_SEC);
+}
+EXPORT_SYMBOL_GPL(ksys_sync_helper);
+
 /* Routines for PM-transition notifications */
 
 static BLOCKING_NOTIFIER_HEAD(pm_chain_head);
diff --git a/kernel/power/snapshot.c b/kernel/power/snapshot.c
index f08a1e4ee1d4..bc9558ab1e5b 100644
--- a/kernel/power/snapshot.c
+++ b/kernel/power/snapshot.c
@@ -1342,8 +1342,9 @@ static inline void do_copy_page(long *dst, long *src)
  * safe_copy_page - Copy a page in a safe way.
  *
  * Check if the page we are going to copy is marked as present in the kernel
- * page tables (this always is the case if CONFIG_DEBUG_PAGEALLOC is not set
- * and in that case kernel_page_present() always returns 'true').
+ * page tables. This always is the case if CONFIG_DEBUG_PAGEALLOC or
+ * CONFIG_ARCH_HAS_SET_DIRECT_MAP is not set. In that case kernel_page_present()
+ * always returns 'true'.
  */
 static void safe_copy_page(void *dst, struct page *s_page)
 {
diff --git a/kernel/power/suspend.c b/kernel/power/suspend.c
index 0bd595a0b610..ef908c134b34 100644
--- a/kernel/power/suspend.c
+++ b/kernel/power/suspend.c
@@ -17,7 +17,6 @@
 #include <linux/console.h>
 #include <linux/cpu.h>
 #include <linux/cpuidle.h>
-#include <linux/syscalls.h>
 #include <linux/gfp.h>
 #include <linux/io.h>
 #include <linux/kernel.h>
@@ -428,7 +427,7 @@ static int suspend_enter(suspend_state_t state, bool *wakeup)
 	if (suspend_test(TEST_PLATFORM))
 		goto Platform_wake;
 
-	error = disable_nonboot_cpus();
+	error = suspend_disable_secondary_cpus();
 	if (error || suspend_test(TEST_CPUS))
 		goto Enable_cpus;
 
@@ -458,7 +457,7 @@ static int suspend_enter(suspend_state_t state, bool *wakeup)
 	BUG_ON(irqs_disabled());
 
  Enable_cpus:
-	enable_nonboot_cpus();
+	suspend_enable_secondary_cpus();
 
  Platform_wake:
 	platform_resume_noirq(state);
@@ -568,13 +567,11 @@ static int enter_state(suspend_state_t state)
 	if (state == PM_SUSPEND_TO_IDLE)
 		s2idle_begin();
 
-#ifndef CONFIG_SUSPEND_SKIP_SYNC
-	trace_suspend_resume(TPS("sync_filesystems"), 0, true);
-	pr_info("Syncing filesystems ... ");
-	ksys_sync();
-	pr_cont("done.\n");
-	trace_suspend_resume(TPS("sync_filesystems"), 0, false);
-#endif
+	if (!IS_ENABLED(CONFIG_SUSPEND_SKIP_SYNC)) {
+		trace_suspend_resume(TPS("sync_filesystems"), 0, true);
+		ksys_sync_helper();
+		trace_suspend_resume(TPS("sync_filesystems"), 0, false);
+	}
 
 	pm_pr_dbg("Preparing system for sleep (%s)\n", mem_sleep_labels[state]);
 	pm_suspend_clear_flags();
diff --git a/kernel/power/user.c b/kernel/power/user.c
index 2d8b60a3c86b..cb24e840a3e6 100644
--- a/kernel/power/user.c
+++ b/kernel/power/user.c
@@ -10,7 +10,6 @@
  */
 
 #include <linux/suspend.h>
-#include <linux/syscalls.h>
 #include <linux/reboot.h>
 #include <linux/string.h>
 #include <linux/device.h>
@@ -228,9 +227,7 @@ static long snapshot_ioctl(struct file *filp, unsigned int cmd,
 		if (data->frozen)
 			break;
 
-		printk("Syncing filesystems ... ");
-		ksys_sync();
-		printk("done.\n");
+		ksys_sync_helper();
 
 		error = freeze_processes();
 		if (error)
diff --git a/kernel/ptrace.c b/kernel/ptrace.c
index 771e93f9c43f..6f357f4fc859 100644
--- a/kernel/ptrace.c
+++ b/kernel/ptrace.c
@@ -29,6 +29,7 @@
 #include <linux/hw_breakpoint.h>
 #include <linux/cn_proc.h>
 #include <linux/compat.h>
+#include <linux/sched/signal.h>
 
 /*
  * Access another process' address space via ptrace.
@@ -924,18 +925,26 @@ int ptrace_request(struct task_struct *child, long request,
 			ret = ptrace_setsiginfo(child, &siginfo);
 		break;
 
-	case PTRACE_GETSIGMASK:
+	case PTRACE_GETSIGMASK: {
+		sigset_t *mask;
+
 		if (addr != sizeof(sigset_t)) {
 			ret = -EINVAL;
 			break;
 		}
 
-		if (copy_to_user(datavp, &child->blocked, sizeof(sigset_t)))
+		if (test_tsk_restore_sigmask(child))
+			mask = &child->saved_sigmask;
+		else
+			mask = &child->blocked;
+
+		if (copy_to_user(datavp, mask, sizeof(sigset_t)))
 			ret = -EFAULT;
 		else
 			ret = 0;
 
 		break;
+	}
 
 	case PTRACE_SETSIGMASK: {
 		sigset_t new_set;
@@ -961,6 +970,8 @@ int ptrace_request(struct task_struct *child, long request,
 		child->blocked = new_set;
 		spin_unlock_irq(&child->sighand->siglock);
 
+		clear_tsk_restore_sigmask(child);
+
 		ret = 0;
 		break;
 	}
diff --git a/kernel/rcu/rcu.h b/kernel/rcu/rcu.h
index acee72c0b24b..4b58c907b4b7 100644
--- a/kernel/rcu/rcu.h
+++ b/kernel/rcu/rcu.h
@@ -233,6 +233,7 @@ static inline bool __rcu_reclaim(const char *rn, struct rcu_head *head)
 #ifdef CONFIG_RCU_STALL_COMMON
 
 extern int rcu_cpu_stall_suppress;
+extern int rcu_cpu_stall_timeout;
 int rcu_jiffies_till_stall_check(void);
 
 #define rcu_ftrace_dump_stall_suppress() \
diff --git a/kernel/rcu/rcuperf.c b/kernel/rcu/rcuperf.c
index c29761152874..7a6890b23c5f 100644
--- a/kernel/rcu/rcuperf.c
+++ b/kernel/rcu/rcuperf.c
@@ -494,6 +494,10 @@ rcu_perf_cleanup(void)
 
 	if (torture_cleanup_begin())
 		return;
+	if (!cur_ops) {
+		torture_cleanup_end();
+		return;
+	}
 
 	if (reader_tasks) {
 		for (i = 0; i < nrealreaders; i++)
@@ -614,6 +618,7 @@ rcu_perf_init(void)
 		pr_cont("\n");
 		WARN_ON(!IS_MODULE(CONFIG_RCU_PERF_TEST));
 		firsterr = -EINVAL;
+		cur_ops = NULL;
 		goto unwind;
 	}
 	if (cur_ops->init)
diff --git a/kernel/rcu/rcutorture.c b/kernel/rcu/rcutorture.c
index f14d1b18a74f..efaa5b3f4d3f 100644
--- a/kernel/rcu/rcutorture.c
+++ b/kernel/rcu/rcutorture.c
@@ -299,7 +299,6 @@ struct rcu_torture_ops {
 	int irq_capable;
 	int can_boost;
 	int extendables;
-	int ext_irq_conflict;
 	const char *name;
 };
 
@@ -592,12 +591,7 @@ static void srcu_torture_init(void)
 
 static void srcu_torture_cleanup(void)
 {
-	static DEFINE_TORTURE_RANDOM(rand);
-
-	if (torture_random(&rand) & 0x800)
-		cleanup_srcu_struct(&srcu_ctld);
-	else
-		cleanup_srcu_struct_quiesced(&srcu_ctld);
+	cleanup_srcu_struct(&srcu_ctld);
 	srcu_ctlp = &srcu_ctl; /* In case of a later rcutorture run. */
 }
 
@@ -1160,7 +1154,7 @@ rcutorture_extend_mask(int oldmask, struct torture_random_state *trsp)
 	unsigned long randmask2 = randmask1 >> 3;
 
 	WARN_ON_ONCE(mask >> RCUTORTURE_RDR_SHIFT);
-	/* Most of the time lots of bits, half the time only one bit. */
+	/* Mostly only one bit (need preemption!), sometimes lots of bits. */
 	if (!(randmask1 & 0x7))
 		mask = mask & randmask2;
 	else
@@ -1170,10 +1164,6 @@ rcutorture_extend_mask(int oldmask, struct torture_random_state *trsp)
 	    ((!(mask & RCUTORTURE_RDR_BH) && (oldmask & RCUTORTURE_RDR_BH)) ||
 	     (!(mask & RCUTORTURE_RDR_RBH) && (oldmask & RCUTORTURE_RDR_RBH))))
 		mask |= RCUTORTURE_RDR_BH | RCUTORTURE_RDR_RBH;
-	if ((mask & RCUTORTURE_RDR_IRQ) &&
-	    !(mask & cur_ops->ext_irq_conflict) &&
-	    (oldmask & cur_ops->ext_irq_conflict))
-		mask |= cur_ops->ext_irq_conflict; /* Or if readers object. */
 	return mask ?: RCUTORTURE_RDR_RCU;
 }
 
@@ -1848,7 +1838,7 @@ static int rcutorture_oom_notify(struct notifier_block *self,
 	WARN(1, "%s invoked upon OOM during forward-progress testing.\n",
 	     __func__);
 	rcu_torture_fwd_cb_hist();
-	rcu_fwd_progress_check(1 + (jiffies - READ_ONCE(rcu_fwd_startat) / 2));
+	rcu_fwd_progress_check(1 + (jiffies - READ_ONCE(rcu_fwd_startat)) / 2);
 	WRITE_ONCE(rcu_fwd_emergency_stop, true);
 	smp_mb(); /* Emergency stop before free and wait to avoid hangs. */
 	pr_info("%s: Freed %lu RCU callbacks.\n",
@@ -2094,6 +2084,10 @@ rcu_torture_cleanup(void)
 			cur_ops->cb_barrier();
 		return;
 	}
+	if (!cur_ops) {
+		torture_cleanup_end();
+		return;
+	}
 
 	rcu_torture_barrier_cleanup();
 	torture_stop_kthread(rcu_torture_fwd_prog, fwd_prog_task);
@@ -2267,6 +2261,7 @@ rcu_torture_init(void)
 		pr_cont("\n");
 		WARN_ON(!IS_MODULE(CONFIG_RCU_TORTURE_TEST));
 		firsterr = -EINVAL;
+		cur_ops = NULL;
 		goto unwind;
 	}
 	if (cur_ops->fqs == NULL && fqs_duration != 0) {
diff --git a/kernel/rcu/srcutiny.c b/kernel/rcu/srcutiny.c
index 5d4a39a6505a..44d6606b8325 100644
--- a/kernel/rcu/srcutiny.c
+++ b/kernel/rcu/srcutiny.c
@@ -76,19 +76,16 @@ EXPORT_SYMBOL_GPL(init_srcu_struct);
  * Must invoke this after you are finished using a given srcu_struct that
  * was initialized via init_srcu_struct(), else you leak memory.
  */
-void _cleanup_srcu_struct(struct srcu_struct *ssp, bool quiesced)
+void cleanup_srcu_struct(struct srcu_struct *ssp)
 {
 	WARN_ON(ssp->srcu_lock_nesting[0] || ssp->srcu_lock_nesting[1]);
-	if (quiesced)
-		WARN_ON(work_pending(&ssp->srcu_work));
-	else
-		flush_work(&ssp->srcu_work);
+	flush_work(&ssp->srcu_work);
 	WARN_ON(ssp->srcu_gp_running);
 	WARN_ON(ssp->srcu_gp_waiting);
 	WARN_ON(ssp->srcu_cb_head);
 	WARN_ON(&ssp->srcu_cb_head != ssp->srcu_cb_tail);
 }
-EXPORT_SYMBOL_GPL(_cleanup_srcu_struct);
+EXPORT_SYMBOL_GPL(cleanup_srcu_struct);
 
 /*
  * Removes the count for the old reader from the appropriate element of
diff --git a/kernel/rcu/srcutree.c b/kernel/rcu/srcutree.c
index a60b8ba9e1ac..9b761e546de8 100644
--- a/kernel/rcu/srcutree.c
+++ b/kernel/rcu/srcutree.c
@@ -360,8 +360,14 @@ static unsigned long srcu_get_delay(struct srcu_struct *ssp)
 	return SRCU_INTERVAL;
 }
 
-/* Helper for cleanup_srcu_struct() and cleanup_srcu_struct_quiesced(). */
-void _cleanup_srcu_struct(struct srcu_struct *ssp, bool quiesced)
+/**
+ * cleanup_srcu_struct - deconstruct a sleep-RCU structure
+ * @ssp: structure to clean up.
+ *
+ * Must invoke this after you are finished using a given srcu_struct that
+ * was initialized via init_srcu_struct(), else you leak memory.
+ */
+void cleanup_srcu_struct(struct srcu_struct *ssp)
 {
 	int cpu;
 
@@ -369,24 +375,14 @@ void _cleanup_srcu_struct(struct srcu_struct *ssp, bool quiesced)
 		return; /* Just leak it! */
 	if (WARN_ON(srcu_readers_active(ssp)))
 		return; /* Just leak it! */
-	if (quiesced) {
-		if (WARN_ON(delayed_work_pending(&ssp->work)))
-			return; /* Just leak it! */
-	} else {
-		flush_delayed_work(&ssp->work);
-	}
+	flush_delayed_work(&ssp->work);
 	for_each_possible_cpu(cpu) {
 		struct srcu_data *sdp = per_cpu_ptr(ssp->sda, cpu);
 
-		if (quiesced) {
-			if (WARN_ON(timer_pending(&sdp->delay_work)))
-				return; /* Just leak it! */
-			if (WARN_ON(work_pending(&sdp->work)))
-				return; /* Just leak it! */
-		} else {
-			del_timer_sync(&sdp->delay_work);
-			flush_work(&sdp->work);
-		}
+		del_timer_sync(&sdp->delay_work);
+		flush_work(&sdp->work);
+		if (WARN_ON(rcu_segcblist_n_cbs(&sdp->srcu_cblist)))
+			return; /* Forgot srcu_barrier(), so just leak it! */
 	}
 	if (WARN_ON(rcu_seq_state(READ_ONCE(ssp->srcu_gp_seq)) != SRCU_STATE_IDLE) ||
 	    WARN_ON(srcu_readers_active(ssp))) {
@@ -397,7 +393,7 @@ void _cleanup_srcu_struct(struct srcu_struct *ssp, bool quiesced)
 	free_percpu(ssp->sda);
 	ssp->sda = NULL;
 }
-EXPORT_SYMBOL_GPL(_cleanup_srcu_struct);
+EXPORT_SYMBOL_GPL(cleanup_srcu_struct);
 
 /*
  * Counts the new reader in the appropriate per-CPU element of the
diff --git a/kernel/rcu/tiny.c b/kernel/rcu/tiny.c
index 911bd9076d43..477b4eb44af5 100644
--- a/kernel/rcu/tiny.c
+++ b/kernel/rcu/tiny.c
@@ -52,7 +52,7 @@ void rcu_qs(void)
 	local_irq_save(flags);
 	if (rcu_ctrlblk.donetail != rcu_ctrlblk.curtail) {
 		rcu_ctrlblk.donetail = rcu_ctrlblk.curtail;
-		raise_softirq(RCU_SOFTIRQ);
+		raise_softirq_irqoff(RCU_SOFTIRQ);
 	}
 	local_irq_restore(flags);
 }
diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c
index acd6ccf56faf..ec77ec336f58 100644
--- a/kernel/rcu/tree.c
+++ b/kernel/rcu/tree.c
@@ -102,11 +102,6 @@ int rcu_num_lvls __read_mostly = RCU_NUM_LVLS;
 /* Number of rcu_nodes at specified level. */
 int num_rcu_lvl[] = NUM_RCU_LVL_INIT;
 int rcu_num_nodes __read_mostly = NUM_RCU_NODES; /* Total # rcu_nodes in use. */
-/* panic() on RCU Stall sysctl. */
-int sysctl_panic_on_rcu_stall __read_mostly;
-/* Commandeer a sysrq key to dump RCU's tree. */
-static bool sysrq_rcu;
-module_param(sysrq_rcu, bool, 0444);
 
 /*
  * The rcu_scheduler_active variable is initialized to the value
@@ -149,7 +144,7 @@ static void sync_sched_exp_online_cleanup(int cpu);
 
 /* rcuc/rcub kthread realtime priority */
 static int kthread_prio = IS_ENABLED(CONFIG_RCU_BOOST) ? 1 : 0;
-module_param(kthread_prio, int, 0644);
+module_param(kthread_prio, int, 0444);
 
 /* Delay in jiffies for grace-period initialization delays, debug only. */
 
@@ -406,7 +401,7 @@ static bool rcu_kick_kthreads;
  */
 static ulong jiffies_till_sched_qs = ULONG_MAX;
 module_param(jiffies_till_sched_qs, ulong, 0444);
-static ulong jiffies_to_sched_qs; /* Adjusted version of above if not default */
+static ulong jiffies_to_sched_qs; /* See adjust_jiffies_till_sched_qs(). */
 module_param(jiffies_to_sched_qs, ulong, 0444); /* Display only! */
 
 /*
@@ -424,6 +419,7 @@ static void adjust_jiffies_till_sched_qs(void)
 		WRITE_ONCE(jiffies_to_sched_qs, jiffies_till_sched_qs);
 		return;
 	}
+	/* Otherwise, set to third fqs scan, but bound below on large system. */
 	j = READ_ONCE(jiffies_till_first_fqs) +
 		      2 * READ_ONCE(jiffies_till_next_fqs);
 	if (j < HZ / 10 + nr_cpu_ids / RCU_JIFFIES_FQS_DIV)
@@ -513,74 +509,6 @@ static const char *gp_state_getname(short gs)
 }
 
 /*
- * Show the state of the grace-period kthreads.
- */
-void show_rcu_gp_kthreads(void)
-{
-	int cpu;
-	unsigned long j;
-	unsigned long ja;
-	unsigned long jr;
-	unsigned long jw;
-	struct rcu_data *rdp;
-	struct rcu_node *rnp;
-
-	j = jiffies;
-	ja = j - READ_ONCE(rcu_state.gp_activity);
-	jr = j - READ_ONCE(rcu_state.gp_req_activity);
-	jw = j - READ_ONCE(rcu_state.gp_wake_time);
-	pr_info("%s: wait state: %s(%d) ->state: %#lx delta ->gp_activity %lu ->gp_req_activity %lu ->gp_wake_time %lu ->gp_wake_seq %ld ->gp_seq %ld ->gp_seq_needed %ld ->gp_flags %#x\n",
-		rcu_state.name, gp_state_getname(rcu_state.gp_state),
-		rcu_state.gp_state,
-		rcu_state.gp_kthread ? rcu_state.gp_kthread->state : 0x1ffffL,
-		ja, jr, jw, (long)READ_ONCE(rcu_state.gp_wake_seq),
-		(long)READ_ONCE(rcu_state.gp_seq),
-		(long)READ_ONCE(rcu_get_root()->gp_seq_needed),
-		READ_ONCE(rcu_state.gp_flags));
-	rcu_for_each_node_breadth_first(rnp) {
-		if (ULONG_CMP_GE(rcu_state.gp_seq, rnp->gp_seq_needed))
-			continue;
-		pr_info("\trcu_node %d:%d ->gp_seq %ld ->gp_seq_needed %ld\n",
-			rnp->grplo, rnp->grphi, (long)rnp->gp_seq,
-			(long)rnp->gp_seq_needed);
-		if (!rcu_is_leaf_node(rnp))
-			continue;
-		for_each_leaf_node_possible_cpu(rnp, cpu) {
-			rdp = per_cpu_ptr(&rcu_data, cpu);
-			if (rdp->gpwrap ||
-			    ULONG_CMP_GE(rcu_state.gp_seq,
-					 rdp->gp_seq_needed))
-				continue;
-			pr_info("\tcpu %d ->gp_seq_needed %ld\n",
-				cpu, (long)rdp->gp_seq_needed);
-		}
-	}
-	/* sched_show_task(rcu_state.gp_kthread); */
-}
-EXPORT_SYMBOL_GPL(show_rcu_gp_kthreads);
-
-/* Dump grace-period-request information due to commandeered sysrq. */
-static void sysrq_show_rcu(int key)
-{
-	show_rcu_gp_kthreads();
-}
-
-static struct sysrq_key_op sysrq_rcudump_op = {
-	.handler = sysrq_show_rcu,
-	.help_msg = "show-rcu(y)",
-	.action_msg = "Show RCU tree",
-	.enable_mask = SYSRQ_ENABLE_DUMP,
-};
-
-static int __init rcu_sysrq_init(void)
-{
-	if (sysrq_rcu)
-		return register_sysrq_key('y', &sysrq_rcudump_op);
-	return 0;
-}
-early_initcall(rcu_sysrq_init);
-
-/*
  * Send along grace-period-related data for rcutorture diagnostics.
  */
 void rcutorture_get_gp_data(enum rcutorture_type test_type, int *flags,
@@ -1034,27 +962,6 @@ static int dyntick_save_progress_counter(struct rcu_data *rdp)
 }
 
 /*
- * Handler for the irq_work request posted when a grace period has
- * gone on for too long, but not yet long enough for an RCU CPU
- * stall warning.  Set state appropriately, but just complain if
- * there is unexpected state on entry.
- */
-static void rcu_iw_handler(struct irq_work *iwp)
-{
-	struct rcu_data *rdp;
-	struct rcu_node *rnp;
-
-	rdp = container_of(iwp, struct rcu_data, rcu_iw);
-	rnp = rdp->mynode;
-	raw_spin_lock_rcu_node(rnp);
-	if (!WARN_ON_ONCE(!rdp->rcu_iw_pending)) {
-		rdp->rcu_iw_gp_seq = rnp->gp_seq;
-		rdp->rcu_iw_pending = false;
-	}
-	raw_spin_unlock_rcu_node(rnp);
-}
-
-/*
  * Return true if the specified CPU has passed through a quiescent
  * state by virtue of being in or having passed through an dynticks
  * idle state since the last call to dyntick_save_progress_counter()
@@ -1167,295 +1074,6 @@ static int rcu_implicit_dynticks_qs(struct rcu_data *rdp)
 	return 0;
 }
 
-static void record_gp_stall_check_time(void)
-{
-	unsigned long j = jiffies;
-	unsigned long j1;
-
-	rcu_state.gp_start = j;
-	j1 = rcu_jiffies_till_stall_check();
-	/* Record ->gp_start before ->jiffies_stall. */
-	smp_store_release(&rcu_state.jiffies_stall, j + j1); /* ^^^ */
-	rcu_state.jiffies_resched = j + j1 / 2;
-	rcu_state.n_force_qs_gpstart = READ_ONCE(rcu_state.n_force_qs);
-}
-
-/*
- * Complain about starvation of grace-period kthread.
- */
-static void rcu_check_gp_kthread_starvation(void)
-{
-	struct task_struct *gpk = rcu_state.gp_kthread;
-	unsigned long j;
-
-	j = jiffies - READ_ONCE(rcu_state.gp_activity);
-	if (j > 2 * HZ) {
-		pr_err("%s kthread starved for %ld jiffies! g%ld f%#x %s(%d) ->state=%#lx ->cpu=%d\n",
-		       rcu_state.name, j,
-		       (long)rcu_seq_current(&rcu_state.gp_seq),
-		       READ_ONCE(rcu_state.gp_flags),
-		       gp_state_getname(rcu_state.gp_state), rcu_state.gp_state,
-		       gpk ? gpk->state : ~0, gpk ? task_cpu(gpk) : -1);
-		if (gpk) {
-			pr_err("RCU grace-period kthread stack dump:\n");
-			sched_show_task(gpk);
-			wake_up_process(gpk);
-		}
-	}
-}
-
-/*
- * Dump stacks of all tasks running on stalled CPUs.  First try using
- * NMIs, but fall back to manual remote stack tracing on architectures
- * that don't support NMI-based stack dumps.  The NMI-triggered stack
- * traces are more accurate because they are printed by the target CPU.
- */
-static void rcu_dump_cpu_stacks(void)
-{
-	int cpu;
-	unsigned long flags;
-	struct rcu_node *rnp;
-
-	rcu_for_each_leaf_node(rnp) {
-		raw_spin_lock_irqsave_rcu_node(rnp, flags);
-		for_each_leaf_node_possible_cpu(rnp, cpu)
-			if (rnp->qsmask & leaf_node_cpu_bit(rnp, cpu))
-				if (!trigger_single_cpu_backtrace(cpu))
-					dump_cpu_task(cpu);
-		raw_spin_unlock_irqrestore_rcu_node(rnp, flags);
-	}
-}
-
-/*
- * If too much time has passed in the current grace period, and if
- * so configured, go kick the relevant kthreads.
- */
-static void rcu_stall_kick_kthreads(void)
-{
-	unsigned long j;
-
-	if (!rcu_kick_kthreads)
-		return;
-	j = READ_ONCE(rcu_state.jiffies_kick_kthreads);
-	if (time_after(jiffies, j) && rcu_state.gp_kthread &&
-	    (rcu_gp_in_progress() || READ_ONCE(rcu_state.gp_flags))) {
-		WARN_ONCE(1, "Kicking %s grace-period kthread\n",
-			  rcu_state.name);
-		rcu_ftrace_dump(DUMP_ALL);
-		wake_up_process(rcu_state.gp_kthread);
-		WRITE_ONCE(rcu_state.jiffies_kick_kthreads, j + HZ);
-	}
-}
-
-static void panic_on_rcu_stall(void)
-{
-	if (sysctl_panic_on_rcu_stall)
-		panic("RCU Stall\n");
-}
-
-static void print_other_cpu_stall(unsigned long gp_seq)
-{
-	int cpu;
-	unsigned long flags;
-	unsigned long gpa;
-	unsigned long j;
-	int ndetected = 0;
-	struct rcu_node *rnp = rcu_get_root();
-	long totqlen = 0;
-
-	/* Kick and suppress, if so configured. */
-	rcu_stall_kick_kthreads();
-	if (rcu_cpu_stall_suppress)
-		return;
-
-	/*
-	 * OK, time to rat on our buddy...
-	 * See Documentation/RCU/stallwarn.txt for info on how to debug
-	 * RCU CPU stall warnings.
-	 */
-	pr_err("INFO: %s detected stalls on CPUs/tasks:", rcu_state.name);
-	print_cpu_stall_info_begin();
-	rcu_for_each_leaf_node(rnp) {
-		raw_spin_lock_irqsave_rcu_node(rnp, flags);
-		ndetected += rcu_print_task_stall(rnp);
-		if (rnp->qsmask != 0) {
-			for_each_leaf_node_possible_cpu(rnp, cpu)
-				if (rnp->qsmask & leaf_node_cpu_bit(rnp, cpu)) {
-					print_cpu_stall_info(cpu);
-					ndetected++;
-				}
-		}
-		raw_spin_unlock_irqrestore_rcu_node(rnp, flags);
-	}
-
-	print_cpu_stall_info_end();
-	for_each_possible_cpu(cpu)
-		totqlen += rcu_get_n_cbs_cpu(cpu);
-	pr_cont("(detected by %d, t=%ld jiffies, g=%ld, q=%lu)\n",
-	       smp_processor_id(), (long)(jiffies - rcu_state.gp_start),
-	       (long)rcu_seq_current(&rcu_state.gp_seq), totqlen);
-	if (ndetected) {
-		rcu_dump_cpu_stacks();
-
-		/* Complain about tasks blocking the grace period. */
-		rcu_print_detail_task_stall();
-	} else {
-		if (rcu_seq_current(&rcu_state.gp_seq) != gp_seq) {
-			pr_err("INFO: Stall ended before state dump start\n");
-		} else {
-			j = jiffies;
-			gpa = READ_ONCE(rcu_state.gp_activity);
-			pr_err("All QSes seen, last %s kthread activity %ld (%ld-%ld), jiffies_till_next_fqs=%ld, root ->qsmask %#lx\n",
-			       rcu_state.name, j - gpa, j, gpa,
-			       READ_ONCE(jiffies_till_next_fqs),
-			       rcu_get_root()->qsmask);
-			/* In this case, the current CPU might be at fault. */
-			sched_show_task(current);
-		}
-	}
-	/* Rewrite if needed in case of slow consoles. */
-	if (ULONG_CMP_GE(jiffies, READ_ONCE(rcu_state.jiffies_stall)))
-		WRITE_ONCE(rcu_state.jiffies_stall,
-			   jiffies + 3 * rcu_jiffies_till_stall_check() + 3);
-
-	rcu_check_gp_kthread_starvation();
-
-	panic_on_rcu_stall();
-
-	rcu_force_quiescent_state();  /* Kick them all. */
-}
-
-static void print_cpu_stall(void)
-{
-	int cpu;
-	unsigned long flags;
-	struct rcu_data *rdp = this_cpu_ptr(&rcu_data);
-	struct rcu_node *rnp = rcu_get_root();
-	long totqlen = 0;
-
-	/* Kick and suppress, if so configured. */
-	rcu_stall_kick_kthreads();
-	if (rcu_cpu_stall_suppress)
-		return;
-
-	/*
-	 * OK, time to rat on ourselves...
-	 * See Documentation/RCU/stallwarn.txt for info on how to debug
-	 * RCU CPU stall warnings.
-	 */
-	pr_err("INFO: %s self-detected stall on CPU", rcu_state.name);
-	print_cpu_stall_info_begin();
-	raw_spin_lock_irqsave_rcu_node(rdp->mynode, flags);
-	print_cpu_stall_info(smp_processor_id());
-	raw_spin_unlock_irqrestore_rcu_node(rdp->mynode, flags);
-	print_cpu_stall_info_end();
-	for_each_possible_cpu(cpu)
-		totqlen += rcu_get_n_cbs_cpu(cpu);
-	pr_cont(" (t=%lu jiffies g=%ld q=%lu)\n",
-		jiffies - rcu_state.gp_start,
-		(long)rcu_seq_current(&rcu_state.gp_seq), totqlen);
-
-	rcu_check_gp_kthread_starvation();
-
-	rcu_dump_cpu_stacks();
-
-	raw_spin_lock_irqsave_rcu_node(rnp, flags);
-	/* Rewrite if needed in case of slow consoles. */
-	if (ULONG_CMP_GE(jiffies, READ_ONCE(rcu_state.jiffies_stall)))
-		WRITE_ONCE(rcu_state.jiffies_stall,
-			   jiffies + 3 * rcu_jiffies_till_stall_check() + 3);
-	raw_spin_unlock_irqrestore_rcu_node(rnp, flags);
-
-	panic_on_rcu_stall();
-
-	/*
-	 * Attempt to revive the RCU machinery by forcing a context switch.
-	 *
-	 * A context switch would normally allow the RCU state machine to make
-	 * progress and it could be we're stuck in kernel space without context
-	 * switches for an entirely unreasonable amount of time.
-	 */
-	set_tsk_need_resched(current);
-	set_preempt_need_resched();
-}
-
-static void check_cpu_stall(struct rcu_data *rdp)
-{
-	unsigned long gs1;
-	unsigned long gs2;
-	unsigned long gps;
-	unsigned long j;
-	unsigned long jn;
-	unsigned long js;
-	struct rcu_node *rnp;
-
-	if ((rcu_cpu_stall_suppress && !rcu_kick_kthreads) ||
-	    !rcu_gp_in_progress())
-		return;
-	rcu_stall_kick_kthreads();
-	j = jiffies;
-
-	/*
-	 * Lots of memory barriers to reject false positives.
-	 *
-	 * The idea is to pick up rcu_state.gp_seq, then
-	 * rcu_state.jiffies_stall, then rcu_state.gp_start, and finally
-	 * another copy of rcu_state.gp_seq.  These values are updated in
-	 * the opposite order with memory barriers (or equivalent) during
-	 * grace-period initialization and cleanup.  Now, a false positive
-	 * can occur if we get an new value of rcu_state.gp_start and a old
-	 * value of rcu_state.jiffies_stall.  But given the memory barriers,
-	 * the only way that this can happen is if one grace period ends
-	 * and another starts between these two fetches.  This is detected
-	 * by comparing the second fetch of rcu_state.gp_seq with the
-	 * previous fetch from rcu_state.gp_seq.
-	 *
-	 * Given this check, comparisons of jiffies, rcu_state.jiffies_stall,
-	 * and rcu_state.gp_start suffice to forestall false positives.
-	 */
-	gs1 = READ_ONCE(rcu_state.gp_seq);
-	smp_rmb(); /* Pick up ->gp_seq first... */
-	js = READ_ONCE(rcu_state.jiffies_stall);
-	smp_rmb(); /* ...then ->jiffies_stall before the rest... */
-	gps = READ_ONCE(rcu_state.gp_start);
-	smp_rmb(); /* ...and finally ->gp_start before ->gp_seq again. */
-	gs2 = READ_ONCE(rcu_state.gp_seq);
-	if (gs1 != gs2 ||
-	    ULONG_CMP_LT(j, js) ||
-	    ULONG_CMP_GE(gps, js))
-		return; /* No stall or GP completed since entering function. */
-	rnp = rdp->mynode;
-	jn = jiffies + 3 * rcu_jiffies_till_stall_check() + 3;
-	if (rcu_gp_in_progress() &&
-	    (READ_ONCE(rnp->qsmask) & rdp->grpmask) &&
-	    cmpxchg(&rcu_state.jiffies_stall, js, jn) == js) {
-
-		/* We haven't checked in, so go dump stack. */
-		print_cpu_stall();
-
-	} else if (rcu_gp_in_progress() &&
-		   ULONG_CMP_GE(j, js + RCU_STALL_RAT_DELAY) &&
-		   cmpxchg(&rcu_state.jiffies_stall, js, jn) == js) {
-
-		/* They had a few time units to dump stack, so complain. */
-		print_other_cpu_stall(gs2);
-	}
-}
-
-/**
- * rcu_cpu_stall_reset - prevent further stall warnings in current grace period
- *
- * Set the stall-warning timeout way off into the future, thus preventing
- * any RCU CPU stall-warning messages from appearing in the current set of
- * RCU grace periods.
- *
- * The caller must disable hard irqs.
- */
-void rcu_cpu_stall_reset(void)
-{
-	WRITE_ONCE(rcu_state.jiffies_stall, jiffies + ULONG_MAX / 2);
-}
-
 /* Trace-event wrapper function for trace_rcu_future_grace_period.  */
 static void trace_rcu_this_gp(struct rcu_node *rnp, struct rcu_data *rdp,
 			      unsigned long gp_seq_req, const char *s)
@@ -1585,7 +1203,7 @@ static bool rcu_future_gp_cleanup(struct rcu_node *rnp)
 static void rcu_gp_kthread_wake(void)
 {
 	if ((current == rcu_state.gp_kthread &&
-	     !in_interrupt() && !in_serving_softirq()) ||
+	     !in_irq() && !in_serving_softirq()) ||
 	    !READ_ONCE(rcu_state.gp_flags) ||
 	    !rcu_state.gp_kthread)
 		return;
@@ -2295,11 +1913,10 @@ rcu_report_qs_rdp(int cpu, struct rcu_data *rdp)
 		return;
 	}
 	mask = rdp->grpmask;
+	rdp->core_needs_qs = false;
 	if ((rnp->qsmask & mask) == 0) {
 		raw_spin_unlock_irqrestore_rcu_node(rnp, flags);
 	} else {
-		rdp->core_needs_qs = false;
-
 		/*
 		 * This GP can't end until cpu checks in, so all of our
 		 * callbacks can be processed during the next GP.
@@ -2548,11 +2165,11 @@ void rcu_sched_clock_irq(int user)
 }
 
 /*
- * Scan the leaf rcu_node structures, processing dyntick state for any that
- * have not yet encountered a quiescent state, using the function specified.
- * Also initiate boosting for any threads blocked on the root rcu_node.
- *
- * The caller must have suppressed start of new grace periods.
+ * Scan the leaf rcu_node structures.  For each structure on which all
+ * CPUs have reported a quiescent state and on which there are tasks
+ * blocking the current grace period, initiate RCU priority boosting.
+ * Otherwise, invoke the specified function to check dyntick state for
+ * each CPU that has not yet reported a quiescent state.
  */
 static void force_qs_rnp(int (*f)(struct rcu_data *rdp))
 {
@@ -2635,101 +2252,6 @@ void rcu_force_quiescent_state(void)
 }
 EXPORT_SYMBOL_GPL(rcu_force_quiescent_state);
 
-/*
- * This function checks for grace-period requests that fail to motivate
- * RCU to come out of its idle mode.
- */
-void
-rcu_check_gp_start_stall(struct rcu_node *rnp, struct rcu_data *rdp,
-			 const unsigned long gpssdelay)
-{
-	unsigned long flags;
-	unsigned long j;
-	struct rcu_node *rnp_root = rcu_get_root();
-	static atomic_t warned = ATOMIC_INIT(0);
-
-	if (!IS_ENABLED(CONFIG_PROVE_RCU) || rcu_gp_in_progress() ||
-	    ULONG_CMP_GE(rnp_root->gp_seq, rnp_root->gp_seq_needed))
-		return;
-	j = jiffies; /* Expensive access, and in common case don't get here. */
-	if (time_before(j, READ_ONCE(rcu_state.gp_req_activity) + gpssdelay) ||
-	    time_before(j, READ_ONCE(rcu_state.gp_activity) + gpssdelay) ||
-	    atomic_read(&warned))
-		return;
-
-	raw_spin_lock_irqsave_rcu_node(rnp, flags);
-	j = jiffies;
-	if (rcu_gp_in_progress() ||
-	    ULONG_CMP_GE(rnp_root->gp_seq, rnp_root->gp_seq_needed) ||
-	    time_before(j, READ_ONCE(rcu_state.gp_req_activity) + gpssdelay) ||
-	    time_before(j, READ_ONCE(rcu_state.gp_activity) + gpssdelay) ||
-	    atomic_read(&warned)) {
-		raw_spin_unlock_irqrestore_rcu_node(rnp, flags);
-		return;
-	}
-	/* Hold onto the leaf lock to make others see warned==1. */
-
-	if (rnp_root != rnp)
-		raw_spin_lock_rcu_node(rnp_root); /* irqs already disabled. */
-	j = jiffies;
-	if (rcu_gp_in_progress() ||
-	    ULONG_CMP_GE(rnp_root->gp_seq, rnp_root->gp_seq_needed) ||
-	    time_before(j, rcu_state.gp_req_activity + gpssdelay) ||
-	    time_before(j, rcu_state.gp_activity + gpssdelay) ||
-	    atomic_xchg(&warned, 1)) {
-		raw_spin_unlock_rcu_node(rnp_root); /* irqs remain disabled. */
-		raw_spin_unlock_irqrestore_rcu_node(rnp, flags);
-		return;
-	}
-	WARN_ON(1);
-	if (rnp_root != rnp)
-		raw_spin_unlock_rcu_node(rnp_root);
-	raw_spin_unlock_irqrestore_rcu_node(rnp, flags);
-	show_rcu_gp_kthreads();
-}
-
-/*
- * Do a forward-progress check for rcutorture.  This is normally invoked
- * due to an OOM event.  The argument "j" gives the time period during
- * which rcutorture would like progress to have been made.
- */
-void rcu_fwd_progress_check(unsigned long j)
-{
-	unsigned long cbs;
-	int cpu;
-	unsigned long max_cbs = 0;
-	int max_cpu = -1;
-	struct rcu_data *rdp;
-
-	if (rcu_gp_in_progress()) {
-		pr_info("%s: GP age %lu jiffies\n",
-			__func__, jiffies - rcu_state.gp_start);
-		show_rcu_gp_kthreads();
-	} else {
-		pr_info("%s: Last GP end %lu jiffies ago\n",
-			__func__, jiffies - rcu_state.gp_end);
-		preempt_disable();
-		rdp = this_cpu_ptr(&rcu_data);
-		rcu_check_gp_start_stall(rdp->mynode, rdp, j);
-		preempt_enable();
-	}
-	for_each_possible_cpu(cpu) {
-		cbs = rcu_get_n_cbs_cpu(cpu);
-		if (!cbs)
-			continue;
-		if (max_cpu < 0)
-			pr_info("%s: callbacks", __func__);
-		pr_cont(" %d: %lu", cpu, cbs);
-		if (cbs <= max_cbs)
-			continue;
-		max_cbs = cbs;
-		max_cpu = cpu;
-	}
-	if (max_cpu >= 0)
-		pr_cont("\n");
-}
-EXPORT_SYMBOL_GPL(rcu_fwd_progress_check);
-
 /* Perform RCU core processing work for the current CPU.  */
 static __latent_entropy void rcu_core(struct softirq_action *unused)
 {
@@ -3559,13 +3081,11 @@ static int rcu_pm_notify(struct notifier_block *self,
 	switch (action) {
 	case PM_HIBERNATION_PREPARE:
 	case PM_SUSPEND_PREPARE:
-		if (nr_cpu_ids <= 256) /* Expediting bad for large systems. */
-			rcu_expedite_gp();
+		rcu_expedite_gp();
 		break;
 	case PM_POST_HIBERNATION:
 	case PM_POST_SUSPEND:
-		if (nr_cpu_ids <= 256) /* Expediting bad for large systems. */
-			rcu_unexpedite_gp();
+		rcu_unexpedite_gp();
 		break;
 	default:
 		break;
@@ -3742,8 +3262,7 @@ static void __init rcu_init_geometry(void)
 		jiffies_till_first_fqs = d;
 	if (jiffies_till_next_fqs == ULONG_MAX)
 		jiffies_till_next_fqs = d;
-	if (jiffies_till_sched_qs == ULONG_MAX)
-		adjust_jiffies_till_sched_qs();
+	adjust_jiffies_till_sched_qs();
 
 	/* If the compile-time values are accurate, just leave. */
 	if (rcu_fanout_leaf == RCU_FANOUT_LEAF &&
@@ -3858,5 +3377,6 @@ void __init rcu_init(void)
 	srcu_init();
 }
 
+#include "tree_stall.h"
 #include "tree_exp.h"
 #include "tree_plugin.h"
diff --git a/kernel/rcu/tree.h b/kernel/rcu/tree.h
index bb4f995f2d3f..e253d11af3c4 100644
--- a/kernel/rcu/tree.h
+++ b/kernel/rcu/tree.h
@@ -393,15 +393,13 @@ static const char *tp_rcu_varname __used __tracepoint_string = rcu_name;
 
 int rcu_dynticks_snap(struct rcu_data *rdp);
 
-/* Forward declarations for rcutree_plugin.h */
+/* Forward declarations for tree_plugin.h */
 static void rcu_bootup_announce(void);
 static void rcu_qs(void);
 static int rcu_preempt_blocked_readers_cgp(struct rcu_node *rnp);
 #ifdef CONFIG_HOTPLUG_CPU
 static bool rcu_preempt_has_tasks(struct rcu_node *rnp);
 #endif /* #ifdef CONFIG_HOTPLUG_CPU */
-static void rcu_print_detail_task_stall(void);
-static int rcu_print_task_stall(struct rcu_node *rnp);
 static int rcu_print_task_exp_stall(struct rcu_node *rnp);
 static void rcu_preempt_check_blocked_tasks(struct rcu_node *rnp);
 static void rcu_flavor_sched_clock_irq(int user);
@@ -418,9 +416,6 @@ static void rcu_prepare_for_idle(void);
 static bool rcu_preempt_has_tasks(struct rcu_node *rnp);
 static bool rcu_preempt_need_deferred_qs(struct task_struct *t);
 static void rcu_preempt_deferred_qs(struct task_struct *t);
-static void print_cpu_stall_info_begin(void);
-static void print_cpu_stall_info(int cpu);
-static void print_cpu_stall_info_end(void);
 static void zero_cpu_stall_ticks(struct rcu_data *rdp);
 static bool rcu_nocb_cpu_needs_barrier(int cpu);
 static struct swait_queue_head *rcu_nocb_gp_get(struct rcu_node *rnp);
@@ -445,3 +440,10 @@ static void rcu_bind_gp_kthread(void);
 static bool rcu_nohz_full_cpu(void);
 static void rcu_dynticks_task_enter(void);
 static void rcu_dynticks_task_exit(void);
+
+/* Forward declarations for tree_stall.h */
+static void record_gp_stall_check_time(void);
+static void rcu_iw_handler(struct irq_work *iwp);
+static void check_cpu_stall(struct rcu_data *rdp);
+static void rcu_check_gp_start_stall(struct rcu_node *rnp, struct rcu_data *rdp,
+				     const unsigned long gpssdelay);
diff --git a/kernel/rcu/tree_exp.h b/kernel/rcu/tree_exp.h
index 4c2a0189e748..9c990df880d1 100644
--- a/kernel/rcu/tree_exp.h
+++ b/kernel/rcu/tree_exp.h
@@ -10,6 +10,7 @@
 #include <linux/lockdep.h>
 
 static void rcu_exp_handler(void *unused);
+static int rcu_print_task_exp_stall(struct rcu_node *rnp);
 
 /*
  * Record the start of an expedited grace period.
@@ -633,7 +634,7 @@ static void rcu_exp_handler(void *unused)
 		raw_spin_lock_irqsave_rcu_node(rnp, flags);
 		if (rnp->expmask & rdp->grpmask) {
 			rdp->deferred_qs = true;
-			WRITE_ONCE(t->rcu_read_unlock_special.b.exp_hint, true);
+			t->rcu_read_unlock_special.b.exp_hint = true;
 		}
 		raw_spin_unlock_irqrestore_rcu_node(rnp, flags);
 		return;
@@ -648,7 +649,7 @@ static void rcu_exp_handler(void *unused)
 	 *
 	 * If the CPU is fully enabled (or if some buggy RCU-preempt
 	 * read-side critical section is being used from idle), just
-	 * invoke rcu_preempt_defer_qs() to immediately report the
+	 * invoke rcu_preempt_deferred_qs() to immediately report the
 	 * quiescent state.  We cannot use rcu_read_unlock_special()
 	 * because we are in an interrupt handler, which will cause that
 	 * function to take an early exit without doing anything.
@@ -670,6 +671,27 @@ static void sync_sched_exp_online_cleanup(int cpu)
 {
 }
 
+/*
+ * Scan the current list of tasks blocked within RCU read-side critical
+ * sections, printing out the tid of each that is blocking the current
+ * expedited grace period.
+ */
+static int rcu_print_task_exp_stall(struct rcu_node *rnp)
+{
+	struct task_struct *t;
+	int ndetected = 0;
+
+	if (!rnp->exp_tasks)
+		return 0;
+	t = list_entry(rnp->exp_tasks->prev,
+		       struct task_struct, rcu_node_entry);
+	list_for_each_entry_continue(t, &rnp->blkd_tasks, rcu_node_entry) {
+		pr_cont(" P%d", t->pid);
+		ndetected++;
+	}
+	return ndetected;
+}
+
 #else /* #ifdef CONFIG_PREEMPT_RCU */
 
 /* Invoked on each online non-idle CPU for expedited quiescent state. */
@@ -709,6 +731,16 @@ static void sync_sched_exp_online_cleanup(int cpu)
 	WARN_ON_ONCE(ret);
 }
 
+/*
+ * Because preemptible RCU does not exist, we never have to check for
+ * tasks blocked within RCU read-side critical sections that are
+ * blocking the current expedited grace period.
+ */
+static int rcu_print_task_exp_stall(struct rcu_node *rnp)
+{
+	return 0;
+}
+
 #endif /* #else #ifdef CONFIG_PREEMPT_RCU */
 
 /**
diff --git a/kernel/rcu/tree_plugin.h b/kernel/rcu/tree_plugin.h
index 97dba50f6fb2..1102765f91fd 100644
--- a/kernel/rcu/tree_plugin.h
+++ b/kernel/rcu/tree_plugin.h
@@ -285,7 +285,7 @@ static void rcu_qs(void)
 				       TPS("cpuqs"));
 		__this_cpu_write(rcu_data.cpu_no_qs.b.norm, false);
 		barrier(); /* Coordinate with rcu_flavor_sched_clock_irq(). */
-		current->rcu_read_unlock_special.b.need_qs = false;
+		WRITE_ONCE(current->rcu_read_unlock_special.b.need_qs, false);
 	}
 }
 
@@ -643,100 +643,6 @@ static void rcu_read_unlock_special(struct task_struct *t)
 }
 
 /*
- * Dump detailed information for all tasks blocking the current RCU
- * grace period on the specified rcu_node structure.
- */
-static void rcu_print_detail_task_stall_rnp(struct rcu_node *rnp)
-{
-	unsigned long flags;
-	struct task_struct *t;
-
-	raw_spin_lock_irqsave_rcu_node(rnp, flags);
-	if (!rcu_preempt_blocked_readers_cgp(rnp)) {
-		raw_spin_unlock_irqrestore_rcu_node(rnp, flags);
-		return;
-	}
-	t = list_entry(rnp->gp_tasks->prev,
-		       struct task_struct, rcu_node_entry);
-	list_for_each_entry_continue(t, &rnp->blkd_tasks, rcu_node_entry) {
-		/*
-		 * We could be printing a lot while holding a spinlock.
-		 * Avoid triggering hard lockup.
-		 */
-		touch_nmi_watchdog();
-		sched_show_task(t);
-	}
-	raw_spin_unlock_irqrestore_rcu_node(rnp, flags);
-}
-
-/*
- * Dump detailed information for all tasks blocking the current RCU
- * grace period.
- */
-static void rcu_print_detail_task_stall(void)
-{
-	struct rcu_node *rnp = rcu_get_root();
-
-	rcu_print_detail_task_stall_rnp(rnp);
-	rcu_for_each_leaf_node(rnp)
-		rcu_print_detail_task_stall_rnp(rnp);
-}
-
-static void rcu_print_task_stall_begin(struct rcu_node *rnp)
-{
-	pr_err("\tTasks blocked on level-%d rcu_node (CPUs %d-%d):",
-	       rnp->level, rnp->grplo, rnp->grphi);
-}
-
-static void rcu_print_task_stall_end(void)
-{
-	pr_cont("\n");
-}
-
-/*
- * Scan the current list of tasks blocked within RCU read-side critical
- * sections, printing out the tid of each.
- */
-static int rcu_print_task_stall(struct rcu_node *rnp)
-{
-	struct task_struct *t;
-	int ndetected = 0;
-
-	if (!rcu_preempt_blocked_readers_cgp(rnp))
-		return 0;
-	rcu_print_task_stall_begin(rnp);
-	t = list_entry(rnp->gp_tasks->prev,
-		       struct task_struct, rcu_node_entry);
-	list_for_each_entry_continue(t, &rnp->blkd_tasks, rcu_node_entry) {
-		pr_cont(" P%d", t->pid);
-		ndetected++;
-	}
-	rcu_print_task_stall_end();
-	return ndetected;
-}
-
-/*
- * Scan the current list of tasks blocked within RCU read-side critical
- * sections, printing out the tid of each that is blocking the current
- * expedited grace period.
- */
-static int rcu_print_task_exp_stall(struct rcu_node *rnp)
-{
-	struct task_struct *t;
-	int ndetected = 0;
-
-	if (!rnp->exp_tasks)
-		return 0;
-	t = list_entry(rnp->exp_tasks->prev,
-		       struct task_struct, rcu_node_entry);
-	list_for_each_entry_continue(t, &rnp->blkd_tasks, rcu_node_entry) {
-		pr_cont(" P%d", t->pid);
-		ndetected++;
-	}
-	return ndetected;
-}
-
-/*
  * Check that the list of blocked tasks for the newly completed grace
  * period is in fact empty.  It is a serious bug to complete a grace
  * period that still has RCU readers blocked!  This function must be
@@ -804,19 +710,25 @@ static void rcu_flavor_sched_clock_irq(int user)
 
 /*
  * Check for a task exiting while in a preemptible-RCU read-side
- * critical section, clean up if so.  No need to issue warnings,
- * as debug_check_no_locks_held() already does this if lockdep
- * is enabled.
+ * critical section, clean up if so.  No need to issue warnings, as
+ * debug_check_no_locks_held() already does this if lockdep is enabled.
+ * Besides, if this function does anything other than just immediately
+ * return, there was a bug of some sort.  Spewing warnings from this
+ * function is like as not to simply obscure important prior warnings.
  */
 void exit_rcu(void)
 {
 	struct task_struct *t = current;
 
-	if (likely(list_empty(&current->rcu_node_entry)))
+	if (unlikely(!list_empty(&current->rcu_node_entry))) {
+		t->rcu_read_lock_nesting = 1;
+		barrier();
+		WRITE_ONCE(t->rcu_read_unlock_special.b.blocked, true);
+	} else if (unlikely(t->rcu_read_lock_nesting)) {
+		t->rcu_read_lock_nesting = 1;
+	} else {
 		return;
-	t->rcu_read_lock_nesting = 1;
-	barrier();
-	t->rcu_read_unlock_special.b.blocked = true;
+	}
 	__rcu_read_unlock();
 	rcu_preempt_deferred_qs(current);
 }
@@ -980,33 +892,6 @@ static bool rcu_preempt_need_deferred_qs(struct task_struct *t)
 static void rcu_preempt_deferred_qs(struct task_struct *t) { }
 
 /*
- * Because preemptible RCU does not exist, we never have to check for
- * tasks blocked within RCU read-side critical sections.
- */
-static void rcu_print_detail_task_stall(void)
-{
-}
-
-/*
- * Because preemptible RCU does not exist, we never have to check for
- * tasks blocked within RCU read-side critical sections.
- */
-static int rcu_print_task_stall(struct rcu_node *rnp)
-{
-	return 0;
-}
-
-/*
- * Because preemptible RCU does not exist, we never have to check for
- * tasks blocked within RCU read-side critical sections that are
- * blocking the current expedited grace period.
- */
-static int rcu_print_task_exp_stall(struct rcu_node *rnp)
-{
-	return 0;
-}
-
-/*
  * Because there is no preemptible RCU, there can be no readers blocked,
  * so there is no need to check for blocked tasks.  So check only for
  * bogus qsmask values.
@@ -1185,8 +1070,6 @@ static int rcu_boost_kthread(void *arg)
 static void rcu_initiate_boost(struct rcu_node *rnp, unsigned long flags)
 	__releases(rnp->lock)
 {
-	struct task_struct *t;
-
 	raw_lockdep_assert_held_rcu_node(rnp);
 	if (!rcu_preempt_blocked_readers_cgp(rnp) && rnp->exp_tasks == NULL) {
 		raw_spin_unlock_irqrestore_rcu_node(rnp, flags);
@@ -1200,9 +1083,8 @@ static void rcu_initiate_boost(struct rcu_node *rnp, unsigned long flags)
 		if (rnp->exp_tasks == NULL)
 			rnp->boost_tasks = rnp->gp_tasks;
 		raw_spin_unlock_irqrestore_rcu_node(rnp, flags);
-		t = rnp->boost_kthread_task;
-		if (t)
-			rcu_wake_cond(t, rnp->boost_kthread_status);
+		rcu_wake_cond(rnp->boost_kthread_task,
+			      rnp->boost_kthread_status);
 	} else {
 		raw_spin_unlock_irqrestore_rcu_node(rnp, flags);
 	}
@@ -1649,98 +1531,6 @@ static void rcu_cleanup_after_idle(void)
 
 #endif /* #else #if !defined(CONFIG_RCU_FAST_NO_HZ) */
 
-#ifdef CONFIG_RCU_FAST_NO_HZ
-
-static void print_cpu_stall_fast_no_hz(char *cp, int cpu)
-{
-	struct rcu_data *rdp = &per_cpu(rcu_data, cpu);
-
-	sprintf(cp, "last_accelerate: %04lx/%04lx, Nonlazy posted: %c%c%c",
-		rdp->last_accelerate & 0xffff, jiffies & 0xffff,
-		".l"[rdp->all_lazy],
-		".L"[!rcu_segcblist_n_nonlazy_cbs(&rdp->cblist)],
-		".D"[!rdp->tick_nohz_enabled_snap]);
-}
-
-#else /* #ifdef CONFIG_RCU_FAST_NO_HZ */
-
-static void print_cpu_stall_fast_no_hz(char *cp, int cpu)
-{
-	*cp = '\0';
-}
-
-#endif /* #else #ifdef CONFIG_RCU_FAST_NO_HZ */
-
-/* Initiate the stall-info list. */
-static void print_cpu_stall_info_begin(void)
-{
-	pr_cont("\n");
-}
-
-/*
- * Print out diagnostic information for the specified stalled CPU.
- *
- * If the specified CPU is aware of the current RCU grace period, then
- * print the number of scheduling clock interrupts the CPU has taken
- * during the time that it has been aware.  Otherwise, print the number
- * of RCU grace periods that this CPU is ignorant of, for example, "1"
- * if the CPU was aware of the previous grace period.
- *
- * Also print out idle and (if CONFIG_RCU_FAST_NO_HZ) idle-entry info.
- */
-static void print_cpu_stall_info(int cpu)
-{
-	unsigned long delta;
-	char fast_no_hz[72];
-	struct rcu_data *rdp = per_cpu_ptr(&rcu_data, cpu);
-	char *ticks_title;
-	unsigned long ticks_value;
-
-	/*
-	 * We could be printing a lot while holding a spinlock.  Avoid
-	 * triggering hard lockup.
-	 */
-	touch_nmi_watchdog();
-
-	ticks_value = rcu_seq_ctr(rcu_state.gp_seq - rdp->gp_seq);
-	if (ticks_value) {
-		ticks_title = "GPs behind";
-	} else {
-		ticks_title = "ticks this GP";
-		ticks_value = rdp->ticks_this_gp;
-	}
-	print_cpu_stall_fast_no_hz(fast_no_hz, cpu);
-	delta = rcu_seq_ctr(rdp->mynode->gp_seq - rdp->rcu_iw_gp_seq);
-	pr_err("\t%d-%c%c%c%c: (%lu %s) idle=%03x/%ld/%#lx softirq=%u/%u fqs=%ld %s\n",
-	       cpu,
-	       "O."[!!cpu_online(cpu)],
-	       "o."[!!(rdp->grpmask & rdp->mynode->qsmaskinit)],
-	       "N."[!!(rdp->grpmask & rdp->mynode->qsmaskinitnext)],
-	       !IS_ENABLED(CONFIG_IRQ_WORK) ? '?' :
-			rdp->rcu_iw_pending ? (int)min(delta, 9UL) + '0' :
-				"!."[!delta],
-	       ticks_value, ticks_title,
-	       rcu_dynticks_snap(rdp) & 0xfff,
-	       rdp->dynticks_nesting, rdp->dynticks_nmi_nesting,
-	       rdp->softirq_snap, kstat_softirqs_cpu(RCU_SOFTIRQ, cpu),
-	       READ_ONCE(rcu_state.n_force_qs) - rcu_state.n_force_qs_gpstart,
-	       fast_no_hz);
-}
-
-/* Terminate the stall-info list. */
-static void print_cpu_stall_info_end(void)
-{
-	pr_err("\t");
-}
-
-/* Zero ->ticks_this_gp and snapshot the number of RCU softirq handlers. */
-static void zero_cpu_stall_ticks(struct rcu_data *rdp)
-{
-	rdp->ticks_this_gp = 0;
-	rdp->softirq_snap = kstat_softirqs_cpu(RCU_SOFTIRQ, smp_processor_id());
-	WRITE_ONCE(rdp->last_fqs_resched, jiffies);
-}
-
 #ifdef CONFIG_RCU_NOCB_CPU
 
 /*
@@ -1766,11 +1556,22 @@ static void zero_cpu_stall_ticks(struct rcu_data *rdp)
  */
 
 
-/* Parse the boot-time rcu_nocb_mask CPU list from the kernel parameters. */
+/*
+ * Parse the boot-time rcu_nocb_mask CPU list from the kernel parameters.
+ * The string after the "rcu_nocbs=" is either "all" for all CPUs, or a
+ * comma-separated list of CPUs and/or CPU ranges.  If an invalid list is
+ * given, a warning is emitted and all CPUs are offloaded.
+ */
 static int __init rcu_nocb_setup(char *str)
 {
 	alloc_bootmem_cpumask_var(&rcu_nocb_mask);
-	cpulist_parse(str, rcu_nocb_mask);
+	if (!strcasecmp(str, "all"))
+		cpumask_setall(rcu_nocb_mask);
+	else
+		if (cpulist_parse(str, rcu_nocb_mask)) {
+			pr_warn("rcu_nocbs= bad CPU range, all CPUs set\n");
+			cpumask_setall(rcu_nocb_mask);
+		}
 	return 1;
 }
 __setup("rcu_nocbs=", rcu_nocb_setup);
diff --git a/kernel/rcu/tree_stall.h b/kernel/rcu/tree_stall.h
new file mode 100644
index 000000000000..f65a73a97323
--- /dev/null
+++ b/kernel/rcu/tree_stall.h
@@ -0,0 +1,709 @@
+// SPDX-License-Identifier: GPL-2.0+
+/*
+ * RCU CPU stall warnings for normal RCU grace periods
+ *
+ * Copyright IBM Corporation, 2019
+ *
+ * Author: Paul E. McKenney <paulmck@linux.ibm.com>
+ */
+
+//////////////////////////////////////////////////////////////////////////////
+//
+// Controlling CPU stall warnings, including delay calculation.
+
+/* panic() on RCU Stall sysctl. */
+int sysctl_panic_on_rcu_stall __read_mostly;
+
+#ifdef CONFIG_PROVE_RCU
+#define RCU_STALL_DELAY_DELTA	       (5 * HZ)
+#else
+#define RCU_STALL_DELAY_DELTA	       0
+#endif
+
+/* Limit-check stall timeouts specified at boottime and runtime. */
+int rcu_jiffies_till_stall_check(void)
+{
+	int till_stall_check = READ_ONCE(rcu_cpu_stall_timeout);
+
+	/*
+	 * Limit check must be consistent with the Kconfig limits
+	 * for CONFIG_RCU_CPU_STALL_TIMEOUT.
+	 */
+	if (till_stall_check < 3) {
+		WRITE_ONCE(rcu_cpu_stall_timeout, 3);
+		till_stall_check = 3;
+	} else if (till_stall_check > 300) {
+		WRITE_ONCE(rcu_cpu_stall_timeout, 300);
+		till_stall_check = 300;
+	}
+	return till_stall_check * HZ + RCU_STALL_DELAY_DELTA;
+}
+EXPORT_SYMBOL_GPL(rcu_jiffies_till_stall_check);
+
+/* Don't do RCU CPU stall warnings during long sysrq printouts. */
+void rcu_sysrq_start(void)
+{
+	if (!rcu_cpu_stall_suppress)
+		rcu_cpu_stall_suppress = 2;
+}
+
+void rcu_sysrq_end(void)
+{
+	if (rcu_cpu_stall_suppress == 2)
+		rcu_cpu_stall_suppress = 0;
+}
+
+/* Don't print RCU CPU stall warnings during a kernel panic. */
+static int rcu_panic(struct notifier_block *this, unsigned long ev, void *ptr)
+{
+	rcu_cpu_stall_suppress = 1;
+	return NOTIFY_DONE;
+}
+
+static struct notifier_block rcu_panic_block = {
+	.notifier_call = rcu_panic,
+};
+
+static int __init check_cpu_stall_init(void)
+{
+	atomic_notifier_chain_register(&panic_notifier_list, &rcu_panic_block);
+	return 0;
+}
+early_initcall(check_cpu_stall_init);
+
+/* If so specified via sysctl, panic, yielding cleaner stall-warning output. */
+static void panic_on_rcu_stall(void)
+{
+	if (sysctl_panic_on_rcu_stall)
+		panic("RCU Stall\n");
+}
+
+/**
+ * rcu_cpu_stall_reset - prevent further stall warnings in current grace period
+ *
+ * Set the stall-warning timeout way off into the future, thus preventing
+ * any RCU CPU stall-warning messages from appearing in the current set of
+ * RCU grace periods.
+ *
+ * The caller must disable hard irqs.
+ */
+void rcu_cpu_stall_reset(void)
+{
+	WRITE_ONCE(rcu_state.jiffies_stall, jiffies + ULONG_MAX / 2);
+}
+
+//////////////////////////////////////////////////////////////////////////////
+//
+// Interaction with RCU grace periods
+
+/* Start of new grace period, so record stall time (and forcing times). */
+static void record_gp_stall_check_time(void)
+{
+	unsigned long j = jiffies;
+	unsigned long j1;
+
+	rcu_state.gp_start = j;
+	j1 = rcu_jiffies_till_stall_check();
+	/* Record ->gp_start before ->jiffies_stall. */
+	smp_store_release(&rcu_state.jiffies_stall, j + j1); /* ^^^ */
+	rcu_state.jiffies_resched = j + j1 / 2;
+	rcu_state.n_force_qs_gpstart = READ_ONCE(rcu_state.n_force_qs);
+}
+
+/* Zero ->ticks_this_gp and snapshot the number of RCU softirq handlers. */
+static void zero_cpu_stall_ticks(struct rcu_data *rdp)
+{
+	rdp->ticks_this_gp = 0;
+	rdp->softirq_snap = kstat_softirqs_cpu(RCU_SOFTIRQ, smp_processor_id());
+	WRITE_ONCE(rdp->last_fqs_resched, jiffies);
+}
+
+/*
+ * If too much time has passed in the current grace period, and if
+ * so configured, go kick the relevant kthreads.
+ */
+static void rcu_stall_kick_kthreads(void)
+{
+	unsigned long j;
+
+	if (!rcu_kick_kthreads)
+		return;
+	j = READ_ONCE(rcu_state.jiffies_kick_kthreads);
+	if (time_after(jiffies, j) && rcu_state.gp_kthread &&
+	    (rcu_gp_in_progress() || READ_ONCE(rcu_state.gp_flags))) {
+		WARN_ONCE(1, "Kicking %s grace-period kthread\n",
+			  rcu_state.name);
+		rcu_ftrace_dump(DUMP_ALL);
+		wake_up_process(rcu_state.gp_kthread);
+		WRITE_ONCE(rcu_state.jiffies_kick_kthreads, j + HZ);
+	}
+}
+
+/*
+ * Handler for the irq_work request posted about halfway into the RCU CPU
+ * stall timeout, and used to detect excessive irq disabling.  Set state
+ * appropriately, but just complain if there is unexpected state on entry.
+ */
+static void rcu_iw_handler(struct irq_work *iwp)
+{
+	struct rcu_data *rdp;
+	struct rcu_node *rnp;
+
+	rdp = container_of(iwp, struct rcu_data, rcu_iw);
+	rnp = rdp->mynode;
+	raw_spin_lock_rcu_node(rnp);
+	if (!WARN_ON_ONCE(!rdp->rcu_iw_pending)) {
+		rdp->rcu_iw_gp_seq = rnp->gp_seq;
+		rdp->rcu_iw_pending = false;
+	}
+	raw_spin_unlock_rcu_node(rnp);
+}
+
+//////////////////////////////////////////////////////////////////////////////
+//
+// Printing RCU CPU stall warnings
+
+#ifdef CONFIG_PREEMPT
+
+/*
+ * Dump detailed information for all tasks blocking the current RCU
+ * grace period on the specified rcu_node structure.
+ */
+static void rcu_print_detail_task_stall_rnp(struct rcu_node *rnp)
+{
+	unsigned long flags;
+	struct task_struct *t;
+
+	raw_spin_lock_irqsave_rcu_node(rnp, flags);
+	if (!rcu_preempt_blocked_readers_cgp(rnp)) {
+		raw_spin_unlock_irqrestore_rcu_node(rnp, flags);
+		return;
+	}
+	t = list_entry(rnp->gp_tasks->prev,
+		       struct task_struct, rcu_node_entry);
+	list_for_each_entry_continue(t, &rnp->blkd_tasks, rcu_node_entry) {
+		/*
+		 * We could be printing a lot while holding a spinlock.
+		 * Avoid triggering hard lockup.
+		 */
+		touch_nmi_watchdog();
+		sched_show_task(t);
+	}
+	raw_spin_unlock_irqrestore_rcu_node(rnp, flags);
+}
+
+/*
+ * Scan the current list of tasks blocked within RCU read-side critical
+ * sections, printing out the tid of each.
+ */
+static int rcu_print_task_stall(struct rcu_node *rnp)
+{
+	struct task_struct *t;
+	int ndetected = 0;
+
+	if (!rcu_preempt_blocked_readers_cgp(rnp))
+		return 0;
+	pr_err("\tTasks blocked on level-%d rcu_node (CPUs %d-%d):",
+	       rnp->level, rnp->grplo, rnp->grphi);
+	t = list_entry(rnp->gp_tasks->prev,
+		       struct task_struct, rcu_node_entry);
+	list_for_each_entry_continue(t, &rnp->blkd_tasks, rcu_node_entry) {
+		pr_cont(" P%d", t->pid);
+		ndetected++;
+	}
+	pr_cont("\n");
+	return ndetected;
+}
+
+#else /* #ifdef CONFIG_PREEMPT */
+
+/*
+ * Because preemptible RCU does not exist, we never have to check for
+ * tasks blocked within RCU read-side critical sections.
+ */
+static void rcu_print_detail_task_stall_rnp(struct rcu_node *rnp)
+{
+}
+
+/*
+ * Because preemptible RCU does not exist, we never have to check for
+ * tasks blocked within RCU read-side critical sections.
+ */
+static int rcu_print_task_stall(struct rcu_node *rnp)
+{
+	return 0;
+}
+#endif /* #else #ifdef CONFIG_PREEMPT */
+
+/*
+ * Dump stacks of all tasks running on stalled CPUs.  First try using
+ * NMIs, but fall back to manual remote stack tracing on architectures
+ * that don't support NMI-based stack dumps.  The NMI-triggered stack
+ * traces are more accurate because they are printed by the target CPU.
+ */
+static void rcu_dump_cpu_stacks(void)
+{
+	int cpu;
+	unsigned long flags;
+	struct rcu_node *rnp;
+
+	rcu_for_each_leaf_node(rnp) {
+		raw_spin_lock_irqsave_rcu_node(rnp, flags);
+		for_each_leaf_node_possible_cpu(rnp, cpu)
+			if (rnp->qsmask & leaf_node_cpu_bit(rnp, cpu))
+				if (!trigger_single_cpu_backtrace(cpu))
+					dump_cpu_task(cpu);
+		raw_spin_unlock_irqrestore_rcu_node(rnp, flags);
+	}
+}
+
+#ifdef CONFIG_RCU_FAST_NO_HZ
+
+static void print_cpu_stall_fast_no_hz(char *cp, int cpu)
+{
+	struct rcu_data *rdp = &per_cpu(rcu_data, cpu);
+
+	sprintf(cp, "last_accelerate: %04lx/%04lx, Nonlazy posted: %c%c%c",
+		rdp->last_accelerate & 0xffff, jiffies & 0xffff,
+		".l"[rdp->all_lazy],
+		".L"[!rcu_segcblist_n_nonlazy_cbs(&rdp->cblist)],
+		".D"[!!rdp->tick_nohz_enabled_snap]);
+}
+
+#else /* #ifdef CONFIG_RCU_FAST_NO_HZ */
+
+static void print_cpu_stall_fast_no_hz(char *cp, int cpu)
+{
+	*cp = '\0';
+}
+
+#endif /* #else #ifdef CONFIG_RCU_FAST_NO_HZ */
+
+/*
+ * Print out diagnostic information for the specified stalled CPU.
+ *
+ * If the specified CPU is aware of the current RCU grace period, then
+ * print the number of scheduling clock interrupts the CPU has taken
+ * during the time that it has been aware.  Otherwise, print the number
+ * of RCU grace periods that this CPU is ignorant of, for example, "1"
+ * if the CPU was aware of the previous grace period.
+ *
+ * Also print out idle and (if CONFIG_RCU_FAST_NO_HZ) idle-entry info.
+ */
+static void print_cpu_stall_info(int cpu)
+{
+	unsigned long delta;
+	char fast_no_hz[72];
+	struct rcu_data *rdp = per_cpu_ptr(&rcu_data, cpu);
+	char *ticks_title;
+	unsigned long ticks_value;
+
+	/*
+	 * We could be printing a lot while holding a spinlock.  Avoid
+	 * triggering hard lockup.
+	 */
+	touch_nmi_watchdog();
+
+	ticks_value = rcu_seq_ctr(rcu_state.gp_seq - rdp->gp_seq);
+	if (ticks_value) {
+		ticks_title = "GPs behind";
+	} else {
+		ticks_title = "ticks this GP";
+		ticks_value = rdp->ticks_this_gp;
+	}
+	print_cpu_stall_fast_no_hz(fast_no_hz, cpu);
+	delta = rcu_seq_ctr(rdp->mynode->gp_seq - rdp->rcu_iw_gp_seq);
+	pr_err("\t%d-%c%c%c%c: (%lu %s) idle=%03x/%ld/%#lx softirq=%u/%u fqs=%ld %s\n",
+	       cpu,
+	       "O."[!!cpu_online(cpu)],
+	       "o."[!!(rdp->grpmask & rdp->mynode->qsmaskinit)],
+	       "N."[!!(rdp->grpmask & rdp->mynode->qsmaskinitnext)],
+	       !IS_ENABLED(CONFIG_IRQ_WORK) ? '?' :
+			rdp->rcu_iw_pending ? (int)min(delta, 9UL) + '0' :
+				"!."[!delta],
+	       ticks_value, ticks_title,
+	       rcu_dynticks_snap(rdp) & 0xfff,
+	       rdp->dynticks_nesting, rdp->dynticks_nmi_nesting,
+	       rdp->softirq_snap, kstat_softirqs_cpu(RCU_SOFTIRQ, cpu),
+	       READ_ONCE(rcu_state.n_force_qs) - rcu_state.n_force_qs_gpstart,
+	       fast_no_hz);
+}
+
+/* Complain about starvation of grace-period kthread.  */
+static void rcu_check_gp_kthread_starvation(void)
+{
+	struct task_struct *gpk = rcu_state.gp_kthread;
+	unsigned long j;
+
+	j = jiffies - READ_ONCE(rcu_state.gp_activity);
+	if (j > 2 * HZ) {
+		pr_err("%s kthread starved for %ld jiffies! g%ld f%#x %s(%d) ->state=%#lx ->cpu=%d\n",
+		       rcu_state.name, j,
+		       (long)rcu_seq_current(&rcu_state.gp_seq),
+		       READ_ONCE(rcu_state.gp_flags),
+		       gp_state_getname(rcu_state.gp_state), rcu_state.gp_state,
+		       gpk ? gpk->state : ~0, gpk ? task_cpu(gpk) : -1);
+		if (gpk) {
+			pr_err("RCU grace-period kthread stack dump:\n");
+			sched_show_task(gpk);
+			wake_up_process(gpk);
+		}
+	}
+}
+
+static void print_other_cpu_stall(unsigned long gp_seq)
+{
+	int cpu;
+	unsigned long flags;
+	unsigned long gpa;
+	unsigned long j;
+	int ndetected = 0;
+	struct rcu_node *rnp;
+	long totqlen = 0;
+
+	/* Kick and suppress, if so configured. */
+	rcu_stall_kick_kthreads();
+	if (rcu_cpu_stall_suppress)
+		return;
+
+	/*
+	 * OK, time to rat on our buddy...
+	 * See Documentation/RCU/stallwarn.txt for info on how to debug
+	 * RCU CPU stall warnings.
+	 */
+	pr_err("INFO: %s detected stalls on CPUs/tasks:\n", rcu_state.name);
+	rcu_for_each_leaf_node(rnp) {
+		raw_spin_lock_irqsave_rcu_node(rnp, flags);
+		ndetected += rcu_print_task_stall(rnp);
+		if (rnp->qsmask != 0) {
+			for_each_leaf_node_possible_cpu(rnp, cpu)
+				if (rnp->qsmask & leaf_node_cpu_bit(rnp, cpu)) {
+					print_cpu_stall_info(cpu);
+					ndetected++;
+				}
+		}
+		raw_spin_unlock_irqrestore_rcu_node(rnp, flags);
+	}
+
+	for_each_possible_cpu(cpu)
+		totqlen += rcu_get_n_cbs_cpu(cpu);
+	pr_cont("\t(detected by %d, t=%ld jiffies, g=%ld, q=%lu)\n",
+	       smp_processor_id(), (long)(jiffies - rcu_state.gp_start),
+	       (long)rcu_seq_current(&rcu_state.gp_seq), totqlen);
+	if (ndetected) {
+		rcu_dump_cpu_stacks();
+
+		/* Complain about tasks blocking the grace period. */
+		rcu_for_each_leaf_node(rnp)
+			rcu_print_detail_task_stall_rnp(rnp);
+	} else {
+		if (rcu_seq_current(&rcu_state.gp_seq) != gp_seq) {
+			pr_err("INFO: Stall ended before state dump start\n");
+		} else {
+			j = jiffies;
+			gpa = READ_ONCE(rcu_state.gp_activity);
+			pr_err("All QSes seen, last %s kthread activity %ld (%ld-%ld), jiffies_till_next_fqs=%ld, root ->qsmask %#lx\n",
+			       rcu_state.name, j - gpa, j, gpa,
+			       READ_ONCE(jiffies_till_next_fqs),
+			       rcu_get_root()->qsmask);
+			/* In this case, the current CPU might be at fault. */
+			sched_show_task(current);
+		}
+	}
+	/* Rewrite if needed in case of slow consoles. */
+	if (ULONG_CMP_GE(jiffies, READ_ONCE(rcu_state.jiffies_stall)))
+		WRITE_ONCE(rcu_state.jiffies_stall,
+			   jiffies + 3 * rcu_jiffies_till_stall_check() + 3);
+
+	rcu_check_gp_kthread_starvation();
+
+	panic_on_rcu_stall();
+
+	rcu_force_quiescent_state();  /* Kick them all. */
+}
+
+static void print_cpu_stall(void)
+{
+	int cpu;
+	unsigned long flags;
+	struct rcu_data *rdp = this_cpu_ptr(&rcu_data);
+	struct rcu_node *rnp = rcu_get_root();
+	long totqlen = 0;
+
+	/* Kick and suppress, if so configured. */
+	rcu_stall_kick_kthreads();
+	if (rcu_cpu_stall_suppress)
+		return;
+
+	/*
+	 * OK, time to rat on ourselves...
+	 * See Documentation/RCU/stallwarn.txt for info on how to debug
+	 * RCU CPU stall warnings.
+	 */
+	pr_err("INFO: %s self-detected stall on CPU\n", rcu_state.name);
+	raw_spin_lock_irqsave_rcu_node(rdp->mynode, flags);
+	print_cpu_stall_info(smp_processor_id());
+	raw_spin_unlock_irqrestore_rcu_node(rdp->mynode, flags);
+	for_each_possible_cpu(cpu)
+		totqlen += rcu_get_n_cbs_cpu(cpu);
+	pr_cont("\t(t=%lu jiffies g=%ld q=%lu)\n",
+		jiffies - rcu_state.gp_start,
+		(long)rcu_seq_current(&rcu_state.gp_seq), totqlen);
+
+	rcu_check_gp_kthread_starvation();
+
+	rcu_dump_cpu_stacks();
+
+	raw_spin_lock_irqsave_rcu_node(rnp, flags);
+	/* Rewrite if needed in case of slow consoles. */
+	if (ULONG_CMP_GE(jiffies, READ_ONCE(rcu_state.jiffies_stall)))
+		WRITE_ONCE(rcu_state.jiffies_stall,
+			   jiffies + 3 * rcu_jiffies_till_stall_check() + 3);
+	raw_spin_unlock_irqrestore_rcu_node(rnp, flags);
+
+	panic_on_rcu_stall();
+
+	/*
+	 * Attempt to revive the RCU machinery by forcing a context switch.
+	 *
+	 * A context switch would normally allow the RCU state machine to make
+	 * progress and it could be we're stuck in kernel space without context
+	 * switches for an entirely unreasonable amount of time.
+	 */
+	set_tsk_need_resched(current);
+	set_preempt_need_resched();
+}
+
+static void check_cpu_stall(struct rcu_data *rdp)
+{
+	unsigned long gs1;
+	unsigned long gs2;
+	unsigned long gps;
+	unsigned long j;
+	unsigned long jn;
+	unsigned long js;
+	struct rcu_node *rnp;
+
+	if ((rcu_cpu_stall_suppress && !rcu_kick_kthreads) ||
+	    !rcu_gp_in_progress())
+		return;
+	rcu_stall_kick_kthreads();
+	j = jiffies;
+
+	/*
+	 * Lots of memory barriers to reject false positives.
+	 *
+	 * The idea is to pick up rcu_state.gp_seq, then
+	 * rcu_state.jiffies_stall, then rcu_state.gp_start, and finally
+	 * another copy of rcu_state.gp_seq.  These values are updated in
+	 * the opposite order with memory barriers (or equivalent) during
+	 * grace-period initialization and cleanup.  Now, a false positive
+	 * can occur if we get an new value of rcu_state.gp_start and a old
+	 * value of rcu_state.jiffies_stall.  But given the memory barriers,
+	 * the only way that this can happen is if one grace period ends
+	 * and another starts between these two fetches.  This is detected
+	 * by comparing the second fetch of rcu_state.gp_seq with the
+	 * previous fetch from rcu_state.gp_seq.
+	 *
+	 * Given this check, comparisons of jiffies, rcu_state.jiffies_stall,
+	 * and rcu_state.gp_start suffice to forestall false positives.
+	 */
+	gs1 = READ_ONCE(rcu_state.gp_seq);
+	smp_rmb(); /* Pick up ->gp_seq first... */
+	js = READ_ONCE(rcu_state.jiffies_stall);
+	smp_rmb(); /* ...then ->jiffies_stall before the rest... */
+	gps = READ_ONCE(rcu_state.gp_start);
+	smp_rmb(); /* ...and finally ->gp_start before ->gp_seq again. */
+	gs2 = READ_ONCE(rcu_state.gp_seq);
+	if (gs1 != gs2 ||
+	    ULONG_CMP_LT(j, js) ||
+	    ULONG_CMP_GE(gps, js))
+		return; /* No stall or GP completed since entering function. */
+	rnp = rdp->mynode;
+	jn = jiffies + 3 * rcu_jiffies_till_stall_check() + 3;
+	if (rcu_gp_in_progress() &&
+	    (READ_ONCE(rnp->qsmask) & rdp->grpmask) &&
+	    cmpxchg(&rcu_state.jiffies_stall, js, jn) == js) {
+
+		/* We haven't checked in, so go dump stack. */
+		print_cpu_stall();
+
+	} else if (rcu_gp_in_progress() &&
+		   ULONG_CMP_GE(j, js + RCU_STALL_RAT_DELAY) &&
+		   cmpxchg(&rcu_state.jiffies_stall, js, jn) == js) {
+
+		/* They had a few time units to dump stack, so complain. */
+		print_other_cpu_stall(gs2);
+	}
+}
+
+//////////////////////////////////////////////////////////////////////////////
+//
+// RCU forward-progress mechanisms, including of callback invocation.
+
+
+/*
+ * Show the state of the grace-period kthreads.
+ */
+void show_rcu_gp_kthreads(void)
+{
+	int cpu;
+	unsigned long j;
+	unsigned long ja;
+	unsigned long jr;
+	unsigned long jw;
+	struct rcu_data *rdp;
+	struct rcu_node *rnp;
+
+	j = jiffies;
+	ja = j - READ_ONCE(rcu_state.gp_activity);
+	jr = j - READ_ONCE(rcu_state.gp_req_activity);
+	jw = j - READ_ONCE(rcu_state.gp_wake_time);
+	pr_info("%s: wait state: %s(%d) ->state: %#lx delta ->gp_activity %lu ->gp_req_activity %lu ->gp_wake_time %lu ->gp_wake_seq %ld ->gp_seq %ld ->gp_seq_needed %ld ->gp_flags %#x\n",
+		rcu_state.name, gp_state_getname(rcu_state.gp_state),
+		rcu_state.gp_state,
+		rcu_state.gp_kthread ? rcu_state.gp_kthread->state : 0x1ffffL,
+		ja, jr, jw, (long)READ_ONCE(rcu_state.gp_wake_seq),
+		(long)READ_ONCE(rcu_state.gp_seq),
+		(long)READ_ONCE(rcu_get_root()->gp_seq_needed),
+		READ_ONCE(rcu_state.gp_flags));
+	rcu_for_each_node_breadth_first(rnp) {
+		if (ULONG_CMP_GE(rcu_state.gp_seq, rnp->gp_seq_needed))
+			continue;
+		pr_info("\trcu_node %d:%d ->gp_seq %ld ->gp_seq_needed %ld\n",
+			rnp->grplo, rnp->grphi, (long)rnp->gp_seq,
+			(long)rnp->gp_seq_needed);
+		if (!rcu_is_leaf_node(rnp))
+			continue;
+		for_each_leaf_node_possible_cpu(rnp, cpu) {
+			rdp = per_cpu_ptr(&rcu_data, cpu);
+			if (rdp->gpwrap ||
+			    ULONG_CMP_GE(rcu_state.gp_seq,
+					 rdp->gp_seq_needed))
+				continue;
+			pr_info("\tcpu %d ->gp_seq_needed %ld\n",
+				cpu, (long)rdp->gp_seq_needed);
+		}
+	}
+	/* sched_show_task(rcu_state.gp_kthread); */
+}
+EXPORT_SYMBOL_GPL(show_rcu_gp_kthreads);
+
+/*
+ * This function checks for grace-period requests that fail to motivate
+ * RCU to come out of its idle mode.
+ */
+static void rcu_check_gp_start_stall(struct rcu_node *rnp, struct rcu_data *rdp,
+				     const unsigned long gpssdelay)
+{
+	unsigned long flags;
+	unsigned long j;
+	struct rcu_node *rnp_root = rcu_get_root();
+	static atomic_t warned = ATOMIC_INIT(0);
+
+	if (!IS_ENABLED(CONFIG_PROVE_RCU) || rcu_gp_in_progress() ||
+	    ULONG_CMP_GE(rnp_root->gp_seq, rnp_root->gp_seq_needed))
+		return;
+	j = jiffies; /* Expensive access, and in common case don't get here. */
+	if (time_before(j, READ_ONCE(rcu_state.gp_req_activity) + gpssdelay) ||
+	    time_before(j, READ_ONCE(rcu_state.gp_activity) + gpssdelay) ||
+	    atomic_read(&warned))
+		return;
+
+	raw_spin_lock_irqsave_rcu_node(rnp, flags);
+	j = jiffies;
+	if (rcu_gp_in_progress() ||
+	    ULONG_CMP_GE(rnp_root->gp_seq, rnp_root->gp_seq_needed) ||
+	    time_before(j, READ_ONCE(rcu_state.gp_req_activity) + gpssdelay) ||
+	    time_before(j, READ_ONCE(rcu_state.gp_activity) + gpssdelay) ||
+	    atomic_read(&warned)) {
+		raw_spin_unlock_irqrestore_rcu_node(rnp, flags);
+		return;
+	}
+	/* Hold onto the leaf lock to make others see warned==1. */
+
+	if (rnp_root != rnp)
+		raw_spin_lock_rcu_node(rnp_root); /* irqs already disabled. */
+	j = jiffies;
+	if (rcu_gp_in_progress() ||
+	    ULONG_CMP_GE(rnp_root->gp_seq, rnp_root->gp_seq_needed) ||
+	    time_before(j, rcu_state.gp_req_activity + gpssdelay) ||
+	    time_before(j, rcu_state.gp_activity + gpssdelay) ||
+	    atomic_xchg(&warned, 1)) {
+		raw_spin_unlock_rcu_node(rnp_root); /* irqs remain disabled. */
+		raw_spin_unlock_irqrestore_rcu_node(rnp, flags);
+		return;
+	}
+	WARN_ON(1);
+	if (rnp_root != rnp)
+		raw_spin_unlock_rcu_node(rnp_root);
+	raw_spin_unlock_irqrestore_rcu_node(rnp, flags);
+	show_rcu_gp_kthreads();
+}
+
+/*
+ * Do a forward-progress check for rcutorture.  This is normally invoked
+ * due to an OOM event.  The argument "j" gives the time period during
+ * which rcutorture would like progress to have been made.
+ */
+void rcu_fwd_progress_check(unsigned long j)
+{
+	unsigned long cbs;
+	int cpu;
+	unsigned long max_cbs = 0;
+	int max_cpu = -1;
+	struct rcu_data *rdp;
+
+	if (rcu_gp_in_progress()) {
+		pr_info("%s: GP age %lu jiffies\n",
+			__func__, jiffies - rcu_state.gp_start);
+		show_rcu_gp_kthreads();
+	} else {
+		pr_info("%s: Last GP end %lu jiffies ago\n",
+			__func__, jiffies - rcu_state.gp_end);
+		preempt_disable();
+		rdp = this_cpu_ptr(&rcu_data);
+		rcu_check_gp_start_stall(rdp->mynode, rdp, j);
+		preempt_enable();
+	}
+	for_each_possible_cpu(cpu) {
+		cbs = rcu_get_n_cbs_cpu(cpu);
+		if (!cbs)
+			continue;
+		if (max_cpu < 0)
+			pr_info("%s: callbacks", __func__);
+		pr_cont(" %d: %lu", cpu, cbs);
+		if (cbs <= max_cbs)
+			continue;
+		max_cbs = cbs;
+		max_cpu = cpu;
+	}
+	if (max_cpu >= 0)
+		pr_cont("\n");
+}
+EXPORT_SYMBOL_GPL(rcu_fwd_progress_check);
+
+/* Commandeer a sysrq key to dump RCU's tree. */
+static bool sysrq_rcu;
+module_param(sysrq_rcu, bool, 0444);
+
+/* Dump grace-period-request information due to commandeered sysrq. */
+static void sysrq_show_rcu(int key)
+{
+	show_rcu_gp_kthreads();
+}
+
+static struct sysrq_key_op sysrq_rcudump_op = {
+	.handler = sysrq_show_rcu,
+	.help_msg = "show-rcu(y)",
+	.action_msg = "Show RCU tree",
+	.enable_mask = SYSRQ_ENABLE_DUMP,
+};
+
+static int __init rcu_sysrq_init(void)
+{
+	if (sysrq_rcu)
+		return register_sysrq_key('y', &sysrq_rcudump_op);
+	return 0;
+}
+early_initcall(rcu_sysrq_init);
diff --git a/kernel/rcu/update.c b/kernel/rcu/update.c
index cbaa976c5945..c3bf44ba42e5 100644
--- a/kernel/rcu/update.c
+++ b/kernel/rcu/update.c
@@ -424,68 +424,11 @@ EXPORT_SYMBOL_GPL(do_trace_rcu_torture_read);
 #endif
 
 #ifdef CONFIG_RCU_STALL_COMMON
-
-#ifdef CONFIG_PROVE_RCU
-#define RCU_STALL_DELAY_DELTA	       (5 * HZ)
-#else
-#define RCU_STALL_DELAY_DELTA	       0
-#endif
-
 int rcu_cpu_stall_suppress __read_mostly; /* 1 = suppress stall warnings. */
 EXPORT_SYMBOL_GPL(rcu_cpu_stall_suppress);
-static int rcu_cpu_stall_timeout __read_mostly = CONFIG_RCU_CPU_STALL_TIMEOUT;
-
 module_param(rcu_cpu_stall_suppress, int, 0644);
+int rcu_cpu_stall_timeout __read_mostly = CONFIG_RCU_CPU_STALL_TIMEOUT;
 module_param(rcu_cpu_stall_timeout, int, 0644);
-
-int rcu_jiffies_till_stall_check(void)
-{
-	int till_stall_check = READ_ONCE(rcu_cpu_stall_timeout);
-
-	/*
-	 * Limit check must be consistent with the Kconfig limits
-	 * for CONFIG_RCU_CPU_STALL_TIMEOUT.
-	 */
-	if (till_stall_check < 3) {
-		WRITE_ONCE(rcu_cpu_stall_timeout, 3);
-		till_stall_check = 3;
-	} else if (till_stall_check > 300) {
-		WRITE_ONCE(rcu_cpu_stall_timeout, 300);
-		till_stall_check = 300;
-	}
-	return till_stall_check * HZ + RCU_STALL_DELAY_DELTA;
-}
-EXPORT_SYMBOL_GPL(rcu_jiffies_till_stall_check);
-
-void rcu_sysrq_start(void)
-{
-	if (!rcu_cpu_stall_suppress)
-		rcu_cpu_stall_suppress = 2;
-}
-
-void rcu_sysrq_end(void)
-{
-	if (rcu_cpu_stall_suppress == 2)
-		rcu_cpu_stall_suppress = 0;
-}
-
-static int rcu_panic(struct notifier_block *this, unsigned long ev, void *ptr)
-{
-	rcu_cpu_stall_suppress = 1;
-	return NOTIFY_DONE;
-}
-
-static struct notifier_block rcu_panic_block = {
-	.notifier_call = rcu_panic,
-};
-
-static int __init check_cpu_stall_init(void)
-{
-	atomic_notifier_chain_register(&panic_notifier_list, &rcu_panic_block);
-	return 0;
-}
-early_initcall(check_cpu_stall_init);
-
 #endif /* #ifdef CONFIG_RCU_STALL_COMMON */
 
 #ifdef CONFIG_TASKS_RCU
diff --git a/kernel/resource.c b/kernel/resource.c
index 92190f62ebc5..8c15f846e8ef 100644
--- a/kernel/resource.c
+++ b/kernel/resource.c
@@ -520,21 +520,20 @@ EXPORT_SYMBOL_GPL(page_is_ram);
 int region_intersects(resource_size_t start, size_t size, unsigned long flags,
 		      unsigned long desc)
 {
-	resource_size_t end = start + size - 1;
+	struct resource res;
 	int type = 0; int other = 0;
 	struct resource *p;
 
+	res.start = start;
+	res.end = start + size - 1;
+
 	read_lock(&resource_lock);
 	for (p = iomem_resource.child; p ; p = p->sibling) {
 		bool is_type = (((p->flags & flags) == flags) &&
 				((desc == IORES_DESC_NONE) ||
 				 (desc == p->desc)));
 
-		if (start >= p->start && start <= p->end)
-			is_type ? type++ : other++;
-		if (end >= p->start && end <= p->end)
-			is_type ? type++ : other++;
-		if (p->start >= start && p->end <= end)
+		if (resource_overlaps(p, &res))
 			is_type ? type++ : other++;
 	}
 	read_unlock(&resource_lock);
diff --git a/kernel/rseq.c b/kernel/rseq.c
index 25e9a7b60eba..9424ee90589e 100644
--- a/kernel/rseq.c
+++ b/kernel/rseq.c
@@ -254,8 +254,7 @@ static int rseq_ip_fixup(struct pt_regs *regs)
  * - signal delivery,
  * and return to user-space.
  *
- * This is how we can ensure that the entire rseq critical section,
- * consisting of both the C part and the assembly instruction sequence,
+ * This is how we can ensure that the entire rseq critical section
  * will issue the commit instruction only if executed atomically with
  * respect to other threads scheduled on the same CPU, and with respect
  * to signal handlers.
@@ -314,7 +313,7 @@ SYSCALL_DEFINE4(rseq, struct rseq __user *, rseq, u32, rseq_len,
 		/* Unregister rseq for current thread. */
 		if (current->rseq != rseq || !current->rseq)
 			return -EINVAL;
-		if (current->rseq_len != rseq_len)
+		if (rseq_len != sizeof(*rseq))
 			return -EINVAL;
 		if (current->rseq_sig != sig)
 			return -EPERM;
@@ -322,7 +321,6 @@ SYSCALL_DEFINE4(rseq, struct rseq __user *, rseq, u32, rseq_len,
 		if (ret)
 			return ret;
 		current->rseq = NULL;
-		current->rseq_len = 0;
 		current->rseq_sig = 0;
 		return 0;
 	}
@@ -336,7 +334,7 @@ SYSCALL_DEFINE4(rseq, struct rseq __user *, rseq, u32, rseq_len,
 		 * the provided address differs from the prior
 		 * one.
 		 */
-		if (current->rseq != rseq || current->rseq_len != rseq_len)
+		if (current->rseq != rseq || rseq_len != sizeof(*rseq))
 			return -EINVAL;
 		if (current->rseq_sig != sig)
 			return -EPERM;
@@ -354,7 +352,6 @@ SYSCALL_DEFINE4(rseq, struct rseq __user *, rseq, u32, rseq_len,
 	if (!access_ok(rseq, rseq_len))
 		return -EFAULT;
 	current->rseq = rseq;
-	current->rseq_len = rseq_len;
 	current->rseq_sig = sig;
 	/*
 	 * If rseq was previously inactive, and has just been
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 4778c48a7fda..102dfcf0a29a 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -792,10 +792,14 @@ void activate_task(struct rq *rq, struct task_struct *p, int flags)
 		rq->nr_uninterruptible--;
 
 	enqueue_task(rq, p, flags);
+
+	p->on_rq = TASK_ON_RQ_QUEUED;
 }
 
 void deactivate_task(struct rq *rq, struct task_struct *p, int flags)
 {
+	p->on_rq = (flags & DEQUEUE_SLEEP) ? 0 : TASK_ON_RQ_MIGRATING;
+
 	if (task_contributes_to_load(p))
 		rq->nr_uninterruptible++;
 
@@ -920,7 +924,7 @@ static inline bool is_per_cpu_kthread(struct task_struct *p)
 }
 
 /*
- * Per-CPU kthreads are allowed to run on !actie && online CPUs, see
+ * Per-CPU kthreads are allowed to run on !active && online CPUs, see
  * __set_cpus_allowed_ptr() and select_fallback_rq().
  */
 static inline bool is_cpu_allowed(struct task_struct *p, int cpu)
@@ -1151,7 +1155,6 @@ static int __set_cpus_allowed_ptr(struct task_struct *p,
 		/* Need help from migration thread: drop lock and wait. */
 		task_rq_unlock(rq, p, &rf);
 		stop_one_cpu(cpu_of(rq), migration_cpu_stop, &arg);
-		tlb_migrate_finish(p->mm);
 		return 0;
 	} else if (task_on_rq_queued(p)) {
 		/*
@@ -1237,11 +1240,9 @@ static void __migrate_swap_task(struct task_struct *p, int cpu)
 		rq_pin_lock(src_rq, &srf);
 		rq_pin_lock(dst_rq, &drf);
 
-		p->on_rq = TASK_ON_RQ_MIGRATING;
 		deactivate_task(src_rq, p, 0);
 		set_task_cpu(p, cpu);
 		activate_task(dst_rq, p, 0);
-		p->on_rq = TASK_ON_RQ_QUEUED;
 		check_preempt_curr(dst_rq, p, 0);
 
 		rq_unpin_lock(dst_rq, &drf);
@@ -1681,16 +1682,6 @@ ttwu_stat(struct task_struct *p, int cpu, int wake_flags)
 		__schedstat_inc(p->se.statistics.nr_wakeups_sync);
 }
 
-static inline void ttwu_activate(struct rq *rq, struct task_struct *p, int en_flags)
-{
-	activate_task(rq, p, en_flags);
-	p->on_rq = TASK_ON_RQ_QUEUED;
-
-	/* If a worker is waking up, notify the workqueue: */
-	if (p->flags & PF_WQ_WORKER)
-		wq_worker_waking_up(p, cpu_of(rq));
-}
-
 /*
  * Mark the task runnable and perform wakeup-preemption.
  */
@@ -1742,7 +1733,7 @@ ttwu_do_activate(struct rq *rq, struct task_struct *p, int wake_flags,
 		en_flags |= ENQUEUE_MIGRATED;
 #endif
 
-	ttwu_activate(rq, p, en_flags);
+	activate_task(rq, p, en_flags);
 	ttwu_do_wakeup(rq, p, wake_flags, rf);
 }
 
@@ -2107,56 +2098,6 @@ out:
 }
 
 /**
- * try_to_wake_up_local - try to wake up a local task with rq lock held
- * @p: the thread to be awakened
- * @rf: request-queue flags for pinning
- *
- * Put @p on the run-queue if it's not already there. The caller must
- * ensure that this_rq() is locked, @p is bound to this_rq() and not
- * the current task.
- */
-static void try_to_wake_up_local(struct task_struct *p, struct rq_flags *rf)
-{
-	struct rq *rq = task_rq(p);
-
-	if (WARN_ON_ONCE(rq != this_rq()) ||
-	    WARN_ON_ONCE(p == current))
-		return;
-
-	lockdep_assert_held(&rq->lock);
-
-	if (!raw_spin_trylock(&p->pi_lock)) {
-		/*
-		 * This is OK, because current is on_cpu, which avoids it being
-		 * picked for load-balance and preemption/IRQs are still
-		 * disabled avoiding further scheduler activity on it and we've
-		 * not yet picked a replacement task.
-		 */
-		rq_unlock(rq, rf);
-		raw_spin_lock(&p->pi_lock);
-		rq_relock(rq, rf);
-	}
-
-	if (!(p->state & TASK_NORMAL))
-		goto out;
-
-	trace_sched_waking(p);
-
-	if (!task_on_rq_queued(p)) {
-		if (p->in_iowait) {
-			delayacct_blkio_end(p);
-			atomic_dec(&rq->nr_iowait);
-		}
-		ttwu_activate(rq, p, ENQUEUE_WAKEUP | ENQUEUE_NOCLOCK);
-	}
-
-	ttwu_do_wakeup(rq, p, 0, rf);
-	ttwu_stat(p, smp_processor_id(), 0);
-out:
-	raw_spin_unlock(&p->pi_lock);
-}
-
-/**
  * wake_up_process - Wake up a specific process
  * @p: The process to be woken up.
  *
@@ -2467,7 +2408,6 @@ void wake_up_new_task(struct task_struct *p)
 	post_init_entity_util_avg(p);
 
 	activate_task(rq, p, ENQUEUE_NOCLOCK);
-	p->on_rq = TASK_ON_RQ_QUEUED;
 	trace_sched_wakeup_new(p);
 	check_preempt_curr(rq, p, WF_FORK);
 #ifdef CONFIG_SMP
@@ -3466,25 +3406,11 @@ static void __sched notrace __schedule(bool preempt)
 			prev->state = TASK_RUNNING;
 		} else {
 			deactivate_task(rq, prev, DEQUEUE_SLEEP | DEQUEUE_NOCLOCK);
-			prev->on_rq = 0;
 
 			if (prev->in_iowait) {
 				atomic_inc(&rq->nr_iowait);
 				delayacct_blkio_start();
 			}
-
-			/*
-			 * If a worker went to sleep, notify and ask workqueue
-			 * whether it wants to wake up a task to maintain
-			 * concurrency.
-			 */
-			if (prev->flags & PF_WQ_WORKER) {
-				struct task_struct *to_wakeup;
-
-				to_wakeup = wq_worker_sleeping(prev);
-				if (to_wakeup)
-					try_to_wake_up_local(to_wakeup, &rf);
-			}
 		}
 		switch_count = &prev->nvcsw;
 	}
@@ -3544,6 +3470,20 @@ static inline void sched_submit_work(struct task_struct *tsk)
 {
 	if (!tsk->state || tsk_is_pi_blocked(tsk))
 		return;
+
+	/*
+	 * If a worker went to sleep, notify and ask workqueue whether
+	 * it wants to wake up a task to maintain concurrency.
+	 * As this function is called inside the schedule() context,
+	 * we disable preemption to avoid it calling schedule() again
+	 * in the possible wakeup of a kworker.
+	 */
+	if (tsk->flags & PF_WQ_WORKER) {
+		preempt_disable();
+		wq_worker_sleeping(tsk);
+		preempt_enable_no_resched();
+	}
+
 	/*
 	 * If we are going to sleep and we have plugged IO queued,
 	 * make sure to submit it to avoid deadlocks.
@@ -3552,6 +3492,12 @@ static inline void sched_submit_work(struct task_struct *tsk)
 		blk_schedule_flush_plug(tsk);
 }
 
+static void sched_update_worker(struct task_struct *tsk)
+{
+	if (tsk->flags & PF_WQ_WORKER)
+		wq_worker_running(tsk);
+}
+
 asmlinkage __visible void __sched schedule(void)
 {
 	struct task_struct *tsk = current;
@@ -3562,6 +3508,7 @@ asmlinkage __visible void __sched schedule(void)
 		__schedule(false);
 		sched_preempt_enable_no_resched();
 	} while (need_resched());
+	sched_update_worker(tsk);
 }
 EXPORT_SYMBOL(schedule);
 
@@ -5918,7 +5865,7 @@ void __init sched_init_smp(void)
 
 static int __init migration_init(void)
 {
-	sched_rq_cpu_starting(smp_processor_id());
+	sched_cpu_starting(smp_processor_id());
 	return 0;
 }
 early_initcall(migration_init);
@@ -6559,6 +6506,8 @@ static void cpu_cgroup_attach(struct cgroup_taskset *tset)
 static int cpu_shares_write_u64(struct cgroup_subsys_state *css,
 				struct cftype *cftype, u64 shareval)
 {
+	if (shareval > scale_load_down(ULONG_MAX))
+		shareval = MAX_SHARES;
 	return sched_group_set_shares(css_tg(css), scale_load(shareval));
 }
 
@@ -6574,7 +6523,7 @@ static u64 cpu_shares_read_u64(struct cgroup_subsys_state *css,
 static DEFINE_MUTEX(cfs_constraints_mutex);
 
 const u64 max_cfs_quota_period = 1 * NSEC_PER_SEC; /* 1s */
-const u64 min_cfs_quota_period = 1 * NSEC_PER_MSEC; /* 1ms */
+static const u64 min_cfs_quota_period = 1 * NSEC_PER_MSEC; /* 1ms */
 
 static int __cfs_schedulable(struct task_group *tg, u64 period, u64 runtime);
 
@@ -6654,20 +6603,22 @@ out_unlock:
 	return ret;
 }
 
-int tg_set_cfs_quota(struct task_group *tg, long cfs_quota_us)
+static int tg_set_cfs_quota(struct task_group *tg, long cfs_quota_us)
 {
 	u64 quota, period;
 
 	period = ktime_to_ns(tg->cfs_bandwidth.period);
 	if (cfs_quota_us < 0)
 		quota = RUNTIME_INF;
-	else
+	else if ((u64)cfs_quota_us <= U64_MAX / NSEC_PER_USEC)
 		quota = (u64)cfs_quota_us * NSEC_PER_USEC;
+	else
+		return -EINVAL;
 
 	return tg_set_cfs_bandwidth(tg, period, quota);
 }
 
-long tg_get_cfs_quota(struct task_group *tg)
+static long tg_get_cfs_quota(struct task_group *tg)
 {
 	u64 quota_us;
 
@@ -6680,17 +6631,20 @@ long tg_get_cfs_quota(struct task_group *tg)
 	return quota_us;
 }
 
-int tg_set_cfs_period(struct task_group *tg, long cfs_period_us)
+static int tg_set_cfs_period(struct task_group *tg, long cfs_period_us)
 {
 	u64 quota, period;
 
+	if ((u64)cfs_period_us > U64_MAX / NSEC_PER_USEC)
+		return -EINVAL;
+
 	period = (u64)cfs_period_us * NSEC_PER_USEC;
 	quota = tg->cfs_bandwidth.quota;
 
 	return tg_set_cfs_bandwidth(tg, period, quota);
 }
 
-long tg_get_cfs_period(struct task_group *tg)
+static long tg_get_cfs_period(struct task_group *tg)
 {
 	u64 cfs_period_us;
 
diff --git a/kernel/sched/cpufreq.c b/kernel/sched/cpufreq.c
index 835671f0f917..b5dcd1d83c7f 100644
--- a/kernel/sched/cpufreq.c
+++ b/kernel/sched/cpufreq.c
@@ -7,7 +7,7 @@
  */
 #include "sched.h"
 
-DEFINE_PER_CPU(struct update_util_data *, cpufreq_update_util_data);
+DEFINE_PER_CPU(struct update_util_data __rcu *, cpufreq_update_util_data);
 
 /**
  * cpufreq_add_update_util_hook - Populate the CPU's update_util_data pointer.
diff --git a/kernel/sched/cpufreq_schedutil.c b/kernel/sched/cpufreq_schedutil.c
index 5c41ea367422..5403479073b0 100644
--- a/kernel/sched/cpufreq_schedutil.c
+++ b/kernel/sched/cpufreq_schedutil.c
@@ -13,6 +13,8 @@
 #include <linux/sched/cpufreq.h>
 #include <trace/events/power.h>
 
+#define IOWAIT_BOOST_MIN	(SCHED_CAPACITY_SCALE / 8)
+
 struct sugov_tunables {
 	struct gov_attr_set	attr_set;
 	unsigned int		rate_limit_us;
@@ -51,7 +53,6 @@ struct sugov_cpu {
 	u64			last_update;
 
 	unsigned long		bw_dl;
-	unsigned long		min;
 	unsigned long		max;
 
 	/* The field below is for single-CPU policies only: */
@@ -291,8 +292,8 @@ static unsigned long sugov_get_util(struct sugov_cpu *sg_cpu)
  *
  * The IO wait boost of a task is disabled after a tick since the last update
  * of a CPU. If a new IO wait boost is requested after more then a tick, then
- * we enable the boost starting from the minimum frequency, which improves
- * energy efficiency by ignoring sporadic wakeups from IO.
+ * we enable the boost starting from IOWAIT_BOOST_MIN, which improves energy
+ * efficiency by ignoring sporadic wakeups from IO.
  */
 static bool sugov_iowait_reset(struct sugov_cpu *sg_cpu, u64 time,
 			       bool set_iowait_boost)
@@ -303,7 +304,7 @@ static bool sugov_iowait_reset(struct sugov_cpu *sg_cpu, u64 time,
 	if (delta_ns <= TICK_NSEC)
 		return false;
 
-	sg_cpu->iowait_boost = set_iowait_boost ? sg_cpu->min : 0;
+	sg_cpu->iowait_boost = set_iowait_boost ? IOWAIT_BOOST_MIN : 0;
 	sg_cpu->iowait_boost_pending = set_iowait_boost;
 
 	return true;
@@ -317,8 +318,9 @@ static bool sugov_iowait_reset(struct sugov_cpu *sg_cpu, u64 time,
  *
  * Each time a task wakes up after an IO operation, the CPU utilization can be
  * boosted to a certain utilization which doubles at each "frequent and
- * successive" wakeup from IO, ranging from the utilization of the minimum
- * OPP to the utilization of the maximum OPP.
+ * successive" wakeup from IO, ranging from IOWAIT_BOOST_MIN to the utilization
+ * of the maximum OPP.
+ *
  * To keep doubling, an IO boost has to be requested at least once per tick,
  * otherwise we restart from the utilization of the minimum OPP.
  */
@@ -349,7 +351,7 @@ static void sugov_iowait_boost(struct sugov_cpu *sg_cpu, u64 time,
 	}
 
 	/* First wakeup after IO: start with minimum boost */
-	sg_cpu->iowait_boost = sg_cpu->min;
+	sg_cpu->iowait_boost = IOWAIT_BOOST_MIN;
 }
 
 /**
@@ -389,7 +391,7 @@ static unsigned long sugov_iowait_apply(struct sugov_cpu *sg_cpu, u64 time,
 		 * No boost pending; reduce the boost value.
 		 */
 		sg_cpu->iowait_boost >>= 1;
-		if (sg_cpu->iowait_boost < sg_cpu->min) {
+		if (sg_cpu->iowait_boost < IOWAIT_BOOST_MIN) {
 			sg_cpu->iowait_boost = 0;
 			return util;
 		}
@@ -771,6 +773,7 @@ out:
 	return 0;
 
 fail:
+	kobject_put(&tunables->attr_set.kobj);
 	policy->governor_data = NULL;
 	sugov_tunables_free(tunables);
 
@@ -826,9 +829,6 @@ static int sugov_start(struct cpufreq_policy *policy)
 		memset(sg_cpu, 0, sizeof(*sg_cpu));
 		sg_cpu->cpu			= cpu;
 		sg_cpu->sg_policy		= sg_policy;
-		sg_cpu->min			=
-			(SCHED_CAPACITY_SCALE * policy->cpuinfo.min_freq) /
-			policy->cpuinfo.max_freq;
 	}
 
 	for_each_cpu(cpu, policy->cpus) {
diff --git a/kernel/sched/deadline.c b/kernel/sched/deadline.c
index 6a73e41a2016..43901fa3f269 100644
--- a/kernel/sched/deadline.c
+++ b/kernel/sched/deadline.c
@@ -252,7 +252,6 @@ static void task_non_contending(struct task_struct *p)
 	if (dl_entity_is_special(dl_se))
 		return;
 
-	WARN_ON(hrtimer_active(&dl_se->inactive_timer));
 	WARN_ON(dl_se->dl_non_contending);
 
 	zerolag_time = dl_se->deadline -
@@ -269,7 +268,7 @@ static void task_non_contending(struct task_struct *p)
 	 * If the "0-lag time" already passed, decrease the active
 	 * utilization now, instead of starting a timer
 	 */
-	if (zerolag_time < 0) {
+	if ((zerolag_time < 0) || hrtimer_active(&dl_se->inactive_timer)) {
 		if (dl_task(p))
 			sub_running_bw(dl_se, dl_rq);
 		if (!dl_task(p) || p->state == TASK_DEAD) {
diff --git a/kernel/sched/debug.c b/kernel/sched/debug.c
index 8039d62ae36e..678bfb9bd87f 100644
--- a/kernel/sched/debug.c
+++ b/kernel/sched/debug.c
@@ -702,7 +702,7 @@ do {									\
 
 static const char *sched_tunable_scaling_names[] = {
 	"none",
-	"logaritmic",
+	"logarithmic",
 	"linear"
 };
 
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index fdab7eb6f351..f35930f5e528 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -2007,6 +2007,10 @@ static u64 numa_get_avg_runtime(struct task_struct *p, u64 *period)
 	if (p->last_task_numa_placement) {
 		delta = runtime - p->last_sum_exec_runtime;
 		*period = now - p->last_task_numa_placement;
+
+		/* Avoid time going backwards, prevent potential divide error: */
+		if (unlikely((s64)*period < 0))
+			*period = 0;
 	} else {
 		delta = p->se.avg.load_sum;
 		*period = LOAD_AVG_MAX;
@@ -2593,7 +2597,7 @@ out:
 /*
  * Drive the periodic memory faults..
  */
-void task_tick_numa(struct rq *rq, struct task_struct *curr)
+static void task_tick_numa(struct rq *rq, struct task_struct *curr)
 {
 	struct callback_head *work = &curr->numa_work;
 	u64 period, now;
@@ -3567,7 +3571,7 @@ static inline u64 cfs_rq_last_update_time(struct cfs_rq *cfs_rq)
  * Synchronize entity load avg of dequeued entity without locking
  * the previous rq.
  */
-void sync_entity_load_avg(struct sched_entity *se)
+static void sync_entity_load_avg(struct sched_entity *se)
 {
 	struct cfs_rq *cfs_rq = cfs_rq_of(se);
 	u64 last_update_time;
@@ -3580,7 +3584,7 @@ void sync_entity_load_avg(struct sched_entity *se)
  * Task first catches up with cfs_rq, and then subtract
  * itself from the cfs_rq (task must be off the queue now).
  */
-void remove_entity_load_avg(struct sched_entity *se)
+static void remove_entity_load_avg(struct sched_entity *se)
 {
 	struct cfs_rq *cfs_rq = cfs_rq_of(se);
 	unsigned long flags;
@@ -4885,6 +4889,8 @@ static enum hrtimer_restart sched_cfs_slack_timer(struct hrtimer *timer)
 	return HRTIMER_NORESTART;
 }
 
+extern const u64 max_cfs_quota_period;
+
 static enum hrtimer_restart sched_cfs_period_timer(struct hrtimer *timer)
 {
 	struct cfs_bandwidth *cfs_b =
@@ -4892,6 +4898,7 @@ static enum hrtimer_restart sched_cfs_period_timer(struct hrtimer *timer)
 	unsigned long flags;
 	int overrun;
 	int idle = 0;
+	int count = 0;
 
 	raw_spin_lock_irqsave(&cfs_b->lock, flags);
 	for (;;) {
@@ -4899,6 +4906,28 @@ static enum hrtimer_restart sched_cfs_period_timer(struct hrtimer *timer)
 		if (!overrun)
 			break;
 
+		if (++count > 3) {
+			u64 new, old = ktime_to_ns(cfs_b->period);
+
+			new = (old * 147) / 128; /* ~115% */
+			new = min(new, max_cfs_quota_period);
+
+			cfs_b->period = ns_to_ktime(new);
+
+			/* since max is 1s, this is limited to 1e9^2, which fits in u64 */
+			cfs_b->quota *= new;
+			cfs_b->quota = div64_u64(cfs_b->quota, old);
+
+			pr_warn_ratelimited(
+	"cfs_period_timer[cpu%d]: period too short, scaling up (new cfs_period_us %lld, cfs_quota_us = %lld)\n",
+				smp_processor_id(),
+				div_u64(new, NSEC_PER_USEC),
+				div_u64(cfs_b->quota, NSEC_PER_USEC));
+
+			/* reset count so we don't come right back in here */
+			count = 0;
+		}
+
 		idle = do_sched_cfs_period_timer(cfs_b, overrun, flags);
 	}
 	if (idle)
@@ -5116,7 +5145,6 @@ static inline void hrtick_update(struct rq *rq)
 
 #ifdef CONFIG_SMP
 static inline unsigned long cpu_util(int cpu);
-static unsigned long capacity_of(int cpu);
 
 static inline bool cpu_overutilized(int cpu)
 {
@@ -7492,7 +7520,6 @@ static void detach_task(struct task_struct *p, struct lb_env *env)
 {
 	lockdep_assert_held(&env->src_rq->lock);
 
-	p->on_rq = TASK_ON_RQ_MIGRATING;
 	deactivate_task(env->src_rq, p, DEQUEUE_NOCLOCK);
 	set_task_cpu(p, env->dst_cpu);
 }
@@ -7628,7 +7655,6 @@ static void attach_task(struct rq *rq, struct task_struct *p)
 
 	BUG_ON(task_rq(p) != rq);
 	activate_task(rq, p, ENQUEUE_NOCLOCK);
-	p->on_rq = TASK_ON_RQ_QUEUED;
 	check_preempt_curr(rq, p, 0);
 }
 
@@ -7784,10 +7810,10 @@ static void update_cfs_rq_h_load(struct cfs_rq *cfs_rq)
 	if (cfs_rq->last_h_load_update == now)
 		return;
 
-	cfs_rq->h_load_next = NULL;
+	WRITE_ONCE(cfs_rq->h_load_next, NULL);
 	for_each_sched_entity(se) {
 		cfs_rq = cfs_rq_of(se);
-		cfs_rq->h_load_next = se;
+		WRITE_ONCE(cfs_rq->h_load_next, se);
 		if (cfs_rq->last_h_load_update == now)
 			break;
 	}
@@ -7797,7 +7823,7 @@ static void update_cfs_rq_h_load(struct cfs_rq *cfs_rq)
 		cfs_rq->last_h_load_update = now;
 	}
 
-	while ((se = cfs_rq->h_load_next) != NULL) {
+	while ((se = READ_ONCE(cfs_rq->h_load_next)) != NULL) {
 		load = cfs_rq->h_load;
 		load = div64_ul(load * se->avg.load_avg,
 			cfs_rq_load_avg(cfs_rq) + 1);
@@ -9522,22 +9548,26 @@ static inline int on_null_domain(struct rq *rq)
  * - When one of the busy CPUs notice that there may be an idle rebalancing
  *   needed, they will kick the idle load balancer, which then does idle
  *   load balancing for all the idle CPUs.
+ * - HK_FLAG_MISC CPUs are used for this task, because HK_FLAG_SCHED not set
+ *   anywhere yet.
  */
 
 static inline int find_new_ilb(void)
 {
-	int ilb = cpumask_first(nohz.idle_cpus_mask);
+	int ilb;
 
-	if (ilb < nr_cpu_ids && idle_cpu(ilb))
-		return ilb;
+	for_each_cpu_and(ilb, nohz.idle_cpus_mask,
+			      housekeeping_cpumask(HK_FLAG_MISC)) {
+		if (idle_cpu(ilb))
+			return ilb;
+	}
 
 	return nr_cpu_ids;
 }
 
 /*
- * Kick a CPU to do the nohz balancing, if it is time for it. We pick the
- * nohz_load_balancer CPU (if there is one) otherwise fallback to any idle
- * CPU (if there is one).
+ * Kick a CPU to do the nohz balancing, if it is time for it. We pick any
+ * idle CPU in the HK_FLAG_MISC housekeeping set (if there is one).
  */
 static void kick_ilb(unsigned int flags)
 {
diff --git a/kernel/sched/isolation.c b/kernel/sched/isolation.c
index b02d148e7672..687302051a27 100644
--- a/kernel/sched/isolation.c
+++ b/kernel/sched/isolation.c
@@ -65,6 +65,7 @@ void __init housekeeping_init(void)
 static int __init housekeeping_setup(char *str, enum hk_flags flags)
 {
 	cpumask_var_t non_housekeeping_mask;
+	cpumask_var_t tmp;
 	int err;
 
 	alloc_bootmem_cpumask_var(&non_housekeeping_mask);
@@ -75,16 +76,23 @@ static int __init housekeeping_setup(char *str, enum hk_flags flags)
 		return 0;
 	}
 
+	alloc_bootmem_cpumask_var(&tmp);
 	if (!housekeeping_flags) {
 		alloc_bootmem_cpumask_var(&housekeeping_mask);
 		cpumask_andnot(housekeeping_mask,
 			       cpu_possible_mask, non_housekeeping_mask);
-		if (cpumask_empty(housekeeping_mask))
+
+		cpumask_andnot(tmp, cpu_present_mask, non_housekeeping_mask);
+		if (cpumask_empty(tmp)) {
+			pr_warn("Housekeeping: must include one present CPU, "
+				"using boot CPU:%d\n", smp_processor_id());
 			__cpumask_set_cpu(smp_processor_id(), housekeeping_mask);
+			__cpumask_clear_cpu(smp_processor_id(), non_housekeeping_mask);
+		}
 	} else {
-		cpumask_var_t tmp;
-
-		alloc_bootmem_cpumask_var(&tmp);
+		cpumask_andnot(tmp, cpu_present_mask, non_housekeeping_mask);
+		if (cpumask_empty(tmp))
+			__cpumask_clear_cpu(smp_processor_id(), non_housekeeping_mask);
 		cpumask_andnot(tmp, cpu_possible_mask, non_housekeeping_mask);
 		if (!cpumask_equal(tmp, housekeeping_mask)) {
 			pr_warn("Housekeeping: nohz_full= must match isolcpus=\n");
@@ -92,8 +100,8 @@ static int __init housekeeping_setup(char *str, enum hk_flags flags)
 			free_bootmem_cpumask_var(non_housekeeping_mask);
 			return 0;
 		}
-		free_bootmem_cpumask_var(tmp);
 	}
+	free_bootmem_cpumask_var(tmp);
 
 	if ((flags & HK_FLAG_TICK) && !(housekeeping_flags & HK_FLAG_TICK)) {
 		if (IS_ENABLED(CONFIG_NO_HZ_FULL)) {
diff --git a/kernel/sched/rt.c b/kernel/sched/rt.c
index 90fa23d36565..1e6b909dca36 100644
--- a/kernel/sched/rt.c
+++ b/kernel/sched/rt.c
@@ -2555,6 +2555,8 @@ int sched_group_set_rt_runtime(struct task_group *tg, long rt_runtime_us)
 	rt_runtime = (u64)rt_runtime_us * NSEC_PER_USEC;
 	if (rt_runtime_us < 0)
 		rt_runtime = RUNTIME_INF;
+	else if ((u64)rt_runtime_us > U64_MAX / NSEC_PER_USEC)
+		return -EINVAL;
 
 	return tg_set_rt_bandwidth(tg, rt_period, rt_runtime);
 }
@@ -2575,6 +2577,9 @@ int sched_group_set_rt_period(struct task_group *tg, u64 rt_period_us)
 {
 	u64 rt_runtime, rt_period;
 
+	if (rt_period_us > U64_MAX / NSEC_PER_USEC)
+		return -EINVAL;
+
 	rt_period = rt_period_us * NSEC_PER_USEC;
 	rt_runtime = tg->rt_bandwidth.rt_runtime;
 
diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
index efa686eeff26..b52ed1ada0be 100644
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h
@@ -780,7 +780,7 @@ struct root_domain {
 	 * NULL-terminated list of performance domains intersecting with the
 	 * CPUs of the rd. Protected by RCU.
 	 */
-	struct perf_domain	*pd;
+	struct perf_domain __rcu *pd;
 };
 
 extern struct root_domain def_root_domain;
@@ -869,8 +869,8 @@ struct rq {
 	atomic_t		nr_iowait;
 
 #ifdef CONFIG_SMP
-	struct root_domain	*rd;
-	struct sched_domain	*sd;
+	struct root_domain		*rd;
+	struct sched_domain __rcu	*sd;
 
 	unsigned long		cpu_capacity;
 	unsigned long		cpu_capacity_orig;
@@ -1324,13 +1324,13 @@ static inline struct sched_domain *lowest_flag_domain(int cpu, int flag)
 	return sd;
 }
 
-DECLARE_PER_CPU(struct sched_domain *, sd_llc);
+DECLARE_PER_CPU(struct sched_domain __rcu *, sd_llc);
 DECLARE_PER_CPU(int, sd_llc_size);
 DECLARE_PER_CPU(int, sd_llc_id);
-DECLARE_PER_CPU(struct sched_domain_shared *, sd_llc_shared);
-DECLARE_PER_CPU(struct sched_domain *, sd_numa);
-DECLARE_PER_CPU(struct sched_domain *, sd_asym_packing);
-DECLARE_PER_CPU(struct sched_domain *, sd_asym_cpucapacity);
+DECLARE_PER_CPU(struct sched_domain_shared __rcu *, sd_llc_shared);
+DECLARE_PER_CPU(struct sched_domain __rcu *, sd_numa);
+DECLARE_PER_CPU(struct sched_domain __rcu *, sd_asym_packing);
+DECLARE_PER_CPU(struct sched_domain __rcu *, sd_asym_cpucapacity);
 extern struct static_key_false sched_asym_cpucapacity;
 
 struct sched_group_capacity {
@@ -2185,7 +2185,7 @@ static inline u64 irq_time_read(int cpu)
 #endif /* CONFIG_IRQ_TIME_ACCOUNTING */
 
 #ifdef CONFIG_CPU_FREQ
-DECLARE_PER_CPU(struct update_util_data *, cpufreq_update_util_data);
+DECLARE_PER_CPU(struct update_util_data __rcu *, cpufreq_update_util_data);
 
 /**
  * cpufreq_update_util - Take a note about CPU utilization changes.
diff --git a/kernel/sched/topology.c b/kernel/sched/topology.c
index ab7f371a3a17..f53f89df837d 100644
--- a/kernel/sched/topology.c
+++ b/kernel/sched/topology.c
@@ -615,13 +615,13 @@ static void destroy_sched_domains(struct sched_domain *sd)
  * the cpumask of the domain), this allows us to quickly tell if
  * two CPUs are in the same cache domain, see cpus_share_cache().
  */
-DEFINE_PER_CPU(struct sched_domain *, sd_llc);
+DEFINE_PER_CPU(struct sched_domain __rcu *, sd_llc);
 DEFINE_PER_CPU(int, sd_llc_size);
 DEFINE_PER_CPU(int, sd_llc_id);
-DEFINE_PER_CPU(struct sched_domain_shared *, sd_llc_shared);
-DEFINE_PER_CPU(struct sched_domain *, sd_numa);
-DEFINE_PER_CPU(struct sched_domain *, sd_asym_packing);
-DEFINE_PER_CPU(struct sched_domain *, sd_asym_cpucapacity);
+DEFINE_PER_CPU(struct sched_domain_shared __rcu *, sd_llc_shared);
+DEFINE_PER_CPU(struct sched_domain __rcu *, sd_numa);
+DEFINE_PER_CPU(struct sched_domain __rcu *, sd_asym_packing);
+DEFINE_PER_CPU(struct sched_domain __rcu *, sd_asym_cpucapacity);
 DEFINE_STATIC_KEY_FALSE(sched_asym_cpucapacity);
 
 static void update_top_cache_domain(int cpu)
@@ -1059,6 +1059,7 @@ static struct sched_group *get_group(int cpu, struct sd_data *sdd)
 	struct sched_domain *sd = *per_cpu_ptr(sdd->sd, cpu);
 	struct sched_domain *child = sd->child;
 	struct sched_group *sg;
+	bool already_visited;
 
 	if (child)
 		cpu = cpumask_first(sched_domain_span(child));
@@ -1066,9 +1067,14 @@ static struct sched_group *get_group(int cpu, struct sd_data *sdd)
 	sg = *per_cpu_ptr(sdd->sg, cpu);
 	sg->sgc = *per_cpu_ptr(sdd->sgc, cpu);
 
-	/* For claim_allocations: */
-	atomic_inc(&sg->ref);
-	atomic_inc(&sg->sgc->ref);
+	/* Increase refcounts for claim_allocations: */
+	already_visited = atomic_inc_return(&sg->ref) > 1;
+	/* sgc visits should follow a similar trend as sg */
+	WARN_ON(already_visited != (atomic_inc_return(&sg->sgc->ref) > 1));
+
+	/* If we have already visited that group, it's already initialized. */
+	if (already_visited)
+		return sg;
 
 	if (child) {
 		cpumask_copy(sched_group_span(sg), sched_domain_span(child));
@@ -1087,8 +1093,8 @@ static struct sched_group *get_group(int cpu, struct sd_data *sdd)
 
 /*
  * build_sched_groups will build a circular linked list of the groups
- * covered by the given span, and will set each group's ->cpumask correctly,
- * and ->cpu_capacity to 0.
+ * covered by the given span, will set each group's ->cpumask correctly,
+ * and will initialize their ->sgc.
  *
  * Assumes the sched_domain tree is fully constructed
  */
@@ -2075,9 +2081,8 @@ void free_sched_domains(cpumask_var_t doms[], unsigned int ndoms)
 }
 
 /*
- * Set up scheduler domains and groups. Callers must hold the hotplug lock.
- * For now this just excludes isolated CPUs, but could be used to
- * exclude other special cases in the future.
+ * Set up scheduler domains and groups.  For now this just excludes isolated
+ * CPUs, but could be used to exclude other special cases in the future.
  */
 int sched_init_domains(const struct cpumask *cpu_map)
 {
diff --git a/kernel/seccomp.c b/kernel/seccomp.c
index 503d02896c5d..a635ecba6fe2 100644
--- a/kernel/seccomp.c
+++ b/kernel/seccomp.c
@@ -149,7 +149,7 @@ static void populate_seccomp_data(struct seccomp_data *sd)
 
 	sd->nr = syscall_get_nr(task, regs);
 	sd->arch = syscall_get_arch();
-	syscall_get_arguments(task, regs, 0, 6, args);
+	syscall_get_arguments(task, regs, args);
 	sd->args[0] = args[0];
 	sd->args[1] = args[1];
 	sd->args[2] = args[2];
@@ -502,7 +502,10 @@ out:
  *
  * Caller must be holding current->sighand->siglock lock.
  *
- * Returns 0 on success, -ve on error.
+ * Returns 0 on success, -ve on error, or
+ *   - in TSYNC mode: the pid of a thread which was either not in the correct
+ *     seccomp mode or did not have an ancestral seccomp filter
+ *   - in NEW_LISTENER mode: the fd of the new listener
  */
 static long seccomp_attach_filter(unsigned int flags,
 				  struct seccomp_filter *filter)
@@ -1258,6 +1261,16 @@ static long seccomp_set_mode_filter(unsigned int flags,
 	if (flags & ~SECCOMP_FILTER_FLAG_MASK)
 		return -EINVAL;
 
+	/*
+	 * In the successful case, NEW_LISTENER returns the new listener fd.
+	 * But in the failure case, TSYNC returns the thread that died. If you
+	 * combine these two flags, there's no way to tell whether something
+	 * succeeded or failed. So, let's disallow this combination.
+	 */
+	if ((flags & SECCOMP_FILTER_FLAG_TSYNC) &&
+	    (flags & SECCOMP_FILTER_FLAG_NEW_LISTENER))
+		return -EINVAL;
+
 	/* Prepare the new filter before holding any locks. */
 	prepared = seccomp_prepare_user_filter(filter);
 	if (IS_ERR(prepared))
@@ -1304,7 +1317,7 @@ out:
 		mutex_unlock(&current->signal->cred_guard_mutex);
 out_put_fd:
 	if (flags & SECCOMP_FILTER_FLAG_NEW_LISTENER) {
-		if (ret < 0) {
+		if (ret) {
 			listener_f->private_data = NULL;
 			fput(listener_f);
 			put_unused_fd(listener);
diff --git a/kernel/signal.c b/kernel/signal.c
index b7953934aa99..227ba170298e 100644
--- a/kernel/signal.c
+++ b/kernel/signal.c
@@ -3581,7 +3581,7 @@ SYSCALL_DEFINE4(pidfd_send_signal, int, pidfd, int, sig,
 	if (flags)
 		return -EINVAL;
 
-	f = fdget_raw(pidfd);
+	f = fdget(pidfd);
 	if (!f.file)
 		return -EBADF;
 
@@ -3605,16 +3605,11 @@ SYSCALL_DEFINE4(pidfd_send_signal, int, pidfd, int, sig,
 		if (unlikely(sig != kinfo.si_signo))
 			goto err;
 
+		/* Only allow sending arbitrary signals to yourself. */
+		ret = -EPERM;
 		if ((task_pid(current) != pid) &&
-		    (kinfo.si_code >= 0 || kinfo.si_code == SI_TKILL)) {
-			/* Only allow sending arbitrary signals to yourself. */
-			ret = -EPERM;
-			if (kinfo.si_code != SI_USER)
-				goto err;
-
-			/* Turn this into a regular kill signal. */
-			prepare_kill_siginfo(sig, &kinfo);
-		}
+		    (kinfo.si_code >= 0 || kinfo.si_code == SI_TKILL))
+			goto err;
 	} else {
 		prepare_kill_siginfo(sig, &kinfo);
 	}
diff --git a/kernel/softirq.c b/kernel/softirq.c
index 10277429ed84..2c3382378d94 100644
--- a/kernel/softirq.c
+++ b/kernel/softirq.c
@@ -573,57 +573,6 @@ void tasklet_kill(struct tasklet_struct *t)
 }
 EXPORT_SYMBOL(tasklet_kill);
 
-/*
- * tasklet_hrtimer
- */
-
-/*
- * The trampoline is called when the hrtimer expires. It schedules a tasklet
- * to run __tasklet_hrtimer_trampoline() which in turn will call the intended
- * hrtimer callback, but from softirq context.
- */
-static enum hrtimer_restart __hrtimer_tasklet_trampoline(struct hrtimer *timer)
-{
-	struct tasklet_hrtimer *ttimer =
-		container_of(timer, struct tasklet_hrtimer, timer);
-
-	tasklet_hi_schedule(&ttimer->tasklet);
-	return HRTIMER_NORESTART;
-}
-
-/*
- * Helper function which calls the hrtimer callback from
- * tasklet/softirq context
- */
-static void __tasklet_hrtimer_trampoline(unsigned long data)
-{
-	struct tasklet_hrtimer *ttimer = (void *)data;
-	enum hrtimer_restart restart;
-
-	restart = ttimer->function(&ttimer->timer);
-	if (restart != HRTIMER_NORESTART)
-		hrtimer_restart(&ttimer->timer);
-}
-
-/**
- * tasklet_hrtimer_init - Init a tasklet/hrtimer combo for softirq callbacks
- * @ttimer:	 tasklet_hrtimer which is initialized
- * @function:	 hrtimer callback function which gets called from softirq context
- * @which_clock: clock id (CLOCK_MONOTONIC/CLOCK_REALTIME)
- * @mode:	 hrtimer mode (HRTIMER_MODE_ABS/HRTIMER_MODE_REL)
- */
-void tasklet_hrtimer_init(struct tasklet_hrtimer *ttimer,
-			  enum hrtimer_restart (*function)(struct hrtimer *),
-			  clockid_t which_clock, enum hrtimer_mode mode)
-{
-	hrtimer_init(&ttimer->timer, which_clock, mode);
-	ttimer->timer.function = __hrtimer_tasklet_trampoline;
-	tasklet_init(&ttimer->tasklet, __tasklet_hrtimer_trampoline,
-		     (unsigned long)ttimer);
-	ttimer->function = function;
-}
-EXPORT_SYMBOL_GPL(tasklet_hrtimer_init);
-
 void __init softirq_init(void)
 {
 	int cpu;
diff --git a/kernel/stacktrace.c b/kernel/stacktrace.c
index f8edee9c792d..27bafc1e271e 100644
--- a/kernel/stacktrace.c
+++ b/kernel/stacktrace.c
@@ -5,41 +5,56 @@
  *
  *  Copyright (C) 2006 Red Hat, Inc., Ingo Molnar <mingo@redhat.com>
  */
+#include <linux/sched/task_stack.h>
+#include <linux/sched/debug.h>
 #include <linux/sched.h>
 #include <linux/kernel.h>
 #include <linux/export.h>
 #include <linux/kallsyms.h>
 #include <linux/stacktrace.h>
 
-void print_stack_trace(struct stack_trace *trace, int spaces)
+/**
+ * stack_trace_print - Print the entries in the stack trace
+ * @entries:	Pointer to storage array
+ * @nr_entries:	Number of entries in the storage array
+ * @spaces:	Number of leading spaces to print
+ */
+void stack_trace_print(unsigned long *entries, unsigned int nr_entries,
+		       int spaces)
 {
-	int i;
+	unsigned int i;
 
-	if (WARN_ON(!trace->entries))
+	if (WARN_ON(!entries))
 		return;
 
-	for (i = 0; i < trace->nr_entries; i++)
-		printk("%*c%pS\n", 1 + spaces, ' ', (void *)trace->entries[i]);
+	for (i = 0; i < nr_entries; i++)
+		printk("%*c%pS\n", 1 + spaces, ' ', (void *)entries[i]);
 }
-EXPORT_SYMBOL_GPL(print_stack_trace);
+EXPORT_SYMBOL_GPL(stack_trace_print);
 
-int snprint_stack_trace(char *buf, size_t size,
-			struct stack_trace *trace, int spaces)
+/**
+ * stack_trace_snprint - Print the entries in the stack trace into a buffer
+ * @buf:	Pointer to the print buffer
+ * @size:	Size of the print buffer
+ * @entries:	Pointer to storage array
+ * @nr_entries:	Number of entries in the storage array
+ * @spaces:	Number of leading spaces to print
+ *
+ * Return: Number of bytes printed.
+ */
+int stack_trace_snprint(char *buf, size_t size, unsigned long *entries,
+			unsigned int nr_entries, int spaces)
 {
-	int i;
-	int generated;
-	int total = 0;
+	unsigned int generated, i, total = 0;
 
-	if (WARN_ON(!trace->entries))
+	if (WARN_ON(!entries))
 		return 0;
 
-	for (i = 0; i < trace->nr_entries; i++) {
+	for (i = 0; i < nr_entries && size; i++) {
 		generated = snprintf(buf, size, "%*c%pS\n", 1 + spaces, ' ',
-				     (void *)trace->entries[i]);
+				     (void *)entries[i]);
 
 		total += generated;
-
-		/* Assume that generated isn't a negative number */
 		if (generated >= size) {
 			buf += size;
 			size = 0;
@@ -51,7 +66,176 @@ int snprint_stack_trace(char *buf, size_t size,
 
 	return total;
 }
-EXPORT_SYMBOL_GPL(snprint_stack_trace);
+EXPORT_SYMBOL_GPL(stack_trace_snprint);
+
+#ifdef CONFIG_ARCH_STACKWALK
+
+struct stacktrace_cookie {
+	unsigned long	*store;
+	unsigned int	size;
+	unsigned int	skip;
+	unsigned int	len;
+};
+
+static bool stack_trace_consume_entry(void *cookie, unsigned long addr,
+				      bool reliable)
+{
+	struct stacktrace_cookie *c = cookie;
+
+	if (c->len >= c->size)
+		return false;
+
+	if (c->skip > 0) {
+		c->skip--;
+		return true;
+	}
+	c->store[c->len++] = addr;
+	return c->len < c->size;
+}
+
+static bool stack_trace_consume_entry_nosched(void *cookie, unsigned long addr,
+					      bool reliable)
+{
+	if (in_sched_functions(addr))
+		return true;
+	return stack_trace_consume_entry(cookie, addr, reliable);
+}
+
+/**
+ * stack_trace_save - Save a stack trace into a storage array
+ * @store:	Pointer to storage array
+ * @size:	Size of the storage array
+ * @skipnr:	Number of entries to skip at the start of the stack trace
+ *
+ * Return: Number of trace entries stored.
+ */
+unsigned int stack_trace_save(unsigned long *store, unsigned int size,
+			      unsigned int skipnr)
+{
+	stack_trace_consume_fn consume_entry = stack_trace_consume_entry;
+	struct stacktrace_cookie c = {
+		.store	= store,
+		.size	= size,
+		.skip	= skipnr + 1,
+	};
+
+	arch_stack_walk(consume_entry, &c, current, NULL);
+	return c.len;
+}
+EXPORT_SYMBOL_GPL(stack_trace_save);
+
+/**
+ * stack_trace_save_tsk - Save a task stack trace into a storage array
+ * @task:	The task to examine
+ * @store:	Pointer to storage array
+ * @size:	Size of the storage array
+ * @skipnr:	Number of entries to skip at the start of the stack trace
+ *
+ * Return: Number of trace entries stored.
+ */
+unsigned int stack_trace_save_tsk(struct task_struct *tsk, unsigned long *store,
+				  unsigned int size, unsigned int skipnr)
+{
+	stack_trace_consume_fn consume_entry = stack_trace_consume_entry_nosched;
+	struct stacktrace_cookie c = {
+		.store	= store,
+		.size	= size,
+		.skip	= skipnr + 1,
+	};
+
+	if (!try_get_task_stack(tsk))
+		return 0;
+
+	arch_stack_walk(consume_entry, &c, tsk, NULL);
+	put_task_stack(tsk);
+	return c.len;
+}
+
+/**
+ * stack_trace_save_regs - Save a stack trace based on pt_regs into a storage array
+ * @regs:	Pointer to pt_regs to examine
+ * @store:	Pointer to storage array
+ * @size:	Size of the storage array
+ * @skipnr:	Number of entries to skip at the start of the stack trace
+ *
+ * Return: Number of trace entries stored.
+ */
+unsigned int stack_trace_save_regs(struct pt_regs *regs, unsigned long *store,
+				   unsigned int size, unsigned int skipnr)
+{
+	stack_trace_consume_fn consume_entry = stack_trace_consume_entry;
+	struct stacktrace_cookie c = {
+		.store	= store,
+		.size	= size,
+		.skip	= skipnr,
+	};
+
+	arch_stack_walk(consume_entry, &c, current, regs);
+	return c.len;
+}
+
+#ifdef CONFIG_HAVE_RELIABLE_STACKTRACE
+/**
+ * stack_trace_save_tsk_reliable - Save task stack with verification
+ * @tsk:	Pointer to the task to examine
+ * @store:	Pointer to storage array
+ * @size:	Size of the storage array
+ *
+ * Return:	An error if it detects any unreliable features of the
+ *		stack. Otherwise it guarantees that the stack trace is
+ *		reliable and returns the number of entries stored.
+ *
+ * If the task is not 'current', the caller *must* ensure the task is inactive.
+ */
+int stack_trace_save_tsk_reliable(struct task_struct *tsk, unsigned long *store,
+				  unsigned int size)
+{
+	stack_trace_consume_fn consume_entry = stack_trace_consume_entry;
+	struct stacktrace_cookie c = {
+		.store	= store,
+		.size	= size,
+	};
+	int ret;
+
+	/*
+	 * If the task doesn't have a stack (e.g., a zombie), the stack is
+	 * "reliably" empty.
+	 */
+	if (!try_get_task_stack(tsk))
+		return 0;
+
+	ret = arch_stack_walk_reliable(consume_entry, &c, tsk);
+	put_task_stack(tsk);
+	return ret;
+}
+#endif
+
+#ifdef CONFIG_USER_STACKTRACE_SUPPORT
+/**
+ * stack_trace_save_user - Save a user space stack trace into a storage array
+ * @store:	Pointer to storage array
+ * @size:	Size of the storage array
+ *
+ * Return: Number of trace entries stored.
+ */
+unsigned int stack_trace_save_user(unsigned long *store, unsigned int size)
+{
+	stack_trace_consume_fn consume_entry = stack_trace_consume_entry;
+	struct stacktrace_cookie c = {
+		.store	= store,
+		.size	= size,
+	};
+
+	/* Trace user stack if not a kernel thread */
+	if (!current->mm)
+		return 0;
+
+	arch_stack_walk_user(consume_entry, &c, task_pt_regs(current));
+	return c.len;
+}
+#endif
+
+#else /* CONFIG_ARCH_STACKWALK */
 
 /*
  * Architectures that do not implement save_stack_trace_*()
@@ -77,3 +261,118 @@ save_stack_trace_tsk_reliable(struct task_struct *tsk,
 	WARN_ONCE(1, KERN_INFO "save_stack_tsk_reliable() not implemented yet.\n");
 	return -ENOSYS;
 }
+
+/**
+ * stack_trace_save - Save a stack trace into a storage array
+ * @store:	Pointer to storage array
+ * @size:	Size of the storage array
+ * @skipnr:	Number of entries to skip at the start of the stack trace
+ *
+ * Return: Number of trace entries stored
+ */
+unsigned int stack_trace_save(unsigned long *store, unsigned int size,
+			      unsigned int skipnr)
+{
+	struct stack_trace trace = {
+		.entries	= store,
+		.max_entries	= size,
+		.skip		= skipnr + 1,
+	};
+
+	save_stack_trace(&trace);
+	return trace.nr_entries;
+}
+EXPORT_SYMBOL_GPL(stack_trace_save);
+
+/**
+ * stack_trace_save_tsk - Save a task stack trace into a storage array
+ * @task:	The task to examine
+ * @store:	Pointer to storage array
+ * @size:	Size of the storage array
+ * @skipnr:	Number of entries to skip at the start of the stack trace
+ *
+ * Return: Number of trace entries stored
+ */
+unsigned int stack_trace_save_tsk(struct task_struct *task,
+				  unsigned long *store, unsigned int size,
+				  unsigned int skipnr)
+{
+	struct stack_trace trace = {
+		.entries	= store,
+		.max_entries	= size,
+		.skip		= skipnr + 1,
+	};
+
+	save_stack_trace_tsk(task, &trace);
+	return trace.nr_entries;
+}
+
+/**
+ * stack_trace_save_regs - Save a stack trace based on pt_regs into a storage array
+ * @regs:	Pointer to pt_regs to examine
+ * @store:	Pointer to storage array
+ * @size:	Size of the storage array
+ * @skipnr:	Number of entries to skip at the start of the stack trace
+ *
+ * Return: Number of trace entries stored
+ */
+unsigned int stack_trace_save_regs(struct pt_regs *regs, unsigned long *store,
+				   unsigned int size, unsigned int skipnr)
+{
+	struct stack_trace trace = {
+		.entries	= store,
+		.max_entries	= size,
+		.skip		= skipnr,
+	};
+
+	save_stack_trace_regs(regs, &trace);
+	return trace.nr_entries;
+}
+
+#ifdef CONFIG_HAVE_RELIABLE_STACKTRACE
+/**
+ * stack_trace_save_tsk_reliable - Save task stack with verification
+ * @tsk:	Pointer to the task to examine
+ * @store:	Pointer to storage array
+ * @size:	Size of the storage array
+ *
+ * Return:	An error if it detects any unreliable features of the
+ *		stack. Otherwise it guarantees that the stack trace is
+ *		reliable and returns the number of entries stored.
+ *
+ * If the task is not 'current', the caller *must* ensure the task is inactive.
+ */
+int stack_trace_save_tsk_reliable(struct task_struct *tsk, unsigned long *store,
+				  unsigned int size)
+{
+	struct stack_trace trace = {
+		.entries	= store,
+		.max_entries	= size,
+	};
+	int ret = save_stack_trace_tsk_reliable(tsk, &trace);
+
+	return ret ? ret : trace.nr_entries;
+}
+#endif
+
+#ifdef CONFIG_USER_STACKTRACE_SUPPORT
+/**
+ * stack_trace_save_user - Save a user space stack trace into a storage array
+ * @store:	Pointer to storage array
+ * @size:	Size of the storage array
+ *
+ * Return: Number of trace entries stored
+ */
+unsigned int stack_trace_save_user(unsigned long *store, unsigned int size)
+{
+	struct stack_trace trace = {
+		.entries	= store,
+		.max_entries	= size,
+	};
+
+	save_stack_trace_user(&trace);
+	return trace.nr_entries;
+}
+#endif /* CONFIG_USER_STACKTRACE_SUPPORT */
+
+#endif /* !CONFIG_ARCH_STACKWALK */
diff --git a/kernel/sysctl.c b/kernel/sysctl.c
index e5da394d1ca3..c9ec050bcf46 100644
--- a/kernel/sysctl.c
+++ b/kernel/sysctl.c
@@ -128,6 +128,7 @@ static int zero;
 static int __maybe_unused one = 1;
 static int __maybe_unused two = 2;
 static int __maybe_unused four = 4;
+static unsigned long zero_ul;
 static unsigned long one_ul = 1;
 static unsigned long long_max = LONG_MAX;
 static int one_hundred = 100;
@@ -1750,7 +1751,7 @@ static struct ctl_table fs_table[] = {
 		.maxlen		= sizeof(files_stat.max_files),
 		.mode		= 0644,
 		.proc_handler	= proc_doulongvec_minmax,
-		.extra1		= &zero,
+		.extra1		= &zero_ul,
 		.extra2		= &long_max,
 	},
 	{
diff --git a/kernel/time/alarmtimer.c b/kernel/time/alarmtimer.c
index 2c97e8c2d29f..0519a8805aab 100644
--- a/kernel/time/alarmtimer.c
+++ b/kernel/time/alarmtimer.c
@@ -594,7 +594,7 @@ static ktime_t alarm_timer_remaining(struct k_itimer *timr, ktime_t now)
 {
 	struct alarm *alarm = &timr->it.alarm.alarmtimer;
 
-	return ktime_sub(now, alarm->node.expires);
+	return ktime_sub(alarm->node.expires, now);
 }
 
 /**
diff --git a/kernel/time/clockevents.c b/kernel/time/clockevents.c
index 5e77662dd2d9..f5490222e134 100644
--- a/kernel/time/clockevents.c
+++ b/kernel/time/clockevents.c
@@ -611,6 +611,22 @@ void clockevents_resume(void)
 }
 
 #ifdef CONFIG_HOTPLUG_CPU
+
+# ifdef CONFIG_GENERIC_CLOCKEVENTS_BROADCAST
+/**
+ * tick_offline_cpu - Take CPU out of the broadcast mechanism
+ * @cpu:	The outgoing CPU
+ *
+ * Called on the outgoing CPU after it took itself offline.
+ */
+void tick_offline_cpu(unsigned int cpu)
+{
+	raw_spin_lock(&clockevents_lock);
+	tick_broadcast_offline(cpu);
+	raw_spin_unlock(&clockevents_lock);
+}
+# endif
+
 /**
  * tick_cleanup_dead_cpu - Cleanup the tick and clockevents of a dead cpu
  */
@@ -621,8 +637,6 @@ void tick_cleanup_dead_cpu(int cpu)
 
 	raw_spin_lock_irqsave(&clockevents_lock, flags);
 
-	tick_shutdown_broadcast_oneshot(cpu);
-	tick_shutdown_broadcast(cpu);
 	tick_shutdown(cpu);
 	/*
 	 * Unregister the clock event devices which were
diff --git a/kernel/time/jiffies.c b/kernel/time/jiffies.c
index ac9c03dd6c7d..d23b434c2ca7 100644
--- a/kernel/time/jiffies.c
+++ b/kernel/time/jiffies.c
@@ -63,7 +63,7 @@ __cacheline_aligned_in_smp DEFINE_SEQLOCK(jiffies_lock);
 #if (BITS_PER_LONG < 64)
 u64 get_jiffies_64(void)
 {
-	unsigned long seq;
+	unsigned int seq;
 	u64 ret;
 
 	do {
diff --git a/kernel/time/sched_clock.c b/kernel/time/sched_clock.c
index 094b82ca95e5..968e4b07918e 100644
--- a/kernel/time/sched_clock.c
+++ b/kernel/time/sched_clock.c
@@ -94,7 +94,7 @@ static inline u64 notrace cyc_to_ns(u64 cyc, u32 mult, u32 shift)
 unsigned long long notrace sched_clock(void)
 {
 	u64 cyc, res;
-	unsigned long seq;
+	unsigned int seq;
 	struct clock_read_data *rd;
 
 	do {
@@ -267,12 +267,12 @@ void __init generic_sched_clock_init(void)
  */
 static u64 notrace suspended_sched_clock_read(void)
 {
-	unsigned long seq = raw_read_seqcount(&cd.seq);
+	unsigned int seq = raw_read_seqcount(&cd.seq);
 
 	return cd.read_data[seq & 1].epoch_cyc;
 }
 
-static int sched_clock_suspend(void)
+int sched_clock_suspend(void)
 {
 	struct clock_read_data *rd = &cd.read_data[0];
 
@@ -283,7 +283,7 @@ static int sched_clock_suspend(void)
 	return 0;
 }
 
-static void sched_clock_resume(void)
+void sched_clock_resume(void)
 {
 	struct clock_read_data *rd = &cd.read_data[0];
 
diff --git a/kernel/time/tick-broadcast.c b/kernel/time/tick-broadcast.c
index ee834d4fb814..e51778c312f1 100644
--- a/kernel/time/tick-broadcast.c
+++ b/kernel/time/tick-broadcast.c
@@ -36,10 +36,16 @@ static __cacheline_aligned_in_smp DEFINE_RAW_SPINLOCK(tick_broadcast_lock);
 static void tick_broadcast_setup_oneshot(struct clock_event_device *bc);
 static void tick_broadcast_clear_oneshot(int cpu);
 static void tick_resume_broadcast_oneshot(struct clock_event_device *bc);
+# ifdef CONFIG_HOTPLUG_CPU
+static void tick_broadcast_oneshot_offline(unsigned int cpu);
+# endif
 #else
 static inline void tick_broadcast_setup_oneshot(struct clock_event_device *bc) { BUG(); }
 static inline void tick_broadcast_clear_oneshot(int cpu) { }
 static inline void tick_resume_broadcast_oneshot(struct clock_event_device *bc) { }
+# ifdef CONFIG_HOTPLUG_CPU
+static inline void tick_broadcast_oneshot_offline(unsigned int cpu) { }
+# endif
 #endif
 
 /*
@@ -433,27 +439,29 @@ void tick_set_periodic_handler(struct clock_event_device *dev, int broadcast)
 }
 
 #ifdef CONFIG_HOTPLUG_CPU
-/*
- * Remove a CPU from broadcasting
- */
-void tick_shutdown_broadcast(unsigned int cpu)
+static void tick_shutdown_broadcast(void)
 {
-	struct clock_event_device *bc;
-	unsigned long flags;
-
-	raw_spin_lock_irqsave(&tick_broadcast_lock, flags);
-
-	bc = tick_broadcast_device.evtdev;
-	cpumask_clear_cpu(cpu, tick_broadcast_mask);
-	cpumask_clear_cpu(cpu, tick_broadcast_on);
+	struct clock_event_device *bc = tick_broadcast_device.evtdev;
 
 	if (tick_broadcast_device.mode == TICKDEV_MODE_PERIODIC) {
 		if (bc && cpumask_empty(tick_broadcast_mask))
 			clockevents_shutdown(bc);
 	}
+}
 
-	raw_spin_unlock_irqrestore(&tick_broadcast_lock, flags);
+/*
+ * Remove a CPU from broadcasting
+ */
+void tick_broadcast_offline(unsigned int cpu)
+{
+	raw_spin_lock(&tick_broadcast_lock);
+	cpumask_clear_cpu(cpu, tick_broadcast_mask);
+	cpumask_clear_cpu(cpu, tick_broadcast_on);
+	tick_broadcast_oneshot_offline(cpu);
+	tick_shutdown_broadcast();
+	raw_spin_unlock(&tick_broadcast_lock);
 }
+
 #endif
 
 void tick_suspend_broadcast(void)
@@ -801,13 +809,13 @@ int __tick_broadcast_oneshot_control(enum tick_broadcast_state state)
 			 * either the CPU handling the broadcast
 			 * interrupt or we got woken by something else.
 			 *
-			 * We are not longer in the broadcast mask, so
+			 * We are no longer in the broadcast mask, so
 			 * if the cpu local expiry time is already
 			 * reached, we would reprogram the cpu local
 			 * timer with an already expired event.
 			 *
 			 * This can lead to a ping-pong when we return
-			 * to idle and therefor rearm the broadcast
+			 * to idle and therefore rearm the broadcast
 			 * timer before the cpu local timer was able
 			 * to fire. This happens because the forced
 			 * reprogramming makes sure that the event
@@ -950,14 +958,10 @@ void hotplug_cpu__broadcast_tick_pull(int deadcpu)
 }
 
 /*
- * Remove a dead CPU from broadcasting
+ * Remove a dying CPU from broadcasting
  */
-void tick_shutdown_broadcast_oneshot(unsigned int cpu)
+static void tick_broadcast_oneshot_offline(unsigned int cpu)
 {
-	unsigned long flags;
-
-	raw_spin_lock_irqsave(&tick_broadcast_lock, flags);
-
 	/*
 	 * Clear the broadcast masks for the dead cpu, but do not stop
 	 * the broadcast device!
@@ -965,8 +969,6 @@ void tick_shutdown_broadcast_oneshot(unsigned int cpu)
 	cpumask_clear_cpu(cpu, tick_broadcast_oneshot_mask);
 	cpumask_clear_cpu(cpu, tick_broadcast_pending_mask);
 	cpumask_clear_cpu(cpu, tick_broadcast_force_mask);
-
-	raw_spin_unlock_irqrestore(&tick_broadcast_lock, flags);
 }
 #endif
 
diff --git a/kernel/time/tick-common.c b/kernel/time/tick-common.c
index 529143b4c8d2..59225b484e4e 100644
--- a/kernel/time/tick-common.c
+++ b/kernel/time/tick-common.c
@@ -46,6 +46,14 @@ ktime_t tick_period;
  *    procedure also covers cpu hotplug.
  */
 int tick_do_timer_cpu __read_mostly = TICK_DO_TIMER_BOOT;
+#ifdef CONFIG_NO_HZ_FULL
+/*
+ * tick_do_timer_boot_cpu indicates the boot CPU temporarily owns
+ * tick_do_timer_cpu and it should be taken over by an eligible secondary
+ * when one comes online.
+ */
+static int tick_do_timer_boot_cpu __read_mostly = -1;
+#endif
 
 /*
  * Debugging: see timer_list.c
@@ -149,7 +157,7 @@ void tick_setup_periodic(struct clock_event_device *dev, int broadcast)
 	    !tick_broadcast_oneshot_active()) {
 		clockevents_switch_state(dev, CLOCK_EVT_STATE_PERIODIC);
 	} else {
-		unsigned long seq;
+		unsigned int seq;
 		ktime_t next;
 
 		do {
@@ -167,6 +175,26 @@ void tick_setup_periodic(struct clock_event_device *dev, int broadcast)
 	}
 }
 
+#ifdef CONFIG_NO_HZ_FULL
+static void giveup_do_timer(void *info)
+{
+	int cpu = *(unsigned int *)info;
+
+	WARN_ON(tick_do_timer_cpu != smp_processor_id());
+
+	tick_do_timer_cpu = cpu;
+}
+
+static void tick_take_do_timer_from_boot(void)
+{
+	int cpu = smp_processor_id();
+	int from = tick_do_timer_boot_cpu;
+
+	if (from >= 0 && from != cpu)
+		smp_call_function_single(from, giveup_do_timer, &cpu, 1);
+}
+#endif
+
 /*
  * Setup the tick device
  */
@@ -186,12 +214,26 @@ static void tick_setup_device(struct tick_device *td,
 		 * this cpu:
 		 */
 		if (tick_do_timer_cpu == TICK_DO_TIMER_BOOT) {
-			if (!tick_nohz_full_cpu(cpu))
-				tick_do_timer_cpu = cpu;
-			else
-				tick_do_timer_cpu = TICK_DO_TIMER_NONE;
+			tick_do_timer_cpu = cpu;
+
 			tick_next_period = ktime_get();
 			tick_period = NSEC_PER_SEC / HZ;
+#ifdef CONFIG_NO_HZ_FULL
+			/*
+			 * The boot CPU may be nohz_full, in which case set
+			 * tick_do_timer_boot_cpu so the first housekeeping
+			 * secondary that comes up will take do_timer from
+			 * us.
+			 */
+			if (tick_nohz_full_cpu(cpu))
+				tick_do_timer_boot_cpu = cpu;
+
+		} else if (tick_do_timer_boot_cpu != -1 &&
+						!tick_nohz_full_cpu(cpu)) {
+			tick_take_do_timer_from_boot();
+			tick_do_timer_boot_cpu = -1;
+			WARN_ON(tick_do_timer_cpu != cpu);
+#endif
 		}
 
 		/*
@@ -487,6 +529,7 @@ void tick_freeze(void)
 		trace_suspend_resume(TPS("timekeeping_freeze"),
 				     smp_processor_id(), true);
 		system_state = SYSTEM_SUSPEND;
+		sched_clock_suspend();
 		timekeeping_suspend();
 	} else {
 		tick_suspend_local();
@@ -510,6 +553,7 @@ void tick_unfreeze(void)
 
 	if (tick_freeze_depth == num_online_cpus()) {
 		timekeeping_resume();
+		sched_clock_resume();
 		system_state = SYSTEM_RUNNING;
 		trace_suspend_resume(TPS("timekeeping_freeze"),
 				     smp_processor_id(), false);
diff --git a/kernel/time/tick-internal.h b/kernel/time/tick-internal.h
index e277284c2831..7b2496136729 100644
--- a/kernel/time/tick-internal.h
+++ b/kernel/time/tick-internal.h
@@ -64,7 +64,6 @@ extern ssize_t sysfs_get_uname(const char *buf, char *dst, size_t cnt);
 extern int tick_device_uses_broadcast(struct clock_event_device *dev, int cpu);
 extern void tick_install_broadcast_device(struct clock_event_device *dev);
 extern int tick_is_broadcast_device(struct clock_event_device *dev);
-extern void tick_shutdown_broadcast(unsigned int cpu);
 extern void tick_suspend_broadcast(void);
 extern void tick_resume_broadcast(void);
 extern bool tick_resume_check_broadcast(void);
@@ -78,7 +77,6 @@ static inline void tick_install_broadcast_device(struct clock_event_device *dev)
 static inline int tick_is_broadcast_device(struct clock_event_device *dev) { return 0; }
 static inline int tick_device_uses_broadcast(struct clock_event_device *dev, int cpu) { return 0; }
 static inline void tick_do_periodic_broadcast(struct clock_event_device *d) { }
-static inline void tick_shutdown_broadcast(unsigned int cpu) { }
 static inline void tick_suspend_broadcast(void) { }
 static inline void tick_resume_broadcast(void) { }
 static inline bool tick_resume_check_broadcast(void) { return false; }
@@ -128,19 +126,23 @@ static inline int tick_check_oneshot_change(int allow_nohz) { return 0; }
 /* Functions related to oneshot broadcasting */
 #if defined(CONFIG_GENERIC_CLOCKEVENTS_BROADCAST) && defined(CONFIG_TICK_ONESHOT)
 extern void tick_broadcast_switch_to_oneshot(void);
-extern void tick_shutdown_broadcast_oneshot(unsigned int cpu);
 extern int tick_broadcast_oneshot_active(void);
 extern void tick_check_oneshot_broadcast_this_cpu(void);
 bool tick_broadcast_oneshot_available(void);
 extern struct cpumask *tick_get_broadcast_oneshot_mask(void);
 #else /* !(BROADCAST && ONESHOT): */
 static inline void tick_broadcast_switch_to_oneshot(void) { }
-static inline void tick_shutdown_broadcast_oneshot(unsigned int cpu) { }
 static inline int tick_broadcast_oneshot_active(void) { return 0; }
 static inline void tick_check_oneshot_broadcast_this_cpu(void) { }
 static inline bool tick_broadcast_oneshot_available(void) { return tick_oneshot_possible(); }
 #endif /* !(BROADCAST && ONESHOT) */
 
+#if defined(CONFIG_GENERIC_CLOCKEVENTS_BROADCAST) && defined(CONFIG_HOTPLUG_CPU)
+extern void tick_broadcast_offline(unsigned int cpu);
+#else
+static inline void tick_broadcast_offline(unsigned int cpu) { }
+#endif
+
 /* NO_HZ_FULL internal */
 #ifdef CONFIG_NO_HZ_FULL
 extern void tick_nohz_init(void);
diff --git a/kernel/time/tick-sched.c b/kernel/time/tick-sched.c
index 6fa52cd6df0b..f4ee1a3428ae 100644
--- a/kernel/time/tick-sched.c
+++ b/kernel/time/tick-sched.c
@@ -121,10 +121,16 @@ static void tick_sched_do_timer(struct tick_sched *ts, ktime_t now)
 	 * into a long sleep. If two CPUs happen to assign themselves to
 	 * this duty, then the jiffies update is still serialized by
 	 * jiffies_lock.
+	 *
+	 * If nohz_full is enabled, this should not happen because the
+	 * tick_do_timer_cpu never relinquishes.
 	 */
-	if (unlikely(tick_do_timer_cpu == TICK_DO_TIMER_NONE)
-	    && !tick_nohz_full_cpu(cpu))
+	if (unlikely(tick_do_timer_cpu == TICK_DO_TIMER_NONE)) {
+#ifdef CONFIG_NO_HZ_FULL
+		WARN_ON(tick_nohz_full_running);
+#endif
 		tick_do_timer_cpu = cpu;
+	}
 #endif
 
 	/* Check, if the jiffies need an update */
@@ -395,8 +401,8 @@ void __init tick_nohz_full_setup(cpumask_var_t cpumask)
 static int tick_nohz_cpu_down(unsigned int cpu)
 {
 	/*
-	 * The boot CPU handles housekeeping duty (unbound timers,
-	 * workqueues, timekeeping, ...) on behalf of full dynticks
+	 * The tick_do_timer_cpu CPU handles housekeeping duty (unbound
+	 * timers, workqueues, timekeeping, ...) on behalf of full dynticks
 	 * CPUs. It must remain online when nohz full is enabled.
 	 */
 	if (tick_nohz_full_running && tick_do_timer_cpu == cpu)
@@ -423,12 +429,15 @@ void __init tick_nohz_init(void)
 		return;
 	}
 
-	cpu = smp_processor_id();
+	if (IS_ENABLED(CONFIG_PM_SLEEP_SMP) &&
+			!IS_ENABLED(CONFIG_PM_SLEEP_SMP_NONZERO_CPU)) {
+		cpu = smp_processor_id();
 
-	if (cpumask_test_cpu(cpu, tick_nohz_full_mask)) {
-		pr_warn("NO_HZ: Clearing %d from nohz_full range for timekeeping\n",
-			cpu);
-		cpumask_clear_cpu(cpu, tick_nohz_full_mask);
+		if (cpumask_test_cpu(cpu, tick_nohz_full_mask)) {
+			pr_warn("NO_HZ: Clearing %d from nohz_full range "
+				"for timekeeping\n", cpu);
+			cpumask_clear_cpu(cpu, tick_nohz_full_mask);
+		}
 	}
 
 	for_each_cpu(cpu, tick_nohz_full_mask)
@@ -645,7 +654,8 @@ static inline bool local_timer_softirq_pending(void)
 static ktime_t tick_nohz_next_event(struct tick_sched *ts, int cpu)
 {
 	u64 basemono, next_tick, next_tmr, next_rcu, delta, expires;
-	unsigned long seq, basejiff;
+	unsigned long basejiff;
+	unsigned int seq;
 
 	/* Read jiffies and the time when jiffies were updated last */
 	do {
@@ -904,8 +914,13 @@ static bool can_stop_idle_tick(int cpu, struct tick_sched *ts)
 		/*
 		 * Boot safety: make sure the timekeeping duty has been
 		 * assigned before entering dyntick-idle mode,
+		 * tick_do_timer_cpu is TICK_DO_TIMER_BOOT
 		 */
-		if (tick_do_timer_cpu == TICK_DO_TIMER_NONE)
+		if (unlikely(tick_do_timer_cpu == TICK_DO_TIMER_BOOT))
+			return false;
+
+		/* Should not happen for nohz-full */
+		if (WARN_ON_ONCE(tick_do_timer_cpu == TICK_DO_TIMER_NONE))
 			return false;
 	}
 
@@ -1023,6 +1038,18 @@ bool tick_nohz_idle_got_tick(void)
 }
 
 /**
+ * tick_nohz_get_next_hrtimer - return the next expiration time for the hrtimer
+ * or the tick, whatever that expires first. Note that, if the tick has been
+ * stopped, it returns the next hrtimer.
+ *
+ * Called from power state control code with interrupts disabled
+ */
+ktime_t tick_nohz_get_next_hrtimer(void)
+{
+	return __this_cpu_read(tick_cpu_device.evtdev)->next_event;
+}
+
+/**
  * tick_nohz_get_sleep_length - return the expected length of the current sleep
  * @delta_next: duration until the next event if the tick cannot be stopped
  *
diff --git a/kernel/time/tick-sched.h b/kernel/time/tick-sched.h
index 6de959a854b2..4fb06527cf64 100644
--- a/kernel/time/tick-sched.h
+++ b/kernel/time/tick-sched.h
@@ -24,12 +24,19 @@ enum tick_nohz_mode {
  * struct tick_sched - sched tick emulation and no idle tick control/stats
  * @sched_timer:	hrtimer to schedule the periodic tick in high
  *			resolution mode
+ * @check_clocks:	Notification mechanism about clocksource changes
+ * @nohz_mode:		Mode - one state of tick_nohz_mode
+ * @inidle:		Indicator that the CPU is in the tick idle mode
+ * @tick_stopped:	Indicator that the idle tick has been stopped
+ * @idle_active:	Indicator that the CPU is actively in the tick idle mode;
+ *			it is resetted during irq handling phases.
+ * @do_timer_lst:	CPU was the last one doing do_timer before going idle
+ * @got_idle_tick:	Tick timer function has run with @inidle set
  * @last_tick:		Store the last tick expiry time when the tick
  *			timer is modified for nohz sleeps. This is necessary
  *			to resume the tick timer operation in the timeline
  *			when the CPU returns from nohz sleep.
  * @next_tick:		Next tick to be fired when in dynticks mode.
- * @tick_stopped:	Indicator that the idle tick has been stopped
  * @idle_jiffies:	jiffies at the entry to idle for idle time accounting
  * @idle_calls:		Total number of idle calls
  * @idle_sleeps:	Number of idle calls, where the sched tick was stopped
@@ -40,8 +47,8 @@ enum tick_nohz_mode {
  * @iowait_sleeptime:	Sum of the time slept in idle with sched tick stopped, with IO outstanding
  * @timer_expires:	Anticipated timer expiration time (in case sched tick is stopped)
  * @timer_expires_base:	Base time clock monotonic for @timer_expires
- * @do_timer_lst:	CPU was the last one doing do_timer before going idle
- * @got_idle_tick:	Tick timer function has run with @inidle set
+ * @next_timer:		Expiry time of next expiring timer for debugging purpose only
+ * @tick_dep_mask:	Tick dependency mask - is set, if someone needs the tick
  */
 struct tick_sched {
 	struct hrtimer			sched_timer;
diff --git a/kernel/time/time.c b/kernel/time/time.c
index c3f756f8534b..86656bbac232 100644
--- a/kernel/time/time.c
+++ b/kernel/time/time.c
@@ -171,7 +171,7 @@ int do_sys_settimeofday64(const struct timespec64 *tv, const struct timezone *tz
 	static int firsttime = 1;
 	int error = 0;
 
-	if (tv && !timespec64_valid(tv))
+	if (tv && !timespec64_valid_settod(tv))
 		return -EINVAL;
 
 	error = security_settime64(tv, tz);
diff --git a/kernel/time/timekeeping.c b/kernel/time/timekeeping.c
index f986e1918d12..5716e28bfa3c 100644
--- a/kernel/time/timekeeping.c
+++ b/kernel/time/timekeeping.c
@@ -720,7 +720,7 @@ static void timekeeping_forward_now(struct timekeeper *tk)
 void ktime_get_real_ts64(struct timespec64 *ts)
 {
 	struct timekeeper *tk = &tk_core.timekeeper;
-	unsigned long seq;
+	unsigned int seq;
 	u64 nsecs;
 
 	WARN_ON(timekeeping_suspended);
@@ -829,7 +829,7 @@ EXPORT_SYMBOL_GPL(ktime_get_coarse_with_offset);
 ktime_t ktime_mono_to_any(ktime_t tmono, enum tk_offsets offs)
 {
 	ktime_t *offset = offsets[offs];
-	unsigned long seq;
+	unsigned int seq;
 	ktime_t tconv;
 
 	do {
@@ -960,7 +960,7 @@ time64_t __ktime_get_real_seconds(void)
 void ktime_get_snapshot(struct system_time_snapshot *systime_snapshot)
 {
 	struct timekeeper *tk = &tk_core.timekeeper;
-	unsigned long seq;
+	unsigned int seq;
 	ktime_t base_raw;
 	ktime_t base_real;
 	u64 nsec_raw;
@@ -1122,7 +1122,7 @@ int get_device_system_crosststamp(int (*get_time_fn)
 	ktime_t base_real, base_raw;
 	u64 nsec_real, nsec_raw;
 	u8 cs_was_changed_seq;
-	unsigned long seq;
+	unsigned int seq;
 	bool do_interp;
 	int ret;
 
@@ -1221,7 +1221,7 @@ int do_settimeofday64(const struct timespec64 *ts)
 	unsigned long flags;
 	int ret = 0;
 
-	if (!timespec64_valid_strict(ts))
+	if (!timespec64_valid_settod(ts))
 		return -EINVAL;
 
 	raw_spin_lock_irqsave(&timekeeper_lock, flags);
@@ -1278,7 +1278,7 @@ static int timekeeping_inject_offset(const struct timespec64 *ts)
 	/* Make sure the proposed value is valid */
 	tmp = timespec64_add(tk_xtime(tk), *ts);
 	if (timespec64_compare(&tk->wall_to_monotonic, ts) > 0 ||
-	    !timespec64_valid_strict(&tmp)) {
+	    !timespec64_valid_settod(&tmp)) {
 		ret = -EINVAL;
 		goto error;
 	}
@@ -1409,7 +1409,7 @@ int timekeeping_notify(struct clocksource *clock)
 void ktime_get_raw_ts64(struct timespec64 *ts)
 {
 	struct timekeeper *tk = &tk_core.timekeeper;
-	unsigned long seq;
+	unsigned int seq;
 	u64 nsecs;
 
 	do {
@@ -1431,7 +1431,7 @@ EXPORT_SYMBOL(ktime_get_raw_ts64);
 int timekeeping_valid_for_hres(void)
 {
 	struct timekeeper *tk = &tk_core.timekeeper;
-	unsigned long seq;
+	unsigned int seq;
 	int ret;
 
 	do {
@@ -1450,7 +1450,7 @@ int timekeeping_valid_for_hres(void)
 u64 timekeeping_max_deferment(void)
 {
 	struct timekeeper *tk = &tk_core.timekeeper;
-	unsigned long seq;
+	unsigned int seq;
 	u64 ret;
 
 	do {
@@ -1527,7 +1527,7 @@ void __init timekeeping_init(void)
 	unsigned long flags;
 
 	read_persistent_wall_and_boot_offset(&wall_time, &boot_offset);
-	if (timespec64_valid_strict(&wall_time) &&
+	if (timespec64_valid_settod(&wall_time) &&
 	    timespec64_to_ns(&wall_time) > 0) {
 		persistent_clock_exists = true;
 	} else if (timespec64_to_ns(&wall_time) != 0) {
@@ -2150,7 +2150,7 @@ EXPORT_SYMBOL_GPL(getboottime64);
 void ktime_get_coarse_real_ts64(struct timespec64 *ts)
 {
 	struct timekeeper *tk = &tk_core.timekeeper;
-	unsigned long seq;
+	unsigned int seq;
 
 	do {
 		seq = read_seqcount_begin(&tk_core.seq);
@@ -2164,7 +2164,7 @@ void ktime_get_coarse_ts64(struct timespec64 *ts)
 {
 	struct timekeeper *tk = &tk_core.timekeeper;
 	struct timespec64 now, mono;
-	unsigned long seq;
+	unsigned int seq;
 
 	do {
 		seq = read_seqcount_begin(&tk_core.seq);
diff --git a/kernel/time/timekeeping.h b/kernel/time/timekeeping.h
index 7a9b4eb7a1d5..141ab3ab0354 100644
--- a/kernel/time/timekeeping.h
+++ b/kernel/time/timekeeping.h
@@ -14,6 +14,13 @@ extern u64 timekeeping_max_deferment(void);
 extern void timekeeping_warp_clock(void);
 extern int timekeeping_suspend(void);
 extern void timekeeping_resume(void);
+#ifdef CONFIG_GENERIC_SCHED_CLOCK
+extern int sched_clock_suspend(void);
+extern void sched_clock_resume(void);
+#else
+static inline int sched_clock_suspend(void) { return 0; }
+static inline void sched_clock_resume(void) { }
+#endif
 
 extern void do_timer(unsigned long ticks);
 extern void update_wall_time(void);
diff --git a/kernel/time/timer.c b/kernel/time/timer.c
index 2fce056f8a49..a9b1bbc2d88d 100644
--- a/kernel/time/timer.c
+++ b/kernel/time/timer.c
@@ -536,6 +536,8 @@ static void enqueue_timer(struct timer_base *base, struct timer_list *timer,
 	hlist_add_head(&timer->entry, base->vectors + idx);
 	__set_bit(idx, base->pending_map);
 	timer_set_idx(timer, idx);
+
+	trace_timer_start(timer, timer->expires, timer->flags);
 }
 
 static void
@@ -757,13 +759,6 @@ static inline void debug_init(struct timer_list *timer)
 	trace_timer_init(timer);
 }
 
-static inline void
-debug_activate(struct timer_list *timer, unsigned long expires)
-{
-	debug_timer_activate(timer);
-	trace_timer_start(timer, expires, timer->flags);
-}
-
 static inline void debug_deactivate(struct timer_list *timer)
 {
 	debug_timer_deactivate(timer);
@@ -1037,7 +1032,7 @@ __mod_timer(struct timer_list *timer, unsigned long expires, unsigned int option
 		}
 	}
 
-	debug_activate(timer, expires);
+	debug_timer_activate(timer);
 
 	timer->expires = expires;
 	/*
@@ -1171,7 +1166,7 @@ void add_timer_on(struct timer_list *timer, int cpu)
 	}
 	forward_timer_base(base);
 
-	debug_activate(timer, timer->expires);
+	debug_timer_activate(timer);
 	internal_add_timer(base, timer);
 	raw_spin_unlock_irqrestore(&base->lock, flags);
 }
@@ -1298,7 +1293,9 @@ int del_timer_sync(struct timer_list *timer)
 EXPORT_SYMBOL(del_timer_sync);
 #endif
 
-static void call_timer_fn(struct timer_list *timer, void (*fn)(struct timer_list *))
+static void call_timer_fn(struct timer_list *timer,
+			  void (*fn)(struct timer_list *),
+			  unsigned long baseclk)
 {
 	int count = preempt_count();
 
@@ -1321,7 +1318,7 @@ static void call_timer_fn(struct timer_list *timer, void (*fn)(struct timer_list
 	 */
 	lock_map_acquire(&lockdep_map);
 
-	trace_timer_expire_entry(timer);
+	trace_timer_expire_entry(timer, baseclk);
 	fn(timer);
 	trace_timer_expire_exit(timer);
 
@@ -1342,6 +1339,13 @@ static void call_timer_fn(struct timer_list *timer, void (*fn)(struct timer_list
 
 static void expire_timers(struct timer_base *base, struct hlist_head *head)
 {
+	/*
+	 * This value is required only for tracing. base->clk was
+	 * incremented directly before expire_timers was called. But expiry
+	 * is related to the old base->clk value.
+	 */
+	unsigned long baseclk = base->clk - 1;
+
 	while (!hlist_empty(head)) {
 		struct timer_list *timer;
 		void (*fn)(struct timer_list *);
@@ -1355,11 +1359,11 @@ static void expire_timers(struct timer_base *base, struct hlist_head *head)
 
 		if (timer->flags & TIMER_IRQSAFE) {
 			raw_spin_unlock(&base->lock);
-			call_timer_fn(timer, fn);
+			call_timer_fn(timer, fn, baseclk);
 			raw_spin_lock(&base->lock);
 		} else {
 			raw_spin_unlock_irq(&base->lock);
-			call_timer_fn(timer, fn);
+			call_timer_fn(timer, fn, baseclk);
 			raw_spin_lock_irq(&base->lock);
 		}
 	}
diff --git a/kernel/torture.c b/kernel/torture.c
index 8faa1a9aaeb9..17b2be9bde12 100644
--- a/kernel/torture.c
+++ b/kernel/torture.c
@@ -88,6 +88,8 @@ bool torture_offline(int cpu, long *n_offl_attempts, long *n_offl_successes,
 
 	if (!cpu_online(cpu) || !cpu_is_hotpluggable(cpu))
 		return false;
+	if (num_online_cpus() <= 1)
+		return false;  /* Can't offline the last CPU. */
 
 	if (verbose > 1)
 		pr_alert("%s" TORTURE_FLAG
diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c
index d64c00afceb5..94b0e37d90ef 100644
--- a/kernel/trace/bpf_trace.c
+++ b/kernel/trace/bpf_trace.c
@@ -14,6 +14,8 @@
 #include <linux/syscalls.h>
 #include <linux/error-injection.h>
 
+#include <asm/tlb.h>
+
 #include "trace_probe.h"
 #include "trace.h"
 
@@ -163,6 +165,10 @@ BPF_CALL_3(bpf_probe_write_user, void *, unsafe_ptr, const void *, src,
 	 * access_ok() should prevent writing to non-user memory, but in
 	 * some situations (nommu, temporary switch, etc) access_ok() does
 	 * not provide enough validation, hence the check on KERNEL_DS.
+	 *
+	 * nmi_uaccess_okay() ensures the probe is not run in an interim
+	 * state, when the task or mm are switched. This is specifically
+	 * required to prevent the use of temporary mm.
 	 */
 
 	if (unlikely(in_interrupt() ||
@@ -170,6 +176,8 @@ BPF_CALL_3(bpf_probe_write_user, void *, unsafe_ptr, const void *, src,
 		return -EPERM;
 	if (unlikely(uaccess_kernel()))
 		return -EPERM;
+	if (unlikely(!nmi_uaccess_okay()))
+		return -EPERM;
 	if (!access_ok(unsafe_ptr, size))
 		return -EPERM;
 
diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c
index fa79323331b2..b920358dd8f7 100644
--- a/kernel/trace/ftrace.c
+++ b/kernel/trace/ftrace.c
@@ -33,6 +33,7 @@
 #include <linux/list.h>
 #include <linux/hash.h>
 #include <linux/rcupdate.h>
+#include <linux/kprobes.h>
 
 #include <trace/events/sched.h>
 
@@ -1992,7 +1993,7 @@ static void print_bug_type(void)
  * modifying the code. @failed should be one of either:
  * EFAULT - if the problem happens on reading the @ip address
  * EINVAL - if what is read at @ip is not what was expected
- * EPERM - if the problem happens on writting to the @ip address
+ * EPERM - if the problem happens on writing to the @ip address
  */
 void ftrace_bug(int failed, struct dyn_ftrace *rec)
 {
@@ -2391,7 +2392,7 @@ __ftrace_replace_code(struct dyn_ftrace *rec, int enable)
 		return ftrace_modify_call(rec, ftrace_old_addr, ftrace_addr);
 	}
 
-	return -1; /* unknow ftrace bug */
+	return -1; /* unknown ftrace bug */
 }
 
 void __weak ftrace_replace_code(int mod_flags)
@@ -3004,7 +3005,7 @@ ftrace_allocate_pages(unsigned long num_to_init)
 	int cnt;
 
 	if (!num_to_init)
-		return 0;
+		return NULL;
 
 	start_pg = pg = kzalloc(sizeof(*pg), GFP_KERNEL);
 	if (!pg)
@@ -4755,7 +4756,7 @@ static int
 ftrace_set_addr(struct ftrace_ops *ops, unsigned long ip, int remove,
 		int reset, int enable)
 {
-	return ftrace_set_hash(ops, 0, 0, ip, remove, reset, enable);
+	return ftrace_set_hash(ops, NULL, 0, ip, remove, reset, enable);
 }
 
 /**
@@ -5463,7 +5464,7 @@ void ftrace_create_filter_files(struct ftrace_ops *ops,
 
 /*
  * The name "destroy_filter_files" is really a misnomer. Although
- * in the future, it may actualy delete the files, but this is
+ * in the future, it may actually delete the files, but this is
  * really intended to make sure the ops passed in are disabled
  * and that when this function returns, the caller is free to
  * free the ops.
@@ -5786,7 +5787,7 @@ void ftrace_module_enable(struct module *mod)
 	/*
 	 * If the tracing is enabled, go ahead and enable the record.
 	 *
-	 * The reason not to enable the record immediatelly is the
+	 * The reason not to enable the record immediately is the
 	 * inherent check of ftrace_make_nop/ftrace_make_call for
 	 * correct previous instructions.  Making first the NOP
 	 * conversion puts the module to the correct state, thus
@@ -6246,7 +6247,7 @@ void ftrace_reset_array_ops(struct trace_array *tr)
 	tr->ops->func = ftrace_stub;
 }
 
-static inline void
+static nokprobe_inline void
 __ftrace_ops_list_func(unsigned long ip, unsigned long parent_ip,
 		       struct ftrace_ops *ignored, struct pt_regs *regs)
 {
@@ -6306,11 +6307,13 @@ static void ftrace_ops_list_func(unsigned long ip, unsigned long parent_ip,
 {
 	__ftrace_ops_list_func(ip, parent_ip, NULL, regs);
 }
+NOKPROBE_SYMBOL(ftrace_ops_list_func);
 #else
 static void ftrace_ops_no_ops(unsigned long ip, unsigned long parent_ip)
 {
 	__ftrace_ops_list_func(ip, parent_ip, NULL, NULL);
 }
+NOKPROBE_SYMBOL(ftrace_ops_no_ops);
 #endif
 
 /*
@@ -6337,6 +6340,7 @@ static void ftrace_ops_assist_func(unsigned long ip, unsigned long parent_ip,
 	preempt_enable_notrace();
 	trace_clear_recursion(bit);
 }
+NOKPROBE_SYMBOL(ftrace_ops_assist_func);
 
 /**
  * ftrace_ops_get_func - get the function a trampoline should call
diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c
index 41b6f96e5366..4ee8d8aa3d0f 100644
--- a/kernel/trace/ring_buffer.c
+++ b/kernel/trace/ring_buffer.c
@@ -762,7 +762,7 @@ u64 ring_buffer_time_stamp(struct ring_buffer *buffer, int cpu)
 
 	preempt_disable_notrace();
 	time = rb_time_stamp(buffer);
-	preempt_enable_no_resched_notrace();
+	preempt_enable_notrace();
 
 	return time;
 }
diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index 21153e64bf1c..ec439999f387 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -159,6 +159,8 @@ static union trace_eval_map_item *trace_eval_maps;
 #endif /* CONFIG_TRACE_EVAL_MAP_FILE */
 
 static int tracing_set_tracer(struct trace_array *tr, const char *buf);
+static void ftrace_trace_userstack(struct ring_buffer *buffer,
+				   unsigned long flags, int pc);
 
 #define MAX_TRACER_SIZE		100
 static char bootup_tracer_buf[MAX_TRACER_SIZE] __initdata;
@@ -496,8 +498,10 @@ int trace_pid_write(struct trace_pid_list *filtered_pids,
 	 * not modified.
 	 */
 	pid_list = kmalloc(sizeof(*pid_list), GFP_KERNEL);
-	if (!pid_list)
+	if (!pid_list) {
+		trace_parser_put(&parser);
 		return -ENOMEM;
+	}
 
 	pid_list->pid_max = READ_ONCE(pid_max);
 
@@ -507,6 +511,7 @@ int trace_pid_write(struct trace_pid_list *filtered_pids,
 
 	pid_list->pids = vzalloc((pid_list->pid_max + 7) >> 3);
 	if (!pid_list->pids) {
+		trace_parser_put(&parser);
 		kfree(pid_list);
 		return -ENOMEM;
 	}
@@ -2749,12 +2754,21 @@ trace_function(struct trace_array *tr,
 
 #ifdef CONFIG_STACKTRACE
 
-#define FTRACE_STACK_MAX_ENTRIES (PAGE_SIZE / sizeof(unsigned long))
+/* Allow 4 levels of nesting: normal, softirq, irq, NMI */
+#define FTRACE_KSTACK_NESTING	4
+
+#define FTRACE_KSTACK_ENTRIES	(PAGE_SIZE / FTRACE_KSTACK_NESTING)
+
 struct ftrace_stack {
-	unsigned long		calls[FTRACE_STACK_MAX_ENTRIES];
+	unsigned long		calls[FTRACE_KSTACK_ENTRIES];
 };
 
-static DEFINE_PER_CPU(struct ftrace_stack, ftrace_stack);
+
+struct ftrace_stacks {
+	struct ftrace_stack	stacks[FTRACE_KSTACK_NESTING];
+};
+
+static DEFINE_PER_CPU(struct ftrace_stacks, ftrace_stacks);
 static DEFINE_PER_CPU(int, ftrace_stack_reserve);
 
 static void __ftrace_trace_stack(struct ring_buffer *buffer,
@@ -2763,13 +2777,10 @@ static void __ftrace_trace_stack(struct ring_buffer *buffer,
 {
 	struct trace_event_call *call = &event_kernel_stack;
 	struct ring_buffer_event *event;
+	unsigned int size, nr_entries;
+	struct ftrace_stack *fstack;
 	struct stack_entry *entry;
-	struct stack_trace trace;
-	int use_stack;
-	int size = FTRACE_STACK_ENTRIES;
-
-	trace.nr_entries	= 0;
-	trace.skip		= skip;
+	int stackidx;
 
 	/*
 	 * Add one, for this function and the call to save_stack_trace()
@@ -2777,7 +2788,7 @@ static void __ftrace_trace_stack(struct ring_buffer *buffer,
 	 */
 #ifndef CONFIG_UNWINDER_ORC
 	if (!regs)
-		trace.skip++;
+		skip++;
 #endif
 
 	/*
@@ -2788,53 +2799,40 @@ static void __ftrace_trace_stack(struct ring_buffer *buffer,
 	 */
 	preempt_disable_notrace();
 
-	use_stack = __this_cpu_inc_return(ftrace_stack_reserve);
+	stackidx = __this_cpu_inc_return(ftrace_stack_reserve) - 1;
+
+	/* This should never happen. If it does, yell once and skip */
+	if (WARN_ON_ONCE(stackidx > FTRACE_KSTACK_NESTING))
+		goto out;
+
 	/*
-	 * We don't need any atomic variables, just a barrier.
-	 * If an interrupt comes in, we don't care, because it would
-	 * have exited and put the counter back to what we want.
-	 * We just need a barrier to keep gcc from moving things
-	 * around.
+	 * The above __this_cpu_inc_return() is 'atomic' cpu local. An
+	 * interrupt will either see the value pre increment or post
+	 * increment. If the interrupt happens pre increment it will have
+	 * restored the counter when it returns.  We just need a barrier to
+	 * keep gcc from moving things around.
 	 */
 	barrier();
-	if (use_stack == 1) {
-		trace.entries		= this_cpu_ptr(ftrace_stack.calls);
-		trace.max_entries	= FTRACE_STACK_MAX_ENTRIES;
 
-		if (regs)
-			save_stack_trace_regs(regs, &trace);
-		else
-			save_stack_trace(&trace);
-
-		if (trace.nr_entries > size)
-			size = trace.nr_entries;
-	} else
-		/* From now on, use_stack is a boolean */
-		use_stack = 0;
+	fstack = this_cpu_ptr(ftrace_stacks.stacks) + stackidx;
+	size = ARRAY_SIZE(fstack->calls);
 
-	size *= sizeof(unsigned long);
+	if (regs) {
+		nr_entries = stack_trace_save_regs(regs, fstack->calls,
+						   size, skip);
+	} else {
+		nr_entries = stack_trace_save(fstack->calls, size, skip);
+	}
 
+	size = nr_entries * sizeof(unsigned long);
 	event = __trace_buffer_lock_reserve(buffer, TRACE_STACK,
 					    sizeof(*entry) + size, flags, pc);
 	if (!event)
 		goto out;
 	entry = ring_buffer_event_data(event);
 
-	memset(&entry->caller, 0, size);
-
-	if (use_stack)
-		memcpy(&entry->caller, trace.entries,
-		       trace.nr_entries * sizeof(unsigned long));
-	else {
-		trace.max_entries	= FTRACE_STACK_ENTRIES;
-		trace.entries		= entry->caller;
-		if (regs)
-			save_stack_trace_regs(regs, &trace);
-		else
-			save_stack_trace(&trace);
-	}
-
-	entry->size = trace.nr_entries;
+	memcpy(&entry->caller, fstack->calls, size);
+	entry->size = nr_entries;
 
 	if (!call_filter_check_discard(call, entry, buffer, event))
 		__buffer_unlock_commit(buffer, event);
@@ -2904,15 +2902,15 @@ void trace_dump_stack(int skip)
 }
 EXPORT_SYMBOL_GPL(trace_dump_stack);
 
+#ifdef CONFIG_USER_STACKTRACE_SUPPORT
 static DEFINE_PER_CPU(int, user_stack_count);
 
-void
+static void
 ftrace_trace_userstack(struct ring_buffer *buffer, unsigned long flags, int pc)
 {
 	struct trace_event_call *call = &event_user_stack;
 	struct ring_buffer_event *event;
 	struct userstack_entry *entry;
-	struct stack_trace trace;
 
 	if (!(global_trace.trace_flags & TRACE_ITER_USERSTACKTRACE))
 		return;
@@ -2943,12 +2941,7 @@ ftrace_trace_userstack(struct ring_buffer *buffer, unsigned long flags, int pc)
 	entry->tgid		= current->tgid;
 	memset(&entry->caller, 0, sizeof(entry->caller));
 
-	trace.nr_entries	= 0;
-	trace.max_entries	= FTRACE_STACK_ENTRIES;
-	trace.skip		= 0;
-	trace.entries		= entry->caller;
-
-	save_stack_trace_user(&trace);
+	stack_trace_save_user(entry->caller, FTRACE_STACK_ENTRIES);
 	if (!call_filter_check_discard(call, entry, buffer, event))
 		__buffer_unlock_commit(buffer, event);
 
@@ -2957,13 +2950,12 @@ ftrace_trace_userstack(struct ring_buffer *buffer, unsigned long flags, int pc)
  out:
 	preempt_enable();
 }
-
-#ifdef UNUSED
-static void __trace_userstack(struct trace_array *tr, unsigned long flags)
+#else /* CONFIG_USER_STACKTRACE_SUPPORT */
+static void ftrace_trace_userstack(struct ring_buffer *buffer,
+				   unsigned long flags, int pc)
 {
-	ftrace_trace_userstack(tr, flags, preempt_count());
 }
-#endif /* UNUSED */
+#endif /* !CONFIG_USER_STACKTRACE_SUPPORT */
 
 #endif /* CONFIG_STACKTRACE */
 
@@ -7025,35 +7017,43 @@ struct buffer_ref {
 	struct ring_buffer	*buffer;
 	void			*page;
 	int			cpu;
-	int			ref;
+	refcount_t		refcount;
 };
 
+static void buffer_ref_release(struct buffer_ref *ref)
+{
+	if (!refcount_dec_and_test(&ref->refcount))
+		return;
+	ring_buffer_free_read_page(ref->buffer, ref->cpu, ref->page);
+	kfree(ref);
+}
+
 static void buffer_pipe_buf_release(struct pipe_inode_info *pipe,
 				    struct pipe_buffer *buf)
 {
 	struct buffer_ref *ref = (struct buffer_ref *)buf->private;
 
-	if (--ref->ref)
-		return;
-
-	ring_buffer_free_read_page(ref->buffer, ref->cpu, ref->page);
-	kfree(ref);
+	buffer_ref_release(ref);
 	buf->private = 0;
 }
 
-static void buffer_pipe_buf_get(struct pipe_inode_info *pipe,
+static bool buffer_pipe_buf_get(struct pipe_inode_info *pipe,
 				struct pipe_buffer *buf)
 {
 	struct buffer_ref *ref = (struct buffer_ref *)buf->private;
 
-	ref->ref++;
+	if (refcount_read(&ref->refcount) > INT_MAX/2)
+		return false;
+
+	refcount_inc(&ref->refcount);
+	return true;
 }
 
 /* Pipe buffer operations for a buffer. */
 static const struct pipe_buf_operations buffer_pipe_buf_ops = {
 	.confirm		= generic_pipe_buf_confirm,
 	.release		= buffer_pipe_buf_release,
-	.steal			= generic_pipe_buf_steal,
+	.steal			= generic_pipe_buf_nosteal,
 	.get			= buffer_pipe_buf_get,
 };
 
@@ -7066,11 +7066,7 @@ static void buffer_spd_release(struct splice_pipe_desc *spd, unsigned int i)
 	struct buffer_ref *ref =
 		(struct buffer_ref *)spd->partial[i].private;
 
-	if (--ref->ref)
-		return;
-
-	ring_buffer_free_read_page(ref->buffer, ref->cpu, ref->page);
-	kfree(ref);
+	buffer_ref_release(ref);
 	spd->partial[i].private = 0;
 }
 
@@ -7125,7 +7121,7 @@ tracing_buffers_splice_read(struct file *file, loff_t *ppos,
 			break;
 		}
 
-		ref->ref = 1;
+		refcount_set(&ref->refcount, 1);
 		ref->buffer = iter->trace_buffer->buffer;
 		ref->page = ring_buffer_alloc_read_page(ref->buffer, iter->cpu_file);
 		if (IS_ERR(ref->page)) {
diff --git a/kernel/trace/trace.h b/kernel/trace/trace.h
index d80cee49e0eb..639047b259d7 100644
--- a/kernel/trace/trace.h
+++ b/kernel/trace/trace.h
@@ -782,17 +782,9 @@ void update_max_tr_single(struct trace_array *tr,
 #endif /* CONFIG_TRACER_MAX_TRACE */
 
 #ifdef CONFIG_STACKTRACE
-void ftrace_trace_userstack(struct ring_buffer *buffer, unsigned long flags,
-			    int pc);
-
 void __trace_stack(struct trace_array *tr, unsigned long flags, int skip,
 		   int pc);
 #else
-static inline void ftrace_trace_userstack(struct ring_buffer *buffer,
-					  unsigned long flags, int pc)
-{
-}
-
 static inline void __trace_stack(struct trace_array *tr, unsigned long flags,
 				 int skip, int pc)
 {
diff --git a/kernel/trace/trace_branch.c b/kernel/trace/trace_branch.c
index 4ad967453b6f..3ea65cdff30d 100644
--- a/kernel/trace/trace_branch.c
+++ b/kernel/trace/trace_branch.c
@@ -205,6 +205,8 @@ void trace_likely_condition(struct ftrace_likely_data *f, int val, int expect)
 void ftrace_likely_update(struct ftrace_likely_data *f, int val,
 			  int expect, int is_constant)
 {
+	unsigned long flags = user_access_save();
+
 	/* A constant is always correct */
 	if (is_constant) {
 		f->constant++;
@@ -223,6 +225,8 @@ void ftrace_likely_update(struct ftrace_likely_data *f, int val,
 		f->data.correct++;
 	else
 		f->data.incorrect++;
+
+	user_access_restore(flags);
 }
 EXPORT_SYMBOL(ftrace_likely_update);
 
diff --git a/kernel/trace/trace_dynevent.c b/kernel/trace/trace_dynevent.c
index dd1f43588d70..fa100ed3b4de 100644
--- a/kernel/trace/trace_dynevent.c
+++ b/kernel/trace/trace_dynevent.c
@@ -74,7 +74,7 @@ int dyn_event_release(int argc, char **argv, struct dyn_event_operations *type)
 static int create_dyn_event(int argc, char **argv)
 {
 	struct dyn_event_operations *ops;
-	int ret;
+	int ret = -ENODEV;
 
 	if (argv[0][0] == '-' || argv[0][0] == '!')
 		return dyn_event_release(argc, argv, NULL);
diff --git a/kernel/trace/trace_events_hist.c b/kernel/trace/trace_events_hist.c
index ca46339f3009..a1d20421f4b0 100644
--- a/kernel/trace/trace_events_hist.c
+++ b/kernel/trace/trace_events_hist.c
@@ -3713,7 +3713,6 @@ static void track_data_destroy(struct hist_trigger_data *hist_data,
 	struct trace_event_file *file = hist_data->event_file;
 
 	destroy_hist_field(data->track_data.track_var, 0);
-	destroy_hist_field(data->track_data.var_ref, 0);
 
 	if (data->action == ACTION_SNAPSHOT) {
 		struct track_data *track_data;
@@ -5187,7 +5186,6 @@ static void event_hist_trigger(struct event_trigger_data *data, void *rec,
 	u64 var_ref_vals[TRACING_MAP_VARS_MAX];
 	char compound_key[HIST_KEY_SIZE_MAX];
 	struct tracing_map_elt *elt = NULL;
-	struct stack_trace stacktrace;
 	struct hist_field *key_field;
 	u64 field_contents;
 	void *key = NULL;
@@ -5199,14 +5197,9 @@ static void event_hist_trigger(struct event_trigger_data *data, void *rec,
 		key_field = hist_data->fields[i];
 
 		if (key_field->flags & HIST_FIELD_FL_STACKTRACE) {
-			stacktrace.max_entries = HIST_STACKTRACE_DEPTH;
-			stacktrace.entries = entries;
-			stacktrace.nr_entries = 0;
-			stacktrace.skip = HIST_STACKTRACE_SKIP;
-
-			memset(stacktrace.entries, 0, HIST_STACKTRACE_SIZE);
-			save_stack_trace(&stacktrace);
-
+			memset(entries, 0, HIST_STACKTRACE_SIZE);
+			stack_trace_save(entries, HIST_STACKTRACE_DEPTH,
+					 HIST_STACKTRACE_SKIP);
 			key = entries;
 		} else {
 			field_contents = key_field->fn(key_field, elt, rbe, rec);
@@ -5247,7 +5240,7 @@ static void hist_trigger_stacktrace_print(struct seq_file *m,
 	unsigned int i;
 
 	for (i = 0; i < max_entries; i++) {
-		if (stacktrace_entries[i] == ULONG_MAX)
+		if (!stacktrace_entries[i])
 			return;
 
 		seq_printf(m, "%*c", 1 + spaces, ' ');
diff --git a/kernel/trace/trace_stack.c b/kernel/trace/trace_stack.c
index eec648a0d673..5d16f73898db 100644
--- a/kernel/trace/trace_stack.c
+++ b/kernel/trace/trace_stack.c
@@ -18,44 +18,32 @@
 
 #include "trace.h"
 
-static unsigned long stack_dump_trace[STACK_TRACE_ENTRIES+1] =
-	 { [0 ... (STACK_TRACE_ENTRIES)] = ULONG_MAX };
-unsigned stack_trace_index[STACK_TRACE_ENTRIES];
+#define STACK_TRACE_ENTRIES 500
 
-/*
- * Reserve one entry for the passed in ip. This will allow
- * us to remove most or all of the stack size overhead
- * added by the stack tracer itself.
- */
-struct stack_trace stack_trace_max = {
-	.max_entries		= STACK_TRACE_ENTRIES - 1,
-	.entries		= &stack_dump_trace[0],
-};
+static unsigned long stack_dump_trace[STACK_TRACE_ENTRIES];
+static unsigned stack_trace_index[STACK_TRACE_ENTRIES];
 
-unsigned long stack_trace_max_size;
-arch_spinlock_t stack_trace_max_lock =
+static unsigned int stack_trace_nr_entries;
+static unsigned long stack_trace_max_size;
+static arch_spinlock_t stack_trace_max_lock =
 	(arch_spinlock_t)__ARCH_SPIN_LOCK_UNLOCKED;
 
 DEFINE_PER_CPU(int, disable_stack_tracer);
 static DEFINE_MUTEX(stack_sysctl_mutex);
 
 int stack_tracer_enabled;
-static int last_stack_tracer_enabled;
 
-void stack_trace_print(void)
+static void print_max_stack(void)
 {
 	long i;
 	int size;
 
 	pr_emerg("        Depth    Size   Location    (%d entries)\n"
 			   "        -----    ----   --------\n",
-			   stack_trace_max.nr_entries);
+			   stack_trace_nr_entries);
 
-	for (i = 0; i < stack_trace_max.nr_entries; i++) {
-		if (stack_dump_trace[i] == ULONG_MAX)
-			break;
-		if (i+1 == stack_trace_max.nr_entries ||
-				stack_dump_trace[i+1] == ULONG_MAX)
+	for (i = 0; i < stack_trace_nr_entries; i++) {
+		if (i + 1 == stack_trace_nr_entries)
 			size = stack_trace_index[i];
 		else
 			size = stack_trace_index[i] - stack_trace_index[i+1];
@@ -65,16 +53,7 @@ void stack_trace_print(void)
 	}
 }
 
-/*
- * When arch-specific code overrides this function, the following
- * data should be filled up, assuming stack_trace_max_lock is held to
- * prevent concurrent updates.
- *     stack_trace_index[]
- *     stack_trace_max
- *     stack_trace_max_size
- */
-void __weak
-check_stack(unsigned long ip, unsigned long *stack)
+static void check_stack(unsigned long ip, unsigned long *stack)
 {
 	unsigned long this_size, flags; unsigned long *p, *top, *start;
 	static int tracer_frame;
@@ -110,13 +89,12 @@ check_stack(unsigned long ip, unsigned long *stack)
 
 	stack_trace_max_size = this_size;
 
-	stack_trace_max.nr_entries = 0;
-	stack_trace_max.skip = 0;
-
-	save_stack_trace(&stack_trace_max);
+	stack_trace_nr_entries = stack_trace_save(stack_dump_trace,
+					       ARRAY_SIZE(stack_dump_trace) - 1,
+					       0);
 
 	/* Skip over the overhead of the stack tracer itself */
-	for (i = 0; i < stack_trace_max.nr_entries; i++) {
+	for (i = 0; i < stack_trace_nr_entries; i++) {
 		if (stack_dump_trace[i] == ip)
 			break;
 	}
@@ -125,7 +103,7 @@ check_stack(unsigned long ip, unsigned long *stack)
 	 * Some archs may not have the passed in ip in the dump.
 	 * If that happens, we need to show everything.
 	 */
-	if (i == stack_trace_max.nr_entries)
+	if (i == stack_trace_nr_entries)
 		i = 0;
 
 	/*
@@ -143,15 +121,13 @@ check_stack(unsigned long ip, unsigned long *stack)
 	 * loop will only happen once. This code only takes place
 	 * on a new max, so it is far from a fast path.
 	 */
-	while (i < stack_trace_max.nr_entries) {
+	while (i < stack_trace_nr_entries) {
 		int found = 0;
 
 		stack_trace_index[x] = this_size;
 		p = start;
 
-		for (; p < top && i < stack_trace_max.nr_entries; p++) {
-			if (stack_dump_trace[i] == ULONG_MAX)
-				break;
+		for (; p < top && i < stack_trace_nr_entries; p++) {
 			/*
 			 * The READ_ONCE_NOCHECK is used to let KASAN know that
 			 * this is not a stack-out-of-bounds error.
@@ -182,12 +158,10 @@ check_stack(unsigned long ip, unsigned long *stack)
 			i++;
 	}
 
-	stack_trace_max.nr_entries = x;
-	for (; x < i; x++)
-		stack_dump_trace[x] = ULONG_MAX;
+	stack_trace_nr_entries = x;
 
 	if (task_stack_end_corrupted(current)) {
-		stack_trace_print();
+		print_max_stack();
 		BUG();
 	}
 
@@ -286,7 +260,7 @@ __next(struct seq_file *m, loff_t *pos)
 {
 	long n = *pos - 1;
 
-	if (n >= stack_trace_max.nr_entries || stack_dump_trace[n] == ULONG_MAX)
+	if (n >= stack_trace_nr_entries)
 		return NULL;
 
 	m->private = (void *)n;
@@ -350,7 +324,7 @@ static int t_show(struct seq_file *m, void *v)
 		seq_printf(m, "        Depth    Size   Location"
 			   "    (%d entries)\n"
 			   "        -----    ----   --------\n",
-			   stack_trace_max.nr_entries);
+			   stack_trace_nr_entries);
 
 		if (!stack_tracer_enabled && !stack_trace_max_size)
 			print_disabled(m);
@@ -360,12 +334,10 @@ static int t_show(struct seq_file *m, void *v)
 
 	i = *(long *)v;
 
-	if (i >= stack_trace_max.nr_entries ||
-	    stack_dump_trace[i] == ULONG_MAX)
+	if (i >= stack_trace_nr_entries)
 		return 0;
 
-	if (i+1 == stack_trace_max.nr_entries ||
-	    stack_dump_trace[i+1] == ULONG_MAX)
+	if (i + 1 == stack_trace_nr_entries)
 		size = stack_trace_index[i];
 	else
 		size = stack_trace_index[i] - stack_trace_index[i+1];
@@ -422,23 +394,21 @@ stack_trace_sysctl(struct ctl_table *table, int write,
 		   void __user *buffer, size_t *lenp,
 		   loff_t *ppos)
 {
+	int was_enabled;
 	int ret;
 
 	mutex_lock(&stack_sysctl_mutex);
+	was_enabled = !!stack_tracer_enabled;
 
 	ret = proc_dointvec(table, write, buffer, lenp, ppos);
 
-	if (ret || !write ||
-	    (last_stack_tracer_enabled == !!stack_tracer_enabled))
+	if (ret || !write || (was_enabled == !!stack_tracer_enabled))
 		goto out;
 
-	last_stack_tracer_enabled = !!stack_tracer_enabled;
-
 	if (stack_tracer_enabled)
 		register_ftrace_function(&trace_ops);
 	else
 		unregister_ftrace_function(&trace_ops);
-
  out:
 	mutex_unlock(&stack_sysctl_mutex);
 	return ret;
@@ -454,7 +424,6 @@ static __init int enable_stacktrace(char *str)
 		strncpy(stack_trace_filter_buf, str + len, COMMAND_LINE_SIZE);
 
 	stack_tracer_enabled = 1;
-	last_stack_tracer_enabled = 1;
 	return 1;
 }
 __setup("stacktrace", enable_stacktrace);
diff --git a/kernel/trace/trace_syscalls.c b/kernel/trace/trace_syscalls.c
index f93a56d2db27..fa8fbff736d6 100644
--- a/kernel/trace/trace_syscalls.c
+++ b/kernel/trace/trace_syscalls.c
@@ -314,6 +314,7 @@ static void ftrace_syscall_enter(void *data, struct pt_regs *regs, long id)
 	struct ring_buffer_event *event;
 	struct ring_buffer *buffer;
 	unsigned long irq_flags;
+	unsigned long args[6];
 	int pc;
 	int syscall_nr;
 	int size;
@@ -347,7 +348,8 @@ static void ftrace_syscall_enter(void *data, struct pt_regs *regs, long id)
 
 	entry = ring_buffer_event_data(event);
 	entry->nr = syscall_nr;
-	syscall_get_arguments(current, regs, 0, sys_data->nb_args, entry->args);
+	syscall_get_arguments(current, regs, args);
+	memcpy(entry->args, args, sizeof(unsigned long) * sys_data->nb_args);
 
 	event_trigger_unlock_commit(trace_file, buffer, event, entry,
 				    irq_flags, pc);
@@ -583,6 +585,7 @@ static void perf_syscall_enter(void *ignore, struct pt_regs *regs, long id)
 	struct syscall_metadata *sys_data;
 	struct syscall_trace_enter *rec;
 	struct hlist_head *head;
+	unsigned long args[6];
 	bool valid_prog_array;
 	int syscall_nr;
 	int rctx;
@@ -613,8 +616,8 @@ static void perf_syscall_enter(void *ignore, struct pt_regs *regs, long id)
 		return;
 
 	rec->nr = syscall_nr;
-	syscall_get_arguments(current, regs, 0, sys_data->nb_args,
-			       (unsigned long *)&rec->args);
+	syscall_get_arguments(current, regs, args);
+	memcpy(&rec->args, args, sizeof(unsigned long) * sys_data->nb_args);
 
 	if ((valid_prog_array &&
 	     !perf_call_bpf_enter(sys_data->enter_event, regs, sys_data, rec)) ||
diff --git a/kernel/watchdog.c b/kernel/watchdog.c
index 403c9bd90413..7f9e7b9306fe 100644
--- a/kernel/watchdog.c
+++ b/kernel/watchdog.c
@@ -554,13 +554,15 @@ static void softlockup_start_all(void)
 
 int lockup_detector_online_cpu(unsigned int cpu)
 {
-	watchdog_enable(cpu);
+	if (cpumask_test_cpu(cpu, &watchdog_allowed_mask))
+		watchdog_enable(cpu);
 	return 0;
 }
 
 int lockup_detector_offline_cpu(unsigned int cpu)
 {
-	watchdog_disable(cpu);
+	if (cpumask_test_cpu(cpu, &watchdog_allowed_mask))
+		watchdog_disable(cpu);
 	return 0;
 }
 
@@ -588,7 +590,7 @@ static void lockup_detector_reconfigure(void)
  * Create the watchdog thread infrastructure and configure the detector(s).
  *
  * The threads are not unparked as watchdog_allowed_mask is empty.  When
- * the threads are sucessfully initialized, take the proper locks and
+ * the threads are successfully initialized, take the proper locks and
  * unpark the threads in the watchdog_cpumask if the watchdog is enabled.
  */
 static __init void lockup_detector_setup(void)
diff --git a/kernel/watchdog_hld.c b/kernel/watchdog_hld.c
index 71381168dede..247bf0b1582c 100644
--- a/kernel/watchdog_hld.c
+++ b/kernel/watchdog_hld.c
@@ -135,7 +135,8 @@ static void watchdog_overflow_callback(struct perf_event *event,
 		if (__this_cpu_read(hard_watchdog_warn) == true)
 			return;
 
-		pr_emerg("Watchdog detected hard LOCKUP on cpu %d", this_cpu);
+		pr_emerg("Watchdog detected hard LOCKUP on cpu %d\n",
+			 this_cpu);
 		print_modules();
 		print_irqtrace_events(current);
 		if (regs)
diff --git a/kernel/workqueue.c b/kernel/workqueue.c
index ddee541ea97a..56180c9286f5 100644
--- a/kernel/workqueue.c
+++ b/kernel/workqueue.c
@@ -841,43 +841,32 @@ static void wake_up_worker(struct worker_pool *pool)
 }
 
 /**
- * wq_worker_waking_up - a worker is waking up
+ * wq_worker_running - a worker is running again
  * @task: task waking up
- * @cpu: CPU @task is waking up to
  *
- * This function is called during try_to_wake_up() when a worker is
- * being awoken.
- *
- * CONTEXT:
- * spin_lock_irq(rq->lock)
+ * This function is called when a worker returns from schedule()
  */
-void wq_worker_waking_up(struct task_struct *task, int cpu)
+void wq_worker_running(struct task_struct *task)
 {
 	struct worker *worker = kthread_data(task);
 
-	if (!(worker->flags & WORKER_NOT_RUNNING)) {
-		WARN_ON_ONCE(worker->pool->cpu != cpu);
+	if (!worker->sleeping)
+		return;
+	if (!(worker->flags & WORKER_NOT_RUNNING))
 		atomic_inc(&worker->pool->nr_running);
-	}
+	worker->sleeping = 0;
 }
 
 /**
  * wq_worker_sleeping - a worker is going to sleep
  * @task: task going to sleep
  *
- * This function is called during schedule() when a busy worker is
- * going to sleep.  Worker on the same cpu can be woken up by
- * returning pointer to its task.
- *
- * CONTEXT:
- * spin_lock_irq(rq->lock)
- *
- * Return:
- * Worker task on @cpu to wake up, %NULL if none.
+ * This function is called from schedule() when a busy worker is
+ * going to sleep.
  */
-struct task_struct *wq_worker_sleeping(struct task_struct *task)
+void wq_worker_sleeping(struct task_struct *task)
 {
-	struct worker *worker = kthread_data(task), *to_wakeup = NULL;
+	struct worker *next, *worker = kthread_data(task);
 	struct worker_pool *pool;
 
 	/*
@@ -886,13 +875,15 @@ struct task_struct *wq_worker_sleeping(struct task_struct *task)
 	 * checking NOT_RUNNING.
 	 */
 	if (worker->flags & WORKER_NOT_RUNNING)
-		return NULL;
+		return;
 
 	pool = worker->pool;
 
-	/* this can only happen on the local cpu */
-	if (WARN_ON_ONCE(pool->cpu != raw_smp_processor_id()))
-		return NULL;
+	if (WARN_ON_ONCE(worker->sleeping))
+		return;
+
+	worker->sleeping = 1;
+	spin_lock_irq(&pool->lock);
 
 	/*
 	 * The counterpart of the following dec_and_test, implied mb,
@@ -906,9 +897,12 @@ struct task_struct *wq_worker_sleeping(struct task_struct *task)
 	 * lock is safe.
 	 */
 	if (atomic_dec_and_test(&pool->nr_running) &&
-	    !list_empty(&pool->worklist))
-		to_wakeup = first_idle_worker(pool);
-	return to_wakeup ? to_wakeup->task : NULL;
+	    !list_empty(&pool->worklist)) {
+		next = first_idle_worker(pool);
+		if (next)
+			wake_up_process(next->task);
+	}
+	spin_unlock_irq(&pool->lock);
 }
 
 /**
@@ -4929,7 +4923,7 @@ static void rebind_workers(struct worker_pool *pool)
 		 *
 		 * WRITE_ONCE() is necessary because @worker->flags may be
 		 * tested without holding any lock in
-		 * wq_worker_waking_up().  Without it, NOT_RUNNING test may
+		 * wq_worker_running().  Without it, NOT_RUNNING test may
 		 * fail incorrectly leading to premature concurrency
 		 * management operations.
 		 */
diff --git a/kernel/workqueue_internal.h b/kernel/workqueue_internal.h
index cb68b03ca89a..498de0e909a4 100644
--- a/kernel/workqueue_internal.h
+++ b/kernel/workqueue_internal.h
@@ -44,6 +44,7 @@ struct worker {
 	unsigned long		last_active;	/* L: last active timestamp */
 	unsigned int		flags;		/* X: flags */
 	int			id;		/* I: worker id */
+	int			sleeping;	/* None */
 
 	/*
 	 * Opaque string set with work_set_desc().  Printed out with task
@@ -72,8 +73,8 @@ static inline struct worker *current_wq_worker(void)
  * Scheduler hooks for concurrency managed workqueue.  Only to be used from
  * sched/ and workqueue.c.
  */
-void wq_worker_waking_up(struct task_struct *task, int cpu);
-struct task_struct *wq_worker_sleeping(struct task_struct *task);
+void wq_worker_running(struct task_struct *task);
+void wq_worker_sleeping(struct task_struct *task);
 work_func_t wq_worker_last_func(struct task_struct *task);
 
 #endif /* _KERNEL_WORKQUEUE_INTERNAL_H */
diff --git a/lib/Kconfig b/lib/Kconfig
index a9e56539bd11..e86975bfca6a 100644
--- a/lib/Kconfig
+++ b/lib/Kconfig
@@ -597,6 +597,10 @@ config ARCH_HAS_UACCESS_FLUSHCACHE
 config ARCH_HAS_UACCESS_MCSAFE
 	bool
 
+# Temporary. Goes away when all archs are cleaned up
+config ARCH_STACKWALK
+       bool
+
 config STACKDEPOT
 	bool
 	select STACKTRACE
diff --git a/lib/Kconfig.debug b/lib/Kconfig.debug
index 0d9e81779e37..4c54a89f06ee 100644
--- a/lib/Kconfig.debug
+++ b/lib/Kconfig.debug
@@ -753,9 +753,9 @@ endmenu # "Memory Debugging"
 config ARCH_HAS_KCOV
 	bool
 	help
-	  KCOV does not have any arch-specific code, but currently it is enabled
-	  only for x86_64. KCOV requires testing on other archs, and most likely
-	  disabling of instrumentation for some early boot code.
+	  An architecture should select this when it can successfully
+	  build and run with CONFIG_KCOV. This typically requires
+	  disabling instrumentation for some early boot code.
 
 config CC_HAS_SANCOV_TRACE_PC
 	def_bool $(cc-option,-fsanitize-coverage=trace-pc)
@@ -1769,6 +1769,9 @@ config TEST_HEXDUMP
 config TEST_STRING_HELPERS
 	tristate "Test functions located in the string_helpers module at runtime"
 
+config TEST_STRSCPY
+	tristate "Test strscpy*() family of functions at runtime"
+
 config TEST_KSTRTOX
 	tristate "Test kstrto*() family of functions at runtime"
 
@@ -1929,6 +1932,7 @@ config TEST_KMOD
 	depends on m
 	depends on BLOCK && (64BIT || LBDAF)	  # for XFS, BTRFS
 	depends on NETDEVICES && NET_CORE && INET # for TUN
+	depends on BLOCK
 	select TEST_LKM
 	select XFS_FS
 	select TUN
diff --git a/lib/Makefile b/lib/Makefile
index 3b08673e8881..07506e3891a0 100644
--- a/lib/Makefile
+++ b/lib/Makefile
@@ -17,6 +17,17 @@ KCOV_INSTRUMENT_list_debug.o := n
 KCOV_INSTRUMENT_debugobjects.o := n
 KCOV_INSTRUMENT_dynamic_debug.o := n
 
+# Early boot use of cmdline, don't instrument it
+ifdef CONFIG_AMD_MEM_ENCRYPT
+KASAN_SANITIZE_string.o := n
+
+ifdef CONFIG_FUNCTION_TRACER
+CFLAGS_REMOVE_string.o = -pg
+endif
+
+CFLAGS_string.o := $(call cc-option, -fno-stack-protector)
+endif
+
 lib-y := ctype.o string.o vsprintf.o cmdline.o \
 	 rbtree.o radix-tree.o timerqueue.o xarray.o \
 	 idr.o int_sqrt.o extable.o \
@@ -70,6 +81,7 @@ obj-$(CONFIG_TEST_STATIC_KEYS) += test_static_keys.o
 obj-$(CONFIG_TEST_STATIC_KEYS) += test_static_key_base.o
 obj-$(CONFIG_TEST_PRINTF) += test_printf.o
 obj-$(CONFIG_TEST_BITMAP) += test_bitmap.o
+obj-$(CONFIG_TEST_STRSCPY) += test_strscpy.o
 obj-$(CONFIG_TEST_BITFIELD) += test_bitfield.o
 obj-$(CONFIG_TEST_UUID) += test_uuid.o
 obj-$(CONFIG_TEST_XARRAY) += test_xarray.o
@@ -268,6 +280,7 @@ obj-$(CONFIG_UCS2_STRING) += ucs2_string.o
 obj-$(CONFIG_UBSAN) += ubsan.o
 
 UBSAN_SANITIZE_ubsan.o := n
+CFLAGS_ubsan.o := $(call cc-option, -fno-conserve-stack -fno-stack-protector)
 
 obj-$(CONFIG_SBITMAP) += sbitmap.o
 
diff --git a/lib/crc-t10dif.c b/lib/crc-t10dif.c
index 4d0d47c1ffbd..e89ebfdbb0fc 100644
--- a/lib/crc-t10dif.c
+++ b/lib/crc-t10dif.c
@@ -69,7 +69,6 @@ __u16 crc_t10dif_update(__u16 crc, const unsigned char *buffer, size_t len)
 
 	rcu_read_lock();
 	desc.shash.tfm = rcu_dereference(crct10dif_tfm);
-	desc.shash.flags = 0;
 	*(__u16 *)desc.ctx = crc;
 
 	err = crypto_shash_update(&desc.shash, buffer, len);
diff --git a/lib/digsig.c b/lib/digsig.c
index 6ba6fcd92dd1..3b0a579bdcdf 100644
--- a/lib/digsig.c
+++ b/lib/digsig.c
@@ -240,7 +240,6 @@ int digsig_verify(struct key *keyring, const char *sig, int siglen,
 		goto err;
 
 	desc->tfm = shash;
-	desc->flags = CRYPTO_TFM_REQ_MAY_SLEEP;
 
 	crypto_shash_init(desc);
 	crypto_shash_update(desc, data, datalen);
diff --git a/lib/fault-inject.c b/lib/fault-inject.c
index cf7b129b0b2b..e26aa4f65eb9 100644
--- a/lib/fault-inject.c
+++ b/lib/fault-inject.c
@@ -65,22 +65,16 @@ static bool fail_task(struct fault_attr *attr, struct task_struct *task)
 
 static bool fail_stacktrace(struct fault_attr *attr)
 {
-	struct stack_trace trace;
 	int depth = attr->stacktrace_depth;
 	unsigned long entries[MAX_STACK_TRACE_DEPTH];
-	int n;
+	int n, nr_entries;
 	bool found = (attr->require_start == 0 && attr->require_end == ULONG_MAX);
 
 	if (depth == 0)
 		return found;
 
-	trace.nr_entries = 0;
-	trace.entries = entries;
-	trace.max_entries = depth;
-	trace.skip = 1;
-
-	save_stack_trace(&trace);
-	for (n = 0; n < trace.nr_entries; n++) {
+	nr_entries = stack_trace_save(entries, depth, 1);
+	for (n = 0; n < nr_entries; n++) {
 		if (attr->reject_start <= entries[n] &&
 			       entries[n] < attr->reject_end)
 			return false;
diff --git a/lib/iov_iter.c b/lib/iov_iter.c
index ea36dc355da1..b396d328a764 100644
--- a/lib/iov_iter.c
+++ b/lib/iov_iter.c
@@ -1528,6 +1528,7 @@ EXPORT_SYMBOL(csum_and_copy_to_iter);
 size_t hash_and_copy_to_iter(const void *addr, size_t bytes, void *hashp,
 		struct iov_iter *i)
 {
+#ifdef CONFIG_CRYPTO
 	struct ahash_request *hash = hashp;
 	struct scatterlist sg;
 	size_t copied;
@@ -1537,6 +1538,9 @@ size_t hash_and_copy_to_iter(const void *addr, size_t bytes, void *hashp,
 	ahash_request_set_crypt(hash, &sg, NULL, copied);
 	crypto_ahash_update(hash);
 	return copied;
+#else
+	return 0;
+#endif
 }
 EXPORT_SYMBOL(hash_and_copy_to_iter);
 
diff --git a/lib/libcrc32c.c b/lib/libcrc32c.c
index f0a2934605bf..4e9829c4d64c 100644
--- a/lib/libcrc32c.c
+++ b/lib/libcrc32c.c
@@ -47,7 +47,6 @@ u32 crc32c(u32 crc, const void *address, unsigned int length)
 	int err;
 
 	shash->tfm = tfm;
-	shash->flags = 0;
 	*ctx = crc;
 
 	err = crypto_shash_update(shash, address, length);
diff --git a/lib/lzo/lzo1x_compress.c b/lib/lzo/lzo1x_compress.c
index 4525fb094844..a8ede77afe0d 100644
--- a/lib/lzo/lzo1x_compress.c
+++ b/lib/lzo/lzo1x_compress.c
@@ -291,13 +291,14 @@ int lzogeneric1x_1_compress(const unsigned char *in, size_t in_len,
 {
 	const unsigned char *ip = in;
 	unsigned char *op = out;
+	unsigned char *data_start;
 	size_t l = in_len;
 	size_t t = 0;
 	signed char state_offset = -2;
 	unsigned int m4_max_offset;
 
-	// LZO v0 will never write 17 as first byte,
-	// so this is used to version the bitstream
+	// LZO v0 will never write 17 as first byte (except for zero-length
+	// input), so this is used to version the bitstream
 	if (bitstream_version > 0) {
 		*op++ = 17;
 		*op++ = bitstream_version;
@@ -306,6 +307,8 @@ int lzogeneric1x_1_compress(const unsigned char *in, size_t in_len,
 		m4_max_offset = M4_MAX_OFFSET_V0;
 	}
 
+	data_start = op;
+
 	while (l > 20) {
 		size_t ll = l <= (m4_max_offset + 1) ? l : (m4_max_offset + 1);
 		uintptr_t ll_end = (uintptr_t) ip + ll;
@@ -324,7 +327,7 @@ int lzogeneric1x_1_compress(const unsigned char *in, size_t in_len,
 	if (t > 0) {
 		const unsigned char *ii = in + in_len - t;
 
-		if (op == out && t <= 238) {
+		if (op == data_start && t <= 238) {
 			*op++ = (17 + t);
 		} else if (t <= 3) {
 			op[state_offset] |= t;
diff --git a/lib/lzo/lzo1x_decompress_safe.c b/lib/lzo/lzo1x_decompress_safe.c
index 6d2600ea3b55..9e07e9ef1aad 100644
--- a/lib/lzo/lzo1x_decompress_safe.c
+++ b/lib/lzo/lzo1x_decompress_safe.c
@@ -54,11 +54,9 @@ int lzo1x_decompress_safe(const unsigned char *in, size_t in_len,
 	if (unlikely(in_len < 3))
 		goto input_overrun;
 
-	if (likely(*ip == 17)) {
+	if (likely(in_len >= 5) && likely(*ip == 17)) {
 		bitstream_version = ip[1];
 		ip += 2;
-		if (unlikely(in_len < 5))
-			goto input_overrun;
 	} else {
 		bitstream_version = 0;
 	}
diff --git a/lib/rhashtable.c b/lib/rhashtable.c
index 0a105d4af166..97f59abc3e92 100644
--- a/lib/rhashtable.c
+++ b/lib/rhashtable.c
@@ -416,8 +416,12 @@ static void rht_deferred_worker(struct work_struct *work)
 	else if (tbl->nest)
 		err = rhashtable_rehash_alloc(ht, tbl, tbl->size);
 
-	if (!err)
-		err = rhashtable_rehash_table(ht);
+	if (!err || err == -EEXIST) {
+		int nerr;
+
+		nerr = rhashtable_rehash_table(ht);
+		err = err ?: nerr;
+	}
 
 	mutex_unlock(&ht->mutex);
 
diff --git a/lib/sbitmap.c b/lib/sbitmap.c
index 5b382c1244ed..155fe38756ec 100644
--- a/lib/sbitmap.c
+++ b/lib/sbitmap.c
@@ -591,6 +591,17 @@ EXPORT_SYMBOL_GPL(sbitmap_queue_wake_up);
 void sbitmap_queue_clear(struct sbitmap_queue *sbq, unsigned int nr,
 			 unsigned int cpu)
 {
+	/*
+	 * Once the clear bit is set, the bit may be allocated out.
+	 *
+	 * Orders READ/WRITE on the asssociated instance(such as request
+	 * of blk_mq) by this bit for avoiding race with re-allocation,
+	 * and its pair is the memory barrier implied in __sbitmap_get_word.
+	 *
+	 * One invariant is that the clear bit has to be zero when the bit
+	 * is in use.
+	 */
+	smp_mb__before_atomic();
 	sbitmap_deferred_clear_bit(&sbq->sb, nr);
 
 	/*
diff --git a/lib/stackdepot.c b/lib/stackdepot.c
index e513459a5601..605c61f65d94 100644
--- a/lib/stackdepot.c
+++ b/lib/stackdepot.c
@@ -194,40 +194,52 @@ static inline struct stack_record *find_stack(struct stack_record *bucket,
 	return NULL;
 }
 
-void depot_fetch_stack(depot_stack_handle_t handle, struct stack_trace *trace)
+/**
+ * stack_depot_fetch - Fetch stack entries from a depot
+ *
+ * @handle:		Stack depot handle which was returned from
+ *			stack_depot_save().
+ * @entries:		Pointer to store the entries address
+ *
+ * Return: The number of trace entries for this depot.
+ */
+unsigned int stack_depot_fetch(depot_stack_handle_t handle,
+			       unsigned long **entries)
 {
 	union handle_parts parts = { .handle = handle };
 	void *slab = stack_slabs[parts.slabindex];
 	size_t offset = parts.offset << STACK_ALLOC_ALIGN;
 	struct stack_record *stack = slab + offset;
 
-	trace->nr_entries = trace->max_entries = stack->size;
-	trace->entries = stack->entries;
-	trace->skip = 0;
+	*entries = stack->entries;
+	return stack->size;
 }
-EXPORT_SYMBOL_GPL(depot_fetch_stack);
+EXPORT_SYMBOL_GPL(stack_depot_fetch);
 
 /**
- * depot_save_stack - save stack in a stack depot.
- * @trace - the stacktrace to save.
- * @alloc_flags - flags for allocating additional memory if required.
+ * stack_depot_save - Save a stack trace from an array
+ *
+ * @entries:		Pointer to storage array
+ * @nr_entries:		Size of the storage array
+ * @alloc_flags:	Allocation gfp flags
  *
- * Returns the handle of the stack struct stored in depot.
+ * Return: The handle of the stack struct stored in depot
  */
-depot_stack_handle_t depot_save_stack(struct stack_trace *trace,
-				    gfp_t alloc_flags)
+depot_stack_handle_t stack_depot_save(unsigned long *entries,
+				      unsigned int nr_entries,
+				      gfp_t alloc_flags)
 {
-	u32 hash;
-	depot_stack_handle_t retval = 0;
 	struct stack_record *found = NULL, **bucket;
-	unsigned long flags;
+	depot_stack_handle_t retval = 0;
 	struct page *page = NULL;
 	void *prealloc = NULL;
+	unsigned long flags;
+	u32 hash;
 
-	if (unlikely(trace->nr_entries == 0))
+	if (unlikely(nr_entries == 0))
 		goto fast_exit;
 
-	hash = hash_stack(trace->entries, trace->nr_entries);
+	hash = hash_stack(entries, nr_entries);
 	bucket = &stack_table[hash & STACK_HASH_MASK];
 
 	/*
@@ -235,8 +247,8 @@ depot_stack_handle_t depot_save_stack(struct stack_trace *trace,
 	 * The smp_load_acquire() here pairs with smp_store_release() to
 	 * |bucket| below.
 	 */
-	found = find_stack(smp_load_acquire(bucket), trace->entries,
-			   trace->nr_entries, hash);
+	found = find_stack(smp_load_acquire(bucket), entries,
+			   nr_entries, hash);
 	if (found)
 		goto exit;
 
@@ -264,10 +276,10 @@ depot_stack_handle_t depot_save_stack(struct stack_trace *trace,
 
 	spin_lock_irqsave(&depot_lock, flags);
 
-	found = find_stack(*bucket, trace->entries, trace->nr_entries, hash);
+	found = find_stack(*bucket, entries, nr_entries, hash);
 	if (!found) {
 		struct stack_record *new =
-			depot_alloc_stack(trace->entries, trace->nr_entries,
+			depot_alloc_stack(entries, nr_entries,
 					  hash, &prealloc, alloc_flags);
 		if (new) {
 			new->next = *bucket;
@@ -297,4 +309,4 @@ exit:
 fast_exit:
 	return retval;
 }
-EXPORT_SYMBOL_GPL(depot_save_stack);
+EXPORT_SYMBOL_GPL(stack_depot_save);
diff --git a/lib/string.c b/lib/string.c
index 38e4ca08e757..6016eb3ac73d 100644
--- a/lib/string.c
+++ b/lib/string.c
@@ -159,11 +159,9 @@ EXPORT_SYMBOL(strlcpy);
  * @src: Where to copy the string from
  * @count: Size of destination buffer
  *
- * Copy the string, or as much of it as fits, into the dest buffer.
- * The routine returns the number of characters copied (not including
- * the trailing NUL) or -E2BIG if the destination buffer wasn't big enough.
- * The behavior is undefined if the string buffers overlap.
- * The destination buffer is always NUL terminated, unless it's zero-sized.
+ * Copy the string, or as much of it as fits, into the dest buffer.  The
+ * behavior is undefined if the string buffers overlap.  The destination
+ * buffer is always NUL terminated, unless it's zero-sized.
  *
  * Preferred to strlcpy() since the API doesn't require reading memory
  * from the src string beyond the specified "count" bytes, and since
@@ -173,8 +171,10 @@ EXPORT_SYMBOL(strlcpy);
  *
  * Preferred to strncpy() since it always returns a valid string, and
  * doesn't unnecessarily force the tail of the destination buffer to be
- * zeroed.  If the zeroing is desired, it's likely cleaner to use strscpy()
- * with an overflow test, then just memset() the tail of the dest buffer.
+ * zeroed.  If zeroing is desired please use strscpy_pad().
+ *
+ * Return: The number of characters copied (not including the trailing
+ *         %NUL) or -E2BIG if the destination buffer wasn't big enough.
  */
 ssize_t strscpy(char *dest, const char *src, size_t count)
 {
@@ -237,6 +237,39 @@ ssize_t strscpy(char *dest, const char *src, size_t count)
 EXPORT_SYMBOL(strscpy);
 #endif
 
+/**
+ * strscpy_pad() - Copy a C-string into a sized buffer
+ * @dest: Where to copy the string to
+ * @src: Where to copy the string from
+ * @count: Size of destination buffer
+ *
+ * Copy the string, or as much of it as fits, into the dest buffer.  The
+ * behavior is undefined if the string buffers overlap.  The destination
+ * buffer is always %NUL terminated, unless it's zero-sized.
+ *
+ * If the source string is shorter than the destination buffer, zeros
+ * the tail of the destination buffer.
+ *
+ * For full explanation of why you may want to consider using the
+ * 'strscpy' functions please see the function docstring for strscpy().
+ *
+ * Return: The number of characters copied (not including the trailing
+ *         %NUL) or -E2BIG if the destination buffer wasn't big enough.
+ */
+ssize_t strscpy_pad(char *dest, const char *src, size_t count)
+{
+	ssize_t written;
+
+	written = strscpy(dest, src, count);
+	if (written < 0 || written == count - 1)
+		return written;
+
+	memset(dest + written + 1, 0, count - written - 1);
+
+	return written;
+}
+EXPORT_SYMBOL(strscpy_pad);
+
 #ifndef __HAVE_ARCH_STRCAT
 /**
  * strcat - Append one %NUL-terminated string to another
@@ -866,6 +899,26 @@ __visible int memcmp(const void *cs, const void *ct, size_t count)
 EXPORT_SYMBOL(memcmp);
 #endif
 
+#ifndef __HAVE_ARCH_BCMP
+/**
+ * bcmp - returns 0 if and only if the buffers have identical contents.
+ * @a: pointer to first buffer.
+ * @b: pointer to second buffer.
+ * @len: size of buffers.
+ *
+ * The sign or magnitude of a non-zero return value has no particular
+ * meaning, and architectures may implement their own more efficient bcmp(). So
+ * while this particular implementation is a simple (tail) call to memcmp, do
+ * not rely on anything but whether the return value is zero or non-zero.
+ */
+#undef bcmp
+int bcmp(const void *a, const void *b, size_t len)
+{
+	return memcmp(a, b, len);
+}
+EXPORT_SYMBOL(bcmp);
+#endif
+
 #ifndef __HAVE_ARCH_MEMSCAN
 /**
  * memscan - Find a character in an area of memory.
diff --git a/lib/strncpy_from_user.c b/lib/strncpy_from_user.c
index 58eacd41526c..023ba9f3b99f 100644
--- a/lib/strncpy_from_user.c
+++ b/lib/strncpy_from_user.c
@@ -23,10 +23,11 @@
  * hit it), 'max' is the address space maximum (and we return
  * -EFAULT if we hit it).
  */
-static inline long do_strncpy_from_user(char *dst, const char __user *src, long count, unsigned long max)
+static inline long do_strncpy_from_user(char *dst, const char __user *src,
+					unsigned long count, unsigned long max)
 {
 	const struct word_at_a_time constants = WORD_AT_A_TIME_CONSTANTS;
-	long res = 0;
+	unsigned long res = 0;
 
 	/*
 	 * Truncate 'max' to the user-specified limit, so that
diff --git a/lib/strnlen_user.c b/lib/strnlen_user.c
index 1c1a1b0e38a5..7f2db3fe311f 100644
--- a/lib/strnlen_user.c
+++ b/lib/strnlen_user.c
@@ -28,7 +28,7 @@
 static inline long do_strnlen_user(const char __user *src, unsigned long count, unsigned long max)
 {
 	const struct word_at_a_time constants = WORD_AT_A_TIME_CONSTANTS;
-	long align, res = 0;
+	unsigned long align, res = 0;
 	unsigned long c;
 
 	/*
@@ -42,7 +42,7 @@ static inline long do_strnlen_user(const char __user *src, unsigned long count,
 	 * Do everything aligned. But that means that we
 	 * need to also expand the maximum..
 	 */
-	align = (sizeof(long) - 1) & (unsigned long)src;
+	align = (sizeof(unsigned long) - 1) & (unsigned long)src;
 	src -= align;
 	max += align;
 
diff --git a/lib/syscall.c b/lib/syscall.c
index 1a7077f20eae..fb328e7ccb08 100644
--- a/lib/syscall.c
+++ b/lib/syscall.c
@@ -5,16 +5,14 @@
 #include <linux/export.h>
 #include <asm/syscall.h>
 
-static int collect_syscall(struct task_struct *target, long *callno,
-			   unsigned long args[6], unsigned int maxargs,
-			   unsigned long *sp, unsigned long *pc)
+static int collect_syscall(struct task_struct *target, struct syscall_info *info)
 {
 	struct pt_regs *regs;
 
 	if (!try_get_task_stack(target)) {
 		/* Task has no stack, so the task isn't in a syscall. */
-		*sp = *pc = 0;
-		*callno = -1;
+		memset(info, 0, sizeof(*info));
+		info->data.nr = -1;
 		return 0;
 	}
 
@@ -24,12 +22,13 @@ static int collect_syscall(struct task_struct *target, long *callno,
 		return -EAGAIN;
 	}
 
-	*sp = user_stack_pointer(regs);
-	*pc = instruction_pointer(regs);
+	info->sp = user_stack_pointer(regs);
+	info->data.instruction_pointer = instruction_pointer(regs);
 
-	*callno = syscall_get_nr(target, regs);
-	if (*callno != -1L && maxargs > 0)
-		syscall_get_arguments(target, regs, 0, maxargs, args);
+	info->data.nr = syscall_get_nr(target, regs);
+	if (info->data.nr != -1L)
+		syscall_get_arguments(target, regs,
+				      (unsigned long *)&info->data.args[0]);
 
 	put_task_stack(target);
 	return 0;
@@ -38,41 +37,35 @@ static int collect_syscall(struct task_struct *target, long *callno,
 /**
  * task_current_syscall - Discover what a blocked task is doing.
  * @target:		thread to examine
- * @callno:		filled with system call number or -1
- * @args:		filled with @maxargs system call arguments
- * @maxargs:		number of elements in @args to fill
- * @sp:			filled with user stack pointer
- * @pc:			filled with user PC
+ * @info:		structure with the following fields:
+ *			 .sp        - filled with user stack pointer
+ *			 .data.nr   - filled with system call number or -1
+ *			 .data.args - filled with @maxargs system call arguments
+ *			 .data.instruction_pointer - filled with user PC
  *
- * If @target is blocked in a system call, returns zero with *@callno
- * set to the the call's number and @args filled in with its arguments.
- * Registers not used for system call arguments may not be available and
- * it is not kosher to use &struct user_regset calls while the system
+ * If @target is blocked in a system call, returns zero with @info.data.nr
+ * set to the the call's number and @info.data.args filled in with its
+ * arguments. Registers not used for system call arguments may not be available
+ * and it is not kosher to use &struct user_regset calls while the system
  * call is still in progress.  Note we may get this result if @target
  * has finished its system call but not yet returned to user mode, such
  * as when it's stopped for signal handling or syscall exit tracing.
  *
  * If @target is blocked in the kernel during a fault or exception,
- * returns zero with *@callno set to -1 and does not fill in @args.
- * If so, it's now safe to examine @target using &struct user_regset
- * get() calls as long as we're sure @target won't return to user mode.
+ * returns zero with *@info.data.nr set to -1 and does not fill in
+ * @info.data.args. If so, it's now safe to examine @target using
+ * &struct user_regset get() calls as long as we're sure @target won't return
+ * to user mode.
  *
  * Returns -%EAGAIN if @target does not remain blocked.
- *
- * Returns -%EINVAL if @maxargs is too large (maximum is six).
  */
-int task_current_syscall(struct task_struct *target, long *callno,
-			 unsigned long args[6], unsigned int maxargs,
-			 unsigned long *sp, unsigned long *pc)
+int task_current_syscall(struct task_struct *target, struct syscall_info *info)
 {
 	long state;
 	unsigned long ncsw;
 
-	if (unlikely(maxargs > 6))
-		return -EINVAL;
-
 	if (target == current)
-		return collect_syscall(target, callno, args, maxargs, sp, pc);
+		return collect_syscall(target, info);
 
 	state = target->state;
 	if (unlikely(!state))
@@ -80,7 +73,7 @@ int task_current_syscall(struct task_struct *target, long *callno,
 
 	ncsw = wait_task_inactive(target, state);
 	if (unlikely(!ncsw) ||
-	    unlikely(collect_syscall(target, callno, args, maxargs, sp, pc)) ||
+	    unlikely(collect_syscall(target, info)) ||
 	    unlikely(wait_task_inactive(target, state) != ncsw))
 		return -EAGAIN;
 
diff --git a/lib/test_bitmap.c b/lib/test_bitmap.c
index 6cd7d0740005..792d90608052 100644
--- a/lib/test_bitmap.c
+++ b/lib/test_bitmap.c
@@ -12,6 +12,8 @@
 #include <linux/slab.h>
 #include <linux/string.h>
 
+#include "../tools/testing/selftests/kselftest_module.h"
+
 static unsigned total_tests __initdata;
 static unsigned failed_tests __initdata;
 
@@ -361,7 +363,7 @@ static void noinline __init test_mem_optimisations(void)
 	}
 }
 
-static int __init test_bitmap_init(void)
+static void __init selftest(void)
 {
 	test_zero_clear();
 	test_fill_set();
@@ -369,22 +371,8 @@ static int __init test_bitmap_init(void)
 	test_bitmap_arr32();
 	test_bitmap_parselist();
 	test_mem_optimisations();
-
-	if (failed_tests == 0)
-		pr_info("all %u tests passed\n", total_tests);
-	else
-		pr_warn("failed %u out of %u tests\n",
-			failed_tests, total_tests);
-
-	return failed_tests ? -EINVAL : 0;
 }
 
-static void __exit test_bitmap_cleanup(void)
-{
-}
-
-module_init(test_bitmap_init);
-module_exit(test_bitmap_cleanup);
-
+KSTM_MODULE_LOADERS(test_bitmap);
 MODULE_AUTHOR("david decotigny <david.decotigny@googlers.com>");
 MODULE_LICENSE("GPL");
diff --git a/lib/test_printf.c b/lib/test_printf.c
index 659b6cc0d483..f4fcc1c43739 100644
--- a/lib/test_printf.c
+++ b/lib/test_printf.c
@@ -21,6 +21,8 @@
 #include <linux/gfp.h>
 #include <linux/mm.h>
 
+#include "../tools/testing/selftests/kselftest_module.h"
+
 #define BUF_SIZE 256
 #define PAD_SIZE 16
 #define FILL_CHAR '$'
@@ -590,12 +592,11 @@ test_pointer(void)
 	flags();
 }
 
-static int __init
-test_printf_init(void)
+static void __init selftest(void)
 {
 	alloced_buffer = kmalloc(BUF_SIZE + 2*PAD_SIZE, GFP_KERNEL);
 	if (!alloced_buffer)
-		return -ENOMEM;
+		return;
 	test_buffer = alloced_buffer + PAD_SIZE;
 
 	test_basic();
@@ -604,16 +605,8 @@ test_printf_init(void)
 	test_pointer();
 
 	kfree(alloced_buffer);
-
-	if (failed_tests == 0)
-		pr_info("all %u tests passed\n", total_tests);
-	else
-		pr_warn("failed %u out of %u tests\n", failed_tests, total_tests);
-
-	return failed_tests ? -EINVAL : 0;
 }
 
-module_init(test_printf_init);
-
+KSTM_MODULE_LOADERS(test_printf);
 MODULE_AUTHOR("Rasmus Villemoes <linux@rasmusvillemoes.dk>");
 MODULE_LICENSE("GPL");
diff --git a/lib/test_strscpy.c b/lib/test_strscpy.c
new file mode 100644
index 000000000000..a827f94601f5
--- /dev/null
+++ b/lib/test_strscpy.c
@@ -0,0 +1,150 @@
+// SPDX-License-Identifier: GPL-2.0+
+
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
+#include <linux/string.h>
+
+#include "../tools/testing/selftests/kselftest_module.h"
+
+/*
+ * Kernel module for testing 'strscpy' family of functions.
+ */
+
+KSTM_MODULE_GLOBALS();
+
+/*
+ * tc() - Run a specific test case.
+ * @src: Source string, argument to strscpy_pad()
+ * @count: Size of destination buffer, argument to strscpy_pad()
+ * @expected: Expected return value from call to strscpy_pad()
+ * @terminator: 1 if there should be a terminating null byte 0 otherwise.
+ * @chars: Number of characters from the src string expected to be
+ *         written to the dst buffer.
+ * @pad: Number of pad characters expected (in the tail of dst buffer).
+ *       (@pad does not include the null terminator byte.)
+ *
+ * Calls strscpy_pad() and verifies the return value and state of the
+ * destination buffer after the call returns.
+ */
+static int __init tc(char *src, int count, int expected,
+		     int chars, int terminator, int pad)
+{
+	int nr_bytes_poison;
+	int max_expected;
+	int max_count;
+	int written;
+	char buf[6];
+	int index, i;
+	const char POISON = 'z';
+
+	total_tests++;
+
+	if (!src) {
+		pr_err("null source string not supported\n");
+		return -1;
+	}
+
+	memset(buf, POISON, sizeof(buf));
+	/* Future proofing test suite, validate args */
+	max_count = sizeof(buf) - 2; /* Space for null and to verify overflow */
+	max_expected = count - 1;    /* Space for the null */
+	if (count > max_count) {
+		pr_err("count (%d) is too big (%d) ... aborting", count, max_count);
+		return -1;
+	}
+	if (expected > max_expected) {
+		pr_warn("expected (%d) is bigger than can possibly be returned (%d)",
+			expected, max_expected);
+	}
+
+	written = strscpy_pad(buf, src, count);
+	if ((written) != (expected)) {
+		pr_err("%d != %d (written, expected)\n", written, expected);
+		goto fail;
+	}
+
+	if (count && written == -E2BIG) {
+		if (strncmp(buf, src, count - 1) != 0) {
+			pr_err("buffer state invalid for -E2BIG\n");
+			goto fail;
+		}
+		if (buf[count - 1] != '\0') {
+			pr_err("too big string is not null terminated correctly\n");
+			goto fail;
+		}
+	}
+
+	for (i = 0; i < chars; i++) {
+		if (buf[i] != src[i]) {
+			pr_err("buf[i]==%c != src[i]==%c\n", buf[i], src[i]);
+			goto fail;
+		}
+	}
+
+	if (terminator) {
+		if (buf[count - 1] != '\0') {
+			pr_err("string is not null terminated correctly\n");
+			goto fail;
+		}
+	}
+
+	for (i = 0; i < pad; i++) {
+		index = chars + terminator + i;
+		if (buf[index] != '\0') {
+			pr_err("padding missing at index: %d\n", i);
+			goto fail;
+		}
+	}
+
+	nr_bytes_poison = sizeof(buf) - chars - terminator - pad;
+	for (i = 0; i < nr_bytes_poison; i++) {
+		index = sizeof(buf) - 1 - i; /* Check from the end back */
+		if (buf[index] != POISON) {
+			pr_err("poison value missing at index: %d\n", i);
+			goto fail;
+		}
+	}
+
+	return 0;
+fail:
+	failed_tests++;
+	return -1;
+}
+
+static void __init selftest(void)
+{
+	/*
+	 * tc() uses a destination buffer of size 6 and needs at
+	 * least 2 characters spare (one for null and one to check for
+	 * overflow).  This means we should only call tc() with
+	 * strings up to a maximum of 4 characters long and 'count'
+	 * should not exceed 4.  To test with longer strings increase
+	 * the buffer size in tc().
+	 */
+
+	/* tc(src, count, expected, chars, terminator, pad) */
+	KSTM_CHECK_ZERO(tc("a", 0, -E2BIG, 0, 0, 0));
+	KSTM_CHECK_ZERO(tc("", 0, -E2BIG, 0, 0, 0));
+
+	KSTM_CHECK_ZERO(tc("a", 1, -E2BIG, 0, 1, 0));
+	KSTM_CHECK_ZERO(tc("", 1, 0, 0, 1, 0));
+
+	KSTM_CHECK_ZERO(tc("ab", 2, -E2BIG, 1, 1, 0));
+	KSTM_CHECK_ZERO(tc("a", 2, 1, 1, 1, 0));
+	KSTM_CHECK_ZERO(tc("", 2, 0, 0, 1, 1));
+
+	KSTM_CHECK_ZERO(tc("abc", 3, -E2BIG, 2, 1, 0));
+	KSTM_CHECK_ZERO(tc("ab", 3, 2, 2, 1, 0));
+	KSTM_CHECK_ZERO(tc("a", 3, 1, 1, 1, 1));
+	KSTM_CHECK_ZERO(tc("", 3, 0, 0, 1, 2));
+
+	KSTM_CHECK_ZERO(tc("abcd", 4, -E2BIG, 3, 1, 0));
+	KSTM_CHECK_ZERO(tc("abc", 4, 3, 3, 1, 0));
+	KSTM_CHECK_ZERO(tc("ab", 4, 2, 2, 1, 1));
+	KSTM_CHECK_ZERO(tc("a", 4, 1, 1, 1, 2));
+	KSTM_CHECK_ZERO(tc("", 4, 0, 0, 1, 3));
+}
+
+KSTM_MODULE_LOADERS(test_strscpy);
+MODULE_AUTHOR("Tobin C. Harding <tobin@kernel.org>");
+MODULE_LICENSE("GPL");
diff --git a/lib/test_vmalloc.c b/lib/test_vmalloc.c
index 83cdcaa82bf6..f832b095afba 100644
--- a/lib/test_vmalloc.c
+++ b/lib/test_vmalloc.c
@@ -383,14 +383,14 @@ static void shuffle_array(int *arr, int n)
 static int test_func(void *private)
 {
 	struct test_driver *t = private;
-	cpumask_t newmask = CPU_MASK_NONE;
 	int random_array[ARRAY_SIZE(test_case_array)];
 	int index, i, j, ret;
 	ktime_t kt;
 	u64 delta;
 
-	cpumask_set_cpu(t->cpu, &newmask);
-	set_cpus_allowed_ptr(current, &newmask);
+	ret = set_cpus_allowed_ptr(current, cpumask_of(t->cpu));
+	if (ret < 0)
+		pr_err("Failed to set affinity to %d CPU\n", t->cpu);
 
 	for (i = 0; i < ARRAY_SIZE(test_case_array); i++)
 		random_array[i] = i;
diff --git a/lib/ubsan.c b/lib/ubsan.c
index e4162f59a81c..ecc179338094 100644
--- a/lib/ubsan.c
+++ b/lib/ubsan.c
@@ -17,6 +17,7 @@
 #include <linux/kernel.h>
 #include <linux/types.h>
 #include <linux/sched.h>
+#include <linux/uaccess.h>
 
 #include "ubsan.h"
 
@@ -86,11 +87,13 @@ static bool is_inline_int(struct type_descriptor *type)
 	return bits <= inline_bits;
 }
 
-static s_max get_signed_val(struct type_descriptor *type, unsigned long val)
+static s_max get_signed_val(struct type_descriptor *type, void *val)
 {
 	if (is_inline_int(type)) {
 		unsigned extra_bits = sizeof(s_max)*8 - type_bit_width(type);
-		return ((s_max)val) << extra_bits >> extra_bits;
+		unsigned long ulong_val = (unsigned long)val;
+
+		return ((s_max)ulong_val) << extra_bits >> extra_bits;
 	}
 
 	if (type_bit_width(type) == 64)
@@ -99,15 +102,15 @@ static s_max get_signed_val(struct type_descriptor *type, unsigned long val)
 	return *(s_max *)val;
 }
 
-static bool val_is_negative(struct type_descriptor *type, unsigned long val)
+static bool val_is_negative(struct type_descriptor *type, void *val)
 {
 	return type_is_signed(type) && get_signed_val(type, val) < 0;
 }
 
-static u_max get_unsigned_val(struct type_descriptor *type, unsigned long val)
+static u_max get_unsigned_val(struct type_descriptor *type, void *val)
 {
 	if (is_inline_int(type))
-		return val;
+		return (unsigned long)val;
 
 	if (type_bit_width(type) == 64)
 		return *(u64 *)val;
@@ -116,7 +119,7 @@ static u_max get_unsigned_val(struct type_descriptor *type, unsigned long val)
 }
 
 static void val_to_string(char *str, size_t size, struct type_descriptor *type,
-	unsigned long value)
+			void *value)
 {
 	if (type_is_int(type)) {
 		if (type_bit_width(type) == 128) {
@@ -163,8 +166,8 @@ static void ubsan_epilogue(unsigned long *flags)
 	current->in_ubsan--;
 }
 
-static void handle_overflow(struct overflow_data *data, unsigned long lhs,
-			unsigned long rhs, char op)
+static void handle_overflow(struct overflow_data *data, void *lhs,
+			void *rhs, char op)
 {
 
 	struct type_descriptor *type = data->type;
@@ -191,8 +194,7 @@ static void handle_overflow(struct overflow_data *data, unsigned long lhs,
 }
 
 void __ubsan_handle_add_overflow(struct overflow_data *data,
-				unsigned long lhs,
-				unsigned long rhs)
+				void *lhs, void *rhs)
 {
 
 	handle_overflow(data, lhs, rhs, '+');
@@ -200,23 +202,21 @@ void __ubsan_handle_add_overflow(struct overflow_data *data,
 EXPORT_SYMBOL(__ubsan_handle_add_overflow);
 
 void __ubsan_handle_sub_overflow(struct overflow_data *data,
-				unsigned long lhs,
-				unsigned long rhs)
+				void *lhs, void *rhs)
 {
 	handle_overflow(data, lhs, rhs, '-');
 }
 EXPORT_SYMBOL(__ubsan_handle_sub_overflow);
 
 void __ubsan_handle_mul_overflow(struct overflow_data *data,
-				unsigned long lhs,
-				unsigned long rhs)
+				void *lhs, void *rhs)
 {
 	handle_overflow(data, lhs, rhs, '*');
 }
 EXPORT_SYMBOL(__ubsan_handle_mul_overflow);
 
 void __ubsan_handle_negate_overflow(struct overflow_data *data,
-				unsigned long old_val)
+				void *old_val)
 {
 	unsigned long flags;
 	char old_val_str[VALUE_LENGTH];
@@ -237,8 +237,7 @@ EXPORT_SYMBOL(__ubsan_handle_negate_overflow);
 
 
 void __ubsan_handle_divrem_overflow(struct overflow_data *data,
-				unsigned long lhs,
-				unsigned long rhs)
+				void *lhs, void *rhs)
 {
 	unsigned long flags;
 	char rhs_val_str[VALUE_LENGTH];
@@ -313,6 +312,7 @@ static void handle_object_size_mismatch(struct type_mismatch_data_common *data,
 static void ubsan_type_mismatch_common(struct type_mismatch_data_common *data,
 				unsigned long ptr)
 {
+	unsigned long flags = user_access_save();
 
 	if (!ptr)
 		handle_null_ptr_deref(data);
@@ -320,10 +320,12 @@ static void ubsan_type_mismatch_common(struct type_mismatch_data_common *data,
 		handle_misaligned_access(data, ptr);
 	else
 		handle_object_size_mismatch(data, ptr);
+
+	user_access_restore(flags);
 }
 
 void __ubsan_handle_type_mismatch(struct type_mismatch_data *data,
-				unsigned long ptr)
+				void *ptr)
 {
 	struct type_mismatch_data_common common_data = {
 		.location = &data->location,
@@ -332,12 +334,12 @@ void __ubsan_handle_type_mismatch(struct type_mismatch_data *data,
 		.type_check_kind = data->type_check_kind
 	};
 
-	ubsan_type_mismatch_common(&common_data, ptr);
+	ubsan_type_mismatch_common(&common_data, (unsigned long)ptr);
 }
 EXPORT_SYMBOL(__ubsan_handle_type_mismatch);
 
 void __ubsan_handle_type_mismatch_v1(struct type_mismatch_data_v1 *data,
-				unsigned long ptr)
+				void *ptr)
 {
 
 	struct type_mismatch_data_common common_data = {
@@ -347,30 +349,11 @@ void __ubsan_handle_type_mismatch_v1(struct type_mismatch_data_v1 *data,
 		.type_check_kind = data->type_check_kind
 	};
 
-	ubsan_type_mismatch_common(&common_data, ptr);
+	ubsan_type_mismatch_common(&common_data, (unsigned long)ptr);
 }
 EXPORT_SYMBOL(__ubsan_handle_type_mismatch_v1);
 
-void __ubsan_handle_vla_bound_not_positive(struct vla_bound_data *data,
-					unsigned long bound)
-{
-	unsigned long flags;
-	char bound_str[VALUE_LENGTH];
-
-	if (suppress_report(&data->location))
-		return;
-
-	ubsan_prologue(&data->location, &flags);
-
-	val_to_string(bound_str, sizeof(bound_str), data->type, bound);
-	pr_err("variable length array bound value %s <= 0\n", bound_str);
-
-	ubsan_epilogue(&flags);
-}
-EXPORT_SYMBOL(__ubsan_handle_vla_bound_not_positive);
-
-void __ubsan_handle_out_of_bounds(struct out_of_bounds_data *data,
-				unsigned long index)
+void __ubsan_handle_out_of_bounds(struct out_of_bounds_data *data, void *index)
 {
 	unsigned long flags;
 	char index_str[VALUE_LENGTH];
@@ -388,7 +371,7 @@ void __ubsan_handle_out_of_bounds(struct out_of_bounds_data *data,
 EXPORT_SYMBOL(__ubsan_handle_out_of_bounds);
 
 void __ubsan_handle_shift_out_of_bounds(struct shift_out_of_bounds_data *data,
-					unsigned long lhs, unsigned long rhs)
+					void *lhs, void *rhs)
 {
 	unsigned long flags;
 	struct type_descriptor *rhs_type = data->rhs_type;
@@ -439,7 +422,7 @@ void __ubsan_handle_builtin_unreachable(struct unreachable_data *data)
 EXPORT_SYMBOL(__ubsan_handle_builtin_unreachable);
 
 void __ubsan_handle_load_invalid_value(struct invalid_value_data *data,
-				unsigned long val)
+				void *val)
 {
 	unsigned long flags;
 	char val_str[VALUE_LENGTH];
diff --git a/lib/ubsan.h b/lib/ubsan.h
index f4d8d0bd4016..b8fa83864467 100644
--- a/lib/ubsan.h
+++ b/lib/ubsan.h
@@ -57,11 +57,6 @@ struct nonnull_arg_data {
 	int arg_index;
 };
 
-struct vla_bound_data {
-	struct source_location location;
-	struct type_descriptor *type;
-};
-
 struct out_of_bounds_data {
 	struct source_location location;
 	struct type_descriptor *array_type;
diff --git a/mm/compaction.c b/mm/compaction.c
index f171a83707ce..3319e0872d01 100644
--- a/mm/compaction.c
+++ b/mm/compaction.c
@@ -242,6 +242,7 @@ __reset_isolation_pfn(struct zone *zone, unsigned long pfn, bool check_source,
 							bool check_target)
 {
 	struct page *page = pfn_to_online_page(pfn);
+	struct page *block_page;
 	struct page *end_page;
 	unsigned long block_pfn;
 
@@ -267,20 +268,26 @@ __reset_isolation_pfn(struct zone *zone, unsigned long pfn, bool check_source,
 	    get_pageblock_migratetype(page) != MIGRATE_MOVABLE)
 		return false;
 
+	/* Ensure the start of the pageblock or zone is online and valid */
+	block_pfn = pageblock_start_pfn(pfn);
+	block_page = pfn_to_online_page(max(block_pfn, zone->zone_start_pfn));
+	if (block_page) {
+		page = block_page;
+		pfn = block_pfn;
+	}
+
+	/* Ensure the end of the pageblock or zone is online and valid */
+	block_pfn += pageblock_nr_pages;
+	block_pfn = min(block_pfn, zone_end_pfn(zone) - 1);
+	end_page = pfn_to_online_page(block_pfn);
+	if (!end_page)
+		return false;
+
 	/*
 	 * Only clear the hint if a sample indicates there is either a
 	 * free page or an LRU page in the block. One or other condition
 	 * is necessary for the block to be a migration source/target.
 	 */
-	block_pfn = pageblock_start_pfn(pfn);
-	pfn = max(block_pfn, zone->zone_start_pfn);
-	page = pfn_to_page(pfn);
-	if (zone != page_zone(page))
-		return false;
-	pfn = block_pfn + pageblock_nr_pages;
-	pfn = min(pfn, zone_end_pfn(zone));
-	end_page = pfn_to_page(pfn);
-
 	do {
 		if (pfn_valid_within(pfn)) {
 			if (check_source && PageLRU(page)) {
@@ -309,7 +316,7 @@ __reset_isolation_pfn(struct zone *zone, unsigned long pfn, bool check_source,
 static void __reset_isolation_suitable(struct zone *zone)
 {
 	unsigned long migrate_pfn = zone->zone_start_pfn;
-	unsigned long free_pfn = zone_end_pfn(zone);
+	unsigned long free_pfn = zone_end_pfn(zone) - 1;
 	unsigned long reset_migrate = free_pfn;
 	unsigned long reset_free = migrate_pfn;
 	bool source_set = false;
@@ -1363,7 +1370,7 @@ fast_isolate_freepages(struct compact_control *cc)
 				count_compact_events(COMPACTISOLATED, nr_isolated);
 			} else {
 				/* If isolation fails, abort the search */
-				order = -1;
+				order = cc->search_order + 1;
 				page = NULL;
 			}
 		}
diff --git a/mm/debug.c b/mm/debug.c
index c0b31b6c3877..eee9c221280c 100644
--- a/mm/debug.c
+++ b/mm/debug.c
@@ -79,7 +79,7 @@ void __dump_page(struct page *page, const char *reason)
 		pr_warn("ksm ");
 	else if (mapping) {
 		pr_warn("%ps ", mapping->a_ops);
-		if (mapping->host->i_dentry.first) {
+		if (mapping->host && mapping->host->i_dentry.first) {
 			struct dentry *dentry;
 			dentry = container_of(mapping->host->i_dentry.first, struct dentry, d_u.d_alias);
 			pr_warn("name:\"%pd\" ", dentry);
@@ -168,7 +168,7 @@ void dump_mm(const struct mm_struct *mm)
 		mm_pgtables_bytes(mm),
 		mm->map_count,
 		mm->hiwater_rss, mm->hiwater_vm, mm->total_vm, mm->locked_vm,
-		atomic64_read(&mm->pinned_vm),
+		(u64)atomic64_read(&mm->pinned_vm),
 		mm->data_vm, mm->exec_vm, mm->stack_vm,
 		mm->start_code, mm->end_code, mm->start_data, mm->end_data,
 		mm->start_brk, mm->brk, mm->start_stack,
diff --git a/mm/gup.c b/mm/gup.c
index f84e22685aaa..91819b8ad9cc 100644
--- a/mm/gup.c
+++ b/mm/gup.c
@@ -160,8 +160,12 @@ retry:
 		goto retry;
 	}
 
-	if (flags & FOLL_GET)
-		get_page(page);
+	if (flags & FOLL_GET) {
+		if (unlikely(!try_get_page(page))) {
+			page = ERR_PTR(-ENOMEM);
+			goto out;
+		}
+	}
 	if (flags & FOLL_TOUCH) {
 		if ((flags & FOLL_WRITE) &&
 		    !pte_dirty(pte) && !PageDirty(page))
@@ -298,7 +302,10 @@ retry_locked:
 			if (pmd_trans_unstable(pmd))
 				ret = -EBUSY;
 		} else {
-			get_page(page);
+			if (unlikely(!try_get_page(page))) {
+				spin_unlock(ptl);
+				return ERR_PTR(-ENOMEM);
+			}
 			spin_unlock(ptl);
 			lock_page(page);
 			ret = split_huge_page(page);
@@ -500,7 +507,10 @@ static int get_gate_page(struct mm_struct *mm, unsigned long address,
 		if (is_device_public_page(*page))
 			goto unmap;
 	}
-	get_page(*page);
+	if (unlikely(!try_get_page(*page))) {
+		ret = -ENOMEM;
+		goto unmap;
+	}
 out:
 	ret = 0;
 unmap:
@@ -1545,6 +1555,20 @@ static void undo_dev_pagemap(int *nr, int nr_start, struct page **pages)
 	}
 }
 
+/*
+ * Return the compund head page with ref appropriately incremented,
+ * or NULL if that failed.
+ */
+static inline struct page *try_get_compound_head(struct page *page, int refs)
+{
+	struct page *head = compound_head(page);
+	if (WARN_ON_ONCE(page_ref_count(head) < 0))
+		return NULL;
+	if (unlikely(!page_cache_add_speculative(head, refs)))
+		return NULL;
+	return head;
+}
+
 #ifdef CONFIG_ARCH_HAS_PTE_SPECIAL
 static int gup_pte_range(pmd_t pmd, unsigned long addr, unsigned long end,
 			 int write, struct page **pages, int *nr)
@@ -1579,9 +1603,9 @@ static int gup_pte_range(pmd_t pmd, unsigned long addr, unsigned long end,
 
 		VM_BUG_ON(!pfn_valid(pte_pfn(pte)));
 		page = pte_page(pte);
-		head = compound_head(page);
 
-		if (!page_cache_get_speculative(head))
+		head = try_get_compound_head(page, 1);
+		if (!head)
 			goto pte_unmap;
 
 		if (unlikely(pte_val(pte) != pte_val(*ptep))) {
@@ -1720,8 +1744,8 @@ static int gup_huge_pmd(pmd_t orig, pmd_t *pmdp, unsigned long addr,
 		refs++;
 	} while (addr += PAGE_SIZE, addr != end);
 
-	head = compound_head(pmd_page(orig));
-	if (!page_cache_add_speculative(head, refs)) {
+	head = try_get_compound_head(pmd_page(orig), refs);
+	if (!head) {
 		*nr -= refs;
 		return 0;
 	}
@@ -1758,8 +1782,8 @@ static int gup_huge_pud(pud_t orig, pud_t *pudp, unsigned long addr,
 		refs++;
 	} while (addr += PAGE_SIZE, addr != end);
 
-	head = compound_head(pud_page(orig));
-	if (!page_cache_add_speculative(head, refs)) {
+	head = try_get_compound_head(pud_page(orig), refs);
+	if (!head) {
 		*nr -= refs;
 		return 0;
 	}
@@ -1795,8 +1819,8 @@ static int gup_huge_pgd(pgd_t orig, pgd_t *pgdp, unsigned long addr,
 		refs++;
 	} while (addr += PAGE_SIZE, addr != end);
 
-	head = compound_head(pgd_page(orig));
-	if (!page_cache_add_speculative(head, refs)) {
+	head = try_get_compound_head(pgd_page(orig), refs);
+	if (!head) {
 		*nr -= refs;
 		return 0;
 	}
diff --git a/mm/huge_memory.c b/mm/huge_memory.c
index 404acdcd0455..b6a34b32d8ac 100644
--- a/mm/huge_memory.c
+++ b/mm/huge_memory.c
@@ -755,6 +755,21 @@ static void insert_pfn_pmd(struct vm_area_struct *vma, unsigned long addr,
 	spinlock_t *ptl;
 
 	ptl = pmd_lock(mm, pmd);
+	if (!pmd_none(*pmd)) {
+		if (write) {
+			if (pmd_pfn(*pmd) != pfn_t_to_pfn(pfn)) {
+				WARN_ON_ONCE(!is_huge_zero_pmd(*pmd));
+				goto out_unlock;
+			}
+			entry = pmd_mkyoung(*pmd);
+			entry = maybe_pmd_mkwrite(pmd_mkdirty(entry), vma);
+			if (pmdp_set_access_flags(vma, addr, pmd, entry, 1))
+				update_mmu_cache_pmd(vma, addr, pmd);
+		}
+
+		goto out_unlock;
+	}
+
 	entry = pmd_mkhuge(pfn_t_pmd(pfn, prot));
 	if (pfn_t_devmap(pfn))
 		entry = pmd_mkdevmap(entry);
@@ -766,11 +781,16 @@ static void insert_pfn_pmd(struct vm_area_struct *vma, unsigned long addr,
 	if (pgtable) {
 		pgtable_trans_huge_deposit(mm, pmd, pgtable);
 		mm_inc_nr_ptes(mm);
+		pgtable = NULL;
 	}
 
 	set_pmd_at(mm, addr, pmd, entry);
 	update_mmu_cache_pmd(vma, addr, pmd);
+
+out_unlock:
 	spin_unlock(ptl);
+	if (pgtable)
+		pte_free(mm, pgtable);
 }
 
 vm_fault_t vmf_insert_pfn_pmd(struct vm_area_struct *vma, unsigned long addr,
@@ -821,6 +841,20 @@ static void insert_pfn_pud(struct vm_area_struct *vma, unsigned long addr,
 	spinlock_t *ptl;
 
 	ptl = pud_lock(mm, pud);
+	if (!pud_none(*pud)) {
+		if (write) {
+			if (pud_pfn(*pud) != pfn_t_to_pfn(pfn)) {
+				WARN_ON_ONCE(!is_huge_zero_pud(*pud));
+				goto out_unlock;
+			}
+			entry = pud_mkyoung(*pud);
+			entry = maybe_pud_mkwrite(pud_mkdirty(entry), vma);
+			if (pudp_set_access_flags(vma, addr, pud, entry, 1))
+				update_mmu_cache_pud(vma, addr, pud);
+		}
+		goto out_unlock;
+	}
+
 	entry = pud_mkhuge(pfn_t_pud(pfn, prot));
 	if (pfn_t_devmap(pfn))
 		entry = pud_mkdevmap(entry);
@@ -830,6 +864,8 @@ static void insert_pfn_pud(struct vm_area_struct *vma, unsigned long addr,
 	}
 	set_pud_at(mm, addr, pud, entry);
 	update_mmu_cache_pud(vma, addr, pud);
+
+out_unlock:
 	spin_unlock(ptl);
 }
 
@@ -1641,7 +1677,7 @@ bool madvise_free_huge_pmd(struct mmu_gather *tlb, struct vm_area_struct *vma,
 	struct mm_struct *mm = tlb->mm;
 	bool ret = false;
 
-	tlb_remove_check_page_size_change(tlb, HPAGE_PMD_SIZE);
+	tlb_change_page_size(tlb, HPAGE_PMD_SIZE);
 
 	ptl = pmd_trans_huge_lock(pmd, vma);
 	if (!ptl)
@@ -1717,7 +1753,7 @@ int zap_huge_pmd(struct mmu_gather *tlb, struct vm_area_struct *vma,
 	pmd_t orig_pmd;
 	spinlock_t *ptl;
 
-	tlb_remove_check_page_size_change(tlb, HPAGE_PMD_SIZE);
+	tlb_change_page_size(tlb, HPAGE_PMD_SIZE);
 
 	ptl = __pmd_trans_huge_lock(pmd, vma);
 	if (!ptl)
diff --git a/mm/hugetlb.c b/mm/hugetlb.c
index 97b1e0290c66..641cedfc8c0f 100644
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -3353,7 +3353,7 @@ void __unmap_hugepage_range(struct mmu_gather *tlb, struct vm_area_struct *vma,
 	 * This is a hugetlb vma, all the pte entries should point
 	 * to huge page.
 	 */
-	tlb_remove_check_page_size_change(tlb, sz);
+	tlb_change_page_size(tlb, sz);
 	tlb_start_vma(tlb, vma);
 
 	/*
@@ -4299,6 +4299,19 @@ long follow_hugetlb_page(struct mm_struct *mm, struct vm_area_struct *vma,
 
 		pfn_offset = (vaddr & ~huge_page_mask(h)) >> PAGE_SHIFT;
 		page = pte_page(huge_ptep_get(pte));
+
+		/*
+		 * Instead of doing 'try_get_page()' below in the same_page
+		 * loop, just check the count once here.
+		 */
+		if (unlikely(page_count(page) <= 0)) {
+			if (pages) {
+				spin_unlock(ptl);
+				remainder = 0;
+				err = -ENOMEM;
+				break;
+			}
+		}
 same_page:
 		if (pages) {
 			pages[i] = mem_map_offset(page, pfn_offset);
diff --git a/mm/kasan/Makefile b/mm/kasan/Makefile
index 5d1065efbd47..08b43de2383b 100644
--- a/mm/kasan/Makefile
+++ b/mm/kasan/Makefile
@@ -2,18 +2,21 @@
 KASAN_SANITIZE := n
 UBSAN_SANITIZE_common.o := n
 UBSAN_SANITIZE_generic.o := n
+UBSAN_SANITIZE_generic_report.o := n
 UBSAN_SANITIZE_tags.o := n
 KCOV_INSTRUMENT := n
 
-CFLAGS_REMOVE_common.o = -pg
-CFLAGS_REMOVE_generic.o = -pg
-CFLAGS_REMOVE_tags.o = -pg
+CFLAGS_REMOVE_common.o = $(CC_FLAGS_FTRACE)
+CFLAGS_REMOVE_generic.o = $(CC_FLAGS_FTRACE)
+CFLAGS_REMOVE_generic_report.o = $(CC_FLAGS_FTRACE)
+CFLAGS_REMOVE_tags.o = $(CC_FLAGS_FTRACE)
 
 # Function splitter causes unnecessary splits in __asan_load1/__asan_store1
 # see: https://gcc.gnu.org/bugzilla/show_bug.cgi?id=63533
 
 CFLAGS_common.o := $(call cc-option, -fno-conserve-stack -fno-stack-protector)
 CFLAGS_generic.o := $(call cc-option, -fno-conserve-stack -fno-stack-protector)
+CFLAGS_generic_report.o := $(call cc-option, -fno-conserve-stack -fno-stack-protector)
 CFLAGS_tags.o := $(call cc-option, -fno-conserve-stack -fno-stack-protector)
 
 obj-$(CONFIG_KASAN) := common.o init.o report.o
diff --git a/mm/kasan/common.c b/mm/kasan/common.c
index 80bbe62b16cd..36afcf64e016 100644
--- a/mm/kasan/common.c
+++ b/mm/kasan/common.c
@@ -36,6 +36,7 @@
 #include <linux/types.h>
 #include <linux/vmalloc.h>
 #include <linux/bug.h>
+#include <linux/uaccess.h>
 
 #include "kasan.h"
 #include "../slab.h"
@@ -48,37 +49,28 @@ static inline int in_irqentry_text(unsigned long ptr)
 		 ptr < (unsigned long)&__softirqentry_text_end);
 }
 
-static inline void filter_irq_stacks(struct stack_trace *trace)
+static inline unsigned int filter_irq_stacks(unsigned long *entries,
+					     unsigned int nr_entries)
 {
-	int i;
+	unsigned int i;
 
-	if (!trace->nr_entries)
-		return;
-	for (i = 0; i < trace->nr_entries; i++)
-		if (in_irqentry_text(trace->entries[i])) {
+	for (i = 0; i < nr_entries; i++) {
+		if (in_irqentry_text(entries[i])) {
 			/* Include the irqentry function into the stack. */
-			trace->nr_entries = i + 1;
-			break;
+			return i + 1;
 		}
+	}
+	return nr_entries;
 }
 
 static inline depot_stack_handle_t save_stack(gfp_t flags)
 {
 	unsigned long entries[KASAN_STACK_DEPTH];
-	struct stack_trace trace = {
-		.nr_entries = 0,
-		.entries = entries,
-		.max_entries = KASAN_STACK_DEPTH,
-		.skip = 0
-	};
+	unsigned int nr_entries;
 
-	save_stack_trace(&trace);
-	filter_irq_stacks(&trace);
-	if (trace.nr_entries != 0 &&
-	    trace.entries[trace.nr_entries-1] == ULONG_MAX)
-		trace.nr_entries--;
-
-	return depot_save_stack(&trace, flags);
+	nr_entries = stack_trace_save(entries, ARRAY_SIZE(entries), 0);
+	nr_entries = filter_irq_stacks(entries, nr_entries);
+	return stack_depot_save(entries, nr_entries, flags);
 }
 
 static inline void set_track(struct kasan_track *track, gfp_t flags)
@@ -614,6 +606,15 @@ void kasan_free_shadow(const struct vm_struct *vm)
 		vfree(kasan_mem_to_shadow(vm->addr));
 }
 
+extern void __kasan_report(unsigned long addr, size_t size, bool is_write, unsigned long ip);
+
+void kasan_report(unsigned long addr, size_t size, bool is_write, unsigned long ip)
+{
+	unsigned long flags = user_access_save();
+	__kasan_report(addr, size, is_write, ip);
+	user_access_restore(flags);
+}
+
 #ifdef CONFIG_MEMORY_HOTPLUG
 static bool shadow_mapped(unsigned long addr)
 {
diff --git a/mm/kasan/kasan.h b/mm/kasan/kasan.h
index 3e0c11f7d7a1..3ce956efa0cb 100644
--- a/mm/kasan/kasan.h
+++ b/mm/kasan/kasan.h
@@ -163,7 +163,10 @@ static inline u8 random_tag(void)
 #endif
 
 #ifndef arch_kasan_set_tag
-#define arch_kasan_set_tag(addr, tag)	((void *)(addr))
+static inline const void *arch_kasan_set_tag(const void *addr, u8 tag)
+{
+	return addr;
+}
 #endif
 #ifndef arch_kasan_reset_tag
 #define arch_kasan_reset_tag(addr)	((void *)(addr))
diff --git a/mm/kasan/report.c b/mm/kasan/report.c
index ca9418fe9232..03a443579386 100644
--- a/mm/kasan/report.c
+++ b/mm/kasan/report.c
@@ -100,10 +100,11 @@ static void print_track(struct kasan_track *track, const char *prefix)
 {
 	pr_err("%s by task %u:\n", prefix, track->pid);
 	if (track->stack) {
-		struct stack_trace trace;
+		unsigned long *entries;
+		unsigned int nr_entries;
 
-		depot_fetch_stack(track->stack, &trace);
-		print_stack_trace(&trace, 0);
+		nr_entries = stack_depot_fetch(track->stack, &entries);
+		stack_trace_print(entries, nr_entries, 0);
 	} else {
 		pr_err("(stack is not available)\n");
 	}
@@ -281,8 +282,7 @@ void kasan_report_invalid_free(void *object, unsigned long ip)
 	end_report(&flags);
 }
 
-void kasan_report(unsigned long addr, size_t size,
-		bool is_write, unsigned long ip)
+void __kasan_report(unsigned long addr, size_t size, bool is_write, unsigned long ip)
 {
 	struct kasan_access_info info;
 	void *tagged_addr;
diff --git a/mm/kmemleak.c b/mm/kmemleak.c
index 707fa5579f66..e57bf810f798 100644
--- a/mm/kmemleak.c
+++ b/mm/kmemleak.c
@@ -410,11 +410,6 @@ static void print_unreferenced(struct seq_file *seq,
  */
 static void dump_object_info(struct kmemleak_object *object)
 {
-	struct stack_trace trace;
-
-	trace.nr_entries = object->trace_len;
-	trace.entries = object->trace;
-
 	pr_notice("Object 0x%08lx (size %zu):\n",
 		  object->pointer, object->size);
 	pr_notice("  comm \"%s\", pid %d, jiffies %lu\n",
@@ -424,7 +419,7 @@ static void dump_object_info(struct kmemleak_object *object)
 	pr_notice("  flags = 0x%x\n", object->flags);
 	pr_notice("  checksum = %u\n", object->checksum);
 	pr_notice("  backtrace:\n");
-	print_stack_trace(&trace, 4);
+	stack_trace_print(object->trace, object->trace_len, 4);
 }
 
 /*
@@ -553,15 +548,7 @@ static struct kmemleak_object *find_and_remove_object(unsigned long ptr, int ali
  */
 static int __save_stack_trace(unsigned long *trace)
 {
-	struct stack_trace stack_trace;
-
-	stack_trace.max_entries = MAX_TRACE;
-	stack_trace.nr_entries = 0;
-	stack_trace.entries = trace;
-	stack_trace.skip = 2;
-	save_stack_trace(&stack_trace);
-
-	return stack_trace.nr_entries;
+	return stack_trace_save(trace, MAX_TRACE, 2);
 }
 
 /*
@@ -1401,6 +1388,7 @@ static void scan_block(void *_start, void *_end,
 /*
  * Scan a large memory block in MAX_SCAN_SIZE chunks to reduce the latency.
  */
+#ifdef CONFIG_SMP
 static void scan_large_block(void *start, void *end)
 {
 	void *next;
@@ -1412,6 +1400,7 @@ static void scan_large_block(void *start, void *end)
 		cond_resched();
 	}
 }
+#endif
 
 /*
  * Scan a memory block corresponding to a kmemleak_object. A condition is
@@ -1529,11 +1518,6 @@ static void kmemleak_scan(void)
 	}
 	rcu_read_unlock();
 
-	/* data/bss scanning */
-	scan_large_block(_sdata, _edata);
-	scan_large_block(__bss_start, __bss_stop);
-	scan_large_block(__start_ro_after_init, __end_ro_after_init);
-
 #ifdef CONFIG_SMP
 	/* per-cpu sections scanning */
 	for_each_possible_cpu(i)
@@ -2024,13 +2008,8 @@ early_param("kmemleak", kmemleak_boot_config);
 
 static void __init print_log_trace(struct early_log *log)
 {
-	struct stack_trace trace;
-
-	trace.nr_entries = log->trace_len;
-	trace.entries = log->trace;
-
 	pr_notice("Early log backtrace:\n");
-	print_stack_trace(&trace, 2);
+	stack_trace_print(log->trace, log->trace_len, 2);
 }
 
 /*
@@ -2071,6 +2050,17 @@ void __init kmemleak_init(void)
 	}
 	local_irq_restore(flags);
 
+	/* register the data/bss sections */
+	create_object((unsigned long)_sdata, _edata - _sdata,
+		      KMEMLEAK_GREY, GFP_ATOMIC);
+	create_object((unsigned long)__bss_start, __bss_stop - __bss_start,
+		      KMEMLEAK_GREY, GFP_ATOMIC);
+	/* only register .data..ro_after_init if not within .data */
+	if (__start_ro_after_init < _sdata || __end_ro_after_init > _edata)
+		create_object((unsigned long)__start_ro_after_init,
+			      __end_ro_after_init - __start_ro_after_init,
+			      KMEMLEAK_GREY, GFP_ATOMIC);
+
 	/*
 	 * This is the point where tracking allocations is safe. Automatic
 	 * scanning is started during the late initcall. Add the early logged
diff --git a/mm/madvise.c b/mm/madvise.c
index 21a7881a2db4..bb3a4554d5d5 100644
--- a/mm/madvise.c
+++ b/mm/madvise.c
@@ -328,7 +328,7 @@ static int madvise_free_pte_range(pmd_t *pmd, unsigned long addr,
 	if (pmd_trans_unstable(pmd))
 		return 0;
 
-	tlb_remove_check_page_size_change(tlb, PAGE_SIZE);
+	tlb_change_page_size(tlb, PAGE_SIZE);
 	orig_pte = pte = pte_offset_map_lock(mm, pmd, addr, &ptl);
 	flush_tlb_batched_pending(mm);
 	arch_enter_lazy_mmu_mode();
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index 532e0e2a4817..81a0d3914ec9 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -3882,6 +3882,22 @@ struct wb_domain *mem_cgroup_wb_domain(struct bdi_writeback *wb)
 	return &memcg->cgwb_domain;
 }
 
+/*
+ * idx can be of type enum memcg_stat_item or node_stat_item.
+ * Keep in sync with memcg_exact_page().
+ */
+static unsigned long memcg_exact_page_state(struct mem_cgroup *memcg, int idx)
+{
+	long x = atomic_long_read(&memcg->stat[idx]);
+	int cpu;
+
+	for_each_online_cpu(cpu)
+		x += per_cpu_ptr(memcg->stat_cpu, cpu)->count[idx];
+	if (x < 0)
+		x = 0;
+	return x;
+}
+
 /**
  * mem_cgroup_wb_stats - retrieve writeback related stats from its memcg
  * @wb: bdi_writeback in question
@@ -3907,10 +3923,10 @@ void mem_cgroup_wb_stats(struct bdi_writeback *wb, unsigned long *pfilepages,
 	struct mem_cgroup *memcg = mem_cgroup_from_css(wb->memcg_css);
 	struct mem_cgroup *parent;
 
-	*pdirty = memcg_page_state(memcg, NR_FILE_DIRTY);
+	*pdirty = memcg_exact_page_state(memcg, NR_FILE_DIRTY);
 
 	/* this should eventually include NR_UNSTABLE_NFS */
-	*pwriteback = memcg_page_state(memcg, NR_WRITEBACK);
+	*pwriteback = memcg_exact_page_state(memcg, NR_WRITEBACK);
 	*pfilepages = mem_cgroup_nr_lru_pages(memcg, (1 << LRU_INACTIVE_FILE) |
 						     (1 << LRU_ACTIVE_FILE));
 	*pheadroom = PAGE_COUNTER_MAX;
diff --git a/mm/memory.c b/mm/memory.c
index 47fe250307c7..36aac6844662 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -356,7 +356,7 @@ void free_pgd_range(struct mmu_gather *tlb,
 	 * We add page table cache pages with PAGE_SIZE,
 	 * (see pte_free_tlb()), flush the tlb if we need
 	 */
-	tlb_remove_check_page_size_change(tlb, PAGE_SIZE);
+	tlb_change_page_size(tlb, PAGE_SIZE);
 	pgd = pgd_offset(tlb->mm, addr);
 	do {
 		next = pgd_addr_end(addr, end);
@@ -1046,7 +1046,7 @@ static unsigned long zap_pte_range(struct mmu_gather *tlb,
 	pte_t *pte;
 	swp_entry_t entry;
 
-	tlb_remove_check_page_size_change(tlb, PAGE_SIZE);
+	tlb_change_page_size(tlb, PAGE_SIZE);
 again:
 	init_rss_vec(rss);
 	start_pte = pte_offset_map_lock(mm, pmd, addr, &ptl);
@@ -1155,7 +1155,7 @@ again:
 	 */
 	if (force_flush) {
 		force_flush = 0;
-		tlb_flush_mmu_free(tlb);
+		tlb_flush_mmu(tlb);
 		if (addr != end)
 			goto again;
 	}
@@ -1549,10 +1549,12 @@ static vm_fault_t insert_pfn(struct vm_area_struct *vma, unsigned long addr,
 				WARN_ON_ONCE(!is_zero_pfn(pte_pfn(*pte)));
 				goto out_unlock;
 			}
-			entry = *pte;
-			goto out_mkwrite;
-		} else
-			goto out_unlock;
+			entry = pte_mkyoung(*pte);
+			entry = maybe_mkwrite(pte_mkdirty(entry), vma);
+			if (ptep_set_access_flags(vma, addr, pte, entry, 1))
+				update_mmu_cache(vma, addr, pte);
+		}
+		goto out_unlock;
 	}
 
 	/* Ok, finally just insert the thing.. */
@@ -1561,7 +1563,6 @@ static vm_fault_t insert_pfn(struct vm_area_struct *vma, unsigned long addr,
 	else
 		entry = pte_mkspecial(pfn_t_pte(pfn, prot));
 
-out_mkwrite:
 	if (mkwrite) {
 		entry = pte_mkyoung(entry);
 		entry = maybe_mkwrite(pte_mkdirty(entry), vma);
diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c
index f767582af4f8..b236069ff0d8 100644
--- a/mm/memory_hotplug.c
+++ b/mm/memory_hotplug.c
@@ -874,6 +874,7 @@ int __ref online_pages(unsigned long pfn, unsigned long nr_pages, int online_typ
 	 */
 	mem = find_memory_block(__pfn_to_section(pfn));
 	nid = mem->nid;
+	put_device(&mem->dev);
 
 	/* associate pfn range with the zone */
 	zone = move_pfn_range(online_type, nid, pfn, nr_pages);
@@ -1576,7 +1577,7 @@ static int __ref __offline_pages(unsigned long start_pfn,
 {
 	unsigned long pfn, nr_pages;
 	long offlined_pages;
-	int ret, node;
+	int ret, node, nr_isolate_pageblock;
 	unsigned long flags;
 	unsigned long valid_start, valid_end;
 	struct zone *zone;
@@ -1602,10 +1603,11 @@ static int __ref __offline_pages(unsigned long start_pfn,
 	ret = start_isolate_page_range(start_pfn, end_pfn,
 				       MIGRATE_MOVABLE,
 				       SKIP_HWPOISON | REPORT_FAILURE);
-	if (ret) {
+	if (ret < 0) {
 		reason = "failure to isolate range";
 		goto failed_removal;
 	}
+	nr_isolate_pageblock = ret;
 
 	arg.start_pfn = start_pfn;
 	arg.nr_pages = nr_pages;
@@ -1657,8 +1659,16 @@ static int __ref __offline_pages(unsigned long start_pfn,
 	/* Ok, all of our target is isolated.
 	   We cannot do rollback at this point. */
 	offline_isolated_pages(start_pfn, end_pfn);
-	/* reset pagetype flags and makes migrate type to be MOVABLE */
-	undo_isolate_page_range(start_pfn, end_pfn, MIGRATE_MOVABLE);
+
+	/*
+	 * Onlining will reset pagetype flags and makes migrate type
+	 * MOVABLE, so just need to decrease the number of isolated
+	 * pageblocks zone counter here.
+	 */
+	spin_lock_irqsave(&zone->lock, flags);
+	zone->nr_isolate_pageblock -= nr_isolate_pageblock;
+	spin_unlock_irqrestore(&zone->lock, flags);
+
 	/* removal success */
 	adjust_managed_page_count(pfn_to_page(start_pfn), -offlined_pages);
 	zone->present_pages -= offlined_pages;
@@ -1690,12 +1700,12 @@ static int __ref __offline_pages(unsigned long start_pfn,
 
 failed_removal_isolated:
 	undo_isolate_page_range(start_pfn, end_pfn, MIGRATE_MOVABLE);
+	memory_notify(MEM_CANCEL_OFFLINE, &arg);
 failed_removal:
 	pr_debug("memory offlining [mem %#010llx-%#010llx] failed due to %s\n",
 		 (unsigned long long) start_pfn << PAGE_SHIFT,
 		 ((unsigned long long) end_pfn << PAGE_SHIFT) - 1,
 		 reason);
-	memory_notify(MEM_CANCEL_OFFLINE, &arg);
 	/* pushback to free area */
 	mem_hotplug_done();
 	return ret;
diff --git a/mm/mempolicy.c b/mm/mempolicy.c
index af171ccb56a2..2219e747df49 100644
--- a/mm/mempolicy.c
+++ b/mm/mempolicy.c
@@ -428,6 +428,13 @@ static inline bool queue_pages_required(struct page *page,
 	return node_isset(nid, *qp->nmask) == !(flags & MPOL_MF_INVERT);
 }
 
+/*
+ * queue_pages_pmd() has three possible return values:
+ * 1 - pages are placed on the right node or queued successfully.
+ * 0 - THP was split.
+ * -EIO - is migration entry or MPOL_MF_STRICT was specified and an existing
+ *        page was already on a node that does not follow the policy.
+ */
 static int queue_pages_pmd(pmd_t *pmd, spinlock_t *ptl, unsigned long addr,
 				unsigned long end, struct mm_walk *walk)
 {
@@ -437,7 +444,7 @@ static int queue_pages_pmd(pmd_t *pmd, spinlock_t *ptl, unsigned long addr,
 	unsigned long flags;
 
 	if (unlikely(is_pmd_migration_entry(*pmd))) {
-		ret = 1;
+		ret = -EIO;
 		goto unlock;
 	}
 	page = pmd_page(*pmd);
@@ -454,8 +461,15 @@ static int queue_pages_pmd(pmd_t *pmd, spinlock_t *ptl, unsigned long addr,
 	ret = 1;
 	flags = qp->flags;
 	/* go to thp migration */
-	if (flags & (MPOL_MF_MOVE | MPOL_MF_MOVE_ALL))
+	if (flags & (MPOL_MF_MOVE | MPOL_MF_MOVE_ALL)) {
+		if (!vma_migratable(walk->vma)) {
+			ret = -EIO;
+			goto unlock;
+		}
+
 		migrate_page_add(page, qp->pagelist, flags);
+	} else
+		ret = -EIO;
 unlock:
 	spin_unlock(ptl);
 out:
@@ -480,8 +494,10 @@ static int queue_pages_pte_range(pmd_t *pmd, unsigned long addr,
 	ptl = pmd_trans_huge_lock(pmd, vma);
 	if (ptl) {
 		ret = queue_pages_pmd(pmd, ptl, addr, end, walk);
-		if (ret)
+		if (ret > 0)
 			return 0;
+		else if (ret < 0)
+			return ret;
 	}
 
 	if (pmd_trans_unstable(pmd))
@@ -502,11 +518,16 @@ static int queue_pages_pte_range(pmd_t *pmd, unsigned long addr,
 			continue;
 		if (!queue_pages_required(page, qp))
 			continue;
-		migrate_page_add(page, qp->pagelist, flags);
+		if (flags & (MPOL_MF_MOVE | MPOL_MF_MOVE_ALL)) {
+			if (!vma_migratable(vma))
+				break;
+			migrate_page_add(page, qp->pagelist, flags);
+		} else
+			break;
 	}
 	pte_unmap_unlock(pte - 1, ptl);
 	cond_resched();
-	return 0;
+	return addr != end ? -EIO : 0;
 }
 
 static int queue_pages_hugetlb(pte_t *pte, unsigned long hmask,
@@ -576,7 +597,12 @@ static int queue_pages_test_walk(unsigned long start, unsigned long end,
 	unsigned long endvma = vma->vm_end;
 	unsigned long flags = qp->flags;
 
-	if (!vma_migratable(vma))
+	/*
+	 * Need check MPOL_MF_STRICT to return -EIO if possible
+	 * regardless of vma_migratable
+	 */
+	if (!vma_migratable(vma) &&
+	    !(flags & MPOL_MF_STRICT))
 		return 1;
 
 	if (endvma > end)
@@ -603,7 +629,7 @@ static int queue_pages_test_walk(unsigned long start, unsigned long end,
 	}
 
 	/* queue pages from current vma */
-	if (flags & (MPOL_MF_MOVE | MPOL_MF_MOVE_ALL))
+	if (flags & MPOL_MF_VALID)
 		return 0;
 	return 1;
 }
diff --git a/mm/migrate.c b/mm/migrate.c
index ac6f4939bb59..663a5449367a 100644
--- a/mm/migrate.c
+++ b/mm/migrate.c
@@ -248,10 +248,8 @@ static bool remove_migration_pte(struct page *page, struct vm_area_struct *vma,
 				pte = swp_entry_to_pte(entry);
 			} else if (is_device_public_page(new)) {
 				pte = pte_mkdevmap(pte);
-				flush_dcache_page(new);
 			}
-		} else
-			flush_dcache_page(new);
+		}
 
 #ifdef CONFIG_HUGETLB_PAGE
 		if (PageHuge(new)) {
@@ -995,6 +993,13 @@ static int move_to_new_page(struct page *newpage, struct page *page,
 		 */
 		if (!PageMappingFlags(page))
 			page->mapping = NULL;
+
+		if (unlikely(is_zone_device_page(newpage))) {
+			if (is_device_public_page(newpage))
+				flush_dcache_page(newpage);
+		} else
+			flush_dcache_page(newpage);
+
 	}
 out:
 	return rc;
diff --git a/mm/mmap.c b/mm/mmap.c
index 41eb48d9b527..bd7b9f293b39 100644
--- a/mm/mmap.c
+++ b/mm/mmap.c
@@ -45,6 +45,7 @@
 #include <linux/moduleparam.h>
 #include <linux/pkeys.h>
 #include <linux/oom.h>
+#include <linux/sched/mm.h>
 
 #include <linux/uaccess.h>
 #include <asm/cacheflush.h>
@@ -2525,7 +2526,8 @@ find_extend_vma(struct mm_struct *mm, unsigned long addr)
 	vma = find_vma_prev(mm, addr, &prev);
 	if (vma && (vma->vm_start <= addr))
 		return vma;
-	if (!prev || expand_stack(prev, addr))
+	/* don't alter vm_end if the coredump is running */
+	if (!prev || !mmget_still_valid(mm) || expand_stack(prev, addr))
 		return NULL;
 	if (prev->vm_flags & VM_LOCKED)
 		populate_vma_page_range(prev, addr, prev->vm_end, NULL);
@@ -2551,6 +2553,9 @@ find_extend_vma(struct mm_struct *mm, unsigned long addr)
 		return vma;
 	if (!(vma->vm_flags & VM_GROWSDOWN))
 		return NULL;
+	/* don't alter vm_start if the coredump is running */
+	if (!mmget_still_valid(mm))
+		return NULL;
 	start = vma->vm_start;
 	if (expand_stack(vma, addr))
 		return NULL;
diff --git a/mm/mmu_gather.c b/mm/mmu_gather.c
index f2f03c655807..99740e1dd273 100644
--- a/mm/mmu_gather.c
+++ b/mm/mmu_gather.c
@@ -11,7 +11,7 @@
 #include <asm/pgalloc.h>
 #include <asm/tlb.h>
 
-#ifdef HAVE_GENERIC_MMU_GATHER
+#ifndef CONFIG_HAVE_MMU_GATHER_NO_GATHER
 
 static bool tlb_next_batch(struct mmu_gather *tlb)
 {
@@ -41,35 +41,10 @@ static bool tlb_next_batch(struct mmu_gather *tlb)
 	return true;
 }
 
-void arch_tlb_gather_mmu(struct mmu_gather *tlb, struct mm_struct *mm,
-				unsigned long start, unsigned long end)
-{
-	tlb->mm = mm;
-
-	/* Is it from 0 to ~0? */
-	tlb->fullmm     = !(start | (end+1));
-	tlb->need_flush_all = 0;
-	tlb->local.next = NULL;
-	tlb->local.nr   = 0;
-	tlb->local.max  = ARRAY_SIZE(tlb->__pages);
-	tlb->active     = &tlb->local;
-	tlb->batch_count = 0;
-
-#ifdef CONFIG_HAVE_RCU_TABLE_FREE
-	tlb->batch = NULL;
-#endif
-	tlb->page_size = 0;
-
-	__tlb_reset_range(tlb);
-}
-
-void tlb_flush_mmu_free(struct mmu_gather *tlb)
+static void tlb_batch_pages_flush(struct mmu_gather *tlb)
 {
 	struct mmu_gather_batch *batch;
 
-#ifdef CONFIG_HAVE_RCU_TABLE_FREE
-	tlb_table_flush(tlb);
-#endif
 	for (batch = &tlb->local; batch && batch->nr; batch = batch->next) {
 		free_pages_and_swap_cache(batch->pages, batch->nr);
 		batch->nr = 0;
@@ -77,31 +52,10 @@ void tlb_flush_mmu_free(struct mmu_gather *tlb)
 	tlb->active = &tlb->local;
 }
 
-void tlb_flush_mmu(struct mmu_gather *tlb)
-{
-	tlb_flush_mmu_tlbonly(tlb);
-	tlb_flush_mmu_free(tlb);
-}
-
-/* tlb_finish_mmu
- *	Called at the end of the shootdown operation to free up any resources
- *	that were required.
- */
-void arch_tlb_finish_mmu(struct mmu_gather *tlb,
-		unsigned long start, unsigned long end, bool force)
+static void tlb_batch_list_free(struct mmu_gather *tlb)
 {
 	struct mmu_gather_batch *batch, *next;
 
-	if (force) {
-		__tlb_reset_range(tlb);
-		__tlb_adjust_range(tlb, start, end - start);
-	}
-
-	tlb_flush_mmu(tlb);
-
-	/* keep the page table cache within bounds */
-	check_pgt_cache();
-
 	for (batch = tlb->local.next; batch; batch = next) {
 		next = batch->next;
 		free_pages((unsigned long)batch, 0);
@@ -109,19 +63,15 @@ void arch_tlb_finish_mmu(struct mmu_gather *tlb,
 	tlb->local.next = NULL;
 }
 
-/* __tlb_remove_page
- *	Must perform the equivalent to __free_pte(pte_get_and_clear(ptep)), while
- *	handling the additional races in SMP caused by other CPUs caching valid
- *	mappings in their TLBs. Returns the number of free page slots left.
- *	When out of page slots we must call tlb_flush_mmu().
- *returns true if the caller should flush.
- */
 bool __tlb_remove_page_size(struct mmu_gather *tlb, struct page *page, int page_size)
 {
 	struct mmu_gather_batch *batch;
 
 	VM_BUG_ON(!tlb->end);
+
+#ifdef CONFIG_HAVE_MMU_GATHER_PAGE_SIZE
 	VM_WARN_ON(tlb->page_size != page_size);
+#endif
 
 	batch = tlb->active;
 	/*
@@ -139,7 +89,7 @@ bool __tlb_remove_page_size(struct mmu_gather *tlb, struct page *page, int page_
 	return false;
 }
 
-#endif /* HAVE_GENERIC_MMU_GATHER */
+#endif /* HAVE_MMU_GATHER_NO_GATHER */
 
 #ifdef CONFIG_HAVE_RCU_TABLE_FREE
 
@@ -152,7 +102,7 @@ bool __tlb_remove_page_size(struct mmu_gather *tlb, struct page *page, int page_
  */
 static inline void tlb_table_invalidate(struct mmu_gather *tlb)
 {
-#ifdef CONFIG_HAVE_RCU_TABLE_INVALIDATE
+#ifndef CONFIG_HAVE_RCU_TABLE_NO_INVALIDATE
 	/*
 	 * Invalidate page-table caches used by hardware walkers. Then we still
 	 * need to RCU-sched wait while freeing the pages because software
@@ -193,7 +143,7 @@ static void tlb_remove_table_rcu(struct rcu_head *head)
 	free_page((unsigned long)batch);
 }
 
-void tlb_table_flush(struct mmu_gather *tlb)
+static void tlb_table_flush(struct mmu_gather *tlb)
 {
 	struct mmu_table_batch **batch = &tlb->batch;
 
@@ -225,6 +175,22 @@ void tlb_remove_table(struct mmu_gather *tlb, void *table)
 
 #endif /* CONFIG_HAVE_RCU_TABLE_FREE */
 
+static void tlb_flush_mmu_free(struct mmu_gather *tlb)
+{
+#ifdef CONFIG_HAVE_RCU_TABLE_FREE
+	tlb_table_flush(tlb);
+#endif
+#ifndef CONFIG_HAVE_MMU_GATHER_NO_GATHER
+	tlb_batch_pages_flush(tlb);
+#endif
+}
+
+void tlb_flush_mmu(struct mmu_gather *tlb)
+{
+	tlb_flush_mmu_tlbonly(tlb);
+	tlb_flush_mmu_free(tlb);
+}
+
 /**
  * tlb_gather_mmu - initialize an mmu_gather structure for page-table tear-down
  * @tlb: the mmu_gather structure to initialize
@@ -240,10 +206,40 @@ void tlb_remove_table(struct mmu_gather *tlb, void *table)
 void tlb_gather_mmu(struct mmu_gather *tlb, struct mm_struct *mm,
 			unsigned long start, unsigned long end)
 {
-	arch_tlb_gather_mmu(tlb, mm, start, end);
+	tlb->mm = mm;
+
+	/* Is it from 0 to ~0? */
+	tlb->fullmm     = !(start | (end+1));
+
+#ifndef CONFIG_HAVE_MMU_GATHER_NO_GATHER
+	tlb->need_flush_all = 0;
+	tlb->local.next = NULL;
+	tlb->local.nr   = 0;
+	tlb->local.max  = ARRAY_SIZE(tlb->__pages);
+	tlb->active     = &tlb->local;
+	tlb->batch_count = 0;
+#endif
+
+#ifdef CONFIG_HAVE_RCU_TABLE_FREE
+	tlb->batch = NULL;
+#endif
+#ifdef CONFIG_HAVE_MMU_GATHER_PAGE_SIZE
+	tlb->page_size = 0;
+#endif
+
+	__tlb_reset_range(tlb);
 	inc_tlb_flush_pending(tlb->mm);
 }
 
+/**
+ * tlb_finish_mmu - finish an mmu_gather structure
+ * @tlb: the mmu_gather structure to finish
+ * @start: start of the region that will be removed from the page-table
+ * @end: end of the region that will be removed from the page-table
+ *
+ * Called at the end of the shootdown operation to free up any resources that
+ * were required.
+ */
 void tlb_finish_mmu(struct mmu_gather *tlb,
 		unsigned long start, unsigned long end)
 {
@@ -254,8 +250,17 @@ void tlb_finish_mmu(struct mmu_gather *tlb,
 	 * the TLB by observing pte_none|!pte_dirty, for example so flush TLB
 	 * forcefully if we detect parallel PTE batching threads.
 	 */
-	bool force = mm_tlb_flush_nested(tlb->mm);
+	if (mm_tlb_flush_nested(tlb->mm)) {
+		__tlb_reset_range(tlb);
+		__tlb_adjust_range(tlb, start, end - start);
+	}
 
-	arch_tlb_finish_mmu(tlb, start, end, force);
+	tlb_flush_mmu(tlb);
+
+	/* keep the page table cache within bounds */
+	check_pgt_cache();
+#ifndef CONFIG_HAVE_MMU_GATHER_NO_GATHER
+	tlb_batch_list_free(tlb);
+#endif
 	dec_tlb_flush_pending(tlb->mm);
 }
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index 03fcf73d47da..59661106da16 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -266,7 +266,20 @@ compound_page_dtor * const compound_page_dtors[] = {
 
 int min_free_kbytes = 1024;
 int user_min_free_kbytes = -1;
+#ifdef CONFIG_DISCONTIGMEM
+/*
+ * DiscontigMem defines memory ranges as separate pg_data_t even if the ranges
+ * are not on separate NUMA nodes. Functionally this works but with
+ * watermark_boost_factor, it can reclaim prematurely as the ranges can be
+ * quite small. By default, do not boost watermarks on discontigmem as in
+ * many cases very high-order allocations like THP are likely to be
+ * unsupported and the premature reclaim offsets the advantage of long-term
+ * fragmentation avoidance.
+ */
+int watermark_boost_factor __read_mostly;
+#else
 int watermark_boost_factor __read_mostly = 15000;
+#endif
 int watermark_scale_factor = 10;
 
 static unsigned long nr_kernel_pages __initdata;
@@ -1131,7 +1144,9 @@ static __always_inline bool free_pages_prepare(struct page *page,
 	}
 	arch_free_page(page, order);
 	kernel_poison_pages(page, 1 << order, 0);
-	kernel_map_pages(page, 1 << order, 0);
+	if (debug_pagealloc_enabled())
+		kernel_map_pages(page, 1 << order, 0);
+
 	kasan_free_nondeferred_pages(page, order);
 
 	return true;
@@ -2001,7 +2016,8 @@ inline void post_alloc_hook(struct page *page, unsigned int order,
 	set_page_refcounted(page);
 
 	arch_alloc_page(page, order);
-	kernel_map_pages(page, 1 << order, 1);
+	if (debug_pagealloc_enabled())
+		kernel_map_pages(page, 1 << order, 1);
 	kasan_alloc_pages(page, order);
 	kernel_poison_pages(page, 1 << order, 1);
 	set_page_owner(page, order, gfp_flags);
@@ -3419,8 +3435,11 @@ alloc_flags_nofragment(struct zone *zone, gfp_t gfp_mask)
 		alloc_flags |= ALLOC_KSWAPD;
 
 #ifdef CONFIG_ZONE_DMA32
+	if (!zone)
+		return alloc_flags;
+
 	if (zone_idx(zone) != ZONE_NORMAL)
-		goto out;
+		return alloc_flags;
 
 	/*
 	 * If ZONE_DMA32 exists, assume it is the one after ZONE_NORMAL and
@@ -3429,9 +3448,9 @@ alloc_flags_nofragment(struct zone *zone, gfp_t gfp_mask)
 	 */
 	BUILD_BUG_ON(ZONE_NORMAL - ZONE_DMA32 != 1);
 	if (nr_online_nodes > 1 && !populated_zone(--zone))
-		goto out;
+		return alloc_flags;
 
-out:
+	alloc_flags |= ALLOC_NOFRAGMENT;
 #endif /* CONFIG_ZONE_DMA32 */
 	return alloc_flags;
 }
@@ -3773,11 +3792,6 @@ __alloc_pages_direct_compact(gfp_t gfp_mask, unsigned int order,
 	memalloc_noreclaim_restore(noreclaim_flag);
 	psi_memstall_leave(&pflags);
 
-	if (*compact_result <= COMPACT_INACTIVE) {
-		WARN_ON_ONCE(page);
-		return NULL;
-	}
-
 	/*
 	 * At least in one zone compaction wasn't deferred or skipped, so let's
 	 * count a compaction stall
@@ -8005,7 +8019,10 @@ void *__init alloc_large_system_hash(const char *tablename,
 bool has_unmovable_pages(struct zone *zone, struct page *page, int count,
 			 int migratetype, int flags)
 {
-	unsigned long pfn, iter, found;
+	unsigned long found;
+	unsigned long iter = 0;
+	unsigned long pfn = page_to_pfn(page);
+	const char *reason = "unmovable page";
 
 	/*
 	 * TODO we could make this much more efficient by not checking every
@@ -8015,17 +8032,20 @@ bool has_unmovable_pages(struct zone *zone, struct page *page, int count,
 	 * can still lead to having bootmem allocations in zone_movable.
 	 */
 
-	/*
-	 * CMA allocations (alloc_contig_range) really need to mark isolate
-	 * CMA pageblocks even when they are not movable in fact so consider
-	 * them movable here.
-	 */
-	if (is_migrate_cma(migratetype) &&
-			is_migrate_cma(get_pageblock_migratetype(page)))
-		return false;
+	if (is_migrate_cma_page(page)) {
+		/*
+		 * CMA allocations (alloc_contig_range) really need to mark
+		 * isolate CMA pageblocks even when they are not movable in fact
+		 * so consider them movable here.
+		 */
+		if (is_migrate_cma(migratetype))
+			return false;
 
-	pfn = page_to_pfn(page);
-	for (found = 0, iter = 0; iter < pageblock_nr_pages; iter++) {
+		reason = "CMA page";
+		goto unmovable;
+	}
+
+	for (found = 0; iter < pageblock_nr_pages; iter++) {
 		unsigned long check = pfn + iter;
 
 		if (!pfn_valid_within(check))
@@ -8105,7 +8125,7 @@ bool has_unmovable_pages(struct zone *zone, struct page *page, int count,
 unmovable:
 	WARN_ON_ONCE(zone_idx(zone) == ZONE_MOVABLE);
 	if (flags & REPORT_FAILURE)
-		dump_page(pfn_to_page(pfn+iter), "unmovable page");
+		dump_page(pfn_to_page(pfn + iter), reason);
 	return true;
 }
 
@@ -8233,7 +8253,7 @@ int alloc_contig_range(unsigned long start, unsigned long end,
 
 	ret = start_isolate_page_range(pfn_max_align_down(start),
 				       pfn_max_align_up(end), migratetype, 0);
-	if (ret)
+	if (ret < 0)
 		return ret;
 
 	/*
diff --git a/mm/page_isolation.c b/mm/page_isolation.c
index ce323e56b34d..019280712e1b 100644
--- a/mm/page_isolation.c
+++ b/mm/page_isolation.c
@@ -59,7 +59,8 @@ static int set_migratetype_isolate(struct page *page, int migratetype, int isol_
 	 * FIXME: Now, memory hotplug doesn't call shrink_slab() by itself.
 	 * We just check MOVABLE pages.
 	 */
-	if (!has_unmovable_pages(zone, page, arg.pages_found, migratetype, flags))
+	if (!has_unmovable_pages(zone, page, arg.pages_found, migratetype,
+				 isol_flags))
 		ret = 0;
 
 	/*
@@ -160,27 +161,36 @@ __first_valid_page(unsigned long pfn, unsigned long nr_pages)
 	return NULL;
 }
 
-/*
- * start_isolate_page_range() -- make page-allocation-type of range of pages
- * to be MIGRATE_ISOLATE.
- * @start_pfn: The lower PFN of the range to be isolated.
- * @end_pfn: The upper PFN of the range to be isolated.
- * @migratetype: migrate type to set in error recovery.
+/**
+ * start_isolate_page_range() - make page-allocation-type of range of pages to
+ * be MIGRATE_ISOLATE.
+ * @start_pfn:		The lower PFN of the range to be isolated.
+ * @end_pfn:		The upper PFN of the range to be isolated.
+ *			start_pfn/end_pfn must be aligned to pageblock_order.
+ * @migratetype:	Migrate type to set in error recovery.
+ * @flags:		The following flags are allowed (they can be combined in
+ *			a bit mask)
+ *			SKIP_HWPOISON - ignore hwpoison pages
+ *			REPORT_FAILURE - report details about the failure to
+ *			isolate the range
  *
  * Making page-allocation-type to be MIGRATE_ISOLATE means free pages in
  * the range will never be allocated. Any free pages and pages freed in the
- * future will not be allocated again.
- *
- * start_pfn/end_pfn must be aligned to pageblock_order.
- * Return 0 on success and -EBUSY if any part of range cannot be isolated.
+ * future will not be allocated again. If specified range includes migrate types
+ * other than MOVABLE or CMA, this will fail with -EBUSY. For isolating all
+ * pages in the range finally, the caller have to free all pages in the range.
+ * test_page_isolated() can be used for test it.
  *
  * There is no high level synchronization mechanism that prevents two threads
- * from trying to isolate overlapping ranges.  If this happens, one thread
+ * from trying to isolate overlapping ranges. If this happens, one thread
  * will notice pageblocks in the overlapping range already set to isolate.
  * This happens in set_migratetype_isolate, and set_migratetype_isolate
- * returns an error.  We then clean up by restoring the migration type on
- * pageblocks we may have modified and return -EBUSY to caller.  This
+ * returns an error. We then clean up by restoring the migration type on
+ * pageblocks we may have modified and return -EBUSY to caller. This
  * prevents two threads from simultaneously working on overlapping ranges.
+ *
+ * Return: the number of isolated pageblocks on success and -EBUSY if any part
+ * of range cannot be isolated.
  */
 int start_isolate_page_range(unsigned long start_pfn, unsigned long end_pfn,
 			     unsigned migratetype, int flags)
@@ -188,6 +198,7 @@ int start_isolate_page_range(unsigned long start_pfn, unsigned long end_pfn,
 	unsigned long pfn;
 	unsigned long undo_pfn;
 	struct page *page;
+	int nr_isolate_pageblock = 0;
 
 	BUG_ON(!IS_ALIGNED(start_pfn, pageblock_nr_pages));
 	BUG_ON(!IS_ALIGNED(end_pfn, pageblock_nr_pages));
@@ -196,13 +207,15 @@ int start_isolate_page_range(unsigned long start_pfn, unsigned long end_pfn,
 	     pfn < end_pfn;
 	     pfn += pageblock_nr_pages) {
 		page = __first_valid_page(pfn, pageblock_nr_pages);
-		if (page &&
-		    set_migratetype_isolate(page, migratetype, flags)) {
-			undo_pfn = pfn;
-			goto undo;
+		if (page) {
+			if (set_migratetype_isolate(page, migratetype, flags)) {
+				undo_pfn = pfn;
+				goto undo;
+			}
+			nr_isolate_pageblock++;
 		}
 	}
-	return 0;
+	return nr_isolate_pageblock;
 undo:
 	for (pfn = start_pfn;
 	     pfn < undo_pfn;
diff --git a/mm/page_owner.c b/mm/page_owner.c
index 925b6f44a444..addcbb2ae4e4 100644
--- a/mm/page_owner.c
+++ b/mm/page_owner.c
@@ -58,15 +58,10 @@ static bool need_page_owner(void)
 static __always_inline depot_stack_handle_t create_dummy_stack(void)
 {
 	unsigned long entries[4];
-	struct stack_trace dummy;
+	unsigned int nr_entries;
 
-	dummy.nr_entries = 0;
-	dummy.max_entries = ARRAY_SIZE(entries);
-	dummy.entries = &entries[0];
-	dummy.skip = 0;
-
-	save_stack_trace(&dummy);
-	return depot_save_stack(&dummy, GFP_KERNEL);
+	nr_entries = stack_trace_save(entries, ARRAY_SIZE(entries), 0);
+	return stack_depot_save(entries, nr_entries, GFP_KERNEL);
 }
 
 static noinline void register_dummy_stack(void)
@@ -120,49 +115,39 @@ void __reset_page_owner(struct page *page, unsigned int order)
 	}
 }
 
-static inline bool check_recursive_alloc(struct stack_trace *trace,
-					unsigned long ip)
+static inline bool check_recursive_alloc(unsigned long *entries,
+					 unsigned int nr_entries,
+					 unsigned long ip)
 {
-	int i;
-
-	if (!trace->nr_entries)
-		return false;
+	unsigned int i;
 
-	for (i = 0; i < trace->nr_entries; i++) {
-		if (trace->entries[i] == ip)
+	for (i = 0; i < nr_entries; i++) {
+		if (entries[i] == ip)
 			return true;
 	}
-
 	return false;
 }
 
 static noinline depot_stack_handle_t save_stack(gfp_t flags)
 {
 	unsigned long entries[PAGE_OWNER_STACK_DEPTH];
-	struct stack_trace trace = {
-		.nr_entries = 0,
-		.entries = entries,
-		.max_entries = PAGE_OWNER_STACK_DEPTH,
-		.skip = 2
-	};
 	depot_stack_handle_t handle;
+	unsigned int nr_entries;
 
-	save_stack_trace(&trace);
-	if (trace.nr_entries != 0 &&
-	    trace.entries[trace.nr_entries-1] == ULONG_MAX)
-		trace.nr_entries--;
+	nr_entries = stack_trace_save(entries, ARRAY_SIZE(entries), 2);
 
 	/*
-	 * We need to check recursion here because our request to stackdepot
-	 * could trigger memory allocation to save new entry. New memory
-	 * allocation would reach here and call depot_save_stack() again
-	 * if we don't catch it. There is still not enough memory in stackdepot
-	 * so it would try to allocate memory again and loop forever.
+	 * We need to check recursion here because our request to
+	 * stackdepot could trigger memory allocation to save new
+	 * entry. New memory allocation would reach here and call
+	 * stack_depot_save_entries() again if we don't catch it. There is
+	 * still not enough memory in stackdepot so it would try to
+	 * allocate memory again and loop forever.
 	 */
-	if (check_recursive_alloc(&trace, _RET_IP_))
+	if (check_recursive_alloc(entries, nr_entries, _RET_IP_))
 		return dummy_handle;
 
-	handle = depot_save_stack(&trace, flags);
+	handle = stack_depot_save(entries, nr_entries, flags);
 	if (!handle)
 		handle = failure_handle;
 
@@ -340,16 +325,10 @@ print_page_owner(char __user *buf, size_t count, unsigned long pfn,
 		struct page *page, struct page_owner *page_owner,
 		depot_stack_handle_t handle)
 {
-	int ret;
-	int pageblock_mt, page_mt;
+	int ret, pageblock_mt, page_mt;
+	unsigned long *entries;
+	unsigned int nr_entries;
 	char *kbuf;
-	unsigned long entries[PAGE_OWNER_STACK_DEPTH];
-	struct stack_trace trace = {
-		.nr_entries = 0,
-		.entries = entries,
-		.max_entries = PAGE_OWNER_STACK_DEPTH,
-		.skip = 0
-	};
 
 	count = min_t(size_t, count, PAGE_SIZE);
 	kbuf = kmalloc(count, GFP_KERNEL);
@@ -378,8 +357,8 @@ print_page_owner(char __user *buf, size_t count, unsigned long pfn,
 	if (ret >= count)
 		goto err;
 
-	depot_fetch_stack(handle, &trace);
-	ret += snprint_stack_trace(kbuf + ret, count - ret, &trace, 0);
+	nr_entries = stack_depot_fetch(handle, &entries);
+	ret += stack_trace_snprint(kbuf + ret, count - ret, entries, nr_entries, 0);
 	if (ret >= count)
 		goto err;
 
@@ -410,14 +389,9 @@ void __dump_page_owner(struct page *page)
 {
 	struct page_ext *page_ext = lookup_page_ext(page);
 	struct page_owner *page_owner;
-	unsigned long entries[PAGE_OWNER_STACK_DEPTH];
-	struct stack_trace trace = {
-		.nr_entries = 0,
-		.entries = entries,
-		.max_entries = PAGE_OWNER_STACK_DEPTH,
-		.skip = 0
-	};
 	depot_stack_handle_t handle;
+	unsigned long *entries;
+	unsigned int nr_entries;
 	gfp_t gfp_mask;
 	int mt;
 
@@ -441,10 +415,10 @@ void __dump_page_owner(struct page *page)
 		return;
 	}
 
-	depot_fetch_stack(handle, &trace);
+	nr_entries = stack_depot_fetch(handle, &entries);
 	pr_alert("page allocated via order %u, migratetype %s, gfp_mask %#x(%pGg)\n",
 		 page_owner->order, migratetype_names[mt], gfp_mask, &gfp_mask);
-	print_stack_trace(&trace, 0);
+	stack_trace_print(entries, nr_entries, 0);
 
 	if (page_owner->last_migrate_reason != -1)
 		pr_alert("page has been migrated, last migrate reason: %s\n",
diff --git a/mm/percpu.c b/mm/percpu.c
index 2e6fc8d552c9..68dd2e7e73b5 100644
--- a/mm/percpu.c
+++ b/mm/percpu.c
@@ -2567,8 +2567,8 @@ int __init pcpu_embed_first_chunk(size_t reserved_size, size_t dyn_size,
 		ai->groups[group].base_offset = areas[group] - base;
 	}
 
-	pr_info("Embedded %zu pages/cpu @%p s%zu r%zu d%zu u%zu\n",
-		PFN_DOWN(size_sum), base, ai->static_size, ai->reserved_size,
+	pr_info("Embedded %zu pages/cpu s%zu r%zu d%zu u%zu\n",
+		PFN_DOWN(size_sum), ai->static_size, ai->reserved_size,
 		ai->dyn_size, ai->unit_size);
 
 	rc = pcpu_setup_first_chunk(ai, base);
@@ -2692,8 +2692,8 @@ int __init pcpu_page_first_chunk(size_t reserved_size,
 	}
 
 	/* we're ready, commit */
-	pr_info("%d %s pages/cpu @%p s%zu r%zu d%zu\n",
-		unit_pages, psize_str, vm.addr, ai->static_size,
+	pr_info("%d %s pages/cpu s%zu r%zu d%zu\n",
+		unit_pages, psize_str, ai->static_size,
 		ai->reserved_size, ai->dyn_size);
 
 	rc = pcpu_setup_first_chunk(ai, vm.addr);
diff --git a/mm/shmem.c b/mm/shmem.c
index b3db3779a30a..2275a0ff7c30 100644
--- a/mm/shmem.c
+++ b/mm/shmem.c
@@ -1081,9 +1081,14 @@ static void shmem_evict_inode(struct inode *inode)
 			}
 			spin_unlock(&sbinfo->shrinklist_lock);
 		}
-		if (!list_empty(&info->swaplist)) {
+		while (!list_empty(&info->swaplist)) {
+			/* Wait while shmem_unuse() is scanning this inode... */
+			wait_var_event(&info->stop_eviction,
+				       !atomic_read(&info->stop_eviction));
 			mutex_lock(&shmem_swaplist_mutex);
-			list_del_init(&info->swaplist);
+			/* ...but beware of the race if we peeked too early */
+			if (!atomic_read(&info->stop_eviction))
+				list_del_init(&info->swaplist);
 			mutex_unlock(&shmem_swaplist_mutex);
 		}
 	}
@@ -1099,10 +1104,11 @@ extern struct swap_info_struct *swap_info[];
 static int shmem_find_swap_entries(struct address_space *mapping,
 				   pgoff_t start, unsigned int nr_entries,
 				   struct page **entries, pgoff_t *indices,
-				   bool frontswap)
+				   unsigned int type, bool frontswap)
 {
 	XA_STATE(xas, &mapping->i_pages, start);
 	struct page *page;
+	swp_entry_t entry;
 	unsigned int ret = 0;
 
 	if (!nr_entries)
@@ -1116,13 +1122,12 @@ static int shmem_find_swap_entries(struct address_space *mapping,
 		if (!xa_is_value(page))
 			continue;
 
-		if (frontswap) {
-			swp_entry_t entry = radix_to_swp_entry(page);
-
-			if (!frontswap_test(swap_info[swp_type(entry)],
-					    swp_offset(entry)))
-				continue;
-		}
+		entry = radix_to_swp_entry(page);
+		if (swp_type(entry) != type)
+			continue;
+		if (frontswap &&
+		    !frontswap_test(swap_info[type], swp_offset(entry)))
+			continue;
 
 		indices[ret] = xas.xa_index;
 		entries[ret] = page;
@@ -1194,7 +1199,7 @@ static int shmem_unuse_inode(struct inode *inode, unsigned int type,
 
 		pvec.nr = shmem_find_swap_entries(mapping, start, nr_entries,
 						  pvec.pages, indices,
-						  frontswap);
+						  type, frontswap);
 		if (pvec.nr == 0) {
 			ret = 0;
 			break;
@@ -1227,36 +1232,27 @@ int shmem_unuse(unsigned int type, bool frontswap,
 		unsigned long *fs_pages_to_unuse)
 {
 	struct shmem_inode_info *info, *next;
-	struct inode *inode;
-	struct inode *prev_inode = NULL;
 	int error = 0;
 
 	if (list_empty(&shmem_swaplist))
 		return 0;
 
 	mutex_lock(&shmem_swaplist_mutex);
-
-	/*
-	 * The extra refcount on the inode is necessary to safely dereference
-	 * p->next after re-acquiring the lock. New shmem inodes with swap
-	 * get added to the end of the list and we will scan them all.
-	 */
 	list_for_each_entry_safe(info, next, &shmem_swaplist, swaplist) {
 		if (!info->swapped) {
 			list_del_init(&info->swaplist);
 			continue;
 		}
-
-		inode = igrab(&info->vfs_inode);
-		if (!inode)
-			continue;
-
+		/*
+		 * Drop the swaplist mutex while searching the inode for swap;
+		 * but before doing so, make sure shmem_evict_inode() will not
+		 * remove placeholder inode from swaplist, nor let it be freed
+		 * (igrab() would protect from unlink, but not from unmount).
+		 */
+		atomic_inc(&info->stop_eviction);
 		mutex_unlock(&shmem_swaplist_mutex);
-		if (prev_inode)
-			iput(prev_inode);
-		prev_inode = inode;
 
-		error = shmem_unuse_inode(inode, type, frontswap,
+		error = shmem_unuse_inode(&info->vfs_inode, type, frontswap,
 					  fs_pages_to_unuse);
 		cond_resched();
 
@@ -1264,14 +1260,13 @@ int shmem_unuse(unsigned int type, bool frontswap,
 		next = list_next_entry(info, swaplist);
 		if (!info->swapped)
 			list_del_init(&info->swaplist);
+		if (atomic_dec_and_test(&info->stop_eviction))
+			wake_up_var(&info->stop_eviction);
 		if (error)
 			break;
 	}
 	mutex_unlock(&shmem_swaplist_mutex);
 
-	if (prev_inode)
-		iput(prev_inode);
-
 	return error;
 }
 
@@ -2238,6 +2233,7 @@ static struct inode *shmem_get_inode(struct super_block *sb, const struct inode
 		info = SHMEM_I(inode);
 		memset(info, 0, (char *)inode - (char *)info);
 		spin_lock_init(&info->lock);
+		atomic_set(&info->stop_eviction, 0);
 		info->seals = F_SEAL_SEAL;
 		info->flags = flags & VM_NORESERVE;
 		INIT_LIST_HEAD(&info->shrinklist);
diff --git a/mm/slab.c b/mm/slab.c
index 28652e4218e0..284ab737faee 100644
--- a/mm/slab.c
+++ b/mm/slab.c
@@ -1467,53 +1467,17 @@ static bool is_debug_pagealloc_cache(struct kmem_cache *cachep)
 }
 
 #ifdef CONFIG_DEBUG_PAGEALLOC
-static void store_stackinfo(struct kmem_cache *cachep, unsigned long *addr,
-			    unsigned long caller)
-{
-	int size = cachep->object_size;
-
-	addr = (unsigned long *)&((char *)addr)[obj_offset(cachep)];
-
-	if (size < 5 * sizeof(unsigned long))
-		return;
-
-	*addr++ = 0x12345678;
-	*addr++ = caller;
-	*addr++ = smp_processor_id();
-	size -= 3 * sizeof(unsigned long);
-	{
-		unsigned long *sptr = &caller;
-		unsigned long svalue;
-
-		while (!kstack_end(sptr)) {
-			svalue = *sptr++;
-			if (kernel_text_address(svalue)) {
-				*addr++ = svalue;
-				size -= sizeof(unsigned long);
-				if (size <= sizeof(unsigned long))
-					break;
-			}
-		}
-
-	}
-	*addr++ = 0x87654321;
-}
-
-static void slab_kernel_map(struct kmem_cache *cachep, void *objp,
-				int map, unsigned long caller)
+static void slab_kernel_map(struct kmem_cache *cachep, void *objp, int map)
 {
 	if (!is_debug_pagealloc_cache(cachep))
 		return;
 
-	if (caller)
-		store_stackinfo(cachep, objp, caller);
-
 	kernel_map_pages(virt_to_page(objp), cachep->size / PAGE_SIZE, map);
 }
 
 #else
 static inline void slab_kernel_map(struct kmem_cache *cachep, void *objp,
-				int map, unsigned long caller) {}
+				int map) {}
 
 #endif
 
@@ -1661,7 +1625,7 @@ static void slab_destroy_debugcheck(struct kmem_cache *cachep,
 
 		if (cachep->flags & SLAB_POISON) {
 			check_poison_obj(cachep, objp);
-			slab_kernel_map(cachep, objp, 1, 0);
+			slab_kernel_map(cachep, objp, 1);
 		}
 		if (cachep->flags & SLAB_RED_ZONE) {
 			if (*dbg_redzone1(cachep, objp) != RED_INACTIVE)
@@ -2115,6 +2079,8 @@ done:
 	cachep->allocflags = __GFP_COMP;
 	if (flags & SLAB_CACHE_DMA)
 		cachep->allocflags |= GFP_DMA;
+	if (flags & SLAB_CACHE_DMA32)
+		cachep->allocflags |= GFP_DMA32;
 	if (flags & SLAB_RECLAIM_ACCOUNT)
 		cachep->allocflags |= __GFP_RECLAIMABLE;
 	cachep->size = size;
@@ -2372,7 +2338,6 @@ static void *alloc_slabmgmt(struct kmem_cache *cachep,
 		/* Slab management obj is off-slab. */
 		freelist = kmem_cache_alloc_node(cachep->freelist_cache,
 					      local_flags, nodeid);
-		freelist = kasan_reset_tag(freelist);
 		if (!freelist)
 			return NULL;
 	} else {
@@ -2432,7 +2397,7 @@ static void cache_init_objs_debug(struct kmem_cache *cachep, struct page *page)
 		/* need to poison the objs? */
 		if (cachep->flags & SLAB_POISON) {
 			poison_obj(cachep, objp, POISON_FREE);
-			slab_kernel_map(cachep, objp, 0, 0);
+			slab_kernel_map(cachep, objp, 0);
 		}
 	}
 #endif
@@ -2811,7 +2776,7 @@ static void *cache_free_debugcheck(struct kmem_cache *cachep, void *objp,
 
 	if (cachep->flags & SLAB_POISON) {
 		poison_obj(cachep, objp, POISON_FREE);
-		slab_kernel_map(cachep, objp, 0, caller);
+		slab_kernel_map(cachep, objp, 0);
 	}
 	return objp;
 }
@@ -3075,7 +3040,7 @@ static void *cache_alloc_debugcheck_after(struct kmem_cache *cachep,
 		return objp;
 	if (cachep->flags & SLAB_POISON) {
 		check_poison_obj(cachep, objp);
-		slab_kernel_map(cachep, objp, 1, 0);
+		slab_kernel_map(cachep, objp, 1);
 		poison_obj(cachep, objp, POISON_INUSE);
 	}
 	if (cachep->flags & SLAB_STORE_USER)
@@ -4306,7 +4271,8 @@ static void show_symbol(struct seq_file *m, unsigned long address)
 
 static int leaks_show(struct seq_file *m, void *p)
 {
-	struct kmem_cache *cachep = list_entry(p, struct kmem_cache, list);
+	struct kmem_cache *cachep = list_entry(p, struct kmem_cache,
+					       root_caches_node);
 	struct page *page;
 	struct kmem_cache_node *n;
 	const char *name;
diff --git a/mm/slab.h b/mm/slab.h
index e5e6658eeacc..43ac818b8592 100644
--- a/mm/slab.h
+++ b/mm/slab.h
@@ -127,7 +127,8 @@ static inline slab_flags_t kmem_cache_flags(unsigned int object_size,
 
 
 /* Legal flag mask for kmem_cache_create(), for various configurations */
-#define SLAB_CORE_FLAGS (SLAB_HWCACHE_ALIGN | SLAB_CACHE_DMA | SLAB_PANIC | \
+#define SLAB_CORE_FLAGS (SLAB_HWCACHE_ALIGN | SLAB_CACHE_DMA | \
+			 SLAB_CACHE_DMA32 | SLAB_PANIC | \
 			 SLAB_TYPESAFE_BY_RCU | SLAB_DEBUG_OBJECTS )
 
 #if defined(CONFIG_DEBUG_SLAB)
diff --git a/mm/slab_common.c b/mm/slab_common.c
index 03eeb8b7b4b1..58251ba63e4a 100644
--- a/mm/slab_common.c
+++ b/mm/slab_common.c
@@ -53,7 +53,7 @@ static DECLARE_WORK(slab_caches_to_rcu_destroy_work,
 		SLAB_FAILSLAB | SLAB_KASAN)
 
 #define SLAB_MERGE_SAME (SLAB_RECLAIM_ACCOUNT | SLAB_CACHE_DMA | \
-			 SLAB_ACCOUNT)
+			 SLAB_CACHE_DMA32 | SLAB_ACCOUNT)
 
 /*
  * Merge control. If this is set then no merging of slab caches will occur.
diff --git a/mm/slub.c b/mm/slub.c
index 1b08fbcb7e61..6b28cd2b5a58 100644
--- a/mm/slub.c
+++ b/mm/slub.c
@@ -552,31 +552,22 @@ static void set_track(struct kmem_cache *s, void *object,
 
 	if (addr) {
 #ifdef CONFIG_STACKTRACE
-		struct stack_trace trace;
-		int i;
+		unsigned int nr_entries;
 
-		trace.nr_entries = 0;
-		trace.max_entries = TRACK_ADDRS_COUNT;
-		trace.entries = p->addrs;
-		trace.skip = 3;
 		metadata_access_enable();
-		save_stack_trace(&trace);
+		nr_entries = stack_trace_save(p->addrs, TRACK_ADDRS_COUNT, 3);
 		metadata_access_disable();
 
-		/* See rant in lockdep.c */
-		if (trace.nr_entries != 0 &&
-		    trace.entries[trace.nr_entries - 1] == ULONG_MAX)
-			trace.nr_entries--;
-
-		for (i = trace.nr_entries; i < TRACK_ADDRS_COUNT; i++)
-			p->addrs[i] = 0;
+		if (nr_entries < TRACK_ADDRS_COUNT)
+			p->addrs[nr_entries] = 0;
 #endif
 		p->addr = addr;
 		p->cpu = smp_processor_id();
 		p->pid = current->pid;
 		p->when = jiffies;
-	} else
+	} else {
 		memset(p, 0, sizeof(struct track));
+	}
 }
 
 static void init_tracking(struct kmem_cache *s, void *object)
@@ -3589,6 +3580,9 @@ static int calculate_sizes(struct kmem_cache *s, int forced_order)
 	if (s->flags & SLAB_CACHE_DMA)
 		s->allocflags |= GFP_DMA;
 
+	if (s->flags & SLAB_CACHE_DMA32)
+		s->allocflags |= GFP_DMA32;
+
 	if (s->flags & SLAB_RECLAIM_ACCOUNT)
 		s->allocflags |= __GFP_RECLAIMABLE;
 
@@ -5679,6 +5673,8 @@ static char *create_unique_id(struct kmem_cache *s)
 	 */
 	if (s->flags & SLAB_CACHE_DMA)
 		*p++ = 'd';
+	if (s->flags & SLAB_CACHE_DMA32)
+		*p++ = 'D';
 	if (s->flags & SLAB_RECLAIM_ACCOUNT)
 		*p++ = 'a';
 	if (s->flags & SLAB_CONSISTENCY_CHECKS)
diff --git a/mm/sparse.c b/mm/sparse.c
index 69904aa6165b..56e057c432f9 100644
--- a/mm/sparse.c
+++ b/mm/sparse.c
@@ -567,7 +567,7 @@ void online_mem_sections(unsigned long start_pfn, unsigned long end_pfn)
 }
 
 #ifdef CONFIG_MEMORY_HOTREMOVE
-/* Mark all memory sections within the pfn range as online */
+/* Mark all memory sections within the pfn range as offline */
 void offline_mem_sections(unsigned long start_pfn, unsigned long end_pfn)
 {
 	unsigned long pfn;
diff --git a/mm/swapfile.c b/mm/swapfile.c
index 2b8d9c3fbb47..cf63b5f01adf 100644
--- a/mm/swapfile.c
+++ b/mm/swapfile.c
@@ -2023,7 +2023,6 @@ static unsigned int find_next_to_unuse(struct swap_info_struct *si,
  * If the boolean frontswap is true, only unuse pages_to_unuse pages;
  * pages_to_unuse==0 means all pages; ignored if frontswap is false
  */
-#define SWAP_UNUSE_MAX_TRIES 3
 int try_to_unuse(unsigned int type, bool frontswap,
 		 unsigned long pages_to_unuse)
 {
@@ -2035,7 +2034,6 @@ int try_to_unuse(unsigned int type, bool frontswap,
 	struct page *page;
 	swp_entry_t entry;
 	unsigned int i;
-	int retries = 0;
 
 	if (!si->inuse_pages)
 		return 0;
@@ -2053,11 +2051,9 @@ retry:
 
 	spin_lock(&mmlist_lock);
 	p = &init_mm.mmlist;
-	while ((p = p->next) != &init_mm.mmlist) {
-		if (signal_pending(current)) {
-			retval = -EINTR;
-			break;
-		}
+	while (si->inuse_pages &&
+	       !signal_pending(current) &&
+	       (p = p->next) != &init_mm.mmlist) {
 
 		mm = list_entry(p, struct mm_struct, mmlist);
 		if (!mmget_not_zero(mm))
@@ -2084,7 +2080,9 @@ retry:
 	mmput(prev_mm);
 
 	i = 0;
-	while ((i = find_next_to_unuse(si, i, frontswap)) != 0) {
+	while (si->inuse_pages &&
+	       !signal_pending(current) &&
+	       (i = find_next_to_unuse(si, i, frontswap)) != 0) {
 
 		entry = swp_entry(type, i);
 		page = find_get_page(swap_address_space(entry), i);
@@ -2117,14 +2115,18 @@ retry:
 	 * If yes, we would need to do retry the unuse logic again.
 	 * Under global memory pressure, swap entries can be reinserted back
 	 * into process space after the mmlist loop above passes over them.
-	 * Its not worth continuosuly retrying to unuse the swap in this case.
-	 * So we try SWAP_UNUSE_MAX_TRIES times.
+	 *
+	 * Limit the number of retries? No: when mmget_not_zero() above fails,
+	 * that mm is likely to be freeing swap from exit_mmap(), which proceeds
+	 * at its own independent pace; and even shmem_writepage() could have
+	 * been preempted after get_swap_page(), temporarily hiding that swap.
+	 * It's easy and robust (though cpu-intensive) just to keep retrying.
 	 */
-	if (++retries >= SWAP_UNUSE_MAX_TRIES)
-		retval = -EBUSY;
-	else if (si->inuse_pages)
-		goto retry;
-
+	if (si->inuse_pages) {
+		if (!signal_pending(current))
+			goto retry;
+		retval = -EINTR;
+	}
 out:
 	return (retval == FRONTSWAP_PAGES_UNUSED) ? 0 : retval;
 }
diff --git a/mm/util.c b/mm/util.c
index d559bde497a9..43a2984bccaa 100644
--- a/mm/util.c
+++ b/mm/util.c
@@ -204,7 +204,7 @@ EXPORT_SYMBOL(vmemdup_user);
  * @s: The string to duplicate
  * @n: Maximum number of bytes to copy, including the trailing NUL.
  *
- * Return: newly allocated copy of @s or %NULL in case of error
+ * Return: newly allocated copy of @s or an ERR_PTR() in case of error
  */
 char *strndup_user(const char __user *s, long n)
 {
diff --git a/mm/vmalloc.c b/mm/vmalloc.c
index e86ba6e74b50..e5e9e1fcac01 100644
--- a/mm/vmalloc.c
+++ b/mm/vmalloc.c
@@ -18,6 +18,7 @@
 #include <linux/interrupt.h>
 #include <linux/proc_fs.h>
 #include <linux/seq_file.h>
+#include <linux/set_memory.h>
 #include <linux/debugobjects.h>
 #include <linux/kallsyms.h>
 #include <linux/list.h>
@@ -1059,24 +1060,9 @@ static void vb_free(const void *addr, unsigned long size)
 		spin_unlock(&vb->lock);
 }
 
-/**
- * vm_unmap_aliases - unmap outstanding lazy aliases in the vmap layer
- *
- * The vmap/vmalloc layer lazily flushes kernel virtual mappings primarily
- * to amortize TLB flushing overheads. What this means is that any page you
- * have now, may, in a former life, have been mapped into kernel virtual
- * address by the vmap layer and so there might be some CPUs with TLB entries
- * still referencing that page (additional to the regular 1:1 kernel mapping).
- *
- * vm_unmap_aliases flushes all such lazy mappings. After it returns, we can
- * be sure that none of the pages we have control over will have any aliases
- * from the vmap layer.
- */
-void vm_unmap_aliases(void)
+static void _vm_unmap_aliases(unsigned long start, unsigned long end, int flush)
 {
-	unsigned long start = ULONG_MAX, end = 0;
 	int cpu;
-	int flush = 0;
 
 	if (unlikely(!vmap_initialized))
 		return;
@@ -1113,6 +1099,27 @@ void vm_unmap_aliases(void)
 		flush_tlb_kernel_range(start, end);
 	mutex_unlock(&vmap_purge_lock);
 }
+
+/**
+ * vm_unmap_aliases - unmap outstanding lazy aliases in the vmap layer
+ *
+ * The vmap/vmalloc layer lazily flushes kernel virtual mappings primarily
+ * to amortize TLB flushing overheads. What this means is that any page you
+ * have now, may, in a former life, have been mapped into kernel virtual
+ * address by the vmap layer and so there might be some CPUs with TLB entries
+ * still referencing that page (additional to the regular 1:1 kernel mapping).
+ *
+ * vm_unmap_aliases flushes all such lazy mappings. After it returns, we can
+ * be sure that none of the pages we have control over will have any aliases
+ * from the vmap layer.
+ */
+void vm_unmap_aliases(void)
+{
+	unsigned long start = ULONG_MAX, end = 0;
+	int flush = 0;
+
+	_vm_unmap_aliases(start, end, flush);
+}
 EXPORT_SYMBOL_GPL(vm_unmap_aliases);
 
 /**
@@ -1505,6 +1512,72 @@ struct vm_struct *remove_vm_area(const void *addr)
 	return NULL;
 }
 
+static inline void set_area_direct_map(const struct vm_struct *area,
+				       int (*set_direct_map)(struct page *page))
+{
+	int i;
+
+	for (i = 0; i < area->nr_pages; i++)
+		if (page_address(area->pages[i]))
+			set_direct_map(area->pages[i]);
+}
+
+/* Handle removing and resetting vm mappings related to the vm_struct. */
+static void vm_remove_mappings(struct vm_struct *area, int deallocate_pages)
+{
+	unsigned long addr = (unsigned long)area->addr;
+	unsigned long start = ULONG_MAX, end = 0;
+	int flush_reset = area->flags & VM_FLUSH_RESET_PERMS;
+	int i;
+
+	/*
+	 * The below block can be removed when all architectures that have
+	 * direct map permissions also have set_direct_map_() implementations.
+	 * This is concerned with resetting the direct map any an vm alias with
+	 * execute permissions, without leaving a RW+X window.
+	 */
+	if (flush_reset && !IS_ENABLED(CONFIG_ARCH_HAS_SET_DIRECT_MAP)) {
+		set_memory_nx(addr, area->nr_pages);
+		set_memory_rw(addr, area->nr_pages);
+	}
+
+	remove_vm_area(area->addr);
+
+	/* If this is not VM_FLUSH_RESET_PERMS memory, no need for the below. */
+	if (!flush_reset)
+		return;
+
+	/*
+	 * If not deallocating pages, just do the flush of the VM area and
+	 * return.
+	 */
+	if (!deallocate_pages) {
+		vm_unmap_aliases();
+		return;
+	}
+
+	/*
+	 * If execution gets here, flush the vm mapping and reset the direct
+	 * map. Find the start and end range of the direct mappings to make sure
+	 * the vm_unmap_aliases() flush includes the direct map.
+	 */
+	for (i = 0; i < area->nr_pages; i++) {
+		if (page_address(area->pages[i])) {
+			start = min(addr, start);
+			end = max(addr, end);
+		}
+	}
+
+	/*
+	 * Set direct map to something invalid so that it won't be cached if
+	 * there are any accesses after the TLB flush, then flush the TLB and
+	 * reset the direct map permissions to the default.
+	 */
+	set_area_direct_map(area, set_direct_map_invalid_noflush);
+	_vm_unmap_aliases(start, end, 1);
+	set_area_direct_map(area, set_direct_map_default_noflush);
+}
+
 static void __vunmap(const void *addr, int deallocate_pages)
 {
 	struct vm_struct *area;
@@ -1526,7 +1599,8 @@ static void __vunmap(const void *addr, int deallocate_pages)
 	debug_check_no_locks_freed(area->addr, get_vm_area_size(area));
 	debug_check_no_obj_freed(area->addr, get_vm_area_size(area));
 
-	remove_vm_area(addr);
+	vm_remove_mappings(area, deallocate_pages);
+
 	if (deallocate_pages) {
 		int i;
 
@@ -1961,8 +2035,9 @@ EXPORT_SYMBOL(vzalloc_node);
  */
 void *vmalloc_exec(unsigned long size)
 {
-	return __vmalloc_node(size, 1, GFP_KERNEL, PAGE_KERNEL_EXEC,
-			      NUMA_NO_NODE, __builtin_return_address(0));
+	return __vmalloc_node_range(size, 1, VMALLOC_START, VMALLOC_END,
+			GFP_KERNEL, PAGE_KERNEL_EXEC, VM_FLUSH_RESET_PERMS,
+			NUMA_NO_NODE, __builtin_return_address(0));
 }
 
 #if defined(CONFIG_64BIT) && defined(CONFIG_ZONE_DMA32)
diff --git a/mm/vmscan.c b/mm/vmscan.c
index a5ad0b35ab8e..a815f73ee4d5 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -2176,7 +2176,6 @@ static void shrink_active_list(unsigned long nr_to_scan,
  *   10TB     320        32GB
  */
 static bool inactive_list_is_low(struct lruvec *lruvec, bool file,
-				 struct mem_cgroup *memcg,
 				 struct scan_control *sc, bool actual_reclaim)
 {
 	enum lru_list active_lru = file * LRU_FILE + LRU_ACTIVE;
@@ -2197,16 +2196,12 @@ static bool inactive_list_is_low(struct lruvec *lruvec, bool file,
 	inactive = lruvec_lru_size(lruvec, inactive_lru, sc->reclaim_idx);
 	active = lruvec_lru_size(lruvec, active_lru, sc->reclaim_idx);
 
-	if (memcg)
-		refaults = memcg_page_state(memcg, WORKINGSET_ACTIVATE);
-	else
-		refaults = node_page_state(pgdat, WORKINGSET_ACTIVATE);
-
 	/*
 	 * When refaults are being observed, it means a new workingset
 	 * is being established. Disable active list protection to get
 	 * rid of the stale workingset quickly.
 	 */
+	refaults = lruvec_page_state(lruvec, WORKINGSET_ACTIVATE);
 	if (file && actual_reclaim && lruvec->refaults != refaults) {
 		inactive_ratio = 0;
 	} else {
@@ -2227,12 +2222,10 @@ static bool inactive_list_is_low(struct lruvec *lruvec, bool file,
 }
 
 static unsigned long shrink_list(enum lru_list lru, unsigned long nr_to_scan,
-				 struct lruvec *lruvec, struct mem_cgroup *memcg,
-				 struct scan_control *sc)
+				 struct lruvec *lruvec, struct scan_control *sc)
 {
 	if (is_active_lru(lru)) {
-		if (inactive_list_is_low(lruvec, is_file_lru(lru),
-					 memcg, sc, true))
+		if (inactive_list_is_low(lruvec, is_file_lru(lru), sc, true))
 			shrink_active_list(nr_to_scan, lruvec, sc, lru);
 		return 0;
 	}
@@ -2332,7 +2325,7 @@ static void get_scan_count(struct lruvec *lruvec, struct mem_cgroup *memcg,
 			 * anonymous pages on the LRU in eligible zones.
 			 * Otherwise, the small LRU gets thrashed.
 			 */
-			if (!inactive_list_is_low(lruvec, false, memcg, sc, false) &&
+			if (!inactive_list_is_low(lruvec, false, sc, false) &&
 			    lruvec_lru_size(lruvec, LRU_INACTIVE_ANON, sc->reclaim_idx)
 					>> sc->priority) {
 				scan_balance = SCAN_ANON;
@@ -2350,7 +2343,7 @@ static void get_scan_count(struct lruvec *lruvec, struct mem_cgroup *memcg,
 	 * lruvec even if it has plenty of old anonymous pages unless the
 	 * system is under heavy pressure.
 	 */
-	if (!inactive_list_is_low(lruvec, true, memcg, sc, false) &&
+	if (!inactive_list_is_low(lruvec, true, sc, false) &&
 	    lruvec_lru_size(lruvec, LRU_INACTIVE_FILE, sc->reclaim_idx) >> sc->priority) {
 		scan_balance = SCAN_FILE;
 		goto out;
@@ -2503,7 +2496,7 @@ static void shrink_node_memcg(struct pglist_data *pgdat, struct mem_cgroup *memc
 				nr[lru] -= nr_to_scan;
 
 				nr_reclaimed += shrink_list(lru, nr_to_scan,
-							    lruvec, memcg, sc);
+							    lruvec, sc);
 			}
 		}
 
@@ -2570,7 +2563,7 @@ static void shrink_node_memcg(struct pglist_data *pgdat, struct mem_cgroup *memc
 	 * Even if we did not try to evict anon pages at all, we want to
 	 * rebalance the anon lru active/inactive ratio.
 	 */
-	if (inactive_list_is_low(lruvec, false, memcg, sc, true))
+	if (inactive_list_is_low(lruvec, false, sc, true))
 		shrink_active_list(SWAP_CLUSTER_MAX, lruvec,
 				   sc, LRU_ACTIVE_ANON);
 }
@@ -2969,12 +2962,8 @@ static void snapshot_refaults(struct mem_cgroup *root_memcg, pg_data_t *pgdat)
 		unsigned long refaults;
 		struct lruvec *lruvec;
 
-		if (memcg)
-			refaults = memcg_page_state(memcg, WORKINGSET_ACTIVATE);
-		else
-			refaults = node_page_state(pgdat, WORKINGSET_ACTIVATE);
-
 		lruvec = mem_cgroup_lruvec(pgdat, memcg);
+		refaults = lruvec_page_state(lruvec, WORKINGSET_ACTIVATE);
 		lruvec->refaults = refaults;
 	} while ((memcg = mem_cgroup_iter(root_memcg, memcg, NULL)));
 }
@@ -3339,7 +3328,7 @@ static void age_active_anon(struct pglist_data *pgdat,
 	do {
 		struct lruvec *lruvec = mem_cgroup_lruvec(pgdat, memcg);
 
-		if (inactive_list_is_low(lruvec, false, memcg, sc, true))
+		if (inactive_list_is_low(lruvec, false, sc, true))
 			shrink_active_list(SWAP_CLUSTER_MAX, lruvec,
 					   sc, LRU_ACTIVE_ANON);
 
diff --git a/mm/vmstat.c b/mm/vmstat.c
index 36b56f858f0f..a7d493366a65 100644
--- a/mm/vmstat.c
+++ b/mm/vmstat.c
@@ -1274,13 +1274,8 @@ const char * const vmstat_text[] = {
 #endif
 #endif /* CONFIG_MEMORY_BALLOON */
 #ifdef CONFIG_DEBUG_TLBFLUSH
-#ifdef CONFIG_SMP
 	"nr_tlb_remote_flush",
 	"nr_tlb_remote_flush_received",
-#else
-	"", /* nr_tlb_remote_flush */
-	"", /* nr_tlb_remote_flush_received */
-#endif /* CONFIG_SMP */
 	"nr_tlb_local_flush_all",
 	"nr_tlb_local_flush_one",
 #endif /* CONFIG_DEBUG_TLBFLUSH */
diff --git a/net/8021q/vlan_dev.c b/net/8021q/vlan_dev.c
index 15293c2a5dd8..8d77b6ee4477 100644
--- a/net/8021q/vlan_dev.c
+++ b/net/8021q/vlan_dev.c
@@ -443,27 +443,29 @@ static int vlan_dev_fcoe_disable(struct net_device *dev)
 	return rc;
 }
 
-static int vlan_dev_fcoe_get_wwn(struct net_device *dev, u64 *wwn, int type)
+static int vlan_dev_fcoe_ddp_target(struct net_device *dev, u16 xid,
+				    struct scatterlist *sgl, unsigned int sgc)
 {
 	struct net_device *real_dev = vlan_dev_priv(dev)->real_dev;
 	const struct net_device_ops *ops = real_dev->netdev_ops;
-	int rc = -EINVAL;
+	int rc = 0;
+
+	if (ops->ndo_fcoe_ddp_target)
+		rc = ops->ndo_fcoe_ddp_target(real_dev, xid, sgl, sgc);
 
-	if (ops->ndo_fcoe_get_wwn)
-		rc = ops->ndo_fcoe_get_wwn(real_dev, wwn, type);
 	return rc;
 }
+#endif
 
-static int vlan_dev_fcoe_ddp_target(struct net_device *dev, u16 xid,
-				    struct scatterlist *sgl, unsigned int sgc)
+#ifdef NETDEV_FCOE_WWNN
+static int vlan_dev_fcoe_get_wwn(struct net_device *dev, u64 *wwn, int type)
 {
 	struct net_device *real_dev = vlan_dev_priv(dev)->real_dev;
 	const struct net_device_ops *ops = real_dev->netdev_ops;
-	int rc = 0;
-
-	if (ops->ndo_fcoe_ddp_target)
-		rc = ops->ndo_fcoe_ddp_target(real_dev, xid, sgl, sgc);
+	int rc = -EINVAL;
 
+	if (ops->ndo_fcoe_get_wwn)
+		rc = ops->ndo_fcoe_get_wwn(real_dev, wwn, type);
 	return rc;
 }
 #endif
@@ -794,9 +796,11 @@ static const struct net_device_ops vlan_netdev_ops = {
 	.ndo_fcoe_ddp_done	= vlan_dev_fcoe_ddp_done,
 	.ndo_fcoe_enable	= vlan_dev_fcoe_enable,
 	.ndo_fcoe_disable	= vlan_dev_fcoe_disable,
-	.ndo_fcoe_get_wwn	= vlan_dev_fcoe_get_wwn,
 	.ndo_fcoe_ddp_target	= vlan_dev_fcoe_ddp_target,
 #endif
+#ifdef NETDEV_FCOE_WWNN
+	.ndo_fcoe_get_wwn	= vlan_dev_fcoe_get_wwn,
+#endif
 #ifdef CONFIG_NET_POLL_CONTROLLER
 	.ndo_poll_controller	= vlan_dev_poll_controller,
 	.ndo_netpoll_setup	= vlan_dev_netpoll_setup,
diff --git a/net/appletalk/aarp.c b/net/appletalk/aarp.c
index 49a16cee2aae..420a98bf79b5 100644
--- a/net/appletalk/aarp.c
+++ b/net/appletalk/aarp.c
@@ -879,15 +879,24 @@ static struct notifier_block aarp_notifier = {
 
 static unsigned char aarp_snap_id[] = { 0x00, 0x00, 0x00, 0x80, 0xF3 };
 
-void __init aarp_proto_init(void)
+int __init aarp_proto_init(void)
 {
+	int rc;
+
 	aarp_dl = register_snap_client(aarp_snap_id, aarp_rcv);
-	if (!aarp_dl)
+	if (!aarp_dl) {
 		printk(KERN_CRIT "Unable to register AARP with SNAP.\n");
+		return -ENOMEM;
+	}
 	timer_setup(&aarp_timer, aarp_expire_timeout, 0);
 	aarp_timer.expires  = jiffies + sysctl_aarp_expiry_time;
 	add_timer(&aarp_timer);
-	register_netdevice_notifier(&aarp_notifier);
+	rc = register_netdevice_notifier(&aarp_notifier);
+	if (rc) {
+		del_timer_sync(&aarp_timer);
+		unregister_snap_client(aarp_dl);
+	}
+	return rc;
 }
 
 /* Remove the AARP entries associated with a device. */
diff --git a/net/appletalk/ddp.c b/net/appletalk/ddp.c
index 795fbc6c06aa..dbe8b1993be9 100644
--- a/net/appletalk/ddp.c
+++ b/net/appletalk/ddp.c
@@ -1904,9 +1904,6 @@ static unsigned char ddp_snap_id[] = { 0x08, 0x00, 0x07, 0x80, 0x9B };
 EXPORT_SYMBOL(atrtr_get_dev);
 EXPORT_SYMBOL(atalk_find_dev_addr);
 
-static const char atalk_err_snap[] __initconst =
-	KERN_CRIT "Unable to register DDP with SNAP.\n";
-
 /* Called by proto.c on kernel start up */
 static int __init atalk_init(void)
 {
@@ -1921,17 +1918,23 @@ static int __init atalk_init(void)
 		goto out_proto;
 
 	ddp_dl = register_snap_client(ddp_snap_id, atalk_rcv);
-	if (!ddp_dl)
-		printk(atalk_err_snap);
+	if (!ddp_dl) {
+		pr_crit("Unable to register DDP with SNAP.\n");
+		rc = -ENOMEM;
+		goto out_sock;
+	}
 
 	dev_add_pack(&ltalk_packet_type);
 	dev_add_pack(&ppptalk_packet_type);
 
 	rc = register_netdevice_notifier(&ddp_notifier);
 	if (rc)
-		goto out_sock;
+		goto out_snap;
+
+	rc = aarp_proto_init();
+	if (rc)
+		goto out_dev;
 
-	aarp_proto_init();
 	rc = atalk_proc_init();
 	if (rc)
 		goto out_aarp;
@@ -1945,11 +1948,13 @@ out_proc:
 	atalk_proc_exit();
 out_aarp:
 	aarp_cleanup_module();
+out_dev:
 	unregister_netdevice_notifier(&ddp_notifier);
-out_sock:
+out_snap:
 	dev_remove_pack(&ppptalk_packet_type);
 	dev_remove_pack(&ltalk_packet_type);
 	unregister_snap_client(ddp_dl);
+out_sock:
 	sock_unregister(PF_APPLETALK);
 out_proto:
 	proto_unregister(&ddp_proto);
diff --git a/net/atm/lec.c b/net/atm/lec.c
index d7f5cf5b7594..ad4f829193f0 100644
--- a/net/atm/lec.c
+++ b/net/atm/lec.c
@@ -710,7 +710,10 @@ static int lec_vcc_attach(struct atm_vcc *vcc, void __user *arg)
 
 static int lec_mcast_attach(struct atm_vcc *vcc, int arg)
 {
-	if (arg < 0 || arg >= MAX_LEC_ITF || !dev_lec[arg])
+	if (arg < 0 || arg >= MAX_LEC_ITF)
+		return -EINVAL;
+	arg = array_index_nospec(arg, MAX_LEC_ITF);
+	if (!dev_lec[arg])
 		return -EINVAL;
 	vcc->proto_data = dev_lec[arg];
 	return lec_mcast_make(netdev_priv(dev_lec[arg]), vcc);
@@ -728,6 +731,7 @@ static int lecd_attach(struct atm_vcc *vcc, int arg)
 		i = arg;
 	if (arg >= MAX_LEC_ITF)
 		return -EINVAL;
+	i = array_index_nospec(arg, MAX_LEC_ITF);
 	if (!dev_lec[i]) {
 		int size;
 
diff --git a/net/batman-adv/bat_v_elp.c b/net/batman-adv/bat_v_elp.c
index a9b7919c9de5..d5df0114f08a 100644
--- a/net/batman-adv/bat_v_elp.c
+++ b/net/batman-adv/bat_v_elp.c
@@ -104,8 +104,10 @@ static u32 batadv_v_elp_get_throughput(struct batadv_hardif_neigh_node *neigh)
 
 		ret = cfg80211_get_station(real_netdev, neigh->addr, &sinfo);
 
-		/* free the TID stats immediately */
-		cfg80211_sinfo_release_content(&sinfo);
+		if (!ret) {
+			/* free the TID stats immediately */
+			cfg80211_sinfo_release_content(&sinfo);
+		}
 
 		dev_put(real_netdev);
 		if (ret == -ENOENT) {
diff --git a/net/batman-adv/bridge_loop_avoidance.c b/net/batman-adv/bridge_loop_avoidance.c
index ef39aabdb694..4fb01108e5f5 100644
--- a/net/batman-adv/bridge_loop_avoidance.c
+++ b/net/batman-adv/bridge_loop_avoidance.c
@@ -803,6 +803,8 @@ static void batadv_bla_del_claim(struct batadv_priv *bat_priv,
 				 const u8 *mac, const unsigned short vid)
 {
 	struct batadv_bla_claim search_claim, *claim;
+	struct batadv_bla_claim *claim_removed_entry;
+	struct hlist_node *claim_removed_node;
 
 	ether_addr_copy(search_claim.addr, mac);
 	search_claim.vid = vid;
@@ -813,10 +815,18 @@ static void batadv_bla_del_claim(struct batadv_priv *bat_priv,
 	batadv_dbg(BATADV_DBG_BLA, bat_priv, "%s(): %pM, vid %d\n", __func__,
 		   mac, batadv_print_vid(vid));
 
-	batadv_hash_remove(bat_priv->bla.claim_hash, batadv_compare_claim,
-			   batadv_choose_claim, claim);
-	batadv_claim_put(claim); /* reference from the hash is gone */
+	claim_removed_node = batadv_hash_remove(bat_priv->bla.claim_hash,
+						batadv_compare_claim,
+						batadv_choose_claim, claim);
+	if (!claim_removed_node)
+		goto free_claim;
 
+	/* reference from the hash is gone */
+	claim_removed_entry = hlist_entry(claim_removed_node,
+					  struct batadv_bla_claim, hash_entry);
+	batadv_claim_put(claim_removed_entry);
+
+free_claim:
 	/* don't need the reference from hash_find() anymore */
 	batadv_claim_put(claim);
 }
diff --git a/net/batman-adv/sysfs.c b/net/batman-adv/sysfs.c
index 0b4b3fb778a6..208655cf6717 100644
--- a/net/batman-adv/sysfs.c
+++ b/net/batman-adv/sysfs.c
@@ -1116,9 +1116,9 @@ static ssize_t batadv_store_throughput_override(struct kobject *kobj,
 						struct attribute *attr,
 						char *buff, size_t count)
 {
-	struct batadv_priv *bat_priv = batadv_kobj_to_batpriv(kobj);
 	struct net_device *net_dev = batadv_kobj_to_netdev(kobj);
 	struct batadv_hard_iface *hard_iface;
+	struct batadv_priv *bat_priv;
 	u32 tp_override;
 	u32 old_tp_override;
 	bool ret;
@@ -1147,7 +1147,10 @@ static ssize_t batadv_store_throughput_override(struct kobject *kobj,
 
 	atomic_set(&hard_iface->bat_v.throughput_override, tp_override);
 
-	batadv_netlink_notify_hardif(bat_priv, hard_iface);
+	if (hard_iface->soft_iface) {
+		bat_priv = netdev_priv(hard_iface->soft_iface);
+		batadv_netlink_notify_hardif(bat_priv, hard_iface);
+	}
 
 out:
 	batadv_hardif_put(hard_iface);
diff --git a/net/batman-adv/translation-table.c b/net/batman-adv/translation-table.c
index f73d79139ae7..26c4e2493ddf 100644
--- a/net/batman-adv/translation-table.c
+++ b/net/batman-adv/translation-table.c
@@ -616,14 +616,26 @@ static void batadv_tt_global_free(struct batadv_priv *bat_priv,
 				  struct batadv_tt_global_entry *tt_global,
 				  const char *message)
 {
+	struct batadv_tt_global_entry *tt_removed_entry;
+	struct hlist_node *tt_removed_node;
+
 	batadv_dbg(BATADV_DBG_TT, bat_priv,
 		   "Deleting global tt entry %pM (vid: %d): %s\n",
 		   tt_global->common.addr,
 		   batadv_print_vid(tt_global->common.vid), message);
 
-	batadv_hash_remove(bat_priv->tt.global_hash, batadv_compare_tt,
-			   batadv_choose_tt, &tt_global->common);
-	batadv_tt_global_entry_put(tt_global);
+	tt_removed_node = batadv_hash_remove(bat_priv->tt.global_hash,
+					     batadv_compare_tt,
+					     batadv_choose_tt,
+					     &tt_global->common);
+	if (!tt_removed_node)
+		return;
+
+	/* drop reference of remove hash entry */
+	tt_removed_entry = hlist_entry(tt_removed_node,
+				       struct batadv_tt_global_entry,
+				       common.hash_entry);
+	batadv_tt_global_entry_put(tt_removed_entry);
 }
 
 /**
@@ -1337,9 +1349,10 @@ u16 batadv_tt_local_remove(struct batadv_priv *bat_priv, const u8 *addr,
 			   unsigned short vid, const char *message,
 			   bool roaming)
 {
+	struct batadv_tt_local_entry *tt_removed_entry;
 	struct batadv_tt_local_entry *tt_local_entry;
 	u16 flags, curr_flags = BATADV_NO_FLAGS;
-	void *tt_entry_exists;
+	struct hlist_node *tt_removed_node;
 
 	tt_local_entry = batadv_tt_local_hash_find(bat_priv, addr, vid);
 	if (!tt_local_entry)
@@ -1368,15 +1381,18 @@ u16 batadv_tt_local_remove(struct batadv_priv *bat_priv, const u8 *addr,
 	 */
 	batadv_tt_local_event(bat_priv, tt_local_entry, BATADV_TT_CLIENT_DEL);
 
-	tt_entry_exists = batadv_hash_remove(bat_priv->tt.local_hash,
+	tt_removed_node = batadv_hash_remove(bat_priv->tt.local_hash,
 					     batadv_compare_tt,
 					     batadv_choose_tt,
 					     &tt_local_entry->common);
-	if (!tt_entry_exists)
+	if (!tt_removed_node)
 		goto out;
 
-	/* extra call to free the local tt entry */
-	batadv_tt_local_entry_put(tt_local_entry);
+	/* drop reference of remove hash entry */
+	tt_removed_entry = hlist_entry(tt_removed_node,
+				       struct batadv_tt_local_entry,
+				       common.hash_entry);
+	batadv_tt_local_entry_put(tt_removed_entry);
 
 out:
 	if (tt_local_entry)
diff --git a/net/bluetooth/amp.c b/net/bluetooth/amp.c
index 78bec8df8525..aaa39409eeb7 100644
--- a/net/bluetooth/amp.c
+++ b/net/bluetooth/amp.c
@@ -161,7 +161,6 @@ static int hmac_sha256(u8 *key, u8 ksize, char *plaintext, u8 psize, u8 *output)
 	}
 
 	shash->tfm = tfm;
-	shash->flags = CRYPTO_TFM_REQ_MAY_SLEEP;
 
 	ret = crypto_shash_digest(shash, plaintext, psize, output);
 
diff --git a/net/bluetooth/sco.c b/net/bluetooth/sco.c
index 9a580999ca57..d892b7c3cc42 100644
--- a/net/bluetooth/sco.c
+++ b/net/bluetooth/sco.c
@@ -523,12 +523,12 @@ static int sco_sock_bind(struct socket *sock, struct sockaddr *addr,
 	struct sock *sk = sock->sk;
 	int err = 0;
 
-	BT_DBG("sk %p %pMR", sk, &sa->sco_bdaddr);
-
 	if (!addr || addr_len < sizeof(struct sockaddr_sco) ||
 	    addr->sa_family != AF_BLUETOOTH)
 		return -EINVAL;
 
+	BT_DBG("sk %p %pMR", sk, &sa->sco_bdaddr);
+
 	lock_sock(sk);
 
 	if (sk->sk_state != BT_OPEN) {
diff --git a/net/bluetooth/smp.c b/net/bluetooth/smp.c
index 621146d04c03..e68c715f8d37 100644
--- a/net/bluetooth/smp.c
+++ b/net/bluetooth/smp.c
@@ -183,7 +183,6 @@ static int aes_cmac(struct crypto_shash *tfm, const u8 k[16], const u8 *m,
 	}
 
 	desc->tfm = tfm;
-	desc->flags = 0;
 
 	/* Swap key and message from LSB to MSB */
 	swap_buf(k, tmp, 16);
diff --git a/net/bridge/br_input.c b/net/bridge/br_input.c
index 5ea7e56119c1..ba303ee99b9b 100644
--- a/net/bridge/br_input.c
+++ b/net/bridge/br_input.c
@@ -197,13 +197,10 @@ static void __br_handle_local_finish(struct sk_buff *skb)
 /* note: already called with rcu_read_lock */
 static int br_handle_local_finish(struct net *net, struct sock *sk, struct sk_buff *skb)
 {
-	struct net_bridge_port *p = br_port_get_rcu(skb->dev);
-
 	__br_handle_local_finish(skb);
 
-	BR_INPUT_SKB_CB(skb)->brdev = p->br->dev;
-	br_pass_frame_up(skb);
-	return 0;
+	/* return 1 to signal the okfn() was called so it's ok to use the skb */
+	return 1;
 }
 
 /*
@@ -280,10 +277,18 @@ rx_handler_result_t br_handle_frame(struct sk_buff **pskb)
 				goto forward;
 		}
 
-		/* Deliver packet to local host only */
-		NF_HOOK(NFPROTO_BRIDGE, NF_BR_LOCAL_IN, dev_net(skb->dev),
-			NULL, skb, skb->dev, NULL, br_handle_local_finish);
-		return RX_HANDLER_CONSUMED;
+		/* The else clause should be hit when nf_hook():
+		 *   - returns < 0 (drop/error)
+		 *   - returns = 0 (stolen/nf_queue)
+		 * Thus return 1 from the okfn() to signal the skb is ok to pass
+		 */
+		if (NF_HOOK(NFPROTO_BRIDGE, NF_BR_LOCAL_IN,
+			    dev_net(skb->dev), NULL, skb, skb->dev, NULL,
+			    br_handle_local_finish) == 1) {
+			return RX_HANDLER_PASS;
+		} else {
+			return RX_HANDLER_CONSUMED;
+		}
 	}
 
 forward:
diff --git a/net/bridge/br_multicast.c b/net/bridge/br_multicast.c
index a0e369179f6d..45e7f4173bba 100644
--- a/net/bridge/br_multicast.c
+++ b/net/bridge/br_multicast.c
@@ -601,6 +601,7 @@ static int br_ip4_multicast_add_group(struct net_bridge *br,
 	if (ipv4_is_local_multicast(group))
 		return 0;
 
+	memset(&br_group, 0, sizeof(br_group));
 	br_group.u.ip4 = group;
 	br_group.proto = htons(ETH_P_IP);
 	br_group.vid = vid;
@@ -1497,6 +1498,7 @@ static void br_ip4_multicast_leave_group(struct net_bridge *br,
 
 	own_query = port ? &port->ip4_own_query : &br->ip4_own_query;
 
+	memset(&br_group, 0, sizeof(br_group));
 	br_group.u.ip4 = group;
 	br_group.proto = htons(ETH_P_IP);
 	br_group.vid = vid;
@@ -1520,6 +1522,7 @@ static void br_ip6_multicast_leave_group(struct net_bridge *br,
 
 	own_query = port ? &port->ip6_own_query : &br->ip6_own_query;
 
+	memset(&br_group, 0, sizeof(br_group));
 	br_group.u.ip6 = *group;
 	br_group.proto = htons(ETH_P_IPV6);
 	br_group.vid = vid;
@@ -2028,7 +2031,8 @@ static void br_multicast_start_querier(struct net_bridge *br,
 
 	__br_multicast_open(br, query);
 
-	list_for_each_entry(port, &br->port_list, list) {
+	rcu_read_lock();
+	list_for_each_entry_rcu(port, &br->port_list, list) {
 		if (port->state == BR_STATE_DISABLED ||
 		    port->state == BR_STATE_BLOCKING)
 			continue;
@@ -2040,6 +2044,7 @@ static void br_multicast_start_querier(struct net_bridge *br,
 			br_multicast_enable(&port->ip6_own_query);
 #endif
 	}
+	rcu_read_unlock();
 }
 
 int br_multicast_toggle(struct net_bridge *br, unsigned long val)
diff --git a/net/bridge/br_netfilter_hooks.c b/net/bridge/br_netfilter_hooks.c
index 9d34de68571b..22afa566cbce 100644
--- a/net/bridge/br_netfilter_hooks.c
+++ b/net/bridge/br_netfilter_hooks.c
@@ -502,6 +502,7 @@ static unsigned int br_nf_pre_routing(void *priv,
 	nf_bridge->ipv4_daddr = ip_hdr(skb)->daddr;
 
 	skb->protocol = htons(ETH_P_IP);
+	skb->transport_header = skb->network_header + ip_hdr(skb)->ihl * 4;
 
 	NF_HOOK(NFPROTO_IPV4, NF_INET_PRE_ROUTING, state->net, state->sk, skb,
 		skb->dev, NULL,
diff --git a/net/bridge/br_netfilter_ipv6.c b/net/bridge/br_netfilter_ipv6.c
index 564710f88f93..e88d6641647b 100644
--- a/net/bridge/br_netfilter_ipv6.c
+++ b/net/bridge/br_netfilter_ipv6.c
@@ -235,6 +235,8 @@ unsigned int br_nf_pre_routing_ipv6(void *priv,
 	nf_bridge->ipv6_daddr = ipv6_hdr(skb)->daddr;
 
 	skb->protocol = htons(ETH_P_IPV6);
+	skb->transport_header = skb->network_header + sizeof(struct ipv6hdr);
+
 	NF_HOOK(NFPROTO_IPV6, NF_INET_PRE_ROUTING, state->net, state->sk, skb,
 		skb->dev, NULL,
 		br_nf_pre_routing_finish_ipv6);
diff --git a/net/bridge/br_netlink.c b/net/bridge/br_netlink.c
index 9c07591b0232..7104cf13da84 100644
--- a/net/bridge/br_netlink.c
+++ b/net/bridge/br_netlink.c
@@ -1441,7 +1441,7 @@ static int br_fill_info(struct sk_buff *skb, const struct net_device *brdev)
 	    nla_put_u8(skb, IFLA_BR_VLAN_STATS_ENABLED,
 		       br_opt_get(br, BROPT_VLAN_STATS_ENABLED)) ||
 	    nla_put_u8(skb, IFLA_BR_VLAN_STATS_PER_PORT,
-		       br_opt_get(br, IFLA_BR_VLAN_STATS_PER_PORT)))
+		       br_opt_get(br, BROPT_VLAN_STATS_PER_PORT)))
 		return -EMSGSIZE;
 #endif
 #ifdef CONFIG_BRIDGE_IGMP_SNOOPING
diff --git a/net/bridge/netfilter/ebtables.c b/net/bridge/netfilter/ebtables.c
index eb15891f8b9f..3cad01ac64e4 100644
--- a/net/bridge/netfilter/ebtables.c
+++ b/net/bridge/netfilter/ebtables.c
@@ -2032,7 +2032,8 @@ static int ebt_size_mwt(struct compat_ebt_entry_mwt *match32,
 		if (match_kern)
 			match_kern->match_size = ret;
 
-		if (WARN_ON(type == EBT_COMPAT_TARGET && size_left))
+		/* rule should have no remaining data after target */
+		if (type == EBT_COMPAT_TARGET && size_left)
 			return -EINVAL;
 
 		match32 = (struct compat_ebt_entry_mwt *) buf;
diff --git a/net/ceph/messenger.c b/net/ceph/messenger.c
index 7e71b0df1fbc..3083988ce729 100644
--- a/net/ceph/messenger.c
+++ b/net/ceph/messenger.c
@@ -840,6 +840,7 @@ static bool ceph_msg_data_bio_advance(struct ceph_msg_data_cursor *cursor,
 					size_t bytes)
 {
 	struct ceph_bio_iter *it = &cursor->bio_iter;
+	struct page *page = bio_iter_page(it->bio, it->iter);
 
 	BUG_ON(bytes > cursor->resid);
 	BUG_ON(bytes > bio_iter_len(it->bio, it->iter));
@@ -851,7 +852,8 @@ static bool ceph_msg_data_bio_advance(struct ceph_msg_data_cursor *cursor,
 		return false;   /* no more data */
 	}
 
-	if (!bytes || (it->iter.bi_size && it->iter.bi_bvec_done))
+	if (!bytes || (it->iter.bi_size && it->iter.bi_bvec_done &&
+		       page == bio_iter_page(it->bio, it->iter)))
 		return false;	/* more bytes to process in this segment */
 
 	if (!it->iter.bi_size) {
@@ -899,6 +901,7 @@ static bool ceph_msg_data_bvecs_advance(struct ceph_msg_data_cursor *cursor,
 					size_t bytes)
 {
 	struct bio_vec *bvecs = cursor->data->bvec_pos.bvecs;
+	struct page *page = bvec_iter_page(bvecs, cursor->bvec_iter);
 
 	BUG_ON(bytes > cursor->resid);
 	BUG_ON(bytes > bvec_iter_len(bvecs, cursor->bvec_iter));
@@ -910,7 +913,8 @@ static bool ceph_msg_data_bvecs_advance(struct ceph_msg_data_cursor *cursor,
 		return false;   /* no more data */
 	}
 
-	if (!bytes || cursor->bvec_iter.bi_bvec_done)
+	if (!bytes || (cursor->bvec_iter.bi_bvec_done &&
+		       page == bvec_iter_page(bvecs, cursor->bvec_iter)))
 		return false;	/* more bytes to process in this segment */
 
 	BUG_ON(cursor->last_piece);
diff --git a/net/core/datagram.c b/net/core/datagram.c
index b2651bb6d2a3..e657289db4ac 100644
--- a/net/core/datagram.c
+++ b/net/core/datagram.c
@@ -279,7 +279,7 @@ struct sk_buff *__skb_try_recv_datagram(struct sock *sk, unsigned int flags,
 			break;
 
 		sk_busy_loop(sk, flags & MSG_DONTWAIT);
-	} while (!skb_queue_empty(&sk->sk_receive_queue));
+	} while (sk->sk_receive_queue.prev != *last);
 
 	error = -EAGAIN;
 
diff --git a/net/core/dev.c b/net/core/dev.c
index 2b67f2aa59dd..f409406254dd 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -1184,7 +1184,21 @@ int dev_change_name(struct net_device *dev, const char *newname)
 	BUG_ON(!dev_net(dev));
 
 	net = dev_net(dev);
-	if (dev->flags & IFF_UP)
+
+	/* Some auto-enslaved devices e.g. failover slaves are
+	 * special, as userspace might rename the device after
+	 * the interface had been brought up and running since
+	 * the point kernel initiated auto-enslavement. Allow
+	 * live name change even when these slave devices are
+	 * up and running.
+	 *
+	 * Typically, users of these auto-enslaving devices
+	 * don't actually care about slave name change, as
+	 * they are supposed to operate on master interface
+	 * directly.
+	 */
+	if (dev->flags & IFF_UP &&
+	    likely(!(dev->priv_flags & IFF_LIVE_RENAME_OK)))
 		return -EBUSY;
 
 	write_seqcount_begin(&devnet_rename_seq);
@@ -5014,8 +5028,10 @@ static inline void __netif_receive_skb_list_ptype(struct list_head *head,
 	if (pt_prev->list_func != NULL)
 		pt_prev->list_func(head, pt_prev, orig_dev);
 	else
-		list_for_each_entry_safe(skb, next, head, list)
+		list_for_each_entry_safe(skb, next, head, list) {
+			skb_list_del_init(skb);
 			pt_prev->func(skb, skb->dev, pt_prev, orig_dev);
+		}
 }
 
 static void __netif_receive_skb_list_core(struct list_head *head, bool pfmemalloc)
diff --git a/net/core/devlink.c b/net/core/devlink.c
index 78e22cea4cc7..da0a29f30885 100644
--- a/net/core/devlink.c
+++ b/net/core/devlink.c
@@ -3897,6 +3897,11 @@ static int devlink_nl_cmd_info_get_dumpit(struct sk_buff *msg,
 			continue;
 		}
 
+		if (!devlink->ops->info_get) {
+			idx++;
+			continue;
+		}
+
 		mutex_lock(&devlink->lock);
 		err = devlink_nl_info_fill(msg, devlink, DEVLINK_CMD_INFO_GET,
 					   NETLINK_CB(cb->skb).portid,
diff --git a/net/core/ethtool.c b/net/core/ethtool.c
index b1eb32419732..36ed619faf36 100644
--- a/net/core/ethtool.c
+++ b/net/core/ethtool.c
@@ -1797,11 +1797,16 @@ static int ethtool_get_strings(struct net_device *dev, void __user *useraddr)
 	WARN_ON_ONCE(!ret);
 
 	gstrings.len = ret;
-	data = vzalloc(array_size(gstrings.len, ETH_GSTRING_LEN));
-	if (gstrings.len && !data)
-		return -ENOMEM;
 
-	__ethtool_get_strings(dev, gstrings.string_set, data);
+	if (gstrings.len) {
+		data = vzalloc(array_size(gstrings.len, ETH_GSTRING_LEN));
+		if (!data)
+			return -ENOMEM;
+
+		__ethtool_get_strings(dev, gstrings.string_set, data);
+	} else {
+		data = NULL;
+	}
 
 	ret = -EFAULT;
 	if (copy_to_user(useraddr, &gstrings, sizeof(gstrings)))
@@ -1897,11 +1902,15 @@ static int ethtool_get_stats(struct net_device *dev, void __user *useraddr)
 		return -EFAULT;
 
 	stats.n_stats = n_stats;
-	data = vzalloc(array_size(n_stats, sizeof(u64)));
-	if (n_stats && !data)
-		return -ENOMEM;
 
-	ops->get_ethtool_stats(dev, &stats, data);
+	if (n_stats) {
+		data = vzalloc(array_size(n_stats, sizeof(u64)));
+		if (!data)
+			return -ENOMEM;
+		ops->get_ethtool_stats(dev, &stats, data);
+	} else {
+		data = NULL;
+	}
 
 	ret = -EFAULT;
 	if (copy_to_user(useraddr, &stats, sizeof(stats)))
@@ -1941,16 +1950,21 @@ static int ethtool_get_phy_stats(struct net_device *dev, void __user *useraddr)
 		return -EFAULT;
 
 	stats.n_stats = n_stats;
-	data = vzalloc(array_size(n_stats, sizeof(u64)));
-	if (n_stats && !data)
-		return -ENOMEM;
 
-	if (dev->phydev && !ops->get_ethtool_phy_stats) {
-		ret = phy_ethtool_get_stats(dev->phydev, &stats, data);
-		if (ret < 0)
-			return ret;
+	if (n_stats) {
+		data = vzalloc(array_size(n_stats, sizeof(u64)));
+		if (!data)
+			return -ENOMEM;
+
+		if (dev->phydev && !ops->get_ethtool_phy_stats) {
+			ret = phy_ethtool_get_stats(dev->phydev, &stats, data);
+			if (ret < 0)
+				goto out;
+		} else {
+			ops->get_ethtool_phy_stats(dev, &stats, data);
+		}
 	} else {
-		ops->get_ethtool_phy_stats(dev, &stats, data);
+		data = NULL;
 	}
 
 	ret = -EFAULT;
diff --git a/net/core/failover.c b/net/core/failover.c
index 4a92a98ccce9..b5cd3c727285 100644
--- a/net/core/failover.c
+++ b/net/core/failover.c
@@ -80,14 +80,14 @@ static int failover_slave_register(struct net_device *slave_dev)
 		goto err_upper_link;
 	}
 
-	slave_dev->priv_flags |= IFF_FAILOVER_SLAVE;
+	slave_dev->priv_flags |= (IFF_FAILOVER_SLAVE | IFF_LIVE_RENAME_OK);
 
 	if (fops && fops->slave_register &&
 	    !fops->slave_register(slave_dev, failover_dev))
 		return NOTIFY_OK;
 
 	netdev_upper_dev_unlink(slave_dev, failover_dev);
-	slave_dev->priv_flags &= ~IFF_FAILOVER_SLAVE;
+	slave_dev->priv_flags &= ~(IFF_FAILOVER_SLAVE | IFF_LIVE_RENAME_OK);
 err_upper_link:
 	netdev_rx_handler_unregister(slave_dev);
 done:
@@ -121,7 +121,7 @@ int failover_slave_unregister(struct net_device *slave_dev)
 
 	netdev_rx_handler_unregister(slave_dev);
 	netdev_upper_dev_unlink(slave_dev, failover_dev);
-	slave_dev->priv_flags &= ~IFF_FAILOVER_SLAVE;
+	slave_dev->priv_flags &= ~(IFF_FAILOVER_SLAVE | IFF_LIVE_RENAME_OK);
 
 	if (fops && fops->slave_unregister &&
 	    !fops->slave_unregister(slave_dev, failover_dev))
diff --git a/net/core/filter.c b/net/core/filter.c
index f274620945ff..27e61ffd9039 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -1796,8 +1796,6 @@ static const struct bpf_func_proto bpf_skb_pull_data_proto = {
 
 BPF_CALL_1(bpf_sk_fullsock, struct sock *, sk)
 {
-	sk = sk_to_full_sk(sk);
-
 	return sk_fullsock(sk) ? (unsigned long)sk : (unsigned long)NULL;
 }
 
@@ -4385,6 +4383,8 @@ BPF_CALL_3(bpf_bind, struct bpf_sock_addr_kern *, ctx, struct sockaddr *, addr,
 	 * Only binding to IP is supported.
 	 */
 	err = -EINVAL;
+	if (addr_len < offsetofend(struct sockaddr, sa_family))
+		return err;
 	if (addr->sa_family == AF_INET) {
 		if (addr_len < sizeof(struct sockaddr_in))
 			return err;
@@ -5266,7 +5266,7 @@ static const struct bpf_func_proto bpf_sk_release_proto = {
 	.func		= bpf_sk_release,
 	.gpl_only	= false,
 	.ret_type	= RET_INTEGER,
-	.arg1_type	= ARG_PTR_TO_SOCKET,
+	.arg1_type	= ARG_PTR_TO_SOCK_COMMON,
 };
 
 BPF_CALL_5(bpf_xdp_sk_lookup_udp, struct xdp_buff *, ctx,
@@ -5407,8 +5407,6 @@ u32 bpf_tcp_sock_convert_ctx_access(enum bpf_access_type type,
 
 BPF_CALL_1(bpf_tcp_sock, struct sock *, sk)
 {
-	sk = sk_to_full_sk(sk);
-
 	if (sk_fullsock(sk) && sk->sk_protocol == IPPROTO_TCP)
 		return (unsigned long)sk;
 
@@ -5422,6 +5420,23 @@ static const struct bpf_func_proto bpf_tcp_sock_proto = {
 	.arg1_type	= ARG_PTR_TO_SOCK_COMMON,
 };
 
+BPF_CALL_1(bpf_get_listener_sock, struct sock *, sk)
+{
+	sk = sk_to_full_sk(sk);
+
+	if (sk->sk_state == TCP_LISTEN && sock_flag(sk, SOCK_RCU_FREE))
+		return (unsigned long)sk;
+
+	return (unsigned long)NULL;
+}
+
+static const struct bpf_func_proto bpf_get_listener_sock_proto = {
+	.func		= bpf_get_listener_sock,
+	.gpl_only	= false,
+	.ret_type	= RET_PTR_TO_SOCKET_OR_NULL,
+	.arg1_type	= ARG_PTR_TO_SOCK_COMMON,
+};
+
 BPF_CALL_1(bpf_skb_ecn_set_ce, struct sk_buff *, skb)
 {
 	unsigned int iphdr_len;
@@ -5607,6 +5622,8 @@ cg_skb_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
 #ifdef CONFIG_INET
 	case BPF_FUNC_tcp_sock:
 		return &bpf_tcp_sock_proto;
+	case BPF_FUNC_get_listener_sock:
+		return &bpf_get_listener_sock_proto;
 	case BPF_FUNC_skb_ecn_set_ce:
 		return &bpf_skb_ecn_set_ce_proto;
 #endif
@@ -5702,6 +5719,8 @@ tc_cls_act_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
 		return &bpf_sk_release_proto;
 	case BPF_FUNC_tcp_sock:
 		return &bpf_tcp_sock_proto;
+	case BPF_FUNC_get_listener_sock:
+		return &bpf_get_listener_sock_proto;
 #endif
 	default:
 		return bpf_base_func_proto(func_id);
@@ -6596,14 +6615,8 @@ static bool flow_dissector_is_valid_access(int off, int size,
 					   const struct bpf_prog *prog,
 					   struct bpf_insn_access_aux *info)
 {
-	if (type == BPF_WRITE) {
-		switch (off) {
-		case bpf_ctx_range_till(struct __sk_buff, cb[0], cb[4]):
-			break;
-		default:
-			return false;
-		}
-	}
+	if (type == BPF_WRITE)
+		return false;
 
 	switch (off) {
 	case bpf_ctx_range(struct __sk_buff, data):
@@ -6615,11 +6628,7 @@ static bool flow_dissector_is_valid_access(int off, int size,
 	case bpf_ctx_range_ptr(struct __sk_buff, flow_keys):
 		info->reg_type = PTR_TO_FLOW_KEYS;
 		break;
-	case bpf_ctx_range(struct __sk_buff, tc_classid):
-	case bpf_ctx_range(struct __sk_buff, data_meta):
-	case bpf_ctx_range_till(struct __sk_buff, family, local_port):
-	case bpf_ctx_range(struct __sk_buff, tstamp):
-	case bpf_ctx_range(struct __sk_buff, wire_len):
+	default:
 		return false;
 	}
 
diff --git a/net/core/flow_dissector.c b/net/core/flow_dissector.c
index bb1a54747d64..94a450b2191a 100644
--- a/net/core/flow_dissector.c
+++ b/net/core/flow_dissector.c
@@ -707,6 +707,7 @@ bool __skb_flow_bpf_dissect(struct bpf_prog *prog,
 	/* Pass parameters to the BPF program */
 	memset(flow_keys, 0, sizeof(*flow_keys));
 	cb->qdisc_cb.flow_keys = flow_keys;
+	flow_keys->n_proto = skb->protocol;
 	flow_keys->nhoff = skb_network_offset(skb);
 	flow_keys->thoff = flow_keys->nhoff;
 
@@ -716,7 +717,8 @@ bool __skb_flow_bpf_dissect(struct bpf_prog *prog,
 	/* Restore state */
 	memcpy(cb, &cb_saved, sizeof(cb_saved));
 
-	flow_keys->nhoff = clamp_t(u16, flow_keys->nhoff, 0, skb->len);
+	flow_keys->nhoff = clamp_t(u16, flow_keys->nhoff,
+				   skb_network_offset(skb), skb->len);
 	flow_keys->thoff = clamp_t(u16, flow_keys->thoff,
 				   flow_keys->nhoff, skb->len);
 
diff --git a/net/core/net-sysfs.c b/net/core/net-sysfs.c
index 4ff661f6f989..8f8b7b6c2945 100644
--- a/net/core/net-sysfs.c
+++ b/net/core/net-sysfs.c
@@ -928,6 +928,8 @@ static int rx_queue_add_kobject(struct net_device *dev, int index)
 	if (error)
 		return error;
 
+	dev_hold(queue->dev);
+
 	if (dev->sysfs_rx_queue_group) {
 		error = sysfs_create_group(kobj, dev->sysfs_rx_queue_group);
 		if (error) {
@@ -937,7 +939,6 @@ static int rx_queue_add_kobject(struct net_device *dev, int index)
 	}
 
 	kobject_uevent(kobj, KOBJ_ADD);
-	dev_hold(queue->dev);
 
 	return error;
 }
@@ -1464,6 +1465,8 @@ static int netdev_queue_add_kobject(struct net_device *dev, int index)
 	if (error)
 		return error;
 
+	dev_hold(queue->dev);
+
 #ifdef CONFIG_BQL
 	error = sysfs_create_group(kobj, &dql_group);
 	if (error) {
@@ -1473,7 +1476,6 @@ static int netdev_queue_add_kobject(struct net_device *dev, int index)
 #endif
 
 	kobject_uevent(kobj, KOBJ_ADD);
-	dev_hold(queue->dev);
 
 	return 0;
 }
diff --git a/net/core/net_namespace.c b/net/core/net_namespace.c
index 17f36317363d..7e6dcc625701 100644
--- a/net/core/net_namespace.c
+++ b/net/core/net_namespace.c
@@ -304,6 +304,7 @@ static __net_init int setup_net(struct net *net, struct user_namespace *user_ns)
 
 	refcount_set(&net->count, 1);
 	refcount_set(&net->passive, 1);
+	get_random_bytes(&net->hash_mix, sizeof(u32));
 	net->dev_base_seq = 1;
 	net->user_ns = user_ns;
 	idr_init(&net->netns_ids);
diff --git a/net/core/ptp_classifier.c b/net/core/ptp_classifier.c
index 703cf76aa7c2..7109c168b5e0 100644
--- a/net/core/ptp_classifier.c
+++ b/net/core/ptp_classifier.c
@@ -185,9 +185,10 @@ void __init ptp_classifier_init(void)
 		{ 0x16,  0,  0, 0x00000000 },
 		{ 0x06,  0,  0, 0x00000000 },
 	};
-	struct sock_fprog_kern ptp_prog = {
-		.len = ARRAY_SIZE(ptp_filter), .filter = ptp_filter,
-	};
+	struct sock_fprog_kern ptp_prog;
+
+	ptp_prog.len = ARRAY_SIZE(ptp_filter);
+	ptp_prog.filter = ptp_filter;
 
 	BUG_ON(bpf_prog_create(&ptp_insns, &ptp_prog));
 }
diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c
index a51cab95ba64..220c56e93659 100644
--- a/net/core/rtnetlink.c
+++ b/net/core/rtnetlink.c
@@ -4948,7 +4948,7 @@ static int rtnl_valid_stats_req(const struct nlmsghdr *nlh, bool strict_check,
 {
 	struct if_stats_msg *ifsm;
 
-	if (nlh->nlmsg_len < sizeof(*ifsm)) {
+	if (nlh->nlmsg_len < nlmsg_msg_size(sizeof(*ifsm))) {
 		NL_SET_ERR_MSG(extack, "Invalid header for stats dump");
 		return -EINVAL;
 	}
diff --git a/net/core/skbuff.c b/net/core/skbuff.c
index 2415d9cb9b89..40796b8bf820 100644
--- a/net/core/skbuff.c
+++ b/net/core/skbuff.c
@@ -3801,7 +3801,7 @@ int skb_gro_receive(struct sk_buff *p, struct sk_buff *skb)
 	unsigned int delta_truesize;
 	struct sk_buff *lp;
 
-	if (unlikely(p->len + len >= 65536))
+	if (unlikely(p->len + len >= 65536 || NAPI_GRO_CB(skb)->flush))
 		return -E2BIG;
 
 	lp = NAPI_GRO_CB(p)->last;
@@ -5083,7 +5083,8 @@ EXPORT_SYMBOL_GPL(skb_gso_validate_mac_len);
 
 static struct sk_buff *skb_reorder_vlan_header(struct sk_buff *skb)
 {
-	int mac_len;
+	int mac_len, meta_len;
+	void *meta;
 
 	if (skb_cow(skb, skb_headroom(skb)) < 0) {
 		kfree_skb(skb);
@@ -5095,6 +5096,13 @@ static struct sk_buff *skb_reorder_vlan_header(struct sk_buff *skb)
 		memmove(skb_mac_header(skb) + VLAN_HLEN, skb_mac_header(skb),
 			mac_len - VLAN_HLEN - ETH_TLEN);
 	}
+
+	meta_len = skb_metadata_len(skb);
+	if (meta_len) {
+		meta = skb_metadata_end(skb) - meta_len;
+		memmove(meta + VLAN_HLEN, meta, meta_len);
+	}
+
 	skb->mac_header += VLAN_HLEN;
 	return skb;
 }
diff --git a/net/core/sock.c b/net/core/sock.c
index 782343bb925b..067878a1e4c5 100644
--- a/net/core/sock.c
+++ b/net/core/sock.c
@@ -348,7 +348,7 @@ static int sock_get_timeout(long timeo, void *optval, bool old_timeval)
 		tv.tv_usec = ((timeo % HZ) * USEC_PER_SEC) / HZ;
 	}
 
-	if (in_compat_syscall() && !COMPAT_USE_64BIT_TIME) {
+	if (old_timeval && in_compat_syscall() && !COMPAT_USE_64BIT_TIME) {
 		struct old_timeval32 tv32 = { tv.tv_sec, tv.tv_usec };
 		*(struct old_timeval32 *)optval = tv32;
 		return sizeof(tv32);
@@ -372,7 +372,7 @@ static int sock_set_timeout(long *timeo_p, char __user *optval, int optlen, bool
 {
 	struct __kernel_sock_timeval tv;
 
-	if (in_compat_syscall() && !COMPAT_USE_64BIT_TIME) {
+	if (old_timeval && in_compat_syscall() && !COMPAT_USE_64BIT_TIME) {
 		struct old_timeval32 tv32;
 
 		if (optlen < sizeof(tv32))
diff --git a/net/dccp/feat.c b/net/dccp/feat.c
index f227f002c73d..db87d9f58019 100644
--- a/net/dccp/feat.c
+++ b/net/dccp/feat.c
@@ -738,7 +738,12 @@ static int __feat_register_sp(struct list_head *fn, u8 feat, u8 is_local,
 	if (dccp_feat_clone_sp_val(&fval, sp_val, sp_len))
 		return -ENOMEM;
 
-	return dccp_feat_push_change(fn, feat, is_local, mandatory, &fval);
+	if (dccp_feat_push_change(fn, feat, is_local, mandatory, &fval)) {
+		kfree(fval.sp.vec);
+		return -ENOMEM;
+	}
+
+	return 0;
 }
 
 /**
diff --git a/net/dccp/ipv6.c b/net/dccp/ipv6.c
index d5740bad5b18..57d84e9b7b6f 100644
--- a/net/dccp/ipv6.c
+++ b/net/dccp/ipv6.c
@@ -436,8 +436,8 @@ static struct sock *dccp_v6_request_recv_sock(const struct sock *sk,
 		newnp->ipv6_mc_list = NULL;
 		newnp->ipv6_ac_list = NULL;
 		newnp->ipv6_fl_list = NULL;
-		newnp->mcast_oif   = inet6_iif(skb);
-		newnp->mcast_hops  = ipv6_hdr(skb)->hop_limit;
+		newnp->mcast_oif   = inet_iif(skb);
+		newnp->mcast_hops  = ip_hdr(skb)->ttl;
 
 		/*
 		 * No need to charge this sock to the relevant IPv6 refcnt debug socks count
diff --git a/net/dsa/tag_qca.c b/net/dsa/tag_qca.c
index ed4f6dc26365..85c22ada4744 100644
--- a/net/dsa/tag_qca.c
+++ b/net/dsa/tag_qca.c
@@ -98,8 +98,18 @@ static struct sk_buff *qca_tag_rcv(struct sk_buff *skb, struct net_device *dev,
 	return skb;
 }
 
+static int qca_tag_flow_dissect(const struct sk_buff *skb, __be16 *proto,
+                                int *offset)
+{
+	*offset = QCA_HDR_LEN;
+	*proto = ((__be16 *)skb->data)[0];
+
+	return 0;
+}
+
 const struct dsa_device_ops qca_netdev_ops = {
 	.xmit	= qca_tag_xmit,
 	.rcv	= qca_tag_rcv,
+	.flow_dissect = qca_tag_flow_dissect,
 	.overhead = QCA_HDR_LEN,
 };
diff --git a/net/ipv4/esp4.c b/net/ipv4/esp4.c
index 10e809b296ec..fb065a8937ea 100644
--- a/net/ipv4/esp4.c
+++ b/net/ipv4/esp4.c
@@ -226,7 +226,7 @@ static void esp_output_fill_trailer(u8 *tail, int tfclen, int plen, __u8 proto)
 	tail[plen - 1] = proto;
 }
 
-static void esp_output_udp_encap(struct xfrm_state *x, struct sk_buff *skb, struct esp_info *esp)
+static int esp_output_udp_encap(struct xfrm_state *x, struct sk_buff *skb, struct esp_info *esp)
 {
 	int encap_type;
 	struct udphdr *uh;
@@ -234,6 +234,7 @@ static void esp_output_udp_encap(struct xfrm_state *x, struct sk_buff *skb, stru
 	__be16 sport, dport;
 	struct xfrm_encap_tmpl *encap = x->encap;
 	struct ip_esp_hdr *esph = esp->esph;
+	unsigned int len;
 
 	spin_lock_bh(&x->lock);
 	sport = encap->encap_sport;
@@ -241,11 +242,14 @@ static void esp_output_udp_encap(struct xfrm_state *x, struct sk_buff *skb, stru
 	encap_type = encap->encap_type;
 	spin_unlock_bh(&x->lock);
 
+	len = skb->len + esp->tailen - skb_transport_offset(skb);
+	if (len + sizeof(struct iphdr) >= IP_MAX_MTU)
+		return -EMSGSIZE;
+
 	uh = (struct udphdr *)esph;
 	uh->source = sport;
 	uh->dest = dport;
-	uh->len = htons(skb->len + esp->tailen
-		  - skb_transport_offset(skb));
+	uh->len = htons(len);
 	uh->check = 0;
 
 	switch (encap_type) {
@@ -262,6 +266,8 @@ static void esp_output_udp_encap(struct xfrm_state *x, struct sk_buff *skb, stru
 
 	*skb_mac_header(skb) = IPPROTO_UDP;
 	esp->esph = esph;
+
+	return 0;
 }
 
 int esp_output_head(struct xfrm_state *x, struct sk_buff *skb, struct esp_info *esp)
@@ -275,8 +281,12 @@ int esp_output_head(struct xfrm_state *x, struct sk_buff *skb, struct esp_info *
 	int tailen = esp->tailen;
 
 	/* this is non-NULL only with UDP Encapsulation */
-	if (x->encap)
-		esp_output_udp_encap(x, skb, esp);
+	if (x->encap) {
+		int err = esp_output_udp_encap(x, skb, esp);
+
+		if (err < 0)
+			return err;
+	}
 
 	if (!skb_cloned(skb)) {
 		if (tailen <= skb_tailroom(skb)) {
diff --git a/net/ipv4/esp4_offload.c b/net/ipv4/esp4_offload.c
index 8756e0e790d2..d3170a8001b2 100644
--- a/net/ipv4/esp4_offload.c
+++ b/net/ipv4/esp4_offload.c
@@ -52,13 +52,13 @@ static struct sk_buff *esp4_gro_receive(struct list_head *head,
 			goto out;
 
 		if (sp->len == XFRM_MAX_DEPTH)
-			goto out;
+			goto out_reset;
 
 		x = xfrm_state_lookup(dev_net(skb->dev), skb->mark,
 				      (xfrm_address_t *)&ip_hdr(skb)->daddr,
 				      spi, IPPROTO_ESP, AF_INET);
 		if (!x)
-			goto out;
+			goto out_reset;
 
 		sp->xvec[sp->len++] = x;
 		sp->olen++;
@@ -66,7 +66,7 @@ static struct sk_buff *esp4_gro_receive(struct list_head *head,
 		xo = xfrm_offload(skb);
 		if (!xo) {
 			xfrm_state_put(x);
-			goto out;
+			goto out_reset;
 		}
 	}
 
@@ -82,6 +82,8 @@ static struct sk_buff *esp4_gro_receive(struct list_head *head,
 	xfrm_input(skb, IPPROTO_ESP, spi, -2);
 
 	return ERR_PTR(-EINPROGRESS);
+out_reset:
+	secpath_reset(skb);
 out:
 	skb_push(skb, offset);
 	NAPI_GRO_CB(skb)->same_flow = 0;
diff --git a/net/ipv4/fou.c b/net/ipv4/fou.c
index 79e98e21cdd7..12ce6c526d72 100644
--- a/net/ipv4/fou.c
+++ b/net/ipv4/fou.c
@@ -121,6 +121,7 @@ static int gue_udp_recv(struct sock *sk, struct sk_buff *skb)
 	struct guehdr *guehdr;
 	void *data;
 	u16 doffset = 0;
+	u8 proto_ctype;
 
 	if (!fou)
 		return 1;
@@ -212,13 +213,14 @@ static int gue_udp_recv(struct sock *sk, struct sk_buff *skb)
 	if (unlikely(guehdr->control))
 		return gue_control_message(skb, guehdr);
 
+	proto_ctype = guehdr->proto_ctype;
 	__skb_pull(skb, sizeof(struct udphdr) + hdrlen);
 	skb_reset_transport_header(skb);
 
 	if (iptunnel_pull_offloads(skb))
 		goto drop;
 
-	return -guehdr->proto_ctype;
+	return -proto_ctype;
 
 drop:
 	kfree_skb(skb);
diff --git a/net/ipv4/ip_gre.c b/net/ipv4/ip_gre.c
index fd219f7bd3ea..4b0526441476 100644
--- a/net/ipv4/ip_gre.c
+++ b/net/ipv4/ip_gre.c
@@ -259,7 +259,6 @@ static int erspan_rcv(struct sk_buff *skb, struct tnl_ptk_info *tpi,
 	struct net *net = dev_net(skb->dev);
 	struct metadata_dst *tun_dst = NULL;
 	struct erspan_base_hdr *ershdr;
-	struct erspan_metadata *pkt_md;
 	struct ip_tunnel_net *itn;
 	struct ip_tunnel *tunnel;
 	const struct iphdr *iph;
@@ -282,9 +281,6 @@ static int erspan_rcv(struct sk_buff *skb, struct tnl_ptk_info *tpi,
 		if (unlikely(!pskb_may_pull(skb, len)))
 			return PACKET_REJECT;
 
-		ershdr = (struct erspan_base_hdr *)(skb->data + gre_hdr_len);
-		pkt_md = (struct erspan_metadata *)(ershdr + 1);
-
 		if (__iptunnel_pull_header(skb,
 					   len,
 					   htons(ETH_P_TEB),
@@ -292,8 +288,9 @@ static int erspan_rcv(struct sk_buff *skb, struct tnl_ptk_info *tpi,
 			goto drop;
 
 		if (tunnel->collect_md) {
+			struct erspan_metadata *pkt_md, *md;
 			struct ip_tunnel_info *info;
-			struct erspan_metadata *md;
+			unsigned char *gh;
 			__be64 tun_id;
 			__be16 flags;
 
@@ -306,6 +303,14 @@ static int erspan_rcv(struct sk_buff *skb, struct tnl_ptk_info *tpi,
 			if (!tun_dst)
 				return PACKET_REJECT;
 
+			/* skb can be uncloned in __iptunnel_pull_header, so
+			 * old pkt_md is no longer valid and we need to reset
+			 * it
+			 */
+			gh = skb_network_header(skb) +
+			     skb_network_header_len(skb);
+			pkt_md = (struct erspan_metadata *)(gh + gre_hdr_len +
+							    sizeof(*ershdr));
 			md = ip_tunnel_info_opts(&tun_dst->u.tun_info);
 			md->version = ver;
 			md2 = &md->u.md2;
diff --git a/net/ipv4/ip_input.c b/net/ipv4/ip_input.c
index ecce2dc78f17..1132d6d1796a 100644
--- a/net/ipv4/ip_input.c
+++ b/net/ipv4/ip_input.c
@@ -257,11 +257,10 @@ int ip_local_deliver(struct sk_buff *skb)
 		       ip_local_deliver_finish);
 }
 
-static inline bool ip_rcv_options(struct sk_buff *skb)
+static inline bool ip_rcv_options(struct sk_buff *skb, struct net_device *dev)
 {
 	struct ip_options *opt;
 	const struct iphdr *iph;
-	struct net_device *dev = skb->dev;
 
 	/* It looks as overkill, because not all
 	   IP options require packet mangling.
@@ -297,7 +296,7 @@ static inline bool ip_rcv_options(struct sk_buff *skb)
 			}
 		}
 
-		if (ip_options_rcv_srr(skb))
+		if (ip_options_rcv_srr(skb, dev))
 			goto drop;
 	}
 
@@ -353,7 +352,7 @@ static int ip_rcv_finish_core(struct net *net, struct sock *sk,
 	}
 #endif
 
-	if (iph->ihl > 5 && ip_rcv_options(skb))
+	if (iph->ihl > 5 && ip_rcv_options(skb, dev))
 		goto drop;
 
 	rt = skb_rtable(skb);
diff --git a/net/ipv4/ip_options.c b/net/ipv4/ip_options.c
index 32a35043c9f5..3db31bb9df50 100644
--- a/net/ipv4/ip_options.c
+++ b/net/ipv4/ip_options.c
@@ -612,7 +612,7 @@ void ip_forward_options(struct sk_buff *skb)
 	}
 }
 
-int ip_options_rcv_srr(struct sk_buff *skb)
+int ip_options_rcv_srr(struct sk_buff *skb, struct net_device *dev)
 {
 	struct ip_options *opt = &(IPCB(skb)->opt);
 	int srrspace, srrptr;
@@ -647,7 +647,7 @@ int ip_options_rcv_srr(struct sk_buff *skb)
 
 		orefdst = skb->_skb_refdst;
 		skb_dst_set(skb, NULL);
-		err = ip_route_input(skb, nexthop, iph->saddr, iph->tos, skb->dev);
+		err = ip_route_input(skb, nexthop, iph->saddr, iph->tos, dev);
 		rt2 = skb_rtable(skb);
 		if (err || (rt2->rt_type != RTN_UNICAST && rt2->rt_type != RTN_LOCAL)) {
 			skb_dst_drop(skb);
diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c
index c80188875f39..e8bb2e85c5a4 100644
--- a/net/ipv4/ip_output.c
+++ b/net/ipv4/ip_output.c
@@ -519,6 +519,7 @@ static void ip_copy_metadata(struct sk_buff *to, struct sk_buff *from)
 	to->pkt_type = from->pkt_type;
 	to->priority = from->priority;
 	to->protocol = from->protocol;
+	to->skb_iif = from->skb_iif;
 	skb_dst_drop(to);
 	skb_dst_copy(to, from);
 	to->dev = from->dev;
diff --git a/net/ipv4/ip_vti.c b/net/ipv4/ip_vti.c
index 68a21bf75dd0..35d8346742e2 100644
--- a/net/ipv4/ip_vti.c
+++ b/net/ipv4/ip_vti.c
@@ -646,10 +646,8 @@ static int __init vti_init(void)
 
 	msg = "ipip tunnel";
 	err = xfrm4_tunnel_register(&ipip_handler, AF_INET);
-	if (err < 0) {
-		pr_info("%s: cant't register tunnel\n",__func__);
+	if (err < 0)
 		goto xfrm_tunnel_failed;
-	}
 
 	msg = "netlink interface";
 	err = rtnl_link_register(&vti_link_ops);
@@ -659,9 +657,9 @@ static int __init vti_init(void)
 	return err;
 
 rtnl_link_failed:
-	xfrm4_protocol_deregister(&vti_ipcomp4_protocol, IPPROTO_COMP);
-xfrm_tunnel_failed:
 	xfrm4_tunnel_deregister(&ipip_handler, AF_INET);
+xfrm_tunnel_failed:
+	xfrm4_protocol_deregister(&vti_ipcomp4_protocol, IPPROTO_COMP);
 xfrm_proto_comp_failed:
 	xfrm4_protocol_deregister(&vti_ah4_protocol, IPPROTO_AH);
 xfrm_proto_ah_failed:
@@ -676,6 +674,7 @@ pernet_dev_failed:
 static void __exit vti_fini(void)
 {
 	rtnl_link_unregister(&vti_link_ops);
+	xfrm4_tunnel_deregister(&ipip_handler, AF_INET);
 	xfrm4_protocol_deregister(&vti_ipcomp4_protocol, IPPROTO_COMP);
 	xfrm4_protocol_deregister(&vti_ah4_protocol, IPPROTO_AH);
 	xfrm4_protocol_deregister(&vti_esp4_protocol, IPPROTO_ESP);
diff --git a/net/ipv4/netfilter/ipt_CLUSTERIP.c b/net/ipv4/netfilter/ipt_CLUSTERIP.c
index 835d50b279f5..a2a88ab07f7b 100644
--- a/net/ipv4/netfilter/ipt_CLUSTERIP.c
+++ b/net/ipv4/netfilter/ipt_CLUSTERIP.c
@@ -56,7 +56,7 @@ struct clusterip_config {
 #endif
 	enum clusterip_hashmode hash_mode;	/* which hashing mode */
 	u_int32_t hash_initval;			/* hash initialization */
-	struct rcu_head rcu;			/* for call_rcu_bh */
+	struct rcu_head rcu;			/* for call_rcu */
 	struct net *net;			/* netns for pernet list */
 	char ifname[IFNAMSIZ];			/* device ifname */
 };
diff --git a/net/ipv4/route.c b/net/ipv4/route.c
index a5da63e5faa2..6fdf1c195d8e 100644
--- a/net/ipv4/route.c
+++ b/net/ipv4/route.c
@@ -1183,11 +1183,39 @@ static struct dst_entry *ipv4_dst_check(struct dst_entry *dst, u32 cookie)
 	return dst;
 }
 
+static void ipv4_send_dest_unreach(struct sk_buff *skb)
+{
+	struct ip_options opt;
+	int res;
+
+	/* Recompile ip options since IPCB may not be valid anymore.
+	 * Also check we have a reasonable ipv4 header.
+	 */
+	if (!pskb_network_may_pull(skb, sizeof(struct iphdr)) ||
+	    ip_hdr(skb)->version != 4 || ip_hdr(skb)->ihl < 5)
+		return;
+
+	memset(&opt, 0, sizeof(opt));
+	if (ip_hdr(skb)->ihl > 5) {
+		if (!pskb_network_may_pull(skb, ip_hdr(skb)->ihl * 4))
+			return;
+		opt.optlen = ip_hdr(skb)->ihl * 4 - sizeof(struct iphdr);
+
+		rcu_read_lock();
+		res = __ip_options_compile(dev_net(skb->dev), &opt, skb, NULL);
+		rcu_read_unlock();
+
+		if (res)
+			return;
+	}
+	__icmp_send(skb, ICMP_DEST_UNREACH, ICMP_HOST_UNREACH, 0, &opt);
+}
+
 static void ipv4_link_failure(struct sk_buff *skb)
 {
 	struct rtable *rt;
 
-	icmp_send(skb, ICMP_DEST_UNREACH, ICMP_HOST_UNREACH, 0);
+	ipv4_send_dest_unreach(skb);
 
 	rt = skb_rtable(skb);
 	if (rt)
diff --git a/net/ipv4/sysctl_net_ipv4.c b/net/ipv4/sysctl_net_ipv4.c
index ba0fc4b18465..eeb4041fa5f9 100644
--- a/net/ipv4/sysctl_net_ipv4.c
+++ b/net/ipv4/sysctl_net_ipv4.c
@@ -49,6 +49,7 @@ static int ip_ping_group_range_min[] = { 0, 0 };
 static int ip_ping_group_range_max[] = { GID_T_MAX, GID_T_MAX };
 static int comp_sack_nr_max = 255;
 static u32 u32_max_div_HZ = UINT_MAX / HZ;
+static int one_day_secs = 24 * 3600;
 
 /* obsolete */
 static int sysctl_tcp_low_latency __read_mostly;
@@ -1151,7 +1152,9 @@ static struct ctl_table ipv4_net_table[] = {
 		.data		= &init_net.ipv4.sysctl_tcp_min_rtt_wlen,
 		.maxlen		= sizeof(int),
 		.mode		= 0644,
-		.proc_handler	= proc_dointvec
+		.proc_handler	= proc_dointvec_minmax,
+		.extra1		= &zero,
+		.extra2		= &one_day_secs
 	},
 	{
 		.procname	= "tcp_autocorking",
diff --git a/net/ipv4/tcp_dctcp.c b/net/ipv4/tcp_dctcp.c
index cd4814f7e962..477cb4aa456c 100644
--- a/net/ipv4/tcp_dctcp.c
+++ b/net/ipv4/tcp_dctcp.c
@@ -49,9 +49,8 @@
 #define DCTCP_MAX_ALPHA	1024U
 
 struct dctcp {
-	u32 acked_bytes_ecn;
-	u32 acked_bytes_total;
-	u32 prior_snd_una;
+	u32 old_delivered;
+	u32 old_delivered_ce;
 	u32 prior_rcv_nxt;
 	u32 dctcp_alpha;
 	u32 next_seq;
@@ -67,19 +66,14 @@ static unsigned int dctcp_alpha_on_init __read_mostly = DCTCP_MAX_ALPHA;
 module_param(dctcp_alpha_on_init, uint, 0644);
 MODULE_PARM_DESC(dctcp_alpha_on_init, "parameter for initial alpha value");
 
-static unsigned int dctcp_clamp_alpha_on_loss __read_mostly;
-module_param(dctcp_clamp_alpha_on_loss, uint, 0644);
-MODULE_PARM_DESC(dctcp_clamp_alpha_on_loss,
-		 "parameter for clamping alpha on loss");
-
 static struct tcp_congestion_ops dctcp_reno;
 
 static void dctcp_reset(const struct tcp_sock *tp, struct dctcp *ca)
 {
 	ca->next_seq = tp->snd_nxt;
 
-	ca->acked_bytes_ecn = 0;
-	ca->acked_bytes_total = 0;
+	ca->old_delivered = tp->delivered;
+	ca->old_delivered_ce = tp->delivered_ce;
 }
 
 static void dctcp_init(struct sock *sk)
@@ -91,7 +85,6 @@ static void dctcp_init(struct sock *sk)
 	     sk->sk_state == TCP_CLOSE)) {
 		struct dctcp *ca = inet_csk_ca(sk);
 
-		ca->prior_snd_una = tp->snd_una;
 		ca->prior_rcv_nxt = tp->rcv_nxt;
 
 		ca->dctcp_alpha = min(dctcp_alpha_on_init, DCTCP_MAX_ALPHA);
@@ -123,37 +116,25 @@ static void dctcp_update_alpha(struct sock *sk, u32 flags)
 {
 	const struct tcp_sock *tp = tcp_sk(sk);
 	struct dctcp *ca = inet_csk_ca(sk);
-	u32 acked_bytes = tp->snd_una - ca->prior_snd_una;
-
-	/* If ack did not advance snd_una, count dupack as MSS size.
-	 * If ack did update window, do not count it at all.
-	 */
-	if (acked_bytes == 0 && !(flags & CA_ACK_WIN_UPDATE))
-		acked_bytes = inet_csk(sk)->icsk_ack.rcv_mss;
-	if (acked_bytes) {
-		ca->acked_bytes_total += acked_bytes;
-		ca->prior_snd_una = tp->snd_una;
-
-		if (flags & CA_ACK_ECE)
-			ca->acked_bytes_ecn += acked_bytes;
-	}
 
 	/* Expired RTT */
 	if (!before(tp->snd_una, ca->next_seq)) {
-		u64 bytes_ecn = ca->acked_bytes_ecn;
+		u32 delivered_ce = tp->delivered_ce - ca->old_delivered_ce;
 		u32 alpha = ca->dctcp_alpha;
 
 		/* alpha = (1 - g) * alpha + g * F */
 
 		alpha -= min_not_zero(alpha, alpha >> dctcp_shift_g);
-		if (bytes_ecn) {
+		if (delivered_ce) {
+			u32 delivered = tp->delivered - ca->old_delivered;
+
 			/* If dctcp_shift_g == 1, a 32bit value would overflow
-			 * after 8 Mbytes.
+			 * after 8 M packets.
 			 */
-			bytes_ecn <<= (10 - dctcp_shift_g);
-			do_div(bytes_ecn, max(1U, ca->acked_bytes_total));
+			delivered_ce <<= (10 - dctcp_shift_g);
+			delivered_ce /= max(1U, delivered);
 
-			alpha = min(alpha + (u32)bytes_ecn, DCTCP_MAX_ALPHA);
+			alpha = min(alpha + delivered_ce, DCTCP_MAX_ALPHA);
 		}
 		/* dctcp_alpha can be read from dctcp_get_info() without
 		 * synchro, so we ask compiler to not use dctcp_alpha
@@ -164,21 +145,23 @@ static void dctcp_update_alpha(struct sock *sk, u32 flags)
 	}
 }
 
-static void dctcp_state(struct sock *sk, u8 new_state)
+static void dctcp_react_to_loss(struct sock *sk)
 {
-	if (dctcp_clamp_alpha_on_loss && new_state == TCP_CA_Loss) {
-		struct dctcp *ca = inet_csk_ca(sk);
+	struct dctcp *ca = inet_csk_ca(sk);
+	struct tcp_sock *tp = tcp_sk(sk);
 
-		/* If this extension is enabled, we clamp dctcp_alpha to
-		 * max on packet loss; the motivation is that dctcp_alpha
-		 * is an indicator to the extend of congestion and packet
-		 * loss is an indicator of extreme congestion; setting
-		 * this in practice turned out to be beneficial, and
-		 * effectively assumes total congestion which reduces the
-		 * window by half.
-		 */
-		ca->dctcp_alpha = DCTCP_MAX_ALPHA;
-	}
+	ca->loss_cwnd = tp->snd_cwnd;
+	tp->snd_ssthresh = max(tp->snd_cwnd >> 1U, 2U);
+}
+
+static void dctcp_state(struct sock *sk, u8 new_state)
+{
+	if (new_state == TCP_CA_Recovery &&
+	    new_state != inet_csk(sk)->icsk_ca_state)
+		dctcp_react_to_loss(sk);
+	/* We handle RTO in dctcp_cwnd_event to ensure that we perform only
+	 * one loss-adjustment per RTT.
+	 */
 }
 
 static void dctcp_cwnd_event(struct sock *sk, enum tcp_ca_event ev)
@@ -190,6 +173,9 @@ static void dctcp_cwnd_event(struct sock *sk, enum tcp_ca_event ev)
 	case CA_EVENT_ECN_NO_CE:
 		dctcp_ece_ack_update(sk, ev, &ca->prior_rcv_nxt, &ca->ce_state);
 		break;
+	case CA_EVENT_LOSS:
+		dctcp_react_to_loss(sk);
+		break;
 	default:
 		/* Don't care for the rest. */
 		break;
@@ -200,6 +186,7 @@ static size_t dctcp_get_info(struct sock *sk, u32 ext, int *attr,
 			     union tcp_cc_info *info)
 {
 	const struct dctcp *ca = inet_csk_ca(sk);
+	const struct tcp_sock *tp = tcp_sk(sk);
 
 	/* Fill it also in case of VEGASINFO due to req struct limits.
 	 * We can still correctly retrieve it later.
@@ -211,8 +198,10 @@ static size_t dctcp_get_info(struct sock *sk, u32 ext, int *attr,
 			info->dctcp.dctcp_enabled = 1;
 			info->dctcp.dctcp_ce_state = (u16) ca->ce_state;
 			info->dctcp.dctcp_alpha = ca->dctcp_alpha;
-			info->dctcp.dctcp_ab_ecn = ca->acked_bytes_ecn;
-			info->dctcp.dctcp_ab_tot = ca->acked_bytes_total;
+			info->dctcp.dctcp_ab_ecn = tp->mss_cache *
+						   (tp->delivered_ce - ca->old_delivered_ce);
+			info->dctcp.dctcp_ab_tot = tp->mss_cache *
+						   (tp->delivered - ca->old_delivered);
 		}
 
 		*attr = INET_DIAG_DCTCPINFO;
diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index 5def3c48870e..731d3045b50a 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -402,11 +402,12 @@ static int __tcp_grow_window(const struct sock *sk, const struct sk_buff *skb)
 static void tcp_grow_window(struct sock *sk, const struct sk_buff *skb)
 {
 	struct tcp_sock *tp = tcp_sk(sk);
+	int room;
+
+	room = min_t(int, tp->window_clamp, tcp_space(sk)) - tp->rcv_ssthresh;
 
 	/* Check #1 */
-	if (tp->rcv_ssthresh < tp->window_clamp &&
-	    (int)tp->rcv_ssthresh < tcp_space(sk) &&
-	    !tcp_under_memory_pressure(sk)) {
+	if (room > 0 && !tcp_under_memory_pressure(sk)) {
 		int incr;
 
 		/* Check #2. Increase window, if skb with such overhead
@@ -419,8 +420,7 @@ static void tcp_grow_window(struct sock *sk, const struct sk_buff *skb)
 
 		if (incr) {
 			incr = max_t(int, incr, 2 * skb->len);
-			tp->rcv_ssthresh = min(tp->rcv_ssthresh + incr,
-					       tp->window_clamp);
+			tp->rcv_ssthresh += min(room, incr);
 			inet_csk(sk)->icsk_ack.quick |= 1;
 		}
 	}
diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
index 277d71239d75..a2896944aa37 100644
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -1673,7 +1673,9 @@ bool tcp_add_backlog(struct sock *sk, struct sk_buff *skb)
 	if (TCP_SKB_CB(tail)->end_seq != TCP_SKB_CB(skb)->seq ||
 	    TCP_SKB_CB(tail)->ip_dsfield != TCP_SKB_CB(skb)->ip_dsfield ||
 	    ((TCP_SKB_CB(tail)->tcp_flags |
-	      TCP_SKB_CB(skb)->tcp_flags) & TCPHDR_URG) ||
+	      TCP_SKB_CB(skb)->tcp_flags) & (TCPHDR_SYN | TCPHDR_RST | TCPHDR_URG)) ||
+	    !((TCP_SKB_CB(tail)->tcp_flags &
+	      TCP_SKB_CB(skb)->tcp_flags) & TCPHDR_ACK) ||
 	    ((TCP_SKB_CB(tail)->tcp_flags ^
 	      TCP_SKB_CB(skb)->tcp_flags) & (TCPHDR_ECE | TCPHDR_CWR)) ||
 #ifdef CONFIG_TLS_DEVICE
@@ -1692,6 +1694,15 @@ bool tcp_add_backlog(struct sock *sk, struct sk_buff *skb)
 		if (after(TCP_SKB_CB(skb)->ack_seq, TCP_SKB_CB(tail)->ack_seq))
 			TCP_SKB_CB(tail)->ack_seq = TCP_SKB_CB(skb)->ack_seq;
 
+		/* We have to update both TCP_SKB_CB(tail)->tcp_flags and
+		 * thtail->fin, so that the fast path in tcp_rcv_established()
+		 * is not entered if we append a packet with a FIN.
+		 * SYN, RST, URG are not present.
+		 * ACK is set on both packets.
+		 * PSH : we do not really care in TCP stack,
+		 *       at least for 'GRO' packets.
+		 */
+		thtail->fin |= th->fin;
 		TCP_SKB_CB(tail)->tcp_flags |= TCP_SKB_CB(skb)->tcp_flags;
 
 		if (TCP_SKB_CB(skb)->has_rxtstamp) {
@@ -2578,7 +2589,8 @@ static void __net_exit tcp_sk_exit(struct net *net)
 {
 	int cpu;
 
-	module_put(net->ipv4.tcp_congestion_control->owner);
+	if (net->ipv4.tcp_congestion_control)
+		module_put(net->ipv4.tcp_congestion_control->owner);
 
 	for_each_possible_cpu(cpu)
 		inet_ctl_sock_destroy(*per_cpu_ptr(net->ipv4.tcp_sk, cpu));
diff --git a/net/ipv4/udp_offload.c b/net/ipv4/udp_offload.c
index 64f9715173ac..065334b41d57 100644
--- a/net/ipv4/udp_offload.c
+++ b/net/ipv4/udp_offload.c
@@ -352,6 +352,7 @@ static struct sk_buff *udp_gro_receive_segment(struct list_head *head,
 	struct sk_buff *pp = NULL;
 	struct udphdr *uh2;
 	struct sk_buff *p;
+	unsigned int ulen;
 
 	/* requires non zero csum, for symmetry with GSO */
 	if (!uh->check) {
@@ -359,6 +360,12 @@ static struct sk_buff *udp_gro_receive_segment(struct list_head *head,
 		return NULL;
 	}
 
+	/* Do not deal with padded or malicious packets, sorry ! */
+	ulen = ntohs(uh->len);
+	if (ulen <= sizeof(*uh) || ulen != skb_gro_len(skb)) {
+		NAPI_GRO_CB(skb)->flush = 1;
+		return NULL;
+	}
 	/* pull encapsulating udp header */
 	skb_gro_pull(skb, sizeof(struct udphdr));
 	skb_gro_postpull_rcsum(skb, uh, sizeof(struct udphdr));
@@ -377,13 +384,14 @@ static struct sk_buff *udp_gro_receive_segment(struct list_head *head,
 
 		/* Terminate the flow on len mismatch or if it grow "too much".
 		 * Under small packet flood GRO count could elsewhere grow a lot
-		 * leading to execessive truesize values
+		 * leading to excessive truesize values.
+		 * On len mismatch merge the first packet shorter than gso_size,
+		 * otherwise complete the GRO packet.
 		 */
-		if (!skb_gro_receive(p, skb) &&
+		if (ulen > ntohs(uh2->len) || skb_gro_receive(p, skb) ||
+		    ulen != ntohs(uh2->len) ||
 		    NAPI_GRO_CB(p)->count >= UDP_GRO_CNT_MAX)
 			pp = p;
-		else if (uh->len != uh2->len)
-			pp = p;
 
 		return pp;
 	}
diff --git a/net/ipv4/xfrm4_policy.c b/net/ipv4/xfrm4_policy.c
index d73a6d6652f6..2b144b92ae46 100644
--- a/net/ipv4/xfrm4_policy.c
+++ b/net/ipv4/xfrm4_policy.c
@@ -111,7 +111,8 @@ static void
 _decode_session4(struct sk_buff *skb, struct flowi *fl, int reverse)
 {
 	const struct iphdr *iph = ip_hdr(skb);
-	u8 *xprth = skb_network_header(skb) + iph->ihl * 4;
+	int ihl = iph->ihl;
+	u8 *xprth = skb_network_header(skb) + ihl * 4;
 	struct flowi4 *fl4 = &fl->u.ip4;
 	int oif = 0;
 
@@ -122,6 +123,11 @@ _decode_session4(struct sk_buff *skb, struct flowi *fl, int reverse)
 	fl4->flowi4_mark = skb->mark;
 	fl4->flowi4_oif = reverse ? skb->skb_iif : oif;
 
+	fl4->flowi4_proto = iph->protocol;
+	fl4->daddr = reverse ? iph->saddr : iph->daddr;
+	fl4->saddr = reverse ? iph->daddr : iph->saddr;
+	fl4->flowi4_tos = iph->tos;
+
 	if (!ip_is_fragment(iph)) {
 		switch (iph->protocol) {
 		case IPPROTO_UDP:
@@ -133,7 +139,7 @@ _decode_session4(struct sk_buff *skb, struct flowi *fl, int reverse)
 			    pskb_may_pull(skb, xprth + 4 - skb->data)) {
 				__be16 *ports;
 
-				xprth = skb_network_header(skb) + iph->ihl * 4;
+				xprth = skb_network_header(skb) + ihl * 4;
 				ports = (__be16 *)xprth;
 
 				fl4->fl4_sport = ports[!!reverse];
@@ -146,7 +152,7 @@ _decode_session4(struct sk_buff *skb, struct flowi *fl, int reverse)
 			    pskb_may_pull(skb, xprth + 2 - skb->data)) {
 				u8 *icmp;
 
-				xprth = skb_network_header(skb) + iph->ihl * 4;
+				xprth = skb_network_header(skb) + ihl * 4;
 				icmp = xprth;
 
 				fl4->fl4_icmp_type = icmp[0];
@@ -159,7 +165,7 @@ _decode_session4(struct sk_buff *skb, struct flowi *fl, int reverse)
 			    pskb_may_pull(skb, xprth + 4 - skb->data)) {
 				__be32 *ehdr;
 
-				xprth = skb_network_header(skb) + iph->ihl * 4;
+				xprth = skb_network_header(skb) + ihl * 4;
 				ehdr = (__be32 *)xprth;
 
 				fl4->fl4_ipsec_spi = ehdr[0];
@@ -171,7 +177,7 @@ _decode_session4(struct sk_buff *skb, struct flowi *fl, int reverse)
 			    pskb_may_pull(skb, xprth + 8 - skb->data)) {
 				__be32 *ah_hdr;
 
-				xprth = skb_network_header(skb) + iph->ihl * 4;
+				xprth = skb_network_header(skb) + ihl * 4;
 				ah_hdr = (__be32 *)xprth;
 
 				fl4->fl4_ipsec_spi = ah_hdr[1];
@@ -183,7 +189,7 @@ _decode_session4(struct sk_buff *skb, struct flowi *fl, int reverse)
 			    pskb_may_pull(skb, xprth + 4 - skb->data)) {
 				__be16 *ipcomp_hdr;
 
-				xprth = skb_network_header(skb) + iph->ihl * 4;
+				xprth = skb_network_header(skb) + ihl * 4;
 				ipcomp_hdr = (__be16 *)xprth;
 
 				fl4->fl4_ipsec_spi = htonl(ntohs(ipcomp_hdr[1]));
@@ -196,7 +202,7 @@ _decode_session4(struct sk_buff *skb, struct flowi *fl, int reverse)
 				__be16 *greflags;
 				__be32 *gre_hdr;
 
-				xprth = skb_network_header(skb) + iph->ihl * 4;
+				xprth = skb_network_header(skb) + ihl * 4;
 				greflags = (__be16 *)xprth;
 				gre_hdr = (__be32 *)xprth;
 
@@ -213,10 +219,6 @@ _decode_session4(struct sk_buff *skb, struct flowi *fl, int reverse)
 			break;
 		}
 	}
-	fl4->flowi4_proto = iph->protocol;
-	fl4->daddr = reverse ? iph->saddr : iph->daddr;
-	fl4->saddr = reverse ? iph->daddr : iph->saddr;
-	fl4->flowi4_tos = iph->tos;
 }
 
 static void xfrm4_update_pmtu(struct dst_entry *dst, struct sock *sk,
diff --git a/net/ipv6/addrlabel.c b/net/ipv6/addrlabel.c
index d43d076c98f5..1766325423b5 100644
--- a/net/ipv6/addrlabel.c
+++ b/net/ipv6/addrlabel.c
@@ -476,7 +476,7 @@ static int ip6addrlbl_valid_dump_req(const struct nlmsghdr *nlh,
 	}
 
 	if (nlmsg_attrlen(nlh, sizeof(*ifal))) {
-		NL_SET_ERR_MSG_MOD(extack, "Invalid data after header for address label dump requewst");
+		NL_SET_ERR_MSG_MOD(extack, "Invalid data after header for address label dump request");
 		return -EINVAL;
 	}
 
diff --git a/net/ipv6/esp6_offload.c b/net/ipv6/esp6_offload.c
index d46b4eb645c2..cb99f6fb79b7 100644
--- a/net/ipv6/esp6_offload.c
+++ b/net/ipv6/esp6_offload.c
@@ -74,13 +74,13 @@ static struct sk_buff *esp6_gro_receive(struct list_head *head,
 			goto out;
 
 		if (sp->len == XFRM_MAX_DEPTH)
-			goto out;
+			goto out_reset;
 
 		x = xfrm_state_lookup(dev_net(skb->dev), skb->mark,
 				      (xfrm_address_t *)&ipv6_hdr(skb)->daddr,
 				      spi, IPPROTO_ESP, AF_INET6);
 		if (!x)
-			goto out;
+			goto out_reset;
 
 		sp->xvec[sp->len++] = x;
 		sp->olen++;
@@ -88,7 +88,7 @@ static struct sk_buff *esp6_gro_receive(struct list_head *head,
 		xo = xfrm_offload(skb);
 		if (!xo) {
 			xfrm_state_put(x);
-			goto out;
+			goto out_reset;
 		}
 	}
 
@@ -109,6 +109,8 @@ static struct sk_buff *esp6_gro_receive(struct list_head *head,
 	xfrm_input(skb, IPPROTO_ESP, spi, -2);
 
 	return ERR_PTR(-EINPROGRESS);
+out_reset:
+	secpath_reset(skb);
 out:
 	skb_push(skb, offset);
 	NAPI_GRO_CB(skb)->same_flow = 0;
diff --git a/net/ipv6/ila/ila_xlat.c b/net/ipv6/ila/ila_xlat.c
index 79d2e43c05c5..5fc1f4e0c0cf 100644
--- a/net/ipv6/ila/ila_xlat.c
+++ b/net/ipv6/ila/ila_xlat.c
@@ -417,6 +417,7 @@ int ila_xlat_nl_cmd_flush(struct sk_buff *skb, struct genl_info *info)
 
 done:
 	rhashtable_walk_stop(&iter);
+	rhashtable_walk_exit(&iter);
 	return ret;
 }
 
diff --git a/net/ipv6/ip6_fib.c b/net/ipv6/ip6_fib.c
index 6613d8dbb0e5..91247a6fc67f 100644
--- a/net/ipv6/ip6_fib.c
+++ b/net/ipv6/ip6_fib.c
@@ -921,9 +921,7 @@ static void fib6_drop_pcpu_from(struct fib6_info *f6i,
 		if (pcpu_rt) {
 			struct fib6_info *from;
 
-			from = rcu_dereference_protected(pcpu_rt->from,
-					     lockdep_is_held(&table->tb6_lock));
-			rcu_assign_pointer(pcpu_rt->from, NULL);
+			from = xchg((__force struct fib6_info **)&pcpu_rt->from, NULL);
 			fib6_info_release(from);
 		}
 	}
diff --git a/net/ipv6/ip6_flowlabel.c b/net/ipv6/ip6_flowlabel.c
index cb54a8a3c273..be5f3d7ceb96 100644
--- a/net/ipv6/ip6_flowlabel.c
+++ b/net/ipv6/ip6_flowlabel.c
@@ -94,15 +94,21 @@ static struct ip6_flowlabel *fl_lookup(struct net *net, __be32 label)
 	return fl;
 }
 
+static void fl_free_rcu(struct rcu_head *head)
+{
+	struct ip6_flowlabel *fl = container_of(head, struct ip6_flowlabel, rcu);
+
+	if (fl->share == IPV6_FL_S_PROCESS)
+		put_pid(fl->owner.pid);
+	kfree(fl->opt);
+	kfree(fl);
+}
+
 
 static void fl_free(struct ip6_flowlabel *fl)
 {
-	if (fl) {
-		if (fl->share == IPV6_FL_S_PROCESS)
-			put_pid(fl->owner.pid);
-		kfree(fl->opt);
-		kfree_rcu(fl, rcu);
-	}
+	if (fl)
+		call_rcu(&fl->rcu, fl_free_rcu);
 }
 
 static void fl_release(struct ip6_flowlabel *fl)
@@ -633,9 +639,9 @@ recheck:
 				if (fl1->share == IPV6_FL_S_EXCL ||
 				    fl1->share != fl->share ||
 				    ((fl1->share == IPV6_FL_S_PROCESS) &&
-				     (fl1->owner.pid == fl->owner.pid)) ||
+				     (fl1->owner.pid != fl->owner.pid)) ||
 				    ((fl1->share == IPV6_FL_S_USER) &&
-				     uid_eq(fl1->owner.uid, fl->owner.uid)))
+				     !uid_eq(fl1->owner.uid, fl->owner.uid)))
 					goto release;
 
 				err = -ENOMEM;
diff --git a/net/ipv6/ip6_gre.c b/net/ipv6/ip6_gre.c
index b32c95f02128..655e46b227f9 100644
--- a/net/ipv6/ip6_gre.c
+++ b/net/ipv6/ip6_gre.c
@@ -525,10 +525,10 @@ static int ip6gre_rcv(struct sk_buff *skb, const struct tnl_ptk_info *tpi)
 }
 
 static int ip6erspan_rcv(struct sk_buff *skb,
-			 struct tnl_ptk_info *tpi)
+			 struct tnl_ptk_info *tpi,
+			 int gre_hdr_len)
 {
 	struct erspan_base_hdr *ershdr;
-	struct erspan_metadata *pkt_md;
 	const struct ipv6hdr *ipv6h;
 	struct erspan_md2 *md2;
 	struct ip6_tnl *tunnel;
@@ -547,18 +547,16 @@ static int ip6erspan_rcv(struct sk_buff *skb,
 		if (unlikely(!pskb_may_pull(skb, len)))
 			return PACKET_REJECT;
 
-		ershdr = (struct erspan_base_hdr *)skb->data;
-		pkt_md = (struct erspan_metadata *)(ershdr + 1);
-
 		if (__iptunnel_pull_header(skb, len,
 					   htons(ETH_P_TEB),
 					   false, false) < 0)
 			return PACKET_REJECT;
 
 		if (tunnel->parms.collect_md) {
+			struct erspan_metadata *pkt_md, *md;
 			struct metadata_dst *tun_dst;
 			struct ip_tunnel_info *info;
-			struct erspan_metadata *md;
+			unsigned char *gh;
 			__be64 tun_id;
 			__be16 flags;
 
@@ -571,6 +569,14 @@ static int ip6erspan_rcv(struct sk_buff *skb,
 			if (!tun_dst)
 				return PACKET_REJECT;
 
+			/* skb can be uncloned in __iptunnel_pull_header, so
+			 * old pkt_md is no longer valid and we need to reset
+			 * it
+			 */
+			gh = skb_network_header(skb) +
+			     skb_network_header_len(skb);
+			pkt_md = (struct erspan_metadata *)(gh + gre_hdr_len +
+							    sizeof(*ershdr));
 			info = &tun_dst->u.tun_info;
 			md = ip_tunnel_info_opts(info);
 			md->version = ver;
@@ -607,7 +613,7 @@ static int gre_rcv(struct sk_buff *skb)
 
 	if (unlikely(tpi.proto == htons(ETH_P_ERSPAN) ||
 		     tpi.proto == htons(ETH_P_ERSPAN2))) {
-		if (ip6erspan_rcv(skb, &tpi) == PACKET_RCVD)
+		if (ip6erspan_rcv(skb, &tpi, hdr_len) == PACKET_RCVD)
 			return 0;
 		goto out;
 	}
diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c
index edbd12067170..e51f3c648b09 100644
--- a/net/ipv6/ip6_output.c
+++ b/net/ipv6/ip6_output.c
@@ -601,7 +601,7 @@ int ip6_fragment(struct net *net, struct sock *sk, struct sk_buff *skb,
 				inet6_sk(skb->sk) : NULL;
 	struct ipv6hdr *tmp_hdr;
 	struct frag_hdr *fh;
-	unsigned int mtu, hlen, left, len;
+	unsigned int mtu, hlen, left, len, nexthdr_offset;
 	int hroom, troom;
 	__be32 frag_id;
 	int ptr, offset = 0, err = 0;
@@ -612,6 +612,7 @@ int ip6_fragment(struct net *net, struct sock *sk, struct sk_buff *skb,
 		goto fail;
 	hlen = err;
 	nexthdr = *prevhdr;
+	nexthdr_offset = prevhdr - skb_network_header(skb);
 
 	mtu = ip6_skb_dst_mtu(skb);
 
@@ -646,6 +647,7 @@ int ip6_fragment(struct net *net, struct sock *sk, struct sk_buff *skb,
 	    (err = skb_checksum_help(skb)))
 		goto fail;
 
+	prevhdr = skb_network_header(skb) + nexthdr_offset;
 	hroom = LL_RESERVED_SPACE(rt->dst.dev);
 	if (skb_has_frag_list(skb)) {
 		unsigned int first_len = skb_pagelen(skb);
diff --git a/net/ipv6/ip6_tunnel.c b/net/ipv6/ip6_tunnel.c
index 0c6403cf8b52..ade1390c6348 100644
--- a/net/ipv6/ip6_tunnel.c
+++ b/net/ipv6/ip6_tunnel.c
@@ -627,7 +627,7 @@ ip4ip6_err(struct sk_buff *skb, struct inet6_skb_parm *opt,
 		rt = ip_route_output_ports(dev_net(skb->dev), &fl4, NULL,
 					   eiph->daddr, eiph->saddr, 0, 0,
 					   IPPROTO_IPIP, RT_TOS(eiph->tos), 0);
-		if (IS_ERR(rt) || rt->dst.dev->type != ARPHRD_TUNNEL) {
+		if (IS_ERR(rt) || rt->dst.dev->type != ARPHRD_TUNNEL6) {
 			if (!IS_ERR(rt))
 				ip_rt_put(rt);
 			goto out;
@@ -636,7 +636,7 @@ ip4ip6_err(struct sk_buff *skb, struct inet6_skb_parm *opt,
 	} else {
 		if (ip_route_input(skb2, eiph->daddr, eiph->saddr, eiph->tos,
 				   skb2->dev) ||
-		    skb_dst(skb2)->dev->type != ARPHRD_TUNNEL)
+		    skb_dst(skb2)->dev->type != ARPHRD_TUNNEL6)
 			goto out;
 	}
 
diff --git a/net/ipv6/netfilter/ip6t_srh.c b/net/ipv6/netfilter/ip6t_srh.c
index 1059894a6f4c..4cb83fb69844 100644
--- a/net/ipv6/netfilter/ip6t_srh.c
+++ b/net/ipv6/netfilter/ip6t_srh.c
@@ -210,6 +210,8 @@ static bool srh1_mt6(const struct sk_buff *skb, struct xt_action_param *par)
 		psidoff = srhoff + sizeof(struct ipv6_sr_hdr) +
 			  ((srh->segments_left + 1) * sizeof(struct in6_addr));
 		psid = skb_header_pointer(skb, psidoff, sizeof(_psid), &_psid);
+		if (!psid)
+			return false;
 		if (NF_SRH_INVF(srhinfo, IP6T_SRH_INV_PSID,
 				ipv6_masked_addr_cmp(psid, &srhinfo->psid_msk,
 						     &srhinfo->psid_addr)))
@@ -223,6 +225,8 @@ static bool srh1_mt6(const struct sk_buff *skb, struct xt_action_param *par)
 		nsidoff = srhoff + sizeof(struct ipv6_sr_hdr) +
 			  ((srh->segments_left - 1) * sizeof(struct in6_addr));
 		nsid = skb_header_pointer(skb, nsidoff, sizeof(_nsid), &_nsid);
+		if (!nsid)
+			return false;
 		if (NF_SRH_INVF(srhinfo, IP6T_SRH_INV_NSID,
 				ipv6_masked_addr_cmp(nsid, &srhinfo->nsid_msk,
 						     &srhinfo->nsid_addr)))
@@ -233,6 +237,8 @@ static bool srh1_mt6(const struct sk_buff *skb, struct xt_action_param *par)
 	if (srhinfo->mt_flags & IP6T_SRH_LSID) {
 		lsidoff = srhoff + sizeof(struct ipv6_sr_hdr);
 		lsid = skb_header_pointer(skb, lsidoff, sizeof(_lsid), &_lsid);
+		if (!lsid)
+			return false;
 		if (NF_SRH_INVF(srhinfo, IP6T_SRH_INV_LSID,
 				ipv6_masked_addr_cmp(lsid, &srhinfo->lsid_msk,
 						     &srhinfo->lsid_addr)))
diff --git a/net/ipv6/route.c b/net/ipv6/route.c
index 4ef4bbdb49d4..0520aca3354b 100644
--- a/net/ipv6/route.c
+++ b/net/ipv6/route.c
@@ -379,11 +379,8 @@ static void ip6_dst_destroy(struct dst_entry *dst)
 		in6_dev_put(idev);
 	}
 
-	rcu_read_lock();
-	from = rcu_dereference(rt->from);
-	rcu_assign_pointer(rt->from, NULL);
+	from = xchg((__force struct fib6_info **)&rt->from, NULL);
 	fib6_info_release(from);
-	rcu_read_unlock();
 }
 
 static void ip6_dst_ifdown(struct dst_entry *dst, struct net_device *dev,
@@ -1040,14 +1037,20 @@ static struct rt6_info *ip6_create_rt_rcu(struct fib6_info *rt)
 	struct rt6_info *nrt;
 
 	if (!fib6_info_hold_safe(rt))
-		return NULL;
+		goto fallback;
 
 	nrt = ip6_dst_alloc(dev_net(dev), dev, flags);
-	if (nrt)
-		ip6_rt_copy_init(nrt, rt);
-	else
+	if (!nrt) {
 		fib6_info_release(rt);
+		goto fallback;
+	}
+
+	ip6_rt_copy_init(nrt, rt);
+	return nrt;
 
+fallback:
+	nrt = dev_net(dev)->ipv6.ip6_null_entry;
+	dst_hold(&nrt->dst);
 	return nrt;
 }
 
@@ -1096,10 +1099,6 @@ restart:
 		dst_hold(&rt->dst);
 	} else {
 		rt = ip6_create_rt_rcu(f6i);
-		if (!rt) {
-			rt = net->ipv6.ip6_null_entry;
-			dst_hold(&rt->dst);
-		}
 	}
 
 	rcu_read_unlock();
@@ -1286,9 +1285,7 @@ static void rt6_remove_exception(struct rt6_exception_bucket *bucket,
 	/* purge completely the exception to allow releasing the held resources:
 	 * some [sk] cache may keep the dst around for unlimited time
 	 */
-	from = rcu_dereference_protected(rt6_ex->rt6i->from,
-					 lockdep_is_held(&rt6_exception_lock));
-	rcu_assign_pointer(rt6_ex->rt6i->from, NULL);
+	from = xchg((__force struct fib6_info **)&rt6_ex->rt6i->from, NULL);
 	fib6_info_release(from);
 	dst_dev_put(&rt6_ex->rt6i->dst);
 
@@ -2328,6 +2325,10 @@ static void __ip6_rt_update_pmtu(struct dst_entry *dst, const struct sock *sk,
 
 		rcu_read_lock();
 		from = rcu_dereference(rt6->from);
+		if (!from) {
+			rcu_read_unlock();
+			return;
+		}
 		nrt6 = ip6_rt_cache_alloc(from, daddr, saddr);
 		if (nrt6) {
 			rt6_do_update_pmtu(nrt6, mtu);
@@ -3391,11 +3392,8 @@ static void rt6_do_redirect(struct dst_entry *dst, struct sock *sk, struct sk_bu
 
 	rcu_read_lock();
 	from = rcu_dereference(rt->from);
-	/* This fib6_info_hold() is safe here because we hold reference to rt
-	 * and rt already holds reference to fib6_info.
-	 */
-	fib6_info_hold(from);
-	rcu_read_unlock();
+	if (!from)
+		goto out;
 
 	nrt = ip6_rt_cache_alloc(from, &msg->dest, NULL);
 	if (!nrt)
@@ -3407,10 +3405,7 @@ static void rt6_do_redirect(struct dst_entry *dst, struct sock *sk, struct sk_bu
 
 	nrt->rt6i_gateway = *(struct in6_addr *)neigh->primary_key;
 
-	/* No need to remove rt from the exception table if rt is
-	 * a cached route because rt6_insert_exception() will
-	 * takes care of it
-	 */
+	/* rt6_insert_exception() will take care of duplicated exceptions */
 	if (rt6_insert_exception(nrt, from)) {
 		dst_release_immediate(&nrt->dst);
 		goto out;
@@ -3423,7 +3418,7 @@ static void rt6_do_redirect(struct dst_entry *dst, struct sock *sk, struct sk_bu
 	call_netevent_notifiers(NETEVENT_REDIRECT, &netevent);
 
 out:
-	fib6_info_release(from);
+	rcu_read_unlock();
 	neigh_release(neigh);
 }
 
@@ -3662,23 +3657,34 @@ int ipv6_route_ioctl(struct net *net, unsigned int cmd, void __user *arg)
 
 static int ip6_pkt_drop(struct sk_buff *skb, u8 code, int ipstats_mib_noroutes)
 {
-	int type;
 	struct dst_entry *dst = skb_dst(skb);
+	struct net *net = dev_net(dst->dev);
+	struct inet6_dev *idev;
+	int type;
+
+	if (netif_is_l3_master(skb->dev) &&
+	    dst->dev == net->loopback_dev)
+		idev = __in6_dev_get_safely(dev_get_by_index_rcu(net, IP6CB(skb)->iif));
+	else
+		idev = ip6_dst_idev(dst);
+
 	switch (ipstats_mib_noroutes) {
 	case IPSTATS_MIB_INNOROUTES:
 		type = ipv6_addr_type(&ipv6_hdr(skb)->daddr);
 		if (type == IPV6_ADDR_ANY) {
-			IP6_INC_STATS(dev_net(dst->dev),
-				      __in6_dev_get_safely(skb->dev),
-				      IPSTATS_MIB_INADDRERRORS);
+			IP6_INC_STATS(net, idev, IPSTATS_MIB_INADDRERRORS);
 			break;
 		}
 		/* FALLTHROUGH */
 	case IPSTATS_MIB_OUTNOROUTES:
-		IP6_INC_STATS(dev_net(dst->dev), ip6_dst_idev(dst),
-			      ipstats_mib_noroutes);
+		IP6_INC_STATS(net, idev, ipstats_mib_noroutes);
 		break;
 	}
+
+	/* Start over by dropping the dst for l3mdev case */
+	if (netif_is_l3_master(skb->dev))
+		skb_dst_drop(skb);
+
 	icmpv6_send(skb, ICMPV6_DEST_UNREACH, code, 0);
 	kfree_skb(skb);
 	return 0;
@@ -5011,16 +5017,20 @@ static int inet6_rtm_getroute(struct sk_buff *in_skb, struct nlmsghdr *nlh,
 
 	rcu_read_lock();
 	from = rcu_dereference(rt->from);
-
-	if (fibmatch)
-		err = rt6_fill_node(net, skb, from, NULL, NULL, NULL, iif,
-				    RTM_NEWROUTE, NETLINK_CB(in_skb).portid,
-				    nlh->nlmsg_seq, 0);
-	else
-		err = rt6_fill_node(net, skb, from, dst, &fl6.daddr,
-				    &fl6.saddr, iif, RTM_NEWROUTE,
-				    NETLINK_CB(in_skb).portid, nlh->nlmsg_seq,
-				    0);
+	if (from) {
+		if (fibmatch)
+			err = rt6_fill_node(net, skb, from, NULL, NULL, NULL,
+					    iif, RTM_NEWROUTE,
+					    NETLINK_CB(in_skb).portid,
+					    nlh->nlmsg_seq, 0);
+		else
+			err = rt6_fill_node(net, skb, from, dst, &fl6.daddr,
+					    &fl6.saddr, iif, RTM_NEWROUTE,
+					    NETLINK_CB(in_skb).portid,
+					    nlh->nlmsg_seq, 0);
+	} else {
+		err = -ENETUNREACH;
+	}
 	rcu_read_unlock();
 
 	if (err < 0) {
diff --git a/net/ipv6/sit.c b/net/ipv6/sit.c
index 07e21a82ce4c..b2109b74857d 100644
--- a/net/ipv6/sit.c
+++ b/net/ipv6/sit.c
@@ -669,6 +669,10 @@ static int ipip6_rcv(struct sk_buff *skb)
 		    !net_eq(tunnel->net, dev_net(tunnel->dev))))
 			goto out;
 
+		/* skb can be uncloned in iptunnel_pull_header, so
+		 * old iph is no longer valid
+		 */
+		iph = (const struct iphdr *)skb_mac_header(skb);
 		err = IP_ECN_decapsulate(iph, skb);
 		if (unlikely(err)) {
 			if (log_ecn_error)
diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c
index 57ef69a10889..44d431849d39 100644
--- a/net/ipv6/tcp_ipv6.c
+++ b/net/ipv6/tcp_ipv6.c
@@ -1110,11 +1110,11 @@ static struct sock *tcp_v6_syn_recv_sock(const struct sock *sk, struct sk_buff *
 		newnp->ipv6_fl_list = NULL;
 		newnp->pktoptions  = NULL;
 		newnp->opt	   = NULL;
-		newnp->mcast_oif   = tcp_v6_iif(skb);
-		newnp->mcast_hops  = ipv6_hdr(skb)->hop_limit;
-		newnp->rcv_flowinfo = ip6_flowinfo(ipv6_hdr(skb));
+		newnp->mcast_oif   = inet_iif(skb);
+		newnp->mcast_hops  = ip_hdr(skb)->ttl;
+		newnp->rcv_flowinfo = 0;
 		if (np->repflow)
-			newnp->flow_label = ip6_flowlabel(ipv6_hdr(skb));
+			newnp->flow_label = 0;
 
 		/*
 		 * No need to charge this sock to the relevant IPv6 refcnt debug socks count
diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c
index b444483cdb2b..622eeaf5732b 100644
--- a/net/ipv6/udp.c
+++ b/net/ipv6/udp.c
@@ -1047,6 +1047,8 @@ static void udp_v6_flush_pending_frames(struct sock *sk)
 static int udpv6_pre_connect(struct sock *sk, struct sockaddr *uaddr,
 			     int addr_len)
 {
+	if (addr_len < offsetofend(struct sockaddr, sa_family))
+		return -EINVAL;
 	/* The following checks are replicated from __ip6_datagram_connect()
 	 * and intended to prevent BPF program called below from accessing
 	 * bytes that are out of the bound specified by user in addr_len.
diff --git a/net/ipv6/xfrm6_tunnel.c b/net/ipv6/xfrm6_tunnel.c
index bc65db782bfb..d9e5f6808811 100644
--- a/net/ipv6/xfrm6_tunnel.c
+++ b/net/ipv6/xfrm6_tunnel.c
@@ -345,7 +345,7 @@ static void __net_exit xfrm6_tunnel_net_exit(struct net *net)
 	unsigned int i;
 
 	xfrm_flush_gc();
-	xfrm_state_flush(net, IPSEC_PROTO_ANY, false, true);
+	xfrm_state_flush(net, 0, false, true);
 
 	for (i = 0; i < XFRM6_TUNNEL_SPI_BYADDR_HSIZE; i++)
 		WARN_ON_ONCE(!hlist_empty(&xfrm6_tn->spi_byaddr[i]));
@@ -402,6 +402,10 @@ static void __exit xfrm6_tunnel_fini(void)
 	xfrm6_tunnel_deregister(&xfrm6_tunnel_handler, AF_INET6);
 	xfrm_unregister_type(&xfrm6_tunnel_type, AF_INET6);
 	unregister_pernet_subsys(&xfrm6_tunnel_net_ops);
+	/* Someone maybe has gotten the xfrm6_tunnel_spi.
+	 * So need to wait it.
+	 */
+	rcu_barrier();
 	kmem_cache_destroy(xfrm6_tunnel_spi_kmem);
 }
 
diff --git a/net/kcm/kcmsock.c b/net/kcm/kcmsock.c
index c5c5ab6c5a1c..44fdc641710d 100644
--- a/net/kcm/kcmsock.c
+++ b/net/kcm/kcmsock.c
@@ -2054,14 +2054,14 @@ static int __init kcm_init(void)
 	if (err)
 		goto fail;
 
-	err = sock_register(&kcm_family_ops);
-	if (err)
-		goto sock_register_fail;
-
 	err = register_pernet_device(&kcm_net_ops);
 	if (err)
 		goto net_ops_fail;
 
+	err = sock_register(&kcm_family_ops);
+	if (err)
+		goto sock_register_fail;
+
 	err = kcm_proc_init();
 	if (err)
 		goto proc_init_fail;
@@ -2069,12 +2069,12 @@ static int __init kcm_init(void)
 	return 0;
 
 proc_init_fail:
-	unregister_pernet_device(&kcm_net_ops);
-
-net_ops_fail:
 	sock_unregister(PF_KCM);
 
 sock_register_fail:
+	unregister_pernet_device(&kcm_net_ops);
+
+net_ops_fail:
 	proto_unregister(&kcm_proto);
 
 fail:
@@ -2090,8 +2090,8 @@ fail:
 static void __exit kcm_exit(void)
 {
 	kcm_proc_exit();
-	unregister_pernet_device(&kcm_net_ops);
 	sock_unregister(PF_KCM);
+	unregister_pernet_device(&kcm_net_ops);
 	proto_unregister(&kcm_proto);
 	destroy_workqueue(kcm_wq);
 
diff --git a/net/key/af_key.c b/net/key/af_key.c
index 5651c29cb5bd..4af1e1d60b9f 100644
--- a/net/key/af_key.c
+++ b/net/key/af_key.c
@@ -1951,8 +1951,10 @@ parse_ipsecrequest(struct xfrm_policy *xp, struct sadb_x_ipsecrequest *rq)
 
 	if (rq->sadb_x_ipsecrequest_mode == 0)
 		return -EINVAL;
+	if (!xfrm_id_proto_valid(rq->sadb_x_ipsecrequest_proto))
+		return -EINVAL;
 
-	t->id.proto = rq->sadb_x_ipsecrequest_proto; /* XXX check proto */
+	t->id.proto = rq->sadb_x_ipsecrequest_proto;
 	if ((mode = pfkey_mode_to_xfrm(rq->sadb_x_ipsecrequest_mode)) < 0)
 		return -EINVAL;
 	t->mode = mode;
diff --git a/net/l2tp/l2tp_core.c b/net/l2tp/l2tp_core.c
index fed6becc5daf..52b5a2797c0c 100644
--- a/net/l2tp/l2tp_core.c
+++ b/net/l2tp/l2tp_core.c
@@ -169,8 +169,8 @@ struct l2tp_tunnel *l2tp_tunnel_get(const struct net *net, u32 tunnel_id)
 
 	rcu_read_lock_bh();
 	list_for_each_entry_rcu(tunnel, &pn->l2tp_tunnel_list, list) {
-		if (tunnel->tunnel_id == tunnel_id) {
-			l2tp_tunnel_inc_refcount(tunnel);
+		if (tunnel->tunnel_id == tunnel_id &&
+		    refcount_inc_not_zero(&tunnel->ref_count)) {
 			rcu_read_unlock_bh();
 
 			return tunnel;
@@ -190,8 +190,8 @@ struct l2tp_tunnel *l2tp_tunnel_get_nth(const struct net *net, int nth)
 
 	rcu_read_lock_bh();
 	list_for_each_entry_rcu(tunnel, &pn->l2tp_tunnel_list, list) {
-		if (++count > nth) {
-			l2tp_tunnel_inc_refcount(tunnel);
+		if (++count > nth &&
+		    refcount_inc_not_zero(&tunnel->ref_count)) {
 			rcu_read_unlock_bh();
 			return tunnel;
 		}
@@ -909,7 +909,7 @@ int l2tp_udp_encap_recv(struct sock *sk, struct sk_buff *skb)
 {
 	struct l2tp_tunnel *tunnel;
 
-	tunnel = l2tp_tunnel(sk);
+	tunnel = rcu_dereference_sk_user_data(sk);
 	if (tunnel == NULL)
 		goto pass_up;
 
diff --git a/net/llc/af_llc.c b/net/llc/af_llc.c
index b99e73a7e7e0..2017b7d780f5 100644
--- a/net/llc/af_llc.c
+++ b/net/llc/af_llc.c
@@ -320,14 +320,13 @@ static int llc_ui_bind(struct socket *sock, struct sockaddr *uaddr, int addrlen)
 	struct llc_sap *sap;
 	int rc = -EINVAL;
 
-	dprintk("%s: binding %02X\n", __func__, addr->sllc_sap);
-
 	lock_sock(sk);
 	if (unlikely(!sock_flag(sk, SOCK_ZAPPED) || addrlen != sizeof(*addr)))
 		goto out;
 	rc = -EAFNOSUPPORT;
 	if (unlikely(addr->sllc_family != AF_LLC))
 		goto out;
+	dprintk("%s: binding %02X\n", __func__, addr->sllc_sap);
 	rc = -ENODEV;
 	rcu_read_lock();
 	if (sk->sk_bound_dev_if) {
diff --git a/net/mac80211/debugfs_netdev.c b/net/mac80211/debugfs_netdev.c
index cff0fb3578c9..deb3faf08337 100644
--- a/net/mac80211/debugfs_netdev.c
+++ b/net/mac80211/debugfs_netdev.c
@@ -841,7 +841,7 @@ void ieee80211_debugfs_rename_netdev(struct ieee80211_sub_if_data *sdata)
 
 	dir = sdata->vif.debugfs_dir;
 
-	if (!dir)
+	if (IS_ERR_OR_NULL(dir))
 		return;
 
 	sprintf(buf, "netdev:%s", sdata->name);
diff --git a/net/mac80211/driver-ops.h b/net/mac80211/driver-ops.h
index 28d022a3eee3..ae4f0be3b393 100644
--- a/net/mac80211/driver-ops.h
+++ b/net/mac80211/driver-ops.h
@@ -1195,6 +1195,9 @@ static inline void drv_wake_tx_queue(struct ieee80211_local *local,
 {
 	struct ieee80211_sub_if_data *sdata = vif_to_sdata(txq->txq.vif);
 
+	if (local->in_reconfig)
+		return;
+
 	if (!check_sdata_in_driver(sdata))
 		return;
 
diff --git a/net/mac80211/ht.c b/net/mac80211/ht.c
index e03c46ac8e4d..c62101857b9b 100644
--- a/net/mac80211/ht.c
+++ b/net/mac80211/ht.c
@@ -112,8 +112,9 @@ void ieee80211_apply_htcap_overrides(struct ieee80211_sub_if_data *sdata,
 			     IEEE80211_HT_CAP_TX_STBC);
 
 	/* Allow user to configure RX STBC bits */
-	if (ht_capa_mask->cap_info & IEEE80211_HT_CAP_RX_STBC)
-		ht_cap->cap |= ht_capa->cap_info & IEEE80211_HT_CAP_RX_STBC;
+	if (ht_capa_mask->cap_info & cpu_to_le16(IEEE80211_HT_CAP_RX_STBC))
+		ht_cap->cap |= le16_to_cpu(ht_capa->cap_info) &
+					IEEE80211_HT_CAP_RX_STBC;
 
 	/* Allow user to decrease AMPDU factor */
 	if (ht_capa_mask->ampdu_params_info &
diff --git a/net/mac80211/iface.c b/net/mac80211/iface.c
index 4a6ff1482a9f..02d2e6f11e93 100644
--- a/net/mac80211/iface.c
+++ b/net/mac80211/iface.c
@@ -1908,6 +1908,9 @@ void ieee80211_if_remove(struct ieee80211_sub_if_data *sdata)
 	list_del_rcu(&sdata->list);
 	mutex_unlock(&sdata->local->iflist_mtx);
 
+	if (sdata->vif.txq)
+		ieee80211_txq_purge(sdata->local, to_txq_info(sdata->vif.txq));
+
 	synchronize_rcu();
 
 	if (sdata->dev) {
diff --git a/net/mac80211/key.c b/net/mac80211/key.c
index 4700718e010f..37e372896230 100644
--- a/net/mac80211/key.c
+++ b/net/mac80211/key.c
@@ -167,8 +167,10 @@ static int ieee80211_key_enable_hw_accel(struct ieee80211_key *key)
 		 * The driver doesn't know anything about VLAN interfaces.
 		 * Hence, don't send GTKs for VLAN interfaces to the driver.
 		 */
-		if (!(key->conf.flags & IEEE80211_KEY_FLAG_PAIRWISE))
+		if (!(key->conf.flags & IEEE80211_KEY_FLAG_PAIRWISE)) {
+			ret = 1;
 			goto out_unsupported;
+		}
 	}
 
 	ret = drv_set_key(key->local, SET_KEY, sdata,
@@ -213,11 +215,8 @@ static int ieee80211_key_enable_hw_accel(struct ieee80211_key *key)
 		/* all of these we can do in software - if driver can */
 		if (ret == 1)
 			return 0;
-		if (ieee80211_hw_check(&key->local->hw, SW_CRYPTO_CONTROL)) {
-			if (sdata->vif.type == NL80211_IFTYPE_AP_VLAN)
-				return 0;
+		if (ieee80211_hw_check(&key->local->hw, SW_CRYPTO_CONTROL))
 			return -EINVAL;
-		}
 		return 0;
 	default:
 		return -EINVAL;
diff --git a/net/mac80211/mesh_pathtbl.c b/net/mac80211/mesh_pathtbl.c
index 95eb5064fa91..b76a2aefa9ec 100644
--- a/net/mac80211/mesh_pathtbl.c
+++ b/net/mac80211/mesh_pathtbl.c
@@ -23,7 +23,7 @@ static void mesh_path_free_rcu(struct mesh_table *tbl, struct mesh_path *mpath);
 static u32 mesh_table_hash(const void *addr, u32 len, u32 seed)
 {
 	/* Use last four bytes of hw addr as hash index */
-	return jhash_1word(*(u32 *)(addr+2), seed);
+	return jhash_1word(__get_unaligned_cpu32((u8 *)addr + 2), seed);
 }
 
 static const struct rhashtable_params mesh_rht_params = {
diff --git a/net/mac80211/rx.c b/net/mac80211/rx.c
index 7f8d93401ce0..bf0b187f994e 100644
--- a/net/mac80211/rx.c
+++ b/net/mac80211/rx.c
@@ -1568,7 +1568,15 @@ static void sta_ps_start(struct sta_info *sta)
 		return;
 
 	for (tid = 0; tid < IEEE80211_NUM_TIDS; tid++) {
-		if (txq_has_queue(sta->sta.txq[tid]))
+		struct ieee80211_txq *txq = sta->sta.txq[tid];
+		struct txq_info *txqi = to_txq_info(txq);
+
+		spin_lock(&local->active_txq_lock[txq->ac]);
+		if (!list_empty(&txqi->schedule_order))
+			list_del_init(&txqi->schedule_order);
+		spin_unlock(&local->active_txq_lock[txq->ac]);
+
+		if (txq_has_queue(txq))
 			set_bit(tid, &sta->txq_buffered_tids);
 		else
 			clear_bit(tid, &sta->txq_buffered_tids);
diff --git a/net/mac80211/trace_msg.h b/net/mac80211/trace_msg.h
index 366b9e6f043e..40141df09f25 100644
--- a/net/mac80211/trace_msg.h
+++ b/net/mac80211/trace_msg.h
@@ -1,4 +1,9 @@
 /* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Portions of this file
+ * Copyright (C) 2019 Intel Corporation
+ */
+
 #ifdef CONFIG_MAC80211_MESSAGE_TRACING
 
 #if !defined(__MAC80211_MSG_DRIVER_TRACE) || defined(TRACE_HEADER_MULTI_READ)
@@ -11,7 +16,7 @@
 #undef TRACE_SYSTEM
 #define TRACE_SYSTEM mac80211_msg
 
-#define MAX_MSG_LEN	100
+#define MAX_MSG_LEN	120
 
 DECLARE_EVENT_CLASS(mac80211_msg_event,
 	TP_PROTO(struct va_format *vaf),
diff --git a/net/mac80211/tx.c b/net/mac80211/tx.c
index 8a49a74c0a37..2e816dd67be7 100644
--- a/net/mac80211/tx.c
+++ b/net/mac80211/tx.c
@@ -3221,6 +3221,7 @@ static bool ieee80211_amsdu_aggregate(struct ieee80211_sub_if_data *sdata,
 	u8 max_subframes = sta->sta.max_amsdu_subframes;
 	int max_frags = local->hw.max_tx_fragments;
 	int max_amsdu_len = sta->sta.max_amsdu_len;
+	int orig_truesize;
 	__be16 len;
 	void *data;
 	bool ret = false;
@@ -3261,6 +3262,7 @@ static bool ieee80211_amsdu_aggregate(struct ieee80211_sub_if_data *sdata,
 	if (!head || skb_is_gso(head))
 		goto out;
 
+	orig_truesize = head->truesize;
 	orig_len = head->len;
 
 	if (skb->len + head->len > max_amsdu_len)
@@ -3318,6 +3320,7 @@ static bool ieee80211_amsdu_aggregate(struct ieee80211_sub_if_data *sdata,
 	*frag_tail = skb;
 
 out_recalc:
+	fq->memory_usage += head->truesize - orig_truesize;
 	if (head->len != orig_len) {
 		flow->backlog += head->len - orig_len;
 		tin->backlog_bytes += head->len - orig_len;
@@ -3646,16 +3649,17 @@ EXPORT_SYMBOL(ieee80211_tx_dequeue);
 struct ieee80211_txq *ieee80211_next_txq(struct ieee80211_hw *hw, u8 ac)
 {
 	struct ieee80211_local *local = hw_to_local(hw);
+	struct ieee80211_txq *ret = NULL;
 	struct txq_info *txqi = NULL;
 
-	lockdep_assert_held(&local->active_txq_lock[ac]);
+	spin_lock_bh(&local->active_txq_lock[ac]);
 
  begin:
 	txqi = list_first_entry_or_null(&local->active_txqs[ac],
 					struct txq_info,
 					schedule_order);
 	if (!txqi)
-		return NULL;
+		goto out;
 
 	if (txqi->txq.sta) {
 		struct sta_info *sta = container_of(txqi->txq.sta,
@@ -3672,24 +3676,30 @@ struct ieee80211_txq *ieee80211_next_txq(struct ieee80211_hw *hw, u8 ac)
 
 
 	if (txqi->schedule_round == local->schedule_round[ac])
-		return NULL;
+		goto out;
 
 	list_del_init(&txqi->schedule_order);
 	txqi->schedule_round = local->schedule_round[ac];
-	return &txqi->txq;
+	ret = &txqi->txq;
+
+out:
+	spin_unlock_bh(&local->active_txq_lock[ac]);
+	return ret;
 }
 EXPORT_SYMBOL(ieee80211_next_txq);
 
-void ieee80211_return_txq(struct ieee80211_hw *hw,
-			  struct ieee80211_txq *txq)
+void __ieee80211_schedule_txq(struct ieee80211_hw *hw,
+			      struct ieee80211_txq *txq,
+			      bool force)
 {
 	struct ieee80211_local *local = hw_to_local(hw);
 	struct txq_info *txqi = to_txq_info(txq);
 
-	lockdep_assert_held(&local->active_txq_lock[txq->ac]);
+	spin_lock_bh(&local->active_txq_lock[txq->ac]);
 
 	if (list_empty(&txqi->schedule_order) &&
-	    (!skb_queue_empty(&txqi->frags) || txqi->tin.backlog_packets)) {
+	    (force || !skb_queue_empty(&txqi->frags) ||
+	     txqi->tin.backlog_packets)) {
 		/* If airtime accounting is active, always enqueue STAs at the
 		 * head of the list to ensure that they only get moved to the
 		 * back by the airtime DRR scheduler once they have a negative
@@ -3706,20 +3716,10 @@ void ieee80211_return_txq(struct ieee80211_hw *hw,
 			list_add_tail(&txqi->schedule_order,
 				      &local->active_txqs[txq->ac]);
 	}
-}
-EXPORT_SYMBOL(ieee80211_return_txq);
 
-void ieee80211_schedule_txq(struct ieee80211_hw *hw,
-			    struct ieee80211_txq *txq)
-	__acquires(txq_lock) __releases(txq_lock)
-{
-	struct ieee80211_local *local = hw_to_local(hw);
-
-	spin_lock_bh(&local->active_txq_lock[txq->ac]);
-	ieee80211_return_txq(hw, txq);
 	spin_unlock_bh(&local->active_txq_lock[txq->ac]);
 }
-EXPORT_SYMBOL(ieee80211_schedule_txq);
+EXPORT_SYMBOL(__ieee80211_schedule_txq);
 
 bool ieee80211_txq_may_transmit(struct ieee80211_hw *hw,
 				struct ieee80211_txq *txq)
@@ -3729,7 +3729,7 @@ bool ieee80211_txq_may_transmit(struct ieee80211_hw *hw,
 	struct sta_info *sta;
 	u8 ac = txq->ac;
 
-	lockdep_assert_held(&local->active_txq_lock[ac]);
+	spin_lock_bh(&local->active_txq_lock[ac]);
 
 	if (!txqi->txq.sta)
 		goto out;
@@ -3759,34 +3759,27 @@ bool ieee80211_txq_may_transmit(struct ieee80211_hw *hw,
 
 	sta->airtime[ac].deficit += sta->airtime_weight;
 	list_move_tail(&txqi->schedule_order, &local->active_txqs[ac]);
+	spin_unlock_bh(&local->active_txq_lock[ac]);
 
 	return false;
 out:
 	if (!list_empty(&txqi->schedule_order))
 		list_del_init(&txqi->schedule_order);
+	spin_unlock_bh(&local->active_txq_lock[ac]);
 
 	return true;
 }
 EXPORT_SYMBOL(ieee80211_txq_may_transmit);
 
 void ieee80211_txq_schedule_start(struct ieee80211_hw *hw, u8 ac)
-	__acquires(txq_lock)
 {
 	struct ieee80211_local *local = hw_to_local(hw);
 
 	spin_lock_bh(&local->active_txq_lock[ac]);
 	local->schedule_round[ac]++;
-}
-EXPORT_SYMBOL(ieee80211_txq_schedule_start);
-
-void ieee80211_txq_schedule_end(struct ieee80211_hw *hw, u8 ac)
-	__releases(txq_lock)
-{
-	struct ieee80211_local *local = hw_to_local(hw);
-
 	spin_unlock_bh(&local->active_txq_lock[ac]);
 }
-EXPORT_SYMBOL(ieee80211_txq_schedule_end);
+EXPORT_SYMBOL(ieee80211_txq_schedule_start);
 
 void __ieee80211_subif_start_xmit(struct sk_buff *skb,
 				  struct net_device *dev,
diff --git a/net/mpls/mpls_iptunnel.c b/net/mpls/mpls_iptunnel.c
index dda8930f20e7..f3a8557494d6 100644
--- a/net/mpls/mpls_iptunnel.c
+++ b/net/mpls/mpls_iptunnel.c
@@ -140,9 +140,15 @@ static int mpls_xmit(struct sk_buff *skb)
 	if (rt)
 		err = neigh_xmit(NEIGH_ARP_TABLE, out_dev, &rt->rt_gateway,
 				 skb);
-	else if (rt6)
-		err = neigh_xmit(NEIGH_ND_TABLE, out_dev, &rt6->rt6i_gateway,
-				 skb);
+	else if (rt6) {
+		if (ipv6_addr_v4mapped(&rt6->rt6i_gateway)) {
+			/* 6PE (RFC 4798) */
+			err = neigh_xmit(NEIGH_ARP_TABLE, out_dev, &rt6->rt6i_gateway.s6_addr32[3],
+					 skb);
+		} else
+			err = neigh_xmit(NEIGH_ND_TABLE, out_dev, &rt6->rt6i_gateway,
+					 skb);
+	}
 	if (err)
 		net_dbg_ratelimited("%s: packet transmission failed: %d\n",
 				    __func__, err);
diff --git a/net/ncsi/ncsi-netlink.c b/net/ncsi/ncsi-netlink.c
index 5d782445d2fc..bad17bba8ba7 100644
--- a/net/ncsi/ncsi-netlink.c
+++ b/net/ncsi/ncsi-netlink.c
@@ -251,6 +251,10 @@ static int ncsi_pkg_info_all_nl(struct sk_buff *skb,
 	}
 
 	attr = nla_nest_start(skb, NCSI_ATTR_PACKAGE_LIST);
+	if (!attr) {
+		rc = -EMSGSIZE;
+		goto err;
+	}
 	rc = ncsi_write_package_info(skb, ndp, package->id);
 	if (rc) {
 		nla_nest_cancel(skb, attr);
diff --git a/net/ncsi/ncsi-rsp.c b/net/ncsi/ncsi-rsp.c
index dc07fcc7938e..802db01e3075 100644
--- a/net/ncsi/ncsi-rsp.c
+++ b/net/ncsi/ncsi-rsp.c
@@ -11,6 +11,7 @@
 #include <linux/kernel.h>
 #include <linux/init.h>
 #include <linux/netdevice.h>
+#include <linux/etherdevice.h>
 #include <linux/skbuff.h>
 
 #include <net/ncsi.h>
@@ -667,7 +668,10 @@ static int ncsi_rsp_handler_oem_bcm_gma(struct ncsi_request *nr)
 	ndev->priv_flags |= IFF_LIVE_ADDR_CHANGE;
 	memcpy(saddr.sa_data, &rsp->data[BCM_MAC_ADDR_OFFSET], ETH_ALEN);
 	/* Increase mac address by 1 for BMC's address */
-	saddr.sa_data[ETH_ALEN - 1]++;
+	eth_addr_inc((u8 *)saddr.sa_data);
+	if (!is_valid_ether_addr((const u8 *)saddr.sa_data))
+		return -ENXIO;
+
 	ret = ops->ndo_set_mac_address(ndev, &saddr);
 	if (ret < 0)
 		netdev_warn(ndev, "NCSI: 'Writing mac address to device failed\n");
diff --git a/net/netfilter/Kconfig b/net/netfilter/Kconfig
index d43ffb09939b..6548271209a0 100644
--- a/net/netfilter/Kconfig
+++ b/net/netfilter/Kconfig
@@ -1007,6 +1007,7 @@ config NETFILTER_XT_TARGET_TEE
 	depends on NETFILTER_ADVANCED
 	depends on IPV6 || IPV6=n
 	depends on !NF_CONNTRACK || NF_CONNTRACK
+	depends on IP6_NF_IPTABLES || !IP6_NF_IPTABLES
 	select NF_DUP_IPV4
 	select NF_DUP_IPV6 if IP6_NF_IPTABLES
 	---help---
diff --git a/net/netfilter/ipvs/ip_vs_core.c b/net/netfilter/ipvs/ip_vs_core.c
index 43bbaa32b1d6..14457551bcb4 100644
--- a/net/netfilter/ipvs/ip_vs_core.c
+++ b/net/netfilter/ipvs/ip_vs_core.c
@@ -1678,7 +1678,7 @@ ip_vs_in_icmp(struct netns_ipvs *ipvs, struct sk_buff *skb, int *related,
 	if (!cp) {
 		int v;
 
-		if (!sysctl_schedule_icmp(ipvs))
+		if (ipip || !sysctl_schedule_icmp(ipvs))
 			return NF_ACCEPT;
 
 		if (!ip_vs_try_to_schedule(ipvs, AF_INET, skb, pd, &v, &cp, &ciph))
diff --git a/net/netfilter/nf_conntrack_core.c b/net/netfilter/nf_conntrack_core.c
index 82bfbeef46af..2a714527cde1 100644
--- a/net/netfilter/nf_conntrack_core.c
+++ b/net/netfilter/nf_conntrack_core.c
@@ -25,6 +25,7 @@
 #include <linux/slab.h>
 #include <linux/random.h>
 #include <linux/jhash.h>
+#include <linux/siphash.h>
 #include <linux/err.h>
 #include <linux/percpu.h>
 #include <linux/moduleparam.h>
@@ -449,6 +450,40 @@ nf_ct_invert_tuple(struct nf_conntrack_tuple *inverse,
 }
 EXPORT_SYMBOL_GPL(nf_ct_invert_tuple);
 
+/* Generate a almost-unique pseudo-id for a given conntrack.
+ *
+ * intentionally doesn't re-use any of the seeds used for hash
+ * table location, we assume id gets exposed to userspace.
+ *
+ * Following nf_conn items do not change throughout lifetime
+ * of the nf_conn after it has been committed to main hash table:
+ *
+ * 1. nf_conn address
+ * 2. nf_conn->ext address
+ * 3. nf_conn->master address (normally NULL)
+ * 4. tuple
+ * 5. the associated net namespace
+ */
+u32 nf_ct_get_id(const struct nf_conn *ct)
+{
+	static __read_mostly siphash_key_t ct_id_seed;
+	unsigned long a, b, c, d;
+
+	net_get_random_once(&ct_id_seed, sizeof(ct_id_seed));
+
+	a = (unsigned long)ct;
+	b = (unsigned long)ct->master ^ net_hash_mix(nf_ct_net(ct));
+	c = (unsigned long)ct->ext;
+	d = (unsigned long)siphash(&ct->tuplehash, sizeof(ct->tuplehash),
+				   &ct_id_seed);
+#ifdef CONFIG_64BIT
+	return siphash_4u64((u64)a, (u64)b, (u64)c, (u64)d, &ct_id_seed);
+#else
+	return siphash_4u32((u32)a, (u32)b, (u32)c, (u32)d, &ct_id_seed);
+#endif
+}
+EXPORT_SYMBOL_GPL(nf_ct_get_id);
+
 static void
 clean_from_lists(struct nf_conn *ct)
 {
@@ -982,12 +1017,9 @@ __nf_conntrack_confirm(struct sk_buff *skb)
 
 	/* set conntrack timestamp, if enabled. */
 	tstamp = nf_conn_tstamp_find(ct);
-	if (tstamp) {
-		if (skb->tstamp == 0)
-			__net_timestamp(skb);
+	if (tstamp)
+		tstamp->start = ktime_get_real_ns();
 
-		tstamp->start = ktime_to_ns(skb->tstamp);
-	}
 	/* Since the lookup is lockless, hash insertion must be done after
 	 * starting the timer and setting the CONFIRMED bit. The RCU barriers
 	 * guarantee that no other CPU can find the conntrack before the above
@@ -1350,6 +1382,7 @@ __nf_conntrack_alloc(struct net *net,
 	/* save hash for reusing when confirming */
 	*(unsigned long *)(&ct->tuplehash[IP_CT_DIR_REPLY].hnnode.pprev) = hash;
 	ct->status = 0;
+	ct->timeout = 0;
 	write_pnet(&ct->ct_net, net);
 	memset(&ct->__nfct_init_offset[0], 0,
 	       offsetof(struct nf_conn, proto) -
diff --git a/net/netfilter/nf_conntrack_netlink.c b/net/netfilter/nf_conntrack_netlink.c
index 66c596d287a5..d7f61b0547c6 100644
--- a/net/netfilter/nf_conntrack_netlink.c
+++ b/net/netfilter/nf_conntrack_netlink.c
@@ -29,6 +29,7 @@
 #include <linux/spinlock.h>
 #include <linux/interrupt.h>
 #include <linux/slab.h>
+#include <linux/siphash.h>
 
 #include <linux/netfilter.h>
 #include <net/netlink.h>
@@ -485,7 +486,9 @@ nla_put_failure:
 
 static int ctnetlink_dump_id(struct sk_buff *skb, const struct nf_conn *ct)
 {
-	if (nla_put_be32(skb, CTA_ID, htonl((unsigned long)ct)))
+	__be32 id = (__force __be32)nf_ct_get_id(ct);
+
+	if (nla_put_be32(skb, CTA_ID, id))
 		goto nla_put_failure;
 	return 0;
 
@@ -1286,8 +1289,9 @@ static int ctnetlink_del_conntrack(struct net *net, struct sock *ctnl,
 	}
 
 	if (cda[CTA_ID]) {
-		u_int32_t id = ntohl(nla_get_be32(cda[CTA_ID]));
-		if (id != (u32)(unsigned long)ct) {
+		__be32 id = nla_get_be32(cda[CTA_ID]);
+
+		if (id != (__force __be32)nf_ct_get_id(ct)) {
 			nf_ct_put(ct);
 			return -ENOENT;
 		}
@@ -2692,6 +2696,25 @@ nla_put_failure:
 
 static const union nf_inet_addr any_addr;
 
+static __be32 nf_expect_get_id(const struct nf_conntrack_expect *exp)
+{
+	static __read_mostly siphash_key_t exp_id_seed;
+	unsigned long a, b, c, d;
+
+	net_get_random_once(&exp_id_seed, sizeof(exp_id_seed));
+
+	a = (unsigned long)exp;
+	b = (unsigned long)exp->helper;
+	c = (unsigned long)exp->master;
+	d = (unsigned long)siphash(&exp->tuple, sizeof(exp->tuple), &exp_id_seed);
+
+#ifdef CONFIG_64BIT
+	return (__force __be32)siphash_4u64((u64)a, (u64)b, (u64)c, (u64)d, &exp_id_seed);
+#else
+	return (__force __be32)siphash_4u32((u32)a, (u32)b, (u32)c, (u32)d, &exp_id_seed);
+#endif
+}
+
 static int
 ctnetlink_exp_dump_expect(struct sk_buff *skb,
 			  const struct nf_conntrack_expect *exp)
@@ -2739,7 +2762,7 @@ ctnetlink_exp_dump_expect(struct sk_buff *skb,
 	}
 #endif
 	if (nla_put_be32(skb, CTA_EXPECT_TIMEOUT, htonl(timeout)) ||
-	    nla_put_be32(skb, CTA_EXPECT_ID, htonl((unsigned long)exp)) ||
+	    nla_put_be32(skb, CTA_EXPECT_ID, nf_expect_get_id(exp)) ||
 	    nla_put_be32(skb, CTA_EXPECT_FLAGS, htonl(exp->flags)) ||
 	    nla_put_be32(skb, CTA_EXPECT_CLASS, htonl(exp->class)))
 		goto nla_put_failure;
@@ -3044,7 +3067,8 @@ static int ctnetlink_get_expect(struct net *net, struct sock *ctnl,
 
 	if (cda[CTA_EXPECT_ID]) {
 		__be32 id = nla_get_be32(cda[CTA_EXPECT_ID]);
-		if (ntohl(id) != (u32)(unsigned long)exp) {
+
+		if (id != nf_expect_get_id(exp)) {
 			nf_ct_expect_put(exp);
 			return -ENOENT;
 		}
diff --git a/net/netfilter/nf_conntrack_proto.c b/net/netfilter/nf_conntrack_proto.c
index b9403a266a2e..37bb530d848f 100644
--- a/net/netfilter/nf_conntrack_proto.c
+++ b/net/netfilter/nf_conntrack_proto.c
@@ -55,7 +55,7 @@ void nf_l4proto_log_invalid(const struct sk_buff *skb,
 	struct va_format vaf;
 	va_list args;
 
-	if (net->ct.sysctl_log_invalid != protonum ||
+	if (net->ct.sysctl_log_invalid != protonum &&
 	    net->ct.sysctl_log_invalid != IPPROTO_RAW)
 		return;
 
diff --git a/net/netfilter/nf_conntrack_proto_icmp.c b/net/netfilter/nf_conntrack_proto_icmp.c
index 7df477996b16..9becac953587 100644
--- a/net/netfilter/nf_conntrack_proto_icmp.c
+++ b/net/netfilter/nf_conntrack_proto_icmp.c
@@ -103,49 +103,94 @@ int nf_conntrack_icmp_packet(struct nf_conn *ct,
 	return NF_ACCEPT;
 }
 
-/* Returns conntrack if it dealt with ICMP, and filled in skb fields */
-static int
-icmp_error_message(struct nf_conn *tmpl, struct sk_buff *skb,
-		   const struct nf_hook_state *state)
+/* Check inner header is related to any of the existing connections */
+int nf_conntrack_inet_error(struct nf_conn *tmpl, struct sk_buff *skb,
+			    unsigned int dataoff,
+			    const struct nf_hook_state *state,
+			    u8 l4proto, union nf_inet_addr *outer_daddr)
 {
 	struct nf_conntrack_tuple innertuple, origtuple;
 	const struct nf_conntrack_tuple_hash *h;
 	const struct nf_conntrack_zone *zone;
 	enum ip_conntrack_info ctinfo;
 	struct nf_conntrack_zone tmp;
+	union nf_inet_addr *ct_daddr;
+	enum ip_conntrack_dir dir;
+	struct nf_conn *ct;
 
 	WARN_ON(skb_nfct(skb));
 	zone = nf_ct_zone_tmpl(tmpl, skb, &tmp);
 
 	/* Are they talking about one of our connections? */
-	if (!nf_ct_get_tuplepr(skb,
-			       skb_network_offset(skb) + ip_hdrlen(skb)
-						       + sizeof(struct icmphdr),
-			       PF_INET, state->net, &origtuple)) {
-		pr_debug("icmp_error_message: failed to get tuple\n");
+	if (!nf_ct_get_tuplepr(skb, dataoff,
+			       state->pf, state->net, &origtuple))
 		return -NF_ACCEPT;
-	}
 
 	/* Ordinarily, we'd expect the inverted tupleproto, but it's
 	   been preserved inside the ICMP. */
-	if (!nf_ct_invert_tuple(&innertuple, &origtuple)) {
-		pr_debug("icmp_error_message: no match\n");
+	if (!nf_ct_invert_tuple(&innertuple, &origtuple))
 		return -NF_ACCEPT;
-	}
-
-	ctinfo = IP_CT_RELATED;
 
 	h = nf_conntrack_find_get(state->net, zone, &innertuple);
-	if (!h) {
-		pr_debug("icmp_error_message: no match\n");
+	if (!h)
+		return -NF_ACCEPT;
+
+	/* Consider: A -> T (=This machine) -> B
+	 *   Conntrack entry will look like this:
+	 *      Original:  A->B
+	 *      Reply:     B->T (SNAT case) OR A
+	 *
+	 * When this function runs, we got packet that looks like this:
+	 * iphdr|icmphdr|inner_iphdr|l4header (tcp, udp, ..).
+	 *
+	 * Above nf_conntrack_find_get() makes lookup based on inner_hdr,
+	 * so we should expect that destination of the found connection
+	 * matches outer header destination address.
+	 *
+	 * In above example, we can consider these two cases:
+	 *  1. Error coming in reply direction from B or M (middle box) to
+	 *     T (SNAT case) or A.
+	 *     Inner saddr will be B, dst will be T or A.
+	 *     The found conntrack will be reply tuple (B->T/A).
+	 *  2. Error coming in original direction from A or M to B.
+	 *     Inner saddr will be A, inner daddr will be B.
+	 *     The found conntrack will be original tuple (A->B).
+	 *
+	 * In both cases, conntrack[dir].dst == inner.dst.
+	 *
+	 * A bogus packet could look like this:
+	 *   Inner: B->T
+	 *   Outer: B->X (other machine reachable by T).
+	 *
+	 * In this case, lookup yields connection A->B and will
+	 * set packet from B->X as *RELATED*, even though no connection
+	 * from X was ever seen.
+	 */
+	ct = nf_ct_tuplehash_to_ctrack(h);
+	dir = NF_CT_DIRECTION(h);
+	ct_daddr = &ct->tuplehash[dir].tuple.dst.u3;
+	if (!nf_inet_addr_cmp(outer_daddr, ct_daddr)) {
+		if (state->pf == AF_INET) {
+			nf_l4proto_log_invalid(skb, state->net, state->pf,
+					       l4proto,
+					       "outer daddr %pI4 != inner %pI4",
+					       &outer_daddr->ip, &ct_daddr->ip);
+		} else if (state->pf == AF_INET6) {
+			nf_l4proto_log_invalid(skb, state->net, state->pf,
+					       l4proto,
+					       "outer daddr %pI6 != inner %pI6",
+					       &outer_daddr->ip6, &ct_daddr->ip6);
+		}
+		nf_ct_put(ct);
 		return -NF_ACCEPT;
 	}
 
-	if (NF_CT_DIRECTION(h) == IP_CT_DIR_REPLY)
+	ctinfo = IP_CT_RELATED;
+	if (dir == IP_CT_DIR_REPLY)
 		ctinfo += IP_CT_IS_REPLY;
 
 	/* Update skb to refer to this connection */
-	nf_ct_set(skb, nf_ct_tuplehash_to_ctrack(h), ctinfo);
+	nf_ct_set(skb, ct, ctinfo);
 	return NF_ACCEPT;
 }
 
@@ -162,11 +207,12 @@ int nf_conntrack_icmpv4_error(struct nf_conn *tmpl,
 			      struct sk_buff *skb, unsigned int dataoff,
 			      const struct nf_hook_state *state)
 {
+	union nf_inet_addr outer_daddr;
 	const struct icmphdr *icmph;
 	struct icmphdr _ih;
 
 	/* Not enough header? */
-	icmph = skb_header_pointer(skb, ip_hdrlen(skb), sizeof(_ih), &_ih);
+	icmph = skb_header_pointer(skb, dataoff, sizeof(_ih), &_ih);
 	if (icmph == NULL) {
 		icmp_error_log(skb, state, "short packet");
 		return -NF_ACCEPT;
@@ -199,7 +245,12 @@ int nf_conntrack_icmpv4_error(struct nf_conn *tmpl,
 	    icmph->type != ICMP_REDIRECT)
 		return NF_ACCEPT;
 
-	return icmp_error_message(tmpl, skb, state);
+	memset(&outer_daddr, 0, sizeof(outer_daddr));
+	outer_daddr.ip = ip_hdr(skb)->daddr;
+
+	dataoff += sizeof(*icmph);
+	return nf_conntrack_inet_error(tmpl, skb, dataoff, state,
+				       IPPROTO_ICMP, &outer_daddr);
 }
 
 #if IS_ENABLED(CONFIG_NF_CT_NETLINK)
diff --git a/net/netfilter/nf_conntrack_proto_icmpv6.c b/net/netfilter/nf_conntrack_proto_icmpv6.c
index bec4a3211658..c63ee3612855 100644
--- a/net/netfilter/nf_conntrack_proto_icmpv6.c
+++ b/net/netfilter/nf_conntrack_proto_icmpv6.c
@@ -123,51 +123,6 @@ int nf_conntrack_icmpv6_packet(struct nf_conn *ct,
 	return NF_ACCEPT;
 }
 
-static int
-icmpv6_error_message(struct net *net, struct nf_conn *tmpl,
-		     struct sk_buff *skb,
-		     unsigned int icmp6off)
-{
-	struct nf_conntrack_tuple intuple, origtuple;
-	const struct nf_conntrack_tuple_hash *h;
-	enum ip_conntrack_info ctinfo;
-	struct nf_conntrack_zone tmp;
-
-	WARN_ON(skb_nfct(skb));
-
-	/* Are they talking about one of our connections? */
-	if (!nf_ct_get_tuplepr(skb,
-			       skb_network_offset(skb)
-				+ sizeof(struct ipv6hdr)
-				+ sizeof(struct icmp6hdr),
-			       PF_INET6, net, &origtuple)) {
-		pr_debug("icmpv6_error: Can't get tuple\n");
-		return -NF_ACCEPT;
-	}
-
-	/* Ordinarily, we'd expect the inverted tupleproto, but it's
-	   been preserved inside the ICMP. */
-	if (!nf_ct_invert_tuple(&intuple, &origtuple)) {
-		pr_debug("icmpv6_error: Can't invert tuple\n");
-		return -NF_ACCEPT;
-	}
-
-	ctinfo = IP_CT_RELATED;
-
-	h = nf_conntrack_find_get(net, nf_ct_zone_tmpl(tmpl, skb, &tmp),
-				  &intuple);
-	if (!h) {
-		pr_debug("icmpv6_error: no match\n");
-		return -NF_ACCEPT;
-	} else {
-		if (NF_CT_DIRECTION(h) == IP_CT_DIR_REPLY)
-			ctinfo += IP_CT_IS_REPLY;
-	}
-
-	/* Update skb to refer to this connection */
-	nf_ct_set(skb, nf_ct_tuplehash_to_ctrack(h), ctinfo);
-	return NF_ACCEPT;
-}
 
 static void icmpv6_error_log(const struct sk_buff *skb,
 			     const struct nf_hook_state *state,
@@ -182,6 +137,7 @@ int nf_conntrack_icmpv6_error(struct nf_conn *tmpl,
 			      unsigned int dataoff,
 			      const struct nf_hook_state *state)
 {
+	union nf_inet_addr outer_daddr;
 	const struct icmp6hdr *icmp6h;
 	struct icmp6hdr _ih;
 	int type;
@@ -210,7 +166,11 @@ int nf_conntrack_icmpv6_error(struct nf_conn *tmpl,
 	if (icmp6h->icmp6_type >= 128)
 		return NF_ACCEPT;
 
-	return icmpv6_error_message(state->net, tmpl, skb, dataoff);
+	memcpy(&outer_daddr.ip6, &ipv6_hdr(skb)->daddr,
+	       sizeof(outer_daddr.ip6));
+	dataoff += sizeof(*icmp6h);
+	return nf_conntrack_inet_error(tmpl, skb, dataoff, state,
+				       IPPROTO_ICMPV6, &outer_daddr);
 }
 
 #if IS_ENABLED(CONFIG_NF_CT_NETLINK)
diff --git a/net/netfilter/nf_conntrack_sip.c b/net/netfilter/nf_conntrack_sip.c
index f067c6b50857..39fcc1ed18f3 100644
--- a/net/netfilter/nf_conntrack_sip.c
+++ b/net/netfilter/nf_conntrack_sip.c
@@ -20,9 +20,9 @@
 #include <linux/udp.h>
 #include <linux/tcp.h>
 #include <linux/netfilter.h>
+#include <linux/netfilter_ipv4.h>
+#include <linux/netfilter_ipv6.h>
 
-#include <net/route.h>
-#include <net/ip6_route.h>
 #include <net/netfilter/nf_conntrack.h>
 #include <net/netfilter/nf_conntrack_core.h>
 #include <net/netfilter/nf_conntrack_expect.h>
@@ -871,38 +871,33 @@ static int set_expected_rtp_rtcp(struct sk_buff *skb, unsigned int protoff,
 	} else if (sip_external_media) {
 		struct net_device *dev = skb_dst(skb)->dev;
 		struct net *net = dev_net(dev);
-		struct rtable *rt;
-		struct flowi4 fl4 = {};
-#if IS_ENABLED(CONFIG_IPV6)
-		struct flowi6 fl6 = {};
-#endif
+		struct flowi fl;
 		struct dst_entry *dst = NULL;
 
+		memset(&fl, 0, sizeof(fl));
+
 		switch (nf_ct_l3num(ct)) {
 			case NFPROTO_IPV4:
-				fl4.daddr = daddr->ip;
-				rt = ip_route_output_key(net, &fl4);
-				if (!IS_ERR(rt))
-					dst = &rt->dst;
+				fl.u.ip4.daddr = daddr->ip;
+				nf_ip_route(net, &dst, &fl, false);
 				break;
 
-#if IS_ENABLED(CONFIG_IPV6)
 			case NFPROTO_IPV6:
-				fl6.daddr = daddr->in6;
-				dst = ip6_route_output(net, NULL, &fl6);
-				if (dst->error) {
-					dst_release(dst);
-					dst = NULL;
-				}
+				fl.u.ip6.daddr = daddr->in6;
+				nf_ip6_route(net, &dst, &fl, false);
 				break;
-#endif
 		}
 
 		/* Don't predict any conntracks when media endpoint is reachable
 		 * through the same interface as the signalling peer.
 		 */
-		if (dst && dst->dev == dev)
-			return NF_ACCEPT;
+		if (dst) {
+			bool external_media = (dst->dev == dev);
+
+			dst_release(dst);
+			if (external_media)
+				return NF_ACCEPT;
+		}
 	}
 
 	/* We need to check whether the registration exists before attempting
diff --git a/net/netfilter/nf_nat_core.c b/net/netfilter/nf_nat_core.c
index af7dc6537758..000952719adf 100644
--- a/net/netfilter/nf_nat_core.c
+++ b/net/netfilter/nf_nat_core.c
@@ -415,9 +415,14 @@ static void nf_nat_l4proto_unique_tuple(struct nf_conntrack_tuple *tuple,
 	case IPPROTO_ICMPV6:
 		/* id is same for either direction... */
 		keyptr = &tuple->src.u.icmp.id;
-		min = range->min_proto.icmp.id;
-		range_size = ntohs(range->max_proto.icmp.id) -
-			     ntohs(range->min_proto.icmp.id) + 1;
+		if (!(range->flags & NF_NAT_RANGE_PROTO_SPECIFIED)) {
+			min = 0;
+			range_size = 65536;
+		} else {
+			min = ntohs(range->min_proto.icmp.id);
+			range_size = ntohs(range->max_proto.icmp.id) -
+				     ntohs(range->min_proto.icmp.id) + 1;
+		}
 		goto find_free_id;
 #if IS_ENABLED(CONFIG_NF_CT_PROTO_GRE)
 	case IPPROTO_GRE:
diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c
index 513f93118604..1606eaa5ae0d 100644
--- a/net/netfilter/nf_tables_api.c
+++ b/net/netfilter/nf_tables_api.c
@@ -1545,7 +1545,7 @@ static int nft_chain_parse_hook(struct net *net,
 		if (IS_ERR(type))
 			return PTR_ERR(type);
 	}
-	if (!(type->hook_mask & (1 << hook->num)))
+	if (hook->num > NF_MAX_HOOKS || !(type->hook_mask & (1 << hook->num)))
 		return -EOPNOTSUPP;
 
 	if (type->type == NFT_CHAIN_T_NAT &&
@@ -2806,8 +2806,11 @@ err2:
 	nf_tables_rule_release(&ctx, rule);
 err1:
 	for (i = 0; i < n; i++) {
-		if (info[i].ops != NULL)
+		if (info[i].ops) {
 			module_put(info[i].ops->type->owner);
+			if (info[i].ops->type->release_ops)
+				info[i].ops->type->release_ops(info[i].ops);
+		}
 	}
 	kvfree(info);
 	return err;
diff --git a/net/netfilter/nfnetlink_log.c b/net/netfilter/nfnetlink_log.c
index b1f9c5303f02..0b3347570265 100644
--- a/net/netfilter/nfnetlink_log.c
+++ b/net/netfilter/nfnetlink_log.c
@@ -540,7 +540,7 @@ __build_packet_message(struct nfnl_log_net *log,
 			goto nla_put_failure;
 	}
 
-	if (skb->tstamp) {
+	if (hooknum <= NF_INET_FORWARD && skb->tstamp) {
 		struct nfulnl_msg_packet_timestamp ts;
 		struct timespec64 kts = ktime_to_timespec64(skb->tstamp);
 		ts.sec = cpu_to_be64(kts.tv_sec);
diff --git a/net/netfilter/nfnetlink_queue.c b/net/netfilter/nfnetlink_queue.c
index 0dcc3592d053..e057b2961d31 100644
--- a/net/netfilter/nfnetlink_queue.c
+++ b/net/netfilter/nfnetlink_queue.c
@@ -582,7 +582,7 @@ nfqnl_build_packet_message(struct net *net, struct nfqnl_instance *queue,
 	if (nfqnl_put_bridge(entry, skb) < 0)
 		goto nla_put_failure;
 
-	if (entskb->tstamp) {
+	if (entry->state.hook <= NF_INET_FORWARD && entskb->tstamp) {
 		struct nfqnl_msg_packet_timestamp ts;
 		struct timespec64 kts = ktime_to_timespec64(entskb->tstamp);
 
diff --git a/net/netfilter/nft_objref.c b/net/netfilter/nft_objref.c
index 457a9ceb46af..8dfa798ea683 100644
--- a/net/netfilter/nft_objref.c
+++ b/net/netfilter/nft_objref.c
@@ -65,21 +65,34 @@ nla_put_failure:
 	return -1;
 }
 
-static void nft_objref_destroy(const struct nft_ctx *ctx,
-			       const struct nft_expr *expr)
+static void nft_objref_deactivate(const struct nft_ctx *ctx,
+				  const struct nft_expr *expr,
+				  enum nft_trans_phase phase)
 {
 	struct nft_object *obj = nft_objref_priv(expr);
 
+	if (phase == NFT_TRANS_COMMIT)
+		return;
+
 	obj->use--;
 }
 
+static void nft_objref_activate(const struct nft_ctx *ctx,
+				const struct nft_expr *expr)
+{
+	struct nft_object *obj = nft_objref_priv(expr);
+
+	obj->use++;
+}
+
 static struct nft_expr_type nft_objref_type;
 static const struct nft_expr_ops nft_objref_ops = {
 	.type		= &nft_objref_type,
 	.size		= NFT_EXPR_SIZE(sizeof(struct nft_object *)),
 	.eval		= nft_objref_eval,
 	.init		= nft_objref_init,
-	.destroy	= nft_objref_destroy,
+	.activate	= nft_objref_activate,
+	.deactivate	= nft_objref_deactivate,
 	.dump		= nft_objref_dump,
 };
 
diff --git a/net/netfilter/nft_redir.c b/net/netfilter/nft_redir.c
index f8092926f704..a340cd8a751b 100644
--- a/net/netfilter/nft_redir.c
+++ b/net/netfilter/nft_redir.c
@@ -233,5 +233,5 @@ module_exit(nft_redir_module_exit);
 
 MODULE_LICENSE("GPL");
 MODULE_AUTHOR("Arturo Borrero Gonzalez <arturo@debian.org>");
-MODULE_ALIAS_NFT_AF_EXPR(AF_INET4, "redir");
+MODULE_ALIAS_NFT_AF_EXPR(AF_INET, "redir");
 MODULE_ALIAS_NFT_AF_EXPR(AF_INET6, "redir");
diff --git a/net/netfilter/nft_set_rbtree.c b/net/netfilter/nft_set_rbtree.c
index fa61208371f8..321a0036fdf5 100644
--- a/net/netfilter/nft_set_rbtree.c
+++ b/net/netfilter/nft_set_rbtree.c
@@ -308,10 +308,6 @@ static void *nft_rbtree_deactivate(const struct net *net,
 		else if (d > 0)
 			parent = parent->rb_right;
 		else {
-			if (!nft_set_elem_active(&rbe->ext, genmask)) {
-				parent = parent->rb_left;
-				continue;
-			}
 			if (nft_rbtree_interval_end(rbe) &&
 			    !nft_rbtree_interval_end(this)) {
 				parent = parent->rb_left;
@@ -320,6 +316,9 @@ static void *nft_rbtree_deactivate(const struct net *net,
 				   nft_rbtree_interval_end(this)) {
 				parent = parent->rb_right;
 				continue;
+			} else if (!nft_set_elem_active(&rbe->ext, genmask)) {
+				parent = parent->rb_left;
+				continue;
 			}
 			nft_rbtree_flush(net, set, rbe);
 			return rbe;
diff --git a/net/netfilter/xt_time.c b/net/netfilter/xt_time.c
index c13bcd0ab491..8dbb4d48f2ed 100644
--- a/net/netfilter/xt_time.c
+++ b/net/netfilter/xt_time.c
@@ -163,19 +163,24 @@ time_mt(const struct sk_buff *skb, struct xt_action_param *par)
 	s64 stamp;
 
 	/*
-	 * We cannot use get_seconds() instead of __net_timestamp() here.
+	 * We need real time here, but we can neither use skb->tstamp
+	 * nor __net_timestamp().
+	 *
+	 * skb->tstamp and skb->skb_mstamp_ns overlap, however, they
+	 * use different clock types (real vs monotonic).
+	 *
 	 * Suppose you have two rules:
-	 * 	1. match before 13:00
-	 * 	2. match after 13:00
+	 *	1. match before 13:00
+	 *	2. match after 13:00
+	 *
 	 * If you match against processing time (get_seconds) it
 	 * may happen that the same packet matches both rules if
-	 * it arrived at the right moment before 13:00.
+	 * it arrived at the right moment before 13:00, so it would be
+	 * better to check skb->tstamp and set it via __net_timestamp()
+	 * if needed.  This however breaks outgoing packets tx timestamp,
+	 * and causes them to get delayed forever by fq packet scheduler.
 	 */
-	if (skb->tstamp == 0)
-		__net_timestamp((struct sk_buff *)skb);
-
-	stamp = ktime_to_ns(skb->tstamp);
-	stamp = div_s64(stamp, NSEC_PER_SEC);
+	stamp = get_seconds();
 
 	if (info->flags & XT_TIME_LOCAL_TZ)
 		/* Adjust for local timezone */
diff --git a/net/netlink/af_netlink.c b/net/netlink/af_netlink.c
index f28e937320a3..216ab915dd54 100644
--- a/net/netlink/af_netlink.c
+++ b/net/netlink/af_netlink.c
@@ -988,7 +988,7 @@ static int netlink_bind(struct socket *sock, struct sockaddr *addr,
 	struct netlink_sock *nlk = nlk_sk(sk);
 	struct sockaddr_nl *nladdr = (struct sockaddr_nl *)addr;
 	int err = 0;
-	unsigned long groups = nladdr->nl_groups;
+	unsigned long groups;
 	bool bound;
 
 	if (addr_len < sizeof(struct sockaddr_nl))
@@ -996,6 +996,7 @@ static int netlink_bind(struct socket *sock, struct sockaddr *addr,
 
 	if (nladdr->nl_family != AF_NETLINK)
 		return -EINVAL;
+	groups = nladdr->nl_groups;
 
 	/* Only superuser is allowed to listen multicasts */
 	if (groups) {
diff --git a/net/netlink/genetlink.c b/net/netlink/genetlink.c
index 25eeb6d2a75a..cb69d35c8e6a 100644
--- a/net/netlink/genetlink.c
+++ b/net/netlink/genetlink.c
@@ -362,11 +362,11 @@ int genl_register_family(struct genl_family *family)
 	} else
 		family->attrbuf = NULL;
 
-	family->id = idr_alloc(&genl_fam_idr, family,
-			       start, end + 1, GFP_KERNEL);
+	family->id = idr_alloc_cyclic(&genl_fam_idr, family,
+				      start, end + 1, GFP_KERNEL);
 	if (family->id < 0) {
 		err = family->id;
-		goto errout_locked;
+		goto errout_free;
 	}
 
 	err = genl_validate_assign_mc_groups(family);
@@ -385,6 +385,7 @@ int genl_register_family(struct genl_family *family)
 
 errout_remove:
 	idr_remove(&genl_fam_idr, family->id);
+errout_free:
 	kfree(family->attrbuf);
 errout_locked:
 	genl_unlock_all();
diff --git a/net/netrom/af_netrom.c b/net/netrom/af_netrom.c
index 1d3144d19903..71ffd1a6dc7c 100644
--- a/net/netrom/af_netrom.c
+++ b/net/netrom/af_netrom.c
@@ -1392,18 +1392,22 @@ static int __init nr_proto_init(void)
 	int i;
 	int rc = proto_register(&nr_proto, 0);
 
-	if (rc != 0)
-		goto out;
+	if (rc)
+		return rc;
 
 	if (nr_ndevs > 0x7fffffff/sizeof(struct net_device *)) {
-		printk(KERN_ERR "NET/ROM: nr_proto_init - nr_ndevs parameter to large\n");
-		return -1;
+		pr_err("NET/ROM: %s - nr_ndevs parameter too large\n",
+		       __func__);
+		rc = -EINVAL;
+		goto unregister_proto;
 	}
 
 	dev_nr = kcalloc(nr_ndevs, sizeof(struct net_device *), GFP_KERNEL);
-	if (dev_nr == NULL) {
-		printk(KERN_ERR "NET/ROM: nr_proto_init - unable to allocate device array\n");
-		return -1;
+	if (!dev_nr) {
+		pr_err("NET/ROM: %s - unable to allocate device array\n",
+		       __func__);
+		rc = -ENOMEM;
+		goto unregister_proto;
 	}
 
 	for (i = 0; i < nr_ndevs; i++) {
@@ -1413,13 +1417,13 @@ static int __init nr_proto_init(void)
 		sprintf(name, "nr%d", i);
 		dev = alloc_netdev(0, name, NET_NAME_UNKNOWN, nr_setup);
 		if (!dev) {
-			printk(KERN_ERR "NET/ROM: nr_proto_init - unable to allocate device structure\n");
+			rc = -ENOMEM;
 			goto fail;
 		}
 
 		dev->base_addr = i;
-		if (register_netdev(dev)) {
-			printk(KERN_ERR "NET/ROM: nr_proto_init - unable to register network device\n");
+		rc = register_netdev(dev);
+		if (rc) {
 			free_netdev(dev);
 			goto fail;
 		}
@@ -1427,36 +1431,64 @@ static int __init nr_proto_init(void)
 		dev_nr[i] = dev;
 	}
 
-	if (sock_register(&nr_family_ops)) {
-		printk(KERN_ERR "NET/ROM: nr_proto_init - unable to register socket family\n");
+	rc = sock_register(&nr_family_ops);
+	if (rc)
 		goto fail;
-	}
 
-	register_netdevice_notifier(&nr_dev_notifier);
+	rc = register_netdevice_notifier(&nr_dev_notifier);
+	if (rc)
+		goto out_sock;
 
 	ax25_register_pid(&nr_pid);
 	ax25_linkfail_register(&nr_linkfail_notifier);
 
 #ifdef CONFIG_SYSCTL
-	nr_register_sysctl();
+	rc = nr_register_sysctl();
+	if (rc)
+		goto out_sysctl;
 #endif
 
 	nr_loopback_init();
 
-	proc_create_seq("nr", 0444, init_net.proc_net, &nr_info_seqops);
-	proc_create_seq("nr_neigh", 0444, init_net.proc_net, &nr_neigh_seqops);
-	proc_create_seq("nr_nodes", 0444, init_net.proc_net, &nr_node_seqops);
-out:
-	return rc;
+	rc = -ENOMEM;
+	if (!proc_create_seq("nr", 0444, init_net.proc_net, &nr_info_seqops))
+		goto proc_remove1;
+	if (!proc_create_seq("nr_neigh", 0444, init_net.proc_net,
+			     &nr_neigh_seqops))
+		goto proc_remove2;
+	if (!proc_create_seq("nr_nodes", 0444, init_net.proc_net,
+			     &nr_node_seqops))
+		goto proc_remove3;
+
+	return 0;
+
+proc_remove3:
+	remove_proc_entry("nr_neigh", init_net.proc_net);
+proc_remove2:
+	remove_proc_entry("nr", init_net.proc_net);
+proc_remove1:
+
+	nr_loopback_clear();
+	nr_rt_free();
+
+#ifdef CONFIG_SYSCTL
+	nr_unregister_sysctl();
+out_sysctl:
+#endif
+	ax25_linkfail_release(&nr_linkfail_notifier);
+	ax25_protocol_release(AX25_P_NETROM);
+	unregister_netdevice_notifier(&nr_dev_notifier);
+out_sock:
+	sock_unregister(PF_NETROM);
 fail:
 	while (--i >= 0) {
 		unregister_netdev(dev_nr[i]);
 		free_netdev(dev_nr[i]);
 	}
 	kfree(dev_nr);
+unregister_proto:
 	proto_unregister(&nr_proto);
-	rc = -1;
-	goto out;
+	return rc;
 }
 
 module_init(nr_proto_init);
diff --git a/net/netrom/nr_loopback.c b/net/netrom/nr_loopback.c
index 215ad22a9647..93d13f019981 100644
--- a/net/netrom/nr_loopback.c
+++ b/net/netrom/nr_loopback.c
@@ -70,7 +70,7 @@ static void nr_loopback_timer(struct timer_list *unused)
 	}
 }
 
-void __exit nr_loopback_clear(void)
+void nr_loopback_clear(void)
 {
 	del_timer_sync(&loopback_timer);
 	skb_queue_purge(&loopback_queue);
diff --git a/net/netrom/nr_route.c b/net/netrom/nr_route.c
index 6485f593e2f0..b76aa668a94b 100644
--- a/net/netrom/nr_route.c
+++ b/net/netrom/nr_route.c
@@ -953,7 +953,7 @@ const struct seq_operations nr_neigh_seqops = {
 /*
  *	Free all memory associated with the nodes and routes lists.
  */
-void __exit nr_rt_free(void)
+void nr_rt_free(void)
 {
 	struct nr_neigh *s = NULL;
 	struct nr_node  *t = NULL;
diff --git a/net/netrom/sysctl_net_netrom.c b/net/netrom/sysctl_net_netrom.c
index ba1c368b3f18..771011b84270 100644
--- a/net/netrom/sysctl_net_netrom.c
+++ b/net/netrom/sysctl_net_netrom.c
@@ -146,9 +146,12 @@ static struct ctl_table nr_table[] = {
 	{ }
 };
 
-void __init nr_register_sysctl(void)
+int __init nr_register_sysctl(void)
 {
 	nr_table_header = register_net_sysctl(&init_net, "net/netrom", nr_table);
+	if (!nr_table_header)
+		return -ENOMEM;
+	return 0;
 }
 
 void nr_unregister_sysctl(void)
diff --git a/net/nfc/llcp_sock.c b/net/nfc/llcp_sock.c
index ae296273ce3d..17dcd0b5eb32 100644
--- a/net/nfc/llcp_sock.c
+++ b/net/nfc/llcp_sock.c
@@ -726,6 +726,10 @@ static int llcp_sock_connect(struct socket *sock, struct sockaddr *_addr,
 	llcp_sock->service_name = kmemdup(addr->service_name,
 					  llcp_sock->service_name_len,
 					  GFP_KERNEL);
+	if (!llcp_sock->service_name) {
+		ret = -ENOMEM;
+		goto sock_llcp_release;
+	}
 
 	nfc_llcp_sock_link(&local->connecting_sockets, sk);
 
@@ -745,10 +749,11 @@ static int llcp_sock_connect(struct socket *sock, struct sockaddr *_addr,
 	return ret;
 
 sock_unlink:
-	nfc_llcp_put_ssap(local, llcp_sock->ssap);
-
 	nfc_llcp_sock_unlink(&local->connecting_sockets, sk);
 
+sock_llcp_release:
+	nfc_llcp_put_ssap(local, llcp_sock->ssap);
+
 put_dev:
 	nfc_put_device(dev);
 
diff --git a/net/nfc/nci/hci.c b/net/nfc/nci/hci.c
index ddfc52ac1f9b..c0d323b58e73 100644
--- a/net/nfc/nci/hci.c
+++ b/net/nfc/nci/hci.c
@@ -312,6 +312,10 @@ static void nci_hci_cmd_received(struct nci_dev *ndev, u8 pipe,
 		create_info = (struct nci_hci_create_pipe_resp *)skb->data;
 		dest_gate = create_info->dest_gate;
 		new_pipe = create_info->pipe;
+		if (new_pipe >= NCI_HCI_MAX_PIPES) {
+			status = NCI_HCI_ANY_E_NOK;
+			goto exit;
+		}
 
 		/* Save the new created pipe and bind with local gate,
 		 * the description for skb->data[3] is destination gate id
@@ -336,6 +340,10 @@ static void nci_hci_cmd_received(struct nci_dev *ndev, u8 pipe,
 			goto exit;
 		}
 		delete_info = (struct nci_hci_delete_pipe_noti *)skb->data;
+		if (delete_info->pipe >= NCI_HCI_MAX_PIPES) {
+			status = NCI_HCI_ANY_E_NOK;
+			goto exit;
+		}
 
 		ndev->hci_dev->pipes[delete_info->pipe].gate =
 						NCI_HCI_INVALID_GATE;
diff --git a/net/openvswitch/datapath.c b/net/openvswitch/datapath.c
index 6679e96ab1dc..9dd158ab51b3 100644
--- a/net/openvswitch/datapath.c
+++ b/net/openvswitch/datapath.c
@@ -448,6 +448,10 @@ static int queue_userspace_packet(struct datapath *dp, struct sk_buff *skb,
 
 	upcall = genlmsg_put(user_skb, 0, 0, &dp_packet_genl_family,
 			     0, upcall_info->cmd);
+	if (!upcall) {
+		err = -EINVAL;
+		goto out;
+	}
 	upcall->dp_ifindex = dp_ifindex;
 
 	err = ovs_nla_put_key(key, key, OVS_PACKET_ATTR_KEY, false, user_skb);
@@ -460,6 +464,10 @@ static int queue_userspace_packet(struct datapath *dp, struct sk_buff *skb,
 
 	if (upcall_info->egress_tun_info) {
 		nla = nla_nest_start(user_skb, OVS_PACKET_ATTR_EGRESS_TUN_KEY);
+		if (!nla) {
+			err = -EMSGSIZE;
+			goto out;
+		}
 		err = ovs_nla_put_tunnel_info(user_skb,
 					      upcall_info->egress_tun_info);
 		BUG_ON(err);
@@ -468,6 +476,10 @@ static int queue_userspace_packet(struct datapath *dp, struct sk_buff *skb,
 
 	if (upcall_info->actions_len) {
 		nla = nla_nest_start(user_skb, OVS_PACKET_ATTR_ACTIONS);
+		if (!nla) {
+			err = -EMSGSIZE;
+			goto out;
+		}
 		err = ovs_nla_put_actions(upcall_info->actions,
 					  upcall_info->actions_len,
 					  user_skb);
diff --git a/net/openvswitch/flow_netlink.c b/net/openvswitch/flow_netlink.c
index 691da853bef5..4bdf5e3ac208 100644
--- a/net/openvswitch/flow_netlink.c
+++ b/net/openvswitch/flow_netlink.c
@@ -2306,14 +2306,14 @@ static struct nlattr *reserve_sfa_size(struct sw_flow_actions **sfa,
 
 	struct sw_flow_actions *acts;
 	int new_acts_size;
-	int req_size = NLA_ALIGN(attr_len);
+	size_t req_size = NLA_ALIGN(attr_len);
 	int next_offset = offsetof(struct sw_flow_actions, actions) +
 					(*sfa)->actions_len;
 
 	if (req_size <= (ksize(*sfa) - next_offset))
 		goto out;
 
-	new_acts_size = ksize(*sfa) * 2;
+	new_acts_size = max(next_offset + req_size, ksize(*sfa) * 2);
 
 	if (new_acts_size > MAX_ACTIONS_BUFSIZE) {
 		if ((MAX_ACTIONS_BUFSIZE - next_offset) < req_size) {
diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c
index 8376bc1c1508..9b81813dd16a 100644
--- a/net/packet/af_packet.c
+++ b/net/packet/af_packet.c
@@ -1852,7 +1852,8 @@ oom:
 
 static void packet_parse_headers(struct sk_buff *skb, struct socket *sock)
 {
-	if (!skb->protocol && sock->type == SOCK_RAW) {
+	if ((!skb->protocol || skb->protocol == htons(ETH_P_ALL)) &&
+	    sock->type == SOCK_RAW) {
 		skb_reset_mac_header(skb);
 		skb->protocol = dev_parse_header_protocol(skb);
 	}
@@ -2601,8 +2602,8 @@ static int tpacket_snd(struct packet_sock *po, struct msghdr *msg)
 	void *ph;
 	DECLARE_SOCKADDR(struct sockaddr_ll *, saddr, msg->msg_name);
 	bool need_wait = !(msg->msg_flags & MSG_DONTWAIT);
+	unsigned char *addr = NULL;
 	int tp_len, size_max;
-	unsigned char *addr;
 	void *data;
 	int len_sum = 0;
 	int status = TP_STATUS_AVAILABLE;
@@ -2613,7 +2614,6 @@ static int tpacket_snd(struct packet_sock *po, struct msghdr *msg)
 	if (likely(saddr == NULL)) {
 		dev	= packet_cached_dev_get(po);
 		proto	= po->num;
-		addr	= NULL;
 	} else {
 		err = -EINVAL;
 		if (msg->msg_namelen < sizeof(struct sockaddr_ll))
@@ -2623,10 +2623,13 @@ static int tpacket_snd(struct packet_sock *po, struct msghdr *msg)
 						sll_addr)))
 			goto out;
 		proto	= saddr->sll_protocol;
-		addr	= saddr->sll_halen ? saddr->sll_addr : NULL;
 		dev = dev_get_by_index(sock_net(&po->sk), saddr->sll_ifindex);
-		if (addr && dev && saddr->sll_halen < dev->addr_len)
-			goto out_put;
+		if (po->sk.sk_socket->type == SOCK_DGRAM) {
+			if (dev && msg->msg_namelen < dev->addr_len +
+				   offsetof(struct sockaddr_ll, sll_addr))
+				goto out_put;
+			addr = saddr->sll_addr;
+		}
 	}
 
 	err = -ENXIO;
@@ -2798,7 +2801,7 @@ static int packet_snd(struct socket *sock, struct msghdr *msg, size_t len)
 	struct sk_buff *skb;
 	struct net_device *dev;
 	__be16 proto;
-	unsigned char *addr;
+	unsigned char *addr = NULL;
 	int err, reserve = 0;
 	struct sockcm_cookie sockc;
 	struct virtio_net_hdr vnet_hdr = { 0 };
@@ -2815,7 +2818,6 @@ static int packet_snd(struct socket *sock, struct msghdr *msg, size_t len)
 	if (likely(saddr == NULL)) {
 		dev	= packet_cached_dev_get(po);
 		proto	= po->num;
-		addr	= NULL;
 	} else {
 		err = -EINVAL;
 		if (msg->msg_namelen < sizeof(struct sockaddr_ll))
@@ -2823,10 +2825,13 @@ static int packet_snd(struct socket *sock, struct msghdr *msg, size_t len)
 		if (msg->msg_namelen < (saddr->sll_halen + offsetof(struct sockaddr_ll, sll_addr)))
 			goto out;
 		proto	= saddr->sll_protocol;
-		addr	= saddr->sll_halen ? saddr->sll_addr : NULL;
 		dev = dev_get_by_index(sock_net(sk), saddr->sll_ifindex);
-		if (addr && dev && saddr->sll_halen < dev->addr_len)
-			goto out_unlock;
+		if (sock->type == SOCK_DGRAM) {
+			if (dev && msg->msg_namelen < dev->addr_len +
+				   offsetof(struct sockaddr_ll, sll_addr))
+				goto out_unlock;
+			addr = saddr->sll_addr;
+		}
 	}
 
 	err = -ENXIO;
@@ -3243,7 +3248,7 @@ static int packet_create(struct net *net, struct socket *sock, int protocol,
 	}
 
 	mutex_lock(&net->packet.sklist_lock);
-	sk_add_node_rcu(sk, &net->packet.sklist);
+	sk_add_node_tail_rcu(sk, &net->packet.sklist);
 	mutex_unlock(&net->packet.sklist_lock);
 
 	preempt_disable();
@@ -3343,20 +3348,29 @@ static int packet_recvmsg(struct socket *sock, struct msghdr *msg, size_t len,
 	sock_recv_ts_and_drops(msg, sk, skb);
 
 	if (msg->msg_name) {
+		int copy_len;
+
 		/* If the address length field is there to be filled
 		 * in, we fill it in now.
 		 */
 		if (sock->type == SOCK_PACKET) {
 			__sockaddr_check_size(sizeof(struct sockaddr_pkt));
 			msg->msg_namelen = sizeof(struct sockaddr_pkt);
+			copy_len = msg->msg_namelen;
 		} else {
 			struct sockaddr_ll *sll = &PACKET_SKB_CB(skb)->sa.ll;
 
 			msg->msg_namelen = sll->sll_halen +
 				offsetof(struct sockaddr_ll, sll_addr);
+			copy_len = msg->msg_namelen;
+			if (msg->msg_namelen < sizeof(struct sockaddr_ll)) {
+				memset(msg->msg_name +
+				       offsetof(struct sockaddr_ll, sll_addr),
+				       0, sizeof(sll->sll_addr));
+				msg->msg_namelen = sizeof(struct sockaddr_ll);
+			}
 		}
-		memcpy(msg->msg_name, &PACKET_SKB_CB(skb)->sa,
-		       msg->msg_namelen);
+		memcpy(msg->msg_name, &PACKET_SKB_CB(skb)->sa, copy_len);
 	}
 
 	if (pkt_sk(sk)->auxdata) {
@@ -4209,7 +4223,7 @@ static struct pgv *alloc_pg_vec(struct tpacket_req *req, int order)
 	struct pgv *pg_vec;
 	int i;
 
-	pg_vec = kcalloc(block_nr, sizeof(struct pgv), GFP_KERNEL);
+	pg_vec = kcalloc(block_nr, sizeof(struct pgv), GFP_KERNEL | __GFP_NOWARN);
 	if (unlikely(!pg_vec))
 		goto out;
 
diff --git a/net/rds/af_rds.c b/net/rds/af_rds.c
index d6cc97fbbbb0..2b969f99ef13 100644
--- a/net/rds/af_rds.c
+++ b/net/rds/af_rds.c
@@ -543,6 +543,9 @@ static int rds_connect(struct socket *sock, struct sockaddr *uaddr,
 	struct rds_sock *rs = rds_sk_to_rs(sk);
 	int ret = 0;
 
+	if (addr_len < offsetofend(struct sockaddr, sa_family))
+		return -EINVAL;
+
 	lock_sock(sk);
 
 	switch (uaddr->sa_family) {
diff --git a/net/rds/bind.c b/net/rds/bind.c
index 17c9d9f0c848..0f4398e7f2a7 100644
--- a/net/rds/bind.c
+++ b/net/rds/bind.c
@@ -173,6 +173,8 @@ int rds_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len)
 	/* We allow an RDS socket to be bound to either IPv4 or IPv6
 	 * address.
 	 */
+	if (addr_len < offsetofend(struct sockaddr, sa_family))
+		return -EINVAL;
 	if (uaddr->sa_family == AF_INET) {
 		struct sockaddr_in *sin = (struct sockaddr_in *)uaddr;
 
diff --git a/net/rds/ib_fmr.c b/net/rds/ib_fmr.c
index 31cf37da4510..93c0437e6a5f 100644
--- a/net/rds/ib_fmr.c
+++ b/net/rds/ib_fmr.c
@@ -44,6 +44,17 @@ struct rds_ib_mr *rds_ib_alloc_fmr(struct rds_ib_device *rds_ibdev, int npages)
 	else
 		pool = rds_ibdev->mr_1m_pool;
 
+	if (atomic_read(&pool->dirty_count) >= pool->max_items / 10)
+		queue_delayed_work(rds_ib_mr_wq, &pool->flush_worker, 10);
+
+	/* Switch pools if one of the pool is reaching upper limit */
+	if (atomic_read(&pool->dirty_count) >=  pool->max_items * 9 / 10) {
+		if (pool->pool_type == RDS_IB_MR_8K_POOL)
+			pool = rds_ibdev->mr_1m_pool;
+		else
+			pool = rds_ibdev->mr_8k_pool;
+	}
+
 	ibmr = rds_ib_try_reuse_ibmr(pool);
 	if (ibmr)
 		return ibmr;
diff --git a/net/rds/ib_rdma.c b/net/rds/ib_rdma.c
index 63c8d107adcf..d664e9ade74d 100644
--- a/net/rds/ib_rdma.c
+++ b/net/rds/ib_rdma.c
@@ -454,9 +454,6 @@ struct rds_ib_mr *rds_ib_try_reuse_ibmr(struct rds_ib_mr_pool *pool)
 	struct rds_ib_mr *ibmr = NULL;
 	int iter = 0;
 
-	if (atomic_read(&pool->dirty_count) >= pool->max_items_soft / 10)
-		queue_delayed_work(rds_ib_mr_wq, &pool->flush_worker, 10);
-
 	while (1) {
 		ibmr = rds_ib_reuse_mr(pool);
 		if (ibmr)
diff --git a/net/rds/ib_recv.c b/net/rds/ib_recv.c
index 70559854837e..8946c89d7392 100644
--- a/net/rds/ib_recv.c
+++ b/net/rds/ib_recv.c
@@ -772,7 +772,7 @@ static void rds_ib_cong_recv(struct rds_connection *conn,
 	unsigned long frag_off;
 	unsigned long to_copy;
 	unsigned long copied;
-	uint64_t uncongested = 0;
+	__le64 uncongested = 0;
 	void *addr;
 
 	/* catch completely corrupt packets */
@@ -789,7 +789,7 @@ static void rds_ib_cong_recv(struct rds_connection *conn,
 	copied = 0;
 
 	while (copied < RDS_CONG_MAP_BYTES) {
-		uint64_t *src, *dst;
+		__le64 *src, *dst;
 		unsigned int k;
 
 		to_copy = min(RDS_FRAG_SIZE - frag_off, PAGE_SIZE - map_off);
@@ -824,9 +824,7 @@ static void rds_ib_cong_recv(struct rds_connection *conn,
 	}
 
 	/* the congestion map is in little endian order */
-	uncongested = le64_to_cpu(uncongested);
-
-	rds_cong_map_updated(map, uncongested);
+	rds_cong_map_updated(map, le64_to_cpu(uncongested));
 }
 
 static void rds_ib_process_recv(struct rds_connection *conn,
diff --git a/net/rds/tcp.c b/net/rds/tcp.c
index fd2694174607..faf726e00e27 100644
--- a/net/rds/tcp.c
+++ b/net/rds/tcp.c
@@ -608,7 +608,7 @@ static void rds_tcp_kill_sock(struct net *net)
 	list_for_each_entry_safe(tc, _tc, &rds_tcp_conn_list, t_tcp_node) {
 		struct net *c_net = read_pnet(&tc->t_cpath->cp_conn->c_net);
 
-		if (net != c_net || !tc->t_sock)
+		if (net != c_net)
 			continue;
 		if (!list_has_conn(&tmp_list, tc->t_cpath->cp_conn)) {
 			list_move_tail(&tc->t_tcp_node, &tmp_list);
diff --git a/net/rose/rose_loopback.c b/net/rose/rose_loopback.c
index 7af4f99c4a93..094a6621f8e8 100644
--- a/net/rose/rose_loopback.c
+++ b/net/rose/rose_loopback.c
@@ -16,6 +16,7 @@
 #include <linux/init.h>
 
 static struct sk_buff_head loopback_queue;
+#define ROSE_LOOPBACK_LIMIT 1000
 static struct timer_list loopback_timer;
 
 static void rose_set_loopback_timer(void);
@@ -35,29 +36,27 @@ static int rose_loopback_running(void)
 
 int rose_loopback_queue(struct sk_buff *skb, struct rose_neigh *neigh)
 {
-	struct sk_buff *skbn;
+	struct sk_buff *skbn = NULL;
 
-	skbn = skb_clone(skb, GFP_ATOMIC);
+	if (skb_queue_len(&loopback_queue) < ROSE_LOOPBACK_LIMIT)
+		skbn = skb_clone(skb, GFP_ATOMIC);
 
-	kfree_skb(skb);
-
-	if (skbn != NULL) {
+	if (skbn) {
+		consume_skb(skb);
 		skb_queue_tail(&loopback_queue, skbn);
 
 		if (!rose_loopback_running())
 			rose_set_loopback_timer();
+	} else {
+		kfree_skb(skb);
 	}
 
 	return 1;
 }
 
-
 static void rose_set_loopback_timer(void)
 {
-	del_timer(&loopback_timer);
-
-	loopback_timer.expires  = jiffies + 10;
-	add_timer(&loopback_timer);
+	mod_timer(&loopback_timer, jiffies + 10);
 }
 
 static void rose_loopback_timer(struct timer_list *unused)
@@ -68,8 +67,12 @@ static void rose_loopback_timer(struct timer_list *unused)
 	struct sock *sk;
 	unsigned short frametype;
 	unsigned int lci_i, lci_o;
+	int count;
 
-	while ((skb = skb_dequeue(&loopback_queue)) != NULL) {
+	for (count = 0; count < ROSE_LOOPBACK_LIMIT; count++) {
+		skb = skb_dequeue(&loopback_queue);
+		if (!skb)
+			return;
 		if (skb->len < ROSE_MIN_LEN) {
 			kfree_skb(skb);
 			continue;
@@ -106,6 +109,8 @@ static void rose_loopback_timer(struct timer_list *unused)
 			kfree_skb(skb);
 		}
 	}
+	if (!skb_queue_empty(&loopback_queue))
+		mod_timer(&loopback_timer, jiffies + 1);
 }
 
 void __exit rose_loopback_clear(void)
diff --git a/net/rose/rose_subr.c b/net/rose/rose_subr.c
index 7ca57741b2fb..7849f286bb93 100644
--- a/net/rose/rose_subr.c
+++ b/net/rose/rose_subr.c
@@ -105,16 +105,17 @@ void rose_write_internal(struct sock *sk, int frametype)
 	struct sk_buff *skb;
 	unsigned char  *dptr;
 	unsigned char  lci1, lci2;
-	char buffer[100];
-	int len, faclen = 0;
+	int maxfaclen = 0;
+	int len, faclen;
+	int reserve;
 
-	len = AX25_BPQ_HEADER_LEN + AX25_MAX_HEADER_LEN + ROSE_MIN_LEN + 1;
+	reserve = AX25_BPQ_HEADER_LEN + AX25_MAX_HEADER_LEN + 1;
+	len = ROSE_MIN_LEN;
 
 	switch (frametype) {
 	case ROSE_CALL_REQUEST:
 		len   += 1 + ROSE_ADDR_LEN + ROSE_ADDR_LEN;
-		faclen = rose_create_facilities(buffer, rose);
-		len   += faclen;
+		maxfaclen = 256;
 		break;
 	case ROSE_CALL_ACCEPTED:
 	case ROSE_CLEAR_REQUEST:
@@ -123,15 +124,16 @@ void rose_write_internal(struct sock *sk, int frametype)
 		break;
 	}
 
-	if ((skb = alloc_skb(len, GFP_ATOMIC)) == NULL)
+	skb = alloc_skb(reserve + len + maxfaclen, GFP_ATOMIC);
+	if (!skb)
 		return;
 
 	/*
 	 *	Space for AX.25 header and PID.
 	 */
-	skb_reserve(skb, AX25_BPQ_HEADER_LEN + AX25_MAX_HEADER_LEN + 1);
+	skb_reserve(skb, reserve);
 
-	dptr = skb_put(skb, skb_tailroom(skb));
+	dptr = skb_put(skb, len);
 
 	lci1 = (rose->lci >> 8) & 0x0F;
 	lci2 = (rose->lci >> 0) & 0xFF;
@@ -146,7 +148,8 @@ void rose_write_internal(struct sock *sk, int frametype)
 		dptr   += ROSE_ADDR_LEN;
 		memcpy(dptr, &rose->source_addr, ROSE_ADDR_LEN);
 		dptr   += ROSE_ADDR_LEN;
-		memcpy(dptr, buffer, faclen);
+		faclen = rose_create_facilities(dptr, rose);
+		skb_put(skb, faclen);
 		dptr   += faclen;
 		break;
 
diff --git a/net/rxrpc/af_rxrpc.c b/net/rxrpc/af_rxrpc.c
index 96f2952bbdfd..ae8c5d7f3bf1 100644
--- a/net/rxrpc/af_rxrpc.c
+++ b/net/rxrpc/af_rxrpc.c
@@ -135,7 +135,7 @@ static int rxrpc_bind(struct socket *sock, struct sockaddr *saddr, int len)
 	struct sockaddr_rxrpc *srx = (struct sockaddr_rxrpc *)saddr;
 	struct rxrpc_local *local;
 	struct rxrpc_sock *rx = rxrpc_sk(sock->sk);
-	u16 service_id = srx->srx_service;
+	u16 service_id;
 	int ret;
 
 	_enter("%p,%p,%d", rx, saddr, len);
@@ -143,6 +143,7 @@ static int rxrpc_bind(struct socket *sock, struct sockaddr *saddr, int len)
 	ret = rxrpc_validate_address(rx, srx, len);
 	if (ret < 0)
 		goto error;
+	service_id = srx->srx_service;
 
 	lock_sock(&rx->sk);
 
@@ -370,18 +371,22 @@ EXPORT_SYMBOL(rxrpc_kernel_end_call);
  * rxrpc_kernel_check_life - Check to see whether a call is still alive
  * @sock: The socket the call is on
  * @call: The call to check
+ * @_life: Where to store the life value
  *
  * Allow a kernel service to find out whether a call is still alive - ie. we're
- * getting ACKs from the server.  Returns a number representing the life state
- * which can be compared to that returned by a previous call.
+ * getting ACKs from the server.  Passes back in *_life a number representing
+ * the life state which can be compared to that returned by a previous call and
+ * return true if the call is still alive.
  *
  * If the life state stalls, rxrpc_kernel_probe_life() should be called and
  * then 2RTT waited.
  */
-u32 rxrpc_kernel_check_life(const struct socket *sock,
-			    const struct rxrpc_call *call)
+bool rxrpc_kernel_check_life(const struct socket *sock,
+			     const struct rxrpc_call *call,
+			     u32 *_life)
 {
-	return call->acks_latest;
+	*_life = call->acks_latest;
+	return call->state != RXRPC_CALL_COMPLETE;
 }
 EXPORT_SYMBOL(rxrpc_kernel_check_life);
 
diff --git a/net/rxrpc/ar-internal.h b/net/rxrpc/ar-internal.h
index 4b1a534d290a..062ca9dc29b8 100644
--- a/net/rxrpc/ar-internal.h
+++ b/net/rxrpc/ar-internal.h
@@ -654,6 +654,7 @@ struct rxrpc_call {
 	u8			ackr_reason;	/* reason to ACK */
 	u16			ackr_skew;	/* skew on packet being ACK'd */
 	rxrpc_serial_t		ackr_serial;	/* serial of packet being ACK'd */
+	rxrpc_serial_t		ackr_first_seq;	/* first sequence number received */
 	rxrpc_seq_t		ackr_prev_seq;	/* previous sequence number received */
 	rxrpc_seq_t		ackr_consumed;	/* Highest packet shown consumed */
 	rxrpc_seq_t		ackr_seen;	/* Highest packet shown seen */
diff --git a/net/rxrpc/call_object.c b/net/rxrpc/call_object.c
index 8aa2937b069f..fe96881a334d 100644
--- a/net/rxrpc/call_object.c
+++ b/net/rxrpc/call_object.c
@@ -604,30 +604,30 @@ void rxrpc_destroy_all_calls(struct rxrpc_net *rxnet)
 
 	_enter("");
 
-	if (list_empty(&rxnet->calls))
-		return;
+	if (!list_empty(&rxnet->calls)) {
+		write_lock(&rxnet->call_lock);
 
-	write_lock(&rxnet->call_lock);
+		while (!list_empty(&rxnet->calls)) {
+			call = list_entry(rxnet->calls.next,
+					  struct rxrpc_call, link);
+			_debug("Zapping call %p", call);
 
-	while (!list_empty(&rxnet->calls)) {
-		call = list_entry(rxnet->calls.next, struct rxrpc_call, link);
-		_debug("Zapping call %p", call);
+			rxrpc_see_call(call);
+			list_del_init(&call->link);
 
-		rxrpc_see_call(call);
-		list_del_init(&call->link);
+			pr_err("Call %p still in use (%d,%s,%lx,%lx)!\n",
+			       call, atomic_read(&call->usage),
+			       rxrpc_call_states[call->state],
+			       call->flags, call->events);
 
-		pr_err("Call %p still in use (%d,%s,%lx,%lx)!\n",
-		       call, atomic_read(&call->usage),
-		       rxrpc_call_states[call->state],
-		       call->flags, call->events);
+			write_unlock(&rxnet->call_lock);
+			cond_resched();
+			write_lock(&rxnet->call_lock);
+		}
 
 		write_unlock(&rxnet->call_lock);
-		cond_resched();
-		write_lock(&rxnet->call_lock);
 	}
 
-	write_unlock(&rxnet->call_lock);
-
 	atomic_dec(&rxnet->nr_calls);
 	wait_var_event(&rxnet->nr_calls, !atomic_read(&rxnet->nr_calls));
 }
diff --git a/net/rxrpc/conn_event.c b/net/rxrpc/conn_event.c
index b6fca8ebb117..8d31fb4c51e1 100644
--- a/net/rxrpc/conn_event.c
+++ b/net/rxrpc/conn_event.c
@@ -153,7 +153,8 @@ static void rxrpc_conn_retransmit_call(struct rxrpc_connection *conn,
  * pass a connection-level abort onto all calls on that connection
  */
 static void rxrpc_abort_calls(struct rxrpc_connection *conn,
-			      enum rxrpc_call_completion compl)
+			      enum rxrpc_call_completion compl,
+			      rxrpc_serial_t serial)
 {
 	struct rxrpc_call *call;
 	int i;
@@ -173,6 +174,9 @@ static void rxrpc_abort_calls(struct rxrpc_connection *conn,
 						  call->call_id, 0,
 						  conn->abort_code,
 						  conn->error);
+			else
+				trace_rxrpc_rx_abort(call, serial,
+						     conn->abort_code);
 			if (rxrpc_set_call_completion(call, compl,
 						      conn->abort_code,
 						      conn->error))
@@ -213,8 +217,6 @@ static int rxrpc_abort_connection(struct rxrpc_connection *conn,
 	conn->state = RXRPC_CONN_LOCALLY_ABORTED;
 	spin_unlock_bh(&conn->state_lock);
 
-	rxrpc_abort_calls(conn, RXRPC_CALL_LOCALLY_ABORTED);
-
 	msg.msg_name	= &conn->params.peer->srx.transport;
 	msg.msg_namelen	= conn->params.peer->srx.transport_len;
 	msg.msg_control	= NULL;
@@ -242,6 +244,7 @@ static int rxrpc_abort_connection(struct rxrpc_connection *conn,
 	len = iov[0].iov_len + iov[1].iov_len;
 
 	serial = atomic_inc_return(&conn->serial);
+	rxrpc_abort_calls(conn, RXRPC_CALL_LOCALLY_ABORTED, serial);
 	whdr.serial = htonl(serial);
 	_proto("Tx CONN ABORT %%%u { %d }", serial, conn->abort_code);
 
@@ -321,7 +324,7 @@ static int rxrpc_process_event(struct rxrpc_connection *conn,
 		conn->error = -ECONNABORTED;
 		conn->abort_code = abort_code;
 		conn->state = RXRPC_CONN_REMOTELY_ABORTED;
-		rxrpc_abort_calls(conn, RXRPC_CALL_REMOTELY_ABORTED);
+		rxrpc_abort_calls(conn, RXRPC_CALL_REMOTELY_ABORTED, sp->hdr.serial);
 		return -ECONNABORTED;
 
 	case RXRPC_PACKET_TYPE_CHALLENGE:
diff --git a/net/rxrpc/input.c b/net/rxrpc/input.c
index 9128aa0e40aa..c2c35cf4e308 100644
--- a/net/rxrpc/input.c
+++ b/net/rxrpc/input.c
@@ -837,7 +837,7 @@ static void rxrpc_input_ack(struct rxrpc_call *call, struct sk_buff *skb,
 		u8 acks[RXRPC_MAXACKS];
 	} buf;
 	rxrpc_serial_t acked_serial;
-	rxrpc_seq_t first_soft_ack, hard_ack;
+	rxrpc_seq_t first_soft_ack, hard_ack, prev_pkt;
 	int nr_acks, offset, ioffset;
 
 	_enter("");
@@ -851,13 +851,14 @@ static void rxrpc_input_ack(struct rxrpc_call *call, struct sk_buff *skb,
 
 	acked_serial = ntohl(buf.ack.serial);
 	first_soft_ack = ntohl(buf.ack.firstPacket);
+	prev_pkt = ntohl(buf.ack.previousPacket);
 	hard_ack = first_soft_ack - 1;
 	nr_acks = buf.ack.nAcks;
 	summary.ack_reason = (buf.ack.reason < RXRPC_ACK__INVALID ?
 			      buf.ack.reason : RXRPC_ACK__INVALID);
 
 	trace_rxrpc_rx_ack(call, sp->hdr.serial, acked_serial,
-			   first_soft_ack, ntohl(buf.ack.previousPacket),
+			   first_soft_ack, prev_pkt,
 			   summary.ack_reason, nr_acks);
 
 	if (buf.ack.reason == RXRPC_ACK_PING_RESPONSE)
@@ -878,8 +879,9 @@ static void rxrpc_input_ack(struct rxrpc_call *call, struct sk_buff *skb,
 				  rxrpc_propose_ack_respond_to_ack);
 	}
 
-	/* Discard any out-of-order or duplicate ACKs. */
-	if (before_eq(sp->hdr.serial, call->acks_latest))
+	/* Discard any out-of-order or duplicate ACKs (outside lock). */
+	if (before(first_soft_ack, call->ackr_first_seq) ||
+	    before(prev_pkt, call->ackr_prev_seq))
 		return;
 
 	buf.info.rxMTU = 0;
@@ -890,12 +892,16 @@ static void rxrpc_input_ack(struct rxrpc_call *call, struct sk_buff *skb,
 
 	spin_lock(&call->input_lock);
 
-	/* Discard any out-of-order or duplicate ACKs. */
-	if (before_eq(sp->hdr.serial, call->acks_latest))
+	/* Discard any out-of-order or duplicate ACKs (inside lock). */
+	if (before(first_soft_ack, call->ackr_first_seq) ||
+	    before(prev_pkt, call->ackr_prev_seq))
 		goto out;
 	call->acks_latest_ts = skb->tstamp;
 	call->acks_latest = sp->hdr.serial;
 
+	call->ackr_first_seq = first_soft_ack;
+	call->ackr_prev_seq = prev_pkt;
+
 	/* Parse rwind and mtu sizes if provided. */
 	if (buf.info.rxMTU)
 		rxrpc_input_ackinfo(call, skb, &buf.info);
@@ -1155,19 +1161,19 @@ int rxrpc_extract_header(struct rxrpc_skb_priv *sp, struct sk_buff *skb)
  * handle data received on the local endpoint
  * - may be called in interrupt context
  *
- * The socket is locked by the caller and this prevents the socket from being
- * shut down and the local endpoint from going away, thus sk_user_data will not
- * be cleared until this function returns.
+ * [!] Note that as this is called from the encap_rcv hook, the socket is not
+ * held locked by the caller and nothing prevents sk_user_data on the UDP from
+ * being cleared in the middle of processing this function.
  *
  * Called with the RCU read lock held from the IP layer via UDP.
  */
 int rxrpc_input_packet(struct sock *udp_sk, struct sk_buff *skb)
 {
+	struct rxrpc_local *local = rcu_dereference_sk_user_data(udp_sk);
 	struct rxrpc_connection *conn;
 	struct rxrpc_channel *chan;
 	struct rxrpc_call *call = NULL;
 	struct rxrpc_skb_priv *sp;
-	struct rxrpc_local *local = udp_sk->sk_user_data;
 	struct rxrpc_peer *peer = NULL;
 	struct rxrpc_sock *rx = NULL;
 	unsigned int channel;
@@ -1175,6 +1181,10 @@ int rxrpc_input_packet(struct sock *udp_sk, struct sk_buff *skb)
 
 	_enter("%p", udp_sk);
 
+	if (unlikely(!local)) {
+		kfree_skb(skb);
+		return 0;
+	}
 	if (skb->tstamp == 0)
 		skb->tstamp = ktime_get_real();
 
diff --git a/net/rxrpc/local_object.c b/net/rxrpc/local_object.c
index 15cf42d5b53a..01959db51445 100644
--- a/net/rxrpc/local_object.c
+++ b/net/rxrpc/local_object.c
@@ -304,7 +304,8 @@ nomem:
 	ret = -ENOMEM;
 sock_error:
 	mutex_unlock(&rxnet->local_mutex);
-	kfree(local);
+	if (local)
+		call_rcu(&local->rcu, rxrpc_local_rcu);
 	_leave(" = %d", ret);
 	return ERR_PTR(ret);
 
diff --git a/net/rxrpc/output.c b/net/rxrpc/output.c
index 736aa9281100..004c762c2e8d 100644
--- a/net/rxrpc/output.c
+++ b/net/rxrpc/output.c
@@ -335,7 +335,6 @@ int rxrpc_send_data_packet(struct rxrpc_call *call, struct sk_buff *skb,
 	struct kvec iov[2];
 	rxrpc_serial_t serial;
 	size_t len;
-	bool lost = false;
 	int ret, opt;
 
 	_enter(",{%d}", skb->len);
@@ -393,14 +392,14 @@ int rxrpc_send_data_packet(struct rxrpc_call *call, struct sk_buff *skb,
 		static int lose;
 		if ((lose++ & 7) == 7) {
 			ret = 0;
-			lost = true;
+			trace_rxrpc_tx_data(call, sp->hdr.seq, serial,
+					    whdr.flags, retrans, true);
+			goto done;
 		}
 	}
 
-	trace_rxrpc_tx_data(call, sp->hdr.seq, serial, whdr.flags,
-			    retrans, lost);
-	if (lost)
-		goto done;
+	trace_rxrpc_tx_data(call, sp->hdr.seq, serial, whdr.flags, retrans,
+			    false);
 
 	/* send the packet with the don't fragment bit set if we currently
 	 * think it's small enough */
diff --git a/net/rxrpc/peer_event.c b/net/rxrpc/peer_event.c
index bc05af89fc38..6e84d878053c 100644
--- a/net/rxrpc/peer_event.c
+++ b/net/rxrpc/peer_event.c
@@ -157,6 +157,11 @@ void rxrpc_error_report(struct sock *sk)
 
 	_enter("%p{%d}", sk, local->debug_id);
 
+	/* Clear the outstanding error value on the socket so that it doesn't
+	 * cause kernel_sendmsg() to return it later.
+	 */
+	sock_error(sk);
+
 	skb = sock_dequeue_err_skb(sk);
 	if (!skb) {
 		_leave("UDP socket errqueue empty");
diff --git a/net/rxrpc/sendmsg.c b/net/rxrpc/sendmsg.c
index 46c9312085b1..bec64deb7b0a 100644
--- a/net/rxrpc/sendmsg.c
+++ b/net/rxrpc/sendmsg.c
@@ -152,12 +152,13 @@ static void rxrpc_notify_end_tx(struct rxrpc_sock *rx, struct rxrpc_call *call,
 }
 
 /*
- * Queue a DATA packet for transmission, set the resend timeout and send the
- * packet immediately
+ * Queue a DATA packet for transmission, set the resend timeout and send
+ * the packet immediately.  Returns the error from rxrpc_send_data_packet()
+ * in case the caller wants to do something with it.
  */
-static void rxrpc_queue_packet(struct rxrpc_sock *rx, struct rxrpc_call *call,
-			       struct sk_buff *skb, bool last,
-			       rxrpc_notify_end_tx_t notify_end_tx)
+static int rxrpc_queue_packet(struct rxrpc_sock *rx, struct rxrpc_call *call,
+			      struct sk_buff *skb, bool last,
+			      rxrpc_notify_end_tx_t notify_end_tx)
 {
 	struct rxrpc_skb_priv *sp = rxrpc_skb(skb);
 	unsigned long now;
@@ -250,7 +251,8 @@ static void rxrpc_queue_packet(struct rxrpc_sock *rx, struct rxrpc_call *call,
 
 out:
 	rxrpc_free_skb(skb, rxrpc_skb_tx_freed);
-	_leave("");
+	_leave(" = %d", ret);
+	return ret;
 }
 
 /*
@@ -423,9 +425,10 @@ static int rxrpc_send_data(struct rxrpc_sock *rx,
 			if (ret < 0)
 				goto out;
 
-			rxrpc_queue_packet(rx, call, skb,
-					   !msg_data_left(msg) && !more,
-					   notify_end_tx);
+			ret = rxrpc_queue_packet(rx, call, skb,
+						 !msg_data_left(msg) && !more,
+						 notify_end_tx);
+			/* Should check for failure here */
 			skb = NULL;
 		}
 	} while (msg_data_left(msg) > 0);
diff --git a/net/sched/Kconfig b/net/sched/Kconfig
index 1b9afdee5ba9..5c02ad97ef23 100644
--- a/net/sched/Kconfig
+++ b/net/sched/Kconfig
@@ -358,8 +358,7 @@ config NET_SCH_PIE
 	help
 	  Say Y here if you want to use the Proportional Integral controller
 	  Enhanced scheduler packet scheduling algorithm.
-	  For more information, please see
-	  http://tools.ietf.org/html/draft-pan-tsvwg-pie-00
+	  For more information, please see https://tools.ietf.org/html/rfc8033
 
 	  To compile this driver as a module, choose M here: the module
 	  will be called sch_pie.
diff --git a/net/sched/act_api.c b/net/sched/act_api.c
index aecf1bf233c8..5a87e271d35a 100644
--- a/net/sched/act_api.c
+++ b/net/sched/act_api.c
@@ -28,27 +28,10 @@
 #include <net/act_api.h>
 #include <net/netlink.h>
 
-static int tcf_action_goto_chain_init(struct tc_action *a, struct tcf_proto *tp)
-{
-	u32 chain_index = a->tcfa_action & TC_ACT_EXT_VAL_MASK;
-
-	if (!tp)
-		return -EINVAL;
-	a->goto_chain = tcf_chain_get_by_act(tp->chain->block, chain_index);
-	if (!a->goto_chain)
-		return -ENOMEM;
-	return 0;
-}
-
-static void tcf_action_goto_chain_fini(struct tc_action *a)
-{
-	tcf_chain_put_by_act(a->goto_chain);
-}
-
 static void tcf_action_goto_chain_exec(const struct tc_action *a,
 				       struct tcf_result *res)
 {
-	const struct tcf_chain *chain = a->goto_chain;
+	const struct tcf_chain *chain = rcu_dereference_bh(a->goto_chain);
 
 	res->goto_tp = rcu_dereference_bh(chain->filter_chain);
 }
@@ -71,6 +54,51 @@ static void tcf_set_action_cookie(struct tc_cookie __rcu **old_cookie,
 		call_rcu(&old->rcu, tcf_free_cookie_rcu);
 }
 
+int tcf_action_check_ctrlact(int action, struct tcf_proto *tp,
+			     struct tcf_chain **newchain,
+			     struct netlink_ext_ack *extack)
+{
+	int opcode = TC_ACT_EXT_OPCODE(action), ret = -EINVAL;
+	u32 chain_index;
+
+	if (!opcode)
+		ret = action > TC_ACT_VALUE_MAX ? -EINVAL : 0;
+	else if (opcode <= TC_ACT_EXT_OPCODE_MAX || action == TC_ACT_UNSPEC)
+		ret = 0;
+	if (ret) {
+		NL_SET_ERR_MSG(extack, "invalid control action");
+		goto end;
+	}
+
+	if (TC_ACT_EXT_CMP(action, TC_ACT_GOTO_CHAIN)) {
+		chain_index = action & TC_ACT_EXT_VAL_MASK;
+		if (!tp || !newchain) {
+			ret = -EINVAL;
+			NL_SET_ERR_MSG(extack,
+				       "can't goto NULL proto/chain");
+			goto end;
+		}
+		*newchain = tcf_chain_get_by_act(tp->chain->block, chain_index);
+		if (!*newchain) {
+			ret = -ENOMEM;
+			NL_SET_ERR_MSG(extack,
+				       "can't allocate goto_chain");
+		}
+	}
+end:
+	return ret;
+}
+EXPORT_SYMBOL(tcf_action_check_ctrlact);
+
+struct tcf_chain *tcf_action_set_ctrlact(struct tc_action *a, int action,
+					 struct tcf_chain *goto_chain)
+{
+	a->tcfa_action = action;
+	rcu_swap_protected(a->goto_chain, goto_chain, 1);
+	return goto_chain;
+}
+EXPORT_SYMBOL(tcf_action_set_ctrlact);
+
 /* XXX: For standalone actions, we don't need a RCU grace period either, because
  * actions are always connected to filters and filters are already destroyed in
  * RCU callbacks, so after a RCU grace period actions are already disconnected
@@ -78,13 +106,15 @@ static void tcf_set_action_cookie(struct tc_cookie __rcu **old_cookie,
  */
 static void free_tcf(struct tc_action *p)
 {
+	struct tcf_chain *chain = rcu_dereference_protected(p->goto_chain, 1);
+
 	free_percpu(p->cpu_bstats);
 	free_percpu(p->cpu_bstats_hw);
 	free_percpu(p->cpu_qstats);
 
 	tcf_set_action_cookie(&p->act_cookie, NULL);
-	if (p->goto_chain)
-		tcf_action_goto_chain_fini(p);
+	if (chain)
+		tcf_chain_put_by_act(chain);
 
 	kfree(p);
 }
@@ -654,6 +684,10 @@ repeat:
 					return TC_ACT_OK;
 			}
 		} else if (TC_ACT_EXT_CMP(ret, TC_ACT_GOTO_CHAIN)) {
+			if (unlikely(!rcu_access_pointer(a->goto_chain))) {
+				net_warn_ratelimited("can't go to NULL chain!\n");
+				return TC_ACT_SHOT;
+			}
 			tcf_action_goto_chain_exec(a, res);
 		}
 
@@ -800,15 +834,6 @@ static struct tc_cookie *nla_memdup_cookie(struct nlattr **tb)
 	return c;
 }
 
-static bool tcf_action_valid(int action)
-{
-	int opcode = TC_ACT_EXT_OPCODE(action);
-
-	if (!opcode)
-		return action <= TC_ACT_VALUE_MAX;
-	return opcode <= TC_ACT_EXT_OPCODE_MAX || action == TC_ACT_UNSPEC;
-}
-
 struct tc_action *tcf_action_init_1(struct net *net, struct tcf_proto *tp,
 				    struct nlattr *nla, struct nlattr *est,
 				    char *name, int ovr, int bind,
@@ -890,10 +915,10 @@ struct tc_action *tcf_action_init_1(struct net *net, struct tcf_proto *tp,
 	/* backward compatibility for policer */
 	if (name == NULL)
 		err = a_o->init(net, tb[TCA_ACT_OPTIONS], est, &a, ovr, bind,
-				rtnl_held, extack);
+				rtnl_held, tp, extack);
 	else
 		err = a_o->init(net, nla, est, &a, ovr, bind, rtnl_held,
-				extack);
+				tp, extack);
 	if (err < 0)
 		goto err_mod;
 
@@ -907,18 +932,10 @@ struct tc_action *tcf_action_init_1(struct net *net, struct tcf_proto *tp,
 	if (err != ACT_P_CREATED)
 		module_put(a_o->owner);
 
-	if (TC_ACT_EXT_CMP(a->tcfa_action, TC_ACT_GOTO_CHAIN)) {
-		err = tcf_action_goto_chain_init(a, tp);
-		if (err) {
-			tcf_action_destroy_1(a, bind);
-			NL_SET_ERR_MSG(extack, "Failed to init TC action chain");
-			return ERR_PTR(err);
-		}
-	}
-
-	if (!tcf_action_valid(a->tcfa_action)) {
+	if (TC_ACT_EXT_CMP(a->tcfa_action, TC_ACT_GOTO_CHAIN) &&
+	    !rcu_access_pointer(a->goto_chain)) {
 		tcf_action_destroy_1(a, bind);
-		NL_SET_ERR_MSG(extack, "Invalid control action value");
+		NL_SET_ERR_MSG(extack, "can't use goto chain with NULL chain");
 		return ERR_PTR(-EINVAL);
 	}
 
diff --git a/net/sched/act_bpf.c b/net/sched/act_bpf.c
index aa5c38d11a30..3841156aa09f 100644
--- a/net/sched/act_bpf.c
+++ b/net/sched/act_bpf.c
@@ -17,6 +17,7 @@
 
 #include <net/netlink.h>
 #include <net/pkt_sched.h>
+#include <net/pkt_cls.h>
 
 #include <linux/tc_act/tc_bpf.h>
 #include <net/tc_act/tc_bpf.h>
@@ -278,10 +279,11 @@ static void tcf_bpf_prog_fill_cfg(const struct tcf_bpf *prog,
 static int tcf_bpf_init(struct net *net, struct nlattr *nla,
 			struct nlattr *est, struct tc_action **act,
 			int replace, int bind, bool rtnl_held,
-			struct netlink_ext_ack *extack)
+			struct tcf_proto *tp, struct netlink_ext_ack *extack)
 {
 	struct tc_action_net *tn = net_generic(net, bpf_net_id);
 	struct nlattr *tb[TCA_ACT_BPF_MAX + 1];
+	struct tcf_chain *goto_ch = NULL;
 	struct tcf_bpf_cfg cfg, old;
 	struct tc_act_bpf *parm;
 	struct tcf_bpf *prog;
@@ -323,12 +325,16 @@ static int tcf_bpf_init(struct net *net, struct nlattr *nla,
 		return ret;
 	}
 
+	ret = tcf_action_check_ctrlact(parm->action, tp, &goto_ch, extack);
+	if (ret < 0)
+		goto release_idr;
+
 	is_bpf = tb[TCA_ACT_BPF_OPS_LEN] && tb[TCA_ACT_BPF_OPS];
 	is_ebpf = tb[TCA_ACT_BPF_FD];
 
 	if ((!is_bpf && !is_ebpf) || (is_bpf && is_ebpf)) {
 		ret = -EINVAL;
-		goto out;
+		goto put_chain;
 	}
 
 	memset(&cfg, 0, sizeof(cfg));
@@ -336,7 +342,7 @@ static int tcf_bpf_init(struct net *net, struct nlattr *nla,
 	ret = is_bpf ? tcf_bpf_init_from_ops(tb, &cfg) :
 		       tcf_bpf_init_from_efd(tb, &cfg);
 	if (ret < 0)
-		goto out;
+		goto put_chain;
 
 	prog = to_bpf(*act);
 
@@ -350,10 +356,13 @@ static int tcf_bpf_init(struct net *net, struct nlattr *nla,
 	if (cfg.bpf_num_ops)
 		prog->bpf_num_ops = cfg.bpf_num_ops;
 
-	prog->tcf_action = parm->action;
+	goto_ch = tcf_action_set_ctrlact(*act, parm->action, goto_ch);
 	rcu_assign_pointer(prog->filter, cfg.filter);
 	spin_unlock_bh(&prog->tcf_lock);
 
+	if (goto_ch)
+		tcf_chain_put_by_act(goto_ch);
+
 	if (res == ACT_P_CREATED) {
 		tcf_idr_insert(tn, *act);
 	} else {
@@ -363,9 +372,13 @@ static int tcf_bpf_init(struct net *net, struct nlattr *nla,
 	}
 
 	return res;
-out:
-	tcf_idr_release(*act, bind);
 
+put_chain:
+	if (goto_ch)
+		tcf_chain_put_by_act(goto_ch);
+
+release_idr:
+	tcf_idr_release(*act, bind);
 	return ret;
 }
 
diff --git a/net/sched/act_connmark.c b/net/sched/act_connmark.c
index 5d24993cccfe..32ae0cd6e31c 100644
--- a/net/sched/act_connmark.c
+++ b/net/sched/act_connmark.c
@@ -21,6 +21,7 @@
 #include <net/netlink.h>
 #include <net/pkt_sched.h>
 #include <net/act_api.h>
+#include <net/pkt_cls.h>
 #include <uapi/linux/tc_act/tc_connmark.h>
 #include <net/tc_act/tc_connmark.h>
 
@@ -97,13 +98,15 @@ static const struct nla_policy connmark_policy[TCA_CONNMARK_MAX + 1] = {
 static int tcf_connmark_init(struct net *net, struct nlattr *nla,
 			     struct nlattr *est, struct tc_action **a,
 			     int ovr, int bind, bool rtnl_held,
+			     struct tcf_proto *tp,
 			     struct netlink_ext_ack *extack)
 {
 	struct tc_action_net *tn = net_generic(net, connmark_net_id);
 	struct nlattr *tb[TCA_CONNMARK_MAX + 1];
+	struct tcf_chain *goto_ch = NULL;
 	struct tcf_connmark_info *ci;
 	struct tc_connmark *parm;
-	int ret = 0;
+	int ret = 0, err;
 
 	if (!nla)
 		return -EINVAL;
@@ -128,7 +131,11 @@ static int tcf_connmark_init(struct net *net, struct nlattr *nla,
 		}
 
 		ci = to_connmark(*a);
-		ci->tcf_action = parm->action;
+		err = tcf_action_check_ctrlact(parm->action, tp, &goto_ch,
+					       extack);
+		if (err < 0)
+			goto release_idr;
+		tcf_action_set_ctrlact(*a, parm->action, goto_ch);
 		ci->net = net;
 		ci->zone = parm->zone;
 
@@ -142,15 +149,24 @@ static int tcf_connmark_init(struct net *net, struct nlattr *nla,
 			tcf_idr_release(*a, bind);
 			return -EEXIST;
 		}
+		err = tcf_action_check_ctrlact(parm->action, tp, &goto_ch,
+					       extack);
+		if (err < 0)
+			goto release_idr;
 		/* replacing action and zone */
 		spin_lock_bh(&ci->tcf_lock);
-		ci->tcf_action = parm->action;
+		goto_ch = tcf_action_set_ctrlact(*a, parm->action, goto_ch);
 		ci->zone = parm->zone;
 		spin_unlock_bh(&ci->tcf_lock);
+		if (goto_ch)
+			tcf_chain_put_by_act(goto_ch);
 		ret = 0;
 	}
 
 	return ret;
+release_idr:
+	tcf_idr_release(*a, bind);
+	return err;
 }
 
 static inline int tcf_connmark_dump(struct sk_buff *skb, struct tc_action *a,
diff --git a/net/sched/act_csum.c b/net/sched/act_csum.c
index c79aca29505e..0c77e7bdf6d5 100644
--- a/net/sched/act_csum.c
+++ b/net/sched/act_csum.c
@@ -33,6 +33,7 @@
 #include <net/sctp/checksum.h>
 
 #include <net/act_api.h>
+#include <net/pkt_cls.h>
 
 #include <linux/tc_act/tc_csum.h>
 #include <net/tc_act/tc_csum.h>
@@ -46,12 +47,13 @@ static struct tc_action_ops act_csum_ops;
 
 static int tcf_csum_init(struct net *net, struct nlattr *nla,
 			 struct nlattr *est, struct tc_action **a, int ovr,
-			 int bind, bool rtnl_held,
+			 int bind, bool rtnl_held, struct tcf_proto *tp,
 			 struct netlink_ext_ack *extack)
 {
 	struct tc_action_net *tn = net_generic(net, csum_net_id);
 	struct tcf_csum_params *params_new;
 	struct nlattr *tb[TCA_CSUM_MAX + 1];
+	struct tcf_chain *goto_ch = NULL;
 	struct tc_csum *parm;
 	struct tcf_csum *p;
 	int ret = 0, err;
@@ -87,21 +89,27 @@ static int tcf_csum_init(struct net *net, struct nlattr *nla,
 		return err;
 	}
 
+	err = tcf_action_check_ctrlact(parm->action, tp, &goto_ch, extack);
+	if (err < 0)
+		goto release_idr;
+
 	p = to_tcf_csum(*a);
 
 	params_new = kzalloc(sizeof(*params_new), GFP_KERNEL);
 	if (unlikely(!params_new)) {
-		tcf_idr_release(*a, bind);
-		return -ENOMEM;
+		err = -ENOMEM;
+		goto put_chain;
 	}
 	params_new->update_flags = parm->update_flags;
 
 	spin_lock_bh(&p->tcf_lock);
-	p->tcf_action = parm->action;
+	goto_ch = tcf_action_set_ctrlact(*a, parm->action, goto_ch);
 	rcu_swap_protected(p->params, params_new,
 			   lockdep_is_held(&p->tcf_lock));
 	spin_unlock_bh(&p->tcf_lock);
 
+	if (goto_ch)
+		tcf_chain_put_by_act(goto_ch);
 	if (params_new)
 		kfree_rcu(params_new, rcu);
 
@@ -109,6 +117,12 @@ static int tcf_csum_init(struct net *net, struct nlattr *nla,
 		tcf_idr_insert(tn, *a);
 
 	return ret;
+put_chain:
+	if (goto_ch)
+		tcf_chain_put_by_act(goto_ch);
+release_idr:
+	tcf_idr_release(*a, bind);
+	return err;
 }
 
 /**
diff --git a/net/sched/act_gact.c b/net/sched/act_gact.c
index 93da0004e9f4..e540e31069d7 100644
--- a/net/sched/act_gact.c
+++ b/net/sched/act_gact.c
@@ -20,6 +20,7 @@
 #include <linux/init.h>
 #include <net/netlink.h>
 #include <net/pkt_sched.h>
+#include <net/pkt_cls.h>
 #include <linux/tc_act/tc_gact.h>
 #include <net/tc_act/tc_gact.h>
 
@@ -57,10 +58,11 @@ static const struct nla_policy gact_policy[TCA_GACT_MAX + 1] = {
 static int tcf_gact_init(struct net *net, struct nlattr *nla,
 			 struct nlattr *est, struct tc_action **a,
 			 int ovr, int bind, bool rtnl_held,
-			 struct netlink_ext_ack *extack)
+			 struct tcf_proto *tp, struct netlink_ext_ack *extack)
 {
 	struct tc_action_net *tn = net_generic(net, gact_net_id);
 	struct nlattr *tb[TCA_GACT_MAX + 1];
+	struct tcf_chain *goto_ch = NULL;
 	struct tc_gact *parm;
 	struct tcf_gact *gact;
 	int ret = 0;
@@ -116,10 +118,13 @@ static int tcf_gact_init(struct net *net, struct nlattr *nla,
 		return err;
 	}
 
+	err = tcf_action_check_ctrlact(parm->action, tp, &goto_ch, extack);
+	if (err < 0)
+		goto release_idr;
 	gact = to_gact(*a);
 
 	spin_lock_bh(&gact->tcf_lock);
-	gact->tcf_action = parm->action;
+	goto_ch = tcf_action_set_ctrlact(*a, parm->action, goto_ch);
 #ifdef CONFIG_GACT_PROB
 	if (p_parm) {
 		gact->tcfg_paction = p_parm->paction;
@@ -133,9 +138,15 @@ static int tcf_gact_init(struct net *net, struct nlattr *nla,
 #endif
 	spin_unlock_bh(&gact->tcf_lock);
 
+	if (goto_ch)
+		tcf_chain_put_by_act(goto_ch);
+
 	if (ret == ACT_P_CREATED)
 		tcf_idr_insert(tn, *a);
 	return ret;
+release_idr:
+	tcf_idr_release(*a, bind);
+	return err;
 }
 
 static int tcf_gact_act(struct sk_buff *skb, const struct tc_action *a,
diff --git a/net/sched/act_ife.c b/net/sched/act_ife.c
index 9b1f2b3990ee..31c6ffb6abe7 100644
--- a/net/sched/act_ife.c
+++ b/net/sched/act_ife.c
@@ -29,6 +29,7 @@
 #include <net/net_namespace.h>
 #include <net/netlink.h>
 #include <net/pkt_sched.h>
+#include <net/pkt_cls.h>
 #include <uapi/linux/tc_act/tc_ife.h>
 #include <net/tc_act/tc_ife.h>
 #include <linux/etherdevice.h>
@@ -469,11 +470,12 @@ static int populate_metalist(struct tcf_ife_info *ife, struct nlattr **tb,
 static int tcf_ife_init(struct net *net, struct nlattr *nla,
 			struct nlattr *est, struct tc_action **a,
 			int ovr, int bind, bool rtnl_held,
-			struct netlink_ext_ack *extack)
+			struct tcf_proto *tp, struct netlink_ext_ack *extack)
 {
 	struct tc_action_net *tn = net_generic(net, ife_net_id);
 	struct nlattr *tb[TCA_IFE_MAX + 1];
 	struct nlattr *tb2[IFE_META_MAX + 1];
+	struct tcf_chain *goto_ch = NULL;
 	struct tcf_ife_params *p;
 	struct tcf_ife_info *ife;
 	u16 ife_type = ETH_P_IFE;
@@ -531,6 +533,10 @@ static int tcf_ife_init(struct net *net, struct nlattr *nla,
 	}
 
 	ife = to_ife(*a);
+	err = tcf_action_check_ctrlact(parm->action, tp, &goto_ch, extack);
+	if (err < 0)
+		goto release_idr;
+
 	p->flags = parm->flags;
 
 	if (parm->flags & IFE_ENCODE) {
@@ -563,13 +569,8 @@ static int tcf_ife_init(struct net *net, struct nlattr *nla,
 	if (tb[TCA_IFE_METALST]) {
 		err = nla_parse_nested(tb2, IFE_META_MAX, tb[TCA_IFE_METALST],
 				       NULL, NULL);
-		if (err) {
-metadata_parse_err:
-			tcf_idr_release(*a, bind);
-			kfree(p);
-			return err;
-		}
-
+		if (err)
+			goto metadata_parse_err;
 		err = populate_metalist(ife, tb2, exists, rtnl_held);
 		if (err)
 			goto metadata_parse_err;
@@ -581,21 +582,20 @@ metadata_parse_err:
 		 * going to bail out
 		 */
 		err = use_all_metadata(ife, exists);
-		if (err) {
-			tcf_idr_release(*a, bind);
-			kfree(p);
-			return err;
-		}
+		if (err)
+			goto metadata_parse_err;
 	}
 
 	if (exists)
 		spin_lock_bh(&ife->tcf_lock);
-	ife->tcf_action = parm->action;
 	/* protected by tcf_lock when modifying existing action */
+	goto_ch = tcf_action_set_ctrlact(*a, parm->action, goto_ch);
 	rcu_swap_protected(ife->params, p, 1);
 
 	if (exists)
 		spin_unlock_bh(&ife->tcf_lock);
+	if (goto_ch)
+		tcf_chain_put_by_act(goto_ch);
 	if (p)
 		kfree_rcu(p, rcu);
 
@@ -603,6 +603,13 @@ metadata_parse_err:
 		tcf_idr_insert(tn, *a);
 
 	return ret;
+metadata_parse_err:
+	if (goto_ch)
+		tcf_chain_put_by_act(goto_ch);
+release_idr:
+	kfree(p);
+	tcf_idr_release(*a, bind);
+	return err;
 }
 
 static int tcf_ife_dump(struct sk_buff *skb, struct tc_action *a, int bind,
diff --git a/net/sched/act_ipt.c b/net/sched/act_ipt.c
index 98f5b6ea77b4..04a0b5c61194 100644
--- a/net/sched/act_ipt.c
+++ b/net/sched/act_ipt.c
@@ -97,7 +97,8 @@ static const struct nla_policy ipt_policy[TCA_IPT_MAX + 1] = {
 
 static int __tcf_ipt_init(struct net *net, unsigned int id, struct nlattr *nla,
 			  struct nlattr *est, struct tc_action **a,
-			  const struct tc_action_ops *ops, int ovr, int bind)
+			  const struct tc_action_ops *ops, int ovr, int bind,
+			  struct tcf_proto *tp)
 {
 	struct tc_action_net *tn = net_generic(net, id);
 	struct nlattr *tb[TCA_IPT_MAX + 1];
@@ -205,20 +206,20 @@ err1:
 
 static int tcf_ipt_init(struct net *net, struct nlattr *nla,
 			struct nlattr *est, struct tc_action **a, int ovr,
-			int bind, bool rtnl_held,
+			int bind, bool rtnl_held, struct tcf_proto *tp,
 			struct netlink_ext_ack *extack)
 {
 	return __tcf_ipt_init(net, ipt_net_id, nla, est, a, &act_ipt_ops, ovr,
-			      bind);
+			      bind, tp);
 }
 
 static int tcf_xt_init(struct net *net, struct nlattr *nla,
 		       struct nlattr *est, struct tc_action **a, int ovr,
-		       int bind, bool unlocked,
+		       int bind, bool unlocked, struct tcf_proto *tp,
 		       struct netlink_ext_ack *extack)
 {
 	return __tcf_ipt_init(net, xt_net_id, nla, est, a, &act_xt_ops, ovr,
-			      bind);
+			      bind, tp);
 }
 
 static int tcf_ipt_act(struct sk_buff *skb, const struct tc_action *a,
diff --git a/net/sched/act_mirred.c b/net/sched/act_mirred.c
index 6692fd054617..17cc6bd4c57c 100644
--- a/net/sched/act_mirred.c
+++ b/net/sched/act_mirred.c
@@ -94,10 +94,12 @@ static struct tc_action_ops act_mirred_ops;
 static int tcf_mirred_init(struct net *net, struct nlattr *nla,
 			   struct nlattr *est, struct tc_action **a,
 			   int ovr, int bind, bool rtnl_held,
+			   struct tcf_proto *tp,
 			   struct netlink_ext_ack *extack)
 {
 	struct tc_action_net *tn = net_generic(net, mirred_net_id);
 	struct nlattr *tb[TCA_MIRRED_MAX + 1];
+	struct tcf_chain *goto_ch = NULL;
 	bool mac_header_xmit = false;
 	struct tc_mirred *parm;
 	struct tcf_mirred *m;
@@ -157,18 +159,23 @@ static int tcf_mirred_init(struct net *net, struct nlattr *nla,
 		tcf_idr_release(*a, bind);
 		return -EEXIST;
 	}
+
 	m = to_mirred(*a);
+	if (ret == ACT_P_CREATED)
+		INIT_LIST_HEAD(&m->tcfm_list);
+
+	err = tcf_action_check_ctrlact(parm->action, tp, &goto_ch, extack);
+	if (err < 0)
+		goto release_idr;
 
 	spin_lock_bh(&m->tcf_lock);
-	m->tcf_action = parm->action;
-	m->tcfm_eaction = parm->eaction;
 
 	if (parm->ifindex) {
 		dev = dev_get_by_index(net, parm->ifindex);
 		if (!dev) {
 			spin_unlock_bh(&m->tcf_lock);
-			tcf_idr_release(*a, bind);
-			return -ENODEV;
+			err = -ENODEV;
+			goto put_chain;
 		}
 		mac_header_xmit = dev_is_mac_header_xmit(dev);
 		rcu_swap_protected(m->tcfm_dev, dev,
@@ -177,7 +184,11 @@ static int tcf_mirred_init(struct net *net, struct nlattr *nla,
 			dev_put(dev);
 		m->tcfm_mac_header_xmit = mac_header_xmit;
 	}
+	goto_ch = tcf_action_set_ctrlact(*a, parm->action, goto_ch);
+	m->tcfm_eaction = parm->eaction;
 	spin_unlock_bh(&m->tcf_lock);
+	if (goto_ch)
+		tcf_chain_put_by_act(goto_ch);
 
 	if (ret == ACT_P_CREATED) {
 		spin_lock(&mirred_list_lock);
@@ -188,6 +199,12 @@ static int tcf_mirred_init(struct net *net, struct nlattr *nla,
 	}
 
 	return ret;
+put_chain:
+	if (goto_ch)
+		tcf_chain_put_by_act(goto_ch);
+release_idr:
+	tcf_idr_release(*a, bind);
+	return err;
 }
 
 static int tcf_mirred_act(struct sk_buff *skb, const struct tc_action *a,
diff --git a/net/sched/act_nat.c b/net/sched/act_nat.c
index 543eab9193f1..e91bb8eb81ec 100644
--- a/net/sched/act_nat.c
+++ b/net/sched/act_nat.c
@@ -21,6 +21,7 @@
 #include <linux/string.h>
 #include <linux/tc_act/tc_nat.h>
 #include <net/act_api.h>
+#include <net/pkt_cls.h>
 #include <net/icmp.h>
 #include <net/ip.h>
 #include <net/netlink.h>
@@ -38,10 +39,12 @@ static const struct nla_policy nat_policy[TCA_NAT_MAX + 1] = {
 
 static int tcf_nat_init(struct net *net, struct nlattr *nla, struct nlattr *est,
 			struct tc_action **a, int ovr, int bind,
-			bool rtnl_held, struct netlink_ext_ack *extack)
+			bool rtnl_held,	struct tcf_proto *tp,
+			struct netlink_ext_ack *extack)
 {
 	struct tc_action_net *tn = net_generic(net, nat_net_id);
 	struct nlattr *tb[TCA_NAT_MAX + 1];
+	struct tcf_chain *goto_ch = NULL;
 	struct tc_nat *parm;
 	int ret = 0, err;
 	struct tcf_nat *p;
@@ -76,6 +79,9 @@ static int tcf_nat_init(struct net *net, struct nlattr *nla, struct nlattr *est,
 	} else {
 		return err;
 	}
+	err = tcf_action_check_ctrlact(parm->action, tp, &goto_ch, extack);
+	if (err < 0)
+		goto release_idr;
 	p = to_tcf_nat(*a);
 
 	spin_lock_bh(&p->tcf_lock);
@@ -84,13 +90,18 @@ static int tcf_nat_init(struct net *net, struct nlattr *nla, struct nlattr *est,
 	p->mask = parm->mask;
 	p->flags = parm->flags;
 
-	p->tcf_action = parm->action;
+	goto_ch = tcf_action_set_ctrlact(*a, parm->action, goto_ch);
 	spin_unlock_bh(&p->tcf_lock);
+	if (goto_ch)
+		tcf_chain_put_by_act(goto_ch);
 
 	if (ret == ACT_P_CREATED)
 		tcf_idr_insert(tn, *a);
 
 	return ret;
+release_idr:
+	tcf_idr_release(*a, bind);
+	return err;
 }
 
 static int tcf_nat_act(struct sk_buff *skb, const struct tc_action *a,
diff --git a/net/sched/act_pedit.c b/net/sched/act_pedit.c
index a80373878df7..287793abfaf9 100644
--- a/net/sched/act_pedit.c
+++ b/net/sched/act_pedit.c
@@ -23,6 +23,7 @@
 #include <linux/tc_act/tc_pedit.h>
 #include <net/tc_act/tc_pedit.h>
 #include <uapi/linux/tc_act/tc_pedit.h>
+#include <net/pkt_cls.h>
 
 static unsigned int pedit_net_id;
 static struct tc_action_ops act_pedit_ops;
@@ -138,10 +139,11 @@ nla_failure:
 static int tcf_pedit_init(struct net *net, struct nlattr *nla,
 			  struct nlattr *est, struct tc_action **a,
 			  int ovr, int bind, bool rtnl_held,
-			  struct netlink_ext_ack *extack)
+			  struct tcf_proto *tp, struct netlink_ext_ack *extack)
 {
 	struct tc_action_net *tn = net_generic(net, pedit_net_id);
 	struct nlattr *tb[TCA_PEDIT_MAX + 1];
+	struct tcf_chain *goto_ch = NULL;
 	struct tc_pedit_key *keys = NULL;
 	struct tcf_pedit_key_ex *keys_ex;
 	struct tc_pedit *parm;
@@ -205,6 +207,11 @@ static int tcf_pedit_init(struct net *net, struct nlattr *nla,
 		goto out_free;
 	}
 
+	err = tcf_action_check_ctrlact(parm->action, tp, &goto_ch, extack);
+	if (err < 0) {
+		ret = err;
+		goto out_release;
+	}
 	p = to_pedit(*a);
 	spin_lock_bh(&p->tcf_lock);
 
@@ -214,7 +221,7 @@ static int tcf_pedit_init(struct net *net, struct nlattr *nla,
 		if (!keys) {
 			spin_unlock_bh(&p->tcf_lock);
 			ret = -ENOMEM;
-			goto out_release;
+			goto put_chain;
 		}
 		kfree(p->tcfp_keys);
 		p->tcfp_keys = keys;
@@ -223,16 +230,21 @@ static int tcf_pedit_init(struct net *net, struct nlattr *nla,
 	memcpy(p->tcfp_keys, parm->keys, ksize);
 
 	p->tcfp_flags = parm->flags;
-	p->tcf_action = parm->action;
+	goto_ch = tcf_action_set_ctrlact(*a, parm->action, goto_ch);
 
 	kfree(p->tcfp_keys_ex);
 	p->tcfp_keys_ex = keys_ex;
 
 	spin_unlock_bh(&p->tcf_lock);
+	if (goto_ch)
+		tcf_chain_put_by_act(goto_ch);
 	if (ret == ACT_P_CREATED)
 		tcf_idr_insert(tn, *a);
 	return ret;
 
+put_chain:
+	if (goto_ch)
+		tcf_chain_put_by_act(goto_ch);
 out_release:
 	tcf_idr_release(*a, bind);
 out_free:
diff --git a/net/sched/act_police.c b/net/sched/act_police.c
index 8271a6263824..2b8581f6ab51 100644
--- a/net/sched/act_police.c
+++ b/net/sched/act_police.c
@@ -21,6 +21,7 @@
 #include <linux/slab.h>
 #include <net/act_api.h>
 #include <net/netlink.h>
+#include <net/pkt_cls.h>
 
 struct tcf_police_params {
 	int			tcfp_result;
@@ -83,10 +84,12 @@ static const struct nla_policy police_policy[TCA_POLICE_MAX + 1] = {
 static int tcf_police_init(struct net *net, struct nlattr *nla,
 			       struct nlattr *est, struct tc_action **a,
 			       int ovr, int bind, bool rtnl_held,
+			       struct tcf_proto *tp,
 			       struct netlink_ext_ack *extack)
 {
 	int ret = 0, tcfp_result = TC_ACT_OK, err, size;
 	struct nlattr *tb[TCA_POLICE_MAX + 1];
+	struct tcf_chain *goto_ch = NULL;
 	struct tc_police *parm;
 	struct tcf_police *police;
 	struct qdisc_rate_table *R_tab = NULL, *P_tab = NULL;
@@ -128,6 +131,9 @@ static int tcf_police_init(struct net *net, struct nlattr *nla,
 		tcf_idr_release(*a, bind);
 		return -EEXIST;
 	}
+	err = tcf_action_check_ctrlact(parm->action, tp, &goto_ch, extack);
+	if (err < 0)
+		goto release_idr;
 
 	police = to_police(*a);
 	if (parm->rate.rate) {
@@ -213,12 +219,14 @@ static int tcf_police_init(struct net *net, struct nlattr *nla,
 	if (new->peak_present)
 		police->tcfp_ptoks = new->tcfp_mtu_ptoks;
 	spin_unlock_bh(&police->tcfp_lock);
-	police->tcf_action = parm->action;
+	goto_ch = tcf_action_set_ctrlact(*a, parm->action, goto_ch);
 	rcu_swap_protected(police->params,
 			   new,
 			   lockdep_is_held(&police->tcf_lock));
 	spin_unlock_bh(&police->tcf_lock);
 
+	if (goto_ch)
+		tcf_chain_put_by_act(goto_ch);
 	if (new)
 		kfree_rcu(new, rcu);
 
@@ -229,6 +237,9 @@ static int tcf_police_init(struct net *net, struct nlattr *nla,
 failure:
 	qdisc_put_rtab(P_tab);
 	qdisc_put_rtab(R_tab);
+	if (goto_ch)
+		tcf_chain_put_by_act(goto_ch);
+release_idr:
 	tcf_idr_release(*a, bind);
 	return err;
 }
diff --git a/net/sched/act_sample.c b/net/sched/act_sample.c
index 203e399e5c85..0f82d50ea232 100644
--- a/net/sched/act_sample.c
+++ b/net/sched/act_sample.c
@@ -22,6 +22,7 @@
 #include <linux/tc_act/tc_sample.h>
 #include <net/tc_act/tc_sample.h>
 #include <net/psample.h>
+#include <net/pkt_cls.h>
 
 #include <linux/if_arp.h>
 
@@ -37,14 +38,15 @@ static const struct nla_policy sample_policy[TCA_SAMPLE_MAX + 1] = {
 
 static int tcf_sample_init(struct net *net, struct nlattr *nla,
 			   struct nlattr *est, struct tc_action **a, int ovr,
-			   int bind, bool rtnl_held,
+			   int bind, bool rtnl_held, struct tcf_proto *tp,
 			   struct netlink_ext_ack *extack)
 {
 	struct tc_action_net *tn = net_generic(net, sample_net_id);
 	struct nlattr *tb[TCA_SAMPLE_MAX + 1];
 	struct psample_group *psample_group;
+	struct tcf_chain *goto_ch = NULL;
+	u32 psample_group_num, rate;
 	struct tc_sample *parm;
-	u32 psample_group_num;
 	struct tcf_sample *s;
 	bool exists = false;
 	int ret, err;
@@ -79,19 +81,28 @@ static int tcf_sample_init(struct net *net, struct nlattr *nla,
 		tcf_idr_release(*a, bind);
 		return -EEXIST;
 	}
+	err = tcf_action_check_ctrlact(parm->action, tp, &goto_ch, extack);
+	if (err < 0)
+		goto release_idr;
 
+	rate = nla_get_u32(tb[TCA_SAMPLE_RATE]);
+	if (!rate) {
+		NL_SET_ERR_MSG(extack, "invalid sample rate");
+		err = -EINVAL;
+		goto put_chain;
+	}
 	psample_group_num = nla_get_u32(tb[TCA_SAMPLE_PSAMPLE_GROUP]);
 	psample_group = psample_group_get(net, psample_group_num);
 	if (!psample_group) {
-		tcf_idr_release(*a, bind);
-		return -ENOMEM;
+		err = -ENOMEM;
+		goto put_chain;
 	}
 
 	s = to_sample(*a);
 
 	spin_lock_bh(&s->tcf_lock);
-	s->tcf_action = parm->action;
-	s->rate = nla_get_u32(tb[TCA_SAMPLE_RATE]);
+	goto_ch = tcf_action_set_ctrlact(*a, parm->action, goto_ch);
+	s->rate = rate;
 	s->psample_group_num = psample_group_num;
 	RCU_INIT_POINTER(s->psample_group, psample_group);
 
@@ -100,10 +111,18 @@ static int tcf_sample_init(struct net *net, struct nlattr *nla,
 		s->trunc_size = nla_get_u32(tb[TCA_SAMPLE_TRUNC_SIZE]);
 	}
 	spin_unlock_bh(&s->tcf_lock);
+	if (goto_ch)
+		tcf_chain_put_by_act(goto_ch);
 
 	if (ret == ACT_P_CREATED)
 		tcf_idr_insert(tn, *a);
 	return ret;
+put_chain:
+	if (goto_ch)
+		tcf_chain_put_by_act(goto_ch);
+release_idr:
+	tcf_idr_release(*a, bind);
+	return err;
 }
 
 static void tcf_sample_cleanup(struct tc_action *a)
diff --git a/net/sched/act_simple.c b/net/sched/act_simple.c
index d54cb608dbaf..23c8ca5615e5 100644
--- a/net/sched/act_simple.c
+++ b/net/sched/act_simple.c
@@ -18,6 +18,7 @@
 #include <linux/rtnetlink.h>
 #include <net/netlink.h>
 #include <net/pkt_sched.h>
+#include <net/pkt_cls.h>
 
 #include <linux/tc_act/tc_defact.h>
 #include <net/tc_act/tc_defact.h>
@@ -60,14 +61,26 @@ static int alloc_defdata(struct tcf_defact *d, const struct nlattr *defdata)
 	return 0;
 }
 
-static void reset_policy(struct tcf_defact *d, const struct nlattr *defdata,
-			 struct tc_defact *p)
+static int reset_policy(struct tc_action *a, const struct nlattr *defdata,
+			struct tc_defact *p, struct tcf_proto *tp,
+			struct netlink_ext_ack *extack)
 {
+	struct tcf_chain *goto_ch = NULL;
+	struct tcf_defact *d;
+	int err;
+
+	err = tcf_action_check_ctrlact(p->action, tp, &goto_ch, extack);
+	if (err < 0)
+		return err;
+	d = to_defact(a);
 	spin_lock_bh(&d->tcf_lock);
-	d->tcf_action = p->action;
+	goto_ch = tcf_action_set_ctrlact(a, p->action, goto_ch);
 	memset(d->tcfd_defdata, 0, SIMP_MAX_DATA);
 	nla_strlcpy(d->tcfd_defdata, defdata, SIMP_MAX_DATA);
 	spin_unlock_bh(&d->tcf_lock);
+	if (goto_ch)
+		tcf_chain_put_by_act(goto_ch);
+	return 0;
 }
 
 static const struct nla_policy simple_policy[TCA_DEF_MAX + 1] = {
@@ -78,10 +91,11 @@ static const struct nla_policy simple_policy[TCA_DEF_MAX + 1] = {
 static int tcf_simp_init(struct net *net, struct nlattr *nla,
 			 struct nlattr *est, struct tc_action **a,
 			 int ovr, int bind, bool rtnl_held,
-			 struct netlink_ext_ack *extack)
+			 struct tcf_proto *tp, struct netlink_ext_ack *extack)
 {
 	struct tc_action_net *tn = net_generic(net, simp_net_id);
 	struct nlattr *tb[TCA_DEF_MAX + 1];
+	struct tcf_chain *goto_ch = NULL;
 	struct tc_defact *parm;
 	struct tcf_defact *d;
 	bool exists = false;
@@ -122,27 +136,37 @@ static int tcf_simp_init(struct net *net, struct nlattr *nla,
 		}
 
 		d = to_defact(*a);
-		ret = alloc_defdata(d, tb[TCA_DEF_DATA]);
-		if (ret < 0) {
-			tcf_idr_release(*a, bind);
-			return ret;
-		}
-		d->tcf_action = parm->action;
+		err = tcf_action_check_ctrlact(parm->action, tp, &goto_ch,
+					       extack);
+		if (err < 0)
+			goto release_idr;
+
+		err = alloc_defdata(d, tb[TCA_DEF_DATA]);
+		if (err < 0)
+			goto put_chain;
+
+		tcf_action_set_ctrlact(*a, parm->action, goto_ch);
 		ret = ACT_P_CREATED;
 	} else {
-		d = to_defact(*a);
-
 		if (!ovr) {
-			tcf_idr_release(*a, bind);
-			return -EEXIST;
+			err = -EEXIST;
+			goto release_idr;
 		}
 
-		reset_policy(d, tb[TCA_DEF_DATA], parm);
+		err = reset_policy(*a, tb[TCA_DEF_DATA], parm, tp, extack);
+		if (err)
+			goto release_idr;
 	}
 
 	if (ret == ACT_P_CREATED)
 		tcf_idr_insert(tn, *a);
 	return ret;
+put_chain:
+	if (goto_ch)
+		tcf_chain_put_by_act(goto_ch);
+release_idr:
+	tcf_idr_release(*a, bind);
+	return err;
 }
 
 static int tcf_simp_dump(struct sk_buff *skb, struct tc_action *a,
diff --git a/net/sched/act_skbedit.c b/net/sched/act_skbedit.c
index 65879500b688..7e1d261a31d2 100644
--- a/net/sched/act_skbedit.c
+++ b/net/sched/act_skbedit.c
@@ -26,6 +26,7 @@
 #include <net/ip.h>
 #include <net/ipv6.h>
 #include <net/dsfield.h>
+#include <net/pkt_cls.h>
 
 #include <linux/tc_act/tc_skbedit.h>
 #include <net/tc_act/tc_skbedit.h>
@@ -96,11 +97,13 @@ static const struct nla_policy skbedit_policy[TCA_SKBEDIT_MAX + 1] = {
 static int tcf_skbedit_init(struct net *net, struct nlattr *nla,
 			    struct nlattr *est, struct tc_action **a,
 			    int ovr, int bind, bool rtnl_held,
+			    struct tcf_proto *tp,
 			    struct netlink_ext_ack *extack)
 {
 	struct tc_action_net *tn = net_generic(net, skbedit_net_id);
 	struct tcf_skbedit_params *params_new;
 	struct nlattr *tb[TCA_SKBEDIT_MAX + 1];
+	struct tcf_chain *goto_ch = NULL;
 	struct tc_skbedit *parm;
 	struct tcf_skbedit *d;
 	u32 flags = 0, *priority = NULL, *mark = NULL, *mask = NULL;
@@ -186,11 +189,14 @@ static int tcf_skbedit_init(struct net *net, struct nlattr *nla,
 			return -EEXIST;
 		}
 	}
+	err = tcf_action_check_ctrlact(parm->action, tp, &goto_ch, extack);
+	if (err < 0)
+		goto release_idr;
 
 	params_new = kzalloc(sizeof(*params_new), GFP_KERNEL);
 	if (unlikely(!params_new)) {
-		tcf_idr_release(*a, bind);
-		return -ENOMEM;
+		err = -ENOMEM;
+		goto put_chain;
 	}
 
 	params_new->flags = flags;
@@ -208,16 +214,24 @@ static int tcf_skbedit_init(struct net *net, struct nlattr *nla,
 		params_new->mask = *mask;
 
 	spin_lock_bh(&d->tcf_lock);
-	d->tcf_action = parm->action;
+	goto_ch = tcf_action_set_ctrlact(*a, parm->action, goto_ch);
 	rcu_swap_protected(d->params, params_new,
 			   lockdep_is_held(&d->tcf_lock));
 	spin_unlock_bh(&d->tcf_lock);
 	if (params_new)
 		kfree_rcu(params_new, rcu);
+	if (goto_ch)
+		tcf_chain_put_by_act(goto_ch);
 
 	if (ret == ACT_P_CREATED)
 		tcf_idr_insert(tn, *a);
 	return ret;
+put_chain:
+	if (goto_ch)
+		tcf_chain_put_by_act(goto_ch);
+release_idr:
+	tcf_idr_release(*a, bind);
+	return err;
 }
 
 static int tcf_skbedit_dump(struct sk_buff *skb, struct tc_action *a,
diff --git a/net/sched/act_skbmod.c b/net/sched/act_skbmod.c
index 7bac1d78e7a3..1d4c324d0a42 100644
--- a/net/sched/act_skbmod.c
+++ b/net/sched/act_skbmod.c
@@ -16,6 +16,7 @@
 #include <linux/rtnetlink.h>
 #include <net/netlink.h>
 #include <net/pkt_sched.h>
+#include <net/pkt_cls.h>
 
 #include <linux/tc_act/tc_skbmod.h>
 #include <net/tc_act/tc_skbmod.h>
@@ -82,11 +83,13 @@ static const struct nla_policy skbmod_policy[TCA_SKBMOD_MAX + 1] = {
 static int tcf_skbmod_init(struct net *net, struct nlattr *nla,
 			   struct nlattr *est, struct tc_action **a,
 			   int ovr, int bind, bool rtnl_held,
+			   struct tcf_proto *tp,
 			   struct netlink_ext_ack *extack)
 {
 	struct tc_action_net *tn = net_generic(net, skbmod_net_id);
 	struct nlattr *tb[TCA_SKBMOD_MAX + 1];
 	struct tcf_skbmod_params *p, *p_old;
+	struct tcf_chain *goto_ch = NULL;
 	struct tc_skbmod *parm;
 	struct tcf_skbmod *d;
 	bool exists = false;
@@ -153,21 +156,24 @@ static int tcf_skbmod_init(struct net *net, struct nlattr *nla,
 		tcf_idr_release(*a, bind);
 		return -EEXIST;
 	}
+	err = tcf_action_check_ctrlact(parm->action, tp, &goto_ch, extack);
+	if (err < 0)
+		goto release_idr;
 
 	d = to_skbmod(*a);
 
 	p = kzalloc(sizeof(struct tcf_skbmod_params), GFP_KERNEL);
 	if (unlikely(!p)) {
-		tcf_idr_release(*a, bind);
-		return -ENOMEM;
+		err = -ENOMEM;
+		goto put_chain;
 	}
 
 	p->flags = lflags;
-	d->tcf_action = parm->action;
 
 	if (ovr)
 		spin_lock_bh(&d->tcf_lock);
 	/* Protected by tcf_lock if overwriting existing action. */
+	goto_ch = tcf_action_set_ctrlact(*a, parm->action, goto_ch);
 	p_old = rcu_dereference_protected(d->skbmod_p, 1);
 
 	if (lflags & SKBMOD_F_DMAC)
@@ -183,10 +189,18 @@ static int tcf_skbmod_init(struct net *net, struct nlattr *nla,
 
 	if (p_old)
 		kfree_rcu(p_old, rcu);
+	if (goto_ch)
+		tcf_chain_put_by_act(goto_ch);
 
 	if (ret == ACT_P_CREATED)
 		tcf_idr_insert(tn, *a);
 	return ret;
+put_chain:
+	if (goto_ch)
+		tcf_chain_put_by_act(goto_ch);
+release_idr:
+	tcf_idr_release(*a, bind);
+	return err;
 }
 
 static void tcf_skbmod_cleanup(struct tc_action *a)
diff --git a/net/sched/act_tunnel_key.c b/net/sched/act_tunnel_key.c
index 7c6591b991d5..d5aaf90a3971 100644
--- a/net/sched/act_tunnel_key.c
+++ b/net/sched/act_tunnel_key.c
@@ -17,6 +17,7 @@
 #include <net/netlink.h>
 #include <net/pkt_sched.h>
 #include <net/dst.h>
+#include <net/pkt_cls.h>
 
 #include <linux/tc_act/tc_tunnel_key.h>
 #include <net/tc_act/tc_tunnel_key.h>
@@ -210,12 +211,14 @@ static void tunnel_key_release_params(struct tcf_tunnel_key_params *p)
 static int tunnel_key_init(struct net *net, struct nlattr *nla,
 			   struct nlattr *est, struct tc_action **a,
 			   int ovr, int bind, bool rtnl_held,
+			   struct tcf_proto *tp,
 			   struct netlink_ext_ack *extack)
 {
 	struct tc_action_net *tn = net_generic(net, tunnel_key_net_id);
 	struct nlattr *tb[TCA_TUNNEL_KEY_MAX + 1];
 	struct tcf_tunnel_key_params *params_new;
 	struct metadata_dst *metadata = NULL;
+	struct tcf_chain *goto_ch = NULL;
 	struct tc_tunnel_key *parm;
 	struct tcf_tunnel_key *t;
 	bool exists = false;
@@ -359,6 +362,12 @@ static int tunnel_key_init(struct net *net, struct nlattr *nla,
 		goto release_tun_meta;
 	}
 
+	err = tcf_action_check_ctrlact(parm->action, tp, &goto_ch, extack);
+	if (err < 0) {
+		ret = err;
+		exists = true;
+		goto release_tun_meta;
+	}
 	t = to_tunnel_key(*a);
 
 	params_new = kzalloc(sizeof(*params_new), GFP_KERNEL);
@@ -366,23 +375,29 @@ static int tunnel_key_init(struct net *net, struct nlattr *nla,
 		NL_SET_ERR_MSG(extack, "Cannot allocate tunnel key parameters");
 		ret = -ENOMEM;
 		exists = true;
-		goto release_tun_meta;
+		goto put_chain;
 	}
 	params_new->tcft_action = parm->t_action;
 	params_new->tcft_enc_metadata = metadata;
 
 	spin_lock_bh(&t->tcf_lock);
-	t->tcf_action = parm->action;
+	goto_ch = tcf_action_set_ctrlact(*a, parm->action, goto_ch);
 	rcu_swap_protected(t->params, params_new,
 			   lockdep_is_held(&t->tcf_lock));
 	spin_unlock_bh(&t->tcf_lock);
 	tunnel_key_release_params(params_new);
+	if (goto_ch)
+		tcf_chain_put_by_act(goto_ch);
 
 	if (ret == ACT_P_CREATED)
 		tcf_idr_insert(tn, *a);
 
 	return ret;
 
+put_chain:
+	if (goto_ch)
+		tcf_chain_put_by_act(goto_ch);
+
 release_tun_meta:
 	if (metadata)
 		dst_release(&metadata->dst);
diff --git a/net/sched/act_vlan.c b/net/sched/act_vlan.c
index ac0061599225..0f40d0a74423 100644
--- a/net/sched/act_vlan.c
+++ b/net/sched/act_vlan.c
@@ -15,6 +15,7 @@
 #include <linux/if_vlan.h>
 #include <net/netlink.h>
 #include <net/pkt_sched.h>
+#include <net/pkt_cls.h>
 
 #include <linux/tc_act/tc_vlan.h>
 #include <net/tc_act/tc_vlan.h>
@@ -105,10 +106,11 @@ static const struct nla_policy vlan_policy[TCA_VLAN_MAX + 1] = {
 static int tcf_vlan_init(struct net *net, struct nlattr *nla,
 			 struct nlattr *est, struct tc_action **a,
 			 int ovr, int bind, bool rtnl_held,
-			 struct netlink_ext_ack *extack)
+			 struct tcf_proto *tp, struct netlink_ext_ack *extack)
 {
 	struct tc_action_net *tn = net_generic(net, vlan_net_id);
 	struct nlattr *tb[TCA_VLAN_MAX + 1];
+	struct tcf_chain *goto_ch = NULL;
 	struct tcf_vlan_params *p;
 	struct tc_vlan *parm;
 	struct tcf_vlan *v;
@@ -200,12 +202,16 @@ static int tcf_vlan_init(struct net *net, struct nlattr *nla,
 		return -EEXIST;
 	}
 
+	err = tcf_action_check_ctrlact(parm->action, tp, &goto_ch, extack);
+	if (err < 0)
+		goto release_idr;
+
 	v = to_vlan(*a);
 
 	p = kzalloc(sizeof(*p), GFP_KERNEL);
 	if (!p) {
-		tcf_idr_release(*a, bind);
-		return -ENOMEM;
+		err = -ENOMEM;
+		goto put_chain;
 	}
 
 	p->tcfv_action = action;
@@ -214,16 +220,24 @@ static int tcf_vlan_init(struct net *net, struct nlattr *nla,
 	p->tcfv_push_proto = push_proto;
 
 	spin_lock_bh(&v->tcf_lock);
-	v->tcf_action = parm->action;
+	goto_ch = tcf_action_set_ctrlact(*a, parm->action, goto_ch);
 	rcu_swap_protected(v->vlan_p, p, lockdep_is_held(&v->tcf_lock));
 	spin_unlock_bh(&v->tcf_lock);
 
+	if (goto_ch)
+		tcf_chain_put_by_act(goto_ch);
 	if (p)
 		kfree_rcu(p, rcu);
 
 	if (ret == ACT_P_CREATED)
 		tcf_idr_insert(tn, *a);
 	return ret;
+put_chain:
+	if (goto_ch)
+		tcf_chain_put_by_act(goto_ch);
+release_idr:
+	tcf_idr_release(*a, bind);
+	return err;
 }
 
 static void tcf_vlan_cleanup(struct tc_action *a)
diff --git a/net/sched/cls_api.c b/net/sched/cls_api.c
index dc10525e90e7..99ae30c177c7 100644
--- a/net/sched/cls_api.c
+++ b/net/sched/cls_api.c
@@ -367,7 +367,7 @@ static void tcf_chain_destroy(struct tcf_chain *chain, bool free_block)
 	struct tcf_block *block = chain->block;
 
 	mutex_destroy(&chain->filter_chain_lock);
-	kfree(chain);
+	kfree_rcu(chain, rcu);
 	if (free_block)
 		tcf_block_destroy(block);
 }
diff --git a/net/sched/cls_matchall.c b/net/sched/cls_matchall.c
index 459921bd3d87..a13bc351a414 100644
--- a/net/sched/cls_matchall.c
+++ b/net/sched/cls_matchall.c
@@ -130,6 +130,11 @@ static void mall_destroy(struct tcf_proto *tp, bool rtnl_held,
 
 static void *mall_get(struct tcf_proto *tp, u32 handle)
 {
+	struct cls_mall_head *head = rtnl_dereference(tp->root);
+
+	if (head && head->handle == handle)
+		return head;
+
 	return NULL;
 }
 
diff --git a/net/sched/sch_cake.c b/net/sched/sch_cake.c
index 1d2a12132abc..259d97bc2abd 100644
--- a/net/sched/sch_cake.c
+++ b/net/sched/sch_cake.c
@@ -211,6 +211,9 @@ struct cake_sched_data {
 	u8		ack_filter;
 	u8		atm_mode;
 
+	u32		fwmark_mask;
+	u16		fwmark_shft;
+
 	/* time_next = time_this + ((len * rate_ns) >> rate_shft) */
 	u16		rate_shft;
 	ktime_t		time_next_packet;
@@ -258,8 +261,7 @@ enum {
 	CAKE_FLAG_AUTORATE_INGRESS = BIT(1),
 	CAKE_FLAG_INGRESS	   = BIT(2),
 	CAKE_FLAG_WASH		   = BIT(3),
-	CAKE_FLAG_SPLIT_GSO	   = BIT(4),
-	CAKE_FLAG_FWMARK	   = BIT(5)
+	CAKE_FLAG_SPLIT_GSO	   = BIT(4)
 };
 
 /* COBALT operates the Codel and BLUE algorithms in parallel, in order to
@@ -1515,16 +1517,27 @@ static unsigned int cake_drop(struct Qdisc *sch, struct sk_buff **to_free)
 
 static u8 cake_handle_diffserv(struct sk_buff *skb, u16 wash)
 {
+	int wlen = skb_network_offset(skb);
 	u8 dscp;
 
-	switch (skb->protocol) {
+	switch (tc_skb_protocol(skb)) {
 	case htons(ETH_P_IP):
+		wlen += sizeof(struct iphdr);
+		if (!pskb_may_pull(skb, wlen) ||
+		    skb_try_make_writable(skb, wlen))
+			return 0;
+
 		dscp = ipv4_get_dsfield(ip_hdr(skb)) >> 2;
 		if (wash && dscp)
 			ipv4_change_dsfield(ip_hdr(skb), INET_ECN_MASK, 0);
 		return dscp;
 
 	case htons(ETH_P_IPV6):
+		wlen += sizeof(struct ipv6hdr);
+		if (!pskb_may_pull(skb, wlen) ||
+		    skb_try_make_writable(skb, wlen))
+			return 0;
+
 		dscp = ipv6_get_dsfield(ipv6_hdr(skb)) >> 2;
 		if (wash && dscp)
 			ipv6_change_dsfield(ipv6_hdr(skb), INET_ECN_MASK, 0);
@@ -1543,7 +1556,7 @@ static struct cake_tin_data *cake_select_tin(struct Qdisc *sch,
 					     struct sk_buff *skb)
 {
 	struct cake_sched_data *q = qdisc_priv(sch);
-	u32 tin;
+	u32 tin, mark;
 	u8 dscp;
 
 	/* Tin selection: Default to diffserv-based selection, allow overriding
@@ -1551,14 +1564,13 @@ static struct cake_tin_data *cake_select_tin(struct Qdisc *sch,
 	 */
 	dscp = cake_handle_diffserv(skb,
 				    q->rate_flags & CAKE_FLAG_WASH);
+	mark = (skb->mark & q->fwmark_mask) >> q->fwmark_shft;
 
 	if (q->tin_mode == CAKE_DIFFSERV_BESTEFFORT)
 		tin = 0;
 
-	else if (q->rate_flags & CAKE_FLAG_FWMARK && /* use fw mark */
-		 skb->mark &&
-		 skb->mark <= q->tin_cnt)
-		tin = q->tin_order[skb->mark - 1];
+	else if (mark && mark <= q->tin_cnt)
+		tin = q->tin_order[mark - 1];
 
 	else if (TC_H_MAJ(skb->priority) == sch->handle &&
 		 TC_H_MIN(skb->priority) > 0 &&
@@ -2172,6 +2184,7 @@ static const struct nla_policy cake_policy[TCA_CAKE_MAX + 1] = {
 	[TCA_CAKE_MPU]		 = { .type = NLA_U32 },
 	[TCA_CAKE_INGRESS]	 = { .type = NLA_U32 },
 	[TCA_CAKE_ACK_FILTER]	 = { .type = NLA_U32 },
+	[TCA_CAKE_FWMARK]	 = { .type = NLA_U32 },
 };
 
 static void cake_set_rate(struct cake_tin_data *b, u64 rate, u32 mtu,
@@ -2619,10 +2632,8 @@ static int cake_change(struct Qdisc *sch, struct nlattr *opt,
 	}
 
 	if (tb[TCA_CAKE_FWMARK]) {
-		if (!!nla_get_u32(tb[TCA_CAKE_FWMARK]))
-			q->rate_flags |= CAKE_FLAG_FWMARK;
-		else
-			q->rate_flags &= ~CAKE_FLAG_FWMARK;
+		q->fwmark_mask = nla_get_u32(tb[TCA_CAKE_FWMARK]);
+		q->fwmark_shft = q->fwmark_mask ? __ffs(q->fwmark_mask) : 0;
 	}
 
 	if (q->tins) {
@@ -2784,8 +2795,7 @@ static int cake_dump(struct Qdisc *sch, struct sk_buff *skb)
 			!!(q->rate_flags & CAKE_FLAG_SPLIT_GSO)))
 		goto nla_put_failure;
 
-	if (nla_put_u32(skb, TCA_CAKE_FWMARK,
-			!!(q->rate_flags & CAKE_FLAG_FWMARK)))
+	if (nla_put_u32(skb, TCA_CAKE_FWMARK, q->fwmark_mask))
 		goto nla_put_failure;
 
 	return nla_nest_end(skb, opts);
diff --git a/net/sched/sch_cbq.c b/net/sched/sch_cbq.c
index 4dc05409e3fb..114b9048ea7e 100644
--- a/net/sched/sch_cbq.c
+++ b/net/sched/sch_cbq.c
@@ -1358,9 +1358,11 @@ cbq_dump_class_stats(struct Qdisc *sch, unsigned long arg,
 {
 	struct cbq_sched_data *q = qdisc_priv(sch);
 	struct cbq_class *cl = (struct cbq_class *)arg;
+	__u32 qlen;
 
 	cl->xstats.avgidle = cl->avgidle;
 	cl->xstats.undertime = 0;
+	qdisc_qstats_qlen_backlog(cl->q, &qlen, &cl->qstats.backlog);
 
 	if (cl->undertime != PSCHED_PASTPERFECT)
 		cl->xstats.undertime = cl->undertime - q->now;
@@ -1368,7 +1370,7 @@ cbq_dump_class_stats(struct Qdisc *sch, unsigned long arg,
 	if (gnet_stats_copy_basic(qdisc_root_sleeping_running(sch),
 				  d, NULL, &cl->bstats) < 0 ||
 	    gnet_stats_copy_rate_est(d, &cl->rate_est) < 0 ||
-	    gnet_stats_copy_queue(d, NULL, &cl->qstats, cl->q->q.qlen) < 0)
+	    gnet_stats_copy_queue(d, NULL, &cl->qstats, qlen) < 0)
 		return -1;
 
 	return gnet_stats_copy_app(d, &cl->xstats, sizeof(cl->xstats));
@@ -1665,17 +1667,13 @@ static int cbq_delete(struct Qdisc *sch, unsigned long arg)
 {
 	struct cbq_sched_data *q = qdisc_priv(sch);
 	struct cbq_class *cl = (struct cbq_class *)arg;
-	unsigned int qlen, backlog;
 
 	if (cl->filters || cl->children || cl == &q->link)
 		return -EBUSY;
 
 	sch_tree_lock(sch);
 
-	qlen = cl->q->q.qlen;
-	backlog = cl->q->qstats.backlog;
-	qdisc_reset(cl->q);
-	qdisc_tree_reduce_backlog(cl->q, qlen, backlog);
+	qdisc_purge_queue(cl->q);
 
 	if (cl->next_alive)
 		cbq_deactivate_class(cl);
diff --git a/net/sched/sch_drr.c b/net/sched/sch_drr.c
index 09b800991065..430df9a55ec4 100644
--- a/net/sched/sch_drr.c
+++ b/net/sched/sch_drr.c
@@ -50,15 +50,6 @@ static struct drr_class *drr_find_class(struct Qdisc *sch, u32 classid)
 	return container_of(clc, struct drr_class, common);
 }
 
-static void drr_purge_queue(struct drr_class *cl)
-{
-	unsigned int len = cl->qdisc->q.qlen;
-	unsigned int backlog = cl->qdisc->qstats.backlog;
-
-	qdisc_reset(cl->qdisc);
-	qdisc_tree_reduce_backlog(cl->qdisc, len, backlog);
-}
-
 static const struct nla_policy drr_policy[TCA_DRR_MAX + 1] = {
 	[TCA_DRR_QUANTUM]	= { .type = NLA_U32 },
 };
@@ -167,7 +158,7 @@ static int drr_delete_class(struct Qdisc *sch, unsigned long arg)
 
 	sch_tree_lock(sch);
 
-	drr_purge_queue(cl);
+	qdisc_purge_queue(cl->qdisc);
 	qdisc_class_hash_remove(&q->clhash, &cl->common);
 
 	sch_tree_unlock(sch);
@@ -269,7 +260,8 @@ static int drr_dump_class_stats(struct Qdisc *sch, unsigned long arg,
 				struct gnet_dump *d)
 {
 	struct drr_class *cl = (struct drr_class *)arg;
-	__u32 qlen = cl->qdisc->q.qlen;
+	__u32 qlen = qdisc_qlen_sum(cl->qdisc);
+	struct Qdisc *cl_q = cl->qdisc;
 	struct tc_drr_stats xstats;
 
 	memset(&xstats, 0, sizeof(xstats));
@@ -279,7 +271,7 @@ static int drr_dump_class_stats(struct Qdisc *sch, unsigned long arg,
 	if (gnet_stats_copy_basic(qdisc_root_sleeping_running(sch),
 				  d, NULL, &cl->bstats) < 0 ||
 	    gnet_stats_copy_rate_est(d, &cl->rate_est) < 0 ||
-	    gnet_stats_copy_queue(d, NULL, &cl->qdisc->qstats, qlen) < 0)
+	    gnet_stats_copy_queue(d, cl_q->cpu_qstats, &cl_q->qstats, qlen) < 0)
 		return -1;
 
 	return gnet_stats_copy_app(d, &xstats, sizeof(xstats));
diff --git a/net/sched/sch_hfsc.c b/net/sched/sch_hfsc.c
index 24cc220a3218..d2ab463f22ae 100644
--- a/net/sched/sch_hfsc.c
+++ b/net/sched/sch_hfsc.c
@@ -845,16 +845,6 @@ qdisc_peek_len(struct Qdisc *sch)
 }
 
 static void
-hfsc_purge_queue(struct Qdisc *sch, struct hfsc_class *cl)
-{
-	unsigned int len = cl->qdisc->q.qlen;
-	unsigned int backlog = cl->qdisc->qstats.backlog;
-
-	qdisc_reset(cl->qdisc);
-	qdisc_tree_reduce_backlog(cl->qdisc, len, backlog);
-}
-
-static void
 hfsc_adjust_levels(struct hfsc_class *cl)
 {
 	struct hfsc_class *p;
@@ -1076,7 +1066,7 @@ hfsc_change_class(struct Qdisc *sch, u32 classid, u32 parentid,
 	qdisc_class_hash_insert(&q->clhash, &cl->cl_common);
 	list_add_tail(&cl->siblings, &parent->children);
 	if (parent->level == 0)
-		hfsc_purge_queue(sch, parent);
+		qdisc_purge_queue(parent->qdisc);
 	hfsc_adjust_levels(parent);
 	sch_tree_unlock(sch);
 
@@ -1112,7 +1102,7 @@ hfsc_delete_class(struct Qdisc *sch, unsigned long arg)
 	list_del(&cl->siblings);
 	hfsc_adjust_levels(cl->cl_parent);
 
-	hfsc_purge_queue(sch, cl);
+	qdisc_purge_queue(cl->qdisc);
 	qdisc_class_hash_remove(&q->clhash, &cl->cl_common);
 
 	sch_tree_unlock(sch);
@@ -1328,8 +1318,9 @@ hfsc_dump_class_stats(struct Qdisc *sch, unsigned long arg,
 {
 	struct hfsc_class *cl = (struct hfsc_class *)arg;
 	struct tc_hfsc_stats xstats;
+	__u32 qlen;
 
-	cl->qstats.backlog = cl->qdisc->qstats.backlog;
+	qdisc_qstats_qlen_backlog(cl->qdisc, &qlen, &cl->qstats.backlog);
 	xstats.level   = cl->level;
 	xstats.period  = cl->cl_vtperiod;
 	xstats.work    = cl->cl_total;
@@ -1337,7 +1328,7 @@ hfsc_dump_class_stats(struct Qdisc *sch, unsigned long arg,
 
 	if (gnet_stats_copy_basic(qdisc_root_sleeping_running(sch), d, NULL, &cl->bstats) < 0 ||
 	    gnet_stats_copy_rate_est(d, &cl->rate_est) < 0 ||
-	    gnet_stats_copy_queue(d, NULL, &cl->qstats, cl->qdisc->q.qlen) < 0)
+	    gnet_stats_copy_queue(d, NULL, &cl->qstats, qlen) < 0)
 		return -1;
 
 	return gnet_stats_copy_app(d, &xstats, sizeof(xstats));
diff --git a/net/sched/sch_htb.c b/net/sched/sch_htb.c
index 30f9da7e1076..2f9883b196e8 100644
--- a/net/sched/sch_htb.c
+++ b/net/sched/sch_htb.c
@@ -1127,10 +1127,9 @@ htb_dump_class_stats(struct Qdisc *sch, unsigned long arg, struct gnet_dump *d)
 	};
 	__u32 qlen = 0;
 
-	if (!cl->level && cl->leaf.q) {
-		qlen = cl->leaf.q->q.qlen;
-		qs.backlog = cl->leaf.q->qstats.backlog;
-	}
+	if (!cl->level && cl->leaf.q)
+		qdisc_qstats_qlen_backlog(cl->leaf.q, &qlen, &qs.backlog);
+
 	cl->xstats.tokens = clamp_t(s64, PSCHED_NS2TICKS(cl->tokens),
 				    INT_MIN, INT_MAX);
 	cl->xstats.ctokens = clamp_t(s64, PSCHED_NS2TICKS(cl->ctokens),
@@ -1270,13 +1269,8 @@ static int htb_delete(struct Qdisc *sch, unsigned long arg)
 
 	sch_tree_lock(sch);
 
-	if (!cl->level) {
-		unsigned int qlen = cl->leaf.q->q.qlen;
-		unsigned int backlog = cl->leaf.q->qstats.backlog;
-
-		qdisc_reset(cl->leaf.q);
-		qdisc_tree_reduce_backlog(cl->leaf.q, qlen, backlog);
-	}
+	if (!cl->level)
+		qdisc_purge_queue(cl->leaf.q);
 
 	/* delete from hash and active; remainder in destroy_class */
 	qdisc_class_hash_remove(&q->clhash, &cl->common);
@@ -1404,12 +1398,8 @@ static int htb_change_class(struct Qdisc *sch, u32 classid,
 					  classid, NULL);
 		sch_tree_lock(sch);
 		if (parent && !parent->level) {
-			unsigned int qlen = parent->leaf.q->q.qlen;
-			unsigned int backlog = parent->leaf.q->qstats.backlog;
-
 			/* turn parent into inner node */
-			qdisc_reset(parent->leaf.q);
-			qdisc_tree_reduce_backlog(parent->leaf.q, qlen, backlog);
+			qdisc_purge_queue(parent->leaf.q);
 			qdisc_put(parent->leaf.q);
 			if (parent->prio_activity)
 				htb_deactivate(q, parent);
diff --git a/net/sched/sch_mq.c b/net/sched/sch_mq.c
index 203659bc3906..3a3312467692 100644
--- a/net/sched/sch_mq.c
+++ b/net/sched/sch_mq.c
@@ -249,7 +249,7 @@ static int mq_dump_class_stats(struct Qdisc *sch, unsigned long cl,
 
 	sch = dev_queue->qdisc_sleeping;
 	if (gnet_stats_copy_basic(&sch->running, d, NULL, &sch->bstats) < 0 ||
-	    gnet_stats_copy_queue(d, NULL, &sch->qstats, sch->q.qlen) < 0)
+	    qdisc_qstats_copy(d, sch) < 0)
 		return -1;
 	return 0;
 }
diff --git a/net/sched/sch_mqprio.c b/net/sched/sch_mqprio.c
index d364e63c396d..ea0dc112b38d 100644
--- a/net/sched/sch_mqprio.c
+++ b/net/sched/sch_mqprio.c
@@ -561,8 +561,7 @@ static int mqprio_dump_class_stats(struct Qdisc *sch, unsigned long cl,
 		sch = dev_queue->qdisc_sleeping;
 		if (gnet_stats_copy_basic(qdisc_root_sleeping_running(sch),
 					  d, NULL, &sch->bstats) < 0 ||
-		    gnet_stats_copy_queue(d, NULL,
-					  &sch->qstats, sch->q.qlen) < 0)
+		    qdisc_qstats_copy(d, sch) < 0)
 			return -1;
 	}
 	return 0;
diff --git a/net/sched/sch_multiq.c b/net/sched/sch_multiq.c
index 7410ce4d0321..35b03ae08e0f 100644
--- a/net/sched/sch_multiq.c
+++ b/net/sched/sch_multiq.c
@@ -201,9 +201,9 @@ static int multiq_tune(struct Qdisc *sch, struct nlattr *opt,
 	for (i = q->bands; i < q->max_bands; i++) {
 		if (q->queues[i] != &noop_qdisc) {
 			struct Qdisc *child = q->queues[i];
+
 			q->queues[i] = &noop_qdisc;
-			qdisc_tree_reduce_backlog(child, child->q.qlen,
-						  child->qstats.backlog);
+			qdisc_tree_flush_backlog(child);
 			qdisc_put(child);
 		}
 	}
@@ -225,9 +225,7 @@ static int multiq_tune(struct Qdisc *sch, struct nlattr *opt,
 					qdisc_hash_add(child, true);
 
 				if (old != &noop_qdisc) {
-					qdisc_tree_reduce_backlog(old,
-								  old->q.qlen,
-								  old->qstats.backlog);
+					qdisc_tree_flush_backlog(old);
 					qdisc_put(old);
 				}
 				sch_tree_unlock(sch);
@@ -344,7 +342,7 @@ static int multiq_dump_class_stats(struct Qdisc *sch, unsigned long cl,
 	cl_q = q->queues[cl - 1];
 	if (gnet_stats_copy_basic(qdisc_root_sleeping_running(sch),
 				  d, NULL, &cl_q->bstats) < 0 ||
-	    gnet_stats_copy_queue(d, NULL, &cl_q->qstats, cl_q->q.qlen) < 0)
+	    qdisc_qstats_copy(d, cl_q) < 0)
 		return -1;
 
 	return 0;
diff --git a/net/sched/sch_prio.c b/net/sched/sch_prio.c
index 847141cd900f..d519b21535b3 100644
--- a/net/sched/sch_prio.c
+++ b/net/sched/sch_prio.c
@@ -216,12 +216,8 @@ static int prio_tune(struct Qdisc *sch, struct nlattr *opt,
 	q->bands = qopt->bands;
 	memcpy(q->prio2band, qopt->priomap, TC_PRIO_MAX+1);
 
-	for (i = q->bands; i < oldbands; i++) {
-		struct Qdisc *child = q->queues[i];
-
-		qdisc_tree_reduce_backlog(child, child->q.qlen,
-					  child->qstats.backlog);
-	}
+	for (i = q->bands; i < oldbands; i++)
+		qdisc_tree_flush_backlog(q->queues[i]);
 
 	for (i = oldbands; i < q->bands; i++) {
 		q->queues[i] = queues[i];
@@ -365,7 +361,7 @@ static int prio_dump_class_stats(struct Qdisc *sch, unsigned long cl,
 	cl_q = q->queues[cl - 1];
 	if (gnet_stats_copy_basic(qdisc_root_sleeping_running(sch),
 				  d, NULL, &cl_q->bstats) < 0 ||
-	    gnet_stats_copy_queue(d, NULL, &cl_q->qstats, cl_q->q.qlen) < 0)
+	    qdisc_qstats_copy(d, cl_q) < 0)
 		return -1;
 
 	return 0;
diff --git a/net/sched/sch_qfq.c b/net/sched/sch_qfq.c
index 29f5c4a24688..1589364b54da 100644
--- a/net/sched/sch_qfq.c
+++ b/net/sched/sch_qfq.c
@@ -217,15 +217,6 @@ static struct qfq_class *qfq_find_class(struct Qdisc *sch, u32 classid)
 	return container_of(clc, struct qfq_class, common);
 }
 
-static void qfq_purge_queue(struct qfq_class *cl)
-{
-	unsigned int len = cl->qdisc->q.qlen;
-	unsigned int backlog = cl->qdisc->qstats.backlog;
-
-	qdisc_reset(cl->qdisc);
-	qdisc_tree_reduce_backlog(cl->qdisc, len, backlog);
-}
-
 static const struct nla_policy qfq_policy[TCA_QFQ_MAX + 1] = {
 	[TCA_QFQ_WEIGHT] = { .type = NLA_U32 },
 	[TCA_QFQ_LMAX] = { .type = NLA_U32 },
@@ -551,7 +542,7 @@ static int qfq_delete_class(struct Qdisc *sch, unsigned long arg)
 
 	sch_tree_lock(sch);
 
-	qfq_purge_queue(cl);
+	qdisc_purge_queue(cl->qdisc);
 	qdisc_class_hash_remove(&q->clhash, &cl->common);
 
 	sch_tree_unlock(sch);
@@ -655,8 +646,7 @@ static int qfq_dump_class_stats(struct Qdisc *sch, unsigned long arg,
 	if (gnet_stats_copy_basic(qdisc_root_sleeping_running(sch),
 				  d, NULL, &cl->bstats) < 0 ||
 	    gnet_stats_copy_rate_est(d, &cl->rate_est) < 0 ||
-	    gnet_stats_copy_queue(d, NULL,
-				  &cl->qdisc->qstats, cl->qdisc->q.qlen) < 0)
+	    qdisc_qstats_copy(d, cl->qdisc) < 0)
 		return -1;
 
 	return gnet_stats_copy_app(d, &xstats, sizeof(xstats));
diff --git a/net/sched/sch_red.c b/net/sched/sch_red.c
index 9df9942340ea..4e8c0abf6194 100644
--- a/net/sched/sch_red.c
+++ b/net/sched/sch_red.c
@@ -233,8 +233,7 @@ static int red_change(struct Qdisc *sch, struct nlattr *opt,
 	q->flags = ctl->flags;
 	q->limit = ctl->limit;
 	if (child) {
-		qdisc_tree_reduce_backlog(q->qdisc, q->qdisc->q.qlen,
-					  q->qdisc->qstats.backlog);
+		qdisc_tree_flush_backlog(q->qdisc);
 		old_child = q->qdisc;
 		q->qdisc = child;
 	}
diff --git a/net/sched/sch_sfb.c b/net/sched/sch_sfb.c
index bab506b01a32..2419fdb75966 100644
--- a/net/sched/sch_sfb.c
+++ b/net/sched/sch_sfb.c
@@ -521,8 +521,7 @@ static int sfb_change(struct Qdisc *sch, struct nlattr *opt,
 		qdisc_hash_add(child, true);
 	sch_tree_lock(sch);
 
-	qdisc_tree_reduce_backlog(q->qdisc, q->qdisc->q.qlen,
-				  q->qdisc->qstats.backlog);
+	qdisc_tree_flush_backlog(q->qdisc);
 	qdisc_put(q->qdisc);
 	q->qdisc = child;
 
diff --git a/net/sched/sch_taprio.c b/net/sched/sch_taprio.c
index 206e4dbed12f..c7041999eb5d 100644
--- a/net/sched/sch_taprio.c
+++ b/net/sched/sch_taprio.c
@@ -895,7 +895,7 @@ static int taprio_dump_class_stats(struct Qdisc *sch, unsigned long cl,
 
 	sch = dev_queue->qdisc_sleeping;
 	if (gnet_stats_copy_basic(&sch->running, d, NULL, &sch->bstats) < 0 ||
-	    gnet_stats_copy_queue(d, NULL, &sch->qstats, sch->q.qlen) < 0)
+	    qdisc_qstats_copy(d, sch) < 0)
 		return -1;
 	return 0;
 }
diff --git a/net/sched/sch_tbf.c b/net/sched/sch_tbf.c
index 7f272a9070c5..f71578dbb9e3 100644
--- a/net/sched/sch_tbf.c
+++ b/net/sched/sch_tbf.c
@@ -391,8 +391,7 @@ static int tbf_change(struct Qdisc *sch, struct nlattr *opt,
 
 	sch_tree_lock(sch);
 	if (child) {
-		qdisc_tree_reduce_backlog(q->qdisc, q->qdisc->q.qlen,
-					  q->qdisc->qstats.backlog);
+		qdisc_tree_flush_backlog(q->qdisc);
 		qdisc_put(q->qdisc);
 		q->qdisc = child;
 	}
diff --git a/net/sctp/auth.c b/net/sctp/auth.c
index 39d72e58b8e5..31569f4809f6 100644
--- a/net/sctp/auth.c
+++ b/net/sctp/auth.c
@@ -760,7 +760,6 @@ void sctp_auth_calculate_hmac(const struct sctp_association *asoc,
 		SHASH_DESC_ON_STACK(desc, tfm);
 
 		desc->tfm = tfm;
-		desc->flags = 0;
 		crypto_shash_digest(desc, (u8 *)auth,
 				    end - (unsigned char *)auth, digest);
 		shash_desc_zero(desc);
diff --git a/net/sctp/protocol.c b/net/sctp/protocol.c
index 6abc8b274270..951afdeea5e9 100644
--- a/net/sctp/protocol.c
+++ b/net/sctp/protocol.c
@@ -600,6 +600,7 @@ out:
 static int sctp_v4_addr_to_user(struct sctp_sock *sp, union sctp_addr *addr)
 {
 	/* No address mapping for V4 sockets */
+	memset(addr->v4.sin_zero, 0, sizeof(addr->v4.sin_zero));
 	return sizeof(struct sockaddr_in);
 }
 
diff --git a/net/sctp/sm_make_chunk.c b/net/sctp/sm_make_chunk.c
index d05c57664e36..72e74503f9fc 100644
--- a/net/sctp/sm_make_chunk.c
+++ b/net/sctp/sm_make_chunk.c
@@ -1684,7 +1684,6 @@ static struct sctp_cookie_param *sctp_pack_cookie(
 
 		/* Sign the message.  */
 		desc->tfm = sctp_sk(ep->base.sk)->hmac;
-		desc->flags = 0;
 
 		err = crypto_shash_setkey(desc->tfm, ep->secret_key,
 					  sizeof(ep->secret_key)) ?:
@@ -1755,7 +1754,6 @@ struct sctp_association *sctp_unpack_cookie(
 		int err;
 
 		desc->tfm = sctp_sk(ep->base.sk)->hmac;
-		desc->flags = 0;
 
 		err = crypto_shash_setkey(desc->tfm, ep->secret_key,
 					  sizeof(ep->secret_key)) ?:
diff --git a/net/sctp/sm_sideeffect.c b/net/sctp/sm_sideeffect.c
index 1d143bc3f73d..4aa03588f87b 100644
--- a/net/sctp/sm_sideeffect.c
+++ b/net/sctp/sm_sideeffect.c
@@ -1112,32 +1112,6 @@ static void sctp_cmd_send_msg(struct sctp_association *asoc,
 }
 
 
-/* Sent the next ASCONF packet currently stored in the association.
- * This happens after the ASCONF_ACK was succeffully processed.
- */
-static void sctp_cmd_send_asconf(struct sctp_association *asoc)
-{
-	struct net *net = sock_net(asoc->base.sk);
-
-	/* Send the next asconf chunk from the addip chunk
-	 * queue.
-	 */
-	if (!list_empty(&asoc->addip_chunk_list)) {
-		struct list_head *entry = asoc->addip_chunk_list.next;
-		struct sctp_chunk *asconf = list_entry(entry,
-						struct sctp_chunk, list);
-		list_del_init(entry);
-
-		/* Hold the chunk until an ASCONF_ACK is received. */
-		sctp_chunk_hold(asconf);
-		if (sctp_primitive_ASCONF(net, asoc, asconf))
-			sctp_chunk_free(asconf);
-		else
-			asoc->addip_last_asconf = asconf;
-	}
-}
-
-
 /* These three macros allow us to pull the debugging code out of the
  * main flow of sctp_do_sm() to keep attention focused on the real
  * functionality there.
@@ -1783,9 +1757,6 @@ static int sctp_cmd_interpreter(enum sctp_event_type event_type,
 			}
 			sctp_cmd_send_msg(asoc, cmd->obj.msg, gfp);
 			break;
-		case SCTP_CMD_SEND_NEXT_ASCONF:
-			sctp_cmd_send_asconf(asoc);
-			break;
 		case SCTP_CMD_PURGE_ASCONF_QUEUE:
 			sctp_asconf_queue_teardown(asoc);
 			break;
diff --git a/net/sctp/sm_statefuns.c b/net/sctp/sm_statefuns.c
index c9ae3404b1bb..713a669d2058 100644
--- a/net/sctp/sm_statefuns.c
+++ b/net/sctp/sm_statefuns.c
@@ -3824,6 +3824,29 @@ enum sctp_disposition sctp_sf_do_asconf(struct net *net,
 	return SCTP_DISPOSITION_CONSUME;
 }
 
+static enum sctp_disposition sctp_send_next_asconf(
+					struct net *net,
+					const struct sctp_endpoint *ep,
+					struct sctp_association *asoc,
+					const union sctp_subtype type,
+					struct sctp_cmd_seq *commands)
+{
+	struct sctp_chunk *asconf;
+	struct list_head *entry;
+
+	if (list_empty(&asoc->addip_chunk_list))
+		return SCTP_DISPOSITION_CONSUME;
+
+	entry = asoc->addip_chunk_list.next;
+	asconf = list_entry(entry, struct sctp_chunk, list);
+
+	list_del_init(entry);
+	sctp_chunk_hold(asconf);
+	asoc->addip_last_asconf = asconf;
+
+	return sctp_sf_do_prm_asconf(net, ep, asoc, type, asconf, commands);
+}
+
 /*
  * ADDIP Section 4.3 General rules for address manipulation
  * When building TLV parameters for the ASCONF Chunk that will add or
@@ -3915,14 +3938,10 @@ enum sctp_disposition sctp_sf_do_asconf_ack(struct net *net,
 				SCTP_TO(SCTP_EVENT_TIMEOUT_T4_RTO));
 
 		if (!sctp_process_asconf_ack((struct sctp_association *)asoc,
-					     asconf_ack)) {
-			/* Successfully processed ASCONF_ACK.  We can
-			 * release the next asconf if we have one.
-			 */
-			sctp_add_cmd_sf(commands, SCTP_CMD_SEND_NEXT_ASCONF,
-					SCTP_NULL());
-			return SCTP_DISPOSITION_CONSUME;
-		}
+					     asconf_ack))
+			return sctp_send_next_asconf(net, ep,
+					(struct sctp_association *)asoc,
+							type, commands);
 
 		abort = sctp_make_abort(asoc, asconf_ack,
 					sizeof(struct sctp_errhdr));
diff --git a/net/sctp/socket.c b/net/sctp/socket.c
index 6140471efd4b..4583fa914e62 100644
--- a/net/sctp/socket.c
+++ b/net/sctp/socket.c
@@ -999,7 +999,7 @@ static int sctp_setsockopt_bindx(struct sock *sk,
 	if (unlikely(addrs_size <= 0))
 		return -EINVAL;
 
-	kaddrs = vmemdup_user(addrs, addrs_size);
+	kaddrs = memdup_user(addrs, addrs_size);
 	if (unlikely(IS_ERR(kaddrs)))
 		return PTR_ERR(kaddrs);
 
@@ -1007,7 +1007,7 @@ static int sctp_setsockopt_bindx(struct sock *sk,
 	addr_buf = kaddrs;
 	while (walk_size < addrs_size) {
 		if (walk_size + sizeof(sa_family_t) > addrs_size) {
-			kvfree(kaddrs);
+			kfree(kaddrs);
 			return -EINVAL;
 		}
 
@@ -1018,7 +1018,7 @@ static int sctp_setsockopt_bindx(struct sock *sk,
 		 * causes the address buffer to overflow return EINVAL.
 		 */
 		if (!af || (walk_size + af->sockaddr_len) > addrs_size) {
-			kvfree(kaddrs);
+			kfree(kaddrs);
 			return -EINVAL;
 		}
 		addrcnt++;
@@ -1054,7 +1054,7 @@ static int sctp_setsockopt_bindx(struct sock *sk,
 	}
 
 out:
-	kvfree(kaddrs);
+	kfree(kaddrs);
 
 	return err;
 }
@@ -1329,7 +1329,7 @@ static int __sctp_setsockopt_connectx(struct sock *sk,
 	if (unlikely(addrs_size <= 0))
 		return -EINVAL;
 
-	kaddrs = vmemdup_user(addrs, addrs_size);
+	kaddrs = memdup_user(addrs, addrs_size);
 	if (unlikely(IS_ERR(kaddrs)))
 		return PTR_ERR(kaddrs);
 
@@ -1349,7 +1349,7 @@ static int __sctp_setsockopt_connectx(struct sock *sk,
 	err = __sctp_connect(sk, kaddrs, addrs_size, flags, assoc_id);
 
 out_free:
-	kvfree(kaddrs);
+	kfree(kaddrs);
 
 	return err;
 }
@@ -2920,6 +2920,9 @@ static int sctp_setsockopt_delayed_ack(struct sock *sk,
 		return 0;
 	}
 
+	if (sctp_style(sk, TCP))
+		params.sack_assoc_id = SCTP_FUTURE_ASSOC;
+
 	if (params.sack_assoc_id == SCTP_FUTURE_ASSOC ||
 	    params.sack_assoc_id == SCTP_ALL_ASSOC) {
 		if (params.sack_delay) {
@@ -3024,6 +3027,9 @@ static int sctp_setsockopt_default_send_param(struct sock *sk,
 		return 0;
 	}
 
+	if (sctp_style(sk, TCP))
+		info.sinfo_assoc_id = SCTP_FUTURE_ASSOC;
+
 	if (info.sinfo_assoc_id == SCTP_FUTURE_ASSOC ||
 	    info.sinfo_assoc_id == SCTP_ALL_ASSOC) {
 		sp->default_stream = info.sinfo_stream;
@@ -3081,6 +3087,9 @@ static int sctp_setsockopt_default_sndinfo(struct sock *sk,
 		return 0;
 	}
 
+	if (sctp_style(sk, TCP))
+		info.snd_assoc_id = SCTP_FUTURE_ASSOC;
+
 	if (info.snd_assoc_id == SCTP_FUTURE_ASSOC ||
 	    info.snd_assoc_id == SCTP_ALL_ASSOC) {
 		sp->default_stream = info.snd_sid;
@@ -3531,6 +3540,9 @@ static int sctp_setsockopt_context(struct sock *sk, char __user *optval,
 		return 0;
 	}
 
+	if (sctp_style(sk, TCP))
+		params.assoc_id = SCTP_FUTURE_ASSOC;
+
 	if (params.assoc_id == SCTP_FUTURE_ASSOC ||
 	    params.assoc_id == SCTP_ALL_ASSOC)
 		sp->default_rcv_context = params.assoc_value;
@@ -3670,6 +3682,9 @@ static int sctp_setsockopt_maxburst(struct sock *sk,
 		return 0;
 	}
 
+	if (sctp_style(sk, TCP))
+		params.assoc_id = SCTP_FUTURE_ASSOC;
+
 	if (params.assoc_id == SCTP_FUTURE_ASSOC ||
 	    params.assoc_id == SCTP_ALL_ASSOC)
 		sp->max_burst = params.assoc_value;
@@ -3798,6 +3813,9 @@ static int sctp_setsockopt_auth_key(struct sock *sk,
 		goto out;
 	}
 
+	if (sctp_style(sk, TCP))
+		authkey->sca_assoc_id = SCTP_FUTURE_ASSOC;
+
 	if (authkey->sca_assoc_id == SCTP_FUTURE_ASSOC ||
 	    authkey->sca_assoc_id == SCTP_ALL_ASSOC) {
 		ret = sctp_auth_set_key(ep, asoc, authkey);
@@ -3853,6 +3871,9 @@ static int sctp_setsockopt_active_key(struct sock *sk,
 	if (asoc)
 		return sctp_auth_set_active_key(ep, asoc, val.scact_keynumber);
 
+	if (sctp_style(sk, TCP))
+		val.scact_assoc_id = SCTP_FUTURE_ASSOC;
+
 	if (val.scact_assoc_id == SCTP_FUTURE_ASSOC ||
 	    val.scact_assoc_id == SCTP_ALL_ASSOC) {
 		ret = sctp_auth_set_active_key(ep, asoc, val.scact_keynumber);
@@ -3904,6 +3925,9 @@ static int sctp_setsockopt_del_key(struct sock *sk,
 	if (asoc)
 		return sctp_auth_del_key_id(ep, asoc, val.scact_keynumber);
 
+	if (sctp_style(sk, TCP))
+		val.scact_assoc_id = SCTP_FUTURE_ASSOC;
+
 	if (val.scact_assoc_id == SCTP_FUTURE_ASSOC ||
 	    val.scact_assoc_id == SCTP_ALL_ASSOC) {
 		ret = sctp_auth_del_key_id(ep, asoc, val.scact_keynumber);
@@ -3954,6 +3978,9 @@ static int sctp_setsockopt_deactivate_key(struct sock *sk, char __user *optval,
 	if (asoc)
 		return sctp_auth_deact_key_id(ep, asoc, val.scact_keynumber);
 
+	if (sctp_style(sk, TCP))
+		val.scact_assoc_id = SCTP_FUTURE_ASSOC;
+
 	if (val.scact_assoc_id == SCTP_FUTURE_ASSOC ||
 	    val.scact_assoc_id == SCTP_ALL_ASSOC) {
 		ret = sctp_auth_deact_key_id(ep, asoc, val.scact_keynumber);
@@ -4169,6 +4196,9 @@ static int sctp_setsockopt_default_prinfo(struct sock *sk,
 		goto out;
 	}
 
+	if (sctp_style(sk, TCP))
+		info.pr_assoc_id = SCTP_FUTURE_ASSOC;
+
 	if (info.pr_assoc_id == SCTP_FUTURE_ASSOC ||
 	    info.pr_assoc_id == SCTP_ALL_ASSOC) {
 		SCTP_PR_SET_POLICY(sp->default_flags, info.pr_policy);
@@ -4251,6 +4281,9 @@ static int sctp_setsockopt_enable_strreset(struct sock *sk,
 		goto out;
 	}
 
+	if (sctp_style(sk, TCP))
+		params.assoc_id = SCTP_FUTURE_ASSOC;
+
 	if (params.assoc_id == SCTP_FUTURE_ASSOC ||
 	    params.assoc_id == SCTP_ALL_ASSOC)
 		ep->strreset_enable = params.assoc_value;
@@ -4376,6 +4409,9 @@ static int sctp_setsockopt_scheduler(struct sock *sk,
 	if (asoc)
 		return sctp_sched_set_sched(asoc, params.assoc_value);
 
+	if (sctp_style(sk, TCP))
+		params.assoc_id = SCTP_FUTURE_ASSOC;
+
 	if (params.assoc_id == SCTP_FUTURE_ASSOC ||
 	    params.assoc_id == SCTP_ALL_ASSOC)
 		sp->default_ss = params.assoc_value;
@@ -4541,6 +4577,9 @@ static int sctp_setsockopt_event(struct sock *sk, char __user *optval,
 	if (asoc)
 		return sctp_assoc_ulpevent_type_set(&param, asoc);
 
+	if (sctp_style(sk, TCP))
+		param.se_assoc_id = SCTP_FUTURE_ASSOC;
+
 	if (param.se_assoc_id == SCTP_FUTURE_ASSOC ||
 	    param.se_assoc_id == SCTP_ALL_ASSOC)
 		sctp_ulpevent_type_set(&sp->subscribe,
@@ -4808,7 +4847,8 @@ static int sctp_connect(struct sock *sk, struct sockaddr *addr,
 	}
 
 	/* Validate addr_len before calling common connect/connectx routine. */
-	af = sctp_get_af_specific(addr->sa_family);
+	af = addr_len < offsetofend(struct sockaddr, sa_family) ? NULL :
+		sctp_get_af_specific(addr->sa_family);
 	if (!af || addr_len < af->sockaddr_len) {
 		err = -EINVAL;
 	} else {
@@ -9169,7 +9209,7 @@ static inline void sctp_copy_descendant(struct sock *sk_to,
 {
 	int ancestor_size = sizeof(struct inet_sock) +
 			    sizeof(struct sctp_sock) -
-			    offsetof(struct sctp_sock, auto_asconf_list);
+			    offsetof(struct sctp_sock, pd_lobby);
 
 	if (sk_from->sk_family == PF_INET6)
 		ancestor_size += sizeof(struct ipv6_pinfo);
@@ -9253,7 +9293,6 @@ static int sctp_sock_migrate(struct sock *oldsk, struct sock *newsk,
 	 * 2) Peeling off partial delivery; keep pd_lobby in new pd_lobby.
 	 * 3) Peeling off non-partial delivery; move pd_lobby to receive_queue.
 	 */
-	skb_queue_head_init(&newsp->pd_lobby);
 	atomic_set(&sctp_sk(newsk)->pd_mode, assoc->ulpq.pd_mode);
 
 	if (atomic_read(&sctp_sk(oldsk)->pd_mode)) {
diff --git a/net/smc/af_smc.c b/net/smc/af_smc.c
index 77ef53596d18..6f869ef49b32 100644
--- a/net/smc/af_smc.c
+++ b/net/smc/af_smc.c
@@ -167,10 +167,9 @@ static int smc_release(struct socket *sock)
 
 	if (sk->sk_state == SMC_CLOSED) {
 		if (smc->clcsock) {
-			mutex_lock(&smc->clcsock_release_lock);
-			sock_release(smc->clcsock);
-			smc->clcsock = NULL;
-			mutex_unlock(&smc->clcsock_release_lock);
+			release_sock(sk);
+			smc_clcsock_release(smc);
+			lock_sock(sk);
 		}
 		if (!smc->use_fallback)
 			smc_conn_free(&smc->conn);
@@ -446,10 +445,19 @@ static void smc_link_save_peer_info(struct smc_link *link,
 	link->peer_mtu = clc->qp_mtu;
 }
 
+static void smc_switch_to_fallback(struct smc_sock *smc)
+{
+	smc->use_fallback = true;
+	if (smc->sk.sk_socket && smc->sk.sk_socket->file) {
+		smc->clcsock->file = smc->sk.sk_socket->file;
+		smc->clcsock->file->private_data = smc->clcsock;
+	}
+}
+
 /* fall back during connect */
 static int smc_connect_fallback(struct smc_sock *smc, int reason_code)
 {
-	smc->use_fallback = true;
+	smc_switch_to_fallback(smc);
 	smc->fallback_rsn = reason_code;
 	smc_copy_sock_settings_to_clc(smc);
 	if (smc->sk.sk_state == SMC_INIT)
@@ -775,10 +783,14 @@ static void smc_connect_work(struct work_struct *work)
 		smc->sk.sk_err = -rc;
 
 out:
-	if (smc->sk.sk_err)
-		smc->sk.sk_state_change(&smc->sk);
-	else
-		smc->sk.sk_write_space(&smc->sk);
+	if (!sock_flag(&smc->sk, SOCK_DEAD)) {
+		if (smc->sk.sk_err) {
+			smc->sk.sk_state_change(&smc->sk);
+		} else { /* allow polling before and after fallback decision */
+			smc->clcsock->sk->sk_write_space(smc->clcsock->sk);
+			smc->sk.sk_write_space(&smc->sk);
+		}
+	}
 	kfree(smc->connect_info);
 	smc->connect_info = NULL;
 	release_sock(&smc->sk);
@@ -872,11 +884,11 @@ static int smc_clcsock_accept(struct smc_sock *lsmc, struct smc_sock **new_smc)
 	if  (rc < 0)
 		lsk->sk_err = -rc;
 	if (rc < 0 || lsk->sk_state == SMC_CLOSED) {
+		new_sk->sk_prot->unhash(new_sk);
 		if (new_clcsock)
 			sock_release(new_clcsock);
 		new_sk->sk_state = SMC_CLOSED;
 		sock_set_flag(new_sk, SOCK_DEAD);
-		new_sk->sk_prot->unhash(new_sk);
 		sock_put(new_sk); /* final */
 		*new_smc = NULL;
 		goto out;
@@ -927,16 +939,21 @@ struct sock *smc_accept_dequeue(struct sock *parent,
 
 		smc_accept_unlink(new_sk);
 		if (new_sk->sk_state == SMC_CLOSED) {
+			new_sk->sk_prot->unhash(new_sk);
 			if (isk->clcsock) {
 				sock_release(isk->clcsock);
 				isk->clcsock = NULL;
 			}
-			new_sk->sk_prot->unhash(new_sk);
 			sock_put(new_sk); /* final */
 			continue;
 		}
-		if (new_sock)
+		if (new_sock) {
 			sock_graft(new_sk, new_sock);
+			if (isk->use_fallback) {
+				smc_sk(new_sk)->clcsock->file = new_sock->file;
+				isk->clcsock->file->private_data = isk->clcsock;
+			}
+		}
 		return new_sk;
 	}
 	return NULL;
@@ -956,6 +973,7 @@ void smc_close_non_accepted(struct sock *sk)
 		sock_set_flag(sk, SOCK_DEAD);
 		sk->sk_shutdown |= SHUTDOWN_MASK;
 	}
+	sk->sk_prot->unhash(sk);
 	if (smc->clcsock) {
 		struct socket *tcp;
 
@@ -971,7 +989,6 @@ void smc_close_non_accepted(struct sock *sk)
 			smc_conn_free(&smc->conn);
 	}
 	release_sock(sk);
-	sk->sk_prot->unhash(sk);
 	sock_put(sk); /* final sock_put */
 }
 
@@ -1037,13 +1054,13 @@ static void smc_listen_out(struct smc_sock *new_smc)
 	struct smc_sock *lsmc = new_smc->listen_smc;
 	struct sock *newsmcsk = &new_smc->sk;
 
-	lock_sock_nested(&lsmc->sk, SINGLE_DEPTH_NESTING);
 	if (lsmc->sk.sk_state == SMC_LISTEN) {
+		lock_sock_nested(&lsmc->sk, SINGLE_DEPTH_NESTING);
 		smc_accept_enqueue(&lsmc->sk, newsmcsk);
+		release_sock(&lsmc->sk);
 	} else { /* no longer listening */
 		smc_close_non_accepted(newsmcsk);
 	}
-	release_sock(&lsmc->sk);
 
 	/* Wake up accept */
 	lsmc->sk.sk_data_ready(&lsmc->sk);
@@ -1087,7 +1104,7 @@ static void smc_listen_decline(struct smc_sock *new_smc, int reason_code,
 		return;
 	}
 	smc_conn_free(&new_smc->conn);
-	new_smc->use_fallback = true;
+	smc_switch_to_fallback(new_smc);
 	new_smc->fallback_rsn = reason_code;
 	if (reason_code && reason_code != SMC_CLC_DECL_PEERDECL) {
 		if (smc_clc_send_decline(new_smc, reason_code) < 0) {
@@ -1237,6 +1254,9 @@ static void smc_listen_work(struct work_struct *work)
 	int rc = 0;
 	u8 ibport;
 
+	if (new_smc->listen_smc->sk.sk_state != SMC_LISTEN)
+		return smc_listen_out_err(new_smc);
+
 	if (new_smc->use_fallback) {
 		smc_listen_out_connected(new_smc);
 		return;
@@ -1244,7 +1264,7 @@ static void smc_listen_work(struct work_struct *work)
 
 	/* check if peer is smc capable */
 	if (!tcp_sk(newclcsock->sk)->syn_smc) {
-		new_smc->use_fallback = true;
+		smc_switch_to_fallback(new_smc);
 		new_smc->fallback_rsn = SMC_CLC_DECL_PEERNOSMC;
 		smc_listen_out_connected(new_smc);
 		return;
@@ -1501,7 +1521,7 @@ static int smc_sendmsg(struct socket *sock, struct msghdr *msg, size_t len)
 
 	if (msg->msg_flags & MSG_FASTOPEN) {
 		if (sk->sk_state == SMC_INIT) {
-			smc->use_fallback = true;
+			smc_switch_to_fallback(smc);
 			smc->fallback_rsn = SMC_CLC_DECL_OPTUNSUPP;
 		} else {
 			rc = -EINVAL;
@@ -1703,7 +1723,7 @@ static int smc_setsockopt(struct socket *sock, int level, int optname,
 	case TCP_FASTOPEN_NO_COOKIE:
 		/* option not supported by SMC */
 		if (sk->sk_state == SMC_INIT) {
-			smc->use_fallback = true;
+			smc_switch_to_fallback(smc);
 			smc->fallback_rsn = SMC_CLC_DECL_OPTUNSUPP;
 		} else {
 			if (!smc->use_fallback)
diff --git a/net/smc/smc_close.c b/net/smc/smc_close.c
index 2ad37e998509..fc06720b53c1 100644
--- a/net/smc/smc_close.c
+++ b/net/smc/smc_close.c
@@ -21,6 +21,22 @@
 
 #define SMC_CLOSE_WAIT_LISTEN_CLCSOCK_TIME	(5 * HZ)
 
+/* release the clcsock that is assigned to the smc_sock */
+void smc_clcsock_release(struct smc_sock *smc)
+{
+	struct socket *tcp;
+
+	if (smc->listen_smc && current_work() != &smc->smc_listen_work)
+		cancel_work_sync(&smc->smc_listen_work);
+	mutex_lock(&smc->clcsock_release_lock);
+	if (smc->clcsock) {
+		tcp = smc->clcsock;
+		smc->clcsock = NULL;
+		sock_release(tcp);
+	}
+	mutex_unlock(&smc->clcsock_release_lock);
+}
+
 static void smc_close_cleanup_listen(struct sock *parent)
 {
 	struct sock *sk;
@@ -321,6 +337,7 @@ static void smc_close_passive_work(struct work_struct *work)
 						   close_work);
 	struct smc_sock *smc = container_of(conn, struct smc_sock, conn);
 	struct smc_cdc_conn_state_flags *rxflags;
+	bool release_clcsock = false;
 	struct sock *sk = &smc->sk;
 	int old_state;
 
@@ -400,13 +417,13 @@ wakeup:
 		if ((sk->sk_state == SMC_CLOSED) &&
 		    (sock_flag(sk, SOCK_DEAD) || !sk->sk_socket)) {
 			smc_conn_free(conn);
-			if (smc->clcsock) {
-				sock_release(smc->clcsock);
-				smc->clcsock = NULL;
-			}
+			if (smc->clcsock)
+				release_clcsock = true;
 		}
 	}
 	release_sock(sk);
+	if (release_clcsock)
+		smc_clcsock_release(smc);
 	sock_put(sk); /* sock_hold done by schedulers of close_work */
 }
 
diff --git a/net/smc/smc_close.h b/net/smc/smc_close.h
index 19eb6a211c23..e0e3b5df25d2 100644
--- a/net/smc/smc_close.h
+++ b/net/smc/smc_close.h
@@ -23,5 +23,6 @@ void smc_close_wake_tx_prepared(struct smc_sock *smc);
 int smc_close_active(struct smc_sock *smc);
 int smc_close_shutdown_write(struct smc_sock *smc);
 void smc_close_init(struct smc_sock *smc);
+void smc_clcsock_release(struct smc_sock *smc);
 
 #endif /* SMC_CLOSE_H */
diff --git a/net/smc/smc_ism.c b/net/smc/smc_ism.c
index 2fff79db1a59..e89e918b88e0 100644
--- a/net/smc/smc_ism.c
+++ b/net/smc/smc_ism.c
@@ -289,6 +289,11 @@ struct smcd_dev *smcd_alloc_dev(struct device *parent, const char *name,
 	INIT_LIST_HEAD(&smcd->vlan);
 	smcd->event_wq = alloc_ordered_workqueue("ism_evt_wq-%s)",
 						 WQ_MEM_RECLAIM, name);
+	if (!smcd->event_wq) {
+		kfree(smcd->conn);
+		kfree(smcd);
+		return NULL;
+	}
 	return smcd;
 }
 EXPORT_SYMBOL_GPL(smcd_alloc_dev);
diff --git a/net/smc/smc_pnet.c b/net/smc/smc_pnet.c
index 8d2f6296279c..0285c7f9e79b 100644
--- a/net/smc/smc_pnet.c
+++ b/net/smc/smc_pnet.c
@@ -603,7 +603,8 @@ static int smc_pnet_flush(struct sk_buff *skb, struct genl_info *info)
 {
 	struct net *net = genl_info_net(info);
 
-	return smc_pnet_remove_by_pnetid(net, NULL);
+	smc_pnet_remove_by_pnetid(net, NULL);
+	return 0;
 }
 
 /* SMC_PNETID generic netlink operation definition */
diff --git a/net/socket.c b/net/socket.c
index 3c176a12fe48..8255f5bda0aa 100644
--- a/net/socket.c
+++ b/net/socket.c
@@ -384,6 +384,18 @@ static struct file_system_type sock_fs_type = {
  *	but we take care of internal coherence yet.
  */
 
+/**
+ *	sock_alloc_file - Bind a &socket to a &file
+ *	@sock: socket
+ *	@flags: file status flags
+ *	@dname: protocol name
+ *
+ *	Returns the &file bound with @sock, implicitly storing it
+ *	in sock->file. If dname is %NULL, sets to "".
+ *	On failure the return is a ERR pointer (see linux/err.h).
+ *	This function uses GFP_KERNEL internally.
+ */
+
 struct file *sock_alloc_file(struct socket *sock, int flags, const char *dname)
 {
 	struct file *file;
@@ -424,6 +436,14 @@ static int sock_map_fd(struct socket *sock, int flags)
 	return PTR_ERR(newfile);
 }
 
+/**
+ *	sock_from_file - Return the &socket bounded to @file.
+ *	@file: file
+ *	@err: pointer to an error code return
+ *
+ *	On failure returns %NULL and assigns -ENOTSOCK to @err.
+ */
+
 struct socket *sock_from_file(struct file *file, int *err)
 {
 	if (file->f_op == &socket_file_ops)
@@ -532,11 +552,11 @@ static const struct inode_operations sockfs_inode_ops = {
 };
 
 /**
- *	sock_alloc	-	allocate a socket
+ *	sock_alloc - allocate a socket
  *
  *	Allocate a new inode and socket object. The two are bound together
  *	and initialised. The socket is then returned. If we are out of inodes
- *	NULL is returned.
+ *	NULL is returned. This functions uses GFP_KERNEL internally.
  */
 
 struct socket *sock_alloc(void)
@@ -561,7 +581,7 @@ struct socket *sock_alloc(void)
 EXPORT_SYMBOL(sock_alloc);
 
 /**
- *	sock_release	-	close a socket
+ *	sock_release - close a socket
  *	@sock: socket to close
  *
  *	The socket is released from the protocol stack if it has a release
@@ -617,6 +637,15 @@ void __sock_tx_timestamp(__u16 tsflags, __u8 *tx_flags)
 }
 EXPORT_SYMBOL(__sock_tx_timestamp);
 
+/**
+ *	sock_sendmsg - send a message through @sock
+ *	@sock: socket
+ *	@msg: message to send
+ *
+ *	Sends @msg through @sock, passing through LSM.
+ *	Returns the number of bytes sent, or an error code.
+ */
+
 static inline int sock_sendmsg_nosec(struct socket *sock, struct msghdr *msg)
 {
 	int ret = sock->ops->sendmsg(sock, msg, msg_data_left(msg));
@@ -633,6 +662,18 @@ int sock_sendmsg(struct socket *sock, struct msghdr *msg)
 }
 EXPORT_SYMBOL(sock_sendmsg);
 
+/**
+ *	kernel_sendmsg - send a message through @sock (kernel-space)
+ *	@sock: socket
+ *	@msg: message header
+ *	@vec: kernel vec
+ *	@num: vec array length
+ *	@size: total message data size
+ *
+ *	Builds the message data with @vec and sends it through @sock.
+ *	Returns the number of bytes sent, or an error code.
+ */
+
 int kernel_sendmsg(struct socket *sock, struct msghdr *msg,
 		   struct kvec *vec, size_t num, size_t size)
 {
@@ -641,6 +682,19 @@ int kernel_sendmsg(struct socket *sock, struct msghdr *msg,
 }
 EXPORT_SYMBOL(kernel_sendmsg);
 
+/**
+ *	kernel_sendmsg_locked - send a message through @sock (kernel-space)
+ *	@sk: sock
+ *	@msg: message header
+ *	@vec: output s/g array
+ *	@num: output s/g array length
+ *	@size: total message data size
+ *
+ *	Builds the message data with @vec and sends it through @sock.
+ *	Returns the number of bytes sent, or an error code.
+ *	Caller must hold @sk.
+ */
+
 int kernel_sendmsg_locked(struct sock *sk, struct msghdr *msg,
 			  struct kvec *vec, size_t num, size_t size)
 {
@@ -811,6 +865,16 @@ void __sock_recv_ts_and_drops(struct msghdr *msg, struct sock *sk,
 }
 EXPORT_SYMBOL_GPL(__sock_recv_ts_and_drops);
 
+/**
+ *	sock_recvmsg - receive a message from @sock
+ *	@sock: socket
+ *	@msg: message to receive
+ *	@flags: message flags
+ *
+ *	Receives @msg from @sock, passing through LSM. Returns the total number
+ *	of bytes received, or an error.
+ */
+
 static inline int sock_recvmsg_nosec(struct socket *sock, struct msghdr *msg,
 				     int flags)
 {
@@ -826,20 +890,21 @@ int sock_recvmsg(struct socket *sock, struct msghdr *msg, int flags)
 EXPORT_SYMBOL(sock_recvmsg);
 
 /**
- * kernel_recvmsg - Receive a message from a socket (kernel space)
- * @sock:       The socket to receive the message from
- * @msg:        Received message
- * @vec:        Input s/g array for message data
- * @num:        Size of input s/g array
- * @size:       Number of bytes to read
- * @flags:      Message flags (MSG_DONTWAIT, etc...)
+ *	kernel_recvmsg - Receive a message from a socket (kernel space)
+ *	@sock: The socket to receive the message from
+ *	@msg: Received message
+ *	@vec: Input s/g array for message data
+ *	@num: Size of input s/g array
+ *	@size: Number of bytes to read
+ *	@flags: Message flags (MSG_DONTWAIT, etc...)
  *
- * On return the msg structure contains the scatter/gather array passed in the
- * vec argument. The array is modified so that it consists of the unfilled
- * portion of the original array.
+ *	On return the msg structure contains the scatter/gather array passed in the
+ *	vec argument. The array is modified so that it consists of the unfilled
+ *	portion of the original array.
  *
- * The returned value is the total number of bytes received, or an error.
+ *	The returned value is the total number of bytes received, or an error.
  */
+
 int kernel_recvmsg(struct socket *sock, struct msghdr *msg,
 		   struct kvec *vec, size_t num, size_t size, int flags)
 {
@@ -1005,6 +1070,13 @@ static long sock_do_ioctl(struct net *net, struct socket *sock,
  *	what to do with it - that's up to the protocol still.
  */
 
+/**
+ *	get_net_ns - increment the refcount of the network namespace
+ *	@ns: common namespace (net)
+ *
+ *	Returns the net's common namespace.
+ */
+
 struct ns_common *get_net_ns(struct ns_common *ns)
 {
 	return &get_net(container_of(ns, struct net, ns))->ns;
@@ -1099,6 +1171,19 @@ static long sock_ioctl(struct file *file, unsigned cmd, unsigned long arg)
 	return err;
 }
 
+/**
+ *	sock_create_lite - creates a socket
+ *	@family: protocol family (AF_INET, ...)
+ *	@type: communication type (SOCK_STREAM, ...)
+ *	@protocol: protocol (0, ...)
+ *	@res: new socket
+ *
+ *	Creates a new socket and assigns it to @res, passing through LSM.
+ *	The new socket initialization is not complete, see kernel_accept().
+ *	Returns 0 or an error. On failure @res is set to %NULL.
+ *	This function internally uses GFP_KERNEL.
+ */
+
 int sock_create_lite(int family, int type, int protocol, struct socket **res)
 {
 	int err;
@@ -1224,6 +1309,21 @@ call_kill:
 }
 EXPORT_SYMBOL(sock_wake_async);
 
+/**
+ *	__sock_create - creates a socket
+ *	@net: net namespace
+ *	@family: protocol family (AF_INET, ...)
+ *	@type: communication type (SOCK_STREAM, ...)
+ *	@protocol: protocol (0, ...)
+ *	@res: new socket
+ *	@kern: boolean for kernel space sockets
+ *
+ *	Creates a new socket and assigns it to @res, passing through LSM.
+ *	Returns 0 or an error. On failure @res is set to %NULL. @kern must
+ *	be set to true if the socket resides in kernel space.
+ *	This function internally uses GFP_KERNEL.
+ */
+
 int __sock_create(struct net *net, int family, int type, int protocol,
 			 struct socket **res, int kern)
 {
@@ -1333,12 +1433,35 @@ out_release:
 }
 EXPORT_SYMBOL(__sock_create);
 
+/**
+ *	sock_create - creates a socket
+ *	@family: protocol family (AF_INET, ...)
+ *	@type: communication type (SOCK_STREAM, ...)
+ *	@protocol: protocol (0, ...)
+ *	@res: new socket
+ *
+ *	A wrapper around __sock_create().
+ *	Returns 0 or an error. This function internally uses GFP_KERNEL.
+ */
+
 int sock_create(int family, int type, int protocol, struct socket **res)
 {
 	return __sock_create(current->nsproxy->net_ns, family, type, protocol, res, 0);
 }
 EXPORT_SYMBOL(sock_create);
 
+/**
+ *	sock_create_kern - creates a socket (kernel space)
+ *	@net: net namespace
+ *	@family: protocol family (AF_INET, ...)
+ *	@type: communication type (SOCK_STREAM, ...)
+ *	@protocol: protocol (0, ...)
+ *	@res: new socket
+ *
+ *	A wrapper around __sock_create().
+ *	Returns 0 or an error. This function internally uses GFP_KERNEL.
+ */
+
 int sock_create_kern(struct net *net, int family, int type, int protocol, struct socket **res)
 {
 	return __sock_create(net, family, type, protocol, res, 1);
@@ -3322,18 +3445,46 @@ static long compat_sock_ioctl(struct file *file, unsigned int cmd,
 }
 #endif
 
+/**
+ *	kernel_bind - bind an address to a socket (kernel space)
+ *	@sock: socket
+ *	@addr: address
+ *	@addrlen: length of address
+ *
+ *	Returns 0 or an error.
+ */
+
 int kernel_bind(struct socket *sock, struct sockaddr *addr, int addrlen)
 {
 	return sock->ops->bind(sock, addr, addrlen);
 }
 EXPORT_SYMBOL(kernel_bind);
 
+/**
+ *	kernel_listen - move socket to listening state (kernel space)
+ *	@sock: socket
+ *	@backlog: pending connections queue size
+ *
+ *	Returns 0 or an error.
+ */
+
 int kernel_listen(struct socket *sock, int backlog)
 {
 	return sock->ops->listen(sock, backlog);
 }
 EXPORT_SYMBOL(kernel_listen);
 
+/**
+ *	kernel_accept - accept a connection (kernel space)
+ *	@sock: listening socket
+ *	@newsock: new connected socket
+ *	@flags: flags
+ *
+ *	@flags must be SOCK_CLOEXEC, SOCK_NONBLOCK or 0.
+ *	If it fails, @newsock is guaranteed to be %NULL.
+ *	Returns 0 or an error.
+ */
+
 int kernel_accept(struct socket *sock, struct socket **newsock, int flags)
 {
 	struct sock *sk = sock->sk;
@@ -3359,6 +3510,19 @@ done:
 }
 EXPORT_SYMBOL(kernel_accept);
 
+/**
+ *	kernel_connect - connect a socket (kernel space)
+ *	@sock: socket
+ *	@addr: address
+ *	@addrlen: address length
+ *	@flags: flags (O_NONBLOCK, ...)
+ *
+ *	For datagram sockets, @addr is the addres to which datagrams are sent
+ *	by default, and the only address from which datagrams are received.
+ *	For stream sockets, attempts to connect to @addr.
+ *	Returns 0 or an error code.
+ */
+
 int kernel_connect(struct socket *sock, struct sockaddr *addr, int addrlen,
 		   int flags)
 {
@@ -3366,18 +3530,48 @@ int kernel_connect(struct socket *sock, struct sockaddr *addr, int addrlen,
 }
 EXPORT_SYMBOL(kernel_connect);
 
+/**
+ *	kernel_getsockname - get the address which the socket is bound (kernel space)
+ *	@sock: socket
+ *	@addr: address holder
+ *
+ * 	Fills the @addr pointer with the address which the socket is bound.
+ *	Returns 0 or an error code.
+ */
+
 int kernel_getsockname(struct socket *sock, struct sockaddr *addr)
 {
 	return sock->ops->getname(sock, addr, 0);
 }
 EXPORT_SYMBOL(kernel_getsockname);
 
+/**
+ *	kernel_peername - get the address which the socket is connected (kernel space)
+ *	@sock: socket
+ *	@addr: address holder
+ *
+ * 	Fills the @addr pointer with the address which the socket is connected.
+ *	Returns 0 or an error code.
+ */
+
 int kernel_getpeername(struct socket *sock, struct sockaddr *addr)
 {
 	return sock->ops->getname(sock, addr, 1);
 }
 EXPORT_SYMBOL(kernel_getpeername);
 
+/**
+ *	kernel_getsockopt - get a socket option (kernel space)
+ *	@sock: socket
+ *	@level: API level (SOL_SOCKET, ...)
+ *	@optname: option tag
+ *	@optval: option value
+ *	@optlen: option length
+ *
+ *	Assigns the option length to @optlen.
+ *	Returns 0 or an error.
+ */
+
 int kernel_getsockopt(struct socket *sock, int level, int optname,
 			char *optval, int *optlen)
 {
@@ -3400,6 +3594,17 @@ int kernel_getsockopt(struct socket *sock, int level, int optname,
 }
 EXPORT_SYMBOL(kernel_getsockopt);
 
+/**
+ *	kernel_setsockopt - set a socket option (kernel space)
+ *	@sock: socket
+ *	@level: API level (SOL_SOCKET, ...)
+ *	@optname: option tag
+ *	@optval: option value
+ *	@optlen: option length
+ *
+ *	Returns 0 or an error.
+ */
+
 int kernel_setsockopt(struct socket *sock, int level, int optname,
 			char *optval, unsigned int optlen)
 {
@@ -3420,6 +3625,17 @@ int kernel_setsockopt(struct socket *sock, int level, int optname,
 }
 EXPORT_SYMBOL(kernel_setsockopt);
 
+/**
+ *	kernel_sendpage - send a &page through a socket (kernel space)
+ *	@sock: socket
+ *	@page: page
+ *	@offset: page offset
+ *	@size: total size in bytes
+ *	@flags: flags (MSG_DONTWAIT, ...)
+ *
+ *	Returns the total amount sent in bytes or an error.
+ */
+
 int kernel_sendpage(struct socket *sock, struct page *page, int offset,
 		    size_t size, int flags)
 {
@@ -3430,6 +3646,18 @@ int kernel_sendpage(struct socket *sock, struct page *page, int offset,
 }
 EXPORT_SYMBOL(kernel_sendpage);
 
+/**
+ *	kernel_sendpage_locked - send a &page through the locked sock (kernel space)
+ *	@sk: sock
+ *	@page: page
+ *	@offset: page offset
+ *	@size: total size in bytes
+ *	@flags: flags (MSG_DONTWAIT, ...)
+ *
+ *	Returns the total amount sent in bytes or an error.
+ *	Caller must hold @sk.
+ */
+
 int kernel_sendpage_locked(struct sock *sk, struct page *page, int offset,
 			   size_t size, int flags)
 {
@@ -3443,17 +3671,30 @@ int kernel_sendpage_locked(struct sock *sk, struct page *page, int offset,
 }
 EXPORT_SYMBOL(kernel_sendpage_locked);
 
+/**
+ *	kernel_shutdown - shut down part of a full-duplex connection (kernel space)
+ *	@sock: socket
+ *	@how: connection part
+ *
+ *	Returns 0 or an error.
+ */
+
 int kernel_sock_shutdown(struct socket *sock, enum sock_shutdown_cmd how)
 {
 	return sock->ops->shutdown(sock, how);
 }
 EXPORT_SYMBOL(kernel_sock_shutdown);
 
-/* This routine returns the IP overhead imposed by a socket i.e.
- * the length of the underlying IP header, depending on whether
- * this is an IPv4 or IPv6 socket and the length from IP options turned
- * on at the socket. Assumes that the caller has a lock on the socket.
+/**
+ *	kernel_sock_ip_overhead - returns the IP overhead imposed by a socket
+ *	@sk: socket
+ *
+ *	This routine returns the IP overhead imposed by a socket i.e.
+ *	the length of the underlying IP header, depending on whether
+ *	this is an IPv4 or IPv6 socket and the length from IP options turned
+ *	on at the socket. Assumes that the caller has a lock on the socket.
  */
+
 u32 kernel_sock_ip_overhead(struct sock *sk)
 {
 	struct inet_sock *inet;
diff --git a/net/strparser/strparser.c b/net/strparser/strparser.c
index da1a676860ca..fa6c977b4c41 100644
--- a/net/strparser/strparser.c
+++ b/net/strparser/strparser.c
@@ -140,13 +140,11 @@ static int __strp_recv(read_descriptor_t *desc, struct sk_buff *orig_skb,
 			/* We are going to append to the frags_list of head.
 			 * Need to unshare the frag_list.
 			 */
-			if (skb_has_frag_list(head)) {
-				err = skb_unclone(head, GFP_ATOMIC);
-				if (err) {
-					STRP_STATS_INCR(strp->stats.mem_fail);
-					desc->error = err;
-					return 0;
-				}
+			err = skb_unclone(head, GFP_ATOMIC);
+			if (err) {
+				STRP_STATS_INCR(strp->stats.mem_fail);
+				desc->error = err;
+				return 0;
 			}
 
 			if (unlikely(skb_shinfo(head)->frag_list)) {
@@ -550,6 +548,8 @@ EXPORT_SYMBOL_GPL(strp_check_rcv);
 static int __init strp_mod_init(void)
 {
 	strp_wq = create_singlethread_workqueue("kstrp");
+	if (unlikely(!strp_wq))
+		return -ENOMEM;
 
 	return 0;
 }
diff --git a/net/sunrpc/auth_gss/gss_krb5_crypto.c b/net/sunrpc/auth_gss/gss_krb5_crypto.c
index 4f43383971ba..6f2d30d7b766 100644
--- a/net/sunrpc/auth_gss/gss_krb5_crypto.c
+++ b/net/sunrpc/auth_gss/gss_krb5_crypto.c
@@ -977,7 +977,6 @@ krb5_rc4_setup_seq_key(struct krb5_ctx *kctx,
 	}
 
 	desc->tfm = hmac;
-	desc->flags = 0;
 
 	/* Compute intermediate Kseq from session key */
 	err = crypto_shash_setkey(hmac, kctx->Ksess, kctx->gk5e->keylength);
@@ -1045,7 +1044,6 @@ krb5_rc4_setup_enc_key(struct krb5_ctx *kctx,
 	}
 
 	desc->tfm = hmac;
-	desc->flags = 0;
 
 	/* Compute intermediate Kcrypt from session key */
 	for (i = 0; i < kctx->gk5e->keylength; i++)
diff --git a/net/sunrpc/auth_gss/gss_krb5_mech.c b/net/sunrpc/auth_gss/gss_krb5_mech.c
index 56cc85c5bc06..6e5d6d240215 100644
--- a/net/sunrpc/auth_gss/gss_krb5_mech.c
+++ b/net/sunrpc/auth_gss/gss_krb5_mech.c
@@ -438,7 +438,6 @@ context_derive_keys_rc4(struct krb5_ctx *ctx)
 	}
 
 	desc->tfm = hmac;
-	desc->flags = 0;
 
 	err = crypto_shash_digest(desc, sigkeyconstant, slen, ctx->cksum);
 	kzfree(desc);
diff --git a/net/sunrpc/cache.c b/net/sunrpc/cache.c
index 12bb23b8e0c5..261131dfa1f1 100644
--- a/net/sunrpc/cache.c
+++ b/net/sunrpc/cache.c
@@ -54,6 +54,7 @@ static void cache_init(struct cache_head *h, struct cache_detail *detail)
 	h->last_refresh = now;
 }
 
+static inline int cache_is_valid(struct cache_head *h);
 static void cache_fresh_locked(struct cache_head *head, time_t expiry,
 				struct cache_detail *detail);
 static void cache_fresh_unlocked(struct cache_head *head,
@@ -105,6 +106,8 @@ static struct cache_head *sunrpc_cache_add_entry(struct cache_detail *detail,
 			if (cache_is_expired(detail, tmp)) {
 				hlist_del_init_rcu(&tmp->cache_list);
 				detail->entries --;
+				if (cache_is_valid(tmp) == -EAGAIN)
+					set_bit(CACHE_NEGATIVE, &tmp->flags);
 				cache_fresh_locked(tmp, 0, detail);
 				freeme = tmp;
 				break;
diff --git a/net/sunrpc/clnt.c b/net/sunrpc/clnt.c
index 228970e6e52b..8ff11dc98d7f 100644
--- a/net/sunrpc/clnt.c
+++ b/net/sunrpc/clnt.c
@@ -1540,7 +1540,6 @@ call_start(struct rpc_task *task)
 	clnt->cl_stats->rpccnt++;
 	task->tk_action = call_reserve;
 	rpc_task_set_transport(task, clnt);
-	call_reserve(task);
 }
 
 /*
@@ -1554,9 +1553,6 @@ call_reserve(struct rpc_task *task)
 	task->tk_status  = 0;
 	task->tk_action  = call_reserveresult;
 	xprt_reserve(task);
-	if (rpc_task_need_resched(task))
-		return;
-	 call_reserveresult(task);
 }
 
 static void call_retry_reserve(struct rpc_task *task);
@@ -1579,7 +1575,6 @@ call_reserveresult(struct rpc_task *task)
 	if (status >= 0) {
 		if (task->tk_rqstp) {
 			task->tk_action = call_refresh;
-			call_refresh(task);
 			return;
 		}
 
@@ -1605,7 +1600,6 @@ call_reserveresult(struct rpc_task *task)
 		/* fall through */
 	case -EAGAIN:	/* woken up; retry */
 		task->tk_action = call_retry_reserve;
-		call_retry_reserve(task);
 		return;
 	case -EIO:	/* probably a shutdown */
 		break;
@@ -1628,9 +1622,6 @@ call_retry_reserve(struct rpc_task *task)
 	task->tk_status  = 0;
 	task->tk_action  = call_reserveresult;
 	xprt_retry_reserve(task);
-	if (rpc_task_need_resched(task))
-		return;
-	call_reserveresult(task);
 }
 
 /*
@@ -1645,9 +1636,6 @@ call_refresh(struct rpc_task *task)
 	task->tk_status = 0;
 	task->tk_client->cl_stats->rpcauthrefresh++;
 	rpcauth_refreshcred(task);
-	if (rpc_task_need_resched(task))
-		return;
-	call_refreshresult(task);
 }
 
 /*
@@ -1666,7 +1654,6 @@ call_refreshresult(struct rpc_task *task)
 	case 0:
 		if (rpcauth_uptodatecred(task)) {
 			task->tk_action = call_allocate;
-			call_allocate(task);
 			return;
 		}
 		/* Use rate-limiting and a max number of retries if refresh
@@ -1685,7 +1672,6 @@ call_refreshresult(struct rpc_task *task)
 		task->tk_cred_retry--;
 		dprintk("RPC: %5u %s: retry refresh creds\n",
 				task->tk_pid, __func__);
-		call_refresh(task);
 		return;
 	}
 	dprintk("RPC: %5u %s: refresh creds failed with error %d\n",
@@ -1711,10 +1697,8 @@ call_allocate(struct rpc_task *task)
 	task->tk_status = 0;
 	task->tk_action = call_encode;
 
-	if (req->rq_buffer) {
-		call_encode(task);
+	if (req->rq_buffer)
 		return;
-	}
 
 	if (proc->p_proc != 0) {
 		BUG_ON(proc->p_arglen == 0);
@@ -1740,12 +1724,8 @@ call_allocate(struct rpc_task *task)
 
 	status = xprt->ops->buf_alloc(task);
 	xprt_inject_disconnect(xprt);
-	if (status == 0) {
-		if (rpc_task_need_resched(task))
-			return;
-		call_encode(task);
+	if (status == 0)
 		return;
-	}
 	if (status != -ENOMEM) {
 		rpc_exit(task, status);
 		return;
@@ -1828,8 +1808,12 @@ call_encode(struct rpc_task *task)
 		xprt_request_enqueue_receive(task);
 	xprt_request_enqueue_transmit(task);
 out:
-	task->tk_action = call_bind;
-	call_bind(task);
+	task->tk_action = call_transmit;
+	/* Check that the connection is OK */
+	if (!xprt_bound(task->tk_xprt))
+		task->tk_action = call_bind;
+	else if (!xprt_connected(task->tk_xprt))
+		task->tk_action = call_connect;
 }
 
 /*
@@ -1847,7 +1831,6 @@ rpc_task_handle_transmitted(struct rpc_task *task)
 {
 	xprt_end_transmit(task);
 	task->tk_action = call_transmit_status;
-	call_transmit_status(task);
 }
 
 /*
@@ -1865,7 +1848,6 @@ call_bind(struct rpc_task *task)
 
 	if (xprt_bound(xprt)) {
 		task->tk_action = call_connect;
-		call_connect(task);
 		return;
 	}
 
@@ -1896,7 +1878,6 @@ call_bind_status(struct rpc_task *task)
 		dprint_status(task);
 		task->tk_status = 0;
 		task->tk_action = call_connect;
-		call_connect(task);
 		return;
 	}
 
@@ -1981,7 +1962,6 @@ call_connect(struct rpc_task *task)
 
 	if (xprt_connected(xprt)) {
 		task->tk_action = call_transmit;
-		call_transmit(task);
 		return;
 	}
 
@@ -2051,7 +2031,6 @@ call_connect_status(struct rpc_task *task)
 	case 0:
 		clnt->cl_stats->netreconn++;
 		task->tk_action = call_transmit;
-		call_transmit(task);
 		return;
 	}
 	rpc_exit(task, status);
@@ -2087,9 +2066,6 @@ call_transmit(struct rpc_task *task)
 		xprt_transmit(task);
 	}
 	xprt_end_transmit(task);
-	if (rpc_task_need_resched(task))
-		return;
-	call_transmit_status(task);
 }
 
 /*
@@ -2105,11 +2081,8 @@ call_transmit_status(struct rpc_task *task)
 	 * test first.
 	 */
 	if (rpc_task_transmitted(task)) {
-		if (task->tk_status == 0)
-			xprt_request_wait_receive(task);
-		if (rpc_task_need_resched(task))
-			return;
-		call_status(task);
+		task->tk_status = 0;
+		xprt_request_wait_receive(task);
 		return;
 	}
 
@@ -2170,7 +2143,6 @@ call_bc_encode(struct rpc_task *task)
 {
 	xprt_request_enqueue_transmit(task);
 	task->tk_action = call_bc_transmit;
-	call_bc_transmit(task);
 }
 
 /*
@@ -2195,6 +2167,9 @@ call_bc_transmit_status(struct rpc_task *task)
 {
 	struct rpc_rqst *req = task->tk_rqstp;
 
+	if (rpc_task_transmitted(task))
+		task->tk_status = 0;
+
 	dprint_status(task);
 
 	switch (task->tk_status) {
@@ -2261,7 +2236,6 @@ call_status(struct rpc_task *task)
 	status = task->tk_status;
 	if (status >= 0) {
 		task->tk_action = call_decode;
-		call_decode(task);
 		return;
 	}
 
@@ -2311,6 +2285,15 @@ out_exit:
 	rpc_exit(task, status);
 }
 
+static bool
+rpc_check_connected(const struct rpc_rqst *req)
+{
+	/* No allocated request or transport? return true */
+	if (!req || !req->rq_xprt)
+		return true;
+	return xprt_connected(req->rq_xprt);
+}
+
 static void
 rpc_check_timeout(struct rpc_task *task)
 {
@@ -2322,10 +2305,11 @@ rpc_check_timeout(struct rpc_task *task)
 	dprintk("RPC: %5u call_timeout (major)\n", task->tk_pid);
 	task->tk_timeouts++;
 
-	if (RPC_IS_SOFTCONN(task)) {
+	if (RPC_IS_SOFTCONN(task) && !rpc_check_connected(task->tk_rqstp)) {
 		rpc_exit(task, -ETIMEDOUT);
 		return;
 	}
+
 	if (RPC_IS_SOFT(task)) {
 		if (clnt->cl_chatty) {
 			printk(KERN_NOTICE "%s: server %s not responding, timed out\n",
diff --git a/net/sunrpc/xprtrdma/verbs.c b/net/sunrpc/xprtrdma/verbs.c
index 89a63391d4d4..30cfc0efe699 100644
--- a/net/sunrpc/xprtrdma/verbs.c
+++ b/net/sunrpc/xprtrdma/verbs.c
@@ -90,7 +90,7 @@ static void rpcrdma_xprt_drain(struct rpcrdma_xprt *r_xprt)
 	/* Flush Receives, then wait for deferred Reply work
 	 * to complete.
 	 */
-	ib_drain_qp(ia->ri_id->qp);
+	ib_drain_rq(ia->ri_id->qp);
 	drain_workqueue(buf->rb_completion_wq);
 
 	/* Deferred Reply processing might have scheduled
diff --git a/net/sunrpc/xprtsock.c b/net/sunrpc/xprtsock.c
index 9359539907ba..732d4b57411a 100644
--- a/net/sunrpc/xprtsock.c
+++ b/net/sunrpc/xprtsock.c
@@ -495,8 +495,8 @@ xs_read_stream_request(struct sock_xprt *transport, struct msghdr *msg,
 		int flags, struct rpc_rqst *req)
 {
 	struct xdr_buf *buf = &req->rq_private_buf;
-	size_t want, read;
-	ssize_t ret;
+	size_t want, uninitialized_var(read);
+	ssize_t uninitialized_var(ret);
 
 	xs_read_header(transport, buf);
 
diff --git a/net/tipc/group.c b/net/tipc/group.c
index 06fee142f09f..63f39201e41e 100644
--- a/net/tipc/group.c
+++ b/net/tipc/group.c
@@ -919,6 +919,9 @@ int tipc_group_fill_sock_diag(struct tipc_group *grp, struct sk_buff *skb)
 {
 	struct nlattr *group = nla_nest_start(skb, TIPC_NLA_SOCK_GROUP);
 
+	if (!group)
+		return -EMSGSIZE;
+
 	if (nla_put_u32(skb, TIPC_NLA_SOCK_GROUP_ID,
 			grp->type) ||
 	    nla_put_u32(skb, TIPC_NLA_SOCK_GROUP_INSTANCE,
diff --git a/net/tipc/link.c b/net/tipc/link.c
index 341ecd796aa4..131aa2f0fd27 100644
--- a/net/tipc/link.c
+++ b/net/tipc/link.c
@@ -869,6 +869,8 @@ void tipc_link_reset(struct tipc_link *l)
 	__skb_queue_head_init(&list);
 
 	l->in_session = false;
+	/* Force re-synch of peer session number before establishing */
+	l->peer_session--;
 	l->session++;
 	l->mtu = l->advertised_mtu;
 
diff --git a/net/tipc/name_table.c b/net/tipc/name_table.c
index bff241f03525..89993afe0fbd 100644
--- a/net/tipc/name_table.c
+++ b/net/tipc/name_table.c
@@ -909,7 +909,8 @@ static int tipc_nl_service_list(struct net *net, struct tipc_nl_msg *msg,
 	for (; i < TIPC_NAMETBL_SIZE; i++) {
 		head = &tn->nametbl->services[i];
 
-		if (*last_type) {
+		if (*last_type ||
+		    (!i && *last_key && (*last_lower == *last_key))) {
 			service = tipc_service_find(net, *last_type);
 			if (!service)
 				return -EPIPE;
diff --git a/net/tipc/net.c b/net/tipc/net.c
index f076edb74338..7ce1e86b024f 100644
--- a/net/tipc/net.c
+++ b/net/tipc/net.c
@@ -163,12 +163,9 @@ void tipc_sched_net_finalize(struct net *net, u32 addr)
 
 void tipc_net_stop(struct net *net)
 {
-	u32 self = tipc_own_addr(net);
-
-	if (!self)
+	if (!tipc_own_id(net))
 		return;
 
-	tipc_nametbl_withdraw(net, TIPC_CFG_SRV, self, self, self);
 	rtnl_lock();
 	tipc_bearer_stop(net);
 	tipc_node_stop(net);
diff --git a/net/tipc/netlink_compat.c b/net/tipc/netlink_compat.c
index 4ad3586da8f0..340a6e7c43a7 100644
--- a/net/tipc/netlink_compat.c
+++ b/net/tipc/netlink_compat.c
@@ -267,8 +267,14 @@ static int tipc_nl_compat_dumpit(struct tipc_nl_compat_cmd_dump *cmd,
 	if (msg->rep_type)
 		tipc_tlv_init(msg->rep, msg->rep_type);
 
-	if (cmd->header)
-		(*cmd->header)(msg);
+	if (cmd->header) {
+		err = (*cmd->header)(msg);
+		if (err) {
+			kfree_skb(msg->rep);
+			msg->rep = NULL;
+			return err;
+		}
+	}
 
 	arg = nlmsg_new(0, GFP_KERNEL);
 	if (!arg) {
@@ -397,7 +403,12 @@ static int tipc_nl_compat_bearer_enable(struct tipc_nl_compat_cmd_doit *cmd,
 	if (!bearer)
 		return -EMSGSIZE;
 
-	len = min_t(int, TLV_GET_DATA_LEN(msg->req), TIPC_MAX_BEARER_NAME);
+	len = TLV_GET_DATA_LEN(msg->req);
+	len -= offsetof(struct tipc_bearer_config, name);
+	if (len <= 0)
+		return -EINVAL;
+
+	len = min_t(int, len, TIPC_MAX_BEARER_NAME);
 	if (!string_is_valid(b->name, len))
 		return -EINVAL;
 
@@ -766,7 +777,12 @@ static int tipc_nl_compat_link_set(struct tipc_nl_compat_cmd_doit *cmd,
 
 	lc = (struct tipc_link_config *)TLV_DATA(msg->req);
 
-	len = min_t(int, TLV_GET_DATA_LEN(msg->req), TIPC_MAX_LINK_NAME);
+	len = TLV_GET_DATA_LEN(msg->req);
+	len -= offsetof(struct tipc_link_config, name);
+	if (len <= 0)
+		return -EINVAL;
+
+	len = min_t(int, len, TIPC_MAX_LINK_NAME);
 	if (!string_is_valid(lc->name, len))
 		return -EINVAL;
 
diff --git a/net/tipc/node.c b/net/tipc/node.c
index 2dc4919ab23c..dd3b6dc17662 100644
--- a/net/tipc/node.c
+++ b/net/tipc/node.c
@@ -817,10 +817,10 @@ static void __tipc_node_link_down(struct tipc_node *n, int *bearer_id,
 static void tipc_node_link_down(struct tipc_node *n, int bearer_id, bool delete)
 {
 	struct tipc_link_entry *le = &n->links[bearer_id];
+	struct tipc_media_addr *maddr = NULL;
 	struct tipc_link *l = le->link;
-	struct tipc_media_addr *maddr;
-	struct sk_buff_head xmitq;
 	int old_bearer_id = bearer_id;
+	struct sk_buff_head xmitq;
 
 	if (!l)
 		return;
@@ -844,7 +844,8 @@ static void tipc_node_link_down(struct tipc_node *n, int bearer_id, bool delete)
 	tipc_node_write_unlock(n);
 	if (delete)
 		tipc_mon_remove_peer(n->net, n->addr, old_bearer_id);
-	tipc_bearer_xmit(n->net, bearer_id, &xmitq, maddr);
+	if (!skb_queue_empty(&xmitq))
+		tipc_bearer_xmit(n->net, bearer_id, &xmitq, maddr);
 	tipc_sk_rcv(n->net, &le->inputq);
 }
 
diff --git a/net/tipc/socket.c b/net/tipc/socket.c
index 3274ef625dba..b542f14ed444 100644
--- a/net/tipc/socket.c
+++ b/net/tipc/socket.c
@@ -2349,6 +2349,16 @@ static int tipc_wait_for_connect(struct socket *sock, long *timeo_p)
 	return 0;
 }
 
+static bool tipc_sockaddr_is_sane(struct sockaddr_tipc *addr)
+{
+	if (addr->family != AF_TIPC)
+		return false;
+	if (addr->addrtype == TIPC_SERVICE_RANGE)
+		return (addr->addr.nameseq.lower <= addr->addr.nameseq.upper);
+	return (addr->addrtype == TIPC_SERVICE_ADDR ||
+		addr->addrtype == TIPC_SOCKET_ADDR);
+}
+
 /**
  * tipc_connect - establish a connection to another TIPC port
  * @sock: socket structure
@@ -2384,18 +2394,18 @@ static int tipc_connect(struct socket *sock, struct sockaddr *dest,
 		if (!tipc_sk_type_connectionless(sk))
 			res = -EINVAL;
 		goto exit;
-	} else if (dst->family != AF_TIPC) {
-		res = -EINVAL;
 	}
-	if (dst->addrtype != TIPC_ADDR_ID && dst->addrtype != TIPC_ADDR_NAME)
+	if (!tipc_sockaddr_is_sane(dst)) {
 		res = -EINVAL;
-	if (res)
 		goto exit;
-
+	}
 	/* DGRAM/RDM connect(), just save the destaddr */
 	if (tipc_sk_type_connectionless(sk)) {
 		memcpy(&tsk->peer, dest, destlen);
 		goto exit;
+	} else if (dst->addrtype == TIPC_SERVICE_RANGE) {
+		res = -EINVAL;
+		goto exit;
 	}
 
 	previous = sk->sk_state;
@@ -3255,6 +3265,8 @@ static int __tipc_nl_add_sk_con(struct sk_buff *skb, struct tipc_sock *tsk)
 	peer_port = tsk_peer_port(tsk);
 
 	nest = nla_nest_start(skb, TIPC_NLA_SOCK_CON);
+	if (!nest)
+		return -EMSGSIZE;
 
 	if (nla_put_u32(skb, TIPC_NLA_CON_NODE, peer_node))
 		goto msg_full;
diff --git a/net/tipc/sysctl.c b/net/tipc/sysctl.c
index 3481e4906bd6..9df82a573aa7 100644
--- a/net/tipc/sysctl.c
+++ b/net/tipc/sysctl.c
@@ -38,6 +38,8 @@
 
 #include <linux/sysctl.h>
 
+static int zero;
+static int one = 1;
 static struct ctl_table_header *tipc_ctl_hdr;
 
 static struct ctl_table tipc_table[] = {
@@ -46,14 +48,16 @@ static struct ctl_table tipc_table[] = {
 		.data		= &sysctl_tipc_rmem,
 		.maxlen		= sizeof(sysctl_tipc_rmem),
 		.mode		= 0644,
-		.proc_handler	= proc_dointvec,
+		.proc_handler	= proc_dointvec_minmax,
+		.extra1         = &one,
 	},
 	{
 		.procname	= "named_timeout",
 		.data		= &sysctl_tipc_named_timeout,
 		.maxlen		= sizeof(sysctl_tipc_named_timeout),
 		.mode		= 0644,
-		.proc_handler	= proc_dointvec,
+		.proc_handler	= proc_dointvec_minmax,
+		.extra1         = &zero,
 	},
 	{
 		.procname       = "sk_filter",
diff --git a/net/tipc/topsrv.c b/net/tipc/topsrv.c
index 4a708a4e8583..b45932d78004 100644
--- a/net/tipc/topsrv.c
+++ b/net/tipc/topsrv.c
@@ -363,6 +363,7 @@ static int tipc_conn_rcv_sub(struct tipc_topsrv *srv,
 	struct tipc_subscription *sub;
 
 	if (tipc_sub_read(s, filter) & TIPC_SUB_CANCEL) {
+		s->filter &= __constant_ntohl(~TIPC_SUB_CANCEL);
 		tipc_conn_delete_sub(con, s);
 		return 0;
 	}
diff --git a/net/tls/tls_device.c b/net/tls/tls_device.c
index 135a7ee9db03..14dedb24fa7b 100644
--- a/net/tls/tls_device.c
+++ b/net/tls/tls_device.c
@@ -52,8 +52,11 @@ static DEFINE_SPINLOCK(tls_device_lock);
 
 static void tls_device_free_ctx(struct tls_context *ctx)
 {
-	if (ctx->tx_conf == TLS_HW)
+	if (ctx->tx_conf == TLS_HW) {
 		kfree(tls_offload_ctx_tx(ctx));
+		kfree(ctx->tx.rec_seq);
+		kfree(ctx->tx.iv);
+	}
 
 	if (ctx->rx_conf == TLS_HW)
 		kfree(tls_offload_ctx_rx(ctx));
@@ -216,6 +219,13 @@ void tls_device_sk_destruct(struct sock *sk)
 }
 EXPORT_SYMBOL(tls_device_sk_destruct);
 
+void tls_device_free_resources_tx(struct sock *sk)
+{
+	struct tls_context *tls_ctx = tls_get_ctx(sk);
+
+	tls_free_partial_record(sk, tls_ctx);
+}
+
 static void tls_append_frag(struct tls_record_info *record,
 			    struct page_frag *pfrag,
 			    int size)
@@ -587,7 +597,7 @@ void handle_device_resync(struct sock *sk, u32 seq, u64 rcd_sn)
 static int tls_device_reencrypt(struct sock *sk, struct sk_buff *skb)
 {
 	struct strp_msg *rxm = strp_msg(skb);
-	int err = 0, offset = rxm->offset, copy, nsg;
+	int err = 0, offset = rxm->offset, copy, nsg, data_len, pos;
 	struct sk_buff *skb_iter, *unused;
 	struct scatterlist sg[1];
 	char *orig_buf, *buf;
@@ -618,25 +628,42 @@ static int tls_device_reencrypt(struct sock *sk, struct sk_buff *skb)
 	else
 		err = 0;
 
-	copy = min_t(int, skb_pagelen(skb) - offset,
-		     rxm->full_len - TLS_CIPHER_AES_GCM_128_TAG_SIZE);
+	data_len = rxm->full_len - TLS_CIPHER_AES_GCM_128_TAG_SIZE;
 
-	if (skb->decrypted)
-		skb_store_bits(skb, offset, buf, copy);
+	if (skb_pagelen(skb) > offset) {
+		copy = min_t(int, skb_pagelen(skb) - offset, data_len);
 
-	offset += copy;
-	buf += copy;
+		if (skb->decrypted)
+			skb_store_bits(skb, offset, buf, copy);
+
+		offset += copy;
+		buf += copy;
+	}
 
+	pos = skb_pagelen(skb);
 	skb_walk_frags(skb, skb_iter) {
-		copy = min_t(int, skb_iter->len,
-			     rxm->full_len - offset + rxm->offset -
-			     TLS_CIPHER_AES_GCM_128_TAG_SIZE);
+		int frag_pos;
+
+		/* Practically all frags must belong to msg if reencrypt
+		 * is needed with current strparser and coalescing logic,
+		 * but strparser may "get optimized", so let's be safe.
+		 */
+		if (pos + skb_iter->len <= offset)
+			goto done_with_frag;
+		if (pos >= data_len + rxm->offset)
+			break;
+
+		frag_pos = offset - pos;
+		copy = min_t(int, skb_iter->len - frag_pos,
+			     data_len + rxm->offset - offset);
 
 		if (skb_iter->decrypted)
-			skb_store_bits(skb_iter, offset, buf, copy);
+			skb_store_bits(skb_iter, frag_pos, buf, copy);
 
 		offset += copy;
 		buf += copy;
+done_with_frag:
+		pos += skb_iter->len;
 	}
 
 free_buf:
@@ -894,7 +921,9 @@ int tls_set_device_offload_rx(struct sock *sk, struct tls_context *ctx)
 	goto release_netdev;
 
 free_sw_resources:
+	up_read(&device_offload_lock);
 	tls_sw_free_resources_rx(sk);
+	down_read(&device_offload_lock);
 release_ctx:
 	ctx->priv_ctx_rx = NULL;
 release_netdev:
@@ -929,8 +958,6 @@ void tls_device_offload_cleanup_rx(struct sock *sk)
 	}
 out:
 	up_read(&device_offload_lock);
-	kfree(tls_ctx->rx.rec_seq);
-	kfree(tls_ctx->rx.iv);
 	tls_sw_release_resources_rx(sk);
 }
 
diff --git a/net/tls/tls_device_fallback.c b/net/tls/tls_device_fallback.c
index 54c3a758f2a7..c3a5fe624b4e 100644
--- a/net/tls/tls_device_fallback.c
+++ b/net/tls/tls_device_fallback.c
@@ -194,18 +194,26 @@ static void update_chksum(struct sk_buff *skb, int headln)
 
 static void complete_skb(struct sk_buff *nskb, struct sk_buff *skb, int headln)
 {
+	struct sock *sk = skb->sk;
+	int delta;
+
 	skb_copy_header(nskb, skb);
 
 	skb_put(nskb, skb->len);
 	memcpy(nskb->data, skb->data, headln);
-	update_chksum(nskb, headln);
 
 	nskb->destructor = skb->destructor;
-	nskb->sk = skb->sk;
+	nskb->sk = sk;
 	skb->destructor = NULL;
 	skb->sk = NULL;
-	refcount_add(nskb->truesize - skb->truesize,
-		     &nskb->sk->sk_wmem_alloc);
+
+	update_chksum(nskb, headln);
+
+	delta = nskb->truesize - skb->truesize;
+	if (likely(delta < 0))
+		WARN_ON_ONCE(refcount_sub_and_test(-delta, &sk->sk_wmem_alloc));
+	else if (delta)
+		refcount_add(delta, &sk->sk_wmem_alloc);
 }
 
 /* This function may be called after the user socket is already
diff --git a/net/tls/tls_main.c b/net/tls/tls_main.c
index df921a2904b9..478603f43964 100644
--- a/net/tls/tls_main.c
+++ b/net/tls/tls_main.c
@@ -208,6 +208,26 @@ int tls_push_partial_record(struct sock *sk, struct tls_context *ctx,
 	return tls_push_sg(sk, ctx, sg, offset, flags);
 }
 
+bool tls_free_partial_record(struct sock *sk, struct tls_context *ctx)
+{
+	struct scatterlist *sg;
+
+	sg = ctx->partially_sent_record;
+	if (!sg)
+		return false;
+
+	while (1) {
+		put_page(sg_page(sg));
+		sk_mem_uncharge(sk, sg->length);
+
+		if (sg_is_last(sg))
+			break;
+		sg++;
+	}
+	ctx->partially_sent_record = NULL;
+	return true;
+}
+
 static void tls_write_space(struct sock *sk)
 {
 	struct tls_context *ctx = tls_get_ctx(sk);
@@ -267,13 +287,14 @@ static void tls_sk_proto_close(struct sock *sk, long timeout)
 		kfree(ctx->tx.rec_seq);
 		kfree(ctx->tx.iv);
 		tls_sw_free_resources_tx(sk);
+#ifdef CONFIG_TLS_DEVICE
+	} else if (ctx->tx_conf == TLS_HW) {
+		tls_device_free_resources_tx(sk);
+#endif
 	}
 
-	if (ctx->rx_conf == TLS_SW) {
-		kfree(ctx->rx.rec_seq);
-		kfree(ctx->rx.iv);
+	if (ctx->rx_conf == TLS_SW)
 		tls_sw_free_resources_rx(sk);
-	}
 
 #ifdef CONFIG_TLS_DEVICE
 	if (ctx->rx_conf == TLS_HW)
diff --git a/net/tls/tls_sw.c b/net/tls/tls_sw.c
index 425351ac2a9b..29d6af43dd24 100644
--- a/net/tls/tls_sw.c
+++ b/net/tls/tls_sw.c
@@ -1484,6 +1484,8 @@ static int decrypt_skb_update(struct sock *sk, struct sk_buff *skb,
 
 				return err;
 			}
+		} else {
+			*zc = false;
 		}
 
 		rxm->full_len -= padding_length(ctx, tls_ctx, skb);
@@ -2050,20 +2052,7 @@ void tls_sw_free_resources_tx(struct sock *sk)
 	/* Free up un-sent records in tx_list. First, free
 	 * the partially sent record if any at head of tx_list.
 	 */
-	if (tls_ctx->partially_sent_record) {
-		struct scatterlist *sg = tls_ctx->partially_sent_record;
-
-		while (1) {
-			put_page(sg_page(sg));
-			sk_mem_uncharge(sk, sg->length);
-
-			if (sg_is_last(sg))
-				break;
-			sg++;
-		}
-
-		tls_ctx->partially_sent_record = NULL;
-
+	if (tls_free_partial_record(sk, tls_ctx)) {
 		rec = list_first_entry(&ctx->tx_list,
 				       struct tls_rec, list);
 		list_del(&rec->list);
@@ -2089,6 +2078,9 @@ void tls_sw_release_resources_rx(struct sock *sk)
 	struct tls_context *tls_ctx = tls_get_ctx(sk);
 	struct tls_sw_context_rx *ctx = tls_sw_ctx_rx(tls_ctx);
 
+	kfree(tls_ctx->rx.rec_seq);
+	kfree(tls_ctx->rx.iv);
+
 	if (ctx->aead_recv) {
 		kfree_skb(ctx->recv_pkt);
 		ctx->recv_pkt = NULL;
diff --git a/net/wireless/lib80211_crypt_tkip.c b/net/wireless/lib80211_crypt_tkip.c
index 35f06563207d..11eaa5956f00 100644
--- a/net/wireless/lib80211_crypt_tkip.c
+++ b/net/wireless/lib80211_crypt_tkip.c
@@ -501,7 +501,6 @@ static int michael_mic(struct crypto_shash *tfm_michael, u8 *key, u8 *hdr,
 	}
 
 	desc->tfm = tfm_michael;
-	desc->flags = 0;
 
 	if (crypto_shash_setkey(tfm_michael, key, 8))
 		return -1;
diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c
index 25a9e3b5c154..47e30a58566c 100644
--- a/net/wireless/nl80211.c
+++ b/net/wireless/nl80211.c
@@ -13650,7 +13650,8 @@ static const struct genl_ops nl80211_ops[] = {
 		.policy = nl80211_policy,
 		.flags = GENL_UNS_ADMIN_PERM,
 		.internal_flags = NL80211_FLAG_NEED_NETDEV_UP |
-				  NL80211_FLAG_NEED_RTNL,
+				  NL80211_FLAG_NEED_RTNL |
+				  NL80211_FLAG_CLEAR_SKB,
 	},
 	{
 		.cmd = NL80211_CMD_DEAUTHENTICATE,
@@ -13701,7 +13702,8 @@ static const struct genl_ops nl80211_ops[] = {
 		.policy = nl80211_policy,
 		.flags = GENL_UNS_ADMIN_PERM,
 		.internal_flags = NL80211_FLAG_NEED_NETDEV_UP |
-				  NL80211_FLAG_NEED_RTNL,
+				  NL80211_FLAG_NEED_RTNL |
+				  NL80211_FLAG_CLEAR_SKB,
 	},
 	{
 		.cmd = NL80211_CMD_UPDATE_CONNECT_PARAMS,
@@ -13709,7 +13711,8 @@ static const struct genl_ops nl80211_ops[] = {
 		.policy = nl80211_policy,
 		.flags = GENL_ADMIN_PERM,
 		.internal_flags = NL80211_FLAG_NEED_NETDEV_UP |
-				  NL80211_FLAG_NEED_RTNL,
+				  NL80211_FLAG_NEED_RTNL |
+				  NL80211_FLAG_CLEAR_SKB,
 	},
 	{
 		.cmd = NL80211_CMD_DISCONNECT,
@@ -13738,7 +13741,8 @@ static const struct genl_ops nl80211_ops[] = {
 		.policy = nl80211_policy,
 		.flags = GENL_UNS_ADMIN_PERM,
 		.internal_flags = NL80211_FLAG_NEED_NETDEV_UP |
-				  NL80211_FLAG_NEED_RTNL,
+				  NL80211_FLAG_NEED_RTNL |
+				  NL80211_FLAG_CLEAR_SKB,
 	},
 	{
 		.cmd = NL80211_CMD_DEL_PMKSA,
@@ -14090,7 +14094,8 @@ static const struct genl_ops nl80211_ops[] = {
 		.policy = nl80211_policy,
 		.flags = GENL_UNS_ADMIN_PERM,
 		.internal_flags = NL80211_FLAG_NEED_WIPHY |
-				  NL80211_FLAG_NEED_RTNL,
+				  NL80211_FLAG_NEED_RTNL |
+				  NL80211_FLAG_CLEAR_SKB,
 	},
 	{
 		.cmd = NL80211_CMD_SET_QOS_MAP,
@@ -14145,7 +14150,8 @@ static const struct genl_ops nl80211_ops[] = {
 		.doit = nl80211_set_pmk,
 		.policy = nl80211_policy,
 		.internal_flags = NL80211_FLAG_NEED_NETDEV_UP |
-				  NL80211_FLAG_NEED_RTNL,
+				  NL80211_FLAG_NEED_RTNL |
+				  NL80211_FLAG_CLEAR_SKB,
 	},
 	{
 		.cmd = NL80211_CMD_DEL_PMK,
diff --git a/net/wireless/reg.c b/net/wireless/reg.c
index 2f1bf91eb226..a6fd5ce199da 100644
--- a/net/wireless/reg.c
+++ b/net/wireless/reg.c
@@ -1309,6 +1309,16 @@ reg_intersect_dfs_region(const enum nl80211_dfs_regions dfs_region1,
 	return dfs_region1;
 }
 
+static void reg_wmm_rules_intersect(const struct ieee80211_wmm_ac *wmm_ac1,
+				    const struct ieee80211_wmm_ac *wmm_ac2,
+				    struct ieee80211_wmm_ac *intersect)
+{
+	intersect->cw_min = max_t(u16, wmm_ac1->cw_min, wmm_ac2->cw_min);
+	intersect->cw_max = max_t(u16, wmm_ac1->cw_max, wmm_ac2->cw_max);
+	intersect->cot = min_t(u16, wmm_ac1->cot, wmm_ac2->cot);
+	intersect->aifsn = max_t(u8, wmm_ac1->aifsn, wmm_ac2->aifsn);
+}
+
 /*
  * Helper for regdom_intersect(), this does the real
  * mathematical intersection fun
@@ -1323,6 +1333,8 @@ static int reg_rules_intersect(const struct ieee80211_regdomain *rd1,
 	struct ieee80211_freq_range *freq_range;
 	const struct ieee80211_power_rule *power_rule1, *power_rule2;
 	struct ieee80211_power_rule *power_rule;
+	const struct ieee80211_wmm_rule *wmm_rule1, *wmm_rule2;
+	struct ieee80211_wmm_rule *wmm_rule;
 	u32 freq_diff, max_bandwidth1, max_bandwidth2;
 
 	freq_range1 = &rule1->freq_range;
@@ -1333,6 +1345,10 @@ static int reg_rules_intersect(const struct ieee80211_regdomain *rd1,
 	power_rule2 = &rule2->power_rule;
 	power_rule = &intersected_rule->power_rule;
 
+	wmm_rule1 = &rule1->wmm_rule;
+	wmm_rule2 = &rule2->wmm_rule;
+	wmm_rule = &intersected_rule->wmm_rule;
+
 	freq_range->start_freq_khz = max(freq_range1->start_freq_khz,
 					 freq_range2->start_freq_khz);
 	freq_range->end_freq_khz = min(freq_range1->end_freq_khz,
@@ -1376,6 +1392,29 @@ static int reg_rules_intersect(const struct ieee80211_regdomain *rd1,
 	intersected_rule->dfs_cac_ms = max(rule1->dfs_cac_ms,
 					   rule2->dfs_cac_ms);
 
+	if (rule1->has_wmm && rule2->has_wmm) {
+		u8 ac;
+
+		for (ac = 0; ac < IEEE80211_NUM_ACS; ac++) {
+			reg_wmm_rules_intersect(&wmm_rule1->client[ac],
+						&wmm_rule2->client[ac],
+						&wmm_rule->client[ac]);
+			reg_wmm_rules_intersect(&wmm_rule1->ap[ac],
+						&wmm_rule2->ap[ac],
+						&wmm_rule->ap[ac]);
+		}
+
+		intersected_rule->has_wmm = true;
+	} else if (rule1->has_wmm) {
+		*wmm_rule = *wmm_rule1;
+		intersected_rule->has_wmm = true;
+	} else if (rule2->has_wmm) {
+		*wmm_rule = *wmm_rule2;
+		intersected_rule->has_wmm = true;
+	} else {
+		intersected_rule->has_wmm = false;
+	}
+
 	if (!is_valid_reg_rule(intersected_rule))
 		return -EINVAL;
 
@@ -3739,10 +3778,9 @@ void wiphy_regulatory_register(struct wiphy *wiphy)
 		/*
 		 * The last request may have been received before this
 		 * registration call. Call the driver notifier if
-		 * initiator is USER and user type is CELL_BASE.
+		 * initiator is USER.
 		 */
-		if (lr->initiator == NL80211_REGDOM_SET_BY_USER &&
-		    lr->user_reg_hint_type == NL80211_USER_REG_HINT_CELL_BASE)
+		if (lr->initiator == NL80211_REGDOM_SET_BY_USER)
 			reg_call_notifier(wiphy, lr);
 	}
 
diff --git a/net/wireless/scan.c b/net/wireless/scan.c
index 287518c6caa4..04d888628f29 100644
--- a/net/wireless/scan.c
+++ b/net/wireless/scan.c
@@ -190,10 +190,9 @@ static size_t cfg80211_gen_new_ie(const u8 *ie, size_t ielen,
 	/* copy subelement as we need to change its content to
 	 * mark an ie after it is processed.
 	 */
-	sub_copy = kmalloc(subie_len, gfp);
+	sub_copy = kmemdup(subelement, subie_len, gfp);
 	if (!sub_copy)
 		return 0;
-	memcpy(sub_copy, subelement, subie_len);
 
 	pos = &new_ie[0];
 
diff --git a/net/wireless/util.c b/net/wireless/util.c
index e4b8db5e81ec..75899b62bdc9 100644
--- a/net/wireless/util.c
+++ b/net/wireless/util.c
@@ -1220,9 +1220,11 @@ static u32 cfg80211_calculate_bitrate_he(struct rate_info *rate)
 	else if (rate->bw == RATE_INFO_BW_HE_RU &&
 		 rate->he_ru_alloc == NL80211_RATE_INFO_HE_RU_ALLOC_26)
 		result = rates_26[rate->he_gi];
-	else if (WARN(1, "invalid HE MCS: bw:%d, ru:%d\n",
-		      rate->bw, rate->he_ru_alloc))
+	else {
+		WARN(1, "invalid HE MCS: bw:%d, ru:%d\n",
+		     rate->bw, rate->he_ru_alloc);
 		return 0;
+	}
 
 	/* now scale to the appropriate MCS */
 	tmp = result;
diff --git a/net/xdp/xdp_umem.c b/net/xdp/xdp_umem.c
index 77520eacee8f..989e52386c35 100644
--- a/net/xdp/xdp_umem.c
+++ b/net/xdp/xdp_umem.c
@@ -193,9 +193,6 @@ static void xdp_umem_unaccount_pages(struct xdp_umem *umem)
 
 static void xdp_umem_release(struct xdp_umem *umem)
 {
-	struct task_struct *task;
-	struct mm_struct *mm;
-
 	xdp_umem_clear_dev(umem);
 
 	ida_simple_remove(&umem_ida, umem->id);
@@ -214,21 +211,10 @@ static void xdp_umem_release(struct xdp_umem *umem)
 
 	xdp_umem_unpin_pages(umem);
 
-	task = get_pid_task(umem->pid, PIDTYPE_PID);
-	put_pid(umem->pid);
-	if (!task)
-		goto out;
-	mm = get_task_mm(task);
-	put_task_struct(task);
-	if (!mm)
-		goto out;
-
-	mmput(mm);
 	kfree(umem->pages);
 	umem->pages = NULL;
 
 	xdp_umem_unaccount_pages(umem);
-out:
 	kfree(umem);
 }
 
@@ -357,7 +343,6 @@ static int xdp_umem_reg(struct xdp_umem *umem, struct xdp_umem_reg *mr)
 	if (size_chk < 0)
 		return -EINVAL;
 
-	umem->pid = get_task_pid(current, PIDTYPE_PID);
 	umem->address = (unsigned long)addr;
 	umem->chunk_mask = ~((u64)chunk_size - 1);
 	umem->size = size;
@@ -373,7 +358,7 @@ static int xdp_umem_reg(struct xdp_umem *umem, struct xdp_umem_reg *mr)
 
 	err = xdp_umem_account_pages(umem);
 	if (err)
-		goto out;
+		return err;
 
 	err = xdp_umem_pin_pages(umem);
 	if (err)
@@ -392,8 +377,6 @@ static int xdp_umem_reg(struct xdp_umem *umem, struct xdp_umem_reg *mr)
 
 out_account:
 	xdp_umem_unaccount_pages(umem);
-out:
-	put_pid(umem->pid);
 	return err;
 }
 
diff --git a/net/xfrm/xfrm_interface.c b/net/xfrm/xfrm_interface.c
index dbb3c1945b5c..85fec98676d3 100644
--- a/net/xfrm/xfrm_interface.c
+++ b/net/xfrm/xfrm_interface.c
@@ -70,17 +70,28 @@ static struct xfrm_if *xfrmi_lookup(struct net *net, struct xfrm_state *x)
 	return NULL;
 }
 
-static struct xfrm_if *xfrmi_decode_session(struct sk_buff *skb)
+static struct xfrm_if *xfrmi_decode_session(struct sk_buff *skb,
+					    unsigned short family)
 {
 	struct xfrmi_net *xfrmn;
-	int ifindex;
 	struct xfrm_if *xi;
+	int ifindex = 0;
 
 	if (!secpath_exists(skb) || !skb->dev)
 		return NULL;
 
+	switch (family) {
+	case AF_INET6:
+		ifindex = inet6_sdif(skb);
+		break;
+	case AF_INET:
+		ifindex = inet_sdif(skb);
+		break;
+	}
+	if (!ifindex)
+		ifindex = skb->dev->ifindex;
+
 	xfrmn = net_generic(xs_net(xfrm_input_state(skb)), xfrmi_net_id);
-	ifindex = skb->dev->ifindex;
 
 	for_each_xfrmi_rcu(xfrmn->xfrmi[0], xi) {
 		if (ifindex == xi->dev->ifindex &&
diff --git a/net/xfrm/xfrm_policy.c b/net/xfrm/xfrm_policy.c
index 8d1a898d0ba5..a6b58df7a70f 100644
--- a/net/xfrm/xfrm_policy.c
+++ b/net/xfrm/xfrm_policy.c
@@ -3313,7 +3313,7 @@ int __xfrm_policy_check(struct sock *sk, int dir, struct sk_buff *skb,
 	ifcb = xfrm_if_get_cb();
 
 	if (ifcb) {
-		xi = ifcb->decode_session(skb);
+		xi = ifcb->decode_session(skb, family);
 		if (xi) {
 			if_id = xi->p.if_id;
 			net = xi->net;
diff --git a/net/xfrm/xfrm_state.c b/net/xfrm/xfrm_state.c
index 1bb971f46fc6..c62f712fdaf7 100644
--- a/net/xfrm/xfrm_state.c
+++ b/net/xfrm/xfrm_state.c
@@ -434,7 +434,7 @@ EXPORT_SYMBOL(xfrm_state_free);
 
 static void ___xfrm_state_destroy(struct xfrm_state *x)
 {
-	tasklet_hrtimer_cancel(&x->mtimer);
+	hrtimer_cancel(&x->mtimer);
 	del_timer_sync(&x->rtimer);
 	kfree(x->aead);
 	kfree(x->aalg);
@@ -479,8 +479,8 @@ static void xfrm_state_gc_task(struct work_struct *work)
 
 static enum hrtimer_restart xfrm_timer_handler(struct hrtimer *me)
 {
-	struct tasklet_hrtimer *thr = container_of(me, struct tasklet_hrtimer, timer);
-	struct xfrm_state *x = container_of(thr, struct xfrm_state, mtimer);
+	struct xfrm_state *x = container_of(me, struct xfrm_state, mtimer);
+	enum hrtimer_restart ret = HRTIMER_NORESTART;
 	time64_t now = ktime_get_real_seconds();
 	time64_t next = TIME64_MAX;
 	int warn = 0;
@@ -544,7 +544,8 @@ static enum hrtimer_restart xfrm_timer_handler(struct hrtimer *me)
 		km_state_expired(x, 0, 0);
 resched:
 	if (next != TIME64_MAX) {
-		tasklet_hrtimer_start(&x->mtimer, ktime_set(next, 0), HRTIMER_MODE_REL);
+		hrtimer_forward_now(&x->mtimer, ktime_set(next, 0));
+		ret = HRTIMER_RESTART;
 	}
 
 	goto out;
@@ -561,7 +562,7 @@ expired:
 
 out:
 	spin_unlock(&x->lock);
-	return HRTIMER_NORESTART;
+	return ret;
 }
 
 static void xfrm_replay_timer_handler(struct timer_list *t);
@@ -580,8 +581,8 @@ struct xfrm_state *xfrm_state_alloc(struct net *net)
 		INIT_HLIST_NODE(&x->bydst);
 		INIT_HLIST_NODE(&x->bysrc);
 		INIT_HLIST_NODE(&x->byspi);
-		tasklet_hrtimer_init(&x->mtimer, xfrm_timer_handler,
-					CLOCK_BOOTTIME, HRTIMER_MODE_ABS);
+		hrtimer_init(&x->mtimer, CLOCK_BOOTTIME, HRTIMER_MODE_ABS_SOFT);
+		x->mtimer.function = xfrm_timer_handler;
 		timer_setup(&x->rtimer, xfrm_replay_timer_handler, 0);
 		x->curlft.add_time = ktime_get_real_seconds();
 		x->lft.soft_byte_limit = XFRM_INF;
@@ -1047,7 +1048,9 @@ found:
 				hlist_add_head_rcu(&x->byspi, net->xfrm.state_byspi + h);
 			}
 			x->lft.hard_add_expires_seconds = net->xfrm.sysctl_acq_expires;
-			tasklet_hrtimer_start(&x->mtimer, ktime_set(net->xfrm.sysctl_acq_expires, 0), HRTIMER_MODE_REL);
+			hrtimer_start(&x->mtimer,
+				      ktime_set(net->xfrm.sysctl_acq_expires, 0),
+				      HRTIMER_MODE_REL_SOFT);
 			net->xfrm.state_num++;
 			xfrm_hash_grow_check(net, x->bydst.next != NULL);
 			spin_unlock_bh(&net->xfrm.xfrm_state_lock);
@@ -1159,7 +1162,7 @@ static void __xfrm_state_insert(struct xfrm_state *x)
 		hlist_add_head_rcu(&x->byspi, net->xfrm.state_byspi + h);
 	}
 
-	tasklet_hrtimer_start(&x->mtimer, ktime_set(1, 0), HRTIMER_MODE_REL);
+	hrtimer_start(&x->mtimer, ktime_set(1, 0), HRTIMER_MODE_REL_SOFT);
 	if (x->replay_maxage)
 		mod_timer(&x->rtimer, jiffies + x->replay_maxage);
 
@@ -1266,7 +1269,9 @@ static struct xfrm_state *__find_acq_core(struct net *net,
 		x->mark.m = m->m;
 		x->lft.hard_add_expires_seconds = net->xfrm.sysctl_acq_expires;
 		xfrm_state_hold(x);
-		tasklet_hrtimer_start(&x->mtimer, ktime_set(net->xfrm.sysctl_acq_expires, 0), HRTIMER_MODE_REL);
+		hrtimer_start(&x->mtimer,
+			      ktime_set(net->xfrm.sysctl_acq_expires, 0),
+			      HRTIMER_MODE_REL_SOFT);
 		list_add(&x->km.all, &net->xfrm.state_all);
 		hlist_add_head_rcu(&x->bydst, net->xfrm.state_bydst + h);
 		h = xfrm_src_hash(net, daddr, saddr, family);
@@ -1571,7 +1576,8 @@ out:
 		memcpy(&x1->lft, &x->lft, sizeof(x1->lft));
 		x1->km.dying = 0;
 
-		tasklet_hrtimer_start(&x1->mtimer, ktime_set(1, 0), HRTIMER_MODE_REL);
+		hrtimer_start(&x1->mtimer, ktime_set(1, 0),
+			      HRTIMER_MODE_REL_SOFT);
 		if (x1->curlft.use_time)
 			xfrm_state_check_expire(x1);
 
@@ -1610,7 +1616,7 @@ int xfrm_state_check_expire(struct xfrm_state *x)
 	if (x->curlft.bytes >= x->lft.hard_byte_limit ||
 	    x->curlft.packets >= x->lft.hard_packet_limit) {
 		x->km.state = XFRM_STATE_EXPIRED;
-		tasklet_hrtimer_start(&x->mtimer, 0, HRTIMER_MODE_REL);
+		hrtimer_start(&x->mtimer, 0, HRTIMER_MODE_REL_SOFT);
 		return -EINVAL;
 	}
 
@@ -2384,7 +2390,7 @@ void xfrm_state_fini(struct net *net)
 
 	flush_work(&net->xfrm.state_hash_work);
 	flush_work(&xfrm_state_gc_work);
-	xfrm_state_flush(net, IPSEC_PROTO_ANY, false, true);
+	xfrm_state_flush(net, 0, false, true);
 
 	WARN_ON(!list_empty(&net->xfrm.state_all));
 
diff --git a/net/xfrm/xfrm_user.c b/net/xfrm/xfrm_user.c
index a131f9ff979e..6916931b1de1 100644
--- a/net/xfrm/xfrm_user.c
+++ b/net/xfrm/xfrm_user.c
@@ -1424,7 +1424,7 @@ static int verify_newpolicy_info(struct xfrm_userpolicy_info *p)
 	ret = verify_policy_dir(p->dir);
 	if (ret)
 		return ret;
-	if (p->index && ((p->index & XFRM_POLICY_MAX) != p->dir))
+	if (p->index && (xfrm_policy_id2dir(p->index) != p->dir))
 		return -EINVAL;
 
 	return 0;
@@ -1513,20 +1513,8 @@ static int validate_tmpl(int nr, struct xfrm_user_tmpl *ut, u16 family)
 			return -EINVAL;
 		}
 
-		switch (ut[i].id.proto) {
-		case IPPROTO_AH:
-		case IPPROTO_ESP:
-		case IPPROTO_COMP:
-#if IS_ENABLED(CONFIG_IPV6)
-		case IPPROTO_ROUTING:
-		case IPPROTO_DSTOPTS:
-#endif
-		case IPSEC_PROTO_ANY:
-			break;
-		default:
+		if (!xfrm_id_proto_valid(ut[i].id.proto))
 			return -EINVAL;
-		}
-
 	}
 
 	return 0;
diff --git a/scripts/Makefile.build b/scripts/Makefile.build
index 2554a15ecf2b..0c5969fa795f 100644
--- a/scripts/Makefile.build
+++ b/scripts/Makefile.build
@@ -199,11 +199,8 @@ sub_cmd_record_mcount = perl $(srctree)/scripts/recordmcount.pl "$(ARCH)" \
 	"$(if $(part-of-module),1,0)" "$(@)";
 recordmcount_source := $(srctree)/scripts/recordmcount.pl
 endif # BUILD_C_RECORDMCOUNT
-cmd_record_mcount =						\
-	if [ "$(findstring $(CC_FLAGS_FTRACE),$(_c_flags))" =	\
-	     "$(CC_FLAGS_FTRACE)" ]; then			\
-		$(sub_cmd_record_mcount)			\
-	fi
+cmd_record_mcount = $(if $(findstring $(strip $(CC_FLAGS_FTRACE)),$(_c_flags)),	\
+	$(sub_cmd_record_mcount))
 endif # CC_USING_RECORD_MCOUNT
 endif # CONFIG_FTRACE_MCOUNT_RECORD
 
@@ -225,6 +222,9 @@ endif
 ifdef CONFIG_RETPOLINE
   objtool_args += --retpoline
 endif
+ifdef CONFIG_X86_SMAP
+  objtool_args += --uaccess
+endif
 
 # 'OBJECT_FILES_NON_STANDARD := y': skip objtool checking for a directory
 # 'OBJECT_FILES_NON_STANDARD_foo.o := 'y': skip objtool checking for a file
diff --git a/scripts/Makefile.ubsan b/scripts/Makefile.ubsan
index 38b2b4818e8e..019771b845c5 100644
--- a/scripts/Makefile.ubsan
+++ b/scripts/Makefile.ubsan
@@ -3,7 +3,6 @@ ifdef CONFIG_UBSAN
       CFLAGS_UBSAN += $(call cc-option, -fsanitize=shift)
       CFLAGS_UBSAN += $(call cc-option, -fsanitize=integer-divide-by-zero)
       CFLAGS_UBSAN += $(call cc-option, -fsanitize=unreachable)
-      CFLAGS_UBSAN += $(call cc-option, -fsanitize=vla-bound)
       CFLAGS_UBSAN += $(call cc-option, -fsanitize=signed-integer-overflow)
       CFLAGS_UBSAN += $(call cc-option, -fsanitize=bounds)
       CFLAGS_UBSAN += $(call cc-option, -fsanitize=object-size)
diff --git a/scripts/atomic/gen-atomics.sh b/scripts/atomic/gen-atomics.sh
index 27400b0cd732..000dc6437893 100644
--- a/scripts/atomic/gen-atomics.sh
+++ b/scripts/atomic/gen-atomics.sh
@@ -13,7 +13,7 @@ gen-atomic-long.sh              asm-generic/atomic-long.h
 gen-atomic-fallback.sh          linux/atomic-fallback.h
 EOF
 while read script header; do
-	${ATOMICDIR}/${script} ${ATOMICTBL} > ${LINUXDIR}/include/${header}
+	/bin/sh ${ATOMICDIR}/${script} ${ATOMICTBL} > ${LINUXDIR}/include/${header}
 	HASH="$(sha1sum ${LINUXDIR}/include/${header})"
 	HASH="${HASH%% *}"
 	printf "// %s\n" "${HASH}" >> ${LINUXDIR}/include/${header}
diff --git a/scripts/checkpatch.pl b/scripts/checkpatch.pl
index 5b756278df13..a09333fd7cef 100755
--- a/scripts/checkpatch.pl
+++ b/scripts/checkpatch.pl
@@ -5977,7 +5977,7 @@ sub process {
 				while ($fmt =~ /(\%[\*\d\.]*p(\w))/g) {
 					$specifier = $1;
 					$extension = $2;
-					if ($extension !~ /[SsBKRraEhMmIiUDdgVCbGNOx]/) {
+					if ($extension !~ /[SsBKRraEhMmIiUDdgVCbGNOxt]/) {
 						$bad_specifier = $specifier;
 						last;
 					}
diff --git a/scripts/coccinelle/api/stream_open.cocci b/scripts/coccinelle/api/stream_open.cocci
new file mode 100644
index 000000000000..350145da7669
--- /dev/null
+++ b/scripts/coccinelle/api/stream_open.cocci
@@ -0,0 +1,363 @@
+// SPDX-License-Identifier: GPL-2.0
+// Author: Kirill Smelkov (kirr@nexedi.com)
+//
+// Search for stream-like files that are using nonseekable_open and convert
+// them to stream_open. A stream-like file is a file that does not use ppos in
+// its read and write. Rationale for the conversion is to avoid deadlock in
+// between read and write.
+
+virtual report
+virtual patch
+virtual explain  // explain decisions in the patch (SPFLAGS="-D explain")
+
+// stream-like reader & writer - ones that do not depend on f_pos.
+@ stream_reader @
+identifier readstream, ppos;
+identifier f, buf, len;
+type loff_t;
+@@
+  ssize_t readstream(struct file *f, char *buf, size_t len, loff_t *ppos)
+  {
+    ... when != ppos
+  }
+
+@ stream_writer @
+identifier writestream, ppos;
+identifier f, buf, len;
+type loff_t;
+@@
+  ssize_t writestream(struct file *f, const char *buf, size_t len, loff_t *ppos)
+  {
+    ... when != ppos
+  }
+
+
+// a function that blocks
+@ blocks @
+identifier block_f;
+identifier wait_event =~ "^wait_event_.*";
+@@
+  block_f(...) {
+    ... when exists
+    wait_event(...)
+    ... when exists
+  }
+
+// stream_reader that can block inside.
+//
+// XXX wait_* can be called not directly from current function (e.g. func -> f -> g -> wait())
+// XXX currently reader_blocks supports only direct and 1-level indirect cases.
+@ reader_blocks_direct @
+identifier stream_reader.readstream;
+identifier wait_event =~ "^wait_event_.*";
+@@
+  readstream(...)
+  {
+    ... when exists
+    wait_event(...)
+    ... when exists
+  }
+
+@ reader_blocks_1 @
+identifier stream_reader.readstream;
+identifier blocks.block_f;
+@@
+  readstream(...)
+  {
+    ... when exists
+    block_f(...)
+    ... when exists
+  }
+
+@ reader_blocks depends on reader_blocks_direct || reader_blocks_1 @
+identifier stream_reader.readstream;
+@@
+  readstream(...) {
+    ...
+  }
+
+
+// file_operations + whether they have _any_ .read, .write, .llseek ... at all.
+//
+// XXX add support for file_operations xxx[N] = ...	(sound/core/pcm_native.c)
+@ fops0 @
+identifier fops;
+@@
+  struct file_operations fops = {
+    ...
+  };
+
+@ has_read @
+identifier fops0.fops;
+identifier read_f;
+@@
+  struct file_operations fops = {
+    .read = read_f,
+  };
+
+@ has_read_iter @
+identifier fops0.fops;
+identifier read_iter_f;
+@@
+  struct file_operations fops = {
+    .read_iter = read_iter_f,
+  };
+
+@ has_write @
+identifier fops0.fops;
+identifier write_f;
+@@
+  struct file_operations fops = {
+    .write = write_f,
+  };
+
+@ has_write_iter @
+identifier fops0.fops;
+identifier write_iter_f;
+@@
+  struct file_operations fops = {
+    .write_iter = write_iter_f,
+  };
+
+@ has_llseek @
+identifier fops0.fops;
+identifier llseek_f;
+@@
+  struct file_operations fops = {
+    .llseek = llseek_f,
+  };
+
+@ has_no_llseek @
+identifier fops0.fops;
+@@
+  struct file_operations fops = {
+    .llseek = no_llseek,
+  };
+
+@ has_mmap @
+identifier fops0.fops;
+identifier mmap_f;
+@@
+  struct file_operations fops = {
+    .mmap = mmap_f,
+  };
+
+@ has_copy_file_range @
+identifier fops0.fops;
+identifier copy_file_range_f;
+@@
+  struct file_operations fops = {
+    .copy_file_range = copy_file_range_f,
+  };
+
+@ has_remap_file_range @
+identifier fops0.fops;
+identifier remap_file_range_f;
+@@
+  struct file_operations fops = {
+    .remap_file_range = remap_file_range_f,
+  };
+
+@ has_splice_read @
+identifier fops0.fops;
+identifier splice_read_f;
+@@
+  struct file_operations fops = {
+    .splice_read = splice_read_f,
+  };
+
+@ has_splice_write @
+identifier fops0.fops;
+identifier splice_write_f;
+@@
+  struct file_operations fops = {
+    .splice_write = splice_write_f,
+  };
+
+
+// file_operations that is candidate for stream_open conversion - it does not
+// use mmap and other methods that assume @offset access to file.
+//
+// XXX for simplicity require no .{read/write}_iter and no .splice_{read/write} for now.
+// XXX maybe_steam.fops cannot be used in other rules - it gives "bad rule maybe_stream or bad variable fops".
+@ maybe_stream depends on (!has_llseek || has_no_llseek) && !has_mmap && !has_copy_file_range && !has_remap_file_range && !has_read_iter && !has_write_iter && !has_splice_read && !has_splice_write @
+identifier fops0.fops;
+@@
+  struct file_operations fops = {
+  };
+
+
+// ---- conversions ----
+
+// XXX .open = nonseekable_open -> .open = stream_open
+// XXX .open = func -> openfunc -> nonseekable_open
+
+// read & write
+//
+// if both are used in the same file_operations together with an opener -
+// under that conditions we can use stream_open instead of nonseekable_open.
+@ fops_rw depends on maybe_stream @
+identifier fops0.fops, openfunc;
+identifier stream_reader.readstream;
+identifier stream_writer.writestream;
+@@
+  struct file_operations fops = {
+      .open  = openfunc,
+      .read  = readstream,
+      .write = writestream,
+  };
+
+@ report_rw depends on report @
+identifier fops_rw.openfunc;
+position p1;
+@@
+  openfunc(...) {
+    <...
+     nonseekable_open@p1
+    ...>
+  }
+
+@ script:python depends on report && reader_blocks @
+fops << fops0.fops;
+p << report_rw.p1;
+@@
+coccilib.report.print_report(p[0],
+  "ERROR: %s: .read() can deadlock .write(); change nonseekable_open -> stream_open to fix." % (fops,))
+
+@ script:python depends on report && !reader_blocks @
+fops << fops0.fops;
+p << report_rw.p1;
+@@
+coccilib.report.print_report(p[0],
+  "WARNING: %s: .read() and .write() have stream semantic; safe to change nonseekable_open -> stream_open." % (fops,))
+
+
+@ explain_rw_deadlocked depends on explain && reader_blocks @
+identifier fops_rw.openfunc;
+@@
+  openfunc(...) {
+    <...
+-    nonseekable_open
++    nonseekable_open /* read & write (was deadlock) */
+    ...>
+  }
+
+
+@ explain_rw_nodeadlock depends on explain && !reader_blocks @
+identifier fops_rw.openfunc;
+@@
+  openfunc(...) {
+    <...
+-    nonseekable_open
++    nonseekable_open /* read & write (no direct deadlock) */
+    ...>
+  }
+
+@ patch_rw depends on patch @
+identifier fops_rw.openfunc;
+@@
+  openfunc(...) {
+    <...
+-   nonseekable_open
++   stream_open
+    ...>
+  }
+
+
+// read, but not write
+@ fops_r depends on maybe_stream && !has_write @
+identifier fops0.fops, openfunc;
+identifier stream_reader.readstream;
+@@
+  struct file_operations fops = {
+      .open  = openfunc,
+      .read  = readstream,
+  };
+
+@ report_r depends on report @
+identifier fops_r.openfunc;
+position p1;
+@@
+  openfunc(...) {
+    <...
+    nonseekable_open@p1
+    ...>
+  }
+
+@ script:python depends on report @
+fops << fops0.fops;
+p << report_r.p1;
+@@
+coccilib.report.print_report(p[0],
+  "WARNING: %s: .read() has stream semantic; safe to change nonseekable_open -> stream_open." % (fops,))
+
+@ explain_r depends on explain @
+identifier fops_r.openfunc;
+@@
+  openfunc(...) {
+    <...
+-   nonseekable_open
++   nonseekable_open /* read only */
+    ...>
+  }
+
+@ patch_r depends on patch @
+identifier fops_r.openfunc;
+@@
+  openfunc(...) {
+    <...
+-   nonseekable_open
++   stream_open
+    ...>
+  }
+
+
+// write, but not read
+@ fops_w depends on maybe_stream && !has_read @
+identifier fops0.fops, openfunc;
+identifier stream_writer.writestream;
+@@
+  struct file_operations fops = {
+      .open  = openfunc,
+      .write = writestream,
+  };
+
+@ report_w depends on report @
+identifier fops_w.openfunc;
+position p1;
+@@
+  openfunc(...) {
+    <...
+    nonseekable_open@p1
+    ...>
+  }
+
+@ script:python depends on report @
+fops << fops0.fops;
+p << report_w.p1;
+@@
+coccilib.report.print_report(p[0],
+  "WARNING: %s: .write() has stream semantic; safe to change nonseekable_open -> stream_open." % (fops,))
+
+@ explain_w depends on explain @
+identifier fops_w.openfunc;
+@@
+  openfunc(...) {
+    <...
+-   nonseekable_open
++   nonseekable_open /* write only */
+    ...>
+  }
+
+@ patch_w depends on patch @
+identifier fops_w.openfunc;
+@@
+  openfunc(...) {
+    <...
+-   nonseekable_open
++   stream_open
+    ...>
+  }
+
+
+// no read, no write - don't change anything
diff --git a/scripts/coccinelle/free/put_device.cocci b/scripts/coccinelle/free/put_device.cocci
index 7395697e7f19..c9f071b0a0ab 100644
--- a/scripts/coccinelle/free/put_device.cocci
+++ b/scripts/coccinelle/free/put_device.cocci
@@ -32,6 +32,7 @@ if (id == NULL || ...) { ... return ...; }
 (    id
 |    (T2)dev_get_drvdata(&id->dev)
 |    (T3)platform_get_drvdata(id)
+|    &id->dev
 );
 | return@p2 ...;
 )
diff --git a/scripts/coccinelle/misc/badty.cocci b/scripts/coccinelle/misc/badty.cocci
index 481cf301ccfc..08470362199c 100644
--- a/scripts/coccinelle/misc/badty.cocci
+++ b/scripts/coccinelle/misc/badty.cocci
@@ -1,4 +1,4 @@
-/// Use ARRAY_SIZE instead of dividing sizeof array with sizeof an element
+/// Correct the size argument to alloc functions
 ///
 //# This makes an effort to find cases where the argument to sizeof is wrong
 //# in memory allocation functions by checking the type of the allocated memory
diff --git a/scripts/kconfig/lxdialog/inputbox.c b/scripts/kconfig/lxdialog/inputbox.c
index 611945611bf8..1dcfb288ee63 100644
--- a/scripts/kconfig/lxdialog/inputbox.c
+++ b/scripts/kconfig/lxdialog/inputbox.c
@@ -113,7 +113,8 @@ do_resize:
 			case KEY_DOWN:
 				break;
 			case KEY_BACKSPACE:
-			case 127:
+			case 8:   /* ^H */
+			case 127: /* ^? */
 				if (pos) {
 					wattrset(dialog, dlg.inputbox.atr);
 					if (input_x == 0) {
diff --git a/scripts/kconfig/nconf.c b/scripts/kconfig/nconf.c
index a4670f4e825a..ac92c0ded6c5 100644
--- a/scripts/kconfig/nconf.c
+++ b/scripts/kconfig/nconf.c
@@ -1048,7 +1048,7 @@ static int do_match(int key, struct match_state *state, int *ans)
 		state->match_direction = FIND_NEXT_MATCH_UP;
 		*ans = get_mext_match(state->pattern,
 				state->match_direction);
-	} else if (key == KEY_BACKSPACE || key == 127) {
+	} else if (key == KEY_BACKSPACE || key == 8 || key == 127) {
 		state->pattern[strlen(state->pattern)-1] = '\0';
 		adj_match_dir(&state->match_direction);
 	} else
diff --git a/scripts/kconfig/nconf.gui.c b/scripts/kconfig/nconf.gui.c
index 7be620a1fcdb..77f525a8617c 100644
--- a/scripts/kconfig/nconf.gui.c
+++ b/scripts/kconfig/nconf.gui.c
@@ -439,7 +439,8 @@ int dialog_inputbox(WINDOW *main_window,
 		case KEY_F(F_EXIT):
 		case KEY_F(F_BACK):
 			break;
-		case 127:
+		case 8:   /* ^H */
+		case 127: /* ^? */
 		case KEY_BACKSPACE:
 			if (cursor_position > 0) {
 				memmove(&result[cursor_position-1],
diff --git a/scripts/mod/modpost.c b/scripts/mod/modpost.c
index 0b0d1080b1c5..f277e116e0eb 100644
--- a/scripts/mod/modpost.c
+++ b/scripts/mod/modpost.c
@@ -639,7 +639,7 @@ static void handle_modversions(struct module *mod, struct elf_info *info,
 			       info->sechdrs[sym->st_shndx].sh_offset -
 			       (info->hdr->e_type != ET_REL ?
 				info->sechdrs[sym->st_shndx].sh_addr : 0);
-			crc = *crcp;
+			crc = TO_NATIVE(*crcp);
 		}
 		sym_update_crc(symname + strlen("__crc_"), mod, crc,
 				export);
diff --git a/scripts/selinux/genheaders/genheaders.c b/scripts/selinux/genheaders/genheaders.c
index 1ceedea847dd..544ca126a8a8 100644
--- a/scripts/selinux/genheaders/genheaders.c
+++ b/scripts/selinux/genheaders/genheaders.c
@@ -9,7 +9,6 @@
 #include <string.h>
 #include <errno.h>
 #include <ctype.h>
-#include <sys/socket.h>
 
 struct security_class_mapping {
 	const char *name;
diff --git a/scripts/selinux/mdp/mdp.c b/scripts/selinux/mdp/mdp.c
index 073fe7537f6c..6d51b74bc679 100644
--- a/scripts/selinux/mdp/mdp.c
+++ b/scripts/selinux/mdp/mdp.c
@@ -32,7 +32,6 @@
 #include <stdlib.h>
 #include <unistd.h>
 #include <string.h>
-#include <sys/socket.h>
 
 static void usage(char *name)
 {
diff --git a/security/Kconfig b/security/Kconfig
index 1d6463fb1450..353cfef71d4e 100644
--- a/security/Kconfig
+++ b/security/Kconfig
@@ -239,8 +239,46 @@ source "security/safesetid/Kconfig"
 
 source "security/integrity/Kconfig"
 
+choice
+	prompt "First legacy 'major LSM' to be initialized"
+	default DEFAULT_SECURITY_SELINUX if SECURITY_SELINUX
+	default DEFAULT_SECURITY_SMACK if SECURITY_SMACK
+	default DEFAULT_SECURITY_TOMOYO if SECURITY_TOMOYO
+	default DEFAULT_SECURITY_APPARMOR if SECURITY_APPARMOR
+	default DEFAULT_SECURITY_DAC
+
+	help
+	  This choice is there only for converting CONFIG_DEFAULT_SECURITY
+	  in old kernel configs to CONFIG_LSM in new kernel configs. Don't
+	  change this choice unless you are creating a fresh kernel config,
+	  for this choice will be ignored after CONFIG_LSM has been set.
+
+	  Selects the legacy "major security module" that will be
+	  initialized first. Overridden by non-default CONFIG_LSM.
+
+	config DEFAULT_SECURITY_SELINUX
+		bool "SELinux" if SECURITY_SELINUX=y
+
+	config DEFAULT_SECURITY_SMACK
+		bool "Simplified Mandatory Access Control" if SECURITY_SMACK=y
+
+	config DEFAULT_SECURITY_TOMOYO
+		bool "TOMOYO" if SECURITY_TOMOYO=y
+
+	config DEFAULT_SECURITY_APPARMOR
+		bool "AppArmor" if SECURITY_APPARMOR=y
+
+	config DEFAULT_SECURITY_DAC
+		bool "Unix Discretionary Access Controls"
+
+endchoice
+
 config LSM
 	string "Ordered list of enabled LSMs"
+	default "yama,loadpin,safesetid,integrity,smack,selinux,tomoyo,apparmor" if DEFAULT_SECURITY_SMACK
+	default "yama,loadpin,safesetid,integrity,apparmor,selinux,smack,tomoyo" if DEFAULT_SECURITY_APPARMOR
+	default "yama,loadpin,safesetid,integrity,tomoyo" if DEFAULT_SECURITY_TOMOYO
+	default "yama,loadpin,safesetid,integrity" if DEFAULT_SECURITY_DAC
 	default "yama,loadpin,safesetid,integrity,selinux,smack,tomoyo,apparmor"
 	help
 	  A comma-separated list of LSMs, in initialization order.
diff --git a/security/apparmor/apparmorfs.c b/security/apparmor/apparmorfs.c
index fefee040bf79..b9298d2e8165 100644
--- a/security/apparmor/apparmorfs.c
+++ b/security/apparmor/apparmorfs.c
@@ -123,17 +123,22 @@ static int aafs_show_path(struct seq_file *seq, struct dentry *dentry)
 	return 0;
 }
 
-static void aafs_evict_inode(struct inode *inode)
+static void aafs_i_callback(struct rcu_head *head)
 {
-	truncate_inode_pages_final(&inode->i_data);
-	clear_inode(inode);
+	struct inode *inode = container_of(head, struct inode, i_rcu);
 	if (S_ISLNK(inode->i_mode))
 		kfree(inode->i_link);
+	free_inode_nonrcu(inode);
+}
+
+static void aafs_destroy_inode(struct inode *inode)
+{
+	call_rcu(&inode->i_rcu, aafs_i_callback);
 }
 
 static const struct super_operations aafs_super_ops = {
 	.statfs = simple_statfs,
-	.evict_inode = aafs_evict_inode,
+	.destroy_inode = aafs_destroy_inode,
 	.show_path = aafs_show_path,
 };
 
diff --git a/security/apparmor/crypto.c b/security/apparmor/crypto.c
index af03d98c7552..baba63bc66b1 100644
--- a/security/apparmor/crypto.c
+++ b/security/apparmor/crypto.c
@@ -43,7 +43,6 @@ char *aa_calc_hash(void *data, size_t len)
 		goto fail;
 
 	desc->tfm = apparmor_tfm;
-	desc->flags = 0;
 
 	error = crypto_shash_init(desc);
 	if (error)
@@ -81,7 +80,6 @@ int aa_calc_profile_hash(struct aa_profile *profile, u32 version, void *start,
 		goto fail;
 
 	desc->tfm = apparmor_tfm;
-	desc->flags = 0;
 
 	error = crypto_shash_init(desc);
 	if (error)
diff --git a/security/apparmor/lsm.c b/security/apparmor/lsm.c
index 49d664ddff44..87500bde5a92 100644
--- a/security/apparmor/lsm.c
+++ b/security/apparmor/lsm.c
@@ -1336,9 +1336,16 @@ module_param_named(path_max, aa_g_path_max, aauint, S_IRUSR);
 bool aa_g_paranoid_load = true;
 module_param_named(paranoid_load, aa_g_paranoid_load, aabool, S_IRUGO);
 
+static int param_get_aaintbool(char *buffer, const struct kernel_param *kp);
+static int param_set_aaintbool(const char *val, const struct kernel_param *kp);
+#define param_check_aaintbool param_check_int
+static const struct kernel_param_ops param_ops_aaintbool = {
+	.set = param_set_aaintbool,
+	.get = param_get_aaintbool
+};
 /* Boot time disable flag */
 static int apparmor_enabled __lsm_ro_after_init = 1;
-module_param_named(enabled, apparmor_enabled, int, 0444);
+module_param_named(enabled, apparmor_enabled, aaintbool, 0444);
 
 static int __init apparmor_enabled_setup(char *str)
 {
@@ -1413,6 +1420,46 @@ static int param_get_aauint(char *buffer, const struct kernel_param *kp)
 	return param_get_uint(buffer, kp);
 }
 
+/* Can only be set before AppArmor is initialized (i.e. on boot cmdline). */
+static int param_set_aaintbool(const char *val, const struct kernel_param *kp)
+{
+	struct kernel_param kp_local;
+	bool value;
+	int error;
+
+	if (apparmor_initialized)
+		return -EPERM;
+
+	/* Create local copy, with arg pointing to bool type. */
+	value = !!*((int *)kp->arg);
+	memcpy(&kp_local, kp, sizeof(kp_local));
+	kp_local.arg = &value;
+
+	error = param_set_bool(val, &kp_local);
+	if (!error)
+		*((int *)kp->arg) = *((bool *)kp_local.arg);
+	return error;
+}
+
+/*
+ * To avoid changing /sys/module/apparmor/parameters/enabled from Y/N to
+ * 1/0, this converts the "int that is actually bool" back to bool for
+ * display in the /sys filesystem, while keeping it "int" for the LSM
+ * infrastructure.
+ */
+static int param_get_aaintbool(char *buffer, const struct kernel_param *kp)
+{
+	struct kernel_param kp_local;
+	bool value;
+
+	/* Create local copy, with arg pointing to bool type. */
+	value = !!*((int *)kp->arg);
+	memcpy(&kp_local, kp, sizeof(kp_local));
+	kp_local.arg = &value;
+
+	return param_get_bool(buffer, &kp_local);
+}
+
 static int param_get_audit(char *buffer, const struct kernel_param *kp)
 {
 	if (!apparmor_enabled)
diff --git a/security/device_cgroup.c b/security/device_cgroup.c
index cd97929fac66..dc28914fa72e 100644
--- a/security/device_cgroup.c
+++ b/security/device_cgroup.c
@@ -560,7 +560,7 @@ static int propagate_exception(struct dev_cgroup *devcg_root,
 		    devcg->behavior == DEVCG_DEFAULT_ALLOW) {
 			rc = dev_exception_add(devcg, ex);
 			if (rc)
-				break;
+				return rc;
 		} else {
 			/*
 			 * in the other possible cases:
diff --git a/security/inode.c b/security/inode.c
index b7772a9b315e..421dd72b5876 100644
--- a/security/inode.c
+++ b/security/inode.c
@@ -27,17 +27,22 @@
 static struct vfsmount *mount;
 static int mount_count;
 
-static void securityfs_evict_inode(struct inode *inode)
+static void securityfs_i_callback(struct rcu_head *head)
 {
-	truncate_inode_pages_final(&inode->i_data);
-	clear_inode(inode);
+	struct inode *inode = container_of(head, struct inode, i_rcu);
 	if (S_ISLNK(inode->i_mode))
 		kfree(inode->i_link);
+	free_inode_nonrcu(inode);
+}
+
+static void securityfs_destroy_inode(struct inode *inode)
+{
+	call_rcu(&inode->i_rcu, securityfs_i_callback);
 }
 
 static const struct super_operations securityfs_super_operations = {
 	.statfs		= simple_statfs,
-	.evict_inode	= securityfs_evict_inode,
+	.destroy_inode	= securityfs_destroy_inode,
 };
 
 static int fill_super(struct super_block *sb, void *data, int silent)
diff --git a/security/integrity/Kconfig b/security/integrity/Kconfig
index 2ea4ec9991d5..3ba1168b1756 100644
--- a/security/integrity/Kconfig
+++ b/security/integrity/Kconfig
@@ -55,13 +55,22 @@ config INTEGRITY_PLATFORM_KEYRING
         bool "Provide keyring for platform/firmware trusted keys"
         depends on INTEGRITY_ASYMMETRIC_KEYS
         depends on SYSTEM_BLACKLIST_KEYRING
-        depends on EFI
         help
          Provide a separate, distinct keyring for platform trusted keys, which
          the kernel automatically populates during initialization from values
          provided by the platform for verifying the kexec'ed kerned image
          and, possibly, the initramfs signature.
 
+config LOAD_UEFI_KEYS
+       depends on INTEGRITY_PLATFORM_KEYRING
+       depends on EFI
+       def_bool y
+
+config LOAD_IPL_KEYS
+       depends on INTEGRITY_PLATFORM_KEYRING
+       depends on S390
+       def_bool y
+
 config INTEGRITY_AUDIT
 	bool "Enables integrity auditing support "
 	depends on AUDIT
diff --git a/security/integrity/Makefile b/security/integrity/Makefile
index 86df9aba8c0f..19faace69644 100644
--- a/security/integrity/Makefile
+++ b/security/integrity/Makefile
@@ -9,10 +9,10 @@ integrity-y := iint.o
 integrity-$(CONFIG_INTEGRITY_AUDIT) += integrity_audit.o
 integrity-$(CONFIG_INTEGRITY_SIGNATURE) += digsig.o
 integrity-$(CONFIG_INTEGRITY_ASYMMETRIC_KEYS) += digsig_asymmetric.o
-integrity-$(CONFIG_INTEGRITY_PLATFORM_KEYRING) += platform_certs/platform_keyring.o \
-						  platform_certs/efi_parser.o \
-						  platform_certs/load_uefi.o
-obj-$(CONFIG_LOAD_UEFI_KEYS) += platform_certs/load_uefi.o
+integrity-$(CONFIG_INTEGRITY_PLATFORM_KEYRING) += platform_certs/platform_keyring.o
+integrity-$(CONFIG_LOAD_UEFI_KEYS) += platform_certs/efi_parser.o \
+					platform_certs/load_uefi.o
+integrity-$(CONFIG_LOAD_IPL_KEYS) += platform_certs/load_ipl_s390.o
 $(obj)/load_uefi.o: KBUILD_CFLAGS += -fshort-wchar
 
 subdir-$(CONFIG_IMA)			+= ima
diff --git a/security/integrity/digsig_asymmetric.c b/security/integrity/digsig_asymmetric.c
index d775e03fbbcc..99080871eb9f 100644
--- a/security/integrity/digsig_asymmetric.c
+++ b/security/integrity/digsig_asymmetric.c
@@ -104,9 +104,16 @@ int asymmetric_verify(struct key *keyring, const char *sig,
 
 	memset(&pks, 0, sizeof(pks));
 
-	pks.pkey_algo = "rsa";
 	pks.hash_algo = hash_algo_name[hdr->hash_algo];
-	pks.encoding = "pkcs1";
+	if (hdr->hash_algo == HASH_ALGO_STREEBOG_256 ||
+	    hdr->hash_algo == HASH_ALGO_STREEBOG_512) {
+		/* EC-RDSA and Streebog should go together. */
+		pks.pkey_algo = "ecrdsa";
+		pks.encoding = "raw";
+	} else {
+		pks.pkey_algo = "rsa";
+		pks.encoding = "pkcs1";
+	}
 	pks.digest = (u8 *)data;
 	pks.digest_size = datalen;
 	pks.s = hdr->sig;
diff --git a/security/integrity/evm/evm_crypto.c b/security/integrity/evm/evm_crypto.c
index c37d08118af5..e11564eb645b 100644
--- a/security/integrity/evm/evm_crypto.c
+++ b/security/integrity/evm/evm_crypto.c
@@ -124,7 +124,6 @@ out:
 		return ERR_PTR(-ENOMEM);
 
 	desc->tfm = *tfm;
-	desc->flags = CRYPTO_TFM_REQ_MAY_SLEEP;
 
 	rc = crypto_shash_init(desc);
 	if (rc) {
diff --git a/security/integrity/ima/ima_crypto.c b/security/integrity/ima/ima_crypto.c
index 16a4f45863b1..a32878e10ebc 100644
--- a/security/integrity/ima/ima_crypto.c
+++ b/security/integrity/ima/ima_crypto.c
@@ -333,7 +333,6 @@ static int ima_calc_file_hash_tfm(struct file *file,
 	SHASH_DESC_ON_STACK(shash, tfm);
 
 	shash->tfm = tfm;
-	shash->flags = 0;
 
 	hash->length = crypto_shash_digestsize(tfm);
 
@@ -469,7 +468,6 @@ static int ima_calc_field_array_hash_tfm(struct ima_field_data *field_data,
 	int rc, i;
 
 	shash->tfm = tfm;
-	shash->flags = 0;
 
 	hash->length = crypto_shash_digestsize(tfm);
 
@@ -591,7 +589,6 @@ static int calc_buffer_shash_tfm(const void *buf, loff_t size,
 	int rc;
 
 	shash->tfm = tfm;
-	shash->flags = 0;
 
 	hash->length = crypto_shash_digestsize(tfm);
 
@@ -664,7 +661,6 @@ static int __init ima_calc_boot_aggregate_tfm(char *digest,
 	SHASH_DESC_ON_STACK(shash, tfm);
 
 	shash->tfm = tfm;
-	shash->flags = 0;
 
 	rc = crypto_shash_init(shash);
 	if (rc != 0)
diff --git a/security/integrity/platform_certs/load_ipl_s390.c b/security/integrity/platform_certs/load_ipl_s390.c
new file mode 100644
index 000000000000..e769dcb7ea94
--- /dev/null
+++ b/security/integrity/platform_certs/load_ipl_s390.c
@@ -0,0 +1,36 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#include <linux/kernel.h>
+#include <linux/sched.h>
+#include <linux/cred.h>
+#include <linux/err.h>
+#include <linux/efi.h>
+#include <linux/slab.h>
+#include <keys/asymmetric-type.h>
+#include <keys/system_keyring.h>
+#include <asm/boot_data.h>
+#include "../integrity.h"
+
+/*
+ * Load the certs contained in the IPL report created by the machine loader
+ * into the platform trusted keyring.
+ */
+static int __init load_ipl_certs(void)
+{
+	void *ptr, *end;
+	unsigned int len;
+
+	if (!ipl_cert_list_addr)
+		return 0;
+	/* Copy the certificates to the system keyring */
+	ptr = (void *) ipl_cert_list_addr;
+	end = ptr + ipl_cert_list_size;
+	while ((void *) ptr < end) {
+		len = *(unsigned int *) ptr;
+		ptr += sizeof(unsigned int);
+		add_to_platform_keyring("IPL:db", ptr, len);
+		ptr += len;
+	}
+	return 0;
+}
+late_initcall(load_ipl_certs);
diff --git a/security/keys/dh.c b/security/keys/dh.c
index 711e89d8c415..23f95dec771b 100644
--- a/security/keys/dh.c
+++ b/security/keys/dh.c
@@ -112,7 +112,6 @@ static int kdf_alloc(struct kdf_sdesc **sdesc_ret, char *hashname)
 	if (!sdesc)
 		goto out_free_tfm;
 	sdesc->shash.tfm = tfm;
-	sdesc->shash.flags = 0x0;
 
 	*sdesc_ret = sdesc;
 
diff --git a/security/keys/encrypted-keys/encrypted.c b/security/keys/encrypted-keys/encrypted.c
index 347108f660a1..1b1456b21a93 100644
--- a/security/keys/encrypted-keys/encrypted.c
+++ b/security/keys/encrypted-keys/encrypted.c
@@ -333,7 +333,6 @@ static int calc_hash(struct crypto_shash *tfm, u8 *digest,
 	int err;
 
 	desc->tfm = tfm;
-	desc->flags = 0;
 
 	err = crypto_shash_digest(desc, buf, buflen, digest);
 	shash_desc_zero(desc);
diff --git a/security/keys/trusted.c b/security/keys/trusted.c
index bcc9c6ead7fd..a75b2f0f1230 100644
--- a/security/keys/trusted.c
+++ b/security/keys/trusted.c
@@ -55,7 +55,6 @@ static struct sdesc *init_sdesc(struct crypto_shash *alg)
 	if (!sdesc)
 		return ERR_PTR(-ENOMEM);
 	sdesc->shash.tfm = alg;
-	sdesc->shash.flags = 0x0;
 	return sdesc;
 }
 
@@ -125,7 +124,7 @@ out:
  */
 int TSS_authhmac(unsigned char *digest, const unsigned char *key,
 			unsigned int keylen, unsigned char *h1,
-			unsigned char *h2, unsigned char h3, ...)
+			unsigned char *h2, unsigned int h3, ...)
 {
 	unsigned char paramdigest[SHA1_DIGEST_SIZE];
 	struct sdesc *sdesc;
@@ -135,13 +134,16 @@ int TSS_authhmac(unsigned char *digest, const unsigned char *key,
 	int ret;
 	va_list argp;
 
+	if (!chip)
+		return -ENODEV;
+
 	sdesc = init_sdesc(hashalg);
 	if (IS_ERR(sdesc)) {
 		pr_info("trusted_key: can't alloc %s\n", hash_alg);
 		return PTR_ERR(sdesc);
 	}
 
-	c = h3;
+	c = !!h3;
 	ret = crypto_shash_init(&sdesc->shash);
 	if (ret < 0)
 		goto out;
@@ -196,6 +198,9 @@ int TSS_checkhmac1(unsigned char *buffer,
 	va_list argp;
 	int ret;
 
+	if (!chip)
+		return -ENODEV;
+
 	bufsize = LOAD32(buffer, TPM_SIZE_OFFSET);
 	tag = LOAD16(buffer, 0);
 	ordinal = command;
@@ -363,6 +368,9 @@ int trusted_tpm_send(unsigned char *cmd, size_t buflen)
 {
 	int rc;
 
+	if (!chip)
+		return -ENODEV;
+
 	dump_tpm_buf(cmd);
 	rc = tpm_send(chip, cmd, buflen);
 	dump_tpm_buf(cmd);
@@ -429,6 +437,9 @@ int oiap(struct tpm_buf *tb, uint32_t *handle, unsigned char *nonce)
 {
 	int ret;
 
+	if (!chip)
+		return -ENODEV;
+
 	INIT_BUF(tb);
 	store16(tb, TPM_TAG_RQU_COMMAND);
 	store32(tb, TPM_OIAP_SIZE);
@@ -1245,9 +1256,13 @@ static int __init init_trusted(void)
 {
 	int ret;
 
+	/* encrypted_keys.ko depends on successful load of this module even if
+	 * TPM is not used.
+	 */
 	chip = tpm_default_chip();
 	if (!chip)
-		return -ENOENT;
+		return 0;
+
 	ret = init_digests();
 	if (ret < 0)
 		goto err_put;
@@ -1269,10 +1284,12 @@ err_put:
 
 static void __exit cleanup_trusted(void)
 {
-	put_device(&chip->dev);
-	kfree(digests);
-	trusted_shash_release();
-	unregister_key_type(&key_type_trusted);
+	if (chip) {
+		put_device(&chip->dev);
+		kfree(digests);
+		trusted_shash_release();
+		unregister_key_type(&key_type_trusted);
+	}
 }
 
 late_initcall(init_trusted);
diff --git a/security/selinux/include/classmap.h b/security/selinux/include/classmap.h
index bd5fe0d3204a..201f7e588a29 100644
--- a/security/selinux/include/classmap.h
+++ b/security/selinux/include/classmap.h
@@ -1,5 +1,6 @@
 /* SPDX-License-Identifier: GPL-2.0 */
 #include <linux/capability.h>
+#include <linux/socket.h>
 
 #define COMMON_FILE_SOCK_PERMS "ioctl", "read", "write", "create", \
     "getattr", "setattr", "lock", "relabelfrom", "relabelto", "append", "map"
diff --git a/sound/core/info.c b/sound/core/info.c
index 96a074019c33..0eb169acc850 100644
--- a/sound/core/info.c
+++ b/sound/core/info.c
@@ -713,8 +713,11 @@ snd_info_create_entry(const char *name, struct snd_info_entry *parent,
 	INIT_LIST_HEAD(&entry->list);
 	entry->parent = parent;
 	entry->module = module;
-	if (parent)
+	if (parent) {
+		mutex_lock(&parent->access);
 		list_add_tail(&entry->list, &parent->children);
+		mutex_unlock(&parent->access);
+	}
 	return entry;
 }
 
@@ -792,7 +795,12 @@ void snd_info_free_entry(struct snd_info_entry * entry)
 	list_for_each_entry_safe(p, n, &entry->children, list)
 		snd_info_free_entry(p);
 
-	list_del(&entry->list);
+	p = entry->parent;
+	if (p) {
+		mutex_lock(&p->access);
+		list_del(&entry->list);
+		mutex_unlock(&p->access);
+	}
 	kfree(entry->name);
 	if (entry->private_free)
 		entry->private_free(entry);
diff --git a/sound/core/init.c b/sound/core/init.c
index 0c4dc40376a7..079c12d64b0e 100644
--- a/sound/core/init.c
+++ b/sound/core/init.c
@@ -382,14 +382,7 @@ int snd_card_disconnect(struct snd_card *card)
 	card->shutdown = 1;
 	spin_unlock(&card->files_lock);
 
-	/* phase 1: disable fops (user space) operations for ALSA API */
-	mutex_lock(&snd_card_mutex);
-	snd_cards[card->number] = NULL;
-	clear_bit(card->number, snd_cards_lock);
-	mutex_unlock(&snd_card_mutex);
-	
-	/* phase 2: replace file->f_op with special dummy operations */
-	
+	/* replace file->f_op with special dummy operations */
 	spin_lock(&card->files_lock);
 	list_for_each_entry(mfile, &card->files_list, list) {
 		/* it's critical part, use endless loop */
@@ -405,7 +398,7 @@ int snd_card_disconnect(struct snd_card *card)
 	}
 	spin_unlock(&card->files_lock);	
 
-	/* phase 3: notify all connected devices about disconnection */
+	/* notify all connected devices about disconnection */
 	/* at this point, they cannot respond to any calls except release() */
 
 #if IS_ENABLED(CONFIG_SND_MIXER_OSS)
@@ -421,6 +414,13 @@ int snd_card_disconnect(struct snd_card *card)
 		device_del(&card->card_dev);
 		card->registered = false;
 	}
+
+	/* disable fops (user space) operations for ALSA API */
+	mutex_lock(&snd_card_mutex);
+	snd_cards[card->number] = NULL;
+	clear_bit(card->number, snd_cards_lock);
+	mutex_unlock(&snd_card_mutex);
+
 #ifdef CONFIG_PM
 	wake_up(&card->power_sleep);
 #endif
diff --git a/sound/core/oss/pcm_oss.c b/sound/core/oss/pcm_oss.c
index d5b0d7ba83c4..f6ae68017608 100644
--- a/sound/core/oss/pcm_oss.c
+++ b/sound/core/oss/pcm_oss.c
@@ -940,6 +940,28 @@ static int snd_pcm_oss_change_params_locked(struct snd_pcm_substream *substream)
 	oss_frame_size = snd_pcm_format_physical_width(params_format(params)) *
 			 params_channels(params) / 8;
 
+	err = snd_pcm_oss_period_size(substream, params, sparams);
+	if (err < 0)
+		goto failure;
+
+	n = snd_pcm_plug_slave_size(substream, runtime->oss.period_bytes / oss_frame_size);
+	err = snd_pcm_hw_param_near(substream, sparams, SNDRV_PCM_HW_PARAM_PERIOD_SIZE, n, NULL);
+	if (err < 0)
+		goto failure;
+
+	err = snd_pcm_hw_param_near(substream, sparams, SNDRV_PCM_HW_PARAM_PERIODS,
+				     runtime->oss.periods, NULL);
+	if (err < 0)
+		goto failure;
+
+	snd_pcm_kernel_ioctl(substream, SNDRV_PCM_IOCTL_DROP, NULL);
+
+	err = snd_pcm_kernel_ioctl(substream, SNDRV_PCM_IOCTL_HW_PARAMS, sparams);
+	if (err < 0) {
+		pcm_dbg(substream->pcm, "HW_PARAMS failed: %i\n", err);
+		goto failure;
+	}
+
 #ifdef CONFIG_SND_PCM_OSS_PLUGINS
 	snd_pcm_oss_plugin_clear(substream);
 	if (!direct) {
@@ -974,27 +996,6 @@ static int snd_pcm_oss_change_params_locked(struct snd_pcm_substream *substream)
 	}
 #endif
 
-	err = snd_pcm_oss_period_size(substream, params, sparams);
-	if (err < 0)
-		goto failure;
-
-	n = snd_pcm_plug_slave_size(substream, runtime->oss.period_bytes / oss_frame_size);
-	err = snd_pcm_hw_param_near(substream, sparams, SNDRV_PCM_HW_PARAM_PERIOD_SIZE, n, NULL);
-	if (err < 0)
-		goto failure;
-
-	err = snd_pcm_hw_param_near(substream, sparams, SNDRV_PCM_HW_PARAM_PERIODS,
-				     runtime->oss.periods, NULL);
-	if (err < 0)
-		goto failure;
-
-	snd_pcm_kernel_ioctl(substream, SNDRV_PCM_IOCTL_DROP, NULL);
-
-	if ((err = snd_pcm_kernel_ioctl(substream, SNDRV_PCM_IOCTL_HW_PARAMS, sparams)) < 0) {
-		pcm_dbg(substream->pcm, "HW_PARAMS failed: %i\n", err);
-		goto failure;
-	}
-
 	if (runtime->oss.trigger) {
 		sw_params->start_threshold = 1;
 	} else {
diff --git a/sound/core/pcm_native.c b/sound/core/pcm_native.c
index f731f904e8cc..1d8452912b14 100644
--- a/sound/core/pcm_native.c
+++ b/sound/core/pcm_native.c
@@ -1445,8 +1445,15 @@ static int snd_pcm_pause(struct snd_pcm_substream *substream, int push)
 static int snd_pcm_pre_suspend(struct snd_pcm_substream *substream, int state)
 {
 	struct snd_pcm_runtime *runtime = substream->runtime;
-	if (runtime->status->state == SNDRV_PCM_STATE_SUSPENDED)
+	switch (runtime->status->state) {
+	case SNDRV_PCM_STATE_SUSPENDED:
 		return -EBUSY;
+	/* unresumable PCM state; return -EBUSY for skipping suspend */
+	case SNDRV_PCM_STATE_OPEN:
+	case SNDRV_PCM_STATE_SETUP:
+	case SNDRV_PCM_STATE_DISCONNECTED:
+		return -EBUSY;
+	}
 	runtime->trigger_master = substream;
 	return 0;
 }
diff --git a/sound/core/rawmidi.c b/sound/core/rawmidi.c
index ee601d7f0926..c0690d1ecd55 100644
--- a/sound/core/rawmidi.c
+++ b/sound/core/rawmidi.c
@@ -30,6 +30,7 @@
 #include <linux/module.h>
 #include <linux/delay.h>
 #include <linux/mm.h>
+#include <linux/nospec.h>
 #include <sound/rawmidi.h>
 #include <sound/info.h>
 #include <sound/control.h>
@@ -601,6 +602,7 @@ static int __snd_rawmidi_info_select(struct snd_card *card,
 		return -ENXIO;
 	if (info->stream < 0 || info->stream > 1)
 		return -EINVAL;
+	info->stream = array_index_nospec(info->stream, 2);
 	pstr = &rmidi->streams[info->stream];
 	if (pstr->substream_count == 0)
 		return -ENOENT;
diff --git a/sound/core/seq/oss/seq_oss_synth.c b/sound/core/seq/oss/seq_oss_synth.c
index 278ebb993122..c93945917235 100644
--- a/sound/core/seq/oss/seq_oss_synth.c
+++ b/sound/core/seq/oss/seq_oss_synth.c
@@ -617,13 +617,14 @@ int
 snd_seq_oss_synth_make_info(struct seq_oss_devinfo *dp, int dev, struct synth_info *inf)
 {
 	struct seq_oss_synth *rec;
+	struct seq_oss_synthinfo *info = get_synthinfo_nospec(dp, dev);
 
-	if (dev < 0 || dev >= dp->max_synthdev)
+	if (!info)
 		return -ENXIO;
 
-	if (dp->synths[dev].is_midi) {
+	if (info->is_midi) {
 		struct midi_info minf;
-		snd_seq_oss_midi_make_info(dp, dp->synths[dev].midi_mapped, &minf);
+		snd_seq_oss_midi_make_info(dp, info->midi_mapped, &minf);
 		inf->synth_type = SYNTH_TYPE_MIDI;
 		inf->synth_subtype = 0;
 		inf->nr_voices = 16;
diff --git a/sound/core/seq/seq_clientmgr.c b/sound/core/seq/seq_clientmgr.c
index 7d4640d1fe9f..38e7deab6384 100644
--- a/sound/core/seq/seq_clientmgr.c
+++ b/sound/core/seq/seq_clientmgr.c
@@ -1252,7 +1252,7 @@ static int snd_seq_ioctl_set_client_info(struct snd_seq_client *client,
 
 	/* fill the info fields */
 	if (client_info->name[0])
-		strlcpy(client->name, client_info->name, sizeof(client->name));
+		strscpy(client->name, client_info->name, sizeof(client->name));
 
 	client->filter = client_info->filter;
 	client->event_lost = client_info->event_lost;
@@ -1530,7 +1530,7 @@ static int snd_seq_ioctl_create_queue(struct snd_seq_client *client, void *arg)
 	/* set queue name */
 	if (!info->name[0])
 		snprintf(info->name, sizeof(info->name), "Queue-%d", q->queue);
-	strlcpy(q->name, info->name, sizeof(q->name));
+	strscpy(q->name, info->name, sizeof(q->name));
 	snd_use_lock_free(&q->use_lock);
 
 	return 0;
@@ -1592,7 +1592,7 @@ static int snd_seq_ioctl_set_queue_info(struct snd_seq_client *client,
 		queuefree(q);
 		return -EPERM;
 	}
-	strlcpy(q->name, info->name, sizeof(q->name));
+	strscpy(q->name, info->name, sizeof(q->name));
 	queuefree(q);
 
 	return 0;
diff --git a/sound/hda/ext/hdac_ext_bus.c b/sound/hda/ext/hdac_ext_bus.c
index 9c37d9af3023..ec7715c6b0c0 100644
--- a/sound/hda/ext/hdac_ext_bus.c
+++ b/sound/hda/ext/hdac_ext_bus.c
@@ -107,7 +107,6 @@ int snd_hdac_ext_bus_init(struct hdac_bus *bus, struct device *dev,
 	INIT_LIST_HEAD(&bus->hlink_list);
 	bus->idx = idx++;
 
-	mutex_init(&bus->lock);
 	bus->cmd_dma_state = true;
 
 	return 0;
diff --git a/sound/hda/hdac_bus.c b/sound/hda/hdac_bus.c
index 012305177f68..ad8eee08013f 100644
--- a/sound/hda/hdac_bus.c
+++ b/sound/hda/hdac_bus.c
@@ -38,6 +38,7 @@ int snd_hdac_bus_init(struct hdac_bus *bus, struct device *dev,
 	INIT_WORK(&bus->unsol_work, snd_hdac_bus_process_unsol_events);
 	spin_lock_init(&bus->reg_lock);
 	mutex_init(&bus->cmd_mutex);
+	mutex_init(&bus->lock);
 	bus->irq = -1;
 	return 0;
 }
diff --git a/sound/hda/hdac_component.c b/sound/hda/hdac_component.c
index 5c95933e739a..1ea51e3b942a 100644
--- a/sound/hda/hdac_component.c
+++ b/sound/hda/hdac_component.c
@@ -69,13 +69,15 @@ void snd_hdac_display_power(struct hdac_bus *bus, unsigned int idx, bool enable)
 
 	dev_dbg(bus->dev, "display power %s\n",
 		enable ? "enable" : "disable");
+
+	mutex_lock(&bus->lock);
 	if (enable)
 		set_bit(idx, &bus->display_power_status);
 	else
 		clear_bit(idx, &bus->display_power_status);
 
 	if (!acomp || !acomp->ops)
-		return;
+		goto unlock;
 
 	if (bus->display_power_status) {
 		if (!bus->display_power_active) {
@@ -92,6 +94,8 @@ void snd_hdac_display_power(struct hdac_bus *bus, unsigned int idx, bool enable)
 			bus->display_power_active = false;
 		}
 	}
+ unlock:
+	mutex_unlock(&bus->lock);
 }
 EXPORT_SYMBOL_GPL(snd_hdac_display_power);
 
diff --git a/sound/pci/hda/hda_codec.c b/sound/pci/hda/hda_codec.c
index ec0b8595eb4d..701a69d856f5 100644
--- a/sound/pci/hda/hda_codec.c
+++ b/sound/pci/hda/hda_codec.c
@@ -969,6 +969,7 @@ int snd_hda_codec_device_new(struct hda_bus *bus, struct snd_card *card,
 
 	/* power-up all before initialization */
 	hda_set_power_state(codec, AC_PWRST_D0);
+	codec->core.dev.power.power_state = PMSG_ON;
 
 	snd_hda_codec_proc_new(codec);
 
diff --git a/sound/pci/hda/hda_intel.c b/sound/pci/hda/hda_intel.c
index ece256a3b48f..2ec91085fa3e 100644
--- a/sound/pci/hda/hda_intel.c
+++ b/sound/pci/hda/hda_intel.c
@@ -2142,6 +2142,8 @@ static struct snd_pci_quirk power_save_blacklist[] = {
 	SND_PCI_QUIRK(0x8086, 0x2040, "Intel DZ77BH-55K", 0),
 	/* https://bugzilla.kernel.org/show_bug.cgi?id=199607 */
 	SND_PCI_QUIRK(0x8086, 0x2057, "Intel NUC5i7RYB", 0),
+	/* https://bugs.launchpad.net/bugs/1821663 */
+	SND_PCI_QUIRK(0x8086, 0x2064, "Intel SDP 8086:2064", 0),
 	/* https://bugzilla.redhat.com/show_bug.cgi?id=1520902 */
 	SND_PCI_QUIRK(0x8086, 0x2068, "Intel NUC7i3BNB", 0),
 	/* https://bugzilla.kernel.org/show_bug.cgi?id=198611 */
@@ -2150,6 +2152,8 @@ static struct snd_pci_quirk power_save_blacklist[] = {
 	SND_PCI_QUIRK(0x17aa, 0x367b, "Lenovo IdeaCentre B550", 0),
 	/* https://bugzilla.redhat.com/show_bug.cgi?id=1572975 */
 	SND_PCI_QUIRK(0x17aa, 0x36a7, "Lenovo C50 All in one", 0),
+	/* https://bugs.launchpad.net/bugs/1821663 */
+	SND_PCI_QUIRK(0x1631, 0xe017, "Packard Bell NEC IMEDIA 5204", 0),
 	{}
 };
 #endif /* CONFIG_PM */
diff --git a/sound/pci/hda/patch_ca0132.c b/sound/pci/hda/patch_ca0132.c
index 29882bda7632..e1ebc6d5f382 100644
--- a/sound/pci/hda/patch_ca0132.c
+++ b/sound/pci/hda/patch_ca0132.c
@@ -1005,7 +1005,6 @@ struct ca0132_spec {
 	unsigned int scp_resp_header;
 	unsigned int scp_resp_data[4];
 	unsigned int scp_resp_count;
-	bool alt_firmware_present;
 	bool startup_check_entered;
 	bool dsp_reload;
 
@@ -7518,7 +7517,7 @@ static bool ca0132_download_dsp_images(struct hda_codec *codec)
 	bool dsp_loaded = false;
 	struct ca0132_spec *spec = codec->spec;
 	const struct dsp_image_seg *dsp_os_image;
-	const struct firmware *fw_entry;
+	const struct firmware *fw_entry = NULL;
 	/*
 	 * Alternate firmwares for different variants. The Recon3Di apparently
 	 * can use the default firmware, but I'll leave the option in case
@@ -7529,33 +7528,26 @@ static bool ca0132_download_dsp_images(struct hda_codec *codec)
 	case QUIRK_R3D:
 	case QUIRK_AE5:
 		if (request_firmware(&fw_entry, DESKTOP_EFX_FILE,
-					codec->card->dev) != 0) {
+					codec->card->dev) != 0)
 			codec_dbg(codec, "Desktop firmware not found.");
-			spec->alt_firmware_present = false;
-		} else {
+		else
 			codec_dbg(codec, "Desktop firmware selected.");
-			spec->alt_firmware_present = true;
-		}
 		break;
 	case QUIRK_R3DI:
 		if (request_firmware(&fw_entry, R3DI_EFX_FILE,
-					codec->card->dev) != 0) {
+					codec->card->dev) != 0)
 			codec_dbg(codec, "Recon3Di alt firmware not detected.");
-			spec->alt_firmware_present = false;
-		} else {
+		else
 			codec_dbg(codec, "Recon3Di firmware selected.");
-			spec->alt_firmware_present = true;
-		}
 		break;
 	default:
-		spec->alt_firmware_present = false;
 		break;
 	}
 	/*
 	 * Use default ctefx.bin if no alt firmware is detected, or if none
 	 * exists for your particular codec.
 	 */
-	if (!spec->alt_firmware_present) {
+	if (!fw_entry) {
 		codec_dbg(codec, "Default firmware selected.");
 		if (request_firmware(&fw_entry, EFX_FILE,
 					codec->card->dev) != 0)
diff --git a/sound/pci/hda/patch_realtek.c b/sound/pci/hda/patch_realtek.c
index 191830d4fa40..42cd3945e0de 100644
--- a/sound/pci/hda/patch_realtek.c
+++ b/sound/pci/hda/patch_realtek.c
@@ -1864,8 +1864,8 @@ enum {
 	ALC887_FIXUP_BASS_CHMAP,
 	ALC1220_FIXUP_GB_DUAL_CODECS,
 	ALC1220_FIXUP_CLEVO_P950,
-	ALC1220_FIXUP_SYSTEM76_ORYP5,
-	ALC1220_FIXUP_SYSTEM76_ORYP5_PINS,
+	ALC1220_FIXUP_CLEVO_PB51ED,
+	ALC1220_FIXUP_CLEVO_PB51ED_PINS,
 };
 
 static void alc889_fixup_coef(struct hda_codec *codec,
@@ -2070,7 +2070,7 @@ static void alc1220_fixup_clevo_p950(struct hda_codec *codec,
 static void alc_fixup_headset_mode_no_hp_mic(struct hda_codec *codec,
 				const struct hda_fixup *fix, int action);
 
-static void alc1220_fixup_system76_oryp5(struct hda_codec *codec,
+static void alc1220_fixup_clevo_pb51ed(struct hda_codec *codec,
 				     const struct hda_fixup *fix,
 				     int action)
 {
@@ -2322,18 +2322,18 @@ static const struct hda_fixup alc882_fixups[] = {
 		.type = HDA_FIXUP_FUNC,
 		.v.func = alc1220_fixup_clevo_p950,
 	},
-	[ALC1220_FIXUP_SYSTEM76_ORYP5] = {
+	[ALC1220_FIXUP_CLEVO_PB51ED] = {
 		.type = HDA_FIXUP_FUNC,
-		.v.func = alc1220_fixup_system76_oryp5,
+		.v.func = alc1220_fixup_clevo_pb51ed,
 	},
-	[ALC1220_FIXUP_SYSTEM76_ORYP5_PINS] = {
+	[ALC1220_FIXUP_CLEVO_PB51ED_PINS] = {
 		.type = HDA_FIXUP_PINS,
 		.v.pins = (const struct hda_pintbl[]) {
 			{ 0x19, 0x01a1913c }, /* use as headset mic, without its own jack detect */
 			{}
 		},
 		.chained = true,
-		.chain_id = ALC1220_FIXUP_SYSTEM76_ORYP5,
+		.chain_id = ALC1220_FIXUP_CLEVO_PB51ED,
 	},
 };
 
@@ -2411,8 +2411,9 @@ static const struct snd_pci_quirk alc882_fixup_tbl[] = {
 	SND_PCI_QUIRK(0x1558, 0x9501, "Clevo P950HR", ALC1220_FIXUP_CLEVO_P950),
 	SND_PCI_QUIRK(0x1558, 0x95e1, "Clevo P95xER", ALC1220_FIXUP_CLEVO_P950),
 	SND_PCI_QUIRK(0x1558, 0x95e2, "Clevo P950ER", ALC1220_FIXUP_CLEVO_P950),
-	SND_PCI_QUIRK(0x1558, 0x96e1, "System76 Oryx Pro (oryp5)", ALC1220_FIXUP_SYSTEM76_ORYP5_PINS),
-	SND_PCI_QUIRK(0x1558, 0x97e1, "System76 Oryx Pro (oryp5)", ALC1220_FIXUP_SYSTEM76_ORYP5_PINS),
+	SND_PCI_QUIRK(0x1558, 0x96e1, "System76 Oryx Pro (oryp5)", ALC1220_FIXUP_CLEVO_PB51ED_PINS),
+	SND_PCI_QUIRK(0x1558, 0x97e1, "System76 Oryx Pro (oryp5)", ALC1220_FIXUP_CLEVO_PB51ED_PINS),
+	SND_PCI_QUIRK(0x1558, 0x65d1, "Tuxedo Book XC1509", ALC1220_FIXUP_CLEVO_PB51ED_PINS),
 	SND_PCI_QUIRK_VENDOR(0x1558, "Clevo laptop", ALC882_FIXUP_EAPD),
 	SND_PCI_QUIRK(0x161f, 0x2054, "Medion laptop", ALC883_FIXUP_EAPD),
 	SND_PCI_QUIRK(0x17aa, 0x3a0d, "Lenovo Y530", ALC882_FIXUP_LENOVO_Y530),
@@ -5449,6 +5450,8 @@ static void alc274_fixup_bind_dacs(struct hda_codec *codec,
 		return;
 
 	spec->gen.preferred_dacs = preferred_pairs;
+	spec->gen.auto_mute_via_amp = 1;
+	codec->power_save_node = 0;
 }
 
 /* The DAC of NID 0x3 will introduce click/pop noise on headphones, so invalidate it */
@@ -5491,7 +5494,7 @@ static void alc_headset_btn_callback(struct hda_codec *codec,
 	jack->jack->button_state = report;
 }
 
-static void alc295_fixup_chromebook(struct hda_codec *codec,
+static void alc_fixup_headset_jack(struct hda_codec *codec,
 				    const struct hda_fixup *fix, int action)
 {
 
@@ -5501,16 +5504,6 @@ static void alc295_fixup_chromebook(struct hda_codec *codec,
 						    alc_headset_btn_callback);
 		snd_hda_jack_add_kctl(codec, 0x55, "Headset Jack", false,
 				      SND_JACK_HEADSET, alc_headset_btn_keymap);
-		switch (codec->core.vendor_id) {
-		case 0x10ec0295:
-			alc_update_coef_idx(codec, 0x4a, 0x8000, 1 << 15); /* Reset HP JD */
-			alc_update_coef_idx(codec, 0x4a, 0x8000, 0 << 15);
-			break;
-		case 0x10ec0236:
-			alc_update_coef_idx(codec, 0x1b, 0x8000, 1 << 15); /* Reset HP JD */
-			alc_update_coef_idx(codec, 0x1b, 0x8000, 0 << 15);
-			break;
-		}
 		break;
 	case HDA_FIXUP_ACT_INIT:
 		switch (codec->core.vendor_id) {
@@ -5531,6 +5524,25 @@ static void alc295_fixup_chromebook(struct hda_codec *codec,
 	}
 }
 
+static void alc295_fixup_chromebook(struct hda_codec *codec,
+				    const struct hda_fixup *fix, int action)
+{
+	switch (action) {
+	case HDA_FIXUP_ACT_INIT:
+		switch (codec->core.vendor_id) {
+		case 0x10ec0295:
+			alc_update_coef_idx(codec, 0x4a, 0x8000, 1 << 15); /* Reset HP JD */
+			alc_update_coef_idx(codec, 0x4a, 0x8000, 0 << 15);
+			break;
+		case 0x10ec0236:
+			alc_update_coef_idx(codec, 0x1b, 0x8000, 1 << 15); /* Reset HP JD */
+			alc_update_coef_idx(codec, 0x1b, 0x8000, 0 << 15);
+			break;
+		}
+		break;
+	}
+}
+
 static void alc_fixup_disable_mic_vref(struct hda_codec *codec,
 				  const struct hda_fixup *fix, int action)
 {
@@ -5663,6 +5675,7 @@ enum {
 	ALC233_FIXUP_ASUS_MIC_NO_PRESENCE,
 	ALC233_FIXUP_EAPD_COEF_AND_MIC_NO_PRESENCE,
 	ALC233_FIXUP_LENOVO_MULTI_CODECS,
+	ALC233_FIXUP_ACER_HEADSET_MIC,
 	ALC294_FIXUP_LENOVO_MIC_LOCATION,
 	ALC225_FIXUP_DELL_WYSE_MIC_NO_PRESENCE,
 	ALC700_FIXUP_INTEL_REFERENCE,
@@ -5684,10 +5697,13 @@ enum {
 	ALC285_FIXUP_LENOVO_PC_BEEP_IN_NOISE,
 	ALC255_FIXUP_ACER_HEADSET_MIC,
 	ALC295_FIXUP_CHROME_BOOK,
+	ALC225_FIXUP_HEADSET_JACK,
 	ALC225_FIXUP_DELL_WYSE_AIO_MIC_NO_PRESENCE,
 	ALC225_FIXUP_WYSE_AUTO_MUTE,
 	ALC225_FIXUP_WYSE_DISABLE_MIC_VREF,
 	ALC286_FIXUP_ACER_AIO_HEADSET_MIC,
+	ALC256_FIXUP_ASUS_MIC_NO_PRESENCE,
+	ALC299_FIXUP_PREDATOR_SPK,
 };
 
 static const struct hda_fixup alc269_fixups[] = {
@@ -6488,6 +6504,16 @@ static const struct hda_fixup alc269_fixups[] = {
 		.type = HDA_FIXUP_FUNC,
 		.v.func = alc233_alc662_fixup_lenovo_dual_codecs,
 	},
+	[ALC233_FIXUP_ACER_HEADSET_MIC] = {
+		.type = HDA_FIXUP_VERBS,
+		.v.verbs = (const struct hda_verb[]) {
+			{ 0x20, AC_VERB_SET_COEF_INDEX, 0x45 },
+			{ 0x20, AC_VERB_SET_PROC_COEF, 0x5089 },
+			{ }
+		},
+		.chained = true,
+		.chain_id = ALC233_FIXUP_ASUS_MIC_NO_PRESENCE
+	},
 	[ALC294_FIXUP_LENOVO_MIC_LOCATION] = {
 		.type = HDA_FIXUP_PINS,
 		.v.pins = (const struct hda_pintbl[]) {
@@ -6633,6 +6659,12 @@ static const struct hda_fixup alc269_fixups[] = {
 	[ALC295_FIXUP_CHROME_BOOK] = {
 		.type = HDA_FIXUP_FUNC,
 		.v.func = alc295_fixup_chromebook,
+		.chained = true,
+		.chain_id = ALC225_FIXUP_HEADSET_JACK
+	},
+	[ALC225_FIXUP_HEADSET_JACK] = {
+		.type = HDA_FIXUP_FUNC,
+		.v.func = alc_fixup_headset_jack,
 	},
 	[ALC293_FIXUP_SYSTEM76_MIC_NO_PRESENCE] = {
 		.type = HDA_FIXUP_PINS,
@@ -6696,6 +6728,22 @@ static const struct hda_fixup alc269_fixups[] = {
 		.chained = true,
 		.chain_id = ALC286_FIXUP_ACER_AIO_MIC_NO_PRESENCE
 	},
+	[ALC256_FIXUP_ASUS_MIC_NO_PRESENCE] = {
+		.type = HDA_FIXUP_PINS,
+		.v.pins = (const struct hda_pintbl[]) {
+			{ 0x19, 0x04a11120 }, /* use as headset mic, without its own jack detect */
+			{ }
+		},
+		.chained = true,
+		.chain_id = ALC256_FIXUP_ASUS_HEADSET_MODE
+	},
+	[ALC299_FIXUP_PREDATOR_SPK] = {
+		.type = HDA_FIXUP_PINS,
+		.v.pins = (const struct hda_pintbl[]) {
+			{ 0x21, 0x90170150 }, /* use as headset mic, without its own jack detect */
+			{ }
+		}
+	},
 };
 
 static const struct snd_pci_quirk alc269_fixup_tbl[] = {
@@ -6712,9 +6760,14 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = {
 	SND_PCI_QUIRK(0x1025, 0x079b, "Acer Aspire V5-573G", ALC282_FIXUP_ASPIRE_V5_PINS),
 	SND_PCI_QUIRK(0x1025, 0x102b, "Acer Aspire C24-860", ALC286_FIXUP_ACER_AIO_MIC_NO_PRESENCE),
 	SND_PCI_QUIRK(0x1025, 0x106d, "Acer Cloudbook 14", ALC283_FIXUP_CHROME_BOOK),
+	SND_PCI_QUIRK(0x1025, 0x1099, "Acer Aspire E5-523G", ALC255_FIXUP_ACER_MIC_NO_PRESENCE),
+	SND_PCI_QUIRK(0x1025, 0x110e, "Acer Aspire ES1-432", ALC255_FIXUP_ACER_MIC_NO_PRESENCE),
+	SND_PCI_QUIRK(0x1025, 0x1246, "Acer Predator Helios 500", ALC299_FIXUP_PREDATOR_SPK),
 	SND_PCI_QUIRK(0x1025, 0x128f, "Acer Veriton Z6860G", ALC286_FIXUP_ACER_AIO_HEADSET_MIC),
 	SND_PCI_QUIRK(0x1025, 0x1290, "Acer Veriton Z4860G", ALC286_FIXUP_ACER_AIO_HEADSET_MIC),
 	SND_PCI_QUIRK(0x1025, 0x1291, "Acer Veriton Z4660G", ALC286_FIXUP_ACER_AIO_HEADSET_MIC),
+	SND_PCI_QUIRK(0x1025, 0x1308, "Acer Aspire Z24-890", ALC286_FIXUP_ACER_AIO_HEADSET_MIC),
+	SND_PCI_QUIRK(0x1025, 0x132a, "Acer TravelMate B114-21", ALC233_FIXUP_ACER_HEADSET_MIC),
 	SND_PCI_QUIRK(0x1025, 0x1330, "Acer TravelMate X514-51T", ALC255_FIXUP_ACER_HEADSET_MIC),
 	SND_PCI_QUIRK(0x1028, 0x0470, "Dell M101z", ALC269_FIXUP_DELL_M101Z),
 	SND_PCI_QUIRK(0x1028, 0x054b, "Dell XPS one 2710", ALC275_FIXUP_DELL_XPS),
@@ -7110,7 +7163,9 @@ static const struct hda_model_fixup alc269_fixup_models[] = {
 	{.id = ALC255_FIXUP_DUMMY_LINEOUT_VERB, .name = "alc255-dummy-lineout"},
 	{.id = ALC255_FIXUP_DELL_HEADSET_MIC, .name = "alc255-dell-headset"},
 	{.id = ALC295_FIXUP_HP_X360, .name = "alc295-hp-x360"},
-	{.id = ALC295_FIXUP_CHROME_BOOK, .name = "alc-sense-combo"},
+	{.id = ALC225_FIXUP_HEADSET_JACK, .name = "alc-headset-jack"},
+	{.id = ALC295_FIXUP_CHROME_BOOK, .name = "alc-chrome-book"},
+	{.id = ALC299_FIXUP_PREDATOR_SPK, .name = "predator-spk"},
 	{}
 };
 #define ALC225_STANDARD_PINS \
@@ -7213,6 +7268,12 @@ static const struct snd_hda_pin_quirk alc269_pin_fixup_tbl[] = {
 		{0x12, 0x90a60140},
 		{0x14, 0x90170150},
 		{0x21, 0x02211020}),
+	SND_HDA_PIN_QUIRK(0x10ec0236, 0x1028, "Dell", ALC255_FIXUP_DELL1_MIC_NO_PRESENCE,
+		{0x21, 0x02211020}),
+	SND_HDA_PIN_QUIRK(0x10ec0236, 0x1028, "Dell", ALC255_FIXUP_DELL1_MIC_NO_PRESENCE,
+		{0x12, 0x40000000},
+		{0x14, 0x90170110},
+		{0x21, 0x02211020}),
 	SND_HDA_PIN_QUIRK(0x10ec0255, 0x1028, "Dell", ALC255_FIXUP_DELL2_MIC_NO_PRESENCE,
 		{0x14, 0x90170110},
 		{0x21, 0x02211020}),
@@ -7323,6 +7384,10 @@ static const struct snd_hda_pin_quirk alc269_pin_fixup_tbl[] = {
 		{0x21, 0x0221101f}),
 	SND_HDA_PIN_QUIRK(0x10ec0256, 0x1028, "Dell", ALC255_FIXUP_DELL1_MIC_NO_PRESENCE,
 		ALC256_STANDARD_PINS),
+	SND_HDA_PIN_QUIRK(0x10ec0256, 0x1028, "Dell", ALC255_FIXUP_DELL1_MIC_NO_PRESENCE,
+		{0x14, 0x90170110},
+		{0x1b, 0x01011020},
+		{0x21, 0x0221101f}),
 	SND_HDA_PIN_QUIRK(0x10ec0256, 0x1043, "ASUS", ALC256_FIXUP_ASUS_MIC,
 		{0x14, 0x90170110},
 		{0x1b, 0x90a70130},
@@ -7331,6 +7396,18 @@ static const struct snd_hda_pin_quirk alc269_pin_fixup_tbl[] = {
 		{0x14, 0x90170110},
 		{0x1b, 0x90a70130},
 		{0x21, 0x03211020}),
+	SND_HDA_PIN_QUIRK(0x10ec0256, 0x1043, "ASUS", ALC256_FIXUP_ASUS_MIC_NO_PRESENCE,
+		{0x12, 0x90a60130},
+		{0x14, 0x90170110},
+		{0x21, 0x03211020}),
+	SND_HDA_PIN_QUIRK(0x10ec0256, 0x1043, "ASUS", ALC256_FIXUP_ASUS_MIC_NO_PRESENCE,
+		{0x12, 0x90a60130},
+		{0x14, 0x90170110},
+		{0x21, 0x04211020}),
+	SND_HDA_PIN_QUIRK(0x10ec0256, 0x1043, "ASUS", ALC256_FIXUP_ASUS_MIC_NO_PRESENCE,
+		{0x1a, 0x90a70130},
+		{0x1b, 0x90170110},
+		{0x21, 0x03211020}),
 	SND_HDA_PIN_QUIRK(0x10ec0274, 0x1028, "Dell", ALC274_FIXUP_DELL_AIO_LINEOUT_VERB,
 		{0x12, 0xb7a60130},
 		{0x13, 0xb8a61140},
@@ -7470,6 +7547,13 @@ static const struct snd_hda_pin_quirk alc269_pin_fixup_tbl[] = {
 		{0x12, 0x90a60130},
 		{0x17, 0x90170110},
 		{0x21, 0x04211020}),
+	SND_HDA_PIN_QUIRK(0x10ec0295, 0x1043, "ASUS", ALC294_FIXUP_ASUS_SPK,
+		{0x12, 0x90a60130},
+		{0x17, 0x90170110},
+		{0x21, 0x03211020}),
+	SND_HDA_PIN_QUIRK(0x10ec0295, 0x1028, "Dell", ALC269_FIXUP_DELL1_MIC_NO_PRESENCE,
+		{0x14, 0x90170110},
+		{0x21, 0x04211020}),
 	SND_HDA_PIN_QUIRK(0x10ec0295, 0x1028, "Dell", ALC269_FIXUP_DELL1_MIC_NO_PRESENCE,
 		ALC295_STANDARD_PINS,
 		{0x17, 0x21014020},
diff --git a/sound/soc/codecs/Kconfig b/sound/soc/codecs/Kconfig
index 419114edfd57..667fc1d59e18 100644
--- a/sound/soc/codecs/Kconfig
+++ b/sound/soc/codecs/Kconfig
@@ -1151,6 +1151,7 @@ config SND_SOC_WCD9335
 	tristate "WCD9335 Codec"
 	depends on SLIMBUS
 	select REGMAP_SLIMBUS
+	select REGMAP_IRQ
 	help
 	  The WCD9335 is a standalone Hi-Fi audio CODEC IC, supports
 	  Qualcomm Technologies, Inc. (QTI) multimedia solutions,
diff --git a/sound/soc/codecs/ab8500-codec.c b/sound/soc/codecs/ab8500-codec.c
index 03bbbcd3b6c1..19e7f0333c2a 100644
--- a/sound/soc/codecs/ab8500-codec.c
+++ b/sound/soc/codecs/ab8500-codec.c
@@ -1062,10 +1062,10 @@ static void anc_iir(struct snd_soc_component *component, unsigned int bnk,
 			snd_soc_component_update_bits(component, AB8500_ANCCONF1,
 					BIT(AB8500_ANCCONF1_ANCIIRINIT),
 					BIT(AB8500_ANCCONF1_ANCIIRINIT));
-			usleep_range(AB8500_ANC_SM_DELAY, AB8500_ANC_SM_DELAY);
+			usleep_range(AB8500_ANC_SM_DELAY, AB8500_ANC_SM_DELAY*2);
 			snd_soc_component_update_bits(component, AB8500_ANCCONF1,
 					BIT(AB8500_ANCCONF1_ANCIIRINIT), 0);
-			usleep_range(AB8500_ANC_SM_DELAY, AB8500_ANC_SM_DELAY);
+			usleep_range(AB8500_ANC_SM_DELAY, AB8500_ANC_SM_DELAY*2);
 		} else {
 			snd_soc_component_update_bits(component, AB8500_ANCCONF1,
 					BIT(AB8500_ANCCONF1_ANCIIRUPDATE),
@@ -2129,6 +2129,7 @@ static int ab8500_codec_set_dai_fmt(struct snd_soc_dai *dai, unsigned int fmt)
 		dev_err(dai->component->dev,
 			"%s: ERROR: The device is either a master or a slave.\n",
 			__func__);
+		/* fall through */
 	default:
 		dev_err(dai->component->dev,
 			"%s: ERROR: Unsupporter master mask 0x%x\n",
diff --git a/sound/soc/codecs/adau1977-spi.c b/sound/soc/codecs/adau1977-spi.c
index 84ffbde9583f..2baf61567b59 100644
--- a/sound/soc/codecs/adau1977-spi.c
+++ b/sound/soc/codecs/adau1977-spi.c
@@ -10,6 +10,8 @@
 #include <linux/mod_devicetable.h>
 #include <linux/module.h>
 #include <linux/regmap.h>
+#include <linux/of.h>
+#include <linux/of_device.h>
 #include <linux/spi/spi.h>
 #include <sound/soc.h>
 
@@ -54,9 +56,18 @@ static const struct spi_device_id adau1977_spi_ids[] = {
 };
 MODULE_DEVICE_TABLE(spi, adau1977_spi_ids);
 
+static const struct of_device_id adau1977_spi_of_match[] = {
+        { .compatible = "adi,adau1977" },
+        { .compatible = "adi,adau1978" },
+        { .compatible = "adi,adau1979" },
+        { },
+};
+MODULE_DEVICE_TABLE(of, adau1977_spi_of_match);
+
 static struct spi_driver adau1977_spi_driver = {
 	.driver = {
 		.name = "adau1977",
+		.of_match_table = of_match_ptr(adau1977_spi_of_match),
 	},
 	.probe = adau1977_spi_probe,
 	.id_table = adau1977_spi_ids,
diff --git a/sound/soc/codecs/cs35l35.c b/sound/soc/codecs/cs35l35.c
index 9f4a59871cee..c71696146c5e 100644
--- a/sound/soc/codecs/cs35l35.c
+++ b/sound/soc/codecs/cs35l35.c
@@ -1635,6 +1635,16 @@ err:
 	return ret;
 }
 
+static int cs35l35_i2c_remove(struct i2c_client *i2c_client)
+{
+	struct cs35l35_private *cs35l35 = i2c_get_clientdata(i2c_client);
+
+	regulator_bulk_disable(cs35l35->num_supplies, cs35l35->supplies);
+	gpiod_set_value_cansleep(cs35l35->reset_gpio, 0);
+
+	return 0;
+}
+
 static const struct of_device_id cs35l35_of_match[] = {
 	{.compatible = "cirrus,cs35l35"},
 	{},
@@ -1655,6 +1665,7 @@ static struct i2c_driver cs35l35_i2c_driver = {
 	},
 	.id_table = cs35l35_id,
 	.probe = cs35l35_i2c_probe,
+	.remove = cs35l35_i2c_remove,
 };
 
 module_i2c_driver(cs35l35_i2c_driver);
diff --git a/sound/soc/codecs/cs4270.c b/sound/soc/codecs/cs4270.c
index 33d74f163bd7..793a14d58667 100644
--- a/sound/soc/codecs/cs4270.c
+++ b/sound/soc/codecs/cs4270.c
@@ -642,6 +642,7 @@ static const struct regmap_config cs4270_regmap = {
 	.reg_defaults =		cs4270_reg_defaults,
 	.num_reg_defaults =	ARRAY_SIZE(cs4270_reg_defaults),
 	.cache_type =		REGCACHE_RBTREE,
+	.write_flag_mask =	CS4270_I2C_INCR,
 
 	.readable_reg =		cs4270_reg_is_readable,
 	.volatile_reg =		cs4270_reg_is_volatile,
diff --git a/sound/soc/codecs/hdac_hda.c b/sound/soc/codecs/hdac_hda.c
index ffecdaaa8cf2..f889d94c8e3c 100644
--- a/sound/soc/codecs/hdac_hda.c
+++ b/sound/soc/codecs/hdac_hda.c
@@ -38,6 +38,9 @@ static void hdac_hda_dai_close(struct snd_pcm_substream *substream,
 			       struct snd_soc_dai *dai);
 static int hdac_hda_dai_prepare(struct snd_pcm_substream *substream,
 				struct snd_soc_dai *dai);
+static int hdac_hda_dai_hw_params(struct snd_pcm_substream *substream,
+				  struct snd_pcm_hw_params *params,
+				  struct snd_soc_dai *dai);
 static int hdac_hda_dai_hw_free(struct snd_pcm_substream *substream,
 				struct snd_soc_dai *dai);
 static int hdac_hda_dai_set_tdm_slot(struct snd_soc_dai *dai,
@@ -50,6 +53,7 @@ static const struct snd_soc_dai_ops hdac_hda_dai_ops = {
 	.startup = hdac_hda_dai_open,
 	.shutdown = hdac_hda_dai_close,
 	.prepare = hdac_hda_dai_prepare,
+	.hw_params = hdac_hda_dai_hw_params,
 	.hw_free = hdac_hda_dai_hw_free,
 	.set_tdm_slot = hdac_hda_dai_set_tdm_slot,
 };
@@ -139,6 +143,39 @@ static int hdac_hda_dai_set_tdm_slot(struct snd_soc_dai *dai,
 	return 0;
 }
 
+static int hdac_hda_dai_hw_params(struct snd_pcm_substream *substream,
+				  struct snd_pcm_hw_params *params,
+				  struct snd_soc_dai *dai)
+{
+	struct snd_soc_component *component = dai->component;
+	struct hdac_hda_priv *hda_pvt;
+	unsigned int format_val;
+	unsigned int maxbps;
+
+	if (substream->stream == SNDRV_PCM_STREAM_PLAYBACK)
+		maxbps = dai->driver->playback.sig_bits;
+	else
+		maxbps = dai->driver->capture.sig_bits;
+
+	hda_pvt = snd_soc_component_get_drvdata(component);
+	format_val = snd_hdac_calc_stream_format(params_rate(params),
+						 params_channels(params),
+						 params_format(params),
+						 maxbps,
+						 0);
+	if (!format_val) {
+		dev_err(dai->dev,
+			"invalid format_val, rate=%d, ch=%d, format=%d, maxbps=%d\n",
+			params_rate(params), params_channels(params),
+			params_format(params), maxbps);
+
+		return -EINVAL;
+	}
+
+	hda_pvt->pcm[dai->id].format_val[substream->stream] = format_val;
+	return 0;
+}
+
 static int hdac_hda_dai_hw_free(struct snd_pcm_substream *substream,
 				struct snd_soc_dai *dai)
 {
@@ -162,10 +199,9 @@ static int hdac_hda_dai_prepare(struct snd_pcm_substream *substream,
 				struct snd_soc_dai *dai)
 {
 	struct snd_soc_component *component = dai->component;
+	struct hda_pcm_stream *hda_stream;
 	struct hdac_hda_priv *hda_pvt;
-	struct snd_pcm_runtime *runtime = substream->runtime;
 	struct hdac_device *hdev;
-	struct hda_pcm_stream *hda_stream;
 	unsigned int format_val;
 	struct hda_pcm *pcm;
 	unsigned int stream;
@@ -179,19 +215,8 @@ static int hdac_hda_dai_prepare(struct snd_pcm_substream *substream,
 
 	hda_stream = &pcm->stream[substream->stream];
 
-	format_val = snd_hdac_calc_stream_format(runtime->rate,
-						 runtime->channels,
-						 runtime->format,
-						 hda_stream->maxbps,
-						 0);
-	if (!format_val) {
-		dev_err(&hdev->dev,
-			"invalid format_val, rate=%d, ch=%d, format=%d\n",
-			runtime->rate, runtime->channels, runtime->format);
-		return -EINVAL;
-	}
-
 	stream = hda_pvt->pcm[dai->id].stream_tag[substream->stream];
+	format_val = hda_pvt->pcm[dai->id].format_val[substream->stream];
 
 	ret = snd_hda_codec_prepare(&hda_pvt->codec, hda_stream,
 				    stream, format_val, substream);
diff --git a/sound/soc/codecs/hdac_hda.h b/sound/soc/codecs/hdac_hda.h
index e444ef593360..6b1bd4f428e7 100644
--- a/sound/soc/codecs/hdac_hda.h
+++ b/sound/soc/codecs/hdac_hda.h
@@ -8,6 +8,7 @@
 
 struct hdac_hda_pcm {
 	int stream_tag[2];
+	unsigned int format_val[2];
 };
 
 struct hdac_hda_priv {
diff --git a/sound/soc/codecs/hdmi-codec.c b/sound/soc/codecs/hdmi-codec.c
index e5b6769b9797..35df73e42cbc 100644
--- a/sound/soc/codecs/hdmi-codec.c
+++ b/sound/soc/codecs/hdmi-codec.c
@@ -484,9 +484,6 @@ static int hdmi_codec_hw_params(struct snd_pcm_substream *substream,
 		params_width(params), params_rate(params),
 		params_channels(params));
 
-	if (params_width(params) > 24)
-		params->msbits = 24;
-
 	ret = snd_pcm_create_iec958_consumer_hw_params(params, hp.iec.status,
 						       sizeof(hp.iec.status));
 	if (ret < 0) {
@@ -529,73 +526,71 @@ static int hdmi_codec_set_fmt(struct snd_soc_dai *dai,
 {
 	struct hdmi_codec_priv *hcp = snd_soc_dai_get_drvdata(dai);
 	struct hdmi_codec_daifmt cf = { 0 };
-	int ret = 0;
 
 	dev_dbg(dai->dev, "%s()\n", __func__);
 
-	if (dai->id == DAI_ID_SPDIF) {
-		cf.fmt = HDMI_SPDIF;
-	} else {
-		switch (fmt & SND_SOC_DAIFMT_MASTER_MASK) {
-		case SND_SOC_DAIFMT_CBM_CFM:
-			cf.bit_clk_master = 1;
-			cf.frame_clk_master = 1;
-			break;
-		case SND_SOC_DAIFMT_CBS_CFM:
-			cf.frame_clk_master = 1;
-			break;
-		case SND_SOC_DAIFMT_CBM_CFS:
-			cf.bit_clk_master = 1;
-			break;
-		case SND_SOC_DAIFMT_CBS_CFS:
-			break;
-		default:
-			return -EINVAL;
-		}
+	if (dai->id == DAI_ID_SPDIF)
+		return 0;
+
+	switch (fmt & SND_SOC_DAIFMT_MASTER_MASK) {
+	case SND_SOC_DAIFMT_CBM_CFM:
+		cf.bit_clk_master = 1;
+		cf.frame_clk_master = 1;
+		break;
+	case SND_SOC_DAIFMT_CBS_CFM:
+		cf.frame_clk_master = 1;
+		break;
+	case SND_SOC_DAIFMT_CBM_CFS:
+		cf.bit_clk_master = 1;
+		break;
+	case SND_SOC_DAIFMT_CBS_CFS:
+		break;
+	default:
+		return -EINVAL;
+	}
 
-		switch (fmt & SND_SOC_DAIFMT_INV_MASK) {
-		case SND_SOC_DAIFMT_NB_NF:
-			break;
-		case SND_SOC_DAIFMT_NB_IF:
-			cf.frame_clk_inv = 1;
-			break;
-		case SND_SOC_DAIFMT_IB_NF:
-			cf.bit_clk_inv = 1;
-			break;
-		case SND_SOC_DAIFMT_IB_IF:
-			cf.frame_clk_inv = 1;
-			cf.bit_clk_inv = 1;
-			break;
-		}
+	switch (fmt & SND_SOC_DAIFMT_INV_MASK) {
+	case SND_SOC_DAIFMT_NB_NF:
+		break;
+	case SND_SOC_DAIFMT_NB_IF:
+		cf.frame_clk_inv = 1;
+		break;
+	case SND_SOC_DAIFMT_IB_NF:
+		cf.bit_clk_inv = 1;
+		break;
+	case SND_SOC_DAIFMT_IB_IF:
+		cf.frame_clk_inv = 1;
+		cf.bit_clk_inv = 1;
+		break;
+	}
 
-		switch (fmt & SND_SOC_DAIFMT_FORMAT_MASK) {
-		case SND_SOC_DAIFMT_I2S:
-			cf.fmt = HDMI_I2S;
-			break;
-		case SND_SOC_DAIFMT_DSP_A:
-			cf.fmt = HDMI_DSP_A;
-			break;
-		case SND_SOC_DAIFMT_DSP_B:
-			cf.fmt = HDMI_DSP_B;
-			break;
-		case SND_SOC_DAIFMT_RIGHT_J:
-			cf.fmt = HDMI_RIGHT_J;
-			break;
-		case SND_SOC_DAIFMT_LEFT_J:
-			cf.fmt = HDMI_LEFT_J;
-			break;
-		case SND_SOC_DAIFMT_AC97:
-			cf.fmt = HDMI_AC97;
-			break;
-		default:
-			dev_err(dai->dev, "Invalid DAI interface format\n");
-			return -EINVAL;
-		}
+	switch (fmt & SND_SOC_DAIFMT_FORMAT_MASK) {
+	case SND_SOC_DAIFMT_I2S:
+		cf.fmt = HDMI_I2S;
+		break;
+	case SND_SOC_DAIFMT_DSP_A:
+		cf.fmt = HDMI_DSP_A;
+		break;
+	case SND_SOC_DAIFMT_DSP_B:
+		cf.fmt = HDMI_DSP_B;
+		break;
+	case SND_SOC_DAIFMT_RIGHT_J:
+		cf.fmt = HDMI_RIGHT_J;
+		break;
+	case SND_SOC_DAIFMT_LEFT_J:
+		cf.fmt = HDMI_LEFT_J;
+		break;
+	case SND_SOC_DAIFMT_AC97:
+		cf.fmt = HDMI_AC97;
+		break;
+	default:
+		dev_err(dai->dev, "Invalid DAI interface format\n");
+		return -EINVAL;
 	}
 
 	hcp->daifmt[dai->id] = cf;
 
-	return ret;
+	return 0;
 }
 
 static int hdmi_codec_digital_mute(struct snd_soc_dai *dai, int mute)
@@ -792,8 +787,10 @@ static int hdmi_codec_probe(struct platform_device *pdev)
 		i++;
 	}
 
-	if (hcd->spdif)
+	if (hcd->spdif) {
 		hcp->daidrv[i] = hdmi_spdif_dai;
+		hcp->daifmt[DAI_ID_SPDIF].fmt = HDMI_SPDIF;
+	}
 
 	dev_set_drvdata(dev, hcp);
 
diff --git a/sound/soc/codecs/nau8810.c b/sound/soc/codecs/nau8810.c
index bfd74b86c9d2..645aa0794123 100644
--- a/sound/soc/codecs/nau8810.c
+++ b/sound/soc/codecs/nau8810.c
@@ -411,9 +411,9 @@ static const struct snd_soc_dapm_widget nau8810_dapm_widgets[] = {
 	SND_SOC_DAPM_MIXER("Mono Mixer", NAU8810_REG_POWER3,
 		NAU8810_MOUTMX_EN_SFT, 0, &nau8810_mono_mixer_controls[0],
 		ARRAY_SIZE(nau8810_mono_mixer_controls)),
-	SND_SOC_DAPM_DAC("DAC", "HiFi Playback", NAU8810_REG_POWER3,
+	SND_SOC_DAPM_DAC("DAC", "Playback", NAU8810_REG_POWER3,
 		NAU8810_DAC_EN_SFT, 0),
-	SND_SOC_DAPM_ADC("ADC", "HiFi Capture", NAU8810_REG_POWER2,
+	SND_SOC_DAPM_ADC("ADC", "Capture", NAU8810_REG_POWER2,
 		NAU8810_ADC_EN_SFT, 0),
 	SND_SOC_DAPM_PGA("SpkN Out", NAU8810_REG_POWER3,
 		NAU8810_NSPK_EN_SFT, 0, NULL, 0),
diff --git a/sound/soc/codecs/nau8824.c b/sound/soc/codecs/nau8824.c
index 87ed3dc496dc..5ab05e75edea 100644
--- a/sound/soc/codecs/nau8824.c
+++ b/sound/soc/codecs/nau8824.c
@@ -681,8 +681,8 @@ static const struct snd_soc_dapm_widget nau8824_dapm_widgets[] = {
 	SND_SOC_DAPM_ADC("ADCR", NULL, NAU8824_REG_ANALOG_ADC_2,
 		NAU8824_ADCR_EN_SFT, 0),
 
-	SND_SOC_DAPM_AIF_OUT("AIFTX", "HiFi Capture", 0, SND_SOC_NOPM, 0, 0),
-	SND_SOC_DAPM_AIF_IN("AIFRX", "HiFi Playback", 0, SND_SOC_NOPM, 0, 0),
+	SND_SOC_DAPM_AIF_OUT("AIFTX", "Capture", 0, SND_SOC_NOPM, 0, 0),
+	SND_SOC_DAPM_AIF_IN("AIFRX", "Playback", 0, SND_SOC_NOPM, 0, 0),
 
 	SND_SOC_DAPM_DAC("DACL", NULL, NAU8824_REG_RDAC,
 		NAU8824_DACL_EN_SFT, 0),
@@ -831,6 +831,36 @@ static void nau8824_int_status_clear_all(struct regmap *regmap)
 	}
 }
 
+static void nau8824_dapm_disable_pin(struct nau8824 *nau8824, const char *pin)
+{
+	struct snd_soc_dapm_context *dapm = nau8824->dapm;
+	const char *prefix = dapm->component->name_prefix;
+	char prefixed_pin[80];
+
+	if (prefix) {
+		snprintf(prefixed_pin, sizeof(prefixed_pin), "%s %s",
+			 prefix, pin);
+		snd_soc_dapm_disable_pin(dapm, prefixed_pin);
+	} else {
+		snd_soc_dapm_disable_pin(dapm, pin);
+	}
+}
+
+static void nau8824_dapm_enable_pin(struct nau8824 *nau8824, const char *pin)
+{
+	struct snd_soc_dapm_context *dapm = nau8824->dapm;
+	const char *prefix = dapm->component->name_prefix;
+	char prefixed_pin[80];
+
+	if (prefix) {
+		snprintf(prefixed_pin, sizeof(prefixed_pin), "%s %s",
+			 prefix, pin);
+		snd_soc_dapm_force_enable_pin(dapm, prefixed_pin);
+	} else {
+		snd_soc_dapm_force_enable_pin(dapm, pin);
+	}
+}
+
 static void nau8824_eject_jack(struct nau8824 *nau8824)
 {
 	struct snd_soc_dapm_context *dapm = nau8824->dapm;
@@ -839,8 +869,8 @@ static void nau8824_eject_jack(struct nau8824 *nau8824)
 	/* Clear all interruption status */
 	nau8824_int_status_clear_all(regmap);
 
-	snd_soc_dapm_disable_pin(dapm, "SAR");
-	snd_soc_dapm_disable_pin(dapm, "MICBIAS");
+	nau8824_dapm_disable_pin(nau8824, "SAR");
+	nau8824_dapm_disable_pin(nau8824, "MICBIAS");
 	snd_soc_dapm_sync(dapm);
 
 	/* Enable the insertion interruption, disable the ejection
@@ -870,8 +900,8 @@ static void nau8824_jdet_work(struct work_struct *work)
 	struct regmap *regmap = nau8824->regmap;
 	int adc_value, event = 0, event_mask = 0;
 
-	snd_soc_dapm_force_enable_pin(dapm, "MICBIAS");
-	snd_soc_dapm_force_enable_pin(dapm, "SAR");
+	nau8824_dapm_enable_pin(nau8824, "MICBIAS");
+	nau8824_dapm_enable_pin(nau8824, "SAR");
 	snd_soc_dapm_sync(dapm);
 
 	msleep(100);
@@ -882,8 +912,8 @@ static void nau8824_jdet_work(struct work_struct *work)
 	if (adc_value < HEADSET_SARADC_THD) {
 		event |= SND_JACK_HEADPHONE;
 
-		snd_soc_dapm_disable_pin(dapm, "SAR");
-		snd_soc_dapm_disable_pin(dapm, "MICBIAS");
+		nau8824_dapm_disable_pin(nau8824, "SAR");
+		nau8824_dapm_disable_pin(nau8824, "MICBIAS");
 		snd_soc_dapm_sync(dapm);
 	} else {
 		event |= SND_JACK_HEADSET;
diff --git a/sound/soc/codecs/rt5682.c b/sound/soc/codecs/rt5682.c
index 9d5acd2d04ab..86a7fa31c294 100644
--- a/sound/soc/codecs/rt5682.c
+++ b/sound/soc/codecs/rt5682.c
@@ -910,13 +910,21 @@ static int rt5682_headset_detect(struct snd_soc_component *component,
 		int jack_insert)
 {
 	struct rt5682_priv *rt5682 = snd_soc_component_get_drvdata(component);
-	struct snd_soc_dapm_context *dapm =
-		snd_soc_component_get_dapm(component);
 	unsigned int val, count;
 
 	if (jack_insert) {
-		snd_soc_dapm_force_enable_pin(dapm, "CBJ Power");
-		snd_soc_dapm_sync(dapm);
+
+		snd_soc_component_update_bits(component, RT5682_PWR_ANLG_1,
+			RT5682_PWR_VREF2 | RT5682_PWR_MB,
+			RT5682_PWR_VREF2 | RT5682_PWR_MB);
+		snd_soc_component_update_bits(component,
+				RT5682_PWR_ANLG_1, RT5682_PWR_FV2, 0);
+		usleep_range(15000, 20000);
+		snd_soc_component_update_bits(component,
+				RT5682_PWR_ANLG_1, RT5682_PWR_FV2, RT5682_PWR_FV2);
+		snd_soc_component_update_bits(component, RT5682_PWR_ANLG_3,
+			RT5682_PWR_CBJ, RT5682_PWR_CBJ);
+
 		snd_soc_component_update_bits(component, RT5682_CBJ_CTRL_1,
 			RT5682_TRIG_JD_MASK, RT5682_TRIG_JD_HIGH);
 
@@ -944,8 +952,10 @@ static int rt5682_headset_detect(struct snd_soc_component *component,
 		rt5682_enable_push_button_irq(component, false);
 		snd_soc_component_update_bits(component, RT5682_CBJ_CTRL_1,
 			RT5682_TRIG_JD_MASK, RT5682_TRIG_JD_LOW);
-		snd_soc_dapm_disable_pin(dapm, "CBJ Power");
-		snd_soc_dapm_sync(dapm);
+		snd_soc_component_update_bits(component, RT5682_PWR_ANLG_1,
+			RT5682_PWR_VREF2 | RT5682_PWR_MB, 0);
+		snd_soc_component_update_bits(component, RT5682_PWR_ANLG_3,
+			RT5682_PWR_CBJ, 0);
 
 		rt5682->jack_type = 0;
 	}
@@ -1198,7 +1208,7 @@ static int set_filter_clk(struct snd_soc_dapm_widget *w,
 	struct snd_soc_component *component =
 		snd_soc_dapm_to_component(w->dapm);
 	struct rt5682_priv *rt5682 = snd_soc_component_get_drvdata(component);
-	int ref, val, reg, sft, mask, idx = -EINVAL;
+	int ref, val, reg, idx = -EINVAL;
 	static const int div_f[] = {1, 2, 3, 4, 6, 8, 12, 16, 24, 32, 48};
 	static const int div_o[] = {1, 2, 4, 6, 8, 12, 16, 24, 32, 48};
 
@@ -1212,15 +1222,10 @@ static int set_filter_clk(struct snd_soc_dapm_widget *w,
 
 	idx = rt5682_div_sel(rt5682, ref, div_f, ARRAY_SIZE(div_f));
 
-	if (w->shift == RT5682_PWR_ADC_S1F_BIT) {
+	if (w->shift == RT5682_PWR_ADC_S1F_BIT)
 		reg = RT5682_PLL_TRACK_3;
-		sft = RT5682_ADC_OSR_SFT;
-		mask = RT5682_ADC_OSR_MASK;
-	} else {
+	else
 		reg = RT5682_PLL_TRACK_2;
-		sft = RT5682_DAC_OSR_SFT;
-		mask = RT5682_DAC_OSR_MASK;
-	}
 
 	snd_soc_component_update_bits(component, reg,
 		RT5682_FILTER_CLK_DIV_MASK, idx << RT5682_FILTER_CLK_DIV_SFT);
@@ -1232,7 +1237,8 @@ static int set_filter_clk(struct snd_soc_dapm_widget *w,
 	}
 
 	snd_soc_component_update_bits(component, RT5682_ADDA_CLK_1,
-		mask, idx << sft);
+		RT5682_ADC_OSR_MASK | RT5682_DAC_OSR_MASK,
+		(idx << RT5682_ADC_OSR_SFT) | (idx << RT5682_DAC_OSR_SFT));
 
 	return 0;
 }
@@ -1591,8 +1597,6 @@ static const struct snd_soc_dapm_widget rt5682_dapm_widgets[] = {
 		0, NULL, 0),
 	SND_SOC_DAPM_SUPPLY("Vref1", RT5682_PWR_ANLG_1, RT5682_PWR_VREF1_BIT, 0,
 		rt5655_set_verf, SND_SOC_DAPM_PRE_PMU | SND_SOC_DAPM_POST_PMU),
-	SND_SOC_DAPM_SUPPLY("Vref2", RT5682_PWR_ANLG_1, RT5682_PWR_VREF2_BIT, 0,
-		rt5655_set_verf, SND_SOC_DAPM_PRE_PMU | SND_SOC_DAPM_POST_PMU),
 
 	/* ASRC */
 	SND_SOC_DAPM_SUPPLY_S("DAC STO1 ASRC", 1, RT5682_PLL_TRACK_1,
@@ -1627,9 +1631,6 @@ static const struct snd_soc_dapm_widget rt5682_dapm_widgets[] = {
 	SND_SOC_DAPM_PGA("BST1 CBJ", SND_SOC_NOPM,
 		0, 0, NULL, 0),
 
-	SND_SOC_DAPM_SUPPLY("CBJ Power", RT5682_PWR_ANLG_3,
-		RT5682_PWR_CBJ_BIT, 0, NULL, 0),
-
 	/* REC Mixer */
 	SND_SOC_DAPM_MIXER("RECMIX1L", SND_SOC_NOPM, 0, 0, rt5682_rec1_l_mix,
 		ARRAY_SIZE(rt5682_rec1_l_mix)),
@@ -1792,17 +1793,13 @@ static const struct snd_soc_dapm_route rt5682_dapm_routes[] = {
 
 	/*Vref*/
 	{"MICBIAS1", NULL, "Vref1"},
-	{"MICBIAS1", NULL, "Vref2"},
 	{"MICBIAS2", NULL, "Vref1"},
-	{"MICBIAS2", NULL, "Vref2"},
 
 	{"CLKDET SYS", NULL, "CLKDET"},
 
 	{"IN1P", NULL, "LDO2"},
 
 	{"BST1 CBJ", NULL, "IN1P"},
-	{"BST1 CBJ", NULL, "CBJ Power"},
-	{"CBJ Power", NULL, "Vref2"},
 
 	{"RECMIX1L", "CBJ Switch", "BST1 CBJ"},
 	{"RECMIX1L", NULL, "RECMIX1L Power"},
@@ -1912,9 +1909,7 @@ static const struct snd_soc_dapm_route rt5682_dapm_routes[] = {
 	{"HP Amp", NULL, "Capless"},
 	{"HP Amp", NULL, "Charge Pump"},
 	{"HP Amp", NULL, "CLKDET SYS"},
-	{"HP Amp", NULL, "CBJ Power"},
 	{"HP Amp", NULL, "Vref1"},
-	{"HP Amp", NULL, "Vref2"},
 	{"HPOL Playback", "Switch", "HP Amp"},
 	{"HPOR Playback", "Switch", "HP Amp"},
 	{"HPOL", NULL, "HPOL Playback"},
@@ -2303,16 +2298,13 @@ static int rt5682_set_bias_level(struct snd_soc_component *component,
 	switch (level) {
 	case SND_SOC_BIAS_PREPARE:
 		regmap_update_bits(rt5682->regmap, RT5682_PWR_ANLG_1,
-			RT5682_PWR_MB | RT5682_PWR_BG,
-			RT5682_PWR_MB | RT5682_PWR_BG);
+			RT5682_PWR_BG, RT5682_PWR_BG);
 		regmap_update_bits(rt5682->regmap, RT5682_PWR_DIG_1,
 			RT5682_DIG_GATE_CTRL | RT5682_PWR_LDO,
 			RT5682_DIG_GATE_CTRL | RT5682_PWR_LDO);
 		break;
 
 	case SND_SOC_BIAS_STANDBY:
-		regmap_update_bits(rt5682->regmap, RT5682_PWR_ANLG_1,
-			RT5682_PWR_MB, RT5682_PWR_MB);
 		regmap_update_bits(rt5682->regmap, RT5682_PWR_DIG_1,
 			RT5682_DIG_GATE_CTRL, RT5682_DIG_GATE_CTRL);
 		break;
@@ -2320,7 +2312,7 @@ static int rt5682_set_bias_level(struct snd_soc_component *component,
 		regmap_update_bits(rt5682->regmap, RT5682_PWR_DIG_1,
 			RT5682_DIG_GATE_CTRL | RT5682_PWR_LDO, 0);
 		regmap_update_bits(rt5682->regmap, RT5682_PWR_ANLG_1,
-			RT5682_PWR_MB | RT5682_PWR_BG, 0);
+			RT5682_PWR_BG, 0);
 		break;
 
 	default:
@@ -2363,6 +2355,8 @@ static int rt5682_resume(struct snd_soc_component *component)
 	regcache_cache_only(rt5682->regmap, false);
 	regcache_sync(rt5682->regmap);
 
+	rt5682_irq(0, rt5682);
+
 	return 0;
 }
 #else
diff --git a/sound/soc/codecs/tlv320aic32x4-i2c.c b/sound/soc/codecs/tlv320aic32x4-i2c.c
index 385fa2e9525a..22c3a6bc0b6c 100644
--- a/sound/soc/codecs/tlv320aic32x4-i2c.c
+++ b/sound/soc/codecs/tlv320aic32x4-i2c.c
@@ -3,7 +3,7 @@
  *
  * Copyright 2011 NW Digital Radio
  *
- * Author: Jeremy McDermond <nh6z@nh6z.net>
+ * Author: Annaliese McDermond <nh6z@nh6z.net>
  *
  * Based on sound/soc/codecs/wm8974 and TI driver for kernel 2.6.27.
  *
@@ -72,5 +72,5 @@ static struct i2c_driver aic32x4_i2c_driver = {
 module_i2c_driver(aic32x4_i2c_driver);
 
 MODULE_DESCRIPTION("ASoC TLV320AIC32x4 codec driver I2C");
-MODULE_AUTHOR("Jeremy McDermond <nh6z@nh6z.net>");
+MODULE_AUTHOR("Annaliese McDermond <nh6z@nh6z.net>");
 MODULE_LICENSE("GPL");
diff --git a/sound/soc/codecs/tlv320aic32x4-spi.c b/sound/soc/codecs/tlv320aic32x4-spi.c
index 07d78ae51e05..aa5b7ba0254b 100644
--- a/sound/soc/codecs/tlv320aic32x4-spi.c
+++ b/sound/soc/codecs/tlv320aic32x4-spi.c
@@ -3,7 +3,7 @@
  *
  * Copyright 2011 NW Digital Radio
  *
- * Author: Jeremy McDermond <nh6z@nh6z.net>
+ * Author: Annaliese McDermond <nh6z@nh6z.net>
  *
  * Based on sound/soc/codecs/wm8974 and TI driver for kernel 2.6.27.
  *
@@ -74,5 +74,5 @@ static struct spi_driver aic32x4_spi_driver = {
 module_spi_driver(aic32x4_spi_driver);
 
 MODULE_DESCRIPTION("ASoC TLV320AIC32x4 codec driver SPI");
-MODULE_AUTHOR("Jeremy McDermond <nh6z@nh6z.net>");
+MODULE_AUTHOR("Annaliese McDermond <nh6z@nh6z.net>");
 MODULE_LICENSE("GPL");
diff --git a/sound/soc/codecs/tlv320aic32x4.c b/sound/soc/codecs/tlv320aic32x4.c
index 96f1526cb258..5520044929f4 100644
--- a/sound/soc/codecs/tlv320aic32x4.c
+++ b/sound/soc/codecs/tlv320aic32x4.c
@@ -490,6 +490,8 @@ static const struct snd_soc_dapm_widget aic32x4_dapm_widgets[] = {
 	SND_SOC_DAPM_INPUT("IN2_R"),
 	SND_SOC_DAPM_INPUT("IN3_L"),
 	SND_SOC_DAPM_INPUT("IN3_R"),
+	SND_SOC_DAPM_INPUT("CM_L"),
+	SND_SOC_DAPM_INPUT("CM_R"),
 };
 
 static const struct snd_soc_dapm_route aic32x4_dapm_routes[] = {
diff --git a/sound/soc/codecs/tlv320aic3x.c b/sound/soc/codecs/tlv320aic3x.c
index 283583d1db60..516d17cb2182 100644
--- a/sound/soc/codecs/tlv320aic3x.c
+++ b/sound/soc/codecs/tlv320aic3x.c
@@ -1609,7 +1609,6 @@ static int aic3x_probe(struct snd_soc_component *component)
 	struct aic3x_priv *aic3x = snd_soc_component_get_drvdata(component);
 	int ret, i;
 
-	INIT_LIST_HEAD(&aic3x->list);
 	aic3x->component = component;
 
 	for (i = 0; i < ARRAY_SIZE(aic3x->supplies); i++) {
@@ -1873,6 +1872,7 @@ static int aic3x_i2c_probe(struct i2c_client *i2c,
 	if (ret != 0)
 		goto err_gpio;
 
+	INIT_LIST_HEAD(&aic3x->list);
 	list_add(&aic3x->list, &reset_list);
 
 	return 0;
@@ -1889,6 +1889,8 @@ static int aic3x_i2c_remove(struct i2c_client *client)
 {
 	struct aic3x_priv *aic3x = i2c_get_clientdata(client);
 
+	list_del(&aic3x->list);
+
 	if (gpio_is_valid(aic3x->gpio_reset) &&
 	    !aic3x_is_shared_reset(aic3x)) {
 		gpio_set_value(aic3x->gpio_reset, 0);
diff --git a/sound/soc/codecs/wm_adsp.c b/sound/soc/codecs/wm_adsp.c
index b93fdc8d2d6f..b0b48eb9c7c9 100644
--- a/sound/soc/codecs/wm_adsp.c
+++ b/sound/soc/codecs/wm_adsp.c
@@ -2905,6 +2905,8 @@ int wm_adsp2_event(struct snd_soc_dapm_widget *w,
 		if (wm_adsp_fw[dsp->fw].num_caps != 0)
 			wm_adsp_buffer_free(dsp);
 
+		dsp->fatal_error = false;
+
 		mutex_unlock(&dsp->pwr_lock);
 
 		adsp_dbg(dsp, "Execution stopped\n");
@@ -3000,6 +3002,9 @@ static int wm_adsp_compr_attach(struct wm_adsp_compr *compr)
 {
 	struct wm_adsp_compr_buf *buf = NULL, *tmp;
 
+	if (compr->dsp->fatal_error)
+		return -EINVAL;
+
 	list_for_each_entry(tmp, &compr->dsp->buffer_list, list) {
 		if (!tmp->name || !strcmp(compr->name, tmp->name)) {
 			buf = tmp;
@@ -3535,11 +3540,11 @@ static int wm_adsp_buffer_get_error(struct wm_adsp_compr_buf *buf)
 
 	ret = wm_adsp_buffer_read(buf, HOST_BUFFER_FIELD(error), &buf->error);
 	if (ret < 0) {
-		adsp_err(buf->dsp, "Failed to check buffer error: %d\n", ret);
+		compr_err(buf, "Failed to check buffer error: %d\n", ret);
 		return ret;
 	}
 	if (buf->error != 0) {
-		adsp_err(buf->dsp, "Buffer error occurred: %d\n", buf->error);
+		compr_err(buf, "Buffer error occurred: %d\n", buf->error);
 		return -EIO;
 	}
 
@@ -3571,8 +3576,6 @@ int wm_adsp_compr_trigger(struct snd_compr_stream *stream, int cmd)
 		if (ret < 0)
 			break;
 
-		wm_adsp_buffer_clear(compr->buf);
-
 		/* Trigger the IRQ at one fragment of data */
 		ret = wm_adsp_buffer_write(compr->buf,
 					   HOST_BUFFER_FIELD(high_water_mark),
@@ -3584,6 +3587,8 @@ int wm_adsp_compr_trigger(struct snd_compr_stream *stream, int cmd)
 		}
 		break;
 	case SNDRV_PCM_TRIGGER_STOP:
+		if (wm_adsp_compr_attached(compr))
+			wm_adsp_buffer_clear(compr->buf);
 		break;
 	default:
 		ret = -EINVAL;
@@ -3917,22 +3922,40 @@ int wm_adsp2_lock(struct wm_adsp *dsp, unsigned int lock_regions)
 }
 EXPORT_SYMBOL_GPL(wm_adsp2_lock);
 
+static void wm_adsp_fatal_error(struct wm_adsp *dsp)
+{
+	struct wm_adsp_compr *compr;
+
+	dsp->fatal_error = true;
+
+	list_for_each_entry(compr, &dsp->compr_list, list) {
+		if (compr->stream) {
+			snd_compr_stop_error(compr->stream,
+					     SNDRV_PCM_STATE_XRUN);
+			snd_compr_fragment_elapsed(compr->stream);
+		}
+	}
+}
+
 irqreturn_t wm_adsp2_bus_error(struct wm_adsp *dsp)
 {
 	unsigned int val;
 	struct regmap *regmap = dsp->regmap;
 	int ret = 0;
 
+	mutex_lock(&dsp->pwr_lock);
+
 	ret = regmap_read(regmap, dsp->base + ADSP2_LOCK_REGION_CTRL, &val);
 	if (ret) {
 		adsp_err(dsp,
 			"Failed to read Region Lock Ctrl register: %d\n", ret);
-		return IRQ_HANDLED;
+		goto error;
 	}
 
 	if (val & ADSP2_WDT_TIMEOUT_STS_MASK) {
 		adsp_err(dsp, "watchdog timeout error\n");
 		wm_adsp_stop_watchdog(dsp);
+		wm_adsp_fatal_error(dsp);
 	}
 
 	if (val & (ADSP2_SLAVE_ERR_MASK | ADSP2_REGION_LOCK_ERR_MASK)) {
@@ -3946,7 +3969,7 @@ irqreturn_t wm_adsp2_bus_error(struct wm_adsp *dsp)
 			adsp_err(dsp,
 				 "Failed to read Bus Err Addr register: %d\n",
 				 ret);
-			return IRQ_HANDLED;
+			goto error;
 		}
 
 		adsp_err(dsp, "bus error address = 0x%x\n",
@@ -3959,7 +3982,7 @@ irqreturn_t wm_adsp2_bus_error(struct wm_adsp *dsp)
 			adsp_err(dsp,
 				 "Failed to read Pmem Xmem Err Addr register: %d\n",
 				 ret);
-			return IRQ_HANDLED;
+			goto error;
 		}
 
 		adsp_err(dsp, "xmem error address = 0x%x\n",
@@ -3972,6 +3995,9 @@ irqreturn_t wm_adsp2_bus_error(struct wm_adsp *dsp)
 	regmap_update_bits(regmap, dsp->base + ADSP2_LOCK_REGION_CTRL,
 			   ADSP2_CTRL_ERR_EINT, ADSP2_CTRL_ERR_EINT);
 
+error:
+	mutex_unlock(&dsp->pwr_lock);
+
 	return IRQ_HANDLED;
 }
 EXPORT_SYMBOL_GPL(wm_adsp2_bus_error);
diff --git a/sound/soc/codecs/wm_adsp.h b/sound/soc/codecs/wm_adsp.h
index 59e07ad16329..8f09b4419a91 100644
--- a/sound/soc/codecs/wm_adsp.h
+++ b/sound/soc/codecs/wm_adsp.h
@@ -85,6 +85,7 @@ struct wm_adsp {
 	bool preloaded;
 	bool booted;
 	bool running;
+	bool fatal_error;
 
 	struct list_head ctl_list;
 
diff --git a/sound/soc/fsl/fsl_asrc.c b/sound/soc/fsl/fsl_asrc.c
index 528e8b108422..0b937924d2e4 100644
--- a/sound/soc/fsl/fsl_asrc.c
+++ b/sound/soc/fsl/fsl_asrc.c
@@ -445,6 +445,19 @@ struct dma_chan *fsl_asrc_get_dma_channel(struct fsl_asrc_pair *pair, bool dir)
 }
 EXPORT_SYMBOL_GPL(fsl_asrc_get_dma_channel);
 
+static int fsl_asrc_dai_startup(struct snd_pcm_substream *substream,
+				struct snd_soc_dai *dai)
+{
+	struct fsl_asrc *asrc_priv = snd_soc_dai_get_drvdata(dai);
+
+	/* Odd channel number is not valid for older ASRC (channel_bits==3) */
+	if (asrc_priv->channel_bits == 3)
+		snd_pcm_hw_constraint_step(substream->runtime, 0,
+					   SNDRV_PCM_HW_PARAM_CHANNELS, 2);
+
+	return 0;
+}
+
 static int fsl_asrc_dai_hw_params(struct snd_pcm_substream *substream,
 				  struct snd_pcm_hw_params *params,
 				  struct snd_soc_dai *dai)
@@ -539,6 +552,7 @@ static int fsl_asrc_dai_trigger(struct snd_pcm_substream *substream, int cmd,
 }
 
 static const struct snd_soc_dai_ops fsl_asrc_dai_ops = {
+	.startup      = fsl_asrc_dai_startup,
 	.hw_params    = fsl_asrc_dai_hw_params,
 	.hw_free      = fsl_asrc_dai_hw_free,
 	.trigger      = fsl_asrc_dai_trigger,
diff --git a/sound/soc/fsl/fsl_esai.c b/sound/soc/fsl/fsl_esai.c
index afe67c865330..3623aa9a6f2e 100644
--- a/sound/soc/fsl/fsl_esai.c
+++ b/sound/soc/fsl/fsl_esai.c
@@ -54,6 +54,8 @@ struct fsl_esai {
 	u32 fifo_depth;
 	u32 slot_width;
 	u32 slots;
+	u32 tx_mask;
+	u32 rx_mask;
 	u32 hck_rate[2];
 	u32 sck_rate[2];
 	bool hck_dir[2];
@@ -361,21 +363,13 @@ static int fsl_esai_set_dai_tdm_slot(struct snd_soc_dai *dai, u32 tx_mask,
 	regmap_update_bits(esai_priv->regmap, REG_ESAI_TCCR,
 			   ESAI_xCCR_xDC_MASK, ESAI_xCCR_xDC(slots));
 
-	regmap_update_bits(esai_priv->regmap, REG_ESAI_TSMA,
-			   ESAI_xSMA_xS_MASK, ESAI_xSMA_xS(tx_mask));
-	regmap_update_bits(esai_priv->regmap, REG_ESAI_TSMB,
-			   ESAI_xSMB_xS_MASK, ESAI_xSMB_xS(tx_mask));
-
 	regmap_update_bits(esai_priv->regmap, REG_ESAI_RCCR,
 			   ESAI_xCCR_xDC_MASK, ESAI_xCCR_xDC(slots));
 
-	regmap_update_bits(esai_priv->regmap, REG_ESAI_RSMA,
-			   ESAI_xSMA_xS_MASK, ESAI_xSMA_xS(rx_mask));
-	regmap_update_bits(esai_priv->regmap, REG_ESAI_RSMB,
-			   ESAI_xSMB_xS_MASK, ESAI_xSMB_xS(rx_mask));
-
 	esai_priv->slot_width = slot_width;
 	esai_priv->slots = slots;
+	esai_priv->tx_mask = tx_mask;
+	esai_priv->rx_mask = rx_mask;
 
 	return 0;
 }
@@ -596,6 +590,7 @@ static int fsl_esai_trigger(struct snd_pcm_substream *substream, int cmd,
 	bool tx = substream->stream == SNDRV_PCM_STREAM_PLAYBACK;
 	u8 i, channels = substream->runtime->channels;
 	u32 pins = DIV_ROUND_UP(channels, esai_priv->slots);
+	u32 mask;
 
 	switch (cmd) {
 	case SNDRV_PCM_TRIGGER_START:
@@ -608,15 +603,38 @@ static int fsl_esai_trigger(struct snd_pcm_substream *substream, int cmd,
 		for (i = 0; tx && i < channels; i++)
 			regmap_write(esai_priv->regmap, REG_ESAI_ETDR, 0x0);
 
+		/*
+		 * When set the TE/RE in the end of enablement flow, there
+		 * will be channel swap issue for multi data line case.
+		 * In order to workaround this issue, we switch the bit
+		 * enablement sequence to below sequence
+		 * 1) clear the xSMB & xSMA: which is done in probe and
+		 *                           stop state.
+		 * 2) set TE/RE
+		 * 3) set xSMB
+		 * 4) set xSMA:  xSMA is the last one in this flow, which
+		 *               will trigger esai to start.
+		 */
 		regmap_update_bits(esai_priv->regmap, REG_ESAI_xCR(tx),
 				   tx ? ESAI_xCR_TE_MASK : ESAI_xCR_RE_MASK,
 				   tx ? ESAI_xCR_TE(pins) : ESAI_xCR_RE(pins));
+		mask = tx ? esai_priv->tx_mask : esai_priv->rx_mask;
+
+		regmap_update_bits(esai_priv->regmap, REG_ESAI_xSMB(tx),
+				   ESAI_xSMB_xS_MASK, ESAI_xSMB_xS(mask));
+		regmap_update_bits(esai_priv->regmap, REG_ESAI_xSMA(tx),
+				   ESAI_xSMA_xS_MASK, ESAI_xSMA_xS(mask));
+
 		break;
 	case SNDRV_PCM_TRIGGER_SUSPEND:
 	case SNDRV_PCM_TRIGGER_STOP:
 	case SNDRV_PCM_TRIGGER_PAUSE_PUSH:
 		regmap_update_bits(esai_priv->regmap, REG_ESAI_xCR(tx),
 				   tx ? ESAI_xCR_TE_MASK : ESAI_xCR_RE_MASK, 0);
+		regmap_update_bits(esai_priv->regmap, REG_ESAI_xSMA(tx),
+				   ESAI_xSMA_xS_MASK, 0);
+		regmap_update_bits(esai_priv->regmap, REG_ESAI_xSMB(tx),
+				   ESAI_xSMB_xS_MASK, 0);
 
 		/* Disable and reset FIFO */
 		regmap_update_bits(esai_priv->regmap, REG_ESAI_xFCR(tx),
@@ -906,6 +924,15 @@ static int fsl_esai_probe(struct platform_device *pdev)
 		return ret;
 	}
 
+	esai_priv->tx_mask = 0xFFFFFFFF;
+	esai_priv->rx_mask = 0xFFFFFFFF;
+
+	/* Clear the TSMA, TSMB, RSMA, RSMB */
+	regmap_write(esai_priv->regmap, REG_ESAI_TSMA, 0);
+	regmap_write(esai_priv->regmap, REG_ESAI_TSMB, 0);
+	regmap_write(esai_priv->regmap, REG_ESAI_RSMA, 0);
+	regmap_write(esai_priv->regmap, REG_ESAI_RSMB, 0);
+
 	ret = devm_snd_soc_register_component(&pdev->dev, &fsl_esai_component,
 					      &fsl_esai_dai, 1);
 	if (ret) {
diff --git a/sound/soc/generic/audio-graph-card.c b/sound/soc/generic/audio-graph-card.c
index bb12351330e8..69bc4848d787 100644
--- a/sound/soc/generic/audio-graph-card.c
+++ b/sound/soc/generic/audio-graph-card.c
@@ -20,6 +20,8 @@
 #include <linux/string.h>
 #include <sound/simple_card_utils.h>
 
+#define DPCM_SELECTABLE 1
+
 struct graph_priv {
 	struct snd_soc_card snd_card;
 	struct graph_dai_props {
@@ -440,6 +442,7 @@ static int graph_for_each_link(struct graph_priv *priv,
 	struct device_node *codec_port;
 	struct device_node *codec_port_old = NULL;
 	struct asoc_simple_card_data adata;
+	uintptr_t dpcm_selectable = (uintptr_t)of_device_get_match_data(dev);
 	int rc, ret;
 
 	/* loop for all listed CPU port */
@@ -470,8 +473,9 @@ static int graph_for_each_link(struct graph_priv *priv,
 			 * if Codec port has many endpoints,
 			 * or has convert-xxx property
 			 */
-			if ((of_get_child_count(codec_port) > 1) ||
-			    adata.convert_rate || adata.convert_channels)
+			if (dpcm_selectable &&
+			    ((of_get_child_count(codec_port) > 1) ||
+			     adata.convert_rate || adata.convert_channels))
 				ret = func_dpcm(priv, cpu_ep, codec_ep, li,
 						(codec_port_old == codec_port));
 			/* else normal sound */
@@ -732,7 +736,8 @@ static int graph_remove(struct platform_device *pdev)
 
 static const struct of_device_id graph_of_match[] = {
 	{ .compatible = "audio-graph-card", },
-	{ .compatible = "audio-graph-scu-card", },
+	{ .compatible = "audio-graph-scu-card",
+	  .data = (void *)DPCM_SELECTABLE },
 	{},
 };
 MODULE_DEVICE_TABLE(of, graph_of_match);
diff --git a/sound/soc/generic/simple-card.c b/sound/soc/generic/simple-card.c
index 7147bba45a2a..34de32efc4c4 100644
--- a/sound/soc/generic/simple-card.c
+++ b/sound/soc/generic/simple-card.c
@@ -9,12 +9,15 @@
 #include <linux/device.h>
 #include <linux/module.h>
 #include <linux/of.h>
+#include <linux/of_device.h>
 #include <linux/platform_device.h>
 #include <linux/string.h>
 #include <sound/simple_card.h>
 #include <sound/soc-dai.h>
 #include <sound/soc.h>
 
+#define DPCM_SELECTABLE 1
+
 struct simple_priv {
 	struct snd_soc_card snd_card;
 	struct simple_dai_props {
@@ -441,6 +444,7 @@ static int simple_for_each_link(struct simple_priv *priv,
 	struct device *dev = simple_priv_to_dev(priv);
 	struct device_node *top = dev->of_node;
 	struct device_node *node;
+	uintptr_t dpcm_selectable = (uintptr_t)of_device_get_match_data(dev);
 	bool is_top = 0;
 	int ret = 0;
 
@@ -480,8 +484,9 @@ static int simple_for_each_link(struct simple_priv *priv,
 			 * if it has many CPUs,
 			 * or has convert-xxx property
 			 */
-			if (num > 2 ||
-			    adata.convert_rate || adata.convert_channels)
+			if (dpcm_selectable &&
+			    (num > 2 ||
+			     adata.convert_rate || adata.convert_channels))
 				ret = func_dpcm(priv, np, codec, li, is_top);
 			/* else normal sound */
 			else
@@ -822,7 +827,8 @@ static int simple_remove(struct platform_device *pdev)
 
 static const struct of_device_id simple_of_match[] = {
 	{ .compatible = "simple-audio-card", },
-	{ .compatible = "simple-scu-audio-card", },
+	{ .compatible = "simple-scu-audio-card",
+	  .data = (void *)DPCM_SELECTABLE },
 	{},
 };
 MODULE_DEVICE_TABLE(of, simple_of_match);
diff --git a/sound/soc/intel/atom/sst-mfld-platform-pcm.c b/sound/soc/intel/atom/sst-mfld-platform-pcm.c
index 08cea5b5cda9..0e8b1c5eec88 100644
--- a/sound/soc/intel/atom/sst-mfld-platform-pcm.c
+++ b/sound/soc/intel/atom/sst-mfld-platform-pcm.c
@@ -706,9 +706,17 @@ static int sst_soc_probe(struct snd_soc_component *component)
 	return sst_dsp_init_v2_dpcm(component);
 }
 
+static void sst_soc_remove(struct snd_soc_component *component)
+{
+	struct sst_data *drv = dev_get_drvdata(component->dev);
+
+	drv->soc_card = NULL;
+}
+
 static const struct snd_soc_component_driver sst_soc_platform_drv  = {
 	.name		= DRV_NAME,
 	.probe		= sst_soc_probe,
+	.remove		= sst_soc_remove,
 	.ops		= &sst_platform_ops,
 	.compr_ops	= &sst_platform_compr_ops,
 	.pcm_new	= sst_pcm_new,
diff --git a/sound/soc/intel/boards/bytcht_da7213.c b/sound/soc/intel/boards/bytcht_da7213.c
index b8e884803777..4decba338156 100644
--- a/sound/soc/intel/boards/bytcht_da7213.c
+++ b/sound/soc/intel/boards/bytcht_da7213.c
@@ -226,7 +226,7 @@ static int bytcht_da7213_probe(struct platform_device *pdev)
 	struct snd_soc_card *card;
 	struct snd_soc_acpi_mach *mach;
 	const char *platform_name;
-	const char *i2c_name = NULL;
+	struct acpi_device *adev;
 	int dai_index = 0;
 	int ret_val = 0;
 	int i;
@@ -244,10 +244,11 @@ static int bytcht_da7213_probe(struct platform_device *pdev)
 	}
 
 	/* fixup codec name based on HID */
-	i2c_name = acpi_dev_get_first_match_name(mach->id, NULL, -1);
-	if (i2c_name) {
+	adev = acpi_dev_get_first_match_dev(mach->id, NULL, -1);
+	if (adev) {
 		snprintf(codec_name, sizeof(codec_name),
-			"%s%s", "i2c-", i2c_name);
+			 "i2c-%s", acpi_dev_name(adev));
+		put_device(&adev->dev);
 		dailink[dai_index].codec_name = codec_name;
 	}
 
diff --git a/sound/soc/intel/boards/bytcht_es8316.c b/sound/soc/intel/boards/bytcht_es8316.c
index d2a7e6ba11ae..6937c00cf63d 100644
--- a/sound/soc/intel/boards/bytcht_es8316.c
+++ b/sound/soc/intel/boards/bytcht_es8316.c
@@ -442,7 +442,7 @@ static int snd_byt_cht_es8316_mc_probe(struct platform_device *pdev)
 	struct device *dev = &pdev->dev;
 	struct snd_soc_acpi_mach *mach;
 	const char *platform_name;
-	const char *i2c_name = NULL;
+	struct acpi_device *adev;
 	struct device *codec_dev;
 	int dai_index = 0;
 	int i;
@@ -463,10 +463,11 @@ static int snd_byt_cht_es8316_mc_probe(struct platform_device *pdev)
 	}
 
 	/* fixup codec name based on HID */
-	i2c_name = acpi_dev_get_first_match_name(mach->id, NULL, -1);
-	if (i2c_name) {
+	adev = acpi_dev_get_first_match_dev(mach->id, NULL, -1);
+	if (adev) {
 		snprintf(codec_name, sizeof(codec_name),
-			"%s%s", "i2c-", i2c_name);
+			 "i2c-%s", acpi_dev_name(adev));
+		put_device(&adev->dev);
 		byt_cht_es8316_dais[dai_index].codec_name = codec_name;
 	}
 
diff --git a/sound/soc/intel/boards/bytcr_rt5640.c b/sound/soc/intel/boards/bytcr_rt5640.c
index 940eb27158da..f9175cf6747e 100644
--- a/sound/soc/intel/boards/bytcr_rt5640.c
+++ b/sound/soc/intel/boards/bytcr_rt5640.c
@@ -1154,7 +1154,7 @@ static int snd_byt_rt5640_mc_probe(struct platform_device *pdev)
 	struct byt_rt5640_private *priv;
 	struct snd_soc_acpi_mach *mach;
 	const char *platform_name;
-	const char *i2c_name = NULL;
+	struct acpi_device *adev;
 	int ret_val = 0;
 	int dai_index = 0;
 	int i;
@@ -1178,11 +1178,11 @@ static int snd_byt_rt5640_mc_probe(struct platform_device *pdev)
 	}
 
 	/* fixup codec name based on HID */
-	i2c_name = acpi_dev_get_first_match_name(mach->id, NULL, -1);
-	if (i2c_name) {
+	adev = acpi_dev_get_first_match_dev(mach->id, NULL, -1);
+	if (adev) {
 		snprintf(byt_rt5640_codec_name, sizeof(byt_rt5640_codec_name),
-			"%s%s", "i2c-", i2c_name);
-
+			 "i2c-%s", acpi_dev_name(adev));
+		put_device(&adev->dev);
 		byt_rt5640_dais[dai_index].codec_name = byt_rt5640_codec_name;
 	}
 
diff --git a/sound/soc/intel/boards/bytcr_rt5651.c b/sound/soc/intel/boards/bytcr_rt5651.c
index b0a4d297176e..b744add01d12 100644
--- a/sound/soc/intel/boards/bytcr_rt5651.c
+++ b/sound/soc/intel/boards/bytcr_rt5651.c
@@ -867,8 +867,8 @@ static int snd_byt_rt5651_mc_probe(struct platform_device *pdev)
 	struct byt_rt5651_private *priv;
 	struct snd_soc_acpi_mach *mach;
 	const char *platform_name;
+	struct acpi_device *adev;
 	struct device *codec_dev;
-	const char *i2c_name = NULL;
 	const char *hp_swapped;
 	bool is_bytcr = false;
 	int ret_val = 0;
@@ -894,14 +894,16 @@ static int snd_byt_rt5651_mc_probe(struct platform_device *pdev)
 	}
 
 	/* fixup codec name based on HID */
-	i2c_name = acpi_dev_get_first_match_name(mach->id, NULL, -1);
-	if (!i2c_name) {
+	adev = acpi_dev_get_first_match_dev(mach->id, NULL, -1);
+	if (adev) {
+		snprintf(byt_rt5651_codec_name, sizeof(byt_rt5651_codec_name),
+			 "i2c-%s", acpi_dev_name(adev));
+		put_device(&adev->dev);
+		byt_rt5651_dais[dai_index].codec_name = byt_rt5651_codec_name;
+	} else {
 		dev_err(&pdev->dev, "Error cannot find '%s' dev\n", mach->id);
 		return -ENODEV;
 	}
-	snprintf(byt_rt5651_codec_name, sizeof(byt_rt5651_codec_name),
-		"%s%s", "i2c-", i2c_name);
-	byt_rt5651_dais[dai_index].codec_name = byt_rt5651_codec_name;
 
 	codec_dev = bus_find_device_by_name(&i2c_bus_type, NULL,
 					    byt_rt5651_codec_name);
diff --git a/sound/soc/intel/boards/cht_bsw_max98090_ti.c b/sound/soc/intel/boards/cht_bsw_max98090_ti.c
index 3263b0495853..c0e0844f75b9 100644
--- a/sound/soc/intel/boards/cht_bsw_max98090_ti.c
+++ b/sound/soc/intel/boards/cht_bsw_max98090_ti.c
@@ -43,6 +43,7 @@ struct cht_mc_private {
 	struct clk *mclk;
 	struct snd_soc_jack jack;
 	bool ts3a227e_present;
+	int quirks;
 };
 
 static int platform_clock_control(struct snd_soc_dapm_widget *w,
@@ -54,6 +55,10 @@ static int platform_clock_control(struct snd_soc_dapm_widget *w,
 	struct cht_mc_private *ctx = snd_soc_card_get_drvdata(card);
 	int ret;
 
+	/* See the comment in snd_cht_mc_probe() */
+	if (ctx->quirks & QUIRK_PMC_PLT_CLK_0)
+		return 0;
+
 	codec_dai = snd_soc_card_get_codec_dai(card, CHT_CODEC_DAI);
 	if (!codec_dai) {
 		dev_err(card->dev, "Codec dai not found; Unable to set platform clock\n");
@@ -223,6 +228,10 @@ static int cht_codec_init(struct snd_soc_pcm_runtime *runtime)
 			"jack detection gpios not added, error %d\n", ret);
 	}
 
+	/* See the comment in snd_cht_mc_probe() */
+	if (ctx->quirks & QUIRK_PMC_PLT_CLK_0)
+		return 0;
+
 	/*
 	 * The firmware might enable the clock at
 	 * boot (this information may or may not
@@ -423,16 +432,15 @@ static int snd_cht_mc_probe(struct platform_device *pdev)
 	const char *mclk_name;
 	struct snd_soc_acpi_mach *mach;
 	const char *platform_name;
-	int quirks = 0;
-
-	dmi_id = dmi_first_match(cht_max98090_quirk_table);
-	if (dmi_id)
-		quirks = (unsigned long)dmi_id->driver_data;
 
 	drv = devm_kzalloc(&pdev->dev, sizeof(*drv), GFP_KERNEL);
 	if (!drv)
 		return -ENOMEM;
 
+	dmi_id = dmi_first_match(cht_max98090_quirk_table);
+	if (dmi_id)
+		drv->quirks = (unsigned long)dmi_id->driver_data;
+
 	drv->ts3a227e_present = acpi_dev_found("104C227E");
 	if (!drv->ts3a227e_present) {
 		/* no need probe TI jack detection chip */
@@ -458,7 +466,7 @@ static int snd_cht_mc_probe(struct platform_device *pdev)
 	snd_soc_card_cht.dev = &pdev->dev;
 	snd_soc_card_set_drvdata(&snd_soc_card_cht, drv);
 
-	if (quirks & QUIRK_PMC_PLT_CLK_0)
+	if (drv->quirks & QUIRK_PMC_PLT_CLK_0)
 		mclk_name = "pmc_plt_clk_0";
 	else
 		mclk_name = "pmc_plt_clk_3";
@@ -471,6 +479,21 @@ static int snd_cht_mc_probe(struct platform_device *pdev)
 		return PTR_ERR(drv->mclk);
 	}
 
+	/*
+	 * Boards which have the MAX98090's clk connected to clk_0 do not seem
+	 * to like it if we muck with the clock. If we disable the clock when
+	 * it is unused we get "max98090 i2c-193C9890:00: PLL unlocked" errors
+	 * and the PLL never seems to lock again.
+	 * So for these boards we enable it here once and leave it at that.
+	 */
+	if (drv->quirks & QUIRK_PMC_PLT_CLK_0) {
+		ret_val = clk_prepare_enable(drv->mclk);
+		if (ret_val < 0) {
+			dev_err(&pdev->dev, "MCLK enable error: %d\n", ret_val);
+			return ret_val;
+		}
+	}
+
 	ret_val = devm_snd_soc_register_card(&pdev->dev, &snd_soc_card_cht);
 	if (ret_val) {
 		dev_err(&pdev->dev,
@@ -481,11 +504,23 @@ static int snd_cht_mc_probe(struct platform_device *pdev)
 	return ret_val;
 }
 
+static int snd_cht_mc_remove(struct platform_device *pdev)
+{
+	struct snd_soc_card *card = platform_get_drvdata(pdev);
+	struct cht_mc_private *ctx = snd_soc_card_get_drvdata(card);
+
+	if (ctx->quirks & QUIRK_PMC_PLT_CLK_0)
+		clk_disable_unprepare(ctx->mclk);
+
+	return 0;
+}
+
 static struct platform_driver snd_cht_mc_driver = {
 	.driver = {
 		.name = "cht-bsw-max98090",
 	},
 	.probe = snd_cht_mc_probe,
+	.remove = snd_cht_mc_remove,
 };
 
 module_platform_driver(snd_cht_mc_driver)
diff --git a/sound/soc/intel/boards/cht_bsw_rt5645.c b/sound/soc/intel/boards/cht_bsw_rt5645.c
index cbc2d458483f..32dbeaf1ab94 100644
--- a/sound/soc/intel/boards/cht_bsw_rt5645.c
+++ b/sound/soc/intel/boards/cht_bsw_rt5645.c
@@ -532,7 +532,7 @@ static int snd_cht_mc_probe(struct platform_device *pdev)
 	struct snd_soc_acpi_mach *mach;
 	const char *platform_name;
 	struct cht_mc_private *drv;
-	const char *i2c_name = NULL;
+	struct acpi_device *adev;
 	bool found = false;
 	bool is_bytcr = false;
 	int dai_index = 0;
@@ -573,10 +573,11 @@ static int snd_cht_mc_probe(struct platform_device *pdev)
 		}
 
 	/* fixup codec name based on HID */
-	i2c_name = acpi_dev_get_first_match_name(mach->id, NULL, -1);
-	if (i2c_name) {
+	adev = acpi_dev_get_first_match_dev(mach->id, NULL, -1);
+	if (adev) {
 		snprintf(cht_rt5645_codec_name, sizeof(cht_rt5645_codec_name),
-			"%s%s", "i2c-", i2c_name);
+			 "i2c-%s", acpi_dev_name(adev));
+		put_device(&adev->dev);
 		cht_dailink[dai_index].codec_name = cht_rt5645_codec_name;
 	}
 
diff --git a/sound/soc/intel/boards/cht_bsw_rt5672.c b/sound/soc/intel/boards/cht_bsw_rt5672.c
index 3d5a2b3a06f0..0f7770822388 100644
--- a/sound/soc/intel/boards/cht_bsw_rt5672.c
+++ b/sound/soc/intel/boards/cht_bsw_rt5672.c
@@ -401,7 +401,7 @@ static int snd_cht_mc_probe(struct platform_device *pdev)
 	struct cht_mc_private *drv;
 	struct snd_soc_acpi_mach *mach = pdev->dev.platform_data;
 	const char *platform_name;
-	const char *i2c_name;
+	struct acpi_device *adev;
 	int i;
 
 	drv = devm_kzalloc(&pdev->dev, sizeof(*drv), GFP_KERNEL);
@@ -411,10 +411,11 @@ static int snd_cht_mc_probe(struct platform_device *pdev)
 	strcpy(drv->codec_name, RT5672_I2C_DEFAULT);
 
 	/* fixup codec name based on HID */
-	i2c_name = acpi_dev_get_first_match_name(mach->id, NULL, -1);
-	if (i2c_name) {
+	adev = acpi_dev_get_first_match_dev(mach->id, NULL, -1);
+	if (adev) {
 		snprintf(drv->codec_name, sizeof(drv->codec_name),
-			 "i2c-%s", i2c_name);
+			 "i2c-%s", acpi_dev_name(adev));
+		put_device(&adev->dev);
 		for (i = 0; i < ARRAY_SIZE(cht_dailink); i++) {
 			if (!strcmp(cht_dailink[i].codec_name,
 				RT5672_I2C_DEFAULT)) {
diff --git a/sound/soc/intel/boards/kbl_rt5663_rt5514_max98927.c b/sound/soc/intel/boards/kbl_rt5663_rt5514_max98927.c
index 7044d8c2b187..879f14257a3e 100644
--- a/sound/soc/intel/boards/kbl_rt5663_rt5514_max98927.c
+++ b/sound/soc/intel/boards/kbl_rt5663_rt5514_max98927.c
@@ -405,7 +405,7 @@ static const struct snd_pcm_hw_constraint_list constraints_dmic_channels = {
 };
 
 static const unsigned int dmic_2ch[] = {
-	4,
+	2,
 };
 
 static const struct snd_pcm_hw_constraint_list constraints_dmic_2ch = {
diff --git a/sound/soc/intel/skylake/skl-messages.c b/sound/soc/intel/skylake/skl-messages.c
index 28c4806b196a..4bf70b4429f0 100644
--- a/sound/soc/intel/skylake/skl-messages.c
+++ b/sound/soc/intel/skylake/skl-messages.c
@@ -483,6 +483,7 @@ static void skl_set_base_module_format(struct skl_sst *ctx,
 	base_cfg->audio_fmt.bit_depth = format->bit_depth;
 	base_cfg->audio_fmt.valid_bit_depth = format->valid_bit_depth;
 	base_cfg->audio_fmt.ch_cfg = format->ch_cfg;
+	base_cfg->audio_fmt.sample_type = format->sample_type;
 
 	dev_dbg(ctx->dev, "bit_depth=%x valid_bd=%x ch_config=%x\n",
 			format->bit_depth, format->valid_bit_depth,
diff --git a/sound/soc/intel/skylake/skl-pcm.c b/sound/soc/intel/skylake/skl-pcm.c
index 1ae83f4ccc36..9735e2412251 100644
--- a/sound/soc/intel/skylake/skl-pcm.c
+++ b/sound/soc/intel/skylake/skl-pcm.c
@@ -181,6 +181,7 @@ int skl_pcm_link_dma_prepare(struct device *dev, struct skl_pipe_params *params)
 	struct hdac_stream *hstream;
 	struct hdac_ext_stream *stream;
 	struct hdac_ext_link *link;
+	unsigned char stream_tag;
 
 	hstream = snd_hdac_get_stream(bus, params->stream,
 					params->link_dma_id + 1);
@@ -199,10 +200,13 @@ int skl_pcm_link_dma_prepare(struct device *dev, struct skl_pipe_params *params)
 
 	snd_hdac_ext_link_stream_setup(stream, format_val);
 
-	list_for_each_entry(link, &bus->hlink_list, list) {
-		if (link->index == params->link_index)
-			snd_hdac_ext_link_set_stream_id(link,
-					hstream->stream_tag);
+	stream_tag = hstream->stream_tag;
+	if (stream->hstream.direction == SNDRV_PCM_STREAM_PLAYBACK) {
+		list_for_each_entry(link, &bus->hlink_list, list) {
+			if (link->index == params->link_index)
+				snd_hdac_ext_link_set_stream_id(link,
+								stream_tag);
+		}
 	}
 
 	stream->link_prepared = 1;
@@ -645,6 +649,7 @@ static int skl_link_hw_free(struct snd_pcm_substream *substream,
 	struct hdac_ext_stream *link_dev =
 				snd_soc_dai_get_dma_data(dai, substream);
 	struct hdac_ext_link *link;
+	unsigned char stream_tag;
 
 	dev_dbg(dai->dev, "%s: %s\n", __func__, dai->name);
 
@@ -654,7 +659,11 @@ static int skl_link_hw_free(struct snd_pcm_substream *substream,
 	if (!link)
 		return -EINVAL;
 
-	snd_hdac_ext_link_clear_stream_id(link, hdac_stream(link_dev)->stream_tag);
+	if (substream->stream == SNDRV_PCM_STREAM_PLAYBACK) {
+		stream_tag = hdac_stream(link_dev)->stream_tag;
+		snd_hdac_ext_link_clear_stream_id(link, stream_tag);
+	}
+
 	snd_hdac_ext_stream_release(link_dev, HDAC_EXT_STREAM_TYPE_LINK);
 	return 0;
 }
@@ -1453,13 +1462,20 @@ static int skl_platform_soc_probe(struct snd_soc_component *component)
 	return 0;
 }
 
+static void skl_pcm_remove(struct snd_soc_component *component)
+{
+	/* remove topology */
+	snd_soc_tplg_component_remove(component, SND_SOC_TPLG_INDEX_ALL);
+}
+
 static const struct snd_soc_component_driver skl_component  = {
 	.name		= "pcm",
 	.probe		= skl_platform_soc_probe,
+	.remove		= skl_pcm_remove,
 	.ops		= &skl_platform_ops,
 	.pcm_new	= skl_pcm_new,
 	.pcm_free	= skl_pcm_free,
-	.ignore_module_refcount = 1, /* do not increase the refcount in core */
+	.module_get_upon_open = 1, /* increment refcount when a pcm is opened */
 };
 
 int skl_platform_register(struct device *dev)
diff --git a/sound/soc/mediatek/common/mtk-btcvsd.c b/sound/soc/mediatek/common/mtk-btcvsd.c
index 1b8bcdaf02d1..9a163d7064d1 100644
--- a/sound/soc/mediatek/common/mtk-btcvsd.c
+++ b/sound/soc/mediatek/common/mtk-btcvsd.c
@@ -49,6 +49,7 @@ enum bt_sco_state {
 	BT_SCO_STATE_IDLE,
 	BT_SCO_STATE_RUNNING,
 	BT_SCO_STATE_ENDING,
+	BT_SCO_STATE_LOOPBACK,
 };
 
 enum bt_sco_direct {
@@ -486,7 +487,8 @@ static irqreturn_t mtk_btcvsd_snd_irq_handler(int irq_id, void *dev)
 	if (bt->rx->state != BT_SCO_STATE_RUNNING &&
 	    bt->rx->state != BT_SCO_STATE_ENDING &&
 	    bt->tx->state != BT_SCO_STATE_RUNNING &&
-	    bt->tx->state != BT_SCO_STATE_ENDING) {
+	    bt->tx->state != BT_SCO_STATE_ENDING &&
+	    bt->tx->state != BT_SCO_STATE_LOOPBACK) {
 		dev_warn(bt->dev, "%s(), in idle state: rx->state: %d, tx->state: %d\n",
 			 __func__, bt->rx->state, bt->tx->state);
 		goto irq_handler_exit;
@@ -512,6 +514,42 @@ static irqreturn_t mtk_btcvsd_snd_irq_handler(int irq_id, void *dev)
 	buf_cnt_tx = btsco_packet_info[packet_type][2];
 	buf_cnt_rx = btsco_packet_info[packet_type][3];
 
+	if (bt->tx->state == BT_SCO_STATE_LOOPBACK) {
+		u8 *src, *dst;
+		unsigned long connsys_addr_rx, ap_addr_rx;
+		unsigned long connsys_addr_tx, ap_addr_tx;
+
+		connsys_addr_rx = *bt->bt_reg_pkt_r;
+		ap_addr_rx = (unsigned long)bt->bt_sram_bank2_base +
+			     (connsys_addr_rx & 0xFFFF);
+
+		connsys_addr_tx = *bt->bt_reg_pkt_w;
+		ap_addr_tx = (unsigned long)bt->bt_sram_bank2_base +
+			     (connsys_addr_tx & 0xFFFF);
+
+		if (connsys_addr_tx == 0xdeadfeed ||
+		    connsys_addr_rx == 0xdeadfeed) {
+			/* bt return 0xdeadfeed if read reg during bt sleep */
+			dev_warn(bt->dev, "%s(), connsys_addr_tx == 0xdeadfeed\n",
+				 __func__);
+			goto irq_handler_exit;
+		}
+
+		src = (u8 *)ap_addr_rx;
+		dst = (u8 *)ap_addr_tx;
+
+		mtk_btcvsd_snd_data_transfer(BT_SCO_DIRECT_BT2ARM, src,
+					     bt->tx->temp_packet_buf,
+					     packet_length,
+					     packet_num);
+		mtk_btcvsd_snd_data_transfer(BT_SCO_DIRECT_ARM2BT,
+					     bt->tx->temp_packet_buf, dst,
+					     packet_length,
+					     packet_num);
+		bt->rx->rw_cnt++;
+		bt->tx->rw_cnt++;
+	}
+
 	if (bt->rx->state == BT_SCO_STATE_RUNNING ||
 	    bt->rx->state == BT_SCO_STATE_ENDING) {
 		if (bt->rx->xrun) {
@@ -1067,6 +1105,33 @@ static int btcvsd_band_set(struct snd_kcontrol *kcontrol,
 	return 0;
 }
 
+static int btcvsd_loopback_get(struct snd_kcontrol *kcontrol,
+			       struct snd_ctl_elem_value *ucontrol)
+{
+	struct snd_soc_component *cmpnt = snd_soc_kcontrol_component(kcontrol);
+	struct mtk_btcvsd_snd *bt = snd_soc_component_get_drvdata(cmpnt);
+	bool lpbk_en = bt->tx->state == BT_SCO_STATE_LOOPBACK;
+
+	ucontrol->value.integer.value[0] = lpbk_en;
+	return 0;
+}
+
+static int btcvsd_loopback_set(struct snd_kcontrol *kcontrol,
+			       struct snd_ctl_elem_value *ucontrol)
+{
+	struct snd_soc_component *cmpnt = snd_soc_kcontrol_component(kcontrol);
+	struct mtk_btcvsd_snd *bt = snd_soc_component_get_drvdata(cmpnt);
+
+	if (ucontrol->value.integer.value[0]) {
+		mtk_btcvsd_snd_set_state(bt, bt->tx, BT_SCO_STATE_LOOPBACK);
+		mtk_btcvsd_snd_set_state(bt, bt->rx, BT_SCO_STATE_LOOPBACK);
+	} else {
+		mtk_btcvsd_snd_set_state(bt, bt->tx, BT_SCO_STATE_RUNNING);
+		mtk_btcvsd_snd_set_state(bt, bt->rx, BT_SCO_STATE_RUNNING);
+	}
+	return 0;
+}
+
 static int btcvsd_tx_mute_get(struct snd_kcontrol *kcontrol,
 			      struct snd_ctl_elem_value *ucontrol)
 {
@@ -1202,6 +1267,8 @@ static int btcvsd_tx_timestamp_get(struct snd_kcontrol *kcontrol,
 static const struct snd_kcontrol_new mtk_btcvsd_snd_controls[] = {
 	SOC_ENUM_EXT("BTCVSD Band", btcvsd_enum[0],
 		     btcvsd_band_get, btcvsd_band_set),
+	SOC_SINGLE_BOOL_EXT("BTCVSD Loopback Switch", 0,
+			    btcvsd_loopback_get, btcvsd_loopback_set),
 	SOC_SINGLE_BOOL_EXT("BTCVSD Tx Mute Switch", 0,
 			    btcvsd_tx_mute_get, btcvsd_tx_mute_set),
 	SOC_SINGLE_BOOL_EXT("BTCVSD Tx Irq Received Switch", 0,
diff --git a/sound/soc/mediatek/mt8183/mt8183-afe-clk.c b/sound/soc/mediatek/mt8183/mt8183-afe-clk.c
index f523ad103acc..48e81c5d52fc 100644
--- a/sound/soc/mediatek/mt8183/mt8183-afe-clk.c
+++ b/sound/soc/mediatek/mt8183/mt8183-afe-clk.c
@@ -605,6 +605,10 @@ void mt8183_mck_disable(struct mtk_base_afe *afe, int mck_id)
 	int m_sel_id = mck_div[mck_id].m_sel_id;
 	int div_clk_id = mck_div[mck_id].div_clk_id;
 
+	/* i2s5 mck not support */
+	if (mck_id == MT8183_I2S5_MCK)
+		return;
+
 	clk_disable_unprepare(afe_priv->clk[div_clk_id]);
 	if (m_sel_id >= 0)
 		clk_disable_unprepare(afe_priv->clk[m_sel_id]);
diff --git a/sound/soc/rockchip/rockchip_pdm.c b/sound/soc/rockchip/rockchip_pdm.c
index 400e29edb1c9..d0b403a0e27b 100644
--- a/sound/soc/rockchip/rockchip_pdm.c
+++ b/sound/soc/rockchip/rockchip_pdm.c
@@ -24,7 +24,7 @@
 
 #include "rockchip_pdm.h"
 
-#define PDM_DMA_BURST_SIZE	(16) /* size * width: 16*4 = 64 bytes */
+#define PDM_DMA_BURST_SIZE	(8) /* size * width: 8*4 = 32 bytes */
 
 struct rk_pdm_dev {
 	struct device *dev;
@@ -208,7 +208,9 @@ static int rockchip_pdm_set_fmt(struct snd_soc_dai *cpu_dai,
 		return -EINVAL;
 	}
 
+	pm_runtime_get_sync(cpu_dai->dev);
 	regmap_update_bits(pdm->regmap, PDM_CLK_CTRL, mask, val);
+	pm_runtime_put(cpu_dai->dev);
 
 	return 0;
 }
diff --git a/sound/soc/samsung/i2s.c b/sound/soc/samsung/i2s.c
index 4231001226f4..ab471d550d17 100644
--- a/sound/soc/samsung/i2s.c
+++ b/sound/soc/samsung/i2s.c
@@ -1130,11 +1130,11 @@ static const struct snd_soc_dapm_widget samsung_i2s_widgets[] = {
 };
 
 static const struct snd_soc_dapm_route samsung_i2s_dapm_routes[] = {
-	{ "Playback Mixer", NULL, "Primary" },
-	{ "Playback Mixer", NULL, "Secondary" },
+	{ "Playback Mixer", NULL, "Primary Playback" },
+	{ "Playback Mixer", NULL, "Secondary Playback" },
 
 	{ "Mixer DAI TX", NULL, "Playback Mixer" },
-	{ "Playback Mixer", NULL, "Mixer DAI RX" },
+	{ "Primary Capture", NULL, "Mixer DAI RX" },
 };
 
 static const struct snd_soc_component_driver samsung_i2s_component = {
@@ -1155,7 +1155,8 @@ static int i2s_alloc_dais(struct samsung_i2s_priv *priv,
 			  int num_dais)
 {
 	static const char *dai_names[] = { "samsung-i2s", "samsung-i2s-sec" };
-	static const char *stream_names[] = { "Primary", "Secondary" };
+	static const char *stream_names[] = { "Primary Playback",
+					      "Secondary Playback" };
 	struct snd_soc_dai_driver *dai_drv;
 	struct i2s_dai *dai;
 	int i;
@@ -1201,6 +1202,7 @@ static int i2s_alloc_dais(struct samsung_i2s_priv *priv,
 	dai_drv->capture.channels_max = 2;
 	dai_drv->capture.rates = i2s_dai_data->pcm_rates;
 	dai_drv->capture.formats = SAMSUNG_I2S_FMTS;
+	dai_drv->capture.stream_name = "Primary Capture";
 
 	return 0;
 }
diff --git a/sound/soc/samsung/odroid.c b/sound/soc/samsung/odroid.c
index 694512f980fd..1dc54c4206f0 100644
--- a/sound/soc/samsung/odroid.c
+++ b/sound/soc/samsung/odroid.c
@@ -91,11 +91,11 @@ static int odroid_card_be_hw_params(struct snd_pcm_substream *substream,
 		return ret;
 
 	/*
-	 *  We add 1 to the rclk_freq value in order to avoid too low clock
+	 *  We add 2 to the rclk_freq value in order to avoid too low clock
 	 *  frequency values due to the EPLL output frequency not being exact
 	 *  multiple of the audio sampling rate.
 	 */
-	rclk_freq = params_rate(params) * rfs + 1;
+	rclk_freq = params_rate(params) * rfs + 2;
 
 	ret = clk_set_rate(priv->sclk_i2s, rclk_freq);
 	if (ret < 0)
diff --git a/sound/soc/sh/rcar/core.c b/sound/soc/sh/rcar/core.c
index 022996d2db13..4fe83e611c01 100644
--- a/sound/soc/sh/rcar/core.c
+++ b/sound/soc/sh/rcar/core.c
@@ -110,6 +110,8 @@ static const struct of_device_id rsnd_of_match[] = {
 	{ .compatible = "renesas,rcar_sound-gen1", .data = (void *)RSND_GEN1 },
 	{ .compatible = "renesas,rcar_sound-gen2", .data = (void *)RSND_GEN2 },
 	{ .compatible = "renesas,rcar_sound-gen3", .data = (void *)RSND_GEN3 },
+	/* Special Handling */
+	{ .compatible = "renesas,rcar_sound-r8a77990", .data = (void *)(RSND_GEN3 | RSND_SOC_E) },
 	{},
 };
 MODULE_DEVICE_TABLE(of, rsnd_of_match);
diff --git a/sound/soc/sh/rcar/rsnd.h b/sound/soc/sh/rcar/rsnd.h
index 90625c57847b..0e6ef4e18400 100644
--- a/sound/soc/sh/rcar/rsnd.h
+++ b/sound/soc/sh/rcar/rsnd.h
@@ -607,6 +607,8 @@ struct rsnd_priv {
 #define RSND_GEN1	(1 << 0)
 #define RSND_GEN2	(2 << 0)
 #define RSND_GEN3	(3 << 0)
+#define RSND_SOC_MASK	(0xFF << 4)
+#define RSND_SOC_E	(1 << 4) /* E1/E2/E3 */
 
 	/*
 	 * below value will be filled on rsnd_gen_probe()
@@ -679,6 +681,9 @@ struct rsnd_priv {
 #define rsnd_is_gen1(priv)	(((priv)->flags & RSND_GEN_MASK) == RSND_GEN1)
 #define rsnd_is_gen2(priv)	(((priv)->flags & RSND_GEN_MASK) == RSND_GEN2)
 #define rsnd_is_gen3(priv)	(((priv)->flags & RSND_GEN_MASK) == RSND_GEN3)
+#define rsnd_is_e3(priv)	(((priv)->flags & \
+					(RSND_GEN_MASK | RSND_SOC_MASK)) == \
+					(RSND_GEN3 | RSND_SOC_E))
 
 #define rsnd_flags_has(p, f) ((p)->flags & (f))
 #define rsnd_flags_set(p, f) ((p)->flags |= (f))
diff --git a/sound/soc/sh/rcar/src.c b/sound/soc/sh/rcar/src.c
index db81e066b92e..585ffba0244b 100644
--- a/sound/soc/sh/rcar/src.c
+++ b/sound/soc/sh/rcar/src.c
@@ -14,7 +14,6 @@
  */
 
 #include "rsnd.h"
-#include <linux/sys_soc.h>
 
 #define SRC_NAME "src"
 
@@ -135,7 +134,7 @@ unsigned int rsnd_src_get_rate(struct rsnd_priv *priv,
 	return rate;
 }
 
-const static u32 bsdsr_table_pattern1[] = {
+static const u32 bsdsr_table_pattern1[] = {
 	0x01800000, /* 6 - 1/6 */
 	0x01000000, /* 6 - 1/4 */
 	0x00c00000, /* 6 - 1/3 */
@@ -144,7 +143,7 @@ const static u32 bsdsr_table_pattern1[] = {
 	0x00400000, /* 6 - 1   */
 };
 
-const static u32 bsdsr_table_pattern2[] = {
+static const u32 bsdsr_table_pattern2[] = {
 	0x02400000, /* 6 - 1/6 */
 	0x01800000, /* 6 - 1/4 */
 	0x01200000, /* 6 - 1/3 */
@@ -153,7 +152,7 @@ const static u32 bsdsr_table_pattern2[] = {
 	0x00600000, /* 6 - 1   */
 };
 
-const static u32 bsisr_table[] = {
+static const u32 bsisr_table[] = {
 	0x00100060, /* 6 - 1/6 */
 	0x00100040, /* 6 - 1/4 */
 	0x00100030, /* 6 - 1/3 */
@@ -162,7 +161,7 @@ const static u32 bsisr_table[] = {
 	0x00100020, /* 6 - 1   */
 };
 
-const static u32 chan288888[] = {
+static const u32 chan288888[] = {
 	0x00000006, /* 1 to 2 */
 	0x000001fe, /* 1 to 8 */
 	0x000001fe, /* 1 to 8 */
@@ -171,7 +170,7 @@ const static u32 chan288888[] = {
 	0x000001fe, /* 1 to 8 */
 };
 
-const static u32 chan244888[] = {
+static const u32 chan244888[] = {
 	0x00000006, /* 1 to 2 */
 	0x0000001e, /* 1 to 4 */
 	0x0000001e, /* 1 to 4 */
@@ -180,7 +179,7 @@ const static u32 chan244888[] = {
 	0x000001fe, /* 1 to 8 */
 };
 
-const static u32 chan222222[] = {
+static const u32 chan222222[] = {
 	0x00000006, /* 1 to 2 */
 	0x00000006, /* 1 to 2 */
 	0x00000006, /* 1 to 2 */
@@ -189,18 +188,12 @@ const static u32 chan222222[] = {
 	0x00000006, /* 1 to 2 */
 };
 
-static const struct soc_device_attribute ov_soc[] = {
-	{ .soc_id = "r8a77990" }, /* E3 */
-	{ /* sentinel */ }
-};
-
 static void rsnd_src_set_convert_rate(struct rsnd_dai_stream *io,
 				      struct rsnd_mod *mod)
 {
 	struct rsnd_priv *priv = rsnd_mod_to_priv(mod);
 	struct device *dev = rsnd_priv_to_dev(priv);
 	struct snd_pcm_runtime *runtime = rsnd_io_to_runtime(io);
-	const struct soc_device_attribute *soc = soc_device_match(ov_soc);
 	int is_play = rsnd_io_is_play(io);
 	int use_src = 0;
 	u32 fin, fout;
@@ -307,7 +300,7 @@ static void rsnd_src_set_convert_rate(struct rsnd_dai_stream *io,
 	/*
 	 * E3 need to overwrite
 	 */
-	if (soc)
+	if (rsnd_is_e3(priv))
 		switch (rsnd_mod_id(mod)) {
 		case 0:
 		case 4:
diff --git a/sound/soc/soc-core.c b/sound/soc/soc-core.c
index 93d316d5bf8e..46e3ab0fced4 100644
--- a/sound/soc/soc-core.c
+++ b/sound/soc/soc-core.c
@@ -947,7 +947,7 @@ static void soc_cleanup_component(struct snd_soc_component *component)
 	snd_soc_dapm_free(snd_soc_component_get_dapm(component));
 	soc_cleanup_component_debugfs(component);
 	component->card = NULL;
-	if (!component->driver->ignore_module_refcount)
+	if (!component->driver->module_get_upon_open)
 		module_put(component->dev->driver->owner);
 }
 
@@ -1381,7 +1381,7 @@ static int soc_probe_component(struct snd_soc_card *card,
 		return 0;
 	}
 
-	if (!component->driver->ignore_module_refcount &&
+	if (!component->driver->module_get_upon_open &&
 	    !try_module_get(component->dev->driver->owner))
 		return -ENODEV;
 
@@ -2797,6 +2797,7 @@ int snd_soc_register_card(struct snd_soc_card *card)
 
 		ret = soc_init_dai_link(card, link);
 		if (ret) {
+			soc_cleanup_platform(card);
 			dev_err(card->dev, "ASoC: failed to init link %s\n",
 				link->name);
 			mutex_unlock(&client_mutex);
@@ -2819,6 +2820,7 @@ int snd_soc_register_card(struct snd_soc_card *card)
 	card->instantiated = 0;
 	mutex_init(&card->mutex);
 	mutex_init(&card->dapm_mutex);
+	spin_lock_init(&card->dpcm_lock);
 
 	return snd_soc_bind_card(card);
 }
diff --git a/sound/soc/soc-dapm.c b/sound/soc/soc-dapm.c
index 1ec06ef6d161..0382a47b30bd 100644
--- a/sound/soc/soc-dapm.c
+++ b/sound/soc/soc-dapm.c
@@ -3650,6 +3650,13 @@ snd_soc_dapm_new_control_unlocked(struct snd_soc_dapm_context *dapm,
 	case snd_soc_dapm_dac:
 	case snd_soc_dapm_aif_in:
 	case snd_soc_dapm_pga:
+	case snd_soc_dapm_buffer:
+	case snd_soc_dapm_scheduler:
+	case snd_soc_dapm_effect:
+	case snd_soc_dapm_src:
+	case snd_soc_dapm_asrc:
+	case snd_soc_dapm_encoder:
+	case snd_soc_dapm_decoder:
 	case snd_soc_dapm_out_drv:
 	case snd_soc_dapm_micbias:
 	case snd_soc_dapm_line:
@@ -3957,6 +3964,10 @@ snd_soc_dapm_free_kcontrol(struct snd_soc_card *card,
 	int count;
 
 	devm_kfree(card->dev, (void *)*private_value);
+
+	if (!w_param_text)
+		return;
+
 	for (count = 0 ; count < num_params; count++)
 		devm_kfree(card->dev, (void *)w_param_text[count]);
 	devm_kfree(card->dev, w_param_text);
diff --git a/sound/soc/soc-pcm.c b/sound/soc/soc-pcm.c
index 0d5ec68a1e50..be80a12fba27 100644
--- a/sound/soc/soc-pcm.c
+++ b/sound/soc/soc-pcm.c
@@ -15,6 +15,7 @@
 #include <linux/delay.h>
 #include <linux/pinctrl/consumer.h>
 #include <linux/pm_runtime.h>
+#include <linux/module.h>
 #include <linux/slab.h>
 #include <linux/workqueue.h>
 #include <linux/export.h>
@@ -463,6 +464,9 @@ static int soc_pcm_components_close(struct snd_pcm_substream *substream,
 			continue;
 
 		component->driver->ops->close(substream);
+
+		if (component->driver->module_get_upon_open)
+			module_put(component->dev->driver->owner);
 	}
 
 	return 0;
@@ -513,6 +517,12 @@ static int soc_pcm_open(struct snd_pcm_substream *substream)
 		    !component->driver->ops->open)
 			continue;
 
+		if (component->driver->module_get_upon_open &&
+		    !try_module_get(component->dev->driver->owner)) {
+			ret = -ENODEV;
+			goto module_err;
+		}
+
 		ret = component->driver->ops->open(substream);
 		if (ret < 0) {
 			dev_err(component->dev,
@@ -628,7 +638,7 @@ codec_dai_err:
 
 component_err:
 	soc_pcm_components_close(substream, component);
-
+module_err:
 	if (cpu_dai->driver->ops->shutdown)
 		cpu_dai->driver->ops->shutdown(substream, cpu_dai);
 out:
@@ -954,10 +964,13 @@ static int soc_pcm_hw_params(struct snd_pcm_substream *substream,
 		codec_params = *params;
 
 		/* fixup params based on TDM slot masks */
-		if (codec_dai->tx_mask)
+		if (substream->stream == SNDRV_PCM_STREAM_PLAYBACK &&
+		    codec_dai->tx_mask)
 			soc_pcm_codec_params_fixup(&codec_params,
 						   codec_dai->tx_mask);
-		if (codec_dai->rx_mask)
+
+		if (substream->stream == SNDRV_PCM_STREAM_CAPTURE &&
+		    codec_dai->rx_mask)
 			soc_pcm_codec_params_fixup(&codec_params,
 						   codec_dai->rx_mask);
 
@@ -1213,6 +1226,7 @@ static int dpcm_be_connect(struct snd_soc_pcm_runtime *fe,
 		struct snd_soc_pcm_runtime *be, int stream)
 {
 	struct snd_soc_dpcm *dpcm;
+	unsigned long flags;
 
 	/* only add new dpcms */
 	for_each_dpcm_be(fe, stream, dpcm) {
@@ -1228,8 +1242,10 @@ static int dpcm_be_connect(struct snd_soc_pcm_runtime *fe,
 	dpcm->fe = fe;
 	be->dpcm[stream].runtime = fe->dpcm[stream].runtime;
 	dpcm->state = SND_SOC_DPCM_LINK_STATE_NEW;
+	spin_lock_irqsave(&fe->card->dpcm_lock, flags);
 	list_add(&dpcm->list_be, &fe->dpcm[stream].be_clients);
 	list_add(&dpcm->list_fe, &be->dpcm[stream].fe_clients);
+	spin_unlock_irqrestore(&fe->card->dpcm_lock, flags);
 
 	dev_dbg(fe->dev, "connected new DPCM %s path %s %s %s\n",
 			stream ? "capture" : "playback",  fe->dai_link->name,
@@ -1275,6 +1291,7 @@ static void dpcm_be_reparent(struct snd_soc_pcm_runtime *fe,
 void dpcm_be_disconnect(struct snd_soc_pcm_runtime *fe, int stream)
 {
 	struct snd_soc_dpcm *dpcm, *d;
+	unsigned long flags;
 
 	for_each_dpcm_be_safe(fe, stream, dpcm, d) {
 		dev_dbg(fe->dev, "ASoC: BE %s disconnect check for %s\n",
@@ -1294,8 +1311,10 @@ void dpcm_be_disconnect(struct snd_soc_pcm_runtime *fe, int stream)
 #ifdef CONFIG_DEBUG_FS
 		debugfs_remove(dpcm->debugfs_state);
 #endif
+		spin_lock_irqsave(&fe->card->dpcm_lock, flags);
 		list_del(&dpcm->list_be);
 		list_del(&dpcm->list_fe);
+		spin_unlock_irqrestore(&fe->card->dpcm_lock, flags);
 		kfree(dpcm);
 	}
 }
@@ -1547,10 +1566,13 @@ int dpcm_process_paths(struct snd_soc_pcm_runtime *fe,
 void dpcm_clear_pending_state(struct snd_soc_pcm_runtime *fe, int stream)
 {
 	struct snd_soc_dpcm *dpcm;
+	unsigned long flags;
 
+	spin_lock_irqsave(&fe->card->dpcm_lock, flags);
 	for_each_dpcm_be(fe, stream, dpcm)
 		dpcm->be->dpcm[stream].runtime_update =
 						SND_SOC_DPCM_UPDATE_NO;
+	spin_unlock_irqrestore(&fe->card->dpcm_lock, flags);
 }
 
 static void dpcm_be_dai_startup_unwind(struct snd_soc_pcm_runtime *fe,
@@ -1899,10 +1921,15 @@ static int dpcm_apply_symmetry(struct snd_pcm_substream *fe_substream,
 		struct snd_soc_pcm_runtime *be = dpcm->be;
 		struct snd_pcm_substream *be_substream =
 			snd_soc_dpcm_get_substream(be, stream);
-		struct snd_soc_pcm_runtime *rtd = be_substream->private_data;
+		struct snd_soc_pcm_runtime *rtd;
 		struct snd_soc_dai *codec_dai;
 		int i;
 
+		/* A backend may not have the requested substream */
+		if (!be_substream)
+			continue;
+
+		rtd = be_substream->private_data;
 		if (rtd->dai_link->be_hw_params_fixup)
 			continue;
 
@@ -2571,6 +2598,7 @@ static int dpcm_run_update_startup(struct snd_soc_pcm_runtime *fe, int stream)
 	struct snd_soc_dpcm *dpcm;
 	enum snd_soc_dpcm_trigger trigger = fe->dai_link->trigger[stream];
 	int ret;
+	unsigned long flags;
 
 	dev_dbg(fe->dev, "ASoC: runtime %s open on FE %s\n",
 			stream ? "capture" : "playback", fe->dai_link->name);
@@ -2640,11 +2668,13 @@ close:
 	dpcm_be_dai_shutdown(fe, stream);
 disconnect:
 	/* disconnect any non started BEs */
+	spin_lock_irqsave(&fe->card->dpcm_lock, flags);
 	for_each_dpcm_be(fe, stream, dpcm) {
 		struct snd_soc_pcm_runtime *be = dpcm->be;
 		if (be->dpcm[stream].state != SND_SOC_DPCM_STATE_START)
 				dpcm->state = SND_SOC_DPCM_LINK_STATE_FREE;
 	}
+	spin_unlock_irqrestore(&fe->card->dpcm_lock, flags);
 
 	return ret;
 }
@@ -3221,7 +3251,10 @@ int snd_soc_dpcm_can_be_free_stop(struct snd_soc_pcm_runtime *fe,
 {
 	struct snd_soc_dpcm *dpcm;
 	int state;
+	int ret = 1;
+	unsigned long flags;
 
+	spin_lock_irqsave(&fe->card->dpcm_lock, flags);
 	for_each_dpcm_fe(be, stream, dpcm) {
 
 		if (dpcm->fe == fe)
@@ -3230,12 +3263,15 @@ int snd_soc_dpcm_can_be_free_stop(struct snd_soc_pcm_runtime *fe,
 		state = dpcm->fe->dpcm[stream].state;
 		if (state == SND_SOC_DPCM_STATE_START ||
 			state == SND_SOC_DPCM_STATE_PAUSED ||
-			state == SND_SOC_DPCM_STATE_SUSPEND)
-			return 0;
+			state == SND_SOC_DPCM_STATE_SUSPEND) {
+			ret = 0;
+			break;
+		}
 	}
+	spin_unlock_irqrestore(&fe->card->dpcm_lock, flags);
 
 	/* it's safe to free/stop this BE DAI */
-	return 1;
+	return ret;
 }
 EXPORT_SYMBOL_GPL(snd_soc_dpcm_can_be_free_stop);
 
@@ -3248,7 +3284,10 @@ int snd_soc_dpcm_can_be_params(struct snd_soc_pcm_runtime *fe,
 {
 	struct snd_soc_dpcm *dpcm;
 	int state;
+	int ret = 1;
+	unsigned long flags;
 
+	spin_lock_irqsave(&fe->card->dpcm_lock, flags);
 	for_each_dpcm_fe(be, stream, dpcm) {
 
 		if (dpcm->fe == fe)
@@ -3258,12 +3297,15 @@ int snd_soc_dpcm_can_be_params(struct snd_soc_pcm_runtime *fe,
 		if (state == SND_SOC_DPCM_STATE_START ||
 			state == SND_SOC_DPCM_STATE_PAUSED ||
 			state == SND_SOC_DPCM_STATE_SUSPEND ||
-			state == SND_SOC_DPCM_STATE_PREPARE)
-			return 0;
+			state == SND_SOC_DPCM_STATE_PREPARE) {
+			ret = 0;
+			break;
+		}
 	}
+	spin_unlock_irqrestore(&fe->card->dpcm_lock, flags);
 
 	/* it's safe to change hw_params */
-	return 1;
+	return ret;
 }
 EXPORT_SYMBOL_GPL(snd_soc_dpcm_can_be_params);
 
@@ -3302,6 +3344,7 @@ static ssize_t dpcm_show_state(struct snd_soc_pcm_runtime *fe,
 	struct snd_pcm_hw_params *params = &fe->dpcm[stream].hw_params;
 	struct snd_soc_dpcm *dpcm;
 	ssize_t offset = 0;
+	unsigned long flags;
 
 	/* FE state */
 	offset += snprintf(buf + offset, size - offset,
@@ -3329,6 +3372,7 @@ static ssize_t dpcm_show_state(struct snd_soc_pcm_runtime *fe,
 		goto out;
 	}
 
+	spin_lock_irqsave(&fe->card->dpcm_lock, flags);
 	for_each_dpcm_be(fe, stream, dpcm) {
 		struct snd_soc_pcm_runtime *be = dpcm->be;
 		params = &dpcm->hw_params;
@@ -3349,7 +3393,7 @@ static ssize_t dpcm_show_state(struct snd_soc_pcm_runtime *fe,
 				params_channels(params),
 				params_rate(params));
 	}
-
+	spin_unlock_irqrestore(&fe->card->dpcm_lock, flags);
 out:
 	return offset;
 }
diff --git a/sound/soc/soc-topology.c b/sound/soc/soc-topology.c
index 25fca7055464..96852d250619 100644
--- a/sound/soc/soc-topology.c
+++ b/sound/soc/soc-topology.c
@@ -482,10 +482,11 @@ static void remove_widget(struct snd_soc_component *comp,
 
 			snd_ctl_remove(card, kcontrol);
 
-			kfree(dobj->control.dvalues);
+			/* free enum kcontrol's dvalues and dtexts */
+			kfree(se->dobj.control.dvalues);
 			for (j = 0; j < se->items; j++)
-				kfree(dobj->control.dtexts[j]);
-			kfree(dobj->control.dtexts);
+				kfree(se->dobj.control.dtexts[j]);
+			kfree(se->dobj.control.dtexts);
 
 			kfree(se);
 			kfree(w->kcontrol_news[i].name);
diff --git a/sound/soc/stm/stm32_adfsdm.c b/sound/soc/stm/stm32_adfsdm.c
index 47901983a6ff..78bed9734713 100644
--- a/sound/soc/stm/stm32_adfsdm.c
+++ b/sound/soc/stm/stm32_adfsdm.c
@@ -9,6 +9,7 @@
 
 #include <linux/clk.h>
 #include <linux/module.h>
+#include <linux/mutex.h>
 #include <linux/platform_device.h>
 #include <linux/slab.h>
 
@@ -37,6 +38,8 @@ struct stm32_adfsdm_priv {
 	/* PCM buffer */
 	unsigned char *pcm_buff;
 	unsigned int pos;
+
+	struct mutex lock; /* protect against race condition on iio state */
 };
 
 static const struct snd_pcm_hardware stm32_adfsdm_pcm_hw = {
@@ -62,10 +65,12 @@ static void stm32_adfsdm_shutdown(struct snd_pcm_substream *substream,
 {
 	struct stm32_adfsdm_priv *priv = snd_soc_dai_get_drvdata(dai);
 
+	mutex_lock(&priv->lock);
 	if (priv->iio_active) {
 		iio_channel_stop_all_cb(priv->iio_cb);
 		priv->iio_active = false;
 	}
+	mutex_unlock(&priv->lock);
 }
 
 static int stm32_adfsdm_dai_prepare(struct snd_pcm_substream *substream,
@@ -74,13 +79,19 @@ static int stm32_adfsdm_dai_prepare(struct snd_pcm_substream *substream,
 	struct stm32_adfsdm_priv *priv = snd_soc_dai_get_drvdata(dai);
 	int ret;
 
+	mutex_lock(&priv->lock);
+	if (priv->iio_active) {
+		iio_channel_stop_all_cb(priv->iio_cb);
+		priv->iio_active = false;
+	}
+
 	ret = iio_write_channel_attribute(priv->iio_ch,
 					  substream->runtime->rate, 0,
 					  IIO_CHAN_INFO_SAMP_FREQ);
 	if (ret < 0) {
 		dev_err(dai->dev, "%s: Failed to set %d sampling rate\n",
 			__func__, substream->runtime->rate);
-		return ret;
+		goto out;
 	}
 
 	if (!priv->iio_active) {
@@ -92,6 +103,9 @@ static int stm32_adfsdm_dai_prepare(struct snd_pcm_substream *substream,
 				__func__, ret);
 	}
 
+out:
+	mutex_unlock(&priv->lock);
+
 	return ret;
 }
 
@@ -291,6 +305,7 @@ MODULE_DEVICE_TABLE(of, stm32_adfsdm_of_match);
 static int stm32_adfsdm_probe(struct platform_device *pdev)
 {
 	struct stm32_adfsdm_priv *priv;
+	struct snd_soc_component *component;
 	int ret;
 
 	priv = devm_kzalloc(&pdev->dev, sizeof(*priv), GFP_KERNEL);
@@ -299,6 +314,7 @@ static int stm32_adfsdm_probe(struct platform_device *pdev)
 
 	priv->dev = &pdev->dev;
 	priv->dai_drv = stm32_adfsdm_dai;
+	mutex_init(&priv->lock);
 
 	dev_set_drvdata(&pdev->dev, priv);
 
@@ -317,9 +333,15 @@ static int stm32_adfsdm_probe(struct platform_device *pdev)
 	if (IS_ERR(priv->iio_cb))
 		return PTR_ERR(priv->iio_cb);
 
-	ret = devm_snd_soc_register_component(&pdev->dev,
-					      &stm32_adfsdm_soc_platform,
-					      NULL, 0);
+	component = devm_kzalloc(&pdev->dev, sizeof(*component), GFP_KERNEL);
+	if (!component)
+		return -ENOMEM;
+#ifdef CONFIG_DEBUG_FS
+	component->debugfs_prefix = "pcm";
+#endif
+
+	ret = snd_soc_add_component(&pdev->dev, component,
+				    &stm32_adfsdm_soc_platform, NULL, 0);
 	if (ret < 0)
 		dev_err(&pdev->dev, "%s: Failed to register PCM platform\n",
 			__func__);
@@ -327,12 +349,20 @@ static int stm32_adfsdm_probe(struct platform_device *pdev)
 	return ret;
 }
 
+static int stm32_adfsdm_remove(struct platform_device *pdev)
+{
+	snd_soc_unregister_component(&pdev->dev);
+
+	return 0;
+}
+
 static struct platform_driver stm32_adfsdm_driver = {
 	.driver = {
 		   .name = STM32_ADFSDM_DRV_NAME,
 		   .of_match_table = stm32_adfsdm_of_match,
 		   },
 	.probe = stm32_adfsdm_probe,
+	.remove = stm32_adfsdm_remove,
 };
 
 module_platform_driver(stm32_adfsdm_driver);
diff --git a/sound/soc/stm/stm32_i2s.c b/sound/soc/stm/stm32_i2s.c
index 47c334de6b09..8968458eec62 100644
--- a/sound/soc/stm/stm32_i2s.c
+++ b/sound/soc/stm/stm32_i2s.c
@@ -281,7 +281,6 @@ static bool stm32_i2s_readable_reg(struct device *dev, unsigned int reg)
 	case STM32_I2S_CFG2_REG:
 	case STM32_I2S_IER_REG:
 	case STM32_I2S_SR_REG:
-	case STM32_I2S_TXDR_REG:
 	case STM32_I2S_RXDR_REG:
 	case STM32_I2S_CGFR_REG:
 		return true;
@@ -293,7 +292,7 @@ static bool stm32_i2s_readable_reg(struct device *dev, unsigned int reg)
 static bool stm32_i2s_volatile_reg(struct device *dev, unsigned int reg)
 {
 	switch (reg) {
-	case STM32_I2S_TXDR_REG:
+	case STM32_I2S_SR_REG:
 	case STM32_I2S_RXDR_REG:
 		return true;
 	default:
diff --git a/sound/soc/stm/stm32_sai.c b/sound/soc/stm/stm32_sai.c
index 14c9591aae42..d68d62f12df5 100644
--- a/sound/soc/stm/stm32_sai.c
+++ b/sound/soc/stm/stm32_sai.c
@@ -105,6 +105,7 @@ static int stm32_sai_set_sync(struct stm32_sai_data *sai_client,
 	if (!pdev) {
 		dev_err(&sai_client->pdev->dev,
 			"Device not found for node %pOFn\n", np_provider);
+		of_node_put(np_provider);
 		return -ENODEV;
 	}
 
@@ -113,19 +114,20 @@ static int stm32_sai_set_sync(struct stm32_sai_data *sai_client,
 		dev_err(&sai_client->pdev->dev,
 			"SAI sync provider data not found\n");
 		ret = -EINVAL;
-		goto out_put_dev;
+		goto error;
 	}
 
 	/* Configure sync client */
 	ret = stm32_sai_sync_conf_client(sai_client, synci);
 	if (ret < 0)
-		goto out_put_dev;
+		goto error;
 
 	/* Configure sync provider */
 	ret = stm32_sai_sync_conf_provider(sai_provider, synco);
 
-out_put_dev:
+error:
 	put_device(&pdev->dev);
+	of_node_put(np_provider);
 	return ret;
 }
 
diff --git a/sound/soc/stm/stm32_sai_sub.c b/sound/soc/stm/stm32_sai_sub.c
index f9297228c41c..d7045aa520de 100644
--- a/sound/soc/stm/stm32_sai_sub.c
+++ b/sound/soc/stm/stm32_sai_sub.c
@@ -70,6 +70,7 @@
 #define SAI_IEC60958_STATUS_BYTES	24
 
 #define SAI_MCLK_NAME_LEN		32
+#define SAI_RATE_11K			11025
 
 /**
  * struct stm32_sai_sub_data - private data of SAI sub block (block A or B)
@@ -100,8 +101,9 @@
  * @slot_mask: rx or tx active slots mask. set at init or at runtime
  * @data_size: PCM data width. corresponds to PCM substream width.
  * @spdif_frm_cnt: S/PDIF playback frame counter
- * @snd_aes_iec958: iec958 data
+ * @iec958: iec958 data
  * @ctrl_lock: control lock
+ * @irq_lock: prevent race condition with IRQ
  */
 struct stm32_sai_sub_data {
 	struct platform_device *pdev;
@@ -133,6 +135,7 @@ struct stm32_sai_sub_data {
 	unsigned int spdif_frm_cnt;
 	struct snd_aes_iec958 iec958;
 	struct mutex ctrl_lock; /* protect resources accessed by controls */
+	spinlock_t irq_lock; /* used to prevent race condition with IRQ */
 };
 
 enum stm32_sai_fifo_th {
@@ -307,6 +310,25 @@ static int stm32_sai_set_clk_div(struct stm32_sai_sub_data *sai,
 	return ret;
 }
 
+static int stm32_sai_set_parent_clock(struct stm32_sai_sub_data *sai,
+				      unsigned int rate)
+{
+	struct platform_device *pdev = sai->pdev;
+	struct clk *parent_clk = sai->pdata->clk_x8k;
+	int ret;
+
+	if (!(rate % SAI_RATE_11K))
+		parent_clk = sai->pdata->clk_x11k;
+
+	ret = clk_set_parent(sai->sai_ck, parent_clk);
+	if (ret)
+		dev_err(&pdev->dev, " Error %d setting sai_ck parent clock. %s",
+			ret, ret == -EBUSY ?
+			"Active stream rates conflict\n" : "\n");
+
+	return ret;
+}
+
 static long stm32_sai_mclk_round_rate(struct clk_hw *hw, unsigned long rate,
 				      unsigned long *prate)
 {
@@ -474,8 +496,10 @@ static irqreturn_t stm32_sai_isr(int irq, void *devid)
 		status = SNDRV_PCM_STATE_XRUN;
 	}
 
-	if (status != SNDRV_PCM_STATE_RUNNING)
+	spin_lock(&sai->irq_lock);
+	if (status != SNDRV_PCM_STATE_RUNNING && sai->substream)
 		snd_pcm_stop_xrun(sai->substream);
+	spin_unlock(&sai->irq_lock);
 
 	return IRQ_HANDLED;
 }
@@ -486,25 +510,29 @@ static int stm32_sai_set_sysclk(struct snd_soc_dai *cpu_dai,
 	struct stm32_sai_sub_data *sai = snd_soc_dai_get_drvdata(cpu_dai);
 	int ret;
 
-	if (dir == SND_SOC_CLOCK_OUT) {
+	if (dir == SND_SOC_CLOCK_OUT && sai->sai_mclk) {
 		ret = regmap_update_bits(sai->regmap, STM_SAI_CR1_REGX,
 					 SAI_XCR1_NODIV,
 					 (unsigned int)~SAI_XCR1_NODIV);
 		if (ret < 0)
 			return ret;
 
-		dev_dbg(cpu_dai->dev, "SAI MCLK frequency is %uHz\n", freq);
-		sai->mclk_rate = freq;
+		/* If master clock is used, set parent clock now */
+		ret = stm32_sai_set_parent_clock(sai, freq);
+		if (ret)
+			return ret;
 
-		if (sai->sai_mclk) {
-			ret = clk_set_rate_exclusive(sai->sai_mclk,
-						     sai->mclk_rate);
-			if (ret) {
-				dev_err(cpu_dai->dev,
-					"Could not set mclk rate\n");
-				return ret;
-			}
+		ret = clk_set_rate_exclusive(sai->sai_mclk, freq);
+		if (ret) {
+			dev_err(cpu_dai->dev,
+				ret == -EBUSY ?
+				"Active streams have incompatible rates" :
+				"Could not set mclk rate\n");
+			return ret;
 		}
+
+		dev_dbg(cpu_dai->dev, "SAI MCLK frequency is %uHz\n", freq);
+		sai->mclk_rate = freq;
 	}
 
 	return 0;
@@ -679,8 +707,19 @@ static int stm32_sai_startup(struct snd_pcm_substream *substream,
 {
 	struct stm32_sai_sub_data *sai = snd_soc_dai_get_drvdata(cpu_dai);
 	int imr, cr2, ret;
+	unsigned long flags;
 
+	spin_lock_irqsave(&sai->irq_lock, flags);
 	sai->substream = substream;
+	spin_unlock_irqrestore(&sai->irq_lock, flags);
+
+	if (STM_SAI_PROTOCOL_IS_SPDIF(sai)) {
+		snd_pcm_hw_constraint_mask64(substream->runtime,
+					     SNDRV_PCM_HW_PARAM_FORMAT,
+					     SNDRV_PCM_FMTBIT_S32_LE);
+		snd_pcm_hw_constraint_single(substream->runtime,
+					     SNDRV_PCM_HW_PARAM_CHANNELS, 2);
+	}
 
 	ret = clk_prepare_enable(sai->sai_ck);
 	if (ret < 0) {
@@ -898,14 +937,16 @@ static int stm32_sai_configure_clock(struct snd_soc_dai *cpu_dai,
 				     struct snd_pcm_hw_params *params)
 {
 	struct stm32_sai_sub_data *sai = snd_soc_dai_get_drvdata(cpu_dai);
-	int div = 0;
+	int div = 0, cr1 = 0;
 	int sai_clk_rate, mclk_ratio, den;
 	unsigned int rate = params_rate(params);
+	int ret;
 
-	if (!(rate % 11025))
-		clk_set_parent(sai->sai_ck, sai->pdata->clk_x11k);
-	else
-		clk_set_parent(sai->sai_ck, sai->pdata->clk_x8k);
+	if (!sai->sai_mclk) {
+		ret = stm32_sai_set_parent_clock(sai, rate);
+		if (ret)
+			return ret;
+	}
 	sai_clk_rate = clk_get_rate(sai->sai_ck);
 
 	if (STM_SAI_IS_F4(sai->pdata)) {
@@ -943,13 +984,19 @@ static int stm32_sai_configure_clock(struct snd_soc_dai *cpu_dai,
 		} else {
 			if (sai->mclk_rate) {
 				mclk_ratio = sai->mclk_rate / rate;
-				if ((mclk_ratio != 512) &&
-				    (mclk_ratio != 256)) {
+				if (mclk_ratio == 512) {
+					cr1 = SAI_XCR1_OSR;
+				} else if (mclk_ratio != 256) {
 					dev_err(cpu_dai->dev,
 						"Wrong mclk ratio %d\n",
 						mclk_ratio);
 					return -EINVAL;
 				}
+
+				regmap_update_bits(sai->regmap,
+						   STM_SAI_CR1_REGX,
+						   SAI_XCR1_OSR, cr1);
+
 				div = stm32_sai_get_clk_div(sai, sai_clk_rate,
 							    sai->mclk_rate);
 				if (div < 0)
@@ -1051,28 +1098,36 @@ static void stm32_sai_shutdown(struct snd_pcm_substream *substream,
 			       struct snd_soc_dai *cpu_dai)
 {
 	struct stm32_sai_sub_data *sai = snd_soc_dai_get_drvdata(cpu_dai);
+	unsigned long flags;
 
 	regmap_update_bits(sai->regmap, STM_SAI_IMR_REGX, SAI_XIMR_MASK, 0);
 
 	regmap_update_bits(sai->regmap, STM_SAI_CR1_REGX, SAI_XCR1_NODIV,
 			   SAI_XCR1_NODIV);
 
-	clk_disable_unprepare(sai->sai_ck);
+	/* Release mclk rate only if rate was actually set */
+	if (sai->mclk_rate) {
+		clk_rate_exclusive_put(sai->sai_mclk);
+		sai->mclk_rate = 0;
+	}
 
-	clk_rate_exclusive_put(sai->sai_mclk);
+	clk_disable_unprepare(sai->sai_ck);
 
+	spin_lock_irqsave(&sai->irq_lock, flags);
 	sai->substream = NULL;
+	spin_unlock_irqrestore(&sai->irq_lock, flags);
 }
 
 static int stm32_sai_pcm_new(struct snd_soc_pcm_runtime *rtd,
 			     struct snd_soc_dai *cpu_dai)
 {
 	struct stm32_sai_sub_data *sai = dev_get_drvdata(cpu_dai->dev);
+	struct snd_kcontrol_new knew = iec958_ctls;
 
 	if (STM_SAI_PROTOCOL_IS_SPDIF(sai)) {
 		dev_dbg(&sai->pdev->dev, "%s: register iec controls", __func__);
-		return snd_ctl_add(rtd->pcm->card,
-				   snd_ctl_new1(&iec958_ctls, sai));
+		knew.device = rtd->pcm->device;
+		return snd_ctl_add(rtd->pcm->card, snd_ctl_new1(&knew, sai));
 	}
 
 	return 0;
@@ -1081,7 +1136,7 @@ static int stm32_sai_pcm_new(struct snd_soc_pcm_runtime *rtd,
 static int stm32_sai_dai_probe(struct snd_soc_dai *cpu_dai)
 {
 	struct stm32_sai_sub_data *sai = dev_get_drvdata(cpu_dai->dev);
-	int cr1 = 0, cr1_mask;
+	int cr1 = 0, cr1_mask, ret;
 
 	sai->cpu_dai = cpu_dai;
 
@@ -1111,8 +1166,10 @@ static int stm32_sai_dai_probe(struct snd_soc_dai *cpu_dai)
 	/* Configure synchronization */
 	if (sai->sync == SAI_SYNC_EXTERNAL) {
 		/* Configure synchro client and provider */
-		sai->pdata->set_sync(sai->pdata, sai->np_sync_provider,
-				     sai->synco, sai->synci);
+		ret = sai->pdata->set_sync(sai->pdata, sai->np_sync_provider,
+					   sai->synco, sai->synci);
+		if (ret)
+			return ret;
 	}
 
 	cr1_mask |= SAI_XCR1_SYNCEN_MASK;
@@ -1392,7 +1449,6 @@ static int stm32_sai_sub_dais_init(struct platform_device *pdev,
 	if (!sai->cpu_dai_drv)
 		return -ENOMEM;
 
-	sai->cpu_dai_drv->name = dev_name(&pdev->dev);
 	if (STM_SAI_IS_PLAYBACK(sai)) {
 		memcpy(sai->cpu_dai_drv, &stm32_sai_playback_dai,
 		       sizeof(stm32_sai_playback_dai));
@@ -1402,6 +1458,7 @@ static int stm32_sai_sub_dais_init(struct platform_device *pdev,
 		       sizeof(stm32_sai_capture_dai));
 		sai->cpu_dai_drv->capture.stream_name = sai->cpu_dai_drv->name;
 	}
+	sai->cpu_dai_drv->name = dev_name(&pdev->dev);
 
 	return 0;
 }
@@ -1424,6 +1481,7 @@ static int stm32_sai_sub_probe(struct platform_device *pdev)
 
 	sai->pdev = pdev;
 	mutex_init(&sai->ctrl_lock);
+	spin_lock_init(&sai->irq_lock);
 	platform_set_drvdata(pdev, sai);
 
 	sai->pdata = dev_get_drvdata(pdev->dev.parent);
diff --git a/sound/soc/txx9/txx9aclc-ac97.c b/sound/soc/txx9/txx9aclc-ac97.c
index 1cfca698ae4b..b0fa285c7ba2 100644
--- a/sound/soc/txx9/txx9aclc-ac97.c
+++ b/sound/soc/txx9/txx9aclc-ac97.c
@@ -102,7 +102,6 @@ static void txx9aclc_ac97_cold_reset(struct snd_ac97 *ac97)
 	u32 ready = ACINT_CODECRDY(ac97->num) | ACINT_REGACCRDY;
 
 	__raw_writel(ACCTL_ENLINK, base + ACCTLDIS);
-	mmiowb();
 	udelay(1);
 	__raw_writel(ACCTL_ENLINK, base + ACCTLEN);
 	/* wait for primary codec ready status */
diff --git a/sound/usb/line6/driver.c b/sound/usb/line6/driver.c
index 7afe8fae4939..b61f65bed4e4 100644
--- a/sound/usb/line6/driver.c
+++ b/sound/usb/line6/driver.c
@@ -351,12 +351,16 @@ int line6_read_data(struct usb_line6 *line6, unsigned address, void *data,
 {
 	struct usb_device *usbdev = line6->usbdev;
 	int ret;
-	unsigned char len;
+	unsigned char *len;
 	unsigned count;
 
 	if (address > 0xffff || datalen > 0xff)
 		return -EINVAL;
 
+	len = kmalloc(sizeof(*len), GFP_KERNEL);
+	if (!len)
+		return -ENOMEM;
+
 	/* query the serial number: */
 	ret = usb_control_msg(usbdev, usb_sndctrlpipe(usbdev, 0), 0x67,
 			      USB_TYPE_VENDOR | USB_RECIP_DEVICE | USB_DIR_OUT,
@@ -365,7 +369,7 @@ int line6_read_data(struct usb_line6 *line6, unsigned address, void *data,
 
 	if (ret < 0) {
 		dev_err(line6->ifcdev, "read request failed (error %d)\n", ret);
-		return ret;
+		goto exit;
 	}
 
 	/* Wait for data length. We'll get 0xff until length arrives. */
@@ -375,28 +379,29 @@ int line6_read_data(struct usb_line6 *line6, unsigned address, void *data,
 		ret = usb_control_msg(usbdev, usb_rcvctrlpipe(usbdev, 0), 0x67,
 				      USB_TYPE_VENDOR | USB_RECIP_DEVICE |
 				      USB_DIR_IN,
-				      0x0012, 0x0000, &len, 1,
+				      0x0012, 0x0000, len, 1,
 				      LINE6_TIMEOUT * HZ);
 		if (ret < 0) {
 			dev_err(line6->ifcdev,
 				"receive length failed (error %d)\n", ret);
-			return ret;
+			goto exit;
 		}
 
-		if (len != 0xff)
+		if (*len != 0xff)
 			break;
 	}
 
-	if (len == 0xff) {
+	ret = -EIO;
+	if (*len == 0xff) {
 		dev_err(line6->ifcdev, "read failed after %d retries\n",
 			count);
-		return -EIO;
-	} else if (len != datalen) {
+		goto exit;
+	} else if (*len != datalen) {
 		/* should be equal or something went wrong */
 		dev_err(line6->ifcdev,
 			"length mismatch (expected %d, got %d)\n",
-			(int)datalen, (int)len);
-		return -EIO;
+			(int)datalen, (int)*len);
+		goto exit;
 	}
 
 	/* receive the result: */
@@ -405,12 +410,12 @@ int line6_read_data(struct usb_line6 *line6, unsigned address, void *data,
 			      0x0013, 0x0000, data, datalen,
 			      LINE6_TIMEOUT * HZ);
 
-	if (ret < 0) {
+	if (ret < 0)
 		dev_err(line6->ifcdev, "read failed (error %d)\n", ret);
-		return ret;
-	}
 
-	return 0;
+exit:
+	kfree(len);
+	return ret;
 }
 EXPORT_SYMBOL_GPL(line6_read_data);
 
@@ -422,12 +427,16 @@ int line6_write_data(struct usb_line6 *line6, unsigned address, void *data,
 {
 	struct usb_device *usbdev = line6->usbdev;
 	int ret;
-	unsigned char status;
+	unsigned char *status;
 	int count;
 
 	if (address > 0xffff || datalen > 0xffff)
 		return -EINVAL;
 
+	status = kmalloc(sizeof(*status), GFP_KERNEL);
+	if (!status)
+		return -ENOMEM;
+
 	ret = usb_control_msg(usbdev, usb_sndctrlpipe(usbdev, 0), 0x67,
 			      USB_TYPE_VENDOR | USB_RECIP_DEVICE | USB_DIR_OUT,
 			      0x0022, address, data, datalen,
@@ -436,7 +445,7 @@ int line6_write_data(struct usb_line6 *line6, unsigned address, void *data,
 	if (ret < 0) {
 		dev_err(line6->ifcdev,
 			"write request failed (error %d)\n", ret);
-		return ret;
+		goto exit;
 	}
 
 	for (count = 0; count < LINE6_READ_WRITE_MAX_RETRIES; count++) {
@@ -447,28 +456,29 @@ int line6_write_data(struct usb_line6 *line6, unsigned address, void *data,
 				      USB_TYPE_VENDOR | USB_RECIP_DEVICE |
 				      USB_DIR_IN,
 				      0x0012, 0x0000,
-				      &status, 1, LINE6_TIMEOUT * HZ);
+				      status, 1, LINE6_TIMEOUT * HZ);
 
 		if (ret < 0) {
 			dev_err(line6->ifcdev,
 				"receiving status failed (error %d)\n", ret);
-			return ret;
+			goto exit;
 		}
 
-		if (status != 0xff)
+		if (*status != 0xff)
 			break;
 	}
 
-	if (status == 0xff) {
+	if (*status == 0xff) {
 		dev_err(line6->ifcdev, "write failed after %d retries\n",
 			count);
-		return -EIO;
-	} else if (status != 0) {
+		ret = -EIO;
+	} else if (*status != 0) {
 		dev_err(line6->ifcdev, "write failed (error %d)\n", ret);
-		return -EIO;
+		ret = -EIO;
 	}
-
-	return 0;
+exit:
+	kfree(status);
+	return ret;
 }
 EXPORT_SYMBOL_GPL(line6_write_data);
 
diff --git a/sound/usb/line6/podhd.c b/sound/usb/line6/podhd.c
index 36ed9c85c0eb..5f3c87264e66 100644
--- a/sound/usb/line6/podhd.c
+++ b/sound/usb/line6/podhd.c
@@ -225,28 +225,32 @@ static void podhd_startup_start_workqueue(struct timer_list *t)
 static int podhd_dev_start(struct usb_line6_podhd *pod)
 {
 	int ret;
-	u8 init_bytes[8];
+	u8 *init_bytes;
 	int i;
 	struct usb_device *usbdev = pod->line6.usbdev;
 
+	init_bytes = kmalloc(8, GFP_KERNEL);
+	if (!init_bytes)
+		return -ENOMEM;
+
 	ret = usb_control_msg(usbdev, usb_sndctrlpipe(usbdev, 0),
 					0x67, USB_TYPE_VENDOR | USB_RECIP_DEVICE | USB_DIR_OUT,
 					0x11, 0,
 					NULL, 0, LINE6_TIMEOUT * HZ);
 	if (ret < 0) {
 		dev_err(pod->line6.ifcdev, "read request failed (error %d)\n", ret);
-		return ret;
+		goto exit;
 	}
 
 	/* NOTE: looks like some kind of ping message */
 	ret = usb_control_msg(usbdev, usb_rcvctrlpipe(usbdev, 0), 0x67,
 					USB_TYPE_VENDOR | USB_RECIP_DEVICE | USB_DIR_IN,
 					0x11, 0x0,
-					&init_bytes, 3, LINE6_TIMEOUT * HZ);
+					init_bytes, 3, LINE6_TIMEOUT * HZ);
 	if (ret < 0) {
 		dev_err(pod->line6.ifcdev,
 			"receive length failed (error %d)\n", ret);
-		return ret;
+		goto exit;
 	}
 
 	pod->firmware_version =
@@ -255,7 +259,7 @@ static int podhd_dev_start(struct usb_line6_podhd *pod)
 	for (i = 0; i <= 16; i++) {
 		ret = line6_read_data(&pod->line6, 0xf000 + 0x08 * i, init_bytes, 8);
 		if (ret < 0)
-			return ret;
+			goto exit;
 	}
 
 	ret = usb_control_msg(usbdev, usb_sndctrlpipe(usbdev, 0),
@@ -263,10 +267,9 @@ static int podhd_dev_start(struct usb_line6_podhd *pod)
 					USB_TYPE_STANDARD | USB_RECIP_DEVICE | USB_DIR_OUT,
 					1, 0,
 					NULL, 0, LINE6_TIMEOUT * HZ);
-	if (ret < 0)
-		return ret;
-
-	return 0;
+exit:
+	kfree(init_bytes);
+	return ret;
 }
 
 static void podhd_startup_workqueue(struct work_struct *work)
diff --git a/sound/usb/line6/toneport.c b/sound/usb/line6/toneport.c
index f47ba94e6f4a..19bee725de00 100644
--- a/sound/usb/line6/toneport.c
+++ b/sound/usb/line6/toneport.c
@@ -365,16 +365,21 @@ static bool toneport_has_source_select(struct usb_line6_toneport *toneport)
 /*
 	Setup Toneport device.
 */
-static void toneport_setup(struct usb_line6_toneport *toneport)
+static int toneport_setup(struct usb_line6_toneport *toneport)
 {
-	u32 ticks;
+	u32 *ticks;
 	struct usb_line6 *line6 = &toneport->line6;
 	struct usb_device *usbdev = line6->usbdev;
 
+	ticks = kmalloc(sizeof(*ticks), GFP_KERNEL);
+	if (!ticks)
+		return -ENOMEM;
+
 	/* sync time on device with host: */
 	/* note: 32-bit timestamps overflow in year 2106 */
-	ticks = (u32)ktime_get_real_seconds();
-	line6_write_data(line6, 0x80c6, &ticks, 4);
+	*ticks = (u32)ktime_get_real_seconds();
+	line6_write_data(line6, 0x80c6, ticks, 4);
+	kfree(ticks);
 
 	/* enable device: */
 	toneport_send_cmd(usbdev, 0x0301, 0x0000);
@@ -389,6 +394,7 @@ static void toneport_setup(struct usb_line6_toneport *toneport)
 		toneport_update_led(toneport);
 
 	mod_timer(&toneport->timer, jiffies + TONEPORT_PCM_DELAY * HZ);
+	return 0;
 }
 
 /*
@@ -451,7 +457,9 @@ static int toneport_init(struct usb_line6 *line6,
 			return err;
 	}
 
-	toneport_setup(toneport);
+	err = toneport_setup(toneport);
+	if (err)
+		return err;
 
 	/* register audio system: */
 	return snd_card_register(line6->card);
@@ -463,7 +471,11 @@ static int toneport_init(struct usb_line6 *line6,
 */
 static int toneport_reset_resume(struct usb_interface *interface)
 {
-	toneport_setup(usb_get_intfdata(interface));
+	int err;
+
+	err = toneport_setup(usb_get_intfdata(interface));
+	if (err)
+		return err;
 	return line6_resume(interface);
 }
 #endif
diff --git a/sound/xen/xen_snd_front_alsa.c b/sound/xen/xen_snd_front_alsa.c
index a7f413cb704d..b14ab512c2ce 100644
--- a/sound/xen/xen_snd_front_alsa.c
+++ b/sound/xen/xen_snd_front_alsa.c
@@ -441,7 +441,7 @@ static int shbuf_setup_backstore(struct xen_snd_front_pcm_stream_info *stream,
 {
 	int i;
 
-	stream->buffer = alloc_pages_exact(stream->buffer_sz, GFP_KERNEL);
+	stream->buffer = alloc_pages_exact(buffer_sz, GFP_KERNEL);
 	if (!stream->buffer)
 		return -ENOMEM;
 
diff --git a/tools/arch/alpha/include/uapi/asm/mman.h b/tools/arch/alpha/include/uapi/asm/mman.h
index c317d3e6867a..ea6a255ae61f 100644
--- a/tools/arch/alpha/include/uapi/asm/mman.h
+++ b/tools/arch/alpha/include/uapi/asm/mman.h
@@ -27,8 +27,6 @@
 #define MAP_NONBLOCK	0x40000
 #define MAP_NORESERVE	0x10000
 #define MAP_POPULATE	0x20000
-#define MAP_PRIVATE	0x02
-#define MAP_SHARED	0x01
 #define MAP_STACK	0x80000
 #define PROT_EXEC	0x4
 #define PROT_GROWSDOWN	0x01000000
diff --git a/tools/arch/arc/include/uapi/asm/unistd.h b/tools/arch/arc/include/uapi/asm/unistd.h
new file mode 100644
index 000000000000..5eafa1115162
--- /dev/null
+++ b/tools/arch/arc/include/uapi/asm/unistd.h
@@ -0,0 +1,51 @@
+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
+/*
+ * Copyright (C) 2004, 2007-2010, 2011-2012 Synopsys, Inc. (www.synopsys.com)
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+/******** no-legacy-syscalls-ABI *******/
+
+/*
+ * Non-typical guard macro to enable inclusion twice in ARCH sys.c
+ * That is how the Generic syscall wrapper generator works
+ */
+#if !defined(_UAPI_ASM_ARC_UNISTD_H) || defined(__SYSCALL)
+#define _UAPI_ASM_ARC_UNISTD_H
+
+#define __ARCH_WANT_RENAMEAT
+#define __ARCH_WANT_STAT64
+#define __ARCH_WANT_SET_GET_RLIMIT
+#define __ARCH_WANT_SYS_EXECVE
+#define __ARCH_WANT_SYS_CLONE
+#define __ARCH_WANT_SYS_VFORK
+#define __ARCH_WANT_SYS_FORK
+#define __ARCH_WANT_TIME32_SYSCALLS
+
+#define sys_mmap2 sys_mmap_pgoff
+
+#include <asm-generic/unistd.h>
+
+#define NR_syscalls	__NR_syscalls
+
+/* Generic syscall (fs/filesystems.c - lost in asm-generic/unistd.h */
+#define __NR_sysfs		(__NR_arch_specific_syscall + 3)
+
+/* ARC specific syscall */
+#define __NR_cacheflush		(__NR_arch_specific_syscall + 0)
+#define __NR_arc_settls		(__NR_arch_specific_syscall + 1)
+#define __NR_arc_gettls		(__NR_arch_specific_syscall + 2)
+#define __NR_arc_usr_cmpxchg	(__NR_arch_specific_syscall + 4)
+
+__SYSCALL(__NR_cacheflush, sys_cacheflush)
+__SYSCALL(__NR_arc_settls, sys_arc_settls)
+__SYSCALL(__NR_arc_gettls, sys_arc_gettls)
+__SYSCALL(__NR_arc_usr_cmpxchg, sys_arc_usr_cmpxchg)
+__SYSCALL(__NR_sysfs, sys_sysfs)
+
+#undef __SYSCALL
+
+#endif
diff --git a/tools/arch/hexagon/include/uapi/asm/unistd.h b/tools/arch/hexagon/include/uapi/asm/unistd.h
new file mode 100644
index 000000000000..432c4db1b623
--- /dev/null
+++ b/tools/arch/hexagon/include/uapi/asm/unistd.h
@@ -0,0 +1,40 @@
+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
+/*
+ * Syscall support for Hexagon
+ *
+ * Copyright (c) 2010-2011, The Linux Foundation. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 and
+ * only version 2 as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA
+ * 02110-1301, USA.
+ */
+
+/*
+ *  The kernel pulls this unistd.h in three different ways:
+ *  1.  the "normal" way which gets all the __NR defines
+ *  2.  with __SYSCALL defined to produce function declarations
+ *  3.  with __SYSCALL defined to produce syscall table initialization
+ *  See also:  syscalltab.c
+ */
+
+#define sys_mmap2 sys_mmap_pgoff
+#define __ARCH_WANT_RENAMEAT
+#define __ARCH_WANT_STAT64
+#define __ARCH_WANT_SET_GET_RLIMIT
+#define __ARCH_WANT_SYS_EXECVE
+#define __ARCH_WANT_SYS_CLONE
+#define __ARCH_WANT_SYS_VFORK
+#define __ARCH_WANT_SYS_FORK
+#define __ARCH_WANT_TIME32_SYSCALLS
+
+#include <asm-generic/unistd.h>
diff --git a/tools/arch/mips/include/uapi/asm/mman.h b/tools/arch/mips/include/uapi/asm/mman.h
index de2206883abc..c8acaa138d46 100644
--- a/tools/arch/mips/include/uapi/asm/mman.h
+++ b/tools/arch/mips/include/uapi/asm/mman.h
@@ -28,8 +28,6 @@
 #define MAP_NONBLOCK	0x20000
 #define MAP_NORESERVE	0x0400
 #define MAP_POPULATE	0x10000
-#define MAP_PRIVATE	0x002
-#define MAP_SHARED	0x001
 #define MAP_STACK	0x40000
 #define PROT_EXEC	0x04
 #define PROT_GROWSDOWN	0x01000000
diff --git a/tools/arch/parisc/include/uapi/asm/mman.h b/tools/arch/parisc/include/uapi/asm/mman.h
index 1bd78758bde9..f9fd1325f5bd 100644
--- a/tools/arch/parisc/include/uapi/asm/mman.h
+++ b/tools/arch/parisc/include/uapi/asm/mman.h
@@ -27,8 +27,6 @@
 #define MAP_NONBLOCK	0x20000
 #define MAP_NORESERVE	0x4000
 #define MAP_POPULATE	0x10000
-#define MAP_PRIVATE	0x02
-#define MAP_SHARED	0x01
 #define MAP_STACK	0x40000
 #define PROT_EXEC	0x4
 #define PROT_GROWSDOWN	0x01000000
diff --git a/tools/arch/powerpc/include/uapi/asm/kvm.h b/tools/arch/powerpc/include/uapi/asm/kvm.h
index 8c876c166ef2..26ca425f4c2c 100644
--- a/tools/arch/powerpc/include/uapi/asm/kvm.h
+++ b/tools/arch/powerpc/include/uapi/asm/kvm.h
@@ -463,10 +463,12 @@ struct kvm_ppc_cpu_char {
 #define KVM_PPC_CPU_CHAR_BR_HINT_HONOURED	(1ULL << 58)
 #define KVM_PPC_CPU_CHAR_MTTRIG_THR_RECONF	(1ULL << 57)
 #define KVM_PPC_CPU_CHAR_COUNT_CACHE_DIS	(1ULL << 56)
+#define KVM_PPC_CPU_CHAR_BCCTR_FLUSH_ASSIST	(1ull << 54)
 
 #define KVM_PPC_CPU_BEHAV_FAVOUR_SECURITY	(1ULL << 63)
 #define KVM_PPC_CPU_BEHAV_L1D_FLUSH_PR		(1ULL << 62)
 #define KVM_PPC_CPU_BEHAV_BNDS_CHK_SPEC_BAR	(1ULL << 61)
+#define KVM_PPC_CPU_BEHAV_FLUSH_COUNT_CACHE	(1ull << 58)
 
 /* Per-vcpu XICS interrupt controller state */
 #define KVM_REG_PPC_ICP_STATE	(KVM_REG_PPC | KVM_REG_SIZE_U64 | 0x8c)
diff --git a/tools/arch/riscv/include/uapi/asm/unistd.h b/tools/arch/riscv/include/uapi/asm/unistd.h
new file mode 100644
index 000000000000..0e2eeeb1fd27
--- /dev/null
+++ b/tools/arch/riscv/include/uapi/asm/unistd.h
@@ -0,0 +1,42 @@
+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
+/*
+ * Copyright (C) 2018 David Abdurachmanov <david.abdurachmanov@gmail.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program.  If not, see <http://www.gnu.org/licenses/>.
+ */
+
+#ifdef __LP64__
+#define __ARCH_WANT_NEW_STAT
+#define __ARCH_WANT_SET_GET_RLIMIT
+#endif /* __LP64__ */
+
+#include <asm-generic/unistd.h>
+
+/*
+ * Allows the instruction cache to be flushed from userspace.  Despite RISC-V
+ * having a direct 'fence.i' instruction available to userspace (which we
+ * can't trap!), that's not actually viable when running on Linux because the
+ * kernel might schedule a process on another hart.  There is no way for
+ * userspace to handle this without invoking the kernel (as it doesn't know the
+ * thread->hart mappings), so we've defined a RISC-V specific system call to
+ * flush the instruction cache.
+ *
+ * __NR_riscv_flush_icache is defined to flush the instruction cache over an
+ * address range, with the flush applying to either all threads or just the
+ * caller.  We don't currently do anything with the address range, that's just
+ * in there for forwards compatibility.
+ */
+#ifndef __NR_riscv_flush_icache
+#define __NR_riscv_flush_icache (__NR_arch_specific_syscall + 15)
+#endif
+__SYSCALL(__NR_riscv_flush_icache, sys_riscv_flush_icache)
diff --git a/tools/arch/x86/include/asm/cpufeatures.h b/tools/arch/x86/include/asm/cpufeatures.h
index 6d6122524711..981ff9479648 100644
--- a/tools/arch/x86/include/asm/cpufeatures.h
+++ b/tools/arch/x86/include/asm/cpufeatures.h
@@ -344,6 +344,7 @@
 /* Intel-defined CPU features, CPUID level 0x00000007:0 (EDX), word 18 */
 #define X86_FEATURE_AVX512_4VNNIW	(18*32+ 2) /* AVX-512 Neural Network Instructions */
 #define X86_FEATURE_AVX512_4FMAPS	(18*32+ 3) /* AVX-512 Multiply Accumulation Single precision */
+#define X86_FEATURE_TSX_FORCE_ABORT	(18*32+13) /* "" TSX_FORCE_ABORT */
 #define X86_FEATURE_PCONFIG		(18*32+18) /* Intel PCONFIG */
 #define X86_FEATURE_SPEC_CTRL		(18*32+26) /* "" Speculation Control (IBRS + IBPB) */
 #define X86_FEATURE_INTEL_STIBP		(18*32+27) /* "" Single Thread Indirect Branch Predictors */
diff --git a/tools/arch/x86/include/uapi/asm/vmx.h b/tools/arch/x86/include/uapi/asm/vmx.h
index f0b0c90dd398..d213ec5c3766 100644
--- a/tools/arch/x86/include/uapi/asm/vmx.h
+++ b/tools/arch/x86/include/uapi/asm/vmx.h
@@ -146,6 +146,7 @@
 
 #define VMX_ABORT_SAVE_GUEST_MSR_FAIL        1
 #define VMX_ABORT_LOAD_HOST_PDPTE_FAIL       2
+#define VMX_ABORT_VMCS_CORRUPTED             3
 #define VMX_ABORT_LOAD_HOST_MSR_FAIL         4
 
 #endif /* _UAPIVMX_H */
diff --git a/tools/arch/xtensa/include/uapi/asm/mman.h b/tools/arch/xtensa/include/uapi/asm/mman.h
index 34dde6f44dae..f2b08c990afc 100644
--- a/tools/arch/xtensa/include/uapi/asm/mman.h
+++ b/tools/arch/xtensa/include/uapi/asm/mman.h
@@ -27,8 +27,6 @@
 #define MAP_NONBLOCK	0x20000
 #define MAP_NORESERVE	0x0400
 #define MAP_POPULATE	0x10000
-#define MAP_PRIVATE	0x002
-#define MAP_SHARED	0x001
 #define MAP_STACK	0x40000
 #define PROT_EXEC	0x4
 #define PROT_GROWSDOWN	0x01000000
diff --git a/tools/bpf/bpftool/map.c b/tools/bpf/bpftool/map.c
index e0c650d91784..994a7e0d16fb 100644
--- a/tools/bpf/bpftool/map.c
+++ b/tools/bpf/bpftool/map.c
@@ -1151,6 +1151,9 @@ static int do_create(int argc, char **argv)
 				return -1;
 			}
 			NEXT_ARG();
+		} else {
+			p_err("unknown arg %s", *argv);
+			return -1;
 		}
 	}
 
diff --git a/tools/build/Makefile.feature b/tools/build/Makefile.feature
index 8d3864b061f3..361207387b1b 100644
--- a/tools/build/Makefile.feature
+++ b/tools/build/Makefile.feature
@@ -67,6 +67,7 @@ FEATURE_TESTS_BASIC :=                  \
         sdt				\
         setns				\
         libaio				\
+        libzstd				\
         disassembler-four-args
 
 # FEATURE_TESTS_BASIC + FEATURE_TESTS_EXTRA is the complete list
@@ -120,6 +121,7 @@ FEATURE_DISPLAY ?=              \
          get_cpuid              \
          bpf			\
          libaio			\
+         libzstd		\
          disassembler-four-args
 
 # Set FEATURE_CHECK_(C|LD)FLAGS-all for all FEATURE_TESTS features.
diff --git a/tools/build/feature/Makefile b/tools/build/feature/Makefile
index 7ceb4441b627..4b8244ee65ce 100644
--- a/tools/build/feature/Makefile
+++ b/tools/build/feature/Makefile
@@ -62,7 +62,8 @@ FILES=                                          \
          test-clang.bin				\
          test-llvm.bin				\
          test-llvm-version.bin			\
-         test-libaio.bin
+         test-libaio.bin			\
+         test-libzstd.bin
 
 FILES := $(addprefix $(OUTPUT),$(FILES))
 
@@ -301,6 +302,9 @@ $(OUTPUT)test-clang.bin:
 $(OUTPUT)test-libaio.bin:
 	$(BUILD) -lrt
 
+$(OUTPUT)test-libzstd.bin:
+	$(BUILD) -lzstd
+
 ###############################
 
 clean:
diff --git a/tools/build/feature/test-all.c b/tools/build/feature/test-all.c
index 7853e6d91090..a59c53705093 100644
--- a/tools/build/feature/test-all.c
+++ b/tools/build/feature/test-all.c
@@ -182,6 +182,10 @@
 # include "test-disassembler-four-args.c"
 #undef main
 
+#define main main_test_zstd
+# include "test-libzstd.c"
+#undef main
+
 int main(int argc, char *argv[])
 {
 	main_test_libpython();
@@ -224,6 +228,7 @@ int main(int argc, char *argv[])
 	main_test_libaio();
 	main_test_reallocarray();
 	main_test_disassembler_four_args();
+	main_test_libzstd();
 
 	return 0;
 }
diff --git a/tools/build/feature/test-libopencsd.c b/tools/build/feature/test-libopencsd.c
index d68eb4fb40cc..2b0e02c38870 100644
--- a/tools/build/feature/test-libopencsd.c
+++ b/tools/build/feature/test-libopencsd.c
@@ -4,9 +4,9 @@
 /*
  * Check OpenCSD library version is sufficient to provide required features
  */
-#define OCSD_MIN_VER ((0 << 16) | (10 << 8) | (0))
+#define OCSD_MIN_VER ((0 << 16) | (11 << 8) | (0))
 #if !defined(OCSD_VER_NUM) || (OCSD_VER_NUM < OCSD_MIN_VER)
-#error "OpenCSD >= 0.10.0 is required"
+#error "OpenCSD >= 0.11.0 is required"
 #endif
 
 int main(void)
diff --git a/tools/build/feature/test-libzstd.c b/tools/build/feature/test-libzstd.c
new file mode 100644
index 000000000000..55268c01b84d
--- /dev/null
+++ b/tools/build/feature/test-libzstd.c
@@ -0,0 +1,12 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <zstd.h>
+
+int main(void)
+{
+	ZSTD_CStream	*cstream;
+
+	cstream = ZSTD_createCStream();
+	ZSTD_freeCStream(cstream);
+
+	return 0;
+}
diff --git a/tools/include/uapi/asm-generic/mman-common-tools.h b/tools/include/uapi/asm-generic/mman-common-tools.h
new file mode 100644
index 000000000000..af7d0d3a3182
--- /dev/null
+++ b/tools/include/uapi/asm-generic/mman-common-tools.h
@@ -0,0 +1,23 @@
+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
+#ifndef __ASM_GENERIC_MMAN_COMMON_TOOLS_ONLY_H
+#define __ASM_GENERIC_MMAN_COMMON_TOOLS_ONLY_H
+
+#include <asm-generic/mman-common.h>
+
+/* We need this because we need to have tools/include/uapi/ included in the tools
+ * header search path to get access to stuff that is not yet in the system's
+ * copy of the files in that directory, but since this cset:
+ *
+ *     746c9398f5ac ("arch: move common mmap flags to linux/mman.h")
+ *
+ * We end up making sys/mman.h, that is in the system headers, to not find the
+ * MAP_SHARED and MAP_PRIVATE defines because they are not anymore in our copy
+ * of asm-generic/mman-common.h. So we define them here and include this header
+ * from each of the per arch mman.h headers.
+ */
+#ifndef MAP_SHARED
+#define MAP_SHARED	0x01		/* Share changes */
+#define MAP_PRIVATE	0x02		/* Changes are private */
+#define MAP_SHARED_VALIDATE 0x03	/* share + validate extension flags */
+#endif
+#endif // __ASM_GENERIC_MMAN_COMMON_TOOLS_ONLY_H
diff --git a/tools/include/uapi/asm-generic/mman-common.h b/tools/include/uapi/asm-generic/mman-common.h
index e7ee32861d51..abd238d0f7a4 100644
--- a/tools/include/uapi/asm-generic/mman-common.h
+++ b/tools/include/uapi/asm-generic/mman-common.h
@@ -15,9 +15,7 @@
 #define PROT_GROWSDOWN	0x01000000	/* mprotect flag: extend change to start of growsdown vma */
 #define PROT_GROWSUP	0x02000000	/* mprotect flag: extend change to end of growsup vma */
 
-#define MAP_SHARED	0x01		/* Share changes */
-#define MAP_PRIVATE	0x02		/* Changes are private */
-#define MAP_SHARED_VALIDATE 0x03	/* share + validate extension flags */
+/* 0x01 - 0x03 are defined in linux/mman.h */
 #define MAP_TYPE	0x0f		/* Mask for type of mapping */
 #define MAP_FIXED	0x10		/* Interpret addr exactly */
 #define MAP_ANONYMOUS	0x20		/* don't use a file */
diff --git a/tools/include/uapi/asm-generic/mman.h b/tools/include/uapi/asm-generic/mman.h
index 653687d9771b..36c197fc44a0 100644
--- a/tools/include/uapi/asm-generic/mman.h
+++ b/tools/include/uapi/asm-generic/mman.h
@@ -2,7 +2,7 @@
 #ifndef __ASM_GENERIC_MMAN_H
 #define __ASM_GENERIC_MMAN_H
 
-#include <asm-generic/mman-common.h>
+#include <asm-generic/mman-common-tools.h>
 
 #define MAP_GROWSDOWN	0x0100		/* stack-like segment */
 #define MAP_DENYWRITE	0x0800		/* ETXTBSY */
diff --git a/tools/include/uapi/asm-generic/unistd.h b/tools/include/uapi/asm-generic/unistd.h
index 12cdf611d217..dee7292e1df6 100644
--- a/tools/include/uapi/asm-generic/unistd.h
+++ b/tools/include/uapi/asm-generic/unistd.h
@@ -824,8 +824,17 @@ __SYSCALL(__NR_futex_time64, sys_futex)
 __SYSCALL(__NR_sched_rr_get_interval_time64, sys_sched_rr_get_interval)
 #endif
 
+#define __NR_pidfd_send_signal 424
+__SYSCALL(__NR_pidfd_send_signal, sys_pidfd_send_signal)
+#define __NR_io_uring_setup 425
+__SYSCALL(__NR_io_uring_setup, sys_io_uring_setup)
+#define __NR_io_uring_enter 426
+__SYSCALL(__NR_io_uring_enter, sys_io_uring_enter)
+#define __NR_io_uring_register 427
+__SYSCALL(__NR_io_uring_register, sys_io_uring_register)
+
 #undef __NR_syscalls
-#define __NR_syscalls 424
+#define __NR_syscalls 428
 
 /*
  * 32 bit systems traditionally used different
diff --git a/tools/include/uapi/drm/i915_drm.h b/tools/include/uapi/drm/i915_drm.h
index 298b2e197744..397810fa2d33 100644
--- a/tools/include/uapi/drm/i915_drm.h
+++ b/tools/include/uapi/drm/i915_drm.h
@@ -1486,9 +1486,73 @@ struct drm_i915_gem_context_param {
 #define   I915_CONTEXT_MAX_USER_PRIORITY	1023 /* inclusive */
 #define   I915_CONTEXT_DEFAULT_PRIORITY		0
 #define   I915_CONTEXT_MIN_USER_PRIORITY	-1023 /* inclusive */
+	/*
+	 * When using the following param, value should be a pointer to
+	 * drm_i915_gem_context_param_sseu.
+	 */
+#define I915_CONTEXT_PARAM_SSEU		0x7
 	__u64 value;
 };
 
+/**
+ * Context SSEU programming
+ *
+ * It may be necessary for either functional or performance reason to configure
+ * a context to run with a reduced number of SSEU (where SSEU stands for Slice/
+ * Sub-slice/EU).
+ *
+ * This is done by configuring SSEU configuration using the below
+ * @struct drm_i915_gem_context_param_sseu for every supported engine which
+ * userspace intends to use.
+ *
+ * Not all GPUs or engines support this functionality in which case an error
+ * code -ENODEV will be returned.
+ *
+ * Also, flexibility of possible SSEU configuration permutations varies between
+ * GPU generations and software imposed limitations. Requesting such a
+ * combination will return an error code of -EINVAL.
+ *
+ * NOTE: When perf/OA is active the context's SSEU configuration is ignored in
+ * favour of a single global setting.
+ */
+struct drm_i915_gem_context_param_sseu {
+	/*
+	 * Engine class & instance to be configured or queried.
+	 */
+	__u16 engine_class;
+	__u16 engine_instance;
+
+	/*
+	 * Unused for now. Must be cleared to zero.
+	 */
+	__u32 flags;
+
+	/*
+	 * Mask of slices to enable for the context. Valid values are a subset
+	 * of the bitmask value returned for I915_PARAM_SLICE_MASK.
+	 */
+	__u64 slice_mask;
+
+	/*
+	 * Mask of subslices to enable for the context. Valid values are a
+	 * subset of the bitmask value return by I915_PARAM_SUBSLICE_MASK.
+	 */
+	__u64 subslice_mask;
+
+	/*
+	 * Minimum/Maximum number of EUs to enable per subslice for the
+	 * context. min_eus_per_subslice must be inferior or equal to
+	 * max_eus_per_subslice.
+	 */
+	__u16 min_eus_per_subslice;
+	__u16 max_eus_per_subslice;
+
+	/*
+	 * Unused for now. Must be cleared to zero.
+	 */
+	__u32 rsvd;
+};
+
 enum drm_i915_oa_format {
 	I915_OA_FORMAT_A13 = 1,	    /* HSW only */
 	I915_OA_FORMAT_A29,	    /* HSW only */
diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h
index 3c38ac9a92a7..929c8e537a14 100644
--- a/tools/include/uapi/linux/bpf.h
+++ b/tools/include/uapi/linux/bpf.h
@@ -502,16 +502,6 @@ union bpf_attr {
  * 	Return
  * 		0 on success, or a negative error in case of failure.
  *
- * int bpf_map_push_elem(struct bpf_map *map, const void *value, u64 flags)
- * 	Description
- * 		Push an element *value* in *map*. *flags* is one of:
- *
- * 		**BPF_EXIST**
- * 		If the queue/stack is full, the oldest element is removed to
- * 		make room for this.
- * 	Return
- * 		0 on success, or a negative error in case of failure.
- *
  * int bpf_probe_read(void *dst, u32 size, const void *src)
  * 	Description
  * 		For tracing programs, safely attempt to read *size* bytes from
@@ -1435,14 +1425,14 @@ union bpf_attr {
  * u64 bpf_get_socket_cookie(struct bpf_sock_addr *ctx)
  * 	Description
  * 		Equivalent to bpf_get_socket_cookie() helper that accepts
- * 		*skb*, but gets socket from **struct bpf_sock_addr** contex.
+ * 		*skb*, but gets socket from **struct bpf_sock_addr** context.
  * 	Return
  * 		A 8-byte long non-decreasing number.
  *
  * u64 bpf_get_socket_cookie(struct bpf_sock_ops *ctx)
  * 	Description
  * 		Equivalent to bpf_get_socket_cookie() helper that accepts
- * 		*skb*, but gets socket from **struct bpf_sock_ops** contex.
+ * 		*skb*, but gets socket from **struct bpf_sock_ops** context.
  * 	Return
  * 		A 8-byte long non-decreasing number.
  *
@@ -2098,52 +2088,52 @@ union bpf_attr {
  *	Return
  * 		0 on success, or a negative error in case of failure.
  *
- * int bpf_rc_keydown(void *ctx, u32 protocol, u64 scancode, u32 toggle)
+ * int bpf_rc_repeat(void *ctx)
  *	Description
  *		This helper is used in programs implementing IR decoding, to
- *		report a successfully decoded key press with *scancode*,
- *		*toggle* value in the given *protocol*. The scancode will be
- *		translated to a keycode using the rc keymap, and reported as
- *		an input key down event. After a period a key up event is
- *		generated. This period can be extended by calling either
- *		**bpf_rc_keydown**\ () again with the same values, or calling
- *		**bpf_rc_repeat**\ ().
+ *		report a successfully decoded repeat key message. This delays
+ *		the generation of a key up event for previously generated
+ *		key down event.
  *
- *		Some protocols include a toggle bit, in case the button	was
- *		released and pressed again between consecutive scancodes.
+ *		Some IR protocols like NEC have a special IR message for
+ *		repeating last button, for when a button is held down.
  *
  *		The *ctx* should point to the lirc sample as passed into
  *		the program.
  *
- *		The *protocol* is the decoded protocol number (see
- *		**enum rc_proto** for some predefined values).
- *
  *		This helper is only available is the kernel was compiled with
  *		the **CONFIG_BPF_LIRC_MODE2** configuration option set to
  *		"**y**".
  *	Return
  *		0
  *
- * int bpf_rc_repeat(void *ctx)
+ * int bpf_rc_keydown(void *ctx, u32 protocol, u64 scancode, u32 toggle)
  *	Description
  *		This helper is used in programs implementing IR decoding, to
- *		report a successfully decoded repeat key message. This delays
- *		the generation of a key up event for previously generated
- *		key down event.
+ *		report a successfully decoded key press with *scancode*,
+ *		*toggle* value in the given *protocol*. The scancode will be
+ *		translated to a keycode using the rc keymap, and reported as
+ *		an input key down event. After a period a key up event is
+ *		generated. This period can be extended by calling either
+ *		**bpf_rc_keydown**\ () again with the same values, or calling
+ *		**bpf_rc_repeat**\ ().
  *
- *		Some IR protocols like NEC have a special IR message for
- *		repeating last button, for when a button is held down.
+ *		Some protocols include a toggle bit, in case the button	was
+ *		released and pressed again between consecutive scancodes.
  *
  *		The *ctx* should point to the lirc sample as passed into
  *		the program.
  *
+ *		The *protocol* is the decoded protocol number (see
+ *		**enum rc_proto** for some predefined values).
+ *
  *		This helper is only available is the kernel was compiled with
  *		the **CONFIG_BPF_LIRC_MODE2** configuration option set to
  *		"**y**".
  *	Return
  *		0
  *
- * uint64_t bpf_skb_cgroup_id(struct sk_buff *skb)
+ * u64 bpf_skb_cgroup_id(struct sk_buff *skb)
  * 	Description
  * 		Return the cgroup v2 id of the socket associated with the *skb*.
  * 		This is roughly similar to the **bpf_get_cgroup_classid**\ ()
@@ -2159,30 +2149,12 @@ union bpf_attr {
  * 	Return
  * 		The id is returned or 0 in case the id could not be retrieved.
  *
- * u64 bpf_skb_ancestor_cgroup_id(struct sk_buff *skb, int ancestor_level)
- *	Description
- *		Return id of cgroup v2 that is ancestor of cgroup associated
- *		with the *skb* at the *ancestor_level*.  The root cgroup is at
- *		*ancestor_level* zero and each step down the hierarchy
- *		increments the level. If *ancestor_level* == level of cgroup
- *		associated with *skb*, then return value will be same as that
- *		of **bpf_skb_cgroup_id**\ ().
- *
- *		The helper is useful to implement policies based on cgroups
- *		that are upper in hierarchy than immediate cgroup associated
- *		with *skb*.
- *
- *		The format of returned id and helper limitations are same as in
- *		**bpf_skb_cgroup_id**\ ().
- *	Return
- *		The id is returned or 0 in case the id could not be retrieved.
- *
  * u64 bpf_get_current_cgroup_id(void)
  * 	Return
  * 		A 64-bit integer containing the current cgroup id based
  * 		on the cgroup within which the current task is running.
  *
- * void* get_local_storage(void *map, u64 flags)
+ * void *bpf_get_local_storage(void *map, u64 flags)
  *	Description
  *		Get the pointer to the local storage area.
  *		The type and the size of the local storage is defined
@@ -2209,6 +2181,24 @@ union bpf_attr {
  *	Return
  *		0 on success, or a negative error in case of failure.
  *
+ * u64 bpf_skb_ancestor_cgroup_id(struct sk_buff *skb, int ancestor_level)
+ *	Description
+ *		Return id of cgroup v2 that is ancestor of cgroup associated
+ *		with the *skb* at the *ancestor_level*.  The root cgroup is at
+ *		*ancestor_level* zero and each step down the hierarchy
+ *		increments the level. If *ancestor_level* == level of cgroup
+ *		associated with *skb*, then return value will be same as that
+ *		of **bpf_skb_cgroup_id**\ ().
+ *
+ *		The helper is useful to implement policies based on cgroups
+ *		that are upper in hierarchy than immediate cgroup associated
+ *		with *skb*.
+ *
+ *		The format of returned id and helper limitations are same as in
+ *		**bpf_skb_cgroup_id**\ ().
+ *	Return
+ *		The id is returned or 0 in case the id could not be retrieved.
+ *
  * struct bpf_sock *bpf_sk_lookup_tcp(void *ctx, struct bpf_sock_tuple *tuple, u32 tuple_size, u64 netns, u64 flags)
  *	Description
  *		Look for TCP socket matching *tuple*, optionally in a child
@@ -2289,6 +2279,16 @@ union bpf_attr {
  *	Return
  *		0 on success, or a negative error in case of failure.
  *
+ * int bpf_map_push_elem(struct bpf_map *map, const void *value, u64 flags)
+ * 	Description
+ * 		Push an element *value* in *map*. *flags* is one of:
+ *
+ * 		**BPF_EXIST**
+ * 			If the queue/stack is full, the oldest element is
+ * 			removed to make room for this.
+ * 	Return
+ * 		0 on success, or a negative error in case of failure.
+ *
  * int bpf_map_pop_elem(struct bpf_map *map, void *value)
  * 	Description
  * 		Pop an element from *map*.
@@ -2343,29 +2343,94 @@ union bpf_attr {
  *	Return
  *		0
  *
+ * int bpf_spin_lock(struct bpf_spin_lock *lock)
+ *	Description
+ *		Acquire a spinlock represented by the pointer *lock*, which is
+ *		stored as part of a value of a map. Taking the lock allows to
+ *		safely update the rest of the fields in that value. The
+ *		spinlock can (and must) later be released with a call to
+ *		**bpf_spin_unlock**\ (\ *lock*\ ).
+ *
+ *		Spinlocks in BPF programs come with a number of restrictions
+ *		and constraints:
+ *
+ *		* **bpf_spin_lock** objects are only allowed inside maps of
+ *		  types **BPF_MAP_TYPE_HASH** and **BPF_MAP_TYPE_ARRAY** (this
+ *		  list could be extended in the future).
+ *		* BTF description of the map is mandatory.
+ *		* The BPF program can take ONE lock at a time, since taking two
+ *		  or more could cause dead locks.
+ *		* Only one **struct bpf_spin_lock** is allowed per map element.
+ *		* When the lock is taken, calls (either BPF to BPF or helpers)
+ *		  are not allowed.
+ *		* The **BPF_LD_ABS** and **BPF_LD_IND** instructions are not
+ *		  allowed inside a spinlock-ed region.
+ *		* The BPF program MUST call **bpf_spin_unlock**\ () to release
+ *		  the lock, on all execution paths, before it returns.
+ *		* The BPF program can access **struct bpf_spin_lock** only via
+ *		  the **bpf_spin_lock**\ () and **bpf_spin_unlock**\ ()
+ *		  helpers. Loading or storing data into the **struct
+ *		  bpf_spin_lock** *lock*\ **;** field of a map is not allowed.
+ *		* To use the **bpf_spin_lock**\ () helper, the BTF description
+ *		  of the map value must be a struct and have **struct
+ *		  bpf_spin_lock** *anyname*\ **;** field at the top level.
+ *		  Nested lock inside another struct is not allowed.
+ *		* The **struct bpf_spin_lock** *lock* field in a map value must
+ *		  be aligned on a multiple of 4 bytes in that value.
+ *		* Syscall with command **BPF_MAP_LOOKUP_ELEM** does not copy
+ *		  the **bpf_spin_lock** field to user space.
+ *		* Syscall with command **BPF_MAP_UPDATE_ELEM**, or update from
+ *		  a BPF program, do not update the **bpf_spin_lock** field.
+ *		* **bpf_spin_lock** cannot be on the stack or inside a
+ *		  networking packet (it can only be inside of a map values).
+ *		* **bpf_spin_lock** is available to root only.
+ *		* Tracing programs and socket filter programs cannot use
+ *		  **bpf_spin_lock**\ () due to insufficient preemption checks
+ *		  (but this may change in the future).
+ *		* **bpf_spin_lock** is not allowed in inner maps of map-in-map.
+ *	Return
+ *		0
+ *
+ * int bpf_spin_unlock(struct bpf_spin_lock *lock)
+ *	Description
+ *		Release the *lock* previously locked by a call to
+ *		**bpf_spin_lock**\ (\ *lock*\ ).
+ *	Return
+ *		0
+ *
  * struct bpf_sock *bpf_sk_fullsock(struct bpf_sock *sk)
  *	Description
  *		This helper gets a **struct bpf_sock** pointer such
- *		that all the fields in bpf_sock can be accessed.
+ *		that all the fields in this **bpf_sock** can be accessed.
  *	Return
- *		A **struct bpf_sock** pointer on success, or NULL in
+ *		A **struct bpf_sock** pointer on success, or **NULL** in
  *		case of failure.
  *
  * struct bpf_tcp_sock *bpf_tcp_sock(struct bpf_sock *sk)
  *	Description
  *		This helper gets a **struct bpf_tcp_sock** pointer from a
  *		**struct bpf_sock** pointer.
- *
  *	Return
- *		A **struct bpf_tcp_sock** pointer on success, or NULL in
+ *		A **struct bpf_tcp_sock** pointer on success, or **NULL** in
  *		case of failure.
  *
  * int bpf_skb_ecn_set_ce(struct sk_buf *skb)
- *     Description
- *             Sets ECN of IP header to ce (congestion encountered) if
- *             current value is ect (ECN capable). Works with IPv6 and IPv4.
- *     Return
- *             1 if set, 0 if not set.
+ *	Description
+ *		Set ECN (Explicit Congestion Notification) field of IP header
+ *		to **CE** (Congestion Encountered) if current value is **ECT**
+ *		(ECN Capable Transport). Otherwise, do nothing. Works with IPv6
+ *		and IPv4.
+ *	Return
+ *		1 if the **CE** flag is set (either by the current helper call
+ *		or because it was already present), 0 if it is not set.
+ *
+ * struct bpf_sock *bpf_get_listener_sock(struct bpf_sock *sk)
+ *	Description
+ *		Return a **struct bpf_sock** pointer in **TCP_LISTEN** state.
+ *		**bpf_sk_release**\ () is unnecessary and not allowed.
+ *	Return
+ *		A **struct bpf_sock** pointer on success, or **NULL** in
+ *		case of failure.
  */
 #define __BPF_FUNC_MAPPER(FN)		\
 	FN(unspec),			\
@@ -2465,7 +2530,8 @@ union bpf_attr {
 	FN(spin_unlock),		\
 	FN(sk_fullsock),		\
 	FN(tcp_sock),			\
-	FN(skb_ecn_set_ce),
+	FN(skb_ecn_set_ce),		\
+	FN(get_listener_sock),
 
 /* integer value in 'imm' field of BPF_CALL instruction selects which helper
  * function eBPF program intends to call
diff --git a/tools/include/uapi/linux/fcntl.h b/tools/include/uapi/linux/fcntl.h
index 6448cdd9a350..a2f8658f1c55 100644
--- a/tools/include/uapi/linux/fcntl.h
+++ b/tools/include/uapi/linux/fcntl.h
@@ -41,6 +41,7 @@
 #define F_SEAL_SHRINK	0x0002	/* prevent file from shrinking */
 #define F_SEAL_GROW	0x0004	/* prevent file from growing */
 #define F_SEAL_WRITE	0x0008	/* prevent writes */
+#define F_SEAL_FUTURE_WRITE	0x0010  /* prevent future writes while mapped */
 /* (1U << 31) is reserved for signed error codes */
 
 /*
diff --git a/tools/include/uapi/linux/mman.h b/tools/include/uapi/linux/mman.h
index d0f515d53299..fc1a64c3447b 100644
--- a/tools/include/uapi/linux/mman.h
+++ b/tools/include/uapi/linux/mman.h
@@ -12,6 +12,10 @@
 #define OVERCOMMIT_ALWAYS		1
 #define OVERCOMMIT_NEVER		2
 
+#define MAP_SHARED	0x01		/* Share changes */
+#define MAP_PRIVATE	0x02		/* Changes are private */
+#define MAP_SHARED_VALIDATE 0x03	/* share + validate extension flags */
+
 /*
  * Huge page size encoding when MAP_HUGETLB is specified, and a huge page
  * size other than the default is desired.  See hugetlb_encode.h.
diff --git a/tools/include/uapi/sound/asound.h b/tools/include/uapi/sound/asound.h
index 404d4b9ffe76..df1153cea0b7 100644
--- a/tools/include/uapi/sound/asound.h
+++ b/tools/include/uapi/sound/asound.h
@@ -32,6 +32,7 @@
 
 #ifndef __KERNEL__
 #include <stdlib.h>
+#include <time.h>
 #endif
 
 /*
diff --git a/tools/io_uring/io_uring-bench.c b/tools/io_uring/io_uring-bench.c
index 512306a37531..0f257139b003 100644
--- a/tools/io_uring/io_uring-bench.c
+++ b/tools/io_uring/io_uring-bench.c
@@ -32,10 +32,6 @@
 #include "liburing.h"
 #include "barrier.h"
 
-#ifndef IOCQE_FLAG_CACHEHIT
-#define IOCQE_FLAG_CACHEHIT	(1U << 0)
-#endif
-
 #define min(a, b)		((a < b) ? (a) : (b))
 
 struct io_sq_ring {
@@ -85,7 +81,6 @@ struct submitter {
 	unsigned long reaps;
 	unsigned long done;
 	unsigned long calls;
-	unsigned long cachehit, cachemiss;
 	volatile int finish;
 
 	__s32 *fds;
@@ -270,10 +265,6 @@ static int reap_events(struct submitter *s)
 				return -1;
 			}
 		}
-		if (cqe->flags & IOCQE_FLAG_CACHEHIT)
-			s->cachehit++;
-		else
-			s->cachemiss++;
 		reaped++;
 		head++;
 	} while (1);
@@ -489,7 +480,7 @@ static void file_depths(char *buf)
 int main(int argc, char *argv[])
 {
 	struct submitter *s = &submitters[0];
-	unsigned long done, calls, reap, cache_hit, cache_miss;
+	unsigned long done, calls, reap;
 	int err, i, flags, fd;
 	char *fdepths;
 	void *ret;
@@ -569,44 +560,29 @@ int main(int argc, char *argv[])
 	pthread_create(&s->thread, NULL, submitter_fn, s);
 
 	fdepths = malloc(8 * s->nr_files);
-	cache_hit = cache_miss = reap = calls = done = 0;
+	reap = calls = done = 0;
 	do {
 		unsigned long this_done = 0;
 		unsigned long this_reap = 0;
 		unsigned long this_call = 0;
-		unsigned long this_cache_hit = 0;
-		unsigned long this_cache_miss = 0;
 		unsigned long rpc = 0, ipc = 0;
-		double hit = 0.0;
 
 		sleep(1);
 		this_done += s->done;
 		this_call += s->calls;
 		this_reap += s->reaps;
-		this_cache_hit += s->cachehit;
-		this_cache_miss += s->cachemiss;
-		if (this_cache_hit && this_cache_miss) {
-			unsigned long hits, total;
-
-			hits = this_cache_hit - cache_hit;
-			total = hits + this_cache_miss - cache_miss;
-			hit = (double) hits / (double) total;
-			hit *= 100.0;
-		}
 		if (this_call - calls) {
 			rpc = (this_done - done) / (this_call - calls);
 			ipc = (this_reap - reap) / (this_call - calls);
 		} else
 			rpc = ipc = -1;
 		file_depths(fdepths);
-		printf("IOPS=%lu, IOS/call=%ld/%ld, inflight=%u (%s), Cachehit=%0.2f%%\n",
+		printf("IOPS=%lu, IOS/call=%ld/%ld, inflight=%u (%s)\n",
 				this_done - done, rpc, ipc, s->inflight,
-				fdepths, hit);
+				fdepths);
 		done = this_done;
 		calls = this_call;
 		reap = this_reap;
-		cache_hit = s->cachehit;
-		cache_miss = s->cachemiss;
 	} while (!finish);
 
 	pthread_join(s->thread, &ret);
diff --git a/tools/lib/bpf/.gitignore b/tools/lib/bpf/.gitignore
index 4db74758c674..fecb78afea3f 100644
--- a/tools/lib/bpf/.gitignore
+++ b/tools/lib/bpf/.gitignore
@@ -1,3 +1,4 @@
 libbpf_version.h
 FEATURE-DUMP.libbpf
 test_libbpf
+libbpf.so.*
diff --git a/tools/lib/bpf/Makefile b/tools/lib/bpf/Makefile
index 61aaacf0cfa1..8e7c56e9590f 100644
--- a/tools/lib/bpf/Makefile
+++ b/tools/lib/bpf/Makefile
@@ -3,7 +3,7 @@
 
 BPF_VERSION = 0
 BPF_PATCHLEVEL = 0
-BPF_EXTRAVERSION = 1
+BPF_EXTRAVERSION = 2
 
 MAKEFLAGS += --no-print-directory
 
@@ -79,8 +79,6 @@ export prefix libdir src obj
 libdir_SQ = $(subst ','\'',$(libdir))
 libdir_relative_SQ = $(subst ','\'',$(libdir_relative))
 
-LIB_FILE = libbpf.a libbpf.so
-
 VERSION		= $(BPF_VERSION)
 PATCHLEVEL	= $(BPF_PATCHLEVEL)
 EXTRAVERSION	= $(BPF_EXTRAVERSION)
@@ -88,7 +86,10 @@ EXTRAVERSION	= $(BPF_EXTRAVERSION)
 OBJ		= $@
 N		=
 
-LIBBPF_VERSION = $(BPF_VERSION).$(BPF_PATCHLEVEL).$(BPF_EXTRAVERSION)
+LIBBPF_VERSION	= $(BPF_VERSION).$(BPF_PATCHLEVEL).$(BPF_EXTRAVERSION)
+
+LIB_TARGET	= libbpf.a libbpf.so.$(LIBBPF_VERSION)
+LIB_FILE	= libbpf.a libbpf.so*
 
 # Set compile option CFLAGS
 ifdef EXTRA_CFLAGS
@@ -128,16 +129,18 @@ all:
 export srctree OUTPUT CC LD CFLAGS V
 include $(srctree)/tools/build/Makefile.include
 
-BPF_IN    := $(OUTPUT)libbpf-in.o
-LIB_FILE := $(addprefix $(OUTPUT),$(LIB_FILE))
-VERSION_SCRIPT := libbpf.map
+BPF_IN		:= $(OUTPUT)libbpf-in.o
+VERSION_SCRIPT	:= libbpf.map
+
+LIB_TARGET	:= $(addprefix $(OUTPUT),$(LIB_TARGET))
+LIB_FILE	:= $(addprefix $(OUTPUT),$(LIB_FILE))
 
 GLOBAL_SYM_COUNT = $(shell readelf -s --wide $(BPF_IN) | \
 			   awk '/GLOBAL/ && /DEFAULT/ && !/UND/ {s++} END{print s}')
 VERSIONED_SYM_COUNT = $(shell readelf -s --wide $(OUTPUT)libbpf.so | \
 			      grep -Eo '[^ ]+@LIBBPF_' | cut -d@ -f1 | sort -u | wc -l)
 
-CMD_TARGETS = $(LIB_FILE)
+CMD_TARGETS = $(LIB_TARGET)
 
 CXX_TEST_TARGET = $(OUTPUT)test_libbpf
 
@@ -170,9 +173,13 @@ $(BPF_IN): force elfdep bpfdep
 	echo "Warning: Kernel ABI header at 'tools/include/uapi/linux/if_xdp.h' differs from latest version at 'include/uapi/linux/if_xdp.h'" >&2 )) || true
 	$(Q)$(MAKE) $(build)=libbpf
 
-$(OUTPUT)libbpf.so: $(BPF_IN)
-	$(QUIET_LINK)$(CC) --shared -Wl,--version-script=$(VERSION_SCRIPT) \
-		$^ -o $@
+$(OUTPUT)libbpf.so: $(OUTPUT)libbpf.so.$(LIBBPF_VERSION)
+
+$(OUTPUT)libbpf.so.$(LIBBPF_VERSION): $(BPF_IN)
+	$(QUIET_LINK)$(CC) --shared -Wl,-soname,libbpf.so.$(VERSION) \
+				    -Wl,--version-script=$(VERSION_SCRIPT) $^ -lelf -o $@
+	@ln -sf $(@F) $(OUTPUT)libbpf.so
+	@ln -sf $(@F) $(OUTPUT)libbpf.so.$(VERSION)
 
 $(OUTPUT)libbpf.a: $(BPF_IN)
 	$(QUIET_LINK)$(RM) $@; $(AR) rcs $@ $^
@@ -192,6 +199,12 @@ check_abi: $(OUTPUT)libbpf.so
 		exit 1;							 \
 	fi
 
+define do_install_mkdir
+	if [ ! -d '$(DESTDIR_SQ)$1' ]; then		\
+		$(INSTALL) -d -m 755 '$(DESTDIR_SQ)$1';	\
+	fi
+endef
+
 define do_install
 	if [ ! -d '$(DESTDIR_SQ)$2' ]; then		\
 		$(INSTALL) -d -m 755 '$(DESTDIR_SQ)$2';	\
@@ -200,14 +213,16 @@ define do_install
 endef
 
 install_lib: all_cmd
-	$(call QUIET_INSTALL, $(LIB_FILE)) \
-		$(call do_install,$(LIB_FILE),$(libdir_SQ))
+	$(call QUIET_INSTALL, $(LIB_TARGET)) \
+		$(call do_install_mkdir,$(libdir_SQ)); \
+		cp -fpR $(LIB_FILE) $(DESTDIR)$(libdir_SQ)
 
 install_headers:
 	$(call QUIET_INSTALL, headers) \
 		$(call do_install,bpf.h,$(prefix)/include/bpf,644); \
-		$(call do_install,libbpf.h,$(prefix)/include/bpf,644);
-		$(call do_install,btf.h,$(prefix)/include/bpf,644);
+		$(call do_install,libbpf.h,$(prefix)/include/bpf,644); \
+		$(call do_install,btf.h,$(prefix)/include/bpf,644); \
+		$(call do_install,xsk.h,$(prefix)/include/bpf,644);
 
 install: install_lib
 
@@ -219,7 +234,7 @@ config-clean:
 
 clean:
 	$(call QUIET_CLEAN, libbpf) $(RM) $(TARGETS) $(CXX_TEST_TARGET) \
-		*.o *~ *.a *.so .*.d .*.cmd LIBBPF-CFLAGS
+		*.o *~ *.a *.so *.so.$(VERSION) .*.d .*.cmd LIBBPF-CFLAGS
 	$(call QUIET_CLEAN, core-gen) $(RM) $(OUTPUT)FEATURE-DUMP.libbpf
 
 
diff --git a/tools/lib/bpf/README.rst b/tools/lib/bpf/README.rst
index 5788479384ca..cef7b77eab69 100644
--- a/tools/lib/bpf/README.rst
+++ b/tools/lib/bpf/README.rst
@@ -111,6 +111,7 @@ starting from ``0.0.1``.
 
 Every time ABI is being changed, e.g. because a new symbol is added or
 semantic of existing symbol is changed, ABI version should be bumped.
+This bump in ABI version is at most once per kernel development cycle.
 
 For example, if current state of ``libbpf.map`` is:
 
diff --git a/tools/lib/bpf/btf.c b/tools/lib/bpf/btf.c
index 1b8d8cdd3575..cf119c9b6f27 100644
--- a/tools/lib/bpf/btf.c
+++ b/tools/lib/bpf/btf.c
@@ -1602,16 +1602,12 @@ static bool btf_equal_int(struct btf_type *t1, struct btf_type *t2)
 /* Calculate type signature hash of ENUM. */
 static __u32 btf_hash_enum(struct btf_type *t)
 {
-	struct btf_enum *member = (struct btf_enum *)(t + 1);
-	__u32 vlen = BTF_INFO_VLEN(t->info);
-	__u32 h = btf_hash_common(t);
-	int i;
+	__u32 h;
 
-	for (i = 0; i < vlen; i++) {
-		h = hash_combine(h, member->name_off);
-		h = hash_combine(h, member->val);
-		member++;
-	}
+	/* don't hash vlen and enum members to support enum fwd resolving */
+	h = hash_combine(0, t->name_off);
+	h = hash_combine(h, t->info & ~0xffff);
+	h = hash_combine(h, t->size);
 	return h;
 }
 
@@ -1637,6 +1633,22 @@ static bool btf_equal_enum(struct btf_type *t1, struct btf_type *t2)
 	return true;
 }
 
+static inline bool btf_is_enum_fwd(struct btf_type *t)
+{
+	return BTF_INFO_KIND(t->info) == BTF_KIND_ENUM &&
+	       BTF_INFO_VLEN(t->info) == 0;
+}
+
+static bool btf_compat_enum(struct btf_type *t1, struct btf_type *t2)
+{
+	if (!btf_is_enum_fwd(t1) && !btf_is_enum_fwd(t2))
+		return btf_equal_enum(t1, t2);
+	/* ignore vlen when comparing */
+	return t1->name_off == t2->name_off &&
+	       (t1->info & ~0xffff) == (t2->info & ~0xffff) &&
+	       t1->size == t2->size;
+}
+
 /*
  * Calculate type signature hash of STRUCT/UNION, ignoring referenced type IDs,
  * as referenced type IDs equivalence is established separately during type
@@ -1860,6 +1872,17 @@ static int btf_dedup_prim_type(struct btf_dedup *d, __u32 type_id)
 				new_id = cand_node->type_id;
 				break;
 			}
+			if (d->opts.dont_resolve_fwds)
+				continue;
+			if (btf_compat_enum(t, cand)) {
+				if (btf_is_enum_fwd(t)) {
+					/* resolve fwd to full enum */
+					new_id = cand_node->type_id;
+					break;
+				}
+				/* resolve canonical enum fwd to full enum */
+				d->map[cand_node->type_id] = type_id;
+			}
 		}
 		break;
 
@@ -2084,7 +2107,7 @@ static int btf_dedup_is_equiv(struct btf_dedup *d, __u32 cand_id,
 		return fwd_kind == real_kind;
 	}
 
-	if (cand_type->info != canon_type->info)
+	if (cand_kind != canon_kind)
 		return 0;
 
 	switch (cand_kind) {
@@ -2092,7 +2115,10 @@ static int btf_dedup_is_equiv(struct btf_dedup *d, __u32 cand_id,
 		return btf_equal_int(cand_type, canon_type);
 
 	case BTF_KIND_ENUM:
-		return btf_equal_enum(cand_type, canon_type);
+		if (d->opts.dont_resolve_fwds)
+			return btf_equal_enum(cand_type, canon_type);
+		else
+			return btf_compat_enum(cand_type, canon_type);
 
 	case BTF_KIND_FWD:
 		return btf_equal_common(cand_type, canon_type);
@@ -2103,6 +2129,8 @@ static int btf_dedup_is_equiv(struct btf_dedup *d, __u32 cand_id,
 	case BTF_KIND_PTR:
 	case BTF_KIND_TYPEDEF:
 	case BTF_KIND_FUNC:
+		if (cand_type->info != canon_type->info)
+			return 0;
 		return btf_dedup_is_equiv(d, cand_type->type, canon_type->type);
 
 	case BTF_KIND_ARRAY: {
diff --git a/tools/lib/bpf/libbpf.c b/tools/lib/bpf/libbpf.c
index e6ad87512519..11c25d9ea431 100644
--- a/tools/lib/bpf/libbpf.c
+++ b/tools/lib/bpf/libbpf.c
@@ -840,12 +840,19 @@ static int bpf_object__elf_collect(struct bpf_object *obj, int flags)
 			obj->efile.maps_shndx = idx;
 		else if (strcmp(name, BTF_ELF_SEC) == 0) {
 			obj->btf = btf__new(data->d_buf, data->d_size);
-			if (IS_ERR(obj->btf) || btf__load(obj->btf)) {
+			if (IS_ERR(obj->btf)) {
 				pr_warning("Error loading ELF section %s: %ld. Ignored and continue.\n",
 					   BTF_ELF_SEC, PTR_ERR(obj->btf));
-				if (!IS_ERR(obj->btf))
-					btf__free(obj->btf);
 				obj->btf = NULL;
+				continue;
+			}
+			err = btf__load(obj->btf);
+			if (err) {
+				pr_warning("Error loading %s into kernel: %d. Ignored and continue.\n",
+					   BTF_ELF_SEC, err);
+				btf__free(obj->btf);
+				obj->btf = NULL;
+				err = 0;
 			}
 		} else if (strcmp(name, BTF_EXT_ELF_SEC) == 0) {
 			btf_ext_data = data;
diff --git a/tools/lib/bpf/xsk.c b/tools/lib/bpf/xsk.c
index f98ac82c9aea..8d0078b65486 100644
--- a/tools/lib/bpf/xsk.c
+++ b/tools/lib/bpf/xsk.c
@@ -126,8 +126,8 @@ static void xsk_set_umem_config(struct xsk_umem_config *cfg,
 	cfg->frame_headroom = usr_cfg->frame_headroom;
 }
 
-static void xsk_set_xdp_socket_config(struct xsk_socket_config *cfg,
-				      const struct xsk_socket_config *usr_cfg)
+static int xsk_set_xdp_socket_config(struct xsk_socket_config *cfg,
+				     const struct xsk_socket_config *usr_cfg)
 {
 	if (!usr_cfg) {
 		cfg->rx_size = XSK_RING_CONS__DEFAULT_NUM_DESCS;
@@ -135,14 +135,19 @@ static void xsk_set_xdp_socket_config(struct xsk_socket_config *cfg,
 		cfg->libbpf_flags = 0;
 		cfg->xdp_flags = 0;
 		cfg->bind_flags = 0;
-		return;
+		return 0;
 	}
 
+	if (usr_cfg->libbpf_flags & ~XSK_LIBBPF_FLAGS__INHIBIT_PROG_LOAD)
+		return -EINVAL;
+
 	cfg->rx_size = usr_cfg->rx_size;
 	cfg->tx_size = usr_cfg->tx_size;
 	cfg->libbpf_flags = usr_cfg->libbpf_flags;
 	cfg->xdp_flags = usr_cfg->xdp_flags;
 	cfg->bind_flags = usr_cfg->bind_flags;
+
+	return 0;
 }
 
 int xsk_umem__create(struct xsk_umem **umem_ptr, void *umem_area, __u64 size,
@@ -557,7 +562,9 @@ int xsk_socket__create(struct xsk_socket **xsk_ptr, const char *ifname,
 	}
 	strncpy(xsk->ifname, ifname, IFNAMSIZ);
 
-	xsk_set_xdp_socket_config(&xsk->config, usr_config);
+	err = xsk_set_xdp_socket_config(&xsk->config, usr_config);
+	if (err)
+		goto out_socket;
 
 	if (rx) {
 		err = setsockopt(xsk->fd, SOL_XDP, XDP_RX_RING,
diff --git a/tools/lib/traceevent/event-parse-api.c b/tools/lib/traceevent/event-parse-api.c
index d463761a58f4..988587840c80 100644
--- a/tools/lib/traceevent/event-parse-api.c
+++ b/tools/lib/traceevent/event-parse-api.c
@@ -9,6 +9,22 @@
 #include "event-utils.h"
 
 /**
+ * tep_get_event - returns the event with the given index
+ * @tep: a handle to the tep_handle
+ * @index: index of the requested event, in the range 0 .. nr_events
+ *
+ * This returns pointer to the element of the events array with the given index
+ * If @tep is NULL, or @index is not in the range 0 .. nr_events, NULL is returned.
+ */
+struct tep_event *tep_get_event(struct tep_handle *tep, int index)
+{
+	if (tep && tep->events && index < tep->nr_events)
+		return tep->events[index];
+
+	return NULL;
+}
+
+/**
  * tep_get_first_event - returns the first event in the events array
  * @tep: a handle to the tep_handle
  *
@@ -17,10 +33,7 @@
  */
 struct tep_event *tep_get_first_event(struct tep_handle *tep)
 {
-	if (tep && tep->events)
-		return tep->events[0];
-
-	return NULL;
+	return tep_get_event(tep, 0);
 }
 
 /**
@@ -32,7 +45,7 @@ struct tep_event *tep_get_first_event(struct tep_handle *tep)
  */
 int tep_get_events_count(struct tep_handle *tep)
 {
-	if(tep)
+	if (tep)
 		return tep->nr_events;
 	return 0;
 }
@@ -43,19 +56,47 @@ int tep_get_events_count(struct tep_handle *tep)
  * @flag: flag, or combination of flags to be set
  * can be any combination from enum tep_flag
  *
- * This sets a flag or mbination of flags  from enum tep_flag
-  */
+ * This sets a flag or combination of flags from enum tep_flag
+ */
 void tep_set_flag(struct tep_handle *tep, int flag)
 {
-	if(tep)
+	if (tep)
 		tep->flags |= flag;
 }
 
-unsigned short tep_data2host2(struct tep_handle *pevent, unsigned short data)
+/**
+ * tep_clear_flag - clear event parser flag
+ * @tep: a handle to the tep_handle
+ * @flag: flag to be cleared
+ *
+ * This clears a tep flag
+ */
+void tep_clear_flag(struct tep_handle *tep, enum tep_flag flag)
+{
+	if (tep)
+		tep->flags &= ~flag;
+}
+
+/**
+ * tep_test_flag - check the state of event parser flag
+ * @tep: a handle to the tep_handle
+ * @flag: flag to be checked
+ *
+ * This returns the state of the requested tep flag.
+ * Returns: true if the flag is set, false otherwise.
+ */
+bool tep_test_flag(struct tep_handle *tep, enum tep_flag flag)
+{
+	if (tep)
+		return tep->flags & flag;
+	return false;
+}
+
+unsigned short tep_data2host2(struct tep_handle *tep, unsigned short data)
 {
 	unsigned short swap;
 
-	if (!pevent || pevent->host_bigendian == pevent->file_bigendian)
+	if (!tep || tep->host_bigendian == tep->file_bigendian)
 		return data;
 
 	swap = ((data & 0xffULL) << 8) |
@@ -64,11 +105,11 @@ unsigned short tep_data2host2(struct tep_handle *pevent, unsigned short data)
 	return swap;
 }
 
-unsigned int tep_data2host4(struct tep_handle *pevent, unsigned int data)
+unsigned int tep_data2host4(struct tep_handle *tep, unsigned int data)
 {
 	unsigned int swap;
 
-	if (!pevent || pevent->host_bigendian == pevent->file_bigendian)
+	if (!tep || tep->host_bigendian == tep->file_bigendian)
 		return data;
 
 	swap = ((data & 0xffULL) << 24) |
@@ -80,11 +121,11 @@ unsigned int tep_data2host4(struct tep_handle *pevent, unsigned int data)
 }
 
 unsigned long long
-tep_data2host8(struct tep_handle *pevent, unsigned long long data)
+tep_data2host8(struct tep_handle *tep, unsigned long long data)
 {
 	unsigned long long swap;
 
-	if (!pevent || pevent->host_bigendian == pevent->file_bigendian)
+	if (!tep || tep->host_bigendian == tep->file_bigendian)
 		return data;
 
 	swap = ((data & 0xffULL) << 56) |
@@ -101,175 +142,232 @@ tep_data2host8(struct tep_handle *pevent, unsigned long long data)
 
 /**
  * tep_get_header_page_size - get size of the header page
- * @pevent: a handle to the tep_handle
+ * @tep: a handle to the tep_handle
  *
  * This returns size of the header page
- * If @pevent is NULL, 0 is returned.
+ * If @tep is NULL, 0 is returned.
+ */
+int tep_get_header_page_size(struct tep_handle *tep)
+{
+	if (tep)
+		return tep->header_page_size_size;
+	return 0;
+}
+
+/**
+ * tep_get_header_timestamp_size - get size of the timestamp in the header page
+ * @tep: a handle to the tep_handle
+ *
+ * This returns size of the timestamp in the header page
+ * If @tep is NULL, 0 is returned.
  */
-int tep_get_header_page_size(struct tep_handle *pevent)
+int tep_get_header_timestamp_size(struct tep_handle *tep)
 {
-	if(pevent)
-		return pevent->header_page_size_size;
+	if (tep)
+		return tep->header_page_ts_size;
 	return 0;
 }
 
 /**
  * tep_get_cpus - get the number of CPUs
- * @pevent: a handle to the tep_handle
+ * @tep: a handle to the tep_handle
  *
  * This returns the number of CPUs
- * If @pevent is NULL, 0 is returned.
+ * If @tep is NULL, 0 is returned.
  */
-int tep_get_cpus(struct tep_handle *pevent)
+int tep_get_cpus(struct tep_handle *tep)
 {
-	if(pevent)
-		return pevent->cpus;
+	if (tep)
+		return tep->cpus;
 	return 0;
 }
 
 /**
  * tep_set_cpus - set the number of CPUs
- * @pevent: a handle to the tep_handle
+ * @tep: a handle to the tep_handle
  *
  * This sets the number of CPUs
  */
-void tep_set_cpus(struct tep_handle *pevent, int cpus)
+void tep_set_cpus(struct tep_handle *tep, int cpus)
 {
-	if(pevent)
-		pevent->cpus = cpus;
+	if (tep)
+		tep->cpus = cpus;
 }
 
 /**
- * tep_get_long_size - get the size of a long integer on the current machine
- * @pevent: a handle to the tep_handle
+ * tep_get_long_size - get the size of a long integer on the traced machine
+ * @tep: a handle to the tep_handle
  *
- * This returns the size of a long integer on the current machine
- * If @pevent is NULL, 0 is returned.
+ * This returns the size of a long integer on the traced machine
+ * If @tep is NULL, 0 is returned.
  */
-int tep_get_long_size(struct tep_handle *pevent)
+int tep_get_long_size(struct tep_handle *tep)
 {
-	if(pevent)
-		return pevent->long_size;
+	if (tep)
+		return tep->long_size;
 	return 0;
 }
 
 /**
- * tep_set_long_size - set the size of a long integer on the current machine
- * @pevent: a handle to the tep_handle
+ * tep_set_long_size - set the size of a long integer on the traced machine
+ * @tep: a handle to the tep_handle
  * @size: size, in bytes, of a long integer
  *
- * This sets the size of a long integer on the current machine
+ * This sets the size of a long integer on the traced machine
  */
-void tep_set_long_size(struct tep_handle *pevent, int long_size)
+void tep_set_long_size(struct tep_handle *tep, int long_size)
 {
-	if(pevent)
-		pevent->long_size = long_size;
+	if (tep)
+		tep->long_size = long_size;
 }
 
 /**
- * tep_get_page_size - get the size of a memory page on the current machine
- * @pevent: a handle to the tep_handle
+ * tep_get_page_size - get the size of a memory page on the traced machine
+ * @tep: a handle to the tep_handle
  *
- * This returns the size of a memory page on the current machine
- * If @pevent is NULL, 0 is returned.
+ * This returns the size of a memory page on the traced machine
+ * If @tep is NULL, 0 is returned.
  */
-int tep_get_page_size(struct tep_handle *pevent)
+int tep_get_page_size(struct tep_handle *tep)
 {
-	if(pevent)
-		return pevent->page_size;
+	if (tep)
+		return tep->page_size;
 	return 0;
 }
 
 /**
- * tep_set_page_size - set the size of a memory page on the current machine
- * @pevent: a handle to the tep_handle
+ * tep_set_page_size - set the size of a memory page on the traced machine
+ * @tep: a handle to the tep_handle
  * @_page_size: size of a memory page, in bytes
  *
- * This sets the size of a memory page on the current machine
+ * This sets the size of a memory page on the traced machine
  */
-void tep_set_page_size(struct tep_handle *pevent, int _page_size)
+void tep_set_page_size(struct tep_handle *tep, int _page_size)
 {
-	if(pevent)
-		pevent->page_size = _page_size;
+	if (tep)
+		tep->page_size = _page_size;
 }
 
 /**
- * tep_file_bigendian - get if the file is in big endian order
- * @pevent: a handle to the tep_handle
+ * tep_is_file_bigendian - return the endian of the file
+ * @tep: a handle to the tep_handle
  *
- * This returns if the file is in big endian order
- * If @pevent is NULL, 0 is returned.
+ * This returns true if the file is in big endian order
+ * If @tep is NULL, false is returned.
  */
-int tep_file_bigendian(struct tep_handle *pevent)
+bool tep_is_file_bigendian(struct tep_handle *tep)
 {
-	if(pevent)
-		return pevent->file_bigendian;
-	return 0;
+	if (tep)
+		return (tep->file_bigendian == TEP_BIG_ENDIAN);
+	return false;
 }
 
 /**
  * tep_set_file_bigendian - set if the file is in big endian order
- * @pevent: a handle to the tep_handle
+ * @tep: a handle to the tep_handle
  * @endian: non zero, if the file is in big endian order
  *
  * This sets if the file is in big endian order
  */
-void tep_set_file_bigendian(struct tep_handle *pevent, enum tep_endian endian)
+void tep_set_file_bigendian(struct tep_handle *tep, enum tep_endian endian)
 {
-	if(pevent)
-		pevent->file_bigendian = endian;
+	if (tep)
+		tep->file_bigendian = endian;
 }
 
 /**
- * tep_is_host_bigendian - get if the order of the current host is big endian
- * @pevent: a handle to the tep_handle
+ * tep_is_local_bigendian - return the endian of the saved local machine
+ * @tep: a handle to the tep_handle
  *
- * This gets if the order of the current host is big endian
- * If @pevent is NULL, 0 is returned.
+ * This returns true if the saved local machine in @tep is big endian.
+ * If @tep is NULL, false is returned.
  */
-int tep_is_host_bigendian(struct tep_handle *pevent)
+bool tep_is_local_bigendian(struct tep_handle *tep)
 {
-	if(pevent)
-		return pevent->host_bigendian;
+	if (tep)
+		return (tep->host_bigendian == TEP_BIG_ENDIAN);
 	return 0;
 }
 
 /**
- * tep_set_host_bigendian - set the order of the local host
- * @pevent: a handle to the tep_handle
+ * tep_set_local_bigendian - set the stored local machine endian order
+ * @tep: a handle to the tep_handle
  * @endian: non zero, if the local host has big endian order
  *
- * This sets the order of the local host
+ * This sets the endian order for the local machine.
  */
-void tep_set_host_bigendian(struct tep_handle *pevent, enum tep_endian endian)
+void tep_set_local_bigendian(struct tep_handle *tep, enum tep_endian endian)
 {
-	if(pevent)
-		pevent->host_bigendian = endian;
+	if (tep)
+		tep->host_bigendian = endian;
 }
 
 /**
  * tep_is_latency_format - get if the latency output format is configured
- * @pevent: a handle to the tep_handle
+ * @tep: a handle to the tep_handle
  *
- * This gets if the latency output format is configured
- * If @pevent is NULL, 0 is returned.
+ * This returns true if the latency output format is configured
+ * If @tep is NULL, false is returned.
  */
-int tep_is_latency_format(struct tep_handle *pevent)
+bool tep_is_latency_format(struct tep_handle *tep)
 {
-	if(pevent)
-		return pevent->latency_format;
-	return 0;
+	if (tep)
+		return (tep->latency_format);
+	return false;
 }
 
 /**
  * tep_set_latency_format - set the latency output format
- * @pevent: a handle to the tep_handle
+ * @tep: a handle to the tep_handle
  * @lat: non zero for latency output format
  *
  * This sets the latency output format
   */
-void tep_set_latency_format(struct tep_handle *pevent, int lat)
+void tep_set_latency_format(struct tep_handle *tep, int lat)
+{
+	if (tep)
+		tep->latency_format = lat;
+}
+
+/**
+ * tep_is_old_format - get if an old kernel is used
+ * @tep: a handle to the tep_handle
+ *
+ * This returns true, if an old kernel is used to generate the tracing events or
+ * false if a new kernel is used. Old kernels did not have header page info.
+ * If @tep is NULL, false is returned.
+ */
+bool tep_is_old_format(struct tep_handle *tep)
+{
+	if (tep)
+		return tep->old_format;
+	return false;
+}
+
+/**
+ * tep_set_print_raw - set a flag to force print in raw format
+ * @tep: a handle to the tep_handle
+ * @print_raw: the new value of the print_raw flag
+ *
+ * This sets a flag to force print in raw format
+ */
+void tep_set_print_raw(struct tep_handle *tep, int print_raw)
+{
+	if (tep)
+		tep->print_raw = print_raw;
+}
+
+/**
+ * tep_set_test_filters - set a flag to test a filter string
+ * @tep: a handle to the tep_handle
+ * @test_filters: the new value of the test_filters flag
+ *
+ * This sets a flag to test a filter string. If this flag is set, when
+ * tep_filter_add_filter_str() API as called,it will print the filter string
+ * instead of adding it.
+ */
+void tep_set_test_filters(struct tep_handle *tep, int test_filters)
 {
-	if(pevent)
-		pevent->latency_format = lat;
+	if (tep)
+		tep->test_filters = test_filters;
 }
diff --git a/tools/lib/traceevent/event-parse-local.h b/tools/lib/traceevent/event-parse-local.h
index 35833ee32d6c..09aa142f7fdd 100644
--- a/tools/lib/traceevent/event-parse-local.h
+++ b/tools/lib/traceevent/event-parse-local.h
@@ -92,8 +92,8 @@ struct tep_handle {
 void tep_free_event(struct tep_event *event);
 void tep_free_format_field(struct tep_format_field *field);
 
-unsigned short tep_data2host2(struct tep_handle *pevent, unsigned short data);
-unsigned int tep_data2host4(struct tep_handle *pevent, unsigned int data);
-unsigned long long tep_data2host8(struct tep_handle *pevent, unsigned long long data);
+unsigned short tep_data2host2(struct tep_handle *tep, unsigned short data);
+unsigned int tep_data2host4(struct tep_handle *tep, unsigned int data);
+unsigned long long tep_data2host8(struct tep_handle *tep, unsigned long long data);
 
 #endif /* _PARSE_EVENTS_INT_H */
diff --git a/tools/lib/traceevent/event-parse.c b/tools/lib/traceevent/event-parse.c
index 87494c7c619d..b36b536a9fcb 100644
--- a/tools/lib/traceevent/event-parse.c
+++ b/tools/lib/traceevent/event-parse.c
@@ -148,14 +148,14 @@ struct cmdline_list {
 	int			pid;
 };
 
-static int cmdline_init(struct tep_handle *pevent)
+static int cmdline_init(struct tep_handle *tep)
 {
-	struct cmdline_list *cmdlist = pevent->cmdlist;
+	struct cmdline_list *cmdlist = tep->cmdlist;
 	struct cmdline_list *item;
 	struct tep_cmdline *cmdlines;
 	int i;
 
-	cmdlines = malloc(sizeof(*cmdlines) * pevent->cmdline_count);
+	cmdlines = malloc(sizeof(*cmdlines) * tep->cmdline_count);
 	if (!cmdlines)
 		return -1;
 
@@ -169,15 +169,15 @@ static int cmdline_init(struct tep_handle *pevent)
 		free(item);
 	}
 
-	qsort(cmdlines, pevent->cmdline_count, sizeof(*cmdlines), cmdline_cmp);
+	qsort(cmdlines, tep->cmdline_count, sizeof(*cmdlines), cmdline_cmp);
 
-	pevent->cmdlines = cmdlines;
-	pevent->cmdlist = NULL;
+	tep->cmdlines = cmdlines;
+	tep->cmdlist = NULL;
 
 	return 0;
 }
 
-static const char *find_cmdline(struct tep_handle *pevent, int pid)
+static const char *find_cmdline(struct tep_handle *tep, int pid)
 {
 	const struct tep_cmdline *comm;
 	struct tep_cmdline key;
@@ -185,13 +185,13 @@ static const char *find_cmdline(struct tep_handle *pevent, int pid)
 	if (!pid)
 		return "<idle>";
 
-	if (!pevent->cmdlines && cmdline_init(pevent))
+	if (!tep->cmdlines && cmdline_init(tep))
 		return "<not enough memory for cmdlines!>";
 
 	key.pid = pid;
 
-	comm = bsearch(&key, pevent->cmdlines, pevent->cmdline_count,
-		       sizeof(*pevent->cmdlines), cmdline_cmp);
+	comm = bsearch(&key, tep->cmdlines, tep->cmdline_count,
+		       sizeof(*tep->cmdlines), cmdline_cmp);
 
 	if (comm)
 		return comm->comm;
@@ -199,32 +199,32 @@ static const char *find_cmdline(struct tep_handle *pevent, int pid)
 }
 
 /**
- * tep_pid_is_registered - return if a pid has a cmdline registered
- * @pevent: handle for the pevent
+ * tep_is_pid_registered - return if a pid has a cmdline registered
+ * @tep: a handle to the trace event parser context
  * @pid: The pid to check if it has a cmdline registered with.
  *
- * Returns 1 if the pid has a cmdline mapped to it
- * 0 otherwise.
+ * Returns true if the pid has a cmdline mapped to it
+ * false otherwise.
  */
-int tep_pid_is_registered(struct tep_handle *pevent, int pid)
+bool tep_is_pid_registered(struct tep_handle *tep, int pid)
 {
 	const struct tep_cmdline *comm;
 	struct tep_cmdline key;
 
 	if (!pid)
-		return 1;
+		return true;
 
-	if (!pevent->cmdlines && cmdline_init(pevent))
-		return 0;
+	if (!tep->cmdlines && cmdline_init(tep))
+		return false;
 
 	key.pid = pid;
 
-	comm = bsearch(&key, pevent->cmdlines, pevent->cmdline_count,
-		       sizeof(*pevent->cmdlines), cmdline_cmp);
+	comm = bsearch(&key, tep->cmdlines, tep->cmdline_count,
+		       sizeof(*tep->cmdlines), cmdline_cmp);
 
 	if (comm)
-		return 1;
-	return 0;
+		return true;
+	return false;
 }
 
 /*
@@ -232,10 +232,10 @@ int tep_pid_is_registered(struct tep_handle *pevent, int pid)
  * we must add this pid. This is much slower than when cmdlines
  * are added before the array is initialized.
  */
-static int add_new_comm(struct tep_handle *pevent,
+static int add_new_comm(struct tep_handle *tep,
 			const char *comm, int pid, bool override)
 {
-	struct tep_cmdline *cmdlines = pevent->cmdlines;
+	struct tep_cmdline *cmdlines = tep->cmdlines;
 	struct tep_cmdline *cmdline;
 	struct tep_cmdline key;
 	char *new_comm;
@@ -246,8 +246,8 @@ static int add_new_comm(struct tep_handle *pevent,
 	/* avoid duplicates */
 	key.pid = pid;
 
-	cmdline = bsearch(&key, pevent->cmdlines, pevent->cmdline_count,
-		       sizeof(*pevent->cmdlines), cmdline_cmp);
+	cmdline = bsearch(&key, tep->cmdlines, tep->cmdline_count,
+			  sizeof(*tep->cmdlines), cmdline_cmp);
 	if (cmdline) {
 		if (!override) {
 			errno = EEXIST;
@@ -264,37 +264,37 @@ static int add_new_comm(struct tep_handle *pevent,
 		return 0;
 	}
 
-	cmdlines = realloc(cmdlines, sizeof(*cmdlines) * (pevent->cmdline_count + 1));
+	cmdlines = realloc(cmdlines, sizeof(*cmdlines) * (tep->cmdline_count + 1));
 	if (!cmdlines) {
 		errno = ENOMEM;
 		return -1;
 	}
 
-	cmdlines[pevent->cmdline_count].comm = strdup(comm);
-	if (!cmdlines[pevent->cmdline_count].comm) {
+	cmdlines[tep->cmdline_count].comm = strdup(comm);
+	if (!cmdlines[tep->cmdline_count].comm) {
 		free(cmdlines);
 		errno = ENOMEM;
 		return -1;
 	}
 
-	cmdlines[pevent->cmdline_count].pid = pid;
+	cmdlines[tep->cmdline_count].pid = pid;
 		
-	if (cmdlines[pevent->cmdline_count].comm)
-		pevent->cmdline_count++;
+	if (cmdlines[tep->cmdline_count].comm)
+		tep->cmdline_count++;
 
-	qsort(cmdlines, pevent->cmdline_count, sizeof(*cmdlines), cmdline_cmp);
-	pevent->cmdlines = cmdlines;
+	qsort(cmdlines, tep->cmdline_count, sizeof(*cmdlines), cmdline_cmp);
+	tep->cmdlines = cmdlines;
 
 	return 0;
 }
 
-static int _tep_register_comm(struct tep_handle *pevent,
+static int _tep_register_comm(struct tep_handle *tep,
 			      const char *comm, int pid, bool override)
 {
 	struct cmdline_list *item;
 
-	if (pevent->cmdlines)
-		return add_new_comm(pevent, comm, pid, override);
+	if (tep->cmdlines)
+		return add_new_comm(tep, comm, pid, override);
 
 	item = malloc(sizeof(*item));
 	if (!item)
@@ -309,17 +309,17 @@ static int _tep_register_comm(struct tep_handle *pevent,
 		return -1;
 	}
 	item->pid = pid;
-	item->next = pevent->cmdlist;
+	item->next = tep->cmdlist;
 
-	pevent->cmdlist = item;
-	pevent->cmdline_count++;
+	tep->cmdlist = item;
+	tep->cmdline_count++;
 
 	return 0;
 }
 
 /**
  * tep_register_comm - register a pid / comm mapping
- * @pevent: handle for the pevent
+ * @tep: a handle to the trace event parser context
  * @comm: the command line to register
  * @pid: the pid to map the command line to
  *
@@ -327,14 +327,14 @@ static int _tep_register_comm(struct tep_handle *pevent,
  * a given pid. The comm is duplicated. If a command with the same pid
  * already exist, -1 is returned and errno is set to EEXIST
  */
-int tep_register_comm(struct tep_handle *pevent, const char *comm, int pid)
+int tep_register_comm(struct tep_handle *tep, const char *comm, int pid)
 {
-	return _tep_register_comm(pevent, comm, pid, false);
+	return _tep_register_comm(tep, comm, pid, false);
 }
 
 /**
  * tep_override_comm - register a pid / comm mapping
- * @pevent: handle for the pevent
+ * @tep: a handle to the trace event parser context
  * @comm: the command line to register
  * @pid: the pid to map the command line to
  *
@@ -342,19 +342,19 @@ int tep_register_comm(struct tep_handle *pevent, const char *comm, int pid)
  * a given pid. The comm is duplicated. If a command with the same pid
  * already exist, the command string is udapted with the new one
  */
-int tep_override_comm(struct tep_handle *pevent, const char *comm, int pid)
+int tep_override_comm(struct tep_handle *tep, const char *comm, int pid)
 {
-	if (!pevent->cmdlines && cmdline_init(pevent)) {
+	if (!tep->cmdlines && cmdline_init(tep)) {
 		errno = ENOMEM;
 		return -1;
 	}
-	return _tep_register_comm(pevent, comm, pid, true);
+	return _tep_register_comm(tep, comm, pid, true);
 }
 
-int tep_register_trace_clock(struct tep_handle *pevent, const char *trace_clock)
+int tep_register_trace_clock(struct tep_handle *tep, const char *trace_clock)
 {
-	pevent->trace_clock = strdup(trace_clock);
-	if (!pevent->trace_clock) {
+	tep->trace_clock = strdup(trace_clock);
+	if (!tep->trace_clock) {
 		errno = ENOMEM;
 		return -1;
 	}
@@ -408,18 +408,18 @@ static int func_bcmp(const void *a, const void *b)
 	return 1;
 }
 
-static int func_map_init(struct tep_handle *pevent)
+static int func_map_init(struct tep_handle *tep)
 {
 	struct func_list *funclist;
 	struct func_list *item;
 	struct func_map *func_map;
 	int i;
 
-	func_map = malloc(sizeof(*func_map) * (pevent->func_count + 1));
+	func_map = malloc(sizeof(*func_map) * (tep->func_count + 1));
 	if (!func_map)
 		return -1;
 
-	funclist = pevent->funclist;
+	funclist = tep->funclist;
 
 	i = 0;
 	while (funclist) {
@@ -432,34 +432,34 @@ static int func_map_init(struct tep_handle *pevent)
 		free(item);
 	}
 
-	qsort(func_map, pevent->func_count, sizeof(*func_map), func_cmp);
+	qsort(func_map, tep->func_count, sizeof(*func_map), func_cmp);
 
 	/*
 	 * Add a special record at the end.
 	 */
-	func_map[pevent->func_count].func = NULL;
-	func_map[pevent->func_count].addr = 0;
-	func_map[pevent->func_count].mod = NULL;
+	func_map[tep->func_count].func = NULL;
+	func_map[tep->func_count].addr = 0;
+	func_map[tep->func_count].mod = NULL;
 
-	pevent->func_map = func_map;
-	pevent->funclist = NULL;
+	tep->func_map = func_map;
+	tep->funclist = NULL;
 
 	return 0;
 }
 
 static struct func_map *
-__find_func(struct tep_handle *pevent, unsigned long long addr)
+__find_func(struct tep_handle *tep, unsigned long long addr)
 {
 	struct func_map *func;
 	struct func_map key;
 
-	if (!pevent->func_map)
-		func_map_init(pevent);
+	if (!tep->func_map)
+		func_map_init(tep);
 
 	key.addr = addr;
 
-	func = bsearch(&key, pevent->func_map, pevent->func_count,
-		       sizeof(*pevent->func_map), func_bcmp);
+	func = bsearch(&key, tep->func_map, tep->func_count,
+		       sizeof(*tep->func_map), func_bcmp);
 
 	return func;
 }
@@ -472,15 +472,14 @@ struct func_resolver {
 
 /**
  * tep_set_function_resolver - set an alternative function resolver
- * @pevent: handle for the pevent
+ * @tep: a handle to the trace event parser context
  * @resolver: function to be used
  * @priv: resolver function private state.
  *
  * Some tools may have already a way to resolve kernel functions, allow them to
- * keep using it instead of duplicating all the entries inside
- * pevent->funclist.
+ * keep using it instead of duplicating all the entries inside tep->funclist.
  */
-int tep_set_function_resolver(struct tep_handle *pevent,
+int tep_set_function_resolver(struct tep_handle *tep,
 			      tep_func_resolver_t *func, void *priv)
 {
 	struct func_resolver *resolver = malloc(sizeof(*resolver));
@@ -491,38 +490,38 @@ int tep_set_function_resolver(struct tep_handle *pevent,
 	resolver->func = func;
 	resolver->priv = priv;
 
-	free(pevent->func_resolver);
-	pevent->func_resolver = resolver;
+	free(tep->func_resolver);
+	tep->func_resolver = resolver;
 
 	return 0;
 }
 
 /**
  * tep_reset_function_resolver - reset alternative function resolver
- * @pevent: handle for the pevent
+ * @tep: a handle to the trace event parser context
  *
  * Stop using whatever alternative resolver was set, use the default
  * one instead.
  */
-void tep_reset_function_resolver(struct tep_handle *pevent)
+void tep_reset_function_resolver(struct tep_handle *tep)
 {
-	free(pevent->func_resolver);
-	pevent->func_resolver = NULL;
+	free(tep->func_resolver);
+	tep->func_resolver = NULL;
 }
 
 static struct func_map *
-find_func(struct tep_handle *pevent, unsigned long long addr)
+find_func(struct tep_handle *tep, unsigned long long addr)
 {
 	struct func_map *map;
 
-	if (!pevent->func_resolver)
-		return __find_func(pevent, addr);
+	if (!tep->func_resolver)
+		return __find_func(tep, addr);
 
-	map = &pevent->func_resolver->map;
+	map = &tep->func_resolver->map;
 	map->mod  = NULL;
 	map->addr = addr;
-	map->func = pevent->func_resolver->func(pevent->func_resolver->priv,
-						&map->addr, &map->mod);
+	map->func = tep->func_resolver->func(tep->func_resolver->priv,
+					     &map->addr, &map->mod);
 	if (map->func == NULL)
 		return NULL;
 
@@ -531,18 +530,18 @@ find_func(struct tep_handle *pevent, unsigned long long addr)
 
 /**
  * tep_find_function - find a function by a given address
- * @pevent: handle for the pevent
+ * @tep: a handle to the trace event parser context
  * @addr: the address to find the function with
  *
  * Returns a pointer to the function stored that has the given
  * address. Note, the address does not have to be exact, it
  * will select the function that would contain the address.
  */
-const char *tep_find_function(struct tep_handle *pevent, unsigned long long addr)
+const char *tep_find_function(struct tep_handle *tep, unsigned long long addr)
 {
 	struct func_map *map;
 
-	map = find_func(pevent, addr);
+	map = find_func(tep, addr);
 	if (!map)
 		return NULL;
 
@@ -551,7 +550,7 @@ const char *tep_find_function(struct tep_handle *pevent, unsigned long long addr
 
 /**
  * tep_find_function_address - find a function address by a given address
- * @pevent: handle for the pevent
+ * @tep: a handle to the trace event parser context
  * @addr: the address to find the function with
  *
  * Returns the address the function starts at. This can be used in
@@ -559,11 +558,11 @@ const char *tep_find_function(struct tep_handle *pevent, unsigned long long addr
  * name and the function offset.
  */
 unsigned long long
-tep_find_function_address(struct tep_handle *pevent, unsigned long long addr)
+tep_find_function_address(struct tep_handle *tep, unsigned long long addr)
 {
 	struct func_map *map;
 
-	map = find_func(pevent, addr);
+	map = find_func(tep, addr);
 	if (!map)
 		return 0;
 
@@ -572,7 +571,7 @@ tep_find_function_address(struct tep_handle *pevent, unsigned long long addr)
 
 /**
  * tep_register_function - register a function with a given address
- * @pevent: handle for the pevent
+ * @tep: a handle to the trace event parser context
  * @function: the function name to register
  * @addr: the address the function starts at
  * @mod: the kernel module the function may be in (NULL for none)
@@ -580,7 +579,7 @@ tep_find_function_address(struct tep_handle *pevent, unsigned long long addr)
  * This registers a function name with an address and module.
  * The @func passed in is duplicated.
  */
-int tep_register_function(struct tep_handle *pevent, char *func,
+int tep_register_function(struct tep_handle *tep, char *func,
 			  unsigned long long addr, char *mod)
 {
 	struct func_list *item = malloc(sizeof(*item));
@@ -588,7 +587,7 @@ int tep_register_function(struct tep_handle *pevent, char *func,
 	if (!item)
 		return -1;
 
-	item->next = pevent->funclist;
+	item->next = tep->funclist;
 	item->func = strdup(func);
 	if (!item->func)
 		goto out_free;
@@ -601,8 +600,8 @@ int tep_register_function(struct tep_handle *pevent, char *func,
 		item->mod = NULL;
 	item->addr = addr;
 
-	pevent->funclist = item;
-	pevent->func_count++;
+	tep->funclist = item;
+	tep->func_count++;
 
 	return 0;
 
@@ -617,23 +616,23 @@ out_free:
 
 /**
  * tep_print_funcs - print out the stored functions
- * @pevent: handle for the pevent
+ * @tep: a handle to the trace event parser context
  *
  * This prints out the stored functions.
  */
-void tep_print_funcs(struct tep_handle *pevent)
+void tep_print_funcs(struct tep_handle *tep)
 {
 	int i;
 
-	if (!pevent->func_map)
-		func_map_init(pevent);
+	if (!tep->func_map)
+		func_map_init(tep);
 
-	for (i = 0; i < (int)pevent->func_count; i++) {
+	for (i = 0; i < (int)tep->func_count; i++) {
 		printf("%016llx %s",
-		       pevent->func_map[i].addr,
-		       pevent->func_map[i].func);
-		if (pevent->func_map[i].mod)
-			printf(" [%s]\n", pevent->func_map[i].mod);
+		       tep->func_map[i].addr,
+		       tep->func_map[i].func);
+		if (tep->func_map[i].mod)
+			printf(" [%s]\n", tep->func_map[i].mod);
 		else
 			printf("\n");
 	}
@@ -663,18 +662,18 @@ static int printk_cmp(const void *a, const void *b)
 	return 0;
 }
 
-static int printk_map_init(struct tep_handle *pevent)
+static int printk_map_init(struct tep_handle *tep)
 {
 	struct printk_list *printklist;
 	struct printk_list *item;
 	struct printk_map *printk_map;
 	int i;
 
-	printk_map = malloc(sizeof(*printk_map) * (pevent->printk_count + 1));
+	printk_map = malloc(sizeof(*printk_map) * (tep->printk_count + 1));
 	if (!printk_map)
 		return -1;
 
-	printklist = pevent->printklist;
+	printklist = tep->printklist;
 
 	i = 0;
 	while (printklist) {
@@ -686,41 +685,41 @@ static int printk_map_init(struct tep_handle *pevent)
 		free(item);
 	}
 
-	qsort(printk_map, pevent->printk_count, sizeof(*printk_map), printk_cmp);
+	qsort(printk_map, tep->printk_count, sizeof(*printk_map), printk_cmp);
 
-	pevent->printk_map = printk_map;
-	pevent->printklist = NULL;
+	tep->printk_map = printk_map;
+	tep->printklist = NULL;
 
 	return 0;
 }
 
 static struct printk_map *
-find_printk(struct tep_handle *pevent, unsigned long long addr)
+find_printk(struct tep_handle *tep, unsigned long long addr)
 {
 	struct printk_map *printk;
 	struct printk_map key;
 
-	if (!pevent->printk_map && printk_map_init(pevent))
+	if (!tep->printk_map && printk_map_init(tep))
 		return NULL;
 
 	key.addr = addr;
 
-	printk = bsearch(&key, pevent->printk_map, pevent->printk_count,
-			 sizeof(*pevent->printk_map), printk_cmp);
+	printk = bsearch(&key, tep->printk_map, tep->printk_count,
+			 sizeof(*tep->printk_map), printk_cmp);
 
 	return printk;
 }
 
 /**
  * tep_register_print_string - register a string by its address
- * @pevent: handle for the pevent
+ * @tep: a handle to the trace event parser context
  * @fmt: the string format to register
  * @addr: the address the string was located at
  *
  * This registers a string by the address it was stored in the kernel.
  * The @fmt passed in is duplicated.
  */
-int tep_register_print_string(struct tep_handle *pevent, const char *fmt,
+int tep_register_print_string(struct tep_handle *tep, const char *fmt,
 			      unsigned long long addr)
 {
 	struct printk_list *item = malloc(sizeof(*item));
@@ -729,7 +728,7 @@ int tep_register_print_string(struct tep_handle *pevent, const char *fmt,
 	if (!item)
 		return -1;
 
-	item->next = pevent->printklist;
+	item->next = tep->printklist;
 	item->addr = addr;
 
 	/* Strip off quotes and '\n' from the end */
@@ -747,8 +746,8 @@ int tep_register_print_string(struct tep_handle *pevent, const char *fmt,
 	if (strcmp(p, "\\n") == 0)
 		*p = 0;
 
-	pevent->printklist = item;
-	pevent->printk_count++;
+	tep->printklist = item;
+	tep->printk_count++;
 
 	return 0;
 
@@ -760,21 +759,21 @@ out_free:
 
 /**
  * tep_print_printk - print out the stored strings
- * @pevent: handle for the pevent
+ * @tep: a handle to the trace event parser context
  *
  * This prints the string formats that were stored.
  */
-void tep_print_printk(struct tep_handle *pevent)
+void tep_print_printk(struct tep_handle *tep)
 {
 	int i;
 
-	if (!pevent->printk_map)
-		printk_map_init(pevent);
+	if (!tep->printk_map)
+		printk_map_init(tep);
 
-	for (i = 0; i < (int)pevent->printk_count; i++) {
+	for (i = 0; i < (int)tep->printk_count; i++) {
 		printf("%016llx %s\n",
-		       pevent->printk_map[i].addr,
-		       pevent->printk_map[i].printk);
+		       tep->printk_map[i].addr,
+		       tep->printk_map[i].printk);
 	}
 }
 
@@ -783,29 +782,29 @@ static struct tep_event *alloc_event(void)
 	return calloc(1, sizeof(struct tep_event));
 }
 
-static int add_event(struct tep_handle *pevent, struct tep_event *event)
+static int add_event(struct tep_handle *tep, struct tep_event *event)
 {
 	int i;
-	struct tep_event **events = realloc(pevent->events, sizeof(event) *
-					    (pevent->nr_events + 1));
+	struct tep_event **events = realloc(tep->events, sizeof(event) *
+					    (tep->nr_events + 1));
 	if (!events)
 		return -1;
 
-	pevent->events = events;
+	tep->events = events;
 
-	for (i = 0; i < pevent->nr_events; i++) {
-		if (pevent->events[i]->id > event->id)
+	for (i = 0; i < tep->nr_events; i++) {
+		if (tep->events[i]->id > event->id)
 			break;
 	}
-	if (i < pevent->nr_events)
-		memmove(&pevent->events[i + 1],
-			&pevent->events[i],
-			sizeof(event) * (pevent->nr_events - i));
+	if (i < tep->nr_events)
+		memmove(&tep->events[i + 1],
+			&tep->events[i],
+			sizeof(event) * (tep->nr_events - i));
 
-	pevent->events[i] = event;
-	pevent->nr_events++;
+	tep->events[i] = event;
+	tep->nr_events++;
 
-	event->pevent = pevent;
+	event->tep = tep;
 
 	return 0;
 }
@@ -1184,7 +1183,7 @@ static enum tep_event_type read_token(char **tok)
 }
 
 /**
- * tep_read_token - access to utilities to use the pevent parser
+ * tep_read_token - access to utilities to use the tep parser
  * @tok: The token to return
  *
  * This will parse tokens from the string given by
@@ -1657,8 +1656,8 @@ static int event_read_fields(struct tep_event *event, struct tep_format_field **
 			else if (field->flags & TEP_FIELD_IS_STRING)
 				field->elementsize = 1;
 			else if (field->flags & TEP_FIELD_IS_LONG)
-				field->elementsize = event->pevent ?
-						     event->pevent->long_size :
+				field->elementsize = event->tep ?
+						     event->tep->long_size :
 						     sizeof(long);
 		} else
 			field->elementsize = field->size;
@@ -2233,7 +2232,7 @@ eval_type_str(unsigned long long val, const char *type, int pointer)
 		return val & 0xffffffff;
 
 	if (strcmp(type, "u64") == 0 ||
-	    strcmp(type, "s64"))
+	    strcmp(type, "s64") == 0)
 		return val;
 
 	if (strcmp(type, "s8") == 0)
@@ -2942,14 +2941,14 @@ process_bitmask(struct tep_event *event __maybe_unused, struct tep_print_arg *ar
 }
 
 static struct tep_function_handler *
-find_func_handler(struct tep_handle *pevent, char *func_name)
+find_func_handler(struct tep_handle *tep, char *func_name)
 {
 	struct tep_function_handler *func;
 
-	if (!pevent)
+	if (!tep)
 		return NULL;
 
-	for (func = pevent->func_handlers; func; func = func->next) {
+	for (func = tep->func_handlers; func; func = func->next) {
 		if (strcmp(func->name, func_name) == 0)
 			break;
 	}
@@ -2957,12 +2956,12 @@ find_func_handler(struct tep_handle *pevent, char *func_name)
 	return func;
 }
 
-static void remove_func_handler(struct tep_handle *pevent, char *func_name)
+static void remove_func_handler(struct tep_handle *tep, char *func_name)
 {
 	struct tep_function_handler *func;
 	struct tep_function_handler **next;
 
-	next = &pevent->func_handlers;
+	next = &tep->func_handlers;
 	while ((func = *next)) {
 		if (strcmp(func->name, func_name) == 0) {
 			*next = func->next;
@@ -3076,7 +3075,7 @@ process_function(struct tep_event *event, struct tep_print_arg *arg,
 		return process_dynamic_array_len(event, arg, tok);
 	}
 
-	func = find_func_handler(event->pevent, token);
+	func = find_func_handler(event->tep, token);
 	if (func) {
 		free_token(token);
 		return process_func_handler(event, func, arg, tok);
@@ -3357,14 +3356,14 @@ tep_find_any_field(struct tep_event *event, const char *name)
 
 /**
  * tep_read_number - read a number from data
- * @pevent: handle for the pevent
+ * @tep: a handle to the trace event parser context
  * @ptr: the raw data
  * @size: the size of the data that holds the number
  *
  * Returns the number (converted to host) from the
  * raw data.
  */
-unsigned long long tep_read_number(struct tep_handle *pevent,
+unsigned long long tep_read_number(struct tep_handle *tep,
 				   const void *ptr, int size)
 {
 	unsigned long long val;
@@ -3373,12 +3372,12 @@ unsigned long long tep_read_number(struct tep_handle *pevent,
 	case 1:
 		return *(unsigned char *)ptr;
 	case 2:
-		return tep_data2host2(pevent, *(unsigned short *)ptr);
+		return tep_data2host2(tep, *(unsigned short *)ptr);
 	case 4:
-		return tep_data2host4(pevent, *(unsigned int *)ptr);
+		return tep_data2host4(tep, *(unsigned int *)ptr);
 	case 8:
 		memcpy(&val, (ptr), sizeof(unsigned long long));
-		return tep_data2host8(pevent, val);
+		return tep_data2host8(tep, val);
 	default:
 		/* BUG! */
 		return 0;
@@ -3406,7 +3405,7 @@ int tep_read_number_field(struct tep_format_field *field, const void *data,
 	case 2:
 	case 4:
 	case 8:
-		*value = tep_read_number(field->event->pevent,
+		*value = tep_read_number(field->event->tep,
 					 data + field->offset, field->size);
 		return 0;
 	default:
@@ -3414,7 +3413,7 @@ int tep_read_number_field(struct tep_format_field *field, const void *data,
 	}
 }
 
-static int get_common_info(struct tep_handle *pevent,
+static int get_common_info(struct tep_handle *tep,
 			   const char *type, int *offset, int *size)
 {
 	struct tep_event *event;
@@ -3424,12 +3423,12 @@ static int get_common_info(struct tep_handle *pevent,
 	 * All events should have the same common elements.
 	 * Pick any event to find where the type is;
 	 */
-	if (!pevent->events) {
+	if (!tep->events) {
 		do_warning("no event_list!");
 		return -1;
 	}
 
-	event = pevent->events[0];
+	event = tep->events[0];
 	field = tep_find_common_field(event, type);
 	if (!field)
 		return -1;
@@ -3440,58 +3439,58 @@ static int get_common_info(struct tep_handle *pevent,
 	return 0;
 }
 
-static int __parse_common(struct tep_handle *pevent, void *data,
+static int __parse_common(struct tep_handle *tep, void *data,
 			  int *size, int *offset, const char *name)
 {
 	int ret;
 
 	if (!*size) {
-		ret = get_common_info(pevent, name, offset, size);
+		ret = get_common_info(tep, name, offset, size);
 		if (ret < 0)
 			return ret;
 	}
-	return tep_read_number(pevent, data + *offset, *size);
+	return tep_read_number(tep, data + *offset, *size);
 }
 
-static int trace_parse_common_type(struct tep_handle *pevent, void *data)
+static int trace_parse_common_type(struct tep_handle *tep, void *data)
 {
-	return __parse_common(pevent, data,
-			      &pevent->type_size, &pevent->type_offset,
+	return __parse_common(tep, data,
+			      &tep->type_size, &tep->type_offset,
 			      "common_type");
 }
 
-static int parse_common_pid(struct tep_handle *pevent, void *data)
+static int parse_common_pid(struct tep_handle *tep, void *data)
 {
-	return __parse_common(pevent, data,
-			      &pevent->pid_size, &pevent->pid_offset,
+	return __parse_common(tep, data,
+			      &tep->pid_size, &tep->pid_offset,
 			      "common_pid");
 }
 
-static int parse_common_pc(struct tep_handle *pevent, void *data)
+static int parse_common_pc(struct tep_handle *tep, void *data)
 {
-	return __parse_common(pevent, data,
-			      &pevent->pc_size, &pevent->pc_offset,
+	return __parse_common(tep, data,
+			      &tep->pc_size, &tep->pc_offset,
 			      "common_preempt_count");
 }
 
-static int parse_common_flags(struct tep_handle *pevent, void *data)
+static int parse_common_flags(struct tep_handle *tep, void *data)
 {
-	return __parse_common(pevent, data,
-			      &pevent->flags_size, &pevent->flags_offset,
+	return __parse_common(tep, data,
+			      &tep->flags_size, &tep->flags_offset,
 			      "common_flags");
 }
 
-static int parse_common_lock_depth(struct tep_handle *pevent, void *data)
+static int parse_common_lock_depth(struct tep_handle *tep, void *data)
 {
-	return __parse_common(pevent, data,
-			      &pevent->ld_size, &pevent->ld_offset,
+	return __parse_common(tep, data,
+			      &tep->ld_size, &tep->ld_offset,
 			      "common_lock_depth");
 }
 
-static int parse_common_migrate_disable(struct tep_handle *pevent, void *data)
+static int parse_common_migrate_disable(struct tep_handle *tep, void *data)
 {
-	return __parse_common(pevent, data,
-			      &pevent->ld_size, &pevent->ld_offset,
+	return __parse_common(tep, data,
+			      &tep->ld_size, &tep->ld_offset,
 			      "common_migrate_disable");
 }
 
@@ -3499,28 +3498,28 @@ static int events_id_cmp(const void *a, const void *b);
 
 /**
  * tep_find_event - find an event by given id
- * @pevent: a handle to the pevent
+ * @tep: a handle to the trace event parser context
  * @id: the id of the event
  *
  * Returns an event that has a given @id.
  */
-struct tep_event *tep_find_event(struct tep_handle *pevent, int id)
+struct tep_event *tep_find_event(struct tep_handle *tep, int id)
 {
 	struct tep_event **eventptr;
 	struct tep_event key;
 	struct tep_event *pkey = &key;
 
 	/* Check cache first */
-	if (pevent->last_event && pevent->last_event->id == id)
-		return pevent->last_event;
+	if (tep->last_event && tep->last_event->id == id)
+		return tep->last_event;
 
 	key.id = id;
 
-	eventptr = bsearch(&pkey, pevent->events, pevent->nr_events,
-			   sizeof(*pevent->events), events_id_cmp);
+	eventptr = bsearch(&pkey, tep->events, tep->nr_events,
+			   sizeof(*tep->events), events_id_cmp);
 
 	if (eventptr) {
-		pevent->last_event = *eventptr;
+		tep->last_event = *eventptr;
 		return *eventptr;
 	}
 
@@ -3529,7 +3528,7 @@ struct tep_event *tep_find_event(struct tep_handle *pevent, int id)
 
 /**
  * tep_find_event_by_name - find an event by given name
- * @pevent: a handle to the pevent
+ * @tep: a handle to the trace event parser context
  * @sys: the system name to search for
  * @name: the name of the event to search for
  *
@@ -3537,19 +3536,19 @@ struct tep_event *tep_find_event(struct tep_handle *pevent, int id)
  * @sys. If @sys is NULL the first event with @name is returned.
  */
 struct tep_event *
-tep_find_event_by_name(struct tep_handle *pevent,
+tep_find_event_by_name(struct tep_handle *tep,
 		       const char *sys, const char *name)
 {
 	struct tep_event *event = NULL;
 	int i;
 
-	if (pevent->last_event &&
-	    strcmp(pevent->last_event->name, name) == 0 &&
-	    (!sys || strcmp(pevent->last_event->system, sys) == 0))
-		return pevent->last_event;
+	if (tep->last_event &&
+	    strcmp(tep->last_event->name, name) == 0 &&
+	    (!sys || strcmp(tep->last_event->system, sys) == 0))
+		return tep->last_event;
 
-	for (i = 0; i < pevent->nr_events; i++) {
-		event = pevent->events[i];
+	for (i = 0; i < tep->nr_events; i++) {
+		event = tep->events[i];
 		if (strcmp(event->name, name) == 0) {
 			if (!sys)
 				break;
@@ -3557,17 +3556,17 @@ tep_find_event_by_name(struct tep_handle *pevent,
 				break;
 		}
 	}
-	if (i == pevent->nr_events)
+	if (i == tep->nr_events)
 		event = NULL;
 
-	pevent->last_event = event;
+	tep->last_event = event;
 	return event;
 }
 
 static unsigned long long
 eval_num_arg(void *data, int size, struct tep_event *event, struct tep_print_arg *arg)
 {
-	struct tep_handle *pevent = event->pevent;
+	struct tep_handle *tep = event->tep;
 	unsigned long long val = 0;
 	unsigned long long left, right;
 	struct tep_print_arg *typearg = NULL;
@@ -3589,7 +3588,7 @@ eval_num_arg(void *data, int size, struct tep_event *event, struct tep_print_arg
 			
 		}
 		/* must be a number */
-		val = tep_read_number(pevent, data + arg->field.field->offset,
+		val = tep_read_number(tep, data + arg->field.field->offset,
 				      arg->field.field->size);
 		break;
 	case TEP_PRINT_FLAGS:
@@ -3629,11 +3628,11 @@ eval_num_arg(void *data, int size, struct tep_event *event, struct tep_print_arg
 			}
 
 			/* Default to long size */
-			field_size = pevent->long_size;
+			field_size = tep->long_size;
 
 			switch (larg->type) {
 			case TEP_PRINT_DYNAMIC_ARRAY:
-				offset = tep_read_number(pevent,
+				offset = tep_read_number(tep,
 						   data + larg->dynarray.field->offset,
 						   larg->dynarray.field->size);
 				if (larg->dynarray.field->elementsize)
@@ -3662,7 +3661,7 @@ eval_num_arg(void *data, int size, struct tep_event *event, struct tep_print_arg
 			default:
 				goto default_op; /* oops, all bets off */
 			}
-			val = tep_read_number(pevent,
+			val = tep_read_number(tep,
 					      data + offset, field_size);
 			if (typearg)
 				val = eval_type(val, typearg, 1);
@@ -3763,7 +3762,7 @@ eval_num_arg(void *data, int size, struct tep_event *event, struct tep_print_arg
 		}
 		break;
 	case TEP_PRINT_DYNAMIC_ARRAY_LEN:
-		offset = tep_read_number(pevent,
+		offset = tep_read_number(tep,
 					 data + arg->dynarray.field->offset,
 					 arg->dynarray.field->size);
 		/*
@@ -3775,7 +3774,7 @@ eval_num_arg(void *data, int size, struct tep_event *event, struct tep_print_arg
 		break;
 	case TEP_PRINT_DYNAMIC_ARRAY:
 		/* Without [], we pass the address to the dynamic data */
-		offset = tep_read_number(pevent,
+		offset = tep_read_number(tep,
 					 data + arg->dynarray.field->offset,
 					 arg->dynarray.field->size);
 		/*
@@ -3850,7 +3849,7 @@ static void print_str_to_seq(struct trace_seq *s, const char *format,
 		trace_seq_printf(s, format, str);
 }
 
-static void print_bitmask_to_seq(struct tep_handle *pevent,
+static void print_bitmask_to_seq(struct tep_handle *tep,
 				 struct trace_seq *s, const char *format,
 				 int len_arg, const void *data, int size)
 {
@@ -3882,7 +3881,7 @@ static void print_bitmask_to_seq(struct tep_handle *pevent,
 		 * In the kernel, this is an array of long words, thus
 		 * endianness is very important.
 		 */
-		if (pevent->file_bigendian)
+		if (tep->file_bigendian)
 			index = size - (len + 1);
 		else
 			index = len;
@@ -3908,7 +3907,7 @@ static void print_str_arg(struct trace_seq *s, void *data, int size,
 			  struct tep_event *event, const char *format,
 			  int len_arg, struct tep_print_arg *arg)
 {
-	struct tep_handle *pevent = event->pevent;
+	struct tep_handle *tep = event->tep;
 	struct tep_print_flag_sym *flag;
 	struct tep_format_field *field;
 	struct printk_map *printk;
@@ -3945,7 +3944,7 @@ static void print_str_arg(struct trace_seq *s, void *data, int size,
 		 * is a pointer.
 		 */
 		if (!(field->flags & TEP_FIELD_IS_ARRAY) &&
-		    field->size == pevent->long_size) {
+		    field->size == tep->long_size) {
 
 			/* Handle heterogeneous recording and processing
 			 * architectures
@@ -3960,12 +3959,12 @@ static void print_str_arg(struct trace_seq *s, void *data, int size,
 			 * on 32-bit devices:
 			 * In this case, 64 bits must be read.
 			 */
-			addr = (pevent->long_size == 8) ?
+			addr = (tep->long_size == 8) ?
 				*(unsigned long long *)(data + field->offset) :
 				(unsigned long long)*(unsigned int *)(data + field->offset);
 
 			/* Check if it matches a print format */
-			printk = find_printk(pevent, addr);
+			printk = find_printk(tep, addr);
 			if (printk)
 				trace_seq_puts(s, printk->printk);
 			else
@@ -4022,7 +4021,7 @@ static void print_str_arg(struct trace_seq *s, void *data, int size,
 	case TEP_PRINT_HEX_STR:
 		if (arg->hex.field->type == TEP_PRINT_DYNAMIC_ARRAY) {
 			unsigned long offset;
-			offset = tep_read_number(pevent,
+			offset = tep_read_number(tep,
 				data + arg->hex.field->dynarray.field->offset,
 				arg->hex.field->dynarray.field->size);
 			hex = data + (offset & 0xffff);
@@ -4053,7 +4052,7 @@ static void print_str_arg(struct trace_seq *s, void *data, int size,
 			unsigned long offset;
 			struct tep_format_field *field =
 				arg->int_array.field->dynarray.field;
-			offset = tep_read_number(pevent,
+			offset = tep_read_number(tep,
 						 data + field->offset,
 						 field->size);
 			num = data + (offset & 0xffff);
@@ -4104,7 +4103,7 @@ static void print_str_arg(struct trace_seq *s, void *data, int size,
 			f = tep_find_any_field(event, arg->string.string);
 			arg->string.offset = f->offset;
 		}
-		str_offset = tep_data2host4(pevent, *(unsigned int *)(data + arg->string.offset));
+		str_offset = tep_data2host4(tep, *(unsigned int *)(data + arg->string.offset));
 		str_offset &= 0xffff;
 		print_str_to_seq(s, format, len_arg, ((char *)data) + str_offset);
 		break;
@@ -4122,10 +4121,10 @@ static void print_str_arg(struct trace_seq *s, void *data, int size,
 			f = tep_find_any_field(event, arg->bitmask.bitmask);
 			arg->bitmask.offset = f->offset;
 		}
-		bitmask_offset = tep_data2host4(pevent, *(unsigned int *)(data + arg->bitmask.offset));
+		bitmask_offset = tep_data2host4(tep, *(unsigned int *)(data + arg->bitmask.offset));
 		bitmask_size = bitmask_offset >> 16;
 		bitmask_offset &= 0xffff;
-		print_bitmask_to_seq(pevent, s, format, len_arg,
+		print_bitmask_to_seq(tep, s, format, len_arg,
 				     data + bitmask_offset, bitmask_size);
 		break;
 	}
@@ -4257,7 +4256,7 @@ static void free_args(struct tep_print_arg *args)
 
 static struct tep_print_arg *make_bprint_args(char *fmt, void *data, int size, struct tep_event *event)
 {
-	struct tep_handle *pevent = event->pevent;
+	struct tep_handle *tep = event->tep;
 	struct tep_format_field *field, *ip_field;
 	struct tep_print_arg *args, *arg, **next;
 	unsigned long long ip, val;
@@ -4265,8 +4264,8 @@ static struct tep_print_arg *make_bprint_args(char *fmt, void *data, int size, s
 	void *bptr;
 	int vsize = 0;
 
-	field = pevent->bprint_buf_field;
-	ip_field = pevent->bprint_ip_field;
+	field = tep->bprint_buf_field;
+	ip_field = tep->bprint_ip_field;
 
 	if (!field) {
 		field = tep_find_field(event, "buf");
@@ -4279,11 +4278,11 @@ static struct tep_print_arg *make_bprint_args(char *fmt, void *data, int size, s
 			do_warning_event(event, "can't find ip field for binary printk");
 			return NULL;
 		}
-		pevent->bprint_buf_field = field;
-		pevent->bprint_ip_field = ip_field;
+		tep->bprint_buf_field = field;
+		tep->bprint_ip_field = ip_field;
 	}
 
-	ip = tep_read_number(pevent, data + ip_field->offset, ip_field->size);
+	ip = tep_read_number(tep, data + ip_field->offset, ip_field->size);
 
 	/*
 	 * The first arg is the IP pointer.
@@ -4338,6 +4337,7 @@ static struct tep_print_arg *make_bprint_args(char *fmt, void *data, int size, s
 					case 'S':
 					case 'f':
 					case 'F':
+					case 'x':
 						break;
 					default:
 						/*
@@ -4360,7 +4360,7 @@ static struct tep_print_arg *make_bprint_args(char *fmt, void *data, int size, s
 					vsize = 4;
 					break;
 				case 1:
-					vsize = pevent->long_size;
+					vsize = tep->long_size;
 					break;
 				case 2:
 					vsize = 8;
@@ -4377,7 +4377,7 @@ static struct tep_print_arg *make_bprint_args(char *fmt, void *data, int size, s
 				/* the pointers are always 4 bytes aligned */
 				bptr = (void *)(((unsigned long)bptr + 3) &
 						~3);
-				val = tep_read_number(pevent, bptr, vsize);
+				val = tep_read_number(tep, bptr, vsize);
 				bptr += vsize;
 				arg = alloc_arg();
 				if (!arg) {
@@ -4434,13 +4434,13 @@ static char *
 get_bprint_format(void *data, int size __maybe_unused,
 		  struct tep_event *event)
 {
-	struct tep_handle *pevent = event->pevent;
+	struct tep_handle *tep = event->tep;
 	unsigned long long addr;
 	struct tep_format_field *field;
 	struct printk_map *printk;
 	char *format;
 
-	field = pevent->bprint_fmt_field;
+	field = tep->bprint_fmt_field;
 
 	if (!field) {
 		field = tep_find_field(event, "fmt");
@@ -4448,12 +4448,12 @@ get_bprint_format(void *data, int size __maybe_unused,
 			do_warning_event(event, "can't find format field for binary printk");
 			return NULL;
 		}
-		pevent->bprint_fmt_field = field;
+		tep->bprint_fmt_field = field;
 	}
 
-	addr = tep_read_number(pevent, data + field->offset, field->size);
+	addr = tep_read_number(tep, data + field->offset, field->size);
 
-	printk = find_printk(pevent, addr);
+	printk = find_printk(tep, addr);
 	if (!printk) {
 		if (asprintf(&format, "%%pf: (NO FORMAT FOUND at %llx)\n", addr) < 0)
 			return NULL;
@@ -4835,13 +4835,13 @@ void tep_print_field(struct trace_seq *s, void *data,
 {
 	unsigned long long val;
 	unsigned int offset, len, i;
-	struct tep_handle *pevent = field->event->pevent;
+	struct tep_handle *tep = field->event->tep;
 
 	if (field->flags & TEP_FIELD_IS_ARRAY) {
 		offset = field->offset;
 		len = field->size;
 		if (field->flags & TEP_FIELD_IS_DYNAMIC) {
-			val = tep_read_number(pevent, data + offset, len);
+			val = tep_read_number(tep, data + offset, len);
 			offset = val;
 			len = offset >> 16;
 			offset &= 0xffff;
@@ -4861,7 +4861,7 @@ void tep_print_field(struct trace_seq *s, void *data,
 			field->flags &= ~TEP_FIELD_IS_STRING;
 		}
 	} else {
-		val = tep_read_number(pevent, data + field->offset,
+		val = tep_read_number(tep, data + field->offset,
 				      field->size);
 		if (field->flags & TEP_FIELD_IS_POINTER) {
 			trace_seq_printf(s, "0x%llx", val);
@@ -4910,7 +4910,7 @@ void tep_print_fields(struct trace_seq *s, void *data,
 
 static void pretty_print(struct trace_seq *s, void *data, int size, struct tep_event *event)
 {
-	struct tep_handle *pevent = event->pevent;
+	struct tep_handle *tep = event->tep;
 	struct tep_print_fmt *print_fmt = &event->print_fmt;
 	struct tep_print_arg *arg = print_fmt->args;
 	struct tep_print_arg *args = NULL;
@@ -5002,7 +5002,7 @@ static void pretty_print(struct trace_seq *s, void *data, int size, struct tep_e
 			case '-':
 				goto cont_process;
 			case 'p':
-				if (pevent->long_size == 4)
+				if (tep->long_size == 4)
 					ls = 1;
 				else
 					ls = 2;
@@ -5063,7 +5063,7 @@ static void pretty_print(struct trace_seq *s, void *data, int size, struct tep_e
 				arg = arg->next;
 
 				if (show_func) {
-					func = find_func(pevent, val);
+					func = find_func(tep, val);
 					if (func) {
 						trace_seq_puts(s, func->func);
 						if (show_func == 'F')
@@ -5073,7 +5073,7 @@ static void pretty_print(struct trace_seq *s, void *data, int size, struct tep_e
 						break;
 					}
 				}
-				if (pevent->long_size == 8 && ls == 1 &&
+				if (tep->long_size == 8 && ls == 1 &&
 				    sizeof(long) != 8) {
 					char *p;
 
@@ -5171,8 +5171,8 @@ out_failed:
 }
 
 /**
- * tep_data_lat_fmt - parse the data for the latency format
- * @pevent: a handle to the pevent
+ * tep_data_latency_format - parse the data for the latency format
+ * @tep: a handle to the trace event parser context
  * @s: the trace_seq to write to
  * @record: the record to read from
  *
@@ -5180,8 +5180,8 @@ out_failed:
  * need rescheduling, in hard/soft interrupt, preempt count
  * and lock depth) and places it into the trace_seq.
  */
-void tep_data_lat_fmt(struct tep_handle *pevent,
-		      struct trace_seq *s, struct tep_record *record)
+void tep_data_latency_format(struct tep_handle *tep,
+			     struct trace_seq *s, struct tep_record *record)
 {
 	static int check_lock_depth = 1;
 	static int check_migrate_disable = 1;
@@ -5195,13 +5195,13 @@ void tep_data_lat_fmt(struct tep_handle *pevent,
 	int softirq;
 	void *data = record->data;
 
-	lat_flags = parse_common_flags(pevent, data);
-	pc = parse_common_pc(pevent, data);
+	lat_flags = parse_common_flags(tep, data);
+	pc = parse_common_pc(tep, data);
 	/* lock_depth may not always exist */
 	if (lock_depth_exists)
-		lock_depth = parse_common_lock_depth(pevent, data);
+		lock_depth = parse_common_lock_depth(tep, data);
 	else if (check_lock_depth) {
-		lock_depth = parse_common_lock_depth(pevent, data);
+		lock_depth = parse_common_lock_depth(tep, data);
 		if (lock_depth < 0)
 			check_lock_depth = 0;
 		else
@@ -5210,9 +5210,9 @@ void tep_data_lat_fmt(struct tep_handle *pevent,
 
 	/* migrate_disable may not always exist */
 	if (migrate_disable_exists)
-		migrate_disable = parse_common_migrate_disable(pevent, data);
+		migrate_disable = parse_common_migrate_disable(tep, data);
 	else if (check_migrate_disable) {
-		migrate_disable = parse_common_migrate_disable(pevent, data);
+		migrate_disable = parse_common_migrate_disable(tep, data);
 		if (migrate_disable < 0)
 			check_migrate_disable = 0;
 		else
@@ -5255,79 +5255,79 @@ void tep_data_lat_fmt(struct tep_handle *pevent,
 
 /**
  * tep_data_type - parse out the given event type
- * @pevent: a handle to the pevent
+ * @tep: a handle to the trace event parser context
  * @rec: the record to read from
  *
  * This returns the event id from the @rec.
  */
-int tep_data_type(struct tep_handle *pevent, struct tep_record *rec)
+int tep_data_type(struct tep_handle *tep, struct tep_record *rec)
 {
-	return trace_parse_common_type(pevent, rec->data);
+	return trace_parse_common_type(tep, rec->data);
 }
 
 /**
  * tep_data_pid - parse the PID from record
- * @pevent: a handle to the pevent
+ * @tep: a handle to the trace event parser context
  * @rec: the record to parse
  *
  * This returns the PID from a record.
  */
-int tep_data_pid(struct tep_handle *pevent, struct tep_record *rec)
+int tep_data_pid(struct tep_handle *tep, struct tep_record *rec)
 {
-	return parse_common_pid(pevent, rec->data);
+	return parse_common_pid(tep, rec->data);
 }
 
 /**
  * tep_data_preempt_count - parse the preempt count from the record
- * @pevent: a handle to the pevent
+ * @tep: a handle to the trace event parser context
  * @rec: the record to parse
  *
  * This returns the preempt count from a record.
  */
-int tep_data_preempt_count(struct tep_handle *pevent, struct tep_record *rec)
+int tep_data_preempt_count(struct tep_handle *tep, struct tep_record *rec)
 {
-	return parse_common_pc(pevent, rec->data);
+	return parse_common_pc(tep, rec->data);
 }
 
 /**
  * tep_data_flags - parse the latency flags from the record
- * @pevent: a handle to the pevent
+ * @tep: a handle to the trace event parser context
  * @rec: the record to parse
  *
  * This returns the latency flags from a record.
  *
  *  Use trace_flag_type enum for the flags (see event-parse.h).
  */
-int tep_data_flags(struct tep_handle *pevent, struct tep_record *rec)
+int tep_data_flags(struct tep_handle *tep, struct tep_record *rec)
 {
-	return parse_common_flags(pevent, rec->data);
+	return parse_common_flags(tep, rec->data);
 }
 
 /**
  * tep_data_comm_from_pid - return the command line from PID
- * @pevent: a handle to the pevent
+ * @tep: a handle to the trace event parser context
  * @pid: the PID of the task to search for
  *
  * This returns a pointer to the command line that has the given
  * @pid.
  */
-const char *tep_data_comm_from_pid(struct tep_handle *pevent, int pid)
+const char *tep_data_comm_from_pid(struct tep_handle *tep, int pid)
 {
 	const char *comm;
 
-	comm = find_cmdline(pevent, pid);
+	comm = find_cmdline(tep, pid);
 	return comm;
 }
 
 static struct tep_cmdline *
-pid_from_cmdlist(struct tep_handle *pevent, const char *comm, struct tep_cmdline *next)
+pid_from_cmdlist(struct tep_handle *tep, const char *comm, struct tep_cmdline *next)
 {
 	struct cmdline_list *cmdlist = (struct cmdline_list *)next;
 
 	if (cmdlist)
 		cmdlist = cmdlist->next;
 	else
-		cmdlist = pevent->cmdlist;
+		cmdlist = tep->cmdlist;
 
 	while (cmdlist && strcmp(cmdlist->comm, comm) != 0)
 		cmdlist = cmdlist->next;
@@ -5337,7 +5337,7 @@ pid_from_cmdlist(struct tep_handle *pevent, const char *comm, struct tep_cmdline
 
 /**
  * tep_data_pid_from_comm - return the pid from a given comm
- * @pevent: a handle to the pevent
+ * @tep: a handle to the trace event parser context
  * @comm: the cmdline to find the pid from
  * @next: the cmdline structure to find the next comm
  *
@@ -5348,7 +5348,7 @@ pid_from_cmdlist(struct tep_handle *pevent, const char *comm, struct tep_cmdline
  * next pid.
  * Also, it does a linear search, so it may be slow.
  */
-struct tep_cmdline *tep_data_pid_from_comm(struct tep_handle *pevent, const char *comm,
+struct tep_cmdline *tep_data_pid_from_comm(struct tep_handle *tep, const char *comm,
 					   struct tep_cmdline *next)
 {
 	struct tep_cmdline *cmdline;
@@ -5357,25 +5357,25 @@ struct tep_cmdline *tep_data_pid_from_comm(struct tep_handle *pevent, const char
 	 * If the cmdlines have not been converted yet, then use
 	 * the list.
 	 */
-	if (!pevent->cmdlines)
-		return pid_from_cmdlist(pevent, comm, next);
+	if (!tep->cmdlines)
+		return pid_from_cmdlist(tep, comm, next);
 
 	if (next) {
 		/*
 		 * The next pointer could have been still from
 		 * a previous call before cmdlines were created
 		 */
-		if (next < pevent->cmdlines ||
-		    next >= pevent->cmdlines + pevent->cmdline_count)
+		if (next < tep->cmdlines ||
+		    next >= tep->cmdlines + tep->cmdline_count)
 			next = NULL;
 		else
 			cmdline  = next++;
 	}
 
 	if (!next)
-		cmdline = pevent->cmdlines;
+		cmdline = tep->cmdlines;
 
-	while (cmdline < pevent->cmdlines + pevent->cmdline_count) {
+	while (cmdline < tep->cmdlines + tep->cmdline_count) {
 		if (strcmp(cmdline->comm, comm) == 0)
 			return cmdline;
 		cmdline++;
@@ -5385,12 +5385,13 @@ struct tep_cmdline *tep_data_pid_from_comm(struct tep_handle *pevent, const char
 
 /**
  * tep_cmdline_pid - return the pid associated to a given cmdline
+ * @tep: a handle to the trace event parser context
  * @cmdline: The cmdline structure to get the pid from
  *
  * Returns the pid for a give cmdline. If @cmdline is NULL, then
  * -1 is returned.
  */
-int tep_cmdline_pid(struct tep_handle *pevent, struct tep_cmdline *cmdline)
+int tep_cmdline_pid(struct tep_handle *tep, struct tep_cmdline *cmdline)
 {
 	struct cmdline_list *cmdlist = (struct cmdline_list *)cmdline;
 
@@ -5401,9 +5402,9 @@ int tep_cmdline_pid(struct tep_handle *pevent, struct tep_cmdline *cmdline)
 	 * If cmdlines have not been created yet, or cmdline is
 	 * not part of the array, then treat it as a cmdlist instead.
 	 */
-	if (!pevent->cmdlines ||
-	    cmdline < pevent->cmdlines ||
-	    cmdline >= pevent->cmdlines + pevent->cmdline_count)
+	if (!tep->cmdlines ||
+	    cmdline < tep->cmdlines ||
+	    cmdline >= tep->cmdlines + tep->cmdline_count)
 		return cmdlist->pid;
 
 	return cmdline->pid;
@@ -5423,7 +5424,7 @@ void tep_event_info(struct trace_seq *s, struct tep_event *event,
 {
 	int print_pretty = 1;
 
-	if (event->pevent->print_raw || (event->flags & TEP_EVENT_FL_PRINTRAW))
+	if (event->tep->print_raw || (event->flags & TEP_EVENT_FL_PRINTRAW))
 		tep_print_fields(s, record->data, record->size, event);
 	else {
 
@@ -5444,7 +5445,8 @@ static bool is_timestamp_in_us(char *trace_clock, bool use_trace_clock)
 		return true;
 
 	if (!strcmp(trace_clock, "local") || !strcmp(trace_clock, "global")
-	    || !strcmp(trace_clock, "uptime") || !strcmp(trace_clock, "perf"))
+	    || !strcmp(trace_clock, "uptime") || !strcmp(trace_clock, "perf")
+	    || !strncmp(trace_clock, "mono", 4))
 		return true;
 
 	/* trace_clock is setting in tsc or counter mode */
@@ -5453,14 +5455,14 @@ static bool is_timestamp_in_us(char *trace_clock, bool use_trace_clock)
 
 /**
  * tep_find_event_by_record - return the event from a given record
- * @pevent: a handle to the pevent
+ * @tep: a handle to the trace event parser context
  * @record: The record to get the event from
  *
  * Returns the associated event for a given record, or NULL if non is
  * is found.
  */
 struct tep_event *
-tep_find_event_by_record(struct tep_handle *pevent, struct tep_record *record)
+tep_find_event_by_record(struct tep_handle *tep, struct tep_record *record)
 {
 	int type;
 
@@ -5469,21 +5471,21 @@ tep_find_event_by_record(struct tep_handle *pevent, struct tep_record *record)
 		return NULL;
 	}
 
-	type = trace_parse_common_type(pevent, record->data);
+	type = trace_parse_common_type(tep, record->data);
 
-	return tep_find_event(pevent, type);
+	return tep_find_event(tep, type);
 }
 
 /**
  * tep_print_event_task - Write the event task comm, pid and CPU
- * @pevent: a handle to the pevent
+ * @tep: a handle to the trace event parser context
  * @s: the trace_seq to write to
  * @event: the handle to the record's event
  * @record: The record to get the event from
  *
  * Writes the tasks comm, pid and CPU to @s.
  */
-void tep_print_event_task(struct tep_handle *pevent, struct trace_seq *s,
+void tep_print_event_task(struct tep_handle *tep, struct trace_seq *s,
 			  struct tep_event *event,
 			  struct tep_record *record)
 {
@@ -5491,27 +5493,26 @@ void tep_print_event_task(struct tep_handle *pevent, struct trace_seq *s,
 	const char *comm;
 	int pid;
 
-	pid = parse_common_pid(pevent, data);
-	comm = find_cmdline(pevent, pid);
+	pid = parse_common_pid(tep, data);
+	comm = find_cmdline(tep, pid);
 
-	if (pevent->latency_format) {
-		trace_seq_printf(s, "%8.8s-%-5d %3d",
-		       comm, pid, record->cpu);
-	} else
+	if (tep->latency_format)
+		trace_seq_printf(s, "%8.8s-%-5d %3d", comm, pid, record->cpu);
+	else
 		trace_seq_printf(s, "%16s-%-5d [%03d]", comm, pid, record->cpu);
 }
 
 /**
  * tep_print_event_time - Write the event timestamp
- * @pevent: a handle to the pevent
+ * @tep: a handle to the trace event parser context
  * @s: the trace_seq to write to
  * @event: the handle to the record's event
  * @record: The record to get the event from
- * @use_trace_clock: Set to parse according to the @pevent->trace_clock
+ * @use_trace_clock: Set to parse according to the @tep->trace_clock
  *
  * Writes the timestamp of the record into @s.
  */
-void tep_print_event_time(struct tep_handle *pevent, struct trace_seq *s,
+void tep_print_event_time(struct tep_handle *tep, struct trace_seq *s,
 			  struct tep_event *event,
 			  struct tep_record *record,
 			  bool use_trace_clock)
@@ -5522,19 +5523,18 @@ void tep_print_event_time(struct tep_handle *pevent, struct trace_seq *s,
 	int p;
 	bool use_usec_format;
 
-	use_usec_format = is_timestamp_in_us(pevent->trace_clock,
-							use_trace_clock);
+	use_usec_format = is_timestamp_in_us(tep->trace_clock, use_trace_clock);
 	if (use_usec_format) {
 		secs = record->ts / NSEC_PER_SEC;
 		nsecs = record->ts - secs * NSEC_PER_SEC;
 	}
 
-	if (pevent->latency_format) {
-		tep_data_lat_fmt(pevent, s, record);
+	if (tep->latency_format) {
+		tep_data_latency_format(tep, s, record);
 	}
 
 	if (use_usec_format) {
-		if (pevent->flags & TEP_NSEC_OUTPUT) {
+		if (tep->flags & TEP_NSEC_OUTPUT) {
 			usecs = nsecs;
 			p = 9;
 		} else {
@@ -5554,14 +5554,14 @@ void tep_print_event_time(struct tep_handle *pevent, struct trace_seq *s,
 
 /**
  * tep_print_event_data - Write the event data section
- * @pevent: a handle to the pevent
+ * @tep: a handle to the trace event parser context
  * @s: the trace_seq to write to
  * @event: the handle to the record's event
  * @record: The record to get the event from
  *
  * Writes the parsing of the record's data to @s.
  */
-void tep_print_event_data(struct tep_handle *pevent, struct trace_seq *s,
+void tep_print_event_data(struct tep_handle *tep, struct trace_seq *s,
 			  struct tep_event *event,
 			  struct tep_record *record)
 {
@@ -5578,15 +5578,15 @@ void tep_print_event_data(struct tep_handle *pevent, struct trace_seq *s,
 	tep_event_info(s, event, record);
 }
 
-void tep_print_event(struct tep_handle *pevent, struct trace_seq *s,
+void tep_print_event(struct tep_handle *tep, struct trace_seq *s,
 		     struct tep_record *record, bool use_trace_clock)
 {
 	struct tep_event *event;
 
-	event = tep_find_event_by_record(pevent, record);
+	event = tep_find_event_by_record(tep, record);
 	if (!event) {
 		int i;
-		int type = trace_parse_common_type(pevent, record->data);
+		int type = trace_parse_common_type(tep, record->data);
 
 		do_warning("ug! no event found for type %d", type);
 		trace_seq_printf(s, "[UNKNOWN TYPE %d]", type);
@@ -5596,9 +5596,9 @@ void tep_print_event(struct tep_handle *pevent, struct trace_seq *s,
 		return;
 	}
 
-	tep_print_event_task(pevent, s, event, record);
-	tep_print_event_time(pevent, s, event, record, use_trace_clock);
-	tep_print_event_data(pevent, s, event, record);
+	tep_print_event_task(tep, s, event, record);
+	tep_print_event_time(tep, s, event, record, use_trace_clock);
+	tep_print_event_data(tep, s, event, record);
 }
 
 static int events_id_cmp(const void *a, const void *b)
@@ -5649,32 +5649,26 @@ static int events_system_cmp(const void *a, const void *b)
 	return events_id_cmp(a, b);
 }
 
-struct tep_event **tep_list_events(struct tep_handle *pevent, enum tep_event_sort_type sort_type)
+static struct tep_event **list_events_copy(struct tep_handle *tep)
 {
 	struct tep_event **events;
-	int (*sort)(const void *a, const void *b);
-
-	events = pevent->sort_events;
-
-	if (events && pevent->last_type == sort_type)
-		return events;
 
-	if (!events) {
-		events = malloc(sizeof(*events) * (pevent->nr_events + 1));
-		if (!events)
-			return NULL;
+	if (!tep)
+		return NULL;
 
-		memcpy(events, pevent->events, sizeof(*events) * pevent->nr_events);
-		events[pevent->nr_events] = NULL;
+	events = malloc(sizeof(*events) * (tep->nr_events + 1));
+	if (!events)
+		return NULL;
 
-		pevent->sort_events = events;
+	memcpy(events, tep->events, sizeof(*events) * tep->nr_events);
+	events[tep->nr_events] = NULL;
+	return events;
+}
 
-		/* the internal events are sorted by id */
-		if (sort_type == TEP_EVENT_SORT_ID) {
-			pevent->last_type = sort_type;
-			return events;
-		}
-	}
+static void list_events_sort(struct tep_event **events, int nr_events,
+			     enum tep_event_sort_type sort_type)
+{
+	int (*sort)(const void *a, const void *b);
 
 	switch (sort_type) {
 	case TEP_EVENT_SORT_ID:
@@ -5687,11 +5681,82 @@ struct tep_event **tep_list_events(struct tep_handle *pevent, enum tep_event_sor
 		sort = events_system_cmp;
 		break;
 	default:
+		sort = NULL;
+	}
+
+	if (sort)
+		qsort(events, nr_events, sizeof(*events), sort);
+}
+
+/**
+ * tep_list_events - Get events, sorted by given criteria.
+ * @tep: a handle to the tep context
+ * @sort_type: desired sort order of the events in the array
+ *
+ * Returns an array of pointers to all events, sorted by the given
+ * @sort_type criteria. The last element of the array is NULL. The returned
+ * memory must not be freed, it is managed by the library.
+ * The function is not thread safe.
+ */
+struct tep_event **tep_list_events(struct tep_handle *tep,
+				   enum tep_event_sort_type sort_type)
+{
+	struct tep_event **events;
+
+	if (!tep)
+		return NULL;
+
+	events = tep->sort_events;
+	if (events && tep->last_type == sort_type)
 		return events;
+
+	if (!events) {
+		events = list_events_copy(tep);
+		if (!events)
+			return NULL;
+
+		tep->sort_events = events;
+
+		/* the internal events are sorted by id */
+		if (sort_type == TEP_EVENT_SORT_ID) {
+			tep->last_type = sort_type;
+			return events;
+		}
 	}
 
-	qsort(events, pevent->nr_events, sizeof(*events), sort);
-	pevent->last_type = sort_type;
+	list_events_sort(events, tep->nr_events, sort_type);
+	tep->last_type = sort_type;
+
+	return events;
+}
+
+
+/**
+ * tep_list_events_copy - Thread safe version of tep_list_events()
+ * @tep: a handle to the tep context
+ * @sort_type: desired sort order of the events in the array
+ *
+ * Returns an array of pointers to all events, sorted by the given
+ * @sort_type criteria. The last element of the array is NULL. The returned
+ * array is newly allocated inside the function and must be freed by the caller
+ */
+struct tep_event **tep_list_events_copy(struct tep_handle *tep,
+					enum tep_event_sort_type sort_type)
+{
+	struct tep_event **events;
+
+	if (!tep)
+		return NULL;
+
+	events = list_events_copy(tep);
+	if (!events)
+		return NULL;
+
+	/* the internal events are sorted by id */
+	if (sort_type == TEP_EVENT_SORT_ID)
+		return events;
+
+	list_events_sort(events, tep->nr_events, sort_type);
 
 	return events;
 }
@@ -5950,7 +6015,7 @@ static void parse_header_field(const char *field,
 
 /**
  * tep_parse_header_page - parse the data stored in the header page
- * @pevent: the handle to the pevent
+ * @tep: a handle to the trace event parser context
  * @buf: the buffer storing the header page format string
  * @size: the size of @buf
  * @long_size: the long size to use if there is no header
@@ -5960,7 +6025,7 @@ static void parse_header_field(const char *field,
  *
  * /sys/kernel/debug/tracing/events/header_page
  */
-int tep_parse_header_page(struct tep_handle *pevent, char *buf, unsigned long size,
+int tep_parse_header_page(struct tep_handle *tep, char *buf, unsigned long size,
 			  int long_size)
 {
 	int ignore;
@@ -5970,22 +6035,22 @@ int tep_parse_header_page(struct tep_handle *pevent, char *buf, unsigned long si
 		 * Old kernels did not have header page info.
 		 * Sorry but we just use what we find here in user space.
 		 */
-		pevent->header_page_ts_size = sizeof(long long);
-		pevent->header_page_size_size = long_size;
-		pevent->header_page_data_offset = sizeof(long long) + long_size;
-		pevent->old_format = 1;
+		tep->header_page_ts_size = sizeof(long long);
+		tep->header_page_size_size = long_size;
+		tep->header_page_data_offset = sizeof(long long) + long_size;
+		tep->old_format = 1;
 		return -1;
 	}
 	init_input_buf(buf, size);
 
-	parse_header_field("timestamp", &pevent->header_page_ts_offset,
-			   &pevent->header_page_ts_size, 1);
-	parse_header_field("commit", &pevent->header_page_size_offset,
-			   &pevent->header_page_size_size, 1);
-	parse_header_field("overwrite", &pevent->header_page_overwrite,
+	parse_header_field("timestamp", &tep->header_page_ts_offset,
+			   &tep->header_page_ts_size, 1);
+	parse_header_field("commit", &tep->header_page_size_offset,
+			   &tep->header_page_size_size, 1);
+	parse_header_field("overwrite", &tep->header_page_overwrite,
 			   &ignore, 0);
-	parse_header_field("data", &pevent->header_page_data_offset,
-			   &pevent->header_page_data_size, 1);
+	parse_header_field("data", &tep->header_page_data_offset,
+			   &tep->header_page_data_size, 1);
 
 	return 0;
 }
@@ -6013,11 +6078,11 @@ static void free_handler(struct event_handler *handle)
 	free(handle);
 }
 
-static int find_event_handle(struct tep_handle *pevent, struct tep_event *event)
+static int find_event_handle(struct tep_handle *tep, struct tep_event *event)
 {
 	struct event_handler *handle, **next;
 
-	for (next = &pevent->handlers; *next;
+	for (next = &tep->handlers; *next;
 	     next = &(*next)->next) {
 		handle = *next;
 		if (event_matches(event, handle->id,
@@ -6055,7 +6120,7 @@ static int find_event_handle(struct tep_handle *pevent, struct tep_event *event)
  * /sys/kernel/debug/tracing/events/.../.../format
  */
 enum tep_errno __tep_parse_format(struct tep_event **eventp,
-				  struct tep_handle *pevent, const char *buf,
+				  struct tep_handle *tep, const char *buf,
 				  unsigned long size, const char *sys)
 {
 	struct tep_event *event;
@@ -6097,8 +6162,8 @@ enum tep_errno __tep_parse_format(struct tep_event **eventp,
 		goto event_alloc_failed;
 	}
 
-	/* Add pevent to event so that it can be referenced */
-	event->pevent = pevent;
+	/* Add tep to event so that it can be referenced */
+	event->tep = tep;
 
 	ret = event_read_format(event);
 	if (ret < 0) {
@@ -6110,7 +6175,7 @@ enum tep_errno __tep_parse_format(struct tep_event **eventp,
 	 * If the event has an override, don't print warnings if the event
 	 * print format fails to parse.
 	 */
-	if (pevent && find_event_handle(pevent, event))
+	if (tep && find_event_handle(tep, event))
 		show_warning = 0;
 
 	ret = event_read_print(event);
@@ -6162,18 +6227,18 @@ enum tep_errno __tep_parse_format(struct tep_event **eventp,
 }
 
 static enum tep_errno
-__parse_event(struct tep_handle *pevent,
+__parse_event(struct tep_handle *tep,
 	      struct tep_event **eventp,
 	      const char *buf, unsigned long size,
 	      const char *sys)
 {
-	int ret = __tep_parse_format(eventp, pevent, buf, size, sys);
+	int ret = __tep_parse_format(eventp, tep, buf, size, sys);
 	struct tep_event *event = *eventp;
 
 	if (event == NULL)
 		return ret;
 
-	if (pevent && add_event(pevent, event)) {
+	if (tep && add_event(tep, event)) {
 		ret = TEP_ERRNO__MEM_ALLOC_FAILED;
 		goto event_add_failed;
 	}
@@ -6191,7 +6256,7 @@ event_add_failed:
 
 /**
  * tep_parse_format - parse the event format
- * @pevent: the handle to the pevent
+ * @tep: a handle to the trace event parser context
  * @eventp: returned format
  * @buf: the buffer storing the event format string
  * @size: the size of @buf
@@ -6204,17 +6269,17 @@ event_add_failed:
  *
  * /sys/kernel/debug/tracing/events/.../.../format
  */
-enum tep_errno tep_parse_format(struct tep_handle *pevent,
+enum tep_errno tep_parse_format(struct tep_handle *tep,
 				struct tep_event **eventp,
 				const char *buf,
 				unsigned long size, const char *sys)
 {
-	return __parse_event(pevent, eventp, buf, size, sys);
+	return __parse_event(tep, eventp, buf, size, sys);
 }
 
 /**
  * tep_parse_event - parse the event format
- * @pevent: the handle to the pevent
+ * @tep: a handle to the trace event parser context
  * @buf: the buffer storing the event format string
  * @size: the size of @buf
  * @sys: the system the event belongs to
@@ -6226,11 +6291,11 @@ enum tep_errno tep_parse_format(struct tep_handle *pevent,
  *
  * /sys/kernel/debug/tracing/events/.../.../format
  */
-enum tep_errno tep_parse_event(struct tep_handle *pevent, const char *buf,
+enum tep_errno tep_parse_event(struct tep_handle *tep, const char *buf,
 			       unsigned long size, const char *sys)
 {
 	struct tep_event *event = NULL;
-	return __parse_event(pevent, &event, buf, size, sys);
+	return __parse_event(tep, &event, buf, size, sys);
 }
 
 int get_field_val(struct trace_seq *s, struct tep_format_field *field,
@@ -6292,8 +6357,8 @@ void *tep_get_field_raw(struct trace_seq *s, struct tep_event *event,
 
 	offset = field->offset;
 	if (field->flags & TEP_FIELD_IS_DYNAMIC) {
-		offset = tep_read_number(event->pevent,
-					    data + offset, field->size);
+		offset = tep_read_number(event->tep,
+					 data + offset, field->size);
 		*len = offset >> 16;
 		offset &= 0xffff;
 	} else
@@ -6386,7 +6451,8 @@ int tep_get_any_field_val(struct trace_seq *s, struct tep_event *event,
  * @record: The record with the field name.
  * @err: print default error if failed.
  *
- * Returns: 0 on success, -1 field not found, or 1 if buffer is full.
+ * Returns positive value on success, negative in case of an error,
+ * or 0 if buffer is full.
  */
 int tep_print_num_field(struct trace_seq *s, const char *fmt,
 			struct tep_event *event, const char *name,
@@ -6418,14 +6484,15 @@ int tep_print_num_field(struct trace_seq *s, const char *fmt,
  * @record: The record with the field name.
  * @err: print default error if failed.
  *
- * Returns: 0 on success, -1 field not found, or 1 if buffer is full.
+ * Returns positive value on success, negative in case of an error,
+ * or 0 if buffer is full.
  */
 int tep_print_func_field(struct trace_seq *s, const char *fmt,
 			 struct tep_event *event, const char *name,
 			 struct tep_record *record, int err)
 {
 	struct tep_format_field *field = tep_find_field(event, name);
-	struct tep_handle *pevent = event->pevent;
+	struct tep_handle *tep = event->tep;
 	unsigned long long val;
 	struct func_map *func;
 	char tmp[128];
@@ -6436,7 +6503,7 @@ int tep_print_func_field(struct trace_seq *s, const char *fmt,
 	if (tep_read_number_field(field, record->data, &val))
 		goto failed;
 
-	func = find_func(pevent, val);
+	func = find_func(tep, val);
 
 	if (func)
 		snprintf(tmp, 128, "%s/0x%llx", func->func, func->addr - val);
@@ -6468,7 +6535,7 @@ static void free_func_handle(struct tep_function_handler *func)
 
 /**
  * tep_register_print_function - register a helper function
- * @pevent: the handle to the pevent
+ * @tep: a handle to the trace event parser context
  * @func: the function to process the helper function
  * @ret_type: the return type of the helper function
  * @name: the name of the helper function
@@ -6481,7 +6548,7 @@ static void free_func_handle(struct tep_function_handler *func)
  * The @parameters is a variable list of tep_func_arg_type enums that
  * must end with TEP_FUNC_ARG_VOID.
  */
-int tep_register_print_function(struct tep_handle *pevent,
+int tep_register_print_function(struct tep_handle *tep,
 				tep_func_handler func,
 				enum tep_func_arg_type ret_type,
 				char *name, ...)
@@ -6493,7 +6560,7 @@ int tep_register_print_function(struct tep_handle *pevent,
 	va_list ap;
 	int ret;
 
-	func_handle = find_func_handler(pevent, name);
+	func_handle = find_func_handler(tep, name);
 	if (func_handle) {
 		/*
 		 * This is most like caused by the users own
@@ -6501,7 +6568,7 @@ int tep_register_print_function(struct tep_handle *pevent,
 		 * system defaults.
 		 */
 		pr_stat("override of function helper '%s'", name);
-		remove_func_handler(pevent, name);
+		remove_func_handler(tep, name);
 	}
 
 	func_handle = calloc(1, sizeof(*func_handle));
@@ -6548,8 +6615,8 @@ int tep_register_print_function(struct tep_handle *pevent,
 	}
 	va_end(ap);
 
-	func_handle->next = pevent->func_handlers;
-	pevent->func_handlers = func_handle;
+	func_handle->next = tep->func_handlers;
+	tep->func_handlers = func_handle;
 
 	return 0;
  out_free:
@@ -6560,7 +6627,7 @@ int tep_register_print_function(struct tep_handle *pevent,
 
 /**
  * tep_unregister_print_function - unregister a helper function
- * @pevent: the handle to the pevent
+ * @tep: a handle to the trace event parser context
  * @func: the function to process the helper function
  * @name: the name of the helper function
  *
@@ -6568,20 +6635,20 @@ int tep_register_print_function(struct tep_handle *pevent,
  *
  * Returns 0 if the handler was removed successully, -1 otherwise.
  */
-int tep_unregister_print_function(struct tep_handle *pevent,
+int tep_unregister_print_function(struct tep_handle *tep,
 				  tep_func_handler func, char *name)
 {
 	struct tep_function_handler *func_handle;
 
-	func_handle = find_func_handler(pevent, name);
+	func_handle = find_func_handler(tep, name);
 	if (func_handle && func_handle->func == func) {
-		remove_func_handler(pevent, name);
+		remove_func_handler(tep, name);
 		return 0;
 	}
 	return -1;
 }
 
-static struct tep_event *search_event(struct tep_handle *pevent, int id,
+static struct tep_event *search_event(struct tep_handle *tep, int id,
 				      const char *sys_name,
 				      const char *event_name)
 {
@@ -6589,7 +6656,7 @@ static struct tep_event *search_event(struct tep_handle *pevent, int id,
 
 	if (id >= 0) {
 		/* search by id */
-		event = tep_find_event(pevent, id);
+		event = tep_find_event(tep, id);
 		if (!event)
 			return NULL;
 		if (event_name && (strcmp(event_name, event->name) != 0))
@@ -6597,7 +6664,7 @@ static struct tep_event *search_event(struct tep_handle *pevent, int id,
 		if (sys_name && (strcmp(sys_name, event->system) != 0))
 			return NULL;
 	} else {
-		event = tep_find_event_by_name(pevent, sys_name, event_name);
+		event = tep_find_event_by_name(tep, sys_name, event_name);
 		if (!event)
 			return NULL;
 	}
@@ -6606,7 +6673,7 @@ static struct tep_event *search_event(struct tep_handle *pevent, int id,
 
 /**
  * tep_register_event_handler - register a way to parse an event
- * @pevent: the handle to the pevent
+ * @tep: a handle to the trace event parser context
  * @id: the id of the event to register
  * @sys_name: the system name the event belongs to
  * @event_name: the name of the event
@@ -6627,14 +6694,14 @@ static struct tep_event *search_event(struct tep_handle *pevent, int id,
  *  negative TEP_ERRNO_... in case of an error
  *
  */
-int tep_register_event_handler(struct tep_handle *pevent, int id,
+int tep_register_event_handler(struct tep_handle *tep, int id,
 			       const char *sys_name, const char *event_name,
 			       tep_event_handler_func func, void *context)
 {
 	struct tep_event *event;
 	struct event_handler *handle;
 
-	event = search_event(pevent, id, sys_name, event_name);
+	event = search_event(tep, id, sys_name, event_name);
 	if (event == NULL)
 		goto not_found;
 
@@ -6669,8 +6736,8 @@ int tep_register_event_handler(struct tep_handle *pevent, int id,
 	}
 
 	handle->func = func;
-	handle->next = pevent->handlers;
-	pevent->handlers = handle;
+	handle->next = tep->handlers;
+	tep->handlers = handle;
 	handle->context = context;
 
 	return TEP_REGISTER_SUCCESS;
@@ -6697,7 +6764,7 @@ static int handle_matches(struct event_handler *handler, int id,
 
 /**
  * tep_unregister_event_handler - unregister an existing event handler
- * @pevent: the handle to the pevent
+ * @tep: a handle to the trace event parser context
  * @id: the id of the event to unregister
  * @sys_name: the system name the handler belongs to
  * @event_name: the name of the event handler
@@ -6711,7 +6778,7 @@ static int handle_matches(struct event_handler *handler, int id,
  *
  * Returns 0 if handler was removed successfully, -1 if event was not found.
  */
-int tep_unregister_event_handler(struct tep_handle *pevent, int id,
+int tep_unregister_event_handler(struct tep_handle *tep, int id,
 				 const char *sys_name, const char *event_name,
 				 tep_event_handler_func func, void *context)
 {
@@ -6719,7 +6786,7 @@ int tep_unregister_event_handler(struct tep_handle *pevent, int id,
 	struct event_handler *handle;
 	struct event_handler **next;
 
-	event = search_event(pevent, id, sys_name, event_name);
+	event = search_event(tep, id, sys_name, event_name);
 	if (event == NULL)
 		goto not_found;
 
@@ -6733,7 +6800,7 @@ int tep_unregister_event_handler(struct tep_handle *pevent, int id,
 	}
 
 not_found:
-	for (next = &pevent->handlers; *next; next = &(*next)->next) {
+	for (next = &tep->handlers; *next; next = &(*next)->next) {
 		handle = *next;
 		if (handle_matches(handle, id, sys_name, event_name,
 				   func, context))
@@ -6750,23 +6817,23 @@ not_found:
 }
 
 /**
- * tep_alloc - create a pevent handle
+ * tep_alloc - create a tep handle
  */
 struct tep_handle *tep_alloc(void)
 {
-	struct tep_handle *pevent = calloc(1, sizeof(*pevent));
+	struct tep_handle *tep = calloc(1, sizeof(*tep));
 
-	if (pevent) {
-		pevent->ref_count = 1;
-		pevent->host_bigendian = tep_host_bigendian();
+	if (tep) {
+		tep->ref_count = 1;
+		tep->host_bigendian = tep_is_bigendian();
 	}
 
-	return pevent;
+	return tep;
 }
 
-void tep_ref(struct tep_handle *pevent)
+void tep_ref(struct tep_handle *tep)
 {
-	pevent->ref_count++;
+	tep->ref_count++;
 }
 
 int tep_get_ref(struct tep_handle *tep)
@@ -6816,10 +6883,10 @@ void tep_free_event(struct tep_event *event)
 }
 
 /**
- * tep_free - free a pevent handle
- * @pevent: the pevent handle to free
+ * tep_free - free a tep handle
+ * @tep: the tep handle to free
  */
-void tep_free(struct tep_handle *pevent)
+void tep_free(struct tep_handle *tep)
 {
 	struct cmdline_list *cmdlist, *cmdnext;
 	struct func_list *funclist, *funcnext;
@@ -6828,21 +6895,21 @@ void tep_free(struct tep_handle *pevent)
 	struct event_handler *handle;
 	int i;
 
-	if (!pevent)
+	if (!tep)
 		return;
 
-	cmdlist = pevent->cmdlist;
-	funclist = pevent->funclist;
-	printklist = pevent->printklist;
+	cmdlist = tep->cmdlist;
+	funclist = tep->funclist;
+	printklist = tep->printklist;
 
-	pevent->ref_count--;
-	if (pevent->ref_count)
+	tep->ref_count--;
+	if (tep->ref_count)
 		return;
 
-	if (pevent->cmdlines) {
-		for (i = 0; i < pevent->cmdline_count; i++)
-			free(pevent->cmdlines[i].comm);
-		free(pevent->cmdlines);
+	if (tep->cmdlines) {
+		for (i = 0; i < tep->cmdline_count; i++)
+			free(tep->cmdlines[i].comm);
+		free(tep->cmdlines);
 	}
 
 	while (cmdlist) {
@@ -6852,12 +6919,12 @@ void tep_free(struct tep_handle *pevent)
 		cmdlist = cmdnext;
 	}
 
-	if (pevent->func_map) {
-		for (i = 0; i < (int)pevent->func_count; i++) {
-			free(pevent->func_map[i].func);
-			free(pevent->func_map[i].mod);
+	if (tep->func_map) {
+		for (i = 0; i < (int)tep->func_count; i++) {
+			free(tep->func_map[i].func);
+			free(tep->func_map[i].mod);
 		}
-		free(pevent->func_map);
+		free(tep->func_map);
 	}
 
 	while (funclist) {
@@ -6868,16 +6935,16 @@ void tep_free(struct tep_handle *pevent)
 		funclist = funcnext;
 	}
 
-	while (pevent->func_handlers) {
-		func_handler = pevent->func_handlers;
-		pevent->func_handlers = func_handler->next;
+	while (tep->func_handlers) {
+		func_handler = tep->func_handlers;
+		tep->func_handlers = func_handler->next;
 		free_func_handle(func_handler);
 	}
 
-	if (pevent->printk_map) {
-		for (i = 0; i < (int)pevent->printk_count; i++)
-			free(pevent->printk_map[i].printk);
-		free(pevent->printk_map);
+	if (tep->printk_map) {
+		for (i = 0; i < (int)tep->printk_count; i++)
+			free(tep->printk_map[i].printk);
+		free(tep->printk_map);
 	}
 
 	while (printklist) {
@@ -6887,24 +6954,24 @@ void tep_free(struct tep_handle *pevent)
 		printklist = printknext;
 	}
 
-	for (i = 0; i < pevent->nr_events; i++)
-		tep_free_event(pevent->events[i]);
+	for (i = 0; i < tep->nr_events; i++)
+		tep_free_event(tep->events[i]);
 
-	while (pevent->handlers) {
-		handle = pevent->handlers;
-		pevent->handlers = handle->next;
+	while (tep->handlers) {
+		handle = tep->handlers;
+		tep->handlers = handle->next;
 		free_handler(handle);
 	}
 
-	free(pevent->trace_clock);
-	free(pevent->events);
-	free(pevent->sort_events);
-	free(pevent->func_resolver);
+	free(tep->trace_clock);
+	free(tep->events);
+	free(tep->sort_events);
+	free(tep->func_resolver);
 
-	free(pevent);
+	free(tep);
 }
 
-void tep_unref(struct tep_handle *pevent)
+void tep_unref(struct tep_handle *tep)
 {
-	tep_free(pevent);
+	tep_free(tep);
 }
diff --git a/tools/lib/traceevent/event-parse.h b/tools/lib/traceevent/event-parse.h
index aec48f2aea8a..642f68ab5fb2 100644
--- a/tools/lib/traceevent/event-parse.h
+++ b/tools/lib/traceevent/event-parse.h
@@ -64,8 +64,8 @@ typedef int (*tep_event_handler_func)(struct trace_seq *s,
 				      struct tep_event *event,
 				      void *context);
 
-typedef int (*tep_plugin_load_func)(struct tep_handle *pevent);
-typedef int (*tep_plugin_unload_func)(struct tep_handle *pevent);
+typedef int (*tep_plugin_load_func)(struct tep_handle *tep);
+typedef int (*tep_plugin_unload_func)(struct tep_handle *tep);
 
 struct tep_plugin_option {
 	struct tep_plugin_option	*next;
@@ -85,12 +85,12 @@ struct tep_plugin_option {
  * TEP_PLUGIN_LOADER:  (required)
  *   The function name to initialized the plugin.
  *
- *   int TEP_PLUGIN_LOADER(struct tep_handle *pevent)
+ *   int TEP_PLUGIN_LOADER(struct tep_handle *tep)
  *
  * TEP_PLUGIN_UNLOADER:  (optional)
  *   The function called just before unloading
  *
- *   int TEP_PLUGIN_UNLOADER(struct tep_handle *pevent)
+ *   int TEP_PLUGIN_UNLOADER(struct tep_handle *tep)
  *
  * TEP_PLUGIN_OPTIONS:  (optional)
  *   Plugin options that can be set before loading
@@ -278,7 +278,7 @@ struct tep_print_fmt {
 };
 
 struct tep_event {
-	struct tep_handle	*pevent;
+	struct tep_handle	*tep;
 	char			*name;
 	int			id;
 	int			flags;
@@ -393,9 +393,9 @@ struct tep_plugin_list;
 
 #define INVALID_PLUGIN_LIST_OPTION	((char **)((unsigned long)-1))
 
-struct tep_plugin_list *tep_load_plugins(struct tep_handle *pevent);
+struct tep_plugin_list *tep_load_plugins(struct tep_handle *tep);
 void tep_unload_plugins(struct tep_plugin_list *plugin_list,
-			struct tep_handle *pevent);
+			struct tep_handle *tep);
 char **tep_plugin_list_options(void);
 void tep_plugin_free_options_list(char **list);
 int tep_plugin_add_options(const char *name,
@@ -409,8 +409,10 @@ void tep_print_plugins(struct trace_seq *s,
 typedef char *(tep_func_resolver_t)(void *priv,
 				    unsigned long long *addrp, char **modp);
 void tep_set_flag(struct tep_handle *tep, int flag);
+void tep_clear_flag(struct tep_handle *tep, enum tep_flag flag);
+bool tep_test_flag(struct tep_handle *tep, enum tep_flag flags);
 
-static inline int tep_host_bigendian(void)
+static inline int tep_is_bigendian(void)
 {
 	unsigned char str[] = { 0x1, 0x2, 0x3, 0x4 };
 	unsigned int val;
@@ -428,37 +430,37 @@ enum trace_flag_type {
 	TRACE_FLAG_SOFTIRQ		= 0x10,
 };
 
-int tep_set_function_resolver(struct tep_handle *pevent,
+int tep_set_function_resolver(struct tep_handle *tep,
 			      tep_func_resolver_t *func, void *priv);
-void tep_reset_function_resolver(struct tep_handle *pevent);
-int tep_register_comm(struct tep_handle *pevent, const char *comm, int pid);
-int tep_override_comm(struct tep_handle *pevent, const char *comm, int pid);
-int tep_register_trace_clock(struct tep_handle *pevent, const char *trace_clock);
-int tep_register_function(struct tep_handle *pevent, char *name,
+void tep_reset_function_resolver(struct tep_handle *tep);
+int tep_register_comm(struct tep_handle *tep, const char *comm, int pid);
+int tep_override_comm(struct tep_handle *tep, const char *comm, int pid);
+int tep_register_trace_clock(struct tep_handle *tep, const char *trace_clock);
+int tep_register_function(struct tep_handle *tep, char *name,
 			  unsigned long long addr, char *mod);
-int tep_register_print_string(struct tep_handle *pevent, const char *fmt,
+int tep_register_print_string(struct tep_handle *tep, const char *fmt,
 			      unsigned long long addr);
-int tep_pid_is_registered(struct tep_handle *pevent, int pid);
+bool tep_is_pid_registered(struct tep_handle *tep, int pid);
 
-void tep_print_event_task(struct tep_handle *pevent, struct trace_seq *s,
+void tep_print_event_task(struct tep_handle *tep, struct trace_seq *s,
 			  struct tep_event *event,
 			  struct tep_record *record);
-void tep_print_event_time(struct tep_handle *pevent, struct trace_seq *s,
+void tep_print_event_time(struct tep_handle *tep, struct trace_seq *s,
 			  struct tep_event *event,
 			  struct tep_record *record,
 			  bool use_trace_clock);
-void tep_print_event_data(struct tep_handle *pevent, struct trace_seq *s,
+void tep_print_event_data(struct tep_handle *tep, struct trace_seq *s,
 			  struct tep_event *event,
 			  struct tep_record *record);
-void tep_print_event(struct tep_handle *pevent, struct trace_seq *s,
+void tep_print_event(struct tep_handle *tep, struct trace_seq *s,
 		     struct tep_record *record, bool use_trace_clock);
 
-int tep_parse_header_page(struct tep_handle *pevent, char *buf, unsigned long size,
+int tep_parse_header_page(struct tep_handle *tep, char *buf, unsigned long size,
 			  int long_size);
 
-enum tep_errno tep_parse_event(struct tep_handle *pevent, const char *buf,
+enum tep_errno tep_parse_event(struct tep_handle *tep, const char *buf,
 			       unsigned long size, const char *sys);
-enum tep_errno tep_parse_format(struct tep_handle *pevent,
+enum tep_errno tep_parse_format(struct tep_handle *tep,
 				struct tep_event **eventp,
 				const char *buf,
 				unsigned long size, const char *sys);
@@ -490,50 +492,50 @@ enum tep_reg_handler {
 	TEP_REGISTER_SUCCESS_OVERWRITE,
 };
 
-int tep_register_event_handler(struct tep_handle *pevent, int id,
+int tep_register_event_handler(struct tep_handle *tep, int id,
 			       const char *sys_name, const char *event_name,
 			       tep_event_handler_func func, void *context);
-int tep_unregister_event_handler(struct tep_handle *pevent, int id,
+int tep_unregister_event_handler(struct tep_handle *tep, int id,
 				 const char *sys_name, const char *event_name,
 				 tep_event_handler_func func, void *context);
-int tep_register_print_function(struct tep_handle *pevent,
+int tep_register_print_function(struct tep_handle *tep,
 				tep_func_handler func,
 				enum tep_func_arg_type ret_type,
 				char *name, ...);
-int tep_unregister_print_function(struct tep_handle *pevent,
+int tep_unregister_print_function(struct tep_handle *tep,
 				  tep_func_handler func, char *name);
 
 struct tep_format_field *tep_find_common_field(struct tep_event *event, const char *name);
 struct tep_format_field *tep_find_field(struct tep_event *event, const char *name);
 struct tep_format_field *tep_find_any_field(struct tep_event *event, const char *name);
 
-const char *tep_find_function(struct tep_handle *pevent, unsigned long long addr);
+const char *tep_find_function(struct tep_handle *tep, unsigned long long addr);
 unsigned long long
-tep_find_function_address(struct tep_handle *pevent, unsigned long long addr);
-unsigned long long tep_read_number(struct tep_handle *pevent, const void *ptr, int size);
+tep_find_function_address(struct tep_handle *tep, unsigned long long addr);
+unsigned long long tep_read_number(struct tep_handle *tep, const void *ptr, int size);
 int tep_read_number_field(struct tep_format_field *field, const void *data,
 			  unsigned long long *value);
 
 struct tep_event *tep_get_first_event(struct tep_handle *tep);
 int tep_get_events_count(struct tep_handle *tep);
-struct tep_event *tep_find_event(struct tep_handle *pevent, int id);
+struct tep_event *tep_find_event(struct tep_handle *tep, int id);
 
 struct tep_event *
-tep_find_event_by_name(struct tep_handle *pevent, const char *sys, const char *name);
+tep_find_event_by_name(struct tep_handle *tep, const char *sys, const char *name);
 struct tep_event *
-tep_find_event_by_record(struct tep_handle *pevent, struct tep_record *record);
-
-void tep_data_lat_fmt(struct tep_handle *pevent,
-		      struct trace_seq *s, struct tep_record *record);
-int tep_data_type(struct tep_handle *pevent, struct tep_record *rec);
-int tep_data_pid(struct tep_handle *pevent, struct tep_record *rec);
-int tep_data_preempt_count(struct tep_handle *pevent, struct tep_record *rec);
-int tep_data_flags(struct tep_handle *pevent, struct tep_record *rec);
-const char *tep_data_comm_from_pid(struct tep_handle *pevent, int pid);
+tep_find_event_by_record(struct tep_handle *tep, struct tep_record *record);
+
+void tep_data_latency_format(struct tep_handle *tep,
+			     struct trace_seq *s, struct tep_record *record);
+int tep_data_type(struct tep_handle *tep, struct tep_record *rec);
+int tep_data_pid(struct tep_handle *tep, struct tep_record *rec);
+int tep_data_preempt_count(struct tep_handle *tep, struct tep_record *rec);
+int tep_data_flags(struct tep_handle *tep, struct tep_record *rec);
+const char *tep_data_comm_from_pid(struct tep_handle *tep, int pid);
 struct tep_cmdline;
-struct tep_cmdline *tep_data_pid_from_comm(struct tep_handle *pevent, const char *comm,
+struct tep_cmdline *tep_data_pid_from_comm(struct tep_handle *tep, const char *comm,
 					   struct tep_cmdline *next);
-int tep_cmdline_pid(struct tep_handle *pevent, struct tep_cmdline *cmdline);
+int tep_cmdline_pid(struct tep_handle *tep, struct tep_cmdline *cmdline);
 
 void tep_print_field(struct trace_seq *s, void *data,
 		     struct tep_format_field *field);
@@ -541,10 +543,12 @@ void tep_print_fields(struct trace_seq *s, void *data,
 		      int size __maybe_unused, struct tep_event *event);
 void tep_event_info(struct trace_seq *s, struct tep_event *event,
 		    struct tep_record *record);
-int tep_strerror(struct tep_handle *pevent, enum tep_errno errnum,
+int tep_strerror(struct tep_handle *tep, enum tep_errno errnum,
 		 char *buf, size_t buflen);
 
-struct tep_event **tep_list_events(struct tep_handle *pevent, enum tep_event_sort_type);
+struct tep_event **tep_list_events(struct tep_handle *tep, enum tep_event_sort_type);
+struct tep_event **tep_list_events_copy(struct tep_handle *tep,
+					enum tep_event_sort_type);
 struct tep_format_field **tep_event_common_fields(struct tep_event *event);
 struct tep_format_field **tep_event_fields(struct tep_event *event);
 
@@ -552,24 +556,28 @@ enum tep_endian {
         TEP_LITTLE_ENDIAN = 0,
         TEP_BIG_ENDIAN
 };
-int tep_get_cpus(struct tep_handle *pevent);
-void tep_set_cpus(struct tep_handle *pevent, int cpus);
-int tep_get_long_size(struct tep_handle *pevent);
-void tep_set_long_size(struct tep_handle *pevent, int long_size);
-int tep_get_page_size(struct tep_handle *pevent);
-void tep_set_page_size(struct tep_handle *pevent, int _page_size);
-int tep_file_bigendian(struct tep_handle *pevent);
-void tep_set_file_bigendian(struct tep_handle *pevent, enum tep_endian endian);
-int tep_is_host_bigendian(struct tep_handle *pevent);
-void tep_set_host_bigendian(struct tep_handle *pevent, enum tep_endian endian);
-int tep_is_latency_format(struct tep_handle *pevent);
-void tep_set_latency_format(struct tep_handle *pevent, int lat);
-int tep_get_header_page_size(struct tep_handle *pevent);
+int tep_get_cpus(struct tep_handle *tep);
+void tep_set_cpus(struct tep_handle *tep, int cpus);
+int tep_get_long_size(struct tep_handle *tep);
+void tep_set_long_size(struct tep_handle *tep, int long_size);
+int tep_get_page_size(struct tep_handle *tep);
+void tep_set_page_size(struct tep_handle *tep, int _page_size);
+bool tep_is_file_bigendian(struct tep_handle *tep);
+void tep_set_file_bigendian(struct tep_handle *tep, enum tep_endian endian);
+bool tep_is_local_bigendian(struct tep_handle *tep);
+void tep_set_local_bigendian(struct tep_handle *tep, enum tep_endian endian);
+bool tep_is_latency_format(struct tep_handle *tep);
+void tep_set_latency_format(struct tep_handle *tep, int lat);
+int tep_get_header_page_size(struct tep_handle *tep);
+int tep_get_header_timestamp_size(struct tep_handle *tep);
+bool tep_is_old_format(struct tep_handle *tep);
+void tep_set_print_raw(struct tep_handle *tep, int print_raw);
+void tep_set_test_filters(struct tep_handle *tep, int test_filters);
 
 struct tep_handle *tep_alloc(void);
-void tep_free(struct tep_handle *pevent);
-void tep_ref(struct tep_handle *pevent);
-void tep_unref(struct tep_handle *pevent);
+void tep_free(struct tep_handle *tep);
+void tep_ref(struct tep_handle *tep);
+void tep_unref(struct tep_handle *tep);
 int tep_get_ref(struct tep_handle *tep);
 
 /* access to the internal parser */
@@ -581,8 +589,8 @@ const char *tep_get_input_buf(void);
 unsigned long long tep_get_input_buf_ptr(void);
 
 /* for debugging */
-void tep_print_funcs(struct tep_handle *pevent);
-void tep_print_printk(struct tep_handle *pevent);
+void tep_print_funcs(struct tep_handle *tep);
+void tep_print_printk(struct tep_handle *tep);
 
 /* ----------------------- filtering ----------------------- */
 
@@ -709,13 +717,13 @@ struct tep_filter_type {
 #define TEP_FILTER_ERROR_BUFSZ  1024
 
 struct tep_event_filter {
-	struct tep_handle	*pevent;
+	struct tep_handle	*tep;
 	int			filters;
 	struct tep_filter_type	*event_filters;
 	char			error_buffer[TEP_FILTER_ERROR_BUFSZ];
 };
 
-struct tep_event_filter *tep_filter_alloc(struct tep_handle *pevent);
+struct tep_event_filter *tep_filter_alloc(struct tep_handle *tep);
 
 /* for backward compatibility */
 #define FILTER_NONE		TEP_ERRNO__NO_FILTER
@@ -723,12 +731,6 @@ struct tep_event_filter *tep_filter_alloc(struct tep_handle *pevent);
 #define FILTER_MISS		TEP_ERRNO__FILTER_MISS
 #define FILTER_MATCH		TEP_ERRNO__FILTER_MATCH
 
-enum tep_filter_trivial_type {
-	TEP_FILTER_TRIVIAL_FALSE,
-	TEP_FILTER_TRIVIAL_TRUE,
-	TEP_FILTER_TRIVIAL_BOTH,
-};
-
 enum tep_errno tep_filter_add_filter_str(struct tep_event_filter *filter,
 					 const char *filter_str);
 
@@ -743,9 +745,6 @@ int tep_event_filtered(struct tep_event_filter *filter,
 
 void tep_filter_reset(struct tep_event_filter *filter);
 
-int tep_filter_clear_trivial(struct tep_event_filter *filter,
-			     enum tep_filter_trivial_type type);
-
 void tep_filter_free(struct tep_event_filter *filter);
 
 char *tep_filter_make_string(struct tep_event_filter *filter, int event_id);
@@ -753,15 +752,8 @@ char *tep_filter_make_string(struct tep_event_filter *filter, int event_id);
 int tep_filter_remove_event(struct tep_event_filter *filter,
 			    int event_id);
 
-int tep_filter_event_has_trivial(struct tep_event_filter *filter,
-				 int event_id,
-				 enum tep_filter_trivial_type type);
-
 int tep_filter_copy(struct tep_event_filter *dest, struct tep_event_filter *source);
 
-int tep_update_trivial(struct tep_event_filter *dest, struct tep_event_filter *source,
-			enum tep_filter_trivial_type type);
-
 int tep_filter_compare(struct tep_event_filter *filter1, struct tep_event_filter *filter2);
 
 #endif /* _PARSE_EVENTS_H */
diff --git a/tools/lib/traceevent/event-plugin.c b/tools/lib/traceevent/event-plugin.c
index e74f16c88398..8ca28de9337a 100644
--- a/tools/lib/traceevent/event-plugin.c
+++ b/tools/lib/traceevent/event-plugin.c
@@ -269,7 +269,7 @@ void tep_print_plugins(struct trace_seq *s,
 }
 
 static void
-load_plugin(struct tep_handle *pevent, const char *path,
+load_plugin(struct tep_handle *tep, const char *path,
 	    const char *file, void *data)
 {
 	struct tep_plugin_list **plugin_list = data;
@@ -316,7 +316,7 @@ load_plugin(struct tep_handle *pevent, const char *path,
 	*plugin_list = list;
 
 	pr_stat("registering plugin: %s", plugin);
-	func(pevent);
+	func(tep);
 	return;
 
  out_free:
@@ -324,9 +324,9 @@ load_plugin(struct tep_handle *pevent, const char *path,
 }
 
 static void
-load_plugins_dir(struct tep_handle *pevent, const char *suffix,
+load_plugins_dir(struct tep_handle *tep, const char *suffix,
 		 const char *path,
-		 void (*load_plugin)(struct tep_handle *pevent,
+		 void (*load_plugin)(struct tep_handle *tep,
 				     const char *path,
 				     const char *name,
 				     void *data),
@@ -359,15 +359,15 @@ load_plugins_dir(struct tep_handle *pevent, const char *suffix,
 		if (strcmp(name + (strlen(name) - strlen(suffix)), suffix) != 0)
 			continue;
 
-		load_plugin(pevent, path, name, data);
+		load_plugin(tep, path, name, data);
 	}
 
 	closedir(dir);
 }
 
 static void
-load_plugins(struct tep_handle *pevent, const char *suffix,
-	     void (*load_plugin)(struct tep_handle *pevent,
+load_plugins(struct tep_handle *tep, const char *suffix,
+	     void (*load_plugin)(struct tep_handle *tep,
 				 const char *path,
 				 const char *name,
 				 void *data),
@@ -378,7 +378,7 @@ load_plugins(struct tep_handle *pevent, const char *suffix,
 	char *envdir;
 	int ret;
 
-	if (pevent->flags & TEP_DISABLE_PLUGINS)
+	if (tep->flags & TEP_DISABLE_PLUGINS)
 		return;
 
 	/*
@@ -386,8 +386,8 @@ load_plugins(struct tep_handle *pevent, const char *suffix,
 	 * check that first.
 	 */
 #ifdef PLUGIN_DIR
-	if (!(pevent->flags & TEP_DISABLE_SYS_PLUGINS))
-		load_plugins_dir(pevent, suffix, PLUGIN_DIR,
+	if (!(tep->flags & TEP_DISABLE_SYS_PLUGINS))
+		load_plugins_dir(tep, suffix, PLUGIN_DIR,
 				 load_plugin, data);
 #endif
 
@@ -397,7 +397,7 @@ load_plugins(struct tep_handle *pevent, const char *suffix,
 	 */
 	envdir = getenv("TRACEEVENT_PLUGIN_DIR");
 	if (envdir)
-		load_plugins_dir(pevent, suffix, envdir, load_plugin, data);
+		load_plugins_dir(tep, suffix, envdir, load_plugin, data);
 
 	/*
 	 * Now let the home directory override the environment
@@ -413,22 +413,22 @@ load_plugins(struct tep_handle *pevent, const char *suffix,
 		return;
 	}
 
-	load_plugins_dir(pevent, suffix, path, load_plugin, data);
+	load_plugins_dir(tep, suffix, path, load_plugin, data);
 
 	free(path);
 }
 
 struct tep_plugin_list*
-tep_load_plugins(struct tep_handle *pevent)
+tep_load_plugins(struct tep_handle *tep)
 {
 	struct tep_plugin_list *list = NULL;
 
-	load_plugins(pevent, ".so", load_plugin, &list);
+	load_plugins(tep, ".so", load_plugin, &list);
 	return list;
 }
 
 void
-tep_unload_plugins(struct tep_plugin_list *plugin_list, struct tep_handle *pevent)
+tep_unload_plugins(struct tep_plugin_list *plugin_list, struct tep_handle *tep)
 {
 	tep_plugin_unload_func func;
 	struct tep_plugin_list *list;
@@ -438,7 +438,7 @@ tep_unload_plugins(struct tep_plugin_list *plugin_list, struct tep_handle *peven
 		plugin_list = list->next;
 		func = dlsym(list->handle, TEP_PLUGIN_UNLOADER_NAME);
 		if (func)
-			func(pevent);
+			func(tep);
 		dlclose(list->handle);
 		free(list->name);
 		free(list);
diff --git a/tools/lib/traceevent/kbuffer-parse.c b/tools/lib/traceevent/kbuffer-parse.c
index af2a1f3b7424..b887e7437d67 100644
--- a/tools/lib/traceevent/kbuffer-parse.c
+++ b/tools/lib/traceevent/kbuffer-parse.c
@@ -727,3 +727,52 @@ int kbuffer_start_of_data(struct kbuffer *kbuf)
 {
 	return kbuf->start;
 }
+
+/**
+ * kbuffer_raw_get - get raw buffer info
+ * @kbuf:	The kbuffer
+ * @subbuf:	Start of mapped subbuffer
+ * @info:	Info descriptor to fill in
+ *
+ * For debugging. This can return internals of the ring buffer.
+ * Expects to have info->next set to what it will read.
+ * The type, length and timestamp delta will be filled in, and
+ * @info->next will be updated to the next element.
+ * The @subbuf is used to know if the info is passed the end of
+ * data and NULL will be returned if it is.
+ */
+struct kbuffer_raw_info *
+kbuffer_raw_get(struct kbuffer *kbuf, void *subbuf, struct kbuffer_raw_info *info)
+{
+	unsigned long long flags;
+	unsigned long long delta;
+	unsigned int type_len;
+	unsigned int size;
+	int start;
+	int length;
+	void *ptr = info->next;
+
+	if (!kbuf || !subbuf)
+		return NULL;
+
+	if (kbuf->flags & KBUFFER_FL_LONG_8)
+		start = 16;
+	else
+		start = 12;
+
+	flags = read_long(kbuf, subbuf + 8);
+	size = (unsigned int)flags & COMMIT_MASK;
+
+	if (ptr < subbuf || ptr >= subbuf + start + size)
+		return NULL;
+
+	type_len = translate_data(kbuf, ptr, &ptr, &delta, &length);
+
+	info->next = ptr + length;
+
+	info->type = type_len;
+	info->delta = delta;
+	info->length = length;
+
+	return info;
+}
diff --git a/tools/lib/traceevent/kbuffer.h b/tools/lib/traceevent/kbuffer.h
index 03dce757553f..ed4d697fc137 100644
--- a/tools/lib/traceevent/kbuffer.h
+++ b/tools/lib/traceevent/kbuffer.h
@@ -65,4 +65,17 @@ int kbuffer_subbuffer_size(struct kbuffer *kbuf);
 void kbuffer_set_old_format(struct kbuffer *kbuf);
 int kbuffer_start_of_data(struct kbuffer *kbuf);
 
+/* Debugging */
+
+struct kbuffer_raw_info {
+	int			type;
+	int			length;
+	unsigned long long	delta;
+	void			*next;
+};
+
+/* Read raw data */
+struct kbuffer_raw_info *kbuffer_raw_get(struct kbuffer *kbuf, void *subbuf,
+					 struct kbuffer_raw_info *info);
+
 #endif /* _K_BUFFER_H */
diff --git a/tools/lib/traceevent/parse-filter.c b/tools/lib/traceevent/parse-filter.c
index cb5ce66dab6e..552592d153fb 100644
--- a/tools/lib/traceevent/parse-filter.c
+++ b/tools/lib/traceevent/parse-filter.c
@@ -154,7 +154,7 @@ add_filter_type(struct tep_event_filter *filter, int id)
 
 	filter_type = &filter->event_filters[i];
 	filter_type->event_id = id;
-	filter_type->event = tep_find_event(filter->pevent, id);
+	filter_type->event = tep_find_event(filter->tep, id);
 	filter_type->filter = NULL;
 
 	filter->filters++;
@@ -164,9 +164,9 @@ add_filter_type(struct tep_event_filter *filter, int id)
 
 /**
  * tep_filter_alloc - create a new event filter
- * @pevent: The pevent that this filter is associated with
+ * @tep: The tep that this filter is associated with
  */
-struct tep_event_filter *tep_filter_alloc(struct tep_handle *pevent)
+struct tep_event_filter *tep_filter_alloc(struct tep_handle *tep)
 {
 	struct tep_event_filter *filter;
 
@@ -175,8 +175,8 @@ struct tep_event_filter *tep_filter_alloc(struct tep_handle *pevent)
 		return NULL;
 
 	memset(filter, 0, sizeof(*filter));
-	filter->pevent = pevent;
-	tep_ref(pevent);
+	filter->tep = tep;
+	tep_ref(tep);
 
 	return filter;
 }
@@ -256,7 +256,7 @@ static int event_match(struct tep_event *event,
 }
 
 static enum tep_errno
-find_event(struct tep_handle *pevent, struct event_list **events,
+find_event(struct tep_handle *tep, struct event_list **events,
 	   char *sys_name, char *event_name)
 {
 	struct tep_event *event;
@@ -299,8 +299,8 @@ find_event(struct tep_handle *pevent, struct event_list **events,
 		}
 	}
 
-	for (i = 0; i < pevent->nr_events; i++) {
-		event = pevent->events[i];
+	for (i = 0; i < tep->nr_events; i++) {
+		event = tep->events[i];
 		if (event_match(event, sys_name ? &sreg : NULL, &ereg)) {
 			match = 1;
 			if (add_event(events, event) < 0) {
@@ -1257,7 +1257,7 @@ static void filter_init_error_buf(struct tep_event_filter *filter)
 enum tep_errno tep_filter_add_filter_str(struct tep_event_filter *filter,
 					 const char *filter_str)
 {
-	struct tep_handle *pevent = filter->pevent;
+	struct tep_handle *tep = filter->tep;
 	struct event_list *event;
 	struct event_list *events = NULL;
 	const char *filter_start;
@@ -1313,7 +1313,7 @@ enum tep_errno tep_filter_add_filter_str(struct tep_event_filter *filter,
 		}
 
 		/* Find this event */
-		ret = find_event(pevent, &events, strim(sys_name), strim(event_name));
+		ret = find_event(tep, &events, strim(sys_name), strim(event_name));
 		if (ret < 0) {
 			free_events(events);
 			free(this_event);
@@ -1334,7 +1334,7 @@ enum tep_errno tep_filter_add_filter_str(struct tep_event_filter *filter,
 		if (ret < 0)
 			rtn = ret;
 
-		if (ret >= 0 && pevent->test_filters) {
+		if (ret >= 0 && tep->test_filters) {
 			char *test;
 			test = tep_filter_make_string(filter, event->event->id);
 			if (test) {
@@ -1346,9 +1346,6 @@ enum tep_errno tep_filter_add_filter_str(struct tep_event_filter *filter,
 
 	free_events(events);
 
-	if (rtn >= 0 && pevent->test_filters)
-		exit(0);
-
 	return rtn;
 }
 
@@ -1380,7 +1377,7 @@ int tep_filter_strerror(struct tep_event_filter *filter, enum tep_errno err,
 		return 0;
 	}
 
-	return tep_strerror(filter->pevent, err, buf, buflen);
+	return tep_strerror(filter->tep, err, buf, buflen);
 }
 
 /**
@@ -1443,7 +1440,7 @@ void tep_filter_reset(struct tep_event_filter *filter)
 
 void tep_filter_free(struct tep_event_filter *filter)
 {
-	tep_unref(filter->pevent);
+	tep_unref(filter->tep);
 
 	tep_filter_reset(filter);
 
@@ -1462,10 +1459,10 @@ static int copy_filter_type(struct tep_event_filter *filter,
 	const char *name;
 	char *str;
 
-	/* Can't assume that the pevent's are the same */
+	/* Can't assume that the tep's are the same */
 	sys = filter_type->event->system;
 	name = filter_type->event->name;
-	event = tep_find_event_by_name(filter->pevent, sys, name);
+	event = tep_find_event_by_name(filter->tep, sys, name);
 	if (!event)
 		return -1;
 
@@ -1522,167 +1519,6 @@ int tep_filter_copy(struct tep_event_filter *dest, struct tep_event_filter *sour
 	return ret;
 }
 
-
-/**
- * tep_update_trivial - update the trivial filters with the given filter
- * @dest - the filter to update
- * @source - the filter as the source of the update
- * @type - the type of trivial filter to update.
- *
- * Scan dest for trivial events matching @type to replace with the source.
- *
- * Returns 0 on success and -1 if there was a problem updating, but
- *   events may have still been updated on error.
- */
-int tep_update_trivial(struct tep_event_filter *dest, struct tep_event_filter *source,
-		       enum tep_filter_trivial_type type)
-{
-	struct tep_handle *src_pevent;
-	struct tep_handle *dest_pevent;
-	struct tep_event *event;
-	struct tep_filter_type *filter_type;
-	struct tep_filter_arg *arg;
-	char *str;
-	int i;
-
-	src_pevent = source->pevent;
-	dest_pevent = dest->pevent;
-
-	/* Do nothing if either of the filters has nothing to filter */
-	if (!dest->filters || !source->filters)
-		return 0;
-
-	for (i = 0; i < dest->filters; i++) {
-		filter_type = &dest->event_filters[i];
-		arg = filter_type->filter;
-		if (arg->type != TEP_FILTER_ARG_BOOLEAN)
-			continue;
-		if ((arg->boolean.value && type == TEP_FILTER_TRIVIAL_FALSE) ||
-		    (!arg->boolean.value && type == TEP_FILTER_TRIVIAL_TRUE))
-			continue;
-
-		event = filter_type->event;
-
-		if (src_pevent != dest_pevent) {
-			/* do a look up */
-			event = tep_find_event_by_name(src_pevent,
-						       event->system,
-						       event->name);
-			if (!event)
-				return -1;
-		}
-
-		str = tep_filter_make_string(source, event->id);
-		if (!str)
-			continue;
-
-		/* Don't bother if the filter is trivial too */
-		if (strcmp(str, "TRUE") != 0 && strcmp(str, "FALSE") != 0)
-			filter_event(dest, event, str, NULL);
-		free(str);
-	}
-	return 0;
-}
-
-/**
- * tep_filter_clear_trivial - clear TRUE and FALSE filters
- * @filter: the filter to remove trivial filters from
- * @type: remove only true, false, or both
- *
- * Removes filters that only contain a TRUE or FALES boolean arg.
- *
- * Returns 0 on success and -1 if there was a problem.
- */
-int tep_filter_clear_trivial(struct tep_event_filter *filter,
-			     enum tep_filter_trivial_type type)
-{
-	struct tep_filter_type *filter_type;
-	int count = 0;
-	int *ids = NULL;
-	int i;
-
-	if (!filter->filters)
-		return 0;
-
-	/*
-	 * Two steps, first get all ids with trivial filters.
-	 *  then remove those ids.
-	 */
-	for (i = 0; i < filter->filters; i++) {
-		int *new_ids;
-
-		filter_type = &filter->event_filters[i];
-		if (filter_type->filter->type != TEP_FILTER_ARG_BOOLEAN)
-			continue;
-		switch (type) {
-		case TEP_FILTER_TRIVIAL_FALSE:
-			if (filter_type->filter->boolean.value)
-				continue;
-			break;
-		case TEP_FILTER_TRIVIAL_TRUE:
-			if (!filter_type->filter->boolean.value)
-				continue;
-		default:
-			break;
-		}
-
-		new_ids = realloc(ids, sizeof(*ids) * (count + 1));
-		if (!new_ids) {
-			free(ids);
-			return -1;
-		}
-
-		ids = new_ids;
-		ids[count++] = filter_type->event_id;
-	}
-
-	if (!count)
-		return 0;
-
-	for (i = 0; i < count; i++)
-		tep_filter_remove_event(filter, ids[i]);
-
-	free(ids);
-	return 0;
-}
-
-/**
- * tep_filter_event_has_trivial - return true event contains trivial filter
- * @filter: the filter with the information
- * @event_id: the id of the event to test
- * @type: trivial type to test for (TRUE, FALSE, EITHER)
- *
- * Returns 1 if the event contains a matching trivial type
- *  otherwise 0.
- */
-int tep_filter_event_has_trivial(struct tep_event_filter *filter,
-				 int event_id,
-				 enum tep_filter_trivial_type type)
-{
-	struct tep_filter_type *filter_type;
-
-	if (!filter->filters)
-		return 0;
-
-	filter_type = find_filter_type(filter, event_id);
-
-	if (!filter_type)
-		return 0;
-
-	if (filter_type->filter->type != TEP_FILTER_ARG_BOOLEAN)
-		return 0;
-
-	switch (type) {
-	case TEP_FILTER_TRIVIAL_FALSE:
-		return !filter_type->filter->boolean.value;
-
-	case TEP_FILTER_TRIVIAL_TRUE:
-		return filter_type->filter->boolean.value;
-	default:
-		return 1;
-	}
-}
-
 static int test_filter(struct tep_event *event, struct tep_filter_arg *arg,
 		       struct tep_record *record, enum tep_errno *err);
 
@@ -1692,8 +1528,8 @@ get_comm(struct tep_event *event, struct tep_record *record)
 	const char *comm;
 	int pid;
 
-	pid = tep_data_pid(event->pevent, record);
-	comm = tep_data_comm_from_pid(event->pevent, pid);
+	pid = tep_data_pid(event->tep, record);
+	comm = tep_data_comm_from_pid(event->tep, pid);
 	return comm;
 }
 
@@ -1861,7 +1697,7 @@ static int test_num(struct tep_event *event, struct tep_filter_arg *arg,
 static const char *get_field_str(struct tep_filter_arg *arg, struct tep_record *record)
 {
 	struct tep_event *event;
-	struct tep_handle *pevent;
+	struct tep_handle *tep;
 	unsigned long long addr;
 	const char *val = NULL;
 	unsigned int size;
@@ -1891,12 +1727,12 @@ static const char *get_field_str(struct tep_filter_arg *arg, struct tep_record *
 
 	} else {
 		event = arg->str.field->event;
-		pevent = event->pevent;
+		tep = event->tep;
 		addr = get_value(event, arg->str.field, record);
 
 		if (arg->str.field->flags & (TEP_FIELD_IS_POINTER | TEP_FIELD_IS_LONG))
 			/* convert to a kernel symbol */
-			val = tep_find_function(pevent, addr);
+			val = tep_find_function(tep, addr);
 
 		if (val == NULL) {
 			/* just use the hex of the string name */
@@ -2036,7 +1872,7 @@ int tep_event_filtered(struct tep_event_filter *filter, int event_id)
 enum tep_errno tep_filter_match(struct tep_event_filter *filter,
 				struct tep_record *record)
 {
-	struct tep_handle *pevent = filter->pevent;
+	struct tep_handle *tep = filter->tep;
 	struct tep_filter_type *filter_type;
 	int event_id;
 	int ret;
@@ -2047,7 +1883,7 @@ enum tep_errno tep_filter_match(struct tep_event_filter *filter,
 	if (!filter->filters)
 		return TEP_ERRNO__NO_FILTER;
 
-	event_id = tep_data_type(pevent, record);
+	event_id = tep_data_type(tep, record);
 
 	filter_type = find_filter_type(filter, event_id);
 	if (!filter_type)
@@ -2409,14 +2245,6 @@ int tep_filter_compare(struct tep_event_filter *filter1, struct tep_event_filter
 			break;
 		if (filter_type1->filter->type != filter_type2->filter->type)
 			break;
-		switch (filter_type1->filter->type) {
-		case TEP_FILTER_TRIVIAL_FALSE:
-		case TEP_FILTER_TRIVIAL_TRUE:
-			/* trivial types just need the type compared */
-			continue;
-		default:
-			break;
-		}
 		/* The best way to compare complex filters is with strings */
 		str1 = arg_to_str(filter1, filter_type1->filter);
 		str2 = arg_to_str(filter2, filter_type2->filter);
diff --git a/tools/lib/traceevent/parse-utils.c b/tools/lib/traceevent/parse-utils.c
index 77e4ec6402dd..e99867111387 100644
--- a/tools/lib/traceevent/parse-utils.c
+++ b/tools/lib/traceevent/parse-utils.c
@@ -14,7 +14,7 @@
 void __vwarning(const char *fmt, va_list ap)
 {
 	if (errno)
-		perror("trace-cmd");
+		perror("libtraceevent");
 	errno = 0;
 
 	fprintf(stderr, "  ");
diff --git a/tools/lib/traceevent/plugin_cfg80211.c b/tools/lib/traceevent/plugin_cfg80211.c
index a51b366f47da..3d43b56a6c98 100644
--- a/tools/lib/traceevent/plugin_cfg80211.c
+++ b/tools/lib/traceevent/plugin_cfg80211.c
@@ -25,9 +25,9 @@ process___le16_to_cpup(struct trace_seq *s, unsigned long long *args)
 	return val ? (long long) le16toh(*val) : 0;
 }
 
-int TEP_PLUGIN_LOADER(struct tep_handle *pevent)
+int TEP_PLUGIN_LOADER(struct tep_handle *tep)
 {
-	tep_register_print_function(pevent,
+	tep_register_print_function(tep,
 				    process___le16_to_cpup,
 				    TEP_FUNC_ARG_INT,
 				    "__le16_to_cpup",
@@ -36,8 +36,8 @@ int TEP_PLUGIN_LOADER(struct tep_handle *pevent)
 	return 0;
 }
 
-void TEP_PLUGIN_UNLOADER(struct tep_handle *pevent)
+void TEP_PLUGIN_UNLOADER(struct tep_handle *tep)
 {
-	tep_unregister_print_function(pevent, process___le16_to_cpup,
+	tep_unregister_print_function(tep, process___le16_to_cpup,
 				      "__le16_to_cpup");
 }
diff --git a/tools/lib/traceevent/plugin_function.c b/tools/lib/traceevent/plugin_function.c
index a73eca34a8f9..7770fcb78e0f 100644
--- a/tools/lib/traceevent/plugin_function.c
+++ b/tools/lib/traceevent/plugin_function.c
@@ -126,7 +126,7 @@ static int add_and_get_index(const char *parent, const char *child, int cpu)
 static int function_handler(struct trace_seq *s, struct tep_record *record,
 			    struct tep_event *event, void *context)
 {
-	struct tep_handle *pevent = event->pevent;
+	struct tep_handle *tep = event->tep;
 	unsigned long long function;
 	unsigned long long pfunction;
 	const char *func;
@@ -136,12 +136,12 @@ static int function_handler(struct trace_seq *s, struct tep_record *record,
 	if (tep_get_field_val(s, event, "ip", record, &function, 1))
 		return trace_seq_putc(s, '!');
 
-	func = tep_find_function(pevent, function);
+	func = tep_find_function(tep, function);
 
 	if (tep_get_field_val(s, event, "parent_ip", record, &pfunction, 1))
 		return trace_seq_putc(s, '!');
 
-	parent = tep_find_function(pevent, pfunction);
+	parent = tep_find_function(tep, pfunction);
 
 	if (parent && ftrace_indent->set)
 		index = add_and_get_index(parent, func, record->cpu);
@@ -164,9 +164,9 @@ static int function_handler(struct trace_seq *s, struct tep_record *record,
 	return 0;
 }
 
-int TEP_PLUGIN_LOADER(struct tep_handle *pevent)
+int TEP_PLUGIN_LOADER(struct tep_handle *tep)
 {
-	tep_register_event_handler(pevent, -1, "ftrace", "function",
+	tep_register_event_handler(tep, -1, "ftrace", "function",
 				   function_handler, NULL);
 
 	tep_plugin_add_options("ftrace", plugin_options);
@@ -174,11 +174,11 @@ int TEP_PLUGIN_LOADER(struct tep_handle *pevent)
 	return 0;
 }
 
-void TEP_PLUGIN_UNLOADER(struct tep_handle *pevent)
+void TEP_PLUGIN_UNLOADER(struct tep_handle *tep)
 {
 	int i, x;
 
-	tep_unregister_event_handler(pevent, -1, "ftrace", "function",
+	tep_unregister_event_handler(tep, -1, "ftrace", "function",
 				     function_handler, NULL);
 
 	for (i = 0; i <= cpus; i++) {
diff --git a/tools/lib/traceevent/plugin_hrtimer.c b/tools/lib/traceevent/plugin_hrtimer.c
index 5db5e401275f..bb434e0ed03a 100644
--- a/tools/lib/traceevent/plugin_hrtimer.c
+++ b/tools/lib/traceevent/plugin_hrtimer.c
@@ -67,23 +67,23 @@ static int timer_start_handler(struct trace_seq *s,
 	return 0;
 }
 
-int TEP_PLUGIN_LOADER(struct tep_handle *pevent)
+int TEP_PLUGIN_LOADER(struct tep_handle *tep)
 {
-	tep_register_event_handler(pevent, -1,
+	tep_register_event_handler(tep, -1,
 				   "timer", "hrtimer_expire_entry",
 				   timer_expire_handler, NULL);
 
-	tep_register_event_handler(pevent, -1, "timer", "hrtimer_start",
+	tep_register_event_handler(tep, -1, "timer", "hrtimer_start",
 				   timer_start_handler, NULL);
 	return 0;
 }
 
-void TEP_PLUGIN_UNLOADER(struct tep_handle *pevent)
+void TEP_PLUGIN_UNLOADER(struct tep_handle *tep)
 {
-	tep_unregister_event_handler(pevent, -1,
+	tep_unregister_event_handler(tep, -1,
 				     "timer", "hrtimer_expire_entry",
 				     timer_expire_handler, NULL);
 
-	tep_unregister_event_handler(pevent, -1, "timer", "hrtimer_start",
+	tep_unregister_event_handler(tep, -1, "timer", "hrtimer_start",
 				     timer_start_handler, NULL);
 }
diff --git a/tools/lib/traceevent/plugin_jbd2.c b/tools/lib/traceevent/plugin_jbd2.c
index a5e34135dd6a..04fc125f38cb 100644
--- a/tools/lib/traceevent/plugin_jbd2.c
+++ b/tools/lib/traceevent/plugin_jbd2.c
@@ -48,16 +48,16 @@ process_jiffies_to_msecs(struct trace_seq *s, unsigned long long *args)
 	return jiffies;
 }
 
-int TEP_PLUGIN_LOADER(struct tep_handle *pevent)
+int TEP_PLUGIN_LOADER(struct tep_handle *tep)
 {
-	tep_register_print_function(pevent,
+	tep_register_print_function(tep,
 				    process_jbd2_dev_to_name,
 				    TEP_FUNC_ARG_STRING,
 				    "jbd2_dev_to_name",
 				    TEP_FUNC_ARG_INT,
 				    TEP_FUNC_ARG_VOID);
 
-	tep_register_print_function(pevent,
+	tep_register_print_function(tep,
 				    process_jiffies_to_msecs,
 				    TEP_FUNC_ARG_LONG,
 				    "jiffies_to_msecs",
@@ -66,11 +66,11 @@ int TEP_PLUGIN_LOADER(struct tep_handle *pevent)
 	return 0;
 }
 
-void TEP_PLUGIN_UNLOADER(struct tep_handle *pevent)
+void TEP_PLUGIN_UNLOADER(struct tep_handle *tep)
 {
-	tep_unregister_print_function(pevent, process_jbd2_dev_to_name,
+	tep_unregister_print_function(tep, process_jbd2_dev_to_name,
 				      "jbd2_dev_to_name");
 
-	tep_unregister_print_function(pevent, process_jiffies_to_msecs,
+	tep_unregister_print_function(tep, process_jiffies_to_msecs,
 				      "jiffies_to_msecs");
 }
diff --git a/tools/lib/traceevent/plugin_kmem.c b/tools/lib/traceevent/plugin_kmem.c
index 0e3c601f9ed1..edaec5d962c3 100644
--- a/tools/lib/traceevent/plugin_kmem.c
+++ b/tools/lib/traceevent/plugin_kmem.c
@@ -39,57 +39,57 @@ static int call_site_handler(struct trace_seq *s, struct tep_record *record,
 	if (tep_read_number_field(field, data, &val))
 		return 1;
 
-	func = tep_find_function(event->pevent, val);
+	func = tep_find_function(event->tep, val);
 	if (!func)
 		return 1;
 
-	addr = tep_find_function_address(event->pevent, val);
+	addr = tep_find_function_address(event->tep, val);
 
 	trace_seq_printf(s, "(%s+0x%x) ", func, (int)(val - addr));
 	return 1;
 }
 
-int TEP_PLUGIN_LOADER(struct tep_handle *pevent)
+int TEP_PLUGIN_LOADER(struct tep_handle *tep)
 {
-	tep_register_event_handler(pevent, -1, "kmem", "kfree",
+	tep_register_event_handler(tep, -1, "kmem", "kfree",
 				   call_site_handler, NULL);
 
-	tep_register_event_handler(pevent, -1, "kmem", "kmalloc",
+	tep_register_event_handler(tep, -1, "kmem", "kmalloc",
 				   call_site_handler, NULL);
 
-	tep_register_event_handler(pevent, -1, "kmem", "kmalloc_node",
+	tep_register_event_handler(tep, -1, "kmem", "kmalloc_node",
 				   call_site_handler, NULL);
 
-	tep_register_event_handler(pevent, -1, "kmem", "kmem_cache_alloc",
+	tep_register_event_handler(tep, -1, "kmem", "kmem_cache_alloc",
 				   call_site_handler, NULL);
 
-	tep_register_event_handler(pevent, -1, "kmem",
+	tep_register_event_handler(tep, -1, "kmem",
 				   "kmem_cache_alloc_node",
 				   call_site_handler, NULL);
 
-	tep_register_event_handler(pevent, -1, "kmem", "kmem_cache_free",
+	tep_register_event_handler(tep, -1, "kmem", "kmem_cache_free",
 				   call_site_handler, NULL);
 	return 0;
 }
 
-void TEP_PLUGIN_UNLOADER(struct tep_handle *pevent)
+void TEP_PLUGIN_UNLOADER(struct tep_handle *tep)
 {
-	tep_unregister_event_handler(pevent, -1, "kmem", "kfree",
+	tep_unregister_event_handler(tep, -1, "kmem", "kfree",
 				     call_site_handler, NULL);
 
-	tep_unregister_event_handler(pevent, -1, "kmem", "kmalloc",
+	tep_unregister_event_handler(tep, -1, "kmem", "kmalloc",
 				     call_site_handler, NULL);
 
-	tep_unregister_event_handler(pevent, -1, "kmem", "kmalloc_node",
+	tep_unregister_event_handler(tep, -1, "kmem", "kmalloc_node",
 				     call_site_handler, NULL);
 
-	tep_unregister_event_handler(pevent, -1, "kmem", "kmem_cache_alloc",
+	tep_unregister_event_handler(tep, -1, "kmem", "kmem_cache_alloc",
 				     call_site_handler, NULL);
 
-	tep_unregister_event_handler(pevent, -1, "kmem",
+	tep_unregister_event_handler(tep, -1, "kmem",
 				     "kmem_cache_alloc_node",
 				     call_site_handler, NULL);
 
-	tep_unregister_event_handler(pevent, -1, "kmem", "kmem_cache_free",
+	tep_unregister_event_handler(tep, -1, "kmem", "kmem_cache_free",
 				     call_site_handler, NULL);
 }
diff --git a/tools/lib/traceevent/plugin_kvm.c b/tools/lib/traceevent/plugin_kvm.c
index 64b9c25a1fd3..c8e623065a7e 100644
--- a/tools/lib/traceevent/plugin_kvm.c
+++ b/tools/lib/traceevent/plugin_kvm.c
@@ -389,8 +389,8 @@ static int kvm_mmu_print_role(struct trace_seq *s, struct tep_record *record,
 	 * We can only use the structure if file is of the same
 	 * endianness.
 	 */
-	if (tep_file_bigendian(event->pevent) ==
-	    tep_is_host_bigendian(event->pevent)) {
+	if (tep_is_file_bigendian(event->tep) ==
+	    tep_is_local_bigendian(event->tep)) {
 
 		trace_seq_printf(s, "%u q%u%s %s%s %spae %snxe %swp%s%s%s",
 				 role.level,
@@ -445,40 +445,40 @@ process_is_writable_pte(struct trace_seq *s, unsigned long long *args)
 	return pte & PT_WRITABLE_MASK;
 }
 
-int TEP_PLUGIN_LOADER(struct tep_handle *pevent)
+int TEP_PLUGIN_LOADER(struct tep_handle *tep)
 {
 	init_disassembler();
 
-	tep_register_event_handler(pevent, -1, "kvm", "kvm_exit",
+	tep_register_event_handler(tep, -1, "kvm", "kvm_exit",
 				   kvm_exit_handler, NULL);
 
-	tep_register_event_handler(pevent, -1, "kvm", "kvm_emulate_insn",
+	tep_register_event_handler(tep, -1, "kvm", "kvm_emulate_insn",
 				   kvm_emulate_insn_handler, NULL);
 
-	tep_register_event_handler(pevent, -1, "kvm", "kvm_nested_vmexit",
+	tep_register_event_handler(tep, -1, "kvm", "kvm_nested_vmexit",
 				   kvm_nested_vmexit_handler, NULL);
 
-	tep_register_event_handler(pevent, -1, "kvm", "kvm_nested_vmexit_inject",
+	tep_register_event_handler(tep, -1, "kvm", "kvm_nested_vmexit_inject",
 				   kvm_nested_vmexit_inject_handler, NULL);
 
-	tep_register_event_handler(pevent, -1, "kvmmmu", "kvm_mmu_get_page",
+	tep_register_event_handler(tep, -1, "kvmmmu", "kvm_mmu_get_page",
 				   kvm_mmu_get_page_handler, NULL);
 
-	tep_register_event_handler(pevent, -1, "kvmmmu", "kvm_mmu_sync_page",
+	tep_register_event_handler(tep, -1, "kvmmmu", "kvm_mmu_sync_page",
 				   kvm_mmu_print_role, NULL);
 
-	tep_register_event_handler(pevent, -1,
+	tep_register_event_handler(tep, -1,
 				   "kvmmmu", "kvm_mmu_unsync_page",
 				   kvm_mmu_print_role, NULL);
 
-	tep_register_event_handler(pevent, -1, "kvmmmu", "kvm_mmu_zap_page",
+	tep_register_event_handler(tep, -1, "kvmmmu", "kvm_mmu_zap_page",
 				   kvm_mmu_print_role, NULL);
 
-	tep_register_event_handler(pevent, -1, "kvmmmu",
+	tep_register_event_handler(tep, -1, "kvmmmu",
 			"kvm_mmu_prepare_zap_page", kvm_mmu_print_role,
 			NULL);
 
-	tep_register_print_function(pevent,
+	tep_register_print_function(tep,
 				    process_is_writable_pte,
 				    TEP_FUNC_ARG_INT,
 				    "is_writable_pte",
@@ -487,37 +487,37 @@ int TEP_PLUGIN_LOADER(struct tep_handle *pevent)
 	return 0;
 }
 
-void TEP_PLUGIN_UNLOADER(struct tep_handle *pevent)
+void TEP_PLUGIN_UNLOADER(struct tep_handle *tep)
 {
-	tep_unregister_event_handler(pevent, -1, "kvm", "kvm_exit",
+	tep_unregister_event_handler(tep, -1, "kvm", "kvm_exit",
 				     kvm_exit_handler, NULL);
 
-	tep_unregister_event_handler(pevent, -1, "kvm", "kvm_emulate_insn",
+	tep_unregister_event_handler(tep, -1, "kvm", "kvm_emulate_insn",
 				     kvm_emulate_insn_handler, NULL);
 
-	tep_unregister_event_handler(pevent, -1, "kvm", "kvm_nested_vmexit",
+	tep_unregister_event_handler(tep, -1, "kvm", "kvm_nested_vmexit",
 				     kvm_nested_vmexit_handler, NULL);
 
-	tep_unregister_event_handler(pevent, -1, "kvm", "kvm_nested_vmexit_inject",
+	tep_unregister_event_handler(tep, -1, "kvm", "kvm_nested_vmexit_inject",
 				     kvm_nested_vmexit_inject_handler, NULL);
 
-	tep_unregister_event_handler(pevent, -1, "kvmmmu", "kvm_mmu_get_page",
+	tep_unregister_event_handler(tep, -1, "kvmmmu", "kvm_mmu_get_page",
 				     kvm_mmu_get_page_handler, NULL);
 
-	tep_unregister_event_handler(pevent, -1, "kvmmmu", "kvm_mmu_sync_page",
+	tep_unregister_event_handler(tep, -1, "kvmmmu", "kvm_mmu_sync_page",
 				     kvm_mmu_print_role, NULL);
 
-	tep_unregister_event_handler(pevent, -1,
+	tep_unregister_event_handler(tep, -1,
 				     "kvmmmu", "kvm_mmu_unsync_page",
 				     kvm_mmu_print_role, NULL);
 
-	tep_unregister_event_handler(pevent, -1, "kvmmmu", "kvm_mmu_zap_page",
+	tep_unregister_event_handler(tep, -1, "kvmmmu", "kvm_mmu_zap_page",
 				     kvm_mmu_print_role, NULL);
 
-	tep_unregister_event_handler(pevent, -1, "kvmmmu",
+	tep_unregister_event_handler(tep, -1, "kvmmmu",
 			"kvm_mmu_prepare_zap_page", kvm_mmu_print_role,
 			NULL);
 
-	tep_unregister_print_function(pevent, process_is_writable_pte,
+	tep_unregister_print_function(tep, process_is_writable_pte,
 				      "is_writable_pte");
 }
diff --git a/tools/lib/traceevent/plugin_mac80211.c b/tools/lib/traceevent/plugin_mac80211.c
index e38b9477aad2..884303c26b5c 100644
--- a/tools/lib/traceevent/plugin_mac80211.c
+++ b/tools/lib/traceevent/plugin_mac80211.c
@@ -87,17 +87,17 @@ static int drv_bss_info_changed(struct trace_seq *s,
 	return 0;
 }
 
-int TEP_PLUGIN_LOADER(struct tep_handle *pevent)
+int TEP_PLUGIN_LOADER(struct tep_handle *tep)
 {
-	tep_register_event_handler(pevent, -1, "mac80211",
+	tep_register_event_handler(tep, -1, "mac80211",
 				   "drv_bss_info_changed",
 				   drv_bss_info_changed, NULL);
 	return 0;
 }
 
-void TEP_PLUGIN_UNLOADER(struct tep_handle *pevent)
+void TEP_PLUGIN_UNLOADER(struct tep_handle *tep)
 {
-	tep_unregister_event_handler(pevent, -1, "mac80211",
+	tep_unregister_event_handler(tep, -1, "mac80211",
 				     "drv_bss_info_changed",
 				     drv_bss_info_changed, NULL);
 }
diff --git a/tools/lib/traceevent/plugin_sched_switch.c b/tools/lib/traceevent/plugin_sched_switch.c
index 834c9e378ff8..957389a0ff7a 100644
--- a/tools/lib/traceevent/plugin_sched_switch.c
+++ b/tools/lib/traceevent/plugin_sched_switch.c
@@ -62,7 +62,7 @@ static void write_and_save_comm(struct tep_format_field *field,
 	comm = &s->buffer[len];
 
 	/* Help out the comm to ids. This will handle dups */
-	tep_register_comm(field->event->pevent, comm, pid);
+	tep_register_comm(field->event->tep, comm, pid);
 }
 
 static int sched_wakeup_handler(struct trace_seq *s,
@@ -135,27 +135,27 @@ static int sched_switch_handler(struct trace_seq *s,
 	return 0;
 }
 
-int TEP_PLUGIN_LOADER(struct tep_handle *pevent)
+int TEP_PLUGIN_LOADER(struct tep_handle *tep)
 {
-	tep_register_event_handler(pevent, -1, "sched", "sched_switch",
+	tep_register_event_handler(tep, -1, "sched", "sched_switch",
 				   sched_switch_handler, NULL);
 
-	tep_register_event_handler(pevent, -1, "sched", "sched_wakeup",
+	tep_register_event_handler(tep, -1, "sched", "sched_wakeup",
 				   sched_wakeup_handler, NULL);
 
-	tep_register_event_handler(pevent, -1, "sched", "sched_wakeup_new",
+	tep_register_event_handler(tep, -1, "sched", "sched_wakeup_new",
 				   sched_wakeup_handler, NULL);
 	return 0;
 }
 
-void TEP_PLUGIN_UNLOADER(struct tep_handle *pevent)
+void TEP_PLUGIN_UNLOADER(struct tep_handle *tep)
 {
-	tep_unregister_event_handler(pevent, -1, "sched", "sched_switch",
+	tep_unregister_event_handler(tep, -1, "sched", "sched_switch",
 				     sched_switch_handler, NULL);
 
-	tep_unregister_event_handler(pevent, -1, "sched", "sched_wakeup",
+	tep_unregister_event_handler(tep, -1, "sched", "sched_wakeup",
 				     sched_wakeup_handler, NULL);
 
-	tep_unregister_event_handler(pevent, -1, "sched", "sched_wakeup_new",
+	tep_unregister_event_handler(tep, -1, "sched", "sched_wakeup_new",
 				     sched_wakeup_handler, NULL);
 }
diff --git a/tools/lib/traceevent/plugin_scsi.c b/tools/lib/traceevent/plugin_scsi.c
index 4eba25cc1431..5d0387a4b65a 100644
--- a/tools/lib/traceevent/plugin_scsi.c
+++ b/tools/lib/traceevent/plugin_scsi.c
@@ -414,9 +414,9 @@ unsigned long long process_scsi_trace_parse_cdb(struct trace_seq *s,
 	return 0;
 }
 
-int TEP_PLUGIN_LOADER(struct tep_handle *pevent)
+int TEP_PLUGIN_LOADER(struct tep_handle *tep)
 {
-	tep_register_print_function(pevent,
+	tep_register_print_function(tep,
 				    process_scsi_trace_parse_cdb,
 				    TEP_FUNC_ARG_STRING,
 				    "scsi_trace_parse_cdb",
@@ -427,8 +427,8 @@ int TEP_PLUGIN_LOADER(struct tep_handle *pevent)
 	return 0;
 }
 
-void TEP_PLUGIN_UNLOADER(struct tep_handle *pevent)
+void TEP_PLUGIN_UNLOADER(struct tep_handle *tep)
 {
-	tep_unregister_print_function(pevent, process_scsi_trace_parse_cdb,
+	tep_unregister_print_function(tep, process_scsi_trace_parse_cdb,
 				      "scsi_trace_parse_cdb");
 }
diff --git a/tools/lib/traceevent/plugin_xen.c b/tools/lib/traceevent/plugin_xen.c
index bc0496e4c296..993b208d0323 100644
--- a/tools/lib/traceevent/plugin_xen.c
+++ b/tools/lib/traceevent/plugin_xen.c
@@ -120,9 +120,9 @@ unsigned long long process_xen_hypercall_name(struct trace_seq *s,
 	return 0;
 }
 
-int TEP_PLUGIN_LOADER(struct tep_handle *pevent)
+int TEP_PLUGIN_LOADER(struct tep_handle *tep)
 {
-	tep_register_print_function(pevent,
+	tep_register_print_function(tep,
 				    process_xen_hypercall_name,
 				    TEP_FUNC_ARG_STRING,
 				    "xen_hypercall_name",
@@ -131,8 +131,8 @@ int TEP_PLUGIN_LOADER(struct tep_handle *pevent)
 	return 0;
 }
 
-void TEP_PLUGIN_UNLOADER(struct tep_handle *pevent)
+void TEP_PLUGIN_UNLOADER(struct tep_handle *tep)
 {
-	tep_unregister_print_function(pevent, process_xen_hypercall_name,
+	tep_unregister_print_function(tep, process_xen_hypercall_name,
 				      "xen_hypercall_name");
 }
diff --git a/tools/memory-model/Documentation/explanation.txt b/tools/memory-model/Documentation/explanation.txt
index 35bff92cc773..68caa9a976d0 100644
--- a/tools/memory-model/Documentation/explanation.txt
+++ b/tools/memory-model/Documentation/explanation.txt
@@ -27,7 +27,7 @@ Explanation of the Linux-Kernel Memory Consistency Model
   19. AND THEN THERE WAS ALPHA
   20. THE HAPPENS-BEFORE RELATION: hb
   21. THE PROPAGATES-BEFORE RELATION: pb
-  22. RCU RELATIONS: rcu-link, gp, rscs, rcu-fence, and rb
+  22. RCU RELATIONS: rcu-link, rcu-gp, rcu-rscsi, rcu-fence, and rb
   23. LOCKING
   24. ODDS AND ENDS
 
@@ -1430,8 +1430,8 @@ they execute means that it cannot have cycles.  This requirement is
 the content of the LKMM's "propagation" axiom.
 
 
-RCU RELATIONS: rcu-link, gp, rscs, rcu-fence, and rb
-----------------------------------------------------
+RCU RELATIONS: rcu-link, rcu-gp, rcu-rscsi, rcu-fence, and rb
+-------------------------------------------------------------
 
 RCU (Read-Copy-Update) is a powerful synchronization mechanism.  It
 rests on two concepts: grace periods and read-side critical sections.
@@ -1446,17 +1446,19 @@ As far as memory models are concerned, RCU's main feature is its
 Grace-Period Guarantee, which states that a critical section can never
 span a full grace period.  In more detail, the Guarantee says:
 
-	If a critical section starts before a grace period then it
-	must end before the grace period does.  In addition, every
-	store that propagates to the critical section's CPU before the
-	end of the critical section must propagate to every CPU before
-	the end of the grace period.
+	For any critical section C and any grace period G, at least
+	one of the following statements must hold:
 
-	If a critical section ends after a grace period ends then it
-	must start after the grace period does.  In addition, every
-	store that propagates to the grace period's CPU before the
-	start of the grace period must propagate to every CPU before
-	the start of the critical section.
+(1)	C ends before G does, and in addition, every store that
+	propagates to C's CPU before the end of C must propagate to
+	every CPU before G ends.
+
+(2)	G starts before C does, and in addition, every store that
+	propagates to G's CPU before the start of G must propagate
+	to every CPU before C starts.
+
+In particular, it is not possible for a critical section to both start
+before and end after a grace period.
 
 Here is a simple example of RCU in action:
 
@@ -1483,10 +1485,11 @@ The Grace Period Guarantee tells us that when this code runs, it will
 never end with r1 = 1 and r2 = 0.  The reasoning is as follows.  r1 = 1
 means that P0's store to x propagated to P1 before P1 called
 synchronize_rcu(), so P0's critical section must have started before
-P1's grace period.  On the other hand, r2 = 0 means that P0's store to
-y, which occurs before the end of the critical section, did not
-propagate to P1 before the end of the grace period, violating the
-Guarantee.
+P1's grace period, contrary to part (2) of the Guarantee.  On the
+other hand, r2 = 0 means that P0's store to y, which occurs before the
+end of the critical section, did not propagate to P1 before the end of
+the grace period, contrary to part (1).  Together the results violate
+the Guarantee.
 
 In the kernel's implementations of RCU, the requirements for stores
 to propagate to every CPU are fulfilled by placing strong fences at
@@ -1504,11 +1507,11 @@ before" or "ends after" a grace period?  Some aspects of the meaning
 are pretty obvious, as in the example above, but the details aren't
 entirely clear.  The LKMM formalizes this notion by means of the
 rcu-link relation.  rcu-link encompasses a very general notion of
-"before": Among other things, X ->rcu-link Z includes cases where X
-happens-before or is equal to some event Y which is equal to or comes
-before Z in the coherence order.  When Y = Z this says that X ->rfe Z
-implies X ->rcu-link Z.  In addition, when Y = X it says that X ->fr Z
-and X ->co Z each imply X ->rcu-link Z.
+"before": If E and F are RCU fence events (i.e., rcu_read_lock(),
+rcu_read_unlock(), or synchronize_rcu()) then among other things,
+E ->rcu-link F includes cases where E is po-before some memory-access
+event X, F is po-after some memory-access event Y, and we have any of
+X ->rfe Y, X ->co Y, or X ->fr Y.
 
 The formal definition of the rcu-link relation is more than a little
 obscure, and we won't give it here.  It is closely related to the pb
@@ -1516,171 +1519,173 @@ relation, and the details don't matter unless you want to comb through
 a somewhat lengthy formal proof.  Pretty much all you need to know
 about rcu-link is the information in the preceding paragraph.
 
-The LKMM also defines the gp and rscs relations.  They bring grace
-periods and read-side critical sections into the picture, in the
+The LKMM also defines the rcu-gp and rcu-rscsi relations.  They bring
+grace periods and read-side critical sections into the picture, in the
 following way:
 
-	E ->gp F means there is a synchronize_rcu() fence event S such
-	that E ->po S and either S ->po F or S = F.  In simple terms,
-	there is a grace period po-between E and F.
+	E ->rcu-gp F means that E and F are in fact the same event,
+	and that event is a synchronize_rcu() fence (i.e., a grace
+	period).
 
-	E ->rscs F means there is a critical section delimited by an
-	rcu_read_lock() fence L and an rcu_read_unlock() fence U, such
-	that E ->po U and either L ->po F or L = F.  You can think of
-	this as saying that E and F are in the same critical section
-	(in fact, it also allows E to be po-before the start of the
-	critical section and F to be po-after the end).
+	E ->rcu-rscsi F means that E and F are the rcu_read_unlock()
+	and rcu_read_lock() fence events delimiting some read-side
+	critical section.  (The 'i' at the end of the name emphasizes
+	that this relation is "inverted": It links the end of the
+	critical section to the start.)
 
 If we think of the rcu-link relation as standing for an extended
-"before", then X ->gp Y ->rcu-link Z says that X executes before a
-grace period which ends before Z executes.  (In fact it covers more
-than this, because it also includes cases where X executes before a
-grace period and some store propagates to Z's CPU before Z executes
-but doesn't propagate to some other CPU until after the grace period
-ends.)  Similarly, X ->rscs Y ->rcu-link Z says that X is part of (or
-before the start of) a critical section which starts before Z
-executes.
-
-The LKMM goes on to define the rcu-fence relation as a sequence of gp
-and rscs links separated by rcu-link links, in which the number of gp
-links is >= the number of rscs links.  For example:
+"before", then X ->rcu-gp Y ->rcu-link Z roughly says that X is a
+grace period which ends before Z begins.  (In fact it covers more than
+this, because it also includes cases where some store propagates to
+Z's CPU before Z begins but doesn't propagate to some other CPU until
+after X ends.)  Similarly, X ->rcu-rscsi Y ->rcu-link Z says that X is
+the end of a critical section which starts before Z begins.
+
+The LKMM goes on to define the rcu-fence relation as a sequence of
+rcu-gp and rcu-rscsi links separated by rcu-link links, in which the
+number of rcu-gp links is >= the number of rcu-rscsi links.  For
+example:
 
-	X ->gp Y ->rcu-link Z ->rscs T ->rcu-link U ->gp V
+	X ->rcu-gp Y ->rcu-link Z ->rcu-rscsi T ->rcu-link U ->rcu-gp V
 
 would imply that X ->rcu-fence V, because this sequence contains two
-gp links and only one rscs link.  (It also implies that X ->rcu-fence T
-and Z ->rcu-fence V.)  On the other hand:
+rcu-gp links and one rcu-rscsi link.  (It also implies that
+X ->rcu-fence T and Z ->rcu-fence V.)  On the other hand:
 
-	X ->rscs Y ->rcu-link Z ->rscs T ->rcu-link U ->gp V
+	X ->rcu-rscsi Y ->rcu-link Z ->rcu-rscsi T ->rcu-link U ->rcu-gp V
 
 does not imply X ->rcu-fence V, because the sequence contains only
-one gp link but two rscs links.
+one rcu-gp link but two rcu-rscsi links.
 
 The rcu-fence relation is important because the Grace Period Guarantee
 means that rcu-fence acts kind of like a strong fence.  In particular,
-if W is a write and we have W ->rcu-fence Z, the Guarantee says that W
-will propagate to every CPU before Z executes.
+E ->rcu-fence F implies not only that E begins before F ends, but also
+that any write po-before E will propagate to every CPU before any
+instruction po-after F can execute.  (However, it does not imply that
+E must execute before F; in fact, each synchronize_rcu() fence event
+is linked to itself by rcu-fence as a degenerate case.)
 
 To prove this in full generality requires some intellectual effort.
 We'll consider just a very simple case:
 
-	W ->gp X ->rcu-link Y ->rscs Z.
+	G ->rcu-gp W ->rcu-link Z ->rcu-rscsi F.
 
-This formula means that there is a grace period G and a critical
-section C such that:
+This formula means that G and W are the same event (a grace period),
+and there are events X, Y and a read-side critical section C such that:
 
-	1. W is po-before G;
+	1. G = W is po-before or equal to X;
 
-	2. X is equal to or po-after G;
+	2. X comes "before" Y in some sense (including rfe, co and fr);
 
-	3. X comes "before" Y in some sense;
+	2. Y is po-before Z;
 
-	4. Y is po-before the end of C;
+	4. Z is the rcu_read_unlock() event marking the end of C;
 
-	5. Z is equal to or po-after the start of C.
+	5. F is the rcu_read_lock() event marking the start of C.
 
-From 2 - 4 we deduce that the grace period G ends before the critical
-section C.  Then the second part of the Grace Period Guarantee says
-not only that G starts before C does, but also that W (which executes
-on G's CPU before G starts) must propagate to every CPU before C
-starts.  In particular, W propagates to every CPU before Z executes
-(or finishes executing, in the case where Z is equal to the
-rcu_read_lock() fence event which starts C.)  This sort of reasoning
-can be expanded to handle all the situations covered by rcu-fence.
+From 1 - 4 we deduce that the grace period G ends before the critical
+section C.  Then part (2) of the Grace Period Guarantee says not only
+that G starts before C does, but also that any write which executes on
+G's CPU before G starts must propagate to every CPU before C starts.
+In particular, the write propagates to every CPU before F finishes
+executing and hence before any instruction po-after F can execute.
+This sort of reasoning can be extended to handle all the situations
+covered by rcu-fence.
 
 Finally, the LKMM defines the RCU-before (rb) relation in terms of
 rcu-fence.  This is done in essentially the same way as the pb
 relation was defined in terms of strong-fence.  We will omit the
-details; the end result is that E ->rb F implies E must execute before
-F, just as E ->pb F does (and for much the same reasons).
+details; the end result is that E ->rb F implies E must execute
+before F, just as E ->pb F does (and for much the same reasons).
 
 Putting this all together, the LKMM expresses the Grace Period
 Guarantee by requiring that the rb relation does not contain a cycle.
-Equivalently, this "rcu" axiom requires that there are no events E and
-F with E ->rcu-link F ->rcu-fence E.  Or to put it a third way, the
-axiom requires that there are no cycles consisting of gp and rscs
-alternating with rcu-link, where the number of gp links is >= the
-number of rscs links.
+Equivalently, this "rcu" axiom requires that there are no events E
+and F with E ->rcu-link F ->rcu-fence E.  Or to put it a third way,
+the axiom requires that there are no cycles consisting of rcu-gp and
+rcu-rscsi alternating with rcu-link, where the number of rcu-gp links
+is >= the number of rcu-rscsi links.
 
 Justifying the axiom isn't easy, but it is in fact a valid
 formalization of the Grace Period Guarantee.  We won't attempt to go
 through the detailed argument, but the following analysis gives a
-taste of what is involved.  Suppose we have a violation of the first
-part of the Guarantee: A critical section starts before a grace
-period, and some store propagates to the critical section's CPU before
-the end of the critical section but doesn't propagate to some other
-CPU until after the end of the grace period.
+taste of what is involved.  Suppose both parts of the Guarantee are
+violated: A critical section starts before a grace period, and some
+store propagates to the critical section's CPU before the end of the
+critical section but doesn't propagate to some other CPU until after
+the end of the grace period.
 
 Putting symbols to these ideas, let L and U be the rcu_read_lock() and
 rcu_read_unlock() fence events delimiting the critical section in
 question, and let S be the synchronize_rcu() fence event for the grace
 period.  Saying that the critical section starts before S means there
-are events E and F where E is po-after L (which marks the start of the
-critical section), E is "before" F in the sense of the rcu-link
-relation, and F is po-before the grace period S:
+are events Q and R where Q is po-after L (which marks the start of the
+critical section), Q is "before" R in the sense used by the rcu-link
+relation, and R is po-before the grace period S.  Thus we have:
 
-	L ->po E ->rcu-link F ->po S.
+	L ->rcu-link S.
 
-Let W be the store mentioned above, let Z come before the end of the
+Let W be the store mentioned above, let Y come before the end of the
 critical section and witness that W propagates to the critical
-section's CPU by reading from W, and let Y on some arbitrary CPU be a
-witness that W has not propagated to that CPU, where Y happens after
+section's CPU by reading from W, and let Z on some arbitrary CPU be a
+witness that W has not propagated to that CPU, where Z happens after
 some event X which is po-after S.  Symbolically, this amounts to:
 
-	S ->po X ->hb* Y ->fr W ->rf Z ->po U.
+	S ->po X ->hb* Z ->fr W ->rf Y ->po U.
 
-The fr link from Y to W indicates that W has not propagated to Y's CPU
-at the time that Y executes.  From this, it can be shown (see the
-discussion of the rcu-link relation earlier) that X and Z are related
-by rcu-link, yielding:
+The fr link from Z to W indicates that W has not propagated to Z's CPU
+at the time that Z executes.  From this, it can be shown (see the
+discussion of the rcu-link relation earlier) that S and U are related
+by rcu-link:
 
-	S ->po X ->rcu-link Z ->po U.
+	S ->rcu-link U.
 
-The formulas say that S is po-between F and X, hence F ->gp X.  They
-also say that Z comes before the end of the critical section and E
-comes after its start, hence Z ->rscs E.  From all this we obtain:
+Since S is a grace period we have S ->rcu-gp S, and since L and U are
+the start and end of the critical section C we have U ->rcu-rscsi L.
+From this we obtain:
 
-	F ->gp X ->rcu-link Z ->rscs E ->rcu-link F,
+	S ->rcu-gp S ->rcu-link U ->rcu-rscsi L ->rcu-link S,
 
 a forbidden cycle.  Thus the "rcu" axiom rules out this violation of
 the Grace Period Guarantee.
 
 For something a little more down-to-earth, let's see how the axiom
 works out in practice.  Consider the RCU code example from above, this
-time with statement labels added to the memory access instructions:
+time with statement labels added:
 
 	int x, y;
 
 	P0()
 	{
-		rcu_read_lock();
-		W: WRITE_ONCE(x, 1);
-		X: WRITE_ONCE(y, 1);
-		rcu_read_unlock();
+		L: rcu_read_lock();
+		X: WRITE_ONCE(x, 1);
+		Y: WRITE_ONCE(y, 1);
+		U: rcu_read_unlock();
 	}
 
 	P1()
 	{
 		int r1, r2;
 
-		Y: r1 = READ_ONCE(x);
-		synchronize_rcu();
-		Z: r2 = READ_ONCE(y);
+		Z: r1 = READ_ONCE(x);
+		S: synchronize_rcu();
+		W: r2 = READ_ONCE(y);
 	}
 
 
-If r2 = 0 at the end then P0's store at X overwrites the value that
-P1's load at Z reads from, so we have Z ->fre X and thus Z ->rcu-link X.
-In addition, there is a synchronize_rcu() between Y and Z, so therefore
-we have Y ->gp Z.
+If r2 = 0 at the end then P0's store at Y overwrites the value that
+P1's load at W reads from, so we have W ->fre Y.  Since S ->po W and
+also Y ->po U, we get S ->rcu-link U.  In addition, S ->rcu-gp S
+because S is a grace period.
 
-If r1 = 1 at the end then P1's load at Y reads from P0's store at W,
-so we have W ->rcu-link Y.  In addition, W and X are in the same critical
-section, so therefore we have X ->rscs W.
+If r1 = 1 at the end then P1's load at Z reads from P0's store at X,
+so we have X ->rfe Z.  Together with L ->po X and Z ->po S, this
+yields L ->rcu-link S.  And since L and U are the start and end of a
+critical section, we have U ->rcu-rscsi L.
 
-Then X ->rscs W ->rcu-link Y ->gp Z ->rcu-link X is a forbidden cycle,
-violating the "rcu" axiom.  Hence the outcome is not allowed by the
-LKMM, as we would expect.
+Then U ->rcu-rscsi L ->rcu-link S ->rcu-gp S ->rcu-link U is a
+forbidden cycle, violating the "rcu" axiom.  Hence the outcome is not
+allowed by the LKMM, as we would expect.
 
 For contrast, let's see what can happen in a more complicated example:
 
@@ -1690,51 +1695,52 @@ For contrast, let's see what can happen in a more complicated example:
 	{
 		int r0;
 
-		rcu_read_lock();
-		W: r0 = READ_ONCE(x);
-		X: WRITE_ONCE(y, 1);
-		rcu_read_unlock();
+		L0: rcu_read_lock();
+		    r0 = READ_ONCE(x);
+		    WRITE_ONCE(y, 1);
+		U0: rcu_read_unlock();
 	}
 
 	P1()
 	{
 		int r1;
 
-		Y: r1 = READ_ONCE(y);
-		synchronize_rcu();
-		Z: WRITE_ONCE(z, 1);
+		    r1 = READ_ONCE(y);
+		S1: synchronize_rcu();
+		    WRITE_ONCE(z, 1);
 	}
 
 	P2()
 	{
 		int r2;
 
-		rcu_read_lock();
-		U: r2 = READ_ONCE(z);
-		V: WRITE_ONCE(x, 1);
-		rcu_read_unlock();
+		L2: rcu_read_lock();
+		    r2 = READ_ONCE(z);
+		    WRITE_ONCE(x, 1);
+		U2: rcu_read_unlock();
 	}
 
 If r0 = r1 = r2 = 1 at the end, then similar reasoning to before shows
-that W ->rscs X ->rcu-link Y ->gp Z ->rcu-link U ->rscs V ->rcu-link W.
-However this cycle is not forbidden, because the sequence of relations
-contains fewer instances of gp (one) than of rscs (two).  Consequently
-the outcome is allowed by the LKMM.  The following instruction timing
-diagram shows how it might actually occur:
+that U0 ->rcu-rscsi L0 ->rcu-link S1 ->rcu-gp S1 ->rcu-link U2 ->rcu-rscsi
+L2 ->rcu-link U0.  However this cycle is not forbidden, because the
+sequence of relations contains fewer instances of rcu-gp (one) than of
+rcu-rscsi (two).  Consequently the outcome is allowed by the LKMM.
+The following instruction timing diagram shows how it might actually
+occur:
 
 P0			P1			P2
 --------------------	--------------------	--------------------
 rcu_read_lock()
-X: WRITE_ONCE(y, 1)
-			Y: r1 = READ_ONCE(y)
+WRITE_ONCE(y, 1)
+			r1 = READ_ONCE(y)
 			synchronize_rcu() starts
 			.			rcu_read_lock()
-			.			V: WRITE_ONCE(x, 1)
-W: r0 = READ_ONCE(x)	.
+			.			WRITE_ONCE(x, 1)
+r0 = READ_ONCE(x)	.
 rcu_read_unlock()	.
 			synchronize_rcu() ends
-			Z: WRITE_ONCE(z, 1)
-						U: r2 = READ_ONCE(z)
+			WRITE_ONCE(z, 1)
+						r2 = READ_ONCE(z)
 						rcu_read_unlock()
 
 This requires P0 and P2 to execute their loads and stores out of
@@ -1744,6 +1750,15 @@ section in P0 both starts before P1's grace period does and ends
 before it does, and the critical section in P2 both starts after P1's
 grace period does and ends after it does.
 
+Addendum: The LKMM now supports SRCU (Sleepable Read-Copy-Update) in
+addition to normal RCU.  The ideas involved are much the same as
+above, with new relations srcu-gp and srcu-rscsi added to represent
+SRCU grace periods and read-side critical sections.  There is a
+restriction on the srcu-gp and srcu-rscsi links that can appear in an
+rcu-fence sequence (the srcu-rscsi links must be paired with srcu-gp
+links having the same SRCU domain with proper nesting); the details
+are relatively unimportant.
+
 
 LOCKING
 -------
diff --git a/tools/memory-model/README b/tools/memory-model/README
index 0f2c366518c6..2b87f3971548 100644
--- a/tools/memory-model/README
+++ b/tools/memory-model/README
@@ -20,13 +20,17 @@ that litmus test to be exercised within the Linux kernel.
 REQUIREMENTS
 ============
 
-Version 7.49 of the "herd7" and "klitmus7" tools must be downloaded
-separately:
+Version 7.52 or higher of the "herd7" and "klitmus7" tools must be
+downloaded separately:
 
   https://github.com/herd/herdtools7
 
 See "herdtools7/INSTALL.md" for installation instructions.
 
+Note that although these tools usually provide backwards compatibility,
+this is not absolutely guaranteed.  Therefore, if a later version does
+not work, please try using the exact version called out above.
+
 
 ==================
 BASIC USAGE: HERD7
@@ -221,8 +225,29 @@ The Linux-kernel memory model has the following limitations:
 		additional call_rcu() process to the site of the
 		emulated rcu-barrier().
 
-	e.	Sleepable RCU (SRCU) is not modeled.  It can be
-		emulated, but perhaps not simply.
+	e.	Although sleepable RCU (SRCU) is now modeled, there
+		are some subtle differences between its semantics and
+		those in the Linux kernel.  For example, the kernel
+		might interpret the following sequence as two partially
+		overlapping SRCU read-side critical sections:
+
+			 1  r1 = srcu_read_lock(&my_srcu);
+			 2  do_something_1();
+			 3  r2 = srcu_read_lock(&my_srcu);
+			 4  do_something_2();
+			 5  srcu_read_unlock(&my_srcu, r1);
+			 6  do_something_3();
+			 7  srcu_read_unlock(&my_srcu, r2);
+
+		In contrast, LKMM will interpret this as a nested pair of
+		SRCU read-side critical sections, with the outer critical
+		section spanning lines 1-7 and the inner critical section
+		spanning lines 3-5.
+
+		This difference would be more of a concern had anyone
+		identified a reasonable use case for partially overlapping
+		SRCU read-side critical sections.  For more information,
+		please see: https://paulmck.livejournal.com/40593.html
 
 	f.	Reader-writer locking is not modeled.  It can be
 		emulated in litmus tests using atomic read-modify-write
diff --git a/tools/memory-model/linux-kernel.bell b/tools/memory-model/linux-kernel.bell
index 796513362c05..def9131d3d8e 100644
--- a/tools/memory-model/linux-kernel.bell
+++ b/tools/memory-model/linux-kernel.bell
@@ -33,8 +33,14 @@ enum Barriers = 'wmb (*smp_wmb*) ||
 		'after-unlock-lock (*smp_mb__after_unlock_lock*)
 instructions F[Barriers]
 
+(* SRCU *)
+enum SRCU = 'srcu-lock || 'srcu-unlock || 'sync-srcu
+instructions SRCU[SRCU]
+(* All srcu events *)
+let Srcu = Srcu-lock | Srcu-unlock | Sync-srcu
+
 (* Compute matching pairs of nested Rcu-lock and Rcu-unlock *)
-let matched = let rec
+let rcu-rscs = let rec
 	    unmatched-locks = Rcu-lock \ domain(matched)
 	and unmatched-unlocks = Rcu-unlock \ range(matched)
 	and unmatched = unmatched-locks | unmatched-unlocks
@@ -46,8 +52,27 @@ let matched = let rec
 	in matched
 
 (* Validate nesting *)
-flag ~empty Rcu-lock \ domain(matched) as unbalanced-rcu-locking
-flag ~empty Rcu-unlock \ range(matched) as unbalanced-rcu-locking
+flag ~empty Rcu-lock \ domain(rcu-rscs) as unbalanced-rcu-locking
+flag ~empty Rcu-unlock \ range(rcu-rscs) as unbalanced-rcu-locking
+
+(* Compute matching pairs of nested Srcu-lock and Srcu-unlock *)
+let srcu-rscs = let rec
+	    unmatched-locks = Srcu-lock \ domain(matched)
+	and unmatched-unlocks = Srcu-unlock \ range(matched)
+	and unmatched = unmatched-locks | unmatched-unlocks
+	and unmatched-po = ([unmatched] ; po ; [unmatched]) & loc
+	and unmatched-locks-to-unlocks =
+		([unmatched-locks] ; po ; [unmatched-unlocks]) & loc
+	and matched = matched | (unmatched-locks-to-unlocks \
+		(unmatched-po ; unmatched-po))
+	in matched
+
+(* Validate nesting *)
+flag ~empty Srcu-lock \ domain(srcu-rscs) as unbalanced-srcu-locking
+flag ~empty Srcu-unlock \ range(srcu-rscs) as unbalanced-srcu-locking
+
+(* Check for use of synchronize_srcu() inside an RCU critical section *)
+flag ~empty rcu-rscs & (po ; [Sync-srcu] ; po) as invalid-sleep
 
-(* Outermost level of nesting only *)
-let crit = matched \ (po^-1 ; matched ; po^-1)
+(* Validate SRCU dynamic match *)
+flag ~empty different-values(srcu-rscs) as srcu-bad-nesting
diff --git a/tools/memory-model/linux-kernel.cat b/tools/memory-model/linux-kernel.cat
index 8f23c74a96fd..8dcb37835b61 100644
--- a/tools/memory-model/linux-kernel.cat
+++ b/tools/memory-model/linux-kernel.cat
@@ -33,7 +33,7 @@ let mb = ([M] ; fencerel(Mb) ; [M]) |
 	([M] ; po? ; [LKW] ; fencerel(After-spinlock) ; [M]) |
 	([M] ; po ; [UL] ; (co | po) ; [LKW] ;
 		fencerel(After-unlock-lock) ; [M])
-let gp = po ; [Sync-rcu] ; po?
+let gp = po ; [Sync-rcu | Sync-srcu] ; po?
 
 let strong-fence = mb | gp
 
@@ -91,32 +91,47 @@ acyclic pb as propagation
 (*******)
 
 (*
- * Effect of read-side critical section proceeds from the rcu_read_lock()
- * onward on the one hand and from the rcu_read_unlock() backwards on the
- * other hand.
+ * Effects of read-side critical sections proceed from the rcu_read_unlock()
+ * or srcu_read_unlock() backwards on the one hand, and from the
+ * rcu_read_lock() or srcu_read_lock() forwards on the other hand.
+ *
+ * In the definition of rcu-fence below, the po term at the left-hand side
+ * of each disjunct and the po? term at the right-hand end have been factored
+ * out.  They have been moved into the definitions of rcu-link and rb.
+ * This was necessary in order to apply the "& loc" tests correctly.
  *)
-let rscs = po ; crit^-1 ; po?
+let rcu-gp = [Sync-rcu]		(* Compare with gp *)
+let srcu-gp = [Sync-srcu]
+let rcu-rscsi = rcu-rscs^-1
+let srcu-rscsi = srcu-rscs^-1
 
 (*
  * The synchronize_rcu() strong fence is special in that it can order not
  * one but two non-rf relations, but only in conjunction with an RCU
  * read-side critical section.
  *)
-let rcu-link = hb* ; pb* ; prop
+let rcu-link = po? ; hb* ; pb* ; prop ; po
 
 (*
  * Any sequence containing at least as many grace periods as RCU read-side
  * critical sections (joined by rcu-link) acts as a generalized strong fence.
+ * Likewise for SRCU grace periods and read-side critical sections, provided
+ * the synchronize_srcu() and srcu_read_[un]lock() calls refer to the same
+ * struct srcu_struct location.
  *)
-let rec rcu-fence = gp |
-	(gp ; rcu-link ; rscs) |
-	(rscs ; rcu-link ; gp) |
-	(gp ; rcu-link ; rcu-fence ; rcu-link ; rscs) |
-	(rscs ; rcu-link ; rcu-fence ; rcu-link ; gp) |
+let rec rcu-fence = rcu-gp | srcu-gp |
+	(rcu-gp ; rcu-link ; rcu-rscsi) |
+	((srcu-gp ; rcu-link ; srcu-rscsi) & loc) |
+	(rcu-rscsi ; rcu-link ; rcu-gp) |
+	((srcu-rscsi ; rcu-link ; srcu-gp) & loc) |
+	(rcu-gp ; rcu-link ; rcu-fence ; rcu-link ; rcu-rscsi) |
+	((srcu-gp ; rcu-link ; rcu-fence ; rcu-link ; srcu-rscsi) & loc) |
+	(rcu-rscsi ; rcu-link ; rcu-fence ; rcu-link ; rcu-gp) |
+	((srcu-rscsi ; rcu-link ; rcu-fence ; rcu-link ; srcu-gp) & loc) |
 	(rcu-fence ; rcu-link ; rcu-fence)
 
 (* rb orders instructions just as pb does *)
-let rb = prop ; rcu-fence ; hb* ; pb*
+let rb = prop ; po ; rcu-fence ; po? ; hb* ; pb*
 
 irreflexive rb as rcu
 
diff --git a/tools/memory-model/linux-kernel.def b/tools/memory-model/linux-kernel.def
index b27911cc087d..551eeaa389d4 100644
--- a/tools/memory-model/linux-kernel.def
+++ b/tools/memory-model/linux-kernel.def
@@ -47,6 +47,12 @@ rcu_read_unlock() { __fence{rcu-unlock}; }
 synchronize_rcu() { __fence{sync-rcu}; }
 synchronize_rcu_expedited() { __fence{sync-rcu}; }
 
+// SRCU
+srcu_read_lock(X)  __srcu{srcu-lock}(X)
+srcu_read_unlock(X,Y) { __srcu{srcu-unlock}(X,Y); }
+synchronize_srcu(X)  { __srcu{sync-srcu}(X); }
+synchronize_srcu_expedited(X)  { __srcu{sync-srcu}(X); }
+
 // Atomic
 atomic_read(X) READ_ONCE(*X)
 atomic_set(X,V) { WRITE_ONCE(*X,V); }
diff --git a/tools/memory-model/lock.cat b/tools/memory-model/lock.cat
index 305ded17e741..a059d1a6d8a2 100644
--- a/tools/memory-model/lock.cat
+++ b/tools/memory-model/lock.cat
@@ -6,9 +6,6 @@
 
 (*
  * Generate coherence orders and handle lock operations
- *
- * Warning: spin_is_locked() crashes herd7 versions strictly before 7.48.
- * spin_is_locked() is functional from herd7 version 7.49.
  *)
 
 include "cross.cat"
diff --git a/tools/objtool/Makefile b/tools/objtool/Makefile
index c9d038f91af6..53f8be0f4a1f 100644
--- a/tools/objtool/Makefile
+++ b/tools/objtool/Makefile
@@ -25,14 +25,17 @@ LIBSUBCMD		= $(LIBSUBCMD_OUTPUT)libsubcmd.a
 OBJTOOL    := $(OUTPUT)objtool
 OBJTOOL_IN := $(OBJTOOL)-in.o
 
+LIBELF_FLAGS := $(shell pkg-config libelf --cflags 2>/dev/null)
+LIBELF_LIBS  := $(shell pkg-config libelf --libs 2>/dev/null || echo -lelf)
+
 all: $(OBJTOOL)
 
 INCLUDES := -I$(srctree)/tools/include \
 	    -I$(srctree)/tools/arch/$(HOSTARCH)/include/uapi \
 	    -I$(srctree)/tools/objtool/arch/$(ARCH)/include
 WARNINGS := $(EXTRA_WARNINGS) -Wno-switch-default -Wno-switch-enum -Wno-packed
-CFLAGS   += -Werror $(WARNINGS) $(KBUILD_HOSTCFLAGS) -g $(INCLUDES)
-LDFLAGS  += -lelf $(LIBSUBCMD) $(KBUILD_HOSTLDFLAGS)
+CFLAGS   += -Werror $(WARNINGS) $(KBUILD_HOSTCFLAGS) -g $(INCLUDES) $(LIBELF_FLAGS)
+LDFLAGS  += $(LIBELF_LIBS) $(LIBSUBCMD) $(KBUILD_HOSTLDFLAGS)
 
 # Allow old libelf to be used:
 elfshdr := $(shell echo '$(pound)include <libelf.h>' | $(CC) $(CFLAGS) -x c -E - | grep elf_getshdr)
diff --git a/tools/objtool/arch.h b/tools/objtool/arch.h
index b0d7dc3d71b5..7a111a77b7aa 100644
--- a/tools/objtool/arch.h
+++ b/tools/objtool/arch.h
@@ -33,7 +33,11 @@
 #define INSN_STACK		8
 #define INSN_BUG		9
 #define INSN_NOP		10
-#define INSN_OTHER		11
+#define INSN_STAC		11
+#define INSN_CLAC		12
+#define INSN_STD		13
+#define INSN_CLD		14
+#define INSN_OTHER		15
 #define INSN_LAST		INSN_OTHER
 
 enum op_dest_type {
@@ -41,6 +45,7 @@ enum op_dest_type {
 	OP_DEST_REG_INDIRECT,
 	OP_DEST_MEM,
 	OP_DEST_PUSH,
+	OP_DEST_PUSHF,
 	OP_DEST_LEAVE,
 };
 
@@ -55,6 +60,7 @@ enum op_src_type {
 	OP_SRC_REG_INDIRECT,
 	OP_SRC_CONST,
 	OP_SRC_POP,
+	OP_SRC_POPF,
 	OP_SRC_ADD,
 	OP_SRC_AND,
 };
diff --git a/tools/objtool/arch/x86/decode.c b/tools/objtool/arch/x86/decode.c
index 540a209b78ab..472e991f6512 100644
--- a/tools/objtool/arch/x86/decode.c
+++ b/tools/objtool/arch/x86/decode.c
@@ -357,19 +357,26 @@ int arch_decode_instruction(struct elf *elf, struct section *sec,
 		/* pushf */
 		*type = INSN_STACK;
 		op->src.type = OP_SRC_CONST;
-		op->dest.type = OP_DEST_PUSH;
+		op->dest.type = OP_DEST_PUSHF;
 		break;
 
 	case 0x9d:
 		/* popf */
 		*type = INSN_STACK;
-		op->src.type = OP_SRC_POP;
+		op->src.type = OP_SRC_POPF;
 		op->dest.type = OP_DEST_MEM;
 		break;
 
 	case 0x0f:
 
-		if (op2 >= 0x80 && op2 <= 0x8f) {
+		if (op2 == 0x01) {
+
+			if (modrm == 0xca)
+				*type = INSN_CLAC;
+			else if (modrm == 0xcb)
+				*type = INSN_STAC;
+
+		} else if (op2 >= 0x80 && op2 <= 0x8f) {
 
 			*type = INSN_JUMP_CONDITIONAL;
 
@@ -444,6 +451,14 @@ int arch_decode_instruction(struct elf *elf, struct section *sec,
 		*type = INSN_CALL;
 		break;
 
+	case 0xfc:
+		*type = INSN_CLD;
+		break;
+
+	case 0xfd:
+		*type = INSN_STD;
+		break;
+
 	case 0xff:
 		if (modrm_reg == 2 || modrm_reg == 3)
 
diff --git a/tools/objtool/builtin-check.c b/tools/objtool/builtin-check.c
index 694abc628e9b..f3b378126011 100644
--- a/tools/objtool/builtin-check.c
+++ b/tools/objtool/builtin-check.c
@@ -29,7 +29,7 @@
 #include "builtin.h"
 #include "check.h"
 
-bool no_fp, no_unreachable, retpoline, module;
+bool no_fp, no_unreachable, retpoline, module, backtrace, uaccess;
 
 static const char * const check_usage[] = {
 	"objtool check [<options>] file.o",
@@ -41,6 +41,8 @@ const struct option check_options[] = {
 	OPT_BOOLEAN('u', "no-unreachable", &no_unreachable, "Skip 'unreachable instruction' warnings"),
 	OPT_BOOLEAN('r', "retpoline", &retpoline, "Validate retpoline assumptions"),
 	OPT_BOOLEAN('m', "module", &module, "Indicates the object will be part of a kernel module"),
+	OPT_BOOLEAN('b', "backtrace", &backtrace, "unwind on error"),
+	OPT_BOOLEAN('a', "uaccess", &uaccess, "enable uaccess checking"),
 	OPT_END(),
 };
 
diff --git a/tools/objtool/builtin.h b/tools/objtool/builtin.h
index 28ff40e19a14..69762f9c5602 100644
--- a/tools/objtool/builtin.h
+++ b/tools/objtool/builtin.h
@@ -20,7 +20,7 @@
 #include <subcmd/parse-options.h>
 
 extern const struct option check_options[];
-extern bool no_fp, no_unreachable, retpoline, module;
+extern bool no_fp, no_unreachable, retpoline, module, backtrace, uaccess;
 
 extern int cmd_check(int argc, const char **argv);
 extern int cmd_orc(int argc, const char **argv);
diff --git a/tools/objtool/check.c b/tools/objtool/check.c
index 5dde107083c6..ac743a1d53ab 100644
--- a/tools/objtool/check.c
+++ b/tools/objtool/check.c
@@ -31,6 +31,7 @@
 struct alternative {
 	struct list_head list;
 	struct instruction *insn;
+	bool skip_orig;
 };
 
 const char *objname;
@@ -105,29 +106,6 @@ static struct instruction *next_insn_same_func(struct objtool_file *file,
 	     insn = next_insn_same_sec(file, insn))
 
 /*
- * Check if the function has been manually whitelisted with the
- * STACK_FRAME_NON_STANDARD macro, or if it should be automatically whitelisted
- * due to its use of a context switching instruction.
- */
-static bool ignore_func(struct objtool_file *file, struct symbol *func)
-{
-	struct rela *rela;
-
-	/* check for STACK_FRAME_NON_STANDARD */
-	if (file->whitelist && file->whitelist->rela)
-		list_for_each_entry(rela, &file->whitelist->rela->rela_list, list) {
-			if (rela->sym->type == STT_SECTION &&
-			    rela->sym->sec == func->sec &&
-			    rela->addend == func->offset)
-				return true;
-			if (rela->sym->type == STT_FUNC && rela->sym == func)
-				return true;
-		}
-
-	return false;
-}
-
-/*
  * This checks to see if the given function is a "noreturn" function.
  *
  * For global functions which are outside the scope of this object file, we
@@ -165,6 +143,7 @@ static int __dead_end_function(struct objtool_file *file, struct symbol *func,
 		"fortify_panic",
 		"usercopy_abort",
 		"machine_real_restart",
+		"rewind_stack_do_exit",
 	};
 
 	if (func->bind == STB_WEAK)
@@ -436,18 +415,107 @@ static void add_ignores(struct objtool_file *file)
 	struct instruction *insn;
 	struct section *sec;
 	struct symbol *func;
+	struct rela *rela;
 
-	for_each_sec(file, sec) {
-		list_for_each_entry(func, &sec->symbol_list, list) {
-			if (func->type != STT_FUNC)
-				continue;
+	sec = find_section_by_name(file->elf, ".rela.discard.func_stack_frame_non_standard");
+	if (!sec)
+		return;
 
-			if (!ignore_func(file, func))
+	list_for_each_entry(rela, &sec->rela_list, list) {
+		switch (rela->sym->type) {
+		case STT_FUNC:
+			func = rela->sym;
+			break;
+
+		case STT_SECTION:
+			func = find_symbol_by_offset(rela->sym->sec, rela->addend);
+			if (!func || func->type != STT_FUNC)
 				continue;
+			break;
 
-			func_for_each_insn_all(file, func, insn)
-				insn->ignore = true;
+		default:
+			WARN("unexpected relocation symbol type in %s: %d", sec->name, rela->sym->type);
+			continue;
 		}
+
+		func_for_each_insn_all(file, func, insn)
+			insn->ignore = true;
+	}
+}
+
+/*
+ * This is a whitelist of functions that is allowed to be called with AC set.
+ * The list is meant to be minimal and only contains compiler instrumentation
+ * ABI and a few functions used to implement *_{to,from}_user() functions.
+ *
+ * These functions must not directly change AC, but may PUSHF/POPF.
+ */
+static const char *uaccess_safe_builtin[] = {
+	/* KASAN */
+	"kasan_report",
+	"check_memory_region",
+	/* KASAN out-of-line */
+	"__asan_loadN_noabort",
+	"__asan_load1_noabort",
+	"__asan_load2_noabort",
+	"__asan_load4_noabort",
+	"__asan_load8_noabort",
+	"__asan_load16_noabort",
+	"__asan_storeN_noabort",
+	"__asan_store1_noabort",
+	"__asan_store2_noabort",
+	"__asan_store4_noabort",
+	"__asan_store8_noabort",
+	"__asan_store16_noabort",
+	/* KASAN in-line */
+	"__asan_report_load_n_noabort",
+	"__asan_report_load1_noabort",
+	"__asan_report_load2_noabort",
+	"__asan_report_load4_noabort",
+	"__asan_report_load8_noabort",
+	"__asan_report_load16_noabort",
+	"__asan_report_store_n_noabort",
+	"__asan_report_store1_noabort",
+	"__asan_report_store2_noabort",
+	"__asan_report_store4_noabort",
+	"__asan_report_store8_noabort",
+	"__asan_report_store16_noabort",
+	/* KCOV */
+	"write_comp_data",
+	"__sanitizer_cov_trace_pc",
+	"__sanitizer_cov_trace_const_cmp1",
+	"__sanitizer_cov_trace_const_cmp2",
+	"__sanitizer_cov_trace_const_cmp4",
+	"__sanitizer_cov_trace_const_cmp8",
+	"__sanitizer_cov_trace_cmp1",
+	"__sanitizer_cov_trace_cmp2",
+	"__sanitizer_cov_trace_cmp4",
+	"__sanitizer_cov_trace_cmp8",
+	/* UBSAN */
+	"ubsan_type_mismatch_common",
+	"__ubsan_handle_type_mismatch",
+	"__ubsan_handle_type_mismatch_v1",
+	/* misc */
+	"csum_partial_copy_generic",
+	"__memcpy_mcsafe",
+	"ftrace_likely_update", /* CONFIG_TRACE_BRANCH_PROFILING */
+	NULL
+};
+
+static void add_uaccess_safe(struct objtool_file *file)
+{
+	struct symbol *func;
+	const char **name;
+
+	if (!uaccess)
+		return;
+
+	for (name = uaccess_safe_builtin; *name; name++) {
+		func = find_symbol_by_name(file->elf, *name);
+		if (!func)
+			continue;
+
+		func->alias->uaccess_safe = true;
 	}
 }
 
@@ -457,13 +525,13 @@ static void add_ignores(struct objtool_file *file)
  * But it at least allows objtool to understand the control flow *around* the
  * retpoline.
  */
-static int add_nospec_ignores(struct objtool_file *file)
+static int add_ignore_alternatives(struct objtool_file *file)
 {
 	struct section *sec;
 	struct rela *rela;
 	struct instruction *insn;
 
-	sec = find_section_by_name(file->elf, ".rela.discard.nospec");
+	sec = find_section_by_name(file->elf, ".rela.discard.ignore_alts");
 	if (!sec)
 		return 0;
 
@@ -475,7 +543,7 @@ static int add_nospec_ignores(struct objtool_file *file)
 
 		insn = find_insn(file, rela->sym->sec, rela->addend);
 		if (!insn) {
-			WARN("bad .discard.nospec entry");
+			WARN("bad .discard.ignore_alts entry");
 			return -1;
 		}
 
@@ -524,7 +592,8 @@ static int add_jump_destinations(struct objtool_file *file)
 			continue;
 		} else {
 			/* sibling call */
-			insn->jump_dest = 0;
+			insn->call_dest = rela->sym;
+			insn->jump_dest = NULL;
 			continue;
 		}
 
@@ -546,25 +615,38 @@ static int add_jump_destinations(struct objtool_file *file)
 		}
 
 		/*
-		 * For GCC 8+, create parent/child links for any cold
-		 * subfunctions.  This is _mostly_ redundant with a similar
-		 * initialization in read_symbols().
-		 *
-		 * If a function has aliases, we want the *first* such function
-		 * in the symbol table to be the subfunction's parent.  In that
-		 * case we overwrite the initialization done in read_symbols().
-		 *
-		 * However this code can't completely replace the
-		 * read_symbols() code because this doesn't detect the case
-		 * where the parent function's only reference to a subfunction
-		 * is through a switch table.
+		 * Cross-function jump.
 		 */
 		if (insn->func && insn->jump_dest->func &&
-		    insn->func != insn->jump_dest->func &&
-		    !strstr(insn->func->name, ".cold.") &&
-		    strstr(insn->jump_dest->func->name, ".cold.")) {
-			insn->func->cfunc = insn->jump_dest->func;
-			insn->jump_dest->func->pfunc = insn->func;
+		    insn->func != insn->jump_dest->func) {
+
+			/*
+			 * For GCC 8+, create parent/child links for any cold
+			 * subfunctions.  This is _mostly_ redundant with a
+			 * similar initialization in read_symbols().
+			 *
+			 * If a function has aliases, we want the *first* such
+			 * function in the symbol table to be the subfunction's
+			 * parent.  In that case we overwrite the
+			 * initialization done in read_symbols().
+			 *
+			 * However this code can't completely replace the
+			 * read_symbols() code because this doesn't detect the
+			 * case where the parent function's only reference to a
+			 * subfunction is through a switch table.
+			 */
+			if (!strstr(insn->func->name, ".cold.") &&
+			    strstr(insn->jump_dest->func->name, ".cold.")) {
+				insn->func->cfunc = insn->jump_dest->func;
+				insn->jump_dest->func->pfunc = insn->func;
+
+			} else if (insn->jump_dest->func->pfunc != insn->func->pfunc &&
+				   insn->jump_dest->offset == insn->jump_dest->func->offset) {
+
+				/* sibling class */
+				insn->call_dest = insn->jump_dest->func;
+				insn->jump_dest = NULL;
+			}
 		}
 	}
 
@@ -633,9 +715,6 @@ static int add_call_destinations(struct objtool_file *file)
  *    conditionally jumps to the _end_ of the entry.  We have to modify these
  *    jumps' destinations to point back to .text rather than the end of the
  *    entry in .altinstr_replacement.
- *
- * 4. It has been requested that we don't validate the !POPCNT feature path
- *    which is a "very very small percentage of machines".
  */
 static int handle_group_alt(struct objtool_file *file,
 			    struct special_alt *special_alt,
@@ -651,9 +730,6 @@ static int handle_group_alt(struct objtool_file *file,
 		if (insn->offset >= special_alt->orig_off + special_alt->orig_len)
 			break;
 
-		if (special_alt->skip_orig)
-			insn->type = INSN_NOP;
-
 		insn->alt_group = true;
 		last_orig_insn = insn;
 	}
@@ -695,6 +771,7 @@ static int handle_group_alt(struct objtool_file *file,
 		last_new_insn = insn;
 
 		insn->ignore = orig_insn->ignore_alts;
+		insn->func = orig_insn->func;
 
 		if (insn->type != INSN_JUMP_CONDITIONAL &&
 		    insn->type != INSN_JUMP_UNCONDITIONAL)
@@ -817,6 +894,8 @@ static int add_special_section_alts(struct objtool_file *file)
 		}
 
 		alt->insn = new_insn;
+		alt->skip_orig = special_alt->skip_orig;
+		orig_insn->ignore_alts |= special_alt->skip_alt;
 		list_add_tail(&alt->list, &orig_insn->alts);
 
 		list_del(&special_alt->list);
@@ -1238,8 +1317,9 @@ static int decode_sections(struct objtool_file *file)
 		return ret;
 
 	add_ignores(file);
+	add_uaccess_safe(file);
 
-	ret = add_nospec_ignores(file);
+	ret = add_ignore_alternatives(file);
 	if (ret)
 		return ret;
 
@@ -1319,11 +1399,11 @@ static int update_insn_state_regs(struct instruction *insn, struct insn_state *s
 		return 0;
 
 	/* push */
-	if (op->dest.type == OP_DEST_PUSH)
+	if (op->dest.type == OP_DEST_PUSH || op->dest.type == OP_DEST_PUSHF)
 		cfa->offset += 8;
 
 	/* pop */
-	if (op->src.type == OP_SRC_POP)
+	if (op->src.type == OP_SRC_POP || op->src.type == OP_SRC_POPF)
 		cfa->offset -= 8;
 
 	/* add immediate to sp */
@@ -1580,6 +1660,7 @@ static int update_insn_state(struct instruction *insn, struct insn_state *state)
 			break;
 
 		case OP_SRC_POP:
+		case OP_SRC_POPF:
 			if (!state->drap && op->dest.type == OP_DEST_REG &&
 			    op->dest.reg == cfa->base) {
 
@@ -1644,6 +1725,7 @@ static int update_insn_state(struct instruction *insn, struct insn_state *state)
 		break;
 
 	case OP_DEST_PUSH:
+	case OP_DEST_PUSHF:
 		state->stack_size += 8;
 		if (cfa->base == CFI_SP)
 			cfa->offset += 8;
@@ -1734,7 +1816,7 @@ static int update_insn_state(struct instruction *insn, struct insn_state *state)
 		break;
 
 	case OP_DEST_MEM:
-		if (op->src.type != OP_SRC_POP) {
+		if (op->src.type != OP_SRC_POP && op->src.type != OP_SRC_POPF) {
 			WARN_FUNC("unknown stack-related memory operation",
 				  insn->sec, insn->offset);
 			return -1;
@@ -1798,6 +1880,50 @@ static bool insn_state_match(struct instruction *insn, struct insn_state *state)
 	return false;
 }
 
+static inline bool func_uaccess_safe(struct symbol *func)
+{
+	if (func)
+		return func->alias->uaccess_safe;
+
+	return false;
+}
+
+static inline const char *insn_dest_name(struct instruction *insn)
+{
+	if (insn->call_dest)
+		return insn->call_dest->name;
+
+	return "{dynamic}";
+}
+
+static int validate_call(struct instruction *insn, struct insn_state *state)
+{
+	if (state->uaccess && !func_uaccess_safe(insn->call_dest)) {
+		WARN_FUNC("call to %s() with UACCESS enabled",
+				insn->sec, insn->offset, insn_dest_name(insn));
+		return 1;
+	}
+
+	if (state->df) {
+		WARN_FUNC("call to %s() with DF set",
+				insn->sec, insn->offset, insn_dest_name(insn));
+		return 1;
+	}
+
+	return 0;
+}
+
+static int validate_sibling_call(struct instruction *insn, struct insn_state *state)
+{
+	if (has_modified_stack_frame(state)) {
+		WARN_FUNC("sibling call from callable instruction with modified stack frame",
+				insn->sec, insn->offset);
+		return 1;
+	}
+
+	return validate_call(insn, state);
+}
+
 /*
  * Follow the branch starting at the given instruction, and recursively follow
  * any other branches (jumps).  Meanwhile, track the frame pointer state at
@@ -1843,7 +1969,9 @@ static int validate_branch(struct objtool_file *file, struct instruction *first,
 			if (!insn->hint && !insn_state_match(insn, &state))
 				return 1;
 
-			return 0;
+			/* If we were here with AC=0, but now have AC=1, go again */
+			if (insn->state.uaccess || !state.uaccess)
+				return 0;
 		}
 
 		if (insn->hint) {
@@ -1892,16 +2020,42 @@ static int validate_branch(struct objtool_file *file, struct instruction *first,
 		insn->visited = true;
 
 		if (!insn->ignore_alts) {
+			bool skip_orig = false;
+
 			list_for_each_entry(alt, &insn->alts, list) {
+				if (alt->skip_orig)
+					skip_orig = true;
+
 				ret = validate_branch(file, alt->insn, state);
-				if (ret)
-					return 1;
+				if (ret) {
+					if (backtrace)
+						BT_FUNC("(alt)", insn);
+					return ret;
+				}
 			}
+
+			if (skip_orig)
+				return 0;
 		}
 
 		switch (insn->type) {
 
 		case INSN_RETURN:
+			if (state.uaccess && !func_uaccess_safe(func)) {
+				WARN_FUNC("return with UACCESS enabled", sec, insn->offset);
+				return 1;
+			}
+
+			if (!state.uaccess && func_uaccess_safe(func)) {
+				WARN_FUNC("return with UACCESS disabled from a UACCESS-safe function", sec, insn->offset);
+				return 1;
+			}
+
+			if (state.df) {
+				WARN_FUNC("return with DF set", sec, insn->offset);
+				return 1;
+			}
+
 			if (func && has_modified_stack_frame(&state)) {
 				WARN_FUNC("return with modified stack frame",
 					  sec, insn->offset);
@@ -1917,17 +2071,22 @@ static int validate_branch(struct objtool_file *file, struct instruction *first,
 			return 0;
 
 		case INSN_CALL:
-			if (is_fentry_call(insn))
-				break;
+		case INSN_CALL_DYNAMIC:
+			ret = validate_call(insn, &state);
+			if (ret)
+				return ret;
 
-			ret = dead_end_function(file, insn->call_dest);
-			if (ret == 1)
-				return 0;
-			if (ret == -1)
-				return 1;
+			if (insn->type == INSN_CALL) {
+				if (is_fentry_call(insn))
+					break;
+
+				ret = dead_end_function(file, insn->call_dest);
+				if (ret == 1)
+					return 0;
+				if (ret == -1)
+					return 1;
+			}
 
-			/* fallthrough */
-		case INSN_CALL_DYNAMIC:
 			if (!no_fp && func && !has_valid_stack_frame(&state)) {
 				WARN_FUNC("call without frame pointer save/setup",
 					  sec, insn->offset);
@@ -1937,18 +2096,21 @@ static int validate_branch(struct objtool_file *file, struct instruction *first,
 
 		case INSN_JUMP_CONDITIONAL:
 		case INSN_JUMP_UNCONDITIONAL:
-			if (insn->jump_dest &&
-			    (!func || !insn->jump_dest->func ||
-			     insn->jump_dest->func->pfunc == func)) {
-				ret = validate_branch(file, insn->jump_dest,
-						      state);
+			if (func && !insn->jump_dest) {
+				ret = validate_sibling_call(insn, &state);
 				if (ret)
-					return 1;
+					return ret;
 
-			} else if (func && has_modified_stack_frame(&state)) {
-				WARN_FUNC("sibling call from callable instruction with modified stack frame",
-					  sec, insn->offset);
-				return 1;
+			} else if (insn->jump_dest &&
+				   (!func || !insn->jump_dest->func ||
+				    insn->jump_dest->func->pfunc == func)) {
+				ret = validate_branch(file, insn->jump_dest,
+						      state);
+				if (ret) {
+					if (backtrace)
+						BT_FUNC("(branch)", insn);
+					return ret;
+				}
 			}
 
 			if (insn->type == INSN_JUMP_UNCONDITIONAL)
@@ -1957,11 +2119,10 @@ static int validate_branch(struct objtool_file *file, struct instruction *first,
 			break;
 
 		case INSN_JUMP_DYNAMIC:
-			if (func && list_empty(&insn->alts) &&
-			    has_modified_stack_frame(&state)) {
-				WARN_FUNC("sibling call from callable instruction with modified stack frame",
-					  sec, insn->offset);
-				return 1;
+			if (func && list_empty(&insn->alts)) {
+				ret = validate_sibling_call(insn, &state);
+				if (ret)
+					return ret;
 			}
 
 			return 0;
@@ -1978,6 +2139,63 @@ static int validate_branch(struct objtool_file *file, struct instruction *first,
 			if (update_insn_state(insn, &state))
 				return 1;
 
+			if (insn->stack_op.dest.type == OP_DEST_PUSHF) {
+				if (!state.uaccess_stack) {
+					state.uaccess_stack = 1;
+				} else if (state.uaccess_stack >> 31) {
+					WARN_FUNC("PUSHF stack exhausted", sec, insn->offset);
+					return 1;
+				}
+				state.uaccess_stack <<= 1;
+				state.uaccess_stack  |= state.uaccess;
+			}
+
+			if (insn->stack_op.src.type == OP_SRC_POPF) {
+				if (state.uaccess_stack) {
+					state.uaccess = state.uaccess_stack & 1;
+					state.uaccess_stack >>= 1;
+					if (state.uaccess_stack == 1)
+						state.uaccess_stack = 0;
+				}
+			}
+
+			break;
+
+		case INSN_STAC:
+			if (state.uaccess) {
+				WARN_FUNC("recursive UACCESS enable", sec, insn->offset);
+				return 1;
+			}
+
+			state.uaccess = true;
+			break;
+
+		case INSN_CLAC:
+			if (!state.uaccess && insn->func) {
+				WARN_FUNC("redundant UACCESS disable", sec, insn->offset);
+				return 1;
+			}
+
+			if (func_uaccess_safe(func) && !state.uaccess_stack) {
+				WARN_FUNC("UACCESS-safe disables UACCESS", sec, insn->offset);
+				return 1;
+			}
+
+			state.uaccess = false;
+			break;
+
+		case INSN_STD:
+			if (state.df)
+				WARN_FUNC("recursive STD", sec, insn->offset);
+
+			state.df = true;
+			break;
+
+		case INSN_CLD:
+			if (!state.df && insn->func)
+				WARN_FUNC("redundant CLD", sec, insn->offset);
+
+			state.df = false;
 			break;
 
 		default:
@@ -2014,6 +2232,8 @@ static int validate_unwind_hints(struct objtool_file *file)
 	for_each_insn(file, insn) {
 		if (insn->hint && !insn->visited) {
 			ret = validate_branch(file, insn, state);
+			if (ret && backtrace)
+				BT_FUNC("<=== (hint)", insn);
 			warnings += ret;
 		}
 	}
@@ -2141,7 +2361,11 @@ static int validate_functions(struct objtool_file *file)
 			if (!insn || insn->ignore)
 				continue;
 
+			state.uaccess = func->alias->uaccess_safe;
+
 			ret = validate_branch(file, insn, state);
+			if (ret && backtrace)
+				BT_FUNC("<=== (func)", insn);
 			warnings += ret;
 		}
 	}
@@ -2198,7 +2422,6 @@ int check(const char *_objname, bool orc)
 
 	INIT_LIST_HEAD(&file.insn_list);
 	hash_init(file.insn_hash);
-	file.whitelist = find_section_by_name(file.elf, ".discard.func_stack_frame_non_standard");
 	file.c_file = find_section_by_name(file.elf, ".comment");
 	file.ignore_unreachables = no_unreachable;
 	file.hints = false;
diff --git a/tools/objtool/check.h b/tools/objtool/check.h
index e6e8a655b556..71e54f97dbcd 100644
--- a/tools/objtool/check.h
+++ b/tools/objtool/check.h
@@ -31,7 +31,8 @@ struct insn_state {
 	int stack_size;
 	unsigned char type;
 	bool bp_scratch;
-	bool drap, end;
+	bool drap, end, uaccess, df;
+	unsigned int uaccess_stack;
 	int drap_reg, drap_offset;
 	struct cfi_reg vals[CFI_NUM_REGS];
 };
@@ -60,7 +61,6 @@ struct objtool_file {
 	struct elf *elf;
 	struct list_head insn_list;
 	DECLARE_HASHTABLE(insn_hash, 16);
-	struct section *whitelist;
 	bool ignore_unreachables, c_file, hints, rodata;
 };
 
diff --git a/tools/objtool/elf.c b/tools/objtool/elf.c
index b8f3cca8e58b..dd198d53387d 100644
--- a/tools/objtool/elf.c
+++ b/tools/objtool/elf.c
@@ -219,7 +219,7 @@ static int read_sections(struct elf *elf)
 static int read_symbols(struct elf *elf)
 {
 	struct section *symtab, *sec;
-	struct symbol *sym, *pfunc;
+	struct symbol *sym, *pfunc, *alias;
 	struct list_head *entry, *tmp;
 	int symbols_nr, i;
 	char *coldstr;
@@ -239,6 +239,7 @@ static int read_symbols(struct elf *elf)
 			return -1;
 		}
 		memset(sym, 0, sizeof(*sym));
+		alias = sym;
 
 		sym->idx = i;
 
@@ -288,11 +289,17 @@ static int read_symbols(struct elf *elf)
 				break;
 			}
 
-			if (sym->offset == s->offset && sym->len >= s->len) {
-				entry = tmp;
-				break;
+			if (sym->offset == s->offset) {
+				if (sym->len == s->len && alias == sym)
+					alias = s;
+
+				if (sym->len >= s->len) {
+					entry = tmp;
+					break;
+				}
 			}
 		}
+		sym->alias = alias;
 		list_add(&sym->list, entry);
 		hash_add(sym->sec->symbol_hash, &sym->hash, sym->idx);
 	}
diff --git a/tools/objtool/elf.h b/tools/objtool/elf.h
index bc97ed86b9cd..2cc2ed49322d 100644
--- a/tools/objtool/elf.h
+++ b/tools/objtool/elf.h
@@ -61,7 +61,8 @@ struct symbol {
 	unsigned char bind, type;
 	unsigned long offset;
 	unsigned int len;
-	struct symbol *pfunc, *cfunc;
+	struct symbol *pfunc, *cfunc, *alias;
+	bool uaccess_safe;
 };
 
 struct rela {
diff --git a/tools/objtool/special.c b/tools/objtool/special.c
index 50af4e1274b3..4e50563d87c6 100644
--- a/tools/objtool/special.c
+++ b/tools/objtool/special.c
@@ -23,6 +23,7 @@
 #include <stdlib.h>
 #include <string.h>
 
+#include "builtin.h"
 #include "special.h"
 #include "warn.h"
 
@@ -42,6 +43,7 @@
 #define ALT_NEW_LEN_OFFSET	11
 
 #define X86_FEATURE_POPCNT (4*32+23)
+#define X86_FEATURE_SMAP   (9*32+20)
 
 struct special_entry {
 	const char *sec;
@@ -110,6 +112,22 @@ static int get_alt_entry(struct elf *elf, struct special_entry *entry,
 		 */
 		if (feature == X86_FEATURE_POPCNT)
 			alt->skip_orig = true;
+
+		/*
+		 * If UACCESS validation is enabled; force that alternative;
+		 * otherwise force it the other way.
+		 *
+		 * What we want to avoid is having both the original and the
+		 * alternative code flow at the same time, in that case we can
+		 * find paths that see the STAC but take the NOP instead of
+		 * CLAC and the other way around.
+		 */
+		if (feature == X86_FEATURE_SMAP) {
+			if (uaccess)
+				alt->skip_orig = true;
+			else
+				alt->skip_alt = true;
+		}
 	}
 
 	orig_rela = find_rela_by_dest(sec, offset + entry->orig);
diff --git a/tools/objtool/special.h b/tools/objtool/special.h
index fad1d092f679..d5c062e718ef 100644
--- a/tools/objtool/special.h
+++ b/tools/objtool/special.h
@@ -26,6 +26,7 @@ struct special_alt {
 
 	bool group;
 	bool skip_orig;
+	bool skip_alt;
 	bool jump_or_nop;
 
 	struct section *orig_sec;
diff --git a/tools/objtool/warn.h b/tools/objtool/warn.h
index afd9f7a05f6d..f4fbb972b611 100644
--- a/tools/objtool/warn.h
+++ b/tools/objtool/warn.h
@@ -64,6 +64,14 @@ static inline char *offstr(struct section *sec, unsigned long offset)
 	free(_str);					\
 })
 
+#define BT_FUNC(format, insn, ...)			\
+({							\
+	struct instruction *_insn = (insn);		\
+	char *_str = offstr(_insn->sec, _insn->offset); \
+	WARN("  %s: " format, _str, ##__VA_ARGS__);	\
+	free(_str);					\
+})
+
 #define WARN_ELF(format, ...)				\
 	WARN(format ": %s", ##__VA_ARGS__, elf_errmsg(-1))
 
diff --git a/tools/perf/Documentation/perf-record.txt b/tools/perf/Documentation/perf-record.txt
index 8fe4dffcadd0..58986f4cc190 100644
--- a/tools/perf/Documentation/perf-record.txt
+++ b/tools/perf/Documentation/perf-record.txt
@@ -459,6 +459,25 @@ Set affinity mask of trace reading thread according to the policy defined by 'mo
   node - thread affinity mask is set to NUMA node cpu mask of the processed mmap buffer
   cpu  - thread affinity mask is set to cpu of the processed mmap buffer
 
+--mmap-flush=number::
+
+Specify minimal number of bytes that is extracted from mmap data pages and
+processed for output. One can specify the number using B/K/M/G suffixes.
+
+The maximal allowed value is a quarter of the size of mmaped data pages.
+
+The default option value is 1 byte which means that every time that the output
+writing thread finds some new data in the mmaped buffer the data is extracted,
+possibly compressed (-z) and written to the output, perf.data or pipe.
+
+Larger data chunks are compressed more effectively in comparison to smaller
+chunks so extraction of larger chunks from the mmap data pages is preferable
+from the perspective of output size reduction.
+
+Also at some cases executing less output write syscalls with bigger data size
+can take less time than executing more output write syscalls with smaller data
+size thus lowering runtime profiling overhead.
+
 --all-kernel::
 Configure all used events to run in kernel space.
 
diff --git a/tools/perf/Makefile.config b/tools/perf/Makefile.config
index fe3f97e342fa..0c52a01dc759 100644
--- a/tools/perf/Makefile.config
+++ b/tools/perf/Makefile.config
@@ -152,6 +152,13 @@ endif
 FEATURE_CHECK_CFLAGS-libbabeltrace := $(LIBBABELTRACE_CFLAGS)
 FEATURE_CHECK_LDFLAGS-libbabeltrace := $(LIBBABELTRACE_LDFLAGS) -lbabeltrace-ctf
 
+ifdef LIBZSTD_DIR
+  LIBZSTD_CFLAGS  := -I$(LIBZSTD_DIR)/lib
+  LIBZSTD_LDFLAGS := -L$(LIBZSTD_DIR)/lib
+endif
+FEATURE_CHECK_CFLAGS-libzstd := $(LIBZSTD_CFLAGS)
+FEATURE_CHECK_LDFLAGS-libzstd := $(LIBZSTD_LDFLAGS)
+
 FEATURE_CHECK_CFLAGS-bpf = -I. -I$(srctree)/tools/include -I$(srctree)/tools/arch/$(SRCARCH)/include/uapi -I$(srctree)/tools/include/uapi
 # include ARCH specific config
 -include $(src-perf)/arch/$(SRCARCH)/Makefile
@@ -227,7 +234,7 @@ FEATURE_CHECK_LDFLAGS-libpython-version := $(PYTHON_EMBED_LDOPTS)
 
 FEATURE_CHECK_LDFLAGS-libaio = -lrt
 
-FEATURE_CHECK_LDFLAGS-disassembler-four-args = -lbfd -lopcodes
+FEATURE_CHECK_LDFLAGS-disassembler-four-args = -lbfd -lopcodes -ldl
 
 CFLAGS += -fno-omit-frame-pointer
 CFLAGS += -ggdb3
@@ -787,6 +794,19 @@ ifndef NO_LZMA
   endif
 endif
 
+ifndef NO_LIBZSTD
+  ifeq ($(feature-libzstd), 1)
+    CFLAGS += -DHAVE_ZSTD_SUPPORT
+    CFLAGS += $(LIBZSTD_CFLAGS)
+    LDFLAGS += $(LIBZSTD_LDFLAGS)
+    EXTLIBS += -lzstd
+    $(call detected,CONFIG_ZSTD)
+  else
+    msg := $(warning No libzstd found, disables trace compression, please install libzstd-dev[el] and/or set LIBZSTD_DIR);
+    NO_LIBZSTD := 1
+  endif
+endif
+
 ifndef NO_BACKTRACE
   ifeq ($(feature-backtrace), 1)
     CFLAGS += -DHAVE_BACKTRACE_SUPPORT
diff --git a/tools/perf/Makefile.perf b/tools/perf/Makefile.perf
index 01f7555fd933..c706548d5b10 100644
--- a/tools/perf/Makefile.perf
+++ b/tools/perf/Makefile.perf
@@ -108,6 +108,9 @@ include ../scripts/utilities.mak
 # streaming for record mode. Currently Posix AIO trace streaming is
 # supported only when linking with glibc.
 #
+# Define NO_LIBZSTD if you do not want support of Zstandard based runtime
+# trace compression in record mode.
+#
 
 # As per kernel Makefile, avoid funny character set dependencies
 unexport LC_ALL
@@ -481,8 +484,8 @@ $(madvise_behavior_array): $(madvise_hdr_dir)/mman-common.h $(madvise_behavior_t
 mmap_flags_array := $(beauty_outdir)/mmap_flags_array.c
 mmap_flags_tbl := $(srctree)/tools/perf/trace/beauty/mmap_flags.sh
 
-$(mmap_flags_array): $(asm_generic_uapi_dir)/mman.h $(asm_generic_uapi_dir)/mman-common.h $(mmap_flags_tbl)
-	$(Q)$(SHELL) '$(mmap_flags_tbl)' $(asm_generic_uapi_dir) $(arch_asm_uapi_dir) > $@
+$(mmap_flags_array): $(linux_uapi_dir)/mman.h $(asm_generic_uapi_dir)/mman.h $(asm_generic_uapi_dir)/mman-common.h $(mmap_flags_tbl)
+	$(Q)$(SHELL) '$(mmap_flags_tbl)' $(linux_uapi_dir) $(asm_generic_uapi_dir) $(arch_asm_uapi_dir) > $@
 
 mount_flags_array := $(beauty_outdir)/mount_flags_array.c
 mount_flags_tbl := $(srctree)/tools/perf/trace/beauty/mount_flags.sh
diff --git a/tools/perf/arch/x86/entry/syscalls/syscall_64.tbl b/tools/perf/arch/x86/entry/syscalls/syscall_64.tbl
index 2ae92fddb6d5..92ee0b4378d4 100644
--- a/tools/perf/arch/x86/entry/syscalls/syscall_64.tbl
+++ b/tools/perf/arch/x86/entry/syscalls/syscall_64.tbl
@@ -345,6 +345,10 @@
 334	common	rseq			__x64_sys_rseq
 # don't use numbers 387 through 423, add new calls after the last
 # 'common' entry
+424	common	pidfd_send_signal	__x64_sys_pidfd_send_signal
+425	common	io_uring_setup		__x64_sys_io_uring_setup
+426	common	io_uring_enter		__x64_sys_io_uring_enter
+427	common	io_uring_register	__x64_sys_io_uring_register
 
 #
 # x32-specific system call numbers start at 512 to avoid cache impact
diff --git a/tools/perf/bench/numa.c b/tools/perf/bench/numa.c
index 98ad783efc69..a7784554a80d 100644
--- a/tools/perf/bench/numa.c
+++ b/tools/perf/bench/numa.c
@@ -39,6 +39,10 @@
 #include <numa.h>
 #include <numaif.h>
 
+#ifndef RUSAGE_THREAD
+# define RUSAGE_THREAD 1
+#endif
+
 /*
  * Regular printout to the terminal, supressed if -q is specified:
  */
diff --git a/tools/perf/builtin-kmem.c b/tools/perf/builtin-kmem.c
index fa520f4b8095..b80eee455111 100644
--- a/tools/perf/builtin-kmem.c
+++ b/tools/perf/builtin-kmem.c
@@ -1975,7 +1975,7 @@ int cmd_kmem(int argc, const char **argv)
 			goto out_delete;
 		}
 
-		kmem_page_size = tep_get_page_size(evsel->tp_format->pevent);
+		kmem_page_size = tep_get_page_size(evsel->tp_format->tep);
 		symbol_conf.use_callchain = true;
 	}
 
diff --git a/tools/perf/builtin-list.c b/tools/perf/builtin-list.c
index a8394b4f1167..e0312a1c4792 100644
--- a/tools/perf/builtin-list.c
+++ b/tools/perf/builtin-list.c
@@ -70,10 +70,11 @@ int cmd_list(int argc, const char **argv)
 			print_symbol_events(NULL, PERF_TYPE_HARDWARE,
 					event_symbols_hw, PERF_COUNT_HW_MAX, raw_dump);
 		else if (strcmp(argv[i], "sw") == 0 ||
-			 strcmp(argv[i], "software") == 0)
+			 strcmp(argv[i], "software") == 0) {
 			print_symbol_events(NULL, PERF_TYPE_SOFTWARE,
 					event_symbols_sw, PERF_COUNT_SW_MAX, raw_dump);
-		else if (strcmp(argv[i], "cache") == 0 ||
+			print_tool_events(NULL, raw_dump);
+		} else if (strcmp(argv[i], "cache") == 0 ||
 			 strcmp(argv[i], "hwcache") == 0)
 			print_hwcache_events(NULL, raw_dump);
 		else if (strcmp(argv[i], "pmu") == 0)
@@ -113,6 +114,7 @@ int cmd_list(int argc, const char **argv)
 					    event_symbols_hw, PERF_COUNT_HW_MAX, raw_dump);
 			print_symbol_events(s, PERF_TYPE_SOFTWARE,
 					    event_symbols_sw, PERF_COUNT_SW_MAX, raw_dump);
+			print_tool_events(s, raw_dump);
 			print_hwcache_events(s, raw_dump);
 			print_pmu_events(s, raw_dump, !desc_flag,
 						long_desc_flag,
diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c
index 4e2d953d4bc5..c5e10552776a 100644
--- a/tools/perf/builtin-record.c
+++ b/tools/perf/builtin-record.c
@@ -337,6 +337,41 @@ static int record__aio_enabled(struct record *rec)
 	return rec->opts.nr_cblocks > 0;
 }
 
+#define MMAP_FLUSH_DEFAULT 1
+static int record__mmap_flush_parse(const struct option *opt,
+				    const char *str,
+				    int unset)
+{
+	int flush_max;
+	struct record_opts *opts = (struct record_opts *)opt->value;
+	static struct parse_tag tags[] = {
+			{ .tag  = 'B', .mult = 1       },
+			{ .tag  = 'K', .mult = 1 << 10 },
+			{ .tag  = 'M', .mult = 1 << 20 },
+			{ .tag  = 'G', .mult = 1 << 30 },
+			{ .tag  = 0 },
+	};
+
+	if (unset)
+		return 0;
+
+	if (str) {
+		opts->mmap_flush = parse_tag_value(str, tags);
+		if (opts->mmap_flush == (int)-1)
+			opts->mmap_flush = strtol(str, NULL, 0);
+	}
+
+	if (!opts->mmap_flush)
+		opts->mmap_flush = MMAP_FLUSH_DEFAULT;
+
+	flush_max = perf_evlist__mmap_size(opts->mmap_pages);
+	flush_max /= 4;
+	if (opts->mmap_flush > flush_max)
+		opts->mmap_flush = flush_max;
+
+	return 0;
+}
+
 static int process_synthesized_event(struct perf_tool *tool,
 				     union perf_event *event,
 				     struct perf_sample *sample __maybe_unused,
@@ -546,7 +581,8 @@ static int record__mmap_evlist(struct record *rec,
 	if (perf_evlist__mmap_ex(evlist, opts->mmap_pages,
 				 opts->auxtrace_mmap_pages,
 				 opts->auxtrace_snapshot_mode,
-				 opts->nr_cblocks, opts->affinity) < 0) {
+				 opts->nr_cblocks, opts->affinity,
+				 opts->mmap_flush) < 0) {
 		if (errno == EPERM) {
 			pr_err("Permission error mapping pages.\n"
 			       "Consider increasing "
@@ -736,7 +772,7 @@ static void record__adjust_affinity(struct record *rec, struct perf_mmap *map)
 }
 
 static int record__mmap_read_evlist(struct record *rec, struct perf_evlist *evlist,
-				    bool overwrite)
+				    bool overwrite, bool synch)
 {
 	u64 bytes_written = rec->bytes_written;
 	int i;
@@ -759,12 +795,19 @@ static int record__mmap_read_evlist(struct record *rec, struct perf_evlist *evli
 		off = record__aio_get_pos(trace_fd);
 
 	for (i = 0; i < evlist->nr_mmaps; i++) {
+		u64 flush = 0;
 		struct perf_mmap *map = &maps[i];
 
 		if (map->base) {
 			record__adjust_affinity(rec, map);
+			if (synch) {
+				flush = map->flush;
+				map->flush = 1;
+			}
 			if (!record__aio_enabled(rec)) {
 				if (perf_mmap__push(map, rec, record__pushfn) != 0) {
+					if (synch)
+						map->flush = flush;
 					rc = -1;
 					goto out;
 				}
@@ -777,10 +820,14 @@ static int record__mmap_read_evlist(struct record *rec, struct perf_evlist *evli
 				idx = record__aio_sync(map, false);
 				if (perf_mmap__aio_push(map, rec, idx, record__aio_pushfn, &off) != 0) {
 					record__aio_set_pos(trace_fd, off);
+					if (synch)
+						map->flush = flush;
 					rc = -1;
 					goto out;
 				}
 			}
+			if (synch)
+				map->flush = flush;
 		}
 
 		if (map->auxtrace_mmap.base && !rec->opts.auxtrace_snapshot_mode &&
@@ -806,15 +853,15 @@ out:
 	return rc;
 }
 
-static int record__mmap_read_all(struct record *rec)
+static int record__mmap_read_all(struct record *rec, bool synch)
 {
 	int err;
 
-	err = record__mmap_read_evlist(rec, rec->evlist, false);
+	err = record__mmap_read_evlist(rec, rec->evlist, false, synch);
 	if (err)
 		return err;
 
-	return record__mmap_read_evlist(rec, rec->evlist, true);
+	return record__mmap_read_evlist(rec, rec->evlist, true, synch);
 }
 
 static void record__init_features(struct record *rec)
@@ -1340,7 +1387,7 @@ static int __cmd_record(struct record *rec, int argc, const char **argv)
 		if (trigger_is_hit(&switch_output_trigger) || done || draining)
 			perf_evlist__toggle_bkw_mmap(rec->evlist, BKW_MMAP_DATA_PENDING);
 
-		if (record__mmap_read_all(rec) < 0) {
+		if (record__mmap_read_all(rec, false) < 0) {
 			trigger_error(&auxtrace_snapshot_trigger);
 			trigger_error(&switch_output_trigger);
 			err = -1;
@@ -1441,6 +1488,7 @@ static int __cmd_record(struct record *rec, int argc, const char **argv)
 		record__synthesize_workload(rec, true);
 
 out_child:
+	record__mmap_read_all(rec, true);
 	record__aio_mmap_read_sync(rec);
 
 	if (forks) {
@@ -1846,6 +1894,7 @@ static struct record record = {
 			.uses_mmap   = true,
 			.default_per_cpu = true,
 		},
+		.mmap_flush          = MMAP_FLUSH_DEFAULT,
 	},
 	.tool = {
 		.sample		= process_sample_event,
@@ -1912,6 +1961,9 @@ static struct option __record_options[] = {
 	OPT_CALLBACK('m', "mmap-pages", &record.opts, "pages[,pages]",
 		     "number of mmap data pages and AUX area tracing mmap pages",
 		     record__parse_mmap_pages),
+	OPT_CALLBACK(0, "mmap-flush", &record.opts, "number",
+		     "Minimal number of bytes that is extracted from mmap data pages (default: 1)",
+		     record__mmap_flush_parse),
 	OPT_BOOLEAN(0, "group", &record.opts.group,
 		    "put the counters into a counter group"),
 	OPT_CALLBACK_NOOPT('g', NULL, &callchain_param,
@@ -2224,6 +2276,7 @@ int cmd_record(int argc, const char **argv)
 		pr_info("nr_cblocks: %d\n", rec->opts.nr_cblocks);
 
 	pr_debug("affinity: %s\n", affinity_tags[rec->opts.affinity]);
+	pr_debug("mmap flush: %d\n", rec->opts.mmap_flush);
 
 	err = __cmd_record(&record, argc, argv);
 out:
diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c
index 49ee3c2033ec..a3c060878faa 100644
--- a/tools/perf/builtin-stat.c
+++ b/tools/perf/builtin-stat.c
@@ -244,11 +244,25 @@ perf_evsel__write_stat_event(struct perf_evsel *counter, u32 cpu, u32 thread,
 					   process_synthesized_event, NULL);
 }
 
+static int read_single_counter(struct perf_evsel *counter, int cpu,
+			       int thread, struct timespec *rs)
+{
+	if (counter->tool_event == PERF_TOOL_DURATION_TIME) {
+		u64 val = rs->tv_nsec + rs->tv_sec*1000000000ULL;
+		struct perf_counts_values *count =
+			perf_counts(counter->counts, cpu, thread);
+		count->ena = count->run = val;
+		count->val = val;
+		return 0;
+	}
+	return perf_evsel__read_counter(counter, cpu, thread);
+}
+
 /*
  * Read out the results of a single counter:
  * do not aggregate counts across CPUs in system-wide mode
  */
-static int read_counter(struct perf_evsel *counter)
+static int read_counter(struct perf_evsel *counter, struct timespec *rs)
 {
 	int nthreads = thread_map__nr(evsel_list->threads);
 	int ncpus, cpu, thread;
@@ -275,7 +289,7 @@ static int read_counter(struct perf_evsel *counter)
 			 * (via perf_evsel__read_counter) and sets threir count->loaded.
 			 */
 			if (!count->loaded &&
-			    perf_evsel__read_counter(counter, cpu, thread)) {
+			    read_single_counter(counter, cpu, thread, rs)) {
 				counter->counts->scaled = -1;
 				perf_counts(counter->counts, cpu, thread)->ena = 0;
 				perf_counts(counter->counts, cpu, thread)->run = 0;
@@ -304,13 +318,13 @@ static int read_counter(struct perf_evsel *counter)
 	return 0;
 }
 
-static void read_counters(void)
+static void read_counters(struct timespec *rs)
 {
 	struct perf_evsel *counter;
 	int ret;
 
 	evlist__for_each_entry(evsel_list, counter) {
-		ret = read_counter(counter);
+		ret = read_counter(counter, rs);
 		if (ret)
 			pr_debug("failed to read counter %s\n", counter->name);
 
@@ -323,11 +337,11 @@ static void process_interval(void)
 {
 	struct timespec ts, rs;
 
-	read_counters();
-
 	clock_gettime(CLOCK_MONOTONIC, &ts);
 	diff_timespec(&rs, &ts, &ref_time);
 
+	read_counters(&rs);
+
 	if (STAT_RECORD) {
 		if (WRITE_STAT_ROUND_EVENT(rs.tv_sec * NSEC_PER_SEC + rs.tv_nsec, INTERVAL))
 			pr_err("failed to write stat round event\n");
@@ -593,7 +607,7 @@ try_again:
 	 * avoid arbitrary skew, we must read all counters before closing any
 	 * group leaders.
 	 */
-	read_counters();
+	read_counters(&(struct timespec) { .tv_nsec = t1-t0 });
 	perf_evlist__close(evsel_list);
 
 	return WEXITSTATUS(status);
@@ -1308,6 +1322,7 @@ static void init_features(struct perf_session *session)
 	for (feat = HEADER_FIRST_FEATURE; feat < HEADER_LAST_FEATURE; feat++)
 		perf_header__set_feat(&session->header, feat);
 
+	perf_header__clear_feat(&session->header, HEADER_DIR_FORMAT);
 	perf_header__clear_feat(&session->header, HEADER_BUILD_ID);
 	perf_header__clear_feat(&session->header, HEADER_TRACING_DATA);
 	perf_header__clear_feat(&session->header, HEADER_BRANCH_STACK);
diff --git a/tools/perf/builtin-top.c b/tools/perf/builtin-top.c
index 1999d6533d12..fbbb0da43abb 100644
--- a/tools/perf/builtin-top.c
+++ b/tools/perf/builtin-top.c
@@ -1377,6 +1377,7 @@ int cmd_top(int argc, const char **argv)
 			 * */
 			.overwrite	= 0,
 			.sample_time	= true,
+			.sample_time_set = true,
 		},
 		.max_stack	     = sysctl__max_stack(),
 		.annotation_opts     = annotation__default_options,
diff --git a/tools/perf/builtin-version.c b/tools/perf/builtin-version.c
index 50df168be326..f470144d1a70 100644
--- a/tools/perf/builtin-version.c
+++ b/tools/perf/builtin-version.c
@@ -78,6 +78,8 @@ static void library_status(void)
 	STATUS(HAVE_LZMA_SUPPORT, lzma);
 	STATUS(HAVE_AUXTRACE_SUPPORT, get_cpuid);
 	STATUS(HAVE_LIBBPF_SUPPORT, bpf);
+	STATUS(HAVE_AIO_SUPPORT, aio);
+	STATUS(HAVE_ZSTD_SUPPORT, zstd);
 }
 
 int cmd_version(int argc, const char **argv)
diff --git a/tools/perf/check-headers.sh b/tools/perf/check-headers.sh
index 7b55613924de..c68ee06cae63 100755
--- a/tools/perf/check-headers.sh
+++ b/tools/perf/check-headers.sh
@@ -103,7 +103,7 @@ done
 # diff with extra ignore lines
 check arch/x86/lib/memcpy_64.S        '-I "^EXPORT_SYMBOL" -I "^#include <asm/export.h>"'
 check arch/x86/lib/memset_64.S        '-I "^EXPORT_SYMBOL" -I "^#include <asm/export.h>"'
-check include/uapi/asm-generic/mman.h '-I "^#include <\(uapi/\)*asm-generic/mman-common.h>"'
+check include/uapi/asm-generic/mman.h '-I "^#include <\(uapi/\)*asm-generic/mman-common\(-tools\)*.h>"'
 check include/uapi/linux/mman.h       '-I "^#include <\(uapi/\)*asm/mman.h>"'
 
 # diff non-symmetric files
diff --git a/tools/perf/examples/bpf/augmented_raw_syscalls.c b/tools/perf/examples/bpf/augmented_raw_syscalls.c
index f9b2161e1ca4..2422894a8194 100644
--- a/tools/perf/examples/bpf/augmented_raw_syscalls.c
+++ b/tools/perf/examples/bpf/augmented_raw_syscalls.c
@@ -15,6 +15,7 @@
  */
 
 #include <unistd.h>
+#include <linux/limits.h>
 #include <pid_filter.h>
 
 /* bpf-output associated map */
@@ -41,32 +42,110 @@ struct syscall_exit_args {
 struct augmented_filename {
 	unsigned int	size;
 	int		reserved;
-	char		value[256];
+	char		value[PATH_MAX];
 };
 
-#define SYS_OPEN 2
-#define SYS_ACCESS 21
-#define SYS_OPENAT 257
+/* syscalls where the first arg is a string */
+#define SYS_OPEN                 2
+#define SYS_STAT                 4
+#define SYS_LSTAT                6
+#define SYS_ACCESS              21
+#define SYS_EXECVE              59
+#define SYS_TRUNCATE            76
+#define SYS_CHDIR               80
+#define SYS_RENAME              82
+#define SYS_MKDIR               83
+#define SYS_RMDIR               84
+#define SYS_CREAT               85
+#define SYS_LINK                86
+#define SYS_UNLINK              87
+#define SYS_SYMLINK             88
+#define SYS_READLINK            89
+#define SYS_CHMOD               90
+#define SYS_CHOWN               92
+#define SYS_LCHOWN              94
+#define SYS_MKNOD              133
+#define SYS_STATFS             137
+#define SYS_PIVOT_ROOT         155
+#define SYS_CHROOT             161
+#define SYS_ACCT               163
+#define SYS_SWAPON             167
+#define SYS_SWAPOFF            168
+#define SYS_DELETE_MODULE      176
+#define SYS_SETXATTR           188
+#define SYS_LSETXATTR          189
+#define SYS_GETXATTR           191
+#define SYS_LGETXATTR          192
+#define SYS_LISTXATTR          194
+#define SYS_LLISTXATTR         195
+#define SYS_REMOVEXATTR        197
+#define SYS_LREMOVEXATTR       198
+#define SYS_MQ_OPEN            240
+#define SYS_MQ_UNLINK          241
+#define SYS_ADD_KEY            248
+#define SYS_REQUEST_KEY        249
+#define SYS_SYMLINKAT          266
+#define SYS_MEMFD_CREATE       319
+
+/* syscalls where the first arg is a string */
+
+#define SYS_PWRITE64            18
+#define SYS_EXECVE              59
+#define SYS_RENAME              82
+#define SYS_QUOTACTL           179
+#define SYS_FSETXATTR          190
+#define SYS_FGETXATTR          193
+#define SYS_FREMOVEXATTR       199
+#define SYS_MQ_TIMEDSEND       242
+#define SYS_REQUEST_KEY        249
+#define SYS_INOTIFY_ADD_WATCH  254
+#define SYS_OPENAT             257
+#define SYS_MKDIRAT            258
+#define SYS_MKNODAT            259
+#define SYS_FCHOWNAT           260
+#define SYS_FUTIMESAT          261
+#define SYS_NEWFSTATAT         262
+#define SYS_UNLINKAT           263
+#define SYS_RENAMEAT           264
+#define SYS_LINKAT             265
+#define SYS_READLINKAT         267
+#define SYS_FCHMODAT           268
+#define SYS_FACCESSAT          269
+#define SYS_UTIMENSAT          280
+#define SYS_NAME_TO_HANDLE_AT  303
+#define SYS_FINIT_MODULE       313
+#define SYS_RENAMEAT2          316
+#define SYS_EXECVEAT           322
+#define SYS_STATX              332
 
 pid_filter(pids_filtered);
 
+struct augmented_args_filename {
+       struct syscall_enter_args args;
+       struct augmented_filename filename;
+};
+
+bpf_map(augmented_filename_map, PERCPU_ARRAY, int, struct augmented_args_filename, 1);
+
 SEC("raw_syscalls:sys_enter")
 int sys_enter(struct syscall_enter_args *args)
 {
-	struct {
-		struct syscall_enter_args args;
-		struct augmented_filename filename;
-	} augmented_args;
-	struct syscall *syscall;
-	unsigned int len = sizeof(augmented_args);
+	struct augmented_args_filename *augmented_args;
+	unsigned int len = sizeof(*augmented_args);
 	const void *filename_arg = NULL;
+	struct syscall *syscall;
+	int key = 0;
+
+        augmented_args = bpf_map_lookup_elem(&augmented_filename_map, &key);
+        if (augmented_args == NULL)
+                return 1;
 
 	if (pid_filter__has(&pids_filtered, getpid()))
 		return 0;
 
-	probe_read(&augmented_args.args, sizeof(augmented_args.args), args);
+	probe_read(&augmented_args->args, sizeof(augmented_args->args), args);
 
-	syscall = bpf_map_lookup_elem(&syscalls, &augmented_args.args.syscall_nr);
+	syscall = bpf_map_lookup_elem(&syscalls, &augmented_args->args.syscall_nr);
 	if (syscall == NULL || !syscall->enabled)
 		return 0;
 	/*
@@ -109,30 +188,105 @@ int sys_enter(struct syscall_enter_args *args)
 	 *
 	 * 	 after the ctx memory access to prevent their down stream merging.
 	 */
-	switch (augmented_args.args.syscall_nr) {
+	/*
+	 * This table of what args are strings will be provided by userspace,
+	 * in the syscalls map, i.e. we will already have to do the lookup to
+	 * see if this specific syscall is filtered, so we can as well get more
+	 * info about what syscall args are strings or pointers, and how many
+	 * bytes to copy, per arg, etc.
+	 *
+	 * For now hard code it, till we have all the basic mechanisms in place
+	 * to automate everything and make the kernel part be completely driven
+	 * by information obtained in userspace for each kernel version and
+	 * processor architecture, making the kernel part the same no matter what
+	 * kernel version or processor architecture it runs on.
+	 */
+	switch (augmented_args->args.syscall_nr) {
+	case SYS_ACCT:
+	case SYS_ADD_KEY:
+	case SYS_CHDIR:
+	case SYS_CHMOD:
+	case SYS_CHOWN:
+	case SYS_CHROOT:
+	case SYS_CREAT:
+	case SYS_DELETE_MODULE:
+	case SYS_EXECVE:
+	case SYS_GETXATTR:
+	case SYS_LCHOWN:
+	case SYS_LGETXATTR:
+	case SYS_LINK:
+	case SYS_LISTXATTR:
+	case SYS_LLISTXATTR:
+	case SYS_LREMOVEXATTR:
+	case SYS_LSETXATTR:
+	case SYS_LSTAT:
+	case SYS_MEMFD_CREATE:
+	case SYS_MKDIR:
+	case SYS_MKNOD:
+	case SYS_MQ_OPEN:
+	case SYS_MQ_UNLINK:
+	case SYS_PIVOT_ROOT:
+	case SYS_READLINK:
+	case SYS_REMOVEXATTR:
+	case SYS_RENAME:
+	case SYS_REQUEST_KEY:
+	case SYS_RMDIR:
+	case SYS_SETXATTR:
+	case SYS_STAT:
+	case SYS_STATFS:
+	case SYS_SWAPOFF:
+	case SYS_SWAPON:
+	case SYS_SYMLINK:
+	case SYS_SYMLINKAT:
+	case SYS_TRUNCATE:
+	case SYS_UNLINK:
 	case SYS_ACCESS:
 	case SYS_OPEN:	 filename_arg = (const void *)args->args[0];
 			__asm__ __volatile__("": : :"memory");
 			 break;
+	case SYS_EXECVEAT:
+	case SYS_FACCESSAT:
+	case SYS_FCHMODAT:
+	case SYS_FCHOWNAT:
+	case SYS_FGETXATTR:
+	case SYS_FINIT_MODULE:
+	case SYS_FREMOVEXATTR:
+	case SYS_FSETXATTR:
+	case SYS_FUTIMESAT:
+	case SYS_INOTIFY_ADD_WATCH:
+	case SYS_LINKAT:
+	case SYS_MKDIRAT:
+	case SYS_MKNODAT:
+	case SYS_MQ_TIMEDSEND:
+	case SYS_NAME_TO_HANDLE_AT:
+	case SYS_NEWFSTATAT:
+	case SYS_PWRITE64:
+	case SYS_QUOTACTL:
+	case SYS_READLINKAT:
+	case SYS_RENAMEAT:
+	case SYS_RENAMEAT2:
+	case SYS_STATX:
+	case SYS_UNLINKAT:
+	case SYS_UTIMENSAT:
 	case SYS_OPENAT: filename_arg = (const void *)args->args[1];
 			 break;
 	}
 
 	if (filename_arg != NULL) {
-		augmented_args.filename.reserved = 0;
-		augmented_args.filename.size = probe_read_str(&augmented_args.filename.value,
-							      sizeof(augmented_args.filename.value),
+		augmented_args->filename.reserved = 0;
+		augmented_args->filename.size = probe_read_str(&augmented_args->filename.value,
+							      sizeof(augmented_args->filename.value),
 							      filename_arg);
-		if (augmented_args.filename.size < sizeof(augmented_args.filename.value)) {
-			len -= sizeof(augmented_args.filename.value) - augmented_args.filename.size;
-			len &= sizeof(augmented_args.filename.value) - 1;
+		if (augmented_args->filename.size < sizeof(augmented_args->filename.value)) {
+			len -= sizeof(augmented_args->filename.value) - augmented_args->filename.size;
+			len &= sizeof(augmented_args->filename.value) - 1;
 		}
 	} else {
-		len = sizeof(augmented_args.args);
+		len = sizeof(augmented_args->args);
 	}
 
 	/* If perf_event_output fails, return non-zero so that it gets recorded unaugmented */
-	return perf_event_output(args, &__augmented_syscalls__, BPF_F_CURRENT_CPU, &augmented_args, len);
+	return perf_event_output(args, &__augmented_syscalls__, BPF_F_CURRENT_CPU, augmented_args, len);
 }
 
 SEC("raw_syscalls:sys_exit")
diff --git a/tools/perf/perf.h b/tools/perf/perf.h
index c59743def8d3..369eae61068d 100644
--- a/tools/perf/perf.h
+++ b/tools/perf/perf.h
@@ -85,6 +85,7 @@ struct record_opts {
 	u64          clockid_res_ns;
 	int	     nr_cblocks;
 	int	     affinity;
+	int	     mmap_flush;
 };
 
 enum perf_affinity {
diff --git a/tools/perf/pmu-events/arch/s390/cf_z14/extended.json b/tools/perf/pmu-events/arch/s390/cf_z14/extended.json
index e7a3524b748f..68618152ea2c 100644
--- a/tools/perf/pmu-events/arch/s390/cf_z14/extended.json
+++ b/tools/perf/pmu-events/arch/s390/cf_z14/extended.json
@@ -4,7 +4,7 @@
 		"EventCode": "128",
 		"EventName": "L1D_RO_EXCL_WRITES",
 		"BriefDescription": "L1D Read-only Exclusive Writes",
-		"PublicDescription": "Counter:128	Name:L1D_RO_EXCL_WRITES A directory write to the Level-1 Data cache where the line was originally in a Read-Only state in the cache but has been updated to be in the Exclusive state that allows stores to the cache line"
+		"PublicDescription": "L1D_RO_EXCL_WRITES A directory write to the Level-1 Data cache where the line was originally in a Read-Only state in the cache but has been updated to be in the Exclusive state that allows stores to the cache line"
 	},
 	{
 		"Unit": "CPU-M-CF",
diff --git a/tools/perf/pmu-events/arch/x86/bonnell/frontend.json b/tools/perf/pmu-events/arch/x86/bonnell/frontend.json
index 935b7dcf067d..ef69540ab61d 100644
--- a/tools/perf/pmu-events/arch/x86/bonnell/frontend.json
+++ b/tools/perf/pmu-events/arch/x86/bonnell/frontend.json
@@ -77,7 +77,7 @@
         "UMask": "0x1",
         "EventName": "UOPS.MS_CYCLES",
         "SampleAfterValue": "2000000",
-        "BriefDescription": "This event counts the cycles where 1 or more uops are issued by the micro-sequencer (MS), including microcode assists and inserted flows, and written to the IQ. ",
+        "BriefDescription": "This event counts the cycles where 1 or more uops are issued by the micro-sequencer (MS), including microcode assists and inserted flows, and written to the IQ.",
         "CounterMask": "1"
     }
 ]
\ No newline at end of file
diff --git a/tools/perf/pmu-events/arch/x86/bonnell/pipeline.json b/tools/perf/pmu-events/arch/x86/bonnell/pipeline.json
index b2e681c78466..09c6de13de20 100644
--- a/tools/perf/pmu-events/arch/x86/bonnell/pipeline.json
+++ b/tools/perf/pmu-events/arch/x86/bonnell/pipeline.json
@@ -189,7 +189,7 @@
         "UMask": "0x8",
         "EventName": "BR_MISSP_TYPE_RETIRED.IND_CALL",
         "SampleAfterValue": "200000",
-        "BriefDescription": "Mispredicted indirect calls, including both register and memory indirect. "
+        "BriefDescription": "Mispredicted indirect calls, including both register and memory indirect."
     },
     {
         "EventCode": "0x89",
diff --git a/tools/perf/pmu-events/arch/x86/broadwell/bdw-metrics.json b/tools/perf/pmu-events/arch/x86/broadwell/bdw-metrics.json
index 00bfdb5c5acb..212b117a8ffb 100644
--- a/tools/perf/pmu-events/arch/x86/broadwell/bdw-metrics.json
+++ b/tools/perf/pmu-events/arch/x86/broadwell/bdw-metrics.json
@@ -1,164 +1,352 @@
 [
     {
-        "BriefDescription": "Instructions Per Cycle (per logical thread)",
+        "MetricExpr": "IDQ_UOPS_NOT_DELIVERED.CORE / (4 * cycles)",
+        "PublicDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend. Frontend denotes the first part of the processor core responsible to fetch operations that are executed later on by the Backend part. Within the Frontend; a branch predictor predicts the next address to fetch; cache-lines are fetched from the memory subsystem; parsed into instructions; and lastly decoded into micro-ops (uops). Ideally the Frontend can issue 4 uops every cycle to the Backend. Frontend Bound denotes unutilized issue-slots when there is no Backend stall; i.e. bubbles where Frontend delivered no uops while Backend could have accepted them. For example; stalls due to instruction-cache misses would be categorized under Frontend Bound.",
+        "BriefDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend",
+        "MetricGroup": "TopdownL1",
+        "MetricName": "Frontend_Bound"
+    },
+    {
+        "MetricExpr": "IDQ_UOPS_NOT_DELIVERED.CORE / (4 * (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )))",
+        "PublicDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend. Frontend denotes the first part of the processor core responsible to fetch operations that are executed later on by the Backend part. Within the Frontend; a branch predictor predicts the next address to fetch; cache-lines are fetched from the memory subsystem; parsed into instructions; and lastly decoded into micro-ops (uops). Ideally the Frontend can issue 4 uops every cycle to the Backend. Frontend Bound denotes unutilized issue-slots when there is no Backend stall; i.e. bubbles where Frontend delivered no uops while Backend could have accepted them. For example; stalls due to instruction-cache misses would be categorized under Frontend Bound. SMT version; use when SMT is enabled and measuring per logical CPU.",
+        "BriefDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend. SMT version; use when SMT is enabled and measuring per logical CPU.",
+        "MetricGroup": "TopdownL1_SMT",
+        "MetricName": "Frontend_Bound_SMT"
+    },
+    {
+        "MetricExpr": "( UOPS_ISSUED.ANY - UOPS_RETIRED.RETIRE_SLOTS + 4 * INT_MISC.RECOVERY_CYCLES ) / (4 * cycles)",
+        "PublicDescription": "This category represents fraction of slots wasted due to incorrect speculations. This include slots used to issue uops that do not eventually get retired and slots for which the issue-pipeline was blocked due to recovery from earlier incorrect speculation. For example; wasted work due to miss-predicted branches are categorized under Bad Speculation category. Incorrect data speculation followed by Memory Ordering Nukes is another example.",
+        "BriefDescription": "This category represents fraction of slots wasted due to incorrect speculations",
+        "MetricGroup": "TopdownL1",
+        "MetricName": "Bad_Speculation"
+    },
+    {
+        "MetricExpr": "( UOPS_ISSUED.ANY - UOPS_RETIRED.RETIRE_SLOTS + 4 * (( INT_MISC.RECOVERY_CYCLES_ANY / 2 )) ) / (4 * (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )))",
+        "PublicDescription": "This category represents fraction of slots wasted due to incorrect speculations. This include slots used to issue uops that do not eventually get retired and slots for which the issue-pipeline was blocked due to recovery from earlier incorrect speculation. For example; wasted work due to miss-predicted branches are categorized under Bad Speculation category. Incorrect data speculation followed by Memory Ordering Nukes is another example. SMT version; use when SMT is enabled and measuring per logical CPU.",
+        "BriefDescription": "This category represents fraction of slots wasted due to incorrect speculations. SMT version; use when SMT is enabled and measuring per logical CPU.",
+        "MetricGroup": "TopdownL1_SMT",
+        "MetricName": "Bad_Speculation_SMT"
+    },
+    {
+        "MetricExpr": "1 - ( (IDQ_UOPS_NOT_DELIVERED.CORE / (4 * cycles)) + (( UOPS_ISSUED.ANY - UOPS_RETIRED.RETIRE_SLOTS + 4 * INT_MISC.RECOVERY_CYCLES ) / (4 * cycles)) + (UOPS_RETIRED.RETIRE_SLOTS / (4 * cycles)) )",
+        "PublicDescription": "This category represents fraction of slots where no uops are being delivered due to a lack of required resources for accepting new uops in the Backend. Backend is the portion of the processor core where the out-of-order scheduler dispatches ready uops into their respective execution units; and once completed these uops get retired according to program order. For example; stalls due to data-cache misses or stalls due to the divider unit being overloaded are both categorized under Backend Bound. Backend Bound is further divided into two main categories: Memory Bound and Core Bound.",
+        "BriefDescription": "This category represents fraction of slots where no uops are being delivered due to a lack of required resources for accepting new uops in the Backend",
+        "MetricGroup": "TopdownL1",
+        "MetricName": "Backend_Bound"
+    },
+    {
+        "MetricExpr": "1 - ( (IDQ_UOPS_NOT_DELIVERED.CORE / (4 * (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )))) + (( UOPS_ISSUED.ANY - UOPS_RETIRED.RETIRE_SLOTS + 4 * (( INT_MISC.RECOVERY_CYCLES_ANY / 2 )) ) / (4 * (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )))) + (UOPS_RETIRED.RETIRE_SLOTS / (4 * (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )))) )",
+        "PublicDescription": "This category represents fraction of slots where no uops are being delivered due to a lack of required resources for accepting new uops in the Backend. Backend is the portion of the processor core where the out-of-order scheduler dispatches ready uops into their respective execution units; and once completed these uops get retired according to program order. For example; stalls due to data-cache misses or stalls due to the divider unit being overloaded are both categorized under Backend Bound. Backend Bound is further divided into two main categories: Memory Bound and Core Bound. SMT version; use when SMT is enabled and measuring per logical CPU.",
+        "BriefDescription": "This category represents fraction of slots where no uops are being delivered due to a lack of required resources for accepting new uops in the Backend. SMT version; use when SMT is enabled and measuring per logical CPU.",
+        "MetricGroup": "TopdownL1_SMT",
+        "MetricName": "Backend_Bound_SMT"
+    },
+    {
+        "MetricExpr": "UOPS_RETIRED.RETIRE_SLOTS / (4 * cycles)",
+        "PublicDescription": "This category represents fraction of slots utilized by useful work i.e. issued uops that eventually get retired. Ideally; all pipeline slots would be attributed to the Retiring category.  Retiring of 100% would indicate the maximum 4 uops retired per cycle has been achieved.  Maximizing Retiring typically increases the Instruction-Per-Cycle metric. Note that a high Retiring value does not necessary mean there is no room for more performance.  For example; Microcode assists are categorized under Retiring. They hurt performance and can often be avoided. ",
+        "BriefDescription": "This category represents fraction of slots utilized by useful work i.e. issued uops that eventually get retired",
+        "MetricGroup": "TopdownL1",
+        "MetricName": "Retiring"
+    },
+    {
+        "MetricExpr": "UOPS_RETIRED.RETIRE_SLOTS / (4 * (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )))",
+        "PublicDescription": "This category represents fraction of slots utilized by useful work i.e. issued uops that eventually get retired. Ideally; all pipeline slots would be attributed to the Retiring category.  Retiring of 100% would indicate the maximum 4 uops retired per cycle has been achieved.  Maximizing Retiring typically increases the Instruction-Per-Cycle metric. Note that a high Retiring value does not necessary mean there is no room for more performance.  For example; Microcode assists are categorized under Retiring. They hurt performance and can often be avoided. SMT version; use when SMT is enabled and measuring per logical CPU.",
+        "BriefDescription": "This category represents fraction of slots utilized by useful work i.e. issued uops that eventually get retired. SMT version; use when SMT is enabled and measuring per logical CPU.",
+        "MetricGroup": "TopdownL1_SMT",
+        "MetricName": "Retiring_SMT"
+    },
+    {
         "MetricExpr": "INST_RETIRED.ANY / CPU_CLK_UNHALTED.THREAD",
+        "BriefDescription": "Instructions Per Cycle (per logical thread)",
         "MetricGroup": "TopDownL1",
         "MetricName": "IPC"
     },
     {
-        "BriefDescription": "Uops Per Instruction",
         "MetricExpr": "UOPS_RETIRED.RETIRE_SLOTS / INST_RETIRED.ANY",
-        "MetricGroup": "Pipeline",
+        "BriefDescription": "Uops Per Instruction",
+        "MetricGroup": "Pipeline;Retiring",
         "MetricName": "UPI"
     },
     {
-        "BriefDescription": "Rough Estimation of fraction of fetched lines bytes that were likely consumed by program instructions",
+        "MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.NEAR_TAKEN",
+        "BriefDescription": "Instruction per taken branch",
+        "MetricGroup": "Branches;PGO",
+        "MetricName": "IpTB"
+    },
+    {
+        "MetricExpr": "BR_INST_RETIRED.ALL_BRANCHES / BR_INST_RETIRED.NEAR_TAKEN",
+        "BriefDescription": "Branch instructions per taken branch. ",
+        "MetricGroup": "Branches;PGO",
+        "MetricName": "BpTB"
+    },
+    {
         "MetricExpr": "min( 1 , IDQ.MITE_UOPS / ( (UOPS_RETIRED.RETIRE_SLOTS / INST_RETIRED.ANY) * 16 * ( ICACHE.HIT + ICACHE.MISSES ) / 4.0 ) )",
-        "MetricGroup": "Frontend",
+        "BriefDescription": "Rough Estimation of fraction of fetched lines bytes that were likely (includes speculatively fetches) consumed by program instructions",
+        "MetricGroup": "PGO",
         "MetricName": "IFetch_Line_Utilization"
     },
     {
-        "BriefDescription": "Fraction of Uops delivered by the DSB (aka Decoded Icache; or Uop Cache)",
-        "MetricExpr": "IDQ.DSB_UOPS / ( IDQ.DSB_UOPS + LSD.UOPS + IDQ.MITE_UOPS + IDQ.MS_UOPS )",
-        "MetricGroup": "DSB; Frontend_Bandwidth",
+        "MetricExpr": "IDQ.DSB_UOPS / (( IDQ.DSB_UOPS + LSD.UOPS + IDQ.MITE_UOPS + IDQ.MS_UOPS ) )",
+        "BriefDescription": "Fraction of Uops delivered by the DSB (aka Decoded ICache; or Uop Cache)",
+        "MetricGroup": "DSB;Frontend_Bandwidth",
         "MetricName": "DSB_Coverage"
     },
     {
-        "BriefDescription": "Cycles Per Instruction (threaded)",
         "MetricExpr": "1 / (INST_RETIRED.ANY / cycles)",
+        "BriefDescription": "Cycles Per Instruction (threaded)",
         "MetricGroup": "Pipeline;Summary",
         "MetricName": "CPI"
     },
     {
-        "BriefDescription": "Per-thread actual clocks when the logical processor is active. This is called 'Clockticks' in VTune.",
         "MetricExpr": "CPU_CLK_UNHALTED.THREAD",
+        "BriefDescription": "Per-thread actual clocks when the logical processor is active.",
         "MetricGroup": "Summary",
         "MetricName": "CLKS"
     },
     {
-        "BriefDescription": "Total issue-pipeline slots",
-        "MetricExpr": "4*(( CPU_CLK_UNHALTED.THREAD_ANY / 2 ) if #SMT_on else cycles)",
+        "MetricExpr": "4 * cycles",
+        "BriefDescription": "Total issue-pipeline slots (per core)",
         "MetricGroup": "TopDownL1",
         "MetricName": "SLOTS"
     },
     {
-        "BriefDescription": "Total number of retired Instructions",
+        "MetricExpr": "4 * (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) ))",
+        "BriefDescription": "Total issue-pipeline slots (per core)",
+        "MetricGroup": "TopDownL1_SMT",
+        "MetricName": "SLOTS_SMT"
+    },
+    {
+        "MetricExpr": "INST_RETIRED.ANY / MEM_UOPS_RETIRED.ALL_LOADS",
+        "BriefDescription": "Instructions per Load (lower number means loads are more frequent)",
+        "MetricGroup": "Instruction_Type;L1_Bound",
+        "MetricName": "IpL"
+    },
+    {
+        "MetricExpr": "INST_RETIRED.ANY / MEM_UOPS_RETIRED.ALL_STORES",
+        "BriefDescription": "Instructions per Store",
+        "MetricGroup": "Instruction_Type;Store_Bound",
+        "MetricName": "IpS"
+    },
+    {
+        "MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.ALL_BRANCHES",
+        "BriefDescription": "Instructions per Branch",
+        "MetricGroup": "Branches;Instruction_Type;Port_5;Port_6",
+        "MetricName": "IpB"
+    },
+    {
+        "MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.NEAR_CALL",
+        "BriefDescription": "Instruction per (near) call",
+        "MetricGroup": "Branches",
+        "MetricName": "IpCall"
+    },
+    {
         "MetricExpr": "INST_RETIRED.ANY",
+        "BriefDescription": "Total number of retired Instructions",
         "MetricGroup": "Summary",
         "MetricName": "Instructions"
     },
     {
+        "MetricExpr": "INST_RETIRED.ANY / cycles",
         "BriefDescription": "Instructions Per Cycle (per physical core)",
-        "MetricExpr": "INST_RETIRED.ANY / (( CPU_CLK_UNHALTED.THREAD_ANY / 2 ) if #SMT_on else cycles)",
         "MetricGroup": "SMT",
         "MetricName": "CoreIPC"
     },
     {
+        "MetricExpr": "INST_RETIRED.ANY / (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) ))",
+        "BriefDescription": "Instructions Per Cycle (per physical core)",
+        "MetricGroup": "SMT",
+        "MetricName": "CoreIPC_SMT"
+    },
+    {
+        "MetricExpr": "(( 1 * ( FP_ARITH_INST_RETIRED.SCALAR_SINGLE + FP_ARITH_INST_RETIRED.SCALAR_DOUBLE ) + 2 * FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE + 4 * ( FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE + FP_ARITH_INST_RETIRED.256B_PACKED_DOUBLE ) + 8 * FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE )) / cycles",
+        "BriefDescription": "Floating Point Operations Per Cycle",
+        "MetricGroup": "FLOPS",
+        "MetricName": "FLOPc"
+    },
+    {
+        "MetricExpr": "(( 1 * ( FP_ARITH_INST_RETIRED.SCALAR_SINGLE + FP_ARITH_INST_RETIRED.SCALAR_DOUBLE ) + 2 * FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE + 4 * ( FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE + FP_ARITH_INST_RETIRED.256B_PACKED_DOUBLE ) + 8 * FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE )) / (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) ))",
+        "BriefDescription": "Floating Point Operations Per Cycle",
+        "MetricGroup": "FLOPS_SMT",
+        "MetricName": "FLOPc_SMT"
+    },
+    {
+        "MetricExpr": "UOPS_EXECUTED.THREAD / (( cpu@UOPS_EXECUTED.CORE\\,cmask\\=1@ / 2 ) if #SMT_on else UOPS_EXECUTED.CYCLES_GE_1_UOP_EXEC)",
         "BriefDescription": "Instruction-Level-Parallelism (average number of uops executed when there is at least 1 uop executed)",
-        "MetricExpr": "UOPS_EXECUTED.THREAD / (( cpu@UOPS_EXECUTED.CORE\\,cmask\\=1@ / 2) if #SMT_on else UOPS_EXECUTED.CYCLES_GE_1_UOP_EXEC)",
         "MetricGroup": "Pipeline;Ports_Utilization",
         "MetricName": "ILP"
     },
     {
-        "BriefDescription": "Average Branch Address Clear Cost (fraction of cycles)",
-        "MetricExpr": "2* (( RS_EVENTS.EMPTY_CYCLES - ICACHE.IFDATA_STALL  - (( 14 * ITLB_MISSES.STLB_HIT + cpu@ITLB_MISSES.WALK_DURATION\\,cmask\\=1@ + 7* ITLB_MISSES.WALK_COMPLETED )) ) / RS_EVENTS.EMPTY_END)",
-        "MetricGroup": "Unknown_Branches",
-        "MetricName": "BAClear_Cost"
+        "MetricExpr": "( ((BR_MISP_RETIRED.ALL_BRANCHES / ( BR_MISP_RETIRED.ALL_BRANCHES + MACHINE_CLEARS.COUNT )) * (( UOPS_ISSUED.ANY - UOPS_RETIRED.RETIRE_SLOTS + 4 * INT_MISC.RECOVERY_CYCLES ) / (4 * cycles))) + (4 * IDQ_UOPS_NOT_DELIVERED.CYCLES_0_UOPS_DELIV.CORE / (4 * cycles)) * (12 * ( BR_MISP_RETIRED.ALL_BRANCHES + MACHINE_CLEARS.COUNT + BACLEARS.ANY ) / cycles) / (4 * IDQ_UOPS_NOT_DELIVERED.CYCLES_0_UOPS_DELIV.CORE / (4 * cycles)) ) * (4 * cycles) / BR_MISP_RETIRED.ALL_BRANCHES",
+        "BriefDescription": "Branch Misprediction Cost: Fraction of TopDown slots wasted per branch misprediction (jeclear and baclear)",
+        "MetricGroup": "Branch_Mispredicts",
+        "MetricName": "Branch_Misprediction_Cost"
     },
     {
+        "MetricExpr": "( ((BR_MISP_RETIRED.ALL_BRANCHES / ( BR_MISP_RETIRED.ALL_BRANCHES + MACHINE_CLEARS.COUNT )) * (( UOPS_ISSUED.ANY - UOPS_RETIRED.RETIRE_SLOTS + 4 * (( INT_MISC.RECOVERY_CYCLES_ANY / 2 )) ) / (4 * (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) ))))) + (4 * IDQ_UOPS_NOT_DELIVERED.CYCLES_0_UOPS_DELIV.CORE / (4 * (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )))) * (12 * ( BR_MISP_RETIRED.ALL_BRANCHES + MACHINE_CLEARS.COUNT + BACLEARS.ANY ) / cycles) / (4 * IDQ_UOPS_NOT_DELIVERED.CYCLES_0_UOPS_DELIV.CORE / (4 * (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )))) ) * (4 * (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) ))) / BR_MISP_RETIRED.ALL_BRANCHES",
+        "BriefDescription": "Branch Misprediction Cost: Fraction of TopDown slots wasted per branch misprediction (jeclear and baclear)",
+        "MetricGroup": "Branch_Mispredicts_SMT",
+        "MetricName": "Branch_Misprediction_Cost_SMT"
+    },
+    {
+        "MetricExpr": "INST_RETIRED.ANY / BR_MISP_RETIRED.ALL_BRANCHES",
+        "BriefDescription": "Number of Instructions per non-speculative Branch Misprediction (JEClear)",
+        "MetricGroup": "Branch_Mispredicts",
+        "MetricName": "IpMispredict"
+    },
+    {
+        "MetricExpr": "( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )",
         "BriefDescription": "Core actual clocks when any thread is active on the physical core",
-        "MetricExpr": "( CPU_CLK_UNHALTED.THREAD_ANY / 2 ) if #SMT_on else CPU_CLK_UNHALTED.THREAD",
         "MetricGroup": "SMT",
         "MetricName": "CORE_CLKS"
     },
     {
-        "BriefDescription": "Actual Average Latency for L1 data-cache miss demand loads",
         "MetricExpr": "L1D_PEND_MISS.PENDING / ( MEM_LOAD_UOPS_RETIRED.L1_MISS + mem_load_uops_retired.hit_lfb )",
+        "BriefDescription": "Actual Average Latency for L1 data-cache miss demand loads (in core cycles)",
         "MetricGroup": "Memory_Bound;Memory_Lat",
         "MetricName": "Load_Miss_Real_Latency"
     },
     {
-        "BriefDescription": "Memory-Level-Parallelism (average number of L1 miss demand load when there is at least 1 such miss)",
-        "MetricExpr": "L1D_PEND_MISS.PENDING / (( cpu@l1d_pend_miss.pending_cycles\\,any\\=1@ / 2) if #SMT_on else L1D_PEND_MISS.PENDING_CYCLES)",
+        "MetricExpr": "L1D_PEND_MISS.PENDING / L1D_PEND_MISS.PENDING_CYCLES",
+        "BriefDescription": "Memory-Level-Parallelism (average number of L1 miss demand load when there is at least one such miss. Per-thread)",
         "MetricGroup": "Memory_Bound;Memory_BW",
         "MetricName": "MLP"
     },
     {
+        "MetricExpr": "( cpu@ITLB_MISSES.WALK_DURATION\\,cmask\\=1@ + cpu@DTLB_LOAD_MISSES.WALK_DURATION\\,cmask\\=1@ + cpu@DTLB_STORE_MISSES.WALK_DURATION\\,cmask\\=1@ + 7 * ( DTLB_STORE_MISSES.WALK_COMPLETED + DTLB_LOAD_MISSES.WALK_COMPLETED + ITLB_MISSES.WALK_COMPLETED ) ) / cycles",
         "BriefDescription": "Utilization of the core's Page Walker(s) serving STLB misses triggered by instruction/Load/Store accesses",
-        "MetricExpr": "( cpu@ITLB_MISSES.WALK_DURATION\\,cmask\\=1@ + cpu@DTLB_LOAD_MISSES.WALK_DURATION\\,cmask\\=1@ + cpu@DTLB_STORE_MISSES.WALK_DURATION\\,cmask\\=1@ + 7*(DTLB_STORE_MISSES.WALK_COMPLETED+DTLB_LOAD_MISSES.WALK_COMPLETED+ITLB_MISSES.WALK_COMPLETED)) / (( CPU_CLK_UNHALTED.THREAD_ANY / 2 ) if #SMT_on else cycles)",
         "MetricGroup": "TLB",
         "MetricName": "Page_Walks_Utilization"
     },
     {
-        "BriefDescription": "Average CPU Utilization",
+        "MetricExpr": "( cpu@ITLB_MISSES.WALK_DURATION\\,cmask\\=1@ + cpu@DTLB_LOAD_MISSES.WALK_DURATION\\,cmask\\=1@ + cpu@DTLB_STORE_MISSES.WALK_DURATION\\,cmask\\=1@ + 7 * ( DTLB_STORE_MISSES.WALK_COMPLETED + DTLB_LOAD_MISSES.WALK_COMPLETED + ITLB_MISSES.WALK_COMPLETED ) ) / (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) ))",
+        "BriefDescription": "Utilization of the core's Page Walker(s) serving STLB misses triggered by instruction/Load/Store accesses",
+        "MetricGroup": "TLB_SMT",
+        "MetricName": "Page_Walks_Utilization_SMT"
+    },
+    {
+        "MetricExpr": "64 * L1D.REPLACEMENT / 1000000000 / duration_time",
+        "BriefDescription": "Average data fill bandwidth to the L1 data cache [GB / sec]",
+        "MetricGroup": "Memory_BW",
+        "MetricName": "L1D_Cache_Fill_BW"
+    },
+    {
+        "MetricExpr": "64 * L2_LINES_IN.ALL / 1000000000 / duration_time",
+        "BriefDescription": "Average data fill bandwidth to the L2 cache [GB / sec]",
+        "MetricGroup": "Memory_BW",
+        "MetricName": "L2_Cache_Fill_BW"
+    },
+    {
+        "MetricExpr": "64 * LONGEST_LAT_CACHE.MISS / 1000000000 / duration_time",
+        "BriefDescription": "Average per-core data fill bandwidth to the L3 cache [GB / sec]",
+        "MetricGroup": "Memory_BW",
+        "MetricName": "L3_Cache_Fill_BW"
+    },
+    {
+        "MetricExpr": "1000 * MEM_LOAD_UOPS_RETIRED.L1_MISS / INST_RETIRED.ANY",
+        "BriefDescription": "L1 cache true misses per kilo instruction for retired demand loads",
+        "MetricGroup": "Cache_Misses;",
+        "MetricName": "L1MPKI"
+    },
+    {
+        "MetricExpr": "1000 * MEM_LOAD_UOPS_RETIRED.L2_MISS / INST_RETIRED.ANY",
+        "BriefDescription": "L2 cache true misses per kilo instruction for retired demand loads",
+        "MetricGroup": "Cache_Misses;",
+        "MetricName": "L2MPKI"
+    },
+    {
+        "MetricExpr": "1000 * L2_RQSTS.MISS / INST_RETIRED.ANY",
+        "BriefDescription": "L2 cache misses per kilo instruction for all request types (including speculative)",
+        "MetricGroup": "Cache_Misses;",
+        "MetricName": "L2MPKI_All"
+    },
+    {
+        "MetricExpr": "1000 * ( L2_RQSTS.REFERENCES - L2_RQSTS.MISS ) / INST_RETIRED.ANY",
+        "BriefDescription": "L2 cache hits per kilo instruction for all request types (including speculative)",
+        "MetricGroup": "Cache_Misses;",
+        "MetricName": "L2HPKI_All"
+    },
+    {
+        "MetricExpr": "1000 * MEM_LOAD_UOPS_RETIRED.L3_MISS / INST_RETIRED.ANY",
+        "BriefDescription": "L3 cache true misses per kilo instruction for retired demand loads",
+        "MetricGroup": "Cache_Misses;",
+        "MetricName": "L3MPKI"
+    },
+    {
         "MetricExpr": "CPU_CLK_UNHALTED.REF_TSC / msr@tsc@",
+        "BriefDescription": "Average CPU Utilization",
         "MetricGroup": "Summary",
         "MetricName": "CPU_Utilization"
     },
     {
+        "MetricExpr": "( (( 1 * ( FP_ARITH_INST_RETIRED.SCALAR_SINGLE + FP_ARITH_INST_RETIRED.SCALAR_DOUBLE ) + 2 * FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE + 4 * ( FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE + FP_ARITH_INST_RETIRED.256B_PACKED_DOUBLE ) + 8 * FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE )) / 1000000000 ) / duration_time",
         "BriefDescription": "Giga Floating Point Operations Per Second",
-        "MetricExpr": "(( 1*( FP_ARITH_INST_RETIRED.SCALAR_SINGLE + FP_ARITH_INST_RETIRED.SCALAR_DOUBLE ) + 2* FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE + 4*( FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE + FP_ARITH_INST_RETIRED.256B_PACKED_DOUBLE ) + 8* FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE )) / 1000000000 / duration_time",
         "MetricGroup": "FLOPS;Summary",
         "MetricName": "GFLOPs"
     },
     {
-        "BriefDescription": "Average Frequency Utilization relative nominal frequency",
         "MetricExpr": "CPU_CLK_UNHALTED.THREAD / CPU_CLK_UNHALTED.REF_TSC",
+        "BriefDescription": "Average Frequency Utilization relative nominal frequency",
         "MetricGroup": "Power",
         "MetricName": "Turbo_Utilization"
     },
     {
-        "BriefDescription": "Fraction of cycles where both hardware threads were active",
         "MetricExpr": "1 - CPU_CLK_THREAD_UNHALTED.ONE_THREAD_ACTIVE / ( CPU_CLK_THREAD_UNHALTED.REF_XCLK_ANY / 2 ) if #SMT_on else 0",
+        "BriefDescription": "Fraction of cycles where both hardware threads were active",
         "MetricGroup": "SMT;Summary",
         "MetricName": "SMT_2T_Utilization"
     },
     {
-        "BriefDescription": "Fraction of cycles spent in Kernel mode",
         "MetricExpr": "CPU_CLK_UNHALTED.REF_TSC:u / CPU_CLK_UNHALTED.REF_TSC",
+        "BriefDescription": "Fraction of cycles spent in Kernel mode",
         "MetricGroup": "Summary",
         "MetricName": "Kernel_Utilization"
     },
     {
-        "BriefDescription": "C3 residency percent per core",
+        "MetricExpr": "64 * ( arb@event\\=0x81\\,umask\\=0x1@ + arb@event\\=0x84\\,umask\\=0x1@ ) / 1000000 / duration_time / 1000",
+        "BriefDescription": "Average external Memory Bandwidth Use for reads and writes [GB / sec]",
+        "MetricGroup": "Memory_BW",
+        "MetricName": "DRAM_BW_Use"
+    },
+    {
         "MetricExpr": "(cstate_core@c3\\-residency@ / msr@tsc@) * 100",
         "MetricGroup": "Power",
+        "BriefDescription": "C3 residency percent per core",
         "MetricName": "C3_Core_Residency"
     },
     {
-        "BriefDescription": "C6 residency percent per core",
         "MetricExpr": "(cstate_core@c6\\-residency@ / msr@tsc@) * 100",
         "MetricGroup": "Power",
+        "BriefDescription": "C6 residency percent per core",
         "MetricName": "C6_Core_Residency"
     },
     {
-        "BriefDescription": "C7 residency percent per core",
         "MetricExpr": "(cstate_core@c7\\-residency@ / msr@tsc@) * 100",
         "MetricGroup": "Power",
+        "BriefDescription": "C7 residency percent per core",
         "MetricName": "C7_Core_Residency"
     },
     {
-        "BriefDescription": "C2 residency percent per package",
         "MetricExpr": "(cstate_pkg@c2\\-residency@ / msr@tsc@) * 100",
         "MetricGroup": "Power",
+        "BriefDescription": "C2 residency percent per package",
         "MetricName": "C2_Pkg_Residency"
     },
     {
-        "BriefDescription": "C3 residency percent per package",
         "MetricExpr": "(cstate_pkg@c3\\-residency@ / msr@tsc@) * 100",
         "MetricGroup": "Power",
+        "BriefDescription": "C3 residency percent per package",
         "MetricName": "C3_Pkg_Residency"
     },
     {
-        "BriefDescription": "C6 residency percent per package",
         "MetricExpr": "(cstate_pkg@c6\\-residency@ / msr@tsc@) * 100",
         "MetricGroup": "Power",
+        "BriefDescription": "C6 residency percent per package",
         "MetricName": "C6_Pkg_Residency"
     },
     {
-        "BriefDescription": "C7 residency percent per package",
         "MetricExpr": "(cstate_pkg@c7\\-residency@ / msr@tsc@) * 100",
         "MetricGroup": "Power",
+        "BriefDescription": "C7 residency percent per package",
         "MetricName": "C7_Pkg_Residency"
     }
 ]
diff --git a/tools/perf/pmu-events/arch/x86/broadwell/cache.json b/tools/perf/pmu-events/arch/x86/broadwell/cache.json
index 0b080b0352d8..7938bf5689ab 100644
--- a/tools/perf/pmu-events/arch/x86/broadwell/cache.json
+++ b/tools/perf/pmu-events/arch/x86/broadwell/cache.json
@@ -56,10 +56,10 @@
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "PublicDescription": "This event counts the number of demand Data Read requests that hit L2 cache. Only not rejected loads are counted.",
+        "PublicDescription": "Counts the number of demand Data Read requests, initiated by load instructions, that hit L2 cache.",
         "EventCode": "0x24",
         "Counter": "0,1,2,3",
-        "UMask": "0x41",
+        "UMask": "0xc1",
         "EventName": "L2_RQSTS.DEMAND_DATA_RD_HIT",
         "SampleAfterValue": "200003",
         "BriefDescription": "Demand Data Read requests that hit L2 cache",
@@ -68,7 +68,7 @@
     {
         "EventCode": "0x24",
         "Counter": "0,1,2,3",
-        "UMask": "0x42",
+        "UMask": "0xc2",
         "EventName": "L2_RQSTS.RFO_HIT",
         "SampleAfterValue": "200003",
         "BriefDescription": "RFO requests that hit L2 cache.",
@@ -77,7 +77,7 @@
     {
         "EventCode": "0x24",
         "Counter": "0,1,2,3",
-        "UMask": "0x44",
+        "UMask": "0xc4",
         "EventName": "L2_RQSTS.CODE_RD_HIT",
         "SampleAfterValue": "200003",
         "BriefDescription": "L2 cache hits when fetching instructions, code reads.",
@@ -87,7 +87,7 @@
         "PublicDescription": "This event counts the number of requests from the L2 hardware prefetchers that hit L2 cache. L3 prefetch new types.",
         "EventCode": "0x24",
         "Counter": "0,1,2,3",
-        "UMask": "0x50",
+        "UMask": "0xd0",
         "EventName": "L2_RQSTS.L2_PF_HIT",
         "SampleAfterValue": "200003",
         "BriefDescription": "L2 prefetch requests that hit L2 cache",
@@ -433,7 +433,7 @@
     },
     {
         "PEBS": "1",
-        "PublicDescription": "This is a precise version (that is, uses PEBS) of the event that counts line-split load uops retired to the architected path. A line split is across 64B cache-line which includes a page split (4K).",
+        "PublicDescription": "This is a precise version (that is, uses PEBS) of the event that counts line-splitted load uops retired to the architected path. A line split is across 64B cache-line which includes a page split (4K).",
         "EventCode": "0xD0",
         "Counter": "0,1,2,3",
         "UMask": "0x41",
@@ -445,7 +445,7 @@
     },
     {
         "PEBS": "1",
-        "PublicDescription": "This is a precise version (that is, uses PEBS) of the event that counts line-split store uops retired to the architected path. A line split is across 64B cache-line which includes a page split (4K).",
+        "PublicDescription": "This is a precise version (that is, uses PEBS) of the event that counts line-splitted store uops retired to the architected path. A line split is across 64B cache-line which includes a page split (4K).",
         "EventCode": "0xD0",
         "Counter": "0,1,2,3",
         "UMask": "0x42",
@@ -771,2628 +771,2628 @@
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "PublicDescription": "Counts demand data reads that have any response type. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts demand data reads have any response type.",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0000010001 ",
+        "MSRValue": "0x0000010001",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.ANY_RESPONSE",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "Counts demand data reads that have any response type.",
+        "BriefDescription": "Counts demand data reads have any response type.",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts demand data reads",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0080020001 ",
+        "MSRValue": "0x0080020001",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.SUPPLIER_NONE.SNOOP_NONE",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "DEMAND_DATA_RD & SUPPLIER_NONE & SNOOP_NONE",
+        "BriefDescription": "Counts demand data reads",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts demand data reads",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0100020001 ",
+        "MSRValue": "0x0100020001",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.SUPPLIER_NONE.SNOOP_NOT_NEEDED",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "DEMAND_DATA_RD & SUPPLIER_NONE & SNOOP_NOT_NEEDED",
+        "BriefDescription": "Counts demand data reads",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts demand data reads",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0200020001 ",
+        "MSRValue": "0x0200020001",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.SUPPLIER_NONE.SNOOP_MISS",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "DEMAND_DATA_RD & SUPPLIER_NONE & SNOOP_MISS",
+        "BriefDescription": "Counts demand data reads",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts demand data reads",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0400020001 ",
+        "MSRValue": "0x0400020001",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.SUPPLIER_NONE.SNOOP_HIT_NO_FWD",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "DEMAND_DATA_RD & SUPPLIER_NONE & SNOOP_HIT_NO_FWD",
+        "BriefDescription": "Counts demand data reads",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts demand data reads",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x1000020001 ",
+        "MSRValue": "0x1000020001",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.SUPPLIER_NONE.SNOOP_HITM",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "DEMAND_DATA_RD & SUPPLIER_NONE & SNOOP_HITM",
+        "BriefDescription": "Counts demand data reads",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts demand data reads",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x3f80020001 ",
+        "MSRValue": "0x3F80020001",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.SUPPLIER_NONE.ANY_SNOOP",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "DEMAND_DATA_RD & SUPPLIER_NONE & ANY_SNOOP",
+        "BriefDescription": "Counts demand data reads",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "Counts demand data reads that hit in the L3 with no details on snoop-related information. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts demand data reads",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x00803c0001 ",
+        "MSRValue": "0x00803C0001",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_HIT.SNOOP_NONE",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "Counts demand data reads that hit in the L3 with no details on snoop-related information.",
+        "BriefDescription": "Counts demand data reads",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "Counts demand data reads that hit in the L3 and sibling core snoops are not needed as either the core-valid bit is not set or the shared line is present in multiple cores. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts demand data reads",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x01003c0001 ",
+        "MSRValue": "0x01003C0001",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_HIT.SNOOP_NOT_NEEDED",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "Counts demand data reads that hit in the L3 and sibling core snoops are not needed as either the core-valid bit is not set or the shared line is present in multiple cores.",
+        "BriefDescription": "Counts demand data reads",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "Counts demand data reads that hit in the L3 with a snoop miss response. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts demand data reads",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x02003c0001 ",
+        "MSRValue": "0x02003C0001",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_HIT.SNOOP_MISS",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "Counts demand data reads that hit in the L3 with a snoop miss response.",
+        "BriefDescription": "Counts demand data reads",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "Counts demand data reads that hit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts demand data reads",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x04003c0001 ",
+        "MSRValue": "0x04003C0001",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_HIT.SNOOP_HIT_NO_FWD",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "Counts demand data reads that hit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded.",
+        "BriefDescription": "Counts demand data reads",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts demand data reads",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x10003c0001 ",
+        "MSRValue": "0x10003C0001",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_HIT.SNOOP_HITM",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "DEMAND_DATA_RD & L3_HIT & SNOOP_HITM",
+        "BriefDescription": "Counts demand data reads",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "Counts demand data reads that hit in the L3. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts demand data reads",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x3f803c0001 ",
+        "MSRValue": "0x3F803C0001",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_HIT.ANY_SNOOP",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "Counts demand data reads that hit in the L3.",
+        "BriefDescription": "Counts demand data reads",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "Counts all demand data writes (RFOs) that have any response type. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all demand data writes (RFOs) have any response type.",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0000010002 ",
+        "MSRValue": "0x0000010002",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.ANY_RESPONSE",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "Counts all demand data writes (RFOs) that have any response type.",
+        "BriefDescription": "Counts all demand data writes (RFOs) have any response type.",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "Counts all demand data writes (RFOs) that hit in the L3 with no details on snoop-related information. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all demand data writes (RFOs)",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x00803c0002 ",
+        "MSRValue": "0x00803C0002",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_HIT.SNOOP_NONE",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "Counts all demand data writes (RFOs) that hit in the L3 with no details on snoop-related information.",
+        "BriefDescription": "Counts all demand data writes (RFOs)",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "Counts all demand data writes (RFOs) that hit in the L3 and sibling core snoops are not needed as either the core-valid bit is not set or the shared line is present in multiple cores. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all demand data writes (RFOs)",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x01003c0002 ",
+        "MSRValue": "0x01003C0002",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_HIT.SNOOP_NOT_NEEDED",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "Counts all demand data writes (RFOs) that hit in the L3 and sibling core snoops are not needed as either the core-valid bit is not set or the shared line is present in multiple cores.",
+        "BriefDescription": "Counts all demand data writes (RFOs)",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "Counts all demand data writes (RFOs) that hit in the L3 with a snoop miss response. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all demand data writes (RFOs)",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x02003c0002 ",
+        "MSRValue": "0x02003C0002",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_HIT.SNOOP_MISS",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "Counts all demand data writes (RFOs) that hit in the L3 with a snoop miss response.",
+        "BriefDescription": "Counts all demand data writes (RFOs)",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "Counts all demand data writes (RFOs) that hit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all demand data writes (RFOs)",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x04003c0002 ",
+        "MSRValue": "0x04003C0002",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_HIT.SNOOP_HIT_NO_FWD",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "Counts all demand data writes (RFOs) that hit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded.",
+        "BriefDescription": "Counts all demand data writes (RFOs)",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all demand data writes (RFOs)",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x10003c0002 ",
+        "MSRValue": "0x10003C0002",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_HIT.SNOOP_HITM",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "DEMAND_RFO & L3_HIT & SNOOP_HITM",
+        "BriefDescription": "Counts all demand data writes (RFOs)",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "Counts all demand data writes (RFOs) that hit in the L3. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all demand data writes (RFOs)",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x3f803c0002 ",
+        "MSRValue": "0x3F803C0002",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_HIT.ANY_SNOOP",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "Counts all demand data writes (RFOs) that hit in the L3.",
+        "BriefDescription": "Counts all demand data writes (RFOs)",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "Counts all demand code reads that have any response type. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all demand code reads have any response type.",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0000010004 ",
+        "MSRValue": "0x0000010004",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.ANY_RESPONSE",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "Counts all demand code reads that have any response type.",
+        "BriefDescription": "Counts all demand code reads have any response type.",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all demand code reads",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0080020004 ",
+        "MSRValue": "0x0080020004",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.SUPPLIER_NONE.SNOOP_NONE",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "DEMAND_CODE_RD & SUPPLIER_NONE & SNOOP_NONE",
+        "BriefDescription": "Counts all demand code reads",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all demand code reads",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0100020004 ",
+        "MSRValue": "0x0100020004",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.SUPPLIER_NONE.SNOOP_NOT_NEEDED",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "DEMAND_CODE_RD & SUPPLIER_NONE & SNOOP_NOT_NEEDED",
+        "BriefDescription": "Counts all demand code reads",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all demand code reads",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0200020004 ",
+        "MSRValue": "0x0200020004",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.SUPPLIER_NONE.SNOOP_MISS",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "DEMAND_CODE_RD & SUPPLIER_NONE & SNOOP_MISS",
+        "BriefDescription": "Counts all demand code reads",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all demand code reads",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0400020004 ",
+        "MSRValue": "0x0400020004",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.SUPPLIER_NONE.SNOOP_HIT_NO_FWD",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "DEMAND_CODE_RD & SUPPLIER_NONE & SNOOP_HIT_NO_FWD",
+        "BriefDescription": "Counts all demand code reads",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all demand code reads",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x1000020004 ",
+        "MSRValue": "0x1000020004",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.SUPPLIER_NONE.SNOOP_HITM",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "DEMAND_CODE_RD & SUPPLIER_NONE & SNOOP_HITM",
+        "BriefDescription": "Counts all demand code reads",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all demand code reads",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x3f80020004 ",
+        "MSRValue": "0x3F80020004",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.SUPPLIER_NONE.ANY_SNOOP",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "DEMAND_CODE_RD & SUPPLIER_NONE & ANY_SNOOP",
+        "BriefDescription": "Counts all demand code reads",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "Counts all demand code reads that hit in the L3 with no details on snoop-related information. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all demand code reads",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x00803c0004 ",
+        "MSRValue": "0x00803C0004",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_HIT.SNOOP_NONE",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "Counts all demand code reads that hit in the L3 with no details on snoop-related information.",
+        "BriefDescription": "Counts all demand code reads",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "Counts all demand code reads that hit in the L3 and sibling core snoops are not needed as either the core-valid bit is not set or the shared line is present in multiple cores. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all demand code reads",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x01003c0004 ",
+        "MSRValue": "0x01003C0004",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_HIT.SNOOP_NOT_NEEDED",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "Counts all demand code reads that hit in the L3 and sibling core snoops are not needed as either the core-valid bit is not set or the shared line is present in multiple cores.",
+        "BriefDescription": "Counts all demand code reads",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "Counts all demand code reads that hit in the L3 with a snoop miss response. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all demand code reads",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x02003c0004 ",
+        "MSRValue": "0x02003C0004",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_HIT.SNOOP_MISS",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "Counts all demand code reads that hit in the L3 with a snoop miss response.",
+        "BriefDescription": "Counts all demand code reads",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "Counts all demand code reads that hit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all demand code reads",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x04003c0004 ",
+        "MSRValue": "0x04003C0004",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_HIT.SNOOP_HIT_NO_FWD",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "Counts all demand code reads that hit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded.",
+        "BriefDescription": "Counts all demand code reads",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all demand code reads",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x10003c0004 ",
+        "MSRValue": "0x10003C0004",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_HIT.SNOOP_HITM",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "DEMAND_CODE_RD & L3_HIT & SNOOP_HITM",
+        "BriefDescription": "Counts all demand code reads",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "Counts all demand code reads that hit in the L3. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all demand code reads",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x3f803c0004 ",
+        "MSRValue": "0x3F803C0004",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_HIT.ANY_SNOOP",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "Counts all demand code reads that hit in the L3.",
+        "BriefDescription": "Counts all demand code reads",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "Counts writebacks (modified to exclusive) that have any response type. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts writebacks (modified to exclusive) have any response type.",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0000010008 ",
+        "MSRValue": "0x0000010008",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.COREWB.ANY_RESPONSE",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "Counts writebacks (modified to exclusive) that have any response type.",
+        "BriefDescription": "Counts writebacks (modified to exclusive) have any response type.",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts writebacks (modified to exclusive)",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0080020008 ",
+        "MSRValue": "0x0080020008",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.COREWB.SUPPLIER_NONE.SNOOP_NONE",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "COREWB & SUPPLIER_NONE & SNOOP_NONE",
+        "BriefDescription": "Counts writebacks (modified to exclusive)",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts writebacks (modified to exclusive)",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0100020008 ",
+        "MSRValue": "0x0100020008",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.COREWB.SUPPLIER_NONE.SNOOP_NOT_NEEDED",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "COREWB & SUPPLIER_NONE & SNOOP_NOT_NEEDED",
+        "BriefDescription": "Counts writebacks (modified to exclusive)",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts writebacks (modified to exclusive)",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0200020008 ",
+        "MSRValue": "0x0200020008",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.COREWB.SUPPLIER_NONE.SNOOP_MISS",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "COREWB & SUPPLIER_NONE & SNOOP_MISS",
+        "BriefDescription": "Counts writebacks (modified to exclusive)",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts writebacks (modified to exclusive)",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0400020008 ",
+        "MSRValue": "0x0400020008",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.COREWB.SUPPLIER_NONE.SNOOP_HIT_NO_FWD",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "COREWB & SUPPLIER_NONE & SNOOP_HIT_NO_FWD",
+        "BriefDescription": "Counts writebacks (modified to exclusive)",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts writebacks (modified to exclusive)",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x1000020008 ",
+        "MSRValue": "0x1000020008",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.COREWB.SUPPLIER_NONE.SNOOP_HITM",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "COREWB & SUPPLIER_NONE & SNOOP_HITM",
+        "BriefDescription": "Counts writebacks (modified to exclusive)",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts writebacks (modified to exclusive)",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x3f80020008 ",
+        "MSRValue": "0x3F80020008",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.COREWB.SUPPLIER_NONE.ANY_SNOOP",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "COREWB & SUPPLIER_NONE & ANY_SNOOP",
+        "BriefDescription": "Counts writebacks (modified to exclusive)",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "Counts writebacks (modified to exclusive) that hit in the L3 with no details on snoop-related information. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts writebacks (modified to exclusive)",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x00803c0008 ",
+        "MSRValue": "0x00803C0008",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.COREWB.L3_HIT.SNOOP_NONE",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "Counts writebacks (modified to exclusive) that hit in the L3 with no details on snoop-related information.",
+        "BriefDescription": "Counts writebacks (modified to exclusive)",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "Counts writebacks (modified to exclusive) that hit in the L3 and sibling core snoops are not needed as either the core-valid bit is not set or the shared line is present in multiple cores. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts writebacks (modified to exclusive)",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x01003c0008 ",
+        "MSRValue": "0x01003C0008",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.COREWB.L3_HIT.SNOOP_NOT_NEEDED",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "Counts writebacks (modified to exclusive) that hit in the L3 and sibling core snoops are not needed as either the core-valid bit is not set or the shared line is present in multiple cores.",
+        "BriefDescription": "Counts writebacks (modified to exclusive)",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "Counts writebacks (modified to exclusive) that hit in the L3 with a snoop miss response. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts writebacks (modified to exclusive)",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x02003c0008 ",
+        "MSRValue": "0x02003C0008",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.COREWB.L3_HIT.SNOOP_MISS",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "Counts writebacks (modified to exclusive) that hit in the L3 with a snoop miss response.",
+        "BriefDescription": "Counts writebacks (modified to exclusive)",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "Counts writebacks (modified to exclusive) that hit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts writebacks (modified to exclusive)",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x04003c0008 ",
+        "MSRValue": "0x04003C0008",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.COREWB.L3_HIT.SNOOP_HIT_NO_FWD",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "Counts writebacks (modified to exclusive) that hit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded.",
+        "BriefDescription": "Counts writebacks (modified to exclusive)",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts writebacks (modified to exclusive)",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x10003c0008 ",
+        "MSRValue": "0x10003C0008",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.COREWB.L3_HIT.SNOOP_HITM",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "COREWB & L3_HIT & SNOOP_HITM",
+        "BriefDescription": "Counts writebacks (modified to exclusive)",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "Counts writebacks (modified to exclusive) that hit in the L3. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts writebacks (modified to exclusive)",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x3f803c0008 ",
+        "MSRValue": "0x3F803C0008",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.COREWB.L3_HIT.ANY_SNOOP",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "Counts writebacks (modified to exclusive) that hit in the L3.",
+        "BriefDescription": "Counts writebacks (modified to exclusive)",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "Counts prefetch (that bring data to L2) data reads that have any response type. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts prefetch (that bring data to L2) data reads have any response type.",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0000010010 ",
+        "MSRValue": "0x0000010010",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.PF_L2_DATA_RD.ANY_RESPONSE",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "Counts prefetch (that bring data to L2) data reads that have any response type.",
+        "BriefDescription": "Counts prefetch (that bring data to L2) data reads have any response type.",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts prefetch (that bring data to L2) data reads",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0080020010 ",
+        "MSRValue": "0x0080020010",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.PF_L2_DATA_RD.SUPPLIER_NONE.SNOOP_NONE",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "PF_L2_DATA_RD & SUPPLIER_NONE & SNOOP_NONE",
+        "BriefDescription": "Counts prefetch (that bring data to L2) data reads",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts prefetch (that bring data to L2) data reads",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0100020010 ",
+        "MSRValue": "0x0100020010",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.PF_L2_DATA_RD.SUPPLIER_NONE.SNOOP_NOT_NEEDED",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "PF_L2_DATA_RD & SUPPLIER_NONE & SNOOP_NOT_NEEDED",
+        "BriefDescription": "Counts prefetch (that bring data to L2) data reads",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts prefetch (that bring data to L2) data reads",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0200020010 ",
+        "MSRValue": "0x0200020010",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.PF_L2_DATA_RD.SUPPLIER_NONE.SNOOP_MISS",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "PF_L2_DATA_RD & SUPPLIER_NONE & SNOOP_MISS",
+        "BriefDescription": "Counts prefetch (that bring data to L2) data reads",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts prefetch (that bring data to L2) data reads",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0400020010 ",
+        "MSRValue": "0x0400020010",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.PF_L2_DATA_RD.SUPPLIER_NONE.SNOOP_HIT_NO_FWD",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "PF_L2_DATA_RD & SUPPLIER_NONE & SNOOP_HIT_NO_FWD",
+        "BriefDescription": "Counts prefetch (that bring data to L2) data reads",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts prefetch (that bring data to L2) data reads",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x1000020010 ",
+        "MSRValue": "0x1000020010",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.PF_L2_DATA_RD.SUPPLIER_NONE.SNOOP_HITM",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "PF_L2_DATA_RD & SUPPLIER_NONE & SNOOP_HITM",
+        "BriefDescription": "Counts prefetch (that bring data to L2) data reads",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts prefetch (that bring data to L2) data reads",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x3f80020010 ",
+        "MSRValue": "0x3F80020010",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.PF_L2_DATA_RD.SUPPLIER_NONE.ANY_SNOOP",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "PF_L2_DATA_RD & SUPPLIER_NONE & ANY_SNOOP",
+        "BriefDescription": "Counts prefetch (that bring data to L2) data reads",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "Counts prefetch (that bring data to L2) data reads that hit in the L3 with no details on snoop-related information. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts prefetch (that bring data to L2) data reads",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x00803c0010 ",
+        "MSRValue": "0x00803C0010",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.PF_L2_DATA_RD.L3_HIT.SNOOP_NONE",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "Counts prefetch (that bring data to L2) data reads that hit in the L3 with no details on snoop-related information.",
+        "BriefDescription": "Counts prefetch (that bring data to L2) data reads",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "Counts prefetch (that bring data to L2) data reads that hit in the L3 and sibling core snoops are not needed as either the core-valid bit is not set or the shared line is present in multiple cores. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts prefetch (that bring data to L2) data reads",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x01003c0010 ",
+        "MSRValue": "0x01003C0010",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.PF_L2_DATA_RD.L3_HIT.SNOOP_NOT_NEEDED",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "Counts prefetch (that bring data to L2) data reads that hit in the L3 and sibling core snoops are not needed as either the core-valid bit is not set or the shared line is present in multiple cores.",
+        "BriefDescription": "Counts prefetch (that bring data to L2) data reads",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "Counts prefetch (that bring data to L2) data reads that hit in the L3 with a snoop miss response. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts prefetch (that bring data to L2) data reads",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x02003c0010 ",
+        "MSRValue": "0x02003C0010",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.PF_L2_DATA_RD.L3_HIT.SNOOP_MISS",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "Counts prefetch (that bring data to L2) data reads that hit in the L3 with a snoop miss response.",
+        "BriefDescription": "Counts prefetch (that bring data to L2) data reads",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "Counts prefetch (that bring data to L2) data reads that hit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts prefetch (that bring data to L2) data reads",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x04003c0010 ",
+        "MSRValue": "0x04003C0010",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.PF_L2_DATA_RD.L3_HIT.SNOOP_HIT_NO_FWD",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "Counts prefetch (that bring data to L2) data reads that hit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded.",
+        "BriefDescription": "Counts prefetch (that bring data to L2) data reads",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts prefetch (that bring data to L2) data reads",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x10003c0010 ",
+        "MSRValue": "0x10003C0010",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.PF_L2_DATA_RD.L3_HIT.SNOOP_HITM",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "PF_L2_DATA_RD & L3_HIT & SNOOP_HITM",
+        "BriefDescription": "Counts prefetch (that bring data to L2) data reads",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "Counts prefetch (that bring data to L2) data reads that hit in the L3. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts prefetch (that bring data to L2) data reads",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x3f803c0010 ",
+        "MSRValue": "0x3F803C0010",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.PF_L2_DATA_RD.L3_HIT.ANY_SNOOP",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "Counts prefetch (that bring data to L2) data reads that hit in the L3.",
+        "BriefDescription": "Counts prefetch (that bring data to L2) data reads",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "Counts all prefetch (that bring data to L2) RFOs that have any response type. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all prefetch (that bring data to L2) RFOs have any response type.",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0000010020 ",
+        "MSRValue": "0x0000010020",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.PF_L2_RFO.ANY_RESPONSE",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "Counts all prefetch (that bring data to L2) RFOs that have any response type.",
+        "BriefDescription": "Counts all prefetch (that bring data to L2) RFOs have any response type.",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all prefetch (that bring data to L2) RFOs",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0080020020 ",
+        "MSRValue": "0x0080020020",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.PF_L2_RFO.SUPPLIER_NONE.SNOOP_NONE",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "PF_L2_RFO & SUPPLIER_NONE & SNOOP_NONE",
+        "BriefDescription": "Counts all prefetch (that bring data to L2) RFOs",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all prefetch (that bring data to L2) RFOs",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0100020020 ",
+        "MSRValue": "0x0100020020",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.PF_L2_RFO.SUPPLIER_NONE.SNOOP_NOT_NEEDED",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "PF_L2_RFO & SUPPLIER_NONE & SNOOP_NOT_NEEDED",
+        "BriefDescription": "Counts all prefetch (that bring data to L2) RFOs",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all prefetch (that bring data to L2) RFOs",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0200020020 ",
+        "MSRValue": "0x0200020020",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.PF_L2_RFO.SUPPLIER_NONE.SNOOP_MISS",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "PF_L2_RFO & SUPPLIER_NONE & SNOOP_MISS",
+        "BriefDescription": "Counts all prefetch (that bring data to L2) RFOs",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all prefetch (that bring data to L2) RFOs",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0400020020 ",
+        "MSRValue": "0x0400020020",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.PF_L2_RFO.SUPPLIER_NONE.SNOOP_HIT_NO_FWD",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "PF_L2_RFO & SUPPLIER_NONE & SNOOP_HIT_NO_FWD",
+        "BriefDescription": "Counts all prefetch (that bring data to L2) RFOs",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all prefetch (that bring data to L2) RFOs",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x1000020020 ",
+        "MSRValue": "0x1000020020",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.PF_L2_RFO.SUPPLIER_NONE.SNOOP_HITM",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "PF_L2_RFO & SUPPLIER_NONE & SNOOP_HITM",
+        "BriefDescription": "Counts all prefetch (that bring data to L2) RFOs",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all prefetch (that bring data to L2) RFOs",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x3f80020020 ",
+        "MSRValue": "0x3F80020020",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.PF_L2_RFO.SUPPLIER_NONE.ANY_SNOOP",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "PF_L2_RFO & SUPPLIER_NONE & ANY_SNOOP",
+        "BriefDescription": "Counts all prefetch (that bring data to L2) RFOs",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "Counts all prefetch (that bring data to L2) RFOs that hit in the L3 with no details on snoop-related information. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all prefetch (that bring data to L2) RFOs",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x00803c0020 ",
+        "MSRValue": "0x00803C0020",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.PF_L2_RFO.L3_HIT.SNOOP_NONE",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "Counts all prefetch (that bring data to L2) RFOs that hit in the L3 with no details on snoop-related information.",
+        "BriefDescription": "Counts all prefetch (that bring data to L2) RFOs",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "Counts all prefetch (that bring data to L2) RFOs that hit in the L3 and sibling core snoops are not needed as either the core-valid bit is not set or the shared line is present in multiple cores. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all prefetch (that bring data to L2) RFOs",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x01003c0020 ",
+        "MSRValue": "0x01003C0020",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.PF_L2_RFO.L3_HIT.SNOOP_NOT_NEEDED",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "Counts all prefetch (that bring data to L2) RFOs that hit in the L3 and sibling core snoops are not needed as either the core-valid bit is not set or the shared line is present in multiple cores.",
+        "BriefDescription": "Counts all prefetch (that bring data to L2) RFOs",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "Counts all prefetch (that bring data to L2) RFOs that hit in the L3 with a snoop miss response. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all prefetch (that bring data to L2) RFOs",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x02003c0020 ",
+        "MSRValue": "0x02003C0020",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.PF_L2_RFO.L3_HIT.SNOOP_MISS",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "Counts all prefetch (that bring data to L2) RFOs that hit in the L3 with a snoop miss response.",
+        "BriefDescription": "Counts all prefetch (that bring data to L2) RFOs",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "Counts all prefetch (that bring data to L2) RFOs that hit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all prefetch (that bring data to L2) RFOs",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x04003c0020 ",
+        "MSRValue": "0x04003C0020",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.PF_L2_RFO.L3_HIT.SNOOP_HIT_NO_FWD",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "Counts all prefetch (that bring data to L2) RFOs that hit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded.",
+        "BriefDescription": "Counts all prefetch (that bring data to L2) RFOs",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all prefetch (that bring data to L2) RFOs",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x10003c0020 ",
+        "MSRValue": "0x10003C0020",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.PF_L2_RFO.L3_HIT.SNOOP_HITM",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "PF_L2_RFO & L3_HIT & SNOOP_HITM",
+        "BriefDescription": "Counts all prefetch (that bring data to L2) RFOs",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "Counts all prefetch (that bring data to L2) RFOs that hit in the L3. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all prefetch (that bring data to L2) RFOs",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x3f803c0020 ",
+        "MSRValue": "0x3F803C0020",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.PF_L2_RFO.L3_HIT.ANY_SNOOP",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "Counts all prefetch (that bring data to L2) RFOs that hit in the L3.",
+        "BriefDescription": "Counts all prefetch (that bring data to L2) RFOs",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "Counts all prefetch (that bring data to LLC only) code reads that have any response type. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all prefetch (that bring data to LLC only) code reads have any response type.",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0000010040 ",
+        "MSRValue": "0x0000010040",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.PF_L2_CODE_RD.ANY_RESPONSE",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "Counts all prefetch (that bring data to LLC only) code reads that have any response type.",
+        "BriefDescription": "Counts all prefetch (that bring data to LLC only) code reads have any response type.",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all prefetch (that bring data to LLC only) code reads",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0080020040 ",
+        "MSRValue": "0x0080020040",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.PF_L2_CODE_RD.SUPPLIER_NONE.SNOOP_NONE",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "PF_L2_CODE_RD & SUPPLIER_NONE & SNOOP_NONE",
+        "BriefDescription": "Counts all prefetch (that bring data to LLC only) code reads",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all prefetch (that bring data to LLC only) code reads",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0100020040 ",
+        "MSRValue": "0x0100020040",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.PF_L2_CODE_RD.SUPPLIER_NONE.SNOOP_NOT_NEEDED",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "PF_L2_CODE_RD & SUPPLIER_NONE & SNOOP_NOT_NEEDED",
+        "BriefDescription": "Counts all prefetch (that bring data to LLC only) code reads",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all prefetch (that bring data to LLC only) code reads",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0200020040 ",
+        "MSRValue": "0x0200020040",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.PF_L2_CODE_RD.SUPPLIER_NONE.SNOOP_MISS",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "PF_L2_CODE_RD & SUPPLIER_NONE & SNOOP_MISS",
+        "BriefDescription": "Counts all prefetch (that bring data to LLC only) code reads",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all prefetch (that bring data to LLC only) code reads",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0400020040 ",
+        "MSRValue": "0x0400020040",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.PF_L2_CODE_RD.SUPPLIER_NONE.SNOOP_HIT_NO_FWD",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "PF_L2_CODE_RD & SUPPLIER_NONE & SNOOP_HIT_NO_FWD",
+        "BriefDescription": "Counts all prefetch (that bring data to LLC only) code reads",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all prefetch (that bring data to LLC only) code reads",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x1000020040 ",
+        "MSRValue": "0x1000020040",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.PF_L2_CODE_RD.SUPPLIER_NONE.SNOOP_HITM",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "PF_L2_CODE_RD & SUPPLIER_NONE & SNOOP_HITM",
+        "BriefDescription": "Counts all prefetch (that bring data to LLC only) code reads",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all prefetch (that bring data to LLC only) code reads",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x3f80020040 ",
+        "MSRValue": "0x3F80020040",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.PF_L2_CODE_RD.SUPPLIER_NONE.ANY_SNOOP",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "PF_L2_CODE_RD & SUPPLIER_NONE & ANY_SNOOP",
+        "BriefDescription": "Counts all prefetch (that bring data to LLC only) code reads",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "Counts all prefetch (that bring data to LLC only) code reads that hit in the L3 with no details on snoop-related information. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all prefetch (that bring data to LLC only) code reads",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x00803c0040 ",
+        "MSRValue": "0x00803C0040",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.PF_L2_CODE_RD.L3_HIT.SNOOP_NONE",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "Counts all prefetch (that bring data to LLC only) code reads that hit in the L3 with no details on snoop-related information.",
+        "BriefDescription": "Counts all prefetch (that bring data to LLC only) code reads",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "Counts all prefetch (that bring data to LLC only) code reads that hit in the L3 and sibling core snoops are not needed as either the core-valid bit is not set or the shared line is present in multiple cores. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all prefetch (that bring data to LLC only) code reads",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x01003c0040 ",
+        "MSRValue": "0x01003C0040",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.PF_L2_CODE_RD.L3_HIT.SNOOP_NOT_NEEDED",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "Counts all prefetch (that bring data to LLC only) code reads that hit in the L3 and sibling core snoops are not needed as either the core-valid bit is not set or the shared line is present in multiple cores.",
+        "BriefDescription": "Counts all prefetch (that bring data to LLC only) code reads",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "Counts all prefetch (that bring data to LLC only) code reads that hit in the L3 with a snoop miss response. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all prefetch (that bring data to LLC only) code reads",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x02003c0040 ",
+        "MSRValue": "0x02003C0040",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.PF_L2_CODE_RD.L3_HIT.SNOOP_MISS",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "Counts all prefetch (that bring data to LLC only) code reads that hit in the L3 with a snoop miss response.",
+        "BriefDescription": "Counts all prefetch (that bring data to LLC only) code reads",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "Counts all prefetch (that bring data to LLC only) code reads that hit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all prefetch (that bring data to LLC only) code reads",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x04003c0040 ",
+        "MSRValue": "0x04003C0040",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.PF_L2_CODE_RD.L3_HIT.SNOOP_HIT_NO_FWD",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "Counts all prefetch (that bring data to LLC only) code reads that hit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded.",
+        "BriefDescription": "Counts all prefetch (that bring data to LLC only) code reads",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all prefetch (that bring data to LLC only) code reads",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x10003c0040 ",
+        "MSRValue": "0x10003C0040",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.PF_L2_CODE_RD.L3_HIT.SNOOP_HITM",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "PF_L2_CODE_RD & L3_HIT & SNOOP_HITM",
+        "BriefDescription": "Counts all prefetch (that bring data to LLC only) code reads",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "Counts all prefetch (that bring data to LLC only) code reads that hit in the L3. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all prefetch (that bring data to LLC only) code reads",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x3f803c0040 ",
+        "MSRValue": "0x3F803C0040",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.PF_L2_CODE_RD.L3_HIT.ANY_SNOOP",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "Counts all prefetch (that bring data to LLC only) code reads that hit in the L3.",
+        "BriefDescription": "Counts all prefetch (that bring data to LLC only) code reads",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "Counts all prefetch (that bring data to LLC only) data reads that have any response type. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all prefetch (that bring data to LLC only) data reads have any response type.",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0000010080 ",
+        "MSRValue": "0x0000010080",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.PF_L3_DATA_RD.ANY_RESPONSE",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "Counts all prefetch (that bring data to LLC only) data reads that have any response type.",
+        "BriefDescription": "Counts all prefetch (that bring data to LLC only) data reads have any response type.",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all prefetch (that bring data to LLC only) data reads",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0080020080 ",
+        "MSRValue": "0x0080020080",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.PF_L3_DATA_RD.SUPPLIER_NONE.SNOOP_NONE",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "PF_L3_DATA_RD & SUPPLIER_NONE & SNOOP_NONE",
+        "BriefDescription": "Counts all prefetch (that bring data to LLC only) data reads",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all prefetch (that bring data to LLC only) data reads",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0100020080 ",
+        "MSRValue": "0x0100020080",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.PF_L3_DATA_RD.SUPPLIER_NONE.SNOOP_NOT_NEEDED",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "PF_L3_DATA_RD & SUPPLIER_NONE & SNOOP_NOT_NEEDED",
+        "BriefDescription": "Counts all prefetch (that bring data to LLC only) data reads",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all prefetch (that bring data to LLC only) data reads",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0200020080 ",
+        "MSRValue": "0x0200020080",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.PF_L3_DATA_RD.SUPPLIER_NONE.SNOOP_MISS",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "PF_L3_DATA_RD & SUPPLIER_NONE & SNOOP_MISS",
+        "BriefDescription": "Counts all prefetch (that bring data to LLC only) data reads",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all prefetch (that bring data to LLC only) data reads",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0400020080 ",
+        "MSRValue": "0x0400020080",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.PF_L3_DATA_RD.SUPPLIER_NONE.SNOOP_HIT_NO_FWD",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "PF_L3_DATA_RD & SUPPLIER_NONE & SNOOP_HIT_NO_FWD",
+        "BriefDescription": "Counts all prefetch (that bring data to LLC only) data reads",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all prefetch (that bring data to LLC only) data reads",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x1000020080 ",
+        "MSRValue": "0x1000020080",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.PF_L3_DATA_RD.SUPPLIER_NONE.SNOOP_HITM",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "PF_L3_DATA_RD & SUPPLIER_NONE & SNOOP_HITM",
+        "BriefDescription": "Counts all prefetch (that bring data to LLC only) data reads",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all prefetch (that bring data to LLC only) data reads",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x3f80020080 ",
+        "MSRValue": "0x3F80020080",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.PF_L3_DATA_RD.SUPPLIER_NONE.ANY_SNOOP",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "PF_L3_DATA_RD & SUPPLIER_NONE & ANY_SNOOP",
+        "BriefDescription": "Counts all prefetch (that bring data to LLC only) data reads",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "Counts all prefetch (that bring data to LLC only) data reads that hit in the L3 with no details on snoop-related information. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all prefetch (that bring data to LLC only) data reads",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x00803c0080 ",
+        "MSRValue": "0x00803C0080",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.PF_L3_DATA_RD.L3_HIT.SNOOP_NONE",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "Counts all prefetch (that bring data to LLC only) data reads that hit in the L3 with no details on snoop-related information.",
+        "BriefDescription": "Counts all prefetch (that bring data to LLC only) data reads",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "Counts all prefetch (that bring data to LLC only) data reads that hit in the L3 and sibling core snoops are not needed as either the core-valid bit is not set or the shared line is present in multiple cores. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all prefetch (that bring data to LLC only) data reads",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x01003c0080 ",
+        "MSRValue": "0x01003C0080",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.PF_L3_DATA_RD.L3_HIT.SNOOP_NOT_NEEDED",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "Counts all prefetch (that bring data to LLC only) data reads that hit in the L3 and sibling core snoops are not needed as either the core-valid bit is not set or the shared line is present in multiple cores.",
+        "BriefDescription": "Counts all prefetch (that bring data to LLC only) data reads",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "Counts all prefetch (that bring data to LLC only) data reads that hit in the L3 with a snoop miss response. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all prefetch (that bring data to LLC only) data reads",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x02003c0080 ",
+        "MSRValue": "0x02003C0080",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.PF_L3_DATA_RD.L3_HIT.SNOOP_MISS",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "Counts all prefetch (that bring data to LLC only) data reads that hit in the L3 with a snoop miss response.",
+        "BriefDescription": "Counts all prefetch (that bring data to LLC only) data reads",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "Counts all prefetch (that bring data to LLC only) data reads that hit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all prefetch (that bring data to LLC only) data reads",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x04003c0080 ",
+        "MSRValue": "0x04003C0080",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.PF_L3_DATA_RD.L3_HIT.SNOOP_HIT_NO_FWD",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "Counts all prefetch (that bring data to LLC only) data reads that hit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded.",
+        "BriefDescription": "Counts all prefetch (that bring data to LLC only) data reads",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all prefetch (that bring data to LLC only) data reads",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x10003c0080 ",
+        "MSRValue": "0x10003C0080",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.PF_L3_DATA_RD.L3_HIT.SNOOP_HITM",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "PF_L3_DATA_RD & L3_HIT & SNOOP_HITM",
+        "BriefDescription": "Counts all prefetch (that bring data to LLC only) data reads",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "Counts all prefetch (that bring data to LLC only) data reads that hit in the L3. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all prefetch (that bring data to LLC only) data reads",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x3f803c0080 ",
+        "MSRValue": "0x3F803C0080",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.PF_L3_DATA_RD.L3_HIT.ANY_SNOOP",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "Counts all prefetch (that bring data to LLC only) data reads that hit in the L3.",
+        "BriefDescription": "Counts all prefetch (that bring data to LLC only) data reads",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "Counts all prefetch (that bring data to LLC only) RFOs that have any response type. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all prefetch (that bring data to LLC only) RFOs have any response type.",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0000010100 ",
+        "MSRValue": "0x0000010100",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.PF_L3_RFO.ANY_RESPONSE",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "Counts all prefetch (that bring data to LLC only) RFOs that have any response type.",
+        "BriefDescription": "Counts all prefetch (that bring data to LLC only) RFOs have any response type.",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all prefetch (that bring data to LLC only) RFOs",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0080020100 ",
+        "MSRValue": "0x0080020100",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.PF_L3_RFO.SUPPLIER_NONE.SNOOP_NONE",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "PF_L3_RFO & SUPPLIER_NONE & SNOOP_NONE",
+        "BriefDescription": "Counts all prefetch (that bring data to LLC only) RFOs",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all prefetch (that bring data to LLC only) RFOs",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0100020100 ",
+        "MSRValue": "0x0100020100",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.PF_L3_RFO.SUPPLIER_NONE.SNOOP_NOT_NEEDED",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "PF_L3_RFO & SUPPLIER_NONE & SNOOP_NOT_NEEDED",
+        "BriefDescription": "Counts all prefetch (that bring data to LLC only) RFOs",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all prefetch (that bring data to LLC only) RFOs",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0200020100 ",
+        "MSRValue": "0x0200020100",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.PF_L3_RFO.SUPPLIER_NONE.SNOOP_MISS",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "PF_L3_RFO & SUPPLIER_NONE & SNOOP_MISS",
+        "BriefDescription": "Counts all prefetch (that bring data to LLC only) RFOs",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all prefetch (that bring data to LLC only) RFOs",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0400020100 ",
+        "MSRValue": "0x0400020100",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.PF_L3_RFO.SUPPLIER_NONE.SNOOP_HIT_NO_FWD",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "PF_L3_RFO & SUPPLIER_NONE & SNOOP_HIT_NO_FWD",
+        "BriefDescription": "Counts all prefetch (that bring data to LLC only) RFOs",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all prefetch (that bring data to LLC only) RFOs",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x1000020100 ",
+        "MSRValue": "0x1000020100",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.PF_L3_RFO.SUPPLIER_NONE.SNOOP_HITM",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "PF_L3_RFO & SUPPLIER_NONE & SNOOP_HITM",
+        "BriefDescription": "Counts all prefetch (that bring data to LLC only) RFOs",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all prefetch (that bring data to LLC only) RFOs",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x3f80020100 ",
+        "MSRValue": "0x3F80020100",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.PF_L3_RFO.SUPPLIER_NONE.ANY_SNOOP",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "PF_L3_RFO & SUPPLIER_NONE & ANY_SNOOP",
+        "BriefDescription": "Counts all prefetch (that bring data to LLC only) RFOs",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "Counts all prefetch (that bring data to LLC only) RFOs that hit in the L3 with no details on snoop-related information. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all prefetch (that bring data to LLC only) RFOs",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x00803c0100 ",
+        "MSRValue": "0x00803C0100",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.PF_L3_RFO.L3_HIT.SNOOP_NONE",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "Counts all prefetch (that bring data to LLC only) RFOs that hit in the L3 with no details on snoop-related information.",
+        "BriefDescription": "Counts all prefetch (that bring data to LLC only) RFOs",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "Counts all prefetch (that bring data to LLC only) RFOs that hit in the L3 and sibling core snoops are not needed as either the core-valid bit is not set or the shared line is present in multiple cores. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all prefetch (that bring data to LLC only) RFOs",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x01003c0100 ",
+        "MSRValue": "0x01003C0100",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.PF_L3_RFO.L3_HIT.SNOOP_NOT_NEEDED",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "Counts all prefetch (that bring data to LLC only) RFOs that hit in the L3 and sibling core snoops are not needed as either the core-valid bit is not set or the shared line is present in multiple cores.",
+        "BriefDescription": "Counts all prefetch (that bring data to LLC only) RFOs",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "Counts all prefetch (that bring data to LLC only) RFOs that hit in the L3 with a snoop miss response. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all prefetch (that bring data to LLC only) RFOs",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x02003c0100 ",
+        "MSRValue": "0x02003C0100",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.PF_L3_RFO.L3_HIT.SNOOP_MISS",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "Counts all prefetch (that bring data to LLC only) RFOs that hit in the L3 with a snoop miss response.",
+        "BriefDescription": "Counts all prefetch (that bring data to LLC only) RFOs",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "Counts all prefetch (that bring data to LLC only) RFOs that hit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all prefetch (that bring data to LLC only) RFOs",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x04003c0100 ",
+        "MSRValue": "0x04003C0100",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.PF_L3_RFO.L3_HIT.SNOOP_HIT_NO_FWD",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "Counts all prefetch (that bring data to LLC only) RFOs that hit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded.",
+        "BriefDescription": "Counts all prefetch (that bring data to LLC only) RFOs",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all prefetch (that bring data to LLC only) RFOs",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x10003c0100 ",
+        "MSRValue": "0x10003C0100",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.PF_L3_RFO.L3_HIT.SNOOP_HITM",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "PF_L3_RFO & L3_HIT & SNOOP_HITM",
+        "BriefDescription": "Counts all prefetch (that bring data to LLC only) RFOs",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "Counts all prefetch (that bring data to LLC only) RFOs that hit in the L3. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all prefetch (that bring data to LLC only) RFOs",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x3f803c0100 ",
+        "MSRValue": "0x3F803C0100",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.PF_L3_RFO.L3_HIT.ANY_SNOOP",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "Counts all prefetch (that bring data to LLC only) RFOs that hit in the L3.",
+        "BriefDescription": "Counts all prefetch (that bring data to LLC only) RFOs",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "Counts prefetch (that bring data to LLC only) code reads that have any response type. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts prefetch (that bring data to LLC only) code reads have any response type.",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0000010200 ",
+        "MSRValue": "0x0000010200",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.PF_L3_CODE_RD.ANY_RESPONSE",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "Counts prefetch (that bring data to LLC only) code reads that have any response type.",
+        "BriefDescription": "Counts prefetch (that bring data to LLC only) code reads have any response type.",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts prefetch (that bring data to LLC only) code reads",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0080020200 ",
+        "MSRValue": "0x0080020200",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.PF_L3_CODE_RD.SUPPLIER_NONE.SNOOP_NONE",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "PF_L3_CODE_RD & SUPPLIER_NONE & SNOOP_NONE",
+        "BriefDescription": "Counts prefetch (that bring data to LLC only) code reads",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts prefetch (that bring data to LLC only) code reads",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0100020200 ",
+        "MSRValue": "0x0100020200",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.PF_L3_CODE_RD.SUPPLIER_NONE.SNOOP_NOT_NEEDED",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "PF_L3_CODE_RD & SUPPLIER_NONE & SNOOP_NOT_NEEDED",
+        "BriefDescription": "Counts prefetch (that bring data to LLC only) code reads",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts prefetch (that bring data to LLC only) code reads",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0200020200 ",
+        "MSRValue": "0x0200020200",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.PF_L3_CODE_RD.SUPPLIER_NONE.SNOOP_MISS",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "PF_L3_CODE_RD & SUPPLIER_NONE & SNOOP_MISS",
+        "BriefDescription": "Counts prefetch (that bring data to LLC only) code reads",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts prefetch (that bring data to LLC only) code reads",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0400020200 ",
+        "MSRValue": "0x0400020200",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.PF_L3_CODE_RD.SUPPLIER_NONE.SNOOP_HIT_NO_FWD",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "PF_L3_CODE_RD & SUPPLIER_NONE & SNOOP_HIT_NO_FWD",
+        "BriefDescription": "Counts prefetch (that bring data to LLC only) code reads",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts prefetch (that bring data to LLC only) code reads",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x1000020200 ",
+        "MSRValue": "0x1000020200",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.PF_L3_CODE_RD.SUPPLIER_NONE.SNOOP_HITM",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "PF_L3_CODE_RD & SUPPLIER_NONE & SNOOP_HITM",
+        "BriefDescription": "Counts prefetch (that bring data to LLC only) code reads",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts prefetch (that bring data to LLC only) code reads",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x3f80020200 ",
+        "MSRValue": "0x3F80020200",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.PF_L3_CODE_RD.SUPPLIER_NONE.ANY_SNOOP",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "PF_L3_CODE_RD & SUPPLIER_NONE & ANY_SNOOP",
+        "BriefDescription": "Counts prefetch (that bring data to LLC only) code reads",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "Counts prefetch (that bring data to LLC only) code reads that hit in the L3 with no details on snoop-related information. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts prefetch (that bring data to LLC only) code reads",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x00803c0200 ",
+        "MSRValue": "0x00803C0200",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.PF_L3_CODE_RD.L3_HIT.SNOOP_NONE",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "Counts prefetch (that bring data to LLC only) code reads that hit in the L3 with no details on snoop-related information.",
+        "BriefDescription": "Counts prefetch (that bring data to LLC only) code reads",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "Counts prefetch (that bring data to LLC only) code reads that hit in the L3 and sibling core snoops are not needed as either the core-valid bit is not set or the shared line is present in multiple cores. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts prefetch (that bring data to LLC only) code reads",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x01003c0200 ",
+        "MSRValue": "0x01003C0200",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.PF_L3_CODE_RD.L3_HIT.SNOOP_NOT_NEEDED",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "Counts prefetch (that bring data to LLC only) code reads that hit in the L3 and sibling core snoops are not needed as either the core-valid bit is not set or the shared line is present in multiple cores.",
+        "BriefDescription": "Counts prefetch (that bring data to LLC only) code reads",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "Counts prefetch (that bring data to LLC only) code reads that hit in the L3 with a snoop miss response. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts prefetch (that bring data to LLC only) code reads",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x02003c0200 ",
+        "MSRValue": "0x02003C0200",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.PF_L3_CODE_RD.L3_HIT.SNOOP_MISS",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "Counts prefetch (that bring data to LLC only) code reads that hit in the L3 with a snoop miss response.",
+        "BriefDescription": "Counts prefetch (that bring data to LLC only) code reads",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "Counts prefetch (that bring data to LLC only) code reads that hit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts prefetch (that bring data to LLC only) code reads",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x04003c0200 ",
+        "MSRValue": "0x04003C0200",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.PF_L3_CODE_RD.L3_HIT.SNOOP_HIT_NO_FWD",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "Counts prefetch (that bring data to LLC only) code reads that hit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded.",
+        "BriefDescription": "Counts prefetch (that bring data to LLC only) code reads",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts prefetch (that bring data to LLC only) code reads",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x10003c0200 ",
+        "MSRValue": "0x10003C0200",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.PF_L3_CODE_RD.L3_HIT.SNOOP_HITM",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "PF_L3_CODE_RD & L3_HIT & SNOOP_HITM",
+        "BriefDescription": "Counts prefetch (that bring data to LLC only) code reads",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "Counts prefetch (that bring data to LLC only) code reads that hit in the L3. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts prefetch (that bring data to LLC only) code reads",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x3f803c0200 ",
+        "MSRValue": "0x3F803C0200",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.PF_L3_CODE_RD.L3_HIT.ANY_SNOOP",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "Counts prefetch (that bring data to LLC only) code reads that hit in the L3.",
+        "BriefDescription": "Counts prefetch (that bring data to LLC only) code reads",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "Counts any other requests that have any response type. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts any other requests have any response type.",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0000018000 ",
+        "MSRValue": "0x0000018000",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.OTHER.ANY_RESPONSE",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "Counts any other requests that have any response type.",
+        "BriefDescription": "Counts any other requests have any response type.",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts any other requests",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0080028000 ",
+        "MSRValue": "0x0080028000",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.OTHER.SUPPLIER_NONE.SNOOP_NONE",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "OTHER & SUPPLIER_NONE & SNOOP_NONE",
+        "BriefDescription": "Counts any other requests",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts any other requests",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0100028000 ",
+        "MSRValue": "0x0100028000",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.OTHER.SUPPLIER_NONE.SNOOP_NOT_NEEDED",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "OTHER & SUPPLIER_NONE & SNOOP_NOT_NEEDED",
+        "BriefDescription": "Counts any other requests",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts any other requests",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0200028000 ",
+        "MSRValue": "0x0200028000",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.OTHER.SUPPLIER_NONE.SNOOP_MISS",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "OTHER & SUPPLIER_NONE & SNOOP_MISS",
+        "BriefDescription": "Counts any other requests",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts any other requests",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0400028000 ",
+        "MSRValue": "0x0400028000",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.OTHER.SUPPLIER_NONE.SNOOP_HIT_NO_FWD",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "OTHER & SUPPLIER_NONE & SNOOP_HIT_NO_FWD",
+        "BriefDescription": "Counts any other requests",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts any other requests",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x1000028000 ",
+        "MSRValue": "0x1000028000",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.OTHER.SUPPLIER_NONE.SNOOP_HITM",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "OTHER & SUPPLIER_NONE & SNOOP_HITM",
+        "BriefDescription": "Counts any other requests",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts any other requests",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x3f80028000 ",
+        "MSRValue": "0x3F80028000",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.OTHER.SUPPLIER_NONE.ANY_SNOOP",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "OTHER & SUPPLIER_NONE & ANY_SNOOP",
+        "BriefDescription": "Counts any other requests",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "Counts any other requests that hit in the L3 with no details on snoop-related information. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts any other requests",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x00803c8000 ",
+        "MSRValue": "0x00803C8000",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.OTHER.L3_HIT.SNOOP_NONE",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "Counts any other requests that hit in the L3 with no details on snoop-related information.",
+        "BriefDescription": "Counts any other requests",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "Counts any other requests that hit in the L3 and sibling core snoops are not needed as either the core-valid bit is not set or the shared line is present in multiple cores. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts any other requests",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x01003c8000 ",
+        "MSRValue": "0x01003C8000",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.OTHER.L3_HIT.SNOOP_NOT_NEEDED",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "Counts any other requests that hit in the L3 and sibling core snoops are not needed as either the core-valid bit is not set or the shared line is present in multiple cores.",
+        "BriefDescription": "Counts any other requests",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "Counts any other requests that hit in the L3 with a snoop miss response. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts any other requests",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x02003c8000 ",
+        "MSRValue": "0x02003C8000",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.OTHER.L3_HIT.SNOOP_MISS",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "Counts any other requests that hit in the L3 with a snoop miss response.",
+        "BriefDescription": "Counts any other requests",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "Counts any other requests that hit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts any other requests",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x04003c8000 ",
+        "MSRValue": "0x04003C8000",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.OTHER.L3_HIT.SNOOP_HIT_NO_FWD",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "Counts any other requests that hit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded.",
+        "BriefDescription": "Counts any other requests",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts any other requests",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x10003c8000 ",
+        "MSRValue": "0x10003C8000",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.OTHER.L3_HIT.SNOOP_HITM",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "OTHER & L3_HIT & SNOOP_HITM",
+        "BriefDescription": "Counts any other requests",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "Counts any other requests that hit in the L3. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts any other requests",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x3f803c8000 ",
+        "MSRValue": "0x3F803C8000",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.OTHER.L3_HIT.ANY_SNOOP",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "Counts any other requests that hit in the L3.",
+        "BriefDescription": "Counts any other requests",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "Counts all prefetch data reads that have any response type. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all prefetch data reads have any response type.",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0000010090 ",
+        "MSRValue": "0x0000010090",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.ALL_PF_DATA_RD.ANY_RESPONSE",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "Counts all prefetch data reads that have any response type.",
+        "BriefDescription": "Counts all prefetch data reads have any response type.",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all prefetch data reads",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0080020090 ",
+        "MSRValue": "0x0080020090",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.ALL_PF_DATA_RD.SUPPLIER_NONE.SNOOP_NONE",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "ALL_PF_DATA_RD & SUPPLIER_NONE & SNOOP_NONE",
+        "BriefDescription": "Counts all prefetch data reads",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all prefetch data reads",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0100020090 ",
+        "MSRValue": "0x0100020090",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.ALL_PF_DATA_RD.SUPPLIER_NONE.SNOOP_NOT_NEEDED",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "ALL_PF_DATA_RD & SUPPLIER_NONE & SNOOP_NOT_NEEDED",
+        "BriefDescription": "Counts all prefetch data reads",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all prefetch data reads",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0200020090 ",
+        "MSRValue": "0x0200020090",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.ALL_PF_DATA_RD.SUPPLIER_NONE.SNOOP_MISS",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "ALL_PF_DATA_RD & SUPPLIER_NONE & SNOOP_MISS",
+        "BriefDescription": "Counts all prefetch data reads",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all prefetch data reads",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0400020090 ",
+        "MSRValue": "0x0400020090",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.ALL_PF_DATA_RD.SUPPLIER_NONE.SNOOP_HIT_NO_FWD",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "ALL_PF_DATA_RD & SUPPLIER_NONE & SNOOP_HIT_NO_FWD",
+        "BriefDescription": "Counts all prefetch data reads",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all prefetch data reads",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x1000020090 ",
+        "MSRValue": "0x1000020090",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.ALL_PF_DATA_RD.SUPPLIER_NONE.SNOOP_HITM",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "ALL_PF_DATA_RD & SUPPLIER_NONE & SNOOP_HITM",
+        "BriefDescription": "Counts all prefetch data reads",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all prefetch data reads",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x3f80020090 ",
+        "MSRValue": "0x3F80020090",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.ALL_PF_DATA_RD.SUPPLIER_NONE.ANY_SNOOP",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "ALL_PF_DATA_RD & SUPPLIER_NONE & ANY_SNOOP",
+        "BriefDescription": "Counts all prefetch data reads",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "Counts all prefetch data reads that hit in the L3 with no details on snoop-related information. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all prefetch data reads",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x00803c0090 ",
+        "MSRValue": "0x00803C0090",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.ALL_PF_DATA_RD.L3_HIT.SNOOP_NONE",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "Counts all prefetch data reads that hit in the L3 with no details on snoop-related information.",
+        "BriefDescription": "Counts all prefetch data reads",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "Counts all prefetch data reads that hit in the L3 and sibling core snoops are not needed as either the core-valid bit is not set or the shared line is present in multiple cores. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all prefetch data reads",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x01003c0090 ",
+        "MSRValue": "0x01003C0090",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.ALL_PF_DATA_RD.L3_HIT.SNOOP_NOT_NEEDED",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "Counts all prefetch data reads that hit in the L3 and sibling core snoops are not needed as either the core-valid bit is not set or the shared line is present in multiple cores.",
+        "BriefDescription": "Counts all prefetch data reads",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "Counts all prefetch data reads that hit in the L3 with a snoop miss response. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all prefetch data reads",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x02003c0090 ",
+        "MSRValue": "0x02003C0090",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.ALL_PF_DATA_RD.L3_HIT.SNOOP_MISS",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "Counts all prefetch data reads that hit in the L3 with a snoop miss response.",
+        "BriefDescription": "Counts all prefetch data reads",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "Counts all prefetch data reads that hit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all prefetch data reads",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x04003c0090 ",
+        "MSRValue": "0x04003C0090",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.ALL_PF_DATA_RD.L3_HIT.SNOOP_HIT_NO_FWD",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "Counts all prefetch data reads that hit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded.",
+        "BriefDescription": "Counts all prefetch data reads",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all prefetch data reads",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x10003c0090 ",
+        "MSRValue": "0x10003C0090",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.ALL_PF_DATA_RD.L3_HIT.SNOOP_HITM",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "ALL_PF_DATA_RD & L3_HIT & SNOOP_HITM",
+        "BriefDescription": "Counts all prefetch data reads",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "Counts all prefetch data reads that hit in the L3. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all prefetch data reads",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x3f803c0090 ",
+        "MSRValue": "0x3F803C0090",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.ALL_PF_DATA_RD.L3_HIT.ANY_SNOOP",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "Counts all prefetch data reads that hit in the L3.",
+        "BriefDescription": "Counts all prefetch data reads",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "Counts prefetch RFOs that have any response type. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts prefetch RFOs have any response type.",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0000010120 ",
+        "MSRValue": "0x0000010120",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.ALL_PF_RFO.ANY_RESPONSE",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "Counts prefetch RFOs that have any response type.",
+        "BriefDescription": "Counts prefetch RFOs have any response type.",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts prefetch RFOs",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0080020120 ",
+        "MSRValue": "0x0080020120",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.ALL_PF_RFO.SUPPLIER_NONE.SNOOP_NONE",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "ALL_PF_RFO & SUPPLIER_NONE & SNOOP_NONE",
+        "BriefDescription": "Counts prefetch RFOs",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts prefetch RFOs",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0100020120 ",
+        "MSRValue": "0x0100020120",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.ALL_PF_RFO.SUPPLIER_NONE.SNOOP_NOT_NEEDED",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "ALL_PF_RFO & SUPPLIER_NONE & SNOOP_NOT_NEEDED",
+        "BriefDescription": "Counts prefetch RFOs",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts prefetch RFOs",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0200020120 ",
+        "MSRValue": "0x0200020120",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.ALL_PF_RFO.SUPPLIER_NONE.SNOOP_MISS",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "ALL_PF_RFO & SUPPLIER_NONE & SNOOP_MISS",
+        "BriefDescription": "Counts prefetch RFOs",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts prefetch RFOs",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0400020120 ",
+        "MSRValue": "0x0400020120",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.ALL_PF_RFO.SUPPLIER_NONE.SNOOP_HIT_NO_FWD",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "ALL_PF_RFO & SUPPLIER_NONE & SNOOP_HIT_NO_FWD",
+        "BriefDescription": "Counts prefetch RFOs",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts prefetch RFOs",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x1000020120 ",
+        "MSRValue": "0x1000020120",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.ALL_PF_RFO.SUPPLIER_NONE.SNOOP_HITM",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "ALL_PF_RFO & SUPPLIER_NONE & SNOOP_HITM",
+        "BriefDescription": "Counts prefetch RFOs",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts prefetch RFOs",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x3f80020120 ",
+        "MSRValue": "0x3F80020120",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.ALL_PF_RFO.SUPPLIER_NONE.ANY_SNOOP",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "ALL_PF_RFO & SUPPLIER_NONE & ANY_SNOOP",
+        "BriefDescription": "Counts prefetch RFOs",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "Counts prefetch RFOs that hit in the L3 with no details on snoop-related information. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts prefetch RFOs",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x00803c0120 ",
+        "MSRValue": "0x00803C0120",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.ALL_PF_RFO.L3_HIT.SNOOP_NONE",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "Counts prefetch RFOs that hit in the L3 with no details on snoop-related information.",
+        "BriefDescription": "Counts prefetch RFOs",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "Counts prefetch RFOs that hit in the L3 and sibling core snoops are not needed as either the core-valid bit is not set or the shared line is present in multiple cores. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts prefetch RFOs",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x01003c0120 ",
+        "MSRValue": "0x01003C0120",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.ALL_PF_RFO.L3_HIT.SNOOP_NOT_NEEDED",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "Counts prefetch RFOs that hit in the L3 and sibling core snoops are not needed as either the core-valid bit is not set or the shared line is present in multiple cores.",
+        "BriefDescription": "Counts prefetch RFOs",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "Counts prefetch RFOs that hit in the L3 with a snoop miss response. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts prefetch RFOs",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x02003c0120 ",
+        "MSRValue": "0x02003C0120",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.ALL_PF_RFO.L3_HIT.SNOOP_MISS",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "Counts prefetch RFOs that hit in the L3 with a snoop miss response.",
+        "BriefDescription": "Counts prefetch RFOs",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "Counts prefetch RFOs that hit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts prefetch RFOs",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x04003c0120 ",
+        "MSRValue": "0x04003C0120",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.ALL_PF_RFO.L3_HIT.SNOOP_HIT_NO_FWD",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "Counts prefetch RFOs that hit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded.",
+        "BriefDescription": "Counts prefetch RFOs",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts prefetch RFOs",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x10003c0120 ",
+        "MSRValue": "0x10003C0120",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.ALL_PF_RFO.L3_HIT.SNOOP_HITM",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "ALL_PF_RFO & L3_HIT & SNOOP_HITM",
+        "BriefDescription": "Counts prefetch RFOs",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "Counts prefetch RFOs that hit in the L3. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts prefetch RFOs",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x3f803c0120 ",
+        "MSRValue": "0x3F803C0120",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.ALL_PF_RFO.L3_HIT.ANY_SNOOP",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "Counts prefetch RFOs that hit in the L3.",
+        "BriefDescription": "Counts prefetch RFOs",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "Counts all prefetch code reads that have any response type. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all prefetch code reads have any response type.",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0000010240 ",
+        "MSRValue": "0x0000010240",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.ALL_PF_CODE_RD.ANY_RESPONSE",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "Counts all prefetch code reads that have any response type.",
+        "BriefDescription": "Counts all prefetch code reads have any response type.",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all prefetch code reads",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0080020240 ",
+        "MSRValue": "0x0080020240",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.ALL_PF_CODE_RD.SUPPLIER_NONE.SNOOP_NONE",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "ALL_PF_CODE_RD & SUPPLIER_NONE & SNOOP_NONE",
+        "BriefDescription": "Counts all prefetch code reads",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all prefetch code reads",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0100020240 ",
+        "MSRValue": "0x0100020240",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.ALL_PF_CODE_RD.SUPPLIER_NONE.SNOOP_NOT_NEEDED",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "ALL_PF_CODE_RD & SUPPLIER_NONE & SNOOP_NOT_NEEDED",
+        "BriefDescription": "Counts all prefetch code reads",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all prefetch code reads",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0200020240 ",
+        "MSRValue": "0x0200020240",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.ALL_PF_CODE_RD.SUPPLIER_NONE.SNOOP_MISS",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "ALL_PF_CODE_RD & SUPPLIER_NONE & SNOOP_MISS",
+        "BriefDescription": "Counts all prefetch code reads",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all prefetch code reads",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0400020240 ",
+        "MSRValue": "0x0400020240",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.ALL_PF_CODE_RD.SUPPLIER_NONE.SNOOP_HIT_NO_FWD",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "ALL_PF_CODE_RD & SUPPLIER_NONE & SNOOP_HIT_NO_FWD",
+        "BriefDescription": "Counts all prefetch code reads",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all prefetch code reads",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x1000020240 ",
+        "MSRValue": "0x1000020240",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.ALL_PF_CODE_RD.SUPPLIER_NONE.SNOOP_HITM",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "ALL_PF_CODE_RD & SUPPLIER_NONE & SNOOP_HITM",
+        "BriefDescription": "Counts all prefetch code reads",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all prefetch code reads",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x3f80020240 ",
+        "MSRValue": "0x3F80020240",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.ALL_PF_CODE_RD.SUPPLIER_NONE.ANY_SNOOP",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "ALL_PF_CODE_RD & SUPPLIER_NONE & ANY_SNOOP",
+        "BriefDescription": "Counts all prefetch code reads",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "Counts all prefetch code reads that hit in the L3 with no details on snoop-related information. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all prefetch code reads",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x00803c0240 ",
+        "MSRValue": "0x00803C0240",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.ALL_PF_CODE_RD.L3_HIT.SNOOP_NONE",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "Counts all prefetch code reads that hit in the L3 with no details on snoop-related information.",
+        "BriefDescription": "Counts all prefetch code reads",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "Counts all prefetch code reads that hit in the L3 and sibling core snoops are not needed as either the core-valid bit is not set or the shared line is present in multiple cores. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all prefetch code reads",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x01003c0240 ",
+        "MSRValue": "0x01003C0240",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.ALL_PF_CODE_RD.L3_HIT.SNOOP_NOT_NEEDED",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "Counts all prefetch code reads that hit in the L3 and sibling core snoops are not needed as either the core-valid bit is not set or the shared line is present in multiple cores.",
+        "BriefDescription": "Counts all prefetch code reads",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "Counts all prefetch code reads that hit in the L3 with a snoop miss response. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all prefetch code reads",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x02003c0240 ",
+        "MSRValue": "0x02003C0240",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.ALL_PF_CODE_RD.L3_HIT.SNOOP_MISS",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "Counts all prefetch code reads that hit in the L3 with a snoop miss response.",
+        "BriefDescription": "Counts all prefetch code reads",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "Counts all prefetch code reads that hit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all prefetch code reads",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x04003c0240 ",
+        "MSRValue": "0x04003C0240",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.ALL_PF_CODE_RD.L3_HIT.SNOOP_HIT_NO_FWD",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "Counts all prefetch code reads that hit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded.",
+        "BriefDescription": "Counts all prefetch code reads",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all prefetch code reads",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x10003c0240 ",
+        "MSRValue": "0x10003C0240",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.ALL_PF_CODE_RD.L3_HIT.SNOOP_HITM",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "ALL_PF_CODE_RD & L3_HIT & SNOOP_HITM",
+        "BriefDescription": "Counts all prefetch code reads",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "Counts all prefetch code reads that hit in the L3. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all prefetch code reads",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x3f803c0240 ",
+        "MSRValue": "0x3F803C0240",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.ALL_PF_CODE_RD.L3_HIT.ANY_SNOOP",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "Counts all prefetch code reads that hit in the L3.",
+        "BriefDescription": "Counts all prefetch code reads",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "Counts all demand & prefetch data reads that have any response type. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all demand & prefetch data reads have any response type.",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0000010091 ",
+        "MSRValue": "0x0000010091",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.ALL_DATA_RD.ANY_RESPONSE",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "Counts all demand & prefetch data reads that have any response type.",
+        "BriefDescription": "Counts all demand & prefetch data reads have any response type.",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all demand & prefetch data reads",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0080020091 ",
+        "MSRValue": "0x0080020091",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.ALL_DATA_RD.SUPPLIER_NONE.SNOOP_NONE",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "ALL_DATA_RD & SUPPLIER_NONE & SNOOP_NONE",
+        "BriefDescription": "Counts all demand & prefetch data reads",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all demand & prefetch data reads",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0100020091 ",
+        "MSRValue": "0x0100020091",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.ALL_DATA_RD.SUPPLIER_NONE.SNOOP_NOT_NEEDED",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "ALL_DATA_RD & SUPPLIER_NONE & SNOOP_NOT_NEEDED",
+        "BriefDescription": "Counts all demand & prefetch data reads",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all demand & prefetch data reads",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0200020091 ",
+        "MSRValue": "0x0200020091",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.ALL_DATA_RD.SUPPLIER_NONE.SNOOP_MISS",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "ALL_DATA_RD & SUPPLIER_NONE & SNOOP_MISS",
+        "BriefDescription": "Counts all demand & prefetch data reads",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all demand & prefetch data reads",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0400020091 ",
+        "MSRValue": "0x0400020091",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.ALL_DATA_RD.SUPPLIER_NONE.SNOOP_HIT_NO_FWD",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "ALL_DATA_RD & SUPPLIER_NONE & SNOOP_HIT_NO_FWD",
+        "BriefDescription": "Counts all demand & prefetch data reads",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all demand & prefetch data reads",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x1000020091 ",
+        "MSRValue": "0x1000020091",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.ALL_DATA_RD.SUPPLIER_NONE.SNOOP_HITM",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "ALL_DATA_RD & SUPPLIER_NONE & SNOOP_HITM",
+        "BriefDescription": "Counts all demand & prefetch data reads",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all demand & prefetch data reads",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x3f80020091 ",
+        "MSRValue": "0x3F80020091",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.ALL_DATA_RD.SUPPLIER_NONE.ANY_SNOOP",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "ALL_DATA_RD & SUPPLIER_NONE & ANY_SNOOP",
+        "BriefDescription": "Counts all demand & prefetch data reads",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "Counts all demand & prefetch data reads that hit in the L3 with no details on snoop-related information. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all demand & prefetch data reads",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x00803c0091 ",
+        "MSRValue": "0x00803C0091",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.ALL_DATA_RD.L3_HIT.SNOOP_NONE",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "Counts all demand & prefetch data reads that hit in the L3 with no details on snoop-related information.",
+        "BriefDescription": "Counts all demand & prefetch data reads",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "Counts all demand & prefetch data reads that hit in the L3 and sibling core snoops are not needed as either the core-valid bit is not set or the shared line is present in multiple cores. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all demand & prefetch data reads",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x01003c0091 ",
+        "MSRValue": "0x01003C0091",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.ALL_DATA_RD.L3_HIT.SNOOP_NOT_NEEDED",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "Counts all demand & prefetch data reads that hit in the L3 and sibling core snoops are not needed as either the core-valid bit is not set or the shared line is present in multiple cores.",
+        "BriefDescription": "Counts all demand & prefetch data reads",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "Counts all demand & prefetch data reads that hit in the L3 with a snoop miss response. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all demand & prefetch data reads",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x02003c0091 ",
+        "MSRValue": "0x02003C0091",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.ALL_DATA_RD.L3_HIT.SNOOP_MISS",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "Counts all demand & prefetch data reads that hit in the L3 with a snoop miss response.",
+        "BriefDescription": "Counts all demand & prefetch data reads",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "Counts all demand & prefetch data reads that hit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all demand & prefetch data reads",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x04003c0091 ",
+        "MSRValue": "0x04003C0091",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.ALL_DATA_RD.L3_HIT.SNOOP_HIT_NO_FWD",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "Counts all demand & prefetch data reads that hit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded.",
+        "BriefDescription": "Counts all demand & prefetch data reads",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all demand & prefetch data reads",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x10003c0091 ",
+        "MSRValue": "0x10003C0091",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.ALL_DATA_RD.L3_HIT.SNOOP_HITM",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "ALL_DATA_RD & L3_HIT & SNOOP_HITM",
+        "BriefDescription": "Counts all demand & prefetch data reads",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "Counts all demand & prefetch data reads that hit in the L3. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all demand & prefetch data reads",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x3f803c0091 ",
+        "MSRValue": "0x3F803C0091",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.ALL_DATA_RD.L3_HIT.ANY_SNOOP",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "Counts all demand & prefetch data reads that hit in the L3.",
+        "BriefDescription": "Counts all demand & prefetch data reads",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "Counts all demand & prefetch RFOs that have any response type. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all demand & prefetch RFOs have any response type.",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0000010122 ",
+        "MSRValue": "0x0000010122",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.ALL_RFO.ANY_RESPONSE",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "Counts all demand & prefetch RFOs that have any response type.",
+        "BriefDescription": "Counts all demand & prefetch RFOs have any response type.",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all demand & prefetch RFOs",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0080020122 ",
+        "MSRValue": "0x0080020122",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.ALL_RFO.SUPPLIER_NONE.SNOOP_NONE",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "ALL_RFO & SUPPLIER_NONE & SNOOP_NONE",
+        "BriefDescription": "Counts all demand & prefetch RFOs",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all demand & prefetch RFOs",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0100020122 ",
+        "MSRValue": "0x0100020122",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.ALL_RFO.SUPPLIER_NONE.SNOOP_NOT_NEEDED",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "ALL_RFO & SUPPLIER_NONE & SNOOP_NOT_NEEDED",
+        "BriefDescription": "Counts all demand & prefetch RFOs",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all demand & prefetch RFOs",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0200020122 ",
+        "MSRValue": "0x0200020122",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.ALL_RFO.SUPPLIER_NONE.SNOOP_MISS",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "ALL_RFO & SUPPLIER_NONE & SNOOP_MISS",
+        "BriefDescription": "Counts all demand & prefetch RFOs",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all demand & prefetch RFOs",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0400020122 ",
+        "MSRValue": "0x0400020122",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.ALL_RFO.SUPPLIER_NONE.SNOOP_HIT_NO_FWD",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "ALL_RFO & SUPPLIER_NONE & SNOOP_HIT_NO_FWD",
+        "BriefDescription": "Counts all demand & prefetch RFOs",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all demand & prefetch RFOs",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x1000020122 ",
+        "MSRValue": "0x1000020122",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.ALL_RFO.SUPPLIER_NONE.SNOOP_HITM",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "ALL_RFO & SUPPLIER_NONE & SNOOP_HITM",
+        "BriefDescription": "Counts all demand & prefetch RFOs",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all demand & prefetch RFOs",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x3f80020122 ",
+        "MSRValue": "0x3F80020122",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.ALL_RFO.SUPPLIER_NONE.ANY_SNOOP",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "ALL_RFO & SUPPLIER_NONE & ANY_SNOOP",
+        "BriefDescription": "Counts all demand & prefetch RFOs",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "Counts all demand & prefetch RFOs that hit in the L3 with no details on snoop-related information. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all demand & prefetch RFOs",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x00803c0122 ",
+        "MSRValue": "0x00803C0122",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.ALL_RFO.L3_HIT.SNOOP_NONE",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "Counts all demand & prefetch RFOs that hit in the L3 with no details on snoop-related information.",
+        "BriefDescription": "Counts all demand & prefetch RFOs",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "Counts all demand & prefetch RFOs that hit in the L3 and sibling core snoops are not needed as either the core-valid bit is not set or the shared line is present in multiple cores. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all demand & prefetch RFOs",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x01003c0122 ",
+        "MSRValue": "0x01003C0122",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.ALL_RFO.L3_HIT.SNOOP_NOT_NEEDED",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "Counts all demand & prefetch RFOs that hit in the L3 and sibling core snoops are not needed as either the core-valid bit is not set or the shared line is present in multiple cores.",
+        "BriefDescription": "Counts all demand & prefetch RFOs",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "Counts all demand & prefetch RFOs that hit in the L3 with a snoop miss response. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all demand & prefetch RFOs",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x02003c0122 ",
+        "MSRValue": "0x02003C0122",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.ALL_RFO.L3_HIT.SNOOP_MISS",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "Counts all demand & prefetch RFOs that hit in the L3 with a snoop miss response.",
+        "BriefDescription": "Counts all demand & prefetch RFOs",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "Counts all demand & prefetch RFOs that hit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all demand & prefetch RFOs",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x04003c0122 ",
+        "MSRValue": "0x04003C0122",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.ALL_RFO.L3_HIT.SNOOP_HIT_NO_FWD",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "Counts all demand & prefetch RFOs that hit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded.",
+        "BriefDescription": "Counts all demand & prefetch RFOs",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all demand & prefetch RFOs",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x10003c0122 ",
+        "MSRValue": "0x10003C0122",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.ALL_RFO.L3_HIT.SNOOP_HITM",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "ALL_RFO & L3_HIT & SNOOP_HITM",
+        "BriefDescription": "Counts all demand & prefetch RFOs",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "Counts all demand & prefetch RFOs that hit in the L3. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all demand & prefetch RFOs",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x3f803c0122 ",
+        "MSRValue": "0x3F803C0122",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.ALL_RFO.L3_HIT.ANY_SNOOP",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "Counts all demand & prefetch RFOs that hit in the L3.",
+        "BriefDescription": "Counts all demand & prefetch RFOs",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     }
diff --git a/tools/perf/pmu-events/arch/x86/broadwell/floating-point.json b/tools/perf/pmu-events/arch/x86/broadwell/floating-point.json
index 689d478dae93..15291239c128 100644
--- a/tools/perf/pmu-events/arch/x86/broadwell/floating-point.json
+++ b/tools/perf/pmu-events/arch/x86/broadwell/floating-point.json
@@ -1,24 +1,26 @@
 [
     {
-        "PublicDescription": "This event counts the number of transitions from AVX-256 to legacy SSE when penalty is applicable.",
+        "PEBS": "1",
+        "PublicDescription": "This is a precise version (that is, uses PEBS) of the event that counts the number of transitions from AVX-256 to legacy SSE when penalty is applicable.",
         "EventCode": "0xC1",
         "Counter": "0,1,2,3",
         "UMask": "0x8",
         "Errata": "BDM30",
         "EventName": "OTHER_ASSISTS.AVX_TO_SSE",
         "SampleAfterValue": "100003",
-        "BriefDescription": "Number of transitions from AVX-256 to legacy SSE when penalty applicable.",
+        "BriefDescription": "Number of transitions from AVX-256 to legacy SSE when penalty applicable (Precise Event)",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "PublicDescription": "This event counts the number of transitions from legacy SSE to AVX-256 when penalty is applicable.",
+        "PEBS": "1",
+        "PublicDescription": "This is a precise version (that is, uses PEBS) of the event that counts the number of transitions from legacy SSE to AVX-256 when penalty is applicable.",
         "EventCode": "0xC1",
         "Counter": "0,1,2,3",
         "UMask": "0x10",
         "Errata": "BDM30",
         "EventName": "OTHER_ASSISTS.SSE_TO_AVX",
         "SampleAfterValue": "100003",
-        "BriefDescription": "Number of transitions from SSE to AVX-256 when penalty applicable.",
+        "BriefDescription": "Number of transitions from legacy SSE to AVX-256 when penalty applicable (Precise Event)",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
@@ -45,7 +47,7 @@
         "UMask": "0x3",
         "EventName": "FP_ARITH_INST_RETIRED.SCALAR",
         "SampleAfterValue": "2000003",
-        "BriefDescription": "Number of SSE/AVX computational scalar floating-point instructions retired. Applies to SSE* and AVX* scalar, double and single precision floating-point: ADD SUB MUL DIV MIN MAX RSQRT RCP SQRT FM(N)ADD/SUB. FM(N)ADD/SUB instructions count twice as they perform multiple calculations per element.",
+        "BriefDescription": "Number of SSE/AVX computational scalar floating-point instructions retired. Applies to SSE* and AVX* scalar, double and single precision floating-point: ADD SUB MUL DIV MIN MAX RSQRT RCP SQRT FM(N)ADD/SUB. FM(N)ADD/SUB instructions count twice as they perform multiple calculations per element. (RSQRT for single precision?)",
         "CounterHTOff": "0,1,2,3"
     },
     {
@@ -54,7 +56,7 @@
         "UMask": "0x4",
         "EventName": "FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE",
         "SampleAfterValue": "2000003",
-        "BriefDescription": "Number of SSE/AVX computational 128-bit packed double precision floating-point instructions retired.  Each count represents 2 computations. Applies to SSE* and AVX* packed double precision floating-point instructions: ADD SUB MUL DIV MIN MAX SQRT DPP FM(N)ADD/SUB.  DPP and FM(N)ADD/SUB instructions count twice as they perform multiple calculations per element.",
+        "BriefDescription": "Number of SSE/AVX computational 128-bit packed double precision floating-point instructions retired.  Each count represents 2 computations. Applies to SSE* and AVX* packed double precision floating-point instructions: ADD SUB HADD HSUB SUBADD MUL DIV MIN MAX SQRT DPP FM(N)ADD/SUB.  DPP and FM(N)ADD/SUB instructions count twice as they perform multiple calculations per element.",
         "CounterHTOff": "0,1,2,3"
     },
     {
@@ -63,7 +65,7 @@
         "UMask": "0x8",
         "EventName": "FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE",
         "SampleAfterValue": "2000003",
-        "BriefDescription": "Number of SSE/AVX computational 128-bit packed single precision floating-point instructions retired.  Each count represents 4 computations. Applies to SSE* and AVX* packed single precision floating-point instructions: ADD SUB MUL DIV MIN MAX RCP RSQRT SQRT DPP FM(N)ADD/SUB.  DPP and FM(N)ADD/SUB instructions count twice as they perform multiple calculations per element.",
+        "BriefDescription": "Number of SSE/AVX computational 128-bit packed single precision floating-point instructions retired.  Each count represents 4 computations. Applies to SSE* and AVX* packed single precision floating-point instructions: ADD SUB HADD HSUB SUBADD MUL DIV MIN MAX SQRT RSQRT DPP FM(N)ADD/SUB.  DPP and FM(N)ADD/SUB instructions count twice as they perform multiple calculations per element.",
         "CounterHTOff": "0,1,2,3"
     },
     {
@@ -72,7 +74,7 @@
         "UMask": "0x10",
         "EventName": "FP_ARITH_INST_RETIRED.256B_PACKED_DOUBLE",
         "SampleAfterValue": "2000003",
-        "BriefDescription": "Number of SSE/AVX computational 256-bit packed double precision floating-point instructions retired.  Each count represents 4 computations. Applies to SSE* and AVX* packed double precision floating-point instructions: ADD SUB MUL DIV MIN MAX SQRT DPP FM(N)ADD/SUB.  DPP and FM(N)ADD/SUB instructions count twice as they perform multiple calculations per element.",
+        "BriefDescription": "Number of SSE/AVX computational 256-bit packed double precision floating-point instructions retired.  Each count represents 4 computations. Applies to SSE* and AVX* packed double precision floating-point instructions: ADD SUB HADD HSUB SUBADD MUL DIV MIN MAX SQRT DPP FM(N)ADD/SUB.  DPP and FM(N)ADD/SUB instructions count twice as they perform multiple calculations per element.",
         "CounterHTOff": "0,1,2,3"
     },
     {
@@ -81,7 +83,7 @@
         "UMask": "0x15",
         "EventName": "FP_ARITH_INST_RETIRED.DOUBLE",
         "SampleAfterValue": "2000006",
-        "BriefDescription": "Number of SSE/AVX computational double precision floating-point instructions retired. Applies to SSE* and AVX*scalar, double and single precision floating-point: ADD SUB MUL DIV MIN MAX SQRT DPP FM(N)ADD/SUB.  DPP and FM(N)ADD/SUB instructions count twice as they perform multiple calculations per element.  ?.",
+        "BriefDescription": "Number of SSE/AVX computational double precision floating-point instructions retired. Applies to SSE* and AVX*scalar, double and single precision floating-point: ADD SUB MUL DIV MIN MAX SQRT DPP FM(N)ADD/SUB.  DPP and FM(N)ADD/SUB instructions count twice as they perform multiple calculations per element.",
         "CounterHTOff": "0,1,2,3"
     },
     {
@@ -90,7 +92,7 @@
         "UMask": "0x20",
         "EventName": "FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE",
         "SampleAfterValue": "2000003",
-        "BriefDescription": "Number of SSE/AVX computational 256-bit packed single precision floating-point instructions retired.  Each count represents 8 computations. Applies to SSE* and AVX* packed single precision floating-point instructions: ADD SUB MUL DIV MIN MAX RCP RSQRT SQRT DPP FM(N)ADD/SUB.  DPP and FM(N)ADD/SUB instructions count twice as they perform multiple calculations per element.",
+        "BriefDescription": "Number of SSE/AVX computational 256-bit packed single precision floating-point instructions retired.  Each count represents 8 computations. Applies to SSE* and AVX* packed single precision floating-point instructions: ADD SUB HADD HSUB SUBADD MUL DIV MIN MAX SQRT RSQRT DPP FM(N)ADD/SUB.  DPP and FM(N)ADD/SUB instructions count twice as they perform multiple calculations per element.",
         "CounterHTOff": "0,1,2,3"
     },
     {
@@ -99,7 +101,7 @@
         "UMask": "0x2a",
         "EventName": "FP_ARITH_INST_RETIRED.SINGLE",
         "SampleAfterValue": "2000005",
-        "BriefDescription": "Number of SSE/AVX computational single precision floating-point instructions retired. Applies to SSE* and AVX*scalar, double and single precision floating-point: ADD SUB MUL DIV MIN MAX RCP RSQRT SQRT DPP FM(N)ADD/SUB.  DPP and FM(N)ADD/SUB instructions count twice as they perform multiple calculations per element. ?.",
+        "BriefDescription": "Number of SSE/AVX computational single precision floating-point instructions retired. Applies to SSE* and AVX*scalar, double and single precision floating-point: ADD SUB MUL DIV MIN MAX RCP RSQRT SQRT DPP FM(N)ADD/SUB.  DPP and FM(N)ADD/SUB instructions count twice as they perform multiple calculations per element.",
         "CounterHTOff": "0,1,2,3"
     },
     {
@@ -108,57 +110,62 @@
         "UMask": "0x3c",
         "EventName": "FP_ARITH_INST_RETIRED.PACKED",
         "SampleAfterValue": "2000004",
-        "BriefDescription": "Number of SSE/AVX computational packed floating-point instructions retired. Applies to SSE* and AVX*, packed, double and single precision floating-point: ADD SUB MUL DIV MIN MAX RSQRT RCP SQRT DPP FM(N)ADD/SUB.  DPP and FM(N)ADD/SUB instructions count twice as they perform multiple calculations per element.",
+        "BriefDescription": "Number of SSE/AVX computational packed floating-point instructions retired. Applies to SSE* and AVX*, packed, double and single precision floating-point: ADD SUB HADD HSUB SUBADD MUL DIV MIN MAX SQRT DPP FM(N)ADD/SUB.  DPP and FM(N)ADD/SUB instructions count twice as they perform multiple calculations per element. (RSQRT for single-precision?)",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "This event counts the number of x87 floating point (FP) micro-code assist (numeric overflow/underflow, inexact result) when the output value (destination register) is invalid.",
+        "PEBS": "1",
+        "PublicDescription": "This is a precise version (that is, uses PEBS) of the event that counts the number of x87 floating point (FP) micro-code assist (numeric overflow/underflow, inexact result) when the output value (destination register) is invalid.",
         "EventCode": "0xCA",
         "Counter": "0,1,2,3",
         "UMask": "0x2",
         "EventName": "FP_ASSIST.X87_OUTPUT",
         "SampleAfterValue": "100003",
-        "BriefDescription": "Number of X87 assists due to output value.",
+        "BriefDescription": "output - Numeric Overflow, Numeric Underflow, Inexact Result  (Precise Event)",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "PublicDescription": "This event counts x87 floating point (FP) micro-code assist (invalid operation, denormal operand, SNaN operand) when the input value (one of the source operands to an FP instruction) is invalid.",
+        "PEBS": "1",
+        "PublicDescription": "This is a precise version (that is, uses PEBS) of the event that counts x87 floating point (FP) micro-code assist (invalid operation, denormal operand, SNaN operand) when the input value (one of the source operands to an FP instruction) is invalid.",
         "EventCode": "0xCA",
         "Counter": "0,1,2,3",
         "UMask": "0x4",
         "EventName": "FP_ASSIST.X87_INPUT",
         "SampleAfterValue": "100003",
-        "BriefDescription": "Number of X87 assists due to input value.",
+        "BriefDescription": "input - Invalid Operation, Denormal Operand, SNaN Operand  (Precise Event)",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "PublicDescription": "This event counts the number of SSE* floating point (FP) micro-code assist (numeric overflow/underflow) when the output value (destination register) is invalid. Counting covers only cases involving penalties that require micro-code assist intervention.",
+        "PEBS": "1",
+        "PublicDescription": "This is a precise version (that is, uses PEBS) of the event that counts the number of SSE* floating point (FP) micro-code assist (numeric overflow/underflow) when the output value (destination register) is invalid. Counting covers only cases involving penalties that require micro-code assist intervention.",
         "EventCode": "0xCA",
         "Counter": "0,1,2,3",
         "UMask": "0x8",
         "EventName": "FP_ASSIST.SIMD_OUTPUT",
         "SampleAfterValue": "100003",
-        "BriefDescription": "Number of SIMD FP assists due to Output values",
+        "BriefDescription": "SSE* FP micro-code assist when output value is invalid. (Precise Event)",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "PublicDescription": "This event counts any input SSE* FP assist - invalid operation, denormal operand, dividing by zero, SNaN operand. Counting includes only cases involving penalties that required micro-code assist intervention.",
+        "PEBS": "1",
+        "PublicDescription": "This is a precise version (that is, uses PEBS) of the event that counts any input SSE* floating-point (FP) assist - invalid operation, denormal operand, dividing by zero, SNaN operand. Counting includes only cases involving penalties that required micro-code assist intervention.",
         "EventCode": "0xCA",
         "Counter": "0,1,2,3",
         "UMask": "0x10",
         "EventName": "FP_ASSIST.SIMD_INPUT",
         "SampleAfterValue": "100003",
-        "BriefDescription": "Number of SIMD FP assists due to input values",
+        "BriefDescription": "Any input SSE* FP Assist -   (Precise Event)",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "PublicDescription": "This event counts cycles with any input and output SSE or x87 FP assist. If an input and output assist are detected on the same cycle the event increments by 1.",
+        "PEBS": "1",
+        "PublicDescription": "This event counts cycles with any input and output SSE or x87 FP assist. If an input and output assist are detected on the same cycle the event increments by 1. Uses PEBS.",
         "EventCode": "0xCA",
         "Counter": "0,1,2,3",
         "UMask": "0x1e",
         "EventName": "FP_ASSIST.ANY",
         "SampleAfterValue": "100003",
-        "BriefDescription": "Cycles with any input/output SSE or FP assist",
+        "BriefDescription": "Counts any FP_ASSIST umask was incrementing   (Precise Event)",
         "CounterMask": "1",
         "CounterHTOff": "0,1,2,3"
     }
diff --git a/tools/perf/pmu-events/arch/x86/broadwell/frontend.json b/tools/perf/pmu-events/arch/x86/broadwell/frontend.json
index 7142c76d7f11..aa4a5d762f21 100644
--- a/tools/perf/pmu-events/arch/x86/broadwell/frontend.json
+++ b/tools/perf/pmu-events/arch/x86/broadwell/frontend.json
@@ -211,7 +211,7 @@
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "PublicDescription": "This event counts the number of uops not delivered to Resource Allocation Table (RAT) per thread adding 4  x when Resource Allocation Table (RAT) is not stalled and Instruction Decode Queue (IDQ) delivers x uops to Resource Allocation Table (RAT) (where x belongs to {0,1,2,3}). Counting does not cover cases when:\n a. IDQ-Resource Allocation Table (RAT) pipe serves the other thread;\n b. Resource Allocation Table (RAT) is stalled for the thread (including uop drops and clear BE conditions); \n c. Instruction Decode Queue (IDQ) delivers four uops.",
+        "PublicDescription": "This event counts the number of uops not delivered to Resource Allocation Table (RAT) per thread adding \u201c4 \u2013 x\u201d when Resource Allocation Table (RAT) is not stalled and Instruction Decode Queue (IDQ) delivers x uops to Resource Allocation Table (RAT) (where x belongs to {0,1,2,3}). Counting does not cover cases when:\n a. IDQ-Resource Allocation Table (RAT) pipe serves the other thread;\n b. Resource Allocation Table (RAT) is stalled for the thread (including uop drops and clear BE conditions); \n c. Instruction Decode Queue (IDQ) delivers four uops.",
         "EventCode": "0x9C",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
@@ -274,7 +274,7 @@
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "This event counts Decode Stream Buffer (DSB)-to-MITE switch true penalty cycles. These cycles do not include uops routed through because of the switch itself, for example, when Instruction Decode Queue (IDQ) pre-allocation is unavailable, or Instruction Decode Queue (IDQ) is full. SBD-to-MITE switch true penalty cycles happen after the merge mux (MM) receives Decode Stream Buffer (DSB) Sync-indication until receiving the first MITE uop. \nMM is placed before Instruction Decode Queue (IDQ) to merge uops being fed from the MITE and Decode Stream Buffer (DSB) paths. Decode Stream Buffer (DSB) inserts the Sync-indication whenever a Decode Stream Buffer (DSB)-to-MITE switch occurs.\nPenalty: A Decode Stream Buffer (DSB) hit followed by a Decode Stream Buffer (DSB) miss can cost up to six cycles in which no uops are delivered to the IDQ. Most often, such switches from the Decode Stream Buffer (DSB) to the legacy pipeline cost 02 cycles.",
+        "PublicDescription": "This event counts Decode Stream Buffer (DSB)-to-MITE switch true penalty cycles. These cycles do not include uops routed through because of the switch itself, for example, when Instruction Decode Queue (IDQ) pre-allocation is unavailable, or Instruction Decode Queue (IDQ) is full. SBD-to-MITE switch true penalty cycles happen after the merge mux (MM) receives Decode Stream Buffer (DSB) Sync-indication until receiving the first MITE uop. \nMM is placed before Instruction Decode Queue (IDQ) to merge uops being fed from the MITE and Decode Stream Buffer (DSB) paths. Decode Stream Buffer (DSB) inserts the Sync-indication whenever a Decode Stream Buffer (DSB)-to-MITE switch occurs.\nPenalty: A Decode Stream Buffer (DSB) hit followed by a Decode Stream Buffer (DSB) miss can cost up to six cycles in which no uops are delivered to the IDQ. Most often, such switches from the Decode Stream Buffer (DSB) to the legacy pipeline cost 0\u20132 cycles.",
         "EventCode": "0xAB",
         "Counter": "0,1,2,3",
         "UMask": "0x2",
diff --git a/tools/perf/pmu-events/arch/x86/broadwell/memory.json b/tools/perf/pmu-events/arch/x86/broadwell/memory.json
index c9154cebbdf0..b6b5247d3d5a 100644
--- a/tools/perf/pmu-events/arch/x86/broadwell/memory.json
+++ b/tools/perf/pmu-events/arch/x86/broadwell/memory.json
@@ -311,7 +311,7 @@
     },
     {
         "PEBS": "2",
-        "PublicDescription": "This event counts loads with latency value being above four.",
+        "PublicDescription": "Counts randomly selected loads with latency value being above four.",
         "EventCode": "0xCD",
         "MSRValue": "0x4",
         "Counter": "3",
@@ -320,13 +320,13 @@
         "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_4",
         "MSRIndex": "0x3F6",
         "SampleAfterValue": "100003",
-        "BriefDescription": "Loads with latency value being above 4",
+        "BriefDescription": "Randomly selected loads with latency value being above 4",
         "TakenAlone": "1",
         "CounterHTOff": "3"
     },
     {
         "PEBS": "2",
-        "PublicDescription": "This event counts loads with latency value being above eight.",
+        "PublicDescription": "Counts randomly selected loads with latency value being above eight.",
         "EventCode": "0xCD",
         "MSRValue": "0x8",
         "Counter": "3",
@@ -335,13 +335,13 @@
         "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_8",
         "MSRIndex": "0x3F6",
         "SampleAfterValue": "50021",
-        "BriefDescription": "Loads with latency value being above 8",
+        "BriefDescription": "Randomly selected loads with latency value being above 8",
         "TakenAlone": "1",
         "CounterHTOff": "3"
     },
     {
         "PEBS": "2",
-        "PublicDescription": "This event counts loads with latency value being above 16.",
+        "PublicDescription": "Counts randomly selected loads with latency value being above 16.",
         "EventCode": "0xCD",
         "MSRValue": "0x10",
         "Counter": "3",
@@ -350,13 +350,13 @@
         "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_16",
         "MSRIndex": "0x3F6",
         "SampleAfterValue": "20011",
-        "BriefDescription": "Loads with latency value being above 16",
+        "BriefDescription": "Randomly selected loads with latency value being above 16",
         "TakenAlone": "1",
         "CounterHTOff": "3"
     },
     {
         "PEBS": "2",
-        "PublicDescription": "This event counts loads with latency value being above 32.",
+        "PublicDescription": "Counts randomly selected loads with latency value being above 32.",
         "EventCode": "0xCD",
         "MSRValue": "0x20",
         "Counter": "3",
@@ -365,13 +365,13 @@
         "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_32",
         "MSRIndex": "0x3F6",
         "SampleAfterValue": "100007",
-        "BriefDescription": "Loads with latency value being above 32",
+        "BriefDescription": "Randomly selected loads with latency value being above 32",
         "TakenAlone": "1",
         "CounterHTOff": "3"
     },
     {
         "PEBS": "2",
-        "PublicDescription": "This event counts loads with latency value being above 64.",
+        "PublicDescription": "Counts randomly selected loads with latency value being above 64.",
         "EventCode": "0xCD",
         "MSRValue": "0x40",
         "Counter": "3",
@@ -380,13 +380,13 @@
         "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_64",
         "MSRIndex": "0x3F6",
         "SampleAfterValue": "2003",
-        "BriefDescription": "Loads with latency value being above 64",
+        "BriefDescription": "Randomly selected loads with latency value being above 64",
         "TakenAlone": "1",
         "CounterHTOff": "3"
     },
     {
         "PEBS": "2",
-        "PublicDescription": "This event counts loads with latency value being above 128.",
+        "PublicDescription": "Counts randomly selected loads with latency value being above 128.",
         "EventCode": "0xCD",
         "MSRValue": "0x80",
         "Counter": "3",
@@ -395,13 +395,13 @@
         "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_128",
         "MSRIndex": "0x3F6",
         "SampleAfterValue": "1009",
-        "BriefDescription": "Loads with latency value being above 128",
+        "BriefDescription": "Randomly selected loads with latency value being above 128",
         "TakenAlone": "1",
         "CounterHTOff": "3"
     },
     {
         "PEBS": "2",
-        "PublicDescription": "This event counts loads with latency value being above 256.",
+        "PublicDescription": "Counts randomly selected loads with latency value being above 256.",
         "EventCode": "0xCD",
         "MSRValue": "0x100",
         "Counter": "3",
@@ -410,13 +410,13 @@
         "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_256",
         "MSRIndex": "0x3F6",
         "SampleAfterValue": "503",
-        "BriefDescription": "Loads with latency value being above 256",
+        "BriefDescription": "Randomly selected loads with latency value being above 256",
         "TakenAlone": "1",
         "CounterHTOff": "3"
     },
     {
         "PEBS": "2",
-        "PublicDescription": "This event counts loads with latency value being above 512.",
+        "PublicDescription": "Counts randomly selected loads with latency value being above 512.",
         "EventCode": "0xCD",
         "MSRValue": "0x200",
         "Counter": "3",
@@ -425,2620 +425,2620 @@
         "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_512",
         "MSRIndex": "0x3F6",
         "SampleAfterValue": "101",
-        "BriefDescription": "Loads with latency value being above 512",
+        "BriefDescription": "Randomly selected loads with latency value being above 512",
         "TakenAlone": "1",
         "CounterHTOff": "3"
     },
     {
-        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts demand data reads",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x2000020001 ",
+        "MSRValue": "0x2000020001",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.SUPPLIER_NONE.SNOOP_NON_DRAM",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "DEMAND_DATA_RD & SUPPLIER_NONE & SNOOP_NON_DRAM",
+        "BriefDescription": "Counts demand data reads",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "Counts demand data reads that hit in the L3 and the target was non-DRAM system address. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts demand data reads",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x20003c0001 ",
+        "MSRValue": "0x20003C0001",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_HIT.SNOOP_NON_DRAM",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "Counts demand data reads that hit in the L3 and the target was non-DRAM system address.",
+        "BriefDescription": "Counts demand data reads",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts demand data reads",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0084000001 ",
+        "MSRValue": "0x0084000001",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_MISS_LOCAL_DRAM.SNOOP_NONE",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "DEMAND_DATA_RD & L3_MISS_LOCAL_DRAM & SNOOP_NONE",
+        "BriefDescription": "Counts demand data reads",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts demand data reads",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0104000001 ",
+        "MSRValue": "0x0104000001",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_MISS_LOCAL_DRAM.SNOOP_NOT_NEEDED",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "DEMAND_DATA_RD & L3_MISS_LOCAL_DRAM & SNOOP_NOT_NEEDED",
+        "BriefDescription": "Counts demand data reads",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts demand data reads",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0204000001 ",
+        "MSRValue": "0x0204000001",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_MISS_LOCAL_DRAM.SNOOP_MISS",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "DEMAND_DATA_RD & L3_MISS_LOCAL_DRAM & SNOOP_MISS",
+        "BriefDescription": "Counts demand data reads",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts demand data reads",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0404000001 ",
+        "MSRValue": "0x0404000001",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_MISS_LOCAL_DRAM.SNOOP_HIT_NO_FWD",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "DEMAND_DATA_RD & L3_MISS_LOCAL_DRAM & SNOOP_HIT_NO_FWD",
+        "BriefDescription": "Counts demand data reads",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts demand data reads",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x1004000001 ",
+        "MSRValue": "0x1004000001",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_MISS_LOCAL_DRAM.SNOOP_HITM",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "DEMAND_DATA_RD & L3_MISS_LOCAL_DRAM & SNOOP_HITM",
+        "BriefDescription": "Counts demand data reads",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts demand data reads",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x2004000001 ",
+        "MSRValue": "0x2004000001",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_MISS_LOCAL_DRAM.SNOOP_NON_DRAM",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "DEMAND_DATA_RD & L3_MISS_LOCAL_DRAM & SNOOP_NON_DRAM",
+        "BriefDescription": "Counts demand data reads",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts demand data reads",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x3f84000001 ",
+        "MSRValue": "0x3F84000001",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_MISS_LOCAL_DRAM.ANY_SNOOP",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "DEMAND_DATA_RD & L3_MISS_LOCAL_DRAM & ANY_SNOOP",
+        "BriefDescription": "Counts demand data reads",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "Counts demand data reads that miss the L3 with no details on snoop-related information. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts demand data reads",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x00bc000001 ",
+        "MSRValue": "0x00BC000001",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_MISS.SNOOP_NONE",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "Counts demand data reads that miss the L3 with no details on snoop-related information.",
+        "BriefDescription": "Counts demand data reads",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts demand data reads",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x013c000001 ",
+        "MSRValue": "0x013C000001",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_MISS.SNOOP_NOT_NEEDED",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "DEMAND_DATA_RD & L3_MISS & SNOOP_NOT_NEEDED",
+        "BriefDescription": "Counts demand data reads",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "Counts demand data reads that miss the L3 with a snoop miss response. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts demand data reads",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x023c000001 ",
+        "MSRValue": "0x023C000001",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_MISS.SNOOP_MISS",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "Counts demand data reads that miss the L3 with a snoop miss response.",
+        "BriefDescription": "Counts demand data reads",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts demand data reads",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x043c000001 ",
+        "MSRValue": "0x043C000001",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_MISS.SNOOP_HIT_NO_FWD",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "DEMAND_DATA_RD & L3_MISS & SNOOP_HIT_NO_FWD",
+        "BriefDescription": "Counts demand data reads",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "Counts all demand data writes (RFOs) that hit in the L3 and the target was non-DRAM system address. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all demand data writes (RFOs)",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x20003c0002 ",
+        "MSRValue": "0x20003C0002",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_HIT.SNOOP_NON_DRAM",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "Counts all demand data writes (RFOs) that hit in the L3 and the target was non-DRAM system address.",
+        "BriefDescription": "Counts all demand data writes (RFOs)",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all demand data writes (RFOs)",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x3f84000002 ",
+        "MSRValue": "0x3F84000002",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_MISS_LOCAL_DRAM.ANY_SNOOP",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "DEMAND_RFO & L3_MISS_LOCAL_DRAM & ANY_SNOOP",
+        "BriefDescription": "Counts all demand data writes (RFOs)",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "Counts all demand data writes (RFOs) that miss the L3 with no details on snoop-related information. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all demand data writes (RFOs)",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x00bc000002 ",
+        "MSRValue": "0x00BC000002",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_MISS.SNOOP_NONE",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "Counts all demand data writes (RFOs) that miss the L3 with no details on snoop-related information.",
+        "BriefDescription": "Counts all demand data writes (RFOs)",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all demand data writes (RFOs)",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x013c000002 ",
+        "MSRValue": "0x013C000002",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_MISS.SNOOP_NOT_NEEDED",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "DEMAND_RFO & L3_MISS & SNOOP_NOT_NEEDED",
+        "BriefDescription": "Counts all demand data writes (RFOs)",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "Counts all demand data writes (RFOs) that miss the L3 with a snoop miss response. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all demand data writes (RFOs)",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x023c000002 ",
+        "MSRValue": "0x023C000002",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_MISS.SNOOP_MISS",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "Counts all demand data writes (RFOs) that miss the L3 with a snoop miss response.",
+        "BriefDescription": "Counts all demand data writes (RFOs)",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all demand data writes (RFOs)",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x043c000002 ",
+        "MSRValue": "0x043C000002",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_MISS.SNOOP_HIT_NO_FWD",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "DEMAND_RFO & L3_MISS & SNOOP_HIT_NO_FWD",
+        "BriefDescription": "Counts all demand data writes (RFOs)",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all demand code reads",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x2000020004 ",
+        "MSRValue": "0x2000020004",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.SUPPLIER_NONE.SNOOP_NON_DRAM",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "DEMAND_CODE_RD & SUPPLIER_NONE & SNOOP_NON_DRAM",
+        "BriefDescription": "Counts all demand code reads",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "Counts all demand code reads that hit in the L3 and the target was non-DRAM system address. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all demand code reads",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x20003c0004 ",
+        "MSRValue": "0x20003C0004",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_HIT.SNOOP_NON_DRAM",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "Counts all demand code reads that hit in the L3 and the target was non-DRAM system address.",
+        "BriefDescription": "Counts all demand code reads",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all demand code reads",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0084000004 ",
+        "MSRValue": "0x0084000004",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_MISS_LOCAL_DRAM.SNOOP_NONE",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "DEMAND_CODE_RD & L3_MISS_LOCAL_DRAM & SNOOP_NONE",
+        "BriefDescription": "Counts all demand code reads",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all demand code reads",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0104000004 ",
+        "MSRValue": "0x0104000004",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_MISS_LOCAL_DRAM.SNOOP_NOT_NEEDED",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "DEMAND_CODE_RD & L3_MISS_LOCAL_DRAM & SNOOP_NOT_NEEDED",
+        "BriefDescription": "Counts all demand code reads",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all demand code reads",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0204000004 ",
+        "MSRValue": "0x0204000004",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_MISS_LOCAL_DRAM.SNOOP_MISS",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "DEMAND_CODE_RD & L3_MISS_LOCAL_DRAM & SNOOP_MISS",
+        "BriefDescription": "Counts all demand code reads",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all demand code reads",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0404000004 ",
+        "MSRValue": "0x0404000004",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_MISS_LOCAL_DRAM.SNOOP_HIT_NO_FWD",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "DEMAND_CODE_RD & L3_MISS_LOCAL_DRAM & SNOOP_HIT_NO_FWD",
+        "BriefDescription": "Counts all demand code reads",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all demand code reads",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x1004000004 ",
+        "MSRValue": "0x1004000004",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_MISS_LOCAL_DRAM.SNOOP_HITM",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "DEMAND_CODE_RD & L3_MISS_LOCAL_DRAM & SNOOP_HITM",
+        "BriefDescription": "Counts all demand code reads",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all demand code reads",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x2004000004 ",
+        "MSRValue": "0x2004000004",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_MISS_LOCAL_DRAM.SNOOP_NON_DRAM",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "DEMAND_CODE_RD & L3_MISS_LOCAL_DRAM & SNOOP_NON_DRAM",
+        "BriefDescription": "Counts all demand code reads",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all demand code reads",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x3f84000004 ",
+        "MSRValue": "0x3F84000004",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_MISS_LOCAL_DRAM.ANY_SNOOP",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "DEMAND_CODE_RD & L3_MISS_LOCAL_DRAM & ANY_SNOOP",
+        "BriefDescription": "Counts all demand code reads",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "Counts all demand code reads that miss the L3 with no details on snoop-related information. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all demand code reads",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x00bc000004 ",
+        "MSRValue": "0x00BC000004",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_MISS.SNOOP_NONE",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "Counts all demand code reads that miss the L3 with no details on snoop-related information.",
+        "BriefDescription": "Counts all demand code reads",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all demand code reads",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x013c000004 ",
+        "MSRValue": "0x013C000004",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_MISS.SNOOP_NOT_NEEDED",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "DEMAND_CODE_RD & L3_MISS & SNOOP_NOT_NEEDED",
+        "BriefDescription": "Counts all demand code reads",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "Counts all demand code reads that miss the L3 with a snoop miss response. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all demand code reads",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x023c000004 ",
+        "MSRValue": "0x023C000004",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_MISS.SNOOP_MISS",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "Counts all demand code reads that miss the L3 with a snoop miss response.",
+        "BriefDescription": "Counts all demand code reads",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all demand code reads",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x043c000004 ",
+        "MSRValue": "0x043C000004",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_MISS.SNOOP_HIT_NO_FWD",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "DEMAND_CODE_RD & L3_MISS & SNOOP_HIT_NO_FWD",
+        "BriefDescription": "Counts all demand code reads",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts writebacks (modified to exclusive)",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x2000020008 ",
+        "MSRValue": "0x2000020008",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.COREWB.SUPPLIER_NONE.SNOOP_NON_DRAM",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "COREWB & SUPPLIER_NONE & SNOOP_NON_DRAM",
+        "BriefDescription": "Counts writebacks (modified to exclusive)",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "Counts writebacks (modified to exclusive) that hit in the L3 and the target was non-DRAM system address. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts writebacks (modified to exclusive)",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x20003c0008 ",
+        "MSRValue": "0x20003C0008",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.COREWB.L3_HIT.SNOOP_NON_DRAM",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "Counts writebacks (modified to exclusive) that hit in the L3 and the target was non-DRAM system address.",
+        "BriefDescription": "Counts writebacks (modified to exclusive)",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts writebacks (modified to exclusive)",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0084000008 ",
+        "MSRValue": "0x0084000008",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.COREWB.L3_MISS_LOCAL_DRAM.SNOOP_NONE",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "COREWB & L3_MISS_LOCAL_DRAM & SNOOP_NONE",
+        "BriefDescription": "Counts writebacks (modified to exclusive)",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts writebacks (modified to exclusive)",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0104000008 ",
+        "MSRValue": "0x0104000008",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.COREWB.L3_MISS_LOCAL_DRAM.SNOOP_NOT_NEEDED",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "COREWB & L3_MISS_LOCAL_DRAM & SNOOP_NOT_NEEDED",
+        "BriefDescription": "Counts writebacks (modified to exclusive)",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts writebacks (modified to exclusive)",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0204000008 ",
+        "MSRValue": "0x0204000008",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.COREWB.L3_MISS_LOCAL_DRAM.SNOOP_MISS",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "COREWB & L3_MISS_LOCAL_DRAM & SNOOP_MISS",
+        "BriefDescription": "Counts writebacks (modified to exclusive)",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts writebacks (modified to exclusive)",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0404000008 ",
+        "MSRValue": "0x0404000008",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.COREWB.L3_MISS_LOCAL_DRAM.SNOOP_HIT_NO_FWD",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "COREWB & L3_MISS_LOCAL_DRAM & SNOOP_HIT_NO_FWD",
+        "BriefDescription": "Counts writebacks (modified to exclusive)",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts writebacks (modified to exclusive)",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x1004000008 ",
+        "MSRValue": "0x1004000008",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.COREWB.L3_MISS_LOCAL_DRAM.SNOOP_HITM",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "COREWB & L3_MISS_LOCAL_DRAM & SNOOP_HITM",
+        "BriefDescription": "Counts writebacks (modified to exclusive)",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts writebacks (modified to exclusive)",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x2004000008 ",
+        "MSRValue": "0x2004000008",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.COREWB.L3_MISS_LOCAL_DRAM.SNOOP_NON_DRAM",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "COREWB & L3_MISS_LOCAL_DRAM & SNOOP_NON_DRAM",
+        "BriefDescription": "Counts writebacks (modified to exclusive)",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts writebacks (modified to exclusive)",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x3f84000008 ",
+        "MSRValue": "0x3F84000008",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.COREWB.L3_MISS_LOCAL_DRAM.ANY_SNOOP",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "COREWB & L3_MISS_LOCAL_DRAM & ANY_SNOOP",
+        "BriefDescription": "Counts writebacks (modified to exclusive)",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "Counts writebacks (modified to exclusive) that miss the L3 with no details on snoop-related information. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts writebacks (modified to exclusive)",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x00bc000008 ",
+        "MSRValue": "0x00BC000008",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.COREWB.L3_MISS.SNOOP_NONE",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "Counts writebacks (modified to exclusive) that miss the L3 with no details on snoop-related information.",
+        "BriefDescription": "Counts writebacks (modified to exclusive)",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts writebacks (modified to exclusive)",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x013c000008 ",
+        "MSRValue": "0x013C000008",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.COREWB.L3_MISS.SNOOP_NOT_NEEDED",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "COREWB & L3_MISS & SNOOP_NOT_NEEDED",
+        "BriefDescription": "Counts writebacks (modified to exclusive)",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "Counts writebacks (modified to exclusive) that miss the L3 with a snoop miss response. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts writebacks (modified to exclusive)",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x023c000008 ",
+        "MSRValue": "0x023C000008",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.COREWB.L3_MISS.SNOOP_MISS",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "Counts writebacks (modified to exclusive) that miss the L3 with a snoop miss response.",
+        "BriefDescription": "Counts writebacks (modified to exclusive)",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts writebacks (modified to exclusive)",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x043c000008 ",
+        "MSRValue": "0x043C000008",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.COREWB.L3_MISS.SNOOP_HIT_NO_FWD",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "COREWB & L3_MISS & SNOOP_HIT_NO_FWD",
+        "BriefDescription": "Counts writebacks (modified to exclusive)",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts prefetch (that bring data to L2) data reads",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x2000020010 ",
+        "MSRValue": "0x2000020010",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.PF_L2_DATA_RD.SUPPLIER_NONE.SNOOP_NON_DRAM",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "PF_L2_DATA_RD & SUPPLIER_NONE & SNOOP_NON_DRAM",
+        "BriefDescription": "Counts prefetch (that bring data to L2) data reads",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "Counts prefetch (that bring data to L2) data reads that hit in the L3 and the target was non-DRAM system address. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts prefetch (that bring data to L2) data reads",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x20003c0010 ",
+        "MSRValue": "0x20003C0010",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.PF_L2_DATA_RD.L3_HIT.SNOOP_NON_DRAM",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "Counts prefetch (that bring data to L2) data reads that hit in the L3 and the target was non-DRAM system address.",
+        "BriefDescription": "Counts prefetch (that bring data to L2) data reads",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts prefetch (that bring data to L2) data reads",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0084000010 ",
+        "MSRValue": "0x0084000010",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.PF_L2_DATA_RD.L3_MISS_LOCAL_DRAM.SNOOP_NONE",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "PF_L2_DATA_RD & L3_MISS_LOCAL_DRAM & SNOOP_NONE",
+        "BriefDescription": "Counts prefetch (that bring data to L2) data reads",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts prefetch (that bring data to L2) data reads",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0104000010 ",
+        "MSRValue": "0x0104000010",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.PF_L2_DATA_RD.L3_MISS_LOCAL_DRAM.SNOOP_NOT_NEEDED",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "PF_L2_DATA_RD & L3_MISS_LOCAL_DRAM & SNOOP_NOT_NEEDED",
+        "BriefDescription": "Counts prefetch (that bring data to L2) data reads",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts prefetch (that bring data to L2) data reads",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0204000010 ",
+        "MSRValue": "0x0204000010",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.PF_L2_DATA_RD.L3_MISS_LOCAL_DRAM.SNOOP_MISS",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "PF_L2_DATA_RD & L3_MISS_LOCAL_DRAM & SNOOP_MISS",
+        "BriefDescription": "Counts prefetch (that bring data to L2) data reads",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts prefetch (that bring data to L2) data reads",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0404000010 ",
+        "MSRValue": "0x0404000010",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.PF_L2_DATA_RD.L3_MISS_LOCAL_DRAM.SNOOP_HIT_NO_FWD",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "PF_L2_DATA_RD & L3_MISS_LOCAL_DRAM & SNOOP_HIT_NO_FWD",
+        "BriefDescription": "Counts prefetch (that bring data to L2) data reads",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts prefetch (that bring data to L2) data reads",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x1004000010 ",
+        "MSRValue": "0x1004000010",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.PF_L2_DATA_RD.L3_MISS_LOCAL_DRAM.SNOOP_HITM",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "PF_L2_DATA_RD & L3_MISS_LOCAL_DRAM & SNOOP_HITM",
+        "BriefDescription": "Counts prefetch (that bring data to L2) data reads",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts prefetch (that bring data to L2) data reads",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x2004000010 ",
+        "MSRValue": "0x2004000010",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.PF_L2_DATA_RD.L3_MISS_LOCAL_DRAM.SNOOP_NON_DRAM",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "PF_L2_DATA_RD & L3_MISS_LOCAL_DRAM & SNOOP_NON_DRAM",
+        "BriefDescription": "Counts prefetch (that bring data to L2) data reads",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts prefetch (that bring data to L2) data reads",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x3f84000010 ",
+        "MSRValue": "0x3F84000010",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.PF_L2_DATA_RD.L3_MISS_LOCAL_DRAM.ANY_SNOOP",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "PF_L2_DATA_RD & L3_MISS_LOCAL_DRAM & ANY_SNOOP",
+        "BriefDescription": "Counts prefetch (that bring data to L2) data reads",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "Counts prefetch (that bring data to L2) data reads that miss the L3 with no details on snoop-related information. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts prefetch (that bring data to L2) data reads",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x00bc000010 ",
+        "MSRValue": "0x00BC000010",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.PF_L2_DATA_RD.L3_MISS.SNOOP_NONE",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "Counts prefetch (that bring data to L2) data reads that miss the L3 with no details on snoop-related information.",
+        "BriefDescription": "Counts prefetch (that bring data to L2) data reads",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts prefetch (that bring data to L2) data reads",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x013c000010 ",
+        "MSRValue": "0x013C000010",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.PF_L2_DATA_RD.L3_MISS.SNOOP_NOT_NEEDED",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "PF_L2_DATA_RD & L3_MISS & SNOOP_NOT_NEEDED",
+        "BriefDescription": "Counts prefetch (that bring data to L2) data reads",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "Counts prefetch (that bring data to L2) data reads that miss the L3 with a snoop miss response. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts prefetch (that bring data to L2) data reads",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x023c000010 ",
+        "MSRValue": "0x023C000010",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.PF_L2_DATA_RD.L3_MISS.SNOOP_MISS",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "Counts prefetch (that bring data to L2) data reads that miss the L3 with a snoop miss response.",
+        "BriefDescription": "Counts prefetch (that bring data to L2) data reads",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts prefetch (that bring data to L2) data reads",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x043c000010 ",
+        "MSRValue": "0x043C000010",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.PF_L2_DATA_RD.L3_MISS.SNOOP_HIT_NO_FWD",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "PF_L2_DATA_RD & L3_MISS & SNOOP_HIT_NO_FWD",
+        "BriefDescription": "Counts prefetch (that bring data to L2) data reads",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all prefetch (that bring data to L2) RFOs",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x2000020020 ",
+        "MSRValue": "0x2000020020",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.PF_L2_RFO.SUPPLIER_NONE.SNOOP_NON_DRAM",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "PF_L2_RFO & SUPPLIER_NONE & SNOOP_NON_DRAM",
+        "BriefDescription": "Counts all prefetch (that bring data to L2) RFOs",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "Counts all prefetch (that bring data to L2) RFOs that hit in the L3 and the target was non-DRAM system address. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all prefetch (that bring data to L2) RFOs",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x20003c0020 ",
+        "MSRValue": "0x20003C0020",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.PF_L2_RFO.L3_HIT.SNOOP_NON_DRAM",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "Counts all prefetch (that bring data to L2) RFOs that hit in the L3 and the target was non-DRAM system address.",
+        "BriefDescription": "Counts all prefetch (that bring data to L2) RFOs",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all prefetch (that bring data to L2) RFOs",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0084000020 ",
+        "MSRValue": "0x0084000020",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.PF_L2_RFO.L3_MISS_LOCAL_DRAM.SNOOP_NONE",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "PF_L2_RFO & L3_MISS_LOCAL_DRAM & SNOOP_NONE",
+        "BriefDescription": "Counts all prefetch (that bring data to L2) RFOs",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all prefetch (that bring data to L2) RFOs",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0104000020 ",
+        "MSRValue": "0x0104000020",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.PF_L2_RFO.L3_MISS_LOCAL_DRAM.SNOOP_NOT_NEEDED",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "PF_L2_RFO & L3_MISS_LOCAL_DRAM & SNOOP_NOT_NEEDED",
+        "BriefDescription": "Counts all prefetch (that bring data to L2) RFOs",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all prefetch (that bring data to L2) RFOs",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0204000020 ",
+        "MSRValue": "0x0204000020",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.PF_L2_RFO.L3_MISS_LOCAL_DRAM.SNOOP_MISS",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "PF_L2_RFO & L3_MISS_LOCAL_DRAM & SNOOP_MISS",
+        "BriefDescription": "Counts all prefetch (that bring data to L2) RFOs",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all prefetch (that bring data to L2) RFOs",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0404000020 ",
+        "MSRValue": "0x0404000020",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.PF_L2_RFO.L3_MISS_LOCAL_DRAM.SNOOP_HIT_NO_FWD",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "PF_L2_RFO & L3_MISS_LOCAL_DRAM & SNOOP_HIT_NO_FWD",
+        "BriefDescription": "Counts all prefetch (that bring data to L2) RFOs",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all prefetch (that bring data to L2) RFOs",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x1004000020 ",
+        "MSRValue": "0x1004000020",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.PF_L2_RFO.L3_MISS_LOCAL_DRAM.SNOOP_HITM",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "PF_L2_RFO & L3_MISS_LOCAL_DRAM & SNOOP_HITM",
+        "BriefDescription": "Counts all prefetch (that bring data to L2) RFOs",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all prefetch (that bring data to L2) RFOs",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x2004000020 ",
+        "MSRValue": "0x2004000020",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.PF_L2_RFO.L3_MISS_LOCAL_DRAM.SNOOP_NON_DRAM",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "PF_L2_RFO & L3_MISS_LOCAL_DRAM & SNOOP_NON_DRAM",
+        "BriefDescription": "Counts all prefetch (that bring data to L2) RFOs",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all prefetch (that bring data to L2) RFOs",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x3f84000020 ",
+        "MSRValue": "0x3F84000020",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.PF_L2_RFO.L3_MISS_LOCAL_DRAM.ANY_SNOOP",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "PF_L2_RFO & L3_MISS_LOCAL_DRAM & ANY_SNOOP",
+        "BriefDescription": "Counts all prefetch (that bring data to L2) RFOs",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "Counts all prefetch (that bring data to L2) RFOs that miss the L3 with no details on snoop-related information. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all prefetch (that bring data to L2) RFOs",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x00bc000020 ",
+        "MSRValue": "0x00BC000020",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.PF_L2_RFO.L3_MISS.SNOOP_NONE",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "Counts all prefetch (that bring data to L2) RFOs that miss the L3 with no details on snoop-related information.",
+        "BriefDescription": "Counts all prefetch (that bring data to L2) RFOs",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all prefetch (that bring data to L2) RFOs",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x013c000020 ",
+        "MSRValue": "0x013C000020",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.PF_L2_RFO.L3_MISS.SNOOP_NOT_NEEDED",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "PF_L2_RFO & L3_MISS & SNOOP_NOT_NEEDED",
+        "BriefDescription": "Counts all prefetch (that bring data to L2) RFOs",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "Counts all prefetch (that bring data to L2) RFOs that miss the L3 with a snoop miss response. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all prefetch (that bring data to L2) RFOs",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x023c000020 ",
+        "MSRValue": "0x023C000020",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.PF_L2_RFO.L3_MISS.SNOOP_MISS",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "Counts all prefetch (that bring data to L2) RFOs that miss the L3 with a snoop miss response.",
+        "BriefDescription": "Counts all prefetch (that bring data to L2) RFOs",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all prefetch (that bring data to L2) RFOs",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x043c000020 ",
+        "MSRValue": "0x043C000020",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.PF_L2_RFO.L3_MISS.SNOOP_HIT_NO_FWD",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "PF_L2_RFO & L3_MISS & SNOOP_HIT_NO_FWD",
+        "BriefDescription": "Counts all prefetch (that bring data to L2) RFOs",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all prefetch (that bring data to LLC only) code reads",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x2000020040 ",
+        "MSRValue": "0x2000020040",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.PF_L2_CODE_RD.SUPPLIER_NONE.SNOOP_NON_DRAM",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "PF_L2_CODE_RD & SUPPLIER_NONE & SNOOP_NON_DRAM",
+        "BriefDescription": "Counts all prefetch (that bring data to LLC only) code reads",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "Counts all prefetch (that bring data to LLC only) code reads that hit in the L3 and the target was non-DRAM system address. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all prefetch (that bring data to LLC only) code reads",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x20003c0040 ",
+        "MSRValue": "0x20003C0040",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.PF_L2_CODE_RD.L3_HIT.SNOOP_NON_DRAM",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "Counts all prefetch (that bring data to LLC only) code reads that hit in the L3 and the target was non-DRAM system address.",
+        "BriefDescription": "Counts all prefetch (that bring data to LLC only) code reads",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all prefetch (that bring data to LLC only) code reads",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0084000040 ",
+        "MSRValue": "0x0084000040",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.PF_L2_CODE_RD.L3_MISS_LOCAL_DRAM.SNOOP_NONE",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "PF_L2_CODE_RD & L3_MISS_LOCAL_DRAM & SNOOP_NONE",
+        "BriefDescription": "Counts all prefetch (that bring data to LLC only) code reads",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all prefetch (that bring data to LLC only) code reads",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0104000040 ",
+        "MSRValue": "0x0104000040",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.PF_L2_CODE_RD.L3_MISS_LOCAL_DRAM.SNOOP_NOT_NEEDED",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "PF_L2_CODE_RD & L3_MISS_LOCAL_DRAM & SNOOP_NOT_NEEDED",
+        "BriefDescription": "Counts all prefetch (that bring data to LLC only) code reads",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all prefetch (that bring data to LLC only) code reads",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0204000040 ",
+        "MSRValue": "0x0204000040",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.PF_L2_CODE_RD.L3_MISS_LOCAL_DRAM.SNOOP_MISS",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "PF_L2_CODE_RD & L3_MISS_LOCAL_DRAM & SNOOP_MISS",
+        "BriefDescription": "Counts all prefetch (that bring data to LLC only) code reads",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all prefetch (that bring data to LLC only) code reads",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0404000040 ",
+        "MSRValue": "0x0404000040",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.PF_L2_CODE_RD.L3_MISS_LOCAL_DRAM.SNOOP_HIT_NO_FWD",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "PF_L2_CODE_RD & L3_MISS_LOCAL_DRAM & SNOOP_HIT_NO_FWD",
+        "BriefDescription": "Counts all prefetch (that bring data to LLC only) code reads",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all prefetch (that bring data to LLC only) code reads",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x1004000040 ",
+        "MSRValue": "0x1004000040",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.PF_L2_CODE_RD.L3_MISS_LOCAL_DRAM.SNOOP_HITM",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "PF_L2_CODE_RD & L3_MISS_LOCAL_DRAM & SNOOP_HITM",
+        "BriefDescription": "Counts all prefetch (that bring data to LLC only) code reads",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all prefetch (that bring data to LLC only) code reads",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x2004000040 ",
+        "MSRValue": "0x2004000040",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.PF_L2_CODE_RD.L3_MISS_LOCAL_DRAM.SNOOP_NON_DRAM",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "PF_L2_CODE_RD & L3_MISS_LOCAL_DRAM & SNOOP_NON_DRAM",
+        "BriefDescription": "Counts all prefetch (that bring data to LLC only) code reads",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all prefetch (that bring data to LLC only) code reads",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x3f84000040 ",
+        "MSRValue": "0x3F84000040",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.PF_L2_CODE_RD.L3_MISS_LOCAL_DRAM.ANY_SNOOP",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "PF_L2_CODE_RD & L3_MISS_LOCAL_DRAM & ANY_SNOOP",
+        "BriefDescription": "Counts all prefetch (that bring data to LLC only) code reads",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "Counts all prefetch (that bring data to LLC only) code reads that miss the L3 with no details on snoop-related information. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all prefetch (that bring data to LLC only) code reads",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x00bc000040 ",
+        "MSRValue": "0x00BC000040",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.PF_L2_CODE_RD.L3_MISS.SNOOP_NONE",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "Counts all prefetch (that bring data to LLC only) code reads that miss the L3 with no details on snoop-related information.",
+        "BriefDescription": "Counts all prefetch (that bring data to LLC only) code reads",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all prefetch (that bring data to LLC only) code reads",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x013c000040 ",
+        "MSRValue": "0x013C000040",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.PF_L2_CODE_RD.L3_MISS.SNOOP_NOT_NEEDED",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "PF_L2_CODE_RD & L3_MISS & SNOOP_NOT_NEEDED",
+        "BriefDescription": "Counts all prefetch (that bring data to LLC only) code reads",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "Counts all prefetch (that bring data to LLC only) code reads that miss the L3 with a snoop miss response. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all prefetch (that bring data to LLC only) code reads",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x023c000040 ",
+        "MSRValue": "0x023C000040",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.PF_L2_CODE_RD.L3_MISS.SNOOP_MISS",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "Counts all prefetch (that bring data to LLC only) code reads that miss the L3 with a snoop miss response.",
+        "BriefDescription": "Counts all prefetch (that bring data to LLC only) code reads",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all prefetch (that bring data to LLC only) code reads",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x043c000040 ",
+        "MSRValue": "0x043C000040",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.PF_L2_CODE_RD.L3_MISS.SNOOP_HIT_NO_FWD",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "PF_L2_CODE_RD & L3_MISS & SNOOP_HIT_NO_FWD",
+        "BriefDescription": "Counts all prefetch (that bring data to LLC only) code reads",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all prefetch (that bring data to LLC only) data reads",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x2000020080 ",
+        "MSRValue": "0x2000020080",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.PF_L3_DATA_RD.SUPPLIER_NONE.SNOOP_NON_DRAM",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "PF_L3_DATA_RD & SUPPLIER_NONE & SNOOP_NON_DRAM",
+        "BriefDescription": "Counts all prefetch (that bring data to LLC only) data reads",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "Counts all prefetch (that bring data to LLC only) data reads that hit in the L3 and the target was non-DRAM system address. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all prefetch (that bring data to LLC only) data reads",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x20003c0080 ",
+        "MSRValue": "0x20003C0080",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.PF_L3_DATA_RD.L3_HIT.SNOOP_NON_DRAM",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "Counts all prefetch (that bring data to LLC only) data reads that hit in the L3 and the target was non-DRAM system address.",
+        "BriefDescription": "Counts all prefetch (that bring data to LLC only) data reads",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all prefetch (that bring data to LLC only) data reads",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0084000080 ",
+        "MSRValue": "0x0084000080",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.PF_L3_DATA_RD.L3_MISS_LOCAL_DRAM.SNOOP_NONE",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "PF_L3_DATA_RD & L3_MISS_LOCAL_DRAM & SNOOP_NONE",
+        "BriefDescription": "Counts all prefetch (that bring data to LLC only) data reads",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all prefetch (that bring data to LLC only) data reads",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0104000080 ",
+        "MSRValue": "0x0104000080",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.PF_L3_DATA_RD.L3_MISS_LOCAL_DRAM.SNOOP_NOT_NEEDED",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "PF_L3_DATA_RD & L3_MISS_LOCAL_DRAM & SNOOP_NOT_NEEDED",
+        "BriefDescription": "Counts all prefetch (that bring data to LLC only) data reads",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all prefetch (that bring data to LLC only) data reads",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0204000080 ",
+        "MSRValue": "0x0204000080",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.PF_L3_DATA_RD.L3_MISS_LOCAL_DRAM.SNOOP_MISS",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "PF_L3_DATA_RD & L3_MISS_LOCAL_DRAM & SNOOP_MISS",
+        "BriefDescription": "Counts all prefetch (that bring data to LLC only) data reads",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all prefetch (that bring data to LLC only) data reads",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0404000080 ",
+        "MSRValue": "0x0404000080",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.PF_L3_DATA_RD.L3_MISS_LOCAL_DRAM.SNOOP_HIT_NO_FWD",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "PF_L3_DATA_RD & L3_MISS_LOCAL_DRAM & SNOOP_HIT_NO_FWD",
+        "BriefDescription": "Counts all prefetch (that bring data to LLC only) data reads",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all prefetch (that bring data to LLC only) data reads",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x1004000080 ",
+        "MSRValue": "0x1004000080",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.PF_L3_DATA_RD.L3_MISS_LOCAL_DRAM.SNOOP_HITM",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "PF_L3_DATA_RD & L3_MISS_LOCAL_DRAM & SNOOP_HITM",
+        "BriefDescription": "Counts all prefetch (that bring data to LLC only) data reads",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all prefetch (that bring data to LLC only) data reads",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x2004000080 ",
+        "MSRValue": "0x2004000080",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.PF_L3_DATA_RD.L3_MISS_LOCAL_DRAM.SNOOP_NON_DRAM",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "PF_L3_DATA_RD & L3_MISS_LOCAL_DRAM & SNOOP_NON_DRAM",
+        "BriefDescription": "Counts all prefetch (that bring data to LLC only) data reads",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all prefetch (that bring data to LLC only) data reads",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x3f84000080 ",
+        "MSRValue": "0x3F84000080",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.PF_L3_DATA_RD.L3_MISS_LOCAL_DRAM.ANY_SNOOP",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "PF_L3_DATA_RD & L3_MISS_LOCAL_DRAM & ANY_SNOOP",
+        "BriefDescription": "Counts all prefetch (that bring data to LLC only) data reads",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "Counts all prefetch (that bring data to LLC only) data reads that miss the L3 with no details on snoop-related information. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all prefetch (that bring data to LLC only) data reads",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x00bc000080 ",
+        "MSRValue": "0x00BC000080",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.PF_L3_DATA_RD.L3_MISS.SNOOP_NONE",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "Counts all prefetch (that bring data to LLC only) data reads that miss the L3 with no details on snoop-related information.",
+        "BriefDescription": "Counts all prefetch (that bring data to LLC only) data reads",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all prefetch (that bring data to LLC only) data reads",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x013c000080 ",
+        "MSRValue": "0x013C000080",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.PF_L3_DATA_RD.L3_MISS.SNOOP_NOT_NEEDED",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "PF_L3_DATA_RD & L3_MISS & SNOOP_NOT_NEEDED",
+        "BriefDescription": "Counts all prefetch (that bring data to LLC only) data reads",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "Counts all prefetch (that bring data to LLC only) data reads that miss the L3 with a snoop miss response. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all prefetch (that bring data to LLC only) data reads",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x023c000080 ",
+        "MSRValue": "0x023C000080",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.PF_L3_DATA_RD.L3_MISS.SNOOP_MISS",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "Counts all prefetch (that bring data to LLC only) data reads that miss the L3 with a snoop miss response.",
+        "BriefDescription": "Counts all prefetch (that bring data to LLC only) data reads",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all prefetch (that bring data to LLC only) data reads",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x043c000080 ",
+        "MSRValue": "0x043C000080",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.PF_L3_DATA_RD.L3_MISS.SNOOP_HIT_NO_FWD",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "PF_L3_DATA_RD & L3_MISS & SNOOP_HIT_NO_FWD",
+        "BriefDescription": "Counts all prefetch (that bring data to LLC only) data reads",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all prefetch (that bring data to LLC only) RFOs",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x2000020100 ",
+        "MSRValue": "0x2000020100",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.PF_L3_RFO.SUPPLIER_NONE.SNOOP_NON_DRAM",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "PF_L3_RFO & SUPPLIER_NONE & SNOOP_NON_DRAM",
+        "BriefDescription": "Counts all prefetch (that bring data to LLC only) RFOs",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "Counts all prefetch (that bring data to LLC only) RFOs that hit in the L3 and the target was non-DRAM system address. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all prefetch (that bring data to LLC only) RFOs",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x20003c0100 ",
+        "MSRValue": "0x20003C0100",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.PF_L3_RFO.L3_HIT.SNOOP_NON_DRAM",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "Counts all prefetch (that bring data to LLC only) RFOs that hit in the L3 and the target was non-DRAM system address.",
+        "BriefDescription": "Counts all prefetch (that bring data to LLC only) RFOs",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all prefetch (that bring data to LLC only) RFOs",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0084000100 ",
+        "MSRValue": "0x0084000100",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.PF_L3_RFO.L3_MISS_LOCAL_DRAM.SNOOP_NONE",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "PF_L3_RFO & L3_MISS_LOCAL_DRAM & SNOOP_NONE",
+        "BriefDescription": "Counts all prefetch (that bring data to LLC only) RFOs",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all prefetch (that bring data to LLC only) RFOs",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0104000100 ",
+        "MSRValue": "0x0104000100",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.PF_L3_RFO.L3_MISS_LOCAL_DRAM.SNOOP_NOT_NEEDED",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "PF_L3_RFO & L3_MISS_LOCAL_DRAM & SNOOP_NOT_NEEDED",
+        "BriefDescription": "Counts all prefetch (that bring data to LLC only) RFOs",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all prefetch (that bring data to LLC only) RFOs",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0204000100 ",
+        "MSRValue": "0x0204000100",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.PF_L3_RFO.L3_MISS_LOCAL_DRAM.SNOOP_MISS",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "PF_L3_RFO & L3_MISS_LOCAL_DRAM & SNOOP_MISS",
+        "BriefDescription": "Counts all prefetch (that bring data to LLC only) RFOs",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all prefetch (that bring data to LLC only) RFOs",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0404000100 ",
+        "MSRValue": "0x0404000100",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.PF_L3_RFO.L3_MISS_LOCAL_DRAM.SNOOP_HIT_NO_FWD",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "PF_L3_RFO & L3_MISS_LOCAL_DRAM & SNOOP_HIT_NO_FWD",
+        "BriefDescription": "Counts all prefetch (that bring data to LLC only) RFOs",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all prefetch (that bring data to LLC only) RFOs",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x1004000100 ",
+        "MSRValue": "0x1004000100",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.PF_L3_RFO.L3_MISS_LOCAL_DRAM.SNOOP_HITM",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "PF_L3_RFO & L3_MISS_LOCAL_DRAM & SNOOP_HITM",
+        "BriefDescription": "Counts all prefetch (that bring data to LLC only) RFOs",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all prefetch (that bring data to LLC only) RFOs",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x2004000100 ",
+        "MSRValue": "0x2004000100",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.PF_L3_RFO.L3_MISS_LOCAL_DRAM.SNOOP_NON_DRAM",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "PF_L3_RFO & L3_MISS_LOCAL_DRAM & SNOOP_NON_DRAM",
+        "BriefDescription": "Counts all prefetch (that bring data to LLC only) RFOs",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all prefetch (that bring data to LLC only) RFOs",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x3f84000100 ",
+        "MSRValue": "0x3F84000100",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.PF_L3_RFO.L3_MISS_LOCAL_DRAM.ANY_SNOOP",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "PF_L3_RFO & L3_MISS_LOCAL_DRAM & ANY_SNOOP",
+        "BriefDescription": "Counts all prefetch (that bring data to LLC only) RFOs",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "Counts all prefetch (that bring data to LLC only) RFOs that miss the L3 with no details on snoop-related information. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all prefetch (that bring data to LLC only) RFOs",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x00bc000100 ",
+        "MSRValue": "0x00BC000100",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.PF_L3_RFO.L3_MISS.SNOOP_NONE",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "Counts all prefetch (that bring data to LLC only) RFOs that miss the L3 with no details on snoop-related information.",
+        "BriefDescription": "Counts all prefetch (that bring data to LLC only) RFOs",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all prefetch (that bring data to LLC only) RFOs",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x013c000100 ",
+        "MSRValue": "0x013C000100",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.PF_L3_RFO.L3_MISS.SNOOP_NOT_NEEDED",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "PF_L3_RFO & L3_MISS & SNOOP_NOT_NEEDED",
+        "BriefDescription": "Counts all prefetch (that bring data to LLC only) RFOs",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "Counts all prefetch (that bring data to LLC only) RFOs that miss the L3 with a snoop miss response. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all prefetch (that bring data to LLC only) RFOs",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x023c000100 ",
+        "MSRValue": "0x023C000100",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.PF_L3_RFO.L3_MISS.SNOOP_MISS",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "Counts all prefetch (that bring data to LLC only) RFOs that miss the L3 with a snoop miss response.",
+        "BriefDescription": "Counts all prefetch (that bring data to LLC only) RFOs",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all prefetch (that bring data to LLC only) RFOs",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x043c000100 ",
+        "MSRValue": "0x043C000100",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.PF_L3_RFO.L3_MISS.SNOOP_HIT_NO_FWD",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "PF_L3_RFO & L3_MISS & SNOOP_HIT_NO_FWD",
+        "BriefDescription": "Counts all prefetch (that bring data to LLC only) RFOs",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts prefetch (that bring data to LLC only) code reads",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x2000020200 ",
+        "MSRValue": "0x2000020200",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.PF_L3_CODE_RD.SUPPLIER_NONE.SNOOP_NON_DRAM",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "PF_L3_CODE_RD & SUPPLIER_NONE & SNOOP_NON_DRAM",
+        "BriefDescription": "Counts prefetch (that bring data to LLC only) code reads",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "Counts prefetch (that bring data to LLC only) code reads that hit in the L3 and the target was non-DRAM system address. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts prefetch (that bring data to LLC only) code reads",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x20003c0200 ",
+        "MSRValue": "0x20003C0200",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.PF_L3_CODE_RD.L3_HIT.SNOOP_NON_DRAM",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "Counts prefetch (that bring data to LLC only) code reads that hit in the L3 and the target was non-DRAM system address.",
+        "BriefDescription": "Counts prefetch (that bring data to LLC only) code reads",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts prefetch (that bring data to LLC only) code reads",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0084000200 ",
+        "MSRValue": "0x0084000200",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.PF_L3_CODE_RD.L3_MISS_LOCAL_DRAM.SNOOP_NONE",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "PF_L3_CODE_RD & L3_MISS_LOCAL_DRAM & SNOOP_NONE",
+        "BriefDescription": "Counts prefetch (that bring data to LLC only) code reads",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts prefetch (that bring data to LLC only) code reads",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0104000200 ",
+        "MSRValue": "0x0104000200",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.PF_L3_CODE_RD.L3_MISS_LOCAL_DRAM.SNOOP_NOT_NEEDED",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "PF_L3_CODE_RD & L3_MISS_LOCAL_DRAM & SNOOP_NOT_NEEDED",
+        "BriefDescription": "Counts prefetch (that bring data to LLC only) code reads",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts prefetch (that bring data to LLC only) code reads",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0204000200 ",
+        "MSRValue": "0x0204000200",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.PF_L3_CODE_RD.L3_MISS_LOCAL_DRAM.SNOOP_MISS",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "PF_L3_CODE_RD & L3_MISS_LOCAL_DRAM & SNOOP_MISS",
+        "BriefDescription": "Counts prefetch (that bring data to LLC only) code reads",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts prefetch (that bring data to LLC only) code reads",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0404000200 ",
+        "MSRValue": "0x0404000200",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.PF_L3_CODE_RD.L3_MISS_LOCAL_DRAM.SNOOP_HIT_NO_FWD",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "PF_L3_CODE_RD & L3_MISS_LOCAL_DRAM & SNOOP_HIT_NO_FWD",
+        "BriefDescription": "Counts prefetch (that bring data to LLC only) code reads",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts prefetch (that bring data to LLC only) code reads",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x1004000200 ",
+        "MSRValue": "0x1004000200",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.PF_L3_CODE_RD.L3_MISS_LOCAL_DRAM.SNOOP_HITM",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "PF_L3_CODE_RD & L3_MISS_LOCAL_DRAM & SNOOP_HITM",
+        "BriefDescription": "Counts prefetch (that bring data to LLC only) code reads",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts prefetch (that bring data to LLC only) code reads",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x2004000200 ",
+        "MSRValue": "0x2004000200",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.PF_L3_CODE_RD.L3_MISS_LOCAL_DRAM.SNOOP_NON_DRAM",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "PF_L3_CODE_RD & L3_MISS_LOCAL_DRAM & SNOOP_NON_DRAM",
+        "BriefDescription": "Counts prefetch (that bring data to LLC only) code reads",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts prefetch (that bring data to LLC only) code reads",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x3f84000200 ",
+        "MSRValue": "0x3F84000200",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.PF_L3_CODE_RD.L3_MISS_LOCAL_DRAM.ANY_SNOOP",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "PF_L3_CODE_RD & L3_MISS_LOCAL_DRAM & ANY_SNOOP",
+        "BriefDescription": "Counts prefetch (that bring data to LLC only) code reads",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "Counts prefetch (that bring data to LLC only) code reads that miss the L3 with no details on snoop-related information. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts prefetch (that bring data to LLC only) code reads",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x00bc000200 ",
+        "MSRValue": "0x00BC000200",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.PF_L3_CODE_RD.L3_MISS.SNOOP_NONE",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "Counts prefetch (that bring data to LLC only) code reads that miss the L3 with no details on snoop-related information.",
+        "BriefDescription": "Counts prefetch (that bring data to LLC only) code reads",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts prefetch (that bring data to LLC only) code reads",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x013c000200 ",
+        "MSRValue": "0x013C000200",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.PF_L3_CODE_RD.L3_MISS.SNOOP_NOT_NEEDED",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "PF_L3_CODE_RD & L3_MISS & SNOOP_NOT_NEEDED",
+        "BriefDescription": "Counts prefetch (that bring data to LLC only) code reads",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "Counts prefetch (that bring data to LLC only) code reads that miss the L3 with a snoop miss response. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts prefetch (that bring data to LLC only) code reads",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x023c000200 ",
+        "MSRValue": "0x023C000200",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.PF_L3_CODE_RD.L3_MISS.SNOOP_MISS",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "Counts prefetch (that bring data to LLC only) code reads that miss the L3 with a snoop miss response.",
+        "BriefDescription": "Counts prefetch (that bring data to LLC only) code reads",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts prefetch (that bring data to LLC only) code reads",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x043c000200 ",
+        "MSRValue": "0x043C000200",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.PF_L3_CODE_RD.L3_MISS.SNOOP_HIT_NO_FWD",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "PF_L3_CODE_RD & L3_MISS & SNOOP_HIT_NO_FWD",
+        "BriefDescription": "Counts prefetch (that bring data to LLC only) code reads",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts any other requests",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x2000028000 ",
+        "MSRValue": "0x2000028000",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.OTHER.SUPPLIER_NONE.SNOOP_NON_DRAM",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "OTHER & SUPPLIER_NONE & SNOOP_NON_DRAM",
+        "BriefDescription": "Counts any other requests",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "Counts any other requests that hit in the L3 and the target was non-DRAM system address. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts any other requests",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x20003c8000 ",
+        "MSRValue": "0x20003C8000",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.OTHER.L3_HIT.SNOOP_NON_DRAM",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "Counts any other requests that hit in the L3 and the target was non-DRAM system address.",
+        "BriefDescription": "Counts any other requests",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts any other requests",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0084008000 ",
+        "MSRValue": "0x0084008000",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.OTHER.L3_MISS_LOCAL_DRAM.SNOOP_NONE",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "OTHER & L3_MISS_LOCAL_DRAM & SNOOP_NONE",
+        "BriefDescription": "Counts any other requests",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts any other requests",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0104008000 ",
+        "MSRValue": "0x0104008000",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.OTHER.L3_MISS_LOCAL_DRAM.SNOOP_NOT_NEEDED",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "OTHER & L3_MISS_LOCAL_DRAM & SNOOP_NOT_NEEDED",
+        "BriefDescription": "Counts any other requests",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts any other requests",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0204008000 ",
+        "MSRValue": "0x0204008000",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.OTHER.L3_MISS_LOCAL_DRAM.SNOOP_MISS",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "OTHER & L3_MISS_LOCAL_DRAM & SNOOP_MISS",
+        "BriefDescription": "Counts any other requests",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts any other requests",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0404008000 ",
+        "MSRValue": "0x0404008000",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.OTHER.L3_MISS_LOCAL_DRAM.SNOOP_HIT_NO_FWD",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "OTHER & L3_MISS_LOCAL_DRAM & SNOOP_HIT_NO_FWD",
+        "BriefDescription": "Counts any other requests",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts any other requests",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x1004008000 ",
+        "MSRValue": "0x1004008000",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.OTHER.L3_MISS_LOCAL_DRAM.SNOOP_HITM",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "OTHER & L3_MISS_LOCAL_DRAM & SNOOP_HITM",
+        "BriefDescription": "Counts any other requests",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts any other requests",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x2004008000 ",
+        "MSRValue": "0x2004008000",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.OTHER.L3_MISS_LOCAL_DRAM.SNOOP_NON_DRAM",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "OTHER & L3_MISS_LOCAL_DRAM & SNOOP_NON_DRAM",
+        "BriefDescription": "Counts any other requests",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts any other requests",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x3f84008000 ",
+        "MSRValue": "0x3F84008000",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.OTHER.L3_MISS_LOCAL_DRAM.ANY_SNOOP",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "OTHER & L3_MISS_LOCAL_DRAM & ANY_SNOOP",
+        "BriefDescription": "Counts any other requests",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "Counts any other requests that miss the L3 with no details on snoop-related information. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts any other requests",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x00bc008000 ",
+        "MSRValue": "0x00BC008000",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.OTHER.L3_MISS.SNOOP_NONE",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "Counts any other requests that miss the L3 with no details on snoop-related information.",
+        "BriefDescription": "Counts any other requests",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts any other requests",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x013c008000 ",
+        "MSRValue": "0x013C008000",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.OTHER.L3_MISS.SNOOP_NOT_NEEDED",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "OTHER & L3_MISS & SNOOP_NOT_NEEDED",
+        "BriefDescription": "Counts any other requests",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "Counts any other requests that miss the L3 with a snoop miss response. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts any other requests",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x023c008000 ",
+        "MSRValue": "0x023C008000",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.OTHER.L3_MISS.SNOOP_MISS",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "Counts any other requests that miss the L3 with a snoop miss response.",
+        "BriefDescription": "Counts any other requests",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts any other requests",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x043c008000 ",
+        "MSRValue": "0x043C008000",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.OTHER.L3_MISS.SNOOP_HIT_NO_FWD",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "OTHER & L3_MISS & SNOOP_HIT_NO_FWD",
+        "BriefDescription": "Counts any other requests",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all prefetch data reads",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x2000020090 ",
+        "MSRValue": "0x2000020090",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.ALL_PF_DATA_RD.SUPPLIER_NONE.SNOOP_NON_DRAM",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "ALL_PF_DATA_RD & SUPPLIER_NONE & SNOOP_NON_DRAM",
+        "BriefDescription": "Counts all prefetch data reads",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "Counts all prefetch data reads that hit in the L3 and the target was non-DRAM system address. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all prefetch data reads",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x20003c0090 ",
+        "MSRValue": "0x20003C0090",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.ALL_PF_DATA_RD.L3_HIT.SNOOP_NON_DRAM",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "Counts all prefetch data reads that hit in the L3 and the target was non-DRAM system address.",
+        "BriefDescription": "Counts all prefetch data reads",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all prefetch data reads",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0084000090 ",
+        "MSRValue": "0x0084000090",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.ALL_PF_DATA_RD.L3_MISS_LOCAL_DRAM.SNOOP_NONE",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "ALL_PF_DATA_RD & L3_MISS_LOCAL_DRAM & SNOOP_NONE",
+        "BriefDescription": "Counts all prefetch data reads",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all prefetch data reads",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0104000090 ",
+        "MSRValue": "0x0104000090",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.ALL_PF_DATA_RD.L3_MISS_LOCAL_DRAM.SNOOP_NOT_NEEDED",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "ALL_PF_DATA_RD & L3_MISS_LOCAL_DRAM & SNOOP_NOT_NEEDED",
+        "BriefDescription": "Counts all prefetch data reads",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all prefetch data reads",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0204000090 ",
+        "MSRValue": "0x0204000090",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.ALL_PF_DATA_RD.L3_MISS_LOCAL_DRAM.SNOOP_MISS",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "ALL_PF_DATA_RD & L3_MISS_LOCAL_DRAM & SNOOP_MISS",
+        "BriefDescription": "Counts all prefetch data reads",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all prefetch data reads",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0404000090 ",
+        "MSRValue": "0x0404000090",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.ALL_PF_DATA_RD.L3_MISS_LOCAL_DRAM.SNOOP_HIT_NO_FWD",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "ALL_PF_DATA_RD & L3_MISS_LOCAL_DRAM & SNOOP_HIT_NO_FWD",
+        "BriefDescription": "Counts all prefetch data reads",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all prefetch data reads",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x1004000090 ",
+        "MSRValue": "0x1004000090",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.ALL_PF_DATA_RD.L3_MISS_LOCAL_DRAM.SNOOP_HITM",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "ALL_PF_DATA_RD & L3_MISS_LOCAL_DRAM & SNOOP_HITM",
+        "BriefDescription": "Counts all prefetch data reads",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all prefetch data reads",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x2004000090 ",
+        "MSRValue": "0x2004000090",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.ALL_PF_DATA_RD.L3_MISS_LOCAL_DRAM.SNOOP_NON_DRAM",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "ALL_PF_DATA_RD & L3_MISS_LOCAL_DRAM & SNOOP_NON_DRAM",
+        "BriefDescription": "Counts all prefetch data reads",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all prefetch data reads",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x3f84000090 ",
+        "MSRValue": "0x3F84000090",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.ALL_PF_DATA_RD.L3_MISS_LOCAL_DRAM.ANY_SNOOP",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "ALL_PF_DATA_RD & L3_MISS_LOCAL_DRAM & ANY_SNOOP",
+        "BriefDescription": "Counts all prefetch data reads",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "Counts all prefetch data reads that miss the L3 with no details on snoop-related information. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all prefetch data reads",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x00bc000090 ",
+        "MSRValue": "0x00BC000090",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.ALL_PF_DATA_RD.L3_MISS.SNOOP_NONE",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "Counts all prefetch data reads that miss the L3 with no details on snoop-related information.",
+        "BriefDescription": "Counts all prefetch data reads",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all prefetch data reads",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x013c000090 ",
+        "MSRValue": "0x013C000090",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.ALL_PF_DATA_RD.L3_MISS.SNOOP_NOT_NEEDED",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "ALL_PF_DATA_RD & L3_MISS & SNOOP_NOT_NEEDED",
+        "BriefDescription": "Counts all prefetch data reads",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "Counts all prefetch data reads that miss the L3 with a snoop miss response. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all prefetch data reads",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x023c000090 ",
+        "MSRValue": "0x023C000090",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.ALL_PF_DATA_RD.L3_MISS.SNOOP_MISS",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "Counts all prefetch data reads that miss the L3 with a snoop miss response.",
+        "BriefDescription": "Counts all prefetch data reads",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all prefetch data reads",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x043c000090 ",
+        "MSRValue": "0x043C000090",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.ALL_PF_DATA_RD.L3_MISS.SNOOP_HIT_NO_FWD",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "ALL_PF_DATA_RD & L3_MISS & SNOOP_HIT_NO_FWD",
+        "BriefDescription": "Counts all prefetch data reads",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts prefetch RFOs",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x2000020120 ",
+        "MSRValue": "0x2000020120",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.ALL_PF_RFO.SUPPLIER_NONE.SNOOP_NON_DRAM",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "ALL_PF_RFO & SUPPLIER_NONE & SNOOP_NON_DRAM",
+        "BriefDescription": "Counts prefetch RFOs",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "Counts prefetch RFOs that hit in the L3 and the target was non-DRAM system address. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts prefetch RFOs",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x20003c0120 ",
+        "MSRValue": "0x20003C0120",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.ALL_PF_RFO.L3_HIT.SNOOP_NON_DRAM",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "Counts prefetch RFOs that hit in the L3 and the target was non-DRAM system address.",
+        "BriefDescription": "Counts prefetch RFOs",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts prefetch RFOs",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0084000120 ",
+        "MSRValue": "0x0084000120",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.ALL_PF_RFO.L3_MISS_LOCAL_DRAM.SNOOP_NONE",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "ALL_PF_RFO & L3_MISS_LOCAL_DRAM & SNOOP_NONE",
+        "BriefDescription": "Counts prefetch RFOs",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts prefetch RFOs",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0104000120 ",
+        "MSRValue": "0x0104000120",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.ALL_PF_RFO.L3_MISS_LOCAL_DRAM.SNOOP_NOT_NEEDED",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "ALL_PF_RFO & L3_MISS_LOCAL_DRAM & SNOOP_NOT_NEEDED",
+        "BriefDescription": "Counts prefetch RFOs",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts prefetch RFOs",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0204000120 ",
+        "MSRValue": "0x0204000120",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.ALL_PF_RFO.L3_MISS_LOCAL_DRAM.SNOOP_MISS",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "ALL_PF_RFO & L3_MISS_LOCAL_DRAM & SNOOP_MISS",
+        "BriefDescription": "Counts prefetch RFOs",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts prefetch RFOs",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0404000120 ",
+        "MSRValue": "0x0404000120",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.ALL_PF_RFO.L3_MISS_LOCAL_DRAM.SNOOP_HIT_NO_FWD",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "ALL_PF_RFO & L3_MISS_LOCAL_DRAM & SNOOP_HIT_NO_FWD",
+        "BriefDescription": "Counts prefetch RFOs",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts prefetch RFOs",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x1004000120 ",
+        "MSRValue": "0x1004000120",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.ALL_PF_RFO.L3_MISS_LOCAL_DRAM.SNOOP_HITM",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "ALL_PF_RFO & L3_MISS_LOCAL_DRAM & SNOOP_HITM",
+        "BriefDescription": "Counts prefetch RFOs",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts prefetch RFOs",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x2004000120 ",
+        "MSRValue": "0x2004000120",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.ALL_PF_RFO.L3_MISS_LOCAL_DRAM.SNOOP_NON_DRAM",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "ALL_PF_RFO & L3_MISS_LOCAL_DRAM & SNOOP_NON_DRAM",
+        "BriefDescription": "Counts prefetch RFOs",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts prefetch RFOs",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x3f84000120 ",
+        "MSRValue": "0x3F84000120",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.ALL_PF_RFO.L3_MISS_LOCAL_DRAM.ANY_SNOOP",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "ALL_PF_RFO & L3_MISS_LOCAL_DRAM & ANY_SNOOP",
+        "BriefDescription": "Counts prefetch RFOs",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "Counts prefetch RFOs that miss the L3 with no details on snoop-related information. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts prefetch RFOs",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x00bc000120 ",
+        "MSRValue": "0x00BC000120",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.ALL_PF_RFO.L3_MISS.SNOOP_NONE",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "Counts prefetch RFOs that miss the L3 with no details on snoop-related information.",
+        "BriefDescription": "Counts prefetch RFOs",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts prefetch RFOs",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x013c000120 ",
+        "MSRValue": "0x013C000120",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.ALL_PF_RFO.L3_MISS.SNOOP_NOT_NEEDED",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "ALL_PF_RFO & L3_MISS & SNOOP_NOT_NEEDED",
+        "BriefDescription": "Counts prefetch RFOs",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "Counts prefetch RFOs that miss the L3 with a snoop miss response. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts prefetch RFOs",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x023c000120 ",
+        "MSRValue": "0x023C000120",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.ALL_PF_RFO.L3_MISS.SNOOP_MISS",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "Counts prefetch RFOs that miss the L3 with a snoop miss response.",
+        "BriefDescription": "Counts prefetch RFOs",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts prefetch RFOs",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x043c000120 ",
+        "MSRValue": "0x043C000120",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.ALL_PF_RFO.L3_MISS.SNOOP_HIT_NO_FWD",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "ALL_PF_RFO & L3_MISS & SNOOP_HIT_NO_FWD",
+        "BriefDescription": "Counts prefetch RFOs",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all prefetch code reads",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x2000020240 ",
+        "MSRValue": "0x2000020240",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.ALL_PF_CODE_RD.SUPPLIER_NONE.SNOOP_NON_DRAM",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "ALL_PF_CODE_RD & SUPPLIER_NONE & SNOOP_NON_DRAM",
+        "BriefDescription": "Counts all prefetch code reads",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "Counts all prefetch code reads that hit in the L3 and the target was non-DRAM system address. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all prefetch code reads",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x20003c0240 ",
+        "MSRValue": "0x20003C0240",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.ALL_PF_CODE_RD.L3_HIT.SNOOP_NON_DRAM",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "Counts all prefetch code reads that hit in the L3 and the target was non-DRAM system address.",
+        "BriefDescription": "Counts all prefetch code reads",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all prefetch code reads",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0084000240 ",
+        "MSRValue": "0x0084000240",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.ALL_PF_CODE_RD.L3_MISS_LOCAL_DRAM.SNOOP_NONE",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "ALL_PF_CODE_RD & L3_MISS_LOCAL_DRAM & SNOOP_NONE",
+        "BriefDescription": "Counts all prefetch code reads",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all prefetch code reads",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0104000240 ",
+        "MSRValue": "0x0104000240",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.ALL_PF_CODE_RD.L3_MISS_LOCAL_DRAM.SNOOP_NOT_NEEDED",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "ALL_PF_CODE_RD & L3_MISS_LOCAL_DRAM & SNOOP_NOT_NEEDED",
+        "BriefDescription": "Counts all prefetch code reads",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all prefetch code reads",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0204000240 ",
+        "MSRValue": "0x0204000240",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.ALL_PF_CODE_RD.L3_MISS_LOCAL_DRAM.SNOOP_MISS",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "ALL_PF_CODE_RD & L3_MISS_LOCAL_DRAM & SNOOP_MISS",
+        "BriefDescription": "Counts all prefetch code reads",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all prefetch code reads",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0404000240 ",
+        "MSRValue": "0x0404000240",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.ALL_PF_CODE_RD.L3_MISS_LOCAL_DRAM.SNOOP_HIT_NO_FWD",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "ALL_PF_CODE_RD & L3_MISS_LOCAL_DRAM & SNOOP_HIT_NO_FWD",
+        "BriefDescription": "Counts all prefetch code reads",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all prefetch code reads",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x1004000240 ",
+        "MSRValue": "0x1004000240",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.ALL_PF_CODE_RD.L3_MISS_LOCAL_DRAM.SNOOP_HITM",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "ALL_PF_CODE_RD & L3_MISS_LOCAL_DRAM & SNOOP_HITM",
+        "BriefDescription": "Counts all prefetch code reads",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all prefetch code reads",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x2004000240 ",
+        "MSRValue": "0x2004000240",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.ALL_PF_CODE_RD.L3_MISS_LOCAL_DRAM.SNOOP_NON_DRAM",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "ALL_PF_CODE_RD & L3_MISS_LOCAL_DRAM & SNOOP_NON_DRAM",
+        "BriefDescription": "Counts all prefetch code reads",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all prefetch code reads",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x3f84000240 ",
+        "MSRValue": "0x3F84000240",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.ALL_PF_CODE_RD.L3_MISS_LOCAL_DRAM.ANY_SNOOP",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "ALL_PF_CODE_RD & L3_MISS_LOCAL_DRAM & ANY_SNOOP",
+        "BriefDescription": "Counts all prefetch code reads",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "Counts all prefetch code reads that miss the L3 with no details on snoop-related information. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all prefetch code reads",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x00bc000240 ",
+        "MSRValue": "0x00BC000240",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.ALL_PF_CODE_RD.L3_MISS.SNOOP_NONE",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "Counts all prefetch code reads that miss the L3 with no details on snoop-related information.",
+        "BriefDescription": "Counts all prefetch code reads",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all prefetch code reads",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x013c000240 ",
+        "MSRValue": "0x013C000240",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.ALL_PF_CODE_RD.L3_MISS.SNOOP_NOT_NEEDED",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "ALL_PF_CODE_RD & L3_MISS & SNOOP_NOT_NEEDED",
+        "BriefDescription": "Counts all prefetch code reads",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "Counts all prefetch code reads that miss the L3 with a snoop miss response. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all prefetch code reads",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x023c000240 ",
+        "MSRValue": "0x023C000240",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.ALL_PF_CODE_RD.L3_MISS.SNOOP_MISS",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "Counts all prefetch code reads that miss the L3 with a snoop miss response.",
+        "BriefDescription": "Counts all prefetch code reads",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all prefetch code reads",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x043c000240 ",
+        "MSRValue": "0x043C000240",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.ALL_PF_CODE_RD.L3_MISS.SNOOP_HIT_NO_FWD",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "ALL_PF_CODE_RD & L3_MISS & SNOOP_HIT_NO_FWD",
+        "BriefDescription": "Counts all prefetch code reads",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all demand & prefetch data reads",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x2000020091 ",
+        "MSRValue": "0x2000020091",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.ALL_DATA_RD.SUPPLIER_NONE.SNOOP_NON_DRAM",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "ALL_DATA_RD & SUPPLIER_NONE & SNOOP_NON_DRAM",
+        "BriefDescription": "Counts all demand & prefetch data reads",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "Counts all demand & prefetch data reads that hit in the L3 and the target was non-DRAM system address. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all demand & prefetch data reads",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x20003c0091 ",
+        "MSRValue": "0x20003C0091",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.ALL_DATA_RD.L3_HIT.SNOOP_NON_DRAM",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "Counts all demand & prefetch data reads that hit in the L3 and the target was non-DRAM system address.",
+        "BriefDescription": "Counts all demand & prefetch data reads",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all demand & prefetch data reads",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0084000091 ",
+        "MSRValue": "0x0084000091",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.ALL_DATA_RD.L3_MISS_LOCAL_DRAM.SNOOP_NONE",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "ALL_DATA_RD & L3_MISS_LOCAL_DRAM & SNOOP_NONE",
+        "BriefDescription": "Counts all demand & prefetch data reads",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all demand & prefetch data reads",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0104000091 ",
+        "MSRValue": "0x0104000091",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.ALL_DATA_RD.L3_MISS_LOCAL_DRAM.SNOOP_NOT_NEEDED",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "ALL_DATA_RD & L3_MISS_LOCAL_DRAM & SNOOP_NOT_NEEDED",
+        "BriefDescription": "Counts all demand & prefetch data reads",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all demand & prefetch data reads",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0204000091 ",
+        "MSRValue": "0x0204000091",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.ALL_DATA_RD.L3_MISS_LOCAL_DRAM.SNOOP_MISS",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "ALL_DATA_RD & L3_MISS_LOCAL_DRAM & SNOOP_MISS",
+        "BriefDescription": "Counts all demand & prefetch data reads",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all demand & prefetch data reads",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0404000091 ",
+        "MSRValue": "0x0404000091",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.ALL_DATA_RD.L3_MISS_LOCAL_DRAM.SNOOP_HIT_NO_FWD",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "ALL_DATA_RD & L3_MISS_LOCAL_DRAM & SNOOP_HIT_NO_FWD",
+        "BriefDescription": "Counts all demand & prefetch data reads",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all demand & prefetch data reads",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x1004000091 ",
+        "MSRValue": "0x1004000091",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.ALL_DATA_RD.L3_MISS_LOCAL_DRAM.SNOOP_HITM",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "ALL_DATA_RD & L3_MISS_LOCAL_DRAM & SNOOP_HITM",
+        "BriefDescription": "Counts all demand & prefetch data reads",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all demand & prefetch data reads",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x2004000091 ",
+        "MSRValue": "0x2004000091",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.ALL_DATA_RD.L3_MISS_LOCAL_DRAM.SNOOP_NON_DRAM",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "ALL_DATA_RD & L3_MISS_LOCAL_DRAM & SNOOP_NON_DRAM",
+        "BriefDescription": "Counts all demand & prefetch data reads",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all demand & prefetch data reads",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x3f84000091 ",
+        "MSRValue": "0x3F84000091",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.ALL_DATA_RD.L3_MISS_LOCAL_DRAM.ANY_SNOOP",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "ALL_DATA_RD & L3_MISS_LOCAL_DRAM & ANY_SNOOP",
+        "BriefDescription": "Counts all demand & prefetch data reads",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "Counts all demand & prefetch data reads that miss the L3 with no details on snoop-related information. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all demand & prefetch data reads",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x00bc000091 ",
+        "MSRValue": "0x00BC000091",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.ALL_DATA_RD.L3_MISS.SNOOP_NONE",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "Counts all demand & prefetch data reads that miss the L3 with no details on snoop-related information.",
+        "BriefDescription": "Counts all demand & prefetch data reads",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all demand & prefetch data reads",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x013c000091 ",
+        "MSRValue": "0x013C000091",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.ALL_DATA_RD.L3_MISS.SNOOP_NOT_NEEDED",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "ALL_DATA_RD & L3_MISS & SNOOP_NOT_NEEDED",
+        "BriefDescription": "Counts all demand & prefetch data reads",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "Counts all demand & prefetch data reads that miss the L3 with a snoop miss response. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all demand & prefetch data reads",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x023c000091 ",
+        "MSRValue": "0x023C000091",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.ALL_DATA_RD.L3_MISS.SNOOP_MISS",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "Counts all demand & prefetch data reads that miss the L3 with a snoop miss response.",
+        "BriefDescription": "Counts all demand & prefetch data reads",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all demand & prefetch data reads",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x043c000091 ",
+        "MSRValue": "0x043C000091",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.ALL_DATA_RD.L3_MISS.SNOOP_HIT_NO_FWD",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "ALL_DATA_RD & L3_MISS & SNOOP_HIT_NO_FWD",
+        "BriefDescription": "Counts all demand & prefetch data reads",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all demand & prefetch RFOs",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x2000020122 ",
+        "MSRValue": "0x2000020122",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.ALL_RFO.SUPPLIER_NONE.SNOOP_NON_DRAM",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "ALL_RFO & SUPPLIER_NONE & SNOOP_NON_DRAM",
+        "BriefDescription": "Counts all demand & prefetch RFOs",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "Counts all demand & prefetch RFOs that hit in the L3 and the target was non-DRAM system address. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all demand & prefetch RFOs",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x20003c0122 ",
+        "MSRValue": "0x20003C0122",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.ALL_RFO.L3_HIT.SNOOP_NON_DRAM",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "Counts all demand & prefetch RFOs that hit in the L3 and the target was non-DRAM system address.",
+        "BriefDescription": "Counts all demand & prefetch RFOs",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all demand & prefetch RFOs",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0084000122 ",
+        "MSRValue": "0x0084000122",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.ALL_RFO.L3_MISS_LOCAL_DRAM.SNOOP_NONE",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "ALL_RFO & L3_MISS_LOCAL_DRAM & SNOOP_NONE",
+        "BriefDescription": "Counts all demand & prefetch RFOs",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all demand & prefetch RFOs",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0104000122 ",
+        "MSRValue": "0x0104000122",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.ALL_RFO.L3_MISS_LOCAL_DRAM.SNOOP_NOT_NEEDED",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "ALL_RFO & L3_MISS_LOCAL_DRAM & SNOOP_NOT_NEEDED",
+        "BriefDescription": "Counts all demand & prefetch RFOs",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all demand & prefetch RFOs",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0204000122 ",
+        "MSRValue": "0x0204000122",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.ALL_RFO.L3_MISS_LOCAL_DRAM.SNOOP_MISS",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "ALL_RFO & L3_MISS_LOCAL_DRAM & SNOOP_MISS",
+        "BriefDescription": "Counts all demand & prefetch RFOs",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all demand & prefetch RFOs",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0404000122 ",
+        "MSRValue": "0x0404000122",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.ALL_RFO.L3_MISS_LOCAL_DRAM.SNOOP_HIT_NO_FWD",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "ALL_RFO & L3_MISS_LOCAL_DRAM & SNOOP_HIT_NO_FWD",
+        "BriefDescription": "Counts all demand & prefetch RFOs",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all demand & prefetch RFOs",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x1004000122 ",
+        "MSRValue": "0x1004000122",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.ALL_RFO.L3_MISS_LOCAL_DRAM.SNOOP_HITM",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "ALL_RFO & L3_MISS_LOCAL_DRAM & SNOOP_HITM",
+        "BriefDescription": "Counts all demand & prefetch RFOs",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all demand & prefetch RFOs",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x2004000122 ",
+        "MSRValue": "0x2004000122",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.ALL_RFO.L3_MISS_LOCAL_DRAM.SNOOP_NON_DRAM",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "ALL_RFO & L3_MISS_LOCAL_DRAM & SNOOP_NON_DRAM",
+        "BriefDescription": "Counts all demand & prefetch RFOs",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all demand & prefetch RFOs",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x3f84000122 ",
+        "MSRValue": "0x3F84000122",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.ALL_RFO.L3_MISS_LOCAL_DRAM.ANY_SNOOP",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "ALL_RFO & L3_MISS_LOCAL_DRAM & ANY_SNOOP",
+        "BriefDescription": "Counts all demand & prefetch RFOs",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "Counts all demand & prefetch RFOs that miss the L3 with no details on snoop-related information. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all demand & prefetch RFOs",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x00bc000122 ",
+        "MSRValue": "0x00BC000122",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.ALL_RFO.L3_MISS.SNOOP_NONE",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "Counts all demand & prefetch RFOs that miss the L3 with no details on snoop-related information.",
+        "BriefDescription": "Counts all demand & prefetch RFOs",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all demand & prefetch RFOs",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x013c000122 ",
+        "MSRValue": "0x013C000122",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.ALL_RFO.L3_MISS.SNOOP_NOT_NEEDED",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "ALL_RFO & L3_MISS & SNOOP_NOT_NEEDED",
+        "BriefDescription": "Counts all demand & prefetch RFOs",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "Counts all demand & prefetch RFOs that miss the L3 with a snoop miss response. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all demand & prefetch RFOs",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x023c000122 ",
+        "MSRValue": "0x023C000122",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.ALL_RFO.L3_MISS.SNOOP_MISS",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "Counts all demand & prefetch RFOs that miss the L3 with a snoop miss response.",
+        "BriefDescription": "Counts all demand & prefetch RFOs",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all demand & prefetch RFOs",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x043c000122 ",
+        "MSRValue": "0x043C000122",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.ALL_RFO.L3_MISS.SNOOP_HIT_NO_FWD",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "ALL_RFO & L3_MISS & SNOOP_HIT_NO_FWD",
+        "BriefDescription": "Counts all demand & prefetch RFOs",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     }
diff --git a/tools/perf/pmu-events/arch/x86/broadwell/pipeline.json b/tools/perf/pmu-events/arch/x86/broadwell/pipeline.json
index 999cf3066363..bb25574b8d21 100644
--- a/tools/perf/pmu-events/arch/x86/broadwell/pipeline.json
+++ b/tools/perf/pmu-events/arch/x86/broadwell/pipeline.json
@@ -1,7 +1,6 @@
 [
     {
         "PublicDescription": "This event counts the number of instructions retired from execution. For instructions that consist of multiple micro-ops, this event counts the retirement of the last micro-op of the instruction. Counting continues during hardware interrupts, traps, and inside interrupt handlers. \nNotes: INST_RETIRED.ANY is counted by a designated fixed counter, leaving the four (eight when Hyperthreading is disabled) programmable counters available for other events. INST_RETIRED.ANY_P is counted by a programmable counter and it is an architectural performance event. \nCounting: Faulting executions of GETSEC/VM entry/VM Exit/MWait will not count as retired instructions.",
-        "EventCode": "0x00",
         "Counter": "Fixed counter 0",
         "UMask": "0x1",
         "EventName": "INST_RETIRED.ANY",
@@ -11,7 +10,6 @@
     },
     {
         "PublicDescription": "This event counts the number of core cycles while the thread is not in a halt state. The thread enters the halt state when it is running the HLT instruction. This event is a component in many key event ratios. The core frequency may change from time to time due to transitions associated with Enhanced Intel SpeedStep Technology or TM2. For this reason this event may have a changing ratio with regards to time. When the core frequency is constant, this event can approximate elapsed time while the core was not in the halt state. It is counted on a dedicated fixed counter, leaving the four (eight when Hyperthreading is disabled) programmable counters available for other events.",
-        "EventCode": "0x00",
         "Counter": "Fixed counter 1",
         "UMask": "0x2",
         "EventName": "CPU_CLK_UNHALTED.THREAD",
@@ -20,7 +18,6 @@
         "CounterHTOff": "Fixed counter 1"
     },
     {
-        "EventCode": "0x00",
         "Counter": "Fixed counter 1",
         "UMask": "0x2",
         "AnyThread": "1",
@@ -31,7 +28,6 @@
     },
     {
         "PublicDescription": "This event counts the number of reference cycles when the core is not in a halt state. The core enters the halt state when it is running the HLT instruction or the MWAIT instruction. This event is not affected by core frequency changes (for example, P states, TM2 transitions) but has the same incrementing frequency as the time stamp counter. This event can approximate elapsed time while the core was not in a halt state. This event has a constant ratio with the CPU_CLK_UNHALTED.REF_XCLK event. It is counted on a dedicated fixed counter, leaving the four (eight when Hyperthreading is disabled) programmable counters available for other events. \nNote: On all current platforms this event stops counting during 'throttling (TM)' states duty off periods the processor is 'halted'.  This event is clocked by base clock (100 Mhz) on Sandy Bridge. The counter update is done at a lower clock rate then the core clock the overflow status bit for this counter may appear 'sticky'.  After the counter has overflowed and software clears the overflow status bit and resets the counter to less than MAX. The reset value to the counter is not clocked immediately so the overflow status bit will flip 'high (1)' and generate another PMI (if enabled) after which the reset value gets clocked into the counter. Therefore, software will get the interrupt, read the overflow status bit '1 for bit 34 while the counter value is less than MAX. Software should ignore this case.",
-        "EventCode": "0x00",
         "Counter": "Fixed counter 2",
         "UMask": "0x3",
         "EventName": "CPU_CLK_UNHALTED.REF_TSC",
@@ -317,7 +313,7 @@
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "PublicDescription": "This event counts stalls occurred due to changing prefix length (66, 67 or REX.W when they change the length of the decoded instruction). Occurrences counting is proportional to the number of prefixes in a 16B-line. This may result in the following penalties: three-cycle penalty for each LCP in a 16-byte chunk.",
+        "PublicDescription": "This event counts stalls occured due to changing prefix length (66, 67 or REX.W when they change the length of the decoded instruction). Occurrences counting is proportional to the number of prefixes in a 16B-line. This may result in the following penalties: three-cycle penalty for each LCP in a 16-byte chunk.",
         "EventCode": "0x87",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
@@ -786,8 +782,8 @@
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "PublicDescription": "This event counts resource-related stall cycles. Reasons for stalls can be as follows:\n - *any* u-arch structure got full (LB, SB, RS, ROB, BOB, LM, Physical Register Reclaim Table (PRRT), or Physical History Table (PHT) slots)\n - *any* u-arch structure got empty (like INT/SIMD FreeLists)\n - FPU control word (FPCW), MXCSR\nand others. This counts cycles that the pipeline backend blocked uop delivery from the front end.",
-        "EventCode": "0xA2",
+        "PublicDescription": "This event counts resource-related stall cycles.",
+        "EventCode": "0xa2",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "RESOURCE_STALLS.ANY",
@@ -973,6 +969,7 @@
         "CounterHTOff": "2"
     },
     {
+        "PublicDescription": "Number of Uops delivered by the LSD.",
         "EventCode": "0xA8",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
@@ -1147,7 +1144,8 @@
         "CounterHTOff": "1"
     },
     {
-        "PublicDescription": "This event counts FP operations retired. For X87 FP operations that have no exceptions counting also includes flows that have several X87, or flows that use X87 uops in the exception handling.",
+        "PEBS": "1",
+        "PublicDescription": "This is a precise version (that is, uses PEBS) of the event that counts FP operations retired. For X87 FP operations that have no exceptions counting also includes flows that have several X87, or flows that use X87 uops in the exception handling.",
         "EventCode": "0xC0",
         "Counter": "0,1,2,3",
         "UMask": "0x2",
@@ -1157,12 +1155,12 @@
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
+        "PEBS": "1",
         "EventCode": "0xC1",
         "Counter": "0,1,2,3",
         "UMask": "0x40",
         "EventName": "OTHER_ASSISTS.ANY_WB_ASSIST",
         "SampleAfterValue": "100003",
-        "BriefDescription": "Number of times any microcode assist is invoked by HW upon uop writeback.",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
@@ -1178,26 +1176,28 @@
         "Data_LA": "1"
     },
     {
-        "PublicDescription": "This event counts cycles without actually retired uops.",
+        "PEBS": "1",
+        "PublicDescription": "This is a precise version (that is, uses PEBS) of the event that counts cycles without actually retired uops.",
         "EventCode": "0xC2",
         "Invert": "1",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "UOPS_RETIRED.STALL_CYCLES",
         "SampleAfterValue": "2000003",
-        "BriefDescription": "Cycles without actually retired uops.",
+        "BriefDescription": "Cycles no executable uops retired (Precise Event)",
         "CounterMask": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "Number of cycles using always true condition (uops_ret < 16) applied to non PEBS uops retired event.",
+        "PEBS": "1",
+        "PublicDescription": "Number of cycles using always true condition (uops_ret < 16) applied to  PEBS uops retired event.",
         "EventCode": "0xC2",
         "Invert": "1",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "UOPS_RETIRED.TOTAL_CYCLES",
         "SampleAfterValue": "2000003",
-        "BriefDescription": "Cycles with less than 10 actually retired uops.",
+        "BriefDescription": "Number of cycles using always true condition applied to  PEBS uops retired event.",
         "CounterMask": "10",
         "CounterHTOff": "0,1,2,3"
     },
@@ -1320,13 +1320,14 @@
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "PublicDescription": "This event counts not taken branch instructions retired.",
+        "PEBS": "1",
+        "PublicDescription": "This is a precise version (that is, uses PEBS) of the event that counts not taken branch instructions retired.",
         "EventCode": "0xC4",
         "Counter": "0,1,2,3",
         "UMask": "0x10",
         "EventName": "BR_INST_RETIRED.NOT_TAKEN",
         "SampleAfterValue": "400009",
-        "BriefDescription": "Not taken branch instructions retired.",
+        "BriefDescription": "Counts all not taken macro branch instructions retired. (Precise Event)",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
@@ -1341,14 +1342,15 @@
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "PublicDescription": "This event counts far branch instructions retired.",
+        "PEBS": "1",
+        "PublicDescription": "This is a precise version (that is, uses PEBS) of the event that counts far branch instructions retired.",
         "EventCode": "0xC4",
         "Counter": "0,1,2,3",
         "UMask": "0x40",
         "Errata": "BDW98",
         "EventName": "BR_INST_RETIRED.FAR_BRANCH",
         "SampleAfterValue": "100007",
-        "BriefDescription": "Far branch instructions retired.",
+        "BriefDescription": "Counts the number of far branch instructions retired.(Precise Event)",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
diff --git a/tools/perf/pmu-events/arch/x86/broadwellde/cache.json b/tools/perf/pmu-events/arch/x86/broadwellde/cache.json
index 4ad425312bdc..bf243fe2a0ec 100644
--- a/tools/perf/pmu-events/arch/x86/broadwellde/cache.json
+++ b/tools/perf/pmu-events/arch/x86/broadwellde/cache.json
@@ -439,7 +439,7 @@
         "PEBS": "1",
         "Counter": "0,1,2,3",
         "EventName": "MEM_UOPS_RETIRED.SPLIT_LOADS",
-        "PublicDescription": "This is a precise version (that is, uses PEBS) of the event that counts line-split load uops retired to the architected path. A line split is across 64B cache-line which includes a page split (4K).",
+        "PublicDescription": "This is a precise version (that is, uses PEBS) of the event that counts line-splitted load uops retired to the architected path. A line split is across 64B cache-line which includes a page split (4K).",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -451,7 +451,7 @@
         "PEBS": "1",
         "Counter": "0,1,2,3",
         "EventName": "MEM_UOPS_RETIRED.SPLIT_STORES",
-        "PublicDescription": "This is a precise version (that is, uses PEBS) of the event that counts line-split store uops retired to the architected path. A line split is across 64B cache-line which includes a page split (4K).",
+        "PublicDescription": "This is a precise version (that is, uses PEBS) of the event that counts line-splitted store uops retired to the architected path. A line split is across 64B cache-line which includes a page split (4K).",
         "SampleAfterValue": "100003",
         "L1_Hit_Indication": "1",
         "CounterHTOff": "0,1,2,3"
diff --git a/tools/perf/pmu-events/arch/x86/broadwellde/pipeline.json b/tools/perf/pmu-events/arch/x86/broadwellde/pipeline.json
index 0d04bf9db000..e2f0540625a2 100644
--- a/tools/perf/pmu-events/arch/x86/broadwellde/pipeline.json
+++ b/tools/perf/pmu-events/arch/x86/broadwellde/pipeline.json
@@ -1,6 +1,5 @@
 [
     {
-        "EventCode": "0x00",
         "UMask": "0x1",
         "BriefDescription": "Instructions retired from execution.",
         "Counter": "Fixed counter 0",
@@ -10,7 +9,6 @@
         "CounterHTOff": "Fixed counter 0"
     },
     {
-        "EventCode": "0x00",
         "UMask": "0x2",
         "BriefDescription": "Core cycles when the thread is not in halt state",
         "Counter": "Fixed counter 1",
@@ -20,7 +18,6 @@
         "CounterHTOff": "Fixed counter 1"
     },
     {
-        "EventCode": "0x00",
         "UMask": "0x2",
         "BriefDescription": "Core cycles when at least one thread on the physical core is not in halt state.",
         "Counter": "Fixed counter 1",
@@ -30,7 +27,6 @@
         "CounterHTOff": "Fixed counter 1"
     },
     {
-        "EventCode": "0x00",
         "UMask": "0x3",
         "BriefDescription": "Reference cycles when the core is not in halt state.",
         "Counter": "Fixed counter 2",
@@ -322,7 +318,7 @@
         "BriefDescription": "Stalls caused by changing prefix length of the instruction.",
         "Counter": "0,1,2,3",
         "EventName": "ILD_STALL.LCP",
-        "PublicDescription": "This event counts stalls occurred due to changing prefix length (66, 67 or REX.W when they change the length of the decoded instruction). Occurrences counting is proportional to the number of prefixes in a 16B-line. This may result in the following penalties: three-cycle penalty for each LCP in a 16-byte chunk.",
+        "PublicDescription": "This event counts stalls occured due to changing prefix length (66, 67 or REX.W when they change the length of the decoded instruction). Occurrences counting is proportional to the number of prefixes in a 16B-line. This may result in the following penalties: three-cycle penalty for each LCP in a 16-byte chunk.",
         "SampleAfterValue": "2000003",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
diff --git a/tools/perf/pmu-events/arch/x86/broadwellx/bdx-metrics.json b/tools/perf/pmu-events/arch/x86/broadwellx/bdx-metrics.json
index 5a7f1ec24200..c6f9762f32c0 100644
--- a/tools/perf/pmu-events/arch/x86/broadwellx/bdx-metrics.json
+++ b/tools/perf/pmu-events/arch/x86/broadwellx/bdx-metrics.json
@@ -1,164 +1,370 @@
 [
     {
-        "BriefDescription": "Instructions Per Cycle (per logical thread)",
+        "MetricExpr": "IDQ_UOPS_NOT_DELIVERED.CORE / (4 * cycles)",
+        "PublicDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend. Frontend denotes the first part of the processor core responsible to fetch operations that are executed later on by the Backend part. Within the Frontend; a branch predictor predicts the next address to fetch; cache-lines are fetched from the memory subsystem; parsed into instructions; and lastly decoded into micro-ops (uops). Ideally the Frontend can issue 4 uops every cycle to the Backend. Frontend Bound denotes unutilized issue-slots when there is no Backend stall; i.e. bubbles where Frontend delivered no uops while Backend could have accepted them. For example; stalls due to instruction-cache misses would be categorized under Frontend Bound.",
+        "BriefDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend",
+        "MetricGroup": "TopdownL1",
+        "MetricName": "Frontend_Bound"
+    },
+    {
+        "MetricExpr": "IDQ_UOPS_NOT_DELIVERED.CORE / (4 * (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )))",
+        "PublicDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend. Frontend denotes the first part of the processor core responsible to fetch operations that are executed later on by the Backend part. Within the Frontend; a branch predictor predicts the next address to fetch; cache-lines are fetched from the memory subsystem; parsed into instructions; and lastly decoded into micro-ops (uops). Ideally the Frontend can issue 4 uops every cycle to the Backend. Frontend Bound denotes unutilized issue-slots when there is no Backend stall; i.e. bubbles where Frontend delivered no uops while Backend could have accepted them. For example; stalls due to instruction-cache misses would be categorized under Frontend Bound. SMT version; use when SMT is enabled and measuring per logical CPU.",
+        "BriefDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend. SMT version; use when SMT is enabled and measuring per logical CPU.",
+        "MetricGroup": "TopdownL1_SMT",
+        "MetricName": "Frontend_Bound_SMT"
+    },
+    {
+        "MetricExpr": "( UOPS_ISSUED.ANY - UOPS_RETIRED.RETIRE_SLOTS + 4 * INT_MISC.RECOVERY_CYCLES ) / (4 * cycles)",
+        "PublicDescription": "This category represents fraction of slots wasted due to incorrect speculations. This include slots used to issue uops that do not eventually get retired and slots for which the issue-pipeline was blocked due to recovery from earlier incorrect speculation. For example; wasted work due to miss-predicted branches are categorized under Bad Speculation category. Incorrect data speculation followed by Memory Ordering Nukes is another example.",
+        "BriefDescription": "This category represents fraction of slots wasted due to incorrect speculations",
+        "MetricGroup": "TopdownL1",
+        "MetricName": "Bad_Speculation"
+    },
+    {
+        "MetricExpr": "( UOPS_ISSUED.ANY - UOPS_RETIRED.RETIRE_SLOTS + 4 * (( INT_MISC.RECOVERY_CYCLES_ANY / 2 )) ) / (4 * (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )))",
+        "PublicDescription": "This category represents fraction of slots wasted due to incorrect speculations. This include slots used to issue uops that do not eventually get retired and slots for which the issue-pipeline was blocked due to recovery from earlier incorrect speculation. For example; wasted work due to miss-predicted branches are categorized under Bad Speculation category. Incorrect data speculation followed by Memory Ordering Nukes is another example. SMT version; use when SMT is enabled and measuring per logical CPU.",
+        "BriefDescription": "This category represents fraction of slots wasted due to incorrect speculations. SMT version; use when SMT is enabled and measuring per logical CPU.",
+        "MetricGroup": "TopdownL1_SMT",
+        "MetricName": "Bad_Speculation_SMT"
+    },
+    {
+        "MetricExpr": "1 - ( (IDQ_UOPS_NOT_DELIVERED.CORE / (4 * cycles)) + (( UOPS_ISSUED.ANY - UOPS_RETIRED.RETIRE_SLOTS + 4 * INT_MISC.RECOVERY_CYCLES ) / (4 * cycles)) + (UOPS_RETIRED.RETIRE_SLOTS / (4 * cycles)) )",
+        "PublicDescription": "This category represents fraction of slots where no uops are being delivered due to a lack of required resources for accepting new uops in the Backend. Backend is the portion of the processor core where the out-of-order scheduler dispatches ready uops into their respective execution units; and once completed these uops get retired according to program order. For example; stalls due to data-cache misses or stalls due to the divider unit being overloaded are both categorized under Backend Bound. Backend Bound is further divided into two main categories: Memory Bound and Core Bound.",
+        "BriefDescription": "This category represents fraction of slots where no uops are being delivered due to a lack of required resources for accepting new uops in the Backend",
+        "MetricGroup": "TopdownL1",
+        "MetricName": "Backend_Bound"
+    },
+    {
+        "MetricExpr": "1 - ( (IDQ_UOPS_NOT_DELIVERED.CORE / (4 * (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )))) + (( UOPS_ISSUED.ANY - UOPS_RETIRED.RETIRE_SLOTS + 4 * (( INT_MISC.RECOVERY_CYCLES_ANY / 2 )) ) / (4 * (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )))) + (UOPS_RETIRED.RETIRE_SLOTS / (4 * (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )))) )",
+        "PublicDescription": "This category represents fraction of slots where no uops are being delivered due to a lack of required resources for accepting new uops in the Backend. Backend is the portion of the processor core where the out-of-order scheduler dispatches ready uops into their respective execution units; and once completed these uops get retired according to program order. For example; stalls due to data-cache misses or stalls due to the divider unit being overloaded are both categorized under Backend Bound. Backend Bound is further divided into two main categories: Memory Bound and Core Bound. SMT version; use when SMT is enabled and measuring per logical CPU.",
+        "BriefDescription": "This category represents fraction of slots where no uops are being delivered due to a lack of required resources for accepting new uops in the Backend. SMT version; use when SMT is enabled and measuring per logical CPU.",
+        "MetricGroup": "TopdownL1_SMT",
+        "MetricName": "Backend_Bound_SMT"
+    },
+    {
+        "MetricExpr": "UOPS_RETIRED.RETIRE_SLOTS / (4 * cycles)",
+        "PublicDescription": "This category represents fraction of slots utilized by useful work i.e. issued uops that eventually get retired. Ideally; all pipeline slots would be attributed to the Retiring category.  Retiring of 100% would indicate the maximum 4 uops retired per cycle has been achieved.  Maximizing Retiring typically increases the Instruction-Per-Cycle metric. Note that a high Retiring value does not necessary mean there is no room for more performance.  For example; Microcode assists are categorized under Retiring. They hurt performance and can often be avoided. ",
+        "BriefDescription": "This category represents fraction of slots utilized by useful work i.e. issued uops that eventually get retired",
+        "MetricGroup": "TopdownL1",
+        "MetricName": "Retiring"
+    },
+    {
+        "MetricExpr": "UOPS_RETIRED.RETIRE_SLOTS / (4 * (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )))",
+        "PublicDescription": "This category represents fraction of slots utilized by useful work i.e. issued uops that eventually get retired. Ideally; all pipeline slots would be attributed to the Retiring category.  Retiring of 100% would indicate the maximum 4 uops retired per cycle has been achieved.  Maximizing Retiring typically increases the Instruction-Per-Cycle metric. Note that a high Retiring value does not necessary mean there is no room for more performance.  For example; Microcode assists are categorized under Retiring. They hurt performance and can often be avoided. SMT version; use when SMT is enabled and measuring per logical CPU.",
+        "BriefDescription": "This category represents fraction of slots utilized by useful work i.e. issued uops that eventually get retired. SMT version; use when SMT is enabled and measuring per logical CPU.",
+        "MetricGroup": "TopdownL1_SMT",
+        "MetricName": "Retiring_SMT"
+    },
+    {
         "MetricExpr": "INST_RETIRED.ANY / CPU_CLK_UNHALTED.THREAD",
+        "BriefDescription": "Instructions Per Cycle (per logical thread)",
         "MetricGroup": "TopDownL1",
         "MetricName": "IPC"
     },
     {
-        "BriefDescription": "Uops Per Instruction",
         "MetricExpr": "UOPS_RETIRED.RETIRE_SLOTS / INST_RETIRED.ANY",
-        "MetricGroup": "Pipeline",
+        "BriefDescription": "Uops Per Instruction",
+        "MetricGroup": "Pipeline;Retiring",
         "MetricName": "UPI"
     },
     {
-        "BriefDescription": "Rough Estimation of fraction of fetched lines bytes that were likely consumed by program instructions",
+        "MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.NEAR_TAKEN",
+        "BriefDescription": "Instruction per taken branch",
+        "MetricGroup": "Branches;PGO",
+        "MetricName": "IpTB"
+    },
+    {
+        "MetricExpr": "BR_INST_RETIRED.ALL_BRANCHES / BR_INST_RETIRED.NEAR_TAKEN",
+        "BriefDescription": "Branch instructions per taken branch. ",
+        "MetricGroup": "Branches;PGO",
+        "MetricName": "BpTB"
+    },
+    {
         "MetricExpr": "min( 1 , IDQ.MITE_UOPS / ( (UOPS_RETIRED.RETIRE_SLOTS / INST_RETIRED.ANY) * 16 * ( ICACHE.HIT + ICACHE.MISSES ) / 4.0 ) )",
-        "MetricGroup": "Frontend",
+        "BriefDescription": "Rough Estimation of fraction of fetched lines bytes that were likely (includes speculatively fetches) consumed by program instructions",
+        "MetricGroup": "PGO",
         "MetricName": "IFetch_Line_Utilization"
     },
     {
-        "BriefDescription": "Fraction of Uops delivered by the DSB (aka Decoded Icache; or Uop Cache)",
-        "MetricExpr": "IDQ.DSB_UOPS / ( IDQ.DSB_UOPS + LSD.UOPS + IDQ.MITE_UOPS + IDQ.MS_UOPS )",
-        "MetricGroup": "DSB; Frontend_Bandwidth",
+        "MetricExpr": "IDQ.DSB_UOPS / (( IDQ.DSB_UOPS + LSD.UOPS + IDQ.MITE_UOPS + IDQ.MS_UOPS ) )",
+        "BriefDescription": "Fraction of Uops delivered by the DSB (aka Decoded ICache; or Uop Cache)",
+        "MetricGroup": "DSB;Frontend_Bandwidth",
         "MetricName": "DSB_Coverage"
     },
     {
-        "BriefDescription": "Cycles Per Instruction (threaded)",
         "MetricExpr": "1 / (INST_RETIRED.ANY / cycles)",
+        "BriefDescription": "Cycles Per Instruction (threaded)",
         "MetricGroup": "Pipeline;Summary",
         "MetricName": "CPI"
     },
     {
-        "BriefDescription": "Per-thread actual clocks when the logical processor is active. This is called 'Clockticks' in VTune.",
         "MetricExpr": "CPU_CLK_UNHALTED.THREAD",
+        "BriefDescription": "Per-thread actual clocks when the logical processor is active.",
         "MetricGroup": "Summary",
         "MetricName": "CLKS"
     },
     {
-        "BriefDescription": "Total issue-pipeline slots",
-        "MetricExpr": "4*(( CPU_CLK_UNHALTED.THREAD_ANY / 2 ) if #SMT_on else cycles)",
+        "MetricExpr": "4 * cycles",
+        "BriefDescription": "Total issue-pipeline slots (per core)",
         "MetricGroup": "TopDownL1",
         "MetricName": "SLOTS"
     },
     {
-        "BriefDescription": "Total number of retired Instructions",
+        "MetricExpr": "4 * (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) ))",
+        "BriefDescription": "Total issue-pipeline slots (per core)",
+        "MetricGroup": "TopDownL1_SMT",
+        "MetricName": "SLOTS_SMT"
+    },
+    {
+        "MetricExpr": "INST_RETIRED.ANY / MEM_UOPS_RETIRED.ALL_LOADS",
+        "BriefDescription": "Instructions per Load (lower number means loads are more frequent)",
+        "MetricGroup": "Instruction_Type;L1_Bound",
+        "MetricName": "IpL"
+    },
+    {
+        "MetricExpr": "INST_RETIRED.ANY / MEM_UOPS_RETIRED.ALL_STORES",
+        "BriefDescription": "Instructions per Store",
+        "MetricGroup": "Instruction_Type;Store_Bound",
+        "MetricName": "IpS"
+    },
+    {
+        "MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.ALL_BRANCHES",
+        "BriefDescription": "Instructions per Branch",
+        "MetricGroup": "Branches;Instruction_Type;Port_5;Port_6",
+        "MetricName": "IpB"
+    },
+    {
+        "MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.NEAR_CALL",
+        "BriefDescription": "Instruction per (near) call",
+        "MetricGroup": "Branches",
+        "MetricName": "IpCall"
+    },
+    {
         "MetricExpr": "INST_RETIRED.ANY",
+        "BriefDescription": "Total number of retired Instructions",
         "MetricGroup": "Summary",
         "MetricName": "Instructions"
     },
     {
+        "MetricExpr": "INST_RETIRED.ANY / cycles",
         "BriefDescription": "Instructions Per Cycle (per physical core)",
-        "MetricExpr": "INST_RETIRED.ANY / (( CPU_CLK_UNHALTED.THREAD_ANY / 2 ) if #SMT_on else cycles)",
         "MetricGroup": "SMT",
         "MetricName": "CoreIPC"
     },
     {
+        "MetricExpr": "INST_RETIRED.ANY / (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) ))",
+        "BriefDescription": "Instructions Per Cycle (per physical core)",
+        "MetricGroup": "SMT",
+        "MetricName": "CoreIPC_SMT"
+    },
+    {
+        "MetricExpr": "(( 1 * ( FP_ARITH_INST_RETIRED.SCALAR_SINGLE + FP_ARITH_INST_RETIRED.SCALAR_DOUBLE ) + 2 * FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE + 4 * ( FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE + FP_ARITH_INST_RETIRED.256B_PACKED_DOUBLE ) + 8 * FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE )) / cycles",
+        "BriefDescription": "Floating Point Operations Per Cycle",
+        "MetricGroup": "FLOPS",
+        "MetricName": "FLOPc"
+    },
+    {
+        "MetricExpr": "(( 1 * ( FP_ARITH_INST_RETIRED.SCALAR_SINGLE + FP_ARITH_INST_RETIRED.SCALAR_DOUBLE ) + 2 * FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE + 4 * ( FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE + FP_ARITH_INST_RETIRED.256B_PACKED_DOUBLE ) + 8 * FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE )) / (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) ))",
+        "BriefDescription": "Floating Point Operations Per Cycle",
+        "MetricGroup": "FLOPS_SMT",
+        "MetricName": "FLOPc_SMT"
+    },
+    {
+        "MetricExpr": "UOPS_EXECUTED.THREAD / (( cpu@UOPS_EXECUTED.CORE\\,cmask\\=1@ / 2 ) if #SMT_on else UOPS_EXECUTED.CYCLES_GE_1_UOP_EXEC)",
         "BriefDescription": "Instruction-Level-Parallelism (average number of uops executed when there is at least 1 uop executed)",
-        "MetricExpr": "UOPS_EXECUTED.THREAD / (( cpu@UOPS_EXECUTED.CORE\\,cmask\\=1@ / 2) if #SMT_on else UOPS_EXECUTED.CYCLES_GE_1_UOP_EXEC)",
         "MetricGroup": "Pipeline;Ports_Utilization",
         "MetricName": "ILP"
     },
     {
-        "BriefDescription": "Average Branch Address Clear Cost (fraction of cycles)",
-        "MetricExpr": "2* (( RS_EVENTS.EMPTY_CYCLES - ICACHE.IFDATA_STALL  - (( 14 * ITLB_MISSES.STLB_HIT + cpu@ITLB_MISSES.WALK_DURATION\\,cmask\\=1@ + 7* ITLB_MISSES.WALK_COMPLETED )) ) / RS_EVENTS.EMPTY_END)",
-        "MetricGroup": "Unknown_Branches",
-        "MetricName": "BAClear_Cost"
+        "MetricExpr": "( ((BR_MISP_RETIRED.ALL_BRANCHES / ( BR_MISP_RETIRED.ALL_BRANCHES + MACHINE_CLEARS.COUNT )) * (( UOPS_ISSUED.ANY - UOPS_RETIRED.RETIRE_SLOTS + 4 * INT_MISC.RECOVERY_CYCLES ) / (4 * cycles))) + (4 * IDQ_UOPS_NOT_DELIVERED.CYCLES_0_UOPS_DELIV.CORE / (4 * cycles)) * (12 * ( BR_MISP_RETIRED.ALL_BRANCHES + MACHINE_CLEARS.COUNT + BACLEARS.ANY ) / cycles) / (4 * IDQ_UOPS_NOT_DELIVERED.CYCLES_0_UOPS_DELIV.CORE / (4 * cycles)) ) * (4 * cycles) / BR_MISP_RETIRED.ALL_BRANCHES",
+        "BriefDescription": "Branch Misprediction Cost: Fraction of TopDown slots wasted per branch misprediction (jeclear and baclear)",
+        "MetricGroup": "Branch_Mispredicts",
+        "MetricName": "Branch_Misprediction_Cost"
+    },
+    {
+        "MetricExpr": "( ((BR_MISP_RETIRED.ALL_BRANCHES / ( BR_MISP_RETIRED.ALL_BRANCHES + MACHINE_CLEARS.COUNT )) * (( UOPS_ISSUED.ANY - UOPS_RETIRED.RETIRE_SLOTS + 4 * (( INT_MISC.RECOVERY_CYCLES_ANY / 2 )) ) / (4 * (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) ))))) + (4 * IDQ_UOPS_NOT_DELIVERED.CYCLES_0_UOPS_DELIV.CORE / (4 * (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )))) * (12 * ( BR_MISP_RETIRED.ALL_BRANCHES + MACHINE_CLEARS.COUNT + BACLEARS.ANY ) / cycles) / (4 * IDQ_UOPS_NOT_DELIVERED.CYCLES_0_UOPS_DELIV.CORE / (4 * (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )))) ) * (4 * (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) ))) / BR_MISP_RETIRED.ALL_BRANCHES",
+        "BriefDescription": "Branch Misprediction Cost: Fraction of TopDown slots wasted per branch misprediction (jeclear and baclear)",
+        "MetricGroup": "Branch_Mispredicts_SMT",
+        "MetricName": "Branch_Misprediction_Cost_SMT"
+    },
+    {
+        "MetricExpr": "INST_RETIRED.ANY / BR_MISP_RETIRED.ALL_BRANCHES",
+        "BriefDescription": "Number of Instructions per non-speculative Branch Misprediction (JEClear)",
+        "MetricGroup": "Branch_Mispredicts",
+        "MetricName": "IpMispredict"
     },
     {
+        "MetricExpr": "( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )",
         "BriefDescription": "Core actual clocks when any thread is active on the physical core",
-        "MetricExpr": "( CPU_CLK_UNHALTED.THREAD_ANY / 2 ) if #SMT_on else CPU_CLK_UNHALTED.THREAD",
         "MetricGroup": "SMT",
         "MetricName": "CORE_CLKS"
     },
     {
-        "BriefDescription": "Actual Average Latency for L1 data-cache miss demand loads",
         "MetricExpr": "L1D_PEND_MISS.PENDING / ( MEM_LOAD_UOPS_RETIRED.L1_MISS + mem_load_uops_retired.hit_lfb )",
+        "BriefDescription": "Actual Average Latency for L1 data-cache miss demand loads (in core cycles)",
         "MetricGroup": "Memory_Bound;Memory_Lat",
         "MetricName": "Load_Miss_Real_Latency"
     },
     {
-        "BriefDescription": "Memory-Level-Parallelism (average number of L1 miss demand load when there is at least 1 such miss)",
-        "MetricExpr": "L1D_PEND_MISS.PENDING / (( cpu@l1d_pend_miss.pending_cycles\\,any\\=1@ / 2) if #SMT_on else L1D_PEND_MISS.PENDING_CYCLES)",
+        "MetricExpr": "L1D_PEND_MISS.PENDING / L1D_PEND_MISS.PENDING_CYCLES",
+        "BriefDescription": "Memory-Level-Parallelism (average number of L1 miss demand load when there is at least one such miss. Per-thread)",
         "MetricGroup": "Memory_Bound;Memory_BW",
         "MetricName": "MLP"
     },
     {
+        "MetricExpr": "( ITLB_MISSES.WALK_DURATION + DTLB_LOAD_MISSES.WALK_DURATION + DTLB_STORE_MISSES.WALK_DURATION + 7 * ( DTLB_STORE_MISSES.WALK_COMPLETED + DTLB_LOAD_MISSES.WALK_COMPLETED + ITLB_MISSES.WALK_COMPLETED ) ) / ( 2 * cycles )",
         "BriefDescription": "Utilization of the core's Page Walker(s) serving STLB misses triggered by instruction/Load/Store accesses",
-        "MetricExpr": "( ITLB_MISSES.WALK_DURATION + DTLB_LOAD_MISSES.WALK_DURATION + DTLB_STORE_MISSES.WALK_DURATION + 7*(DTLB_STORE_MISSES.WALK_COMPLETED+DTLB_LOAD_MISSES.WALK_COMPLETED+ITLB_MISSES.WALK_COMPLETED) ) / (2*(( CPU_CLK_UNHALTED.THREAD_ANY / 2 ) if #SMT_on else cycles))",
         "MetricGroup": "TLB",
         "MetricName": "Page_Walks_Utilization"
     },
     {
-        "BriefDescription": "Average CPU Utilization",
+        "MetricExpr": "( ITLB_MISSES.WALK_DURATION + DTLB_LOAD_MISSES.WALK_DURATION + DTLB_STORE_MISSES.WALK_DURATION + 7 * ( DTLB_STORE_MISSES.WALK_COMPLETED + DTLB_LOAD_MISSES.WALK_COMPLETED + ITLB_MISSES.WALK_COMPLETED ) ) / ( 2 * (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )) )",
+        "BriefDescription": "Utilization of the core's Page Walker(s) serving STLB misses triggered by instruction/Load/Store accesses",
+        "MetricGroup": "TLB_SMT",
+        "MetricName": "Page_Walks_Utilization_SMT"
+    },
+    {
+        "MetricExpr": "64 * L1D.REPLACEMENT / 1000000000 / duration_time",
+        "BriefDescription": "Average data fill bandwidth to the L1 data cache [GB / sec]",
+        "MetricGroup": "Memory_BW",
+        "MetricName": "L1D_Cache_Fill_BW"
+    },
+    {
+        "MetricExpr": "64 * L2_LINES_IN.ALL / 1000000000 / duration_time",
+        "BriefDescription": "Average data fill bandwidth to the L2 cache [GB / sec]",
+        "MetricGroup": "Memory_BW",
+        "MetricName": "L2_Cache_Fill_BW"
+    },
+    {
+        "MetricExpr": "64 * LONGEST_LAT_CACHE.MISS / 1000000000 / duration_time",
+        "BriefDescription": "Average per-core data fill bandwidth to the L3 cache [GB / sec]",
+        "MetricGroup": "Memory_BW",
+        "MetricName": "L3_Cache_Fill_BW"
+    },
+    {
+        "MetricExpr": "1000 * MEM_LOAD_UOPS_RETIRED.L1_MISS / INST_RETIRED.ANY",
+        "BriefDescription": "L1 cache true misses per kilo instruction for retired demand loads",
+        "MetricGroup": "Cache_Misses;",
+        "MetricName": "L1MPKI"
+    },
+    {
+        "MetricExpr": "1000 * MEM_LOAD_UOPS_RETIRED.L2_MISS / INST_RETIRED.ANY",
+        "BriefDescription": "L2 cache true misses per kilo instruction for retired demand loads",
+        "MetricGroup": "Cache_Misses;",
+        "MetricName": "L2MPKI"
+    },
+    {
+        "MetricExpr": "1000 * L2_RQSTS.MISS / INST_RETIRED.ANY",
+        "BriefDescription": "L2 cache misses per kilo instruction for all request types (including speculative)",
+        "MetricGroup": "Cache_Misses;",
+        "MetricName": "L2MPKI_All"
+    },
+    {
+        "MetricExpr": "1000 * ( L2_RQSTS.REFERENCES - L2_RQSTS.MISS ) / INST_RETIRED.ANY",
+        "BriefDescription": "L2 cache hits per kilo instruction for all request types (including speculative)",
+        "MetricGroup": "Cache_Misses;",
+        "MetricName": "L2HPKI_All"
+    },
+    {
+        "MetricExpr": "1000 * MEM_LOAD_UOPS_RETIRED.L3_MISS / INST_RETIRED.ANY",
+        "BriefDescription": "L3 cache true misses per kilo instruction for retired demand loads",
+        "MetricGroup": "Cache_Misses;",
+        "MetricName": "L3MPKI"
+    },
+    {
         "MetricExpr": "CPU_CLK_UNHALTED.REF_TSC / msr@tsc@",
+        "BriefDescription": "Average CPU Utilization",
         "MetricGroup": "Summary",
         "MetricName": "CPU_Utilization"
     },
     {
+        "MetricExpr": "( (( 1 * ( FP_ARITH_INST_RETIRED.SCALAR_SINGLE + FP_ARITH_INST_RETIRED.SCALAR_DOUBLE ) + 2 * FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE + 4 * ( FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE + FP_ARITH_INST_RETIRED.256B_PACKED_DOUBLE ) + 8 * FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE )) / 1000000000 ) / duration_time",
         "BriefDescription": "Giga Floating Point Operations Per Second",
-        "MetricExpr": "(( 1*( FP_ARITH_INST_RETIRED.SCALAR_SINGLE + FP_ARITH_INST_RETIRED.SCALAR_DOUBLE ) + 2* FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE + 4*( FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE + FP_ARITH_INST_RETIRED.256B_PACKED_DOUBLE ) + 8* FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE )) / 1000000000 / duration_time",
         "MetricGroup": "FLOPS;Summary",
         "MetricName": "GFLOPs"
     },
     {
-        "BriefDescription": "Average Frequency Utilization relative nominal frequency",
         "MetricExpr": "CPU_CLK_UNHALTED.THREAD / CPU_CLK_UNHALTED.REF_TSC",
+        "BriefDescription": "Average Frequency Utilization relative nominal frequency",
         "MetricGroup": "Power",
         "MetricName": "Turbo_Utilization"
     },
     {
-        "BriefDescription": "Fraction of cycles where both hardware threads were active",
         "MetricExpr": "1 - CPU_CLK_THREAD_UNHALTED.ONE_THREAD_ACTIVE / ( CPU_CLK_THREAD_UNHALTED.REF_XCLK_ANY / 2 ) if #SMT_on else 0",
+        "BriefDescription": "Fraction of cycles where both hardware threads were active",
         "MetricGroup": "SMT;Summary",
         "MetricName": "SMT_2T_Utilization"
     },
     {
-        "BriefDescription": "Fraction of cycles spent in Kernel mode",
         "MetricExpr": "CPU_CLK_UNHALTED.REF_TSC:u / CPU_CLK_UNHALTED.REF_TSC",
+        "BriefDescription": "Fraction of cycles spent in Kernel mode",
         "MetricGroup": "Summary",
         "MetricName": "Kernel_Utilization"
     },
     {
-        "BriefDescription": "C3 residency percent per core",
+        "MetricExpr": "( 64 * ( uncore_imc@cas_count_read@ + uncore_imc@cas_count_write@ ) / 1000000000 ) / duration_time",
+        "BriefDescription": "Average external Memory Bandwidth Use for reads and writes [GB / sec]",
+        "MetricGroup": "Memory_BW",
+        "MetricName": "DRAM_BW_Use"
+    },
+    {
+        "MetricExpr": "1000000000 * ( cbox@event\\=0x36\\,umask\\=0x3\\,filter_opc\\=0x182@ / cbox@event\\=0x35\\,umask\\=0x3\\,filter_opc\\=0x182@ ) / ( cbox_0@event\\=0x0@ / duration_time )",
+        "BriefDescription": "Average latency of data read request to external memory (in nanoseconds). Accounts for demand loads and L1/L2 prefetches",
+        "MetricGroup": "Memory_Lat",
+        "MetricName": "DRAM_Read_Latency"
+    },
+    {
+        "MetricExpr": "cbox@event\\=0x36\\,umask\\=0x3\\,filter_opc\\=0x182@ / cbox@event\\=0x36\\,umask\\=0x3\\,filter_opc\\=0x182\\,thresh\\=1@",
+        "BriefDescription": "Average number of parallel data read requests to external memory. Accounts for demand loads and L1/L2 prefetches",
+        "MetricGroup": "Memory_BW",
+        "MetricName": "DRAM_Parallel_Reads"
+    },
+    {
+        "MetricExpr": "cbox_0@event\\=0x0@",
+        "BriefDescription": "Socket actual clocks when any core is active on that socket",
+        "MetricGroup": "",
+        "MetricName": "Socket_CLKS"
+    },
+    {
         "MetricExpr": "(cstate_core@c3\\-residency@ / msr@tsc@) * 100",
         "MetricGroup": "Power",
+        "BriefDescription": "C3 residency percent per core",
         "MetricName": "C3_Core_Residency"
     },
     {
-        "BriefDescription": "C6 residency percent per core",
         "MetricExpr": "(cstate_core@c6\\-residency@ / msr@tsc@) * 100",
         "MetricGroup": "Power",
+        "BriefDescription": "C6 residency percent per core",
         "MetricName": "C6_Core_Residency"
     },
     {
-        "BriefDescription": "C7 residency percent per core",
         "MetricExpr": "(cstate_core@c7\\-residency@ / msr@tsc@) * 100",
         "MetricGroup": "Power",
+        "BriefDescription": "C7 residency percent per core",
         "MetricName": "C7_Core_Residency"
     },
     {
-        "BriefDescription": "C2 residency percent per package",
         "MetricExpr": "(cstate_pkg@c2\\-residency@ / msr@tsc@) * 100",
         "MetricGroup": "Power",
+        "BriefDescription": "C2 residency percent per package",
         "MetricName": "C2_Pkg_Residency"
     },
     {
-        "BriefDescription": "C3 residency percent per package",
         "MetricExpr": "(cstate_pkg@c3\\-residency@ / msr@tsc@) * 100",
         "MetricGroup": "Power",
+        "BriefDescription": "C3 residency percent per package",
         "MetricName": "C3_Pkg_Residency"
     },
     {
-        "BriefDescription": "C6 residency percent per package",
         "MetricExpr": "(cstate_pkg@c6\\-residency@ / msr@tsc@) * 100",
         "MetricGroup": "Power",
+        "BriefDescription": "C6 residency percent per package",
         "MetricName": "C6_Pkg_Residency"
     },
     {
-        "BriefDescription": "C7 residency percent per package",
         "MetricExpr": "(cstate_pkg@c7\\-residency@ / msr@tsc@) * 100",
         "MetricGroup": "Power",
+        "BriefDescription": "C7 residency percent per package",
         "MetricName": "C7_Pkg_Residency"
     }
 ]
diff --git a/tools/perf/pmu-events/arch/x86/broadwellx/cache.json b/tools/perf/pmu-events/arch/x86/broadwellx/cache.json
index 141b1080429d..75a3098d5775 100644
--- a/tools/perf/pmu-events/arch/x86/broadwellx/cache.json
+++ b/tools/perf/pmu-events/arch/x86/broadwellx/cache.json
@@ -57,17 +57,17 @@
     },
     {
         "EventCode": "0x24",
-        "UMask": "0x41",
+        "UMask": "0xc1",
         "BriefDescription": "Demand Data Read requests that hit L2 cache",
         "Counter": "0,1,2,3",
         "EventName": "L2_RQSTS.DEMAND_DATA_RD_HIT",
-        "PublicDescription": "This event counts the number of demand Data Read requests that hit L2 cache. Only not rejected loads are counted.",
+        "PublicDescription": "Counts the number of demand Data Read requests, initiated by load instructions, that hit L2 cache.",
         "SampleAfterValue": "200003",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
         "EventCode": "0x24",
-        "UMask": "0x42",
+        "UMask": "0xc2",
         "BriefDescription": "RFO requests that hit L2 cache.",
         "Counter": "0,1,2,3",
         "EventName": "L2_RQSTS.RFO_HIT",
@@ -76,7 +76,7 @@
     },
     {
         "EventCode": "0x24",
-        "UMask": "0x44",
+        "UMask": "0xc4",
         "BriefDescription": "L2 cache hits when fetching instructions, code reads.",
         "Counter": "0,1,2,3",
         "EventName": "L2_RQSTS.CODE_RD_HIT",
@@ -85,7 +85,7 @@
     },
     {
         "EventCode": "0x24",
-        "UMask": "0x50",
+        "UMask": "0xd0",
         "BriefDescription": "L2 prefetch requests that hit L2 cache",
         "Counter": "0,1,2,3",
         "EventName": "L2_RQSTS.L2_PF_HIT",
@@ -396,24 +396,24 @@
     {
         "EventCode": "0xD0",
         "UMask": "0x11",
-        "BriefDescription": "Retired load uops that miss the STLB. (Precise Event - PEBS)",
+        "BriefDescription": "Retired load uops that miss the STLB.",
         "Data_LA": "1",
         "PEBS": "1",
         "Counter": "0,1,2,3",
         "EventName": "MEM_UOPS_RETIRED.STLB_MISS_LOADS",
-        "PublicDescription": "This is a precise version (that is, uses PEBS) of the event that counts load uops with true STLB miss retired to the architected path. True STLB miss is an uop triggering page walk that gets completed without blocks, and later gets retired. This page walk can end up with or without a fault.",
+        "PublicDescription": "This event counts load uops with true STLB miss retired to the architected path. True STLB miss is an uop triggering page walk that gets completed without blocks, and later gets retired. This page walk can end up with or without a fault.",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
     {
         "EventCode": "0xD0",
         "UMask": "0x12",
-        "BriefDescription": "Retired store uops that miss the STLB. (Precise Event - PEBS)",
+        "BriefDescription": "Retired store uops that miss the STLB.",
         "Data_LA": "1",
         "PEBS": "1",
         "Counter": "0,1,2,3",
         "EventName": "MEM_UOPS_RETIRED.STLB_MISS_STORES",
-        "PublicDescription": "This is a precise version (that is, uses PEBS) of the event that counts store uops true STLB miss retired to the architected path. True STLB miss is an uop triggering page walk that gets completed without blocks, and later gets retired. This page walk can end up with or without a fault.",
+        "PublicDescription": "This event counts store uops with true STLB miss retired to the architected path. True STLB miss is an uop triggering page walk that gets completed without blocks, and later gets retired. This page walk can end up with or without a fault.",
         "SampleAfterValue": "100003",
         "L1_Hit_Indication": "1",
         "CounterHTOff": "0,1,2,3"
@@ -421,37 +421,37 @@
     {
         "EventCode": "0xD0",
         "UMask": "0x21",
-        "BriefDescription": "Retired load uops with locked access. (Precise Event - PEBS)",
+        "BriefDescription": "Retired load uops with locked access.",
         "Data_LA": "1",
         "PEBS": "1",
         "Counter": "0,1,2,3",
         "EventName": "MEM_UOPS_RETIRED.LOCK_LOADS",
         "Errata": "BDM35",
-        "PublicDescription": "This is a precise version (that is, uses PEBS) of the event that counts load uops with locked access retired to the architected path.",
+        "PublicDescription": "This event counts load uops with locked access retired to the architected path.",
         "SampleAfterValue": "100007",
         "CounterHTOff": "0,1,2,3"
     },
     {
         "EventCode": "0xD0",
         "UMask": "0x41",
-        "BriefDescription": "Retired load uops that split across a cacheline boundary.(Precise Event - PEBS)",
+        "BriefDescription": "Retired load uops that split across a cacheline boundary.",
         "Data_LA": "1",
         "PEBS": "1",
         "Counter": "0,1,2,3",
         "EventName": "MEM_UOPS_RETIRED.SPLIT_LOADS",
-        "PublicDescription": "This is a precise version (that is, uses PEBS) of the event that counts line-split load uops retired to the architected path. A line split is across 64B cache-line which includes a page split (4K).",
+        "PublicDescription": "This event counts line-splitted load uops retired to the architected path. A line split is across 64B cache-line which includes a page split (4K).",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
     {
         "EventCode": "0xD0",
         "UMask": "0x42",
-        "BriefDescription": "Retired store uops that split across a cacheline boundary. (Precise Event - PEBS)",
+        "BriefDescription": "Retired store uops that split across a cacheline boundary.",
         "Data_LA": "1",
         "PEBS": "1",
         "Counter": "0,1,2,3",
         "EventName": "MEM_UOPS_RETIRED.SPLIT_STORES",
-        "PublicDescription": "This is a precise version (that is, uses PEBS) of the event that counts line-split store uops retired to the architected path. A line split is across 64B cache-line which includes a page split (4K).",
+        "PublicDescription": "This event counts line-splitted store uops retired to the architected path. A line split is across 64B cache-line which includes a page split (4K).",
         "SampleAfterValue": "100003",
         "L1_Hit_Indication": "1",
         "CounterHTOff": "0,1,2,3"
@@ -459,24 +459,24 @@
     {
         "EventCode": "0xD0",
         "UMask": "0x81",
-        "BriefDescription": "All retired load uops. (Precise Event - PEBS)",
+        "BriefDescription": "All retired load uops.",
         "Data_LA": "1",
         "PEBS": "1",
         "Counter": "0,1,2,3",
         "EventName": "MEM_UOPS_RETIRED.ALL_LOADS",
-        "PublicDescription": "This is a precise version (that is, uses PEBS) of the event that counts load uops retired to the architected path with a filter on bits 0 and 1 applied.\nNote: This event ?ounts AVX-256bit load/store double-pump memory uops as a single uop at retirement. This event also counts SW prefetches.",
+        "PublicDescription": "This event counts load uops retired to the architected path with a filter on bits 0 and 1 applied.\nNote: This event counts AVX-256bit load/store double-pump memory uops as a single uop at retirement. This event also counts SW prefetches.",
         "SampleAfterValue": "2000003",
         "CounterHTOff": "0,1,2,3"
     },
     {
         "EventCode": "0xD0",
         "UMask": "0x82",
-        "BriefDescription": "Retired store uops that split across a cacheline boundary. (Precise Event - PEBS)",
+        "BriefDescription": "All retired store uops.",
         "Data_LA": "1",
         "PEBS": "1",
         "Counter": "0,1,2,3",
         "EventName": "MEM_UOPS_RETIRED.ALL_STORES",
-        "PublicDescription": "This is a precise version (that is, uses PEBS) of the event that counts store uops retired to the architected path with a filter on bits 0 and 1 applied.\nNote: This event ?ounts AVX-256bit load/store double-pump memory uops as a single uop at retirement.",
+        "PublicDescription": "This event counts store uops retired to the architected path with a filter on bits 0 and 1 applied.\nNote: This event counts AVX-256bit load/store double-pump memory uops as a single uop at retirement.",
         "SampleAfterValue": "2000003",
         "L1_Hit_Indication": "1",
         "CounterHTOff": "0,1,2,3"
@@ -484,69 +484,69 @@
     {
         "EventCode": "0xD1",
         "UMask": "0x1",
-        "BriefDescription": "Retired load uops with L1 cache hits as data sources. (Precise Event - PEBS)",
+        "BriefDescription": "Retired load uops with L1 cache hits as data sources.",
         "Data_LA": "1",
         "PEBS": "1",
         "Counter": "0,1,2,3",
         "EventName": "MEM_LOAD_UOPS_RETIRED.L1_HIT",
-        "PublicDescription": "This is a precise version (that is, uses PEBS) of the event that counts retired load uops which data source were hits in the nearest-level (L1) cache.\nNote: Only two data-sources of L1/FB are applicable for AVX-256bit  even though the corresponding AVX load could be serviced by a deeper level in the memory hierarchy. Data source is reported for the Low-half load. This event also counts SW prefetches independent of the actual data source.",
+        "PublicDescription": "This event counts retired load uops which data sources were hits in the nearest-level (L1) cache.\nNote: Only two data-sources of L1/FB are applicable for AVX-256bit  even though the corresponding AVX load could be serviced by a deeper level in the memory hierarchy. Data source is reported for the Low-half load. This event also counts SW prefetches independent of the actual data source.",
         "SampleAfterValue": "2000003",
         "CounterHTOff": "0,1,2,3"
     },
     {
         "EventCode": "0xD1",
         "UMask": "0x2",
-        "BriefDescription": "Retired load uops with L2 cache hits as data sources. (Precise Event - PEBS)",
+        "BriefDescription": "Retired load uops with L2 cache hits as data sources.",
         "Data_LA": "1",
         "PEBS": "1",
         "Counter": "0,1,2,3",
         "EventName": "MEM_LOAD_UOPS_RETIRED.L2_HIT",
         "Errata": "BDM35",
-        "PublicDescription": "This is a precise version (that is, uses PEBS) of the event that counts retired load uops which data sources were hits in the mid-level (L2) cache.",
+        "PublicDescription": "This event counts retired load uops which data sources were hits in the mid-level (L2) cache.",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
     {
         "EventCode": "0xD1",
         "UMask": "0x4",
-        "BriefDescription": "Hit in last-level (L3) cache. Excludes Unknown data-source. (Precise Event - PEBS)",
+        "BriefDescription": "Retired load uops which data sources were data hits in L3 without snoops required.",
         "Data_LA": "1",
         "PEBS": "1",
         "Counter": "0,1,2,3",
         "EventName": "MEM_LOAD_UOPS_RETIRED.L3_HIT",
         "Errata": "BDM100",
-        "PublicDescription": "This is a precise version (that is, uses PEBS) of the event that counts retired load uops which data sources were data hits in the last-level (L3) cache without snoops required.",
+        "PublicDescription": "This event counts retired load uops which data sources were data hits in the last-level (L3) cache without snoops required.",
         "SampleAfterValue": "50021",
         "CounterHTOff": "0,1,2,3"
     },
     {
         "EventCode": "0xD1",
         "UMask": "0x8",
-        "BriefDescription": "Retired load uops misses in L1 cache as data sources. Uses PEBS.",
+        "BriefDescription": "Retired load uops misses in L1 cache as data sources.",
         "Data_LA": "1",
         "PEBS": "1",
         "Counter": "0,1,2,3",
         "EventName": "MEM_LOAD_UOPS_RETIRED.L1_MISS",
-        "PublicDescription": "This is a precise version (that is, uses PEBS) of the event that counts retired load uops which data sources were misses in the nearest-level (L1) cache. Counting excludes unknown and UC data source.",
+        "PublicDescription": "This event counts retired load uops which data sources were misses in the nearest-level (L1) cache. Counting excludes unknown and UC data source.",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
     {
         "EventCode": "0xD1",
         "UMask": "0x10",
-        "BriefDescription": "Retired load uops with L2 cache misses as data sources. Uses PEBS.",
+        "BriefDescription": "Miss in mid-level (L2) cache. Excludes Unknown data-source.",
         "Data_LA": "1",
         "PEBS": "1",
         "Counter": "0,1,2,3",
         "EventName": "MEM_LOAD_UOPS_RETIRED.L2_MISS",
-        "PublicDescription": "This is a precise version (that is, uses PEBS) of the event that counts retired load uops which data sources were misses in the mid-level (L2) cache. Counting excludes unknown and UC data source.",
+        "PublicDescription": "This event counts retired load uops which data sources were misses in the mid-level (L2) cache. Counting excludes unknown and UC data source.",
         "SampleAfterValue": "50021",
         "CounterHTOff": "0,1,2,3"
     },
     {
         "EventCode": "0xD1",
         "UMask": "0x20",
-        "BriefDescription": "Miss in last-level (L3) cache. Excludes Unknown data-source. (Precise Event - PEBS).",
+        "BriefDescription": "Miss in last-level (L3) cache. Excludes Unknown data-source.",
         "Data_LA": "1",
         "PEBS": "1",
         "Counter": "0,1,2,3",
@@ -558,83 +558,84 @@
     {
         "EventCode": "0xD1",
         "UMask": "0x40",
-        "BriefDescription": "Retired load uops which data sources were load uops missed L1 but hit FB due to preceding miss to the same cache line with data not ready. (Precise Event - PEBS)",
+        "BriefDescription": "Retired load uops which data sources were load uops missed L1 but hit FB due to preceding miss to the same cache line with data not ready.",
         "Data_LA": "1",
         "PEBS": "1",
         "Counter": "0,1,2,3",
         "EventName": "MEM_LOAD_UOPS_RETIRED.HIT_LFB",
-        "PublicDescription": "This is a precise version (that is, uses PEBS) of the event that counts retired load uops which data sources were load uops missed L1 but hit a fill buffer due to a preceding miss to the same cache line with the data not ready.\nNote: Only two data-sources of L1/FB are applicable for AVX-256bit  even though the corresponding AVX load could be serviced by a deeper level in the memory hierarchy. Data source is reported for the Low-half load.",
+        "PublicDescription": "This event counts retired load uops which data sources were load uops missed L1 but hit a fill buffer due to a preceding miss to the same cache line with the data not ready.\nNote: Only two data-sources of L1/FB are applicable for AVX-256bit  even though the corresponding AVX load could be serviced by a deeper level in the memory hierarchy. Data source is reported for the Low-half load.",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
     {
         "EventCode": "0xD2",
         "UMask": "0x1",
-        "BriefDescription": "Retired load uops which data sources were L3 hit and cross-core snoop missed in on-pkg core cache. (Precise Event - PEBS)",
+        "BriefDescription": "Retired load uops which data sources were L3 hit and cross-core snoop missed in on-pkg core cache.",
         "Data_LA": "1",
         "PEBS": "1",
         "Counter": "0,1,2,3",
         "EventName": "MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_MISS",
         "Errata": "BDM100",
-        "PublicDescription": "This is a precise version (that is, uses PEBS) of the event that counts retired load uops which data sources were L3 Hit and a cross-core snoop missed in the on-pkg core cache.",
+        "PublicDescription": "This event counts retired load uops which data sources were L3 Hit and a cross-core snoop missed in the on-pkg core cache.",
         "SampleAfterValue": "20011",
         "CounterHTOff": "0,1,2,3"
     },
     {
         "EventCode": "0xD2",
         "UMask": "0x2",
-        "BriefDescription": "Retired load uops which data sources were L3 and cross-core snoop hits in on-pkg core cache. (Precise Event - PEBS)",
+        "BriefDescription": "Retired load uops which data sources were L3 and cross-core snoop hits in on-pkg core cache.",
         "Data_LA": "1",
         "PEBS": "1",
         "Counter": "0,1,2,3",
         "EventName": "MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HIT",
         "Errata": "BDM100",
-        "PublicDescription": "This is a precise version (that is, uses PEBS) of the event that counts retired load uops which data sources were L3 hit and a cross-core snoop hit in the on-pkg core cache.",
+        "PublicDescription": "This event counts retired load uops which data sources were L3 hit and a cross-core snoop hit in the on-pkg core cache.",
         "SampleAfterValue": "20011",
         "CounterHTOff": "0,1,2,3"
     },
     {
         "EventCode": "0xD2",
         "UMask": "0x4",
-        "BriefDescription": "Retired load uops which data sources were HitM responses from shared L3. (Precise Event - PEBS)",
+        "BriefDescription": "Retired load uops which data sources were HitM responses from shared L3.",
         "Data_LA": "1",
         "PEBS": "1",
         "Counter": "0,1,2,3",
         "EventName": "MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HITM",
         "Errata": "BDM100",
-        "PublicDescription": "This is a precise version (that is, uses PEBS) of the event that counts retired load uops which data sources were HitM responses from a core on same socket (shared L3).",
+        "PublicDescription": "This event counts retired load uops which data sources were HitM responses from a core on same socket (shared L3).",
         "SampleAfterValue": "20011",
         "CounterHTOff": "0,1,2,3"
     },
     {
         "EventCode": "0xD2",
         "UMask": "0x8",
-        "BriefDescription": "Retired load uops which data sources were hits in L3 without snoops required. (Precise Event - PEBS)",
+        "BriefDescription": "Retired load uops which data sources were hits in L3 without snoops required.",
         "Data_LA": "1",
         "PEBS": "1",
         "Counter": "0,1,2,3",
         "EventName": "MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_NONE",
         "Errata": "BDM100",
-        "PublicDescription": "This is a precise version (that is, uses PEBS) of the event that counts retired load uops which data sources were hits in the last-level (L3) cache without snoops required.",
+        "PublicDescription": "This event counts retired load uops which data sources were hits in the last-level (L3) cache without snoops required.",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
     {
         "EventCode": "0xD3",
         "UMask": "0x1",
+        "BriefDescription": "Data from local DRAM either Snoop not needed or Snoop Miss (RspI)",
         "Data_LA": "1",
         "PEBS": "1",
         "Counter": "0,1,2,3",
         "EventName": "MEM_LOAD_UOPS_L3_MISS_RETIRED.LOCAL_DRAM",
         "Errata": "BDE70, BDM100",
-        "PublicDescription": "This event counts retired load uops where the data came from local DRAM. This does not include hardware prefetches. This is a precise event.",
+        "PublicDescription": "Retired load uop whose Data Source was: local DRAM either Snoop not needed or Snoop Miss (RspI).",
         "SampleAfterValue": "100007",
         "CounterHTOff": "0,1,2,3"
     },
     {
         "EventCode": "0xD3",
         "UMask": "0x4",
-        "BriefDescription": "Retired load uop whose Data Source was: remote DRAM either Snoop not needed or Snoop Miss (RspI) (Precise Event)",
+        "BriefDescription": "Retired load uop whose Data Source was: remote DRAM either Snoop not needed or Snoop Miss (RspI)",
         "Data_LA": "1",
         "PEBS": "1",
         "Counter": "0,1,2,3",
@@ -646,7 +647,7 @@
     {
         "EventCode": "0xD3",
         "UMask": "0x10",
-        "BriefDescription": "Retired load uop whose Data Source was: Remote cache HITM (Precise Event)",
+        "BriefDescription": "Retired load uop whose Data Source was: Remote cache HITM",
         "Data_LA": "1",
         "PEBS": "1",
         "Counter": "0,1,2,3",
@@ -658,7 +659,7 @@
     {
         "EventCode": "0xD3",
         "UMask": "0x20",
-        "BriefDescription": "Retired load uop whose Data Source was: forwarded from remote cache (Precise Event)",
+        "BriefDescription": "Retired load uop whose Data Source was: forwarded from remote cache",
         "Data_LA": "1",
         "PEBS": "1",
         "Counter": "0,1,2,3",
@@ -810,12 +811,12 @@
         "Offcore": "1",
         "EventCode": "0xB7, 0xBB",
         "UMask": "0x1",
-        "BriefDescription": "Counts all requests that hit in the L3",
-        "MSRValue": "0x3f803c8fff",
+        "BriefDescription": "Counts all requests hit in the L3",
+        "MSRValue": "0x3F803C8FFF",
         "Counter": "0,1,2,3",
         "EventName": "OFFCORE_RESPONSE.ALL_REQUESTS.LLC_HIT.ANY_RESPONSE",
         "MSRIndex": "0x1a6,0x1a7",
-        "PublicDescription": "Counts all requests that hit in the L3 Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all requests hit in the L3",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -823,12 +824,12 @@
         "Offcore": "1",
         "EventCode": "0xB7, 0xBB",
         "UMask": "0x1",
-        "BriefDescription": "Counts all data/code/rfo reads (demand & prefetch) that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded",
-        "MSRValue": "0x10003c07f7",
+        "BriefDescription": "Counts all data/code/rfo reads (demand & prefetch) hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded",
+        "MSRValue": "0x10003C07F7",
         "Counter": "0,1,2,3",
         "EventName": "OFFCORE_RESPONSE.ALL_READS.LLC_HIT.HITM_OTHER_CORE",
         "MSRIndex": "0x1a6,0x1a7",
-        "PublicDescription": "Counts all data/code/rfo reads (demand & prefetch) that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all data/code/rfo reads (demand & prefetch) hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -836,12 +837,12 @@
         "Offcore": "1",
         "EventCode": "0xB7, 0xBB",
         "UMask": "0x1",
-        "BriefDescription": "Counts all data/code/rfo reads (demand & prefetch) that hit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded",
-        "MSRValue": "0x04003c07f7",
+        "BriefDescription": "Counts all data/code/rfo reads (demand & prefetch) hit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded",
+        "MSRValue": "0x04003C07F7",
         "Counter": "0,1,2,3",
         "EventName": "OFFCORE_RESPONSE.ALL_READS.LLC_HIT.HIT_OTHER_CORE_NO_FWD",
         "MSRIndex": "0x1a6,0x1a7",
-        "PublicDescription": "Counts all data/code/rfo reads (demand & prefetch) that hit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all data/code/rfo reads (demand & prefetch) hit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -849,12 +850,12 @@
         "Offcore": "1",
         "EventCode": "0xB7, 0xBB",
         "UMask": "0x1",
-        "BriefDescription": "Counts all demand & prefetch code reads that hit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded",
-        "MSRValue": "0x04003c0244",
+        "BriefDescription": "Counts all demand & prefetch code reads hit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded",
+        "MSRValue": "0x04003C0244",
         "Counter": "0,1,2,3",
         "EventName": "OFFCORE_RESPONSE.ALL_CODE_RD.LLC_HIT.HIT_OTHER_CORE_NO_FWD",
         "MSRIndex": "0x1a6,0x1a7",
-        "PublicDescription": "Counts all demand & prefetch code reads that hit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all demand & prefetch code reads hit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -862,12 +863,12 @@
         "Offcore": "1",
         "EventCode": "0xB7, 0xBB",
         "UMask": "0x1",
-        "BriefDescription": "Counts all demand & prefetch RFOs that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded",
-        "MSRValue": "0x10003c0122",
+        "BriefDescription": "Counts all demand & prefetch RFOs hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded",
+        "MSRValue": "0x10003C0122",
         "Counter": "0,1,2,3",
         "EventName": "OFFCORE_RESPONSE.ALL_RFO.LLC_HIT.HITM_OTHER_CORE",
         "MSRIndex": "0x1a6,0x1a7",
-        "PublicDescription": "Counts all demand & prefetch RFOs that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all demand & prefetch RFOs hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -875,12 +876,12 @@
         "Offcore": "1",
         "EventCode": "0xB7, 0xBB",
         "UMask": "0x1",
-        "BriefDescription": "Counts all demand & prefetch RFOs that hit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded",
-        "MSRValue": "0x04003c0122",
+        "BriefDescription": "Counts all demand & prefetch RFOs hit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded",
+        "MSRValue": "0x04003C0122",
         "Counter": "0,1,2,3",
         "EventName": "OFFCORE_RESPONSE.ALL_RFO.LLC_HIT.HIT_OTHER_CORE_NO_FWD",
         "MSRIndex": "0x1a6,0x1a7",
-        "PublicDescription": "Counts all demand & prefetch RFOs that hit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all demand & prefetch RFOs hit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -888,12 +889,12 @@
         "Offcore": "1",
         "EventCode": "0xB7, 0xBB",
         "UMask": "0x1",
-        "BriefDescription": "Counts all demand & prefetch data reads that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded",
-        "MSRValue": "0x10003c0091",
+        "BriefDescription": "Counts all demand & prefetch data reads hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded",
+        "MSRValue": "0x10003C0091",
         "Counter": "0,1,2,3",
         "EventName": "OFFCORE_RESPONSE.ALL_DATA_RD.LLC_HIT.HITM_OTHER_CORE",
         "MSRIndex": "0x1a6,0x1a7",
-        "PublicDescription": "Counts all demand & prefetch data reads that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all demand & prefetch data reads hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -901,12 +902,12 @@
         "Offcore": "1",
         "EventCode": "0xB7, 0xBB",
         "UMask": "0x1",
-        "BriefDescription": "Counts all demand & prefetch data reads that hit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded",
-        "MSRValue": "0x04003c0091",
+        "BriefDescription": "Counts all demand & prefetch data reads hit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded",
+        "MSRValue": "0x04003C0091",
         "Counter": "0,1,2,3",
         "EventName": "OFFCORE_RESPONSE.ALL_DATA_RD.LLC_HIT.HIT_OTHER_CORE_NO_FWD",
         "MSRIndex": "0x1a6,0x1a7",
-        "PublicDescription": "Counts all demand & prefetch data reads that hit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all demand & prefetch data reads hit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -914,12 +915,12 @@
         "Offcore": "1",
         "EventCode": "0xB7, 0xBB",
         "UMask": "0x1",
-        "BriefDescription": "Counts prefetch (that bring data to LLC only) code reads that hit in the L3",
-        "MSRValue": "0x3f803c0200",
+        "BriefDescription": "Counts prefetch (that bring data to LLC only) code reads hit in the L3",
+        "MSRValue": "0x3F803C0200",
         "Counter": "0,1,2,3",
         "EventName": "OFFCORE_RESPONSE.PF_LLC_CODE_RD.LLC_HIT.ANY_RESPONSE",
         "MSRIndex": "0x1a6,0x1a7",
-        "PublicDescription": "Counts prefetch (that bring data to LLC only) code reads that hit in the L3 Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts prefetch (that bring data to LLC only) code reads hit in the L3",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -927,12 +928,12 @@
         "Offcore": "1",
         "EventCode": "0xB7, 0xBB",
         "UMask": "0x1",
-        "BriefDescription": "Counts all prefetch (that bring data to LLC only) RFOs that hit in the L3",
-        "MSRValue": "0x3f803c0100",
+        "BriefDescription": "Counts all prefetch (that bring data to LLC only) RFOs hit in the L3",
+        "MSRValue": "0x3F803C0100",
         "Counter": "0,1,2,3",
         "EventName": "OFFCORE_RESPONSE.PF_LLC_RFO.LLC_HIT.ANY_RESPONSE",
         "MSRIndex": "0x1a6,0x1a7",
-        "PublicDescription": "Counts all prefetch (that bring data to LLC only) RFOs that hit in the L3 Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all prefetch (that bring data to LLC only) RFOs hit in the L3",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -940,12 +941,12 @@
         "Offcore": "1",
         "EventCode": "0xB7, 0xBB",
         "UMask": "0x1",
-        "BriefDescription": "Counts all demand data writes (RFOs) that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded",
-        "MSRValue": "0x10003c0002",
+        "BriefDescription": "Counts all demand data writes (RFOs) hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded",
+        "MSRValue": "0x10003C0002",
         "Counter": "0,1,2,3",
         "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.LLC_HIT.HITM_OTHER_CORE",
         "MSRIndex": "0x1a6,0x1a7",
-        "PublicDescription": "Counts all demand data writes (RFOs) that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all demand data writes (RFOs) hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -953,12 +954,12 @@
         "Offcore": "1",
         "EventCode": "0xB7, 0xBB",
         "UMask": "0x1",
-        "BriefDescription": "Counts all demand data writes (RFOs) that hit in the L3",
-        "MSRValue": "0x3f803c0002",
+        "BriefDescription": "Counts all demand data writes (RFOs) hit in the L3",
+        "MSRValue": "0x3F803C0002",
         "Counter": "0,1,2,3",
         "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.LLC_HIT.ANY_RESPONSE",
         "MSRIndex": "0x1a6,0x1a7",
-        "PublicDescription": "Counts all demand data writes (RFOs) that hit in the L3 Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all demand data writes (RFOs) hit in the L3",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     }
diff --git a/tools/perf/pmu-events/arch/x86/broadwellx/floating-point.json b/tools/perf/pmu-events/arch/x86/broadwellx/floating-point.json
index d7b9d9c9c518..ba0e0c4e74eb 100644
--- a/tools/perf/pmu-events/arch/x86/broadwellx/floating-point.json
+++ b/tools/perf/pmu-events/arch/x86/broadwellx/floating-point.json
@@ -42,7 +42,7 @@
     {
         "EventCode": "0xC7",
         "UMask": "0x3",
-        "BriefDescription": "Number of SSE/AVX computational scalar floating-point instructions retired. Applies to SSE* and AVX* scalar, double and single precision floating-point: ADD SUB MUL DIV MIN MAX RSQRT RCP SQRT FM(N)ADD/SUB. FM(N)ADD/SUB instructions count twice as they perform multiple calculations per element.",
+        "BriefDescription": "Number of SSE/AVX computational scalar floating-point instructions retired. Applies to SSE* and AVX* scalar, double and single precision floating-point: ADD SUB MUL DIV MIN MAX RSQRT RCP SQRT FM(N)ADD/SUB. FM(N)ADD/SUB instructions count twice as they perform multiple calculations per element. (RSQRT for single precision?)",
         "Counter": "0,1,2,3",
         "EventName": "FP_ARITH_INST_RETIRED.SCALAR",
         "SampleAfterValue": "2000003",
@@ -51,7 +51,7 @@
     {
         "EventCode": "0xC7",
         "UMask": "0x4",
-        "BriefDescription": "Number of SSE/AVX computational 128-bit packed double precision floating-point instructions retired.  Each count represents 2 computations. Applies to SSE* and AVX* packed double precision floating-point instructions: ADD SUB MUL DIV MIN MAX SQRT DPP FM(N)ADD/SUB.  DPP and FM(N)ADD/SUB instructions count twice as they perform multiple calculations per element.",
+        "BriefDescription": "Number of SSE/AVX computational 128-bit packed double precision floating-point instructions retired.  Each count represents 2 computations. Applies to SSE* and AVX* packed double precision floating-point instructions: ADD SUB HADD HSUB SUBADD MUL DIV MIN MAX SQRT DPP FM(N)ADD/SUB.  DPP and FM(N)ADD/SUB instructions count twice as they perform multiple calculations per element.",
         "Counter": "0,1,2,3",
         "EventName": "FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE",
         "SampleAfterValue": "2000003",
@@ -60,7 +60,7 @@
     {
         "EventCode": "0xC7",
         "UMask": "0x8",
-        "BriefDescription": "Number of SSE/AVX computational 128-bit packed single precision floating-point instructions retired.  Each count represents 4 computations. Applies to SSE* and AVX* packed single precision floating-point instructions: ADD SUB MUL DIV MIN MAX RCP RSQRT SQRT DPP FM(N)ADD/SUB.  DPP and FM(N)ADD/SUB instructions count twice as they perform multiple calculations per element.",
+        "BriefDescription": "Number of SSE/AVX computational 128-bit packed single precision floating-point instructions retired.  Each count represents 4 computations. Applies to SSE* and AVX* packed single precision floating-point instructions: ADD SUB HADD HSUB SUBADD MUL DIV MIN MAX SQRT RSQRT DPP FM(N)ADD/SUB.  DPP and FM(N)ADD/SUB instructions count twice as they perform multiple calculations per element.",
         "Counter": "0,1,2,3",
         "EventName": "FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE",
         "SampleAfterValue": "2000003",
@@ -69,7 +69,7 @@
     {
         "EventCode": "0xC7",
         "UMask": "0x10",
-        "BriefDescription": "Number of SSE/AVX computational 256-bit packed double precision floating-point instructions retired.  Each count represents 4 computations. Applies to SSE* and AVX* packed double precision floating-point instructions: ADD SUB MUL DIV MIN MAX SQRT DPP FM(N)ADD/SUB.  DPP and FM(N)ADD/SUB instructions count twice as they perform multiple calculations per element.",
+        "BriefDescription": "Number of SSE/AVX computational 256-bit packed double precision floating-point instructions retired.  Each count represents 4 computations. Applies to SSE* and AVX* packed double precision floating-point instructions: ADD SUB HADD HSUB SUBADD MUL DIV MIN MAX SQRT DPP FM(N)ADD/SUB.  DPP and FM(N)ADD/SUB instructions count twice as they perform multiple calculations per element.",
         "Counter": "0,1,2,3",
         "EventName": "FP_ARITH_INST_RETIRED.256B_PACKED_DOUBLE",
         "SampleAfterValue": "2000003",
@@ -78,7 +78,7 @@
     {
         "EventCode": "0xC7",
         "UMask": "0x15",
-        "BriefDescription": "Number of SSE/AVX computational double precision floating-point instructions retired. Applies to SSE* and AVX*scalar, double and single precision floating-point: ADD SUB MUL DIV MIN MAX SQRT DPP FM(N)ADD/SUB.  DPP and FM(N)ADD/SUB instructions count twice as they perform multiple calculations per element.  ?.",
+        "BriefDescription": "Number of SSE/AVX computational double precision floating-point instructions retired. Applies to SSE* and AVX*scalar, double and single precision floating-point: ADD SUB MUL DIV MIN MAX SQRT DPP FM(N)ADD/SUB.  DPP and FM(N)ADD/SUB instructions count twice as they perform multiple calculations per element.",
         "Counter": "0,1,2,3",
         "EventName": "FP_ARITH_INST_RETIRED.DOUBLE",
         "SampleAfterValue": "2000006",
@@ -87,7 +87,7 @@
     {
         "EventCode": "0xc7",
         "UMask": "0x20",
-        "BriefDescription": "Number of SSE/AVX computational 256-bit packed single precision floating-point instructions retired.  Each count represents 8 computations. Applies to SSE* and AVX* packed single precision floating-point instructions: ADD SUB MUL DIV MIN MAX RCP RSQRT SQRT DPP FM(N)ADD/SUB.  DPP and FM(N)ADD/SUB instructions count twice as they perform multiple calculations per element.",
+        "BriefDescription": "Number of SSE/AVX computational 256-bit packed single precision floating-point instructions retired.  Each count represents 8 computations. Applies to SSE* and AVX* packed single precision floating-point instructions: ADD SUB HADD HSUB SUBADD MUL DIV MIN MAX SQRT RSQRT DPP FM(N)ADD/SUB.  DPP and FM(N)ADD/SUB instructions count twice as they perform multiple calculations per element.",
         "Counter": "0,1,2,3",
         "EventName": "FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE",
         "SampleAfterValue": "2000003",
@@ -96,7 +96,7 @@
     {
         "EventCode": "0xC7",
         "UMask": "0x2a",
-        "BriefDescription": "Number of SSE/AVX computational single precision floating-point instructions retired. Applies to SSE* and AVX*scalar, double and single precision floating-point: ADD SUB MUL DIV MIN MAX RCP RSQRT SQRT DPP FM(N)ADD/SUB.  DPP and FM(N)ADD/SUB instructions count twice as they perform multiple calculations per element. ?.",
+        "BriefDescription": "Number of SSE/AVX computational single precision floating-point instructions retired. Applies to SSE* and AVX*scalar, double and single precision floating-point: ADD SUB MUL DIV MIN MAX RCP RSQRT SQRT DPP FM(N)ADD/SUB.  DPP and FM(N)ADD/SUB instructions count twice as they perform multiple calculations per element.",
         "Counter": "0,1,2,3",
         "EventName": "FP_ARITH_INST_RETIRED.SINGLE",
         "SampleAfterValue": "2000005",
@@ -105,7 +105,7 @@
     {
         "EventCode": "0xC7",
         "UMask": "0x3c",
-        "BriefDescription": "Number of SSE/AVX computational packed floating-point instructions retired. Applies to SSE* and AVX*, packed, double and single precision floating-point: ADD SUB MUL DIV MIN MAX RSQRT RCP SQRT DPP FM(N)ADD/SUB.  DPP and FM(N)ADD/SUB instructions count twice as they perform multiple calculations per element.",
+        "BriefDescription": "Number of SSE/AVX computational packed floating-point instructions retired. Applies to SSE* and AVX*, packed, double and single precision floating-point: ADD SUB HADD HSUB SUBADD MUL DIV MIN MAX SQRT DPP FM(N)ADD/SUB.  DPP and FM(N)ADD/SUB instructions count twice as they perform multiple calculations per element. (RSQRT for single-precision?)",
         "Counter": "0,1,2,3",
         "EventName": "FP_ARITH_INST_RETIRED.PACKED",
         "SampleAfterValue": "2000004",
diff --git a/tools/perf/pmu-events/arch/x86/broadwellx/memory.json b/tools/perf/pmu-events/arch/x86/broadwellx/memory.json
index d79a5cfea44b..ecb413bb67ca 100644
--- a/tools/perf/pmu-events/arch/x86/broadwellx/memory.json
+++ b/tools/perf/pmu-events/arch/x86/broadwellx/memory.json
@@ -170,11 +170,11 @@
     {
         "EventCode": "0xc8",
         "UMask": "0x4",
-        "BriefDescription": "Number of times HLE abort was triggered (PEBS)",
+        "BriefDescription": "Number of times HLE abort was triggered",
         "PEBS": "1",
         "Counter": "0,1,2,3",
         "EventName": "HLE_RETIRED.ABORTED",
-        "PublicDescription": "Number of times HLE abort was triggered (PEBS).",
+        "PublicDescription": "Number of times HLE abort was triggered.",
         "SampleAfterValue": "2000003",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
@@ -251,11 +251,11 @@
     {
         "EventCode": "0xc9",
         "UMask": "0x4",
-        "BriefDescription": "Number of times RTM abort was triggered (PEBS)",
+        "BriefDescription": "Number of times RTM abort was triggered",
         "PEBS": "1",
         "Counter": "0,1,2,3",
         "EventName": "RTM_RETIRED.ABORTED",
-        "PublicDescription": "Number of times RTM abort was triggered (PEBS).",
+        "PublicDescription": "Number of times RTM abort was triggered .",
         "SampleAfterValue": "2000003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -312,14 +312,14 @@
     {
         "EventCode": "0xCD",
         "UMask": "0x1",
-        "BriefDescription": "Loads with latency value being above 4",
+        "BriefDescription": "Randomly selected loads with latency value being above 4",
         "PEBS": "2",
         "MSRValue": "0x4",
         "Counter": "3",
         "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_4",
         "MSRIndex": "0x3F6",
         "Errata": "BDM100, BDM35",
-        "PublicDescription": "This event counts loads with latency value being above four.",
+        "PublicDescription": "Counts randomly selected loads with latency value being above four.",
         "TakenAlone": "1",
         "SampleAfterValue": "100003",
         "CounterHTOff": "3"
@@ -327,14 +327,14 @@
     {
         "EventCode": "0xCD",
         "UMask": "0x1",
-        "BriefDescription": "Loads with latency value being above 8",
+        "BriefDescription": "Randomly selected loads with latency value being above 8",
         "PEBS": "2",
         "MSRValue": "0x8",
         "Counter": "3",
         "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_8",
         "MSRIndex": "0x3F6",
         "Errata": "BDM100, BDM35",
-        "PublicDescription": "This event counts loads with latency value being above eight.",
+        "PublicDescription": "Counts randomly selected loads with latency value being above eight.",
         "TakenAlone": "1",
         "SampleAfterValue": "50021",
         "CounterHTOff": "3"
@@ -342,14 +342,14 @@
     {
         "EventCode": "0xCD",
         "UMask": "0x1",
-        "BriefDescription": "Loads with latency value being above 16",
+        "BriefDescription": "Randomly selected loads with latency value being above 16",
         "PEBS": "2",
         "MSRValue": "0x10",
         "Counter": "3",
         "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_16",
         "MSRIndex": "0x3F6",
         "Errata": "BDM100, BDM35",
-        "PublicDescription": "This event counts loads with latency value being above 16.",
+        "PublicDescription": "Counts randomly selected loads with latency value being above 16.",
         "TakenAlone": "1",
         "SampleAfterValue": "20011",
         "CounterHTOff": "3"
@@ -357,14 +357,14 @@
     {
         "EventCode": "0xCD",
         "UMask": "0x1",
-        "BriefDescription": "Loads with latency value being above 32",
+        "BriefDescription": "Randomly selected loads with latency value being above 32",
         "PEBS": "2",
         "MSRValue": "0x20",
         "Counter": "3",
         "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_32",
         "MSRIndex": "0x3F6",
         "Errata": "BDM100, BDM35",
-        "PublicDescription": "This event counts loads with latency value being above 32.",
+        "PublicDescription": "Counts randomly selected loads with latency value being above 32.",
         "TakenAlone": "1",
         "SampleAfterValue": "100007",
         "CounterHTOff": "3"
@@ -372,14 +372,14 @@
     {
         "EventCode": "0xCD",
         "UMask": "0x1",
-        "BriefDescription": "Loads with latency value being above 64",
+        "BriefDescription": "Randomly selected loads with latency value being above 64",
         "PEBS": "2",
         "MSRValue": "0x40",
         "Counter": "3",
         "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_64",
         "MSRIndex": "0x3F6",
         "Errata": "BDM100, BDM35",
-        "PublicDescription": "This event counts loads with latency value being above 64.",
+        "PublicDescription": "Counts randomly selected loads with latency value being above 64.",
         "TakenAlone": "1",
         "SampleAfterValue": "2003",
         "CounterHTOff": "3"
@@ -387,14 +387,14 @@
     {
         "EventCode": "0xCD",
         "UMask": "0x1",
-        "BriefDescription": "Loads with latency value being above 128",
+        "BriefDescription": "Randomly selected loads with latency value being above 128",
         "PEBS": "2",
         "MSRValue": "0x80",
         "Counter": "3",
         "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_128",
         "MSRIndex": "0x3F6",
         "Errata": "BDM100, BDM35",
-        "PublicDescription": "This event counts loads with latency value being above 128.",
+        "PublicDescription": "Counts randomly selected loads with latency value being above 128.",
         "TakenAlone": "1",
         "SampleAfterValue": "1009",
         "CounterHTOff": "3"
@@ -402,14 +402,14 @@
     {
         "EventCode": "0xCD",
         "UMask": "0x1",
-        "BriefDescription": "Loads with latency value being above 256",
+        "BriefDescription": "Randomly selected loads with latency value being above 256",
         "PEBS": "2",
         "MSRValue": "0x100",
         "Counter": "3",
         "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_256",
         "MSRIndex": "0x3F6",
         "Errata": "BDM100, BDM35",
-        "PublicDescription": "This event counts loads with latency value being above 256.",
+        "PublicDescription": "Counts randomly selected loads with latency value being above 256.",
         "TakenAlone": "1",
         "SampleAfterValue": "503",
         "CounterHTOff": "3"
@@ -417,14 +417,14 @@
     {
         "EventCode": "0xCD",
         "UMask": "0x1",
-        "BriefDescription": "Loads with latency value being above 512",
+        "BriefDescription": "Randomly selected loads with latency value being above 512",
         "PEBS": "2",
         "MSRValue": "0x200",
         "Counter": "3",
         "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_512",
         "MSRIndex": "0x3F6",
         "Errata": "BDM100, BDM35",
-        "PublicDescription": "This event counts loads with latency value being above 512.",
+        "PublicDescription": "Counts randomly selected loads with latency value being above 512.",
         "TakenAlone": "1",
         "SampleAfterValue": "101",
         "CounterHTOff": "3"
@@ -433,12 +433,12 @@
         "Offcore": "1",
         "EventCode": "0xB7, 0xBB",
         "UMask": "0x1",
-        "BriefDescription": "Counts all requests that miss in the L3",
-        "MSRValue": "0x3fbfc08fff",
+        "BriefDescription": "Counts all requests miss in the L3",
+        "MSRValue": "0x3FBFC08FFF",
         "Counter": "0,1,2,3",
         "EventName": "OFFCORE_RESPONSE.ALL_REQUESTS.LLC_MISS.ANY_RESPONSE",
         "MSRIndex": "0x1a6,0x1a7",
-        "PublicDescription": "Counts all requests that miss in the L3 Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all requests miss in the L3",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -446,12 +446,12 @@
         "Offcore": "1",
         "EventCode": "0xB7, 0xBB",
         "UMask": "0x1",
-        "BriefDescription": "Counts all data/code/rfo reads (demand & prefetch) that miss the L3 and clean or shared data is transferred from remote cache",
-        "MSRValue": "0x087fc007f7",
+        "BriefDescription": "Counts all data/code/rfo reads (demand & prefetch) miss the L3 and clean or shared data is transferred from remote cache",
+        "MSRValue": "0x087FC007F7",
         "Counter": "0,1,2,3",
         "EventName": "OFFCORE_RESPONSE.ALL_READS.LLC_MISS.REMOTE_HIT_FORWARD",
         "MSRIndex": "0x1a6,0x1a7",
-        "PublicDescription": "Counts all data/code/rfo reads (demand & prefetch) that miss the L3 and clean or shared data is transferred from remote cache Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all data/code/rfo reads (demand & prefetch) miss the L3 and clean or shared data is transferred from remote cache",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -459,12 +459,12 @@
         "Offcore": "1",
         "EventCode": "0xB7, 0xBB",
         "UMask": "0x1",
-        "BriefDescription": "Counts all data/code/rfo reads (demand & prefetch) that miss the L3 and the modified data is transferred from remote cache",
-        "MSRValue": "0x103fc007f7",
+        "BriefDescription": "Counts all data/code/rfo reads (demand & prefetch) miss the L3 and the modified data is transferred from remote cache",
+        "MSRValue": "0x103FC007F7",
         "Counter": "0,1,2,3",
         "EventName": "OFFCORE_RESPONSE.ALL_READS.LLC_MISS.REMOTE_HITM",
         "MSRIndex": "0x1a6,0x1a7",
-        "PublicDescription": "Counts all data/code/rfo reads (demand & prefetch) that miss the L3 and the modified data is transferred from remote cache Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all data/code/rfo reads (demand & prefetch) miss the L3 and the modified data is transferred from remote cache",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -472,12 +472,12 @@
         "Offcore": "1",
         "EventCode": "0xB7, 0xBB",
         "UMask": "0x1",
-        "BriefDescription": "Counts all data/code/rfo reads (demand & prefetch) that miss the L3 and the data is returned from remote dram",
-        "MSRValue": "0x063bc007f7",
+        "BriefDescription": "Counts all data/code/rfo reads (demand & prefetch) miss the L3 and the data is returned from remote dram",
+        "MSRValue": "0x063BC007F7",
         "Counter": "0,1,2,3",
         "EventName": "OFFCORE_RESPONSE.ALL_READS.LLC_MISS.REMOTE_DRAM",
         "MSRIndex": "0x1a6,0x1a7",
-        "PublicDescription": "Counts all data/code/rfo reads (demand & prefetch) that miss the L3 and the data is returned from remote dram Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all data/code/rfo reads (demand & prefetch) miss the L3 and the data is returned from remote dram",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -485,12 +485,12 @@
         "Offcore": "1",
         "EventCode": "0xB7, 0xBB",
         "UMask": "0x1",
-        "BriefDescription": "Counts all data/code/rfo reads (demand & prefetch) that miss the L3 and the data is returned from local dram",
-        "MSRValue": "0x06040007f7",
+        "BriefDescription": "Counts all data/code/rfo reads (demand & prefetch) miss the L3 and the data is returned from local dram",
+        "MSRValue": "0x06040007F7",
         "Counter": "0,1,2,3",
         "EventName": "OFFCORE_RESPONSE.ALL_READS.LLC_MISS.LOCAL_DRAM",
         "MSRIndex": "0x1a6,0x1a7",
-        "PublicDescription": "Counts all data/code/rfo reads (demand & prefetch) that miss the L3 and the data is returned from local dram Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all data/code/rfo reads (demand & prefetch) miss the L3 and the data is returned from local dram",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -498,12 +498,12 @@
         "Offcore": "1",
         "EventCode": "0xB7, 0xBB",
         "UMask": "0x1",
-        "BriefDescription": "Counts all data/code/rfo reads (demand & prefetch) that miss in the L3",
-        "MSRValue": "0x3fbfc007f7",
+        "BriefDescription": "Counts all data/code/rfo reads (demand & prefetch) miss in the L3",
+        "MSRValue": "0x3FBFC007F7",
         "Counter": "0,1,2,3",
         "EventName": "OFFCORE_RESPONSE.ALL_READS.LLC_MISS.ANY_RESPONSE",
         "MSRIndex": "0x1a6,0x1a7",
-        "PublicDescription": "Counts all data/code/rfo reads (demand & prefetch) that miss in the L3 Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all data/code/rfo reads (demand & prefetch) miss in the L3",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -511,12 +511,12 @@
         "Offcore": "1",
         "EventCode": "0xB7, 0xBB",
         "UMask": "0x1",
-        "BriefDescription": "Counts all demand & prefetch code reads that miss the L3 and the data is returned from local dram",
+        "BriefDescription": "Counts all demand & prefetch code reads miss the L3 and the data is returned from local dram",
         "MSRValue": "0x0604000244",
         "Counter": "0,1,2,3",
         "EventName": "OFFCORE_RESPONSE.ALL_CODE_RD.LLC_MISS.LOCAL_DRAM",
         "MSRIndex": "0x1a6,0x1a7",
-        "PublicDescription": "Counts all demand & prefetch code reads that miss the L3 and the data is returned from local dram Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all demand & prefetch code reads miss the L3 and the data is returned from local dram",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -524,12 +524,12 @@
         "Offcore": "1",
         "EventCode": "0xB7, 0xBB",
         "UMask": "0x1",
-        "BriefDescription": "Counts all demand & prefetch code reads that miss in the L3",
-        "MSRValue": "0x3fbfc00244",
+        "BriefDescription": "Counts all demand & prefetch code reads miss in the L3",
+        "MSRValue": "0x3FBFC00244",
         "Counter": "0,1,2,3",
         "EventName": "OFFCORE_RESPONSE.ALL_CODE_RD.LLC_MISS.ANY_RESPONSE",
         "MSRIndex": "0x1a6,0x1a7",
-        "PublicDescription": "Counts all demand & prefetch code reads that miss in the L3 Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all demand & prefetch code reads miss in the L3",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -537,12 +537,12 @@
         "Offcore": "1",
         "EventCode": "0xB7, 0xBB",
         "UMask": "0x1",
-        "BriefDescription": "Counts all demand & prefetch RFOs that miss the L3 and the data is returned from local dram",
+        "BriefDescription": "Counts all demand & prefetch RFOs miss the L3 and the data is returned from local dram",
         "MSRValue": "0x0604000122",
         "Counter": "0,1,2,3",
         "EventName": "OFFCORE_RESPONSE.ALL_RFO.LLC_MISS.LOCAL_DRAM",
         "MSRIndex": "0x1a6,0x1a7",
-        "PublicDescription": "Counts all demand & prefetch RFOs that miss the L3 and the data is returned from local dram Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all demand & prefetch RFOs miss the L3 and the data is returned from local dram",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -550,12 +550,12 @@
         "Offcore": "1",
         "EventCode": "0xB7, 0xBB",
         "UMask": "0x1",
-        "BriefDescription": "Counts all demand & prefetch RFOs that miss in the L3",
-        "MSRValue": "0x3fbfc00122",
+        "BriefDescription": "Counts all demand & prefetch RFOs miss in the L3",
+        "MSRValue": "0x3FBFC00122",
         "Counter": "0,1,2,3",
         "EventName": "OFFCORE_RESPONSE.ALL_RFO.LLC_MISS.ANY_RESPONSE",
         "MSRIndex": "0x1a6,0x1a7",
-        "PublicDescription": "Counts all demand & prefetch RFOs that miss in the L3 Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all demand & prefetch RFOs miss in the L3",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -563,12 +563,12 @@
         "Offcore": "1",
         "EventCode": "0xB7, 0xBB",
         "UMask": "0x1",
-        "BriefDescription": "Counts all demand & prefetch data reads that miss the L3 and clean or shared data is transferred from remote cache",
-        "MSRValue": "0x087fc00091",
+        "BriefDescription": "Counts all demand & prefetch data reads miss the L3 and clean or shared data is transferred from remote cache",
+        "MSRValue": "0x087FC00091",
         "Counter": "0,1,2,3",
         "EventName": "OFFCORE_RESPONSE.ALL_DATA_RD.LLC_MISS.REMOTE_HIT_FORWARD",
         "MSRIndex": "0x1a6,0x1a7",
-        "PublicDescription": "Counts all demand & prefetch data reads that miss the L3 and clean or shared data is transferred from remote cache Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all demand & prefetch data reads miss the L3 and clean or shared data is transferred from remote cache",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -576,12 +576,12 @@
         "Offcore": "1",
         "EventCode": "0xB7, 0xBB",
         "UMask": "0x1",
-        "BriefDescription": "Counts all demand & prefetch data reads that miss the L3 and the modified data is transferred from remote cache",
-        "MSRValue": "0x103fc00091",
+        "BriefDescription": "Counts all demand & prefetch data reads miss the L3 and the modified data is transferred from remote cache",
+        "MSRValue": "0x103FC00091",
         "Counter": "0,1,2,3",
         "EventName": "OFFCORE_RESPONSE.ALL_DATA_RD.LLC_MISS.REMOTE_HITM",
         "MSRIndex": "0x1a6,0x1a7",
-        "PublicDescription": "Counts all demand & prefetch data reads that miss the L3 and the modified data is transferred from remote cache Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all demand & prefetch data reads miss the L3 and the modified data is transferred from remote cache",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -589,12 +589,12 @@
         "Offcore": "1",
         "EventCode": "0xB7, 0xBB",
         "UMask": "0x1",
-        "BriefDescription": "Counts all demand & prefetch data reads that miss the L3 and the data is returned from remote dram",
-        "MSRValue": "0x063bc00091",
+        "BriefDescription": "Counts all demand & prefetch data reads miss the L3 and the data is returned from remote dram",
+        "MSRValue": "0x063BC00091",
         "Counter": "0,1,2,3",
         "EventName": "OFFCORE_RESPONSE.ALL_DATA_RD.LLC_MISS.REMOTE_DRAM",
         "MSRIndex": "0x1a6,0x1a7",
-        "PublicDescription": "Counts all demand & prefetch data reads that miss the L3 and the data is returned from remote dram Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all demand & prefetch data reads miss the L3 and the data is returned from remote dram",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -602,12 +602,12 @@
         "Offcore": "1",
         "EventCode": "0xB7, 0xBB",
         "UMask": "0x1",
-        "BriefDescription": "Counts all demand & prefetch data reads that miss the L3 and the data is returned from local dram",
+        "BriefDescription": "Counts all demand & prefetch data reads miss the L3 and the data is returned from local dram",
         "MSRValue": "0x0604000091",
         "Counter": "0,1,2,3",
         "EventName": "OFFCORE_RESPONSE.ALL_DATA_RD.LLC_MISS.LOCAL_DRAM",
         "MSRIndex": "0x1a6,0x1a7",
-        "PublicDescription": "Counts all demand & prefetch data reads that miss the L3 and the data is returned from local dram Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all demand & prefetch data reads miss the L3 and the data is returned from local dram",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -615,12 +615,12 @@
         "Offcore": "1",
         "EventCode": "0xB7, 0xBB",
         "UMask": "0x1",
-        "BriefDescription": "Counts all demand & prefetch data reads that miss in the L3",
-        "MSRValue": "0x3fbfc00091",
+        "BriefDescription": "Counts all demand & prefetch data reads miss in the L3",
+        "MSRValue": "0x3FBFC00091",
         "Counter": "0,1,2,3",
         "EventName": "OFFCORE_RESPONSE.ALL_DATA_RD.LLC_MISS.ANY_RESPONSE",
         "MSRIndex": "0x1a6,0x1a7",
-        "PublicDescription": "Counts all demand & prefetch data reads that miss in the L3 Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all demand & prefetch data reads miss in the L3",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -628,12 +628,12 @@
         "Offcore": "1",
         "EventCode": "0xB7, 0xBB",
         "UMask": "0x1",
-        "BriefDescription": "Counts prefetch (that bring data to LLC only) code reads that miss in the L3",
-        "MSRValue": "0x3fbfc00200",
+        "BriefDescription": "Counts prefetch (that bring data to LLC only) code reads miss in the L3",
+        "MSRValue": "0x3FBFC00200",
         "Counter": "0,1,2,3",
         "EventName": "OFFCORE_RESPONSE.PF_LLC_CODE_RD.LLC_MISS.ANY_RESPONSE",
         "MSRIndex": "0x1a6,0x1a7",
-        "PublicDescription": "Counts prefetch (that bring data to LLC only) code reads that miss in the L3 Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts prefetch (that bring data to LLC only) code reads miss in the L3",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -641,12 +641,12 @@
         "Offcore": "1",
         "EventCode": "0xB7, 0xBB",
         "UMask": "0x1",
-        "BriefDescription": "Counts all prefetch (that bring data to LLC only) RFOs that miss in the L3",
-        "MSRValue": "0x3fbfc00100",
+        "BriefDescription": "Counts all prefetch (that bring data to LLC only) RFOs miss in the L3",
+        "MSRValue": "0x3FBFC00100",
         "Counter": "0,1,2,3",
         "EventName": "OFFCORE_RESPONSE.PF_LLC_RFO.LLC_MISS.ANY_RESPONSE",
         "MSRIndex": "0x1a6,0x1a7",
-        "PublicDescription": "Counts all prefetch (that bring data to LLC only) RFOs that miss in the L3 Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all prefetch (that bring data to LLC only) RFOs miss in the L3",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -654,12 +654,12 @@
         "Offcore": "1",
         "EventCode": "0xB7, 0xBB",
         "UMask": "0x1",
-        "BriefDescription": "Counts all demand data writes (RFOs) that miss the L3 and the modified data is transferred from remote cache",
-        "MSRValue": "0x103fc00002",
+        "BriefDescription": "Counts all demand data writes (RFOs) miss the L3 and the modified data is transferred from remote cache",
+        "MSRValue": "0x103FC00002",
         "Counter": "0,1,2,3",
         "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.LLC_MISS.REMOTE_HITM",
         "MSRIndex": "0x1a6,0x1a7",
-        "PublicDescription": "Counts all demand data writes (RFOs) that miss the L3 and the modified data is transferred from remote cache Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all demand data writes (RFOs) miss the L3 and the modified data is transferred from remote cache",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -667,12 +667,12 @@
         "Offcore": "1",
         "EventCode": "0xB7, 0xBB",
         "UMask": "0x1",
-        "BriefDescription": "Counts all demand data writes (RFOs) that miss in the L3",
-        "MSRValue": "0x3fbfc00002",
+        "BriefDescription": "Counts all demand data writes (RFOs) miss in the L3",
+        "MSRValue": "0x3FBFC00002",
         "Counter": "0,1,2,3",
         "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.LLC_MISS.ANY_RESPONSE",
         "MSRIndex": "0x1a6,0x1a7",
-        "PublicDescription": "Counts all demand data writes (RFOs) that miss in the L3 Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all demand data writes (RFOs) miss in the L3",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     }
diff --git a/tools/perf/pmu-events/arch/x86/broadwellx/pipeline.json b/tools/perf/pmu-events/arch/x86/broadwellx/pipeline.json
index 0d04bf9db000..c2f6932a5817 100644
--- a/tools/perf/pmu-events/arch/x86/broadwellx/pipeline.json
+++ b/tools/perf/pmu-events/arch/x86/broadwellx/pipeline.json
@@ -1,6 +1,5 @@
 [
     {
-        "EventCode": "0x00",
         "UMask": "0x1",
         "BriefDescription": "Instructions retired from execution.",
         "Counter": "Fixed counter 0",
@@ -10,7 +9,6 @@
         "CounterHTOff": "Fixed counter 0"
     },
     {
-        "EventCode": "0x00",
         "UMask": "0x2",
         "BriefDescription": "Core cycles when the thread is not in halt state",
         "Counter": "Fixed counter 1",
@@ -20,7 +18,6 @@
         "CounterHTOff": "Fixed counter 1"
     },
     {
-        "EventCode": "0x00",
         "UMask": "0x2",
         "BriefDescription": "Core cycles when at least one thread on the physical core is not in halt state.",
         "Counter": "Fixed counter 1",
@@ -30,7 +27,6 @@
         "CounterHTOff": "Fixed counter 1"
     },
     {
-        "EventCode": "0x00",
         "UMask": "0x3",
         "BriefDescription": "Reference cycles when the core is not in halt state.",
         "Counter": "Fixed counter 2",
@@ -322,7 +318,7 @@
         "BriefDescription": "Stalls caused by changing prefix length of the instruction.",
         "Counter": "0,1,2,3",
         "EventName": "ILD_STALL.LCP",
-        "PublicDescription": "This event counts stalls occurred due to changing prefix length (66, 67 or REX.W when they change the length of the decoded instruction). Occurrences counting is proportional to the number of prefixes in a 16B-line. This may result in the following penalties: three-cycle penalty for each LCP in a 16-byte chunk.",
+        "PublicDescription": "This event counts stalls occured due to changing prefix length (66, 67 or REX.W when they change the length of the decoded instruction). Occurrences counting is proportional to the number of prefixes in a 16B-line. This may result in the following penalties: three-cycle penalty for each LCP in a 16-byte chunk.",
         "SampleAfterValue": "2000003",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
@@ -786,12 +782,12 @@
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "EventCode": "0xA2",
+        "EventCode": "0xa2",
         "UMask": "0x1",
         "BriefDescription": "Resource-related stall cycles",
         "Counter": "0,1,2,3",
         "EventName": "RESOURCE_STALLS.ANY",
-        "PublicDescription": "This event counts resource-related stall cycles. Reasons for stalls can be as follows:\n - *any* u-arch structure got full (LB, SB, RS, ROB, BOB, LM, Physical Register Reclaim Table (PRRT), or Physical History Table (PHT) slots)\n - *any* u-arch structure got empty (like INT/SIMD FreeLists)\n - FPU control word (FPCW), MXCSR\nand others. This counts cycles that the pipeline backend blocked uop delivery from the front end.",
+        "PublicDescription": "This event counts resource-related stall cycles.",
         "SampleAfterValue": "2000003",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
@@ -1168,12 +1164,12 @@
     {
         "EventCode": "0xC2",
         "UMask": "0x1",
-        "BriefDescription": "Actually retired uops. (Precise Event - PEBS)",
+        "BriefDescription": "Actually retired uops.",
         "Data_LA": "1",
         "PEBS": "1",
         "Counter": "0,1,2,3",
         "EventName": "UOPS_RETIRED.ALL",
-        "PublicDescription": "This is a precise version (that is, uses PEBS) of the event that counts all actually retired uops. Counting increments by two for micro-fused uops, and by one for macro-fused and other uops. Maximal increment value for one cycle is eight.",
+        "PublicDescription": "This event counts all actually retired uops. Counting increments by two for micro-fused uops, and by one for macro-fused and other uops. Maximal increment value for one cycle is eight.",
         "SampleAfterValue": "2000003",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
@@ -1204,11 +1200,11 @@
     {
         "EventCode": "0xC2",
         "UMask": "0x2",
-        "BriefDescription": "Retirement slots used. (Precise Event - PEBS)",
+        "BriefDescription": "Retirement slots used.",
         "PEBS": "1",
         "Counter": "0,1,2,3",
         "EventName": "UOPS_RETIRED.RETIRE_SLOTS",
-        "PublicDescription": "This is a precise version (that is, uses PEBS) of the event that counts the number of retirement slots used.",
+        "PublicDescription": "This event counts the number of retirement slots used.",
         "SampleAfterValue": "2000003",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
@@ -1266,33 +1262,33 @@
     {
         "EventCode": "0xC4",
         "UMask": "0x1",
-        "BriefDescription": "Conditional branch instructions retired. (Precise Event - PEBS)",
+        "BriefDescription": "Conditional branch instructions retired.",
         "PEBS": "1",
         "Counter": "0,1,2,3",
         "EventName": "BR_INST_RETIRED.CONDITIONAL",
-        "PublicDescription": "This is a precise version (that is, uses PEBS) of the event that counts conditional branch instructions retired.",
+        "PublicDescription": "This event counts conditional branch instructions retired.",
         "SampleAfterValue": "400009",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
         "EventCode": "0xC4",
         "UMask": "0x2",
-        "BriefDescription": "Direct and indirect near call instructions retired. (Precise Event - PEBS)",
+        "BriefDescription": "Direct and indirect near call instructions retired.",
         "PEBS": "1",
         "Counter": "0,1,2,3",
         "EventName": "BR_INST_RETIRED.NEAR_CALL",
-        "PublicDescription": "This is a precise version (that is, uses PEBS) of the event that counts both direct and indirect near call instructions retired.",
+        "PublicDescription": "This event counts both direct and indirect near call instructions retired.",
         "SampleAfterValue": "100007",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
         "EventCode": "0xC4",
         "UMask": "0x2",
-        "BriefDescription": "Direct and indirect macro near call instructions retired (captured in ring 3). (Precise Event - PEBS)",
+        "BriefDescription": "Direct and indirect macro near call instructions retired (captured in ring 3).",
         "PEBS": "1",
         "Counter": "0,1,2,3",
         "EventName": "BR_INST_RETIRED.NEAR_CALL_R3",
-        "PublicDescription": "This is a precise version (that is, uses PEBS) of the event that counts both direct and indirect macro near call instructions retired (captured in ring 3).",
+        "PublicDescription": "This event counts both direct and indirect macro near call instructions retired (captured in ring 3).",
         "SampleAfterValue": "100007",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
@@ -1311,11 +1307,11 @@
     {
         "EventCode": "0xC4",
         "UMask": "0x8",
-        "BriefDescription": "Return instructions retired. (Precise Event - PEBS)",
+        "BriefDescription": "Return instructions retired.",
         "PEBS": "1",
         "Counter": "0,1,2,3",
         "EventName": "BR_INST_RETIRED.NEAR_RETURN",
-        "PublicDescription": "This is a precise version (that is, uses PEBS) of the event that counts return instructions retired.",
+        "PublicDescription": "This event counts return instructions retired.",
         "SampleAfterValue": "100007",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
@@ -1332,11 +1328,11 @@
     {
         "EventCode": "0xC4",
         "UMask": "0x20",
-        "BriefDescription": "Taken branch instructions retired. (Precise Event - PEBS)",
+        "BriefDescription": "Taken branch instructions retired.",
         "PEBS": "1",
         "Counter": "0,1,2,3",
         "EventName": "BR_INST_RETIRED.NEAR_TAKEN",
-        "PublicDescription": "This is a precise version (that is, uses PEBS) of the event that counts taken branch instructions retired.",
+        "PublicDescription": "This event counts taken branch instructions retired.",
         "SampleAfterValue": "400009",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
@@ -1364,11 +1360,11 @@
     {
         "EventCode": "0xC5",
         "UMask": "0x1",
-        "BriefDescription": "Mispredicted conditional branch instructions retired. (Precise Event - PEBS)",
+        "BriefDescription": "Mispredicted conditional branch instructions retired.",
         "PEBS": "1",
         "Counter": "0,1,2,3",
         "EventName": "BR_MISP_RETIRED.CONDITIONAL",
-        "PublicDescription": "This is a precise version (that is, uses PEBS) of the event that counts mispredicted conditional branch instructions retired.",
+        "PublicDescription": "This event counts mispredicted conditional branch instructions retired.",
         "SampleAfterValue": "400009",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
@@ -1386,22 +1382,22 @@
     {
         "EventCode": "0xC5",
         "UMask": "0x8",
-        "BriefDescription": "This event counts the number of mispredicted ret instructions retired.(Precise Event)",
+        "BriefDescription": "This event counts the number of mispredicted ret instructions retired. Non PEBS",
         "PEBS": "1",
         "Counter": "0,1,2,3",
         "EventName": "BR_MISP_RETIRED.RET",
-        "PublicDescription": "This is a precise version (that is, uses PEBS) of the event that counts mispredicted return instructions retired.",
+        "PublicDescription": "This event counts mispredicted return instructions retired.",
         "SampleAfterValue": "100007",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
         "EventCode": "0xC5",
         "UMask": "0x20",
-        "BriefDescription": "number of near branch instructions retired that were mispredicted and taken. (Precise Event - PEBS).",
+        "BriefDescription": "number of near branch instructions retired that were mispredicted and taken.",
         "PEBS": "1",
         "Counter": "0,1,2,3",
         "EventName": "BR_MISP_RETIRED.NEAR_TAKEN",
-        "PublicDescription": "Number of near branch instructions retired that were mispredicted and taken. (Precise Event - PEBS).",
+        "PublicDescription": "Number of near branch instructions retired that were mispredicted and taken.",
         "SampleAfterValue": "400009",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
diff --git a/tools/perf/pmu-events/arch/x86/cascadelakex/clx-metrics.json b/tools/perf/pmu-events/arch/x86/cascadelakex/clx-metrics.json
index 71e9737f4614..1a1a3501180a 100644
--- a/tools/perf/pmu-events/arch/x86/cascadelakex/clx-metrics.json
+++ b/tools/perf/pmu-events/arch/x86/cascadelakex/clx-metrics.json
@@ -1,164 +1,394 @@
 [
     {
-        "BriefDescription": "Instructions Per Cycle (per logical thread)",
+        "MetricExpr": "IDQ_UOPS_NOT_DELIVERED.CORE / (4 * cycles)",
+        "PublicDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend. Frontend denotes the first part of the processor core responsible to fetch operations that are executed later on by the Backend part. Within the Frontend; a branch predictor predicts the next address to fetch; cache-lines are fetched from the memory subsystem; parsed into instructions; and lastly decoded into micro-ops (uops). Ideally the Frontend can issue 4 uops every cycle to the Backend. Frontend Bound denotes unutilized issue-slots when there is no Backend stall; i.e. bubbles where Frontend delivered no uops while Backend could have accepted them. For example; stalls due to instruction-cache misses would be categorized under Frontend Bound.",
+        "BriefDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend",
+        "MetricGroup": "TopdownL1",
+        "MetricName": "Frontend_Bound"
+    },
+    {
+        "MetricExpr": "IDQ_UOPS_NOT_DELIVERED.CORE / (4 * (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )))",
+        "PublicDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend. Frontend denotes the first part of the processor core responsible to fetch operations that are executed later on by the Backend part. Within the Frontend; a branch predictor predicts the next address to fetch; cache-lines are fetched from the memory subsystem; parsed into instructions; and lastly decoded into micro-ops (uops). Ideally the Frontend can issue 4 uops every cycle to the Backend. Frontend Bound denotes unutilized issue-slots when there is no Backend stall; i.e. bubbles where Frontend delivered no uops while Backend could have accepted them. For example; stalls due to instruction-cache misses would be categorized under Frontend Bound. SMT version; use when SMT is enabled and measuring per logical CPU.",
+        "BriefDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend. SMT version; use when SMT is enabled and measuring per logical CPU.",
+        "MetricGroup": "TopdownL1_SMT",
+        "MetricName": "Frontend_Bound_SMT"
+    },
+    {
+        "MetricExpr": "( UOPS_ISSUED.ANY - UOPS_RETIRED.RETIRE_SLOTS + 4 * INT_MISC.RECOVERY_CYCLES ) / (4 * cycles)",
+        "PublicDescription": "This category represents fraction of slots wasted due to incorrect speculations. This include slots used to issue uops that do not eventually get retired and slots for which the issue-pipeline was blocked due to recovery from earlier incorrect speculation. For example; wasted work due to miss-predicted branches are categorized under Bad Speculation category. Incorrect data speculation followed by Memory Ordering Nukes is another example.",
+        "BriefDescription": "This category represents fraction of slots wasted due to incorrect speculations",
+        "MetricGroup": "TopdownL1",
+        "MetricName": "Bad_Speculation"
+    },
+    {
+        "MetricExpr": "( UOPS_ISSUED.ANY - UOPS_RETIRED.RETIRE_SLOTS + 4 * (( INT_MISC.RECOVERY_CYCLES_ANY / 2 )) ) / (4 * (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )))",
+        "PublicDescription": "This category represents fraction of slots wasted due to incorrect speculations. This include slots used to issue uops that do not eventually get retired and slots for which the issue-pipeline was blocked due to recovery from earlier incorrect speculation. For example; wasted work due to miss-predicted branches are categorized under Bad Speculation category. Incorrect data speculation followed by Memory Ordering Nukes is another example. SMT version; use when SMT is enabled and measuring per logical CPU.",
+        "BriefDescription": "This category represents fraction of slots wasted due to incorrect speculations. SMT version; use when SMT is enabled and measuring per logical CPU.",
+        "MetricGroup": "TopdownL1_SMT",
+        "MetricName": "Bad_Speculation_SMT"
+    },
+    {
+        "MetricExpr": "1 - ( (IDQ_UOPS_NOT_DELIVERED.CORE / (4 * cycles)) + (( UOPS_ISSUED.ANY - UOPS_RETIRED.RETIRE_SLOTS + 4 * INT_MISC.RECOVERY_CYCLES ) / (4 * cycles)) + (UOPS_RETIRED.RETIRE_SLOTS / (4 * cycles)) )",
+        "PublicDescription": "This category represents fraction of slots where no uops are being delivered due to a lack of required resources for accepting new uops in the Backend. Backend is the portion of the processor core where the out-of-order scheduler dispatches ready uops into their respective execution units; and once completed these uops get retired according to program order. For example; stalls due to data-cache misses or stalls due to the divider unit being overloaded are both categorized under Backend Bound. Backend Bound is further divided into two main categories: Memory Bound and Core Bound.",
+        "BriefDescription": "This category represents fraction of slots where no uops are being delivered due to a lack of required resources for accepting new uops in the Backend",
+        "MetricGroup": "TopdownL1",
+        "MetricName": "Backend_Bound"
+    },
+    {
+        "MetricExpr": "1 - ( (IDQ_UOPS_NOT_DELIVERED.CORE / (4 * (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )))) + (( UOPS_ISSUED.ANY - UOPS_RETIRED.RETIRE_SLOTS + 4 * (( INT_MISC.RECOVERY_CYCLES_ANY / 2 )) ) / (4 * (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )))) + (UOPS_RETIRED.RETIRE_SLOTS / (4 * (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )))) )",
+        "PublicDescription": "This category represents fraction of slots where no uops are being delivered due to a lack of required resources for accepting new uops in the Backend. Backend is the portion of the processor core where the out-of-order scheduler dispatches ready uops into their respective execution units; and once completed these uops get retired according to program order. For example; stalls due to data-cache misses or stalls due to the divider unit being overloaded are both categorized under Backend Bound. Backend Bound is further divided into two main categories: Memory Bound and Core Bound. SMT version; use when SMT is enabled and measuring per logical CPU.",
+        "BriefDescription": "This category represents fraction of slots where no uops are being delivered due to a lack of required resources for accepting new uops in the Backend. SMT version; use when SMT is enabled and measuring per logical CPU.",
+        "MetricGroup": "TopdownL1_SMT",
+        "MetricName": "Backend_Bound_SMT"
+    },
+    {
+        "MetricExpr": "UOPS_RETIRED.RETIRE_SLOTS / (4 * cycles)",
+        "PublicDescription": "This category represents fraction of slots utilized by useful work i.e. issued uops that eventually get retired. Ideally; all pipeline slots would be attributed to the Retiring category.  Retiring of 100% would indicate the maximum 4 uops retired per cycle has been achieved.  Maximizing Retiring typically increases the Instruction-Per-Cycle metric. Note that a high Retiring value does not necessary mean there is no room for more performance.  For example; Microcode assists are categorized under Retiring. They hurt performance and can often be avoided. ",
+        "BriefDescription": "This category represents fraction of slots utilized by useful work i.e. issued uops that eventually get retired",
+        "MetricGroup": "TopdownL1",
+        "MetricName": "Retiring"
+    },
+    {
+        "MetricExpr": "UOPS_RETIRED.RETIRE_SLOTS / (4 * (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )))",
+        "PublicDescription": "This category represents fraction of slots utilized by useful work i.e. issued uops that eventually get retired. Ideally; all pipeline slots would be attributed to the Retiring category.  Retiring of 100% would indicate the maximum 4 uops retired per cycle has been achieved.  Maximizing Retiring typically increases the Instruction-Per-Cycle metric. Note that a high Retiring value does not necessary mean there is no room for more performance.  For example; Microcode assists are categorized under Retiring. They hurt performance and can often be avoided. SMT version; use when SMT is enabled and measuring per logical CPU.",
+        "BriefDescription": "This category represents fraction of slots utilized by useful work i.e. issued uops that eventually get retired. SMT version; use when SMT is enabled and measuring per logical CPU.",
+        "MetricGroup": "TopdownL1_SMT",
+        "MetricName": "Retiring_SMT"
+    },
+    {
         "MetricExpr": "INST_RETIRED.ANY / CPU_CLK_UNHALTED.THREAD",
+        "BriefDescription": "Instructions Per Cycle (per logical thread)",
         "MetricGroup": "TopDownL1",
         "MetricName": "IPC"
     },
     {
-        "BriefDescription": "Uops Per Instruction",
         "MetricExpr": "UOPS_RETIRED.RETIRE_SLOTS / INST_RETIRED.ANY",
-        "MetricGroup": "Pipeline",
+        "BriefDescription": "Uops Per Instruction",
+        "MetricGroup": "Pipeline;Retiring",
         "MetricName": "UPI"
     },
     {
-        "BriefDescription": "Rough Estimation of fraction of fetched lines bytes that were likely consumed by program instructions",
-        "MetricExpr": "min( 1 , UOPS_ISSUED.ANY / ((UOPS_RETIRED.RETIRE_SLOTS / INST_RETIRED.ANY) * 64 * ( ICACHE_64B.IFTAG_HIT + ICACHE_64B.IFTAG_MISS ) / 4.1) )",
-        "MetricGroup": "Frontend",
+        "MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.NEAR_TAKEN",
+        "BriefDescription": "Instruction per taken branch",
+        "MetricGroup": "Branches;PGO",
+        "MetricName": "IpTB"
+    },
+    {
+        "MetricExpr": "BR_INST_RETIRED.ALL_BRANCHES / BR_INST_RETIRED.NEAR_TAKEN",
+        "BriefDescription": "Branch instructions per taken branch. ",
+        "MetricGroup": "Branches;PGO",
+        "MetricName": "BpTB"
+    },
+    {
+        "MetricExpr": "min( 1 , UOPS_ISSUED.ANY / ( (UOPS_RETIRED.RETIRE_SLOTS / INST_RETIRED.ANY) * 64 * ( ICACHE_64B.IFTAG_HIT + ICACHE_64B.IFTAG_MISS ) / 4.1 ) )",
+        "BriefDescription": "Rough Estimation of fraction of fetched lines bytes that were likely (includes speculatively fetches) consumed by program instructions",
+        "MetricGroup": "PGO",
         "MetricName": "IFetch_Line_Utilization"
     },
     {
-        "BriefDescription": "Fraction of Uops delivered by the DSB (aka Decoded Icache; or Uop Cache)",
-        "MetricExpr": "IDQ.DSB_UOPS / ( IDQ.DSB_UOPS + LSD.UOPS + IDQ.MITE_UOPS + IDQ.MS_UOPS )",
-        "MetricGroup": "DSB; Frontend_Bandwidth",
+        "MetricExpr": "IDQ.DSB_UOPS / (( IDQ.DSB_UOPS + LSD.UOPS + IDQ.MITE_UOPS + IDQ.MS_UOPS ))",
+        "BriefDescription": "Fraction of Uops delivered by the DSB (aka Decoded ICache; or Uop Cache)",
+        "MetricGroup": "DSB;Frontend_Bandwidth",
         "MetricName": "DSB_Coverage"
     },
     {
-        "BriefDescription": "Cycles Per Instruction (threaded)",
         "MetricExpr": "1 / (INST_RETIRED.ANY / cycles)",
+        "BriefDescription": "Cycles Per Instruction (threaded)",
         "MetricGroup": "Pipeline;Summary",
         "MetricName": "CPI"
     },
     {
-        "BriefDescription": "Per-thread actual clocks when the logical processor is active. This is called 'Clockticks' in VTune.",
         "MetricExpr": "CPU_CLK_UNHALTED.THREAD",
+        "BriefDescription": "Per-thread actual clocks when the logical processor is active.",
         "MetricGroup": "Summary",
         "MetricName": "CLKS"
     },
     {
-        "BriefDescription": "Total issue-pipeline slots",
-        "MetricExpr": "4*(( CPU_CLK_UNHALTED.THREAD_ANY / 2 ) if #SMT_on else cycles)",
+        "MetricExpr": "4 * cycles",
+        "BriefDescription": "Total issue-pipeline slots (per core)",
         "MetricGroup": "TopDownL1",
         "MetricName": "SLOTS"
     },
     {
-        "BriefDescription": "Total number of retired Instructions",
+        "MetricExpr": "4 * (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) ))",
+        "BriefDescription": "Total issue-pipeline slots (per core)",
+        "MetricGroup": "TopDownL1_SMT",
+        "MetricName": "SLOTS_SMT"
+    },
+    {
+        "MetricExpr": "INST_RETIRED.ANY / MEM_INST_RETIRED.ALL_LOADS",
+        "BriefDescription": "Instructions per Load (lower number means loads are more frequent)",
+        "MetricGroup": "Instruction_Type;L1_Bound",
+        "MetricName": "IpL"
+    },
+    {
+        "MetricExpr": "INST_RETIRED.ANY / MEM_INST_RETIRED.ALL_STORES",
+        "BriefDescription": "Instructions per Store",
+        "MetricGroup": "Instruction_Type;Store_Bound",
+        "MetricName": "IpS"
+    },
+    {
+        "MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.ALL_BRANCHES",
+        "BriefDescription": "Instructions per Branch",
+        "MetricGroup": "Branches;Instruction_Type;Port_5;Port_6",
+        "MetricName": "IpB"
+    },
+    {
+        "MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.NEAR_CALL",
+        "BriefDescription": "Instruction per (near) call",
+        "MetricGroup": "Branches",
+        "MetricName": "IpCall"
+    },
+    {
         "MetricExpr": "INST_RETIRED.ANY",
+        "BriefDescription": "Total number of retired Instructions",
         "MetricGroup": "Summary",
         "MetricName": "Instructions"
     },
     {
+        "MetricExpr": "INST_RETIRED.ANY / cycles",
         "BriefDescription": "Instructions Per Cycle (per physical core)",
-        "MetricExpr": "INST_RETIRED.ANY / (( CPU_CLK_UNHALTED.THREAD_ANY / 2 ) if #SMT_on else cycles)",
         "MetricGroup": "SMT",
         "MetricName": "CoreIPC"
     },
     {
+        "MetricExpr": "INST_RETIRED.ANY / (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) ))",
+        "BriefDescription": "Instructions Per Cycle (per physical core)",
+        "MetricGroup": "SMT",
+        "MetricName": "CoreIPC_SMT"
+    },
+    {
+        "MetricExpr": "(( 1 * ( FP_ARITH_INST_RETIRED.SCALAR_SINGLE + FP_ARITH_INST_RETIRED.SCALAR_DOUBLE ) + 2 * FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE + 4 * ( FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE + FP_ARITH_INST_RETIRED.256B_PACKED_DOUBLE ) + 8 * ( FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE + FP_ARITH_INST_RETIRED.512B_PACKED_DOUBLE ) + 16 * FP_ARITH_INST_RETIRED.512B_PACKED_SINGLE )) / cycles",
+        "BriefDescription": "Floating Point Operations Per Cycle",
+        "MetricGroup": "FLOPS",
+        "MetricName": "FLOPc"
+    },
+    {
+        "MetricExpr": "(( 1 * ( FP_ARITH_INST_RETIRED.SCALAR_SINGLE + FP_ARITH_INST_RETIRED.SCALAR_DOUBLE ) + 2 * FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE + 4 * ( FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE + FP_ARITH_INST_RETIRED.256B_PACKED_DOUBLE ) + 8 * ( FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE + FP_ARITH_INST_RETIRED.512B_PACKED_DOUBLE ) + 16 * FP_ARITH_INST_RETIRED.512B_PACKED_SINGLE )) / (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) ))",
+        "BriefDescription": "Floating Point Operations Per Cycle",
+        "MetricGroup": "FLOPS_SMT",
+        "MetricName": "FLOPc_SMT"
+    },
+    {
+        "MetricExpr": "UOPS_EXECUTED.THREAD / (( UOPS_EXECUTED.CORE_CYCLES_GE_1 / 2 ) if #SMT_on else UOPS_EXECUTED.CORE_CYCLES_GE_1)",
         "BriefDescription": "Instruction-Level-Parallelism (average number of uops executed when there is at least 1 uop executed)",
-        "MetricExpr": "UOPS_EXECUTED.THREAD / (( UOPS_EXECUTED.CORE_CYCLES_GE_1 / 2) if #SMT_on else UOPS_EXECUTED.CORE_CYCLES_GE_1)",
         "MetricGroup": "Pipeline;Ports_Utilization",
         "MetricName": "ILP"
     },
     {
-        "BriefDescription": "Average Branch Address Clear Cost (fraction of cycles)",
-        "MetricExpr": "2* (( RS_EVENTS.EMPTY_CYCLES - ICACHE_16B.IFDATA_STALL  - ICACHE_64B.IFTAG_STALL ) / RS_EVENTS.EMPTY_END)",
-        "MetricGroup": "Unknown_Branches",
-        "MetricName": "BAClear_Cost"
+        "MetricExpr": "( ((BR_MISP_RETIRED.ALL_BRANCHES / ( BR_MISP_RETIRED.ALL_BRANCHES + MACHINE_CLEARS.COUNT )) * (( UOPS_ISSUED.ANY - UOPS_RETIRED.RETIRE_SLOTS + 4 * INT_MISC.RECOVERY_CYCLES ) / (4 * cycles))) + (4 * IDQ_UOPS_NOT_DELIVERED.CYCLES_0_UOPS_DELIV.CORE / (4 * cycles)) * (( INT_MISC.CLEAR_RESTEER_CYCLES + 9 * BACLEARS.ANY ) / cycles) / (4 * IDQ_UOPS_NOT_DELIVERED.CYCLES_0_UOPS_DELIV.CORE / (4 * cycles)) ) * (4 * cycles) / BR_MISP_RETIRED.ALL_BRANCHES",
+        "BriefDescription": "Branch Misprediction Cost: Fraction of TopDown slots wasted per branch misprediction (jeclear and baclear)",
+        "MetricGroup": "Branch_Mispredicts",
+        "MetricName": "Branch_Misprediction_Cost"
+    },
+    {
+        "MetricExpr": "( ((BR_MISP_RETIRED.ALL_BRANCHES / ( BR_MISP_RETIRED.ALL_BRANCHES + MACHINE_CLEARS.COUNT )) * (( UOPS_ISSUED.ANY - UOPS_RETIRED.RETIRE_SLOTS + 4 * (( INT_MISC.RECOVERY_CYCLES_ANY / 2 )) ) / (4 * (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) ))))) + (4 * IDQ_UOPS_NOT_DELIVERED.CYCLES_0_UOPS_DELIV.CORE / (4 * (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )))) * (( INT_MISC.CLEAR_RESTEER_CYCLES + 9 * BACLEARS.ANY ) / cycles) / (4 * IDQ_UOPS_NOT_DELIVERED.CYCLES_0_UOPS_DELIV.CORE / (4 * (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )))) ) * (4 * (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) ))) / BR_MISP_RETIRED.ALL_BRANCHES",
+        "BriefDescription": "Branch Misprediction Cost: Fraction of TopDown slots wasted per branch misprediction (jeclear and baclear)",
+        "MetricGroup": "Branch_Mispredicts_SMT",
+        "MetricName": "Branch_Misprediction_Cost_SMT"
     },
     {
+        "MetricExpr": "INST_RETIRED.ANY / BR_MISP_RETIRED.ALL_BRANCHES",
+        "BriefDescription": "Number of Instructions per non-speculative Branch Misprediction (JEClear)",
+        "MetricGroup": "Branch_Mispredicts",
+        "MetricName": "IpMispredict"
+    },
+    {
+        "MetricExpr": "( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )",
         "BriefDescription": "Core actual clocks when any thread is active on the physical core",
-        "MetricExpr": "( CPU_CLK_UNHALTED.THREAD_ANY / 2 ) if #SMT_on else CPU_CLK_UNHALTED.THREAD",
         "MetricGroup": "SMT",
         "MetricName": "CORE_CLKS"
     },
     {
-        "BriefDescription": "Actual Average Latency for L1 data-cache miss demand loads",
         "MetricExpr": "L1D_PEND_MISS.PENDING / ( MEM_LOAD_RETIRED.L1_MISS + MEM_LOAD_RETIRED.FB_HIT )",
+        "BriefDescription": "Actual Average Latency for L1 data-cache miss demand loads (in core cycles)",
         "MetricGroup": "Memory_Bound;Memory_Lat",
         "MetricName": "Load_Miss_Real_Latency"
     },
     {
-        "BriefDescription": "Memory-Level-Parallelism (average number of L1 miss demand load when there is at least 1 such miss)",
-        "MetricExpr": "L1D_PEND_MISS.PENDING / (( L1D_PEND_MISS.PENDING_CYCLES_ANY / 2) if #SMT_on else L1D_PEND_MISS.PENDING_CYCLES)",
+        "MetricExpr": "L1D_PEND_MISS.PENDING / L1D_PEND_MISS.PENDING_CYCLES",
+        "BriefDescription": "Memory-Level-Parallelism (average number of L1 miss demand load when there is at least one such miss. Per-thread)",
         "MetricGroup": "Memory_Bound;Memory_BW",
         "MetricName": "MLP"
     },
     {
+        "MetricExpr": "( ITLB_MISSES.WALK_PENDING + DTLB_LOAD_MISSES.WALK_PENDING + DTLB_STORE_MISSES.WALK_PENDING + EPT.WALK_PENDING ) / ( 2 * cycles )",
         "BriefDescription": "Utilization of the core's Page Walker(s) serving STLB misses triggered by instruction/Load/Store accesses",
-        "MetricExpr": "( ITLB_MISSES.WALK_PENDING + DTLB_LOAD_MISSES.WALK_PENDING + DTLB_STORE_MISSES.WALK_PENDING + EPT.WALK_PENDING ) / ( 2 * (( CPU_CLK_UNHALTED.THREAD_ANY / 2 ) if #SMT_on else cycles) )",
         "MetricGroup": "TLB",
         "MetricName": "Page_Walks_Utilization"
     },
     {
-        "BriefDescription": "Average CPU Utilization",
+        "MetricExpr": "( ITLB_MISSES.WALK_PENDING + DTLB_LOAD_MISSES.WALK_PENDING + DTLB_STORE_MISSES.WALK_PENDING + EPT.WALK_PENDING ) / ( 2 * (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )) )",
+        "BriefDescription": "Utilization of the core's Page Walker(s) serving STLB misses triggered by instruction/Load/Store accesses",
+        "MetricGroup": "TLB_SMT",
+        "MetricName": "Page_Walks_Utilization_SMT"
+    },
+    {
+        "MetricExpr": "64 * L1D.REPLACEMENT / 1000000000 / duration_time",
+        "BriefDescription": "Average data fill bandwidth to the L1 data cache [GB / sec]",
+        "MetricGroup": "Memory_BW",
+        "MetricName": "L1D_Cache_Fill_BW"
+    },
+    {
+        "MetricExpr": "64 * L2_LINES_IN.ALL / 1000000000 / duration_time",
+        "BriefDescription": "Average data fill bandwidth to the L2 cache [GB / sec]",
+        "MetricGroup": "Memory_BW",
+        "MetricName": "L2_Cache_Fill_BW"
+    },
+    {
+        "MetricExpr": "64 * LONGEST_LAT_CACHE.MISS / 1000000000 / duration_time",
+        "BriefDescription": "Average per-core data fill bandwidth to the L3 cache [GB / sec]",
+        "MetricGroup": "Memory_BW",
+        "MetricName": "L3_Cache_Fill_BW"
+    },
+    {
+        "MetricExpr": "64 * OFFCORE_REQUESTS.ALL_REQUESTS / 1000000000 / duration_time",
+        "BriefDescription": "Average per-core data fill bandwidth to the L3 cache [GB / sec]",
+        "MetricGroup": "Memory_BW",
+        "MetricName": "L3_Cache_Access_BW"
+    },
+    {
+        "MetricExpr": "1000 * MEM_LOAD_RETIRED.L1_MISS / INST_RETIRED.ANY",
+        "BriefDescription": "L1 cache true misses per kilo instruction for retired demand loads",
+        "MetricGroup": "Cache_Misses;",
+        "MetricName": "L1MPKI"
+    },
+    {
+        "MetricExpr": "1000 * MEM_LOAD_RETIRED.L2_MISS / INST_RETIRED.ANY",
+        "BriefDescription": "L2 cache true misses per kilo instruction for retired demand loads",
+        "MetricGroup": "Cache_Misses;",
+        "MetricName": "L2MPKI"
+    },
+    {
+        "MetricExpr": "1000 * L2_RQSTS.MISS / INST_RETIRED.ANY",
+        "BriefDescription": "L2 cache misses per kilo instruction for all request types (including speculative)",
+        "MetricGroup": "Cache_Misses;",
+        "MetricName": "L2MPKI_All"
+    },
+    {
+        "MetricExpr": "1000 * ( L2_RQSTS.REFERENCES - L2_RQSTS.MISS ) / INST_RETIRED.ANY",
+        "BriefDescription": "L2 cache hits per kilo instruction for all request types (including speculative)",
+        "MetricGroup": "Cache_Misses;",
+        "MetricName": "L2HPKI_All"
+    },
+    {
+        "MetricExpr": "1000 * MEM_LOAD_RETIRED.L3_MISS / INST_RETIRED.ANY",
+        "BriefDescription": "L3 cache true misses per kilo instruction for retired demand loads",
+        "MetricGroup": "Cache_Misses;",
+        "MetricName": "L3MPKI"
+    },
+    {
         "MetricExpr": "CPU_CLK_UNHALTED.REF_TSC / msr@tsc@",
+        "BriefDescription": "Average CPU Utilization",
         "MetricGroup": "Summary",
         "MetricName": "CPU_Utilization"
     },
     {
+        "MetricExpr": "( (( 1 * ( FP_ARITH_INST_RETIRED.SCALAR_SINGLE + FP_ARITH_INST_RETIRED.SCALAR_DOUBLE ) + 2 * FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE + 4 * ( FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE + FP_ARITH_INST_RETIRED.256B_PACKED_DOUBLE ) + 8 * ( FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE + FP_ARITH_INST_RETIRED.512B_PACKED_DOUBLE ) + 16 * FP_ARITH_INST_RETIRED.512B_PACKED_SINGLE )) / 1000000000 ) / duration_time",
         "BriefDescription": "Giga Floating Point Operations Per Second",
-        "MetricExpr": "(( 1*( FP_ARITH_INST_RETIRED.SCALAR_SINGLE + FP_ARITH_INST_RETIRED.SCALAR_DOUBLE ) + 2* FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE + 4*( FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE + FP_ARITH_INST_RETIRED.256B_PACKED_DOUBLE ) + 8* FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE )) / 1000000000 / duration_time",
         "MetricGroup": "FLOPS;Summary",
         "MetricName": "GFLOPs"
     },
     {
-        "BriefDescription": "Average Frequency Utilization relative nominal frequency",
         "MetricExpr": "CPU_CLK_UNHALTED.THREAD / CPU_CLK_UNHALTED.REF_TSC",
+        "BriefDescription": "Average Frequency Utilization relative nominal frequency",
         "MetricGroup": "Power",
         "MetricName": "Turbo_Utilization"
     },
     {
-        "BriefDescription": "Fraction of cycles where both hardware threads were active",
         "MetricExpr": "1 - CPU_CLK_THREAD_UNHALTED.ONE_THREAD_ACTIVE / ( CPU_CLK_THREAD_UNHALTED.REF_XCLK_ANY / 2 ) if #SMT_on else 0",
+        "BriefDescription": "Fraction of cycles where both hardware threads were active",
         "MetricGroup": "SMT;Summary",
         "MetricName": "SMT_2T_Utilization"
     },
     {
-        "BriefDescription": "Fraction of cycles spent in Kernel mode",
         "MetricExpr": "CPU_CLK_UNHALTED.REF_TSC:u / CPU_CLK_UNHALTED.REF_TSC",
+        "BriefDescription": "Fraction of cycles spent in Kernel mode",
         "MetricGroup": "Summary",
         "MetricName": "Kernel_Utilization"
     },
     {
-        "BriefDescription": "C3 residency percent per core",
+        "MetricExpr": "( 64 * ( uncore_imc@cas_count_read@ + uncore_imc@cas_count_write@ ) / 1000000000 ) / duration_time",
+        "BriefDescription": "Average external Memory Bandwidth Use for reads and writes [GB / sec]",
+        "MetricGroup": "Memory_BW",
+        "MetricName": "DRAM_BW_Use"
+    },
+    {
+        "MetricExpr": "1000000000 * ( cha@event\\=0x36\\\\\\,umask\\=0x21@ / cha@event\\=0x35\\\\\\,umask\\=0x21@ ) / ( cha_0@event\\=0x0@ / duration_time )",
+        "BriefDescription": "Average latency of data read request to external memory (in nanoseconds). Accounts for demand loads and L1/L2 prefetches",
+        "MetricGroup": "Memory_Lat",
+        "MetricName": "DRAM_Read_Latency"
+    },
+    {
+        "MetricExpr": "cha@event\\=0x36\\\\\\,umask\\=0x21@ / cha@event\\=0x36\\\\\\,umask\\=0x21\\\\\\,thresh\\=1@",
+        "BriefDescription": "Average number of parallel data read requests to external memory. Accounts for demand loads and L1/L2 prefetches",
+        "MetricGroup": "Memory_BW",
+        "MetricName": "DRAM_Parallel_Reads"
+    },
+    {
+        "MetricExpr": "( 1000000000 * ( imc@event\\=0xe0\\\\\\,umask\\=0x1@ / imc@event\\=0xe3@ ) / imc_0@event\\=0x0@ ) if 1 if 1 == 1 else 0 else 0",
+        "BriefDescription": "Average latency of data read request to external 3D X-Point memory [in nanoseconds]. Accounts for demand loads and L1/L2 data-read prefetches",
+        "MetricGroup": "Memory_Lat",
+        "MetricName": "MEM_PMM_Read_Latency"
+    },
+    {
+        "MetricExpr": "( ( 64 * imc@event\\=0xe3@ / 1000000000 ) / duration_time ) if 1 if 1 == 1 else 0 else 0",
+        "BriefDescription": "Average 3DXP Memory Bandwidth Use for reads [GB / sec]",
+        "MetricGroup": "Memory_BW",
+        "MetricName": "PMM_Read_BW"
+    },
+    {
+        "MetricExpr": "( ( 64 * imc@event\\=0xe7@ / 1000000000 ) / duration_time ) if 1 if 1 == 1 else 0 else 0",
+        "BriefDescription": "Average 3DXP Memory Bandwidth Use for Writes [GB / sec]",
+        "MetricGroup": "Memory_BW",
+        "MetricName": "PMM_Write_BW"
+    },
+    {
+        "MetricExpr": "cha_0@event\\=0x0@",
+        "BriefDescription": "Socket actual clocks when any core is active on that socket",
+        "MetricGroup": "",
+        "MetricName": "Socket_CLKS"
+    },
+    {
         "MetricExpr": "(cstate_core@c3\\-residency@ / msr@tsc@) * 100",
         "MetricGroup": "Power",
+        "BriefDescription": "C3 residency percent per core",
         "MetricName": "C3_Core_Residency"
     },
     {
-        "BriefDescription": "C6 residency percent per core",
         "MetricExpr": "(cstate_core@c6\\-residency@ / msr@tsc@) * 100",
         "MetricGroup": "Power",
+        "BriefDescription": "C6 residency percent per core",
         "MetricName": "C6_Core_Residency"
     },
     {
-        "BriefDescription": "C7 residency percent per core",
         "MetricExpr": "(cstate_core@c7\\-residency@ / msr@tsc@) * 100",
         "MetricGroup": "Power",
+        "BriefDescription": "C7 residency percent per core",
         "MetricName": "C7_Core_Residency"
     },
     {
-        "BriefDescription": "C2 residency percent per package",
         "MetricExpr": "(cstate_pkg@c2\\-residency@ / msr@tsc@) * 100",
         "MetricGroup": "Power",
+        "BriefDescription": "C2 residency percent per package",
         "MetricName": "C2_Pkg_Residency"
     },
     {
-        "BriefDescription": "C3 residency percent per package",
         "MetricExpr": "(cstate_pkg@c3\\-residency@ / msr@tsc@) * 100",
         "MetricGroup": "Power",
+        "BriefDescription": "C3 residency percent per package",
         "MetricName": "C3_Pkg_Residency"
     },
     {
-        "BriefDescription": "C6 residency percent per package",
         "MetricExpr": "(cstate_pkg@c6\\-residency@ / msr@tsc@) * 100",
         "MetricGroup": "Power",
+        "BriefDescription": "C6 residency percent per package",
         "MetricName": "C6_Pkg_Residency"
     },
     {
-        "BriefDescription": "C7 residency percent per package",
         "MetricExpr": "(cstate_pkg@c7\\-residency@ / msr@tsc@) * 100",
         "MetricGroup": "Power",
+        "BriefDescription": "C7 residency percent per package",
         "MetricName": "C7_Pkg_Residency"
     }
 ]
diff --git a/tools/perf/pmu-events/arch/x86/goldmont/cache.json b/tools/perf/pmu-events/arch/x86/goldmont/cache.json
index f8bbe087b0f8..52a105666afc 100644
--- a/tools/perf/pmu-events/arch/x86/goldmont/cache.json
+++ b/tools/perf/pmu-events/arch/x86/goldmont/cache.json
@@ -77,7 +77,8 @@
         "UMask": "0x21",
         "EventName": "MEM_UOPS_RETIRED.LOCK_LOADS",
         "SampleAfterValue": "200003",
-        "BriefDescription": "Locked load uops retired (Precise event capable)"
+        "BriefDescription": "Locked load uops retired (Precise event capable)",
+        "Data_LA": "1"
     },
     {
         "PEBS": "2",
@@ -88,7 +89,8 @@
         "UMask": "0x41",
         "EventName": "MEM_UOPS_RETIRED.SPLIT_LOADS",
         "SampleAfterValue": "200003",
-        "BriefDescription": "Load uops retired that split a cache-line (Precise event capable)"
+        "BriefDescription": "Load uops retired that split a cache-line (Precise event capable)",
+        "Data_LA": "1"
     },
     {
         "PEBS": "2",
@@ -99,7 +101,8 @@
         "UMask": "0x42",
         "EventName": "MEM_UOPS_RETIRED.SPLIT_STORES",
         "SampleAfterValue": "200003",
-        "BriefDescription": "Stores uops retired that split a cache-line (Precise event capable)"
+        "BriefDescription": "Stores uops retired that split a cache-line (Precise event capable)",
+        "Data_LA": "1"
     },
     {
         "PEBS": "2",
@@ -110,7 +113,8 @@
         "UMask": "0x43",
         "EventName": "MEM_UOPS_RETIRED.SPLIT",
         "SampleAfterValue": "200003",
-        "BriefDescription": "Memory uops retired that split a cache-line (Precise event capable)"
+        "BriefDescription": "Memory uops retired that split a cache-line (Precise event capable)",
+        "Data_LA": "1"
     },
     {
         "PEBS": "2",
@@ -121,7 +125,8 @@
         "UMask": "0x81",
         "EventName": "MEM_UOPS_RETIRED.ALL_LOADS",
         "SampleAfterValue": "200003",
-        "BriefDescription": "Load uops retired (Precise event capable)"
+        "BriefDescription": "Load uops retired (Precise event capable)",
+        "Data_LA": "1"
     },
     {
         "PEBS": "2",
@@ -132,7 +137,8 @@
         "UMask": "0x82",
         "EventName": "MEM_UOPS_RETIRED.ALL_STORES",
         "SampleAfterValue": "200003",
-        "BriefDescription": "Store uops retired (Precise event capable)"
+        "BriefDescription": "Store uops retired (Precise event capable)",
+        "Data_LA": "1"
     },
     {
         "PEBS": "2",
@@ -143,7 +149,8 @@
         "UMask": "0x83",
         "EventName": "MEM_UOPS_RETIRED.ALL",
         "SampleAfterValue": "200003",
-        "BriefDescription": "Memory uops retired (Precise event capable)"
+        "BriefDescription": "Memory uops retired (Precise event capable)",
+        "Data_LA": "1"
     },
     {
         "PEBS": "2",
@@ -154,7 +161,8 @@
         "UMask": "0x1",
         "EventName": "MEM_LOAD_UOPS_RETIRED.L1_HIT",
         "SampleAfterValue": "200003",
-        "BriefDescription": "Load uops retired that hit L1 data cache (Precise event capable)"
+        "BriefDescription": "Load uops retired that hit L1 data cache (Precise event capable)",
+        "Data_LA": "1"
     },
     {
         "PEBS": "2",
@@ -165,7 +173,8 @@
         "UMask": "0x2",
         "EventName": "MEM_LOAD_UOPS_RETIRED.L2_HIT",
         "SampleAfterValue": "200003",
-        "BriefDescription": "Load uops retired that hit L2 (Precise event capable)"
+        "BriefDescription": "Load uops retired that hit L2 (Precise event capable)",
+        "Data_LA": "1"
     },
     {
         "PEBS": "2",
@@ -176,7 +185,8 @@
         "UMask": "0x8",
         "EventName": "MEM_LOAD_UOPS_RETIRED.L1_MISS",
         "SampleAfterValue": "200003",
-        "BriefDescription": "Load uops retired that missed L1 data cache (Precise event capable)"
+        "BriefDescription": "Load uops retired that missed L1 data cache (Precise event capable)",
+        "Data_LA": "1"
     },
     {
         "PEBS": "2",
@@ -187,7 +197,8 @@
         "UMask": "0x10",
         "EventName": "MEM_LOAD_UOPS_RETIRED.L2_MISS",
         "SampleAfterValue": "200003",
-        "BriefDescription": "Load uops retired that missed L2 (Precise event capable)"
+        "BriefDescription": "Load uops retired that missed L2 (Precise event capable)",
+        "Data_LA": "1"
     },
     {
         "PEBS": "2",
@@ -198,7 +209,8 @@
         "UMask": "0x20",
         "EventName": "MEM_LOAD_UOPS_RETIRED.HITM",
         "SampleAfterValue": "200003",
-        "BriefDescription": "Memory uop retired where cross core or cross module HITM occurred (Precise event capable)"
+        "BriefDescription": "Memory uop retired where cross core or cross module HITM occurred (Precise event capable)",
+        "Data_LA": "1"
     },
     {
         "PEBS": "2",
@@ -209,7 +221,8 @@
         "UMask": "0x40",
         "EventName": "MEM_LOAD_UOPS_RETIRED.WCB_HIT",
         "SampleAfterValue": "200003",
-        "BriefDescription": "Loads retired that hit WCB (Precise event capable)"
+        "BriefDescription": "Loads retired that hit WCB (Precise event capable)",
+        "Data_LA": "1"
     },
     {
         "PEBS": "2",
@@ -220,26 +233,14 @@
         "UMask": "0x80",
         "EventName": "MEM_LOAD_UOPS_RETIRED.DRAM_HIT",
         "SampleAfterValue": "200003",
-        "BriefDescription": "Loads retired that came from DRAM (Precise event capable)"
-    },
-    {
-        "CollectPEBSRecord": "1",
-        "PublicDescription": "Counts data read, code read, and read for ownership (RFO) requests (demand & prefetch) that are outstanding, per cycle, from the time of the L2 miss to when any response is received. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
-        "EventCode": "0xB7",
-        "MSRValue": "0x40000032b7 ",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.ANY_READ.OUTSTANDING",
-        "MSRIndex": "0x1a6",
-        "SampleAfterValue": "100007",
-        "BriefDescription": "Counts data read, code read, and read for ownership (RFO) requests (demand & prefetch) that are outstanding, per cycle, from the time of the L2 miss to when any response is received.",
-        "Offcore": "1"
+        "BriefDescription": "Loads retired that came from DRAM (Precise event capable)",
+        "Data_LA": "1"
     },
     {
         "CollectPEBSRecord": "1",
         "PublicDescription": "Counts data read, code read, and read for ownership (RFO) requests (demand & prefetch) that miss the L2 cache. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
         "EventCode": "0xB7",
-        "MSRValue": "0x36000032b7 ",
+        "MSRValue": "0x36000032b7",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.ANY_READ.L2_MISS.ANY",
@@ -252,7 +253,7 @@
         "CollectPEBSRecord": "1",
         "PublicDescription": "Counts data read, code read, and read for ownership (RFO) requests (demand & prefetch) that miss the L2 cache with a snoop hit in the other processor module, data forwarding is required. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
         "EventCode": "0xB7",
-        "MSRValue": "0x10000032b7 ",
+        "MSRValue": "0x10000032b7",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.ANY_READ.L2_MISS.HITM_OTHER_CORE",
@@ -265,7 +266,7 @@
         "CollectPEBSRecord": "1",
         "PublicDescription": "Counts data read, code read, and read for ownership (RFO) requests (demand & prefetch) that miss the L2 cache with a snoop hit in the other processor module, no data forwarding is required. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
         "EventCode": "0xB7",
-        "MSRValue": "0x04000032b7 ",
+        "MSRValue": "0x04000032b7",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.ANY_READ.L2_MISS.HIT_OTHER_CORE_NO_FWD",
@@ -278,20 +279,20 @@
         "CollectPEBSRecord": "1",
         "PublicDescription": "Counts data read, code read, and read for ownership (RFO) requests (demand & prefetch) that true miss for the L2 cache with a snoop miss in the other processor module.  Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
         "EventCode": "0xB7",
-        "MSRValue": "0x02000032b7 ",
+        "MSRValue": "0x02000032b7",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.ANY_READ.L2_MISS.SNOOP_MISS_OR_NO_SNOOP_NEEDED",
         "MSRIndex": "0x1a6,0x1a7",
         "SampleAfterValue": "100007",
-        "BriefDescription": "Counts data read, code read, and read for ownership (RFO) requests (demand & prefetch) that true miss for the L2 cache with a snoop miss in the other processor module. ",
+        "BriefDescription": "Counts data read, code read, and read for ownership (RFO) requests (demand & prefetch) that true miss for the L2 cache with a snoop miss in the other processor module.",
         "Offcore": "1"
     },
     {
         "CollectPEBSRecord": "1",
         "PublicDescription": "Counts data read, code read, and read for ownership (RFO) requests (demand & prefetch) that hit the L2 cache. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
         "EventCode": "0xB7",
-        "MSRValue": "0x00000432b7 ",
+        "MSRValue": "0x00000432b7",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.ANY_READ.L2_HIT",
@@ -302,35 +303,9 @@
     },
     {
         "CollectPEBSRecord": "1",
-        "PublicDescription": "Counts data read, code read, and read for ownership (RFO) requests (demand & prefetch) that have any transaction responses from the uncore subsystem. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
-        "EventCode": "0xB7",
-        "MSRValue": "0x00000132b7 ",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.ANY_READ.ANY_RESPONSE",
-        "MSRIndex": "0x1a6,0x1a7",
-        "SampleAfterValue": "100007",
-        "BriefDescription": "Counts data read, code read, and read for ownership (RFO) requests (demand & prefetch) that have any transaction responses from the uncore subsystem.",
-        "Offcore": "1"
-    },
-    {
-        "CollectPEBSRecord": "1",
-        "PublicDescription": "Counts reads for ownership (RFO) requests (demand & prefetch) that are outstanding, per cycle, from the time of the L2 miss to when any response is received. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
-        "EventCode": "0xB7",
-        "MSRValue": "0x4000000022 ",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.ANY_RFO.OUTSTANDING",
-        "MSRIndex": "0x1a6",
-        "SampleAfterValue": "100007",
-        "BriefDescription": "Counts reads for ownership (RFO) requests (demand & prefetch) that are outstanding, per cycle, from the time of the L2 miss to when any response is received.",
-        "Offcore": "1"
-    },
-    {
-        "CollectPEBSRecord": "1",
         "PublicDescription": "Counts reads for ownership (RFO) requests (demand & prefetch) that miss the L2 cache. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
         "EventCode": "0xB7",
-        "MSRValue": "0x3600000022 ",
+        "MSRValue": "0x3600000022",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.ANY_RFO.L2_MISS.ANY",
@@ -343,7 +318,7 @@
         "CollectPEBSRecord": "1",
         "PublicDescription": "Counts reads for ownership (RFO) requests (demand & prefetch) that miss the L2 cache with a snoop hit in the other processor module, data forwarding is required. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
         "EventCode": "0xB7",
-        "MSRValue": "0x1000000022 ",
+        "MSRValue": "0x1000000022",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.ANY_RFO.L2_MISS.HITM_OTHER_CORE",
@@ -356,7 +331,7 @@
         "CollectPEBSRecord": "1",
         "PublicDescription": "Counts reads for ownership (RFO) requests (demand & prefetch) that miss the L2 cache with a snoop hit in the other processor module, no data forwarding is required. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
         "EventCode": "0xB7",
-        "MSRValue": "0x0400000022 ",
+        "MSRValue": "0x0400000022",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.ANY_RFO.L2_MISS.HIT_OTHER_CORE_NO_FWD",
@@ -369,20 +344,20 @@
         "CollectPEBSRecord": "1",
         "PublicDescription": "Counts reads for ownership (RFO) requests (demand & prefetch) that true miss for the L2 cache with a snoop miss in the other processor module.  Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
         "EventCode": "0xB7",
-        "MSRValue": "0x0200000022 ",
+        "MSRValue": "0x0200000022",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.ANY_RFO.L2_MISS.SNOOP_MISS_OR_NO_SNOOP_NEEDED",
         "MSRIndex": "0x1a6,0x1a7",
         "SampleAfterValue": "100007",
-        "BriefDescription": "Counts reads for ownership (RFO) requests (demand & prefetch) that true miss for the L2 cache with a snoop miss in the other processor module. ",
+        "BriefDescription": "Counts reads for ownership (RFO) requests (demand & prefetch) that true miss for the L2 cache with a snoop miss in the other processor module.",
         "Offcore": "1"
     },
     {
         "CollectPEBSRecord": "1",
         "PublicDescription": "Counts reads for ownership (RFO) requests (demand & prefetch) that hit the L2 cache. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
         "EventCode": "0xB7",
-        "MSRValue": "0x0000040022 ",
+        "MSRValue": "0x0000040022",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.ANY_RFO.L2_HIT",
@@ -393,32 +368,6 @@
     },
     {
         "CollectPEBSRecord": "1",
-        "PublicDescription": "Counts reads for ownership (RFO) requests (demand & prefetch) that have any transaction responses from the uncore subsystem. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
-        "EventCode": "0xB7",
-        "MSRValue": "0x0000010022 ",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.ANY_RFO.ANY_RESPONSE",
-        "MSRIndex": "0x1a6,0x1a7",
-        "SampleAfterValue": "100007",
-        "BriefDescription": "Counts reads for ownership (RFO) requests (demand & prefetch) that have any transaction responses from the uncore subsystem.",
-        "Offcore": "1"
-    },
-    {
-        "CollectPEBSRecord": "1",
-        "PublicDescription": "Counts data reads (demand & prefetch) that are outstanding, per cycle, from the time of the L2 miss to when any response is received. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
-        "EventCode": "0xB7",
-        "MSRValue": "0x4000003091",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.ANY_DATA_RD.OUTSTANDING",
-        "MSRIndex": "0x1a6",
-        "SampleAfterValue": "100007",
-        "BriefDescription": "Counts data reads (demand & prefetch) that are outstanding, per cycle, from the time of the L2 miss to when any response is received.",
-        "Offcore": "1"
-    },
-    {
-        "CollectPEBSRecord": "1",
         "PublicDescription": "Counts data reads (demand & prefetch) that miss the L2 cache. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
         "EventCode": "0xB7",
         "MSRValue": "0x3600003091",
@@ -466,7 +415,7 @@
         "EventName": "OFFCORE_RESPONSE.ANY_DATA_RD.L2_MISS.SNOOP_MISS_OR_NO_SNOOP_NEEDED",
         "MSRIndex": "0x1a6,0x1a7",
         "SampleAfterValue": "100007",
-        "BriefDescription": "Counts data reads (demand & prefetch) that true miss for the L2 cache with a snoop miss in the other processor module. ",
+        "BriefDescription": "Counts data reads (demand & prefetch) that true miss for the L2 cache with a snoop miss in the other processor module.",
         "Offcore": "1"
     },
     {
@@ -484,35 +433,9 @@
     },
     {
         "CollectPEBSRecord": "1",
-        "PublicDescription": "Counts data reads (demand & prefetch) that have any transaction responses from the uncore subsystem. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
-        "EventCode": "0xB7",
-        "MSRValue": "0x0000013091",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.ANY_DATA_RD.ANY_RESPONSE",
-        "MSRIndex": "0x1a6,0x1a7",
-        "SampleAfterValue": "100007",
-        "BriefDescription": "Counts data reads (demand & prefetch) that have any transaction responses from the uncore subsystem.",
-        "Offcore": "1"
-    },
-    {
-        "CollectPEBSRecord": "1",
-        "PublicDescription": "Counts data reads generated by L1 or L2 prefetchers that are outstanding, per cycle, from the time of the L2 miss to when any response is received. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
-        "EventCode": "0xB7",
-        "MSRValue": "0x4000003010 ",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.ANY_PF_DATA_RD.OUTSTANDING",
-        "MSRIndex": "0x1a6",
-        "SampleAfterValue": "100007",
-        "BriefDescription": "Counts data reads generated by L1 or L2 prefetchers that are outstanding, per cycle, from the time of the L2 miss to when any response is received.",
-        "Offcore": "1"
-    },
-    {
-        "CollectPEBSRecord": "1",
         "PublicDescription": "Counts data reads generated by L1 or L2 prefetchers that miss the L2 cache. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
         "EventCode": "0xB7",
-        "MSRValue": "0x3600003010 ",
+        "MSRValue": "0x3600003010",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.ANY_PF_DATA_RD.L2_MISS.ANY",
@@ -525,7 +448,7 @@
         "CollectPEBSRecord": "1",
         "PublicDescription": "Counts data reads generated by L1 or L2 prefetchers that miss the L2 cache with a snoop hit in the other processor module, data forwarding is required. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
         "EventCode": "0xB7",
-        "MSRValue": "0x1000003010 ",
+        "MSRValue": "0x1000003010",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.ANY_PF_DATA_RD.L2_MISS.HITM_OTHER_CORE",
@@ -538,7 +461,7 @@
         "CollectPEBSRecord": "1",
         "PublicDescription": "Counts data reads generated by L1 or L2 prefetchers that miss the L2 cache with a snoop hit in the other processor module, no data forwarding is required. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
         "EventCode": "0xB7",
-        "MSRValue": "0x0400003010 ",
+        "MSRValue": "0x0400003010",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.ANY_PF_DATA_RD.L2_MISS.HIT_OTHER_CORE_NO_FWD",
@@ -551,20 +474,20 @@
         "CollectPEBSRecord": "1",
         "PublicDescription": "Counts data reads generated by L1 or L2 prefetchers that true miss for the L2 cache with a snoop miss in the other processor module.  Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
         "EventCode": "0xB7",
-        "MSRValue": "0x0200003010 ",
+        "MSRValue": "0x0200003010",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.ANY_PF_DATA_RD.L2_MISS.SNOOP_MISS_OR_NO_SNOOP_NEEDED",
         "MSRIndex": "0x1a6,0x1a7",
         "SampleAfterValue": "100007",
-        "BriefDescription": "Counts data reads generated by L1 or L2 prefetchers that true miss for the L2 cache with a snoop miss in the other processor module. ",
+        "BriefDescription": "Counts data reads generated by L1 or L2 prefetchers that true miss for the L2 cache with a snoop miss in the other processor module.",
         "Offcore": "1"
     },
     {
         "CollectPEBSRecord": "1",
         "PublicDescription": "Counts data reads generated by L1 or L2 prefetchers that hit the L2 cache. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
         "EventCode": "0xB7",
-        "MSRValue": "0x0000043010 ",
+        "MSRValue": "0x0000043010",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.ANY_PF_DATA_RD.L2_HIT",
@@ -575,48 +498,9 @@
     },
     {
         "CollectPEBSRecord": "1",
-        "PublicDescription": "Counts data reads generated by L1 or L2 prefetchers that have any transaction responses from the uncore subsystem. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
-        "EventCode": "0xB7",
-        "MSRValue": "0x0000013010 ",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.ANY_PF_DATA_RD.ANY_RESPONSE",
-        "MSRIndex": "0x1a6,0x1a7",
-        "SampleAfterValue": "100007",
-        "BriefDescription": "Counts data reads generated by L1 or L2 prefetchers that have any transaction responses from the uncore subsystem.",
-        "Offcore": "1"
-    },
-    {
-        "CollectPEBSRecord": "1",
-        "PublicDescription": "Counts requests to the uncore subsystem that are outstanding, per cycle, from the time of the L2 miss to when any response is received. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
-        "EventCode": "0xB7",
-        "MSRValue": "0x4000008000 ",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.ANY_REQUEST.OUTSTANDING",
-        "MSRIndex": "0x1a6",
-        "SampleAfterValue": "100007",
-        "BriefDescription": "Counts requests to the uncore subsystem that are outstanding, per cycle, from the time of the L2 miss to when any response is received.",
-        "Offcore": "1"
-    },
-    {
-        "CollectPEBSRecord": "1",
-        "PublicDescription": "Counts requests to the uncore subsystem that miss the L2 cache. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
-        "EventCode": "0xB7",
-        "MSRValue": "0x3600008000 ",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.ANY_REQUEST.L2_MISS.ANY",
-        "MSRIndex": "0x1a6,0x1a7",
-        "SampleAfterValue": "100007",
-        "BriefDescription": "Counts requests to the uncore subsystem that miss the L2 cache.",
-        "Offcore": "1"
-    },
-    {
-        "CollectPEBSRecord": "1",
         "PublicDescription": "Counts requests to the uncore subsystem that miss the L2 cache with a snoop hit in the other processor module, data forwarding is required. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
         "EventCode": "0xB7",
-        "MSRValue": "0x1000008000 ",
+        "MSRValue": "0x1000008000",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.ANY_REQUEST.L2_MISS.HITM_OTHER_CORE",
@@ -629,7 +513,7 @@
         "CollectPEBSRecord": "1",
         "PublicDescription": "Counts requests to the uncore subsystem that miss the L2 cache with a snoop hit in the other processor module, no data forwarding is required. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
         "EventCode": "0xB7",
-        "MSRValue": "0x0400008000 ",
+        "MSRValue": "0x0400008000",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.ANY_REQUEST.L2_MISS.HIT_OTHER_CORE_NO_FWD",
@@ -642,20 +526,20 @@
         "CollectPEBSRecord": "1",
         "PublicDescription": "Counts requests to the uncore subsystem that true miss for the L2 cache with a snoop miss in the other processor module.  Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
         "EventCode": "0xB7",
-        "MSRValue": "0x0200008000 ",
+        "MSRValue": "0x0200008000",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.ANY_REQUEST.L2_MISS.SNOOP_MISS_OR_NO_SNOOP_NEEDED",
         "MSRIndex": "0x1a6,0x1a7",
         "SampleAfterValue": "100007",
-        "BriefDescription": "Counts requests to the uncore subsystem that true miss for the L2 cache with a snoop miss in the other processor module. ",
+        "BriefDescription": "Counts requests to the uncore subsystem that true miss for the L2 cache with a snoop miss in the other processor module.",
         "Offcore": "1"
     },
     {
         "CollectPEBSRecord": "1",
         "PublicDescription": "Counts requests to the uncore subsystem that hit the L2 cache. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
         "EventCode": "0xB7",
-        "MSRValue": "0x0000048000 ",
+        "MSRValue": "0x0000048000",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.ANY_REQUEST.L2_HIT",
@@ -668,7 +552,7 @@
         "CollectPEBSRecord": "1",
         "PublicDescription": "Counts requests to the uncore subsystem that have any transaction responses from the uncore subsystem. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
         "EventCode": "0xB7",
-        "MSRValue": "0x0000018000 ",
+        "MSRValue": "0x0000018000",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.ANY_REQUEST.ANY_RESPONSE",
@@ -679,22 +563,9 @@
     },
     {
         "CollectPEBSRecord": "1",
-        "PublicDescription": "Counts any data writes to uncacheable write combining (USWC) memory region  that are outstanding, per cycle, from the time of the L2 miss to when any response is received. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
-        "EventCode": "0xB7",
-        "MSRValue": "0x4000004800 ",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.STREAMING_STORES.OUTSTANDING",
-        "MSRIndex": "0x1a6",
-        "SampleAfterValue": "100007",
-        "BriefDescription": "Counts any data writes to uncacheable write combining (USWC) memory region  that are outstanding, per cycle, from the time of the L2 miss to when any response is received.",
-        "Offcore": "1"
-    },
-    {
-        "CollectPEBSRecord": "1",
         "PublicDescription": "Counts any data writes to uncacheable write combining (USWC) memory region  that miss the L2 cache. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
         "EventCode": "0xB7",
-        "MSRValue": "0x3600004800 ",
+        "MSRValue": "0x3600004800",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.STREAMING_STORES.L2_MISS.ANY",
@@ -705,48 +576,9 @@
     },
     {
         "CollectPEBSRecord": "1",
-        "PublicDescription": "Counts any data writes to uncacheable write combining (USWC) memory region  that miss the L2 cache with a snoop hit in the other processor module, data forwarding is required. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
-        "EventCode": "0xB7",
-        "MSRValue": "0x1000004800 ",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.STREAMING_STORES.L2_MISS.HITM_OTHER_CORE",
-        "MSRIndex": "0x1a6,0x1a7",
-        "SampleAfterValue": "100007",
-        "BriefDescription": "Counts any data writes to uncacheable write combining (USWC) memory region  that miss the L2 cache with a snoop hit in the other processor module, data forwarding is required.",
-        "Offcore": "1"
-    },
-    {
-        "CollectPEBSRecord": "1",
-        "PublicDescription": "Counts any data writes to uncacheable write combining (USWC) memory region  that miss the L2 cache with a snoop hit in the other processor module, no data forwarding is required. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
-        "EventCode": "0xB7",
-        "MSRValue": "0x0400004800 ",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.STREAMING_STORES.L2_MISS.HIT_OTHER_CORE_NO_FWD",
-        "MSRIndex": "0x1a6,0x1a7",
-        "SampleAfterValue": "100007",
-        "BriefDescription": "Counts any data writes to uncacheable write combining (USWC) memory region  that miss the L2 cache with a snoop hit in the other processor module, no data forwarding is required.",
-        "Offcore": "1"
-    },
-    {
-        "CollectPEBSRecord": "1",
-        "PublicDescription": "Counts any data writes to uncacheable write combining (USWC) memory region  that true miss for the L2 cache with a snoop miss in the other processor module.  Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
-        "EventCode": "0xB7",
-        "MSRValue": "0x0200004800 ",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.STREAMING_STORES.L2_MISS.SNOOP_MISS_OR_NO_SNOOP_NEEDED",
-        "MSRIndex": "0x1a6,0x1a7",
-        "SampleAfterValue": "100007",
-        "BriefDescription": "Counts any data writes to uncacheable write combining (USWC) memory region  that true miss for the L2 cache with a snoop miss in the other processor module. ",
-        "Offcore": "1"
-    },
-    {
-        "CollectPEBSRecord": "1",
         "PublicDescription": "Counts any data writes to uncacheable write combining (USWC) memory region  that hit the L2 cache. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
         "EventCode": "0xB7",
-        "MSRValue": "0x0000044800 ",
+        "MSRValue": "0x0000044800",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.STREAMING_STORES.L2_HIT",
@@ -757,35 +589,9 @@
     },
     {
         "CollectPEBSRecord": "1",
-        "PublicDescription": "Counts any data writes to uncacheable write combining (USWC) memory region  that have any transaction responses from the uncore subsystem. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
-        "EventCode": "0xB7",
-        "MSRValue": "0x0000014800 ",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.STREAMING_STORES.ANY_RESPONSE",
-        "MSRIndex": "0x1a6,0x1a7",
-        "SampleAfterValue": "100007",
-        "BriefDescription": "Counts any data writes to uncacheable write combining (USWC) memory region  that have any transaction responses from the uncore subsystem.",
-        "Offcore": "1"
-    },
-    {
-        "CollectPEBSRecord": "1",
-        "PublicDescription": "Counts partial cache line data writes to uncacheable write combining (USWC) memory region  that are outstanding, per cycle, from the time of the L2 miss to when any response is received. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
-        "EventCode": "0xB7",
-        "MSRValue": "0x4000004000 ",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.PARTIAL_STREAMING_STORES.OUTSTANDING",
-        "MSRIndex": "0x1a6",
-        "SampleAfterValue": "100007",
-        "BriefDescription": "Counts partial cache line data writes to uncacheable write combining (USWC) memory region  that are outstanding, per cycle, from the time of the L2 miss to when any response is received.",
-        "Offcore": "1"
-    },
-    {
-        "CollectPEBSRecord": "1",
         "PublicDescription": "Counts partial cache line data writes to uncacheable write combining (USWC) memory region  that miss the L2 cache. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
         "EventCode": "0xB7",
-        "MSRValue": "0x3600004000 ",
+        "MSRValue": "0x3600004000",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.PARTIAL_STREAMING_STORES.L2_MISS.ANY",
@@ -798,7 +604,7 @@
         "CollectPEBSRecord": "1",
         "PublicDescription": "Counts partial cache line data writes to uncacheable write combining (USWC) memory region  that miss the L2 cache with a snoop hit in the other processor module, data forwarding is required. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
         "EventCode": "0xB7",
-        "MSRValue": "0x1000004000 ",
+        "MSRValue": "0x1000004000",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.PARTIAL_STREAMING_STORES.L2_MISS.HITM_OTHER_CORE",
@@ -811,7 +617,7 @@
         "CollectPEBSRecord": "1",
         "PublicDescription": "Counts partial cache line data writes to uncacheable write combining (USWC) memory region  that miss the L2 cache with a snoop hit in the other processor module, no data forwarding is required. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
         "EventCode": "0xB7",
-        "MSRValue": "0x0400004000 ",
+        "MSRValue": "0x0400004000",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.PARTIAL_STREAMING_STORES.L2_MISS.HIT_OTHER_CORE_NO_FWD",
@@ -824,20 +630,20 @@
         "CollectPEBSRecord": "1",
         "PublicDescription": "Counts partial cache line data writes to uncacheable write combining (USWC) memory region  that true miss for the L2 cache with a snoop miss in the other processor module.  Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
         "EventCode": "0xB7",
-        "MSRValue": "0x0200004000 ",
+        "MSRValue": "0x0200004000",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.PARTIAL_STREAMING_STORES.L2_MISS.SNOOP_MISS_OR_NO_SNOOP_NEEDED",
         "MSRIndex": "0x1a6,0x1a7",
         "SampleAfterValue": "100007",
-        "BriefDescription": "Counts partial cache line data writes to uncacheable write combining (USWC) memory region  that true miss for the L2 cache with a snoop miss in the other processor module. ",
+        "BriefDescription": "Counts partial cache line data writes to uncacheable write combining (USWC) memory region  that true miss for the L2 cache with a snoop miss in the other processor module.",
         "Offcore": "1"
     },
     {
         "CollectPEBSRecord": "1",
         "PublicDescription": "Counts partial cache line data writes to uncacheable write combining (USWC) memory region  that hit the L2 cache. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
         "EventCode": "0xB7",
-        "MSRValue": "0x0000044000 ",
+        "MSRValue": "0x0000044000",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.PARTIAL_STREAMING_STORES.L2_HIT",
@@ -848,35 +654,9 @@
     },
     {
         "CollectPEBSRecord": "1",
-        "PublicDescription": "Counts partial cache line data writes to uncacheable write combining (USWC) memory region  that have any transaction responses from the uncore subsystem. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
-        "EventCode": "0xB7",
-        "MSRValue": "0x0000014000 ",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.PARTIAL_STREAMING_STORES.ANY_RESPONSE",
-        "MSRIndex": "0x1a6,0x1a7",
-        "SampleAfterValue": "100007",
-        "BriefDescription": "Counts partial cache line data writes to uncacheable write combining (USWC) memory region  that have any transaction responses from the uncore subsystem.",
-        "Offcore": "1"
-    },
-    {
-        "CollectPEBSRecord": "1",
-        "PublicDescription": "Counts data cache line reads generated by hardware L1 data cache prefetcher that are outstanding, per cycle, from the time of the L2 miss to when any response is received. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
-        "EventCode": "0xB7",
-        "MSRValue": "0x4000002000 ",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.PF_L1_DATA_RD.OUTSTANDING",
-        "MSRIndex": "0x1a6",
-        "SampleAfterValue": "100007",
-        "BriefDescription": "Counts data cache line reads generated by hardware L1 data cache prefetcher that are outstanding, per cycle, from the time of the L2 miss to when any response is received.",
-        "Offcore": "1"
-    },
-    {
-        "CollectPEBSRecord": "1",
         "PublicDescription": "Counts data cache line reads generated by hardware L1 data cache prefetcher that miss the L2 cache. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
         "EventCode": "0xB7",
-        "MSRValue": "0x3600002000 ",
+        "MSRValue": "0x3600002000",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.PF_L1_DATA_RD.L2_MISS.ANY",
@@ -889,7 +669,7 @@
         "CollectPEBSRecord": "1",
         "PublicDescription": "Counts data cache line reads generated by hardware L1 data cache prefetcher that miss the L2 cache with a snoop hit in the other processor module, data forwarding is required. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
         "EventCode": "0xB7",
-        "MSRValue": "0x1000002000 ",
+        "MSRValue": "0x1000002000",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.PF_L1_DATA_RD.L2_MISS.HITM_OTHER_CORE",
@@ -902,7 +682,7 @@
         "CollectPEBSRecord": "1",
         "PublicDescription": "Counts data cache line reads generated by hardware L1 data cache prefetcher that miss the L2 cache with a snoop hit in the other processor module, no data forwarding is required. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
         "EventCode": "0xB7",
-        "MSRValue": "0x0400002000 ",
+        "MSRValue": "0x0400002000",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.PF_L1_DATA_RD.L2_MISS.HIT_OTHER_CORE_NO_FWD",
@@ -915,20 +695,20 @@
         "CollectPEBSRecord": "1",
         "PublicDescription": "Counts data cache line reads generated by hardware L1 data cache prefetcher that true miss for the L2 cache with a snoop miss in the other processor module.  Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
         "EventCode": "0xB7",
-        "MSRValue": "0x0200002000 ",
+        "MSRValue": "0x0200002000",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.PF_L1_DATA_RD.L2_MISS.SNOOP_MISS_OR_NO_SNOOP_NEEDED",
         "MSRIndex": "0x1a6,0x1a7",
         "SampleAfterValue": "100007",
-        "BriefDescription": "Counts data cache line reads generated by hardware L1 data cache prefetcher that true miss for the L2 cache with a snoop miss in the other processor module. ",
+        "BriefDescription": "Counts data cache line reads generated by hardware L1 data cache prefetcher that true miss for the L2 cache with a snoop miss in the other processor module.",
         "Offcore": "1"
     },
     {
         "CollectPEBSRecord": "1",
         "PublicDescription": "Counts data cache line reads generated by hardware L1 data cache prefetcher that hit the L2 cache. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
         "EventCode": "0xB7",
-        "MSRValue": "0x0000042000 ",
+        "MSRValue": "0x0000042000",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.PF_L1_DATA_RD.L2_HIT",
@@ -939,35 +719,9 @@
     },
     {
         "CollectPEBSRecord": "1",
-        "PublicDescription": "Counts data cache line reads generated by hardware L1 data cache prefetcher that have any transaction responses from the uncore subsystem. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
-        "EventCode": "0xB7",
-        "MSRValue": "0x0000012000 ",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.PF_L1_DATA_RD.ANY_RESPONSE",
-        "MSRIndex": "0x1a6,0x1a7",
-        "SampleAfterValue": "100007",
-        "BriefDescription": "Counts data cache line reads generated by hardware L1 data cache prefetcher that have any transaction responses from the uncore subsystem.",
-        "Offcore": "1"
-    },
-    {
-        "CollectPEBSRecord": "1",
-        "PublicDescription": "Counts data cache lines requests by software prefetch instructions that are outstanding, per cycle, from the time of the L2 miss to when any response is received. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
-        "EventCode": "0xB7",
-        "MSRValue": "0x4000001000 ",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.SW_PREFETCH.OUTSTANDING",
-        "MSRIndex": "0x1a6",
-        "SampleAfterValue": "100007",
-        "BriefDescription": "Counts data cache lines requests by software prefetch instructions that are outstanding, per cycle, from the time of the L2 miss to when any response is received.",
-        "Offcore": "1"
-    },
-    {
-        "CollectPEBSRecord": "1",
         "PublicDescription": "Counts data cache lines requests by software prefetch instructions that miss the L2 cache. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
         "EventCode": "0xB7",
-        "MSRValue": "0x3600001000 ",
+        "MSRValue": "0x3600001000",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.SW_PREFETCH.L2_MISS.ANY",
@@ -980,7 +734,7 @@
         "CollectPEBSRecord": "1",
         "PublicDescription": "Counts data cache lines requests by software prefetch instructions that miss the L2 cache with a snoop hit in the other processor module, data forwarding is required. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
         "EventCode": "0xB7",
-        "MSRValue": "0x1000001000 ",
+        "MSRValue": "0x1000001000",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.SW_PREFETCH.L2_MISS.HITM_OTHER_CORE",
@@ -993,7 +747,7 @@
         "CollectPEBSRecord": "1",
         "PublicDescription": "Counts data cache lines requests by software prefetch instructions that miss the L2 cache with a snoop hit in the other processor module, no data forwarding is required. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
         "EventCode": "0xB7",
-        "MSRValue": "0x0400001000 ",
+        "MSRValue": "0x0400001000",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.SW_PREFETCH.L2_MISS.HIT_OTHER_CORE_NO_FWD",
@@ -1006,20 +760,20 @@
         "CollectPEBSRecord": "1",
         "PublicDescription": "Counts data cache lines requests by software prefetch instructions that true miss for the L2 cache with a snoop miss in the other processor module.  Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
         "EventCode": "0xB7",
-        "MSRValue": "0x0200001000 ",
+        "MSRValue": "0x0200001000",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.SW_PREFETCH.L2_MISS.SNOOP_MISS_OR_NO_SNOOP_NEEDED",
         "MSRIndex": "0x1a6,0x1a7",
         "SampleAfterValue": "100007",
-        "BriefDescription": "Counts data cache lines requests by software prefetch instructions that true miss for the L2 cache with a snoop miss in the other processor module. ",
+        "BriefDescription": "Counts data cache lines requests by software prefetch instructions that true miss for the L2 cache with a snoop miss in the other processor module.",
         "Offcore": "1"
     },
     {
         "CollectPEBSRecord": "1",
         "PublicDescription": "Counts data cache lines requests by software prefetch instructions that hit the L2 cache. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
         "EventCode": "0xB7",
-        "MSRValue": "0x0000041000 ",
+        "MSRValue": "0x0000041000",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.SW_PREFETCH.L2_HIT",
@@ -1030,35 +784,9 @@
     },
     {
         "CollectPEBSRecord": "1",
-        "PublicDescription": "Counts data cache lines requests by software prefetch instructions that have any transaction responses from the uncore subsystem. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
-        "EventCode": "0xB7",
-        "MSRValue": "0x0000011000 ",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.SW_PREFETCH.ANY_RESPONSE",
-        "MSRIndex": "0x1a6,0x1a7",
-        "SampleAfterValue": "100007",
-        "BriefDescription": "Counts data cache lines requests by software prefetch instructions that have any transaction responses from the uncore subsystem.",
-        "Offcore": "1"
-    },
-    {
-        "CollectPEBSRecord": "1",
-        "PublicDescription": "Counts full cache line data writes to uncacheable write combining (USWC) memory region and full cache-line non-temporal writes that are outstanding, per cycle, from the time of the L2 miss to when any response is received. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
-        "EventCode": "0xB7",
-        "MSRValue": "0x4000000800 ",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.FULL_STREAMING_STORES.OUTSTANDING",
-        "MSRIndex": "0x1a6",
-        "SampleAfterValue": "100007",
-        "BriefDescription": "Counts full cache line data writes to uncacheable write combining (USWC) memory region and full cache-line non-temporal writes that are outstanding, per cycle, from the time of the L2 miss to when any response is received.",
-        "Offcore": "1"
-    },
-    {
-        "CollectPEBSRecord": "1",
         "PublicDescription": "Counts full cache line data writes to uncacheable write combining (USWC) memory region and full cache-line non-temporal writes that miss the L2 cache. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
         "EventCode": "0xB7",
-        "MSRValue": "0x3600000800 ",
+        "MSRValue": "0x3600000800",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.FULL_STREAMING_STORES.L2_MISS.ANY",
@@ -1071,7 +799,7 @@
         "CollectPEBSRecord": "1",
         "PublicDescription": "Counts full cache line data writes to uncacheable write combining (USWC) memory region and full cache-line non-temporal writes that miss the L2 cache with a snoop hit in the other processor module, data forwarding is required. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
         "EventCode": "0xB7",
-        "MSRValue": "0x1000000800 ",
+        "MSRValue": "0x1000000800",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.FULL_STREAMING_STORES.L2_MISS.HITM_OTHER_CORE",
@@ -1084,7 +812,7 @@
         "CollectPEBSRecord": "1",
         "PublicDescription": "Counts full cache line data writes to uncacheable write combining (USWC) memory region and full cache-line non-temporal writes that miss the L2 cache with a snoop hit in the other processor module, no data forwarding is required. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
         "EventCode": "0xB7",
-        "MSRValue": "0x0400000800 ",
+        "MSRValue": "0x0400000800",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.FULL_STREAMING_STORES.L2_MISS.HIT_OTHER_CORE_NO_FWD",
@@ -1097,20 +825,20 @@
         "CollectPEBSRecord": "1",
         "PublicDescription": "Counts full cache line data writes to uncacheable write combining (USWC) memory region and full cache-line non-temporal writes that true miss for the L2 cache with a snoop miss in the other processor module.  Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
         "EventCode": "0xB7",
-        "MSRValue": "0x0200000800 ",
+        "MSRValue": "0x0200000800",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.FULL_STREAMING_STORES.L2_MISS.SNOOP_MISS_OR_NO_SNOOP_NEEDED",
         "MSRIndex": "0x1a6,0x1a7",
         "SampleAfterValue": "100007",
-        "BriefDescription": "Counts full cache line data writes to uncacheable write combining (USWC) memory region and full cache-line non-temporal writes that true miss for the L2 cache with a snoop miss in the other processor module. ",
+        "BriefDescription": "Counts full cache line data writes to uncacheable write combining (USWC) memory region and full cache-line non-temporal writes that true miss for the L2 cache with a snoop miss in the other processor module.",
         "Offcore": "1"
     },
     {
         "CollectPEBSRecord": "1",
         "PublicDescription": "Counts full cache line data writes to uncacheable write combining (USWC) memory region and full cache-line non-temporal writes that hit the L2 cache. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
         "EventCode": "0xB7",
-        "MSRValue": "0x0000040800 ",
+        "MSRValue": "0x0000040800",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.FULL_STREAMING_STORES.L2_HIT",
@@ -1121,100 +849,9 @@
     },
     {
         "CollectPEBSRecord": "1",
-        "PublicDescription": "Counts full cache line data writes to uncacheable write combining (USWC) memory region and full cache-line non-temporal writes that have any transaction responses from the uncore subsystem. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
-        "EventCode": "0xB7",
-        "MSRValue": "0x0000010800 ",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.FULL_STREAMING_STORES.ANY_RESPONSE",
-        "MSRIndex": "0x1a6,0x1a7",
-        "SampleAfterValue": "100007",
-        "BriefDescription": "Counts full cache line data writes to uncacheable write combining (USWC) memory region and full cache-line non-temporal writes that have any transaction responses from the uncore subsystem.",
-        "Offcore": "1"
-    },
-    {
-        "CollectPEBSRecord": "1",
-        "PublicDescription": "Counts bus lock and split lock requests that are outstanding, per cycle, from the time of the L2 miss to when any response is received. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
-        "EventCode": "0xB7",
-        "MSRValue": "0x4000000400 ",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.BUS_LOCKS.OUTSTANDING",
-        "MSRIndex": "0x1a6",
-        "SampleAfterValue": "100007",
-        "BriefDescription": "Counts bus lock and split lock requests that are outstanding, per cycle, from the time of the L2 miss to when any response is received.",
-        "Offcore": "1"
-    },
-    {
-        "CollectPEBSRecord": "1",
-        "PublicDescription": "Counts bus lock and split lock requests that miss the L2 cache. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
-        "EventCode": "0xB7",
-        "MSRValue": "0x3600000400 ",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.BUS_LOCKS.L2_MISS.ANY",
-        "MSRIndex": "0x1a6,0x1a7",
-        "SampleAfterValue": "100007",
-        "BriefDescription": "Counts bus lock and split lock requests that miss the L2 cache.",
-        "Offcore": "1"
-    },
-    {
-        "CollectPEBSRecord": "1",
-        "PublicDescription": "Counts bus lock and split lock requests that miss the L2 cache with a snoop hit in the other processor module, data forwarding is required. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
-        "EventCode": "0xB7",
-        "MSRValue": "0x1000000400 ",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.BUS_LOCKS.L2_MISS.HITM_OTHER_CORE",
-        "MSRIndex": "0x1a6,0x1a7",
-        "SampleAfterValue": "100007",
-        "BriefDescription": "Counts bus lock and split lock requests that miss the L2 cache with a snoop hit in the other processor module, data forwarding is required.",
-        "Offcore": "1"
-    },
-    {
-        "CollectPEBSRecord": "1",
-        "PublicDescription": "Counts bus lock and split lock requests that miss the L2 cache with a snoop hit in the other processor module, no data forwarding is required. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
-        "EventCode": "0xB7",
-        "MSRValue": "0x0400000400 ",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.BUS_LOCKS.L2_MISS.HIT_OTHER_CORE_NO_FWD",
-        "MSRIndex": "0x1a6,0x1a7",
-        "SampleAfterValue": "100007",
-        "BriefDescription": "Counts bus lock and split lock requests that miss the L2 cache with a snoop hit in the other processor module, no data forwarding is required.",
-        "Offcore": "1"
-    },
-    {
-        "CollectPEBSRecord": "1",
-        "PublicDescription": "Counts bus lock and split lock requests that true miss for the L2 cache with a snoop miss in the other processor module.  Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
-        "EventCode": "0xB7",
-        "MSRValue": "0x0200000400 ",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.BUS_LOCKS.L2_MISS.SNOOP_MISS_OR_NO_SNOOP_NEEDED",
-        "MSRIndex": "0x1a6,0x1a7",
-        "SampleAfterValue": "100007",
-        "BriefDescription": "Counts bus lock and split lock requests that true miss for the L2 cache with a snoop miss in the other processor module. ",
-        "Offcore": "1"
-    },
-    {
-        "CollectPEBSRecord": "1",
-        "PublicDescription": "Counts bus lock and split lock requests that hit the L2 cache. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
-        "EventCode": "0xB7",
-        "MSRValue": "0x0000040400 ",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.BUS_LOCKS.L2_HIT",
-        "MSRIndex": "0x1a6,0x1a7",
-        "SampleAfterValue": "100007",
-        "BriefDescription": "Counts bus lock and split lock requests that hit the L2 cache.",
-        "Offcore": "1"
-    },
-    {
-        "CollectPEBSRecord": "1",
         "PublicDescription": "Counts bus lock and split lock requests that have any transaction responses from the uncore subsystem. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
         "EventCode": "0xB7",
-        "MSRValue": "0x0000010400 ",
+        "MSRValue": "0x0000010400",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.BUS_LOCKS.ANY_RESPONSE",
@@ -1225,113 +862,9 @@
     },
     {
         "CollectPEBSRecord": "1",
-        "PublicDescription": "Counts code reads in uncacheable (UC) memory region that are outstanding, per cycle, from the time of the L2 miss to when any response is received. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
-        "EventCode": "0xB7",
-        "MSRValue": "0x4000000200 ",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.UC_CODE_RD.OUTSTANDING",
-        "MSRIndex": "0x1a6",
-        "SampleAfterValue": "100007",
-        "BriefDescription": "Counts code reads in uncacheable (UC) memory region that are outstanding, per cycle, from the time of the L2 miss to when any response is received.",
-        "Offcore": "1"
-    },
-    {
-        "CollectPEBSRecord": "1",
-        "PublicDescription": "Counts code reads in uncacheable (UC) memory region that miss the L2 cache. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
-        "EventCode": "0xB7",
-        "MSRValue": "0x3600000200 ",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.UC_CODE_RD.L2_MISS.ANY",
-        "MSRIndex": "0x1a6,0x1a7",
-        "SampleAfterValue": "100007",
-        "BriefDescription": "Counts code reads in uncacheable (UC) memory region that miss the L2 cache.",
-        "Offcore": "1"
-    },
-    {
-        "CollectPEBSRecord": "1",
-        "PublicDescription": "Counts code reads in uncacheable (UC) memory region that miss the L2 cache with a snoop hit in the other processor module, data forwarding is required. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
-        "EventCode": "0xB7",
-        "MSRValue": "0x1000000200 ",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.UC_CODE_RD.L2_MISS.HITM_OTHER_CORE",
-        "MSRIndex": "0x1a6,0x1a7",
-        "SampleAfterValue": "100007",
-        "BriefDescription": "Counts code reads in uncacheable (UC) memory region that miss the L2 cache with a snoop hit in the other processor module, data forwarding is required.",
-        "Offcore": "1"
-    },
-    {
-        "CollectPEBSRecord": "1",
-        "PublicDescription": "Counts code reads in uncacheable (UC) memory region that miss the L2 cache with a snoop hit in the other processor module, no data forwarding is required. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
-        "EventCode": "0xB7",
-        "MSRValue": "0x0400000200 ",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.UC_CODE_RD.L2_MISS.HIT_OTHER_CORE_NO_FWD",
-        "MSRIndex": "0x1a6,0x1a7",
-        "SampleAfterValue": "100007",
-        "BriefDescription": "Counts code reads in uncacheable (UC) memory region that miss the L2 cache with a snoop hit in the other processor module, no data forwarding is required.",
-        "Offcore": "1"
-    },
-    {
-        "CollectPEBSRecord": "1",
-        "PublicDescription": "Counts code reads in uncacheable (UC) memory region that true miss for the L2 cache with a snoop miss in the other processor module.  Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
-        "EventCode": "0xB7",
-        "MSRValue": "0x0200000200 ",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.UC_CODE_RD.L2_MISS.SNOOP_MISS_OR_NO_SNOOP_NEEDED",
-        "MSRIndex": "0x1a6,0x1a7",
-        "SampleAfterValue": "100007",
-        "BriefDescription": "Counts code reads in uncacheable (UC) memory region that true miss for the L2 cache with a snoop miss in the other processor module. ",
-        "Offcore": "1"
-    },
-    {
-        "CollectPEBSRecord": "1",
-        "PublicDescription": "Counts code reads in uncacheable (UC) memory region that hit the L2 cache. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
-        "EventCode": "0xB7",
-        "MSRValue": "0x0000040200 ",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.UC_CODE_RD.L2_HIT",
-        "MSRIndex": "0x1a6,0x1a7",
-        "SampleAfterValue": "100007",
-        "BriefDescription": "Counts code reads in uncacheable (UC) memory region that hit the L2 cache.",
-        "Offcore": "1"
-    },
-    {
-        "CollectPEBSRecord": "1",
-        "PublicDescription": "Counts code reads in uncacheable (UC) memory region that have any transaction responses from the uncore subsystem. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
-        "EventCode": "0xB7",
-        "MSRValue": "0x0000010200 ",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.UC_CODE_RD.ANY_RESPONSE",
-        "MSRIndex": "0x1a6,0x1a7",
-        "SampleAfterValue": "100007",
-        "BriefDescription": "Counts code reads in uncacheable (UC) memory region that have any transaction responses from the uncore subsystem.",
-        "Offcore": "1"
-    },
-    {
-        "CollectPEBSRecord": "1",
-        "PublicDescription": "Counts the number of demand write requests (RFO) generated by a write to partial data cache line, including the writes to uncacheable (UC) and write through (WT), and write protected (WP) types of memory that are outstanding, per cycle, from the time of the L2 miss to when any response is received. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
-        "EventCode": "0xB7",
-        "MSRValue": "0x4000000100 ",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.PARTIAL_WRITES.OUTSTANDING",
-        "MSRIndex": "0x1a6",
-        "SampleAfterValue": "100007",
-        "BriefDescription": "Counts the number of demand write requests (RFO) generated by a write to partial data cache line, including the writes to uncacheable (UC) and write through (WT), and write protected (WP) types of memory that are outstanding, per cycle, from the time of the L2 miss to when any response is received.",
-        "Offcore": "1"
-    },
-    {
-        "CollectPEBSRecord": "1",
         "PublicDescription": "Counts the number of demand write requests (RFO) generated by a write to partial data cache line, including the writes to uncacheable (UC) and write through (WT), and write protected (WP) types of memory that miss the L2 cache. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
         "EventCode": "0xB7",
-        "MSRValue": "0x3600000100 ",
+        "MSRValue": "0x3600000100",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.PARTIAL_WRITES.L2_MISS.ANY",
@@ -1342,87 +875,9 @@
     },
     {
         "CollectPEBSRecord": "1",
-        "PublicDescription": "Counts the number of demand write requests (RFO) generated by a write to partial data cache line, including the writes to uncacheable (UC) and write through (WT), and write protected (WP) types of memory that miss the L2 cache with a snoop hit in the other processor module, data forwarding is required. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
-        "EventCode": "0xB7",
-        "MSRValue": "0x1000000100 ",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.PARTIAL_WRITES.L2_MISS.HITM_OTHER_CORE",
-        "MSRIndex": "0x1a6,0x1a7",
-        "SampleAfterValue": "100007",
-        "BriefDescription": "Counts the number of demand write requests (RFO) generated by a write to partial data cache line, including the writes to uncacheable (UC) and write through (WT), and write protected (WP) types of memory that miss the L2 cache with a snoop hit in the other processor module, data forwarding is required.",
-        "Offcore": "1"
-    },
-    {
-        "CollectPEBSRecord": "1",
-        "PublicDescription": "Counts the number of demand write requests (RFO) generated by a write to partial data cache line, including the writes to uncacheable (UC) and write through (WT), and write protected (WP) types of memory that miss the L2 cache with a snoop hit in the other processor module, no data forwarding is required. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
-        "EventCode": "0xB7",
-        "MSRValue": "0x0400000100 ",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.PARTIAL_WRITES.L2_MISS.HIT_OTHER_CORE_NO_FWD",
-        "MSRIndex": "0x1a6,0x1a7",
-        "SampleAfterValue": "100007",
-        "BriefDescription": "Counts the number of demand write requests (RFO) generated by a write to partial data cache line, including the writes to uncacheable (UC) and write through (WT), and write protected (WP) types of memory that miss the L2 cache with a snoop hit in the other processor module, no data forwarding is required.",
-        "Offcore": "1"
-    },
-    {
-        "CollectPEBSRecord": "1",
-        "PublicDescription": "Counts the number of demand write requests (RFO) generated by a write to partial data cache line, including the writes to uncacheable (UC) and write through (WT), and write protected (WP) types of memory that true miss for the L2 cache with a snoop miss in the other processor module.  Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
-        "EventCode": "0xB7",
-        "MSRValue": "0x0200000100 ",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.PARTIAL_WRITES.L2_MISS.SNOOP_MISS_OR_NO_SNOOP_NEEDED",
-        "MSRIndex": "0x1a6,0x1a7",
-        "SampleAfterValue": "100007",
-        "BriefDescription": "Counts the number of demand write requests (RFO) generated by a write to partial data cache line, including the writes to uncacheable (UC) and write through (WT), and write protected (WP) types of memory that true miss for the L2 cache with a snoop miss in the other processor module. ",
-        "Offcore": "1"
-    },
-    {
-        "CollectPEBSRecord": "1",
-        "PublicDescription": "Counts the number of demand write requests (RFO) generated by a write to partial data cache line, including the writes to uncacheable (UC) and write through (WT), and write protected (WP) types of memory that hit the L2 cache. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
-        "EventCode": "0xB7",
-        "MSRValue": "0x0000040100 ",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.PARTIAL_WRITES.L2_HIT",
-        "MSRIndex": "0x1a6,0x1a7",
-        "SampleAfterValue": "100007",
-        "BriefDescription": "Counts the number of demand write requests (RFO) generated by a write to partial data cache line, including the writes to uncacheable (UC) and write through (WT), and write protected (WP) types of memory that hit the L2 cache.",
-        "Offcore": "1"
-    },
-    {
-        "CollectPEBSRecord": "1",
-        "PublicDescription": "Counts the number of demand write requests (RFO) generated by a write to partial data cache line, including the writes to uncacheable (UC) and write through (WT), and write protected (WP) types of memory that have any transaction responses from the uncore subsystem. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
-        "EventCode": "0xB7",
-        "MSRValue": "0x0000010100 ",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.PARTIAL_WRITES.ANY_RESPONSE",
-        "MSRIndex": "0x1a6,0x1a7",
-        "SampleAfterValue": "100007",
-        "BriefDescription": "Counts the number of demand write requests (RFO) generated by a write to partial data cache line, including the writes to uncacheable (UC) and write through (WT), and write protected (WP) types of memory that have any transaction responses from the uncore subsystem.",
-        "Offcore": "1"
-    },
-    {
-        "CollectPEBSRecord": "1",
-        "PublicDescription": "Counts demand data partial reads, including data in uncacheable (UC) or uncacheable write combining (USWC) memory types that are outstanding, per cycle, from the time of the L2 miss to when any response is received. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
-        "EventCode": "0xB7",
-        "MSRValue": "0x4000000080 ",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.PARTIAL_READS.OUTSTANDING",
-        "MSRIndex": "0x1a6",
-        "SampleAfterValue": "100007",
-        "BriefDescription": "Counts demand data partial reads, including data in uncacheable (UC) or uncacheable write combining (USWC) memory types that are outstanding, per cycle, from the time of the L2 miss to when any response is received.",
-        "Offcore": "1"
-    },
-    {
-        "CollectPEBSRecord": "1",
         "PublicDescription": "Counts demand data partial reads, including data in uncacheable (UC) or uncacheable write combining (USWC) memory types that miss the L2 cache. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
         "EventCode": "0xB7",
-        "MSRValue": "0x3600000080 ",
+        "MSRValue": "0x3600000080",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.PARTIAL_READS.L2_MISS.ANY",
@@ -1433,87 +888,9 @@
     },
     {
         "CollectPEBSRecord": "1",
-        "PublicDescription": "Counts demand data partial reads, including data in uncacheable (UC) or uncacheable write combining (USWC) memory types that miss the L2 cache with a snoop hit in the other processor module, data forwarding is required. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
-        "EventCode": "0xB7",
-        "MSRValue": "0x1000000080 ",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.PARTIAL_READS.L2_MISS.HITM_OTHER_CORE",
-        "MSRIndex": "0x1a6,0x1a7",
-        "SampleAfterValue": "100007",
-        "BriefDescription": "Counts demand data partial reads, including data in uncacheable (UC) or uncacheable write combining (USWC) memory types that miss the L2 cache with a snoop hit in the other processor module, data forwarding is required.",
-        "Offcore": "1"
-    },
-    {
-        "CollectPEBSRecord": "1",
-        "PublicDescription": "Counts demand data partial reads, including data in uncacheable (UC) or uncacheable write combining (USWC) memory types that miss the L2 cache with a snoop hit in the other processor module, no data forwarding is required. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
-        "EventCode": "0xB7",
-        "MSRValue": "0x0400000080 ",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.PARTIAL_READS.L2_MISS.HIT_OTHER_CORE_NO_FWD",
-        "MSRIndex": "0x1a6,0x1a7",
-        "SampleAfterValue": "100007",
-        "BriefDescription": "Counts demand data partial reads, including data in uncacheable (UC) or uncacheable write combining (USWC) memory types that miss the L2 cache with a snoop hit in the other processor module, no data forwarding is required.",
-        "Offcore": "1"
-    },
-    {
-        "CollectPEBSRecord": "1",
-        "PublicDescription": "Counts demand data partial reads, including data in uncacheable (UC) or uncacheable write combining (USWC) memory types that true miss for the L2 cache with a snoop miss in the other processor module.  Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
-        "EventCode": "0xB7",
-        "MSRValue": "0x0200000080 ",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.PARTIAL_READS.L2_MISS.SNOOP_MISS_OR_NO_SNOOP_NEEDED",
-        "MSRIndex": "0x1a6,0x1a7",
-        "SampleAfterValue": "100007",
-        "BriefDescription": "Counts demand data partial reads, including data in uncacheable (UC) or uncacheable write combining (USWC) memory types that true miss for the L2 cache with a snoop miss in the other processor module. ",
-        "Offcore": "1"
-    },
-    {
-        "CollectPEBSRecord": "1",
-        "PublicDescription": "Counts demand data partial reads, including data in uncacheable (UC) or uncacheable write combining (USWC) memory types that hit the L2 cache. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
-        "EventCode": "0xB7",
-        "MSRValue": "0x0000040080 ",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.PARTIAL_READS.L2_HIT",
-        "MSRIndex": "0x1a6,0x1a7",
-        "SampleAfterValue": "100007",
-        "BriefDescription": "Counts demand data partial reads, including data in uncacheable (UC) or uncacheable write combining (USWC) memory types that hit the L2 cache.",
-        "Offcore": "1"
-    },
-    {
-        "CollectPEBSRecord": "1",
-        "PublicDescription": "Counts demand data partial reads, including data in uncacheable (UC) or uncacheable write combining (USWC) memory types that have any transaction responses from the uncore subsystem. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
-        "EventCode": "0xB7",
-        "MSRValue": "0x0000010080 ",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.PARTIAL_READS.ANY_RESPONSE",
-        "MSRIndex": "0x1a6,0x1a7",
-        "SampleAfterValue": "100007",
-        "BriefDescription": "Counts demand data partial reads, including data in uncacheable (UC) or uncacheable write combining (USWC) memory types that have any transaction responses from the uncore subsystem.",
-        "Offcore": "1"
-    },
-    {
-        "CollectPEBSRecord": "1",
-        "PublicDescription": "Counts reads for ownership (RFO) requests generated by L2 prefetcher that are outstanding, per cycle, from the time of the L2 miss to when any response is received. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
-        "EventCode": "0xB7",
-        "MSRValue": "0x4000000020 ",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.PF_L2_RFO.OUTSTANDING",
-        "MSRIndex": "0x1a6",
-        "SampleAfterValue": "100007",
-        "BriefDescription": "Counts reads for ownership (RFO) requests generated by L2 prefetcher that are outstanding, per cycle, from the time of the L2 miss to when any response is received.",
-        "Offcore": "1"
-    },
-    {
-        "CollectPEBSRecord": "1",
         "PublicDescription": "Counts reads for ownership (RFO) requests generated by L2 prefetcher that miss the L2 cache. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
         "EventCode": "0xB7",
-        "MSRValue": "0x3600000020 ",
+        "MSRValue": "0x3600000020",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.PF_L2_RFO.L2_MISS.ANY",
@@ -1526,7 +903,7 @@
         "CollectPEBSRecord": "1",
         "PublicDescription": "Counts reads for ownership (RFO) requests generated by L2 prefetcher that miss the L2 cache with a snoop hit in the other processor module, data forwarding is required. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
         "EventCode": "0xB7",
-        "MSRValue": "0x1000000020 ",
+        "MSRValue": "0x1000000020",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.PF_L2_RFO.L2_MISS.HITM_OTHER_CORE",
@@ -1539,7 +916,7 @@
         "CollectPEBSRecord": "1",
         "PublicDescription": "Counts reads for ownership (RFO) requests generated by L2 prefetcher that miss the L2 cache with a snoop hit in the other processor module, no data forwarding is required. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
         "EventCode": "0xB7",
-        "MSRValue": "0x0400000020 ",
+        "MSRValue": "0x0400000020",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.PF_L2_RFO.L2_MISS.HIT_OTHER_CORE_NO_FWD",
@@ -1552,20 +929,20 @@
         "CollectPEBSRecord": "1",
         "PublicDescription": "Counts reads for ownership (RFO) requests generated by L2 prefetcher that true miss for the L2 cache with a snoop miss in the other processor module.  Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
         "EventCode": "0xB7",
-        "MSRValue": "0x0200000020 ",
+        "MSRValue": "0x0200000020",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.PF_L2_RFO.L2_MISS.SNOOP_MISS_OR_NO_SNOOP_NEEDED",
         "MSRIndex": "0x1a6,0x1a7",
         "SampleAfterValue": "100007",
-        "BriefDescription": "Counts reads for ownership (RFO) requests generated by L2 prefetcher that true miss for the L2 cache with a snoop miss in the other processor module. ",
+        "BriefDescription": "Counts reads for ownership (RFO) requests generated by L2 prefetcher that true miss for the L2 cache with a snoop miss in the other processor module.",
         "Offcore": "1"
     },
     {
         "CollectPEBSRecord": "1",
         "PublicDescription": "Counts reads for ownership (RFO) requests generated by L2 prefetcher that hit the L2 cache. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
         "EventCode": "0xB7",
-        "MSRValue": "0x0000040020 ",
+        "MSRValue": "0x0000040020",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.PF_L2_RFO.L2_HIT",
@@ -1576,35 +953,9 @@
     },
     {
         "CollectPEBSRecord": "1",
-        "PublicDescription": "Counts reads for ownership (RFO) requests generated by L2 prefetcher that have any transaction responses from the uncore subsystem. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
-        "EventCode": "0xB7",
-        "MSRValue": "0x0000010020 ",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.PF_L2_RFO.ANY_RESPONSE",
-        "MSRIndex": "0x1a6,0x1a7",
-        "SampleAfterValue": "100007",
-        "BriefDescription": "Counts reads for ownership (RFO) requests generated by L2 prefetcher that have any transaction responses from the uncore subsystem.",
-        "Offcore": "1"
-    },
-    {
-        "CollectPEBSRecord": "1",
-        "PublicDescription": "Counts data cacheline reads generated by hardware L2 cache prefetcher that are outstanding, per cycle, from the time of the L2 miss to when any response is received. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
-        "EventCode": "0xB7",
-        "MSRValue": "0x4000000010 ",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.PF_L2_DATA_RD.OUTSTANDING",
-        "MSRIndex": "0x1a6",
-        "SampleAfterValue": "100007",
-        "BriefDescription": "Counts data cacheline reads generated by hardware L2 cache prefetcher that are outstanding, per cycle, from the time of the L2 miss to when any response is received.",
-        "Offcore": "1"
-    },
-    {
-        "CollectPEBSRecord": "1",
         "PublicDescription": "Counts data cacheline reads generated by hardware L2 cache prefetcher that miss the L2 cache. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
         "EventCode": "0xB7",
-        "MSRValue": "0x3600000010 ",
+        "MSRValue": "0x3600000010",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.PF_L2_DATA_RD.L2_MISS.ANY",
@@ -1617,7 +968,7 @@
         "CollectPEBSRecord": "1",
         "PublicDescription": "Counts data cacheline reads generated by hardware L2 cache prefetcher that miss the L2 cache with a snoop hit in the other processor module, data forwarding is required. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
         "EventCode": "0xB7",
-        "MSRValue": "0x1000000010 ",
+        "MSRValue": "0x1000000010",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.PF_L2_DATA_RD.L2_MISS.HITM_OTHER_CORE",
@@ -1630,7 +981,7 @@
         "CollectPEBSRecord": "1",
         "PublicDescription": "Counts data cacheline reads generated by hardware L2 cache prefetcher that miss the L2 cache with a snoop hit in the other processor module, no data forwarding is required. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
         "EventCode": "0xB7",
-        "MSRValue": "0x0400000010 ",
+        "MSRValue": "0x0400000010",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.PF_L2_DATA_RD.L2_MISS.HIT_OTHER_CORE_NO_FWD",
@@ -1643,20 +994,20 @@
         "CollectPEBSRecord": "1",
         "PublicDescription": "Counts data cacheline reads generated by hardware L2 cache prefetcher that true miss for the L2 cache with a snoop miss in the other processor module.  Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
         "EventCode": "0xB7",
-        "MSRValue": "0x0200000010 ",
+        "MSRValue": "0x0200000010",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.PF_L2_DATA_RD.L2_MISS.SNOOP_MISS_OR_NO_SNOOP_NEEDED",
         "MSRIndex": "0x1a6,0x1a7",
         "SampleAfterValue": "100007",
-        "BriefDescription": "Counts data cacheline reads generated by hardware L2 cache prefetcher that true miss for the L2 cache with a snoop miss in the other processor module. ",
+        "BriefDescription": "Counts data cacheline reads generated by hardware L2 cache prefetcher that true miss for the L2 cache with a snoop miss in the other processor module.",
         "Offcore": "1"
     },
     {
         "CollectPEBSRecord": "1",
         "PublicDescription": "Counts data cacheline reads generated by hardware L2 cache prefetcher that hit the L2 cache. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
         "EventCode": "0xB7",
-        "MSRValue": "0x0000040010 ",
+        "MSRValue": "0x0000040010",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.PF_L2_DATA_RD.L2_HIT",
@@ -1667,35 +1018,9 @@
     },
     {
         "CollectPEBSRecord": "1",
-        "PublicDescription": "Counts data cacheline reads generated by hardware L2 cache prefetcher that have any transaction responses from the uncore subsystem. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
-        "EventCode": "0xB7",
-        "MSRValue": "0x0000010010 ",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.PF_L2_DATA_RD.ANY_RESPONSE",
-        "MSRIndex": "0x1a6,0x1a7",
-        "SampleAfterValue": "100007",
-        "BriefDescription": "Counts data cacheline reads generated by hardware L2 cache prefetcher that have any transaction responses from the uncore subsystem.",
-        "Offcore": "1"
-    },
-    {
-        "CollectPEBSRecord": "1",
-        "PublicDescription": "Counts the number of writeback transactions caused by L1 or L2 cache evictions that are outstanding, per cycle, from the time of the L2 miss to when any response is received. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
-        "EventCode": "0xB7",
-        "MSRValue": "0x4000000008 ",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.COREWB.OUTSTANDING",
-        "MSRIndex": "0x1a6",
-        "SampleAfterValue": "100007",
-        "BriefDescription": "Counts the number of writeback transactions caused by L1 or L2 cache evictions that are outstanding, per cycle, from the time of the L2 miss to when any response is received.",
-        "Offcore": "1"
-    },
-    {
-        "CollectPEBSRecord": "1",
         "PublicDescription": "Counts the number of writeback transactions caused by L1 or L2 cache evictions that miss the L2 cache. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
         "EventCode": "0xB7",
-        "MSRValue": "0x3600000008 ",
+        "MSRValue": "0x3600000008",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.COREWB.L2_MISS.ANY",
@@ -1708,7 +1033,7 @@
         "CollectPEBSRecord": "1",
         "PublicDescription": "Counts the number of writeback transactions caused by L1 or L2 cache evictions that miss the L2 cache with a snoop hit in the other processor module, data forwarding is required. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
         "EventCode": "0xB7",
-        "MSRValue": "0x1000000008 ",
+        "MSRValue": "0x1000000008",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.COREWB.L2_MISS.HITM_OTHER_CORE",
@@ -1721,7 +1046,7 @@
         "CollectPEBSRecord": "1",
         "PublicDescription": "Counts the number of writeback transactions caused by L1 or L2 cache evictions that miss the L2 cache with a snoop hit in the other processor module, no data forwarding is required. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
         "EventCode": "0xB7",
-        "MSRValue": "0x0400000008 ",
+        "MSRValue": "0x0400000008",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.COREWB.L2_MISS.HIT_OTHER_CORE_NO_FWD",
@@ -1734,20 +1059,20 @@
         "CollectPEBSRecord": "1",
         "PublicDescription": "Counts the number of writeback transactions caused by L1 or L2 cache evictions that true miss for the L2 cache with a snoop miss in the other processor module.  Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
         "EventCode": "0xB7",
-        "MSRValue": "0x0200000008 ",
+        "MSRValue": "0x0200000008",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.COREWB.L2_MISS.SNOOP_MISS_OR_NO_SNOOP_NEEDED",
         "MSRIndex": "0x1a6",
         "SampleAfterValue": "100007",
-        "BriefDescription": "Counts the number of writeback transactions caused by L1 or L2 cache evictions that true miss for the L2 cache with a snoop miss in the other processor module. ",
+        "BriefDescription": "Counts the number of writeback transactions caused by L1 or L2 cache evictions that true miss for the L2 cache with a snoop miss in the other processor module.",
         "Offcore": "1"
     },
     {
         "CollectPEBSRecord": "1",
         "PublicDescription": "Counts the number of writeback transactions caused by L1 or L2 cache evictions that hit the L2 cache. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
         "EventCode": "0xB7",
-        "MSRValue": "0x0000040008 ",
+        "MSRValue": "0x0000040008",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.COREWB.L2_HIT",
@@ -1758,22 +1083,9 @@
     },
     {
         "CollectPEBSRecord": "1",
-        "PublicDescription": "Counts the number of writeback transactions caused by L1 or L2 cache evictions that have any transaction responses from the uncore subsystem. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
-        "EventCode": "0xB7",
-        "MSRValue": "0x0000010008 ",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.COREWB.ANY_RESPONSE",
-        "MSRIndex": "0x1a6",
-        "SampleAfterValue": "100007",
-        "BriefDescription": "Counts the number of writeback transactions caused by L1 or L2 cache evictions that have any transaction responses from the uncore subsystem.",
-        "Offcore": "1"
-    },
-    {
-        "CollectPEBSRecord": "1",
         "PublicDescription": "Counts demand instruction cacheline and I-side prefetch requests that miss the instruction cache that are outstanding, per cycle, from the time of the L2 miss to when any response is received. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
         "EventCode": "0xB7",
-        "MSRValue": "0x4000000004 ",
+        "MSRValue": "0x4000000004",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.OUTSTANDING",
@@ -1786,7 +1098,7 @@
         "CollectPEBSRecord": "1",
         "PublicDescription": "Counts demand instruction cacheline and I-side prefetch requests that miss the instruction cache that miss the L2 cache. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
         "EventCode": "0xB7",
-        "MSRValue": "0x3600000004 ",
+        "MSRValue": "0x3600000004",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L2_MISS.ANY",
@@ -1797,22 +1109,9 @@
     },
     {
         "CollectPEBSRecord": "1",
-        "PublicDescription": "Counts demand instruction cacheline and I-side prefetch requests that miss the instruction cache that miss the L2 cache with a snoop hit in the other processor module, data forwarding is required. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
-        "EventCode": "0xB7",
-        "MSRValue": "0x1000000004 ",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L2_MISS.HITM_OTHER_CORE",
-        "MSRIndex": "0x1a6,0x1a7",
-        "SampleAfterValue": "100007",
-        "BriefDescription": "Counts demand instruction cacheline and I-side prefetch requests that miss the instruction cache that miss the L2 cache with a snoop hit in the other processor module, data forwarding is required.",
-        "Offcore": "1"
-    },
-    {
-        "CollectPEBSRecord": "1",
         "PublicDescription": "Counts demand instruction cacheline and I-side prefetch requests that miss the instruction cache that miss the L2 cache with a snoop hit in the other processor module, no data forwarding is required. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
         "EventCode": "0xB7",
-        "MSRValue": "0x0400000004 ",
+        "MSRValue": "0x0400000004",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L2_MISS.HIT_OTHER_CORE_NO_FWD",
@@ -1825,20 +1124,20 @@
         "CollectPEBSRecord": "1",
         "PublicDescription": "Counts demand instruction cacheline and I-side prefetch requests that miss the instruction cache that true miss for the L2 cache with a snoop miss in the other processor module.  Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
         "EventCode": "0xB7",
-        "MSRValue": "0x0200000004 ",
+        "MSRValue": "0x0200000004",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L2_MISS.SNOOP_MISS_OR_NO_SNOOP_NEEDED",
         "MSRIndex": "0x1a6,0x1a7",
         "SampleAfterValue": "100007",
-        "BriefDescription": "Counts demand instruction cacheline and I-side prefetch requests that miss the instruction cache that true miss for the L2 cache with a snoop miss in the other processor module. ",
+        "BriefDescription": "Counts demand instruction cacheline and I-side prefetch requests that miss the instruction cache that true miss for the L2 cache with a snoop miss in the other processor module.",
         "Offcore": "1"
     },
     {
         "CollectPEBSRecord": "1",
         "PublicDescription": "Counts demand instruction cacheline and I-side prefetch requests that miss the instruction cache that hit the L2 cache. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
         "EventCode": "0xB7",
-        "MSRValue": "0x0000040004 ",
+        "MSRValue": "0x0000040004",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L2_HIT",
@@ -1849,22 +1148,9 @@
     },
     {
         "CollectPEBSRecord": "1",
-        "PublicDescription": "Counts demand instruction cacheline and I-side prefetch requests that miss the instruction cache that have any transaction responses from the uncore subsystem. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
-        "EventCode": "0xB7",
-        "MSRValue": "0x0000010004 ",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.ANY_RESPONSE",
-        "MSRIndex": "0x1a6,0x1a7",
-        "SampleAfterValue": "100007",
-        "BriefDescription": "Counts demand instruction cacheline and I-side prefetch requests that miss the instruction cache that have any transaction responses from the uncore subsystem.",
-        "Offcore": "1"
-    },
-    {
-        "CollectPEBSRecord": "1",
         "PublicDescription": "Counts demand reads for ownership (RFO) requests generated by a write to full data cache line that are outstanding, per cycle, from the time of the L2 miss to when any response is received. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
         "EventCode": "0xB7",
-        "MSRValue": "0x4000000002 ",
+        "MSRValue": "0x4000000002",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.OUTSTANDING",
@@ -1877,7 +1163,7 @@
         "CollectPEBSRecord": "1",
         "PublicDescription": "Counts demand reads for ownership (RFO) requests generated by a write to full data cache line that miss the L2 cache. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
         "EventCode": "0xB7",
-        "MSRValue": "0x3600000002 ",
+        "MSRValue": "0x3600000002",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L2_MISS.ANY",
@@ -1890,7 +1176,7 @@
         "CollectPEBSRecord": "1",
         "PublicDescription": "Counts demand reads for ownership (RFO) requests generated by a write to full data cache line that miss the L2 cache with a snoop hit in the other processor module, data forwarding is required. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
         "EventCode": "0xB7",
-        "MSRValue": "0x1000000002 ",
+        "MSRValue": "0x1000000002",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L2_MISS.HITM_OTHER_CORE",
@@ -1903,7 +1189,7 @@
         "CollectPEBSRecord": "1",
         "PublicDescription": "Counts demand reads for ownership (RFO) requests generated by a write to full data cache line that miss the L2 cache with a snoop hit in the other processor module, no data forwarding is required. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
         "EventCode": "0xB7",
-        "MSRValue": "0x0400000002 ",
+        "MSRValue": "0x0400000002",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L2_MISS.HIT_OTHER_CORE_NO_FWD",
@@ -1916,20 +1202,20 @@
         "CollectPEBSRecord": "1",
         "PublicDescription": "Counts demand reads for ownership (RFO) requests generated by a write to full data cache line that true miss for the L2 cache with a snoop miss in the other processor module.  Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
         "EventCode": "0xB7",
-        "MSRValue": "0x0200000002 ",
+        "MSRValue": "0x0200000002",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L2_MISS.SNOOP_MISS_OR_NO_SNOOP_NEEDED",
         "MSRIndex": "0x1a6,0x1a7",
         "SampleAfterValue": "100007",
-        "BriefDescription": "Counts demand reads for ownership (RFO) requests generated by a write to full data cache line that true miss for the L2 cache with a snoop miss in the other processor module. ",
+        "BriefDescription": "Counts demand reads for ownership (RFO) requests generated by a write to full data cache line that true miss for the L2 cache with a snoop miss in the other processor module.",
         "Offcore": "1"
     },
     {
         "CollectPEBSRecord": "1",
         "PublicDescription": "Counts demand reads for ownership (RFO) requests generated by a write to full data cache line that hit the L2 cache. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
         "EventCode": "0xB7",
-        "MSRValue": "0x0000040002 ",
+        "MSRValue": "0x0000040002",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L2_HIT",
@@ -1940,22 +1226,9 @@
     },
     {
         "CollectPEBSRecord": "1",
-        "PublicDescription": "Counts demand reads for ownership (RFO) requests generated by a write to full data cache line that have any transaction responses from the uncore subsystem. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
-        "EventCode": "0xB7",
-        "MSRValue": "0x0000010002 ",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.ANY_RESPONSE",
-        "MSRIndex": "0x1a6,0x1a7",
-        "SampleAfterValue": "100007",
-        "BriefDescription": "Counts demand reads for ownership (RFO) requests generated by a write to full data cache line that have any transaction responses from the uncore subsystem.",
-        "Offcore": "1"
-    },
-    {
-        "CollectPEBSRecord": "1",
         "PublicDescription": "Counts demand cacheable data reads of full cache lines that are outstanding, per cycle, from the time of the L2 miss to when any response is received. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
         "EventCode": "0xB7",
-        "MSRValue": "0x4000000001 ",
+        "MSRValue": "0x4000000001",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.OUTSTANDING",
@@ -1968,7 +1241,7 @@
         "CollectPEBSRecord": "1",
         "PublicDescription": "Counts demand cacheable data reads of full cache lines that miss the L2 cache. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
         "EventCode": "0xB7",
-        "MSRValue": "0x3600000001 ",
+        "MSRValue": "0x3600000001",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L2_MISS.ANY",
@@ -1981,7 +1254,7 @@
         "CollectPEBSRecord": "1",
         "PublicDescription": "Counts demand cacheable data reads of full cache lines that miss the L2 cache with a snoop hit in the other processor module, data forwarding is required. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
         "EventCode": "0xB7",
-        "MSRValue": "0x1000000001 ",
+        "MSRValue": "0x1000000001",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L2_MISS.HITM_OTHER_CORE",
@@ -1994,7 +1267,7 @@
         "CollectPEBSRecord": "1",
         "PublicDescription": "Counts demand cacheable data reads of full cache lines that miss the L2 cache with a snoop hit in the other processor module, no data forwarding is required. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
         "EventCode": "0xB7",
-        "MSRValue": "0x0400000001 ",
+        "MSRValue": "0x0400000001",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L2_MISS.HIT_OTHER_CORE_NO_FWD",
@@ -2007,20 +1280,20 @@
         "CollectPEBSRecord": "1",
         "PublicDescription": "Counts demand cacheable data reads of full cache lines that true miss for the L2 cache with a snoop miss in the other processor module.  Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
         "EventCode": "0xB7",
-        "MSRValue": "0x0200000001 ",
+        "MSRValue": "0x0200000001",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L2_MISS.SNOOP_MISS_OR_NO_SNOOP_NEEDED",
         "MSRIndex": "0x1a6,0x1a7",
         "SampleAfterValue": "100007",
-        "BriefDescription": "Counts demand cacheable data reads of full cache lines that true miss for the L2 cache with a snoop miss in the other processor module. ",
+        "BriefDescription": "Counts demand cacheable data reads of full cache lines that true miss for the L2 cache with a snoop miss in the other processor module.",
         "Offcore": "1"
     },
     {
         "CollectPEBSRecord": "1",
         "PublicDescription": "Counts demand cacheable data reads of full cache lines that hit the L2 cache. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
         "EventCode": "0xB7",
-        "MSRValue": "0x0000040001 ",
+        "MSRValue": "0x0000040001",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L2_HIT",
@@ -2028,18 +1301,5 @@
         "SampleAfterValue": "100007",
         "BriefDescription": "Counts demand cacheable data reads of full cache lines that hit the L2 cache.",
         "Offcore": "1"
-    },
-    {
-        "CollectPEBSRecord": "1",
-        "PublicDescription": "Counts demand cacheable data reads of full cache lines that have any transaction responses from the uncore subsystem. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
-        "EventCode": "0xB7",
-        "MSRValue": "0x0000010001 ",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.ANY_RESPONSE",
-        "MSRIndex": "0x1a6,0x1a7",
-        "SampleAfterValue": "100007",
-        "BriefDescription": "Counts demand cacheable data reads of full cache lines that have any transaction responses from the uncore subsystem.",
-        "Offcore": "1"
     }
 ]
\ No newline at end of file
diff --git a/tools/perf/pmu-events/arch/x86/goldmont/memory.json b/tools/perf/pmu-events/arch/x86/goldmont/memory.json
index 690cebd12a94..197dc76d49dd 100644
--- a/tools/perf/pmu-events/arch/x86/goldmont/memory.json
+++ b/tools/perf/pmu-events/arch/x86/goldmont/memory.json
@@ -30,265 +30,5 @@
         "EventName": "MACHINE_CLEARS.MEMORY_ORDERING",
         "SampleAfterValue": "200003",
         "BriefDescription": "Machine clears due to memory ordering issue"
-    },
-    {
-        "CollectPEBSRecord": "1",
-        "PublicDescription": "Counts data read, code read, and read for ownership (RFO) requests (demand & prefetch) that miss the L2 cache and targets non-DRAM system address. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
-        "EventCode": "0xB7",
-        "MSRValue": "0x20000032b7 ",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.ANY_READ.L2_MISS.NON_DRAM",
-        "MSRIndex": "0x1a6,0x1a7",
-        "SampleAfterValue": "100007",
-        "BriefDescription": "Counts data read, code read, and read for ownership (RFO) requests (demand & prefetch) that miss the L2 cache and targets non-DRAM system address.",
-        "Offcore": "1"
-    },
-    {
-        "CollectPEBSRecord": "1",
-        "PublicDescription": "Counts reads for ownership (RFO) requests (demand & prefetch) that miss the L2 cache and targets non-DRAM system address. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
-        "EventCode": "0xB7",
-        "MSRValue": "0x2000000022 ",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.ANY_RFO.L2_MISS.NON_DRAM",
-        "MSRIndex": "0x1a6,0x1a7",
-        "SampleAfterValue": "100007",
-        "BriefDescription": "Counts reads for ownership (RFO) requests (demand & prefetch) that miss the L2 cache and targets non-DRAM system address.",
-        "Offcore": "1"
-    },
-    {
-        "CollectPEBSRecord": "1",
-        "PublicDescription": "Counts data reads (demand & prefetch) that miss the L2 cache and targets non-DRAM system address. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
-        "EventCode": "0xB7",
-        "MSRValue": "0x2000003091",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.ANY_DATA_RD.L2_MISS.NON_DRAM",
-        "MSRIndex": "0x1a6,0x1a7",
-        "SampleAfterValue": "100007",
-        "BriefDescription": "Counts data reads (demand & prefetch) that miss the L2 cache and targets non-DRAM system address.",
-        "Offcore": "1"
-    },
-    {
-        "CollectPEBSRecord": "1",
-        "PublicDescription": "Counts data reads generated by L1 or L2 prefetchers that miss the L2 cache and targets non-DRAM system address. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
-        "EventCode": "0xB7",
-        "MSRValue": "0x2000003010 ",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.ANY_PF_DATA_RD.L2_MISS.NON_DRAM",
-        "MSRIndex": "0x1a6,0x1a7",
-        "SampleAfterValue": "100007",
-        "BriefDescription": "Counts data reads generated by L1 or L2 prefetchers that miss the L2 cache and targets non-DRAM system address.",
-        "Offcore": "1"
-    },
-    {
-        "CollectPEBSRecord": "1",
-        "PublicDescription": "Counts requests to the uncore subsystem that miss the L2 cache and targets non-DRAM system address. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
-        "EventCode": "0xB7",
-        "MSRValue": "0x2000008000 ",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.ANY_REQUEST.L2_MISS.NON_DRAM",
-        "MSRIndex": "0x1a6,0x1a7",
-        "SampleAfterValue": "100007",
-        "BriefDescription": "Counts requests to the uncore subsystem that miss the L2 cache and targets non-DRAM system address.",
-        "Offcore": "1"
-    },
-    {
-        "CollectPEBSRecord": "1",
-        "PublicDescription": "Counts any data writes to uncacheable write combining (USWC) memory region  that miss the L2 cache and targets non-DRAM system address. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
-        "EventCode": "0xB7",
-        "MSRValue": "0x2000004800 ",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.STREAMING_STORES.L2_MISS.NON_DRAM",
-        "MSRIndex": "0x1a6,0x1a7",
-        "SampleAfterValue": "100007",
-        "BriefDescription": "Counts any data writes to uncacheable write combining (USWC) memory region  that miss the L2 cache and targets non-DRAM system address.",
-        "Offcore": "1"
-    },
-    {
-        "CollectPEBSRecord": "1",
-        "PublicDescription": "Counts partial cache line data writes to uncacheable write combining (USWC) memory region  that miss the L2 cache and targets non-DRAM system address. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
-        "EventCode": "0xB7",
-        "MSRValue": "0x2000004000 ",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.PARTIAL_STREAMING_STORES.L2_MISS.NON_DRAM",
-        "MSRIndex": "0x1a6,0x1a7",
-        "SampleAfterValue": "100007",
-        "BriefDescription": "Counts partial cache line data writes to uncacheable write combining (USWC) memory region  that miss the L2 cache and targets non-DRAM system address.",
-        "Offcore": "1"
-    },
-    {
-        "CollectPEBSRecord": "1",
-        "PublicDescription": "Counts data cache line reads generated by hardware L1 data cache prefetcher that miss the L2 cache and targets non-DRAM system address. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
-        "EventCode": "0xB7",
-        "MSRValue": "0x2000002000 ",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.PF_L1_DATA_RD.L2_MISS.NON_DRAM",
-        "MSRIndex": "0x1a6,0x1a7",
-        "SampleAfterValue": "100007",
-        "BriefDescription": "Counts data cache line reads generated by hardware L1 data cache prefetcher that miss the L2 cache and targets non-DRAM system address.",
-        "Offcore": "1"
-    },
-    {
-        "CollectPEBSRecord": "1",
-        "PublicDescription": "Counts data cache lines requests by software prefetch instructions that miss the L2 cache and targets non-DRAM system address. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
-        "EventCode": "0xB7",
-        "MSRValue": "0x2000001000 ",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.SW_PREFETCH.L2_MISS.NON_DRAM",
-        "MSRIndex": "0x1a6,0x1a7",
-        "SampleAfterValue": "100007",
-        "BriefDescription": "Counts data cache lines requests by software prefetch instructions that miss the L2 cache and targets non-DRAM system address.",
-        "Offcore": "1"
-    },
-    {
-        "CollectPEBSRecord": "1",
-        "PublicDescription": "Counts full cache line data writes to uncacheable write combining (USWC) memory region and full cache-line non-temporal writes that miss the L2 cache and targets non-DRAM system address. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
-        "EventCode": "0xB7",
-        "MSRValue": "0x2000000800 ",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.FULL_STREAMING_STORES.L2_MISS.NON_DRAM",
-        "MSRIndex": "0x1a6,0x1a7",
-        "SampleAfterValue": "100007",
-        "BriefDescription": "Counts full cache line data writes to uncacheable write combining (USWC) memory region and full cache-line non-temporal writes that miss the L2 cache and targets non-DRAM system address.",
-        "Offcore": "1"
-    },
-    {
-        "CollectPEBSRecord": "1",
-        "PublicDescription": "Counts bus lock and split lock requests that miss the L2 cache and targets non-DRAM system address. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
-        "EventCode": "0xB7",
-        "MSRValue": "0x2000000400 ",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.BUS_LOCKS.L2_MISS.NON_DRAM",
-        "MSRIndex": "0x1a6,0x1a7",
-        "SampleAfterValue": "100007",
-        "BriefDescription": "Counts bus lock and split lock requests that miss the L2 cache and targets non-DRAM system address.",
-        "Offcore": "1"
-    },
-    {
-        "CollectPEBSRecord": "1",
-        "PublicDescription": "Counts code reads in uncacheable (UC) memory region that miss the L2 cache and targets non-DRAM system address. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
-        "EventCode": "0xB7",
-        "MSRValue": "0x2000000200 ",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.UC_CODE_RD.L2_MISS.NON_DRAM",
-        "MSRIndex": "0x1a6,0x1a7",
-        "SampleAfterValue": "100007",
-        "BriefDescription": "Counts code reads in uncacheable (UC) memory region that miss the L2 cache and targets non-DRAM system address.",
-        "Offcore": "1"
-    },
-    {
-        "CollectPEBSRecord": "1",
-        "PublicDescription": "Counts the number of demand write requests (RFO) generated by a write to partial data cache line, including the writes to uncacheable (UC) and write through (WT), and write protected (WP) types of memory that miss the L2 cache and targets non-DRAM system address. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
-        "EventCode": "0xB7",
-        "MSRValue": "0x2000000100 ",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.PARTIAL_WRITES.L2_MISS.NON_DRAM",
-        "MSRIndex": "0x1a6,0x1a7",
-        "SampleAfterValue": "100007",
-        "BriefDescription": "Counts the number of demand write requests (RFO) generated by a write to partial data cache line, including the writes to uncacheable (UC) and write through (WT), and write protected (WP) types of memory that miss the L2 cache and targets non-DRAM system address.",
-        "Offcore": "1"
-    },
-    {
-        "CollectPEBSRecord": "1",
-        "PublicDescription": "Counts demand data partial reads, including data in uncacheable (UC) or uncacheable write combining (USWC) memory types that miss the L2 cache and targets non-DRAM system address. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
-        "EventCode": "0xB7",
-        "MSRValue": "0x2000000080 ",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.PARTIAL_READS.L2_MISS.NON_DRAM",
-        "MSRIndex": "0x1a6,0x1a7",
-        "SampleAfterValue": "100007",
-        "BriefDescription": "Counts demand data partial reads, including data in uncacheable (UC) or uncacheable write combining (USWC) memory types that miss the L2 cache and targets non-DRAM system address.",
-        "Offcore": "1"
-    },
-    {
-        "CollectPEBSRecord": "1",
-        "PublicDescription": "Counts reads for ownership (RFO) requests generated by L2 prefetcher that miss the L2 cache and targets non-DRAM system address. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
-        "EventCode": "0xB7",
-        "MSRValue": "0x2000000020 ",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.PF_L2_RFO.L2_MISS.NON_DRAM",
-        "MSRIndex": "0x1a6,0x1a7",
-        "SampleAfterValue": "100007",
-        "BriefDescription": "Counts reads for ownership (RFO) requests generated by L2 prefetcher that miss the L2 cache and targets non-DRAM system address.",
-        "Offcore": "1"
-    },
-    {
-        "CollectPEBSRecord": "1",
-        "PublicDescription": "Counts data cacheline reads generated by hardware L2 cache prefetcher that miss the L2 cache and targets non-DRAM system address. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
-        "EventCode": "0xB7",
-        "MSRValue": "0x2000000010 ",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.PF_L2_DATA_RD.L2_MISS.NON_DRAM",
-        "MSRIndex": "0x1a6,0x1a7",
-        "SampleAfterValue": "100007",
-        "BriefDescription": "Counts data cacheline reads generated by hardware L2 cache prefetcher that miss the L2 cache and targets non-DRAM system address.",
-        "Offcore": "1"
-    },
-    {
-        "CollectPEBSRecord": "1",
-        "PublicDescription": "Counts the number of writeback transactions caused by L1 or L2 cache evictions that miss the L2 cache and targets non-DRAM system address. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
-        "EventCode": "0xB7",
-        "MSRValue": "0x2000000008 ",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.COREWB.L2_MISS.NON_DRAM",
-        "MSRIndex": "0x1a6",
-        "SampleAfterValue": "100007",
-        "BriefDescription": "Counts the number of writeback transactions caused by L1 or L2 cache evictions that miss the L2 cache and targets non-DRAM system address.",
-        "Offcore": "1"
-    },
-    {
-        "CollectPEBSRecord": "1",
-        "PublicDescription": "Counts demand instruction cacheline and I-side prefetch requests that miss the instruction cache that miss the L2 cache and targets non-DRAM system address. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
-        "EventCode": "0xB7",
-        "MSRValue": "0x2000000004 ",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L2_MISS.NON_DRAM",
-        "MSRIndex": "0x1a6,0x1a7",
-        "SampleAfterValue": "100007",
-        "BriefDescription": "Counts demand instruction cacheline and I-side prefetch requests that miss the instruction cache that miss the L2 cache and targets non-DRAM system address.",
-        "Offcore": "1"
-    },
-    {
-        "CollectPEBSRecord": "1",
-        "PublicDescription": "Counts demand reads for ownership (RFO) requests generated by a write to full data cache line that miss the L2 cache and targets non-DRAM system address. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
-        "EventCode": "0xB7",
-        "MSRValue": "0x2000000002 ",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L2_MISS.NON_DRAM",
-        "MSRIndex": "0x1a6,0x1a7",
-        "SampleAfterValue": "100007",
-        "BriefDescription": "Counts demand reads for ownership (RFO) requests generated by a write to full data cache line that miss the L2 cache and targets non-DRAM system address.",
-        "Offcore": "1"
-    },
-    {
-        "CollectPEBSRecord": "1",
-        "PublicDescription": "Counts demand cacheable data reads of full cache lines that miss the L2 cache and targets non-DRAM system address. Requires MSR_OFFCORE_RESP[0,1] to specify request type and response. (duplicated for both MSRs)",
-        "EventCode": "0xB7",
-        "MSRValue": "0x2000000001 ",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L2_MISS.NON_DRAM",
-        "MSRIndex": "0x1a6,0x1a7",
-        "SampleAfterValue": "100007",
-        "BriefDescription": "Counts demand cacheable data reads of full cache lines that miss the L2 cache and targets non-DRAM system address.",
-        "Offcore": "1"
     }
 ]
\ No newline at end of file
diff --git a/tools/perf/pmu-events/arch/x86/goldmont/pipeline.json b/tools/perf/pmu-events/arch/x86/goldmont/pipeline.json
index 254788af8ab6..6342368accf8 100644
--- a/tools/perf/pmu-events/arch/x86/goldmont/pipeline.json
+++ b/tools/perf/pmu-events/arch/x86/goldmont/pipeline.json
@@ -1,7 +1,6 @@
 [
     {
         "PublicDescription": "Counts the number of instructions that retire execution. For instructions that consist of multiple uops, this event counts the retirement of the last uop of the instruction. The counter continues counting during hardware interrupts, traps, and inside interrupt handlers.  This event uses fixed counter 0.  You cannot collect a PEBs record for this event.",
-        "EventCode": "0x00",
         "Counter": "Fixed counter 0",
         "UMask": "0x1",
         "EventName": "INST_RETIRED.ANY",
@@ -10,7 +9,6 @@
     },
     {
         "PublicDescription": "Counts the number of core cycles while the core is not in a halt state.  The core enters the halt state when it is running the HLT instruction. In mobile systems the core frequency may change from time to time. For this reason this event may have a changing ratio with regards to time.  This event uses fixed counter 1.  You cannot collect a PEBs record for this event.",
-        "EventCode": "0x00",
         "Counter": "Fixed counter 1",
         "UMask": "0x2",
         "EventName": "CPU_CLK_UNHALTED.CORE",
@@ -19,7 +17,6 @@
     },
     {
         "PublicDescription": "Counts the number of reference cycles that the core is not in a halt state. The core enters the halt state when it is running the HLT instruction.  In mobile systems the core frequency may change from time.  This event is not affected by core frequency changes but counts as if the core is running at the maximum frequency all the time.  This event uses fixed counter 2.  You cannot collect a PEBs record for this event.",
-        "EventCode": "0x00",
         "Counter": "Fixed counter 2",
         "UMask": "0x3",
         "EventName": "CPU_CLK_UNHALTED.REF_TSC",
@@ -188,7 +185,7 @@
     },
     {
         "CollectPEBSRecord": "1",
-        "PublicDescription": "Counts the number of times that the processor detects that a program is writing to a code section and has to perform a machine clear because of that modification.  Self-modifying code (SMC) causes a severe penalty in all Intel architecture processors.",
+        "PublicDescription": "Counts the number of times that the processor detects that a program is writing to a code section and has to perform a machine clear because of that modification.  Self-modifying code (SMC) causes a severe penalty in all Intel\u00ae architecture processors.",
         "EventCode": "0xC3",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
diff --git a/tools/perf/pmu-events/arch/x86/goldmont/virtual-memory.json b/tools/perf/pmu-events/arch/x86/goldmont/virtual-memory.json
index 9805198d3f5f..343d66bbd777 100644
--- a/tools/perf/pmu-events/arch/x86/goldmont/virtual-memory.json
+++ b/tools/perf/pmu-events/arch/x86/goldmont/virtual-memory.json
@@ -48,7 +48,8 @@
         "UMask": "0x11",
         "EventName": "MEM_UOPS_RETIRED.DTLB_MISS_LOADS",
         "SampleAfterValue": "200003",
-        "BriefDescription": "Load uops retired that missed the DTLB (Precise event capable)"
+        "BriefDescription": "Load uops retired that missed the DTLB (Precise event capable)",
+        "Data_LA": "1"
     },
     {
         "PEBS": "2",
@@ -59,7 +60,8 @@
         "UMask": "0x12",
         "EventName": "MEM_UOPS_RETIRED.DTLB_MISS_STORES",
         "SampleAfterValue": "200003",
-        "BriefDescription": "Store uops retired that missed the DTLB (Precise event capable)"
+        "BriefDescription": "Store uops retired that missed the DTLB (Precise event capable)",
+        "Data_LA": "1"
     },
     {
         "PEBS": "2",
@@ -70,6 +72,7 @@
         "UMask": "0x13",
         "EventName": "MEM_UOPS_RETIRED.DTLB_MISS",
         "SampleAfterValue": "200003",
-        "BriefDescription": "Memory uops retired that missed the DTLB (Precise event capable)"
+        "BriefDescription": "Memory uops retired that missed the DTLB (Precise event capable)",
+        "Data_LA": "1"
     }
 ]
\ No newline at end of file
diff --git a/tools/perf/pmu-events/arch/x86/goldmontplus/cache.json b/tools/perf/pmu-events/arch/x86/goldmontplus/cache.json
index b4791b443a66..5a6ac8285ad4 100644
--- a/tools/perf/pmu-events/arch/x86/goldmontplus/cache.json
+++ b/tools/perf/pmu-events/arch/x86/goldmontplus/cache.json
@@ -92,7 +92,8 @@
         "PEBScounters": "0,1,2,3",
         "EventName": "MEM_UOPS_RETIRED.LOCK_LOADS",
         "SampleAfterValue": "200003",
-        "BriefDescription": "Locked load uops retired (Precise event capable)"
+        "BriefDescription": "Locked load uops retired (Precise event capable)",
+        "Data_LA": "1"
     },
     {
         "PEBS": "2",
@@ -104,7 +105,8 @@
         "PEBScounters": "0,1,2,3",
         "EventName": "MEM_UOPS_RETIRED.SPLIT_LOADS",
         "SampleAfterValue": "200003",
-        "BriefDescription": "Load uops retired that split a cache-line (Precise event capable)"
+        "BriefDescription": "Load uops retired that split a cache-line (Precise event capable)",
+        "Data_LA": "1"
     },
     {
         "PEBS": "2",
@@ -116,7 +118,8 @@
         "PEBScounters": "0,1,2,3",
         "EventName": "MEM_UOPS_RETIRED.SPLIT_STORES",
         "SampleAfterValue": "200003",
-        "BriefDescription": "Stores uops retired that split a cache-line (Precise event capable)"
+        "BriefDescription": "Stores uops retired that split a cache-line (Precise event capable)",
+        "Data_LA": "1"
     },
     {
         "PEBS": "2",
@@ -128,7 +131,8 @@
         "PEBScounters": "0,1,2,3",
         "EventName": "MEM_UOPS_RETIRED.SPLIT",
         "SampleAfterValue": "200003",
-        "BriefDescription": "Memory uops retired that split a cache-line (Precise event capable)"
+        "BriefDescription": "Memory uops retired that split a cache-line (Precise event capable)",
+        "Data_LA": "1"
     },
     {
         "PEBS": "2",
@@ -140,7 +144,8 @@
         "PEBScounters": "0,1,2,3",
         "EventName": "MEM_UOPS_RETIRED.ALL_LOADS",
         "SampleAfterValue": "200003",
-        "BriefDescription": "Load uops retired (Precise event capable)"
+        "BriefDescription": "Load uops retired (Precise event capable)",
+        "Data_LA": "1"
     },
     {
         "PEBS": "2",
@@ -152,7 +157,8 @@
         "PEBScounters": "0,1,2,3",
         "EventName": "MEM_UOPS_RETIRED.ALL_STORES",
         "SampleAfterValue": "200003",
-        "BriefDescription": "Store uops retired (Precise event capable)"
+        "BriefDescription": "Store uops retired (Precise event capable)",
+        "Data_LA": "1"
     },
     {
         "PEBS": "2",
@@ -164,7 +170,8 @@
         "PEBScounters": "0,1,2,3",
         "EventName": "MEM_UOPS_RETIRED.ALL",
         "SampleAfterValue": "200003",
-        "BriefDescription": "Memory uops retired (Precise event capable)"
+        "BriefDescription": "Memory uops retired (Precise event capable)",
+        "Data_LA": "1"
     },
     {
         "PEBS": "2",
@@ -176,7 +183,8 @@
         "PEBScounters": "0,1,2,3",
         "EventName": "MEM_LOAD_UOPS_RETIRED.L1_HIT",
         "SampleAfterValue": "200003",
-        "BriefDescription": "Load uops retired that hit L1 data cache (Precise event capable)"
+        "BriefDescription": "Load uops retired that hit L1 data cache (Precise event capable)",
+        "Data_LA": "1"
     },
     {
         "PEBS": "2",
@@ -188,7 +196,8 @@
         "PEBScounters": "0,1,2,3",
         "EventName": "MEM_LOAD_UOPS_RETIRED.L2_HIT",
         "SampleAfterValue": "200003",
-        "BriefDescription": "Load uops retired that hit L2 (Precise event capable)"
+        "BriefDescription": "Load uops retired that hit L2 (Precise event capable)",
+        "Data_LA": "1"
     },
     {
         "PEBS": "2",
@@ -200,7 +209,8 @@
         "PEBScounters": "0,1,2,3",
         "EventName": "MEM_LOAD_UOPS_RETIRED.L1_MISS",
         "SampleAfterValue": "200003",
-        "BriefDescription": "Load uops retired that missed L1 data cache (Precise event capable)"
+        "BriefDescription": "Load uops retired that missed L1 data cache (Precise event capable)",
+        "Data_LA": "1"
     },
     {
         "PEBS": "2",
@@ -212,7 +222,8 @@
         "PEBScounters": "0,1,2,3",
         "EventName": "MEM_LOAD_UOPS_RETIRED.L2_MISS",
         "SampleAfterValue": "200003",
-        "BriefDescription": "Load uops retired that missed L2 (Precise event capable)"
+        "BriefDescription": "Load uops retired that missed L2 (Precise event capable)",
+        "Data_LA": "1"
     },
     {
         "PEBS": "2",
@@ -224,7 +235,8 @@
         "PEBScounters": "0,1,2,3",
         "EventName": "MEM_LOAD_UOPS_RETIRED.HITM",
         "SampleAfterValue": "200003",
-        "BriefDescription": "Memory uop retired where cross core or cross module HITM occurred (Precise event capable)"
+        "BriefDescription": "Memory uop retired where cross core or cross module HITM occurred (Precise event capable)",
+        "Data_LA": "1"
     },
     {
         "PEBS": "2",
@@ -236,7 +248,8 @@
         "PEBScounters": "0,1,2,3",
         "EventName": "MEM_LOAD_UOPS_RETIRED.WCB_HIT",
         "SampleAfterValue": "200003",
-        "BriefDescription": "Loads retired that hit WCB (Precise event capable)"
+        "BriefDescription": "Loads retired that hit WCB (Precise event capable)",
+        "Data_LA": "1"
     },
     {
         "PEBS": "2",
@@ -248,7 +261,8 @@
         "PEBScounters": "0,1,2,3",
         "EventName": "MEM_LOAD_UOPS_RETIRED.DRAM_HIT",
         "SampleAfterValue": "200003",
-        "BriefDescription": "Loads retired that came from DRAM (Precise event capable)"
+        "BriefDescription": "Loads retired that came from DRAM (Precise event capable)",
+        "Data_LA": "1"
     },
     {
         "CollectPEBSRecord": "1",
@@ -292,7 +306,7 @@
         "PDIR_COUNTER": "na",
         "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100007",
-        "BriefDescription": "Counts demand cacheable data reads of full cache lines true miss for the L2 cache with a snoop miss in the other processor module. ",
+        "BriefDescription": "Counts demand cacheable data reads of full cache lines true miss for the L2 cache with a snoop miss in the other processor module.",
         "Offcore": "1"
     },
     {
@@ -367,7 +381,7 @@
         "PDIR_COUNTER": "na",
         "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100007",
-        "BriefDescription": "Counts demand reads for ownership (RFO) requests generated by a write to full data cache line true miss for the L2 cache with a snoop miss in the other processor module. ",
+        "BriefDescription": "Counts demand reads for ownership (RFO) requests generated by a write to full data cache line true miss for the L2 cache with a snoop miss in the other processor module.",
         "Offcore": "1"
     },
     {
@@ -442,7 +456,7 @@
         "PDIR_COUNTER": "na",
         "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100007",
-        "BriefDescription": "Counts demand instruction cacheline and I-side prefetch requests that miss the instruction cache true miss for the L2 cache with a snoop miss in the other processor module. ",
+        "BriefDescription": "Counts demand instruction cacheline and I-side prefetch requests that miss the instruction cache true miss for the L2 cache with a snoop miss in the other processor module.",
         "Offcore": "1"
     },
     {
@@ -517,7 +531,7 @@
         "PDIR_COUNTER": "na",
         "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100007",
-        "BriefDescription": "Counts the number of writeback transactions caused by L1 or L2 cache evictions true miss for the L2 cache with a snoop miss in the other processor module. ",
+        "BriefDescription": "Counts the number of writeback transactions caused by L1 or L2 cache evictions true miss for the L2 cache with a snoop miss in the other processor module.",
         "Offcore": "1"
     },
     {
@@ -592,7 +606,7 @@
         "PDIR_COUNTER": "na",
         "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100007",
-        "BriefDescription": "Counts data cacheline reads generated by hardware L2 cache prefetcher true miss for the L2 cache with a snoop miss in the other processor module. ",
+        "BriefDescription": "Counts data cacheline reads generated by hardware L2 cache prefetcher true miss for the L2 cache with a snoop miss in the other processor module.",
         "Offcore": "1"
     },
     {
@@ -667,7 +681,7 @@
         "PDIR_COUNTER": "na",
         "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100007",
-        "BriefDescription": "Counts reads for ownership (RFO) requests generated by L2 prefetcher true miss for the L2 cache with a snoop miss in the other processor module. ",
+        "BriefDescription": "Counts reads for ownership (RFO) requests generated by L2 prefetcher true miss for the L2 cache with a snoop miss in the other processor module.",
         "Offcore": "1"
     },
     {
@@ -742,7 +756,7 @@
         "PDIR_COUNTER": "na",
         "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100007",
-        "BriefDescription": "Counts bus lock and split lock requests true miss for the L2 cache with a snoop miss in the other processor module. ",
+        "BriefDescription": "Counts bus lock and split lock requests true miss for the L2 cache with a snoop miss in the other processor module.",
         "Offcore": "1"
     },
     {
@@ -817,7 +831,7 @@
         "PDIR_COUNTER": "na",
         "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100007",
-        "BriefDescription": "Counts full cache line data writes to uncacheable write combining (USWC) memory region and full cache-line non-temporal writes true miss for the L2 cache with a snoop miss in the other processor module. ",
+        "BriefDescription": "Counts full cache line data writes to uncacheable write combining (USWC) memory region and full cache-line non-temporal writes true miss for the L2 cache with a snoop miss in the other processor module.",
         "Offcore": "1"
     },
     {
@@ -892,7 +906,7 @@
         "PDIR_COUNTER": "na",
         "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100007",
-        "BriefDescription": "Counts data cache lines requests by software prefetch instructions true miss for the L2 cache with a snoop miss in the other processor module. ",
+        "BriefDescription": "Counts data cache lines requests by software prefetch instructions true miss for the L2 cache with a snoop miss in the other processor module.",
         "Offcore": "1"
     },
     {
@@ -967,7 +981,7 @@
         "PDIR_COUNTER": "na",
         "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100007",
-        "BriefDescription": "Counts data cache line reads generated by hardware L1 data cache prefetcher true miss for the L2 cache with a snoop miss in the other processor module. ",
+        "BriefDescription": "Counts data cache line reads generated by hardware L1 data cache prefetcher true miss for the L2 cache with a snoop miss in the other processor module.",
         "Offcore": "1"
     },
     {
@@ -1042,7 +1056,7 @@
         "PDIR_COUNTER": "na",
         "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100007",
-        "BriefDescription": "Counts any data writes to uncacheable write combining (USWC) memory region  true miss for the L2 cache with a snoop miss in the other processor module. ",
+        "BriefDescription": "Counts any data writes to uncacheable write combining (USWC) memory region  true miss for the L2 cache with a snoop miss in the other processor module.",
         "Offcore": "1"
     },
     {
@@ -1117,7 +1131,7 @@
         "PDIR_COUNTER": "na",
         "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100007",
-        "BriefDescription": "Counts requests to the uncore subsystem true miss for the L2 cache with a snoop miss in the other processor module. ",
+        "BriefDescription": "Counts requests to the uncore subsystem true miss for the L2 cache with a snoop miss in the other processor module.",
         "Offcore": "1"
     },
     {
@@ -1192,7 +1206,7 @@
         "PDIR_COUNTER": "na",
         "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100007",
-        "BriefDescription": "Counts data reads generated by L1 or L2 prefetchers true miss for the L2 cache with a snoop miss in the other processor module. ",
+        "BriefDescription": "Counts data reads generated by L1 or L2 prefetchers true miss for the L2 cache with a snoop miss in the other processor module.",
         "Offcore": "1"
     },
     {
@@ -1267,7 +1281,7 @@
         "PDIR_COUNTER": "na",
         "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100007",
-        "BriefDescription": "Counts data reads (demand & prefetch) true miss for the L2 cache with a snoop miss in the other processor module. ",
+        "BriefDescription": "Counts data reads (demand & prefetch) true miss for the L2 cache with a snoop miss in the other processor module.",
         "Offcore": "1"
     },
     {
@@ -1342,7 +1356,7 @@
         "PDIR_COUNTER": "na",
         "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100007",
-        "BriefDescription": "Counts reads for ownership (RFO) requests (demand & prefetch) true miss for the L2 cache with a snoop miss in the other processor module. ",
+        "BriefDescription": "Counts reads for ownership (RFO) requests (demand & prefetch) true miss for the L2 cache with a snoop miss in the other processor module.",
         "Offcore": "1"
     },
     {
@@ -1417,7 +1431,7 @@
         "PDIR_COUNTER": "na",
         "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100007",
-        "BriefDescription": "Counts data read, code read, and read for ownership (RFO) requests (demand & prefetch) true miss for the L2 cache with a snoop miss in the other processor module. ",
+        "BriefDescription": "Counts data read, code read, and read for ownership (RFO) requests (demand & prefetch) true miss for the L2 cache with a snoop miss in the other processor module.",
         "Offcore": "1"
     },
     {
diff --git a/tools/perf/pmu-events/arch/x86/goldmontplus/pipeline.json b/tools/perf/pmu-events/arch/x86/goldmontplus/pipeline.json
index ccf1aed69197..e3fa1a0ba71b 100644
--- a/tools/perf/pmu-events/arch/x86/goldmontplus/pipeline.json
+++ b/tools/perf/pmu-events/arch/x86/goldmontplus/pipeline.json
@@ -3,7 +3,6 @@
         "PEBS": "2",
         "CollectPEBSRecord": "1",
         "PublicDescription": "Counts the number of instructions that retire execution. For instructions that consist of multiple uops, this event counts the retirement of the last uop of the instruction. The counter continues counting during hardware interrupts, traps, and inside interrupt handlers.  This event uses fixed counter 0.  You cannot collect a PEBs record for this event.",
-        "EventCode": "0x00",
         "Counter": "Fixed counter 0",
         "UMask": "0x1",
         "PEBScounters": "32",
@@ -15,7 +14,6 @@
     {
         "CollectPEBSRecord": "1",
         "PublicDescription": "Counts the number of core cycles while the core is not in a halt state.  The core enters the halt state when it is running the HLT instruction. In mobile systems the core frequency may change from time to time. For this reason this event may have a changing ratio with regards to time.  This event uses fixed counter 1.  You cannot collect a PEBs record for this event.",
-        "EventCode": "0x00",
         "Counter": "Fixed counter 1",
         "UMask": "0x2",
         "PEBScounters": "33",
@@ -27,7 +25,6 @@
     {
         "CollectPEBSRecord": "1",
         "PublicDescription": "Counts the number of reference cycles that the core is not in a halt state. The core enters the halt state when it is running the HLT instruction.  In mobile systems the core frequency may change from time.  This event is not affected by core frequency changes but counts as if the core is running at the maximum frequency all the time.  This event uses fixed counter 2.  You cannot collect a PEBs record for this event.",
-        "EventCode": "0x00",
         "Counter": "Fixed counter 2",
         "UMask": "0x3",
         "PEBScounters": "34",
@@ -231,7 +228,7 @@
     },
     {
         "CollectPEBSRecord": "1",
-        "PublicDescription": "Counts the number of times that the processor detects that a program is writing to a code section and has to perform a machine clear because of that modification.  Self-modifying code (SMC) causes a severe penalty in all Intel architecture processors.",
+        "PublicDescription": "Counts the number of times that the processor detects that a program is writing to a code section and has to perform a machine clear because of that modification.  Self-modifying code (SMC) causes a severe penalty in all Intel\u00ae architecture processors.",
         "EventCode": "0xC3",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
diff --git a/tools/perf/pmu-events/arch/x86/goldmontplus/virtual-memory.json b/tools/perf/pmu-events/arch/x86/goldmontplus/virtual-memory.json
index 0b53a3b0dfb8..0d32fd26ded1 100644
--- a/tools/perf/pmu-events/arch/x86/goldmontplus/virtual-memory.json
+++ b/tools/perf/pmu-events/arch/x86/goldmontplus/virtual-memory.json
@@ -189,7 +189,8 @@
         "PEBScounters": "0,1,2,3",
         "EventName": "MEM_UOPS_RETIRED.DTLB_MISS_LOADS",
         "SampleAfterValue": "200003",
-        "BriefDescription": "Load uops retired that missed the DTLB (Precise event capable)"
+        "BriefDescription": "Load uops retired that missed the DTLB (Precise event capable)",
+        "Data_LA": "1"
     },
     {
         "PEBS": "2",
@@ -201,7 +202,8 @@
         "PEBScounters": "0,1,2,3",
         "EventName": "MEM_UOPS_RETIRED.DTLB_MISS_STORES",
         "SampleAfterValue": "200003",
-        "BriefDescription": "Store uops retired that missed the DTLB (Precise event capable)"
+        "BriefDescription": "Store uops retired that missed the DTLB (Precise event capable)",
+        "Data_LA": "1"
     },
     {
         "PEBS": "2",
@@ -213,6 +215,7 @@
         "PEBScounters": "0,1,2,3",
         "EventName": "MEM_UOPS_RETIRED.DTLB_MISS",
         "SampleAfterValue": "200003",
-        "BriefDescription": "Memory uops retired that missed the DTLB (Precise event capable)"
+        "BriefDescription": "Memory uops retired that missed the DTLB (Precise event capable)",
+        "Data_LA": "1"
     }
 ]
\ No newline at end of file
diff --git a/tools/perf/pmu-events/arch/x86/haswell/cache.json b/tools/perf/pmu-events/arch/x86/haswell/cache.json
index da4d6ddd4f92..7fb0ad8d8ca1 100644
--- a/tools/perf/pmu-events/arch/x86/haswell/cache.json
+++ b/tools/perf/pmu-events/arch/x86/haswell/cache.json
@@ -63,10 +63,10 @@
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "PublicDescription": "Demand data read requests that hit L2 cache.",
+        "PublicDescription": "Counts the number of demand Data Read requests, initiated by load instructions, that hit L2 cache",
         "EventCode": "0x24",
         "Counter": "0,1,2,3",
-        "UMask": "0x41",
+        "UMask": "0xc1",
         "Errata": "HSD78",
         "EventName": "L2_RQSTS.DEMAND_DATA_RD_HIT",
         "SampleAfterValue": "200003",
@@ -77,7 +77,7 @@
         "PublicDescription": "Counts the number of store RFO requests that hit the L2 cache.",
         "EventCode": "0x24",
         "Counter": "0,1,2,3",
-        "UMask": "0x42",
+        "UMask": "0xc2",
         "EventName": "L2_RQSTS.RFO_HIT",
         "SampleAfterValue": "200003",
         "BriefDescription": "RFO requests that hit L2 cache",
@@ -87,7 +87,7 @@
         "PublicDescription": "Number of instruction fetches that hit the L2 cache.",
         "EventCode": "0x24",
         "Counter": "0,1,2,3",
-        "UMask": "0x44",
+        "UMask": "0xc4",
         "EventName": "L2_RQSTS.CODE_RD_HIT",
         "SampleAfterValue": "200003",
         "BriefDescription": "L2 cache hits when fetching instructions, code reads.",
@@ -97,7 +97,7 @@
         "PublicDescription": "Counts all L2 HW prefetcher requests that hit L2.",
         "EventCode": "0x24",
         "Counter": "0,1,2,3",
-        "UMask": "0x50",
+        "UMask": "0xd0",
         "EventName": "L2_RQSTS.L2_PF_HIT",
         "SampleAfterValue": "200003",
         "BriefDescription": "L2 prefetch requests that hit L2 cache",
@@ -610,7 +610,7 @@
         "Errata": "HSD29, HSD25, HSM26, HSM30",
         "EventName": "MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HIT",
         "SampleAfterValue": "20011",
-        "BriefDescription": "Retired load uops which data sources were L3 and cross-core snoop hits in on-pkg core cache. ",
+        "BriefDescription": "Retired load uops which data sources were L3 and cross-core snoop hits in on-pkg core cache.",
         "CounterHTOff": "0,1,2,3",
         "Data_LA": "1"
     },
@@ -623,7 +623,7 @@
         "Errata": "HSD29, HSD25, HSM26, HSM30",
         "EventName": "MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HITM",
         "SampleAfterValue": "20011",
-        "BriefDescription": "Retired load uops which data sources were HitM responses from shared L3. ",
+        "BriefDescription": "Retired load uops which data sources were HitM responses from shared L3.",
         "CounterHTOff": "0,1,2,3",
         "Data_LA": "1"
     },
@@ -792,7 +792,6 @@
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "PublicDescription": "",
         "EventCode": "0xf4",
         "Counter": "0,1,2,3",
         "UMask": "0x10",
@@ -802,262 +801,262 @@
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "PublicDescription": "Counts all requests that hit in the L3 Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all requests hit in the L3",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x3f803c8fff",
+        "MSRValue": "0x3F803C8FFF",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.ALL_REQUESTS.L3_HIT.ANY_RESPONSE",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "Counts all requests that hit in the L3",
+        "BriefDescription": "Counts all requests hit in the L3",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "Counts all data/code/rfo reads (demand & prefetch) that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x10003c07f7",
+        "MSRValue": "0x10003C07F7",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.ALL_READS.L3_HIT.HITM_OTHER_CORE",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "Counts all data/code/rfo reads (demand & prefetch) that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded",
+        "BriefDescription": "hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "Counts all data/code/rfo reads (demand & prefetch) that hit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "hit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x04003c07f7",
+        "MSRValue": "0x04003C07F7",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.ALL_READS.L3_HIT.HIT_OTHER_CORE_NO_FWD",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "Counts all data/code/rfo reads (demand & prefetch) that hit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded",
+        "BriefDescription": "hit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "Counts all demand & prefetch code reads that hit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all demand & prefetch code reads hit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x04003c0244",
+        "MSRValue": "0x04003C0244",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.ALL_CODE_RD.L3_HIT.HIT_OTHER_CORE_NO_FWD",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "Counts all demand & prefetch code reads that hit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded",
+        "BriefDescription": "Counts all demand & prefetch code reads hit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "Counts all demand & prefetch RFOs that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all demand & prefetch RFOs hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x10003c0122",
+        "MSRValue": "0x10003C0122",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.ALL_RFO.L3_HIT.HITM_OTHER_CORE",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "Counts all demand & prefetch RFOs that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded",
+        "BriefDescription": "Counts all demand & prefetch RFOs hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "Counts all demand & prefetch RFOs that hit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all demand & prefetch RFOs hit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x04003c0122",
+        "MSRValue": "0x04003C0122",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.ALL_RFO.L3_HIT.HIT_OTHER_CORE_NO_FWD",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "Counts all demand & prefetch RFOs that hit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded",
+        "BriefDescription": "Counts all demand & prefetch RFOs hit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "Counts all demand & prefetch data reads that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all demand & prefetch data reads hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x10003c0091",
+        "MSRValue": "0x10003C0091",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.ALL_DATA_RD.L3_HIT.HITM_OTHER_CORE",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "Counts all demand & prefetch data reads that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded",
+        "BriefDescription": "Counts all demand & prefetch data reads hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "Counts all demand & prefetch data reads that hit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all demand & prefetch data reads hit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x04003c0091",
+        "MSRValue": "0x04003C0091",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.ALL_DATA_RD.L3_HIT.HIT_OTHER_CORE_NO_FWD",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "Counts all demand & prefetch data reads that hit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded",
+        "BriefDescription": "Counts all demand & prefetch data reads hit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "Counts prefetch (that bring data to LLC only) code reads that hit in the L3 Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts prefetch (that bring data to LLC only) code reads hit in the L3",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x3f803c0200",
+        "MSRValue": "0x3F803C0200",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.PF_L3_CODE_RD.L3_HIT.ANY_RESPONSE",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "Counts prefetch (that bring data to LLC only) code reads that hit in the L3",
+        "BriefDescription": "Counts prefetch (that bring data to LLC only) code reads hit in the L3",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "Counts all prefetch (that bring data to LLC only) RFOs  that hit in the L3 Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all prefetch (that bring data to LLC only) RFOs hit in the L3",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x3f803c0100",
+        "MSRValue": "0x3F803C0100",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.PF_L3_RFO.L3_HIT.ANY_RESPONSE",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "Counts all prefetch (that bring data to LLC only) RFOs  that hit in the L3",
+        "BriefDescription": "Counts all prefetch (that bring data to LLC only) RFOs hit in the L3",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "Counts all prefetch (that bring data to LLC only) data reads that hit in the L3 Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all prefetch (that bring data to LLC only) data reads hit in the L3",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x3f803c0080",
+        "MSRValue": "0x3F803C0080",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.PF_L3_DATA_RD.L3_HIT.ANY_RESPONSE",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "Counts all prefetch (that bring data to LLC only) data reads that hit in the L3",
+        "BriefDescription": "Counts all prefetch (that bring data to LLC only) data reads hit in the L3",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "Counts all prefetch (that bring data to LLC only) code reads that hit in the L3 Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all prefetch (that bring data to LLC only) code reads hit in the L3",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x3f803c0040",
+        "MSRValue": "0x3F803C0040",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.PF_L2_CODE_RD.L3_HIT.ANY_RESPONSE",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "Counts all prefetch (that bring data to LLC only) code reads that hit in the L3",
+        "BriefDescription": "Counts all prefetch (that bring data to LLC only) code reads hit in the L3",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "Counts all prefetch (that bring data to L2) RFOs that hit in the L3 Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all prefetch (that bring data to L2) RFOs hit in the L3",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x3f803c0020",
+        "MSRValue": "0x3F803C0020",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.PF_L2_RFO.L3_HIT.ANY_RESPONSE",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "Counts all prefetch (that bring data to L2) RFOs that hit in the L3",
+        "BriefDescription": "Counts all prefetch (that bring data to L2) RFOs hit in the L3",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "Counts prefetch (that bring data to L2) data reads that hit in the L3 Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts prefetch (that bring data to L2) data reads hit in the L3",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x3f803c0010",
+        "MSRValue": "0x3F803C0010",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.PF_L2_DATA_RD.L3_HIT.ANY_RESPONSE",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "Counts prefetch (that bring data to L2) data reads that hit in the L3",
+        "BriefDescription": "Counts prefetch (that bring data to L2) data reads hit in the L3",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "Counts all demand code reads that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all demand code reads hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x10003c0004",
+        "MSRValue": "0x10003C0004",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_HIT.HITM_OTHER_CORE",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "Counts all demand code reads that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded",
+        "BriefDescription": "Counts all demand code reads hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "Counts all demand code reads that hit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all demand code reads hit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x04003c0004",
+        "MSRValue": "0x04003C0004",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_HIT.HIT_OTHER_CORE_NO_FWD",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "Counts all demand code reads that hit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded",
+        "BriefDescription": "Counts all demand code reads hit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "Counts all demand data writes (RFOs) that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all demand data writes (RFOs) hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x10003c0002",
+        "MSRValue": "0x10003C0002",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_HIT.HITM_OTHER_CORE",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "Counts all demand data writes (RFOs) that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded",
+        "BriefDescription": "Counts all demand data writes (RFOs) hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "Counts all demand data writes (RFOs) that hit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all demand data writes (RFOs) hit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x04003c0002",
+        "MSRValue": "0x04003C0002",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_HIT.HIT_OTHER_CORE_NO_FWD",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "Counts all demand data writes (RFOs) that hit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded",
+        "BriefDescription": "Counts all demand data writes (RFOs) hit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "Counts demand data reads that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts demand data reads hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x10003c0001",
+        "MSRValue": "0x10003C0001",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_HIT.HITM_OTHER_CORE",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "Counts demand data reads that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded",
+        "BriefDescription": "Counts demand data reads hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "Counts demand data reads that hit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts demand data reads hit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x04003c0001",
+        "MSRValue": "0x04003C0001",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_HIT.HIT_OTHER_CORE_NO_FWD",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "Counts demand data reads that hit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded",
+        "BriefDescription": "Counts demand data reads hit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     }
diff --git a/tools/perf/pmu-events/arch/x86/haswell/floating-point.json b/tools/perf/pmu-events/arch/x86/haswell/floating-point.json
index f9843e5a9b42..f5a3beaa19fc 100644
--- a/tools/perf/pmu-events/arch/x86/haswell/floating-point.json
+++ b/tools/perf/pmu-events/arch/x86/haswell/floating-point.json
@@ -1,22 +1,26 @@
 [
     {
+        "PEBS": "1",
+        "PublicDescription": "",
         "EventCode": "0xC1",
         "Counter": "0,1,2,3",
         "UMask": "0x8",
         "Errata": "HSD56, HSM57",
         "EventName": "OTHER_ASSISTS.AVX_TO_SSE",
         "SampleAfterValue": "100003",
-        "BriefDescription": "Number of transitions from AVX-256 to legacy SSE when penalty applicable.",
+        "BriefDescription": "Number of transitions from AVX-256 to legacy SSE when penalty applicable",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
+        "PEBS": "1",
+        "PublicDescription": "",
         "EventCode": "0xC1",
         "Counter": "0,1,2,3",
         "UMask": "0x10",
         "Errata": "HSD56, HSM57",
         "EventName": "OTHER_ASSISTS.SSE_TO_AVX",
         "SampleAfterValue": "100003",
-        "BriefDescription": "Number of transitions from SSE to AVX-256 when penalty applicable.",
+        "BriefDescription": "Number of transitions from legacy SSE to AVX-256 when penalty applicable",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
@@ -30,53 +34,58 @@
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "PublicDescription": "Number of X87 FP assists due to output values.",
+        "PEBS": "1",
+        "PublicDescription": "",
         "EventCode": "0xCA",
         "Counter": "0,1,2,3",
         "UMask": "0x2",
         "EventName": "FP_ASSIST.X87_OUTPUT",
         "SampleAfterValue": "100003",
-        "BriefDescription": "Number of X87 assists due to output value.",
+        "BriefDescription": "output - Numeric Overflow, Numeric Underflow, Inexact Result",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "PublicDescription": "Number of X87 FP assists due to input values.",
+        "PEBS": "1",
+        "PublicDescription": "",
         "EventCode": "0xCA",
         "Counter": "0,1,2,3",
         "UMask": "0x4",
         "EventName": "FP_ASSIST.X87_INPUT",
         "SampleAfterValue": "100003",
-        "BriefDescription": "Number of X87 assists due to input value.",
+        "BriefDescription": "input - Invalid Operation, Denormal Operand, SNaN Operand",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "PublicDescription": "Number of SIMD FP assists due to output values.",
+        "PEBS": "1",
+        "PublicDescription": "",
         "EventCode": "0xCA",
         "Counter": "0,1,2,3",
         "UMask": "0x8",
         "EventName": "FP_ASSIST.SIMD_OUTPUT",
         "SampleAfterValue": "100003",
-        "BriefDescription": "Number of SIMD FP assists due to Output values",
+        "BriefDescription": "SSE* FP micro-code assist when output value is invalid.",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "PublicDescription": "Number of SIMD FP assists due to input values.",
+        "PEBS": "1",
+        "PublicDescription": "",
         "EventCode": "0xCA",
         "Counter": "0,1,2,3",
         "UMask": "0x10",
         "EventName": "FP_ASSIST.SIMD_INPUT",
         "SampleAfterValue": "100003",
-        "BriefDescription": "Number of SIMD FP assists due to input values",
+        "BriefDescription": "Any input SSE* FP Assist",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "PublicDescription": "Cycles with any input/output SSE* or FP assists.",
+        "PEBS": "1",
+        "PublicDescription": "",
         "EventCode": "0xCA",
         "Counter": "0,1,2,3",
         "UMask": "0x1e",
         "EventName": "FP_ASSIST.ANY",
         "SampleAfterValue": "100003",
-        "BriefDescription": "Cycles with any input/output SSE or FP assist",
+        "BriefDescription": "Counts any FP_ASSIST umask was incrementing",
         "CounterMask": "1",
         "CounterHTOff": "0,1,2,3"
     }
diff --git a/tools/perf/pmu-events/arch/x86/haswell/hsw-metrics.json b/tools/perf/pmu-events/arch/x86/haswell/hsw-metrics.json
index 5ab5c78fe580..21b27488b621 100644
--- a/tools/perf/pmu-events/arch/x86/haswell/hsw-metrics.json
+++ b/tools/perf/pmu-events/arch/x86/haswell/hsw-metrics.json
@@ -1,158 +1,322 @@
 [
     {
-        "BriefDescription": "Instructions Per Cycle (per logical thread)",
+        "MetricExpr": "IDQ_UOPS_NOT_DELIVERED.CORE / (4 * cycles)",
+        "PublicDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend. Frontend denotes the first part of the processor core responsible to fetch operations that are executed later on by the Backend part. Within the Frontend; a branch predictor predicts the next address to fetch; cache-lines are fetched from the memory subsystem; parsed into instructions; and lastly decoded into micro-ops (uops). Ideally the Frontend can issue 4 uops every cycle to the Backend. Frontend Bound denotes unutilized issue-slots when there is no Backend stall; i.e. bubbles where Frontend delivered no uops while Backend could have accepted them. For example; stalls due to instruction-cache misses would be categorized under Frontend Bound.",
+        "BriefDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend",
+        "MetricGroup": "TopdownL1",
+        "MetricName": "Frontend_Bound"
+    },
+    {
+        "MetricExpr": "IDQ_UOPS_NOT_DELIVERED.CORE / (4 * (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )))",
+        "PublicDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend. Frontend denotes the first part of the processor core responsible to fetch operations that are executed later on by the Backend part. Within the Frontend; a branch predictor predicts the next address to fetch; cache-lines are fetched from the memory subsystem; parsed into instructions; and lastly decoded into micro-ops (uops). Ideally the Frontend can issue 4 uops every cycle to the Backend. Frontend Bound denotes unutilized issue-slots when there is no Backend stall; i.e. bubbles where Frontend delivered no uops while Backend could have accepted them. For example; stalls due to instruction-cache misses would be categorized under Frontend Bound. SMT version; use when SMT is enabled and measuring per logical CPU.",
+        "BriefDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend. SMT version; use when SMT is enabled and measuring per logical CPU.",
+        "MetricGroup": "TopdownL1_SMT",
+        "MetricName": "Frontend_Bound_SMT"
+    },
+    {
+        "MetricExpr": "( UOPS_ISSUED.ANY - UOPS_RETIRED.RETIRE_SLOTS + 4 * INT_MISC.RECOVERY_CYCLES ) / (4 * cycles)",
+        "PublicDescription": "This category represents fraction of slots wasted due to incorrect speculations. This include slots used to issue uops that do not eventually get retired and slots for which the issue-pipeline was blocked due to recovery from earlier incorrect speculation. For example; wasted work due to miss-predicted branches are categorized under Bad Speculation category. Incorrect data speculation followed by Memory Ordering Nukes is another example.",
+        "BriefDescription": "This category represents fraction of slots wasted due to incorrect speculations",
+        "MetricGroup": "TopdownL1",
+        "MetricName": "Bad_Speculation"
+    },
+    {
+        "MetricExpr": "( UOPS_ISSUED.ANY - UOPS_RETIRED.RETIRE_SLOTS + 4 * (( INT_MISC.RECOVERY_CYCLES_ANY / 2 )) ) / (4 * (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )))",
+        "PublicDescription": "This category represents fraction of slots wasted due to incorrect speculations. This include slots used to issue uops that do not eventually get retired and slots for which the issue-pipeline was blocked due to recovery from earlier incorrect speculation. For example; wasted work due to miss-predicted branches are categorized under Bad Speculation category. Incorrect data speculation followed by Memory Ordering Nukes is another example. SMT version; use when SMT is enabled and measuring per logical CPU.",
+        "BriefDescription": "This category represents fraction of slots wasted due to incorrect speculations. SMT version; use when SMT is enabled and measuring per logical CPU.",
+        "MetricGroup": "TopdownL1_SMT",
+        "MetricName": "Bad_Speculation_SMT"
+    },
+    {
+        "MetricExpr": "1 - ( (IDQ_UOPS_NOT_DELIVERED.CORE / (4 * cycles)) + (( UOPS_ISSUED.ANY - UOPS_RETIRED.RETIRE_SLOTS + 4 * INT_MISC.RECOVERY_CYCLES ) / (4 * cycles)) + (UOPS_RETIRED.RETIRE_SLOTS / (4 * cycles)) )",
+        "PublicDescription": "This category represents fraction of slots where no uops are being delivered due to a lack of required resources for accepting new uops in the Backend. Backend is the portion of the processor core where the out-of-order scheduler dispatches ready uops into their respective execution units; and once completed these uops get retired according to program order. For example; stalls due to data-cache misses or stalls due to the divider unit being overloaded are both categorized under Backend Bound. Backend Bound is further divided into two main categories: Memory Bound and Core Bound.",
+        "BriefDescription": "This category represents fraction of slots where no uops are being delivered due to a lack of required resources for accepting new uops in the Backend",
+        "MetricGroup": "TopdownL1",
+        "MetricName": "Backend_Bound"
+    },
+    {
+        "MetricExpr": "1 - ( (IDQ_UOPS_NOT_DELIVERED.CORE / (4 * (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )))) + (( UOPS_ISSUED.ANY - UOPS_RETIRED.RETIRE_SLOTS + 4 * (( INT_MISC.RECOVERY_CYCLES_ANY / 2 )) ) / (4 * (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )))) + (UOPS_RETIRED.RETIRE_SLOTS / (4 * (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )))) )",
+        "PublicDescription": "This category represents fraction of slots where no uops are being delivered due to a lack of required resources for accepting new uops in the Backend. Backend is the portion of the processor core where the out-of-order scheduler dispatches ready uops into their respective execution units; and once completed these uops get retired according to program order. For example; stalls due to data-cache misses or stalls due to the divider unit being overloaded are both categorized under Backend Bound. Backend Bound is further divided into two main categories: Memory Bound and Core Bound. SMT version; use when SMT is enabled and measuring per logical CPU.",
+        "BriefDescription": "This category represents fraction of slots where no uops are being delivered due to a lack of required resources for accepting new uops in the Backend. SMT version; use when SMT is enabled and measuring per logical CPU.",
+        "MetricGroup": "TopdownL1_SMT",
+        "MetricName": "Backend_Bound_SMT"
+    },
+    {
+        "MetricExpr": "UOPS_RETIRED.RETIRE_SLOTS / (4 * cycles)",
+        "PublicDescription": "This category represents fraction of slots utilized by useful work i.e. issued uops that eventually get retired. Ideally; all pipeline slots would be attributed to the Retiring category.  Retiring of 100% would indicate the maximum 4 uops retired per cycle has been achieved.  Maximizing Retiring typically increases the Instruction-Per-Cycle metric. Note that a high Retiring value does not necessary mean there is no room for more performance.  For example; Microcode assists are categorized under Retiring. They hurt performance and can often be avoided. ",
+        "BriefDescription": "This category represents fraction of slots utilized by useful work i.e. issued uops that eventually get retired",
+        "MetricGroup": "TopdownL1",
+        "MetricName": "Retiring"
+    },
+    {
+        "MetricExpr": "UOPS_RETIRED.RETIRE_SLOTS / (4 * (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )))",
+        "PublicDescription": "This category represents fraction of slots utilized by useful work i.e. issued uops that eventually get retired. Ideally; all pipeline slots would be attributed to the Retiring category.  Retiring of 100% would indicate the maximum 4 uops retired per cycle has been achieved.  Maximizing Retiring typically increases the Instruction-Per-Cycle metric. Note that a high Retiring value does not necessary mean there is no room for more performance.  For example; Microcode assists are categorized under Retiring. They hurt performance and can often be avoided. SMT version; use when SMT is enabled and measuring per logical CPU.",
+        "BriefDescription": "This category represents fraction of slots utilized by useful work i.e. issued uops that eventually get retired. SMT version; use when SMT is enabled and measuring per logical CPU.",
+        "MetricGroup": "TopdownL1_SMT",
+        "MetricName": "Retiring_SMT"
+    },
+    {
         "MetricExpr": "INST_RETIRED.ANY / CPU_CLK_UNHALTED.THREAD",
+        "BriefDescription": "Instructions Per Cycle (per logical thread)",
         "MetricGroup": "TopDownL1",
         "MetricName": "IPC"
     },
     {
-        "BriefDescription": "Uops Per Instruction",
         "MetricExpr": "UOPS_RETIRED.RETIRE_SLOTS / INST_RETIRED.ANY",
-        "MetricGroup": "Pipeline",
+        "BriefDescription": "Uops Per Instruction",
+        "MetricGroup": "Pipeline;Retiring",
         "MetricName": "UPI"
     },
     {
-        "BriefDescription": "Rough Estimation of fraction of fetched lines bytes that were likely consumed by program instructions",
+        "MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.NEAR_TAKEN",
+        "BriefDescription": "Instruction per taken branch",
+        "MetricGroup": "Branches;PGO",
+        "MetricName": "IpTB"
+    },
+    {
+        "MetricExpr": "BR_INST_RETIRED.ALL_BRANCHES / BR_INST_RETIRED.NEAR_TAKEN",
+        "BriefDescription": "Branch instructions per taken branch. ",
+        "MetricGroup": "Branches;PGO",
+        "MetricName": "BpTB"
+    },
+    {
         "MetricExpr": "min( 1 , IDQ.MITE_UOPS / ( (UOPS_RETIRED.RETIRE_SLOTS / INST_RETIRED.ANY) * 16 * ( ICACHE.HIT + ICACHE.MISSES ) / 4.0 ) )",
-        "MetricGroup": "Frontend",
+        "BriefDescription": "Rough Estimation of fraction of fetched lines bytes that were likely (includes speculatively fetches) consumed by program instructions",
+        "MetricGroup": "PGO",
         "MetricName": "IFetch_Line_Utilization"
     },
     {
-        "BriefDescription": "Fraction of Uops delivered by the DSB (aka Decoded Icache; or Uop Cache)",
-        "MetricExpr": "IDQ.DSB_UOPS / ( IDQ.DSB_UOPS + LSD.UOPS + IDQ.MITE_UOPS + IDQ.MS_UOPS )",
-        "MetricGroup": "DSB; Frontend_Bandwidth",
+        "MetricExpr": "IDQ.DSB_UOPS / (( IDQ.DSB_UOPS + LSD.UOPS + IDQ.MITE_UOPS + IDQ.MS_UOPS ) )",
+        "BriefDescription": "Fraction of Uops delivered by the DSB (aka Decoded ICache; or Uop Cache)",
+        "MetricGroup": "DSB;Frontend_Bandwidth",
         "MetricName": "DSB_Coverage"
     },
     {
-        "BriefDescription": "Cycles Per Instruction (threaded)",
         "MetricExpr": "1 / (INST_RETIRED.ANY / cycles)",
+        "BriefDescription": "Cycles Per Instruction (threaded)",
         "MetricGroup": "Pipeline;Summary",
         "MetricName": "CPI"
     },
     {
-        "BriefDescription": "Per-thread actual clocks when the logical processor is active. This is called 'Clockticks' in VTune.",
         "MetricExpr": "CPU_CLK_UNHALTED.THREAD",
+        "BriefDescription": "Per-thread actual clocks when the logical processor is active.",
         "MetricGroup": "Summary",
         "MetricName": "CLKS"
     },
     {
-        "BriefDescription": "Total issue-pipeline slots",
-        "MetricExpr": "4*(( CPU_CLK_UNHALTED.THREAD_ANY / 2 ) if #SMT_on else cycles)",
+        "MetricExpr": "4 * cycles",
+        "BriefDescription": "Total issue-pipeline slots (per core)",
         "MetricGroup": "TopDownL1",
         "MetricName": "SLOTS"
     },
     {
-        "BriefDescription": "Total number of retired Instructions",
+        "MetricExpr": "4 * (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) ))",
+        "BriefDescription": "Total issue-pipeline slots (per core)",
+        "MetricGroup": "TopDownL1_SMT",
+        "MetricName": "SLOTS_SMT"
+    },
+    {
+        "MetricExpr": "INST_RETIRED.ANY / MEM_UOPS_RETIRED.ALL_LOADS",
+        "BriefDescription": "Instructions per Load (lower number means loads are more frequent)",
+        "MetricGroup": "Instruction_Type;L1_Bound",
+        "MetricName": "IpL"
+    },
+    {
+        "MetricExpr": "INST_RETIRED.ANY / MEM_UOPS_RETIRED.ALL_STORES",
+        "BriefDescription": "Instructions per Store",
+        "MetricGroup": "Instruction_Type;Store_Bound",
+        "MetricName": "IpS"
+    },
+    {
+        "MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.ALL_BRANCHES",
+        "BriefDescription": "Instructions per Branch",
+        "MetricGroup": "Branches;Instruction_Type;Port_5;Port_6",
+        "MetricName": "IpB"
+    },
+    {
+        "MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.NEAR_CALL",
+        "BriefDescription": "Instruction per (near) call",
+        "MetricGroup": "Branches",
+        "MetricName": "IpCall"
+    },
+    {
         "MetricExpr": "INST_RETIRED.ANY",
+        "BriefDescription": "Total number of retired Instructions",
         "MetricGroup": "Summary",
         "MetricName": "Instructions"
     },
     {
+        "MetricExpr": "INST_RETIRED.ANY / cycles",
         "BriefDescription": "Instructions Per Cycle (per physical core)",
-        "MetricExpr": "INST_RETIRED.ANY / (( CPU_CLK_UNHALTED.THREAD_ANY / 2 ) if #SMT_on else cycles)",
         "MetricGroup": "SMT",
         "MetricName": "CoreIPC"
     },
     {
+        "MetricExpr": "INST_RETIRED.ANY / (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) ))",
+        "BriefDescription": "Instructions Per Cycle (per physical core)",
+        "MetricGroup": "SMT",
+        "MetricName": "CoreIPC_SMT"
+    },
+    {
+        "MetricExpr": "( UOPS_EXECUTED.CORE / 2 / (( cpu@UOPS_EXECUTED.CORE\\,cmask\\=1@ / 2 ) if #SMT_on else cpu@UOPS_EXECUTED.CORE\\,cmask\\=1@) ) if #SMT_on else UOPS_EXECUTED.CORE / (( cpu@UOPS_EXECUTED.CORE\\,cmask\\=1@ / 2 ) if #SMT_on else cpu@UOPS_EXECUTED.CORE\\,cmask\\=1@)",
         "BriefDescription": "Instruction-Level-Parallelism (average number of uops executed when there is at least 1 uop executed)",
-        "MetricExpr": "( UOPS_EXECUTED.CORE / 2 / (( cpu@UOPS_EXECUTED.CORE\\,cmask\\=1@ / 2) if #SMT_on else cpu@UOPS_EXECUTED.CORE\\,cmask\\=1@) ) if #SMT_on else UOPS_EXECUTED.CORE / (( cpu@UOPS_EXECUTED.CORE\\,cmask\\=1@ / 2) if #SMT_on else cpu@UOPS_EXECUTED.CORE\\,cmask\\=1@)",
         "MetricGroup": "Pipeline;Ports_Utilization",
         "MetricName": "ILP"
     },
     {
-        "BriefDescription": "Average Branch Address Clear Cost (fraction of cycles)",
-        "MetricExpr": "2* (( RS_EVENTS.EMPTY_CYCLES - ICACHE.IFDATA_STALL  - (( 14 * ITLB_MISSES.STLB_HIT + ITLB_MISSES.WALK_DURATION )) ) / RS_EVENTS.EMPTY_END)",
-        "MetricGroup": "Unknown_Branches",
-        "MetricName": "BAClear_Cost"
+        "MetricExpr": "INST_RETIRED.ANY / BR_MISP_RETIRED.ALL_BRANCHES",
+        "BriefDescription": "Number of Instructions per non-speculative Branch Misprediction (JEClear)",
+        "MetricGroup": "Branch_Mispredicts",
+        "MetricName": "IpMispredict"
     },
     {
+        "MetricExpr": "( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )",
         "BriefDescription": "Core actual clocks when any thread is active on the physical core",
-        "MetricExpr": "( CPU_CLK_UNHALTED.THREAD_ANY / 2 ) if #SMT_on else CPU_CLK_UNHALTED.THREAD",
         "MetricGroup": "SMT",
         "MetricName": "CORE_CLKS"
     },
     {
-        "BriefDescription": "Actual Average Latency for L1 data-cache miss demand loads",
         "MetricExpr": "L1D_PEND_MISS.PENDING / ( MEM_LOAD_UOPS_RETIRED.L1_MISS + mem_load_uops_retired.hit_lfb )",
+        "BriefDescription": "Actual Average Latency for L1 data-cache miss demand loads (in core cycles)",
         "MetricGroup": "Memory_Bound;Memory_Lat",
         "MetricName": "Load_Miss_Real_Latency"
     },
     {
-        "BriefDescription": "Memory-Level-Parallelism (average number of L1 miss demand load when there is at least 1 such miss)",
-        "MetricExpr": "L1D_PEND_MISS.PENDING / (( cpu@l1d_pend_miss.pending_cycles\\,any\\=1@ / 2) if #SMT_on else L1D_PEND_MISS.PENDING_CYCLES)",
+        "MetricExpr": "L1D_PEND_MISS.PENDING / L1D_PEND_MISS.PENDING_CYCLES",
+        "BriefDescription": "Memory-Level-Parallelism (average number of L1 miss demand load when there is at least one such miss. Per-thread)",
         "MetricGroup": "Memory_Bound;Memory_BW",
         "MetricName": "MLP"
     },
     {
+        "MetricExpr": "( ITLB_MISSES.WALK_DURATION + DTLB_LOAD_MISSES.WALK_DURATION + DTLB_STORE_MISSES.WALK_DURATION ) / cycles",
         "BriefDescription": "Utilization of the core's Page Walker(s) serving STLB misses triggered by instruction/Load/Store accesses",
-        "MetricExpr": "( ITLB_MISSES.WALK_DURATION + DTLB_LOAD_MISSES.WALK_DURATION + DTLB_STORE_MISSES.WALK_DURATION ) / (( CPU_CLK_UNHALTED.THREAD_ANY / 2 ) if #SMT_on else cycles)",
         "MetricGroup": "TLB",
         "MetricName": "Page_Walks_Utilization"
     },
     {
-        "BriefDescription": "Average CPU Utilization",
+        "MetricExpr": "( ITLB_MISSES.WALK_DURATION + DTLB_LOAD_MISSES.WALK_DURATION + DTLB_STORE_MISSES.WALK_DURATION ) / (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) ))",
+        "BriefDescription": "Utilization of the core's Page Walker(s) serving STLB misses triggered by instruction/Load/Store accesses",
+        "MetricGroup": "TLB_SMT",
+        "MetricName": "Page_Walks_Utilization_SMT"
+    },
+    {
+        "MetricExpr": "64 * L1D.REPLACEMENT / 1000000000 / duration_time",
+        "BriefDescription": "Average data fill bandwidth to the L1 data cache [GB / sec]",
+        "MetricGroup": "Memory_BW",
+        "MetricName": "L1D_Cache_Fill_BW"
+    },
+    {
+        "MetricExpr": "64 * L2_LINES_IN.ALL / 1000000000 / duration_time",
+        "BriefDescription": "Average data fill bandwidth to the L2 cache [GB / sec]",
+        "MetricGroup": "Memory_BW",
+        "MetricName": "L2_Cache_Fill_BW"
+    },
+    {
+        "MetricExpr": "64 * LONGEST_LAT_CACHE.MISS / 1000000000 / duration_time",
+        "BriefDescription": "Average per-core data fill bandwidth to the L3 cache [GB / sec]",
+        "MetricGroup": "Memory_BW",
+        "MetricName": "L3_Cache_Fill_BW"
+    },
+    {
+        "MetricExpr": "1000 * MEM_LOAD_UOPS_RETIRED.L1_MISS / INST_RETIRED.ANY",
+        "BriefDescription": "L1 cache true misses per kilo instruction for retired demand loads",
+        "MetricGroup": "Cache_Misses;",
+        "MetricName": "L1MPKI"
+    },
+    {
+        "MetricExpr": "1000 * MEM_LOAD_UOPS_RETIRED.L2_MISS / INST_RETIRED.ANY",
+        "BriefDescription": "L2 cache true misses per kilo instruction for retired demand loads",
+        "MetricGroup": "Cache_Misses;",
+        "MetricName": "L2MPKI"
+    },
+    {
+        "MetricExpr": "1000 * MEM_LOAD_UOPS_RETIRED.L2_MISS / INST_RETIRED.ANY",
+        "BriefDescription": "L2 cache misses per kilo instruction for all request types (including speculative)",
+        "MetricGroup": "Cache_Misses;",
+        "MetricName": "L2MPKI_All"
+    },
+    {
+        "MetricExpr": "1000 * MEM_LOAD_UOPS_RETIRED.L2_MISS / INST_RETIRED.ANY",
+        "BriefDescription": "L2 cache hits per kilo instruction for all request types (including speculative)",
+        "MetricGroup": "Cache_Misses;",
+        "MetricName": "L2HPKI_All"
+    },
+    {
+        "MetricExpr": "1000 * MEM_LOAD_UOPS_RETIRED.L3_MISS / INST_RETIRED.ANY",
+        "BriefDescription": "L3 cache true misses per kilo instruction for retired demand loads",
+        "MetricGroup": "Cache_Misses;",
+        "MetricName": "L3MPKI"
+    },
+    {
         "MetricExpr": "CPU_CLK_UNHALTED.REF_TSC / msr@tsc@",
+        "BriefDescription": "Average CPU Utilization",
         "MetricGroup": "Summary",
         "MetricName": "CPU_Utilization"
     },
     {
-        "BriefDescription": "Average Frequency Utilization relative nominal frequency",
         "MetricExpr": "CPU_CLK_UNHALTED.THREAD / CPU_CLK_UNHALTED.REF_TSC",
+        "BriefDescription": "Average Frequency Utilization relative nominal frequency",
         "MetricGroup": "Power",
         "MetricName": "Turbo_Utilization"
     },
     {
-        "BriefDescription": "Fraction of cycles where both hardware threads were active",
         "MetricExpr": "1 - CPU_CLK_THREAD_UNHALTED.ONE_THREAD_ACTIVE / ( CPU_CLK_THREAD_UNHALTED.REF_XCLK_ANY / 2 ) if #SMT_on else 0",
+        "BriefDescription": "Fraction of cycles where both hardware threads were active",
         "MetricGroup": "SMT;Summary",
         "MetricName": "SMT_2T_Utilization"
     },
     {
-        "BriefDescription": "Fraction of cycles spent in Kernel mode",
         "MetricExpr": "CPU_CLK_UNHALTED.REF_TSC:u / CPU_CLK_UNHALTED.REF_TSC",
+        "BriefDescription": "Fraction of cycles spent in Kernel mode",
         "MetricGroup": "Summary",
         "MetricName": "Kernel_Utilization"
     },
     {
-        "BriefDescription": "C3 residency percent per core",
+        "MetricExpr": "64 * ( arb@event\\=0x81\\,umask\\=0x1@ + arb@event\\=0x84\\,umask\\=0x1@ ) / 1000000 / duration_time / 1000",
+        "BriefDescription": "Average external Memory Bandwidth Use for reads and writes [GB / sec]",
+        "MetricGroup": "Memory_BW",
+        "MetricName": "DRAM_BW_Use"
+    },
+    {
         "MetricExpr": "(cstate_core@c3\\-residency@ / msr@tsc@) * 100",
         "MetricGroup": "Power",
+        "BriefDescription": "C3 residency percent per core",
         "MetricName": "C3_Core_Residency"
     },
     {
-        "BriefDescription": "C6 residency percent per core",
         "MetricExpr": "(cstate_core@c6\\-residency@ / msr@tsc@) * 100",
         "MetricGroup": "Power",
+        "BriefDescription": "C6 residency percent per core",
         "MetricName": "C6_Core_Residency"
     },
     {
-        "BriefDescription": "C7 residency percent per core",
         "MetricExpr": "(cstate_core@c7\\-residency@ / msr@tsc@) * 100",
         "MetricGroup": "Power",
+        "BriefDescription": "C7 residency percent per core",
         "MetricName": "C7_Core_Residency"
     },
     {
-        "BriefDescription": "C2 residency percent per package",
         "MetricExpr": "(cstate_pkg@c2\\-residency@ / msr@tsc@) * 100",
         "MetricGroup": "Power",
+        "BriefDescription": "C2 residency percent per package",
         "MetricName": "C2_Pkg_Residency"
     },
     {
-        "BriefDescription": "C3 residency percent per package",
         "MetricExpr": "(cstate_pkg@c3\\-residency@ / msr@tsc@) * 100",
         "MetricGroup": "Power",
+        "BriefDescription": "C3 residency percent per package",
         "MetricName": "C3_Pkg_Residency"
     },
     {
-        "BriefDescription": "C6 residency percent per package",
         "MetricExpr": "(cstate_pkg@c6\\-residency@ / msr@tsc@) * 100",
         "MetricGroup": "Power",
+        "BriefDescription": "C6 residency percent per package",
         "MetricName": "C6_Pkg_Residency"
     },
     {
-        "BriefDescription": "C7 residency percent per package",
         "MetricExpr": "(cstate_pkg@c7\\-residency@ / msr@tsc@) * 100",
         "MetricGroup": "Power",
+        "BriefDescription": "C7 residency percent per package",
         "MetricName": "C7_Pkg_Residency"
     }
 ]
diff --git a/tools/perf/pmu-events/arch/x86/haswell/memory.json b/tools/perf/pmu-events/arch/x86/haswell/memory.json
index e5f9fa6655b3..ef13ed88e2ea 100644
--- a/tools/perf/pmu-events/arch/x86/haswell/memory.json
+++ b/tools/perf/pmu-events/arch/x86/haswell/memory.json
@@ -298,7 +298,7 @@
         "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_4",
         "MSRIndex": "0x3F6",
         "SampleAfterValue": "100003",
-        "BriefDescription": "Loads with latency value being above 4.",
+        "BriefDescription": "Randomly selected loads with latency value being above 4.",
         "TakenAlone": "1",
         "CounterHTOff": "3"
     },
@@ -312,7 +312,7 @@
         "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_8",
         "MSRIndex": "0x3F6",
         "SampleAfterValue": "50021",
-        "BriefDescription": "Loads with latency value being above 8.",
+        "BriefDescription": "Randomly selected loads with latency value being above 8.",
         "TakenAlone": "1",
         "CounterHTOff": "3"
     },
@@ -326,7 +326,7 @@
         "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_16",
         "MSRIndex": "0x3F6",
         "SampleAfterValue": "20011",
-        "BriefDescription": "Loads with latency value being above 16.",
+        "BriefDescription": "Randomly selected loads with latency value being above 16.",
         "TakenAlone": "1",
         "CounterHTOff": "3"
     },
@@ -340,7 +340,7 @@
         "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_32",
         "MSRIndex": "0x3F6",
         "SampleAfterValue": "100003",
-        "BriefDescription": "Loads with latency value being above 32.",
+        "BriefDescription": "Randomly selected loads with latency value being above 32.",
         "TakenAlone": "1",
         "CounterHTOff": "3"
     },
@@ -354,7 +354,7 @@
         "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_64",
         "MSRIndex": "0x3F6",
         "SampleAfterValue": "2003",
-        "BriefDescription": "Loads with latency value being above 64.",
+        "BriefDescription": "Randomly selected loads with latency value being above 64.",
         "TakenAlone": "1",
         "CounterHTOff": "3"
     },
@@ -368,7 +368,7 @@
         "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_128",
         "MSRIndex": "0x3F6",
         "SampleAfterValue": "1009",
-        "BriefDescription": "Loads with latency value being above 128.",
+        "BriefDescription": "Randomly selected loads with latency value being above 128.",
         "TakenAlone": "1",
         "CounterHTOff": "3"
     },
@@ -382,7 +382,7 @@
         "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_256",
         "MSRIndex": "0x3F6",
         "SampleAfterValue": "503",
-        "BriefDescription": "Loads with latency value being above 256.",
+        "BriefDescription": "Randomly selected loads with latency value being above 256.",
         "TakenAlone": "1",
         "CounterHTOff": "3"
     },
@@ -396,280 +396,280 @@
         "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_512",
         "MSRIndex": "0x3F6",
         "SampleAfterValue": "101",
-        "BriefDescription": "Loads with latency value being above 512.",
+        "BriefDescription": "Randomly selected loads with latency value being above 512.",
         "TakenAlone": "1",
         "CounterHTOff": "3"
     },
     {
-        "PublicDescription": "Counts all requests that miss in the L3 Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all requests miss in the L3",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x3fffc08fff",
+        "MSRValue": "0x3FFFC08FFF",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.ALL_REQUESTS.L3_MISS.ANY_RESPONSE",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "Counts all requests that miss in the L3",
+        "BriefDescription": "Counts all requests miss in the L3",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "Counts all data/code/rfo reads (demand & prefetch) that miss the L3 and the data is returned from local dram Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "miss the L3 and the data is returned from local dram",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x01004007f7",
+        "MSRValue": "0x01004007F7",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.ALL_READS.L3_MISS.LOCAL_DRAM",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "Counts all data/code/rfo reads (demand & prefetch) that miss the L3 and the data is returned from local dram",
+        "BriefDescription": "miss the L3 and the data is returned from local dram",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "Counts all data/code/rfo reads (demand & prefetch) that miss in the L3 Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "miss in the L3",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x3fffc007f7",
+        "MSRValue": "0x3FFFC007F7",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.ALL_READS.L3_MISS.ANY_RESPONSE",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "Counts all data/code/rfo reads (demand & prefetch) that miss in the L3",
+        "BriefDescription": "miss in the L3",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "Counts all demand & prefetch code reads that miss the L3 and the data is returned from local dram Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all demand & prefetch code reads miss the L3 and the data is returned from local dram",
         "EventCode": "0xB7, 0xBB",
         "MSRValue": "0x0100400244",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.ALL_CODE_RD.L3_MISS.LOCAL_DRAM",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "Counts all demand & prefetch code reads that miss the L3 and the data is returned from local dram",
+        "BriefDescription": "Counts all demand & prefetch code reads miss the L3 and the data is returned from local dram",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "Counts all demand & prefetch code reads that miss in the L3 Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all demand & prefetch code reads miss in the L3",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x3fffc00244",
+        "MSRValue": "0x3FFFC00244",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.ALL_CODE_RD.L3_MISS.ANY_RESPONSE",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "Counts all demand & prefetch code reads that miss in the L3",
+        "BriefDescription": "Counts all demand & prefetch code reads miss in the L3",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "Counts all demand & prefetch RFOs that miss the L3 and the data is returned from local dram Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all demand & prefetch RFOs miss the L3 and the data is returned from local dram",
         "EventCode": "0xB7, 0xBB",
         "MSRValue": "0x0100400122",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.ALL_RFO.L3_MISS.LOCAL_DRAM",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "Counts all demand & prefetch RFOs that miss the L3 and the data is returned from local dram",
+        "BriefDescription": "Counts all demand & prefetch RFOs miss the L3 and the data is returned from local dram",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "Counts all demand & prefetch RFOs that miss in the L3 Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all demand & prefetch RFOs miss in the L3",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x3fffc00122",
+        "MSRValue": "0x3FFFC00122",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.ALL_RFO.L3_MISS.ANY_RESPONSE",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "Counts all demand & prefetch RFOs that miss in the L3",
+        "BriefDescription": "Counts all demand & prefetch RFOs miss in the L3",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "Counts all demand & prefetch data reads that miss the L3 and the data is returned from local dram Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all demand & prefetch data reads miss the L3 and the data is returned from local dram",
         "EventCode": "0xB7, 0xBB",
         "MSRValue": "0x0100400091",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.ALL_DATA_RD.L3_MISS.LOCAL_DRAM",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "Counts all demand & prefetch data reads that miss the L3 and the data is returned from local dram",
+        "BriefDescription": "Counts all demand & prefetch data reads miss the L3 and the data is returned from local dram",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "Counts all demand & prefetch data reads that miss in the L3 Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all demand & prefetch data reads miss in the L3",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x3fffc00091",
+        "MSRValue": "0x3FFFC00091",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.ALL_DATA_RD.L3_MISS.ANY_RESPONSE",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "Counts all demand & prefetch data reads that miss in the L3",
+        "BriefDescription": "Counts all demand & prefetch data reads miss in the L3",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "Counts prefetch (that bring data to LLC only) code reads that miss in the L3 Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts prefetch (that bring data to LLC only) code reads miss in the L3",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x3fffc00200",
+        "MSRValue": "0x3FFFC00200",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.PF_L3_CODE_RD.L3_MISS.ANY_RESPONSE",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "Counts prefetch (that bring data to LLC only) code reads that miss in the L3",
+        "BriefDescription": "Counts prefetch (that bring data to LLC only) code reads miss in the L3",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "Counts all prefetch (that bring data to LLC only) RFOs  that miss in the L3 Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all prefetch (that bring data to LLC only) RFOs miss in the L3",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x3fffc00100",
+        "MSRValue": "0x3FFFC00100",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.PF_L3_RFO.L3_MISS.ANY_RESPONSE",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "Counts all prefetch (that bring data to LLC only) RFOs  that miss in the L3",
+        "BriefDescription": "Counts all prefetch (that bring data to LLC only) RFOs miss in the L3",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "Counts all prefetch (that bring data to LLC only) data reads that miss in the L3 Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all prefetch (that bring data to LLC only) data reads miss in the L3",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x3fffc00080",
+        "MSRValue": "0x3FFFC00080",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.PF_L3_DATA_RD.L3_MISS.ANY_RESPONSE",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "Counts all prefetch (that bring data to LLC only) data reads that miss in the L3",
+        "BriefDescription": "Counts all prefetch (that bring data to LLC only) data reads miss in the L3",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "Counts all prefetch (that bring data to LLC only) code reads that miss in the L3 Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all prefetch (that bring data to LLC only) code reads miss in the L3",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x3fffc00040",
+        "MSRValue": "0x3FFFC00040",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.PF_L2_CODE_RD.L3_MISS.ANY_RESPONSE",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "Counts all prefetch (that bring data to LLC only) code reads that miss in the L3",
+        "BriefDescription": "Counts all prefetch (that bring data to LLC only) code reads miss in the L3",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "Counts all prefetch (that bring data to L2) RFOs that miss in the L3 Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all prefetch (that bring data to L2) RFOs miss in the L3",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x3fffc00020",
+        "MSRValue": "0x3FFFC00020",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.PF_L2_RFO.L3_MISS.ANY_RESPONSE",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "Counts all prefetch (that bring data to L2) RFOs that miss in the L3",
+        "BriefDescription": "Counts all prefetch (that bring data to L2) RFOs miss in the L3",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "Counts prefetch (that bring data to L2) data reads that miss in the L3 Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts prefetch (that bring data to L2) data reads miss in the L3",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x3fffc00010",
+        "MSRValue": "0x3FFFC00010",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.PF_L2_DATA_RD.L3_MISS.ANY_RESPONSE",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "Counts prefetch (that bring data to L2) data reads that miss in the L3",
+        "BriefDescription": "Counts prefetch (that bring data to L2) data reads miss in the L3",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "Counts all demand code reads that miss the L3 and the data is returned from local dram Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all demand code reads miss the L3 and the data is returned from local dram",
         "EventCode": "0xB7, 0xBB",
         "MSRValue": "0x0100400004",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_MISS.LOCAL_DRAM",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "Counts all demand code reads that miss the L3 and the data is returned from local dram",
+        "BriefDescription": "Counts all demand code reads miss the L3 and the data is returned from local dram",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "Counts all demand code reads that miss in the L3 Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all demand code reads miss in the L3",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x3fffc00004",
+        "MSRValue": "0x3FFFC00004",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_MISS.ANY_RESPONSE",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "Counts all demand code reads that miss in the L3",
+        "BriefDescription": "Counts all demand code reads miss in the L3",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "Counts all demand data writes (RFOs) that miss the L3 and the data is returned from local dram Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all demand data writes (RFOs) miss the L3 and the data is returned from local dram",
         "EventCode": "0xB7, 0xBB",
         "MSRValue": "0x0100400002",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_MISS.LOCAL_DRAM",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "Counts all demand data writes (RFOs) that miss the L3 and the data is returned from local dram",
+        "BriefDescription": "Counts all demand data writes (RFOs) miss the L3 and the data is returned from local dram",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "Counts all demand data writes (RFOs) that miss in the L3 Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all demand data writes (RFOs) miss in the L3",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x3fffc00002",
+        "MSRValue": "0x3FFFC00002",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_MISS.ANY_RESPONSE",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "Counts all demand data writes (RFOs) that miss in the L3",
+        "BriefDescription": "Counts all demand data writes (RFOs) miss in the L3",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "Counts demand data reads that miss the L3 and the data is returned from local dram Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts demand data reads miss the L3 and the data is returned from local dram",
         "EventCode": "0xB7, 0xBB",
         "MSRValue": "0x0100400001",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_MISS.LOCAL_DRAM",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "Counts demand data reads that miss the L3 and the data is returned from local dram",
+        "BriefDescription": "Counts demand data reads miss the L3 and the data is returned from local dram",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "Counts demand data reads that miss in the L3 Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts demand data reads miss in the L3",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x3fffc00001",
+        "MSRValue": "0x3FFFC00001",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_MISS.ANY_RESPONSE",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "Counts demand data reads that miss in the L3",
+        "BriefDescription": "Counts demand data reads miss in the L3",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     }
diff --git a/tools/perf/pmu-events/arch/x86/haswell/pipeline.json b/tools/perf/pmu-events/arch/x86/haswell/pipeline.json
index a4dcfce4a512..734d3873729e 100644
--- a/tools/perf/pmu-events/arch/x86/haswell/pipeline.json
+++ b/tools/perf/pmu-events/arch/x86/haswell/pipeline.json
@@ -1,7 +1,6 @@
 [
     {
         "PublicDescription": "This event counts the number of instructions retired from execution. For instructions that consist of multiple micro-ops, this event counts the retirement of the last micro-op of the instruction. Counting continues during hardware interrupts, traps, and inside interrupt handlers. INST_RETIRED.ANY is counted by a designated fixed counter, leaving the programmable counters available for other events. Faulting executions of GETSEC/VM entry/VM Exit/MWait will not count as retired instructions.",
-        "EventCode": "0x00",
         "Counter": "Fixed counter 0",
         "UMask": "0x1",
         "Errata": "HSD140, HSD143",
@@ -12,7 +11,6 @@
     },
     {
         "PublicDescription": "This event counts the number of thread cycles while the thread is not in a halt state. The thread enters the halt state when it is running the HLT instruction. The core frequency may change from time to time due to power or thermal throttling.",
-        "EventCode": "0x00",
         "Counter": "Fixed counter 1",
         "UMask": "0x2",
         "EventName": "CPU_CLK_UNHALTED.THREAD",
@@ -21,7 +19,6 @@
         "CounterHTOff": "Fixed counter 1"
     },
     {
-        "EventCode": "0x00",
         "Counter": "Fixed counter 1",
         "UMask": "0x2",
         "AnyThread": "1",
@@ -32,7 +29,6 @@
     },
     {
         "PublicDescription": "This event counts the number of reference cycles when the core is not in a halt state. The core enters the halt state when it is running the HLT instruction or the MWAIT instruction. This event is not affected by core frequency changes (for example, P states, TM2 transitions) but has the same incrementing frequency as the time stamp counter. This event can approximate elapsed time while the core was not in a halt state.",
-        "EventCode": "0x00",
         "Counter": "Fixed counter 2",
         "UMask": "0x3",
         "EventName": "CPU_CLK_UNHALTED.REF_TSC",
@@ -1071,7 +1067,8 @@
         "CounterHTOff": "1"
     },
     {
-        "PublicDescription": "This is a non-precise version (that is, does not use PEBS) of the event that counts FP operations retired. For X87 FP operations that have no exceptions counting also includes flows that have several X87, or flows that use X87 uops in the exception handling.",
+        "PEBS": "1",
+        "PublicDescription": "This is a precise version (that is, uses PEBS) of the event that counts FP operations retired. For X87 FP operations that have no exceptions counting also includes flows that have several X87, or flows that use X87 uops in the exception handling.",
         "EventCode": "0xC0",
         "Counter": "0,1,2,3",
         "UMask": "0x2",
@@ -1081,13 +1078,13 @@
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "PublicDescription": "Number of microcode assists invoked by HW upon uop writeback.",
+        "PEBS": "1",
+        "PublicDescription": "",
         "EventCode": "0xC1",
         "Counter": "0,1,2,3",
         "UMask": "0x40",
         "EventName": "OTHER_ASSISTS.ANY_WB_ASSIST",
         "SampleAfterValue": "100003",
-        "BriefDescription": "Number of times any microcode assist is invoked by HW upon uop writeback.",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
@@ -1102,28 +1099,34 @@
         "Data_LA": "1"
     },
     {
+        "PEBS": "1",
+        "PublicDescription": "",
         "EventCode": "0xC2",
         "Invert": "1",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "UOPS_RETIRED.STALL_CYCLES",
         "SampleAfterValue": "2000003",
-        "BriefDescription": "Cycles without actually retired uops.",
+        "BriefDescription": "Cycles no executable uops retired",
         "CounterMask": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
+        "PEBS": "1",
+        "PublicDescription": "",
         "EventCode": "0xC2",
         "Invert": "1",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "UOPS_RETIRED.TOTAL_CYCLES",
         "SampleAfterValue": "2000003",
-        "BriefDescription": "Cycles with less than 10 actually retired uops.",
+        "BriefDescription": "Number of cycles using always true condition applied to  PEBS uops retired event.",
         "CounterMask": "10",
         "CounterHTOff": "0,1,2,3"
     },
     {
+        "PEBS": "1",
+        "PublicDescription": "",
         "EventCode": "0xC2",
         "Invert": "1",
         "Counter": "0,1,2,3",
@@ -1131,7 +1134,7 @@
         "AnyThread": "1",
         "EventName": "UOPS_RETIRED.CORE_STALL_CYCLES",
         "SampleAfterValue": "2000003",
-        "BriefDescription": "Cycles without actually retired uops.",
+        "BriefDescription": "Cycles no executable uops retired on core",
         "CounterMask": "1",
         "CounterHTOff": "0,1,2,3"
     },
@@ -1245,13 +1248,14 @@
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "PublicDescription": "Counts the number of not taken branch instructions retired.",
+        "PEBS": "1",
+        "PublicDescription": "",
         "EventCode": "0xC4",
         "Counter": "0,1,2,3",
         "UMask": "0x10",
         "EventName": "BR_INST_RETIRED.NOT_TAKEN",
         "SampleAfterValue": "400009",
-        "BriefDescription": "Not taken branch instructions retired.",
+        "BriefDescription": "Counts all not taken macro branch instructions retired.",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
@@ -1265,13 +1269,14 @@
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "PublicDescription": "Number of far branches retired.",
+        "PEBS": "1",
+        "PublicDescription": "",
         "EventCode": "0xC4",
         "Counter": "0,1,2,3",
         "UMask": "0x40",
         "EventName": "BR_INST_RETIRED.FAR_BRANCH",
         "SampleAfterValue": "100003",
-        "BriefDescription": "Far branch instructions retired.",
+        "BriefDescription": "Counts the number of far branch instructions retired.",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
diff --git a/tools/perf/pmu-events/arch/x86/haswellx/cache.json b/tools/perf/pmu-events/arch/x86/haswellx/cache.json
index b2fbd617306a..a9e62d4357af 100644
--- a/tools/perf/pmu-events/arch/x86/haswellx/cache.json
+++ b/tools/perf/pmu-events/arch/x86/haswellx/cache.json
@@ -64,18 +64,18 @@
     },
     {
         "EventCode": "0x24",
-        "UMask": "0x41",
+        "UMask": "0xc1",
         "BriefDescription": "Demand Data Read requests that hit L2 cache",
         "Counter": "0,1,2,3",
         "EventName": "L2_RQSTS.DEMAND_DATA_RD_HIT",
         "Errata": "HSD78",
-        "PublicDescription": "Demand data read requests that hit L2 cache.",
+        "PublicDescription": "Counts the number of demand Data Read requests, initiated by load instructions, that hit L2 cache",
         "SampleAfterValue": "200003",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
         "EventCode": "0x24",
-        "UMask": "0x42",
+        "UMask": "0xc2",
         "BriefDescription": "RFO requests that hit L2 cache",
         "Counter": "0,1,2,3",
         "EventName": "L2_RQSTS.RFO_HIT",
@@ -85,7 +85,7 @@
     },
     {
         "EventCode": "0x24",
-        "UMask": "0x44",
+        "UMask": "0xc4",
         "BriefDescription": "L2 cache hits when fetching instructions, code reads.",
         "Counter": "0,1,2,3",
         "EventName": "L2_RQSTS.CODE_RD_HIT",
@@ -95,7 +95,7 @@
     },
     {
         "EventCode": "0x24",
-        "UMask": "0x50",
+        "UMask": "0xd0",
         "BriefDescription": "L2 prefetch requests that hit L2 cache",
         "Counter": "0,1,2,3",
         "EventName": "L2_RQSTS.L2_PF_HIT",
@@ -416,7 +416,7 @@
     {
         "EventCode": "0xD0",
         "UMask": "0x11",
-        "BriefDescription": "Retired load uops that miss the STLB. (precise Event)",
+        "BriefDescription": "Retired load uops that miss the STLB.",
         "Data_LA": "1",
         "PEBS": "1",
         "Counter": "0,1,2,3",
@@ -428,7 +428,7 @@
     {
         "EventCode": "0xD0",
         "UMask": "0x12",
-        "BriefDescription": "Retired store uops that miss the STLB. (precise Event)",
+        "BriefDescription": "Retired store uops that miss the STLB.",
         "Data_LA": "1",
         "PEBS": "1",
         "Counter": "0,1,2,3",
@@ -441,7 +441,7 @@
     {
         "EventCode": "0xD0",
         "UMask": "0x21",
-        "BriefDescription": "Retired load uops with locked access. (precise Event)",
+        "BriefDescription": "Retired load uops with locked access.",
         "Data_LA": "1",
         "PEBS": "1",
         "Counter": "0,1,2,3",
@@ -453,34 +453,32 @@
     {
         "EventCode": "0xD0",
         "UMask": "0x41",
-        "BriefDescription": "Retired load uops that split across a cacheline boundary. (precise Event)",
+        "BriefDescription": "Retired load uops that split across a cacheline boundary.",
         "Data_LA": "1",
         "PEBS": "1",
         "Counter": "0,1,2,3",
         "EventName": "MEM_UOPS_RETIRED.SPLIT_LOADS",
         "Errata": "HSD29, HSM30",
-        "PublicDescription": "This event counts load uops retired which had memory addresses spilt across 2 cache lines. A line split is across 64B cache-lines which may include a page split (4K). This is a precise event.",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
     {
         "EventCode": "0xD0",
         "UMask": "0x42",
-        "BriefDescription": "Retired store uops that split across a cacheline boundary. (precise Event)",
+        "BriefDescription": "Retired store uops that split across a cacheline boundary.",
         "Data_LA": "1",
         "PEBS": "1",
         "Counter": "0,1,2,3",
         "EventName": "MEM_UOPS_RETIRED.SPLIT_STORES",
         "Errata": "HSD29, HSM30",
         "L1_Hit_Indication": "1",
-        "PublicDescription": "This event counts store uops retired which had memory addresses spilt across 2 cache lines. A line split is across 64B cache-lines which may include a page split (4K). This is a precise event.",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
     {
         "EventCode": "0xD0",
         "UMask": "0x81",
-        "BriefDescription": "All retired load uops. (precise Event)",
+        "BriefDescription": "All retired load uops.",
         "Data_LA": "1",
         "PEBS": "1",
         "Counter": "0,1,2,3",
@@ -492,14 +490,13 @@
     {
         "EventCode": "0xD0",
         "UMask": "0x82",
-        "BriefDescription": "All retired store uops. (precise Event)",
+        "BriefDescription": "All retired store uops.",
         "Data_LA": "1",
         "PEBS": "1",
         "Counter": "0,1,2,3",
         "EventName": "MEM_UOPS_RETIRED.ALL_STORES",
         "Errata": "HSD29, HSM30",
         "L1_Hit_Indication": "1",
-        "PublicDescription": "This event counts all store uops retired. This is a precise event.",
         "SampleAfterValue": "2000003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -530,13 +527,13 @@
     {
         "EventCode": "0xD1",
         "UMask": "0x4",
-        "BriefDescription": "Miss in last-level (L3) cache. Excludes Unknown data-source.",
+        "BriefDescription": "Retired load uops which data sources were data hits in L3 without snoops required.",
         "Data_LA": "1",
         "PEBS": "1",
         "Counter": "0,1,2,3",
         "EventName": "MEM_LOAD_UOPS_RETIRED.L3_HIT",
         "Errata": "HSD74, HSD29, HSD25, HSM26, HSM30",
-        "PublicDescription": "This event counts retired load uops in which data sources were data hits in the L3 cache without snoops required. This does not include hardware prefetches. This is a precise event.",
+        "PublicDescription": "Retired load uops with L3 cache hits as data sources.",
         "SampleAfterValue": "50021",
         "CounterHTOff": "0,1,2,3"
     },
@@ -549,19 +546,20 @@
         "Counter": "0,1,2,3",
         "EventName": "MEM_LOAD_UOPS_RETIRED.L1_MISS",
         "Errata": "HSM30",
-        "PublicDescription": "This event counts retired load uops in which data sources missed in the L1 cache. This does not include hardware prefetches. This is a precise event.",
+        "PublicDescription": "Retired load uops missed L1 cache as data sources.",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
     {
         "EventCode": "0xD1",
         "UMask": "0x10",
-        "BriefDescription": "Retired load uops with L2 cache misses as data sources.",
+        "BriefDescription": "Miss in mid-level (L2) cache. Excludes Unknown data-source.",
         "Data_LA": "1",
         "PEBS": "1",
         "Counter": "0,1,2,3",
         "EventName": "MEM_LOAD_UOPS_RETIRED.L2_MISS",
         "Errata": "HSD29, HSM30",
+        "PublicDescription": "Retired load uops missed L2. Unknown data source excluded.",
         "SampleAfterValue": "50021",
         "CounterHTOff": "0,1,2,3"
     },
@@ -574,6 +572,7 @@
         "Counter": "0,1,2,3",
         "EventName": "MEM_LOAD_UOPS_RETIRED.L3_MISS",
         "Errata": "HSD74, HSD29, HSD25, HSM26, HSM30",
+        "PublicDescription": "Retired load uops missed L3. Excludes unknown data source .",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -604,26 +603,24 @@
     {
         "EventCode": "0xD2",
         "UMask": "0x2",
-        "BriefDescription": "Retired load uops which data sources were L3 and cross-core snoop hits in on-pkg core cache. ",
+        "BriefDescription": "Retired load uops which data sources were L3 and cross-core snoop hits in on-pkg core cache.",
         "Data_LA": "1",
         "PEBS": "1",
         "Counter": "0,1,2,3",
         "EventName": "MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HIT",
         "Errata": "HSD29, HSD25, HSM26, HSM30",
-        "PublicDescription": "This event counts retired load uops that hit in the L3 cache, but required a cross-core snoop which resulted in a HIT in an on-pkg core cache. This does not include hardware prefetches. This is a precise event.",
         "SampleAfterValue": "20011",
         "CounterHTOff": "0,1,2,3"
     },
     {
         "EventCode": "0xD2",
         "UMask": "0x4",
-        "BriefDescription": "Retired load uops which data sources were HitM responses from shared L3. ",
+        "BriefDescription": "Retired load uops which data sources were HitM responses from shared L3.",
         "Data_LA": "1",
         "PEBS": "1",
         "Counter": "0,1,2,3",
         "EventName": "MEM_LOAD_UOPS_L3_HIT_RETIRED.XSNP_HITM",
         "Errata": "HSD29, HSD25, HSM26, HSM30",
-        "PublicDescription": "This event counts retired load uops that hit in the L3 cache, but required a cross-core snoop which resulted in a HITM (hit modified) in an on-pkg core cache. This does not include hardware prefetches. This is a precise event.",
         "SampleAfterValue": "20011",
         "CounterHTOff": "0,1,2,3"
     },
@@ -642,19 +639,20 @@
     {
         "EventCode": "0xD3",
         "UMask": "0x1",
+        "BriefDescription": "Data from local DRAM either Snoop not needed or Snoop Miss (RspI)",
         "Data_LA": "1",
         "PEBS": "1",
         "Counter": "0,1,2,3",
         "EventName": "MEM_LOAD_UOPS_L3_MISS_RETIRED.LOCAL_DRAM",
         "Errata": "HSD74, HSD29, HSD25, HSM30",
-        "PublicDescription": "This event counts retired load uops where the data came from local DRAM. This does not include hardware prefetches. This is a precise event.",
+        "PublicDescription": "This event counts retired load uops where the data came from local DRAM. This does not include hardware prefetches.",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
     {
         "EventCode": "0xD3",
         "UMask": "0x4",
-        "BriefDescription": "Retired load uop whose Data Source was: remote DRAM either Snoop not needed or Snoop Miss (RspI) (Precise Event)",
+        "BriefDescription": "Retired load uop whose Data Source was: remote DRAM either Snoop not needed or Snoop Miss (RspI)",
         "Data_LA": "1",
         "PEBS": "1",
         "Counter": "0,1,2,3",
@@ -666,7 +664,7 @@
     {
         "EventCode": "0xD3",
         "UMask": "0x10",
-        "BriefDescription": "Retired load uop whose Data Source was: Remote cache HITM (Precise Event)",
+        "BriefDescription": "Retired load uop whose Data Source was: Remote cache HITM",
         "Data_LA": "1",
         "PEBS": "1",
         "Counter": "0,1,2,3",
@@ -678,7 +676,7 @@
     {
         "EventCode": "0xD3",
         "UMask": "0x20",
-        "BriefDescription": "Retired load uop whose Data Source was: forwarded from remote cache (Precise Event)",
+        "BriefDescription": "Retired load uop whose Data Source was: forwarded from remote cache",
         "Data_LA": "1",
         "PEBS": "1",
         "Counter": "0,1,2,3",
@@ -833,7 +831,6 @@
         "BriefDescription": "Split locks in SQ",
         "Counter": "0,1,2,3",
         "EventName": "SQ_MISC.SPLIT_LOCK",
-        "PublicDescription": "",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
@@ -841,12 +838,12 @@
         "Offcore": "1",
         "EventCode": "0xB7, 0xBB",
         "UMask": "0x1",
-        "BriefDescription": "Counts demand data reads that hit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded",
-        "MSRValue": "0x04003c0001",
+        "BriefDescription": "Counts demand data reads hit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded",
+        "MSRValue": "0x04003C0001",
         "Counter": "0,1,2,3",
         "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.LLC_HIT.HIT_OTHER_CORE_NO_FWD",
         "MSRIndex": "0x1a6,0x1a7",
-        "PublicDescription": "Counts demand data reads that hit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts demand data reads hit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -854,12 +851,12 @@
         "Offcore": "1",
         "EventCode": "0xB7, 0xBB",
         "UMask": "0x1",
-        "BriefDescription": "Counts demand data reads that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded",
-        "MSRValue": "0x10003c0001",
+        "BriefDescription": "Counts demand data reads hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded",
+        "MSRValue": "0x10003C0001",
         "Counter": "0,1,2,3",
         "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.LLC_HIT.HITM_OTHER_CORE",
         "MSRIndex": "0x1a6,0x1a7",
-        "PublicDescription": "Counts demand data reads that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts demand data reads hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -867,12 +864,12 @@
         "Offcore": "1",
         "EventCode": "0xB7, 0xBB",
         "UMask": "0x1",
-        "BriefDescription": "Counts all demand data writes (RFOs) that hit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded",
-        "MSRValue": "0x04003c0002",
+        "BriefDescription": "Counts all demand data writes (RFOs) hit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded",
+        "MSRValue": "0x04003C0002",
         "Counter": "0,1,2,3",
         "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.LLC_HIT.HIT_OTHER_CORE_NO_FWD",
         "MSRIndex": "0x1a6,0x1a7",
-        "PublicDescription": "Counts all demand data writes (RFOs) that hit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all demand data writes (RFOs) hit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -880,12 +877,12 @@
         "Offcore": "1",
         "EventCode": "0xB7, 0xBB",
         "UMask": "0x1",
-        "BriefDescription": "Counts all demand data writes (RFOs) that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded",
-        "MSRValue": "0x10003c0002",
+        "BriefDescription": "Counts all demand data writes (RFOs) hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded",
+        "MSRValue": "0x10003C0002",
         "Counter": "0,1,2,3",
         "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.LLC_HIT.HITM_OTHER_CORE",
         "MSRIndex": "0x1a6,0x1a7",
-        "PublicDescription": "Counts all demand data writes (RFOs) that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all demand data writes (RFOs) hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -893,12 +890,12 @@
         "Offcore": "1",
         "EventCode": "0xB7, 0xBB",
         "UMask": "0x1",
-        "BriefDescription": "Counts all demand code reads that hit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded",
-        "MSRValue": "0x04003c0004",
+        "BriefDescription": "Counts all demand code reads hit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded",
+        "MSRValue": "0x04003C0004",
         "Counter": "0,1,2,3",
         "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.LLC_HIT.HIT_OTHER_CORE_NO_FWD",
         "MSRIndex": "0x1a6,0x1a7",
-        "PublicDescription": "Counts all demand code reads that hit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all demand code reads hit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -906,12 +903,12 @@
         "Offcore": "1",
         "EventCode": "0xB7, 0xBB",
         "UMask": "0x1",
-        "BriefDescription": "Counts all demand code reads that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded",
-        "MSRValue": "0x10003c0004",
+        "BriefDescription": "Counts all demand code reads hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded",
+        "MSRValue": "0x10003C0004",
         "Counter": "0,1,2,3",
         "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.LLC_HIT.HITM_OTHER_CORE",
         "MSRIndex": "0x1a6,0x1a7",
-        "PublicDescription": "Counts all demand code reads that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all demand code reads hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -919,12 +916,12 @@
         "Offcore": "1",
         "EventCode": "0xB7, 0xBB",
         "UMask": "0x1",
-        "BriefDescription": "Counts prefetch (that bring data to L2) data reads that hit in the L3",
-        "MSRValue": "0x3f803c0010",
+        "BriefDescription": "Counts prefetch (that bring data to L2) data reads hit in the L3",
+        "MSRValue": "0x3F803C0010",
         "Counter": "0,1,2,3",
         "EventName": "OFFCORE_RESPONSE.PF_L2_DATA_RD.LLC_HIT.ANY_RESPONSE",
         "MSRIndex": "0x1a6,0x1a7",
-        "PublicDescription": "Counts prefetch (that bring data to L2) data reads that hit in the L3 Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts prefetch (that bring data to L2) data reads hit in the L3",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -932,12 +929,12 @@
         "Offcore": "1",
         "EventCode": "0xB7, 0xBB",
         "UMask": "0x1",
-        "BriefDescription": "Counts all prefetch (that bring data to L2) RFOs that hit in the L3",
-        "MSRValue": "0x3f803c0020",
+        "BriefDescription": "Counts all prefetch (that bring data to L2) RFOs hit in the L3",
+        "MSRValue": "0x3F803C0020",
         "Counter": "0,1,2,3",
         "EventName": "OFFCORE_RESPONSE.PF_L2_RFO.LLC_HIT.ANY_RESPONSE",
         "MSRIndex": "0x1a6,0x1a7",
-        "PublicDescription": "Counts all prefetch (that bring data to L2) RFOs that hit in the L3 Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all prefetch (that bring data to L2) RFOs hit in the L3",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -945,12 +942,12 @@
         "Offcore": "1",
         "EventCode": "0xB7, 0xBB",
         "UMask": "0x1",
-        "BriefDescription": "Counts all prefetch (that bring data to LLC only) code reads that hit in the L3",
-        "MSRValue": "0x3f803c0040",
+        "BriefDescription": "Counts all prefetch (that bring data to LLC only) code reads hit in the L3",
+        "MSRValue": "0x3F803C0040",
         "Counter": "0,1,2,3",
         "EventName": "OFFCORE_RESPONSE.PF_L2_CODE_RD.LLC_HIT.ANY_RESPONSE",
         "MSRIndex": "0x1a6,0x1a7",
-        "PublicDescription": "Counts all prefetch (that bring data to LLC only) code reads that hit in the L3 Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all prefetch (that bring data to LLC only) code reads hit in the L3",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -958,12 +955,12 @@
         "Offcore": "1",
         "EventCode": "0xB7, 0xBB",
         "UMask": "0x1",
-        "BriefDescription": "Counts all prefetch (that bring data to LLC only) data reads that hit in the L3",
-        "MSRValue": "0x3f803c0080",
+        "BriefDescription": "Counts all prefetch (that bring data to LLC only) data reads hit in the L3",
+        "MSRValue": "0x3F803C0080",
         "Counter": "0,1,2,3",
         "EventName": "OFFCORE_RESPONSE.PF_LLC_DATA_RD.LLC_HIT.ANY_RESPONSE",
         "MSRIndex": "0x1a6,0x1a7",
-        "PublicDescription": "Counts all prefetch (that bring data to LLC only) data reads that hit in the L3 Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all prefetch (that bring data to LLC only) data reads hit in the L3",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -971,12 +968,12 @@
         "Offcore": "1",
         "EventCode": "0xB7, 0xBB",
         "UMask": "0x1",
-        "BriefDescription": "Counts all prefetch (that bring data to LLC only) RFOs that hit in the L3",
-        "MSRValue": "0x3f803c0100",
+        "BriefDescription": "Counts all prefetch (that bring data to LLC only) RFOs hit in the L3",
+        "MSRValue": "0x3F803C0100",
         "Counter": "0,1,2,3",
         "EventName": "OFFCORE_RESPONSE.PF_LLC_RFO.LLC_HIT.ANY_RESPONSE",
         "MSRIndex": "0x1a6,0x1a7",
-        "PublicDescription": "Counts all prefetch (that bring data to LLC only) RFOs that hit in the L3 Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all prefetch (that bring data to LLC only) RFOs hit in the L3",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -984,12 +981,12 @@
         "Offcore": "1",
         "EventCode": "0xB7, 0xBB",
         "UMask": "0x1",
-        "BriefDescription": "Counts prefetch (that bring data to LLC only) code reads that hit in the L3",
-        "MSRValue": "0x3f803c0200",
+        "BriefDescription": "Counts prefetch (that bring data to LLC only) code reads hit in the L3",
+        "MSRValue": "0x3F803C0200",
         "Counter": "0,1,2,3",
         "EventName": "OFFCORE_RESPONSE.PF_LLC_CODE_RD.LLC_HIT.ANY_RESPONSE",
         "MSRIndex": "0x1a6,0x1a7",
-        "PublicDescription": "Counts prefetch (that bring data to LLC only) code reads that hit in the L3 Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts prefetch (that bring data to LLC only) code reads hit in the L3",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -997,12 +994,12 @@
         "Offcore": "1",
         "EventCode": "0xB7, 0xBB",
         "UMask": "0x1",
-        "BriefDescription": "Counts all demand & prefetch data reads that hit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded",
-        "MSRValue": "0x04003c0091",
+        "BriefDescription": "Counts all demand & prefetch data reads hit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded",
+        "MSRValue": "0x04003C0091",
         "Counter": "0,1,2,3",
         "EventName": "OFFCORE_RESPONSE.ALL_DATA_RD.LLC_HIT.HIT_OTHER_CORE_NO_FWD",
         "MSRIndex": "0x1a6,0x1a7",
-        "PublicDescription": "Counts all demand & prefetch data reads that hit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all demand & prefetch data reads hit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -1010,12 +1007,12 @@
         "Offcore": "1",
         "EventCode": "0xB7, 0xBB",
         "UMask": "0x1",
-        "BriefDescription": "Counts all demand & prefetch data reads that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded",
-        "MSRValue": "0x10003c0091",
+        "BriefDescription": "Counts all demand & prefetch data reads hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded",
+        "MSRValue": "0x10003C0091",
         "Counter": "0,1,2,3",
         "EventName": "OFFCORE_RESPONSE.ALL_DATA_RD.LLC_HIT.HITM_OTHER_CORE",
         "MSRIndex": "0x1a6,0x1a7",
-        "PublicDescription": "Counts all demand & prefetch data reads that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all demand & prefetch data reads hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -1023,12 +1020,12 @@
         "Offcore": "1",
         "EventCode": "0xB7, 0xBB",
         "UMask": "0x1",
-        "BriefDescription": "Counts all demand & prefetch RFOs that hit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded",
-        "MSRValue": "0x04003c0122",
+        "BriefDescription": "Counts all demand & prefetch RFOs hit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded",
+        "MSRValue": "0x04003C0122",
         "Counter": "0,1,2,3",
         "EventName": "OFFCORE_RESPONSE.ALL_RFO.LLC_HIT.HIT_OTHER_CORE_NO_FWD",
         "MSRIndex": "0x1a6,0x1a7",
-        "PublicDescription": "Counts all demand & prefetch RFOs that hit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all demand & prefetch RFOs hit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -1036,12 +1033,12 @@
         "Offcore": "1",
         "EventCode": "0xB7, 0xBB",
         "UMask": "0x1",
-        "BriefDescription": "Counts all demand & prefetch RFOs that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded",
-        "MSRValue": "0x10003c0122",
+        "BriefDescription": "Counts all demand & prefetch RFOs hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded",
+        "MSRValue": "0x10003C0122",
         "Counter": "0,1,2,3",
         "EventName": "OFFCORE_RESPONSE.ALL_RFO.LLC_HIT.HITM_OTHER_CORE",
         "MSRIndex": "0x1a6,0x1a7",
-        "PublicDescription": "Counts all demand & prefetch RFOs that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all demand & prefetch RFOs hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -1049,12 +1046,12 @@
         "Offcore": "1",
         "EventCode": "0xB7, 0xBB",
         "UMask": "0x1",
-        "BriefDescription": "Counts all demand & prefetch code reads that hit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded",
-        "MSRValue": "0x04003c0244",
+        "BriefDescription": "Counts all demand & prefetch code reads hit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded",
+        "MSRValue": "0x04003C0244",
         "Counter": "0,1,2,3",
         "EventName": "OFFCORE_RESPONSE.ALL_CODE_RD.LLC_HIT.HIT_OTHER_CORE_NO_FWD",
         "MSRIndex": "0x1a6,0x1a7",
-        "PublicDescription": "Counts all demand & prefetch code reads that hit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all demand & prefetch code reads hit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -1062,12 +1059,12 @@
         "Offcore": "1",
         "EventCode": "0xB7, 0xBB",
         "UMask": "0x1",
-        "BriefDescription": "Counts all data/code/rfo reads (demand & prefetch) that hit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded",
-        "MSRValue": "0x04003c07f7",
+        "BriefDescription": "Counts all data/code/rfo reads (demand & prefetch) hit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded",
+        "MSRValue": "0x04003C07F7",
         "Counter": "0,1,2,3",
         "EventName": "OFFCORE_RESPONSE.ALL_READS.LLC_HIT.HIT_OTHER_CORE_NO_FWD",
         "MSRIndex": "0x1a6,0x1a7",
-        "PublicDescription": "Counts all data/code/rfo reads (demand & prefetch) that hit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all data/code/rfo reads (demand & prefetch) hit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -1075,12 +1072,12 @@
         "Offcore": "1",
         "EventCode": "0xB7, 0xBB",
         "UMask": "0x1",
-        "BriefDescription": "Counts all data/code/rfo reads (demand & prefetch) that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded",
-        "MSRValue": "0x10003c07f7",
+        "BriefDescription": "Counts all data/code/rfo reads (demand & prefetch) hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded",
+        "MSRValue": "0x10003C07F7",
         "Counter": "0,1,2,3",
         "EventName": "OFFCORE_RESPONSE.ALL_READS.LLC_HIT.HITM_OTHER_CORE",
         "MSRIndex": "0x1a6,0x1a7",
-        "PublicDescription": "Counts all data/code/rfo reads (demand & prefetch) that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all data/code/rfo reads (demand & prefetch) hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -1088,12 +1085,12 @@
         "Offcore": "1",
         "EventCode": "0xB7, 0xBB",
         "UMask": "0x1",
-        "BriefDescription": "Counts all requests that hit in the L3",
-        "MSRValue": "0x3f803c8fff",
+        "BriefDescription": "Counts all requests hit in the L3",
+        "MSRValue": "0x3F803C8FFF",
         "Counter": "0,1,2,3",
         "EventName": "OFFCORE_RESPONSE.ALL_REQUESTS.LLC_HIT.ANY_RESPONSE",
         "MSRIndex": "0x1a6,0x1a7",
-        "PublicDescription": "Counts all requests that hit in the L3 Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all requests hit in the L3",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     }
diff --git a/tools/perf/pmu-events/arch/x86/haswellx/hsx-metrics.json b/tools/perf/pmu-events/arch/x86/haswellx/hsx-metrics.json
index 5ab5c78fe580..e5aac148c941 100644
--- a/tools/perf/pmu-events/arch/x86/haswellx/hsx-metrics.json
+++ b/tools/perf/pmu-events/arch/x86/haswellx/hsx-metrics.json
@@ -1,158 +1,340 @@
 [
     {
-        "BriefDescription": "Instructions Per Cycle (per logical thread)",
+        "MetricExpr": "IDQ_UOPS_NOT_DELIVERED.CORE / (4 * cycles)",
+        "PublicDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend. Frontend denotes the first part of the processor core responsible to fetch operations that are executed later on by the Backend part. Within the Frontend; a branch predictor predicts the next address to fetch; cache-lines are fetched from the memory subsystem; parsed into instructions; and lastly decoded into micro-ops (uops). Ideally the Frontend can issue 4 uops every cycle to the Backend. Frontend Bound denotes unutilized issue-slots when there is no Backend stall; i.e. bubbles where Frontend delivered no uops while Backend could have accepted them. For example; stalls due to instruction-cache misses would be categorized under Frontend Bound.",
+        "BriefDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend",
+        "MetricGroup": "TopdownL1",
+        "MetricName": "Frontend_Bound"
+    },
+    {
+        "MetricExpr": "IDQ_UOPS_NOT_DELIVERED.CORE / (4 * (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )))",
+        "PublicDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend. Frontend denotes the first part of the processor core responsible to fetch operations that are executed later on by the Backend part. Within the Frontend; a branch predictor predicts the next address to fetch; cache-lines are fetched from the memory subsystem; parsed into instructions; and lastly decoded into micro-ops (uops). Ideally the Frontend can issue 4 uops every cycle to the Backend. Frontend Bound denotes unutilized issue-slots when there is no Backend stall; i.e. bubbles where Frontend delivered no uops while Backend could have accepted them. For example; stalls due to instruction-cache misses would be categorized under Frontend Bound. SMT version; use when SMT is enabled and measuring per logical CPU.",
+        "BriefDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend. SMT version; use when SMT is enabled and measuring per logical CPU.",
+        "MetricGroup": "TopdownL1_SMT",
+        "MetricName": "Frontend_Bound_SMT"
+    },
+    {
+        "MetricExpr": "( UOPS_ISSUED.ANY - UOPS_RETIRED.RETIRE_SLOTS + 4 * INT_MISC.RECOVERY_CYCLES ) / (4 * cycles)",
+        "PublicDescription": "This category represents fraction of slots wasted due to incorrect speculations. This include slots used to issue uops that do not eventually get retired and slots for which the issue-pipeline was blocked due to recovery from earlier incorrect speculation. For example; wasted work due to miss-predicted branches are categorized under Bad Speculation category. Incorrect data speculation followed by Memory Ordering Nukes is another example.",
+        "BriefDescription": "This category represents fraction of slots wasted due to incorrect speculations",
+        "MetricGroup": "TopdownL1",
+        "MetricName": "Bad_Speculation"
+    },
+    {
+        "MetricExpr": "( UOPS_ISSUED.ANY - UOPS_RETIRED.RETIRE_SLOTS + 4 * (( INT_MISC.RECOVERY_CYCLES_ANY / 2 )) ) / (4 * (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )))",
+        "PublicDescription": "This category represents fraction of slots wasted due to incorrect speculations. This include slots used to issue uops that do not eventually get retired and slots for which the issue-pipeline was blocked due to recovery from earlier incorrect speculation. For example; wasted work due to miss-predicted branches are categorized under Bad Speculation category. Incorrect data speculation followed by Memory Ordering Nukes is another example. SMT version; use when SMT is enabled and measuring per logical CPU.",
+        "BriefDescription": "This category represents fraction of slots wasted due to incorrect speculations. SMT version; use when SMT is enabled and measuring per logical CPU.",
+        "MetricGroup": "TopdownL1_SMT",
+        "MetricName": "Bad_Speculation_SMT"
+    },
+    {
+        "MetricExpr": "1 - ( (IDQ_UOPS_NOT_DELIVERED.CORE / (4 * cycles)) + (( UOPS_ISSUED.ANY - UOPS_RETIRED.RETIRE_SLOTS + 4 * INT_MISC.RECOVERY_CYCLES ) / (4 * cycles)) + (UOPS_RETIRED.RETIRE_SLOTS / (4 * cycles)) )",
+        "PublicDescription": "This category represents fraction of slots where no uops are being delivered due to a lack of required resources for accepting new uops in the Backend. Backend is the portion of the processor core where the out-of-order scheduler dispatches ready uops into their respective execution units; and once completed these uops get retired according to program order. For example; stalls due to data-cache misses or stalls due to the divider unit being overloaded are both categorized under Backend Bound. Backend Bound is further divided into two main categories: Memory Bound and Core Bound.",
+        "BriefDescription": "This category represents fraction of slots where no uops are being delivered due to a lack of required resources for accepting new uops in the Backend",
+        "MetricGroup": "TopdownL1",
+        "MetricName": "Backend_Bound"
+    },
+    {
+        "MetricExpr": "1 - ( (IDQ_UOPS_NOT_DELIVERED.CORE / (4 * (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )))) + (( UOPS_ISSUED.ANY - UOPS_RETIRED.RETIRE_SLOTS + 4 * (( INT_MISC.RECOVERY_CYCLES_ANY / 2 )) ) / (4 * (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )))) + (UOPS_RETIRED.RETIRE_SLOTS / (4 * (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )))) )",
+        "PublicDescription": "This category represents fraction of slots where no uops are being delivered due to a lack of required resources for accepting new uops in the Backend. Backend is the portion of the processor core where the out-of-order scheduler dispatches ready uops into their respective execution units; and once completed these uops get retired according to program order. For example; stalls due to data-cache misses or stalls due to the divider unit being overloaded are both categorized under Backend Bound. Backend Bound is further divided into two main categories: Memory Bound and Core Bound. SMT version; use when SMT is enabled and measuring per logical CPU.",
+        "BriefDescription": "This category represents fraction of slots where no uops are being delivered due to a lack of required resources for accepting new uops in the Backend. SMT version; use when SMT is enabled and measuring per logical CPU.",
+        "MetricGroup": "TopdownL1_SMT",
+        "MetricName": "Backend_Bound_SMT"
+    },
+    {
+        "MetricExpr": "UOPS_RETIRED.RETIRE_SLOTS / (4 * cycles)",
+        "PublicDescription": "This category represents fraction of slots utilized by useful work i.e. issued uops that eventually get retired. Ideally; all pipeline slots would be attributed to the Retiring category.  Retiring of 100% would indicate the maximum 4 uops retired per cycle has been achieved.  Maximizing Retiring typically increases the Instruction-Per-Cycle metric. Note that a high Retiring value does not necessary mean there is no room for more performance.  For example; Microcode assists are categorized under Retiring. They hurt performance and can often be avoided. ",
+        "BriefDescription": "This category represents fraction of slots utilized by useful work i.e. issued uops that eventually get retired",
+        "MetricGroup": "TopdownL1",
+        "MetricName": "Retiring"
+    },
+    {
+        "MetricExpr": "UOPS_RETIRED.RETIRE_SLOTS / (4 * (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )))",
+        "PublicDescription": "This category represents fraction of slots utilized by useful work i.e. issued uops that eventually get retired. Ideally; all pipeline slots would be attributed to the Retiring category.  Retiring of 100% would indicate the maximum 4 uops retired per cycle has been achieved.  Maximizing Retiring typically increases the Instruction-Per-Cycle metric. Note that a high Retiring value does not necessary mean there is no room for more performance.  For example; Microcode assists are categorized under Retiring. They hurt performance and can often be avoided. SMT version; use when SMT is enabled and measuring per logical CPU.",
+        "BriefDescription": "This category represents fraction of slots utilized by useful work i.e. issued uops that eventually get retired. SMT version; use when SMT is enabled and measuring per logical CPU.",
+        "MetricGroup": "TopdownL1_SMT",
+        "MetricName": "Retiring_SMT"
+    },
+    {
         "MetricExpr": "INST_RETIRED.ANY / CPU_CLK_UNHALTED.THREAD",
+        "BriefDescription": "Instructions Per Cycle (per logical thread)",
         "MetricGroup": "TopDownL1",
         "MetricName": "IPC"
     },
     {
-        "BriefDescription": "Uops Per Instruction",
         "MetricExpr": "UOPS_RETIRED.RETIRE_SLOTS / INST_RETIRED.ANY",
-        "MetricGroup": "Pipeline",
+        "BriefDescription": "Uops Per Instruction",
+        "MetricGroup": "Pipeline;Retiring",
         "MetricName": "UPI"
     },
     {
-        "BriefDescription": "Rough Estimation of fraction of fetched lines bytes that were likely consumed by program instructions",
+        "MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.NEAR_TAKEN",
+        "BriefDescription": "Instruction per taken branch",
+        "MetricGroup": "Branches;PGO",
+        "MetricName": "IpTB"
+    },
+    {
+        "MetricExpr": "BR_INST_RETIRED.ALL_BRANCHES / BR_INST_RETIRED.NEAR_TAKEN",
+        "BriefDescription": "Branch instructions per taken branch. ",
+        "MetricGroup": "Branches;PGO",
+        "MetricName": "BpTB"
+    },
+    {
         "MetricExpr": "min( 1 , IDQ.MITE_UOPS / ( (UOPS_RETIRED.RETIRE_SLOTS / INST_RETIRED.ANY) * 16 * ( ICACHE.HIT + ICACHE.MISSES ) / 4.0 ) )",
-        "MetricGroup": "Frontend",
+        "BriefDescription": "Rough Estimation of fraction of fetched lines bytes that were likely (includes speculatively fetches) consumed by program instructions",
+        "MetricGroup": "PGO",
         "MetricName": "IFetch_Line_Utilization"
     },
     {
-        "BriefDescription": "Fraction of Uops delivered by the DSB (aka Decoded Icache; or Uop Cache)",
-        "MetricExpr": "IDQ.DSB_UOPS / ( IDQ.DSB_UOPS + LSD.UOPS + IDQ.MITE_UOPS + IDQ.MS_UOPS )",
-        "MetricGroup": "DSB; Frontend_Bandwidth",
+        "MetricExpr": "IDQ.DSB_UOPS / (( IDQ.DSB_UOPS + LSD.UOPS + IDQ.MITE_UOPS + IDQ.MS_UOPS ) )",
+        "BriefDescription": "Fraction of Uops delivered by the DSB (aka Decoded ICache; or Uop Cache)",
+        "MetricGroup": "DSB;Frontend_Bandwidth",
         "MetricName": "DSB_Coverage"
     },
     {
-        "BriefDescription": "Cycles Per Instruction (threaded)",
         "MetricExpr": "1 / (INST_RETIRED.ANY / cycles)",
+        "BriefDescription": "Cycles Per Instruction (threaded)",
         "MetricGroup": "Pipeline;Summary",
         "MetricName": "CPI"
     },
     {
-        "BriefDescription": "Per-thread actual clocks when the logical processor is active. This is called 'Clockticks' in VTune.",
         "MetricExpr": "CPU_CLK_UNHALTED.THREAD",
+        "BriefDescription": "Per-thread actual clocks when the logical processor is active.",
         "MetricGroup": "Summary",
         "MetricName": "CLKS"
     },
     {
-        "BriefDescription": "Total issue-pipeline slots",
-        "MetricExpr": "4*(( CPU_CLK_UNHALTED.THREAD_ANY / 2 ) if #SMT_on else cycles)",
+        "MetricExpr": "4 * cycles",
+        "BriefDescription": "Total issue-pipeline slots (per core)",
         "MetricGroup": "TopDownL1",
         "MetricName": "SLOTS"
     },
     {
-        "BriefDescription": "Total number of retired Instructions",
+        "MetricExpr": "4 * (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) ))",
+        "BriefDescription": "Total issue-pipeline slots (per core)",
+        "MetricGroup": "TopDownL1_SMT",
+        "MetricName": "SLOTS_SMT"
+    },
+    {
+        "MetricExpr": "INST_RETIRED.ANY / MEM_UOPS_RETIRED.ALL_LOADS",
+        "BriefDescription": "Instructions per Load (lower number means loads are more frequent)",
+        "MetricGroup": "Instruction_Type;L1_Bound",
+        "MetricName": "IpL"
+    },
+    {
+        "MetricExpr": "INST_RETIRED.ANY / MEM_UOPS_RETIRED.ALL_STORES",
+        "BriefDescription": "Instructions per Store",
+        "MetricGroup": "Instruction_Type;Store_Bound",
+        "MetricName": "IpS"
+    },
+    {
+        "MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.ALL_BRANCHES",
+        "BriefDescription": "Instructions per Branch",
+        "MetricGroup": "Branches;Instruction_Type;Port_5;Port_6",
+        "MetricName": "IpB"
+    },
+    {
+        "MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.NEAR_CALL",
+        "BriefDescription": "Instruction per (near) call",
+        "MetricGroup": "Branches",
+        "MetricName": "IpCall"
+    },
+    {
         "MetricExpr": "INST_RETIRED.ANY",
+        "BriefDescription": "Total number of retired Instructions",
         "MetricGroup": "Summary",
         "MetricName": "Instructions"
     },
     {
+        "MetricExpr": "INST_RETIRED.ANY / cycles",
         "BriefDescription": "Instructions Per Cycle (per physical core)",
-        "MetricExpr": "INST_RETIRED.ANY / (( CPU_CLK_UNHALTED.THREAD_ANY / 2 ) if #SMT_on else cycles)",
         "MetricGroup": "SMT",
         "MetricName": "CoreIPC"
     },
     {
+        "MetricExpr": "INST_RETIRED.ANY / (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) ))",
+        "BriefDescription": "Instructions Per Cycle (per physical core)",
+        "MetricGroup": "SMT",
+        "MetricName": "CoreIPC_SMT"
+    },
+    {
+        "MetricExpr": "( UOPS_EXECUTED.CORE / 2 / (( cpu@UOPS_EXECUTED.CORE\\,cmask\\=1@ / 2 ) if #SMT_on else cpu@UOPS_EXECUTED.CORE\\,cmask\\=1@) ) if #SMT_on else UOPS_EXECUTED.CORE / (( cpu@UOPS_EXECUTED.CORE\\,cmask\\=1@ / 2 ) if #SMT_on else cpu@UOPS_EXECUTED.CORE\\,cmask\\=1@)",
         "BriefDescription": "Instruction-Level-Parallelism (average number of uops executed when there is at least 1 uop executed)",
-        "MetricExpr": "( UOPS_EXECUTED.CORE / 2 / (( cpu@UOPS_EXECUTED.CORE\\,cmask\\=1@ / 2) if #SMT_on else cpu@UOPS_EXECUTED.CORE\\,cmask\\=1@) ) if #SMT_on else UOPS_EXECUTED.CORE / (( cpu@UOPS_EXECUTED.CORE\\,cmask\\=1@ / 2) if #SMT_on else cpu@UOPS_EXECUTED.CORE\\,cmask\\=1@)",
         "MetricGroup": "Pipeline;Ports_Utilization",
         "MetricName": "ILP"
     },
     {
-        "BriefDescription": "Average Branch Address Clear Cost (fraction of cycles)",
-        "MetricExpr": "2* (( RS_EVENTS.EMPTY_CYCLES - ICACHE.IFDATA_STALL  - (( 14 * ITLB_MISSES.STLB_HIT + ITLB_MISSES.WALK_DURATION )) ) / RS_EVENTS.EMPTY_END)",
-        "MetricGroup": "Unknown_Branches",
-        "MetricName": "BAClear_Cost"
+        "MetricExpr": "INST_RETIRED.ANY / BR_MISP_RETIRED.ALL_BRANCHES",
+        "BriefDescription": "Number of Instructions per non-speculative Branch Misprediction (JEClear)",
+        "MetricGroup": "Branch_Mispredicts",
+        "MetricName": "IpMispredict"
     },
     {
+        "MetricExpr": "( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )",
         "BriefDescription": "Core actual clocks when any thread is active on the physical core",
-        "MetricExpr": "( CPU_CLK_UNHALTED.THREAD_ANY / 2 ) if #SMT_on else CPU_CLK_UNHALTED.THREAD",
         "MetricGroup": "SMT",
         "MetricName": "CORE_CLKS"
     },
     {
-        "BriefDescription": "Actual Average Latency for L1 data-cache miss demand loads",
         "MetricExpr": "L1D_PEND_MISS.PENDING / ( MEM_LOAD_UOPS_RETIRED.L1_MISS + mem_load_uops_retired.hit_lfb )",
+        "BriefDescription": "Actual Average Latency for L1 data-cache miss demand loads (in core cycles)",
         "MetricGroup": "Memory_Bound;Memory_Lat",
         "MetricName": "Load_Miss_Real_Latency"
     },
     {
-        "BriefDescription": "Memory-Level-Parallelism (average number of L1 miss demand load when there is at least 1 such miss)",
-        "MetricExpr": "L1D_PEND_MISS.PENDING / (( cpu@l1d_pend_miss.pending_cycles\\,any\\=1@ / 2) if #SMT_on else L1D_PEND_MISS.PENDING_CYCLES)",
+        "MetricExpr": "L1D_PEND_MISS.PENDING / L1D_PEND_MISS.PENDING_CYCLES",
+        "BriefDescription": "Memory-Level-Parallelism (average number of L1 miss demand load when there is at least one such miss. Per-thread)",
         "MetricGroup": "Memory_Bound;Memory_BW",
         "MetricName": "MLP"
     },
     {
+        "MetricExpr": "( ITLB_MISSES.WALK_DURATION + DTLB_LOAD_MISSES.WALK_DURATION + DTLB_STORE_MISSES.WALK_DURATION ) / cycles",
         "BriefDescription": "Utilization of the core's Page Walker(s) serving STLB misses triggered by instruction/Load/Store accesses",
-        "MetricExpr": "( ITLB_MISSES.WALK_DURATION + DTLB_LOAD_MISSES.WALK_DURATION + DTLB_STORE_MISSES.WALK_DURATION ) / (( CPU_CLK_UNHALTED.THREAD_ANY / 2 ) if #SMT_on else cycles)",
         "MetricGroup": "TLB",
         "MetricName": "Page_Walks_Utilization"
     },
     {
-        "BriefDescription": "Average CPU Utilization",
+        "MetricExpr": "( ITLB_MISSES.WALK_DURATION + DTLB_LOAD_MISSES.WALK_DURATION + DTLB_STORE_MISSES.WALK_DURATION ) / (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) ))",
+        "BriefDescription": "Utilization of the core's Page Walker(s) serving STLB misses triggered by instruction/Load/Store accesses",
+        "MetricGroup": "TLB_SMT",
+        "MetricName": "Page_Walks_Utilization_SMT"
+    },
+    {
+        "MetricExpr": "64 * L1D.REPLACEMENT / 1000000000 / duration_time",
+        "BriefDescription": "Average data fill bandwidth to the L1 data cache [GB / sec]",
+        "MetricGroup": "Memory_BW",
+        "MetricName": "L1D_Cache_Fill_BW"
+    },
+    {
+        "MetricExpr": "64 * L2_LINES_IN.ALL / 1000000000 / duration_time",
+        "BriefDescription": "Average data fill bandwidth to the L2 cache [GB / sec]",
+        "MetricGroup": "Memory_BW",
+        "MetricName": "L2_Cache_Fill_BW"
+    },
+    {
+        "MetricExpr": "64 * LONGEST_LAT_CACHE.MISS / 1000000000 / duration_time",
+        "BriefDescription": "Average per-core data fill bandwidth to the L3 cache [GB / sec]",
+        "MetricGroup": "Memory_BW",
+        "MetricName": "L3_Cache_Fill_BW"
+    },
+    {
+        "MetricExpr": "1000 * MEM_LOAD_UOPS_RETIRED.L1_MISS / INST_RETIRED.ANY",
+        "BriefDescription": "L1 cache true misses per kilo instruction for retired demand loads",
+        "MetricGroup": "Cache_Misses;",
+        "MetricName": "L1MPKI"
+    },
+    {
+        "MetricExpr": "1000 * MEM_LOAD_UOPS_RETIRED.L2_MISS / INST_RETIRED.ANY",
+        "BriefDescription": "L2 cache true misses per kilo instruction for retired demand loads",
+        "MetricGroup": "Cache_Misses;",
+        "MetricName": "L2MPKI"
+    },
+    {
+        "MetricExpr": "1000 * MEM_LOAD_UOPS_RETIRED.L2_MISS / INST_RETIRED.ANY",
+        "BriefDescription": "L2 cache misses per kilo instruction for all request types (including speculative)",
+        "MetricGroup": "Cache_Misses;",
+        "MetricName": "L2MPKI_All"
+    },
+    {
+        "MetricExpr": "1000 * MEM_LOAD_UOPS_RETIRED.L2_MISS / INST_RETIRED.ANY",
+        "BriefDescription": "L2 cache hits per kilo instruction for all request types (including speculative)",
+        "MetricGroup": "Cache_Misses;",
+        "MetricName": "L2HPKI_All"
+    },
+    {
+        "MetricExpr": "1000 * MEM_LOAD_UOPS_RETIRED.L3_MISS / INST_RETIRED.ANY",
+        "BriefDescription": "L3 cache true misses per kilo instruction for retired demand loads",
+        "MetricGroup": "Cache_Misses;",
+        "MetricName": "L3MPKI"
+    },
+    {
         "MetricExpr": "CPU_CLK_UNHALTED.REF_TSC / msr@tsc@",
+        "BriefDescription": "Average CPU Utilization",
         "MetricGroup": "Summary",
         "MetricName": "CPU_Utilization"
     },
     {
-        "BriefDescription": "Average Frequency Utilization relative nominal frequency",
         "MetricExpr": "CPU_CLK_UNHALTED.THREAD / CPU_CLK_UNHALTED.REF_TSC",
+        "BriefDescription": "Average Frequency Utilization relative nominal frequency",
         "MetricGroup": "Power",
         "MetricName": "Turbo_Utilization"
     },
     {
-        "BriefDescription": "Fraction of cycles where both hardware threads were active",
         "MetricExpr": "1 - CPU_CLK_THREAD_UNHALTED.ONE_THREAD_ACTIVE / ( CPU_CLK_THREAD_UNHALTED.REF_XCLK_ANY / 2 ) if #SMT_on else 0",
+        "BriefDescription": "Fraction of cycles where both hardware threads were active",
         "MetricGroup": "SMT;Summary",
         "MetricName": "SMT_2T_Utilization"
     },
     {
-        "BriefDescription": "Fraction of cycles spent in Kernel mode",
         "MetricExpr": "CPU_CLK_UNHALTED.REF_TSC:u / CPU_CLK_UNHALTED.REF_TSC",
+        "BriefDescription": "Fraction of cycles spent in Kernel mode",
         "MetricGroup": "Summary",
         "MetricName": "Kernel_Utilization"
     },
     {
-        "BriefDescription": "C3 residency percent per core",
+        "MetricExpr": "( 64 * ( uncore_imc@cas_count_read@ + uncore_imc@cas_count_write@ ) / 1000000000 ) / duration_time",
+        "BriefDescription": "Average external Memory Bandwidth Use for reads and writes [GB / sec]",
+        "MetricGroup": "Memory_BW",
+        "MetricName": "DRAM_BW_Use"
+    },
+    {
+        "MetricExpr": "1000000000 * ( cbox@event\\=0x36\\,umask\\=0x3\\,filter_opc\\=0x182@ / cbox@event\\=0x35\\,umask\\=0x3\\,filter_opc\\=0x182@ ) / ( cbox_0@event\\=0x0@ / duration_time )",
+        "BriefDescription": "Average latency of data read request to external memory (in nanoseconds). Accounts for demand loads and L1/L2 prefetches",
+        "MetricGroup": "Memory_Lat",
+        "MetricName": "DRAM_Read_Latency"
+    },
+    {
+        "MetricExpr": "cbox@event\\=0x36\\,umask\\=0x3\\,filter_opc\\=0x182@ / cbox@event\\=0x36\\,umask\\=0x3\\,filter_opc\\=0x182\\,thresh\\=1@",
+        "BriefDescription": "Average number of parallel data read requests to external memory. Accounts for demand loads and L1/L2 prefetches",
+        "MetricGroup": "Memory_BW",
+        "MetricName": "DRAM_Parallel_Reads"
+    },
+    {
+        "MetricExpr": "cbox_0@event\\=0x0@",
+        "BriefDescription": "Socket actual clocks when any core is active on that socket",
+        "MetricGroup": "",
+        "MetricName": "Socket_CLKS"
+    },
+    {
         "MetricExpr": "(cstate_core@c3\\-residency@ / msr@tsc@) * 100",
         "MetricGroup": "Power",
+        "BriefDescription": "C3 residency percent per core",
         "MetricName": "C3_Core_Residency"
     },
     {
-        "BriefDescription": "C6 residency percent per core",
         "MetricExpr": "(cstate_core@c6\\-residency@ / msr@tsc@) * 100",
         "MetricGroup": "Power",
+        "BriefDescription": "C6 residency percent per core",
         "MetricName": "C6_Core_Residency"
     },
     {
-        "BriefDescription": "C7 residency percent per core",
         "MetricExpr": "(cstate_core@c7\\-residency@ / msr@tsc@) * 100",
         "MetricGroup": "Power",
+        "BriefDescription": "C7 residency percent per core",
         "MetricName": "C7_Core_Residency"
     },
     {
-        "BriefDescription": "C2 residency percent per package",
         "MetricExpr": "(cstate_pkg@c2\\-residency@ / msr@tsc@) * 100",
         "MetricGroup": "Power",
+        "BriefDescription": "C2 residency percent per package",
         "MetricName": "C2_Pkg_Residency"
     },
     {
-        "BriefDescription": "C3 residency percent per package",
         "MetricExpr": "(cstate_pkg@c3\\-residency@ / msr@tsc@) * 100",
         "MetricGroup": "Power",
+        "BriefDescription": "C3 residency percent per package",
         "MetricName": "C3_Pkg_Residency"
     },
     {
-        "BriefDescription": "C6 residency percent per package",
         "MetricExpr": "(cstate_pkg@c6\\-residency@ / msr@tsc@) * 100",
         "MetricGroup": "Power",
+        "BriefDescription": "C6 residency percent per package",
         "MetricName": "C6_Pkg_Residency"
     },
     {
-        "BriefDescription": "C7 residency percent per package",
         "MetricExpr": "(cstate_pkg@c7\\-residency@ / msr@tsc@) * 100",
         "MetricGroup": "Power",
+        "BriefDescription": "C7 residency percent per package",
         "MetricName": "C7_Pkg_Residency"
     }
 ]
diff --git a/tools/perf/pmu-events/arch/x86/haswellx/memory.json b/tools/perf/pmu-events/arch/x86/haswellx/memory.json
index 56b0f24b8029..a42d5ce86b6f 100644
--- a/tools/perf/pmu-events/arch/x86/haswellx/memory.json
+++ b/tools/perf/pmu-events/arch/x86/haswellx/memory.json
@@ -291,7 +291,7 @@
     {
         "EventCode": "0xCD",
         "UMask": "0x1",
-        "BriefDescription": "Loads with latency value being above 4.",
+        "BriefDescription": "Randomly selected loads with latency value being above 4.",
         "PEBS": "2",
         "MSRValue": "0x4",
         "Counter": "3",
@@ -305,7 +305,7 @@
     {
         "EventCode": "0xCD",
         "UMask": "0x1",
-        "BriefDescription": "Loads with latency value being above 8.",
+        "BriefDescription": "Randomly selected loads with latency value being above 8.",
         "PEBS": "2",
         "MSRValue": "0x8",
         "Counter": "3",
@@ -319,7 +319,7 @@
     {
         "EventCode": "0xCD",
         "UMask": "0x1",
-        "BriefDescription": "Loads with latency value being above 16.",
+        "BriefDescription": "Randomly selected loads with latency value being above 16.",
         "PEBS": "2",
         "MSRValue": "0x10",
         "Counter": "3",
@@ -333,7 +333,7 @@
     {
         "EventCode": "0xCD",
         "UMask": "0x1",
-        "BriefDescription": "Loads with latency value being above 32.",
+        "BriefDescription": "Randomly selected loads with latency value being above 32.",
         "PEBS": "2",
         "MSRValue": "0x20",
         "Counter": "3",
@@ -347,7 +347,7 @@
     {
         "EventCode": "0xCD",
         "UMask": "0x1",
-        "BriefDescription": "Loads with latency value being above 64.",
+        "BriefDescription": "Randomly selected loads with latency value being above 64.",
         "PEBS": "2",
         "MSRValue": "0x40",
         "Counter": "3",
@@ -361,7 +361,7 @@
     {
         "EventCode": "0xCD",
         "UMask": "0x1",
-        "BriefDescription": "Loads with latency value being above 128.",
+        "BriefDescription": "Randomly selected loads with latency value being above 128.",
         "PEBS": "2",
         "MSRValue": "0x80",
         "Counter": "3",
@@ -375,7 +375,7 @@
     {
         "EventCode": "0xCD",
         "UMask": "0x1",
-        "BriefDescription": "Loads with latency value being above 256.",
+        "BriefDescription": "Randomly selected loads with latency value being above 256.",
         "PEBS": "2",
         "MSRValue": "0x100",
         "Counter": "3",
@@ -389,7 +389,7 @@
     {
         "EventCode": "0xCD",
         "UMask": "0x1",
-        "BriefDescription": "Loads with latency value being above 512.",
+        "BriefDescription": "Randomly selected loads with latency value being above 512.",
         "PEBS": "2",
         "MSRValue": "0x200",
         "Counter": "3",
@@ -404,12 +404,12 @@
         "Offcore": "1",
         "EventCode": "0xB7, 0xBB",
         "UMask": "0x1",
-        "BriefDescription": "Counts demand data reads that miss in the L3",
-        "MSRValue": "0x3fbfc00001",
+        "BriefDescription": "Counts demand data reads miss in the L3",
+        "MSRValue": "0x3FBFC00001",
         "Counter": "0,1,2,3",
         "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.LLC_MISS.ANY_RESPONSE",
         "MSRIndex": "0x1a6,0x1a7",
-        "PublicDescription": "Counts demand data reads that miss in the L3 Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts demand data reads miss in the L3",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -417,12 +417,12 @@
         "Offcore": "1",
         "EventCode": "0xB7, 0xBB",
         "UMask": "0x1",
-        "BriefDescription": "Counts demand data reads that miss the L3 and the data is returned from local dram",
+        "BriefDescription": "Counts demand data reads miss the L3 and the data is returned from local dram",
         "MSRValue": "0x0600400001",
         "Counter": "0,1,2,3",
         "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.LLC_MISS.LOCAL_DRAM",
         "MSRIndex": "0x1a6,0x1a7",
-        "PublicDescription": "Counts demand data reads that miss the L3 and the data is returned from local dram Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts demand data reads miss the L3 and the data is returned from local dram",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -430,12 +430,12 @@
         "Offcore": "1",
         "EventCode": "0xB7, 0xBB",
         "UMask": "0x1",
-        "BriefDescription": "Counts all demand data writes (RFOs) that miss in the L3",
-        "MSRValue": "0x3fbfc00002",
+        "BriefDescription": "Counts all demand data writes (RFOs) miss in the L3",
+        "MSRValue": "0x3FBFC00002",
         "Counter": "0,1,2,3",
         "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.LLC_MISS.ANY_RESPONSE",
         "MSRIndex": "0x1a6,0x1a7",
-        "PublicDescription": "Counts all demand data writes (RFOs) that miss in the L3 Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all demand data writes (RFOs) miss in the L3",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -443,12 +443,12 @@
         "Offcore": "1",
         "EventCode": "0xB7, 0xBB",
         "UMask": "0x1",
-        "BriefDescription": "Counts all demand data writes (RFOs) that miss the L3 and the data is returned from local dram",
+        "BriefDescription": "Counts all demand data writes (RFOs) miss the L3 and the data is returned from local dram",
         "MSRValue": "0x0600400002",
         "Counter": "0,1,2,3",
         "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.LLC_MISS.LOCAL_DRAM",
         "MSRIndex": "0x1a6,0x1a7",
-        "PublicDescription": "Counts all demand data writes (RFOs) that miss the L3 and the data is returned from local dram Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all demand data writes (RFOs) miss the L3 and the data is returned from local dram",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -456,12 +456,12 @@
         "Offcore": "1",
         "EventCode": "0xB7, 0xBB",
         "UMask": "0x1",
-        "BriefDescription": "Counts all demand data writes (RFOs) that miss the L3 and the modified data is transferred from remote cache",
-        "MSRValue": "0x103fc00002",
+        "BriefDescription": "Counts all demand data writes (RFOs) miss the L3 and the modified data is transferred from remote cache",
+        "MSRValue": "0x103FC00002",
         "Counter": "0,1,2,3",
         "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.LLC_MISS.REMOTE_HITM",
         "MSRIndex": "0x1a6,0x1a7",
-        "PublicDescription": "Counts all demand data writes (RFOs) that miss the L3 and the modified data is transferred from remote cache Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all demand data writes (RFOs) miss the L3 and the modified data is transferred from remote cache",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -469,12 +469,12 @@
         "Offcore": "1",
         "EventCode": "0xB7, 0xBB",
         "UMask": "0x1",
-        "BriefDescription": "Counts all demand code reads that miss in the L3",
-        "MSRValue": "0x3fbfc00004",
+        "BriefDescription": "Counts all demand code reads miss in the L3",
+        "MSRValue": "0x3FBFC00004",
         "Counter": "0,1,2,3",
         "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.LLC_MISS.ANY_RESPONSE",
         "MSRIndex": "0x1a6,0x1a7",
-        "PublicDescription": "Counts all demand code reads that miss in the L3 Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all demand code reads miss in the L3",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -482,12 +482,12 @@
         "Offcore": "1",
         "EventCode": "0xB7, 0xBB",
         "UMask": "0x1",
-        "BriefDescription": "Counts all demand code reads that miss the L3 and the data is returned from local dram",
+        "BriefDescription": "Counts all demand code reads miss the L3 and the data is returned from local dram",
         "MSRValue": "0x0600400004",
         "Counter": "0,1,2,3",
         "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.LLC_MISS.LOCAL_DRAM",
         "MSRIndex": "0x1a6,0x1a7",
-        "PublicDescription": "Counts all demand code reads that miss the L3 and the data is returned from local dram Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all demand code reads miss the L3 and the data is returned from local dram",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -495,12 +495,12 @@
         "Offcore": "1",
         "EventCode": "0xB7, 0xBB",
         "UMask": "0x1",
-        "BriefDescription": "Counts prefetch (that bring data to L2) data reads that miss in the L3",
-        "MSRValue": "0x3fbfc00010",
+        "BriefDescription": "Counts prefetch (that bring data to L2) data reads miss in the L3",
+        "MSRValue": "0x3FBFC00010",
         "Counter": "0,1,2,3",
         "EventName": "OFFCORE_RESPONSE.PF_L2_DATA_RD.LLC_MISS.ANY_RESPONSE",
         "MSRIndex": "0x1a6,0x1a7",
-        "PublicDescription": "Counts prefetch (that bring data to L2) data reads that miss in the L3 Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts prefetch (that bring data to L2) data reads miss in the L3",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -508,12 +508,12 @@
         "Offcore": "1",
         "EventCode": "0xB7, 0xBB",
         "UMask": "0x1",
-        "BriefDescription": "Counts all prefetch (that bring data to L2) RFOs that miss in the L3",
-        "MSRValue": "0x3fbfc00020",
+        "BriefDescription": "Counts all prefetch (that bring data to L2) RFOs miss in the L3",
+        "MSRValue": "0x3FBFC00020",
         "Counter": "0,1,2,3",
         "EventName": "OFFCORE_RESPONSE.PF_L2_RFO.LLC_MISS.ANY_RESPONSE",
         "MSRIndex": "0x1a6,0x1a7",
-        "PublicDescription": "Counts all prefetch (that bring data to L2) RFOs that miss in the L3 Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all prefetch (that bring data to L2) RFOs miss in the L3",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -521,12 +521,12 @@
         "Offcore": "1",
         "EventCode": "0xB7, 0xBB",
         "UMask": "0x1",
-        "BriefDescription": "Counts all prefetch (that bring data to LLC only) code reads that miss in the L3",
-        "MSRValue": "0x3fbfc00040",
+        "BriefDescription": "Counts all prefetch (that bring data to LLC only) code reads miss in the L3",
+        "MSRValue": "0x3FBFC00040",
         "Counter": "0,1,2,3",
         "EventName": "OFFCORE_RESPONSE.PF_L2_CODE_RD.LLC_MISS.ANY_RESPONSE",
         "MSRIndex": "0x1a6,0x1a7",
-        "PublicDescription": "Counts all prefetch (that bring data to LLC only) code reads that miss in the L3 Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all prefetch (that bring data to LLC only) code reads miss in the L3",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -534,12 +534,12 @@
         "Offcore": "1",
         "EventCode": "0xB7, 0xBB",
         "UMask": "0x1",
-        "BriefDescription": "Counts all prefetch (that bring data to LLC only) data reads that miss in the L3",
-        "MSRValue": "0x3fbfc00080",
+        "BriefDescription": "Counts all prefetch (that bring data to LLC only) data reads miss in the L3",
+        "MSRValue": "0x3FBFC00080",
         "Counter": "0,1,2,3",
         "EventName": "OFFCORE_RESPONSE.PF_LLC_DATA_RD.LLC_MISS.ANY_RESPONSE",
         "MSRIndex": "0x1a6,0x1a7",
-        "PublicDescription": "Counts all prefetch (that bring data to LLC only) data reads that miss in the L3 Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all prefetch (that bring data to LLC only) data reads miss in the L3",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -547,12 +547,12 @@
         "Offcore": "1",
         "EventCode": "0xB7, 0xBB",
         "UMask": "0x1",
-        "BriefDescription": "Counts all prefetch (that bring data to LLC only) RFOs that miss in the L3",
-        "MSRValue": "0x3fbfc00100",
+        "BriefDescription": "Counts all prefetch (that bring data to LLC only) RFOs miss in the L3",
+        "MSRValue": "0x3FBFC00100",
         "Counter": "0,1,2,3",
         "EventName": "OFFCORE_RESPONSE.PF_LLC_RFO.LLC_MISS.ANY_RESPONSE",
         "MSRIndex": "0x1a6,0x1a7",
-        "PublicDescription": "Counts all prefetch (that bring data to LLC only) RFOs that miss in the L3 Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all prefetch (that bring data to LLC only) RFOs miss in the L3",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -560,12 +560,12 @@
         "Offcore": "1",
         "EventCode": "0xB7, 0xBB",
         "UMask": "0x1",
-        "BriefDescription": "Counts prefetch (that bring data to LLC only) code reads that miss in the L3",
-        "MSRValue": "0x3fbfc00200",
+        "BriefDescription": "Counts prefetch (that bring data to LLC only) code reads miss in the L3",
+        "MSRValue": "0x3FBFC00200",
         "Counter": "0,1,2,3",
         "EventName": "OFFCORE_RESPONSE.PF_LLC_CODE_RD.LLC_MISS.ANY_RESPONSE",
         "MSRIndex": "0x1a6,0x1a7",
-        "PublicDescription": "Counts prefetch (that bring data to LLC only) code reads that miss in the L3 Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts prefetch (that bring data to LLC only) code reads miss in the L3",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -573,12 +573,12 @@
         "Offcore": "1",
         "EventCode": "0xB7, 0xBB",
         "UMask": "0x1",
-        "BriefDescription": "Counts all demand & prefetch data reads that miss in the L3",
-        "MSRValue": "0x3fbfc00091",
+        "BriefDescription": "Counts all demand & prefetch data reads miss in the L3",
+        "MSRValue": "0x3FBFC00091",
         "Counter": "0,1,2,3",
         "EventName": "OFFCORE_RESPONSE.ALL_DATA_RD.LLC_MISS.ANY_RESPONSE",
         "MSRIndex": "0x1a6,0x1a7",
-        "PublicDescription": "Counts all demand & prefetch data reads that miss in the L3 Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all demand & prefetch data reads miss in the L3",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -586,12 +586,12 @@
         "Offcore": "1",
         "EventCode": "0xB7, 0xBB",
         "UMask": "0x1",
-        "BriefDescription": "Counts all demand & prefetch data reads that miss the L3 and the data is returned from local dram",
+        "BriefDescription": "Counts all demand & prefetch data reads miss the L3 and the data is returned from local dram",
         "MSRValue": "0x0600400091",
         "Counter": "0,1,2,3",
         "EventName": "OFFCORE_RESPONSE.ALL_DATA_RD.LLC_MISS.LOCAL_DRAM",
         "MSRIndex": "0x1a6,0x1a7",
-        "PublicDescription": "Counts all demand & prefetch data reads that miss the L3 and the data is returned from local dram Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all demand & prefetch data reads miss the L3 and the data is returned from local dram",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -599,12 +599,12 @@
         "Offcore": "1",
         "EventCode": "0xB7, 0xBB",
         "UMask": "0x1",
-        "BriefDescription": "Counts all demand & prefetch data reads that miss the L3 and the data is returned from remote dram",
-        "MSRValue": "0x063f800091",
+        "BriefDescription": "Counts all demand & prefetch data reads miss the L3 and the data is returned from remote dram",
+        "MSRValue": "0x063F800091",
         "Counter": "0,1,2,3",
         "EventName": "OFFCORE_RESPONSE.ALL_DATA_RD.LLC_MISS.REMOTE_DRAM",
         "MSRIndex": "0x1a6,0x1a7",
-        "PublicDescription": "Counts all demand & prefetch data reads that miss the L3 and the data is returned from remote dram Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all demand & prefetch data reads miss the L3 and the data is returned from remote dram",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -612,12 +612,12 @@
         "Offcore": "1",
         "EventCode": "0xB7, 0xBB",
         "UMask": "0x1",
-        "BriefDescription": "Counts all demand & prefetch data reads that miss the L3 and the modified data is transferred from remote cache",
-        "MSRValue": "0x103fc00091",
+        "BriefDescription": "Counts all demand & prefetch data reads miss the L3 and the modified data is transferred from remote cache",
+        "MSRValue": "0x103FC00091",
         "Counter": "0,1,2,3",
         "EventName": "OFFCORE_RESPONSE.ALL_DATA_RD.LLC_MISS.REMOTE_HITM",
         "MSRIndex": "0x1a6,0x1a7",
-        "PublicDescription": "Counts all demand & prefetch data reads that miss the L3 and the modified data is transferred from remote cache Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all demand & prefetch data reads miss the L3 and the modified data is transferred from remote cache",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -625,12 +625,12 @@
         "Offcore": "1",
         "EventCode": "0xB7, 0xBB",
         "UMask": "0x1",
-        "BriefDescription": "Counts all demand & prefetch data reads that miss the L3 and clean or shared data is transferred from remote cache",
-        "MSRValue": "0x083fc00091",
+        "BriefDescription": "Counts all demand & prefetch data reads miss the L3 and clean or shared data is transferred from remote cache",
+        "MSRValue": "0x083FC00091",
         "Counter": "0,1,2,3",
         "EventName": "OFFCORE_RESPONSE.ALL_DATA_RD.LLC_MISS.REMOTE_HIT_FORWARD",
         "MSRIndex": "0x1a6,0x1a7",
-        "PublicDescription": "Counts all demand & prefetch data reads that miss the L3 and clean or shared data is transferred from remote cache Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all demand & prefetch data reads miss the L3 and clean or shared data is transferred from remote cache",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -638,12 +638,12 @@
         "Offcore": "1",
         "EventCode": "0xB7, 0xBB",
         "UMask": "0x1",
-        "BriefDescription": "Counts all demand & prefetch RFOs that miss in the L3",
-        "MSRValue": "0x3fbfc00122",
+        "BriefDescription": "Counts all demand & prefetch RFOs miss in the L3",
+        "MSRValue": "0x3FBFC00122",
         "Counter": "0,1,2,3",
         "EventName": "OFFCORE_RESPONSE.ALL_RFO.LLC_MISS.ANY_RESPONSE",
         "MSRIndex": "0x1a6,0x1a7",
-        "PublicDescription": "Counts all demand & prefetch RFOs that miss in the L3 Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all demand & prefetch RFOs miss in the L3",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -651,12 +651,12 @@
         "Offcore": "1",
         "EventCode": "0xB7, 0xBB",
         "UMask": "0x1",
-        "BriefDescription": "Counts all demand & prefetch RFOs that miss the L3 and the data is returned from local dram",
+        "BriefDescription": "Counts all demand & prefetch RFOs miss the L3 and the data is returned from local dram",
         "MSRValue": "0x0600400122",
         "Counter": "0,1,2,3",
         "EventName": "OFFCORE_RESPONSE.ALL_RFO.LLC_MISS.LOCAL_DRAM",
         "MSRIndex": "0x1a6,0x1a7",
-        "PublicDescription": "Counts all demand & prefetch RFOs that miss the L3 and the data is returned from local dram Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all demand & prefetch RFOs miss the L3 and the data is returned from local dram",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -664,12 +664,12 @@
         "Offcore": "1",
         "EventCode": "0xB7, 0xBB",
         "UMask": "0x1",
-        "BriefDescription": "Counts all demand & prefetch code reads that miss in the L3",
-        "MSRValue": "0x3fbfc00244",
+        "BriefDescription": "Counts all demand & prefetch code reads miss in the L3",
+        "MSRValue": "0x3FBFC00244",
         "Counter": "0,1,2,3",
         "EventName": "OFFCORE_RESPONSE.ALL_CODE_RD.LLC_MISS.ANY_RESPONSE",
         "MSRIndex": "0x1a6,0x1a7",
-        "PublicDescription": "Counts all demand & prefetch code reads that miss in the L3 Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all demand & prefetch code reads miss in the L3",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -677,12 +677,12 @@
         "Offcore": "1",
         "EventCode": "0xB7, 0xBB",
         "UMask": "0x1",
-        "BriefDescription": "Counts all demand & prefetch code reads that miss the L3 and the data is returned from local dram",
+        "BriefDescription": "Counts all demand & prefetch code reads miss the L3 and the data is returned from local dram",
         "MSRValue": "0x0600400244",
         "Counter": "0,1,2,3",
         "EventName": "OFFCORE_RESPONSE.ALL_CODE_RD.LLC_MISS.LOCAL_DRAM",
         "MSRIndex": "0x1a6,0x1a7",
-        "PublicDescription": "Counts all demand & prefetch code reads that miss the L3 and the data is returned from local dram Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all demand & prefetch code reads miss the L3 and the data is returned from local dram",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -690,12 +690,12 @@
         "Offcore": "1",
         "EventCode": "0xB7, 0xBB",
         "UMask": "0x1",
-        "BriefDescription": "Counts all data/code/rfo reads (demand & prefetch) that miss in the L3",
-        "MSRValue": "0x3fbfc007f7",
+        "BriefDescription": "Counts all data/code/rfo reads (demand & prefetch) miss in the L3",
+        "MSRValue": "0x3FBFC007F7",
         "Counter": "0,1,2,3",
         "EventName": "OFFCORE_RESPONSE.ALL_READS.LLC_MISS.ANY_RESPONSE",
         "MSRIndex": "0x1a6,0x1a7",
-        "PublicDescription": "Counts all data/code/rfo reads (demand & prefetch) that miss in the L3 Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all data/code/rfo reads (demand & prefetch) miss in the L3",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -703,12 +703,12 @@
         "Offcore": "1",
         "EventCode": "0xB7, 0xBB",
         "UMask": "0x1",
-        "BriefDescription": "Counts all data/code/rfo reads (demand & prefetch) that miss the L3 and the data is returned from local dram",
-        "MSRValue": "0x06004007f7",
+        "BriefDescription": "Counts all data/code/rfo reads (demand & prefetch) miss the L3 and the data is returned from local dram",
+        "MSRValue": "0x06004007F7",
         "Counter": "0,1,2,3",
         "EventName": "OFFCORE_RESPONSE.ALL_READS.LLC_MISS.LOCAL_DRAM",
         "MSRIndex": "0x1a6,0x1a7",
-        "PublicDescription": "Counts all data/code/rfo reads (demand & prefetch) that miss the L3 and the data is returned from local dram Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all data/code/rfo reads (demand & prefetch) miss the L3 and the data is returned from local dram",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -716,12 +716,12 @@
         "Offcore": "1",
         "EventCode": "0xB7, 0xBB",
         "UMask": "0x1",
-        "BriefDescription": "Counts all data/code/rfo reads (demand & prefetch) that miss the L3 and the data is returned from remote dram",
-        "MSRValue": "0x063f8007f7",
+        "BriefDescription": "Counts all data/code/rfo reads (demand & prefetch) miss the L3 and the data is returned from remote dram",
+        "MSRValue": "0x063F8007F7",
         "Counter": "0,1,2,3",
         "EventName": "OFFCORE_RESPONSE.ALL_READS.LLC_MISS.REMOTE_DRAM",
         "MSRIndex": "0x1a6,0x1a7",
-        "PublicDescription": "Counts all data/code/rfo reads (demand & prefetch) that miss the L3 and the data is returned from remote dram Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all data/code/rfo reads (demand & prefetch) miss the L3 and the data is returned from remote dram",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -729,12 +729,12 @@
         "Offcore": "1",
         "EventCode": "0xB7, 0xBB",
         "UMask": "0x1",
-        "BriefDescription": "Counts all data/code/rfo reads (demand & prefetch) that miss the L3 and the modified data is transferred from remote cache",
-        "MSRValue": "0x103fc007f7",
+        "BriefDescription": "Counts all data/code/rfo reads (demand & prefetch) miss the L3 and the modified data is transferred from remote cache",
+        "MSRValue": "0x103FC007F7",
         "Counter": "0,1,2,3",
         "EventName": "OFFCORE_RESPONSE.ALL_READS.LLC_MISS.REMOTE_HITM",
         "MSRIndex": "0x1a6,0x1a7",
-        "PublicDescription": "Counts all data/code/rfo reads (demand & prefetch) that miss the L3 and the modified data is transferred from remote cache Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all data/code/rfo reads (demand & prefetch) miss the L3 and the modified data is transferred from remote cache",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -742,12 +742,12 @@
         "Offcore": "1",
         "EventCode": "0xB7, 0xBB",
         "UMask": "0x1",
-        "BriefDescription": "Counts all data/code/rfo reads (demand & prefetch) that miss the L3 and clean or shared data is transferred from remote cache",
-        "MSRValue": "0x083fc007f7",
+        "BriefDescription": "Counts all data/code/rfo reads (demand & prefetch) miss the L3 and clean or shared data is transferred from remote cache",
+        "MSRValue": "0x083FC007F7",
         "Counter": "0,1,2,3",
         "EventName": "OFFCORE_RESPONSE.ALL_READS.LLC_MISS.REMOTE_HIT_FORWARD",
         "MSRIndex": "0x1a6,0x1a7",
-        "PublicDescription": "Counts all data/code/rfo reads (demand & prefetch) that miss the L3 and clean or shared data is transferred from remote cache Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all data/code/rfo reads (demand & prefetch) miss the L3 and clean or shared data is transferred from remote cache",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -755,12 +755,12 @@
         "Offcore": "1",
         "EventCode": "0xB7, 0xBB",
         "UMask": "0x1",
-        "BriefDescription": "Counts all requests that miss in the L3",
-        "MSRValue": "0x3fbfc08fff",
+        "BriefDescription": "Counts all requests miss in the L3",
+        "MSRValue": "0x3FBFC08FFF",
         "Counter": "0,1,2,3",
         "EventName": "OFFCORE_RESPONSE.ALL_REQUESTS.LLC_MISS.ANY_RESPONSE",
         "MSRIndex": "0x1a6,0x1a7",
-        "PublicDescription": "Counts all requests that miss in the L3 Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts all requests miss in the L3",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     }
diff --git a/tools/perf/pmu-events/arch/x86/haswellx/pipeline.json b/tools/perf/pmu-events/arch/x86/haswellx/pipeline.json
index 8a18bfe9e3e4..26f2888341ee 100644
--- a/tools/perf/pmu-events/arch/x86/haswellx/pipeline.json
+++ b/tools/perf/pmu-events/arch/x86/haswellx/pipeline.json
@@ -1,6 +1,5 @@
 [
     {
-        "EventCode": "0x00",
         "UMask": "0x1",
         "BriefDescription": "Instructions retired from execution.",
         "Counter": "Fixed counter 0",
@@ -11,7 +10,6 @@
         "CounterHTOff": "Fixed counter 0"
     },
     {
-        "EventCode": "0x00",
         "UMask": "0x2",
         "BriefDescription": "Core cycles when the thread is not in halt state.",
         "Counter": "Fixed counter 1",
@@ -21,7 +19,6 @@
         "CounterHTOff": "Fixed counter 1"
     },
     {
-        "EventCode": "0x00",
         "UMask": "0x2",
         "BriefDescription": "Core cycles when at least one thread on the physical core is not in halt state.",
         "Counter": "Fixed counter 1",
@@ -31,7 +28,6 @@
         "CounterHTOff": "Fixed counter 1"
     },
     {
-        "EventCode": "0x00",
         "UMask": "0x3",
         "BriefDescription": "Reference cycles when the core is not in halt state.",
         "Counter": "Fixed counter 2",
@@ -1098,6 +1094,7 @@
         "PEBS": "1",
         "Counter": "0,1,2,3",
         "EventName": "UOPS_RETIRED.ALL",
+        "PublicDescription": "Counts the number of micro-ops retired. Use Cmask=1 and invert to count active cycles or stalled cycles.",
         "SampleAfterValue": "2000003",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
@@ -1142,6 +1139,7 @@
         "PEBS": "1",
         "Counter": "0,1,2,3",
         "EventName": "UOPS_RETIRED.RETIRE_SLOTS",
+        "PublicDescription": "This event counts the number of retirement slots used each cycle.  There are potentially 4 slots that can be used each cycle - meaning, 4 uops or 4 instructions could retire each cycle.",
         "SampleAfterValue": "2000003",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
@@ -1201,6 +1199,7 @@
         "PEBS": "1",
         "Counter": "0,1,2,3",
         "EventName": "BR_INST_RETIRED.CONDITIONAL",
+        "PublicDescription": "Counts the number of conditional branch instructions retired.",
         "SampleAfterValue": "400009",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
@@ -1241,6 +1240,7 @@
         "PEBS": "1",
         "Counter": "0,1,2,3",
         "EventName": "BR_INST_RETIRED.NEAR_RETURN",
+        "PublicDescription": "Counts the number of near return instructions retired.",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
@@ -1261,6 +1261,7 @@
         "PEBS": "1",
         "Counter": "0,1,2,3",
         "EventName": "BR_INST_RETIRED.NEAR_TAKEN",
+        "PublicDescription": "Number of near taken branches retired.",
         "SampleAfterValue": "400009",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
@@ -1312,6 +1313,7 @@
         "PEBS": "1",
         "Counter": "0,1,2,3",
         "EventName": "BR_MISP_RETIRED.NEAR_TAKEN",
+        "PublicDescription": "Number of near branch instructions retired that were taken but mispredicted.",
         "SampleAfterValue": "400009",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
diff --git a/tools/perf/pmu-events/arch/x86/ivybridge/cache.json b/tools/perf/pmu-events/arch/x86/ivybridge/cache.json
index 999a01bc6467..5f6cb2abc384 100644
--- a/tools/perf/pmu-events/arch/x86/ivybridge/cache.json
+++ b/tools/perf/pmu-events/arch/x86/ivybridge/cache.json
@@ -1012,7 +1012,7 @@
         "EventName": "OFFCORE_RESPONSE.SPLIT_LOCK_UC_LOCK.ANY_RESPONSE",
         "MSRIndex": "0x1a6,0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "Counts requests where the address of an atomic lock instruction spans a cache line boundary or the lock instruction is executed on uncacheable address ",
+        "BriefDescription": "Counts requests where the address of an atomic lock instruction spans a cache line boundary or the lock instruction is executed on uncacheable address",
         "CounterHTOff": "0,1,2,3"
     },
     {
@@ -1036,7 +1036,7 @@
         "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.ANY_RESPONSE",
         "MSRIndex": "0x1a6,0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "Counts all demand data reads ",
+        "BriefDescription": "Counts all demand data reads",
         "CounterHTOff": "0,1,2,3"
     },
     {
@@ -1048,7 +1048,7 @@
         "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.ANY_RESPONSE",
         "MSRIndex": "0x1a6,0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "Counts all demand rfo's ",
+        "BriefDescription": "Counts all demand rfo's",
         "CounterHTOff": "0,1,2,3"
     },
     {
@@ -1084,7 +1084,7 @@
         "EventName": "OFFCORE_RESPONSE.ALL_RFO.ANY_RESPONSE",
         "MSRIndex": "0x1a6,0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "Counts all demand & prefetch prefetch RFOs ",
+        "BriefDescription": "Counts all demand & prefetch prefetch RFOs",
         "CounterHTOff": "0,1,2,3"
     },
     {
@@ -1096,7 +1096,7 @@
         "EventName": "OFFCORE_RESPONSE.ALL_READS.ANY_RESPONSE",
         "MSRIndex": "0x1a6,0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "Counts all data/code/rfo references (demand & prefetch) ",
+        "BriefDescription": "Counts all data/code/rfo references (demand & prefetch)",
         "CounterHTOff": "0,1,2,3"
     }
 ]
\ No newline at end of file
diff --git a/tools/perf/pmu-events/arch/x86/ivybridge/ivb-metrics.json b/tools/perf/pmu-events/arch/x86/ivybridge/ivb-metrics.json
index 7c2679514efb..bc4d5fc284a0 100644
--- a/tools/perf/pmu-events/arch/x86/ivybridge/ivb-metrics.json
+++ b/tools/perf/pmu-events/arch/x86/ivybridge/ivb-metrics.json
@@ -1,164 +1,340 @@
 [
     {
-        "BriefDescription": "Instructions Per Cycle (per logical thread)",
+        "MetricExpr": "IDQ_UOPS_NOT_DELIVERED.CORE / (4 * cycles)",
+        "PublicDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend. Frontend denotes the first part of the processor core responsible to fetch operations that are executed later on by the Backend part. Within the Frontend; a branch predictor predicts the next address to fetch; cache-lines are fetched from the memory subsystem; parsed into instructions; and lastly decoded into micro-ops (uops). Ideally the Frontend can issue 4 uops every cycle to the Backend. Frontend Bound denotes unutilized issue-slots when there is no Backend stall; i.e. bubbles where Frontend delivered no uops while Backend could have accepted them. For example; stalls due to instruction-cache misses would be categorized under Frontend Bound.",
+        "BriefDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend",
+        "MetricGroup": "TopdownL1",
+        "MetricName": "Frontend_Bound"
+    },
+    {
+        "MetricExpr": "IDQ_UOPS_NOT_DELIVERED.CORE / (4 * (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )))",
+        "PublicDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend. Frontend denotes the first part of the processor core responsible to fetch operations that are executed later on by the Backend part. Within the Frontend; a branch predictor predicts the next address to fetch; cache-lines are fetched from the memory subsystem; parsed into instructions; and lastly decoded into micro-ops (uops). Ideally the Frontend can issue 4 uops every cycle to the Backend. Frontend Bound denotes unutilized issue-slots when there is no Backend stall; i.e. bubbles where Frontend delivered no uops while Backend could have accepted them. For example; stalls due to instruction-cache misses would be categorized under Frontend Bound. SMT version; use when SMT is enabled and measuring per logical CPU.",
+        "BriefDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend. SMT version; use when SMT is enabled and measuring per logical CPU.",
+        "MetricGroup": "TopdownL1_SMT",
+        "MetricName": "Frontend_Bound_SMT"
+    },
+    {
+        "MetricExpr": "( UOPS_ISSUED.ANY - UOPS_RETIRED.RETIRE_SLOTS + 4 * INT_MISC.RECOVERY_CYCLES ) / (4 * cycles)",
+        "PublicDescription": "This category represents fraction of slots wasted due to incorrect speculations. This include slots used to issue uops that do not eventually get retired and slots for which the issue-pipeline was blocked due to recovery from earlier incorrect speculation. For example; wasted work due to miss-predicted branches are categorized under Bad Speculation category. Incorrect data speculation followed by Memory Ordering Nukes is another example.",
+        "BriefDescription": "This category represents fraction of slots wasted due to incorrect speculations",
+        "MetricGroup": "TopdownL1",
+        "MetricName": "Bad_Speculation"
+    },
+    {
+        "MetricExpr": "( UOPS_ISSUED.ANY - UOPS_RETIRED.RETIRE_SLOTS + 4 * (( INT_MISC.RECOVERY_CYCLES_ANY / 2 )) ) / (4 * (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )))",
+        "PublicDescription": "This category represents fraction of slots wasted due to incorrect speculations. This include slots used to issue uops that do not eventually get retired and slots for which the issue-pipeline was blocked due to recovery from earlier incorrect speculation. For example; wasted work due to miss-predicted branches are categorized under Bad Speculation category. Incorrect data speculation followed by Memory Ordering Nukes is another example. SMT version; use when SMT is enabled and measuring per logical CPU.",
+        "BriefDescription": "This category represents fraction of slots wasted due to incorrect speculations. SMT version; use when SMT is enabled and measuring per logical CPU.",
+        "MetricGroup": "TopdownL1_SMT",
+        "MetricName": "Bad_Speculation_SMT"
+    },
+    {
+        "MetricExpr": "1 - ( (IDQ_UOPS_NOT_DELIVERED.CORE / (4 * cycles)) + (( UOPS_ISSUED.ANY - UOPS_RETIRED.RETIRE_SLOTS + 4 * INT_MISC.RECOVERY_CYCLES ) / (4 * cycles)) + (UOPS_RETIRED.RETIRE_SLOTS / (4 * cycles)) )",
+        "PublicDescription": "This category represents fraction of slots where no uops are being delivered due to a lack of required resources for accepting new uops in the Backend. Backend is the portion of the processor core where the out-of-order scheduler dispatches ready uops into their respective execution units; and once completed these uops get retired according to program order. For example; stalls due to data-cache misses or stalls due to the divider unit being overloaded are both categorized under Backend Bound. Backend Bound is further divided into two main categories: Memory Bound and Core Bound.",
+        "BriefDescription": "This category represents fraction of slots where no uops are being delivered due to a lack of required resources for accepting new uops in the Backend",
+        "MetricGroup": "TopdownL1",
+        "MetricName": "Backend_Bound"
+    },
+    {
+        "MetricExpr": "1 - ( (IDQ_UOPS_NOT_DELIVERED.CORE / (4 * (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )))) + (( UOPS_ISSUED.ANY - UOPS_RETIRED.RETIRE_SLOTS + 4 * (( INT_MISC.RECOVERY_CYCLES_ANY / 2 )) ) / (4 * (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )))) + (UOPS_RETIRED.RETIRE_SLOTS / (4 * (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )))) )",
+        "PublicDescription": "This category represents fraction of slots where no uops are being delivered due to a lack of required resources for accepting new uops in the Backend. Backend is the portion of the processor core where the out-of-order scheduler dispatches ready uops into their respective execution units; and once completed these uops get retired according to program order. For example; stalls due to data-cache misses or stalls due to the divider unit being overloaded are both categorized under Backend Bound. Backend Bound is further divided into two main categories: Memory Bound and Core Bound. SMT version; use when SMT is enabled and measuring per logical CPU.",
+        "BriefDescription": "This category represents fraction of slots where no uops are being delivered due to a lack of required resources for accepting new uops in the Backend. SMT version; use when SMT is enabled and measuring per logical CPU.",
+        "MetricGroup": "TopdownL1_SMT",
+        "MetricName": "Backend_Bound_SMT"
+    },
+    {
+        "MetricExpr": "UOPS_RETIRED.RETIRE_SLOTS / (4 * cycles)",
+        "PublicDescription": "This category represents fraction of slots utilized by useful work i.e. issued uops that eventually get retired. Ideally; all pipeline slots would be attributed to the Retiring category.  Retiring of 100% would indicate the maximum 4 uops retired per cycle has been achieved.  Maximizing Retiring typically increases the Instruction-Per-Cycle metric. Note that a high Retiring value does not necessary mean there is no room for more performance.  For example; Microcode assists are categorized under Retiring. They hurt performance and can often be avoided. ",
+        "BriefDescription": "This category represents fraction of slots utilized by useful work i.e. issued uops that eventually get retired",
+        "MetricGroup": "TopdownL1",
+        "MetricName": "Retiring"
+    },
+    {
+        "MetricExpr": "UOPS_RETIRED.RETIRE_SLOTS / (4 * (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )))",
+        "PublicDescription": "This category represents fraction of slots utilized by useful work i.e. issued uops that eventually get retired. Ideally; all pipeline slots would be attributed to the Retiring category.  Retiring of 100% would indicate the maximum 4 uops retired per cycle has been achieved.  Maximizing Retiring typically increases the Instruction-Per-Cycle metric. Note that a high Retiring value does not necessary mean there is no room for more performance.  For example; Microcode assists are categorized under Retiring. They hurt performance and can often be avoided. SMT version; use when SMT is enabled and measuring per logical CPU.",
+        "BriefDescription": "This category represents fraction of slots utilized by useful work i.e. issued uops that eventually get retired. SMT version; use when SMT is enabled and measuring per logical CPU.",
+        "MetricGroup": "TopdownL1_SMT",
+        "MetricName": "Retiring_SMT"
+    },
+    {
         "MetricExpr": "INST_RETIRED.ANY / CPU_CLK_UNHALTED.THREAD",
+        "BriefDescription": "Instructions Per Cycle (per logical thread)",
         "MetricGroup": "TopDownL1",
         "MetricName": "IPC"
     },
     {
-        "BriefDescription": "Uops Per Instruction",
         "MetricExpr": "UOPS_RETIRED.RETIRE_SLOTS / INST_RETIRED.ANY",
-        "MetricGroup": "Pipeline",
+        "BriefDescription": "Uops Per Instruction",
+        "MetricGroup": "Pipeline;Retiring",
         "MetricName": "UPI"
     },
     {
-        "BriefDescription": "Rough Estimation of fraction of fetched lines bytes that were likely consumed by program instructions",
-        "MetricExpr": "min( 1 , UOPS_ISSUED.ANY / ( (UOPS_RETIRED.RETIRE_SLOTS / INST_RETIRED.ANY) * 32 * ( ICACHE.HIT + ICACHE.MISSES ) / 4) )",
-        "MetricGroup": "Frontend",
+        "MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.NEAR_TAKEN",
+        "BriefDescription": "Instruction per taken branch",
+        "MetricGroup": "Branches;PGO",
+        "MetricName": "IpTB"
+    },
+    {
+        "MetricExpr": "BR_INST_RETIRED.ALL_BRANCHES / BR_INST_RETIRED.NEAR_TAKEN",
+        "BriefDescription": "Branch instructions per taken branch. ",
+        "MetricGroup": "Branches;PGO",
+        "MetricName": "BpTB"
+    },
+    {
+        "MetricExpr": "min( 1 , UOPS_ISSUED.ANY / ( (UOPS_RETIRED.RETIRE_SLOTS / INST_RETIRED.ANY) * 32 * ( ICACHE.HIT + ICACHE.MISSES ) / 4 ) )",
+        "BriefDescription": "Rough Estimation of fraction of fetched lines bytes that were likely (includes speculatively fetches) consumed by program instructions",
+        "MetricGroup": "PGO",
         "MetricName": "IFetch_Line_Utilization"
     },
     {
-        "BriefDescription": "Fraction of Uops delivered by the DSB (aka Decoded Icache; or Uop Cache)",
-        "MetricExpr": "IDQ.DSB_UOPS / ( IDQ.DSB_UOPS + LSD.UOPS + IDQ.MITE_UOPS + IDQ.MS_UOPS )",
-        "MetricGroup": "DSB; Frontend_Bandwidth",
+        "MetricExpr": "IDQ.DSB_UOPS / (( IDQ.DSB_UOPS + LSD.UOPS + IDQ.MITE_UOPS + IDQ.MS_UOPS ) )",
+        "BriefDescription": "Fraction of Uops delivered by the DSB (aka Decoded ICache; or Uop Cache)",
+        "MetricGroup": "DSB;Frontend_Bandwidth",
         "MetricName": "DSB_Coverage"
     },
     {
-        "BriefDescription": "Cycles Per Instruction (threaded)",
         "MetricExpr": "1 / (INST_RETIRED.ANY / cycles)",
+        "BriefDescription": "Cycles Per Instruction (threaded)",
         "MetricGroup": "Pipeline;Summary",
         "MetricName": "CPI"
     },
     {
-        "BriefDescription": "Per-thread actual clocks when the logical processor is active. This is called 'Clockticks' in VTune.",
         "MetricExpr": "CPU_CLK_UNHALTED.THREAD",
+        "BriefDescription": "Per-thread actual clocks when the logical processor is active.",
         "MetricGroup": "Summary",
         "MetricName": "CLKS"
     },
     {
-        "BriefDescription": "Total issue-pipeline slots",
-        "MetricExpr": "4*(( CPU_CLK_UNHALTED.THREAD_ANY / 2 ) if #SMT_on else cycles)",
+        "MetricExpr": "4 * cycles",
+        "BriefDescription": "Total issue-pipeline slots (per core)",
         "MetricGroup": "TopDownL1",
         "MetricName": "SLOTS"
     },
     {
-        "BriefDescription": "Total number of retired Instructions",
+        "MetricExpr": "4 * (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) ))",
+        "BriefDescription": "Total issue-pipeline slots (per core)",
+        "MetricGroup": "TopDownL1_SMT",
+        "MetricName": "SLOTS_SMT"
+    },
+    {
+        "MetricExpr": "INST_RETIRED.ANY / MEM_UOPS_RETIRED.ALL_LOADS",
+        "BriefDescription": "Instructions per Load (lower number means loads are more frequent)",
+        "MetricGroup": "Instruction_Type;L1_Bound",
+        "MetricName": "IpL"
+    },
+    {
+        "MetricExpr": "INST_RETIRED.ANY / MEM_UOPS_RETIRED.ALL_STORES",
+        "BriefDescription": "Instructions per Store",
+        "MetricGroup": "Instruction_Type;Store_Bound",
+        "MetricName": "IpS"
+    },
+    {
+        "MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.ALL_BRANCHES",
+        "BriefDescription": "Instructions per Branch",
+        "MetricGroup": "Branches;Instruction_Type;Port_5;Port_6",
+        "MetricName": "IpB"
+    },
+    {
+        "MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.NEAR_CALL",
+        "BriefDescription": "Instruction per (near) call",
+        "MetricGroup": "Branches",
+        "MetricName": "IpCall"
+    },
+    {
         "MetricExpr": "INST_RETIRED.ANY",
+        "BriefDescription": "Total number of retired Instructions",
         "MetricGroup": "Summary",
         "MetricName": "Instructions"
     },
     {
+        "MetricExpr": "INST_RETIRED.ANY / cycles",
         "BriefDescription": "Instructions Per Cycle (per physical core)",
-        "MetricExpr": "INST_RETIRED.ANY / (( CPU_CLK_UNHALTED.THREAD_ANY / 2 ) if #SMT_on else cycles)",
         "MetricGroup": "SMT",
         "MetricName": "CoreIPC"
     },
     {
+        "MetricExpr": "INST_RETIRED.ANY / (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) ))",
+        "BriefDescription": "Instructions Per Cycle (per physical core)",
+        "MetricGroup": "SMT",
+        "MetricName": "CoreIPC_SMT"
+    },
+    {
+        "MetricExpr": "(( 1 * ( FP_COMP_OPS_EXE.SSE_SCALAR_SINGLE + FP_COMP_OPS_EXE.SSE_SCALAR_DOUBLE ) + 2 * FP_COMP_OPS_EXE.SSE_PACKED_DOUBLE + 4 * ( FP_COMP_OPS_EXE.SSE_PACKED_SINGLE + SIMD_FP_256.PACKED_DOUBLE ) + 8 * SIMD_FP_256.PACKED_SINGLE )) / cycles",
+        "BriefDescription": "Floating Point Operations Per Cycle",
+        "MetricGroup": "FLOPS",
+        "MetricName": "FLOPc"
+    },
+    {
+        "MetricExpr": "(( 1 * ( FP_COMP_OPS_EXE.SSE_SCALAR_SINGLE + FP_COMP_OPS_EXE.SSE_SCALAR_DOUBLE ) + 2 * FP_COMP_OPS_EXE.SSE_PACKED_DOUBLE + 4 * ( FP_COMP_OPS_EXE.SSE_PACKED_SINGLE + SIMD_FP_256.PACKED_DOUBLE ) + 8 * SIMD_FP_256.PACKED_SINGLE )) / (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) ))",
+        "BriefDescription": "Floating Point Operations Per Cycle",
+        "MetricGroup": "FLOPS_SMT",
+        "MetricName": "FLOPc_SMT"
+    },
+    {
+        "MetricExpr": "UOPS_EXECUTED.THREAD / (( cpu@UOPS_EXECUTED.CORE\\,cmask\\=1@ / 2 ) if #SMT_on else UOPS_EXECUTED.CYCLES_GE_1_UOP_EXEC)",
         "BriefDescription": "Instruction-Level-Parallelism (average number of uops executed when there is at least 1 uop executed)",
-        "MetricExpr": "UOPS_EXECUTED.THREAD / (( cpu@UOPS_EXECUTED.CORE\\,cmask\\=1@ / 2) if #SMT_on else UOPS_EXECUTED.CYCLES_GE_1_UOP_EXEC)",
         "MetricGroup": "Pipeline;Ports_Utilization",
         "MetricName": "ILP"
     },
     {
-        "BriefDescription": "Average Branch Address Clear Cost (fraction of cycles)",
-        "MetricExpr": "2* (( RS_EVENTS.EMPTY_CYCLES - ICACHE.IFETCH_STALL ) / RS_EVENTS.EMPTY_END)",
-        "MetricGroup": "Unknown_Branches",
-        "MetricName": "BAClear_Cost"
+        "MetricExpr": "INST_RETIRED.ANY / BR_MISP_RETIRED.ALL_BRANCHES",
+        "BriefDescription": "Number of Instructions per non-speculative Branch Misprediction (JEClear)",
+        "MetricGroup": "Branch_Mispredicts",
+        "MetricName": "IpMispredict"
     },
     {
+        "MetricExpr": "( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )",
         "BriefDescription": "Core actual clocks when any thread is active on the physical core",
-        "MetricExpr": "( CPU_CLK_UNHALTED.THREAD_ANY / 2 ) if #SMT_on else CPU_CLK_UNHALTED.THREAD",
         "MetricGroup": "SMT",
         "MetricName": "CORE_CLKS"
     },
     {
-        "BriefDescription": "Actual Average Latency for L1 data-cache miss demand loads",
         "MetricExpr": "L1D_PEND_MISS.PENDING / ( MEM_LOAD_UOPS_RETIRED.L1_MISS + mem_load_uops_retired.hit_lfb )",
+        "BriefDescription": "Actual Average Latency for L1 data-cache miss demand loads (in core cycles)",
         "MetricGroup": "Memory_Bound;Memory_Lat",
         "MetricName": "Load_Miss_Real_Latency"
     },
     {
-        "BriefDescription": "Memory-Level-Parallelism (average number of L1 miss demand load when there is at least 1 such miss)",
-        "MetricExpr": "L1D_PEND_MISS.PENDING / (( cpu@l1d_pend_miss.pending_cycles\\,any\\=1@ / 2) if #SMT_on else L1D_PEND_MISS.PENDING_CYCLES)",
+        "MetricExpr": "L1D_PEND_MISS.PENDING / L1D_PEND_MISS.PENDING_CYCLES",
+        "BriefDescription": "Memory-Level-Parallelism (average number of L1 miss demand load when there is at least one such miss. Per-thread)",
         "MetricGroup": "Memory_Bound;Memory_BW",
         "MetricName": "MLP"
     },
     {
+        "MetricExpr": "( ITLB_MISSES.WALK_DURATION + DTLB_LOAD_MISSES.WALK_DURATION + DTLB_STORE_MISSES.WALK_DURATION ) / cycles",
         "BriefDescription": "Utilization of the core's Page Walker(s) serving STLB misses triggered by instruction/Load/Store accesses",
-        "MetricExpr": "( ITLB_MISSES.WALK_DURATION + DTLB_LOAD_MISSES.WALK_DURATION + DTLB_STORE_MISSES.WALK_DURATION ) / (( CPU_CLK_UNHALTED.THREAD_ANY / 2 ) if #SMT_on else cycles)",
         "MetricGroup": "TLB",
         "MetricName": "Page_Walks_Utilization"
     },
     {
-        "BriefDescription": "Average CPU Utilization",
+        "MetricExpr": "( ITLB_MISSES.WALK_DURATION + DTLB_LOAD_MISSES.WALK_DURATION + DTLB_STORE_MISSES.WALK_DURATION ) / (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) ))",
+        "BriefDescription": "Utilization of the core's Page Walker(s) serving STLB misses triggered by instruction/Load/Store accesses",
+        "MetricGroup": "TLB_SMT",
+        "MetricName": "Page_Walks_Utilization_SMT"
+    },
+    {
+        "MetricExpr": "64 * L1D.REPLACEMENT / 1000000000 / duration_time",
+        "BriefDescription": "Average data fill bandwidth to the L1 data cache [GB / sec]",
+        "MetricGroup": "Memory_BW",
+        "MetricName": "L1D_Cache_Fill_BW"
+    },
+    {
+        "MetricExpr": "64 * L2_LINES_IN.ALL / 1000000000 / duration_time",
+        "BriefDescription": "Average data fill bandwidth to the L2 cache [GB / sec]",
+        "MetricGroup": "Memory_BW",
+        "MetricName": "L2_Cache_Fill_BW"
+    },
+    {
+        "MetricExpr": "64 * LONGEST_LAT_CACHE.MISS / 1000000000 / duration_time",
+        "BriefDescription": "Average per-core data fill bandwidth to the L3 cache [GB / sec]",
+        "MetricGroup": "Memory_BW",
+        "MetricName": "L3_Cache_Fill_BW"
+    },
+    {
+        "MetricExpr": "1000 * MEM_LOAD_UOPS_RETIRED.L1_MISS / INST_RETIRED.ANY",
+        "BriefDescription": "L1 cache true misses per kilo instruction for retired demand loads",
+        "MetricGroup": "Cache_Misses;",
+        "MetricName": "L1MPKI"
+    },
+    {
+        "MetricExpr": "1000 * MEM_LOAD_UOPS_RETIRED.L2_MISS / INST_RETIRED.ANY",
+        "BriefDescription": "L2 cache true misses per kilo instruction for retired demand loads",
+        "MetricGroup": "Cache_Misses;",
+        "MetricName": "L2MPKI"
+    },
+    {
+        "MetricExpr": "1000 * MEM_LOAD_UOPS_RETIRED.L2_MISS / INST_RETIRED.ANY",
+        "BriefDescription": "L2 cache misses per kilo instruction for all request types (including speculative)",
+        "MetricGroup": "Cache_Misses;",
+        "MetricName": "L2MPKI_All"
+    },
+    {
+        "MetricExpr": "1000 * MEM_LOAD_UOPS_RETIRED.L2_MISS / INST_RETIRED.ANY",
+        "BriefDescription": "L2 cache hits per kilo instruction for all request types (including speculative)",
+        "MetricGroup": "Cache_Misses;",
+        "MetricName": "L2HPKI_All"
+    },
+    {
+        "MetricExpr": "1000 * MEM_LOAD_UOPS_RETIRED.LLC_MISS / INST_RETIRED.ANY",
+        "BriefDescription": "L3 cache true misses per kilo instruction for retired demand loads",
+        "MetricGroup": "Cache_Misses;",
+        "MetricName": "L3MPKI"
+    },
+    {
         "MetricExpr": "CPU_CLK_UNHALTED.REF_TSC / msr@tsc@",
+        "BriefDescription": "Average CPU Utilization",
         "MetricGroup": "Summary",
         "MetricName": "CPU_Utilization"
     },
     {
+        "MetricExpr": "( (( 1 * ( FP_COMP_OPS_EXE.SSE_SCALAR_SINGLE + FP_COMP_OPS_EXE.SSE_SCALAR_DOUBLE ) + 2 * FP_COMP_OPS_EXE.SSE_PACKED_DOUBLE + 4 * ( FP_COMP_OPS_EXE.SSE_PACKED_SINGLE + SIMD_FP_256.PACKED_DOUBLE ) + 8 * SIMD_FP_256.PACKED_SINGLE )) / 1000000000 ) / duration_time",
         "BriefDescription": "Giga Floating Point Operations Per Second",
-        "MetricExpr": "(( 1*( FP_COMP_OPS_EXE.SSE_SCALAR_SINGLE + FP_COMP_OPS_EXE.SSE_SCALAR_DOUBLE ) + 2* FP_COMP_OPS_EXE.SSE_PACKED_DOUBLE + 4*( FP_COMP_OPS_EXE.SSE_PACKED_SINGLE + SIMD_FP_256.PACKED_DOUBLE ) + 8* SIMD_FP_256.PACKED_SINGLE )) / 1000000000 / duration_time",
         "MetricGroup": "FLOPS;Summary",
         "MetricName": "GFLOPs"
     },
     {
-        "BriefDescription": "Average Frequency Utilization relative nominal frequency",
         "MetricExpr": "CPU_CLK_UNHALTED.THREAD / CPU_CLK_UNHALTED.REF_TSC",
+        "BriefDescription": "Average Frequency Utilization relative nominal frequency",
         "MetricGroup": "Power",
         "MetricName": "Turbo_Utilization"
     },
     {
-        "BriefDescription": "Fraction of cycles where both hardware threads were active",
         "MetricExpr": "1 - CPU_CLK_THREAD_UNHALTED.ONE_THREAD_ACTIVE / ( CPU_CLK_THREAD_UNHALTED.REF_XCLK_ANY / 2 ) if #SMT_on else 0",
+        "BriefDescription": "Fraction of cycles where both hardware threads were active",
         "MetricGroup": "SMT;Summary",
         "MetricName": "SMT_2T_Utilization"
     },
     {
-        "BriefDescription": "Fraction of cycles spent in Kernel mode",
         "MetricExpr": "CPU_CLK_UNHALTED.REF_TSC:u / CPU_CLK_UNHALTED.REF_TSC",
+        "BriefDescription": "Fraction of cycles spent in Kernel mode",
         "MetricGroup": "Summary",
         "MetricName": "Kernel_Utilization"
     },
     {
-        "BriefDescription": "C3 residency percent per core",
+        "MetricExpr": "64 * ( arb@event\\=0x81\\,umask\\=0x1@ + arb@event\\=0x84\\,umask\\=0x1@ ) / 1000000 / duration_time / 1000",
+        "BriefDescription": "Average external Memory Bandwidth Use for reads and writes [GB / sec]",
+        "MetricGroup": "Memory_BW",
+        "MetricName": "DRAM_BW_Use"
+    },
+    {
         "MetricExpr": "(cstate_core@c3\\-residency@ / msr@tsc@) * 100",
         "MetricGroup": "Power",
+        "BriefDescription": "C3 residency percent per core",
         "MetricName": "C3_Core_Residency"
     },
     {
-        "BriefDescription": "C6 residency percent per core",
         "MetricExpr": "(cstate_core@c6\\-residency@ / msr@tsc@) * 100",
         "MetricGroup": "Power",
+        "BriefDescription": "C6 residency percent per core",
         "MetricName": "C6_Core_Residency"
     },
     {
-        "BriefDescription": "C7 residency percent per core",
         "MetricExpr": "(cstate_core@c7\\-residency@ / msr@tsc@) * 100",
         "MetricGroup": "Power",
+        "BriefDescription": "C7 residency percent per core",
         "MetricName": "C7_Core_Residency"
     },
     {
-        "BriefDescription": "C2 residency percent per package",
         "MetricExpr": "(cstate_pkg@c2\\-residency@ / msr@tsc@) * 100",
         "MetricGroup": "Power",
+        "BriefDescription": "C2 residency percent per package",
         "MetricName": "C2_Pkg_Residency"
     },
     {
-        "BriefDescription": "C3 residency percent per package",
         "MetricExpr": "(cstate_pkg@c3\\-residency@ / msr@tsc@) * 100",
         "MetricGroup": "Power",
+        "BriefDescription": "C3 residency percent per package",
         "MetricName": "C3_Pkg_Residency"
     },
     {
-        "BriefDescription": "C6 residency percent per package",
         "MetricExpr": "(cstate_pkg@c6\\-residency@ / msr@tsc@) * 100",
         "MetricGroup": "Power",
+        "BriefDescription": "C6 residency percent per package",
         "MetricName": "C6_Pkg_Residency"
     },
     {
-        "BriefDescription": "C7 residency percent per package",
         "MetricExpr": "(cstate_pkg@c7\\-residency@ / msr@tsc@) * 100",
         "MetricGroup": "Power",
+        "BriefDescription": "C7 residency percent per package",
         "MetricName": "C7_Pkg_Residency"
     }
 ]
diff --git a/tools/perf/pmu-events/arch/x86/ivybridge/pipeline.json b/tools/perf/pmu-events/arch/x86/ivybridge/pipeline.json
index 0afbfd95ea30..2a0aad91d83d 100644
--- a/tools/perf/pmu-events/arch/x86/ivybridge/pipeline.json
+++ b/tools/perf/pmu-events/arch/x86/ivybridge/pipeline.json
@@ -1,6 +1,5 @@
 [
     {
-        "EventCode": "0x00",
         "Counter": "Fixed counter 0",
         "UMask": "0x1",
         "EventName": "INST_RETIRED.ANY",
@@ -9,7 +8,6 @@
         "CounterHTOff": "Fixed counter 0"
     },
     {
-        "EventCode": "0x00",
         "Counter": "Fixed counter 1",
         "UMask": "0x2",
         "EventName": "CPU_CLK_UNHALTED.THREAD",
@@ -19,7 +17,6 @@
     },
     {
         "PublicDescription": "Core cycles when at least one thread on the physical core is not in halt state.",
-        "EventCode": "0x00",
         "Counter": "Fixed counter 1",
         "UMask": "0x2",
         "AnyThread": "1",
@@ -29,7 +26,6 @@
         "CounterHTOff": "Fixed counter 1"
     },
     {
-        "EventCode": "0x00",
         "Counter": "Fixed counter 2",
         "UMask": "0x3",
         "EventName": "CPU_CLK_UNHALTED.REF_TSC",
diff --git a/tools/perf/pmu-events/arch/x86/ivytown/ivt-metrics.json b/tools/perf/pmu-events/arch/x86/ivytown/ivt-metrics.json
index 7c2679514efb..f3874b5f9995 100644
--- a/tools/perf/pmu-events/arch/x86/ivytown/ivt-metrics.json
+++ b/tools/perf/pmu-events/arch/x86/ivytown/ivt-metrics.json
@@ -1,164 +1,346 @@
 [
     {
-        "BriefDescription": "Instructions Per Cycle (per logical thread)",
+        "MetricExpr": "IDQ_UOPS_NOT_DELIVERED.CORE / (4 * cycles)",
+        "PublicDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend. Frontend denotes the first part of the processor core responsible to fetch operations that are executed later on by the Backend part. Within the Frontend; a branch predictor predicts the next address to fetch; cache-lines are fetched from the memory subsystem; parsed into instructions; and lastly decoded into micro-ops (uops). Ideally the Frontend can issue 4 uops every cycle to the Backend. Frontend Bound denotes unutilized issue-slots when there is no Backend stall; i.e. bubbles where Frontend delivered no uops while Backend could have accepted them. For example; stalls due to instruction-cache misses would be categorized under Frontend Bound.",
+        "BriefDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend",
+        "MetricGroup": "TopdownL1",
+        "MetricName": "Frontend_Bound"
+    },
+    {
+        "MetricExpr": "IDQ_UOPS_NOT_DELIVERED.CORE / (4 * (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )))",
+        "PublicDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend. Frontend denotes the first part of the processor core responsible to fetch operations that are executed later on by the Backend part. Within the Frontend; a branch predictor predicts the next address to fetch; cache-lines are fetched from the memory subsystem; parsed into instructions; and lastly decoded into micro-ops (uops). Ideally the Frontend can issue 4 uops every cycle to the Backend. Frontend Bound denotes unutilized issue-slots when there is no Backend stall; i.e. bubbles where Frontend delivered no uops while Backend could have accepted them. For example; stalls due to instruction-cache misses would be categorized under Frontend Bound. SMT version; use when SMT is enabled and measuring per logical CPU.",
+        "BriefDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend. SMT version; use when SMT is enabled and measuring per logical CPU.",
+        "MetricGroup": "TopdownL1_SMT",
+        "MetricName": "Frontend_Bound_SMT"
+    },
+    {
+        "MetricExpr": "( UOPS_ISSUED.ANY - UOPS_RETIRED.RETIRE_SLOTS + 4 * INT_MISC.RECOVERY_CYCLES ) / (4 * cycles)",
+        "PublicDescription": "This category represents fraction of slots wasted due to incorrect speculations. This include slots used to issue uops that do not eventually get retired and slots for which the issue-pipeline was blocked due to recovery from earlier incorrect speculation. For example; wasted work due to miss-predicted branches are categorized under Bad Speculation category. Incorrect data speculation followed by Memory Ordering Nukes is another example.",
+        "BriefDescription": "This category represents fraction of slots wasted due to incorrect speculations",
+        "MetricGroup": "TopdownL1",
+        "MetricName": "Bad_Speculation"
+    },
+    {
+        "MetricExpr": "( UOPS_ISSUED.ANY - UOPS_RETIRED.RETIRE_SLOTS + 4 * (( INT_MISC.RECOVERY_CYCLES_ANY / 2 )) ) / (4 * (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )))",
+        "PublicDescription": "This category represents fraction of slots wasted due to incorrect speculations. This include slots used to issue uops that do not eventually get retired and slots for which the issue-pipeline was blocked due to recovery from earlier incorrect speculation. For example; wasted work due to miss-predicted branches are categorized under Bad Speculation category. Incorrect data speculation followed by Memory Ordering Nukes is another example. SMT version; use when SMT is enabled and measuring per logical CPU.",
+        "BriefDescription": "This category represents fraction of slots wasted due to incorrect speculations. SMT version; use when SMT is enabled and measuring per logical CPU.",
+        "MetricGroup": "TopdownL1_SMT",
+        "MetricName": "Bad_Speculation_SMT"
+    },
+    {
+        "MetricExpr": "1 - ( (IDQ_UOPS_NOT_DELIVERED.CORE / (4 * cycles)) + (( UOPS_ISSUED.ANY - UOPS_RETIRED.RETIRE_SLOTS + 4 * INT_MISC.RECOVERY_CYCLES ) / (4 * cycles)) + (UOPS_RETIRED.RETIRE_SLOTS / (4 * cycles)) )",
+        "PublicDescription": "This category represents fraction of slots where no uops are being delivered due to a lack of required resources for accepting new uops in the Backend. Backend is the portion of the processor core where the out-of-order scheduler dispatches ready uops into their respective execution units; and once completed these uops get retired according to program order. For example; stalls due to data-cache misses or stalls due to the divider unit being overloaded are both categorized under Backend Bound. Backend Bound is further divided into two main categories: Memory Bound and Core Bound.",
+        "BriefDescription": "This category represents fraction of slots where no uops are being delivered due to a lack of required resources for accepting new uops in the Backend",
+        "MetricGroup": "TopdownL1",
+        "MetricName": "Backend_Bound"
+    },
+    {
+        "MetricExpr": "1 - ( (IDQ_UOPS_NOT_DELIVERED.CORE / (4 * (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )))) + (( UOPS_ISSUED.ANY - UOPS_RETIRED.RETIRE_SLOTS + 4 * (( INT_MISC.RECOVERY_CYCLES_ANY / 2 )) ) / (4 * (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )))) + (UOPS_RETIRED.RETIRE_SLOTS / (4 * (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )))) )",
+        "PublicDescription": "This category represents fraction of slots where no uops are being delivered due to a lack of required resources for accepting new uops in the Backend. Backend is the portion of the processor core where the out-of-order scheduler dispatches ready uops into their respective execution units; and once completed these uops get retired according to program order. For example; stalls due to data-cache misses or stalls due to the divider unit being overloaded are both categorized under Backend Bound. Backend Bound is further divided into two main categories: Memory Bound and Core Bound. SMT version; use when SMT is enabled and measuring per logical CPU.",
+        "BriefDescription": "This category represents fraction of slots where no uops are being delivered due to a lack of required resources for accepting new uops in the Backend. SMT version; use when SMT is enabled and measuring per logical CPU.",
+        "MetricGroup": "TopdownL1_SMT",
+        "MetricName": "Backend_Bound_SMT"
+    },
+    {
+        "MetricExpr": "UOPS_RETIRED.RETIRE_SLOTS / (4 * cycles)",
+        "PublicDescription": "This category represents fraction of slots utilized by useful work i.e. issued uops that eventually get retired. Ideally; all pipeline slots would be attributed to the Retiring category.  Retiring of 100% would indicate the maximum 4 uops retired per cycle has been achieved.  Maximizing Retiring typically increases the Instruction-Per-Cycle metric. Note that a high Retiring value does not necessary mean there is no room for more performance.  For example; Microcode assists are categorized under Retiring. They hurt performance and can often be avoided. ",
+        "BriefDescription": "This category represents fraction of slots utilized by useful work i.e. issued uops that eventually get retired",
+        "MetricGroup": "TopdownL1",
+        "MetricName": "Retiring"
+    },
+    {
+        "MetricExpr": "UOPS_RETIRED.RETIRE_SLOTS / (4 * (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )))",
+        "PublicDescription": "This category represents fraction of slots utilized by useful work i.e. issued uops that eventually get retired. Ideally; all pipeline slots would be attributed to the Retiring category.  Retiring of 100% would indicate the maximum 4 uops retired per cycle has been achieved.  Maximizing Retiring typically increases the Instruction-Per-Cycle metric. Note that a high Retiring value does not necessary mean there is no room for more performance.  For example; Microcode assists are categorized under Retiring. They hurt performance and can often be avoided. SMT version; use when SMT is enabled and measuring per logical CPU.",
+        "BriefDescription": "This category represents fraction of slots utilized by useful work i.e. issued uops that eventually get retired. SMT version; use when SMT is enabled and measuring per logical CPU.",
+        "MetricGroup": "TopdownL1_SMT",
+        "MetricName": "Retiring_SMT"
+    },
+    {
         "MetricExpr": "INST_RETIRED.ANY / CPU_CLK_UNHALTED.THREAD",
+        "BriefDescription": "Instructions Per Cycle (per logical thread)",
         "MetricGroup": "TopDownL1",
         "MetricName": "IPC"
     },
     {
-        "BriefDescription": "Uops Per Instruction",
         "MetricExpr": "UOPS_RETIRED.RETIRE_SLOTS / INST_RETIRED.ANY",
-        "MetricGroup": "Pipeline",
+        "BriefDescription": "Uops Per Instruction",
+        "MetricGroup": "Pipeline;Retiring",
         "MetricName": "UPI"
     },
     {
-        "BriefDescription": "Rough Estimation of fraction of fetched lines bytes that were likely consumed by program instructions",
-        "MetricExpr": "min( 1 , UOPS_ISSUED.ANY / ( (UOPS_RETIRED.RETIRE_SLOTS / INST_RETIRED.ANY) * 32 * ( ICACHE.HIT + ICACHE.MISSES ) / 4) )",
-        "MetricGroup": "Frontend",
+        "MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.NEAR_TAKEN",
+        "BriefDescription": "Instruction per taken branch",
+        "MetricGroup": "Branches;PGO",
+        "MetricName": "IpTB"
+    },
+    {
+        "MetricExpr": "BR_INST_RETIRED.ALL_BRANCHES / BR_INST_RETIRED.NEAR_TAKEN",
+        "BriefDescription": "Branch instructions per taken branch. ",
+        "MetricGroup": "Branches;PGO",
+        "MetricName": "BpTB"
+    },
+    {
+        "MetricExpr": "min( 1 , UOPS_ISSUED.ANY / ( (UOPS_RETIRED.RETIRE_SLOTS / INST_RETIRED.ANY) * 32 * ( ICACHE.HIT + ICACHE.MISSES ) / 4 ) )",
+        "BriefDescription": "Rough Estimation of fraction of fetched lines bytes that were likely (includes speculatively fetches) consumed by program instructions",
+        "MetricGroup": "PGO",
         "MetricName": "IFetch_Line_Utilization"
     },
     {
-        "BriefDescription": "Fraction of Uops delivered by the DSB (aka Decoded Icache; or Uop Cache)",
-        "MetricExpr": "IDQ.DSB_UOPS / ( IDQ.DSB_UOPS + LSD.UOPS + IDQ.MITE_UOPS + IDQ.MS_UOPS )",
-        "MetricGroup": "DSB; Frontend_Bandwidth",
+        "MetricExpr": "IDQ.DSB_UOPS / (( IDQ.DSB_UOPS + LSD.UOPS + IDQ.MITE_UOPS + IDQ.MS_UOPS ) )",
+        "BriefDescription": "Fraction of Uops delivered by the DSB (aka Decoded ICache; or Uop Cache)",
+        "MetricGroup": "DSB;Frontend_Bandwidth",
         "MetricName": "DSB_Coverage"
     },
     {
-        "BriefDescription": "Cycles Per Instruction (threaded)",
         "MetricExpr": "1 / (INST_RETIRED.ANY / cycles)",
+        "BriefDescription": "Cycles Per Instruction (threaded)",
         "MetricGroup": "Pipeline;Summary",
         "MetricName": "CPI"
     },
     {
-        "BriefDescription": "Per-thread actual clocks when the logical processor is active. This is called 'Clockticks' in VTune.",
         "MetricExpr": "CPU_CLK_UNHALTED.THREAD",
+        "BriefDescription": "Per-thread actual clocks when the logical processor is active.",
         "MetricGroup": "Summary",
         "MetricName": "CLKS"
     },
     {
-        "BriefDescription": "Total issue-pipeline slots",
-        "MetricExpr": "4*(( CPU_CLK_UNHALTED.THREAD_ANY / 2 ) if #SMT_on else cycles)",
+        "MetricExpr": "4 * cycles",
+        "BriefDescription": "Total issue-pipeline slots (per core)",
         "MetricGroup": "TopDownL1",
         "MetricName": "SLOTS"
     },
     {
-        "BriefDescription": "Total number of retired Instructions",
+        "MetricExpr": "4 * (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) ))",
+        "BriefDescription": "Total issue-pipeline slots (per core)",
+        "MetricGroup": "TopDownL1_SMT",
+        "MetricName": "SLOTS_SMT"
+    },
+    {
+        "MetricExpr": "INST_RETIRED.ANY / MEM_UOPS_RETIRED.ALL_LOADS",
+        "BriefDescription": "Instructions per Load (lower number means loads are more frequent)",
+        "MetricGroup": "Instruction_Type;L1_Bound",
+        "MetricName": "IpL"
+    },
+    {
+        "MetricExpr": "INST_RETIRED.ANY / MEM_UOPS_RETIRED.ALL_STORES",
+        "BriefDescription": "Instructions per Store",
+        "MetricGroup": "Instruction_Type;Store_Bound",
+        "MetricName": "IpS"
+    },
+    {
+        "MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.ALL_BRANCHES",
+        "BriefDescription": "Instructions per Branch",
+        "MetricGroup": "Branches;Instruction_Type;Port_5;Port_6",
+        "MetricName": "IpB"
+    },
+    {
+        "MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.NEAR_CALL",
+        "BriefDescription": "Instruction per (near) call",
+        "MetricGroup": "Branches",
+        "MetricName": "IpCall"
+    },
+    {
         "MetricExpr": "INST_RETIRED.ANY",
+        "BriefDescription": "Total number of retired Instructions",
         "MetricGroup": "Summary",
         "MetricName": "Instructions"
     },
     {
+        "MetricExpr": "INST_RETIRED.ANY / cycles",
         "BriefDescription": "Instructions Per Cycle (per physical core)",
-        "MetricExpr": "INST_RETIRED.ANY / (( CPU_CLK_UNHALTED.THREAD_ANY / 2 ) if #SMT_on else cycles)",
         "MetricGroup": "SMT",
         "MetricName": "CoreIPC"
     },
     {
+        "MetricExpr": "INST_RETIRED.ANY / (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) ))",
+        "BriefDescription": "Instructions Per Cycle (per physical core)",
+        "MetricGroup": "SMT",
+        "MetricName": "CoreIPC_SMT"
+    },
+    {
+        "MetricExpr": "(( 1 * ( FP_COMP_OPS_EXE.SSE_SCALAR_SINGLE + FP_COMP_OPS_EXE.SSE_SCALAR_DOUBLE ) + 2 * FP_COMP_OPS_EXE.SSE_PACKED_DOUBLE + 4 * ( FP_COMP_OPS_EXE.SSE_PACKED_SINGLE + SIMD_FP_256.PACKED_DOUBLE ) + 8 * SIMD_FP_256.PACKED_SINGLE )) / cycles",
+        "BriefDescription": "Floating Point Operations Per Cycle",
+        "MetricGroup": "FLOPS",
+        "MetricName": "FLOPc"
+    },
+    {
+        "MetricExpr": "(( 1 * ( FP_COMP_OPS_EXE.SSE_SCALAR_SINGLE + FP_COMP_OPS_EXE.SSE_SCALAR_DOUBLE ) + 2 * FP_COMP_OPS_EXE.SSE_PACKED_DOUBLE + 4 * ( FP_COMP_OPS_EXE.SSE_PACKED_SINGLE + SIMD_FP_256.PACKED_DOUBLE ) + 8 * SIMD_FP_256.PACKED_SINGLE )) / (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) ))",
+        "BriefDescription": "Floating Point Operations Per Cycle",
+        "MetricGroup": "FLOPS_SMT",
+        "MetricName": "FLOPc_SMT"
+    },
+    {
+        "MetricExpr": "UOPS_EXECUTED.THREAD / (( cpu@UOPS_EXECUTED.CORE\\,cmask\\=1@ / 2 ) if #SMT_on else UOPS_EXECUTED.CYCLES_GE_1_UOP_EXEC)",
         "BriefDescription": "Instruction-Level-Parallelism (average number of uops executed when there is at least 1 uop executed)",
-        "MetricExpr": "UOPS_EXECUTED.THREAD / (( cpu@UOPS_EXECUTED.CORE\\,cmask\\=1@ / 2) if #SMT_on else UOPS_EXECUTED.CYCLES_GE_1_UOP_EXEC)",
         "MetricGroup": "Pipeline;Ports_Utilization",
         "MetricName": "ILP"
     },
     {
-        "BriefDescription": "Average Branch Address Clear Cost (fraction of cycles)",
-        "MetricExpr": "2* (( RS_EVENTS.EMPTY_CYCLES - ICACHE.IFETCH_STALL ) / RS_EVENTS.EMPTY_END)",
-        "MetricGroup": "Unknown_Branches",
-        "MetricName": "BAClear_Cost"
+        "MetricExpr": "INST_RETIRED.ANY / BR_MISP_RETIRED.ALL_BRANCHES",
+        "BriefDescription": "Number of Instructions per non-speculative Branch Misprediction (JEClear)",
+        "MetricGroup": "Branch_Mispredicts",
+        "MetricName": "IpMispredict"
     },
     {
+        "MetricExpr": "( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )",
         "BriefDescription": "Core actual clocks when any thread is active on the physical core",
-        "MetricExpr": "( CPU_CLK_UNHALTED.THREAD_ANY / 2 ) if #SMT_on else CPU_CLK_UNHALTED.THREAD",
         "MetricGroup": "SMT",
         "MetricName": "CORE_CLKS"
     },
     {
-        "BriefDescription": "Actual Average Latency for L1 data-cache miss demand loads",
         "MetricExpr": "L1D_PEND_MISS.PENDING / ( MEM_LOAD_UOPS_RETIRED.L1_MISS + mem_load_uops_retired.hit_lfb )",
+        "BriefDescription": "Actual Average Latency for L1 data-cache miss demand loads (in core cycles)",
         "MetricGroup": "Memory_Bound;Memory_Lat",
         "MetricName": "Load_Miss_Real_Latency"
     },
     {
-        "BriefDescription": "Memory-Level-Parallelism (average number of L1 miss demand load when there is at least 1 such miss)",
-        "MetricExpr": "L1D_PEND_MISS.PENDING / (( cpu@l1d_pend_miss.pending_cycles\\,any\\=1@ / 2) if #SMT_on else L1D_PEND_MISS.PENDING_CYCLES)",
+        "MetricExpr": "L1D_PEND_MISS.PENDING / L1D_PEND_MISS.PENDING_CYCLES",
+        "BriefDescription": "Memory-Level-Parallelism (average number of L1 miss demand load when there is at least one such miss. Per-thread)",
         "MetricGroup": "Memory_Bound;Memory_BW",
         "MetricName": "MLP"
     },
     {
+        "MetricExpr": "( ITLB_MISSES.WALK_DURATION + DTLB_LOAD_MISSES.WALK_DURATION + DTLB_STORE_MISSES.WALK_DURATION ) / cycles",
         "BriefDescription": "Utilization of the core's Page Walker(s) serving STLB misses triggered by instruction/Load/Store accesses",
-        "MetricExpr": "( ITLB_MISSES.WALK_DURATION + DTLB_LOAD_MISSES.WALK_DURATION + DTLB_STORE_MISSES.WALK_DURATION ) / (( CPU_CLK_UNHALTED.THREAD_ANY / 2 ) if #SMT_on else cycles)",
         "MetricGroup": "TLB",
         "MetricName": "Page_Walks_Utilization"
     },
     {
-        "BriefDescription": "Average CPU Utilization",
+        "MetricExpr": "( ITLB_MISSES.WALK_DURATION + DTLB_LOAD_MISSES.WALK_DURATION + DTLB_STORE_MISSES.WALK_DURATION ) / (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) ))",
+        "BriefDescription": "Utilization of the core's Page Walker(s) serving STLB misses triggered by instruction/Load/Store accesses",
+        "MetricGroup": "TLB_SMT",
+        "MetricName": "Page_Walks_Utilization_SMT"
+    },
+    {
+        "MetricExpr": "64 * L1D.REPLACEMENT / 1000000000 / duration_time",
+        "BriefDescription": "Average data fill bandwidth to the L1 data cache [GB / sec]",
+        "MetricGroup": "Memory_BW",
+        "MetricName": "L1D_Cache_Fill_BW"
+    },
+    {
+        "MetricExpr": "64 * L2_LINES_IN.ALL / 1000000000 / duration_time",
+        "BriefDescription": "Average data fill bandwidth to the L2 cache [GB / sec]",
+        "MetricGroup": "Memory_BW",
+        "MetricName": "L2_Cache_Fill_BW"
+    },
+    {
+        "MetricExpr": "64 * LONGEST_LAT_CACHE.MISS / 1000000000 / duration_time",
+        "BriefDescription": "Average per-core data fill bandwidth to the L3 cache [GB / sec]",
+        "MetricGroup": "Memory_BW",
+        "MetricName": "L3_Cache_Fill_BW"
+    },
+    {
+        "MetricExpr": "1000 * MEM_LOAD_UOPS_RETIRED.L1_MISS / INST_RETIRED.ANY",
+        "BriefDescription": "L1 cache true misses per kilo instruction for retired demand loads",
+        "MetricGroup": "Cache_Misses;",
+        "MetricName": "L1MPKI"
+    },
+    {
+        "MetricExpr": "1000 * MEM_LOAD_UOPS_RETIRED.L2_MISS / INST_RETIRED.ANY",
+        "BriefDescription": "L2 cache true misses per kilo instruction for retired demand loads",
+        "MetricGroup": "Cache_Misses;",
+        "MetricName": "L2MPKI"
+    },
+    {
+        "MetricExpr": "1000 * MEM_LOAD_UOPS_RETIRED.L2_MISS / INST_RETIRED.ANY",
+        "BriefDescription": "L2 cache misses per kilo instruction for all request types (including speculative)",
+        "MetricGroup": "Cache_Misses;",
+        "MetricName": "L2MPKI_All"
+    },
+    {
+        "MetricExpr": "1000 * MEM_LOAD_UOPS_RETIRED.L2_MISS / INST_RETIRED.ANY",
+        "BriefDescription": "L2 cache hits per kilo instruction for all request types (including speculative)",
+        "MetricGroup": "Cache_Misses;",
+        "MetricName": "L2HPKI_All"
+    },
+    {
+        "MetricExpr": "1000 * MEM_LOAD_UOPS_RETIRED.LLC_MISS / INST_RETIRED.ANY",
+        "BriefDescription": "L3 cache true misses per kilo instruction for retired demand loads",
+        "MetricGroup": "Cache_Misses;",
+        "MetricName": "L3MPKI"
+    },
+    {
         "MetricExpr": "CPU_CLK_UNHALTED.REF_TSC / msr@tsc@",
+        "BriefDescription": "Average CPU Utilization",
         "MetricGroup": "Summary",
         "MetricName": "CPU_Utilization"
     },
     {
+        "MetricExpr": "( (( 1 * ( FP_COMP_OPS_EXE.SSE_SCALAR_SINGLE + FP_COMP_OPS_EXE.SSE_SCALAR_DOUBLE ) + 2 * FP_COMP_OPS_EXE.SSE_PACKED_DOUBLE + 4 * ( FP_COMP_OPS_EXE.SSE_PACKED_SINGLE + SIMD_FP_256.PACKED_DOUBLE ) + 8 * SIMD_FP_256.PACKED_SINGLE )) / 1000000000 ) / duration_time",
         "BriefDescription": "Giga Floating Point Operations Per Second",
-        "MetricExpr": "(( 1*( FP_COMP_OPS_EXE.SSE_SCALAR_SINGLE + FP_COMP_OPS_EXE.SSE_SCALAR_DOUBLE ) + 2* FP_COMP_OPS_EXE.SSE_PACKED_DOUBLE + 4*( FP_COMP_OPS_EXE.SSE_PACKED_SINGLE + SIMD_FP_256.PACKED_DOUBLE ) + 8* SIMD_FP_256.PACKED_SINGLE )) / 1000000000 / duration_time",
         "MetricGroup": "FLOPS;Summary",
         "MetricName": "GFLOPs"
     },
     {
-        "BriefDescription": "Average Frequency Utilization relative nominal frequency",
         "MetricExpr": "CPU_CLK_UNHALTED.THREAD / CPU_CLK_UNHALTED.REF_TSC",
+        "BriefDescription": "Average Frequency Utilization relative nominal frequency",
         "MetricGroup": "Power",
         "MetricName": "Turbo_Utilization"
     },
     {
-        "BriefDescription": "Fraction of cycles where both hardware threads were active",
         "MetricExpr": "1 - CPU_CLK_THREAD_UNHALTED.ONE_THREAD_ACTIVE / ( CPU_CLK_THREAD_UNHALTED.REF_XCLK_ANY / 2 ) if #SMT_on else 0",
+        "BriefDescription": "Fraction of cycles where both hardware threads were active",
         "MetricGroup": "SMT;Summary",
         "MetricName": "SMT_2T_Utilization"
     },
     {
-        "BriefDescription": "Fraction of cycles spent in Kernel mode",
         "MetricExpr": "CPU_CLK_UNHALTED.REF_TSC:u / CPU_CLK_UNHALTED.REF_TSC",
+        "BriefDescription": "Fraction of cycles spent in Kernel mode",
         "MetricGroup": "Summary",
         "MetricName": "Kernel_Utilization"
     },
     {
-        "BriefDescription": "C3 residency percent per core",
+        "MetricExpr": "( 64 * ( uncore_imc@cas_count_read@ + uncore_imc@cas_count_write@ ) / 1000000000 ) / duration_time",
+        "BriefDescription": "Average external Memory Bandwidth Use for reads and writes [GB / sec]",
+        "MetricGroup": "Memory_BW",
+        "MetricName": "DRAM_BW_Use"
+    },
+    {
+        "MetricExpr": "cbox_0@event\\=0x0@",
+        "BriefDescription": "Socket actual clocks when any core is active on that socket",
+        "MetricGroup": "",
+        "MetricName": "Socket_CLKS"
+    },
+    {
         "MetricExpr": "(cstate_core@c3\\-residency@ / msr@tsc@) * 100",
         "MetricGroup": "Power",
+        "BriefDescription": "C3 residency percent per core",
         "MetricName": "C3_Core_Residency"
     },
     {
-        "BriefDescription": "C6 residency percent per core",
         "MetricExpr": "(cstate_core@c6\\-residency@ / msr@tsc@) * 100",
         "MetricGroup": "Power",
+        "BriefDescription": "C6 residency percent per core",
         "MetricName": "C6_Core_Residency"
     },
     {
-        "BriefDescription": "C7 residency percent per core",
         "MetricExpr": "(cstate_core@c7\\-residency@ / msr@tsc@) * 100",
         "MetricGroup": "Power",
+        "BriefDescription": "C7 residency percent per core",
         "MetricName": "C7_Core_Residency"
     },
     {
-        "BriefDescription": "C2 residency percent per package",
         "MetricExpr": "(cstate_pkg@c2\\-residency@ / msr@tsc@) * 100",
         "MetricGroup": "Power",
+        "BriefDescription": "C2 residency percent per package",
         "MetricName": "C2_Pkg_Residency"
     },
     {
-        "BriefDescription": "C3 residency percent per package",
         "MetricExpr": "(cstate_pkg@c3\\-residency@ / msr@tsc@) * 100",
         "MetricGroup": "Power",
+        "BriefDescription": "C3 residency percent per package",
         "MetricName": "C3_Pkg_Residency"
     },
     {
-        "BriefDescription": "C6 residency percent per package",
         "MetricExpr": "(cstate_pkg@c6\\-residency@ / msr@tsc@) * 100",
         "MetricGroup": "Power",
+        "BriefDescription": "C6 residency percent per package",
         "MetricName": "C6_Pkg_Residency"
     },
     {
-        "BriefDescription": "C7 residency percent per package",
         "MetricExpr": "(cstate_pkg@c7\\-residency@ / msr@tsc@) * 100",
         "MetricGroup": "Power",
+        "BriefDescription": "C7 residency percent per package",
         "MetricName": "C7_Pkg_Residency"
     }
 ]
diff --git a/tools/perf/pmu-events/arch/x86/ivytown/pipeline.json b/tools/perf/pmu-events/arch/x86/ivytown/pipeline.json
index 0afbfd95ea30..2a0aad91d83d 100644
--- a/tools/perf/pmu-events/arch/x86/ivytown/pipeline.json
+++ b/tools/perf/pmu-events/arch/x86/ivytown/pipeline.json
@@ -1,6 +1,5 @@
 [
     {
-        "EventCode": "0x00",
         "Counter": "Fixed counter 0",
         "UMask": "0x1",
         "EventName": "INST_RETIRED.ANY",
@@ -9,7 +8,6 @@
         "CounterHTOff": "Fixed counter 0"
     },
     {
-        "EventCode": "0x00",
         "Counter": "Fixed counter 1",
         "UMask": "0x2",
         "EventName": "CPU_CLK_UNHALTED.THREAD",
@@ -19,7 +17,6 @@
     },
     {
         "PublicDescription": "Core cycles when at least one thread on the physical core is not in halt state.",
-        "EventCode": "0x00",
         "Counter": "Fixed counter 1",
         "UMask": "0x2",
         "AnyThread": "1",
@@ -29,7 +26,6 @@
         "CounterHTOff": "Fixed counter 1"
     },
     {
-        "EventCode": "0x00",
         "Counter": "Fixed counter 2",
         "UMask": "0x3",
         "EventName": "CPU_CLK_UNHALTED.REF_TSC",
diff --git a/tools/perf/pmu-events/arch/x86/jaketown/cache.json b/tools/perf/pmu-events/arch/x86/jaketown/cache.json
index ee22e4a5e30d..52dc6ef40e63 100644
--- a/tools/perf/pmu-events/arch/x86/jaketown/cache.json
+++ b/tools/perf/pmu-events/arch/x86/jaketown/cache.json
@@ -31,7 +31,7 @@
     },
     {
         "PEBS": "1",
-        "PublicDescription": "This event counts line-split load uops retired to the architected path. A line split is across 64B cache-line which includes a page split (4K).",
+        "PublicDescription": "This event counts line-splitted load uops retired to the architected path. A line split is across 64B cache-line which includes a page split (4K).",
         "EventCode": "0xD0",
         "Counter": "0,1,2,3",
         "UMask": "0x41",
@@ -42,7 +42,7 @@
     },
     {
         "PEBS": "1",
-        "PublicDescription": "This event counts line-split store uops retired to the architected path. A line split is across 64B cache-line which includes a page split (4K).",
+        "PublicDescription": "This event counts line-splitted store uops retired to the architected path. A line split is across 64B cache-line which includes a page split (4K).",
         "EventCode": "0xD0",
         "Counter": "0,1,2,3",
         "UMask": "0x42",
@@ -179,7 +179,7 @@
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "This event counts L1D data line replacements.  Replacements occur when a new line is brought into the cache, causing eviction of a line loaded earlier.  ",
+        "PublicDescription": "This event counts L1D data line replacements.  Replacements occur when a new line is brought into the cache, causing eviction of a line loaded earlier.",
         "EventCode": "0x51",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
diff --git a/tools/perf/pmu-events/arch/x86/jaketown/jkt-metrics.json b/tools/perf/pmu-events/arch/x86/jaketown/jkt-metrics.json
index fd7d7c438226..98c73e430b05 100644
--- a/tools/perf/pmu-events/arch/x86/jaketown/jkt-metrics.json
+++ b/tools/perf/pmu-events/arch/x86/jaketown/jkt-metrics.json
@@ -1,140 +1,232 @@
 [
     {
-        "BriefDescription": "Instructions Per Cycle (per logical thread)",
+        "MetricExpr": "IDQ_UOPS_NOT_DELIVERED.CORE / (4 * cycles)",
+        "PublicDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend. Frontend denotes the first part of the processor core responsible to fetch operations that are executed later on by the Backend part. Within the Frontend; a branch predictor predicts the next address to fetch; cache-lines are fetched from the memory subsystem; parsed into instructions; and lastly decoded into micro-ops (uops). Ideally the Frontend can issue 4 uops every cycle to the Backend. Frontend Bound denotes unutilized issue-slots when there is no Backend stall; i.e. bubbles where Frontend delivered no uops while Backend could have accepted them. For example; stalls due to instruction-cache misses would be categorized under Frontend Bound.",
+        "BriefDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend",
+        "MetricGroup": "TopdownL1",
+        "MetricName": "Frontend_Bound"
+    },
+    {
+        "MetricExpr": "IDQ_UOPS_NOT_DELIVERED.CORE / (4 * (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )))",
+        "PublicDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend. Frontend denotes the first part of the processor core responsible to fetch operations that are executed later on by the Backend part. Within the Frontend; a branch predictor predicts the next address to fetch; cache-lines are fetched from the memory subsystem; parsed into instructions; and lastly decoded into micro-ops (uops). Ideally the Frontend can issue 4 uops every cycle to the Backend. Frontend Bound denotes unutilized issue-slots when there is no Backend stall; i.e. bubbles where Frontend delivered no uops while Backend could have accepted them. For example; stalls due to instruction-cache misses would be categorized under Frontend Bound. SMT version; use when SMT is enabled and measuring per logical CPU.",
+        "BriefDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend. SMT version; use when SMT is enabled and measuring per logical CPU.",
+        "MetricGroup": "TopdownL1_SMT",
+        "MetricName": "Frontend_Bound_SMT"
+    },
+    {
+        "MetricExpr": "( UOPS_ISSUED.ANY - UOPS_RETIRED.RETIRE_SLOTS + 4 * INT_MISC.RECOVERY_CYCLES ) / (4 * cycles)",
+        "PublicDescription": "This category represents fraction of slots wasted due to incorrect speculations. This include slots used to issue uops that do not eventually get retired and slots for which the issue-pipeline was blocked due to recovery from earlier incorrect speculation. For example; wasted work due to miss-predicted branches are categorized under Bad Speculation category. Incorrect data speculation followed by Memory Ordering Nukes is another example.",
+        "BriefDescription": "This category represents fraction of slots wasted due to incorrect speculations",
+        "MetricGroup": "TopdownL1",
+        "MetricName": "Bad_Speculation"
+    },
+    {
+        "MetricExpr": "( UOPS_ISSUED.ANY - UOPS_RETIRED.RETIRE_SLOTS + 4 * (( INT_MISC.RECOVERY_CYCLES_ANY / 2 )) ) / (4 * (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )))",
+        "PublicDescription": "This category represents fraction of slots wasted due to incorrect speculations. This include slots used to issue uops that do not eventually get retired and slots for which the issue-pipeline was blocked due to recovery from earlier incorrect speculation. For example; wasted work due to miss-predicted branches are categorized under Bad Speculation category. Incorrect data speculation followed by Memory Ordering Nukes is another example. SMT version; use when SMT is enabled and measuring per logical CPU.",
+        "BriefDescription": "This category represents fraction of slots wasted due to incorrect speculations. SMT version; use when SMT is enabled and measuring per logical CPU.",
+        "MetricGroup": "TopdownL1_SMT",
+        "MetricName": "Bad_Speculation_SMT"
+    },
+    {
+        "MetricExpr": "1 - ( (IDQ_UOPS_NOT_DELIVERED.CORE / (4 * cycles)) + (( UOPS_ISSUED.ANY - UOPS_RETIRED.RETIRE_SLOTS + 4 * INT_MISC.RECOVERY_CYCLES ) / (4 * cycles)) + (UOPS_RETIRED.RETIRE_SLOTS / (4 * cycles)) )",
+        "PublicDescription": "This category represents fraction of slots where no uops are being delivered due to a lack of required resources for accepting new uops in the Backend. Backend is the portion of the processor core where the out-of-order scheduler dispatches ready uops into their respective execution units; and once completed these uops get retired according to program order. For example; stalls due to data-cache misses or stalls due to the divider unit being overloaded are both categorized under Backend Bound. Backend Bound is further divided into two main categories: Memory Bound and Core Bound.",
+        "BriefDescription": "This category represents fraction of slots where no uops are being delivered due to a lack of required resources for accepting new uops in the Backend",
+        "MetricGroup": "TopdownL1",
+        "MetricName": "Backend_Bound"
+    },
+    {
+        "MetricExpr": "1 - ( (IDQ_UOPS_NOT_DELIVERED.CORE / (4 * (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )))) + (( UOPS_ISSUED.ANY - UOPS_RETIRED.RETIRE_SLOTS + 4 * (( INT_MISC.RECOVERY_CYCLES_ANY / 2 )) ) / (4 * (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )))) + (UOPS_RETIRED.RETIRE_SLOTS / (4 * (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )))) )",
+        "PublicDescription": "This category represents fraction of slots where no uops are being delivered due to a lack of required resources for accepting new uops in the Backend. Backend is the portion of the processor core where the out-of-order scheduler dispatches ready uops into their respective execution units; and once completed these uops get retired according to program order. For example; stalls due to data-cache misses or stalls due to the divider unit being overloaded are both categorized under Backend Bound. Backend Bound is further divided into two main categories: Memory Bound and Core Bound. SMT version; use when SMT is enabled and measuring per logical CPU.",
+        "BriefDescription": "This category represents fraction of slots where no uops are being delivered due to a lack of required resources for accepting new uops in the Backend. SMT version; use when SMT is enabled and measuring per logical CPU.",
+        "MetricGroup": "TopdownL1_SMT",
+        "MetricName": "Backend_Bound_SMT"
+    },
+    {
+        "MetricExpr": "UOPS_RETIRED.RETIRE_SLOTS / (4 * cycles)",
+        "PublicDescription": "This category represents fraction of slots utilized by useful work i.e. issued uops that eventually get retired. Ideally; all pipeline slots would be attributed to the Retiring category.  Retiring of 100% would indicate the maximum 4 uops retired per cycle has been achieved.  Maximizing Retiring typically increases the Instruction-Per-Cycle metric. Note that a high Retiring value does not necessary mean there is no room for more performance.  For example; Microcode assists are categorized under Retiring. They hurt performance and can often be avoided. ",
+        "BriefDescription": "This category represents fraction of slots utilized by useful work i.e. issued uops that eventually get retired",
+        "MetricGroup": "TopdownL1",
+        "MetricName": "Retiring"
+    },
+    {
+        "MetricExpr": "UOPS_RETIRED.RETIRE_SLOTS / (4 * (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )))",
+        "PublicDescription": "This category represents fraction of slots utilized by useful work i.e. issued uops that eventually get retired. Ideally; all pipeline slots would be attributed to the Retiring category.  Retiring of 100% would indicate the maximum 4 uops retired per cycle has been achieved.  Maximizing Retiring typically increases the Instruction-Per-Cycle metric. Note that a high Retiring value does not necessary mean there is no room for more performance.  For example; Microcode assists are categorized under Retiring. They hurt performance and can often be avoided. SMT version; use when SMT is enabled and measuring per logical CPU.",
+        "BriefDescription": "This category represents fraction of slots utilized by useful work i.e. issued uops that eventually get retired. SMT version; use when SMT is enabled and measuring per logical CPU.",
+        "MetricGroup": "TopdownL1_SMT",
+        "MetricName": "Retiring_SMT"
+    },
+    {
         "MetricExpr": "INST_RETIRED.ANY / CPU_CLK_UNHALTED.THREAD",
+        "BriefDescription": "Instructions Per Cycle (per logical thread)",
         "MetricGroup": "TopDownL1",
         "MetricName": "IPC"
     },
     {
-        "BriefDescription": "Uops Per Instruction",
         "MetricExpr": "UOPS_RETIRED.RETIRE_SLOTS / INST_RETIRED.ANY",
-        "MetricGroup": "Pipeline",
+        "BriefDescription": "Uops Per Instruction",
+        "MetricGroup": "Pipeline;Retiring",
         "MetricName": "UPI"
     },
     {
-        "BriefDescription": "Rough Estimation of fraction of fetched lines bytes that were likely consumed by program instructions",
-        "MetricExpr": "min( 1 , UOPS_ISSUED.ANY / ( (UOPS_RETIRED.RETIRE_SLOTS / INST_RETIRED.ANY) * 32 * ( ICACHE.HIT + ICACHE.MISSES ) / 4) )",
-        "MetricGroup": "Frontend",
+        "MetricExpr": "min( 1 , UOPS_ISSUED.ANY / ( (UOPS_RETIRED.RETIRE_SLOTS / INST_RETIRED.ANY) * 32 * ( ICACHE.HIT + ICACHE.MISSES ) / 4 ) )",
+        "BriefDescription": "Rough Estimation of fraction of fetched lines bytes that were likely (includes speculatively fetches) consumed by program instructions",
+        "MetricGroup": "PGO",
         "MetricName": "IFetch_Line_Utilization"
     },
     {
-        "BriefDescription": "Fraction of Uops delivered by the DSB (aka Decoded Icache; or Uop Cache)",
-        "MetricExpr": "IDQ.DSB_UOPS / ( IDQ.DSB_UOPS + LSD.UOPS + IDQ.MITE_UOPS + IDQ.MS_UOPS )",
-        "MetricGroup": "DSB; Frontend_Bandwidth",
+        "MetricExpr": "IDQ.DSB_UOPS / (( IDQ.DSB_UOPS + LSD.UOPS + IDQ.MITE_UOPS + IDQ.MS_UOPS ) )",
+        "BriefDescription": "Fraction of Uops delivered by the DSB (aka Decoded ICache; or Uop Cache)",
+        "MetricGroup": "DSB;Frontend_Bandwidth",
         "MetricName": "DSB_Coverage"
     },
     {
-        "BriefDescription": "Cycles Per Instruction (threaded)",
         "MetricExpr": "1 / (INST_RETIRED.ANY / cycles)",
+        "BriefDescription": "Cycles Per Instruction (threaded)",
         "MetricGroup": "Pipeline;Summary",
         "MetricName": "CPI"
     },
     {
-        "BriefDescription": "Per-thread actual clocks when the logical processor is active. This is called 'Clockticks' in VTune.",
         "MetricExpr": "CPU_CLK_UNHALTED.THREAD",
+        "BriefDescription": "Per-thread actual clocks when the logical processor is active.",
         "MetricGroup": "Summary",
         "MetricName": "CLKS"
     },
     {
-        "BriefDescription": "Total issue-pipeline slots",
-        "MetricExpr": "4*(( CPU_CLK_UNHALTED.THREAD_ANY / 2 ) if #SMT_on else cycles)",
+        "MetricExpr": "4 * cycles",
+        "BriefDescription": "Total issue-pipeline slots (per core)",
         "MetricGroup": "TopDownL1",
         "MetricName": "SLOTS"
     },
     {
-        "BriefDescription": "Total number of retired Instructions",
+        "MetricExpr": "4 * (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) ))",
+        "BriefDescription": "Total issue-pipeline slots (per core)",
+        "MetricGroup": "TopDownL1_SMT",
+        "MetricName": "SLOTS_SMT"
+    },
+    {
         "MetricExpr": "INST_RETIRED.ANY",
+        "BriefDescription": "Total number of retired Instructions",
         "MetricGroup": "Summary",
         "MetricName": "Instructions"
     },
     {
+        "MetricExpr": "INST_RETIRED.ANY / cycles",
         "BriefDescription": "Instructions Per Cycle (per physical core)",
-        "MetricExpr": "INST_RETIRED.ANY / (( CPU_CLK_UNHALTED.THREAD_ANY / 2 ) if #SMT_on else cycles)",
         "MetricGroup": "SMT",
         "MetricName": "CoreIPC"
     },
     {
+        "MetricExpr": "INST_RETIRED.ANY / (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) ))",
+        "BriefDescription": "Instructions Per Cycle (per physical core)",
+        "MetricGroup": "SMT",
+        "MetricName": "CoreIPC_SMT"
+    },
+    {
+        "MetricExpr": "(( 1 * ( FP_COMP_OPS_EXE.SSE_SCALAR_SINGLE + FP_COMP_OPS_EXE.SSE_SCALAR_DOUBLE ) + 2 * FP_COMP_OPS_EXE.SSE_PACKED_DOUBLE + 4 * ( FP_COMP_OPS_EXE.SSE_PACKED_SINGLE + SIMD_FP_256.PACKED_DOUBLE ) + 8 * SIMD_FP_256.PACKED_SINGLE )) / cycles",
+        "BriefDescription": "Floating Point Operations Per Cycle",
+        "MetricGroup": "FLOPS",
+        "MetricName": "FLOPc"
+    },
+    {
+        "MetricExpr": "(( 1 * ( FP_COMP_OPS_EXE.SSE_SCALAR_SINGLE + FP_COMP_OPS_EXE.SSE_SCALAR_DOUBLE ) + 2 * FP_COMP_OPS_EXE.SSE_PACKED_DOUBLE + 4 * ( FP_COMP_OPS_EXE.SSE_PACKED_SINGLE + SIMD_FP_256.PACKED_DOUBLE ) + 8 * SIMD_FP_256.PACKED_SINGLE )) / (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) ))",
+        "BriefDescription": "Floating Point Operations Per Cycle",
+        "MetricGroup": "FLOPS_SMT",
+        "MetricName": "FLOPc_SMT"
+    },
+    {
+        "MetricExpr": "UOPS_DISPATCHED.THREAD / (( cpu@UOPS_DISPATCHED.CORE\\,cmask\\=1@ / 2 ) if #SMT_on else cpu@UOPS_DISPATCHED.CORE\\,cmask\\=1@)",
         "BriefDescription": "Instruction-Level-Parallelism (average number of uops executed when there is at least 1 uop executed)",
-        "MetricExpr": "UOPS_DISPATCHED.THREAD / (( cpu@UOPS_DISPATCHED.CORE\\,cmask\\=1@ / 2) if #SMT_on else cpu@UOPS_DISPATCHED.CORE\\,cmask\\=1@)",
         "MetricGroup": "Pipeline;Ports_Utilization",
         "MetricName": "ILP"
     },
     {
+        "MetricExpr": "( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )",
         "BriefDescription": "Core actual clocks when any thread is active on the physical core",
-        "MetricExpr": "( CPU_CLK_UNHALTED.THREAD_ANY / 2 ) if #SMT_on else CPU_CLK_UNHALTED.THREAD",
         "MetricGroup": "SMT",
         "MetricName": "CORE_CLKS"
     },
     {
-        "BriefDescription": "Average CPU Utilization",
         "MetricExpr": "CPU_CLK_UNHALTED.REF_TSC / msr@tsc@",
+        "BriefDescription": "Average CPU Utilization",
         "MetricGroup": "Summary",
         "MetricName": "CPU_Utilization"
     },
     {
+        "MetricExpr": "( (( 1 * ( FP_COMP_OPS_EXE.SSE_SCALAR_SINGLE + FP_COMP_OPS_EXE.SSE_SCALAR_DOUBLE ) + 2 * FP_COMP_OPS_EXE.SSE_PACKED_DOUBLE + 4 * ( FP_COMP_OPS_EXE.SSE_PACKED_SINGLE + SIMD_FP_256.PACKED_DOUBLE ) + 8 * SIMD_FP_256.PACKED_SINGLE )) / 1000000000 ) / duration_time",
         "BriefDescription": "Giga Floating Point Operations Per Second",
-        "MetricExpr": "(( 1*( FP_COMP_OPS_EXE.SSE_SCALAR_SINGLE + FP_COMP_OPS_EXE.SSE_SCALAR_DOUBLE ) + 2* FP_COMP_OPS_EXE.SSE_PACKED_DOUBLE + 4*( FP_COMP_OPS_EXE.SSE_PACKED_SINGLE + SIMD_FP_256.PACKED_DOUBLE ) + 8* SIMD_FP_256.PACKED_SINGLE )) / 1000000000 / duration_time",
         "MetricGroup": "FLOPS;Summary",
         "MetricName": "GFLOPs"
     },
     {
-        "BriefDescription": "Average Frequency Utilization relative nominal frequency",
         "MetricExpr": "CPU_CLK_UNHALTED.THREAD / CPU_CLK_UNHALTED.REF_TSC",
+        "BriefDescription": "Average Frequency Utilization relative nominal frequency",
         "MetricGroup": "Power",
         "MetricName": "Turbo_Utilization"
     },
     {
-        "BriefDescription": "Fraction of cycles where both hardware threads were active",
         "MetricExpr": "1 - CPU_CLK_THREAD_UNHALTED.ONE_THREAD_ACTIVE / ( CPU_CLK_THREAD_UNHALTED.REF_XCLK_ANY / 2 ) if #SMT_on else 0",
+        "BriefDescription": "Fraction of cycles where both hardware threads were active",
         "MetricGroup": "SMT;Summary",
         "MetricName": "SMT_2T_Utilization"
     },
     {
-        "BriefDescription": "Fraction of cycles spent in Kernel mode",
         "MetricExpr": "CPU_CLK_UNHALTED.REF_TSC:u / CPU_CLK_UNHALTED.REF_TSC",
+        "BriefDescription": "Fraction of cycles spent in Kernel mode",
         "MetricGroup": "Summary",
         "MetricName": "Kernel_Utilization"
     },
     {
-        "BriefDescription": "C3 residency percent per core",
+        "MetricExpr": "( 64 * ( uncore_imc@cas_count_read@ + uncore_imc@cas_count_write@ ) / 1000000000 ) / duration_time",
+        "BriefDescription": "Average external Memory Bandwidth Use for reads and writes [GB / sec]",
+        "MetricGroup": "Memory_BW",
+        "MetricName": "DRAM_BW_Use"
+    },
+    {
+        "MetricExpr": "cbox_0@event\\=0x0@",
+        "BriefDescription": "Socket actual clocks when any core is active on that socket",
+        "MetricGroup": "",
+        "MetricName": "Socket_CLKS"
+    },
+    {
         "MetricExpr": "(cstate_core@c3\\-residency@ / msr@tsc@) * 100",
         "MetricGroup": "Power",
+        "BriefDescription": "C3 residency percent per core",
         "MetricName": "C3_Core_Residency"
     },
     {
-        "BriefDescription": "C6 residency percent per core",
         "MetricExpr": "(cstate_core@c6\\-residency@ / msr@tsc@) * 100",
         "MetricGroup": "Power",
+        "BriefDescription": "C6 residency percent per core",
         "MetricName": "C6_Core_Residency"
     },
     {
-        "BriefDescription": "C7 residency percent per core",
         "MetricExpr": "(cstate_core@c7\\-residency@ / msr@tsc@) * 100",
         "MetricGroup": "Power",
+        "BriefDescription": "C7 residency percent per core",
         "MetricName": "C7_Core_Residency"
     },
     {
-        "BriefDescription": "C2 residency percent per package",
         "MetricExpr": "(cstate_pkg@c2\\-residency@ / msr@tsc@) * 100",
         "MetricGroup": "Power",
+        "BriefDescription": "C2 residency percent per package",
         "MetricName": "C2_Pkg_Residency"
     },
     {
-        "BriefDescription": "C3 residency percent per package",
         "MetricExpr": "(cstate_pkg@c3\\-residency@ / msr@tsc@) * 100",
         "MetricGroup": "Power",
+        "BriefDescription": "C3 residency percent per package",
         "MetricName": "C3_Pkg_Residency"
     },
     {
-        "BriefDescription": "C6 residency percent per package",
         "MetricExpr": "(cstate_pkg@c6\\-residency@ / msr@tsc@) * 100",
         "MetricGroup": "Power",
+        "BriefDescription": "C6 residency percent per package",
         "MetricName": "C6_Pkg_Residency"
     },
     {
-        "BriefDescription": "C7 residency percent per package",
         "MetricExpr": "(cstate_pkg@c7\\-residency@ / msr@tsc@) * 100",
         "MetricGroup": "Power",
+        "BriefDescription": "C7 residency percent per package",
         "MetricName": "C7_Pkg_Residency"
     }
 ]
diff --git a/tools/perf/pmu-events/arch/x86/jaketown/pipeline.json b/tools/perf/pmu-events/arch/x86/jaketown/pipeline.json
index 34a519d9bfa0..783a5b4a67b1 100644
--- a/tools/perf/pmu-events/arch/x86/jaketown/pipeline.json
+++ b/tools/perf/pmu-events/arch/x86/jaketown/pipeline.json
@@ -1,7 +1,6 @@
 [
     {
-        "PublicDescription": "This event counts the number of instructions retired from execution. For instructions that consist of multiple micro-ops, this event counts the retirement of the last micro-op of the instruction. Counting continues during hardware interrupts, traps, and inside interrupt handlers. ",
-        "EventCode": "0x00",
+        "PublicDescription": "This event counts the number of instructions retired from execution. For instructions that consist of multiple micro-ops, this event counts the retirement of the last micro-op of the instruction. Counting continues during hardware interrupts, traps, and inside interrupt handlers.",
         "Counter": "Fixed counter 1",
         "UMask": "0x1",
         "EventName": "INST_RETIRED.ANY",
@@ -10,8 +9,7 @@
         "CounterHTOff": "Fixed counter 1"
     },
     {
-        "PublicDescription": "This event counts the number of core cycles while the thread is not in a halt state. The thread enters the halt state when it is running the HLT instruction. This event is a component in many key event ratios. The core frequency may change from time to time due to transitions associated with Enhanced Intel SpeedStep Technology or TM2. For this reason this event may have a changing ratio with regards to time. When the core frequency is constant, this event can approximate elapsed time while the core was not in the halt state. It is counted on a dedicated fixed counter, leaving the four (eight when Hyperthreading is disabled) programmable counters available for other events. ",
-        "EventCode": "0x00",
+        "PublicDescription": "This event counts the number of core cycles while the thread is not in a halt state. The thread enters the halt state when it is running the HLT instruction. This event is a component in many key event ratios. The core frequency may change from time to time due to transitions associated with Enhanced Intel SpeedStep Technology or TM2. For this reason this event may have a changing ratio with regards to time. When the core frequency is constant, this event can approximate elapsed time while the core was not in the halt state. It is counted on a dedicated fixed counter, leaving the four (eight when Hyperthreading is disabled) programmable counters available for other events.",
         "Counter": "Fixed counter 2",
         "UMask": "0x2",
         "EventName": "CPU_CLK_UNHALTED.THREAD",
@@ -20,8 +18,7 @@
         "CounterHTOff": "Fixed counter 2"
     },
     {
-        "PublicDescription": "This event counts the number of reference cycles when the core is not in a halt state. The core enters the halt state when it is running the HLT instruction or the MWAIT instruction. This event is not affected by core frequency changes (for example, P states, TM2 transitions) but has the same incrementing frequency as the time stamp counter. This event can approximate elapsed time while the core was not in a halt state. This event has a constant ratio with the CPU_CLK_UNHALTED.REF_XCLK event. It is counted on a dedicated fixed counter, leaving the four (eight when Hyperthreading is disabled) programmable counters available for other events. ",
-        "EventCode": "0x00",
+        "PublicDescription": "This event counts the number of reference cycles when the core is not in a halt state. The core enters the halt state when it is running the HLT instruction or the MWAIT instruction. This event is not affected by core frequency changes (for example, P states, TM2 transitions) but has the same incrementing frequency as the time stamp counter. This event can approximate elapsed time while the core was not in a halt state. This event has a constant ratio with the CPU_CLK_UNHALTED.REF_XCLK event. It is counted on a dedicated fixed counter, leaving the four (eight when Hyperthreading is disabled) programmable counters available for other events.",
         "Counter": "Fixed counter 3",
         "UMask": "0x3",
         "EventName": "CPU_CLK_UNHALTED.REF_TSC",
@@ -778,7 +775,7 @@
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "PublicDescription": "This event counts loads that followed a store to the same address, where the data could not be forwarded inside the pipeline from the store to the load.  The most common reason why store forwarding would be blocked is when a load's address range overlaps with a preceding smaller uncompleted store.  See the table of not supported store forwards in the Intel? 64 and IA-32 Architectures Optimization Reference Manual.  The penalty for blocked store forwarding is that the load must wait for the store to complete before it can be issued.",
+        "PublicDescription": "This event counts loads that followed a store to the same address, where the data could not be forwarded inside the pipeline from the store to the load.  The most common reason why store forwarding would be blocked is when a load's address range overlaps with a preceeding smaller uncompleted store.  See the table of not supported store forwards in the Intel? 64 and IA-32 Architectures Optimization Reference Manual.  The penalty for blocked store forwarding is that the load must wait for the store to complete before it can be issued.",
         "EventCode": "0x03",
         "Counter": "0,1,2,3",
         "UMask": "0x2",
@@ -1098,7 +1095,6 @@
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "EventCode": "0x00",
         "Counter": "Fixed counter 2",
         "UMask": "0x2",
         "AnyThread": "1",
diff --git a/tools/perf/pmu-events/arch/x86/knightslanding/cache.json b/tools/perf/pmu-events/arch/x86/knightslanding/cache.json
index e434ec723001..e847b0fd696d 100644
--- a/tools/perf/pmu-events/arch/x86/knightslanding/cache.json
+++ b/tools/perf/pmu-events/arch/x86/knightslanding/cache.json
@@ -32,16 +32,16 @@
         "BriefDescription": "Counts the number of L2 cache misses"
     },
     {
-        "PublicDescription": "This event counts the number of core cycles the fetch stalls because of an icache miss. This is a cumulative count of cycles the NIP stalled for all icache misses. ",
+        "PublicDescription": "This event counts the number of core cycles the fetch stalls because of an icache miss. This is a cumulative count of cycles the NIP stalled for all icache misses.",
         "EventCode": "0x86",
         "Counter": "0,1",
         "UMask": "0x4",
         "EventName": "FETCH_STALL.ICACHE_FILL_PENDING_CYCLES",
         "SampleAfterValue": "200003",
-        "BriefDescription": "Counts the number of core cycles the fetch stalls because of an icache miss. This is a cummulative count of core cycles the fetch stalled for all icache misses. "
+        "BriefDescription": "Counts the number of core cycles the fetch stalls because of an icache miss. This is a cummulative count of core cycles the fetch stalled for all icache misses."
     },
     {
-        "PublicDescription": "This event counts the number of load micro-ops retired that miss in L1 Data cache. Note that prefetch misses will not be counted. ",
+        "PublicDescription": "This event counts the number of load micro-ops retired that miss in L1 Data cache. Note that prefetch misses will not be counted.",
         "EventCode": "0x04",
         "Counter": "0,1",
         "UMask": "0x1",
@@ -115,29 +115,29 @@
     },
     {
         "EventCode": "0xB7",
-        "MSRValue": "0x4000000070 ",
+        "MSRValue": "0x4000000070",
         "Counter": "0,1",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.ANY_PF_L2.OUTSTANDING",
         "MSRIndex": "0x1a6",
         "SampleAfterValue": "100007",
-        "BriefDescription": "Counts any Prefetch requests that are outstanding, per weighted cycle, from the time of the request to when any response is received. The outstanding response should be programmed only on PMC0. ",
+        "BriefDescription": "Counts any Prefetch requests that are outstanding, per weighted cycle, from the time of the request to when any response is received. The oustanding response should be programmed only on PMC0.",
         "Offcore": "1"
     },
     {
         "EventCode": "0xB7",
-        "MSRValue": "0x1000400070 ",
+        "MSRValue": "0x1000400070",
         "Counter": "0,1",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.ANY_PF_L2.L2_HIT_FAR_TILE_M",
         "MSRIndex": "0x1a6,0x1a7",
         "SampleAfterValue": "100007",
-        "BriefDescription": "Counts any Prefetch requests that accounts for responses from a snoop request hit with data forwarded from its Far(not in the same quadrant as the request)-other tile's L2 in M state. ",
+        "BriefDescription": "Counts any Prefetch requests that accounts for responses from a snoop request hit with data forwarded from its Far(not in the same quadrant as the request)-other tile's L2 in M state.",
         "Offcore": "1"
     },
     {
         "EventCode": "0xB7",
-        "MSRValue": "0x0800400070 ",
+        "MSRValue": "0x0800400070",
         "Counter": "0,1",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.ANY_PF_L2.L2_HIT_FAR_TILE_E_F",
@@ -148,29 +148,29 @@
     },
     {
         "EventCode": "0xB7",
-        "MSRValue": "0x1000080070 ",
+        "MSRValue": "0x1000080070",
         "Counter": "0,1",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.ANY_PF_L2.L2_HIT_NEAR_TILE_M",
         "MSRIndex": "0x1a6,0x1a7",
         "SampleAfterValue": "100007",
-        "BriefDescription": "Counts any Prefetch requests that accounts for responses from a snoop request hit with data forwarded from its Near-other tile's L2 in M state. ",
+        "BriefDescription": "Counts any Prefetch requests that accounts for responses from a snoop request hit with data forwarded from its Near-other tile's L2 in M state.",
         "Offcore": "1"
     },
     {
         "EventCode": "0xB7",
-        "MSRValue": "0x0800080070 ",
+        "MSRValue": "0x0800080070",
         "Counter": "0,1",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.ANY_PF_L2.L2_HIT_NEAR_TILE_E_F",
         "MSRIndex": "0x1a6,0x1a7",
         "SampleAfterValue": "100007",
-        "BriefDescription": "Counts any Prefetch requests that accounts for responses from a snoop request hit with data forwarded from its Near-other tile's L2 in E/F state. ",
+        "BriefDescription": "Counts any Prefetch requests that accounts for responses from a snoop request hit with data forwarded from its Near-other tile's L2 in E/F state.",
         "Offcore": "1"
     },
     {
         "EventCode": "0xB7",
-        "MSRValue": "0x0000010070 ",
+        "MSRValue": "0x0000010070",
         "Counter": "0,1",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.ANY_PF_L2.ANY_RESPONSE",
@@ -181,29 +181,29 @@
     },
     {
         "EventCode": "0xB7",
-        "MSRValue": "0x40000032f7 ",
+        "MSRValue": "0x40000032f7",
         "Counter": "0,1",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.ANY_READ.OUTSTANDING",
         "MSRIndex": "0x1a6",
         "SampleAfterValue": "100007",
-        "BriefDescription": "Counts any Read request  that are outstanding, per weighted cycle, from the time of the request to when any response is received. The outstanding response should be programmed only on PMC0. ",
+        "BriefDescription": "Counts any Read request  that are outstanding, per weighted cycle, from the time of the request to when any response is received. The oustanding response should be programmed only on PMC0.",
         "Offcore": "1"
     },
     {
         "EventCode": "0xB7",
-        "MSRValue": "0x10004032f7 ",
+        "MSRValue": "0x10004032f7",
         "Counter": "0,1",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.ANY_READ.L2_HIT_FAR_TILE_M",
         "MSRIndex": "0x1a6,0x1a7",
         "SampleAfterValue": "100007",
-        "BriefDescription": "Counts any Read request  that accounts for responses from a snoop request hit with data forwarded from its Far(not in the same quadrant as the request)-other tile's L2 in M state. ",
+        "BriefDescription": "Counts any Read request  that accounts for responses from a snoop request hit with data forwarded from its Far(not in the same quadrant as the request)-other tile's L2 in M state.",
         "Offcore": "1"
     },
     {
         "EventCode": "0xB7",
-        "MSRValue": "0x08004032f7 ",
+        "MSRValue": "0x08004032f7",
         "Counter": "0,1",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.ANY_READ.L2_HIT_FAR_TILE_E_F",
@@ -214,29 +214,29 @@
     },
     {
         "EventCode": "0xB7",
-        "MSRValue": "0x10000832f7 ",
+        "MSRValue": "0x10000832f7",
         "Counter": "0,1",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.ANY_READ.L2_HIT_NEAR_TILE_M",
         "MSRIndex": "0x1a6,0x1a7",
         "SampleAfterValue": "100007",
-        "BriefDescription": "Counts any Read request  that accounts for responses from a snoop request hit with data forwarded from its Near-other tile's L2 in M state. ",
+        "BriefDescription": "Counts any Read request  that accounts for responses from a snoop request hit with data forwarded from its Near-other tile's L2 in M state.",
         "Offcore": "1"
     },
     {
         "EventCode": "0xB7",
-        "MSRValue": "0x08000832f7 ",
+        "MSRValue": "0x08000832f7",
         "Counter": "0,1",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.ANY_READ.L2_HIT_NEAR_TILE_E_F",
         "MSRIndex": "0x1a6,0x1a7",
         "SampleAfterValue": "100007",
-        "BriefDescription": "Counts any Read request  that accounts for responses from a snoop request hit with data forwarded from its Near-other tile's L2 in E/F state. ",
+        "BriefDescription": "Counts any Read request  that accounts for responses from a snoop request hit with data forwarded from its Near-other tile's L2 in E/F state.",
         "Offcore": "1"
     },
     {
         "EventCode": "0xB7",
-        "MSRValue": "0x00000132f7 ",
+        "MSRValue": "0x00000132f7",
         "Counter": "0,1",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.ANY_READ.ANY_RESPONSE",
@@ -247,29 +247,29 @@
     },
     {
         "EventCode": "0xB7",
-        "MSRValue": "0x4000000044 ",
+        "MSRValue": "0x4000000044",
         "Counter": "0,1",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.ANY_CODE_RD.OUTSTANDING",
         "MSRIndex": "0x1a6",
         "SampleAfterValue": "100007",
-        "BriefDescription": "Counts Demand code reads and prefetch code read requests  that are outstanding, per weighted cycle, from the time of the request to when any response is received. The outstanding response should be programmed only on PMC0. ",
+        "BriefDescription": "Counts Demand code reads and prefetch code read requests  that are outstanding, per weighted cycle, from the time of the request to when any response is received. The oustanding response should be programmed only on PMC0.",
         "Offcore": "1"
     },
     {
         "EventCode": "0xB7",
-        "MSRValue": "0x1000400044 ",
+        "MSRValue": "0x1000400044",
         "Counter": "0,1",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.ANY_CODE_RD.L2_HIT_FAR_TILE_M",
         "MSRIndex": "0x1a6,0x1a7",
         "SampleAfterValue": "100007",
-        "BriefDescription": "Counts Demand code reads and prefetch code read requests  that accounts for responses from a snoop request hit with data forwarded from its Far(not in the same quadrant as the request)-other tile's L2 in M state. ",
+        "BriefDescription": "Counts Demand code reads and prefetch code read requests  that accounts for responses from a snoop request hit with data forwarded from its Far(not in the same quadrant as the request)-other tile's L2 in M state.",
         "Offcore": "1"
     },
     {
         "EventCode": "0xB7",
-        "MSRValue": "0x0800400044 ",
+        "MSRValue": "0x0800400044",
         "Counter": "0,1",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.ANY_CODE_RD.L2_HIT_FAR_TILE_E_F",
@@ -280,29 +280,29 @@
     },
     {
         "EventCode": "0xB7",
-        "MSRValue": "0x1000080044 ",
+        "MSRValue": "0x1000080044",
         "Counter": "0,1",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.ANY_CODE_RD.L2_HIT_NEAR_TILE_M",
         "MSRIndex": "0x1a6,0x1a7",
         "SampleAfterValue": "100007",
-        "BriefDescription": "Counts Demand code reads and prefetch code read requests  that accounts for responses from a snoop request hit with data forwarded from its Near-other tile's L2 in M state. ",
+        "BriefDescription": "Counts Demand code reads and prefetch code read requests  that accounts for responses from a snoop request hit with data forwarded from its Near-other tile's L2 in M state.",
         "Offcore": "1"
     },
     {
         "EventCode": "0xB7",
-        "MSRValue": "0x0800080044 ",
+        "MSRValue": "0x0800080044",
         "Counter": "0,1",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.ANY_CODE_RD.L2_HIT_NEAR_TILE_E_F",
         "MSRIndex": "0x1a6,0x1a7",
         "SampleAfterValue": "100007",
-        "BriefDescription": "Counts Demand code reads and prefetch code read requests  that accounts for responses from a snoop request hit with data forwarded from its Near-other tile's L2 in E/F state. ",
+        "BriefDescription": "Counts Demand code reads and prefetch code read requests  that accounts for responses from a snoop request hit with data forwarded from its Near-other tile's L2 in E/F state.",
         "Offcore": "1"
     },
     {
         "EventCode": "0xB7",
-        "MSRValue": "0x0000010044 ",
+        "MSRValue": "0x0000010044",
         "Counter": "0,1",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.ANY_CODE_RD.ANY_RESPONSE",
@@ -313,29 +313,29 @@
     },
     {
         "EventCode": "0xB7",
-        "MSRValue": "0x4000000022 ",
+        "MSRValue": "0x4000000022",
         "Counter": "0,1",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.ANY_RFO.OUTSTANDING",
         "MSRIndex": "0x1a6",
         "SampleAfterValue": "100007",
-        "BriefDescription": "Counts Demand cacheable data write requests  that are outstanding, per weighted cycle, from the time of the request to when any response is received. The outstanding response should be programmed only on PMC0. ",
+        "BriefDescription": "Counts Demand cacheable data write requests  that are outstanding, per weighted cycle, from the time of the request to when any response is received. The oustanding response should be programmed only on PMC0.",
         "Offcore": "1"
     },
     {
         "EventCode": "0xB7",
-        "MSRValue": "0x1000400022 ",
+        "MSRValue": "0x1000400022",
         "Counter": "0,1",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.ANY_RFO.L2_HIT_FAR_TILE_M",
         "MSRIndex": "0x1a6,0x1a7",
         "SampleAfterValue": "100007",
-        "BriefDescription": "Counts Demand cacheable data write requests  that accounts for responses from a snoop request hit with data forwarded from its Far(not in the same quadrant as the request)-other tile's L2 in M state. ",
+        "BriefDescription": "Counts Demand cacheable data write requests  that accounts for responses from a snoop request hit with data forwarded from its Far(not in the same quadrant as the request)-other tile's L2 in M state.",
         "Offcore": "1"
     },
     {
         "EventCode": "0xB7",
-        "MSRValue": "0x0800400022 ",
+        "MSRValue": "0x0800400022",
         "Counter": "0,1",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.ANY_RFO.L2_HIT_FAR_TILE_E_F",
@@ -346,29 +346,29 @@
     },
     {
         "EventCode": "0xB7",
-        "MSRValue": "0x1000080022 ",
+        "MSRValue": "0x1000080022",
         "Counter": "0,1",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.ANY_RFO.L2_HIT_NEAR_TILE_M",
         "MSRIndex": "0x1a6,0x1a7",
         "SampleAfterValue": "100007",
-        "BriefDescription": "Counts Demand cacheable data write requests  that accounts for responses from a snoop request hit with data forwarded from its Near-other tile's L2 in M state. ",
+        "BriefDescription": "Counts Demand cacheable data write requests  that accounts for responses from a snoop request hit with data forwarded from its Near-other tile's L2 in M state.",
         "Offcore": "1"
     },
     {
         "EventCode": "0xB7",
-        "MSRValue": "0x0800080022 ",
+        "MSRValue": "0x0800080022",
         "Counter": "0,1",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.ANY_RFO.L2_HIT_NEAR_TILE_E_F",
         "MSRIndex": "0x1a6,0x1a7",
         "SampleAfterValue": "100007",
-        "BriefDescription": "Counts Demand cacheable data write requests  that accounts for responses from a snoop request hit with data forwarded from its Near-other tile's L2 in E/F state. ",
+        "BriefDescription": "Counts Demand cacheable data write requests  that accounts for responses from a snoop request hit with data forwarded from its Near-other tile's L2 in E/F state.",
         "Offcore": "1"
     },
     {
         "EventCode": "0xB7",
-        "MSRValue": "0x0000010022 ",
+        "MSRValue": "0x0000010022",
         "Counter": "0,1",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.ANY_RFO.ANY_RESPONSE",
@@ -379,29 +379,29 @@
     },
     {
         "EventCode": "0xB7",
-        "MSRValue": "0x4000003091 ",
+        "MSRValue": "0x4000003091",
         "Counter": "0,1",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.ANY_DATA_RD.OUTSTANDING",
         "MSRIndex": "0x1a6",
         "SampleAfterValue": "100007",
-        "BriefDescription": "Counts Demand cacheable data and L1 prefetch data read requests  that are outstanding, per weighted cycle, from the time of the request to when any response is received. The outstanding response should be programmed only on PMC0. ",
+        "BriefDescription": "Counts Demand cacheable data and L1 prefetch data read requests  that are outstanding, per weighted cycle, from the time of the request to when any response is received. The oustanding response should be programmed only on PMC0.",
         "Offcore": "1"
     },
     {
         "EventCode": "0xB7",
-        "MSRValue": "0x1000403091 ",
+        "MSRValue": "0x1000403091",
         "Counter": "0,1",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.ANY_DATA_RD.L2_HIT_FAR_TILE_M",
         "MSRIndex": "0x1a6,0x1a7",
         "SampleAfterValue": "100007",
-        "BriefDescription": "Counts Demand cacheable data and L1 prefetch data read requests  that accounts for responses from a snoop request hit with data forwarded from its Far(not in the same quadrant as the request)-other tile's L2 in M state. ",
+        "BriefDescription": "Counts Demand cacheable data and L1 prefetch data read requests  that accounts for responses from a snoop request hit with data forwarded from its Far(not in the same quadrant as the request)-other tile's L2 in M state.",
         "Offcore": "1"
     },
     {
         "EventCode": "0xB7",
-        "MSRValue": "0x0800403091 ",
+        "MSRValue": "0x0800403091",
         "Counter": "0,1",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.ANY_DATA_RD.L2_HIT_FAR_TILE_E_F",
@@ -412,29 +412,29 @@
     },
     {
         "EventCode": "0xB7",
-        "MSRValue": "0x1000083091 ",
+        "MSRValue": "0x1000083091",
         "Counter": "0,1",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.ANY_DATA_RD.L2_HIT_NEAR_TILE_M",
         "MSRIndex": "0x1a6,0x1a7",
         "SampleAfterValue": "100007",
-        "BriefDescription": "Counts Demand cacheable data and L1 prefetch data read requests  that accounts for responses from a snoop request hit with data forwarded from its Near-other tile's L2 in M state. ",
+        "BriefDescription": "Counts Demand cacheable data and L1 prefetch data read requests  that accounts for responses from a snoop request hit with data forwarded from its Near-other tile's L2 in M state.",
         "Offcore": "1"
     },
     {
         "EventCode": "0xB7",
-        "MSRValue": "0x0800083091 ",
+        "MSRValue": "0x0800083091",
         "Counter": "0,1",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.ANY_DATA_RD.L2_HIT_NEAR_TILE_E_F",
         "MSRIndex": "0x1a6,0x1a7",
         "SampleAfterValue": "100007",
-        "BriefDescription": "Counts Demand cacheable data and L1 prefetch data read requests  that accounts for responses from a snoop request hit with data forwarded from its Near-other tile's L2 in E/F state. ",
+        "BriefDescription": "Counts Demand cacheable data and L1 prefetch data read requests  that accounts for responses from a snoop request hit with data forwarded from its Near-other tile's L2 in E/F state.",
         "Offcore": "1"
     },
     {
         "EventCode": "0xB7",
-        "MSRValue": "0x0000013091 ",
+        "MSRValue": "0x0000013091",
         "Counter": "0,1",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.ANY_DATA_RD.ANY_RESPONSE",
@@ -445,29 +445,29 @@
     },
     {
         "EventCode": "0xB7",
-        "MSRValue": "0x4000008000 ",
+        "MSRValue": "0x4000008000",
         "Counter": "0,1",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.ANY_REQUEST.OUTSTANDING",
         "MSRIndex": "0x1a6",
         "SampleAfterValue": "100007",
-        "BriefDescription": "Counts any request that are outstanding, per weighted cycle, from the time of the request to when any response is received. The outstanding response should be programmed only on PMC0. ",
+        "BriefDescription": "Counts any request that are outstanding, per weighted cycle, from the time of the request to when any response is received. The oustanding response should be programmed only on PMC0.",
         "Offcore": "1"
     },
     {
         "EventCode": "0xB7",
-        "MSRValue": "0x1000408000 ",
+        "MSRValue": "0x1000408000",
         "Counter": "0,1",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.ANY_REQUEST.L2_HIT_FAR_TILE_M",
         "MSRIndex": "0x1a6,0x1a7",
         "SampleAfterValue": "100007",
-        "BriefDescription": "Counts any request that accounts for responses from a snoop request hit with data forwarded from its Far(not in the same quadrant as the request)-other tile's L2 in M state. ",
+        "BriefDescription": "Counts any request that accounts for responses from a snoop request hit with data forwarded from its Far(not in the same quadrant as the request)-other tile's L2 in M state.",
         "Offcore": "1"
     },
     {
         "EventCode": "0xB7",
-        "MSRValue": "0x0800408000 ",
+        "MSRValue": "0x0800408000",
         "Counter": "0,1",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.ANY_REQUEST.L2_HIT_FAR_TILE_E_F",
@@ -478,29 +478,29 @@
     },
     {
         "EventCode": "0xB7",
-        "MSRValue": "0x1000088000 ",
+        "MSRValue": "0x1000088000",
         "Counter": "0,1",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.ANY_REQUEST.L2_HIT_NEAR_TILE_M",
         "MSRIndex": "0x1a6,0x1a7",
         "SampleAfterValue": "100007",
-        "BriefDescription": "Counts any request that accounts for responses from a snoop request hit with data forwarded from its Near-other tile's L2 in M state. ",
+        "BriefDescription": "Counts any request that accounts for responses from a snoop request hit with data forwarded from its Near-other tile's L2 in M state.",
         "Offcore": "1"
     },
     {
         "EventCode": "0xB7",
-        "MSRValue": "0x0800088000 ",
+        "MSRValue": "0x0800088000",
         "Counter": "0,1",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.ANY_REQUEST.L2_HIT_NEAR_TILE_E_F",
         "MSRIndex": "0x1a6,0x1a7",
         "SampleAfterValue": "100007",
-        "BriefDescription": "Counts any request that accounts for responses from a snoop request hit with data forwarded from its Near-other tile's L2 in E/F state. ",
+        "BriefDescription": "Counts any request that accounts for responses from a snoop request hit with data forwarded from its Near-other tile's L2 in E/F state.",
         "Offcore": "1"
     },
     {
         "EventCode": "0xB7",
-        "MSRValue": "0x0000018000 ",
+        "MSRValue": "0x0000018000",
         "Counter": "0,1",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.ANY_REQUEST.ANY_RESPONSE",
@@ -511,7 +511,7 @@
     },
     {
         "EventCode": "0xB7",
-        "MSRValue": "0x0000014800 ",
+        "MSRValue": "0x0000014800",
         "Counter": "0,1",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.STREAMING_STORES.ANY_RESPONSE",
@@ -522,7 +522,7 @@
     },
     {
         "EventCode": "0xB7",
-        "MSRValue": "0x0000014000 ",
+        "MSRValue": "0x0000014000",
         "Counter": "0,1",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.PARTIAL_STREAMING_STORES.ANY_RESPONSE",
@@ -533,29 +533,29 @@
     },
     {
         "EventCode": "0xB7",
-        "MSRValue": "0x4000002000 ",
+        "MSRValue": "0x4000002000",
         "Counter": "0,1",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.PF_L1_DATA_RD.OUTSTANDING",
         "MSRIndex": "0x1a6",
         "SampleAfterValue": "100007",
-        "BriefDescription": "Counts L1 data HW prefetches that are outstanding, per weighted cycle, from the time of the request to when any response is received. The outstanding response should be programmed only on PMC0. ",
+        "BriefDescription": "Counts L1 data HW prefetches that are outstanding, per weighted cycle, from the time of the request to when any response is received. The oustanding response should be programmed only on PMC0.",
         "Offcore": "1"
     },
     {
         "EventCode": "0xB7",
-        "MSRValue": "0x1000402000 ",
+        "MSRValue": "0x1000402000",
         "Counter": "0,1",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.PF_L1_DATA_RD.L2_HIT_FAR_TILE_M",
         "MSRIndex": "0x1a6,0x1a7",
         "SampleAfterValue": "100007",
-        "BriefDescription": "Counts L1 data HW prefetches that accounts for responses from a snoop request hit with data forwarded from its Far(not in the same quadrant as the request)-other tile's L2 in M state. ",
+        "BriefDescription": "Counts L1 data HW prefetches that accounts for responses from a snoop request hit with data forwarded from its Far(not in the same quadrant as the request)-other tile's L2 in M state.",
         "Offcore": "1"
     },
     {
         "EventCode": "0xB7",
-        "MSRValue": "0x0800402000 ",
+        "MSRValue": "0x0800402000",
         "Counter": "0,1",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.PF_L1_DATA_RD.L2_HIT_FAR_TILE_E_F",
@@ -566,29 +566,29 @@
     },
     {
         "EventCode": "0xB7",
-        "MSRValue": "0x1000082000 ",
+        "MSRValue": "0x1000082000",
         "Counter": "0,1",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.PF_L1_DATA_RD.L2_HIT_NEAR_TILE_M",
         "MSRIndex": "0x1a6,0x1a7",
         "SampleAfterValue": "100007",
-        "BriefDescription": "Counts L1 data HW prefetches that accounts for responses from a snoop request hit with data forwarded from its Near-other tile's L2 in M state. ",
+        "BriefDescription": "Counts L1 data HW prefetches that accounts for responses from a snoop request hit with data forwarded from its Near-other tile's L2 in M state.",
         "Offcore": "1"
     },
     {
         "EventCode": "0xB7",
-        "MSRValue": "0x0800082000 ",
+        "MSRValue": "0x0800082000",
         "Counter": "0,1",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.PF_L1_DATA_RD.L2_HIT_NEAR_TILE_E_F",
         "MSRIndex": "0x1a6,0x1a7",
         "SampleAfterValue": "100007",
-        "BriefDescription": "Counts L1 data HW prefetches that accounts for responses from a snoop request hit with data forwarded from its Near-other tile's L2 in E/F state. ",
+        "BriefDescription": "Counts L1 data HW prefetches that accounts for responses from a snoop request hit with data forwarded from its Near-other tile's L2 in E/F state.",
         "Offcore": "1"
     },
     {
         "EventCode": "0xB7",
-        "MSRValue": "0x0000012000 ",
+        "MSRValue": "0x0000012000",
         "Counter": "0,1",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.PF_L1_DATA_RD.ANY_RESPONSE",
@@ -599,29 +599,29 @@
     },
     {
         "EventCode": "0xB7",
-        "MSRValue": "0x4000001000 ",
+        "MSRValue": "0x4000001000",
         "Counter": "0,1",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.PF_SOFTWARE.OUTSTANDING",
         "MSRIndex": "0x1a6",
         "SampleAfterValue": "100007",
-        "BriefDescription": "Counts Software Prefetches that are outstanding, per weighted cycle, from the time of the request to when any response is received. The outstanding response should be programmed only on PMC0. ",
+        "BriefDescription": "Counts Software Prefetches that are outstanding, per weighted cycle, from the time of the request to when any response is received. The oustanding response should be programmed only on PMC0.",
         "Offcore": "1"
     },
     {
         "EventCode": "0xB7",
-        "MSRValue": "0x1000401000 ",
+        "MSRValue": "0x1000401000",
         "Counter": "0,1",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.PF_SOFTWARE.L2_HIT_FAR_TILE_M",
         "MSRIndex": "0x1a6,0x1a7",
         "SampleAfterValue": "100007",
-        "BriefDescription": "Counts Software Prefetches that accounts for responses from a snoop request hit with data forwarded from its Far(not in the same quadrant as the request)-other tile's L2 in M state. ",
+        "BriefDescription": "Counts Software Prefetches that accounts for responses from a snoop request hit with data forwarded from its Far(not in the same quadrant as the request)-other tile's L2 in M state.",
         "Offcore": "1"
     },
     {
         "EventCode": "0xB7",
-        "MSRValue": "0x0800401000 ",
+        "MSRValue": "0x0800401000",
         "Counter": "0,1",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.PF_SOFTWARE.L2_HIT_FAR_TILE_E_F",
@@ -632,29 +632,29 @@
     },
     {
         "EventCode": "0xB7",
-        "MSRValue": "0x1000081000 ",
+        "MSRValue": "0x1000081000",
         "Counter": "0,1",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.PF_SOFTWARE.L2_HIT_NEAR_TILE_M",
         "MSRIndex": "0x1a6,0x1a7",
         "SampleAfterValue": "100007",
-        "BriefDescription": "Counts Software Prefetches that accounts for responses from a snoop request hit with data forwarded from its Near-other tile's L2 in M state. ",
+        "BriefDescription": "Counts Software Prefetches that accounts for responses from a snoop request hit with data forwarded from its Near-other tile's L2 in M state.",
         "Offcore": "1"
     },
     {
         "EventCode": "0xB7",
-        "MSRValue": "0x0800081000 ",
+        "MSRValue": "0x0800081000",
         "Counter": "0,1",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.PF_SOFTWARE.L2_HIT_NEAR_TILE_E_F",
         "MSRIndex": "0x1a6,0x1a7",
         "SampleAfterValue": "100007",
-        "BriefDescription": "Counts Software Prefetches that accounts for responses from a snoop request hit with data forwarded from its Near-other tile's L2 in E/F state. ",
+        "BriefDescription": "Counts Software Prefetches that accounts for responses from a snoop request hit with data forwarded from its Near-other tile's L2 in E/F state.",
         "Offcore": "1"
     },
     {
         "EventCode": "0xB7",
-        "MSRValue": "0x0000011000 ",
+        "MSRValue": "0x0000011000",
         "Counter": "0,1",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.PF_SOFTWARE.ANY_RESPONSE",
@@ -665,7 +665,7 @@
     },
     {
         "EventCode": "0xB7",
-        "MSRValue": "0x0000010800 ",
+        "MSRValue": "0x0000010800",
         "Counter": "0,1",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.FULL_STREAMING_STORES.ANY_RESPONSE",
@@ -676,29 +676,29 @@
     },
     {
         "EventCode": "0xB7",
-        "MSRValue": "0x4000000400 ",
+        "MSRValue": "0x4000000400",
         "Counter": "0,1",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.BUS_LOCKS.OUTSTANDING",
         "MSRIndex": "0x1a6",
         "SampleAfterValue": "100007",
-        "BriefDescription": "Counts Bus locks and split lock requests that are outstanding, per weighted cycle, from the time of the request to when any response is received. The outstanding response should be programmed only on PMC0. ",
+        "BriefDescription": "Counts Bus locks and split lock requests that are outstanding, per weighted cycle, from the time of the request to when any response is received. The oustanding response should be programmed only on PMC0.",
         "Offcore": "1"
     },
     {
         "EventCode": "0xB7",
-        "MSRValue": "0x1000400400 ",
+        "MSRValue": "0x1000400400",
         "Counter": "0,1",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.BUS_LOCKS.L2_HIT_FAR_TILE_M",
         "MSRIndex": "0x1a6,0x1a7",
         "SampleAfterValue": "100007",
-        "BriefDescription": "Counts Bus locks and split lock requests that accounts for responses from a snoop request hit with data forwarded from its Far(not in the same quadrant as the request)-other tile's L2 in M state. ",
+        "BriefDescription": "Counts Bus locks and split lock requests that accounts for responses from a snoop request hit with data forwarded from its Far(not in the same quadrant as the request)-other tile's L2 in M state.",
         "Offcore": "1"
     },
     {
         "EventCode": "0xB7",
-        "MSRValue": "0x0800400400 ",
+        "MSRValue": "0x0800400400",
         "Counter": "0,1",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.BUS_LOCKS.L2_HIT_FAR_TILE_E_F",
@@ -709,29 +709,29 @@
     },
     {
         "EventCode": "0xB7",
-        "MSRValue": "0x1000080400 ",
+        "MSRValue": "0x1000080400",
         "Counter": "0,1",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.BUS_LOCKS.L2_HIT_NEAR_TILE_M",
         "MSRIndex": "0x1a6,0x1a7",
         "SampleAfterValue": "100007",
-        "BriefDescription": "Counts Bus locks and split lock requests that accounts for responses from a snoop request hit with data forwarded from its Near-other tile's L2 in M state. ",
+        "BriefDescription": "Counts Bus locks and split lock requests that accounts for responses from a snoop request hit with data forwarded from its Near-other tile's L2 in M state.",
         "Offcore": "1"
     },
     {
         "EventCode": "0xB7",
-        "MSRValue": "0x0800080400 ",
+        "MSRValue": "0x0800080400",
         "Counter": "0,1",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.BUS_LOCKS.L2_HIT_NEAR_TILE_E_F",
         "MSRIndex": "0x1a6,0x1a7",
         "SampleAfterValue": "100007",
-        "BriefDescription": "Counts Bus locks and split lock requests that accounts for responses from a snoop request hit with data forwarded from its Near-other tile's L2 in E/F state. ",
+        "BriefDescription": "Counts Bus locks and split lock requests that accounts for responses from a snoop request hit with data forwarded from its Near-other tile's L2 in E/F state.",
         "Offcore": "1"
     },
     {
         "EventCode": "0xB7",
-        "MSRValue": "0x0000010400 ",
+        "MSRValue": "0x0000010400",
         "Counter": "0,1",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.BUS_LOCKS.ANY_RESPONSE",
@@ -742,29 +742,29 @@
     },
     {
         "EventCode": "0xB7",
-        "MSRValue": "0x4000000200 ",
+        "MSRValue": "0x4000000200",
         "Counter": "0,1",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.UC_CODE_READS.OUTSTANDING",
         "MSRIndex": "0x1a6",
         "SampleAfterValue": "100007",
-        "BriefDescription": "Counts UC code reads (valid only for Outstanding response type)  that are outstanding, per weighted cycle, from the time of the request to when any response is received. The outstanding response should be programmed only on PMC0. ",
+        "BriefDescription": "Counts UC code reads (valid only for Outstanding response type)  that are outstanding, per weighted cycle, from the time of the request to when any response is received. The oustanding response should be programmed only on PMC0.",
         "Offcore": "1"
     },
     {
         "EventCode": "0xB7",
-        "MSRValue": "0x1000400200 ",
+        "MSRValue": "0x1000400200",
         "Counter": "0,1",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.UC_CODE_READS.L2_HIT_FAR_TILE_M",
         "MSRIndex": "0x1a6,0x1a7",
         "SampleAfterValue": "100007",
-        "BriefDescription": "Counts UC code reads (valid only for Outstanding response type)  that accounts for responses from a snoop request hit with data forwarded from its Far(not in the same quadrant as the request)-other tile's L2 in M state. ",
+        "BriefDescription": "Counts UC code reads (valid only for Outstanding response type)  that accounts for responses from a snoop request hit with data forwarded from its Far(not in the same quadrant as the request)-other tile's L2 in M state.",
         "Offcore": "1"
     },
     {
         "EventCode": "0xB7",
-        "MSRValue": "0x0800400200 ",
+        "MSRValue": "0x0800400200",
         "Counter": "0,1",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.UC_CODE_READS.L2_HIT_FAR_TILE_E_F",
@@ -775,29 +775,29 @@
     },
     {
         "EventCode": "0xB7",
-        "MSRValue": "0x1000080200 ",
+        "MSRValue": "0x1000080200",
         "Counter": "0,1",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.UC_CODE_READS.L2_HIT_NEAR_TILE_M",
         "MSRIndex": "0x1a6,0x1a7",
         "SampleAfterValue": "100007",
-        "BriefDescription": "Counts UC code reads (valid only for Outstanding response type)  that accounts for responses from a snoop request hit with data forwarded from its Near-other tile's L2 in M state. ",
+        "BriefDescription": "Counts UC code reads (valid only for Outstanding response type)  that accounts for responses from a snoop request hit with data forwarded from its Near-other tile's L2 in M state.",
         "Offcore": "1"
     },
     {
         "EventCode": "0xB7",
-        "MSRValue": "0x0800080200 ",
+        "MSRValue": "0x0800080200",
         "Counter": "0,1",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.UC_CODE_READS.L2_HIT_NEAR_TILE_E_F",
         "MSRIndex": "0x1a6,0x1a7",
         "SampleAfterValue": "100007",
-        "BriefDescription": "Counts UC code reads (valid only for Outstanding response type)  that accounts for responses from a snoop request hit with data forwarded from its Near-other tile's L2 in E/F state. ",
+        "BriefDescription": "Counts UC code reads (valid only for Outstanding response type)  that accounts for responses from a snoop request hit with data forwarded from its Near-other tile's L2 in E/F state.",
         "Offcore": "1"
     },
     {
         "EventCode": "0xB7",
-        "MSRValue": "0x0000010200 ",
+        "MSRValue": "0x0000010200",
         "Counter": "0,1",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.UC_CODE_READS.ANY_RESPONSE",
@@ -808,18 +808,18 @@
     },
     {
         "EventCode": "0xB7",
-        "MSRValue": "0x1000400100 ",
+        "MSRValue": "0x1000400100",
         "Counter": "0,1",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.PARTIAL_WRITES.L2_HIT_FAR_TILE_M",
         "MSRIndex": "0x1a7",
         "SampleAfterValue": "100007",
-        "BriefDescription": "Counts Partial writes (UC or WT or WP and should be programmed on PMC1) that accounts for responses from a snoop request hit with data forwarded from its Far(not in the same quadrant as the request)-other tile's L2 in M state. ",
+        "BriefDescription": "Counts Partial writes (UC or WT or WP and should be programmed on PMC1) that accounts for responses from a snoop request hit with data forwarded from its Far(not in the same quadrant as the request)-other tile's L2 in M state.",
         "Offcore": "1"
     },
     {
         "EventCode": "0xB7",
-        "MSRValue": "0x0800400100 ",
+        "MSRValue": "0x0800400100",
         "Counter": "0,1",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.PARTIAL_WRITES.L2_HIT_FAR_TILE_E_F",
@@ -830,29 +830,29 @@
     },
     {
         "EventCode": "0xB7",
-        "MSRValue": "0x1000080100 ",
+        "MSRValue": "0x1000080100",
         "Counter": "0,1",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.PARTIAL_WRITES.L2_HIT_NEAR_TILE_M",
         "MSRIndex": "0x1a7",
         "SampleAfterValue": "100007",
-        "BriefDescription": "Counts Partial writes (UC or WT or WP and should be programmed on PMC1) that accounts for responses from a snoop request hit with data forwarded from its Near-other tile's L2 in M state. ",
+        "BriefDescription": "Counts Partial writes (UC or WT or WP and should be programmed on PMC1) that accounts for responses from a snoop request hit with data forwarded from its Near-other tile's L2 in M state.",
         "Offcore": "1"
     },
     {
         "EventCode": "0xB7",
-        "MSRValue": "0x0800080100 ",
+        "MSRValue": "0x0800080100",
         "Counter": "0,1",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.PARTIAL_WRITES.L2_HIT_NEAR_TILE_E_F",
         "MSRIndex": "0x1a7",
         "SampleAfterValue": "100007",
-        "BriefDescription": "Counts Partial writes (UC or WT or WP and should be programmed on PMC1) that accounts for responses from a snoop request hit with data forwarded from its Near-other tile's L2 in E/F state. ",
+        "BriefDescription": "Counts Partial writes (UC or WT or WP and should be programmed on PMC1) that accounts for responses from a snoop request hit with data forwarded from its Near-other tile's L2 in E/F state.",
         "Offcore": "1"
     },
     {
         "EventCode": "0xB7",
-        "MSRValue": "0x0000010100 ",
+        "MSRValue": "0x0000010100",
         "Counter": "0,1",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.PARTIAL_WRITES.ANY_RESPONSE",
@@ -863,29 +863,29 @@
     },
     {
         "EventCode": "0xB7",
-        "MSRValue": "0x4000000080 ",
+        "MSRValue": "0x4000000080",
         "Counter": "0,1",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.PARTIAL_READS.OUTSTANDING",
         "MSRIndex": "0x1a6",
         "SampleAfterValue": "100007",
-        "BriefDescription": "Counts Partial reads (UC or WC and is valid only for Outstanding response type).  that are outstanding, per weighted cycle, from the time of the request to when any response is received. The outstanding response should be programmed only on PMC0. ",
+        "BriefDescription": "Counts Partial reads (UC or WC and is valid only for Outstanding response type).  that are outstanding, per weighted cycle, from the time of the request to when any response is received. The oustanding response should be programmed only on PMC0.",
         "Offcore": "1"
     },
     {
         "EventCode": "0xB7",
-        "MSRValue": "0x1000400080 ",
+        "MSRValue": "0x1000400080",
         "Counter": "0,1",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.PARTIAL_READS.L2_HIT_FAR_TILE_M",
         "MSRIndex": "0x1a6,0x1a7",
         "SampleAfterValue": "100007",
-        "BriefDescription": "Counts Partial reads (UC or WC and is valid only for Outstanding response type).  that accounts for responses from a snoop request hit with data forwarded from its Far(not in the same quadrant as the request)-other tile's L2 in M state. ",
+        "BriefDescription": "Counts Partial reads (UC or WC and is valid only for Outstanding response type).  that accounts for responses from a snoop request hit with data forwarded from its Far(not in the same quadrant as the request)-other tile's L2 in M state.",
         "Offcore": "1"
     },
     {
         "EventCode": "0xB7",
-        "MSRValue": "0x0800400080 ",
+        "MSRValue": "0x0800400080",
         "Counter": "0,1",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.PARTIAL_READS.L2_HIT_FAR_TILE_E_F",
@@ -896,29 +896,29 @@
     },
     {
         "EventCode": "0xB7",
-        "MSRValue": "0x1000080080 ",
+        "MSRValue": "0x1000080080",
         "Counter": "0,1",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.PARTIAL_READS.L2_HIT_NEAR_TILE_M",
         "MSRIndex": "0x1a6,0x1a7",
         "SampleAfterValue": "100007",
-        "BriefDescription": "Counts Partial reads (UC or WC and is valid only for Outstanding response type).  that accounts for responses from a snoop request hit with data forwarded from its Near-other tile's L2 in M state. ",
+        "BriefDescription": "Counts Partial reads (UC or WC and is valid only for Outstanding response type).  that accounts for responses from a snoop request hit with data forwarded from its Near-other tile's L2 in M state.",
         "Offcore": "1"
     },
     {
         "EventCode": "0xB7",
-        "MSRValue": "0x0800080080 ",
+        "MSRValue": "0x0800080080",
         "Counter": "0,1",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.PARTIAL_READS.L2_HIT_NEAR_TILE_E_F",
         "MSRIndex": "0x1a6,0x1a7",
         "SampleAfterValue": "100007",
-        "BriefDescription": "Counts Partial reads (UC or WC and is valid only for Outstanding response type).  that accounts for responses from a snoop request hit with data forwarded from its Near-other tile's L2 in E/F state. ",
+        "BriefDescription": "Counts Partial reads (UC or WC and is valid only for Outstanding response type).  that accounts for responses from a snoop request hit with data forwarded from its Near-other tile's L2 in E/F state.",
         "Offcore": "1"
     },
     {
         "EventCode": "0xB7",
-        "MSRValue": "0x0000010080 ",
+        "MSRValue": "0x0000010080",
         "Counter": "0,1",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.PARTIAL_READS.ANY_RESPONSE",
@@ -929,29 +929,29 @@
     },
     {
         "EventCode": "0xB7",
-        "MSRValue": "0x4000000040 ",
+        "MSRValue": "0x4000000040",
         "Counter": "0,1",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.PF_L2_CODE_RD.OUTSTANDING",
         "MSRIndex": "0x1a6",
         "SampleAfterValue": "100007",
-        "BriefDescription": "Counts L2 code HW prefetches that are outstanding, per weighted cycle, from the time of the request to when any response is received. The outstanding response should be programmed only on PMC0. ",
+        "BriefDescription": "Counts L2 code HW prefetches that are outstanding, per weighted cycle, from the time of the request to when any response is received. The oustanding response should be programmed only on PMC0.",
         "Offcore": "1"
     },
     {
         "EventCode": "0xB7",
-        "MSRValue": "0x1000400040 ",
+        "MSRValue": "0x1000400040",
         "Counter": "0,1",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.PF_L2_CODE_RD.L2_HIT_FAR_TILE_M",
         "MSRIndex": "0x1a6,0x1a7",
         "SampleAfterValue": "100007",
-        "BriefDescription": "Counts L2 code HW prefetches that accounts for responses from a snoop request hit with data forwarded from its Far(not in the same quadrant as the request)-other tile's L2 in M state. ",
+        "BriefDescription": "Counts L2 code HW prefetches that accounts for responses from a snoop request hit with data forwarded from its Far(not in the same quadrant as the request)-other tile's L2 in M state.",
         "Offcore": "1"
     },
     {
         "EventCode": "0xB7",
-        "MSRValue": "0x0800400040 ",
+        "MSRValue": "0x0800400040",
         "Counter": "0,1",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.PF_L2_CODE_RD.L2_HIT_FAR_TILE_E_F",
@@ -962,29 +962,29 @@
     },
     {
         "EventCode": "0xB7",
-        "MSRValue": "0x1000080040 ",
+        "MSRValue": "0x1000080040",
         "Counter": "0,1",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.PF_L2_CODE_RD.L2_HIT_NEAR_TILE_M",
         "MSRIndex": "0x1a6,0x1a7",
         "SampleAfterValue": "100007",
-        "BriefDescription": "Counts L2 code HW prefetches that accounts for responses from a snoop request hit with data forwarded from its Near-other tile's L2 in M state. ",
+        "BriefDescription": "Counts L2 code HW prefetches that accounts for responses from a snoop request hit with data forwarded from its Near-other tile's L2 in M state.",
         "Offcore": "1"
     },
     {
         "EventCode": "0xB7",
-        "MSRValue": "0x0800080040 ",
+        "MSRValue": "0x0800080040",
         "Counter": "0,1",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.PF_L2_CODE_RD.L2_HIT_NEAR_TILE_E_F",
         "MSRIndex": "0x1a6,0x1a7",
         "SampleAfterValue": "100007",
-        "BriefDescription": "Counts L2 code HW prefetches that accounts for responses from a snoop request hit with data forwarded from its Near-other tile's L2 in E/F state. ",
+        "BriefDescription": "Counts L2 code HW prefetches that accounts for responses from a snoop request hit with data forwarded from its Near-other tile's L2 in E/F state.",
         "Offcore": "1"
     },
     {
         "EventCode": "0xB7",
-        "MSRValue": "0x0000010040 ",
+        "MSRValue": "0x0000010040",
         "Counter": "0,1",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.PF_L2_CODE_RD.ANY_RESPONSE",
@@ -995,18 +995,18 @@
     },
     {
         "EventCode": "0xB7",
-        "MSRValue": "0x1000400020 ",
+        "MSRValue": "0x1000400020",
         "Counter": "0,1",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.PF_L2_RFO.L2_HIT_FAR_TILE_M",
         "MSRIndex": "0x1a6,0x1a7",
         "SampleAfterValue": "100007",
-        "BriefDescription": "Counts L2 data RFO prefetches (includes PREFETCHW instruction) that accounts for responses from a snoop request hit with data forwarded from its Far(not in the same quadrant as the request)-other tile's L2 in M state. ",
+        "BriefDescription": "Counts L2 data RFO prefetches (includes PREFETCHW instruction) that accounts for responses from a snoop request hit with data forwarded from its Far(not in the same quadrant as the request)-other tile's L2 in M state.",
         "Offcore": "1"
     },
     {
         "EventCode": "0xB7",
-        "MSRValue": "0x0800400020 ",
+        "MSRValue": "0x0800400020",
         "Counter": "0,1",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.PF_L2_RFO.L2_HIT_FAR_TILE_E_F",
@@ -1017,29 +1017,29 @@
     },
     {
         "EventCode": "0xB7",
-        "MSRValue": "0x1000080020 ",
+        "MSRValue": "0x1000080020",
         "Counter": "0,1",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.PF_L2_RFO.L2_HIT_NEAR_TILE_M",
         "MSRIndex": "0x1a6,0x1a7",
         "SampleAfterValue": "100007",
-        "BriefDescription": "Counts L2 data RFO prefetches (includes PREFETCHW instruction) that accounts for responses from a snoop request hit with data forwarded from its Near-other tile's L2 in M state. ",
+        "BriefDescription": "Counts L2 data RFO prefetches (includes PREFETCHW instruction) that accounts for responses from a snoop request hit with data forwarded from its Near-other tile's L2 in M state.",
         "Offcore": "1"
     },
     {
         "EventCode": "0xB7",
-        "MSRValue": "0x0800080020 ",
+        "MSRValue": "0x0800080020",
         "Counter": "0,1",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.PF_L2_RFO.L2_HIT_NEAR_TILE_E_F",
         "MSRIndex": "0x1a6,0x1a7",
         "SampleAfterValue": "100007",
-        "BriefDescription": "Counts L2 data RFO prefetches (includes PREFETCHW instruction) that accounts for responses from a snoop request hit with data forwarded from its Near-other tile's L2 in E/F state. ",
+        "BriefDescription": "Counts L2 data RFO prefetches (includes PREFETCHW instruction) that accounts for responses from a snoop request hit with data forwarded from its Near-other tile's L2 in E/F state.",
         "Offcore": "1"
     },
     {
         "EventCode": "0xB7",
-        "MSRValue": "0x0000020020 ",
+        "MSRValue": "0x0000020020",
         "Counter": "0,1",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.PF_L2_RFO.SUPPLIER_NONE",
@@ -1050,7 +1050,7 @@
     },
     {
         "EventCode": "0xB7",
-        "MSRValue": "0x0000010020 ",
+        "MSRValue": "0x0000010020",
         "Counter": "0,1",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.PF_L2_RFO.ANY_RESPONSE",
@@ -1061,29 +1061,29 @@
     },
     {
         "EventCode": "0xB7",
-        "MSRValue": "0x4000000004 ",
+        "MSRValue": "0x4000000004",
         "Counter": "0,1",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.OUTSTANDING",
         "MSRIndex": "0x1a6",
         "SampleAfterValue": "100007",
-        "BriefDescription": "Counts demand code reads and prefetch code reads that are outstanding, per weighted cycle, from the time of the request to when any response is received. The outstanding response should be programmed only on PMC0. ",
+        "BriefDescription": "Counts demand code reads and prefetch code reads that are outstanding, per weighted cycle, from the time of the request to when any response is received. The oustanding response should be programmed only on PMC0.",
         "Offcore": "1"
     },
     {
         "EventCode": "0xB7",
-        "MSRValue": "0x1000400004 ",
+        "MSRValue": "0x1000400004",
         "Counter": "0,1",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L2_HIT_FAR_TILE_M",
         "MSRIndex": "0x1a6,0x1a7",
         "SampleAfterValue": "100007",
-        "BriefDescription": "Counts demand code reads and prefetch code reads that accounts for responses from a snoop request hit with data forwarded from its Far(not in the same quadrant as the request)-other tile's L2 in M state. ",
+        "BriefDescription": "Counts demand code reads and prefetch code reads that accounts for responses from a snoop request hit with data forwarded from its Far(not in the same quadrant as the request)-other tile's L2 in M state.",
         "Offcore": "1"
     },
     {
         "EventCode": "0xB7",
-        "MSRValue": "0x0800400004 ",
+        "MSRValue": "0x0800400004",
         "Counter": "0,1",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L2_HIT_FAR_TILE_E_F",
@@ -1094,29 +1094,29 @@
     },
     {
         "EventCode": "0xB7",
-        "MSRValue": "0x1000080004 ",
+        "MSRValue": "0x1000080004",
         "Counter": "0,1",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L2_HIT_NEAR_TILE_M",
         "MSRIndex": "0x1a6,0x1a7",
         "SampleAfterValue": "100007",
-        "BriefDescription": "Counts demand code reads and prefetch code reads that accounts for responses from a snoop request hit with data forwarded from its Near-other tile's L2 in M state. ",
+        "BriefDescription": "Counts demand code reads and prefetch code reads that accounts for responses from a snoop request hit with data forwarded from its Near-other tile's L2 in M state.",
         "Offcore": "1"
     },
     {
         "EventCode": "0xB7",
-        "MSRValue": "0x0800080004 ",
+        "MSRValue": "0x0800080004",
         "Counter": "0,1",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L2_HIT_NEAR_TILE_E_F",
         "MSRIndex": "0x1a6,0x1a7",
         "SampleAfterValue": "100007",
-        "BriefDescription": "Counts demand code reads and prefetch code reads that accounts for responses from a snoop request hit with data forwarded from its Near-other tile's L2 in E/F state. ",
+        "BriefDescription": "Counts demand code reads and prefetch code reads that accounts for responses from a snoop request hit with data forwarded from its Near-other tile's L2 in E/F state.",
         "Offcore": "1"
     },
     {
         "EventCode": "0xB7",
-        "MSRValue": "0x0000010004 ",
+        "MSRValue": "0x0000010004",
         "Counter": "0,1",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.ANY_RESPONSE",
@@ -1127,29 +1127,29 @@
     },
     {
         "EventCode": "0xB7",
-        "MSRValue": "0x4000000002 ",
+        "MSRValue": "0x4000000002",
         "Counter": "0,1",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.OUTSTANDING",
         "MSRIndex": "0x1a6",
         "SampleAfterValue": "100007",
-        "BriefDescription": "Counts Demand cacheable data writes that are outstanding, per weighted cycle, from the time of the request to when any response is received. The outstanding response should be programmed only on PMC0. ",
+        "BriefDescription": "Counts Demand cacheable data writes that are outstanding, per weighted cycle, from the time of the request to when any response is received. The oustanding response should be programmed only on PMC0.",
         "Offcore": "1"
     },
     {
         "EventCode": "0xB7",
-        "MSRValue": "0x1000400002 ",
+        "MSRValue": "0x1000400002",
         "Counter": "0,1",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L2_HIT_FAR_TILE_M",
         "MSRIndex": "0x1a6,0x1a7",
         "SampleAfterValue": "100007",
-        "BriefDescription": "Counts Demand cacheable data writes that accounts for responses from a snoop request hit with data forwarded from its Far(not in the same quadrant as the request)-other tile's L2 in M state. ",
+        "BriefDescription": "Counts Demand cacheable data writes that accounts for responses from a snoop request hit with data forwarded from its Far(not in the same quadrant as the request)-other tile's L2 in M state.",
         "Offcore": "1"
     },
     {
         "EventCode": "0xB7",
-        "MSRValue": "0x0800400002 ",
+        "MSRValue": "0x0800400002",
         "Counter": "0,1",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L2_HIT_FAR_TILE_E_F",
@@ -1160,29 +1160,29 @@
     },
     {
         "EventCode": "0xB7",
-        "MSRValue": "0x1000080002 ",
+        "MSRValue": "0x1000080002",
         "Counter": "0,1",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L2_HIT_NEAR_TILE_M",
         "MSRIndex": "0x1a6,0x1a7",
         "SampleAfterValue": "100007",
-        "BriefDescription": "Counts Demand cacheable data writes that accounts for responses from a snoop request hit with data forwarded from its Near-other tile's L2 in M state. ",
+        "BriefDescription": "Counts Demand cacheable data writes that accounts for responses from a snoop request hit with data forwarded from its Near-other tile's L2 in M state.",
         "Offcore": "1"
     },
     {
         "EventCode": "0xB7",
-        "MSRValue": "0x0800080002 ",
+        "MSRValue": "0x0800080002",
         "Counter": "0,1",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L2_HIT_NEAR_TILE_E_F",
         "MSRIndex": "0x1a6,0x1a7",
         "SampleAfterValue": "100007",
-        "BriefDescription": "Counts Demand cacheable data writes that accounts for responses from a snoop request hit with data forwarded from its Near-other tile's L2 in E/F state. ",
+        "BriefDescription": "Counts Demand cacheable data writes that accounts for responses from a snoop request hit with data forwarded from its Near-other tile's L2 in E/F state.",
         "Offcore": "1"
     },
     {
         "EventCode": "0xB7",
-        "MSRValue": "0x0000010002 ",
+        "MSRValue": "0x0000010002",
         "Counter": "0,1",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.ANY_RESPONSE",
@@ -1193,29 +1193,29 @@
     },
     {
         "EventCode": "0xB7",
-        "MSRValue": "0x4000000001 ",
+        "MSRValue": "0x4000000001",
         "Counter": "0,1",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.OUTSTANDING",
         "MSRIndex": "0x1a6",
         "SampleAfterValue": "100007",
-        "BriefDescription": "Counts demand cacheable data and L1 prefetch data reads that are outstanding, per weighted cycle, from the time of the request to when any response is received. The outstanding response should be programmed only on PMC0. ",
+        "BriefDescription": "Counts demand cacheable data and L1 prefetch data reads that are outstanding, per weighted cycle, from the time of the request to when any response is received. The oustanding response should be programmed only on PMC0.",
         "Offcore": "1"
     },
     {
         "EventCode": "0xB7",
-        "MSRValue": "0x1000400001 ",
+        "MSRValue": "0x1000400001",
         "Counter": "0,1",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L2_HIT_FAR_TILE_M",
         "MSRIndex": "0x1a6,0x1a7",
         "SampleAfterValue": "100007",
-        "BriefDescription": "Counts demand cacheable data and L1 prefetch data reads that accounts for responses from a snoop request hit with data forwarded from its Far(not in the same quadrant as the request)-other tile's L2 in M state. ",
+        "BriefDescription": "Counts demand cacheable data and L1 prefetch data reads that accounts for responses from a snoop request hit with data forwarded from its Far(not in the same quadrant as the request)-other tile's L2 in M state.",
         "Offcore": "1"
     },
     {
         "EventCode": "0xB7",
-        "MSRValue": "0x0800400001 ",
+        "MSRValue": "0x0800400001",
         "Counter": "0,1",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L2_HIT_FAR_TILE_E_F",
@@ -1226,29 +1226,29 @@
     },
     {
         "EventCode": "0xB7",
-        "MSRValue": "0x1000080001 ",
+        "MSRValue": "0x1000080001",
         "Counter": "0,1",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L2_HIT_NEAR_TILE_M",
         "MSRIndex": "0x1a6,0x1a7",
         "SampleAfterValue": "100007",
-        "BriefDescription": "Counts demand cacheable data and L1 prefetch data reads that accounts for responses from a snoop request hit with data forwarded from its Near-other tile's L2 in M state. ",
+        "BriefDescription": "Counts demand cacheable data and L1 prefetch data reads that accounts for responses from a snoop request hit with data forwarded from its Near-other tile's L2 in M state.",
         "Offcore": "1"
     },
     {
         "EventCode": "0xB7",
-        "MSRValue": "0x0800080001 ",
+        "MSRValue": "0x0800080001",
         "Counter": "0,1",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L2_HIT_NEAR_TILE_E_F",
         "MSRIndex": "0x1a6,0x1a7",
         "SampleAfterValue": "100007",
-        "BriefDescription": "Counts demand cacheable data and L1 prefetch data reads that accounts for responses from a snoop request hit with data forwarded from its Near-other tile's L2 in E/F state. ",
+        "BriefDescription": "Counts demand cacheable data and L1 prefetch data reads that accounts for responses from a snoop request hit with data forwarded from its Near-other tile's L2 in E/F state.",
         "Offcore": "1"
     },
     {
         "EventCode": "0xB7",
-        "MSRValue": "0x0000010001 ",
+        "MSRValue": "0x0000010001",
         "Counter": "0,1",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.ANY_RESPONSE",
@@ -1259,722 +1259,722 @@
     },
     {
         "EventCode": "0xB7",
-        "MSRValue": "0x0002000001 ",
+        "MSRValue": "0x0002000001",
         "Counter": "0,1",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L2_HIT_THIS_TILE_M",
         "MSRIndex": "0x1a6,0x1a7",
         "SampleAfterValue": "100007",
-        "BriefDescription": "Counts demand cacheable data and L1 prefetch data reads that accounts for responses which hit its own tile's L2 with data in M state ",
+        "BriefDescription": "Counts demand cacheable data and L1 prefetch data reads that accounts for responses which hit its own tile's L2 with data in M state",
         "Offcore": "1"
     },
     {
         "EventCode": "0xB7",
-        "MSRValue": "0x0002000002 ",
+        "MSRValue": "0x0002000002",
         "Counter": "0,1",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L2_HIT_THIS_TILE_M",
         "MSRIndex": "0x1a6,0x1a7",
         "SampleAfterValue": "100007",
-        "BriefDescription": "Counts Demand cacheable data writes that accounts for responses which hit its own tile's L2 with data in M state ",
+        "BriefDescription": "Counts Demand cacheable data writes that accounts for responses which hit its own tile's L2 with data in M state",
         "Offcore": "1"
     },
     {
         "EventCode": "0xB7",
-        "MSRValue": "0x0002000004 ",
+        "MSRValue": "0x0002000004",
         "Counter": "0,1",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L2_HIT_THIS_TILE_M",
         "MSRIndex": "0x1a6,0x1a7",
         "SampleAfterValue": "100007",
-        "BriefDescription": "Counts demand code reads and prefetch code reads that accounts for responses which hit its own tile's L2 with data in M state ",
+        "BriefDescription": "Counts demand code reads and prefetch code reads that accounts for responses which hit its own tile's L2 with data in M state",
         "Offcore": "1"
     },
     {
         "EventCode": "0xB7",
-        "MSRValue": "0x0002000020 ",
+        "MSRValue": "0x0002000020",
         "Counter": "0,1",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.PF_L2_RFO.L2_HIT_THIS_TILE_M",
         "MSRIndex": "0x1a6,0x1a7",
         "SampleAfterValue": "100007",
-        "BriefDescription": "Counts L2 data RFO prefetches (includes PREFETCHW instruction) that accounts for responses which hit its own tile's L2 with data in M state ",
+        "BriefDescription": "Counts L2 data RFO prefetches (includes PREFETCHW instruction) that accounts for responses which hit its own tile's L2 with data in M state",
         "Offcore": "1"
     },
     {
         "EventCode": "0xB7",
-        "MSRValue": "0x0002000080 ",
+        "MSRValue": "0x0002000080",
         "Counter": "0,1",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.PARTIAL_READS.L2_HIT_THIS_TILE_M",
         "MSRIndex": "0x1a6,0x1a7",
         "SampleAfterValue": "100007",
-        "BriefDescription": "Counts Partial reads (UC or WC and is valid only for Outstanding response type).  that accounts for responses which hit its own tile's L2 with data in M state ",
+        "BriefDescription": "Counts Partial reads (UC or WC and is valid only for Outstanding response type).  that accounts for responses which hit its own tile's L2 with data in M state",
         "Offcore": "1"
     },
     {
         "EventCode": "0xB7",
-        "MSRValue": "0x0002000100 ",
+        "MSRValue": "0x0002000100",
         "Counter": "0,1",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.PARTIAL_WRITES.L2_HIT_THIS_TILE_M",
         "MSRIndex": "0x1a7",
         "SampleAfterValue": "100007",
-        "BriefDescription": "Counts Partial writes (UC or WT or WP and should be programmed on PMC1) that accounts for responses which hit its own tile's L2 with data in M state ",
+        "BriefDescription": "Counts Partial writes (UC or WT or WP and should be programmed on PMC1) that accounts for responses which hit its own tile's L2 with data in M state",
         "Offcore": "1"
     },
     {
         "EventCode": "0xB7",
-        "MSRValue": "0x0002000200 ",
+        "MSRValue": "0x0002000200",
         "Counter": "0,1",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.UC_CODE_READS.L2_HIT_THIS_TILE_M",
         "MSRIndex": "0x1a6,0x1a7",
         "SampleAfterValue": "100007",
-        "BriefDescription": "Counts UC code reads (valid only for Outstanding response type)  that accounts for responses which hit its own tile's L2 with data in M state ",
+        "BriefDescription": "Counts UC code reads (valid only for Outstanding response type)  that accounts for responses which hit its own tile's L2 with data in M state",
         "Offcore": "1"
     },
     {
         "EventCode": "0xB7",
-        "MSRValue": "0x0002000400 ",
+        "MSRValue": "0x0002000400",
         "Counter": "0,1",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.BUS_LOCKS.L2_HIT_THIS_TILE_M",
         "MSRIndex": "0x1a6,0x1a7",
         "SampleAfterValue": "100007",
-        "BriefDescription": "Counts Bus locks and split lock requests that accounts for responses which hit its own tile's L2 with data in M state ",
+        "BriefDescription": "Counts Bus locks and split lock requests that accounts for responses which hit its own tile's L2 with data in M state",
         "Offcore": "1"
     },
     {
         "EventCode": "0xB7",
-        "MSRValue": "0x0002001000 ",
+        "MSRValue": "0x0002001000",
         "Counter": "0,1",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.PF_SOFTWARE.L2_HIT_THIS_TILE_M",
         "MSRIndex": "0x1a6,0x1a7",
         "SampleAfterValue": "100007",
-        "BriefDescription": "Counts Software Prefetches that accounts for responses which hit its own tile's L2 with data in M state ",
+        "BriefDescription": "Counts Software Prefetches that accounts for responses which hit its own tile's L2 with data in M state",
         "Offcore": "1"
     },
     {
         "EventCode": "0xB7",
-        "MSRValue": "0x0002002000 ",
+        "MSRValue": "0x0002002000",
         "Counter": "0,1",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.PF_L1_DATA_RD.L2_HIT_THIS_TILE_M",
         "MSRIndex": "0x1a6,0x1a7",
         "SampleAfterValue": "100007",
-        "BriefDescription": "Counts L1 data HW prefetches that accounts for responses which hit its own tile's L2 with data in M state ",
+        "BriefDescription": "Counts L1 data HW prefetches that accounts for responses which hit its own tile's L2 with data in M state",
         "Offcore": "1"
     },
     {
         "EventCode": "0xB7",
-        "MSRValue": "0x0002008000 ",
+        "MSRValue": "0x0002008000",
         "Counter": "0,1",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.ANY_REQUEST.L2_HIT_THIS_TILE_M",
         "MSRIndex": "0x1a6,0x1a7",
         "SampleAfterValue": "100007",
-        "BriefDescription": "Counts any request that accounts for responses which hit its own tile's L2 with data in M state ",
+        "BriefDescription": "Counts any request that accounts for responses which hit its own tile's L2 with data in M state",
         "Offcore": "1"
     },
     {
         "EventCode": "0xB7",
-        "MSRValue": "0x0002003091 ",
+        "MSRValue": "0x0002003091",
         "Counter": "0,1",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.ANY_DATA_RD.L2_HIT_THIS_TILE_M",
         "MSRIndex": "0x1a6,0x1a7",
         "SampleAfterValue": "100007",
-        "BriefDescription": "Counts Demand cacheable data and L1 prefetch data read requests  that accounts for responses which hit its own tile's L2 with data in M state ",
+        "BriefDescription": "Counts Demand cacheable data and L1 prefetch data read requests  that accounts for responses which hit its own tile's L2 with data in M state",
         "Offcore": "1"
     },
     {
         "EventCode": "0xB7",
-        "MSRValue": "0x0002000022 ",
+        "MSRValue": "0x0002000022",
         "Counter": "0,1",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.ANY_RFO.L2_HIT_THIS_TILE_M",
         "MSRIndex": "0x1a6,0x1a7",
         "SampleAfterValue": "100007",
-        "BriefDescription": "Counts Demand cacheable data write requests  that accounts for responses which hit its own tile's L2 with data in M state ",
+        "BriefDescription": "Counts Demand cacheable data write requests  that accounts for responses which hit its own tile's L2 with data in M state",
         "Offcore": "1"
     },
     {
         "EventCode": "0xB7",
-        "MSRValue": "0x0002000044 ",
+        "MSRValue": "0x0002000044",
         "Counter": "0,1",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.ANY_CODE_RD.L2_HIT_THIS_TILE_M",
         "MSRIndex": "0x1a6,0x1a7",
         "SampleAfterValue": "100007",
-        "BriefDescription": "Counts Demand code reads and prefetch code read requests  that accounts for responses which hit its own tile's L2 with data in M state ",
+        "BriefDescription": "Counts Demand code reads and prefetch code read requests  that accounts for responses which hit its own tile's L2 with data in M state",
         "Offcore": "1"
     },
     {
         "EventCode": "0xB7",
-        "MSRValue": "0x00020032f7 ",
+        "MSRValue": "0x00020032f7",
         "Counter": "0,1",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.ANY_READ.L2_HIT_THIS_TILE_M",
         "MSRIndex": "0x1a6,0x1a7",
         "SampleAfterValue": "100007",
-        "BriefDescription": "Counts any Read request  that accounts for responses which hit its own tile's L2 with data in M state ",
+        "BriefDescription": "Counts any Read request  that accounts for responses which hit its own tile's L2 with data in M state",
         "Offcore": "1"
     },
     {
         "EventCode": "0xB7",
-        "MSRValue": "0x0002000070 ",
+        "MSRValue": "0x0002000070",
         "Counter": "0,1",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.ANY_PF_L2.L2_HIT_THIS_TILE_M",
         "MSRIndex": "0x1a6,0x1a7",
         "SampleAfterValue": "100007",
-        "BriefDescription": "Counts any Prefetch requests that accounts for responses which hit its own tile's L2 with data in M state ",
+        "BriefDescription": "Counts any Prefetch requests that accounts for responses which hit its own tile's L2 with data in M state",
         "Offcore": "1"
     },
     {
         "EventCode": "0xB7",
-        "MSRValue": "0x0004000001 ",
+        "MSRValue": "0x0004000001",
         "Counter": "0,1",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L2_HIT_THIS_TILE_E",
         "MSRIndex": "0x1a6,0x1a7",
         "SampleAfterValue": "100007",
-        "BriefDescription": "Counts demand cacheable data and L1 prefetch data reads that accounts for responses which hit its own tile's L2 with data in E state ",
+        "BriefDescription": "Counts demand cacheable data and L1 prefetch data reads that accounts for responses which hit its own tile's L2 with data in E state",
         "Offcore": "1"
     },
     {
         "EventCode": "0xB7",
-        "MSRValue": "0x0004000002 ",
+        "MSRValue": "0x0004000002",
         "Counter": "0,1",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L2_HIT_THIS_TILE_E",
         "MSRIndex": "0x1a6,0x1a7",
         "SampleAfterValue": "100007",
-        "BriefDescription": "Counts Demand cacheable data writes that accounts for responses which hit its own tile's L2 with data in E state ",
+        "BriefDescription": "Counts Demand cacheable data writes that accounts for responses which hit its own tile's L2 with data in E state",
         "Offcore": "1"
     },
     {
         "EventCode": "0xB7",
-        "MSRValue": "0x0004000004 ",
+        "MSRValue": "0x0004000004",
         "Counter": "0,1",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L2_HIT_THIS_TILE_E",
         "MSRIndex": "0x1a6,0x1a7",
         "SampleAfterValue": "100007",
-        "BriefDescription": "Counts demand code reads and prefetch code reads that accounts for responses which hit its own tile's L2 with data in E state ",
+        "BriefDescription": "Counts demand code reads and prefetch code reads that accounts for responses which hit its own tile's L2 with data in E state",
         "Offcore": "1"
     },
     {
         "EventCode": "0xB7",
-        "MSRValue": "0x0004000020 ",
+        "MSRValue": "0x0004000020",
         "Counter": "0,1",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.PF_L2_RFO.L2_HIT_THIS_TILE_E",
         "MSRIndex": "0x1a6,0x1a7",
         "SampleAfterValue": "100007",
-        "BriefDescription": "Counts L2 data RFO prefetches (includes PREFETCHW instruction) that accounts for responses which hit its own tile's L2 with data in E state ",
+        "BriefDescription": "Counts L2 data RFO prefetches (includes PREFETCHW instruction) that accounts for responses which hit its own tile's L2 with data in E state",
         "Offcore": "1"
     },
     {
         "EventCode": "0xB7",
-        "MSRValue": "0x0004000040 ",
+        "MSRValue": "0x0004000040",
         "Counter": "0,1",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.PF_L2_CODE_RD.L2_HIT_THIS_TILE_E",
         "MSRIndex": "0x1a6,0x1a7",
         "SampleAfterValue": "100007",
-        "BriefDescription": "Counts L2 code HW prefetches that accounts for responses which hit its own tile's L2 with data in E state ",
+        "BriefDescription": "Counts L2 code HW prefetches that accounts for responses which hit its own tile's L2 with data in E state",
         "Offcore": "1"
     },
     {
         "EventCode": "0xB7",
-        "MSRValue": "0x0004000080 ",
+        "MSRValue": "0x0004000080",
         "Counter": "0,1",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.PARTIAL_READS.L2_HIT_THIS_TILE_E",
         "MSRIndex": "0x1a6,0x1a7",
         "SampleAfterValue": "100007",
-        "BriefDescription": "Counts Partial reads (UC or WC and is valid only for Outstanding response type).  that accounts for responses which hit its own tile's L2 with data in E state ",
+        "BriefDescription": "Counts Partial reads (UC or WC and is valid only for Outstanding response type).  that accounts for responses which hit its own tile's L2 with data in E state",
         "Offcore": "1"
     },
     {
         "EventCode": "0xB7",
-        "MSRValue": "0x0004000100 ",
+        "MSRValue": "0x0004000100",
         "Counter": "0,1",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.PARTIAL_WRITES.L2_HIT_THIS_TILE_E",
         "MSRIndex": "0x1a7",
         "SampleAfterValue": "100007",
-        "BriefDescription": "Counts Partial writes (UC or WT or WP and should be programmed on PMC1) that accounts for responses which hit its own tile's L2 with data in E state ",
+        "BriefDescription": "Counts Partial writes (UC or WT or WP and should be programmed on PMC1) that accounts for responses which hit its own tile's L2 with data in E state",
         "Offcore": "1"
     },
     {
         "EventCode": "0xB7",
-        "MSRValue": "0x0004000200 ",
+        "MSRValue": "0x0004000200",
         "Counter": "0,1",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.UC_CODE_READS.L2_HIT_THIS_TILE_E",
         "MSRIndex": "0x1a6,0x1a7",
         "SampleAfterValue": "100007",
-        "BriefDescription": "Counts UC code reads (valid only for Outstanding response type)  that accounts for responses which hit its own tile's L2 with data in E state ",
+        "BriefDescription": "Counts UC code reads (valid only for Outstanding response type)  that accounts for responses which hit its own tile's L2 with data in E state",
         "Offcore": "1"
     },
     {
         "EventCode": "0xB7",
-        "MSRValue": "0x0004000400 ",
+        "MSRValue": "0x0004000400",
         "Counter": "0,1",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.BUS_LOCKS.L2_HIT_THIS_TILE_E",
         "MSRIndex": "0x1a6,0x1a7",
         "SampleAfterValue": "100007",
-        "BriefDescription": "Counts Bus locks and split lock requests that accounts for responses which hit its own tile's L2 with data in E state ",
+        "BriefDescription": "Counts Bus locks and split lock requests that accounts for responses which hit its own tile's L2 with data in E state",
         "Offcore": "1"
     },
     {
         "EventCode": "0xB7",
-        "MSRValue": "0x0004001000 ",
+        "MSRValue": "0x0004001000",
         "Counter": "0,1",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.PF_SOFTWARE.L2_HIT_THIS_TILE_E",
         "MSRIndex": "0x1a6,0x1a7",
         "SampleAfterValue": "100007",
-        "BriefDescription": "Counts Software Prefetches that accounts for responses which hit its own tile's L2 with data in E state ",
+        "BriefDescription": "Counts Software Prefetches that accounts for responses which hit its own tile's L2 with data in E state",
         "Offcore": "1"
     },
     {
         "EventCode": "0xB7",
-        "MSRValue": "0x0004002000 ",
+        "MSRValue": "0x0004002000",
         "Counter": "0,1",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.PF_L1_DATA_RD.L2_HIT_THIS_TILE_E",
         "MSRIndex": "0x1a6,0x1a7",
         "SampleAfterValue": "100007",
-        "BriefDescription": "Counts L1 data HW prefetches that accounts for responses which hit its own tile's L2 with data in E state ",
+        "BriefDescription": "Counts L1 data HW prefetches that accounts for responses which hit its own tile's L2 with data in E state",
         "Offcore": "1"
     },
     {
         "EventCode": "0xB7",
-        "MSRValue": "0x0004008000 ",
+        "MSRValue": "0x0004008000",
         "Counter": "0,1",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.ANY_REQUEST.L2_HIT_THIS_TILE_E",
         "MSRIndex": "0x1a6,0x1a7",
         "SampleAfterValue": "100007",
-        "BriefDescription": "Counts any request that accounts for responses which hit its own tile's L2 with data in E state ",
+        "BriefDescription": "Counts any request that accounts for responses which hit its own tile's L2 with data in E state",
         "Offcore": "1"
     },
     {
         "EventCode": "0xB7",
-        "MSRValue": "0x0004003091 ",
+        "MSRValue": "0x0004003091",
         "Counter": "0,1",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.ANY_DATA_RD.L2_HIT_THIS_TILE_E",
         "MSRIndex": "0x1a6,0x1a7",
         "SampleAfterValue": "100007",
-        "BriefDescription": "Counts Demand cacheable data and L1 prefetch data read requests  that accounts for responses which hit its own tile's L2 with data in E state ",
+        "BriefDescription": "Counts Demand cacheable data and L1 prefetch data read requests  that accounts for responses which hit its own tile's L2 with data in E state",
         "Offcore": "1"
     },
     {
         "EventCode": "0xB7",
-        "MSRValue": "0x0004000022 ",
+        "MSRValue": "0x0004000022",
         "Counter": "0,1",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.ANY_RFO.L2_HIT_THIS_TILE_E",
         "MSRIndex": "0x1a6,0x1a7",
         "SampleAfterValue": "100007",
-        "BriefDescription": "Counts Demand cacheable data write requests  that accounts for responses which hit its own tile's L2 with data in E state ",
+        "BriefDescription": "Counts Demand cacheable data write requests  that accounts for responses which hit its own tile's L2 with data in E state",
         "Offcore": "1"
     },
     {
         "EventCode": "0xB7",
-        "MSRValue": "0x0004000044 ",
+        "MSRValue": "0x0004000044",
         "Counter": "0,1",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.ANY_CODE_RD.L2_HIT_THIS_TILE_E",
         "MSRIndex": "0x1a6,0x1a7",
         "SampleAfterValue": "100007",
-        "BriefDescription": "Counts Demand code reads and prefetch code read requests  that accounts for responses which hit its own tile's L2 with data in E state ",
+        "BriefDescription": "Counts Demand code reads and prefetch code read requests  that accounts for responses which hit its own tile's L2 with data in E state",
         "Offcore": "1"
     },
     {
         "EventCode": "0xB7",
-        "MSRValue": "0x00040032f7 ",
+        "MSRValue": "0x00040032f7",
         "Counter": "0,1",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.ANY_READ.L2_HIT_THIS_TILE_E",
         "MSRIndex": "0x1a6,0x1a7",
         "SampleAfterValue": "100007",
-        "BriefDescription": "Counts any Read request  that accounts for responses which hit its own tile's L2 with data in E state ",
+        "BriefDescription": "Counts any Read request  that accounts for responses which hit its own tile's L2 with data in E state",
         "Offcore": "1"
     },
     {
         "EventCode": "0xB7",
-        "MSRValue": "0x0004000070 ",
+        "MSRValue": "0x0004000070",
         "Counter": "0,1",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.ANY_PF_L2.L2_HIT_THIS_TILE_E",
         "MSRIndex": "0x1a6,0x1a7",
         "SampleAfterValue": "100007",
-        "BriefDescription": "Counts any Prefetch requests that accounts for responses which hit its own tile's L2 with data in E state ",
+        "BriefDescription": "Counts any Prefetch requests that accounts for responses which hit its own tile's L2 with data in E state",
         "Offcore": "1"
     },
     {
         "EventCode": "0xB7",
-        "MSRValue": "0x0008000001 ",
+        "MSRValue": "0x0008000001",
         "Counter": "0,1",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L2_HIT_THIS_TILE_S",
         "MSRIndex": "0x1a6,0x1a7",
         "SampleAfterValue": "100007",
-        "BriefDescription": "Counts demand cacheable data and L1 prefetch data reads that accounts for responses which hit its own tile's L2 with data in S state ",
+        "BriefDescription": "Counts demand cacheable data and L1 prefetch data reads that accounts for responses which hit its own tile's L2 with data in S state",
         "Offcore": "1"
     },
     {
         "EventCode": "0xB7",
-        "MSRValue": "0x0008000002 ",
+        "MSRValue": "0x0008000002",
         "Counter": "0,1",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L2_HIT_THIS_TILE_S",
         "MSRIndex": "0x1a6,0x1a7",
         "SampleAfterValue": "100007",
-        "BriefDescription": "Counts Demand cacheable data writes that accounts for responses which hit its own tile's L2 with data in S state ",
+        "BriefDescription": "Counts Demand cacheable data writes that accounts for responses which hit its own tile's L2 with data in S state",
         "Offcore": "1"
     },
     {
         "EventCode": "0xB7",
-        "MSRValue": "0x0008000004 ",
+        "MSRValue": "0x0008000004",
         "Counter": "0,1",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L2_HIT_THIS_TILE_S",
         "MSRIndex": "0x1a6,0x1a7",
         "SampleAfterValue": "100007",
-        "BriefDescription": "Counts demand code reads and prefetch code reads that accounts for responses which hit its own tile's L2 with data in S state ",
+        "BriefDescription": "Counts demand code reads and prefetch code reads that accounts for responses which hit its own tile's L2 with data in S state",
         "Offcore": "1"
     },
     {
         "EventCode": "0xB7",
-        "MSRValue": "0x0008000020 ",
+        "MSRValue": "0x0008000020",
         "Counter": "0,1",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.PF_L2_RFO.L2_HIT_THIS_TILE_S",
         "MSRIndex": "0x1a6,0x1a7",
         "SampleAfterValue": "100007",
-        "BriefDescription": "Counts L2 data RFO prefetches (includes PREFETCHW instruction) that accounts for responses which hit its own tile's L2 with data in S state ",
+        "BriefDescription": "Counts L2 data RFO prefetches (includes PREFETCHW instruction) that accounts for responses which hit its own tile's L2 with data in S state",
         "Offcore": "1"
     },
     {
         "EventCode": "0xB7",
-        "MSRValue": "0x0008000080 ",
+        "MSRValue": "0x0008000080",
         "Counter": "0,1",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.PARTIAL_READS.L2_HIT_THIS_TILE_S",
         "MSRIndex": "0x1a6,0x1a7",
         "SampleAfterValue": "100007",
-        "BriefDescription": "Counts Partial reads (UC or WC and is valid only for Outstanding response type).  that accounts for responses which hit its own tile's L2 with data in S state ",
+        "BriefDescription": "Counts Partial reads (UC or WC and is valid only for Outstanding response type).  that accounts for responses which hit its own tile's L2 with data in S state",
         "Offcore": "1"
     },
     {
         "EventCode": "0xB7",
-        "MSRValue": "0x0008000100 ",
+        "MSRValue": "0x0008000100",
         "Counter": "0,1",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.PARTIAL_WRITES.L2_HIT_THIS_TILE_S",
         "MSRIndex": "0x1a7",
         "SampleAfterValue": "100007",
-        "BriefDescription": "Counts Partial writes (UC or WT or WP and should be programmed on PMC1) that accounts for responses which hit its own tile's L2 with data in S state ",
+        "BriefDescription": "Counts Partial writes (UC or WT or WP and should be programmed on PMC1) that accounts for responses which hit its own tile's L2 with data in S state",
         "Offcore": "1"
     },
     {
         "EventCode": "0xB7",
-        "MSRValue": "0x0008000200 ",
+        "MSRValue": "0x0008000200",
         "Counter": "0,1",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.UC_CODE_READS.L2_HIT_THIS_TILE_S",
         "MSRIndex": "0x1a6,0x1a7",
         "SampleAfterValue": "100007",
-        "BriefDescription": "Counts UC code reads (valid only for Outstanding response type)  that accounts for responses which hit its own tile's L2 with data in S state ",
+        "BriefDescription": "Counts UC code reads (valid only for Outstanding response type)  that accounts for responses which hit its own tile's L2 with data in S state",
         "Offcore": "1"
     },
     {
         "EventCode": "0xB7",
-        "MSRValue": "0x0008000400 ",
+        "MSRValue": "0x0008000400",
         "Counter": "0,1",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.BUS_LOCKS.L2_HIT_THIS_TILE_S",
         "MSRIndex": "0x1a6,0x1a7",
         "SampleAfterValue": "100007",
-        "BriefDescription": "Counts Bus locks and split lock requests that accounts for responses which hit its own tile's L2 with data in S state ",
+        "BriefDescription": "Counts Bus locks and split lock requests that accounts for responses which hit its own tile's L2 with data in S state",
         "Offcore": "1"
     },
     {
         "EventCode": "0xB7",
-        "MSRValue": "0x0008001000 ",
+        "MSRValue": "0x0008001000",
         "Counter": "0,1",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.PF_SOFTWARE.L2_HIT_THIS_TILE_S",
         "MSRIndex": "0x1a6,0x1a7",
         "SampleAfterValue": "100007",
-        "BriefDescription": "Counts Software Prefetches that accounts for responses which hit its own tile's L2 with data in S state ",
+        "BriefDescription": "Counts Software Prefetches that accounts for responses which hit its own tile's L2 with data in S state",
         "Offcore": "1"
     },
     {
         "EventCode": "0xB7",
-        "MSRValue": "0x0008002000 ",
+        "MSRValue": "0x0008002000",
         "Counter": "0,1",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.PF_L1_DATA_RD.L2_HIT_THIS_TILE_S",
         "MSRIndex": "0x1a6,0x1a7",
         "SampleAfterValue": "100007",
-        "BriefDescription": "Counts L1 data HW prefetches that accounts for responses which hit its own tile's L2 with data in S state ",
+        "BriefDescription": "Counts L1 data HW prefetches that accounts for responses which hit its own tile's L2 with data in S state",
         "Offcore": "1"
     },
     {
         "EventCode": "0xB7",
-        "MSRValue": "0x0008008000 ",
+        "MSRValue": "0x0008008000",
         "Counter": "0,1",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.ANY_REQUEST.L2_HIT_THIS_TILE_S",
         "MSRIndex": "0x1a6,0x1a7",
         "SampleAfterValue": "100007",
-        "BriefDescription": "Counts any request that accounts for responses which hit its own tile's L2 with data in S state ",
+        "BriefDescription": "Counts any request that accounts for responses which hit its own tile's L2 with data in S state",
         "Offcore": "1"
     },
     {
         "EventCode": "0xB7",
-        "MSRValue": "0x0008003091 ",
+        "MSRValue": "0x0008003091",
         "Counter": "0,1",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.ANY_DATA_RD.L2_HIT_THIS_TILE_S",
         "MSRIndex": "0x1a6,0x1a7",
         "SampleAfterValue": "100007",
-        "BriefDescription": "Counts Demand cacheable data and L1 prefetch data read requests  that accounts for responses which hit its own tile's L2 with data in S state ",
+        "BriefDescription": "Counts Demand cacheable data and L1 prefetch data read requests  that accounts for responses which hit its own tile's L2 with data in S state",
         "Offcore": "1"
     },
     {
         "EventCode": "0xB7",
-        "MSRValue": "0x0008000022 ",
+        "MSRValue": "0x0008000022",
         "Counter": "0,1",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.ANY_RFO.L2_HIT_THIS_TILE_S",
         "MSRIndex": "0x1a6,0x1a7",
         "SampleAfterValue": "100007",
-        "BriefDescription": "Counts Demand cacheable data write requests  that accounts for responses which hit its own tile's L2 with data in S state ",
+        "BriefDescription": "Counts Demand cacheable data write requests  that accounts for responses which hit its own tile's L2 with data in S state",
         "Offcore": "1"
     },
     {
         "EventCode": "0xB7",
-        "MSRValue": "0x0008000044 ",
+        "MSRValue": "0x0008000044",
         "Counter": "0,1",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.ANY_CODE_RD.L2_HIT_THIS_TILE_S",
         "MSRIndex": "0x1a6,0x1a7",
         "SampleAfterValue": "100007",
-        "BriefDescription": "Counts Demand code reads and prefetch code read requests  that accounts for responses which hit its own tile's L2 with data in S state ",
+        "BriefDescription": "Counts Demand code reads and prefetch code read requests  that accounts for responses which hit its own tile's L2 with data in S state",
         "Offcore": "1"
     },
     {
         "EventCode": "0xB7",
-        "MSRValue": "0x00080032f7 ",
+        "MSRValue": "0x00080032f7",
         "Counter": "0,1",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.ANY_READ.L2_HIT_THIS_TILE_S",
         "MSRIndex": "0x1a6,0x1a7",
         "SampleAfterValue": "100007",
-        "BriefDescription": "Counts any Read request  that accounts for responses which hit its own tile's L2 with data in S state ",
+        "BriefDescription": "Counts any Read request  that accounts for responses which hit its own tile's L2 with data in S state",
         "Offcore": "1"
     },
     {
         "EventCode": "0xB7",
-        "MSRValue": "0x0010000001 ",
+        "MSRValue": "0x0010000001",
         "Counter": "0,1",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L2_HIT_THIS_TILE_F",
         "MSRIndex": "0x1a6,0x1a7",
         "SampleAfterValue": "100007",
-        "BriefDescription": "Counts demand cacheable data and L1 prefetch data reads that accounts for responses which hit its own tile's L2 with data in F state ",
+        "BriefDescription": "Counts demand cacheable data and L1 prefetch data reads that accounts for responses which hit its own tile's L2 with data in F state",
         "Offcore": "1"
     },
     {
         "EventCode": "0xB7",
-        "MSRValue": "0x0010000002 ",
+        "MSRValue": "0x0010000002",
         "Counter": "0,1",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L2_HIT_THIS_TILE_F",
         "MSRIndex": "0x1a6,0x1a7",
         "SampleAfterValue": "100007",
-        "BriefDescription": "Counts Demand cacheable data writes that accounts for responses which hit its own tile's L2 with data in F state ",
+        "BriefDescription": "Counts Demand cacheable data writes that accounts for responses which hit its own tile's L2 with data in F state",
         "Offcore": "1"
     },
     {
         "EventCode": "0xB7",
-        "MSRValue": "0x0010000004 ",
+        "MSRValue": "0x0010000004",
         "Counter": "0,1",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L2_HIT_THIS_TILE_F",
         "MSRIndex": "0x1a6,0x1a7",
         "SampleAfterValue": "100007",
-        "BriefDescription": "Counts demand code reads and prefetch code reads that accounts for responses which hit its own tile's L2 with data in F state ",
+        "BriefDescription": "Counts demand code reads and prefetch code reads that accounts for responses which hit its own tile's L2 with data in F state",
         "Offcore": "1"
     },
     {
         "EventCode": "0xB7",
-        "MSRValue": "0x0010000020 ",
+        "MSRValue": "0x0010000020",
         "Counter": "0,1",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.PF_L2_RFO.L2_HIT_THIS_TILE_F",
         "MSRIndex": "0x1a6,0x1a7",
         "SampleAfterValue": "100007",
-        "BriefDescription": "Counts L2 data RFO prefetches (includes PREFETCHW instruction) that accounts for responses which hit its own tile's L2 with data in F state ",
+        "BriefDescription": "Counts L2 data RFO prefetches (includes PREFETCHW instruction) that accounts for responses which hit its own tile's L2 with data in F state",
         "Offcore": "1"
     },
     {
         "EventCode": "0xB7",
-        "MSRValue": "0x0010000040 ",
+        "MSRValue": "0x0010000040",
         "Counter": "0,1",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.PF_L2_CODE_RD.L2_HIT_THIS_TILE_F",
         "MSRIndex": "0x1a6,0x1a7",
         "SampleAfterValue": "100007",
-        "BriefDescription": "Counts L2 code HW prefetches that accounts for responses which hit its own tile's L2 with data in F state ",
+        "BriefDescription": "Counts L2 code HW prefetches that accounts for responses which hit its own tile's L2 with data in F state",
         "Offcore": "1"
     },
     {
         "EventCode": "0xB7",
-        "MSRValue": "0x0010000080 ",
+        "MSRValue": "0x0010000080",
         "Counter": "0,1",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.PARTIAL_READS.L2_HIT_THIS_TILE_F",
         "MSRIndex": "0x1a6,0x1a7",
         "SampleAfterValue": "100007",
-        "BriefDescription": "Counts Partial reads (UC or WC and is valid only for Outstanding response type).  that accounts for responses which hit its own tile's L2 with data in F state ",
+        "BriefDescription": "Counts Partial reads (UC or WC and is valid only for Outstanding response type).  that accounts for responses which hit its own tile's L2 with data in F state",
         "Offcore": "1"
     },
     {
         "EventCode": "0xB7",
-        "MSRValue": "0x0010000100 ",
+        "MSRValue": "0x0010000100",
         "Counter": "0,1",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.PARTIAL_WRITES.L2_HIT_THIS_TILE_F",
         "MSRIndex": "0x1a7",
         "SampleAfterValue": "100007",
-        "BriefDescription": "Counts Partial writes (UC or WT or WP and should be programmed on PMC1) that accounts for responses which hit its own tile's L2 with data in F state ",
+        "BriefDescription": "Counts Partial writes (UC or WT or WP and should be programmed on PMC1) that accounts for responses which hit its own tile's L2 with data in F state",
         "Offcore": "1"
     },
     {
         "EventCode": "0xB7",
-        "MSRValue": "0x0010000200 ",
+        "MSRValue": "0x0010000200",
         "Counter": "0,1",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.UC_CODE_READS.L2_HIT_THIS_TILE_F",
         "MSRIndex": "0x1a6,0x1a7",
         "SampleAfterValue": "100007",
-        "BriefDescription": "Counts UC code reads (valid only for Outstanding response type)  that accounts for responses which hit its own tile's L2 with data in F state ",
+        "BriefDescription": "Counts UC code reads (valid only for Outstanding response type)  that accounts for responses which hit its own tile's L2 with data in F state",
         "Offcore": "1"
     },
     {
         "EventCode": "0xB7",
-        "MSRValue": "0x0010000400 ",
+        "MSRValue": "0x0010000400",
         "Counter": "0,1",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.BUS_LOCKS.L2_HIT_THIS_TILE_F",
         "MSRIndex": "0x1a6,0x1a7",
         "SampleAfterValue": "100007",
-        "BriefDescription": "Counts Bus locks and split lock requests that accounts for responses which hit its own tile's L2 with data in F state ",
+        "BriefDescription": "Counts Bus locks and split lock requests that accounts for responses which hit its own tile's L2 with data in F state",
         "Offcore": "1"
     },
     {
         "EventCode": "0xB7",
-        "MSRValue": "0x0010001000 ",
+        "MSRValue": "0x0010001000",
         "Counter": "0,1",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.PF_SOFTWARE.L2_HIT_THIS_TILE_F",
         "MSRIndex": "0x1a6,0x1a7",
         "SampleAfterValue": "100007",
-        "BriefDescription": "Counts Software Prefetches that accounts for responses which hit its own tile's L2 with data in F state ",
+        "BriefDescription": "Counts Software Prefetches that accounts for responses which hit its own tile's L2 with data in F state",
         "Offcore": "1"
     },
     {
         "EventCode": "0xB7",
-        "MSRValue": "0x0010002000 ",
+        "MSRValue": "0x0010002000",
         "Counter": "0,1",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.PF_L1_DATA_RD.L2_HIT_THIS_TILE_F",
         "MSRIndex": "0x1a6,0x1a7",
         "SampleAfterValue": "100007",
-        "BriefDescription": "Counts L1 data HW prefetches that accounts for responses which hit its own tile's L2 with data in F state ",
+        "BriefDescription": "Counts L1 data HW prefetches that accounts for responses which hit its own tile's L2 with data in F state",
         "Offcore": "1"
     },
     {
         "EventCode": "0xB7",
-        "MSRValue": "0x0010008000 ",
+        "MSRValue": "0x0010008000",
         "Counter": "0,1",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.ANY_REQUEST.L2_HIT_THIS_TILE_F",
         "MSRIndex": "0x1a6,0x1a7",
         "SampleAfterValue": "100007",
-        "BriefDescription": "Counts any request that accounts for responses which hit its own tile's L2 with data in F state ",
+        "BriefDescription": "Counts any request that accounts for responses which hit its own tile's L2 with data in F state",
         "Offcore": "1"
     },
     {
         "EventCode": "0xB7",
-        "MSRValue": "0x0010003091 ",
+        "MSRValue": "0x0010003091",
         "Counter": "0,1",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.ANY_DATA_RD.L2_HIT_THIS_TILE_F",
         "MSRIndex": "0x1a6,0x1a7",
         "SampleAfterValue": "100007",
-        "BriefDescription": "Counts Demand cacheable data and L1 prefetch data read requests  that accounts for responses which hit its own tile's L2 with data in F state ",
+        "BriefDescription": "Counts Demand cacheable data and L1 prefetch data read requests  that accounts for responses which hit its own tile's L2 with data in F state",
         "Offcore": "1"
     },
     {
         "EventCode": "0xB7",
-        "MSRValue": "0x0010000022 ",
+        "MSRValue": "0x0010000022",
         "Counter": "0,1",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.ANY_RFO.L2_HIT_THIS_TILE_F",
         "MSRIndex": "0x1a6,0x1a7",
         "SampleAfterValue": "100007",
-        "BriefDescription": "Counts Demand cacheable data write requests  that accounts for responses which hit its own tile's L2 with data in F state ",
+        "BriefDescription": "Counts Demand cacheable data write requests  that accounts for responses which hit its own tile's L2 with data in F state",
         "Offcore": "1"
     },
     {
         "EventCode": "0xB7",
-        "MSRValue": "0x0010000044 ",
+        "MSRValue": "0x0010000044",
         "Counter": "0,1",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.ANY_CODE_RD.L2_HIT_THIS_TILE_F",
         "MSRIndex": "0x1a6,0x1a7",
         "SampleAfterValue": "100007",
-        "BriefDescription": "Counts Demand code reads and prefetch code read requests  that accounts for responses which hit its own tile's L2 with data in F state ",
+        "BriefDescription": "Counts Demand code reads and prefetch code read requests  that accounts for responses which hit its own tile's L2 with data in F state",
         "Offcore": "1"
     },
     {
         "EventCode": "0xB7",
-        "MSRValue": "0x00100032f7 ",
+        "MSRValue": "0x00100032f7",
         "Counter": "0,1",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.ANY_READ.L2_HIT_THIS_TILE_F",
         "MSRIndex": "0x1a6,0x1a7",
         "SampleAfterValue": "100007",
-        "BriefDescription": "Counts any Read request  that accounts for responses which hit its own tile's L2 with data in F state ",
+        "BriefDescription": "Counts any Read request  that accounts for responses which hit its own tile's L2 with data in F state",
         "Offcore": "1"
     },
     {
         "EventCode": "0xB7",
-        "MSRValue": "0x0010000070 ",
+        "MSRValue": "0x0010000070",
         "Counter": "0,1",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.ANY_PF_L2.L2_HIT_THIS_TILE_F",
         "MSRIndex": "0x1a6,0x1a7",
         "SampleAfterValue": "100007",
-        "BriefDescription": "Counts any Prefetch requests that accounts for responses which hit its own tile's L2 with data in F state ",
+        "BriefDescription": "Counts any Prefetch requests that accounts for responses which hit its own tile's L2 with data in F state",
         "Offcore": "1"
     },
     {
         "EventCode": "0xB7",
-        "MSRValue": "0x1800180002 ",
+        "MSRValue": "0x1800180002",
         "Counter": "0,1",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L2_HIT_NEAR_TILE",
@@ -1985,7 +1985,7 @@
     },
     {
         "EventCode": "0xB7",
-        "MSRValue": "0x1800180004 ",
+        "MSRValue": "0x1800180004",
         "Counter": "0,1",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L2_HIT_NEAR_TILE",
@@ -1996,7 +1996,7 @@
     },
     {
         "EventCode": "0xB7",
-        "MSRValue": "0x1800180020 ",
+        "MSRValue": "0x1800180020",
         "Counter": "0,1",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.PF_L2_RFO.L2_HIT_NEAR_TILE",
@@ -2007,7 +2007,7 @@
     },
     {
         "EventCode": "0xB7",
-        "MSRValue": "0x1800180040 ",
+        "MSRValue": "0x1800180040",
         "Counter": "0,1",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.PF_L2_CODE_RD.L2_HIT_NEAR_TILE",
@@ -2018,7 +2018,7 @@
     },
     {
         "EventCode": "0xB7",
-        "MSRValue": "0x1800180080 ",
+        "MSRValue": "0x1800180080",
         "Counter": "0,1",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.PARTIAL_READS.L2_HIT_NEAR_TILE",
@@ -2029,7 +2029,7 @@
     },
     {
         "EventCode": "0xB7",
-        "MSRValue": "0x1800180100 ",
+        "MSRValue": "0x1800180100",
         "Counter": "0,1",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.PARTIAL_WRITES.L2_HIT_NEAR_TILE",
@@ -2040,7 +2040,7 @@
     },
     {
         "EventCode": "0xB7",
-        "MSRValue": "0x1800180200 ",
+        "MSRValue": "0x1800180200",
         "Counter": "0,1",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.UC_CODE_READS.L2_HIT_NEAR_TILE",
@@ -2051,7 +2051,7 @@
     },
     {
         "EventCode": "0xB7",
-        "MSRValue": "0x1800180400 ",
+        "MSRValue": "0x1800180400",
         "Counter": "0,1",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.BUS_LOCKS.L2_HIT_NEAR_TILE",
@@ -2062,7 +2062,7 @@
     },
     {
         "EventCode": "0xB7",
-        "MSRValue": "0x1800181000 ",
+        "MSRValue": "0x1800181000",
         "Counter": "0,1",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.PF_SOFTWARE.L2_HIT_NEAR_TILE",
@@ -2073,7 +2073,7 @@
     },
     {
         "EventCode": "0xB7",
-        "MSRValue": "0x1800182000 ",
+        "MSRValue": "0x1800182000",
         "Counter": "0,1",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.PF_L1_DATA_RD.L2_HIT_NEAR_TILE",
@@ -2084,7 +2084,7 @@
     },
     {
         "EventCode": "0xB7",
-        "MSRValue": "0x1800188000 ",
+        "MSRValue": "0x1800188000",
         "Counter": "0,1",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.ANY_REQUEST.L2_HIT_NEAR_TILE",
@@ -2095,7 +2095,7 @@
     },
     {
         "EventCode": "0xB7",
-        "MSRValue": "0x1800183091 ",
+        "MSRValue": "0x1800183091",
         "Counter": "0,1",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.ANY_DATA_RD.L2_HIT_NEAR_TILE",
@@ -2106,7 +2106,7 @@
     },
     {
         "EventCode": "0xB7",
-        "MSRValue": "0x1800180022 ",
+        "MSRValue": "0x1800180022",
         "Counter": "0,1",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.ANY_RFO.L2_HIT_NEAR_TILE",
@@ -2117,7 +2117,7 @@
     },
     {
         "EventCode": "0xB7",
-        "MSRValue": "0x1800180044 ",
+        "MSRValue": "0x1800180044",
         "Counter": "0,1",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.ANY_CODE_RD.L2_HIT_NEAR_TILE",
@@ -2128,7 +2128,7 @@
     },
     {
         "EventCode": "0xB7",
-        "MSRValue": "0x18001832f7 ",
+        "MSRValue": "0x18001832f7",
         "Counter": "0,1",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.ANY_READ.L2_HIT_NEAR_TILE",
@@ -2139,7 +2139,7 @@
     },
     {
         "EventCode": "0xB7",
-        "MSRValue": "0x1800180070 ",
+        "MSRValue": "0x1800180070",
         "Counter": "0,1",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.ANY_PF_L2.L2_HIT_NEAR_TILE",
@@ -2150,7 +2150,7 @@
     },
     {
         "EventCode": "0xB7",
-        "MSRValue": "0x1800400002 ",
+        "MSRValue": "0x1800400002",
         "Counter": "0,1",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L2_HIT_FAR_TILE",
@@ -2161,7 +2161,7 @@
     },
     {
         "EventCode": "0xB7",
-        "MSRValue": "0x1800400004 ",
+        "MSRValue": "0x1800400004",
         "Counter": "0,1",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L2_HIT_FAR_TILE",
@@ -2172,7 +2172,7 @@
     },
     {
         "EventCode": "0xB7",
-        "MSRValue": "0x1800400040 ",
+        "MSRValue": "0x1800400040",
         "Counter": "0,1",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.PF_L2_CODE_RD.L2_HIT_FAR_TILE",
@@ -2183,7 +2183,7 @@
     },
     {
         "EventCode": "0xB7",
-        "MSRValue": "0x1800400080 ",
+        "MSRValue": "0x1800400080",
         "Counter": "0,1",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.PARTIAL_READS.L2_HIT_FAR_TILE",
@@ -2194,7 +2194,7 @@
     },
     {
         "EventCode": "0xB7",
-        "MSRValue": "0x1800400100 ",
+        "MSRValue": "0x1800400100",
         "Counter": "0,1",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.PARTIAL_WRITES.L2_HIT_FAR_TILE",
@@ -2205,7 +2205,7 @@
     },
     {
         "EventCode": "0xB7",
-        "MSRValue": "0x1800400400 ",
+        "MSRValue": "0x1800400400",
         "Counter": "0,1",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.BUS_LOCKS.L2_HIT_FAR_TILE",
@@ -2216,7 +2216,7 @@
     },
     {
         "EventCode": "0xB7",
-        "MSRValue": "0x1800401000 ",
+        "MSRValue": "0x1800401000",
         "Counter": "0,1",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.PF_SOFTWARE.L2_HIT_FAR_TILE",
@@ -2227,7 +2227,7 @@
     },
     {
         "EventCode": "0xB7",
-        "MSRValue": "0x1800402000 ",
+        "MSRValue": "0x1800402000",
         "Counter": "0,1",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.PF_L1_DATA_RD.L2_HIT_FAR_TILE",
@@ -2238,7 +2238,7 @@
     },
     {
         "EventCode": "0xB7",
-        "MSRValue": "0x1800408000 ",
+        "MSRValue": "0x1800408000",
         "Counter": "0,1",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.ANY_REQUEST.L2_HIT_FAR_TILE",
@@ -2249,7 +2249,7 @@
     },
     {
         "EventCode": "0xB7",
-        "MSRValue": "0x1800403091 ",
+        "MSRValue": "0x1800403091",
         "Counter": "0,1",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.ANY_DATA_RD.L2_HIT_FAR_TILE",
@@ -2260,7 +2260,7 @@
     },
     {
         "EventCode": "0xB7",
-        "MSRValue": "0x1800400022 ",
+        "MSRValue": "0x1800400022",
         "Counter": "0,1",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.ANY_RFO.L2_HIT_FAR_TILE",
@@ -2271,7 +2271,7 @@
     },
     {
         "EventCode": "0xB7",
-        "MSRValue": "0x1800400044 ",
+        "MSRValue": "0x1800400044",
         "Counter": "0,1",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.ANY_CODE_RD.L2_HIT_FAR_TILE",
@@ -2282,7 +2282,7 @@
     },
     {
         "EventCode": "0xB7",
-        "MSRValue": "0x18004032f7 ",
+        "MSRValue": "0x18004032f7",
         "Counter": "0,1",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.ANY_READ.L2_HIT_FAR_TILE",
@@ -2293,7 +2293,7 @@
     },
     {
         "EventCode": "0xB7",
-        "MSRValue": "0x1800400070 ",
+        "MSRValue": "0x1800400070",
         "Counter": "0,1",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.ANY_PF_L2.L2_HIT_FAR_TILE",
diff --git a/tools/perf/pmu-events/arch/x86/knightslanding/memory.json b/tools/perf/pmu-events/arch/x86/knightslanding/memory.json
index 700652566200..c6bb16ba0f86 100644
--- a/tools/perf/pmu-events/arch/x86/knightslanding/memory.json
+++ b/tools/perf/pmu-events/arch/x86/knightslanding/memory.json
@@ -9,18 +9,18 @@
     },
     {
         "EventCode": "0xB7",
-        "MSRValue": "0x0100400070 ",
+        "MSRValue": "0x0100400070",
         "Counter": "0,1",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.ANY_PF_L2.MCDRAM_FAR",
         "MSRIndex": "0x1a6,0x1a7",
         "SampleAfterValue": "100007",
-        "BriefDescription": "Counts any Prefetch requests that accounts for data responses from MCDRAM Far or Other tile L2 hit far. ",
+        "BriefDescription": "Counts any Prefetch requests that accounts for data responses from MCDRAM Far or Other tile L2 hit far.",
         "Offcore": "1"
     },
     {
         "EventCode": "0xB7",
-        "MSRValue": "0x0080200070 ",
+        "MSRValue": "0x0080200070",
         "Counter": "0,1",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.ANY_PF_L2.MCDRAM_NEAR",
@@ -31,18 +31,18 @@
     },
     {
         "EventCode": "0xB7",
-        "MSRValue": "0x0101000070 ",
+        "MSRValue": "0x0101000070",
         "Counter": "0,1",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.ANY_PF_L2.DDR_FAR",
         "MSRIndex": "0x1a6,0x1a7",
         "SampleAfterValue": "100007",
-        "BriefDescription": "Counts any Prefetch requests that accounts for data responses from DRAM Far. ",
+        "BriefDescription": "Counts any Prefetch requests that accounts for data responses from DRAM Far.",
         "Offcore": "1"
     },
     {
         "EventCode": "0xB7",
-        "MSRValue": "0x0080800070 ",
+        "MSRValue": "0x0080800070",
         "Counter": "0,1",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.ANY_PF_L2.DDR_NEAR",
@@ -53,18 +53,18 @@
     },
     {
         "EventCode": "0xB7",
-        "MSRValue": "0x01004032f7 ",
+        "MSRValue": "0x01004032f7",
         "Counter": "0,1",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.ANY_READ.MCDRAM_FAR",
         "MSRIndex": "0x1a6,0x1a7",
         "SampleAfterValue": "100007",
-        "BriefDescription": "Counts any Read request  that accounts for data responses from MCDRAM Far or Other tile L2 hit far. ",
+        "BriefDescription": "Counts any Read request  that accounts for data responses from MCDRAM Far or Other tile L2 hit far.",
         "Offcore": "1"
     },
     {
         "EventCode": "0xB7",
-        "MSRValue": "0x00802032f7 ",
+        "MSRValue": "0x00802032f7",
         "Counter": "0,1",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.ANY_READ.MCDRAM_NEAR",
@@ -75,18 +75,18 @@
     },
     {
         "EventCode": "0xB7",
-        "MSRValue": "0x01010032f7 ",
+        "MSRValue": "0x01010032f7",
         "Counter": "0,1",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.ANY_READ.DDR_FAR",
         "MSRIndex": "0x1a6,0x1a7",
         "SampleAfterValue": "100007",
-        "BriefDescription": "Counts any Read request  that accounts for data responses from DRAM Far. ",
+        "BriefDescription": "Counts any Read request  that accounts for data responses from DRAM Far.",
         "Offcore": "1"
     },
     {
         "EventCode": "0xB7",
-        "MSRValue": "0x00808032f7 ",
+        "MSRValue": "0x00808032f7",
         "Counter": "0,1",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.ANY_READ.DDR_NEAR",
@@ -97,18 +97,18 @@
     },
     {
         "EventCode": "0xB7",
-        "MSRValue": "0x0100400044 ",
+        "MSRValue": "0x0100400044",
         "Counter": "0,1",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.ANY_CODE_RD.MCDRAM_FAR",
         "MSRIndex": "0x1a6,0x1a7",
         "SampleAfterValue": "100007",
-        "BriefDescription": "Counts Demand code reads and prefetch code read requests  that accounts for data responses from MCDRAM Far or Other tile L2 hit far. ",
+        "BriefDescription": "Counts Demand code reads and prefetch code read requests  that accounts for data responses from MCDRAM Far or Other tile L2 hit far.",
         "Offcore": "1"
     },
     {
         "EventCode": "0xB7",
-        "MSRValue": "0x0080200044 ",
+        "MSRValue": "0x0080200044",
         "Counter": "0,1",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.ANY_CODE_RD.MCDRAM_NEAR",
@@ -119,18 +119,18 @@
     },
     {
         "EventCode": "0xB7",
-        "MSRValue": "0x0101000044 ",
+        "MSRValue": "0x0101000044",
         "Counter": "0,1",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.ANY_CODE_RD.DDR_FAR",
         "MSRIndex": "0x1a6,0x1a7",
         "SampleAfterValue": "100007",
-        "BriefDescription": "Counts Demand code reads and prefetch code read requests  that accounts for data responses from DRAM Far. ",
+        "BriefDescription": "Counts Demand code reads and prefetch code read requests  that accounts for data responses from DRAM Far.",
         "Offcore": "1"
     },
     {
         "EventCode": "0xB7",
-        "MSRValue": "0x0080800044 ",
+        "MSRValue": "0x0080800044",
         "Counter": "0,1",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.ANY_CODE_RD.DDR_NEAR",
@@ -141,18 +141,18 @@
     },
     {
         "EventCode": "0xB7",
-        "MSRValue": "0x0100400022 ",
+        "MSRValue": "0x0100400022",
         "Counter": "0,1",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.ANY_RFO.MCDRAM_FAR",
         "MSRIndex": "0x1a6,0x1a7",
         "SampleAfterValue": "100007",
-        "BriefDescription": "Counts Demand cacheable data write requests  that accounts for data responses from MCDRAM Far or Other tile L2 hit far. ",
+        "BriefDescription": "Counts Demand cacheable data write requests  that accounts for data responses from MCDRAM Far or Other tile L2 hit far.",
         "Offcore": "1"
     },
     {
         "EventCode": "0xB7",
-        "MSRValue": "0x0080200022 ",
+        "MSRValue": "0x0080200022",
         "Counter": "0,1",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.ANY_RFO.MCDRAM_NEAR",
@@ -163,18 +163,18 @@
     },
     {
         "EventCode": "0xB7",
-        "MSRValue": "0x0101000022 ",
+        "MSRValue": "0x0101000022",
         "Counter": "0,1",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.ANY_RFO.DDR_FAR",
         "MSRIndex": "0x1a6,0x1a7",
         "SampleAfterValue": "100007",
-        "BriefDescription": "Counts Demand cacheable data write requests  that accounts for data responses from DRAM Far. ",
+        "BriefDescription": "Counts Demand cacheable data write requests  that accounts for data responses from DRAM Far.",
         "Offcore": "1"
     },
     {
         "EventCode": "0xB7",
-        "MSRValue": "0x0080800022 ",
+        "MSRValue": "0x0080800022",
         "Counter": "0,1",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.ANY_RFO.DDR_NEAR",
@@ -185,18 +185,18 @@
     },
     {
         "EventCode": "0xB7",
-        "MSRValue": "0x0100403091 ",
+        "MSRValue": "0x0100403091",
         "Counter": "0,1",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.ANY_DATA_RD.MCDRAM_FAR",
         "MSRIndex": "0x1a6,0x1a7",
         "SampleAfterValue": "100007",
-        "BriefDescription": "Counts Demand cacheable data and L1 prefetch data read requests  that accounts for data responses from MCDRAM Far or Other tile L2 hit far. ",
+        "BriefDescription": "Counts Demand cacheable data and L1 prefetch data read requests  that accounts for data responses from MCDRAM Far or Other tile L2 hit far.",
         "Offcore": "1"
     },
     {
         "EventCode": "0xB7",
-        "MSRValue": "0x0080203091 ",
+        "MSRValue": "0x0080203091",
         "Counter": "0,1",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.ANY_DATA_RD.MCDRAM_NEAR",
@@ -207,18 +207,18 @@
     },
     {
         "EventCode": "0xB7",
-        "MSRValue": "0x0101003091 ",
+        "MSRValue": "0x0101003091",
         "Counter": "0,1",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.ANY_DATA_RD.DDR_FAR",
         "MSRIndex": "0x1a6,0x1a7",
         "SampleAfterValue": "100007",
-        "BriefDescription": "Counts Demand cacheable data and L1 prefetch data read requests  that accounts for data responses from DRAM Far. ",
+        "BriefDescription": "Counts Demand cacheable data and L1 prefetch data read requests  that accounts for data responses from DRAM Far.",
         "Offcore": "1"
     },
     {
         "EventCode": "0xB7",
-        "MSRValue": "0x0080803091 ",
+        "MSRValue": "0x0080803091",
         "Counter": "0,1",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.ANY_DATA_RD.DDR_NEAR",
@@ -229,18 +229,18 @@
     },
     {
         "EventCode": "0xB7",
-        "MSRValue": "0x0100408000 ",
+        "MSRValue": "0x0100408000",
         "Counter": "0,1",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.ANY_REQUEST.MCDRAM_FAR",
         "MSRIndex": "0x1a6,0x1a7",
         "SampleAfterValue": "100007",
-        "BriefDescription": "Counts any request that accounts for data responses from MCDRAM Far or Other tile L2 hit far. ",
+        "BriefDescription": "Counts any request that accounts for data responses from MCDRAM Far or Other tile L2 hit far.",
         "Offcore": "1"
     },
     {
         "EventCode": "0xB7",
-        "MSRValue": "0x0080208000 ",
+        "MSRValue": "0x0080208000",
         "Counter": "0,1",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.ANY_REQUEST.MCDRAM_NEAR",
@@ -251,18 +251,18 @@
     },
     {
         "EventCode": "0xB7",
-        "MSRValue": "0x0101008000 ",
+        "MSRValue": "0x0101008000",
         "Counter": "0,1",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.ANY_REQUEST.DDR_FAR",
         "MSRIndex": "0x1a6,0x1a7",
         "SampleAfterValue": "100007",
-        "BriefDescription": "Counts any request that accounts for data responses from DRAM Far. ",
+        "BriefDescription": "Counts any request that accounts for data responses from DRAM Far.",
         "Offcore": "1"
     },
     {
         "EventCode": "0xB7",
-        "MSRValue": "0x0080808000 ",
+        "MSRValue": "0x0080808000",
         "Counter": "0,1",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.ANY_REQUEST.DDR_NEAR",
@@ -273,18 +273,18 @@
     },
     {
         "EventCode": "0xB7",
-        "MSRValue": "0x0100402000 ",
+        "MSRValue": "0x0100402000",
         "Counter": "0,1",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.PF_L1_DATA_RD.MCDRAM_FAR",
         "MSRIndex": "0x1a6,0x1a7",
         "SampleAfterValue": "100007",
-        "BriefDescription": "Counts L1 data HW prefetches that accounts for data responses from MCDRAM Far or Other tile L2 hit far. ",
+        "BriefDescription": "Counts L1 data HW prefetches that accounts for data responses from MCDRAM Far or Other tile L2 hit far.",
         "Offcore": "1"
     },
     {
         "EventCode": "0xB7",
-        "MSRValue": "0x0080202000 ",
+        "MSRValue": "0x0080202000",
         "Counter": "0,1",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.PF_L1_DATA_RD.MCDRAM_NEAR",
@@ -295,18 +295,18 @@
     },
     {
         "EventCode": "0xB7",
-        "MSRValue": "0x0101002000 ",
+        "MSRValue": "0x0101002000",
         "Counter": "0,1",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.PF_L1_DATA_RD.DDR_FAR",
         "MSRIndex": "0x1a6,0x1a7",
         "SampleAfterValue": "100007",
-        "BriefDescription": "Counts L1 data HW prefetches that accounts for data responses from DRAM Far. ",
+        "BriefDescription": "Counts L1 data HW prefetches that accounts for data responses from DRAM Far.",
         "Offcore": "1"
     },
     {
         "EventCode": "0xB7",
-        "MSRValue": "0x0080802000 ",
+        "MSRValue": "0x0080802000",
         "Counter": "0,1",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.PF_L1_DATA_RD.DDR_NEAR",
@@ -317,18 +317,18 @@
     },
     {
         "EventCode": "0xB7",
-        "MSRValue": "0x0100401000 ",
+        "MSRValue": "0x0100401000",
         "Counter": "0,1",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.PF_SOFTWARE.MCDRAM_FAR",
         "MSRIndex": "0x1a6,0x1a7",
         "SampleAfterValue": "100007",
-        "BriefDescription": "Counts Software Prefetches that accounts for data responses from MCDRAM Far or Other tile L2 hit far. ",
+        "BriefDescription": "Counts Software Prefetches that accounts for data responses from MCDRAM Far or Other tile L2 hit far.",
         "Offcore": "1"
     },
     {
         "EventCode": "0xB7",
-        "MSRValue": "0x0080201000 ",
+        "MSRValue": "0x0080201000",
         "Counter": "0,1",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.PF_SOFTWARE.MCDRAM_NEAR",
@@ -339,18 +339,18 @@
     },
     {
         "EventCode": "0xB7",
-        "MSRValue": "0x0101001000 ",
+        "MSRValue": "0x0101001000",
         "Counter": "0,1",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.PF_SOFTWARE.DDR_FAR",
         "MSRIndex": "0x1a6,0x1a7",
         "SampleAfterValue": "100007",
-        "BriefDescription": "Counts Software Prefetches that accounts for data responses from DRAM Far. ",
+        "BriefDescription": "Counts Software Prefetches that accounts for data responses from DRAM Far.",
         "Offcore": "1"
     },
     {
         "EventCode": "0xB7",
-        "MSRValue": "0x0080801000 ",
+        "MSRValue": "0x0080801000",
         "Counter": "0,1",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.PF_SOFTWARE.DDR_NEAR",
@@ -361,18 +361,18 @@
     },
     {
         "EventCode": "0xB7",
-        "MSRValue": "0x0100400400 ",
+        "MSRValue": "0x0100400400",
         "Counter": "0,1",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.BUS_LOCKS.MCDRAM_FAR",
         "MSRIndex": "0x1a6,0x1a7",
         "SampleAfterValue": "100007",
-        "BriefDescription": "Counts Bus locks and split lock requests that accounts for data responses from MCDRAM Far or Other tile L2 hit far. ",
+        "BriefDescription": "Counts Bus locks and split lock requests that accounts for data responses from MCDRAM Far or Other tile L2 hit far.",
         "Offcore": "1"
     },
     {
         "EventCode": "0xB7",
-        "MSRValue": "0x0080200400 ",
+        "MSRValue": "0x0080200400",
         "Counter": "0,1",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.BUS_LOCKS.MCDRAM_NEAR",
@@ -383,18 +383,18 @@
     },
     {
         "EventCode": "0xB7",
-        "MSRValue": "0x0101000400 ",
+        "MSRValue": "0x0101000400",
         "Counter": "0,1",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.BUS_LOCKS.DDR_FAR",
         "MSRIndex": "0x1a6,0x1a7",
         "SampleAfterValue": "100007",
-        "BriefDescription": "Counts Bus locks and split lock requests that accounts for data responses from DRAM Far. ",
+        "BriefDescription": "Counts Bus locks and split lock requests that accounts for data responses from DRAM Far.",
         "Offcore": "1"
     },
     {
         "EventCode": "0xB7",
-        "MSRValue": "0x0080800400 ",
+        "MSRValue": "0x0080800400",
         "Counter": "0,1",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.BUS_LOCKS.DDR_NEAR",
@@ -405,18 +405,18 @@
     },
     {
         "EventCode": "0xB7",
-        "MSRValue": "0x0100400200 ",
+        "MSRValue": "0x0100400200",
         "Counter": "0,1",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.UC_CODE_READS.MCDRAM_FAR",
         "MSRIndex": "0x1a6,0x1a7",
         "SampleAfterValue": "100007",
-        "BriefDescription": "Counts UC code reads (valid only for Outstanding response type)  that accounts for data responses from MCDRAM Far or Other tile L2 hit far. ",
+        "BriefDescription": "Counts UC code reads (valid only for Outstanding response type)  that accounts for data responses from MCDRAM Far or Other tile L2 hit far.",
         "Offcore": "1"
     },
     {
         "EventCode": "0xB7",
-        "MSRValue": "0x0080200200 ",
+        "MSRValue": "0x0080200200",
         "Counter": "0,1",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.UC_CODE_READS.MCDRAM_NEAR",
@@ -427,18 +427,18 @@
     },
     {
         "EventCode": "0xB7",
-        "MSRValue": "0x0101000200 ",
+        "MSRValue": "0x0101000200",
         "Counter": "0,1",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.UC_CODE_READS.DDR_FAR",
         "MSRIndex": "0x1a6,0x1a7",
         "SampleAfterValue": "100007",
-        "BriefDescription": "Counts UC code reads (valid only for Outstanding response type)  that accounts for data responses from DRAM Far. ",
+        "BriefDescription": "Counts UC code reads (valid only for Outstanding response type)  that accounts for data responses from DRAM Far.",
         "Offcore": "1"
     },
     {
         "EventCode": "0xB7",
-        "MSRValue": "0x0080800200 ",
+        "MSRValue": "0x0080800200",
         "Counter": "0,1",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.UC_CODE_READS.DDR_NEAR",
@@ -449,18 +449,18 @@
     },
     {
         "EventCode": "0xB7",
-        "MSRValue": "0x0100400100 ",
+        "MSRValue": "0x0100400100",
         "Counter": "0,1",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.PARTIAL_WRITES.MCDRAM_FAR",
         "MSRIndex": "0x1a7",
         "SampleAfterValue": "100007",
-        "BriefDescription": "Counts Partial writes (UC or WT or WP and should be programmed on PMC1) that accounts for data responses from MCDRAM Far or Other tile L2 hit far. ",
+        "BriefDescription": "Counts Partial writes (UC or WT or WP and should be programmed on PMC1) that accounts for data responses from MCDRAM Far or Other tile L2 hit far.",
         "Offcore": "1"
     },
     {
         "EventCode": "0xB7",
-        "MSRValue": "0x0080200100 ",
+        "MSRValue": "0x0080200100",
         "Counter": "0,1",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.PARTIAL_WRITES.MCDRAM_NEAR",
@@ -471,18 +471,18 @@
     },
     {
         "EventCode": "0xB7",
-        "MSRValue": "0x0101000100 ",
+        "MSRValue": "0x0101000100",
         "Counter": "0,1",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.PARTIAL_WRITES.DDR_FAR",
         "MSRIndex": "0x1a7",
         "SampleAfterValue": "100007",
-        "BriefDescription": "Counts Partial writes (UC or WT or WP and should be programmed on PMC1) that accounts for data responses from DRAM Far. ",
+        "BriefDescription": "Counts Partial writes (UC or WT or WP and should be programmed on PMC1) that accounts for data responses from DRAM Far.",
         "Offcore": "1"
     },
     {
         "EventCode": "0xB7",
-        "MSRValue": "0x0080800100 ",
+        "MSRValue": "0x0080800100",
         "Counter": "0,1",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.PARTIAL_WRITES.DDR_NEAR",
@@ -493,7 +493,7 @@
     },
     {
         "EventCode": "0xB7",
-        "MSRValue": "0x2000020080 ",
+        "MSRValue": "0x2000020080",
         "Counter": "0,1",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.PARTIAL_READS.NON_DRAM",
@@ -504,18 +504,18 @@
     },
     {
         "EventCode": "0xB7",
-        "MSRValue": "0x0100400080 ",
+        "MSRValue": "0x0100400080",
         "Counter": "0,1",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.PARTIAL_READS.MCDRAM_FAR",
         "MSRIndex": "0x1a6,0x1a7",
         "SampleAfterValue": "100007",
-        "BriefDescription": "Counts Partial reads (UC or WC and is valid only for Outstanding response type).  that accounts for data responses from MCDRAM Far or Other tile L2 hit far. ",
+        "BriefDescription": "Counts Partial reads (UC or WC and is valid only for Outstanding response type).  that accounts for data responses from MCDRAM Far or Other tile L2 hit far.",
         "Offcore": "1"
     },
     {
         "EventCode": "0xB7",
-        "MSRValue": "0x0080200080 ",
+        "MSRValue": "0x0080200080",
         "Counter": "0,1",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.PARTIAL_READS.MCDRAM_NEAR",
@@ -526,18 +526,18 @@
     },
     {
         "EventCode": "0xB7",
-        "MSRValue": "0x0101000080 ",
+        "MSRValue": "0x0101000080",
         "Counter": "0,1",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.PARTIAL_READS.DDR_FAR",
         "MSRIndex": "0x1a6,0x1a7",
         "SampleAfterValue": "100007",
-        "BriefDescription": "Counts Partial reads (UC or WC and is valid only for Outstanding response type).  that accounts for data responses from DRAM Far. ",
+        "BriefDescription": "Counts Partial reads (UC or WC and is valid only for Outstanding response type).  that accounts for data responses from DRAM Far.",
         "Offcore": "1"
     },
     {
         "EventCode": "0xB7",
-        "MSRValue": "0x0080800080 ",
+        "MSRValue": "0x0080800080",
         "Counter": "0,1",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.PARTIAL_READS.DDR_NEAR",
@@ -548,18 +548,18 @@
     },
     {
         "EventCode": "0xB7",
-        "MSRValue": "0x0100400040 ",
+        "MSRValue": "0x0100400040",
         "Counter": "0,1",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.PF_L2_CODE_RD.MCDRAM_FAR",
         "MSRIndex": "0x1a6,0x1a7",
         "SampleAfterValue": "100007",
-        "BriefDescription": "Counts L2 code HW prefetches that accounts for data responses from MCDRAM Far or Other tile L2 hit far. ",
+        "BriefDescription": "Counts L2 code HW prefetches that accounts for data responses from MCDRAM Far or Other tile L2 hit far.",
         "Offcore": "1"
     },
     {
         "EventCode": "0xB7",
-        "MSRValue": "0x0080200040 ",
+        "MSRValue": "0x0080200040",
         "Counter": "0,1",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.PF_L2_CODE_RD.MCDRAM_NEAR",
@@ -570,18 +570,18 @@
     },
     {
         "EventCode": "0xB7",
-        "MSRValue": "0x0101000040 ",
+        "MSRValue": "0x0101000040",
         "Counter": "0,1",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.PF_L2_CODE_RD.DDR_FAR",
         "MSRIndex": "0x1a6,0x1a7",
         "SampleAfterValue": "100007",
-        "BriefDescription": "Counts L2 code HW prefetches that accounts for data responses from DRAM Far. ",
+        "BriefDescription": "Counts L2 code HW prefetches that accounts for data responses from DRAM Far.",
         "Offcore": "1"
     },
     {
         "EventCode": "0xB7",
-        "MSRValue": "0x0080800040 ",
+        "MSRValue": "0x0080800040",
         "Counter": "0,1",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.PF_L2_CODE_RD.DDR_NEAR",
@@ -592,7 +592,7 @@
     },
     {
         "EventCode": "0xB7",
-        "MSRValue": "0x2000020020 ",
+        "MSRValue": "0x2000020020",
         "Counter": "0,1",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.PF_L2_RFO.NON_DRAM",
@@ -603,18 +603,18 @@
     },
     {
         "EventCode": "0xB7",
-        "MSRValue": "0x0100400020 ",
+        "MSRValue": "0x0100400020",
         "Counter": "0,1",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.PF_L2_RFO.MCDRAM_FAR",
         "MSRIndex": "0x1a6,0x1a7",
         "SampleAfterValue": "100007",
-        "BriefDescription": "Counts L2 data RFO prefetches (includes PREFETCHW instruction) that accounts for data responses from MCDRAM Far or Other tile L2 hit far. ",
+        "BriefDescription": "Counts L2 data RFO prefetches (includes PREFETCHW instruction) that accounts for data responses from MCDRAM Far or Other tile L2 hit far.",
         "Offcore": "1"
     },
     {
         "EventCode": "0xB7",
-        "MSRValue": "0x0080200020 ",
+        "MSRValue": "0x0080200020",
         "Counter": "0,1",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.PF_L2_RFO.MCDRAM_NEAR",
@@ -625,18 +625,18 @@
     },
     {
         "EventCode": "0xB7",
-        "MSRValue": "0x0101000020 ",
+        "MSRValue": "0x0101000020",
         "Counter": "0,1",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.PF_L2_RFO.DDR_FAR",
         "MSRIndex": "0x1a6,0x1a7",
         "SampleAfterValue": "100007",
-        "BriefDescription": "Counts L2 data RFO prefetches (includes PREFETCHW instruction) that accounts for data responses from DRAM Far. ",
+        "BriefDescription": "Counts L2 data RFO prefetches (includes PREFETCHW instruction) that accounts for data responses from DRAM Far.",
         "Offcore": "1"
     },
     {
         "EventCode": "0xB7",
-        "MSRValue": "0x0080800020 ",
+        "MSRValue": "0x0080800020",
         "Counter": "0,1",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.PF_L2_RFO.DDR_NEAR",
@@ -647,18 +647,18 @@
     },
     {
         "EventCode": "0xB7",
-        "MSRValue": "0x0100400004 ",
+        "MSRValue": "0x0100400004",
         "Counter": "0,1",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.MCDRAM_FAR",
         "MSRIndex": "0x1a6,0x1a7",
         "SampleAfterValue": "100007",
-        "BriefDescription": "Counts demand code reads and prefetch code reads that accounts for data responses from MCDRAM Far or Other tile L2 hit far. ",
+        "BriefDescription": "Counts demand code reads and prefetch code reads that accounts for data responses from MCDRAM Far or Other tile L2 hit far.",
         "Offcore": "1"
     },
     {
         "EventCode": "0xB7",
-        "MSRValue": "0x0080200004 ",
+        "MSRValue": "0x0080200004",
         "Counter": "0,1",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.MCDRAM_NEAR",
@@ -669,18 +669,18 @@
     },
     {
         "EventCode": "0xB7",
-        "MSRValue": "0x0101000004 ",
+        "MSRValue": "0x0101000004",
         "Counter": "0,1",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.DDR_FAR",
         "MSRIndex": "0x1a6,0x1a7",
         "SampleAfterValue": "100007",
-        "BriefDescription": "Counts demand code reads and prefetch code reads that accounts for data responses from DRAM Far. ",
+        "BriefDescription": "Counts demand code reads and prefetch code reads that accounts for data responses from DRAM Far.",
         "Offcore": "1"
     },
     {
         "EventCode": "0xB7",
-        "MSRValue": "0x0080800004 ",
+        "MSRValue": "0x0080800004",
         "Counter": "0,1",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.DDR_NEAR",
@@ -691,18 +691,18 @@
     },
     {
         "EventCode": "0xB7",
-        "MSRValue": "0x0100400002 ",
+        "MSRValue": "0x0100400002",
         "Counter": "0,1",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.MCDRAM_FAR",
         "MSRIndex": "0x1a6,0x1a7",
         "SampleAfterValue": "100007",
-        "BriefDescription": "Counts Demand cacheable data writes that accounts for data responses from MCDRAM Far or Other tile L2 hit far. ",
+        "BriefDescription": "Counts Demand cacheable data writes that accounts for data responses from MCDRAM Far or Other tile L2 hit far.",
         "Offcore": "1"
     },
     {
         "EventCode": "0xB7",
-        "MSRValue": "0x0080200002 ",
+        "MSRValue": "0x0080200002",
         "Counter": "0,1",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.MCDRAM_NEAR",
@@ -713,18 +713,18 @@
     },
     {
         "EventCode": "0xB7",
-        "MSRValue": "0x0101000002 ",
+        "MSRValue": "0x0101000002",
         "Counter": "0,1",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.DDR_FAR",
         "MSRIndex": "0x1a6,0x1a7",
         "SampleAfterValue": "100007",
-        "BriefDescription": "Counts Demand cacheable data writes that accounts for data responses from DRAM Far. ",
+        "BriefDescription": "Counts Demand cacheable data writes that accounts for data responses from DRAM Far.",
         "Offcore": "1"
     },
     {
         "EventCode": "0xB7",
-        "MSRValue": "0x0080800002 ",
+        "MSRValue": "0x0080800002",
         "Counter": "0,1",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.DDR_NEAR",
@@ -735,18 +735,18 @@
     },
     {
         "EventCode": "0xB7",
-        "MSRValue": "0x0100400001 ",
+        "MSRValue": "0x0100400001",
         "Counter": "0,1",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.MCDRAM_FAR",
         "MSRIndex": "0x1a6,0x1a7",
         "SampleAfterValue": "100007",
-        "BriefDescription": "Counts demand cacheable data and L1 prefetch data reads that accounts for data responses from MCDRAM Far or Other tile L2 hit far. ",
+        "BriefDescription": "Counts demand cacheable data and L1 prefetch data reads that accounts for data responses from MCDRAM Far or Other tile L2 hit far.",
         "Offcore": "1"
     },
     {
         "EventCode": "0xB7",
-        "MSRValue": "0x0080200001 ",
+        "MSRValue": "0x0080200001",
         "Counter": "0,1",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.MCDRAM_NEAR",
@@ -757,18 +757,18 @@
     },
     {
         "EventCode": "0xB7",
-        "MSRValue": "0x0101000001 ",
+        "MSRValue": "0x0101000001",
         "Counter": "0,1",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.DDR_FAR",
         "MSRIndex": "0x1a6,0x1a7",
         "SampleAfterValue": "100007",
-        "BriefDescription": "Counts demand cacheable data and L1 prefetch data reads that accounts for data responses from DRAM Far. ",
+        "BriefDescription": "Counts demand cacheable data and L1 prefetch data reads that accounts for data responses from DRAM Far.",
         "Offcore": "1"
     },
     {
         "EventCode": "0xB7",
-        "MSRValue": "0x0080800001 ",
+        "MSRValue": "0x0080800001",
         "Counter": "0,1",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.DDR_NEAR",
@@ -779,7 +779,7 @@
     },
     {
         "EventCode": "0xB7",
-        "MSRValue": "0x0180600001 ",
+        "MSRValue": "0x0180600001",
         "Counter": "0,1",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.MCDRAM",
@@ -790,7 +790,7 @@
     },
     {
         "EventCode": "0xB7",
-        "MSRValue": "0x0180600002 ",
+        "MSRValue": "0x0180600002",
         "Counter": "0,1",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.MCDRAM",
@@ -801,7 +801,7 @@
     },
     {
         "EventCode": "0xB7",
-        "MSRValue": "0x0180600004 ",
+        "MSRValue": "0x0180600004",
         "Counter": "0,1",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.MCDRAM",
@@ -812,7 +812,7 @@
     },
     {
         "EventCode": "0xB7",
-        "MSRValue": "0x0180600020 ",
+        "MSRValue": "0x0180600020",
         "Counter": "0,1",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.PF_L2_RFO.MCDRAM",
@@ -823,7 +823,7 @@
     },
     {
         "EventCode": "0xB7",
-        "MSRValue": "0x0180600080 ",
+        "MSRValue": "0x0180600080",
         "Counter": "0,1",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.PARTIAL_READS.MCDRAM",
@@ -834,7 +834,7 @@
     },
     {
         "EventCode": "0xB7",
-        "MSRValue": "0x0180600100 ",
+        "MSRValue": "0x0180600100",
         "Counter": "0,1",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.PARTIAL_WRITES.MCDRAM",
@@ -845,7 +845,7 @@
     },
     {
         "EventCode": "0xB7",
-        "MSRValue": "0x0180600200 ",
+        "MSRValue": "0x0180600200",
         "Counter": "0,1",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.UC_CODE_READS.MCDRAM",
@@ -856,7 +856,7 @@
     },
     {
         "EventCode": "0xB7",
-        "MSRValue": "0x0180600400 ",
+        "MSRValue": "0x0180600400",
         "Counter": "0,1",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.BUS_LOCKS.MCDRAM",
@@ -867,7 +867,7 @@
     },
     {
         "EventCode": "0xB7",
-        "MSRValue": "0x0180601000 ",
+        "MSRValue": "0x0180601000",
         "Counter": "0,1",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.PF_SOFTWARE.MCDRAM",
@@ -878,7 +878,7 @@
     },
     {
         "EventCode": "0xB7",
-        "MSRValue": "0x0180608000 ",
+        "MSRValue": "0x0180608000",
         "Counter": "0,1",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.ANY_REQUEST.MCDRAM",
@@ -889,7 +889,7 @@
     },
     {
         "EventCode": "0xB7",
-        "MSRValue": "0x0180603091 ",
+        "MSRValue": "0x0180603091",
         "Counter": "0,1",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.ANY_DATA_RD.MCDRAM",
@@ -900,7 +900,7 @@
     },
     {
         "EventCode": "0xB7",
-        "MSRValue": "0x0180600022 ",
+        "MSRValue": "0x0180600022",
         "Counter": "0,1",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.ANY_RFO.MCDRAM",
@@ -911,7 +911,7 @@
     },
     {
         "EventCode": "0xB7",
-        "MSRValue": "0x0180600044 ",
+        "MSRValue": "0x0180600044",
         "Counter": "0,1",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.ANY_CODE_RD.MCDRAM",
@@ -922,7 +922,7 @@
     },
     {
         "EventCode": "0xB7",
-        "MSRValue": "0x01806032f7 ",
+        "MSRValue": "0x01806032f7",
         "Counter": "0,1",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.ANY_READ.MCDRAM",
@@ -933,7 +933,7 @@
     },
     {
         "EventCode": "0xB7",
-        "MSRValue": "0x0180600070 ",
+        "MSRValue": "0x0180600070",
         "Counter": "0,1",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.ANY_PF_L2.MCDRAM",
@@ -944,7 +944,7 @@
     },
     {
         "EventCode": "0xB7",
-        "MSRValue": "0x0181800001 ",
+        "MSRValue": "0x0181800001",
         "Counter": "0,1",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.DDR",
@@ -955,7 +955,7 @@
     },
     {
         "EventCode": "0xB7",
-        "MSRValue": "0x0181800002 ",
+        "MSRValue": "0x0181800002",
         "Counter": "0,1",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.DDR",
@@ -966,7 +966,7 @@
     },
     {
         "EventCode": "0xB7",
-        "MSRValue": "0x0181800004 ",
+        "MSRValue": "0x0181800004",
         "Counter": "0,1",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.DDR",
@@ -977,7 +977,7 @@
     },
     {
         "EventCode": "0xB7",
-        "MSRValue": "0x0181800020 ",
+        "MSRValue": "0x0181800020",
         "Counter": "0,1",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.PF_L2_RFO.DDR",
@@ -988,7 +988,7 @@
     },
     {
         "EventCode": "0xB7",
-        "MSRValue": "0x0181800040 ",
+        "MSRValue": "0x0181800040",
         "Counter": "0,1",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.PF_L2_CODE_RD.DDR",
@@ -999,7 +999,7 @@
     },
     {
         "EventCode": "0xB7",
-        "MSRValue": "0x0181800080 ",
+        "MSRValue": "0x0181800080",
         "Counter": "0,1",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.PARTIAL_READS.DDR",
@@ -1010,7 +1010,7 @@
     },
     {
         "EventCode": "0xB7",
-        "MSRValue": "0x0181800200 ",
+        "MSRValue": "0x0181800200",
         "Counter": "0,1",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.UC_CODE_READS.DDR",
@@ -1021,7 +1021,7 @@
     },
     {
         "EventCode": "0xB7",
-        "MSRValue": "0x0181800400 ",
+        "MSRValue": "0x0181800400",
         "Counter": "0,1",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.BUS_LOCKS.DDR",
@@ -1032,7 +1032,7 @@
     },
     {
         "EventCode": "0xB7",
-        "MSRValue": "0x0181801000 ",
+        "MSRValue": "0x0181801000",
         "Counter": "0,1",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.PF_SOFTWARE.DDR",
@@ -1043,7 +1043,7 @@
     },
     {
         "EventCode": "0xB7",
-        "MSRValue": "0x0181802000 ",
+        "MSRValue": "0x0181802000",
         "Counter": "0,1",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.PF_L1_DATA_RD.DDR",
@@ -1054,7 +1054,7 @@
     },
     {
         "EventCode": "0xB7",
-        "MSRValue": "0x0181808000 ",
+        "MSRValue": "0x0181808000",
         "Counter": "0,1",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.ANY_REQUEST.DDR",
@@ -1065,7 +1065,7 @@
     },
     {
         "EventCode": "0xB7",
-        "MSRValue": "0x0181803091 ",
+        "MSRValue": "0x0181803091",
         "Counter": "0,1",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.ANY_DATA_RD.DDR",
@@ -1076,7 +1076,7 @@
     },
     {
         "EventCode": "0xB7",
-        "MSRValue": "0x0181800022 ",
+        "MSRValue": "0x0181800022",
         "Counter": "0,1",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.ANY_RFO.DDR",
@@ -1087,7 +1087,7 @@
     },
     {
         "EventCode": "0xB7",
-        "MSRValue": "0x0181800044 ",
+        "MSRValue": "0x0181800044",
         "Counter": "0,1",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.ANY_CODE_RD.DDR",
@@ -1098,7 +1098,7 @@
     },
     {
         "EventCode": "0xB7",
-        "MSRValue": "0x01818032f7 ",
+        "MSRValue": "0x01818032f7",
         "Counter": "0,1",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.ANY_READ.DDR",
diff --git a/tools/perf/pmu-events/arch/x86/knightslanding/pipeline.json b/tools/perf/pmu-events/arch/x86/knightslanding/pipeline.json
index bb5494cfb5ae..92e4ef2e22c6 100644
--- a/tools/perf/pmu-events/arch/x86/knightslanding/pipeline.json
+++ b/tools/perf/pmu-events/arch/x86/knightslanding/pipeline.json
@@ -144,7 +144,7 @@
         "BriefDescription": "Counts the number of micro-ops retired that are from the complex flows issued by the micro-sequencer (MS)."
     },
     {
-        "PublicDescription": "This event counts the number of micro-ops (uops) retired. The processor decodes complex macro instructions into a sequence of simpler uops. Most instructions are composed of one or two uops. Some instructions are decoded into longer sequences such as repeat instructions, floating point transcendental instructions, and assists. ",
+        "PublicDescription": "This event counts the number of micro-ops (uops) retired. The processor decodes complex macro instructions into a sequence of simpler uops. Most instructions are composed of one or two uops. Some instructions are decoded into longer sequences such as repeat instructions, floating point transcendental instructions, and assists.",
         "EventCode": "0xC2",
         "Counter": "0,1",
         "UMask": "0x10",
@@ -218,7 +218,7 @@
         "UMask": "0x20",
         "EventName": "NO_ALLOC_CYCLES.RAT_STALL",
         "SampleAfterValue": "200003",
-        "BriefDescription": "Counts the number of core cycles when no micro-ops are allocated and a RATstall (caused by reservation station full) is asserted.  "
+        "BriefDescription": "Counts the number of core cycles when no micro-ops are allocated and a RATstall (caused by reservation station full) is asserted."
     },
     {
         "PublicDescription": "This event counts the number of core cycles when no uops are allocated, the instruction queue is empty and the alloc pipe is stalled waiting for instructions to be fetched.",
@@ -251,7 +251,7 @@
         "UMask": "0x1f",
         "EventName": "RS_FULL_STALL.ALL",
         "SampleAfterValue": "200003",
-        "BriefDescription": "Counts the total number of core cycles the Alloc pipeline is stalled when any one of the reservation stations is full. "
+        "BriefDescription": "Counts the total number of core cycles the Alloc pipeline is stalled when any one of the reservation stations is full."
     },
     {
         "EventCode": "0xC0",
@@ -268,11 +268,10 @@
         "UMask": "0x1",
         "EventName": "CYCLES_DIV_BUSY.ALL",
         "SampleAfterValue": "2000003",
-        "BriefDescription": "Cycles the number of core cycles when divider is busy.  Does not imply a stall waiting for the divider.  "
+        "BriefDescription": "Cycles the number of core cycles when divider is busy.  Does not imply a stall waiting for the divider."
     },
     {
         "PublicDescription": "This event counts the number of instructions that retire.  For instructions that consist of multiple micro-ops, this event counts exactly once, as the last micro-op of the instruction retires.  The event continues counting while instructions retire, including during interrupt service routines caused by hardware interrupts, faults or traps.",
-        "EventCode": "0x00",
         "Counter": "Fixed counter 1",
         "UMask": "0x1",
         "EventName": "INST_RETIRED.ANY",
@@ -296,8 +295,7 @@
         "BriefDescription": "Counts the number of unhalted reference clock cycles"
     },
     {
-        "PublicDescription": "This event counts the number of core cycles while the thread is not in a halt state. The thread enters the halt state when it is running the HLT instruction. This event is a component in many key event ratios. The core frequency may change from time to time due to transitions associated with Enhanced Intel SpeedStep Technology or TM2. For this reason this event may have a changing ratio with regards to time. When the core frequency is constant, this event can approximate elapsed time while the core was not in the halt state. It is counted on a dedicated fixed counter\r\n",
-        "EventCode": "0x00",
+        "PublicDescription": "This event counts the number of core cycles while the thread is not in a halt state. The thread enters the halt state when it is running the HLT instruction. This event is a component in many key event ratios. The core frequency may change from time to time due to transitions associated with Enhanced Intel SpeedStep Technology or TM2. For this reason this event may have a changing ratio with regards to time. When the core frequency is constant, this event can approximate elapsed time while the core was not in the halt state. It is counted on a dedicated fixed counter",
         "Counter": "Fixed counter 2",
         "UMask": "0x2",
         "EventName": "CPU_CLK_UNHALTED.THREAD",
@@ -305,7 +303,6 @@
         "BriefDescription": "Fixed Counter: Counts the number of unhalted core clock cycles"
     },
     {
-        "EventCode": "0x00",
         "Counter": "Fixed counter 3",
         "UMask": "0x3",
         "EventName": "CPU_CLK_UNHALTED.REF_TSC",
@@ -343,7 +340,7 @@
         "UMask": "0x1",
         "EventName": "RECYCLEQ.LD_BLOCK_ST_FORWARD",
         "SampleAfterValue": "200003",
-        "BriefDescription": "Counts the number of occurences a retired load gets blocked because its address partially overlaps with a store ",
+        "BriefDescription": "Counts the number of occurences a retired load gets blocked because its address partially overlaps with a store",
         "Data_LA": "1"
     },
     {
diff --git a/tools/perf/pmu-events/arch/x86/knightslanding/virtual-memory.json b/tools/perf/pmu-events/arch/x86/knightslanding/virtual-memory.json
index f31594507f8c..9e493977771f 100644
--- a/tools/perf/pmu-events/arch/x86/knightslanding/virtual-memory.json
+++ b/tools/perf/pmu-events/arch/x86/knightslanding/virtual-memory.json
@@ -36,7 +36,7 @@
         "EdgeDetect": "1"
     },
     {
-        "PublicDescription": "This event counts every cycle when an I-side (walks due to an instruction fetch) page walk is in progress. ",
+        "PublicDescription": "This event counts every cycle when an I-side (walks due to an instruction fetch) page walk is in progress.",
         "EventCode": "0x05",
         "Counter": "0,1",
         "UMask": "0x2",
diff --git a/tools/perf/pmu-events/arch/x86/sandybridge/cache.json b/tools/perf/pmu-events/arch/x86/sandybridge/cache.json
index 16b04a20bc12..bb79e89c2049 100644
--- a/tools/perf/pmu-events/arch/x86/sandybridge/cache.json
+++ b/tools/perf/pmu-events/arch/x86/sandybridge/cache.json
@@ -1,207 +1,200 @@
 [
     {
-        "PEBS": "1",
-        "EventCode": "0xD0",
+        "EventCode": "0x24",
         "Counter": "0,1,2,3",
-        "UMask": "0x11",
-        "EventName": "MEM_UOPS_RETIRED.STLB_MISS_LOADS",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "Retired load uops that miss the STLB.",
-        "CounterHTOff": "0,1,2,3"
+        "UMask": "0x1",
+        "EventName": "L2_RQSTS.DEMAND_DATA_RD_HIT",
+        "SampleAfterValue": "200003",
+        "BriefDescription": "Demand Data Read requests that hit L2 cache.",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "PEBS": "1",
-        "EventCode": "0xD0",
+        "EventCode": "0x24",
         "Counter": "0,1,2,3",
-        "UMask": "0x12",
-        "EventName": "MEM_UOPS_RETIRED.STLB_MISS_STORES",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "Retired store uops that miss the STLB.",
-        "CounterHTOff": "0,1,2,3"
+        "UMask": "0x3",
+        "EventName": "L2_RQSTS.ALL_DEMAND_DATA_RD",
+        "SampleAfterValue": "200003",
+        "BriefDescription": "Demand Data Read requests.",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "PEBS": "1",
-        "EventCode": "0xD0",
+        "EventCode": "0x24",
         "Counter": "0,1,2,3",
-        "UMask": "0x21",
-        "EventName": "MEM_UOPS_RETIRED.LOCK_LOADS",
-        "SampleAfterValue": "100007",
-        "BriefDescription": "Retired load uops with locked access.",
-        "CounterHTOff": "0,1,2,3"
+        "UMask": "0x4",
+        "EventName": "L2_RQSTS.RFO_HIT",
+        "SampleAfterValue": "200003",
+        "BriefDescription": "RFO requests that hit L2 cache.",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "PEBS": "1",
-        "PublicDescription": "This event counts line-split load uops retired to the architected path. A line split is across 64B cache-line which includes a page split (4K).",
-        "EventCode": "0xD0",
+        "EventCode": "0x24",
         "Counter": "0,1,2,3",
-        "UMask": "0x41",
-        "EventName": "MEM_UOPS_RETIRED.SPLIT_LOADS",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "Retired load uops that split across a cacheline boundary.",
-        "CounterHTOff": "0,1,2,3"
+        "UMask": "0x8",
+        "EventName": "L2_RQSTS.RFO_MISS",
+        "SampleAfterValue": "200003",
+        "BriefDescription": "RFO requests that miss L2 cache.",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "PEBS": "1",
-        "PublicDescription": "This event counts line-split store uops retired to the architected path. A line split is across 64B cache-line which includes a page split (4K).",
-        "EventCode": "0xD0",
+        "EventCode": "0x24",
         "Counter": "0,1,2,3",
-        "UMask": "0x42",
-        "EventName": "MEM_UOPS_RETIRED.SPLIT_STORES",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "Retired store uops that split across a cacheline boundary.",
-        "CounterHTOff": "0,1,2,3"
+        "UMask": "0xc",
+        "EventName": "L2_RQSTS.ALL_RFO",
+        "SampleAfterValue": "200003",
+        "BriefDescription": "RFO requests to L2 cache.",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "PEBS": "1",
-        "PublicDescription": "This event counts the number of load uops retired",
-        "EventCode": "0xD0",
+        "EventCode": "0x24",
         "Counter": "0,1,2,3",
-        "UMask": "0x81",
-        "EventName": "MEM_UOPS_RETIRED.ALL_LOADS",
-        "SampleAfterValue": "2000003",
-        "BriefDescription": "All retired load uops.",
-        "CounterHTOff": "0,1,2,3"
+        "UMask": "0x10",
+        "EventName": "L2_RQSTS.CODE_RD_HIT",
+        "SampleAfterValue": "200003",
+        "BriefDescription": "L2 cache hits when fetching instructions, code reads.",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "PEBS": "1",
-        "PublicDescription": "This event counts the number of store uops retired.",
-        "EventCode": "0xD0",
+        "EventCode": "0x24",
         "Counter": "0,1,2,3",
-        "UMask": "0x82",
-        "EventName": "MEM_UOPS_RETIRED.ALL_STORES",
-        "SampleAfterValue": "2000003",
-        "BriefDescription": "All retired store uops.",
-        "CounterHTOff": "0,1,2,3"
+        "UMask": "0x20",
+        "EventName": "L2_RQSTS.CODE_RD_MISS",
+        "SampleAfterValue": "200003",
+        "BriefDescription": "L2 cache misses when fetching instructions.",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "PEBS": "1",
-        "EventCode": "0xD1",
+        "EventCode": "0x24",
         "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "MEM_LOAD_UOPS_RETIRED.L1_HIT",
-        "SampleAfterValue": "2000003",
-        "BriefDescription": "Retired load uops with L1 cache hits as data sources.",
-        "CounterHTOff": "0,1,2,3"
+        "UMask": "0x30",
+        "EventName": "L2_RQSTS.ALL_CODE_RD",
+        "SampleAfterValue": "200003",
+        "BriefDescription": "L2 code requests.",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "PEBS": "1",
-        "EventCode": "0xD1",
+        "EventCode": "0x24",
         "Counter": "0,1,2,3",
-        "UMask": "0x2",
-        "EventName": "MEM_LOAD_UOPS_RETIRED.L2_HIT",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "Retired load uops with L2 cache hits as data sources.",
-        "CounterHTOff": "0,1,2,3"
+        "UMask": "0x40",
+        "EventName": "L2_RQSTS.PF_HIT",
+        "SampleAfterValue": "200003",
+        "BriefDescription": "Requests from the L2 hardware prefetchers that hit L2 cache.",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "PEBS": "1",
-        "PublicDescription": "This event counts retired load uops that hit in the last-level (L3) cache without snoops required.",
-        "EventCode": "0xD1",
+        "EventCode": "0x24",
         "Counter": "0,1,2,3",
-        "UMask": "0x4",
-        "EventName": "MEM_LOAD_UOPS_RETIRED.LLC_HIT",
-        "SampleAfterValue": "50021",
-        "BriefDescription": "Retired load uops which data sources were data hits in LLC without snoops required.",
-        "CounterHTOff": "0,1,2,3"
+        "UMask": "0x80",
+        "EventName": "L2_RQSTS.PF_MISS",
+        "SampleAfterValue": "200003",
+        "BriefDescription": "Requests from the L2 hardware prefetchers that miss L2 cache.",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "PEBS": "1",
-        "EventCode": "0xD1",
+        "EventCode": "0x24",
         "Counter": "0,1,2,3",
-        "UMask": "0x40",
-        "EventName": "MEM_LOAD_UOPS_RETIRED.HIT_LFB",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "Retired load uops which data sources were load uops missed L1 but hit FB due to preceding miss to the same cache line with data not ready.",
-        "CounterHTOff": "0,1,2,3"
+        "UMask": "0xc0",
+        "EventName": "L2_RQSTS.ALL_PF",
+        "SampleAfterValue": "200003",
+        "BriefDescription": "Requests from L2 hardware prefetchers.",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "PEBS": "1",
-        "EventCode": "0xD2",
+        "EventCode": "0x27",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
-        "EventName": "MEM_LOAD_UOPS_LLC_HIT_RETIRED.XSNP_MISS",
-        "SampleAfterValue": "20011",
-        "BriefDescription": "Retired load uops which data sources were LLC hit and cross-core snoop missed in on-pkg core cache.",
-        "CounterHTOff": "0,1,2,3"
-    },
-    {
-        "PEBS": "1",
-        "PublicDescription": "This event counts retired load uops that hit in the last-level cache (L3) and were found in a non-modified state in a neighboring core's private cache (same package).  Since the last level cache is inclusive, hits to the L3 may require snooping the private L2 caches of any cores on the same socket that have the line.  In this case, a snoop was required, and another L2 had the line in a non-modified state.",
-        "EventCode": "0xD2",
-        "Counter": "0,1,2,3",
-        "UMask": "0x2",
-        "EventName": "MEM_LOAD_UOPS_LLC_HIT_RETIRED.XSNP_HIT",
-        "SampleAfterValue": "20011",
-        "BriefDescription": "Retired load uops which data sources were LLC and cross-core snoop hits in on-pkg core cache.",
-        "CounterHTOff": "0,1,2,3"
+        "EventName": "L2_STORE_LOCK_RQSTS.MISS",
+        "SampleAfterValue": "200003",
+        "BriefDescription": "RFOs that miss cache lines.",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "PEBS": "1",
-        "PublicDescription": "This event counts retired load uops that hit in the last-level cache (L3) and were found in a non-modified state in a neighboring core's private cache (same package).  Since the last level cache is inclusive, hits to the L3 may require snooping the private L2 caches of any cores on the same socket that have the line.  In this case, a snoop was required, and another L2 had the line in a modified state, so the line had to be invalidated in that L2 cache and transferred to the requesting L2.",
-        "EventCode": "0xD2",
+        "EventCode": "0x27",
         "Counter": "0,1,2,3",
         "UMask": "0x4",
-        "EventName": "MEM_LOAD_UOPS_LLC_HIT_RETIRED.XSNP_HITM",
-        "SampleAfterValue": "20011",
-        "BriefDescription": "Retired load uops which data sources were HitM responses from shared LLC.",
-        "CounterHTOff": "0,1,2,3"
+        "EventName": "L2_STORE_LOCK_RQSTS.HIT_E",
+        "SampleAfterValue": "200003",
+        "BriefDescription": "RFOs that hit cache lines in E state.",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "PEBS": "1",
-        "EventCode": "0xD2",
+        "EventCode": "0x27",
         "Counter": "0,1,2,3",
         "UMask": "0x8",
-        "EventName": "MEM_LOAD_UOPS_LLC_HIT_RETIRED.XSNP_NONE",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "Retired load uops which data sources were hits in LLC without snoops required.",
-        "CounterHTOff": "0,1,2,3"
+        "EventName": "L2_STORE_LOCK_RQSTS.HIT_M",
+        "SampleAfterValue": "200003",
+        "BriefDescription": "RFOs that hit cache lines in M state.",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "PEBS": "1",
-        "PublicDescription": "This event counts retired demand loads that missed the  last-level (L3) cache. This means that the load is usually satisfied from memory in a client system or possibly from the remote socket in a server. Demand loads are non speculative load uops.",
-        "EventCode": "0xD4",
+        "EventCode": "0x27",
         "Counter": "0,1,2,3",
-        "UMask": "0x2",
-        "EventName": "MEM_LOAD_UOPS_MISC_RETIRED.LLC_MISS",
-        "SampleAfterValue": "100007",
-        "BriefDescription": "Retired load uops with unknown information as data source in cache serviced the load.",
-        "CounterHTOff": "0,1,2,3"
+        "UMask": "0xf",
+        "EventName": "L2_STORE_LOCK_RQSTS.ALL",
+        "SampleAfterValue": "200003",
+        "BriefDescription": "RFOs that access cache lines in any state.",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "PublicDescription": "This event counts L1D data line replacements.  Replacements occur when a new line is brought into the cache, causing eviction of a line loaded earlier.  ",
-        "EventCode": "0x51",
+        "EventCode": "0x28",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
-        "EventName": "L1D.REPLACEMENT",
-        "SampleAfterValue": "2000003",
-        "BriefDescription": "L1D data line replacements.",
+        "EventName": "L2_L1D_WB_RQSTS.MISS",
+        "SampleAfterValue": "200003",
+        "BriefDescription": "Count the number of modified Lines evicted from L1 and missed L2. (Non-rejected WBs from the DCU.).",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "EventCode": "0x51",
+        "EventCode": "0x28",
         "Counter": "0,1,2,3",
         "UMask": "0x2",
-        "EventName": "L1D.ALLOCATED_IN_M",
-        "SampleAfterValue": "2000003",
-        "BriefDescription": "Allocated L1D data cache lines in M state.",
+        "EventName": "L2_L1D_WB_RQSTS.HIT_S",
+        "SampleAfterValue": "200003",
+        "BriefDescription": "Not rejected writebacks from L1D to L2 cache lines in S state.",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "EventCode": "0x51",
+        "EventCode": "0x28",
         "Counter": "0,1,2,3",
         "UMask": "0x4",
-        "EventName": "L1D.EVICTION",
-        "SampleAfterValue": "2000003",
-        "BriefDescription": "L1D data cache lines in M state evicted due to replacement.",
+        "EventName": "L2_L1D_WB_RQSTS.HIT_E",
+        "SampleAfterValue": "200003",
+        "BriefDescription": "Not rejected writebacks from L1D to L2 cache lines in E state.",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "EventCode": "0x51",
+        "EventCode": "0x28",
         "Counter": "0,1,2,3",
         "UMask": "0x8",
-        "EventName": "L1D.ALL_M_REPLACEMENT",
-        "SampleAfterValue": "2000003",
-        "BriefDescription": "Cache lines in M state evicted out of L1D due to Snoop HitM or dirty line replacement.",
+        "EventName": "L2_L1D_WB_RQSTS.HIT_M",
+        "SampleAfterValue": "200003",
+        "BriefDescription": "Not rejected writebacks from L1D to L2 cache lines in M state.",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0x28",
+        "Counter": "0,1,2,3",
+        "UMask": "0xf",
+        "EventName": "L2_L1D_WB_RQSTS.ALL",
+        "SampleAfterValue": "200003",
+        "BriefDescription": "Not rejected writebacks from L1D to L2 cache lines in any state.",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0x2E",
+        "Counter": "0,1,2,3",
+        "UMask": "0x41",
+        "EventName": "LONGEST_LAT_CACHE.MISS",
+        "SampleAfterValue": "100003",
+        "BriefDescription": "Core-originated cacheable demand requests missed LLC.",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0x2E",
+        "Counter": "0,1,2,3",
+        "UMask": "0x4f",
+        "EventName": "LONGEST_LAT_CACHE.REFERENCE",
+        "SampleAfterValue": "100003",
+        "BriefDescription": "Core-originated cacheable demand requests that refer to LLC.",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
@@ -224,12 +217,61 @@
         "CounterHTOff": "2"
     },
     {
-        "EventCode": "0x63",
+        "EventCode": "0x48",
+        "Counter": "2",
+        "UMask": "0x1",
+        "AnyThread": "1",
+        "EventName": "L1D_PEND_MISS.PENDING_CYCLES_ANY",
+        "SampleAfterValue": "2000003",
+        "BriefDescription": "Cycles with L1D load Misses outstanding from any thread on physical core.",
+        "CounterMask": "1",
+        "CounterHTOff": "2"
+    },
+    {
+        "EventCode": "0x48",
         "Counter": "0,1,2,3",
         "UMask": "0x2",
-        "EventName": "LOCK_CYCLES.CACHE_LOCK_DURATION",
+        "EventName": "L1D_PEND_MISS.FB_FULL",
         "SampleAfterValue": "2000003",
-        "BriefDescription": "Cycles when L1D is locked.",
+        "BriefDescription": "Cycles a demand request was blocked due to Fill Buffers inavailability.",
+        "CounterMask": "1",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "PublicDescription": "This event counts L1D data line replacements.  Replacements occur when a new line is brought into the cache, causing eviction of a line loaded earlier.",
+        "EventCode": "0x51",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "EventName": "L1D.REPLACEMENT",
+        "SampleAfterValue": "2000003",
+        "BriefDescription": "L1D data line replacements.",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0x51",
+        "Counter": "0,1,2,3",
+        "UMask": "0x2",
+        "EventName": "L1D.ALLOCATED_IN_M",
+        "SampleAfterValue": "2000003",
+        "BriefDescription": "Allocated L1D data cache lines in M state.",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0x51",
+        "Counter": "0,1,2,3",
+        "UMask": "0x4",
+        "EventName": "L1D.EVICTION",
+        "SampleAfterValue": "2000003",
+        "BriefDescription": "L1D data cache lines in M state evicted due to replacement.",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0x51",
+        "Counter": "0,1,2,3",
+        "UMask": "0x8",
+        "EventName": "L1D.ALL_M_REPLACEMENT",
+        "SampleAfterValue": "2000003",
+        "BriefDescription": "Cache lines in M state evicted out of L1D due to Snoop HitM or dirty line replacement.",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
@@ -254,6 +296,16 @@
     {
         "EventCode": "0x60",
         "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "EventName": "OFFCORE_REQUESTS_OUTSTANDING.DEMAND_DATA_RD_C6",
+        "SampleAfterValue": "2000003",
+        "BriefDescription": "Cycles with at least 6 offcore outstanding Demand Data Read transactions in uncore queue.",
+        "CounterMask": "6",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0x60",
+        "Counter": "0,1,2,3",
         "UMask": "0x4",
         "EventName": "OFFCORE_REQUESTS_OUTSTANDING.DEMAND_RFO",
         "SampleAfterValue": "2000003",
@@ -263,6 +315,16 @@
     {
         "EventCode": "0x60",
         "Counter": "0,1,2,3",
+        "UMask": "0x4",
+        "EventName": "OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DEMAND_RFO",
+        "SampleAfterValue": "2000003",
+        "BriefDescription": "Offcore outstanding demand rfo reads transactions in SuperQueue (SQ), queue to uncore, every cycle.",
+        "CounterMask": "1",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0x60",
+        "Counter": "0,1,2,3",
         "UMask": "0x8",
         "EventName": "OFFCORE_REQUESTS_OUTSTANDING.ALL_DATA_RD",
         "SampleAfterValue": "2000003",
@@ -280,6 +342,15 @@
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
+        "EventCode": "0x63",
+        "Counter": "0,1,2,3",
+        "UMask": "0x2",
+        "EventName": "LOCK_CYCLES.CACHE_LOCK_DURATION",
+        "SampleAfterValue": "2000003",
+        "BriefDescription": "Cycles when L1D is locked.",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
         "EventCode": "0xB0",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
@@ -325,148 +396,182 @@
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "EventCode": "0x24",
+        "EventCode": "0xBF",
         "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "L2_RQSTS.DEMAND_DATA_RD_HIT",
-        "SampleAfterValue": "200003",
-        "BriefDescription": "Demand Data Read requests that hit L2 cache.",
+        "UMask": "0x5",
+        "EventName": "L1D_BLOCKS.BANK_CONFLICT_CYCLES",
+        "SampleAfterValue": "100003",
+        "BriefDescription": "Cycles when dispatched loads are cancelled due to L1D bank conflicts with other load ports.",
+        "CounterMask": "1",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "EventCode": "0x24",
+        "PEBS": "1",
+        "EventCode": "0xD0",
         "Counter": "0,1,2,3",
-        "UMask": "0x4",
-        "EventName": "L2_RQSTS.RFO_HIT",
-        "SampleAfterValue": "200003",
-        "BriefDescription": "RFO requests that hit L2 cache.",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
+        "UMask": "0x11",
+        "EventName": "MEM_UOPS_RETIRED.STLB_MISS_LOADS",
+        "SampleAfterValue": "100003",
+        "BriefDescription": "Retired load uops that miss the STLB. (Precise Event - PEBS).",
+        "CounterHTOff": "0,1,2,3"
     },
     {
-        "EventCode": "0x24",
+        "PEBS": "1",
+        "EventCode": "0xD0",
         "Counter": "0,1,2,3",
-        "UMask": "0x8",
-        "EventName": "L2_RQSTS.RFO_MISS",
-        "SampleAfterValue": "200003",
-        "BriefDescription": "RFO requests that miss L2 cache.",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
+        "UMask": "0x12",
+        "EventName": "MEM_UOPS_RETIRED.STLB_MISS_STORES",
+        "SampleAfterValue": "100003",
+        "BriefDescription": "Retired store uops that miss the STLB. (Precise Event - PEBS).",
+        "CounterHTOff": "0,1,2,3"
     },
     {
-        "EventCode": "0x24",
+        "PEBS": "1",
+        "EventCode": "0xD0",
         "Counter": "0,1,2,3",
-        "UMask": "0x10",
-        "EventName": "L2_RQSTS.CODE_RD_HIT",
-        "SampleAfterValue": "200003",
-        "BriefDescription": "L2 cache hits when fetching instructions, code reads.",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
+        "UMask": "0x21",
+        "EventName": "MEM_UOPS_RETIRED.LOCK_LOADS",
+        "SampleAfterValue": "100007",
+        "BriefDescription": "Retired load uops with locked access. (Precise Event - PEBS).",
+        "CounterHTOff": "0,1,2,3"
     },
     {
-        "EventCode": "0x24",
+        "PEBS": "1",
+        "PublicDescription": "This event counts line-splitted load uops retired to the architected path. A line split is across 64B cache-line which includes a page split (4K). (Precise Event - PEBS)",
+        "EventCode": "0xD0",
         "Counter": "0,1,2,3",
-        "UMask": "0x20",
-        "EventName": "L2_RQSTS.CODE_RD_MISS",
-        "SampleAfterValue": "200003",
-        "BriefDescription": "L2 cache misses when fetching instructions.",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
+        "UMask": "0x41",
+        "EventName": "MEM_UOPS_RETIRED.SPLIT_LOADS",
+        "SampleAfterValue": "100003",
+        "BriefDescription": "Retired load uops that split across a cacheline boundary. (Precise Event - PEBS).",
+        "CounterHTOff": "0,1,2,3"
     },
     {
-        "EventCode": "0x24",
+        "PEBS": "1",
+        "PublicDescription": "This event counts line-splitted store uops retired to the architected path. A line split is across 64B cache-line which includes a page split (4K). (Precise Event - PEBS)",
+        "EventCode": "0xD0",
         "Counter": "0,1,2,3",
-        "UMask": "0x40",
-        "EventName": "L2_RQSTS.PF_HIT",
-        "SampleAfterValue": "200003",
-        "BriefDescription": "Requests from the L2 hardware prefetchers that hit L2 cache.",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
+        "UMask": "0x42",
+        "EventName": "MEM_UOPS_RETIRED.SPLIT_STORES",
+        "SampleAfterValue": "100003",
+        "BriefDescription": "Retired store uops that split across a cacheline boundary. (Precise Event - PEBS).",
+        "CounterHTOff": "0,1,2,3"
     },
     {
-        "EventCode": "0x24",
+        "PEBS": "1",
+        "PublicDescription": "This event counts the number of load uops retired (Precise Event)",
+        "EventCode": "0xD0",
         "Counter": "0,1,2,3",
-        "UMask": "0x80",
-        "EventName": "L2_RQSTS.PF_MISS",
-        "SampleAfterValue": "200003",
-        "BriefDescription": "Requests from the L2 hardware prefetchers that miss L2 cache.",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
+        "UMask": "0x81",
+        "EventName": "MEM_UOPS_RETIRED.ALL_LOADS",
+        "SampleAfterValue": "2000003",
+        "BriefDescription": "All retired load uops. (Precise Event - PEBS).",
+        "CounterHTOff": "0,1,2,3"
     },
     {
-        "EventCode": "0x27",
+        "PEBS": "1",
+        "PublicDescription": "This event counts the number of store uops retired. (Precise Event - PEBS)",
+        "EventCode": "0xD0",
+        "Counter": "0,1,2,3",
+        "UMask": "0x82",
+        "EventName": "MEM_UOPS_RETIRED.ALL_STORES",
+        "SampleAfterValue": "2000003",
+        "BriefDescription": "All retired store uops. (Precise Event - PEBS).",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "PEBS": "1",
+        "EventCode": "0xD1",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
-        "EventName": "L2_STORE_LOCK_RQSTS.MISS",
-        "SampleAfterValue": "200003",
-        "BriefDescription": "RFOs that miss cache lines.",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
+        "EventName": "MEM_LOAD_UOPS_RETIRED.L1_HIT",
+        "SampleAfterValue": "2000003",
+        "BriefDescription": "Retired load uops with L1 cache hits as data sources. (Precise Event - PEBS).",
+        "CounterHTOff": "0,1,2,3"
     },
     {
-        "EventCode": "0x27",
+        "PEBS": "1",
+        "EventCode": "0xD1",
         "Counter": "0,1,2,3",
-        "UMask": "0x4",
-        "EventName": "L2_STORE_LOCK_RQSTS.HIT_E",
-        "SampleAfterValue": "200003",
-        "BriefDescription": "RFOs that hit cache lines in E state.",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
+        "UMask": "0x2",
+        "EventName": "MEM_LOAD_UOPS_RETIRED.L2_HIT",
+        "SampleAfterValue": "100003",
+        "BriefDescription": "Retired load uops with L2 cache hits as data sources. (Precise Event - PEBS).",
+        "CounterHTOff": "0,1,2,3"
     },
     {
-        "EventCode": "0x27",
+        "PEBS": "1",
+        "PublicDescription": "This event counts retired load uops that hit in the last-level (L3) cache without snoops required. (Precise Event - PEBS)",
+        "EventCode": "0xD1",
         "Counter": "0,1,2,3",
-        "UMask": "0x8",
-        "EventName": "L2_STORE_LOCK_RQSTS.HIT_M",
-        "SampleAfterValue": "200003",
-        "BriefDescription": "RFOs that hit cache lines in M state.",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
+        "UMask": "0x4",
+        "EventName": "MEM_LOAD_UOPS_RETIRED.LLC_HIT",
+        "SampleAfterValue": "50021",
+        "BriefDescription": "Retired load uops which data sources were data hits in LLC without snoops required. (Precise Event - PEBS).",
+        "CounterHTOff": "0,1,2,3"
     },
     {
-        "EventCode": "0x27",
+        "PEBS": "1",
+        "EventCode": "0xD1",
         "Counter": "0,1,2,3",
-        "UMask": "0xf",
-        "EventName": "L2_STORE_LOCK_RQSTS.ALL",
-        "SampleAfterValue": "200003",
-        "BriefDescription": "RFOs that access cache lines in any state.",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
+        "UMask": "0x40",
+        "EventName": "MEM_LOAD_UOPS_RETIRED.HIT_LFB",
+        "SampleAfterValue": "100003",
+        "BriefDescription": "Retired load uops which data sources were load uops missed L1 but hit FB due to preceding miss to the same cache line with data not ready. (Precise Event - PEBS).",
+        "CounterHTOff": "0,1,2,3"
     },
     {
-        "EventCode": "0x28",
+        "PEBS": "1",
+        "EventCode": "0xD2",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
-        "EventName": "L2_L1D_WB_RQSTS.MISS",
-        "SampleAfterValue": "200003",
-        "BriefDescription": "Count the number of modified Lines evicted from L1 and missed L2. (Non-rejected WBs from the DCU.).",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
+        "EventName": "MEM_LOAD_UOPS_LLC_HIT_RETIRED.XSNP_MISS",
+        "SampleAfterValue": "20011",
+        "BriefDescription": "Retired load uops which data sources were LLC hit and cross-core snoop missed in on-pkg core cache. (Precise Event - PEBS).",
+        "CounterHTOff": "0,1,2,3"
     },
     {
-        "EventCode": "0x28",
+        "PEBS": "1",
+        "PublicDescription": "This event counts retired load uops that hit in the last-level cache (L3) and were found in a non-modified state in a neighboring core's private cache (same package).  Since the last level cache is inclusive, hits to the L3 may require snooping the private L2 caches of any cores on the same socket that have the line.  In this case, a snoop was required, and another L2 had the line in a non-modified state. (Precise Event - PEBS)",
+        "EventCode": "0xD2",
         "Counter": "0,1,2,3",
         "UMask": "0x2",
-        "EventName": "L2_L1D_WB_RQSTS.HIT_S",
-        "SampleAfterValue": "200003",
-        "BriefDescription": "Not rejected writebacks from L1D to L2 cache lines in S state.",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
+        "EventName": "MEM_LOAD_UOPS_LLC_HIT_RETIRED.XSNP_HIT",
+        "SampleAfterValue": "20011",
+        "BriefDescription": "Retired load uops which data sources were LLC and cross-core snoop hits in on-pkg core cache. (Precise Event - PEBS).",
+        "CounterHTOff": "0,1,2,3"
     },
     {
-        "EventCode": "0x28",
+        "PEBS": "1",
+        "PublicDescription": "This event counts retired load uops that hit in the last-level cache (L3) and were found in a non-modified state in a neighboring core's private cache (same package).  Since the last level cache is inclusive, hits to the L3 may require snooping the private L2 caches of any cores on the same socket that have the line.  In this case, a snoop was required, and another L2 had the line in a modified state, so the line had to be invalidated in that L2 cache and transferred to the requesting L2. (Precise Event - PEBS)",
+        "EventCode": "0xD2",
         "Counter": "0,1,2,3",
         "UMask": "0x4",
-        "EventName": "L2_L1D_WB_RQSTS.HIT_E",
-        "SampleAfterValue": "200003",
-        "BriefDescription": "Not rejected writebacks from L1D to L2 cache lines in E state.",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
+        "EventName": "MEM_LOAD_UOPS_LLC_HIT_RETIRED.XSNP_HITM",
+        "SampleAfterValue": "20011",
+        "BriefDescription": "Retired load uops which data sources were HitM responses from shared LLC. (Precise Event - PEBS).",
+        "CounterHTOff": "0,1,2,3"
     },
     {
-        "EventCode": "0x28",
+        "PEBS": "1",
+        "EventCode": "0xD2",
         "Counter": "0,1,2,3",
         "UMask": "0x8",
-        "EventName": "L2_L1D_WB_RQSTS.HIT_M",
-        "SampleAfterValue": "200003",
-        "BriefDescription": "Not rejected writebacks from L1D to L2 cache lines in M state.",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
+        "EventName": "MEM_LOAD_UOPS_LLC_HIT_RETIRED.XSNP_NONE",
+        "SampleAfterValue": "100003",
+        "BriefDescription": "Retired load uops which data sources were hits in LLC without snoops required. (Precise Event - PEBS).",
+        "CounterHTOff": "0,1,2,3"
     },
     {
-        "EventCode": "0x28",
+        "PEBS": "1",
+        "PublicDescription": "This event counts retired demand loads that missed the  last-level (L3) cache. This means that the load is usually satisfied from memory in a client system or possibly from the remote socket in a server. Demand loads are non speculative load uops. (Precise Event - PEBS)",
+        "EventCode": "0xD4",
         "Counter": "0,1,2,3",
-        "UMask": "0xf",
-        "EventName": "L2_L1D_WB_RQSTS.ALL",
-        "SampleAfterValue": "200003",
-        "BriefDescription": "Not rejected writebacks from L1D to L2 cache lines in any state.",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
+        "UMask": "0x2",
+        "EventName": "MEM_LOAD_UOPS_MISC_RETIRED.LLC_MISS",
+        "SampleAfterValue": "100007",
+        "BriefDescription": "Retired load uops with unknown information as data source in cache serviced the load. (Precise Event - PEBS).",
+        "CounterHTOff": "0,1,2,3"
     },
     {
         "EventCode": "0xF0",
@@ -623,24 +728,6 @@
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "EventCode": "0x2E",
-        "Counter": "0,1,2,3",
-        "UMask": "0x41",
-        "EventName": "LONGEST_LAT_CACHE.MISS",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "Core-originated cacheable demand requests missed LLC.",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
-    },
-    {
-        "EventCode": "0x2E",
-        "Counter": "0,1,2,3",
-        "UMask": "0x4f",
-        "EventName": "LONGEST_LAT_CACHE.REFERENCE",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "Core-originated cacheable demand requests that refer to LLC.",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
-    },
-    {
         "EventCode": "0xF4",
         "Counter": "0,1,2,3",
         "UMask": "0x10",
@@ -650,93 +737,6 @@
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "EventCode": "0x24",
-        "Counter": "0,1,2,3",
-        "UMask": "0x3",
-        "EventName": "L2_RQSTS.ALL_DEMAND_DATA_RD",
-        "SampleAfterValue": "200003",
-        "BriefDescription": "Demand Data Read requests.",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
-    },
-    {
-        "EventCode": "0x24",
-        "Counter": "0,1,2,3",
-        "UMask": "0xc",
-        "EventName": "L2_RQSTS.ALL_RFO",
-        "SampleAfterValue": "200003",
-        "BriefDescription": "RFO requests to L2 cache.",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
-    },
-    {
-        "EventCode": "0x24",
-        "Counter": "0,1,2,3",
-        "UMask": "0x30",
-        "EventName": "L2_RQSTS.ALL_CODE_RD",
-        "SampleAfterValue": "200003",
-        "BriefDescription": "L2 code requests.",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
-    },
-    {
-        "EventCode": "0x24",
-        "Counter": "0,1,2,3",
-        "UMask": "0xc0",
-        "EventName": "L2_RQSTS.ALL_PF",
-        "SampleAfterValue": "200003",
-        "BriefDescription": "Requests from L2 hardware prefetchers.",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
-    },
-    {
-        "EventCode": "0xBF",
-        "Counter": "0,1,2,3",
-        "UMask": "0x5",
-        "EventName": "L1D_BLOCKS.BANK_CONFLICT_CYCLES",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "Cycles when dispatched loads are cancelled due to L1D bank conflicts with other load ports.",
-        "CounterMask": "1",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
-    },
-    {
-        "EventCode": "0x60",
-        "Counter": "0,1,2,3",
-        "UMask": "0x4",
-        "EventName": "OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DEMAND_RFO",
-        "SampleAfterValue": "2000003",
-        "BriefDescription": "Offcore outstanding demand rfo reads transactions in SuperQueue (SQ), queue to uncore, every cycle.",
-        "CounterMask": "1",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
-    },
-    {
-        "EventCode": "0x60",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "OFFCORE_REQUESTS_OUTSTANDING.DEMAND_DATA_RD_C6",
-        "SampleAfterValue": "2000003",
-        "BriefDescription": "Cycles with at least 6 offcore outstanding Demand Data Read transactions in uncore queue.",
-        "CounterMask": "6",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
-    },
-    {
-        "EventCode": "0x48",
-        "Counter": "2",
-        "UMask": "0x1",
-        "AnyThread": "1",
-        "EventName": "L1D_PEND_MISS.PENDING_CYCLES_ANY",
-        "SampleAfterValue": "2000003",
-        "BriefDescription": "Cycles with L1D load Misses outstanding from any thread on physical core.",
-        "CounterMask": "1",
-        "CounterHTOff": "2"
-    },
-    {
-        "EventCode": "0x48",
-        "Counter": "0,1,2,3",
-        "UMask": "0x2",
-        "EventName": "L1D_PEND_MISS.FB_FULL",
-        "SampleAfterValue": "2000003",
-        "BriefDescription": "Cycles a demand request was blocked due to Fill Buffers inavailability.",
-        "CounterMask": "1",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
-    },
-    {
         "EventCode": "0xB7, 0xBB",
         "MSRValue": "0x10003c0244",
         "Counter": "0,1,2,3",
@@ -1825,7 +1825,7 @@
         "EventName": "OFFCORE_RESPONSE.DATA_IN.ANY_RESPONSE",
         "MSRIndex": "0x1a6,0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": " REQUEST = DATA_INTO_CORE and RESPONSE = ANY_RESPONSE",
+        "BriefDescription": "REQUEST = DATA_INTO_CORE and RESPONSE = ANY_RESPONSE",
         "CounterHTOff": "0,1,2,3"
     },
     {
@@ -1837,7 +1837,7 @@
         "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.LLC_HIT_M.HITM",
         "MSRIndex": "0x1a6,0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": " REQUEST = DEMAND_RFO and RESPONSE = LLC_HIT_M and SNOOP = HITM",
+        "BriefDescription": "REQUEST = DEMAND_RFO and RESPONSE = LLC_HIT_M and SNOOP = HITM",
         "CounterHTOff": "0,1,2,3"
     },
     {
@@ -1849,7 +1849,7 @@
         "EventName": "OFFCORE_RESPONSE.PF_IFETCH.ANY_RESPONSE",
         "MSRIndex": "0x1a6,0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": " REQUEST = PF_RFO and RESPONSE = ANY_RESPONSE",
+        "BriefDescription": "REQUEST = PF_RFO and RESPONSE = ANY_RESPONSE",
         "CounterHTOff": "0,1,2,3"
     },
     {
@@ -1861,7 +1861,7 @@
         "EventName": "OFFCORE_RESPONSE.PF_L_DATA_RD.ANY_RESPONSE",
         "MSRIndex": "0x1a6,0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": " REQUEST = PF_LLC_DATA_RD and RESPONSE = ANY_RESPONSE",
+        "BriefDescription": "REQUEST = PF_LLC_DATA_RD and RESPONSE = ANY_RESPONSE",
         "CounterHTOff": "0,1,2,3"
     },
     {
@@ -1873,7 +1873,7 @@
         "EventName": "OFFCORE_RESPONSE.PF_L_IFETCH.ANY_RESPONSE",
         "MSRIndex": "0x1a6,0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": " REQUEST = PF_LLC_IFETCH and RESPONSE = ANY_RESPONSE",
+        "BriefDescription": "REQUEST = PF_LLC_IFETCH and RESPONSE = ANY_RESPONSE",
         "CounterHTOff": "0,1,2,3"
     }
 ]
\ No newline at end of file
diff --git a/tools/perf/pmu-events/arch/x86/sandybridge/floating-point.json b/tools/perf/pmu-events/arch/x86/sandybridge/floating-point.json
index 982eda48785e..ce26537c7d47 100644
--- a/tools/perf/pmu-events/arch/x86/sandybridge/floating-point.json
+++ b/tools/perf/pmu-events/arch/x86/sandybridge/floating-point.json
@@ -1,68 +1,5 @@
 [
     {
-        "EventCode": "0xC1",
-        "Counter": "0,1,2,3",
-        "UMask": "0x8",
-        "EventName": "OTHER_ASSISTS.AVX_STORE",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "Number of GSSE memory assist for stores. GSSE microcode assist is being invoked whenever the hardware is unable to properly handle GSSE-256b operations.",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
-    },
-    {
-        "EventCode": "0xC1",
-        "Counter": "0,1,2,3",
-        "UMask": "0x10",
-        "EventName": "OTHER_ASSISTS.AVX_TO_SSE",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "Number of transitions from AVX-256 to legacy SSE when penalty applicable.",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
-    },
-    {
-        "EventCode": "0xC1",
-        "Counter": "0,1,2,3",
-        "UMask": "0x20",
-        "EventName": "OTHER_ASSISTS.SSE_TO_AVX",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "Number of transitions from SSE to AVX-256 when penalty applicable.",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
-    },
-    {
-        "EventCode": "0xCA",
-        "Counter": "0,1,2,3",
-        "UMask": "0x2",
-        "EventName": "FP_ASSIST.X87_OUTPUT",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "Number of X87 assists due to output value.",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
-    },
-    {
-        "EventCode": "0xCA",
-        "Counter": "0,1,2,3",
-        "UMask": "0x4",
-        "EventName": "FP_ASSIST.X87_INPUT",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "Number of X87 assists due to input value.",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
-    },
-    {
-        "EventCode": "0xCA",
-        "Counter": "0,1,2,3",
-        "UMask": "0x8",
-        "EventName": "FP_ASSIST.SIMD_OUTPUT",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "Number of SIMD FP assists due to Output values.",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
-    },
-    {
-        "EventCode": "0xCA",
-        "Counter": "0,1,2,3",
-        "UMask": "0x10",
-        "EventName": "FP_ASSIST.SIMD_INPUT",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "Number of SIMD FP assists due to input values.",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
-    },
-    {
         "EventCode": "0x10",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
@@ -126,6 +63,69 @@
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
+        "EventCode": "0xC1",
+        "Counter": "0,1,2,3",
+        "UMask": "0x8",
+        "EventName": "OTHER_ASSISTS.AVX_STORE",
+        "SampleAfterValue": "100003",
+        "BriefDescription": "Number of GSSE memory assist for stores. GSSE microcode assist is being invoked whenever the hardware is unable to properly handle GSSE-256b operations.",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0xC1",
+        "Counter": "0,1,2,3",
+        "UMask": "0x10",
+        "EventName": "OTHER_ASSISTS.AVX_TO_SSE",
+        "SampleAfterValue": "100003",
+        "BriefDescription": "Number of transitions from AVX-256 to legacy SSE when penalty applicable.",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0xC1",
+        "Counter": "0,1,2,3",
+        "UMask": "0x20",
+        "EventName": "OTHER_ASSISTS.SSE_TO_AVX",
+        "SampleAfterValue": "100003",
+        "BriefDescription": "Number of transitions from SSE to AVX-256 when penalty applicable.",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0xCA",
+        "Counter": "0,1,2,3",
+        "UMask": "0x2",
+        "EventName": "FP_ASSIST.X87_OUTPUT",
+        "SampleAfterValue": "100003",
+        "BriefDescription": "Number of X87 assists due to output value.",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0xCA",
+        "Counter": "0,1,2,3",
+        "UMask": "0x4",
+        "EventName": "FP_ASSIST.X87_INPUT",
+        "SampleAfterValue": "100003",
+        "BriefDescription": "Number of X87 assists due to input value.",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0xCA",
+        "Counter": "0,1,2,3",
+        "UMask": "0x8",
+        "EventName": "FP_ASSIST.SIMD_OUTPUT",
+        "SampleAfterValue": "100003",
+        "BriefDescription": "Number of SIMD FP assists due to Output values.",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0xCA",
+        "Counter": "0,1,2,3",
+        "UMask": "0x10",
+        "EventName": "FP_ASSIST.SIMD_INPUT",
+        "SampleAfterValue": "100003",
+        "BriefDescription": "Number of SIMD FP assists due to input values.",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
         "EventCode": "0xCA",
         "Counter": "0,1,2,3",
         "UMask": "0x1e",
diff --git a/tools/perf/pmu-events/arch/x86/sandybridge/frontend.json b/tools/perf/pmu-events/arch/x86/sandybridge/frontend.json
index 1b7b1dd36c68..e58ed14a204c 100644
--- a/tools/perf/pmu-events/arch/x86/sandybridge/frontend.json
+++ b/tools/perf/pmu-events/arch/x86/sandybridge/frontend.json
@@ -1,24 +1,5 @@
 [
     {
-        "EventCode": "0x80",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "ICACHE.HIT",
-        "SampleAfterValue": "2000003",
-        "BriefDescription": "Number of Instruction Cache, Streaming Buffer and Victim Cache Reads. both cacheable and noncacheable, including UC fetches.",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
-    },
-    {
-        "PublicDescription": "This event counts the number of instruction cache, streaming buffer and victim cache misses. Counting includes unchacheable accesses.",
-        "EventCode": "0x80",
-        "Counter": "0,1,2,3",
-        "UMask": "0x2",
-        "EventName": "ICACHE.MISSES",
-        "SampleAfterValue": "200003",
-        "BriefDescription": "Instruction cache, streaming buffer and victim cache misses.",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
-    },
-    {
         "EventCode": "0x79",
         "Counter": "0,1,2,3",
         "UMask": "0x2",
@@ -39,159 +20,201 @@
     {
         "EventCode": "0x79",
         "Counter": "0,1,2,3",
-        "UMask": "0x8",
-        "EventName": "IDQ.DSB_UOPS",
+        "UMask": "0x4",
+        "EventName": "IDQ.MITE_CYCLES",
         "SampleAfterValue": "2000003",
-        "BriefDescription": "Uops delivered to Instruction Decode Queue (IDQ) from the Decode Stream Buffer (DSB) path.",
+        "BriefDescription": "Cycles when uops are being delivered to Instruction Decode Queue (IDQ) from MITE path.",
+        "CounterMask": "1",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
         "EventCode": "0x79",
         "Counter": "0,1,2,3",
-        "UMask": "0x10",
-        "EventName": "IDQ.MS_DSB_UOPS",
+        "UMask": "0x8",
+        "EventName": "IDQ.DSB_UOPS",
         "SampleAfterValue": "2000003",
-        "BriefDescription": "Uops initiated by Decode Stream Buffer (DSB) that are being delivered to Instruction Decode Queue (IDQ) while Microcode Sequenser (MS) is busy.",
+        "BriefDescription": "Uops delivered to Instruction Decode Queue (IDQ) from the Decode Stream Buffer (DSB) path.",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
         "EventCode": "0x79",
         "Counter": "0,1,2,3",
-        "UMask": "0x20",
-        "EventName": "IDQ.MS_MITE_UOPS",
+        "UMask": "0x8",
+        "EventName": "IDQ.DSB_CYCLES",
         "SampleAfterValue": "2000003",
-        "BriefDescription": "Uops initiated by MITE and delivered to Instruction Decode Queue (IDQ) while Microcode Sequenser (MS) is busy.",
+        "BriefDescription": "Cycles when uops are being delivered to Instruction Decode Queue (IDQ) from Decode Stream Buffer (DSB) path.",
+        "CounterMask": "1",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
         "EventCode": "0x79",
         "Counter": "0,1,2,3",
-        "UMask": "0x30",
-        "EventName": "IDQ.MS_UOPS",
+        "UMask": "0x10",
+        "EventName": "IDQ.MS_DSB_UOPS",
         "SampleAfterValue": "2000003",
-        "BriefDescription": "Uops delivered to Instruction Decode Queue (IDQ) while Microcode Sequenser (MS) is busy.",
+        "BriefDescription": "Uops initiated by Decode Stream Buffer (DSB) that are being delivered to Instruction Decode Queue (IDQ) while Microcode Sequenser (MS) is busy.",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "PublicDescription": "This event counts cycles during which the microcode sequencer assisted the front-end in delivering uops.  Microcode assists are used for complex instructions or scenarios that can't be handled by the standard decoder.  Using other instructions, if possible, will usually improve performance.  See the Intel? 64 and IA-32 Architectures Optimization Reference Manual for more information.",
         "EventCode": "0x79",
         "Counter": "0,1,2,3",
-        "UMask": "0x30",
-        "EventName": "IDQ.MS_CYCLES",
+        "UMask": "0x10",
+        "EventName": "IDQ.MS_DSB_CYCLES",
         "SampleAfterValue": "2000003",
-        "BriefDescription": "Cycles when uops are being delivered to Instruction Decode Queue (IDQ) while Microcode Sequenser (MS) is busy.",
+        "BriefDescription": "Cycles when uops initiated by Decode Stream Buffer (DSB) are being delivered to Instruction Decode Queue (IDQ) while Microcode Sequenser (MS) is busy.",
         "CounterMask": "1",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "PublicDescription": "This event counts the number of uops not delivered to the back-end per cycle, per thread, when the back-end was not stalled.  In the ideal case 4 uops can be delivered each cycle.  The event counts the undelivered uops - so if 3 were delivered in one cycle, the counter would be incremented by 1 for that cycle (4 - 3). If the back-end is stalled, the count for this event is not incremented even when uops were not delivered, because the back-end would not have been able to accept them.  This event is used in determining the front-end bound category of the top-down pipeline slots characterization.",
-        "EventCode": "0x9C",
+        "EventCode": "0x79",
         "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "IDQ_UOPS_NOT_DELIVERED.CORE",
+        "UMask": "0x10",
+        "EdgeDetect": "1",
+        "EventName": "IDQ.MS_DSB_OCCUR",
         "SampleAfterValue": "2000003",
-        "BriefDescription": "Uops not delivered to Resource Allocation Table (RAT) per thread when backend of the machine is not stalled .",
-        "CounterHTOff": "0,1,2,3"
+        "BriefDescription": "Deliveries to Instruction Decode Queue (IDQ) initiated by Decode Stream Buffer (DSB) while Microcode Sequenser (MS) is busy.",
+        "CounterMask": "1",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "EventCode": "0x9C",
+        "EventCode": "0x79",
         "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "IDQ_UOPS_NOT_DELIVERED.CYCLES_0_UOPS_DELIV.CORE",
+        "UMask": "0x18",
+        "EventName": "IDQ.ALL_DSB_CYCLES_4_UOPS",
         "SampleAfterValue": "2000003",
-        "BriefDescription": "Cycles per thread when 4 or more uops are not delivered to Resource Allocation Table (RAT) when backend of the machine is not stalled.",
+        "BriefDescription": "Cycles Decode Stream Buffer (DSB) is delivering 4 Uops.",
         "CounterMask": "4",
-        "CounterHTOff": "0,1,2,3"
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "EventCode": "0x9C",
+        "EventCode": "0x79",
         "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "IDQ_UOPS_NOT_DELIVERED.CYCLES_LE_1_UOP_DELIV.CORE",
+        "UMask": "0x18",
+        "EventName": "IDQ.ALL_DSB_CYCLES_ANY_UOPS",
         "SampleAfterValue": "2000003",
-        "BriefDescription": "Cycles per thread when 3 or more uops are not delivered to Resource Allocation Table (RAT) when backend of the machine is not stalled.",
-        "CounterMask": "3",
-        "CounterHTOff": "0,1,2,3"
+        "BriefDescription": "Cycles Decode Stream Buffer (DSB) is delivering any Uop.",
+        "CounterMask": "1",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "EventCode": "0xAB",
+        "EventCode": "0x79",
         "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "DSB2MITE_SWITCHES.COUNT",
+        "UMask": "0x20",
+        "EventName": "IDQ.MS_MITE_UOPS",
         "SampleAfterValue": "2000003",
-        "BriefDescription": "Decode Stream Buffer (DSB)-to-MITE switches.",
+        "BriefDescription": "Uops initiated by MITE and delivered to Instruction Decode Queue (IDQ) while Microcode Sequenser (MS) is busy.",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "PublicDescription": "This event counts the cycles attributed to a switch from the Decoded Stream Buffer (DSB), which holds decoded instructions, to the legacy decode pipeline.  It excludes cycles when the back-end cannot  accept new micro-ops.  The penalty for these switches is potentially several cycles of instruction starvation, where no micro-ops are delivered to the back-end.",
-        "EventCode": "0xAB",
+        "EventCode": "0x79",
         "Counter": "0,1,2,3",
-        "UMask": "0x2",
-        "EventName": "DSB2MITE_SWITCHES.PENALTY_CYCLES",
+        "UMask": "0x24",
+        "EventName": "IDQ.ALL_MITE_CYCLES_4_UOPS",
         "SampleAfterValue": "2000003",
-        "BriefDescription": "Decode Stream Buffer (DSB)-to-MITE switch true penalty cycles.",
+        "BriefDescription": "Cycles MITE is delivering 4 Uops.",
+        "CounterMask": "4",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "EventCode": "0xAC",
+        "EventCode": "0x79",
         "Counter": "0,1,2,3",
-        "UMask": "0x2",
-        "EventName": "DSB_FILL.OTHER_CANCEL",
+        "UMask": "0x24",
+        "EventName": "IDQ.ALL_MITE_CYCLES_ANY_UOPS",
         "SampleAfterValue": "2000003",
-        "BriefDescription": "Cases of cancelling valid DSB fill not because of exceeding way limit.",
+        "BriefDescription": "Cycles MITE is delivering any Uop.",
+        "CounterMask": "1",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "EventCode": "0xAC",
+        "EventCode": "0x79",
         "Counter": "0,1,2,3",
-        "UMask": "0x8",
-        "EventName": "DSB_FILL.EXCEED_DSB_LINES",
+        "UMask": "0x30",
+        "EventName": "IDQ.MS_UOPS",
         "SampleAfterValue": "2000003",
-        "BriefDescription": "Cycles when Decode Stream Buffer (DSB) fill encounter more than 3 Decode Stream Buffer (DSB) lines.",
+        "BriefDescription": "Uops delivered to Instruction Decode Queue (IDQ) while Microcode Sequenser (MS) is busy.",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
+        "PublicDescription": "This event counts cycles during which the microcode sequencer assisted the front-end in delivering uops.  Microcode assists are used for complex instructions or scenarios that can't be handled by the standard decoder.  Using other instructions, if possible, will usually improve performance.  See the Intel\u00ae 64 and IA-32 Architectures Optimization Reference Manual for more information.",
         "EventCode": "0x79",
         "Counter": "0,1,2,3",
-        "UMask": "0x4",
-        "EventName": "IDQ.MITE_CYCLES",
+        "UMask": "0x30",
+        "EventName": "IDQ.MS_CYCLES",
         "SampleAfterValue": "2000003",
-        "BriefDescription": "Cycles when uops are being delivered to Instruction Decode Queue (IDQ) from MITE path.",
+        "BriefDescription": "Cycles when uops are being delivered to Instruction Decode Queue (IDQ) while Microcode Sequenser (MS) is busy.",
         "CounterMask": "1",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
         "EventCode": "0x79",
         "Counter": "0,1,2,3",
-        "UMask": "0x8",
-        "EventName": "IDQ.DSB_CYCLES",
+        "UMask": "0x30",
+        "EdgeDetect": "1",
+        "EventName": "IDQ.MS_SWITCHES",
         "SampleAfterValue": "2000003",
-        "BriefDescription": "Cycles when uops are being delivered to Instruction Decode Queue (IDQ) from Decode Stream Buffer (DSB) path.",
+        "BriefDescription": "Number of switches from DSB (Decode Stream Buffer) or MITE (legacy decode pipeline) to the Microcode Sequencer.",
         "CounterMask": "1",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
         "EventCode": "0x79",
         "Counter": "0,1,2,3",
-        "UMask": "0x10",
-        "EventName": "IDQ.MS_DSB_CYCLES",
+        "UMask": "0x3c",
+        "EventName": "IDQ.MITE_ALL_UOPS",
         "SampleAfterValue": "2000003",
-        "BriefDescription": "Cycles when uops initiated by Decode Stream Buffer (DSB) are being delivered to Instruction Decode Queue (IDQ) while Microcode Sequenser (MS) is busy.",
-        "CounterMask": "1",
+        "BriefDescription": "Uops delivered to Instruction Decode Queue (IDQ) from MITE path.",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "EventCode": "0x79",
+        "EventCode": "0x80",
         "Counter": "0,1,2,3",
-        "UMask": "0x10",
-        "EdgeDetect": "1",
-        "EventName": "IDQ.MS_DSB_OCCUR",
+        "UMask": "0x1",
+        "EventName": "ICACHE.HIT",
         "SampleAfterValue": "2000003",
-        "BriefDescription": "Deliveries to Instruction Decode Queue (IDQ) initiated by Decode Stream Buffer (DSB) while Microcode Sequenser (MS) is busy.",
-        "CounterMask": "1",
+        "BriefDescription": "Number of Instruction Cache, Streaming Buffer and Victim Cache Reads. both cacheable and noncacheable, including UC fetches.",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
+        "PublicDescription": "This event counts the number of instruction cache, streaming buffer and victim cache misses. Counting includes unchacheable accesses.",
+        "EventCode": "0x80",
+        "Counter": "0,1,2,3",
+        "UMask": "0x2",
+        "EventName": "ICACHE.MISSES",
+        "SampleAfterValue": "200003",
+        "BriefDescription": "Instruction cache, streaming buffer and victim cache misses.",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "PublicDescription": "This event counts the number of uops not delivered to the back-end per cycle, per thread, when the back-end was not stalled.  In the ideal case 4 uops can be delivered each cycle.  The event counts the undelivered uops - so if 3 were delivered in one cycle, the counter would be incremented by 1 for that cycle (4 - 3). If the back-end is stalled, the count for this event is not incremented even when uops were not delivered, because the back-end would not have been able to accept them.  This event is used in determining the front-end bound category of the top-down pipeline slots characterization.",
+        "EventCode": "0x9C",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "EventName": "IDQ_UOPS_NOT_DELIVERED.CORE",
+        "SampleAfterValue": "2000003",
+        "BriefDescription": "Uops not delivered to Resource Allocation Table (RAT) per thread when backend of the machine is not stalled .",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "EventCode": "0x9C",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "EventName": "IDQ_UOPS_NOT_DELIVERED.CYCLES_0_UOPS_DELIV.CORE",
+        "SampleAfterValue": "2000003",
+        "BriefDescription": "Cycles per thread when 4 or more uops are not delivered to Resource Allocation Table (RAT) when backend of the machine is not stalled.",
+        "CounterMask": "4",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "EventCode": "0x9C",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "EventName": "IDQ_UOPS_NOT_DELIVERED.CYCLES_LE_1_UOP_DELIV.CORE",
+        "SampleAfterValue": "2000003",
+        "BriefDescription": "Cycles per thread when 3 or more uops are not delivered to Resource Allocation Table (RAT) when backend of the machine is not stalled.",
+        "CounterMask": "3",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
         "EventCode": "0x9C",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
@@ -223,83 +246,60 @@
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "EventCode": "0x79",
-        "Counter": "0,1,2,3",
-        "UMask": "0x18",
-        "EventName": "IDQ.ALL_DSB_CYCLES_4_UOPS",
-        "SampleAfterValue": "2000003",
-        "BriefDescription": "Cycles Decode Stream Buffer (DSB) is delivering 4 Uops.",
-        "CounterMask": "4",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
-    },
-    {
-        "EventCode": "0x79",
+        "EventCode": "0x9C",
+        "Invert": "1",
         "Counter": "0,1,2,3",
-        "UMask": "0x18",
-        "EventName": "IDQ.ALL_DSB_CYCLES_ANY_UOPS",
+        "UMask": "0x1",
+        "EventName": "IDQ_UOPS_NOT_DELIVERED.CYCLES_FE_WAS_OK",
         "SampleAfterValue": "2000003",
-        "BriefDescription": "Cycles Decode Stream Buffer (DSB) is delivering any Uop.",
+        "BriefDescription": "Counts cycles FE delivered 4 uops or Resource Allocation Table (RAT) was stalling FE.",
         "CounterMask": "1",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
+        "CounterHTOff": "0,1,2,3"
     },
     {
-        "EventCode": "0x79",
+        "EventCode": "0xAB",
         "Counter": "0,1,2,3",
-        "UMask": "0x24",
-        "EventName": "IDQ.ALL_MITE_CYCLES_4_UOPS",
+        "UMask": "0x1",
+        "EventName": "DSB2MITE_SWITCHES.COUNT",
         "SampleAfterValue": "2000003",
-        "BriefDescription": "Cycles MITE is delivering 4 Uops.",
-        "CounterMask": "4",
+        "BriefDescription": "Decode Stream Buffer (DSB)-to-MITE switches.",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "EventCode": "0x79",
+        "PublicDescription": "This event counts the cycles attributed to a switch from the Decoded Stream Buffer (DSB), which holds decoded instructions, to the legacy decode pipeline.  It excludes cycles when the back-end cannot  accept new micro-ops.  The penalty for these switches is potentially several cycles of instruction starvation, where no micro-ops are delivered to the back-end.",
+        "EventCode": "0xAB",
         "Counter": "0,1,2,3",
-        "UMask": "0x24",
-        "EventName": "IDQ.ALL_MITE_CYCLES_ANY_UOPS",
+        "UMask": "0x2",
+        "EventName": "DSB2MITE_SWITCHES.PENALTY_CYCLES",
         "SampleAfterValue": "2000003",
-        "BriefDescription": "Cycles MITE is delivering any Uop.",
-        "CounterMask": "1",
+        "BriefDescription": "Decode Stream Buffer (DSB)-to-MITE switch true penalty cycles.",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
         "EventCode": "0xAC",
         "Counter": "0,1,2,3",
-        "UMask": "0xa",
-        "EventName": "DSB_FILL.ALL_CANCEL",
+        "UMask": "0x2",
+        "EventName": "DSB_FILL.OTHER_CANCEL",
         "SampleAfterValue": "2000003",
-        "BriefDescription": "Cases of cancelling valid Decode Stream Buffer (DSB) fill not because of exceeding way limit.",
+        "BriefDescription": "Cases of cancelling valid DSB fill not because of exceeding way limit.",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "EventCode": "0x9C",
-        "Invert": "1",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "IDQ_UOPS_NOT_DELIVERED.CYCLES_FE_WAS_OK",
-        "SampleAfterValue": "2000003",
-        "BriefDescription": "Counts cycles FE delivered 4 uops or Resource Allocation Table (RAT) was stalling FE.",
-        "CounterMask": "1",
-        "CounterHTOff": "0,1,2,3"
-    },
-    {
-        "EventCode": "0x79",
+        "EventCode": "0xAC",
         "Counter": "0,1,2,3",
-        "UMask": "0x3c",
-        "EventName": "IDQ.MITE_ALL_UOPS",
+        "UMask": "0x8",
+        "EventName": "DSB_FILL.EXCEED_DSB_LINES",
         "SampleAfterValue": "2000003",
-        "BriefDescription": "Uops delivered to Instruction Decode Queue (IDQ) from MITE path.",
+        "BriefDescription": "Cycles when Decode Stream Buffer (DSB) fill encounter more than 3 Decode Stream Buffer (DSB) lines.",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "EventCode": "0x79",
+        "EventCode": "0xAC",
         "Counter": "0,1,2,3",
-        "UMask": "0x30",
-        "EdgeDetect": "1",
-        "EventName": "IDQ.MS_SWITCHES",
+        "UMask": "0xa",
+        "EventName": "DSB_FILL.ALL_CANCEL",
         "SampleAfterValue": "2000003",
-        "BriefDescription": "Number of switches from DSB (Decode Stream Buffer) or MITE (legacy decode pipeline) to the Microcode Sequencer.",
-        "CounterMask": "1",
+        "BriefDescription": "Cases of cancelling valid Decode Stream Buffer (DSB) fill not because of exceeding way limit.",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     }
 ]
\ No newline at end of file
diff --git a/tools/perf/pmu-events/arch/x86/sandybridge/memory.json b/tools/perf/pmu-events/arch/x86/sandybridge/memory.json
index e6dfa89d00f3..78c1a987f9a2 100644
--- a/tools/perf/pmu-events/arch/x86/sandybridge/memory.json
+++ b/tools/perf/pmu-events/arch/x86/sandybridge/memory.json
@@ -1,5 +1,32 @@
 [
     {
+        "EventCode": "0x05",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "EventName": "MISALIGN_MEM_REF.LOADS",
+        "SampleAfterValue": "2000003",
+        "BriefDescription": "Speculative cache line split load uops dispatched to L1 cache.",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0x05",
+        "Counter": "0,1,2,3",
+        "UMask": "0x2",
+        "EventName": "MISALIGN_MEM_REF.STORES",
+        "SampleAfterValue": "2000003",
+        "BriefDescription": "Speculative cache line split STA uops dispatched to L1 cache.",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0xBE",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "EventName": "PAGE_WALKS.LLC_MISS",
+        "SampleAfterValue": "100003",
+        "BriefDescription": "Number of any page walk that had a miss in LLC. Does not necessary cause a SUSPEND.",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
         "PublicDescription": "This event counts the number of memory ordering Machine Clears detected. Memory Ordering Machine Clears can result from memory disambiguation, external snoops, or cross SMT-HW-thread snoop (stores) hitting load buffers.  Machine clears can have a significant performance impact if they are happening frequently.",
         "EventCode": "0xC3",
         "Counter": "0,1,2,3",
@@ -126,33 +153,6 @@
         "CounterHTOff": "3"
     },
     {
-        "EventCode": "0xBE",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "PAGE_WALKS.LLC_MISS",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "Number of any page walk that had a miss in LLC. Does not necessary cause a SUSPEND.",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
-    },
-    {
-        "EventCode": "0x05",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "MISALIGN_MEM_REF.LOADS",
-        "SampleAfterValue": "2000003",
-        "BriefDescription": "Speculative cache line split load uops dispatched to L1 cache.",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
-    },
-    {
-        "EventCode": "0x05",
-        "Counter": "0,1,2,3",
-        "UMask": "0x2",
-        "EventName": "MISALIGN_MEM_REF.STORES",
-        "SampleAfterValue": "2000003",
-        "BriefDescription": "Speculative cache line split STA uops dispatched to L1 cache.",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
-    },
-    {
         "EventCode": "0xB7, 0xBB",
         "MSRValue": "0x300400244",
         "Counter": "0,1,2,3",
@@ -367,7 +367,7 @@
         "EventName": "OFFCORE_RESPONSE.ANY_REQUEST.LLC_MISS_LOCAL.DRAM",
         "MSRIndex": "0x1a6,0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": " REQUEST = ANY_REQUEST and RESPONSE = LLC_MISS_LOCAL and SNOOP = DRAM",
+        "BriefDescription": "REQUEST = ANY_REQUEST and RESPONSE = LLC_MISS_LOCAL and SNOOP = DRAM",
         "CounterHTOff": "0,1,2,3"
     },
     {
@@ -379,7 +379,7 @@
         "EventName": "OFFCORE_RESPONSE.DATA_IN_SOCKET.LLC_MISS_LOCAL.ANY_LLC_HIT",
         "MSRIndex": "0x1a6,0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": " REQUEST = DATA_IN_SOCKET and RESPONSE = LLC_MISS_LOCAL and SNOOP = ANY_LLC_HIT",
+        "BriefDescription": "REQUEST = DATA_IN_SOCKET and RESPONSE = LLC_MISS_LOCAL and SNOOP = ANY_LLC_HIT",
         "CounterHTOff": "0,1,2,3"
     },
     {
@@ -391,7 +391,7 @@
         "EventName": "OFFCORE_RESPONSE.DEMAND_IFETCH.LLC_MISS_LOCAL.DRAM",
         "MSRIndex": "0x1a6,0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": " REQUEST = DEMAND_IFETCH and RESPONSE = LLC_MISS_LOCAL and SNOOP = DRAM",
+        "BriefDescription": "REQUEST = DEMAND_IFETCH and RESPONSE = LLC_MISS_LOCAL and SNOOP = DRAM",
         "CounterHTOff": "0,1,2,3"
     },
     {
@@ -403,7 +403,7 @@
         "EventName": "OFFCORE_RESPONSE.PF_DATA_RD.LLC_MISS_LOCAL.DRAM",
         "MSRIndex": "0x1a6,0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": " REQUEST = PF_DATA_RD and RESPONSE = LLC_MISS_LOCAL and SNOOP = DRAM",
+        "BriefDescription": "REQUEST = PF_DATA_RD and RESPONSE = LLC_MISS_LOCAL and SNOOP = DRAM",
         "CounterHTOff": "0,1,2,3"
     },
     {
@@ -415,7 +415,7 @@
         "EventName": "OFFCORE_RESPONSE.PF_IFETCH.LLC_MISS_LOCAL.DRAM",
         "MSRIndex": "0x1a6,0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": " REQUEST = PF_RFO and RESPONSE = LLC_MISS_LOCAL and SNOOP = DRAM",
+        "BriefDescription": "REQUEST = PF_RFO and RESPONSE = LLC_MISS_LOCAL and SNOOP = DRAM",
         "CounterHTOff": "0,1,2,3"
     },
     {
@@ -427,7 +427,7 @@
         "EventName": "OFFCORE_RESPONSE.PF_L_DATA_RD.LLC_MISS_LOCAL.DRAM",
         "MSRIndex": "0x1a6,0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": " REQUEST = PF_LLC_DATA_RD and RESPONSE = LLC_MISS_LOCAL and SNOOP = DRAM",
+        "BriefDescription": "REQUEST = PF_LLC_DATA_RD and RESPONSE = LLC_MISS_LOCAL and SNOOP = DRAM",
         "CounterHTOff": "0,1,2,3"
     },
     {
@@ -439,7 +439,7 @@
         "EventName": "OFFCORE_RESPONSE.PF_L_IFETCH.LLC_MISS_LOCAL.DRAM",
         "MSRIndex": "0x1a6,0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": " REQUEST = PF_LLC_IFETCH and RESPONSE = LLC_MISS_LOCAL and SNOOP = DRAM",
+        "BriefDescription": "REQUEST = PF_LLC_IFETCH and RESPONSE = LLC_MISS_LOCAL and SNOOP = DRAM",
         "CounterHTOff": "0,1,2,3"
     }
 ]
\ No newline at end of file
diff --git a/tools/perf/pmu-events/arch/x86/sandybridge/other.json b/tools/perf/pmu-events/arch/x86/sandybridge/other.json
index 64b195b82c50..874eb40a2e0f 100644
--- a/tools/perf/pmu-events/arch/x86/sandybridge/other.json
+++ b/tools/perf/pmu-events/arch/x86/sandybridge/other.json
@@ -9,6 +9,15 @@
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
+        "EventCode": "0x4E",
+        "Counter": "0,1,2,3",
+        "UMask": "0x2",
+        "EventName": "HW_PRE_REQ.DL1_MISS",
+        "SampleAfterValue": "2000003",
+        "BriefDescription": "Hardware Prefetch requests that miss the L1D cache. This accounts for both L1 streamer and IP-based (IPP) HW prefetchers. A request is being counted each time it access the cache & miss it, including if a block is applicable or if hit the Fill Buffer for .",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
         "EventCode": "0x5C",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
@@ -38,15 +47,6 @@
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "EventCode": "0x4E",
-        "Counter": "0,1,2,3",
-        "UMask": "0x2",
-        "EventName": "HW_PRE_REQ.DL1_MISS",
-        "SampleAfterValue": "2000003",
-        "BriefDescription": "Hardware Prefetch requests that miss the L1D cache. This accounts for both L1 streamer and IP-based (IPP) HW prefetchers. A request is being counted each time it access the cache & miss it, including if a block is applicable or if hit the Fill Buffer for .",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
-    },
-    {
         "EventCode": "0x63",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
diff --git a/tools/perf/pmu-events/arch/x86/sandybridge/pipeline.json b/tools/perf/pmu-events/arch/x86/sandybridge/pipeline.json
index 34a519d9bfa0..b7150f65f16d 100644
--- a/tools/perf/pmu-events/arch/x86/sandybridge/pipeline.json
+++ b/tools/perf/pmu-events/arch/x86/sandybridge/pipeline.json
@@ -1,289 +1,307 @@
 [
     {
-        "PublicDescription": "This event counts the number of instructions retired from execution. For instructions that consist of multiple micro-ops, this event counts the retirement of the last micro-op of the instruction. Counting continues during hardware interrupts, traps, and inside interrupt handlers. ",
-        "EventCode": "0x00",
-        "Counter": "Fixed counter 1",
+        "PublicDescription": "This event counts the number of reference cycles when the core is not in a halt state. The core enters the halt state when it is running the HLT instruction or the MWAIT instruction. This event is not affected by core frequency changes (for example, P states, TM2 transitions) but has the same incrementing frequency as the time stamp counter. This event can approximate elapsed time while the core was not in a halt state. This event has a constant ratio with the CPU_CLK_UNHALTED.REF_XCLK event. It is counted on a dedicated fixed counter, leaving the four (eight when Hyperthreading is disabled) programmable counters available for other events.",
+        "Counter": "Fixed counter 2",
+        "UMask": "0x3",
+        "EventName": "CPU_CLK_UNHALTED.REF_TSC",
+        "SampleAfterValue": "2000003",
+        "BriefDescription": "Reference cycles when the core is not in halt state.",
+        "CounterHTOff": "Fixed counter 2"
+    },
+    {
+        "PublicDescription": "This event counts the number of instructions retired from execution. For instructions that consist of multiple micro-ops, this event counts the retirement of the last micro-op of the instruction. Counting continues during hardware interrupts, traps, and inside interrupt handlers.",
+        "Counter": "Fixed counter 0",
         "UMask": "0x1",
         "EventName": "INST_RETIRED.ANY",
         "SampleAfterValue": "2000003",
         "BriefDescription": "Instructions retired from execution.",
-        "CounterHTOff": "Fixed counter 1"
+        "CounterHTOff": "Fixed counter 0"
     },
     {
-        "PublicDescription": "This event counts the number of core cycles while the thread is not in a halt state. The thread enters the halt state when it is running the HLT instruction. This event is a component in many key event ratios. The core frequency may change from time to time due to transitions associated with Enhanced Intel SpeedStep Technology or TM2. For this reason this event may have a changing ratio with regards to time. When the core frequency is constant, this event can approximate elapsed time while the core was not in the halt state. It is counted on a dedicated fixed counter, leaving the four (eight when Hyperthreading is disabled) programmable counters available for other events. ",
-        "EventCode": "0x00",
-        "Counter": "Fixed counter 2",
+        "PublicDescription": "This event counts the number of core cycles while the thread is not in a halt state. The thread enters the halt state when it is running the HLT instruction. This event is a component in many key event ratios. The core frequency may change from time to time due to transitions associated with Enhanced Intel SpeedStep Technology or TM2. For this reason this event may have a changing ratio with regards to time. When the core frequency is constant, this event can approximate elapsed time while the core was not in the halt state. It is counted on a dedicated fixed counter, leaving the four (eight when Hyperthreading is disabled) programmable counters available for other events.",
+        "Counter": "Fixed counter 1",
         "UMask": "0x2",
         "EventName": "CPU_CLK_UNHALTED.THREAD",
         "SampleAfterValue": "2000003",
         "BriefDescription": "Core cycles when the thread is not in halt state.",
-        "CounterHTOff": "Fixed counter 2"
+        "CounterHTOff": "Fixed counter 1"
     },
     {
-        "PublicDescription": "This event counts the number of reference cycles when the core is not in a halt state. The core enters the halt state when it is running the HLT instruction or the MWAIT instruction. This event is not affected by core frequency changes (for example, P states, TM2 transitions) but has the same incrementing frequency as the time stamp counter. This event can approximate elapsed time while the core was not in a halt state. This event has a constant ratio with the CPU_CLK_UNHALTED.REF_XCLK event. It is counted on a dedicated fixed counter, leaving the four (eight when Hyperthreading is disabled) programmable counters available for other events. ",
-        "EventCode": "0x00",
-        "Counter": "Fixed counter 3",
-        "UMask": "0x3",
-        "EventName": "CPU_CLK_UNHALTED.REF_TSC",
+        "Counter": "Fixed counter 1",
+        "UMask": "0x2",
+        "AnyThread": "1",
+        "EventName": "CPU_CLK_UNHALTED.THREAD_ANY",
         "SampleAfterValue": "2000003",
-        "BriefDescription": "Reference cycles when the core is not in halt state.",
-        "CounterHTOff": "Fixed counter 3"
-    },
-    {
-        "EventCode": "0x88",
-        "Counter": "0,1,2,3",
-        "UMask": "0x41",
-        "EventName": "BR_INST_EXEC.NONTAKEN_CONDITIONAL",
-        "SampleAfterValue": "200003",
-        "BriefDescription": "Not taken macro-conditional branches.",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
+        "BriefDescription": "Core cycles when at least one thread on the physical core is not in halt state.",
+        "CounterHTOff": "Fixed counter 1"
     },
     {
-        "EventCode": "0x88",
+        "EventCode": "0x03",
         "Counter": "0,1,2,3",
-        "UMask": "0x81",
-        "EventName": "BR_INST_EXEC.TAKEN_CONDITIONAL",
-        "SampleAfterValue": "200003",
-        "BriefDescription": "Taken speculative and retired macro-conditional branches.",
+        "UMask": "0x1",
+        "EventName": "LD_BLOCKS.DATA_UNKNOWN",
+        "SampleAfterValue": "100003",
+        "BriefDescription": "Loads delayed due to SB blocks, preceding store operations with known addresses but unknown data.",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "EventCode": "0x88",
+        "PublicDescription": "This event counts loads that followed a store to the same address, where the data could not be forwarded inside the pipeline from the store to the load.  The most common reason why store forwarding would be blocked is when a load's address range overlaps with a preceeding smaller uncompleted store.  See the table of not supported store forwards in the Intel\u00ae 64 and IA-32 Architectures Optimization Reference Manual.  The penalty for blocked store forwarding is that the load must wait for the store to complete before it can be issued.",
+        "EventCode": "0x03",
         "Counter": "0,1,2,3",
-        "UMask": "0x82",
-        "EventName": "BR_INST_EXEC.TAKEN_DIRECT_JUMP",
-        "SampleAfterValue": "200003",
-        "BriefDescription": "Taken speculative and retired macro-conditional branch instructions excluding calls and indirects.",
+        "UMask": "0x2",
+        "EventName": "LD_BLOCKS.STORE_FORWARD",
+        "SampleAfterValue": "100003",
+        "BriefDescription": "Cases when loads get true Block-on-Store blocking code preventing store forwarding.",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "EventCode": "0x88",
+        "EventCode": "0x03",
         "Counter": "0,1,2,3",
-        "UMask": "0x84",
-        "EventName": "BR_INST_EXEC.TAKEN_INDIRECT_JUMP_NON_CALL_RET",
-        "SampleAfterValue": "200003",
-        "BriefDescription": "Taken speculative and retired indirect branches excluding calls and returns.",
+        "UMask": "0x8",
+        "EventName": "LD_BLOCKS.NO_SR",
+        "SampleAfterValue": "100003",
+        "BriefDescription": "This event counts the number of times that split load operations are temporarily blocked because all resources for handling the split accesses are in use.",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "EventCode": "0x88",
+        "EventCode": "0x03",
         "Counter": "0,1,2,3",
-        "UMask": "0x88",
-        "EventName": "BR_INST_EXEC.TAKEN_INDIRECT_NEAR_RETURN",
-        "SampleAfterValue": "200003",
-        "BriefDescription": "Taken speculative and retired indirect branches with return mnemonic.",
+        "UMask": "0x10",
+        "EventName": "LD_BLOCKS.ALL_BLOCK",
+        "SampleAfterValue": "100003",
+        "BriefDescription": "Number of cases where any load ends up with a valid block-code written to the load buffer (including blocks due to Memory Order Buffer (MOB), Data Cache Unit (DCU), TLB, but load has no DCU miss).",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "EventCode": "0x88",
+        "PublicDescription": "Aliasing occurs when a load is issued after a store and their memory addresses are offset by 4K.  This event counts the number of loads that aliased with a preceding store, resulting in an extended address check in the pipeline.  The enhanced address check typically has a performance penalty of 5 cycles.",
+        "EventCode": "0x07",
         "Counter": "0,1,2,3",
-        "UMask": "0x90",
-        "EventName": "BR_INST_EXEC.TAKEN_DIRECT_NEAR_CALL",
-        "SampleAfterValue": "200003",
-        "BriefDescription": "Taken speculative and retired direct near calls.",
+        "UMask": "0x1",
+        "EventName": "LD_BLOCKS_PARTIAL.ADDRESS_ALIAS",
+        "SampleAfterValue": "100003",
+        "BriefDescription": "False dependencies in MOB due to partial compare.",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "EventCode": "0x88",
+        "EventCode": "0x07",
         "Counter": "0,1,2,3",
-        "UMask": "0xa0",
-        "EventName": "BR_INST_EXEC.TAKEN_INDIRECT_NEAR_CALL",
-        "SampleAfterValue": "200003",
-        "BriefDescription": "Taken speculative and retired indirect calls.",
+        "UMask": "0x8",
+        "EventName": "LD_BLOCKS_PARTIAL.ALL_STA_BLOCK",
+        "SampleAfterValue": "100003",
+        "BriefDescription": "This event counts the number of times that load operations are temporarily blocked because of older stores, with addresses that are not yet known. A load operation may incur more than one block of this type.",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "EventCode": "0x88",
+        "EventCode": "0x0D",
         "Counter": "0,1,2,3",
-        "UMask": "0xc1",
-        "EventName": "BR_INST_EXEC.ALL_CONDITIONAL",
-        "SampleAfterValue": "200003",
-        "BriefDescription": "Speculative and retired macro-conditional branches.",
+        "UMask": "0x3",
+        "EventName": "INT_MISC.RECOVERY_CYCLES",
+        "SampleAfterValue": "2000003",
+        "BriefDescription": "Number of cycles waiting for the checkpoints in Resource Allocation Table (RAT) to be recovered after Nuke due to all other cases except JEClear (e.g. whenever a ucode assist is needed like SSE exception, memory disambiguation, etc...).",
+        "CounterMask": "1",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "EventCode": "0x88",
+        "EventCode": "0x0D",
         "Counter": "0,1,2,3",
-        "UMask": "0xc2",
-        "EventName": "BR_INST_EXEC.ALL_DIRECT_JMP",
-        "SampleAfterValue": "200003",
-        "BriefDescription": "Speculative and retired macro-unconditional branches excluding calls and indirects.",
+        "UMask": "0x3",
+        "EdgeDetect": "1",
+        "EventName": "INT_MISC.RECOVERY_STALLS_COUNT",
+        "SampleAfterValue": "2000003",
+        "BriefDescription": "Number of occurences waiting for the checkpoints in Resource Allocation Table (RAT) to be recovered after Nuke due to all other cases except JEClear (e.g. whenever a ucode assist is needed like SSE exception, memory disambiguation, etc...).",
+        "CounterMask": "1",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "EventCode": "0x88",
+        "EventCode": "0x0D",
         "Counter": "0,1,2,3",
-        "UMask": "0xc4",
-        "EventName": "BR_INST_EXEC.ALL_INDIRECT_JUMP_NON_CALL_RET",
-        "SampleAfterValue": "200003",
-        "BriefDescription": "Speculative and retired indirect branches excluding calls and returns.",
+        "UMask": "0x3",
+        "AnyThread": "1",
+        "EventName": "INT_MISC.RECOVERY_CYCLES_ANY",
+        "SampleAfterValue": "2000003",
+        "BriefDescription": "Core cycles the allocator was stalled due to recovery from earlier clear event for any thread running on the physical core (e.g. misprediction or memory nuke).",
+        "CounterMask": "1",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "EventCode": "0x88",
+        "EventCode": "0x0D",
         "Counter": "0,1,2,3",
-        "UMask": "0xc8",
-        "EventName": "BR_INST_EXEC.ALL_INDIRECT_NEAR_RETURN",
-        "SampleAfterValue": "200003",
-        "BriefDescription": "Speculative and retired indirect return branches.",
+        "UMask": "0x40",
+        "EventName": "INT_MISC.RAT_STALL_CYCLES",
+        "SampleAfterValue": "2000003",
+        "BriefDescription": "Cycles when Resource Allocation Table (RAT) external stall is sent to Instruction Decode Queue (IDQ) for the thread.",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "EventCode": "0x88",
+        "PublicDescription": "This event counts the number of Uops issued by the front-end of the pipeilne to the back-end.",
+        "EventCode": "0x0E",
         "Counter": "0,1,2,3",
-        "UMask": "0xd0",
-        "EventName": "BR_INST_EXEC.ALL_DIRECT_NEAR_CALL",
-        "SampleAfterValue": "200003",
-        "BriefDescription": "Speculative and retired direct near calls.",
+        "UMask": "0x1",
+        "EventName": "UOPS_ISSUED.ANY",
+        "SampleAfterValue": "2000003",
+        "BriefDescription": "Uops that Resource Allocation Table (RAT) issues to Reservation Station (RS).",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "EventCode": "0x89",
+        "EventCode": "0x0E",
+        "Invert": "1",
         "Counter": "0,1,2,3",
-        "UMask": "0x41",
-        "EventName": "BR_MISP_EXEC.NONTAKEN_CONDITIONAL",
-        "SampleAfterValue": "200003",
-        "BriefDescription": "Not taken speculative and retired mispredicted macro conditional branches.",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
+        "UMask": "0x1",
+        "EventName": "UOPS_ISSUED.STALL_CYCLES",
+        "SampleAfterValue": "2000003",
+        "BriefDescription": "Cycles when Resource Allocation Table (RAT) does not issue Uops to Reservation Station (RS) for the thread.",
+        "CounterMask": "1",
+        "CounterHTOff": "0,1,2,3"
     },
     {
-        "EventCode": "0x89",
+        "EventCode": "0x0E",
+        "Invert": "1",
         "Counter": "0,1,2,3",
-        "UMask": "0x81",
-        "EventName": "BR_MISP_EXEC.TAKEN_CONDITIONAL",
-        "SampleAfterValue": "200003",
-        "BriefDescription": "Taken speculative and retired mispredicted macro conditional branches.",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
+        "UMask": "0x1",
+        "AnyThread": "1",
+        "EventName": "UOPS_ISSUED.CORE_STALL_CYCLES",
+        "SampleAfterValue": "2000003",
+        "BriefDescription": "Cycles when Resource Allocation Table (RAT) does not issue Uops to Reservation Station (RS) for all threads.",
+        "CounterMask": "1",
+        "CounterHTOff": "0,1,2,3"
     },
     {
-        "EventCode": "0x89",
+        "EventCode": "0x14",
         "Counter": "0,1,2,3",
-        "UMask": "0x84",
-        "EventName": "BR_MISP_EXEC.TAKEN_INDIRECT_JUMP_NON_CALL_RET",
-        "SampleAfterValue": "200003",
-        "BriefDescription": "Taken speculative and retired mispredicted indirect branches excluding calls and returns.",
+        "UMask": "0x1",
+        "EventName": "ARITH.FPU_DIV_ACTIVE",
+        "SampleAfterValue": "2000003",
+        "BriefDescription": "Cycles when divider is busy executing divide operations.",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "EventCode": "0x89",
+        "PublicDescription": "This event counts the number of the divide operations executed.",
+        "EventCode": "0x14",
         "Counter": "0,1,2,3",
-        "UMask": "0x88",
-        "EventName": "BR_MISP_EXEC.TAKEN_RETURN_NEAR",
-        "SampleAfterValue": "200003",
-        "BriefDescription": "Taken speculative and retired mispredicted indirect branches with return mnemonic.",
+        "UMask": "0x1",
+        "EdgeDetect": "1",
+        "EventName": "ARITH.FPU_DIV",
+        "SampleAfterValue": "100003",
+        "BriefDescription": "Divide operations executed.",
+        "CounterMask": "1",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "EventCode": "0x89",
+        "EventCode": "0x3C",
         "Counter": "0,1,2,3",
-        "UMask": "0x90",
-        "EventName": "BR_MISP_EXEC.TAKEN_DIRECT_NEAR_CALL",
-        "SampleAfterValue": "200003",
-        "BriefDescription": "Taken speculative and retired mispredicted direct near calls.",
+        "UMask": "0x0",
+        "EventName": "CPU_CLK_UNHALTED.THREAD_P",
+        "SampleAfterValue": "2000003",
+        "BriefDescription": "Thread cycles when thread is not in halt state.",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "EventCode": "0x89",
+        "EventCode": "0x3C",
         "Counter": "0,1,2,3",
-        "UMask": "0xa0",
-        "EventName": "BR_MISP_EXEC.TAKEN_INDIRECT_NEAR_CALL",
-        "SampleAfterValue": "200003",
-        "BriefDescription": "Taken speculative and retired mispredicted indirect calls.",
+        "UMask": "0x0",
+        "AnyThread": "1",
+        "EventName": "CPU_CLK_UNHALTED.THREAD_P_ANY",
+        "SampleAfterValue": "2000003",
+        "BriefDescription": "Core cycles when at least one thread on the physical core is not in halt state.",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "EventCode": "0x89",
+        "EventCode": "0x3C",
         "Counter": "0,1,2,3",
-        "UMask": "0xc1",
-        "EventName": "BR_MISP_EXEC.ALL_CONDITIONAL",
-        "SampleAfterValue": "200003",
-        "BriefDescription": "Speculative and retired mispredicted macro conditional branches.",
+        "UMask": "0x1",
+        "EventName": "CPU_CLK_THREAD_UNHALTED.REF_XCLK",
+        "SampleAfterValue": "2000003",
+        "BriefDescription": "Reference cycles when the thread is unhalted (counts at 100 MHz rate).",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "EventCode": "0x89",
+        "EventCode": "0x3C",
         "Counter": "0,1,2,3",
-        "UMask": "0xc4",
-        "EventName": "BR_MISP_EXEC.ALL_INDIRECT_JUMP_NON_CALL_RET",
-        "SampleAfterValue": "200003",
-        "BriefDescription": "Mispredicted indirect branches excluding calls and returns.",
+        "UMask": "0x1",
+        "AnyThread": "1",
+        "EventName": "CPU_CLK_THREAD_UNHALTED.REF_XCLK_ANY",
+        "SampleAfterValue": "2000003",
+        "BriefDescription": "Reference cycles when the at least one thread on the physical core is unhalted (counts at 100 MHz rate).",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "EventCode": "0x89",
+        "PublicDescription": "Reference cycles when the thread is unhalted (counts at 100 MHz rate)",
+        "EventCode": "0x3C",
         "Counter": "0,1,2,3",
-        "UMask": "0xd0",
-        "EventName": "BR_MISP_EXEC.ALL_DIRECT_NEAR_CALL",
-        "SampleAfterValue": "200003",
-        "BriefDescription": "Speculative and retired mispredicted direct near calls.",
+        "UMask": "0x1",
+        "EventName": "CPU_CLK_UNHALTED.REF_XCLK",
+        "SampleAfterValue": "2000003",
+        "BriefDescription": "Reference cycles when the thread is unhalted (counts at 100 MHz rate).",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
         "EventCode": "0x3C",
         "Counter": "0,1,2,3",
-        "UMask": "0x0",
-        "EventName": "CPU_CLK_UNHALTED.THREAD_P",
+        "UMask": "0x1",
+        "AnyThread": "1",
+        "EventName": "CPU_CLK_UNHALTED.REF_XCLK_ANY",
         "SampleAfterValue": "2000003",
-        "BriefDescription": "Thread cycles when thread is not in halt state.",
+        "BriefDescription": "Reference cycles when the at least one thread on the physical core is unhalted (counts at 100 MHz rate).",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "EventCode": "0xA8",
+        "EventCode": "0x3C",
         "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "LSD.UOPS",
+        "UMask": "0x2",
+        "EventName": "CPU_CLK_THREAD_UNHALTED.ONE_THREAD_ACTIVE",
         "SampleAfterValue": "2000003",
-        "BriefDescription": "Number of Uops delivered by the LSD.",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
+        "BriefDescription": "Count XClk pulses when this thread is unhalted and the other is halted.",
+        "CounterHTOff": "0,1,2,3"
     },
     {
-        "EventCode": "0xA8",
+        "EventCode": "0x3C",
         "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "LSD.CYCLES_ACTIVE",
+        "UMask": "0x2",
+        "EventName": "CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE",
         "SampleAfterValue": "2000003",
-        "BriefDescription": "Cycles Uops delivered by the LSD, but didn't come from the decoder.",
-        "CounterMask": "1",
+        "BriefDescription": "Count XClk pulses when this thread is unhalted and the other thread is halted.",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "EventCode": "0x87",
+        "EventCode": "0x4C",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
-        "EventName": "ILD_STALL.LCP",
-        "SampleAfterValue": "2000003",
-        "BriefDescription": "Stalls caused by changing prefix length of the instruction.",
+        "EventName": "LOAD_HIT_PRE.SW_PF",
+        "SampleAfterValue": "100003",
+        "BriefDescription": "Not software-prefetch load dispatches that hit FB allocated for software prefetch.",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "EventCode": "0x87",
+        "EventCode": "0x4C",
         "Counter": "0,1,2,3",
-        "UMask": "0x4",
-        "EventName": "ILD_STALL.IQ_FULL",
-        "SampleAfterValue": "2000003",
-        "BriefDescription": "Stall cycles because IQ is full.",
+        "UMask": "0x2",
+        "EventName": "LOAD_HIT_PRE.HW_PF",
+        "SampleAfterValue": "100003",
+        "BriefDescription": "Not software-prefetch load dispatches that hit FB allocated for hardware prefetch.",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "EventCode": "0x0D",
+        "EventCode": "0x59",
         "Counter": "0,1,2,3",
-        "UMask": "0x40",
-        "EventName": "INT_MISC.RAT_STALL_CYCLES",
+        "UMask": "0x20",
+        "EventName": "PARTIAL_RAT_STALLS.FLAGS_MERGE_UOP",
         "SampleAfterValue": "2000003",
-        "BriefDescription": "Cycles when Resource Allocation Table (RAT) external stall is sent to Instruction Decode Queue (IDQ) for the thread.",
+        "BriefDescription": "Increments the number of flags-merge uops in flight each cycle.",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
+        "PublicDescription": "This event counts the number of cycles spent executing performance-sensitive flags-merging uops. For example, shift CL (merge_arith_flags). For more details, See the Intel\u00ae 64 and IA-32 Architectures Optimization Reference Manual.",
         "EventCode": "0x59",
         "Counter": "0,1,2,3",
         "UMask": "0x20",
-        "EventName": "PARTIAL_RAT_STALLS.FLAGS_MERGE_UOP",
+        "EventName": "PARTIAL_RAT_STALLS.FLAGS_MERGE_UOP_CYCLES",
         "SampleAfterValue": "2000003",
-        "BriefDescription": "Increments the number of flags-merge uops in flight each cycle.",
+        "BriefDescription": "Performance sensitive flags-merging uops added by Sandy Bridge u-arch.",
+        "CounterMask": "1",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "PublicDescription": "This event counts the number of cycles with at least one slow LEA uop being allocated. A uop is generally considered as slow LEA if it has three sources (for example, two sources and immediate) regardless of whether it is a result of LEA instruction or not. Examples of the slow LEA uop are or uops with base, index, and offset source operands using base and index reqisters, where base is EBR/RBP/R13, using RIP relative or 16-bit addressing modes. See the Intel? 64 and IA-32 Architectures Optimization Reference Manual for more details about slow LEA instructions.",
+        "PublicDescription": "This event counts the number of cycles with at least one slow LEA uop being allocated. A uop is generally considered as slow LEA if it has three sources (for example, two sources and immediate) regardless of whether it is a result of LEA instruction or not. Examples of the slow LEA uop are or uops with base, index, and offset source operands using base and index reqisters, where base is EBR/RBP/R13, using RIP relative or 16-bit addressing modes. See the Intel\u00ae 64 and IA-32 Architectures Optimization Reference Manual for more details about slow LEA instructions.",
         "EventCode": "0x59",
         "Counter": "0,1,2,3",
         "UMask": "0x40",
@@ -302,48 +320,21 @@
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "EventCode": "0xA2",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "RESOURCE_STALLS.ANY",
-        "SampleAfterValue": "2000003",
-        "BriefDescription": "Resource-related stall cycles.",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
-    },
-    {
-        "EventCode": "0xA2",
-        "Counter": "0,1,2,3",
-        "UMask": "0x2",
-        "EventName": "RESOURCE_STALLS.LB",
-        "SampleAfterValue": "2000003",
-        "BriefDescription": "Counts the cycles of stall due to lack of load buffers.",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
-    },
-    {
-        "EventCode": "0xA2",
-        "Counter": "0,1,2,3",
-        "UMask": "0x4",
-        "EventName": "RESOURCE_STALLS.RS",
-        "SampleAfterValue": "2000003",
-        "BriefDescription": "Cycles stalled due to no eligible RS entry available.",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
-    },
-    {
-        "EventCode": "0xA2",
+        "EventCode": "0x5B",
         "Counter": "0,1,2,3",
-        "UMask": "0x8",
-        "EventName": "RESOURCE_STALLS.SB",
+        "UMask": "0xc",
+        "EventName": "RESOURCE_STALLS2.ALL_FL_EMPTY",
         "SampleAfterValue": "2000003",
-        "BriefDescription": "Cycles stalled due to no store buffers available. (not including draining form sync).",
+        "BriefDescription": "Cycles with either free list is empty.",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "EventCode": "0xA2",
+        "EventCode": "0x5B",
         "Counter": "0,1,2,3",
-        "UMask": "0x10",
-        "EventName": "RESOURCE_STALLS.ROB",
+        "UMask": "0xf",
+        "EventName": "RESOURCE_STALLS2.ALL_PRF_CONTROL",
         "SampleAfterValue": "2000003",
-        "BriefDescription": "Cycles stalled due to re-order buffer full.",
+        "BriefDescription": "Resource stalls2 control structures full for physical registers.",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
@@ -356,702 +347,663 @@
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "PublicDescription": "This event counts the number of Uops issued by the front-end of the pipeilne to the back-end.",
-        "EventCode": "0x0E",
+        "EventCode": "0x5B",
         "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "UOPS_ISSUED.ANY",
+        "UMask": "0x4f",
+        "EventName": "RESOURCE_STALLS2.OOO_RSRC",
         "SampleAfterValue": "2000003",
-        "BriefDescription": "Uops that Resource Allocation Table (RAT) issues to Reservation Station (RS).",
+        "BriefDescription": "Resource stalls out of order resources full.",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "EventCode": "0x0E",
-        "Invert": "1",
+        "EventCode": "0x5E",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
-        "EventName": "UOPS_ISSUED.STALL_CYCLES",
+        "EventName": "RS_EVENTS.EMPTY_CYCLES",
         "SampleAfterValue": "2000003",
-        "BriefDescription": "Cycles when Resource Allocation Table (RAT) does not issue Uops to Reservation Station (RS) for the thread.",
-        "CounterMask": "1",
-        "CounterHTOff": "0,1,2,3"
+        "BriefDescription": "Cycles when Reservation Station (RS) is empty for the thread.",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "EventCode": "0x0E",
+        "EventCode": "0x5E",
         "Invert": "1",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
-        "AnyThread": "1",
-        "EventName": "UOPS_ISSUED.CORE_STALL_CYCLES",
+        "EdgeDetect": "1",
+        "EventName": "RS_EVENTS.EMPTY_END",
         "SampleAfterValue": "2000003",
-        "BriefDescription": "Cycles when Resource Allocation Table (RAT) does not issue Uops to Reservation Station (RS) for all threads.",
+        "BriefDescription": "Counts end of periods where the Reservation Station (RS) was empty. Could be useful to precisely locate Frontend Latency Bound issues.",
         "CounterMask": "1",
-        "CounterHTOff": "0,1,2,3"
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "EventCode": "0x5E",
+        "EventCode": "0x87",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
-        "EventName": "RS_EVENTS.EMPTY_CYCLES",
+        "EventName": "ILD_STALL.LCP",
         "SampleAfterValue": "2000003",
-        "BriefDescription": "Cycles when Reservation Station (RS) is empty for the thread.",
+        "BriefDescription": "Stalls caused by changing prefix length of the instruction.",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "EventCode": "0xCC",
+        "EventCode": "0x87",
         "Counter": "0,1,2,3",
-        "UMask": "0x20",
-        "EventName": "ROB_MISC_EVENTS.LBR_INSERTS",
+        "UMask": "0x4",
+        "EventName": "ILD_STALL.IQ_FULL",
         "SampleAfterValue": "2000003",
-        "BriefDescription": "Count cases of saving new LBR.",
+        "BriefDescription": "Stall cycles because IQ is full.",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "PublicDescription": "This event is incremented when self-modifying code (SMC) is detected, which causes a machine clear.  Machine clears can have a significant performance impact if they are happening frequently.",
-        "EventCode": "0xC3",
+        "EventCode": "0x88",
         "Counter": "0,1,2,3",
-        "UMask": "0x4",
-        "EventName": "MACHINE_CLEARS.SMC",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "Self-modifying code (SMC) detected.",
+        "UMask": "0x41",
+        "EventName": "BR_INST_EXEC.NONTAKEN_CONDITIONAL",
+        "SampleAfterValue": "200003",
+        "BriefDescription": "Not taken macro-conditional branches.",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "PublicDescription": "Maskmov false fault - counts number of time ucode passes through Maskmov flow due to instruction's mask being 0 while the flow was completed without raising a fault.",
-        "EventCode": "0xC3",
+        "EventCode": "0x88",
         "Counter": "0,1,2,3",
-        "UMask": "0x20",
-        "EventName": "MACHINE_CLEARS.MASKMOV",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "This event counts the number of executed Intel AVX masked load operations that refer to an illegal address range with the mask bits set to 0.",
+        "UMask": "0x81",
+        "EventName": "BR_INST_EXEC.TAKEN_CONDITIONAL",
+        "SampleAfterValue": "200003",
+        "BriefDescription": "Taken speculative and retired macro-conditional branches.",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "EventCode": "0xC0",
+        "EventCode": "0x88",
         "Counter": "0,1,2,3",
-        "UMask": "0x0",
-        "EventName": "INST_RETIRED.ANY_P",
-        "SampleAfterValue": "2000003",
-        "BriefDescription": "Number of instructions retired. General Counter   - architectural event.",
+        "UMask": "0x82",
+        "EventName": "BR_INST_EXEC.TAKEN_DIRECT_JUMP",
+        "SampleAfterValue": "200003",
+        "BriefDescription": "Taken speculative and retired macro-conditional branch instructions excluding calls and indirects.",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "PEBS": "1",
-        "PublicDescription": "This event counts the number of micro-ops retired.",
-        "EventCode": "0xC2",
+        "EventCode": "0x88",
         "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "UOPS_RETIRED.ALL",
-        "SampleAfterValue": "2000003",
-        "BriefDescription": "Actually retired uops.",
+        "UMask": "0x84",
+        "EventName": "BR_INST_EXEC.TAKEN_INDIRECT_JUMP_NON_CALL_RET",
+        "SampleAfterValue": "200003",
+        "BriefDescription": "Taken speculative and retired indirect branches excluding calls and returns.",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "PEBS": "1",
-        "PublicDescription": "This event counts the number of retirement slots used each cycle.  There are potentially 4 slots that can be used each cycle - meaning, 4 micro-ops or 4 instructions could retire each cycle.  This event is used in determining the 'Retiring' category of the Top-Down pipeline slots characterization.",
-        "EventCode": "0xC2",
+        "EventCode": "0x88",
         "Counter": "0,1,2,3",
-        "UMask": "0x2",
-        "EventName": "UOPS_RETIRED.RETIRE_SLOTS",
-        "SampleAfterValue": "2000003",
-        "BriefDescription": "Retirement slots used.",
+        "UMask": "0x88",
+        "EventName": "BR_INST_EXEC.TAKEN_INDIRECT_NEAR_RETURN",
+        "SampleAfterValue": "200003",
+        "BriefDescription": "Taken speculative and retired indirect branches with return mnemonic.",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "EventCode": "0xC2",
-        "Invert": "1",
+        "EventCode": "0x88",
         "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "UOPS_RETIRED.STALL_CYCLES",
-        "SampleAfterValue": "2000003",
-        "BriefDescription": "Cycles without actually retired uops.",
-        "CounterMask": "1",
-        "CounterHTOff": "0,1,2,3"
+        "UMask": "0x90",
+        "EventName": "BR_INST_EXEC.TAKEN_DIRECT_NEAR_CALL",
+        "SampleAfterValue": "200003",
+        "BriefDescription": "Taken speculative and retired direct near calls.",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "EventCode": "0xC2",
-        "Invert": "1",
+        "EventCode": "0x88",
         "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "UOPS_RETIRED.TOTAL_CYCLES",
-        "SampleAfterValue": "2000003",
-        "BriefDescription": "Cycles with less than 10 actually retired uops.",
-        "CounterMask": "10",
-        "CounterHTOff": "0,1,2,3"
+        "UMask": "0xa0",
+        "EventName": "BR_INST_EXEC.TAKEN_INDIRECT_NEAR_CALL",
+        "SampleAfterValue": "200003",
+        "BriefDescription": "Taken speculative and retired indirect calls.",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "PEBS": "1",
-        "EventCode": "0xC4",
+        "EventCode": "0x88",
         "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "BR_INST_RETIRED.CONDITIONAL",
-        "SampleAfterValue": "400009",
-        "BriefDescription": "Conditional branch instructions retired.",
+        "UMask": "0xc1",
+        "EventName": "BR_INST_EXEC.ALL_CONDITIONAL",
+        "SampleAfterValue": "200003",
+        "BriefDescription": "Speculative and retired macro-conditional branches.",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "PEBS": "1",
-        "EventCode": "0xC4",
+        "EventCode": "0x88",
         "Counter": "0,1,2,3",
-        "UMask": "0x2",
-        "EventName": "BR_INST_RETIRED.NEAR_CALL",
-        "SampleAfterValue": "100007",
-        "BriefDescription": "Direct and indirect near call instructions retired.",
+        "UMask": "0xc2",
+        "EventName": "BR_INST_EXEC.ALL_DIRECT_JMP",
+        "SampleAfterValue": "200003",
+        "BriefDescription": "Speculative and retired macro-unconditional branches excluding calls and indirects.",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "EventCode": "0xC4",
+        "EventCode": "0x88",
         "Counter": "0,1,2,3",
-        "UMask": "0x0",
-        "EventName": "BR_INST_RETIRED.ALL_BRANCHES",
-        "SampleAfterValue": "400009",
-        "BriefDescription": "All (macro) branch instructions retired.",
+        "UMask": "0xc4",
+        "EventName": "BR_INST_EXEC.ALL_INDIRECT_JUMP_NON_CALL_RET",
+        "SampleAfterValue": "200003",
+        "BriefDescription": "Speculative and retired indirect branches excluding calls and returns.",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "PEBS": "1",
-        "EventCode": "0xC4",
+        "EventCode": "0x88",
         "Counter": "0,1,2,3",
-        "UMask": "0x8",
-        "EventName": "BR_INST_RETIRED.NEAR_RETURN",
-        "SampleAfterValue": "100007",
-        "BriefDescription": "Return instructions retired.",
+        "UMask": "0xc8",
+        "EventName": "BR_INST_EXEC.ALL_INDIRECT_NEAR_RETURN",
+        "SampleAfterValue": "200003",
+        "BriefDescription": "Speculative and retired indirect return branches.",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "EventCode": "0xC4",
+        "EventCode": "0x88",
         "Counter": "0,1,2,3",
-        "UMask": "0x10",
-        "EventName": "BR_INST_RETIRED.NOT_TAKEN",
-        "SampleAfterValue": "400009",
-        "BriefDescription": "Not taken branch instructions retired.",
+        "UMask": "0xd0",
+        "EventName": "BR_INST_EXEC.ALL_DIRECT_NEAR_CALL",
+        "SampleAfterValue": "200003",
+        "BriefDescription": "Speculative and retired direct near calls.",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "PEBS": "1",
-        "EventCode": "0xC4",
+        "EventCode": "0x88",
         "Counter": "0,1,2,3",
-        "UMask": "0x20",
-        "EventName": "BR_INST_RETIRED.NEAR_TAKEN",
-        "SampleAfterValue": "400009",
-        "BriefDescription": "Taken branch instructions retired.",
+        "UMask": "0xff",
+        "EventName": "BR_INST_EXEC.ALL_BRANCHES",
+        "SampleAfterValue": "200003",
+        "BriefDescription": "Speculative and retired  branches.",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "EventCode": "0xC4",
+        "EventCode": "0x89",
         "Counter": "0,1,2,3",
-        "UMask": "0x40",
-        "EventName": "BR_INST_RETIRED.FAR_BRANCH",
-        "SampleAfterValue": "100007",
-        "BriefDescription": "Far branch instructions retired.",
+        "UMask": "0x41",
+        "EventName": "BR_MISP_EXEC.NONTAKEN_CONDITIONAL",
+        "SampleAfterValue": "200003",
+        "BriefDescription": "Not taken speculative and retired mispredicted macro conditional branches.",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "PEBS": "2",
-        "EventCode": "0xC4",
+        "EventCode": "0x89",
         "Counter": "0,1,2,3",
-        "UMask": "0x4",
-        "EventName": "BR_INST_RETIRED.ALL_BRANCHES_PEBS",
-        "SampleAfterValue": "400009",
-        "BriefDescription": "All (macro) branch instructions retired. (Precise Event - PEBS).",
-        "CounterHTOff": "0,1,2,3"
+        "UMask": "0x81",
+        "EventName": "BR_MISP_EXEC.TAKEN_CONDITIONAL",
+        "SampleAfterValue": "200003",
+        "BriefDescription": "Taken speculative and retired mispredicted macro conditional branches.",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "PEBS": "1",
-        "EventCode": "0xC5",
+        "EventCode": "0x89",
         "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "BR_MISP_RETIRED.CONDITIONAL",
-        "SampleAfterValue": "400009",
-        "BriefDescription": "Mispredicted conditional branch instructions retired.",
+        "UMask": "0x84",
+        "EventName": "BR_MISP_EXEC.TAKEN_INDIRECT_JUMP_NON_CALL_RET",
+        "SampleAfterValue": "200003",
+        "BriefDescription": "Taken speculative and retired mispredicted indirect branches excluding calls and returns.",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "PEBS": "1",
-        "EventCode": "0xC5",
+        "EventCode": "0x89",
         "Counter": "0,1,2,3",
-        "UMask": "0x2",
-        "EventName": "BR_MISP_RETIRED.NEAR_CALL",
-        "SampleAfterValue": "100007",
-        "BriefDescription": "Direct and indirect mispredicted near call instructions retired.",
+        "UMask": "0x88",
+        "EventName": "BR_MISP_EXEC.TAKEN_RETURN_NEAR",
+        "SampleAfterValue": "200003",
+        "BriefDescription": "Taken speculative and retired mispredicted indirect branches with return mnemonic.",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "EventCode": "0xC5",
+        "EventCode": "0x89",
         "Counter": "0,1,2,3",
-        "UMask": "0x0",
-        "EventName": "BR_MISP_RETIRED.ALL_BRANCHES",
-        "SampleAfterValue": "400009",
-        "BriefDescription": "All mispredicted macro branch instructions retired.",
+        "UMask": "0x90",
+        "EventName": "BR_MISP_EXEC.TAKEN_DIRECT_NEAR_CALL",
+        "SampleAfterValue": "200003",
+        "BriefDescription": "Taken speculative and retired mispredicted direct near calls.",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "PEBS": "1",
-        "EventCode": "0xC5",
+        "EventCode": "0x89",
         "Counter": "0,1,2,3",
-        "UMask": "0x10",
-        "EventName": "BR_MISP_RETIRED.NOT_TAKEN",
-        "SampleAfterValue": "400009",
-        "BriefDescription": "Mispredicted not taken branch instructions retired.",
+        "UMask": "0xa0",
+        "EventName": "BR_MISP_EXEC.TAKEN_INDIRECT_NEAR_CALL",
+        "SampleAfterValue": "200003",
+        "BriefDescription": "Taken speculative and retired mispredicted indirect calls.",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "PEBS": "1",
-        "EventCode": "0xC5",
+        "EventCode": "0x89",
         "Counter": "0,1,2,3",
-        "UMask": "0x20",
-        "EventName": "BR_MISP_RETIRED.TAKEN",
-        "SampleAfterValue": "400009",
-        "BriefDescription": "Mispredicted taken branch instructions retired.",
+        "UMask": "0xc1",
+        "EventName": "BR_MISP_EXEC.ALL_CONDITIONAL",
+        "SampleAfterValue": "200003",
+        "BriefDescription": "Speculative and retired mispredicted macro conditional branches.",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "PEBS": "2",
-        "PublicDescription": "Mispredicted macro branch instructions retired. (Precise Event - PEBS)",
-        "EventCode": "0xC5",
+        "EventCode": "0x89",
         "Counter": "0,1,2,3",
-        "UMask": "0x4",
-        "EventName": "BR_MISP_RETIRED.ALL_BRANCHES_PEBS",
-        "SampleAfterValue": "400009",
-        "BriefDescription": "Mispredicted macro branch instructions retired. (Precise Event - PEBS).",
-        "CounterHTOff": "0,1,2,3"
+        "UMask": "0xc4",
+        "EventName": "BR_MISP_EXEC.ALL_INDIRECT_JUMP_NON_CALL_RET",
+        "SampleAfterValue": "200003",
+        "BriefDescription": "Mispredicted indirect branches excluding calls and returns.",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "EventCode": "0xC1",
+        "EventCode": "0x89",
         "Counter": "0,1,2,3",
-        "UMask": "0x2",
-        "EventName": "OTHER_ASSISTS.ITLB_MISS_RETIRED",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "Retired instructions experiencing ITLB misses.",
+        "UMask": "0xd0",
+        "EventName": "BR_MISP_EXEC.ALL_DIRECT_NEAR_CALL",
+        "SampleAfterValue": "200003",
+        "BriefDescription": "Speculative and retired mispredicted direct near calls.",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "EventCode": "0x14",
+        "EventCode": "0x89",
         "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "ARITH.FPU_DIV_ACTIVE",
-        "SampleAfterValue": "2000003",
-        "BriefDescription": "Cycles when divider is busy executing divide operations.",
+        "UMask": "0xff",
+        "EventName": "BR_MISP_EXEC.ALL_BRANCHES",
+        "SampleAfterValue": "200003",
+        "BriefDescription": "Speculative and retired mispredicted macro conditional branches.",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "PublicDescription": "This event counts the number of the divide operations executed.",
-        "EventCode": "0x14",
+        "EventCode": "0xA1",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
-        "EdgeDetect": "1",
-        "EventName": "ARITH.FPU_DIV",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "Divide operations executed.",
-        "CounterMask": "1",
+        "EventName": "UOPS_DISPATCHED_PORT.PORT_0",
+        "SampleAfterValue": "2000003",
+        "BriefDescription": "Cycles per thread when uops are dispatched to port 0.",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "EventCode": "0xB1",
+        "EventCode": "0xA1",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
-        "EventName": "UOPS_DISPATCHED.THREAD",
+        "AnyThread": "1",
+        "EventName": "UOPS_DISPATCHED_PORT.PORT_0_CORE",
         "SampleAfterValue": "2000003",
-        "BriefDescription": "Uops dispatched per thread.",
+        "BriefDescription": "Cycles per core when uops are dispatched to port 0.",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "EventCode": "0xB1",
+        "EventCode": "0xA1",
         "Counter": "0,1,2,3",
         "UMask": "0x2",
-        "EventName": "UOPS_DISPATCHED.CORE",
+        "EventName": "UOPS_DISPATCHED_PORT.PORT_1",
         "SampleAfterValue": "2000003",
-        "BriefDescription": "Uops dispatched from any thread.",
+        "BriefDescription": "Cycles per thread when uops are dispatched to port 1.",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
         "EventCode": "0xA1",
         "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "UOPS_DISPATCHED_PORT.PORT_0",
+        "UMask": "0x2",
+        "AnyThread": "1",
+        "EventName": "UOPS_DISPATCHED_PORT.PORT_1_CORE",
         "SampleAfterValue": "2000003",
-        "BriefDescription": "Cycles per thread when uops are dispatched to port 0.",
+        "BriefDescription": "Cycles per core when uops are dispatched to port 1.",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
         "EventCode": "0xA1",
         "Counter": "0,1,2,3",
-        "UMask": "0x2",
-        "EventName": "UOPS_DISPATCHED_PORT.PORT_1",
+        "UMask": "0xc",
+        "EventName": "UOPS_DISPATCHED_PORT.PORT_2",
         "SampleAfterValue": "2000003",
-        "BriefDescription": "Cycles per thread when uops are dispatched to port 1.",
+        "BriefDescription": "Cycles per thread when load or STA uops are dispatched to port 2.",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
         "EventCode": "0xA1",
         "Counter": "0,1,2,3",
-        "UMask": "0x40",
-        "EventName": "UOPS_DISPATCHED_PORT.PORT_4",
+        "UMask": "0xc",
+        "AnyThread": "1",
+        "EventName": "UOPS_DISPATCHED_PORT.PORT_2_CORE",
         "SampleAfterValue": "2000003",
-        "BriefDescription": "Cycles per thread when uops are dispatched to port 4.",
+        "BriefDescription": "Cycles per core when load or STA uops are dispatched to port 2.",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
         "EventCode": "0xA1",
         "Counter": "0,1,2,3",
-        "UMask": "0x80",
-        "EventName": "UOPS_DISPATCHED_PORT.PORT_5",
+        "UMask": "0x30",
+        "EventName": "UOPS_DISPATCHED_PORT.PORT_3",
         "SampleAfterValue": "2000003",
-        "BriefDescription": "Cycles per thread when uops are dispatched to port 5.",
+        "BriefDescription": "Cycles per thread when load or STA uops are dispatched to port 3.",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "EventCode": "0xA3",
+        "EventCode": "0xA1",
         "Counter": "0,1,2,3",
-        "UMask": "0x4",
-        "EventName": "CYCLE_ACTIVITY.CYCLES_NO_DISPATCH",
+        "UMask": "0x30",
+        "AnyThread": "1",
+        "EventName": "UOPS_DISPATCHED_PORT.PORT_3_CORE",
         "SampleAfterValue": "2000003",
-        "BriefDescription": "Each cycle there was no dispatch for this thread, increment by 1. Note this is connect to Umask 2. No dispatch can be deduced from the UOPS_EXECUTED event.",
-        "CounterMask": "4",
-        "CounterHTOff": "0,1,2,3"
+        "BriefDescription": "Cycles per core when load or STA uops are dispatched to port 3.",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "EventCode": "0xA3",
-        "Counter": "2",
-        "UMask": "0x2",
-        "EventName": "CYCLE_ACTIVITY.CYCLES_L1D_PENDING",
+        "EventCode": "0xA1",
+        "Counter": "0,1,2,3",
+        "UMask": "0x40",
+        "EventName": "UOPS_DISPATCHED_PORT.PORT_4",
         "SampleAfterValue": "2000003",
-        "BriefDescription": "Each cycle there was a miss-pending demand load this thread, increment by 1. Note this is in DCU and connected to Umask 1. Miss Pending demand load should be deduced by OR-ing increment bits of DCACHE_MISS_PEND.PENDING.",
-        "CounterMask": "2",
-        "CounterHTOff": "2"
+        "BriefDescription": "Cycles per thread when uops are dispatched to port 4.",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "EventCode": "0xA3",
+        "EventCode": "0xA1",
         "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "CYCLE_ACTIVITY.CYCLES_L2_PENDING",
+        "UMask": "0x40",
+        "AnyThread": "1",
+        "EventName": "UOPS_DISPATCHED_PORT.PORT_4_CORE",
         "SampleAfterValue": "2000003",
-        "BriefDescription": "Each cycle there was a MLC-miss pending demand load this thread (i.e. Non-completed valid SQ entry allocated for demand load and waiting for Uncore), increment by 1. Note this is in MLC and connected to Umask 0.",
-        "CounterMask": "1",
+        "BriefDescription": "Cycles per core when uops are dispatched to port 4.",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "EventCode": "0xA3",
-        "Counter": "2",
-        "UMask": "0x6",
-        "EventName": "CYCLE_ACTIVITY.STALLS_L1D_PENDING",
+        "EventCode": "0xA1",
+        "Counter": "0,1,2,3",
+        "UMask": "0x80",
+        "EventName": "UOPS_DISPATCHED_PORT.PORT_5",
         "SampleAfterValue": "2000003",
-        "BriefDescription": "Each cycle there was a miss-pending demand load this thread and no uops dispatched, increment by 1. Note this is in DCU and connected to Umask 1 and 2. Miss Pending demand load should be deduced by OR-ing increment bits of DCACHE_MISS_PEND.PENDING.",
-        "CounterMask": "6",
-        "CounterHTOff": "2"
+        "BriefDescription": "Cycles per thread when uops are dispatched to port 5.",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "EventCode": "0xA3",
+        "EventCode": "0xA1",
         "Counter": "0,1,2,3",
-        "UMask": "0x5",
-        "EventName": "CYCLE_ACTIVITY.STALLS_L2_PENDING",
+        "UMask": "0x80",
+        "AnyThread": "1",
+        "EventName": "UOPS_DISPATCHED_PORT.PORT_5_CORE",
         "SampleAfterValue": "2000003",
-        "BriefDescription": "Each cycle there was a MLC-miss pending demand load and no uops dispatched on this thread (i.e. Non-completed valid SQ entry allocated for demand load and waiting for Uncore), increment by 1. Note this is in MLC and connected to Umask 0 and 2.",
-        "CounterMask": "5",
-        "CounterHTOff": "0,1,2,3"
+        "BriefDescription": "Cycles per core when uops are dispatched to port 5.",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "EventCode": "0x4C",
+        "EventCode": "0xA2",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
-        "EventName": "LOAD_HIT_PRE.SW_PF",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "Not software-prefetch load dispatches that hit FB allocated for software prefetch.",
+        "EventName": "RESOURCE_STALLS.ANY",
+        "SampleAfterValue": "2000003",
+        "BriefDescription": "Resource-related stall cycles.",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "EventCode": "0x4C",
+        "EventCode": "0xA2",
         "Counter": "0,1,2,3",
         "UMask": "0x2",
-        "EventName": "LOAD_HIT_PRE.HW_PF",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "Not software-prefetch load dispatches that hit FB allocated for hardware prefetch.",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
-    },
-    {
-        "EventCode": "0x03",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "LD_BLOCKS.DATA_UNKNOWN",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "Loads delayed due to SB blocks, preceding store operations with known addresses but unknown data.",
+        "EventName": "RESOURCE_STALLS.LB",
+        "SampleAfterValue": "2000003",
+        "BriefDescription": "Counts the cycles of stall due to lack of load buffers.",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "PublicDescription": "This event counts loads that followed a store to the same address, where the data could not be forwarded inside the pipeline from the store to the load.  The most common reason why store forwarding would be blocked is when a load's address range overlaps with a preceding smaller uncompleted store.  See the table of not supported store forwards in the Intel? 64 and IA-32 Architectures Optimization Reference Manual.  The penalty for blocked store forwarding is that the load must wait for the store to complete before it can be issued.",
-        "EventCode": "0x03",
+        "EventCode": "0xA2",
         "Counter": "0,1,2,3",
-        "UMask": "0x2",
-        "EventName": "LD_BLOCKS.STORE_FORWARD",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "Cases when loads get true Block-on-Store blocking code preventing store forwarding.",
+        "UMask": "0x4",
+        "EventName": "RESOURCE_STALLS.RS",
+        "SampleAfterValue": "2000003",
+        "BriefDescription": "Cycles stalled due to no eligible RS entry available.",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "EventCode": "0x03",
+        "EventCode": "0xA2",
         "Counter": "0,1,2,3",
         "UMask": "0x8",
-        "EventName": "LD_BLOCKS.NO_SR",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "This event counts the number of times that split load operations are temporarily blocked because all resources for handling the split accesses are in use.",
+        "EventName": "RESOURCE_STALLS.SB",
+        "SampleAfterValue": "2000003",
+        "BriefDescription": "Cycles stalled due to no store buffers available. (not including draining form sync).",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "EventCode": "0x03",
+        "EventCode": "0xA2",
         "Counter": "0,1,2,3",
-        "UMask": "0x10",
-        "EventName": "LD_BLOCKS.ALL_BLOCK",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "Number of cases where any load ends up with a valid block-code written to the load buffer (including blocks due to Memory Order Buffer (MOB), Data Cache Unit (DCU), TLB, but load has no DCU miss).",
+        "UMask": "0xa",
+        "EventName": "RESOURCE_STALLS.LB_SB",
+        "SampleAfterValue": "2000003",
+        "BriefDescription": "Resource stalls due to load or store buffers all being in use.",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "PublicDescription": "Aliasing occurs when a load is issued after a store and their memory addresses are offset by 4K.  This event counts the number of loads that aliased with a preceding store, resulting in an extended address check in the pipeline.  The enhanced address check typically has a performance penalty of 5 cycles.",
-        "EventCode": "0x07",
+        "EventCode": "0xA2",
         "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "LD_BLOCKS_PARTIAL.ADDRESS_ALIAS",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "False dependencies in MOB due to partial compare.",
+        "UMask": "0xe",
+        "EventName": "RESOURCE_STALLS.MEM_RS",
+        "SampleAfterValue": "2000003",
+        "BriefDescription": "Resource stalls due to memory buffers or Reservation Station (RS) being fully utilized.",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "EventCode": "0x07",
+        "EventCode": "0xA2",
         "Counter": "0,1,2,3",
-        "UMask": "0x8",
-        "EventName": "LD_BLOCKS_PARTIAL.ALL_STA_BLOCK",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "This event counts the number of times that load operations are temporarily blocked because of older stores, with addresses that are not yet known. A load operation may incur more than one block of this type.",
+        "UMask": "0x10",
+        "EventName": "RESOURCE_STALLS.ROB",
+        "SampleAfterValue": "2000003",
+        "BriefDescription": "Cycles stalled due to re-order buffer full.",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "EventCode": "0xB6",
+        "EventCode": "0xA2",
         "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "AGU_BYPASS_CANCEL.COUNT",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "This event counts executed load operations with all the following traits: 1. addressing of the format [base + offset], 2. the offset is between 1 and 2047, 3. the address specified in the base register is in one page and the address [base+offset] is in an.",
+        "UMask": "0xf0",
+        "EventName": "RESOURCE_STALLS.OOO_RSRC",
+        "SampleAfterValue": "2000003",
+        "BriefDescription": "Resource stalls due to Rob being full, FCSW, MXCSR and OTHER.",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "EventCode": "0x3C",
+        "EventCode": "0xA3",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
-        "EventName": "CPU_CLK_THREAD_UNHALTED.REF_XCLK",
+        "EventName": "CYCLE_ACTIVITY.CYCLES_L2_PENDING",
         "SampleAfterValue": "2000003",
-        "BriefDescription": "Reference cycles when the thread is unhalted (counts at 100 MHz rate).",
+        "BriefDescription": "Each cycle there was a MLC-miss pending demand load this thread (i.e. Non-completed valid SQ entry allocated for demand load and waiting for Uncore), increment by 1. Note this is in MLC and connected to Umask 0.",
+        "CounterMask": "1",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "EventCode": "0x3C",
-        "Counter": "0,1,2,3",
+        "EventCode": "0xA3",
+        "Counter": "2",
         "UMask": "0x2",
-        "EventName": "CPU_CLK_THREAD_UNHALTED.ONE_THREAD_ACTIVE",
+        "EventName": "CYCLE_ACTIVITY.CYCLES_L1D_PENDING",
         "SampleAfterValue": "2000003",
-        "BriefDescription": "Count XClk pulses when this thread is unhalted and the other is halted.",
-        "CounterHTOff": "0,1,2,3"
+        "BriefDescription": "Each cycle there was a miss-pending demand load this thread, increment by 1. Note this is in DCU and connected to Umask 1. Miss Pending demand load should be deduced by OR-ing increment bits of DCACHE_MISS_PEND.PENDING.",
+        "CounterMask": "2",
+        "CounterHTOff": "2"
     },
     {
-        "EventCode": "0xA1",
+        "EventCode": "0xA3",
         "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "AnyThread": "1",
-        "EventName": "UOPS_DISPATCHED_PORT.PORT_0_CORE",
+        "UMask": "0x4",
+        "EventName": "CYCLE_ACTIVITY.CYCLES_NO_DISPATCH",
         "SampleAfterValue": "2000003",
-        "BriefDescription": "Cycles per core when uops are dispatched to port 0.",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
+        "BriefDescription": "Each cycle there was no dispatch for this thread, increment by 1. Note this is connect to Umask 2. No dispatch can be deduced from the UOPS_EXECUTED event.",
+        "CounterMask": "4",
+        "CounterHTOff": "0,1,2,3"
     },
     {
-        "EventCode": "0xA1",
+        "EventCode": "0xA3",
         "Counter": "0,1,2,3",
-        "UMask": "0x2",
-        "AnyThread": "1",
-        "EventName": "UOPS_DISPATCHED_PORT.PORT_1_CORE",
+        "UMask": "0x5",
+        "EventName": "CYCLE_ACTIVITY.STALLS_L2_PENDING",
         "SampleAfterValue": "2000003",
-        "BriefDescription": "Cycles per core when uops are dispatched to port 1.",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
+        "BriefDescription": "Each cycle there was a MLC-miss pending demand load and no uops dispatched on this thread (i.e. Non-completed valid SQ entry allocated for demand load and waiting for Uncore), increment by 1. Note this is in MLC and connected to Umask 0 and 2.",
+        "CounterMask": "5",
+        "CounterHTOff": "0,1,2,3"
     },
     {
-        "EventCode": "0xA1",
-        "Counter": "0,1,2,3",
-        "UMask": "0x40",
-        "AnyThread": "1",
-        "EventName": "UOPS_DISPATCHED_PORT.PORT_4_CORE",
+        "EventCode": "0xA3",
+        "Counter": "2",
+        "UMask": "0x6",
+        "EventName": "CYCLE_ACTIVITY.STALLS_L1D_PENDING",
         "SampleAfterValue": "2000003",
-        "BriefDescription": "Cycles per core when uops are dispatched to port 4.",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
+        "BriefDescription": "Each cycle there was a miss-pending demand load this thread and no uops dispatched, increment by 1. Note this is in DCU and connected to Umask 1 and 2. Miss Pending demand load should be deduced by OR-ing increment bits of DCACHE_MISS_PEND.PENDING.",
+        "CounterMask": "6",
+        "CounterHTOff": "2"
     },
     {
-        "EventCode": "0xA1",
+        "EventCode": "0xA8",
         "Counter": "0,1,2,3",
-        "UMask": "0x80",
-        "AnyThread": "1",
-        "EventName": "UOPS_DISPATCHED_PORT.PORT_5_CORE",
+        "UMask": "0x1",
+        "EventName": "LSD.UOPS",
         "SampleAfterValue": "2000003",
-        "BriefDescription": "Cycles per core when uops are dispatched to port 5.",
+        "BriefDescription": "Number of Uops delivered by the LSD.",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "EventCode": "0xA1",
+        "EventCode": "0xA8",
         "Counter": "0,1,2,3",
-        "UMask": "0xc",
-        "EventName": "UOPS_DISPATCHED_PORT.PORT_2",
+        "UMask": "0x1",
+        "EventName": "LSD.CYCLES_ACTIVE",
         "SampleAfterValue": "2000003",
-        "BriefDescription": "Cycles per thread when load or STA uops are dispatched to port 2.",
+        "BriefDescription": "Cycles Uops delivered by the LSD, but didn't come from the decoder.",
+        "CounterMask": "1",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "EventCode": "0xA1",
+        "EventCode": "0xA8",
         "Counter": "0,1,2,3",
-        "UMask": "0x30",
-        "EventName": "UOPS_DISPATCHED_PORT.PORT_3",
+        "UMask": "0x1",
+        "EventName": "LSD.CYCLES_4_UOPS",
         "SampleAfterValue": "2000003",
-        "BriefDescription": "Cycles per thread when load or STA uops are dispatched to port 3.",
+        "BriefDescription": "Cycles 4 Uops delivered by the LSD, but didn't come from the decoder.",
+        "CounterMask": "4",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "EventCode": "0xA1",
+        "EventCode": "0xB1",
         "Counter": "0,1,2,3",
-        "UMask": "0xc",
-        "AnyThread": "1",
-        "EventName": "UOPS_DISPATCHED_PORT.PORT_2_CORE",
+        "UMask": "0x1",
+        "EventName": "UOPS_DISPATCHED.THREAD",
         "SampleAfterValue": "2000003",
-        "BriefDescription": "Cycles per core when load or STA uops are dispatched to port 2.",
+        "BriefDescription": "Uops dispatched per thread.",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "EventCode": "0xA1",
+        "EventCode": "0xB1",
         "Counter": "0,1,2,3",
-        "UMask": "0x30",
-        "AnyThread": "1",
-        "EventName": "UOPS_DISPATCHED_PORT.PORT_3_CORE",
+        "UMask": "0x2",
+        "EventName": "UOPS_DISPATCHED.CORE",
         "SampleAfterValue": "2000003",
-        "BriefDescription": "Cycles per core when load or STA uops are dispatched to port 3.",
+        "BriefDescription": "Uops dispatched from any thread.",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "PEBS": "2",
-        "EventCode": "0xC0",
-        "Counter": "1",
-        "UMask": "0x1",
-        "EventName": "INST_RETIRED.PREC_DIST",
-        "SampleAfterValue": "2000003",
-        "BriefDescription": "Instructions retired. (Precise Event - PEBS).",
-        "TakenAlone": "1",
-        "CounterHTOff": "1"
-    },
-    {
-        "EventCode": "0x5B",
+        "EventCode": "0xB1",
         "Counter": "0,1,2,3",
-        "UMask": "0xf",
-        "EventName": "RESOURCE_STALLS2.ALL_PRF_CONTROL",
+        "UMask": "0x2",
+        "EventName": "UOPS_EXECUTED.CORE_CYCLES_GE_1",
         "SampleAfterValue": "2000003",
-        "BriefDescription": "Resource stalls2 control structures full for physical registers.",
+        "BriefDescription": "Cycles at least 1 micro-op is executed from any thread on physical core.",
+        "CounterMask": "1",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "EventCode": "0x5B",
+        "EventCode": "0xB1",
         "Counter": "0,1,2,3",
-        "UMask": "0xc",
-        "EventName": "RESOURCE_STALLS2.ALL_FL_EMPTY",
+        "UMask": "0x2",
+        "EventName": "UOPS_EXECUTED.CORE_CYCLES_GE_2",
         "SampleAfterValue": "2000003",
-        "BriefDescription": "Cycles with either free list is empty.",
+        "BriefDescription": "Cycles at least 2 micro-op is executed from any thread on physical core.",
+        "CounterMask": "2",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "EventCode": "0xA2",
+        "EventCode": "0xB1",
         "Counter": "0,1,2,3",
-        "UMask": "0xe",
-        "EventName": "RESOURCE_STALLS.MEM_RS",
+        "UMask": "0x2",
+        "EventName": "UOPS_EXECUTED.CORE_CYCLES_GE_3",
         "SampleAfterValue": "2000003",
-        "BriefDescription": "Resource stalls due to memory buffers or Reservation Station (RS) being fully utilized.",
+        "BriefDescription": "Cycles at least 3 micro-op is executed from any thread on physical core.",
+        "CounterMask": "3",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "EventCode": "0xA2",
+        "EventCode": "0xB1",
         "Counter": "0,1,2,3",
-        "UMask": "0xf0",
-        "EventName": "RESOURCE_STALLS.OOO_RSRC",
+        "UMask": "0x2",
+        "EventName": "UOPS_EXECUTED.CORE_CYCLES_GE_4",
         "SampleAfterValue": "2000003",
-        "BriefDescription": "Resource stalls due to Rob being full, FCSW, MXCSR and OTHER.",
+        "BriefDescription": "Cycles at least 4 micro-op is executed from any thread on physical core.",
+        "CounterMask": "4",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "EventCode": "0x5B",
+        "EventCode": "0xB1",
+        "Invert": "1",
         "Counter": "0,1,2,3",
-        "UMask": "0x4f",
-        "EventName": "RESOURCE_STALLS2.OOO_RSRC",
+        "UMask": "0x2",
+        "EventName": "UOPS_EXECUTED.CORE_CYCLES_NONE",
         "SampleAfterValue": "2000003",
-        "BriefDescription": "Resource stalls out of order resources full.",
+        "BriefDescription": "Cycles with no micro-ops executed from any thread on physical core.",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "EventCode": "0xA2",
+        "EventCode": "0xB6",
         "Counter": "0,1,2,3",
-        "UMask": "0xa",
-        "EventName": "RESOURCE_STALLS.LB_SB",
-        "SampleAfterValue": "2000003",
-        "BriefDescription": "Resource stalls due to load or store buffers all being in use.",
+        "UMask": "0x1",
+        "EventName": "AGU_BYPASS_CANCEL.COUNT",
+        "SampleAfterValue": "100003",
+        "BriefDescription": "This event counts executed load operations with all the following traits: 1. addressing of the format [base + offset], 2. the offset is between 1 and 2047, 3. the address specified in the base register is in one page and the address [base+offset] is in an.",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "EventCode": "0x0D",
+        "EventCode": "0xC0",
         "Counter": "0,1,2,3",
-        "UMask": "0x3",
-        "EventName": "INT_MISC.RECOVERY_CYCLES",
+        "UMask": "0x0",
+        "EventName": "INST_RETIRED.ANY_P",
         "SampleAfterValue": "2000003",
-        "BriefDescription": "Number of cycles waiting for the checkpoints in Resource Allocation Table (RAT) to be recovered after Nuke due to all other cases except JEClear (e.g. whenever a ucode assist is needed like SSE exception, memory disambiguation, etc...).",
-        "CounterMask": "1",
+        "BriefDescription": "Number of instructions retired. General Counter   - architectural event.",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "PublicDescription": "This event counts the number of cycles spent executing performance-sensitive flags-merging uops. For example, shift CL (merge_arith_flags). For more details, See the Intel? 64 and IA-32 Architectures Optimization Reference Manual.",
-        "EventCode": "0x59",
-        "Counter": "0,1,2,3",
-        "UMask": "0x20",
-        "EventName": "PARTIAL_RAT_STALLS.FLAGS_MERGE_UOP_CYCLES",
+        "PEBS": "2",
+        "EventCode": "0xC0",
+        "Counter": "1",
+        "UMask": "0x1",
+        "EventName": "INST_RETIRED.PREC_DIST",
         "SampleAfterValue": "2000003",
-        "BriefDescription": "Performance sensitive flags-merging uops added by Sandy Bridge u-arch.",
-        "CounterMask": "1",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
+        "BriefDescription": "Instructions retired. (Precise Event - PEBS).",
+        "TakenAlone": "1",
+        "CounterHTOff": "1"
     },
     {
-        "EventCode": "0x0D",
+        "EventCode": "0xC1",
         "Counter": "0,1,2,3",
-        "UMask": "0x3",
-        "EdgeDetect": "1",
-        "EventName": "INT_MISC.RECOVERY_STALLS_COUNT",
-        "SampleAfterValue": "2000003",
-        "BriefDescription": "Number of occurences waiting for the checkpoints in Resource Allocation Table (RAT) to be recovered after Nuke due to all other cases except JEClear (e.g. whenever a ucode assist is needed like SSE exception, memory disambiguation, etc...).",
-        "CounterMask": "1",
+        "UMask": "0x2",
+        "EventName": "OTHER_ASSISTS.ITLB_MISS_RETIRED",
+        "SampleAfterValue": "100003",
+        "BriefDescription": "Retired instructions experiencing ITLB misses.",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "EventCode": "0xE6",
+        "PEBS": "1",
+        "PublicDescription": "This event counts the number of micro-ops retired. (Precise Event)",
+        "EventCode": "0xC2",
         "Counter": "0,1,2,3",
-        "UMask": "0x1f",
-        "EventName": "BACLEARS.ANY",
-        "SampleAfterValue": "100003",
-        "BriefDescription": "Counts the total number when the front end is resteered, mainly when the BPU cannot provide a correct prediction and this is corrected by other branch handling mechanisms at the front end.",
+        "UMask": "0x1",
+        "EventName": "UOPS_RETIRED.ALL",
+        "SampleAfterValue": "2000003",
+        "BriefDescription": "Actually retired uops. (Precise Event - PEBS).",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "EventCode": "0x88",
+        "EventCode": "0xC2",
+        "Invert": "1",
         "Counter": "0,1,2,3",
-        "UMask": "0xff",
-        "EventName": "BR_INST_EXEC.ALL_BRANCHES",
-        "SampleAfterValue": "200003",
-        "BriefDescription": "Speculative and retired  branches.",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
+        "UMask": "0x1",
+        "EventName": "UOPS_RETIRED.STALL_CYCLES",
+        "SampleAfterValue": "2000003",
+        "BriefDescription": "Cycles without actually retired uops.",
+        "CounterMask": "1",
+        "CounterHTOff": "0,1,2,3"
     },
     {
-        "EventCode": "0x89",
+        "EventCode": "0xC2",
+        "Invert": "1",
         "Counter": "0,1,2,3",
-        "UMask": "0xff",
-        "EventName": "BR_MISP_EXEC.ALL_BRANCHES",
-        "SampleAfterValue": "200003",
-        "BriefDescription": "Speculative and retired mispredicted macro conditional branches.",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
+        "UMask": "0x1",
+        "EventName": "UOPS_RETIRED.TOTAL_CYCLES",
+        "SampleAfterValue": "2000003",
+        "BriefDescription": "Cycles with less than 10 actually retired uops.",
+        "CounterMask": "10",
+        "CounterHTOff": "0,1,2,3"
     },
     {
         "EventCode": "0xC2",
@@ -1065,13 +1017,14 @@
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "EventCode": "0xA8",
+        "PEBS": "1",
+        "PublicDescription": "This event counts the number of retirement slots used each cycle.  There are potentially 4 slots that can be used each cycle - meaning, 4 micro-ops or 4 instructions could retire each cycle.  This event is used in determining the 'Retiring' category of the Top-Down pipeline slots characterization. (Precise Event - PEBS)",
+        "EventCode": "0xC2",
         "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "LSD.CYCLES_4_UOPS",
+        "UMask": "0x2",
+        "EventName": "UOPS_RETIRED.RETIRE_SLOTS",
         "SampleAfterValue": "2000003",
-        "BriefDescription": "Cycles 4 Uops delivered by the LSD, but didn't come from the decoder.",
-        "CounterMask": "4",
+        "BriefDescription": "Retirement slots used. (Precise Event - PEBS).",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
@@ -1086,135 +1039,188 @@
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "EventCode": "0x5E",
-        "Invert": "1",
+        "PublicDescription": "This event is incremented when self-modifying code (SMC) is detected, which causes a machine clear.  Machine clears can have a significant performance impact if they are happening frequently.",
+        "EventCode": "0xC3",
         "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EdgeDetect": "1",
-        "EventName": "RS_EVENTS.EMPTY_END",
-        "SampleAfterValue": "2000003",
-        "BriefDescription": "Counts end of periods where the Reservation Station (RS) was empty. Could be useful to precisely locate Frontend Latency Bound issues.",
-        "CounterMask": "1",
+        "UMask": "0x4",
+        "EventName": "MACHINE_CLEARS.SMC",
+        "SampleAfterValue": "100003",
+        "BriefDescription": "Self-modifying code (SMC) detected.",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "EventCode": "0x00",
-        "Counter": "Fixed counter 2",
-        "UMask": "0x2",
-        "AnyThread": "1",
-        "EventName": "CPU_CLK_UNHALTED.THREAD_ANY",
-        "SampleAfterValue": "2000003",
-        "BriefDescription": "Core cycles when at least one thread on the physical core is not in halt state.",
-        "CounterHTOff": "Fixed counter 2"
+        "PublicDescription": "Maskmov false fault - counts number of time ucode passes through Maskmov flow due to instruction's mask being 0 while the flow was completed without raising a fault.",
+        "EventCode": "0xC3",
+        "Counter": "0,1,2,3",
+        "UMask": "0x20",
+        "EventName": "MACHINE_CLEARS.MASKMOV",
+        "SampleAfterValue": "100003",
+        "BriefDescription": "This event counts the number of executed Intel AVX masked load operations that refer to an illegal address range with the mask bits set to 0.",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "EventCode": "0x3C",
+        "EventCode": "0xC4",
         "Counter": "0,1,2,3",
         "UMask": "0x0",
-        "AnyThread": "1",
-        "EventName": "CPU_CLK_UNHALTED.THREAD_P_ANY",
-        "SampleAfterValue": "2000003",
-        "BriefDescription": "Core cycles when at least one thread on the physical core is not in halt state.",
+        "EventName": "BR_INST_RETIRED.ALL_BRANCHES",
+        "SampleAfterValue": "400009",
+        "BriefDescription": "All (macro) branch instructions retired.",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "EventCode": "0x3C",
+        "PEBS": "1",
+        "EventCode": "0xC4",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
-        "AnyThread": "1",
-        "EventName": "CPU_CLK_THREAD_UNHALTED.REF_XCLK_ANY",
-        "SampleAfterValue": "2000003",
-        "BriefDescription": "Reference cycles when the at least one thread on the physical core is unhalted (counts at 100 MHz rate).",
+        "EventName": "BR_INST_RETIRED.CONDITIONAL",
+        "SampleAfterValue": "400009",
+        "BriefDescription": "Conditional branch instructions retired. (Precise Event - PEBS).",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "EventCode": "0x0D",
+        "PEBS": "1",
+        "EventCode": "0xC4",
         "Counter": "0,1,2,3",
-        "UMask": "0x3",
-        "AnyThread": "1",
-        "EventName": "INT_MISC.RECOVERY_CYCLES_ANY",
-        "SampleAfterValue": "2000003",
-        "BriefDescription": "Core cycles the allocator was stalled due to recovery from earlier clear event for any thread running on the physical core (e.g. misprediction or memory nuke).",
-        "CounterMask": "1",
+        "UMask": "0x2",
+        "EventName": "BR_INST_RETIRED.NEAR_CALL",
+        "SampleAfterValue": "100007",
+        "BriefDescription": "Direct and indirect near call instructions retired. (Precise Event - PEBS).",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "EventCode": "0xB1",
+        "PEBS": "1",
+        "EventCode": "0xC4",
         "Counter": "0,1,2,3",
         "UMask": "0x2",
-        "EventName": "UOPS_EXECUTED.CORE_CYCLES_GE_1",
-        "SampleAfterValue": "2000003",
-        "BriefDescription": "Cycles at least 1 micro-op is executed from any thread on physical core.",
-        "CounterMask": "1",
+        "EventName": "BR_INST_RETIRED.NEAR_CALL_R3",
+        "SampleAfterValue": "100007",
+        "BriefDescription": "Direct and indirect macro near call instructions retired (captured in ring 3). (Precise Event - PEBS).",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "EventCode": "0xB1",
+        "PEBS": "2",
+        "EventCode": "0xC4",
         "Counter": "0,1,2,3",
-        "UMask": "0x2",
-        "EventName": "UOPS_EXECUTED.CORE_CYCLES_GE_2",
-        "SampleAfterValue": "2000003",
-        "BriefDescription": "Cycles at least 2 micro-op is executed from any thread on physical core.",
-        "CounterMask": "2",
+        "UMask": "0x4",
+        "EventName": "BR_INST_RETIRED.ALL_BRANCHES_PEBS",
+        "SampleAfterValue": "400009",
+        "BriefDescription": "All (macro) branch instructions retired. (Precise Event - PEBS).",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "PEBS": "1",
+        "EventCode": "0xC4",
+        "Counter": "0,1,2,3",
+        "UMask": "0x8",
+        "EventName": "BR_INST_RETIRED.NEAR_RETURN",
+        "SampleAfterValue": "100007",
+        "BriefDescription": "Return instructions retired. (Precise Event - PEBS).",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "EventCode": "0xB1",
+        "EventCode": "0xC4",
         "Counter": "0,1,2,3",
-        "UMask": "0x2",
-        "EventName": "UOPS_EXECUTED.CORE_CYCLES_GE_3",
-        "SampleAfterValue": "2000003",
-        "BriefDescription": "Cycles at least 3 micro-op is executed from any thread on physical core.",
-        "CounterMask": "3",
+        "UMask": "0x10",
+        "EventName": "BR_INST_RETIRED.NOT_TAKEN",
+        "SampleAfterValue": "400009",
+        "BriefDescription": "Not taken branch instructions retired.",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "EventCode": "0xB1",
+        "PEBS": "1",
+        "EventCode": "0xC4",
         "Counter": "0,1,2,3",
-        "UMask": "0x2",
-        "EventName": "UOPS_EXECUTED.CORE_CYCLES_GE_4",
-        "SampleAfterValue": "2000003",
-        "BriefDescription": "Cycles at least 4 micro-op is executed from any thread on physical core.",
-        "CounterMask": "4",
+        "UMask": "0x20",
+        "EventName": "BR_INST_RETIRED.NEAR_TAKEN",
+        "SampleAfterValue": "400009",
+        "BriefDescription": "Taken branch instructions retired. (Precise Event - PEBS).",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "EventCode": "0xB1",
-        "Invert": "1",
+        "EventCode": "0xC4",
         "Counter": "0,1,2,3",
-        "UMask": "0x2",
-        "EventName": "UOPS_EXECUTED.CORE_CYCLES_NONE",
-        "SampleAfterValue": "2000003",
-        "BriefDescription": "Cycles with no micro-ops executed from any thread on physical core.",
+        "UMask": "0x40",
+        "EventName": "BR_INST_RETIRED.FAR_BRANCH",
+        "SampleAfterValue": "100007",
+        "BriefDescription": "Far branch instructions retired.",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "PublicDescription": "Reference cycles when the thread is unhalted (counts at 100 MHz rate)",
-        "EventCode": "0x3C",
+        "EventCode": "0xC5",
         "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "CPU_CLK_UNHALTED.REF_XCLK",
-        "SampleAfterValue": "2000003",
-        "BriefDescription": "Reference cycles when the thread is unhalted (counts at 100 MHz rate).",
+        "UMask": "0x0",
+        "EventName": "BR_MISP_RETIRED.ALL_BRANCHES",
+        "SampleAfterValue": "400009",
+        "BriefDescription": "All mispredicted macro branch instructions retired.",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "EventCode": "0x3C",
+        "PEBS": "1",
+        "EventCode": "0xC5",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
-        "AnyThread": "1",
-        "EventName": "CPU_CLK_UNHALTED.REF_XCLK_ANY",
-        "SampleAfterValue": "2000003",
-        "BriefDescription": "Reference cycles when the at least one thread on the physical core is unhalted (counts at 100 MHz rate).",
+        "EventName": "BR_MISP_RETIRED.CONDITIONAL",
+        "SampleAfterValue": "400009",
+        "BriefDescription": "Mispredicted conditional branch instructions retired. (Precise Event - PEBS).",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "EventCode": "0x3C",
+        "PEBS": "1",
+        "EventCode": "0xC5",
         "Counter": "0,1,2,3",
         "UMask": "0x2",
-        "EventName": "CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE",
+        "EventName": "BR_MISP_RETIRED.NEAR_CALL",
+        "SampleAfterValue": "100007",
+        "BriefDescription": "Direct and indirect mispredicted near call instructions retired. (Precise Event - PEBS).",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "PEBS": "2",
+        "PublicDescription": "Mispredicted macro branch instructions retired. (Precise Event - PEBS)",
+        "EventCode": "0xC5",
+        "Counter": "0,1,2,3",
+        "UMask": "0x4",
+        "EventName": "BR_MISP_RETIRED.ALL_BRANCHES_PEBS",
+        "SampleAfterValue": "400009",
+        "BriefDescription": "Mispredicted macro branch instructions retired. (Precise Event - PEBS).",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "PEBS": "1",
+        "EventCode": "0xC5",
+        "Counter": "0,1,2,3",
+        "UMask": "0x10",
+        "EventName": "BR_MISP_RETIRED.NOT_TAKEN",
+        "SampleAfterValue": "400009",
+        "BriefDescription": "Mispredicted not taken branch instructions retired.(Precise Event - PEBS).",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "PEBS": "1",
+        "EventCode": "0xC5",
+        "Counter": "0,1,2,3",
+        "UMask": "0x20",
+        "EventName": "BR_MISP_RETIRED.TAKEN",
+        "SampleAfterValue": "400009",
+        "BriefDescription": "Mispredicted taken branch instructions retired. (Precise Event - PEBS).",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0xCC",
+        "Counter": "0,1,2,3",
+        "UMask": "0x20",
+        "EventName": "ROB_MISC_EVENTS.LBR_INSERTS",
         "SampleAfterValue": "2000003",
-        "BriefDescription": "Count XClk pulses when this thread is unhalted and the other thread is halted.",
+        "BriefDescription": "Count cases of saving new LBR.",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0xE6",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1f",
+        "EventName": "BACLEARS.ANY",
+        "SampleAfterValue": "100003",
+        "BriefDescription": "Counts the total number when the front end is resteered, mainly when the BPU cannot provide a correct prediction and this is corrected by other branch handling mechanisms at the front end.",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     }
 ]
\ No newline at end of file
diff --git a/tools/perf/pmu-events/arch/x86/sandybridge/snb-metrics.json b/tools/perf/pmu-events/arch/x86/sandybridge/snb-metrics.json
index fd7d7c438226..cfeba5067bab 100644
--- a/tools/perf/pmu-events/arch/x86/sandybridge/snb-metrics.json
+++ b/tools/perf/pmu-events/arch/x86/sandybridge/snb-metrics.json
@@ -1,140 +1,226 @@
 [
     {
-        "BriefDescription": "Instructions Per Cycle (per logical thread)",
+        "MetricExpr": "IDQ_UOPS_NOT_DELIVERED.CORE / (4 * cycles)",
+        "PublicDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend. Frontend denotes the first part of the processor core responsible to fetch operations that are executed later on by the Backend part. Within the Frontend; a branch predictor predicts the next address to fetch; cache-lines are fetched from the memory subsystem; parsed into instructions; and lastly decoded into micro-ops (uops). Ideally the Frontend can issue 4 uops every cycle to the Backend. Frontend Bound denotes unutilized issue-slots when there is no Backend stall; i.e. bubbles where Frontend delivered no uops while Backend could have accepted them. For example; stalls due to instruction-cache misses would be categorized under Frontend Bound.",
+        "BriefDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend",
+        "MetricGroup": "TopdownL1",
+        "MetricName": "Frontend_Bound"
+    },
+    {
+        "MetricExpr": "IDQ_UOPS_NOT_DELIVERED.CORE / (4 * (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )))",
+        "PublicDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend. Frontend denotes the first part of the processor core responsible to fetch operations that are executed later on by the Backend part. Within the Frontend; a branch predictor predicts the next address to fetch; cache-lines are fetched from the memory subsystem; parsed into instructions; and lastly decoded into micro-ops (uops). Ideally the Frontend can issue 4 uops every cycle to the Backend. Frontend Bound denotes unutilized issue-slots when there is no Backend stall; i.e. bubbles where Frontend delivered no uops while Backend could have accepted them. For example; stalls due to instruction-cache misses would be categorized under Frontend Bound. SMT version; use when SMT is enabled and measuring per logical CPU.",
+        "BriefDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend. SMT version; use when SMT is enabled and measuring per logical CPU.",
+        "MetricGroup": "TopdownL1_SMT",
+        "MetricName": "Frontend_Bound_SMT"
+    },
+    {
+        "MetricExpr": "( UOPS_ISSUED.ANY - UOPS_RETIRED.RETIRE_SLOTS + 4 * INT_MISC.RECOVERY_CYCLES ) / (4 * cycles)",
+        "PublicDescription": "This category represents fraction of slots wasted due to incorrect speculations. This include slots used to issue uops that do not eventually get retired and slots for which the issue-pipeline was blocked due to recovery from earlier incorrect speculation. For example; wasted work due to miss-predicted branches are categorized under Bad Speculation category. Incorrect data speculation followed by Memory Ordering Nukes is another example.",
+        "BriefDescription": "This category represents fraction of slots wasted due to incorrect speculations",
+        "MetricGroup": "TopdownL1",
+        "MetricName": "Bad_Speculation"
+    },
+    {
+        "MetricExpr": "( UOPS_ISSUED.ANY - UOPS_RETIRED.RETIRE_SLOTS + 4 * (( INT_MISC.RECOVERY_CYCLES_ANY / 2 )) ) / (4 * (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )))",
+        "PublicDescription": "This category represents fraction of slots wasted due to incorrect speculations. This include slots used to issue uops that do not eventually get retired and slots for which the issue-pipeline was blocked due to recovery from earlier incorrect speculation. For example; wasted work due to miss-predicted branches are categorized under Bad Speculation category. Incorrect data speculation followed by Memory Ordering Nukes is another example. SMT version; use when SMT is enabled and measuring per logical CPU.",
+        "BriefDescription": "This category represents fraction of slots wasted due to incorrect speculations. SMT version; use when SMT is enabled and measuring per logical CPU.",
+        "MetricGroup": "TopdownL1_SMT",
+        "MetricName": "Bad_Speculation_SMT"
+    },
+    {
+        "MetricExpr": "1 - ( (IDQ_UOPS_NOT_DELIVERED.CORE / (4 * cycles)) + (( UOPS_ISSUED.ANY - UOPS_RETIRED.RETIRE_SLOTS + 4 * INT_MISC.RECOVERY_CYCLES ) / (4 * cycles)) + (UOPS_RETIRED.RETIRE_SLOTS / (4 * cycles)) )",
+        "PublicDescription": "This category represents fraction of slots where no uops are being delivered due to a lack of required resources for accepting new uops in the Backend. Backend is the portion of the processor core where the out-of-order scheduler dispatches ready uops into their respective execution units; and once completed these uops get retired according to program order. For example; stalls due to data-cache misses or stalls due to the divider unit being overloaded are both categorized under Backend Bound. Backend Bound is further divided into two main categories: Memory Bound and Core Bound.",
+        "BriefDescription": "This category represents fraction of slots where no uops are being delivered due to a lack of required resources for accepting new uops in the Backend",
+        "MetricGroup": "TopdownL1",
+        "MetricName": "Backend_Bound"
+    },
+    {
+        "MetricExpr": "1 - ( (IDQ_UOPS_NOT_DELIVERED.CORE / (4 * (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )))) + (( UOPS_ISSUED.ANY - UOPS_RETIRED.RETIRE_SLOTS + 4 * (( INT_MISC.RECOVERY_CYCLES_ANY / 2 )) ) / (4 * (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )))) + (UOPS_RETIRED.RETIRE_SLOTS / (4 * (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )))) )",
+        "PublicDescription": "This category represents fraction of slots where no uops are being delivered due to a lack of required resources for accepting new uops in the Backend. Backend is the portion of the processor core where the out-of-order scheduler dispatches ready uops into their respective execution units; and once completed these uops get retired according to program order. For example; stalls due to data-cache misses or stalls due to the divider unit being overloaded are both categorized under Backend Bound. Backend Bound is further divided into two main categories: Memory Bound and Core Bound. SMT version; use when SMT is enabled and measuring per logical CPU.",
+        "BriefDescription": "This category represents fraction of slots where no uops are being delivered due to a lack of required resources for accepting new uops in the Backend. SMT version; use when SMT is enabled and measuring per logical CPU.",
+        "MetricGroup": "TopdownL1_SMT",
+        "MetricName": "Backend_Bound_SMT"
+    },
+    {
+        "MetricExpr": "UOPS_RETIRED.RETIRE_SLOTS / (4 * cycles)",
+        "PublicDescription": "This category represents fraction of slots utilized by useful work i.e. issued uops that eventually get retired. Ideally; all pipeline slots would be attributed to the Retiring category.  Retiring of 100% would indicate the maximum 4 uops retired per cycle has been achieved.  Maximizing Retiring typically increases the Instruction-Per-Cycle metric. Note that a high Retiring value does not necessary mean there is no room for more performance.  For example; Microcode assists are categorized under Retiring. They hurt performance and can often be avoided. ",
+        "BriefDescription": "This category represents fraction of slots utilized by useful work i.e. issued uops that eventually get retired",
+        "MetricGroup": "TopdownL1",
+        "MetricName": "Retiring"
+    },
+    {
+        "MetricExpr": "UOPS_RETIRED.RETIRE_SLOTS / (4 * (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )))",
+        "PublicDescription": "This category represents fraction of slots utilized by useful work i.e. issued uops that eventually get retired. Ideally; all pipeline slots would be attributed to the Retiring category.  Retiring of 100% would indicate the maximum 4 uops retired per cycle has been achieved.  Maximizing Retiring typically increases the Instruction-Per-Cycle metric. Note that a high Retiring value does not necessary mean there is no room for more performance.  For example; Microcode assists are categorized under Retiring. They hurt performance and can often be avoided. SMT version; use when SMT is enabled and measuring per logical CPU.",
+        "BriefDescription": "This category represents fraction of slots utilized by useful work i.e. issued uops that eventually get retired. SMT version; use when SMT is enabled and measuring per logical CPU.",
+        "MetricGroup": "TopdownL1_SMT",
+        "MetricName": "Retiring_SMT"
+    },
+    {
         "MetricExpr": "INST_RETIRED.ANY / CPU_CLK_UNHALTED.THREAD",
+        "BriefDescription": "Instructions Per Cycle (per logical thread)",
         "MetricGroup": "TopDownL1",
         "MetricName": "IPC"
     },
     {
-        "BriefDescription": "Uops Per Instruction",
         "MetricExpr": "UOPS_RETIRED.RETIRE_SLOTS / INST_RETIRED.ANY",
-        "MetricGroup": "Pipeline",
+        "BriefDescription": "Uops Per Instruction",
+        "MetricGroup": "Pipeline;Retiring",
         "MetricName": "UPI"
     },
     {
-        "BriefDescription": "Rough Estimation of fraction of fetched lines bytes that were likely consumed by program instructions",
-        "MetricExpr": "min( 1 , UOPS_ISSUED.ANY / ( (UOPS_RETIRED.RETIRE_SLOTS / INST_RETIRED.ANY) * 32 * ( ICACHE.HIT + ICACHE.MISSES ) / 4) )",
-        "MetricGroup": "Frontend",
+        "MetricExpr": "min( 1 , UOPS_ISSUED.ANY / ( (UOPS_RETIRED.RETIRE_SLOTS / INST_RETIRED.ANY) * 32 * ( ICACHE.HIT + ICACHE.MISSES ) / 4 ) )",
+        "BriefDescription": "Rough Estimation of fraction of fetched lines bytes that were likely (includes speculatively fetches) consumed by program instructions",
+        "MetricGroup": "PGO",
         "MetricName": "IFetch_Line_Utilization"
     },
     {
-        "BriefDescription": "Fraction of Uops delivered by the DSB (aka Decoded Icache; or Uop Cache)",
-        "MetricExpr": "IDQ.DSB_UOPS / ( IDQ.DSB_UOPS + LSD.UOPS + IDQ.MITE_UOPS + IDQ.MS_UOPS )",
-        "MetricGroup": "DSB; Frontend_Bandwidth",
+        "MetricExpr": "IDQ.DSB_UOPS / (( IDQ.DSB_UOPS + LSD.UOPS + IDQ.MITE_UOPS + IDQ.MS_UOPS ) )",
+        "BriefDescription": "Fraction of Uops delivered by the DSB (aka Decoded ICache; or Uop Cache)",
+        "MetricGroup": "DSB;Frontend_Bandwidth",
         "MetricName": "DSB_Coverage"
     },
     {
-        "BriefDescription": "Cycles Per Instruction (threaded)",
         "MetricExpr": "1 / (INST_RETIRED.ANY / cycles)",
+        "BriefDescription": "Cycles Per Instruction (threaded)",
         "MetricGroup": "Pipeline;Summary",
         "MetricName": "CPI"
     },
     {
-        "BriefDescription": "Per-thread actual clocks when the logical processor is active. This is called 'Clockticks' in VTune.",
         "MetricExpr": "CPU_CLK_UNHALTED.THREAD",
+        "BriefDescription": "Per-thread actual clocks when the logical processor is active.",
         "MetricGroup": "Summary",
         "MetricName": "CLKS"
     },
     {
-        "BriefDescription": "Total issue-pipeline slots",
-        "MetricExpr": "4*(( CPU_CLK_UNHALTED.THREAD_ANY / 2 ) if #SMT_on else cycles)",
+        "MetricExpr": "4 * cycles",
+        "BriefDescription": "Total issue-pipeline slots (per core)",
         "MetricGroup": "TopDownL1",
         "MetricName": "SLOTS"
     },
     {
-        "BriefDescription": "Total number of retired Instructions",
+        "MetricExpr": "4 * (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) ))",
+        "BriefDescription": "Total issue-pipeline slots (per core)",
+        "MetricGroup": "TopDownL1_SMT",
+        "MetricName": "SLOTS_SMT"
+    },
+    {
         "MetricExpr": "INST_RETIRED.ANY",
+        "BriefDescription": "Total number of retired Instructions",
         "MetricGroup": "Summary",
         "MetricName": "Instructions"
     },
     {
+        "MetricExpr": "INST_RETIRED.ANY / cycles",
         "BriefDescription": "Instructions Per Cycle (per physical core)",
-        "MetricExpr": "INST_RETIRED.ANY / (( CPU_CLK_UNHALTED.THREAD_ANY / 2 ) if #SMT_on else cycles)",
         "MetricGroup": "SMT",
         "MetricName": "CoreIPC"
     },
     {
+        "MetricExpr": "INST_RETIRED.ANY / (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) ))",
+        "BriefDescription": "Instructions Per Cycle (per physical core)",
+        "MetricGroup": "SMT",
+        "MetricName": "CoreIPC_SMT"
+    },
+    {
+        "MetricExpr": "(( 1 * ( FP_COMP_OPS_EXE.SSE_SCALAR_SINGLE + FP_COMP_OPS_EXE.SSE_SCALAR_DOUBLE ) + 2 * FP_COMP_OPS_EXE.SSE_PACKED_DOUBLE + 4 * ( FP_COMP_OPS_EXE.SSE_PACKED_SINGLE + SIMD_FP_256.PACKED_DOUBLE ) + 8 * SIMD_FP_256.PACKED_SINGLE )) / cycles",
+        "BriefDescription": "Floating Point Operations Per Cycle",
+        "MetricGroup": "FLOPS",
+        "MetricName": "FLOPc"
+    },
+    {
+        "MetricExpr": "(( 1 * ( FP_COMP_OPS_EXE.SSE_SCALAR_SINGLE + FP_COMP_OPS_EXE.SSE_SCALAR_DOUBLE ) + 2 * FP_COMP_OPS_EXE.SSE_PACKED_DOUBLE + 4 * ( FP_COMP_OPS_EXE.SSE_PACKED_SINGLE + SIMD_FP_256.PACKED_DOUBLE ) + 8 * SIMD_FP_256.PACKED_SINGLE )) / (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) ))",
+        "BriefDescription": "Floating Point Operations Per Cycle",
+        "MetricGroup": "FLOPS_SMT",
+        "MetricName": "FLOPc_SMT"
+    },
+    {
+        "MetricExpr": "UOPS_DISPATCHED.THREAD / (( cpu@UOPS_DISPATCHED.CORE\\,cmask\\=1@ / 2 ) if #SMT_on else cpu@UOPS_DISPATCHED.CORE\\,cmask\\=1@)",
         "BriefDescription": "Instruction-Level-Parallelism (average number of uops executed when there is at least 1 uop executed)",
-        "MetricExpr": "UOPS_DISPATCHED.THREAD / (( cpu@UOPS_DISPATCHED.CORE\\,cmask\\=1@ / 2) if #SMT_on else cpu@UOPS_DISPATCHED.CORE\\,cmask\\=1@)",
         "MetricGroup": "Pipeline;Ports_Utilization",
         "MetricName": "ILP"
     },
     {
+        "MetricExpr": "( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )",
         "BriefDescription": "Core actual clocks when any thread is active on the physical core",
-        "MetricExpr": "( CPU_CLK_UNHALTED.THREAD_ANY / 2 ) if #SMT_on else CPU_CLK_UNHALTED.THREAD",
         "MetricGroup": "SMT",
         "MetricName": "CORE_CLKS"
     },
     {
-        "BriefDescription": "Average CPU Utilization",
         "MetricExpr": "CPU_CLK_UNHALTED.REF_TSC / msr@tsc@",
+        "BriefDescription": "Average CPU Utilization",
         "MetricGroup": "Summary",
         "MetricName": "CPU_Utilization"
     },
     {
+        "MetricExpr": "( (( 1 * ( FP_COMP_OPS_EXE.SSE_SCALAR_SINGLE + FP_COMP_OPS_EXE.SSE_SCALAR_DOUBLE ) + 2 * FP_COMP_OPS_EXE.SSE_PACKED_DOUBLE + 4 * ( FP_COMP_OPS_EXE.SSE_PACKED_SINGLE + SIMD_FP_256.PACKED_DOUBLE ) + 8 * SIMD_FP_256.PACKED_SINGLE )) / 1000000000 ) / duration_time",
         "BriefDescription": "Giga Floating Point Operations Per Second",
-        "MetricExpr": "(( 1*( FP_COMP_OPS_EXE.SSE_SCALAR_SINGLE + FP_COMP_OPS_EXE.SSE_SCALAR_DOUBLE ) + 2* FP_COMP_OPS_EXE.SSE_PACKED_DOUBLE + 4*( FP_COMP_OPS_EXE.SSE_PACKED_SINGLE + SIMD_FP_256.PACKED_DOUBLE ) + 8* SIMD_FP_256.PACKED_SINGLE )) / 1000000000 / duration_time",
         "MetricGroup": "FLOPS;Summary",
         "MetricName": "GFLOPs"
     },
     {
-        "BriefDescription": "Average Frequency Utilization relative nominal frequency",
         "MetricExpr": "CPU_CLK_UNHALTED.THREAD / CPU_CLK_UNHALTED.REF_TSC",
+        "BriefDescription": "Average Frequency Utilization relative nominal frequency",
         "MetricGroup": "Power",
         "MetricName": "Turbo_Utilization"
     },
     {
-        "BriefDescription": "Fraction of cycles where both hardware threads were active",
         "MetricExpr": "1 - CPU_CLK_THREAD_UNHALTED.ONE_THREAD_ACTIVE / ( CPU_CLK_THREAD_UNHALTED.REF_XCLK_ANY / 2 ) if #SMT_on else 0",
+        "BriefDescription": "Fraction of cycles where both hardware threads were active",
         "MetricGroup": "SMT;Summary",
         "MetricName": "SMT_2T_Utilization"
     },
     {
-        "BriefDescription": "Fraction of cycles spent in Kernel mode",
         "MetricExpr": "CPU_CLK_UNHALTED.REF_TSC:u / CPU_CLK_UNHALTED.REF_TSC",
+        "BriefDescription": "Fraction of cycles spent in Kernel mode",
         "MetricGroup": "Summary",
         "MetricName": "Kernel_Utilization"
     },
     {
-        "BriefDescription": "C3 residency percent per core",
+        "MetricExpr": "64 * ( arb@event\\=0x81\\,umask\\=0x1@ + arb@event\\=0x84\\,umask\\=0x1@ ) / 1000000 / duration_time / 1000",
+        "BriefDescription": "Average external Memory Bandwidth Use for reads and writes [GB / sec]",
+        "MetricGroup": "Memory_BW",
+        "MetricName": "DRAM_BW_Use"
+    },
+    {
         "MetricExpr": "(cstate_core@c3\\-residency@ / msr@tsc@) * 100",
         "MetricGroup": "Power",
+        "BriefDescription": "C3 residency percent per core",
         "MetricName": "C3_Core_Residency"
     },
     {
-        "BriefDescription": "C6 residency percent per core",
         "MetricExpr": "(cstate_core@c6\\-residency@ / msr@tsc@) * 100",
         "MetricGroup": "Power",
+        "BriefDescription": "C6 residency percent per core",
         "MetricName": "C6_Core_Residency"
     },
     {
-        "BriefDescription": "C7 residency percent per core",
         "MetricExpr": "(cstate_core@c7\\-residency@ / msr@tsc@) * 100",
         "MetricGroup": "Power",
+        "BriefDescription": "C7 residency percent per core",
         "MetricName": "C7_Core_Residency"
     },
     {
-        "BriefDescription": "C2 residency percent per package",
         "MetricExpr": "(cstate_pkg@c2\\-residency@ / msr@tsc@) * 100",
         "MetricGroup": "Power",
+        "BriefDescription": "C2 residency percent per package",
         "MetricName": "C2_Pkg_Residency"
     },
     {
-        "BriefDescription": "C3 residency percent per package",
         "MetricExpr": "(cstate_pkg@c3\\-residency@ / msr@tsc@) * 100",
         "MetricGroup": "Power",
+        "BriefDescription": "C3 residency percent per package",
         "MetricName": "C3_Pkg_Residency"
     },
     {
-        "BriefDescription": "C6 residency percent per package",
         "MetricExpr": "(cstate_pkg@c6\\-residency@ / msr@tsc@) * 100",
         "MetricGroup": "Power",
+        "BriefDescription": "C6 residency percent per package",
         "MetricName": "C6_Pkg_Residency"
     },
     {
-        "BriefDescription": "C7 residency percent per package",
         "MetricExpr": "(cstate_pkg@c7\\-residency@ / msr@tsc@) * 100",
         "MetricGroup": "Power",
+        "BriefDescription": "C7 residency percent per package",
         "MetricName": "C7_Pkg_Residency"
     }
 ]
diff --git a/tools/perf/pmu-events/arch/x86/sandybridge/virtual-memory.json b/tools/perf/pmu-events/arch/x86/sandybridge/virtual-memory.json
index a654ab771fce..b8eccce5d75d 100644
--- a/tools/perf/pmu-events/arch/x86/sandybridge/virtual-memory.json
+++ b/tools/perf/pmu-events/arch/x86/sandybridge/virtual-memory.json
@@ -1,131 +1,131 @@
 [
     {
-        "EventCode": "0xAE",
-        "Counter": "0,1,2,3",
-        "UMask": "0x1",
-        "EventName": "ITLB.ITLB_FLUSH",
-        "SampleAfterValue": "100007",
-        "BriefDescription": "Flushing of the Instruction TLB (ITLB) pages, includes 4k/2M/4M pages.",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
-    },
-    {
-        "EventCode": "0x4F",
-        "Counter": "0,1,2,3",
-        "UMask": "0x10",
-        "EventName": "EPT.WALK_CYCLES",
-        "SampleAfterValue": "2000003",
-        "BriefDescription": "Cycle count for an Extended Page table walk.  The Extended Page Directory cache is used by Virtual Machine operating systems while the guest operating systems use the standard TLB caches.",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
-    },
-    {
-        "EventCode": "0x85",
+        "EventCode": "0x08",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
-        "EventName": "ITLB_MISSES.MISS_CAUSES_A_WALK",
+        "EventName": "DTLB_LOAD_MISSES.MISS_CAUSES_A_WALK",
         "SampleAfterValue": "100003",
-        "BriefDescription": "Misses at all ITLB levels that cause page walks.",
+        "BriefDescription": "Load misses in all DTLB levels that cause page walks.",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "EventCode": "0x85",
+        "EventCode": "0x08",
         "Counter": "0,1,2,3",
         "UMask": "0x2",
-        "EventName": "ITLB_MISSES.WALK_COMPLETED",
+        "EventName": "DTLB_LOAD_MISSES.WALK_COMPLETED",
         "SampleAfterValue": "100003",
-        "BriefDescription": "Misses in all ITLB levels that cause completed page walks.",
+        "BriefDescription": "Load misses at all DTLB levels that cause completed page walks.",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "PublicDescription": "This event count cycles when Page Miss Handler (PMH) is servicing page walks caused by ITLB misses.",
-        "EventCode": "0x85",
+        "PublicDescription": "This event counts cycles when the  page miss handler (PMH) is servicing page walks caused by DTLB load misses.",
+        "EventCode": "0x08",
         "Counter": "0,1,2,3",
         "UMask": "0x4",
-        "EventName": "ITLB_MISSES.WALK_DURATION",
+        "EventName": "DTLB_LOAD_MISSES.WALK_DURATION",
         "SampleAfterValue": "2000003",
         "BriefDescription": "Cycles when PMH is busy with page walks.",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "EventCode": "0x85",
+        "PublicDescription": "This event counts load operations that miss the first DTLB level but hit the second and do not cause any page walks. The penalty in this case is approximately 7 cycles.",
+        "EventCode": "0x08",
         "Counter": "0,1,2,3",
         "UMask": "0x10",
-        "EventName": "ITLB_MISSES.STLB_HIT",
+        "EventName": "DTLB_LOAD_MISSES.STLB_HIT",
         "SampleAfterValue": "100003",
-        "BriefDescription": "Operations that miss the first ITLB level but hit the second and do not cause any page walks.",
+        "BriefDescription": "Load operations that miss the first DTLB level but hit the second and do not cause page walks.",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "EventCode": "0x08",
+        "EventCode": "0x49",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
-        "EventName": "DTLB_LOAD_MISSES.MISS_CAUSES_A_WALK",
+        "EventName": "DTLB_STORE_MISSES.MISS_CAUSES_A_WALK",
         "SampleAfterValue": "100003",
-        "BriefDescription": "Load misses in all DTLB levels that cause page walks.",
+        "BriefDescription": "Store misses in all DTLB levels that cause page walks.",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "EventCode": "0x08",
+        "EventCode": "0x49",
         "Counter": "0,1,2,3",
         "UMask": "0x2",
-        "EventName": "DTLB_LOAD_MISSES.WALK_COMPLETED",
+        "EventName": "DTLB_STORE_MISSES.WALK_COMPLETED",
         "SampleAfterValue": "100003",
-        "BriefDescription": "Load misses at all DTLB levels that cause completed page walks.",
+        "BriefDescription": "Store misses in all DTLB levels that cause completed page walks.",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "PublicDescription": "This event counts cycles when the  page miss handler (PMH) is servicing page walks caused by DTLB load misses.",
-        "EventCode": "0x08",
+        "EventCode": "0x49",
         "Counter": "0,1,2,3",
         "UMask": "0x4",
-        "EventName": "DTLB_LOAD_MISSES.WALK_DURATION",
+        "EventName": "DTLB_STORE_MISSES.WALK_DURATION",
         "SampleAfterValue": "2000003",
         "BriefDescription": "Cycles when PMH is busy with page walks.",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "PublicDescription": "This event counts load operations that miss the first DTLB level but hit the second and do not cause any page walks. The penalty in this case is approximately 7 cycles.",
-        "EventCode": "0x08",
+        "EventCode": "0x49",
         "Counter": "0,1,2,3",
         "UMask": "0x10",
-        "EventName": "DTLB_LOAD_MISSES.STLB_HIT",
+        "EventName": "DTLB_STORE_MISSES.STLB_HIT",
         "SampleAfterValue": "100003",
-        "BriefDescription": "Load operations that miss the first DTLB level but hit the second and do not cause page walks.",
+        "BriefDescription": "Store operations that miss the first TLB level but hit the second and do not cause page walks.",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "EventCode": "0x49",
+        "EventCode": "0x4F",
+        "Counter": "0,1,2,3",
+        "UMask": "0x10",
+        "EventName": "EPT.WALK_CYCLES",
+        "SampleAfterValue": "2000003",
+        "BriefDescription": "Cycle count for an Extended Page table walk.  The Extended Page Directory cache is used by Virtual Machine operating systems while the guest operating systems use the standard TLB caches.",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0x85",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
-        "EventName": "DTLB_STORE_MISSES.MISS_CAUSES_A_WALK",
+        "EventName": "ITLB_MISSES.MISS_CAUSES_A_WALK",
         "SampleAfterValue": "100003",
-        "BriefDescription": "Store misses in all DTLB levels that cause page walks.",
+        "BriefDescription": "Misses at all ITLB levels that cause page walks.",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "EventCode": "0x49",
+        "EventCode": "0x85",
         "Counter": "0,1,2,3",
         "UMask": "0x2",
-        "EventName": "DTLB_STORE_MISSES.WALK_COMPLETED",
+        "EventName": "ITLB_MISSES.WALK_COMPLETED",
         "SampleAfterValue": "100003",
-        "BriefDescription": "Store misses in all DTLB levels that cause completed page walks.",
+        "BriefDescription": "Misses in all ITLB levels that cause completed page walks.",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "EventCode": "0x49",
+        "PublicDescription": "This event count cycles when Page Miss Handler (PMH) is servicing page walks caused by ITLB misses.",
+        "EventCode": "0x85",
         "Counter": "0,1,2,3",
         "UMask": "0x4",
-        "EventName": "DTLB_STORE_MISSES.WALK_DURATION",
+        "EventName": "ITLB_MISSES.WALK_DURATION",
         "SampleAfterValue": "2000003",
         "BriefDescription": "Cycles when PMH is busy with page walks.",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "EventCode": "0x49",
+        "EventCode": "0x85",
         "Counter": "0,1,2,3",
         "UMask": "0x10",
-        "EventName": "DTLB_STORE_MISSES.STLB_HIT",
+        "EventName": "ITLB_MISSES.STLB_HIT",
         "SampleAfterValue": "100003",
-        "BriefDescription": "Store operations that miss the first TLB level but hit the second and do not cause page walks.",
+        "BriefDescription": "Operations that miss the first ITLB level but hit the second and do not cause any page walks.",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0xAE",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "EventName": "ITLB.ITLB_FLUSH",
+        "SampleAfterValue": "100007",
+        "BriefDescription": "Flushing of the Instruction TLB (ITLB) pages, includes 4k/2M/4M pages.",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
diff --git a/tools/perf/pmu-events/arch/x86/silvermont/cache.json b/tools/perf/pmu-events/arch/x86/silvermont/cache.json
index 82be7d1b8b81..805ef1436539 100644
--- a/tools/perf/pmu-events/arch/x86/silvermont/cache.json
+++ b/tools/perf/pmu-events/arch/x86/silvermont/cache.json
@@ -36,7 +36,7 @@
         "BriefDescription": "L2 cache request misses"
     },
     {
-        "PublicDescription": "Counts cycles that fetch is stalled due to an outstanding ICache miss. That is, the decoder queue is able to accept bytes, but the fetch unit is unable to provide bytes due to an ICache miss.  Note: this event is not the same as the total number of cycles spent retrieving instruction cache lines from the memory hierarchy.\r\nCounts cycles that fetch is stalled due to any reason. That is, the decoder queue is able to accept bytes, but the fetch unit is unable to provide bytes.  This will include cycles due to an ITLB miss, ICache miss and other events. \r\n",
+        "PublicDescription": "Counts cycles that fetch is stalled due to an outstanding ICache miss. That is, the decoder queue is able to accept bytes, but the fetch unit is unable to provide bytes due to an ICache miss.  Note: this event is not the same as the total number of cycles spent retrieving instruction cache lines from the memory hierarchy.\r\nCounts cycles that fetch is stalled due to any reason. That is, the decoder queue is able to accept bytes, but the fetch unit is unable to provide bytes.  This will include cycles due to an ITLB miss, ICache miss and other events.",
         "EventCode": "0x86",
         "Counter": "0,1",
         "UMask": "0x4",
diff --git a/tools/perf/pmu-events/arch/x86/silvermont/other.json b/tools/perf/pmu-events/arch/x86/silvermont/other.json
new file mode 100644
index 000000000000..47814046fa9d
--- /dev/null
+++ b/tools/perf/pmu-events/arch/x86/silvermont/other.json
@@ -0,0 +1,20 @@
+[
+    {
+        "PublicDescription": "Counts cycles that fetch is stalled due to an outstanding ITLB miss. That is, the decoder queue is able to accept bytes, but the fetch unit is unable to provide bytes due to an ITLB miss.  Note: this event is not the same as page walk cycles to retrieve an instruction translation.",
+        "EventCode": "0x86",
+        "Counter": "0,1",
+        "UMask": "0x2",
+        "EventName": "FETCH_STALL.ITLB_FILL_PENDING_CYCLES",
+        "SampleAfterValue": "200003",
+        "BriefDescription": "Cycles code-fetch stalled due to an outstanding ITLB miss."
+    },
+    {
+        "PublicDescription": "Counts cycles that fetch is stalled due to any reason. That is, the decoder queue is able to accept bytes, but the fetch unit is unable to provide bytes.  This will include cycles due to an ITLB miss, ICache miss and other events.",
+        "EventCode": "0x86",
+        "Counter": "0,1",
+        "UMask": "0x3f",
+        "EventName": "FETCH_STALL.ALL",
+        "SampleAfterValue": "200003",
+        "BriefDescription": "Cycles code-fetch stalled due to any reason."
+    }
+]
\ No newline at end of file
diff --git a/tools/perf/pmu-events/arch/x86/silvermont/pipeline.json b/tools/perf/pmu-events/arch/x86/silvermont/pipeline.json
index 7468af99190a..1ed62ad4cf77 100644
--- a/tools/perf/pmu-events/arch/x86/silvermont/pipeline.json
+++ b/tools/perf/pmu-events/arch/x86/silvermont/pipeline.json
@@ -210,7 +210,7 @@
         "UMask": "0x4",
         "EventName": "NO_ALLOC_CYCLES.MISPREDICTS",
         "SampleAfterValue": "200003",
-        "BriefDescription": "Counts the number of cycles when no uops are allocated and the alloc pipe is stalled waiting for a mispredicted jump to retire.  After the misprediction is detected, the front end will start immediately but the allocate pipe stalls until the mispredicted "
+        "BriefDescription": "Counts the number of cycles when no uops are allocated and the alloc pipe is stalled waiting for a mispredicted jump to retire.  After the misprediction is detected, the front end will start immediately but the allocate pipe stalls until the mispredicted"
     },
     {
         "EventCode": "0xCA",
@@ -275,7 +275,6 @@
     },
     {
         "PublicDescription": "This event counts the number of instructions that retire.  For instructions that consist of multiple micro-ops, this event counts exactly once, as the last micro-op of the instruction retires.  The event continues counting while instructions retire, including during interrupt service routines caused by hardware interrupts, faults or traps.  Background: Modern microprocessors employ extensive pipelining and speculative techniques.  Since sometimes an instruction is started but never completed, the notion of \"retirement\" is introduced.  A retired instruction is one that commits its states. Or stated differently, an instruction might be abandoned at some point. No instruction is truly finished until it retires.  This counter measures the number of completed instructions.  The fixed event is INST_RETIRED.ANY and the programmable event is INST_RETIRED.ANY_P.",
-        "EventCode": "0x00",
         "Counter": "Fixed counter 1",
         "UMask": "0x1",
         "EventName": "INST_RETIRED.ANY",
@@ -284,7 +283,6 @@
     },
     {
         "PublicDescription": "Counts the number of core cycles while the core is not in a halt state. The core enters the halt state when it is running the HLT instruction. This event is a component in many key event ratios.  The core frequency may change from time to time. For this reason this event may have a changing ratio with regards to time. In systems with a constant core frequency, this event can give you a measurement of the elapsed time while the core was not in halt state by dividing the event count by the core frequency. This event is architecturally defined and is a designated fixed counter.  CPU_CLK_UNHALTED.CORE and CPU_CLK_UNHALTED.CORE_P use the core frequency which may change from time to time.  CPU_CLK_UNHALTE.REF_TSC and CPU_CLK_UNHALTED.REF are not affected by core frequency changes but counts as if the core is running at the maximum frequency all the time.  The fixed events are CPU_CLK_UNHALTED.CORE and CPU_CLK_UNHALTED.REF_TSC and the programmable events are CPU_CLK_UNHALTED.CORE_P and CPU_CLK_UNHALTED.REF.",
-        "EventCode": "0x00",
         "Counter": "Fixed counter 2",
         "UMask": "0x2",
         "EventName": "CPU_CLK_UNHALTED.CORE",
@@ -293,7 +291,6 @@
     },
     {
         "PublicDescription": "Counts the number of reference cycles while the core is not in a halt state. The core enters the halt state when it is running the HLT instruction. This event is a component in many key event ratios.  The core frequency may change from time. This event is not affected by core frequency changes but counts as if the core is running at the maximum frequency all the time.  Divide this event count by core frequency to determine the elapsed time while the core was not in halt state.  Divide this event count by core frequency to determine the elapsed time while the core was not in halt state.  This event is architecturally defined and is a designated fixed counter.  CPU_CLK_UNHALTED.CORE and CPU_CLK_UNHALTED.CORE_P use the core frequency which may change from time to time.  CPU_CLK_UNHALTE.REF_TSC and CPU_CLK_UNHALTED.REF are not affected by core frequency changes but counts as if the core is running at the maximum frequency all the time.  The fixed events are CPU_CLK_UNHALTED.CORE and CPU_CLK_UNHALTED.REF_TSC and the programmable events are CPU_CLK_UNHALTED.CORE_P and CPU_CLK_UNHALTED.REF.",
-        "EventCode": "0x00",
         "Counter": "Fixed counter 3",
         "UMask": "0x3",
         "EventName": "CPU_CLK_UNHALTED.REF_TSC",
diff --git a/tools/perf/pmu-events/arch/x86/skylake/cache.json b/tools/perf/pmu-events/arch/x86/skylake/cache.json
index 54bfe9e4045c..720458139049 100644
--- a/tools/perf/pmu-events/arch/x86/skylake/cache.json
+++ b/tools/perf/pmu-events/arch/x86/skylake/cache.json
@@ -60,10 +60,10 @@
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "PublicDescription": "Counts the number of demand Data Read requests that hit L2 cache. Only non rejected loads are counted.",
+        "PublicDescription": "Counts the number of demand Data Read requests, initiated by load instructions, that hit L2 cache",
         "EventCode": "0x24",
         "Counter": "0,1,2,3",
-        "UMask": "0x41",
+        "UMask": "0xc1",
         "EventName": "L2_RQSTS.DEMAND_DATA_RD_HIT",
         "SampleAfterValue": "200003",
         "BriefDescription": "Demand Data Read requests that hit L2 cache",
@@ -73,7 +73,7 @@
         "PublicDescription": "Counts the RFO (Read-for-Ownership) requests that hit L2 cache.",
         "EventCode": "0x24",
         "Counter": "0,1,2,3",
-        "UMask": "0x42",
+        "UMask": "0xc2",
         "EventName": "L2_RQSTS.RFO_HIT",
         "SampleAfterValue": "200003",
         "BriefDescription": "RFO requests that hit L2 cache",
@@ -83,7 +83,7 @@
         "PublicDescription": "Counts L2 cache hits when fetching instructions, code reads.",
         "EventCode": "0x24",
         "Counter": "0,1,2,3",
-        "UMask": "0x44",
+        "UMask": "0xc4",
         "EventName": "L2_RQSTS.CODE_RD_HIT",
         "SampleAfterValue": "200003",
         "BriefDescription": "L2 cache hits when fetching instructions, code reads.",
@@ -482,7 +482,7 @@
     },
     {
         "PEBS": "1",
-        "PublicDescription": "Counts retired load instructions with at least one uop that hit in the L1 data cache. This event includes all SW prefetches and lock instructions regardless of the data source.\r\n",
+        "PublicDescription": "Counts retired load instructions with at least one uop that hit in the L1 data cache. This event includes all SW prefetches and lock instructions regardless of the data source.",
         "EventCode": "0xD1",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
@@ -554,7 +554,7 @@
     },
     {
         "PEBS": "1",
-        "PublicDescription": "Counts retired load instructions with at least one uop was load missed in L1 but hit FB (Fill Buffers) due to preceding miss to the same cache line with data not ready. \r\n",
+        "PublicDescription": "Counts retired load instructions with at least one uop was load missed in L1 but hit FB (Fill Buffers) due to preceding miss to the same cache line with data not ready.",
         "EventCode": "0xD1",
         "Counter": "0,1,2,3",
         "UMask": "0x40",
@@ -661,13 +661,13 @@
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "PublicDescription": "Counts the number of lines that have been hardware prefetched but not used and now evicted by L2 cache.",
+        "PublicDescription": "This event is deprecated. Refer to new event L2_LINES_OUT.USELESS_HWPF",
         "EventCode": "0xF2",
         "Counter": "0,1,2,3",
         "UMask": "0x4",
         "EventName": "L2_LINES_OUT.USELESS_PREF",
         "SampleAfterValue": "200003",
-        "BriefDescription": "Counts the number of lines that have been hardware prefetched but not used and now evicted by L2 cache",
+        "BriefDescription": "This event is deprecated. Refer to new event L2_LINES_OUT.USELESS_HWPF",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
@@ -690,249 +690,2238 @@
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts any other requests",
+        "EventCode": "0xB7, 0xBB",
+        "MSRValue": "0x3FC0408000",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "EventName": "OFFCORE_RESPONSE.OTHER.L4_HIT_LOCAL_L4.ANY_SNOOP",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "SampleAfterValue": "100003",
+        "BriefDescription": "Counts any other requests",
+        "Offcore": "1",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "PublicDescription": "Counts any other requests",
+        "EventCode": "0xB7, 0xBB",
+        "MSRValue": "0x1000408000",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "EventName": "OFFCORE_RESPONSE.OTHER.L4_HIT_LOCAL_L4.SNOOP_HITM",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "SampleAfterValue": "100003",
+        "BriefDescription": "Counts any other requests",
+        "Offcore": "1",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "PublicDescription": "Counts any other requests",
+        "EventCode": "0xB7, 0xBB",
+        "MSRValue": "0x0400408000",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "EventName": "OFFCORE_RESPONSE.OTHER.L4_HIT_LOCAL_L4.SNOOP_HIT_NO_FWD",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "SampleAfterValue": "100003",
+        "BriefDescription": "Counts any other requests",
+        "Offcore": "1",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "PublicDescription": "Counts any other requests",
+        "EventCode": "0xB7, 0xBB",
+        "MSRValue": "0x0200408000",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "EventName": "OFFCORE_RESPONSE.OTHER.L4_HIT_LOCAL_L4.SNOOP_MISS",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "SampleAfterValue": "100003",
+        "BriefDescription": "Counts any other requests",
+        "Offcore": "1",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "PublicDescription": "Counts any other requests",
+        "EventCode": "0xB7, 0xBB",
+        "MSRValue": "0x0100408000",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "EventName": "OFFCORE_RESPONSE.OTHER.L4_HIT_LOCAL_L4.SNOOP_NOT_NEEDED",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "SampleAfterValue": "100003",
+        "BriefDescription": "Counts any other requests",
+        "Offcore": "1",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "PublicDescription": "Counts any other requests",
+        "EventCode": "0xB7, 0xBB",
+        "MSRValue": "0x0080408000",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "EventName": "OFFCORE_RESPONSE.OTHER.L4_HIT_LOCAL_L4.SNOOP_NONE",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "SampleAfterValue": "100003",
+        "BriefDescription": "Counts any other requests",
+        "Offcore": "1",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "PublicDescription": "Counts any other requests",
+        "EventCode": "0xB7, 0xBB",
+        "MSRValue": "0x0040408000",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "EventName": "OFFCORE_RESPONSE.OTHER.L4_HIT_LOCAL_L4.SPL_HIT",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "SampleAfterValue": "100003",
+        "BriefDescription": "Counts any other requests",
+        "Offcore": "1",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "PublicDescription": "Counts any other requests",
+        "EventCode": "0xB7, 0xBB",
+        "MSRValue": "0x3FC01C8000",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "EventName": "OFFCORE_RESPONSE.OTHER.L3_HIT.ANY_SNOOP",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "SampleAfterValue": "100003",
+        "BriefDescription": "Counts any other requests",
+        "Offcore": "1",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "PublicDescription": "Counts any other requests",
+        "EventCode": "0xB7, 0xBB",
+        "MSRValue": "0x10001C8000",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "EventName": "OFFCORE_RESPONSE.OTHER.L3_HIT.SNOOP_HITM",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "SampleAfterValue": "100003",
+        "BriefDescription": "Counts any other requests",
+        "Offcore": "1",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "PublicDescription": "Counts any other requests",
+        "EventCode": "0xB7, 0xBB",
+        "MSRValue": "0x04001C8000",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "EventName": "OFFCORE_RESPONSE.OTHER.L3_HIT.SNOOP_HIT_NO_FWD",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "SampleAfterValue": "100003",
+        "BriefDescription": "Counts any other requests",
+        "Offcore": "1",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "PublicDescription": "Counts any other requests",
+        "EventCode": "0xB7, 0xBB",
+        "MSRValue": "0x02001C8000",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "EventName": "OFFCORE_RESPONSE.OTHER.L3_HIT.SNOOP_MISS",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "SampleAfterValue": "100003",
+        "BriefDescription": "Counts any other requests",
+        "Offcore": "1",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "PublicDescription": "Counts any other requests",
+        "EventCode": "0xB7, 0xBB",
+        "MSRValue": "0x01001C8000",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "EventName": "OFFCORE_RESPONSE.OTHER.L3_HIT.SNOOP_NOT_NEEDED",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "SampleAfterValue": "100003",
+        "BriefDescription": "Counts any other requests",
+        "Offcore": "1",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "PublicDescription": "Counts any other requests",
+        "EventCode": "0xB7, 0xBB",
+        "MSRValue": "0x00801C8000",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "EventName": "OFFCORE_RESPONSE.OTHER.L3_HIT.SNOOP_NONE",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "SampleAfterValue": "100003",
+        "BriefDescription": "Counts any other requests",
+        "Offcore": "1",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "PublicDescription": "Counts any other requests",
+        "EventCode": "0xB7, 0xBB",
+        "MSRValue": "0x00401C8000",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "EventName": "OFFCORE_RESPONSE.OTHER.L3_HIT.SPL_HIT",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "SampleAfterValue": "100003",
+        "BriefDescription": "Counts any other requests",
+        "Offcore": "1",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "PublicDescription": "Counts any other requests",
+        "EventCode": "0xB7, 0xBB",
+        "MSRValue": "0x3FC0108000",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "EventName": "OFFCORE_RESPONSE.OTHER.L3_HIT_S.ANY_SNOOP",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "SampleAfterValue": "100003",
+        "BriefDescription": "Counts any other requests",
+        "Offcore": "1",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "PublicDescription": "Counts any other requests",
+        "EventCode": "0xB7, 0xBB",
+        "MSRValue": "0x1000108000",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "EventName": "OFFCORE_RESPONSE.OTHER.L3_HIT_S.SNOOP_HITM",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "SampleAfterValue": "100003",
+        "BriefDescription": "Counts any other requests",
+        "Offcore": "1",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "PublicDescription": "Counts any other requests",
+        "EventCode": "0xB7, 0xBB",
+        "MSRValue": "0x0400108000",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "EventName": "OFFCORE_RESPONSE.OTHER.L3_HIT_S.SNOOP_HIT_NO_FWD",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "SampleAfterValue": "100003",
+        "BriefDescription": "Counts any other requests",
+        "Offcore": "1",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "PublicDescription": "Counts any other requests",
+        "EventCode": "0xB7, 0xBB",
+        "MSRValue": "0x0200108000",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "EventName": "OFFCORE_RESPONSE.OTHER.L3_HIT_S.SNOOP_MISS",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "SampleAfterValue": "100003",
+        "BriefDescription": "Counts any other requests",
+        "Offcore": "1",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "PublicDescription": "Counts any other requests",
+        "EventCode": "0xB7, 0xBB",
+        "MSRValue": "0x0100108000",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "EventName": "OFFCORE_RESPONSE.OTHER.L3_HIT_S.SNOOP_NOT_NEEDED",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "SampleAfterValue": "100003",
+        "BriefDescription": "Counts any other requests",
+        "Offcore": "1",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "PublicDescription": "Counts any other requests",
+        "EventCode": "0xB7, 0xBB",
+        "MSRValue": "0x0080108000",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "EventName": "OFFCORE_RESPONSE.OTHER.L3_HIT_S.SNOOP_NONE",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "SampleAfterValue": "100003",
+        "BriefDescription": "Counts any other requests",
+        "Offcore": "1",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "PublicDescription": "Counts any other requests",
+        "EventCode": "0xB7, 0xBB",
+        "MSRValue": "0x0040108000",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "EventName": "OFFCORE_RESPONSE.OTHER.L3_HIT_S.SPL_HIT",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "SampleAfterValue": "100003",
+        "BriefDescription": "Counts any other requests",
+        "Offcore": "1",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "PublicDescription": "Counts any other requests",
+        "EventCode": "0xB7, 0xBB",
+        "MSRValue": "0x3FC0088000",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "EventName": "OFFCORE_RESPONSE.OTHER.L3_HIT_E.ANY_SNOOP",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "SampleAfterValue": "100003",
+        "BriefDescription": "Counts any other requests",
+        "Offcore": "1",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "PublicDescription": "Counts any other requests",
+        "EventCode": "0xB7, 0xBB",
+        "MSRValue": "0x1000088000",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "EventName": "OFFCORE_RESPONSE.OTHER.L3_HIT_E.SNOOP_HITM",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "SampleAfterValue": "100003",
+        "BriefDescription": "Counts any other requests",
+        "Offcore": "1",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "PublicDescription": "Counts any other requests",
+        "EventCode": "0xB7, 0xBB",
+        "MSRValue": "0x0400088000",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "EventName": "OFFCORE_RESPONSE.OTHER.L3_HIT_E.SNOOP_HIT_NO_FWD",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "SampleAfterValue": "100003",
+        "BriefDescription": "Counts any other requests",
+        "Offcore": "1",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "PublicDescription": "Counts any other requests",
+        "EventCode": "0xB7, 0xBB",
+        "MSRValue": "0x0200088000",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "EventName": "OFFCORE_RESPONSE.OTHER.L3_HIT_E.SNOOP_MISS",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "SampleAfterValue": "100003",
+        "BriefDescription": "Counts any other requests",
+        "Offcore": "1",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "PublicDescription": "Counts any other requests",
+        "EventCode": "0xB7, 0xBB",
+        "MSRValue": "0x0100088000",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "EventName": "OFFCORE_RESPONSE.OTHER.L3_HIT_E.SNOOP_NOT_NEEDED",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "SampleAfterValue": "100003",
+        "BriefDescription": "Counts any other requests",
+        "Offcore": "1",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "PublicDescription": "Counts any other requests",
+        "EventCode": "0xB7, 0xBB",
+        "MSRValue": "0x0080088000",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "EventName": "OFFCORE_RESPONSE.OTHER.L3_HIT_E.SNOOP_NONE",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "SampleAfterValue": "100003",
+        "BriefDescription": "Counts any other requests",
+        "Offcore": "1",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "PublicDescription": "Counts any other requests",
+        "EventCode": "0xB7, 0xBB",
+        "MSRValue": "0x0040088000",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "EventName": "OFFCORE_RESPONSE.OTHER.L3_HIT_E.SPL_HIT",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "SampleAfterValue": "100003",
+        "BriefDescription": "Counts any other requests",
+        "Offcore": "1",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "PublicDescription": "Counts any other requests",
+        "EventCode": "0xB7, 0xBB",
+        "MSRValue": "0x3FC0048000",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "EventName": "OFFCORE_RESPONSE.OTHER.L3_HIT_M.ANY_SNOOP",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "SampleAfterValue": "100003",
+        "BriefDescription": "Counts any other requests",
+        "Offcore": "1",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "PublicDescription": "Counts any other requests",
+        "EventCode": "0xB7, 0xBB",
+        "MSRValue": "0x1000048000",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "EventName": "OFFCORE_RESPONSE.OTHER.L3_HIT_M.SNOOP_HITM",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "SampleAfterValue": "100003",
+        "BriefDescription": "Counts any other requests",
+        "Offcore": "1",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "PublicDescription": "Counts any other requests",
+        "EventCode": "0xB7, 0xBB",
+        "MSRValue": "0x0400048000",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "EventName": "OFFCORE_RESPONSE.OTHER.L3_HIT_M.SNOOP_HIT_NO_FWD",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "SampleAfterValue": "100003",
+        "BriefDescription": "Counts any other requests",
+        "Offcore": "1",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "PublicDescription": "Counts any other requests",
+        "EventCode": "0xB7, 0xBB",
+        "MSRValue": "0x0200048000",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "EventName": "OFFCORE_RESPONSE.OTHER.L3_HIT_M.SNOOP_MISS",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "SampleAfterValue": "100003",
+        "BriefDescription": "Counts any other requests",
+        "Offcore": "1",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "PublicDescription": "Counts any other requests",
+        "EventCode": "0xB7, 0xBB",
+        "MSRValue": "0x0100048000",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "EventName": "OFFCORE_RESPONSE.OTHER.L3_HIT_M.SNOOP_NOT_NEEDED",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "SampleAfterValue": "100003",
+        "BriefDescription": "Counts any other requests",
+        "Offcore": "1",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "PublicDescription": "Counts any other requests",
+        "EventCode": "0xB7, 0xBB",
+        "MSRValue": "0x0080048000",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "EventName": "OFFCORE_RESPONSE.OTHER.L3_HIT_M.SNOOP_NONE",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "SampleAfterValue": "100003",
+        "BriefDescription": "Counts any other requests",
+        "Offcore": "1",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "PublicDescription": "Counts any other requests",
+        "EventCode": "0xB7, 0xBB",
+        "MSRValue": "0x0040048000",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "EventName": "OFFCORE_RESPONSE.OTHER.L3_HIT_M.SPL_HIT",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "SampleAfterValue": "100003",
+        "BriefDescription": "Counts any other requests",
+        "Offcore": "1",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "PublicDescription": "Counts any other requests",
+        "EventCode": "0xB7, 0xBB",
+        "MSRValue": "0x3FC0028000",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "EventName": "OFFCORE_RESPONSE.OTHER.SUPPLIER_NONE.ANY_SNOOP",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "SampleAfterValue": "100003",
+        "BriefDescription": "Counts any other requests",
+        "Offcore": "1",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "PublicDescription": "Counts any other requests",
+        "EventCode": "0xB7, 0xBB",
+        "MSRValue": "0x1000028000",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "EventName": "OFFCORE_RESPONSE.OTHER.SUPPLIER_NONE.SNOOP_HITM",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "SampleAfterValue": "100003",
+        "BriefDescription": "Counts any other requests",
+        "Offcore": "1",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "PublicDescription": "Counts any other requests",
+        "EventCode": "0xB7, 0xBB",
+        "MSRValue": "0x0400028000",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "EventName": "OFFCORE_RESPONSE.OTHER.SUPPLIER_NONE.SNOOP_HIT_NO_FWD",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "SampleAfterValue": "100003",
+        "BriefDescription": "Counts any other requests",
+        "Offcore": "1",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "PublicDescription": "Counts any other requests",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x3fc0400001 ",
+        "MSRValue": "0x0200028000",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "EventName": "OFFCORE_RESPONSE.OTHER.SUPPLIER_NONE.SNOOP_MISS",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "SampleAfterValue": "100003",
+        "BriefDescription": "Counts any other requests",
+        "Offcore": "1",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "PublicDescription": "Counts any other requests",
+        "EventCode": "0xB7, 0xBB",
+        "MSRValue": "0x0100028000",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "EventName": "OFFCORE_RESPONSE.OTHER.SUPPLIER_NONE.SNOOP_NOT_NEEDED",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "SampleAfterValue": "100003",
+        "BriefDescription": "Counts any other requests",
+        "Offcore": "1",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "PublicDescription": "Counts any other requests",
+        "EventCode": "0xB7, 0xBB",
+        "MSRValue": "0x0080028000",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "EventName": "OFFCORE_RESPONSE.OTHER.SUPPLIER_NONE.SNOOP_NONE",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "SampleAfterValue": "100003",
+        "BriefDescription": "Counts any other requests",
+        "Offcore": "1",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "PublicDescription": "Counts any other requests",
+        "EventCode": "0xB7, 0xBB",
+        "MSRValue": "0x0040028000",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "EventName": "OFFCORE_RESPONSE.OTHER.SUPPLIER_NONE.SPL_HIT",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "SampleAfterValue": "100003",
+        "BriefDescription": "Counts any other requests",
+        "Offcore": "1",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "PublicDescription": "Counts any other requests have any response type.",
+        "EventCode": "0xB7, 0xBB",
+        "MSRValue": "0x0000018000",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "EventName": "OFFCORE_RESPONSE.OTHER.ANY_RESPONSE",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "SampleAfterValue": "100003",
+        "BriefDescription": "Counts any other requests have any response type.",
+        "Offcore": "1",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that",
+        "EventCode": "0xB7, 0xBB",
+        "MSRValue": "0x3FC0400004",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L4_HIT_LOCAL_L4.ANY_SNOOP",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "SampleAfterValue": "100003",
+        "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that",
+        "Offcore": "1",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that",
+        "EventCode": "0xB7, 0xBB",
+        "MSRValue": "0x1000400004",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L4_HIT_LOCAL_L4.SNOOP_HITM",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "SampleAfterValue": "100003",
+        "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that",
+        "Offcore": "1",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that",
+        "EventCode": "0xB7, 0xBB",
+        "MSRValue": "0x0400400004",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L4_HIT_LOCAL_L4.SNOOP_HIT_NO_FWD",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "SampleAfterValue": "100003",
+        "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that",
+        "Offcore": "1",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that",
+        "EventCode": "0xB7, 0xBB",
+        "MSRValue": "0x0200400004",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L4_HIT_LOCAL_L4.SNOOP_MISS",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "SampleAfterValue": "100003",
+        "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that",
+        "Offcore": "1",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that",
+        "EventCode": "0xB7, 0xBB",
+        "MSRValue": "0x0100400004",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L4_HIT_LOCAL_L4.SNOOP_NOT_NEEDED",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "SampleAfterValue": "100003",
+        "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that",
+        "Offcore": "1",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that",
+        "EventCode": "0xB7, 0xBB",
+        "MSRValue": "0x0080400004",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L4_HIT_LOCAL_L4.SNOOP_NONE",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "SampleAfterValue": "100003",
+        "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that",
+        "Offcore": "1",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that",
+        "EventCode": "0xB7, 0xBB",
+        "MSRValue": "0x0040400004",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L4_HIT_LOCAL_L4.SPL_HIT",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "SampleAfterValue": "100003",
+        "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that",
+        "Offcore": "1",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that",
+        "EventCode": "0xB7, 0xBB",
+        "MSRValue": "0x3FC01C0004",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_HIT.ANY_SNOOP",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "SampleAfterValue": "100003",
+        "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that",
+        "Offcore": "1",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that",
+        "EventCode": "0xB7, 0xBB",
+        "MSRValue": "0x10001C0004",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_HIT.SNOOP_HITM",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "SampleAfterValue": "100003",
+        "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that",
+        "Offcore": "1",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that",
+        "EventCode": "0xB7, 0xBB",
+        "MSRValue": "0x04001C0004",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_HIT.SNOOP_HIT_NO_FWD",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "SampleAfterValue": "100003",
+        "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that",
+        "Offcore": "1",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that",
+        "EventCode": "0xB7, 0xBB",
+        "MSRValue": "0x02001C0004",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_HIT.SNOOP_MISS",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "SampleAfterValue": "100003",
+        "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that",
+        "Offcore": "1",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that",
+        "EventCode": "0xB7, 0xBB",
+        "MSRValue": "0x01001C0004",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_HIT.SNOOP_NOT_NEEDED",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "SampleAfterValue": "100003",
+        "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that",
+        "Offcore": "1",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that",
+        "EventCode": "0xB7, 0xBB",
+        "MSRValue": "0x00801C0004",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_HIT.SNOOP_NONE",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "SampleAfterValue": "100003",
+        "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that",
+        "Offcore": "1",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that",
+        "EventCode": "0xB7, 0xBB",
+        "MSRValue": "0x00401C0004",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_HIT.SPL_HIT",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "SampleAfterValue": "100003",
+        "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that",
+        "Offcore": "1",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that",
+        "EventCode": "0xB7, 0xBB",
+        "MSRValue": "0x3FC0100004",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_HIT_S.ANY_SNOOP",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "SampleAfterValue": "100003",
+        "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that",
+        "Offcore": "1",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that",
+        "EventCode": "0xB7, 0xBB",
+        "MSRValue": "0x1000100004",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_HIT_S.SNOOP_HITM",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "SampleAfterValue": "100003",
+        "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that",
+        "Offcore": "1",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that",
+        "EventCode": "0xB7, 0xBB",
+        "MSRValue": "0x0400100004",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_HIT_S.SNOOP_HIT_NO_FWD",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "SampleAfterValue": "100003",
+        "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that",
+        "Offcore": "1",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that",
+        "EventCode": "0xB7, 0xBB",
+        "MSRValue": "0x0200100004",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_HIT_S.SNOOP_MISS",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "SampleAfterValue": "100003",
+        "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that",
+        "Offcore": "1",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that",
+        "EventCode": "0xB7, 0xBB",
+        "MSRValue": "0x0100100004",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_HIT_S.SNOOP_NOT_NEEDED",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "SampleAfterValue": "100003",
+        "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that",
+        "Offcore": "1",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that",
+        "EventCode": "0xB7, 0xBB",
+        "MSRValue": "0x0080100004",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_HIT_S.SNOOP_NONE",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "SampleAfterValue": "100003",
+        "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that",
+        "Offcore": "1",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that",
+        "EventCode": "0xB7, 0xBB",
+        "MSRValue": "0x0040100004",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_HIT_S.SPL_HIT",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "SampleAfterValue": "100003",
+        "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that",
+        "Offcore": "1",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that",
+        "EventCode": "0xB7, 0xBB",
+        "MSRValue": "0x3FC0080004",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_HIT_E.ANY_SNOOP",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "SampleAfterValue": "100003",
+        "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that",
+        "Offcore": "1",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that",
+        "EventCode": "0xB7, 0xBB",
+        "MSRValue": "0x1000080004",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_HIT_E.SNOOP_HITM",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "SampleAfterValue": "100003",
+        "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that",
+        "Offcore": "1",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that",
+        "EventCode": "0xB7, 0xBB",
+        "MSRValue": "0x0400080004",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_HIT_E.SNOOP_HIT_NO_FWD",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "SampleAfterValue": "100003",
+        "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that",
+        "Offcore": "1",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that",
+        "EventCode": "0xB7, 0xBB",
+        "MSRValue": "0x0200080004",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_HIT_E.SNOOP_MISS",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "SampleAfterValue": "100003",
+        "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that",
+        "Offcore": "1",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that",
+        "EventCode": "0xB7, 0xBB",
+        "MSRValue": "0x0100080004",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_HIT_E.SNOOP_NOT_NEEDED",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "SampleAfterValue": "100003",
+        "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that",
+        "Offcore": "1",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that",
+        "EventCode": "0xB7, 0xBB",
+        "MSRValue": "0x0080080004",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_HIT_E.SNOOP_NONE",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "SampleAfterValue": "100003",
+        "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that",
+        "Offcore": "1",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that",
+        "EventCode": "0xB7, 0xBB",
+        "MSRValue": "0x0040080004",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_HIT_E.SPL_HIT",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "SampleAfterValue": "100003",
+        "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that",
+        "Offcore": "1",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that",
+        "EventCode": "0xB7, 0xBB",
+        "MSRValue": "0x3FC0040004",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_HIT_M.ANY_SNOOP",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "SampleAfterValue": "100003",
+        "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that",
+        "Offcore": "1",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that",
+        "EventCode": "0xB7, 0xBB",
+        "MSRValue": "0x1000040004",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_HIT_M.SNOOP_HITM",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "SampleAfterValue": "100003",
+        "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that",
+        "Offcore": "1",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that",
+        "EventCode": "0xB7, 0xBB",
+        "MSRValue": "0x0400040004",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_HIT_M.SNOOP_HIT_NO_FWD",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "SampleAfterValue": "100003",
+        "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that",
+        "Offcore": "1",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that",
+        "EventCode": "0xB7, 0xBB",
+        "MSRValue": "0x0200040004",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_HIT_M.SNOOP_MISS",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "SampleAfterValue": "100003",
+        "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that",
+        "Offcore": "1",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that",
+        "EventCode": "0xB7, 0xBB",
+        "MSRValue": "0x0100040004",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_HIT_M.SNOOP_NOT_NEEDED",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "SampleAfterValue": "100003",
+        "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that",
+        "Offcore": "1",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that",
+        "EventCode": "0xB7, 0xBB",
+        "MSRValue": "0x0080040004",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_HIT_M.SNOOP_NONE",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "SampleAfterValue": "100003",
+        "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that",
+        "Offcore": "1",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that",
+        "EventCode": "0xB7, 0xBB",
+        "MSRValue": "0x0040040004",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_HIT_M.SPL_HIT",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "SampleAfterValue": "100003",
+        "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that",
+        "Offcore": "1",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that",
+        "EventCode": "0xB7, 0xBB",
+        "MSRValue": "0x3FC0020004",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.SUPPLIER_NONE.ANY_SNOOP",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "SampleAfterValue": "100003",
+        "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that",
+        "Offcore": "1",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that",
+        "EventCode": "0xB7, 0xBB",
+        "MSRValue": "0x1000020004",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.SUPPLIER_NONE.SNOOP_HITM",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "SampleAfterValue": "100003",
+        "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that",
+        "Offcore": "1",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that",
+        "EventCode": "0xB7, 0xBB",
+        "MSRValue": "0x0400020004",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.SUPPLIER_NONE.SNOOP_HIT_NO_FWD",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "SampleAfterValue": "100003",
+        "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that",
+        "Offcore": "1",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that",
+        "EventCode": "0xB7, 0xBB",
+        "MSRValue": "0x0200020004",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.SUPPLIER_NONE.SNOOP_MISS",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "SampleAfterValue": "100003",
+        "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that",
+        "Offcore": "1",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that",
+        "EventCode": "0xB7, 0xBB",
+        "MSRValue": "0x0100020004",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.SUPPLIER_NONE.SNOOP_NOT_NEEDED",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "SampleAfterValue": "100003",
+        "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that",
+        "Offcore": "1",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that",
+        "EventCode": "0xB7, 0xBB",
+        "MSRValue": "0x0080020004",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.SUPPLIER_NONE.SNOOP_NONE",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "SampleAfterValue": "100003",
+        "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that",
+        "Offcore": "1",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that",
+        "EventCode": "0xB7, 0xBB",
+        "MSRValue": "0x0040020004",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.SUPPLIER_NONE.SPL_HIT",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "SampleAfterValue": "100003",
+        "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that",
+        "Offcore": "1",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that have any response type.",
+        "EventCode": "0xB7, 0xBB",
+        "MSRValue": "0x0000010004",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.ANY_RESPONSE",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "SampleAfterValue": "100003",
+        "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that have any response type.",
+        "Offcore": "1",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "PublicDescription": "Counts all demand data writes (RFOs)",
+        "EventCode": "0xB7, 0xBB",
+        "MSRValue": "0x3FC0400002",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L4_HIT_LOCAL_L4.ANY_SNOOP",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "SampleAfterValue": "100003",
+        "BriefDescription": "Counts all demand data writes (RFOs)",
+        "Offcore": "1",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "PublicDescription": "Counts all demand data writes (RFOs)",
+        "EventCode": "0xB7, 0xBB",
+        "MSRValue": "0x1000400002",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L4_HIT_LOCAL_L4.SNOOP_HITM",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "SampleAfterValue": "100003",
+        "BriefDescription": "Counts all demand data writes (RFOs)",
+        "Offcore": "1",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "PublicDescription": "Counts all demand data writes (RFOs)",
+        "EventCode": "0xB7, 0xBB",
+        "MSRValue": "0x0400400002",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L4_HIT_LOCAL_L4.SNOOP_HIT_NO_FWD",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "SampleAfterValue": "100003",
+        "BriefDescription": "Counts all demand data writes (RFOs)",
+        "Offcore": "1",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "PublicDescription": "Counts all demand data writes (RFOs)",
+        "EventCode": "0xB7, 0xBB",
+        "MSRValue": "0x0200400002",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L4_HIT_LOCAL_L4.SNOOP_MISS",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "SampleAfterValue": "100003",
+        "BriefDescription": "Counts all demand data writes (RFOs)",
+        "Offcore": "1",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "PublicDescription": "Counts all demand data writes (RFOs)",
+        "EventCode": "0xB7, 0xBB",
+        "MSRValue": "0x0100400002",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L4_HIT_LOCAL_L4.SNOOP_NOT_NEEDED",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "SampleAfterValue": "100003",
+        "BriefDescription": "Counts all demand data writes (RFOs)",
+        "Offcore": "1",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "PublicDescription": "Counts all demand data writes (RFOs)",
+        "EventCode": "0xB7, 0xBB",
+        "MSRValue": "0x0080400002",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L4_HIT_LOCAL_L4.SNOOP_NONE",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "SampleAfterValue": "100003",
+        "BriefDescription": "Counts all demand data writes (RFOs)",
+        "Offcore": "1",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "PublicDescription": "Counts all demand data writes (RFOs)",
+        "EventCode": "0xB7, 0xBB",
+        "MSRValue": "0x0040400002",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L4_HIT_LOCAL_L4.SPL_HIT",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "SampleAfterValue": "100003",
+        "BriefDescription": "Counts all demand data writes (RFOs)",
+        "Offcore": "1",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "PublicDescription": "Counts all demand data writes (RFOs)",
+        "EventCode": "0xB7, 0xBB",
+        "MSRValue": "0x3FC01C0002",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_HIT.ANY_SNOOP",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "SampleAfterValue": "100003",
+        "BriefDescription": "Counts all demand data writes (RFOs)",
+        "Offcore": "1",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "PublicDescription": "Counts all demand data writes (RFOs)",
+        "EventCode": "0xB7, 0xBB",
+        "MSRValue": "0x10001C0002",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_HIT.SNOOP_HITM",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "SampleAfterValue": "100003",
+        "BriefDescription": "Counts all demand data writes (RFOs)",
+        "Offcore": "1",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "PublicDescription": "Counts all demand data writes (RFOs)",
+        "EventCode": "0xB7, 0xBB",
+        "MSRValue": "0x04001C0002",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_HIT.SNOOP_HIT_NO_FWD",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "SampleAfterValue": "100003",
+        "BriefDescription": "Counts all demand data writes (RFOs)",
+        "Offcore": "1",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "PublicDescription": "Counts all demand data writes (RFOs)",
+        "EventCode": "0xB7, 0xBB",
+        "MSRValue": "0x02001C0002",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_HIT.SNOOP_MISS",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "SampleAfterValue": "100003",
+        "BriefDescription": "Counts all demand data writes (RFOs)",
+        "Offcore": "1",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "PublicDescription": "Counts all demand data writes (RFOs)",
+        "EventCode": "0xB7, 0xBB",
+        "MSRValue": "0x01001C0002",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_HIT.SNOOP_NOT_NEEDED",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "SampleAfterValue": "100003",
+        "BriefDescription": "Counts all demand data writes (RFOs)",
+        "Offcore": "1",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "PublicDescription": "Counts all demand data writes (RFOs)",
+        "EventCode": "0xB7, 0xBB",
+        "MSRValue": "0x00801C0002",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_HIT.SNOOP_NONE",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "SampleAfterValue": "100003",
+        "BriefDescription": "Counts all demand data writes (RFOs)",
+        "Offcore": "1",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "PublicDescription": "Counts all demand data writes (RFOs)",
+        "EventCode": "0xB7, 0xBB",
+        "MSRValue": "0x00401C0002",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_HIT.SPL_HIT",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "SampleAfterValue": "100003",
+        "BriefDescription": "Counts all demand data writes (RFOs)",
+        "Offcore": "1",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "PublicDescription": "Counts all demand data writes (RFOs)",
+        "EventCode": "0xB7, 0xBB",
+        "MSRValue": "0x3FC0100002",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_HIT_S.ANY_SNOOP",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "SampleAfterValue": "100003",
+        "BriefDescription": "Counts all demand data writes (RFOs)",
+        "Offcore": "1",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "PublicDescription": "Counts all demand data writes (RFOs)",
+        "EventCode": "0xB7, 0xBB",
+        "MSRValue": "0x1000100002",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_HIT_S.SNOOP_HITM",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "SampleAfterValue": "100003",
+        "BriefDescription": "Counts all demand data writes (RFOs)",
+        "Offcore": "1",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "PublicDescription": "Counts all demand data writes (RFOs)",
+        "EventCode": "0xB7, 0xBB",
+        "MSRValue": "0x0400100002",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_HIT_S.SNOOP_HIT_NO_FWD",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "SampleAfterValue": "100003",
+        "BriefDescription": "Counts all demand data writes (RFOs)",
+        "Offcore": "1",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "PublicDescription": "Counts all demand data writes (RFOs)",
+        "EventCode": "0xB7, 0xBB",
+        "MSRValue": "0x0200100002",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_HIT_S.SNOOP_MISS",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "SampleAfterValue": "100003",
+        "BriefDescription": "Counts all demand data writes (RFOs)",
+        "Offcore": "1",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "PublicDescription": "Counts all demand data writes (RFOs)",
+        "EventCode": "0xB7, 0xBB",
+        "MSRValue": "0x0100100002",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_HIT_S.SNOOP_NOT_NEEDED",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "SampleAfterValue": "100003",
+        "BriefDescription": "Counts all demand data writes (RFOs)",
+        "Offcore": "1",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "PublicDescription": "Counts all demand data writes (RFOs)",
+        "EventCode": "0xB7, 0xBB",
+        "MSRValue": "0x0080100002",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_HIT_S.SNOOP_NONE",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "SampleAfterValue": "100003",
+        "BriefDescription": "Counts all demand data writes (RFOs)",
+        "Offcore": "1",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "PublicDescription": "Counts all demand data writes (RFOs)",
+        "EventCode": "0xB7, 0xBB",
+        "MSRValue": "0x0040100002",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_HIT_S.SPL_HIT",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "SampleAfterValue": "100003",
+        "BriefDescription": "Counts all demand data writes (RFOs)",
+        "Offcore": "1",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "PublicDescription": "Counts all demand data writes (RFOs)",
+        "EventCode": "0xB7, 0xBB",
+        "MSRValue": "0x3FC0080002",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_HIT_E.ANY_SNOOP",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "SampleAfterValue": "100003",
+        "BriefDescription": "Counts all demand data writes (RFOs)",
+        "Offcore": "1",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "PublicDescription": "Counts all demand data writes (RFOs)",
+        "EventCode": "0xB7, 0xBB",
+        "MSRValue": "0x1000080002",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_HIT_E.SNOOP_HITM",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "SampleAfterValue": "100003",
+        "BriefDescription": "Counts all demand data writes (RFOs)",
+        "Offcore": "1",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "PublicDescription": "Counts all demand data writes (RFOs)",
+        "EventCode": "0xB7, 0xBB",
+        "MSRValue": "0x0400080002",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_HIT_E.SNOOP_HIT_NO_FWD",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "SampleAfterValue": "100003",
+        "BriefDescription": "Counts all demand data writes (RFOs)",
+        "Offcore": "1",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "PublicDescription": "Counts all demand data writes (RFOs)",
+        "EventCode": "0xB7, 0xBB",
+        "MSRValue": "0x0200080002",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_HIT_E.SNOOP_MISS",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "SampleAfterValue": "100003",
+        "BriefDescription": "Counts all demand data writes (RFOs)",
+        "Offcore": "1",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "PublicDescription": "Counts all demand data writes (RFOs)",
+        "EventCode": "0xB7, 0xBB",
+        "MSRValue": "0x0100080002",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_HIT_E.SNOOP_NOT_NEEDED",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "SampleAfterValue": "100003",
+        "BriefDescription": "Counts all demand data writes (RFOs)",
+        "Offcore": "1",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "PublicDescription": "Counts all demand data writes (RFOs)",
+        "EventCode": "0xB7, 0xBB",
+        "MSRValue": "0x0080080002",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_HIT_E.SNOOP_NONE",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "SampleAfterValue": "100003",
+        "BriefDescription": "Counts all demand data writes (RFOs)",
+        "Offcore": "1",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "PublicDescription": "Counts all demand data writes (RFOs)",
+        "EventCode": "0xB7, 0xBB",
+        "MSRValue": "0x0040080002",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_HIT_E.SPL_HIT",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "SampleAfterValue": "100003",
+        "BriefDescription": "Counts all demand data writes (RFOs)",
+        "Offcore": "1",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "PublicDescription": "Counts all demand data writes (RFOs)",
+        "EventCode": "0xB7, 0xBB",
+        "MSRValue": "0x3FC0040002",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_HIT_M.ANY_SNOOP",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "SampleAfterValue": "100003",
+        "BriefDescription": "Counts all demand data writes (RFOs)",
+        "Offcore": "1",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "PublicDescription": "Counts all demand data writes (RFOs)",
+        "EventCode": "0xB7, 0xBB",
+        "MSRValue": "0x1000040002",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_HIT_M.SNOOP_HITM",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "SampleAfterValue": "100003",
+        "BriefDescription": "Counts all demand data writes (RFOs)",
+        "Offcore": "1",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "PublicDescription": "Counts all demand data writes (RFOs)",
+        "EventCode": "0xB7, 0xBB",
+        "MSRValue": "0x0400040002",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_HIT_M.SNOOP_HIT_NO_FWD",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "SampleAfterValue": "100003",
+        "BriefDescription": "Counts all demand data writes (RFOs)",
+        "Offcore": "1",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "PublicDescription": "Counts all demand data writes (RFOs)",
+        "EventCode": "0xB7, 0xBB",
+        "MSRValue": "0x0200040002",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_HIT_M.SNOOP_MISS",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "SampleAfterValue": "100003",
+        "BriefDescription": "Counts all demand data writes (RFOs)",
+        "Offcore": "1",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "PublicDescription": "Counts all demand data writes (RFOs)",
+        "EventCode": "0xB7, 0xBB",
+        "MSRValue": "0x0100040002",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_HIT_M.SNOOP_NOT_NEEDED",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "SampleAfterValue": "100003",
+        "BriefDescription": "Counts all demand data writes (RFOs)",
+        "Offcore": "1",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "PublicDescription": "Counts all demand data writes (RFOs)",
+        "EventCode": "0xB7, 0xBB",
+        "MSRValue": "0x0080040002",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_HIT_M.SNOOP_NONE",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "SampleAfterValue": "100003",
+        "BriefDescription": "Counts all demand data writes (RFOs)",
+        "Offcore": "1",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "PublicDescription": "Counts all demand data writes (RFOs)",
+        "EventCode": "0xB7, 0xBB",
+        "MSRValue": "0x0040040002",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_HIT_M.SPL_HIT",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "SampleAfterValue": "100003",
+        "BriefDescription": "Counts all demand data writes (RFOs)",
+        "Offcore": "1",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "PublicDescription": "Counts all demand data writes (RFOs)",
+        "EventCode": "0xB7, 0xBB",
+        "MSRValue": "0x3FC0020002",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.SUPPLIER_NONE.ANY_SNOOP",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "SampleAfterValue": "100003",
+        "BriefDescription": "Counts all demand data writes (RFOs)",
+        "Offcore": "1",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "PublicDescription": "Counts all demand data writes (RFOs)",
+        "EventCode": "0xB7, 0xBB",
+        "MSRValue": "0x1000020002",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.SUPPLIER_NONE.SNOOP_HITM",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "SampleAfterValue": "100003",
+        "BriefDescription": "Counts all demand data writes (RFOs)",
+        "Offcore": "1",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "PublicDescription": "Counts all demand data writes (RFOs)",
+        "EventCode": "0xB7, 0xBB",
+        "MSRValue": "0x0400020002",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.SUPPLIER_NONE.SNOOP_HIT_NO_FWD",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "SampleAfterValue": "100003",
+        "BriefDescription": "Counts all demand data writes (RFOs)",
+        "Offcore": "1",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "PublicDescription": "Counts all demand data writes (RFOs)",
+        "EventCode": "0xB7, 0xBB",
+        "MSRValue": "0x0200020002",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.SUPPLIER_NONE.SNOOP_MISS",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "SampleAfterValue": "100003",
+        "BriefDescription": "Counts all demand data writes (RFOs)",
+        "Offcore": "1",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "PublicDescription": "Counts all demand data writes (RFOs)",
+        "EventCode": "0xB7, 0xBB",
+        "MSRValue": "0x0100020002",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.SUPPLIER_NONE.SNOOP_NOT_NEEDED",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "SampleAfterValue": "100003",
+        "BriefDescription": "Counts all demand data writes (RFOs)",
+        "Offcore": "1",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "PublicDescription": "Counts all demand data writes (RFOs)",
+        "EventCode": "0xB7, 0xBB",
+        "MSRValue": "0x0080020002",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.SUPPLIER_NONE.SNOOP_NONE",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "SampleAfterValue": "100003",
+        "BriefDescription": "Counts all demand data writes (RFOs)",
+        "Offcore": "1",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "PublicDescription": "Counts all demand data writes (RFOs)",
+        "EventCode": "0xB7, 0xBB",
+        "MSRValue": "0x0040020002",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.SUPPLIER_NONE.SPL_HIT",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "SampleAfterValue": "100003",
+        "BriefDescription": "Counts all demand data writes (RFOs)",
+        "Offcore": "1",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "PublicDescription": "Counts all demand data writes (RFOs) have any response type.",
+        "EventCode": "0xB7, 0xBB",
+        "MSRValue": "0x0000010002",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.ANY_RESPONSE",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "SampleAfterValue": "100003",
+        "BriefDescription": "Counts all demand data writes (RFOs) have any response type.",
+        "Offcore": "1",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "PublicDescription": "Counts demand data reads",
+        "EventCode": "0xB7, 0xBB",
+        "MSRValue": "0x3FC0400001",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L4_HIT_LOCAL_L4.ANY_SNOOP",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "DEMAND_DATA_RD & L4_HIT_LOCAL_L4 & ANY_SNOOP",
+        "BriefDescription": "Counts demand data reads",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts demand data reads",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x1000400001 ",
+        "MSRValue": "0x1000400001",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L4_HIT_LOCAL_L4.SNOOP_HITM",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "DEMAND_DATA_RD & L4_HIT_LOCAL_L4 & SNOOP_HITM",
+        "BriefDescription": "Counts demand data reads",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts demand data reads",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0400400001 ",
+        "MSRValue": "0x0400400001",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L4_HIT_LOCAL_L4.SNOOP_HIT_NO_FWD",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "DEMAND_DATA_RD & L4_HIT_LOCAL_L4 & SNOOP_HIT_NO_FWD",
+        "BriefDescription": "Counts demand data reads",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts demand data reads",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0200400001 ",
+        "MSRValue": "0x0200400001",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L4_HIT_LOCAL_L4.SNOOP_MISS",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "DEMAND_DATA_RD & L4_HIT_LOCAL_L4 & SNOOP_MISS",
+        "BriefDescription": "Counts demand data reads",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts demand data reads",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0100400001 ",
+        "MSRValue": "0x0100400001",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L4_HIT_LOCAL_L4.SNOOP_NOT_NEEDED",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "DEMAND_DATA_RD & L4_HIT_LOCAL_L4 & SNOOP_NOT_NEEDED",
+        "BriefDescription": "Counts demand data reads",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts demand data reads",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0080400001 ",
+        "MSRValue": "0x0080400001",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L4_HIT_LOCAL_L4.SNOOP_NONE",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "SampleAfterValue": "100003",
+        "BriefDescription": "Counts demand data reads",
+        "Offcore": "1",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "PublicDescription": "Counts demand data reads",
+        "EventCode": "0xB7, 0xBB",
+        "MSRValue": "0x0040400001",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L4_HIT_LOCAL_L4.SPL_HIT",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "DEMAND_DATA_RD & L4_HIT_LOCAL_L4 & SNOOP_NONE",
+        "BriefDescription": "Counts demand data reads",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts demand data reads",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x3fc01c0001 ",
+        "MSRValue": "0x3FC01C0001",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_HIT.ANY_SNOOP",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "DEMAND_DATA_RD & L3_HIT & ANY_SNOOP",
+        "BriefDescription": "Counts demand data reads",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts demand data reads",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x10001c0001 ",
+        "MSRValue": "0x10001C0001",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_HIT.SNOOP_HITM",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "DEMAND_DATA_RD & L3_HIT & SNOOP_HITM",
+        "BriefDescription": "Counts demand data reads",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "Counts demand data reads that hit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts demand data reads",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x04001c0001 ",
+        "MSRValue": "0x04001C0001",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_HIT.SNOOP_HIT_NO_FWD",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "Counts demand data reads that hit in the L3 and the snoops to sibling cores hit in either E/S state and the line is not forwarded.",
+        "BriefDescription": "Counts demand data reads",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "Counts demand data reads that hit in the L3 and the snoops sent to sibling cores return clean response. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts demand data reads",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x02001c0001 ",
+        "MSRValue": "0x02001C0001",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_HIT.SNOOP_MISS",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "Counts demand data reads that hit in the L3 and the snoops sent to sibling cores return clean response.",
+        "BriefDescription": "Counts demand data reads",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "Counts demand data reads that hit in the L3 and sibling core snoops are not needed as either the core-valid bit is not set or the shared line is present in multiple cores. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts demand data reads",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x01001c0001 ",
+        "MSRValue": "0x01001C0001",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_HIT.SNOOP_NOT_NEEDED",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "Counts demand data reads that hit in the L3 and sibling core snoops are not needed as either the core-valid bit is not set or the shared line is present in multiple cores.",
+        "BriefDescription": "Counts demand data reads",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts demand data reads",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x00801c0001 ",
+        "MSRValue": "0x00801C0001",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_HIT.SNOOP_NONE",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "SampleAfterValue": "100003",
+        "BriefDescription": "Counts demand data reads",
+        "Offcore": "1",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "PublicDescription": "Counts demand data reads",
+        "EventCode": "0xB7, 0xBB",
+        "MSRValue": "0x00401C0001",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_HIT.SPL_HIT",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "SampleAfterValue": "100003",
+        "BriefDescription": "Counts demand data reads",
+        "Offcore": "1",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "PublicDescription": "Counts demand data reads",
+        "EventCode": "0xB7, 0xBB",
+        "MSRValue": "0x3FC0100001",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_HIT_S.ANY_SNOOP",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "SampleAfterValue": "100003",
+        "BriefDescription": "Counts demand data reads",
+        "Offcore": "1",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "PublicDescription": "Counts demand data reads",
+        "EventCode": "0xB7, 0xBB",
+        "MSRValue": "0x1000100001",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_HIT_S.SNOOP_HITM",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "SampleAfterValue": "100003",
+        "BriefDescription": "Counts demand data reads",
+        "Offcore": "1",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "PublicDescription": "Counts demand data reads",
+        "EventCode": "0xB7, 0xBB",
+        "MSRValue": "0x0400100001",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_HIT_S.SNOOP_HIT_NO_FWD",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "SampleAfterValue": "100003",
+        "BriefDescription": "Counts demand data reads",
+        "Offcore": "1",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "PublicDescription": "Counts demand data reads",
+        "EventCode": "0xB7, 0xBB",
+        "MSRValue": "0x0200100001",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_HIT_S.SNOOP_MISS",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "SampleAfterValue": "100003",
+        "BriefDescription": "Counts demand data reads",
+        "Offcore": "1",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "PublicDescription": "Counts demand data reads",
+        "EventCode": "0xB7, 0xBB",
+        "MSRValue": "0x0100100001",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_HIT_S.SNOOP_NOT_NEEDED",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "DEMAND_DATA_RD & L3_HIT & SNOOP_NONE",
+        "BriefDescription": "Counts demand data reads",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts demand data reads",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x3fc0020001 ",
+        "MSRValue": "0x0080100001",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_HIT_S.SNOOP_NONE",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "SampleAfterValue": "100003",
+        "BriefDescription": "Counts demand data reads",
+        "Offcore": "1",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "PublicDescription": "Counts demand data reads",
+        "EventCode": "0xB7, 0xBB",
+        "MSRValue": "0x0040100001",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_HIT_S.SPL_HIT",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "SampleAfterValue": "100003",
+        "BriefDescription": "Counts demand data reads",
+        "Offcore": "1",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "PublicDescription": "Counts demand data reads",
+        "EventCode": "0xB7, 0xBB",
+        "MSRValue": "0x3FC0080001",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_HIT_E.ANY_SNOOP",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "SampleAfterValue": "100003",
+        "BriefDescription": "Counts demand data reads",
+        "Offcore": "1",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "PublicDescription": "Counts demand data reads",
+        "EventCode": "0xB7, 0xBB",
+        "MSRValue": "0x1000080001",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_HIT_E.SNOOP_HITM",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "SampleAfterValue": "100003",
+        "BriefDescription": "Counts demand data reads",
+        "Offcore": "1",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "PublicDescription": "Counts demand data reads",
+        "EventCode": "0xB7, 0xBB",
+        "MSRValue": "0x0400080001",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_HIT_E.SNOOP_HIT_NO_FWD",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "SampleAfterValue": "100003",
+        "BriefDescription": "Counts demand data reads",
+        "Offcore": "1",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "PublicDescription": "Counts demand data reads",
+        "EventCode": "0xB7, 0xBB",
+        "MSRValue": "0x0200080001",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_HIT_E.SNOOP_MISS",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "SampleAfterValue": "100003",
+        "BriefDescription": "Counts demand data reads",
+        "Offcore": "1",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "PublicDescription": "Counts demand data reads",
+        "EventCode": "0xB7, 0xBB",
+        "MSRValue": "0x0100080001",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_HIT_E.SNOOP_NOT_NEEDED",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "SampleAfterValue": "100003",
+        "BriefDescription": "Counts demand data reads",
+        "Offcore": "1",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "PublicDescription": "Counts demand data reads",
+        "EventCode": "0xB7, 0xBB",
+        "MSRValue": "0x0080080001",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_HIT_E.SNOOP_NONE",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "SampleAfterValue": "100003",
+        "BriefDescription": "Counts demand data reads",
+        "Offcore": "1",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "PublicDescription": "Counts demand data reads",
+        "EventCode": "0xB7, 0xBB",
+        "MSRValue": "0x0040080001",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_HIT_E.SPL_HIT",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "SampleAfterValue": "100003",
+        "BriefDescription": "Counts demand data reads",
+        "Offcore": "1",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "PublicDescription": "Counts demand data reads",
+        "EventCode": "0xB7, 0xBB",
+        "MSRValue": "0x3FC0040001",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_HIT_M.ANY_SNOOP",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "SampleAfterValue": "100003",
+        "BriefDescription": "Counts demand data reads",
+        "Offcore": "1",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "PublicDescription": "Counts demand data reads",
+        "EventCode": "0xB7, 0xBB",
+        "MSRValue": "0x1000040001",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_HIT_M.SNOOP_HITM",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "SampleAfterValue": "100003",
+        "BriefDescription": "Counts demand data reads",
+        "Offcore": "1",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "PublicDescription": "Counts demand data reads",
+        "EventCode": "0xB7, 0xBB",
+        "MSRValue": "0x0400040001",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_HIT_M.SNOOP_HIT_NO_FWD",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "SampleAfterValue": "100003",
+        "BriefDescription": "Counts demand data reads",
+        "Offcore": "1",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "PublicDescription": "Counts demand data reads",
+        "EventCode": "0xB7, 0xBB",
+        "MSRValue": "0x0200040001",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_HIT_M.SNOOP_MISS",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "SampleAfterValue": "100003",
+        "BriefDescription": "Counts demand data reads",
+        "Offcore": "1",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "PublicDescription": "Counts demand data reads",
+        "EventCode": "0xB7, 0xBB",
+        "MSRValue": "0x0100040001",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_HIT_M.SNOOP_NOT_NEEDED",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "SampleAfterValue": "100003",
+        "BriefDescription": "Counts demand data reads",
+        "Offcore": "1",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "PublicDescription": "Counts demand data reads",
+        "EventCode": "0xB7, 0xBB",
+        "MSRValue": "0x0080040001",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_HIT_M.SNOOP_NONE",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "SampleAfterValue": "100003",
+        "BriefDescription": "Counts demand data reads",
+        "Offcore": "1",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "PublicDescription": "Counts demand data reads",
+        "EventCode": "0xB7, 0xBB",
+        "MSRValue": "0x0040040001",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_HIT_M.SPL_HIT",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "SampleAfterValue": "100003",
+        "BriefDescription": "Counts demand data reads",
+        "Offcore": "1",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "PublicDescription": "Counts demand data reads",
+        "EventCode": "0xB7, 0xBB",
+        "MSRValue": "0x3FC0020001",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.SUPPLIER_NONE.ANY_SNOOP",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "DEMAND_DATA_RD & SUPPLIER_NONE & ANY_SNOOP",
+        "BriefDescription": "Counts demand data reads",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts demand data reads",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x1000020001 ",
+        "MSRValue": "0x1000020001",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.SUPPLIER_NONE.SNOOP_HITM",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "DEMAND_DATA_RD & SUPPLIER_NONE & SNOOP_HITM",
+        "BriefDescription": "Counts demand data reads",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts demand data reads",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0400020001 ",
+        "MSRValue": "0x0400020001",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.SUPPLIER_NONE.SNOOP_HIT_NO_FWD",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "DEMAND_DATA_RD & SUPPLIER_NONE & SNOOP_HIT_NO_FWD",
+        "BriefDescription": "Counts demand data reads",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts demand data reads",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0200020001 ",
+        "MSRValue": "0x0200020001",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.SUPPLIER_NONE.SNOOP_MISS",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "DEMAND_DATA_RD & SUPPLIER_NONE & SNOOP_MISS",
+        "BriefDescription": "Counts demand data reads",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts demand data reads",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0100020001 ",
+        "MSRValue": "0x0100020001",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.SUPPLIER_NONE.SNOOP_NOT_NEEDED",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "DEMAND_DATA_RD & SUPPLIER_NONE & SNOOP_NOT_NEEDED",
+        "BriefDescription": "Counts demand data reads",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts demand data reads",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0080020001 ",
+        "MSRValue": "0x0080020001",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.SUPPLIER_NONE.SNOOP_NONE",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "SampleAfterValue": "100003",
+        "BriefDescription": "Counts demand data reads",
+        "Offcore": "1",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "PublicDescription": "Counts demand data reads",
+        "EventCode": "0xB7, 0xBB",
+        "MSRValue": "0x0040020001",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.SUPPLIER_NONE.SPL_HIT",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "DEMAND_DATA_RD & SUPPLIER_NONE & SNOOP_NONE",
+        "BriefDescription": "Counts demand data reads",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "Counts demand data reads that have any response type. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts demand data reads have any response type.",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0000010001 ",
+        "MSRValue": "0x0000010001",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.ANY_RESPONSE",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "Counts demand data reads that have any response type.",
+        "BriefDescription": "Counts demand data reads have any response type.",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     }
diff --git a/tools/perf/pmu-events/arch/x86/skylake/frontend.json b/tools/perf/pmu-events/arch/x86/skylake/frontend.json
index 578dff5bd823..7fa95a35e3ca 100644
--- a/tools/perf/pmu-events/arch/x86/skylake/frontend.json
+++ b/tools/perf/pmu-events/arch/x86/skylake/frontend.json
@@ -177,7 +177,7 @@
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "PublicDescription": "Counts the number of uops not delivered to Resource Allocation Table (RAT) per thread adding 4  x when Resource Allocation Table (RAT) is not stalled and Instruction Decode Queue (IDQ) delivers x uops to Resource Allocation Table (RAT) (where x belongs to {0,1,2,3}). Counting does not cover cases when: a. IDQ-Resource Allocation Table (RAT) pipe serves the other thread. b. Resource Allocation Table (RAT) is stalled for the thread (including uop drops and clear BE conditions).  c. Instruction Decode Queue (IDQ) delivers four uops.",
+        "PublicDescription": "Counts the number of uops not delivered to Resource Allocation Table (RAT) per thread adding \u201c4 \u2013 x\u201d when Resource Allocation Table (RAT) is not stalled and Instruction Decode Queue (IDQ) delivers x uops to Resource Allocation Table (RAT) (where x belongs to {0,1,2,3}). Counting does not cover cases when: a. IDQ-Resource Allocation Table (RAT) pipe serves the other thread. b. Resource Allocation Table (RAT) is stalled for the thread (including uop drops and clear BE conditions).  c. Instruction Decode Queue (IDQ) delivers four uops.",
         "EventCode": "0x9C",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
@@ -242,7 +242,7 @@
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "PublicDescription": "Counts Decode Stream Buffer (DSB)-to-MITE switch true penalty cycles. These cycles do not include uops routed through because of the switch itself, for example, when Instruction Decode Queue (IDQ) pre-allocation is unavailable, or Instruction Decode Queue (IDQ) is full. SBD-to-MITE switch true penalty cycles happen after the merge mux (MM) receives Decode Stream Buffer (DSB) Sync-indication until receiving the first MITE uop. MM is placed before Instruction Decode Queue (IDQ) to merge uops being fed from the MITE and Decode Stream Buffer (DSB) paths. Decode Stream Buffer (DSB) inserts the Sync-indication whenever a Decode Stream Buffer (DSB)-to-MITE switch occurs.Penalty: A Decode Stream Buffer (DSB) hit followed by a Decode Stream Buffer (DSB) miss can cost up to six cycles in which no uops are delivered to the IDQ. Most often, such switches from the Decode Stream Buffer (DSB) to the legacy pipeline cost 02 cycles.",
+        "PublicDescription": "Counts Decode Stream Buffer (DSB)-to-MITE switch true penalty cycles. These cycles do not include uops routed through because of the switch itself, for example, when Instruction Decode Queue (IDQ) pre-allocation is unavailable, or Instruction Decode Queue (IDQ) is full. SBD-to-MITE switch true penalty cycles happen after the merge mux (MM) receives Decode Stream Buffer (DSB) Sync-indication until receiving the first MITE uop. MM is placed before Instruction Decode Queue (IDQ) to merge uops being fed from the MITE and Decode Stream Buffer (DSB) paths. Decode Stream Buffer (DSB) inserts the Sync-indication whenever a Decode Stream Buffer (DSB)-to-MITE switch occurs.Penalty: A Decode Stream Buffer (DSB) hit followed by a Decode Stream Buffer (DSB) miss can cost up to six cycles in which no uops are delivered to the IDQ. Most often, such switches from the Decode Stream Buffer (DSB) to the legacy pipeline cost 0\u20132 cycles.",
         "EventCode": "0xAB",
         "Counter": "0,1,2,3",
         "UMask": "0x2",
@@ -253,7 +253,7 @@
     },
     {
         "PEBS": "1",
-        "PublicDescription": "Counts retired Instructions that experienced DSB (Decode stream buffer i.e. the decoded instruction-cache) miss. \r\n",
+        "PublicDescription": "Counts retired Instructions that experienced DSB (Decode stream buffer i.e. the decoded instruction-cache) miss.",
         "EventCode": "0xC6",
         "MSRValue": "0x11",
         "Counter": "0,1,2,3",
@@ -360,7 +360,7 @@
     },
     {
         "PEBS": "1",
-        "PublicDescription": "Counts retired instructions that are delivered to the back-end after a front-end stall of at least 8 cycles. During this period the front-end delivered no uops. \r\n",
+        "PublicDescription": "Counts retired instructions that are delivered to the back-end after a front-end stall of at least 8 cycles. During this period the front-end delivered no uops.",
         "EventCode": "0xC6",
         "MSRValue": "0x400806",
         "Counter": "0,1,2,3",
@@ -374,7 +374,7 @@
     },
     {
         "PEBS": "1",
-        "PublicDescription": "Counts retired instructions that are delivered to the back-end after a front-end stall of at least 16 cycles. During this period the front-end delivered no uops.\r\n",
+        "PublicDescription": "Counts retired instructions that are delivered to the back-end after a front-end stall of at least 16 cycles. During this period the front-end delivered no uops.",
         "EventCode": "0xC6",
         "MSRValue": "0x401006",
         "Counter": "0,1,2,3",
@@ -388,7 +388,7 @@
     },
     {
         "PEBS": "1",
-        "PublicDescription": "Counts retired instructions that are delivered to the back-end  after a front-end stall of at least 32 cycles. During this period the front-end delivered no uops.\r\n",
+        "PublicDescription": "Counts retired instructions that are delivered to the back-end  after a front-end stall of at least 32 cycles. During this period the front-end delivered no uops.",
         "EventCode": "0xC6",
         "MSRValue": "0x402006",
         "Counter": "0,1,2,3",
@@ -454,7 +454,7 @@
     },
     {
         "PEBS": "1",
-        "PublicDescription": "Counts retired instructions that are delivered to the back-end after the front-end had at least 1 bubble-slot for a period of 2 cycles. A bubble-slot is an empty issue-pipeline slot while there was no RAT stall.\r\n",
+        "PublicDescription": "Counts retired instructions that are delivered to the back-end after the front-end had at least 1 bubble-slot for a period of 2 cycles. A bubble-slot is an empty issue-pipeline slot while there was no RAT stall.",
         "EventCode": "0xC6",
         "MSRValue": "0x100206",
         "Counter": "0,1,2,3",
diff --git a/tools/perf/pmu-events/arch/x86/skylake/memory.json b/tools/perf/pmu-events/arch/x86/skylake/memory.json
index 3bd8b712c889..f197b4c7695b 100644
--- a/tools/perf/pmu-events/arch/x86/skylake/memory.json
+++ b/tools/perf/pmu-events/arch/x86/skylake/memory.json
@@ -215,7 +215,7 @@
         "UMask": "0x4",
         "EventName": "HLE_RETIRED.ABORTED",
         "SampleAfterValue": "2000003",
-        "BriefDescription": "Number of times an HLE execution aborted due to any reasons (multiple categories may count as one). ",
+        "BriefDescription": "Number of times an HLE execution aborted due to any reasons (multiple categories may count as one).",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
@@ -237,6 +237,7 @@
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
+        "PublicDescription": "Number of times an HLE execution aborted due to HLE-unfriendly instructions and certain unfriendly events (such as AD assists etc.).",
         "EventCode": "0xC8",
         "Counter": "0,1,2,3",
         "UMask": "0x20",
@@ -292,7 +293,7 @@
         "UMask": "0x4",
         "EventName": "RTM_RETIRED.ABORTED",
         "SampleAfterValue": "2000003",
-        "BriefDescription": "Number of times an RTM execution aborted due to any reasons (multiple categories may count as one). ",
+        "BriefDescription": "Number of times an RTM execution aborted due to any reasons (multiple categories may count as one).",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
@@ -346,7 +347,7 @@
     },
     {
         "PEBS": "2",
-        "PublicDescription": "Counts loads when the latency from first dispatch to completion is greater than 4 cycles.  Reported latency may be longer than just the memory latency.",
+        "PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 4 cycles.  Reported latency may be longer than just the memory latency.",
         "EventCode": "0xCD",
         "MSRValue": "0x4",
         "Counter": "0,1,2,3",
@@ -354,13 +355,13 @@
         "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_4",
         "MSRIndex": "0x3F6",
         "SampleAfterValue": "100003",
-        "BriefDescription": "Counts loads when the latency from first dispatch to completion is greater than 4 cycles.",
+        "BriefDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 4 cycles.",
         "TakenAlone": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
         "PEBS": "2",
-        "PublicDescription": "Counts loads when the latency from first dispatch to completion is greater than 8 cycles.  Reported latency may be longer than just the memory latency.",
+        "PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 8 cycles.  Reported latency may be longer than just the memory latency.",
         "EventCode": "0xCD",
         "MSRValue": "0x8",
         "Counter": "0,1,2,3",
@@ -368,13 +369,13 @@
         "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_8",
         "MSRIndex": "0x3F6",
         "SampleAfterValue": "50021",
-        "BriefDescription": "Counts loads when the latency from first dispatch to completion is greater than 8 cycles.",
+        "BriefDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 8 cycles.",
         "TakenAlone": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
         "PEBS": "2",
-        "PublicDescription": "Counts loads when the latency from first dispatch to completion is greater than 16 cycles.  Reported latency may be longer than just the memory latency.",
+        "PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 16 cycles.  Reported latency may be longer than just the memory latency.",
         "EventCode": "0xCD",
         "MSRValue": "0x10",
         "Counter": "0,1,2,3",
@@ -382,13 +383,13 @@
         "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_16",
         "MSRIndex": "0x3F6",
         "SampleAfterValue": "20011",
-        "BriefDescription": "Counts loads when the latency from first dispatch to completion is greater than 16 cycles.",
+        "BriefDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 16 cycles.",
         "TakenAlone": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
         "PEBS": "2",
-        "PublicDescription": "Counts loads when the latency from first dispatch to completion is greater than 32 cycles.  Reported latency may be longer than just the memory latency.",
+        "PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 32 cycles.  Reported latency may be longer than just the memory latency.",
         "EventCode": "0xCD",
         "MSRValue": "0x20",
         "Counter": "0,1,2,3",
@@ -396,13 +397,13 @@
         "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_32",
         "MSRIndex": "0x3F6",
         "SampleAfterValue": "100007",
-        "BriefDescription": "Counts loads when the latency from first dispatch to completion is greater than 32 cycles.",
+        "BriefDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 32 cycles.",
         "TakenAlone": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
         "PEBS": "2",
-        "PublicDescription": "Counts loads when the latency from first dispatch to completion is greater than 64 cycles.  Reported latency may be longer than just the memory latency.",
+        "PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 64 cycles.  Reported latency may be longer than just the memory latency.",
         "EventCode": "0xCD",
         "MSRValue": "0x40",
         "Counter": "0,1,2,3",
@@ -410,13 +411,13 @@
         "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_64",
         "MSRIndex": "0x3F6",
         "SampleAfterValue": "2003",
-        "BriefDescription": "Counts loads when the latency from first dispatch to completion is greater than 64 cycles.",
+        "BriefDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 64 cycles.",
         "TakenAlone": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
         "PEBS": "2",
-        "PublicDescription": "Counts loads when the latency from first dispatch to completion is greater than 128 cycles.  Reported latency may be longer than just the memory latency.",
+        "PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 128 cycles.  Reported latency may be longer than just the memory latency.",
         "EventCode": "0xCD",
         "MSRValue": "0x80",
         "Counter": "0,1,2,3",
@@ -424,13 +425,13 @@
         "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_128",
         "MSRIndex": "0x3F6",
         "SampleAfterValue": "1009",
-        "BriefDescription": "Counts loads when the latency from first dispatch to completion is greater than 128 cycles.",
+        "BriefDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 128 cycles.",
         "TakenAlone": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
         "PEBS": "2",
-        "PublicDescription": "Counts loads when the latency from first dispatch to completion is greater than 256 cycles.  Reported latency may be longer than just the memory latency.",
+        "PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 256 cycles.  Reported latency may be longer than just the memory latency.",
         "EventCode": "0xCD",
         "MSRValue": "0x100",
         "Counter": "0,1,2,3",
@@ -438,13 +439,13 @@
         "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_256",
         "MSRIndex": "0x3F6",
         "SampleAfterValue": "503",
-        "BriefDescription": "Counts loads when the latency from first dispatch to completion is greater than 256 cycles.",
+        "BriefDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 256 cycles.",
         "TakenAlone": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
         "PEBS": "2",
-        "PublicDescription": "Counts loads when the latency from first dispatch to completion is greater than 512 cycles.  Reported latency may be longer than just the memory latency.",
+        "PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 512 cycles.  Reported latency may be longer than just the memory latency.",
         "EventCode": "0xCD",
         "MSRValue": "0x200",
         "Counter": "0,1,2,3",
@@ -452,163 +453,1151 @@
         "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_512",
         "MSRIndex": "0x3F6",
         "SampleAfterValue": "101",
-        "BriefDescription": "Counts loads when the latency from first dispatch to completion is greater than 512 cycles.",
+        "BriefDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 512 cycles.",
         "TakenAlone": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts any other requests",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x3ffc000001 ",
+        "MSRValue": "0x3FFC408000",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "EventName": "OFFCORE_RESPONSE.OTHER.L3_MISS.ANY_SNOOP",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "SampleAfterValue": "100003",
+        "BriefDescription": "Counts any other requests",
+        "Offcore": "1",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "PublicDescription": "Counts any other requests",
+        "EventCode": "0xB7, 0xBB",
+        "MSRValue": "0x203C408000",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "EventName": "OFFCORE_RESPONSE.OTHER.L3_MISS.SNOOP_NON_DRAM",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "SampleAfterValue": "100003",
+        "BriefDescription": "Counts any other requests",
+        "Offcore": "1",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "PublicDescription": "Counts any other requests",
+        "EventCode": "0xB7, 0xBB",
+        "MSRValue": "0x103C408000",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "EventName": "OFFCORE_RESPONSE.OTHER.L3_MISS.SNOOP_HITM",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "SampleAfterValue": "100003",
+        "BriefDescription": "Counts any other requests",
+        "Offcore": "1",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "PublicDescription": "Counts any other requests",
+        "EventCode": "0xB7, 0xBB",
+        "MSRValue": "0x043C408000",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "EventName": "OFFCORE_RESPONSE.OTHER.L3_MISS.SNOOP_HIT_NO_FWD",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "SampleAfterValue": "100003",
+        "BriefDescription": "Counts any other requests",
+        "Offcore": "1",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "PublicDescription": "Counts any other requests",
+        "EventCode": "0xB7, 0xBB",
+        "MSRValue": "0x023C408000",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "EventName": "OFFCORE_RESPONSE.OTHER.L3_MISS.SNOOP_MISS",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "SampleAfterValue": "100003",
+        "BriefDescription": "Counts any other requests",
+        "Offcore": "1",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "PublicDescription": "Counts any other requests",
+        "EventCode": "0xB7, 0xBB",
+        "MSRValue": "0x013C408000",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "EventName": "OFFCORE_RESPONSE.OTHER.L3_MISS.SNOOP_NOT_NEEDED",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "SampleAfterValue": "100003",
+        "BriefDescription": "Counts any other requests",
+        "Offcore": "1",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "PublicDescription": "Counts any other requests",
+        "EventCode": "0xB7, 0xBB",
+        "MSRValue": "0x00BC408000",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "EventName": "OFFCORE_RESPONSE.OTHER.L3_MISS.SNOOP_NONE",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "SampleAfterValue": "100003",
+        "BriefDescription": "Counts any other requests",
+        "Offcore": "1",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "PublicDescription": "Counts any other requests",
+        "EventCode": "0xB7, 0xBB",
+        "MSRValue": "0x007C408000",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "EventName": "OFFCORE_RESPONSE.OTHER.L3_MISS.SPL_HIT",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "SampleAfterValue": "100003",
+        "BriefDescription": "Counts any other requests",
+        "Offcore": "1",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "PublicDescription": "Counts any other requests",
+        "EventCode": "0xB7, 0xBB",
+        "MSRValue": "0x3FC4008000",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "EventName": "OFFCORE_RESPONSE.OTHER.L3_MISS_LOCAL_DRAM.ANY_SNOOP",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "SampleAfterValue": "100003",
+        "BriefDescription": "Counts any other requests",
+        "Offcore": "1",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "PublicDescription": "Counts any other requests",
+        "EventCode": "0xB7, 0xBB",
+        "MSRValue": "0x2004008000",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "EventName": "OFFCORE_RESPONSE.OTHER.L3_MISS_LOCAL_DRAM.SNOOP_NON_DRAM",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "SampleAfterValue": "100003",
+        "BriefDescription": "Counts any other requests",
+        "Offcore": "1",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "PublicDescription": "Counts any other requests",
+        "EventCode": "0xB7, 0xBB",
+        "MSRValue": "0x1004008000",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "EventName": "OFFCORE_RESPONSE.OTHER.L3_MISS_LOCAL_DRAM.SNOOP_HITM",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "SampleAfterValue": "100003",
+        "BriefDescription": "Counts any other requests",
+        "Offcore": "1",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "PublicDescription": "Counts any other requests",
+        "EventCode": "0xB7, 0xBB",
+        "MSRValue": "0x0404008000",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "EventName": "OFFCORE_RESPONSE.OTHER.L3_MISS_LOCAL_DRAM.SNOOP_HIT_NO_FWD",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "SampleAfterValue": "100003",
+        "BriefDescription": "Counts any other requests",
+        "Offcore": "1",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "PublicDescription": "Counts any other requests",
+        "EventCode": "0xB7, 0xBB",
+        "MSRValue": "0x0204008000",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "EventName": "OFFCORE_RESPONSE.OTHER.L3_MISS_LOCAL_DRAM.SNOOP_MISS",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "SampleAfterValue": "100003",
+        "BriefDescription": "Counts any other requests",
+        "Offcore": "1",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "PublicDescription": "Counts any other requests",
+        "EventCode": "0xB7, 0xBB",
+        "MSRValue": "0x0104008000",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "EventName": "OFFCORE_RESPONSE.OTHER.L3_MISS_LOCAL_DRAM.SNOOP_NOT_NEEDED",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "SampleAfterValue": "100003",
+        "BriefDescription": "Counts any other requests",
+        "Offcore": "1",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "PublicDescription": "Counts any other requests",
+        "EventCode": "0xB7, 0xBB",
+        "MSRValue": "0x0084008000",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "EventName": "OFFCORE_RESPONSE.OTHER.L3_MISS_LOCAL_DRAM.SNOOP_NONE",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "SampleAfterValue": "100003",
+        "BriefDescription": "Counts any other requests",
+        "Offcore": "1",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "PublicDescription": "Counts any other requests",
+        "EventCode": "0xB7, 0xBB",
+        "MSRValue": "0x0044008000",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "EventName": "OFFCORE_RESPONSE.OTHER.L3_MISS_LOCAL_DRAM.SPL_HIT",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "SampleAfterValue": "100003",
+        "BriefDescription": "Counts any other requests",
+        "Offcore": "1",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "PublicDescription": "Counts any other requests",
+        "EventCode": "0xB7, 0xBB",
+        "MSRValue": "0x2000408000",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "EventName": "OFFCORE_RESPONSE.OTHER.L4_HIT_LOCAL_L4.SNOOP_NON_DRAM",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "SampleAfterValue": "100003",
+        "BriefDescription": "Counts any other requests",
+        "Offcore": "1",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "PublicDescription": "Counts any other requests",
+        "EventCode": "0xB7, 0xBB",
+        "MSRValue": "0x20001C8000",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "EventName": "OFFCORE_RESPONSE.OTHER.L3_HIT.SNOOP_NON_DRAM",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "SampleAfterValue": "100003",
+        "BriefDescription": "Counts any other requests",
+        "Offcore": "1",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "PublicDescription": "Counts any other requests",
+        "EventCode": "0xB7, 0xBB",
+        "MSRValue": "0x2000108000",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "EventName": "OFFCORE_RESPONSE.OTHER.L3_HIT_S.SNOOP_NON_DRAM",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "SampleAfterValue": "100003",
+        "BriefDescription": "Counts any other requests",
+        "Offcore": "1",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "PublicDescription": "Counts any other requests",
+        "EventCode": "0xB7, 0xBB",
+        "MSRValue": "0x2000088000",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "EventName": "OFFCORE_RESPONSE.OTHER.L3_HIT_E.SNOOP_NON_DRAM",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "SampleAfterValue": "100003",
+        "BriefDescription": "Counts any other requests",
+        "Offcore": "1",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "PublicDescription": "Counts any other requests",
+        "EventCode": "0xB7, 0xBB",
+        "MSRValue": "0x2000048000",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "EventName": "OFFCORE_RESPONSE.OTHER.L3_HIT_M.SNOOP_NON_DRAM",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "SampleAfterValue": "100003",
+        "BriefDescription": "Counts any other requests",
+        "Offcore": "1",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "PublicDescription": "Counts any other requests",
+        "EventCode": "0xB7, 0xBB",
+        "MSRValue": "0x2000028000",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "EventName": "OFFCORE_RESPONSE.OTHER.SUPPLIER_NONE.SNOOP_NON_DRAM",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "SampleAfterValue": "100003",
+        "BriefDescription": "Counts any other requests",
+        "Offcore": "1",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that",
+        "EventCode": "0xB7, 0xBB",
+        "MSRValue": "0x3FFC400004",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_MISS.ANY_SNOOP",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "SampleAfterValue": "100003",
+        "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that",
+        "Offcore": "1",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that",
+        "EventCode": "0xB7, 0xBB",
+        "MSRValue": "0x203C400004",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_MISS.SNOOP_NON_DRAM",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "SampleAfterValue": "100003",
+        "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that",
+        "Offcore": "1",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that",
+        "EventCode": "0xB7, 0xBB",
+        "MSRValue": "0x103C400004",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_MISS.SNOOP_HITM",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "SampleAfterValue": "100003",
+        "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that",
+        "Offcore": "1",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that",
+        "EventCode": "0xB7, 0xBB",
+        "MSRValue": "0x043C400004",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_MISS.SNOOP_HIT_NO_FWD",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "SampleAfterValue": "100003",
+        "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that",
+        "Offcore": "1",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that",
+        "EventCode": "0xB7, 0xBB",
+        "MSRValue": "0x023C400004",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_MISS.SNOOP_MISS",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "SampleAfterValue": "100003",
+        "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that",
+        "Offcore": "1",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that",
+        "EventCode": "0xB7, 0xBB",
+        "MSRValue": "0x013C400004",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_MISS.SNOOP_NOT_NEEDED",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "SampleAfterValue": "100003",
+        "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that",
+        "Offcore": "1",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that",
+        "EventCode": "0xB7, 0xBB",
+        "MSRValue": "0x00BC400004",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_MISS.SNOOP_NONE",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "SampleAfterValue": "100003",
+        "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that",
+        "Offcore": "1",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that",
+        "EventCode": "0xB7, 0xBB",
+        "MSRValue": "0x007C400004",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_MISS.SPL_HIT",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "SampleAfterValue": "100003",
+        "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that",
+        "Offcore": "1",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that",
+        "EventCode": "0xB7, 0xBB",
+        "MSRValue": "0x3FC4000004",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_MISS_LOCAL_DRAM.ANY_SNOOP",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "SampleAfterValue": "100003",
+        "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that",
+        "Offcore": "1",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that",
+        "EventCode": "0xB7, 0xBB",
+        "MSRValue": "0x2004000004",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_MISS_LOCAL_DRAM.SNOOP_NON_DRAM",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "SampleAfterValue": "100003",
+        "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that",
+        "Offcore": "1",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that",
+        "EventCode": "0xB7, 0xBB",
+        "MSRValue": "0x1004000004",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_MISS_LOCAL_DRAM.SNOOP_HITM",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "SampleAfterValue": "100003",
+        "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that",
+        "Offcore": "1",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that",
+        "EventCode": "0xB7, 0xBB",
+        "MSRValue": "0x0404000004",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_MISS_LOCAL_DRAM.SNOOP_HIT_NO_FWD",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "SampleAfterValue": "100003",
+        "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that",
+        "Offcore": "1",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that",
+        "EventCode": "0xB7, 0xBB",
+        "MSRValue": "0x0204000004",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_MISS_LOCAL_DRAM.SNOOP_MISS",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "SampleAfterValue": "100003",
+        "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that",
+        "Offcore": "1",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that",
+        "EventCode": "0xB7, 0xBB",
+        "MSRValue": "0x0104000004",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_MISS_LOCAL_DRAM.SNOOP_NOT_NEEDED",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "SampleAfterValue": "100003",
+        "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that",
+        "Offcore": "1",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that",
+        "EventCode": "0xB7, 0xBB",
+        "MSRValue": "0x0084000004",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_MISS_LOCAL_DRAM.SNOOP_NONE",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "SampleAfterValue": "100003",
+        "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that",
+        "Offcore": "1",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that",
+        "EventCode": "0xB7, 0xBB",
+        "MSRValue": "0x0044000004",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_MISS_LOCAL_DRAM.SPL_HIT",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "SampleAfterValue": "100003",
+        "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that",
+        "Offcore": "1",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that",
+        "EventCode": "0xB7, 0xBB",
+        "MSRValue": "0x2000400004",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L4_HIT_LOCAL_L4.SNOOP_NON_DRAM",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "SampleAfterValue": "100003",
+        "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that",
+        "Offcore": "1",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that",
+        "EventCode": "0xB7, 0xBB",
+        "MSRValue": "0x20001C0004",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_HIT.SNOOP_NON_DRAM",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "SampleAfterValue": "100003",
+        "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that",
+        "Offcore": "1",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that",
+        "EventCode": "0xB7, 0xBB",
+        "MSRValue": "0x2000100004",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_HIT_S.SNOOP_NON_DRAM",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "SampleAfterValue": "100003",
+        "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that",
+        "Offcore": "1",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that",
+        "EventCode": "0xB7, 0xBB",
+        "MSRValue": "0x2000080004",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_HIT_E.SNOOP_NON_DRAM",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "SampleAfterValue": "100003",
+        "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that",
+        "Offcore": "1",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that",
+        "EventCode": "0xB7, 0xBB",
+        "MSRValue": "0x2000040004",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_HIT_M.SNOOP_NON_DRAM",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "SampleAfterValue": "100003",
+        "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that",
+        "Offcore": "1",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that",
+        "EventCode": "0xB7, 0xBB",
+        "MSRValue": "0x2000020004",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.SUPPLIER_NONE.SNOOP_NON_DRAM",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "SampleAfterValue": "100003",
+        "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that",
+        "Offcore": "1",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "PublicDescription": "Counts all demand data writes (RFOs)",
+        "EventCode": "0xB7, 0xBB",
+        "MSRValue": "0x3FFC400002",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_MISS.ANY_SNOOP",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "SampleAfterValue": "100003",
+        "BriefDescription": "Counts all demand data writes (RFOs)",
+        "Offcore": "1",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "PublicDescription": "Counts all demand data writes (RFOs)",
+        "EventCode": "0xB7, 0xBB",
+        "MSRValue": "0x203C400002",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_MISS.SNOOP_NON_DRAM",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "SampleAfterValue": "100003",
+        "BriefDescription": "Counts all demand data writes (RFOs)",
+        "Offcore": "1",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "PublicDescription": "Counts all demand data writes (RFOs)",
+        "EventCode": "0xB7, 0xBB",
+        "MSRValue": "0x103C400002",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_MISS.SNOOP_HITM",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "SampleAfterValue": "100003",
+        "BriefDescription": "Counts all demand data writes (RFOs)",
+        "Offcore": "1",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "PublicDescription": "Counts all demand data writes (RFOs)",
+        "EventCode": "0xB7, 0xBB",
+        "MSRValue": "0x043C400002",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_MISS.SNOOP_HIT_NO_FWD",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "SampleAfterValue": "100003",
+        "BriefDescription": "Counts all demand data writes (RFOs)",
+        "Offcore": "1",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "PublicDescription": "Counts all demand data writes (RFOs)",
+        "EventCode": "0xB7, 0xBB",
+        "MSRValue": "0x023C400002",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_MISS.SNOOP_MISS",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "SampleAfterValue": "100003",
+        "BriefDescription": "Counts all demand data writes (RFOs)",
+        "Offcore": "1",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "PublicDescription": "Counts all demand data writes (RFOs)",
+        "EventCode": "0xB7, 0xBB",
+        "MSRValue": "0x013C400002",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_MISS.SNOOP_NOT_NEEDED",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "SampleAfterValue": "100003",
+        "BriefDescription": "Counts all demand data writes (RFOs)",
+        "Offcore": "1",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "PublicDescription": "Counts all demand data writes (RFOs)",
+        "EventCode": "0xB7, 0xBB",
+        "MSRValue": "0x00BC400002",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_MISS.SNOOP_NONE",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "SampleAfterValue": "100003",
+        "BriefDescription": "Counts all demand data writes (RFOs)",
+        "Offcore": "1",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "PublicDescription": "Counts all demand data writes (RFOs)",
+        "EventCode": "0xB7, 0xBB",
+        "MSRValue": "0x007C400002",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_MISS.SPL_HIT",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "SampleAfterValue": "100003",
+        "BriefDescription": "Counts all demand data writes (RFOs)",
+        "Offcore": "1",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "PublicDescription": "Counts all demand data writes (RFOs)",
+        "EventCode": "0xB7, 0xBB",
+        "MSRValue": "0x3FC4000002",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_MISS_LOCAL_DRAM.ANY_SNOOP",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "SampleAfterValue": "100003",
+        "BriefDescription": "Counts all demand data writes (RFOs)",
+        "Offcore": "1",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "PublicDescription": "Counts all demand data writes (RFOs)",
+        "EventCode": "0xB7, 0xBB",
+        "MSRValue": "0x2004000002",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_MISS_LOCAL_DRAM.SNOOP_NON_DRAM",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "SampleAfterValue": "100003",
+        "BriefDescription": "Counts all demand data writes (RFOs)",
+        "Offcore": "1",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "PublicDescription": "Counts all demand data writes (RFOs)",
+        "EventCode": "0xB7, 0xBB",
+        "MSRValue": "0x1004000002",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_MISS_LOCAL_DRAM.SNOOP_HITM",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "SampleAfterValue": "100003",
+        "BriefDescription": "Counts all demand data writes (RFOs)",
+        "Offcore": "1",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "PublicDescription": "Counts all demand data writes (RFOs)",
+        "EventCode": "0xB7, 0xBB",
+        "MSRValue": "0x0404000002",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_MISS_LOCAL_DRAM.SNOOP_HIT_NO_FWD",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "SampleAfterValue": "100003",
+        "BriefDescription": "Counts all demand data writes (RFOs)",
+        "Offcore": "1",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "PublicDescription": "Counts all demand data writes (RFOs)",
+        "EventCode": "0xB7, 0xBB",
+        "MSRValue": "0x0204000002",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_MISS_LOCAL_DRAM.SNOOP_MISS",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "SampleAfterValue": "100003",
+        "BriefDescription": "Counts all demand data writes (RFOs)",
+        "Offcore": "1",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "PublicDescription": "Counts all demand data writes (RFOs)",
+        "EventCode": "0xB7, 0xBB",
+        "MSRValue": "0x0104000002",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_MISS_LOCAL_DRAM.SNOOP_NOT_NEEDED",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "SampleAfterValue": "100003",
+        "BriefDescription": "Counts all demand data writes (RFOs)",
+        "Offcore": "1",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "PublicDescription": "Counts all demand data writes (RFOs)",
+        "EventCode": "0xB7, 0xBB",
+        "MSRValue": "0x0084000002",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_MISS_LOCAL_DRAM.SNOOP_NONE",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "SampleAfterValue": "100003",
+        "BriefDescription": "Counts all demand data writes (RFOs)",
+        "Offcore": "1",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "PublicDescription": "Counts all demand data writes (RFOs)",
+        "EventCode": "0xB7, 0xBB",
+        "MSRValue": "0x0044000002",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_MISS_LOCAL_DRAM.SPL_HIT",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "SampleAfterValue": "100003",
+        "BriefDescription": "Counts all demand data writes (RFOs)",
+        "Offcore": "1",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "PublicDescription": "Counts all demand data writes (RFOs)",
+        "EventCode": "0xB7, 0xBB",
+        "MSRValue": "0x2000400002",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L4_HIT_LOCAL_L4.SNOOP_NON_DRAM",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "SampleAfterValue": "100003",
+        "BriefDescription": "Counts all demand data writes (RFOs)",
+        "Offcore": "1",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "PublicDescription": "Counts all demand data writes (RFOs)",
+        "EventCode": "0xB7, 0xBB",
+        "MSRValue": "0x20001C0002",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_HIT.SNOOP_NON_DRAM",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "SampleAfterValue": "100003",
+        "BriefDescription": "Counts all demand data writes (RFOs)",
+        "Offcore": "1",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "PublicDescription": "Counts all demand data writes (RFOs)",
+        "EventCode": "0xB7, 0xBB",
+        "MSRValue": "0x2000100002",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_HIT_S.SNOOP_NON_DRAM",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "SampleAfterValue": "100003",
+        "BriefDescription": "Counts all demand data writes (RFOs)",
+        "Offcore": "1",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "PublicDescription": "Counts all demand data writes (RFOs)",
+        "EventCode": "0xB7, 0xBB",
+        "MSRValue": "0x2000080002",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_HIT_E.SNOOP_NON_DRAM",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "SampleAfterValue": "100003",
+        "BriefDescription": "Counts all demand data writes (RFOs)",
+        "Offcore": "1",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "PublicDescription": "Counts all demand data writes (RFOs)",
+        "EventCode": "0xB7, 0xBB",
+        "MSRValue": "0x2000040002",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_HIT_M.SNOOP_NON_DRAM",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "SampleAfterValue": "100003",
+        "BriefDescription": "Counts all demand data writes (RFOs)",
+        "Offcore": "1",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "PublicDescription": "Counts all demand data writes (RFOs)",
+        "EventCode": "0xB7, 0xBB",
+        "MSRValue": "0x2000020002",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.SUPPLIER_NONE.SNOOP_NON_DRAM",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "SampleAfterValue": "100003",
+        "BriefDescription": "Counts all demand data writes (RFOs)",
+        "Offcore": "1",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "PublicDescription": "Counts demand data reads",
+        "EventCode": "0xB7, 0xBB",
+        "MSRValue": "0x3FFC400001",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_MISS.ANY_SNOOP",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "SampleAfterValue": "100003",
+        "BriefDescription": "Counts demand data reads",
+        "Offcore": "1",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "PublicDescription": "Counts demand data reads",
+        "EventCode": "0xB7, 0xBB",
+        "MSRValue": "0x203C400001",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_MISS.SNOOP_NON_DRAM",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "DEMAND_DATA_RD & L3_MISS & ANY_SNOOP",
+        "BriefDescription": "Counts demand data reads",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts demand data reads",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x103c000001 ",
+        "MSRValue": "0x103C400001",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_MISS.SNOOP_HITM",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "DEMAND_DATA_RD & L3_MISS & SNOOP_HITM",
+        "BriefDescription": "Counts demand data reads",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts demand data reads",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x043c000001 ",
+        "MSRValue": "0x043C400001",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_MISS.SNOOP_HIT_NO_FWD",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "DEMAND_DATA_RD & L3_MISS & SNOOP_HIT_NO_FWD",
+        "BriefDescription": "Counts demand data reads",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts demand data reads",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x023c000001 ",
+        "MSRValue": "0x023C400001",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_MISS.SNOOP_MISS",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "DEMAND_DATA_RD & L3_MISS & SNOOP_MISS",
+        "BriefDescription": "Counts demand data reads",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts demand data reads",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x013c000001 ",
+        "MSRValue": "0x013C400001",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_MISS.SNOOP_NOT_NEEDED",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "DEMAND_DATA_RD & L3_MISS & SNOOP_NOT_NEEDED",
+        "BriefDescription": "Counts demand data reads",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts demand data reads",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x00bc000001 ",
+        "MSRValue": "0x00BC400001",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_MISS.SNOOP_NONE",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "DEMAND_DATA_RD & L3_MISS & SNOOP_NONE",
+        "BriefDescription": "Counts demand data reads",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts demand data reads",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x3fc4000001 ",
+        "MSRValue": "0x007C400001",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_MISS.SPL_HIT",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "SampleAfterValue": "100003",
+        "BriefDescription": "Counts demand data reads",
+        "Offcore": "1",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "PublicDescription": "Counts demand data reads",
+        "EventCode": "0xB7, 0xBB",
+        "MSRValue": "0x3FC4000001",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_MISS_LOCAL_DRAM.ANY_SNOOP",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "SampleAfterValue": "100003",
+        "BriefDescription": "Counts demand data reads",
+        "Offcore": "1",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "PublicDescription": "Counts demand data reads",
+        "EventCode": "0xB7, 0xBB",
+        "MSRValue": "0x2004000001",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_MISS_LOCAL_DRAM.SNOOP_NON_DRAM",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "DEMAND_DATA_RD & L3_MISS_LOCAL_DRAM & ANY_SNOOP",
+        "BriefDescription": "Counts demand data reads",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts demand data reads",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x1004000001 ",
+        "MSRValue": "0x1004000001",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_MISS_LOCAL_DRAM.SNOOP_HITM",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "DEMAND_DATA_RD & L3_MISS_LOCAL_DRAM & SNOOP_HITM",
+        "BriefDescription": "Counts demand data reads",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts demand data reads",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0404000001 ",
+        "MSRValue": "0x0404000001",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_MISS_LOCAL_DRAM.SNOOP_HIT_NO_FWD",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "DEMAND_DATA_RD & L3_MISS_LOCAL_DRAM & SNOOP_HIT_NO_FWD",
+        "BriefDescription": "Counts demand data reads",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts demand data reads",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0204000001 ",
+        "MSRValue": "0x0204000001",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_MISS_LOCAL_DRAM.SNOOP_MISS",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "DEMAND_DATA_RD & L3_MISS_LOCAL_DRAM & SNOOP_MISS",
+        "BriefDescription": "Counts demand data reads",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts demand data reads",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0104000001 ",
+        "MSRValue": "0x0104000001",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_MISS_LOCAL_DRAM.SNOOP_NOT_NEEDED",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "DEMAND_DATA_RD & L3_MISS_LOCAL_DRAM & SNOOP_NOT_NEEDED",
+        "BriefDescription": "Counts demand data reads",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     },
     {
-        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "PublicDescription": "Counts demand data reads",
         "EventCode": "0xB7, 0xBB",
-        "MSRValue": "0x0084000001 ",
+        "MSRValue": "0x0084000001",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_MISS_LOCAL_DRAM.SNOOP_NONE",
-        "MSRIndex": "0x1a6,0x1a7",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "SampleAfterValue": "100003",
+        "BriefDescription": "Counts demand data reads",
+        "Offcore": "1",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "PublicDescription": "Counts demand data reads",
+        "EventCode": "0xB7, 0xBB",
+        "MSRValue": "0x0044000001",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_MISS_LOCAL_DRAM.SPL_HIT",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "SampleAfterValue": "100003",
+        "BriefDescription": "Counts demand data reads",
+        "Offcore": "1",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "PublicDescription": "Counts demand data reads",
+        "EventCode": "0xB7, 0xBB",
+        "MSRValue": "0x2000400001",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L4_HIT_LOCAL_L4.SNOOP_NON_DRAM",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "SampleAfterValue": "100003",
+        "BriefDescription": "Counts demand data reads",
+        "Offcore": "1",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "PublicDescription": "Counts demand data reads",
+        "EventCode": "0xB7, 0xBB",
+        "MSRValue": "0x20001C0001",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_HIT.SNOOP_NON_DRAM",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "SampleAfterValue": "100003",
+        "BriefDescription": "Counts demand data reads",
+        "Offcore": "1",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "PublicDescription": "Counts demand data reads",
+        "EventCode": "0xB7, 0xBB",
+        "MSRValue": "0x2000100001",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_HIT_S.SNOOP_NON_DRAM",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "SampleAfterValue": "100003",
+        "BriefDescription": "Counts demand data reads",
+        "Offcore": "1",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "PublicDescription": "Counts demand data reads",
+        "EventCode": "0xB7, 0xBB",
+        "MSRValue": "0x2000080001",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_HIT_E.SNOOP_NON_DRAM",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "SampleAfterValue": "100003",
+        "BriefDescription": "Counts demand data reads",
+        "Offcore": "1",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "PublicDescription": "Counts demand data reads",
+        "EventCode": "0xB7, 0xBB",
+        "MSRValue": "0x2000040001",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_HIT_M.SNOOP_NON_DRAM",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "SampleAfterValue": "100003",
+        "BriefDescription": "Counts demand data reads",
+        "Offcore": "1",
+        "CounterHTOff": "0,1,2,3"
+    },
+    {
+        "PublicDescription": "Counts demand data reads",
+        "EventCode": "0xB7, 0xBB",
+        "MSRValue": "0x2000020001",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.SUPPLIER_NONE.SNOOP_NON_DRAM",
+        "MSRIndex": "0x1a6, 0x1a7",
         "SampleAfterValue": "100003",
-        "BriefDescription": "DEMAND_DATA_RD & L3_MISS_LOCAL_DRAM & SNOOP_NONE",
+        "BriefDescription": "Counts demand data reads",
         "Offcore": "1",
         "CounterHTOff": "0,1,2,3"
     }
diff --git a/tools/perf/pmu-events/arch/x86/skylake/pipeline.json b/tools/perf/pmu-events/arch/x86/skylake/pipeline.json
index bc6d2afbcd8a..4a891fbbc4bb 100644
--- a/tools/perf/pmu-events/arch/x86/skylake/pipeline.json
+++ b/tools/perf/pmu-events/arch/x86/skylake/pipeline.json
@@ -1,7 +1,6 @@
 [
     {
         "PublicDescription": "Counts the number of instructions retired from execution. For instructions that consist of multiple micro-ops, Counts the retirement of the last micro-op of the instruction. Counting continues during hardware interrupts, traps, and inside interrupt handlers. Notes: INST_RETIRED.ANY is counted by a designated fixed counter, leaving the four (eight when Hyperthreading is disabled) programmable counters available for other events. INST_RETIRED.ANY_P is counted by a programmable counter and it is an architectural performance event. Counting: Faulting executions of GETSEC/VM entry/VM Exit/MWait will not count as retired instructions.",
-        "EventCode": "0x00",
         "Counter": "Fixed counter 0",
         "UMask": "0x1",
         "EventName": "INST_RETIRED.ANY",
@@ -11,7 +10,6 @@
     },
     {
         "PublicDescription": "Counts the number of core cycles while the thread is not in a halt state. The thread enters the halt state when it is running the HLT instruction. This event is a component in many key event ratios. The core frequency may change from time to time due to transitions associated with Enhanced Intel SpeedStep Technology or TM2. For this reason this event may have a changing ratio with regards to time. When the core frequency is constant, this event can approximate elapsed time while the core was not in the halt state. It is counted on a dedicated fixed counter, leaving the four (eight when Hyperthreading is disabled) programmable counters available for other events.",
-        "EventCode": "0x00",
         "Counter": "Fixed counter 1",
         "UMask": "0x2",
         "EventName": "CPU_CLK_UNHALTED.THREAD",
@@ -20,7 +18,6 @@
         "CounterHTOff": "Fixed counter 1"
     },
     {
-        "EventCode": "0x00",
         "Counter": "Fixed counter 1",
         "UMask": "0x2",
         "AnyThread": "1",
@@ -31,7 +28,6 @@
     },
     {
         "PublicDescription": "Counts the number of reference cycles when the core is not in a halt state. The core enters the halt state when it is running the HLT instruction or the MWAIT instruction. This event is not affected by core frequency changes (for example, P states, TM2 transitions) but has the same incrementing frequency as the time stamp counter. This event can approximate elapsed time while the core was not in a halt state. This event has a constant ratio with the CPU_CLK_UNHALTED.REF_XCLK event. It is counted on a dedicated fixed counter, leaving the four (eight when Hyperthreading is disabled) programmable counters available for other events. Note: On all current platforms this event stops counting during 'throttling (TM)' states duty off periods the processor is 'halted'.  The counter update is done at a lower clock rate then the core clock the overflow status bit for this counter may appear 'sticky'.  After the counter has overflowed and software clears the overflow status bit and resets the counter to less than MAX. The reset value to the counter is not clocked immediately so the overflow status bit will flip 'high (1)' and generate another PMI (if enabled) after which the reset value gets clocked into the counter. Therefore, software will get the interrupt, read the overflow status bit '1 for bit 34 while the counter value is less than MAX. Software should ignore this case.",
-        "EventCode": "0x00",
         "Counter": "Fixed counter 2",
         "UMask": "0x3",
         "EventName": "CPU_CLK_UNHALTED.REF_TSC",
@@ -121,7 +117,7 @@
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "PublicDescription": "Counts the number of Blend Uops issued by the Resource Allocation Table (RAT) to the reservation station (RS) in order to preserve upper bits of vector registers. Starting with the Skylake microarchitecture, these Blend uops are needed since every Intel SSE instruction executed in Dirty Upper State needs to preserve bits 128-255 of the destination register. For more information, refer to Mixing Intel AVX and Intel SSE Code section of the Optimization Guide.",
+        "PublicDescription": "Counts the number of Blend Uops issued by the Resource Allocation Table (RAT) to the reservation station (RS) in order to preserve upper bits of vector registers. Starting with the Skylake microarchitecture, these Blend uops are needed since every Intel SSE instruction executed in Dirty Upper State needs to preserve bits 128-255 of the destination register. For more information, refer to \u201cMixing Intel AVX and Intel SSE Code\u201d section of the Optimization Guide.",
         "EventCode": "0x0E",
         "Counter": "0,1,2,3",
         "UMask": "0x2",
@@ -248,6 +244,16 @@
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
+        "PublicDescription": "This event counts cycles during which the microcode scoreboard stalls happen.",
+        "EventCode": "0x59",
+        "Counter": "0,1,2,3",
+        "UMask": "0x1",
+        "EventName": "PARTIAL_RAT_STALLS.SCOREBOARD",
+        "SampleAfterValue": "2000003",
+        "BriefDescription": "Cycles where the pipeline is stalled due to serializing operations.",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
         "PublicDescription": "Counts cycles during which the reservation station (RS) is empty for the thread.; Note: In ST-mode, not active thread should drive 0. This is usually caused by severely costly branch mispredictions, or allocator/FE issues.",
         "EventCode": "0x5E",
         "Counter": "0,1,2,3",
@@ -361,8 +367,8 @@
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "PublicDescription": "Counts resource-related stall cycles. Reasons for stalls can be as follows:a. *any* u-arch structure got full (LB, SB, RS, ROB, BOB, LM, Physical Register Reclaim Table (PRRT), or Physical History Table (PHT) slots).b. *any* u-arch structure got empty (like INT/SIMD FreeLists).c. FPU control word (FPCW), MXCSR.and others. This counts cycles that the pipeline back-end blocked uop delivery from the front-end.",
-        "EventCode": "0xA2",
+        "PublicDescription": "Counts resource-related stall cycles.",
+        "EventCode": "0xa2",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
         "EventName": "RESOURCE_STALLS.ANY",
@@ -735,7 +741,7 @@
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "PublicDescription": "This is a non-precise version (that is, does not use PEBS) of the event that counts cycles without actually retired uops.",
+        "PublicDescription": "This event counts cycles without actually retired uops.",
         "EventCode": "0xC2",
         "Invert": "1",
         "Counter": "0,1,2,3",
@@ -759,6 +765,7 @@
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
+        "PublicDescription": "Number of machine clears (nukes) of any type.",
         "EventCode": "0xC3",
         "Counter": "0,1,2,3",
         "UMask": "0x1",
@@ -839,14 +846,15 @@
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "PublicDescription": "This is a non-precise version (that is, does not use PEBS) of the event that counts not taken branch instructions retired.",
+        "PEBS": "1",
+        "PublicDescription": "This is a precise version (that is, uses PEBS) of the event that counts not taken branch instructions retired.",
         "EventCode": "0xC4",
         "Counter": "0,1,2,3",
         "UMask": "0x10",
         "Errata": "SKL091",
         "EventName": "BR_INST_RETIRED.NOT_TAKEN",
         "SampleAfterValue": "400009",
-        "BriefDescription": "Not taken branch instructions retired.",
+        "BriefDescription": "Counts all not taken macro branch instructions retired.",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
@@ -924,7 +932,7 @@
         "UMask": "0x20",
         "EventName": "BR_MISP_RETIRED.NEAR_TAKEN",
         "SampleAfterValue": "400009",
-        "BriefDescription": "Number of near branch instructions retired that were mispredicted and taken. ",
+        "BriefDescription": "Number of near branch instructions retired that were mispredicted and taken.",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
@@ -938,6 +946,15 @@
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
+        "EventCode": "0xCC",
+        "Counter": "0,1,2,3",
+        "UMask": "0x40",
+        "EventName": "ROB_MISC_EVENTS.PAUSE_INST",
+        "SampleAfterValue": "2000003",
+        "BriefDescription": "Number of retired PAUSE instructions (that do not end up with a VMExit to the VMM; TSX aborted Instructions may be counted). This event is not supported on first SKL and KBL products.",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
         "PublicDescription": "Counts the number of times the front-end is resteered when it finds a branch instruction in a fetch line. This occurs for the first time a branch instruction is fetched or when the branch is not tracked by the BPU (Branch Prediction Unit) anymore.",
         "EventCode": "0xE6",
         "Counter": "0,1,2,3",
diff --git a/tools/perf/pmu-events/arch/x86/skylake/skl-metrics.json b/tools/perf/pmu-events/arch/x86/skylake/skl-metrics.json
index 71e9737f4614..2c95417a4dae 100644
--- a/tools/perf/pmu-events/arch/x86/skylake/skl-metrics.json
+++ b/tools/perf/pmu-events/arch/x86/skylake/skl-metrics.json
@@ -1,164 +1,364 @@
 [
     {
-        "BriefDescription": "Instructions Per Cycle (per logical thread)",
+        "MetricExpr": "IDQ_UOPS_NOT_DELIVERED.CORE / (4 * cycles)",
+        "PublicDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend. Frontend denotes the first part of the processor core responsible to fetch operations that are executed later on by the Backend part. Within the Frontend; a branch predictor predicts the next address to fetch; cache-lines are fetched from the memory subsystem; parsed into instructions; and lastly decoded into micro-ops (uops). Ideally the Frontend can issue 4 uops every cycle to the Backend. Frontend Bound denotes unutilized issue-slots when there is no Backend stall; i.e. bubbles where Frontend delivered no uops while Backend could have accepted them. For example; stalls due to instruction-cache misses would be categorized under Frontend Bound.",
+        "BriefDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend",
+        "MetricGroup": "TopdownL1",
+        "MetricName": "Frontend_Bound"
+    },
+    {
+        "MetricExpr": "IDQ_UOPS_NOT_DELIVERED.CORE / (4 * (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )))",
+        "PublicDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend. Frontend denotes the first part of the processor core responsible to fetch operations that are executed later on by the Backend part. Within the Frontend; a branch predictor predicts the next address to fetch; cache-lines are fetched from the memory subsystem; parsed into instructions; and lastly decoded into micro-ops (uops). Ideally the Frontend can issue 4 uops every cycle to the Backend. Frontend Bound denotes unutilized issue-slots when there is no Backend stall; i.e. bubbles where Frontend delivered no uops while Backend could have accepted them. For example; stalls due to instruction-cache misses would be categorized under Frontend Bound. SMT version; use when SMT is enabled and measuring per logical CPU.",
+        "BriefDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend. SMT version; use when SMT is enabled and measuring per logical CPU.",
+        "MetricGroup": "TopdownL1_SMT",
+        "MetricName": "Frontend_Bound_SMT"
+    },
+    {
+        "MetricExpr": "( UOPS_ISSUED.ANY - UOPS_RETIRED.RETIRE_SLOTS + 4 * INT_MISC.RECOVERY_CYCLES ) / (4 * cycles)",
+        "PublicDescription": "This category represents fraction of slots wasted due to incorrect speculations. This include slots used to issue uops that do not eventually get retired and slots for which the issue-pipeline was blocked due to recovery from earlier incorrect speculation. For example; wasted work due to miss-predicted branches are categorized under Bad Speculation category. Incorrect data speculation followed by Memory Ordering Nukes is another example.",
+        "BriefDescription": "This category represents fraction of slots wasted due to incorrect speculations",
+        "MetricGroup": "TopdownL1",
+        "MetricName": "Bad_Speculation"
+    },
+    {
+        "MetricExpr": "( UOPS_ISSUED.ANY - UOPS_RETIRED.RETIRE_SLOTS + 4 * (( INT_MISC.RECOVERY_CYCLES_ANY / 2 )) ) / (4 * (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )))",
+        "PublicDescription": "This category represents fraction of slots wasted due to incorrect speculations. This include slots used to issue uops that do not eventually get retired and slots for which the issue-pipeline was blocked due to recovery from earlier incorrect speculation. For example; wasted work due to miss-predicted branches are categorized under Bad Speculation category. Incorrect data speculation followed by Memory Ordering Nukes is another example. SMT version; use when SMT is enabled and measuring per logical CPU.",
+        "BriefDescription": "This category represents fraction of slots wasted due to incorrect speculations. SMT version; use when SMT is enabled and measuring per logical CPU.",
+        "MetricGroup": "TopdownL1_SMT",
+        "MetricName": "Bad_Speculation_SMT"
+    },
+    {
+        "MetricExpr": "1 - ( (IDQ_UOPS_NOT_DELIVERED.CORE / (4 * cycles)) + (( UOPS_ISSUED.ANY - UOPS_RETIRED.RETIRE_SLOTS + 4 * INT_MISC.RECOVERY_CYCLES ) / (4 * cycles)) + (UOPS_RETIRED.RETIRE_SLOTS / (4 * cycles)) )",
+        "PublicDescription": "This category represents fraction of slots where no uops are being delivered due to a lack of required resources for accepting new uops in the Backend. Backend is the portion of the processor core where the out-of-order scheduler dispatches ready uops into their respective execution units; and once completed these uops get retired according to program order. For example; stalls due to data-cache misses or stalls due to the divider unit being overloaded are both categorized under Backend Bound. Backend Bound is further divided into two main categories: Memory Bound and Core Bound.",
+        "BriefDescription": "This category represents fraction of slots where no uops are being delivered due to a lack of required resources for accepting new uops in the Backend",
+        "MetricGroup": "TopdownL1",
+        "MetricName": "Backend_Bound"
+    },
+    {
+        "MetricExpr": "1 - ( (IDQ_UOPS_NOT_DELIVERED.CORE / (4 * (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )))) + (( UOPS_ISSUED.ANY - UOPS_RETIRED.RETIRE_SLOTS + 4 * (( INT_MISC.RECOVERY_CYCLES_ANY / 2 )) ) / (4 * (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )))) + (UOPS_RETIRED.RETIRE_SLOTS / (4 * (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )))) )",
+        "PublicDescription": "This category represents fraction of slots where no uops are being delivered due to a lack of required resources for accepting new uops in the Backend. Backend is the portion of the processor core where the out-of-order scheduler dispatches ready uops into their respective execution units; and once completed these uops get retired according to program order. For example; stalls due to data-cache misses or stalls due to the divider unit being overloaded are both categorized under Backend Bound. Backend Bound is further divided into two main categories: Memory Bound and Core Bound. SMT version; use when SMT is enabled and measuring per logical CPU.",
+        "BriefDescription": "This category represents fraction of slots where no uops are being delivered due to a lack of required resources for accepting new uops in the Backend. SMT version; use when SMT is enabled and measuring per logical CPU.",
+        "MetricGroup": "TopdownL1_SMT",
+        "MetricName": "Backend_Bound_SMT"
+    },
+    {
+        "MetricExpr": "UOPS_RETIRED.RETIRE_SLOTS / (4 * cycles)",
+        "PublicDescription": "This category represents fraction of slots utilized by useful work i.e. issued uops that eventually get retired. Ideally; all pipeline slots would be attributed to the Retiring category.  Retiring of 100% would indicate the maximum 4 uops retired per cycle has been achieved.  Maximizing Retiring typically increases the Instruction-Per-Cycle metric. Note that a high Retiring value does not necessary mean there is no room for more performance.  For example; Microcode assists are categorized under Retiring. They hurt performance and can often be avoided. ",
+        "BriefDescription": "This category represents fraction of slots utilized by useful work i.e. issued uops that eventually get retired",
+        "MetricGroup": "TopdownL1",
+        "MetricName": "Retiring"
+    },
+    {
+        "MetricExpr": "UOPS_RETIRED.RETIRE_SLOTS / (4 * (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )))",
+        "PublicDescription": "This category represents fraction of slots utilized by useful work i.e. issued uops that eventually get retired. Ideally; all pipeline slots would be attributed to the Retiring category.  Retiring of 100% would indicate the maximum 4 uops retired per cycle has been achieved.  Maximizing Retiring typically increases the Instruction-Per-Cycle metric. Note that a high Retiring value does not necessary mean there is no room for more performance.  For example; Microcode assists are categorized under Retiring. They hurt performance and can often be avoided. SMT version; use when SMT is enabled and measuring per logical CPU.",
+        "BriefDescription": "This category represents fraction of slots utilized by useful work i.e. issued uops that eventually get retired. SMT version; use when SMT is enabled and measuring per logical CPU.",
+        "MetricGroup": "TopdownL1_SMT",
+        "MetricName": "Retiring_SMT"
+    },
+    {
         "MetricExpr": "INST_RETIRED.ANY / CPU_CLK_UNHALTED.THREAD",
+        "BriefDescription": "Instructions Per Cycle (per logical thread)",
         "MetricGroup": "TopDownL1",
         "MetricName": "IPC"
     },
     {
-        "BriefDescription": "Uops Per Instruction",
         "MetricExpr": "UOPS_RETIRED.RETIRE_SLOTS / INST_RETIRED.ANY",
-        "MetricGroup": "Pipeline",
+        "BriefDescription": "Uops Per Instruction",
+        "MetricGroup": "Pipeline;Retiring",
         "MetricName": "UPI"
     },
     {
-        "BriefDescription": "Rough Estimation of fraction of fetched lines bytes that were likely consumed by program instructions",
-        "MetricExpr": "min( 1 , UOPS_ISSUED.ANY / ((UOPS_RETIRED.RETIRE_SLOTS / INST_RETIRED.ANY) * 64 * ( ICACHE_64B.IFTAG_HIT + ICACHE_64B.IFTAG_MISS ) / 4.1) )",
-        "MetricGroup": "Frontend",
+        "MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.NEAR_TAKEN",
+        "BriefDescription": "Instruction per taken branch",
+        "MetricGroup": "Branches;PGO",
+        "MetricName": "IpTB"
+    },
+    {
+        "MetricExpr": "BR_INST_RETIRED.ALL_BRANCHES / BR_INST_RETIRED.NEAR_TAKEN",
+        "BriefDescription": "Branch instructions per taken branch. ",
+        "MetricGroup": "Branches;PGO",
+        "MetricName": "BpTB"
+    },
+    {
+        "MetricExpr": "min( 1 , UOPS_ISSUED.ANY / ( (UOPS_RETIRED.RETIRE_SLOTS / INST_RETIRED.ANY) * 64 * ( ICACHE_64B.IFTAG_HIT + ICACHE_64B.IFTAG_MISS ) / 4.1 ) )",
+        "BriefDescription": "Rough Estimation of fraction of fetched lines bytes that were likely (includes speculatively fetches) consumed by program instructions",
+        "MetricGroup": "PGO",
         "MetricName": "IFetch_Line_Utilization"
     },
     {
-        "BriefDescription": "Fraction of Uops delivered by the DSB (aka Decoded Icache; or Uop Cache)",
-        "MetricExpr": "IDQ.DSB_UOPS / ( IDQ.DSB_UOPS + LSD.UOPS + IDQ.MITE_UOPS + IDQ.MS_UOPS )",
-        "MetricGroup": "DSB; Frontend_Bandwidth",
+        "MetricExpr": "IDQ.DSB_UOPS / (( IDQ.DSB_UOPS + IDQ.MITE_UOPS + IDQ.MS_UOPS ))",
+        "BriefDescription": "Fraction of Uops delivered by the DSB (aka Decoded ICache; or Uop Cache)",
+        "MetricGroup": "DSB;Frontend_Bandwidth",
         "MetricName": "DSB_Coverage"
     },
     {
-        "BriefDescription": "Cycles Per Instruction (threaded)",
         "MetricExpr": "1 / (INST_RETIRED.ANY / cycles)",
+        "BriefDescription": "Cycles Per Instruction (threaded)",
         "MetricGroup": "Pipeline;Summary",
         "MetricName": "CPI"
     },
     {
-        "BriefDescription": "Per-thread actual clocks when the logical processor is active. This is called 'Clockticks' in VTune.",
         "MetricExpr": "CPU_CLK_UNHALTED.THREAD",
+        "BriefDescription": "Per-thread actual clocks when the logical processor is active.",
         "MetricGroup": "Summary",
         "MetricName": "CLKS"
     },
     {
-        "BriefDescription": "Total issue-pipeline slots",
-        "MetricExpr": "4*(( CPU_CLK_UNHALTED.THREAD_ANY / 2 ) if #SMT_on else cycles)",
+        "MetricExpr": "4 * cycles",
+        "BriefDescription": "Total issue-pipeline slots (per core)",
         "MetricGroup": "TopDownL1",
         "MetricName": "SLOTS"
     },
     {
-        "BriefDescription": "Total number of retired Instructions",
+        "MetricExpr": "4 * (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) ))",
+        "BriefDescription": "Total issue-pipeline slots (per core)",
+        "MetricGroup": "TopDownL1_SMT",
+        "MetricName": "SLOTS_SMT"
+    },
+    {
+        "MetricExpr": "INST_RETIRED.ANY / MEM_INST_RETIRED.ALL_LOADS",
+        "BriefDescription": "Instructions per Load (lower number means loads are more frequent)",
+        "MetricGroup": "Instruction_Type;L1_Bound",
+        "MetricName": "IpL"
+    },
+    {
+        "MetricExpr": "INST_RETIRED.ANY / MEM_INST_RETIRED.ALL_STORES",
+        "BriefDescription": "Instructions per Store",
+        "MetricGroup": "Instruction_Type;Store_Bound",
+        "MetricName": "IpS"
+    },
+    {
+        "MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.ALL_BRANCHES",
+        "BriefDescription": "Instructions per Branch",
+        "MetricGroup": "Branches;Instruction_Type;Port_5;Port_6",
+        "MetricName": "IpB"
+    },
+    {
+        "MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.NEAR_CALL",
+        "BriefDescription": "Instruction per (near) call",
+        "MetricGroup": "Branches",
+        "MetricName": "IpCall"
+    },
+    {
         "MetricExpr": "INST_RETIRED.ANY",
+        "BriefDescription": "Total number of retired Instructions",
         "MetricGroup": "Summary",
         "MetricName": "Instructions"
     },
     {
+        "MetricExpr": "INST_RETIRED.ANY / cycles",
         "BriefDescription": "Instructions Per Cycle (per physical core)",
-        "MetricExpr": "INST_RETIRED.ANY / (( CPU_CLK_UNHALTED.THREAD_ANY / 2 ) if #SMT_on else cycles)",
         "MetricGroup": "SMT",
         "MetricName": "CoreIPC"
     },
     {
+        "MetricExpr": "INST_RETIRED.ANY / (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) ))",
+        "BriefDescription": "Instructions Per Cycle (per physical core)",
+        "MetricGroup": "SMT",
+        "MetricName": "CoreIPC_SMT"
+    },
+    {
+        "MetricExpr": "(( 1 * ( FP_ARITH_INST_RETIRED.SCALAR_SINGLE + FP_ARITH_INST_RETIRED.SCALAR_DOUBLE ) + 2 * FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE + 4 * ( FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE + FP_ARITH_INST_RETIRED.256B_PACKED_DOUBLE ) + 8 * FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE )) / cycles",
+        "BriefDescription": "Floating Point Operations Per Cycle",
+        "MetricGroup": "FLOPS",
+        "MetricName": "FLOPc"
+    },
+    {
+        "MetricExpr": "(( 1 * ( FP_ARITH_INST_RETIRED.SCALAR_SINGLE + FP_ARITH_INST_RETIRED.SCALAR_DOUBLE ) + 2 * FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE + 4 * ( FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE + FP_ARITH_INST_RETIRED.256B_PACKED_DOUBLE ) + 8 * FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE )) / (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) ))",
+        "BriefDescription": "Floating Point Operations Per Cycle",
+        "MetricGroup": "FLOPS_SMT",
+        "MetricName": "FLOPc_SMT"
+    },
+    {
+        "MetricExpr": "UOPS_EXECUTED.THREAD / (( UOPS_EXECUTED.CORE_CYCLES_GE_1 / 2 ) if #SMT_on else UOPS_EXECUTED.CORE_CYCLES_GE_1)",
         "BriefDescription": "Instruction-Level-Parallelism (average number of uops executed when there is at least 1 uop executed)",
-        "MetricExpr": "UOPS_EXECUTED.THREAD / (( UOPS_EXECUTED.CORE_CYCLES_GE_1 / 2) if #SMT_on else UOPS_EXECUTED.CORE_CYCLES_GE_1)",
         "MetricGroup": "Pipeline;Ports_Utilization",
         "MetricName": "ILP"
     },
     {
-        "BriefDescription": "Average Branch Address Clear Cost (fraction of cycles)",
-        "MetricExpr": "2* (( RS_EVENTS.EMPTY_CYCLES - ICACHE_16B.IFDATA_STALL  - ICACHE_64B.IFTAG_STALL ) / RS_EVENTS.EMPTY_END)",
-        "MetricGroup": "Unknown_Branches",
-        "MetricName": "BAClear_Cost"
+        "MetricExpr": "( ((BR_MISP_RETIRED.ALL_BRANCHES / ( BR_MISP_RETIRED.ALL_BRANCHES + MACHINE_CLEARS.COUNT )) * (( UOPS_ISSUED.ANY - UOPS_RETIRED.RETIRE_SLOTS + 4 * INT_MISC.RECOVERY_CYCLES ) / (4 * cycles))) + (4 * IDQ_UOPS_NOT_DELIVERED.CYCLES_0_UOPS_DELIV.CORE / (4 * cycles)) * (( INT_MISC.CLEAR_RESTEER_CYCLES + 9 * BACLEARS.ANY ) / cycles) / (4 * IDQ_UOPS_NOT_DELIVERED.CYCLES_0_UOPS_DELIV.CORE / (4 * cycles)) ) * (4 * cycles) / BR_MISP_RETIRED.ALL_BRANCHES",
+        "BriefDescription": "Branch Misprediction Cost: Fraction of TopDown slots wasted per branch misprediction (jeclear and baclear)",
+        "MetricGroup": "Branch_Mispredicts",
+        "MetricName": "Branch_Misprediction_Cost"
     },
     {
+        "MetricExpr": "( ((BR_MISP_RETIRED.ALL_BRANCHES / ( BR_MISP_RETIRED.ALL_BRANCHES + MACHINE_CLEARS.COUNT )) * (( UOPS_ISSUED.ANY - UOPS_RETIRED.RETIRE_SLOTS + 4 * (( INT_MISC.RECOVERY_CYCLES_ANY / 2 )) ) / (4 * (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) ))))) + (4 * IDQ_UOPS_NOT_DELIVERED.CYCLES_0_UOPS_DELIV.CORE / (4 * (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )))) * (( INT_MISC.CLEAR_RESTEER_CYCLES + 9 * BACLEARS.ANY ) / cycles) / (4 * IDQ_UOPS_NOT_DELIVERED.CYCLES_0_UOPS_DELIV.CORE / (4 * (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )))) ) * (4 * (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) ))) / BR_MISP_RETIRED.ALL_BRANCHES",
+        "BriefDescription": "Branch Misprediction Cost: Fraction of TopDown slots wasted per branch misprediction (jeclear and baclear)",
+        "MetricGroup": "Branch_Mispredicts_SMT",
+        "MetricName": "Branch_Misprediction_Cost_SMT"
+    },
+    {
+        "MetricExpr": "INST_RETIRED.ANY / BR_MISP_RETIRED.ALL_BRANCHES",
+        "BriefDescription": "Number of Instructions per non-speculative Branch Misprediction (JEClear)",
+        "MetricGroup": "Branch_Mispredicts",
+        "MetricName": "IpMispredict"
+    },
+    {
+        "MetricExpr": "( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )",
         "BriefDescription": "Core actual clocks when any thread is active on the physical core",
-        "MetricExpr": "( CPU_CLK_UNHALTED.THREAD_ANY / 2 ) if #SMT_on else CPU_CLK_UNHALTED.THREAD",
         "MetricGroup": "SMT",
         "MetricName": "CORE_CLKS"
     },
     {
-        "BriefDescription": "Actual Average Latency for L1 data-cache miss demand loads",
         "MetricExpr": "L1D_PEND_MISS.PENDING / ( MEM_LOAD_RETIRED.L1_MISS + MEM_LOAD_RETIRED.FB_HIT )",
+        "BriefDescription": "Actual Average Latency for L1 data-cache miss demand loads (in core cycles)",
         "MetricGroup": "Memory_Bound;Memory_Lat",
         "MetricName": "Load_Miss_Real_Latency"
     },
     {
-        "BriefDescription": "Memory-Level-Parallelism (average number of L1 miss demand load when there is at least 1 such miss)",
-        "MetricExpr": "L1D_PEND_MISS.PENDING / (( L1D_PEND_MISS.PENDING_CYCLES_ANY / 2) if #SMT_on else L1D_PEND_MISS.PENDING_CYCLES)",
+        "MetricExpr": "L1D_PEND_MISS.PENDING / L1D_PEND_MISS.PENDING_CYCLES",
+        "BriefDescription": "Memory-Level-Parallelism (average number of L1 miss demand load when there is at least one such miss. Per-thread)",
         "MetricGroup": "Memory_Bound;Memory_BW",
         "MetricName": "MLP"
     },
     {
+        "MetricExpr": "( ITLB_MISSES.WALK_PENDING + DTLB_LOAD_MISSES.WALK_PENDING + DTLB_STORE_MISSES.WALK_PENDING + EPT.WALK_PENDING ) / ( 2 * cycles )",
         "BriefDescription": "Utilization of the core's Page Walker(s) serving STLB misses triggered by instruction/Load/Store accesses",
-        "MetricExpr": "( ITLB_MISSES.WALK_PENDING + DTLB_LOAD_MISSES.WALK_PENDING + DTLB_STORE_MISSES.WALK_PENDING + EPT.WALK_PENDING ) / ( 2 * (( CPU_CLK_UNHALTED.THREAD_ANY / 2 ) if #SMT_on else cycles) )",
         "MetricGroup": "TLB",
         "MetricName": "Page_Walks_Utilization"
     },
     {
-        "BriefDescription": "Average CPU Utilization",
+        "MetricExpr": "( ITLB_MISSES.WALK_PENDING + DTLB_LOAD_MISSES.WALK_PENDING + DTLB_STORE_MISSES.WALK_PENDING + EPT.WALK_PENDING ) / ( 2 * (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )) )",
+        "BriefDescription": "Utilization of the core's Page Walker(s) serving STLB misses triggered by instruction/Load/Store accesses",
+        "MetricGroup": "TLB_SMT",
+        "MetricName": "Page_Walks_Utilization_SMT"
+    },
+    {
+        "MetricExpr": "64 * L1D.REPLACEMENT / 1000000000 / duration_time",
+        "BriefDescription": "Average data fill bandwidth to the L1 data cache [GB / sec]",
+        "MetricGroup": "Memory_BW",
+        "MetricName": "L1D_Cache_Fill_BW"
+    },
+    {
+        "MetricExpr": "64 * L2_LINES_IN.ALL / 1000000000 / duration_time",
+        "BriefDescription": "Average data fill bandwidth to the L2 cache [GB / sec]",
+        "MetricGroup": "Memory_BW",
+        "MetricName": "L2_Cache_Fill_BW"
+    },
+    {
+        "MetricExpr": "64 * LONGEST_LAT_CACHE.MISS / 1000000000 / duration_time",
+        "BriefDescription": "Average per-core data fill bandwidth to the L3 cache [GB / sec]",
+        "MetricGroup": "Memory_BW",
+        "MetricName": "L3_Cache_Fill_BW"
+    },
+    {
+        "MetricExpr": "64 * OFFCORE_REQUESTS.ALL_REQUESTS / 1000000000 / duration_time",
+        "BriefDescription": "Average per-core data fill bandwidth to the L3 cache [GB / sec]",
+        "MetricGroup": "Memory_BW",
+        "MetricName": "L3_Cache_Access_BW"
+    },
+    {
+        "MetricExpr": "1000 * MEM_LOAD_RETIRED.L1_MISS / INST_RETIRED.ANY",
+        "BriefDescription": "L1 cache true misses per kilo instruction for retired demand loads",
+        "MetricGroup": "Cache_Misses;",
+        "MetricName": "L1MPKI"
+    },
+    {
+        "MetricExpr": "1000 * MEM_LOAD_RETIRED.L2_MISS / INST_RETIRED.ANY",
+        "BriefDescription": "L2 cache true misses per kilo instruction for retired demand loads",
+        "MetricGroup": "Cache_Misses;",
+        "MetricName": "L2MPKI"
+    },
+    {
+        "MetricExpr": "1000 * L2_RQSTS.MISS / INST_RETIRED.ANY",
+        "BriefDescription": "L2 cache misses per kilo instruction for all request types (including speculative)",
+        "MetricGroup": "Cache_Misses;",
+        "MetricName": "L2MPKI_All"
+    },
+    {
+        "MetricExpr": "1000 * ( L2_RQSTS.REFERENCES - L2_RQSTS.MISS ) / INST_RETIRED.ANY",
+        "BriefDescription": "L2 cache hits per kilo instruction for all request types (including speculative)",
+        "MetricGroup": "Cache_Misses;",
+        "MetricName": "L2HPKI_All"
+    },
+    {
+        "MetricExpr": "1000 * MEM_LOAD_RETIRED.L3_MISS / INST_RETIRED.ANY",
+        "BriefDescription": "L3 cache true misses per kilo instruction for retired demand loads",
+        "MetricGroup": "Cache_Misses;",
+        "MetricName": "L3MPKI"
+    },
+    {
         "MetricExpr": "CPU_CLK_UNHALTED.REF_TSC / msr@tsc@",
+        "BriefDescription": "Average CPU Utilization",
         "MetricGroup": "Summary",
         "MetricName": "CPU_Utilization"
     },
     {
+        "MetricExpr": "( (( 1 * ( FP_ARITH_INST_RETIRED.SCALAR_SINGLE + FP_ARITH_INST_RETIRED.SCALAR_DOUBLE ) + 2 * FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE + 4 * ( FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE + FP_ARITH_INST_RETIRED.256B_PACKED_DOUBLE ) + 8 * FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE )) / 1000000000 ) / duration_time",
         "BriefDescription": "Giga Floating Point Operations Per Second",
-        "MetricExpr": "(( 1*( FP_ARITH_INST_RETIRED.SCALAR_SINGLE + FP_ARITH_INST_RETIRED.SCALAR_DOUBLE ) + 2* FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE + 4*( FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE + FP_ARITH_INST_RETIRED.256B_PACKED_DOUBLE ) + 8* FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE )) / 1000000000 / duration_time",
         "MetricGroup": "FLOPS;Summary",
         "MetricName": "GFLOPs"
     },
     {
-        "BriefDescription": "Average Frequency Utilization relative nominal frequency",
         "MetricExpr": "CPU_CLK_UNHALTED.THREAD / CPU_CLK_UNHALTED.REF_TSC",
+        "BriefDescription": "Average Frequency Utilization relative nominal frequency",
         "MetricGroup": "Power",
         "MetricName": "Turbo_Utilization"
     },
     {
-        "BriefDescription": "Fraction of cycles where both hardware threads were active",
         "MetricExpr": "1 - CPU_CLK_THREAD_UNHALTED.ONE_THREAD_ACTIVE / ( CPU_CLK_THREAD_UNHALTED.REF_XCLK_ANY / 2 ) if #SMT_on else 0",
+        "BriefDescription": "Fraction of cycles where both hardware threads were active",
         "MetricGroup": "SMT;Summary",
         "MetricName": "SMT_2T_Utilization"
     },
     {
-        "BriefDescription": "Fraction of cycles spent in Kernel mode",
         "MetricExpr": "CPU_CLK_UNHALTED.REF_TSC:u / CPU_CLK_UNHALTED.REF_TSC",
+        "BriefDescription": "Fraction of cycles spent in Kernel mode",
         "MetricGroup": "Summary",
         "MetricName": "Kernel_Utilization"
     },
     {
-        "BriefDescription": "C3 residency percent per core",
+        "MetricExpr": "64 * ( arb@event\\=0x81\\,umask\\=0x1@ + arb@event\\=0x84\\,umask\\=0x1@ ) / 1000000 / duration_time / 1000",
+        "BriefDescription": "Average external Memory Bandwidth Use for reads and writes [GB / sec]",
+        "MetricGroup": "Memory_BW",
+        "MetricName": "DRAM_BW_Use"
+    },
+    {
+        "MetricExpr": "arb@event\\=0x80\\,umask\\=0x2@ / arb@event\\=0x80\\,umask\\=0x2\\,thresh\\=1@",
+        "BriefDescription": "Average number of parallel data read requests to external memory. Accounts for demand loads and L1/L2 prefetches",
+        "MetricGroup": "Memory_BW",
+        "MetricName": "DRAM_Parallel_Reads"
+    },
+    {
         "MetricExpr": "(cstate_core@c3\\-residency@ / msr@tsc@) * 100",
         "MetricGroup": "Power",
+        "BriefDescription": "C3 residency percent per core",
         "MetricName": "C3_Core_Residency"
     },
     {
-        "BriefDescription": "C6 residency percent per core",
         "MetricExpr": "(cstate_core@c6\\-residency@ / msr@tsc@) * 100",
         "MetricGroup": "Power",
+        "BriefDescription": "C6 residency percent per core",
         "MetricName": "C6_Core_Residency"
     },
     {
-        "BriefDescription": "C7 residency percent per core",
         "MetricExpr": "(cstate_core@c7\\-residency@ / msr@tsc@) * 100",
         "MetricGroup": "Power",
+        "BriefDescription": "C7 residency percent per core",
         "MetricName": "C7_Core_Residency"
     },
     {
-        "BriefDescription": "C2 residency percent per package",
         "MetricExpr": "(cstate_pkg@c2\\-residency@ / msr@tsc@) * 100",
         "MetricGroup": "Power",
+        "BriefDescription": "C2 residency percent per package",
         "MetricName": "C2_Pkg_Residency"
     },
     {
-        "BriefDescription": "C3 residency percent per package",
         "MetricExpr": "(cstate_pkg@c3\\-residency@ / msr@tsc@) * 100",
         "MetricGroup": "Power",
+        "BriefDescription": "C3 residency percent per package",
         "MetricName": "C3_Pkg_Residency"
     },
     {
-        "BriefDescription": "C6 residency percent per package",
         "MetricExpr": "(cstate_pkg@c6\\-residency@ / msr@tsc@) * 100",
         "MetricGroup": "Power",
+        "BriefDescription": "C6 residency percent per package",
         "MetricName": "C6_Pkg_Residency"
     },
     {
-        "BriefDescription": "C7 residency percent per package",
         "MetricExpr": "(cstate_pkg@c7\\-residency@ / msr@tsc@) * 100",
         "MetricGroup": "Power",
+        "BriefDescription": "C7 residency percent per package",
         "MetricName": "C7_Pkg_Residency"
     }
 ]
diff --git a/tools/perf/pmu-events/arch/x86/skylakex/cache.json b/tools/perf/pmu-events/arch/x86/skylakex/cache.json
index 5c9940866acd..24df183693fa 100644
--- a/tools/perf/pmu-events/arch/x86/skylakex/cache.json
+++ b/tools/perf/pmu-events/arch/x86/skylakex/cache.json
@@ -61,17 +61,17 @@
     },
     {
         "EventCode": "0x24",
-        "UMask": "0x41",
+        "UMask": "0xc1",
         "BriefDescription": "Demand Data Read requests that hit L2 cache",
         "Counter": "0,1,2,3",
         "EventName": "L2_RQSTS.DEMAND_DATA_RD_HIT",
-        "PublicDescription": "Counts the number of demand Data Read requests that hit L2 cache. Only non rejected loads are counted.",
+        "PublicDescription": "Counts the number of demand Data Read requests, initiated by load instructions, that hit L2 cache",
         "SampleAfterValue": "200003",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
         "EventCode": "0x24",
-        "UMask": "0x42",
+        "UMask": "0xc2",
         "BriefDescription": "RFO requests that hit L2 cache",
         "Counter": "0,1,2,3",
         "EventName": "L2_RQSTS.RFO_HIT",
@@ -81,7 +81,7 @@
     },
     {
         "EventCode": "0x24",
-        "UMask": "0x44",
+        "UMask": "0xc4",
         "BriefDescription": "L2 cache hits when fetching instructions, code reads.",
         "Counter": "0,1,2,3",
         "EventName": "L2_RQSTS.CODE_RD_HIT",
@@ -165,6 +165,7 @@
         "BriefDescription": "Core-originated cacheable demand requests missed L3",
         "Counter": "0,1,2,3",
         "EventName": "LONGEST_LAT_CACHE.MISS",
+        "Errata": "SKL057",
         "PublicDescription": "Counts core-originated cacheable requests that miss the L3 cache (Longest Latency cache). Requests include data and code reads, Reads-for-Ownership (RFOs), speculative accesses and hardware prefetches from L1 and L2. It does not include all misses to the L3.",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
@@ -175,28 +176,29 @@
         "BriefDescription": "Core-originated cacheable demand requests that refer to L3",
         "Counter": "0,1,2,3",
         "EventName": "LONGEST_LAT_CACHE.REFERENCE",
-        "PublicDescription": "Counts core-originated cacheable requests to the L3 cache (Longest Latency cache). Requests include data and code reads, Reads-for-Ownership (RFOs), speculative accesses and hardware prefetches from L1 and L2.  It does not include all accesses to the L3.",
+        "Errata": "SKL057",
+        "PublicDescription": "Counts core-originated cacheable requests to the  L3 cache (Longest Latency cache). Requests include data and code reads, Reads-for-Ownership (RFOs), speculative accesses and hardware prefetches from L1 and L2.  It does not include all accesses to the L3.",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
         "EventCode": "0x48",
         "UMask": "0x1",
-        "BriefDescription": "L1D miss outstandings duration in cycles",
+        "BriefDescription": "Cycles with L1D load Misses outstanding.",
         "Counter": "0,1,2,3",
-        "EventName": "L1D_PEND_MISS.PENDING",
-        "PublicDescription": "Counts duration of L1D miss outstanding, that is each cycle number of Fill Buffers (FB) outstanding required by Demand Reads. FB either is held by demand loads, or it is held by non-demand loads and gets hit at least once by demand. The valid outstanding interval is defined until the FB deallocation by one of the following ways: from FB allocation, if FB is allocated by demand from the demand Hit FB, if it is allocated by hardware or software prefetch.Note: In the L1D, a Demand Read contains cacheable or noncacheable demand loads, including ones causing cache-line splits and reads due to page walks resulted from any request type.",
+        "EventName": "L1D_PEND_MISS.PENDING_CYCLES",
+        "CounterMask": "1",
+        "PublicDescription": "Counts duration of L1D miss outstanding in cycles.",
         "SampleAfterValue": "2000003",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
         "EventCode": "0x48",
         "UMask": "0x1",
-        "BriefDescription": "Cycles with L1D load Misses outstanding.",
+        "BriefDescription": "L1D miss outstandings duration in cycles",
         "Counter": "0,1,2,3",
-        "EventName": "L1D_PEND_MISS.PENDING_CYCLES",
-        "CounterMask": "1",
-        "PublicDescription": "Counts duration of L1D miss outstanding in cycles.",
+        "EventName": "L1D_PEND_MISS.PENDING",
+        "PublicDescription": "Counts duration of L1D miss outstanding, that is each cycle number of Fill Buffers (FB) outstanding required by Demand Reads. FB either is held by demand loads, or it is held by non-demand loads and gets hit at least once by demand. The valid outstanding interval is defined until the FB deallocation by one of the following ways: from FB allocation, if FB is allocated by demand from the demand Hit FB, if it is allocated by hardware or software prefetch.Note: In the L1D, a Demand Read contains cacheable or noncacheable demand loads, including ones causing cache-line splits and reads due to page walks resulted from any request type.",
         "SampleAfterValue": "2000003",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
@@ -234,21 +236,21 @@
     {
         "EventCode": "0x60",
         "UMask": "0x1",
-        "BriefDescription": "Offcore outstanding Demand Data Read transactions in uncore queue.",
+        "BriefDescription": "Cycles when offcore outstanding Demand Data Read transactions are present in SuperQueue (SQ), queue to uncore",
         "Counter": "0,1,2,3",
-        "EventName": "OFFCORE_REQUESTS_OUTSTANDING.DEMAND_DATA_RD",
-        "PublicDescription": "Counts the number of offcore outstanding Demand Data Read transactions in the super queue (SQ) every cycle. A transaction is considered to be in the Offcore outstanding state between L2 miss and transaction completion sent to requestor. See the corresponding Umask under OFFCORE_REQUESTS.Note: A prefetch promoted to Demand is counted from the promotion point.",
+        "EventName": "OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DEMAND_DATA_RD",
+        "CounterMask": "1",
+        "PublicDescription": "Counts cycles when offcore outstanding Demand Data Read transactions are present in the super queue (SQ). A transaction is considered to be in the Offcore outstanding state between L2 miss and transaction completion sent to requestor (SQ de-allocation).",
         "SampleAfterValue": "2000003",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
         "EventCode": "0x60",
         "UMask": "0x1",
-        "BriefDescription": "Cycles when offcore outstanding Demand Data Read transactions are present in SuperQueue (SQ), queue to uncore",
+        "BriefDescription": "Offcore outstanding Demand Data Read transactions in uncore queue.",
         "Counter": "0,1,2,3",
-        "EventName": "OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DEMAND_DATA_RD",
-        "CounterMask": "1",
-        "PublicDescription": "Counts cycles when offcore outstanding Demand Data Read transactions are present in the super queue (SQ). A transaction is considered to be in the Offcore outstanding state between L2 miss and transaction completion sent to requestor (SQ de-allocation).",
+        "EventName": "OFFCORE_REQUESTS_OUTSTANDING.DEMAND_DATA_RD",
+        "PublicDescription": "Counts the number of offcore outstanding Demand Data Read transactions in the super queue (SQ) every cycle. A transaction is considered to be in the Offcore outstanding state between L2 miss and transaction completion sent to requestor. See the corresponding Umask under OFFCORE_REQUESTS.Note: A prefetch promoted to Demand is counted from the promotion point.",
         "SampleAfterValue": "2000003",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
@@ -307,21 +309,21 @@
     {
         "EventCode": "0x60",
         "UMask": "0x8",
-        "BriefDescription": "Offcore outstanding cacheable Core Data Read transactions in SuperQueue (SQ), queue to uncore",
+        "BriefDescription": "Cycles when offcore outstanding cacheable Core Data Read transactions are present in SuperQueue (SQ), queue to uncore.",
         "Counter": "0,1,2,3",
-        "EventName": "OFFCORE_REQUESTS_OUTSTANDING.ALL_DATA_RD",
-        "PublicDescription": "Counts the number of offcore outstanding cacheable Core Data Read transactions in the super queue every cycle. A transaction is considered to be in the Offcore outstanding state between L2 miss and transaction completion sent to requestor (SQ de-allocation). See corresponding Umask under OFFCORE_REQUESTS.",
+        "EventName": "OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DATA_RD",
+        "CounterMask": "1",
+        "PublicDescription": "Counts cycles when offcore outstanding cacheable Core Data Read transactions are present in the super queue. A transaction is considered to be in the Offcore outstanding state between L2 miss and transaction completion sent to requestor (SQ de-allocation). See corresponding Umask under OFFCORE_REQUESTS.",
         "SampleAfterValue": "2000003",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
         "EventCode": "0x60",
         "UMask": "0x8",
-        "BriefDescription": "Cycles when offcore outstanding cacheable Core Data Read transactions are present in SuperQueue (SQ), queue to uncore.",
+        "BriefDescription": "Offcore outstanding cacheable Core Data Read transactions in SuperQueue (SQ), queue to uncore",
         "Counter": "0,1,2,3",
-        "EventName": "OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DATA_RD",
-        "CounterMask": "1",
-        "PublicDescription": "Counts cycles when offcore outstanding cacheable Core Data Read transactions are present in the super queue. A transaction is considered to be in the Offcore outstanding state between L2 miss and transaction completion sent to requestor (SQ de-allocation). See corresponding Umask under OFFCORE_REQUESTS.",
+        "EventName": "OFFCORE_REQUESTS_OUTSTANDING.ALL_DATA_RD",
+        "PublicDescription": "Counts the number of offcore outstanding cacheable Core Data Read transactions in the super queue every cycle. A transaction is considered to be in the Offcore outstanding state between L2 miss and transaction completion sent to requestor (SQ de-allocation). See corresponding Umask under OFFCORE_REQUESTS.",
         "SampleAfterValue": "2000003",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
@@ -486,7 +488,7 @@
         "PEBS": "1",
         "Counter": "0,1,2,3",
         "EventName": "MEM_LOAD_RETIRED.L1_HIT",
-        "PublicDescription": "Counts retired load instructions with at least one uop that hit in the L1 data cache. This event includes all SW prefetches and lock instructions regardless of the data source.\r\n",
+        "PublicDescription": "Counts retired load instructions with at least one uop that hit in the L1 data cache. This event includes all SW prefetches and lock instructions regardless of the data source.",
         "SampleAfterValue": "2000003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -558,7 +560,7 @@
         "PEBS": "1",
         "Counter": "0,1,2,3",
         "EventName": "MEM_LOAD_RETIRED.FB_HIT",
-        "PublicDescription": "Counts retired load instructions with at least one uop was load missed in L1 but hit FB (Fill Buffers) due to preceding miss to the same cache line with data not ready. \r\n",
+        "PublicDescription": "Counts retired load instructions with at least one uop was load missed in L1 but hit FB (Fill Buffers) due to preceding miss to the same cache line with data not ready.",
         "SampleAfterValue": "100007",
         "CounterHTOff": "0,1,2,3"
     },
@@ -690,6 +692,7 @@
         "BriefDescription": "Counts the number of lines that are silently dropped by L2 cache when triggered by an L2 cache fill. These lines are typically in Shared state. A non-threaded event.",
         "Counter": "0,1,2,3",
         "EventName": "L2_LINES_OUT.SILENT",
+        "PublicDescription": "Counts the number of lines that are silently dropped by L2 cache when triggered by an L2 cache fill. These lines are typically in Shared or Exclusive state. A non-threaded event.",
         "SampleAfterValue": "200003",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
@@ -699,17 +702,18 @@
         "BriefDescription": "Counts the number of lines that are evicted by L2 cache when triggered by an L2 cache fill. Those lines can be either in modified state or clean state. Modified lines may either be written back to L3 or directly written to memory and not allocated in L3.  Clean lines may either be allocated in L3 or dropped",
         "Counter": "0,1,2,3",
         "EventName": "L2_LINES_OUT.NON_SILENT",
-        "PublicDescription": "Counts the number of lines that are evicted by L2 cache when triggered by an L2 cache fill. Those lines can be either in modified state or clean state. Modified lines may either be written back to L3 or directly written to memory and not allocated in L3.  Clean lines may either be allocated in L3 or dropped.",
+        "PublicDescription": "Counts the number of lines that are evicted by L2 cache when triggered by an L2 cache fill. Those lines are in Modified state. Modified lines are written back to L3",
         "SampleAfterValue": "200003",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
         "EventCode": "0xF2",
         "UMask": "0x4",
-        "BriefDescription": "Counts the number of lines that have been hardware prefetched but not used and now evicted by L2 cache",
+        "BriefDescription": "This event is deprecated. Refer to new event L2_LINES_OUT.USELESS_HWPF",
+        "Deprecated": "1",
         "Counter": "0,1,2,3",
         "EventName": "L2_LINES_OUT.USELESS_PREF",
-        "PublicDescription": "Counts the number of lines that have been hardware prefetched but not used and now evicted by L2 cache.",
+        "PublicDescription": "This event is deprecated. Refer to new event L2_LINES_OUT.USELESS_HWPF",
         "SampleAfterValue": "200003",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
@@ -736,12 +740,12 @@
         "Offcore": "1",
         "EventCode": "0xB7, 0xBB",
         "UMask": "0x1",
-        "BriefDescription": "Counts demand data reads that have any response type.",
-        "MSRValue": "0x0000010001 ",
+        "BriefDescription": "Counts demand data reads have any response type.",
+        "MSRValue": "0x0000010001",
         "Counter": "0,1,2,3",
         "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.ANY_RESPONSE",
-        "MSRIndex": "0x1a6,0x1a7",
-        "PublicDescription": "Counts demand data reads that have any response type. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "PublicDescription": "Counts demand data reads have any response type.",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -749,12 +753,12 @@
         "Offcore": "1",
         "EventCode": "0xB7, 0xBB",
         "UMask": "0x1",
-        "BriefDescription": "Counts demand data reads that hit in the L3 and sibling core snoops are not needed as either the core-valid bit is not set or the shared line is present in multiple cores.",
-        "MSRValue": "0x01003c0001 ",
+        "BriefDescription": "Counts demand data reads TBD TBD",
+        "MSRValue": "0x01003C0001",
         "Counter": "0,1,2,3",
         "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_HIT.NO_SNOOP_NEEDED",
-        "MSRIndex": "0x1a6,0x1a7",
-        "PublicDescription": "Counts demand data reads that hit in the L3 and sibling core snoops are not needed as either the core-valid bit is not set or the shared line is present in multiple cores. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "PublicDescription": "Counts demand data reads TBD TBD",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -762,25 +766,12 @@
         "Offcore": "1",
         "EventCode": "0xB7, 0xBB",
         "UMask": "0x1",
-        "BriefDescription": "Counts demand data reads that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded.",
-        "MSRValue": "0x04003c0001 ",
+        "BriefDescription": "Counts demand data reads TBD TBD",
+        "MSRValue": "0x04003C0001",
         "Counter": "0,1,2,3",
         "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_HIT.HIT_OTHER_CORE_NO_FWD",
-        "MSRIndex": "0x1a6,0x1a7",
-        "PublicDescription": "Counts demand data reads that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
-        "SampleAfterValue": "100003",
-        "CounterHTOff": "0,1,2,3"
-    },
-    {
-        "Offcore": "1",
-        "EventCode": "0xB7, 0xBB",
-        "UMask": "0x1",
-        "BriefDescription": "DEMAND_DATA_RD & L3_HIT & SNOOP_HIT_WITH_FWD",
-        "MSRValue": "0x08003c0001 ",
-        "Counter": "0,1,2,3",
-        "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_HIT.SNOOP_HIT_WITH_FWD",
-        "MSRIndex": "0x1a6,0x1a7",
-        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "PublicDescription": "Counts demand data reads TBD TBD",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -788,12 +779,12 @@
         "Offcore": "1",
         "EventCode": "0xB7, 0xBB",
         "UMask": "0x1",
-        "BriefDescription": "Counts demand data reads that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded.",
-        "MSRValue": "0x10003c0001 ",
+        "BriefDescription": "Counts demand data reads TBD TBD",
+        "MSRValue": "0x10003C0001",
         "Counter": "0,1,2,3",
         "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_HIT.HITM_OTHER_CORE",
-        "MSRIndex": "0x1a6,0x1a7",
-        "PublicDescription": "Counts demand data reads that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "PublicDescription": "Counts demand data reads TBD TBD",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -801,12 +792,12 @@
         "Offcore": "1",
         "EventCode": "0xB7, 0xBB",
         "UMask": "0x1",
-        "BriefDescription": "Counts demand data reads that hit in the L3.",
-        "MSRValue": "0x3f803c0001 ",
+        "BriefDescription": "Counts demand data reads TBD TBD",
+        "MSRValue": "0x3F803C0001",
         "Counter": "0,1,2,3",
         "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_HIT.ANY_SNOOP",
-        "MSRIndex": "0x1a6,0x1a7",
-        "PublicDescription": "Counts demand data reads that hit in the L3. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "PublicDescription": "Counts demand data reads TBD TBD",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -814,12 +805,12 @@
         "Offcore": "1",
         "EventCode": "0xB7, 0xBB",
         "UMask": "0x1",
-        "BriefDescription": "Counts all demand data writes (RFOs) that have any response type.",
-        "MSRValue": "0x0000010002 ",
+        "BriefDescription": "Counts all demand data writes (RFOs) have any response type.",
+        "MSRValue": "0x0000010002",
         "Counter": "0,1,2,3",
         "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.ANY_RESPONSE",
-        "MSRIndex": "0x1a6,0x1a7",
-        "PublicDescription": "Counts all demand data writes (RFOs) that have any response type. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "PublicDescription": "Counts all demand data writes (RFOs) have any response type.",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -827,12 +818,12 @@
         "Offcore": "1",
         "EventCode": "0xB7, 0xBB",
         "UMask": "0x1",
-        "BriefDescription": "Counts all demand data writes (RFOs) that hit in the L3 and sibling core snoops are not needed as either the core-valid bit is not set or the shared line is present in multiple cores.",
-        "MSRValue": "0x01003c0002 ",
+        "BriefDescription": "Counts all demand data writes (RFOs) TBD TBD",
+        "MSRValue": "0x01003C0002",
         "Counter": "0,1,2,3",
         "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_HIT.NO_SNOOP_NEEDED",
-        "MSRIndex": "0x1a6,0x1a7",
-        "PublicDescription": "Counts all demand data writes (RFOs) that hit in the L3 and sibling core snoops are not needed as either the core-valid bit is not set or the shared line is present in multiple cores. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "PublicDescription": "Counts all demand data writes (RFOs) TBD TBD",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -840,12 +831,12 @@
         "Offcore": "1",
         "EventCode": "0xB7, 0xBB",
         "UMask": "0x1",
-        "BriefDescription": "Counts all demand data writes (RFOs) that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded.",
-        "MSRValue": "0x04003c0002 ",
+        "BriefDescription": "Counts all demand data writes (RFOs) TBD TBD",
+        "MSRValue": "0x04003C0002",
         "Counter": "0,1,2,3",
         "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_HIT.HIT_OTHER_CORE_NO_FWD",
-        "MSRIndex": "0x1a6,0x1a7",
-        "PublicDescription": "Counts all demand data writes (RFOs) that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "PublicDescription": "Counts all demand data writes (RFOs) TBD TBD",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -853,25 +844,12 @@
         "Offcore": "1",
         "EventCode": "0xB7, 0xBB",
         "UMask": "0x1",
-        "BriefDescription": "DEMAND_RFO & L3_HIT & SNOOP_HIT_WITH_FWD",
-        "MSRValue": "0x08003c0002 ",
-        "Counter": "0,1,2,3",
-        "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_HIT.SNOOP_HIT_WITH_FWD",
-        "MSRIndex": "0x1a6,0x1a7",
-        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
-        "SampleAfterValue": "100003",
-        "CounterHTOff": "0,1,2,3"
-    },
-    {
-        "Offcore": "1",
-        "EventCode": "0xB7, 0xBB",
-        "UMask": "0x1",
-        "BriefDescription": "Counts all demand data writes (RFOs) that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded.",
-        "MSRValue": "0x10003c0002 ",
+        "BriefDescription": "Counts all demand data writes (RFOs) TBD TBD",
+        "MSRValue": "0x10003C0002",
         "Counter": "0,1,2,3",
         "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_HIT.HITM_OTHER_CORE",
-        "MSRIndex": "0x1a6,0x1a7",
-        "PublicDescription": "Counts all demand data writes (RFOs) that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "PublicDescription": "Counts all demand data writes (RFOs) TBD TBD",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -879,12 +857,12 @@
         "Offcore": "1",
         "EventCode": "0xB7, 0xBB",
         "UMask": "0x1",
-        "BriefDescription": "Counts all demand data writes (RFOs) that hit in the L3.",
-        "MSRValue": "0x3f803c0002 ",
+        "BriefDescription": "Counts all demand data writes (RFOs) TBD TBD",
+        "MSRValue": "0x3F803C0002",
         "Counter": "0,1,2,3",
         "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_HIT.ANY_SNOOP",
-        "MSRIndex": "0x1a6,0x1a7",
-        "PublicDescription": "Counts all demand data writes (RFOs) that hit in the L3. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "PublicDescription": "Counts all demand data writes (RFOs) TBD TBD",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -892,12 +870,12 @@
         "Offcore": "1",
         "EventCode": "0xB7, 0xBB",
         "UMask": "0x1",
-        "BriefDescription": "Counts all demand code reads that have any response type.",
-        "MSRValue": "0x0000010004 ",
+        "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that have any response type.",
+        "MSRValue": "0x0000010004",
         "Counter": "0,1,2,3",
         "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.ANY_RESPONSE",
-        "MSRIndex": "0x1a6,0x1a7",
-        "PublicDescription": "Counts all demand code reads that have any response type. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that have any response type.",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -905,12 +883,12 @@
         "Offcore": "1",
         "EventCode": "0xB7, 0xBB",
         "UMask": "0x1",
-        "BriefDescription": "Counts all demand code reads that hit in the L3 and sibling core snoops are not needed as either the core-valid bit is not set or the shared line is present in multiple cores.",
-        "MSRValue": "0x01003c0004 ",
+        "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that TBD TBD",
+        "MSRValue": "0x01003C0004",
         "Counter": "0,1,2,3",
         "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_HIT.NO_SNOOP_NEEDED",
-        "MSRIndex": "0x1a6,0x1a7",
-        "PublicDescription": "Counts all demand code reads that hit in the L3 and sibling core snoops are not needed as either the core-valid bit is not set or the shared line is present in multiple cores. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that TBD TBD",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -918,12 +896,12 @@
         "Offcore": "1",
         "EventCode": "0xB7, 0xBB",
         "UMask": "0x1",
-        "BriefDescription": "Counts all demand code reads that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded.",
-        "MSRValue": "0x04003c0004 ",
+        "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that TBD TBD",
+        "MSRValue": "0x04003C0004",
         "Counter": "0,1,2,3",
         "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_HIT.HIT_OTHER_CORE_NO_FWD",
-        "MSRIndex": "0x1a6,0x1a7",
-        "PublicDescription": "Counts all demand code reads that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that TBD TBD",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -931,25 +909,12 @@
         "Offcore": "1",
         "EventCode": "0xB7, 0xBB",
         "UMask": "0x1",
-        "BriefDescription": "DEMAND_CODE_RD & L3_HIT & SNOOP_HIT_WITH_FWD",
-        "MSRValue": "0x08003c0004 ",
-        "Counter": "0,1,2,3",
-        "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_HIT.SNOOP_HIT_WITH_FWD",
-        "MSRIndex": "0x1a6,0x1a7",
-        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
-        "SampleAfterValue": "100003",
-        "CounterHTOff": "0,1,2,3"
-    },
-    {
-        "Offcore": "1",
-        "EventCode": "0xB7, 0xBB",
-        "UMask": "0x1",
-        "BriefDescription": "Counts all demand code reads that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded.",
-        "MSRValue": "0x10003c0004 ",
+        "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that TBD TBD",
+        "MSRValue": "0x10003C0004",
         "Counter": "0,1,2,3",
         "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_HIT.HITM_OTHER_CORE",
-        "MSRIndex": "0x1a6,0x1a7",
-        "PublicDescription": "Counts all demand code reads that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that TBD TBD",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -957,12 +922,12 @@
         "Offcore": "1",
         "EventCode": "0xB7, 0xBB",
         "UMask": "0x1",
-        "BriefDescription": "Counts all demand code reads that hit in the L3.",
-        "MSRValue": "0x3f803c0004 ",
+        "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that TBD TBD",
+        "MSRValue": "0x3F803C0004",
         "Counter": "0,1,2,3",
         "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_HIT.ANY_SNOOP",
-        "MSRIndex": "0x1a6,0x1a7",
-        "PublicDescription": "Counts all demand code reads that hit in the L3. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that TBD TBD",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -970,12 +935,12 @@
         "Offcore": "1",
         "EventCode": "0xB7, 0xBB",
         "UMask": "0x1",
-        "BriefDescription": "Counts prefetch (that bring data to L2) data reads that have any response type.",
-        "MSRValue": "0x0000010010 ",
+        "BriefDescription": "Counts prefetch (that bring data to L2) data reads have any response type.",
+        "MSRValue": "0x0000010010",
         "Counter": "0,1,2,3",
         "EventName": "OFFCORE_RESPONSE.PF_L2_DATA_RD.ANY_RESPONSE",
-        "MSRIndex": "0x1a6,0x1a7",
-        "PublicDescription": "Counts prefetch (that bring data to L2) data reads that have any response type. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "PublicDescription": "Counts prefetch (that bring data to L2) data reads have any response type.",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -983,12 +948,12 @@
         "Offcore": "1",
         "EventCode": "0xB7, 0xBB",
         "UMask": "0x1",
-        "BriefDescription": "Counts prefetch (that bring data to L2) data reads that hit in the L3 and sibling core snoops are not needed as either the core-valid bit is not set or the shared line is present in multiple cores.",
-        "MSRValue": "0x01003c0010 ",
+        "BriefDescription": "Counts prefetch (that bring data to L2) data reads TBD TBD",
+        "MSRValue": "0x01003C0010",
         "Counter": "0,1,2,3",
         "EventName": "OFFCORE_RESPONSE.PF_L2_DATA_RD.L3_HIT.NO_SNOOP_NEEDED",
-        "MSRIndex": "0x1a6,0x1a7",
-        "PublicDescription": "Counts prefetch (that bring data to L2) data reads that hit in the L3 and sibling core snoops are not needed as either the core-valid bit is not set or the shared line is present in multiple cores. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "PublicDescription": "Counts prefetch (that bring data to L2) data reads TBD TBD",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -996,12 +961,12 @@
         "Offcore": "1",
         "EventCode": "0xB7, 0xBB",
         "UMask": "0x1",
-        "BriefDescription": "Counts prefetch (that bring data to L2) data reads that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded.",
-        "MSRValue": "0x04003c0010 ",
+        "BriefDescription": "Counts prefetch (that bring data to L2) data reads TBD TBD",
+        "MSRValue": "0x04003C0010",
         "Counter": "0,1,2,3",
         "EventName": "OFFCORE_RESPONSE.PF_L2_DATA_RD.L3_HIT.HIT_OTHER_CORE_NO_FWD",
-        "MSRIndex": "0x1a6,0x1a7",
-        "PublicDescription": "Counts prefetch (that bring data to L2) data reads that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "PublicDescription": "Counts prefetch (that bring data to L2) data reads TBD TBD",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -1009,25 +974,12 @@
         "Offcore": "1",
         "EventCode": "0xB7, 0xBB",
         "UMask": "0x1",
-        "BriefDescription": "PF_L2_DATA_RD & L3_HIT & SNOOP_HIT_WITH_FWD",
-        "MSRValue": "0x08003c0010 ",
-        "Counter": "0,1,2,3",
-        "EventName": "OFFCORE_RESPONSE.PF_L2_DATA_RD.L3_HIT.SNOOP_HIT_WITH_FWD",
-        "MSRIndex": "0x1a6,0x1a7",
-        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
-        "SampleAfterValue": "100003",
-        "CounterHTOff": "0,1,2,3"
-    },
-    {
-        "Offcore": "1",
-        "EventCode": "0xB7, 0xBB",
-        "UMask": "0x1",
-        "BriefDescription": "Counts prefetch (that bring data to L2) data reads that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded.",
-        "MSRValue": "0x10003c0010 ",
+        "BriefDescription": "Counts prefetch (that bring data to L2) data reads TBD TBD",
+        "MSRValue": "0x10003C0010",
         "Counter": "0,1,2,3",
         "EventName": "OFFCORE_RESPONSE.PF_L2_DATA_RD.L3_HIT.HITM_OTHER_CORE",
-        "MSRIndex": "0x1a6,0x1a7",
-        "PublicDescription": "Counts prefetch (that bring data to L2) data reads that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "PublicDescription": "Counts prefetch (that bring data to L2) data reads TBD TBD",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -1035,12 +987,12 @@
         "Offcore": "1",
         "EventCode": "0xB7, 0xBB",
         "UMask": "0x1",
-        "BriefDescription": "Counts prefetch (that bring data to L2) data reads that hit in the L3.",
-        "MSRValue": "0x3f803c0010 ",
+        "BriefDescription": "Counts prefetch (that bring data to L2) data reads TBD TBD",
+        "MSRValue": "0x3F803C0010",
         "Counter": "0,1,2,3",
         "EventName": "OFFCORE_RESPONSE.PF_L2_DATA_RD.L3_HIT.ANY_SNOOP",
-        "MSRIndex": "0x1a6,0x1a7",
-        "PublicDescription": "Counts prefetch (that bring data to L2) data reads that hit in the L3. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "PublicDescription": "Counts prefetch (that bring data to L2) data reads TBD TBD",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -1048,12 +1000,12 @@
         "Offcore": "1",
         "EventCode": "0xB7, 0xBB",
         "UMask": "0x1",
-        "BriefDescription": "Counts all prefetch (that bring data to L2) RFOs that have any response type.",
-        "MSRValue": "0x0000010020 ",
+        "BriefDescription": "Counts all prefetch (that bring data to L2) RFOs have any response type.",
+        "MSRValue": "0x0000010020",
         "Counter": "0,1,2,3",
         "EventName": "OFFCORE_RESPONSE.PF_L2_RFO.ANY_RESPONSE",
-        "MSRIndex": "0x1a6,0x1a7",
-        "PublicDescription": "Counts all prefetch (that bring data to L2) RFOs that have any response type. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "PublicDescription": "Counts all prefetch (that bring data to L2) RFOs have any response type.",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -1061,12 +1013,12 @@
         "Offcore": "1",
         "EventCode": "0xB7, 0xBB",
         "UMask": "0x1",
-        "BriefDescription": "Counts all prefetch (that bring data to L2) RFOs that hit in the L3 and sibling core snoops are not needed as either the core-valid bit is not set or the shared line is present in multiple cores.",
-        "MSRValue": "0x01003c0020 ",
+        "BriefDescription": "Counts all prefetch (that bring data to L2) RFOs TBD TBD",
+        "MSRValue": "0x01003C0020",
         "Counter": "0,1,2,3",
         "EventName": "OFFCORE_RESPONSE.PF_L2_RFO.L3_HIT.NO_SNOOP_NEEDED",
-        "MSRIndex": "0x1a6,0x1a7",
-        "PublicDescription": "Counts all prefetch (that bring data to L2) RFOs that hit in the L3 and sibling core snoops are not needed as either the core-valid bit is not set or the shared line is present in multiple cores. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "PublicDescription": "Counts all prefetch (that bring data to L2) RFOs TBD TBD",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -1074,12 +1026,12 @@
         "Offcore": "1",
         "EventCode": "0xB7, 0xBB",
         "UMask": "0x1",
-        "BriefDescription": "Counts all prefetch (that bring data to L2) RFOs that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded.",
-        "MSRValue": "0x04003c0020 ",
+        "BriefDescription": "Counts all prefetch (that bring data to L2) RFOs TBD TBD",
+        "MSRValue": "0x04003C0020",
         "Counter": "0,1,2,3",
         "EventName": "OFFCORE_RESPONSE.PF_L2_RFO.L3_HIT.HIT_OTHER_CORE_NO_FWD",
-        "MSRIndex": "0x1a6,0x1a7",
-        "PublicDescription": "Counts all prefetch (that bring data to L2) RFOs that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "PublicDescription": "Counts all prefetch (that bring data to L2) RFOs TBD TBD",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -1087,25 +1039,12 @@
         "Offcore": "1",
         "EventCode": "0xB7, 0xBB",
         "UMask": "0x1",
-        "BriefDescription": "PF_L2_RFO & L3_HIT & SNOOP_HIT_WITH_FWD",
-        "MSRValue": "0x08003c0020 ",
-        "Counter": "0,1,2,3",
-        "EventName": "OFFCORE_RESPONSE.PF_L2_RFO.L3_HIT.SNOOP_HIT_WITH_FWD",
-        "MSRIndex": "0x1a6,0x1a7",
-        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
-        "SampleAfterValue": "100003",
-        "CounterHTOff": "0,1,2,3"
-    },
-    {
-        "Offcore": "1",
-        "EventCode": "0xB7, 0xBB",
-        "UMask": "0x1",
-        "BriefDescription": "Counts all prefetch (that bring data to L2) RFOs that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded.",
-        "MSRValue": "0x10003c0020 ",
+        "BriefDescription": "Counts all prefetch (that bring data to L2) RFOs TBD TBD",
+        "MSRValue": "0x10003C0020",
         "Counter": "0,1,2,3",
         "EventName": "OFFCORE_RESPONSE.PF_L2_RFO.L3_HIT.HITM_OTHER_CORE",
-        "MSRIndex": "0x1a6,0x1a7",
-        "PublicDescription": "Counts all prefetch (that bring data to L2) RFOs that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "PublicDescription": "Counts all prefetch (that bring data to L2) RFOs TBD TBD",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -1113,12 +1052,12 @@
         "Offcore": "1",
         "EventCode": "0xB7, 0xBB",
         "UMask": "0x1",
-        "BriefDescription": "Counts all prefetch (that bring data to L2) RFOs that hit in the L3.",
-        "MSRValue": "0x3f803c0020 ",
+        "BriefDescription": "Counts all prefetch (that bring data to L2) RFOs TBD TBD",
+        "MSRValue": "0x3F803C0020",
         "Counter": "0,1,2,3",
         "EventName": "OFFCORE_RESPONSE.PF_L2_RFO.L3_HIT.ANY_SNOOP",
-        "MSRIndex": "0x1a6,0x1a7",
-        "PublicDescription": "Counts all prefetch (that bring data to L2) RFOs that hit in the L3. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "PublicDescription": "Counts all prefetch (that bring data to L2) RFOs TBD TBD",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -1126,12 +1065,12 @@
         "Offcore": "1",
         "EventCode": "0xB7, 0xBB",
         "UMask": "0x1",
-        "BriefDescription": "Counts all prefetch (that bring data to LLC only) data reads that have any response type.",
-        "MSRValue": "0x0000010080 ",
+        "BriefDescription": "Counts all prefetch (that bring data to LLC only) data reads have any response type.",
+        "MSRValue": "0x0000010080",
         "Counter": "0,1,2,3",
         "EventName": "OFFCORE_RESPONSE.PF_L3_DATA_RD.ANY_RESPONSE",
-        "MSRIndex": "0x1a6,0x1a7",
-        "PublicDescription": "Counts all prefetch (that bring data to LLC only) data reads that have any response type. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "PublicDescription": "Counts all prefetch (that bring data to LLC only) data reads have any response type.",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -1139,12 +1078,12 @@
         "Offcore": "1",
         "EventCode": "0xB7, 0xBB",
         "UMask": "0x1",
-        "BriefDescription": "Counts all prefetch (that bring data to LLC only) data reads that hit in the L3 and sibling core snoops are not needed as either the core-valid bit is not set or the shared line is present in multiple cores.",
-        "MSRValue": "0x01003c0080 ",
+        "BriefDescription": "Counts all prefetch (that bring data to LLC only) data reads TBD TBD",
+        "MSRValue": "0x01003C0080",
         "Counter": "0,1,2,3",
         "EventName": "OFFCORE_RESPONSE.PF_L3_DATA_RD.L3_HIT.NO_SNOOP_NEEDED",
-        "MSRIndex": "0x1a6,0x1a7",
-        "PublicDescription": "Counts all prefetch (that bring data to LLC only) data reads that hit in the L3 and sibling core snoops are not needed as either the core-valid bit is not set or the shared line is present in multiple cores. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "PublicDescription": "Counts all prefetch (that bring data to LLC only) data reads TBD TBD",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -1152,25 +1091,12 @@
         "Offcore": "1",
         "EventCode": "0xB7, 0xBB",
         "UMask": "0x1",
-        "BriefDescription": "Counts all prefetch (that bring data to LLC only) data reads that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded.",
-        "MSRValue": "0x04003c0080 ",
+        "BriefDescription": "Counts all prefetch (that bring data to LLC only) data reads TBD TBD",
+        "MSRValue": "0x04003C0080",
         "Counter": "0,1,2,3",
         "EventName": "OFFCORE_RESPONSE.PF_L3_DATA_RD.L3_HIT.HIT_OTHER_CORE_NO_FWD",
-        "MSRIndex": "0x1a6,0x1a7",
-        "PublicDescription": "Counts all prefetch (that bring data to LLC only) data reads that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
-        "SampleAfterValue": "100003",
-        "CounterHTOff": "0,1,2,3"
-    },
-    {
-        "Offcore": "1",
-        "EventCode": "0xB7, 0xBB",
-        "UMask": "0x1",
-        "BriefDescription": "PF_L3_DATA_RD & L3_HIT & SNOOP_HIT_WITH_FWD",
-        "MSRValue": "0x08003c0080 ",
-        "Counter": "0,1,2,3",
-        "EventName": "OFFCORE_RESPONSE.PF_L3_DATA_RD.L3_HIT.SNOOP_HIT_WITH_FWD",
-        "MSRIndex": "0x1a6,0x1a7",
-        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "PublicDescription": "Counts all prefetch (that bring data to LLC only) data reads TBD TBD",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -1178,12 +1104,12 @@
         "Offcore": "1",
         "EventCode": "0xB7, 0xBB",
         "UMask": "0x1",
-        "BriefDescription": "Counts all prefetch (that bring data to LLC only) data reads that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded.",
-        "MSRValue": "0x10003c0080 ",
+        "BriefDescription": "Counts all prefetch (that bring data to LLC only) data reads TBD TBD",
+        "MSRValue": "0x10003C0080",
         "Counter": "0,1,2,3",
         "EventName": "OFFCORE_RESPONSE.PF_L3_DATA_RD.L3_HIT.HITM_OTHER_CORE",
-        "MSRIndex": "0x1a6,0x1a7",
-        "PublicDescription": "Counts all prefetch (that bring data to LLC only) data reads that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "PublicDescription": "Counts all prefetch (that bring data to LLC only) data reads TBD TBD",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -1191,12 +1117,12 @@
         "Offcore": "1",
         "EventCode": "0xB7, 0xBB",
         "UMask": "0x1",
-        "BriefDescription": "Counts all prefetch (that bring data to LLC only) data reads that hit in the L3.",
-        "MSRValue": "0x3f803c0080 ",
+        "BriefDescription": "Counts all prefetch (that bring data to LLC only) data reads TBD TBD",
+        "MSRValue": "0x3F803C0080",
         "Counter": "0,1,2,3",
         "EventName": "OFFCORE_RESPONSE.PF_L3_DATA_RD.L3_HIT.ANY_SNOOP",
-        "MSRIndex": "0x1a6,0x1a7",
-        "PublicDescription": "Counts all prefetch (that bring data to LLC only) data reads that hit in the L3. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "PublicDescription": "Counts all prefetch (that bring data to LLC only) data reads TBD TBD",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -1204,12 +1130,12 @@
         "Offcore": "1",
         "EventCode": "0xB7, 0xBB",
         "UMask": "0x1",
-        "BriefDescription": "Counts all prefetch (that bring data to LLC only) RFOs that have any response type.",
-        "MSRValue": "0x0000010100 ",
+        "BriefDescription": "Counts all prefetch (that bring data to LLC only) RFOs have any response type.",
+        "MSRValue": "0x0000010100",
         "Counter": "0,1,2,3",
         "EventName": "OFFCORE_RESPONSE.PF_L3_RFO.ANY_RESPONSE",
-        "MSRIndex": "0x1a6,0x1a7",
-        "PublicDescription": "Counts all prefetch (that bring data to LLC only) RFOs that have any response type. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "PublicDescription": "Counts all prefetch (that bring data to LLC only) RFOs have any response type.",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -1217,12 +1143,12 @@
         "Offcore": "1",
         "EventCode": "0xB7, 0xBB",
         "UMask": "0x1",
-        "BriefDescription": "Counts all prefetch (that bring data to LLC only) RFOs that hit in the L3 and sibling core snoops are not needed as either the core-valid bit is not set or the shared line is present in multiple cores.",
-        "MSRValue": "0x01003c0100 ",
+        "BriefDescription": "Counts all prefetch (that bring data to LLC only) RFOs TBD TBD",
+        "MSRValue": "0x01003C0100",
         "Counter": "0,1,2,3",
         "EventName": "OFFCORE_RESPONSE.PF_L3_RFO.L3_HIT.NO_SNOOP_NEEDED",
-        "MSRIndex": "0x1a6,0x1a7",
-        "PublicDescription": "Counts all prefetch (that bring data to LLC only) RFOs that hit in the L3 and sibling core snoops are not needed as either the core-valid bit is not set or the shared line is present in multiple cores. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "PublicDescription": "Counts all prefetch (that bring data to LLC only) RFOs TBD TBD",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -1230,12 +1156,12 @@
         "Offcore": "1",
         "EventCode": "0xB7, 0xBB",
         "UMask": "0x1",
-        "BriefDescription": "Counts all prefetch (that bring data to LLC only) RFOs that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded.",
-        "MSRValue": "0x04003c0100 ",
+        "BriefDescription": "Counts all prefetch (that bring data to LLC only) RFOs TBD TBD",
+        "MSRValue": "0x04003C0100",
         "Counter": "0,1,2,3",
         "EventName": "OFFCORE_RESPONSE.PF_L3_RFO.L3_HIT.HIT_OTHER_CORE_NO_FWD",
-        "MSRIndex": "0x1a6,0x1a7",
-        "PublicDescription": "Counts all prefetch (that bring data to LLC only) RFOs that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "PublicDescription": "Counts all prefetch (that bring data to LLC only) RFOs TBD TBD",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -1243,12 +1169,12 @@
         "Offcore": "1",
         "EventCode": "0xB7, 0xBB",
         "UMask": "0x1",
-        "BriefDescription": "PF_L3_RFO & L3_HIT & SNOOP_HIT_WITH_FWD",
-        "MSRValue": "0x08003c0100 ",
+        "BriefDescription": "Counts all prefetch (that bring data to LLC only) RFOs TBD TBD",
+        "MSRValue": "0x10003C0100",
         "Counter": "0,1,2,3",
-        "EventName": "OFFCORE_RESPONSE.PF_L3_RFO.L3_HIT.SNOOP_HIT_WITH_FWD",
-        "MSRIndex": "0x1a6,0x1a7",
-        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "EventName": "OFFCORE_RESPONSE.PF_L3_RFO.L3_HIT.HITM_OTHER_CORE",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "PublicDescription": "Counts all prefetch (that bring data to LLC only) RFOs TBD TBD",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -1256,12 +1182,12 @@
         "Offcore": "1",
         "EventCode": "0xB7, 0xBB",
         "UMask": "0x1",
-        "BriefDescription": "Counts all prefetch (that bring data to LLC only) RFOs that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded.",
-        "MSRValue": "0x10003c0100 ",
+        "BriefDescription": "Counts all prefetch (that bring data to LLC only) RFOs TBD TBD",
+        "MSRValue": "0x3F803C0100",
         "Counter": "0,1,2,3",
-        "EventName": "OFFCORE_RESPONSE.PF_L3_RFO.L3_HIT.HITM_OTHER_CORE",
-        "MSRIndex": "0x1a6,0x1a7",
-        "PublicDescription": "Counts all prefetch (that bring data to LLC only) RFOs that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "EventName": "OFFCORE_RESPONSE.PF_L3_RFO.L3_HIT.ANY_SNOOP",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "PublicDescription": "Counts all prefetch (that bring data to LLC only) RFOs TBD TBD",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -1269,12 +1195,12 @@
         "Offcore": "1",
         "EventCode": "0xB7, 0xBB",
         "UMask": "0x1",
-        "BriefDescription": "Counts all prefetch (that bring data to LLC only) RFOs that hit in the L3.",
-        "MSRValue": "0x3f803c0100 ",
+        "BriefDescription": "Counts L1 data cache hardware prefetch requests and software prefetch requests have any response type.",
+        "MSRValue": "0x0000010400",
         "Counter": "0,1,2,3",
-        "EventName": "OFFCORE_RESPONSE.PF_L3_RFO.L3_HIT.ANY_SNOOP",
-        "MSRIndex": "0x1a6,0x1a7",
-        "PublicDescription": "Counts all prefetch (that bring data to LLC only) RFOs that hit in the L3. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "EventName": "OFFCORE_RESPONSE.PF_L1D_AND_SW.ANY_RESPONSE",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "PublicDescription": "Counts L1 data cache hardware prefetch requests and software prefetch requests have any response type.",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -1282,12 +1208,12 @@
         "Offcore": "1",
         "EventCode": "0xB7, 0xBB",
         "UMask": "0x1",
-        "BriefDescription": "Counts L1 data cache hardware prefetch requests and software prefetch requests that have any response type.",
-        "MSRValue": "0x0000010400 ",
+        "BriefDescription": "Counts L1 data cache hardware prefetch requests and software prefetch requests TBD TBD",
+        "MSRValue": "0x01003C0400",
         "Counter": "0,1,2,3",
-        "EventName": "OFFCORE_RESPONSE.PF_L1D_AND_SW.ANY_RESPONSE",
-        "MSRIndex": "0x1a6,0x1a7",
-        "PublicDescription": "Counts L1 data cache hardware prefetch requests and software prefetch requests that have any response type. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "EventName": "OFFCORE_RESPONSE.PF_L1D_AND_SW.L3_HIT.NO_SNOOP_NEEDED",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "PublicDescription": "Counts L1 data cache hardware prefetch requests and software prefetch requests TBD TBD",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -1295,12 +1221,12 @@
         "Offcore": "1",
         "EventCode": "0xB7, 0xBB",
         "UMask": "0x1",
-        "BriefDescription": "Counts L1 data cache hardware prefetch requests and software prefetch requests that hit in the L3 and sibling core snoops are not needed as either the core-valid bit is not set or the shared line is present in multiple cores.",
-        "MSRValue": "0x01003c0400 ",
+        "BriefDescription": "Counts L1 data cache hardware prefetch requests and software prefetch requests TBD TBD",
+        "MSRValue": "0x04003C0400",
         "Counter": "0,1,2,3",
-        "EventName": "OFFCORE_RESPONSE.PF_L1D_AND_SW.L3_HIT.NO_SNOOP_NEEDED",
-        "MSRIndex": "0x1a6,0x1a7",
-        "PublicDescription": "Counts L1 data cache hardware prefetch requests and software prefetch requests that hit in the L3 and sibling core snoops are not needed as either the core-valid bit is not set or the shared line is present in multiple cores. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "EventName": "OFFCORE_RESPONSE.PF_L1D_AND_SW.L3_HIT.HIT_OTHER_CORE_NO_FWD",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "PublicDescription": "Counts L1 data cache hardware prefetch requests and software prefetch requests TBD TBD",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -1308,12 +1234,12 @@
         "Offcore": "1",
         "EventCode": "0xB7, 0xBB",
         "UMask": "0x1",
-        "BriefDescription": "Counts L1 data cache hardware prefetch requests and software prefetch requests that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded.",
-        "MSRValue": "0x04003c0400 ",
+        "BriefDescription": "Counts L1 data cache hardware prefetch requests and software prefetch requests TBD TBD",
+        "MSRValue": "0x10003C0400",
         "Counter": "0,1,2,3",
-        "EventName": "OFFCORE_RESPONSE.PF_L1D_AND_SW.L3_HIT.HIT_OTHER_CORE_NO_FWD",
-        "MSRIndex": "0x1a6,0x1a7",
-        "PublicDescription": "Counts L1 data cache hardware prefetch requests and software prefetch requests that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "EventName": "OFFCORE_RESPONSE.PF_L1D_AND_SW.L3_HIT.HITM_OTHER_CORE",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "PublicDescription": "Counts L1 data cache hardware prefetch requests and software prefetch requests TBD TBD",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -1321,12 +1247,12 @@
         "Offcore": "1",
         "EventCode": "0xB7, 0xBB",
         "UMask": "0x1",
-        "BriefDescription": "PF_L1D_AND_SW & L3_HIT & SNOOP_HIT_WITH_FWD",
-        "MSRValue": "0x08003c0400 ",
+        "BriefDescription": "Counts L1 data cache hardware prefetch requests and software prefetch requests TBD TBD",
+        "MSRValue": "0x3F803C0400",
         "Counter": "0,1,2,3",
-        "EventName": "OFFCORE_RESPONSE.PF_L1D_AND_SW.L3_HIT.SNOOP_HIT_WITH_FWD",
-        "MSRIndex": "0x1a6,0x1a7",
-        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "EventName": "OFFCORE_RESPONSE.PF_L1D_AND_SW.L3_HIT.ANY_SNOOP",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "PublicDescription": "Counts L1 data cache hardware prefetch requests and software prefetch requests TBD TBD",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -1334,12 +1260,12 @@
         "Offcore": "1",
         "EventCode": "0xB7, 0xBB",
         "UMask": "0x1",
-        "BriefDescription": "Counts L1 data cache hardware prefetch requests and software prefetch requests that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded.",
-        "MSRValue": "0x10003c0400 ",
+        "BriefDescription": "TBD have any response type.",
+        "MSRValue": "0x0000010490",
         "Counter": "0,1,2,3",
-        "EventName": "OFFCORE_RESPONSE.PF_L1D_AND_SW.L3_HIT.HITM_OTHER_CORE",
-        "MSRIndex": "0x1a6,0x1a7",
-        "PublicDescription": "Counts L1 data cache hardware prefetch requests and software prefetch requests that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "EventName": "OFFCORE_RESPONSE.ALL_PF_DATA_RD.ANY_RESPONSE",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "PublicDescription": "TBD have any response type.",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -1347,12 +1273,12 @@
         "Offcore": "1",
         "EventCode": "0xB7, 0xBB",
         "UMask": "0x1",
-        "BriefDescription": "Counts L1 data cache hardware prefetch requests and software prefetch requests that hit in the L3.",
-        "MSRValue": "0x3f803c0400 ",
+        "BriefDescription": "TBD TBD TBD",
+        "MSRValue": "0x01003C0490",
         "Counter": "0,1,2,3",
-        "EventName": "OFFCORE_RESPONSE.PF_L1D_AND_SW.L3_HIT.ANY_SNOOP",
-        "MSRIndex": "0x1a6,0x1a7",
-        "PublicDescription": "Counts L1 data cache hardware prefetch requests and software prefetch requests that hit in the L3. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "EventName": "OFFCORE_RESPONSE.ALL_PF_DATA_RD.L3_HIT.NO_SNOOP_NEEDED",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "PublicDescription": "TBD TBD TBD",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -1360,12 +1286,12 @@
         "Offcore": "1",
         "EventCode": "0xB7, 0xBB",
         "UMask": "0x1",
-        "BriefDescription": "Counts any other requests that have any response type.",
-        "MSRValue": "0x0000018000 ",
+        "BriefDescription": "TBD TBD TBD",
+        "MSRValue": "0x04003C0490",
         "Counter": "0,1,2,3",
-        "EventName": "OFFCORE_RESPONSE.OTHER.ANY_RESPONSE",
-        "MSRIndex": "0x1a6,0x1a7",
-        "PublicDescription": "Counts any other requests that have any response type. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "EventName": "OFFCORE_RESPONSE.ALL_PF_DATA_RD.L3_HIT.HIT_OTHER_CORE_NO_FWD",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "PublicDescription": "TBD TBD TBD",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -1373,12 +1299,12 @@
         "Offcore": "1",
         "EventCode": "0xB7, 0xBB",
         "UMask": "0x1",
-        "BriefDescription": "Counts any other requests that hit in the L3 and sibling core snoops are not needed as either the core-valid bit is not set or the shared line is present in multiple cores.",
-        "MSRValue": "0x01003c8000 ",
+        "BriefDescription": "TBD TBD TBD",
+        "MSRValue": "0x10003C0490",
         "Counter": "0,1,2,3",
-        "EventName": "OFFCORE_RESPONSE.OTHER.L3_HIT.NO_SNOOP_NEEDED",
-        "MSRIndex": "0x1a6,0x1a7",
-        "PublicDescription": "Counts any other requests that hit in the L3 and sibling core snoops are not needed as either the core-valid bit is not set or the shared line is present in multiple cores. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "EventName": "OFFCORE_RESPONSE.ALL_PF_DATA_RD.L3_HIT.HITM_OTHER_CORE",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "PublicDescription": "TBD TBD TBD",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -1386,12 +1312,12 @@
         "Offcore": "1",
         "EventCode": "0xB7, 0xBB",
         "UMask": "0x1",
-        "BriefDescription": "Counts any other requests that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded.",
-        "MSRValue": "0x04003c8000 ",
+        "BriefDescription": "TBD TBD TBD",
+        "MSRValue": "0x3F803C0490",
         "Counter": "0,1,2,3",
-        "EventName": "OFFCORE_RESPONSE.OTHER.L3_HIT.HIT_OTHER_CORE_NO_FWD",
-        "MSRIndex": "0x1a6,0x1a7",
-        "PublicDescription": "Counts any other requests that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "EventName": "OFFCORE_RESPONSE.ALL_PF_DATA_RD.L3_HIT.ANY_SNOOP",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "PublicDescription": "TBD TBD TBD",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -1399,12 +1325,12 @@
         "Offcore": "1",
         "EventCode": "0xB7, 0xBB",
         "UMask": "0x1",
-        "BriefDescription": "OTHER & L3_HIT & SNOOP_HIT_WITH_FWD",
-        "MSRValue": "0x08003c8000 ",
+        "BriefDescription": "TBD have any response type.",
+        "MSRValue": "0x0000010120",
         "Counter": "0,1,2,3",
-        "EventName": "OFFCORE_RESPONSE.OTHER.L3_HIT.SNOOP_HIT_WITH_FWD",
-        "MSRIndex": "0x1a6,0x1a7",
-        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "EventName": "OFFCORE_RESPONSE.ALL_PF_RFO.ANY_RESPONSE",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "PublicDescription": "TBD have any response type.",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -1412,12 +1338,12 @@
         "Offcore": "1",
         "EventCode": "0xB7, 0xBB",
         "UMask": "0x1",
-        "BriefDescription": "Counts any other requests that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded.",
-        "MSRValue": "0x10003c8000 ",
+        "BriefDescription": "TBD TBD TBD",
+        "MSRValue": "0x01003C0120",
         "Counter": "0,1,2,3",
-        "EventName": "OFFCORE_RESPONSE.OTHER.L3_HIT.HITM_OTHER_CORE",
-        "MSRIndex": "0x1a6,0x1a7",
-        "PublicDescription": "Counts any other requests that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "EventName": "OFFCORE_RESPONSE.ALL_PF_RFO.L3_HIT.NO_SNOOP_NEEDED",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "PublicDescription": "TBD TBD TBD",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -1425,12 +1351,12 @@
         "Offcore": "1",
         "EventCode": "0xB7, 0xBB",
         "UMask": "0x1",
-        "BriefDescription": "Counts any other requests that hit in the L3.",
-        "MSRValue": "0x3f803c8000 ",
+        "BriefDescription": "TBD TBD TBD",
+        "MSRValue": "0x04003C0120",
         "Counter": "0,1,2,3",
-        "EventName": "OFFCORE_RESPONSE.OTHER.L3_HIT.ANY_SNOOP",
-        "MSRIndex": "0x1a6,0x1a7",
-        "PublicDescription": "Counts any other requests that hit in the L3. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "EventName": "OFFCORE_RESPONSE.ALL_PF_RFO.L3_HIT.HIT_OTHER_CORE_NO_FWD",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "PublicDescription": "TBD TBD TBD",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -1438,12 +1364,12 @@
         "Offcore": "1",
         "EventCode": "0xB7, 0xBB",
         "UMask": "0x1",
-        "BriefDescription": "Counts all prefetch data reads that have any response type.",
-        "MSRValue": "0x0000010490 ",
+        "BriefDescription": "TBD TBD TBD",
+        "MSRValue": "0x10003C0120",
         "Counter": "0,1,2,3",
-        "EventName": "OFFCORE_RESPONSE.ALL_PF_DATA_RD.ANY_RESPONSE",
-        "MSRIndex": "0x1a6,0x1a7",
-        "PublicDescription": "Counts all prefetch data reads that have any response type. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "EventName": "OFFCORE_RESPONSE.ALL_PF_RFO.L3_HIT.HITM_OTHER_CORE",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "PublicDescription": "TBD TBD TBD",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -1451,12 +1377,12 @@
         "Offcore": "1",
         "EventCode": "0xB7, 0xBB",
         "UMask": "0x1",
-        "BriefDescription": "Counts all prefetch data reads that hit in the L3 and sibling core snoops are not needed as either the core-valid bit is not set or the shared line is present in multiple cores.",
-        "MSRValue": "0x01003c0490 ",
+        "BriefDescription": "TBD TBD TBD",
+        "MSRValue": "0x3F803C0120",
         "Counter": "0,1,2,3",
-        "EventName": "OFFCORE_RESPONSE.ALL_PF_DATA_RD.L3_HIT.NO_SNOOP_NEEDED",
-        "MSRIndex": "0x1a6,0x1a7",
-        "PublicDescription": "Counts all prefetch data reads that hit in the L3 and sibling core snoops are not needed as either the core-valid bit is not set or the shared line is present in multiple cores. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "EventName": "OFFCORE_RESPONSE.ALL_PF_RFO.L3_HIT.ANY_SNOOP",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "PublicDescription": "TBD TBD TBD",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -1464,12 +1390,12 @@
         "Offcore": "1",
         "EventCode": "0xB7, 0xBB",
         "UMask": "0x1",
-        "BriefDescription": "Counts all prefetch data reads that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded.",
-        "MSRValue": "0x04003c0490 ",
+        "BriefDescription": "TBD have any response type.",
+        "MSRValue": "0x0000010491",
         "Counter": "0,1,2,3",
-        "EventName": "OFFCORE_RESPONSE.ALL_PF_DATA_RD.L3_HIT.HIT_OTHER_CORE_NO_FWD",
-        "MSRIndex": "0x1a6,0x1a7",
-        "PublicDescription": "Counts all prefetch data reads that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "EventName": "OFFCORE_RESPONSE.ALL_DATA_RD.ANY_RESPONSE",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "PublicDescription": "TBD have any response type.",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -1477,12 +1403,12 @@
         "Offcore": "1",
         "EventCode": "0xB7, 0xBB",
         "UMask": "0x1",
-        "BriefDescription": "ALL_PF_DATA_RD & L3_HIT & SNOOP_HIT_WITH_FWD",
-        "MSRValue": "0x08003c0490 ",
+        "BriefDescription": "TBD TBD TBD",
+        "MSRValue": "0x01003C0491",
         "Counter": "0,1,2,3",
-        "EventName": "OFFCORE_RESPONSE.ALL_PF_DATA_RD.L3_HIT.SNOOP_HIT_WITH_FWD",
-        "MSRIndex": "0x1a6,0x1a7",
-        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "EventName": "OFFCORE_RESPONSE.ALL_DATA_RD.L3_HIT.NO_SNOOP_NEEDED",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "PublicDescription": "TBD TBD TBD",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -1490,12 +1416,12 @@
         "Offcore": "1",
         "EventCode": "0xB7, 0xBB",
         "UMask": "0x1",
-        "BriefDescription": "Counts all prefetch data reads that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded.",
-        "MSRValue": "0x10003c0490 ",
+        "BriefDescription": "TBD TBD TBD",
+        "MSRValue": "0x04003C0491",
         "Counter": "0,1,2,3",
-        "EventName": "OFFCORE_RESPONSE.ALL_PF_DATA_RD.L3_HIT.HITM_OTHER_CORE",
-        "MSRIndex": "0x1a6,0x1a7",
-        "PublicDescription": "Counts all prefetch data reads that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "EventName": "OFFCORE_RESPONSE.ALL_DATA_RD.L3_HIT.HIT_OTHER_CORE_NO_FWD",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "PublicDescription": "TBD TBD TBD",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -1503,12 +1429,12 @@
         "Offcore": "1",
         "EventCode": "0xB7, 0xBB",
         "UMask": "0x1",
-        "BriefDescription": "Counts all prefetch data reads that hit in the L3.",
-        "MSRValue": "0x3f803c0490 ",
+        "BriefDescription": "TBD TBD TBD",
+        "MSRValue": "0x10003C0491",
         "Counter": "0,1,2,3",
-        "EventName": "OFFCORE_RESPONSE.ALL_PF_DATA_RD.L3_HIT.ANY_SNOOP",
-        "MSRIndex": "0x1a6,0x1a7",
-        "PublicDescription": "Counts all prefetch data reads that hit in the L3. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "EventName": "OFFCORE_RESPONSE.ALL_DATA_RD.L3_HIT.HITM_OTHER_CORE",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "PublicDescription": "TBD TBD TBD",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -1516,12 +1442,12 @@
         "Offcore": "1",
         "EventCode": "0xB7, 0xBB",
         "UMask": "0x1",
-        "BriefDescription": "Counts prefetch RFOs that have any response type.",
-        "MSRValue": "0x0000010120 ",
+        "BriefDescription": "TBD TBD TBD",
+        "MSRValue": "0x3F803C0491",
         "Counter": "0,1,2,3",
-        "EventName": "OFFCORE_RESPONSE.ALL_PF_RFO.ANY_RESPONSE",
-        "MSRIndex": "0x1a6,0x1a7",
-        "PublicDescription": "Counts prefetch RFOs that have any response type. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "EventName": "OFFCORE_RESPONSE.ALL_DATA_RD.L3_HIT.ANY_SNOOP",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "PublicDescription": "TBD TBD TBD",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -1529,12 +1455,12 @@
         "Offcore": "1",
         "EventCode": "0xB7, 0xBB",
         "UMask": "0x1",
-        "BriefDescription": "Counts prefetch RFOs that hit in the L3 and sibling core snoops are not needed as either the core-valid bit is not set or the shared line is present in multiple cores.",
-        "MSRValue": "0x01003c0120 ",
+        "BriefDescription": "TBD have any response type.",
+        "MSRValue": "0x0000010122",
         "Counter": "0,1,2,3",
-        "EventName": "OFFCORE_RESPONSE.ALL_PF_RFO.L3_HIT.NO_SNOOP_NEEDED",
-        "MSRIndex": "0x1a6,0x1a7",
-        "PublicDescription": "Counts prefetch RFOs that hit in the L3 and sibling core snoops are not needed as either the core-valid bit is not set or the shared line is present in multiple cores. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "EventName": "OFFCORE_RESPONSE.ALL_RFO.ANY_RESPONSE",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "PublicDescription": "TBD have any response type.",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -1542,12 +1468,12 @@
         "Offcore": "1",
         "EventCode": "0xB7, 0xBB",
         "UMask": "0x1",
-        "BriefDescription": "Counts prefetch RFOs that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded.",
-        "MSRValue": "0x04003c0120 ",
+        "BriefDescription": "TBD TBD TBD",
+        "MSRValue": "0x01003C0122",
         "Counter": "0,1,2,3",
-        "EventName": "OFFCORE_RESPONSE.ALL_PF_RFO.L3_HIT.HIT_OTHER_CORE_NO_FWD",
-        "MSRIndex": "0x1a6,0x1a7",
-        "PublicDescription": "Counts prefetch RFOs that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "EventName": "OFFCORE_RESPONSE.ALL_RFO.L3_HIT.NO_SNOOP_NEEDED",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "PublicDescription": "TBD TBD TBD",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -1555,12 +1481,12 @@
         "Offcore": "1",
         "EventCode": "0xB7, 0xBB",
         "UMask": "0x1",
-        "BriefDescription": "ALL_PF_RFO & L3_HIT & SNOOP_HIT_WITH_FWD",
-        "MSRValue": "0x08003c0120 ",
+        "BriefDescription": "TBD TBD TBD",
+        "MSRValue": "0x04003C0122",
         "Counter": "0,1,2,3",
-        "EventName": "OFFCORE_RESPONSE.ALL_PF_RFO.L3_HIT.SNOOP_HIT_WITH_FWD",
-        "MSRIndex": "0x1a6,0x1a7",
-        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "EventName": "OFFCORE_RESPONSE.ALL_RFO.L3_HIT.HIT_OTHER_CORE_NO_FWD",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "PublicDescription": "TBD TBD TBD",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -1568,12 +1494,12 @@
         "Offcore": "1",
         "EventCode": "0xB7, 0xBB",
         "UMask": "0x1",
-        "BriefDescription": "Counts prefetch RFOs that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded.",
-        "MSRValue": "0x10003c0120 ",
+        "BriefDescription": "TBD TBD TBD",
+        "MSRValue": "0x10003C0122",
         "Counter": "0,1,2,3",
-        "EventName": "OFFCORE_RESPONSE.ALL_PF_RFO.L3_HIT.HITM_OTHER_CORE",
-        "MSRIndex": "0x1a6,0x1a7",
-        "PublicDescription": "Counts prefetch RFOs that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "EventName": "OFFCORE_RESPONSE.ALL_RFO.L3_HIT.HITM_OTHER_CORE",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "PublicDescription": "TBD TBD TBD",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -1581,12 +1507,12 @@
         "Offcore": "1",
         "EventCode": "0xB7, 0xBB",
         "UMask": "0x1",
-        "BriefDescription": "Counts prefetch RFOs that hit in the L3.",
-        "MSRValue": "0x3f803c0120 ",
+        "BriefDescription": "TBD TBD TBD",
+        "MSRValue": "0x3F803C0122",
         "Counter": "0,1,2,3",
-        "EventName": "OFFCORE_RESPONSE.ALL_PF_RFO.L3_HIT.ANY_SNOOP",
-        "MSRIndex": "0x1a6,0x1a7",
-        "PublicDescription": "Counts prefetch RFOs that hit in the L3. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "EventName": "OFFCORE_RESPONSE.ALL_RFO.L3_HIT.ANY_SNOOP",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "PublicDescription": "TBD TBD TBD",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -1594,12 +1520,11 @@
         "Offcore": "1",
         "EventCode": "0xB7, 0xBB",
         "UMask": "0x1",
-        "BriefDescription": "Counts all demand & prefetch data reads that have any response type.",
-        "MSRValue": "0x0000010491 ",
+        "BriefDescription": "Counts demand data reads",
+        "MSRValue": "0x08007C0001",
         "Counter": "0,1,2,3",
-        "EventName": "OFFCORE_RESPONSE.ALL_DATA_RD.ANY_RESPONSE",
-        "MSRIndex": "0x1a6,0x1a7",
-        "PublicDescription": "Counts all demand & prefetch data reads that have any response type. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_HIT.SNOOP_HIT_WITH_FWD",
+        "PublicDescription": "Counts demand data reads",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -1607,12 +1532,11 @@
         "Offcore": "1",
         "EventCode": "0xB7, 0xBB",
         "UMask": "0x1",
-        "BriefDescription": "Counts all demand & prefetch data reads that hit in the L3 and sibling core snoops are not needed as either the core-valid bit is not set or the shared line is present in multiple cores.",
-        "MSRValue": "0x01003c0491 ",
+        "BriefDescription": "Counts all demand data writes (RFOs)",
+        "MSRValue": "0x08007C0002",
         "Counter": "0,1,2,3",
-        "EventName": "OFFCORE_RESPONSE.ALL_DATA_RD.L3_HIT.NO_SNOOP_NEEDED",
-        "MSRIndex": "0x1a6,0x1a7",
-        "PublicDescription": "Counts all demand & prefetch data reads that hit in the L3 and sibling core snoops are not needed as either the core-valid bit is not set or the shared line is present in multiple cores. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_HIT.SNOOP_HIT_WITH_FWD",
+        "PublicDescription": "Counts all demand data writes (RFOs)",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -1620,12 +1544,11 @@
         "Offcore": "1",
         "EventCode": "0xB7, 0xBB",
         "UMask": "0x1",
-        "BriefDescription": "Counts all demand & prefetch data reads that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded.",
-        "MSRValue": "0x04003c0491 ",
+        "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that",
+        "MSRValue": "0x08007C0004",
         "Counter": "0,1,2,3",
-        "EventName": "OFFCORE_RESPONSE.ALL_DATA_RD.L3_HIT.HIT_OTHER_CORE_NO_FWD",
-        "MSRIndex": "0x1a6,0x1a7",
-        "PublicDescription": "Counts all demand & prefetch data reads that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_HIT.SNOOP_HIT_WITH_FWD",
+        "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -1633,12 +1556,11 @@
         "Offcore": "1",
         "EventCode": "0xB7, 0xBB",
         "UMask": "0x1",
-        "BriefDescription": "ALL_DATA_RD & L3_HIT & SNOOP_HIT_WITH_FWD",
-        "MSRValue": "0x08003c0491 ",
+        "BriefDescription": "Counts prefetch (that bring data to L2) data reads",
+        "MSRValue": "0x08007C0010",
         "Counter": "0,1,2,3",
-        "EventName": "OFFCORE_RESPONSE.ALL_DATA_RD.L3_HIT.SNOOP_HIT_WITH_FWD",
-        "MSRIndex": "0x1a6,0x1a7",
-        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "EventName": "OFFCORE_RESPONSE.PF_L2_DATA_RD.L3_HIT.SNOOP_HIT_WITH_FWD",
+        "PublicDescription": "Counts prefetch (that bring data to L2) data reads",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -1646,12 +1568,11 @@
         "Offcore": "1",
         "EventCode": "0xB7, 0xBB",
         "UMask": "0x1",
-        "BriefDescription": "Counts all demand & prefetch data reads that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded.",
-        "MSRValue": "0x10003c0491 ",
+        "BriefDescription": "Counts all prefetch (that bring data to L2) RFOs",
+        "MSRValue": "0x08007C0020",
         "Counter": "0,1,2,3",
-        "EventName": "OFFCORE_RESPONSE.ALL_DATA_RD.L3_HIT.HITM_OTHER_CORE",
-        "MSRIndex": "0x1a6,0x1a7",
-        "PublicDescription": "Counts all demand & prefetch data reads that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "EventName": "OFFCORE_RESPONSE.PF_L2_RFO.L3_HIT.SNOOP_HIT_WITH_FWD",
+        "PublicDescription": "Counts all prefetch (that bring data to L2) RFOs",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -1659,12 +1580,11 @@
         "Offcore": "1",
         "EventCode": "0xB7, 0xBB",
         "UMask": "0x1",
-        "BriefDescription": "Counts all demand & prefetch data reads that hit in the L3.",
-        "MSRValue": "0x3f803c0491 ",
+        "BriefDescription": "Counts all prefetch (that bring data to LLC only) data reads",
+        "MSRValue": "0x08007C0080",
         "Counter": "0,1,2,3",
-        "EventName": "OFFCORE_RESPONSE.ALL_DATA_RD.L3_HIT.ANY_SNOOP",
-        "MSRIndex": "0x1a6,0x1a7",
-        "PublicDescription": "Counts all demand & prefetch data reads that hit in the L3. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "EventName": "OFFCORE_RESPONSE.PF_L3_DATA_RD.L3_HIT.SNOOP_HIT_WITH_FWD",
+        "PublicDescription": "Counts all prefetch (that bring data to LLC only) data reads",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -1672,12 +1592,11 @@
         "Offcore": "1",
         "EventCode": "0xB7, 0xBB",
         "UMask": "0x1",
-        "BriefDescription": "Counts all demand & prefetch RFOs that have any response type.",
-        "MSRValue": "0x0000010122 ",
+        "BriefDescription": "Counts all prefetch (that bring data to LLC only) RFOs",
+        "MSRValue": "0x08007C0100",
         "Counter": "0,1,2,3",
-        "EventName": "OFFCORE_RESPONSE.ALL_RFO.ANY_RESPONSE",
-        "MSRIndex": "0x1a6,0x1a7",
-        "PublicDescription": "Counts all demand & prefetch RFOs that have any response type. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "EventName": "OFFCORE_RESPONSE.PF_L3_RFO.L3_HIT.SNOOP_HIT_WITH_FWD",
+        "PublicDescription": "Counts all prefetch (that bring data to LLC only) RFOs",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -1685,12 +1604,11 @@
         "Offcore": "1",
         "EventCode": "0xB7, 0xBB",
         "UMask": "0x1",
-        "BriefDescription": "Counts all demand & prefetch RFOs that hit in the L3 and sibling core snoops are not needed as either the core-valid bit is not set or the shared line is present in multiple cores.",
-        "MSRValue": "0x01003c0122 ",
+        "BriefDescription": "Counts L1 data cache hardware prefetch requests and software prefetch requests",
+        "MSRValue": "0x08007C0400",
         "Counter": "0,1,2,3",
-        "EventName": "OFFCORE_RESPONSE.ALL_RFO.L3_HIT.NO_SNOOP_NEEDED",
-        "MSRIndex": "0x1a6,0x1a7",
-        "PublicDescription": "Counts all demand & prefetch RFOs that hit in the L3 and sibling core snoops are not needed as either the core-valid bit is not set or the shared line is present in multiple cores. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "EventName": "OFFCORE_RESPONSE.PF_L1D_AND_SW.L3_HIT.SNOOP_HIT_WITH_FWD",
+        "PublicDescription": "Counts L1 data cache hardware prefetch requests and software prefetch requests",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -1698,12 +1616,11 @@
         "Offcore": "1",
         "EventCode": "0xB7, 0xBB",
         "UMask": "0x1",
-        "BriefDescription": "Counts all demand & prefetch RFOs that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded.",
-        "MSRValue": "0x04003c0122 ",
+        "BriefDescription": "TBD",
+        "MSRValue": "0x08007C0490",
         "Counter": "0,1,2,3",
-        "EventName": "OFFCORE_RESPONSE.ALL_RFO.L3_HIT.HIT_OTHER_CORE_NO_FWD",
-        "MSRIndex": "0x1a6,0x1a7",
-        "PublicDescription": "Counts all demand & prefetch RFOs that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "EventName": "OFFCORE_RESPONSE.ALL_PF_DATA_RD.L3_HIT.SNOOP_HIT_WITH_FWD",
+        "PublicDescription": "TBD",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -1711,12 +1628,11 @@
         "Offcore": "1",
         "EventCode": "0xB7, 0xBB",
         "UMask": "0x1",
-        "BriefDescription": "ALL_RFO & L3_HIT & SNOOP_HIT_WITH_FWD",
-        "MSRValue": "0x08003c0122 ",
+        "BriefDescription": "TBD",
+        "MSRValue": "0x08007C0120",
         "Counter": "0,1,2,3",
-        "EventName": "OFFCORE_RESPONSE.ALL_RFO.L3_HIT.SNOOP_HIT_WITH_FWD",
-        "MSRIndex": "0x1a6,0x1a7",
-        "PublicDescription": "tbd Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "EventName": "OFFCORE_RESPONSE.ALL_PF_RFO.L3_HIT.SNOOP_HIT_WITH_FWD",
+        "PublicDescription": "TBD",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -1724,12 +1640,11 @@
         "Offcore": "1",
         "EventCode": "0xB7, 0xBB",
         "UMask": "0x1",
-        "BriefDescription": "Counts all demand & prefetch RFOs that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded.",
-        "MSRValue": "0x10003c0122 ",
+        "BriefDescription": "TBD",
+        "MSRValue": "0x08007C0491",
         "Counter": "0,1,2,3",
-        "EventName": "OFFCORE_RESPONSE.ALL_RFO.L3_HIT.HITM_OTHER_CORE",
-        "MSRIndex": "0x1a6,0x1a7",
-        "PublicDescription": "Counts all demand & prefetch RFOs that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "EventName": "OFFCORE_RESPONSE.ALL_DATA_RD.L3_HIT.SNOOP_HIT_WITH_FWD",
+        "PublicDescription": "TBD",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -1737,12 +1652,11 @@
         "Offcore": "1",
         "EventCode": "0xB7, 0xBB",
         "UMask": "0x1",
-        "BriefDescription": "Counts all demand & prefetch RFOs that hit in the L3.",
-        "MSRValue": "0x3f803c0122 ",
+        "BriefDescription": "TBD",
+        "MSRValue": "0x08007C0122",
         "Counter": "0,1,2,3",
-        "EventName": "OFFCORE_RESPONSE.ALL_RFO.L3_HIT.ANY_SNOOP",
-        "MSRIndex": "0x1a6,0x1a7",
-        "PublicDescription": "Counts all demand & prefetch RFOs that hit in the L3. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "EventName": "OFFCORE_RESPONSE.ALL_RFO.L3_HIT.SNOOP_HIT_WITH_FWD",
+        "PublicDescription": "TBD",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     }
diff --git a/tools/perf/pmu-events/arch/x86/skylakex/floating-point.json b/tools/perf/pmu-events/arch/x86/skylakex/floating-point.json
index 286ed1a37ec9..c5d0babe89fc 100644
--- a/tools/perf/pmu-events/arch/x86/skylakex/floating-point.json
+++ b/tools/perf/pmu-events/arch/x86/skylakex/floating-point.json
@@ -59,7 +59,6 @@
         "BriefDescription": "Number of Packed Double-Precision FP arithmetic instructions (Use operation multiplier of 8)",
         "Counter": "0,1,2,3",
         "EventName": "FP_ARITH_INST_RETIRED.512B_PACKED_DOUBLE",
-        "PublicDescription": "Number of Packed Double-Precision FP arithmetic instructions (Use operation multiplier of 8).",
         "SampleAfterValue": "2000003",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
@@ -69,7 +68,6 @@
         "BriefDescription": "Number of Packed Single-Precision FP arithmetic instructions (Use operation multiplier of 16)",
         "Counter": "0,1,2,3",
         "EventName": "FP_ARITH_INST_RETIRED.512B_PACKED_SINGLE",
-        "PublicDescription": "Number of Packed Single-Precision FP arithmetic instructions (Use operation multiplier of 16).",
         "SampleAfterValue": "2000003",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
diff --git a/tools/perf/pmu-events/arch/x86/skylakex/frontend.json b/tools/perf/pmu-events/arch/x86/skylakex/frontend.json
index 403a4f89e9b2..4dc583cfb545 100644
--- a/tools/perf/pmu-events/arch/x86/skylakex/frontend.json
+++ b/tools/perf/pmu-events/arch/x86/skylakex/frontend.json
@@ -2,16 +2,6 @@
     {
         "EventCode": "0x79",
         "UMask": "0x4",
-        "BriefDescription": "Uops delivered to Instruction Decode Queue (IDQ) from MITE path",
-        "Counter": "0,1,2,3",
-        "EventName": "IDQ.MITE_UOPS",
-        "PublicDescription": "Counts the number of uops delivered to Instruction Decode Queue (IDQ) from the MITE path. Counting includes uops that may 'bypass' the IDQ. This also means that uops are not being delivered from the Decode Stream Buffer (DSB).",
-        "SampleAfterValue": "2000003",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
-    },
-    {
-        "EventCode": "0x79",
-        "UMask": "0x4",
         "BriefDescription": "Cycles when uops are being delivered to Instruction Decode Queue (IDQ) from MITE path",
         "Counter": "0,1,2,3",
         "EventName": "IDQ.MITE_CYCLES",
@@ -22,11 +12,11 @@
     },
     {
         "EventCode": "0x79",
-        "UMask": "0x8",
-        "BriefDescription": "Uops delivered to Instruction Decode Queue (IDQ) from the Decode Stream Buffer (DSB) path",
+        "UMask": "0x4",
+        "BriefDescription": "Uops delivered to Instruction Decode Queue (IDQ) from MITE path",
         "Counter": "0,1,2,3",
-        "EventName": "IDQ.DSB_UOPS",
-        "PublicDescription": "Counts the number of uops delivered to Instruction Decode Queue (IDQ) from the Decode Stream Buffer (DSB) path. Counting includes uops that may 'bypass' the IDQ.",
+        "EventName": "IDQ.MITE_UOPS",
+        "PublicDescription": "Counts the number of uops delivered to Instruction Decode Queue (IDQ) from the MITE path. Counting includes uops that may 'bypass' the IDQ. This also means that uops are not being delivered from the Decode Stream Buffer (DSB).",
         "SampleAfterValue": "2000003",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
@@ -43,6 +33,16 @@
     },
     {
         "EventCode": "0x79",
+        "UMask": "0x8",
+        "BriefDescription": "Uops delivered to Instruction Decode Queue (IDQ) from the Decode Stream Buffer (DSB) path",
+        "Counter": "0,1,2,3",
+        "EventName": "IDQ.DSB_UOPS",
+        "PublicDescription": "Counts the number of uops delivered to Instruction Decode Queue (IDQ) from the Decode Stream Buffer (DSB) path. Counting includes uops that may 'bypass' the IDQ.",
+        "SampleAfterValue": "2000003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0x79",
         "UMask": "0x10",
         "BriefDescription": "Cycles when uops initiated by Decode Stream Buffer (DSB) are being delivered to Instruction Decode Queue (IDQ) while Microcode Sequenser (MS) is busy",
         "Counter": "0,1,2,3",
@@ -55,22 +55,22 @@
     {
         "EventCode": "0x79",
         "UMask": "0x18",
-        "BriefDescription": "Cycles Decode Stream Buffer (DSB) is delivering 4 Uops",
+        "BriefDescription": "Cycles Decode Stream Buffer (DSB) is delivering any Uop",
         "Counter": "0,1,2,3",
-        "EventName": "IDQ.ALL_DSB_CYCLES_4_UOPS",
-        "CounterMask": "4",
-        "PublicDescription": "Counts the number of cycles 4 uops were delivered to Instruction Decode Queue (IDQ) from the Decode Stream Buffer (DSB) path. Count includes uops that may 'bypass' the IDQ.",
+        "EventName": "IDQ.ALL_DSB_CYCLES_ANY_UOPS",
+        "CounterMask": "1",
+        "PublicDescription": "Counts the number of cycles uops were delivered to Instruction Decode Queue (IDQ) from the Decode Stream Buffer (DSB) path. Count includes uops that may 'bypass' the IDQ.",
         "SampleAfterValue": "2000003",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
         "EventCode": "0x79",
         "UMask": "0x18",
-        "BriefDescription": "Cycles Decode Stream Buffer (DSB) is delivering any Uop",
+        "BriefDescription": "Cycles Decode Stream Buffer (DSB) is delivering 4 Uops",
         "Counter": "0,1,2,3",
-        "EventName": "IDQ.ALL_DSB_CYCLES_ANY_UOPS",
-        "CounterMask": "1",
-        "PublicDescription": "Counts the number of cycles uops were delivered to Instruction Decode Queue (IDQ) from the Decode Stream Buffer (DSB) path. Count includes uops that may 'bypass' the IDQ.",
+        "EventName": "IDQ.ALL_DSB_CYCLES_4_UOPS",
+        "CounterMask": "4",
+        "PublicDescription": "Counts the number of cycles 4 uops were delivered to Instruction Decode Queue (IDQ) from the Decode Stream Buffer (DSB) path. Count includes uops that may 'bypass' the IDQ.",
         "SampleAfterValue": "2000003",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
@@ -87,22 +87,22 @@
     {
         "EventCode": "0x79",
         "UMask": "0x24",
-        "BriefDescription": "Cycles MITE is delivering 4 Uops",
+        "BriefDescription": "Cycles MITE is delivering any Uop",
         "Counter": "0,1,2,3",
-        "EventName": "IDQ.ALL_MITE_CYCLES_4_UOPS",
-        "CounterMask": "4",
-        "PublicDescription": "Counts the number of cycles 4 uops were delivered to the Instruction Decode Queue (IDQ) from the MITE (legacy decode pipeline) path. Counting includes uops that may 'bypass' the IDQ. During these cycles uops are not being delivered from the Decode Stream Buffer (DSB).",
+        "EventName": "IDQ.ALL_MITE_CYCLES_ANY_UOPS",
+        "CounterMask": "1",
+        "PublicDescription": "Counts the number of cycles uops were delivered to the Instruction Decode Queue (IDQ) from the MITE (legacy decode pipeline) path. Counting includes uops that may 'bypass' the IDQ. During these cycles uops are not being delivered from the Decode Stream Buffer (DSB).",
         "SampleAfterValue": "2000003",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
         "EventCode": "0x79",
         "UMask": "0x24",
-        "BriefDescription": "Cycles MITE is delivering any Uop",
+        "BriefDescription": "Cycles MITE is delivering 4 Uops",
         "Counter": "0,1,2,3",
-        "EventName": "IDQ.ALL_MITE_CYCLES_ANY_UOPS",
-        "CounterMask": "1",
-        "PublicDescription": "Counts the number of cycles uops were delivered to the Instruction Decode Queue (IDQ) from the MITE (legacy decode pipeline) path. Counting includes uops that may 'bypass' the IDQ. During these cycles uops are not being delivered from the Decode Stream Buffer (DSB).",
+        "EventName": "IDQ.ALL_MITE_CYCLES_4_UOPS",
+        "CounterMask": "4",
+        "PublicDescription": "Counts the number of cycles 4 uops were delivered to the Instruction Decode Queue (IDQ) from the MITE (legacy decode pipeline) path. Counting includes uops that may 'bypass' the IDQ. During these cycles uops are not being delivered from the Decode Stream Buffer (DSB).",
         "SampleAfterValue": "2000003",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
@@ -118,24 +118,24 @@
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "EdgeDetect": "1",
         "EventCode": "0x79",
         "UMask": "0x30",
-        "BriefDescription": "Number of switches from DSB (Decode Stream Buffer) or MITE (legacy decode pipeline) to the Microcode Sequencer",
+        "BriefDescription": "Uops delivered to Instruction Decode Queue (IDQ) while Microcode Sequenser (MS) is busy",
         "Counter": "0,1,2,3",
-        "EventName": "IDQ.MS_SWITCHES",
-        "CounterMask": "1",
-        "PublicDescription": "Number of switches from DSB (Decode Stream Buffer) or MITE (legacy decode pipeline) to the Microcode Sequencer.",
+        "EventName": "IDQ.MS_UOPS",
+        "PublicDescription": "Counts the total number of uops delivered by the Microcode Sequencer (MS). Any instruction over 4 uops will be delivered by the MS. Some instructions such as transcendentals may additionally generate uops from the MS.",
         "SampleAfterValue": "2000003",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
+        "EdgeDetect": "1",
         "EventCode": "0x79",
         "UMask": "0x30",
-        "BriefDescription": "Uops delivered to Instruction Decode Queue (IDQ) while Microcode Sequenser (MS) is busy",
+        "BriefDescription": "Number of switches from DSB (Decode Stream Buffer) or MITE (legacy decode pipeline) to the Microcode Sequencer",
         "Counter": "0,1,2,3",
-        "EventName": "IDQ.MS_UOPS",
-        "PublicDescription": "Counts the total number of uops delivered by the Microcode Sequencer (MS). Any instruction over 4 uops will be delivered by the MS. Some instructions such as transcendentals may additionally generate uops from the MS.",
+        "EventName": "IDQ.MS_SWITCHES",
+        "CounterMask": "1",
+        "PublicDescription": "Number of switches from DSB (Decode Stream Buffer) or MITE (legacy decode pipeline) to the Microcode Sequencer.",
         "SampleAfterValue": "2000003",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
@@ -177,67 +177,67 @@
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
+        "Invert": "1",
         "EventCode": "0x9C",
         "UMask": "0x1",
-        "BriefDescription": "Uops not delivered to Resource Allocation Table (RAT) per thread when backend of the machine is not stalled",
+        "BriefDescription": "Counts cycles FE delivered 4 uops or Resource Allocation Table (RAT) was stalling FE.",
         "Counter": "0,1,2,3",
-        "EventName": "IDQ_UOPS_NOT_DELIVERED.CORE",
-        "PublicDescription": "Counts the number of uops not delivered to Resource Allocation Table (RAT) per thread adding 4  x when Resource Allocation Table (RAT) is not stalled and Instruction Decode Queue (IDQ) delivers x uops to Resource Allocation Table (RAT) (where x belongs to {0,1,2,3}). Counting does not cover cases when: a. IDQ-Resource Allocation Table (RAT) pipe serves the other thread. b. Resource Allocation Table (RAT) is stalled for the thread (including uop drops and clear BE conditions).  c. Instruction Decode Queue (IDQ) delivers four uops.",
+        "EventName": "IDQ_UOPS_NOT_DELIVERED.CYCLES_FE_WAS_OK",
+        "CounterMask": "1",
         "SampleAfterValue": "2000003",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
         "EventCode": "0x9C",
         "UMask": "0x1",
-        "BriefDescription": "Cycles per thread when 4 or more uops are not delivered to Resource Allocation Table (RAT) when backend of the machine is not stalled",
+        "BriefDescription": "Cycles with less than 3 uops delivered by the front end.",
         "Counter": "0,1,2,3",
-        "EventName": "IDQ_UOPS_NOT_DELIVERED.CYCLES_0_UOPS_DELIV.CORE",
-        "CounterMask": "4",
-        "PublicDescription": "Counts, on the per-thread basis, cycles when no uops are delivered to Resource Allocation Table (RAT). IDQ_Uops_Not_Delivered.core =4.",
+        "EventName": "IDQ_UOPS_NOT_DELIVERED.CYCLES_LE_3_UOP_DELIV.CORE",
+        "CounterMask": "1",
+        "PublicDescription": "Cycles with less than 3 uops delivered by the front-end.",
         "SampleAfterValue": "2000003",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
         "EventCode": "0x9C",
         "UMask": "0x1",
-        "BriefDescription": "Cycles per thread when 3 or more uops are not delivered to Resource Allocation Table (RAT) when backend of the machine is not stalled",
+        "BriefDescription": "Cycles with less than 2 uops delivered by the front end.",
         "Counter": "0,1,2,3",
-        "EventName": "IDQ_UOPS_NOT_DELIVERED.CYCLES_LE_1_UOP_DELIV.CORE",
-        "CounterMask": "3",
-        "PublicDescription": "Counts, on the per-thread basis, cycles when less than 1 uop is delivered to Resource Allocation Table (RAT). IDQ_Uops_Not_Delivered.core >= 3.",
+        "EventName": "IDQ_UOPS_NOT_DELIVERED.CYCLES_LE_2_UOP_DELIV.CORE",
+        "CounterMask": "2",
+        "PublicDescription": "Cycles with less than 2 uops delivered by the front-end.",
         "SampleAfterValue": "2000003",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
         "EventCode": "0x9C",
         "UMask": "0x1",
-        "BriefDescription": "Cycles with less than 2 uops delivered by the front end.",
+        "BriefDescription": "Cycles per thread when 3 or more uops are not delivered to Resource Allocation Table (RAT) when backend of the machine is not stalled",
         "Counter": "0,1,2,3",
-        "EventName": "IDQ_UOPS_NOT_DELIVERED.CYCLES_LE_2_UOP_DELIV.CORE",
-        "CounterMask": "2",
-        "PublicDescription": "Cycles with less than 2 uops delivered by the front-end.",
+        "EventName": "IDQ_UOPS_NOT_DELIVERED.CYCLES_LE_1_UOP_DELIV.CORE",
+        "CounterMask": "3",
+        "PublicDescription": "Counts, on the per-thread basis, cycles when less than 1 uop is delivered to Resource Allocation Table (RAT). IDQ_Uops_Not_Delivered.core >= 3.",
         "SampleAfterValue": "2000003",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
         "EventCode": "0x9C",
         "UMask": "0x1",
-        "BriefDescription": "Cycles with less than 3 uops delivered by the front end.",
+        "BriefDescription": "Cycles per thread when 4 or more uops are not delivered to Resource Allocation Table (RAT) when backend of the machine is not stalled",
         "Counter": "0,1,2,3",
-        "EventName": "IDQ_UOPS_NOT_DELIVERED.CYCLES_LE_3_UOP_DELIV.CORE",
-        "CounterMask": "1",
-        "PublicDescription": "Cycles with less than 3 uops delivered by the front-end.",
+        "EventName": "IDQ_UOPS_NOT_DELIVERED.CYCLES_0_UOPS_DELIV.CORE",
+        "CounterMask": "4",
+        "PublicDescription": "Counts, on the per-thread basis, cycles when no uops are delivered to Resource Allocation Table (RAT). IDQ_Uops_Not_Delivered.core =4.",
         "SampleAfterValue": "2000003",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "Invert": "1",
         "EventCode": "0x9C",
         "UMask": "0x1",
-        "BriefDescription": "Counts cycles FE delivered 4 uops or Resource Allocation Table (RAT) was stalling FE.",
+        "BriefDescription": "Uops not delivered to Resource Allocation Table (RAT) per thread when backend of the machine is not stalled",
         "Counter": "0,1,2,3",
-        "EventName": "IDQ_UOPS_NOT_DELIVERED.CYCLES_FE_WAS_OK",
-        "CounterMask": "1",
+        "EventName": "IDQ_UOPS_NOT_DELIVERED.CORE",
+        "PublicDescription": "Counts the number of uops not delivered to Resource Allocation Table (RAT) per thread adding \u201c4 \u2013 x\u201d when Resource Allocation Table (RAT) is not stalled and Instruction Decode Queue (IDQ) delivers x uops to Resource Allocation Table (RAT) (where x belongs to {0,1,2,3}). Counting does not cover cases when: a. IDQ-Resource Allocation Table (RAT) pipe serves the other thread. b. Resource Allocation Table (RAT) is stalled for the thread (including uop drops and clear BE conditions).  c. Instruction Decode Queue (IDQ) delivers four uops.",
         "SampleAfterValue": "2000003",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
@@ -247,20 +247,19 @@
         "BriefDescription": "Decode Stream Buffer (DSB)-to-MITE switch true penalty cycles.",
         "Counter": "0,1,2,3",
         "EventName": "DSB2MITE_SWITCHES.PENALTY_CYCLES",
-        "PublicDescription": "Counts Decode Stream Buffer (DSB)-to-MITE switch true penalty cycles. These cycles do not include uops routed through because of the switch itself, for example, when Instruction Decode Queue (IDQ) pre-allocation is unavailable, or Instruction Decode Queue (IDQ) is full. SBD-to-MITE switch true penalty cycles happen after the merge mux (MM) receives Decode Stream Buffer (DSB) Sync-indication until receiving the first MITE uop. MM is placed before Instruction Decode Queue (IDQ) to merge uops being fed from the MITE and Decode Stream Buffer (DSB) paths. Decode Stream Buffer (DSB) inserts the Sync-indication whenever a Decode Stream Buffer (DSB)-to-MITE switch occurs.Penalty: A Decode Stream Buffer (DSB) hit followed by a Decode Stream Buffer (DSB) miss can cost up to six cycles in which no uops are delivered to the IDQ. Most often, such switches from the Decode Stream Buffer (DSB) to the legacy pipeline cost 02 cycles.",
+        "PublicDescription": "Counts Decode Stream Buffer (DSB)-to-MITE switch true penalty cycles. These cycles do not include uops routed through because of the switch itself, for example, when Instruction Decode Queue (IDQ) pre-allocation is unavailable, or Instruction Decode Queue (IDQ) is full. SBD-to-MITE switch true penalty cycles happen after the merge mux (MM) receives Decode Stream Buffer (DSB) Sync-indication until receiving the first MITE uop. MM is placed before Instruction Decode Queue (IDQ) to merge uops being fed from the MITE and Decode Stream Buffer (DSB) paths. Decode Stream Buffer (DSB) inserts the Sync-indication whenever a Decode Stream Buffer (DSB)-to-MITE switch occurs.Penalty: A Decode Stream Buffer (DSB) hit followed by a Decode Stream Buffer (DSB) miss can cost up to six cycles in which no uops are delivered to the IDQ. Most often, such switches from the Decode Stream Buffer (DSB) to the legacy pipeline cost 0\u20132 cycles.",
         "SampleAfterValue": "2000003",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
         "EventCode": "0xC6",
         "UMask": "0x1",
-        "BriefDescription": "Retired Instructions who experienced decode stream buffer (DSB - the decoded instruction-cache) miss. Precise Event.",
+        "BriefDescription": "Retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 4 cycles which was not interrupted by a back-end stall. Precise Event.",
         "PEBS": "1",
-        "MSRValue": "0x11",
+        "MSRValue": "0x400406",
         "Counter": "0,1,2,3",
-        "EventName": "FRONTEND_RETIRED.DSB_MISS",
+        "EventName": "FRONTEND_RETIRED.LATENCY_GE_4",
         "MSRIndex": "0x3F7",
-        "PublicDescription": "Counts retired Instructions that experienced DSB (Decode stream buffer i.e. the decoded instruction-cache) miss. \r\n",
         "TakenAlone": "1",
         "SampleAfterValue": "100007",
         "CounterHTOff": "0,1,2,3"
@@ -268,11 +267,11 @@
     {
         "EventCode": "0xC6",
         "UMask": "0x1",
-        "BriefDescription": "Retired Instructions who experienced Instruction L1 Cache true miss. Precise Event.",
+        "BriefDescription": "Retired instructions that are fetched after an interval where the front-end had at least 2 bubble-slots for a period of 2 cycles which was not interrupted by a back-end stall. Precise Event.",
         "PEBS": "1",
-        "MSRValue": "0x12",
+        "MSRValue": "0x200206",
         "Counter": "0,1,2,3",
-        "EventName": "FRONTEND_RETIRED.L1I_MISS",
+        "EventName": "FRONTEND_RETIRED.LATENCY_GE_2_BUBBLES_GE_2",
         "MSRIndex": "0x3F7",
         "TakenAlone": "1",
         "SampleAfterValue": "100007",
@@ -281,11 +280,11 @@
     {
         "EventCode": "0xC6",
         "UMask": "0x1",
-        "BriefDescription": "Retired Instructions who experienced Instruction L2 Cache true miss. Precise Event.",
+        "BriefDescription": "Retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 2 cycles which was not interrupted by a back-end stall. Precise Event.",
         "PEBS": "1",
-        "MSRValue": "0x13",
+        "MSRValue": "0x400206",
         "Counter": "0,1,2,3",
-        "EventName": "FRONTEND_RETIRED.L2_MISS",
+        "EventName": "FRONTEND_RETIRED.LATENCY_GE_2",
         "MSRIndex": "0x3F7",
         "TakenAlone": "1",
         "SampleAfterValue": "100007",
@@ -294,13 +293,13 @@
     {
         "EventCode": "0xC6",
         "UMask": "0x1",
-        "BriefDescription": "Retired Instructions who experienced iTLB true miss. Precise Event.",
+        "BriefDescription": "Retired Instructions who experienced STLB (2nd level TLB) true miss. Precise Event.",
         "PEBS": "1",
-        "MSRValue": "0x14",
+        "MSRValue": "0x15",
         "Counter": "0,1,2,3",
-        "EventName": "FRONTEND_RETIRED.ITLB_MISS",
+        "EventName": "FRONTEND_RETIRED.STLB_MISS",
         "MSRIndex": "0x3F7",
-        "PublicDescription": "Counts retired Instructions that experienced iTLB (Instruction TLB) true miss.",
+        "PublicDescription": "Counts retired Instructions that experienced STLB (2nd level TLB) true miss.",
         "TakenAlone": "1",
         "SampleAfterValue": "100007",
         "CounterHTOff": "0,1,2,3"
@@ -308,13 +307,13 @@
     {
         "EventCode": "0xC6",
         "UMask": "0x1",
-        "BriefDescription": "Retired Instructions who experienced STLB (2nd level TLB) true miss. Precise Event.",
+        "BriefDescription": "Retired Instructions who experienced iTLB true miss. Precise Event.",
         "PEBS": "1",
-        "MSRValue": "0x15",
+        "MSRValue": "0x14",
         "Counter": "0,1,2,3",
-        "EventName": "FRONTEND_RETIRED.STLB_MISS",
+        "EventName": "FRONTEND_RETIRED.ITLB_MISS",
         "MSRIndex": "0x3F7",
-        "PublicDescription": "Counts retired Instructions that experienced STLB (2nd level TLB) true miss.",
+        "PublicDescription": "Counts retired Instructions that experienced iTLB (Instruction TLB) true miss.",
         "TakenAlone": "1",
         "SampleAfterValue": "100007",
         "CounterHTOff": "0,1,2,3"
@@ -322,11 +321,11 @@
     {
         "EventCode": "0xC6",
         "UMask": "0x1",
-        "BriefDescription": "Retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 2 cycles which was not interrupted by a back-end stall. Precise Event.",
+        "BriefDescription": "Retired Instructions who experienced Instruction L2 Cache true miss. Precise Event.",
         "PEBS": "1",
-        "MSRValue": "0x400206",
+        "MSRValue": "0x13",
         "Counter": "0,1,2,3",
-        "EventName": "FRONTEND_RETIRED.LATENCY_GE_2",
+        "EventName": "FRONTEND_RETIRED.L2_MISS",
         "MSRIndex": "0x3F7",
         "TakenAlone": "1",
         "SampleAfterValue": "100007",
@@ -335,11 +334,11 @@
     {
         "EventCode": "0xC6",
         "UMask": "0x1",
-        "BriefDescription": "Retired instructions that are fetched after an interval where the front-end had at least 2 bubble-slots for a period of 2 cycles which was not interrupted by a back-end stall. Precise Event.",
+        "BriefDescription": "Retired Instructions who experienced Instruction L1 Cache true miss. Precise Event.",
         "PEBS": "1",
-        "MSRValue": "0x200206",
+        "MSRValue": "0x12",
         "Counter": "0,1,2,3",
-        "EventName": "FRONTEND_RETIRED.LATENCY_GE_2_BUBBLES_GE_2",
+        "EventName": "FRONTEND_RETIRED.L1I_MISS",
         "MSRIndex": "0x3F7",
         "TakenAlone": "1",
         "SampleAfterValue": "100007",
@@ -348,12 +347,13 @@
     {
         "EventCode": "0xC6",
         "UMask": "0x1",
-        "BriefDescription": "Retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 4 cycles which was not interrupted by a back-end stall. Precise Event.",
+        "BriefDescription": "Retired Instructions who experienced decode stream buffer (DSB - the decoded instruction-cache) miss. Precise Event.",
         "PEBS": "1",
-        "MSRValue": "0x400406",
+        "MSRValue": "0x11",
         "Counter": "0,1,2,3",
-        "EventName": "FRONTEND_RETIRED.LATENCY_GE_4",
+        "EventName": "FRONTEND_RETIRED.DSB_MISS",
         "MSRIndex": "0x3F7",
+        "PublicDescription": "Counts retired Instructions that experienced DSB (Decode stream buffer i.e. the decoded instruction-cache) miss.",
         "TakenAlone": "1",
         "SampleAfterValue": "100007",
         "CounterHTOff": "0,1,2,3"
@@ -361,13 +361,12 @@
     {
         "EventCode": "0xC6",
         "UMask": "0x1",
-        "BriefDescription": "Retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 8 cycles which was not interrupted by a back-end stall.",
+        "BriefDescription": "Retired instructions that are fetched after an interval where the front-end had at least 3 bubble-slots for a period of 2 cycles which was not interrupted by a back-end stall. Precise Event.",
         "PEBS": "1",
-        "MSRValue": "0x400806",
+        "MSRValue": "0x300206",
         "Counter": "0,1,2,3",
-        "EventName": "FRONTEND_RETIRED.LATENCY_GE_8",
+        "EventName": "FRONTEND_RETIRED.LATENCY_GE_2_BUBBLES_GE_3",
         "MSRIndex": "0x3F7",
-        "PublicDescription": "Counts retired instructions that are delivered to the back-end after a front-end stall of at least 8 cycles. During this period the front-end delivered no uops. \r\n",
         "TakenAlone": "1",
         "SampleAfterValue": "100007",
         "CounterHTOff": "0,1,2,3"
@@ -375,13 +374,13 @@
     {
         "EventCode": "0xC6",
         "UMask": "0x1",
-        "BriefDescription": "Retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 16 cycles which was not interrupted by a back-end stall. Precise Event.",
+        "BriefDescription": "Retired instructions that are fetched after an interval where the front-end had at least 1 bubble-slot for a period of 2 cycles which was not interrupted by a back-end stall. Precise Event.",
         "PEBS": "1",
-        "MSRValue": "0x401006",
+        "MSRValue": "0x100206",
         "Counter": "0,1,2,3",
-        "EventName": "FRONTEND_RETIRED.LATENCY_GE_16",
+        "EventName": "FRONTEND_RETIRED.LATENCY_GE_2_BUBBLES_GE_1",
         "MSRIndex": "0x3F7",
-        "PublicDescription": "Counts retired instructions that are delivered to the back-end after a front-end stall of at least 16 cycles. During this period the front-end delivered no uops.\r\n",
+        "PublicDescription": "Counts retired instructions that are delivered to the back-end after the front-end had at least 1 bubble-slot for a period of 2 cycles. A bubble-slot is an empty issue-pipeline slot while there was no RAT stall.",
         "TakenAlone": "1",
         "SampleAfterValue": "100007",
         "CounterHTOff": "0,1,2,3"
@@ -389,13 +388,12 @@
     {
         "EventCode": "0xC6",
         "UMask": "0x1",
-        "BriefDescription": "Retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 32 cycles which was not interrupted by a back-end stall. Precise Event.",
+        "BriefDescription": "Retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 512 cycles which was not interrupted by a back-end stall. Precise Event.",
         "PEBS": "1",
-        "MSRValue": "0x402006",
+        "MSRValue": "0x420006",
         "Counter": "0,1,2,3",
-        "EventName": "FRONTEND_RETIRED.LATENCY_GE_32",
+        "EventName": "FRONTEND_RETIRED.LATENCY_GE_512",
         "MSRIndex": "0x3F7",
-        "PublicDescription": "Counts retired instructions that are delivered to the back-end  after a front-end stall of at least 32 cycles. During this period the front-end delivered no uops.\r\n",
         "TakenAlone": "1",
         "SampleAfterValue": "100007",
         "CounterHTOff": "0,1,2,3"
@@ -403,11 +401,11 @@
     {
         "EventCode": "0xC6",
         "UMask": "0x1",
-        "BriefDescription": "Retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 64 cycles which was not interrupted by a back-end stall. Precise Event.",
+        "BriefDescription": "Retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 256 cycles which was not interrupted by a back-end stall. Precise Event.",
         "PEBS": "1",
-        "MSRValue": "0x404006",
+        "MSRValue": "0x410006",
         "Counter": "0,1,2,3",
-        "EventName": "FRONTEND_RETIRED.LATENCY_GE_64",
+        "EventName": "FRONTEND_RETIRED.LATENCY_GE_256",
         "MSRIndex": "0x3F7",
         "TakenAlone": "1",
         "SampleAfterValue": "100007",
@@ -429,11 +427,11 @@
     {
         "EventCode": "0xC6",
         "UMask": "0x1",
-        "BriefDescription": "Retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 256 cycles which was not interrupted by a back-end stall. Precise Event.",
+        "BriefDescription": "Retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 64 cycles which was not interrupted by a back-end stall. Precise Event.",
         "PEBS": "1",
-        "MSRValue": "0x410006",
+        "MSRValue": "0x404006",
         "Counter": "0,1,2,3",
-        "EventName": "FRONTEND_RETIRED.LATENCY_GE_256",
+        "EventName": "FRONTEND_RETIRED.LATENCY_GE_64",
         "MSRIndex": "0x3F7",
         "TakenAlone": "1",
         "SampleAfterValue": "100007",
@@ -442,12 +440,13 @@
     {
         "EventCode": "0xC6",
         "UMask": "0x1",
-        "BriefDescription": "Retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 512 cycles which was not interrupted by a back-end stall. Precise Event.",
+        "BriefDescription": "Retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 32 cycles which was not interrupted by a back-end stall. Precise Event.",
         "PEBS": "1",
-        "MSRValue": "0x420006",
+        "MSRValue": "0x402006",
         "Counter": "0,1,2,3",
-        "EventName": "FRONTEND_RETIRED.LATENCY_GE_512",
+        "EventName": "FRONTEND_RETIRED.LATENCY_GE_32",
         "MSRIndex": "0x3F7",
+        "PublicDescription": "Counts retired instructions that are delivered to the back-end  after a front-end stall of at least 32 cycles. During this period the front-end delivered no uops.",
         "TakenAlone": "1",
         "SampleAfterValue": "100007",
         "CounterHTOff": "0,1,2,3"
@@ -455,13 +454,13 @@
     {
         "EventCode": "0xC6",
         "UMask": "0x1",
-        "BriefDescription": "Retired instructions that are fetched after an interval where the front-end had at least 1 bubble-slot for a period of 2 cycles which was not interrupted by a back-end stall. Precise Event.",
+        "BriefDescription": "Retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 16 cycles which was not interrupted by a back-end stall. Precise Event.",
         "PEBS": "1",
-        "MSRValue": "0x100206",
+        "MSRValue": "0x401006",
         "Counter": "0,1,2,3",
-        "EventName": "FRONTEND_RETIRED.LATENCY_GE_2_BUBBLES_GE_1",
+        "EventName": "FRONTEND_RETIRED.LATENCY_GE_16",
         "MSRIndex": "0x3F7",
-        "PublicDescription": "Counts retired instructions that are delivered to the back-end after the front-end had at least 1 bubble-slot for a period of 2 cycles. A bubble-slot is an empty issue-pipeline slot while there was no RAT stall.\r\n",
+        "PublicDescription": "Counts retired instructions that are delivered to the back-end after a front-end stall of at least 16 cycles. During this period the front-end delivered no uops.",
         "TakenAlone": "1",
         "SampleAfterValue": "100007",
         "CounterHTOff": "0,1,2,3"
@@ -469,12 +468,13 @@
     {
         "EventCode": "0xC6",
         "UMask": "0x1",
-        "BriefDescription": "Retired instructions that are fetched after an interval where the front-end had at least 3 bubble-slots for a period of 2 cycles which was not interrupted by a back-end stall. Precise Event.",
+        "BriefDescription": "Retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 8 cycles which was not interrupted by a back-end stall.",
         "PEBS": "1",
-        "MSRValue": "0x300206",
+        "MSRValue": "0x400806",
         "Counter": "0,1,2,3",
-        "EventName": "FRONTEND_RETIRED.LATENCY_GE_2_BUBBLES_GE_3",
+        "EventName": "FRONTEND_RETIRED.LATENCY_GE_8",
         "MSRIndex": "0x3F7",
+        "PublicDescription": "Counts retired instructions that are delivered to the back-end after a front-end stall of at least 8 cycles. During this period the front-end delivered no uops.",
         "TakenAlone": "1",
         "SampleAfterValue": "100007",
         "CounterHTOff": "0,1,2,3"
diff --git a/tools/perf/pmu-events/arch/x86/skylakex/memory.json b/tools/perf/pmu-events/arch/x86/skylakex/memory.json
index e7f1aa31226d..48a9cdf81307 100644
--- a/tools/perf/pmu-events/arch/x86/skylakex/memory.json
+++ b/tools/perf/pmu-events/arch/x86/skylakex/memory.json
@@ -129,20 +129,20 @@
     {
         "EventCode": "0x60",
         "UMask": "0x10",
-        "BriefDescription": "Cycles with at least 1 Demand Data Read requests who miss L3 cache in the superQ.",
+        "BriefDescription": "Cycles with at least 6 Demand Data Read requests that miss L3 cache in the superQ.",
         "Counter": "0,1,2,3",
-        "EventName": "OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_L3_MISS_DEMAND_DATA_RD",
-        "CounterMask": "1",
+        "EventName": "OFFCORE_REQUESTS_OUTSTANDING.L3_MISS_DEMAND_DATA_RD_GE_6",
+        "CounterMask": "6",
         "SampleAfterValue": "2000003",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
         "EventCode": "0x60",
         "UMask": "0x10",
-        "BriefDescription": "Cycles with at least 6 Demand Data Read requests that miss L3 cache in the superQ.",
+        "BriefDescription": "Cycles with at least 1 Demand Data Read requests who miss L3 cache in the superQ.",
         "Counter": "0,1,2,3",
-        "EventName": "OFFCORE_REQUESTS_OUTSTANDING.L3_MISS_DEMAND_DATA_RD_GE_6",
-        "CounterMask": "6",
+        "EventName": "OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_L3_MISS_DEMAND_DATA_RD",
+        "CounterMask": "1",
         "SampleAfterValue": "2000003",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
@@ -210,7 +210,7 @@
     {
         "EventCode": "0xC8",
         "UMask": "0x4",
-        "BriefDescription": "Number of times an HLE execution aborted due to any reasons (multiple categories may count as one). ",
+        "BriefDescription": "Number of times an HLE execution aborted due to any reasons (multiple categories may count as one).",
         "PEBS": "1",
         "Counter": "0,1,2,3",
         "EventName": "HLE_RETIRED.ABORTED",
@@ -242,6 +242,7 @@
         "BriefDescription": "Number of times an HLE execution aborted due to HLE-unfriendly instructions and certain unfriendly events (such as AD assists etc.).",
         "Counter": "0,1,2,3",
         "EventName": "HLE_RETIRED.ABORTED_UNFRIENDLY",
+        "PublicDescription": "Number of times an HLE execution aborted due to HLE-unfriendly instructions and certain unfriendly events (such as AD assists etc.).",
         "SampleAfterValue": "2000003",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
@@ -287,7 +288,7 @@
     {
         "EventCode": "0xC9",
         "UMask": "0x4",
-        "BriefDescription": "Number of times an RTM execution aborted due to any reasons (multiple categories may count as one). ",
+        "BriefDescription": "Number of times an RTM execution aborted due to any reasons (multiple categories may count as one).",
         "PEBS": "1",
         "Counter": "0,1,2,3",
         "EventName": "RTM_RETIRED.ABORTED",
@@ -347,125 +348,125 @@
     {
         "EventCode": "0xCD",
         "UMask": "0x1",
-        "BriefDescription": "Counts loads when the latency from first dispatch to completion is greater than 4 cycles.",
+        "BriefDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 512 cycles.",
         "PEBS": "2",
-        "MSRValue": "0x4",
+        "MSRValue": "0x200",
         "Counter": "0,1,2,3",
-        "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_4",
+        "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_512",
         "MSRIndex": "0x3F6",
-        "PublicDescription": "Counts loads when the latency from first dispatch to completion is greater than 4 cycles.  Reported latency may be longer than just the memory latency.",
+        "PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 512 cycles.  Reported latency may be longer than just the memory latency.",
         "TakenAlone": "1",
-        "SampleAfterValue": "100003",
+        "SampleAfterValue": "101",
         "CounterHTOff": "0,1,2,3"
     },
     {
         "EventCode": "0xCD",
         "UMask": "0x1",
-        "BriefDescription": "Counts loads when the latency from first dispatch to completion is greater than 8 cycles.",
+        "BriefDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 256 cycles.",
         "PEBS": "2",
-        "MSRValue": "0x8",
+        "MSRValue": "0x100",
         "Counter": "0,1,2,3",
-        "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_8",
+        "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_256",
         "MSRIndex": "0x3F6",
-        "PublicDescription": "Counts loads when the latency from first dispatch to completion is greater than 8 cycles.  Reported latency may be longer than just the memory latency.",
+        "PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 256 cycles.  Reported latency may be longer than just the memory latency.",
         "TakenAlone": "1",
-        "SampleAfterValue": "50021",
+        "SampleAfterValue": "503",
         "CounterHTOff": "0,1,2,3"
     },
     {
         "EventCode": "0xCD",
         "UMask": "0x1",
-        "BriefDescription": "Counts loads when the latency from first dispatch to completion is greater than 16 cycles.",
+        "BriefDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 128 cycles.",
         "PEBS": "2",
-        "MSRValue": "0x10",
+        "MSRValue": "0x80",
         "Counter": "0,1,2,3",
-        "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_16",
+        "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_128",
         "MSRIndex": "0x3F6",
-        "PublicDescription": "Counts loads when the latency from first dispatch to completion is greater than 16 cycles.  Reported latency may be longer than just the memory latency.",
+        "PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 128 cycles.  Reported latency may be longer than just the memory latency.",
         "TakenAlone": "1",
-        "SampleAfterValue": "20011",
+        "SampleAfterValue": "1009",
         "CounterHTOff": "0,1,2,3"
     },
     {
         "EventCode": "0xCD",
         "UMask": "0x1",
-        "BriefDescription": "Counts loads when the latency from first dispatch to completion is greater than 32 cycles.",
+        "BriefDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 64 cycles.",
         "PEBS": "2",
-        "MSRValue": "0x20",
+        "MSRValue": "0x40",
         "Counter": "0,1,2,3",
-        "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_32",
+        "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_64",
         "MSRIndex": "0x3F6",
-        "PublicDescription": "Counts loads when the latency from first dispatch to completion is greater than 32 cycles.  Reported latency may be longer than just the memory latency.",
+        "PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 64 cycles.  Reported latency may be longer than just the memory latency.",
         "TakenAlone": "1",
-        "SampleAfterValue": "100007",
+        "SampleAfterValue": "2003",
         "CounterHTOff": "0,1,2,3"
     },
     {
         "EventCode": "0xCD",
         "UMask": "0x1",
-        "BriefDescription": "Counts loads when the latency from first dispatch to completion is greater than 64 cycles.",
+        "BriefDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 32 cycles.",
         "PEBS": "2",
-        "MSRValue": "0x40",
+        "MSRValue": "0x20",
         "Counter": "0,1,2,3",
-        "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_64",
+        "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_32",
         "MSRIndex": "0x3F6",
-        "PublicDescription": "Counts loads when the latency from first dispatch to completion is greater than 64 cycles.  Reported latency may be longer than just the memory latency.",
+        "PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 32 cycles.  Reported latency may be longer than just the memory latency.",
         "TakenAlone": "1",
-        "SampleAfterValue": "2003",
+        "SampleAfterValue": "100007",
         "CounterHTOff": "0,1,2,3"
     },
     {
         "EventCode": "0xCD",
         "UMask": "0x1",
-        "BriefDescription": "Counts loads when the latency from first dispatch to completion is greater than 128 cycles.",
+        "BriefDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 16 cycles.",
         "PEBS": "2",
-        "MSRValue": "0x80",
+        "MSRValue": "0x10",
         "Counter": "0,1,2,3",
-        "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_128",
+        "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_16",
         "MSRIndex": "0x3F6",
-        "PublicDescription": "Counts loads when the latency from first dispatch to completion is greater than 128 cycles.  Reported latency may be longer than just the memory latency.",
+        "PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 16 cycles.  Reported latency may be longer than just the memory latency.",
         "TakenAlone": "1",
-        "SampleAfterValue": "1009",
+        "SampleAfterValue": "20011",
         "CounterHTOff": "0,1,2,3"
     },
     {
         "EventCode": "0xCD",
         "UMask": "0x1",
-        "BriefDescription": "Counts loads when the latency from first dispatch to completion is greater than 256 cycles.",
+        "BriefDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 8 cycles.",
         "PEBS": "2",
-        "MSRValue": "0x100",
+        "MSRValue": "0x8",
         "Counter": "0,1,2,3",
-        "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_256",
+        "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_8",
         "MSRIndex": "0x3F6",
-        "PublicDescription": "Counts loads when the latency from first dispatch to completion is greater than 256 cycles.  Reported latency may be longer than just the memory latency.",
+        "PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 8 cycles.  Reported latency may be longer than just the memory latency.",
         "TakenAlone": "1",
-        "SampleAfterValue": "503",
+        "SampleAfterValue": "50021",
         "CounterHTOff": "0,1,2,3"
     },
     {
         "EventCode": "0xCD",
         "UMask": "0x1",
-        "BriefDescription": "Counts loads when the latency from first dispatch to completion is greater than 512 cycles.",
+        "BriefDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 4 cycles.",
         "PEBS": "2",
-        "MSRValue": "0x200",
+        "MSRValue": "0x4",
         "Counter": "0,1,2,3",
-        "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_512",
+        "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_4",
         "MSRIndex": "0x3F6",
-        "PublicDescription": "Counts loads when the latency from first dispatch to completion is greater than 512 cycles.  Reported latency may be longer than just the memory latency.",
+        "PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 4 cycles.  Reported latency may be longer than just the memory latency.",
         "TakenAlone": "1",
-        "SampleAfterValue": "101",
+        "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
     {
         "Offcore": "1",
         "EventCode": "0xB7, 0xBB",
         "UMask": "0x1",
-        "BriefDescription": "Counts demand data reads that miss in the L3.",
-        "MSRValue": "0x3fbc000001 ",
+        "BriefDescription": "Counts demand data reads TBD TBD",
+        "MSRValue": "0x3FBC000001",
         "Counter": "0,1,2,3",
         "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_MISS.ANY_SNOOP",
-        "MSRIndex": "0x1a6,0x1a7",
-        "PublicDescription": "Counts demand data reads that miss in the L3. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "PublicDescription": "Counts demand data reads TBD TBD",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -473,12 +474,12 @@
         "Offcore": "1",
         "EventCode": "0xB7, 0xBB",
         "UMask": "0x1",
-        "BriefDescription": "Counts demand data reads that miss the L3 and clean or shared data is transferred from remote cache.",
-        "MSRValue": "0x083fc00001 ",
+        "BriefDescription": "Counts demand data reads TBD",
+        "MSRValue": "0x083FC00001",
         "Counter": "0,1,2,3",
         "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_MISS.REMOTE_HIT_FORWARD",
-        "MSRIndex": "0x1a6,0x1a7",
-        "PublicDescription": "Counts demand data reads that miss the L3 and clean or shared data is transferred from remote cache. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "PublicDescription": "Counts demand data reads TBD",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -486,12 +487,12 @@
         "Offcore": "1",
         "EventCode": "0xB7, 0xBB",
         "UMask": "0x1",
-        "BriefDescription": "Counts demand data reads that miss the L3 and the modified data is transferred from remote cache.",
-        "MSRValue": "0x103fc00001 ",
+        "BriefDescription": "Counts demand data reads TBD",
+        "MSRValue": "0x103FC00001",
         "Counter": "0,1,2,3",
         "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_MISS.REMOTE_HITM",
-        "MSRIndex": "0x1a6,0x1a7",
-        "PublicDescription": "Counts demand data reads that miss the L3 and the modified data is transferred from remote cache. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "PublicDescription": "Counts demand data reads TBD",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -499,12 +500,12 @@
         "Offcore": "1",
         "EventCode": "0xB7, 0xBB",
         "UMask": "0x1",
-        "BriefDescription": "Counts demand data reads that miss the L3 and the data is returned from local or remote dram.",
-        "MSRValue": "0x063fc00001 ",
+        "BriefDescription": "Counts demand data reads TBD",
+        "MSRValue": "0x063FC00001",
         "Counter": "0,1,2,3",
         "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_MISS.SNOOP_MISS_OR_NO_FWD",
-        "MSRIndex": "0x1a6,0x1a7",
-        "PublicDescription": "Counts demand data reads that miss the L3 and the data is returned from local or remote dram. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "PublicDescription": "Counts demand data reads TBD",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -512,12 +513,12 @@
         "Offcore": "1",
         "EventCode": "0xB7, 0xBB",
         "UMask": "0x1",
-        "BriefDescription": "Counts demand data reads that miss the L3 and the data is returned from remote dram.",
-        "MSRValue": "0x063b800001 ",
+        "BriefDescription": "Counts demand data reads TBD",
+        "MSRValue": "0x063B800001",
         "Counter": "0,1,2,3",
         "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_MISS_REMOTE_DRAM.SNOOP_MISS_OR_NO_FWD",
-        "MSRIndex": "0x1a6,0x1a7",
-        "PublicDescription": "Counts demand data reads that miss the L3 and the data is returned from remote dram. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "PublicDescription": "Counts demand data reads TBD",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -525,12 +526,12 @@
         "Offcore": "1",
         "EventCode": "0xB7, 0xBB",
         "UMask": "0x1",
-        "BriefDescription": "Counts demand data reads that miss the L3 and the data is returned from local dram.",
-        "MSRValue": "0x0604000001 ",
+        "BriefDescription": "Counts demand data reads TBD",
+        "MSRValue": "0x0604000001",
         "Counter": "0,1,2,3",
         "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_MISS_LOCAL_DRAM.SNOOP_MISS_OR_NO_FWD",
-        "MSRIndex": "0x1a6,0x1a7",
-        "PublicDescription": "Counts demand data reads that miss the L3 and the data is returned from local dram. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "PublicDescription": "Counts demand data reads TBD",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -538,12 +539,12 @@
         "Offcore": "1",
         "EventCode": "0xB7, 0xBB",
         "UMask": "0x1",
-        "BriefDescription": "Counts all demand data writes (RFOs) that miss in the L3.",
-        "MSRValue": "0x3fbc000002 ",
+        "BriefDescription": "Counts all demand data writes (RFOs) TBD TBD",
+        "MSRValue": "0x3FBC000002",
         "Counter": "0,1,2,3",
         "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_MISS.ANY_SNOOP",
-        "MSRIndex": "0x1a6,0x1a7",
-        "PublicDescription": "Counts all demand data writes (RFOs) that miss in the L3. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "PublicDescription": "Counts all demand data writes (RFOs) TBD TBD",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -551,12 +552,12 @@
         "Offcore": "1",
         "EventCode": "0xB7, 0xBB",
         "UMask": "0x1",
-        "BriefDescription": "Counts all demand data writes (RFOs) that miss the L3 and clean or shared data is transferred from remote cache.",
-        "MSRValue": "0x083fc00002 ",
+        "BriefDescription": "Counts all demand data writes (RFOs) TBD",
+        "MSRValue": "0x083FC00002",
         "Counter": "0,1,2,3",
         "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_MISS.REMOTE_HIT_FORWARD",
-        "MSRIndex": "0x1a6,0x1a7",
-        "PublicDescription": "Counts all demand data writes (RFOs) that miss the L3 and clean or shared data is transferred from remote cache. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "PublicDescription": "Counts all demand data writes (RFOs) TBD",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -564,12 +565,12 @@
         "Offcore": "1",
         "EventCode": "0xB7, 0xBB",
         "UMask": "0x1",
-        "BriefDescription": "Counts all demand data writes (RFOs) that miss the L3 and the modified data is transferred from remote cache.",
-        "MSRValue": "0x103fc00002 ",
+        "BriefDescription": "Counts all demand data writes (RFOs) TBD",
+        "MSRValue": "0x103FC00002",
         "Counter": "0,1,2,3",
         "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_MISS.REMOTE_HITM",
-        "MSRIndex": "0x1a6,0x1a7",
-        "PublicDescription": "Counts all demand data writes (RFOs) that miss the L3 and the modified data is transferred from remote cache. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "PublicDescription": "Counts all demand data writes (RFOs) TBD",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -577,12 +578,12 @@
         "Offcore": "1",
         "EventCode": "0xB7, 0xBB",
         "UMask": "0x1",
-        "BriefDescription": "Counts all demand data writes (RFOs) that miss the L3 and the data is returned from local or remote dram.",
-        "MSRValue": "0x063fc00002 ",
+        "BriefDescription": "Counts all demand data writes (RFOs) TBD",
+        "MSRValue": "0x063FC00002",
         "Counter": "0,1,2,3",
         "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_MISS.SNOOP_MISS_OR_NO_FWD",
-        "MSRIndex": "0x1a6,0x1a7",
-        "PublicDescription": "Counts all demand data writes (RFOs) that miss the L3 and the data is returned from local or remote dram. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "PublicDescription": "Counts all demand data writes (RFOs) TBD",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -590,12 +591,12 @@
         "Offcore": "1",
         "EventCode": "0xB7, 0xBB",
         "UMask": "0x1",
-        "BriefDescription": "Counts all demand data writes (RFOs) that miss the L3 and the data is returned from remote dram.",
-        "MSRValue": "0x063b800002 ",
+        "BriefDescription": "Counts all demand data writes (RFOs) TBD",
+        "MSRValue": "0x063B800002",
         "Counter": "0,1,2,3",
         "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_MISS_REMOTE_DRAM.SNOOP_MISS_OR_NO_FWD",
-        "MSRIndex": "0x1a6,0x1a7",
-        "PublicDescription": "Counts all demand data writes (RFOs) that miss the L3 and the data is returned from remote dram. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "PublicDescription": "Counts all demand data writes (RFOs) TBD",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -603,12 +604,12 @@
         "Offcore": "1",
         "EventCode": "0xB7, 0xBB",
         "UMask": "0x1",
-        "BriefDescription": "Counts all demand data writes (RFOs) that miss the L3 and the data is returned from local dram.",
-        "MSRValue": "0x0604000002 ",
+        "BriefDescription": "Counts all demand data writes (RFOs) TBD",
+        "MSRValue": "0x0604000002",
         "Counter": "0,1,2,3",
         "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_MISS_LOCAL_DRAM.SNOOP_MISS_OR_NO_FWD",
-        "MSRIndex": "0x1a6,0x1a7",
-        "PublicDescription": "Counts all demand data writes (RFOs) that miss the L3 and the data is returned from local dram. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "PublicDescription": "Counts all demand data writes (RFOs) TBD",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -616,12 +617,12 @@
         "Offcore": "1",
         "EventCode": "0xB7, 0xBB",
         "UMask": "0x1",
-        "BriefDescription": "Counts all demand code reads that miss in the L3.",
-        "MSRValue": "0x3fbc000004 ",
+        "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that TBD TBD",
+        "MSRValue": "0x3FBC000004",
         "Counter": "0,1,2,3",
         "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_MISS.ANY_SNOOP",
-        "MSRIndex": "0x1a6,0x1a7",
-        "PublicDescription": "Counts all demand code reads that miss in the L3. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that TBD TBD",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -629,12 +630,12 @@
         "Offcore": "1",
         "EventCode": "0xB7, 0xBB",
         "UMask": "0x1",
-        "BriefDescription": "Counts all demand code reads that miss the L3 and clean or shared data is transferred from remote cache.",
-        "MSRValue": "0x083fc00004 ",
+        "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that TBD",
+        "MSRValue": "0x083FC00004",
         "Counter": "0,1,2,3",
         "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_MISS.REMOTE_HIT_FORWARD",
-        "MSRIndex": "0x1a6,0x1a7",
-        "PublicDescription": "Counts all demand code reads that miss the L3 and clean or shared data is transferred from remote cache. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that TBD",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -642,12 +643,12 @@
         "Offcore": "1",
         "EventCode": "0xB7, 0xBB",
         "UMask": "0x1",
-        "BriefDescription": "Counts all demand code reads that miss the L3 and the modified data is transferred from remote cache.",
-        "MSRValue": "0x103fc00004 ",
+        "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that TBD",
+        "MSRValue": "0x103FC00004",
         "Counter": "0,1,2,3",
         "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_MISS.REMOTE_HITM",
-        "MSRIndex": "0x1a6,0x1a7",
-        "PublicDescription": "Counts all demand code reads that miss the L3 and the modified data is transferred from remote cache. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that TBD",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -655,12 +656,12 @@
         "Offcore": "1",
         "EventCode": "0xB7, 0xBB",
         "UMask": "0x1",
-        "BriefDescription": "Counts all demand code reads that miss the L3 and the data is returned from local or remote dram.",
-        "MSRValue": "0x063fc00004 ",
+        "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that TBD",
+        "MSRValue": "0x063FC00004",
         "Counter": "0,1,2,3",
         "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_MISS.SNOOP_MISS_OR_NO_FWD",
-        "MSRIndex": "0x1a6,0x1a7",
-        "PublicDescription": "Counts all demand code reads that miss the L3 and the data is returned from local or remote dram. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that TBD",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -668,12 +669,12 @@
         "Offcore": "1",
         "EventCode": "0xB7, 0xBB",
         "UMask": "0x1",
-        "BriefDescription": "Counts all demand code reads that miss the L3 and the data is returned from remote dram.",
-        "MSRValue": "0x063b800004 ",
+        "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that TBD",
+        "MSRValue": "0x063B800004",
         "Counter": "0,1,2,3",
         "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_MISS_REMOTE_DRAM.SNOOP_MISS_OR_NO_FWD",
-        "MSRIndex": "0x1a6,0x1a7",
-        "PublicDescription": "Counts all demand code reads that miss the L3 and the data is returned from remote dram. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that TBD",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -681,12 +682,12 @@
         "Offcore": "1",
         "EventCode": "0xB7, 0xBB",
         "UMask": "0x1",
-        "BriefDescription": "Counts all demand code reads that miss the L3 and the data is returned from local dram.",
-        "MSRValue": "0x0604000004 ",
+        "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that TBD",
+        "MSRValue": "0x0604000004",
         "Counter": "0,1,2,3",
         "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_MISS_LOCAL_DRAM.SNOOP_MISS_OR_NO_FWD",
-        "MSRIndex": "0x1a6,0x1a7",
-        "PublicDescription": "Counts all demand code reads that miss the L3 and the data is returned from local dram. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "PublicDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that TBD",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -694,12 +695,12 @@
         "Offcore": "1",
         "EventCode": "0xB7, 0xBB",
         "UMask": "0x1",
-        "BriefDescription": "Counts prefetch (that bring data to L2) data reads that miss in the L3.",
-        "MSRValue": "0x3fbc000010 ",
+        "BriefDescription": "Counts prefetch (that bring data to L2) data reads TBD TBD",
+        "MSRValue": "0x3FBC000010",
         "Counter": "0,1,2,3",
         "EventName": "OFFCORE_RESPONSE.PF_L2_DATA_RD.L3_MISS.ANY_SNOOP",
-        "MSRIndex": "0x1a6,0x1a7",
-        "PublicDescription": "Counts prefetch (that bring data to L2) data reads that miss in the L3. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "PublicDescription": "Counts prefetch (that bring data to L2) data reads TBD TBD",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -707,12 +708,12 @@
         "Offcore": "1",
         "EventCode": "0xB7, 0xBB",
         "UMask": "0x1",
-        "BriefDescription": "Counts prefetch (that bring data to L2) data reads that miss the L3 and clean or shared data is transferred from remote cache.",
-        "MSRValue": "0x083fc00010 ",
+        "BriefDescription": "Counts prefetch (that bring data to L2) data reads TBD",
+        "MSRValue": "0x083FC00010",
         "Counter": "0,1,2,3",
         "EventName": "OFFCORE_RESPONSE.PF_L2_DATA_RD.L3_MISS.REMOTE_HIT_FORWARD",
-        "MSRIndex": "0x1a6,0x1a7",
-        "PublicDescription": "Counts prefetch (that bring data to L2) data reads that miss the L3 and clean or shared data is transferred from remote cache. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "PublicDescription": "Counts prefetch (that bring data to L2) data reads TBD",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -720,12 +721,12 @@
         "Offcore": "1",
         "EventCode": "0xB7, 0xBB",
         "UMask": "0x1",
-        "BriefDescription": "Counts prefetch (that bring data to L2) data reads that miss the L3 and the modified data is transferred from remote cache.",
-        "MSRValue": "0x103fc00010 ",
+        "BriefDescription": "Counts prefetch (that bring data to L2) data reads TBD",
+        "MSRValue": "0x103FC00010",
         "Counter": "0,1,2,3",
         "EventName": "OFFCORE_RESPONSE.PF_L2_DATA_RD.L3_MISS.REMOTE_HITM",
-        "MSRIndex": "0x1a6,0x1a7",
-        "PublicDescription": "Counts prefetch (that bring data to L2) data reads that miss the L3 and the modified data is transferred from remote cache. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "PublicDescription": "Counts prefetch (that bring data to L2) data reads TBD",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -733,12 +734,12 @@
         "Offcore": "1",
         "EventCode": "0xB7, 0xBB",
         "UMask": "0x1",
-        "BriefDescription": "Counts prefetch (that bring data to L2) data reads that miss the L3 and the data is returned from local or remote dram.",
-        "MSRValue": "0x063fc00010 ",
+        "BriefDescription": "Counts prefetch (that bring data to L2) data reads TBD",
+        "MSRValue": "0x063FC00010",
         "Counter": "0,1,2,3",
         "EventName": "OFFCORE_RESPONSE.PF_L2_DATA_RD.L3_MISS.SNOOP_MISS_OR_NO_FWD",
-        "MSRIndex": "0x1a6,0x1a7",
-        "PublicDescription": "Counts prefetch (that bring data to L2) data reads that miss the L3 and the data is returned from local or remote dram. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "PublicDescription": "Counts prefetch (that bring data to L2) data reads TBD",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -746,12 +747,12 @@
         "Offcore": "1",
         "EventCode": "0xB7, 0xBB",
         "UMask": "0x1",
-        "BriefDescription": "Counts prefetch (that bring data to L2) data reads that miss the L3 and the data is returned from remote dram.",
-        "MSRValue": "0x063b800010 ",
+        "BriefDescription": "Counts prefetch (that bring data to L2) data reads TBD",
+        "MSRValue": "0x063B800010",
         "Counter": "0,1,2,3",
         "EventName": "OFFCORE_RESPONSE.PF_L2_DATA_RD.L3_MISS_REMOTE_DRAM.SNOOP_MISS_OR_NO_FWD",
-        "MSRIndex": "0x1a6,0x1a7",
-        "PublicDescription": "Counts prefetch (that bring data to L2) data reads that miss the L3 and the data is returned from remote dram. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "PublicDescription": "Counts prefetch (that bring data to L2) data reads TBD",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -759,12 +760,12 @@
         "Offcore": "1",
         "EventCode": "0xB7, 0xBB",
         "UMask": "0x1",
-        "BriefDescription": "Counts prefetch (that bring data to L2) data reads that miss the L3 and the data is returned from local dram.",
-        "MSRValue": "0x0604000010 ",
+        "BriefDescription": "Counts prefetch (that bring data to L2) data reads TBD",
+        "MSRValue": "0x0604000010",
         "Counter": "0,1,2,3",
         "EventName": "OFFCORE_RESPONSE.PF_L2_DATA_RD.L3_MISS_LOCAL_DRAM.SNOOP_MISS_OR_NO_FWD",
-        "MSRIndex": "0x1a6,0x1a7",
-        "PublicDescription": "Counts prefetch (that bring data to L2) data reads that miss the L3 and the data is returned from local dram. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "PublicDescription": "Counts prefetch (that bring data to L2) data reads TBD",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -772,12 +773,12 @@
         "Offcore": "1",
         "EventCode": "0xB7, 0xBB",
         "UMask": "0x1",
-        "BriefDescription": "Counts all prefetch (that bring data to L2) RFOs that miss in the L3.",
-        "MSRValue": "0x3fbc000020 ",
+        "BriefDescription": "Counts all prefetch (that bring data to L2) RFOs TBD TBD",
+        "MSRValue": "0x3FBC000020",
         "Counter": "0,1,2,3",
         "EventName": "OFFCORE_RESPONSE.PF_L2_RFO.L3_MISS.ANY_SNOOP",
-        "MSRIndex": "0x1a6,0x1a7",
-        "PublicDescription": "Counts all prefetch (that bring data to L2) RFOs that miss in the L3. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "PublicDescription": "Counts all prefetch (that bring data to L2) RFOs TBD TBD",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -785,12 +786,12 @@
         "Offcore": "1",
         "EventCode": "0xB7, 0xBB",
         "UMask": "0x1",
-        "BriefDescription": "Counts all prefetch (that bring data to L2) RFOs that miss the L3 and clean or shared data is transferred from remote cache.",
-        "MSRValue": "0x083fc00020 ",
+        "BriefDescription": "Counts all prefetch (that bring data to L2) RFOs TBD",
+        "MSRValue": "0x083FC00020",
         "Counter": "0,1,2,3",
         "EventName": "OFFCORE_RESPONSE.PF_L2_RFO.L3_MISS.REMOTE_HIT_FORWARD",
-        "MSRIndex": "0x1a6,0x1a7",
-        "PublicDescription": "Counts all prefetch (that bring data to L2) RFOs that miss the L3 and clean or shared data is transferred from remote cache. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "PublicDescription": "Counts all prefetch (that bring data to L2) RFOs TBD",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -798,12 +799,12 @@
         "Offcore": "1",
         "EventCode": "0xB7, 0xBB",
         "UMask": "0x1",
-        "BriefDescription": "Counts all prefetch (that bring data to L2) RFOs that miss the L3 and the modified data is transferred from remote cache.",
-        "MSRValue": "0x103fc00020 ",
+        "BriefDescription": "Counts all prefetch (that bring data to L2) RFOs TBD",
+        "MSRValue": "0x103FC00020",
         "Counter": "0,1,2,3",
         "EventName": "OFFCORE_RESPONSE.PF_L2_RFO.L3_MISS.REMOTE_HITM",
-        "MSRIndex": "0x1a6,0x1a7",
-        "PublicDescription": "Counts all prefetch (that bring data to L2) RFOs that miss the L3 and the modified data is transferred from remote cache. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "PublicDescription": "Counts all prefetch (that bring data to L2) RFOs TBD",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -811,12 +812,12 @@
         "Offcore": "1",
         "EventCode": "0xB7, 0xBB",
         "UMask": "0x1",
-        "BriefDescription": "Counts all prefetch (that bring data to L2) RFOs that miss the L3 and the data is returned from local or remote dram.",
-        "MSRValue": "0x063fc00020 ",
+        "BriefDescription": "Counts all prefetch (that bring data to L2) RFOs TBD",
+        "MSRValue": "0x063FC00020",
         "Counter": "0,1,2,3",
         "EventName": "OFFCORE_RESPONSE.PF_L2_RFO.L3_MISS.SNOOP_MISS_OR_NO_FWD",
-        "MSRIndex": "0x1a6,0x1a7",
-        "PublicDescription": "Counts all prefetch (that bring data to L2) RFOs that miss the L3 and the data is returned from local or remote dram. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "PublicDescription": "Counts all prefetch (that bring data to L2) RFOs TBD",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -824,12 +825,12 @@
         "Offcore": "1",
         "EventCode": "0xB7, 0xBB",
         "UMask": "0x1",
-        "BriefDescription": "Counts all prefetch (that bring data to L2) RFOs that miss the L3 and the data is returned from remote dram.",
-        "MSRValue": "0x063b800020 ",
+        "BriefDescription": "Counts all prefetch (that bring data to L2) RFOs TBD",
+        "MSRValue": "0x063B800020",
         "Counter": "0,1,2,3",
         "EventName": "OFFCORE_RESPONSE.PF_L2_RFO.L3_MISS_REMOTE_DRAM.SNOOP_MISS_OR_NO_FWD",
-        "MSRIndex": "0x1a6,0x1a7",
-        "PublicDescription": "Counts all prefetch (that bring data to L2) RFOs that miss the L3 and the data is returned from remote dram. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "PublicDescription": "Counts all prefetch (that bring data to L2) RFOs TBD",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -837,12 +838,12 @@
         "Offcore": "1",
         "EventCode": "0xB7, 0xBB",
         "UMask": "0x1",
-        "BriefDescription": "Counts all prefetch (that bring data to L2) RFOs that miss the L3 and the data is returned from local dram.",
-        "MSRValue": "0x0604000020 ",
+        "BriefDescription": "Counts all prefetch (that bring data to L2) RFOs TBD",
+        "MSRValue": "0x0604000020",
         "Counter": "0,1,2,3",
         "EventName": "OFFCORE_RESPONSE.PF_L2_RFO.L3_MISS_LOCAL_DRAM.SNOOP_MISS_OR_NO_FWD",
-        "MSRIndex": "0x1a6,0x1a7",
-        "PublicDescription": "Counts all prefetch (that bring data to L2) RFOs that miss the L3 and the data is returned from local dram. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "PublicDescription": "Counts all prefetch (that bring data to L2) RFOs TBD",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -850,12 +851,12 @@
         "Offcore": "1",
         "EventCode": "0xB7, 0xBB",
         "UMask": "0x1",
-        "BriefDescription": "Counts all prefetch (that bring data to LLC only) data reads that miss in the L3.",
-        "MSRValue": "0x3fbc000080 ",
+        "BriefDescription": "Counts all prefetch (that bring data to LLC only) data reads TBD TBD",
+        "MSRValue": "0x3FBC000080",
         "Counter": "0,1,2,3",
         "EventName": "OFFCORE_RESPONSE.PF_L3_DATA_RD.L3_MISS.ANY_SNOOP",
-        "MSRIndex": "0x1a6,0x1a7",
-        "PublicDescription": "Counts all prefetch (that bring data to LLC only) data reads that miss in the L3. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "PublicDescription": "Counts all prefetch (that bring data to LLC only) data reads TBD TBD",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -863,12 +864,12 @@
         "Offcore": "1",
         "EventCode": "0xB7, 0xBB",
         "UMask": "0x1",
-        "BriefDescription": "Counts all prefetch (that bring data to LLC only) data reads that miss the L3 and clean or shared data is transferred from remote cache.",
-        "MSRValue": "0x083fc00080 ",
+        "BriefDescription": "Counts all prefetch (that bring data to LLC only) data reads TBD",
+        "MSRValue": "0x083FC00080",
         "Counter": "0,1,2,3",
         "EventName": "OFFCORE_RESPONSE.PF_L3_DATA_RD.L3_MISS.REMOTE_HIT_FORWARD",
-        "MSRIndex": "0x1a6,0x1a7",
-        "PublicDescription": "Counts all prefetch (that bring data to LLC only) data reads that miss the L3 and clean or shared data is transferred from remote cache. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "PublicDescription": "Counts all prefetch (that bring data to LLC only) data reads TBD",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -876,12 +877,12 @@
         "Offcore": "1",
         "EventCode": "0xB7, 0xBB",
         "UMask": "0x1",
-        "BriefDescription": "Counts all prefetch (that bring data to LLC only) data reads that miss the L3 and the modified data is transferred from remote cache.",
-        "MSRValue": "0x103fc00080 ",
+        "BriefDescription": "Counts all prefetch (that bring data to LLC only) data reads TBD",
+        "MSRValue": "0x103FC00080",
         "Counter": "0,1,2,3",
         "EventName": "OFFCORE_RESPONSE.PF_L3_DATA_RD.L3_MISS.REMOTE_HITM",
-        "MSRIndex": "0x1a6,0x1a7",
-        "PublicDescription": "Counts all prefetch (that bring data to LLC only) data reads that miss the L3 and the modified data is transferred from remote cache. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "PublicDescription": "Counts all prefetch (that bring data to LLC only) data reads TBD",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -889,12 +890,12 @@
         "Offcore": "1",
         "EventCode": "0xB7, 0xBB",
         "UMask": "0x1",
-        "BriefDescription": "Counts all prefetch (that bring data to LLC only) data reads that miss the L3 and the data is returned from local or remote dram.",
-        "MSRValue": "0x063fc00080 ",
+        "BriefDescription": "Counts all prefetch (that bring data to LLC only) data reads TBD",
+        "MSRValue": "0x063FC00080",
         "Counter": "0,1,2,3",
         "EventName": "OFFCORE_RESPONSE.PF_L3_DATA_RD.L3_MISS.SNOOP_MISS_OR_NO_FWD",
-        "MSRIndex": "0x1a6,0x1a7",
-        "PublicDescription": "Counts all prefetch (that bring data to LLC only) data reads that miss the L3 and the data is returned from local or remote dram. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "PublicDescription": "Counts all prefetch (that bring data to LLC only) data reads TBD",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -902,12 +903,12 @@
         "Offcore": "1",
         "EventCode": "0xB7, 0xBB",
         "UMask": "0x1",
-        "BriefDescription": "Counts all prefetch (that bring data to LLC only) data reads that miss the L3 and the data is returned from remote dram.",
-        "MSRValue": "0x063b800080 ",
+        "BriefDescription": "Counts all prefetch (that bring data to LLC only) data reads TBD",
+        "MSRValue": "0x063B800080",
         "Counter": "0,1,2,3",
         "EventName": "OFFCORE_RESPONSE.PF_L3_DATA_RD.L3_MISS_REMOTE_DRAM.SNOOP_MISS_OR_NO_FWD",
-        "MSRIndex": "0x1a6,0x1a7",
-        "PublicDescription": "Counts all prefetch (that bring data to LLC only) data reads that miss the L3 and the data is returned from remote dram. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "PublicDescription": "Counts all prefetch (that bring data to LLC only) data reads TBD",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -915,12 +916,12 @@
         "Offcore": "1",
         "EventCode": "0xB7, 0xBB",
         "UMask": "0x1",
-        "BriefDescription": "Counts all prefetch (that bring data to LLC only) data reads that miss the L3 and the data is returned from local dram.",
-        "MSRValue": "0x0604000080 ",
+        "BriefDescription": "Counts all prefetch (that bring data to LLC only) data reads TBD",
+        "MSRValue": "0x0604000080",
         "Counter": "0,1,2,3",
         "EventName": "OFFCORE_RESPONSE.PF_L3_DATA_RD.L3_MISS_LOCAL_DRAM.SNOOP_MISS_OR_NO_FWD",
-        "MSRIndex": "0x1a6,0x1a7",
-        "PublicDescription": "Counts all prefetch (that bring data to LLC only) data reads that miss the L3 and the data is returned from local dram. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "PublicDescription": "Counts all prefetch (that bring data to LLC only) data reads TBD",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -928,12 +929,12 @@
         "Offcore": "1",
         "EventCode": "0xB7, 0xBB",
         "UMask": "0x1",
-        "BriefDescription": "Counts all prefetch (that bring data to LLC only) RFOs that miss in the L3.",
-        "MSRValue": "0x3fbc000100 ",
+        "BriefDescription": "Counts all prefetch (that bring data to LLC only) RFOs TBD TBD",
+        "MSRValue": "0x3FBC000100",
         "Counter": "0,1,2,3",
         "EventName": "OFFCORE_RESPONSE.PF_L3_RFO.L3_MISS.ANY_SNOOP",
-        "MSRIndex": "0x1a6,0x1a7",
-        "PublicDescription": "Counts all prefetch (that bring data to LLC only) RFOs that miss in the L3. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "PublicDescription": "Counts all prefetch (that bring data to LLC only) RFOs TBD TBD",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -941,12 +942,12 @@
         "Offcore": "1",
         "EventCode": "0xB7, 0xBB",
         "UMask": "0x1",
-        "BriefDescription": "Counts all prefetch (that bring data to LLC only) RFOs that miss the L3 and clean or shared data is transferred from remote cache.",
-        "MSRValue": "0x083fc00100 ",
+        "BriefDescription": "Counts all prefetch (that bring data to LLC only) RFOs TBD",
+        "MSRValue": "0x083FC00100",
         "Counter": "0,1,2,3",
         "EventName": "OFFCORE_RESPONSE.PF_L3_RFO.L3_MISS.REMOTE_HIT_FORWARD",
-        "MSRIndex": "0x1a6,0x1a7",
-        "PublicDescription": "Counts all prefetch (that bring data to LLC only) RFOs that miss the L3 and clean or shared data is transferred from remote cache. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "PublicDescription": "Counts all prefetch (that bring data to LLC only) RFOs TBD",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -954,12 +955,12 @@
         "Offcore": "1",
         "EventCode": "0xB7, 0xBB",
         "UMask": "0x1",
-        "BriefDescription": "Counts all prefetch (that bring data to LLC only) RFOs that miss the L3 and the modified data is transferred from remote cache.",
-        "MSRValue": "0x103fc00100 ",
+        "BriefDescription": "Counts all prefetch (that bring data to LLC only) RFOs TBD",
+        "MSRValue": "0x103FC00100",
         "Counter": "0,1,2,3",
         "EventName": "OFFCORE_RESPONSE.PF_L3_RFO.L3_MISS.REMOTE_HITM",
-        "MSRIndex": "0x1a6,0x1a7",
-        "PublicDescription": "Counts all prefetch (that bring data to LLC only) RFOs that miss the L3 and the modified data is transferred from remote cache. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "PublicDescription": "Counts all prefetch (that bring data to LLC only) RFOs TBD",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -967,12 +968,12 @@
         "Offcore": "1",
         "EventCode": "0xB7, 0xBB",
         "UMask": "0x1",
-        "BriefDescription": "Counts all prefetch (that bring data to LLC only) RFOs that miss the L3 and the data is returned from local or remote dram.",
-        "MSRValue": "0x063fc00100 ",
+        "BriefDescription": "Counts all prefetch (that bring data to LLC only) RFOs TBD",
+        "MSRValue": "0x063FC00100",
         "Counter": "0,1,2,3",
         "EventName": "OFFCORE_RESPONSE.PF_L3_RFO.L3_MISS.SNOOP_MISS_OR_NO_FWD",
-        "MSRIndex": "0x1a6,0x1a7",
-        "PublicDescription": "Counts all prefetch (that bring data to LLC only) RFOs that miss the L3 and the data is returned from local or remote dram. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "PublicDescription": "Counts all prefetch (that bring data to LLC only) RFOs TBD",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -980,12 +981,12 @@
         "Offcore": "1",
         "EventCode": "0xB7, 0xBB",
         "UMask": "0x1",
-        "BriefDescription": "Counts all prefetch (that bring data to LLC only) RFOs that miss the L3 and the data is returned from remote dram.",
-        "MSRValue": "0x063b800100 ",
+        "BriefDescription": "Counts all prefetch (that bring data to LLC only) RFOs TBD",
+        "MSRValue": "0x063B800100",
         "Counter": "0,1,2,3",
         "EventName": "OFFCORE_RESPONSE.PF_L3_RFO.L3_MISS_REMOTE_DRAM.SNOOP_MISS_OR_NO_FWD",
-        "MSRIndex": "0x1a6,0x1a7",
-        "PublicDescription": "Counts all prefetch (that bring data to LLC only) RFOs that miss the L3 and the data is returned from remote dram. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "PublicDescription": "Counts all prefetch (that bring data to LLC only) RFOs TBD",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -993,12 +994,12 @@
         "Offcore": "1",
         "EventCode": "0xB7, 0xBB",
         "UMask": "0x1",
-        "BriefDescription": "Counts all prefetch (that bring data to LLC only) RFOs that miss the L3 and the data is returned from local dram.",
-        "MSRValue": "0x0604000100 ",
+        "BriefDescription": "Counts all prefetch (that bring data to LLC only) RFOs TBD",
+        "MSRValue": "0x0604000100",
         "Counter": "0,1,2,3",
         "EventName": "OFFCORE_RESPONSE.PF_L3_RFO.L3_MISS_LOCAL_DRAM.SNOOP_MISS_OR_NO_FWD",
-        "MSRIndex": "0x1a6,0x1a7",
-        "PublicDescription": "Counts all prefetch (that bring data to LLC only) RFOs that miss the L3 and the data is returned from local dram. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "PublicDescription": "Counts all prefetch (that bring data to LLC only) RFOs TBD",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -1006,12 +1007,12 @@
         "Offcore": "1",
         "EventCode": "0xB7, 0xBB",
         "UMask": "0x1",
-        "BriefDescription": "Counts L1 data cache hardware prefetch requests and software prefetch requests that miss in the L3.",
-        "MSRValue": "0x3fbc000400 ",
+        "BriefDescription": "Counts L1 data cache hardware prefetch requests and software prefetch requests TBD TBD",
+        "MSRValue": "0x3FBC000400",
         "Counter": "0,1,2,3",
         "EventName": "OFFCORE_RESPONSE.PF_L1D_AND_SW.L3_MISS.ANY_SNOOP",
-        "MSRIndex": "0x1a6,0x1a7",
-        "PublicDescription": "Counts L1 data cache hardware prefetch requests and software prefetch requests that miss in the L3. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "PublicDescription": "Counts L1 data cache hardware prefetch requests and software prefetch requests TBD TBD",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -1019,12 +1020,12 @@
         "Offcore": "1",
         "EventCode": "0xB7, 0xBB",
         "UMask": "0x1",
-        "BriefDescription": "Counts L1 data cache hardware prefetch requests and software prefetch requests that miss the L3 and clean or shared data is transferred from remote cache.",
-        "MSRValue": "0x083fc00400 ",
+        "BriefDescription": "Counts L1 data cache hardware prefetch requests and software prefetch requests TBD",
+        "MSRValue": "0x083FC00400",
         "Counter": "0,1,2,3",
         "EventName": "OFFCORE_RESPONSE.PF_L1D_AND_SW.L3_MISS.REMOTE_HIT_FORWARD",
-        "MSRIndex": "0x1a6,0x1a7",
-        "PublicDescription": "Counts L1 data cache hardware prefetch requests and software prefetch requests that miss the L3 and clean or shared data is transferred from remote cache. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "PublicDescription": "Counts L1 data cache hardware prefetch requests and software prefetch requests TBD",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -1032,12 +1033,12 @@
         "Offcore": "1",
         "EventCode": "0xB7, 0xBB",
         "UMask": "0x1",
-        "BriefDescription": "Counts L1 data cache hardware prefetch requests and software prefetch requests that miss the L3 and the modified data is transferred from remote cache.",
-        "MSRValue": "0x103fc00400 ",
+        "BriefDescription": "Counts L1 data cache hardware prefetch requests and software prefetch requests TBD",
+        "MSRValue": "0x103FC00400",
         "Counter": "0,1,2,3",
         "EventName": "OFFCORE_RESPONSE.PF_L1D_AND_SW.L3_MISS.REMOTE_HITM",
-        "MSRIndex": "0x1a6,0x1a7",
-        "PublicDescription": "Counts L1 data cache hardware prefetch requests and software prefetch requests that miss the L3 and the modified data is transferred from remote cache. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "PublicDescription": "Counts L1 data cache hardware prefetch requests and software prefetch requests TBD",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -1045,12 +1046,12 @@
         "Offcore": "1",
         "EventCode": "0xB7, 0xBB",
         "UMask": "0x1",
-        "BriefDescription": "Counts L1 data cache hardware prefetch requests and software prefetch requests that miss the L3 and the data is returned from local or remote dram.",
-        "MSRValue": "0x063fc00400 ",
+        "BriefDescription": "Counts L1 data cache hardware prefetch requests and software prefetch requests TBD",
+        "MSRValue": "0x063FC00400",
         "Counter": "0,1,2,3",
         "EventName": "OFFCORE_RESPONSE.PF_L1D_AND_SW.L3_MISS.SNOOP_MISS_OR_NO_FWD",
-        "MSRIndex": "0x1a6,0x1a7",
-        "PublicDescription": "Counts L1 data cache hardware prefetch requests and software prefetch requests that miss the L3 and the data is returned from local or remote dram. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "PublicDescription": "Counts L1 data cache hardware prefetch requests and software prefetch requests TBD",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -1058,12 +1059,12 @@
         "Offcore": "1",
         "EventCode": "0xB7, 0xBB",
         "UMask": "0x1",
-        "BriefDescription": "Counts L1 data cache hardware prefetch requests and software prefetch requests that miss the L3 and the data is returned from remote dram.",
-        "MSRValue": "0x063b800400 ",
+        "BriefDescription": "Counts L1 data cache hardware prefetch requests and software prefetch requests TBD",
+        "MSRValue": "0x063B800400",
         "Counter": "0,1,2,3",
         "EventName": "OFFCORE_RESPONSE.PF_L1D_AND_SW.L3_MISS_REMOTE_DRAM.SNOOP_MISS_OR_NO_FWD",
-        "MSRIndex": "0x1a6,0x1a7",
-        "PublicDescription": "Counts L1 data cache hardware prefetch requests and software prefetch requests that miss the L3 and the data is returned from remote dram. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "PublicDescription": "Counts L1 data cache hardware prefetch requests and software prefetch requests TBD",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -1071,90 +1072,12 @@
         "Offcore": "1",
         "EventCode": "0xB7, 0xBB",
         "UMask": "0x1",
-        "BriefDescription": "Counts L1 data cache hardware prefetch requests and software prefetch requests that miss the L3 and the data is returned from local dram.",
-        "MSRValue": "0x0604000400 ",
+        "BriefDescription": "Counts L1 data cache hardware prefetch requests and software prefetch requests TBD",
+        "MSRValue": "0x0604000400",
         "Counter": "0,1,2,3",
         "EventName": "OFFCORE_RESPONSE.PF_L1D_AND_SW.L3_MISS_LOCAL_DRAM.SNOOP_MISS_OR_NO_FWD",
-        "MSRIndex": "0x1a6,0x1a7",
-        "PublicDescription": "Counts L1 data cache hardware prefetch requests and software prefetch requests that miss the L3 and the data is returned from local dram. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
-        "SampleAfterValue": "100003",
-        "CounterHTOff": "0,1,2,3"
-    },
-    {
-        "Offcore": "1",
-        "EventCode": "0xB7, 0xBB",
-        "UMask": "0x1",
-        "BriefDescription": "Counts any other requests that miss in the L3.",
-        "MSRValue": "0x3fbc008000 ",
-        "Counter": "0,1,2,3",
-        "EventName": "OFFCORE_RESPONSE.OTHER.L3_MISS.ANY_SNOOP",
-        "MSRIndex": "0x1a6,0x1a7",
-        "PublicDescription": "Counts any other requests that miss in the L3. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
-        "SampleAfterValue": "100003",
-        "CounterHTOff": "0,1,2,3"
-    },
-    {
-        "Offcore": "1",
-        "EventCode": "0xB7, 0xBB",
-        "UMask": "0x1",
-        "BriefDescription": "Counts any other requests that miss the L3 and clean or shared data is transferred from remote cache.",
-        "MSRValue": "0x083fc08000 ",
-        "Counter": "0,1,2,3",
-        "EventName": "OFFCORE_RESPONSE.OTHER.L3_MISS.REMOTE_HIT_FORWARD",
-        "MSRIndex": "0x1a6,0x1a7",
-        "PublicDescription": "Counts any other requests that miss the L3 and clean or shared data is transferred from remote cache. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
-        "SampleAfterValue": "100003",
-        "CounterHTOff": "0,1,2,3"
-    },
-    {
-        "Offcore": "1",
-        "EventCode": "0xB7, 0xBB",
-        "UMask": "0x1",
-        "BriefDescription": "Counts any other requests that miss the L3 and the modified data is transferred from remote cache.",
-        "MSRValue": "0x103fc08000 ",
-        "Counter": "0,1,2,3",
-        "EventName": "OFFCORE_RESPONSE.OTHER.L3_MISS.REMOTE_HITM",
-        "MSRIndex": "0x1a6,0x1a7",
-        "PublicDescription": "Counts any other requests that miss the L3 and the modified data is transferred from remote cache. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
-        "SampleAfterValue": "100003",
-        "CounterHTOff": "0,1,2,3"
-    },
-    {
-        "Offcore": "1",
-        "EventCode": "0xB7, 0xBB",
-        "UMask": "0x1",
-        "BriefDescription": "Counts any other requests that miss the L3 and the data is returned from local or remote dram.",
-        "MSRValue": "0x063fc08000 ",
-        "Counter": "0,1,2,3",
-        "EventName": "OFFCORE_RESPONSE.OTHER.L3_MISS.SNOOP_MISS_OR_NO_FWD",
-        "MSRIndex": "0x1a6,0x1a7",
-        "PublicDescription": "Counts any other requests that miss the L3 and the data is returned from local or remote dram. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
-        "SampleAfterValue": "100003",
-        "CounterHTOff": "0,1,2,3"
-    },
-    {
-        "Offcore": "1",
-        "EventCode": "0xB7, 0xBB",
-        "UMask": "0x1",
-        "BriefDescription": "Counts any other requests that miss the L3 and the data is returned from remote dram.",
-        "MSRValue": "0x063b808000 ",
-        "Counter": "0,1,2,3",
-        "EventName": "OFFCORE_RESPONSE.OTHER.L3_MISS_REMOTE_DRAM.SNOOP_MISS_OR_NO_FWD",
-        "MSRIndex": "0x1a6,0x1a7",
-        "PublicDescription": "Counts any other requests that miss the L3 and the data is returned from remote dram. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
-        "SampleAfterValue": "100003",
-        "CounterHTOff": "0,1,2,3"
-    },
-    {
-        "Offcore": "1",
-        "EventCode": "0xB7, 0xBB",
-        "UMask": "0x1",
-        "BriefDescription": "Counts any other requests that miss the L3 and the data is returned from local dram.",
-        "MSRValue": "0x0604008000 ",
-        "Counter": "0,1,2,3",
-        "EventName": "OFFCORE_RESPONSE.OTHER.L3_MISS_LOCAL_DRAM.SNOOP_MISS_OR_NO_FWD",
-        "MSRIndex": "0x1a6,0x1a7",
-        "PublicDescription": "Counts any other requests that miss the L3 and the data is returned from local dram. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "PublicDescription": "Counts L1 data cache hardware prefetch requests and software prefetch requests TBD",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -1162,12 +1085,12 @@
         "Offcore": "1",
         "EventCode": "0xB7, 0xBB",
         "UMask": "0x1",
-        "BriefDescription": "Counts all prefetch data reads that miss in the L3.",
-        "MSRValue": "0x3fbc000490 ",
+        "BriefDescription": "TBD TBD TBD",
+        "MSRValue": "0x3FBC000490",
         "Counter": "0,1,2,3",
         "EventName": "OFFCORE_RESPONSE.ALL_PF_DATA_RD.L3_MISS.ANY_SNOOP",
-        "MSRIndex": "0x1a6,0x1a7",
-        "PublicDescription": "Counts all prefetch data reads that miss in the L3. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "PublicDescription": "TBD TBD TBD",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -1175,12 +1098,12 @@
         "Offcore": "1",
         "EventCode": "0xB7, 0xBB",
         "UMask": "0x1",
-        "BriefDescription": "Counts all prefetch data reads that miss the L3 and clean or shared data is transferred from remote cache.",
-        "MSRValue": "0x083fc00490 ",
+        "BriefDescription": "TBD TBD",
+        "MSRValue": "0x083FC00490",
         "Counter": "0,1,2,3",
         "EventName": "OFFCORE_RESPONSE.ALL_PF_DATA_RD.L3_MISS.REMOTE_HIT_FORWARD",
-        "MSRIndex": "0x1a6,0x1a7",
-        "PublicDescription": "Counts all prefetch data reads that miss the L3 and clean or shared data is transferred from remote cache. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "PublicDescription": "TBD TBD",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -1188,12 +1111,12 @@
         "Offcore": "1",
         "EventCode": "0xB7, 0xBB",
         "UMask": "0x1",
-        "BriefDescription": "Counts all prefetch data reads that miss the L3 and the modified data is transferred from remote cache.",
-        "MSRValue": "0x103fc00490 ",
+        "BriefDescription": "TBD TBD",
+        "MSRValue": "0x103FC00490",
         "Counter": "0,1,2,3",
         "EventName": "OFFCORE_RESPONSE.ALL_PF_DATA_RD.L3_MISS.REMOTE_HITM",
-        "MSRIndex": "0x1a6,0x1a7",
-        "PublicDescription": "Counts all prefetch data reads that miss the L3 and the modified data is transferred from remote cache. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "PublicDescription": "TBD TBD",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -1201,12 +1124,12 @@
         "Offcore": "1",
         "EventCode": "0xB7, 0xBB",
         "UMask": "0x1",
-        "BriefDescription": "Counts all prefetch data reads that miss the L3 and the data is returned from local or remote dram.",
-        "MSRValue": "0x063fc00490 ",
+        "BriefDescription": "TBD TBD",
+        "MSRValue": "0x063FC00490",
         "Counter": "0,1,2,3",
         "EventName": "OFFCORE_RESPONSE.ALL_PF_DATA_RD.L3_MISS.SNOOP_MISS_OR_NO_FWD",
-        "MSRIndex": "0x1a6,0x1a7",
-        "PublicDescription": "Counts all prefetch data reads that miss the L3 and the data is returned from local or remote dram. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "PublicDescription": "TBD TBD",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -1214,12 +1137,12 @@
         "Offcore": "1",
         "EventCode": "0xB7, 0xBB",
         "UMask": "0x1",
-        "BriefDescription": "Counts all prefetch data reads that miss the L3 and the data is returned from remote dram.",
-        "MSRValue": "0x063b800490 ",
+        "BriefDescription": "TBD TBD",
+        "MSRValue": "0x063B800490",
         "Counter": "0,1,2,3",
         "EventName": "OFFCORE_RESPONSE.ALL_PF_DATA_RD.L3_MISS_REMOTE_DRAM.SNOOP_MISS_OR_NO_FWD",
-        "MSRIndex": "0x1a6,0x1a7",
-        "PublicDescription": "Counts all prefetch data reads that miss the L3 and the data is returned from remote dram. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "PublicDescription": "TBD TBD",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -1227,12 +1150,12 @@
         "Offcore": "1",
         "EventCode": "0xB7, 0xBB",
         "UMask": "0x1",
-        "BriefDescription": "Counts all prefetch data reads that miss the L3 and the data is returned from local dram.",
-        "MSRValue": "0x0604000490 ",
+        "BriefDescription": "TBD TBD",
+        "MSRValue": "0x0604000490",
         "Counter": "0,1,2,3",
         "EventName": "OFFCORE_RESPONSE.ALL_PF_DATA_RD.L3_MISS_LOCAL_DRAM.SNOOP_MISS_OR_NO_FWD",
-        "MSRIndex": "0x1a6,0x1a7",
-        "PublicDescription": "Counts all prefetch data reads that miss the L3 and the data is returned from local dram. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "PublicDescription": "TBD TBD",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -1240,12 +1163,12 @@
         "Offcore": "1",
         "EventCode": "0xB7, 0xBB",
         "UMask": "0x1",
-        "BriefDescription": "Counts prefetch RFOs that miss in the L3.",
-        "MSRValue": "0x3fbc000120 ",
+        "BriefDescription": "TBD TBD TBD",
+        "MSRValue": "0x3FBC000120",
         "Counter": "0,1,2,3",
         "EventName": "OFFCORE_RESPONSE.ALL_PF_RFO.L3_MISS.ANY_SNOOP",
-        "MSRIndex": "0x1a6,0x1a7",
-        "PublicDescription": "Counts prefetch RFOs that miss in the L3. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "PublicDescription": "TBD TBD TBD",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -1253,12 +1176,12 @@
         "Offcore": "1",
         "EventCode": "0xB7, 0xBB",
         "UMask": "0x1",
-        "BriefDescription": "Counts prefetch RFOs that miss the L3 and clean or shared data is transferred from remote cache.",
-        "MSRValue": "0x083fc00120 ",
+        "BriefDescription": "TBD TBD",
+        "MSRValue": "0x083FC00120",
         "Counter": "0,1,2,3",
         "EventName": "OFFCORE_RESPONSE.ALL_PF_RFO.L3_MISS.REMOTE_HIT_FORWARD",
-        "MSRIndex": "0x1a6,0x1a7",
-        "PublicDescription": "Counts prefetch RFOs that miss the L3 and clean or shared data is transferred from remote cache. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "PublicDescription": "TBD TBD",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -1266,12 +1189,12 @@
         "Offcore": "1",
         "EventCode": "0xB7, 0xBB",
         "UMask": "0x1",
-        "BriefDescription": "Counts prefetch RFOs that miss the L3 and the modified data is transferred from remote cache.",
-        "MSRValue": "0x103fc00120 ",
+        "BriefDescription": "TBD TBD",
+        "MSRValue": "0x103FC00120",
         "Counter": "0,1,2,3",
         "EventName": "OFFCORE_RESPONSE.ALL_PF_RFO.L3_MISS.REMOTE_HITM",
-        "MSRIndex": "0x1a6,0x1a7",
-        "PublicDescription": "Counts prefetch RFOs that miss the L3 and the modified data is transferred from remote cache. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "PublicDescription": "TBD TBD",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -1279,12 +1202,12 @@
         "Offcore": "1",
         "EventCode": "0xB7, 0xBB",
         "UMask": "0x1",
-        "BriefDescription": "Counts prefetch RFOs that miss the L3 and the data is returned from local or remote dram.",
-        "MSRValue": "0x063fc00120 ",
+        "BriefDescription": "TBD TBD",
+        "MSRValue": "0x063FC00120",
         "Counter": "0,1,2,3",
         "EventName": "OFFCORE_RESPONSE.ALL_PF_RFO.L3_MISS.SNOOP_MISS_OR_NO_FWD",
-        "MSRIndex": "0x1a6,0x1a7",
-        "PublicDescription": "Counts prefetch RFOs that miss the L3 and the data is returned from local or remote dram. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "PublicDescription": "TBD TBD",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -1292,12 +1215,12 @@
         "Offcore": "1",
         "EventCode": "0xB7, 0xBB",
         "UMask": "0x1",
-        "BriefDescription": "Counts prefetch RFOs that miss the L3 and the data is returned from remote dram.",
-        "MSRValue": "0x063b800120 ",
+        "BriefDescription": "TBD TBD",
+        "MSRValue": "0x063B800120",
         "Counter": "0,1,2,3",
         "EventName": "OFFCORE_RESPONSE.ALL_PF_RFO.L3_MISS_REMOTE_DRAM.SNOOP_MISS_OR_NO_FWD",
-        "MSRIndex": "0x1a6,0x1a7",
-        "PublicDescription": "Counts prefetch RFOs that miss the L3 and the data is returned from remote dram. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "PublicDescription": "TBD TBD",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -1305,12 +1228,12 @@
         "Offcore": "1",
         "EventCode": "0xB7, 0xBB",
         "UMask": "0x1",
-        "BriefDescription": "Counts prefetch RFOs that miss the L3 and the data is returned from local dram.",
-        "MSRValue": "0x0604000120 ",
+        "BriefDescription": "TBD TBD",
+        "MSRValue": "0x0604000120",
         "Counter": "0,1,2,3",
         "EventName": "OFFCORE_RESPONSE.ALL_PF_RFO.L3_MISS_LOCAL_DRAM.SNOOP_MISS_OR_NO_FWD",
-        "MSRIndex": "0x1a6,0x1a7",
-        "PublicDescription": "Counts prefetch RFOs that miss the L3 and the data is returned from local dram. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "PublicDescription": "TBD TBD",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -1318,12 +1241,12 @@
         "Offcore": "1",
         "EventCode": "0xB7, 0xBB",
         "UMask": "0x1",
-        "BriefDescription": "Counts all demand & prefetch data reads that miss in the L3.",
-        "MSRValue": "0x3fbc000491 ",
+        "BriefDescription": "TBD TBD TBD",
+        "MSRValue": "0x3FBC000491",
         "Counter": "0,1,2,3",
         "EventName": "OFFCORE_RESPONSE.ALL_DATA_RD.L3_MISS.ANY_SNOOP",
-        "MSRIndex": "0x1a6,0x1a7",
-        "PublicDescription": "Counts all demand & prefetch data reads that miss in the L3. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "PublicDescription": "TBD TBD TBD",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -1331,12 +1254,12 @@
         "Offcore": "1",
         "EventCode": "0xB7, 0xBB",
         "UMask": "0x1",
-        "BriefDescription": "Counts all demand & prefetch data reads that miss the L3 and clean or shared data is transferred from remote cache.",
-        "MSRValue": "0x083fc00491 ",
+        "BriefDescription": "TBD TBD",
+        "MSRValue": "0x083FC00491",
         "Counter": "0,1,2,3",
         "EventName": "OFFCORE_RESPONSE.ALL_DATA_RD.L3_MISS.REMOTE_HIT_FORWARD",
-        "MSRIndex": "0x1a6,0x1a7",
-        "PublicDescription": "Counts all demand & prefetch data reads that miss the L3 and clean or shared data is transferred from remote cache. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "PublicDescription": "TBD TBD",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -1344,12 +1267,12 @@
         "Offcore": "1",
         "EventCode": "0xB7, 0xBB",
         "UMask": "0x1",
-        "BriefDescription": "Counts all demand & prefetch data reads that miss the L3 and the modified data is transferred from remote cache.",
-        "MSRValue": "0x103fc00491 ",
+        "BriefDescription": "TBD TBD",
+        "MSRValue": "0x103FC00491",
         "Counter": "0,1,2,3",
         "EventName": "OFFCORE_RESPONSE.ALL_DATA_RD.L3_MISS.REMOTE_HITM",
-        "MSRIndex": "0x1a6,0x1a7",
-        "PublicDescription": "Counts all demand & prefetch data reads that miss the L3 and the modified data is transferred from remote cache. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "PublicDescription": "TBD TBD",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -1357,12 +1280,12 @@
         "Offcore": "1",
         "EventCode": "0xB7, 0xBB",
         "UMask": "0x1",
-        "BriefDescription": "Counts all demand & prefetch data reads that miss the L3 and the data is returned from local or remote dram.",
-        "MSRValue": "0x063fc00491 ",
+        "BriefDescription": "TBD TBD",
+        "MSRValue": "0x063FC00491",
         "Counter": "0,1,2,3",
         "EventName": "OFFCORE_RESPONSE.ALL_DATA_RD.L3_MISS.SNOOP_MISS_OR_NO_FWD",
-        "MSRIndex": "0x1a6,0x1a7",
-        "PublicDescription": "Counts all demand & prefetch data reads that miss the L3 and the data is returned from local or remote dram. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "PublicDescription": "TBD TBD",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -1370,12 +1293,12 @@
         "Offcore": "1",
         "EventCode": "0xB7, 0xBB",
         "UMask": "0x1",
-        "BriefDescription": "Counts all demand & prefetch data reads that miss the L3 and the data is returned from remote dram.",
-        "MSRValue": "0x063b800491 ",
+        "BriefDescription": "TBD TBD",
+        "MSRValue": "0x063B800491",
         "Counter": "0,1,2,3",
         "EventName": "OFFCORE_RESPONSE.ALL_DATA_RD.L3_MISS_REMOTE_DRAM.SNOOP_MISS_OR_NO_FWD",
-        "MSRIndex": "0x1a6,0x1a7",
-        "PublicDescription": "Counts all demand & prefetch data reads that miss the L3 and the data is returned from remote dram. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "PublicDescription": "TBD TBD",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -1383,12 +1306,12 @@
         "Offcore": "1",
         "EventCode": "0xB7, 0xBB",
         "UMask": "0x1",
-        "BriefDescription": "Counts all demand & prefetch data reads that miss the L3 and the data is returned from local dram.",
-        "MSRValue": "0x0604000491 ",
+        "BriefDescription": "TBD TBD",
+        "MSRValue": "0x0604000491",
         "Counter": "0,1,2,3",
         "EventName": "OFFCORE_RESPONSE.ALL_DATA_RD.L3_MISS_LOCAL_DRAM.SNOOP_MISS_OR_NO_FWD",
-        "MSRIndex": "0x1a6,0x1a7",
-        "PublicDescription": "Counts all demand & prefetch data reads that miss the L3 and the data is returned from local dram. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "PublicDescription": "TBD TBD",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -1396,12 +1319,12 @@
         "Offcore": "1",
         "EventCode": "0xB7, 0xBB",
         "UMask": "0x1",
-        "BriefDescription": "Counts all demand & prefetch RFOs that miss in the L3.",
-        "MSRValue": "0x3fbc000122 ",
+        "BriefDescription": "TBD TBD TBD",
+        "MSRValue": "0x3FBC000122",
         "Counter": "0,1,2,3",
         "EventName": "OFFCORE_RESPONSE.ALL_RFO.L3_MISS.ANY_SNOOP",
-        "MSRIndex": "0x1a6,0x1a7",
-        "PublicDescription": "Counts all demand & prefetch RFOs that miss in the L3. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "PublicDescription": "TBD TBD TBD",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -1409,12 +1332,12 @@
         "Offcore": "1",
         "EventCode": "0xB7, 0xBB",
         "UMask": "0x1",
-        "BriefDescription": "Counts all demand & prefetch RFOs that miss the L3 and clean or shared data is transferred from remote cache.",
-        "MSRValue": "0x083fc00122 ",
+        "BriefDescription": "TBD TBD",
+        "MSRValue": "0x083FC00122",
         "Counter": "0,1,2,3",
         "EventName": "OFFCORE_RESPONSE.ALL_RFO.L3_MISS.REMOTE_HIT_FORWARD",
-        "MSRIndex": "0x1a6,0x1a7",
-        "PublicDescription": "Counts all demand & prefetch RFOs that miss the L3 and clean or shared data is transferred from remote cache. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "PublicDescription": "TBD TBD",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -1422,12 +1345,12 @@
         "Offcore": "1",
         "EventCode": "0xB7, 0xBB",
         "UMask": "0x1",
-        "BriefDescription": "Counts all demand & prefetch RFOs that miss the L3 and the modified data is transferred from remote cache.",
-        "MSRValue": "0x103fc00122 ",
+        "BriefDescription": "TBD TBD",
+        "MSRValue": "0x103FC00122",
         "Counter": "0,1,2,3",
         "EventName": "OFFCORE_RESPONSE.ALL_RFO.L3_MISS.REMOTE_HITM",
-        "MSRIndex": "0x1a6,0x1a7",
-        "PublicDescription": "Counts all demand & prefetch RFOs that miss the L3 and the modified data is transferred from remote cache. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "PublicDescription": "TBD TBD",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -1435,12 +1358,12 @@
         "Offcore": "1",
         "EventCode": "0xB7, 0xBB",
         "UMask": "0x1",
-        "BriefDescription": "Counts all demand & prefetch RFOs that miss the L3 and the data is returned from local or remote dram.",
-        "MSRValue": "0x063fc00122 ",
+        "BriefDescription": "TBD TBD",
+        "MSRValue": "0x063FC00122",
         "Counter": "0,1,2,3",
         "EventName": "OFFCORE_RESPONSE.ALL_RFO.L3_MISS.SNOOP_MISS_OR_NO_FWD",
-        "MSRIndex": "0x1a6,0x1a7",
-        "PublicDescription": "Counts all demand & prefetch RFOs that miss the L3 and the data is returned from local or remote dram. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "PublicDescription": "TBD TBD",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -1448,12 +1371,12 @@
         "Offcore": "1",
         "EventCode": "0xB7, 0xBB",
         "UMask": "0x1",
-        "BriefDescription": "Counts all demand & prefetch RFOs that miss the L3 and the data is returned from remote dram.",
-        "MSRValue": "0x063b800122 ",
+        "BriefDescription": "TBD TBD",
+        "MSRValue": "0x063B800122",
         "Counter": "0,1,2,3",
         "EventName": "OFFCORE_RESPONSE.ALL_RFO.L3_MISS_REMOTE_DRAM.SNOOP_MISS_OR_NO_FWD",
-        "MSRIndex": "0x1a6,0x1a7",
-        "PublicDescription": "Counts all demand & prefetch RFOs that miss the L3 and the data is returned from remote dram. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "PublicDescription": "TBD TBD",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     },
@@ -1461,12 +1384,12 @@
         "Offcore": "1",
         "EventCode": "0xB7, 0xBB",
         "UMask": "0x1",
-        "BriefDescription": "Counts all demand & prefetch RFOs that miss the L3 and the data is returned from local dram.",
-        "MSRValue": "0x0604000122 ",
+        "BriefDescription": "TBD TBD",
+        "MSRValue": "0x0604000122",
         "Counter": "0,1,2,3",
         "EventName": "OFFCORE_RESPONSE.ALL_RFO.L3_MISS_LOCAL_DRAM.SNOOP_MISS_OR_NO_FWD",
-        "MSRIndex": "0x1a6,0x1a7",
-        "PublicDescription": "Counts all demand & prefetch RFOs that miss the L3 and the data is returned from local dram. Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.",
+        "MSRIndex": "0x1a6, 0x1a7",
+        "PublicDescription": "TBD TBD",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3"
     }
diff --git a/tools/perf/pmu-events/arch/x86/skylakex/pipeline.json b/tools/perf/pmu-events/arch/x86/skylakex/pipeline.json
index f99f7ae27820..369f56c1d1b5 100644
--- a/tools/perf/pmu-events/arch/x86/skylakex/pipeline.json
+++ b/tools/perf/pmu-events/arch/x86/skylakex/pipeline.json
@@ -1,6 +1,5 @@
 [
     {
-        "EventCode": "0x00",
         "UMask": "0x1",
         "BriefDescription": "Instructions retired from execution.",
         "Counter": "Fixed counter 0",
@@ -10,7 +9,6 @@
         "CounterHTOff": "Fixed counter 0"
     },
     {
-        "EventCode": "0x00",
         "UMask": "0x2",
         "BriefDescription": "Core cycles when the thread is not in halt state",
         "Counter": "Fixed counter 1",
@@ -20,7 +18,6 @@
         "CounterHTOff": "Fixed counter 1"
     },
     {
-        "EventCode": "0x00",
         "UMask": "0x2",
         "BriefDescription": "Core cycles when at least one thread on the physical core is not in halt state.",
         "Counter": "Fixed counter 1",
@@ -30,7 +27,6 @@
         "CounterHTOff": "Fixed counter 1"
     },
     {
-        "EventCode": "0x00",
         "UMask": "0x3",
         "BriefDescription": "Reference cycles when the core is not in halt state.",
         "Counter": "Fixed counter 2",
@@ -99,24 +95,24 @@
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
+        "Invert": "1",
         "EventCode": "0x0E",
         "UMask": "0x1",
-        "BriefDescription": "Uops that Resource Allocation Table (RAT) issues to Reservation Station (RS)",
+        "BriefDescription": "Cycles when Resource Allocation Table (RAT) does not issue Uops to Reservation Station (RS) for the thread",
         "Counter": "0,1,2,3",
-        "EventName": "UOPS_ISSUED.ANY",
-        "PublicDescription": "Counts the number of uops that the Resource Allocation Table (RAT) issues to the Reservation Station (RS).",
+        "EventName": "UOPS_ISSUED.STALL_CYCLES",
+        "CounterMask": "1",
+        "PublicDescription": "Counts cycles during which the Resource Allocation Table (RAT) does not issue any Uops to the reservation station (RS) for the current thread.",
         "SampleAfterValue": "2000003",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "Invert": "1",
         "EventCode": "0x0E",
         "UMask": "0x1",
-        "BriefDescription": "Cycles when Resource Allocation Table (RAT) does not issue Uops to Reservation Station (RS) for the thread",
+        "BriefDescription": "Uops that Resource Allocation Table (RAT) issues to Reservation Station (RS)",
         "Counter": "0,1,2,3",
-        "EventName": "UOPS_ISSUED.STALL_CYCLES",
-        "CounterMask": "1",
-        "PublicDescription": "Counts cycles during which the Resource Allocation Table (RAT) does not issue any Uops to the reservation station (RS) for the current thread.",
+        "EventName": "UOPS_ISSUED.ANY",
+        "PublicDescription": "Counts the number of uops that the Resource Allocation Table (RAT) issues to the Reservation Station (RS).",
         "SampleAfterValue": "2000003",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
@@ -126,7 +122,7 @@
         "BriefDescription": "Uops inserted at issue-stage in order to preserve upper bits of vector registers.",
         "Counter": "0,1,2,3",
         "EventName": "UOPS_ISSUED.VECTOR_WIDTH_MISMATCH",
-        "PublicDescription": "Counts the number of Blend Uops issued by the Resource Allocation Table (RAT) to the reservation station (RS) in order to preserve upper bits of vector registers. Starting with the Skylake microarchitecture, these Blend uops are needed since every Intel SSE instruction executed in Dirty Upper State needs to preserve bits 128-255 of the destination register. For more information, refer to Mixing Intel AVX and Intel SSE Code section of the Optimization Guide.",
+        "PublicDescription": "Counts the number of Blend Uops issued by the Resource Allocation Table (RAT) to the reservation station (RS) in order to preserve upper bits of vector registers. Starting with the Skylake microarchitecture, these Blend uops are needed since every Intel SSE instruction executed in Dirty Upper State needs to preserve bits 128-255 of the destination register. For more information, refer to \u201cMixing Intel AVX and Intel SSE Code\u201d section of the Optimization Guide.",
         "SampleAfterValue": "2000003",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
@@ -203,19 +199,19 @@
     {
         "EventCode": "0x3C",
         "UMask": "0x1",
-        "BriefDescription": "Core crystal clock cycles when the thread is unhalted.",
+        "BriefDescription": "Core crystal clock cycles when at least one thread on the physical core is unhalted.",
         "Counter": "0,1,2,3",
-        "EventName": "CPU_CLK_UNHALTED.REF_XCLK",
+        "EventName": "CPU_CLK_UNHALTED.REF_XCLK_ANY",
+        "AnyThread": "1",
         "SampleAfterValue": "2503",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
         "EventCode": "0x3C",
         "UMask": "0x1",
-        "BriefDescription": "Core crystal clock cycles when at least one thread on the physical core is unhalted.",
+        "BriefDescription": "Core crystal clock cycles when the thread is unhalted.",
         "Counter": "0,1,2,3",
-        "EventName": "CPU_CLK_UNHALTED.REF_XCLK_ANY",
-        "AnyThread": "1",
+        "EventName": "CPU_CLK_UNHALTED.REF_XCLK",
         "SampleAfterValue": "2503",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
@@ -248,12 +244,12 @@
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "EventCode": "0x5E",
+        "EventCode": "0x59",
         "UMask": "0x1",
-        "BriefDescription": "Cycles when Reservation Station (RS) is empty for the thread",
+        "BriefDescription": "Cycles where the pipeline is stalled due to serializing operations.",
         "Counter": "0,1,2,3",
-        "EventName": "RS_EVENTS.EMPTY_CYCLES",
-        "PublicDescription": "Counts cycles during which the reservation station (RS) is empty for the thread.; Note: In ST-mode, not active thread should drive 0. This is usually caused by severely costly branch mispredictions, or allocator/FE issues.",
+        "EventName": "PARTIAL_RAT_STALLS.SCOREBOARD",
+        "PublicDescription": "This event counts cycles during which the microcode scoreboard stalls happen.",
         "SampleAfterValue": "2000003",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
@@ -271,6 +267,16 @@
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
+        "EventCode": "0x5E",
+        "UMask": "0x1",
+        "BriefDescription": "Cycles when Reservation Station (RS) is empty for the thread",
+        "Counter": "0,1,2,3",
+        "EventName": "RS_EVENTS.EMPTY_CYCLES",
+        "PublicDescription": "Counts cycles during which the reservation station (RS) is empty for the thread.; Note: In ST-mode, not active thread should drive 0. This is usually caused by severely costly branch mispredictions, or allocator/FE issues.",
+        "SampleAfterValue": "2000003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
         "EventCode": "0x87",
         "UMask": "0x1",
         "BriefDescription": "Stalls caused by changing prefix length of the instruction.",
@@ -361,12 +367,12 @@
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "EventCode": "0xA2",
+        "EventCode": "0xa2",
         "UMask": "0x1",
         "BriefDescription": "Resource-related stall cycles",
         "Counter": "0,1,2,3",
         "EventName": "RESOURCE_STALLS.ANY",
-        "PublicDescription": "Counts resource-related stall cycles. Reasons for stalls can be as follows:a. *any* u-arch structure got full (LB, SB, RS, ROB, BOB, LM, Physical Register Reclaim Table (PRRT), or Physical History Table (PHT) slots).b. *any* u-arch structure got empty (like INT/SIMD FreeLists).c. FPU control word (FPCW), MXCSR.and others. This counts cycles that the pipeline back-end blocked uop delivery from the front-end.",
+        "PublicDescription": "Counts resource-related stall cycles.",
         "SampleAfterValue": "2000003",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
@@ -522,6 +528,17 @@
     {
         "EventCode": "0xA8",
         "UMask": "0x1",
+        "BriefDescription": "Cycles 4 Uops delivered by the LSD, but didn't come from the decoder.",
+        "Counter": "0,1,2,3",
+        "EventName": "LSD.CYCLES_4_UOPS",
+        "CounterMask": "4",
+        "PublicDescription": "Counts the cycles when 4 uops are delivered by the LSD (Loop-stream detector).",
+        "SampleAfterValue": "2000003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
+        "EventCode": "0xA8",
+        "UMask": "0x1",
         "BriefDescription": "Cycles Uops delivered by the LSD, but didn't come from the decoder.",
         "Counter": "0,1,2,3",
         "EventName": "LSD.CYCLES_ACTIVE",
@@ -531,35 +548,35 @@
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "EventCode": "0xA8",
+        "EventCode": "0xB1",
         "UMask": "0x1",
-        "BriefDescription": "Cycles 4 Uops delivered by the LSD, but didn't come from the decoder.",
+        "BriefDescription": "Cycles where at least 4 uops were executed per-thread",
         "Counter": "0,1,2,3",
-        "EventName": "LSD.CYCLES_4_UOPS",
+        "EventName": "UOPS_EXECUTED.CYCLES_GE_4_UOPS_EXEC",
         "CounterMask": "4",
-        "PublicDescription": "Counts the cycles when 4 uops are delivered by the LSD (Loop-stream detector).",
+        "PublicDescription": "Cycles where at least 4 uops were executed per-thread.",
         "SampleAfterValue": "2000003",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
         "EventCode": "0xB1",
         "UMask": "0x1",
-        "BriefDescription": "Counts the number of uops to be executed per-thread each cycle.",
+        "BriefDescription": "Cycles where at least 3 uops were executed per-thread",
         "Counter": "0,1,2,3",
-        "EventName": "UOPS_EXECUTED.THREAD",
-        "PublicDescription": "Number of uops to be executed per-thread each cycle.",
+        "EventName": "UOPS_EXECUTED.CYCLES_GE_3_UOPS_EXEC",
+        "CounterMask": "3",
+        "PublicDescription": "Cycles where at least 3 uops were executed per-thread.",
         "SampleAfterValue": "2000003",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "Invert": "1",
         "EventCode": "0xB1",
         "UMask": "0x1",
-        "BriefDescription": "Counts number of cycles no uops were dispatched to be executed on this thread.",
+        "BriefDescription": "Cycles where at least 2 uops were executed per-thread",
         "Counter": "0,1,2,3",
-        "EventName": "UOPS_EXECUTED.STALL_CYCLES",
-        "CounterMask": "1",
-        "PublicDescription": "Counts cycles during which no uops were dispatched from the Reservation Station (RS) per thread.",
+        "EventName": "UOPS_EXECUTED.CYCLES_GE_2_UOPS_EXEC",
+        "CounterMask": "2",
+        "PublicDescription": "Cycles where at least 2 uops were executed per-thread.",
         "SampleAfterValue": "2000003",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
@@ -575,35 +592,24 @@
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
+        "Invert": "1",
         "EventCode": "0xB1",
         "UMask": "0x1",
-        "BriefDescription": "Cycles where at least 2 uops were executed per-thread",
-        "Counter": "0,1,2,3",
-        "EventName": "UOPS_EXECUTED.CYCLES_GE_2_UOPS_EXEC",
-        "CounterMask": "2",
-        "PublicDescription": "Cycles where at least 2 uops were executed per-thread.",
-        "SampleAfterValue": "2000003",
-        "CounterHTOff": "0,1,2,3,4,5,6,7"
-    },
-    {
-        "EventCode": "0xB1",
-        "UMask": "0x1",
-        "BriefDescription": "Cycles where at least 3 uops were executed per-thread",
+        "BriefDescription": "Counts number of cycles no uops were dispatched to be executed on this thread.",
         "Counter": "0,1,2,3",
-        "EventName": "UOPS_EXECUTED.CYCLES_GE_3_UOPS_EXEC",
-        "CounterMask": "3",
-        "PublicDescription": "Cycles where at least 3 uops were executed per-thread.",
+        "EventName": "UOPS_EXECUTED.STALL_CYCLES",
+        "CounterMask": "1",
+        "PublicDescription": "Counts cycles during which no uops were dispatched from the Reservation Station (RS) per thread.",
         "SampleAfterValue": "2000003",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
         "EventCode": "0xB1",
         "UMask": "0x1",
-        "BriefDescription": "Cycles where at least 4 uops were executed per-thread",
+        "BriefDescription": "Counts the number of uops to be executed per-thread each cycle.",
         "Counter": "0,1,2,3",
-        "EventName": "UOPS_EXECUTED.CYCLES_GE_4_UOPS_EXEC",
-        "CounterMask": "4",
-        "PublicDescription": "Cycles where at least 4 uops were executed per-thread.",
+        "EventName": "UOPS_EXECUTED.THREAD",
+        "PublicDescription": "Number of uops to be executed per-thread each cycle.",
         "SampleAfterValue": "2000003",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
@@ -618,11 +624,12 @@
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
+        "Invert": "1",
         "EventCode": "0xB1",
         "UMask": "0x2",
-        "BriefDescription": "Cycles at least 1 micro-op is executed from any thread on physical core.",
+        "BriefDescription": "Cycles with no micro-ops executed from any thread on physical core.",
         "Counter": "0,1,2,3",
-        "EventName": "UOPS_EXECUTED.CORE_CYCLES_GE_1",
+        "EventName": "UOPS_EXECUTED.CORE_CYCLES_NONE",
         "CounterMask": "1",
         "SampleAfterValue": "2000003",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
@@ -630,10 +637,10 @@
     {
         "EventCode": "0xB1",
         "UMask": "0x2",
-        "BriefDescription": "Cycles at least 2 micro-op is executed from any thread on physical core.",
+        "BriefDescription": "Cycles at least 4 micro-op is executed from any thread on physical core.",
         "Counter": "0,1,2,3",
-        "EventName": "UOPS_EXECUTED.CORE_CYCLES_GE_2",
-        "CounterMask": "2",
+        "EventName": "UOPS_EXECUTED.CORE_CYCLES_GE_4",
+        "CounterMask": "4",
         "SampleAfterValue": "2000003",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
@@ -650,20 +657,19 @@
     {
         "EventCode": "0xB1",
         "UMask": "0x2",
-        "BriefDescription": "Cycles at least 4 micro-op is executed from any thread on physical core.",
+        "BriefDescription": "Cycles at least 2 micro-op is executed from any thread on physical core.",
         "Counter": "0,1,2,3",
-        "EventName": "UOPS_EXECUTED.CORE_CYCLES_GE_4",
-        "CounterMask": "4",
+        "EventName": "UOPS_EXECUTED.CORE_CYCLES_GE_2",
+        "CounterMask": "2",
         "SampleAfterValue": "2000003",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "Invert": "1",
         "EventCode": "0xB1",
         "UMask": "0x2",
-        "BriefDescription": "Cycles with no micro-ops executed from any thread on physical core.",
+        "BriefDescription": "Cycles at least 1 micro-op is executed from any thread on physical core.",
         "Counter": "0,1,2,3",
-        "EventName": "UOPS_EXECUTED.CORE_CYCLES_NONE",
+        "EventName": "UOPS_EXECUTED.CORE_CYCLES_GE_1",
         "CounterMask": "1",
         "SampleAfterValue": "2000003",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
@@ -725,12 +731,14 @@
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
+        "Invert": "1",
         "EventCode": "0xC2",
         "UMask": "0x2",
-        "BriefDescription": "Retirement slots used.",
+        "BriefDescription": "Cycles with less than 10 actually retired uops.",
         "Counter": "0,1,2,3",
-        "EventName": "UOPS_RETIRED.RETIRE_SLOTS",
-        "PublicDescription": "Counts the retirement slots used.",
+        "EventName": "UOPS_RETIRED.TOTAL_CYCLES",
+        "CounterMask": "10",
+        "PublicDescription": "Number of cycles using always true condition (uops_ret < 16) applied to non PEBS uops retired event.",
         "SampleAfterValue": "2000003",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
@@ -742,19 +750,17 @@
         "Counter": "0,1,2,3",
         "EventName": "UOPS_RETIRED.STALL_CYCLES",
         "CounterMask": "1",
-        "PublicDescription": "This is a non-precise version (that is, does not use PEBS) of the event that counts cycles without actually retired uops.",
+        "PublicDescription": "This event counts cycles without actually retired uops.",
         "SampleAfterValue": "2000003",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
-        "Invert": "1",
         "EventCode": "0xC2",
         "UMask": "0x2",
-        "BriefDescription": "Cycles with less than 10 actually retired uops.",
+        "BriefDescription": "Retirement slots used.",
         "Counter": "0,1,2,3",
-        "EventName": "UOPS_RETIRED.TOTAL_CYCLES",
-        "CounterMask": "10",
-        "PublicDescription": "Number of cycles using always true condition (uops_ret < 16) applied to non PEBS uops retired event.",
+        "EventName": "UOPS_RETIRED.RETIRE_SLOTS",
+        "PublicDescription": "Counts the retirement slots used.",
         "SampleAfterValue": "2000003",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
@@ -766,6 +772,7 @@
         "Counter": "0,1,2,3",
         "EventName": "MACHINE_CLEARS.COUNT",
         "CounterMask": "1",
+        "PublicDescription": "Number of machine clears (nukes) of any type.",
         "SampleAfterValue": "100003",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
@@ -841,11 +848,12 @@
     {
         "EventCode": "0xC4",
         "UMask": "0x10",
-        "BriefDescription": "Not taken branch instructions retired.",
+        "BriefDescription": "Counts all not taken macro branch instructions retired.",
+        "PEBS": "1",
         "Counter": "0,1,2,3",
         "EventName": "BR_INST_RETIRED.NOT_TAKEN",
         "Errata": "SKL091",
-        "PublicDescription": "This is a non-precise version (that is, does not use PEBS) of the event that counts not taken branch instructions retired.",
+        "PublicDescription": "This is a precise version (that is, uses PEBS) of the event that counts not taken branch instructions retired.",
         "SampleAfterValue": "400009",
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
@@ -919,7 +927,7 @@
     {
         "EventCode": "0xC5",
         "UMask": "0x20",
-        "BriefDescription": "Number of near branch instructions retired that were mispredicted and taken. ",
+        "BriefDescription": "Number of near branch instructions retired that were mispredicted and taken.",
         "PEBS": "1",
         "Counter": "0,1,2,3",
         "EventName": "BR_MISP_RETIRED.NEAR_TAKEN",
@@ -938,6 +946,15 @@
         "CounterHTOff": "0,1,2,3,4,5,6,7"
     },
     {
+        "EventCode": "0xCC",
+        "UMask": "0x40",
+        "BriefDescription": "Number of retired PAUSE instructions (that do not end up with a VMExit to the VMM; TSX aborted Instructions may be counted). This event is not supported on first SKL and KBL products.",
+        "Counter": "0,1,2,3",
+        "EventName": "ROB_MISC_EVENTS.PAUSE_INST",
+        "SampleAfterValue": "2000003",
+        "CounterHTOff": "0,1,2,3,4,5,6,7"
+    },
+    {
         "EventCode": "0xE6",
         "UMask": "0x1",
         "BriefDescription": "Counts the total number when the front end is resteered, mainly when the BPU cannot provide a correct prediction and this is corrected by other branch handling mechanisms at the front end.",
diff --git a/tools/perf/pmu-events/arch/x86/skylakex/skx-metrics.json b/tools/perf/pmu-events/arch/x86/skylakex/skx-metrics.json
index 71e9737f4614..56e03ba771f4 100644
--- a/tools/perf/pmu-events/arch/x86/skylakex/skx-metrics.json
+++ b/tools/perf/pmu-events/arch/x86/skylakex/skx-metrics.json
@@ -1,164 +1,394 @@
 [
     {
-        "BriefDescription": "Instructions Per Cycle (per logical thread)",
+        "MetricExpr": "IDQ_UOPS_NOT_DELIVERED.CORE / (4 * cycles)",
+        "PublicDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend. Frontend denotes the first part of the processor core responsible to fetch operations that are executed later on by the Backend part. Within the Frontend; a branch predictor predicts the next address to fetch; cache-lines are fetched from the memory subsystem; parsed into instructions; and lastly decoded into micro-ops (uops). Ideally the Frontend can issue 4 uops every cycle to the Backend. Frontend Bound denotes unutilized issue-slots when there is no Backend stall; i.e. bubbles where Frontend delivered no uops while Backend could have accepted them. For example; stalls due to instruction-cache misses would be categorized under Frontend Bound.",
+        "BriefDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend",
+        "MetricGroup": "TopdownL1",
+        "MetricName": "Frontend_Bound"
+    },
+    {
+        "MetricExpr": "IDQ_UOPS_NOT_DELIVERED.CORE / (4 * (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )))",
+        "PublicDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend. Frontend denotes the first part of the processor core responsible to fetch operations that are executed later on by the Backend part. Within the Frontend; a branch predictor predicts the next address to fetch; cache-lines are fetched from the memory subsystem; parsed into instructions; and lastly decoded into micro-ops (uops). Ideally the Frontend can issue 4 uops every cycle to the Backend. Frontend Bound denotes unutilized issue-slots when there is no Backend stall; i.e. bubbles where Frontend delivered no uops while Backend could have accepted them. For example; stalls due to instruction-cache misses would be categorized under Frontend Bound. SMT version; use when SMT is enabled and measuring per logical CPU.",
+        "BriefDescription": "This category represents fraction of slots where the processor's Frontend undersupplies its Backend. SMT version; use when SMT is enabled and measuring per logical CPU.",
+        "MetricGroup": "TopdownL1_SMT",
+        "MetricName": "Frontend_Bound_SMT"
+    },
+    {
+        "MetricExpr": "( UOPS_ISSUED.ANY - UOPS_RETIRED.RETIRE_SLOTS + 4 * INT_MISC.RECOVERY_CYCLES ) / (4 * cycles)",
+        "PublicDescription": "This category represents fraction of slots wasted due to incorrect speculations. This include slots used to issue uops that do not eventually get retired and slots for which the issue-pipeline was blocked due to recovery from earlier incorrect speculation. For example; wasted work due to miss-predicted branches are categorized under Bad Speculation category. Incorrect data speculation followed by Memory Ordering Nukes is another example.",
+        "BriefDescription": "This category represents fraction of slots wasted due to incorrect speculations",
+        "MetricGroup": "TopdownL1",
+        "MetricName": "Bad_Speculation"
+    },
+    {
+        "MetricExpr": "( UOPS_ISSUED.ANY - UOPS_RETIRED.RETIRE_SLOTS + 4 * (( INT_MISC.RECOVERY_CYCLES_ANY / 2 )) ) / (4 * (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )))",
+        "PublicDescription": "This category represents fraction of slots wasted due to incorrect speculations. This include slots used to issue uops that do not eventually get retired and slots for which the issue-pipeline was blocked due to recovery from earlier incorrect speculation. For example; wasted work due to miss-predicted branches are categorized under Bad Speculation category. Incorrect data speculation followed by Memory Ordering Nukes is another example. SMT version; use when SMT is enabled and measuring per logical CPU.",
+        "BriefDescription": "This category represents fraction of slots wasted due to incorrect speculations. SMT version; use when SMT is enabled and measuring per logical CPU.",
+        "MetricGroup": "TopdownL1_SMT",
+        "MetricName": "Bad_Speculation_SMT"
+    },
+    {
+        "MetricExpr": "1 - ( (IDQ_UOPS_NOT_DELIVERED.CORE / (4 * cycles)) + (( UOPS_ISSUED.ANY - UOPS_RETIRED.RETIRE_SLOTS + 4 * INT_MISC.RECOVERY_CYCLES ) / (4 * cycles)) + (UOPS_RETIRED.RETIRE_SLOTS / (4 * cycles)) )",
+        "PublicDescription": "This category represents fraction of slots where no uops are being delivered due to a lack of required resources for accepting new uops in the Backend. Backend is the portion of the processor core where the out-of-order scheduler dispatches ready uops into their respective execution units; and once completed these uops get retired according to program order. For example; stalls due to data-cache misses or stalls due to the divider unit being overloaded are both categorized under Backend Bound. Backend Bound is further divided into two main categories: Memory Bound and Core Bound.",
+        "BriefDescription": "This category represents fraction of slots where no uops are being delivered due to a lack of required resources for accepting new uops in the Backend",
+        "MetricGroup": "TopdownL1",
+        "MetricName": "Backend_Bound"
+    },
+    {
+        "MetricExpr": "1 - ( (IDQ_UOPS_NOT_DELIVERED.CORE / (4 * (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )))) + (( UOPS_ISSUED.ANY - UOPS_RETIRED.RETIRE_SLOTS + 4 * (( INT_MISC.RECOVERY_CYCLES_ANY / 2 )) ) / (4 * (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )))) + (UOPS_RETIRED.RETIRE_SLOTS / (4 * (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )))) )",
+        "PublicDescription": "This category represents fraction of slots where no uops are being delivered due to a lack of required resources for accepting new uops in the Backend. Backend is the portion of the processor core where the out-of-order scheduler dispatches ready uops into their respective execution units; and once completed these uops get retired according to program order. For example; stalls due to data-cache misses or stalls due to the divider unit being overloaded are both categorized under Backend Bound. Backend Bound is further divided into two main categories: Memory Bound and Core Bound. SMT version; use when SMT is enabled and measuring per logical CPU.",
+        "BriefDescription": "This category represents fraction of slots where no uops are being delivered due to a lack of required resources for accepting new uops in the Backend. SMT version; use when SMT is enabled and measuring per logical CPU.",
+        "MetricGroup": "TopdownL1_SMT",
+        "MetricName": "Backend_Bound_SMT"
+    },
+    {
+        "MetricExpr": "UOPS_RETIRED.RETIRE_SLOTS / (4 * cycles)",
+        "PublicDescription": "This category represents fraction of slots utilized by useful work i.e. issued uops that eventually get retired. Ideally; all pipeline slots would be attributed to the Retiring category.  Retiring of 100% would indicate the maximum 4 uops retired per cycle has been achieved.  Maximizing Retiring typically increases the Instruction-Per-Cycle metric. Note that a high Retiring value does not necessary mean there is no room for more performance.  For example; Microcode assists are categorized under Retiring. They hurt performance and can often be avoided. ",
+        "BriefDescription": "This category represents fraction of slots utilized by useful work i.e. issued uops that eventually get retired",
+        "MetricGroup": "TopdownL1",
+        "MetricName": "Retiring"
+    },
+    {
+        "MetricExpr": "UOPS_RETIRED.RETIRE_SLOTS / (4 * (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )))",
+        "PublicDescription": "This category represents fraction of slots utilized by useful work i.e. issued uops that eventually get retired. Ideally; all pipeline slots would be attributed to the Retiring category.  Retiring of 100% would indicate the maximum 4 uops retired per cycle has been achieved.  Maximizing Retiring typically increases the Instruction-Per-Cycle metric. Note that a high Retiring value does not necessary mean there is no room for more performance.  For example; Microcode assists are categorized under Retiring. They hurt performance and can often be avoided. SMT version; use when SMT is enabled and measuring per logical CPU.",
+        "BriefDescription": "This category represents fraction of slots utilized by useful work i.e. issued uops that eventually get retired. SMT version; use when SMT is enabled and measuring per logical CPU.",
+        "MetricGroup": "TopdownL1_SMT",
+        "MetricName": "Retiring_SMT"
+    },
+    {
         "MetricExpr": "INST_RETIRED.ANY / CPU_CLK_UNHALTED.THREAD",
+        "BriefDescription": "Instructions Per Cycle (per logical thread)",
         "MetricGroup": "TopDownL1",
         "MetricName": "IPC"
     },
     {
-        "BriefDescription": "Uops Per Instruction",
         "MetricExpr": "UOPS_RETIRED.RETIRE_SLOTS / INST_RETIRED.ANY",
-        "MetricGroup": "Pipeline",
+        "BriefDescription": "Uops Per Instruction",
+        "MetricGroup": "Pipeline;Retiring",
         "MetricName": "UPI"
     },
     {
-        "BriefDescription": "Rough Estimation of fraction of fetched lines bytes that were likely consumed by program instructions",
-        "MetricExpr": "min( 1 , UOPS_ISSUED.ANY / ((UOPS_RETIRED.RETIRE_SLOTS / INST_RETIRED.ANY) * 64 * ( ICACHE_64B.IFTAG_HIT + ICACHE_64B.IFTAG_MISS ) / 4.1) )",
-        "MetricGroup": "Frontend",
+        "MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.NEAR_TAKEN",
+        "BriefDescription": "Instruction per taken branch",
+        "MetricGroup": "Branches;PGO",
+        "MetricName": "IpTB"
+    },
+    {
+        "MetricExpr": "BR_INST_RETIRED.ALL_BRANCHES / BR_INST_RETIRED.NEAR_TAKEN",
+        "BriefDescription": "Branch instructions per taken branch. ",
+        "MetricGroup": "Branches;PGO",
+        "MetricName": "BpTB"
+    },
+    {
+        "MetricExpr": "min( 1 , UOPS_ISSUED.ANY / ( (UOPS_RETIRED.RETIRE_SLOTS / INST_RETIRED.ANY) * 64 * ( ICACHE_64B.IFTAG_HIT + ICACHE_64B.IFTAG_MISS ) / 4.1 ) )",
+        "BriefDescription": "Rough Estimation of fraction of fetched lines bytes that were likely (includes speculatively fetches) consumed by program instructions",
+        "MetricGroup": "PGO",
         "MetricName": "IFetch_Line_Utilization"
     },
     {
-        "BriefDescription": "Fraction of Uops delivered by the DSB (aka Decoded Icache; or Uop Cache)",
-        "MetricExpr": "IDQ.DSB_UOPS / ( IDQ.DSB_UOPS + LSD.UOPS + IDQ.MITE_UOPS + IDQ.MS_UOPS )",
-        "MetricGroup": "DSB; Frontend_Bandwidth",
+        "MetricExpr": "IDQ.DSB_UOPS / (( IDQ.DSB_UOPS + IDQ.MITE_UOPS + IDQ.MS_UOPS ))",
+        "BriefDescription": "Fraction of Uops delivered by the DSB (aka Decoded ICache; or Uop Cache)",
+        "MetricGroup": "DSB;Frontend_Bandwidth",
         "MetricName": "DSB_Coverage"
     },
     {
-        "BriefDescription": "Cycles Per Instruction (threaded)",
         "MetricExpr": "1 / (INST_RETIRED.ANY / cycles)",
+        "BriefDescription": "Cycles Per Instruction (threaded)",
         "MetricGroup": "Pipeline;Summary",
         "MetricName": "CPI"
     },
     {
-        "BriefDescription": "Per-thread actual clocks when the logical processor is active. This is called 'Clockticks' in VTune.",
         "MetricExpr": "CPU_CLK_UNHALTED.THREAD",
+        "BriefDescription": "Per-thread actual clocks when the logical processor is active.",
         "MetricGroup": "Summary",
         "MetricName": "CLKS"
     },
     {
-        "BriefDescription": "Total issue-pipeline slots",
-        "MetricExpr": "4*(( CPU_CLK_UNHALTED.THREAD_ANY / 2 ) if #SMT_on else cycles)",
+        "MetricExpr": "4 * cycles",
+        "BriefDescription": "Total issue-pipeline slots (per core)",
         "MetricGroup": "TopDownL1",
         "MetricName": "SLOTS"
     },
     {
-        "BriefDescription": "Total number of retired Instructions",
+        "MetricExpr": "4 * (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) ))",
+        "BriefDescription": "Total issue-pipeline slots (per core)",
+        "MetricGroup": "TopDownL1_SMT",
+        "MetricName": "SLOTS_SMT"
+    },
+    {
+        "MetricExpr": "INST_RETIRED.ANY / MEM_INST_RETIRED.ALL_LOADS",
+        "BriefDescription": "Instructions per Load (lower number means loads are more frequent)",
+        "MetricGroup": "Instruction_Type;L1_Bound",
+        "MetricName": "IpL"
+    },
+    {
+        "MetricExpr": "INST_RETIRED.ANY / MEM_INST_RETIRED.ALL_STORES",
+        "BriefDescription": "Instructions per Store",
+        "MetricGroup": "Instruction_Type;Store_Bound",
+        "MetricName": "IpS"
+    },
+    {
+        "MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.ALL_BRANCHES",
+        "BriefDescription": "Instructions per Branch",
+        "MetricGroup": "Branches;Instruction_Type;Port_5;Port_6",
+        "MetricName": "IpB"
+    },
+    {
+        "MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.NEAR_CALL",
+        "BriefDescription": "Instruction per (near) call",
+        "MetricGroup": "Branches",
+        "MetricName": "IpCall"
+    },
+    {
         "MetricExpr": "INST_RETIRED.ANY",
+        "BriefDescription": "Total number of retired Instructions",
         "MetricGroup": "Summary",
         "MetricName": "Instructions"
     },
     {
+        "MetricExpr": "INST_RETIRED.ANY / cycles",
         "BriefDescription": "Instructions Per Cycle (per physical core)",
-        "MetricExpr": "INST_RETIRED.ANY / (( CPU_CLK_UNHALTED.THREAD_ANY / 2 ) if #SMT_on else cycles)",
         "MetricGroup": "SMT",
         "MetricName": "CoreIPC"
     },
     {
+        "MetricExpr": "INST_RETIRED.ANY / (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) ))",
+        "BriefDescription": "Instructions Per Cycle (per physical core)",
+        "MetricGroup": "SMT",
+        "MetricName": "CoreIPC_SMT"
+    },
+    {
+        "MetricExpr": "(( 1 * ( FP_ARITH_INST_RETIRED.SCALAR_SINGLE + FP_ARITH_INST_RETIRED.SCALAR_DOUBLE ) + 2 * FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE + 4 * ( FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE + FP_ARITH_INST_RETIRED.256B_PACKED_DOUBLE ) + 8 * ( FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE + FP_ARITH_INST_RETIRED.512B_PACKED_DOUBLE ) + 16 * FP_ARITH_INST_RETIRED.512B_PACKED_SINGLE )) / cycles",
+        "BriefDescription": "Floating Point Operations Per Cycle",
+        "MetricGroup": "FLOPS",
+        "MetricName": "FLOPc"
+    },
+    {
+        "MetricExpr": "(( 1 * ( FP_ARITH_INST_RETIRED.SCALAR_SINGLE + FP_ARITH_INST_RETIRED.SCALAR_DOUBLE ) + 2 * FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE + 4 * ( FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE + FP_ARITH_INST_RETIRED.256B_PACKED_DOUBLE ) + 8 * ( FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE + FP_ARITH_INST_RETIRED.512B_PACKED_DOUBLE ) + 16 * FP_ARITH_INST_RETIRED.512B_PACKED_SINGLE )) / (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) ))",
+        "BriefDescription": "Floating Point Operations Per Cycle",
+        "MetricGroup": "FLOPS_SMT",
+        "MetricName": "FLOPc_SMT"
+    },
+    {
+        "MetricExpr": "UOPS_EXECUTED.THREAD / (( UOPS_EXECUTED.CORE_CYCLES_GE_1 / 2 ) if #SMT_on else UOPS_EXECUTED.CORE_CYCLES_GE_1)",
         "BriefDescription": "Instruction-Level-Parallelism (average number of uops executed when there is at least 1 uop executed)",
-        "MetricExpr": "UOPS_EXECUTED.THREAD / (( UOPS_EXECUTED.CORE_CYCLES_GE_1 / 2) if #SMT_on else UOPS_EXECUTED.CORE_CYCLES_GE_1)",
         "MetricGroup": "Pipeline;Ports_Utilization",
         "MetricName": "ILP"
     },
     {
-        "BriefDescription": "Average Branch Address Clear Cost (fraction of cycles)",
-        "MetricExpr": "2* (( RS_EVENTS.EMPTY_CYCLES - ICACHE_16B.IFDATA_STALL  - ICACHE_64B.IFTAG_STALL ) / RS_EVENTS.EMPTY_END)",
-        "MetricGroup": "Unknown_Branches",
-        "MetricName": "BAClear_Cost"
+        "MetricExpr": "( ((BR_MISP_RETIRED.ALL_BRANCHES / ( BR_MISP_RETIRED.ALL_BRANCHES + MACHINE_CLEARS.COUNT )) * (( UOPS_ISSUED.ANY - UOPS_RETIRED.RETIRE_SLOTS + 4 * INT_MISC.RECOVERY_CYCLES ) / (4 * cycles))) + (4 * IDQ_UOPS_NOT_DELIVERED.CYCLES_0_UOPS_DELIV.CORE / (4 * cycles)) * (( INT_MISC.CLEAR_RESTEER_CYCLES + 9 * BACLEARS.ANY ) / cycles) / (4 * IDQ_UOPS_NOT_DELIVERED.CYCLES_0_UOPS_DELIV.CORE / (4 * cycles)) ) * (4 * cycles) / BR_MISP_RETIRED.ALL_BRANCHES",
+        "BriefDescription": "Branch Misprediction Cost: Fraction of TopDown slots wasted per branch misprediction (jeclear and baclear)",
+        "MetricGroup": "Branch_Mispredicts",
+        "MetricName": "Branch_Misprediction_Cost"
+    },
+    {
+        "MetricExpr": "( ((BR_MISP_RETIRED.ALL_BRANCHES / ( BR_MISP_RETIRED.ALL_BRANCHES + MACHINE_CLEARS.COUNT )) * (( UOPS_ISSUED.ANY - UOPS_RETIRED.RETIRE_SLOTS + 4 * (( INT_MISC.RECOVERY_CYCLES_ANY / 2 )) ) / (4 * (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) ))))) + (4 * IDQ_UOPS_NOT_DELIVERED.CYCLES_0_UOPS_DELIV.CORE / (4 * (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )))) * (( INT_MISC.CLEAR_RESTEER_CYCLES + 9 * BACLEARS.ANY ) / cycles) / (4 * IDQ_UOPS_NOT_DELIVERED.CYCLES_0_UOPS_DELIV.CORE / (4 * (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )))) ) * (4 * (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) ))) / BR_MISP_RETIRED.ALL_BRANCHES",
+        "BriefDescription": "Branch Misprediction Cost: Fraction of TopDown slots wasted per branch misprediction (jeclear and baclear)",
+        "MetricGroup": "Branch_Mispredicts_SMT",
+        "MetricName": "Branch_Misprediction_Cost_SMT"
     },
     {
+        "MetricExpr": "INST_RETIRED.ANY / BR_MISP_RETIRED.ALL_BRANCHES",
+        "BriefDescription": "Number of Instructions per non-speculative Branch Misprediction (JEClear)",
+        "MetricGroup": "Branch_Mispredicts",
+        "MetricName": "IpMispredict"
+    },
+    {
+        "MetricExpr": "( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )",
         "BriefDescription": "Core actual clocks when any thread is active on the physical core",
-        "MetricExpr": "( CPU_CLK_UNHALTED.THREAD_ANY / 2 ) if #SMT_on else CPU_CLK_UNHALTED.THREAD",
         "MetricGroup": "SMT",
         "MetricName": "CORE_CLKS"
     },
     {
-        "BriefDescription": "Actual Average Latency for L1 data-cache miss demand loads",
         "MetricExpr": "L1D_PEND_MISS.PENDING / ( MEM_LOAD_RETIRED.L1_MISS + MEM_LOAD_RETIRED.FB_HIT )",
+        "BriefDescription": "Actual Average Latency for L1 data-cache miss demand loads (in core cycles)",
         "MetricGroup": "Memory_Bound;Memory_Lat",
         "MetricName": "Load_Miss_Real_Latency"
     },
     {
-        "BriefDescription": "Memory-Level-Parallelism (average number of L1 miss demand load when there is at least 1 such miss)",
-        "MetricExpr": "L1D_PEND_MISS.PENDING / (( L1D_PEND_MISS.PENDING_CYCLES_ANY / 2) if #SMT_on else L1D_PEND_MISS.PENDING_CYCLES)",
+        "MetricExpr": "L1D_PEND_MISS.PENDING / L1D_PEND_MISS.PENDING_CYCLES",
+        "BriefDescription": "Memory-Level-Parallelism (average number of L1 miss demand load when there is at least one such miss. Per-thread)",
         "MetricGroup": "Memory_Bound;Memory_BW",
         "MetricName": "MLP"
     },
     {
+        "MetricExpr": "( ITLB_MISSES.WALK_PENDING + DTLB_LOAD_MISSES.WALK_PENDING + DTLB_STORE_MISSES.WALK_PENDING + EPT.WALK_PENDING ) / ( 2 * cycles )",
         "BriefDescription": "Utilization of the core's Page Walker(s) serving STLB misses triggered by instruction/Load/Store accesses",
-        "MetricExpr": "( ITLB_MISSES.WALK_PENDING + DTLB_LOAD_MISSES.WALK_PENDING + DTLB_STORE_MISSES.WALK_PENDING + EPT.WALK_PENDING ) / ( 2 * (( CPU_CLK_UNHALTED.THREAD_ANY / 2 ) if #SMT_on else cycles) )",
         "MetricGroup": "TLB",
         "MetricName": "Page_Walks_Utilization"
     },
     {
-        "BriefDescription": "Average CPU Utilization",
+        "MetricExpr": "( ITLB_MISSES.WALK_PENDING + DTLB_LOAD_MISSES.WALK_PENDING + DTLB_STORE_MISSES.WALK_PENDING + EPT.WALK_PENDING ) / ( 2 * (( ( CPU_CLK_UNHALTED.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )) )",
+        "BriefDescription": "Utilization of the core's Page Walker(s) serving STLB misses triggered by instruction/Load/Store accesses",
+        "MetricGroup": "TLB_SMT",
+        "MetricName": "Page_Walks_Utilization_SMT"
+    },
+    {
+        "MetricExpr": "64 * L1D.REPLACEMENT / 1000000000 / duration_time",
+        "BriefDescription": "Average data fill bandwidth to the L1 data cache [GB / sec]",
+        "MetricGroup": "Memory_BW",
+        "MetricName": "L1D_Cache_Fill_BW"
+    },
+    {
+        "MetricExpr": "64 * L2_LINES_IN.ALL / 1000000000 / duration_time",
+        "BriefDescription": "Average data fill bandwidth to the L2 cache [GB / sec]",
+        "MetricGroup": "Memory_BW",
+        "MetricName": "L2_Cache_Fill_BW"
+    },
+    {
+        "MetricExpr": "64 * LONGEST_LAT_CACHE.MISS / 1000000000 / duration_time",
+        "BriefDescription": "Average per-core data fill bandwidth to the L3 cache [GB / sec]",
+        "MetricGroup": "Memory_BW",
+        "MetricName": "L3_Cache_Fill_BW"
+    },
+    {
+        "MetricExpr": "64 * OFFCORE_REQUESTS.ALL_REQUESTS / 1000000000 / duration_time",
+        "BriefDescription": "Average per-core data fill bandwidth to the L3 cache [GB / sec]",
+        "MetricGroup": "Memory_BW",
+        "MetricName": "L3_Cache_Access_BW"
+    },
+    {
+        "MetricExpr": "1000 * MEM_LOAD_RETIRED.L1_MISS / INST_RETIRED.ANY",
+        "BriefDescription": "L1 cache true misses per kilo instruction for retired demand loads",
+        "MetricGroup": "Cache_Misses;",
+        "MetricName": "L1MPKI"
+    },
+    {
+        "MetricExpr": "1000 * MEM_LOAD_RETIRED.L2_MISS / INST_RETIRED.ANY",
+        "BriefDescription": "L2 cache true misses per kilo instruction for retired demand loads",
+        "MetricGroup": "Cache_Misses;",
+        "MetricName": "L2MPKI"
+    },
+    {
+        "MetricExpr": "1000 * L2_RQSTS.MISS / INST_RETIRED.ANY",
+        "BriefDescription": "L2 cache misses per kilo instruction for all request types (including speculative)",
+        "MetricGroup": "Cache_Misses;",
+        "MetricName": "L2MPKI_All"
+    },
+    {
+        "MetricExpr": "1000 * ( L2_RQSTS.REFERENCES - L2_RQSTS.MISS ) / INST_RETIRED.ANY",
+        "BriefDescription": "L2 cache hits per kilo instruction for all request types (including speculative)",
+        "MetricGroup": "Cache_Misses;",
+        "MetricName": "L2HPKI_All"
+    },
+    {
+        "MetricExpr": "1000 * MEM_LOAD_RETIRED.L3_MISS / INST_RETIRED.ANY",
+        "BriefDescription": "L3 cache true misses per kilo instruction for retired demand loads",
+        "MetricGroup": "Cache_Misses;",
+        "MetricName": "L3MPKI"
+    },
+    {
         "MetricExpr": "CPU_CLK_UNHALTED.REF_TSC / msr@tsc@",
+        "BriefDescription": "Average CPU Utilization",
         "MetricGroup": "Summary",
         "MetricName": "CPU_Utilization"
     },
     {
+        "MetricExpr": "( (( 1 * ( FP_ARITH_INST_RETIRED.SCALAR_SINGLE + FP_ARITH_INST_RETIRED.SCALAR_DOUBLE ) + 2 * FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE + 4 * ( FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE + FP_ARITH_INST_RETIRED.256B_PACKED_DOUBLE ) + 8 * ( FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE + FP_ARITH_INST_RETIRED.512B_PACKED_DOUBLE ) + 16 * FP_ARITH_INST_RETIRED.512B_PACKED_SINGLE )) / 1000000000 ) / duration_time",
         "BriefDescription": "Giga Floating Point Operations Per Second",
-        "MetricExpr": "(( 1*( FP_ARITH_INST_RETIRED.SCALAR_SINGLE + FP_ARITH_INST_RETIRED.SCALAR_DOUBLE ) + 2* FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE + 4*( FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE + FP_ARITH_INST_RETIRED.256B_PACKED_DOUBLE ) + 8* FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE )) / 1000000000 / duration_time",
         "MetricGroup": "FLOPS;Summary",
         "MetricName": "GFLOPs"
     },
     {
-        "BriefDescription": "Average Frequency Utilization relative nominal frequency",
         "MetricExpr": "CPU_CLK_UNHALTED.THREAD / CPU_CLK_UNHALTED.REF_TSC",
+        "BriefDescription": "Average Frequency Utilization relative nominal frequency",
         "MetricGroup": "Power",
         "MetricName": "Turbo_Utilization"
     },
     {
-        "BriefDescription": "Fraction of cycles where both hardware threads were active",
         "MetricExpr": "1 - CPU_CLK_THREAD_UNHALTED.ONE_THREAD_ACTIVE / ( CPU_CLK_THREAD_UNHALTED.REF_XCLK_ANY / 2 ) if #SMT_on else 0",
+        "BriefDescription": "Fraction of cycles where both hardware threads were active",
         "MetricGroup": "SMT;Summary",
         "MetricName": "SMT_2T_Utilization"
     },
     {
-        "BriefDescription": "Fraction of cycles spent in Kernel mode",
         "MetricExpr": "CPU_CLK_UNHALTED.REF_TSC:u / CPU_CLK_UNHALTED.REF_TSC",
+        "BriefDescription": "Fraction of cycles spent in Kernel mode",
         "MetricGroup": "Summary",
         "MetricName": "Kernel_Utilization"
     },
     {
-        "BriefDescription": "C3 residency percent per core",
+        "MetricExpr": "( 64 * ( uncore_imc@cas_count_read@ + uncore_imc@cas_count_write@ ) / 1000000000 ) / duration_time",
+        "BriefDescription": "Average external Memory Bandwidth Use for reads and writes [GB / sec]",
+        "MetricGroup": "Memory_BW",
+        "MetricName": "DRAM_BW_Use"
+    },
+    {
+        "MetricExpr": "1000000000 * ( cha@event\\=0x36\\\\\\,umask\\=0x21@ / cha@event\\=0x35\\\\\\,umask\\=0x21@ ) / ( cha_0@event\\=0x0@ / duration_time )",
+        "BriefDescription": "Average latency of data read request to external memory (in nanoseconds). Accounts for demand loads and L1/L2 prefetches",
+        "MetricGroup": "Memory_Lat",
+        "MetricName": "DRAM_Read_Latency"
+    },
+    {
+        "MetricExpr": "cha@event\\=0x36\\\\\\,umask\\=0x21@ / cha@event\\=0x36\\\\\\,umask\\=0x21\\\\\\,thresh\\=1@",
+        "BriefDescription": "Average number of parallel data read requests to external memory. Accounts for demand loads and L1/L2 prefetches",
+        "MetricGroup": "Memory_BW",
+        "MetricName": "DRAM_Parallel_Reads"
+    },
+    {
+        "MetricExpr": "( 1000000000 * ( imc@event\\=0xe0\\\\\\,umask\\=0x1@ / imc@event\\=0xe3@ ) / imc_0@event\\=0x0@ ) if 1 if 0 == 1 else 0 else 0",
+        "BriefDescription": "Average latency of data read request to external 3D X-Point memory [in nanoseconds]. Accounts for demand loads and L1/L2 data-read prefetches",
+        "MetricGroup": "Memory_Lat",
+        "MetricName": "MEM_PMM_Read_Latency"
+    },
+    {
+        "MetricExpr": "( ( 64 * imc@event\\=0xe3@ / 1000000000 ) / duration_time ) if 1 if 0 == 1 else 0 else 0",
+        "BriefDescription": "Average 3DXP Memory Bandwidth Use for reads [GB / sec]",
+        "MetricGroup": "Memory_BW",
+        "MetricName": "PMM_Read_BW"
+    },
+    {
+        "MetricExpr": "( ( 64 * imc@event\\=0xe7@ / 1000000000 ) / duration_time ) if 1 if 0 == 1 else 0 else 0",
+        "BriefDescription": "Average 3DXP Memory Bandwidth Use for Writes [GB / sec]",
+        "MetricGroup": "Memory_BW",
+        "MetricName": "PMM_Write_BW"
+    },
+    {
+        "MetricExpr": "cha_0@event\\=0x0@",
+        "BriefDescription": "Socket actual clocks when any core is active on that socket",
+        "MetricGroup": "",
+        "MetricName": "Socket_CLKS"
+    },
+    {
         "MetricExpr": "(cstate_core@c3\\-residency@ / msr@tsc@) * 100",
         "MetricGroup": "Power",
+        "BriefDescription": "C3 residency percent per core",
         "MetricName": "C3_Core_Residency"
     },
     {
-        "BriefDescription": "C6 residency percent per core",
         "MetricExpr": "(cstate_core@c6\\-residency@ / msr@tsc@) * 100",
         "MetricGroup": "Power",
+        "BriefDescription": "C6 residency percent per core",
         "MetricName": "C6_Core_Residency"
     },
     {
-        "BriefDescription": "C7 residency percent per core",
         "MetricExpr": "(cstate_core@c7\\-residency@ / msr@tsc@) * 100",
         "MetricGroup": "Power",
+        "BriefDescription": "C7 residency percent per core",
         "MetricName": "C7_Core_Residency"
     },
     {
-        "BriefDescription": "C2 residency percent per package",
         "MetricExpr": "(cstate_pkg@c2\\-residency@ / msr@tsc@) * 100",
         "MetricGroup": "Power",
+        "BriefDescription": "C2 residency percent per package",
         "MetricName": "C2_Pkg_Residency"
     },
     {
-        "BriefDescription": "C3 residency percent per package",
         "MetricExpr": "(cstate_pkg@c3\\-residency@ / msr@tsc@) * 100",
         "MetricGroup": "Power",
+        "BriefDescription": "C3 residency percent per package",
         "MetricName": "C3_Pkg_Residency"
     },
     {
-        "BriefDescription": "C6 residency percent per package",
         "MetricExpr": "(cstate_pkg@c6\\-residency@ / msr@tsc@) * 100",
         "MetricGroup": "Power",
+        "BriefDescription": "C6 residency percent per package",
         "MetricName": "C6_Pkg_Residency"
     },
     {
-        "BriefDescription": "C7 residency percent per package",
         "MetricExpr": "(cstate_pkg@c7\\-residency@ / msr@tsc@) * 100",
         "MetricGroup": "Power",
+        "BriefDescription": "C7 residency percent per package",
         "MetricName": "C7_Pkg_Residency"
     }
 ]
diff --git a/tools/perf/scripts/python/export-to-sqlite.py b/tools/perf/scripts/python/export-to-sqlite.py
index 3b71902a5a21..bf271fbc3a88 100644
--- a/tools/perf/scripts/python/export-to-sqlite.py
+++ b/tools/perf/scripts/python/export-to-sqlite.py
@@ -331,7 +331,7 @@ if perf_db_export_calls:
 			'return_id,'
 			'CASE WHEN flags=0 THEN \'\' WHEN flags=1 THEN \'no call\' WHEN flags=2 THEN \'no return\' WHEN flags=3 THEN \'no call/return\' WHEN flags=6 THEN \'jump\' ELSE flags END AS flags,'
 			'parent_call_path_id,'
-			'parent_id'
+			'calls.parent_id'
 		' FROM calls INNER JOIN call_paths ON call_paths.id = call_path_id')
 
 do_query(query, 'CREATE VIEW samples_view AS '
diff --git a/tools/perf/scripts/python/exported-sql-viewer.py b/tools/perf/scripts/python/exported-sql-viewer.py
index e38518cdcbc3..74ef92f1d19a 100755
--- a/tools/perf/scripts/python/exported-sql-viewer.py
+++ b/tools/perf/scripts/python/exported-sql-viewer.py
@@ -107,6 +107,7 @@ import os
 from PySide.QtCore import *
 from PySide.QtGui import *
 from PySide.QtSql import *
+pyside_version_1 = True
 from decimal import *
 from ctypes import *
 from multiprocessing import Process, Array, Value, Event
@@ -1526,6 +1527,19 @@ def BranchDataPrep(query):
 			" (" + dsoname(query.value(15)) + ")")
 	return data
 
+def BranchDataPrepWA(query):
+	data = []
+	data.append(query.value(0))
+	# Workaround pyside failing to handle large integers (i.e. time) in python3 by converting to a string
+	data.append("{:>19}".format(query.value(1)))
+	for i in xrange(2, 8):
+		data.append(query.value(i))
+	data.append(tohex(query.value(8)).rjust(16) + " " + query.value(9) + offstr(query.value(10)) +
+			" (" + dsoname(query.value(11)) + ")" + " -> " +
+			tohex(query.value(12)) + " " + query.value(13) + offstr(query.value(14)) +
+			" (" + dsoname(query.value(15)) + ")")
+	return data
+
 # Branch data model
 
 class BranchModel(TreeModel):
@@ -1553,7 +1567,11 @@ class BranchModel(TreeModel):
 			" AND evsel_id = " + str(self.event_id) +
 			" ORDER BY samples.id"
 			" LIMIT " + str(glb_chunk_sz))
-		self.fetcher = SQLFetcher(glb, sql, BranchDataPrep, self.AddSample)
+		if pyside_version_1 and sys.version_info[0] == 3:
+			prep = BranchDataPrepWA
+		else:
+			prep = BranchDataPrep
+		self.fetcher = SQLFetcher(glb, sql, prep, self.AddSample)
 		self.fetcher.done.connect(self.Update)
 		self.fetcher.Fetch(glb_chunk_sz)
 
@@ -2079,14 +2097,6 @@ def IsSelectable(db, table, sql = ""):
 		return False
 	return True
 
-# SQL data preparation
-
-def SQLTableDataPrep(query, count):
-	data = []
-	for i in xrange(count):
-		data.append(query.value(i))
-	return data
-
 # SQL table data model item
 
 class SQLTableItem():
@@ -2110,7 +2120,7 @@ class SQLTableModel(TableModel):
 		self.more = True
 		self.populated = 0
 		self.column_headers = column_headers
-		self.fetcher = SQLFetcher(glb, sql, lambda x, y=len(column_headers): SQLTableDataPrep(x, y), self.AddSample)
+		self.fetcher = SQLFetcher(glb, sql, lambda x, y=len(column_headers): self.SQLTableDataPrep(x, y), self.AddSample)
 		self.fetcher.done.connect(self.Update)
 		self.fetcher.Fetch(glb_chunk_sz)
 
@@ -2154,6 +2164,12 @@ class SQLTableModel(TableModel):
 	def columnHeader(self, column):
 		return self.column_headers[column]
 
+	def SQLTableDataPrep(self, query, count):
+		data = []
+		for i in xrange(count):
+			data.append(query.value(i))
+		return data
+
 # SQL automatic table data model
 
 class SQLAutoTableModel(SQLTableModel):
@@ -2182,8 +2198,32 @@ class SQLAutoTableModel(SQLTableModel):
 			QueryExec(query, "SELECT column_name FROM information_schema.columns WHERE table_schema = '" + schema + "' and table_name = '" + select_table_name + "'")
 			while query.next():
 				column_headers.append(query.value(0))
+		if pyside_version_1 and sys.version_info[0] == 3:
+			if table_name == "samples_view":
+				self.SQLTableDataPrep = self.samples_view_DataPrep
+			if table_name == "samples":
+				self.SQLTableDataPrep = self.samples_DataPrep
 		super(SQLAutoTableModel, self).__init__(glb, sql, column_headers, parent)
 
+	def samples_view_DataPrep(self, query, count):
+		data = []
+		data.append(query.value(0))
+		# Workaround pyside failing to handle large integers (i.e. time) in python3 by converting to a string
+		data.append("{:>19}".format(query.value(1)))
+		for i in xrange(2, count):
+			data.append(query.value(i))
+		return data
+
+	def samples_DataPrep(self, query, count):
+		data = []
+		for i in xrange(9):
+			data.append(query.value(i))
+		# Workaround pyside failing to handle large integers (i.e. time) in python3 by converting to a string
+		data.append("{:>19}".format(query.value(9)))
+		for i in xrange(10, count):
+			data.append(query.value(i))
+		return data
+
 # Base class for custom ResizeColumnsToContents
 
 class ResizeColumnsToContentsBase(QObject):
@@ -2868,9 +2908,13 @@ class LibXED():
 		ok = self.xed_format_context(2, inst.xedp, inst.bufferp, sizeof(inst.buffer), ip, 0, 0)
 		if not ok:
 			return 0, ""
+		if sys.version_info[0] == 2:
+			result = inst.buffer.value
+		else:
+			result = inst.buffer.value.decode()
 		# Return instruction length and the disassembled instruction text
 		# For now, assume the length is in byte 166
-		return inst.xedd[166], inst.buffer.value
+		return inst.xedd[166], result
 
 def TryOpen(file_name):
 	try:
@@ -2886,9 +2930,14 @@ def Is64Bit(f):
 	header = f.read(7)
 	f.seek(pos)
 	magic = header[0:4]
-	eclass = ord(header[4])
-	encoding = ord(header[5])
-	version = ord(header[6])
+	if sys.version_info[0] == 2:
+		eclass = ord(header[4])
+		encoding = ord(header[5])
+		version = ord(header[6])
+	else:
+		eclass = header[4]
+		encoding = header[5]
+		version = header[6]
 	if magic == chr(127) + "ELF" and eclass > 0 and eclass < 3 and encoding > 0 and encoding < 3 and version == 1:
 		result = True if eclass == 2 else False
 	return result
diff --git a/tools/perf/trace/beauty/mmap_flags.sh b/tools/perf/trace/beauty/mmap_flags.sh
index 32bac9c0d694..5f5eefcb3c74 100755
--- a/tools/perf/trace/beauty/mmap_flags.sh
+++ b/tools/perf/trace/beauty/mmap_flags.sh
@@ -1,15 +1,18 @@
 #!/bin/sh
 # SPDX-License-Identifier: LGPL-2.1
 
-if [ $# -ne 2 ] ; then
+if [ $# -ne 3 ] ; then
 	[ $# -eq 1 ] && hostarch=$1 || hostarch=`uname -m | sed -e s/i.86/x86/ -e s/x86_64/x86/`
+	linux_header_dir=tools/include/uapi/linux
 	header_dir=tools/include/uapi/asm-generic
 	arch_header_dir=tools/arch/${hostarch}/include/uapi/asm
 else
-	header_dir=$1
-	arch_header_dir=$2
+	linux_header_dir=$1
+	header_dir=$2
+	arch_header_dir=$3
 fi
 
+linux_mman=${linux_header_dir}/mman.h
 arch_mman=${arch_header_dir}/mman.h
 
 # those in egrep -vw are flags, we want just the bits
@@ -20,6 +23,11 @@ egrep -q $regex ${arch_mman} && \
 (egrep $regex ${arch_mman} | \
 	sed -r "s/$regex/\2 \1/g"	| \
 	xargs printf "\t[ilog2(%s) + 1] = \"%s\",\n")
+egrep -q $regex ${linux_mman} && \
+(egrep $regex ${linux_mman} | \
+	egrep -vw 'MAP_(UNINITIALIZED|TYPE|SHARED_VALIDATE)' | \
+	sed -r "s/$regex/\2 \1/g"	| \
+	xargs printf "\t[ilog2(%s) + 1] = \"%s\",\n")
 ([ ! -f ${arch_mman} ] || egrep -q '#[[:space:]]*include[[:space:]]+<uapi/asm-generic/mman.*' ${arch_mman}) &&
 (egrep $regex ${header_dir}/mman-common.h | \
 	egrep -vw 'MAP_(UNINITIALIZED|TYPE|SHARED_VALIDATE)' | \
diff --git a/tools/perf/trace/beauty/renameat.c b/tools/perf/trace/beauty/renameat.c
index 6dab340cc506..852d2e271833 100644
--- a/tools/perf/trace/beauty/renameat.c
+++ b/tools/perf/trace/beauty/renameat.c
@@ -2,7 +2,6 @@
 // Copyright (C) 2018, Red Hat Inc, Arnaldo Carvalho de Melo <acme@redhat.com>
 
 #include "trace/beauty/beauty.h"
-#include <uapi/linux/fs.h>
 
 static size_t renameat2__scnprintf_flags(unsigned long flags, char *bf, size_t size, bool show_prefix)
 {
diff --git a/tools/perf/trace/strace/groups/string b/tools/perf/trace/strace/groups/string
new file mode 100644
index 000000000000..c87129a3e3c4
--- /dev/null
+++ b/tools/perf/trace/strace/groups/string
@@ -0,0 +1,65 @@
+access
+acct
+add_key
+chdir
+chmod
+chown
+chroot
+creat
+delete_module
+execve
+execveat
+faccessat
+fchmodat
+fchownat
+fgetxattr
+finit_module
+fremovexattr
+fsetxattr
+futimesat
+getxattr
+inotify_add_watch
+lchown
+lgetxattr
+link
+linkat
+listxattr
+llistxattr
+lremovexattr
+lsetxattr
+lstat
+memfd_create
+mkdir
+mkdirat
+mknod
+mknodat
+mq_open
+mq_timedsend
+mq_unlink
+name_to_handle_at
+newfstatat
+open
+openat
+pivot_root
+pwrite64
+quotactl
+readlink
+readlinkat
+removexattr
+rename
+renameat
+renameat2
+request_key
+rmdir
+setxattr
+stat
+statfs
+statx
+swapoff
+swapon
+symlink
+symlinkat
+truncate
+unlink
+unlinkat
+utimensat
diff --git a/tools/perf/util/annotate.c b/tools/perf/util/annotate.c
index c8b01176c9e1..09762985c713 100644
--- a/tools/perf/util/annotate.c
+++ b/tools/perf/util/annotate.c
@@ -1714,8 +1714,8 @@ static int symbol__disassemble_bpf(struct symbol *sym,
 	if (dso->binary_type != DSO_BINARY_TYPE__BPF_PROG_INFO)
 		return -1;
 
-	pr_debug("%s: handling sym %s addr %lx len %lx\n", __func__,
-		 sym->name, sym->start, sym->end - sym->start);
+	pr_debug("%s: handling sym %s addr %" PRIx64 " len %" PRIx64 "\n", __func__,
+		  sym->name, sym->start, sym->end - sym->start);
 
 	memset(tpath, 0, sizeof(tpath));
 	perf_exe(tpath, sizeof(tpath));
@@ -1740,7 +1740,7 @@ static int symbol__disassemble_bpf(struct symbol *sym,
 	info_linear = info_node->info_linear;
 	sub_id = dso->bpf_prog.sub_id;
 
-	info.buffer = (void *)(info_linear->info.jited_prog_insns);
+	info.buffer = (void *)(uintptr_t)(info_linear->info.jited_prog_insns);
 	info.buffer_length = info_linear->info.jited_prog_len;
 
 	if (info_linear->info.nr_line_info)
@@ -1776,7 +1776,7 @@ static int symbol__disassemble_bpf(struct symbol *sym,
 		const char *srcline;
 		u64 addr;
 
-		addr = pc + ((u64 *)(info_linear->info.jited_ksyms))[sub_id];
+		addr = pc + ((u64 *)(uintptr_t)(info_linear->info.jited_ksyms))[sub_id];
 		count = disassemble(pc, &info);
 
 		if (prog_linfo)
diff --git a/tools/perf/util/cloexec.c b/tools/perf/util/cloexec.c
index ca0fff6272be..06f48312c5ed 100644
--- a/tools/perf/util/cloexec.c
+++ b/tools/perf/util/cloexec.c
@@ -7,7 +7,6 @@
 #include "asm/bug.h"
 #include "debug.h"
 #include <unistd.h>
-#include <asm/unistd.h>
 #include <sys/syscall.h>
 
 static unsigned long flag = PERF_FLAG_FD_CLOEXEC;
diff --git a/tools/perf/util/cs-etm-decoder/cs-etm-decoder.c b/tools/perf/util/cs-etm-decoder/cs-etm-decoder.c
index ba4c623cd8de..39fe21e1cf93 100644
--- a/tools/perf/util/cs-etm-decoder/cs-etm-decoder.c
+++ b/tools/perf/util/cs-etm-decoder/cs-etm-decoder.c
@@ -387,6 +387,7 @@ cs_etm_decoder__buffer_range(struct cs_etm_decoder *decoder,
 		break;
 	case OCSD_INSTR_ISB:
 	case OCSD_INSTR_DSB_DMB:
+	case OCSD_INSTR_WFI_WFE:
 	case OCSD_INSTR_OTHER:
 	default:
 		packet->last_instr_taken_branch = false;
diff --git a/tools/perf/util/cs-etm.c b/tools/perf/util/cs-etm.c
index 110804936fc3..de488b43f440 100644
--- a/tools/perf/util/cs-etm.c
+++ b/tools/perf/util/cs-etm.c
@@ -422,11 +422,9 @@ static struct cs_etm_queue *cs_etm__alloc_queue(struct cs_etm_auxtrace *etm)
 	if (!etmq->packet)
 		goto out_free;
 
-	if (etm->synth_opts.last_branch || etm->sample_branches) {
-		etmq->prev_packet = zalloc(szp);
-		if (!etmq->prev_packet)
-			goto out_free;
-	}
+	etmq->prev_packet = zalloc(szp);
+	if (!etmq->prev_packet)
+		goto out_free;
 
 	if (etm->synth_opts.last_branch) {
 		size_t sz = sizeof(struct branch_stack);
@@ -981,7 +979,6 @@ static int cs_etm__sample(struct cs_etm_queue *etmq)
 	 * PREV_PACKET is a branch.
 	 */
 	if (etm->synth_opts.last_branch &&
-	    etmq->prev_packet &&
 	    etmq->prev_packet->sample_type == CS_ETM_RANGE &&
 	    etmq->prev_packet->last_instr_taken_branch)
 		cs_etm__update_last_branch_rb(etmq);
@@ -1014,7 +1011,7 @@ static int cs_etm__sample(struct cs_etm_queue *etmq)
 		etmq->period_instructions = instrs_over;
 	}
 
-	if (etm->sample_branches && etmq->prev_packet) {
+	if (etm->sample_branches) {
 		bool generate_sample = false;
 
 		/* Generate sample for tracing on packet */
@@ -1071,9 +1068,6 @@ static int cs_etm__flush(struct cs_etm_queue *etmq)
 	struct cs_etm_auxtrace *etm = etmq->etm;
 	struct cs_etm_packet *tmp;
 
-	if (!etmq->prev_packet)
-		return 0;
-
 	/* Handle start tracing packet */
 	if (etmq->prev_packet->sample_type == CS_ETM_EMPTY)
 		goto swap_packet;
diff --git a/tools/perf/util/data-convert-bt.c b/tools/perf/util/data-convert-bt.c
index 26af43ad9ddd..e0311c9750ad 100644
--- a/tools/perf/util/data-convert-bt.c
+++ b/tools/perf/util/data-convert-bt.c
@@ -310,7 +310,7 @@ static int add_tracepoint_field_value(struct ctf_writer *cw,
 	if (flags & TEP_FIELD_IS_DYNAMIC) {
 		unsigned long long tmp_val;
 
-		tmp_val = tep_read_number(fmtf->event->pevent,
+		tmp_val = tep_read_number(fmtf->event->tep,
 					  data + offset, len);
 		offset = tmp_val;
 		len = offset >> 16;
@@ -354,7 +354,7 @@ static int add_tracepoint_field_value(struct ctf_writer *cw,
 			unsigned long long value_int;
 
 			value_int = tep_read_number(
-					fmtf->event->pevent,
+					fmtf->event->tep,
 					data + offset + i * len, len);
 
 			if (!(flags & TEP_FIELD_IS_SIGNED))
diff --git a/tools/perf/util/env.c b/tools/perf/util/env.c
index c6351b557bb0..6a3eaf7d9353 100644
--- a/tools/perf/util/env.c
+++ b/tools/perf/util/env.c
@@ -57,9 +57,11 @@ struct bpf_prog_info_node *perf_env__find_bpf_prog_info(struct perf_env *env,
 		else if (prog_id > node->info_linear->info.id)
 			n = n->rb_right;
 		else
-			break;
+			goto out;
 	}
+	node = NULL;
 
+out:
 	up_read(&env->bpf_progs.lock);
 	return node;
 }
@@ -109,9 +111,11 @@ struct btf_node *perf_env__find_btf(struct perf_env *env, __u32 btf_id)
 		else if (btf_id > node->id)
 			n = n->rb_right;
 		else
-			break;
+			goto out;
 	}
+	node = NULL;
 
+out:
 	up_read(&env->bpf_progs.lock);
 	return node;
 }
diff --git a/tools/perf/util/event.h b/tools/perf/util/event.h
index 36ae7e92dab1..4e908ec1ef64 100644
--- a/tools/perf/util/event.h
+++ b/tools/perf/util/event.h
@@ -6,6 +6,7 @@
 #include <stdio.h>
 #include <linux/kernel.h>
 #include <linux/bpf.h>
+#include <linux/perf_event.h>
 
 #include "../perf.h"
 #include "build-id.h"
diff --git a/tools/perf/util/evlist.c b/tools/perf/util/evlist.c
index ec78e93085de..4b6783ff5813 100644
--- a/tools/perf/util/evlist.c
+++ b/tools/perf/util/evlist.c
@@ -231,35 +231,6 @@ void perf_evlist__set_leader(struct perf_evlist *evlist)
 	}
 }
 
-void perf_event_attr__set_max_precise_ip(struct perf_event_attr *pattr)
-{
-	struct perf_event_attr attr = {
-		.type		= PERF_TYPE_HARDWARE,
-		.config		= PERF_COUNT_HW_CPU_CYCLES,
-		.exclude_kernel	= 1,
-		.precise_ip	= 3,
-	};
-
-	event_attr_init(&attr);
-
-	/*
-	 * Unnamed union member, not supported as struct member named
-	 * initializer in older compilers such as gcc 4.4.7
-	 */
-	attr.sample_period = 1;
-
-	while (attr.precise_ip != 0) {
-		int fd = sys_perf_event_open(&attr, 0, -1, -1, 0);
-		if (fd != -1) {
-			close(fd);
-			break;
-		}
-		--attr.precise_ip;
-	}
-
-	pattr->precise_ip = attr.precise_ip;
-}
-
 int __perf_evlist__add_default(struct perf_evlist *evlist, bool precise)
 {
 	struct perf_evsel *evsel = perf_evsel__new_cycles(precise);
@@ -1038,7 +1009,7 @@ int perf_evlist__parse_mmap_pages(const struct option *opt, const char *str,
  */
 int perf_evlist__mmap_ex(struct perf_evlist *evlist, unsigned int pages,
 			 unsigned int auxtrace_pages,
-			 bool auxtrace_overwrite, int nr_cblocks, int affinity)
+			 bool auxtrace_overwrite, int nr_cblocks, int affinity, int flush)
 {
 	struct perf_evsel *evsel;
 	const struct cpu_map *cpus = evlist->cpus;
@@ -1048,7 +1019,7 @@ int perf_evlist__mmap_ex(struct perf_evlist *evlist, unsigned int pages,
 	 * Its value is decided by evsel's write_backward.
 	 * So &mp should not be passed through const pointer.
 	 */
-	struct mmap_params mp = { .nr_cblocks = nr_cblocks, .affinity = affinity };
+	struct mmap_params mp = { .nr_cblocks = nr_cblocks, .affinity = affinity, .flush = flush };
 
 	if (!evlist->mmap)
 		evlist->mmap = perf_evlist__alloc_mmap(evlist, false);
@@ -1080,7 +1051,7 @@ int perf_evlist__mmap_ex(struct perf_evlist *evlist, unsigned int pages,
 
 int perf_evlist__mmap(struct perf_evlist *evlist, unsigned int pages)
 {
-	return perf_evlist__mmap_ex(evlist, pages, 0, false, 0, PERF_AFFINITY_SYS);
+	return perf_evlist__mmap_ex(evlist, pages, 0, false, 0, PERF_AFFINITY_SYS, 1);
 }
 
 int perf_evlist__create_maps(struct perf_evlist *evlist, struct target *target)
@@ -1897,12 +1868,12 @@ static void *perf_evlist__poll_thread(void *arg)
 {
 	struct perf_evlist *evlist = arg;
 	bool draining = false;
-	int i;
+	int i, done = 0;
+
+	while (!done) {
+		bool got_data = false;
 
-	while (draining || !(evlist->thread.done)) {
-		if (draining)
-			draining = false;
-		else if (evlist->thread.done)
+		if (evlist->thread.done)
 			draining = true;
 
 		if (!draining)
@@ -1923,9 +1894,13 @@ static void *perf_evlist__poll_thread(void *arg)
 					pr_warning("cannot locate proper evsel for the side band event\n");
 
 				perf_mmap__consume(map);
+				got_data = true;
 			}
 			perf_mmap__read_done(map);
 		}
+
+		if (draining && !got_data)
+			break;
 	}
 	return NULL;
 }
diff --git a/tools/perf/util/evlist.h b/tools/perf/util/evlist.h
index dcb68f34d2cd..c9a0f72677fd 100644
--- a/tools/perf/util/evlist.h
+++ b/tools/perf/util/evlist.h
@@ -177,7 +177,8 @@ unsigned long perf_event_mlock_kb_in_pages(void);
 
 int perf_evlist__mmap_ex(struct perf_evlist *evlist, unsigned int pages,
 			 unsigned int auxtrace_pages,
-			 bool auxtrace_overwrite, int nr_cblocks, int affinity);
+			 bool auxtrace_overwrite, int nr_cblocks,
+			 int affinity, int flush);
 int perf_evlist__mmap(struct perf_evlist *evlist, unsigned int pages);
 void perf_evlist__munmap(struct perf_evlist *evlist);
 
@@ -315,8 +316,6 @@ void perf_evlist__to_front(struct perf_evlist *evlist,
 void perf_evlist__set_tracking_event(struct perf_evlist *evlist,
 				     struct perf_evsel *tracking_evsel);
 
-void perf_event_attr__set_max_precise_ip(struct perf_event_attr *attr);
-
 struct perf_evsel *
 perf_evlist__find_evsel_by_str(struct perf_evlist *evlist, const char *str);
 
diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c
index 7835e05f0c0a..a10cf4cde920 100644
--- a/tools/perf/util/evsel.c
+++ b/tools/perf/util/evsel.c
@@ -295,7 +295,6 @@ struct perf_evsel *perf_evsel__new_cycles(bool precise)
 	if (!precise)
 		goto new_event;
 
-	perf_event_attr__set_max_precise_ip(&attr);
 	/*
 	 * Now let the usual logic to set up the perf_event_attr defaults
 	 * to kick in when we return and before perf_evsel__open() is called.
@@ -305,6 +304,8 @@ new_event:
 	if (evsel == NULL)
 		goto out;
 
+	evsel->precise_max = true;
+
 	/* use asprintf() because free(evsel) assumes name is allocated */
 	if (asprintf(&evsel->name, "cycles%s%s%.*s",
 		     (attr.precise_ip || attr.exclude_kernel) ? ":" : "",
@@ -579,6 +580,12 @@ static int perf_evsel__raw_name(struct perf_evsel *evsel, char *bf, size_t size)
 	return ret + perf_evsel__add_modifiers(evsel, bf + ret, size - ret);
 }
 
+static int perf_evsel__tool_name(char *bf, size_t size)
+{
+	int ret = scnprintf(bf, size, "duration_time");
+	return ret;
+}
+
 const char *perf_evsel__name(struct perf_evsel *evsel)
 {
 	char bf[128];
@@ -600,7 +607,10 @@ const char *perf_evsel__name(struct perf_evsel *evsel)
 		break;
 
 	case PERF_TYPE_SOFTWARE:
-		perf_evsel__sw_name(evsel, bf, sizeof(bf));
+		if (evsel->tool_event)
+			perf_evsel__tool_name(bf, sizeof(bf));
+		else
+			perf_evsel__sw_name(evsel, bf, sizeof(bf));
 		break;
 
 	case PERF_TYPE_TRACEPOINT:
@@ -1083,7 +1093,7 @@ void perf_evsel__config(struct perf_evsel *evsel, struct record_opts *opts,
 	}
 
 	if (evsel->precise_max)
-		perf_event_attr__set_max_precise_ip(attr);
+		attr->precise_ip = 3;
 
 	if (opts->all_user) {
 		attr->exclude_kernel = 1;
@@ -1749,6 +1759,59 @@ static bool ignore_missing_thread(struct perf_evsel *evsel,
 	return true;
 }
 
+static void display_attr(struct perf_event_attr *attr)
+{
+	if (verbose >= 2) {
+		fprintf(stderr, "%.60s\n", graph_dotted_line);
+		fprintf(stderr, "perf_event_attr:\n");
+		perf_event_attr__fprintf(stderr, attr, __open_attr__fprintf, NULL);
+		fprintf(stderr, "%.60s\n", graph_dotted_line);
+	}
+}
+
+static int perf_event_open(struct perf_evsel *evsel,
+			   pid_t pid, int cpu, int group_fd,
+			   unsigned long flags)
+{
+	int precise_ip = evsel->attr.precise_ip;
+	int fd;
+
+	while (1) {
+		pr_debug2("sys_perf_event_open: pid %d  cpu %d  group_fd %d  flags %#lx",
+			  pid, cpu, group_fd, flags);
+
+		fd = sys_perf_event_open(&evsel->attr, pid, cpu, group_fd, flags);
+		if (fd >= 0)
+			break;
+
+		/*
+		 * Do quick precise_ip fallback if:
+		 *  - there is precise_ip set in perf_event_attr
+		 *  - maximum precise is requested
+		 *  - sys_perf_event_open failed with ENOTSUP error,
+		 *    which is associated with wrong precise_ip
+		 */
+		if (!precise_ip || !evsel->precise_max || (errno != ENOTSUP))
+			break;
+
+		/*
+		 * We tried all the precise_ip values, and it's
+		 * still failing, so leave it to standard fallback.
+		 */
+		if (!evsel->attr.precise_ip) {
+			evsel->attr.precise_ip = precise_ip;
+			break;
+		}
+
+		pr_debug2("\nsys_perf_event_open failed, error %d\n", -ENOTSUP);
+		evsel->attr.precise_ip--;
+		pr_debug2("decreasing precise_ip by one (%d)\n", evsel->attr.precise_ip);
+		display_attr(&evsel->attr);
+	}
+
+	return fd;
+}
+
 int perf_evsel__open(struct perf_evsel *evsel, struct cpu_map *cpus,
 		     struct thread_map *threads)
 {
@@ -1824,12 +1887,7 @@ retry_sample_id:
 	if (perf_missing_features.sample_id_all)
 		evsel->attr.sample_id_all = 0;
 
-	if (verbose >= 2) {
-		fprintf(stderr, "%.60s\n", graph_dotted_line);
-		fprintf(stderr, "perf_event_attr:\n");
-		perf_event_attr__fprintf(stderr, &evsel->attr, __open_attr__fprintf, NULL);
-		fprintf(stderr, "%.60s\n", graph_dotted_line);
-	}
+	display_attr(&evsel->attr);
 
 	for (cpu = 0; cpu < cpus->nr; cpu++) {
 
@@ -1841,13 +1899,10 @@ retry_sample_id:
 
 			group_fd = get_group_fd(evsel, cpu, thread);
 retry_open:
-			pr_debug2("sys_perf_event_open: pid %d  cpu %d  group_fd %d  flags %#lx",
-				  pid, cpus->map[cpu], group_fd, flags);
-
 			test_attr__ready();
 
-			fd = sys_perf_event_open(&evsel->attr, pid, cpus->map[cpu],
-						 group_fd, flags);
+			fd = perf_event_open(evsel, pid, cpus->map[cpu],
+					     group_fd, flags);
 
 			FD(evsel, cpu, thread) = fd;
 
@@ -2322,7 +2377,7 @@ int perf_evsel__parse_sample(struct perf_evsel *evsel, union perf_event *event,
 		if (data->user_regs.abi) {
 			u64 mask = evsel->attr.sample_regs_user;
 
-			sz = hweight_long(mask) * sizeof(u64);
+			sz = hweight64(mask) * sizeof(u64);
 			OVERFLOW_CHECK(array, sz, max_size);
 			data->user_regs.mask = mask;
 			data->user_regs.regs = (u64 *)array;
@@ -2378,7 +2433,7 @@ int perf_evsel__parse_sample(struct perf_evsel *evsel, union perf_event *event,
 		if (data->intr_regs.abi != PERF_SAMPLE_REGS_ABI_NONE) {
 			u64 mask = evsel->attr.sample_regs_intr;
 
-			sz = hweight_long(mask) * sizeof(u64);
+			sz = hweight64(mask) * sizeof(u64);
 			OVERFLOW_CHECK(array, sz, max_size);
 			data->intr_regs.mask = mask;
 			data->intr_regs.regs = (u64 *)array;
@@ -2506,7 +2561,7 @@ size_t perf_event__sample_event_size(const struct perf_sample *sample, u64 type,
 	if (type & PERF_SAMPLE_REGS_USER) {
 		if (sample->user_regs.abi) {
 			result += sizeof(u64);
-			sz = hweight_long(sample->user_regs.mask) * sizeof(u64);
+			sz = hweight64(sample->user_regs.mask) * sizeof(u64);
 			result += sz;
 		} else {
 			result += sizeof(u64);
@@ -2534,7 +2589,7 @@ size_t perf_event__sample_event_size(const struct perf_sample *sample, u64 type,
 	if (type & PERF_SAMPLE_REGS_INTR) {
 		if (sample->intr_regs.abi) {
 			result += sizeof(u64);
-			sz = hweight_long(sample->intr_regs.mask) * sizeof(u64);
+			sz = hweight64(sample->intr_regs.mask) * sizeof(u64);
 			result += sz;
 		} else {
 			result += sizeof(u64);
@@ -2664,7 +2719,7 @@ int perf_event__synthesize_sample(union perf_event *event, u64 type,
 	if (type & PERF_SAMPLE_REGS_USER) {
 		if (sample->user_regs.abi) {
 			*array++ = sample->user_regs.abi;
-			sz = hweight_long(sample->user_regs.mask) * sizeof(u64);
+			sz = hweight64(sample->user_regs.mask) * sizeof(u64);
 			memcpy(array, sample->user_regs.regs, sz);
 			array = (void *)array + sz;
 		} else {
@@ -2700,7 +2755,7 @@ int perf_event__synthesize_sample(union perf_event *event, u64 type,
 	if (type & PERF_SAMPLE_REGS_INTR) {
 		if (sample->intr_regs.abi) {
 			*array++ = sample->intr_regs.abi;
-			sz = hweight_long(sample->intr_regs.mask) * sizeof(u64);
+			sz = hweight64(sample->intr_regs.mask) * sizeof(u64);
 			memcpy(array, sample->intr_regs.regs, sz);
 			array = (void *)array + sz;
 		} else {
diff --git a/tools/perf/util/evsel.h b/tools/perf/util/evsel.h
index 0f2c6c93d721..6d190cbf1070 100644
--- a/tools/perf/util/evsel.h
+++ b/tools/perf/util/evsel.h
@@ -75,6 +75,11 @@ struct perf_stat_evsel;
 
 typedef int (perf_evsel__sb_cb_t)(union perf_event *event, void *data);
 
+enum perf_tool_event {
+	PERF_TOOL_NONE		= 0,
+	PERF_TOOL_DURATION_TIME = 1,
+};
+
 /** struct perf_evsel - event selector
  *
  * @evlist - evlist this evsel is in, if it is in one.
@@ -121,6 +126,7 @@ struct perf_evsel {
 	unsigned int		sample_size;
 	int			id_pos;
 	int			is_pos;
+	enum perf_tool_event	tool_event;
 	bool			uniquified_name;
 	bool			snapshot;
 	bool 			supported;
diff --git a/tools/perf/util/header.c b/tools/perf/util/header.c
index b9e693825873..2d2af2ac2b1e 100644
--- a/tools/perf/util/header.c
+++ b/tools/perf/util/header.c
@@ -2606,6 +2606,7 @@ static int process_bpf_prog_info(struct feat_fd *ff, void *data __maybe_unused)
 		perf_env__insert_bpf_prog_info(env, info_node);
 	}
 
+	up_write(&env->bpf_progs.lock);
 	return 0;
 out:
 	free(info_linear);
@@ -2623,7 +2624,9 @@ static int process_bpf_prog_info(struct feat_fd *ff __maybe_unused, void *data _
 static int process_bpf_btf(struct feat_fd *ff, void *data __maybe_unused)
 {
 	struct perf_env *env = &ff->ph->env;
+	struct btf_node *node = NULL;
 	u32 count, i;
+	int err = -1;
 
 	if (ff->ph->needs_swap) {
 		pr_warning("interpreting btf from systems with endianity is not yet supported\n");
@@ -2636,31 +2639,32 @@ static int process_bpf_btf(struct feat_fd *ff, void *data __maybe_unused)
 	down_write(&env->bpf_progs.lock);
 
 	for (i = 0; i < count; ++i) {
-		struct btf_node *node;
 		u32 id, data_size;
 
 		if (do_read_u32(ff, &id))
-			return -1;
+			goto out;
 		if (do_read_u32(ff, &data_size))
-			return -1;
+			goto out;
 
 		node = malloc(sizeof(struct btf_node) + data_size);
 		if (!node)
-			return -1;
+			goto out;
 
 		node->id = id;
 		node->data_size = data_size;
 
-		if (__do_read(ff, node->data, data_size)) {
-			free(node);
-			return -1;
-		}
+		if (__do_read(ff, node->data, data_size))
+			goto out;
 
 		perf_env__insert_btf(env, node);
+		node = NULL;
 	}
 
+	err = 0;
+out:
 	up_write(&env->bpf_progs.lock);
-	return 0;
+	free(node);
+	return err;
 }
 
 struct feature_ops {
diff --git a/tools/perf/util/intel-pt-decoder/intel-pt-decoder.c b/tools/perf/util/intel-pt-decoder/intel-pt-decoder.c
index 6e03db142091..872fab163585 100644
--- a/tools/perf/util/intel-pt-decoder/intel-pt-decoder.c
+++ b/tools/perf/util/intel-pt-decoder/intel-pt-decoder.c
@@ -251,19 +251,15 @@ struct intel_pt_decoder *intel_pt_decoder_new(struct intel_pt_params *params)
 		if (!(decoder->tsc_ctc_ratio_n % decoder->tsc_ctc_ratio_d))
 			decoder->tsc_ctc_mult = decoder->tsc_ctc_ratio_n /
 						decoder->tsc_ctc_ratio_d;
-
-		/*
-		 * Allow for timestamps appearing to backwards because a TSC
-		 * packet has slipped past a MTC packet, so allow 2 MTC ticks
-		 * or ...
-		 */
-		decoder->tsc_slip = multdiv(2 << decoder->mtc_shift,
-					decoder->tsc_ctc_ratio_n,
-					decoder->tsc_ctc_ratio_d);
 	}
-	/* ... or 0x100 paranoia */
-	if (decoder->tsc_slip < 0x100)
-		decoder->tsc_slip = 0x100;
+
+	/*
+	 * A TSC packet can slip past MTC packets so that the timestamp appears
+	 * to go backwards. One estimate is that can be up to about 40 CPU
+	 * cycles, which is certainly less than 0x1000 TSC ticks, but accept
+	 * slippage an order of magnitude more to be on the safe side.
+	 */
+	decoder->tsc_slip = 0x10000;
 
 	intel_pt_log("timestamp: mtc_shift %u\n", decoder->mtc_shift);
 	intel_pt_log("timestamp: tsc_ctc_ratio_n %u\n", decoder->tsc_ctc_ratio_n);
diff --git a/tools/perf/util/machine.c b/tools/perf/util/machine.c
index 61959aba7e27..3c520baa198c 100644
--- a/tools/perf/util/machine.c
+++ b/tools/perf/util/machine.c
@@ -1421,6 +1421,20 @@ static void machine__set_kernel_mmap(struct machine *machine,
 		machine->vmlinux_map->end = ~0ULL;
 }
 
+static void machine__update_kernel_mmap(struct machine *machine,
+				     u64 start, u64 end)
+{
+	struct map *map = machine__kernel_map(machine);
+
+	map__get(map);
+	map_groups__remove(&machine->kmaps, map);
+
+	machine__set_kernel_mmap(machine, start, end);
+
+	map_groups__insert(&machine->kmaps, map);
+	map__put(map);
+}
+
 int machine__create_kernel_maps(struct machine *machine)
 {
 	struct dso *kernel = machine__get_kernel(machine);
@@ -1453,17 +1467,11 @@ int machine__create_kernel_maps(struct machine *machine)
 			goto out_put;
 		}
 
-		/* we have a real start address now, so re-order the kmaps */
-		map = machine__kernel_map(machine);
-
-		map__get(map);
-		map_groups__remove(&machine->kmaps, map);
-
-		/* assume it's the last in the kmaps */
-		machine__set_kernel_mmap(machine, addr, ~0ULL);
-
-		map_groups__insert(&machine->kmaps, map);
-		map__put(map);
+		/*
+		 * we have a real start address now, so re-order the kmaps
+		 * assume it's the last in the kmaps
+		 */
+		machine__update_kernel_mmap(machine, addr, ~0ULL);
 	}
 
 	if (machine__create_extra_kernel_maps(machine, kernel))
@@ -1599,7 +1607,7 @@ static int machine__process_kernel_mmap_event(struct machine *machine,
 		if (strstr(kernel->long_name, "vmlinux"))
 			dso__set_short_name(kernel, "[kernel.vmlinux]", false);
 
-		machine__set_kernel_mmap(machine, event->mmap.start,
+		machine__update_kernel_mmap(machine, event->mmap.start,
 					 event->mmap.start + event->mmap.len);
 
 		/*
diff --git a/tools/perf/util/map.c b/tools/perf/util/map.c
index e32628cd20a7..ee71efb9db62 100644
--- a/tools/perf/util/map.c
+++ b/tools/perf/util/map.c
@@ -261,6 +261,22 @@ bool __map__is_extra_kernel_map(const struct map *map)
 	return kmap && kmap->name[0];
 }
 
+bool __map__is_bpf_prog(const struct map *map)
+{
+	const char *name;
+
+	if (map->dso->binary_type == DSO_BINARY_TYPE__BPF_PROG_INFO)
+		return true;
+
+	/*
+	 * If PERF_RECORD_BPF_EVENT is not included, the dso will not have
+	 * type of DSO_BINARY_TYPE__BPF_PROG_INFO. In such cases, we can
+	 * guess the type based on name.
+	 */
+	name = map->dso->short_name;
+	return name && (strstr(name, "bpf_prog_") == name);
+}
+
 bool map__has_symbols(const struct map *map)
 {
 	return dso__has_symbols(map->dso);
@@ -910,10 +926,8 @@ static void __maps__insert_name(struct maps *maps, struct map *map)
 		rc = strcmp(m->dso->short_name, map->dso->short_name);
 		if (rc < 0)
 			p = &(*p)->rb_left;
-		else if (rc  > 0)
-			p = &(*p)->rb_right;
 		else
-			return;
+			p = &(*p)->rb_right;
 	}
 	rb_link_node(&map->rb_node_name, parent, p);
 	rb_insert_color(&map->rb_node_name, &maps->names);
diff --git a/tools/perf/util/map.h b/tools/perf/util/map.h
index 0e20749f2c55..dc93787c74f0 100644
--- a/tools/perf/util/map.h
+++ b/tools/perf/util/map.h
@@ -159,10 +159,12 @@ int map__set_kallsyms_ref_reloc_sym(struct map *map, const char *symbol_name,
 
 bool __map__is_kernel(const struct map *map);
 bool __map__is_extra_kernel_map(const struct map *map);
+bool __map__is_bpf_prog(const struct map *map);
 
 static inline bool __map__is_kmodule(const struct map *map)
 {
-	return !__map__is_kernel(map) && !__map__is_extra_kernel_map(map);
+	return !__map__is_kernel(map) && !__map__is_extra_kernel_map(map) &&
+	       !__map__is_bpf_prog(map);
 }
 
 bool map__has_symbols(const struct map *map);
diff --git a/tools/perf/util/mmap.c b/tools/perf/util/mmap.c
index cdc7740fc181..ef3d79b2c90b 100644
--- a/tools/perf/util/mmap.c
+++ b/tools/perf/util/mmap.c
@@ -440,6 +440,8 @@ int perf_mmap__mmap(struct perf_mmap *map, struct mmap_params *mp, int fd, int c
 
 	perf_mmap__setup_affinity_mask(map, mp);
 
+	map->flush = mp->flush;
+
 	if (auxtrace_mmap__mmap(&map->auxtrace_mmap,
 				&mp->auxtrace_mp, map->base, fd))
 		return -1;
@@ -492,7 +494,7 @@ static int __perf_mmap__read_init(struct perf_mmap *md)
 	md->start = md->overwrite ? head : old;
 	md->end = md->overwrite ? old : head;
 
-	if (md->start == md->end)
+	if ((md->end - md->start) < md->flush)
 		return -EAGAIN;
 
 	size = md->end - md->start;
diff --git a/tools/perf/util/mmap.h b/tools/perf/util/mmap.h
index e566c19b242b..b82f8c2d55c4 100644
--- a/tools/perf/util/mmap.h
+++ b/tools/perf/util/mmap.h
@@ -39,6 +39,7 @@ struct perf_mmap {
 	} aio;
 #endif
 	cpu_set_t	affinity_mask;
+	u64		flush;
 };
 
 /*
@@ -70,7 +71,7 @@ enum bkw_mmap_state {
 };
 
 struct mmap_params {
-	int			    prot, mask, nr_cblocks, affinity;
+	int			    prot, mask, nr_cblocks, affinity, flush;
 	struct auxtrace_mmap_params auxtrace_mp;
 };
 
diff --git a/tools/perf/util/parse-events.c b/tools/perf/util/parse-events.c
index 5ef4939408f2..4432bfe039fd 100644
--- a/tools/perf/util/parse-events.c
+++ b/tools/perf/util/parse-events.c
@@ -317,10 +317,12 @@ static struct perf_evsel *
 __add_event(struct list_head *list, int *idx,
 	    struct perf_event_attr *attr,
 	    char *name, struct perf_pmu *pmu,
-	    struct list_head *config_terms, bool auto_merge_stats)
+	    struct list_head *config_terms, bool auto_merge_stats,
+	    const char *cpu_list)
 {
 	struct perf_evsel *evsel;
-	struct cpu_map *cpus = pmu ? pmu->cpus : NULL;
+	struct cpu_map *cpus = pmu ? pmu->cpus :
+			       cpu_list ? cpu_map__new(cpu_list) : NULL;
 
 	event_attr_init(attr);
 
@@ -348,7 +350,25 @@ static int add_event(struct list_head *list, int *idx,
 		     struct perf_event_attr *attr, char *name,
 		     struct list_head *config_terms)
 {
-	return __add_event(list, idx, attr, name, NULL, config_terms, false) ? 0 : -ENOMEM;
+	return __add_event(list, idx, attr, name, NULL, config_terms, false, NULL) ? 0 : -ENOMEM;
+}
+
+static int add_event_tool(struct list_head *list, int *idx,
+			  enum perf_tool_event tool_event)
+{
+	struct perf_evsel *evsel;
+	struct perf_event_attr attr = {
+		.type = PERF_TYPE_SOFTWARE,
+		.config = PERF_COUNT_SW_DUMMY,
+	};
+
+	evsel = __add_event(list, idx, &attr, NULL, NULL, NULL, false, "0");
+	if (!evsel)
+		return -ENOMEM;
+	evsel->tool_event = tool_event;
+	if (tool_event == PERF_TOOL_DURATION_TIME)
+		evsel->unit = strdup("ns");
+	return 0;
 }
 
 static int parse_aliases(char *str, const char *names[][PERF_EVSEL__MAX_ALIASES], int size)
@@ -1233,6 +1253,13 @@ int parse_events_add_numeric(struct parse_events_state *parse_state,
 			 get_config_name(head_config), &config_terms);
 }
 
+int parse_events_add_tool(struct parse_events_state *parse_state,
+			  struct list_head *list,
+			  enum perf_tool_event tool_event)
+{
+	return add_event_tool(list, &parse_state->idx, tool_event);
+}
+
 int parse_events_add_pmu(struct parse_events_state *parse_state,
 			 struct list_head *list, char *name,
 			 struct list_head *head_config,
@@ -1267,7 +1294,8 @@ int parse_events_add_pmu(struct parse_events_state *parse_state,
 
 	if (!head_config) {
 		attr.type = pmu->type;
-		evsel = __add_event(list, &parse_state->idx, &attr, NULL, pmu, NULL, auto_merge_stats);
+		evsel = __add_event(list, &parse_state->idx, &attr, NULL, pmu, NULL,
+				    auto_merge_stats, NULL);
 		if (evsel) {
 			evsel->pmu_name = name;
 			evsel->use_uncore_alias = use_uncore_alias;
@@ -1295,7 +1323,7 @@ int parse_events_add_pmu(struct parse_events_state *parse_state,
 
 	evsel = __add_event(list, &parse_state->idx, &attr,
 			    get_config_name(head_config), pmu,
-			    &config_terms, auto_merge_stats);
+			    &config_terms, auto_merge_stats, NULL);
 	if (evsel) {
 		evsel->unit = info.unit;
 		evsel->scale = info.scale;
@@ -2429,6 +2457,25 @@ out_enomem:
 	return evt_num;
 }
 
+static void print_tool_event(const char *name, const char *event_glob,
+			     bool name_only)
+{
+	if (event_glob && !strglobmatch(name, event_glob))
+		return;
+	if (name_only)
+		printf("%s ", name);
+	else
+		printf("  %-50s [%s]\n", name, "Tool event");
+
+}
+
+void print_tool_events(const char *event_glob, bool name_only)
+{
+	print_tool_event("duration_time", event_glob, name_only);
+	if (pager_in_use())
+		printf("\n");
+}
+
 void print_symbol_events(const char *event_glob, unsigned type,
 				struct event_symbol *syms, unsigned max,
 				bool name_only)
@@ -2512,6 +2559,7 @@ void print_events(const char *event_glob, bool name_only, bool quiet_flag,
 
 	print_symbol_events(event_glob, PERF_TYPE_SOFTWARE,
 			    event_symbols_sw, PERF_COUNT_SW_MAX, name_only);
+	print_tool_events(event_glob, name_only);
 
 	print_hwcache_events(event_glob, name_only);
 
diff --git a/tools/perf/util/parse-events.h b/tools/perf/util/parse-events.h
index 5ed035cbcbb7..a052cd6ac63e 100644
--- a/tools/perf/util/parse-events.h
+++ b/tools/perf/util/parse-events.h
@@ -160,6 +160,10 @@ int parse_events_add_numeric(struct parse_events_state *parse_state,
 			     struct list_head *list,
 			     u32 type, u64 config,
 			     struct list_head *head_config);
+enum perf_tool_event;
+int parse_events_add_tool(struct parse_events_state *parse_state,
+			  struct list_head *list,
+			  enum perf_tool_event tool_event);
 int parse_events_add_cache(struct list_head *list, int *idx,
 			   char *type, char *op_result1, char *op_result2,
 			   struct parse_events_error *error,
@@ -200,6 +204,7 @@ extern struct event_symbol event_symbols_sw[];
 void print_symbol_events(const char *event_glob, unsigned type,
 				struct event_symbol *syms, unsigned max,
 				bool name_only);
+void print_tool_events(const char *event_glob, bool name_only);
 void print_tracepoint_events(const char *subsys_glob, const char *event_glob,
 			     bool name_only);
 int print_hwcache_events(const char *event_glob, bool name_only);
diff --git a/tools/perf/util/parse-events.l b/tools/perf/util/parse-events.l
index 7805c71aaae2..c54bfe88626c 100644
--- a/tools/perf/util/parse-events.l
+++ b/tools/perf/util/parse-events.l
@@ -15,6 +15,7 @@
 #include "../perf.h"
 #include "parse-events.h"
 #include "parse-events-bison.h"
+#include "evsel.h"
 
 char *parse_events_get_text(yyscan_t yyscanner);
 YYSTYPE *parse_events_get_lval(yyscan_t yyscanner);
@@ -154,6 +155,14 @@ static int sym(yyscan_t scanner, int type, int config)
 	return type == PERF_TYPE_HARDWARE ? PE_VALUE_SYM_HW : PE_VALUE_SYM_SW;
 }
 
+static int tool(yyscan_t scanner, enum perf_tool_event event)
+{
+	YYSTYPE *yylval = parse_events_get_lval(scanner);
+
+	yylval->num = event;
+	return PE_VALUE_SYM_TOOL;
+}
+
 static int term(yyscan_t scanner, int type)
 {
 	YYSTYPE *yylval = parse_events_get_lval(scanner);
@@ -322,7 +331,7 @@ cpu-migrations|migrations			{ return sym(yyscanner, PERF_TYPE_SOFTWARE, PERF_COU
 alignment-faults				{ return sym(yyscanner, PERF_TYPE_SOFTWARE, PERF_COUNT_SW_ALIGNMENT_FAULTS); }
 emulation-faults				{ return sym(yyscanner, PERF_TYPE_SOFTWARE, PERF_COUNT_SW_EMULATION_FAULTS); }
 dummy						{ return sym(yyscanner, PERF_TYPE_SOFTWARE, PERF_COUNT_SW_DUMMY); }
-duration_time					{ return sym(yyscanner, PERF_TYPE_SOFTWARE, PERF_COUNT_SW_DUMMY); }
+duration_time					{ return tool(yyscanner, PERF_TOOL_DURATION_TIME); }
 bpf-output					{ return sym(yyscanner, PERF_TYPE_SOFTWARE, PERF_COUNT_SW_BPF_OUTPUT); }
 
 	/*
diff --git a/tools/perf/util/parse-events.y b/tools/perf/util/parse-events.y
index 44819bdb037d..6ad8d4914969 100644
--- a/tools/perf/util/parse-events.y
+++ b/tools/perf/util/parse-events.y
@@ -14,6 +14,7 @@
 #include <linux/types.h>
 #include "util.h"
 #include "pmu.h"
+#include "evsel.h"
 #include "debug.h"
 #include "parse-events.h"
 #include "parse-events-bison.h"
@@ -45,6 +46,7 @@ static void inc_group_count(struct list_head *list,
 
 %token PE_START_EVENTS PE_START_TERMS
 %token PE_VALUE PE_VALUE_SYM_HW PE_VALUE_SYM_SW PE_RAW PE_TERM
+%token PE_VALUE_SYM_TOOL
 %token PE_EVENT_NAME
 %token PE_NAME
 %token PE_BPF_OBJECT PE_BPF_SOURCE
@@ -58,6 +60,7 @@ static void inc_group_count(struct list_head *list,
 %type <num> PE_VALUE
 %type <num> PE_VALUE_SYM_HW
 %type <num> PE_VALUE_SYM_SW
+%type <num> PE_VALUE_SYM_TOOL
 %type <num> PE_RAW
 %type <num> PE_TERM
 %type <str> PE_NAME
@@ -321,6 +324,15 @@ value_sym sep_slash_slash_dc
 	ABORT_ON(parse_events_add_numeric(_parse_state, list, type, config, NULL));
 	$$ = list;
 }
+|
+PE_VALUE_SYM_TOOL sep_slash_slash_dc
+{
+	struct list_head *list;
+
+	ALLOC_LIST(list);
+	ABORT_ON(parse_events_add_tool(_parse_state, list, $1));
+	$$ = list;
+}
 
 event_legacy_cache:
 PE_NAME_CACHE_TYPE '-' PE_NAME_CACHE_OP_RESULT '-' PE_NAME_CACHE_OP_RESULT opt_event_config
diff --git a/tools/perf/util/pmu.c b/tools/perf/util/pmu.c
index 6199a3174ab9..e0429f4ef335 100644
--- a/tools/perf/util/pmu.c
+++ b/tools/perf/util/pmu.c
@@ -732,10 +732,20 @@ static void pmu_add_cpu_aliases(struct list_head *head, struct perf_pmu *pmu)
 
 		if (!is_arm_pmu_core(name)) {
 			pname = pe->pmu ? pe->pmu : "cpu";
+
+			/*
+			 * uncore alias may be from different PMU
+			 * with common prefix
+			 */
+			if (pmu_is_uncore(name) &&
+			    !strncmp(pname, name, strlen(pname)))
+				goto new_alias;
+
 			if (strcmp(pname, name))
 				continue;
 		}
 
+new_alias:
 		/* need type casts to override 'const' */
 		__perf_pmu__new_alias(head, NULL, (char *)pe->name,
 				(char *)pe->desc, (char *)pe->event,
diff --git a/tools/perf/util/python.c b/tools/perf/util/python.c
index dda0ac978b1e..6aa7e2352e16 100644
--- a/tools/perf/util/python.c
+++ b/tools/perf/util/python.c
@@ -342,7 +342,7 @@ static bool is_tracepoint(struct pyrf_event *pevent)
 static PyObject*
 tracepoint_field(struct pyrf_event *pe, struct tep_format_field *field)
 {
-	struct tep_handle *pevent = field->event->pevent;
+	struct tep_handle *pevent = field->event->tep;
 	void *data = pe->sample.raw_data;
 	PyObject *ret = NULL;
 	unsigned long long val;
diff --git a/tools/perf/util/scripting-engines/trace-event-perl.c b/tools/perf/util/scripting-engines/trace-event-perl.c
index 5f06378a482b..61aa7f3df915 100644
--- a/tools/perf/util/scripting-engines/trace-event-perl.c
+++ b/tools/perf/util/scripting-engines/trace-event-perl.c
@@ -372,7 +372,7 @@ static void perl_process_tracepoint(struct perf_sample *sample,
 	ns = nsecs - s * NSEC_PER_SEC;
 
 	scripting_context->event_data = data;
-	scripting_context->pevent = evsel->tp_format->pevent;
+	scripting_context->pevent = evsel->tp_format->tep;
 
 	ENTER;
 	SAVETMPS;
diff --git a/tools/perf/util/scripting-engines/trace-event-python.c b/tools/perf/util/scripting-engines/trace-event-python.c
index 09604c6508f0..22f52b669871 100644
--- a/tools/perf/util/scripting-engines/trace-event-python.c
+++ b/tools/perf/util/scripting-engines/trace-event-python.c
@@ -837,7 +837,7 @@ static void python_process_tracepoint(struct perf_sample *sample,
 	ns = nsecs - s * NSEC_PER_SEC;
 
 	scripting_context->event_data = data;
-	scripting_context->pevent = evsel->tp_format->pevent;
+	scripting_context->pevent = evsel->tp_format->tep;
 
 	context = _PyCapsule_New(scripting_context, NULL, NULL);
 
diff --git a/tools/perf/util/session.c b/tools/perf/util/session.c
index b17f1c9bc965..bad5f87ae001 100644
--- a/tools/perf/util/session.c
+++ b/tools/perf/util/session.c
@@ -1928,12 +1928,14 @@ more:
 
 	size = event->header.size;
 
+	skip = -EINVAL;
+
 	if (size < sizeof(struct perf_event_header) ||
 	    (skip = rd->process(session, event, file_pos)) < 0) {
-		pr_err("%#" PRIx64 " [%#x]: failed to process type: %d\n",
+		pr_err("%#" PRIx64 " [%#x]: failed to process type: %d [%s]\n",
 		       file_offset + head, event->header.size,
-		       event->header.type);
-		err = -EINVAL;
+		       event->header.type, strerror(-skip));
+		err = skip;
 		goto out;
 	}
 
diff --git a/tools/perf/util/stat-display.c b/tools/perf/util/stat-display.c
index 6d043c78f3c2..3324f23c7efc 100644
--- a/tools/perf/util/stat-display.c
+++ b/tools/perf/util/stat-display.c
@@ -18,11 +18,6 @@
 #define CNTR_NOT_SUPPORTED	"<not supported>"
 #define CNTR_NOT_COUNTED	"<not counted>"
 
-static bool is_duration_time(struct perf_evsel *evsel)
-{
-	return !strcmp(evsel->name, "duration_time");
-}
-
 static void print_running(struct perf_stat_config *config,
 			  u64 run, u64 ena)
 {
@@ -628,9 +623,6 @@ static void print_aggr(struct perf_stat_config *config,
 		ad.id = id = config->aggr_map->map[s];
 		first = true;
 		evlist__for_each_entry(evlist, counter) {
-			if (is_duration_time(counter))
-				continue;
-
 			ad.val = ad.ena = ad.run = 0;
 			ad.nr = 0;
 			if (!collect_data(config, counter, aggr_cb, &ad))
@@ -848,8 +840,6 @@ static void print_no_aggr_metric(struct perf_stat_config *config,
 		if (prefix)
 			fputs(prefix, config->output);
 		evlist__for_each_entry(evlist, counter) {
-			if (is_duration_time(counter))
-				continue;
 			if (first) {
 				aggr_printout(config, counter, cpu, 0);
 				first = false;
@@ -906,8 +896,6 @@ static void print_metric_headers(struct perf_stat_config *config,
 
 	/* Print metrics headers only */
 	evlist__for_each_entry(evlist, counter) {
-		if (is_duration_time(counter))
-			continue;
 		os.evsel = counter;
 		out.ctx = &os;
 		out.print_metric = print_metric_header;
@@ -1136,15 +1124,11 @@ perf_evlist__print_counters(struct perf_evlist *evlist,
 		break;
 	case AGGR_THREAD:
 		evlist__for_each_entry(evlist, counter) {
-			if (is_duration_time(counter))
-				continue;
 			print_aggr_thread(config, _target, counter, prefix);
 		}
 		break;
 	case AGGR_GLOBAL:
 		evlist__for_each_entry(evlist, counter) {
-			if (is_duration_time(counter))
-				continue;
 			print_counter_aggr(config, counter, prefix);
 		}
 		if (metric_only)
@@ -1155,8 +1139,6 @@ perf_evlist__print_counters(struct perf_evlist *evlist,
 			print_no_aggr_metric(config, evlist, prefix);
 		else {
 			evlist__for_each_entry(evlist, counter) {
-				if (is_duration_time(counter))
-					continue;
 				print_counter(config, counter, prefix);
 			}
 		}
diff --git a/tools/perf/util/trace-event-parse.c b/tools/perf/util/trace-event-parse.c
index ad74be1f0e42..863955e4094e 100644
--- a/tools/perf/util/trace-event-parse.c
+++ b/tools/perf/util/trace-event-parse.c
@@ -111,7 +111,7 @@ raw_field_value(struct tep_event *event, const char *name, void *data)
 
 unsigned long long read_size(struct tep_event *event, void *ptr, int size)
 {
-	return tep_read_number(event->pevent, ptr, size);
+	return tep_read_number(event->tep, ptr, size);
 }
 
 void event_format__fprintf(struct tep_event *event,
diff --git a/tools/perf/util/trace-event-read.c b/tools/perf/util/trace-event-read.c
index efe2f58cff4e..48d53d8e3e16 100644
--- a/tools/perf/util/trace-event-read.c
+++ b/tools/perf/util/trace-event-read.c
@@ -442,7 +442,7 @@ ssize_t trace_report(int fd, struct trace_event *tevent, bool __repipe)
 
 	tep_set_flag(pevent, TEP_NSEC_OUTPUT);
 	tep_set_file_bigendian(pevent, file_bigendian);
-	tep_set_host_bigendian(pevent, host_bigendian);
+	tep_set_local_bigendian(pevent, host_bigendian);
 
 	if (do_read(buf, 1) < 0)
 		goto out;
diff --git a/tools/perf/util/trace-event.c b/tools/perf/util/trace-event.c
index cbe0dd758e3a..01b9d89bf5bf 100644
--- a/tools/perf/util/trace-event.c
+++ b/tools/perf/util/trace-event.c
@@ -40,7 +40,7 @@ int trace_event__init(struct trace_event *t)
 
 static int trace_event__init2(void)
 {
-	int be = tep_host_bigendian();
+	int be = tep_is_bigendian();
 	struct tep_handle *pevent;
 
 	if (trace_event__init(&tevent))
@@ -49,7 +49,7 @@ static int trace_event__init2(void)
 	pevent = tevent.pevent;
 	tep_set_flag(pevent, TEP_NSEC_OUTPUT);
 	tep_set_file_bigendian(pevent, be);
-	tep_set_host_bigendian(pevent, be);
+	tep_set_local_bigendian(pevent, be);
 	tevent_initialized = true;
 	return 0;
 }
diff --git a/tools/power/acpi/os_specific/service_layers/oslinuxtbl.c b/tools/power/acpi/os_specific/service_layers/oslinuxtbl.c
index 2a1fd9182f94..d1f3d44e315e 100644
--- a/tools/power/acpi/os_specific/service_layers/oslinuxtbl.c
+++ b/tools/power/acpi/os_specific/service_layers/oslinuxtbl.c
@@ -19,7 +19,7 @@ ACPI_MODULE_NAME("oslinuxtbl")
 typedef struct osl_table_info {
 	struct osl_table_info *next;
 	u32 instance;
-	char signature[ACPI_NAME_SIZE];
+	char signature[ACPI_NAMESEG_SIZE];
 
 } osl_table_info;
 
@@ -286,14 +286,14 @@ static acpi_status osl_add_table_to_list(char *signature, u32 instance)
 		return (AE_NO_MEMORY);
 	}
 
-	ACPI_MOVE_NAME(new_info->signature, signature);
+	ACPI_COPY_NAMESEG(new_info->signature, signature);
 
 	if (!gbl_table_list_head) {
 		gbl_table_list_head = new_info;
 	} else {
 		next = gbl_table_list_head;
 		while (1) {
-			if (ACPI_COMPARE_NAME(next->signature, signature)) {
+			if (ACPI_COMPARE_NAMESEG(next->signature, signature)) {
 				if (next->instance == instance) {
 					found = TRUE;
 				}
@@ -782,11 +782,11 @@ osl_get_bios_table(char *signature,
 
 	/* Handle special tables whose addresses are not in RSDT/XSDT */
 
-	if (ACPI_COMPARE_NAME(signature, ACPI_RSDP_NAME) ||
-	    ACPI_COMPARE_NAME(signature, ACPI_SIG_RSDT) ||
-	    ACPI_COMPARE_NAME(signature, ACPI_SIG_XSDT) ||
-	    ACPI_COMPARE_NAME(signature, ACPI_SIG_DSDT) ||
-	    ACPI_COMPARE_NAME(signature, ACPI_SIG_FACS)) {
+	if (ACPI_COMPARE_NAMESEG(signature, ACPI_RSDP_NAME) ||
+	    ACPI_COMPARE_NAMESEG(signature, ACPI_SIG_RSDT) ||
+	    ACPI_COMPARE_NAMESEG(signature, ACPI_SIG_XSDT) ||
+	    ACPI_COMPARE_NAMESEG(signature, ACPI_SIG_DSDT) ||
+	    ACPI_COMPARE_NAMESEG(signature, ACPI_SIG_FACS)) {
 
 find_next_instance:
 
@@ -797,7 +797,7 @@ find_next_instance:
 		 * careful about the FADT length and validate table addresses.
 		 * Note: The 64-bit addresses have priority.
 		 */
-		if (ACPI_COMPARE_NAME(signature, ACPI_SIG_DSDT)) {
+		if (ACPI_COMPARE_NAMESEG(signature, ACPI_SIG_DSDT)) {
 			if (current_instance < 2) {
 				if ((gbl_fadt->header.length >=
 				     MIN_FADT_FOR_XDSDT) && gbl_fadt->Xdsdt
@@ -815,7 +815,7 @@ find_next_instance:
 					    dsdt;
 				}
 			}
-		} else if (ACPI_COMPARE_NAME(signature, ACPI_SIG_FACS)) {
+		} else if (ACPI_COMPARE_NAMESEG(signature, ACPI_SIG_FACS)) {
 			if (current_instance < 2) {
 				if ((gbl_fadt->header.length >=
 				     MIN_FADT_FOR_XFACS) && gbl_fadt->Xfacs
@@ -833,7 +833,7 @@ find_next_instance:
 					    facs;
 				}
 			}
-		} else if (ACPI_COMPARE_NAME(signature, ACPI_SIG_XSDT)) {
+		} else if (ACPI_COMPARE_NAMESEG(signature, ACPI_SIG_XSDT)) {
 			if (!gbl_revision) {
 				return (AE_BAD_SIGNATURE);
 			}
@@ -842,7 +842,7 @@ find_next_instance:
 				    (acpi_physical_address)gbl_rsdp.
 				    xsdt_physical_address;
 			}
-		} else if (ACPI_COMPARE_NAME(signature, ACPI_SIG_RSDT)) {
+		} else if (ACPI_COMPARE_NAMESEG(signature, ACPI_SIG_RSDT)) {
 			if (current_instance == 0) {
 				table_address =
 				    (acpi_physical_address)gbl_rsdp.
@@ -931,7 +931,7 @@ find_next_instance:
 
 			/* Does this table match the requested signature? */
 
-			if (!ACPI_COMPARE_NAME
+			if (!ACPI_COMPARE_NAMESEG
 			    (mapped_table->signature, signature)) {
 				osl_unmap_table(mapped_table);
 				mapped_table = NULL;
@@ -995,7 +995,7 @@ static acpi_status osl_list_customized_tables(char *directory)
 {
 	void *table_dir;
 	u32 instance;
-	char temp_name[ACPI_NAME_SIZE];
+	char temp_name[ACPI_NAMESEG_SIZE];
 	char *filename;
 	acpi_status status = AE_OK;
 
@@ -1086,8 +1086,8 @@ osl_map_table(acpi_size address,
 				return (AE_BAD_SIGNATURE);
 			}
 		} else
-		    if (!ACPI_COMPARE_NAME(signature, mapped_table->signature))
-		{
+		    if (!ACPI_COMPARE_NAMESEG
+			(signature, mapped_table->signature)) {
 			acpi_os_unmap_memory(mapped_table,
 					     sizeof(struct acpi_table_header));
 			return (AE_BAD_SIGNATURE);
@@ -1158,15 +1158,15 @@ osl_table_name_from_file(char *filename, char *signature, u32 *instance)
 
 	/* Ignore meaningless files */
 
-	if (strlen(filename) < ACPI_NAME_SIZE) {
+	if (strlen(filename) < ACPI_NAMESEG_SIZE) {
 		return (AE_BAD_SIGNATURE);
 	}
 
 	/* Extract instance number */
 
-	if (isdigit((int)filename[ACPI_NAME_SIZE])) {
-		sscanf(&filename[ACPI_NAME_SIZE], "%u", instance);
-	} else if (strlen(filename) != ACPI_NAME_SIZE) {
+	if (isdigit((int)filename[ACPI_NAMESEG_SIZE])) {
+		sscanf(&filename[ACPI_NAMESEG_SIZE], "%u", instance);
+	} else if (strlen(filename) != ACPI_NAMESEG_SIZE) {
 		return (AE_BAD_SIGNATURE);
 	} else {
 		*instance = 0;
@@ -1174,7 +1174,7 @@ osl_table_name_from_file(char *filename, char *signature, u32 *instance)
 
 	/* Extract signature */
 
-	ACPI_MOVE_NAME(signature, filename);
+	ACPI_COPY_NAMESEG(signature, filename);
 	return (AE_OK);
 }
 
@@ -1236,7 +1236,7 @@ osl_read_table_from_file(char *filename,
 				status = AE_BAD_SIGNATURE;
 				goto exit;
 			}
-		} else if (!ACPI_COMPARE_NAME(signature, header.signature)) {
+		} else if (!ACPI_COMPARE_NAMESEG(signature, header.signature)) {
 			fprintf(stderr,
 				"Incorrect signature: Expecting %4.4s, found %4.4s\n",
 				signature, header.signature);
@@ -1311,7 +1311,7 @@ osl_get_customized_table(char *pathname,
 {
 	void *table_dir;
 	u32 current_instance = 0;
-	char temp_name[ACPI_NAME_SIZE];
+	char temp_name[ACPI_NAMESEG_SIZE];
 	char table_filename[PATH_MAX];
 	char *filename;
 	acpi_status status;
@@ -1329,7 +1329,7 @@ osl_get_customized_table(char *pathname,
 
 		/* Ignore meaningless files */
 
-		if (!ACPI_COMPARE_NAME(filename, signature)) {
+		if (!ACPI_COMPARE_NAMESEG(filename, signature)) {
 			continue;
 		}
 
diff --git a/tools/power/acpi/tools/acpidump/apdump.c b/tools/power/acpi/tools/acpidump/apdump.c
index e256c2ac5ddc..820baeb5092b 100644
--- a/tools/power/acpi/tools/acpidump/apdump.c
+++ b/tools/power/acpi/tools/acpidump/apdump.c
@@ -289,14 +289,14 @@ int ap_dump_table_by_address(char *ascii_address)
 
 int ap_dump_table_by_name(char *signature)
 {
-	char local_signature[ACPI_NAME_SIZE + 1];
+	char local_signature[ACPI_NAMESEG_SIZE + 1];
 	u32 instance;
 	struct acpi_table_header *table;
 	acpi_physical_address address;
 	acpi_status status;
 	int table_status;
 
-	if (strlen(signature) != ACPI_NAME_SIZE) {
+	if (strlen(signature) != ACPI_NAMESEG_SIZE) {
 		fprintf(stderr,
 			"Invalid table signature [%s]: must be exactly 4 characters\n",
 			signature);
@@ -310,9 +310,9 @@ int ap_dump_table_by_name(char *signature)
 
 	/* To be friendly, handle tables whose signatures do not match the name */
 
-	if (ACPI_COMPARE_NAME(local_signature, "FADT")) {
+	if (ACPI_COMPARE_NAMESEG(local_signature, "FADT")) {
 		strcpy(local_signature, ACPI_SIG_FADT);
-	} else if (ACPI_COMPARE_NAME(local_signature, "MADT")) {
+	} else if (ACPI_COMPARE_NAMESEG(local_signature, "MADT")) {
 		strcpy(local_signature, ACPI_SIG_MADT);
 	}
 
diff --git a/tools/power/acpi/tools/acpidump/apfiles.c b/tools/power/acpi/tools/acpidump/apfiles.c
index 49972bc78bc5..a42cfcaa3293 100644
--- a/tools/power/acpi/tools/acpidump/apfiles.c
+++ b/tools/power/acpi/tools/acpidump/apfiles.c
@@ -97,7 +97,7 @@ int ap_open_output_file(char *pathname)
 
 int ap_write_to_binary_file(struct acpi_table_header *table, u32 instance)
 {
-	char filename[ACPI_NAME_SIZE + 16];
+	char filename[ACPI_NAMESEG_SIZE + 16];
 	char instance_str[16];
 	ACPI_FILE file;
 	acpi_size actual;
@@ -110,16 +110,16 @@ int ap_write_to_binary_file(struct acpi_table_header *table, u32 instance)
 	/* Construct lower-case filename from the table local signature */
 
 	if (ACPI_VALIDATE_RSDP_SIG(table->signature)) {
-		ACPI_MOVE_NAME(filename, ACPI_RSDP_NAME);
+		ACPI_COPY_NAMESEG(filename, ACPI_RSDP_NAME);
 	} else {
-		ACPI_MOVE_NAME(filename, table->signature);
+		ACPI_COPY_NAMESEG(filename, table->signature);
 	}
 
 	filename[0] = (char)tolower((int)filename[0]);
 	filename[1] = (char)tolower((int)filename[1]);
 	filename[2] = (char)tolower((int)filename[2]);
 	filename[3] = (char)tolower((int)filename[3]);
-	filename[ACPI_NAME_SIZE] = 0;
+	filename[ACPI_NAMESEG_SIZE] = 0;
 
 	/* Handle multiple SSDts - create different filenames for each */
 
diff --git a/tools/power/x86/turbostat/turbostat.c b/tools/power/x86/turbostat/turbostat.c
index c3fad065c89c..c7727be9719f 100644
--- a/tools/power/x86/turbostat/turbostat.c
+++ b/tools/power/x86/turbostat/turbostat.c
@@ -44,6 +44,7 @@
 #include <cpuid.h>
 #include <linux/capability.h>
 #include <errno.h>
+#include <math.h>
 
 char *proc_stat = "/proc/stat";
 FILE *outf;
@@ -63,7 +64,6 @@ unsigned int dump_only;
 unsigned int do_snb_cstates;
 unsigned int do_knl_cstates;
 unsigned int do_slm_cstates;
-unsigned int do_cnl_cstates;
 unsigned int use_c1_residency_msr;
 unsigned int has_aperf;
 unsigned int has_epb;
@@ -141,9 +141,21 @@ unsigned int first_counter_read = 1;
 
 #define RAPL_CORES_ENERGY_STATUS	(1 << 9)
 					/* 0x639 MSR_PP0_ENERGY_STATUS */
+#define RAPL_PER_CORE_ENERGY	(1 << 10)
+					/* Indicates cores energy collection is per-core,
+					 * not per-package. */
+#define RAPL_AMD_F17H		(1 << 11)
+					/* 0xc0010299 MSR_RAPL_PWR_UNIT */
+					/* 0xc001029a MSR_CORE_ENERGY_STAT */
+					/* 0xc001029b MSR_PKG_ENERGY_STAT */
 #define RAPL_CORES (RAPL_CORES_ENERGY_STATUS | RAPL_CORES_POWER_LIMIT)
 #define	TJMAX_DEFAULT	100
 
+/* MSRs that are not yet in the kernel-provided header. */
+#define MSR_RAPL_PWR_UNIT	0xc0010299
+#define MSR_CORE_ENERGY_STAT	0xc001029a
+#define MSR_PKG_ENERGY_STAT	0xc001029b
+
 #define MAX(a, b) ((a) > (b) ? (a) : (b))
 
 /*
@@ -187,6 +199,7 @@ struct core_data {
 	unsigned long long c7;
 	unsigned long long mc6_us;	/* duplicate as per-core for now, even though per module */
 	unsigned int core_temp_c;
+	unsigned int core_energy;	/* MSR_CORE_ENERGY_STAT */
 	unsigned int core_id;
 	unsigned long long counter[MAX_ADDED_COUNTERS];
 } *core_even, *core_odd;
@@ -273,6 +286,7 @@ struct system_summary {
 
 struct cpu_topology {
 	int physical_package_id;
+	int die_id;
 	int logical_cpu_id;
 	int physical_node_id;
 	int logical_node_id;	/* 0-based count within the package */
@@ -283,6 +297,7 @@ struct cpu_topology {
 
 struct topo_params {
 	int num_packages;
+	int num_die;
 	int num_cpus;
 	int num_cores;
 	int max_cpu_num;
@@ -314,9 +329,8 @@ int for_all_cpus(int (func)(struct thread_data *, struct core_data *, struct pkg
 	int retval, pkg_no, core_no, thread_no, node_no;
 
 	for (pkg_no = 0; pkg_no < topo.num_packages; ++pkg_no) {
-		for (core_no = 0; core_no < topo.cores_per_node; ++core_no) {
-			for (node_no = 0; node_no < topo.nodes_per_pkg;
-			     node_no++) {
+		for (node_no = 0; node_no < topo.nodes_per_pkg; node_no++) {
+			for (core_no = 0; core_no < topo.cores_per_node; ++core_no) {
 				for (thread_no = 0; thread_no <
 					topo.threads_per_core; ++thread_no) {
 					struct thread_data *t;
@@ -442,6 +456,7 @@ struct msr_counter bic[] = {
 	{ 0x0, "CPU" },
 	{ 0x0, "APIC" },
 	{ 0x0, "X2APIC" },
+	{ 0x0, "Die" },
 };
 
 #define MAX_BIC (sizeof(bic) / sizeof(struct msr_counter))
@@ -495,6 +510,7 @@ struct msr_counter bic[] = {
 #define	BIC_CPU		(1ULL << 47)
 #define	BIC_APIC	(1ULL << 48)
 #define	BIC_X2APIC	(1ULL << 49)
+#define	BIC_Die		(1ULL << 50)
 
 #define BIC_DISABLED_BY_DEFAULT	(BIC_USEC | BIC_TOD | BIC_APIC | BIC_X2APIC)
 
@@ -621,6 +637,8 @@ void print_header(char *delim)
 		outp += sprintf(outp, "%sTime_Of_Day_Seconds", (printed++ ? delim : ""));
 	if (DO_BIC(BIC_Package))
 		outp += sprintf(outp, "%sPackage", (printed++ ? delim : ""));
+	if (DO_BIC(BIC_Die))
+		outp += sprintf(outp, "%sDie", (printed++ ? delim : ""));
 	if (DO_BIC(BIC_Node))
 		outp += sprintf(outp, "%sNode", (printed++ ? delim : ""));
 	if (DO_BIC(BIC_Core))
@@ -667,7 +685,7 @@ void print_header(char *delim)
 
 	if (DO_BIC(BIC_CPU_c1))
 		outp += sprintf(outp, "%sCPU%%c1", (printed++ ? delim : ""));
-	if (DO_BIC(BIC_CPU_c3) && !do_slm_cstates && !do_knl_cstates && !do_cnl_cstates)
+	if (DO_BIC(BIC_CPU_c3))
 		outp += sprintf(outp, "%sCPU%%c3", (printed++ ? delim : ""));
 	if (DO_BIC(BIC_CPU_c6))
 		outp += sprintf(outp, "%sCPU%%c6", (printed++ ? delim : ""));
@@ -680,6 +698,14 @@ void print_header(char *delim)
 	if (DO_BIC(BIC_CoreTmp))
 		outp += sprintf(outp, "%sCoreTmp", (printed++ ? delim : ""));
 
+	if (do_rapl && !rapl_joules) {
+		if (DO_BIC(BIC_CorWatt) && (do_rapl & RAPL_PER_CORE_ENERGY))
+			outp += sprintf(outp, "%sCorWatt", (printed++ ? delim : ""));
+	} else if (do_rapl && rapl_joules) {
+		if (DO_BIC(BIC_Cor_J) && (do_rapl & RAPL_PER_CORE_ENERGY))
+			outp += sprintf(outp, "%sCor_J", (printed++ ? delim : ""));
+	}
+
 	for (mp = sys.cp; mp; mp = mp->next) {
 		if (mp->format == FORMAT_RAW) {
 			if (mp->width == 64)
@@ -734,7 +760,7 @@ void print_header(char *delim)
 	if (do_rapl && !rapl_joules) {
 		if (DO_BIC(BIC_PkgWatt))
 			outp += sprintf(outp, "%sPkgWatt", (printed++ ? delim : ""));
-		if (DO_BIC(BIC_CorWatt))
+		if (DO_BIC(BIC_CorWatt) && !(do_rapl & RAPL_PER_CORE_ENERGY))
 			outp += sprintf(outp, "%sCorWatt", (printed++ ? delim : ""));
 		if (DO_BIC(BIC_GFXWatt))
 			outp += sprintf(outp, "%sGFXWatt", (printed++ ? delim : ""));
@@ -747,7 +773,7 @@ void print_header(char *delim)
 	} else if (do_rapl && rapl_joules) {
 		if (DO_BIC(BIC_Pkg_J))
 			outp += sprintf(outp, "%sPkg_J", (printed++ ? delim : ""));
-		if (DO_BIC(BIC_Cor_J))
+		if (DO_BIC(BIC_Cor_J) && !(do_rapl & RAPL_PER_CORE_ENERGY))
 			outp += sprintf(outp, "%sCor_J", (printed++ ? delim : ""));
 		if (DO_BIC(BIC_GFX_J))
 			outp += sprintf(outp, "%sGFX_J", (printed++ ? delim : ""));
@@ -808,6 +834,7 @@ int dump_counters(struct thread_data *t, struct core_data *c,
 		outp += sprintf(outp, "c6: %016llX\n", c->c6);
 		outp += sprintf(outp, "c7: %016llX\n", c->c7);
 		outp += sprintf(outp, "DTS: %dC\n", c->core_temp_c);
+		outp += sprintf(outp, "Joules: %0X\n", c->core_energy);
 
 		for (i = 0, mp = sys.cp; mp; i++, mp = mp->next) {
 			outp += sprintf(outp, "cADDED [%d] msr0x%x: %08llX\n",
@@ -904,6 +931,8 @@ int format_counters(struct thread_data *t, struct core_data *c,
 	if (t == &average.threads) {
 		if (DO_BIC(BIC_Package))
 			outp += sprintf(outp, "%s-", (printed++ ? delim : ""));
+		if (DO_BIC(BIC_Die))
+			outp += sprintf(outp, "%s-", (printed++ ? delim : ""));
 		if (DO_BIC(BIC_Node))
 			outp += sprintf(outp, "%s-", (printed++ ? delim : ""));
 		if (DO_BIC(BIC_Core))
@@ -921,6 +950,12 @@ int format_counters(struct thread_data *t, struct core_data *c,
 			else
 				outp += sprintf(outp, "%s-", (printed++ ? delim : ""));
 		}
+		if (DO_BIC(BIC_Die)) {
+			if (c)
+				outp += sprintf(outp, "%s%d", (printed++ ? delim : ""), cpus[t->cpu_id].die_id);
+			else
+				outp += sprintf(outp, "%s-", (printed++ ? delim : ""));
+		}
 		if (DO_BIC(BIC_Node)) {
 			if (t)
 				outp += sprintf(outp, "%s%d",
@@ -1003,7 +1038,7 @@ int format_counters(struct thread_data *t, struct core_data *c,
 	if (!(t->flags & CPU_IS_FIRST_THREAD_IN_CORE))
 		goto done;
 
-	if (DO_BIC(BIC_CPU_c3) && !do_slm_cstates && !do_knl_cstates && !do_cnl_cstates)
+	if (DO_BIC(BIC_CPU_c3))
 		outp += sprintf(outp, "%s%.2f", (printed++ ? delim : ""), 100.0 * c->c3/tsc);
 	if (DO_BIC(BIC_CPU_c6))
 		outp += sprintf(outp, "%s%.2f", (printed++ ? delim : ""), 100.0 * c->c6/tsc);
@@ -1033,6 +1068,20 @@ int format_counters(struct thread_data *t, struct core_data *c,
 		}
 	}
 
+	/*
+	 * If measurement interval exceeds minimum RAPL Joule Counter range,
+	 * indicate that results are suspect by printing "**" in fraction place.
+	 */
+	if (interval_float < rapl_joule_counter_range)
+		fmt8 = "%s%.2f";
+	else
+		fmt8 = "%6.0f**";
+
+	if (DO_BIC(BIC_CorWatt) && (do_rapl & RAPL_PER_CORE_ENERGY))
+		outp += sprintf(outp, fmt8, (printed++ ? delim : ""), c->core_energy * rapl_energy_units / interval_float);
+	if (DO_BIC(BIC_Cor_J) && (do_rapl & RAPL_PER_CORE_ENERGY))
+		outp += sprintf(outp, fmt8, (printed++ ? delim : ""), c->core_energy * rapl_energy_units);
+
 	/* print per-package data only for 1st core in package */
 	if (!(t->flags & CPU_IS_FIRST_CORE_IN_PACKAGE))
 		goto done;
@@ -1085,18 +1134,9 @@ int format_counters(struct thread_data *t, struct core_data *c,
 	if (DO_BIC(BIC_SYS_LPI))
 		outp += sprintf(outp, "%s%.2f", (printed++ ? delim : ""), 100.0 * p->sys_lpi / 1000000.0 / interval_float);
 
-	/*
- 	 * If measurement interval exceeds minimum RAPL Joule Counter range,
- 	 * indicate that results are suspect by printing "**" in fraction place.
- 	 */
-	if (interval_float < rapl_joule_counter_range)
-		fmt8 = "%s%.2f";
-	else
-		fmt8 = "%6.0f**";
-
 	if (DO_BIC(BIC_PkgWatt))
 		outp += sprintf(outp, fmt8, (printed++ ? delim : ""), p->energy_pkg * rapl_energy_units / interval_float);
-	if (DO_BIC(BIC_CorWatt))
+	if (DO_BIC(BIC_CorWatt) && !(do_rapl & RAPL_PER_CORE_ENERGY))
 		outp += sprintf(outp, fmt8, (printed++ ? delim : ""), p->energy_cores * rapl_energy_units / interval_float);
 	if (DO_BIC(BIC_GFXWatt))
 		outp += sprintf(outp, fmt8, (printed++ ? delim : ""), p->energy_gfx * rapl_energy_units / interval_float);
@@ -1104,7 +1144,7 @@ int format_counters(struct thread_data *t, struct core_data *c,
 		outp += sprintf(outp, fmt8, (printed++ ? delim : ""), p->energy_dram * rapl_dram_energy_units / interval_float);
 	if (DO_BIC(BIC_Pkg_J))
 		outp += sprintf(outp, fmt8, (printed++ ? delim : ""), p->energy_pkg * rapl_energy_units);
-	if (DO_BIC(BIC_Cor_J))
+	if (DO_BIC(BIC_Cor_J) && !(do_rapl & RAPL_PER_CORE_ENERGY))
 		outp += sprintf(outp, fmt8, (printed++ ? delim : ""), p->energy_cores * rapl_energy_units);
 	if (DO_BIC(BIC_GFX_J))
 		outp += sprintf(outp, fmt8, (printed++ ? delim : ""), p->energy_gfx * rapl_energy_units);
@@ -1249,6 +1289,8 @@ delta_core(struct core_data *new, struct core_data *old)
 	old->core_temp_c = new->core_temp_c;
 	old->mc6_us = new->mc6_us - old->mc6_us;
 
+	DELTA_WRAP32(new->core_energy, old->core_energy);
+
 	for (i = 0, mp = sys.cp; mp; i++, mp = mp->next) {
 		if (mp->format == FORMAT_RAW)
 			old->counter[i] = new->counter[i];
@@ -1391,6 +1433,7 @@ void clear_counters(struct thread_data *t, struct core_data *c, struct pkg_data
 	c->c7 = 0;
 	c->mc6_us = 0;
 	c->core_temp_c = 0;
+	c->core_energy = 0;
 
 	p->pkg_wtd_core_c0 = 0;
 	p->pkg_any_core_c0 = 0;
@@ -1473,6 +1516,8 @@ int sum_counters(struct thread_data *t, struct core_data *c,
 
 	average.cores.core_temp_c = MAX(average.cores.core_temp_c, c->core_temp_c);
 
+	average.cores.core_energy += c->core_energy;
+
 	for (i = 0, mp = sys.cp; mp; i++, mp = mp->next) {
 		if (mp->format == FORMAT_RAW)
 			continue;
@@ -1818,7 +1863,7 @@ retry:
 	if (!(t->flags & CPU_IS_FIRST_THREAD_IN_CORE))
 		goto done;
 
-	if (DO_BIC(BIC_CPU_c3) && !do_slm_cstates && !do_knl_cstates && !do_cnl_cstates) {
+	if (DO_BIC(BIC_CPU_c3)) {
 		if (get_msr(cpu, MSR_CORE_C3_RESIDENCY, &c->c3))
 			return -6;
 	}
@@ -1845,6 +1890,12 @@ retry:
 		c->core_temp_c = tcc_activation_temp - ((msr >> 16) & 0x7F);
 	}
 
+	if (do_rapl & RAPL_AMD_F17H) {
+		if (get_msr(cpu, MSR_CORE_ENERGY_STAT, &msr))
+			return -14;
+		c->core_energy = msr & 0xFFFFFFFF;
+	}
+
 	for (i = 0, mp = sys.cp; mp; i++, mp = mp->next) {
 		if (get_mp(cpu, mp, &c->counter[i]))
 			return -10;
@@ -1934,6 +1985,11 @@ retry:
 			return -16;
 		p->rapl_dram_perf_status = msr & 0xFFFFFFFF;
 	}
+	if (do_rapl & RAPL_AMD_F17H) {
+		if (get_msr(cpu, MSR_PKG_ENERGY_STAT, &msr))
+			return -13;
+		p->energy_pkg = msr & 0xFFFFFFFF;
+	}
 	if (DO_BIC(BIC_PkgTmp)) {
 		if (get_msr(cpu, MSR_IA32_PACKAGE_THERM_STATUS, &msr))
 			return -17;
@@ -2456,6 +2512,8 @@ void free_all_buffers(void)
 
 /*
  * Parse a file containing a single int.
+ * Return 0 if file can not be opened
+ * Exit if file can be opened, but can not be parsed
  */
 int parse_int_file(const char *fmt, ...)
 {
@@ -2467,7 +2525,9 @@ int parse_int_file(const char *fmt, ...)
 	va_start(args, fmt);
 	vsnprintf(path, sizeof(path), fmt, args);
 	va_end(args);
-	filep = fopen_or_die(path, "r");
+	filep = fopen(path, "r");
+	if (!filep)
+		return 0;
 	if (fscanf(filep, "%d", &value) != 1)
 		err(1, "%s: failed to parse number from file", path);
 	fclose(filep);
@@ -2488,6 +2548,11 @@ int get_physical_package_id(int cpu)
 	return parse_int_file("/sys/devices/system/cpu/cpu%d/topology/physical_package_id", cpu);
 }
 
+int get_die_id(int cpu)
+{
+	return parse_int_file("/sys/devices/system/cpu/cpu%d/topology/die_id", cpu);
+}
+
 int get_core_id(int cpu)
 {
 	return parse_int_file("/sys/devices/system/cpu/cpu%d/topology/core_id", cpu);
@@ -2578,7 +2643,8 @@ int get_thread_siblings(struct cpu_topology *thiscpu)
 	filep = fopen_or_die(path, "r");
 	do {
 		offset -= BITMASK_SIZE;
-		fscanf(filep, "%lx%c", &map, &character);
+		if (fscanf(filep, "%lx%c", &map, &character) != 2)
+			err(1, "%s: failed to parse file", path);
 		for (shift = 0; shift < BITMASK_SIZE; shift++) {
 			if ((map >> shift) & 0x1) {
 				so = shift + offset;
@@ -2855,8 +2921,11 @@ int snapshot_cpu_lpi_us(void)
 	fp = fopen_or_die("/sys/devices/system/cpu/cpuidle/low_power_idle_cpu_residency_us", "r");
 
 	retval = fscanf(fp, "%lld", &cpuidle_cur_cpu_lpi_us);
-	if (retval != 1)
-		err(1, "CPU LPI");
+	if (retval != 1) {
+		fprintf(stderr, "Disabling Low Power Idle CPU output\n");
+		BIC_NOT_PRESENT(BIC_CPU_LPI);
+		return -1;
+	}
 
 	fclose(fp);
 
@@ -2878,9 +2947,11 @@ int snapshot_sys_lpi_us(void)
 	fp = fopen_or_die("/sys/devices/system/cpu/cpuidle/low_power_idle_system_residency_us", "r");
 
 	retval = fscanf(fp, "%lld", &cpuidle_cur_sys_lpi_us);
-	if (retval != 1)
-		err(1, "SYS LPI");
-
+	if (retval != 1) {
+		fprintf(stderr, "Disabling Low Power Idle System output\n");
+		BIC_NOT_PRESENT(BIC_SYS_LPI);
+		return -1;
+	}
 	fclose(fp);
 
 	return 0;
@@ -3410,14 +3481,14 @@ dump_sysfs_cstate_config(void)
 		input = fopen(path, "r");
 		if (input == NULL)
 			continue;
-		fgets(name_buf, sizeof(name_buf), input);
+		if (!fgets(name_buf, sizeof(name_buf), input))
+			err(1, "%s: failed to read file", path);
 
 		 /* truncate "C1-HSW\n" to "C1", or truncate "C1\n" to "C1" */
 		sp = strchr(name_buf, '-');
 		if (!sp)
 			sp = strchrnul(name_buf, '\n');
 		*sp = '\0';
-
 		fclose(input);
 
 		sprintf(path, "/sys/devices/system/cpu/cpu%d/cpuidle/state%d/desc",
@@ -3425,7 +3496,8 @@ dump_sysfs_cstate_config(void)
 		input = fopen(path, "r");
 		if (input == NULL)
 			continue;
-		fgets(desc, sizeof(desc), input);
+		if (!fgets(desc, sizeof(desc), input))
+			err(1, "%s: failed to read file", path);
 
 		fprintf(outf, "cpu%d: %s: %s", base_cpu, name_buf, desc);
 		fclose(input);
@@ -3444,20 +3516,22 @@ dump_sysfs_pstate_config(void)
 			base_cpu);
 	input = fopen(path, "r");
 	if (input == NULL) {
-		fprintf(stderr, "NSFOD %s\n", path);
+		fprintf(outf, "NSFOD %s\n", path);
 		return;
 	}
-	fgets(driver_buf, sizeof(driver_buf), input);
+	if (!fgets(driver_buf, sizeof(driver_buf), input))
+		err(1, "%s: failed to read file", path);
 	fclose(input);
 
 	sprintf(path, "/sys/devices/system/cpu/cpu%d/cpufreq/scaling_governor",
 			base_cpu);
 	input = fopen(path, "r");
 	if (input == NULL) {
-		fprintf(stderr, "NSFOD %s\n", path);
+		fprintf(outf, "NSFOD %s\n", path);
 		return;
 	}
-	fgets(governor_buf, sizeof(governor_buf), input);
+	if (!fgets(governor_buf, sizeof(governor_buf), input))
+		err(1, "%s: failed to read file", path);
 	fclose(input);
 
 	fprintf(outf, "cpu%d: cpufreq driver: %s", base_cpu, driver_buf);
@@ -3466,7 +3540,8 @@ dump_sysfs_pstate_config(void)
 	sprintf(path, "/sys/devices/system/cpu/cpufreq/boost");
 	input = fopen(path, "r");
 	if (input != NULL) {
-		fscanf(input, "%d", &turbo);
+		if (fscanf(input, "%d", &turbo) != 1)
+			err(1, "%s: failed to parse number from file", path);
 		fprintf(outf, "cpufreq boost: %d\n", turbo);
 		fclose(input);
 	}
@@ -3474,7 +3549,8 @@ dump_sysfs_pstate_config(void)
 	sprintf(path, "/sys/devices/system/cpu/intel_pstate/no_turbo");
 	input = fopen(path, "r");
 	if (input != NULL) {
-		fscanf(input, "%d", &turbo);
+		if (fscanf(input, "%d", &turbo) != 1)
+			err(1, "%s: failed to parse number from file", path);
 		fprintf(outf, "cpufreq intel_pstate no_turbo: %d\n", turbo);
 		fclose(input);
 	}
@@ -3718,7 +3794,7 @@ int print_perf_limit(struct thread_data *t, struct core_data *c, struct pkg_data
 #define	RAPL_POWER_GRANULARITY	0x7FFF	/* 15 bit power granularity */
 #define	RAPL_TIME_GRANULARITY	0x3F /* 6 bit time granularity */
 
-double get_tdp(unsigned int model)
+double get_tdp_intel(unsigned int model)
 {
 	unsigned long long msr;
 
@@ -3735,6 +3811,16 @@ double get_tdp(unsigned int model)
 	}
 }
 
+double get_tdp_amd(unsigned int family)
+{
+	switch (family) {
+	case 0x17:
+	default:
+		/* This is the max stock TDP of HEDT/Server Fam17h chips */
+		return 250.0;
+	}
+}
+
 /*
  * rapl_dram_energy_units_probe()
  * Energy units are either hard-coded, or come from RAPL Energy Unit MSR.
@@ -3754,21 +3840,12 @@ rapl_dram_energy_units_probe(int  model, double rapl_energy_units)
 	}
 }
 
-
-/*
- * rapl_probe()
- *
- * sets do_rapl, rapl_power_units, rapl_energy_units, rapl_time_units
- */
-void rapl_probe(unsigned int family, unsigned int model)
+void rapl_probe_intel(unsigned int family, unsigned int model)
 {
 	unsigned long long msr;
 	unsigned int time_unit;
 	double tdp;
 
-	if (!genuine_intel)
-		return;
-
 	if (family != 6)
 		return;
 
@@ -3892,13 +3969,69 @@ void rapl_probe(unsigned int family, unsigned int model)
 
 	rapl_time_units = 1.0 / (1 << (time_unit));
 
-	tdp = get_tdp(model);
+	tdp = get_tdp_intel(model);
 
 	rapl_joule_counter_range = 0xFFFFFFFF * rapl_energy_units / tdp;
 	if (!quiet)
 		fprintf(outf, "RAPL: %.0f sec. Joule Counter Range, at %.0f Watts\n", rapl_joule_counter_range, tdp);
+}
 
-	return;
+void rapl_probe_amd(unsigned int family, unsigned int model)
+{
+	unsigned long long msr;
+	unsigned int eax, ebx, ecx, edx;
+	unsigned int has_rapl = 0;
+	double tdp;
+
+	if (max_extended_level >= 0x80000007) {
+		__cpuid(0x80000007, eax, ebx, ecx, edx);
+		/* RAPL (Fam 17h) */
+		has_rapl = edx & (1 << 14);
+	}
+
+	if (!has_rapl)
+		return;
+
+	switch (family) {
+	case 0x17: /* Zen, Zen+ */
+		do_rapl = RAPL_AMD_F17H | RAPL_PER_CORE_ENERGY;
+		if (rapl_joules) {
+			BIC_PRESENT(BIC_Pkg_J);
+			BIC_PRESENT(BIC_Cor_J);
+		} else {
+			BIC_PRESENT(BIC_PkgWatt);
+			BIC_PRESENT(BIC_CorWatt);
+		}
+		break;
+	default:
+		return;
+	}
+
+	if (get_msr(base_cpu, MSR_RAPL_PWR_UNIT, &msr))
+		return;
+
+	rapl_time_units = ldexp(1.0, -(msr >> 16 & 0xf));
+	rapl_energy_units = ldexp(1.0, -(msr >> 8 & 0x1f));
+	rapl_power_units = ldexp(1.0, -(msr & 0xf));
+
+	tdp = get_tdp_amd(model);
+
+	rapl_joule_counter_range = 0xFFFFFFFF * rapl_energy_units / tdp;
+	if (!quiet)
+		fprintf(outf, "RAPL: %.0f sec. Joule Counter Range, at %.0f Watts\n", rapl_joule_counter_range, tdp);
+}
+
+/*
+ * rapl_probe()
+ *
+ * sets do_rapl, rapl_power_units, rapl_energy_units, rapl_time_units
+ */
+void rapl_probe(unsigned int family, unsigned int model)
+{
+	if (genuine_intel)
+		rapl_probe_intel(family, model);
+	if (authentic_amd)
+		rapl_probe_amd(family, model);
 }
 
 void perf_limit_reasons_probe(unsigned int family, unsigned int model)
@@ -4003,6 +4136,7 @@ void print_power_limit_msr(int cpu, unsigned long long msr, char *label)
 int print_rapl(struct thread_data *t, struct core_data *c, struct pkg_data *p)
 {
 	unsigned long long msr;
+	const char *msr_name;
 	int cpu;
 
 	if (!do_rapl)
@@ -4018,10 +4152,17 @@ int print_rapl(struct thread_data *t, struct core_data *c, struct pkg_data *p)
 		return -1;
 	}
 
-	if (get_msr(cpu, MSR_RAPL_POWER_UNIT, &msr))
-		return -1;
+	if (do_rapl & RAPL_AMD_F17H) {
+		msr_name = "MSR_RAPL_PWR_UNIT";
+		if (get_msr(cpu, MSR_RAPL_PWR_UNIT, &msr))
+			return -1;
+	} else {
+		msr_name = "MSR_RAPL_POWER_UNIT";
+		if (get_msr(cpu, MSR_RAPL_POWER_UNIT, &msr))
+			return -1;
+	}
 
-	fprintf(outf, "cpu%d: MSR_RAPL_POWER_UNIT: 0x%08llx (%f Watts, %f Joules, %f sec.)\n", cpu, msr,
+	fprintf(outf, "cpu%d: %s: 0x%08llx (%f Watts, %f Joules, %f sec.)\n", cpu, msr_name, msr,
 		rapl_power_units, rapl_energy_units, rapl_time_units);
 
 	if (do_rapl & RAPL_PKG_POWER_INFO) {
@@ -4451,6 +4592,9 @@ unsigned int intel_model_duplicates(unsigned int model)
 	case INTEL_FAM6_KABYLAKE_MOBILE:
 	case INTEL_FAM6_KABYLAKE_DESKTOP:
 		return INTEL_FAM6_SKYLAKE_MOBILE;
+
+	case INTEL_FAM6_ICELAKE_MOBILE:
+		return INTEL_FAM6_CANNONLAKE_MOBILE;
 	}
 	return model;
 }
@@ -4702,7 +4846,9 @@ void process_cpuid()
 	}
 	do_slm_cstates = is_slm(family, model);
 	do_knl_cstates  = is_knl(family, model);
-	do_cnl_cstates = is_cnl(family, model);
+
+	if (do_slm_cstates || do_knl_cstates || is_cnl(family, model))
+		BIC_NOT_PRESENT(BIC_CPU_c3);
 
 	if (!quiet)
 		decode_misc_pwr_mgmt_msr();
@@ -4769,6 +4915,7 @@ void topology_probe()
 	int i;
 	int max_core_id = 0;
 	int max_package_id = 0;
+	int max_die_id = 0;
 	int max_siblings = 0;
 
 	/* Initialize num_cpus, max_cpu_num */
@@ -4835,6 +4982,11 @@ void topology_probe()
 		if (cpus[i].physical_package_id > max_package_id)
 			max_package_id = cpus[i].physical_package_id;
 
+		/* get die information */
+		cpus[i].die_id = get_die_id(i);
+		if (cpus[i].die_id > max_die_id)
+			max_die_id = cpus[i].die_id;
+
 		/* get numa node information */
 		cpus[i].physical_node_id = get_physical_node_id(&cpus[i]);
 		if (cpus[i].physical_node_id > topo.max_node_num)
@@ -4860,6 +5012,13 @@ void topology_probe()
 	if (!summary_only && topo.cores_per_node > 1)
 		BIC_PRESENT(BIC_Core);
 
+	topo.num_die = max_die_id + 1;
+	if (debug > 1)
+		fprintf(outf, "max_die_id %d, sizing for %d die\n",
+				max_die_id, topo.num_die);
+	if (!summary_only && topo.num_die > 1)
+		BIC_PRESENT(BIC_Die);
+
 	topo.num_packages = max_package_id + 1;
 	if (debug > 1)
 		fprintf(outf, "max_package_id %d, sizing for %d packages\n",
@@ -4884,8 +5043,8 @@ void topology_probe()
 		if (cpu_is_not_present(i))
 			continue;
 		fprintf(outf,
-			"cpu %d pkg %d node %d lnode %d core %d thread %d\n",
-			i, cpus[i].physical_package_id,
+			"cpu %d pkg %d die %d node %d lnode %d core %d thread %d\n",
+			i, cpus[i].physical_package_id, cpus[i].die_id,
 			cpus[i].physical_node_id,
 			cpus[i].logical_node_id,
 			cpus[i].physical_core_id,
@@ -5122,7 +5281,7 @@ int get_and_dump_counters(void)
 }
 
 void print_version() {
-	fprintf(outf, "turbostat version 18.07.27"
+	fprintf(outf, "turbostat version 19.03.20"
 		" - Len Brown <lenb@kernel.org>\n");
 }
 
@@ -5319,7 +5478,8 @@ void probe_sysfs(void)
 		input = fopen(path, "r");
 		if (input == NULL)
 			continue;
-		fgets(name_buf, sizeof(name_buf), input);
+		if (!fgets(name_buf, sizeof(name_buf), input))
+			err(1, "%s: failed to read file", path);
 
 		 /* truncate "C1-HSW\n" to "C1", or truncate "C1\n" to "C1" */
 		sp = strchr(name_buf, '-');
@@ -5346,7 +5506,8 @@ void probe_sysfs(void)
 		input = fopen(path, "r");
 		if (input == NULL)
 			continue;
-		fgets(name_buf, sizeof(name_buf), input);
+		if (!fgets(name_buf, sizeof(name_buf), input))
+			err(1, "%s: failed to read file", path);
 		 /* truncate "C1-HSW\n" to "C1", or truncate "C1\n" to "C1" */
 		sp = strchr(name_buf, '-');
 		if (!sp)
diff --git a/tools/testing/nvdimm/test/nfit.c b/tools/testing/nvdimm/test/nfit.c
index b579f962451d..85ffdcfa596b 100644
--- a/tools/testing/nvdimm/test/nfit.c
+++ b/tools/testing/nvdimm/test/nfit.c
@@ -146,6 +146,7 @@ static int dimm_fail_cmd_code[ARRAY_SIZE(handle)];
 struct nfit_test_sec {
 	u8 state;
 	u8 ext_state;
+	u8 old_state;
 	u8 passphrase[32];
 	u8 master_passphrase[32];
 	u64 overwrite_end_time;
@@ -225,6 +226,8 @@ static struct workqueue_struct *nfit_wq;
 
 static struct gen_pool *nfit_pool;
 
+static const char zero_key[NVDIMM_PASSPHRASE_LEN];
+
 static struct nfit_test *to_nfit_test(struct device *dev)
 {
 	struct platform_device *pdev = to_platform_device(dev);
@@ -1059,8 +1062,7 @@ static int nd_intel_test_cmd_secure_erase(struct nfit_test *t,
 	struct device *dev = &t->pdev.dev;
 	struct nfit_test_sec *sec = &dimm_sec_info[dimm];
 
-	if (!(sec->state & ND_INTEL_SEC_STATE_ENABLED) ||
-			(sec->state & ND_INTEL_SEC_STATE_FROZEN)) {
+	if (sec->state & ND_INTEL_SEC_STATE_FROZEN) {
 		nd_cmd->status = ND_INTEL_STATUS_INVALID_STATE;
 		dev_dbg(dev, "secure erase: wrong security state\n");
 	} else if (memcmp(nd_cmd->passphrase, sec->passphrase,
@@ -1068,6 +1070,12 @@ static int nd_intel_test_cmd_secure_erase(struct nfit_test *t,
 		nd_cmd->status = ND_INTEL_STATUS_INVALID_PASS;
 		dev_dbg(dev, "secure erase: wrong passphrase\n");
 	} else {
+		if (!(sec->state & ND_INTEL_SEC_STATE_ENABLED)
+				&& (memcmp(nd_cmd->passphrase, zero_key,
+					ND_INTEL_PASSPHRASE_SIZE) != 0)) {
+			dev_dbg(dev, "invalid zero key\n");
+			return 0;
+		}
 		memset(sec->passphrase, 0, ND_INTEL_PASSPHRASE_SIZE);
 		memset(sec->master_passphrase, 0, ND_INTEL_PASSPHRASE_SIZE);
 		sec->state = 0;
@@ -1093,7 +1101,7 @@ static int nd_intel_test_cmd_overwrite(struct nfit_test *t,
 		return 0;
 	}
 
-	memset(sec->passphrase, 0, ND_INTEL_PASSPHRASE_SIZE);
+	sec->old_state = sec->state;
 	sec->state = ND_INTEL_SEC_STATE_OVERWRITE;
 	dev_dbg(dev, "overwrite progressing.\n");
 	sec->overwrite_end_time = get_jiffies_64() + 5 * HZ;
@@ -1115,7 +1123,8 @@ static int nd_intel_test_cmd_query_overwrite(struct nfit_test *t,
 
 	if (time_is_before_jiffies64(sec->overwrite_end_time)) {
 		sec->overwrite_end_time = 0;
-		sec->state = 0;
+		sec->state = sec->old_state;
+		sec->old_state = 0;
 		sec->ext_state = ND_INTEL_SEC_ESTATE_ENABLED;
 		dev_dbg(dev, "overwrite is complete\n");
 	} else
diff --git a/tools/testing/selftests/Makefile b/tools/testing/selftests/Makefile
index 971fc8428117..f2ebf8cf4686 100644
--- a/tools/testing/selftests/Makefile
+++ b/tools/testing/selftests/Makefile
@@ -15,11 +15,11 @@ TARGETS += firmware
 TARGETS += ftrace
 TARGETS += futex
 TARGETS += gpio
-TARGETS += ima
 TARGETS += intel_pstate
 TARGETS += ipc
 TARGETS += ir
 TARGETS += kcmp
+TARGETS += kexec
 TARGETS += kvm
 TARGETS += lib
 TARGETS += livepatch
@@ -75,12 +75,15 @@ ifneq ($(KBUILD_SRC),)
 override LDFLAGS =
 endif
 
-BUILD := $(O)
-ifndef BUILD
-  BUILD := $(KBUILD_OUTPUT)
-endif
-ifndef BUILD
-  BUILD := $(shell pwd)
+ifneq ($(O),)
+	BUILD := $(O)
+else
+	ifneq ($(KBUILD_OUTPUT),)
+		BUILD := $(KBUILD_OUTPUT)
+	else
+		BUILD := $(shell pwd)
+		DEFAULT_INSTALL_HDR_PATH := 1
+	endif
 endif
 
 # KSFT_TAP_LEVEL is used from KSFT framework to prevent nested TAP header
@@ -89,8 +92,50 @@ endif
 # with system() call. Export it here to cover override RUN_TESTS defines.
 export KSFT_TAP_LEVEL=`echo 1`
 
+# Prepare for headers install
+top_srcdir ?= ../../..
+include $(top_srcdir)/scripts/subarch.include
+ARCH           ?= $(SUBARCH)
+export KSFT_KHDR_INSTALL_DONE := 1
 export BUILD
-all:
+
+# build and run gpio when output directory is the src dir.
+# gpio has dependency on tools/gpio and builds tools/gpio
+# objects in the src directory in all cases making the src
+# repo dirty even when objects are relocated.
+ifneq (1,$(DEFAULT_INSTALL_HDR_PATH))
+	TMP := $(filter-out gpio, $(TARGETS))
+	TARGETS := $(TMP)
+endif
+
+# set default goal to all, so make without a target runs all, even when
+# all isn't the first target in the file.
+.DEFAULT_GOAL := all
+
+# Install headers here once for all tests. KSFT_KHDR_INSTALL_DONE
+# is used to avoid running headers_install from lib.mk.
+# Invoke headers install with --no-builtin-rules to avoid circular
+# dependency in "make kselftest" case. In this case, second level
+# make inherits builtin-rules which will use the rule generate
+# Makefile.o and runs into
+# "Circular Makefile.o <- prepare dependency dropped."
+# and headers_install fails and test compile fails.
+#
+# O= KBUILD_OUTPUT cases don't run into this error, since main Makefile
+# invokes them as sub-makes and --no-builtin-rules is not necessary,
+# but doesn't cause any failures. Keep it simple and use the same
+# flags in both cases.
+# Local build cases: "make kselftest", "make -C" - headers are installed
+# in the default INSTALL_HDR_PATH usr/include.
+khdr:
+ifeq (1,$(DEFAULT_INSTALL_HDR_PATH))
+	make --no-builtin-rules ARCH=$(ARCH) -C $(top_srcdir) headers_install
+else
+	make --no-builtin-rules INSTALL_HDR_PATH=$$BUILD/usr \
+		ARCH=$(ARCH) -C $(top_srcdir) headers_install
+endif
+
+all: khdr
 	@for TARGET in $(TARGETS); do		\
 		BUILD_TARGET=$$BUILD/$$TARGET;	\
 		mkdir $$BUILD_TARGET  -p;	\
@@ -173,4 +218,4 @@ clean:
 		make OUTPUT=$$BUILD_TARGET -C $$TARGET clean;\
 	done;
 
-.PHONY: all run_tests hotplug run_hotplug clean_hotplug run_pstore_crash install clean
+.PHONY: khdr all run_tests hotplug run_hotplug clean_hotplug run_pstore_crash install clean
diff --git a/tools/testing/selftests/bpf/bpf_helpers.h b/tools/testing/selftests/bpf/bpf_helpers.h
index c9433a496d54..c81fc350f7ad 100644
--- a/tools/testing/selftests/bpf/bpf_helpers.h
+++ b/tools/testing/selftests/bpf/bpf_helpers.h
@@ -180,6 +180,8 @@ static struct bpf_sock *(*bpf_sk_fullsock)(struct bpf_sock *sk) =
 	(void *) BPF_FUNC_sk_fullsock;
 static struct bpf_tcp_sock *(*bpf_tcp_sock)(struct bpf_sock *sk) =
 	(void *) BPF_FUNC_tcp_sock;
+static struct bpf_sock *(*bpf_get_listener_sock)(struct bpf_sock *sk) =
+	(void *) BPF_FUNC_get_listener_sock;
 static int (*bpf_skb_ecn_set_ce)(void *ctx) =
 	(void *) BPF_FUNC_skb_ecn_set_ce;
 
diff --git a/tools/testing/selftests/bpf/prog_tests/flow_dissector.c b/tools/testing/selftests/bpf/prog_tests/flow_dissector.c
index bcbd928c96ab..fc818bc1d729 100644
--- a/tools/testing/selftests/bpf/prog_tests/flow_dissector.c
+++ b/tools/testing/selftests/bpf/prog_tests/flow_dissector.c
@@ -39,6 +39,58 @@ static struct bpf_flow_keys pkt_v6_flow_keys = {
 	.n_proto = __bpf_constant_htons(ETH_P_IPV6),
 };
 
+#define VLAN_HLEN	4
+
+static struct {
+	struct ethhdr eth;
+	__u16 vlan_tci;
+	__u16 vlan_proto;
+	struct iphdr iph;
+	struct tcphdr tcp;
+} __packed pkt_vlan_v4 = {
+	.eth.h_proto = __bpf_constant_htons(ETH_P_8021Q),
+	.vlan_proto = __bpf_constant_htons(ETH_P_IP),
+	.iph.ihl = 5,
+	.iph.protocol = IPPROTO_TCP,
+	.iph.tot_len = __bpf_constant_htons(MAGIC_BYTES),
+	.tcp.urg_ptr = 123,
+	.tcp.doff = 5,
+};
+
+static struct bpf_flow_keys pkt_vlan_v4_flow_keys = {
+	.nhoff = VLAN_HLEN,
+	.thoff = VLAN_HLEN + sizeof(struct iphdr),
+	.addr_proto = ETH_P_IP,
+	.ip_proto = IPPROTO_TCP,
+	.n_proto = __bpf_constant_htons(ETH_P_IP),
+};
+
+static struct {
+	struct ethhdr eth;
+	__u16 vlan_tci;
+	__u16 vlan_proto;
+	__u16 vlan_tci2;
+	__u16 vlan_proto2;
+	struct ipv6hdr iph;
+	struct tcphdr tcp;
+} __packed pkt_vlan_v6 = {
+	.eth.h_proto = __bpf_constant_htons(ETH_P_8021AD),
+	.vlan_proto = __bpf_constant_htons(ETH_P_8021Q),
+	.vlan_proto2 = __bpf_constant_htons(ETH_P_IPV6),
+	.iph.nexthdr = IPPROTO_TCP,
+	.iph.payload_len = __bpf_constant_htons(MAGIC_BYTES),
+	.tcp.urg_ptr = 123,
+	.tcp.doff = 5,
+};
+
+static struct bpf_flow_keys pkt_vlan_v6_flow_keys = {
+	.nhoff = VLAN_HLEN * 2,
+	.thoff = VLAN_HLEN * 2 + sizeof(struct ipv6hdr),
+	.addr_proto = ETH_P_IPV6,
+	.ip_proto = IPPROTO_TCP,
+	.n_proto = __bpf_constant_htons(ETH_P_IPV6),
+};
+
 void test_flow_dissector(void)
 {
 	struct bpf_flow_keys flow_keys;
@@ -68,5 +120,21 @@ void test_flow_dissector(void)
 	      err, errno, retval, duration, size, sizeof(flow_keys));
 	CHECK_FLOW_KEYS("ipv6_flow_keys", flow_keys, pkt_v6_flow_keys);
 
+	err = bpf_prog_test_run(prog_fd, 10, &pkt_vlan_v4, sizeof(pkt_vlan_v4),
+				&flow_keys, &size, &retval, &duration);
+	CHECK(size != sizeof(flow_keys) || err || retval != 1, "vlan_ipv4",
+	      "err %d errno %d retval %d duration %d size %u/%lu\n",
+	      err, errno, retval, duration, size, sizeof(flow_keys));
+	CHECK_FLOW_KEYS("vlan_ipv4_flow_keys", flow_keys,
+			pkt_vlan_v4_flow_keys);
+
+	err = bpf_prog_test_run(prog_fd, 10, &pkt_vlan_v6, sizeof(pkt_vlan_v6),
+				&flow_keys, &size, &retval, &duration);
+	CHECK(size != sizeof(flow_keys) || err || retval != 1, "vlan_ipv6",
+	      "err %d errno %d retval %d duration %d size %u/%lu\n",
+	      err, errno, retval, duration, size, sizeof(flow_keys));
+	CHECK_FLOW_KEYS("vlan_ipv6_flow_keys", flow_keys,
+			pkt_vlan_v6_flow_keys);
+
 	bpf_object__close(obj);
 }
diff --git a/tools/testing/selftests/bpf/prog_tests/map_lock.c b/tools/testing/selftests/bpf/prog_tests/map_lock.c
index 90f8a206340a..ee99368c595c 100644
--- a/tools/testing/selftests/bpf/prog_tests/map_lock.c
+++ b/tools/testing/selftests/bpf/prog_tests/map_lock.c
@@ -37,7 +37,7 @@ void test_map_lock(void)
 	const char *file = "./test_map_lock.o";
 	int prog_fd, map_fd[2], vars[17] = {};
 	pthread_t thread_id[6];
-	struct bpf_object *obj;
+	struct bpf_object *obj = NULL;
 	int err = 0, key = 0, i;
 	void *ret;
 
diff --git a/tools/testing/selftests/bpf/prog_tests/spinlock.c b/tools/testing/selftests/bpf/prog_tests/spinlock.c
index 9a573a9675d7..114ebe6a438e 100644
--- a/tools/testing/selftests/bpf/prog_tests/spinlock.c
+++ b/tools/testing/selftests/bpf/prog_tests/spinlock.c
@@ -5,7 +5,7 @@ void test_spinlock(void)
 {
 	const char *file = "./test_spin_lock.o";
 	pthread_t thread_id[4];
-	struct bpf_object *obj;
+	struct bpf_object *obj = NULL;
 	int prog_fd;
 	int err = 0, i;
 	void *ret;
diff --git a/tools/testing/selftests/bpf/progs/bpf_flow.c b/tools/testing/selftests/bpf/progs/bpf_flow.c
index 284660f5aa95..75b17cada539 100644
--- a/tools/testing/selftests/bpf/progs/bpf_flow.c
+++ b/tools/testing/selftests/bpf/progs/bpf_flow.c
@@ -92,7 +92,6 @@ static __always_inline int parse_eth_proto(struct __sk_buff *skb, __be16 proto)
 {
 	struct bpf_flow_keys *keys = skb->flow_keys;
 
-	keys->n_proto = proto;
 	switch (proto) {
 	case bpf_htons(ETH_P_IP):
 		bpf_tail_call(skb, &jmp_table, IP);
@@ -119,10 +118,9 @@ static __always_inline int parse_eth_proto(struct __sk_buff *skb, __be16 proto)
 SEC("flow_dissector")
 int _dissect(struct __sk_buff *skb)
 {
-	if (!skb->vlan_present)
-		return parse_eth_proto(skb, skb->protocol);
-	else
-		return parse_eth_proto(skb, skb->vlan_proto);
+	struct bpf_flow_keys *keys = skb->flow_keys;
+
+	return parse_eth_proto(skb, keys->n_proto);
 }
 
 /* Parses on IPPROTO_* */
@@ -336,15 +334,9 @@ PROG(VLAN)(struct __sk_buff *skb)
 {
 	struct bpf_flow_keys *keys = skb->flow_keys;
 	struct vlan_hdr *vlan, _vlan;
-	__be16 proto;
-
-	/* Peek back to see if single or double-tagging */
-	if (bpf_skb_load_bytes(skb, keys->thoff - sizeof(proto), &proto,
-			       sizeof(proto)))
-		return BPF_DROP;
 
 	/* Account for double-tagging */
-	if (proto == bpf_htons(ETH_P_8021AD)) {
+	if (keys->n_proto == bpf_htons(ETH_P_8021AD)) {
 		vlan = bpf_flow_dissect_get_header(skb, sizeof(*vlan), &_vlan);
 		if (!vlan)
 			return BPF_DROP;
@@ -352,6 +344,7 @@ PROG(VLAN)(struct __sk_buff *skb)
 		if (vlan->h_vlan_encapsulated_proto != bpf_htons(ETH_P_8021Q))
 			return BPF_DROP;
 
+		keys->nhoff += sizeof(*vlan);
 		keys->thoff += sizeof(*vlan);
 	}
 
@@ -359,12 +352,14 @@ PROG(VLAN)(struct __sk_buff *skb)
 	if (!vlan)
 		return BPF_DROP;
 
+	keys->nhoff += sizeof(*vlan);
 	keys->thoff += sizeof(*vlan);
 	/* Only allow 8021AD + 8021Q double tagging and no triple tagging.*/
 	if (vlan->h_vlan_encapsulated_proto == bpf_htons(ETH_P_8021AD) ||
 	    vlan->h_vlan_encapsulated_proto == bpf_htons(ETH_P_8021Q))
 		return BPF_DROP;
 
+	keys->n_proto = vlan->h_vlan_encapsulated_proto;
 	return parse_eth_proto(skb, vlan->h_vlan_encapsulated_proto);
 }
 
diff --git a/tools/testing/selftests/bpf/progs/test_sock_fields_kern.c b/tools/testing/selftests/bpf/progs/test_sock_fields_kern.c
index de1a43e8f610..37328f148538 100644
--- a/tools/testing/selftests/bpf/progs/test_sock_fields_kern.c
+++ b/tools/testing/selftests/bpf/progs/test_sock_fields_kern.c
@@ -8,38 +8,51 @@
 #include "bpf_helpers.h"
 #include "bpf_endian.h"
 
-enum bpf_array_idx {
-	SRV_IDX,
-	CLI_IDX,
-	__NR_BPF_ARRAY_IDX,
+enum bpf_addr_array_idx {
+	ADDR_SRV_IDX,
+	ADDR_CLI_IDX,
+	__NR_BPF_ADDR_ARRAY_IDX,
+};
+
+enum bpf_result_array_idx {
+	EGRESS_SRV_IDX,
+	EGRESS_CLI_IDX,
+	INGRESS_LISTEN_IDX,
+	__NR_BPF_RESULT_ARRAY_IDX,
+};
+
+enum bpf_linum_array_idx {
+	EGRESS_LINUM_IDX,
+	INGRESS_LINUM_IDX,
+	__NR_BPF_LINUM_ARRAY_IDX,
 };
 
 struct bpf_map_def SEC("maps") addr_map = {
 	.type = BPF_MAP_TYPE_ARRAY,
 	.key_size = sizeof(__u32),
 	.value_size = sizeof(struct sockaddr_in6),
-	.max_entries = __NR_BPF_ARRAY_IDX,
+	.max_entries = __NR_BPF_ADDR_ARRAY_IDX,
 };
 
 struct bpf_map_def SEC("maps") sock_result_map = {
 	.type = BPF_MAP_TYPE_ARRAY,
 	.key_size = sizeof(__u32),
 	.value_size = sizeof(struct bpf_sock),
-	.max_entries = __NR_BPF_ARRAY_IDX,
+	.max_entries = __NR_BPF_RESULT_ARRAY_IDX,
 };
 
 struct bpf_map_def SEC("maps") tcp_sock_result_map = {
 	.type = BPF_MAP_TYPE_ARRAY,
 	.key_size = sizeof(__u32),
 	.value_size = sizeof(struct bpf_tcp_sock),
-	.max_entries = __NR_BPF_ARRAY_IDX,
+	.max_entries = __NR_BPF_RESULT_ARRAY_IDX,
 };
 
 struct bpf_map_def SEC("maps") linum_map = {
 	.type = BPF_MAP_TYPE_ARRAY,
 	.key_size = sizeof(__u32),
 	.value_size = sizeof(__u32),
-	.max_entries = 1,
+	.max_entries = __NR_BPF_LINUM_ARRAY_IDX,
 };
 
 static bool is_loopback6(__u32 *a6)
@@ -100,18 +113,20 @@ static void tpcpy(struct bpf_tcp_sock *dst,
 
 #define RETURN {						\
 	linum = __LINE__;					\
-	bpf_map_update_elem(&linum_map, &idx0, &linum, 0);	\
+	bpf_map_update_elem(&linum_map, &linum_idx, &linum, 0);	\
 	return 1;						\
 }
 
 SEC("cgroup_skb/egress")
-int read_sock_fields(struct __sk_buff *skb)
+int egress_read_sock_fields(struct __sk_buff *skb)
 {
-	__u32 srv_idx = SRV_IDX, cli_idx = CLI_IDX, idx;
+	__u32 srv_idx = ADDR_SRV_IDX, cli_idx = ADDR_CLI_IDX, result_idx;
 	struct sockaddr_in6 *srv_sa6, *cli_sa6;
 	struct bpf_tcp_sock *tp, *tp_ret;
 	struct bpf_sock *sk, *sk_ret;
-	__u32 linum, idx0 = 0;
+	__u32 linum, linum_idx;
+
+	linum_idx = EGRESS_LINUM_IDX;
 
 	sk = skb->sk;
 	if (!sk || sk->state == 10)
@@ -132,14 +147,55 @@ int read_sock_fields(struct __sk_buff *skb)
 		RETURN;
 
 	if (sk->src_port == bpf_ntohs(srv_sa6->sin6_port))
-		idx = srv_idx;
+		result_idx = EGRESS_SRV_IDX;
 	else if (sk->src_port == bpf_ntohs(cli_sa6->sin6_port))
-		idx = cli_idx;
+		result_idx = EGRESS_CLI_IDX;
 	else
 		RETURN;
 
-	sk_ret = bpf_map_lookup_elem(&sock_result_map, &idx);
-	tp_ret = bpf_map_lookup_elem(&tcp_sock_result_map, &idx);
+	sk_ret = bpf_map_lookup_elem(&sock_result_map, &result_idx);
+	tp_ret = bpf_map_lookup_elem(&tcp_sock_result_map, &result_idx);
+	if (!sk_ret || !tp_ret)
+		RETURN;
+
+	skcpy(sk_ret, sk);
+	tpcpy(tp_ret, tp);
+
+	RETURN;
+}
+
+SEC("cgroup_skb/ingress")
+int ingress_read_sock_fields(struct __sk_buff *skb)
+{
+	__u32 srv_idx = ADDR_SRV_IDX, result_idx = INGRESS_LISTEN_IDX;
+	struct bpf_tcp_sock *tp, *tp_ret;
+	struct bpf_sock *sk, *sk_ret;
+	struct sockaddr_in6 *srv_sa6;
+	__u32 linum, linum_idx;
+
+	linum_idx = INGRESS_LINUM_IDX;
+
+	sk = skb->sk;
+	if (!sk || sk->family != AF_INET6 || !is_loopback6(sk->src_ip6))
+		RETURN;
+
+	srv_sa6 = bpf_map_lookup_elem(&addr_map, &srv_idx);
+	if (!srv_sa6 || sk->src_port != bpf_ntohs(srv_sa6->sin6_port))
+		RETURN;
+
+	if (sk->state != 10 && sk->state != 12)
+		RETURN;
+
+	sk = bpf_get_listener_sock(sk);
+	if (!sk)
+		RETURN;
+
+	tp = bpf_tcp_sock(sk);
+	if (!tp)
+		RETURN;
+
+	sk_ret = bpf_map_lookup_elem(&sock_result_map, &result_idx);
+	tp_ret = bpf_map_lookup_elem(&tcp_sock_result_map, &result_idx);
 	if (!sk_ret || !tp_ret)
 		RETURN;
 
diff --git a/tools/testing/selftests/bpf/test_btf.c b/tools/testing/selftests/bpf/test_btf.c
index 38797aa627a7..ec5794e4205b 100644
--- a/tools/testing/selftests/bpf/test_btf.c
+++ b/tools/testing/selftests/bpf/test_btf.c
@@ -5777,6 +5777,53 @@ const struct btf_dedup_test dedup_tests[] = {
 	},
 },
 {
+	.descr = "dedup: void equiv check",
+	/*
+	 * // CU 1:
+	 * struct s {
+	 *	struct {} *x;
+	 * };
+	 * // CU 2:
+	 * struct s {
+	 *	int *x;
+	 * };
+	 */
+	.input = {
+		.raw_types = {
+			/* CU 1 */
+			BTF_STRUCT_ENC(0, 0, 1),				/* [1] struct {}  */
+			BTF_PTR_ENC(1),						/* [2] ptr -> [1] */
+			BTF_STRUCT_ENC(NAME_NTH(1), 1, 8),			/* [3] struct s   */
+				BTF_MEMBER_ENC(NAME_NTH(2), 2, 0),
+			/* CU 2 */
+			BTF_PTR_ENC(0),						/* [4] ptr -> void */
+			BTF_STRUCT_ENC(NAME_NTH(1), 1, 8),			/* [5] struct s   */
+				BTF_MEMBER_ENC(NAME_NTH(2), 4, 0),
+			BTF_END_RAW,
+		},
+		BTF_STR_SEC("\0s\0x"),
+	},
+	.expect = {
+		.raw_types = {
+			/* CU 1 */
+			BTF_STRUCT_ENC(0, 0, 1),				/* [1] struct {}  */
+			BTF_PTR_ENC(1),						/* [2] ptr -> [1] */
+			BTF_STRUCT_ENC(NAME_NTH(1), 1, 8),			/* [3] struct s   */
+				BTF_MEMBER_ENC(NAME_NTH(2), 2, 0),
+			/* CU 2 */
+			BTF_PTR_ENC(0),						/* [4] ptr -> void */
+			BTF_STRUCT_ENC(NAME_NTH(1), 1, 8),			/* [5] struct s   */
+				BTF_MEMBER_ENC(NAME_NTH(2), 4, 0),
+			BTF_END_RAW,
+		},
+		BTF_STR_SEC("\0s\0x"),
+	},
+	.opts = {
+		.dont_resolve_fwds = false,
+		.dedup_table_size = 1, /* force hash collisions */
+	},
+},
+{
 	.descr = "dedup: all possible kinds (no duplicates)",
 	.input = {
 		.raw_types = {
@@ -5874,6 +5921,50 @@ const struct btf_dedup_test dedup_tests[] = {
 		.dont_resolve_fwds = false,
 	},
 },
+{
+	.descr = "dedup: enum fwd resolution",
+	.input = {
+		.raw_types = {
+			/* [1] fwd enum 'e1' before full enum */
+			BTF_TYPE_ENC(NAME_NTH(1), BTF_INFO_ENC(BTF_KIND_ENUM, 0, 0), 4),
+			/* [2] full enum 'e1' after fwd */
+			BTF_TYPE_ENC(NAME_NTH(1), BTF_INFO_ENC(BTF_KIND_ENUM, 0, 1), 4),
+				BTF_ENUM_ENC(NAME_NTH(2), 123),
+			/* [3] full enum 'e2' before fwd */
+			BTF_TYPE_ENC(NAME_NTH(3), BTF_INFO_ENC(BTF_KIND_ENUM, 0, 1), 4),
+				BTF_ENUM_ENC(NAME_NTH(4), 456),
+			/* [4] fwd enum 'e2' after full enum */
+			BTF_TYPE_ENC(NAME_NTH(3), BTF_INFO_ENC(BTF_KIND_ENUM, 0, 0), 4),
+			/* [5] incompatible fwd enum with different size */
+			BTF_TYPE_ENC(NAME_NTH(1), BTF_INFO_ENC(BTF_KIND_ENUM, 0, 0), 1),
+			/* [6] incompatible full enum with different value */
+			BTF_TYPE_ENC(NAME_NTH(1), BTF_INFO_ENC(BTF_KIND_ENUM, 0, 1), 4),
+				BTF_ENUM_ENC(NAME_NTH(2), 321),
+			BTF_END_RAW,
+		},
+		BTF_STR_SEC("\0e1\0e1_val\0e2\0e2_val"),
+	},
+	.expect = {
+		.raw_types = {
+			/* [1] full enum 'e1' */
+			BTF_TYPE_ENC(NAME_NTH(1), BTF_INFO_ENC(BTF_KIND_ENUM, 0, 1), 4),
+				BTF_ENUM_ENC(NAME_NTH(2), 123),
+			/* [2] full enum 'e2' */
+			BTF_TYPE_ENC(NAME_NTH(3), BTF_INFO_ENC(BTF_KIND_ENUM, 0, 1), 4),
+				BTF_ENUM_ENC(NAME_NTH(4), 456),
+			/* [3] incompatible fwd enum with different size */
+			BTF_TYPE_ENC(NAME_NTH(1), BTF_INFO_ENC(BTF_KIND_ENUM, 0, 0), 1),
+			/* [4] incompatible full enum with different value */
+			BTF_TYPE_ENC(NAME_NTH(1), BTF_INFO_ENC(BTF_KIND_ENUM, 0, 1), 4),
+				BTF_ENUM_ENC(NAME_NTH(2), 321),
+			BTF_END_RAW,
+		},
+		BTF_STR_SEC("\0e1\0e1_val\0e2\0e2_val"),
+	},
+	.opts = {
+		.dont_resolve_fwds = false,
+	},
+},
 
 };
 
diff --git a/tools/testing/selftests/bpf/test_sock_fields.c b/tools/testing/selftests/bpf/test_sock_fields.c
index bc8943938bf5..dcae7f664dce 100644
--- a/tools/testing/selftests/bpf/test_sock_fields.c
+++ b/tools/testing/selftests/bpf/test_sock_fields.c
@@ -16,10 +16,23 @@
 #include "cgroup_helpers.h"
 #include "bpf_rlimit.h"
 
-enum bpf_array_idx {
-	SRV_IDX,
-	CLI_IDX,
-	__NR_BPF_ARRAY_IDX,
+enum bpf_addr_array_idx {
+	ADDR_SRV_IDX,
+	ADDR_CLI_IDX,
+	__NR_BPF_ADDR_ARRAY_IDX,
+};
+
+enum bpf_result_array_idx {
+	EGRESS_SRV_IDX,
+	EGRESS_CLI_IDX,
+	INGRESS_LISTEN_IDX,
+	__NR_BPF_RESULT_ARRAY_IDX,
+};
+
+enum bpf_linum_array_idx {
+	EGRESS_LINUM_IDX,
+	INGRESS_LINUM_IDX,
+	__NR_BPF_LINUM_ARRAY_IDX,
 };
 
 #define CHECK(condition, tag, format...) ({				\
@@ -41,8 +54,16 @@ static int linum_map_fd;
 static int addr_map_fd;
 static int tp_map_fd;
 static int sk_map_fd;
-static __u32 srv_idx = SRV_IDX;
-static __u32 cli_idx = CLI_IDX;
+
+static __u32 addr_srv_idx = ADDR_SRV_IDX;
+static __u32 addr_cli_idx = ADDR_CLI_IDX;
+
+static __u32 egress_srv_idx = EGRESS_SRV_IDX;
+static __u32 egress_cli_idx = EGRESS_CLI_IDX;
+static __u32 ingress_listen_idx = INGRESS_LISTEN_IDX;
+
+static __u32 egress_linum_idx = EGRESS_LINUM_IDX;
+static __u32 ingress_linum_idx = INGRESS_LINUM_IDX;
 
 static void init_loopback6(struct sockaddr_in6 *sa6)
 {
@@ -93,29 +114,46 @@ static void print_tp(const struct bpf_tcp_sock *tp)
 
 static void check_result(void)
 {
-	struct bpf_tcp_sock srv_tp, cli_tp;
-	struct bpf_sock srv_sk, cli_sk;
-	__u32 linum, idx0 = 0;
+	struct bpf_tcp_sock srv_tp, cli_tp, listen_tp;
+	struct bpf_sock srv_sk, cli_sk, listen_sk;
+	__u32 ingress_linum, egress_linum;
 	int err;
 
-	err = bpf_map_lookup_elem(linum_map_fd, &idx0, &linum);
+	err = bpf_map_lookup_elem(linum_map_fd, &egress_linum_idx,
+				  &egress_linum);
 	CHECK(err == -1, "bpf_map_lookup_elem(linum_map_fd)",
 	      "err:%d errno:%d", err, errno);
 
-	err = bpf_map_lookup_elem(sk_map_fd, &srv_idx, &srv_sk);
-	CHECK(err == -1, "bpf_map_lookup_elem(sk_map_fd, &srv_idx)",
+	err = bpf_map_lookup_elem(linum_map_fd, &ingress_linum_idx,
+				  &ingress_linum);
+	CHECK(err == -1, "bpf_map_lookup_elem(linum_map_fd)",
+	      "err:%d errno:%d", err, errno);
+
+	err = bpf_map_lookup_elem(sk_map_fd, &egress_srv_idx, &srv_sk);
+	CHECK(err == -1, "bpf_map_lookup_elem(sk_map_fd, &egress_srv_idx)",
+	      "err:%d errno:%d", err, errno);
+	err = bpf_map_lookup_elem(tp_map_fd, &egress_srv_idx, &srv_tp);
+	CHECK(err == -1, "bpf_map_lookup_elem(tp_map_fd, &egress_srv_idx)",
+	      "err:%d errno:%d", err, errno);
+
+	err = bpf_map_lookup_elem(sk_map_fd, &egress_cli_idx, &cli_sk);
+	CHECK(err == -1, "bpf_map_lookup_elem(sk_map_fd, &egress_cli_idx)",
 	      "err:%d errno:%d", err, errno);
-	err = bpf_map_lookup_elem(tp_map_fd, &srv_idx, &srv_tp);
-	CHECK(err == -1, "bpf_map_lookup_elem(tp_map_fd, &srv_idx)",
+	err = bpf_map_lookup_elem(tp_map_fd, &egress_cli_idx, &cli_tp);
+	CHECK(err == -1, "bpf_map_lookup_elem(tp_map_fd, &egress_cli_idx)",
 	      "err:%d errno:%d", err, errno);
 
-	err = bpf_map_lookup_elem(sk_map_fd, &cli_idx, &cli_sk);
-	CHECK(err == -1, "bpf_map_lookup_elem(sk_map_fd, &cli_idx)",
+	err = bpf_map_lookup_elem(sk_map_fd, &ingress_listen_idx, &listen_sk);
+	CHECK(err == -1, "bpf_map_lookup_elem(sk_map_fd, &ingress_listen_idx)",
 	      "err:%d errno:%d", err, errno);
-	err = bpf_map_lookup_elem(tp_map_fd, &cli_idx, &cli_tp);
-	CHECK(err == -1, "bpf_map_lookup_elem(tp_map_fd, &cli_idx)",
+	err = bpf_map_lookup_elem(tp_map_fd, &ingress_listen_idx, &listen_tp);
+	CHECK(err == -1, "bpf_map_lookup_elem(tp_map_fd, &ingress_listen_idx)",
 	      "err:%d errno:%d", err, errno);
 
+	printf("listen_sk: ");
+	print_sk(&listen_sk);
+	printf("\n");
+
 	printf("srv_sk: ");
 	print_sk(&srv_sk);
 	printf("\n");
@@ -124,6 +162,10 @@ static void check_result(void)
 	print_sk(&cli_sk);
 	printf("\n");
 
+	printf("listen_tp: ");
+	print_tp(&listen_tp);
+	printf("\n");
+
 	printf("srv_tp: ");
 	print_tp(&srv_tp);
 	printf("\n");
@@ -132,6 +174,19 @@ static void check_result(void)
 	print_tp(&cli_tp);
 	printf("\n");
 
+	CHECK(listen_sk.state != 10 ||
+	      listen_sk.family != AF_INET6 ||
+	      listen_sk.protocol != IPPROTO_TCP ||
+	      memcmp(listen_sk.src_ip6, &in6addr_loopback,
+		     sizeof(listen_sk.src_ip6)) ||
+	      listen_sk.dst_ip6[0] || listen_sk.dst_ip6[1] ||
+	      listen_sk.dst_ip6[2] || listen_sk.dst_ip6[3] ||
+	      listen_sk.src_port != ntohs(srv_sa6.sin6_port) ||
+	      listen_sk.dst_port,
+	      "Unexpected listen_sk",
+	      "Check listen_sk output. ingress_linum:%u",
+	      ingress_linum);
+
 	CHECK(srv_sk.state == 10 ||
 	      !srv_sk.state ||
 	      srv_sk.family != AF_INET6 ||
@@ -142,7 +197,8 @@ static void check_result(void)
 		     sizeof(srv_sk.dst_ip6)) ||
 	      srv_sk.src_port != ntohs(srv_sa6.sin6_port) ||
 	      srv_sk.dst_port != cli_sa6.sin6_port,
-	      "Unexpected srv_sk", "Check srv_sk output. linum:%u", linum);
+	      "Unexpected srv_sk", "Check srv_sk output. egress_linum:%u",
+	      egress_linum);
 
 	CHECK(cli_sk.state == 10 ||
 	      !cli_sk.state ||
@@ -154,21 +210,31 @@ static void check_result(void)
 		     sizeof(cli_sk.dst_ip6)) ||
 	      cli_sk.src_port != ntohs(cli_sa6.sin6_port) ||
 	      cli_sk.dst_port != srv_sa6.sin6_port,
-	      "Unexpected cli_sk", "Check cli_sk output. linum:%u", linum);
+	      "Unexpected cli_sk", "Check cli_sk output. egress_linum:%u",
+	      egress_linum);
+
+	CHECK(listen_tp.data_segs_out ||
+	      listen_tp.data_segs_in ||
+	      listen_tp.total_retrans ||
+	      listen_tp.bytes_acked,
+	      "Unexpected listen_tp", "Check listen_tp output. ingress_linum:%u",
+	      ingress_linum);
 
 	CHECK(srv_tp.data_segs_out != 1 ||
 	      srv_tp.data_segs_in ||
 	      srv_tp.snd_cwnd != 10 ||
 	      srv_tp.total_retrans ||
 	      srv_tp.bytes_acked != DATA_LEN,
-	      "Unexpected srv_tp", "Check srv_tp output. linum:%u", linum);
+	      "Unexpected srv_tp", "Check srv_tp output. egress_linum:%u",
+	      egress_linum);
 
 	CHECK(cli_tp.data_segs_out ||
 	      cli_tp.data_segs_in != 1 ||
 	      cli_tp.snd_cwnd != 10 ||
 	      cli_tp.total_retrans ||
 	      cli_tp.bytes_received != DATA_LEN,
-	      "Unexpected cli_tp", "Check cli_tp output. linum:%u", linum);
+	      "Unexpected cli_tp", "Check cli_tp output. egress_linum:%u",
+	      egress_linum);
 }
 
 static void test(void)
@@ -211,10 +277,10 @@ static void test(void)
 	      err, errno);
 
 	/* Update addr_map with srv_sa6 and cli_sa6 */
-	err = bpf_map_update_elem(addr_map_fd, &srv_idx, &srv_sa6, 0);
+	err = bpf_map_update_elem(addr_map_fd, &addr_srv_idx, &srv_sa6, 0);
 	CHECK(err, "map_update", "err:%d errno:%d", err, errno);
 
-	err = bpf_map_update_elem(addr_map_fd, &cli_idx, &cli_sa6, 0);
+	err = bpf_map_update_elem(addr_map_fd, &addr_cli_idx, &cli_sa6, 0);
 	CHECK(err, "map_update", "err:%d errno:%d", err, errno);
 
 	/* Connect from cli_sa6 to srv_sa6 */
@@ -273,9 +339,9 @@ int main(int argc, char **argv)
 	struct bpf_prog_load_attr attr = {
 		.file = "test_sock_fields_kern.o",
 		.prog_type = BPF_PROG_TYPE_CGROUP_SKB,
-		.expected_attach_type = BPF_CGROUP_INET_EGRESS,
 	};
-	int cgroup_fd, prog_fd, err;
+	int cgroup_fd, egress_fd, ingress_fd, err;
+	struct bpf_program *ingress_prog;
 	struct bpf_object *obj;
 	struct bpf_map *map;
 
@@ -293,12 +359,24 @@ int main(int argc, char **argv)
 	err = join_cgroup(TEST_CGROUP);
 	CHECK(err, "join_cgroup", "err:%d errno:%d", err, errno);
 
-	err = bpf_prog_load_xattr(&attr, &obj, &prog_fd);
+	err = bpf_prog_load_xattr(&attr, &obj, &egress_fd);
 	CHECK(err, "bpf_prog_load_xattr()", "err:%d", err);
 
-	err = bpf_prog_attach(prog_fd, cgroup_fd, BPF_CGROUP_INET_EGRESS, 0);
+	ingress_prog = bpf_object__find_program_by_title(obj,
+							 "cgroup_skb/ingress");
+	CHECK(!ingress_prog,
+	      "bpf_object__find_program_by_title(cgroup_skb/ingress)",
+	      "not found");
+	ingress_fd = bpf_program__fd(ingress_prog);
+
+	err = bpf_prog_attach(egress_fd, cgroup_fd, BPF_CGROUP_INET_EGRESS, 0);
 	CHECK(err == -1, "bpf_prog_attach(CPF_CGROUP_INET_EGRESS)",
 	      "err:%d errno%d", err, errno);
+
+	err = bpf_prog_attach(ingress_fd, cgroup_fd,
+			      BPF_CGROUP_INET_INGRESS, 0);
+	CHECK(err == -1, "bpf_prog_attach(CPF_CGROUP_INET_INGRESS)",
+	      "err:%d errno%d", err, errno);
 	close(cgroup_fd);
 
 	map = bpf_object__find_map_by_name(obj, "addr_map");
diff --git a/tools/testing/selftests/bpf/verifier/calls.c b/tools/testing/selftests/bpf/verifier/calls.c
index 4004891afa9c..9093a8f64dc6 100644
--- a/tools/testing/selftests/bpf/verifier/calls.c
+++ b/tools/testing/selftests/bpf/verifier/calls.c
@@ -375,6 +375,31 @@
 	.flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
 },
 {
+	"calls: ptr null check in subprog",
+	.insns = {
+	BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0),
+	BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
+	BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8),
+	BPF_LD_MAP_FD(BPF_REG_1, 0),
+	BPF_EMIT_CALL(BPF_FUNC_map_lookup_elem),
+	BPF_MOV64_REG(BPF_REG_1, BPF_REG_0),
+	BPF_MOV64_REG(BPF_REG_6, BPF_REG_0),
+	BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 1, 0, 3),
+	BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 1),
+	BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_6, 0),
+	BPF_EXIT_INSN(),
+	BPF_MOV64_IMM(BPF_REG_0, 0),
+	BPF_JMP_IMM(BPF_JEQ, BPF_REG_1, 0, 1),
+	BPF_MOV64_IMM(BPF_REG_0, 1),
+	BPF_EXIT_INSN(),
+	},
+	.errstr_unpriv = "function calls to other bpf functions are allowed for root only",
+	.fixup_map_hash_48b = { 3 },
+	.result_unpriv = REJECT,
+	.result = ACCEPT,
+	.retval = 0,
+},
+{
 	"calls: two calls with args",
 	.insns = {
 	BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 1, 0, 1),
@@ -908,6 +933,44 @@
 	.result = REJECT,
 },
 {
+	"calls: stack depth check in dead code",
+	.insns = {
+	/* main */
+	BPF_MOV64_IMM(BPF_REG_1, 0),
+	BPF_RAW_INSN(BPF_JMP|BPF_CALL, 0, 1, 0, 1), /* call A */
+	BPF_EXIT_INSN(),
+	/* A */
+	BPF_JMP_IMM(BPF_JEQ, BPF_REG_1, 0, 1),
+	BPF_RAW_INSN(BPF_JMP|BPF_CALL, 0, 1, 0, 2), /* call B */
+	BPF_MOV64_IMM(BPF_REG_0, 0),
+	BPF_EXIT_INSN(),
+	/* B */
+	BPF_RAW_INSN(BPF_JMP|BPF_CALL, 0, 1, 0, 1), /* call C */
+	BPF_EXIT_INSN(),
+	/* C */
+	BPF_RAW_INSN(BPF_JMP|BPF_CALL, 0, 1, 0, 1), /* call D */
+	BPF_EXIT_INSN(),
+	/* D */
+	BPF_RAW_INSN(BPF_JMP|BPF_CALL, 0, 1, 0, 1), /* call E */
+	BPF_EXIT_INSN(),
+	/* E */
+	BPF_RAW_INSN(BPF_JMP|BPF_CALL, 0, 1, 0, 1), /* call F */
+	BPF_EXIT_INSN(),
+	/* F */
+	BPF_RAW_INSN(BPF_JMP|BPF_CALL, 0, 1, 0, 1), /* call G */
+	BPF_EXIT_INSN(),
+	/* G */
+	BPF_RAW_INSN(BPF_JMP|BPF_CALL, 0, 1, 0, 1), /* call H */
+	BPF_EXIT_INSN(),
+	/* H */
+	BPF_MOV64_IMM(BPF_REG_0, 0),
+	BPF_EXIT_INSN(),
+	},
+	.prog_type = BPF_PROG_TYPE_XDP,
+	.errstr = "call stack",
+	.result = REJECT,
+},
+{
 	"calls: spill into caller stack frame",
 	.insns = {
 	BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0),
@@ -1940,3 +2003,28 @@
 	.errstr = "!read_ok",
 	.result = REJECT,
 },
+{
+	"calls: cross frame pruning - liveness propagation",
+	.insns = {
+	BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_get_prandom_u32),
+	BPF_MOV64_IMM(BPF_REG_8, 0),
+	BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 0, 1),
+	BPF_MOV64_IMM(BPF_REG_8, 1),
+	BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_get_prandom_u32),
+	BPF_MOV64_IMM(BPF_REG_9, 0),
+	BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 0, 1),
+	BPF_MOV64_IMM(BPF_REG_9, 1),
+	BPF_MOV64_REG(BPF_REG_1, BPF_REG_0),
+	BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 1, 0, 4),
+	BPF_JMP_IMM(BPF_JEQ, BPF_REG_8, 1, 1),
+	BPF_LDX_MEM(BPF_B, BPF_REG_1, BPF_REG_2, 0),
+	BPF_MOV64_IMM(BPF_REG_0, 0),
+	BPF_EXIT_INSN(),
+	BPF_JMP_IMM(BPF_JEQ, BPF_REG_1, 0, 0),
+	BPF_EXIT_INSN(),
+	},
+	.prog_type = BPF_PROG_TYPE_SOCKET_FILTER,
+	.errstr_unpriv = "function calls to other bpf functions are allowed for root only",
+	.errstr = "!read_ok",
+	.result = REJECT,
+},
diff --git a/tools/testing/selftests/bpf/verifier/direct_packet_access.c b/tools/testing/selftests/bpf/verifier/direct_packet_access.c
index e3fc22e672c2..d5c596fdc4b9 100644
--- a/tools/testing/selftests/bpf/verifier/direct_packet_access.c
+++ b/tools/testing/selftests/bpf/verifier/direct_packet_access.c
@@ -631,3 +631,25 @@
 	.errstr = "invalid access to packet",
 	.prog_type = BPF_PROG_TYPE_SCHED_CLS,
 },
+{
+	"direct packet access: test29 (reg > pkt_end in subprog)",
+	.insns = {
+	BPF_LDX_MEM(BPF_W, BPF_REG_6, BPF_REG_1,
+		    offsetof(struct __sk_buff, data)),
+	BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1,
+		    offsetof(struct __sk_buff, data_end)),
+	BPF_MOV64_REG(BPF_REG_3, BPF_REG_6),
+	BPF_ALU64_IMM(BPF_ADD, BPF_REG_3, 8),
+	BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 1, 0, 4),
+	BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 1),
+	BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_6, 0),
+	BPF_MOV64_IMM(BPF_REG_0, 0),
+	BPF_EXIT_INSN(),
+	BPF_MOV64_IMM(BPF_REG_0, 0),
+	BPF_JMP_REG(BPF_JGT, BPF_REG_3, BPF_REG_2, 1),
+	BPF_MOV64_IMM(BPF_REG_0, 1),
+	BPF_EXIT_INSN(),
+	},
+	.result = ACCEPT,
+	.prog_type = BPF_PROG_TYPE_SCHED_CLS,
+},
diff --git a/tools/testing/selftests/bpf/verifier/ref_tracking.c b/tools/testing/selftests/bpf/verifier/ref_tracking.c
index 3ed3593bd8b6..923f2110072d 100644
--- a/tools/testing/selftests/bpf/verifier/ref_tracking.c
+++ b/tools/testing/selftests/bpf/verifier/ref_tracking.c
@@ -605,3 +605,171 @@
 	.prog_type = BPF_PROG_TYPE_SCHED_CLS,
 	.result = ACCEPT,
 },
+{
+	"reference tracking: use ptr from bpf_tcp_sock() after release",
+	.insns = {
+	BPF_SK_LOOKUP,
+	BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 0, 1),
+	BPF_EXIT_INSN(),
+	BPF_MOV64_REG(BPF_REG_6, BPF_REG_0),
+	BPF_MOV64_REG(BPF_REG_1, BPF_REG_0),
+	BPF_EMIT_CALL(BPF_FUNC_tcp_sock),
+	BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 0, 3),
+	BPF_MOV64_REG(BPF_REG_1, BPF_REG_6),
+	BPF_EMIT_CALL(BPF_FUNC_sk_release),
+	BPF_EXIT_INSN(),
+	BPF_MOV64_REG(BPF_REG_7, BPF_REG_0),
+	BPF_MOV64_REG(BPF_REG_1, BPF_REG_6),
+	BPF_EMIT_CALL(BPF_FUNC_sk_release),
+	BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_7, offsetof(struct bpf_tcp_sock, snd_cwnd)),
+	BPF_EXIT_INSN(),
+	},
+	.prog_type = BPF_PROG_TYPE_SCHED_CLS,
+	.result = REJECT,
+	.errstr = "invalid mem access",
+},
+{
+	"reference tracking: use ptr from bpf_sk_fullsock() after release",
+	.insns = {
+	BPF_SK_LOOKUP,
+	BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 0, 1),
+	BPF_EXIT_INSN(),
+	BPF_MOV64_REG(BPF_REG_6, BPF_REG_0),
+	BPF_MOV64_REG(BPF_REG_1, BPF_REG_0),
+	BPF_EMIT_CALL(BPF_FUNC_sk_fullsock),
+	BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 0, 3),
+	BPF_MOV64_REG(BPF_REG_1, BPF_REG_6),
+	BPF_EMIT_CALL(BPF_FUNC_sk_release),
+	BPF_EXIT_INSN(),
+	BPF_MOV64_REG(BPF_REG_7, BPF_REG_0),
+	BPF_MOV64_REG(BPF_REG_1, BPF_REG_6),
+	BPF_EMIT_CALL(BPF_FUNC_sk_release),
+	BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_7, offsetof(struct bpf_sock, type)),
+	BPF_EXIT_INSN(),
+	},
+	.prog_type = BPF_PROG_TYPE_SCHED_CLS,
+	.result = REJECT,
+	.errstr = "invalid mem access",
+},
+{
+	"reference tracking: use ptr from bpf_sk_fullsock(tp) after release",
+	.insns = {
+	BPF_SK_LOOKUP,
+	BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 0, 1),
+	BPF_EXIT_INSN(),
+	BPF_MOV64_REG(BPF_REG_6, BPF_REG_0),
+	BPF_MOV64_REG(BPF_REG_1, BPF_REG_0),
+	BPF_EMIT_CALL(BPF_FUNC_tcp_sock),
+	BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 0, 3),
+	BPF_MOV64_REG(BPF_REG_1, BPF_REG_6),
+	BPF_EMIT_CALL(BPF_FUNC_sk_release),
+	BPF_EXIT_INSN(),
+	BPF_MOV64_REG(BPF_REG_1, BPF_REG_0),
+	BPF_EMIT_CALL(BPF_FUNC_sk_fullsock),
+	BPF_MOV64_REG(BPF_REG_1, BPF_REG_6),
+	BPF_MOV64_REG(BPF_REG_6, BPF_REG_0),
+	BPF_EMIT_CALL(BPF_FUNC_sk_release),
+	BPF_JMP_IMM(BPF_JNE, BPF_REG_6, 0, 1),
+	BPF_EXIT_INSN(),
+	BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_6, offsetof(struct bpf_sock, type)),
+	BPF_EXIT_INSN(),
+	},
+	.prog_type = BPF_PROG_TYPE_SCHED_CLS,
+	.result = REJECT,
+	.errstr = "invalid mem access",
+},
+{
+	"reference tracking: use sk after bpf_sk_release(tp)",
+	.insns = {
+	BPF_SK_LOOKUP,
+	BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 0, 1),
+	BPF_EXIT_INSN(),
+	BPF_MOV64_REG(BPF_REG_6, BPF_REG_0),
+	BPF_MOV64_REG(BPF_REG_1, BPF_REG_0),
+	BPF_EMIT_CALL(BPF_FUNC_tcp_sock),
+	BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 0, 3),
+	BPF_MOV64_REG(BPF_REG_1, BPF_REG_6),
+	BPF_EMIT_CALL(BPF_FUNC_sk_release),
+	BPF_EXIT_INSN(),
+	BPF_MOV64_REG(BPF_REG_1, BPF_REG_0),
+	BPF_EMIT_CALL(BPF_FUNC_sk_release),
+	BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_6, offsetof(struct bpf_sock, type)),
+	BPF_EXIT_INSN(),
+	},
+	.prog_type = BPF_PROG_TYPE_SCHED_CLS,
+	.result = REJECT,
+	.errstr = "invalid mem access",
+},
+{
+	"reference tracking: use ptr from bpf_get_listener_sock() after bpf_sk_release(sk)",
+	.insns = {
+	BPF_SK_LOOKUP,
+	BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 0, 1),
+	BPF_EXIT_INSN(),
+	BPF_MOV64_REG(BPF_REG_6, BPF_REG_0),
+	BPF_MOV64_REG(BPF_REG_1, BPF_REG_0),
+	BPF_EMIT_CALL(BPF_FUNC_get_listener_sock),
+	BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 0, 3),
+	BPF_MOV64_REG(BPF_REG_1, BPF_REG_6),
+	BPF_EMIT_CALL(BPF_FUNC_sk_release),
+	BPF_EXIT_INSN(),
+	BPF_MOV64_REG(BPF_REG_1, BPF_REG_6),
+	BPF_MOV64_REG(BPF_REG_6, BPF_REG_0),
+	BPF_EMIT_CALL(BPF_FUNC_sk_release),
+	BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_6, offsetof(struct bpf_sock, src_port)),
+	BPF_EXIT_INSN(),
+	},
+	.prog_type = BPF_PROG_TYPE_SCHED_CLS,
+	.result = ACCEPT,
+},
+{
+	"reference tracking: bpf_sk_release(listen_sk)",
+	.insns = {
+	BPF_SK_LOOKUP,
+	BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 0, 1),
+	BPF_EXIT_INSN(),
+	BPF_MOV64_REG(BPF_REG_6, BPF_REG_0),
+	BPF_MOV64_REG(BPF_REG_1, BPF_REG_0),
+	BPF_EMIT_CALL(BPF_FUNC_get_listener_sock),
+	BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 0, 3),
+	BPF_MOV64_REG(BPF_REG_1, BPF_REG_6),
+	BPF_EMIT_CALL(BPF_FUNC_sk_release),
+	BPF_EXIT_INSN(),
+	BPF_MOV64_REG(BPF_REG_1, BPF_REG_0),
+	BPF_EMIT_CALL(BPF_FUNC_sk_release),
+	BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_6, offsetof(struct bpf_sock, type)),
+	BPF_MOV64_REG(BPF_REG_1, BPF_REG_6),
+	BPF_EMIT_CALL(BPF_FUNC_sk_release),
+	BPF_EXIT_INSN(),
+	},
+	.prog_type = BPF_PROG_TYPE_SCHED_CLS,
+	.result = REJECT,
+	.errstr = "reference has not been acquired before",
+},
+{
+	/* !bpf_sk_fullsock(sk) is checked but !bpf_tcp_sock(sk) is not checked */
+	"reference tracking: tp->snd_cwnd after bpf_sk_fullsock(sk) and bpf_tcp_sock(sk)",
+	.insns = {
+	BPF_SK_LOOKUP,
+	BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 0, 1),
+	BPF_EXIT_INSN(),
+	BPF_MOV64_REG(BPF_REG_6, BPF_REG_0),
+	BPF_MOV64_REG(BPF_REG_1, BPF_REG_0),
+	BPF_EMIT_CALL(BPF_FUNC_sk_fullsock),
+	BPF_MOV64_REG(BPF_REG_7, BPF_REG_0),
+	BPF_MOV64_REG(BPF_REG_1, BPF_REG_6),
+	BPF_EMIT_CALL(BPF_FUNC_tcp_sock),
+	BPF_MOV64_REG(BPF_REG_8, BPF_REG_0),
+	BPF_JMP_IMM(BPF_JNE, BPF_REG_7, 0, 3),
+	BPF_MOV64_REG(BPF_REG_1, BPF_REG_6),
+	BPF_EMIT_CALL(BPF_FUNC_sk_release),
+	BPF_EXIT_INSN(),
+	BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_8, offsetof(struct bpf_tcp_sock, snd_cwnd)),
+	BPF_MOV64_REG(BPF_REG_1, BPF_REG_6),
+	BPF_EMIT_CALL(BPF_FUNC_sk_release),
+	BPF_EXIT_INSN(),
+	},
+	.prog_type = BPF_PROG_TYPE_SCHED_CLS,
+	.result = REJECT,
+	.errstr = "invalid mem access",
+},
diff --git a/tools/testing/selftests/bpf/verifier/sock.c b/tools/testing/selftests/bpf/verifier/sock.c
index 0ddfdf76aba5..416436231fab 100644
--- a/tools/testing/selftests/bpf/verifier/sock.c
+++ b/tools/testing/selftests/bpf/verifier/sock.c
@@ -342,7 +342,7 @@
 	},
 	.prog_type = BPF_PROG_TYPE_SCHED_CLS,
 	.result = REJECT,
-	.errstr = "type=sock_common expected=sock",
+	.errstr = "reference has not been acquired before",
 },
 {
 	"bpf_sk_release(bpf_sk_fullsock(skb->sk))",
@@ -380,5 +380,5 @@
 	},
 	.prog_type = BPF_PROG_TYPE_SCHED_CLS,
 	.result = REJECT,
-	.errstr = "type=tcp_sock expected=sock",
+	.errstr = "reference has not been acquired before",
 },
diff --git a/tools/testing/selftests/cgroup/test_memcontrol.c b/tools/testing/selftests/cgroup/test_memcontrol.c
index 28d321ba311b..6f339882a6ca 100644
--- a/tools/testing/selftests/cgroup/test_memcontrol.c
+++ b/tools/testing/selftests/cgroup/test_memcontrol.c
@@ -26,7 +26,7 @@
  */
 static int test_memcg_subtree_control(const char *root)
 {
-	char *parent, *child, *parent2, *child2;
+	char *parent, *child, *parent2 = NULL, *child2 = NULL;
 	int ret = KSFT_FAIL;
 	char buf[PAGE_SIZE];
 
@@ -34,50 +34,54 @@ static int test_memcg_subtree_control(const char *root)
 	parent = cg_name(root, "memcg_test_0");
 	child = cg_name(root, "memcg_test_0/memcg_test_1");
 	if (!parent || !child)
-		goto cleanup;
+		goto cleanup_free;
 
 	if (cg_create(parent))
-		goto cleanup;
+		goto cleanup_free;
 
 	if (cg_write(parent, "cgroup.subtree_control", "+memory"))
-		goto cleanup;
+		goto cleanup_parent;
 
 	if (cg_create(child))
-		goto cleanup;
+		goto cleanup_parent;
 
 	if (cg_read_strstr(child, "cgroup.controllers", "memory"))
-		goto cleanup;
+		goto cleanup_child;
 
 	/* Create two nested cgroups without enabling memory controller */
 	parent2 = cg_name(root, "memcg_test_1");
 	child2 = cg_name(root, "memcg_test_1/memcg_test_1");
 	if (!parent2 || !child2)
-		goto cleanup;
+		goto cleanup_free2;
 
 	if (cg_create(parent2))
-		goto cleanup;
+		goto cleanup_free2;
 
 	if (cg_create(child2))
-		goto cleanup;
+		goto cleanup_parent2;
 
 	if (cg_read(child2, "cgroup.controllers", buf, sizeof(buf)))
-		goto cleanup;
+		goto cleanup_all;
 
 	if (!cg_read_strstr(child2, "cgroup.controllers", "memory"))
-		goto cleanup;
+		goto cleanup_all;
 
 	ret = KSFT_PASS;
 
-cleanup:
-	cg_destroy(child);
-	cg_destroy(parent);
-	free(parent);
-	free(child);
-
+cleanup_all:
 	cg_destroy(child2);
+cleanup_parent2:
 	cg_destroy(parent2);
+cleanup_free2:
 	free(parent2);
 	free(child2);
+cleanup_child:
+	cg_destroy(child);
+cleanup_parent:
+	cg_destroy(parent);
+cleanup_free:
+	free(parent);
+	free(child);
 
 	return ret;
 }
diff --git a/tools/testing/selftests/drivers/net/mlxsw/rtnetlink.sh b/tools/testing/selftests/drivers/net/mlxsw/rtnetlink.sh
index c4cf6e6d800e..a6c196c8534c 100755
--- a/tools/testing/selftests/drivers/net/mlxsw/rtnetlink.sh
+++ b/tools/testing/selftests/drivers/net/mlxsw/rtnetlink.sh
@@ -11,6 +11,7 @@ lib_dir=$(dirname $0)/../../../net/forwarding
 
 ALL_TESTS="
 	rif_set_addr_test
+	rif_vrf_set_addr_test
 	rif_inherit_bridge_addr_test
 	rif_non_inherit_bridge_addr_test
 	vlan_interface_deletion_test
@@ -98,6 +99,25 @@ rif_set_addr_test()
 	ip link set dev $swp1 addr $swp1_mac
 }
 
+rif_vrf_set_addr_test()
+{
+	# Test that it is possible to set an IP address on a VRF upper despite
+	# its random MAC address.
+	RET=0
+
+	ip link add name vrf-test type vrf table 10
+	ip link set dev $swp1 master vrf-test
+
+	ip -4 address add 192.0.2.1/24 dev vrf-test
+	check_err $? "failed to set IPv4 address on VRF"
+	ip -6 address add 2001:db8:1::1/64 dev vrf-test
+	check_err $? "failed to set IPv6 address on VRF"
+
+	log_test "RIF - setting IP address on VRF"
+
+	ip link del dev vrf-test
+}
+
 rif_inherit_bridge_addr_test()
 {
 	RET=0
diff --git a/tools/testing/selftests/efivarfs/efivarfs.sh b/tools/testing/selftests/efivarfs/efivarfs.sh
index a47029a799d2..a90f394f9aa9 100755
--- a/tools/testing/selftests/efivarfs/efivarfs.sh
+++ b/tools/testing/selftests/efivarfs/efivarfs.sh
@@ -7,6 +7,12 @@ test_guid=210be57c-9849-4fc7-a635-e6382d1aec27
 # Kselftest framework requirement - SKIP code is 4.
 ksft_skip=4
 
+file_cleanup()
+{
+	chattr -i $1
+	rm -f $1
+}
+
 check_prereqs()
 {
 	local msg="skip all tests:"
@@ -58,8 +64,10 @@ test_create()
 
 	if [ $(stat -c %s $file) -ne 5 ]; then
 		echo "$file has invalid size" >&2
+		file_cleanup $file
 		exit 1
 	fi
+	file_cleanup $file
 }
 
 test_create_empty()
@@ -72,12 +80,14 @@ test_create_empty()
 		echo "$file can not be created without writing" >&2
 		exit 1
 	fi
+	file_cleanup $file
 }
 
 test_create_read()
 {
 	local file=$efivarfs_mount/$FUNCNAME-$test_guid
 	./create-read $file
+	file_cleanup $file
 }
 
 test_delete()
@@ -92,11 +102,7 @@ test_delete()
 		exit 1
 	fi
 
-	rm $file 2>/dev/null
-	if [ $? -ne 0 ]; then
-		chattr -i $file
-		rm $file
-	fi
+	file_cleanup $file
 
 	if [ -e $file ]; then
 		echo "$file couldn't be deleted" >&2
@@ -150,11 +156,7 @@ test_valid_filenames()
 			echo "$file could not be created" >&2
 			ret=1
 		else
-			rm $file 2>/dev/null
-			if [ $? -ne 0 ]; then
-				chattr -i $file
-				rm $file
-			fi
+			file_cleanup $file
 		fi
 	done
 
@@ -187,11 +189,7 @@ test_invalid_filenames()
 
 		if [ -e $file ]; then
 			echo "Creating $file should have failed" >&2
-			rm $file 2>/dev/null
-			if [ $? -ne 0 ]; then
-				chattr -i $file
-				rm $file
-			fi
+			file_cleanup $file
 			ret=1
 		fi
 	done
diff --git a/tools/testing/selftests/gpio/gpio-mockup-chardev.c b/tools/testing/selftests/gpio/gpio-mockup-chardev.c
index aaa1e9f083c3..d587c814a9ca 100644
--- a/tools/testing/selftests/gpio/gpio-mockup-chardev.c
+++ b/tools/testing/selftests/gpio/gpio-mockup-chardev.c
@@ -12,7 +12,6 @@
 #include <unistd.h>
 #include <stdio.h>
 #include <stdlib.h>
-#include <stdio.h>
 #include <errno.h>
 #include <string.h>
 #include <fcntl.h>
diff --git a/tools/testing/selftests/ima/config b/tools/testing/selftests/ima/config
deleted file mode 100644
index 6bc86d4d9bb4..000000000000
--- a/tools/testing/selftests/ima/config
+++ /dev/null
@@ -1,4 +0,0 @@
-CONFIG_IMA_APPRAISE
-CONFIG_IMA_ARCH_POLICY
-CONFIG_SECURITYFS
-CONFIG_KEXEC_VERIFY_SIG
diff --git a/tools/testing/selftests/ima/test_kexec_load.sh b/tools/testing/selftests/ima/test_kexec_load.sh
deleted file mode 100755
index 1c10093fb526..000000000000
--- a/tools/testing/selftests/ima/test_kexec_load.sh
+++ /dev/null
@@ -1,54 +0,0 @@
-#!/bin/sh
-# SPDX-License-Identifier: GPL-2.0+
-# Loading a kernel image via the kexec_load syscall should fail
-# when the kerne is CONFIG_KEXEC_VERIFY_SIG enabled and the system
-# is booted in secureboot mode.
-
-TEST="$0"
-EFIVARFS="/sys/firmware/efi/efivars"
-rc=0
-
-# Kselftest framework requirement - SKIP code is 4.
-ksft_skip=4
-
-# kexec requires root privileges
-if [ $UID != 0 ]; then
-	echo "$TEST: must be run as root" >&2
-	exit $ksft_skip
-fi
-
-# Make sure that efivars is mounted in the normal location
-if ! grep -q "^\S\+ $EFIVARFS efivarfs" /proc/mounts; then
-	echo "$TEST: efivars is not mounted on $EFIVARFS" >&2
-	exit $ksft_skip
-fi
-
-# Get secureboot mode
-file="$EFIVARFS/SecureBoot-*"
-if [ ! -e $file ]; then
-	echo "$TEST: unknown secureboot mode" >&2
-	exit $ksft_skip
-fi
-secureboot=`hexdump $file | awk '{print substr($4,length($4),1)}'`
-
-# kexec_load should fail in secure boot mode
-KERNEL_IMAGE="/boot/vmlinuz-`uname -r`"
-kexec -l $KERNEL_IMAGE &>> /dev/null
-if [ $? == 0 ]; then
-	kexec -u
-	if [ "$secureboot" == "1" ]; then
-		echo "$TEST: kexec_load succeeded [FAIL]"
-		rc=1
-	else
-		echo "$TEST: kexec_load succeeded [PASS]"
-	fi
-else
-	if [ "$secureboot" == "1" ]; then
-		echo "$TEST: kexec_load failed [PASS]"
-	else
-		echo "$TEST: kexec_load failed [FAIL]"
-		rc=1
-	fi
-fi
-
-exit $rc
diff --git a/tools/testing/selftests/ipc/msgque.c b/tools/testing/selftests/ipc/msgque.c
index dac927e82336..4c156aeab6b8 100644
--- a/tools/testing/selftests/ipc/msgque.c
+++ b/tools/testing/selftests/ipc/msgque.c
@@ -1,9 +1,10 @@
 // SPDX-License-Identifier: GPL-2.0
+#define _GNU_SOURCE
 #include <stdlib.h>
 #include <stdio.h>
 #include <string.h>
 #include <errno.h>
-#include <linux/msg.h>
+#include <sys/msg.h>
 #include <fcntl.h>
 
 #include "../kselftest.h"
@@ -73,7 +74,7 @@ int restore_queue(struct msgque_data *msgque)
 	return 0;
 
 destroy:
-	if (msgctl(id, IPC_RMID, 0))
+	if (msgctl(id, IPC_RMID, NULL))
 		printf("Failed to destroy queue: %d\n", -errno);
 	return ret;
 }
@@ -120,7 +121,7 @@ int check_and_destroy_queue(struct msgque_data *msgque)
 
 	ret = 0;
 err:
-	if (msgctl(msgque->msq_id, IPC_RMID, 0)) {
+	if (msgctl(msgque->msq_id, IPC_RMID, NULL)) {
 		printf("Failed to destroy queue: %d\n", -errno);
 		return -errno;
 	}
@@ -129,7 +130,7 @@ err:
 
 int dump_queue(struct msgque_data *msgque)
 {
-	struct msqid64_ds ds;
+	struct msqid_ds ds;
 	int kern_id;
 	int i, ret;
 
@@ -245,7 +246,7 @@ int main(int argc, char **argv)
 	return ksft_exit_pass();
 
 err_destroy:
-	if (msgctl(msgque.msq_id, IPC_RMID, 0)) {
+	if (msgctl(msgque.msq_id, IPC_RMID, NULL)) {
 		printf("Failed to destroy queue: %d\n", -errno);
 		return ksft_exit_fail();
 	}
diff --git a/tools/testing/selftests/ima/Makefile b/tools/testing/selftests/kexec/Makefile
index 0b3adf5444b6..8e9b27a7452f 100644
--- a/tools/testing/selftests/ima/Makefile
+++ b/tools/testing/selftests/kexec/Makefile
@@ -1,10 +1,11 @@
-# Makefile for kexec_load
+# Makefile for kexec tests
 
 uname_M := $(shell uname -m 2>/dev/null || echo not)
 ARCH ?= $(shell echo $(uname_M) | sed -e s/i.86/x86/ -e s/x86_64/x86/)
 
 ifeq ($(ARCH),x86)
-TEST_PROGS := test_kexec_load.sh
+TEST_PROGS := test_kexec_load.sh test_kexec_file_load.sh
+TEST_FILES := kexec_common_lib.sh
 
 include ../lib.mk
 
diff --git a/tools/testing/selftests/kexec/config b/tools/testing/selftests/kexec/config
new file mode 100644
index 000000000000..8962e862b2b8
--- /dev/null
+++ b/tools/testing/selftests/kexec/config
@@ -0,0 +1,3 @@
+CONFIG_IMA_APPRAISE=y
+CONFIG_IMA_ARCH_POLICY=y
+CONFIG_SECURITYFS=y
diff --git a/tools/testing/selftests/kexec/kexec_common_lib.sh b/tools/testing/selftests/kexec/kexec_common_lib.sh
new file mode 100755
index 000000000000..43017cfe88f7
--- /dev/null
+++ b/tools/testing/selftests/kexec/kexec_common_lib.sh
@@ -0,0 +1,220 @@
+#!/bin/sh
+# SPDX-License-Identifier: GPL-2.0
+#
+# Kselftest framework defines: ksft_pass=0, ksft_fail=1, ksft_skip=4
+
+VERBOSE="${VERBOSE:-1}"
+IKCONFIG="/tmp/config-`uname -r`"
+KERNEL_IMAGE="/boot/vmlinuz-`uname -r`"
+SECURITYFS=$(grep "securityfs" /proc/mounts | awk '{print $2}')
+
+log_info()
+{
+	[ $VERBOSE -ne 0 ] && echo "[INFO] $1"
+}
+
+# The ksefltest framework requirement returns 0 for PASS.
+log_pass()
+{
+	[ $VERBOSE -ne 0 ] && echo "$1 [PASS]"
+	exit 0
+}
+
+# The ksefltest framework requirement returns 1 for FAIL.
+log_fail()
+{
+	[ $VERBOSE -ne 0 ] && echo "$1 [FAIL]"
+	exit 1
+}
+
+# The ksefltest framework requirement returns 4 for SKIP.
+log_skip()
+{
+	[ $VERBOSE -ne 0 ] && echo "$1"
+	exit 4
+}
+
+# Check efivar SecureBoot-$(the UUID) and SetupMode-$(the UUID).
+# (Based on kdump-lib.sh)
+get_efivarfs_secureboot_mode()
+{
+	local efivarfs="/sys/firmware/efi/efivars"
+	local secure_boot_file=""
+	local setup_mode_file=""
+	local secureboot_mode=0
+	local setup_mode=0
+
+	# Make sure that efivar_fs is mounted in the normal location
+	if ! grep -q "^\S\+ $efivarfs efivarfs" /proc/mounts; then
+		log_info "efivars is not mounted on $efivarfs"
+		return 0;
+	fi
+	secure_boot_file=$(find "$efivarfs" -name SecureBoot-* 2>/dev/null)
+	setup_mode_file=$(find "$efivarfs" -name SetupMode-* 2>/dev/null)
+	if [ -f "$secure_boot_file" ] && [ -f "$setup_mode_file" ]; then
+		secureboot_mode=$(hexdump -v -e '/1 "%d\ "' \
+			"$secure_boot_file"|cut -d' ' -f 5)
+		setup_mode=$(hexdump -v -e '/1 "%d\ "' \
+			"$setup_mode_file"|cut -d' ' -f 5)
+
+		if [ $secureboot_mode -eq 1 ] && [ $setup_mode -eq 0 ]; then
+			log_info "secure boot mode enabled (CONFIG_EFIVAR_FS)"
+			return 1;
+		fi
+	fi
+	return 0;
+}
+
+get_efi_var_secureboot_mode()
+{
+	local efi_vars
+	local secure_boot_file
+	local setup_mode_file
+	local secureboot_mode
+	local setup_mode
+
+	if [ ! -d "$efi_vars" ]; then
+		log_skip "efi_vars is not enabled\n"
+	fi
+	secure_boot_file=$(find "$efi_vars" -name SecureBoot-* 2>/dev/null)
+	setup_mode_file=$(find "$efi_vars" -name SetupMode-* 2>/dev/null)
+	if [ -f "$secure_boot_file/data" ] && \
+	   [ -f "$setup_mode_file/data" ]; then
+		secureboot_mode=`od -An -t u1 "$secure_boot_file/data"`
+		setup_mode=`od -An -t u1 "$setup_mode_file/data"`
+
+		if [ $secureboot_mode -eq 1 ] && [ $setup_mode -eq 0 ]; then
+			log_info "secure boot mode enabled (CONFIG_EFI_VARS)"
+			return 1;
+		fi
+	fi
+	return 0;
+}
+
+# Check efivar SecureBoot-$(the UUID) and SetupMode-$(the UUID).
+# The secure boot mode can be accessed either as the last integer
+# of "od -An -t u1 /sys/firmware/efi/efivars/SecureBoot-*" or from
+# "od -An -t u1 /sys/firmware/efi/vars/SecureBoot-*/data".  The efi
+# SetupMode can be similarly accessed.
+# Return 1 for SecureBoot mode enabled and SetupMode mode disabled.
+get_secureboot_mode()
+{
+	local secureboot_mode=0
+
+	get_efivarfs_secureboot_mode
+	secureboot_mode=$?
+
+	# fallback to using the efi_var files
+	if [ $secureboot_mode -eq 0 ]; then
+		get_efi_var_secureboot_mode
+		secureboot_mode=$?
+	fi
+
+	if [ $secureboot_mode -eq 0 ]; then
+		log_info "secure boot mode not enabled"
+	fi
+	return $secureboot_mode;
+}
+
+require_root_privileges()
+{
+	if [ $(id -ru) -ne 0 ]; then
+		log_skip "requires root privileges"
+	fi
+}
+
+# Look for config option in Kconfig file.
+# Return 1 for found and 0 for not found.
+kconfig_enabled()
+{
+	local config="$1"
+	local msg="$2"
+
+	grep -E -q $config $IKCONFIG
+	if [ $? -eq 0 ]; then
+		log_info "$msg"
+		return 1
+	fi
+	return 0
+}
+
+# Attempt to get the kernel config first via proc, and then by
+# extracting it from the kernel image or the configs.ko using
+# scripts/extract-ikconfig.
+# Return 1 for found.
+get_kconfig()
+{
+	local proc_config="/proc/config.gz"
+	local module_dir="/lib/modules/`uname -r`"
+	local configs_module="$module_dir/kernel/kernel/configs.ko"
+
+	if [ ! -f $proc_config ]; then
+		modprobe configs > /dev/null 2>&1
+	fi
+	if [ -f $proc_config ]; then
+		cat $proc_config | gunzip > $IKCONFIG 2>/dev/null
+		if [ $? -eq 0 ]; then
+			return 1
+		fi
+	fi
+
+	local extract_ikconfig="$module_dir/source/scripts/extract-ikconfig"
+	if [ ! -f $extract_ikconfig ]; then
+		log_skip "extract-ikconfig not found"
+	fi
+
+	$extract_ikconfig $KERNEL_IMAGE > $IKCONFIG 2>/dev/null
+	if [ $? -eq 1 ]; then
+		if [ ! -f $configs_module ]; then
+			log_skip "CONFIG_IKCONFIG not enabled"
+		fi
+		$extract_ikconfig $configs_module > $IKCONFIG
+		if [ $? -eq 1 ]; then
+			log_skip "CONFIG_IKCONFIG not enabled"
+		fi
+	fi
+	return 1
+}
+
+# Make sure that securityfs is mounted
+mount_securityfs()
+{
+	if [ -z $SECURITYFS ]; then
+		SECURITYFS=/sys/kernel/security
+		mount -t securityfs security $SECURITYFS
+	fi
+
+	if [ ! -d "$SECURITYFS" ]; then
+		log_fail "$SECURITYFS :securityfs is not mounted"
+	fi
+}
+
+# The policy rule format is an "action" followed by key-value pairs.  This
+# function supports up to two key-value pairs, in any order.
+# For example: action func=<keyword> [appraise_type=<type>]
+# Return 1 for found and 0 for not found.
+check_ima_policy()
+{
+	local action="$1"
+	local keypair1="$2"
+	local keypair2="$3"
+	local ret=0
+
+	mount_securityfs
+
+	local ima_policy=$SECURITYFS/ima/policy
+	if [ ! -e $ima_policy ]; then
+		log_fail "$ima_policy not found"
+	fi
+
+	if [ -n $keypair2 ]; then
+		grep -e "^$action.*$keypair1" "$ima_policy" | \
+			grep -q -e "$keypair2"
+	else
+		grep -q -e "^$action.*$keypair1" "$ima_policy"
+	fi
+
+	# invert "grep -q" result, returning 1 for found.
+	[ $? -eq 0 ] && ret=1
+	return $ret
+}
diff --git a/tools/testing/selftests/kexec/test_kexec_file_load.sh b/tools/testing/selftests/kexec/test_kexec_file_load.sh
new file mode 100755
index 000000000000..fa7c24e8eefb
--- /dev/null
+++ b/tools/testing/selftests/kexec/test_kexec_file_load.sh
@@ -0,0 +1,208 @@
+#!/bin/sh
+# SPDX-License-Identifier: GPL-2.0
+#
+# Loading a kernel image via the kexec_file_load syscall can verify either
+# the IMA signature stored in the security.ima xattr or the PE signature,
+# both signatures depending on the IMA policy, or none.
+#
+# To determine whether the kernel image is signed, this test depends
+# on pesign and getfattr.  This test also requires the kernel to be
+# built with CONFIG_IKCONFIG enabled and either CONFIG_IKCONFIG_PROC
+# enabled or access to the extract-ikconfig script.
+
+TEST="KEXEC_FILE_LOAD"
+. ./kexec_common_lib.sh
+
+trap "{ rm -f $IKCONFIG ; }" EXIT
+
+# Some of the IMA builtin policies may require the kexec kernel image to
+# be signed, but these policy rules may be replaced with a custom
+# policy.  Only CONFIG_IMA_APPRAISE_REQUIRE_KEXEC_SIGS persists after
+# loading a custom policy.  Check if it is enabled, before reading the
+# IMA runtime sysfs policy file.
+# Return 1 for IMA signature required and 0 for not required.
+is_ima_sig_required()
+{
+	local ret=0
+
+	kconfig_enabled "CONFIG_IMA_APPRAISE_REQUIRE_KEXEC_SIGS=y" \
+		"IMA kernel image signature required"
+	if [ $? -eq 1 ]; then
+		log_info "IMA signature required"
+		return 1
+	fi
+
+	# The architecture specific or a custom policy may require the
+	# kexec kernel image be signed.  Policy rules are walked
+	# sequentially.  As a result, a policy rule may be defined, but
+	# might not necessarily be used.  This test assumes if a policy
+	# rule is specified, that is the intent.
+	if [ $ima_read_policy -eq 1 ]; then
+		check_ima_policy "appraise" "func=KEXEC_KERNEL_CHECK" \
+			"appraise_type=imasig"
+		ret=$?
+		[ $ret -eq 1 ] && log_info "IMA signature required";
+	fi
+	return $ret
+}
+
+# The kexec_file_load_test() is complicated enough, require pesign.
+# Return 1 for PE signature found and 0 for not found.
+check_for_pesig()
+{
+	which pesign > /dev/null 2>&1 || log_skip "pesign not found"
+
+	pesign -i $KERNEL_IMAGE --show-signature | grep -q "No signatures"
+	local ret=$?
+	if [ $ret -eq 1 ]; then
+		log_info "kexec kernel image PE signed"
+	else
+		log_info "kexec kernel image not PE signed"
+	fi
+	return $ret
+}
+
+# The kexec_file_load_test() is complicated enough, require getfattr.
+# Return 1 for IMA signature found and 0 for not found.
+check_for_imasig()
+{
+	local ret=0
+
+	which getfattr > /dev/null 2>&1
+	if [ $?	-eq 1 ]; then
+		log_skip "getfattr not found"
+	fi
+
+	line=$(getfattr -n security.ima -e hex --absolute-names $KERNEL_IMAGE 2>&1)
+	echo $line | grep -q "security.ima=0x03"
+	if [ $? -eq 0 ]; then
+		ret=1
+		log_info "kexec kernel image IMA signed"
+	else
+		log_info "kexec kernel image not IMA signed"
+	fi
+	return $ret
+}
+
+kexec_file_load_test()
+{
+	local succeed_msg="kexec_file_load succeeded"
+	local failed_msg="kexec_file_load failed"
+	local key_msg="try enabling the CONFIG_INTEGRITY_PLATFORM_KEYRING"
+
+	line=$(kexec --load --kexec-file-syscall $KERNEL_IMAGE 2>&1)
+
+	if [ $? -eq 0 ]; then
+		kexec --unload --kexec-file-syscall
+
+		# In secureboot mode with an architecture  specific
+		# policy, make sure either an IMA or PE signature exists.
+		if [ $secureboot -eq 1 ] && [ $arch_policy -eq 1 ] && \
+			[ $ima_signed -eq 0 ] && [ $pe_signed -eq 0 ]; then
+			log_fail "$succeed_msg (missing sig)"
+		fi
+
+		if [ $kexec_sig_required -eq 1 -o $pe_sig_required -eq 1 ] \
+		     && [ $pe_signed -eq 0 ]; then
+			log_fail "$succeed_msg (missing PE sig)"
+		fi
+
+		if [ $ima_sig_required -eq 1 ] && [ $ima_signed -eq 0 ]; then
+			log_fail "$succeed_msg (missing IMA sig)"
+		fi
+
+		if [ $pe_sig_required -eq 0 ] && [ $ima_appraise -eq 1 ] \
+		    && [ $ima_sig_required -eq 0 ] && [ $ima_signed -eq 0 ] \
+	            && [ $ima_read_policy -eq 0 ]; then
+			log_fail "$succeed_msg (possibly missing IMA sig)"
+		fi
+
+		if [ $pe_sig_required -eq 0 ] && [ $ima_appraise -eq 0 ]; then
+			log_info "No signature verification required"
+		elif [ $pe_sig_required -eq 0 ] && [ $ima_appraise -eq 1 ] \
+		    && [ $ima_sig_required -eq 0 ] && [ $ima_signed -eq 0 ] \
+	            && [ $ima_read_policy -eq 1 ]; then
+			log_info "No signature verification required"
+		fi
+
+		log_pass "$succeed_msg"
+	fi
+
+	# Check the reason for the kexec_file_load failure
+	echo $line | grep -q "Required key not available"
+	if [ $? -eq 0 ]; then
+		if [ $platform_keyring -eq 0 ]; then
+			log_pass "$failed_msg (-ENOKEY), $key_msg"
+		else
+			log_pass "$failed_msg (-ENOKEY)"
+		fi
+	fi
+
+	if [ $kexec_sig_required -eq 1 -o $pe_sig_required -eq 1 ] \
+	     && [ $pe_signed -eq 0 ]; then
+		log_pass "$failed_msg (missing PE sig)"
+	fi
+
+	if [ $ima_sig_required -eq 1 ] && [ $ima_signed -eq 0 ]; then
+		log_pass "$failed_msg (missing IMA sig)"
+	fi
+
+	if [ $pe_sig_required -eq 0 ] && [ $ima_appraise -eq 1 ] \
+	    && [ $ima_sig_required -eq 0 ] && [ $ima_read_policy -eq 0 ] \
+	    && [ $ima_signed -eq 0 ]; then
+		log_pass "$failed_msg (possibly missing IMA sig)"
+	fi
+
+	log_pass "$failed_msg"
+	return 0
+}
+
+# kexec requires root privileges
+require_root_privileges
+
+# get the kernel config
+get_kconfig
+
+kconfig_enabled "CONFIG_KEXEC_FILE=y" "kexec_file_load is enabled"
+if [ $? -eq 0 ]; then
+	log_skip "kexec_file_load is not enabled"
+fi
+
+# Determine which kernel config options are enabled
+kconfig_enabled "CONFIG_IMA_APPRAISE=y" "IMA enabled"
+ima_appraise=$?
+
+kconfig_enabled "CONFIG_IMA_ARCH_POLICY=y" \
+	"architecture specific policy enabled"
+arch_policy=$?
+
+kconfig_enabled "CONFIG_INTEGRITY_PLATFORM_KEYRING=y" \
+	"platform keyring enabled"
+platform_keyring=$?
+
+kconfig_enabled "CONFIG_IMA_READ_POLICY=y" "reading IMA policy permitted"
+ima_read_policy=$?
+
+kconfig_enabled "CONFIG_KEXEC_SIG_FORCE=y" \
+	"kexec signed kernel image required"
+kexec_sig_required=$?
+
+kconfig_enabled "CONFIG_KEXEC_BZIMAGE_VERIFY_SIG=y" \
+	"PE signed kernel image required"
+pe_sig_required=$?
+
+is_ima_sig_required
+ima_sig_required=$?
+
+get_secureboot_mode
+secureboot=$?
+
+# Are there pe and ima signatures
+check_for_pesig
+pe_signed=$?
+
+check_for_imasig
+ima_signed=$?
+
+# Test loading the kernel image via kexec_file_load syscall
+kexec_file_load_test
diff --git a/tools/testing/selftests/kexec/test_kexec_load.sh b/tools/testing/selftests/kexec/test_kexec_load.sh
new file mode 100755
index 000000000000..49c6aa929137
--- /dev/null
+++ b/tools/testing/selftests/kexec/test_kexec_load.sh
@@ -0,0 +1,47 @@
+#!/bin/sh
+# SPDX-License-Identifier: GPL-2.0
+#
+# Prevent loading a kernel image via the kexec_load syscall when
+# signatures are required.  (Dependent on CONFIG_IMA_ARCH_POLICY.)
+
+TEST="$0"
+. ./kexec_common_lib.sh
+
+# kexec requires root privileges
+require_root_privileges
+
+# get the kernel config
+get_kconfig
+
+kconfig_enabled "CONFIG_KEXEC=y" "kexec_load is enabled"
+if [ $? -eq 0 ]; then
+	log_skip "kexec_load is not enabled"
+fi
+
+kconfig_enabled "CONFIG_IMA_APPRAISE=y" "IMA enabled"
+ima_appraise=$?
+
+kconfig_enabled "CONFIG_IMA_ARCH_POLICY=y" \
+	"IMA architecture specific policy enabled"
+arch_policy=$?
+
+get_secureboot_mode
+secureboot=$?
+
+# kexec_load should fail in secure boot mode and CONFIG_IMA_ARCH_POLICY enabled
+kexec --load $KERNEL_IMAGE > /dev/null 2>&1
+if [ $? -eq 0 ]; then
+	kexec --unload
+	if [ $secureboot -eq 1 ] && [ $arch_policy -eq 1 ]; then
+		log_fail "kexec_load succeeded"
+	elif [ $ima_appraise -eq 0 -o $arch_policy -eq 0 ]; then
+		log_info "Either IMA or the IMA arch policy is not enabled"
+	fi
+	log_pass "kexec_load succeeded"
+else
+	if [ $secureboot -eq 1 ] && [ $arch_policy -eq 1 ] ; then
+		log_pass "kexec_load failed"
+	else
+		log_fail "kexec_load failed"
+	fi
+fi
diff --git a/tools/testing/selftests/kselftest_harness.h b/tools/testing/selftests/kselftest_harness.h
index 2d90c98eeb67..941d9391377f 100644
--- a/tools/testing/selftests/kselftest_harness.h
+++ b/tools/testing/selftests/kselftest_harness.h
@@ -696,6 +696,7 @@ void __run_test(struct __test_metadata *t)
 	t->passed = 1;
 	t->trigger = 0;
 	printf("[ RUN      ] %s\n", t->name);
+	alarm(30);
 	child_pid = fork();
 	if (child_pid < 0) {
 		printf("ERROR SPAWNING TEST CHILD\n");
@@ -744,6 +745,7 @@ void __run_test(struct __test_metadata *t)
 		}
 	}
 	printf("[     %4s ] %s\n", (t->passed ? "OK" : "FAIL"), t->name);
+	alarm(0);
 }
 
 static int test_harness_run(int __attribute__((unused)) argc,
diff --git a/tools/testing/selftests/kselftest_module.h b/tools/testing/selftests/kselftest_module.h
new file mode 100644
index 000000000000..e8eafaf0941a
--- /dev/null
+++ b/tools/testing/selftests/kselftest_module.h
@@ -0,0 +1,48 @@
+/* SPDX-License-Identifier: GPL-2.0+ */
+#ifndef __KSELFTEST_MODULE_H
+#define __KSELFTEST_MODULE_H
+
+#include <linux/module.h>
+
+/*
+ * Test framework for writing test modules to be loaded by kselftest.
+ * See Documentation/dev-tools/kselftest.rst for an example test module.
+ */
+
+#define KSTM_MODULE_GLOBALS()			\
+static unsigned int total_tests __initdata;	\
+static unsigned int failed_tests __initdata
+
+#define KSTM_CHECK_ZERO(x) do {						\
+	total_tests++;							\
+	if (x) {							\
+		pr_warn("TC failed at %s:%d\n", __func__, __LINE__);	\
+		failed_tests++;						\
+	}								\
+} while (0)
+
+static inline int kstm_report(unsigned int total_tests, unsigned int failed_tests)
+{
+	if (failed_tests == 0)
+		pr_info("all %u tests passed\n", total_tests);
+	else
+		pr_warn("failed %u out of %u tests\n", failed_tests, total_tests);
+
+	return failed_tests ? -EINVAL : 0;
+}
+
+#define KSTM_MODULE_LOADERS(__module)			\
+static int __init __module##_init(void)			\
+{							\
+	pr_info("loaded.\n");				\
+	selftest();					\
+	return kstm_report(total_tests, failed_tests);	\
+}							\
+static void __exit __module##_exit(void)		\
+{							\
+	pr_info("unloaded.\n");				\
+}							\
+module_init(__module##_init);				\
+module_exit(__module##_exit)
+
+#endif	/* __KSELFTEST_MODULE_H */
diff --git a/tools/testing/selftests/kselftest_module.sh b/tools/testing/selftests/kselftest_module.sh
new file mode 100755
index 000000000000..18e1c7992d30
--- /dev/null
+++ b/tools/testing/selftests/kselftest_module.sh
@@ -0,0 +1,84 @@
+#!/bin/sh
+# SPDX-License-Identifier: GPL-2.0+
+
+#
+# Runs an individual test module.
+#
+# kselftest expects a separate executable for each test, this can be
+# created by adding a script like this:
+#
+#   #!/bin/sh
+#   SPDX-License-Identifier: GPL-2.0+
+#   $(dirname $0)/../kselftest_module.sh "description" module_name
+#
+# Example: tools/testing/selftests/lib/printf.sh
+
+desc=""				# Output prefix.
+module=""			# Filename (without the .ko).
+args=""				# modprobe arguments.
+
+modprobe="/sbin/modprobe"
+
+main() {
+    parse_args "$@"
+    assert_root
+    assert_have_module
+    run_module
+}
+
+parse_args() {
+    script=${0##*/}
+
+    if [ $# -lt 2 ]; then
+	echo "Usage: $script <description> <module_name> [FAIL]"
+	exit 1
+    fi
+
+    desc="$1"
+    shift || true
+    module="$1"
+    shift || true
+    args="$@"
+}
+
+assert_root() {
+    if [ ! -w /dev ]; then
+	skip "please run as root"
+    fi
+}
+
+assert_have_module() {
+    if ! $modprobe -q -n $module; then
+	skip "module $module is not found"
+    fi
+}
+
+run_module() {
+    if $modprobe -q $module $args; then
+	$modprobe -q -r $module
+	say "ok"
+    else
+	fail ""
+    fi
+}
+
+say() {
+    echo "$desc: $1"
+}
+
+
+fail() {
+    say "$1 [FAIL]" >&2
+    exit 1
+}
+
+skip() {
+    say "$1 [SKIP]" >&2
+    # Kselftest framework requirement - SKIP code is 4.
+    exit 4
+}
+
+#
+# Main script
+#
+main "$@"
diff --git a/tools/testing/selftests/kvm/Makefile b/tools/testing/selftests/kvm/Makefile
index 3c1f4bdf9000..f8588cca2bef 100644
--- a/tools/testing/selftests/kvm/Makefile
+++ b/tools/testing/selftests/kvm/Makefile
@@ -1,3 +1,5 @@
+include ../../../../scripts/Kbuild.include
+
 all:
 
 top_srcdir = ../../../..
@@ -17,6 +19,7 @@ TEST_GEN_PROGS_x86_64 += x86_64/state_test
 TEST_GEN_PROGS_x86_64 += x86_64/evmcs_test
 TEST_GEN_PROGS_x86_64 += x86_64/hyperv_cpuid
 TEST_GEN_PROGS_x86_64 += x86_64/vmx_close_while_nested_test
+TEST_GEN_PROGS_x86_64 += x86_64/smm_test
 TEST_GEN_PROGS_x86_64 += dirty_log_test
 TEST_GEN_PROGS_x86_64 += clear_dirty_log_test
 
@@ -29,8 +32,12 @@ LIBKVM += $(LIBKVM_$(UNAME_M))
 INSTALL_HDR_PATH = $(top_srcdir)/usr
 LINUX_HDR_PATH = $(INSTALL_HDR_PATH)/include/
 LINUX_TOOL_INCLUDE = $(top_srcdir)/tools/include
-CFLAGS += -O2 -g -std=gnu99 -I$(LINUX_TOOL_INCLUDE) -I$(LINUX_HDR_PATH) -Iinclude -I$(<D) -Iinclude/$(UNAME_M) -I..
-LDFLAGS += -pthread
+CFLAGS += -O2 -g -std=gnu99 -fno-stack-protector -fno-PIE -I$(LINUX_TOOL_INCLUDE) -I$(LINUX_HDR_PATH) -Iinclude -I$(<D) -Iinclude/$(UNAME_M) -I..
+
+no-pie-option := $(call try-run, echo 'int main() { return 0; }' | \
+        $(CC) -Werror $(KBUILD_CPPFLAGS) $(CC_OPTION_CFLAGS) -no-pie -x c - -o "$$TMP", -no-pie)
+
+LDFLAGS += -pthread $(no-pie-option)
 
 # After inclusion, $(OUTPUT) is defined and
 # $(TEST_GEN_PROGS) starts with $(OUTPUT)/
diff --git a/tools/testing/selftests/kvm/dirty_log_test.c b/tools/testing/selftests/kvm/dirty_log_test.c
index 4715cfba20dc..93f99c6b7d79 100644
--- a/tools/testing/selftests/kvm/dirty_log_test.c
+++ b/tools/testing/selftests/kvm/dirty_log_test.c
@@ -288,8 +288,11 @@ static void run_test(enum vm_guest_mode mode, unsigned long iterations,
 #endif
 	max_gfn = (1ul << (guest_pa_bits - guest_page_shift)) - 1;
 	guest_page_size = (1ul << guest_page_shift);
-	/* 1G of guest page sized pages */
-	guest_num_pages = (1ul << (30 - guest_page_shift));
+	/*
+	 * A little more than 1G of guest page sized pages.  Cover the
+	 * case where the size is not aligned to 64 pages.
+	 */
+	guest_num_pages = (1ul << (30 - guest_page_shift)) + 3;
 	host_page_size = getpagesize();
 	host_num_pages = (guest_num_pages * guest_page_size) / host_page_size +
 			 !!((guest_num_pages * guest_page_size) % host_page_size);
@@ -359,7 +362,7 @@ static void run_test(enum vm_guest_mode mode, unsigned long iterations,
 		kvm_vm_get_dirty_log(vm, TEST_MEM_SLOT_INDEX, bmap);
 #ifdef USE_CLEAR_DIRTY_LOG
 		kvm_vm_clear_dirty_log(vm, TEST_MEM_SLOT_INDEX, bmap, 0,
-				       DIV_ROUND_UP(host_num_pages, 64) * 64);
+				       host_num_pages);
 #endif
 		vm_dirty_log_verify(bmap);
 		iteration++;
diff --git a/tools/testing/selftests/kvm/include/kvm_util.h b/tools/testing/selftests/kvm/include/kvm_util.h
index a84785b02557..07b71ad9734a 100644
--- a/tools/testing/selftests/kvm/include/kvm_util.h
+++ b/tools/testing/selftests/kvm/include/kvm_util.h
@@ -102,6 +102,7 @@ vm_paddr_t addr_gva2gpa(struct kvm_vm *vm, vm_vaddr_t gva);
 struct kvm_run *vcpu_state(struct kvm_vm *vm, uint32_t vcpuid);
 void vcpu_run(struct kvm_vm *vm, uint32_t vcpuid);
 int _vcpu_run(struct kvm_vm *vm, uint32_t vcpuid);
+void vcpu_run_complete_io(struct kvm_vm *vm, uint32_t vcpuid);
 void vcpu_set_mp_state(struct kvm_vm *vm, uint32_t vcpuid,
 		       struct kvm_mp_state *mp_state);
 void vcpu_regs_get(struct kvm_vm *vm, uint32_t vcpuid, struct kvm_regs *regs);
diff --git a/tools/testing/selftests/kvm/include/x86_64/processor.h b/tools/testing/selftests/kvm/include/x86_64/processor.h
index e2884c2b81ff..6063d5b2f356 100644
--- a/tools/testing/selftests/kvm/include/x86_64/processor.h
+++ b/tools/testing/selftests/kvm/include/x86_64/processor.h
@@ -778,6 +778,33 @@ void vcpu_set_msr(struct kvm_vm *vm, uint32_t vcpuid, uint64_t msr_index,
 #define MSR_IA32_APICBASE_ENABLE	(1<<11)
 #define MSR_IA32_APICBASE_BASE		(0xfffff<<12)
 
+#define APIC_BASE_MSR	0x800
+#define X2APIC_ENABLE	(1UL << 10)
+#define	APIC_ICR	0x300
+#define		APIC_DEST_SELF		0x40000
+#define		APIC_DEST_ALLINC	0x80000
+#define		APIC_DEST_ALLBUT	0xC0000
+#define		APIC_ICR_RR_MASK	0x30000
+#define		APIC_ICR_RR_INVALID	0x00000
+#define		APIC_ICR_RR_INPROG	0x10000
+#define		APIC_ICR_RR_VALID	0x20000
+#define		APIC_INT_LEVELTRIG	0x08000
+#define		APIC_INT_ASSERT		0x04000
+#define		APIC_ICR_BUSY		0x01000
+#define		APIC_DEST_LOGICAL	0x00800
+#define		APIC_DEST_PHYSICAL	0x00000
+#define		APIC_DM_FIXED		0x00000
+#define		APIC_DM_FIXED_MASK	0x00700
+#define		APIC_DM_LOWEST		0x00100
+#define		APIC_DM_SMI		0x00200
+#define		APIC_DM_REMRD		0x00300
+#define		APIC_DM_NMI		0x00400
+#define		APIC_DM_INIT		0x00500
+#define		APIC_DM_STARTUP		0x00600
+#define		APIC_DM_EXTINT		0x00700
+#define		APIC_VECTOR_MASK	0x000FF
+#define	APIC_ICR2	0x310
+
 #define MSR_IA32_TSCDEADLINE		0x000006e0
 
 #define MSR_IA32_UCODE_WRITE		0x00000079
diff --git a/tools/testing/selftests/kvm/lib/kvm_util.c b/tools/testing/selftests/kvm/lib/kvm_util.c
index b52cfdefecbf..4ca96b228e46 100644
--- a/tools/testing/selftests/kvm/lib/kvm_util.c
+++ b/tools/testing/selftests/kvm/lib/kvm_util.c
@@ -91,6 +91,11 @@ static void vm_open(struct kvm_vm *vm, int perm, unsigned long type)
 	if (vm->kvm_fd < 0)
 		exit(KSFT_SKIP);
 
+	if (!kvm_check_cap(KVM_CAP_IMMEDIATE_EXIT)) {
+		fprintf(stderr, "immediate_exit not available, skipping test\n");
+		exit(KSFT_SKIP);
+	}
+
 	vm->fd = ioctl(vm->kvm_fd, KVM_CREATE_VM, type);
 	TEST_ASSERT(vm->fd >= 0, "KVM_CREATE_VM ioctl failed, "
 		"rc: %i errno: %i", vm->fd, errno);
@@ -1121,6 +1126,22 @@ int _vcpu_run(struct kvm_vm *vm, uint32_t vcpuid)
 	return rc;
 }
 
+void vcpu_run_complete_io(struct kvm_vm *vm, uint32_t vcpuid)
+{
+	struct vcpu *vcpu = vcpu_find(vm, vcpuid);
+	int ret;
+
+	TEST_ASSERT(vcpu != NULL, "vcpu not found, vcpuid: %u", vcpuid);
+
+	vcpu->state->immediate_exit = 1;
+	ret = ioctl(vcpu->fd, KVM_RUN, NULL);
+	vcpu->state->immediate_exit = 0;
+
+	TEST_ASSERT(ret == -1 && errno == EINTR,
+		    "KVM_RUN IOCTL didn't exit immediately, rc: %i, errno: %i",
+		    ret, errno);
+}
+
 /*
  * VM VCPU Set MP State
  *
diff --git a/tools/testing/selftests/kvm/lib/x86_64/processor.c b/tools/testing/selftests/kvm/lib/x86_64/processor.c
index f28127f4a3af..dc7fae9fa424 100644
--- a/tools/testing/selftests/kvm/lib/x86_64/processor.c
+++ b/tools/testing/selftests/kvm/lib/x86_64/processor.c
@@ -1030,6 +1030,14 @@ struct kvm_x86_state *vcpu_save_state(struct kvm_vm *vm, uint32_t vcpuid)
 			    nested_size, sizeof(state->nested_));
 	}
 
+	/*
+	 * When KVM exits to userspace with KVM_EXIT_IO, KVM guarantees
+	 * guest state is consistent only after userspace re-enters the
+	 * kernel with KVM_RUN.  Complete IO prior to migrating state
+	 * to a new VM.
+	 */
+	vcpu_run_complete_io(vm, vcpuid);
+
 	nmsrs = kvm_get_num_msrs(vm);
 	list = malloc(sizeof(*list) + nmsrs * sizeof(list->indices[0]));
 	list->nmsrs = nmsrs;
@@ -1093,12 +1101,6 @@ void vcpu_load_state(struct kvm_vm *vm, uint32_t vcpuid, struct kvm_x86_state *s
 	struct vcpu *vcpu = vcpu_find(vm, vcpuid);
 	int r;
 
-	if (state->nested.size) {
-		r = ioctl(vcpu->fd, KVM_SET_NESTED_STATE, &state->nested);
-		TEST_ASSERT(r == 0, "Unexpected result from KVM_SET_NESTED_STATE, r: %i",
-			r);
-	}
-
 	r = ioctl(vcpu->fd, KVM_SET_XSAVE, &state->xsave);
         TEST_ASSERT(r == 0, "Unexpected result from KVM_SET_XSAVE, r: %i",
                 r);
@@ -1130,4 +1132,10 @@ void vcpu_load_state(struct kvm_vm *vm, uint32_t vcpuid, struct kvm_x86_state *s
 	r = ioctl(vcpu->fd, KVM_SET_REGS, &state->regs);
         TEST_ASSERT(r == 0, "Unexpected result from KVM_SET_REGS, r: %i",
                 r);
+
+	if (state->nested.size) {
+		r = ioctl(vcpu->fd, KVM_SET_NESTED_STATE, &state->nested);
+		TEST_ASSERT(r == 0, "Unexpected result from KVM_SET_NESTED_STATE, r: %i",
+			r);
+	}
 }
diff --git a/tools/testing/selftests/kvm/x86_64/cr4_cpuid_sync_test.c b/tools/testing/selftests/kvm/x86_64/cr4_cpuid_sync_test.c
index d503a51fad30..7c2c4d4055a8 100644
--- a/tools/testing/selftests/kvm/x86_64/cr4_cpuid_sync_test.c
+++ b/tools/testing/selftests/kvm/x86_64/cr4_cpuid_sync_test.c
@@ -87,22 +87,25 @@ int main(int argc, char *argv[])
 	while (1) {
 		rc = _vcpu_run(vm, VCPU_ID);
 
-		if (run->exit_reason == KVM_EXIT_IO) {
-			switch (get_ucall(vm, VCPU_ID, &uc)) {
-			case UCALL_SYNC:
-				/* emulate hypervisor clearing CR4.OSXSAVE */
-				vcpu_sregs_get(vm, VCPU_ID, &sregs);
-				sregs.cr4 &= ~X86_CR4_OSXSAVE;
-				vcpu_sregs_set(vm, VCPU_ID, &sregs);
-				break;
-			case UCALL_ABORT:
-				TEST_ASSERT(false, "Guest CR4 bit (OSXSAVE) unsynchronized with CPUID bit.");
-				break;
-			case UCALL_DONE:
-				goto done;
-			default:
-				TEST_ASSERT(false, "Unknown ucall 0x%x.", uc.cmd);
-			}
+		TEST_ASSERT(run->exit_reason == KVM_EXIT_IO,
+			    "Unexpected exit reason: %u (%s),\n",
+			    run->exit_reason,
+			    exit_reason_str(run->exit_reason));
+
+		switch (get_ucall(vm, VCPU_ID, &uc)) {
+		case UCALL_SYNC:
+			/* emulate hypervisor clearing CR4.OSXSAVE */
+			vcpu_sregs_get(vm, VCPU_ID, &sregs);
+			sregs.cr4 &= ~X86_CR4_OSXSAVE;
+			vcpu_sregs_set(vm, VCPU_ID, &sregs);
+			break;
+		case UCALL_ABORT:
+			TEST_ASSERT(false, "Guest CR4 bit (OSXSAVE) unsynchronized with CPUID bit.");
+			break;
+		case UCALL_DONE:
+			goto done;
+		default:
+			TEST_ASSERT(false, "Unknown ucall 0x%x.", uc.cmd);
 		}
 	}
 
diff --git a/tools/testing/selftests/kvm/x86_64/evmcs_test.c b/tools/testing/selftests/kvm/x86_64/evmcs_test.c
index c49c2a28b0eb..36669684eca5 100644
--- a/tools/testing/selftests/kvm/x86_64/evmcs_test.c
+++ b/tools/testing/selftests/kvm/x86_64/evmcs_test.c
@@ -123,8 +123,6 @@ int main(int argc, char *argv[])
 			    stage, run->exit_reason,
 			    exit_reason_str(run->exit_reason));
 
-		memset(&regs1, 0, sizeof(regs1));
-		vcpu_regs_get(vm, VCPU_ID, &regs1);
 		switch (get_ucall(vm, VCPU_ID, &uc)) {
 		case UCALL_ABORT:
 			TEST_ASSERT(false, "%s at %s:%d", (const char *)uc.args[0],
@@ -144,6 +142,9 @@ int main(int argc, char *argv[])
 			    stage, (ulong)uc.args[1]);
 
 		state = vcpu_save_state(vm, VCPU_ID);
+		memset(&regs1, 0, sizeof(regs1));
+		vcpu_regs_get(vm, VCPU_ID, &regs1);
+
 		kvm_vm_release(vm);
 
 		/* Restore state in a new VM.  */
diff --git a/tools/testing/selftests/kvm/x86_64/hyperv_cpuid.c b/tools/testing/selftests/kvm/x86_64/hyperv_cpuid.c
index 264425f75806..9a21e912097c 100644
--- a/tools/testing/selftests/kvm/x86_64/hyperv_cpuid.c
+++ b/tools/testing/selftests/kvm/x86_64/hyperv_cpuid.c
@@ -141,7 +141,13 @@ int main(int argc, char *argv[])
 
 	free(hv_cpuid_entries);
 
-	vcpu_ioctl(vm, VCPU_ID, KVM_ENABLE_CAP, &enable_evmcs_cap);
+	rv = _vcpu_ioctl(vm, VCPU_ID, KVM_ENABLE_CAP, &enable_evmcs_cap);
+
+	if (rv) {
+		fprintf(stderr,
+			"Enlightened VMCS is unsupported, skip related test\n");
+		goto vm_free;
+	}
 
 	hv_cpuid_entries = kvm_get_supported_hv_cpuid(vm);
 	if (!hv_cpuid_entries)
@@ -151,6 +157,7 @@ int main(int argc, char *argv[])
 
 	free(hv_cpuid_entries);
 
+vm_free:
 	kvm_vm_free(vm);
 
 	return 0;
diff --git a/tools/testing/selftests/kvm/x86_64/smm_test.c b/tools/testing/selftests/kvm/x86_64/smm_test.c
new file mode 100644
index 000000000000..fb8086964d83
--- /dev/null
+++ b/tools/testing/selftests/kvm/x86_64/smm_test.c
@@ -0,0 +1,157 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (C) 2018, Red Hat, Inc.
+ *
+ * Tests for SMM.
+ */
+#define _GNU_SOURCE /* for program_invocation_short_name */
+#include <fcntl.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <stdint.h>
+#include <string.h>
+#include <sys/ioctl.h>
+
+#include "test_util.h"
+
+#include "kvm_util.h"
+
+#include "vmx.h"
+
+#define VCPU_ID	      1
+
+#define PAGE_SIZE  4096
+
+#define SMRAM_SIZE 65536
+#define SMRAM_MEMSLOT ((1 << 16) | 1)
+#define SMRAM_PAGES (SMRAM_SIZE / PAGE_SIZE)
+#define SMRAM_GPA 0x1000000
+#define SMRAM_STAGE 0xfe
+
+#define STR(x) #x
+#define XSTR(s) STR(s)
+
+#define SYNC_PORT 0xe
+#define DONE 0xff
+
+/*
+ * This is compiled as normal 64-bit code, however, SMI handler is executed
+ * in real-address mode. To stay simple we're limiting ourselves to a mode
+ * independent subset of asm here.
+ * SMI handler always report back fixed stage SMRAM_STAGE.
+ */
+uint8_t smi_handler[] = {
+	0xb0, SMRAM_STAGE,    /* mov $SMRAM_STAGE, %al */
+	0xe4, SYNC_PORT,      /* in $SYNC_PORT, %al */
+	0x0f, 0xaa,           /* rsm */
+};
+
+void sync_with_host(uint64_t phase)
+{
+	asm volatile("in $" XSTR(SYNC_PORT)", %%al \n"
+		     : : "a" (phase));
+}
+
+void self_smi(void)
+{
+	wrmsr(APIC_BASE_MSR + (APIC_ICR >> 4),
+	      APIC_DEST_SELF | APIC_INT_ASSERT | APIC_DM_SMI);
+}
+
+void guest_code(struct vmx_pages *vmx_pages)
+{
+	uint64_t apicbase = rdmsr(MSR_IA32_APICBASE);
+
+	sync_with_host(1);
+
+	wrmsr(MSR_IA32_APICBASE, apicbase | X2APIC_ENABLE);
+
+	sync_with_host(2);
+
+	self_smi();
+
+	sync_with_host(4);
+
+	if (vmx_pages) {
+		GUEST_ASSERT(prepare_for_vmx_operation(vmx_pages));
+
+		sync_with_host(5);
+
+		self_smi();
+
+		sync_with_host(7);
+	}
+
+	sync_with_host(DONE);
+}
+
+int main(int argc, char *argv[])
+{
+	struct vmx_pages *vmx_pages = NULL;
+	vm_vaddr_t vmx_pages_gva = 0;
+
+	struct kvm_regs regs;
+	struct kvm_vm *vm;
+	struct kvm_run *run;
+	struct kvm_x86_state *state;
+	int stage, stage_reported;
+
+	/* Create VM */
+	vm = vm_create_default(VCPU_ID, 0, guest_code);
+
+	vcpu_set_cpuid(vm, VCPU_ID, kvm_get_supported_cpuid());
+
+	run = vcpu_state(vm, VCPU_ID);
+
+	vm_userspace_mem_region_add(vm, VM_MEM_SRC_ANONYMOUS, SMRAM_GPA,
+				    SMRAM_MEMSLOT, SMRAM_PAGES, 0);
+	TEST_ASSERT(vm_phy_pages_alloc(vm, SMRAM_PAGES, SMRAM_GPA, SMRAM_MEMSLOT)
+		    == SMRAM_GPA, "could not allocate guest physical addresses?");
+
+	memset(addr_gpa2hva(vm, SMRAM_GPA), 0x0, SMRAM_SIZE);
+	memcpy(addr_gpa2hva(vm, SMRAM_GPA) + 0x8000, smi_handler,
+	       sizeof(smi_handler));
+
+	vcpu_set_msr(vm, VCPU_ID, MSR_IA32_SMBASE, SMRAM_GPA);
+
+	if (kvm_check_cap(KVM_CAP_NESTED_STATE)) {
+		vmx_pages = vcpu_alloc_vmx(vm, &vmx_pages_gva);
+		vcpu_args_set(vm, VCPU_ID, 1, vmx_pages_gva);
+	} else {
+		printf("will skip SMM test with VMX enabled\n");
+		vcpu_args_set(vm, VCPU_ID, 1, 0);
+	}
+
+	for (stage = 1;; stage++) {
+		_vcpu_run(vm, VCPU_ID);
+		TEST_ASSERT(run->exit_reason == KVM_EXIT_IO,
+			    "Stage %d: unexpected exit reason: %u (%s),\n",
+			    stage, run->exit_reason,
+			    exit_reason_str(run->exit_reason));
+
+		memset(&regs, 0, sizeof(regs));
+		vcpu_regs_get(vm, VCPU_ID, &regs);
+
+		stage_reported = regs.rax & 0xff;
+
+		if (stage_reported == DONE)
+			goto done;
+
+		TEST_ASSERT(stage_reported == stage ||
+			    stage_reported == SMRAM_STAGE,
+			    "Unexpected stage: #%x, got %x",
+			    stage, stage_reported);
+
+		state = vcpu_save_state(vm, VCPU_ID);
+		kvm_vm_release(vm);
+		kvm_vm_restart(vm, O_RDWR);
+		vm_vcpu_add(vm, VCPU_ID, 0, 0);
+		vcpu_set_cpuid(vm, VCPU_ID, kvm_get_supported_cpuid());
+		vcpu_load_state(vm, VCPU_ID, state);
+		run = vcpu_state(vm, VCPU_ID);
+		free(state);
+	}
+
+done:
+	kvm_vm_free(vm);
+}
diff --git a/tools/testing/selftests/kvm/x86_64/state_test.c b/tools/testing/selftests/kvm/x86_64/state_test.c
index 4b3f556265f1..e0a3c0204b7c 100644
--- a/tools/testing/selftests/kvm/x86_64/state_test.c
+++ b/tools/testing/selftests/kvm/x86_64/state_test.c
@@ -156,8 +156,6 @@ int main(int argc, char *argv[])
 			    stage, run->exit_reason,
 			    exit_reason_str(run->exit_reason));
 
-		memset(&regs1, 0, sizeof(regs1));
-		vcpu_regs_get(vm, VCPU_ID, &regs1);
 		switch (get_ucall(vm, VCPU_ID, &uc)) {
 		case UCALL_ABORT:
 			TEST_ASSERT(false, "%s at %s:%d", (const char *)uc.args[0],
@@ -177,6 +175,9 @@ int main(int argc, char *argv[])
 			    stage, (ulong)uc.args[1]);
 
 		state = vcpu_save_state(vm, VCPU_ID);
+		memset(&regs1, 0, sizeof(regs1));
+		vcpu_regs_get(vm, VCPU_ID, &regs1);
+
 		kvm_vm_release(vm);
 
 		/* Restore state in a new VM.  */
diff --git a/tools/testing/selftests/lib.mk b/tools/testing/selftests/lib.mk
index 8b0f16409ed7..5979fdc4f36c 100644
--- a/tools/testing/selftests/lib.mk
+++ b/tools/testing/selftests/lib.mk
@@ -3,7 +3,16 @@
 CC := $(CROSS_COMPILE)gcc
 
 ifeq (0,$(MAKELEVEL))
-OUTPUT := $(shell pwd)
+    ifneq ($(O),)
+	OUTPUT := $(O)
+    else
+	ifneq ($(KBUILD_OUTPUT),)
+		OUTPUT := $(KBUILD_OUTPUT)
+	else
+		OUTPUT := $(shell pwd)
+		DEFAULT_INSTALL_HDR_PATH := 1
+	endif
+    endif
 endif
 
 # The following are built by lib.mk common compile rules.
@@ -21,9 +30,34 @@ top_srcdir ?= ../../../..
 include $(top_srcdir)/scripts/subarch.include
 ARCH		?= $(SUBARCH)
 
+# set default goal to all, so make without a target runs all, even when
+# all isn't the first target in the file.
+.DEFAULT_GOAL := all
+
+# Invoke headers install with --no-builtin-rules to avoid circular
+# dependency in "make kselftest" case. In this case, second level
+# make inherits builtin-rules which will use the rule generate
+# Makefile.o and runs into
+# "Circular Makefile.o <- prepare dependency dropped."
+# and headers_install fails and test compile fails.
+# O= KBUILD_OUTPUT cases don't run into this error, since main Makefile
+# invokes them as sub-makes and --no-builtin-rules is not necessary,
+# but doesn't cause any failures. Keep it simple and use the same
+# flags in both cases.
+# Note that the support to install headers from lib.mk is necessary
+# when test Makefile is run directly with "make -C".
+# When local build is done, headers are installed in the default
+# INSTALL_HDR_PATH usr/include.
 .PHONY: khdr
 khdr:
-	make ARCH=$(ARCH) -C $(top_srcdir) headers_install
+ifndef KSFT_KHDR_INSTALL_DONE
+ifeq (1,$(DEFAULT_INSTALL_HDR_PATH))
+	make --no-builtin-rules ARCH=$(ARCH) -C $(top_srcdir) headers_install
+else
+	make --no-builtin-rules INSTALL_HDR_PATH=$$OUTPUT/usr \
+		ARCH=$(ARCH) -C $(top_srcdir) headers_install
+endif
+endif
 
 all: khdr $(TEST_GEN_PROGS) $(TEST_GEN_PROGS_EXTENDED) $(TEST_GEN_FILES)
 else
diff --git a/tools/testing/selftests/lib/Makefile b/tools/testing/selftests/lib/Makefile
index 70d5711e3ac8..9f26635f3e57 100644
--- a/tools/testing/selftests/lib/Makefile
+++ b/tools/testing/selftests/lib/Makefile
@@ -3,6 +3,6 @@
 # No binaries, but make sure arg-less "make" doesn't trigger "run_tests"
 all:
 
-TEST_PROGS := printf.sh bitmap.sh prime_numbers.sh
+TEST_PROGS := printf.sh bitmap.sh prime_numbers.sh strscpy.sh
 
 include ../lib.mk
diff --git a/tools/testing/selftests/lib/bitmap.sh b/tools/testing/selftests/lib/bitmap.sh
index 5a90006d1aea..5511dddc5c2d 100755
--- a/tools/testing/selftests/lib/bitmap.sh
+++ b/tools/testing/selftests/lib/bitmap.sh
@@ -1,19 +1,3 @@
 #!/bin/sh
 # SPDX-License-Identifier: GPL-2.0
-
-# Kselftest framework requirement - SKIP code is 4.
-ksft_skip=4
-
-# Runs bitmap infrastructure tests using test_bitmap kernel module
-if ! /sbin/modprobe -q -n test_bitmap; then
-	echo "bitmap: module test_bitmap is not found [SKIP]"
-	exit $ksft_skip
-fi
-
-if /sbin/modprobe -q test_bitmap; then
-	/sbin/modprobe -q -r test_bitmap
-	echo "bitmap: ok"
-else
-	echo "bitmap: [FAIL]"
-	exit 1
-fi
+$(dirname $0)/../kselftest_module.sh "bitmap" test_bitmap
diff --git a/tools/testing/selftests/lib/config b/tools/testing/selftests/lib/config
index 126933bcc950..14a77ea4a8da 100644
--- a/tools/testing/selftests/lib/config
+++ b/tools/testing/selftests/lib/config
@@ -1,3 +1,4 @@
 CONFIG_TEST_PRINTF=m
 CONFIG_TEST_BITMAP=m
 CONFIG_PRIME_NUMBERS=m
+CONFIG_TEST_STRSCPY=m
diff --git a/tools/testing/selftests/lib/prime_numbers.sh b/tools/testing/selftests/lib/prime_numbers.sh
index 78e7483c8d60..43b28f24e453 100755
--- a/tools/testing/selftests/lib/prime_numbers.sh
+++ b/tools/testing/selftests/lib/prime_numbers.sh
@@ -1,19 +1,4 @@
 #!/bin/sh
 # SPDX-License-Identifier: GPL-2.0
 # Checks fast/slow prime_number generation for inconsistencies
-
-# Kselftest framework requirement - SKIP code is 4.
-ksft_skip=4
-
-if ! /sbin/modprobe -q -n prime_numbers; then
-	echo "prime_numbers: module prime_numbers is not found [SKIP]"
-	exit $ksft_skip
-fi
-
-if /sbin/modprobe -q prime_numbers selftest=65536; then
-	/sbin/modprobe -q -r prime_numbers
-	echo "prime_numbers: ok"
-else
-	echo "prime_numbers: [FAIL]"
-	exit 1
-fi
+$(dirname $0)/../kselftest_module.sh "prime numbers" prime_numbers selftest=65536
diff --git a/tools/testing/selftests/lib/printf.sh b/tools/testing/selftests/lib/printf.sh
index 45a23e2d64ad..2ffa61da0296 100755
--- a/tools/testing/selftests/lib/printf.sh
+++ b/tools/testing/selftests/lib/printf.sh
@@ -1,19 +1,4 @@
 #!/bin/sh
 # SPDX-License-Identifier: GPL-2.0
-# Runs printf infrastructure using test_printf kernel module
-
-# Kselftest framework requirement - SKIP code is 4.
-ksft_skip=4
-
-if ! /sbin/modprobe -q -n test_printf; then
-	echo "printf: module test_printf is not found [SKIP]"
-	exit $ksft_skip
-fi
-
-if /sbin/modprobe -q test_printf; then
-	/sbin/modprobe -q -r test_printf
-	echo "printf: ok"
-else
-	echo "printf: [FAIL]"
-	exit 1
-fi
+# Tests the printf infrastructure using test_printf kernel module.
+$(dirname $0)/../kselftest_module.sh "printf" test_printf
diff --git a/tools/testing/selftests/lib/strscpy.sh b/tools/testing/selftests/lib/strscpy.sh
new file mode 100755
index 000000000000..71f2be6afba6
--- /dev/null
+++ b/tools/testing/selftests/lib/strscpy.sh
@@ -0,0 +1,3 @@
+#!/bin/sh
+# SPDX-License-Identifier: GPL-2.0+
+$(dirname $0)/../kselftest_module.sh "strscpy*" test_strscpy
diff --git a/tools/testing/selftests/net/fib_rule_tests.sh b/tools/testing/selftests/net/fib_rule_tests.sh
index d4cfb6a7a086..4b7e107865bf 100755
--- a/tools/testing/selftests/net/fib_rule_tests.sh
+++ b/tools/testing/selftests/net/fib_rule_tests.sh
@@ -27,6 +27,7 @@ log_test()
 		nsuccess=$((nsuccess+1))
 		printf "\n    TEST: %-50s  [ OK ]\n" "${msg}"
 	else
+		ret=1
 		nfail=$((nfail+1))
 		printf "\n    TEST: %-50s  [FAIL]\n" "${msg}"
 		if [ "${PAUSE_ON_FAIL}" = "yes" ]; then
@@ -147,8 +148,8 @@ fib_rule6_test()
 
 	fib_check_iproute_support "ipproto" "ipproto"
 	if [ $? -eq 0 ]; then
-		match="ipproto icmp"
-		fib_rule6_test_match_n_redirect "$match" "$match" "ipproto icmp match"
+		match="ipproto ipv6-icmp"
+		fib_rule6_test_match_n_redirect "$match" "$match" "ipproto ipv6-icmp match"
 	fi
 }
 
@@ -245,4 +246,9 @@ setup
 run_fibrule_tests
 cleanup
 
+if [ "$TESTS" != "none" ]; then
+	printf "\nTests passed: %3d\n" ${nsuccess}
+	printf "Tests failed: %3d\n"   ${nfail}
+fi
+
 exit $ret
diff --git a/tools/testing/selftests/net/fib_tests.sh b/tools/testing/selftests/net/fib_tests.sh
index 1080ff55a788..0d2a5f4f1e63 100755
--- a/tools/testing/selftests/net/fib_tests.sh
+++ b/tools/testing/selftests/net/fib_tests.sh
@@ -605,6 +605,39 @@ run_cmd()
 	return $rc
 }
 
+check_expected()
+{
+	local out="$1"
+	local expected="$2"
+	local rc=0
+
+	[ "${out}" = "${expected}" ] && return 0
+
+	if [ -z "${out}" ]; then
+		if [ "$VERBOSE" = "1" ]; then
+			printf "\nNo route entry found\n"
+			printf "Expected:\n"
+			printf "    ${expected}\n"
+		fi
+		return 1
+	fi
+
+	# tricky way to convert output to 1-line without ip's
+	# messy '\'; this drops all extra white space
+	out=$(echo ${out})
+	if [ "${out}" != "${expected}" ]; then
+		rc=1
+		if [ "${VERBOSE}" = "1" ]; then
+			printf "    Unexpected route entry. Have:\n"
+			printf "        ${out}\n"
+			printf "    Expected:\n"
+			printf "        ${expected}\n\n"
+		fi
+	fi
+
+	return $rc
+}
+
 # add route for a prefix, flushing any existing routes first
 # expected to be the first step of a test
 add_route6()
@@ -652,31 +685,7 @@ check_route6()
 	pfx=$1
 
 	out=$($IP -6 ro ls match ${pfx} | sed -e 's/ pref medium//')
-	[ "${out}" = "${expected}" ] && return 0
-
-	if [ -z "${out}" ]; then
-		if [ "$VERBOSE" = "1" ]; then
-			printf "\nNo route entry found\n"
-			printf "Expected:\n"
-			printf "    ${expected}\n"
-		fi
-		return 1
-	fi
-
-	# tricky way to convert output to 1-line without ip's
-	# messy '\'; this drops all extra white space
-	out=$(echo ${out})
-	if [ "${out}" != "${expected}" ]; then
-		rc=1
-		if [ "${VERBOSE}" = "1" ]; then
-			printf "    Unexpected route entry. Have:\n"
-			printf "        ${out}\n"
-			printf "    Expected:\n"
-			printf "        ${expected}\n\n"
-		fi
-	fi
-
-	return $rc
+	check_expected "${out}" "${expected}"
 }
 
 route_cleanup()
@@ -725,7 +734,7 @@ route_setup()
 	ip -netns ns2 addr add 172.16.103.2/24 dev veth4
 	ip -netns ns2 addr add 172.16.104.1/24 dev dummy1
 
-	set +ex
+	set +e
 }
 
 # assumption is that basic add of a single path route works
@@ -960,7 +969,8 @@ ipv6_addr_metric_test()
 	run_cmd "$IP li set dev dummy2 down"
 	rc=$?
 	if [ $rc -eq 0 ]; then
-		check_route6 ""
+		out=$($IP -6 ro ls match 2001:db8:104::/64)
+		check_expected "${out}" ""
 		rc=$?
 	fi
 	log_test $rc 0 "Prefix route removed on link down"
@@ -1091,38 +1101,13 @@ check_route()
 	local pfx
 	local expected="$1"
 	local out
-	local rc=0
 
 	set -- $expected
 	pfx=$1
 	[ "${pfx}" = "unreachable" ] && pfx=$2
 
 	out=$($IP ro ls match ${pfx})
-	[ "${out}" = "${expected}" ] && return 0
-
-	if [ -z "${out}" ]; then
-		if [ "$VERBOSE" = "1" ]; then
-			printf "\nNo route entry found\n"
-			printf "Expected:\n"
-			printf "    ${expected}\n"
-		fi
-		return 1
-	fi
-
-	# tricky way to convert output to 1-line without ip's
-	# messy '\'; this drops all extra white space
-	out=$(echo ${out})
-	if [ "${out}" != "${expected}" ]; then
-		rc=1
-		if [ "${VERBOSE}" = "1" ]; then
-			printf "    Unexpected route entry. Have:\n"
-			printf "        ${out}\n"
-			printf "    Expected:\n"
-			printf "        ${expected}\n\n"
-		fi
-	fi
-
-	return $rc
+	check_expected "${out}" "${expected}"
 }
 
 # assumption is that basic add of a single path route works
@@ -1387,7 +1372,8 @@ ipv4_addr_metric_test()
 	run_cmd "$IP li set dev dummy2 down"
 	rc=$?
 	if [ $rc -eq 0 ]; then
-		check_route ""
+		out=$($IP ro ls match 172.16.104.0/24)
+		check_expected "${out}" ""
 		rc=$?
 	fi
 	log_test $rc 0 "Prefix route removed on link down"
diff --git a/tools/testing/selftests/net/run_afpackettests b/tools/testing/selftests/net/run_afpackettests
index 2dc95fda7ef7..ea5938ec009a 100755
--- a/tools/testing/selftests/net/run_afpackettests
+++ b/tools/testing/selftests/net/run_afpackettests
@@ -6,12 +6,14 @@ if [ $(id -u) != 0 ]; then
 	exit 0
 fi
 
+ret=0
 echo "--------------------"
 echo "running psock_fanout test"
 echo "--------------------"
 ./in_netns.sh ./psock_fanout
 if [ $? -ne 0 ]; then
 	echo "[FAIL]"
+	ret=1
 else
 	echo "[PASS]"
 fi
@@ -22,6 +24,7 @@ echo "--------------------"
 ./in_netns.sh ./psock_tpacket
 if [ $? -ne 0 ]; then
 	echo "[FAIL]"
+	ret=1
 else
 	echo "[PASS]"
 fi
@@ -32,6 +35,8 @@ echo "--------------------"
 ./in_netns.sh ./txring_overwrite
 if [ $? -ne 0 ]; then
 	echo "[FAIL]"
+	ret=1
 else
 	echo "[PASS]"
 fi
+exit $ret
diff --git a/tools/testing/selftests/net/run_netsocktests b/tools/testing/selftests/net/run_netsocktests
index b093f39c298c..14e41faf2c57 100755
--- a/tools/testing/selftests/net/run_netsocktests
+++ b/tools/testing/selftests/net/run_netsocktests
@@ -7,7 +7,7 @@ echo "--------------------"
 ./socket
 if [ $? -ne 0 ]; then
 	echo "[FAIL]"
+	exit 1
 else
 	echo "[PASS]"
 fi
-
diff --git a/tools/testing/selftests/netfilter/Makefile b/tools/testing/selftests/netfilter/Makefile
index c9ff2b47bd1c..a37cb1192c6a 100644
--- a/tools/testing/selftests/netfilter/Makefile
+++ b/tools/testing/selftests/netfilter/Makefile
@@ -1,6 +1,6 @@
 # SPDX-License-Identifier: GPL-2.0
 # Makefile for netfilter selftests
 
-TEST_PROGS := nft_trans_stress.sh nft_nat.sh
+TEST_PROGS := nft_trans_stress.sh nft_nat.sh conntrack_icmp_related.sh
 
 include ../lib.mk
diff --git a/tools/testing/selftests/netfilter/conntrack_icmp_related.sh b/tools/testing/selftests/netfilter/conntrack_icmp_related.sh
new file mode 100755
index 000000000000..b48e1833bc89
--- /dev/null
+++ b/tools/testing/selftests/netfilter/conntrack_icmp_related.sh
@@ -0,0 +1,283 @@
+#!/bin/bash
+#
+# check that ICMP df-needed/pkttoobig icmp are set are set as related
+# state
+#
+# Setup is:
+#
+# nsclient1 -> nsrouter1 -> nsrouter2 -> nsclient2
+# MTU 1500, except for nsrouter2 <-> nsclient2 link (1280).
+# ping nsclient2 from nsclient1, checking that conntrack did set RELATED
+# 'fragmentation needed' icmp packet.
+#
+# In addition, nsrouter1 will perform IP masquerading, i.e. also
+# check the icmp errors are propagated to the correct host as per
+# nat of "established" icmp-echo "connection".
+
+# Kselftest framework requirement - SKIP code is 4.
+ksft_skip=4
+ret=0
+
+nft --version > /dev/null 2>&1
+if [ $? -ne 0 ];then
+	echo "SKIP: Could not run test without nft tool"
+	exit $ksft_skip
+fi
+
+ip -Version > /dev/null 2>&1
+if [ $? -ne 0 ];then
+	echo "SKIP: Could not run test without ip tool"
+	exit $ksft_skip
+fi
+
+cleanup() {
+	for i in 1 2;do ip netns del nsclient$i;done
+	for i in 1 2;do ip netns del nsrouter$i;done
+}
+
+ipv4() {
+    echo -n 192.168.$1.2
+}
+
+ipv6 () {
+    echo -n dead:$1::2
+}
+
+check_counter()
+{
+	ns=$1
+	name=$2
+	expect=$3
+	local lret=0
+
+	cnt=$(ip netns exec $ns nft list counter inet filter "$name" | grep -q "$expect")
+	if [ $? -ne 0 ]; then
+		echo "ERROR: counter $name in $ns has unexpected value (expected $expect)" 1>&2
+		ip netns exec $ns nft list counter inet filter "$name" 1>&2
+		lret=1
+	fi
+
+	return $lret
+}
+
+check_unknown()
+{
+	expect="packets 0 bytes 0"
+	for n in nsclient1 nsclient2 nsrouter1 nsrouter2; do
+		check_counter $n "unknown" "$expect"
+		if [ $? -ne 0 ] ;then
+			return 1
+		fi
+	done
+
+	return 0
+}
+
+for n in nsclient1 nsclient2 nsrouter1 nsrouter2; do
+  ip netns add $n
+  ip -net $n link set lo up
+done
+
+DEV=veth0
+ip link add $DEV netns nsclient1 type veth peer name eth1 netns nsrouter1
+DEV=veth0
+ip link add $DEV netns nsclient2 type veth peer name eth1 netns nsrouter2
+
+DEV=veth0
+ip link add $DEV netns nsrouter1 type veth peer name eth2 netns nsrouter2
+
+DEV=veth0
+for i in 1 2; do
+    ip -net nsclient$i link set $DEV up
+    ip -net nsclient$i addr add $(ipv4 $i)/24 dev $DEV
+    ip -net nsclient$i addr add $(ipv6 $i)/64 dev $DEV
+done
+
+ip -net nsrouter1 link set eth1 up
+ip -net nsrouter1 link set veth0 up
+
+ip -net nsrouter2 link set eth1 up
+ip -net nsrouter2 link set eth2 up
+
+ip -net nsclient1 route add default via 192.168.1.1
+ip -net nsclient1 -6 route add default via dead:1::1
+
+ip -net nsclient2 route add default via 192.168.2.1
+ip -net nsclient2 route add default via dead:2::1
+
+i=3
+ip -net nsrouter1 addr add 192.168.1.1/24 dev eth1
+ip -net nsrouter1 addr add 192.168.3.1/24 dev veth0
+ip -net nsrouter1 addr add dead:1::1/64 dev eth1
+ip -net nsrouter1 addr add dead:3::1/64 dev veth0
+ip -net nsrouter1 route add default via 192.168.3.10
+ip -net nsrouter1 -6 route add default via dead:3::10
+
+ip -net nsrouter2 addr add 192.168.2.1/24 dev eth1
+ip -net nsrouter2 addr add 192.168.3.10/24 dev eth2
+ip -net nsrouter2 addr add dead:2::1/64 dev eth1
+ip -net nsrouter2 addr add dead:3::10/64 dev eth2
+ip -net nsrouter2 route add default via 192.168.3.1
+ip -net nsrouter2 route add default via dead:3::1
+
+sleep 2
+for i in 4 6; do
+	ip netns exec nsrouter1 sysctl -q net.ipv$i.conf.all.forwarding=1
+	ip netns exec nsrouter2 sysctl -q net.ipv$i.conf.all.forwarding=1
+done
+
+for netns in nsrouter1 nsrouter2; do
+ip netns exec $netns nft -f - <<EOF
+table inet filter {
+	counter unknown { }
+	counter related { }
+	chain forward {
+		type filter hook forward priority 0; policy accept;
+		meta l4proto icmpv6 icmpv6 type "packet-too-big" ct state "related" counter name "related" accept
+		meta l4proto icmp icmp type "destination-unreachable" ct state "related" counter name "related" accept
+		meta l4proto { icmp, icmpv6 } ct state new,established accept
+		counter name "unknown" drop
+	}
+}
+EOF
+done
+
+ip netns exec nsclient1 nft -f - <<EOF
+table inet filter {
+	counter unknown { }
+	counter related { }
+	chain input {
+		type filter hook input priority 0; policy accept;
+		meta l4proto { icmp, icmpv6 } ct state established,untracked accept
+
+		meta l4proto { icmp, icmpv6 } ct state "related" counter name "related" accept
+		counter name "unknown" drop
+	}
+}
+EOF
+
+ip netns exec nsclient2 nft -f - <<EOF
+table inet filter {
+	counter unknown { }
+	counter new { }
+	counter established { }
+
+	chain input {
+		type filter hook input priority 0; policy accept;
+		meta l4proto { icmp, icmpv6 } ct state established,untracked accept
+
+		meta l4proto { icmp, icmpv6 } ct state "new" counter name "new" accept
+		meta l4proto { icmp, icmpv6 } ct state "established" counter name "established" accept
+		counter name "unknown" drop
+	}
+	chain output {
+		type filter hook output priority 0; policy accept;
+		meta l4proto { icmp, icmpv6 } ct state established,untracked accept
+
+		meta l4proto { icmp, icmpv6 } ct state "new" counter name "new"
+		meta l4proto { icmp, icmpv6 } ct state "established" counter name "established"
+		counter name "unknown" drop
+	}
+}
+EOF
+
+
+# make sure NAT core rewrites adress of icmp error if nat is used according to
+# conntrack nat information (icmp error will be directed at nsrouter1 address,
+# but it needs to be routed to nsclient1 address).
+ip netns exec nsrouter1 nft -f - <<EOF
+table ip nat {
+	chain postrouting {
+		type nat hook postrouting priority 0; policy accept;
+		ip protocol icmp oifname "veth0" counter masquerade
+	}
+}
+table ip6 nat {
+	chain postrouting {
+		type nat hook postrouting priority 0; policy accept;
+		ip6 nexthdr icmpv6 oifname "veth0" counter masquerade
+	}
+}
+EOF
+
+ip netns exec nsrouter2 ip link set eth1  mtu 1280
+ip netns exec nsclient2 ip link set veth0 mtu 1280
+sleep 1
+
+ip netns exec nsclient1 ping -c 1 -s 1000 -q -M do 192.168.2.2 >/dev/null
+if [ $? -ne 0 ]; then
+	echo "ERROR: netns ip routing/connectivity broken" 1>&2
+	cleanup
+	exit 1
+fi
+ip netns exec nsclient1 ping6 -q -c 1 -s 1000 dead:2::2 >/dev/null
+if [ $? -ne 0 ]; then
+	echo "ERROR: netns ipv6 routing/connectivity broken" 1>&2
+	cleanup
+	exit 1
+fi
+
+check_unknown
+if [ $? -ne 0 ]; then
+	ret=1
+fi
+
+expect="packets 0 bytes 0"
+for netns in nsrouter1 nsrouter2 nsclient1;do
+	check_counter "$netns" "related" "$expect"
+	if [ $? -ne 0 ]; then
+		ret=1
+	fi
+done
+
+expect="packets 2 bytes 2076"
+check_counter nsclient2 "new" "$expect"
+if [ $? -ne 0 ]; then
+	ret=1
+fi
+
+ip netns exec nsclient1 ping -q -c 1 -s 1300 -M do 192.168.2.2 > /dev/null
+if [ $? -eq 0 ]; then
+	echo "ERROR: ping should have failed with PMTU too big error" 1>&2
+	ret=1
+fi
+
+# nsrouter2 should have generated the icmp error, so
+# related counter should be 0 (its in forward).
+expect="packets 0 bytes 0"
+check_counter "nsrouter2" "related" "$expect"
+if [ $? -ne 0 ]; then
+	ret=1
+fi
+
+# but nsrouter1 should have seen it, same for nsclient1.
+expect="packets 1 bytes 576"
+for netns in nsrouter1 nsclient1;do
+	check_counter "$netns" "related" "$expect"
+	if [ $? -ne 0 ]; then
+		ret=1
+	fi
+done
+
+ip netns exec nsclient1 ping6 -c 1 -s 1300 dead:2::2 > /dev/null
+if [ $? -eq 0 ]; then
+	echo "ERROR: ping6 should have failed with PMTU too big error" 1>&2
+	ret=1
+fi
+
+expect="packets 2 bytes 1856"
+for netns in nsrouter1 nsclient1;do
+	check_counter "$netns" "related" "$expect"
+	if [ $? -ne 0 ]; then
+		ret=1
+	fi
+done
+
+if [ $ret -eq 0 ];then
+	echo "PASS: icmp mtu error had RELATED state"
+else
+	echo "ERROR: icmp error RELATED state test has failed"
+fi
+
+cleanup
+exit $ret
diff --git a/tools/testing/selftests/netfilter/nft_nat.sh b/tools/testing/selftests/netfilter/nft_nat.sh
index 8ec76681605c..3194007cf8d1 100755
--- a/tools/testing/selftests/netfilter/nft_nat.sh
+++ b/tools/testing/selftests/netfilter/nft_nat.sh
@@ -321,6 +321,7 @@ EOF
 
 test_masquerade6()
 {
+	local natflags=$1
 	local lret=0
 
 	ip netns exec ns0 sysctl net.ipv6.conf.all.forwarding=1 > /dev/null
@@ -354,13 +355,13 @@ ip netns exec ns0 nft -f - <<EOF
 table ip6 nat {
 	chain postrouting {
 		type nat hook postrouting priority 0; policy accept;
-		meta oif veth0 masquerade
+		meta oif veth0 masquerade $natflags
 	}
 }
 EOF
 	ip netns exec ns2 ping -q -c 1 dead:1::99 > /dev/null # ping ns2->ns1
 	if [ $? -ne 0 ] ; then
-		echo "ERROR: cannot ping ns1 from ns2 with active ipv6 masquerading"
+		echo "ERROR: cannot ping ns1 from ns2 with active ipv6 masquerade $natflags"
 		lret=1
 	fi
 
@@ -397,19 +398,26 @@ EOF
 		fi
 	done
 
+	ip netns exec ns2 ping -q -c 1 dead:1::99 > /dev/null # ping ns2->ns1
+	if [ $? -ne 0 ] ; then
+		echo "ERROR: cannot ping ns1 from ns2 with active ipv6 masquerade $natflags (attempt 2)"
+		lret=1
+	fi
+
 	ip netns exec ns0 nft flush chain ip6 nat postrouting
 	if [ $? -ne 0 ]; then
 		echo "ERROR: Could not flush ip6 nat postrouting" 1>&2
 		lret=1
 	fi
 
-	test $lret -eq 0 && echo "PASS: IPv6 masquerade for ns2"
+	test $lret -eq 0 && echo "PASS: IPv6 masquerade $natflags for ns2"
 
 	return $lret
 }
 
 test_masquerade()
 {
+	local natflags=$1
 	local lret=0
 
 	ip netns exec ns0 sysctl net.ipv4.conf.veth0.forwarding=1 > /dev/null
@@ -417,7 +425,7 @@ test_masquerade()
 
 	ip netns exec ns2 ping -q -c 1 10.0.1.99 > /dev/null # ping ns2->ns1
 	if [ $? -ne 0 ] ; then
-		echo "ERROR: canot ping ns1 from ns2"
+		echo "ERROR: cannot ping ns1 from ns2 $natflags"
 		lret=1
 	fi
 
@@ -443,13 +451,13 @@ ip netns exec ns0 nft -f - <<EOF
 table ip nat {
 	chain postrouting {
 		type nat hook postrouting priority 0; policy accept;
-		meta oif veth0 masquerade
+		meta oif veth0 masquerade $natflags
 	}
 }
 EOF
 	ip netns exec ns2 ping -q -c 1 10.0.1.99 > /dev/null # ping ns2->ns1
 	if [ $? -ne 0 ] ; then
-		echo "ERROR: cannot ping ns1 from ns2 with active ip masquerading"
+		echo "ERROR: cannot ping ns1 from ns2 with active ip masquere $natflags"
 		lret=1
 	fi
 
@@ -485,13 +493,19 @@ EOF
 		fi
 	done
 
+	ip netns exec ns2 ping -q -c 1 10.0.1.99 > /dev/null # ping ns2->ns1
+	if [ $? -ne 0 ] ; then
+		echo "ERROR: cannot ping ns1 from ns2 with active ip masquerade $natflags (attempt 2)"
+		lret=1
+	fi
+
 	ip netns exec ns0 nft flush chain ip nat postrouting
 	if [ $? -ne 0 ]; then
 		echo "ERROR: Could not flush nat postrouting" 1>&2
 		lret=1
 	fi
 
-	test $lret -eq 0 && echo "PASS: IP masquerade for ns2"
+	test $lret -eq 0 && echo "PASS: IP masquerade $natflags for ns2"
 
 	return $lret
 }
@@ -750,8 +764,12 @@ test_local_dnat
 test_local_dnat6
 
 reset_counters
-test_masquerade
-test_masquerade6
+test_masquerade ""
+test_masquerade6 ""
+
+reset_counters
+test_masquerade "fully-random"
+test_masquerade6 "fully-random"
 
 reset_counters
 test_redirect
diff --git a/tools/testing/selftests/proc/proc-pid-vm.c b/tools/testing/selftests/proc/proc-pid-vm.c
index 7202bbac976e..853aa164a401 100644
--- a/tools/testing/selftests/proc/proc-pid-vm.c
+++ b/tools/testing/selftests/proc/proc-pid-vm.c
@@ -187,8 +187,8 @@ static int make_exe(const uint8_t *payload, size_t len)
 	ph.p_offset = 0;
 	ph.p_vaddr = VADDR;
 	ph.p_paddr = 0;
-	ph.p_filesz = sizeof(struct elf64_hdr) + sizeof(struct elf64_phdr) + sizeof(payload);
-	ph.p_memsz = sizeof(struct elf64_hdr) + sizeof(struct elf64_phdr) + sizeof(payload);
+	ph.p_filesz = sizeof(struct elf64_hdr) + sizeof(struct elf64_phdr) + len;
+	ph.p_memsz = sizeof(struct elf64_hdr) + sizeof(struct elf64_phdr) + len;
 	ph.p_align = 4096;
 
 	fd = openat(AT_FDCWD, "/tmp", O_WRONLY|O_EXCL|O_TMPFILE, 0700);
diff --git a/tools/testing/selftests/proc/proc-self-map-files-002.c b/tools/testing/selftests/proc/proc-self-map-files-002.c
index 762cb01f2ca7..47b7473dedef 100644
--- a/tools/testing/selftests/proc/proc-self-map-files-002.c
+++ b/tools/testing/selftests/proc/proc-self-map-files-002.c
@@ -46,12 +46,9 @@ static void fail(const char *fmt, unsigned long a, unsigned long b)
 
 int main(void)
 {
-	const unsigned int PAGE_SIZE = sysconf(_SC_PAGESIZE);
-#ifdef __arm__
-	unsigned long va = 2 * PAGE_SIZE;
-#else
-	unsigned long va = 0;
-#endif
+	const int PAGE_SIZE = sysconf(_SC_PAGESIZE);
+	const unsigned long va_max = 1UL << 32;
+	unsigned long va;
 	void *p;
 	int fd;
 	unsigned long a, b;
@@ -60,10 +57,13 @@ int main(void)
 	if (fd == -1)
 		return 1;
 
-	p = mmap((void *)va, PAGE_SIZE, PROT_NONE, MAP_PRIVATE|MAP_FILE|MAP_FIXED, fd, 0);
-	if (p == MAP_FAILED) {
-		if (errno == EPERM)
-			return 4;
+	for (va = 0; va < va_max; va += PAGE_SIZE) {
+		p = mmap((void *)va, PAGE_SIZE, PROT_NONE, MAP_PRIVATE|MAP_FILE|MAP_FIXED, fd, 0);
+		if (p == (void *)va)
+			break;
+	}
+	if (va == va_max) {
+		fprintf(stderr, "error: mmap doesn't like you\n");
 		return 1;
 	}
 
diff --git a/tools/testing/selftests/rcutorture/bin/configNR_CPUS.sh b/tools/testing/selftests/rcutorture/bin/configNR_CPUS.sh
index 43540f1828cc..2deea2169fc2 100755
--- a/tools/testing/selftests/rcutorture/bin/configNR_CPUS.sh
+++ b/tools/testing/selftests/rcutorture/bin/configNR_CPUS.sh
@@ -1,4 +1,5 @@
 #!/bin/bash
+# SPDX-License-Identifier: GPL-2.0+
 #
 # Extract the number of CPUs expected from the specified Kconfig-file
 # fragment by checking CONFIG_SMP and CONFIG_NR_CPUS.  If the specified
@@ -7,23 +8,9 @@
 #
 # Usage: configNR_CPUS.sh config-frag
 #
-# This program is free software; you can redistribute it and/or modify
-# it under the terms of the GNU General Public License as published by
-# the Free Software Foundation; either version 2 of the License, or
-# (at your option) any later version.
-#
-# This program is distributed in the hope that it will be useful,
-# but WITHOUT ANY WARRANTY; without even the implied warranty of
-# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
-# GNU General Public License for more details.
-#
-# You should have received a copy of the GNU General Public License
-# along with this program; if not, you can access it online at
-# http://www.gnu.org/licenses/gpl-2.0.html.
-#
 # Copyright (C) IBM Corporation, 2013
 #
-# Authors: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
+# Authors: Paul E. McKenney <paulmck@linux.ibm.com>
 
 cf=$1
 if test ! -r $cf
diff --git a/tools/testing/selftests/rcutorture/bin/config_override.sh b/tools/testing/selftests/rcutorture/bin/config_override.sh
index ef7fcbac3d42..90016c359e83 100755
--- a/tools/testing/selftests/rcutorture/bin/config_override.sh
+++ b/tools/testing/selftests/rcutorture/bin/config_override.sh
@@ -1,4 +1,5 @@
 #!/bin/bash
+# SPDX-License-Identifier: GPL-2.0+
 #
 # config_override.sh base override
 #
@@ -6,23 +7,9 @@
 # that conflict with any in override, concatenating what remains and
 # sending the result to standard output.
 #
-# This program is free software; you can redistribute it and/or modify
-# it under the terms of the GNU General Public License as published by
-# the Free Software Foundation; either version 2 of the License, or
-# (at your option) any later version.
-#
-# This program is distributed in the hope that it will be useful,
-# but WITHOUT ANY WARRANTY; without even the implied warranty of
-# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
-# GNU General Public License for more details.
-#
-# You should have received a copy of the GNU General Public License
-# along with this program; if not, you can access it online at
-# http://www.gnu.org/licenses/gpl-2.0.html.
-#
 # Copyright (C) IBM Corporation, 2017
 #
-# Authors: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
+# Authors: Paul E. McKenney <paulmck@linux.ibm.com>
 
 base=$1
 if test -r $base
diff --git a/tools/testing/selftests/rcutorture/bin/configcheck.sh b/tools/testing/selftests/rcutorture/bin/configcheck.sh
index 197deece7c7c..31584cee84d7 100755
--- a/tools/testing/selftests/rcutorture/bin/configcheck.sh
+++ b/tools/testing/selftests/rcutorture/bin/configcheck.sh
@@ -1,23 +1,11 @@
 #!/bin/bash
-# Usage: configcheck.sh .config .config-template
-#
-# This program is free software; you can redistribute it and/or modify
-# it under the terms of the GNU General Public License as published by
-# the Free Software Foundation; either version 2 of the License, or
-# (at your option) any later version.
+# SPDX-License-Identifier: GPL-2.0+
 #
-# This program is distributed in the hope that it will be useful,
-# but WITHOUT ANY WARRANTY; without even the implied warranty of
-# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
-# GNU General Public License for more details.
-#
-# You should have received a copy of the GNU General Public License
-# along with this program; if not, you can access it online at
-# http://www.gnu.org/licenses/gpl-2.0.html.
+# Usage: configcheck.sh .config .config-template
 #
 # Copyright (C) IBM Corporation, 2011
 #
-# Authors: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
+# Authors: Paul E. McKenney <paulmck@linux.ibm.com>
 
 T=${TMPDIR-/tmp}/abat-chk-config.sh.$$
 trap 'rm -rf $T' 0
@@ -26,6 +14,7 @@ mkdir $T
 cat $1 > $T/.config
 
 cat $2 | sed -e 's/\(.*\)=n/# \1 is not set/' -e 's/^#CHECK#//' |
+grep -v '^CONFIG_INITRAMFS_SOURCE' |
 awk	'
 {
 		print "if grep -q \"" $0 "\" < '"$T/.config"'";
diff --git a/tools/testing/selftests/rcutorture/bin/configinit.sh b/tools/testing/selftests/rcutorture/bin/configinit.sh
index 65541c21a544..40359486b3a8 100755
--- a/tools/testing/selftests/rcutorture/bin/configinit.sh
+++ b/tools/testing/selftests/rcutorture/bin/configinit.sh
@@ -1,4 +1,5 @@
 #!/bin/bash
+# SPDX-License-Identifier: GPL-2.0+
 #
 # Usage: configinit.sh config-spec-file build-output-dir results-dir
 #
@@ -14,23 +15,9 @@
 # for example, "O=/tmp/foo".  If this argument is omitted, the .config
 # file will be generated directly in the current directory.
 #
-# This program is free software; you can redistribute it and/or modify
-# it under the terms of the GNU General Public License as published by
-# the Free Software Foundation; either version 2 of the License, or
-# (at your option) any later version.
-#
-# This program is distributed in the hope that it will be useful,
-# but WITHOUT ANY WARRANTY; without even the implied warranty of
-# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
-# GNU General Public License for more details.
-#
-# You should have received a copy of the GNU General Public License
-# along with this program; if not, you can access it online at
-# http://www.gnu.org/licenses/gpl-2.0.html.
-#
 # Copyright (C) IBM Corporation, 2013
 #
-# Authors: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
+# Authors: Paul E. McKenney <paulmck@linux.ibm.com>
 
 T=${TMPDIR-/tmp}/configinit.sh.$$
 trap 'rm -rf $T' 0
diff --git a/tools/testing/selftests/rcutorture/bin/cpus2use.sh b/tools/testing/selftests/rcutorture/bin/cpus2use.sh
index bb99cde3f5f9..ff7102212703 100755
--- a/tools/testing/selftests/rcutorture/bin/cpus2use.sh
+++ b/tools/testing/selftests/rcutorture/bin/cpus2use.sh
@@ -1,26 +1,13 @@
 #!/bin/bash
+# SPDX-License-Identifier: GPL-2.0+
 #
 # Get an estimate of how CPU-hoggy to be.
 #
 # Usage: cpus2use.sh
 #
-# This program is free software; you can redistribute it and/or modify
-# it under the terms of the GNU General Public License as published by
-# the Free Software Foundation; either version 2 of the License, or
-# (at your option) any later version.
-#
-# This program is distributed in the hope that it will be useful,
-# but WITHOUT ANY WARRANTY; without even the implied warranty of
-# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
-# GNU General Public License for more details.
-#
-# You should have received a copy of the GNU General Public License
-# along with this program; if not, you can access it online at
-# http://www.gnu.org/licenses/gpl-2.0.html.
-#
 # Copyright (C) IBM Corporation, 2013
 #
-# Authors: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
+# Authors: Paul E. McKenney <paulmck@linux.ibm.com>
 
 ncpus=`grep '^processor' /proc/cpuinfo | wc -l`
 idlecpus=`mpstat | tail -1 | \
diff --git a/tools/testing/selftests/rcutorture/bin/functions.sh b/tools/testing/selftests/rcutorture/bin/functions.sh
index 65f6655026f0..6bcb8b5b2ff2 100644
--- a/tools/testing/selftests/rcutorture/bin/functions.sh
+++ b/tools/testing/selftests/rcutorture/bin/functions.sh
@@ -1,24 +1,11 @@
 #!/bin/bash
+# SPDX-License-Identifier: GPL-2.0+
 #
 # Shell functions for the rest of the scripts.
 #
-# This program is free software; you can redistribute it and/or modify
-# it under the terms of the GNU General Public License as published by
-# the Free Software Foundation; either version 2 of the License, or
-# (at your option) any later version.
-#
-# This program is distributed in the hope that it will be useful,
-# but WITHOUT ANY WARRANTY; without even the implied warranty of
-# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
-# GNU General Public License for more details.
-#
-# You should have received a copy of the GNU General Public License
-# along with this program; if not, you can access it online at
-# http://www.gnu.org/licenses/gpl-2.0.html.
-#
 # Copyright (C) IBM Corporation, 2013
 #
-# Authors: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
+# Authors: Paul E. McKenney <paulmck@linux.ibm.com>
 
 # bootparam_hotplug_cpu bootparam-string
 #
diff --git a/tools/testing/selftests/rcutorture/bin/jitter.sh b/tools/testing/selftests/rcutorture/bin/jitter.sh
index 3633828375e3..435b60933985 100755
--- a/tools/testing/selftests/rcutorture/bin/jitter.sh
+++ b/tools/testing/selftests/rcutorture/bin/jitter.sh
@@ -1,4 +1,5 @@
 #!/bin/bash
+# SPDX-License-Identifier: GPL-2.0+
 #
 # Alternate sleeping and spinning on randomly selected CPUs.  The purpose
 # of this script is to inflict random OS jitter on a concurrently running
@@ -11,23 +12,9 @@
 # sleepmax: Maximum microseconds to sleep, defaults to one second.
 # spinmax: Maximum microseconds to spin, defaults to one millisecond.
 #
-# This program is free software; you can redistribute it and/or modify
-# it under the terms of the GNU General Public License as published by
-# the Free Software Foundation; either version 2 of the License, or
-# (at your option) any later version.
-#
-# This program is distributed in the hope that it will be useful,
-# but WITHOUT ANY WARRANTY; without even the implied warranty of
-# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
-# GNU General Public License for more details.
-#
-# You should have received a copy of the GNU General Public License
-# along with this program; if not, you can access it online at
-# http://www.gnu.org/licenses/gpl-2.0.html.
-#
 # Copyright (C) IBM Corporation, 2016
 #
-# Authors: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
+# Authors: Paul E. McKenney <paulmck@linux.ibm.com>
 
 me=$(($1 * 1000))
 duration=$2
diff --git a/tools/testing/selftests/rcutorture/bin/kvm-build.sh b/tools/testing/selftests/rcutorture/bin/kvm-build.sh
index 9115fcdb5617..c27a0bbb9c02 100755
--- a/tools/testing/selftests/rcutorture/bin/kvm-build.sh
+++ b/tools/testing/selftests/rcutorture/bin/kvm-build.sh
@@ -1,26 +1,13 @@
 #!/bin/bash
+# SPDX-License-Identifier: GPL-2.0+
 #
 # Build a kvm-ready Linux kernel from the tree in the current directory.
 #
 # Usage: kvm-build.sh config-template build-dir resdir
 #
-# This program is free software; you can redistribute it and/or modify
-# it under the terms of the GNU General Public License as published by
-# the Free Software Foundation; either version 2 of the License, or
-# (at your option) any later version.
-#
-# This program is distributed in the hope that it will be useful,
-# but WITHOUT ANY WARRANTY; without even the implied warranty of
-# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
-# GNU General Public License for more details.
-#
-# You should have received a copy of the GNU General Public License
-# along with this program; if not, you can access it online at
-# http://www.gnu.org/licenses/gpl-2.0.html.
-#
 # Copyright (C) IBM Corporation, 2011
 #
-# Authors: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
+# Authors: Paul E. McKenney <paulmck@linux.ibm.com>
 
 config_template=${1}
 if test -z "$config_template" -o ! -f "$config_template" -o ! -r "$config_template"
diff --git a/tools/testing/selftests/rcutorture/bin/kvm-find-errors.sh b/tools/testing/selftests/rcutorture/bin/kvm-find-errors.sh
index 98f650c9bf54..8426fe1f15ee 100755
--- a/tools/testing/selftests/rcutorture/bin/kvm-find-errors.sh
+++ b/tools/testing/selftests/rcutorture/bin/kvm-find-errors.sh
@@ -1,4 +1,5 @@
 #!/bin/sh
+# SPDX-License-Identifier: GPL-2.0+
 #
 # Invoke a text editor on all console.log files for all runs with diagnostics,
 # that is, on all such files having a console.log.diags counterpart.
@@ -10,6 +11,10 @@
 #
 # The "directory" above should end with the date/time directory, for example,
 # "tools/testing/selftests/rcutorture/res/2018.02.25-14:27:27".
+#
+# Copyright (C) IBM Corporation, 2018
+#
+# Author: Paul E. McKenney <paulmck@linux.ibm.com>
 
 rundir="${1}"
 if test -z "$rundir" -o ! -d "$rundir"
diff --git a/tools/testing/selftests/rcutorture/bin/kvm-recheck-lock.sh b/tools/testing/selftests/rcutorture/bin/kvm-recheck-lock.sh
index 2de92f43ee8c..f3a7a5e2b89d 100755
--- a/tools/testing/selftests/rcutorture/bin/kvm-recheck-lock.sh
+++ b/tools/testing/selftests/rcutorture/bin/kvm-recheck-lock.sh
@@ -1,26 +1,13 @@
 #!/bin/bash
+# SPDX-License-Identifier: GPL-2.0+
 #
 # Analyze a given results directory for locktorture progress.
 #
 # Usage: kvm-recheck-lock.sh resdir
 #
-# This program is free software; you can redistribute it and/or modify
-# it under the terms of the GNU General Public License as published by
-# the Free Software Foundation; either version 2 of the License, or
-# (at your option) any later version.
-#
-# This program is distributed in the hope that it will be useful,
-# but WITHOUT ANY WARRANTY; without even the implied warranty of
-# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
-# GNU General Public License for more details.
-#
-# You should have received a copy of the GNU General Public License
-# along with this program; if not, you can access it online at
-# http://www.gnu.org/licenses/gpl-2.0.html.
-#
 # Copyright (C) IBM Corporation, 2014
 #
-# Authors: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
+# Authors: Paul E. McKenney <paulmck@linux.ibm.com>
 
 i="$1"
 if test -d "$i" -a -r "$i"
diff --git a/tools/testing/selftests/rcutorture/bin/kvm-recheck-rcu.sh b/tools/testing/selftests/rcutorture/bin/kvm-recheck-rcu.sh
index 0fa8a61ccb7b..2a7f3f4756a7 100755
--- a/tools/testing/selftests/rcutorture/bin/kvm-recheck-rcu.sh
+++ b/tools/testing/selftests/rcutorture/bin/kvm-recheck-rcu.sh
@@ -1,26 +1,13 @@
 #!/bin/bash
+# SPDX-License-Identifier: GPL-2.0+
 #
 # Analyze a given results directory for rcutorture progress.
 #
 # Usage: kvm-recheck-rcu.sh resdir
 #
-# This program is free software; you can redistribute it and/or modify
-# it under the terms of the GNU General Public License as published by
-# the Free Software Foundation; either version 2 of the License, or
-# (at your option) any later version.
-#
-# This program is distributed in the hope that it will be useful,
-# but WITHOUT ANY WARRANTY; without even the implied warranty of
-# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
-# GNU General Public License for more details.
-#
-# You should have received a copy of the GNU General Public License
-# along with this program; if not, you can access it online at
-# http://www.gnu.org/licenses/gpl-2.0.html.
-#
 # Copyright (C) IBM Corporation, 2014
 #
-# Authors: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
+# Authors: Paul E. McKenney <paulmck@linux.ibm.com>
 
 i="$1"
 if test -d "$i" -a -r "$i"
diff --git a/tools/testing/selftests/rcutorture/bin/kvm-recheck-rcuperf-ftrace.sh b/tools/testing/selftests/rcutorture/bin/kvm-recheck-rcuperf-ftrace.sh
index 8948f7926b21..7d3c2be66c64 100755
--- a/tools/testing/selftests/rcutorture/bin/kvm-recheck-rcuperf-ftrace.sh
+++ b/tools/testing/selftests/rcutorture/bin/kvm-recheck-rcuperf-ftrace.sh
@@ -1,4 +1,5 @@
 #!/bin/bash
+# SPDX-License-Identifier: GPL-2.0+
 #
 # Analyze a given results directory for rcuperf performance measurements,
 # looking for ftrace data.  Exits with 0 if data was found, analyzed, and
@@ -7,23 +8,9 @@
 #
 # Usage: kvm-recheck-rcuperf-ftrace.sh resdir
 #
-# This program is free software; you can redistribute it and/or modify
-# it under the terms of the GNU General Public License as published by
-# the Free Software Foundation; either version 2 of the License, or
-# (at your option) any later version.
-#
-# This program is distributed in the hope that it will be useful,
-# but WITHOUT ANY WARRANTY; without even the implied warranty of
-# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
-# GNU General Public License for more details.
-#
-# You should have received a copy of the GNU General Public License
-# along with this program; if not, you can access it online at
-# http://www.gnu.org/licenses/gpl-2.0.html.
-#
 # Copyright (C) IBM Corporation, 2016
 #
-# Authors: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
+# Authors: Paul E. McKenney <paulmck@linux.ibm.com>
 
 i="$1"
 . functions.sh
diff --git a/tools/testing/selftests/rcutorture/bin/kvm-recheck-rcuperf.sh b/tools/testing/selftests/rcutorture/bin/kvm-recheck-rcuperf.sh
index ccebf772fa1e..db0375a57f28 100755
--- a/tools/testing/selftests/rcutorture/bin/kvm-recheck-rcuperf.sh
+++ b/tools/testing/selftests/rcutorture/bin/kvm-recheck-rcuperf.sh
@@ -1,26 +1,13 @@
 #!/bin/bash
+# SPDX-License-Identifier: GPL-2.0+
 #
 # Analyze a given results directory for rcuperf performance measurements.
 #
 # Usage: kvm-recheck-rcuperf.sh resdir
 #
-# This program is free software; you can redistribute it and/or modify
-# it under the terms of the GNU General Public License as published by
-# the Free Software Foundation; either version 2 of the License, or
-# (at your option) any later version.
-#
-# This program is distributed in the hope that it will be useful,
-# but WITHOUT ANY WARRANTY; without even the implied warranty of
-# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
-# GNU General Public License for more details.
-#
-# You should have received a copy of the GNU General Public License
-# along with this program; if not, you can access it online at
-# http://www.gnu.org/licenses/gpl-2.0.html.
-#
 # Copyright (C) IBM Corporation, 2016
 #
-# Authors: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
+# Authors: Paul E. McKenney <paulmck@linux.ibm.com>
 
 i="$1"
 if test -d "$i" -a -r "$i"
diff --git a/tools/testing/selftests/rcutorture/bin/kvm-recheck.sh b/tools/testing/selftests/rcutorture/bin/kvm-recheck.sh
index c9bab57a77eb..2adde6aaafdb 100755
--- a/tools/testing/selftests/rcutorture/bin/kvm-recheck.sh
+++ b/tools/testing/selftests/rcutorture/bin/kvm-recheck.sh
@@ -1,4 +1,5 @@
 #!/bin/bash
+# SPDX-License-Identifier: GPL-2.0+
 #
 # Given the results directories for previous KVM-based torture runs,
 # check the build and console output for errors.  Given a directory
@@ -6,23 +7,9 @@
 #
 # Usage: kvm-recheck.sh resdir ...
 #
-# This program is free software; you can redistribute it and/or modify
-# it under the terms of the GNU General Public License as published by
-# the Free Software Foundation; either version 2 of the License, or
-# (at your option) any later version.
-#
-# This program is distributed in the hope that it will be useful,
-# but WITHOUT ANY WARRANTY; without even the implied warranty of
-# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
-# GNU General Public License for more details.
-#
-# You should have received a copy of the GNU General Public License
-# along with this program; if not, you can access it online at
-# http://www.gnu.org/licenses/gpl-2.0.html.
-#
 # Copyright (C) IBM Corporation, 2011
 #
-# Authors: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
+# Authors: Paul E. McKenney <paulmck@linux.ibm.com>
 
 PATH=`pwd`/tools/testing/selftests/rcutorture/bin:$PATH; export PATH
 . functions.sh
diff --git a/tools/testing/selftests/rcutorture/bin/kvm-test-1-run.sh b/tools/testing/selftests/rcutorture/bin/kvm-test-1-run.sh
index 58ca758a5786..0eb1ec16d78a 100755
--- a/tools/testing/selftests/rcutorture/bin/kvm-test-1-run.sh
+++ b/tools/testing/selftests/rcutorture/bin/kvm-test-1-run.sh
@@ -1,4 +1,5 @@
 #!/bin/bash
+# SPDX-License-Identifier: GPL-2.0+
 #
 # Run a kvm-based test of the specified tree on the specified configs.
 # Fully automated run and error checking, no graphics console.
@@ -20,23 +21,9 @@
 #
 # More sophisticated argument parsing is clearly needed.
 #
-# This program is free software; you can redistribute it and/or modify
-# it under the terms of the GNU General Public License as published by
-# the Free Software Foundation; either version 2 of the License, or
-# (at your option) any later version.
-#
-# This program is distributed in the hope that it will be useful,
-# but WITHOUT ANY WARRANTY; without even the implied warranty of
-# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
-# GNU General Public License for more details.
-#
-# You should have received a copy of the GNU General Public License
-# along with this program; if not, you can access it online at
-# http://www.gnu.org/licenses/gpl-2.0.html.
-#
 # Copyright (C) IBM Corporation, 2011
 #
-# Authors: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
+# Authors: Paul E. McKenney <paulmck@linux.ibm.com>
 
 T=${TMPDIR-/tmp}/kvm-test-1-run.sh.$$
 trap 'rm -rf $T' 0
diff --git a/tools/testing/selftests/rcutorture/bin/kvm.sh b/tools/testing/selftests/rcutorture/bin/kvm.sh
index 19864f1cb27a..8f1e337b9b54 100755
--- a/tools/testing/selftests/rcutorture/bin/kvm.sh
+++ b/tools/testing/selftests/rcutorture/bin/kvm.sh
@@ -1,4 +1,5 @@
 #!/bin/bash
+# SPDX-License-Identifier: GPL-2.0+
 #
 # Run a series of tests under KVM.  By default, this series is specified
 # by the relevant CFLIST file, but can be overridden by the --configs
@@ -6,23 +7,9 @@
 #
 # Usage: kvm.sh [ options ]
 #
-# This program is free software; you can redistribute it and/or modify
-# it under the terms of the GNU General Public License as published by
-# the Free Software Foundation; either version 2 of the License, or
-# (at your option) any later version.
-#
-# This program is distributed in the hope that it will be useful,
-# but WITHOUT ANY WARRANTY; without even the implied warranty of
-# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
-# GNU General Public License for more details.
-#
-# You should have received a copy of the GNU General Public License
-# along with this program; if not, you can access it online at
-# http://www.gnu.org/licenses/gpl-2.0.html.
-#
 # Copyright (C) IBM Corporation, 2011
 #
-# Authors: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
+# Authors: Paul E. McKenney <paulmck@linux.ibm.com>
 
 scriptname=$0
 args="$*"
diff --git a/tools/testing/selftests/rcutorture/bin/mkinitrd.sh b/tools/testing/selftests/rcutorture/bin/mkinitrd.sh
index 83552bb007b4..6fa9bd1ddc09 100755
--- a/tools/testing/selftests/rcutorture/bin/mkinitrd.sh
+++ b/tools/testing/selftests/rcutorture/bin/mkinitrd.sh
@@ -1,21 +1,8 @@
 #!/bin/bash
+# SPDX-License-Identifier: GPL-2.0+
 #
 # Create an initrd directory if one does not already exist.
 #
-# This program is free software; you can redistribute it and/or modify
-# it under the terms of the GNU General Public License as published by
-# the Free Software Foundation; either version 2 of the License, or
-# (at your option) any later version.
-#
-# This program is distributed in the hope that it will be useful,
-# but WITHOUT ANY WARRANTY; without even the implied warranty of
-# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
-# GNU General Public License for more details.
-#
-# You should have received a copy of the GNU General Public License
-# along with this program; if not, you can access it online at
-# http://www.gnu.org/licenses/gpl-2.0.html.
-#
 # Copyright (C) IBM Corporation, 2013
 #
 # Author: Connor Shu <Connor.Shu@ibm.com>
diff --git a/tools/testing/selftests/rcutorture/bin/parse-build.sh b/tools/testing/selftests/rcutorture/bin/parse-build.sh
index 24fe5f822b28..0701b3bf6ade 100755
--- a/tools/testing/selftests/rcutorture/bin/parse-build.sh
+++ b/tools/testing/selftests/rcutorture/bin/parse-build.sh
@@ -1,4 +1,5 @@
 #!/bin/bash
+# SPDX-License-Identifier: GPL-2.0+
 #
 # Check the build output from an rcutorture run for goodness.
 # The "file" is a pathname on the local system, and "title" is
@@ -8,23 +9,9 @@
 #
 # Usage: parse-build.sh file title
 #
-# This program is free software; you can redistribute it and/or modify
-# it under the terms of the GNU General Public License as published by
-# the Free Software Foundation; either version 2 of the License, or
-# (at your option) any later version.
-#
-# This program is distributed in the hope that it will be useful,
-# but WITHOUT ANY WARRANTY; without even the implied warranty of
-# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
-# GNU General Public License for more details.
-#
-# You should have received a copy of the GNU General Public License
-# along with this program; if not, you can access it online at
-# http://www.gnu.org/licenses/gpl-2.0.html.
-#
 # Copyright (C) IBM Corporation, 2011
 #
-# Authors: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
+# Authors: Paul E. McKenney <paulmck@linux.ibm.com>
 
 F=$1
 title=$2
diff --git a/tools/testing/selftests/rcutorture/bin/parse-console.sh b/tools/testing/selftests/rcutorture/bin/parse-console.sh
index 84933f6aed77..4508373a922f 100755
--- a/tools/testing/selftests/rcutorture/bin/parse-console.sh
+++ b/tools/testing/selftests/rcutorture/bin/parse-console.sh
@@ -1,4 +1,5 @@
 #!/bin/bash
+# SPDX-License-Identifier: GPL-2.0+
 #
 # Check the console output from an rcutorture run for oopses.
 # The "file" is a pathname on the local system, and "title" is
@@ -6,23 +7,9 @@
 #
 # Usage: parse-console.sh file title
 #
-# This program is free software; you can redistribute it and/or modify
-# it under the terms of the GNU General Public License as published by
-# the Free Software Foundation; either version 2 of the License, or
-# (at your option) any later version.
-#
-# This program is distributed in the hope that it will be useful,
-# but WITHOUT ANY WARRANTY; without even the implied warranty of
-# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
-# GNU General Public License for more details.
-#
-# You should have received a copy of the GNU General Public License
-# along with this program; if not, you can access it online at
-# http://www.gnu.org/licenses/gpl-2.0.html.
-#
 # Copyright (C) IBM Corporation, 2011
 #
-# Authors: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
+# Authors: Paul E. McKenney <paulmck@linux.ibm.com>
 
 T=${TMPDIR-/tmp}/parse-console.sh.$$
 file="$1"
diff --git a/tools/testing/selftests/rcutorture/configs/lock/ver_functions.sh b/tools/testing/selftests/rcutorture/configs/lock/ver_functions.sh
index 80eb646e1319..d3e4b2971f92 100644
--- a/tools/testing/selftests/rcutorture/configs/lock/ver_functions.sh
+++ b/tools/testing/selftests/rcutorture/configs/lock/ver_functions.sh
@@ -1,24 +1,11 @@
 #!/bin/bash
+# SPDX-License-Identifier: GPL-2.0+
 #
 # Kernel-version-dependent shell functions for the rest of the scripts.
 #
-# This program is free software; you can redistribute it and/or modify
-# it under the terms of the GNU General Public License as published by
-# the Free Software Foundation; either version 2 of the License, or
-# (at your option) any later version.
-#
-# This program is distributed in the hope that it will be useful,
-# but WITHOUT ANY WARRANTY; without even the implied warranty of
-# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
-# GNU General Public License for more details.
-#
-# You should have received a copy of the GNU General Public License
-# along with this program; if not, you can access it online at
-# http://www.gnu.org/licenses/gpl-2.0.html.
-#
 # Copyright (C) IBM Corporation, 2014
 #
-# Authors: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
+# Authors: Paul E. McKenney <paulmck@linux.ibm.com>
 
 # locktorture_param_onoff bootparam-string config-file
 #
diff --git a/tools/testing/selftests/rcutorture/configs/rcu/ver_functions.sh b/tools/testing/selftests/rcutorture/configs/rcu/ver_functions.sh
index 7bab8246392b..effa415f9b92 100644
--- a/tools/testing/selftests/rcutorture/configs/rcu/ver_functions.sh
+++ b/tools/testing/selftests/rcutorture/configs/rcu/ver_functions.sh
@@ -1,24 +1,11 @@
 #!/bin/bash
+# SPDX-License-Identifier: GPL-2.0+
 #
 # Kernel-version-dependent shell functions for the rest of the scripts.
 #
-# This program is free software; you can redistribute it and/or modify
-# it under the terms of the GNU General Public License as published by
-# the Free Software Foundation; either version 2 of the License, or
-# (at your option) any later version.
-#
-# This program is distributed in the hope that it will be useful,
-# but WITHOUT ANY WARRANTY; without even the implied warranty of
-# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
-# GNU General Public License for more details.
-#
-# You should have received a copy of the GNU General Public License
-# along with this program; if not, you can access it online at
-# http://www.gnu.org/licenses/gpl-2.0.html.
-#
 # Copyright (C) IBM Corporation, 2013
 #
-# Authors: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
+# Authors: Paul E. McKenney <paulmck@linux.ibm.com>
 
 # rcutorture_param_n_barrier_cbs bootparam-string
 #
diff --git a/tools/testing/selftests/rcutorture/configs/rcuperf/ver_functions.sh b/tools/testing/selftests/rcutorture/configs/rcuperf/ver_functions.sh
index d36b8fd6f0fc..777d5b0c190f 100644
--- a/tools/testing/selftests/rcutorture/configs/rcuperf/ver_functions.sh
+++ b/tools/testing/selftests/rcutorture/configs/rcuperf/ver_functions.sh
@@ -1,24 +1,11 @@
 #!/bin/bash
+# SPDX-License-Identifier: GPL-2.0+
 #
 # Torture-suite-dependent shell functions for the rest of the scripts.
 #
-# This program is free software; you can redistribute it and/or modify
-# it under the terms of the GNU General Public License as published by
-# the Free Software Foundation; either version 2 of the License, or
-# (at your option) any later version.
-#
-# This program is distributed in the hope that it will be useful,
-# but WITHOUT ANY WARRANTY; without even the implied warranty of
-# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
-# GNU General Public License for more details.
-#
-# You should have received a copy of the GNU General Public License
-# along with this program; if not, you can access it online at
-# http://www.gnu.org/licenses/gpl-2.0.html.
-#
 # Copyright (C) IBM Corporation, 2015
 #
-# Authors: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
+# Authors: Paul E. McKenney <paulmck@linux.ibm.com>
 
 # per_version_boot_params bootparam-string config-file seconds
 #
diff --git a/tools/testing/selftests/rseq/rseq-s390.h b/tools/testing/selftests/rseq/rseq-s390.h
index 1069e85258ce..0afdf7957974 100644
--- a/tools/testing/selftests/rseq/rseq-s390.h
+++ b/tools/testing/selftests/rseq/rseq-s390.h
@@ -1,6 +1,13 @@
 /* SPDX-License-Identifier: LGPL-2.1 OR MIT */
 
-#define RSEQ_SIG	0x53053053
+/*
+ * RSEQ_SIG uses the trap4 instruction. As Linux does not make use of the
+ * access-register mode nor the linkage stack this instruction will always
+ * cause a special-operation exception (the trap-enabled bit in the DUCT
+ * is and will stay 0). The instruction pattern is
+ *	b2 ff 0f ff	trap4	4095(%r0)
+ */
+#define RSEQ_SIG	0xB2FF0FFF
 
 #define rseq_smp_mb()	__asm__ __volatile__ ("bcr 15,0" ::: "memory")
 #define rseq_smp_rmb()	rseq_smp_mb()
diff --git a/tools/testing/selftests/rseq/rseq.h b/tools/testing/selftests/rseq/rseq.h
index c72eb70f9b52..6c1126e7f685 100644
--- a/tools/testing/selftests/rseq/rseq.h
+++ b/tools/testing/selftests/rseq/rseq.h
@@ -16,7 +16,6 @@
 #include <errno.h>
 #include <stdio.h>
 #include <stdlib.h>
-#include <sched.h>
 #include <linux/rseq.h>
 
 /*
diff --git a/tools/testing/selftests/rseq/run_param_test.sh b/tools/testing/selftests/rseq/run_param_test.sh
index 3acd6d75ff9f..e426304fd4a0 100755
--- a/tools/testing/selftests/rseq/run_param_test.sh
+++ b/tools/testing/selftests/rseq/run_param_test.sh
@@ -1,6 +1,8 @@
 #!/bin/bash
 # SPDX-License-Identifier: GPL-2.0+ or MIT
 
+NR_CPUS=`grep '^processor' /proc/cpuinfo | wc -l`
+
 EXTRA_ARGS=${@}
 
 OLDIFS="$IFS"
@@ -28,15 +30,16 @@ IFS="$OLDIFS"
 
 REPS=1000
 SLOW_REPS=100
+NR_THREADS=$((6*${NR_CPUS}))
 
 function do_tests()
 {
 	local i=0
 	while [ "$i" -lt "${#TEST_LIST[@]}" ]; do
 		echo "Running test ${TEST_NAME[$i]}"
-		./param_test ${TEST_LIST[$i]} -r ${REPS} ${@} ${EXTRA_ARGS} || exit 1
+		./param_test ${TEST_LIST[$i]} -r ${REPS} -t ${NR_THREADS} ${@} ${EXTRA_ARGS} || exit 1
 		echo "Running compare-twice test ${TEST_NAME[$i]}"
-		./param_test_compare_twice ${TEST_LIST[$i]} -r ${REPS} ${@} ${EXTRA_ARGS} || exit 1
+		./param_test_compare_twice ${TEST_LIST[$i]} -r ${REPS} -t ${NR_THREADS} ${@} ${EXTRA_ARGS} || exit 1
 		let "i++"
 	done
 }
diff --git a/tools/testing/selftests/seccomp/seccomp_bpf.c b/tools/testing/selftests/seccomp/seccomp_bpf.c
index f69d2ee29742..0fad0dc62338 100644
--- a/tools/testing/selftests/seccomp/seccomp_bpf.c
+++ b/tools/testing/selftests/seccomp/seccomp_bpf.c
@@ -2166,11 +2166,14 @@ TEST(detect_seccomp_filter_flags)
 				 SECCOMP_FILTER_FLAG_LOG,
 				 SECCOMP_FILTER_FLAG_SPEC_ALLOW,
 				 SECCOMP_FILTER_FLAG_NEW_LISTENER };
-	unsigned int flag, all_flags;
+	unsigned int exclusive[] = {
+				SECCOMP_FILTER_FLAG_TSYNC,
+				SECCOMP_FILTER_FLAG_NEW_LISTENER };
+	unsigned int flag, all_flags, exclusive_mask;
 	int i;
 	long ret;
 
-	/* Test detection of known-good filter flags */
+	/* Test detection of individual known-good filter flags */
 	for (i = 0, all_flags = 0; i < ARRAY_SIZE(flags); i++) {
 		int bits = 0;
 
@@ -2197,16 +2200,29 @@ TEST(detect_seccomp_filter_flags)
 		all_flags |= flag;
 	}
 
-	/* Test detection of all known-good filter flags */
-	ret = seccomp(SECCOMP_SET_MODE_FILTER, all_flags, NULL);
-	EXPECT_EQ(-1, ret);
-	EXPECT_EQ(EFAULT, errno) {
-		TH_LOG("Failed to detect that all known-good filter flags (0x%X) are supported!",
-		       all_flags);
+	/*
+	 * Test detection of all known-good filter flags combined. But
+	 * for the exclusive flags we need to mask them out and try them
+	 * individually for the "all flags" testing.
+	 */
+	exclusive_mask = 0;
+	for (i = 0; i < ARRAY_SIZE(exclusive); i++)
+		exclusive_mask |= exclusive[i];
+	for (i = 0; i < ARRAY_SIZE(exclusive); i++) {
+		flag = all_flags & ~exclusive_mask;
+		flag |= exclusive[i];
+
+		ret = seccomp(SECCOMP_SET_MODE_FILTER, flag, NULL);
+		EXPECT_EQ(-1, ret);
+		EXPECT_EQ(EFAULT, errno) {
+			TH_LOG("Failed to detect that all known-good filter flags (0x%X) are supported!",
+			       flag);
+		}
 	}
 
-	/* Test detection of an unknown filter flag */
+	/* Test detection of an unknown filter flags, without exclusives. */
 	flag = -1;
+	flag &= ~exclusive_mask;
 	ret = seccomp(SECCOMP_SET_MODE_FILTER, flag, NULL);
 	EXPECT_EQ(-1, ret);
 	EXPECT_EQ(EINVAL, errno) {
@@ -3079,9 +3095,9 @@ TEST(user_notification_basic)
 
 	/* Check that we get -ENOSYS with no listener attached */
 	if (pid == 0) {
-		if (user_trap_syscall(__NR_getpid, 0) < 0)
+		if (user_trap_syscall(__NR_getppid, 0) < 0)
 			exit(1);
-		ret = syscall(__NR_getpid);
+		ret = syscall(__NR_getppid);
 		exit(ret >= 0 || errno != ENOSYS);
 	}
 
@@ -3096,12 +3112,12 @@ TEST(user_notification_basic)
 	EXPECT_EQ(seccomp(SECCOMP_SET_MODE_FILTER, 0, &prog), 0);
 
 	/* Check that the basic notification machinery works */
-	listener = user_trap_syscall(__NR_getpid,
+	listener = user_trap_syscall(__NR_getppid,
 				     SECCOMP_FILTER_FLAG_NEW_LISTENER);
 	ASSERT_GE(listener, 0);
 
 	/* Installing a second listener in the chain should EBUSY */
-	EXPECT_EQ(user_trap_syscall(__NR_getpid,
+	EXPECT_EQ(user_trap_syscall(__NR_getppid,
 				    SECCOMP_FILTER_FLAG_NEW_LISTENER),
 		  -1);
 	EXPECT_EQ(errno, EBUSY);
@@ -3110,7 +3126,7 @@ TEST(user_notification_basic)
 	ASSERT_GE(pid, 0);
 
 	if (pid == 0) {
-		ret = syscall(__NR_getpid);
+		ret = syscall(__NR_getppid);
 		exit(ret != USER_NOTIF_MAGIC);
 	}
 
@@ -3128,7 +3144,7 @@ TEST(user_notification_basic)
 	EXPECT_GT(poll(&pollfd, 1, -1), 0);
 	EXPECT_EQ(pollfd.revents, POLLOUT);
 
-	EXPECT_EQ(req.data.nr,  __NR_getpid);
+	EXPECT_EQ(req.data.nr,  __NR_getppid);
 
 	resp.id = req.id;
 	resp.error = 0;
@@ -3160,7 +3176,7 @@ TEST(user_notification_kill_in_middle)
 		TH_LOG("Kernel does not support PR_SET_NO_NEW_PRIVS!");
 	}
 
-	listener = user_trap_syscall(__NR_getpid,
+	listener = user_trap_syscall(__NR_getppid,
 				     SECCOMP_FILTER_FLAG_NEW_LISTENER);
 	ASSERT_GE(listener, 0);
 
@@ -3172,7 +3188,7 @@ TEST(user_notification_kill_in_middle)
 	ASSERT_GE(pid, 0);
 
 	if (pid == 0) {
-		ret = syscall(__NR_getpid);
+		ret = syscall(__NR_getppid);
 		exit(ret != USER_NOTIF_MAGIC);
 	}
 
@@ -3282,7 +3298,7 @@ TEST(user_notification_closed_listener)
 		TH_LOG("Kernel does not support PR_SET_NO_NEW_PRIVS!");
 	}
 
-	listener = user_trap_syscall(__NR_getpid,
+	listener = user_trap_syscall(__NR_getppid,
 				     SECCOMP_FILTER_FLAG_NEW_LISTENER);
 	ASSERT_GE(listener, 0);
 
@@ -3293,7 +3309,7 @@ TEST(user_notification_closed_listener)
 	ASSERT_GE(pid, 0);
 	if (pid == 0) {
 		close(listener);
-		ret = syscall(__NR_getpid);
+		ret = syscall(__NR_getppid);
 		exit(ret != -1 && errno != ENOSYS);
 	}
 
@@ -3316,14 +3332,15 @@ TEST(user_notification_child_pid_ns)
 
 	ASSERT_EQ(unshare(CLONE_NEWUSER | CLONE_NEWPID), 0);
 
-	listener = user_trap_syscall(__NR_getpid, SECCOMP_FILTER_FLAG_NEW_LISTENER);
+	listener = user_trap_syscall(__NR_getppid,
+				     SECCOMP_FILTER_FLAG_NEW_LISTENER);
 	ASSERT_GE(listener, 0);
 
 	pid = fork();
 	ASSERT_GE(pid, 0);
 
 	if (pid == 0)
-		exit(syscall(__NR_getpid) != USER_NOTIF_MAGIC);
+		exit(syscall(__NR_getppid) != USER_NOTIF_MAGIC);
 
 	EXPECT_EQ(ioctl(listener, SECCOMP_IOCTL_NOTIF_RECV, &req), 0);
 	EXPECT_EQ(req.pid, pid);
@@ -3355,7 +3372,8 @@ TEST(user_notification_sibling_pid_ns)
 		TH_LOG("Kernel does not support PR_SET_NO_NEW_PRIVS!");
 	}
 
-	listener = user_trap_syscall(__NR_getpid, SECCOMP_FILTER_FLAG_NEW_LISTENER);
+	listener = user_trap_syscall(__NR_getppid,
+				     SECCOMP_FILTER_FLAG_NEW_LISTENER);
 	ASSERT_GE(listener, 0);
 
 	pid = fork();
@@ -3368,7 +3386,7 @@ TEST(user_notification_sibling_pid_ns)
 		ASSERT_GE(pid2, 0);
 
 		if (pid2 == 0)
-			exit(syscall(__NR_getpid) != USER_NOTIF_MAGIC);
+			exit(syscall(__NR_getppid) != USER_NOTIF_MAGIC);
 
 		EXPECT_EQ(waitpid(pid2, &status, 0), pid2);
 		EXPECT_EQ(true, WIFEXITED(status));
@@ -3377,11 +3395,11 @@ TEST(user_notification_sibling_pid_ns)
 	}
 
 	/* Create the sibling ns, and sibling in it. */
-	EXPECT_EQ(unshare(CLONE_NEWPID), 0);
-	EXPECT_EQ(errno, 0);
+	ASSERT_EQ(unshare(CLONE_NEWPID), 0);
+	ASSERT_EQ(errno, 0);
 
 	pid2 = fork();
-	EXPECT_GE(pid2, 0);
+	ASSERT_GE(pid2, 0);
 
 	if (pid2 == 0) {
 		ASSERT_EQ(ioctl(listener, SECCOMP_IOCTL_NOTIF_RECV, &req), 0);
@@ -3389,7 +3407,7 @@ TEST(user_notification_sibling_pid_ns)
 		 * The pid should be 0, i.e. the task is in some namespace that
 		 * we can't "see".
 		 */
-		ASSERT_EQ(req.pid, 0);
+		EXPECT_EQ(req.pid, 0);
 
 		resp.id = req.id;
 		resp.error = 0;
@@ -3419,14 +3437,15 @@ TEST(user_notification_fault_recv)
 
 	ASSERT_EQ(unshare(CLONE_NEWUSER), 0);
 
-	listener = user_trap_syscall(__NR_getpid, SECCOMP_FILTER_FLAG_NEW_LISTENER);
+	listener = user_trap_syscall(__NR_getppid,
+				     SECCOMP_FILTER_FLAG_NEW_LISTENER);
 	ASSERT_GE(listener, 0);
 
 	pid = fork();
 	ASSERT_GE(pid, 0);
 
 	if (pid == 0)
-		exit(syscall(__NR_getpid) != USER_NOTIF_MAGIC);
+		exit(syscall(__NR_getppid) != USER_NOTIF_MAGIC);
 
 	/* Do a bad recv() */
 	EXPECT_EQ(ioctl(listener, SECCOMP_IOCTL_NOTIF_RECV, NULL), -1);
diff --git a/tools/testing/selftests/tc-testing/tc-tests/actions/bpf.json b/tools/testing/selftests/tc-testing/tc-tests/actions/bpf.json
index 5970cee6d05f..b074ea9b6fe8 100644
--- a/tools/testing/selftests/tc-testing/tc-tests/actions/bpf.json
+++ b/tools/testing/selftests/tc-testing/tc-tests/actions/bpf.json
@@ -286,5 +286,30 @@
         "teardown": [
             "$TC action flush action bpf"
         ]
+    },
+    {
+        "id": "b8a1",
+        "name": "Replace bpf action with invalid goto_chain control",
+        "category": [
+            "actions",
+            "bpf"
+        ],
+        "setup": [
+            [
+                "$TC actions flush action bpf",
+                0,
+                1,
+                255
+            ],
+            "$TC action add action bpf bytecode '1,6 0 0 4294967295' pass index 90"
+        ],
+        "cmdUnderTest": "$TC action replace action bpf bytecode '1,6 0 0 4294967295' goto chain 42 index 90 cookie c1a0c1a0",
+        "expExitCode": "255",
+        "verifyCmd": "$TC action list action bpf",
+        "matchPattern": "action order [0-9]*: bpf.* default-action pass.*index 90",
+        "matchCount": "1",
+        "teardown": [
+            "$TC action flush action bpf"
+        ]
     }
 ]
diff --git a/tools/testing/selftests/tc-testing/tc-tests/actions/connmark.json b/tools/testing/selftests/tc-testing/tc-tests/actions/connmark.json
index 13147a1f5731..cadde8f41fcd 100644
--- a/tools/testing/selftests/tc-testing/tc-tests/actions/connmark.json
+++ b/tools/testing/selftests/tc-testing/tc-tests/actions/connmark.json
@@ -287,5 +287,30 @@
         "teardown": [
             "$TC actions flush action connmark"
         ]
+    },
+    {
+        "id": "c506",
+        "name": "Replace connmark with invalid goto chain control",
+        "category": [
+            "actions",
+            "connmark"
+        ],
+        "setup": [
+            [
+                "$TC actions flush action connmark",
+                0,
+                1,
+                255
+            ],
+            "$TC actions add action connmark pass index 90"
+        ],
+        "cmdUnderTest": "$TC actions replace action connmark goto chain 42 index 90 cookie c1a0c1a0",
+        "expExitCode": "255",
+        "verifyCmd": "$TC actions get action connmark index 90",
+        "matchPattern": "action order [0-9]+: connmark zone 0 pass.*index 90 ref",
+        "matchCount": "1",
+        "teardown": [
+            "$TC actions flush action connmark"
+        ]
     }
 ]
diff --git a/tools/testing/selftests/tc-testing/tc-tests/actions/csum.json b/tools/testing/selftests/tc-testing/tc-tests/actions/csum.json
index a022792d392a..ddabb2fbb7c7 100644
--- a/tools/testing/selftests/tc-testing/tc-tests/actions/csum.json
+++ b/tools/testing/selftests/tc-testing/tc-tests/actions/csum.json
@@ -500,5 +500,30 @@
         "matchPattern": "^[ \t]+index [0-9]+ ref",
         "matchCount": "0",
         "teardown": []
+    },
+    {
+        "id": "d128",
+        "name": "Replace csum action with invalid goto chain control",
+        "category": [
+            "actions",
+            "csum"
+        ],
+        "setup": [
+            [
+                "$TC actions flush action csum",
+                0,
+                1,
+                255
+            ],
+            "$TC actions add action csum iph index 90"
+        ],
+        "cmdUnderTest": "$TC actions replace action csum iph goto chain 42 index 90 cookie c1a0c1a0",
+        "expExitCode": "255",
+        "verifyCmd": "$TC actions get action csum index 90",
+        "matchPattern": "action order [0-9]*: csum \\(iph\\) action pass.*index 90 ref",
+        "matchCount": "1",
+        "teardown": [
+            "$TC actions flush action csum"
+        ]
     }
 ]
diff --git a/tools/testing/selftests/tc-testing/tc-tests/actions/gact.json b/tools/testing/selftests/tc-testing/tc-tests/actions/gact.json
index 89189a03ce3d..814b7a8a478b 100644
--- a/tools/testing/selftests/tc-testing/tc-tests/actions/gact.json
+++ b/tools/testing/selftests/tc-testing/tc-tests/actions/gact.json
@@ -560,5 +560,30 @@
         "teardown": [
             "$TC actions flush action gact"
         ]
+    },
+    {
+        "id": "ca89",
+        "name": "Replace gact action with invalid goto chain control",
+        "category": [
+            "actions",
+            "gact"
+        ],
+        "setup": [
+            [
+                "$TC actions flush action gact",
+                0,
+                1,
+                255
+            ],
+            "$TC actions add action pass random determ drop 2 index 90"
+        ],
+        "cmdUnderTest": "$TC actions replace action goto chain 42 random determ drop 5 index 90 cookie c1a0c1a0",
+        "expExitCode": "255",
+        "verifyCmd": "$TC actions list action gact",
+        "matchPattern": "action order [0-9]*: gact action pass.*random type determ drop val 2.*index 90 ref",
+        "matchCount": "1",
+        "teardown": [
+            "$TC actions flush action gact"
+        ]
     }
 ]
diff --git a/tools/testing/selftests/tc-testing/tc-tests/actions/ife.json b/tools/testing/selftests/tc-testing/tc-tests/actions/ife.json
index 0da3545cabdb..c13a68b98fc7 100644
--- a/tools/testing/selftests/tc-testing/tc-tests/actions/ife.json
+++ b/tools/testing/selftests/tc-testing/tc-tests/actions/ife.json
@@ -1060,5 +1060,30 @@
         "matchPattern": "action order [0-9]*: ife encode action pipe.*allow prio.*index 4",
         "matchCount": "0",
         "teardown": []
+    },
+    {
+        "id": "a0e2",
+        "name": "Replace ife encode action with invalid goto chain control",
+        "category": [
+            "actions",
+            "ife"
+        ],
+        "setup": [
+            [
+                "$TC actions flush action ife",
+                0,
+                1,
+                255
+            ],
+            "$TC actions add action ife encode allow mark pass index 90"
+        ],
+        "cmdUnderTest": "$TC actions replace action ife encode allow mark goto chain 42 index 90 cookie c1a0c1a0",
+        "expExitCode": "255",
+        "verifyCmd": "$TC actions get action ife index 90",
+        "matchPattern": "action order [0-9]*: ife encode action pass.*type 0[xX]ED3E .*allow mark.*index 90 ref",
+        "matchCount": "1",
+        "teardown": [
+            "$TC actions flush action ife"
+        ]
     }
 ]
diff --git a/tools/testing/selftests/tc-testing/tc-tests/actions/mirred.json b/tools/testing/selftests/tc-testing/tc-tests/actions/mirred.json
index db49fd0f8445..6e5fb3d25681 100644
--- a/tools/testing/selftests/tc-testing/tc-tests/actions/mirred.json
+++ b/tools/testing/selftests/tc-testing/tc-tests/actions/mirred.json
@@ -434,5 +434,30 @@
         "teardown": [
             "$TC actions flush action mirred"
         ]
+    },
+    {
+        "id": "2a9a",
+        "name": "Replace mirred action with invalid goto chain control",
+        "category": [
+            "actions",
+            "mirred"
+        ],
+        "setup": [
+            [
+                "$TC actions flush action mirred",
+                0,
+                1,
+                255
+            ],
+            "$TC actions add action mirred ingress mirror dev lo drop index 90"
+        ],
+        "cmdUnderTest": "$TC actions replace action mirred ingress mirror dev lo goto chain 42 index 90 cookie c1a0c1a0",
+        "expExitCode": "255",
+        "verifyCmd": "$TC actions get action mirred index 90",
+        "matchPattern": "action order [0-9]*: mirred \\(Ingress Mirror to device lo\\) drop.*index 90 ref",
+        "matchCount": "1",
+        "teardown": [
+            "$TC actions flush action mirred"
+        ]
     }
 ]
diff --git a/tools/testing/selftests/tc-testing/tc-tests/actions/nat.json b/tools/testing/selftests/tc-testing/tc-tests/actions/nat.json
index 0080dc2fd41c..bc12c1ccad30 100644
--- a/tools/testing/selftests/tc-testing/tc-tests/actions/nat.json
+++ b/tools/testing/selftests/tc-testing/tc-tests/actions/nat.json
@@ -589,5 +589,30 @@
         "teardown": [
             "$TC actions flush action nat"
         ]
+    },
+    {
+        "id": "4b12",
+        "name": "Replace nat action with invalid goto chain control",
+        "category": [
+            "actions",
+            "nat"
+        ],
+        "setup": [
+            [
+                "$TC actions flush action nat",
+                0,
+                1,
+                255
+            ],
+            "$TC actions add action nat ingress 1.18.1.1 1.18.2.2 drop index 90"
+        ],
+        "cmdUnderTest": "$TC actions replace action nat ingress 1.18.1.1 1.18.2.2 goto chain 42 index 90 cookie c1a0c1a0",
+        "expExitCode": "255",
+        "verifyCmd": "$TC actions get action nat index 90",
+        "matchPattern": "action order [0-9]+:  nat ingress 1.18.1.1/32 1.18.2.2 drop.*index 90 ref",
+        "matchCount": "1",
+        "teardown": [
+            "$TC actions flush action nat"
+        ]
     }
 ]
diff --git a/tools/testing/selftests/tc-testing/tc-tests/actions/pedit.json b/tools/testing/selftests/tc-testing/tc-tests/actions/pedit.json
new file mode 100644
index 000000000000..b73ceb9e28b1
--- /dev/null
+++ b/tools/testing/selftests/tc-testing/tc-tests/actions/pedit.json
@@ -0,0 +1,51 @@
+[
+    {
+        "id": "319a",
+        "name": "Add pedit action that mangles IP TTL",
+        "category": [
+            "actions",
+            "pedit"
+        ],
+        "setup": [
+            [
+                "$TC actions flush action pedit",
+                0,
+                1,
+                255
+            ]
+        ],
+        "cmdUnderTest": "$TC actions add action pedit ex munge ip ttl set 10",
+        "expExitCode": "0",
+        "verifyCmd": "$TC actions ls action pedit",
+        "matchPattern": "action order [0-9]+:  pedit action pass keys 1.*index 1 ref.*key #0  at ipv4\\+8: val 0a000000 mask 00ffffff",
+        "matchCount": "1",
+        "teardown": [
+            "$TC actions flush action pedit"
+        ]
+    },
+    {
+        "id": "7e67",
+        "name": "Replace pedit action with invalid goto chain",
+        "category": [
+            "actions",
+            "pedit"
+        ],
+        "setup": [
+            [
+                "$TC actions flush action pedit",
+                0,
+                1,
+                255
+            ],
+            "$TC actions add action pedit ex munge ip ttl set 10 pass index 90"
+        ],
+        "cmdUnderTest": "$TC actions replace action pedit ex munge ip ttl set 10 goto chain 42 index 90 cookie c1a0c1a0",
+        "expExitCode": "255",
+        "verifyCmd": "$TC actions ls action pedit",
+        "matchPattern": "action order [0-9]+:  pedit action pass keys 1.*index 90 ref.*key #0  at ipv4\\+8: val 0a000000 mask 00ffffff",
+        "matchCount": "1",
+        "teardown": [
+            "$TC actions flush action pedit"
+        ]
+    }
+]
diff --git a/tools/testing/selftests/tc-testing/tc-tests/actions/police.json b/tools/testing/selftests/tc-testing/tc-tests/actions/police.json
index 4086a50a670e..b8268da5adaa 100644
--- a/tools/testing/selftests/tc-testing/tc-tests/actions/police.json
+++ b/tools/testing/selftests/tc-testing/tc-tests/actions/police.json
@@ -739,5 +739,30 @@
         "teardown": [
             "$TC actions flush action police"
         ]
+    },
+    {
+        "id": "689e",
+        "name": "Replace police action with invalid goto chain control",
+        "category": [
+            "actions",
+            "police"
+        ],
+        "setup": [
+            [
+                "$TC actions flush action police",
+                0,
+                1,
+                255
+            ],
+            "$TC actions add action police rate 3mbit burst 250k drop index 90"
+        ],
+        "cmdUnderTest": "$TC actions replace action police rate 3mbit burst 250k goto chain 42 index 90 cookie c1a0c1a0",
+        "expExitCode": "255",
+        "verifyCmd": "$TC actions get action police index 90",
+        "matchPattern": "action order [0-9]*:  police 0x5a rate 3Mbit burst 250Kb mtu 2Kb action drop",
+        "matchCount": "1",
+        "teardown": [
+            "$TC actions flush action police"
+        ]
     }
 ]
diff --git a/tools/testing/selftests/tc-testing/tc-tests/actions/sample.json b/tools/testing/selftests/tc-testing/tc-tests/actions/sample.json
index 3aca33c00039..ddabb160a11b 100644
--- a/tools/testing/selftests/tc-testing/tc-tests/actions/sample.json
+++ b/tools/testing/selftests/tc-testing/tc-tests/actions/sample.json
@@ -144,6 +144,30 @@
         ]
     },
     {
+        "id": "7571",
+        "name": "Add sample action with invalid rate",
+        "category": [
+            "actions",
+            "sample"
+        ],
+        "setup": [
+            [
+                "$TC actions flush action sample",
+                0,
+                1,
+                255
+            ]
+        ],
+        "cmdUnderTest": "$TC actions add action sample rate 0 group 1 index 2",
+        "expExitCode": "255",
+        "verifyCmd": "$TC actions get action sample index 2",
+        "matchPattern": "action order [0-9]+: sample rate 1/0 group 1.*index 2 ref",
+        "matchCount": "0",
+        "teardown": [
+            "$TC actions flush action sample"
+        ]
+    },
+    {
         "id": "b6d4",
         "name": "Add sample action with mandatory arguments and invalid control action",
         "category": [
@@ -584,5 +608,30 @@
         "teardown": [
             "$TC actions flush action sample"
         ]
+    },
+    {
+        "id": "0a6e",
+        "name": "Replace sample action with invalid goto chain control",
+        "category": [
+            "actions",
+            "sample"
+        ],
+        "setup": [
+            [
+                "$TC actions flush action sample",
+                0,
+                1,
+                255
+            ],
+            "$TC actions add action sample rate 1024 group 4 pass index 90"
+        ],
+        "cmdUnderTest": "$TC actions replace action sample rate 1024 group 7 goto chain 42 index 90 cookie c1a0c1a0",
+        "expExitCode": "255",
+        "verifyCmd": "$TC actions list action sample",
+        "matchPattern": "action order [0-9]+: sample rate 1/1024 group 4 pass.*index 90",
+        "matchCount": "1",
+        "teardown": [
+            "$TC actions flush action sample"
+        ]
     }
 ]
diff --git a/tools/testing/selftests/tc-testing/tc-tests/actions/simple.json b/tools/testing/selftests/tc-testing/tc-tests/actions/simple.json
index e89a7aa4012d..8e8c1ae12260 100644
--- a/tools/testing/selftests/tc-testing/tc-tests/actions/simple.json
+++ b/tools/testing/selftests/tc-testing/tc-tests/actions/simple.json
@@ -126,5 +126,30 @@
         "teardown": [
             ""
         ]
+    },
+    {
+        "id": "b776",
+        "name": "Replace simple action with invalid goto chain control",
+        "category": [
+            "actions",
+            "simple"
+        ],
+        "setup": [
+            [
+                "$TC actions flush action simple",
+                0,
+                1,
+                255
+            ],
+            "$TC actions add action simple sdata \"hello\" pass index 90"
+        ],
+        "cmdUnderTest": "$TC actions replace action simple sdata \"world\" goto chain 42 index  90 cookie c1a0c1a0",
+        "expExitCode": "255",
+        "verifyCmd": "$TC actions list action simple",
+        "matchPattern": "action order [0-9]*: Simple <hello>.*index 90 ref",
+        "matchCount": "1",
+        "teardown": [
+            "$TC actions flush action simple"
+        ]
     }
 ]
diff --git a/tools/testing/selftests/tc-testing/tc-tests/actions/skbedit.json b/tools/testing/selftests/tc-testing/tc-tests/actions/skbedit.json
index 5aaf593b914a..ecd96eda7f6a 100644
--- a/tools/testing/selftests/tc-testing/tc-tests/actions/skbedit.json
+++ b/tools/testing/selftests/tc-testing/tc-tests/actions/skbedit.json
@@ -484,5 +484,30 @@
         "teardown": [
             "$TC actions flush action skbedit"
         ]
+    },
+    {
+        "id": "1b2b",
+        "name": "Replace skbedit action with invalid goto_chain control",
+        "category": [
+            "actions",
+            "skbedit"
+        ],
+        "setup": [
+            [
+                "$TC actions flush action skbedit",
+                0,
+                1,
+                255
+            ],
+            "$TC actions add action skbedit ptype host pass index 90"
+        ],
+        "cmdUnderTest": "$TC actions replace action skbedit ptype host goto chain 42 index 90 cookie c1a0c1a0",
+        "expExitCode": "255",
+        "verifyCmd": "$TC actions list action skbedit",
+        "matchPattern": "action order [0-9]*: skbedit  ptype host pass.*index 90 ref",
+        "matchCount": "1",
+        "teardown": [
+            "$TC actions flush action skbedit"
+        ]
     }
 ]
diff --git a/tools/testing/selftests/tc-testing/tc-tests/actions/skbmod.json b/tools/testing/selftests/tc-testing/tc-tests/actions/skbmod.json
index fe3326e939c1..6eb4c4f97060 100644
--- a/tools/testing/selftests/tc-testing/tc-tests/actions/skbmod.json
+++ b/tools/testing/selftests/tc-testing/tc-tests/actions/skbmod.json
@@ -392,5 +392,30 @@
         "teardown": [
             "$TC actions flush action skbmod"
         ]
+    },
+    {
+        "id": "b651",
+        "name": "Replace skbmod action with invalid goto_chain control",
+        "category": [
+            "actions",
+            "skbmod"
+        ],
+        "setup": [
+            [
+                "$TC actions flush action skbmod",
+                0,
+                1,
+                255
+            ],
+            "$TC actions add action skbmod set etype 0x1111 pass index 90"
+        ],
+        "cmdUnderTest": "$TC actions replace action skbmod set etype 0x1111 goto chain 42 index 90 cookie c1a0c1a0",
+        "expExitCode": "255",
+        "verifyCmd": "$TC actions ls action skbmod",
+        "matchPattern": "action order [0-9]*: skbmod pass set etype 0x1111\\s+index 90 ref",
+        "matchCount": "1",
+        "teardown": [
+            "$TC actions flush action skbmod"
+        ]
     }
 ]
diff --git a/tools/testing/selftests/tc-testing/tc-tests/actions/tunnel_key.json b/tools/testing/selftests/tc-testing/tc-tests/actions/tunnel_key.json
index e7e15a7336b6..28453a445fdb 100644
--- a/tools/testing/selftests/tc-testing/tc-tests/actions/tunnel_key.json
+++ b/tools/testing/selftests/tc-testing/tc-tests/actions/tunnel_key.json
@@ -884,5 +884,30 @@
         "teardown": [
 	    "$TC actions flush action tunnel_key"
 	]
+    },
+    {
+        "id": "8242",
+        "name": "Replace tunnel_key set action with invalid goto chain",
+        "category": [
+            "actions",
+            "tunnel_key"
+        ],
+        "setup": [
+            [
+                "$TC actions flush action tunnel_key",
+                0,
+                1,
+                255
+            ],
+            "$TC actions add action tunnel_key set src_ip 10.10.10.1 dst_ip 20.20.20.2 dst_port 3128 nocsum id 1 pass index 90"
+        ],
+        "cmdUnderTest": "$TC actions replace action tunnel_key set src_ip 10.10.10.2 dst_ip 20.20.20.1 dst_port 3129 id 2 csum goto chain 42 index 90 cookie c1a0c1a0",
+        "expExitCode": "255",
+        "verifyCmd": "$TC actions get action tunnel_key index 90",
+        "matchPattern": "action order [0-9]+: tunnel_key.*set.*src_ip 10.10.10.1.*dst_ip 20.20.20.2.*key_id 1.*dst_port 3128.*csum pass.*index 90 ref",
+        "matchCount": "1",
+        "teardown": [
+            "$TC actions flush action tunnel_key"
+        ]
     }
 ]
diff --git a/tools/testing/selftests/tc-testing/tc-tests/actions/vlan.json b/tools/testing/selftests/tc-testing/tc-tests/actions/vlan.json
index 69ea09eefffc..cc7c7d758008 100644
--- a/tools/testing/selftests/tc-testing/tc-tests/actions/vlan.json
+++ b/tools/testing/selftests/tc-testing/tc-tests/actions/vlan.json
@@ -688,5 +688,30 @@
         "teardown": [
             "$TC actions flush action vlan"
         ]
+    },
+    {
+        "id": "e394",
+        "name": "Replace vlan push action with invalid goto chain control",
+        "category": [
+            "actions",
+            "vlan"
+        ],
+        "setup": [
+            [
+                "$TC actions flush action vlan",
+                0,
+                1,
+                255
+            ],
+            "$TC actions add action vlan push id 500 pass index 90"
+        ],
+        "cmdUnderTest": "$TC actions replace action vlan push id 500 goto chain 42 index 90 cookie c1a0c1a0",
+        "expExitCode": "255",
+        "verifyCmd": "$TC actions get action vlan index 90",
+        "matchPattern": "action order [0-9]+: vlan.*push id 500 protocol 802.1Q priority 0 pass.*index 90 ref",
+        "matchCount": "1",
+        "teardown": [
+            "$TC actions flush action vlan"
+        ]
     }
 ]
diff --git a/tools/testing/selftests/tc-testing/tc-tests/filters/tests.json b/tools/testing/selftests/tc-testing/tc-tests/filters/tests.json
index 99a5ffca1088..2d096b2abf2c 100644
--- a/tools/testing/selftests/tc-testing/tc-tests/filters/tests.json
+++ b/tools/testing/selftests/tc-testing/tc-tests/filters/tests.json
@@ -19,6 +19,26 @@
         ]
     },
     {
+        "id": "2638",
+        "name": "Add matchall and try to get it",
+        "category": [
+            "filter",
+            "matchall"
+        ],
+        "setup": [
+            "$TC qdisc add dev $DEV1 clsact",
+            "$TC filter add dev $DEV1 protocol all pref 1 ingress handle 0x1234 matchall action ok"
+        ],
+        "cmdUnderTest": "$TC filter get dev $DEV1 protocol all pref 1 ingress handle 0x1234 matchall",
+        "expExitCode": "0",
+        "verifyCmd": "$TC filter show dev $DEV1 ingress",
+        "matchPattern": "filter protocol all pref 1 matchall chain 0 handle 0x1234",
+        "matchCount": "1",
+        "teardown": [
+            "$TC qdisc del dev $DEV1 clsact"
+        ]
+    },
+    {
         "id": "d052",
         "name": "Add 1M filters with the same action",
         "category": [
diff --git a/tools/testing/selftests/timers/skew_consistency.c b/tools/testing/selftests/timers/skew_consistency.c
index 022b711c78ee..8066be9aff11 100644
--- a/tools/testing/selftests/timers/skew_consistency.c
+++ b/tools/testing/selftests/timers/skew_consistency.c
@@ -32,7 +32,6 @@
 #include <sys/types.h>
 #include <sys/stat.h>
 #include <fcntl.h>
-#include <stdlib.h>
 #include <string.h>
 #include <sys/wait.h>
 #include "../kselftest.h"
diff --git a/tools/testing/selftests/tpm2/tpm2.py b/tools/testing/selftests/tpm2/tpm2.py
index 40ea95ce2ead..828c18584624 100644
--- a/tools/testing/selftests/tpm2/tpm2.py
+++ b/tools/testing/selftests/tpm2/tpm2.py
@@ -22,6 +22,7 @@ TPM2_CC_UNSEAL = 0x015E
 TPM2_CC_FLUSH_CONTEXT = 0x0165
 TPM2_CC_START_AUTH_SESSION = 0x0176
 TPM2_CC_GET_CAPABILITY	= 0x017A
+TPM2_CC_GET_RANDOM = 0x017B
 TPM2_CC_PCR_READ = 0x017E
 TPM2_CC_POLICY_PCR = 0x017F
 TPM2_CC_PCR_EXTEND = 0x0182
@@ -357,9 +358,9 @@ class Client:
         self.flags = flags
 
         if (self.flags & Client.FLAG_SPACE) == 0:
-            self.tpm = open('/dev/tpm0', 'r+b')
+            self.tpm = open('/dev/tpm0', 'r+b', buffering=0)
         else:
-            self.tpm = open('/dev/tpmrm0', 'r+b')
+            self.tpm = open('/dev/tpmrm0', 'r+b', buffering=0)
 
     def close(self):
         self.tpm.close()
diff --git a/tools/testing/selftests/tpm2/tpm2_tests.py b/tools/testing/selftests/tpm2/tpm2_tests.py
index 3bb066fea4a0..d4973be53493 100644
--- a/tools/testing/selftests/tpm2/tpm2_tests.py
+++ b/tools/testing/selftests/tpm2/tpm2_tests.py
@@ -158,6 +158,69 @@ class SmokeTest(unittest.TestCase):
             pass
         self.assertEqual(rejected, True)
 
+    def test_read_partial_resp(self):
+        try:
+            fmt = '>HIIH'
+            cmd = struct.pack(fmt,
+                              tpm2.TPM2_ST_NO_SESSIONS,
+                              struct.calcsize(fmt),
+                              tpm2.TPM2_CC_GET_RANDOM,
+                              0x20)
+            self.client.tpm.write(cmd)
+            hdr = self.client.tpm.read(10)
+            sz = struct.unpack('>I', hdr[2:6])[0]
+            rsp = self.client.tpm.read()
+        except:
+            pass
+        self.assertEqual(sz, 10 + 2 + 32)
+        self.assertEqual(len(rsp), 2 + 32)
+
+    def test_read_partial_overwrite(self):
+        try:
+            fmt = '>HIIH'
+            cmd = struct.pack(fmt,
+                              tpm2.TPM2_ST_NO_SESSIONS,
+                              struct.calcsize(fmt),
+                              tpm2.TPM2_CC_GET_RANDOM,
+                              0x20)
+            self.client.tpm.write(cmd)
+            # Read part of the respone
+            rsp1 = self.client.tpm.read(15)
+
+            # Send a new cmd
+            self.client.tpm.write(cmd)
+
+            # Read the whole respone
+            rsp2 = self.client.tpm.read()
+        except:
+            pass
+        self.assertEqual(len(rsp1), 15)
+        self.assertEqual(len(rsp2), 10 + 2 + 32)
+
+    def test_send_two_cmds(self):
+        rejected = False
+        try:
+            fmt = '>HIIH'
+            cmd = struct.pack(fmt,
+                              tpm2.TPM2_ST_NO_SESSIONS,
+                              struct.calcsize(fmt),
+                              tpm2.TPM2_CC_GET_RANDOM,
+                              0x20)
+            self.client.tpm.write(cmd)
+
+            # expect the second one to raise -EBUSY error
+            self.client.tpm.write(cmd)
+            rsp = self.client.tpm.read()
+
+        except IOError, e:
+            # read the response
+            rsp = self.client.tpm.read()
+            rejected = True
+            pass
+        except:
+            pass
+        self.assertEqual(rejected, True)
+
 class SpaceTest(unittest.TestCase):
     def setUp(self):
         logging.basicConfig(filename='SpaceTest.log', level=logging.DEBUG)
diff --git a/tools/testing/selftests/x86/mpx-dig.c b/tools/testing/selftests/x86/mpx-dig.c
index c13607ef5c11..880fbf676968 100644
--- a/tools/testing/selftests/x86/mpx-dig.c
+++ b/tools/testing/selftests/x86/mpx-dig.c
@@ -8,9 +8,7 @@
 #include <unistd.h>
 #include <stdio.h>
 #include <errno.h>
-#include <sys/types.h>
 #include <sys/stat.h>
-#include <unistd.h>
 #include <sys/mman.h>
 #include <string.h>
 #include <fcntl.h>
diff --git a/virt/kvm/arm/arch_timer.c b/virt/kvm/arm/arch_timer.c
index 3417f2dbc366..7fc272ecae16 100644
--- a/virt/kvm/arm/arch_timer.c
+++ b/virt/kvm/arm/arch_timer.c
@@ -508,6 +508,14 @@ static void kvm_timer_vcpu_load_nogic(struct kvm_vcpu *vcpu)
 	struct arch_timer_context *vtimer = vcpu_vtimer(vcpu);
 
 	/*
+	 * Update the timer output so that it is likely to match the
+	 * state we're about to restore. If the timer expires between
+	 * this point and the register restoration, we'll take the
+	 * interrupt anyway.
+	 */
+	kvm_timer_update_irq(vcpu, kvm_timer_should_fire(vtimer), vtimer);
+
+	/*
 	 * When using a userspace irqchip with the architected timers and a
 	 * host interrupt controller that doesn't support an active state, we
 	 * must still prevent continuously exiting from the guest, and
@@ -730,7 +738,6 @@ static void kvm_timer_init_interrupt(void *info)
 int kvm_arm_timer_set_reg(struct kvm_vcpu *vcpu, u64 regid, u64 value)
 {
 	struct arch_timer_context *timer;
-	bool level;
 
 	switch (regid) {
 	case KVM_REG_ARM_TIMER_CTL:
@@ -758,10 +765,6 @@ int kvm_arm_timer_set_reg(struct kvm_vcpu *vcpu, u64 regid, u64 value)
 		return -1;
 	}
 
-	level = kvm_timer_should_fire(timer);
-	kvm_timer_update_irq(vcpu, level, timer);
-	timer_emulate(timer);
-
 	return 0;
 }
 
@@ -812,7 +815,7 @@ static u64 kvm_arm_timer_read(struct kvm_vcpu *vcpu,
 
 	switch (treg) {
 	case TIMER_REG_TVAL:
-		val = kvm_phys_timer_read() - timer->cntvoff - timer->cnt_cval;
+		val = timer->cnt_cval - kvm_phys_timer_read() + timer->cntvoff;
 		break;
 
 	case TIMER_REG_CTL:
@@ -858,7 +861,7 @@ static void kvm_arm_timer_write(struct kvm_vcpu *vcpu,
 {
 	switch (treg) {
 	case TIMER_REG_TVAL:
-		timer->cnt_cval = val - kvm_phys_timer_read() - timer->cntvoff;
+		timer->cnt_cval = kvm_phys_timer_read() - timer->cntvoff + val;
 		break;
 
 	case TIMER_REG_CTL:
diff --git a/virt/kvm/arm/arm.c b/virt/kvm/arm/arm.c
index 99c37384ba7b..f412ebc90610 100644
--- a/virt/kvm/arm/arm.c
+++ b/virt/kvm/arm/arm.c
@@ -934,7 +934,7 @@ int kvm_vm_ioctl_irq_line(struct kvm *kvm, struct kvm_irq_level *irq_level,
 static int kvm_vcpu_set_target(struct kvm_vcpu *vcpu,
 			       const struct kvm_vcpu_init *init)
 {
-	unsigned int i;
+	unsigned int i, ret;
 	int phys_target = kvm_target_cpu();
 
 	if (init->target != phys_target)
@@ -969,9 +969,14 @@ static int kvm_vcpu_set_target(struct kvm_vcpu *vcpu,
 	vcpu->arch.target = phys_target;
 
 	/* Now we know what it is, we can reset it. */
-	return kvm_reset_vcpu(vcpu);
-}
+	ret = kvm_reset_vcpu(vcpu);
+	if (ret) {
+		vcpu->arch.target = -1;
+		bitmap_zero(vcpu->arch.features, KVM_VCPU_MAX_FEATURES);
+	}
 
+	return ret;
+}
 
 static int kvm_arch_vcpu_ioctl_vcpu_init(struct kvm_vcpu *vcpu,
 					 struct kvm_vcpu_init *init)
diff --git a/virt/kvm/arm/hyp/vgic-v3-sr.c b/virt/kvm/arm/hyp/vgic-v3-sr.c
index 264d92da3240..370bd6c5e6cb 100644
--- a/virt/kvm/arm/hyp/vgic-v3-sr.c
+++ b/virt/kvm/arm/hyp/vgic-v3-sr.c
@@ -222,7 +222,7 @@ void __hyp_text __vgic_v3_save_state(struct kvm_vcpu *vcpu)
 		}
 	}
 
-	if (used_lrs) {
+	if (used_lrs || cpu_if->its_vpe.its_vm) {
 		int i;
 		u32 elrsr;
 
@@ -247,7 +247,7 @@ void __hyp_text __vgic_v3_restore_state(struct kvm_vcpu *vcpu)
 	u64 used_lrs = vcpu->arch.vgic_cpu.used_lrs;
 	int i;
 
-	if (used_lrs) {
+	if (used_lrs || cpu_if->its_vpe.its_vm) {
 		write_gicreg(cpu_if->vgic_hcr, ICH_HCR_EL2);
 
 		for (i = 0; i < used_lrs; i++)
diff --git a/virt/kvm/arm/mmu.c b/virt/kvm/arm/mmu.c
index ffd7acdceac7..74b6582eaa3c 100644
--- a/virt/kvm/arm/mmu.c
+++ b/virt/kvm/arm/mmu.c
@@ -102,8 +102,7 @@ static bool kvm_is_device_pfn(unsigned long pfn)
  * @addr:	IPA
  * @pmd:	pmd pointer for IPA
  *
- * Function clears a PMD entry, flushes addr 1st and 2nd stage TLBs. Marks all
- * pages in the range dirty.
+ * Function clears a PMD entry, flushes addr 1st and 2nd stage TLBs.
  */
 static void stage2_dissolve_pmd(struct kvm *kvm, phys_addr_t addr, pmd_t *pmd)
 {
@@ -121,8 +120,7 @@ static void stage2_dissolve_pmd(struct kvm *kvm, phys_addr_t addr, pmd_t *pmd)
  * @addr:	IPA
  * @pud:	pud pointer for IPA
  *
- * Function clears a PUD entry, flushes addr 1st and 2nd stage TLBs. Marks all
- * pages in the range dirty.
+ * Function clears a PUD entry, flushes addr 1st and 2nd stage TLBs.
  */
 static void stage2_dissolve_pud(struct kvm *kvm, phys_addr_t addr, pud_t *pudp)
 {
@@ -191,7 +189,7 @@ static void clear_stage2_pmd_entry(struct kvm *kvm, pmd_t *pmd, phys_addr_t addr
 	VM_BUG_ON(pmd_thp_or_huge(*pmd));
 	pmd_clear(pmd);
 	kvm_tlb_flush_vmid_ipa(kvm, addr);
-	pte_free_kernel(NULL, pte_table);
+	free_page((unsigned long)pte_table);
 	put_page(virt_to_page(pmd));
 }
 
@@ -899,9 +897,8 @@ int create_hyp_exec_mappings(phys_addr_t phys_addr, size_t size,
  * kvm_alloc_stage2_pgd - allocate level-1 table for stage-2 translation.
  * @kvm:	The KVM struct pointer for the VM.
  *
- * Allocates only the stage-2 HW PGD level table(s) (can support either full
- * 40-bit input addresses or limited to 32-bit input addresses). Clears the
- * allocated pages.
+ * Allocates only the stage-2 HW PGD level table(s) of size defined by
+ * stage2_pgd_size(kvm).
  *
  * Note we don't need locking here as this is only called when the VM is
  * created, which can only be done once.
@@ -1067,25 +1064,43 @@ static int stage2_set_pmd_huge(struct kvm *kvm, struct kvm_mmu_memory_cache
 {
 	pmd_t *pmd, old_pmd;
 
+retry:
 	pmd = stage2_get_pmd(kvm, cache, addr);
 	VM_BUG_ON(!pmd);
 
 	old_pmd = *pmd;
+	/*
+	 * Multiple vcpus faulting on the same PMD entry, can
+	 * lead to them sequentially updating the PMD with the
+	 * same value. Following the break-before-make
+	 * (pmd_clear() followed by tlb_flush()) process can
+	 * hinder forward progress due to refaults generated
+	 * on missing translations.
+	 *
+	 * Skip updating the page table if the entry is
+	 * unchanged.
+	 */
+	if (pmd_val(old_pmd) == pmd_val(*new_pmd))
+		return 0;
+
 	if (pmd_present(old_pmd)) {
 		/*
-		 * Multiple vcpus faulting on the same PMD entry, can
-		 * lead to them sequentially updating the PMD with the
-		 * same value. Following the break-before-make
-		 * (pmd_clear() followed by tlb_flush()) process can
-		 * hinder forward progress due to refaults generated
-		 * on missing translations.
+		 * If we already have PTE level mapping for this block,
+		 * we must unmap it to avoid inconsistent TLB state and
+		 * leaking the table page. We could end up in this situation
+		 * if the memory slot was marked for dirty logging and was
+		 * reverted, leaving PTE level mappings for the pages accessed
+		 * during the period. So, unmap the PTE level mapping for this
+		 * block and retry, as we could have released the upper level
+		 * table in the process.
 		 *
-		 * Skip updating the page table if the entry is
-		 * unchanged.
+		 * Normal THP split/merge follows mmu_notifier callbacks and do
+		 * get handled accordingly.
 		 */
-		if (pmd_val(old_pmd) == pmd_val(*new_pmd))
-			return 0;
-
+		if (!pmd_thp_or_huge(old_pmd)) {
+			unmap_stage2_range(kvm, addr & S2_PMD_MASK, S2_PMD_SIZE);
+			goto retry;
+		}
 		/*
 		 * Mapping in huge pages should only happen through a
 		 * fault.  If a page is merged into a transparent huge
@@ -1097,8 +1112,7 @@ static int stage2_set_pmd_huge(struct kvm *kvm, struct kvm_mmu_memory_cache
 		 * should become splitting first, unmapped, merged,
 		 * and mapped back in on-demand.
 		 */
-		VM_BUG_ON(pmd_pfn(old_pmd) != pmd_pfn(*new_pmd));
-
+		WARN_ON_ONCE(pmd_pfn(old_pmd) != pmd_pfn(*new_pmd));
 		pmd_clear(pmd);
 		kvm_tlb_flush_vmid_ipa(kvm, addr);
 	} else {
@@ -1114,6 +1128,7 @@ static int stage2_set_pud_huge(struct kvm *kvm, struct kvm_mmu_memory_cache *cac
 {
 	pud_t *pudp, old_pud;
 
+retry:
 	pudp = stage2_get_pud(kvm, cache, addr);
 	VM_BUG_ON(!pudp);
 
@@ -1121,14 +1136,23 @@ static int stage2_set_pud_huge(struct kvm *kvm, struct kvm_mmu_memory_cache *cac
 
 	/*
 	 * A large number of vcpus faulting on the same stage 2 entry,
-	 * can lead to a refault due to the
-	 * stage2_pud_clear()/tlb_flush(). Skip updating the page
-	 * tables if there is no change.
+	 * can lead to a refault due to the stage2_pud_clear()/tlb_flush().
+	 * Skip updating the page tables if there is no change.
 	 */
 	if (pud_val(old_pud) == pud_val(*new_pudp))
 		return 0;
 
 	if (stage2_pud_present(kvm, old_pud)) {
+		/*
+		 * If we already have table level mapping for this block, unmap
+		 * the range for this block and retry.
+		 */
+		if (!stage2_pud_huge(kvm, old_pud)) {
+			unmap_stage2_range(kvm, addr & S2_PUD_MASK, S2_PUD_SIZE);
+			goto retry;
+		}
+
+		WARN_ON_ONCE(kvm_pud_pfn(old_pud) != kvm_pud_pfn(*new_pudp));
 		stage2_pud_clear(kvm, pudp);
 		kvm_tlb_flush_vmid_ipa(kvm, addr);
 	} else {
@@ -1451,13 +1475,11 @@ static void stage2_wp_pmds(struct kvm *kvm, pud_t *pud,
 }
 
 /**
-  * stage2_wp_puds - write protect PGD range
-  * @pgd:	pointer to pgd entry
-  * @addr:	range start address
-  * @end:	range end address
-  *
-  * Process PUD entries, for a huge PUD we cause a panic.
-  */
+ * stage2_wp_puds - write protect PGD range
+ * @pgd:	pointer to pgd entry
+ * @addr:	range start address
+ * @end:	range end address
+ */
 static void  stage2_wp_puds(struct kvm *kvm, pgd_t *pgd,
 			    phys_addr_t addr, phys_addr_t end)
 {
@@ -1594,8 +1616,9 @@ static void kvm_send_hwpoison_signal(unsigned long address,
 	send_sig_mceerr(BUS_MCEERR_AR, (void __user *)address, lsb, current);
 }
 
-static bool fault_supports_stage2_pmd_mappings(struct kvm_memory_slot *memslot,
-					       unsigned long hva)
+static bool fault_supports_stage2_huge_mapping(struct kvm_memory_slot *memslot,
+					       unsigned long hva,
+					       unsigned long map_size)
 {
 	gpa_t gpa_start;
 	hva_t uaddr_start, uaddr_end;
@@ -1610,34 +1633,34 @@ static bool fault_supports_stage2_pmd_mappings(struct kvm_memory_slot *memslot,
 
 	/*
 	 * Pages belonging to memslots that don't have the same alignment
-	 * within a PMD for userspace and IPA cannot be mapped with stage-2
-	 * PMD entries, because we'll end up mapping the wrong pages.
+	 * within a PMD/PUD for userspace and IPA cannot be mapped with stage-2
+	 * PMD/PUD entries, because we'll end up mapping the wrong pages.
 	 *
 	 * Consider a layout like the following:
 	 *
 	 *    memslot->userspace_addr:
 	 *    +-----+--------------------+--------------------+---+
-	 *    |abcde|fgh  Stage-1 PMD    |    Stage-1 PMD   tv|xyz|
+	 *    |abcde|fgh  Stage-1 block  |    Stage-1 block tv|xyz|
 	 *    +-----+--------------------+--------------------+---+
 	 *
 	 *    memslot->base_gfn << PAGE_SIZE:
 	 *      +---+--------------------+--------------------+-----+
-	 *      |abc|def  Stage-2 PMD    |    Stage-2 PMD     |tvxyz|
+	 *      |abc|def  Stage-2 block  |    Stage-2 block   |tvxyz|
 	 *      +---+--------------------+--------------------+-----+
 	 *
-	 * If we create those stage-2 PMDs, we'll end up with this incorrect
+	 * If we create those stage-2 blocks, we'll end up with this incorrect
 	 * mapping:
 	 *   d -> f
 	 *   e -> g
 	 *   f -> h
 	 */
-	if ((gpa_start & ~S2_PMD_MASK) != (uaddr_start & ~S2_PMD_MASK))
+	if ((gpa_start & (map_size - 1)) != (uaddr_start & (map_size - 1)))
 		return false;
 
 	/*
 	 * Next, let's make sure we're not trying to map anything not covered
-	 * by the memslot. This means we have to prohibit PMD size mappings
-	 * for the beginning and end of a non-PMD aligned and non-PMD sized
+	 * by the memslot. This means we have to prohibit block size mappings
+	 * for the beginning and end of a non-block aligned and non-block sized
 	 * memory slot (illustrated by the head and tail parts of the
 	 * userspace view above containing pages 'abcde' and 'xyz',
 	 * respectively).
@@ -1646,8 +1669,8 @@ static bool fault_supports_stage2_pmd_mappings(struct kvm_memory_slot *memslot,
 	 * userspace_addr or the base_gfn, as both are equally aligned (per
 	 * the check above) and equally sized.
 	 */
-	return (hva & S2_PMD_MASK) >= uaddr_start &&
-	       (hva & S2_PMD_MASK) + S2_PMD_SIZE <= uaddr_end;
+	return (hva & ~(map_size - 1)) >= uaddr_start &&
+	       (hva & ~(map_size - 1)) + map_size <= uaddr_end;
 }
 
 static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa,
@@ -1676,12 +1699,6 @@ static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa,
 		return -EFAULT;
 	}
 
-	if (!fault_supports_stage2_pmd_mappings(memslot, hva))
-		force_pte = true;
-
-	if (logging_active)
-		force_pte = true;
-
 	/* Let's check if we will get back a huge page backed by hugetlbfs */
 	down_read(&current->mm->mmap_sem);
 	vma = find_vma_intersection(current->mm, hva, hva + 1);
@@ -1692,6 +1709,12 @@ static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa,
 	}
 
 	vma_pagesize = vma_kernel_pagesize(vma);
+	if (logging_active ||
+	    !fault_supports_stage2_huge_mapping(memslot, hva, vma_pagesize)) {
+		force_pte = true;
+		vma_pagesize = PAGE_SIZE;
+	}
+
 	/*
 	 * The stage2 has a minimum of 2 level table (For arm64 see
 	 * kvm_arm_setup_stage2()). Hence, we are guaranteed that we can
@@ -1699,11 +1722,9 @@ static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa,
 	 * As for PUD huge maps, we must make sure that we have at least
 	 * 3 levels, i.e, PMD is not folded.
 	 */
-	if ((vma_pagesize == PMD_SIZE ||
-	     (vma_pagesize == PUD_SIZE && kvm_stage2_has_pmd(kvm))) &&
-	    !force_pte) {
+	if (vma_pagesize == PMD_SIZE ||
+	    (vma_pagesize == PUD_SIZE && kvm_stage2_has_pmd(kvm)))
 		gfn = (fault_ipa & huge_page_mask(hstate_vma(vma))) >> PAGE_SHIFT;
-	}
 	up_read(&current->mm->mmap_sem);
 
 	/* We need minimum second+third level pages */
@@ -1760,8 +1781,12 @@ static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa,
 		 * Only PMD_SIZE transparent hugepages(THP) are
 		 * currently supported. This code will need to be
 		 * updated to support other THP sizes.
+		 *
+		 * Make sure the host VA and the guest IPA are sufficiently
+		 * aligned and that the block is contained within the memslot.
 		 */
-		if (transparent_hugepage_adjust(&pfn, &fault_ipa))
+		if (fault_supports_stage2_huge_mapping(memslot, hva, PMD_SIZE) &&
+		    transparent_hugepage_adjust(&pfn, &fault_ipa))
 			vma_pagesize = PMD_SIZE;
 	}
 
diff --git a/virt/kvm/arm/vgic/vgic-its.c b/virt/kvm/arm/vgic/vgic-its.c
index ab3f47745d9c..44ceaccb18cf 100644
--- a/virt/kvm/arm/vgic/vgic-its.c
+++ b/virt/kvm/arm/vgic/vgic-its.c
@@ -754,8 +754,9 @@ static bool vgic_its_check_id(struct vgic_its *its, u64 baser, u32 id,
 	u64 indirect_ptr, type = GITS_BASER_TYPE(baser);
 	phys_addr_t base = GITS_BASER_ADDR_48_to_52(baser);
 	int esz = GITS_BASER_ENTRY_SIZE(baser);
-	int index;
+	int index, idx;
 	gfn_t gfn;
+	bool ret;
 
 	switch (type) {
 	case GITS_BASER_TYPE_DEVICE:
@@ -782,7 +783,8 @@ static bool vgic_its_check_id(struct vgic_its *its, u64 baser, u32 id,
 
 		if (eaddr)
 			*eaddr = addr;
-		return kvm_is_visible_gfn(its->dev->kvm, gfn);
+
+		goto out;
 	}
 
 	/* calculate and check the index into the 1st level */
@@ -812,7 +814,12 @@ static bool vgic_its_check_id(struct vgic_its *its, u64 baser, u32 id,
 
 	if (eaddr)
 		*eaddr = indirect_ptr;
-	return kvm_is_visible_gfn(its->dev->kvm, gfn);
+
+out:
+	idx = srcu_read_lock(&its->dev->kvm->srcu);
+	ret = kvm_is_visible_gfn(its->dev->kvm, gfn);
+	srcu_read_unlock(&its->dev->kvm->srcu, idx);
+	return ret;
 }
 
 static int vgic_its_alloc_collection(struct vgic_its *its,
@@ -1729,8 +1736,8 @@ static void vgic_its_destroy(struct kvm_device *kvm_dev)
 	kfree(its);
 }
 
-int vgic_its_has_attr_regs(struct kvm_device *dev,
-			   struct kvm_device_attr *attr)
+static int vgic_its_has_attr_regs(struct kvm_device *dev,
+				  struct kvm_device_attr *attr)
 {
 	const struct vgic_register_region *region;
 	gpa_t offset = attr->attr;
@@ -1750,9 +1757,9 @@ int vgic_its_has_attr_regs(struct kvm_device *dev,
 	return 0;
 }
 
-int vgic_its_attr_regs_access(struct kvm_device *dev,
-			      struct kvm_device_attr *attr,
-			      u64 *reg, bool is_write)
+static int vgic_its_attr_regs_access(struct kvm_device *dev,
+				     struct kvm_device_attr *attr,
+				     u64 *reg, bool is_write)
 {
 	const struct vgic_register_region *region;
 	struct vgic_its *its;
@@ -1919,7 +1926,7 @@ static int vgic_its_save_ite(struct vgic_its *its, struct its_device *dev,
 	       ((u64)ite->irq->intid << KVM_ITS_ITE_PINTID_SHIFT) |
 		ite->collection->collection_id;
 	val = cpu_to_le64(val);
-	return kvm_write_guest(kvm, gpa, &val, ite_esz);
+	return kvm_write_guest_lock(kvm, gpa, &val, ite_esz);
 }
 
 /**
@@ -2066,7 +2073,7 @@ static int vgic_its_save_dte(struct vgic_its *its, struct its_device *dev,
 	       (itt_addr_field << KVM_ITS_DTE_ITTADDR_SHIFT) |
 		(dev->num_eventid_bits - 1));
 	val = cpu_to_le64(val);
-	return kvm_write_guest(kvm, ptr, &val, dte_esz);
+	return kvm_write_guest_lock(kvm, ptr, &val, dte_esz);
 }
 
 /**
@@ -2246,7 +2253,7 @@ static int vgic_its_save_cte(struct vgic_its *its,
 	       ((u64)collection->target_addr << KVM_ITS_CTE_RDBASE_SHIFT) |
 	       collection->collection_id);
 	val = cpu_to_le64(val);
-	return kvm_write_guest(its->dev->kvm, gpa, &val, esz);
+	return kvm_write_guest_lock(its->dev->kvm, gpa, &val, esz);
 }
 
 static int vgic_its_restore_cte(struct vgic_its *its, gpa_t gpa, int esz)
@@ -2317,7 +2324,7 @@ static int vgic_its_save_collection_table(struct vgic_its *its)
 	 */
 	val = 0;
 	BUG_ON(cte_esz > sizeof(val));
-	ret = kvm_write_guest(its->dev->kvm, gpa, &val, cte_esz);
+	ret = kvm_write_guest_lock(its->dev->kvm, gpa, &val, cte_esz);
 	return ret;
 }
 
diff --git a/virt/kvm/arm/vgic/vgic-mmio-v3.c b/virt/kvm/arm/vgic/vgic-mmio-v3.c
index 4a12322bf7df..9f4843fe9cda 100644
--- a/virt/kvm/arm/vgic/vgic-mmio-v3.c
+++ b/virt/kvm/arm/vgic/vgic-mmio-v3.c
@@ -200,6 +200,9 @@ static void vgic_mmio_write_v3r_ctlr(struct kvm_vcpu *vcpu,
 
 	vgic_cpu->lpis_enabled = val & GICR_CTLR_ENABLE_LPIS;
 
+	if (was_enabled && !vgic_cpu->lpis_enabled)
+		vgic_flush_pending_lpis(vcpu);
+
 	if (!was_enabled && vgic_cpu->lpis_enabled)
 		vgic_enable_lpis(vcpu);
 }
diff --git a/virt/kvm/arm/vgic/vgic-v3.c b/virt/kvm/arm/vgic/vgic-v3.c
index 408a78eb6a97..9f87e58dbd4a 100644
--- a/virt/kvm/arm/vgic/vgic-v3.c
+++ b/virt/kvm/arm/vgic/vgic-v3.c
@@ -358,7 +358,7 @@ retry:
 	if (status) {
 		/* clear consumed data */
 		val &= ~(1 << bit_nr);
-		ret = kvm_write_guest(kvm, ptr, &val, 1);
+		ret = kvm_write_guest_lock(kvm, ptr, &val, 1);
 		if (ret)
 			return ret;
 	}
@@ -409,7 +409,7 @@ int vgic_v3_save_pending_tables(struct kvm *kvm)
 		else
 			val &= ~(1 << bit_nr);
 
-		ret = kvm_write_guest(kvm, ptr, &val, 1);
+		ret = kvm_write_guest_lock(kvm, ptr, &val, 1);
 		if (ret)
 			return ret;
 	}
diff --git a/virt/kvm/arm/vgic/vgic.c b/virt/kvm/arm/vgic/vgic.c
index abd9c7352677..191deccf60bf 100644
--- a/virt/kvm/arm/vgic/vgic.c
+++ b/virt/kvm/arm/vgic/vgic.c
@@ -151,6 +151,27 @@ void vgic_put_irq(struct kvm *kvm, struct vgic_irq *irq)
 	kfree(irq);
 }
 
+void vgic_flush_pending_lpis(struct kvm_vcpu *vcpu)
+{
+	struct vgic_cpu *vgic_cpu = &vcpu->arch.vgic_cpu;
+	struct vgic_irq *irq, *tmp;
+	unsigned long flags;
+
+	raw_spin_lock_irqsave(&vgic_cpu->ap_list_lock, flags);
+
+	list_for_each_entry_safe(irq, tmp, &vgic_cpu->ap_list_head, ap_list) {
+		if (irq->intid >= VGIC_MIN_LPI) {
+			raw_spin_lock(&irq->irq_lock);
+			list_del(&irq->ap_list);
+			irq->vcpu = NULL;
+			raw_spin_unlock(&irq->irq_lock);
+			vgic_put_irq(vcpu->kvm, irq);
+		}
+	}
+
+	raw_spin_unlock_irqrestore(&vgic_cpu->ap_list_lock, flags);
+}
+
 void vgic_irq_set_phys_pending(struct vgic_irq *irq, bool pending)
 {
 	WARN_ON(irq_set_irqchip_state(irq->host_irq,
@@ -867,15 +888,21 @@ void kvm_vgic_flush_hwstate(struct kvm_vcpu *vcpu)
 	 * either observe the new interrupt before or after doing this check,
 	 * and introducing additional synchronization mechanism doesn't change
 	 * this.
+	 *
+	 * Note that we still need to go through the whole thing if anything
+	 * can be directly injected (GICv4).
 	 */
-	if (list_empty(&vcpu->arch.vgic_cpu.ap_list_head))
+	if (list_empty(&vcpu->arch.vgic_cpu.ap_list_head) &&
+	    !vgic_supports_direct_msis(vcpu->kvm))
 		return;
 
 	DEBUG_SPINLOCK_BUG_ON(!irqs_disabled());
 
-	raw_spin_lock(&vcpu->arch.vgic_cpu.ap_list_lock);
-	vgic_flush_lr_state(vcpu);
-	raw_spin_unlock(&vcpu->arch.vgic_cpu.ap_list_lock);
+	if (!list_empty(&vcpu->arch.vgic_cpu.ap_list_head)) {
+		raw_spin_lock(&vcpu->arch.vgic_cpu.ap_list_lock);
+		vgic_flush_lr_state(vcpu);
+		raw_spin_unlock(&vcpu->arch.vgic_cpu.ap_list_lock);
+	}
 
 	if (can_access_vgic_from_kernel())
 		vgic_restore_state(vcpu);
diff --git a/virt/kvm/arm/vgic/vgic.h b/virt/kvm/arm/vgic/vgic.h
index a90024718ca4..abeeffabc456 100644
--- a/virt/kvm/arm/vgic/vgic.h
+++ b/virt/kvm/arm/vgic/vgic.h
@@ -238,6 +238,7 @@ void vgic_v3_put(struct kvm_vcpu *vcpu);
 bool vgic_has_its(struct kvm *kvm);
 int kvm_vgic_register_its_device(void);
 void vgic_enable_lpis(struct kvm_vcpu *vcpu);
+void vgic_flush_pending_lpis(struct kvm_vcpu *vcpu);
 int vgic_its_inject_msi(struct kvm *kvm, struct kvm_msi *msi);
 int vgic_v3_has_attr_regs(struct kvm_device *dev, struct kvm_device_attr *attr);
 int vgic_v3_dist_uaccess(struct kvm_vcpu *vcpu, bool is_write,
diff --git a/virt/kvm/eventfd.c b/virt/kvm/eventfd.c
index 4325250afd72..001aeda4c154 100644
--- a/virt/kvm/eventfd.c
+++ b/virt/kvm/eventfd.c
@@ -214,9 +214,9 @@ irqfd_wakeup(wait_queue_entry_t *wait, unsigned mode, int sync, void *key)
 
 	if (flags & EPOLLHUP) {
 		/* The eventfd is closing, detach from KVM */
-		unsigned long flags;
+		unsigned long iflags;
 
-		spin_lock_irqsave(&kvm->irqfds.lock, flags);
+		spin_lock_irqsave(&kvm->irqfds.lock, iflags);
 
 		/*
 		 * We must check if someone deactivated the irqfd before
@@ -230,7 +230,7 @@ irqfd_wakeup(wait_queue_entry_t *wait, unsigned mode, int sync, void *key)
 		if (irqfd_is_active(irqfd))
 			irqfd_deactivate(irqfd);
 
-		spin_unlock_irqrestore(&kvm->irqfds.lock, flags);
+		spin_unlock_irqrestore(&kvm->irqfds.lock, iflags);
 	}
 
 	return 0;
diff --git a/virt/kvm/irqchip.c b/virt/kvm/irqchip.c
index 3547b0d8c91e..79e59e4fa3dc 100644
--- a/virt/kvm/irqchip.c
+++ b/virt/kvm/irqchip.c
@@ -144,18 +144,19 @@ static int setup_routing_entry(struct kvm *kvm,
 {
 	struct kvm_kernel_irq_routing_entry *ei;
 	int r;
+	u32 gsi = array_index_nospec(ue->gsi, KVM_MAX_IRQ_ROUTES);
 
 	/*
 	 * Do not allow GSI to be mapped to the same irqchip more than once.
 	 * Allow only one to one mapping between GSI and non-irqchip routing.
 	 */
-	hlist_for_each_entry(ei, &rt->map[ue->gsi], link)
+	hlist_for_each_entry(ei, &rt->map[gsi], link)
 		if (ei->type != KVM_IRQ_ROUTING_IRQCHIP ||
 		    ue->type != KVM_IRQ_ROUTING_IRQCHIP ||
 		    ue->u.irqchip.irqchip == ei->irqchip.irqchip)
 			return -EINVAL;
 
-	e->gsi = ue->gsi;
+	e->gsi = gsi;
 	e->type = ue->type;
 	r = kvm_set_routing_entry(kvm, e, ue);
 	if (r)
diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c
index f25aa98a94df..a704d1f9bd96 100644
--- a/virt/kvm/kvm_main.c
+++ b/virt/kvm/kvm_main.c
@@ -1240,7 +1240,7 @@ int kvm_clear_dirty_log_protect(struct kvm *kvm,
 	if (as_id >= KVM_ADDRESS_SPACE_NUM || id >= KVM_USER_MEM_SLOTS)
 		return -EINVAL;
 
-	if ((log->first_page & 63) || (log->num_pages & 63))
+	if (log->first_page & 63)
 		return -EINVAL;
 
 	slots = __kvm_memslots(kvm, as_id);
@@ -1253,8 +1253,9 @@ int kvm_clear_dirty_log_protect(struct kvm *kvm,
 	n = kvm_dirty_bitmap_bytes(memslot);
 
 	if (log->first_page > memslot->npages ||
-	    log->num_pages > memslot->npages - log->first_page)
-			return -EINVAL;
+	    log->num_pages > memslot->npages - log->first_page ||
+	    (log->num_pages < memslot->npages - log->first_page && (log->num_pages & 63)))
+	    return -EINVAL;
 
 	*flush = false;
 	dirty_bitmap_buffer = kvm_second_dirty_bitmap(memslot);
@@ -2905,6 +2906,9 @@ static long kvm_device_ioctl(struct file *filp, unsigned int ioctl,
 {
 	struct kvm_device *dev = filp->private_data;
 
+	if (dev->kvm->mm != current->mm)
+		return -EIO;
+
 	switch (ioctl) {
 	case KVM_SET_DEVICE_ATTR:
 		return kvm_device_ioctl_attr(dev, dev->ops->set_attr, arg);
@@ -2974,12 +2978,14 @@ static int kvm_ioctl_create_device(struct kvm *kvm,
 	struct kvm_device_ops *ops = NULL;
 	struct kvm_device *dev;
 	bool test = cd->flags & KVM_CREATE_DEVICE_TEST;
+	int type;
 	int ret;
 
 	if (cd->type >= ARRAY_SIZE(kvm_device_ops_table))
 		return -ENODEV;
 
-	ops = kvm_device_ops_table[cd->type];
+	type = array_index_nospec(cd->type, ARRAY_SIZE(kvm_device_ops_table));
+	ops = kvm_device_ops_table[type];
 	if (ops == NULL)
 		return -ENODEV;
 
@@ -2994,7 +3000,7 @@ static int kvm_ioctl_create_device(struct kvm *kvm,
 	dev->kvm = kvm;
 
 	mutex_lock(&kvm->lock);
-	ret = ops->create(dev, cd->type);
+	ret = ops->create(dev, type);
 	if (ret < 0) {
 		mutex_unlock(&kvm->lock);
 		kfree(dev);